net: bcmsysport: use __napi_schedule_irqoff()

Both bcm_sysport_tx_isr() and bcm_sysport_rx_isr() run in hard irq context, we do not need to block irq again. Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
author: Florian Fainelli 2016-04-20 20:37:08 +0200
committer: David S. Miller 2016-04-21 21:06:04 +0200
commit: ba90950c94713f294e8778e891eef4143183957c (patch)
tree: e8136c9d614d94326476d04070b831c79344821a
parent: Merge branch 'nlattr_align' (diff)
download: kernel-qcow2-linux-ba90950c94713f294e8778e891eef4143183957c.tar.gz
kernel-qcow2-linux-ba90950c94713f294e8778e891eef4143183957c.tar.xz
kernel-qcow2-linux-ba90950c94713f294e8778e891eef4143183957c.zip
1 files changed, 2 insertions, 2 deletions
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 993c780bdfab..9e3ec739d860 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -873,7 +873,7 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id)
 		if (likely(napi_schedule_prep(&priv->napi))) {
 			/* disable RX interrupts */
 			intrl2_0_mask_set(priv, INTRL2_0_RDMA_MBDONE);
-			__napi_schedule(&priv->napi);
+			__napi_schedule_irqoff(&priv->napi);
 		}
 	}
 
@@ -916,7 +916,7 @@ static irqreturn_t bcm_sysport_tx_isr(int irq, void *dev_id)
 
 		if (likely(napi_schedule_prep(&txr->napi))) {
 			intrl2_1_mask_set(priv, BIT(ring));
-			__napi_schedule(&txr->napi);
+			__napi_schedule_irqoff(&txr->napi);
 		}
 	}
 
diff --git a/.gitignore b/.gitignore
index f6050b88e95b..705e09913dc2 100644
--- a/.gitignore
+++ b/.gitignore
@@ -66,6 +66,11 @@ modules.builtin
 /debian/
 
 #
+# Snap directory (make snap-pkg)
+#
+/snap/
+
+#
 # tar directory (make tar*-pkg)
 #
 /tar-install/
diff --git a/.mailmap b/.mailmap
index 1469ff0d3f4d..e18cab73e209 100644
--- a/.mailmap
+++ b/.mailmap
@@ -107,6 +107,7 @@ Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
 Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
 Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com>
 Mark Brown <broonie@sirena.org.uk>
+Mark Yao <markyao0591@gmail.com> <mark.yao@rock-chips.com>
 Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com>
 Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com>
 Matthieu CASTET <castet.matthieu@free.fr>
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 3bec49c33bbb..7f3a0728ccf2 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -228,8 +228,6 @@ isdn/
 	- directory with info on the Linux ISDN support, and supported cards.
 kbuild/
 	- directory with info about the kernel build process.
-kernel-doc-nano-HOWTO.txt
-	- outdated info about kernel-doc documentation.
 kdump/
 	- directory with mini HowTo on getting the crash dump code to work.
 doc-guide/
@@ -346,8 +344,6 @@ prctl/
 	- directory with info on the priveledge control subsystem
 preempt-locking.txt
 	- info on locking under a preemptive kernel.
-printk-formats.txt
-	- how to get printk format specifiers right
 process/
 	- how to work with the mainline kernel development process.
 pps/
diff --git a/Documentation/ABI/stable/sysfs-bus-vmbus b/Documentation/ABI/stable/sysfs-bus-vmbus
index d4077cc60d55..e46be65d0e1d 100644
--- a/Documentation/ABI/stable/sysfs-bus-vmbus
+++ b/Documentation/ABI/stable/sysfs-bus-vmbus
@@ -42,72 +42,93 @@ Contact:	K. Y. Srinivasan <kys@microsoft.com>
 Description:	The 16 bit vendor ID of the device
 Users:		tools/hv/lsvmbus and user level RDMA libraries
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/relid/cpu
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN
+Date:		September. 2017
+KernelVersion:	4.14
+Contact:	Stephen Hemminger <sthemmin@microsoft.com>
+Description:	Directory for per-channel information
+		NN is the VMBUS relid associtated with the channel.
+
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/cpu
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	VCPU (sub)channel is affinitized to
-Users:		tools/hv/lsvmbus and other debuggig tools
+Users:		tools/hv/lsvmbus and other debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/relid/cpu
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/cpu
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	VCPU (sub)channel is affinitized to
-Users:		tools/hv/lsvmbus and other debuggig tools
+Users:		tools/hv/lsvmbus and other debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/relid/in_mask
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/in_mask
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
-Description:	Inbound channel signaling state
+Description:	Host to guest channel interrupt mask
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/relid/latency
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/latency
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Channel signaling latency
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/relid/out_mask
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/out_mask
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
-Description:	Outbound channel signaling state
+Description:	Guest to host channel interrupt mask
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/relid/pending
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/pending
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Channel interrupt pending state
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/relid/read_avail
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/read_avail
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
-Description:	Bytes availabble to read
+Description:	Bytes available to read
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/relid/write_avail
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/write_avail
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
-Description:	Bytes availabble to write
+Description:	Bytes available to write
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/relid/events
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/events
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Number of times we have signaled the host
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/relid/interrupts
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/interrupts
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Number of times we have taken an interrupt (incoming)
 Users:		Debugging tools
+
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/subchannel_id
+Date:		January. 2018
+KernelVersion:	4.16
+Contact:	Stephen Hemminger <sthemmin@microsoft.com>
+Description:	Subchannel ID associated with VMBUS channel
+Users:		Debugging tools and userspace drivers
+
+What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/monitor_id
+Date:		January. 2018
+KernelVersion:	4.16
+Contact:	Stephen Hemminger <sthemmin@microsoft.com>
+Description:	Monitor bit associated with channel
+Users:		Debugging tools and userspace drivers
diff --git a/Documentation/ABI/testing/devlink-resource-mlxsw b/Documentation/ABI/testing/devlink-resource-mlxsw
new file mode 100644
index 000000000000..259ed2948ec0
--- /dev/null
+++ b/Documentation/ABI/testing/devlink-resource-mlxsw
@@ -0,0 +1,33 @@
+What: 		/kvd/
+Date:		08-Jan-2018
+KernelVersion:	v4.16
+Contact:	mlxsw@mellanox.com
+Description:	The main database in the Spectrum device is a centralized
+		KVD database used for many of the tables used to configure
+		the chip including L2 FDB, L3 LPM, ECMP and more. The KVD
+		is divided into two sections, the first is hash-based table
+		and the second is a linear access table. The division
+		between the linear and hash-based sections is static and
+		require reload before the changes take effect.
+
+What: 		/kvd/linear
+Date:		08-Jan-2018
+KernelVersion:	v4.16
+Contact:	mlxsw@mellanox.com
+Description:	The linear section of the KVD is managed by software as a
+		flat memory accessed using an index.
+
+What: 		/kvd/hash_single
+Date:		08-Jan-2018
+KernelVersion:	v4.16
+Contact:	mlxsw@mellanox.com
+Description:	The hash based section of the KVD is managed by the switch
+		device. Used in case the key size is smaller or equal to
+		64bit.
+
+What: 		/kvd/hash_double
+Date:		08-Jan-2018
+KernelVersion:	v4.16
+Contact:	mlxsw@mellanox.com
+Description:	The hash based section of the KVD is managed by the switch
+		device. Used in case the key is larger than 64 bit.
diff --git a/Documentation/ABI/testing/evm b/Documentation/ABI/testing/evm
index 9578247e1792..d12cb2eae9ee 100644
--- a/Documentation/ABI/testing/evm
+++ b/Documentation/ABI/testing/evm
@@ -14,30 +14,46 @@ Description:
 		generated either locally or remotely using an
 		asymmetric key. These keys are loaded onto root's
 		keyring using keyctl, and EVM is then enabled by
-		echoing a value to <securityfs>/evm:
+		echoing a value to <securityfs>/evm made up of the
+		following bits:
 
-		1: enable HMAC validation and creation
-		2: enable digital signature validation
-		3: enable HMAC and digital signature validation and HMAC
-		   creation
+		Bit	  Effect
+		0	  Enable HMAC validation and creation
+		1	  Enable digital signature validation
+		2	  Permit modification of EVM-protected metadata at
+			  runtime. Not supported if HMAC validation and
+			  creation is enabled.
+		31	  Disable further runtime modification of EVM policy
 
-		Further writes will be blocked if HMAC support is enabled or
-		if bit 32 is set:
+		For example:
 
-		echo 0x80000002 ><securityfs>/evm
+		echo 1 ><securityfs>/evm
 
-		will enable digital signature validation and block
-		further writes to <securityfs>/evm.
+		will enable HMAC validation and creation
 
-		Until this is done, EVM can not create or validate the
-		'security.evm' xattr, but returns INTEGRITY_UNKNOWN.
-		Loading keys and signaling EVM should be done as early
-		as possible.  Normally this is done in the initramfs,
-		which has already been measured as part of the trusted
-		boot.  For more information on creating and loading
-		existing trusted/encrypted keys, refer to:
+		echo 0x80000003 ><securityfs>/evm
 
-		Documentation/security/keys/trusted-encrypted.rst. Both dracut
-		(via 97masterkey and 98integrity) and systemd (via
+		will enable HMAC and digital signature validation and
+		HMAC creation and disable all further modification of policy.
+
+		echo 0x80000006 ><securityfs>/evm
+
+		will enable digital signature validation, permit
+		modification of EVM-protected metadata and
+		disable all further modification of policy
+
+		Note that once a key has been loaded, it will no longer be
+		possible to enable metadata modification.
+
+		Until key loading has been signaled EVM can not create
+		or validate the 'security.evm' xattr, but returns
+		INTEGRITY_UNKNOWN.  Loading keys and signaling EVM
+		should be done as early as possible.  Normally this is
+		done in the initramfs, which has already been measured
+		as part of the trusted boot.  For more information on
+		creating and loading existing trusted/encrypted keys,
+		refer to:
+		Documentation/security/keys/trusted-encrypted.rst. Both
+		dracut (via 97masterkey and 98integrity) and systemd (via
 		core/ima-setup) have support for loading keys at boot
 		time.
diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy
index e76432b9954d..2028f2d093b2 100644
--- a/Documentation/ABI/testing/ima_policy
+++ b/Documentation/ABI/testing/ima_policy
@@ -17,7 +17,8 @@ Description:
 
 		rule format: action [condition ...]
 
-		action: measure | dont_measure | appraise | dont_appraise | audit
+		action: measure | dont_measure | appraise | dont_appraise |
+			audit | hash | dont_hash
 		condition:= base | lsm  [option]
 			base:	[[func=] [mask=] [fsmagic=] [fsuuid=] [uid=]
 				[euid=] [fowner=]]
diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 2e3f919485f4..6a5f34b4d5b9 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -32,7 +32,7 @@ Description:
 		Description of the physical chip / device for device X.
 		Typically a part number.
 
-What:		/sys/bus/iio/devices/iio:deviceX/timestamp_clock
+What:		/sys/bus/iio/devices/iio:deviceX/current_timestamp_clock
 KernelVersion:	4.5
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -1290,7 +1290,7 @@ KernelVersion:	3.4
 Contact:	linux-iio@vger.kernel.org
 Description:
 		Unit-less light intensity. Modifiers both and ir indicate
-		that measurements contains visible and infrared light
+		that measurements contain visible and infrared light
 		components or just infrared light, respectively. Modifier uv indicates
 		that measurements contain ultraviolet light components.
 
@@ -1413,6 +1413,16 @@ Description:
 		the available samples after the timeout expires and thus have a
 		maximum delay guarantee.
 
+What:		/sys/bus/iio/devices/iio:deviceX/buffer/data_available
+KernelVersion: 4.16
+Contact:	linux-iio@vger.kernel.org
+Description:
+		A read-only value indicating the bytes of data available in the
+		buffer. In the case of an output buffer, this indicates the
+		amount of empty space available to write data to. In the case of
+		an input buffer, this indicates the amount of data available for
+		reading.
+
 What:		/sys/bus/iio/devices/iio:deviceX/buffer/hwfifo_enabled
 KernelVersion: 4.2
 Contact:	linux-iio@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-dfsdm-adc-stm32 b/Documentation/ABI/testing/sysfs-bus-iio-dfsdm-adc-stm32
new file mode 100644
index 000000000000..da9822309f07
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-iio-dfsdm-adc-stm32
@@ -0,0 +1,16 @@
+What:		/sys/bus/iio/devices/iio:deviceX/in_voltage_spi_clk_freq
+KernelVersion:	4.14
+Contact:	arnaud.pouliquen@st.com
+Description:
+		For audio purpose only.
+		Used by audio driver to set/get the spi input frequency.
+		This is mandatory if DFSDM is slave on SPI bus, to
+		provide information on the SPI clock frequency during runtime
+		Notice that the SPI frequency should be a multiple of sample
+		frequency to ensure the precision.
+		if DFSDM input is SPI master
+			Reading  SPI clkout frequency,
+			error on writing
+		If DFSDM input is SPI Slave:
+			Reading returns value previously set.
+			Writing value before starting conversions.
+\ No newline at end of file
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd b/Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd
new file mode 100644
index 000000000000..0088aba4caa8
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd
@@ -0,0 +1,25 @@
+What:		/sys/bus/pci/drivers/xhci_hcd/.../dbc
+Date:		June 2017
+Contact:	Lu Baolu <baolu.lu@linux.intel.com>
+Description:
+		xHCI compatible USB host controllers (i.e. super-speed
+		USB3 controllers) are often implemented with the Debug
+		Capability (DbC). It can present a debug device which
+		is fully compliant with the USB framework and provides
+		the equivalent of a very high performance full-duplex
+		serial link for debug purpose.
+
+		The DbC debug device shares a root port with xHCI host.
+		When the DbC is enabled, the root port will be assigned
+		to the Debug Capability. Otherwise, it will be assigned
+		to xHCI.
+
+		Writing "enable" to this attribute will enable the DbC
+		functionality and the shared root port will be assigned
+		to the DbC device. Writing "disable" to this attribute
+		will disable the DbC functionality and the shared root
+		port will roll back to the xHCI.
+
+		Reading this attribute gives the state of the DbC. It
+		can be one of the following states: disabled, enabled,
+		initialized, connected, configured and stalled.
diff --git a/Documentation/ABI/testing/sysfs-bus-siox b/Documentation/ABI/testing/sysfs-bus-siox
new file mode 100644
index 000000000000..fed7c3765a4e
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-siox
@@ -0,0 +1,87 @@
+What:		/sys/bus/siox/devices/siox-X/active
+KernelVersion:	4.16
+Contact:	Gavin Schenk <g.schenk@eckelmann.de>, Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Description:
+		On reading represents the current state of the bus. If it
+		contains a "0" the bus is stopped and connected devices are
+		expected to not do anything because their watchdog triggered.
+		When the file contains a "1" the bus is operated and periodically
+		does a push-pull cycle to write and read data from the
+		connected devices.
+		When writing a "0" or "1" the bus moves to the described state.
+
+What:		/sys/bus/siox/devices/siox-X/device_add
+KernelVersion:	4.16
+Contact:	Gavin Schenk <g.schenk@eckelmann.de>, Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Description:
+		Write-only file. Write
+
+			<type> <inbytes> <outbytes> <statustype>
+
+		to add a new device dynamically. <type> is the name that is used to match
+		to a driver (similar to the platform bus). <inbytes> and <outbytes> define
+		the length of the input and output shift register in bytes respectively.
+		<statustype> defines the 4 bit device type that is check to identify connection
+		problems.
+		The new device is added to the end of the existing chain.
+
+What:		/sys/bus/siox/devices/siox-X/device_remove
+KernelVersion:	4.16
+Contact:	Gavin Schenk <g.schenk@eckelmann.de>, Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Description:
+		Write-only file. A single write removes the last device in the siox chain.
+
+What:		/sys/bus/siox/devices/siox-X/poll_interval_ns
+KernelVersion:	4.16
+Contact:	Gavin Schenk <g.schenk@eckelmann.de>, Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Description:
+		Defines the interval between two poll cycles in nano seconds.
+		Note this is rounded to jiffies on writing. On reading the current value
+		is returned.
+
+What:		/sys/bus/siox/devices/siox-X-Y/connected
+KernelVersion:	4.16
+Contact:	Gavin Schenk <g.schenk@eckelmann.de>, Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Description:
+		Read-only value. "0" means the Yth device on siox bus X isn't "connected" i.e.
+		communication with it is not ensured. "1" signals a working connection.
+
+What:		/sys/bus/siox/devices/siox-X-Y/inbytes
+KernelVersion:	4.16
+Contact:	Gavin Schenk <g.schenk@eckelmann.de>, Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Description:
+		Read-only value reporting the inbytes value provided to siox-X/device_add
+
+What:		/sys/bus/siox/devices/siox-X-Y/status_errors
+KernelVersion:	4.16
+Contact:	Gavin Schenk <g.schenk@eckelmann.de>, Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Description:
+		Counts the number of time intervals when the read status byte doesn't yield the
+		expected value.
+
+What:		/sys/bus/siox/devices/siox-X-Y/type
+KernelVersion:	4.16
+Contact:	Gavin Schenk <g.schenk@eckelmann.de>, Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Description:
+		Read-only value reporting the type value provided to siox-X/device_add.
+
+What:		/sys/bus/siox/devices/siox-X-Y/watchdog
+KernelVersion:	4.16
+Contact:	Gavin Schenk <g.schenk@eckelmann.de>, Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Description:
+		Read-only value reporting if the watchdog of the siox device is
+		active. "0" means the watchdog is not active and the device is expected to
+		be operational. "1" means the watchdog keeps the device in reset.
+
+What:		/sys/bus/siox/devices/siox-X-Y/watchdog_errors
+KernelVersion:	4.16
+Contact:	Gavin Schenk <g.schenk@eckelmann.de>, Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Description:
+		Read-only value reporting the number to time intervals when the
+		watchdog was active.
+
+What:		/sys/bus/siox/devices/siox-X-Y/outbytes
+KernelVersion:	4.16
+Contact:	Gavin Schenk <g.schenk@eckelmann.de>, Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Description:
+		Read-only value reporting the outbytes value provided to siox-X/device_add.
diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-netdev b/Documentation/ABI/testing/sysfs-class-led-trigger-netdev
new file mode 100644
index 000000000000..451af6d6768c
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-led-trigger-netdev
@@ -0,0 +1,45 @@
+What:		/sys/class/leds/<led>/device_name
+Date:		Dec 2017
+KernelVersion:	4.16
+Contact:	linux-leds@vger.kernel.org
+Description:
+		Specifies the network device name to monitor.
+
+What:		/sys/class/leds/<led>/interval
+Date:		Dec 2017
+KernelVersion:	4.16
+Contact:	linux-leds@vger.kernel.org
+Description:
+		Specifies the duration of the LED blink in milliseconds.
+		Defaults to 50 ms.
+
+What:		/sys/class/leds/<led>/link
+Date:		Dec 2017
+KernelVersion:	4.16
+Contact:	linux-leds@vger.kernel.org
+Description:
+		Signal the link state of the named network device.
+		If set to 0 (default), the LED's normal state is off.
+		If set to 1, the LED's normal state reflects the link state
+		of the named network device.
+		Setting this value also immediately changes the LED state.
+
+What:		/sys/class/leds/<led>/tx
+Date:		Dec 2017
+KernelVersion:	4.16
+Contact:	linux-leds@vger.kernel.org
+Description:
+		Signal transmission of data on the named network device.
+		If set to 0 (default), the LED will not blink on transmission.
+		If set to 1, the LED will blink for the milliseconds specified
+		in interval to signal transmission.
+
+What:		/sys/class/leds/<led>/rx
+Date:		Dec 2017
+KernelVersion:	4.16
+Contact:	linux-leds@vger.kernel.org
+Description:
+		Signal reception of data on the named network device.
+		If set to 0 (default), the LED will not blink on reception.
+		If set to 1, the LED will blink for the milliseconds specified
+		in interval to signal reception.
diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net
index 6856da99b6f7..2f1788111cd9 100644
--- a/Documentation/ABI/testing/sysfs-class-net
+++ b/Documentation/ABI/testing/sysfs-class-net
@@ -259,3 +259,27 @@ Contact:	netdev@vger.kernel.org
 Description:
 		Symbolic link to the PHY device this network device is attached
 		to.
+
+What:		/sys/class/net/<iface>/carrier_changes
+Date:		Mar 2014
+KernelVersion:	3.15
+Contact:	netdev@vger.kernel.org
+Description:
+		32-bit unsigned integer counting the number of times the link has
+		seen a change from UP to DOWN and vice versa
+
+What:		/sys/class/net/<iface>/carrier_up_count
+Date:		Jan 2018
+KernelVersion:	4.16
+Contact:	netdev@vger.kernel.org
+Description:
+		32-bit unsigned integer counting the number of times the link has
+		been up
+
+What:		/sys/class/net/<iface>/carrier_down_count
+Date:		Jan 2018
+KernelVersion:	4.16
+Contact:	netdev@vger.kernel.org
+Description:
+		32-bit unsigned integer counting the number of times the link has
+		been down
diff --git a/Documentation/ABI/testing/sysfs-class-ocxl b/Documentation/ABI/testing/sysfs-class-ocxl
new file mode 100644
index 000000000000..b5b1fa197592
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-ocxl
@@ -0,0 +1,35 @@
+What:		/sys/class/ocxl/<afu name>/afu_version
+Date:		January 2018
+Contact:	linuxppc-dev@lists.ozlabs.org
+Description:	read only
+		Version of the AFU, in the format <major>:<minor>
+		Reflects what is read in the configuration space of the AFU
+
+What:		/sys/class/ocxl/<afu name>/contexts
+Date:		January 2018
+Contact:	linuxppc-dev@lists.ozlabs.org
+Description:	read only
+		Number of contexts for the AFU, in the format <n>/<max>
+		where:
+			n:	number of currently active contexts, for debug
+			max:	maximum number of contexts supported by the AFU
+
+What:		/sys/class/ocxl/<afu name>/pp_mmio_size
+Date:		January 2018
+Contact:	linuxppc-dev@lists.ozlabs.org
+Description:	read only
+		Size of the per-process mmio area, as defined in the
+		configuration space of the AFU
+
+What:		/sys/class/ocxl/<afu name>/global_mmio_size
+Date:		January 2018
+Contact:	linuxppc-dev@lists.ozlabs.org
+Description:	read only
+		Size of the global mmio area, as defined in the
+		configuration space of the AFU
+
+What:		/sys/class/ocxl/<afu name>/global_mmio_area
+Date:		January 2018
+Contact:	linuxppc-dev@lists.ozlabs.org
+Description:	read/write
+		Give access the global mmio area for the AFU
diff --git a/Documentation/ABI/testing/sysfs-devices-coredump b/Documentation/ABI/testing/sysfs-devices-coredump
new file mode 100644
index 000000000000..e459368533a4
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-coredump
@@ -0,0 +1,10 @@
+What:		/sys/devices/.../coredump
+Date:		December 2017
+Contact:	Arend van Spriel <aspriel@gmail.com>
+Description:
+		The /sys/devices/.../coredump attribute is only present when the
+		device is bound to a driver, which provides the .coredump()
+		callback. The attribute is write only. Anything written to this
+		file will trigger the .coredump() callback.
+
+		Available when CONFIG_DEV_COREDUMP is enabled.
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index d6d862db3b5d..bfd29bc8d37a 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -375,3 +375,19 @@ Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	information about CPUs heterogeneity.
 
 		cpu_capacity: capacity of cpu#.
+
+What:		/sys/devices/system/cpu/vulnerabilities
+		/sys/devices/system/cpu/vulnerabilities/meltdown
+		/sys/devices/system/cpu/vulnerabilities/spectre_v1
+		/sys/devices/system/cpu/vulnerabilities/spectre_v2
+Date:		January 2018
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Information about CPU vulnerabilities
+
+		The files are named after the code names of CPU
+		vulnerabilities. The output of those files reflects the
+		state of the CPUs in the system. Possible output values:
+
+		"Not affected"	  CPU is not affected by the vulnerability
+		"Vulnerable"	  CPU is affected and no mitigation in effect
+		"Mitigation: $M"  CPU is affected and mitigation $M is in effect
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index a7799c2fca28..d870b5514d15 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -186,3 +186,9 @@ Date:		August 2017
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
 Description:
 		 Controls sleep time of GC urgent mode
+
+What:		/sys/fs/f2fs/<disk>/readdir_ra
+Date:		November 2017
+Contact:	"Sheng Yong" <shengyong1@huawei.com>
+Description:
+		 Controls readahead inode block in readdir.
diff --git a/Documentation/ABI/testing/sysfs-kernel-livepatch b/Documentation/ABI/testing/sysfs-kernel-livepatch
index d5d39748382f..dac7e1e62a8b 100644
--- a/Documentation/ABI/testing/sysfs-kernel-livepatch
+++ b/Documentation/ABI/testing/sysfs-kernel-livepatch
@@ -33,6 +33,32 @@ Description:
 		An attribute which indicates whether the patch is currently in
 		transition.
 
+What:		/sys/kernel/livepatch/<patch>/signal
+Date:		Nov 2017
+KernelVersion:	4.15.0
+Contact:	live-patching@vger.kernel.org
+Description:
+		A writable attribute that allows administrator to affect the
+		course of an existing transition. Writing 1 sends a fake
+		signal to all remaining blocking tasks. The fake signal
+		means that no proper signal is delivered (there is no data in
+		signal pending structures). Tasks are interrupted or woken up,
+		and forced to change their patched state.
+
+What:		/sys/kernel/livepatch/<patch>/force
+Date:		Nov 2017
+KernelVersion:	4.15.0
+Contact:	live-patching@vger.kernel.org
+Description:
+		A writable attribute that allows administrator to affect the
+		course of an existing transition. Writing 1 clears
+		TIF_PATCH_PENDING flag of all tasks and thus forces the tasks to
+		the patched or unpatched state. Administrator should not
+		use this feature without a clearance from a patch
+		distributor. Removal (rmmod) of patch modules is permanently
+		disabled when the feature is used. See
+		Documentation/livepatch/livepatch.txt for more information.
+
 What:		/sys/kernel/livepatch/<patch>/<object>
 Date:		Nov 2014
 KernelVersion:	3.19.0
diff --git a/Documentation/IRQ-domain.txt b/Documentation/IRQ-domain.txt
index 4a1cd7645d85..507775cce753 100644
--- a/Documentation/IRQ-domain.txt
+++ b/Documentation/IRQ-domain.txt
@@ -265,37 +265,5 @@ support other architectures, such as ARM, ARM64 etc.
 
 === Debugging ===
 
-If you switch on CONFIG_IRQ_DOMAIN_DEBUG (which depends on
-CONFIG_IRQ_DOMAIN and CONFIG_DEBUG_FS), you will find a new file in
-your debugfs mount point, called irq_domain_mapping. This file
-contains a live snapshot of all the IRQ domains in the system:
-
- name              mapped  linear-max  direct-max  devtree-node
- pl061                  8           8           0  /smb/gpio@e0080000
- pl061                  8           8           0  /smb/gpio@e1050000
- pMSI                   0           0           0  /interrupt-controller@e1101000/v2m@e0080000
- MSI                   37           0           0  /interrupt-controller@e1101000/v2m@e0080000
- GICv2m                37           0           0  /interrupt-controller@e1101000/v2m@e0080000
- GICv2                448         448           0  /interrupt-controller@e1101000
-
-it also iterates over the interrupts to display their mapping in the
-domains, and makes the domain stacking visible:
-
-
-irq    hwirq    chip name        chip data           active  type            domain
-    1  0x00019  GICv2            0xffff00000916bfd8     *    LINEAR          GICv2
-    2  0x0001d  GICv2            0xffff00000916bfd8          LINEAR          GICv2
-    3  0x0001e  GICv2            0xffff00000916bfd8     *    LINEAR          GICv2
-    4  0x0001b  GICv2            0xffff00000916bfd8     *    LINEAR          GICv2
-    5  0x0001a  GICv2            0xffff00000916bfd8          LINEAR          GICv2
-[...]
-   96  0x81808  MSI              0x          (null)           RADIX          MSI
-   96+ 0x00063  GICv2m           0xffff8003ee116980           RADIX          GICv2m
-   96+ 0x00063  GICv2            0xffff00000916bfd8          LINEAR          GICv2
-   97  0x08800  MSI              0x          (null)     *     RADIX          MSI
-   97+ 0x00064  GICv2m           0xffff8003ee116980     *     RADIX          GICv2m
-   97+ 0x00064  GICv2            0xffff00000916bfd8     *    LINEAR          GICv2
-
-Here, interrupts 1-5 are only using a single domain, while 96 and 97
-are build out of a stack of three domain, each level performing a
-particular function.
+Most of the internals of the IRQ subsystem are exposed in debugfs by
+turning CONFIG_GENERIC_IRQ_DEBUGFS on.
diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
index 38d6d800761f..6c06e10bd04b 100644
--- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html
+++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
@@ -1097,7 +1097,8 @@ will cause the CPU to disregard the values of its counters on
 its next exit from idle.
 Finally, the <tt>rcu_qs_ctr_snap</tt> field is used to detect
 cases where a given operation has resulted in a quiescent state
-for all flavors of RCU, for example, <tt>cond_resched_rcu_qs()</tt>.
+for all flavors of RCU, for example, <tt>cond_resched()</tt>
+when RCU has indicated a need for quiescent states.
 
 <h5>RCU Callback Handling</h5>
 
@@ -1182,8 +1183,8 @@ CPU (and from tracing) unless otherwise stated.
 Its fields are as follows:
 
 <pre>
-  1   int dynticks_nesting;
-  2   int dynticks_nmi_nesting;
+  1   long dynticks_nesting;
+  2   long dynticks_nmi_nesting;
   3   atomic_t dynticks;
   4   bool rcu_need_heavy_qs;
   5   unsigned long rcu_qs_ctr;
@@ -1191,15 +1192,31 @@ Its fields are as follows:
 </pre>
 
 <p>The <tt>-&gt;dynticks_nesting</tt> field counts the
-nesting depth of normal interrupts.
-In addition, this counter is incremented when exiting dyntick-idle
-mode and decremented when entering it.
+nesting depth of process execution, so that in normal circumstances
+this counter has value zero or one.
+NMIs, irqs, and tracers are counted by the <tt>-&gt;dynticks_nmi_nesting</tt>
+field.
+Because NMIs cannot be masked, changes to this variable have to be
+undertaken carefully using an algorithm provided by Andy Lutomirski.
+The initial transition from idle adds one, and nested transitions
+add two, so that a nesting level of five is represented by a
+<tt>-&gt;dynticks_nmi_nesting</tt> value of nine.
 This counter can therefore be thought of as counting the number
 of reasons why this CPU cannot be permitted to enter dyntick-idle
-mode, aside from non-maskable interrupts (NMIs).
-NMIs are counted by the <tt>-&gt;dynticks_nmi_nesting</tt>
-field, except that NMIs that interrupt non-dyntick-idle execution
-are not counted.
+mode, aside from process-level transitions.
+
+<p>However, it turns out that when running in non-idle kernel context,
+the Linux kernel is fully capable of entering interrupt handlers that
+never exit and perhaps also vice versa.
+Therefore, whenever the <tt>-&gt;dynticks_nesting</tt> field is
+incremented up from zero, the <tt>-&gt;dynticks_nmi_nesting</tt> field
+is set to a large positive number, and whenever the
+<tt>-&gt;dynticks_nesting</tt> field is decremented down to zero,
+the the <tt>-&gt;dynticks_nmi_nesting</tt> field is set to zero.
+Assuming that the number of misnested interrupts is not sufficient
+to overflow the counter, this approach corrects the
+<tt>-&gt;dynticks_nmi_nesting</tt> field every time the corresponding
+CPU enters the idle loop from process context.
 
 </p><p>The <tt>-&gt;dynticks</tt> field counts the corresponding
 CPU's transitions to and from dyntick-idle mode, so that this counter
@@ -1231,14 +1248,16 @@ in response.
 <tr><th>&nbsp;</th></tr>
 <tr><th align="left">Quick Quiz:</th></tr>
 <tr><td>
-	Why not just count all NMIs?
-	Wouldn't that be simpler and less error prone?
+	Why not simply combine the <tt>-&gt;dynticks_nesting</tt>
+	and <tt>-&gt;dynticks_nmi_nesting</tt> counters into a
+	single counter that just counts the number of reasons that
+	the corresponding CPU is non-idle?
 </td></tr>
 <tr><th align="left">Answer:</th></tr>
 <tr><td bgcolor="#ffffff"><font color="ffffff">
-	It seems simpler only until you think hard about how to go about
-	updating the <tt>rcu_dynticks</tt> structure's
-	<tt>-&gt;dynticks</tt> field.
+	Because this would fail in the presence of interrupts whose
+	handlers never return and of handlers that manage to return
+	from a made-up interrupt.
 </font></td></tr>
 <tr><td>&nbsp;</td></tr>
 </table>
diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html
index 62e847bcdcdd..49690228b1c6 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.html
+++ b/Documentation/RCU/Design/Requirements/Requirements.html
@@ -581,7 +581,8 @@ This guarantee was only partially premeditated.
 DYNIX/ptx used an explicit memory barrier for publication, but had nothing
 resembling <tt>rcu_dereference()</tt> for subscription, nor did it
 have anything resembling the <tt>smp_read_barrier_depends()</tt>
-that was later subsumed into <tt>rcu_dereference()</tt>.
+that was later subsumed into <tt>rcu_dereference()</tt> and later
+still into <tt>READ_ONCE()</tt>.
 The need for these operations made itself known quite suddenly at a
 late-1990s meeting with the DEC Alpha architects, back in the days when
 DEC was still a free-standing company.
@@ -2797,7 +2798,7 @@ RCU must avoid degrading real-time response for CPU-bound threads, whether
 executing in usermode (which is one use case for
 <tt>CONFIG_NO_HZ_FULL=y</tt>) or in the kernel.
 That said, CPU-bound loops in the kernel must execute
-<tt>cond_resched_rcu_qs()</tt> at least once per few tens of milliseconds
+<tt>cond_resched()</tt> at least once per few tens of milliseconds
 in order to avoid receiving an IPI from RCU.
 
 <p>
@@ -3128,7 +3129,7 @@ The solution, in the form of
 is to have implicit
 read-side critical sections that are delimited by voluntary context
 switches, that is, calls to <tt>schedule()</tt>,
-<tt>cond_resched_rcu_qs()</tt>, and
+<tt>cond_resched()</tt>, and
 <tt>synchronize_rcu_tasks()</tt>.
 In addition, transitions to and from userspace execution also delimit
 tasks-RCU read-side critical sections.
diff --git a/Documentation/RCU/rcu_dereference.txt b/Documentation/RCU/rcu_dereference.txt
index 1acb26b09b48..ab96227bad42 100644
--- a/Documentation/RCU/rcu_dereference.txt
+++ b/Documentation/RCU/rcu_dereference.txt
@@ -122,11 +122,7 @@ o	Be very careful about comparing pointers obtained from
 		Note that if checks for being within an RCU read-side
 		critical section are not required and the pointer is never
 		dereferenced, rcu_access_pointer() should be used in place
-		of rcu_dereference(). The rcu_access_pointer() primitive
-		does not require an enclosing read-side critical section,
-		and also omits the smp_read_barrier_depends() included in
-		rcu_dereference(), which in turn should provide a small
-		performance gain in some CPUs (e.g., the DEC Alpha).
+		of rcu_dereference().
 
 	o	The comparison is against a pointer that references memory
 		that was initialized "a long time ago."  The reason
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index a08f928c8557..4259f95c3261 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -23,12 +23,10 @@ o	A CPU looping with preemption disabled.  This condition can
 o	A CPU looping with bottom halves disabled.  This condition can
 	result in RCU-sched and RCU-bh stalls.
 
-o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the
-	kernel without invoking schedule().  Note that cond_resched()
-	does not necessarily prevent RCU CPU stall warnings.  Therefore,
-	if the looping in the kernel is really expected and desirable
-	behavior, you might need to replace some of the cond_resched()
-	calls with calls to cond_resched_rcu_qs().
+o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
+	without invoking schedule().  If the looping in the kernel is
+	really expected and desirable behavior, you might need to add
+	some calls to cond_resched().
 
 o	Booting Linux using a console connection that is too slow to
 	keep up with the boot-time console-message rate.  For example,
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index df62466da4e0..a27fbfb0efb8 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -600,8 +600,7 @@ don't forget about them when submitting patches making use of RCU!]
 
 	#define rcu_dereference(p) \
 	({ \
-		typeof(p) _________p1 = p; \
-		smp_read_barrier_depends(); \
+		typeof(p) _________p1 = READ_ONCE(p); \
 		(_________p1); \
 	})
 
diff --git a/Documentation/accelerators/ocxl.rst b/Documentation/accelerators/ocxl.rst
new file mode 100644
index 000000000000..4f7af841d935
--- /dev/null
+++ b/Documentation/accelerators/ocxl.rst
@@ -0,0 +1,160 @@
+========================================================
+OpenCAPI (Open Coherent Accelerator Processor Interface)
+========================================================
+
+OpenCAPI is an interface between processors and accelerators. It aims
+at being low-latency and high-bandwidth. The specification is
+developed by the `OpenCAPI Consortium <http://opencapi.org/>`_.
+
+It allows an accelerator (which could be a FPGA, ASICs, ...) to access
+the host memory coherently, using virtual addresses. An OpenCAPI
+device can also host its own memory, that can be accessed from the
+host.
+
+OpenCAPI is known in linux as 'ocxl', as the open, processor-agnostic
+evolution of 'cxl' (the driver for the IBM CAPI interface for
+powerpc), which was named that way to avoid confusion with the ISDN
+CAPI subsystem.
+
+
+High-level view
+===============
+
+OpenCAPI defines a Data Link Layer (DL) and Transaction Layer (TL), to
+be implemented on top of a physical link. Any processor or device
+implementing the DL and TL can start sharing memory.
+
+::
+
+  +-----------+                         +-------------+
+  |           |                         |             |
+  |           |                         | Accelerated |
+  | Processor |                         |  Function   |
+  |           |  +--------+             |    Unit     |  +--------+
+  |           |--| Memory |             |    (AFU)    |--| Memory |
+  |           |  +--------+             |             |  +--------+
+  +-----------+                         +-------------+
+       |                                       |
+  +-----------+                         +-------------+
+  |    TL     |                         |    TLX      |
+  +-----------+                         +-------------+
+       |                                       |
+  +-----------+                         +-------------+
+  |    DL     |                         |    DLX      |
+  +-----------+                         +-------------+
+       |                                       |
+       |                   PHY                 |
+       +---------------------------------------+
+
+
+
+Device discovery
+================
+
+OpenCAPI relies on a PCI-like configuration space, implemented on the
+device. So the host can discover AFUs by querying the config space.
+
+OpenCAPI devices in Linux are treated like PCI devices (with a few
+caveats). The firmware is expected to abstract the hardware as if it
+was a PCI link. A lot of the existing PCI infrastructure is reused:
+devices are scanned and BARs are assigned during the standard PCI
+enumeration. Commands like 'lspci' can therefore be used to see what
+devices are available.
+
+The configuration space defines the AFU(s) that can be found on the
+physical adapter, such as its name, how many memory contexts it can
+work with, the size of its MMIO areas, ...
+
+
+
+MMIO
+====
+
+OpenCAPI defines two MMIO areas for each AFU:
+
+* the global MMIO area, with registers pertinent to the whole AFU.
+* a per-process MMIO area, which has a fixed size for each context.
+
+
+
+AFU interrupts
+==============
+
+OpenCAPI includes the possibility for an AFU to send an interrupt to a
+host process. It is done through a 'intrp_req' defined in the
+Transaction Layer, specifying a 64-bit object handle which defines the
+interrupt.
+
+The driver allows a process to allocate an interrupt and obtain its
+64-bit object handle, that can be passed to the AFU.
+
+
+
+char devices
+============
+
+The driver creates one char device per AFU found on the physical
+device. A physical device may have multiple functions and each
+function can have multiple AFUs. At the time of this writing though,
+it has only been tested with devices exporting only one AFU.
+
+Char devices can be found in /dev/ocxl/ and are named as:
+/dev/ocxl/<AFU name>.<location>.<index>
+
+where <AFU name> is a max 20-character long name, as found in the
+config space of the AFU.
+<location> is added by the driver and can help distinguish devices
+when a system has more than one instance of the same OpenCAPI device.
+<index> is also to help distinguish AFUs in the unlikely case where a
+device carries multiple copies of the same AFU.
+
+
+
+Sysfs class
+===========
+
+An ocxl class is added for the devices representing the AFUs. See
+/sys/class/ocxl. The layout is described in
+Documentation/ABI/testing/sysfs-class-ocxl
+
+
+
+User API
+========
+
+open
+----
+
+Based on the AFU definition found in the config space, an AFU may
+support working with more than one memory context, in which case the
+associated char device may be opened multiple times by different
+processes.
+
+
+ioctl
+-----
+
+OCXL_IOCTL_ATTACH:
+
+  Attach the memory context of the calling process to the AFU so that
+  the AFU can access its memory.
+
+OCXL_IOCTL_IRQ_ALLOC:
+
+  Allocate an AFU interrupt and return an identifier.
+
+OCXL_IOCTL_IRQ_FREE:
+
+  Free a previously allocated AFU interrupt.
+
+OCXL_IOCTL_IRQ_SET_FD:
+
+  Associate an event fd to an AFU interrupt so that the user process
+  can be notified when the AFU sends an interrupt.
+
+
+mmap
+----
+
+A process can mmap the per-process MMIO area for interactions with the
+AFU.
diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst
index 63066db39910..af5a437198d0 100644
--- a/Documentation/admin-guide/README.rst
+++ b/Documentation/admin-guide/README.rst
@@ -170,11 +170,6 @@ Configuring the kernel
                         your existing ./.config file and asking about
                         new config symbols.
 
-     "make silentoldconfig"
-                        Like above, but avoids cluttering the screen
-                        with questions already answered.
-                        Additionally updates the dependencies.
-
      "make olddefconfig"
                         Like above, but sets new symbols to their default
                         values without prompting.
diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index b2598cc9834c..7242cbda15dd 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/Documentation/admin-guide/kernel-parameters.rst
@@ -109,6 +109,7 @@ parameter is applicable::
 	IPV6	IPv6 support is enabled.
 	ISAPNP	ISA PnP code is enabled.
 	ISDN	Appropriate ISDN support is enabled.
+	ISOL	CPU Isolation is enabled.
 	JOY	Appropriate joystick support is enabled.
 	KGDB	Kernel debugger support is enabled.
 	KVM	Kernel Virtual Machine support is enabled.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 6571fbfdb2a1..90cefbddf1ed 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -114,7 +114,6 @@
 			This facility can be used to prevent such uncontrolled
 			GPE floodings.
 			Format: <int>
-			Support masking of GPEs numbered from 0x00 to 0x7f.
 
 	acpi_no_auto_serialize	[HW,ACPI]
 			Disable auto-serialization of AML methods
@@ -223,7 +222,7 @@
 
 	acpi_sleep=	[HW,ACPI] Sleep options
 			Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
-				  old_ordering, nonvs, sci_force_enable }
+				  old_ordering, nonvs, sci_force_enable, nobl }
 			See Documentation/power/video.txt for information on
 			s3_bios and s3_mode.
 			s3_beep is for debugging; it makes the PC's speaker beep
@@ -239,6 +238,9 @@
 			sci_force_enable causes the kernel to set SCI_EN directly
 			on resume from S1/S3 (which is against the ACPI spec,
 			but some broken systems don't work without it).
+			nobl causes the internal blacklist of systems known to
+			behave incorrectly in some ways with respect to system
+			suspend and resume to be ignored (use wisely).
 
 	acpi_use_timer_override [HW,ACPI]
 			Use timer override. For some broken Nvidia NF5 boards
@@ -328,11 +330,15 @@
 			not play well with APC CPU idle - disable it if you have
 			APC and your system crashes randomly.
 
-	apic=		[APIC,X86-32] Advanced Programmable Interrupt Controller
+	apic=		[APIC,X86] Advanced Programmable Interrupt Controller
 			Change the output verbosity whilst booting
 			Format: { quiet (default) | verbose | debug }
 			Change the amount of debugging information output
 			when initialising the APIC and IO-APIC components.
+			For X86-32, this can also be used to specify an APIC
+			driver name.
+			Format: apic=driver_name
+			Examples: apic=bigsmp
 
 	apic_extnmi=	[APIC,X86] External NMI delivery setting
 			Format: { bsp (default) | all | none }
@@ -640,6 +646,20 @@
 			console=brl,ttyS0
 		For now, only VisioBraille is supported.
 
+	console_msg_format=
+			[KNL] Change console messages format
+		default
+			By default we print messages on consoles in
+			"[time stamp] text\n" format (time stamp may not be
+			printed, depending on CONFIG_PRINTK_TIME or
+			`printk_time' param).
+		syslog
+			Switch to syslog format: "<%u>[time stamp] text\n"
+			IOW, each message will have a facility and loglevel
+			prefix. The format is similar to one used by syslog()
+			syscall, or to executing "dmesg -S --raw" or to reading
+			from /proc/kmsg.
+
 	consoleblank=	[KNL] The console blank (screen saver) timeout in
 			seconds. A value of 0 disables the blank timer.
                        Defaults to 0.
@@ -709,9 +729,6 @@
 			It will be ignored when crashkernel=X,high is not used
 			or memory reserved is below 4G.
 
-	crossrelease_fullstack
-			[KNL] Allow to record full stack trace in cross-release
-
 	cryptomgr.notests
                         [KNL] Disable crypto self-tests
 
@@ -1737,7 +1754,7 @@
 	isapnp=		[ISAPNP]
 			Format: <RDP>,<reset>,<pci_scan>,<verbosity>
 
-	isolcpus=	[KNL,SMP] Isolate a given set of CPUs from disturbance.
+	isolcpus=	[KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance.
 			[Deprecated - use cpusets instead]
 			Format: [flag-list,]<cpu-list>
 
@@ -2049,9 +2066,6 @@
 			This tests the locking primitive's ability to
 			transition abruptly to and from idle.
 
-	locktorture.torture_runnable= [BOOT]
-			Start locktorture running at boot time.
-
 	locktorture.torture_type= [KNL]
 			Specify the locking implementation to test.
 
@@ -2538,6 +2552,9 @@
 			This is useful when you use a panic=... timeout and
 			need the box quickly up again.
 
+			These settings can be accessed at runtime via
+			the nmi_watchdog and hardlockup_panic sysctls.
+
 	netpoll.carrier_timeout=
 			[NET] Specifies amount of time (in seconds) that
 			netpoll should wait for a carrier. By default netpoll
@@ -2622,6 +2639,11 @@
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
+	nospectre_v2	[X86] Disable all mitigations for the Spectre variant 2
+			(indirect branch prediction) vulnerability. System may
+			allow data leaks with this option, which is equivalent
+			to spectre_v2=off.
+
 	noxsave		[BUGS=X86] Disables x86 extended register state save
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
@@ -2662,7 +2684,7 @@
 			Valid arguments: on, off
 			Default: on
 
-	nohz_full=	[KNL,BOOT]
+	nohz_full=	[KNL,BOOT,SMP,ISOL]
 			The argument is a cpu list, as described above.
 			In kernels built with CONFIG_NO_HZ_FULL=y, set
 			the specified list of CPUs whose tick will be stopped
@@ -3094,6 +3116,12 @@
 		pcie_scan_all	Scan all possible PCIe devices.  Otherwise we
 				only look for one device below a PCIe downstream
 				port.
+		big_root_window	Try to add a big 64bit memory window to the PCIe
+				root complex on AMD CPUs. Some GFX hardware
+				can resize a BAR to allow access to all VRAM.
+				Adding the window is slightly risky (it may
+				conflict with unreported devices), so this
+				taints the kernel.
 
 	pcie_aspm=	[PCIE] Forcibly enable or disable PCIe Active State Power
 			Management.
@@ -3282,6 +3310,21 @@
 	pt.		[PARIDE]
 			See Documentation/blockdev/paride.txt.
 
+	pti=		[X86_64] Control Page Table Isolation of user and
+			kernel address spaces.  Disabling this feature
+			removes hardening, but improves performance of
+			system calls and interrupts.
+
+			on   - unconditionally enable
+			off  - unconditionally disable
+			auto - kernel detects whether your CPU model is
+			       vulnerable to issues that PTI mitigates
+
+			Not specifying this option is equivalent to pti=auto.
+
+	nopti		[X86_64]
+			Equivalent to pti=off
+
 	pty.legacy_count=
 			[KNL] Number of legacy pty's. Overwrites compiled-in
 			default number.
@@ -3459,9 +3502,6 @@
 			the same as for rcuperf.nreaders.
 			N, where N is the number of CPUs
 
-	rcuperf.perf_runnable= [BOOT]
-			Start rcuperf running at boot time.
-
 	rcuperf.perf_type= [KNL]
 			Specify the RCU implementation to test.
 
@@ -3595,9 +3635,6 @@
 			Test RCU's dyntick-idle handling.  See also the
 			rcutorture.shuffle_interval parameter.
 
-	rcutorture.torture_runnable= [BOOT]
-			Start rcutorture running at boot time.
-
 	rcutorture.torture_type= [KNL]
 			Specify the RCU implementation to test.
 
@@ -3655,7 +3692,8 @@
 
 	rdt=		[HW,X86,RDT]
 			Turn on/off individual RDT features. List is:
-			cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, mba.
+			cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
+			mba.
 			E.g. to turn on cmt and turn off mba use:
 				rdt=cmt,!mba
 
@@ -3931,6 +3969,29 @@
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
 			See Documentation/laptops/sonypi.txt
 
+	spectre_v2=	[X86] Control mitigation of Spectre variant 2
+			(indirect branch speculation) vulnerability.
+
+			on   - unconditionally enable
+			off  - unconditionally disable
+			auto - kernel detects whether your CPU model is
+			       vulnerable
+
+			Selecting 'on' will, and 'auto' may, choose a
+			mitigation method at run time according to the
+			CPU, the available microcode, the setting of the
+			CONFIG_RETPOLINE configuration option, and the
+			compiler with which the kernel was built.
+
+			Specific mitigations can also be selected manually:
+
+			retpoline	  - replace indirect branches
+			retpoline,generic - google's original retpoline
+			retpoline,amd     - AMD-specific minimal thunk
+
+			Not specifying this option is equivalent to
+			spectre_v2=auto.
+
 	spia_io_base=	[HW,MTD]
 	spia_fio_base=
 	spia_pedr=
diff --git a/Documentation/admin-guide/mono.rst b/Documentation/admin-guide/mono.rst
index cdddc099af64..59e6d59f0ed9 100644
--- a/Documentation/admin-guide/mono.rst
+++ b/Documentation/admin-guide/mono.rst
@@ -9,14 +9,14 @@ This will allow you to execute Mono-based .NET binaries just like any
 other program after you have done the following:
 
 1) You MUST FIRST install the Mono CLR support, either by downloading
-   a binary package, a source tarball or by installing from CVS. Binary
+   a binary package, a source tarball or by installing from Git. Binary
    packages for several distributions can be found at:
 
-	http://go-mono.com/download.html
+	http://www.mono-project.com/download/
 
    Instructions for compiling Mono can be found at:
 
-	http://www.go-mono.com/compiling.html
+	http://www.mono-project.com/docs/compiling-mono/linux/
 
    Once the Mono CLR support has been installed, just check that
    ``/usr/bin/mono`` (which could be located elsewhere, for example
diff --git a/Documentation/admin-guide/thunderbolt.rst b/Documentation/admin-guide/thunderbolt.rst
index de50a8561774..9b55952039a6 100644
--- a/Documentation/admin-guide/thunderbolt.rst
+++ b/Documentation/admin-guide/thunderbolt.rst
@@ -230,7 +230,7 @@ If supported by your machine this will be exposed by the WMI bus with
 a sysfs attribute called "force_power".
 
 For example the intel-wmi-thunderbolt driver exposes this attribute in:
-  /sys/devices/platform/PNP0C14:00/wmi_bus/wmi_bus-PNP0C14:00/86CCFD48-205E-4A77-9C48-2021CBEDE341/force_power
+  /sys/bus/wmi/devices/86CCFD48-205E-4A77-9C48-2021CBEDE341/force_power
 
   To force the power to on, write 1 to this attribute file.
   To disable force power, write 0 to this attribute file.
diff --git a/Documentation/arm64/cpu-feature-registers.txt b/Documentation/arm64/cpu-feature-registers.txt
index bd9b3faab2c4..a70090b28b07 100644
--- a/Documentation/arm64/cpu-feature-registers.txt
+++ b/Documentation/arm64/cpu-feature-registers.txt
@@ -110,7 +110,9 @@ infrastructure:
      x--------------------------------------------------x
      | Name                         |  bits   | visible |
      |--------------------------------------------------|
-     | RES0                         | [63-48] |    n    |
+     | RES0                         | [63-52] |    n    |
+     |--------------------------------------------------|
+     | FHM                          | [51-48] |    y    |
      |--------------------------------------------------|
      | DP                           | [47-44] |    y    |
      |--------------------------------------------------|
diff --git a/Documentation/arm64/elf_hwcaps.txt b/Documentation/arm64/elf_hwcaps.txt
index 89edba12a9e0..57324ee55ecc 100644
--- a/Documentation/arm64/elf_hwcaps.txt
+++ b/Documentation/arm64/elf_hwcaps.txt
@@ -158,3 +158,7 @@ HWCAP_SHA512
 HWCAP_SVE
 
     Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001.
+
+HWCAP_ASIMDFHM
+
+   Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0001.
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index 304bf22bb83c..c1d520de6dfe 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -72,6 +72,7 @@ stable kernels.
 | Hisilicon      | Hip0{6,7}       | #161010701      | N/A                         |
 | Hisilicon      | Hip07           | #161600802      | HISILICON_ERRATUM_161600802 |
 |                |                 |                 |                             |
-| Qualcomm Tech. | Falkor v1       | E1003           | QCOM_FALKOR_ERRATUM_1003    |
+| Qualcomm Tech. | Kryo/Falkor v1  | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |
 | Qualcomm Tech. | QDF2400 ITS     | E0065           | QCOM_QDF2400_ERRATUM_0065   |
+| Qualcomm Tech. | Falkor v{1,2}   | E1041           | QCOM_FALKOR_ERRATUM_1041    |
diff --git a/Documentation/bpf/bpf_devel_QA.txt b/Documentation/bpf/bpf_devel_QA.txt
new file mode 100644
index 000000000000..cefef855dea4
--- /dev/null
+++ b/Documentation/bpf/bpf_devel_QA.txt
@@ -0,0 +1,519 @@
+This document provides information for the BPF subsystem about various
+workflows related to reporting bugs, submitting patches, and queueing
+patches for stable kernels.
+
+For general information about submitting patches, please refer to
+Documentation/process/. This document only describes additional specifics
+related to BPF.
+
+Reporting bugs:
+---------------
+
+Q: How do I report bugs for BPF kernel code?
+
+A: Since all BPF kernel development as well as bpftool and iproute2 BPF
+   loader development happens through the netdev kernel mailing list,
+   please report any found issues around BPF to the following mailing
+   list:
+
+     netdev@vger.kernel.org
+
+   This may also include issues related to XDP, BPF tracing, etc.
+
+   Given netdev has a high volume of traffic, please also add the BPF
+   maintainers to Cc (from kernel MAINTAINERS file):
+
+     Alexei Starovoitov <ast@kernel.org>
+     Daniel Borkmann <daniel@iogearbox.net>
+
+   In case a buggy commit has already been identified, make sure to keep
+   the actual commit authors in Cc as well for the report. They can
+   typically be identified through the kernel's git tree.
+
+   Please do *not* report BPF issues to bugzilla.kernel.org since it
+   is a guarantee that the reported issue will be overlooked.
+
+Submitting patches:
+-------------------
+
+Q: To which mailing list do I need to submit my BPF patches?
+
+A: Please submit your BPF patches to the netdev kernel mailing list:
+
+     netdev@vger.kernel.org
+
+   Historically, BPF came out of networking and has always been maintained
+   by the kernel networking community. Although these days BPF touches
+   many other subsystems as well, the patches are still routed mainly
+   through the networking community.
+
+   In case your patch has changes in various different subsystems (e.g.
+   tracing, security, etc), make sure to Cc the related kernel mailing
+   lists and maintainers from there as well, so they are able to review
+   the changes and provide their Acked-by's to the patches.
+
+Q: Where can I find patches currently under discussion for BPF subsystem?
+
+A: All patches that are Cc'ed to netdev are queued for review under netdev
+   patchwork project:
+
+     http://patchwork.ozlabs.org/project/netdev/list/
+
+   Those patches which target BPF, are assigned to a 'bpf' delegate for
+   further processing from BPF maintainers. The current queue with
+   patches under review can be found at:
+
+     https://patchwork.ozlabs.org/project/netdev/list/?delegate=77147
+
+   Once the patches have been reviewed by the BPF community as a whole
+   and approved by the BPF maintainers, their status in patchwork will be
+   changed to 'Accepted' and the submitter will be notified by mail. This
+   means that the patches look good from a BPF perspective and have been
+   applied to one of the two BPF kernel trees.
+
+   In case feedback from the community requires a respin of the patches,
+   their status in patchwork will be set to 'Changes Requested', and purged
+   from the current review queue. Likewise for cases where patches would
+   get rejected or are not applicable to the BPF trees (but assigned to
+   the 'bpf' delegate).
+
+Q: How do the changes make their way into Linux?
+
+A: There are two BPF kernel trees (git repositories). Once patches have
+   been accepted by the BPF maintainers, they will be applied to one
+   of the two BPF trees:
+
+     https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git/
+     https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/
+
+   The bpf tree itself is for fixes only, whereas bpf-next for features,
+   cleanups or other kind of improvements ("next-like" content). This is
+   analogous to net and net-next trees for networking. Both bpf and
+   bpf-next will only have a master branch in order to simplify against
+   which branch patches should get rebased to.
+
+   Accumulated BPF patches in the bpf tree will regularly get pulled
+   into the net kernel tree. Likewise, accumulated BPF patches accepted
+   into the bpf-next tree will make their way into net-next tree. net and
+   net-next are both run by David S. Miller. From there, they will go
+   into the kernel mainline tree run by Linus Torvalds. To read up on the
+   process of net and net-next being merged into the mainline tree, see
+   the netdev FAQ under:
+
+     Documentation/networking/netdev-FAQ.txt
+
+   Occasionally, to prevent merge conflicts, we might send pull requests
+   to other trees (e.g. tracing) with a small subset of the patches, but
+   net and net-next are always the main trees targeted for integration.
+
+   The pull requests will contain a high-level summary of the accumulated
+   patches and can be searched on netdev kernel mailing list through the
+   following subject lines (yyyy-mm-dd is the date of the pull request):
+
+     pull-request: bpf yyyy-mm-dd
+     pull-request: bpf-next yyyy-mm-dd
+
+Q: How do I indicate which tree (bpf vs. bpf-next) my patch should be
+   applied to?
+
+A: The process is the very same as described in the netdev FAQ, so
+   please read up on it. The subject line must indicate whether the
+   patch is a fix or rather "next-like" content in order to let the
+   maintainers know whether it is targeted at bpf or bpf-next.
+
+   For fixes eventually landing in bpf -> net tree, the subject must
+   look like:
+
+     git format-patch --subject-prefix='PATCH bpf' start..finish
+
+   For features/improvements/etc that should eventually land in
+   bpf-next -> net-next, the subject must look like:
+
+     git format-patch --subject-prefix='PATCH bpf-next' start..finish
+
+   If unsure whether the patch or patch series should go into bpf
+   or net directly, or bpf-next or net-next directly, it is not a
+   problem either if the subject line says net or net-next as target.
+   It is eventually up to the maintainers to do the delegation of
+   the patches.
+
+   If it is clear that patches should go into bpf or bpf-next tree,
+   please make sure to rebase the patches against those trees in
+   order to reduce potential conflicts.
+
+   In case the patch or patch series has to be reworked and sent out
+   again in a second or later revision, it is also required to add a
+   version number (v2, v3, ...) into the subject prefix:
+
+     git format-patch --subject-prefix='PATCH net-next v2' start..finish
+
+   When changes have been requested to the patch series, always send the
+   whole patch series again with the feedback incorporated (never send
+   individual diffs on top of the old series).
+
+Q: What does it mean when a patch gets applied to bpf or bpf-next tree?
+
+A: It means that the patch looks good for mainline inclusion from
+   a BPF point of view.
+
+   Be aware that this is not a final verdict that the patch will
+   automatically get accepted into net or net-next trees eventually:
+
+   On the netdev kernel mailing list reviews can come in at any point
+   in time. If discussions around a patch conclude that they cannot
+   get included as-is, we will either apply a follow-up fix or drop
+   them from the trees entirely. Therefore, we also reserve to rebase
+   the trees when deemed necessary. After all, the purpose of the tree
+   is to i) accumulate and stage BPF patches for integration into trees
+   like net and net-next, and ii) run extensive BPF test suite and
+   workloads on the patches before they make their way any further.
+
+   Once the BPF pull request was accepted by David S. Miller, then
+   the patches end up in net or net-next tree, respectively, and
+   make their way from there further into mainline. Again, see the
+   netdev FAQ for additional information e.g. on how often they are
+   merged to mainline.
+
+Q: How long do I need to wait for feedback on my BPF patches?
+
+A: We try to keep the latency low. The usual time to feedback will
+   be around 2 or 3 business days. It may vary depending on the
+   complexity of changes and current patch load.
+
+Q: How often do you send pull requests to major kernel trees like
+   net or net-next?
+
+A: Pull requests will be sent out rather often in order to not
+   accumulate too many patches in bpf or bpf-next.
+
+   As a rule of thumb, expect pull requests for each tree regularly
+   at the end of the week. In some cases pull requests could additionally
+   come also in the middle of the week depending on the current patch
+   load or urgency.
+
+Q: Are patches applied to bpf-next when the merge window is open?
+
+A: For the time when the merge window is open, bpf-next will not be
+   processed. This is roughly analogous to net-next patch processing,
+   so feel free to read up on the netdev FAQ about further details.
+
+   During those two weeks of merge window, we might ask you to resend
+   your patch series once bpf-next is open again. Once Linus released
+   a v*-rc1 after the merge window, we continue processing of bpf-next.
+
+   For non-subscribers to kernel mailing lists, there is also a status
+   page run by David S. Miller on net-next that provides guidance:
+
+     http://vger.kernel.org/~davem/net-next.html
+
+Q: I made a BPF verifier change, do I need to add test cases for
+   BPF kernel selftests?
+
+A: If the patch has changes to the behavior of the verifier, then yes,
+   it is absolutely necessary to add test cases to the BPF kernel
+   selftests suite. If they are not present and we think they are
+   needed, then we might ask for them before accepting any changes.
+
+   In particular, test_verifier.c is tracking a high number of BPF test
+   cases, including a lot of corner cases that LLVM BPF back end may
+   generate out of the restricted C code. Thus, adding test cases is
+   absolutely crucial to make sure future changes do not accidentally
+   affect prior use-cases. Thus, treat those test cases as: verifier
+   behavior that is not tracked in test_verifier.c could potentially
+   be subject to change.
+
+Q: When should I add code to samples/bpf/ and when to BPF kernel
+   selftests?
+
+A: In general, we prefer additions to BPF kernel selftests rather than
+   samples/bpf/. The rationale is very simple: kernel selftests are
+   regularly run by various bots to test for kernel regressions.
+
+   The more test cases we add to BPF selftests, the better the coverage
+   and the less likely it is that those could accidentally break. It is
+   not that BPF kernel selftests cannot demo how a specific feature can
+   be used.
+
+   That said, samples/bpf/ may be a good place for people to get started,
+   so it might be advisable that simple demos of features could go into
+   samples/bpf/, but advanced functional and corner-case testing rather
+   into kernel selftests.
+
+   If your sample looks like a test case, then go for BPF kernel selftests
+   instead!
+
+Q: When should I add code to the bpftool?
+
+A: The main purpose of bpftool (under tools/bpf/bpftool/) is to provide
+   a central user space tool for debugging and introspection of BPF programs
+   and maps that are active in the kernel. If UAPI changes related to BPF
+   enable for dumping additional information of programs or maps, then
+   bpftool should be extended as well to support dumping them.
+
+Q: When should I add code to iproute2's BPF loader?
+
+A: For UAPI changes related to the XDP or tc layer (e.g. cls_bpf), the
+   convention is that those control-path related changes are added to
+   iproute2's BPF loader as well from user space side. This is not only
+   useful to have UAPI changes properly designed to be usable, but also
+   to make those changes available to a wider user base of major
+   downstream distributions.
+
+Q: Do you accept patches as well for iproute2's BPF loader?
+
+A: Patches for the iproute2's BPF loader have to be sent to:
+
+     netdev@vger.kernel.org
+
+   While those patches are not processed by the BPF kernel maintainers,
+   please keep them in Cc as well, so they can be reviewed.
+
+   The official git repository for iproute2 is run by Stephen Hemminger
+   and can be found at:
+
+     https://git.kernel.org/pub/scm/linux/kernel/git/shemminger/iproute2.git/
+
+   The patches need to have a subject prefix of '[PATCH iproute2 master]'
+   or '[PATCH iproute2 net-next]'. 'master' or 'net-next' describes the
+   target branch where the patch should be applied to. Meaning, if kernel
+   changes went into the net-next kernel tree, then the related iproute2
+   changes need to go into the iproute2 net-next branch, otherwise they
+   can be targeted at master branch. The iproute2 net-next branch will get
+   merged into the master branch after the current iproute2 version from
+   master has been released.
+
+   Like BPF, the patches end up in patchwork under the netdev project and
+   are delegated to 'shemminger' for further processing:
+
+     http://patchwork.ozlabs.org/project/netdev/list/?delegate=389
+
+Q: What is the minimum requirement before I submit my BPF patches?
+
+A: When submitting patches, always take the time and properly test your
+   patches *prior* to submission. Never rush them! If maintainers find
+   that your patches have not been properly tested, it is a good way to
+   get them grumpy. Testing patch submissions is a hard requirement!
+
+   Note, fixes that go to bpf tree *must* have a Fixes: tag included. The
+   same applies to fixes that target bpf-next, where the affected commit
+   is in net-next (or in some cases bpf-next). The Fixes: tag is crucial
+   in order to identify follow-up commits and tremendously helps for people
+   having to do backporting, so it is a must have!
+
+   We also don't accept patches with an empty commit message. Take your
+   time and properly write up a high quality commit message, it is
+   essential!
+
+   Think about it this way: other developers looking at your code a month
+   from now need to understand *why* a certain change has been done that
+   way, and whether there have been flaws in the analysis or assumptions
+   that the original author did. Thus providing a proper rationale and
+   describing the use-case for the changes is a must.
+
+   Patch submissions with >1 patch must have a cover letter which includes
+   a high level description of the series. This high level summary will
+   then be placed into the merge commit by the BPF maintainers such that
+   it is also accessible from the git log for future reference.
+
+Q: What do I need to consider when adding a new instruction or feature
+   that would require BPF JIT and/or LLVM integration as well?
+
+A: We try hard to keep all BPF JITs up to date such that the same user
+   experience can be guaranteed when running BPF programs on different
+   architectures without having the program punt to the less efficient
+   interpreter in case the in-kernel BPF JIT is enabled.
+
+   If you are unable to implement or test the required JIT changes for
+   certain architectures, please work together with the related BPF JIT
+   developers in order to get the feature implemented in a timely manner.
+   Please refer to the git log (arch/*/net/) to locate the necessary
+   people for helping out.
+
+   Also always make sure to add BPF test cases (e.g. test_bpf.c and
+   test_verifier.c) for new instructions, so that they can receive
+   broad test coverage and help run-time testing the various BPF JITs.
+
+   In case of new BPF instructions, once the changes have been accepted
+   into the Linux kernel, please implement support into LLVM's BPF back
+   end. See LLVM section below for further information.
+
+Stable submission:
+------------------
+
+Q: I need a specific BPF commit in stable kernels. What should I do?
+
+A: In case you need a specific fix in stable kernels, first check whether
+   the commit has already been applied in the related linux-*.y branches:
+
+     https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git/
+
+   If not the case, then drop an email to the BPF maintainers with the
+   netdev kernel mailing list in Cc and ask for the fix to be queued up:
+
+     netdev@vger.kernel.org
+
+   The process in general is the same as on netdev itself, see also the
+   netdev FAQ document.
+
+Q: Do you also backport to kernels not currently maintained as stable?
+
+A: No. If you need a specific BPF commit in kernels that are currently not
+   maintained by the stable maintainers, then you are on your own.
+
+   The current stable and longterm stable kernels are all listed here:
+
+     https://www.kernel.org/
+
+Q: The BPF patch I am about to submit needs to go to stable as well. What
+   should I do?
+
+A: The same rules apply as with netdev patch submissions in general, see
+   netdev FAQ under:
+
+     Documentation/networking/netdev-FAQ.txt
+
+   Never add "Cc: stable@vger.kernel.org" to the patch description, but
+   ask the BPF maintainers to queue the patches instead. This can be done
+   with a note, for example, under the "---" part of the patch which does
+   not go into the git log. Alternatively, this can be done as a simple
+   request by mail instead.
+
+Q: Where do I find currently queued BPF patches that will be submitted
+   to stable?
+
+A: Once patches that fix critical bugs got applied into the bpf tree, they
+   are queued up for stable submission under:
+
+     http://patchwork.ozlabs.org/bundle/bpf/stable/?state=*
+
+   They will be on hold there at minimum until the related commit made its
+   way into the mainline kernel tree.
+
+   After having been under broader exposure, the queued patches will be
+   submitted by the BPF maintainers to the stable maintainers.
+
+Testing patches:
+----------------
+
+Q: Which BPF kernel selftests version should I run my kernel against?
+
+A: If you run a kernel xyz, then always run the BPF kernel selftests from
+   that kernel xyz as well. Do not expect that the BPF selftest from the
+   latest mainline tree will pass all the time.
+
+   In particular, test_bpf.c and test_verifier.c have a large number of
+   test cases and are constantly updated with new BPF test sequences, or
+   existing ones are adapted to verifier changes e.g. due to verifier
+   becoming smarter and being able to better track certain things.
+
+LLVM:
+-----
+
+Q: Where do I find LLVM with BPF support?
+
+A: The BPF back end for LLVM is upstream in LLVM since version 3.7.1.
+
+   All major distributions these days ship LLVM with BPF back end enabled,
+   so for the majority of use-cases it is not required to compile LLVM by
+   hand anymore, just install the distribution provided package.
+
+   LLVM's static compiler lists the supported targets through 'llc --version',
+   make sure BPF targets are listed. Example:
+
+     $ llc --version
+     LLVM (http://llvm.org/):
+       LLVM version 6.0.0svn
+       Optimized build.
+       Default target: x86_64-unknown-linux-gnu
+       Host CPU: skylake
+
+       Registered Targets:
+         bpf    - BPF (host endian)
+         bpfeb  - BPF (big endian)
+         bpfel  - BPF (little endian)
+         x86    - 32-bit X86: Pentium-Pro and above
+         x86-64 - 64-bit X86: EM64T and AMD64
+
+   For developers in order to utilize the latest features added to LLVM's
+   BPF back end, it is advisable to run the latest LLVM releases. Support
+   for new BPF kernel features such as additions to the BPF instruction
+   set are often developed together.
+
+   All LLVM releases can be found at: http://releases.llvm.org/
+
+Q: Got it, so how do I build LLVM manually anyway?
+
+A: You need cmake and gcc-c++ as build requisites for LLVM. Once you have
+   that set up, proceed with building the latest LLVM and clang version
+   from the git repositories:
+
+     $ git clone http://llvm.org/git/llvm.git
+     $ cd llvm/tools
+     $ git clone --depth 1 http://llvm.org/git/clang.git
+     $ cd ..; mkdir build; cd build
+     $ cmake .. -DLLVM_TARGETS_TO_BUILD="BPF;X86" \
+                -DBUILD_SHARED_LIBS=OFF           \
+                -DCMAKE_BUILD_TYPE=Release        \
+                -DLLVM_BUILD_RUNTIME=OFF
+     $ make -j $(getconf _NPROCESSORS_ONLN)
+
+   The built binaries can then be found in the build/bin/ directory, where
+   you can point the PATH variable to.
+
+Q: Should I notify BPF kernel maintainers about issues in LLVM's BPF code
+   generation back end or about LLVM generated code that the verifier
+   refuses to accept?
+
+A: Yes, please do! LLVM's BPF back end is a key piece of the whole BPF
+   infrastructure and it ties deeply into verification of programs from the
+   kernel side. Therefore, any issues on either side need to be investigated
+   and fixed whenever necessary.
+
+   Therefore, please make sure to bring them up at netdev kernel mailing
+   list and Cc BPF maintainers for LLVM and kernel bits:
+
+     Yonghong Song <yhs@fb.com>
+     Alexei Starovoitov <ast@kernel.org>
+     Daniel Borkmann <daniel@iogearbox.net>
+
+   LLVM also has an issue tracker where BPF related bugs can be found:
+
+     https://bugs.llvm.org/buglist.cgi?quicksearch=bpf
+
+   However, it is better to reach out through mailing lists with having
+   maintainers in Cc.
+
+Q: I have added a new BPF instruction to the kernel, how can I integrate
+   it into LLVM?
+
+A: LLVM has a -mcpu selector for the BPF back end in order to allow the
+   selection of BPF instruction set extensions. By default the 'generic'
+   processor target is used, which is the base instruction set (v1) of BPF.
+
+   LLVM has an option to select -mcpu=probe where it will probe the host
+   kernel for supported BPF instruction set extensions and selects the
+   optimal set automatically.
+
+   For cross-compilation, a specific version can be select manually as well.
+
+     $ llc -march bpf -mcpu=help
+     Available CPUs for this target:
+
+       generic - Select the generic processor.
+       probe   - Select the probe processor.
+       v1      - Select the v1 processor.
+       v2      - Select the v2 processor.
+     [...]
+
+   Newly added BPF instructions to the Linux kernel need to follow the same
+   scheme, bump the instruction set version and implement probing for the
+   extensions such that -mcpu=probe users can benefit from the optimization
+   transparently when upgrading their kernels.
+
+   If you are unable to implement support for the newly added BPF instruction
+   please reach out to BPF developers for help.
+
+   By the way, the BPF kernel selftests run with -mcpu=probe for better
+   test coverage.
+
+Happy BPF hacking!
diff --git a/Documentation/cgroup-v1/cgroups.txt b/Documentation/cgroup-v1/cgroups.txt
index 308e5ff7207a..059f7063eea6 100644
--- a/Documentation/cgroup-v1/cgroups.txt
+++ b/Documentation/cgroup-v1/cgroups.txt
@@ -523,12 +523,7 @@ Accessing a task's cgroup pointer may be done in the following ways:
 Each subsystem should:
 
 - add an entry in linux/cgroup_subsys.h
-- define a cgroup_subsys object called <name>_subsys
-
-If a subsystem can be compiled as a module, it should also have in its
-module initcall a call to cgroup_load_subsys(), and in its exitcall a
-call to cgroup_unload_subsys(). It should also set its_subsys.module =
-THIS_MODULE in its .c file.
+- define a cgroup_subsys object called <name>_cgrp_subsys
 
 Each subsystem may export the following methods. The only mandatory
 methods are css_alloc/free. Any others that are null are presumed to
diff --git a/Documentation/cgroup-v1/memory.txt b/Documentation/cgroup-v1/memory.txt
index cefb63639070..a4af2e124e24 100644
--- a/Documentation/cgroup-v1/memory.txt
+++ b/Documentation/cgroup-v1/memory.txt
@@ -524,9 +524,9 @@ Note:
 	Only anonymous and swap cache memory is listed as part of 'rss' stat.
 	This should not be confused with the true 'resident set size' or the
 	amount of physical memory used by the cgroup.
-	'rss + file_mapped" will give you resident set size of cgroup.
+	'rss + mapped_file" will give you resident set size of cgroup.
 	(Note: file and shmem may be shared among other cgroups. In that case,
-	 file_mapped is accounted only when the memory cgroup is owner of page
+	 mapped_file is accounted only when the memory cgroup is owner of page
 	 cache.)
 
 5.3 swappiness
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index 779211fbb69f..74cdeaed9f7a 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -53,10 +53,14 @@ v1 is available under Documentation/cgroup-v1/.
        5-3-2. Writeback
      5-4. PID
        5-4-1. PID Interface Files
-     5-5. RDMA
-       5-5-1. RDMA Interface Files
-     5-6. Misc
-       5-6-1. perf_event
+     5-5. Device
+     5-6. RDMA
+       5-6-1. RDMA Interface Files
+     5-7. Misc
+       5-7-1. perf_event
+     5-N. Non-normative information
+       5-N-1. CPU controller root cgroup process behaviour
+       5-N-2. IO controller root cgroup process behaviour
    6. Namespace
      6-1. Basics
      6-2. The Root and Views
@@ -279,7 +283,7 @@ thread mode, the following conditions must be met.
   exempt from this requirement.
 
 Topology-wise, a cgroup can be in an invalid state.  Please consider
-the following toplogy::
+the following topology::
 
   A (threaded domain) - B (threaded) - C (domain, just created)
 
@@ -420,7 +424,9 @@ The root cgroup is exempt from this restriction.  Root contains
 processes and anonymous resource consumption which can't be associated
 with any other cgroups and requires special treatment from most
 controllers.  How resource consumption in the root cgroup is governed
-is up to each controller.
+is up to each controller (for more information on this topic please
+refer to the Non-normative information section in the Controllers
+chapter).
 
 Note that the restriction doesn't get in the way if there is no
 enabled controller in the cgroup's "cgroup.subtree_control".  This is
@@ -898,6 +904,13 @@ controller implements weight and absolute bandwidth limit models for
 normal scheduling policy and absolute bandwidth allocation model for
 realtime scheduling policy.
 
+WARNING: cgroup2 doesn't yet support control of realtime processes and
+the cpu controller can only be enabled when all RT processes are in
+the root cgroup.  Be aware that system management software may already
+have placed RT processes into nonroot cgroups during the system boot
+process, and these processes may need to be moved to the root cgroup
+before the cpu controller can be enabled.
+
 
 CPU Interface Files
 ~~~~~~~~~~~~~~~~~~~
@@ -1056,10 +1069,10 @@ PAGE_SIZE multiple when read back.
 		reached the limit and allocation was about to fail.
 
 		Depending on context result could be invocation of OOM
-		killer and retrying allocation or failing alloction.
+		killer and retrying allocation or failing allocation.
 
 		Failed allocation in its turn could be returned into
-		userspace as -ENOMEM or siletly ignored in cases like
+		userspace as -ENOMEM or silently ignored in cases like
 		disk readahead.  For now OOM in memory cgroup kills
 		tasks iff shortage has happened inside page fault.
 
@@ -1184,7 +1197,7 @@ PAGE_SIZE multiple when read back.
 	cgroups.  The default is "max".
 
 	Swap usage hard limit.  If a cgroup's swap usage reaches this
-	limit, anonymous meomry of the cgroup will not be swapped out.
+	limit, anonymous memory of the cgroup will not be swapped out.
 
 
 Usage Guidelines
@@ -1422,6 +1435,30 @@ through fork() or clone(). These will return -EAGAIN if the creation
 of a new process would cause a cgroup policy to be violated.
 
 
+Device controller
+-----------------
+
+Device controller manages access to device files. It includes both
+creation of new device files (using mknod), and access to the
+existing device files.
+
+Cgroup v2 device controller has no interface files and is implemented
+on top of cgroup BPF. To control access to device files, a user may
+create bpf programs of the BPF_CGROUP_DEVICE type and attach them
+to cgroups. On an attempt to access a device file, corresponding
+BPF programs will be executed, and depending on the return value
+the attempt will succeed or fail with -EPERM.
+
+A BPF_CGROUP_DEVICE program takes a pointer to the bpf_cgroup_dev_ctx
+structure, which describes the device access attempt: access type
+(mknod/read/write) and device (type, major and minor numbers).
+If the program returns 0, the attempt fails with -EPERM, otherwise
+it succeeds.
+
+An example of BPF_CGROUP_DEVICE program may be found in the kernel
+source tree in the tools/testing/selftests/bpf/dev_cgroup.c file.
+
+
 RDMA
 ----
 
@@ -1474,6 +1511,35 @@ always be filtered by cgroup v2 path.  The controller can still be
 moved to a legacy hierarchy after v2 hierarchy is populated.
 
 
+Non-normative information
+-------------------------
+
+This section contains information that isn't considered to be a part of
+the stable kernel API and so is subject to change.
+
+
+CPU controller root cgroup process behaviour
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+When distributing CPU cycles in the root cgroup each thread in this
+cgroup is treated as if it was hosted in a separate child cgroup of the
+root cgroup. This child cgroup weight is dependent on its thread nice
+level.
+
+For details of this mapping see sched_prio_to_weight array in
+kernel/sched/core.c file (values from this array should be scaled
+appropriately so the neutral - nice 0 - value is 100 instead of 1024).
+
+
+IO controller root cgroup process behaviour
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Root cgroup processes are hosted in an implicit leaf child node.
+When distributing IO resources this implicit child node is taken into
+account as if it was a normal child cgroup of the root cgroup with a
+weight value of 200.
+
+
 Namespace
 =========
 
diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt
index d4628174b7c5..53e51caa3347 100644
--- a/Documentation/circular-buffers.txt
+++ b/Documentation/circular-buffers.txt
@@ -220,8 +220,7 @@ before it writes the new tail pointer, which will erase the item.
 
 Note the use of READ_ONCE() and smp_load_acquire() to read the
 opposition index.  This prevents the compiler from discarding and
-reloading its cached value - which some compilers will do across
-smp_read_barrier_depends().  This isn't strictly needed if you can
+reloading its cached value.  This isn't strictly needed if you can
 be sure that the opposition index will _only_ be used the once.
 The smp_load_acquire() additionally forces the CPU to order against
 subsequent memory references.  Similarly, smp_store_release() is used
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 63857d33778c..62ac5a9f3a9f 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -88,7 +88,6 @@ finally:
     if makefile_version and makefile_patchlevel:
         version = release = makefile_version + '.' + makefile_patchlevel
     else:
-        sys.stderr.write('Warning: Could not extract kernel version\n')
         version = release = "unknown version"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
diff --git a/Documentation/errseq.rst b/Documentation/core-api/errseq.rst
index 4c29bd5afbc5..ff332e272405 100644
--- a/Documentation/errseq.rst
+++ b/Documentation/core-api/errseq.rst
@@ -1,5 +1,7 @@
+=====================
 The errseq_t datatype
 =====================
+
 An errseq_t is a way of recording errors in one place, and allowing any
 number of "subscribers" to tell whether it has changed since a previous
 point where it was sampled.
@@ -21,12 +23,13 @@ a flag to tell whether the value has been sampled since a new value was
 recorded.  That allows us to avoid bumping the counter if no one has
 sampled it since the last time an error was recorded.
 
-Thus we end up with a value that looks something like this::
+Thus we end up with a value that looks something like this:
 
-    bit:  31..13        12        11..0
-    +-----------------+----+----------------+
-    |     counter     | SF |      errno     |
-    +-----------------+----+----------------+
++--------------------------------------+----+------------------------+
+| 31..13                               | 12 | 11..0                  |
++--------------------------------------+----+------------------------+
+| counter                              | SF | errno                  |
++--------------------------------------+----+------------------------+
 
 The general idea is for "watchers" to sample an errseq_t value and keep
 it as a running cursor.  That value can later be used to tell whether
@@ -42,6 +45,7 @@ has ever been an error set since it was first initialized.
 
 API usage
 =========
+
 Let me tell you a story about a worker drone.  Now, he's a good worker
 overall, but the company is a little...management heavy.  He has to
 report to 77 supervisors today, and tomorrow the "big boss" is coming in
@@ -125,6 +129,7 @@ not usable by anyone else.
 
 Serializing errseq_t cursor updates
 ===================================
+
 Note that the errseq_t API does not protect the errseq_t cursor during a
 check_and_advance_operation. Only the canonical error code is handled
 atomically.  In a situation where more than one task might be using the
@@ -147,3 +152,8 @@ errseq_check_and_advance after taking the lock. e.g.::
 
 That avoids the spinlock in the common case where nothing has changed
 since the last time it was checked.
+
+Functions
+=========
+
+.. kernel-doc:: lib/errseq.c
diff --git a/Documentation/core-api/genericirq.rst b/Documentation/core-api/genericirq.rst
index 0054bd48be84..4da67b65cecf 100644
--- a/Documentation/core-api/genericirq.rst
+++ b/Documentation/core-api/genericirq.rst
@@ -225,9 +225,9 @@ interrupts.
 
 The following control flow is implemented (simplified excerpt)::
 
-    :c:func:`desc->irq_data.chip->irq_mask_ack`;
+    desc->irq_data.chip->irq_mask_ack();
     handle_irq_event(desc->action);
-    :c:func:`desc->irq_data.chip->irq_unmask`;
+    desc->irq_data.chip->irq_unmask();
 
 
 Default Fast EOI IRQ flow handler
@@ -239,7 +239,7 @@ which only need an EOI at the end of the handler.
 The following control flow is implemented (simplified excerpt)::
 
     handle_irq_event(desc->action);
-    :c:func:`desc->irq_data.chip->irq_eoi`;
+    desc->irq_data.chip->irq_eoi();
 
 
 Default Edge IRQ flow handler
@@ -251,15 +251,15 @@ interrupts.
 The following control flow is implemented (simplified excerpt)::
 
     if (desc->status & running) {
-        :c:func:`desc->irq_data.chip->irq_mask_ack`;
+        desc->irq_data.chip->irq_mask_ack();
         desc->status |= pending | masked;
         return;
     }
-    :c:func:`desc->irq_data.chip->irq_ack`;
+    desc->irq_data.chip->irq_ack();
     desc->status |= running;
     do {
         if (desc->status & masked)
-            :c:func:`desc->irq_data.chip->irq_unmask`;
+            desc->irq_data.chip->irq_unmask();
         desc->status &= ~pending;
         handle_irq_event(desc->action);
     } while (status & pending);
@@ -293,10 +293,10 @@ simplified version without locking.
 The following control flow is implemented (simplified excerpt)::
 
     if (desc->irq_data.chip->irq_ack)
-        :c:func:`desc->irq_data.chip->irq_ack`;
+        desc->irq_data.chip->irq_ack();
     handle_irq_event(desc->action);
     if (desc->irq_data.chip->irq_eoi)
-            :c:func:`desc->irq_data.chip->irq_eoi`;
+        desc->irq_data.chip->irq_eoi();
 
 
 EOI Edge IRQ flow handler
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index d5bbe035316d..1b1fd01990b5 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -14,6 +14,7 @@ Core utilities
    kernel-api
    assoc_array
    atomic_ops
+   refcount-vs-atomic
    cpu_hotplug
    local_ops
    workqueue
@@ -21,6 +22,8 @@ Core utilities
    flexible-arrays
    librs
    genalloc
+   errseq
+   printk-formats
 
 Interfaces for kernel debugging
 ===============================
diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst
index 2d9da6c40a4d..e7fadf02c511 100644
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -139,6 +139,21 @@ Division Functions
 .. kernel-doc:: lib/gcd.c
    :export:
 
+Sorting
+-------
+
+.. kernel-doc:: lib/sort.c
+   :export:
+
+.. kernel-doc:: lib/list_sort.c
+   :export:
+
+UUID/GUID
+---------
+
+.. kernel-doc:: lib/uuid.c
+   :export:
+
 Memory Management in Linux
 ==========================
 
diff --git a/Documentation/printk-formats.txt b/Documentation/core-api/printk-formats.rst
index 361789df51ec..934559b3c130 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/core-api/printk-formats.rst
@@ -26,79 +26,101 @@ Integer types
 		s64			%lld or %llx
 		u64			%llu or %llx
 
-If <type> is dependent on a config option for its size (e.g., ``sector_t``,
-``blkcnt_t``) or is architecture-dependent for its size (e.g., ``tcflag_t``),
-use a format specifier of its largest possible type and explicitly cast to it.
+
+If <type> is dependent on a config option for its size (e.g., sector_t,
+blkcnt_t) or is architecture-dependent for its size (e.g., tcflag_t), use a
+format specifier of its largest possible type and explicitly cast to it.
 
 Example::
 
 	printk("test: sector number/total blocks: %llu/%llu\n",
 		(unsigned long long)sector, (unsigned long long)blockcount);
 
-Reminder: ``sizeof()`` result is of type ``size_t``.
+Reminder: sizeof() returns type size_t.
 
-The kernel's printf does not support ``%n``. For obvious reasons, floating
-point formats (``%e, %f, %g, %a``) are also not recognized. Use of any
+The kernel's printf does not support %n. Floating point formats (%e, %f,
+%g, %a) are also not recognized, for obvious reasons. Use of any
 unsupported specifier or length qualifier results in a WARN and early
-return from vsnprintf.
+return from vsnprintf().
+
+Pointer types
+=============
 
-Raw pointer value SHOULD be printed with %p. The kernel supports
-the following extended format specifiers for pointer types:
+A raw pointer value may be printed with %p which will hash the address
+before printing. The kernel also supports extended specifiers for printing
+pointers of different types.
+
+Plain Pointers
+--------------
+
+::
+
+	%p	abcdef12 or 00000000abcdef12
+
+Pointers printed without a specifier extension (i.e unadorned %p) are
+hashed to prevent leaking information about the kernel memory layout. This
+has the added benefit of providing a unique identifier. On 64-bit machines
+the first 32 bits are zeroed. If you *really* want the address see %px
+below.
 
 Symbols/Function Pointers
-=========================
+-------------------------
 
 ::
 
+	%pS	versatile_init+0x0/0x110
+	%ps	versatile_init
 	%pF	versatile_init+0x0/0x110
 	%pf	versatile_init
-	%pS	versatile_init+0x0/0x110
 	%pSR	versatile_init+0x9/0x110
 		(with __builtin_extract_return_addr() translation)
-	%ps	versatile_init
 	%pB	prev_fn_of_versatile_init+0x88/0x88
 
-The ``F`` and ``f`` specifiers are for printing function pointers,
-for example, f->func, &gettimeofday. They have the same result as
-``S`` and ``s`` specifiers. But they do an extra conversion on
-ia64, ppc64 and parisc64 architectures where the function pointers
-are actually function descriptors.
 
-The ``S`` and ``s`` specifiers can be used for printing symbols
-from direct addresses, for example, __builtin_return_address(0),
-(void *)regs->ip. They result in the symbol name with (``S``) or
-without (``s``) offsets. If KALLSYMS are disabled then the symbol
-address is printed instead.
+The ``S`` and ``s`` specifiers are used for printing a pointer in symbolic
+format. They result in the symbol name with (S) or without (s)
+offsets. If KALLSYMS are disabled then the symbol address is printed instead.
+
+Note, that the ``F`` and ``f`` specifiers are identical to ``S`` (``s``)
+and thus deprecated. We have ``F`` and ``f`` because on ia64, ppc64 and
+parisc64 function pointers are indirect and, in fact, are function
+descriptors, which require additional dereferencing before we can lookup
+the symbol. As of now, ``S`` and ``s`` perform dereferencing on those
+platforms (when needed), so ``F`` and ``f`` exist for compatibility
+reasons only.
 
 The ``B`` specifier results in the symbol name with offsets and should be
 used when printing stack backtraces. The specifier takes into
 consideration the effect of compiler optimisations which may occur
-when tail-call``s are used and marked with the noreturn GCC attribute.
-
-Examples::
-
-	printk("Going to call: %pF\n", gettimeofday);
-	printk("Going to call: %pF\n", p->func);
-	printk("%s: called from %pS\n", __func__, (void *)_RET_IP_);
-	printk("%s: called from %pS\n", __func__,
-				(void *)__builtin_return_address(0));
-	printk("Faulted at %pS\n", (void *)regs->ip);
-	printk(" %s%pB\n", (reliable ? "" : "? "), (void *)*stack);
-
+when tail-calls are used and marked with the noreturn GCC attribute.
 
 Kernel Pointers
-===============
+---------------
 
 ::
 
-	%pK	0x01234567 or 0x0123456789abcdef
+	%pK	01234567 or 0123456789abcdef
 
 For printing kernel pointers which should be hidden from unprivileged
-users. The behaviour of ``%pK`` depends on the ``kptr_restrict sysctl`` - see
+users. The behaviour of %pK depends on the kptr_restrict sysctl - see
 Documentation/sysctl/kernel.txt for more details.
 
+Unmodified Addresses
+--------------------
+
+::
+
+	%px	01234567 or 0123456789abcdef
+
+For printing pointers when you *really* want to print the address. Please
+consider whether or not you are leaking sensitive information about the
+kernel memory layout before printing pointers with %px. %px is functionally
+equivalent to %lx (or %lu). %px is preferred because it is more uniquely
+grep'able. If in the future we need to modify the way the kernel handles
+printing pointers we will be better equipped to find the call sites.
+
 Struct Resources
-================
+----------------
 
 ::
 
@@ -108,32 +130,37 @@ Struct Resources
 		[mem 0x0000000060000000-0x000000006fffffff pref]
 
 For printing struct resources. The ``R`` and ``r`` specifiers result in a
-printed resource with (``R``) or without (``r``) a decoded flags member.
+printed resource with (R) or without (r) a decoded flags member.
+
 Passed by reference.
 
-Physical addresses types ``phys_addr_t``
-========================================
+Physical address types phys_addr_t
+----------------------------------
 
 ::
 
 	%pa[p]	0x01234567 or 0x0123456789abcdef
 
-For printing a ``phys_addr_t`` type (and its derivatives, such as
-``resource_size_t``) which can vary based on build options, regardless of
-the width of the CPU data path. Passed by reference.
+For printing a phys_addr_t type (and its derivatives, such as
+resource_size_t) which can vary based on build options, regardless of the
+width of the CPU data path.
+
+Passed by reference.
 
-DMA addresses types ``dma_addr_t``
-==================================
+DMA address types dma_addr_t
+----------------------------
 
 ::
 
 	%pad	0x01234567 or 0x0123456789abcdef
 
-For printing a ``dma_addr_t`` type which can vary based on build options,
-regardless of the width of the CPU data path. Passed by reference.
+For printing a dma_addr_t type which can vary based on build options,
+regardless of the width of the CPU data path.
+
+Passed by reference.
 
 Raw buffer as an escaped string
-===============================
+-------------------------------
 
 ::
 
@@ -143,8 +170,8 @@ For printing raw buffer as an escaped string. For the following buffer::
 
 		1b 62 20 5c 43 07 22 90 0d 5d
 
-few examples show how the conversion would be done (the result string
-without surrounding quotes)::
+A few examples show how the conversion would be done (excluding surrounding
+quotes)::
 
 		%*pE		"\eb \C\a"\220\r]"
 		%*pEhp		"\x1bb \C\x07"\x90\x0d]"
@@ -154,23 +181,23 @@ The conversion rules are applied according to an optional combination
 of flags (see :c:func:`string_escape_mem` kernel documentation for the
 details):
 
-	- ``a`` - ESCAPE_ANY
-	- ``c`` - ESCAPE_SPECIAL
-	- ``h`` - ESCAPE_HEX
-	- ``n`` - ESCAPE_NULL
-	- ``o`` - ESCAPE_OCTAL
-	- ``p`` - ESCAPE_NP
-	- ``s`` - ESCAPE_SPACE
+	- a - ESCAPE_ANY
+	- c - ESCAPE_SPECIAL
+	- h - ESCAPE_HEX
+	- n - ESCAPE_NULL
+	- o - ESCAPE_OCTAL
+	- p - ESCAPE_NP
+	- s - ESCAPE_SPACE
 
 By default ESCAPE_ANY_NP is used.
 
 ESCAPE_ANY_NP is the sane choice for many cases, in particularly for
 printing SSIDs.
 
-If field width is omitted the 1 byte only will be escaped.
+If field width is omitted then 1 byte only will be escaped.
 
 Raw buffer as a hex string
-==========================
+--------------------------
 
 ::
 
@@ -179,12 +206,12 @@ Raw buffer as a hex string
 	%*phD	00-01-02- ... -3f
 	%*phN	000102 ... 3f
 
-For printing a small buffers (up to 64 bytes long) as a hex string with
-certain separator. For the larger buffers consider to use
+For printing small buffers (up to 64 bytes long) as a hex string with a
+certain separator. For larger buffers consider using
 :c:func:`print_hex_dump`.
 
 MAC/FDDI addresses
-==================
+------------------
 
 ::
 
@@ -195,11 +222,11 @@ MAC/FDDI addresses
 	%pmR	050403020100
 
 For printing 6-byte MAC/FDDI addresses in hex notation. The ``M`` and ``m``
-specifiers result in a printed address with (``M``) or without (``m``) byte
-separators. The default byte separator is the colon (``:``).
+specifiers result in a printed address with (M) or without (m) byte
+separators. The default byte separator is the colon (:).
 
 Where FDDI addresses are concerned the ``F`` specifier can be used after
-the ``M`` specifier to use dash (``-``) separators instead of the default
+the ``M`` specifier to use dash (-) separators instead of the default
 separator.
 
 For Bluetooth addresses the ``R`` specifier shall be used after the ``M``
@@ -209,7 +236,7 @@ of Bluetooth addresses which are in the little endian order.
 Passed by reference.
 
 IPv4 addresses
-==============
+--------------
 
 ::
 
@@ -218,8 +245,8 @@ IPv4 addresses
 	%p[Ii]4[hnbl]
 
 For printing IPv4 dot-separated decimal addresses. The ``I4`` and ``i4``
-specifiers result in a printed address with (``i4``) or without (``I4``)
-leading zeros.
+specifiers result in a printed address with (i4) or without (I4) leading
+zeros.
 
 The additional ``h``, ``n``, ``b``, and ``l`` specifiers are used to specify
 host, network, big or little endian order addresses respectively. Where
@@ -228,7 +255,7 @@ no specifier is provided the default network/big endian order is used.
 Passed by reference.
 
 IPv6 addresses
-==============
+--------------
 
 ::
 
@@ -237,7 +264,7 @@ IPv6 addresses
 	%pI6c	1:2:3:4:5:6:7:8
 
 For printing IPv6 network-order 16-bit hex addresses. The ``I6`` and ``i6``
-specifiers result in a printed address with (``I6``) or without (``i6``)
+specifiers result in a printed address with (I6) or without (i6)
 colon-separators. Leading zeros are always used.
 
 The additional ``c`` specifier can be used with the ``I`` specifier to
@@ -247,7 +274,7 @@ http://tools.ietf.org/html/rfc5952
 Passed by reference.
 
 IPv4/IPv6 addresses (generic, with port, flowinfo, scope)
-=========================================================
+---------------------------------------------------------
 
 ::
 
@@ -257,8 +284,8 @@ IPv4/IPv6 addresses (generic, with port, flowinfo, scope)
 	%pISpc	1.2.3.4:12345	or [1:2:3:4:5:6:7:8]:12345
 	%p[Ii]S[pfschnbl]
 
-For printing an IP address without the need to distinguish whether it``s
-of type AF_INET or AF_INET6, a pointer to a valid ``struct sockaddr``,
+For printing an IP address without the need to distinguish whether it's of
+type AF_INET or AF_INET6. A pointer to a valid struct sockaddr,
 specified through ``IS`` or ``iS``, can be passed to this format specifier.
 
 The additional ``p``, ``f``, and ``s`` specifiers are used to specify port
@@ -284,7 +311,7 @@ Further examples::
 	%pISpfc		1.2.3.4:12345	or [1:2:3:4:5:6:7:8]:12345/123456789
 
 UUID/GUID addresses
-===================
+-------------------
 
 ::
 
@@ -293,33 +320,33 @@ UUID/GUID addresses
 	%pUl	03020100-0504-0706-0809-0a0b0c0e0e0f
 	%pUL	03020100-0504-0706-0809-0A0B0C0E0E0F
 
-For printing 16-byte UUID/GUIDs addresses. The additional 'l', 'L',
-'b' and 'B' specifiers are used to specify a little endian order in
-lower ('l') or upper case ('L') hex characters - and big endian order
-in lower ('b') or upper case ('B') hex characters.
+For printing 16-byte UUID/GUIDs addresses. The additional ``l``, ``L``,
+``b`` and ``B`` specifiers are used to specify a little endian order in
+lower (l) or upper case (L) hex notation - and big endian order in lower (b)
+or upper case (B) hex notation.
 
 Where no additional specifiers are used the default big endian
-order with lower case hex characters will be printed.
+order with lower case hex notation will be printed.
 
 Passed by reference.
 
 dentry names
-============
+------------
 
 ::
 
 	%pd{,2,3,4}
 	%pD{,2,3,4}
 
-For printing dentry name; if we race with :c:func:`d_move`, the name might be
-a mix of old and new ones, but it won't oops.  ``%pd`` dentry is a safer
-equivalent of ``%s`` ``dentry->d_name.name`` we used to use, ``%pd<n>`` prints
-``n`` last components.  ``%pD`` does the same thing for struct file.
+For printing dentry name; if we race with :c:func:`d_move`, the name might
+be a mix of old and new ones, but it won't oops.  %pd dentry is a safer
+equivalent of %s dentry->d_name.name we used to use, %pd<n> prints ``n``
+last components.  %pD does the same thing for struct file.
 
 Passed by reference.
 
 block_device names
-==================
+------------------
 
 ::
 
@@ -328,7 +355,7 @@ block_device names
 For printing name of block_device pointers.
 
 struct va_format
-================
+----------------
 
 ::
 
@@ -350,31 +377,27 @@ correctness of the format string and va_list arguments.
 Passed by reference.
 
 kobjects
-========
+--------
 
 ::
 
-	%pO
+	%pOF[fnpPcCF]
 
-	Base specifier for kobject based structs. Must be followed with
-	character for specific type of kobject as listed below:
 
-	Device tree nodes:
+For printing kobject based structs (device nodes). Default behaviour is
+equivalent to %pOFf.
 
-	%pOF[fnpPcCF]
+	- f - device node full_name
+	- n - device node name
+	- p - device node phandle
+	- P - device node path spec (name + @unit)
+	- F - device node flags
+	- c - major compatible string
+	- C - full compatible string
 
-	For printing device tree nodes. The optional arguments are:
-	    f device node full_name
-	    n device node name
-	    p device node phandle
-	    P device node path spec (name + @unit)
-	    F device node flags
-	    c major compatible string
-	    C full compatible string
-	Without any arguments prints full_name (same as %pOFf)
-	The separator when using multiple arguments is ':'
+The separator when using multiple arguments is ':'
 
-	Examples:
+Examples::
 
 	%pOF	/foo/bar@0			- Node full name
 	%pOFf	/foo/bar@0			- Same as above
@@ -387,11 +410,10 @@ kobjects
 							P - Populated
 							B - Populated bus
 
-	Passed by reference.
-
+Passed by reference.
 
 struct clk
-==========
+----------
 
 ::
 
@@ -399,14 +421,14 @@ struct clk
 	%pCn	pll1
 	%pCr	1560000000
 
-For printing struct clk structures. ``%pC`` and ``%pCn`` print the name
+For printing struct clk structures. %pC and %pCn print the name
 (Common Clock Framework) or address (legacy clock framework) of the
-structure; ``%pCr`` prints the current clock rate.
+structure; %pCr prints the current clock rate.
 
 Passed by reference.
 
 bitmap and its derivatives such as cpumask and nodemask
-=======================================================
+-------------------------------------------------------
 
 ::
 
@@ -414,13 +436,13 @@ bitmap and its derivatives such as cpumask and nodemask
 	%*pbl	0,3-6,8-10
 
 For printing bitmap and its derivatives such as cpumask and nodemask,
-``%*pb`` output the bitmap with field width as the number of bits and ``%*pbl``
+%*pb outputs the bitmap with field width as the number of bits and %*pbl
 output the bitmap as range list with field width as the number of bits.
 
 Passed by reference.
 
 Flags bitfields such as page flags, gfp_flags
-=============================================
+---------------------------------------------
 
 ::
 
@@ -434,14 +456,14 @@ character. Currently supported are [p]age flags, [v]ma_flags (both
 expect ``unsigned long *``) and [g]fp_flags (expects ``gfp_t *``). The flag
 names and print order depends on the particular	type.
 
-Note that this format should not be used directly in :c:func:`TP_printk()` part
-of a tracepoint. Instead, use the ``show_*_flags()`` functions from
-<trace/events/mmflags.h>.
+Note that this format should not be used directly in the
+:c:func:`TP_printk()` part of a tracepoint. Instead, use the show_*_flags()
+functions from <trace/events/mmflags.h>.
 
 Passed by reference.
 
 Network device features
-=======================
+-----------------------
 
 ::
 
@@ -451,8 +473,10 @@ For printing netdev_features_t.
 
 Passed by reference.
 
-If you add other ``%p`` extensions, please extend lib/test_printf.c with
-one or more test cases, if at all feasible.
+Thanks
+======
 
+If you add other %p extensions, please extend <lib/test_printf.c> with
+one or more test cases, if at all feasible.
 
 Thank you for your cooperation and attention.
diff --git a/Documentation/core-api/refcount-vs-atomic.rst b/Documentation/core-api/refcount-vs-atomic.rst
new file mode 100644
index 000000000000..83351c258cdb
--- /dev/null
+++ b/Documentation/core-api/refcount-vs-atomic.rst
@@ -0,0 +1,150 @@
+===================================
+refcount_t API compared to atomic_t
+===================================
+
+.. contents:: :local:
+
+Introduction
+============
+
+The goal of refcount_t API is to provide a minimal API for implementing
+an object's reference counters. While a generic architecture-independent
+implementation from lib/refcount.c uses atomic operations underneath,
+there are a number of differences between some of the ``refcount_*()`` and
+``atomic_*()`` functions with regards to the memory ordering guarantees.
+This document outlines the differences and provides respective examples
+in order to help maintainers validate their code against the change in
+these memory ordering guarantees.
+
+The terms used through this document try to follow the formal LKMM defined in
+github.com/aparri/memory-model/blob/master/Documentation/explanation.txt
+
+memory-barriers.txt and atomic_t.txt provide more background to the
+memory ordering in general and for atomic operations specifically.
+
+Relevant types of memory ordering
+=================================
+
+.. note:: The following section only covers some of the memory
+   ordering types that are relevant for the atomics and reference
+   counters and used through this document. For a much broader picture
+   please consult memory-barriers.txt document.
+
+In the absence of any memory ordering guarantees (i.e. fully unordered)
+atomics & refcounters only provide atomicity and
+program order (po) relation (on the same CPU). It guarantees that
+each ``atomic_*()`` and ``refcount_*()`` operation is atomic and instructions
+are executed in program order on a single CPU.
+This is implemented using :c:func:`READ_ONCE`/:c:func:`WRITE_ONCE` and
+compare-and-swap primitives.
+
+A strong (full) memory ordering guarantees that all prior loads and
+stores (all po-earlier instructions) on the same CPU are completed
+before any po-later instruction is executed on the same CPU.
+It also guarantees that all po-earlier stores on the same CPU
+and all propagated stores from other CPUs must propagate to all
+other CPUs before any po-later instruction is executed on the original
+CPU (A-cumulative property). This is implemented using :c:func:`smp_mb`.
+
+A RELEASE memory ordering guarantees that all prior loads and
+stores (all po-earlier instructions) on the same CPU are completed
+before the operation. It also guarantees that all po-earlier
+stores on the same CPU and all propagated stores from other CPUs
+must propagate to all other CPUs before the release operation
+(A-cumulative property). This is implemented using
+:c:func:`smp_store_release`.
+
+A control dependency (on success) for refcounters guarantees that
+if a reference for an object was successfully obtained (reference
+counter increment or addition happened, function returned true),
+then further stores are ordered against this operation.
+Control dependency on stores are not implemented using any explicit
+barriers, but rely on CPU not to speculate on stores. This is only
+a single CPU relation and provides no guarantees for other CPUs.
+
+
+Comparison of functions
+=======================
+
+case 1) - non-"Read/Modify/Write" (RMW) ops
+-------------------------------------------
+
+Function changes:
+
+ * :c:func:`atomic_set` --> :c:func:`refcount_set`
+ * :c:func:`atomic_read` --> :c:func:`refcount_read`
+
+Memory ordering guarantee changes:
+
+ * none (both fully unordered)
+
+
+case 2) - increment-based ops that return no value
+--------------------------------------------------
+
+Function changes:
+
+ * :c:func:`atomic_inc` --> :c:func:`refcount_inc`
+ * :c:func:`atomic_add` --> :c:func:`refcount_add`
+
+Memory ordering guarantee changes:
+
+ * none (both fully unordered)
+
+case 3) - decrement-based RMW ops that return no value
+------------------------------------------------------
+
+Function changes:
+
+ * :c:func:`atomic_dec` --> :c:func:`refcount_dec`
+
+Memory ordering guarantee changes:
+
+ * fully unordered --> RELEASE ordering
+
+
+case 4) - increment-based RMW ops that return a value
+-----------------------------------------------------
+
+Function changes:
+
+ * :c:func:`atomic_inc_not_zero` --> :c:func:`refcount_inc_not_zero`
+ * no atomic counterpart --> :c:func:`refcount_add_not_zero`
+
+Memory ordering guarantees changes:
+
+ * fully ordered --> control dependency on success for stores
+
+.. note:: We really assume here that necessary ordering is provided as a
+   result of obtaining pointer to the object!
+
+
+case 5) - decrement-based RMW ops that return a value
+-----------------------------------------------------
+
+Function changes:
+
+ * :c:func:`atomic_dec_and_test` --> :c:func:`refcount_dec_and_test`
+ * :c:func:`atomic_sub_and_test` --> :c:func:`refcount_sub_and_test`
+ * no atomic counterpart --> :c:func:`refcount_dec_if_one`
+ * ``atomic_add_unless(&var, -1, 1)`` --> ``refcount_dec_not_one(&var)``
+
+Memory ordering guarantees changes:
+
+ * fully ordered --> RELEASE ordering + control dependency
+
+.. note:: :c:func:`atomic_add_unless` only provides full order on success.
+
+
+case 6) - lock-based RMW
+------------------------
+
+Function changes:
+
+ * :c:func:`atomic_dec_and_lock` --> :c:func:`refcount_dec_and_lock`
+ * :c:func:`atomic_dec_and_mutex_lock` --> :c:func:`refcount_dec_and_mutex_lock`
+
+Memory ordering guarantees changes:
+
+ * fully ordered --> RELEASE ordering + control dependency + hold
+   :c:func:`spin_lock` on success
diff --git a/Documentation/device-mapper/cache-policies.txt b/Documentation/device-mapper/cache-policies.txt
index d3ca8af21a31..86786d87d9a8 100644
--- a/Documentation/device-mapper/cache-policies.txt
+++ b/Documentation/device-mapper/cache-policies.txt
@@ -60,7 +60,7 @@ Memory usage:
 The mq policy used a lot of memory; 88 bytes per cache block on a 64
 bit machine.
 
-smq uses 28bit indexes to implement it's data structures rather than
+smq uses 28bit indexes to implement its data structures rather than
 pointers.  It avoids storing an explicit hit count for each block.  It
 has a 'hotspot' queue, rather than a pre-cache, which uses a quarter of
 the entries (each hotspot block covers a larger area than a single
@@ -84,7 +84,7 @@ resulting in better promotion/demotion decisions.
 
 Adaptability:
 The mq policy maintained a hit count for each cache block.  For a
-different block to get promoted to the cache it's hit count has to
+different block to get promoted to the cache its hit count has to
 exceed the lowest currently in the cache.  This meant it could take a
 long time for the cache to adapt between varying IO patterns.
 
diff --git a/Documentation/device-mapper/cache.txt b/Documentation/device-mapper/cache.txt
index cdfd0feb294e..ff0841711fd5 100644
--- a/Documentation/device-mapper/cache.txt
+++ b/Documentation/device-mapper/cache.txt
@@ -59,7 +59,7 @@ Fixed block size
 The origin is divided up into blocks of a fixed size.  This block size
 is configurable when you first create the cache.  Typically we've been
 using block sizes of 256KB - 1024KB.  The block size must be between 64
-(32KB) and 2097152 (1GB) and a multiple of 64 (32KB).
+sectors (32KB) and 2097152 sectors (1GB) and a multiple of 64 sectors (32KB).
 
 Having a fixed block size simplifies the target a lot.  But it is
 something of a compromise.  For instance, a small part of a block may be
@@ -119,7 +119,7 @@ doing here to avoid migrating during those peak io moments.
 
 For the time being, a message "migration_threshold <#sectors>"
 can be used to set the maximum number of sectors being migrated,
-the default being 204800 sectors (or 100MB).
+the default being 2048 sectors (1MB).
 
 Updating on-disk metadata
 -------------------------
@@ -143,11 +143,6 @@ the policy how big this chunk is, but it should be kept small.  Like the
 dirty flags this data is lost if there's a crash so a safe fallback
 value should always be possible.
 
-For instance, the 'mq' policy, which is currently the default policy,
-uses this facility to store the hit count of the cache blocks.  If
-there's a crash this information will be lost, which means the cache
-may be less efficient until those hit counts are regenerated.
-
 Policy hints affect performance, not correctness.
 
 Policy messaging
diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index 32df07e29f68..390c145f01d7 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -343,5 +343,8 @@ Version History
 1.11.0  Fix table line argument order
 	(wrong raid10_copies/raid10_format sequence)
 1.11.1  Add raid4/5/6 journal write-back support via journal_mode option
-1.12.1  fix for MD deadlock between mddev_suspend() and md_write_start() available
+1.12.1  Fix for MD deadlock between mddev_suspend() and md_write_start() available
 1.13.0  Fix dev_health status at end of "recover" (was 'a', now 'A')
+1.13.1  Fix deadlock caused by early md_stop_writes().  Also fix size an
+	state races.
+1.13.2  Fix raid redundancy validation and avoid keeping raid set frozen
diff --git a/Documentation/device-mapper/snapshot.txt b/Documentation/device-mapper/snapshot.txt
index ad6949bff2e3..b8bbb516f989 100644
--- a/Documentation/device-mapper/snapshot.txt
+++ b/Documentation/device-mapper/snapshot.txt
@@ -49,6 +49,10 @@ The difference between persistent and transient is with transient
 snapshots less metadata must be saved on disk - they can be kept in
 memory by the kernel.
 
+When loading or unloading the snapshot target, the corresponding
+snapshot-origin or snapshot-merge target must be suspended. A failure to
+suspend the origin target could result in data corruption.
+
 
 * snapshot-merge <origin> <COW device> <persistent> <chunksize>
 
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 1699a55b7b70..4bcd4b7f79f9 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -112,9 +112,11 @@ $low_water_mark is expressed in blocks of size $data_block_size.  If
 free space on the data device drops below this level then a dm event
 will be triggered which a userspace daemon should catch allowing it to
 extend the pool device.  Only one such event will be sent.
-Resuming a device with a new table itself triggers an event so the
-userspace daemon can use this to detect a situation where a new table
-already exceeds the threshold.
+
+No special event is triggered if a just resumed device's free space is below
+the low water mark. However, resuming a device always triggers an
+event; a userspace daemon should verify that free space exceeds the low
+water mark when handling this event.
 
 A low water mark for the metadata device is maintained in the kernel and
 will trigger a dm event if free space on the metadata device drops below
@@ -274,7 +276,8 @@ ii) Status
 
     <transaction id> <used metadata blocks>/<total metadata blocks>
     <used data blocks>/<total data blocks> <held metadata root>
-    [no_]discard_passdown ro|rw
+    ro|rw|out_of_data_space [no_]discard_passdown [error|queue]_if_no_space
+    needs_check|-
 
     transaction id:
 	A 64-bit number used by userspace to help synchronise with metadata
@@ -394,3 +397,6 @@ ii) Status
 	If the pool has encountered device errors and failed, the status
 	will just contain the string 'Fail'.  The userspace recovery
 	tools should then be used.
+
+    In the case where <nr mapped sectors> is 0, there is no highest
+    mapped sector and the value of <highest mapped sector> is unspecified.
diff --git a/Documentation/device-mapper/unstriped.txt b/Documentation/device-mapper/unstriped.txt
new file mode 100644
index 000000000000..0b2a306c54ee
--- /dev/null
+++ b/Documentation/device-mapper/unstriped.txt
@@ -0,0 +1,124 @@
+Introduction
+============
+
+The device-mapper "unstriped" target provides a transparent mechanism to
+unstripe a device-mapper "striped" target to access the underlying disks
+without having to touch the true backing block-device.  It can also be
+used to unstripe a hardware RAID-0 to access backing disks.
+
+Parameters:
+<number of stripes> <chunk size> <stripe #> <dev_path> <offset>
+
+<number of stripes>
+        The number of stripes in the RAID 0.
+
+<chunk size>
+	The amount of 512B sectors in the chunk striping.
+
+<dev_path>
+	The block device you wish to unstripe.
+
+<stripe #>
+        The stripe number within the device that corresponds to physical
+        drive you wish to unstripe.  This must be 0 indexed.
+
+
+Why use this module?
+====================
+
+An example of undoing an existing dm-stripe
+-------------------------------------------
+
+This small bash script will setup 4 loop devices and use the existing
+striped target to combine the 4 devices into one.  It then will use
+the unstriped target ontop of the striped device to access the
+individual backing loop devices.  We write data to the newly exposed
+unstriped devices and verify the data written matches the correct
+underlying device on the striped array.
+
+#!/bin/bash
+
+MEMBER_SIZE=$((128 * 1024 * 1024))
+NUM=4
+SEQ_END=$((${NUM}-1))
+CHUNK=256
+BS=4096
+
+RAID_SIZE=$((${MEMBER_SIZE}*${NUM}/512))
+DM_PARMS="0 ${RAID_SIZE} striped ${NUM} ${CHUNK}"
+COUNT=$((${MEMBER_SIZE} / ${BS}))
+
+for i in $(seq 0 ${SEQ_END}); do
+  dd if=/dev/zero of=member-${i} bs=${MEMBER_SIZE} count=1 oflag=direct
+  losetup /dev/loop${i} member-${i}
+  DM_PARMS+=" /dev/loop${i} 0"
+done
+
+echo $DM_PARMS | dmsetup create raid0
+for i in $(seq 0 ${SEQ_END}); do
+  echo "0 1 unstriped ${NUM} ${CHUNK} ${i} /dev/mapper/raid0 0" | dmsetup create set-${i}
+done;
+
+for i in $(seq 0 ${SEQ_END}); do
+  dd if=/dev/urandom of=/dev/mapper/set-${i} bs=${BS} count=${COUNT} oflag=direct
+  diff /dev/mapper/set-${i} member-${i}
+done;
+
+for i in $(seq 0 ${SEQ_END}); do
+  dmsetup remove set-${i}
+done
+
+dmsetup remove raid0
+
+for i in $(seq 0 ${SEQ_END}); do
+  losetup -d /dev/loop${i}
+  rm -f member-${i}
+done
+
+Another example
+---------------
+
+Intel NVMe drives contain two cores on the physical device.
+Each core of the drive has segregated access to its LBA range.
+The current LBA model has a RAID 0 128k chunk on each core, resulting
+in a 256k stripe across the two cores:
+
+   Core 0:       Core 1:
+  __________    __________
+  | LBA 512|    | LBA 768|
+  | LBA 0  |    | LBA 256|
+  ----------    ----------
+
+The purpose of this unstriping is to provide better QoS in noisy
+neighbor environments. When two partitions are created on the
+aggregate drive without this unstriping, reads on one partition
+can affect writes on another partition.  This is because the partitions
+are striped across the two cores.  When we unstripe this hardware RAID 0
+and make partitions on each new exposed device the two partitions are now
+physically separated.
+
+With the dm-unstriped target we're able to segregate an fio script that
+has read and write jobs that are independent of each other.  Compared to
+when we run the test on a combined drive with partitions, we were able
+to get a 92% reduction in read latency using this device mapper target.
+
+
+Example dmsetup usage
+=====================
+
+unstriped ontop of Intel NVMe device that has 2 cores
+-----------------------------------------------------
+dmsetup create nvmset0 --table '0 512 unstriped 2 256 0 /dev/nvme0n1 0'
+dmsetup create nvmset1 --table '0 512 unstriped 2 256 1 /dev/nvme0n1 0'
+
+There will now be two devices that expose Intel NVMe core 0 and 1
+respectively:
+/dev/mapper/nvmset0
+/dev/mapper/nvmset1
+
+unstriped ontop of striped with 4 drives using 128K chunk size
+--------------------------------------------------------------
+dmsetup create raid_disk0 --table '0 512 unstriped 4 256 0 /dev/mapper/striped 0'
+dmsetup create raid_disk1 --table '0 512 unstriped 4 256 1 /dev/mapper/striped 0'
+dmsetup create raid_disk2 --table '0 512 unstriped 4 256 2 /dev/mapper/striped 0'
+dmsetup create raid_disk3 --table '0 512 unstriped 4 256 3 /dev/mapper/striped 0'
diff --git a/Documentation/devicetree/bindings/arm/actions.txt b/Documentation/devicetree/bindings/arm/actions.txt
index ced764a8549e..d54f33c4e0da 100644
--- a/Documentation/devicetree/bindings/arm/actions.txt
+++ b/Documentation/devicetree/bindings/arm/actions.txt
@@ -21,10 +21,26 @@ Boards:
 
 Root node property compatible must contain, depending on board:
 
+ - Allo.com Sparky: "allo,sparky"
  - Cubietech CubieBoard6: "cubietech,cubieboard6"
  - LeMaker Guitar Base Board rev. B: "lemaker,guitar-bb-rev-b", "lemaker,guitar"
 
 
+S700 SoC
+========
+
+Required root node properties:
+
+- compatible :  must contain "actions,s700"
+
+
+Boards:
+
+Root node property compatible must contain, depending on board:
+
+ - Cubietech CubieBoard7: "cubietech,cubieboard7"
+
+
 S900 SoC
 ========
 
diff --git a/Documentation/devicetree/bindings/arm/arm-dsu-pmu.txt b/Documentation/devicetree/bindings/arm/arm-dsu-pmu.txt
new file mode 100644
index 000000000000..6efabba530f1
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/arm-dsu-pmu.txt
@@ -0,0 +1,27 @@
+* ARM DynamIQ Shared Unit (DSU) Performance Monitor Unit (PMU)
+
+ARM DyanmIQ Shared Unit (DSU) integrates one or more CPU cores
+with a shared L3 memory system, control logic and external interfaces to
+form a multicore cluster. The PMU enables to gather various statistics on
+the operations of the DSU. The PMU provides independent 32bit counters that
+can count any of the supported events, along with a 64bit cycle counter.
+The PMU is accessed via CPU system registers and has no MMIO component.
+
+** DSU PMU required properties:
+
+- compatible	: should be one of :
+
+		"arm,dsu-pmu"
+
+- interrupts	: Exactly 1 SPI must be listed.
+
+- cpus		: List of phandles for the CPUs connected to this DSU instance.
+
+
+** Example:
+
+dsu-pmu-0 {
+	compatible = "arm,dsu-pmu";
+	interrupts = <GIC_SPI 02 IRQ_TYPE_LEVEL_HIGH>;
+	cpus = <&cpu_0>, <&cpu_1>;
+};
diff --git a/Documentation/devicetree/bindings/arm/atmel-at91.txt b/Documentation/devicetree/bindings/arm/atmel-at91.txt
index 91cb8e4f2a4f..31220b54d85d 100644
--- a/Documentation/devicetree/bindings/arm/atmel-at91.txt
+++ b/Documentation/devicetree/bindings/arm/atmel-at91.txt
@@ -90,38 +90,6 @@ System Timer (ST) required properties:
 Its subnodes can be:
 - watchdog: compatible should be "atmel,at91rm9200-wdt"
 
-TC/TCLIB Timer required properties:
-- compatible: Should be "atmel,<chip>-tcb".
-  <chip> can be "at91rm9200" or "at91sam9x5"
-- reg: Should contain registers location and length
-- interrupts: Should contain all interrupts for the TC block
-  Note that you can specify several interrupt cells if the TC
-  block has one interrupt per channel.
-- clock-names: tuple listing input clock names.
-	Required elements: "t0_clk", "slow_clk"
-	Optional elements: "t1_clk", "t2_clk"
-- clocks: phandles to input clocks.
-
-Examples:
-
-One interrupt per TC block:
-	tcb0: timer@fff7c000 {
-		compatible = "atmel,at91rm9200-tcb";
-		reg = <0xfff7c000 0x100>;
-		interrupts = <18 4>;
-		clocks = <&tcb0_clk>;
-		clock-names = "t0_clk";
-	};
-
-One interrupt per TC channel in a TC block:
-	tcb1: timer@fffdc000 {
-		compatible = "atmel,at91rm9200-tcb";
-		reg = <0xfffdc000 0x100>;
-		interrupts = <26 4 27 4 28 4>;
-		clocks = <&tcb1_clk>;
-		clock-names = "t0_clk";
-	};
-
 RSTC Reset Controller required properties:
 - compatible: Should be "atmel,<chip>-rstc".
   <chip> can be "at91sam9260" or "at91sam9g45" or "sama5d3"
diff --git a/Documentation/devicetree/bindings/arm/axentia.txt b/Documentation/devicetree/bindings/arm/axentia.txt
index ea3fb96ae465..de58f2463880 100644
--- a/Documentation/devicetree/bindings/arm/axentia.txt
+++ b/Documentation/devicetree/bindings/arm/axentia.txt
@@ -10,6 +10,15 @@ compatible = "axentia,linea",
 and following the rules from atmel-at91.txt for a sama5d31 SoC.
 
 
+Nattis v2 board with Natte v2 power board
+-----------------------------------------
+
+Required root node properties:
+compatible = "axentia,nattis-2", "axentia,natte-2", "axentia,linea",
+	     "atmel,sama5d31", "atmel,sama5d3", "atmel,sama5";
+and following the rules from above for the axentia,linea CPU module.
+
+
 TSE-850 v3 board
 ----------------
 
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,brcmstb.txt b/Documentation/devicetree/bindings/arm/bcm/brcm,brcmstb.txt
index 790e6b0b8306..c052caad36e8 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,brcmstb.txt
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,brcmstb.txt
@@ -17,21 +17,23 @@ Further, syscon nodes that map platform-specific registers used for general
 system control is required:
 
     - compatible: "brcm,bcm<chip_id>-sun-top-ctrl", "syscon"
-    - compatible: "brcm,bcm<chip_id>-hif-cpubiuctrl", "syscon"
+    - compatible: "brcm,bcm<chip_id>-cpu-biu-ctrl",
+		  "brcm,brcmstb-cpu-biu-ctrl",
+		  "syscon"
     - compatible: "brcm,bcm<chip_id>-hif-continuation", "syscon"
 
-hif-cpubiuctrl node
+cpu-biu-ctrl node
 -------------------
-SoCs with Broadcom Brahma15 ARM-based CPUs have a specific Bus Interface Unit
-(BIU) block which controls and interfaces the CPU complex to the different
-Memory Controller Ports (MCP), one per memory controller (MEMC). This BIU block
-offers a feature called Write Pairing which consists in collapsing two adjacent
-cache lines into a single (bursted) write transaction towards the memory
-controller (MEMC) to maximize write bandwidth.
+SoCs with Broadcom Brahma15 ARM-based and Brahma53 ARM64-based CPUs have a
+specific Bus Interface Unit (BIU) block which controls and interfaces the CPU
+complex to the different Memory Controller Ports (MCP), one per memory
+controller (MEMC). This BIU block offers a feature called Write Pairing which
+consists in collapsing two adjacent cache lines into a single (bursted) write
+transaction towards the memory controller (MEMC) to maximize write bandwidth.
 
 Required properties:
 
-    - compatible: must be "brcm,bcm7445-hif-cpubiuctrl", "syscon"
+    - compatible: must be "brcm,bcm7445-cpu-biu-ctrl", "brcm,brcmstb-cpu-biu-ctrl", "syscon"
 
 Optional properties:
 
@@ -52,7 +54,7 @@ example:
         };
 
         hif_cpubiuctrl: syscon@3e2400 {
-            compatible = "brcm,bcm7445-hif-cpubiuctrl", "syscon";
+            compatible = "brcm,bcm7445-cpu-biu-ctrl", "brcm,brcmstb-cpu-biu-ctrl", "syscon";
             reg = <0x3e2400 0x5b4>;
             brcm,write-pairing;
         };
diff --git a/Documentation/devicetree/bindings/arm/ccn.txt b/Documentation/devicetree/bindings/arm/ccn.txt
index 29801456c9ee..43b5a71a5a9d 100644
--- a/Documentation/devicetree/bindings/arm/ccn.txt
+++ b/Documentation/devicetree/bindings/arm/ccn.txt
@@ -15,7 +15,7 @@ Required properties:
 
 Example:
 
-	ccn@0x2000000000 {
+	ccn@2000000000 {
 		compatible = "arm,ccn-504";
 		reg = <0x20 0x00000000 0 0x1000000>;
 		interrupts = <0 181 4>;
diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt
index a0009b72e9be..f4a777039f03 100644
--- a/Documentation/devicetree/bindings/arm/cpus.txt
+++ b/Documentation/devicetree/bindings/arm/cpus.txt
@@ -169,6 +169,7 @@ described below.
 			    "arm,cortex-r5"
 			    "arm,cortex-r7"
 			    "brcm,brahma-b15"
+			    "brcm,brahma-b53"
 			    "brcm,vulcan"
 			    "cavium,thunder"
 			    "cavium,thunder2"
diff --git a/Documentation/devicetree/bindings/arm/firmware/sdei.txt b/Documentation/devicetree/bindings/arm/firmware/sdei.txt
new file mode 100644
index 000000000000..ee3f0ff49889
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/firmware/sdei.txt
@@ -0,0 +1,42 @@
+* Software Delegated Exception Interface (SDEI)
+
+Firmware implementing the SDEI functions described in ARM document number
+ARM DEN 0054A ("Software Delegated Exception Interface") can be used by
+Linux to receive notification of events such as those generated by
+firmware-first error handling, or from an IRQ that has been promoted to
+a firmware-assisted NMI.
+
+The interface provides a number of API functions for registering callbacks
+and enabling/disabling events. Functions are invoked by trapping to the
+privilege level of the SDEI firmware (specified as part of the binding
+below) and passing arguments in a manner specified by the "SMC Calling
+Convention (ARM DEN 0028B):
+
+	 r0		=> 32-bit Function ID / return value
+	{r1 - r3}	=> Parameters
+
+Note that the immediate field of the trapping instruction must be set
+to #0.
+
+The SDEI_EVENT_REGISTER function registers a callback in the kernel
+text to handle the specified event number.
+
+The sdei node should be a child node of '/firmware' and have required
+properties:
+
+ - compatible    : should contain:
+	* "arm,sdei-1.0" : For implementations complying to SDEI version 1.x.
+
+ - method        : The method of calling the SDEI firmware. Permitted
+                   values are:
+	* "smc" : SMC #0, with the register assignments specified in this
+	          binding.
+	* "hvc" : HVC #0, with the register assignments specified in this
+	          binding.
+Example:
+	firmware {
+		sdei {
+			compatible	= "arm,sdei-1.0";
+			method		= "smc";
+		};
+	};
diff --git a/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt b/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt
index 51336e5fc761..35c3c3460d17 100644
--- a/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt
+++ b/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt
@@ -14,3 +14,22 @@ following property before the previous one:
 Example:
 
 compatible = "marvell,armada-3720-db", "marvell,armada3720", "marvell,armada3710";
+
+
+Power management
+----------------
+
+For power management (particularly DVFS and AVS), the North Bridge
+Power Management component is needed:
+
+Required properties:
+- compatible     : should contain "marvell,armada-3700-nb-pm", "syscon";
+- reg            : the register start and length for the North Bridge
+		    Power Management
+
+Example:
+
+nb_pm: syscon@14000 {
+	compatible = "marvell,armada-3700-nb-pm", "syscon";
+	reg = <0x14000 0x60>;
+}
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,ethsys.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,ethsys.txt
index 7aa3fa167668..6cc7840ff37a 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,ethsys.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,ethsys.txt
@@ -20,4 +20,5 @@ ethsys: clock-controller@1b000000 {
 	compatible = "mediatek,mt2701-ethsys", "syscon";
 	reg = <0 0x1b000000 0 0x1000>;
 	#clock-cells = <1>;
+	#reset-cells = <1>;
 };
diff --git a/Documentation/devicetree/bindings/arm/omap/crossbar.txt b/Documentation/devicetree/bindings/arm/omap/crossbar.txt
index bb5727ae004a..ecb360ed0e33 100644
--- a/Documentation/devicetree/bindings/arm/omap/crossbar.txt
+++ b/Documentation/devicetree/bindings/arm/omap/crossbar.txt
@@ -49,7 +49,7 @@ An interrupt consumer on an SoC using crossbar will use:
 	interrupts = <GIC_SPI request_number interrupt_level>
 
 Example:
-	device_x@0x4a023000 {
+	device_x@4a023000 {
 		/* Crossbar 8 used */
 		interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>;
 		...
diff --git a/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt b/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt
index ccaaec6014bd..6c49db7f8ad2 100644
--- a/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt
+++ b/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt
@@ -55,7 +55,7 @@ Note: child nodes can be added for auto probing from device tree.
 
 Example: adding device info in dtsi file
 
-adc: adc@12D10000 {
+adc: adc@12d10000 {
 	compatible = "samsung,exynos-adc-v1";
 	reg = <0x12D10000 0x100>;
 	interrupts = <0 106 0>;
@@ -71,7 +71,7 @@ adc: adc@12D10000 {
 
 Example: adding device info in dtsi file for Exynos3250 with additional sclk
 
-adc: adc@126C0000 {
+adc: adc@126c0000 {
 	compatible = "samsung,exynos3250-adc", "samsung,exynos-adc-v2;
 	reg = <0x126C0000 0x100>;
 	interrupts = <0 137 0>;
@@ -87,7 +87,7 @@ adc: adc@126C0000 {
 
 Example: Adding child nodes in dts file
 
-adc@12D10000 {
+adc@12d10000 {
 
 	/* NTC thermistor is a hwmon device */
 	ncp15wb473@0 {
diff --git a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
index e13459618581..469ac98ecf8f 100644
--- a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
+++ b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
@@ -72,7 +72,7 @@ Optional nodes:
         - compatible: only "samsung,secure-firmware" is currently supported
         - reg: address of non-secure SYSRAM used for communication with firmware
 
-	firmware@203F000 {
+	firmware@203f000 {
 		compatible = "samsung,secure-firmware";
 		reg = <0x0203F000 0x1000>;
 	};
diff --git a/Documentation/devicetree/bindings/arm/shmobile.txt b/Documentation/devicetree/bindings/arm/shmobile.txt
index 020d758fc0c5..5c3af7ef0761 100644
--- a/Documentation/devicetree/bindings/arm/shmobile.txt
+++ b/Documentation/devicetree/bindings/arm/shmobile.txt
@@ -104,12 +104,16 @@ Boards:
     compatible = "renesas,salvator-x", "renesas,r8a7796"
   - Salvator-XS (Salvator-X 2nd version, RTP0RC7795SIPB0012S)
     compatible = "renesas,salvator-xs", "renesas,r8a7795"
+  - Salvator-XS (Salvator-X 2nd version, RTP0RC7796SIPB0012S)
+    compatible = "renesas,salvator-xs", "renesas,r8a7796"
   - SILK (RTP0RC7794LCB00011S)
     compatible = "renesas,silk", "renesas,r8a7794"
   - SK-RZG1E (YR8A77450S000BE)
     compatible = "renesas,sk-rzg1e", "renesas,r8a7745"
   - SK-RZG1M (YR8A77430S000BE)
     compatible = "renesas,sk-rzg1m", "renesas,r8a7743"
+  - V3MSK
+    compatible = "renesas,v3msk", "renesas,r8a77970"
   - Wheat
     compatible = "renesas,wheat", "renesas,r8a7792"
 
diff --git a/Documentation/devicetree/bindings/arm/stm32.txt b/Documentation/devicetree/bindings/arm/stm32.txt
new file mode 100644
index 000000000000..05762b08a7bb
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/stm32.txt
@@ -0,0 +1,9 @@
+STMicroelectronics STM32 Platforms Device Tree Bindings
+
+Each device tree must specify which STM32 SoC it uses,
+using one of the following compatible strings:
+
+  st,stm32f429
+  st,stm32f469
+  st,stm32f746
+  st,stm32h743
diff --git a/Documentation/devicetree/bindings/arm/technologic.txt b/Documentation/devicetree/bindings/arm/technologic.txt
index 33797acad846..f1cedc00dcab 100644
--- a/Documentation/devicetree/bindings/arm/technologic.txt
+++ b/Documentation/devicetree/bindings/arm/technologic.txt
@@ -1,6 +1,11 @@
 Technologic Systems Platforms Device Tree Bindings
 --------------------------------------------------
 
+TS-4600 is a System-on-Module based on the Freescale i.MX28 System-on-Chip.
+It can be mounted on a carrier board providing additional peripheral connectors.
+Required root node properties:
+	- compatible = "technologic,imx28-ts4600", "fsl,imx28"
+
 TS-4800 board
 Required root node properties:
 	- compatible = "technologic,imx51-ts4800", "fsl,imx51";
@@ -10,3 +15,9 @@ It can be mounted on a carrier board providing additional peripheral connectors.
 Required root node properties:
 	- compatible = "technologic,imx6dl-ts4900", "fsl,imx6dl"
 	- compatible = "technologic,imx6q-ts4900", "fsl,imx6q"
+
+TS-7970 is a System-on-Module based on the Freescale i.MX6 System-on-Chip.
+It can be mounted on a carrier board providing additional peripheral connectors.
+Required root node properties:
+	- compatible = "technologic,imx6dl-ts7970", "fsl,imx6dl"
+	- compatible = "technologic,imx6q-ts7970", "fsl,imx6q"
diff --git a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-mc.txt b/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-mc.txt
index 866d93421eba..f9632bacbd04 100644
--- a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-mc.txt
+++ b/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-mc.txt
@@ -8,7 +8,7 @@ Required properties:
 - interrupts : Should contain MC General interrupt.
 
 Example:
-	memory-controller@0x7000f000 {
+	memory-controller@7000f000 {
 		compatible = "nvidia,tegra20-mc";
 		reg = <0x7000f000 0x024
 		       0x7000f03c 0x3c4>;
diff --git a/Documentation/devicetree/bindings/bus/ti-sysc.txt b/Documentation/devicetree/bindings/bus/ti-sysc.txt
index fb1790e39398..2957a9ae291f 100644
--- a/Documentation/devicetree/bindings/bus/ti-sysc.txt
+++ b/Documentation/devicetree/bindings/bus/ti-sysc.txt
@@ -19,6 +19,7 @@ Required standard properties:
 
 - compatible	shall be one of the following generic types:
 
+		"ti,sysc"
 		"ti,sysc-omap2"
 		"ti,sysc-omap4"
 		"ti,sysc-omap4-simple"
@@ -26,6 +27,8 @@ Required standard properties:
 		or one of the following derivative types for hardware
 		needing special workarounds:
 
+		"ti,sysc-omap2-timer"
+		"ti,sysc-omap4-timer"
 		"ti,sysc-omap3430-sr"
 		"ti,sysc-omap3630-sr"
 		"ti,sysc-omap4-sr"
@@ -49,6 +52,26 @@ Required standard properties:
 
 Optional properties:
 
+- ti,sysc-mask	shall contain mask of supported register bits for the
+		SYSCONFIG register as documented in the Technical Reference
+		Manual (TRM) for the interconnect target module
+
+- ti,sysc-midle	list of master idle modes supported by the interconnect
+		target module as documented in the TRM for SYSCONFIG
+		register MIDLEMODE bits
+
+- ti,sysc-sidle	list of slave idle modes supported by the interconnect
+		target module as documented in the TRM for SYSCONFIG
+		register SIDLEMODE bits
+
+- ti,sysc-delay-us	delay needed after OCP softreset before accssing
+			SYSCONFIG register again
+
+- ti,syss-mask	optional mask of reset done status bits as described in the
+		TRM for SYSSTATUS registers, typically 1 with some devices
+		having separate reset done bits for children like OHCI and
+		EHCI
+
 - clocks	clock specifier for each name in the clock-names as
 		specified in the binding documentation for ti-clkctrl,
 		typically available for all interconnect targets on TI SoCs
@@ -61,6 +84,9 @@ Optional properties:
 - ti,hwmods	optional TI interconnect module name to use legacy
 		hwmod platform data
 
+- ti,no-reset-on-init	interconnect target module should not be reset at init
+
+- ti,no-idle-on-init	interconnect target module should not be idled at init
 
 Example: Single instance of MUSB controller on omap4 using interconnect ranges
 using offsets from l4_cfg second segment (0x4a000000 + 0x80000 = 0x4a0ab000):
@@ -74,6 +100,17 @@ using offsets from l4_cfg second segment (0x4a000000 + 0x80000 = 0x4a0ab000):
 		reg-names = "rev", "sysc", "syss";
 		clocks = <&l3_init_clkctrl OMAP4_USB_OTG_HS_CLKCTRL 0>;
 		clock-names = "fck";
+		ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP |
+				 SYSC_OMAP2_SOFTRESET |
+				 SYSC_OMAP2_AUTOIDLE)>;
+		ti,sysc-midle = <SYSC_IDLE_FORCE>,
+				<SYSC_IDLE_NO>,
+				<SYSC_IDLE_SMART>;
+		ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+				<SYSC_IDLE_NO>,
+				<SYSC_IDLE_SMART>,
+				<SYSC_IDLE_SMART_WKUP>;
+		ti,syss-mask = <1>;
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ranges = <0 0x2b000 0x1000>;
diff --git a/Documentation/devicetree/bindings/chosen.txt b/Documentation/devicetree/bindings/chosen.txt
index e3b13ea7d2ae..45e79172a646 100644
--- a/Documentation/devicetree/bindings/chosen.txt
+++ b/Documentation/devicetree/bindings/chosen.txt
@@ -120,3 +120,18 @@ e.g.
 While this property does not represent a real hardware, the address
 and the size are expressed in #address-cells and #size-cells,
 respectively, of the root node.
+
+linux,initrd-start and linux,initrd-end
+---------------------------------------
+
+These properties hold the physical start and end address of an initrd that's
+loaded by the bootloader. Note that linux,initrd-start is inclusive, but
+linux,initrd-end is exclusive.
+e.g.
+
+/ {
+	chosen {
+		linux,initrd-start = <0x82000000>;
+		linux,initrd-end = <0x82800000>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/clock/amlogic,gxbb-clkc.txt b/Documentation/devicetree/bindings/clock/amlogic,gxbb-clkc.txt
index 924040769186..e2b377ed6f91 100644
--- a/Documentation/devicetree/bindings/clock/amlogic,gxbb-clkc.txt
+++ b/Documentation/devicetree/bindings/clock/amlogic,gxbb-clkc.txt
@@ -5,8 +5,11 @@ controllers within the SoC.
 
 Required Properties:
 
-- compatible: should be "amlogic,gxbb-clkc" for GXBB SoC,
-	      or "amlogic,gxl-clkc" for GXL and GXM SoC.
+- compatible: should be:
+		"amlogic,gxbb-clkc" for GXBB SoC,
+		"amlogic,gxl-clkc" for GXL and GXM SoC,
+		"amlogic,axg-clkc" for AXG SoC.
+
 - reg: physical base address of the clock controller and length of memory
        mapped region.
 
diff --git a/Documentation/devicetree/bindings/clock/axi-clkgen.txt b/Documentation/devicetree/bindings/clock/axi-clkgen.txt
index fb40da303d25..aca94fe9416f 100644
--- a/Documentation/devicetree/bindings/clock/axi-clkgen.txt
+++ b/Documentation/devicetree/bindings/clock/axi-clkgen.txt
@@ -17,7 +17,7 @@ Optional properties:
 - clock-output-names : From common clock binding.
 
 Example:
-	clock@0xff000000 {
+	clock@ff000000 {
 		compatible = "adi,axi-clkgen";
 		#clock-cells = <0>;
 		reg = <0xff000000 0x1000>;
diff --git a/Documentation/devicetree/bindings/clock/brcm,bcm2835-aux-clock.txt b/Documentation/devicetree/bindings/clock/brcm,bcm2835-aux-clock.txt
index 7a837d2182ac..4acfc8f641b6 100644
--- a/Documentation/devicetree/bindings/clock/brcm,bcm2835-aux-clock.txt
+++ b/Documentation/devicetree/bindings/clock/brcm,bcm2835-aux-clock.txt
@@ -23,7 +23,7 @@ Example:
 		clocks = <&clk_osc>;
 	};
 
-	aux: aux@0x7e215004 {
+	aux: aux@7e215004 {
 		compatible = "brcm,bcm2835-aux";
 		#clock-cells = <1>;
 		reg = <0x7e215000 0x8>;
diff --git a/Documentation/devicetree/bindings/clock/exynos3250-clock.txt b/Documentation/devicetree/bindings/clock/exynos3250-clock.txt
index f1738b88c225..7441ed519f02 100644
--- a/Documentation/devicetree/bindings/clock/exynos3250-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos3250-clock.txt
@@ -32,7 +32,7 @@ Example 1: Examples of clock controller nodes are listed below.
 		#clock-cells = <1>;
 	};
 
-	cmu_dmc: clock-controller@105C0000 {
+	cmu_dmc: clock-controller@105c0000 {
 		compatible = "samsung,exynos3250-cmu-dmc";
 		reg = <0x105C0000 0x2000>;
 		#clock-cells = <1>;
diff --git a/Documentation/devicetree/bindings/clock/exynos4-clock.txt b/Documentation/devicetree/bindings/clock/exynos4-clock.txt
index bc61c952cb0b..17bb11365354 100644
--- a/Documentation/devicetree/bindings/clock/exynos4-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos4-clock.txt
@@ -24,7 +24,7 @@ tree sources.
 
 Example 1: An example of a clock controller node is listed below.
 
-	clock: clock-controller@0x10030000 {
+	clock: clock-controller@10030000 {
 		compatible = "samsung,exynos4210-clock";
 		reg = <0x10030000 0x20000>;
 		#clock-cells = <1>;
diff --git a/Documentation/devicetree/bindings/clock/exynos5250-clock.txt b/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
index 536eacd1063f..aff266a12eeb 100644
--- a/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
@@ -22,7 +22,7 @@ tree sources.
 
 Example 1: An example of a clock controller node is listed below.
 
-	clock: clock-controller@0x10010000 {
+	clock: clock-controller@10010000 {
 		compatible = "samsung,exynos5250-clock";
 		reg = <0x10010000 0x30000>;
 		#clock-cells = <1>;
diff --git a/Documentation/devicetree/bindings/clock/exynos5260-clock.txt b/Documentation/devicetree/bindings/clock/exynos5260-clock.txt
index 5496b2fac483..c79d31f7f66e 100644
--- a/Documentation/devicetree/bindings/clock/exynos5260-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos5260-clock.txt
@@ -180,7 +180,7 @@ Example 2: UART controller node that consumes the clock generated by the
 		peri clock controller. Refer to the standard clock bindings for
 		information about 'clocks' and 'clock-names' property.
 
-	serial@12C00000 {
+	serial@12c00000 {
 		compatible = "samsung,exynos4210-uart";
 		reg = <0x12C00000 0x100>;
 		interrupts = <0 146 0>;
diff --git a/Documentation/devicetree/bindings/clock/exynos5410-clock.txt b/Documentation/devicetree/bindings/clock/exynos5410-clock.txt
index 4527de3ea205..217beb27c30e 100644
--- a/Documentation/devicetree/bindings/clock/exynos5410-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos5410-clock.txt
@@ -30,7 +30,7 @@ Example 1: An example of a clock controller node is listed below.
 		#clock-cells = <0>;
 	};
 
-	clock: clock-controller@0x10010000 {
+	clock: clock-controller@10010000 {
 		compatible = "samsung,exynos5410-clock";
 		reg = <0x10010000 0x30000>;
 		#clock-cells = <1>;
@@ -41,7 +41,7 @@ Example 2: UART controller node that consumes the clock generated by the clock
 	   controller. Refer to the standard clock bindings for information
 	   about 'clocks' and 'clock-names' property.
 
-	serial@12C20000 {
+	serial@12c20000 {
 		compatible = "samsung,exynos4210-uart";
 		reg = <0x12C00000 0x100>;
 		interrupts = <0 51 0>;
diff --git a/Documentation/devicetree/bindings/clock/exynos5420-clock.txt b/Documentation/devicetree/bindings/clock/exynos5420-clock.txt
index d54f42cf0440..717a7b1531c7 100644
--- a/Documentation/devicetree/bindings/clock/exynos5420-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos5420-clock.txt
@@ -23,7 +23,7 @@ tree sources.
 
 Example 1: An example of a clock controller node is listed below.
 
-	clock: clock-controller@0x10010000 {
+	clock: clock-controller@10010000 {
 		compatible = "samsung,exynos5420-clock";
 		reg = <0x10010000 0x30000>;
 		#clock-cells = <1>;
diff --git a/Documentation/devicetree/bindings/clock/exynos5433-clock.txt b/Documentation/devicetree/bindings/clock/exynos5433-clock.txt
index c473dd38dd55..50d5897c9849 100644
--- a/Documentation/devicetree/bindings/clock/exynos5433-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos5433-clock.txt
@@ -472,7 +472,7 @@ Example 2: Examples of clock controller nodes are listed below.
 Example 3: UART controller node that consumes the clock generated by the clock
 	   controller.
 
-	serial_0: serial@14C10000 {
+	serial_0: serial@14c10000 {
 		compatible = "samsung,exynos5433-uart";
 		reg = <0x14C10000 0x100>;
 		interrupts = <0 421 0>;
diff --git a/Documentation/devicetree/bindings/clock/exynos5440-clock.txt b/Documentation/devicetree/bindings/clock/exynos5440-clock.txt
index 5f7005f73058..c7d227c31e95 100644
--- a/Documentation/devicetree/bindings/clock/exynos5440-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos5440-clock.txt
@@ -21,7 +21,7 @@ tree sources.
 
 Example: An example of a clock controller node is listed below.
 
-	clock: clock-controller@0x10010000 {
+	clock: clock-controller@10010000 {
 		compatible = "samsung,exynos5440-clock";
 		reg = <0x160000 0x10000>;
 		#clock-cells = <1>;
diff --git a/Documentation/devicetree/bindings/clock/hi3660-clock.txt b/Documentation/devicetree/bindings/clock/hi3660-clock.txt
index 0035a7ecaf20..946da7cee54f 100644
--- a/Documentation/devicetree/bindings/clock/hi3660-clock.txt
+++ b/Documentation/devicetree/bindings/clock/hi3660-clock.txt
@@ -13,12 +13,18 @@ Required Properties:
 	- "hisilicon,hi3660-pmuctrl"
 	- "hisilicon,hi3660-sctrl"
 	- "hisilicon,hi3660-iomcu"
+	- "hisilicon,hi3660-stub-clk"
 
 - reg: physical base address of the controller and length of memory mapped
   region.
 
 - #clock-cells: should be 1.
 
+Optional Properties:
+
+- mboxes: Phandle to the mailbox for sending message to MCU.
+            (See: ../mailbox/hisilicon,hi3660-mailbox.txt for more info)
+
 Each clock is assigned an identifier and client nodes use this identifier
 to specify the clock which they consume.
 
diff --git a/Documentation/devicetree/bindings/clock/qcom,a53pll.txt b/Documentation/devicetree/bindings/clock/qcom,a53pll.txt
new file mode 100644
index 000000000000..e3fa8118eaee
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,a53pll.txt
@@ -0,0 +1,22 @@
+Qualcomm MSM8916 A53 PLL Binding
+--------------------------------
+The A53 PLL on MSM8916 platforms is the main CPU PLL used used for frequencies
+above 1GHz.
+
+Required properties :
+- compatible : Shall contain only one of the following:
+
+		"qcom,msm8916-a53pll"
+
+- reg : shall contain base register location and length
+
+- #clock-cells : must be set to <0>
+
+Example:
+
+	a53pll: clock@b016000 {
+		compatible = "qcom,msm8916-a53pll";
+		reg = <0xb016000 0x40>;
+		#clock-cells = <0>;
+	};
+
diff --git a/Documentation/devicetree/bindings/clock/qcom,spmi-clkdiv.txt b/Documentation/devicetree/bindings/clock/qcom,spmi-clkdiv.txt
new file mode 100644
index 000000000000..7474aba36607
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,spmi-clkdiv.txt
@@ -0,0 +1,59 @@
+Qualcomm Technologies, Inc. SPMI PMIC clock divider (clkdiv)
+
+clkdiv configures the clock frequency of a set of outputs on the PMIC.
+These clocks are typically wired through alternate functions on
+gpio pins.
+
+=======================
+Properties
+=======================
+
+- compatible
+	Usage:      required
+	Value type: <string>
+	Definition: must be "qcom,spmi-clkdiv".
+
+- reg
+	Usage:      required
+	Value type: <prop-encoded-array>
+	Definition: base address of CLKDIV peripherals.
+
+- qcom,num-clkdivs
+	Usage:      required
+	Value type: <u32>
+	Definition: number of CLKDIV peripherals.
+
+- clocks:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: reference to the xo clock.
+
+- clock-names:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "xo".
+
+- #clock-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: shall contain 1.
+
+=======
+Example
+=======
+
+pm8998_clk_divs: clock-controller@5b00 {
+	compatible = "qcom,spmi-clkdiv";
+	reg = <0x5b00>;
+	#clock-cells = <1>;
+	qcom,num-clkdivs = <3>;
+	clocks = <&xo_board>;
+	clock-names = "xo";
+
+	assigned-clocks = <&pm8998_clk_divs 1>,
+			  <&pm8998_clk_divs 2>,
+			  <&pm8998_clk_divs 3>;
+	assigned-clock-rates = <9600000>,
+			       <9600000>,
+			       <9600000>;
+};
diff --git a/Documentation/devicetree/bindings/clock/qoriq-clock.txt b/Documentation/devicetree/bindings/clock/qoriq-clock.txt
index 6498e1fdbb33..97f46adac85f 100644
--- a/Documentation/devicetree/bindings/clock/qoriq-clock.txt
+++ b/Documentation/devicetree/bindings/clock/qoriq-clock.txt
@@ -78,6 +78,7 @@ second cell is the clock index for the specified type.
 	2	hwaccel		index (n in CLKCGnHWACSR)
 	3	fman		0 for fm1, 1 for fm2
 	4	platform pll	0=pll, 1=pll/2, 2=pll/3, 3=pll/4
+				4=pll/5, 5=pll/6, 6=pll/7, 7=pll/8
 	5	coreclk		must be 0
 
 3. Example
diff --git a/Documentation/devicetree/bindings/clock/silabs,si5351.txt b/Documentation/devicetree/bindings/clock/silabs,si5351.txt
index a6c4ef343b44..f00191cad8cd 100644
--- a/Documentation/devicetree/bindings/clock/silabs,si5351.txt
+++ b/Documentation/devicetree/bindings/clock/silabs,si5351.txt
@@ -49,6 +49,7 @@ Optional child node properties:
 - silabs,multisynth-source: source pll A(0) or B(1) of corresponding multisynth
   divider.
 - silabs,pll-master: boolean, multisynth can change pll frequency.
+- silabs,pll-reset: boolean, clock output can reset its pll.
 - silabs,disable-state : clock output disable state, shall be
   0 = clock output is driven LOW when disabled
   1 = clock output is driven HIGH when disabled
diff --git a/Documentation/devicetree/bindings/clock/sprd.txt b/Documentation/devicetree/bindings/clock/sprd.txt
new file mode 100644
index 000000000000..e9d179e882d9
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/sprd.txt
@@ -0,0 +1,63 @@
+Spreadtrum Clock Binding
+------------------------
+
+Required properties:
+- compatible: should contain the following compatible strings:
+	- "sprd,sc9860-pmu-gate"
+	- "sprd,sc9860-pll"
+	- "sprd,sc9860-ap-clk"
+	- "sprd,sc9860-aon-prediv"
+	- "sprd,sc9860-apahb-gate"
+	- "sprd,sc9860-aon-gate"
+	- "sprd,sc9860-aonsecure-clk"
+	- "sprd,sc9860-agcp-gate"
+	- "sprd,sc9860-gpu-clk"
+	- "sprd,sc9860-vsp-clk"
+	- "sprd,sc9860-vsp-gate"
+	- "sprd,sc9860-cam-clk"
+	- "sprd,sc9860-cam-gate"
+	- "sprd,sc9860-disp-clk"
+	- "sprd,sc9860-disp-gate"
+	- "sprd,sc9860-apapb-gate"
+
+- #clock-cells: must be 1
+
+- clocks : Should be the input parent clock(s) phandle for the clock, this
+	   property here just simply shows which clock group the clocks'
+	   parents are in, since each clk node would represent many clocks
+	   which are defined in the driver.  The detailed dependency
+	   relationship (i.e. how many parents and which are the parents)
+	   are implemented in driver code.
+
+Optional properties:
+
+- reg:	Contain the registers base address and length. It must be configured
+	only if no 'sprd,syscon' under the node.
+
+- sprd,syscon: phandle to the syscon which is in the same address area with
+	       the clock, and so we can get regmap for the clocks from the
+	       syscon device.
+
+Example:
+
+	pmu_gate: pmu-gate {
+		compatible = "sprd,sc9860-pmu-gate";
+		sprd,syscon = <&pmu_regs>;
+		clocks = <&ext_26m>;
+		#clock-cells = <1>;
+	};
+
+	pll: pll {
+		compatible = "sprd,sc9860-pll";
+		sprd,syscon = <&ana_regs>;
+		clocks = <&pmu_gate 0>;
+		#clock-cells = <1>;
+	};
+
+	ap_clk: clock-controller@20000000 {
+		compatible = "sprd,sc9860-ap-clk";
+		reg = <0 0x20000000 0 0x400>;
+		clocks = <&ext_26m>, <&pll 0>,
+			 <&pmu_gate 0>;
+		#clock-cells = <1>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/sun8i-de2.txt b/Documentation/devicetree/bindings/clock/sun8i-de2.txt
index 631d27cd89d6..f2fa87c4765c 100644
--- a/Documentation/devicetree/bindings/clock/sun8i-de2.txt
+++ b/Documentation/devicetree/bindings/clock/sun8i-de2.txt
@@ -4,13 +4,14 @@ Allwinner Display Engine 2.0 Clock Control Binding
 Required properties :
 - compatible: must contain one of the following compatibles:
 		- "allwinner,sun8i-a83t-de2-clk"
+		- "allwinner,sun8i-h3-de2-clk"
 		- "allwinner,sun8i-v3s-de2-clk"
 		- "allwinner,sun50i-h5-de2-clk"
 
 - reg: Must contain the registers base address and length
 - clocks: phandle to the clocks feeding the display engine subsystem.
 	  Three are needed:
-  - "mod": the display engine module clock
+  - "mod": the display engine module clock (on A83T it's the DE PLL)
   - "bus": the bus clock for the whole display engine subsystem
 - clock-names: Must contain the clock names described just above
 - resets: phandle to the reset control for the display engine subsystem.
@@ -19,7 +20,7 @@ Required properties :
 
 Example:
 de2_clocks: clock@1000000 {
-	compatible = "allwinner,sun8i-a83t-de2-clk";
+	compatible = "allwinner,sun8i-h3-de2-clk";
 	reg = <0x01000000 0x100000>;
 	clocks = <&ccu CLK_BUS_DE>,
 		 <&ccu CLK_DE>;
diff --git a/Documentation/devicetree/bindings/clock/ti-keystone-pllctrl.txt b/Documentation/devicetree/bindings/clock/ti-keystone-pllctrl.txt
index 3e6a81e99804..c35cb6c4af4d 100644
--- a/Documentation/devicetree/bindings/clock/ti-keystone-pllctrl.txt
+++ b/Documentation/devicetree/bindings/clock/ti-keystone-pllctrl.txt
@@ -14,7 +14,7 @@ Required properties:
 
 Example:
 
-pllctrl: pll-controller@0x02310000 {
+pllctrl: pll-controller@02310000 {
 	compatible = "ti,keystone-pllctrl", "syscon";
 	reg = <0x02310000 0x200>;
 };
diff --git a/Documentation/devicetree/bindings/clock/zx296702-clk.txt b/Documentation/devicetree/bindings/clock/zx296702-clk.txt
index e85ecb510d56..5c91c9e4f1be 100644
--- a/Documentation/devicetree/bindings/clock/zx296702-clk.txt
+++ b/Documentation/devicetree/bindings/clock/zx296702-clk.txt
@@ -20,13 +20,13 @@ ID in its "clocks" phandle cell. See include/dt-bindings/clock/zx296702-clock.h
 for the full list of zx296702 clock IDs.
 
 
-topclk: topcrm@0x09800000 {
+topclk: topcrm@09800000 {
         compatible = "zte,zx296702-topcrm-clk";
         reg = <0x09800000 0x1000>;
         #clock-cells = <1>;
 };
 
-uart0: serial@0x09405000 {
+uart0: serial@09405000 {
         compatible = "zte,zx296702-uart";
         reg = <0x09405000 0x1000>;
         interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt b/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt
new file mode 100644
index 000000000000..cec8d5d74e26
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt
@@ -0,0 +1,22 @@
+Arm TrustZone CryptoCell cryptographic engine
+
+Required properties:
+- compatible: Should be "arm,cryptocell-712-ree".
+- reg: Base physical address of the engine and length of memory mapped region.
+- interrupts: Interrupt number for the device.
+
+Optional properties:
+- interrupt-parent: The phandle for the interrupt controller that services
+  interrupts for this device.
+- clocks: Reference to the crypto engine clock.
+- dma-coherent: Present if dma operations are coherent.
+
+Examples:
+
+       arm_cc712: crypto@80000000 {
+               compatible = "arm,cryptocell-712-ree";
+               interrupt-parent = <&intc>;
+               interrupts = < 0 30 4 >;
+               reg = < 0x80000000 0x10000 >;
+
+       };
diff --git a/Documentation/devicetree/bindings/crypto/atmel-crypto.txt b/Documentation/devicetree/bindings/crypto/atmel-crypto.txt
index 7de1a9674c70..6b458bb2440d 100644
--- a/Documentation/devicetree/bindings/crypto/atmel-crypto.txt
+++ b/Documentation/devicetree/bindings/crypto/atmel-crypto.txt
@@ -75,7 +75,7 @@ Required properties:
 - clock-frequency: must be present in the i2c controller node.
 
 Example:
-atecc508a@C0 {
+atecc508a@c0 {
 	compatible = "atmel,atecc508a";
 	reg = <0xC0>;
 };
diff --git a/Documentation/devicetree/bindings/crypto/fsl-sec4.txt b/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
index 7aef0eae58d4..76aec8a3724d 100644
--- a/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
+++ b/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
@@ -456,7 +456,7 @@ System ON/OFF key driver
       Definition: this is phandle to the register map node.
 
 EXAMPLE:
-	snvs-pwrkey@0x020cc000 {
+	snvs-pwrkey@020cc000 {
 		compatible = "fsl,sec-v4.0-pwrkey";
 		regmap = <&snvs>;
 		interrupts = <0 4 0x4>
@@ -545,7 +545,7 @@ FULL EXAMPLE
 			interrupts = <93 2>;
 		};
 
-		snvs-pwrkey@0x020cc000 {
+		snvs-pwrkey@020cc000 {
 			compatible = "fsl,sec-v4.0-pwrkey";
 			regmap = <&sec_mon>;
 			interrupts = <0 4 0x4>;
diff --git a/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt b/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
index fbc07d12322f..30c3ce6b502e 100644
--- a/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
+++ b/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
@@ -1,7 +1,8 @@
 Inside Secure SafeXcel cryptographic engine
 
 Required properties:
-- compatible: Should be "inside-secure,safexcel-eip197".
+- compatible: Should be "inside-secure,safexcel-eip197" or
+              "inside-secure,safexcel-eip97".
 - reg: Base physical address of the engine and length of memory mapped region.
 - interrupts: Interrupt numbers for the rings and engine.
 - interrupt-names: Should be "ring0", "ring1", "ring2", "ring3", "eip", "mem".
diff --git a/Documentation/devicetree/bindings/crypto/samsung,exynos-rng4.txt b/Documentation/devicetree/bindings/crypto/samsung,exynos-rng4.txt
index 4ca8dd4d7e66..a13fbdb4bd88 100644
--- a/Documentation/devicetree/bindings/crypto/samsung,exynos-rng4.txt
+++ b/Documentation/devicetree/bindings/crypto/samsung,exynos-rng4.txt
@@ -2,7 +2,9 @@ Exynos Pseudo Random Number Generator
 
 Required properties:
 
-- compatible  : Should be "samsung,exynos4-rng".
+- compatible  : One of:
+                - "samsung,exynos4-rng" for Exynos4210 and Exynos4412
+                - "samsung,exynos5250-prng" for Exynos5250+
 - reg         : Specifies base physical address and size of the registers map.
 - clocks      : Phandle to clock-controller plus clock-specifier pair.
 - clock-names : "secss" as a clock name.
diff --git a/Documentation/devicetree/bindings/crypto/st,stm32-cryp.txt b/Documentation/devicetree/bindings/crypto/st,stm32-cryp.txt
new file mode 100644
index 000000000000..970487fa40b8
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/st,stm32-cryp.txt
@@ -0,0 +1,19 @@
+* STMicroelectronics STM32 CRYP
+
+Required properties:
+- compatible: Should be "st,stm32f756-cryp".
+- reg: The address and length of the peripheral registers space
+- clocks: The input clock of the CRYP instance
+- interrupts: The CRYP interrupt
+
+Optional properties:
+- resets: The input reset of the CRYP instance
+
+Example:
+crypto@50060000 {
+	compatible = "st,stm32f756-cryp";
+	reg = <0x50060000 0x400>;
+	interrupts = <79>;
+	clocks = <&rcc 0 STM32F7_AHB2_CLOCK(CRYP)>;
+	resets = <&rcc STM32F7_AHB2_RESET(CRYP)>;
+};
diff --git a/Documentation/devicetree/bindings/devfreq/event/exynos-nocp.txt b/Documentation/devicetree/bindings/devfreq/event/exynos-nocp.txt
index fd459f00aa5a..aeaebd425d1f 100644
--- a/Documentation/devicetree/bindings/devfreq/event/exynos-nocp.txt
+++ b/Documentation/devicetree/bindings/devfreq/event/exynos-nocp.txt
@@ -20,7 +20,7 @@ Optional properties:
 
 Example : NoC Probe nodes in Device Tree are listed below.
 
-	nocp_mem0_0: nocp@10CA1000 {
+	nocp_mem0_0: nocp@10ca1000 {
 		compatible = "samsung,exynos5420-nocp";
 		reg = <0x10CA1000 0x200>;
 	};
diff --git a/Documentation/devicetree/bindings/devfreq/event/rockchip-dfi.txt b/Documentation/devicetree/bindings/devfreq/event/rockchip-dfi.txt
index 001dd63979a9..148191b0fc15 100644
--- a/Documentation/devicetree/bindings/devfreq/event/rockchip-dfi.txt
+++ b/Documentation/devicetree/bindings/devfreq/event/rockchip-dfi.txt
@@ -9,7 +9,7 @@ Required properties:
 - clock-names : the name of clock used by the DFI, must be "pclk_ddr_mon";
 
 Example:
-	dfi: dfi@0xff630000 {
+	dfi: dfi@ff630000 {
 		compatible = "rockchip,rk3399-dfi";
 		reg = <0x00 0xff630000 0x00 0x4000>;
 		rockchip,pmu = <&pmugrf>;
diff --git a/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.txt b/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.txt
index 7f040edc16fe..bf4a18047309 100644
--- a/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.txt
+++ b/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.txt
@@ -48,6 +48,10 @@ Required properties:
   Documentation/devicetree/bindings/reset/reset.txt,
   the reset-names should be "hdmitx_apb", "hdmitx", "hdmitx_phy"
 
+Optional properties:
+- hdmi-supply: Optional phandle to an external 5V regulator to power the HDMI
+  logic, as described in the file ../regulator/regulator.txt
+
 Required nodes:
 
 The connections to the HDMI ports are modeled using the OF graph
diff --git a/Documentation/devicetree/bindings/display/amlogic,meson-vpu.txt b/Documentation/devicetree/bindings/display/amlogic,meson-vpu.txt
index 00f74bad1e95..057b81335775 100644
--- a/Documentation/devicetree/bindings/display/amlogic,meson-vpu.txt
+++ b/Documentation/devicetree/bindings/display/amlogic,meson-vpu.txt
@@ -64,6 +64,10 @@ Required properties:
 - reg-names: should contain the names of the previous memory regions
 - interrupts: should contain the VENC Vsync interrupt number
 
+Optional properties:
+- power-domains: Optional phandle to associated power domain as described in
+	the file ../power/power_domain.txt
+
 Required nodes:
 
 The connections to the VPU output video ports are modeled using the OF graph
diff --git a/Documentation/devicetree/bindings/display/atmel,lcdc.txt b/Documentation/devicetree/bindings/display/atmel,lcdc.txt
index 1a21202778ee..acb5a0132127 100644
--- a/Documentation/devicetree/bindings/display/atmel,lcdc.txt
+++ b/Documentation/devicetree/bindings/display/atmel,lcdc.txt
@@ -27,7 +27,7 @@ Optional properties:
 
 Example:
 
-	fb0: fb@0x00500000 {
+	fb0: fb@00500000 {
 		compatible = "atmel,at91sam9g45-lcdc";
 		reg = <0x00500000 0x1000>;
 		interrupts = <23 3 0>;
@@ -41,7 +41,7 @@ Example:
 
 Example for fixed framebuffer memory:
 
-	fb0: fb@0x00500000 {
+	fb0: fb@00500000 {
 		compatible = "atmel,at91sam9263-lcdc";
 		reg = <0x00700000 0x1000 0x70000000 0x200000>;
 		[...]
diff --git a/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt b/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt
index ca5204b3bc21..2fff8b406f4c 100644
--- a/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt
+++ b/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt
@@ -54,7 +54,7 @@ Video interfaces:
 
 Example:
 
-	dsi@11C80000 {
+	dsi@11c80000 {
 		compatible = "samsung,exynos4210-mipi-dsi";
 		reg = <0x11C80000 0x10000>;
 		interrupts = <0 79 0>;
diff --git a/Documentation/devicetree/bindings/display/ilitek,ili9225.txt b/Documentation/devicetree/bindings/display/ilitek,ili9225.txt
new file mode 100644
index 000000000000..a59feb52015b
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/ilitek,ili9225.txt
@@ -0,0 +1,25 @@
+Ilitek ILI9225 display panels
+
+This binding is for display panels using an Ilitek ILI9225 controller in SPI
+mode.
+
+Required properties:
+- compatible:	"vot,v220hf01a-t", "ilitek,ili9225"
+- rs-gpios:	Register select signal
+- reset-gpios:	Reset pin
+
+The node for this driver must be a child node of a SPI controller, hence
+all mandatory properties described in ../spi/spi-bus.txt must be specified.
+
+Optional properties:
+- rotation:	panel rotation in degrees counter clockwise (0,90,180,270)
+
+Example:
+	display@0{
+		compatible = "vot,v220hf01a-t", "ilitek,ili9225";
+		reg = <0>;
+		spi-max-frequency = <12000000>;
+		rs-gpios = <&gpio0 9 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio0 8 GPIO_ACTIVE_HIGH>;
+		rotation = <270>;
+	};
diff --git a/Documentation/devicetree/bindings/display/panel/ilitek,ili9322.txt b/Documentation/devicetree/bindings/display/panel/ilitek,ili9322.txt
new file mode 100644
index 000000000000..3d5ce6ad6ec7
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/ilitek,ili9322.txt
@@ -0,0 +1,49 @@
+Ilitek ILI9322 TFT panel driver with SPI control bus
+
+This is a driver for 320x240 TFT panels, accepting a variety of input
+streams that get adapted and scaled to the panel. The panel output has
+960 TFT source driver pins and 240 TFT gate driver pins, VCOM, VCOML and
+VCOMH outputs.
+
+Required properties:
+  - compatible: "dlink,dir-685-panel", "ilitek,ili9322"
+    (full system-specific compatible is always required to look up configuration)
+  - reg: address of the panel on the SPI bus
+
+Optional properties:
+  - vcc-supply: core voltage supply, see regulator/regulator.txt
+  - iovcc-supply: voltage supply for the interface input/output signals,
+    see regulator/regulator.txt
+  - vci-supply: voltage supply for analog parts, see regulator/regulator.txt
+  - reset-gpios: a GPIO spec for the reset pin, see gpio/gpio.txt
+
+  The following optional properties only apply to RGB and YUV input modes and
+  can be omitted for BT.656 input modes:
+
+  - pixelclk-active: see display/panel/display-timing.txt
+  - de-active: see display/panel/display-timing.txt
+  - hsync-active: see display/panel/display-timing.txt
+  - vsync-active: see display/panel/display-timing.txt
+
+The panel must obey the rules for a SPI slave device as specified in
+spi/spi-bus.txt
+
+The device node can contain one 'port' child node with one child
+'endpoint' node, according to the bindings defined in
+media/video-interfaces.txt. This node should describe panel's video bus.
+
+Example:
+
+panel: display@0 {
+	compatible = "dlink,dir-685-panel", "ilitek,ili9322";
+	reg = <0>;
+	vcc-supply = <&vdisp>;
+	iovcc-supply = <&vdisp>;
+	vci-supply = <&vdisp>;
+
+	port {
+		panel_in: endpoint {
+			remote-endpoint = <&display_out>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/display/panel/mitsubishi,aa070mc01.txt b/Documentation/devicetree/bindings/display/panel/mitsubishi,aa070mc01.txt
new file mode 100644
index 000000000000..7d8f6eeef6d9
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/mitsubishi,aa070mc01.txt
@@ -0,0 +1,7 @@
+Mitsubishi "AA070MC01 7.0" WVGA TFT LCD panel
+
+Required properties:
+- compatible: should be "mitsubishi,aa070mc01-ca1"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/panel-common.txt b/Documentation/devicetree/bindings/display/panel/panel-common.txt
index ec52c472c845..557fa765adcb 100644
--- a/Documentation/devicetree/bindings/display/panel/panel-common.txt
+++ b/Documentation/devicetree/bindings/display/panel/panel-common.txt
@@ -78,6 +78,16 @@ used for panels that implement compatible control signals.
   while active. Active high reset signals can be supported by inverting the
   GPIO specifier polarity flag.
 
+Power
+-----
+
+- power-supply: display panels require power to be supplied. While several
+  panels need more than one power supply with panel-specific constraints
+  governing the order and timings of the power supplies, in many cases a single
+  power supply is sufficient, either because the panel has a single power rail,
+  or because all its power rails can be driven by the same supply. In that case
+  the power-supply property specifies the supply powering the panel as a phandle
+  to a regulator.
 
 Backlight
 ---------
diff --git a/Documentation/devicetree/bindings/display/panel/panel-lvds.txt b/Documentation/devicetree/bindings/display/panel/panel-lvds.txt
index b938269f841e..250850a2150b 100644
--- a/Documentation/devicetree/bindings/display/panel/panel-lvds.txt
+++ b/Documentation/devicetree/bindings/display/panel/panel-lvds.txt
@@ -32,6 +32,7 @@ Optional properties:
 - label: See panel-common.txt.
 - gpios: See panel-common.txt.
 - backlight: See panel-common.txt.
+- power-supply: See panel-common.txt.
 - data-mirror: If set, reverse the bit order described in the data mappings
   below on all data lanes, transmitting bits for slots 6 to 0 instead of
   0 to 6.
diff --git a/Documentation/devicetree/bindings/display/panel/sgd,gktw70sdae4se.txt b/Documentation/devicetree/bindings/display/panel/sgd,gktw70sdae4se.txt
new file mode 100644
index 000000000000..d06644b555bd
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/sgd,gktw70sdae4se.txt
@@ -0,0 +1,41 @@
+Solomon Goldentek Display GKTW70SDAE4SE LVDS Display Panel
+==========================================================
+
+The GKTW70SDAE4SE is a 7" WVGA TFT-LCD display panel.
+
+These DT bindings follow the LVDS panel bindings defined in panel-lvds.txt
+with the following device-specific properties.
+
+Required properties:
+
+- compatible: Shall contain "sgd,gktw70sdae4se" and "panel-lvds", in that order.
+
+Example
+-------
+
+panel {
+	compatible = "sgd,gktw70sdae4se", "panel-lvds";
+
+	width-mm = <153>;
+	height-mm = <86>;
+
+	data-mapping = "jeida-18";
+
+	panel-timing {
+		clock-frequency = <32000000>;
+		hactive = <800>;
+		vactive = <480>;
+		hback-porch = <39>;
+		hfront-porch = <39>;
+		vback-porch = <29>;
+		vfront-porch = <13>;
+		hsync-len = <47>;
+		vsync-len = <2>;
+	};
+
+	port {
+		panel_in: endpoint {
+			remote-endpoint = <&lvds_encoder>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/display/panel/simple-panel.txt b/Documentation/devicetree/bindings/display/panel/simple-panel.txt
index 1341bbf4aa3d..16d8ff088b7d 100644
--- a/Documentation/devicetree/bindings/display/panel/simple-panel.txt
+++ b/Documentation/devicetree/bindings/display/panel/simple-panel.txt
@@ -1,7 +1,7 @@
 Simple display panel
 
 Required properties:
-- power-supply: regulator to provide the supply voltage
+- power-supply: See panel-common.txt
 
 Optional properties:
 - ddc-i2c-bus: phandle of an I2C controller used for DDC EDID probing
diff --git a/Documentation/devicetree/bindings/display/panel/tianma,tm070rvhg71.txt b/Documentation/devicetree/bindings/display/panel/tianma,tm070rvhg71.txt
new file mode 100644
index 000000000000..b25261e63a6d
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/tianma,tm070rvhg71.txt
@@ -0,0 +1,29 @@
+Tianma Micro-electronics TM070RVHG71 7.0" WXGA TFT LCD panel
+
+Required properties:
+- compatible: should be "tianma,tm070rvhg71"
+- power-supply: single regulator to provide the supply voltage
+- backlight: phandle of the backlight device attached to the panel
+
+Required nodes:
+- port: LVDS port mapping to connect this display
+
+This panel needs single power supply voltage. Its backlight is conntrolled
+via PWM signal.
+
+Example:
+--------
+
+Example device-tree definition when connected to iMX6Q based board
+
+	panel: panel-lvds0 {
+		compatible = "tianma,tm070rvhg71";
+		backlight = <&backlight_lvds>;
+		power-supply = <&reg_lvds>;
+
+		port {
+			panel_in_lvds0: endpoint {
+				remote-endpoint = <&lvds0_out>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/panel/toshiba,lt089ac29000.txt b/Documentation/devicetree/bindings/display/panel/toshiba,lt089ac29000.txt
index 4c0caaf246c9..89826116628c 100644
--- a/Documentation/devicetree/bindings/display/panel/toshiba,lt089ac29000.txt
+++ b/Documentation/devicetree/bindings/display/panel/toshiba,lt089ac29000.txt
@@ -1,7 +1,7 @@
 Toshiba 8.9" WXGA (1280x768) TFT LCD panel
 
 Required properties:
-- compatible: should be "toshiba,lt089ac29000.txt"
+- compatible: should be "toshiba,lt089ac29000"
 - power-supply: as specified in the base binding
 
 This binding is compatible with the simple-panel binding, which is specified
diff --git a/Documentation/devicetree/bindings/display/panel/toppoly,td028ttec1.txt b/Documentation/devicetree/bindings/display/panel/tpo,td028ttec1.txt
index 7175dc3740ac..ed34253d9fb1 100644
--- a/Documentation/devicetree/bindings/display/panel/toppoly,td028ttec1.txt
+++ b/Documentation/devicetree/bindings/display/panel/tpo,td028ttec1.txt
@@ -2,7 +2,7 @@ Toppoly TD028TTEC1 Panel
 ========================
 
 Required properties:
-- compatible: "toppoly,td028ttec1"
+- compatible: "tpo,td028ttec1"
 
 Optional properties:
 - label: a symbolic name for the panel
@@ -14,7 +14,7 @@ Example
 -------
 
 lcd-panel: td028ttec1@0 {
-	compatible = "toppoly,td028ttec1";
+	compatible = "tpo,td028ttec1";
 	reg = <0>;
 	spi-max-frequency = <100000>;
 	spi-cpol;
diff --git a/Documentation/devicetree/bindings/display/renesas,du.txt b/Documentation/devicetree/bindings/display/renesas,du.txt
index 4bbd1e9bf3be..cd48aba3bc8c 100644
--- a/Documentation/devicetree/bindings/display/renesas,du.txt
+++ b/Documentation/devicetree/bindings/display/renesas,du.txt
@@ -3,6 +3,8 @@
 Required Properties:
 
   - compatible: must be one of the following.
+    - "renesas,du-r8a7743" for R8A7743 (RZ/G1M) compatible DU
+    - "renesas,du-r8a7745" for R8A7745 (RZ/G1E) compatible DU
     - "renesas,du-r8a7779" for R8A7779 (R-Car H1) compatible DU
     - "renesas,du-r8a7790" for R8A7790 (R-Car H2) compatible DU
     - "renesas,du-r8a7791" for R8A7791 (R-Car M2-W) compatible DU
@@ -27,10 +29,10 @@ Required Properties:
   - clock-names: Name of the clocks. This property is model-dependent.
     - R8A7779 uses a single functional clock. The clock doesn't need to be
       named.
-    - R8A779[0123456] use one functional clock per channel and one clock per
-      LVDS encoder (if available). The functional clocks must be named "du.x"
-      with "x" being the channel numerical index. The LVDS clocks must be
-      named "lvds.x" with "x" being the LVDS encoder numerical index.
+    - All other DU instances use one functional clock per channel and one
+      clock per LVDS encoder (if available). The functional clocks must be
+      named "du.x" with "x" being the channel numerical index. The LVDS clocks
+      must be named "lvds.x" with "x" being the LVDS encoder numerical index.
     - In addition to the functional and encoder clocks, all DU versions also
       support externally supplied pixel clocks. Those clocks are optional.
       When supplied they must be named "dclkin.x" with "x" being the input
@@ -49,16 +51,18 @@ bindings specified in Documentation/devicetree/bindings/graph.txt.
 The following table lists for each supported model the port number
 corresponding to each DU output.
 
-		Port 0		Port1		Port2		Port3
+                      Port0          Port1          Port2          Port3
 -----------------------------------------------------------------------------
- R8A7779 (H1)	DPAD 0		DPAD 1		-		-
- R8A7790 (H2)	DPAD		LVDS 0		LVDS 1		-
- R8A7791 (M2-W)	DPAD		LVDS 0		-		-
- R8A7792 (V2H)	DPAD 0		DPAD 1		-		-
- R8A7793 (M2-N)	DPAD		LVDS 0		-		-
- R8A7794 (E2)	DPAD 0		DPAD 1		-		-
- R8A7795 (H3)	DPAD		HDMI 0		HDMI 1		LVDS
- R8A7796 (M3-W)	DPAD		HDMI		LVDS		-
+ R8A7743 (RZ/G1M)     DPAD 0         LVDS 0         -              -
+ R8A7745 (RZ/G1E)     DPAD 0         DPAD 1         -              -
+ R8A7779 (R-Car H1)   DPAD 0         DPAD 1         -              -
+ R8A7790 (R-Car H2)   DPAD 0         LVDS 0         LVDS 1         -
+ R8A7791 (R-Car M2-W) DPAD 0         LVDS 0         -              -
+ R8A7792 (R-Car V2H)  DPAD 0         DPAD 1         -              -
+ R8A7793 (R-Car M2-N) DPAD 0         LVDS 0         -              -
+ R8A7794 (R-Car E2)   DPAD 0         DPAD 1         -              -
+ R8A7795 (R-Car H3)   DPAD 0         HDMI 0         HDMI 1         LVDS 0
+ R8A7796 (R-Car M3-W) DPAD 0         HDMI 0         LVDS 0         -
 
 
 Example: R8A7795 (R-Car H3) ES2.0 DU
diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip-vop.txt b/Documentation/devicetree/bindings/display/rockchip/rockchip-vop.txt
index 5d835d9c1ba8..eeda3597011e 100644
--- a/Documentation/devicetree/bindings/display/rockchip/rockchip-vop.txt
+++ b/Documentation/devicetree/bindings/display/rockchip/rockchip-vop.txt
@@ -7,6 +7,7 @@ buffer to an external LCD interface.
 Required properties:
 - compatible: value should be one of the following
 		"rockchip,rk3036-vop";
+		"rockchip,rk3126-vop";
 		"rockchip,rk3288-vop";
 		"rockchip,rk3368-vop";
 		"rockchip,rk3366-vop";
diff --git a/Documentation/devicetree/bindings/display/simple-framebuffer-sunxi.txt b/Documentation/devicetree/bindings/display/simple-framebuffer-sunxi.txt
index a9168ae6946c..d693b8dc9a62 100644
--- a/Documentation/devicetree/bindings/display/simple-framebuffer-sunxi.txt
+++ b/Documentation/devicetree/bindings/display/simple-framebuffer-sunxi.txt
@@ -15,6 +15,10 @@ Required properties:
   "de_be1-lcd1"
   "de_be0-lcd0-hdmi"
   "de_be1-lcd1-hdmi"
+  "mixer0-lcd0"
+  "mixer0-lcd0-hdmi"
+  "mixer1-lcd1-hdmi"
+  "mixer1-lcd1-tve"
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/display/sitronix,st7735r.txt b/Documentation/devicetree/bindings/display/sitronix,st7735r.txt
new file mode 100644
index 000000000000..f0a5090a3326
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/sitronix,st7735r.txt
@@ -0,0 +1,35 @@
+Sitronix ST7735R display panels
+
+This binding is for display panels using a Sitronix ST7735R controller in SPI
+mode.
+
+Required properties:
+- compatible:	"jianda,jd-t18003-t01", "sitronix,st7735r"
+- dc-gpios:	Display data/command selection (D/CX)
+- reset-gpios:	Reset signal (RSTX)
+
+The node for this driver must be a child node of a SPI controller, hence
+all mandatory properties described in ../spi/spi-bus.txt must be specified.
+
+Optional properties:
+- rotation:	panel rotation in degrees counter clockwise (0,90,180,270)
+- backlight:	phandle of the backlight device attached to the panel
+
+Example:
+
+	backlight: backlight {
+		compatible = "gpio-backlight";
+		gpios = <&gpio 44 GPIO_ACTIVE_HIGH>;
+	}
+
+	...
+
+	display@0{
+		compatible = "jianda,jd-t18003-t01", "sitronix,st7735r";
+		reg = <0>;
+		spi-max-frequency = <32000000>;
+		dc-gpios = <&gpio 43 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio 80 GPIO_ACTIVE_HIGH>;
+		rotation = <270>;
+		backlight = &backlight;
+	};
diff --git a/Documentation/devicetree/bindings/display/st,stih4xx.txt b/Documentation/devicetree/bindings/display/st,stih4xx.txt
index a352ed30cd70..6778b3e7ad5b 100644
--- a/Documentation/devicetree/bindings/display/st,stih4xx.txt
+++ b/Documentation/devicetree/bindings/display/st,stih4xx.txt
@@ -119,7 +119,7 @@ Example:
 / {
 	...
 
-	vtg_main_slave: sti-vtg-main-slave@fe85A800 {
+	vtg_main_slave: sti-vtg-main-slave@fe85a800 {
 		compatible	= "st,vtg";
 		reg		= <0xfe85A800 0x300>;
 		interrupts	= <GIC_SPI 175 IRQ_TYPE_NONE>;
diff --git a/Documentation/devicetree/bindings/display/st,stm32-ltdc.txt b/Documentation/devicetree/bindings/display/st,stm32-ltdc.txt
index 74b5ac7b26d6..029252253ad4 100644
--- a/Documentation/devicetree/bindings/display/st,stm32-ltdc.txt
+++ b/Documentation/devicetree/bindings/display/st,stm32-ltdc.txt
@@ -10,7 +10,11 @@
       - "lcd" for the clock feeding the output pixel clock & IP clock.
   - resets: reset to be used by the device (defined by use of RCC macro).
   Required nodes:
-    - Video port for RGB output.
+  - Video port for DPI RGB output: ltdc has one video port with up to 2
+    endpoints:
+      - for external dpi rgb panel or bridge, using gpios.
+      - for internal dpi input of the MIPI DSI host controller.
+      Note: These 2 endpoints cannot be activated simultaneously.
 
 * STMicroelectronics STM32 DSI controller specific extensions to Synopsys
   DesignWare MIPI DSI host controller
diff --git a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
index 50cc72ee1168..cd626ee1147a 100644
--- a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
+++ b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
@@ -93,6 +93,7 @@ Required properties:
    * allwinner,sun6i-a31s-tcon
    * allwinner,sun7i-a20-tcon
    * allwinner,sun8i-a33-tcon
+   * allwinner,sun8i-a83t-tcon-lcd
    * allwinner,sun8i-v3s-tcon
  - reg: base address and size of memory-mapped region
  - interrupts: interrupt associated to this IP
@@ -121,6 +122,14 @@ Required properties:
 On SoCs other than the A33 and V3s, there is one more clock required:
    - 'tcon-ch1': The clock driving the TCON channel 1
 
+On SoCs that support LVDS (all SoCs but the A13, H3, H5 and V3s), you
+need one more reset line:
+   - 'lvds': The reset line driving the LVDS logic
+
+And on the A23, A31, A31s and A33, you need one more clock line:
+   - 'lvds-alt': An alternative clock source, separate from the TCON channel 0
+                 clock, that can be used to drive the LVDS clock
+
 DRC
 ---
 
@@ -216,6 +225,7 @@ supported.
 
 Required properties:
   - compatible: value must be one of:
+    * allwinner,sun8i-a83t-de2-mixer-0
     * allwinner,sun8i-v3s-de2-mixer
   - reg: base address and size of the memory-mapped region.
   - clocks: phandles to the clocks feeding the mixer
@@ -245,6 +255,7 @@ Required properties:
     * allwinner,sun6i-a31s-display-engine
     * allwinner,sun7i-a20-display-engine
     * allwinner,sun8i-a33-display-engine
+    * allwinner,sun8i-a83t-display-engine
     * allwinner,sun8i-v3s-display-engine
 
   - allwinner,pipelines: list of phandle to the display engine
diff --git a/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt b/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt
index 844e0103fb0d..593be44a53c9 100644
--- a/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt
+++ b/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt
@@ -206,21 +206,33 @@ of the following host1x client modules:
     - "nvidia,tegra132-sor": for Tegra132
     - "nvidia,tegra210-sor": for Tegra210
     - "nvidia,tegra210-sor1": for Tegra210
+    - "nvidia,tegra186-sor": for Tegra186
+    - "nvidia,tegra186-sor1": for Tegra186
   - reg: Physical base address and length of the controller's registers.
   - interrupts: The interrupt outputs from the controller.
   - clocks: Must contain an entry for each entry in clock-names.
     See ../clocks/clock-bindings.txt for details.
   - clock-names: Must include the following entries:
     - sor: clock input for the SOR hardware
-    - source: source clock for the SOR clock
+    - out: SOR output clock
     - parent: input for the pixel clock
     - dp: reference clock for the SOR clock
     - safe: safe reference for the SOR clock during power up
+
+    For Tegra186 and later:
+    - pad: SOR pad output clock (on Tegra186 and later)
+
+    Obsolete:
+    - source: source clock for the SOR clock (obsolete, use "out" instead)
+
   - resets: Must contain an entry for each entry in reset-names.
     See ../reset/reset.txt for details.
   - reset-names: Must include the following entries:
     - sor
 
+  Required properties on Tegra186 and later:
+  - nvidia,interface: index of the SOR interface
+
   Optional properties:
   - nvidia,ddc-i2c-bus: phandle of an I2C controller used for DDC EDID probing
   - nvidia,hpd-gpio: specifies a GPIO used for hotplug detection
diff --git a/Documentation/devicetree/bindings/display/ti/ti,dra7-dss.txt b/Documentation/devicetree/bindings/display/ti/ti,dra7-dss.txt
index c30f9ec189ed..91279f1060fe 100644
--- a/Documentation/devicetree/bindings/display/ti/ti,dra7-dss.txt
+++ b/Documentation/devicetree/bindings/display/ti/ti,dra7-dss.txt
@@ -47,6 +47,11 @@ Required properties:
 - clocks: handle to fclk
 - clock-names: "fck"
 
+Optional properties:
+- max-memory-bandwidth: Input memory (from main memory to dispc) bandwidth limit
+			in bytes per second
+
+
 HDMI
 ----
 
diff --git a/Documentation/devicetree/bindings/display/ti/ti,omap2-dss.txt b/Documentation/devicetree/bindings/display/ti/ti,omap2-dss.txt
index afcd5a86c6a4..ee867c4d1152 100644
--- a/Documentation/devicetree/bindings/display/ti/ti,omap2-dss.txt
+++ b/Documentation/devicetree/bindings/display/ti/ti,omap2-dss.txt
@@ -28,6 +28,10 @@ Required properties:
 - ti,hwmods: "dss_dispc"
 - interrupts: the DISPC interrupt
 
+Optional properties:
+- max-memory-bandwidth: Input memory (from main memory to dispc) bandwidth limit
+			in bytes per second
+
 
 RFBI
 ----
diff --git a/Documentation/devicetree/bindings/display/ti/ti,omap3-dss.txt b/Documentation/devicetree/bindings/display/ti/ti,omap3-dss.txt
index dc66e1447c31..cd02516a40b6 100644
--- a/Documentation/devicetree/bindings/display/ti/ti,omap3-dss.txt
+++ b/Documentation/devicetree/bindings/display/ti/ti,omap3-dss.txt
@@ -37,6 +37,10 @@ Required properties:
 - clocks: handle to fclk
 - clock-names: "fck"
 
+Optional properties:
+- max-memory-bandwidth: Input memory (from main memory to dispc) bandwidth limit
+			in bytes per second
+
 
 RFBI
 ----
diff --git a/Documentation/devicetree/bindings/display/ti/ti,omap4-dss.txt b/Documentation/devicetree/bindings/display/ti/ti,omap4-dss.txt
index bc624db8888d..0f85f6b3a5a8 100644
--- a/Documentation/devicetree/bindings/display/ti/ti,omap4-dss.txt
+++ b/Documentation/devicetree/bindings/display/ti/ti,omap4-dss.txt
@@ -36,6 +36,10 @@ Required properties:
 - clocks: handle to fclk
 - clock-names: "fck"
 
+Optional properties:
+- max-memory-bandwidth: Input memory (from main memory to dispc) bandwidth limit
+			in bytes per second
+
 
 RFBI
 ----
diff --git a/Documentation/devicetree/bindings/display/ti/ti,omap5-dss.txt b/Documentation/devicetree/bindings/display/ti/ti,omap5-dss.txt
index 118a486c47bb..20861218649f 100644
--- a/Documentation/devicetree/bindings/display/ti/ti,omap5-dss.txt
+++ b/Documentation/devicetree/bindings/display/ti/ti,omap5-dss.txt
@@ -36,6 +36,10 @@ Required properties:
 - clocks: handle to fclk
 - clock-names: "fck"
 
+Optional properties:
+- max-memory-bandwidth: Input memory (from main memory to dispc) bandwidth limit
+			in bytes per second
+
 
 RFBI
 ----
diff --git a/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt b/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
index 55492c264d17..1ae4748730a8 100644
--- a/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
+++ b/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
@@ -47,8 +47,8 @@ When the OS is not in control of the management interface (i.e. it's a guest),
 the channel nodes appear on their own, not under a management node.
 
 Required properties:
-- compatible: must contain "qcom,hidma-1.0" for initial HW or "qcom,hidma-1.1"
-for MSI capable HW.
+- compatible: must contain "qcom,hidma-1.0" for initial HW or
+  "qcom,hidma-1.1"/"qcom,hidma-1.2" for MSI capable HW.
 - reg: Addresses for the transfer and event channel
 - interrupts: Should contain the event interrupt
 - desc-count: Number of asynchronous requests this channel can handle
@@ -73,7 +73,7 @@ Hypervisor OS configuration:
 		max-read-transactions = <31>;
 		channel-reset-timeout-cycles = <0x500>;
 
-		hidma_24: dma-controller@0x5c050000 {
+		hidma_24: dma-controller@5c050000 {
 			compatible = "qcom,hidma-1.0";
 			reg = <0 0x5c050000 0x0 0x1000>,
 			      <0 0x5c0b0000 0x0 0x1000>;
@@ -85,7 +85,7 @@ Hypervisor OS configuration:
 
 Guest OS configuration:
 
-	hidma_24: dma-controller@0x5c050000 {
+	hidma_24: dma-controller@5c050000 {
 		compatible = "qcom,hidma-1.0";
 		reg = <0 0x5c050000 0x0 0x1000>,
 		      <0 0x5c0b0000 0x0 0x1000>;
diff --git a/Documentation/devicetree/bindings/dma/snps-dma.txt b/Documentation/devicetree/bindings/dma/snps-dma.txt
index a122723907ac..99acc712f83a 100644
--- a/Documentation/devicetree/bindings/dma/snps-dma.txt
+++ b/Documentation/devicetree/bindings/dma/snps-dma.txt
@@ -64,6 +64,6 @@ Example:
 		reg = <0xe0000000 0x1000>;
 		interrupts = <0 35 0x4>;
 		dmas = <&dmahost 12 0 1>,
-			<&dmahost 13 0 1 0>;
+			<&dmahost 13 1 0>;
 		dma-names = "rx", "rx";
 	};
diff --git a/Documentation/devicetree/bindings/dma/ste-dma40.txt b/Documentation/devicetree/bindings/dma/ste-dma40.txt
index aa7dbd565ad0..99ab5c4d331e 100644
--- a/Documentation/devicetree/bindings/dma/ste-dma40.txt
+++ b/Documentation/devicetree/bindings/dma/ste-dma40.txt
@@ -15,7 +15,7 @@ Optional properties:
 
 Example:
 
-	dma: dma-controller@801C0000 {
+	dma: dma-controller@801c0000 {
 		compatible = "stericsson,db8500-dma40", "stericsson,dma40";
 		reg = <0x801C0000 0x1000  0x40010000 0x800>;
 		reg-names = "base", "lcpa";
diff --git a/Documentation/devicetree/bindings/dma/zxdma.txt b/Documentation/devicetree/bindings/dma/zxdma.txt
index abec59f35fde..0ab80f69e566 100644
--- a/Documentation/devicetree/bindings/dma/zxdma.txt
+++ b/Documentation/devicetree/bindings/dma/zxdma.txt
@@ -13,7 +13,7 @@ Required properties:
 Example:
 
 Controller:
-	dma: dma-controller@0x09c00000{
+	dma: dma-controller@09c00000{
 		compatible = "zte,zx296702-dma";
 		reg = <0x09c00000 0x1000>;
 		clocks = <&topclk ZX296702_DMA_ACLK>;
diff --git a/Documentation/devicetree/bindings/eeprom/at25.txt b/Documentation/devicetree/bindings/eeprom/at25.txt
index 1d3447165c37..b3bde97dc199 100644
--- a/Documentation/devicetree/bindings/eeprom/at25.txt
+++ b/Documentation/devicetree/bindings/eeprom/at25.txt
@@ -1,19 +1,26 @@
 EEPROMs (SPI) compatible with Atmel at25.
 
 Required properties:
-- compatible : "atmel,at25".
+- compatible : Should be "<vendor>,<type>", and generic value "atmel,at25".
+  Example "<vendor>,<type>" values:
+    "microchip,25lc040"
+    "st,m95m02"
+    "st,m95256"
+
 - reg : chip select number
 - spi-max-frequency : max spi frequency to use
 - pagesize : size of the eeprom page
 - size : total eeprom size in bytes
-- address-width : number of address bits (one of 8, 16, or 24)
+- address-width : number of address bits (one of 8, 9, 16, or 24).
+  For 9 bits, the MSB of the address is sent as bit 3 of the instruction
+  byte, before the address byte.
 
 Optional properties:
 - spi-cpha : SPI shifted clock phase, as per spi-bus bindings.
 - spi-cpol : SPI inverse clock polarity, as per spi-bus bindings.
 - read-only : this parameter-less property disables writes to the eeprom
 
-Obsolete legacy properties are can be used in place of "size", "pagesize",
+Obsolete legacy properties can be used in place of "size", "pagesize",
 "address-width", and "read-only":
 - at25,byte-len : total eeprom size in bytes
 - at25,addr-mode : addr-mode flags, as defined in include/linux/spi/eeprom.h
@@ -22,8 +29,8 @@ Obsolete legacy properties are can be used in place of "size", "pagesize",
 Additional compatible properties are also allowed.
 
 Example:
-	at25@0 {
-		compatible = "atmel,at25", "st,m95256";
+	eeprom@0 {
+		compatible = "st,m95256", "atmel,at25";
 		reg = <0>
 		spi-max-frequency = <5000000>;
 		spi-cpha;
diff --git a/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt b/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt
index 00611aceed3e..a25c87b650e5 100644
--- a/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt
@@ -21,7 +21,7 @@ Documentation/devicetree/bindings/gpio/gpio.txt
 
 Example:
 
-	gpioa: gpio@FF140000 {
+	gpioa: gpio@ff140000 {
 		compatible = "abilis,tb10x-gpio";
 		interrupt-controller;
 		#interrupt-cells = <1>;
diff --git a/Documentation/devicetree/bindings/gpio/gpio-altera.txt b/Documentation/devicetree/bindings/gpio/gpio-altera.txt
index 826a7208ca93..146e554b3c67 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-altera.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-altera.txt
@@ -30,7 +30,7 @@ Optional properties:
 
 Example:
 
-gpio_altr: gpio@0xff200000 {
+gpio_altr: gpio@ff200000 {
 	compatible = "altr,pio-1.0";
 	reg = <0xff200000 0x10>;
 	interrupts = <0 45 4>;
diff --git a/Documentation/devicetree/bindings/gpio/gpio-axp209.txt b/Documentation/devicetree/bindings/gpio/gpio-axp209.txt
index a6611304dd3c..fc42b2caa06d 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-axp209.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-axp209.txt
@@ -1,10 +1,17 @@
-AXP209 GPIO controller
+AXP209 GPIO & pinctrl controller
 
 This driver follows the usual GPIO bindings found in
 Documentation/devicetree/bindings/gpio/gpio.txt
 
+This driver follows the usual pinctrl bindings found in
+Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
+
+This driver employs the per-pin muxing pattern.
+
 Required properties:
-- compatible: Should be "x-powers,axp209-gpio"
+- compatible: Should be one of:
+	- "x-powers,axp209-gpio"
+	- "x-powers,axp813-gpio"
 - #gpio-cells: Should be two. The first cell is the pin number and the
   second is the GPIO flags.
 - gpio-controller: Marks the device node as a GPIO controller.
@@ -28,3 +35,41 @@ axp209: pmic@34 {
 		#gpio-cells = <2>;
 	};
 };
+
+The GPIOs can be muxed to other functions and therefore, must be a subnode of
+axp_gpio.
+
+Example:
+
+&axp_gpio {
+	gpio0_adc: gpio0-adc {
+		pins = "GPIO0";
+		function = "adc";
+	};
+};
+
+&example_node {
+	pinctrl-names = "default";
+	pinctrl-0 = <&gpio0_adc>;
+};
+
+GPIOs and their functions
+-------------------------
+
+Each GPIO is independent from the other (i.e. GPIO0 in gpio_in function does
+not force GPIO1 and GPIO2 to be in gpio_in function as well).
+
+axp209
+------
+GPIO	|	Functions
+------------------------
+GPIO0	|	gpio_in, gpio_out, ldo, adc
+GPIO1	|	gpio_in, gpio_out, ldo, adc
+GPIO2	|	gpio_in, gpio_out
+
+axp813
+------
+GPIO	|	Functions
+------------------------
+GPIO0	|	gpio_in, gpio_out, ldo, adc
+GPIO1	|	gpio_in, gpio_out, ldo
diff --git a/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
index 7f57271df2bc..0d0158728f89 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
@@ -27,7 +27,7 @@ Required properties:
 	ti,tca6424
 	ti,tca9539
 	ti,tca9554
-	onsemi,pca9654
+	onnn,pca9654
 	exar,xra1202
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/gpio/gpio-stp-xway.txt b/Documentation/devicetree/bindings/gpio/gpio-stp-xway.txt
index 854de130a971..78458adbf4b7 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-stp-xway.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-stp-xway.txt
@@ -27,7 +27,7 @@ Optional properties:
 
 Example:
 
-gpio1: stp@E100BB0 {
+gpio1: stp@e100bb0 {
 	compatible = "lantiq,gpio-stp-xway";
 	reg = <0xE100BB0 0x40>;
 	#gpio-cells = <2>;
diff --git a/Documentation/devicetree/bindings/gpio/gpio.txt b/Documentation/devicetree/bindings/gpio/gpio.txt
index 802402f6cc5d..b5de08e3b1a2 100644
--- a/Documentation/devicetree/bindings/gpio/gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio.txt
@@ -290,7 +290,7 @@ pins 50..69.
 
 Example 2:
 
-	gpio_pio_i: gpio-controller@14B0 {
+	gpio_pio_i: gpio-controller@14b0 {
 		#gpio-cells = <2>;
 		compatible = "fsl,qe-pario-bank-e", "fsl,qe-pario-bank";
 		reg = <0x1480 0x18>;
diff --git a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
index a7ac460ad657..9474138d776e 100644
--- a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
+++ b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
@@ -5,7 +5,7 @@ Required Properties:
   - compatible: should contain one or more of the following:
     - "renesas,gpio-r8a7743": for R8A7743 (RZ/G1M) compatible GPIO controller.
     - "renesas,gpio-r8a7745": for R8A7745 (RZ/G1E) compatible GPIO controller.
-    - "renesas,gpio-r8a7778": for R8A7778 (R-Mobile M1) compatible GPIO controller.
+    - "renesas,gpio-r8a7778": for R8A7778 (R-Car M1) compatible GPIO controller.
     - "renesas,gpio-r8a7779": for R8A7779 (R-Car H1) compatible GPIO controller.
     - "renesas,gpio-r8a7790": for R8A7790 (R-Car H2) compatible GPIO controller.
     - "renesas,gpio-r8a7791": for R8A7791 (R-Car M2-W) compatible GPIO controller.
diff --git a/Documentation/devicetree/bindings/gpu/arm,mali-utgard.txt b/Documentation/devicetree/bindings/gpu/arm,mali-utgard.txt
index c6814d7cc2b2..ad876548ab5d 100644
--- a/Documentation/devicetree/bindings/gpu/arm,mali-utgard.txt
+++ b/Documentation/devicetree/bindings/gpu/arm,mali-utgard.txt
@@ -17,6 +17,7 @@ Required properties:
       + rockchip,rk3066-mali
       + rockchip,rk3188-mali
       + rockchip,rk3228-mali
+      + rockchip,rk3328-mali
       + stericsson,db8500-mali
 
   - reg: Physical base address and length of the GPU registers
diff --git a/Documentation/devicetree/bindings/hwmon/aspeed-pwm-tacho.txt b/Documentation/devicetree/bindings/hwmon/aspeed-pwm-tacho.txt
index 367c8203213b..3ac02988a1a5 100644
--- a/Documentation/devicetree/bindings/hwmon/aspeed-pwm-tacho.txt
+++ b/Documentation/devicetree/bindings/hwmon/aspeed-pwm-tacho.txt
@@ -22,8 +22,9 @@ Required properties for pwm-tacho node:
 - compatible : should be "aspeed,ast2400-pwm-tacho" for AST2400 and
 	       "aspeed,ast2500-pwm-tacho" for AST2500.
 
-- clocks : a fixed clock providing input clock frequency(PWM
-	   and Fan Tach clock)
+- clocks : phandle to clock provider with the clock number in the second cell
+
+- resets : phandle to reset controller with the reset number in the second cell
 
 fan subnode format:
 ===================
@@ -48,19 +49,14 @@ Required properties for each child node:
 
 Examples:
 
-pwm_tacho_fixed_clk: fixedclk {
-	compatible = "fixed-clock";
-	#clock-cells = <0>;
-	clock-frequency = <24000000>;
-};
-
 pwm_tacho: pwmtachocontroller@1e786000 {
 	#address-cells = <1>;
 	#size-cells = <1>;
 	#cooling-cells = <2>;
 	reg = <0x1E786000 0x1000>;
 	compatible = "aspeed,ast2500-pwm-tacho";
-	clocks = <&pwm_tacho_fixed_clk>;
+	clocks = <&syscon ASPEED_CLK_APB>;
+	resets = <&syscon ASPEED_RESET_PWM>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_pwm0_default &pinctrl_pwm1_default>;
 
diff --git a/Documentation/devicetree/bindings/hwmon/jc42.txt b/Documentation/devicetree/bindings/hwmon/jc42.txt
index 07a250498fbb..f569db58f64a 100644
--- a/Documentation/devicetree/bindings/hwmon/jc42.txt
+++ b/Documentation/devicetree/bindings/hwmon/jc42.txt
@@ -34,6 +34,10 @@ Required properties:
 
 - reg: I2C address
 
+Optional properties:
+- smbus-timeout-disable: When set, the smbus timeout function will be disabled.
+			 This is not supported on all chips.
+
 Example:
 
 temp-sensor@1a {
diff --git a/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt b/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt
index 248a155414c2..548a73cde796 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt
@@ -54,7 +54,7 @@ Optional properties:
 
 
 Example:
-	i2c@12CA0000 {
+	i2c@12ca0000 {
 		compatible = "acme,some-i2c-device";
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
index 70c054a9a997..60fe90d69f4e 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
@@ -11,7 +11,7 @@ Required properties:
 
 Examples:
 
-lpi2c7: lpi2c7@40A50000 {
+lpi2c7: lpi2c7@40a50000 {
 	compatible = "fsl,imx8dv-lpi2c";
 	reg = <0x40A50000 0x10000>;
 	interrupt-parent = <&intc>;
diff --git a/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt b/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt
index 231e4cc4008c..d4a082acf92f 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt
@@ -18,7 +18,7 @@ Optional properties:
 Example
 
 / {
-	i2c4: i2c4@0x10054000 {
+	i2c4: i2c4@10054000 {
 		compatible = "ingenic,jz4780-i2c";
 		reg = <0x10054000 0x1000>;
 
diff --git a/Documentation/devicetree/bindings/iio/adc/amlogic,meson-saradc.txt b/Documentation/devicetree/bindings/iio/adc/amlogic,meson-saradc.txt
index f413e82c8b83..1e6ee3deb4fa 100644
--- a/Documentation/devicetree/bindings/iio/adc/amlogic,meson-saradc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/amlogic,meson-saradc.txt
@@ -15,7 +15,6 @@ Required properties:
 			- "clkin" for the reference clock (typically XTAL)
 			- "core" for the SAR ADC core clock
 		optional clocks:
-			- "sana" for the analog clock
 			- "adc_clk" for the ADC (sampling) clock
 			- "adc_sel" for the ADC (sampling) clock mux
 - vref-supply:	the regulator supply for the ADC reference voltage
diff --git a/Documentation/devicetree/bindings/iio/adc/aspeed_adc.txt b/Documentation/devicetree/bindings/iio/adc/aspeed_adc.txt
index 674e133b7cd7..034fc2ba100e 100644
--- a/Documentation/devicetree/bindings/iio/adc/aspeed_adc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/aspeed_adc.txt
@@ -8,6 +8,7 @@ Required properties:
 - reg: memory window mapping address and length
 - clocks: Input clock used to derive the sample clock. Expected to be the
           SoC's APB clock.
+- resets: Reset controller phandle
 - #io-channel-cells: Must be set to <1> to indicate channels are selected
                      by index.
 
@@ -15,6 +16,7 @@ Example:
 	adc@1e6e9000 {
 		compatible = "aspeed,ast2400-adc";
 		reg = <0x1e6e9000 0xb0>;
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_ADC>;
 		#io-channel-cells = <1>;
 	};
diff --git a/Documentation/devicetree/bindings/iio/adc/at91-sama5d2_adc.txt b/Documentation/devicetree/bindings/iio/adc/at91-sama5d2_adc.txt
index 552e7a83951d..6469a4cd2a6d 100644
--- a/Documentation/devicetree/bindings/iio/adc/at91-sama5d2_adc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/at91-sama5d2_adc.txt
@@ -17,6 +17,11 @@ Required properties:
   This property uses the IRQ edge types values: IRQ_TYPE_EDGE_RISING ,
   IRQ_TYPE_EDGE_FALLING or IRQ_TYPE_EDGE_BOTH
 
+Optional properties:
+  - dmas: Phandle to dma channel for the ADC.
+  - dma-names: Must be "rx" when dmas property is being used.
+  See ../../dma/dma.txt for details.
+
 Example:
 
 adc: adc@fc030000 {
@@ -31,4 +36,6 @@ adc: adc@fc030000 {
 	vddana-supply = <&vdd_3v3_lp_reg>;
 	vref-supply = <&vdd_3v3_lp_reg>;
 	atmel,trigger-edge-type = <IRQ_TYPE_EDGE_BOTH>;
+	dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | AT91_XDMAC_DT_PERID(25))>;
+	dma-names = "rx";
 }
diff --git a/Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.txt b/Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.txt
new file mode 100644
index 000000000000..e9ebb8a20e0d
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.txt
@@ -0,0 +1,13 @@
+Device-Tree bindings for sigma delta modulator
+
+Required properties:
+- compatible: should be "ads1201", "sd-modulator". "sd-modulator" can be use
+	as a generic SD modulator if modulator not specified in compatible list.
+- #io-channel-cells = <1>: See the IIO bindings section "IIO consumers".
+
+Example node:
+
+	ads1202: adc@0 {
+		compatible = "sd-modulator";
+		#io-channel-cells = <1>;
+	};
diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt
index 48bfcaa3ffcd..e8bb8243e92c 100644
--- a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt
@@ -62,6 +62,15 @@ Required properties:
 - st,adc-channels: List of single-ended channels muxed for this ADC.
   It can have up to 16 channels on stm32f4 or 20 channels on stm32h7, numbered
   from 0 to 15 or 19 (resp. for in0..in15 or in0..in19).
+- st,adc-diff-channels: List of differential channels muxed for this ADC.
+  Depending on part used, some channels can be configured as differential
+  instead of single-ended (e.g. stm32h7). List here positive and negative
+  inputs pairs as <vinp vinn>, <vinp vinn>,... vinp and vinn are numbered
+  from 0 to 19 on stm32h7)
+  Note: At least one of "st,adc-channels" or "st,adc-diff-channels" is required.
+  Both properties can be used together. Some channels can be used as
+  single-ended and some other ones as differential (mixed). But channels
+  can't be configured both as single-ended and differential (invalid).
 - #io-channel-cells = <1>: See the IIO bindings section "IIO consumers" in
   Documentation/devicetree/bindings/iio/iio-bindings.txt
 
@@ -111,3 +120,18 @@ Example:
 		...
 		other adc child nodes follow...
 	};
+
+Example to setup:
+- channel 1 as single-ended
+- channels 2 & 3 as differential (with resp. 6 & 7 negative inputs)
+
+	adc: adc@40022000 {
+		compatible = "st,stm32h7-adc-core";
+		...
+		adc1: adc@0 {
+			compatible = "st,stm32h7-adc";
+			...
+			st,adc-channels = <1>;
+			st,adc-diff-channels = <2 6>, <3 7>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.txt b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.txt
new file mode 100644
index 000000000000..911492da48f3
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.txt
@@ -0,0 +1,128 @@
+STMicroelectronics STM32 DFSDM ADC device driver
+
+
+STM32 DFSDM ADC is a sigma delta analog-to-digital converter dedicated to
+interface external sigma delta modulators to STM32 micro controllers.
+It is mainly targeted for:
+- Sigma delta modulators (motor control, metering...)
+- PDM microphones (audio digital microphone)
+
+It features up to 8 serial digital interfaces (SPI or Manchester) and
+up to 4 filters on stm32h7.
+
+Each child node match with a filter instance.
+
+Contents of a STM32 DFSDM root node:
+------------------------------------
+Required properties:
+- compatible: Should be "st,stm32h7-dfsdm".
+- reg: Offset and length of the DFSDM block register set.
+- clocks: IP and serial interfaces clocking. Should be set according
+		to rcc clock ID and "clock-names".
+- clock-names: Input clock name "dfsdm" must be defined,
+		"audio" is optional. If defined CLKOUT is based on the audio
+		clock, else "dfsdm" is used.
+- #interrupt-cells = <1>;
+- #address-cells = <1>;
+- #size-cells = <0>;
+
+Optional properties:
+- spi-max-frequency: Requested only for SPI master mode.
+		  SPI clock OUT frequency (Hz). This clock must be set according
+		  to "clock" property. Frequency must be a multiple of the rcc
+		  clock frequency. If not, SPI CLKOUT frequency will not be
+		  accurate.
+
+Contents of a STM32 DFSDM child nodes:
+--------------------------------------
+
+Required properties:
+- compatible: Must be:
+	"st,stm32-dfsdm-adc" for sigma delta ADCs
+	"st,stm32-dfsdm-dmic" for audio digital microphone.
+- reg: Specifies the DFSDM filter instance used.
+- interrupts: IRQ lines connected to each DFSDM filter instance.
+- st,adc-channels:	List of single-ended channels muxed for this ADC.
+			valid values:
+				"st,stm32h7-dfsdm" compatibility: 0 to 7.
+- st,adc-channel-names:	List of single-ended channel names.
+- st,filter-order:  SinC filter order from 0 to 5.
+			0: FastSinC
+			[1-5]: order 1 to 5.
+			For audio purpose it is recommended to use order 3 to 5.
+- #io-channel-cells = <1>: See the IIO bindings section "IIO consumers".
+
+Required properties for "st,stm32-dfsdm-adc" compatibility:
+- io-channels: From common IIO binding. Used to pipe external sigma delta
+		modulator or internal ADC output to DFSDM channel.
+		This is not required for "st,stm32-dfsdm-pdm" compatibility as
+		PDM microphone is binded in Audio DT node.
+
+Required properties for "st,stm32-dfsdm-pdm" compatibility:
+- #sound-dai-cells: Must be set to 0.
+- dma: DMA controller phandle and DMA request line associated to the
+		filter instance (specified by the field "reg")
+- dma-names: Must be "rx"
+
+Optional properties:
+- st,adc-channel-types:	Single-ended channel input type.
+			- "SPI_R": SPI with data on rising edge (default)
+			- "SPI_F": SPI with data on falling edge
+			- "MANCH_R": manchester codec, rising edge = logic 0
+			- "MANCH_F": manchester codec, falling edge = logic 1
+- st,adc-channel-clk-src: Conversion clock source.
+			  - "CLKIN": external SPI clock (CLKIN x)
+			  - "CLKOUT": internal SPI clock (CLKOUT) (default)
+			  - "CLKOUT_F": internal SPI clock divided by 2 (falling edge).
+			  - "CLKOUT_R": internal SPI clock divided by 2 (rising edge).
+
+- st,adc-alt-channel: Must be defined if two sigma delta modulator are
+			  connected on same SPI input.
+			  If not set, channel n is connected to SPI input n.
+			  If set, channel n is connected to SPI input n + 1.
+
+- st,filter0-sync: Set to 1 to synchronize with DFSDM filter instance 0.
+		   Used for multi microphones synchronization.
+
+Example of a sigma delta adc connected on DFSDM SPI port 0
+and a pdm microphone connected on DFSDM SPI port 1:
+
+	ads1202: simple_sd_adc@0 {
+		compatible = "ads1202";
+		#io-channel-cells = <1>;
+	};
+
+	dfsdm: dfsdm@40017000 {
+		compatible = "st,stm32h7-dfsdm";
+		reg = <0x40017000 0x400>;
+		clocks = <&rcc DFSDM1_CK>;
+		clock-names = "dfsdm";
+		#interrupt-cells = <1>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		dfsdm_adc0: filter@0 {
+			compatible = "st,stm32-dfsdm-adc";
+			#io-channel-cells = <1>;
+			reg = <0>;
+			interrupts = <110>;
+			st,adc-channels = <0>;
+			st,adc-channel-names = "sd_adc0";
+			st,adc-channel-types = "SPI_F";
+			st,adc-channel-clk-src = "CLKOUT";
+			io-channels = <&ads1202 0>;
+			st,filter-order = <3>;
+		};
+		dfsdm_pdm1: filter@1 {
+			compatible = "st,stm32-dfsdm-dmic";
+			reg = <1>;
+			interrupts = <111>;
+			dmas = <&dmamux1 102 0x400 0x00>;
+			dma-names = "rx";
+			st,adc-channels = <1>;
+			st,adc-channel-names = "dmic1";
+			st,adc-channel-types = "SPI_R";
+			st,adc-channel-clk-src = "CLKOUT";
+			st,filter-order = <5>;
+		};
+	}
diff --git a/Documentation/devicetree/bindings/iio/health/max30102.txt b/Documentation/devicetree/bindings/iio/health/max30102.txt
index 8629c18b0e78..ef2ca0a0306f 100644
--- a/Documentation/devicetree/bindings/iio/health/max30102.txt
+++ b/Documentation/devicetree/bindings/iio/health/max30102.txt
@@ -1,9 +1,11 @@
 Maxim MAX30102 heart rate and pulse oximeter sensor
+Maxim MAX30105 optical particle-sensing module
 
 * https://datasheets.maximintegrated.com/en/ds/MAX30102.pdf
+* https://datasheets.maximintegrated.com/en/ds/MAX30105.pdf
 
 Required properties:
-  - compatible: must be "maxim,max30102"
+  - compatible: must be "maxim,max30102" or "maxim,max30105"
   - reg: the I2C address of the sensor
   - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
@@ -12,8 +14,10 @@ Required properties:
   interrupt client node bindings.
 
 Optional properties:
-  - maxim,red-led-current-microamp: configuration for RED LED current
+  - maxim,red-led-current-microamp: configuration for red LED current
   - maxim,ir-led-current-microamp: configuration for IR LED current
+  - maxim,green-led-current-microamp: configuration for green LED current
+    (max30105 only)
 
     Note that each step is approximately 200 microamps, ranging from 0 uA to
     50800 uA.
diff --git a/Documentation/devicetree/bindings/iio/light/uvis25.txt b/Documentation/devicetree/bindings/iio/light/uvis25.txt
new file mode 100644
index 000000000000..3041207e3f3c
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/light/uvis25.txt
@@ -0,0 +1,23 @@
+* ST UVIS25 uv sensor
+
+Required properties:
+- compatible: should be "st,uvis25"
+- reg: i2c address of the sensor / spi cs line
+
+Optional properties:
+- interrupt-parent: should be the phandle for the interrupt controller
+- interrupts: interrupt mapping for IRQ. It should be configured with
+  flags IRQ_TYPE_LEVEL_HIGH, IRQ_TYPE_EDGE_RISING, IRQ_TYPE_LEVEL_LOW or
+  IRQ_TYPE_EDGE_FALLING.
+
+  Refer to interrupt-controller/interrupts.txt for generic interrupt
+  client node bindings.
+
+Example:
+
+uvis25@47 {
+	compatible = "st,uvis25";
+	reg = <0x47>;
+	interrupt-parent = <&gpio0>;
+	interrupts = <0 IRQ_TYPE_EDGE_RISING>;
+};
diff --git a/Documentation/devicetree/bindings/iio/pressure/hp03.txt b/Documentation/devicetree/bindings/iio/pressure/hp03.txt
index 54e7e70bcea5..831dbee7a5c3 100644
--- a/Documentation/devicetree/bindings/iio/pressure/hp03.txt
+++ b/Documentation/devicetree/bindings/iio/pressure/hp03.txt
@@ -10,7 +10,7 @@ Required properties:
 
 Example:
 
-hp03@0x77 {
+hp03@77 {
 	compatible = "hoperf,hp03";
 	reg = <0x77>;
 	xclr-gpio = <&portc 0 0x0>;
diff --git a/Documentation/devicetree/bindings/input/hid-over-i2c.txt b/Documentation/devicetree/bindings/input/hid-over-i2c.txt
index 28e8bd8b7d64..4d3da9d91de4 100644
--- a/Documentation/devicetree/bindings/input/hid-over-i2c.txt
+++ b/Documentation/devicetree/bindings/input/hid-over-i2c.txt
@@ -31,7 +31,7 @@ device-specific compatible properties, which should be used in addition to the
 
 - vdd-supply: phandle of the regulator that provides the supply voltage.
 - post-power-on-delay-ms: time required by the device after enabling its regulators
-  before it is ready for communication. Must be used with 'vdd-supply'.
+  or powering it on, before it is ready for communication.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/input/samsung-keypad.txt b/Documentation/devicetree/bindings/input/samsung-keypad.txt
index 5305e74e5742..4c5c0a82586d 100644
--- a/Documentation/devicetree/bindings/input/samsung-keypad.txt
+++ b/Documentation/devicetree/bindings/input/samsung-keypad.txt
@@ -45,7 +45,7 @@ Optional Properties specific to linux:
 
 
 Example:
-	keypad@100A0000 {
+	keypad@100a0000 {
 		compatible = "samsung,s5pv210-keypad";
 		reg = <0x100A0000 0x100>;
 		interrupts = <173>;
diff --git a/Documentation/devicetree/bindings/input/touchscreen/brcm,iproc-touchscreen.txt b/Documentation/devicetree/bindings/input/touchscreen/brcm,iproc-touchscreen.txt
index ac5dff412e25..f127a2117072 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/brcm,iproc-touchscreen.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/brcm,iproc-touchscreen.txt
@@ -66,7 +66,7 @@ Example: An example of touchscreen node
 		reg = <0x180a6000 0xc30>;
 	};
 
-	touchscreen: touchscreen@180A6000 {
+	touchscreen: touchscreen@180a6000 {
 		compatible = "brcm,iproc-touchscreen";
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/Documentation/devicetree/bindings/input/touchscreen/bu21013.txt b/Documentation/devicetree/bindings/input/touchscreen/bu21013.txt
index ca5a2c86480c..56d835242af2 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/bu21013.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/bu21013.txt
@@ -15,7 +15,7 @@ Optional properties:
 Example:
 
 	i2c@80110000 {
-		bu21013_tp@0x5c {
+		bu21013_tp@5c {
 			compatible = "rohm,bu21013_tp";
 			reg = <0x5c>;
 			touch-gpio = <&gpio2 20 0x4>;
diff --git a/Documentation/devicetree/bindings/input/touchscreen/mms114.txt b/Documentation/devicetree/bindings/input/touchscreen/mms114.txt
index 89d4c56c5671..2cd954051d29 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/mms114.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/mms114.txt
@@ -1,17 +1,23 @@
-* MELFAS MMS114 touchscreen controller
+* MELFAS MMS114/MMS152 touchscreen controller
 
 Required properties:
-- compatible: must be "melfas,mms114"
+- compatible: should be one of:
+	- "melfas,mms114"
+	- "melfas,mms152"
 - reg: I2C address of the chip
 - interrupts: interrupt to which the chip is connected
-- x-size: horizontal resolution of touchscreen
-- y-size: vertical resolution of touchscreen
+- touchscreen-size-x: See [1]
+- touchscreen-size-y: See [1]
 
 Optional properties:
-- contact-threshold:
-- moving-threshold:
-- x-invert: invert X axis
-- y-invert: invert Y axis
+- touchscreen-fuzz-x: See [1]
+- touchscreen-fuzz-y: See [1]
+- touchscreen-fuzz-pressure: See [1]
+- touchscreen-inverted-x: See [1]
+- touchscreen-inverted-y: See [1]
+- touchscreen-swapped-x-y: See [1]
+
+[1]: Documentation/devicetree/bindings/input/touchscreen/touchscreen.txt
 
 Example:
 
@@ -22,12 +28,13 @@ Example:
 			compatible = "melfas,mms114";
 			reg = <0x48>;
 			interrupts = <39 0>;
-			x-size = <720>;
-			y-size = <1280>;
-			contact-threshold = <10>;
-			moving-threshold = <10>;
-			x-invert;
-			y-invert;
+			touchscreen-size-x = <720>;
+			touchscreen-size-y = <1280>;
+			touchscreen-fuzz-x = <10>;
+			touchscreen-fuzz-y = <10>;
+			touchscreen-fuzz-pressure = <10>;
+			touchscreen-inverted-x;
+			touchscreen-inverted-y;
 		};
 
 		/* ... */
diff --git a/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt b/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt
index 6aa625e0cb8d..84752de12412 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt
@@ -23,6 +23,8 @@ Optional properties:
 - touchscreen-inverted-y  : See touchscreen.txt
 - touchscreen-swapped-x-y : See touchscreen.txt
 - silead,max-fingers	  : maximum number of fingers the touchscreen can detect
+- silead,home-button	  : Boolean, set to true on devices which have a
+			    capacitive home-button build into the touchscreen
 - vddio-supply		  : regulator phandle for controller VDDIO
 - avdd-supply		  : regulator phandle for controller AVDD
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
index 560d8a727b8f..2f3244648646 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
@@ -155,7 +155,7 @@ Example:
 		      <0x0 0xe112f000 0 0x02000>,
 		      <0x0 0xe1140000 0 0x10000>,
 		      <0x0 0xe1160000 0 0x10000>;
-		v2m0: v2m@0x8000 {
+		v2m0: v2m@8000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x80000 0 0x1000>;
@@ -163,7 +163,7 @@ Example:
 
 		....
 
-		v2mN: v2m@0x9000 {
+		v2mN: v2m@9000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x90000 0 0x1000>;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2836-l1-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2836-l1-intc.txt
index f320dcd6e69b..8ced1696c325 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2836-l1-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2836-l1-intc.txt
@@ -12,7 +12,7 @@ Required properties:
 			  registers
 - interrupt-controller:	Identifies the node as an interrupt controller
 - #interrupt-cells:	Specifies the number of cells needed to encode an
-			  interrupt source. The value shall be 1
+			  interrupt source. The value shall be 2
 
 Please refer to interrupts.txt in this directory for details of the common
 Interrupt Controllers bindings used by client devices.
@@ -32,6 +32,6 @@ local_intc: local_intc {
 	compatible = "brcm,bcm2836-l1-intc";
 	reg = <0x40000000 0x100>;
 	interrupt-controller;
-	#interrupt-cells = <1>;
+	#interrupt-cells = <2>;
 	interrupt-parent = <&local_intc>;
 };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/google,goldfish-pic.txt b/Documentation/devicetree/bindings/interrupt-controller/google,goldfish-pic.txt
new file mode 100644
index 000000000000..35f752706e7d
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/google,goldfish-pic.txt
@@ -0,0 +1,30 @@
+Android Goldfish PIC
+
+Android Goldfish programmable interrupt device used by Android
+emulator.
+
+Required properties:
+
+- compatible : should contain "google,goldfish-pic"
+- reg        : <registers mapping>
+- interrupts : <interrupt mapping>
+
+Example for mips when used in cascade mode:
+
+        cpuintc {
+                #interrupt-cells = <0x1>;
+                #address-cells = <0>;
+                interrupt-controller;
+                compatible = "mti,cpu-interrupt-controller";
+        };
+
+        interrupt-controller@1f000000 {
+                compatible = "google,goldfish-pic";
+                reg = <0x1f000000 0x1000>;
+
+                interrupt-controller;
+                #interrupt-cells = <0x1>;
+
+                interrupt-parent = <&cpuintc>;
+                interrupts = <0x2>;
+        };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/img,meta-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/img,meta-intc.txt
index 80994adab392..42431f44697f 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/img,meta-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/img,meta-intc.txt
@@ -71,7 +71,7 @@ Example 2:
 	 * An interrupt generating device that is wired to a Meta external
 	 * trigger block.
 	 */
-	uart1: uart@0x02004c00 {
+	uart1: uart@02004c00 {
 		// Interrupt source '5' that is level-sensitive.
 		// Note that there are only two cells as specified in the
 		// interrupt parent's '#interrupt-cells' property.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/img,pdc-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/img,pdc-intc.txt
index a69118550344..5dc2a55ad811 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/img,pdc-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/img,pdc-intc.txt
@@ -51,7 +51,7 @@ Example 1:
 	/*
 	 * TZ1090 PDC block
 	 */
-	pdc: pdc@0x02006000 {
+	pdc: pdc@02006000 {
 		// This is an interrupt controller node.
 		interrupt-controller;
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt b/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt
index 715a013ed4bd..2ab0ea39867b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt
@@ -39,7 +39,7 @@ Example:
 
 The following is an example from the SPEAr320 SoC dtsi file.
 
-shirq: interrupt-controller@0xb3000000 {
+shirq: interrupt-controller@b3000000 {
 	compatible = "st,spear320-shirq";
 	reg = <0xb3000000 0x1000>;
 	interrupts = <28 29 30 1>;
diff --git a/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt b/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt
index 85f068805dd8..b1682c80b490 100644
--- a/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt
+++ b/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt
@@ -56,7 +56,7 @@ Examples:
 		iommus = <&sysmmu_gsc0>;
 	};
 
-	sysmmu_gsc0: sysmmu@13E80000 {
+	sysmmu_gsc0: sysmmu@13e80000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x13E80000 0x1000>;
 		interrupt-parent = <&combiner>;
diff --git a/Documentation/devicetree/bindings/leds/leds-lm3692x.txt b/Documentation/devicetree/bindings/leds/leds-lm3692x.txt
new file mode 100644
index 000000000000..6c9074f84a51
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-lm3692x.txt
@@ -0,0 +1,49 @@
+* Texas Instruments - LM3692x Highly Efficient White LED Driver
+
+The LM3692x is an ultra-compact, highly efficient,
+white-LED driver designed for LCD display backlighting.
+
+The main difference between the LM36922 and LM36923 is the number of
+LED strings it supports.  The LM36922 supports two strings while the LM36923
+supports three strings.
+
+Required properties:
+	- compatible:
+		"ti,lm36922"
+		"ti,lm36923"
+	- reg :  I2C slave address
+	- #address-cells : 1
+	- #size-cells : 0
+
+Optional properties:
+	- enable-gpios : gpio pin to enable/disable the device.
+	- vled-supply : LED supply
+
+Required child properties:
+	- reg : 0
+
+Optional child properties:
+	- label : see Documentation/devicetree/bindings/leds/common.txt
+	- linux,default-trigger :
+	   see Documentation/devicetree/bindings/leds/common.txt
+
+Example:
+
+led-controller@36 {
+	compatible = "ti,lm3692x";
+	reg = <0x36>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	enable-gpios = <&gpio1 28 GPIO_ACTIVE_HIGH>;
+	vled-supply = <&vbatt>;
+
+	led@0 {
+		reg = <0>;
+		label = "white:backlight_cluster";
+		linux,default-trigger = "backlight";
+	};
+}
+
+For more product information please see the link below:
+http://www.ti.com/lit/ds/snvsa29/snvsa29.pdf
diff --git a/Documentation/devicetree/bindings/leds/leds-lp8860.txt b/Documentation/devicetree/bindings/leds/leds-lp8860.txt
index aad38dd94d4b..5f0e892ad759 100644
--- a/Documentation/devicetree/bindings/leds/leds-lp8860.txt
+++ b/Documentation/devicetree/bindings/leds/leds-lp8860.txt
@@ -6,23 +6,39 @@ current sinks that can be controlled by a PWM input
 signal, a SPI/I2C master, or both.
 
 Required properties:
-	- compatible:
+	- compatible :
 		"ti,lp8860"
-	- reg -  I2C slave address
-	- label - Used for naming LEDs
+	- reg : I2C slave address
+	- #address-cells : 1
+	- #size-cells : 0
 
 Optional properties:
-	- enable-gpio - gpio pin to enable/disable the device.
-	- supply - "vled" - LED supply
+	- enable-gpios : gpio pin to enable (active high)/disable the device.
+	- vled-supply : LED supply
+
+Required child properties:
+	- reg : 0
+
+Optional child properties:
+	- label : see Documentation/devicetree/bindings/leds/common.txt
+	- linux,default-trigger :
+	   see Documentation/devicetree/bindings/leds/common.txt
 
 Example:
 
-leds: leds@6 {
+led-controller@2d {
 	compatible = "ti,lp8860";
+	#address-cells = <1>;
+	#size-cells = <0>;
 	reg = <0x2d>;
-	label = "display_cluster";
-	enable-gpio = <&gpio1 28 GPIO_ACTIVE_HIGH>;
+	enable-gpios = <&gpio1 28 GPIO_ACTIVE_HIGH>;
 	vled-supply = <&vbatt>;
+
+	led@0 {
+		reg = <0>;
+		label = "white:backlight";
+		linux,default-trigger = "backlight";
+	};
 }
 
 For more product information please see the link below:
diff --git a/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt b/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt
index c2619797ce0c..49cfc8c337c4 100644
--- a/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt
+++ b/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt
@@ -14,7 +14,7 @@ Optional properties:
 			depends on the interrupt controller parent.
 
 Example:
-	mbox_tx: mailbox@0x100 {
+	mbox_tx: mailbox@100 {
 		compatible = "altr,mailbox-1.0";
 		reg = <0x100 0x8>;
 		interrupt-parent = < &gic_0 >;
@@ -22,7 +22,7 @@ Example:
 		#mbox-cells = <1>;
 	};
 
-	mbox_rx: mailbox@0x200 {
+	mbox_rx: mailbox@200 {
 		compatible = "altr,mailbox-1.0";
 		reg = <0x200 0x8>;
 		interrupt-parent = < &gic_0 >;
@@ -40,7 +40,7 @@ support only one channel).The equivalent "mbox-names" property value can be
 used to give a name to the communication channel to be used by the client user.
 
 Example:
-	mclient0: mclient0@0x400 {
+	mclient0: mclient0@400 {
 		compatible = "client-1.0";
 		reg = <0x400 0x10>;
 		mbox-names = "mbox-tx", "mbox-rx";
diff --git a/Documentation/devicetree/bindings/mailbox/brcm,iproc-pdc-mbox.txt b/Documentation/devicetree/bindings/mailbox/brcm,iproc-pdc-mbox.txt
index 0f3ee81d92c2..9bcdf2087625 100644
--- a/Documentation/devicetree/bindings/mailbox/brcm,iproc-pdc-mbox.txt
+++ b/Documentation/devicetree/bindings/mailbox/brcm,iproc-pdc-mbox.txt
@@ -15,7 +15,7 @@ Optional properties:
 - brcm,use-bcm-hdr:  present if a BCM header precedes each frame.
 
 Example:
-	pdc0: iproc-pdc0@0x612c0000 {
+	pdc0: iproc-pdc0@612c0000 {
 		compatible = "brcm,iproc-pdc-mbox";
 		reg = <0 0x612c0000 0 0x445>;  /* PDC FS0 regs */
 		interrupts = <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt b/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt
index 9b40c4925aa9..0ef372656a3e 100644
--- a/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt
+++ b/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt
@@ -124,7 +124,7 @@ dsp {
 };
 
 /* AM33xx */
-mailbox: mailbox@480C8000 {
+mailbox: mailbox@480c8000 {
 	compatible = "ti,omap4-mailbox";
 	reg = <0x480C8000 0x200>;
 	interrupts = <77>;
diff --git a/Documentation/devicetree/bindings/mailbox/ti,message-manager.txt b/Documentation/devicetree/bindings/mailbox/ti,message-manager.txt
index c3b55b3ede8a..ebf0e3710cee 100644
--- a/Documentation/devicetree/bindings/mailbox/ti,message-manager.txt
+++ b/Documentation/devicetree/bindings/mailbox/ti,message-manager.txt
@@ -20,9 +20,9 @@ Required properties:
 		        order referring to the transfer path.
 - interrupt-names:	Contains interrupt names matching the rx transfer path
 			for a given SoC. Receive interrupts shall be of the
-			format: "rx_<QID>_<PID>".
+			format: "rx_<QID>".
 			For ti,k2g-message-manager, this shall contain:
-				"rx_005_002", "rx_057_002"
+				"rx_005", "rx_057"
 - interrupts:		Contains the interrupt information corresponding to
 			interrupt-names property.
 
diff --git a/Documentation/devicetree/bindings/media/exynos5-gsc.txt b/Documentation/devicetree/bindings/media/exynos5-gsc.txt
index 0d4fdaedc6f1..bc963a6d305a 100644
--- a/Documentation/devicetree/bindings/media/exynos5-gsc.txt
+++ b/Documentation/devicetree/bindings/media/exynos5-gsc.txt
@@ -17,7 +17,7 @@ Optional properties:
 
 Example:
 
-gsc_0:  gsc@0x13e00000 {
+gsc_0:  gsc@13e00000 {
 	compatible = "samsung,exynos5250-gsc";
 	reg = <0x13e00000 0x1000>;
 	interrupts = <0 85 0>;
diff --git a/Documentation/devicetree/bindings/media/mediatek-vcodec.txt b/Documentation/devicetree/bindings/media/mediatek-vcodec.txt
index 46c15c54175d..2a615d84a682 100644
--- a/Documentation/devicetree/bindings/media/mediatek-vcodec.txt
+++ b/Documentation/devicetree/bindings/media/mediatek-vcodec.txt
@@ -68,7 +68,7 @@ vcodec_dec: vcodec@16000000 {
                   "vdec_bus_clk_src";
   };
 
-  vcodec_enc: vcodec@0x18002000 {
+  vcodec_enc: vcodec@18002000 {
     compatible = "mediatek,mt8173-vcodec-enc";
     reg = <0 0x18002000 0 0x1000>,    /*VENC_SYS*/
           <0 0x19002000 0 0x1000>;    /*VENC_LT_SYS*/
diff --git a/Documentation/devicetree/bindings/media/rcar_vin.txt b/Documentation/devicetree/bindings/media/rcar_vin.txt
index 6e4ef8caf759..19357d0bbe65 100644
--- a/Documentation/devicetree/bindings/media/rcar_vin.txt
+++ b/Documentation/devicetree/bindings/media/rcar_vin.txt
@@ -44,7 +44,7 @@ Device node example
 	       vin0 = &vin0;
 	};
 
-        vin0: vin@0xe6ef0000 {
+        vin0: vin@e6ef0000 {
                 compatible = "renesas,vin-r8a7790", "renesas,rcar-gen2-vin";
                 clocks = <&mstp8_clks R8A7790_CLK_VIN0>;
                 reg = <0 0xe6ef0000 0 0x1000>;
diff --git a/Documentation/devicetree/bindings/media/s5p-cec.txt b/Documentation/devicetree/bindings/media/s5p-cec.txt
index 6f3756da900f..e847291d4aff 100644
--- a/Documentation/devicetree/bindings/media/s5p-cec.txt
+++ b/Documentation/devicetree/bindings/media/s5p-cec.txt
@@ -23,7 +23,7 @@ Optional:
 
 Example:
 
-hdmicec: cec@100B0000 {
+hdmicec: cec@100b0000 {
 	compatible = "samsung,s5p-cec";
 	reg = <0x100B0000 0x200>;
 	interrupts = <0 114 0>;
diff --git a/Documentation/devicetree/bindings/media/samsung-fimc.txt b/Documentation/devicetree/bindings/media/samsung-fimc.txt
index e4e15d8d7521..48c599dacbdf 100644
--- a/Documentation/devicetree/bindings/media/samsung-fimc.txt
+++ b/Documentation/devicetree/bindings/media/samsung-fimc.txt
@@ -138,7 +138,7 @@ Example:
 		};
 
 		/* MIPI CSI-2 bus IF sensor */
-		s5c73m3: sensor@0x1a {
+		s5c73m3: sensor@1a {
 			compatible = "samsung,s5c73m3";
 			reg = <0x1a>;
 			vddio-supply = <...>;
diff --git a/Documentation/devicetree/bindings/media/samsung-s5c73m3.txt b/Documentation/devicetree/bindings/media/samsung-s5c73m3.txt
index 2c85c4538a6d..21f31fdf5543 100644
--- a/Documentation/devicetree/bindings/media/samsung-s5c73m3.txt
+++ b/Documentation/devicetree/bindings/media/samsung-s5c73m3.txt
@@ -62,7 +62,7 @@ For more details see description of the SPI busses bindings
 
 Example:
 
-i2c@138A000000 {
+i2c@138a000000 {
 	...
 	s5c73m3@3c {
 		compatible = "samsung,s5c73m3";
diff --git a/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt b/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt
index 1ce4e46bcbb7..17a8e81ca0cc 100644
--- a/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt
+++ b/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt
@@ -8,7 +8,7 @@ Bindings, specific for the sh_mobile_ceu_camera.c driver:
 
 Example:
 
-ceu0: ceu@0xfe910000 {
+ceu0: ceu@fe910000 {
 	compatible = "renesas,sh-mobile-ceu";
 	reg = <0xfe910000 0xa0>;
 	interrupt-parent = <&intcs>;
diff --git a/Documentation/devicetree/bindings/media/video-interfaces.txt b/Documentation/devicetree/bindings/media/video-interfaces.txt
index 3994b0143dd1..258b8dfddf48 100644
--- a/Documentation/devicetree/bindings/media/video-interfaces.txt
+++ b/Documentation/devicetree/bindings/media/video-interfaces.txt
@@ -154,7 +154,7 @@ imx074 is linked to ceu0 through the MIPI CSI-2 receiver (csi2). ceu0 has a
 'port' node which may indicate that at any time only one of the following data
 pipelines can be active: ov772x -> ceu0 or imx074 -> csi2 -> ceu0.
 
-	ceu0: ceu@0xfe910000 {
+	ceu0: ceu@fe910000 {
 		compatible = "renesas,sh-mobile-ceu";
 		reg = <0xfe910000 0xa0>;
 		interrupts = <0x880>;
@@ -193,9 +193,9 @@ pipelines can be active: ov772x -> ceu0 or imx074 -> csi2 -> ceu0.
 		};
 	};
 
-	i2c0: i2c@0xfff20000 {
+	i2c0: i2c@fff20000 {
 		...
-		ov772x_1: camera@0x21 {
+		ov772x_1: camera@21 {
 			compatible = "ovti,ov772x";
 			reg = <0x21>;
 			vddio-supply = <&regulator1>;
@@ -219,7 +219,7 @@ pipelines can be active: ov772x -> ceu0 or imx074 -> csi2 -> ceu0.
 			};
 		};
 
-		imx074: camera@0x1a {
+		imx074: camera@1a {
 			compatible = "sony,imx074";
 			reg = <0x1a>;
 			vddio-supply = <&regulator1>;
@@ -239,7 +239,7 @@ pipelines can be active: ov772x -> ceu0 or imx074 -> csi2 -> ceu0.
 		};
 	};
 
-	csi2: csi2@0xffc90000 {
+	csi2: csi2@ffc90000 {
 		compatible = "renesas,sh-mobile-csi2";
 		reg = <0xffc90000 0x1000>;
 		interrupts = <0x17a0>;
diff --git a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra30-mc.txt b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra30-mc.txt
index 8dbe47013c2b..14968b048cd3 100644
--- a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra30-mc.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra30-mc.txt
@@ -12,6 +12,8 @@ Required properties:
 - clock-names: Must include the following entries:
   - mc: the module's clock input
 - interrupts: The interrupt outputs from the controller.
+
+Required properties for Tegra30, Tegra114, Tegra124, Tegra132 and Tegra210:
 - #iommu-cells: Should be 1. The single cell of the IOMMU specifier defines
   the SWGROUP of the master.
 
diff --git a/Documentation/devicetree/bindings/memory-controllers/ti-aemif.txt b/Documentation/devicetree/bindings/memory-controllers/ti-aemif.txt
index 9592717f483f..190437a0c146 100644
--- a/Documentation/devicetree/bindings/memory-controllers/ti-aemif.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/ti-aemif.txt
@@ -138,7 +138,7 @@ from the corresponding HW reg.
 
 Example for aemif, davinci nand and nor flash chip select shown below.
 
-memory-controller@21000A00 {
+memory-controller@21000a00 {
 	compatible = "ti,davinci-aemif";
 	#address-cells = <2>;
 	#size-cells = <1>;
diff --git a/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt b/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
index fd823d6091b2..621b41c79faa 100644
--- a/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
@@ -23,6 +23,13 @@ Required properties:
   the value shall be "emif<n>" where <n> is the number of the EMIF
   instance with base 1.
 
+Required only for "ti,emif-am3352" and "ti,emif-am4372":
+- sram			: Phandles for generic sram driver nodes,
+  first should be type 'protect-exec' for the driver to use to copy
+  and run PM functions, second should be regular pool to be used for
+  data region for code. See Documentation/devicetree/bindings/sram/sram.txt
+  for more details.
+
 Optional properties:
 - cs1-used		: Have this property if CS1 of this EMIF
   instance has a memory part attached to it. If there is a memory
@@ -44,9 +51,9 @@ Optional properties:
 - hw-caps-temp-alert	: Have this property if the controller
   has capability for generating SDRAM temperature alerts
 
-Example:
+-Examples:
 
-emif1: emif@0x4c000000 {
+emif1: emif@4c000000 {
 	compatible	= "ti,emif-4d";
 	ti,hwmods	= "emif2";
 	phy-type	= <1>;
@@ -56,3 +63,11 @@ emif1: emif@0x4c000000 {
 	hw-caps-ll-interface;
 	hw-caps-temp-alert;
 };
+
+/* From am33xx.dtsi */
+emif: emif@4c000000 {
+        compatible = "ti,emif-am3352";
+        reg =   <0x4C000000 0x1000>;
+        sram = <&pm_sram_code
+                &pm_sram_data>;
+};
diff --git a/Documentation/devicetree/bindings/mfd/atmel-tcb.txt b/Documentation/devicetree/bindings/mfd/atmel-tcb.txt
new file mode 100644
index 000000000000..c4a83e364cb6
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/atmel-tcb.txt
@@ -0,0 +1,56 @@
+* Device tree bindings for Atmel Timer Counter Blocks
+- compatible: Should be "atmel,<chip>-tcb", "simple-mfd", "syscon".
+  <chip> can be "at91rm9200" or "at91sam9x5"
+- reg: Should contain registers location and length
+- #address-cells: has to be 1
+- #size-cells: has to be 0
+- interrupts: Should contain all interrupts for the TC block
+  Note that you can specify several interrupt cells if the TC
+  block has one interrupt per channel.
+- clock-names: tuple listing input clock names.
+	Required elements: "t0_clk", "slow_clk"
+	Optional elements: "t1_clk", "t2_clk"
+- clocks: phandles to input clocks.
+
+The TCB can expose multiple subdevices:
+ * a timer
+   - compatible: Should be "atmel,tcb-timer"
+   - reg: Should contain the TCB channels to be used. If the
+     counter width is 16 bits (at91rm9200-tcb), two consecutive
+     channels are needed. Else, only one channel will be used.
+
+Examples:
+
+One interrupt per TC block:
+	tcb0: timer@fff7c000 {
+		compatible = "atmel,at91rm9200-tcb", "simple-mfd", "syscon";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0xfff7c000 0x100>;
+		interrupts = <18 4>;
+		clocks = <&tcb0_clk>, <&clk32k>;
+		clock-names = "t0_clk", "slow_clk";
+
+		timer@0 {
+			compatible = "atmel,tcb-timer";
+			reg = <0>, <1>;
+		};
+
+		timer@2 {
+			compatible = "atmel,tcb-timer";
+			reg = <2>;
+		};
+	};
+
+One interrupt per TC channel in a TC block:
+	tcb1: timer@fffdc000 {
+		compatible = "atmel,at91rm9200-tcb", "simple-mfd", "syscon";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0xfffdc000 0x100>;
+		interrupts = <26 4>, <27 4>, <28 4>;
+		clocks = <&tcb1_clk>, <&clk32k>;
+		clock-names = "t0_clk", "slow_clk";
+	};
+
+
diff --git a/Documentation/devicetree/bindings/mfd/cros-ec.txt b/Documentation/devicetree/bindings/mfd/cros-ec.txt
index 136e0c2da44d..6245c9b1a68b 100644
--- a/Documentation/devicetree/bindings/mfd/cros-ec.txt
+++ b/Documentation/devicetree/bindings/mfd/cros-ec.txt
@@ -41,7 +41,7 @@ Optional properties (all):
 
 Example for I2C:
 
-i2c@12CA0000 {
+i2c@12ca0000 {
 	cros-ec@1e {
 		reg = <0x1e>;
 		compatible = "google,cros-ec-i2c";
diff --git a/Documentation/devicetree/bindings/mfd/mc13xxx.txt b/Documentation/devicetree/bindings/mfd/mc13xxx.txt
index ac235fe385fc..8261ea73278a 100644
--- a/Documentation/devicetree/bindings/mfd/mc13xxx.txt
+++ b/Documentation/devicetree/bindings/mfd/mc13xxx.txt
@@ -130,7 +130,7 @@ ecspi@70010000 { /* ECSPI1 */
 			#size-cells = <0>;
 			led-control = <0x000 0x000 0x0e0 0x000>;
 
-			sysled {
+			sysled@3 {
 				reg = <3>;
 				label = "system:red:live";
 				linux,default-trigger = "heartbeat";
diff --git a/Documentation/devicetree/bindings/mfd/syscon.txt b/Documentation/devicetree/bindings/mfd/syscon.txt
index 8b92d4576c42..25d9e9c2fd53 100644
--- a/Documentation/devicetree/bindings/mfd/syscon.txt
+++ b/Documentation/devicetree/bindings/mfd/syscon.txt
@@ -16,9 +16,17 @@ Required properties:
 Optional property:
 - reg-io-width: the size (in bytes) of the IO accesses that should be
   performed on the device.
+- hwlocks: reference to a phandle of a hardware spinlock provider node.
 
 Examples:
 gpr: iomuxc-gpr@20e0000 {
 	compatible = "fsl,imx6q-iomuxc-gpr", "syscon";
 	reg = <0x020e0000 0x38>;
+	hwlocks = <&hwlock1 1>;
+};
+
+hwlock1: hwspinlock@40500000 {
+	...
+	reg = <0x40500000 0x1000>;
+	#hwlock-cells = <1>;
 };
diff --git a/Documentation/devicetree/bindings/mfd/ti-keystone-devctrl.txt b/Documentation/devicetree/bindings/mfd/ti-keystone-devctrl.txt
index 20963c76b4bc..71a1f5963936 100644
--- a/Documentation/devicetree/bindings/mfd/ti-keystone-devctrl.txt
+++ b/Documentation/devicetree/bindings/mfd/ti-keystone-devctrl.txt
@@ -13,7 +13,7 @@ Required properties:
 
 Example:
 
-devctrl: device-state-control@0x02620000 {
+devctrl: device-state-control@02620000 {
 	compatible = "ti,keystone-devctrl", "syscon";
 	reg = <0x02620000 0x1000>;
 };
diff --git a/Documentation/devicetree/bindings/misc/brcm,kona-smc.txt b/Documentation/devicetree/bindings/misc/brcm,kona-smc.txt
index 6c9f176f3571..05b47232ed9e 100644
--- a/Documentation/devicetree/bindings/misc/brcm,kona-smc.txt
+++ b/Documentation/devicetree/bindings/misc/brcm,kona-smc.txt
@@ -9,7 +9,7 @@ Required properties:
 - reg : Location and size of bounce buffer
 
 Example:
-	smc@0x3404c000 {
+	smc@3404c000 {
 		compatible = "brcm,bcm11351-smc", "brcm,kona-smc";
 		reg = <0x3404c000 0x400>; //1 KiB in SRAM
 	};
diff --git a/Documentation/devicetree/bindings/misc/nvidia,tegra186-misc.txt b/Documentation/devicetree/bindings/misc/nvidia,tegra186-misc.txt
new file mode 100644
index 000000000000..892ba4384abc
--- /dev/null
+++ b/Documentation/devicetree/bindings/misc/nvidia,tegra186-misc.txt
@@ -0,0 +1,12 @@
+NVIDIA Tegra186 MISC register block
+
+The MISC register block found on Tegra186 SoCs contains registers that can be
+used to identify a given chip and various strapping options.
+
+Required properties:
+- compatible: Must be:
+  - Tegra186: "nvidia,tegra186-misc"
+- reg: Should contain 2 entries: The first entry gives the physical address
+       and length of the register region which contains revision and debug
+       features. The second entry specifies the physical address and length
+       of the register region indicating the strapping options.
diff --git a/Documentation/devicetree/bindings/mmc/brcm,kona-sdhci.txt b/Documentation/devicetree/bindings/mmc/brcm,kona-sdhci.txt
index aaba2483b4ff..7f5dd83f5bd9 100644
--- a/Documentation/devicetree/bindings/mmc/brcm,kona-sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/brcm,kona-sdhci.txt
@@ -12,7 +12,7 @@ Refer to clocks/clock-bindings.txt for generic clock consumer properties.
 
 Example:
 
-sdio2: sdio@0x3f1a0000 {
+sdio2: sdio@3f1a0000 {
 	compatible = "brcm,kona-sdhci";
 	reg = <0x3f1a0000 0x10000>;
 	clocks = <&sdio3_clk>;
diff --git a/Documentation/devicetree/bindings/mmc/brcm,sdhci-iproc.txt b/Documentation/devicetree/bindings/mmc/brcm,sdhci-iproc.txt
index 954561d09a8e..fa90d253dc7e 100644
--- a/Documentation/devicetree/bindings/mmc/brcm,sdhci-iproc.txt
+++ b/Documentation/devicetree/bindings/mmc/brcm,sdhci-iproc.txt
@@ -24,7 +24,7 @@ Optional properties:
 
 Example:
 
-sdhci0: sdhci@0x18041000 {
+sdhci0: sdhci@18041000 {
 	compatible = "brcm,sdhci-iproc-cygnus";
 	reg = <0x18041000 0x100>;
 	interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt
index fb11ae8b3b72..467cd7b147ce 100644
--- a/Documentation/devicetree/bindings/mmc/mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc.txt
@@ -67,10 +67,10 @@ logic applies to the "wp-inverted" property.
 CD and WP lines can be implemented on the hardware in one of two ways: as GPIOs,
 specified in cd-gpios and wp-gpios properties, or as dedicated pins. Polarity of
 dedicated pins can be specified, using *-inverted properties. GPIO polarity can
-also be specified using the OF_GPIO_ACTIVE_LOW flag. This creates an ambiguity
+also be specified using the GPIO_ACTIVE_LOW flag. This creates an ambiguity
 in the latter case. We choose to use the XOR logic for GPIO CD and WP lines.
 This means, the two properties are "superimposed," for example leaving the
-OF_GPIO_ACTIVE_LOW flag clear and specifying the respective *-inverted
+GPIO_ACTIVE_LOW flag clear and specifying the respective *-inverted property
 property results in a double-inversion and actually means the "normal" line
 polarity is in effect.
 
diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.txt b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
index 72d2a734ab85..9b8017670870 100644
--- a/Documentation/devicetree/bindings/mmc/mtk-sd.txt
+++ b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
@@ -12,6 +12,8 @@ Required properties:
 	"mediatek,mt8173-mmc": for mmc host ip compatible with mt8173
 	"mediatek,mt2701-mmc": for mmc host ip compatible with mt2701
 	"mediatek,mt2712-mmc": for mmc host ip compatible with mt2712
+	"mediatek,mt7623-mmc", "mediatek,mt2701-mmc": for MT7623 SoC
+
 - reg: physical base address of the controller and length
 - interrupts: Should contain MSDC interrupt number
 - clocks: Should contain phandle for the clock feeding the MMC controller
diff --git a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt
index 3a4ac401e6f9..19f5508a7569 100644
--- a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt
+++ b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt
@@ -55,7 +55,7 @@ Examples:
 
 [hwmod populated DMA resources]
 
-	mmc1: mmc@0x4809c000 {
+	mmc1: mmc@4809c000 {
 		compatible = "ti,omap4-hsmmc";
 		reg = <0x4809c000 0x400>;
 		ti,hwmods = "mmc1";
@@ -67,7 +67,7 @@ Examples:
 
 [generic DMA request binding]
 
-	mmc1: mmc@0x4809c000 {
+	mmc1: mmc@4809c000 {
 		compatible = "ti,omap4-hsmmc";
 		reg = <0x4809c000 0x400>;
 		ti,hwmods = "mmc1";
diff --git a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
index 3c6762430fd9..d8685cb83325 100644
--- a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
@@ -26,6 +26,7 @@ Required properties:
 		"renesas,sdhi-r8a7794" - SDHI IP on R8A7794 SoC
 		"renesas,sdhi-r8a7795" - SDHI IP on R8A7795 SoC
 		"renesas,sdhi-r8a7796" - SDHI IP on R8A7796 SoC
+		"renesas,sdhi-r8a77995" - SDHI IP on R8A77995 SoC
 		"renesas,sdhi-shmobile" - a generic sh-mobile SDHI controller
 		"renesas,rcar-gen1-sdhi" - a generic R-Car Gen1 SDHI controller
 		"renesas,rcar-gen2-sdhi" - a generic R-Car Gen2 or RZ/G1
diff --git a/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt b/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt
index c34aa6f8a424..63d4d626fbd5 100644
--- a/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt
+++ b/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt
@@ -12,7 +12,7 @@ Required properties:
   - reg-names: Should contain the reg names "QuadSPI" and "QuadSPI-memory"
   - interrupts : Should contain the interrupt for the device
   - clocks : The clocks needed by the QuadSPI controller
-  - clock-names : the name of the clocks
+  - clock-names : Should contain the name of the clocks: "qspi_en" and "qspi".
 
 Optional properties:
   - fsl,qspi-has-second-chip: The controller has two buses, bus A and bus B.
diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nor.txt b/Documentation/devicetree/bindings/mtd/gpmc-nor.txt
index 131d3a74d0bd..c8567b40fe13 100644
--- a/Documentation/devicetree/bindings/mtd/gpmc-nor.txt
+++ b/Documentation/devicetree/bindings/mtd/gpmc-nor.txt
@@ -82,15 +82,15 @@ gpmc: gpmc@6e000000 {
 			label = "bootloader-nor";
 			reg = <0 0x40000>;
 		};
-		partition@0x40000 {
+		partition@40000 {
 			label = "params-nor";
 			reg = <0x40000 0x40000>;
 		};
-		partition@0x80000 {
+		partition@80000 {
 			label = "kernel-nor";
 			reg = <0x80000 0x200000>;
 		};
-		partition@0x280000 {
+		partition@280000 {
 			label = "filesystem-nor";
 			reg = <0x240000 0x7d80000>;
 		};
diff --git a/Documentation/devicetree/bindings/mtd/gpmc-onenand.txt b/Documentation/devicetree/bindings/mtd/gpmc-onenand.txt
index b6e8bfd024f4..e9f01a963a0a 100644
--- a/Documentation/devicetree/bindings/mtd/gpmc-onenand.txt
+++ b/Documentation/devicetree/bindings/mtd/gpmc-onenand.txt
@@ -9,13 +9,14 @@ Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt
 
 Required properties:
 
+ - compatible:		"ti,omap2-onenand"
  - reg:			The CS line the peripheral is connected to
- - gpmc,device-width	Width of the ONENAND device connected to the GPMC
+ - gpmc,device-width:	Width of the ONENAND device connected to the GPMC
 			in bytes. Must be 1 or 2.
 
 Optional properties:
 
- - dma-channel:		DMA Channel index
+ - int-gpios:		GPIO specifier for the INT pin.
 
 For inline partition table parsing (optional):
 
@@ -35,6 +36,7 @@ Example for an OMAP3430 board:
 		#size-cells = <1>;
 
 		onenand@0 {
+			compatible = "ti,omap2-onenand";
 			reg = <0 0 0>; /* CS0, offset 0 */
 			gpmc,device-width = <2>;
 
diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
index 376fa2f50e6b..956bb046e599 100644
--- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
+++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
@@ -13,7 +13,6 @@ Required properties:
                  at25df321a
                  at25df641
                  at26df081a
-                 en25s64
                  mr25h128
                  mr25h256
                  mr25h10
@@ -33,7 +32,6 @@ Required properties:
                  s25fl008k
                  s25fl064k
                  sst25vf040b
-                 sst25wf040b
                  m25p40
                  m25p80
                  m25p16
diff --git a/Documentation/devicetree/bindings/mtd/lpc32xx-mlc.txt b/Documentation/devicetree/bindings/mtd/lpc32xx-mlc.txt
index d0a37252eb22..6d60bc3063f5 100644
--- a/Documentation/devicetree/bindings/mtd/lpc32xx-mlc.txt
+++ b/Documentation/devicetree/bindings/mtd/lpc32xx-mlc.txt
@@ -23,7 +23,7 @@ Optional subnodes:
 
 Example:
 
-	mlc: flash@200A8000 {
+	mlc: flash@200a8000 {
 		compatible = "nxp,lpc3220-mlc";
 		reg = <0x200A8000 0x11000>;
 		interrupts = <11 0>;
diff --git a/Documentation/devicetree/bindings/mtd/marvell-nand.txt b/Documentation/devicetree/bindings/mtd/marvell-nand.txt
new file mode 100644
index 000000000000..c08fb477b3c6
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/marvell-nand.txt
@@ -0,0 +1,123 @@
+Marvell NAND Flash Controller (NFC)
+
+Required properties:
+- compatible: can be one of the following:
+    * "marvell,armada-8k-nand-controller"
+    * "marvell,armada370-nand-controller"
+    * "marvell,pxa3xx-nand-controller"
+    * "marvell,armada-8k-nand" (deprecated)
+    * "marvell,armada370-nand" (deprecated)
+    * "marvell,pxa3xx-nand" (deprecated)
+  Compatibles marked deprecated support only the old bindings described
+  at the bottom.
+- reg: NAND flash controller memory area.
+- #address-cells: shall be set to 1. Encode the NAND CS.
+- #size-cells: shall be set to 0.
+- interrupts: shall define the NAND controller interrupt.
+- clocks: shall reference the NAND controller clock.
+- marvell,system-controller: Set to retrieve the syscon node that handles
+  NAND controller related registers (only required with the
+  "marvell,armada-8k-nand[-controller]" compatibles).
+
+Optional properties:
+- label: see partition.txt. New platforms shall omit this property.
+- dmas: shall reference DMA channel associated to the NAND controller.
+  This property is only used with "marvell,pxa3xx-nand[-controller]"
+  compatible strings.
+- dma-names: shall be "rxtx".
+  This property is only used with "marvell,pxa3xx-nand[-controller]"
+  compatible strings.
+
+Optional children nodes:
+Children nodes represent the available NAND chips.
+
+Required properties:
+- reg: shall contain the native Chip Select ids (0-3).
+- nand-rb: see nand.txt (0-1).
+
+Optional properties:
+- marvell,nand-keep-config: orders the driver not to take the timings
+  from the core and leaving them completely untouched. Bootloader
+  timings will then be used.
+- label: MTD name.
+- nand-on-flash-bbt: see nand.txt.
+- nand-ecc-mode: see nand.txt. Will use hardware ECC if not specified.
+- nand-ecc-algo: see nand.txt. This property is essentially useful when
+  not using hardware ECC. Howerver, it may be added when using hardware
+  ECC for clarification but will be ignored by the driver because ECC
+  mode is chosen depending on the page size and the strength required by
+  the NAND chip. This value may be overwritten with nand-ecc-strength
+  property.
+- nand-ecc-strength: see nand.txt.
+- nand-ecc-step-size: see nand.txt. Marvell's NAND flash controller does
+  use fixed strength (1-bit for Hamming, 16-bit for BCH), so the actual
+  step size will shrink or grow in order to fit the required strength.
+  Step sizes are not completely random for all and follow certain
+  patterns described in AN-379, "Marvell SoC NFC ECC".
+
+See Documentation/devicetree/bindings/mtd/nand.txt for more details on
+generic bindings.
+
+
+Example:
+nand_controller: nand-controller@d0000 {
+	compatible = "marvell,armada370-nand-controller";
+	reg = <0xd0000 0x54>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&coredivclk 0>;
+
+	nand@0 {
+		reg = <0>;
+		label = "main-storage";
+		nand-rb = <0>;
+		nand-ecc-mode = "hw";
+		marvell,nand-keep-config;
+		nand-on-flash-bbt;
+		nand-ecc-strength = <4>;
+		nand-ecc-step-size = <512>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "Rootfs";
+				reg = <0x00000000 0x40000000>;
+			};
+		};
+	};
+};
+
+
+Note on legacy bindings: One can find, in not-updated device trees,
+bindings slightly different than described above with other properties
+described below as well as the partitions node at the root of a so
+called "nand" node (without clear controller/chip separation).
+
+Legacy properties:
+- marvell,nand-enable-arbiter: To enable the arbiter, all boards blindly
+  used it, this bit was set by the bootloader for many boards and even if
+  it is marked reserved in several datasheets, it might be needed to set
+  it (otherwise it is harmless) so whether or not this property is set,
+  the bit is selected by the driver.
+- num-cs: Number of chip-select lines to use, all boards blindly set 1
+  to this and for a reason, other values would have failed. The value of
+  this property is ignored.
+
+Example:
+
+	nand0: nand@43100000 {
+		compatible = "marvell,pxa3xx-nand";
+		reg = <0x43100000 90>;
+		interrupts = <45>;
+		dmas = <&pdma 97 0>;
+		dma-names = "rxtx";
+		#address-cells = <1>;
+		marvell,nand-keep-config;
+		marvell,nand-enable-arbiter;
+		num-cs = <1>;
+		/* Partitions (optional) */
+       };
diff --git a/Documentation/devicetree/bindings/mtd/mtk-nand.txt b/Documentation/devicetree/bindings/mtd/mtk-nand.txt
index dbf9e054c11c..1c88526dedfc 100644
--- a/Documentation/devicetree/bindings/mtd/mtk-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/mtk-nand.txt
@@ -12,8 +12,10 @@ tree nodes.
 
 The first part of NFC is NAND Controller Interface (NFI) HW.
 Required NFI properties:
-- compatible:			Should be one of "mediatek,mt2701-nfc",
-				"mediatek,mt2712-nfc".
+- compatible:			Should be one of
+				"mediatek,mt2701-nfc",
+				"mediatek,mt2712-nfc",
+				"mediatek,mt7622-nfc".
 - reg:				Base physical address and size of NFI.
 - interrupts:			Interrupts of NFI.
 - clocks:			NFI required clocks.
@@ -131,7 +133,7 @@ Example:
 				read-only;
 				reg = <0x00000000 0x00400000>;
 			};
-			android@0x00400000 {
+			android@00400000 {
 				label = "android";
 				reg = <0x00400000 0x12c00000>;
 			};
@@ -142,7 +144,10 @@ Example:
 ==============
 
 Required BCH properties:
-- compatible:	Should be one of "mediatek,mt2701-ecc", "mediatek,mt2712-ecc".
+- compatible:	Should be one of
+		"mediatek,mt2701-ecc",
+		"mediatek,mt2712-ecc",
+		"mediatek,mt7622-ecc".
 - reg:		Base physical address and size of ECC.
 - interrupts:	Interrupts of ECC.
 - clocks:	ECC required clocks.
diff --git a/Documentation/devicetree/bindings/mtd/nand.txt b/Documentation/devicetree/bindings/mtd/nand.txt
index 133f3813719c..8bb11d809429 100644
--- a/Documentation/devicetree/bindings/mtd/nand.txt
+++ b/Documentation/devicetree/bindings/mtd/nand.txt
@@ -43,6 +43,7 @@ Optional NAND chip properties:
 		     This is particularly useful when only the in-band area is
 		     used by the upper layers, and you want to make your NAND
 		     as reliable as possible.
+- nand-rb: shall contain the native Ready/Busy ids.
 
 The ECC strength and ECC step size properties define the correction capability
 of a controller. Together, they say a controller can correct "{strength} bit
diff --git a/Documentation/devicetree/bindings/net/altera_tse.txt b/Documentation/devicetree/bindings/net/altera_tse.txt
index a706297998e9..0e21df94a53f 100644
--- a/Documentation/devicetree/bindings/net/altera_tse.txt
+++ b/Documentation/devicetree/bindings/net/altera_tse.txt
@@ -52,7 +52,7 @@ Optional properties:
 
 Example:
 
-	tse_sub_0_eth_tse_0: ethernet@0x1,00000000 {
+	tse_sub_0_eth_tse_0: ethernet@1,00000000 {
 		compatible = "altr,tse-msgdma-1.0";
 		reg =	<0x00000001 0x00000000 0x00000400>,
 			<0x00000001 0x00000460 0x00000020>,
@@ -90,7 +90,7 @@ Example:
 		};
 	};
 
-	tse_sub_1_eth_tse_0: ethernet@0x1,00001000 {
+	tse_sub_1_eth_tse_0: ethernet@1,00001000 {
 		compatible = "altr,tse-msgdma-1.0";
 		reg = 	<0x00000001 0x00001000 0x00000400>,
 			<0x00000001 0x00001460 0x00000020>,
diff --git a/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt b/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt
index 9a734d808aa7..b7336b9d6a3c 100644
--- a/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt
+++ b/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt
@@ -2,7 +2,10 @@
 
 Required properties:
 
-- compatible: should be "brcm,bcm7445-switch-v4.0" or "brcm,bcm7278-switch-v4.0"
+- compatible: should be one of
+	"brcm,bcm7445-switch-v4.0"
+	"brcm,bcm7278-switch-v4.0"
+	"brcm,bcm7278-switch-v4.8"
 - reg: addresses and length of the register sets for the device, must be 6
   pairs of register addresses and lengths
 - interrupts: interrupts for the devices, must be two interrupts
diff --git a/Documentation/devicetree/bindings/net/can/can-transceiver.txt b/Documentation/devicetree/bindings/net/can/can-transceiver.txt
new file mode 100644
index 000000000000..0011f53ff159
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/can-transceiver.txt
@@ -0,0 +1,24 @@
+Generic CAN transceiver Device Tree binding
+------------------------------
+
+CAN transceiver typically limits the max speed in standard CAN and CAN FD
+modes. Typically these limitations are static and the transceivers themselves
+provide no way to detect this limitation at runtime. For this situation,
+the "can-transceiver" node can be used.
+
+Required Properties:
+ max-bitrate:	a positive non 0 value that determines the max
+		speed that CAN/CAN-FD can run. Any other value
+		will be ignored.
+
+Examples:
+
+Based on Texas Instrument's TCAN1042HGV CAN Transceiver
+
+m_can0 {
+	....
+	can-transceiver {
+		max-bitrate = <5000000>;
+	};
+	...
+};
diff --git a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
index 56d6cc336e1c..bfc0c433654f 100644
--- a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
+++ b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
@@ -18,6 +18,12 @@ Optional properties:
 
 - xceiver-supply: Regulator that powers the CAN transceiver
 
+- big-endian: This means the registers of FlexCAN controller are big endian.
+              This is optional property.i.e. if this property is not present in
+              device tree node then controller is assumed to be little endian.
+              if this property is present then controller is assumed to be big
+              endian.
+
 Example:
 
 	can@1c000 {
diff --git a/Documentation/devicetree/bindings/net/can/m_can.txt b/Documentation/devicetree/bindings/net/can/m_can.txt
index 63e90421d029..ed614383af9c 100644
--- a/Documentation/devicetree/bindings/net/can/m_can.txt
+++ b/Documentation/devicetree/bindings/net/can/m_can.txt
@@ -43,6 +43,11 @@ Required properties:
 			  Please refer to 2.4.1 Message RAM Configuration in
 			  Bosch M_CAN user manual for details.
 
+Optional Subnode:
+- can-transceiver	: Can-transceiver subnode describing maximum speed
+			  that can be used for CAN/CAN-FD modes. See
+			  Documentation/devicetree/bindings/net/can/can-transceiver.txt
+			  for details.
 Example:
 SoC dtsi:
 m_can1: can@20e8000 {
@@ -63,4 +68,8 @@ Board dts:
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_m_can1>;
 	status = "enabled";
+
+	can-transceiver {
+		max-bitrate = <5000000>;
+	};
 };
diff --git a/Documentation/devicetree/bindings/net/can/rcar_can.txt b/Documentation/devicetree/bindings/net/can/rcar_can.txt
index 06bb7cc334c8..94a7f33ac5e9 100644
--- a/Documentation/devicetree/bindings/net/can/rcar_can.txt
+++ b/Documentation/devicetree/bindings/net/can/rcar_can.txt
@@ -2,7 +2,9 @@ Renesas R-Car CAN controller Device Tree Bindings
 -------------------------------------------------
 
 Required properties:
-- compatible: "renesas,can-r8a7778" if CAN controller is a part of R8A7778 SoC.
+- compatible: "renesas,can-r8a7743" if CAN controller is a part of R8A7743 SoC.
+	      "renesas,can-r8a7745" if CAN controller is a part of R8A7745 SoC.
+	      "renesas,can-r8a7778" if CAN controller is a part of R8A7778 SoC.
 	      "renesas,can-r8a7779" if CAN controller is a part of R8A7779 SoC.
 	      "renesas,can-r8a7790" if CAN controller is a part of R8A7790 SoC.
 	      "renesas,can-r8a7791" if CAN controller is a part of R8A7791 SoC.
@@ -12,7 +14,8 @@ Required properties:
 	      "renesas,can-r8a7795" if CAN controller is a part of R8A7795 SoC.
 	      "renesas,can-r8a7796" if CAN controller is a part of R8A7796 SoC.
 	      "renesas,rcar-gen1-can" for a generic R-Car Gen1 compatible device.
-	      "renesas,rcar-gen2-can" for a generic R-Car Gen2 compatible device.
+	      "renesas,rcar-gen2-can" for a generic R-Car Gen2 or RZ/G1
+	      compatible device.
 	      "renesas,rcar-gen3-can" for a generic R-Car Gen3 compatible device.
 	      When compatible with the generic version, nodes must list the
 	      SoC-specific version corresponding to the platform first
diff --git a/Documentation/devicetree/bindings/net/cortina,gemini-ethernet.txt b/Documentation/devicetree/bindings/net/cortina,gemini-ethernet.txt
new file mode 100644
index 000000000000..6c559981d110
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/cortina,gemini-ethernet.txt
@@ -0,0 +1,92 @@
+Cortina Systems Gemini Ethernet Controller
+==========================================
+
+This ethernet controller is found in the Gemini SoC family:
+StorLink SL3512 and SL3516, also known as Cortina Systems
+CS3512 and CS3516.
+
+Required properties:
+- compatible: must be "cortina,gemini-ethernet"
+- reg: must contain the global registers and the V-bit and A-bit
+  memory areas, in total three register sets.
+- syscon: a phandle to the system controller
+- #address-cells: must be specified, must be <1>
+- #size-cells: must be specified, must be <1>
+- ranges: should be state like this giving a 1:1 address translation
+  for the subnodes
+
+The subnodes represents the two ethernet ports in this device.
+They are not independent of each other since they share resources
+in the parent node, and are thus children.
+
+Required subnodes:
+- port0: contains the resources for ethernet port 0
+- port1: contains the resources for ethernet port 1
+
+Required subnode properties:
+- compatible: must be "cortina,gemini-ethernet-port"
+- reg: must contain two register areas: the DMA/TOE memory and
+  the GMAC memory area of the port
+- interrupts: should contain the interrupt line of the port.
+  this is nominally a level interrupt active high.
+- resets: this must provide an SoC-integrated reset line for
+  the port.
+- clocks: this should contain a handle to the PCLK clock for
+  clocking the silicon in this port
+- clock-names: must be "PCLK"
+
+Optional subnode properties:
+- phy-mode: see ethernet.txt
+- phy-handle: see ethernet.txt
+
+Example:
+
+mdio-bus {
+	(...)
+	phy0: ethernet-phy@1 {
+		reg = <1>;
+		device_type = "ethernet-phy";
+	};
+	phy1: ethernet-phy@3 {
+		reg = <3>;
+		device_type = "ethernet-phy";
+	};
+};
+
+
+ethernet@60000000 {
+	compatible = "cortina,gemini-ethernet";
+	reg = <0x60000000 0x4000>, /* Global registers, queue */
+	      <0x60004000 0x2000>, /* V-bit */
+	      <0x60006000 0x2000>; /* A-bit */
+	syscon = <&syscon>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+	ranges;
+
+	gmac0: ethernet-port@0 {
+		compatible = "cortina,gemini-ethernet-port";
+		reg = <0x60008000 0x2000>, /* Port 0 DMA/TOE */
+		      <0x6000a000 0x2000>; /* Port 0 GMAC */
+		interrupt-parent = <&intcon>;
+		interrupts = <1 IRQ_TYPE_LEVEL_HIGH>;
+		resets = <&syscon GEMINI_RESET_GMAC0>;
+		clocks = <&syscon GEMINI_CLK_GATE_GMAC0>;
+		clock-names = "PCLK";
+		phy-mode = "rgmii";
+		phy-handle = <&phy0>;
+	};
+
+	gmac1: ethernet-port@1 {
+		compatible = "cortina,gemini-ethernet-port";
+		reg = <0x6000c000 0x2000>, /* Port 1 DMA/TOE */
+		      <0x6000e000 0x2000>; /* Port 1 GMAC */
+		interrupt-parent = <&intcon>;
+		interrupts = <2 IRQ_TYPE_LEVEL_HIGH>;
+		resets = <&syscon GEMINI_RESET_GMAC1>;
+		clocks = <&syscon GEMINI_CLK_GATE_GMAC1>;
+		clock-names = "PCLK";
+		phy-mode = "rgmii";
+		phy-handle = <&phy1>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index 7cc15c96ea95..4cb4925a28ab 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -61,7 +61,7 @@ file.
 
 Examples:
 
-	mac: ethernet@4A100000 {
+	mac: ethernet@4a100000 {
 		compatible = "ti,cpsw";
 		reg = <0x4A100000 0x1000>;
 		interrupts = <55 0x4>;
@@ -91,7 +91,7 @@ Examples:
 	};
 
 (or)
-	mac: ethernet@4A100000 {
+	mac: ethernet@4a100000 {
 		compatible = "ti,cpsw";
 		ti,hwmods = "cpgmac0";
 		cpdma_channels = <8>;
diff --git a/Documentation/devicetree/bindings/net/davinci-mdio.txt b/Documentation/devicetree/bindings/net/davinci-mdio.txt
index 621156ca4ffd..e6527de80f10 100644
--- a/Documentation/devicetree/bindings/net/davinci-mdio.txt
+++ b/Documentation/devicetree/bindings/net/davinci-mdio.txt
@@ -21,7 +21,7 @@ file.
 
 Examples:
 
-	mdio: davinci_mdio@4A101000 {
+	mdio: davinci_mdio@4a101000 {
 		compatible = "ti,davinci_mdio";
 		reg = <0x4A101000 0x1000>;
 		bus_freq = <1000000>;
@@ -29,7 +29,7 @@ Examples:
 
 (or)
 
-	mdio: davinci_mdio@4A101000 {
+	mdio: davinci_mdio@4a101000 {
 		compatible = "ti,davinci_mdio";
 		ti,hwmods = "davinci_mdio";
 		bus_freq = <1000000>;
diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt
index f0dc94409107..2d41fb96ce0a 100644
--- a/Documentation/devicetree/bindings/net/fsl-fec.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fec.txt
@@ -59,7 +59,7 @@ ethernet@83fec000 {
 	reg = <0x83fec000 0x4000>;
 	interrupts = <87>;
 	phy-mode = "mii";
-	phy-reset-gpios = <&gpio2 14 0>; /* GPIO2_14 */
+	phy-reset-gpios = <&gpio2 14 GPIO_ACTIVE_LOW>; /* GPIO2_14 */
 	local-mac-address = [00 04 9F 01 1B B9];
 	phy-supply = <&reg_fec_supply>;
 };
@@ -71,7 +71,7 @@ ethernet@83fec000 {
 	reg = <0x83fec000 0x4000>;
 	interrupts = <87>;
 	phy-mode = "mii";
-	phy-reset-gpios = <&gpio2 14 0>; /* GPIO2_14 */
+	phy-reset-gpios = <&gpio2 14 GPIO_ACTIVE_LOW>; /* GPIO2_14 */
 	local-mac-address = [00 04 9F 01 1B B9];
 	phy-supply = <&reg_fec_supply>;
 	phy-handle = <&ethphy>;
diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
index db74f0dc290c..594982c6b9f9 100644
--- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
+++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
@@ -136,7 +136,7 @@ Clock Properties:
 
 Example:
 
-	ptp_clock@24E00 {
+	ptp_clock@24e00 {
 		compatible = "fsl,etsec-ptp";
 		reg = <0x24E00 0xB0>;
 		interrupts = <12 0x8 13 0x8>;
diff --git a/Documentation/devicetree/bindings/net/ieee802154/adf7242.txt b/Documentation/devicetree/bindings/net/ieee802154/adf7242.txt
index dea5124cdc52..d24172cc6d32 100644
--- a/Documentation/devicetree/bindings/net/ieee802154/adf7242.txt
+++ b/Documentation/devicetree/bindings/net/ieee802154/adf7242.txt
@@ -1,7 +1,7 @@
 * ADF7242 IEEE 802.15.4 *
 
 Required properties:
-  - compatible:		should be "adi,adf7242"
+  - compatible:		should be "adi,adf7242", "adi,adf7241"
   - spi-max-frequency:	maximal bus speed (12.5 MHz)
   - reg:		the chipselect index
   - interrupts:		the interrupt generated by the device via pin IRQ1.
diff --git a/Documentation/devicetree/bindings/net/mdio.txt b/Documentation/devicetree/bindings/net/mdio.txt
index 96a53f89aa6e..e3e1603f256c 100644
--- a/Documentation/devicetree/bindings/net/mdio.txt
+++ b/Documentation/devicetree/bindings/net/mdio.txt
@@ -18,7 +18,7 @@ Example :
 This example shows these optional properties, plus other properties
 required for the TI Davinci MDIO driver.
 
-	davinci_mdio: ethernet@0x5c030000 {
+	davinci_mdio: ethernet@5c030000 {
 		compatible = "ti,davinci_mdio";
 		reg = <0x5c030000 0x1000>;
 		#address-cells = <1>;
diff --git a/Documentation/devicetree/bindings/net/mediatek-net.txt b/Documentation/devicetree/bindings/net/mediatek-net.txt
index 214eaa9a6683..53c13ee384a4 100644
--- a/Documentation/devicetree/bindings/net/mediatek-net.txt
+++ b/Documentation/devicetree/bindings/net/mediatek-net.txt
@@ -28,7 +28,7 @@ Required properties:
 - mediatek,sgmiisys: phandle to the syscon node that handles the SGMII setup
 	which is required for those SoCs equipped with SGMII such as MT7622 SoC.
 - mediatek,pctl: phandle to the syscon node that handles the ports slew rate
-	and driver current
+	and driver current: only for MT2701 and MT7623 SoC
 
 Optional properties:
 - interrupt-parent: Should be the phandle for the interrupt controller
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index 77d0b2a61ffa..d2169a56f5e3 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -53,6 +53,14 @@ Optional Properties:
   to ensure the integrated PHY is used. The absence of this property indicates
   the muxers should be configured so that the external PHY is used.
 
+- reset-gpios: The GPIO phandle and specifier for the PHY reset signal.
+
+- reset-assert-us: Delay after the reset was asserted in microseconds.
+  If this property is missing the delay will be skipped.
+
+- reset-deassert-us: Delay after the reset was deasserted in microseconds.
+  If this property is missing the delay will be skipped.
+
 Example:
 
 ethernet-phy@0 {
@@ -60,4 +68,8 @@ ethernet-phy@0 {
 	interrupt-parent = <&PIC>;
 	interrupts = <35 IRQ_TYPE_EDGE_RISING>;
 	reg = <0>;
+
+	reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+	reset-assert-us = <1000>;
+	reset-deassert-us = <2000>;
 };
diff --git a/Documentation/devicetree/bindings/net/sff,sfp.txt b/Documentation/devicetree/bindings/net/sff,sfp.txt
index 60e970ce10ee..f1c441bedf68 100644
--- a/Documentation/devicetree/bindings/net/sff,sfp.txt
+++ b/Documentation/devicetree/bindings/net/sff,sfp.txt
@@ -3,7 +3,9 @@ Transceiver
 
 Required properties:
 
-- compatible : must be "sff,sfp"
+- compatible : must be one of
+  "sff,sfp" for SFP modules
+  "sff,sff" for soldered down SFF modules
 
 Optional Properties:
 
@@ -11,7 +13,8 @@ Optional Properties:
   interface
 
 - mod-def0-gpios : GPIO phandle and a specifier of the MOD-DEF0 (AKA Mod_ABS)
-  module presence input gpio signal, active (module absent) high
+  module presence input gpio signal, active (module absent) high. Must
+  not be present for SFF modules
 
 - los-gpios : GPIO phandle and a specifier of the Receiver Loss of Signal
   Indication input gpio signal, active (signal lost) high
@@ -24,10 +27,11 @@ Optional Properties:
 
 - rate-select0-gpios : GPIO phandle and a specifier of the Rx Signaling Rate
   Select (AKA RS0) output gpio signal, low: low Rx rate, high: high Rx rate
+  Must not be present for SFF modules
 
 - rate-select1-gpios : GPIO phandle and a specifier of the Tx Signaling Rate
   Select (AKA RS1) output gpio signal (SFP+ only), low: low Tx rate, high:
-  high Tx rate
+  high Tx rate. Must not be present for SFF modules
 
 Example #1: Direct serdes to SFP connection
 
diff --git a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt b/Documentation/devicetree/bindings/net/socfpga-dwmac.txt
index b30d04b54ee9..17d6819669c8 100644
--- a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/socfpga-dwmac.txt
@@ -28,7 +28,7 @@ Required properties:
 
 Example:
 
-gmii_to_sgmii_converter: phy@0x100000240 {
+gmii_to_sgmii_converter: phy@100000240 {
 	compatible = "altr,gmii-to-sgmii-2.0";
 	reg = <0x00000001 0x00000240 0x00000008>,
 		<0x00000001 0x00000200 0x00000040>;
diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt
new file mode 100644
index 000000000000..270ea4efff13
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt
@@ -0,0 +1,48 @@
+* Socionext AVE ethernet controller
+
+This describes the devicetree bindings for AVE ethernet controller
+implemented on Socionext UniPhier SoCs.
+
+Required properties:
+ - compatible: Should be
+	- "socionext,uniphier-pro4-ave4" : for Pro4 SoC
+	- "socionext,uniphier-pxs2-ave4" : for PXs2 SoC
+	- "socionext,uniphier-ld11-ave4" : for LD11 SoC
+	- "socionext,uniphier-ld20-ave4" : for LD20 SoC
+ - reg: Address where registers are mapped and size of region.
+ - interrupts: Should contain the MAC interrupt.
+ - phy-mode: See ethernet.txt in the same directory. Allow to choose
+	"rgmii", "rmii", or "mii" according to the PHY.
+ - phy-handle: Should point to the external phy device.
+	See ethernet.txt file in the same directory.
+ - clocks: A phandle to the clock for the MAC.
+
+Optional properties:
+ - resets: A phandle to the reset control for the MAC.
+ - local-mac-address: See ethernet.txt in the same directory.
+
+Required subnode:
+ - mdio: A container for child nodes representing phy nodes.
+         See phy.txt in the same directory.
+
+Example:
+
+	ether: ethernet@65000000 {
+		compatible = "socionext,uniphier-ld20-ave4";
+		reg = <0x65000000 0x8500>;
+		interrupts = <0 66 4>;
+		phy-mode = "rgmii";
+		phy-handle = <&ethphy>;
+		clocks = <&sys_clk 6>;
+		resets = <&sys_rst 6>;
+		local-mac-address = [00 00 00 00 00 00];
+
+		mdio {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			ethphy: ethphy@1 {
+				reg = <1>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/net/socionext-netsec.txt b/Documentation/devicetree/bindings/net/socionext-netsec.txt
new file mode 100644
index 000000000000..0cff94fb0433
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/socionext-netsec.txt
@@ -0,0 +1,53 @@
+* Socionext NetSec Ethernet Controller IP
+
+Required properties:
+- compatible: Should be "socionext,synquacer-netsec"
+- reg: Address and length of the control register area, followed by the
+       address and length of the EEPROM holding the MAC address and
+       microengine firmware
+- interrupts: Should contain ethernet controller interrupt
+- clocks: phandle to the PHY reference clock
+- clock-names: Should be "phy_ref_clk"
+- phy-mode: See ethernet.txt file in the same directory
+- phy-handle: See ethernet.txt in the same directory.
+
+- mdio device tree subnode: When the Netsec has a phy connected to its local
+		mdio, there must be device tree subnode with the following
+		required properties:
+
+	- #address-cells: Must be <1>.
+	- #size-cells: Must be <0>.
+
+	For each phy on the mdio bus, there must be a node with the following
+	fields:
+	- compatible: Refer to phy.txt
+	- reg: phy id used to communicate to phy.
+
+Optional properties: (See ethernet.txt file in the same directory)
+- dma-coherent: Boolean property, must only be present if memory
+	accesses performed by the device are cache coherent.
+- local-mac-address: See ethernet.txt in the same directory.
+- mac-address: See ethernet.txt in the same directory.
+- max-speed: See ethernet.txt in the same directory.
+- max-frame-size: See ethernet.txt in the same directory.
+
+Example:
+	eth0: ethernet@522d0000 {
+		compatible = "socionext,synquacer-netsec";
+		reg = <0 0x522d0000 0x0 0x10000>, <0 0x10000000 0x0 0x10000>;
+		interrupts = <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&clk_netsec>;
+		clock-names = "phy_ref_clk";
+		phy-mode = "rgmii";
+		max-speed = <1000>;
+		max-frame-size = <9000>;
+		phy-handle = <&phy1>;
+
+		mdio {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			phy1: ethernet-phy@1 {
+				compatible = "ethernet-phy-ieee802.3-c22";
+				reg = <1>;
+			};
+		};
diff --git a/Documentation/devicetree/bindings/net/ti,wilink-st.txt b/Documentation/devicetree/bindings/net/ti-bluetooth.txt
index 1649c1f66b07..6d03ff8c7068 100644
--- a/Documentation/devicetree/bindings/net/ti,wilink-st.txt
+++ b/Documentation/devicetree/bindings/net/ti-bluetooth.txt
@@ -1,10 +1,18 @@
-TI WiLink 7/8 (wl12xx/wl18xx) Shared Transport BT/FM/GPS devices
+Texas Instruments Bluetooth Chips
+---------------------------------
+
+This documents the binding structure and common properties for serial
+attached TI Bluetooth devices. The following chips are included in this
+binding:
+
+* TI CC256x Bluetooth devices
+* TI WiLink 7/8 (wl12xx/wl18xx) Shared Transport BT/FM/GPS devices
 
 TI WiLink devices have a UART interface for providing Bluetooth, FM radio,
 and GPS over what's called "shared transport". The shared transport is
 standard BT HCI protocol with additional channels for the other functions.
 
-These devices also have a separate WiFi interface as described in
+TI WiLink devices also have a separate WiFi interface as described in
 wireless/ti,wlcore.txt.
 
 This bindings follows the UART slave device binding in
@@ -12,6 +20,7 @@ This bindings follows the UART slave device binding in
 
 Required properties:
  - compatible: should be one of the following:
+    "ti,cc2560"
     "ti,wl1271-st"
     "ti,wl1273-st"
     "ti,wl1281-st"
@@ -32,6 +41,9 @@ Optional properties:
    See ../clocks/clock-bindings.txt for details.
  - clock-names : Must include the following entry:
    "ext_clock" (External clock provided to the TI combo chip).
+ - nvmem-cells: phandle to nvmem data cell that contains a 6 byte BD address
+   with the most significant byte first (big-endian).
+ - nvmem-cell-names: "bd-address" (required when nvmem-cells is specified)
 
 Example:
 
@@ -43,5 +55,7 @@ Example:
 		enable-gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
 		clocks = <&clk32k_wl18xx>;
 		clock-names = "ext_clock";
+		nvmem-cells = <&bd_address>;
+		nvmem-cell-names = "bd-address";
 	};
 };
diff --git a/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.txt b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.txt
new file mode 100644
index 000000000000..0c17a0ec9b7b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.txt
@@ -0,0 +1,32 @@
+* MediaTek mt76xx devices
+
+This node provides properties for configuring the MediaTek mt76xx wireless
+device. The node is expected to be specified as a child node of the PCI
+controller to which the wireless chip is connected.
+
+Optional properties:
+
+- mac-address: See ethernet.txt in the parent directory
+- local-mac-address: See ethernet.txt in the parent directory
+- ieee80211-freq-limit: See ieee80211.txt
+- mediatek,mtd-eeprom: Specify a MTD partition + offset containing EEPROM data
+
+Optional nodes:
+- led: Properties for a connected LED
+  Optional properties:
+    - led-sources: See Documentation/devicetree/bindings/leds/common.txt
+
+&pcie {
+	pcie0 {
+		wifi@0,0 {
+			compatible = "mediatek,mt76";
+			reg = <0x0000 0 0 0 0>;
+			ieee80211-freq-limit = <5000000 6000000>;
+			mediatek,mtd-eeprom = <&factory 0x8000>;
+
+			led {
+				led-sources = <2>;
+			};
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
index 74d7f0af209c..3d2a031217da 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
@@ -41,6 +41,9 @@ Optional properties:
 - qcom,msi_addr: MSI interrupt address.
 - qcom,msi_base: Base value to add before writing MSI data into
 		MSI address register.
+- qcom,ath10k-calibration-variant: string to search for in the board-2.bin
+				   variant list with the same bus and device
+				   specific ids
 - qcom,ath10k-calibration-data : calibration data + board specific data
 				 as an array, the length can vary between
 				 hw versions.
diff --git a/Documentation/devicetree/bindings/nios2/nios2.txt b/Documentation/devicetree/bindings/nios2/nios2.txt
index d6d0a94cb3bb..b95e831bcba3 100644
--- a/Documentation/devicetree/bindings/nios2/nios2.txt
+++ b/Documentation/devicetree/bindings/nios2/nios2.txt
@@ -36,7 +36,7 @@ Optional properties:
 
 Example:
 
-cpu@0x0 {
+cpu@0 {
 	device_type = "cpu";
 	compatible = "altr,nios2-1.0";
 	reg = <0>;
diff --git a/Documentation/devicetree/bindings/nvmem/rockchip-efuse.txt b/Documentation/devicetree/bindings/nvmem/rockchip-efuse.txt
index 60bec4782806..265bdb7dc8aa 100644
--- a/Documentation/devicetree/bindings/nvmem/rockchip-efuse.txt
+++ b/Documentation/devicetree/bindings/nvmem/rockchip-efuse.txt
@@ -6,12 +6,17 @@ Required properties:
   - "rockchip,rk3188-efuse" - for RK3188 SoCs.
   - "rockchip,rk3228-efuse" - for RK3228 SoCs.
   - "rockchip,rk3288-efuse" - for RK3288 SoCs.
+  - "rockchip,rk3328-efuse" - for RK3328 SoCs.
   - "rockchip,rk3368-efuse" - for RK3368 SoCs.
   - "rockchip,rk3399-efuse" - for RK3399 SoCs.
 - reg: Should contain the registers location and exact eFuse size
 - clocks: Should be the clock id of eFuse
 - clock-names: Should be "pclk_efuse"
 
+Optional properties:
+- rockchip,efuse-size: Should be exact eFuse size in byte, the eFuse
+  size in property <reg> will be invalid if define this property.
+
 Deprecated properties:
 - compatible: "rockchip,rockchip-efuse"
   Old efuse compatible value compatible to rk3066a, rk3188 and rk3288
diff --git a/Documentation/devicetree/bindings/opp/opp.txt b/Documentation/devicetree/bindings/opp/opp.txt
index 9d733af26be7..4e4f30288c8b 100644
--- a/Documentation/devicetree/bindings/opp/opp.txt
+++ b/Documentation/devicetree/bindings/opp/opp.txt
@@ -45,6 +45,11 @@ Devices supporting OPPs must set their "operating-points-v2" property with
 phandle to a OPP table in their DT node. The OPP core will use this phandle to
 find the operating points for the device.
 
+This can contain more than one phandle for power domain providers that provide
+multiple power domains. That is, one phandle for each power domain. If only one
+phandle is available, then the same OPP table will be used for all power domains
+provided by the power domain provider.
+
 If required, this can be extended for SoC vendor specific bindings. Such bindings
 should be documented as Documentation/devicetree/bindings/power/<vendor>-opp.txt
 and should have a compatible description like: "operating-points-v2-<vendor>".
@@ -154,6 +159,14 @@ Optional properties:
 
 - status: Marks the node enabled/disabled.
 
+- required-opp: This contains phandle to an OPP node in another device's OPP
+  table. It may contain an array of phandles, where each phandle points to an
+  OPP of a different device. It should not contain multiple phandles to the OPP
+  nodes in the same OPP table. This specifies the minimum required OPP of the
+  device(s), whose OPP's phandle is present in this property, for the
+  functioning of the current device at the current OPP (where this property is
+  present).
+
 Example 1: Single cluster Dual-core ARM cortex A9, switch DVFS states together.
 
 / {
diff --git a/Documentation/devicetree/bindings/opp/ti-omap5-opp-supply.txt b/Documentation/devicetree/bindings/opp/ti-omap5-opp-supply.txt
new file mode 100644
index 000000000000..832346e489a3
--- /dev/null
+++ b/Documentation/devicetree/bindings/opp/ti-omap5-opp-supply.txt
@@ -0,0 +1,63 @@
+Texas Instruments OMAP compatible OPP supply description
+
+OMAP5, DRA7, and AM57 family of SoCs have Class0 AVS eFuse registers which
+contain data that can be used to adjust voltages programmed for some of their
+supplies for more efficient operation. This binding provides the information
+needed to read these values and use them to program the main regulator during
+an OPP transitions.
+
+Also, some supplies may have an associated vbb-supply which is an Adaptive Body
+Bias regulator which much be transitioned in a specific sequence with regards
+to the vdd-supply and clk when making an OPP transition. By supplying two
+regulators to the device that will undergo OPP transitions we can make use
+of the multi regulator binding that is part of the OPP core described here [1]
+to describe both regulators needed by the platform.
+
+[1] Documentation/devicetree/bindings/opp/opp.txt
+
+Required Properties for Device Node:
+- vdd-supply: phandle to regulator controlling VDD supply
+- vbb-supply: phandle to regulator controlling Body Bias supply
+	      (Usually Adaptive Body Bias regulator)
+
+Required Properties for opp-supply node:
+- compatible: Should be one of:
+	"ti,omap-opp-supply" - basic OPP supply controlling VDD and VBB
+	"ti,omap5-opp-supply" - OMAP5+ optimized voltages in efuse(class0)VDD
+			    along with VBB
+	"ti,omap5-core-opp-supply" - OMAP5+ optimized voltages in efuse(class0) VDD
+			    but no VBB.
+- reg: Address and length of the efuse register set for the device (mandatory
+	only for "ti,omap5-opp-supply")
+- ti,efuse-settings: An array of u32 tuple items providing information about
+	optimized efuse configuration. Each item consists of the following:
+	volt: voltage in uV - reference voltage (OPP voltage)
+	efuse_offseet: efuse offset from reg where the optimized voltage is stored.
+- ti,absolute-max-voltage-uv: absolute maximum voltage for the OPP supply.
+
+Example:
+
+/* Device Node (CPU)  */
+cpus {
+	cpu0: cpu@0 {
+		device_type = "cpu";
+
+		...
+
+		vdd-supply = <&vcc>;
+		vbb-supply = <&abb_mpu>;
+	};
+};
+
+/* OMAP OPP Supply with Class0 registers */
+opp_supply_mpu: opp_supply@4a003b20 {
+	compatible = "ti,omap5-opp-supply";
+	reg = <0x4a003b20 0x8>;
+	ti,efuse-settings = <
+	/* uV   offset */
+	1060000 0x0
+	1160000 0x4
+	1210000 0x8
+	>;
+	ti,absolute-max-voltage-uv = <1500000>;
+};
diff --git a/Documentation/devicetree/bindings/pci/altera-pcie.txt b/Documentation/devicetree/bindings/pci/altera-pcie.txt
index 495880193adc..a1dc9366a8fc 100644
--- a/Documentation/devicetree/bindings/pci/altera-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/altera-pcie.txt
@@ -25,7 +25,7 @@ Optional properties:
 - bus-range:	PCI bus numbers covered
 
 Example
-	pcie_0: pcie@0xc00000000 {
+	pcie_0: pcie@c00000000 {
 		compatible = "altr,pcie-root-port-1.0";
 		reg = <0xc0000000 0x20000000>,
 			<0xff220000 0x00004000>;
diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt
index 7b1e48bf172b..cb33421184a0 100644
--- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt
@@ -41,6 +41,7 @@ Optional properties:
 Additional required properties for imx6sx-pcie:
 - clock names: Must include the following additional entries:
 	- "pcie_inbound_axi"
+- power-domains: Must be set to a phandle pointing to the PCIE_PHY power domain
 
 Additional required properties for imx7d-pcie:
 - power-domains: Must be set to a phandle pointing to PCIE_PHY power domain
@@ -52,7 +53,7 @@ Additional required properties for imx7d-pcie:
 
 Example:
 
-	pcie@0x01000000 {
+	pcie@01000000 {
 		compatible = "fsl,imx6q-pcie", "snps,dw-pcie";
 		reg = <0x01ffc000 0x04000>,
 		      <0x01f00000 0x80000>;
diff --git a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
index bdb7ab39d2d7..7bf9df047a1e 100644
--- a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
@@ -21,7 +21,7 @@ Optional properties:
 - dma-coherent: Present if DMA operations are coherent.
 
 Hip05 Example (note that Hip06 is the same except compatible):
-	pcie@0xb0080000 {
+	pcie@b0080000 {
 		compatible = "hisilicon,hip05-pcie", "snps,dw-pcie";
 		reg = <0 0xb0080000 0 0x10000>, <0x220 0x00000000 0 0x2000>;
 		reg-names = "rc_dbi", "config";
diff --git a/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt b/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt
index cbc7847dbf6c..c1ce5a0a652e 100644
--- a/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt
+++ b/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt
@@ -45,7 +45,7 @@ Optional properties:
 - usb3_vbus-supply : regulator phandle for controller usb3 vbus
 
 Example:
-	usbphy: phy@0x01c13400 {
+	usbphy: phy@01c13400 {
 		#phy-cells = <1>;
 		compatible = "allwinner,sun4i-a10-usb-phy";
 		/* phy base regs, phy1 pmu reg, phy2 pmu reg */
diff --git a/Documentation/devicetree/bindings/phy/ti-phy.txt b/Documentation/devicetree/bindings/phy/ti-phy.txt
index cd13e6157088..57dfda8a7a1d 100644
--- a/Documentation/devicetree/bindings/phy/ti-phy.txt
+++ b/Documentation/devicetree/bindings/phy/ti-phy.txt
@@ -120,7 +120,7 @@ usb3phy@4a084400 {
 			"refclk";
 };
 
-sata_phy: phy@4A096000 {
+sata_phy: phy@4a096000 {
 	compatible = "ti,phy-pipe3-sata";
 	reg = <0x4A096000 0x80>, /* phy_rx */
 	      <0x4A096400 0x64>, /* phy_tx */
diff --git a/Documentation/devicetree/bindings/pinctrl/abilis,tb10x-iomux.txt b/Documentation/devicetree/bindings/pinctrl/abilis,tb10x-iomux.txt
index 2c11866221c2..c591b9cb5ba0 100644
--- a/Documentation/devicetree/bindings/pinctrl/abilis,tb10x-iomux.txt
+++ b/Documentation/devicetree/bindings/pinctrl/abilis,tb10x-iomux.txt
@@ -49,7 +49,7 @@ explained in Documentation/devicetree/bindings/gpio/gpio.txt.
 Example
 -------
 
-iomux: iomux@FF10601c {
+iomux: iomux@ff10601c {
 	compatible = "abilis,tb10x-iomux";
 	reg = <0xFF10601c 0x4>;
 	pctl_gpio_a: pctl-gpio-a {
@@ -59,7 +59,7 @@ iomux: iomux@FF10601c {
 		abilis,function = "uart0";
 	};
 };
-uart@FF100000 {
+uart@ff100000 {
 	compatible = "snps,dw-apb-uart";
 	reg = <0xFF100000 0x100>;
 	clock-frequency = <166666666>;
@@ -69,7 +69,7 @@ uart@FF100000 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pctl_uart0>;
 };
-gpioa: gpio@FF140000 {
+gpioa: gpio@ff140000 {
 	compatible = "abilis,tb10x-gpio";
 	reg = <0xFF140000 0x1000>;
 	gpio-controller;
diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,cygnus-pinmux.txt b/Documentation/devicetree/bindings/pinctrl/brcm,cygnus-pinmux.txt
index 3600d5c6c4d7..3914529a3214 100644
--- a/Documentation/devicetree/bindings/pinctrl/brcm,cygnus-pinmux.txt
+++ b/Documentation/devicetree/bindings/pinctrl/brcm,cygnus-pinmux.txt
@@ -25,7 +25,7 @@ Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
 
 For example:
 
-	pinmux: pinmux@0x0301d0c8 {
+	pinmux: pinmux@0301d0c8 {
 		compatible = "brcm,cygnus-pinmux";
 		reg = <0x0301d0c8 0x1b0>;
 
diff --git a/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt
index 0326154c7925..a72dc3178179 100644
--- a/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt
@@ -152,7 +152,7 @@ resetn
 
 Example:
 --------
-pinctrl@18101C00 {
+pinctrl@18101c00 {
 	compatible = "img,pistachio-system-pinctrl";
 	reg = <0x18101C00 0x400>;
 
diff --git a/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt b/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt
index 8e5216bcd748..4658f105fa09 100644
--- a/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt
+++ b/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt
@@ -163,7 +163,7 @@ Valid values for xRX300 pin names:
 						io42-io43,io48-io61.
 
 Example:
-	gpio: pinmux@E100B10 {
+	gpio: pinmux@e100b10 {
 		compatible = "lantiq,danube-pinctrl";
 		pinctrl-names = "default";
 		pinctrl-0 = <&state_default>;
diff --git a/Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt
index 2392557ede27..2c12f9789116 100644
--- a/Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt
@@ -9,6 +9,8 @@ Required properties for the root node:
 		      "amlogic,meson-gxbb-aobus-pinctrl"
 		      "amlogic,meson-gxl-periphs-pinctrl"
 		      "amlogic,meson-gxl-aobus-pinctrl"
+		      "amlogic,meson-axg-periphs-pinctrl"
+		      "amlogic,meson-axg-aobus-pinctrl"
  - reg: address and size of registers controlling irq functionality
 
 === GPIO sub-nodes ===
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-atlas7.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-atlas7.txt
index eecf028ff485..bf9b07016c87 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-atlas7.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-atlas7.txt
@@ -96,14 +96,14 @@ For example, pinctrl might have subnodes like the following:
 
 For a specific board, if it wants to use sd1,
 it can add the following to its board-specific .dts file.
-sd1: sd@0x12340000 {
+sd1: sd@12340000 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&sd1_pmx0>;
 }
 
 or
 
-sd1: sd@0x12340000 {
+sd1: sd@12340000 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&sd1_pmx1>;
 }
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
index 231fa1db7c5e..afa8a18ea11a 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
@@ -81,7 +81,7 @@ Examples:
 		reg = <0 0x10005000 0 0x1000>;
 	};
 
-	syscfg_pctl_b: syscfg_pctl_b@1020C020 {
+	syscfg_pctl_b: syscfg_pctl_b@1020c020 {
 		compatible = "mediatek,mt8135-pctl-b-syscfg", "syscon";
 		reg = <0 0x1020C020 0 0x1000>;
 	};
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-sirf.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-sirf.txt
index 5f55be59d914..f8420520e14b 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-sirf.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-sirf.txt
@@ -41,7 +41,7 @@ For example, pinctrl might have subnodes like the following:
 
 For a specific board, if it wants to use uart2 without hardware flow control,
 it can add the following to its board-specific .dts file.
-uart2: uart@0xb0070000 {
+uart2: uart@b0070000 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart2_noflow_pins_a>;
 }
diff --git a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
index 4864e3a74de3..a01a3b8a2363 100644
--- a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
@@ -136,7 +136,7 @@ Example for rk3188:
 		#size-cells = <1>;
 		ranges;
 
-		gpio0: gpio0@0x2000a000 {
+		gpio0: gpio0@2000a000 {
 			compatible = "rockchip,rk3188-gpio-bank0";
 			reg = <0x2000a000 0x100>;
 			interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>;
@@ -149,7 +149,7 @@ Example for rk3188:
 			#interrupt-cells = <2>;
 		};
 
-		gpio1: gpio1@0x2003c000 {
+		gpio1: gpio1@2003c000 {
 			compatible = "rockchip,gpio-bank";
 			reg = <0x2003c000 0x100>;
 			interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/power/actions,owl-sps.txt b/Documentation/devicetree/bindings/power/actions,owl-sps.txt
index 007b9a7ae723..78edd63641e8 100644
--- a/Documentation/devicetree/bindings/power/actions,owl-sps.txt
+++ b/Documentation/devicetree/bindings/power/actions,owl-sps.txt
@@ -2,10 +2,12 @@ Actions Semi Owl Smart Power System (SPS)
 
 Required properties:
 - compatible          :  "actions,s500-sps" for S500
+                         "actions,s700-sps" for S700
 - reg                 :  Offset and length of the register set for the device.
 - #power-domain-cells :  Must be 1.
                          See macros in:
                           include/dt-bindings/power/owl-s500-powergate.h for S500
+                          include/dt-bindings/power/owl-s700-powergate.h for S700
 
 
 Example:
diff --git a/Documentation/devicetree/bindings/power/fsl,imx-gpc.txt b/Documentation/devicetree/bindings/power/fsl,imx-gpc.txt
index e371b262d709..b31d6bbeee16 100644
--- a/Documentation/devicetree/bindings/power/fsl,imx-gpc.txt
+++ b/Documentation/devicetree/bindings/power/fsl,imx-gpc.txt
@@ -9,6 +9,7 @@ Required properties:
   - fsl,imx6q-gpc
   - fsl,imx6qp-gpc
   - fsl,imx6sl-gpc
+  - fsl,imx6sx-gpc
 - reg: should be register base and length as documented in the
   datasheet
 - interrupts: Should contain one interrupt specifier for the GPC interrupt
@@ -29,6 +30,8 @@ Required properties:
   PU_DOMAIN      1
   The following additional DOMAIN_INDEX value is valid for i.MX6SL:
   DISPLAY_DOMAIN 2
+  The following additional DOMAIN_INDEX value is valid for i.MX6SX:
+  PCI_DOMAIN     3
 
 - #power-domain-cells: Should be 0
 
diff --git a/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.txt b/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.txt
index 02f45c65fd87..9acce75b29ab 100644
--- a/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.txt
+++ b/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.txt
@@ -44,10 +44,10 @@ Example:
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			pgc_pcie_phy: power-domain@3 {
+			pgc_pcie_phy: power-domain@1 {
 				#power-domain-cells = <0>;
 
-				reg = <IMX7_POWER_DOMAIN_PCIE_PHY>;
+				reg = <1>;
 				power-supply = <&reg_1p0d>;
 			};
 		};
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
index 14bd9e945ff6..f3355313c020 100644
--- a/Documentation/devicetree/bindings/power/power_domain.txt
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -40,6 +40,12 @@ Optional properties:
   domain's idle states. In the absence of this property, the domain would be
   considered as capable of being powered-on or powered-off.
 
+- operating-points-v2 : Phandles to the OPP tables of power domains provided by
+  a power domain provider. If the provider provides a single power domain only
+  or all the power domains provided by the provider have identical OPP tables,
+  then this shall contain a single phandle. Refer to ../opp/opp.txt for more
+  information.
+
 Example:
 
 	power: power-controller@12340000 {
@@ -120,4 +126,63 @@ The node above defines a typical PM domain consumer device, which is located
 inside a PM domain with index 0 of a power controller represented by a node
 with the label "power".
 
+Optional properties:
+- required-opp: This contains phandle to an OPP node in another device's OPP
+  table. It may contain an array of phandles, where each phandle points to an
+  OPP of a different device. It should not contain multiple phandles to the OPP
+  nodes in the same OPP table. This specifies the minimum required OPP of the
+  device(s), whose OPP's phandle is present in this property, for the
+  functioning of the current device at the current OPP (where this property is
+  present).
+
+Example:
+- OPP table for domain provider that provides two domains.
+
+	domain0_opp_table: opp-table0 {
+		compatible = "operating-points-v2";
+
+		domain0_opp_0: opp-1000000000 {
+			opp-hz = /bits/ 64 <1000000000>;
+			opp-microvolt = <975000 970000 985000>;
+		};
+		domain0_opp_1: opp-1100000000 {
+			opp-hz = /bits/ 64 <1100000000>;
+			opp-microvolt = <1000000 980000 1010000>;
+		};
+	};
+
+	domain1_opp_table: opp-table1 {
+		compatible = "operating-points-v2";
+
+		domain1_opp_0: opp-1200000000 {
+			opp-hz = /bits/ 64 <1200000000>;
+			opp-microvolt = <975000 970000 985000>;
+		};
+		domain1_opp_1: opp-1300000000 {
+			opp-hz = /bits/ 64 <1300000000>;
+			opp-microvolt = <1000000 980000 1010000>;
+		};
+	};
+
+	power: power-controller@12340000 {
+		compatible = "foo,power-controller";
+		reg = <0x12340000 0x1000>;
+		#power-domain-cells = <1>;
+		operating-points-v2 = <&domain0_opp_table>, <&domain1_opp_table>;
+	};
+
+	leaky-device0@12350000 {
+		compatible = "foo,i-leak-current";
+		reg = <0x12350000 0x1000>;
+		power-domains = <&power 0>;
+		required-opp = <&domain0_opp_0>;
+	};
+
+	leaky-device1@12350000 {
+		compatible = "foo,i-leak-current";
+		reg = <0x12350000 0x1000>;
+		power-domains = <&power 1>;
+		required-opp = <&domain1_opp_1>;
+	};
+
 [1]. Documentation/devicetree/bindings/power/domain-idle-state.txt
diff --git a/Documentation/devicetree/bindings/power/reset/imx-snvs-poweroff.txt b/Documentation/devicetree/bindings/power/reset/imx-snvs-poweroff.txt
deleted file mode 100644
index 1b81fcd9fb72..000000000000
--- a/Documentation/devicetree/bindings/power/reset/imx-snvs-poweroff.txt
+++ /dev/null
@@ -1,23 +0,0 @@
-i.mx6 Poweroff Driver
-
-SNVS_LPCR in SNVS module can power off the whole system by pull
-PMIC_ON_REQ low if PMIC_ON_REQ is connected with external PMIC.
-If you don't want to use PMIC_ON_REQ as power on/off control,
-please set status='disabled' to disable this driver.
-
-Required Properties:
--compatible: "fsl,sec-v4.0-poweroff"
--reg: Specifies the physical address of the SNVS_LPCR register
-
-Example:
-	snvs@20cc000 {
-		compatible = "fsl,sec-v4.0-mon", "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges = <0 0x020cc000 0x4000>;
-		.....
-		snvs_poweroff: snvs-poweroff@38 {
-			compatible = "fsl,sec-v4.0-poweroff";
-			reg = <0x38 0x4>;
-		};
-	}
diff --git a/Documentation/devicetree/bindings/power/supply/bq27xxx.txt b/Documentation/devicetree/bindings/power/supply/bq27xxx.txt
index 6858e1a804ad..615c1cb6889f 100644
--- a/Documentation/devicetree/bindings/power/supply/bq27xxx.txt
+++ b/Documentation/devicetree/bindings/power/supply/bq27xxx.txt
@@ -15,6 +15,7 @@ Required properties:
  * "ti,bq27520g2" - BQ27520-g2
  * "ti,bq27520g3" - BQ27520-g3
  * "ti,bq27520g4" - BQ27520-g4
+ * "ti,bq27521" - BQ27521
  * "ti,bq27530" - BQ27530
  * "ti,bq27531" - BQ27531
  * "ti,bq27541" - BQ27541
diff --git a/Documentation/devicetree/bindings/power/ti-smartreflex.txt b/Documentation/devicetree/bindings/power/ti-smartreflex.txt
index 9780957c9115..21ef14d6af12 100644
--- a/Documentation/devicetree/bindings/power/ti-smartreflex.txt
+++ b/Documentation/devicetree/bindings/power/ti-smartreflex.txt
@@ -7,7 +7,7 @@ Required properties:
 
 compatible: Shall be one of the following:
 	    "ti,omap3-smartreflex-core"
-	    "ti,omap3-smartreflex-iva"
+	    "ti,omap3-smartreflex-mpu-iva"
 	    "ti,omap4-smartreflex-core"
 	    "ti,omap4-smartreflex-mpu"
 	    "ti,omap4-smartreflex-iva"
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/interlaken-lac.txt b/Documentation/devicetree/bindings/powerpc/fsl/interlaken-lac.txt
index 641bc13983e1..ed6a414b2e10 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/interlaken-lac.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/interlaken-lac.txt
@@ -223,37 +223,37 @@ lac-portals {
 		reg = <0x9000 0x1000>;
 	};
 
-	lportal10: lac-portal@A000 {
+	lportal10: lac-portal@a000 {
 		compatible = "fsl,interlaken-lac-portal-v1.0";
 		fsl,liodn = <0x20E>;
 		reg = <0xA000 0x1000>;
 	};
 
-	lportal11: lac-portal@B000 {
+	lportal11: lac-portal@b000 {
 		compatible = "fsl,interlaken-lac-portal-v1.0";
 		fsl,liodn = <0x20F>;
 		reg = <0xB000 0x1000>;
 	};
 
-	lportal12: lac-portal@C000 {
+	lportal12: lac-portal@c000 {
 		compatible = "fsl,interlaken-lac-portal-v1.0";
 		fsl,liodn = <0x210>;
 		reg = <0xC000 0x1000>;
 	};
 
-	lportal13: lac-portal@D000 {
+	lportal13: lac-portal@d000 {
 		compatible = "fsl,interlaken-lac-portal-v1.0";
 		fsl,liodn = <0x211>;
 		reg = <0xD000 0x1000>;
 	};
 
-	lportal14: lac-portal@E000 {
+	lportal14: lac-portal@e000 {
 		compatible = "fsl,interlaken-lac-portal-v1.0";
 		fsl,liodn = <0x212>;
 		reg = <0xE000 0x1000>;
 	};
 
-	lportal15: lac-portal@F000 {
+	lportal15: lac-portal@f000 {
 		compatible = "fsl,interlaken-lac-portal-v1.0";
 		fsl,liodn = <0x213>;
 		reg = <0xF000 0x1000>;
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/mpc5200.txt b/Documentation/devicetree/bindings/powerpc/fsl/mpc5200.txt
index 4ccb2cd5df94..d096cf461d81 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/mpc5200.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/mpc5200.txt
@@ -195,4 +195,4 @@ External interrupts:
 
 fsl,mpc5200-mscan nodes
 -----------------------
-See file can.txt in this directory.
+See file Documentation/devicetree/bindings/powerpc/fsl/mpc5200.txt
diff --git a/Documentation/devicetree/bindings/regulator/regulator.txt b/Documentation/devicetree/bindings/regulator/regulator.txt
index 378f6dc8b8bd..2babe15b618d 100644
--- a/Documentation/devicetree/bindings/regulator/regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/regulator.txt
@@ -42,8 +42,16 @@ Optional properties:
 - regulator-state-[mem/disk] node has following common properties:
 	- regulator-on-in-suspend: regulator should be on in suspend state.
 	- regulator-off-in-suspend: regulator should be off in suspend state.
-	- regulator-suspend-microvolt: regulator should be set to this voltage
-	  in suspend.
+	- regulator-suspend-min-microvolt: minimum voltage may be set in
+	  suspend state.
+	- regulator-suspend-max-microvolt: maximum voltage may be set in
+	  suspend state.
+	- regulator-suspend-microvolt: the default voltage which regulator
+	  would be set in suspend. This property is now deprecated, instead
+	  setting voltage for suspend mode via the API which regulator
+	  driver provides is recommended.
+	- regulator-changeable-in-suspend: whether the default voltage and
+	  the regulator on/off in suspend can be changed in runtime.
 	- regulator-mode: operating mode in the given suspend state.
 	  The set of possible operating modes depends on the capabilities of
 	  every hardware so the valid modes are documented on each regulator
@@ -107,7 +115,7 @@ regulators (twl_reg1 and twl_reg2),
 		...
 	};
 
-	mmc: mmc@0x0 {
+	mmc: mmc@0 {
 		...
 		...
 		vmmc-supply = <&twl_reg1>;
diff --git a/Documentation/devicetree/bindings/regulator/sprd,sc2731-regulator.txt b/Documentation/devicetree/bindings/regulator/sprd,sc2731-regulator.txt
new file mode 100644
index 000000000000..63dc07877cd6
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/sprd,sc2731-regulator.txt
@@ -0,0 +1,43 @@
+Spreadtrum SC2731 Voltage regulators
+
+The SC2731 integrates low-voltage and low quiescent current DCDC/LDO.
+14 LDO and 3 DCDCs are designed for external use. All DCDCs/LDOs have
+their own bypass (power-down) control signals. External tantalum or MLCC
+ceramic capacitors are recommended to use with these LDOs.
+
+Required properties:
+ - compatible: should be "sprd,sc27xx-regulator".
+
+List of regulators provided by this controller. It is named according to
+its regulator type, BUCK_<name> and LDO_<name>. The definition for each
+of these nodes is defined using the standard binding for regulators at
+Documentation/devicetree/bindings/regulator/regulator.txt.
+
+The valid names for regulators are:
+BUCK:
+	BUCK_CPU0, BUCK_CPU1, BUCK_RF
+LDO:
+	LDO_CAMA0, LDO_CAMA1, LDO_CAMMOT, LDO_VLDO, LDO_EMMCCORE, LDO_SDCORE,
+	LDO_SDIO, LDO_WIFIPA, LDO_USB33, LDO_CAMD0, LDO_CAMD1, LDO_CON,
+	LDO_CAMIO, LDO_SRAM
+
+Example:
+	regulators {
+		compatible = "sprd,sc27xx-regulator";
+
+		vddarm0: BUCK_CPU0 {
+			regulator-name = "vddarm0";
+			regulator-min-microvolt = <400000>;
+			regulator-max-microvolt = <1996875>;
+			regulator-ramp-delay = <25000>;
+			regulator-always-on;
+		};
+
+		vddcama0: LDO_CAMA0 {
+			regulator-name = "vddcama0";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <3750000>;
+			regulator-enable-ramp-delay = <100>;
+		};
+		...
+	};
diff --git a/Documentation/devicetree/bindings/regulator/st,stm32-vrefbuf.txt b/Documentation/devicetree/bindings/regulator/st,stm32-vrefbuf.txt
index 3944ee3e731e..5ddb8500a929 100644
--- a/Documentation/devicetree/bindings/regulator/st,stm32-vrefbuf.txt
+++ b/Documentation/devicetree/bindings/regulator/st,stm32-vrefbuf.txt
@@ -10,7 +10,7 @@ Required properties:
 - clocks:		Must contain an entry for peripheral clock.
 
 Example:
-	vrefbuf: regulator@58003C00 {
+	vrefbuf: regulator@58003c00 {
 		compatible = "st,stm32-vrefbuf";
 		reg = <0x58003C00 0x8>;
 		clocks = <&rcc VREF_CK>;
diff --git a/Documentation/devicetree/bindings/reset/amlogic,meson-reset.txt b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.txt
index e746b631793a..28ef6c295c76 100644
--- a/Documentation/devicetree/bindings/reset/amlogic,meson-reset.txt
+++ b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.txt
@@ -5,7 +5,8 @@ Please also refer to reset.txt in this directory for common reset
 controller binding usage.
 
 Required properties:
-- compatible: Should be "amlogic,meson8b-reset" or "amlogic,meson-gxbb-reset"
+- compatible: Should be "amlogic,meson8b-reset", "amlogic,meson-gxbb-reset" or
+	"amlogic,meson-axg-reset".
 - reg: should contain the register address base
 - #reset-cells: 1, see below
 
diff --git a/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt b/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt
index 26542690b578..627b29531a32 100644
--- a/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt
+++ b/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt
@@ -1,11 +1,19 @@
-BCM2835 Random number generator
+BCM2835/6368 Random number generator
 
 Required properties:
 
-- compatible : should be "brcm,bcm2835-rng"  or "brcm,bcm-nsp-rng" or
-  "brcm,bcm5301x-rng"
+- compatible : should be one of
+	"brcm,bcm2835-rng"
+	"brcm,bcm-nsp-rng"
+	"brcm,bcm5301x-rng" or
+	"brcm,bcm6368-rng"
 - reg : Specifies base physical address and size of the registers.
 
+Optional properties:
+
+- clocks : phandle to clock-controller plus clock-specifier pair
+- clock-names : "ipsec" as a clock name
+
 Example:
 
 rng {
@@ -17,3 +25,11 @@ rng@18033000 {
 	compatible = "brcm,bcm-nsp-rng";
 	reg = <0x18033000 0x14>;
 };
+
+random: rng@10004180 {
+	compatible = "brcm,bcm6368-rng";
+	reg = <0x10004180 0x14>;
+
+	clocks = <&periph_clk 18>;
+	clock-names = "ipsec";
+};
diff --git a/Documentation/devicetree/bindings/rng/brcm,bcm6368.txt b/Documentation/devicetree/bindings/rng/brcm,bcm6368.txt
deleted file mode 100644
index 4b5ac600bfbd..000000000000
--- a/Documentation/devicetree/bindings/rng/brcm,bcm6368.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-BCM6368 Random number generator
-
-Required properties:
-
-- compatible : should be "brcm,bcm6368-rng"
-- reg : Specifies base physical address and size of the registers
-- clocks : phandle to clock-controller plus clock-specifier pair
-- clock-names : "ipsec" as a clock name
-
-Example:
-	random: rng@10004180 {
-		compatible = "brcm,bcm6368-rng";
-		reg = <0x10004180 0x14>;
-
-		clocks = <&periph_clk 18>;
-		clock-names = "ipsec";
-	};
diff --git a/Documentation/devicetree/bindings/scsi/hisilicon-sas.txt b/Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
index b6a869f97715..df3bef7998fa 100644
--- a/Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
+++ b/Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
@@ -8,7 +8,10 @@ Main node required properties:
 	(b) "hisilicon,hip06-sas-v2" for v2 hw in hip06 chipset
 	(c) "hisilicon,hip07-sas-v2" for v2 hw in hip07 chipset
   - sas-addr : array of 8 bytes for host SAS address
-  - reg : Address and length of the SAS register
+  - reg : Contains two regions. The first is the address and length of the SAS
+          register. The second is the address and length of CPLD register for
+          SGPIO control. The second is optional, and should be set only when
+          we use a CPLD for directly attached disk LED control.
   - hisilicon,sas-syscon: phandle of syscon used for sas control
   - ctrl-reset-reg : offset to controller reset register in ctrl reg
   - ctrl-reset-sts-reg : offset to controller reset status register in ctrl reg
diff --git a/Documentation/devicetree/bindings/serial/efm32-uart.txt b/Documentation/devicetree/bindings/serial/efm32-uart.txt
index 8adbab268ca3..4f8d8fde0c1c 100644
--- a/Documentation/devicetree/bindings/serial/efm32-uart.txt
+++ b/Documentation/devicetree/bindings/serial/efm32-uart.txt
@@ -12,7 +12,7 @@ Optional properties:
 
 Example:
 
-uart@0x4000c400 {
+uart@4000c400 {
 	compatible = "energymicro,efm32-uart";
 	reg = <0x4000c400 0x400>;
 	interrupts = <15>;
diff --git a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
index 860a9559839a..afcfbc34e243 100644
--- a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
+++ b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
@@ -6,10 +6,10 @@ Required properties:
 - interrupts : Should contain uart interrupt
 
 Optional properties:
-- fsl,irda-mode : Indicate the uart supports irda mode
 - fsl,dte-mode : Indicate the uart works in DTE mode. The uart works
                   in DCE mode by default.
-- rs485-rts-delay, rs485-rx-during-tx, linux,rs485-enabled-at-boot-time: see rs485.txt
+- rs485-rts-delay, rs485-rts-active-low, rs485-rx-during-tx,
+  linux,rs485-enabled-at-boot-time: see rs485.txt
 
 Please check Documentation/devicetree/bindings/serial/serial.txt
 for the complete list of generic properties.
diff --git a/Documentation/devicetree/bindings/serial/fsl-lpuart.txt b/Documentation/devicetree/bindings/serial/fsl-lpuart.txt
index 59567b51cf09..6bd3f2e93d61 100644
--- a/Documentation/devicetree/bindings/serial/fsl-lpuart.txt
+++ b/Documentation/devicetree/bindings/serial/fsl-lpuart.txt
@@ -16,7 +16,8 @@ Required properties:
 Optional properties:
 - dmas: A list of two dma specifiers, one for each entry in dma-names.
 - dma-names: should contain "tx" and "rx".
-- rs485-rts-delay, rs485-rx-during-tx, linux,rs485-enabled-at-boot-time: see rs485.txt
+- rs485-rts-delay, rs485-rts-active-low, rs485-rx-during-tx,
+  linux,rs485-enabled-at-boot-time: see rs485.txt
 
 Note: Optional properties for DMA support. Write them both or both not.
 
diff --git a/Documentation/devicetree/bindings/serial/ingenic,uart.txt b/Documentation/devicetree/bindings/serial/ingenic,uart.txt
index 02cb7fe59cb7..c3c6406d5cfe 100644
--- a/Documentation/devicetree/bindings/serial/ingenic,uart.txt
+++ b/Documentation/devicetree/bindings/serial/ingenic,uart.txt
@@ -1,8 +1,12 @@
 * Ingenic SoC UART
 
 Required properties:
-- compatible : "ingenic,jz4740-uart", "ingenic,jz4760-uart",
-	"ingenic,jz4775-uart" or "ingenic,jz4780-uart"
+- compatible : One of:
+  - "ingenic,jz4740-uart",
+  - "ingenic,jz4760-uart",
+  - "ingenic,jz4770-uart",
+  - "ingenic,jz4775-uart",
+  - "ingenic,jz4780-uart".
 - reg : offset and length of the register set for the device.
 - interrupts : should contain uart interrupt.
 - clocks : phandles to the module & baud clocks.
diff --git a/Documentation/devicetree/bindings/serial/lantiq_asc.txt b/Documentation/devicetree/bindings/serial/lantiq_asc.txt
index 5b78591aaa46..3acbd309ab9d 100644
--- a/Documentation/devicetree/bindings/serial/lantiq_asc.txt
+++ b/Documentation/devicetree/bindings/serial/lantiq_asc.txt
@@ -8,7 +8,7 @@ Required properties:
 
 Example:
 
-asc1: serial@E100C00 {
+asc1: serial@e100c00 {
 	compatible = "lantiq,asc";
 	reg = <0xE100C00 0x400>;
 	interrupt-parent = <&icu0>;
diff --git a/Documentation/devicetree/bindings/serial/maxim,max310x.txt b/Documentation/devicetree/bindings/serial/maxim,max310x.txt
index 83a919c241b0..823f77dd7978 100644
--- a/Documentation/devicetree/bindings/serial/maxim,max310x.txt
+++ b/Documentation/devicetree/bindings/serial/maxim,max310x.txt
@@ -24,13 +24,27 @@ Optional properties:
     1 = active low.
 
 Example:
+
+/ {
+	clocks {
+		spi_uart_clk: osc_max14830 {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <3686400>;
+		};
+
+	};
+};
+
+&spi0 {
 	max14830: max14830@0 {
 		compatible = "maxim,max14830";
 		reg = <0>;
-		clocks = <&clk20m>;
+		clocks = <&spi_uart_clk>;
 		clock-names = "osc";
 		interrupt-parent = <&gpio3>;
-		interrupts = <7 IRQ_TYPE_EDGE_FALLING>;
+		interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
 		gpio-controller;
 		#gpio-cells = <2>;
 	};
+};
diff --git a/Documentation/devicetree/bindings/serial/mvebu-uart.txt b/Documentation/devicetree/bindings/serial/mvebu-uart.txt
index d37fabe17bd1..2ae2fee7e023 100644
--- a/Documentation/devicetree/bindings/serial/mvebu-uart.txt
+++ b/Documentation/devicetree/bindings/serial/mvebu-uart.txt
@@ -1,13 +1,53 @@
-* Marvell UART : Non standard UART used in some of Marvell EBU SoCs (e.g., Armada-3700)
+* Marvell UART : Non standard UART used in some of Marvell EBU SoCs
+                 e.g., Armada-3700.
 
 Required properties:
-- compatible: "marvell,armada-3700-uart"
+- compatible:
+    - "marvell,armada-3700-uart" for the standard variant of the UART
+      (32 bytes FIFO, no DMA, level interrupts, 8-bit access to the
+      FIFO, baudrate limited to 230400).
+    - "marvell,armada-3700-uart-ext" for the extended variant of the
+      UART (128 bytes FIFO, DMA, front interrupts, 8-bit or 32-bit
+      accesses to the FIFO, baudrate unlimited by the dividers).
 - reg: offset and length of the register set for the device.
-- interrupts: device interrupt
+- clocks: UART reference clock used to derive the baudrate. If no clock
+      is provided (possible only with the "marvell,armada-3700-uart"
+      compatible string for backward compatibility), it will only work
+      if the baudrate was initialized by the bootloader and no baudrate
+      change will then be possible.
+- interrupts:
+    - Must contain three elements for the standard variant of the IP
+      (marvell,armada-3700-uart): "uart-sum", "uart-tx" and "uart-rx",
+      respectively the UART sum interrupt, the UART TX interrupt and
+      UART RX interrupt. A corresponding interrupt-names property must
+      be defined.
+    - Must contain two elements for the extended variant of the IP
+      (marvell,armada-3700-uart-ext): "uart-tx" and "uart-rx",
+      respectively the UART TX interrupt and the UART RX interrupt. A
+      corresponding interrupts-names property must be defined.
+    - For backward compatibility reasons, a single element interrupts
+      property is also supported for the standard variant of the IP,
+      containing only the UART sum interrupt. This form is deprecated
+      and should no longer be used.
 
 Example:
-	serial@12000 {
+	uart0: serial@12000 {
 		compatible = "marvell,armada-3700-uart";
 		reg = <0x12000 0x200>;
-		interrupts = <43>;
+		clocks = <&xtalclk>;
+		interrupts =
+		<GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "uart-sum", "uart-tx", "uart-rx";
+	};
+
+	uart1: serial@12200 {
+		compatible = "marvell,armada-3700-uart-ext";
+		reg = <0x12200 0x30>;
+		clocks = <&xtalclk>;
+		interrupts =
+		<GIC_SPI 30 IRQ_TYPE_EDGE_RISING>,
+		<GIC_SPI 31 IRQ_TYPE_EDGE_RISING>;
+		interrupt-names = "uart-tx", "uart-rx";
 	};
diff --git a/Documentation/devicetree/bindings/serial/omap_serial.txt b/Documentation/devicetree/bindings/serial/omap_serial.txt
index 43eac675f21f..4b0f05adb228 100644
--- a/Documentation/devicetree/bindings/serial/omap_serial.txt
+++ b/Documentation/devicetree/bindings/serial/omap_serial.txt
@@ -20,6 +20,7 @@ Optional properties:
          node and a DMA channel number.
 - dma-names : "rx" for receive channel, "tx" for transmit channel.
 - rs485-rts-delay, rs485-rx-during-tx, linux,rs485-enabled-at-boot-time: see rs485.txt
+- rs485-rts-active-high: drive RTS high when sending (default is low).
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/serial/rs485.txt b/Documentation/devicetree/bindings/serial/rs485.txt
index b8415936dfdb..b7c29f74ebb2 100644
--- a/Documentation/devicetree/bindings/serial/rs485.txt
+++ b/Documentation/devicetree/bindings/serial/rs485.txt
@@ -12,6 +12,7 @@ Optional properties:
   * b is the delay between end of data sent and rts signal in milliseconds
       it corresponds to the delay after sending data and actual release of the line.
   If this property is not specified, <0 0> is assumed.
+- rs485-rts-active-low: drive RTS low when sending (default is high).
 - linux,rs485-enabled-at-boot-time: empty property telling to enable the rs485
   feature at boot time. It can be disabled later with proper ioctl.
 - rs485-rx-during-tx: empty property that enables the receiving of data even
diff --git a/Documentation/devicetree/bindings/serio/allwinner,sun4i-ps2.txt b/Documentation/devicetree/bindings/serio/allwinner,sun4i-ps2.txt
index f311472990a7..75996b6111bb 100644
--- a/Documentation/devicetree/bindings/serio/allwinner,sun4i-ps2.txt
+++ b/Documentation/devicetree/bindings/serio/allwinner,sun4i-ps2.txt
@@ -14,7 +14,7 @@ Required properties:
 
 
 Example:
-	ps20: ps2@0x01c2a000 {
+	ps20: ps2@01c2a000 {
 		compatible = "allwinner,sun4i-a10-ps2";
 		reg = <0x01c2a000 0x400>;
 		interrupts = <0 62 4>;
diff --git a/Documentation/devicetree/bindings/siox/eckelmann,siox-gpio.txt b/Documentation/devicetree/bindings/siox/eckelmann,siox-gpio.txt
new file mode 100644
index 000000000000..55259cf39c25
--- /dev/null
+++ b/Documentation/devicetree/bindings/siox/eckelmann,siox-gpio.txt
@@ -0,0 +1,19 @@
+Eckelmann SIOX GPIO bus
+
+Required properties:
+- compatible : "eckelmann,siox-gpio"
+- din-gpios, dout-gpios, dclk-gpios, dld-gpios: references gpios for the
+    corresponding bus signals.
+
+Examples:
+
+        siox {
+                compatible = "eckelmann,siox-gpio";
+                pinctrl-names = "default";
+                pinctrl-0 = <&pinctrl_siox>;
+
+                din-gpios = <&gpio6 11 0>;
+                dout-gpios = <&gpio6 8 0>;
+                dclk-gpios = <&gpio6 9 0>;
+                dld-gpios = <&gpio6 10 0>;
+        };
diff --git a/Documentation/devicetree/bindings/slimbus/bus.txt b/Documentation/devicetree/bindings/slimbus/bus.txt
new file mode 100644
index 000000000000..52fa6426388c
--- /dev/null
+++ b/Documentation/devicetree/bindings/slimbus/bus.txt
@@ -0,0 +1,50 @@
+SLIM(Serial Low Power Interchip Media Bus) bus
+
+SLIMbus is a 2-wire bus, and is used to communicate with peripheral
+components like audio-codec.
+
+Required property for SLIMbus controller node:
+- compatible	- name of SLIMbus controller
+
+Child nodes:
+Every SLIMbus controller node can contain zero or more child nodes
+representing slave devices on the bus. Every SLIMbus slave device is
+uniquely determined by the enumeration address containing 4 fields:
+Manufacturer ID, Product code, Device index, and Instance value for
+the device.
+If child node is not present and it is instantiated after device
+discovery (slave device reporting itself present).
+
+In some cases it may be necessary to describe non-probeable device
+details such as non-standard ways of powering up a device. In
+such cases, child nodes for those devices will be present as
+slaves of the SLIMbus controller, as detailed below.
+
+Required property for SLIMbus child node if it is present:
+- reg		- Should be ('Device index', 'Instance ID') from SLIMbus
+		  Enumeration  Address.
+		  Device Index Uniquely identifies multiple Devices within
+		  a single Component.
+		  Instance ID Is for the cases where multiple Devices of the
+		  same type or Class are attached to the bus.
+
+- compatible	-"slimMID,PID". The textual representation of Manufacturer ID,
+	 	  Product Code, shall be in lower case hexadecimal with leading
+		  zeroes suppressed
+
+SLIMbus example for Qualcomm's slimbus manager component:
+
+	slim@28080000 {
+		compatible = "qcom,apq8064-slim", "qcom,slim";
+		reg = <0x28080000 0x2000>,
+		interrupts = <0 33 0>;
+		clocks = <&lcc SLIMBUS_SRC>, <&lcc AUDIO_SLIMBUS_CLK>;
+		clock-names = "iface", "core";
+		#address-cells = <2>;
+		#size-cell = <0>;
+
+		codec: wcd9310@1,0{
+			compatible = "slim217,60";
+			reg = <1 0>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/slimbus/slim-qcom-ctrl.txt b/Documentation/devicetree/bindings/slimbus/slim-qcom-ctrl.txt
new file mode 100644
index 000000000000..922dcb8ff24a
--- /dev/null
+++ b/Documentation/devicetree/bindings/slimbus/slim-qcom-ctrl.txt
@@ -0,0 +1,39 @@
+Qualcomm SLIMbus controller
+This controller is used if applications processor driver controls SLIMbus
+master component.
+
+Required properties:
+
+ - #address-cells - refer to Documentation/devicetree/bindings/slimbus/bus.txt
+ - #size-cells	- refer to Documentation/devicetree/bindings/slimbus/bus.txt
+
+ - reg : Offset and length of the register region(s) for the device
+ - reg-names : Register region name(s) referenced in reg above
+	 Required register resource entries are:
+	 "ctrl": Physical address of controller register blocks
+ 	 "slew": required for "qcom,apq8064-slim" SOC.
+ - compatible : should be "qcom,<SOC-NAME>-slim" for SOC specific compatible
+ 		followed by "qcom,slim" for fallback.
+ - interrupts : Interrupt number used by this controller
+ - clocks : Interface and core clocks used by this SLIMbus controller
+ - clock-names : Required clock-name entries are:
+	"iface" : Interface clock for this controller
+	"core" : Interrupt for controller core's BAM
+
+Example:
+
+	slim@28080000 {
+		compatible = "qcom,apq8064-slim", "qcom,slim";
+		reg = <0x28080000 0x2000>, <0x80207C 4>;
+		reg-names = "ctrl", "slew";
+		interrupts = <0 33 0>;
+		clocks = <&lcc SLIMBUS_SRC>, <&lcc AUDIO_SLIMBUS_CLK>;
+		clock-names = "iface", "core";
+		#address-cells = <2>;
+		#size-cell = <0>;
+
+		wcd9310: audio-codec@1,0{
+			compatible = "slim217,60";
+			reg = <1 0>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/soc/mediatek/scpsys.txt b/Documentation/devicetree/bindings/soc/mediatek/scpsys.txt
index 40056f7990f8..76bf45b893fa 100644
--- a/Documentation/devicetree/bindings/soc/mediatek/scpsys.txt
+++ b/Documentation/devicetree/bindings/soc/mediatek/scpsys.txt
@@ -12,11 +12,13 @@ power/power_domain.txt. It provides the power domains defined in
 - include/dt-bindings/power/mt8173-power.h
 - include/dt-bindings/power/mt6797-power.h
 - include/dt-bindings/power/mt2701-power.h
+- include/dt-bindings/power/mt2712-power.h
 - include/dt-bindings/power/mt7622-power.h
 
 Required properties:
 - compatible: Should be one of:
 	- "mediatek,mt2701-scpsys"
+	- "mediatek,mt2712-scpsys"
 	- "mediatek,mt6797-scpsys"
 	- "mediatek,mt7622-scpsys"
 	- "mediatek,mt8173-scpsys"
@@ -27,6 +29,7 @@ Required properties:
                       These are clocks which hardware needs to be
                       enabled before enabling certain power domains.
 	Required clocks for MT2701: "mm", "mfg", "ethif"
+	Required clocks for MT2712: "mm", "mfg", "venc", "jpgdec", "audio", "vdec"
 	Required clocks for MT6797: "mm", "mfg", "vdec"
 	Required clocks for MT7622: "hif_sel"
 	Required clocks for MT8173: "mm", "mfg", "venc", "venc_lt"
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,smp2p.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,smp2p.txt
index af9ca37221ce..a35af2dafdad 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,smp2p.txt
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,smp2p.txt
@@ -17,9 +17,15 @@ processor ID) and a string identifier.
 	Value type: <prop-encoded-array>
 	Definition: one entry specifying the smp2p notification interrupt
 
-- qcom,ipc:
+- mboxes:
 	Usage: required
 	Value type: <prop-encoded-array>
+	Definition: reference to the associated doorbell in APCS, as described
+		    in mailbox/mailbox.txt
+
+- qcom,ipc:
+	Usage: required, unless mboxes is specified
+	Value type: <prop-encoded-array>
 	Definition: three entries specifying the outgoing ipc bit used for
 		    signaling the remote end of the smp2p edge:
 		    - phandle to a syscon node representing the apcs registers
diff --git a/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt b/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt
index 64c66a5644e7..77cd42cc5f54 100644
--- a/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt
+++ b/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt
@@ -220,7 +220,7 @@ qmss: qmss@2a40000 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ranges;
-		pdsp0@0x2a10000 {
+		pdsp0@2a10000 {
 			reg = <0x2a10000 0x1000>,
 			      <0x2a0f000 0x100>,
 			      <0x2a0c000 0x3c8>,
diff --git a/Documentation/devicetree/bindings/soc/xilinx/xlnx,vcu.txt b/Documentation/devicetree/bindings/soc/xilinx/xlnx,vcu.txt
new file mode 100644
index 000000000000..6786d6715df0
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/xilinx/xlnx,vcu.txt
@@ -0,0 +1,31 @@
+LogicoreIP designed compatible with Xilinx ZYNQ family.
+-------------------------------------------------------
+
+General concept
+---------------
+
+LogicoreIP design to provide the isolation between processing system
+and programmable logic. Also provides the list of register set to configure
+the frequency.
+
+Required properties:
+- compatible: shall be one of:
+	"xlnx,vcu"
+	"xlnx,vcu-logicoreip-1.0"
+- reg, reg-names: There are two sets of registers need to provide.
+	1. vcu slcr
+	2. Logicore
+	reg-names should contain name for the each register sequence.
+- clocks: phandle for aclk and pll_ref clocksource
+- clock-names: The identification string, "aclk", is always required for
+   the axi clock. "pll_ref" is required for pll.
+Example:
+
+	xlnx_vcu: vcu@a0040000 {
+		compatible = "xlnx,vcu-logicoreip-1.0";
+		reg = <0x0 0xa0040000 0x0 0x1000>,
+			 <0x0 0xa0041000 0x0 0x1000>;
+		reg-names = "vcu_slcr", "logicore";
+		clocks = <&si570_1>, <&clkc 71>;
+		clock-names = "pll_ref", "aclk";
+	};
diff --git a/Documentation/devicetree/bindings/sound/adi,axi-i2s.txt b/Documentation/devicetree/bindings/sound/adi,axi-i2s.txt
index 5875ca459ed1..4248b662deff 100644
--- a/Documentation/devicetree/bindings/sound/adi,axi-i2s.txt
+++ b/Documentation/devicetree/bindings/sound/adi,axi-i2s.txt
@@ -21,7 +21,7 @@ please check:
 
 Example:
 
-	i2s: i2s@0x77600000 {
+	i2s: i2s@77600000 {
 		compatible = "adi,axi-i2s-1.00.a";
 		reg = <0x77600000 0x1000>;
 		clocks = <&clk 15>, <&audio_clock>;
diff --git a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt
index 4eb7997674a0..7b664e7cb4ae 100644
--- a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt
+++ b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt
@@ -20,7 +20,7 @@ please check:
 
 Example:
 
-	spdif: spdif@0x77400000 {
+	spdif: spdif@77400000 {
 		compatible = "adi,axi-spdif-tx-1.00.a";
 		reg = <0x77600000 0x1000>;
 		clocks = <&clk 15>, <&audio_clock>;
diff --git a/Documentation/devicetree/bindings/sound/ak4613.txt b/Documentation/devicetree/bindings/sound/ak4613.txt
index 1783f9ef0930..49a2e74fd9cb 100644
--- a/Documentation/devicetree/bindings/sound/ak4613.txt
+++ b/Documentation/devicetree/bindings/sound/ak4613.txt
@@ -20,7 +20,7 @@ Optional properties:
 Example:
 
 &i2c {
-	ak4613: ak4613@0x10 {
+	ak4613: ak4613@10 {
 		compatible = "asahi-kasei,ak4613";
 		reg = <0x10>;
 	};
diff --git a/Documentation/devicetree/bindings/sound/ak4642.txt b/Documentation/devicetree/bindings/sound/ak4642.txt
index 340784db6808..58e48ee97175 100644
--- a/Documentation/devicetree/bindings/sound/ak4642.txt
+++ b/Documentation/devicetree/bindings/sound/ak4642.txt
@@ -17,7 +17,7 @@ Optional properties:
 Example 1:
 
 &i2c {
-	ak4648: ak4648@0x12 {
+	ak4648: ak4648@12 {
 		compatible = "asahi-kasei,ak4642";
 		reg = <0x12>;
 	};
diff --git a/Documentation/devicetree/bindings/sound/da7218.txt b/Documentation/devicetree/bindings/sound/da7218.txt
index 5ca5a709b6aa..3ab9dfef38d1 100644
--- a/Documentation/devicetree/bindings/sound/da7218.txt
+++ b/Documentation/devicetree/bindings/sound/da7218.txt
@@ -73,7 +73,7 @@ Example:
 		compatible = "dlg,da7218";
 		reg = <0x1a>;
 		interrupt-parent = <&gpio6>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 		wakeup-source;
 
 		VDD-supply = <&reg_audio>;
diff --git a/Documentation/devicetree/bindings/sound/da7219.txt b/Documentation/devicetree/bindings/sound/da7219.txt
index cf61681826b6..5b54d2d045c3 100644
--- a/Documentation/devicetree/bindings/sound/da7219.txt
+++ b/Documentation/devicetree/bindings/sound/da7219.txt
@@ -77,7 +77,7 @@ Example:
 		reg = <0x1a>;
 
 		interrupt-parent = <&gpio6>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 
 		VDD-supply = <&reg_audio>;
 		VDDMIC-supply = <&reg_audio>;
diff --git a/Documentation/devicetree/bindings/sound/dmic.txt b/Documentation/devicetree/bindings/sound/dmic.txt
index 54c8ef6498a8..f7bf65611453 100644
--- a/Documentation/devicetree/bindings/sound/dmic.txt
+++ b/Documentation/devicetree/bindings/sound/dmic.txt
@@ -7,10 +7,12 @@ Required properties:
 
 Optional properties:
 	- dmicen-gpios: GPIO specifier for dmic to control start and stop
+	- num-channels: Number of microphones on this DAI
 
 Example node:
 
 	dmic_codec: dmic@0 {
 		compatible = "dmic-codec";
 		dmicen-gpios = <&gpio4 3 GPIO_ACTIVE_HIGH>;
+		num-channels = <1>;
 	};
diff --git a/Documentation/devicetree/bindings/sound/img,i2s-out.txt b/Documentation/devicetree/bindings/sound/img,i2s-out.txt
index 0159415b3338..6b0ee9b7e11b 100644
--- a/Documentation/devicetree/bindings/sound/img,i2s-out.txt
+++ b/Documentation/devicetree/bindings/sound/img,i2s-out.txt
@@ -35,7 +35,7 @@ Optional Properties:
 
 Example:
 
-i2s_out: i2s-out@18100A00 {
+i2s_out: i2s-out@18100a00 {
 	compatible = "img,i2s-out";
 	reg = <0x18100A00 0x200>;
 	interrupts = <GIC_SHARED 13 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/sound/img,parallel-out.txt b/Documentation/devicetree/bindings/sound/img,parallel-out.txt
index a3015d2a06e0..37a3f94cc126 100644
--- a/Documentation/devicetree/bindings/sound/img,parallel-out.txt
+++ b/Documentation/devicetree/bindings/sound/img,parallel-out.txt
@@ -29,7 +29,7 @@ Optional Properties:
 
 Example:
 
-parallel_out: parallel-out@18100C00 {
+parallel_out: parallel-out@18100c00 {
 	compatible = "img,parallel-out";
 	reg = <0x18100C00 0x100>;
 	interrupts = <GIC_SHARED 19 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/sound/img,spdif-in.txt b/Documentation/devicetree/bindings/sound/img,spdif-in.txt
index aab9a81f7e13..f7ea8c87bf34 100644
--- a/Documentation/devicetree/bindings/sound/img,spdif-in.txt
+++ b/Documentation/devicetree/bindings/sound/img,spdif-in.txt
@@ -29,7 +29,7 @@ Optional Properties:
 
 Example:
 
-spdif_in: spdif-in@18100E00 {
+spdif_in: spdif-in@18100e00 {
 	compatible = "img,spdif-in";
 	reg = <0x18100E00 0x100>;
 	interrupts = <GIC_SHARED 20 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/sound/img,spdif-out.txt b/Documentation/devicetree/bindings/sound/img,spdif-out.txt
index 470a5191e101..413ed8b01870 100644
--- a/Documentation/devicetree/bindings/sound/img,spdif-out.txt
+++ b/Documentation/devicetree/bindings/sound/img,spdif-out.txt
@@ -29,7 +29,7 @@ Optional Properties:
 
 Example:
 
-spdif_out: spdif-out@18100D00 {
+spdif_out: spdif-out@18100d00 {
 	compatible = "img,spdif-out";
 	reg = <0x18100D00 0x100>;
 	interrupts = <GIC_SHARED 21 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/sound/max98371.txt b/Documentation/devicetree/bindings/sound/max98371.txt
index 6c285235e64b..8b2b2704b574 100644
--- a/Documentation/devicetree/bindings/sound/max98371.txt
+++ b/Documentation/devicetree/bindings/sound/max98371.txt
@@ -10,7 +10,7 @@ Required properties:
 Example:
 
 &i2c {
-	max98371: max98371@0x31 {
+	max98371: max98371@31 {
 		compatible = "maxim,max98371";
 		reg = <0x31>;
 	};
diff --git a/Documentation/devicetree/bindings/sound/max98373.txt b/Documentation/devicetree/bindings/sound/max98373.txt
new file mode 100644
index 000000000000..456cb1c59353
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/max98373.txt
@@ -0,0 +1,40 @@
+Maxim Integrated MAX98373 Speaker Amplifier
+
+This device supports I2C.
+
+Required properties:
+
+ - compatible : "maxim,max98373"
+
+ - reg : the I2C address of the device.
+
+Optional properties:
+
+  - maxim,vmon-slot-no : slot number used to send voltage information
+                   or in inteleave mode this will be used as
+                   interleave slot.
+                   slot range : 0 ~ 15,  Default : 0
+
+  - maxim,imon-slot-no : slot number used to send current information
+                   slot range : 0 ~ 15,  Default : 0
+
+  - maxim,spkfb-slot-no : slot number used to send speaker feedback information
+                   slot range : 0 ~ 15,  Default : 0
+
+  - maxim,interleave-mode : For cases where a single combined channel
+		   for the I/V sense data is not sufficient, the device can also be configured
+		   to share a single data output channel on alternating frames.
+		   In this configuration, the current and voltage data will be frame interleaved
+		   on a single output channel.
+                   Boolean, define to enable the interleave mode, Default : false
+
+Example:
+
+codec: max98373@31 {
+   compatible = "maxim,max98373";
+   reg = <0x31>;
+   maxim,vmon-slot-no = <0>;
+   maxim,imon-slot-no = <1>;
+   maxim,spkfb-slot-no = <2>;
+   maxim,interleave-mode;
+};
diff --git a/Documentation/devicetree/bindings/sound/max9867.txt b/Documentation/devicetree/bindings/sound/max9867.txt
index 394cd4eb17ec..b8bd914ee697 100644
--- a/Documentation/devicetree/bindings/sound/max9867.txt
+++ b/Documentation/devicetree/bindings/sound/max9867.txt
@@ -10,7 +10,7 @@ Required properties:
 Example:
 
 &i2c {
-	max9867: max9867@0x18 {
+	max9867: max9867@18 {
 		compatible = "maxim,max9867";
 		reg = <0x18>;
 	};
diff --git a/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt b/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt
index 77a57f84bed4..6df87b97f7cb 100644
--- a/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt
+++ b/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt
@@ -2,153 +2,143 @@ Mediatek AFE PCM controller for mt2701
 
 Required properties:
 - compatible = "mediatek,mt2701-audio";
-- reg: register location and size
 - interrupts: should contain AFE and ASYS interrupts
 - interrupt-names: should be "afe" and "asys"
 - power-domains: should define the power domain
+- clocks: Must contain an entry for each entry in clock-names
+  See ../clocks/clock-bindings.txt for details
 - clock-names: should have these clock names:
 		"infra_sys_audio_clk",
 		"top_audio_mux1_sel",
 		"top_audio_mux2_sel",
-		"top_audio_mux1_div",
-		"top_audio_mux2_div",
-		"top_audio_48k_timing",
-		"top_audio_44k_timing",
-		"top_audpll_mux_sel",
-		"top_apll_sel",
-		"top_aud1_pll_98M",
-		"top_aud2_pll_90M",
-		"top_hadds2_pll_98M",
-		"top_hadds2_pll_294M",
-		"top_audpll",
-		"top_audpll_d4",
-		"top_audpll_d8",
-		"top_audpll_d16",
-		"top_audpll_d24",
-		"top_audintbus_sel",
-		"clk_26m",
-		"top_syspll1_d4",
-		"top_aud_k1_src_sel",
-		"top_aud_k2_src_sel",
-		"top_aud_k3_src_sel",
-		"top_aud_k4_src_sel",
-		"top_aud_k5_src_sel",
-		"top_aud_k6_src_sel",
-		"top_aud_k1_src_div",
-		"top_aud_k2_src_div",
-		"top_aud_k3_src_div",
-		"top_aud_k4_src_div",
-		"top_aud_k5_src_div",
-		"top_aud_k6_src_div",
-		"top_aud_i2s1_mclk",
-		"top_aud_i2s2_mclk",
-		"top_aud_i2s3_mclk",
-		"top_aud_i2s4_mclk",
-		"top_aud_i2s5_mclk",
-		"top_aud_i2s6_mclk",
-		"top_asm_m_sel",
-		"top_asm_h_sel",
-		"top_univpll2_d4",
-		"top_univpll2_d2",
-		"top_syspll_d5";
+		"top_audio_a1sys_hp",
+		"top_audio_a2sys_hp",
+		"i2s0_src_sel",
+		"i2s1_src_sel",
+		"i2s2_src_sel",
+		"i2s3_src_sel",
+		"i2s0_src_div",
+		"i2s1_src_div",
+		"i2s2_src_div",
+		"i2s3_src_div",
+		"i2s0_mclk_en",
+		"i2s1_mclk_en",
+		"i2s2_mclk_en",
+		"i2s3_mclk_en",
+		"i2so0_hop_ck",
+		"i2so1_hop_ck",
+		"i2so2_hop_ck",
+		"i2so3_hop_ck",
+		"i2si0_hop_ck",
+		"i2si1_hop_ck",
+		"i2si2_hop_ck",
+		"i2si3_hop_ck",
+		"asrc0_out_ck",
+		"asrc1_out_ck",
+		"asrc2_out_ck",
+		"asrc3_out_ck",
+		"audio_afe_pd",
+		"audio_afe_conn_pd",
+		"audio_a1sys_pd",
+		"audio_a2sys_pd",
+		"audio_mrgif_pd";
+- assigned-clocks: list of input clocks and dividers for the audio system.
+		   See ../clocks/clock-bindings.txt for details.
+- assigned-clocks-parents: parent of input clocks of assigned clocks.
+- assigned-clock-rates: list of clock frequencies of assigned clocks.
+
+Must be a subnode of MediaTek audsys device tree node.
+See ../arm/mediatek/mediatek,audsys.txt for details about the parent node.
 
 Example:
 
-	afe: mt2701-afe-pcm@11220000 {
-		compatible = "mediatek,mt2701-audio";
-		reg = <0 0x11220000 0 0x2000>,
-		      <0 0x112A0000 0 0x20000>;
-		interrupts = <GIC_SPI 104 IRQ_TYPE_LEVEL_LOW>,
-			     <GIC_SPI 132 IRQ_TYPE_LEVEL_LOW>;
-		interrupt-names	= "afe", "asys";
-		power-domains = <&scpsys MT2701_POWER_DOMAIN_IFR_MSC>;
-		clocks = <&infracfg CLK_INFRA_AUDIO>,
-			 <&topckgen CLK_TOP_AUD_MUX1_SEL>,
-			 <&topckgen CLK_TOP_AUD_MUX2_SEL>,
-			 <&topckgen CLK_TOP_AUD_MUX1_DIV>,
-			 <&topckgen CLK_TOP_AUD_MUX2_DIV>,
-			 <&topckgen CLK_TOP_AUD_48K_TIMING>,
-			 <&topckgen CLK_TOP_AUD_44K_TIMING>,
-			 <&topckgen CLK_TOP_AUDPLL_MUX_SEL>,
-			 <&topckgen CLK_TOP_APLL_SEL>,
-			 <&topckgen CLK_TOP_AUD1PLL_98M>,
-			 <&topckgen CLK_TOP_AUD2PLL_90M>,
-			 <&topckgen CLK_TOP_HADDS2PLL_98M>,
-			 <&topckgen CLK_TOP_HADDS2PLL_294M>,
-			 <&topckgen CLK_TOP_AUDPLL>,
-			 <&topckgen CLK_TOP_AUDPLL_D4>,
-			 <&topckgen CLK_TOP_AUDPLL_D8>,
-			 <&topckgen CLK_TOP_AUDPLL_D16>,
-			 <&topckgen CLK_TOP_AUDPLL_D24>,
-			 <&topckgen CLK_TOP_AUDINTBUS_SEL>,
-			 <&clk26m>,
-			 <&topckgen CLK_TOP_SYSPLL1_D4>,
-			 <&topckgen CLK_TOP_AUD_K1_SRC_SEL>,
-			 <&topckgen CLK_TOP_AUD_K2_SRC_SEL>,
-			 <&topckgen CLK_TOP_AUD_K3_SRC_SEL>,
-			 <&topckgen CLK_TOP_AUD_K4_SRC_SEL>,
-			 <&topckgen CLK_TOP_AUD_K5_SRC_SEL>,
-			 <&topckgen CLK_TOP_AUD_K6_SRC_SEL>,
-			 <&topckgen CLK_TOP_AUD_K1_SRC_DIV>,
-			 <&topckgen CLK_TOP_AUD_K2_SRC_DIV>,
-			 <&topckgen CLK_TOP_AUD_K3_SRC_DIV>,
-			 <&topckgen CLK_TOP_AUD_K4_SRC_DIV>,
-			 <&topckgen CLK_TOP_AUD_K5_SRC_DIV>,
-			 <&topckgen CLK_TOP_AUD_K6_SRC_DIV>,
-			 <&topckgen CLK_TOP_AUD_I2S1_MCLK>,
-			 <&topckgen CLK_TOP_AUD_I2S2_MCLK>,
-			 <&topckgen CLK_TOP_AUD_I2S3_MCLK>,
-			 <&topckgen CLK_TOP_AUD_I2S4_MCLK>,
-			 <&topckgen CLK_TOP_AUD_I2S5_MCLK>,
-			 <&topckgen CLK_TOP_AUD_I2S6_MCLK>,
-			 <&topckgen CLK_TOP_ASM_M_SEL>,
-			 <&topckgen CLK_TOP_ASM_H_SEL>,
-			 <&topckgen CLK_TOP_UNIVPLL2_D4>,
-			 <&topckgen CLK_TOP_UNIVPLL2_D2>,
-			 <&topckgen CLK_TOP_SYSPLL_D5>;
+	audsys: audio-subsystem@11220000 {
+		compatible = "mediatek,mt2701-audsys", "syscon", "simple-mfd";
+		...
+
+		afe: audio-controller {
+			compatible = "mediatek,mt2701-audio";
+			interrupts =  <GIC_SPI 104 IRQ_TYPE_LEVEL_LOW>,
+				      <GIC_SPI 132 IRQ_TYPE_LEVEL_LOW>;
+			interrupt-names	= "afe", "asys";
+			power-domains = <&scpsys MT2701_POWER_DOMAIN_IFR_MSC>;
+
+			clocks = <&infracfg CLK_INFRA_AUDIO>,
+				 <&topckgen CLK_TOP_AUD_MUX1_SEL>,
+				 <&topckgen CLK_TOP_AUD_MUX2_SEL>,
+				 <&topckgen CLK_TOP_AUD_48K_TIMING>,
+				 <&topckgen CLK_TOP_AUD_44K_TIMING>,
+				 <&topckgen CLK_TOP_AUD_K1_SRC_SEL>,
+				 <&topckgen CLK_TOP_AUD_K2_SRC_SEL>,
+				 <&topckgen CLK_TOP_AUD_K3_SRC_SEL>,
+				 <&topckgen CLK_TOP_AUD_K4_SRC_SEL>,
+				 <&topckgen CLK_TOP_AUD_K1_SRC_DIV>,
+				 <&topckgen CLK_TOP_AUD_K2_SRC_DIV>,
+				 <&topckgen CLK_TOP_AUD_K3_SRC_DIV>,
+				 <&topckgen CLK_TOP_AUD_K4_SRC_DIV>,
+				 <&topckgen CLK_TOP_AUD_I2S1_MCLK>,
+				 <&topckgen CLK_TOP_AUD_I2S2_MCLK>,
+				 <&topckgen CLK_TOP_AUD_I2S3_MCLK>,
+				 <&topckgen CLK_TOP_AUD_I2S4_MCLK>,
+				 <&audsys CLK_AUD_I2SO1>,
+				 <&audsys CLK_AUD_I2SO2>,
+				 <&audsys CLK_AUD_I2SO3>,
+				 <&audsys CLK_AUD_I2SO4>,
+				 <&audsys CLK_AUD_I2SIN1>,
+				 <&audsys CLK_AUD_I2SIN2>,
+				 <&audsys CLK_AUD_I2SIN3>,
+				 <&audsys CLK_AUD_I2SIN4>,
+				 <&audsys CLK_AUD_ASRCO1>,
+				 <&audsys CLK_AUD_ASRCO2>,
+				 <&audsys CLK_AUD_ASRCO3>,
+				 <&audsys CLK_AUD_ASRCO4>,
+				 <&audsys CLK_AUD_AFE>,
+				 <&audsys CLK_AUD_AFE_CONN>,
+				 <&audsys CLK_AUD_A1SYS>,
+				 <&audsys CLK_AUD_A2SYS>,
+				 <&audsys CLK_AUD_AFE_MRGIF>;
+
+			clock-names = "infra_sys_audio_clk",
+				      "top_audio_mux1_sel",
+				      "top_audio_mux2_sel",
+				      "top_audio_a1sys_hp",
+				      "top_audio_a2sys_hp",
+				      "i2s0_src_sel",
+				      "i2s1_src_sel",
+				      "i2s2_src_sel",
+				      "i2s3_src_sel",
+				      "i2s0_src_div",
+				      "i2s1_src_div",
+				      "i2s2_src_div",
+				      "i2s3_src_div",
+				      "i2s0_mclk_en",
+				      "i2s1_mclk_en",
+				      "i2s2_mclk_en",
+				      "i2s3_mclk_en",
+				      "i2so0_hop_ck",
+				      "i2so1_hop_ck",
+				      "i2so2_hop_ck",
+				      "i2so3_hop_ck",
+				      "i2si0_hop_ck",
+				      "i2si1_hop_ck",
+				      "i2si2_hop_ck",
+				      "i2si3_hop_ck",
+				      "asrc0_out_ck",
+				      "asrc1_out_ck",
+				      "asrc2_out_ck",
+				      "asrc3_out_ck",
+				      "audio_afe_pd",
+				      "audio_afe_conn_pd",
+				      "audio_a1sys_pd",
+				      "audio_a2sys_pd",
+				      "audio_mrgif_pd";
 
-		clock-names = "infra_sys_audio_clk",
-			      "top_audio_mux1_sel",
-			      "top_audio_mux2_sel",
-			      "top_audio_mux1_div",
-			      "top_audio_mux2_div",
-			      "top_audio_48k_timing",
-			      "top_audio_44k_timing",
-			      "top_audpll_mux_sel",
-			      "top_apll_sel",
-			      "top_aud1_pll_98M",
-			      "top_aud2_pll_90M",
-			      "top_hadds2_pll_98M",
-			      "top_hadds2_pll_294M",
-			      "top_audpll",
-			      "top_audpll_d4",
-			      "top_audpll_d8",
-			      "top_audpll_d16",
-			      "top_audpll_d24",
-			      "top_audintbus_sel",
-			      "clk_26m",
-			      "top_syspll1_d4",
-			      "top_aud_k1_src_sel",
-			      "top_aud_k2_src_sel",
-			      "top_aud_k3_src_sel",
-			      "top_aud_k4_src_sel",
-			      "top_aud_k5_src_sel",
-			      "top_aud_k6_src_sel",
-			      "top_aud_k1_src_div",
-			      "top_aud_k2_src_div",
-			      "top_aud_k3_src_div",
-			      "top_aud_k4_src_div",
-			      "top_aud_k5_src_div",
-			      "top_aud_k6_src_div",
-			      "top_aud_i2s1_mclk",
-			      "top_aud_i2s2_mclk",
-			      "top_aud_i2s3_mclk",
-			      "top_aud_i2s4_mclk",
-			      "top_aud_i2s5_mclk",
-			      "top_aud_i2s6_mclk",
-			      "top_asm_m_sel",
-			      "top_asm_h_sel",
-			      "top_univpll2_d4",
-			      "top_univpll2_d2",
-			      "top_syspll_d5";
+			assigned-clocks = <&topckgen CLK_TOP_AUD_MUX1_SEL>,
+					  <&topckgen CLK_TOP_AUD_MUX2_SEL>,
+					  <&topckgen CLK_TOP_AUD_MUX1_DIV>,
+					  <&topckgen CLK_TOP_AUD_MUX2_DIV>;
+			assigned-clock-parents = <&topckgen CLK_TOP_AUD1PLL_98M>,
+						 <&topckgen CLK_TOP_AUD2PLL_90M>;
+			assigned-clock-rates = <0>, <0>, <49152000>, <45158400>;
+		};
 	};
diff --git a/Documentation/devicetree/bindings/sound/mxs-audio-sgtl5000.txt b/Documentation/devicetree/bindings/sound/mxs-audio-sgtl5000.txt
index 601c518eddaa..4eb980bd0287 100644
--- a/Documentation/devicetree/bindings/sound/mxs-audio-sgtl5000.txt
+++ b/Documentation/devicetree/bindings/sound/mxs-audio-sgtl5000.txt
@@ -1,10 +1,31 @@
 * Freescale MXS audio complex with SGTL5000 codec
 
 Required properties:
-- compatible: "fsl,mxs-audio-sgtl5000"
-- model: The user-visible name of this sound complex
-- saif-controllers: The phandle list of the MXS SAIF controller
-- audio-codec: The phandle of the SGTL5000 audio codec
+- compatible		: "fsl,mxs-audio-sgtl5000"
+- model			: The user-visible name of this sound complex
+- saif-controllers	: The phandle list of the MXS SAIF controller
+- audio-codec		: The phandle of the SGTL5000 audio codec
+- audio-routing		: A list of the connections between audio components.
+			  Each entry is a pair of strings, the first being the
+			  connection's sink, the second being the connection's
+			  source. Valid names could be power supplies, SGTL5000
+			  pins, and the jacks on the board:
+
+			  Power supplies:
+			   * Mic Bias
+
+			  SGTL5000 pins:
+			   * MIC_IN
+			   * LINE_IN
+			   * HP_OUT
+			   * LINE_OUT
+
+			  Board connectors:
+			   * Mic Jack
+			   * Line In Jack
+			   * Headphone Jack
+			   * Line Out Jack
+			   * Ext Spk
 
 Example:
 
@@ -14,4 +35,8 @@ sound {
 	model = "imx28-evk-sgtl5000";
 	saif-controllers = <&saif0 &saif1>;
 	audio-codec = <&sgtl5000>;
+	audio-routing =
+		"MIC_IN", "Mic Jack",
+		"Mic Jack", "Mic Bias",
+		"Headphone Jack", "HP_OUT";
 };
diff --git a/Documentation/devicetree/bindings/sound/nau8825.txt b/Documentation/devicetree/bindings/sound/nau8825.txt
index 2f5e973285a6..d16d96839bcb 100644
--- a/Documentation/devicetree/bindings/sound/nau8825.txt
+++ b/Documentation/devicetree/bindings/sound/nau8825.txt
@@ -69,7 +69,7 @@ Optional properties:
   - nuvoton,jack-insert-debounce: number from 0 to 7 that sets debounce time to 2^(n+2) ms
   - nuvoton,jack-eject-debounce: number from 0 to 7 that sets debounce time to 2^(n+2) ms
 
-  - nuvoton,crosstalk-bypass: make crosstalk function bypass if set.
+  - nuvoton,crosstalk-enable: make crosstalk function enable if set.
 
   - clocks: list of phandle and clock specifier pairs according to common clock bindings for the
       clocks described in clock-names
@@ -98,7 +98,7 @@ Example:
       nuvoton,short-key-debounce = <2>;
       nuvoton,jack-insert-debounce = <7>;
       nuvoton,jack-eject-debounce = <7>;
-      nuvoton,crosstalk-bypass;
+      nuvoton,crosstalk-enable;
 
       clock-names = "mclk";
       clocks = <&tegra_car TEGRA210_CLK_CLK_OUT_2>;
diff --git a/Documentation/devicetree/bindings/sound/pcm186x.txt b/Documentation/devicetree/bindings/sound/pcm186x.txt
new file mode 100644
index 000000000000..1087f4855980
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/pcm186x.txt
@@ -0,0 +1,42 @@
+Texas Instruments PCM186x Universal Audio ADC
+
+These devices support both I2C and SPI (configured with pin strapping
+on the board).
+
+Required properties:
+
+ - compatible : "ti,pcm1862",
+                "ti,pcm1863",
+                "ti,pcm1864",
+                "ti,pcm1865"
+
+ - reg : The I2C address of the device for I2C, the chip select
+         number for SPI.
+
+ - avdd-supply: Analog core power supply (3.3v)
+ - dvdd-supply: Digital core power supply
+ - iovdd-supply: Digital IO power supply
+        See regulator/regulator.txt for more information
+
+CODEC input pins:
+ * VINL1
+ * VINR1
+ * VINL2
+ * VINR2
+ * VINL3
+ * VINR3
+ * VINL4
+ * VINR4
+
+The pins can be used in referring sound node's audio-routing property.
+
+Example:
+
+	pcm186x: audio-codec@4a {
+		compatible = "ti,pcm1865";
+		reg = <0x4a>;
+
+		avdd-supply = <&reg_3v3_analog>;
+		dvdd-supply = <&reg_3v3>;
+		iovdd-supply = <&reg_1v8>;
+	};
diff --git a/Documentation/devicetree/bindings/sound/renesas,fsi.txt b/Documentation/devicetree/bindings/sound/renesas,fsi.txt
index 0d0ab51105b0..0cf0f819b823 100644
--- a/Documentation/devicetree/bindings/sound/renesas,fsi.txt
+++ b/Documentation/devicetree/bindings/sound/renesas,fsi.txt
@@ -20,7 +20,7 @@ Required properties:
 
 Example:
 
-sh_fsi2: sh_fsi2@0xec230000 {
+sh_fsi2: sh_fsi2@ec230000 {
 	compatible = "renesas,sh_fsi2";
 	reg = <0xec230000 0x400>;
 	interrupts = <0 146 0x4>;
diff --git a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
index 085bec364caf..5bed9a595772 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
+++ b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
@@ -4,7 +4,7 @@ Renesas R-Car sound
 * Modules
 =============================================
 
-Renesas R-Car sound is constructed from below modules
+Renesas R-Car and RZ/G sound is constructed from below modules
 (for Gen2 or later)
 
  SCU		: Sampling Rate Converter Unit
@@ -197,12 +197,17 @@ Ex)
 	[MEM] -> [SRC2] -> [CTU03] -+
 
 	sound {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
 		compatible = "simple-scu-audio-card";
 		...
-		simple-audio-card,cpu-0 {
+		simple-audio-card,cpu@0 {
+			reg = <0>;
 			sound-dai = <&rcar_sound 0>;
 		};
-		simple-audio-card,cpu-1 {
+		simple-audio-card,cpu@1 {
+			reg = <1>;
 			sound-dai = <&rcar_sound 1>;
 		};
 		simple-audio-card,codec {
@@ -334,9 +339,11 @@ Required properties:
 
 - compatible			: "renesas,rcar_sound-<soctype>", fallbacks
 				  "renesas,rcar_sound-gen1" if generation1, and
-				  "renesas,rcar_sound-gen2" if generation2
+				  "renesas,rcar_sound-gen2" if generation2 (or RZ/G1)
 				  "renesas,rcar_sound-gen3" if generation3
 				  Examples with soctypes are:
+				    - "renesas,rcar_sound-r8a7743" (RZ/G1M)
+				    - "renesas,rcar_sound-r8a7745" (RZ/G1E)
 				    - "renesas,rcar_sound-r8a7778" (R-Car M1A)
 				    - "renesas,rcar_sound-r8a7779" (R-Car H1)
 				    - "renesas,rcar_sound-r8a7790" (R-Car H2)
diff --git a/Documentation/devicetree/bindings/sound/rockchip-spdif.txt b/Documentation/devicetree/bindings/sound/rockchip-spdif.txt
index 0a1dc4e1815c..ec20c1271e92 100644
--- a/Documentation/devicetree/bindings/sound/rockchip-spdif.txt
+++ b/Documentation/devicetree/bindings/sound/rockchip-spdif.txt
@@ -33,7 +33,7 @@ Required properties on RK3288:
 
 Example for the rk3188 SPDIF controller:
 
-spdif: spdif@0x1011e000 {
+spdif: spdif@1011e000 {
 	compatible = "rockchip,rk3188-spdif", "rockchip,rk3066-spdif";
 	reg = <0x1011e000 0x2000>;
 	interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/sound/simple-card.txt b/Documentation/devicetree/bindings/sound/simple-card.txt
index 166f2290233b..17c13e74667d 100644
--- a/Documentation/devicetree/bindings/sound/simple-card.txt
+++ b/Documentation/devicetree/bindings/sound/simple-card.txt
@@ -140,6 +140,7 @@ sound {
 	simple-audio-card,name = "Cubox Audio";
 
 	simple-audio-card,dai-link@0 {		/* I2S - HDMI */
+		reg = <0>;
 		format = "i2s";
 		cpu {
 			sound-dai = <&audio1 0>;
@@ -150,6 +151,7 @@ sound {
 	};
 
 	simple-audio-card,dai-link@1 {		/* S/PDIF - HDMI */
+		reg = <1>;
 		cpu {
 			sound-dai = <&audio1 1>;
 		};
@@ -159,6 +161,7 @@ sound {
 	};
 
 	simple-audio-card,dai-link@2 {		/* S/PDIF - S/PDIF */
+		reg = <2>;
 		cpu {
 			sound-dai = <&audio1 1>;
 		};
diff --git a/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
index 40068ec0e9a5..4d51f3f5ea98 100644
--- a/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
+++ b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
@@ -51,7 +51,7 @@ Optional properties:
 
 Example:
 
-	sti_uni_player1: sti-uni-player@0x8D81000 {
+	sti_uni_player1: sti-uni-player@8d81000 {
 		compatible = "st,stih407-uni-player-hdmi";
 		#sound-dai-cells = <0>;
 		st,syscfg = <&syscfg_core>;
@@ -63,7 +63,7 @@ Example:
 		st,tdm-mode = <1>;
 	};
 
-	sti_uni_player2: sti-uni-player@0x8D82000 {
+	sti_uni_player2: sti-uni-player@8d82000 {
 		compatible = "st,stih407-uni-player-pcm-out";
 		#sound-dai-cells = <0>;
 		st,syscfg = <&syscfg_core>;
@@ -74,7 +74,7 @@ Example:
 		dma-names = "tx";
 	};
 
-	sti_uni_player3: sti-uni-player@0x8D85000 {
+	sti_uni_player3: sti-uni-player@8d85000 {
 		compatible = "st,stih407-uni-player-spdif";
 		#sound-dai-cells = <0>;
 		st,syscfg = <&syscfg_core>;
@@ -85,7 +85,7 @@ Example:
 		dma-names = "tx";
 	};
 
-	sti_uni_reader1: sti-uni-reader@0x8D84000 {
+	sti_uni_reader1: sti-uni-reader@8d84000 {
 		compatible = "st,stih407-uni-reader-hdmi";
 		#sound-dai-cells = <0>;
 		st,syscfg = <&syscfg_core>;
diff --git a/Documentation/devicetree/bindings/sound/st,stm32-adfsdm.txt b/Documentation/devicetree/bindings/sound/st,stm32-adfsdm.txt
new file mode 100644
index 000000000000..864f5b00b031
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/st,stm32-adfsdm.txt
@@ -0,0 +1,63 @@
+STMicroelectronics Audio Digital Filter Sigma Delta modulators(DFSDM)
+
+The DFSDM allows PDM microphones capture through SPI interface. The Audio
+interface is seems as a sub block of the DFSDM device.
+For details on DFSDM bindings refer to ../iio/adc/st,stm32-dfsdm-adc.txt
+
+Required properties:
+  - compatible: "st,stm32h7-dfsdm-dai".
+
+  - #sound-dai-cells : Must be equal to 0
+
+  - io-channels : phandle to iio dfsdm instance node.
+
+Example of a sound card using audio DFSDM node.
+
+	sound_card {
+		compatible = "audio-graph-card";
+
+		dais = <&cpu_port>;
+	};
+
+	dfsdm: dfsdm@40017000 {
+		compatible = "st,stm32h7-dfsdm";
+		reg = <0x40017000 0x400>;
+		clocks = <&rcc DFSDM1_CK>;
+		clock-names = "dfsdm";
+		#interrupt-cells = <1>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		dfsdm_adc0: filter@0 {
+			compatible = "st,stm32-dfsdm-dmic";
+			reg = <0>;
+			interrupts = <110>;
+			dmas = <&dmamux1 101 0x400 0x00>;
+			dma-names = "rx";
+			st,adc-channels = <1>;
+			st,adc-channel-names = "dmic0";
+			st,adc-channel-types = "SPI_R";
+			st,adc-channel-clk-src = "CLKOUT";
+			st,filter-order = <5>;
+
+			dfsdm_dai0: dfsdm-dai {
+				compatible = "st,stm32h7-dfsdm-dai";
+				#sound-dai-cells = <0>;
+				io-channels = <&dfsdm_adc0 0>;
+				cpu_port: port {
+				dfsdm_endpoint: endpoint {
+					remote-endpoint = <&dmic0_endpoint>;
+				};
+			};
+		};
+	};
+
+	dmic0: dmic@0 {
+		compatible = "dmic-codec";
+		#sound-dai-cells = <0>;
+		port {
+			dmic0_endpoint: endpoint {
+				remote-endpoint = <&dfsdm_endpoint>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/sound/st,stm32-sai.txt b/Documentation/devicetree/bindings/sound/st,stm32-sai.txt
index 1f9cd7095337..b1acc1a256ba 100644
--- a/Documentation/devicetree/bindings/sound/st,stm32-sai.txt
+++ b/Documentation/devicetree/bindings/sound/st,stm32-sai.txt
@@ -20,11 +20,6 @@ Required properties:
 
 Optional properties:
   - resets: Reference to a reset controller asserting the SAI
-  - st,sync: specify synchronization mode.
-	By default SAI sub-block is in asynchronous mode.
-	This property sets SAI sub-block as slave of another SAI sub-block.
-	Must contain the phandle and index of the sai sub-block providing
-	the synchronization.
 
 SAI subnodes:
 Two subnodes corresponding to SAI sub-block instances A et B can be defined.
@@ -44,6 +39,13 @@ SAI subnodes required properties:
   - pinctrl-names: should contain only value "default"
   - pinctrl-0: see Documentation/devicetree/bindings/pinctrl/pinctrl-stm32.txt
 
+SAI subnodes Optional properties:
+  - st,sync: specify synchronization mode.
+	By default SAI sub-block is in asynchronous mode.
+	This property sets SAI sub-block as slave of another SAI sub-block.
+	Must contain the phandle and index of the sai sub-block providing
+	the synchronization.
+
 The device node should contain one 'port' child node with one child 'endpoint'
 node, according to the bindings defined in Documentation/devicetree/bindings/
 graph.txt.
diff --git a/Documentation/devicetree/bindings/sound/sun4i-i2s.txt b/Documentation/devicetree/bindings/sound/sun4i-i2s.txt
index 05d7135a8d2f..b9d50d6cdef3 100644
--- a/Documentation/devicetree/bindings/sound/sun4i-i2s.txt
+++ b/Documentation/devicetree/bindings/sound/sun4i-i2s.txt
@@ -8,6 +8,7 @@ Required properties:
 - compatible: should be one of the following:
    - "allwinner,sun4i-a10-i2s"
    - "allwinner,sun6i-a31-i2s"
+   - "allwinner,sun8i-a83t-i2s"
    - "allwinner,sun8i-h3-i2s"
 - reg: physical base address of the controller and length of memory mapped
   region.
@@ -23,6 +24,7 @@ Required properties:
 
 Required properties for the following compatibles:
 	- "allwinner,sun6i-a31-i2s"
+	- "allwinner,sun8i-a83t-i2s"
 	- "allwinner,sun8i-h3-i2s"
 - resets: phandle to the reset line for this codec
 
diff --git a/Documentation/devicetree/bindings/sound/tas5720.txt b/Documentation/devicetree/bindings/sound/tas5720.txt
index 40d94f82beb3..7481653fe8e3 100644
--- a/Documentation/devicetree/bindings/sound/tas5720.txt
+++ b/Documentation/devicetree/bindings/sound/tas5720.txt
@@ -6,10 +6,12 @@ audio playback. For more product information please see the links below:
 
 http://www.ti.com/product/TAS5720L
 http://www.ti.com/product/TAS5720M
+http://www.ti.com/product/TAS5722L
 
 Required properties:
 
-- compatible : "ti,tas5720"
+- compatible : "ti,tas5720",
+               "ti,tas5722"
 - reg : I2C slave address
 - dvdd-supply : phandle to a 3.3-V supply for the digital circuitry
 - pvdd-supply : phandle to a supply used for the Class-D amp and the analog
diff --git a/Documentation/devicetree/bindings/sound/tfa9879.txt b/Documentation/devicetree/bindings/sound/tfa9879.txt
index 23ba522d9e2b..1620e6848436 100644
--- a/Documentation/devicetree/bindings/sound/tfa9879.txt
+++ b/Documentation/devicetree/bindings/sound/tfa9879.txt
@@ -6,18 +6,18 @@ Required properties:
 
 - reg : the I2C address of the device
 
+- #sound-dai-cells : must be 0.
+
 Example:
 
 &i2c1 {
-	clock-frequency = <100000>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_i2c1>;
-	status = "okay";
 
-	codec: tfa9879@6c {
+	amp: amp@6c {
 		#sound-dai-cells = <0>;
 		compatible = "nxp,tfa9879";
 		reg = <0x6c>;
-        };
+	};
 };
 
diff --git a/Documentation/devicetree/bindings/sound/ti,tas6424.txt b/Documentation/devicetree/bindings/sound/ti,tas6424.txt
new file mode 100644
index 000000000000..1c4ada0eef4e
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/ti,tas6424.txt
@@ -0,0 +1,20 @@
+Texas Instruments TAS6424 Quad-Channel Audio amplifier
+
+The TAS6424 serial control bus communicates through I2C protocols.
+
+Required properties:
+	- compatible: "ti,tas6424" - TAS6424
+	- reg: I2C slave address
+	- sound-dai-cells: must be equal to 0
+
+Example:
+
+tas6424: tas6424@6a {
+	compatible = "ti,tas6424";
+	reg = <0x6a>;
+
+	#sound-dai-cells = <0>;
+};
+
+For more product information please see the link below:
+http://www.ti.com/product/TAS6424-Q1
diff --git a/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt b/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt
index 6fbba562eaa7..5b3c33bb99e5 100644
--- a/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt
+++ b/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt
@@ -22,7 +22,7 @@ Required properties:
 
 Optional properties:
 
-- gpio-reset - gpio pin number used for codec reset
+- reset-gpios - GPIO specification for the active low RESET input.
 - ai31xx-micbias-vg - MicBias Voltage setting
         1 or MICBIAS_2_0V - MICBIAS output is powered to 2.0V
         2 or MICBIAS_2_5V - MICBIAS output is powered to 2.5V
@@ -30,6 +30,10 @@ Optional properties:
 	If this node is not mentioned or if the value is unknown, then
 	micbias	is set to 2.0V.
 
+Deprecated properties:
+
+- gpio-reset - gpio pin number used for codec reset
+
 CODEC output pins:
   * HPL
   * HPR
@@ -48,6 +52,7 @@ CODEC input pins:
 The pins can be used in referring sound node's audio-routing property.
 
 Example:
+#include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/sound/tlv320aic31xx-micbias.h>
 
 tlv320aic31xx: tlv320aic31xx@18 {
@@ -56,6 +61,8 @@ tlv320aic31xx: tlv320aic31xx@18 {
 
 	ai31xx-micbias-vg = <MICBIAS_OFF>;
 
+	reset-gpios = <&gpio1 17 GPIO_ACTIVE_LOW>;
+
 	HPVDD-supply = <&regulator>;
 	SPRVDD-supply = <&regulator>;
 	SPLVDD-supply = <&regulator>;
diff --git a/Documentation/devicetree/bindings/sound/tlv320aic3x.txt b/Documentation/devicetree/bindings/sound/tlv320aic3x.txt
index ba5b45c483f5..9796c4639262 100644
--- a/Documentation/devicetree/bindings/sound/tlv320aic3x.txt
+++ b/Documentation/devicetree/bindings/sound/tlv320aic3x.txt
@@ -17,7 +17,7 @@ Required properties:
 
 Optional properties:
 
-- gpio-reset - gpio pin number used for codec reset
+- reset-gpios - GPIO specification for the active low RESET input.
 - ai3x-gpio-func - <array of 2 int> - AIC3X_GPIO1 & AIC3X_GPIO2 Functionality
 				    - Not supported on tlv320aic3104
 - ai3x-micbias-vg - MicBias Voltage required.
@@ -34,6 +34,10 @@ Optional properties:
 - AVDD-supply, IOVDD-supply, DRVDD-supply, DVDD-supply : power supplies for the
   device as covered in Documentation/devicetree/bindings/regulator/regulator.txt
 
+Deprecated properties:
+
+- gpio-reset - gpio pin number used for codec reset
+
 CODEC output pins:
   * LLOUT
   * RLOUT
@@ -61,10 +65,14 @@ The pins can be used in referring sound node's audio-routing property.
 
 Example:
 
+#include <dt-bindings/gpio/gpio.h>
+
 tlv320aic3x: tlv320aic3x@1b {
 	compatible = "ti,tlv320aic3x";
 	reg = <0x1b>;
 
+	reset-gpios = <&gpio1 17 GPIO_ACTIVE_LOW>;
+
 	AVDD-supply = <&regulator>;
 	IOVDD-supply = <&regulator>;
 	DRVDD-supply = <&regulator>;
diff --git a/Documentation/devicetree/bindings/sound/tscs42xx.txt b/Documentation/devicetree/bindings/sound/tscs42xx.txt
new file mode 100644
index 000000000000..2ac2f0996697
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/tscs42xx.txt
@@ -0,0 +1,16 @@
+TSCS42XX Audio CODEC
+
+Required Properties:
+
+	- compatible :	"tempo,tscs42A1" for analog mic
+			"tempo,tscs42A2" for digital mic
+
+	- reg : 	<0x71> for analog mic
+			<0x69> for digital mic
+
+Example:
+
+wookie: codec@69 {
+	compatible = "tempo,tscs42A2";
+	reg = <0x69>;
+};
diff --git a/Documentation/devicetree/bindings/sound/uniphier,evea.txt b/Documentation/devicetree/bindings/sound/uniphier,evea.txt
new file mode 100644
index 000000000000..3f31b235f18b
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/uniphier,evea.txt
@@ -0,0 +1,26 @@
+Socionext EVEA - UniPhier SoC internal codec driver
+
+Required properties:
+- compatible      : should be "socionext,uniphier-evea".
+- reg             : offset and length of the register set for the device.
+- clock-names     : should include following entries:
+                    "evea", "exiv"
+- clocks          : a list of phandle, should contain an entry for each
+                    entries in clock-names.
+- reset-names     : should include following entries:
+                    "evea", "exiv", "adamv"
+- resets          : a list of phandle, should contain reset entries of
+                    reset-names.
+- #sound-dai-cells: should be 1.
+
+Example:
+
+	codec {
+		compatible = "socionext,uniphier-evea";
+		reg = <0x57900000 0x1000>;
+		clock-names = "evea", "exiv";
+		clocks = <&sys_clk 41>, <&sys_clk 42>;
+		reset-names = "evea", "exiv", "adamv";
+		resets = <&sys_rst 41>, <&sys_rst 42>, <&adamv_rst 0>;
+		#sound-dai-cells = <1>;
+	};
diff --git a/Documentation/devicetree/bindings/spi/efm32-spi.txt b/Documentation/devicetree/bindings/spi/efm32-spi.txt
index 2c1e6a43930b..e0fa61a1be0c 100644
--- a/Documentation/devicetree/bindings/spi/efm32-spi.txt
+++ b/Documentation/devicetree/bindings/spi/efm32-spi.txt
@@ -19,7 +19,7 @@ Recommended properties :
 
 Example:
 
-spi1: spi@0x4000c400 { /* USART1 */
+spi1: spi@4000c400 { /* USART1 */
 	#address-cells = <1>;
 	#size-cells = <0>;
 	compatible = "energymicro,efm32-spi";
diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt
index 5bf13960f7f4..e3c48b20b1a6 100644
--- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt
+++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt
@@ -12,24 +12,30 @@ Required properties:
   - "fsl,imx53-ecspi" for SPI compatible with the one integrated on i.MX53 and later Soc
 - reg : Offset and length of the register set for the device
 - interrupts : Should contain CSPI/eCSPI interrupt
-- cs-gpios : Specifies the gpio pins to be used for chipselects.
 - clocks : Clock specifiers for both ipg and per clocks.
 - clock-names : Clock names should include both "ipg" and "per"
 See the clock consumer binding,
 	Documentation/devicetree/bindings/clock/clock-bindings.txt
-- dmas: DMA specifiers for tx and rx dma. See the DMA client binding,
-		Documentation/devicetree/bindings/dma/dma.txt
-- dma-names: DMA request names should include "tx" and "rx" if present.
 
-Obsolete properties:
-- fsl,spi-num-chipselects : Contains the number of the chipselect
+Recommended properties:
+- cs-gpios : GPIOs to use as chip selects, see spi-bus.txt.  While the native chip
+select lines can be used, they appear to always generate a pulse between each
+word of a transfer.  Most use cases will require GPIO based chip selects to
+generate a valid transaction.
 
 Optional properties:
+- num-cs :  Number of total chip selects, see spi-bus.txt.
+- dmas: DMA specifiers for tx and rx dma. See the DMA client binding,
+Documentation/devicetree/bindings/dma/dma.txt.
+- dma-names: DMA request names, if present, should include "tx" and "rx".
 - fsl,spi-rdy-drctl: Integer, representing the value of DRCTL, the register
 controlling the SPI_READY handling. Note that to enable the DRCTL consideration,
 the SPI_READY mode-flag needs to be set too.
 Valid values are: 0 (disabled), 1 (edge-triggered burst) and 2 (level-triggered burst).
 
+Obsolete properties:
+- fsl,spi-num-chipselects : Contains the number of the chipselect
+
 Example:
 
 ecspi@70010000 {
diff --git a/Documentation/devicetree/bindings/spi/sh-msiof.txt b/Documentation/devicetree/bindings/spi/sh-msiof.txt
index bdd83959019c..80710f0f0448 100644
--- a/Documentation/devicetree/bindings/spi/sh-msiof.txt
+++ b/Documentation/devicetree/bindings/spi/sh-msiof.txt
@@ -36,7 +36,21 @@ Required properties:
 
 Optional properties:
 - clocks               : Must contain a reference to the functional clock.
-- num-cs               : Total number of chip-selects (default is 1)
+- num-cs               : Total number of chip selects (default is 1).
+			 Up to 3 native chip selects are supported:
+			   0: MSIOF_SYNC
+			   1: MSIOF_SS1
+			   2: MSIOF_SS2
+			 Hardware limitations related to chip selects:
+			   - Native chip selects are always deasserted in
+			     between transfers that are part of the same
+			     message.  Use cs-gpios to work around this.
+			   - All slaves using native chip selects must use the
+			     same spi-cs-high configuration.  Use cs-gpios to
+			     work around this.
+			   - When using GPIO chip selects, at least one native
+			     chip select must be left unused, as it will be
+			     driven anyway.
 - dmas                 : Must contain a list of two references to DMA
 			 specifiers, one for transmission, and one for
 			 reception.
diff --git a/Documentation/devicetree/bindings/spi/spi-davinci.txt b/Documentation/devicetree/bindings/spi/spi-davinci.txt
index 1925277bfc1e..9f5b4c7c0c08 100644
--- a/Documentation/devicetree/bindings/spi/spi-davinci.txt
+++ b/Documentation/devicetree/bindings/spi/spi-davinci.txt
@@ -68,7 +68,7 @@ SPI_SOMI/SIMO+-----------------+                           +-----------
 Example of a NOR flash slave device (n25q032) connected to DaVinci
 SPI controller device over the SPI bus.
 
-spi0:spi@20BF0000 {
+spi0:spi@20bf0000 {
 	#address-cells			= <1>;
 	#size-cells			= <0>;
 	compatible			= "ti,dm6446-spi";
diff --git a/Documentation/devicetree/bindings/spi/spi-lantiq-ssc.txt b/Documentation/devicetree/bindings/spi/spi-lantiq-ssc.txt
index 6069b95a883d..ce3230c8e28d 100644
--- a/Documentation/devicetree/bindings/spi/spi-lantiq-ssc.txt
+++ b/Documentation/devicetree/bindings/spi/spi-lantiq-ssc.txt
@@ -16,7 +16,7 @@ Optional properties:
 Example:
 
 
-spi: spi@E100800 {
+spi: spi@e100800 {
 	compatible = "lantiq,xrx200-spi", "lantiq,xrx100-spi";
 	reg = <0xE100800 0x100>;
 	interrupt-parent = <&icu0>;
diff --git a/Documentation/devicetree/bindings/spi/spi-meson.txt b/Documentation/devicetree/bindings/spi/spi-meson.txt
index 825c39cae74a..b7f5e86fed22 100644
--- a/Documentation/devicetree/bindings/spi/spi-meson.txt
+++ b/Documentation/devicetree/bindings/spi/spi-meson.txt
@@ -27,7 +27,9 @@ The Meson SPICC is generic SPI controller for general purpose Full-Duplex
 communications with dedicated 16 words RX/TX PIO FIFOs.
 
 Required properties:
- - compatible: should be "amlogic,meson-gx-spicc" on Amlogic GX SoCs.
+ - compatible: should be:
+	"amlogic,meson-gx-spicc" on Amlogic GX and compatible SoCs.
+	"amlogic,meson-axg-spicc" on Amlogic AXG and compatible SoCs
  - reg: physical base address and length of the controller registers
  - interrupts: The interrupt specifier
  - clock-names: Must contain "core"
diff --git a/Documentation/devicetree/bindings/spi/spi-orion.txt b/Documentation/devicetree/bindings/spi/spi-orion.txt
index df8ec31f2f07..8434a65fc12a 100644
--- a/Documentation/devicetree/bindings/spi/spi-orion.txt
+++ b/Documentation/devicetree/bindings/spi/spi-orion.txt
@@ -18,8 +18,17 @@ Required properties:
 	The eight register sets following the control registers refer to
 	chip-select lines 0 through 7 respectively.
 - cell-index : Which of multiple SPI controllers is this.
+- clocks : pointers to the reference clocks for this device, the first
+	   one is the one used for the clock on the spi bus, the
+	   second one is optional and is the clock used for the
+	   functional part of the controller
+
 Optional properties:
 - interrupts : Is currently not used.
+- clock-names : names of used clocks, mandatory if the second clock is
+		used, the name must be "core", and "axi" (the latter
+		is only for Armada 7K/8K).
+
 
 Example:
        spi@10600 {
diff --git a/Documentation/devicetree/bindings/spi/spi-xilinx.txt b/Documentation/devicetree/bindings/spi/spi-xilinx.txt
index c7b7856bd528..7bf61efc66c8 100644
--- a/Documentation/devicetree/bindings/spi/spi-xilinx.txt
+++ b/Documentation/devicetree/bindings/spi/spi-xilinx.txt
@@ -2,7 +2,7 @@ Xilinx SPI controller Device Tree Bindings
 -------------------------------------------------
 
 Required properties:
-- compatible		: Should be "xlnx,xps-spi-2.00.a" or "xlnx,xps-spi-2.00.b"
+- compatible		: Should be "xlnx,xps-spi-2.00.a", "xlnx,xps-spi-2.00.b" or "xlnx,axi-quad-spi-1.00.a"
 - reg			: Physical base address and size of SPI registers map.
 - interrupts		: Property with a value describing the interrupt
 			  number.
diff --git a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
index 9b4c7b017495..1b596fd38dc4 100644
--- a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
@@ -70,7 +70,7 @@ Following properties are mandatory (depending on SoC):
 
 Example 1):
 
-	tmu@100C0000 {
+	tmu@100c0000 {
 		compatible = "samsung,exynos4412-tmu";
 		interrupt-parent = <&combiner>;
 		reg = <0x100C0000 0x100>;
diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt
index 88b6ea1ad290..1719d47a5e2f 100644
--- a/Documentation/devicetree/bindings/thermal/thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/thermal.txt
@@ -239,7 +239,7 @@ cpus {
 	 * A simple fan controller which supports 10 speeds of operation
 	 * (represented as 0-9).
 	 */
-	fan0: fan@0x48 {
+	fan0: fan@48 {
 		...
 		cooling-min-level = <0>;
 		cooling-max-level = <9>;
@@ -252,7 +252,7 @@ ocp {
 	/*
 	 * A simple IC with a single bandgap temperature sensor.
 	 */
-	bandgap0: bandgap@0x0000ED00 {
+	bandgap0: bandgap@0000ed00 {
 		...
 		#thermal-sensor-cells = <0>;
 	};
@@ -330,7 +330,7 @@ ocp {
 	/*
 	 * A simple IC with several bandgap temperature sensors.
 	 */
-	bandgap0: bandgap@0x0000ED00 {
+	bandgap0: bandgap@0000ed00 {
 		...
 		#thermal-sensor-cells = <1>;
 	};
@@ -447,7 +447,7 @@ one thermal zone.
 	/*
 	 * A simple IC with a single temperature sensor.
 	 */
-	adc: sensor@0x49 {
+	adc: sensor@49 {
 		...
 		#thermal-sensor-cells = <0>;
 	};
@@ -458,7 +458,7 @@ ocp {
 	/*
 	 * A simple IC with a single bandgap temperature sensor.
 	 */
-	bandgap0: bandgap@0x0000ED00 {
+	bandgap0: bandgap@0000ed00 {
 		...
 		#thermal-sensor-cells = <0>;
 	};
@@ -516,7 +516,7 @@ with many sensors and many cooling devices.
 	/*
 	 * An IC with several temperature sensor.
 	 */
-	adc_dummy: sensor@0x50 {
+	adc_dummy: sensor@50 {
 		...
 		#thermal-sensor-cells = <1>; /* sensor internal ID */
 	};
diff --git a/Documentation/devicetree/bindings/timer/actions,owl-timer.txt b/Documentation/devicetree/bindings/timer/actions,owl-timer.txt
index e3c28da80cb2..977054f87563 100644
--- a/Documentation/devicetree/bindings/timer/actions,owl-timer.txt
+++ b/Documentation/devicetree/bindings/timer/actions,owl-timer.txt
@@ -2,6 +2,7 @@ Actions Semi Owl Timer
 
 Required properties:
 - compatible      :  "actions,s500-timer" for S500
+                     "actions,s700-timer" for S700
                      "actions,s900-timer" for S900
 - reg             :  Offset and length of the register set for the device.
 - interrupts      :  Should contain the interrupts.
diff --git a/Documentation/devicetree/bindings/timer/renesas,tpu.txt b/Documentation/devicetree/bindings/timer/renesas,tpu.txt
index f8b25897fb31..1d46f9de4feb 100644
--- a/Documentation/devicetree/bindings/timer/renesas,tpu.txt
+++ b/Documentation/devicetree/bindings/timer/renesas,tpu.txt
@@ -1,4 +1,4 @@
-* Renesas H8/300 Timer Pluse Unit
+* Renesas H8/300 Timer Pulse Unit
 
 The TPU is a 16bit timer/counter with configurable clock inputs and
 programmable compare match.
diff --git a/Documentation/devicetree/bindings/timer/samsung,exynos4210-mct.txt b/Documentation/devicetree/bindings/timer/samsung,exynos4210-mct.txt
index 167d5dab9f64..8f78640ad64c 100644
--- a/Documentation/devicetree/bindings/timer/samsung,exynos4210-mct.txt
+++ b/Documentation/devicetree/bindings/timer/samsung,exynos4210-mct.txt
@@ -51,7 +51,7 @@ Example 2: In this example, the timer interrupts are connected to two separate
 	   interrupt controllers. Hence, an interrupt-map is created to map
 	   the interrupts to the respective interrupt controllers.
 
-	mct@101C0000 {
+	mct@101c0000 {
 		compatible = "samsung,exynos4210-mct";
 		reg = <0x101C0000 0x800>;
 		interrupt-parent = <&mct_map>;
diff --git a/Documentation/devicetree/bindings/timer/spreadtrum,sprd-timer.txt b/Documentation/devicetree/bindings/timer/spreadtrum,sprd-timer.txt
new file mode 100644
index 000000000000..6d97e7d0f6e8
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/spreadtrum,sprd-timer.txt
@@ -0,0 +1,20 @@
+Spreadtrum timers
+
+The Spreadtrum SC9860 platform provides 3 general-purpose timers.
+These timers can support 32bit or 64bit counter, as well as supporting
+period mode or one-shot mode, and they are can be wakeup source
+during deep sleep.
+
+Required properties:
+- compatible: should be "sprd,sc9860-timer" for SC9860 platform.
+- reg: The register address of the timer device.
+- interrupts: Should contain the interrupt for the timer device.
+- clocks: The phandle to the source clock (usually a 32.768 KHz fixed clock).
+
+Example:
+	timer@40050000 {
+		compatible = "sprd,sc9860-timer";
+		reg = <0 0x40050000 0 0x20>;
+		interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&ext_32k>;
+	};
diff --git a/Documentation/devicetree/bindings/trivial-devices.txt b/Documentation/devicetree/bindings/trivial-devices.txt
index 5f3143f97098..2e3740f98c41 100644
--- a/Documentation/devicetree/bindings/trivial-devices.txt
+++ b/Documentation/devicetree/bindings/trivial-devices.txt
@@ -63,6 +63,7 @@ fsl,sgtl5000		SGTL5000: Ultra Low-Power Audio Codec
 gmt,g751		G751: Digital Temperature Sensor and Thermal Watchdog with Two-Wire Interface
 infineon,slb9635tt	Infineon SLB9635 (Soft-) I2C TPM (old protocol, max 100khz)
 infineon,slb9645tt	Infineon SLB9645 I2C TPM (new protocol, max 400khz)
+infineon,tlv493d-a1b6	Infineon TLV493D-A1B6 I2C 3D Magnetic Sensor
 isil,isl1208		Intersil ISL1208 Low Power RTC with Battery Backed SRAM
 isil,isl1218		Intersil ISL1218 Low Power RTC with Battery Backed SRAM
 isil,isl12022		Intersil ISL12022 Real-time Clock
@@ -151,6 +152,7 @@ national,lm85		Temperature sensor with integrated fan control
 national,lm92		±0.33°C Accurate, 12-Bit + Sign Temperature Sensor and Thermal Window Comparator with Two-Wire Interface
 nuvoton,npct501		i2c trusted platform module (TPM)
 nuvoton,npct601		i2c trusted platform module (TPM2)
+nuvoton,w83773g		Nuvoton Temperature Sensor
 nxp,pca9556		Octal SMBus and I2C registered interface
 nxp,pca9557		8-bit I2C-bus and SMBus I/O port with reset
 nxp,pcf2127		Real-time clock
diff --git a/Documentation/devicetree/bindings/ufs/ufs-qcom.txt b/Documentation/devicetree/bindings/ufs/ufs-qcom.txt
index 1f69ee1a61ea..21d9a93db2e9 100644
--- a/Documentation/devicetree/bindings/ufs/ufs-qcom.txt
+++ b/Documentation/devicetree/bindings/ufs/ufs-qcom.txt
@@ -32,7 +32,7 @@ Optional properties:
 
 Example:
 
-	ufsphy1: ufsphy@0xfc597000 {
+	ufsphy1: ufsphy@fc597000 {
 		compatible = "qcom,ufs-phy-qmp-20nm";
 		reg = <0xfc597000 0x800>;
 		reg-names = "phy_mem";
@@ -53,7 +53,7 @@ Example:
 			<&clock_gcc clk_gcc_ufs_rx_cfg_clk>;
 	};
 
-	ufshc@0xfc598000 {
+	ufshc@fc598000 {
 		...
 		phys = <&ufsphy1>;
 		phy-names = "ufsphy";
diff --git a/Documentation/devicetree/bindings/ufs/ufshcd-pltfrm.txt b/Documentation/devicetree/bindings/ufs/ufshcd-pltfrm.txt
index a99ed5565b26..c39dfef76a18 100644
--- a/Documentation/devicetree/bindings/ufs/ufshcd-pltfrm.txt
+++ b/Documentation/devicetree/bindings/ufs/ufshcd-pltfrm.txt
@@ -46,7 +46,7 @@ Note: If above properties are not defined it can be assumed that the supply
 regulators or clocks are always on.
 
 Example:
-	ufshc@0xfc598000 {
+	ufshc@fc598000 {
 		compatible = "jedec,ufs-1.1";
 		reg = <0xfc598000 0x800>;
 		interrupts = <0 28 0>;
diff --git a/Documentation/devicetree/bindings/usb/am33xx-usb.txt b/Documentation/devicetree/bindings/usb/am33xx-usb.txt
index 7a33f22c815a..7a198a30408a 100644
--- a/Documentation/devicetree/bindings/usb/am33xx-usb.txt
+++ b/Documentation/devicetree/bindings/usb/am33xx-usb.txt
@@ -95,6 +95,7 @@ usb: usb@47400000 {
 		reg = <0x47401300 0x100>;
 		reg-names = "phy";
 		ti,ctrl_mod = <&ctrl_mod>;
+		#phy-cells = <0>;
 	};
 
 	usb0: usb@47401000 {
@@ -141,6 +142,7 @@ usb: usb@47400000 {
 		reg = <0x47401b00 0x100>;
 		reg-names = "phy";
 		ti,ctrl_mod = <&ctrl_mod>;
+		#phy-cells = <0>;
 	};
 
 	usb1: usb@47401800 {
diff --git a/Documentation/devicetree/bindings/usb/dwc3.txt b/Documentation/devicetree/bindings/usb/dwc3.txt
index 52fb41046b34..44e8bab159ad 100644
--- a/Documentation/devicetree/bindings/usb/dwc3.txt
+++ b/Documentation/devicetree/bindings/usb/dwc3.txt
@@ -47,6 +47,8 @@ Optional properties:
 			from P0 to P1/P2/P3 without delay.
  - snps,dis-tx-ipgap-linecheck-quirk: when set, disable u2mac linestate check
 			during HS transmit.
+ - snps,dis_metastability_quirk: when set, disable metastability workaround.
+			CAUTION: use only if you are absolutely sure of it.
  - snps,is-utmi-l1-suspend: true when DWC3 asserts output signal
 			utmi_l1_suspend_n, false when asserts utmi_sleep_n
  - snps,hird-threshold: HIRD threshold
diff --git a/Documentation/devicetree/bindings/usb/ehci-st.txt b/Documentation/devicetree/bindings/usb/ehci-st.txt
index 9feea6c3e4d9..065c91d955ad 100644
--- a/Documentation/devicetree/bindings/usb/ehci-st.txt
+++ b/Documentation/devicetree/bindings/usb/ehci-st.txt
@@ -22,7 +22,7 @@ See: Documentation/devicetree/bindings/reset/reset.txt
 
 Example:
 
-	ehci1: usb@0xfe203e00 {
+	ehci1: usb@fe203e00 {
 		compatible = "st,st-ehci-300x";
 		reg = <0xfe203e00 0x100>;
 		interrupts = <GIC_SPI 148 IRQ_TYPE_NONE>;
diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt
index 30595964876a..88d9f4a4b280 100644
--- a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt
+++ b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt
@@ -35,10 +35,14 @@ Required properties:
  - phys : a list of phandle + phy specifier pairs
 
 Optional properties:
- - mediatek,wakeup-src : 1: ip sleep wakeup mode; 2: line state wakeup
-	mode;
- - mediatek,syscon-wakeup : phandle to syscon used to access USB wakeup
-	control register, it depends on "mediatek,wakeup-src".
+ - wakeup-source : enable USB remote wakeup;
+ - mediatek,syscon-wakeup : phandle to syscon used to access the register
+	of the USB wakeup glue layer between xHCI and SPM; it depends on
+	"wakeup-source", and has two arguments:
+	- the first one : register base address of the glue layer in syscon;
+	- the second one : hardware version of the glue layer
+		- 1 : used by mt8173 etc
+		- 2 : used by mt2712 etc
  - mediatek,u3p-dis-msk : mask to disable u3ports, bit0 for u3port0,
 	bit1 for u3port1, ... etc;
  - vbus-supply : reference to the VBUS regulator;
@@ -46,6 +50,7 @@ Optional properties:
  - pinctrl-names : a pinctrl state named "default" must be defined
  - pinctrl-0 : pin control group
 	See: Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
+ - imod-interval-ns: default interrupt moderation interval is 5000ns
 
 Example:
 usb30: usb@11270000 {
@@ -64,8 +69,9 @@ usb30: usb@11270000 {
 	vusb33-supply = <&mt6397_vusb_reg>;
 	vbus-supply = <&usb_p1_vbus>;
 	usb3-lpm-capable;
-	mediatek,syscon-wakeup = <&pericfg>;
-	mediatek,wakeup-src = <1>;
+	mediatek,syscon-wakeup = <&pericfg 0x400 1>;
+	wakeup-source;
+	imod-interval-ns = <10000>;
 };
 
 2nd: dual-role mode with xHCI driver
diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt b/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt
index b2271d8e6b50..d589a1ef96a1 100644
--- a/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt
+++ b/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt
@@ -42,9 +42,14 @@ Optional properties:
  - enable-manual-drd : supports manual dual-role switch via debugfs; usually
 	used when receptacle is TYPE-A and also wants to support dual-role
 	mode.
- - mediatek,enable-wakeup : supports ip sleep wakeup used by host mode
- - mediatek,syscon-wakeup : phandle to syscon used to access USB wakeup
-	control register, it depends on "mediatek,enable-wakeup".
+ - wakeup-source: enable USB remote wakeup of host mode.
+ - mediatek,syscon-wakeup : phandle to syscon used to access the register
+	of the USB wakeup glue layer between SSUSB and SPM; it depends on
+	"wakeup-source", and has two arguments:
+	- the first one : register base address of the glue layer in syscon;
+	- the second one : hardware version of the glue layer
+		- 1 : used by mt8173 etc
+		- 2 : used by mt2712 etc
  - mediatek,u3p-dis-msk : mask to disable u3ports, bit0 for u3port0,
 	bit1 for u3port1, ... etc;
 
@@ -71,8 +76,8 @@ ssusb: usb@11271000 {
 	vbus-supply = <&usb_p0_vbus>;
 	extcon = <&extcon_usb>;
 	dr_mode = "otg";
-	mediatek,enable-wakeup;
-	mediatek,syscon-wakeup = <&pericfg>;
+	wakeup-source;
+	mediatek,syscon-wakeup = <&pericfg 0x400 1>;
 	#address-cells = <2>;
 	#size-cells = <2>;
 	ranges;
diff --git a/Documentation/devicetree/bindings/usb/ohci-st.txt b/Documentation/devicetree/bindings/usb/ohci-st.txt
index d893ec9131c3..44c998c16f85 100644
--- a/Documentation/devicetree/bindings/usb/ohci-st.txt
+++ b/Documentation/devicetree/bindings/usb/ohci-st.txt
@@ -20,7 +20,7 @@ See: Documentation/devicetree/bindings/reset/reset.txt
 
 Example:
 
-	ohci0: usb@0xfe1ffc00 {
+	ohci0: usb@fe1ffc00 {
 		compatible = "st,st-ohci-300x";
 		reg = <0xfe1ffc00 0x100>;
 		interrupts = <GIC_SPI 149 IRQ_TYPE_NONE>;
diff --git a/Documentation/devicetree/bindings/usb/renesas_usbhs.txt b/Documentation/devicetree/bindings/usb/renesas_usbhs.txt
index 47394ab788e3..d060172f1529 100644
--- a/Documentation/devicetree/bindings/usb/renesas_usbhs.txt
+++ b/Documentation/devicetree/bindings/usb/renesas_usbhs.txt
@@ -13,8 +13,10 @@ Required properties:
 	- "renesas,usbhs-r8a7795" for r8a7795 (R-Car H3) compatible device
 	- "renesas,usbhs-r8a7796" for r8a7796 (R-Car M3-W) compatible device
 	- "renesas,usbhs-r8a77995" for r8a77995 (R-Car D3) compatible device
+	- "renesas,usbhs-r7s72100" for r7s72100 (RZ/A1) compatible device
 	- "renesas,rcar-gen2-usbhs" for R-Car Gen2 or RZ/G1 compatible devices
 	- "renesas,rcar-gen3-usbhs" for R-Car Gen3 compatible device
+	- "renesas,rza1-usbhs" for RZ/A1 compatible device
 
 	When compatible with the generic version, nodes must list the
 	SoC-specific version corresponding to the platform first followed
diff --git a/Documentation/devicetree/bindings/usb/usb-device.txt b/Documentation/devicetree/bindings/usb/usb-device.txt
index 1b27cebb47f4..036be172b1ae 100644
--- a/Documentation/devicetree/bindings/usb/usb-device.txt
+++ b/Documentation/devicetree/bindings/usb/usb-device.txt
@@ -4,8 +4,49 @@ Usually, we only use device tree for hard wired USB device.
 The reference binding doc is from:
 http://www.devicetree.org/open-firmware/bindings/usb/usb-1_0.ps
 
+Four types of device-tree nodes are defined: "host-controller nodes"
+representing USB host controllers, "device nodes" representing USB devices,
+"interface nodes" representing USB interfaces and "combined nodes"
+representing simple USB devices.
 
-Required properties:
+A combined node shall be used instead of a device node and an interface node
+for devices of class 0 or 9 (hub) with a single configuration and a single
+interface.
+
+A "hub node" is a combined node or an interface node that represents a USB
+hub.
+
+
+Required properties for device nodes:
+- compatible: "usbVID,PID", where VID is the vendor id and PID the product id.
+  The textual representation of VID and PID shall be in lower case hexadecimal
+  with leading zeroes suppressed. The other compatible strings from the above
+  standard binding could also be used, but a device adhering to this binding
+  may leave out all except for "usbVID,PID".
+- reg: the number of the USB hub port or the USB host-controller port to which
+  this device is attached. The range is 1-255.
+
+
+Required properties for device nodes with interface nodes:
+- #address-cells: shall be 2
+- #size-cells: shall be 0
+
+
+Required properties for interface nodes:
+- compatible: "usbifVID,PID.configCN.IN", where VID is the vendor id, PID is
+  the product id, CN is the configuration value and IN is the interface
+  number. The textual representation of VID, PID, CN and IN shall be in lower
+  case hexadecimal with leading zeroes suppressed. The other compatible
+  strings from the above standard binding could also be used, but a device
+  adhering to this binding may leave out all except for
+  "usbifVID,PID.configCN.IN".
+- reg: the interface number and configuration value
+
+The configuration component is not included in the textual representation of
+an interface-node unit address for configuration 1.
+
+
+Required properties for combined nodes:
 - compatible: "usbVID,PID", where VID is the vendor id and PID the product id.
   The textual representation of VID and PID shall be in lower case hexadecimal
   with leading zeroes suppressed. The other compatible strings from the above
@@ -31,8 +72,31 @@ Example:
 	#address-cells = <1>;
 	#size-cells = <0>;
 
-	hub@1 {	/* hub connected to port 1 */
+	hub@1 {		/* hub connected to port 1 */
 		compatible = "usb5e3,608";
 		reg = <1>;
 	};
+
+	device@2 {	/* device connected to port 2 */
+		compatible = "usb123,4567";
+		reg = <2>;
+	};
+
+	device@3 { 	/* device connected to port 3 */
+		compatible = "usb123,abcd";
+		reg = <3>;
+
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		interface@0 {	/* interface 0 of configuration 1 */
+			compatible = "usbif123,abcd.config1.0";
+			reg = <0 1>;
+		};
+
+		interface@0,2 {	/* interface 0 of configuration 2 */
+			compatible = "usbif123,abcd.config2.0";
+			reg = <0 2>;
+		};
+	};
 };
diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.txt b/Documentation/devicetree/bindings/usb/usb-xhci.txt
index ae6e484a8d7c..e2ea59bbca93 100644
--- a/Documentation/devicetree/bindings/usb/usb-xhci.txt
+++ b/Documentation/devicetree/bindings/usb/usb-xhci.txt
@@ -7,12 +7,14 @@ Required properties:
     - "marvell,armada3700-xhci" for Armada 37xx SoCs
     - "marvell,armada-375-xhci" for Armada 375 SoCs
     - "marvell,armada-380-xhci" for Armada 38x SoCs
+    - "renesas,xhci-r8a7743" for r8a7743 SoC
     - "renesas,xhci-r8a7790" for r8a7790 SoC
     - "renesas,xhci-r8a7791" for r8a7791 SoC
     - "renesas,xhci-r8a7793" for r8a7793 SoC
     - "renesas,xhci-r8a7795" for r8a7795 SoC
     - "renesas,xhci-r8a7796" for r8a7796 SoC
-    - "renesas,rcar-gen2-xhci" for a generic R-Car Gen2 compatible device
+    - "renesas,rcar-gen2-xhci" for a generic R-Car Gen2 or RZ/G1 compatible
+      device
     - "renesas,rcar-gen3-xhci" for a generic R-Car Gen3 compatible device
     - "xhci-platform" (deprecated)
 
@@ -29,6 +31,7 @@ Optional properties:
   - usb2-lpm-disable: indicate if we don't want to enable USB2 HW LPM
   - usb3-lpm-capable: determines if platform is USB3 LPM capable
   - quirk-broken-port-ped: set if the controller has broken port disable mechanism
+  - imod-interval-ns: default interrupt moderation interval is 5000ns
 
 Example:
 	usb@f0931000 {
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 0994bdd82cd3..b1fa64a1d4d0 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -15,6 +15,7 @@ adi	Analog Devices, Inc.
 advantech	Advantech Corporation
 aeroflexgaisler	Aeroflex Gaisler AB
 al	Annapurna Labs
+allo	Allo.com
 allwinner	Allwinner Technology Co., Ltd.
 alphascale	AlphaScale Integrated Circuits Systems, Inc.
 altr	Altera Corp.
@@ -97,6 +98,7 @@ dptechnics	DPTechnics
 dragino	Dragino Technology Co., Limited
 ea	Embedded Artists AB
 ebv	EBV Elektronik
+eckelmann	Eckelmann AG
 edt	Emerging Display Technologies
 eeti	eGalax_eMPIA Technology Inc
 elan	Elan Microelectronic Corp.
@@ -154,6 +156,7 @@ i2se	I2SE GmbH
 ibm	International Business Machines (IBM)
 idt	Integrated Device Technologies, Inc.
 ifi	Ingenieurburo Fur Ic-Technologie (I/F/I)
+ilitek	ILI Technology Corporation (ILITEK)
 img	Imagination Technologies Ltd.
 infineon Infineon Technologies
 inforce	Inforce Computing
@@ -172,6 +175,7 @@ itead	ITEAD Intelligent Systems Co.Ltd
 iwave  iWave Systems Technologies Pvt. Ltd.
 jdi	Japan Display Inc.
 jedec	JEDEC Solid State Technology Association
+jianda	Jiandangjing Technology Co., Ltd.
 karo	Ka-Ro electronics GmbH
 keithkoep	Keith & Koep GmbH
 keymile	Keymile GmbH
@@ -305,6 +309,7 @@ seagate	Seagate Technology PLC
 semtech	Semtech Corporation
 sensirion	Sensirion AG
 sff	Small Form Factor Committee
+sgd	Solomon Goldentek Display Corporation
 sgx	SGX Sensortech
 sharp	Sharp Corporation
 shimafuji	Shimafuji Electric, Inc.
@@ -347,6 +352,7 @@ tcg	Trusted Computing Group
 tcl	Toby Churchill Ltd.
 technexion	TechNexion
 technologic	Technologic Systems
+tempo	Tempo Semiconductor
 terasic	Terasic Inc.
 thine	THine Electronics, Inc.
 ti	Texas Instruments
@@ -379,6 +385,7 @@ virtio	Virtual I/O Device Specification, developed by the OASIS consortium
 vivante	Vivante Corporation
 vocore VoCore Studio
 voipac	Voipac Technologies s.r.o.
+vot	Vision Optical Technology Co., Ltd.
 wd	Western Digital Corp.
 wetek	WeTek Electronics, limited.
 wexler	Wexler
diff --git a/Documentation/devicetree/bindings/watchdog/ingenic,jz4740-wdt.txt b/Documentation/devicetree/bindings/watchdog/ingenic,jz4740-wdt.txt
index e27763ef0049..3c7a1cd13b10 100644
--- a/Documentation/devicetree/bindings/watchdog/ingenic,jz4740-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/ingenic,jz4740-wdt.txt
@@ -6,7 +6,7 @@ reg: Register address and length for watchdog registers
 
 Example:
 
-watchdog: jz4740-watchdog@0x10002000 {
+watchdog: jz4740-watchdog@10002000 {
 	compatible = "ingenic,jz4740-watchdog";
 	reg = <0x10002000 0x100>;
 };
diff --git a/Documentation/devicetree/bindings/watchdog/pnx4008-wdt.txt b/Documentation/devicetree/bindings/watchdog/pnx4008-wdt.txt
index 556d06c17c92..4b76bec62af9 100644
--- a/Documentation/devicetree/bindings/watchdog/pnx4008-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/pnx4008-wdt.txt
@@ -10,7 +10,7 @@ Optional properties:
 
 Example:
 
-	watchdog@4003C000 {
+	watchdog@4003c000 {
 		compatible = "nxp,pnx4008-wdt";
 		reg = <0x4003C000 0x1000>;
 		timeout-sec = <10>;
diff --git a/Documentation/devicetree/bindings/watchdog/samsung-wdt.txt b/Documentation/devicetree/bindings/watchdog/samsung-wdt.txt
index 1f6e101e299a..46dcb48e75b4 100644
--- a/Documentation/devicetree/bindings/watchdog/samsung-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/samsung-wdt.txt
@@ -25,7 +25,7 @@ Optional properties:
 
 Example:
 
-watchdog@101D0000 {
+watchdog@101d0000 {
 	compatible = "samsung,exynos5250-wdt";
 	reg = <0x101D0000 0x100>;
 	interrupts = <0 42 0>;
diff --git a/Documentation/devicetree/bindings/watchdog/zii,rave-sp-wdt.txt b/Documentation/devicetree/bindings/watchdog/zii,rave-sp-wdt.txt
new file mode 100644
index 000000000000..3de96186e92e
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/zii,rave-sp-wdt.txt
@@ -0,0 +1,39 @@
+Zodiac Inflight Innovations RAVE Supervisory Processor Watchdog Bindings
+
+RAVE SP watchdog device is a "MFD cell" device corresponding to
+watchdog functionality of RAVE Supervisory Processor. It is expected
+that its Device Tree node is specified as a child of the node
+corresponding to the parent RAVE SP device (as documented in
+Documentation/devicetree/bindings/mfd/zii,rave-sp.txt)
+
+Required properties:
+
+- compatible: Depending on wire protocol implemented by RAVE SP
+  firmware, should be one of:
+	- "zii,rave-sp-watchdog"
+	- "zii,rave-sp-watchdog-legacy"
+
+Optional properties:
+
+- wdt-timeout:	Two byte nvmem cell specified as per
+		Documentation/devicetree/bindings/nvmem/nvmem.txt
+
+Example:
+
+	rave-sp {
+		compatible = "zii,rave-sp-rdu1";
+		current-speed = <38400>;
+
+		eeprom {
+			wdt_timeout: wdt-timeout@8E {
+				reg = <0x8E 2>;
+			};
+		};
+
+		watchdog {
+			compatible = "zii,rave-sp-watchdog";
+			nvmem-cells = <&wdt_timeout>;
+			nvmem-cell-names = "wdt-timeout";
+		};
+	}
+
diff --git a/Documentation/devicetree/booting-without-of.txt b/Documentation/devicetree/booting-without-of.txt
index 417f91110010..e86bd2f64117 100644
--- a/Documentation/devicetree/booting-without-of.txt
+++ b/Documentation/devicetree/booting-without-of.txt
@@ -1309,7 +1309,7 @@ number and level/sense information. All interrupt children in an
 OpenPIC interrupt domain use 2 cells per interrupt in their interrupts
 property.
 
-The PCI bus binding specifies a #interrupt-cell value of 1 to encode
+The PCI bus binding specifies a #interrupt-cells value of 1 to encode
 which interrupt pin (INTA,INTB,INTC,INTD) is used.
 
 2) interrupt-parent property
diff --git a/Documentation/doc-guide/kernel-doc.rst b/Documentation/doc-guide/kernel-doc.rst
index 0268335414ce..722d4525f7cf 100644
--- a/Documentation/doc-guide/kernel-doc.rst
+++ b/Documentation/doc-guide/kernel-doc.rst
@@ -112,16 +112,17 @@ Example kernel-doc function comment::
 
   /**
    * foobar() - Brief description of foobar.
-   * @arg: Description of argument of foobar.
+   * @argument1: Description of parameter argument1 of foobar.
+   * @argument2: Description of parameter argument2 of foobar.
    *
    * Longer description of foobar.
    *
    * Return: Description of return value of foobar.
    */
-  int foobar(int arg)
+  int foobar(int argument1, char *argument2)
 
 The format is similar for documentation for structures, enums, paragraphs,
-etc. See the sections below for details.
+etc. See the sections below for specific details of each type.
 
 The kernel-doc structure is extracted from the comments, and proper `Sphinx C
 Domain`_ function and type descriptions with anchors are generated for them. The
@@ -130,6 +131,226 @@ cross-references. See below for details.
 
 .. _Sphinx C Domain: http://www.sphinx-doc.org/en/stable/domains.html
 
+
+Parameters and member arguments
+-------------------------------
+
+The kernel-doc function comments describe each parameter to the function and
+function typedefs or each member of struct/union, in order, with the
+``@argument:`` descriptions. For each non-private member argument, one
+``@argument`` definition is needed.
+
+The ``@argument:`` descriptions begin on the very next line following
+the opening brief function description line, with no intervening blank
+comment lines.
+
+The ``@argument:`` descriptions may span multiple lines.
+
+.. note::
+
+   If the ``@argument`` description has multiple lines, the continuation
+   of the description should be starting exactly at the same column as
+   the previous line, e. g.::
+
+      * @argument: some long description
+      *       that continues on next lines
+
+   or::
+
+      * @argument:
+      *		some long description
+      *		that continues on next lines
+
+If a function or typedef parameter argument is ``...`` (e. g. a variable
+number of arguments), its description should be listed in kernel-doc
+notation as::
+
+      * @...: description
+
+Private members
+~~~~~~~~~~~~~~~
+
+Inside a struct or union description, you can use the ``private:`` and
+``public:`` comment tags. Structure fields that are inside a ``private:``
+area are not listed in the generated output documentation.
+
+The ``private:`` and ``public:`` tags must begin immediately following a
+``/*`` comment marker.  They may optionally include comments between the
+``:`` and the ending ``*/`` marker.
+
+Example::
+
+  /**
+   * struct my_struct - short description
+   * @a: first member
+   * @b: second member
+   * @d: fourth member
+   *
+   * Longer description
+   */
+  struct my_struct {
+      int a;
+      int b;
+  /* private: internal use only */
+      int c;
+  /* public: the next one is public */
+      int d;
+  };
+
+Function documentation
+----------------------
+
+The general format of a function and function-like macro kernel-doc comment is::
+
+  /**
+   * function_name() - Brief description of function.
+   * @arg1: Describe the first argument.
+   * @arg2: Describe the second argument.
+   *        One can provide multiple line descriptions
+   *        for arguments.
+   *
+   * A longer description, with more discussion of the function function_name()
+   * that might be useful to those using or modifying it. Begins with an
+   * empty comment line, and may include additional embedded empty
+   * comment lines.
+   *
+   * The longer description may have multiple paragraphs.
+   *
+   * Return: Describe the return value of foobar.
+   *
+   * The return value description can also have multiple paragraphs, and should
+   * be placed at the end of the comment block.
+   */
+
+The brief description following the function name may span multiple lines, and
+ends with an argument description, a blank comment line, or the end of the
+comment block.
+
+Return values
+~~~~~~~~~~~~~
+
+The return value, if any, should be described in a dedicated section
+named ``Return``.
+
+.. note::
+
+  #) The multi-line descriptive text you provide does *not* recognize
+     line breaks, so if you try to format some text nicely, as in::
+
+	* Return:
+	* 0 - OK
+	* -EINVAL - invalid argument
+	* -ENOMEM - out of memory
+
+     this will all run together and produce::
+
+	Return: 0 - OK -EINVAL - invalid argument -ENOMEM - out of memory
+
+     So, in order to produce the desired line breaks, you need to use a
+     ReST list, e. g.::
+
+      * Return:
+      * * 0		- OK to runtime suspend the device
+      * * -EBUSY	- Device should not be runtime suspended
+
+  #) If the descriptive text you provide has lines that begin with
+     some phrase followed by a colon, each of those phrases will be taken
+     as a new section heading, with probably won't produce the desired
+     effect.
+
+Structure, union, and enumeration documentation
+-----------------------------------------------
+
+The general format of a struct, union, and enum kernel-doc comment is::
+
+  /**
+   * struct struct_name - Brief description.
+   * @argument: Description of member member_name.
+   *
+   * Description of the structure.
+   */
+
+On the above, ``struct`` is used to mean structs. You can also use ``union``
+and ``enum``  to describe unions and enums. ``argument`` is used
+to mean struct and union member names as well as enumerations in an enum.
+
+The brief description following the structure name may span multiple lines, and
+ends with a member description, a blank comment line, or the end of the
+comment block.
+
+The kernel-doc data structure comments describe each member of the structure,
+in order, with the member descriptions.
+
+Nested structs/unions
+~~~~~~~~~~~~~~~~~~~~~
+
+It is possible to document nested structs unions, like::
+
+      /**
+       * struct nested_foobar - a struct with nested unions and structs
+       * @arg1: - first argument of anonymous union/anonymous struct
+       * @arg2: - second argument of anonymous union/anonymous struct
+       * @arg3: - third argument of anonymous union/anonymous struct
+       * @arg4: - fourth argument of anonymous union/anonymous struct
+       * @bar.st1.arg1 - first argument of struct st1 on union bar
+       * @bar.st1.arg2 - second argument of struct st1 on union bar
+       * @bar.st2.arg1 - first argument of struct st2 on union bar
+       * @bar.st2.arg2 - second argument of struct st2 on union bar
+      struct nested_foobar {
+        /* Anonymous union/struct*/
+        union {
+          struct {
+            int arg1;
+            int arg2;
+	  }
+          struct {
+            void *arg3;
+            int arg4;
+	  }
+	}
+	union {
+          struct {
+            int arg1;
+            int arg2;
+	  } st1;
+          struct {
+            void *arg1;
+            int arg2;
+	  } st2;
+	} bar;
+      };
+
+.. note::
+
+   #) When documenting nested structs or unions, if the struct/union ``foo``
+      is named, the argument ``bar`` inside it should be documented as
+      ``@foo.bar:``
+   #) When the nested struct/union is anonymous, the argument ``bar`` on it
+      should be documented as ``@bar:``
+
+Typedef documentation
+---------------------
+
+The general format of a typedef kernel-doc comment is::
+
+  /**
+   * typedef type_name - Brief description.
+   *
+   * Description of the type.
+   */
+
+Typedefs with function prototypes can also be documented::
+
+  /**
+   * typedef type_name - Brief description.
+   * @arg1: description of arg1
+   * @arg2: description of arg2
+   *
+   * Description of the type.
+   */
+   typedef void (*type_name)(struct v4l2_ctrl *arg1, void *arg2);
+
+
 Highlights and cross-references
 -------------------------------
 
@@ -201,70 +422,7 @@ cross-references.
 
 For further details, please refer to the `Sphinx C Domain`_ documentation.
 
-Function documentation
-----------------------
-
-The general format of a function and function-like macro kernel-doc comment is::
-
-  /**
-   * function_name() - Brief description of function.
-   * @arg1: Describe the first argument.
-   * @arg2: Describe the second argument.
-   *        One can provide multiple line descriptions
-   *        for arguments.
-   *
-   * A longer description, with more discussion of the function function_name()
-   * that might be useful to those using or modifying it. Begins with an
-   * empty comment line, and may include additional embedded empty
-   * comment lines.
-   *
-   * The longer description may have multiple paragraphs.
-   *
-   * Return: Describe the return value of foobar.
-   *
-   * The return value description can also have multiple paragraphs, and should
-   * be placed at the end of the comment block.
-   */
-
-The brief description following the function name may span multiple lines, and
-ends with an ``@argument:`` description, a blank comment line, or the end of the
-comment block.
-
-The kernel-doc function comments describe each parameter to the function, in
-order, with the ``@argument:`` descriptions. The ``@argument:`` descriptions
-must begin on the very next line following the opening brief function
-description line, with no intervening blank comment lines. The ``@argument:``
-descriptions may span multiple lines. The continuation lines may contain
-indentation. If a function parameter is ``...`` (varargs), it should be listed
-in kernel-doc notation as: ``@...:``.
-
-The return value, if any, should be described in a dedicated section at the end
-of the comment starting with "Return:".
-
-Structure, union, and enumeration documentation
------------------------------------------------
-
-The general format of a struct, union, and enum kernel-doc comment is::
-
-  /**
-   * struct struct_name - Brief description.
-   * @member_name: Description of member member_name.
-   *
-   * Description of the structure.
-   */
-
-Below, "struct" is used to mean structs, unions and enums, and "member" is used
-to mean struct and union members as well as enumerations in an enum.
-
-The brief description following the structure name may span multiple lines, and
-ends with a ``@member:`` description, a blank comment line, or the end of the
-comment block.
 
-The kernel-doc data structure comments describe each member of the structure, in
-order, with the ``@member:`` descriptions. The ``@member:`` descriptions must
-begin on the very next line following the opening brief function description
-line, with no intervening blank comment lines. The ``@member:`` descriptions may
-span multiple lines. The continuation lines may contain indentation.
 
 In-line member documentation comments
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -294,42 +452,6 @@ on a line of their own, like all other kernel-doc comments::
         int foobar;
   }
 
-Private members
-~~~~~~~~~~~~~~~
-
-Inside a struct description, you can use the "private:" and "public:" comment
-tags. Structure fields that are inside a "private:" area are not listed in the
-generated output documentation.  The "private:" and "public:" tags must begin
-immediately following a ``/*`` comment marker.  They may optionally include
-comments between the ``:`` and the ending ``*/`` marker.
-
-Example::
-
-  /**
-   * struct my_struct - short description
-   * @a: first member
-   * @b: second member
-   *
-   * Longer description
-   */
-  struct my_struct {
-      int a;
-      int b;
-  /* private: internal use only */
-      int c;
-  };
-
-
-Typedef documentation
----------------------
-
-The general format of a typedef kernel-doc comment is::
-
-  /**
-   * typedef type_name - Brief description.
-   *
-   * Description of the type.
-   */
 
 Overview documentation comments
 -------------------------------
@@ -376,3 +498,37 @@ file.
 
 Data structures visible in kernel include files should also be documented using
 kernel-doc formatted comments.
+
+How to use kernel-doc to generate man pages
+-------------------------------------------
+
+If you just want to use kernel-doc to generate man pages you can do this
+from the Kernel git tree::
+
+  $ scripts/kernel-doc -man $(git grep -l '/\*\*' |grep -v Documentation/) | ./split-man.pl /tmp/man
+
+Using the small ``split-man.pl`` script below::
+
+
+  #!/usr/bin/perl
+
+  if ($#ARGV < 0) {
+     die "where do I put the results?\n";
+  }
+
+  mkdir $ARGV[0],0777;
+  $state = 0;
+  while (<STDIN>) {
+      if (/^\.TH \"[^\"]*\" 9 \"([^\"]*)\"/) {
+	if ($state == 1) { close OUT }
+	$state = 1;
+	$fn = "$ARGV[0]/$1.9";
+	print STDERR "Creating $fn\n";
+	open OUT, ">$fn" or die "can't open $fn: $!\n";
+	print OUT $_;
+      } elsif ($state != 0) {
+	print OUT $_;
+      }
+  }
+
+  close OUT;
diff --git a/Documentation/driver-api/basics.rst b/Documentation/driver-api/basics.rst
index 73fa7d42bbba..826e85d50a16 100644
--- a/Documentation/driver-api/basics.rst
+++ b/Documentation/driver-api/basics.rst
@@ -13,12 +13,6 @@ Driver device table
 .. kernel-doc:: include/linux/mod_devicetable.h
    :internal:
 
-Atomic and pointer manipulation
--------------------------------
-
-.. kernel-doc:: arch/x86/include/asm/atomic.h
-   :internal:
-
 Delaying, scheduling, and timer routines
 ----------------------------------------
 
@@ -85,6 +79,21 @@ Internal Functions
 .. kernel-doc:: kernel/kthread.c
    :export:
 
+Reference counting
+------------------
+
+.. kernel-doc:: include/linux/refcount.h
+   :internal:
+
+.. kernel-doc:: lib/refcount.c
+   :export:
+
+Atomics
+-------
+
+.. kernel-doc:: arch/x86/include/asm/atomic.h
+   :internal:
+
 Kernel objects manipulation
 ---------------------------
 
diff --git a/Documentation/driver-api/dmaengine/client.rst b/Documentation/driver-api/dmaengine/client.rst
index 6245c99af8c1..fbbb2831f29f 100644
--- a/Documentation/driver-api/dmaengine/client.rst
+++ b/Documentation/driver-api/dmaengine/client.rst
@@ -185,7 +185,7 @@ The details of these operations are:
       void dma_async_issue_pending(struct dma_chan *chan);
 
 Further APIs:
-------------
+-------------
 
 1. Terminate APIs
 
diff --git a/Documentation/driver-api/dmaengine/provider.rst b/Documentation/driver-api/dmaengine/provider.rst
index 814acb4d2294..dfc4486b5743 100644
--- a/Documentation/driver-api/dmaengine/provider.rst
+++ b/Documentation/driver-api/dmaengine/provider.rst
@@ -111,40 +111,36 @@ The first thing you need to do in your driver is to allocate this
 structure. Any of the usual memory allocators will do, but you'll also
 need to initialize a few fields in there:
 
-- channels: should be initialized as a list using the
+- ``channels``: should be initialized as a list using the
   INIT_LIST_HEAD macro for example
 
-- src_addr_widths:
+- ``src_addr_widths``:
   should contain a bitmask of the supported source transfer width
 
-- dst_addr_widths:
+- ``dst_addr_widths``:
   should contain a bitmask of the supported destination transfer width
 
-- directions:
+- ``directions``:
   should contain a bitmask of the supported slave directions
   (i.e. excluding mem2mem transfers)
 
-- residue_granularity:
+- ``residue_granularity``:
+  granularity of the transfer residue reported to dma_set_residue.
+  This can be either:
 
-  - Granularity of the transfer residue reported to dma_set_residue.
-    This can be either:
+  - Descriptor:
+    your device doesn't support any kind of residue
+    reporting. The framework will only know that a particular
+    transaction descriptor is done.
 
-  - Descriptor
+  - Segment:
+    your device is able to report which chunks have been transferred
 
-    - Your device doesn't support any kind of residue
-      reporting. The framework will only know that a particular
-      transaction descriptor is done.
+  - Burst:
+    your device is able to report which burst have been transferred
 
-      - Segment
-
-        - Your device is able to report which chunks have been transferred
-
-      - Burst
-
-        - Your device is able to report which burst have been transferred
-
-  - dev: should hold the pointer to the ``struct device`` associated
-    to your current driver instance.
+- ``dev``: should hold the pointer to the ``struct device`` associated
+  to your current driver instance.
 
 Supported transaction types
 ---------------------------
diff --git a/Documentation/driver-api/firmware/built-in-fw.rst b/Documentation/driver-api/firmware/built-in-fw.rst
index 7300e66857f8..396cdf591ac5 100644
--- a/Documentation/driver-api/firmware/built-in-fw.rst
+++ b/Documentation/driver-api/firmware/built-in-fw.rst
@@ -11,13 +11,8 @@ options:
   * CONFIG_EXTRA_FIRMWARE
   * CONFIG_EXTRA_FIRMWARE_DIR
 
-This should not be confused with CONFIG_FIRMWARE_IN_KERNEL, this is for drivers
-which enables firmware to be built as part of the kernel build process. This
-option, CONFIG_FIRMWARE_IN_KERNEL, will build all firmware for all drivers
-enabled which ship its firmware inside the Linux kernel source tree.
-
 There are a few reasons why you might want to consider building your firmware
-into the kernel with CONFIG_EXTRA_FIRMWARE though:
+into the kernel with CONFIG_EXTRA_FIRMWARE:
 
 * Speed
 * Firmware is needed for accessing the boot device, and the user doesn't
diff --git a/Documentation/driver-api/firmware/fallback-mechanisms.rst b/Documentation/driver-api/firmware/fallback-mechanisms.rst
index d19354794e67..4055ac76b288 100644
--- a/Documentation/driver-api/firmware/fallback-mechanisms.rst
+++ b/Documentation/driver-api/firmware/fallback-mechanisms.rst
@@ -71,7 +71,7 @@ via fw_create_instance(). This call creates a new struct device named after
 the firmware requested, and establishes it in the device hierarchy by
 associating the device used to make the request as the device's parent.
 The sysfs directory's file attributes are defined and controlled through
-the new device's class (firmare_class) and group (fw_dev_attr_groups).
+the new device's class (firmware_class) and group (fw_dev_attr_groups).
 This is actually where the original firmware_class.c file name comes from,
 as originally the only firmware loading mechanism available was the
 mechanism we now use as a fallback mechanism.
diff --git a/Documentation/driver-api/iio/hw-consumer.rst b/Documentation/driver-api/iio/hw-consumer.rst
new file mode 100644
index 000000000000..8facce6a6733
--- /dev/null
+++ b/Documentation/driver-api/iio/hw-consumer.rst
@@ -0,0 +1,51 @@
+===========
+HW consumer
+===========
+An IIO device can be directly connected to another device in hardware. in this
+case the buffers between IIO provider and IIO consumer are handled by hardware.
+The Industrial I/O HW consumer offers a way to bond these IIO devices without
+software buffer for data. The implementation can be found under
+:file:`drivers/iio/buffer/hw-consumer.c`
+
+
+* struct :c:type:`iio_hw_consumer` — Hardware consumer structure
+* :c:func:`iio_hw_consumer_alloc` — Allocate IIO hardware consumer
+* :c:func:`iio_hw_consumer_free` — Free IIO hardware consumer
+* :c:func:`iio_hw_consumer_enable` — Enable IIO hardware consumer
+* :c:func:`iio_hw_consumer_disable` — Disable IIO hardware consumer
+
+
+HW consumer setup
+=================
+
+As standard IIO device the implementation is based on IIO provider/consumer.
+A typical IIO HW consumer setup looks like this::
+
+	static struct iio_hw_consumer *hwc;
+
+	static const struct iio_info adc_info = {
+		.read_raw = adc_read_raw,
+	};
+
+	static int adc_read_raw(struct iio_dev *indio_dev,
+				struct iio_chan_spec const *chan, int *val,
+				int *val2, long mask)
+	{
+		ret = iio_hw_consumer_enable(hwc);
+
+		/* Acquire data */
+
+		ret = iio_hw_consumer_disable(hwc);
+	}
+
+	static int adc_probe(struct platform_device *pdev)
+	{
+		hwc = devm_iio_hw_consumer_alloc(&iio->dev);
+	}
+
+More details
+============
+.. kernel-doc:: include/linux/iio/hw-consumer.h
+.. kernel-doc:: drivers/iio/buffer/industrialio-hw-consumer.c
+   :export:
+
diff --git a/Documentation/driver-api/iio/index.rst b/Documentation/driver-api/iio/index.rst
index e5c3922d1b6f..7fba341bd8b2 100644
--- a/Documentation/driver-api/iio/index.rst
+++ b/Documentation/driver-api/iio/index.rst
@@ -15,3 +15,4 @@ Contents:
    buffers
    triggers
    triggered-buffers
+   hw-consumer
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index d17a9876b473..e9b41b1634f3 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -47,6 +47,8 @@ available subsections can be seen below.
    gpio
    misc_devices
    dmaengine/index
+   slimbus
+   soundwire/index
 
 .. only::  subproject and html
 
diff --git a/Documentation/driver-api/pci.rst b/Documentation/driver-api/pci.rst
index 01a6c8b7d3a7..ca85e5e78b2c 100644
--- a/Documentation/driver-api/pci.rst
+++ b/Documentation/driver-api/pci.rst
@@ -25,9 +25,6 @@ PCI Support Library
 .. kernel-doc:: drivers/pci/irq.c
    :export:
 
-.. kernel-doc:: drivers/pci/htirq.c
-   :export:
-
 .. kernel-doc:: drivers/pci/probe.c
    :export:
 
diff --git a/Documentation/driver-api/pm/devices.rst b/Documentation/driver-api/pm/devices.rst
index 53c1b0b06da5..1128705a5731 100644
--- a/Documentation/driver-api/pm/devices.rst
+++ b/Documentation/driver-api/pm/devices.rst
@@ -777,17 +777,51 @@ The driver can indicate that by setting ``DPM_FLAG_SMART_SUSPEND`` in
 runtime suspend at the beginning of the ``suspend_late`` phase of system-wide
 suspend (or in the ``poweroff_late`` phase of hibernation), when runtime PM
 has been disabled for it, under the assumption that its state should not change
-after that point until the system-wide transition is over.  If that happens, the
-driver's system-wide resume callbacks, if present, may still be invoked during
-the subsequent system-wide resume transition and the device's runtime power
-management status may be set to "active" before enabling runtime PM for it,
-so the driver must be prepared to cope with the invocation of its system-wide
-resume callbacks back-to-back with its ``->runtime_suspend`` one (without the
-intervening ``->runtime_resume`` and so on) and the final state of the device
-must reflect the "active" status for runtime PM in that case.
+after that point until the system-wide transition is over (the PM core itself
+does that for devices whose "noirq", "late" and "early" system-wide PM callbacks
+are executed directly by it).  If that happens, the driver's system-wide resume
+callbacks, if present, may still be invoked during the subsequent system-wide
+resume transition and the device's runtime power management status may be set
+to "active" before enabling runtime PM for it, so the driver must be prepared to
+cope with the invocation of its system-wide resume callbacks back-to-back with
+its ``->runtime_suspend`` one (without the intervening ``->runtime_resume`` and
+so on) and the final state of the device must reflect the "active" runtime PM
+status in that case.
 
 During system-wide resume from a sleep state it's easiest to put devices into
 the full-power state, as explained in :file:`Documentation/power/runtime_pm.txt`.
-Refer to that document for more information regarding this particular issue as
+[Refer to that document for more information regarding this particular issue as
 well as for information on the device runtime power management framework in
-general.
+general.]
+
+However, it often is desirable to leave devices in suspend after system
+transitions to the working state, especially if those devices had been in
+runtime suspend before the preceding system-wide suspend (or analogous)
+transition.  Device drivers can use the ``DPM_FLAG_LEAVE_SUSPENDED`` flag to
+indicate to the PM core (and middle-layer code) that they prefer the specific
+devices handled by them to be left suspended and they have no problems with
+skipping their system-wide resume callbacks for this reason.  Whether or not the
+devices will actually be left in suspend may depend on their state before the
+given system suspend-resume cycle and on the type of the system transition under
+way.  In particular, devices are not left suspended if that transition is a
+restore from hibernation, as device states are not guaranteed to be reflected
+by the information stored in the hibernation image in that case.
+
+The middle-layer code involved in the handling of the device is expected to
+indicate to the PM core if the device may be left in suspend by setting its
+:c:member:`power.may_skip_resume` status bit which is checked by the PM core
+during the "noirq" phase of the preceding system-wide suspend (or analogous)
+transition.  The middle layer is then responsible for handling the device as
+appropriate in its "noirq" resume callback, which is executed regardless of
+whether or not the device is left suspended, but the other resume callbacks
+(except for ``->complete``) will be skipped automatically by the PM core if the
+device really can be left in suspend.
+
+For devices whose "noirq", "late" and "early" driver callbacks are invoked
+directly by the PM core, all of the system-wide resume callbacks are skipped if
+``DPM_FLAG_LEAVE_SUSPENDED`` is set and the device is in runtime suspend during
+the ``suspend_noirq`` (or analogous) phase or the transition under way is a
+proper system suspend (rather than anything related to hibernation) and the
+device's wakeup settings are suitable for runtime PM (that is, it cannot
+generate wakeup signals at all or it is allowed to wake up the system from
+sleep).
diff --git a/Documentation/driver-api/scsi.rst b/Documentation/driver-api/scsi.rst
index 9ae03171daca..3ae337929721 100644
--- a/Documentation/driver-api/scsi.rst
+++ b/Documentation/driver-api/scsi.rst
@@ -224,6 +224,14 @@ mid to lowlevel SCSI driver interface
 .. kernel-doc:: drivers/scsi/hosts.c
    :export:
 
+drivers/scsi/scsi_common.c
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+general support functions
+
+.. kernel-doc:: drivers/scsi/scsi_common.c
+   :export:
+
 Transport classes
 -----------------
 
@@ -332,5 +340,5 @@ todo
 ~~~~
 
 Parallel (fast/wide/ultra) SCSI, USB, SATA, SAS, Fibre Channel,
-FireWire, ATAPI devices, Infiniband, I20, iSCSI, Parallel ports,
+FireWire, ATAPI devices, Infiniband, I2O, iSCSI, Parallel ports,
 netlink...
diff --git a/Documentation/driver-api/slimbus.rst b/Documentation/driver-api/slimbus.rst
new file mode 100644
index 000000000000..7555ecd538de
--- /dev/null
+++ b/Documentation/driver-api/slimbus.rst
@@ -0,0 +1,127 @@
+============================
+Linux kernel SLIMbus support
+============================
+
+Overview
+========
+
+What is SLIMbus?
+----------------
+SLIMbus (Serial Low Power Interchip Media Bus) is a specification developed by
+MIPI (Mobile Industry Processor Interface) alliance. The bus uses master/slave
+configuration, and is a 2-wire multi-drop implementation (clock, and data).
+
+Currently, SLIMbus is used to interface between application processors of SoCs
+(System-on-Chip) and peripheral components (typically codec). SLIMbus uses
+Time-Division-Multiplexing to accommodate multiple data channels, and
+a control channel.
+
+The control channel is used for various control functions such as bus
+management, configuration and status updates. These messages can be unicast (e.g.
+reading/writing device specific values), or multicast (e.g. data channel
+reconfiguration sequence is a broadcast message announced to all devices)
+
+A data channel is used for data-transfer between 2 SLIMbus devices. Data
+channel uses dedicated ports on the device.
+
+Hardware description:
+---------------------
+SLIMbus specification has different types of device classifications based on
+their capabilities.
+A manager device is responsible for enumeration, configuration, and dynamic
+channel allocation. Every bus has 1 active manager.
+
+A generic device is a device providing application functionality (e.g. codec).
+
+Framer device is responsible for clocking the bus, and transmitting frame-sync
+and framing information on the bus.
+
+Each SLIMbus component has an interface device for monitoring physical layer.
+
+Typically each SoC contains SLIMbus component having 1 manager, 1 framer device,
+1 generic device (for data channel support), and 1 interface device.
+External peripheral SLIMbus component usually has 1 generic device (for
+functionality/data channel support), and an associated interface device.
+The generic device's registers are mapped as 'value elements' so that they can
+be written/read using SLIMbus control channel exchanging control/status type of
+information.
+In case there are multiple framer devices on the same bus, manager device is
+responsible to select the active-framer for clocking the bus.
+
+Per specification, SLIMbus uses "clock gears" to do power management based on
+current frequency and bandwidth requirements. There are 10 clock gears and each
+gear changes the SLIMbus frequency to be twice its previous gear.
+
+Each device has a 6-byte enumeration-address and the manager assigns every
+device with a 1-byte logical address after the devices report presence on the
+bus.
+
+Software description:
+---------------------
+There are 2 types of SLIMbus drivers:
+
+slim_controller represents a 'controller' for SLIMbus. This driver should
+implement duties needed by the SoC (manager device, associated
+interface device for monitoring the layers and reporting errors, default
+framer device).
+
+slim_device represents the 'generic device/component' for SLIMbus, and a
+slim_driver should implement driver for that slim_device.
+
+Device notifications to the driver:
+-----------------------------------
+Since SLIMbus devices have mechanisms for reporting their presence, the
+framework allows drivers to bind when corresponding devices report their
+presence on the bus.
+However, it is possible that the driver needs to be probed
+first so that it can enable corresponding SLIMbus device (e.g. power it up and/or
+take it out of reset). To support that behavior, the framework allows drivers
+to probe first as well  (e.g. using standard DeviceTree compatibility field).
+This creates the necessity for the driver to know when the device is functional
+(i.e. reported present). device_up callback is used for that reason when the
+device reports present and is assigned a logical address by the controller.
+
+Similarly, SLIMbus devices 'report absent' when they go down. A 'device_down'
+callback notifies the driver when the device reports absent and its logical
+address assignment is invalidated by the controller.
+
+Another notification "boot_device" is used to notify the slim_driver when
+controller resets the bus. This notification allows the driver to take necessary
+steps to boot the device so that it's functional after the bus has been reset.
+
+Driver and Controller APIs:
+--------------------------
+.. kernel-doc:: include/linux/slimbus.h
+   :internal:
+
+.. kernel-doc:: drivers/slimbus/slimbus.h
+   :internal:
+
+.. kernel-doc:: drivers/slimbus/core.c
+   :export:
+
+Clock-pause:
+------------
+SLIMbus mandates that a reconfiguration sequence (known as clock-pause) be
+broadcast to all active devices on the bus before the bus can enter low-power
+mode. Controller uses this sequence when it decides to enter low-power mode so
+that corresponding clocks and/or power-rails can be turned off to save power.
+Clock-pause is exited by waking up framer device (if controller driver initiates
+exiting low power mode), or by toggling the data line (if a slave device wants
+to initiate it).
+
+Clock-pause APIs:
+~~~~~~~~~~~~~~~~~
+.. kernel-doc:: drivers/slimbus/sched.c
+   :export:
+
+Messaging:
+----------
+The framework supports regmap and read/write apis to exchange control-information
+with a SLIMbus device. APIs can be synchronous or asynchronous.
+The header file <linux/slimbus.h> has more documentation about messaging APIs.
+
+Messaging APIs:
+~~~~~~~~~~~~~~~
+.. kernel-doc:: drivers/slimbus/messaging.c
+   :export:
diff --git a/Documentation/driver-api/soundwire/index.rst b/Documentation/driver-api/soundwire/index.rst
new file mode 100644
index 000000000000..647e94654752
--- /dev/null
+++ b/Documentation/driver-api/soundwire/index.rst
@@ -0,0 +1,15 @@
+=======================
+SoundWire Documentation
+=======================
+
+.. toctree::
+   :maxdepth: 1
+
+   summary
+
+.. only::  subproject
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/driver-api/soundwire/summary.rst b/Documentation/driver-api/soundwire/summary.rst
new file mode 100644
index 000000000000..8193125a2bfb
--- /dev/null
+++ b/Documentation/driver-api/soundwire/summary.rst
@@ -0,0 +1,207 @@
+===========================
+SoundWire Subsystem Summary
+===========================
+
+SoundWire is a new interface ratified in 2015 by the MIPI Alliance.
+SoundWire is used for transporting data typically related to audio
+functions. SoundWire interface is optimized to integrate audio devices in
+mobile or mobile inspired systems.
+
+SoundWire is a 2-pin multi-drop interface with data and clock line. It
+facilitates development of low cost, efficient, high performance systems.
+Broad level key features of SoundWire interface include:
+
+ (1) Transporting all of payload data channels, control information, and setup
+     commands over a single two-pin interface.
+
+ (2) Lower clock frequency, and hence lower power consumption, by use of DDR
+     (Dual Data Rate) data transmission.
+
+ (3) Clock scaling and optional multiple data lanes to give wide flexibility
+     in data rate to match system requirements.
+
+ (4) Device status monitoring, including interrupt-style alerts to the Master.
+
+The SoundWire protocol supports up to eleven Slave interfaces. All the
+interfaces share the common Bus containing data and clock line. Each of the
+Slaves can support up to 14 Data Ports. 13 Data Ports are dedicated to audio
+transport. Data Port0 is dedicated to transport of Bulk control information,
+each of the audio Data Ports (1..14) can support up to 8 Channels in
+transmit or receiving mode (typically fixed direction but configurable
+direction is enabled by the specification).  Bandwidth restrictions to
+~19.2..24.576Mbits/s don't however allow for 11*13*8 channels to be
+transmitted simultaneously.
+
+Below figure shows an example of connectivity between a SoundWire Master and
+two Slave devices. ::
+
+        +---------------+                                       +---------------+
+        |               |                       Clock Signal    |               |
+        |    Master     |-------+-------------------------------|    Slave      |
+        |   Interface   |       |               Data Signal     |  Interface 1  |
+        |               |-------|-------+-----------------------|               |
+        +---------------+       |       |                       +---------------+
+                                |       |
+                                |       |
+                                |       |
+                             +--+-------+--+
+                             |             |
+                             |   Slave     |
+                             | Interface 2 |
+                             |             |
+                             +-------------+
+
+
+Terminology
+===========
+
+The MIPI SoundWire specification uses the term 'device' to refer to a Master
+or Slave interface, which of course can be confusing. In this summary and
+code we use the term interface only to refer to the hardware. We follow the
+Linux device model by mapping each Slave interface connected on the bus as a
+device managed by a specific driver. The Linux SoundWire subsystem provides
+a framework to implement a SoundWire Slave driver with an API allowing
+3rd-party vendors to enable implementation-defined functionality while
+common setup/configuration tasks are handled by the bus.
+
+Bus:
+Implements SoundWire Linux Bus which handles the SoundWire protocol.
+Programs all the MIPI-defined Slave registers. Represents a SoundWire
+Master. Multiple instances of Bus may be present in a system.
+
+Slave:
+Registers as SoundWire Slave device (Linux Device). Multiple Slave devices
+can register to a Bus instance.
+
+Slave driver:
+Driver controlling the Slave device. MIPI-specified registers are controlled
+directly by the Bus (and transmitted through the Master driver/interface).
+Any implementation-defined Slave register is controlled by Slave driver. In
+practice, it is expected that the Slave driver relies on regmap and does not
+request direct register access.
+
+Programming interfaces (SoundWire Master interface Driver)
+==========================================================
+
+SoundWire Bus supports programming interfaces for the SoundWire Master
+implementation and SoundWire Slave devices. All the code uses the "sdw"
+prefix commonly used by SoC designers and 3rd party vendors.
+
+Each of the SoundWire Master interfaces needs to be registered to the Bus.
+Bus implements API to read standard Master MIPI properties and also provides
+callback in Master ops for Master driver to implement its own functions that
+provides capabilities information. DT support is not implemented at this
+time but should be trivial to add since capabilities are enabled with the
+``device_property_`` API.
+
+The Master interface along with the Master interface capabilities are
+registered based on board file, DT or ACPI.
+
+Following is the Bus API to register the SoundWire Bus:
+
+.. code-block:: c
+
+	int sdw_add_bus_master(struct sdw_bus *bus)
+	{
+		if (!bus->dev)
+			return -ENODEV;
+
+		mutex_init(&bus->lock);
+		INIT_LIST_HEAD(&bus->slaves);
+
+		/* Check ACPI for Slave devices */
+		sdw_acpi_find_slaves(bus);
+
+		/* Check DT for Slave devices */
+		sdw_of_find_slaves(bus);
+
+		return 0;
+	}
+
+This will initialize sdw_bus object for Master device. "sdw_master_ops" and
+"sdw_master_port_ops" callback functions are provided to the Bus.
+
+"sdw_master_ops" is used by Bus to control the Bus in the hardware specific
+way. It includes Bus control functions such as sending the SoundWire
+read/write messages on Bus, setting up clock frequency & Stream
+Synchronization Point (SSP). The "sdw_master_ops" structure abstracts the
+hardware details of the Master from the Bus.
+
+"sdw_master_port_ops" is used by Bus to setup the Port parameters of the
+Master interface Port. Master interface Port register map is not defined by
+MIPI specification, so Bus calls the "sdw_master_port_ops" callback
+function to do Port operations like "Port Prepare", "Port Transport params
+set", "Port enable and disable". The implementation of the Master driver can
+then perform hardware-specific configurations.
+
+Programming interfaces (SoundWire Slave Driver)
+===============================================
+
+The MIPI specification requires each Slave interface to expose a unique
+48-bit identifier, stored in 6 read-only dev_id registers. This dev_id
+identifier contains vendor and part information, as well as a field enabling
+to differentiate between identical components. An additional class field is
+currently unused. Slave driver is written for a specific vendor and part
+identifier, Bus enumerates the Slave device based on these two ids.
+Slave device and driver match is done based on these two ids . Probe
+of the Slave driver is called by Bus on successful match between device and
+driver id. A parent/child relationship is enforced between Master and Slave
+devices (the logical representation is aligned with the physical
+connectivity).
+
+The information on Master/Slave dependencies is stored in platform data,
+board-file, ACPI or DT. The MIPI Software specification defines additional
+link_id parameters for controllers that have multiple Master interfaces. The
+dev_id registers are only unique in the scope of a link, and the link_id
+unique in the scope of a controller. Both dev_id and link_id are not
+necessarily unique at the system level but the parent/child information is
+used to avoid ambiguity.
+
+.. code-block:: c
+
+	static const struct sdw_device_id slave_id[] = {
+	        SDW_SLAVE_ENTRY(0x025d, 0x700, 0),
+	        {},
+	};
+	MODULE_DEVICE_TABLE(sdw, slave_id);
+
+	static struct sdw_driver slave_sdw_driver = {
+	        .driver = {
+	                   .name = "slave_xxx",
+	                   .pm = &slave_runtime_pm,
+	                   },
+		.probe = slave_sdw_probe,
+		.remove = slave_sdw_remove,
+		.ops = &slave_slave_ops,
+		.id_table = slave_id,
+	};
+
+
+For capabilities, Bus implements API to read standard Slave MIPI properties
+and also provides callback in Slave ops for Slave driver to implement own
+function that provides capabilities information. Bus needs to know a set of
+Slave capabilities to program Slave registers and to control the Bus
+reconfigurations.
+
+Future enhancements to be done
+==============================
+
+ (1) Bulk Register Access (BRA) transfers.
+
+
+ (2) Multiple data lane support.
+
+Links
+=====
+
+SoundWire MIPI specification 1.1 is available at:
+https://members.mipi.org/wg/All-Members/document/70290
+
+SoundWire MIPI DisCo (Discovery and Configuration) specification is
+available at:
+https://www.mipi.org/specifications/mipi-disco-soundwire
+
+(publicly accessible with registration or directly accessible to MIPI
+members)
+
+MIPI Alliance Manufacturer ID Page: mid.mipi.org
diff --git a/Documentation/driver-api/uio-howto.rst b/Documentation/driver-api/uio-howto.rst
index f73d660b2956..693e3bd84e79 100644
--- a/Documentation/driver-api/uio-howto.rst
+++ b/Documentation/driver-api/uio-howto.rst
@@ -667,27 +667,28 @@ Making the driver recognize the device
 Since the driver does not declare any device GUID's, it will not get
 loaded automatically and will not automatically bind to any devices, you
 must load it and allocate id to the driver yourself. For example, to use
-the network device GUID::
+the network device class GUID::
 
      modprobe uio_hv_generic
      echo "f8615163-df3e-46c5-913f-f2d2f965ed0e" > /sys/bus/vmbus/drivers/uio_hv_generic/new_id
 
 If there already is a hardware specific kernel driver for the device,
 the generic driver still won't bind to it, in this case if you want to
-use the generic driver (why would you?) you'll have to manually unbind
-the hardware specific driver and bind the generic driver, like this::
+use the generic driver for a userspace library you'll have to manually unbind
+the hardware specific driver and bind the generic driver, using the device specific GUID
+like this::
 
-          echo -n vmbus-ed963694-e847-4b2a-85af-bc9cfc11d6f3 > /sys/bus/vmbus/drivers/hv_netvsc/unbind
-          echo -n vmbus-ed963694-e847-4b2a-85af-bc9cfc11d6f3 > /sys/bus/vmbus/drivers/uio_hv_generic/bind
+          echo -n ed963694-e847-4b2a-85af-bc9cfc11d6f3 > /sys/bus/vmbus/drivers/hv_netvsc/unbind
+          echo -n ed963694-e847-4b2a-85af-bc9cfc11d6f3 > /sys/bus/vmbus/drivers/uio_hv_generic/bind
 
 You can verify that the device has been bound to the driver by looking
 for it in sysfs, for example like the following::
 
-        ls -l /sys/bus/vmbus/devices/vmbus-ed963694-e847-4b2a-85af-bc9cfc11d6f3/driver
+        ls -l /sys/bus/vmbus/devices/ed963694-e847-4b2a-85af-bc9cfc11d6f3/driver
 
 Which if successful should print::
 
-      .../vmbus-ed963694-e847-4b2a-85af-bc9cfc11d6f3/driver -> ../../../bus/vmbus/drivers/uio_hv_generic
+      .../ed963694-e847-4b2a-85af-bc9cfc11d6f3/driver -> ../../../bus/vmbus/drivers/uio_hv_generic
 
 Things to know about uio_hv_generic
 -----------------------------------
@@ -697,6 +698,17 @@ prevents the device from generating further interrupts until the bit is
 cleared. The userspace driver should clear this bit before blocking and
 waiting for more interrupts.
 
+When host rescinds a device, the interrupt file descriptor is marked down
+and any reads of the interrupt file descriptor will return -EIO. Similar
+to a closed socket or disconnected serial device.
+
+The vmbus device regions are mapped into uio device resources:
+    0) Channel ring buffers: guest to host and host to guest
+    1) Guest to host interrupt signalling pages
+    2) Guest to host monitor page
+    3) Network receive buffer region
+    4) Network send buffer region
+
 Further information
 ===================
 
diff --git a/Documentation/driver-api/usb/usb3-debug-port.rst b/Documentation/driver-api/usb/usb3-debug-port.rst
index feb1a36a65b7..b9fd131f4723 100644
--- a/Documentation/driver-api/usb/usb3-debug-port.rst
+++ b/Documentation/driver-api/usb/usb3-debug-port.rst
@@ -98,3 +98,55 @@ you to check the sanity of the setup.
 	cat /dev/ttyUSB0
 	done
 	===== end of bash scripts ===============
+
+Serial TTY
+==========
+
+The DbC support has been added to the xHCI driver. You can get a
+debug device provided by the DbC at runtime.
+
+In order to use this, you need to make sure your kernel has been
+configured to support USB_XHCI_DBGCAP. A sysfs attribute under
+the xHCI device node is used to enable or disable DbC. By default,
+DbC is disabled::
+
+	root@target:/sys/bus/pci/devices/0000:00:14.0# cat dbc
+	disabled
+
+Enable DbC with the following command::
+
+	root@target:/sys/bus/pci/devices/0000:00:14.0# echo enable > dbc
+
+You can check the DbC state at anytime::
+
+	root@target:/sys/bus/pci/devices/0000:00:14.0# cat dbc
+	enabled
+
+Connect the debug target to the debug host with a USB 3.0 super-
+speed A-to-A debugging cable. You can see /dev/ttyDBC0 created
+on the debug target. You will see below kernel message lines::
+
+	root@target: tail -f /var/log/kern.log
+	[  182.730103] xhci_hcd 0000:00:14.0: DbC connected
+	[  191.169420] xhci_hcd 0000:00:14.0: DbC configured
+	[  191.169597] xhci_hcd 0000:00:14.0: DbC now attached to /dev/ttyDBC0
+
+Accordingly, the DbC state has been brought up to::
+
+	root@target:/sys/bus/pci/devices/0000:00:14.0# cat dbc
+	configured
+
+On the debug host, you will see the debug device has been enumerated.
+You will see below kernel message lines::
+
+	root@host: tail -f /var/log/kern.log
+	[   79.454780] usb 2-2.1: new SuperSpeed USB device number 3 using xhci_hcd
+	[   79.475003] usb 2-2.1: LPM exit latency is zeroed, disabling LPM.
+	[   79.475389] usb 2-2.1: New USB device found, idVendor=1d6b, idProduct=0010
+	[   79.475390] usb 2-2.1: New USB device strings: Mfr=1, Product=2, SerialNumber=3
+	[   79.475391] usb 2-2.1: Product: Linux USB Debug Target
+	[   79.475392] usb 2-2.1: Manufacturer: Linux Foundation
+	[   79.475393] usb 2-2.1: SerialNumber: 0001
+
+The debug device works now. You can use any communication or debugging
+program to talk between the host and the target.
diff --git a/Documentation/driver-api/usb/writing_usb_driver.rst b/Documentation/driver-api/usb/writing_usb_driver.rst
index 69f077dcdb78..4fe1c06b6a13 100644
--- a/Documentation/driver-api/usb/writing_usb_driver.rst
+++ b/Documentation/driver-api/usb/writing_usb_driver.rst
@@ -321,6 +321,6 @@ linux-usb-devel Mailing List Archives:
 http://marc.theaimsgroup.com/?l=linux-usb-devel
 
 Programming Guide for Linux USB Device Drivers:
-http://usb.cs.tum.edu/usbdoc
+http://lmu.web.psi.ch/docu/manuals/software_manuals/linux_sl/usb_linux_programming_guide.pdf
 
 USB Home Page: http://www.usb.org
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index c180045eb43b..7c1bb3d0c222 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -384,6 +384,9 @@ RESET
   devm_reset_control_get()
   devm_reset_controller_register()
 
+SERDEV
+  devm_serdev_device_open()
+
 SLAVE DMA ENGINE
   devm_acpi_dma_controller_register()
 
diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt
index 918972babcd8..de1dc35fe500 100644
--- a/Documentation/fault-injection/fault-injection.txt
+++ b/Documentation/fault-injection/fault-injection.txt
@@ -1,7 +1,7 @@
 Fault injection capabilities infrastructure
 ===========================================
 
-See also drivers/md/faulty.c and "every_nth" module option for scsi_debug.
+See also drivers/md/md-faulty.c and "every_nth" module option for scsi_debug.
 
 
 Available fault injection capabilities
@@ -30,6 +30,12 @@ o fail_mmc_request
   injects MMC data errors on devices permitted by setting
   debugfs entries under /sys/kernel/debug/mmc0/fail_mmc_request
 
+o fail_function
+
+  injects error return on specific functions, which are marked by
+  ALLOW_ERROR_INJECTION() macro, by setting debugfs entries
+  under /sys/kernel/debug/fail_function. No boot option supported.
+
 Configure fault-injection capabilities behavior
 -----------------------------------------------
 
@@ -123,6 +129,29 @@ configuration of fault-injection capabilities.
 	default is 'N', setting it to 'Y' will disable failure injections
 	when dealing with private (address space) futexes.
 
+- /sys/kernel/debug/fail_function/inject:
+
+	Format: { 'function-name' | '!function-name' | '' }
+	specifies the target function of error injection by name.
+	If the function name leads '!' prefix, given function is
+	removed from injection list. If nothing specified ('')
+	injection list is cleared.
+
+- /sys/kernel/debug/fail_function/injectable:
+
+	(read only) shows error injectable functions and what type of
+	error values can be specified. The error type will be one of
+	below;
+	- NULL:	retval must be 0.
+	- ERRNO: retval must be -1 to -MAX_ERRNO (-4096).
+	- ERR_NULL: retval must be 0 or -1 to -MAX_ERRNO (-4096).
+
+- /sys/kernel/debug/fail_function/<functiuon-name>/retval:
+
+	specifies the "error" return value to inject to the given
+	function for given function. This will be created when
+	user specifies new injection entry.
+
 o Boot option
 
 In order to inject faults while debugfs is not available (early boot time),
@@ -268,6 +297,45 @@ trap "echo 0 > /sys/kernel/debug/$FAILTYPE/probability" SIGINT SIGTERM EXIT
 echo "Injecting errors into the module $module... (interrupt to stop)"
 sleep 1000000
 
+------------------------------------------------------------------------------
+
+o Inject open_ctree error while btrfs mount
+
+#!/bin/bash
+
+rm -f testfile.img
+dd if=/dev/zero of=testfile.img bs=1M seek=1000 count=1
+DEVICE=$(losetup --show -f testfile.img)
+mkfs.btrfs -f $DEVICE
+mkdir -p tmpmnt
+
+FAILTYPE=fail_function
+FAILFUNC=open_ctree
+echo $FAILFUNC > /sys/kernel/debug/$FAILTYPE/inject
+echo -12 > /sys/kernel/debug/$FAILTYPE/$FAILFUNC/retval
+echo N > /sys/kernel/debug/$FAILTYPE/task-filter
+echo 100 > /sys/kernel/debug/$FAILTYPE/probability
+echo 0 > /sys/kernel/debug/$FAILTYPE/interval
+echo -1 > /sys/kernel/debug/$FAILTYPE/times
+echo 0 > /sys/kernel/debug/$FAILTYPE/space
+echo 1 > /sys/kernel/debug/$FAILTYPE/verbose
+
+mount -t btrfs $DEVICE tmpmnt
+if [ $? -ne 0 ]
+then
+	echo "SUCCESS!"
+else
+	echo "FAILED!"
+	umount tmpmnt
+fi
+
+echo > /sys/kernel/debug/$FAILTYPE/inject
+
+rmdir tmpmnt
+losetup -d $DEVICE
+rm testfile.img
+
+
 Tool to run command with failslab or fail_page_alloc
 ----------------------------------------------------
 In order to make it easier to accomplish the tasks mentioned above, we can use
diff --git a/Documentation/features/debug/KASAN/arch-support.txt b/Documentation/features/debug/KASAN/arch-support.txt
index f377290fe48e..3406fae833c3 100644
--- a/Documentation/features/debug/KASAN/arch-support.txt
+++ b/Documentation/features/debug/KASAN/arch-support.txt
@@ -35,5 +35,5 @@
     |          um: | TODO |
     |   unicore32: | TODO |
     |         x86: |  ok  | 64-bit only
-    |      xtensa: | TODO |
+    |      xtensa: |  ok  |
     -----------------------
diff --git a/Documentation/features/debug/stackprotector/arch-support.txt b/Documentation/features/debug/stackprotector/arch-support.txt
index d7acd7bd3619..59a4c9ffb7f3 100644
--- a/Documentation/features/debug/stackprotector/arch-support.txt
+++ b/Documentation/features/debug/stackprotector/arch-support.txt
@@ -35,5 +35,5 @@
     |          um: | TODO |
     |   unicore32: | TODO |
     |         x86: |  ok  |
-    |      xtensa: | TODO |
+    |      xtensa: |  ok  |
     -----------------------
diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt
index 3be3b266be41..70cb68bed2e8 100644
--- a/Documentation/filesystems/dax.txt
+++ b/Documentation/filesystems/dax.txt
@@ -46,7 +46,6 @@ stall the CPU for an extended period, you should also not attempt to
 implement direct_access.
 
 These block devices may be used for inspiration:
-- axonram: Axon DDR2 device driver
 - brd: RAM backed block device driver
 - dcssblk: s390 dcss block device driver
 - pmem: NVDIMM persistent memory driver
diff --git a/Documentation/filesystems/ext2.txt b/Documentation/filesystems/ext2.txt
index 55755395d3dc..81c0becab225 100644
--- a/Documentation/filesystems/ext2.txt
+++ b/Documentation/filesystems/ext2.txt
@@ -49,12 +49,10 @@ sb=n				Use alternate superblock at this location.
 
 user_xattr			Enable "user." POSIX Extended Attributes
 				(requires CONFIG_EXT2_FS_XATTR).
-				See also http://acl.bestbits.at
 nouser_xattr			Don't support "user." extended attributes.
 
 acl				Enable POSIX Access Control Lists support
 				(requires CONFIG_EXT2_FS_POSIX_ACL).
-				See also http://acl.bestbits.at
 noacl				Don't support POSIX ACLs.
 
 nobh				Do not attach buffer_heads to file pagecache.
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 75236c0c2ac2..8cd63e16f171 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -202,15 +202,14 @@ inode_readahead_blks=n	This tuning parameter controls the maximum
 			the buffer cache.  The default value is 32 blocks.
 
 nouser_xattr		Disables Extended User Attributes.  See the
-			attr(5) manual page and http://acl.bestbits.at/
-			for more information about extended attributes.
+			attr(5) manual page for more information about
+			extended attributes.
 
 noacl			This option disables POSIX Access Control List
 			support. If ACL support is enabled in the kernel
 			configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL is
 			enabled by default on mount. See the acl(5) manual
-			page and http://acl.bestbits.at/ for more information
-			about acl.
+			page for more information about acl.
 
 bsddf		(*)	Make 'df' act like BSD.
 minixdf			Make 'df' act like Minix.
diff --git a/Documentation/filesystems/nfs/Exporting b/Documentation/filesystems/nfs/Exporting
index 520a4becb75c..63889149f532 100644
--- a/Documentation/filesystems/nfs/Exporting
+++ b/Documentation/filesystems/nfs/Exporting
@@ -56,13 +56,25 @@ a/ A dentry flag DCACHE_DISCONNECTED which is set on
    any dentry that might not be part of the proper prefix.
    This is set when anonymous dentries are created, and cleared when a
    dentry is noticed to be a child of a dentry which is in the proper
-   prefix. 
-
-b/ A per-superblock list "s_anon" of dentries which are the roots of
-   subtrees that are not in the proper prefix.  These dentries, as
-   well as the proper prefix, need to be released at unmount time.  As
-   these dentries will not be hashed, they are linked together on the
-   d_hash list_head.
+   prefix.  If the refcount on a dentry with this flag set
+   becomes zero, the dentry is immediately discarded, rather than being
+   kept in the dcache.  If a dentry that is not already in the dcache
+   is repeatedly accessed by filehandle (as NFSD might do), an new dentry
+   will be a allocated for each access, and discarded at the end of
+   the access.
+
+   Note that such a dentry can acquire children, name, ancestors, etc.
+   without losing DCACHE_DISCONNECTED - that flag is only cleared when
+   subtree is successfully reconnected to root.  Until then dentries
+   in such subtree are retained only as long as there are references;
+   refcount reaching zero means immediate eviction, same as for unhashed
+   dentries.  That guarantees that we won't need to hunt them down upon
+   umount.
+
+b/ A primitive for creation of secondary roots - d_obtain_root(inode).
+   Those do _not_ bear DCACHE_DISCONNECTED.  They are placed on the
+   per-superblock list (->s_roots), so they can be located at umount
+   time for eviction purposes.
 
 c/ Helper routines to allocate anonymous dentries, and to help attach
    loose directory dentries at lookup time. They are:
@@ -77,7 +89,6 @@ c/ Helper routines to allocate anonymous dentries, and to help attach
       (such as an anonymous one created by d_obtain_alias), if appropriate.
       It returns NULL when the passed-in dentry is used, following the calling
       convention of ->lookup.
-
  
 Filesystem Issues
 -----------------
diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt
index c0727dc36271..f2f3f8592a6f 100644
--- a/Documentation/filesystems/nilfs2.txt
+++ b/Documentation/filesystems/nilfs2.txt
@@ -25,8 +25,8 @@ available from the following download page.  At least "mkfs.nilfs2",
 cleaner or garbage collector) are required.  Details on the tools are
 described in the man pages included in the package.
 
-Project web page:    http://nilfs.sourceforge.net/
-Download page:       http://nilfs.sourceforge.net/en/download.html
+Project web page:    https://nilfs.sourceforge.io/
+Download page:       https://nilfs.sourceforge.io/en/download.html
 List info:           http://vger.kernel.org/vger-lists.html#linux-nilfs
 
 Caveats
diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt
index 8caa60734647..e6a5f4912b6d 100644
--- a/Documentation/filesystems/overlayfs.txt
+++ b/Documentation/filesystems/overlayfs.txt
@@ -156,6 +156,40 @@ handle it in two different ways:
    root of the overlay.  Finally the directory is moved to the new
    location.
 
+There are several ways to tune the "redirect_dir" feature.
+
+Kernel config options:
+
+- OVERLAY_FS_REDIRECT_DIR:
+    If this is enabled, then redirect_dir is turned on by  default.
+- OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW:
+    If this is enabled, then redirects are always followed by default. Enabling
+    this results in a less secure configuration.  Enable this option only when
+    worried about backward compatibility with kernels that have the redirect_dir
+    feature and follow redirects even if turned off.
+
+Module options (can also be changed through /sys/module/overlay/parameters/*):
+
+- "redirect_dir=BOOL":
+    See OVERLAY_FS_REDIRECT_DIR kernel config option above.
+- "redirect_always_follow=BOOL":
+    See OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW kernel config option above.
+- "redirect_max=NUM":
+    The maximum number of bytes in an absolute redirect (default is 256).
+
+Mount options:
+
+- "redirect_dir=on":
+    Redirects are enabled.
+- "redirect_dir=follow":
+    Redirects are not created, but followed.
+- "redirect_dir=off":
+    Redirects are not created and only followed if "redirect_always_follow"
+    feature is enabled in the kernel/module config.
+- "redirect_dir=nofollow":
+    Redirects are not created and not followed (equivalent to "redirect_dir=off"
+    if "redirect_always_follow" feature is not enabled).
+
 Non-directories
 ---------------
 
diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt
index 9a3658cc399e..a1426cabcef1 100644
--- a/Documentation/filesystems/sysfs.txt
+++ b/Documentation/filesystems/sysfs.txt
@@ -154,8 +154,8 @@ static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr,
         if (dev_attr->show)
                 ret = dev_attr->show(dev, dev_attr, buf);
         if (ret >= (ssize_t)PAGE_SIZE) {
-                print_symbol("dev_attr_show: %s returned bad count\n",
-                                (unsigned long)dev_attr->show);
+                printk("dev_attr_show: %pS returned bad count\n",
+                                dev_attr->show);
         }
         return ret;
 }
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index cf51360e3a9f..91031298beb1 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -344,4 +344,4 @@ the following:
 	   characters in the final slot are set to Unicode 0xFFFF.
 
 Finally, note that the extended name is stored in Unicode.  Each Unicode
-character takes two bytes.
+character takes either two or four bytes, UTF-16LE encoded.
diff --git a/Documentation/fpga/fpga-mgr.txt b/Documentation/fpga/fpga-mgr.txt
index 78f197fadfd1..cc6413ed6fc9 100644
--- a/Documentation/fpga/fpga-mgr.txt
+++ b/Documentation/fpga/fpga-mgr.txt
@@ -11,61 +11,65 @@ hidden away in a low level driver which registers a set of ops with the core.
 The FPGA image data itself is very manufacturer specific, but for our purposes
 it's just binary data.  The FPGA manager core won't parse it.
 
+The FPGA image to be programmed can be in a scatter gather list, a single
+contiguous buffer, or a firmware file.  Because allocating contiguous kernel
+memory for the buffer should be avoided, users are encouraged to use a scatter
+gather list instead if possible.
+
+The particulars for programming the image are presented in a structure (struct
+fpga_image_info).  This struct contains parameters such as pointers to the
+FPGA image as well as image-specific particulars such as whether the image was
+built for full or partial reconfiguration.
 
 API Functions:
 ==============
 
-To program the FPGA from a file or from a buffer:
--------------------------------------------------
-
-	int fpga_mgr_buf_load(struct fpga_manager *mgr,
-			      struct fpga_image_info *info,
-		              const char *buf, size_t count);
-
-Load the FPGA from an image which exists as a contiguous buffer in
-memory. Allocating contiguous kernel memory for the buffer should be avoided,
-users are encouraged to use the _sg interface instead of this.
-
-        int fpga_mgr_buf_load_sg(struct fpga_manager *mgr,
-				 struct fpga_image_info *info,
-				 struct sg_table *sgt);
+To program the FPGA:
+--------------------
 
-Load the FPGA from an image from non-contiguous in memory. Callers can
-construct a sg_table using alloc_page backed memory.
+	int fpga_mgr_load(struct fpga_manager *mgr,
+			  struct fpga_image_info *info);
 
-	int fpga_mgr_firmware_load(struct fpga_manager *mgr,
-				   struct fpga_image_info *info,
-		                   const char *image_name);
-
-Load the FPGA from an image which exists as a file.  The image file must be on
-the firmware search path (see the firmware class documentation).  If successful,
+Load the FPGA from an image which is indicated in the info.  If successful,
 the FPGA ends up in operating mode.  Return 0 on success or a negative error
 code.
 
-A FPGA design contained in a FPGA image file will likely have particulars that
-affect how the image is programmed to the FPGA.  These are contained in struct
-fpga_image_info.  Currently the only such particular is a single flag bit
-indicating whether the image is for full or partial reconfiguration.
+To allocate or free a struct fpga_image_info:
+---------------------------------------------
+
+	struct fpga_image_info *fpga_image_info_alloc(struct device *dev);
+
+	void fpga_image_info_free(struct fpga_image_info *info);
 
 To get/put a reference to a FPGA manager:
 -----------------------------------------
 
 	struct fpga_manager *of_fpga_mgr_get(struct device_node *node);
 	struct fpga_manager *fpga_mgr_get(struct device *dev);
+	void fpga_mgr_put(struct fpga_manager *mgr);
 
-Given a DT node or device, get an exclusive reference to a FPGA manager.
+Given a DT node or device, get a reference to a FPGA manager.  This pointer
+can be saved until you are ready to program the FPGA.  fpga_mgr_put releases
+the reference.
 
-	void fpga_mgr_put(struct fpga_manager *mgr);
 
-Release the reference.
+To get exclusive control of a FPGA manager:
+-------------------------------------------
+
+	int fpga_mgr_lock(struct fpga_manager *mgr);
+	void fpga_mgr_unlock(struct fpga_manager *mgr);
+
+The user should call fpga_mgr_lock and verify that it returns 0 before
+attempting to program the FPGA.  Likewise, the user should call
+fpga_mgr_unlock when done programming the FPGA.
 
 
 To register or unregister the low level FPGA-specific driver:
 -------------------------------------------------------------
 
 	int fpga_mgr_register(struct device *dev, const char *name,
-		              const struct fpga_manager_ops *mops,
-		              void *priv);
+			      const struct fpga_manager_ops *mops,
+			      void *priv);
 
 	void fpga_mgr_unregister(struct device *dev);
 
@@ -75,62 +79,58 @@ device."
 
 How to write an image buffer to a supported FPGA
 ================================================
-/* Include to get the API */
 #include <linux/fpga/fpga-mgr.h>
 
-/* device node that specifies the FPGA manager to use */
-struct device_node *mgr_node = ...
+struct fpga_manager *mgr;
+struct fpga_image_info *info;
+int ret;
 
-/* FPGA image is in this buffer.  count is size of the buffer. */
-char *buf = ...
-int count = ...
+/*
+ * Get a reference to FPGA manager.  The manager is not locked, so you can
+ * hold onto this reference without it preventing programming.
+ *
+ * This example uses the device node of the manager.  Alternatively, use
+ * fpga_mgr_get(dev) instead if you have the device.
+ */
+mgr = of_fpga_mgr_get(mgr_node);
 
 /* struct with information about the FPGA image to program. */
-struct fpga_image_info info;
+info = fpga_image_info_alloc(dev);
 
 /* flags indicates whether to do full or partial reconfiguration */
-info.flags = 0;
+info->flags = FPGA_MGR_PARTIAL_RECONFIG;
 
-int ret;
+/*
+ * At this point, indicate where the image is. This is pseudo-code; you're
+ * going to use one of these three.
+ */
+if (image is in a scatter gather table) {
 
-/* Get exclusive control of FPGA manager */
-struct fpga_manager *mgr = of_fpga_mgr_get(mgr_node);
+	info->sgt = [your scatter gather table]
 
-/* Load the buffer to the FPGA */
-ret = fpga_mgr_buf_load(mgr, &info, buf, count);
-
-/* Release the FPGA manager */
-fpga_mgr_put(mgr);
-
-
-How to write an image file to a supported FPGA
-==============================================
-/* Include to get the API */
-#include <linux/fpga/fpga-mgr.h>
+} else if (image is in a buffer) {
 
-/* device node that specifies the FPGA manager to use */
-struct device_node *mgr_node = ...
+	info->buf = [your image buffer]
+	info->count = [image buffer size]
 
-/* FPGA image is in this file which is in the firmware search path */
-const char *path = "fpga-image-9.rbf"
+} else if (image is in a firmware file) {
 
-/* struct with information about the FPGA image to program. */
-struct fpga_image_info info;
-
-/* flags indicates whether to do full or partial reconfiguration */
-info.flags = 0;
+	info->firmware_name = devm_kstrdup(dev, firmware_name, GFP_KERNEL);
 
-int ret;
+}
 
 /* Get exclusive control of FPGA manager */
-struct fpga_manager *mgr = of_fpga_mgr_get(mgr_node);
+ret = fpga_mgr_lock(mgr);
 
-/* Get the firmware image (path) and load it to the FPGA */
-ret = fpga_mgr_firmware_load(mgr, &info, path);
+/* Load the buffer to the FPGA */
+ret = fpga_mgr_buf_load(mgr, &info, buf, count);
 
 /* Release the FPGA manager */
+fpga_mgr_unlock(mgr);
 fpga_mgr_put(mgr);
 
+/* Deallocate the image info if you're done with it */
+fpga_image_info_free(info);
 
 How to support a new FPGA device
 ================================
diff --git a/Documentation/fpga/fpga-region.txt b/Documentation/fpga/fpga-region.txt
new file mode 100644
index 000000000000..139a02ba1ff6
--- /dev/null
+++ b/Documentation/fpga/fpga-region.txt
@@ -0,0 +1,95 @@
+FPGA Regions
+
+Alan Tull 2017
+
+CONTENTS
+ - Introduction
+ - The FPGA region API
+ - Usage example
+
+Introduction
+============
+
+This document is meant to be an brief overview of the FPGA region API usage.  A
+more conceptual look at regions can be found in [1].
+
+For the purposes of this API document, let's just say that a region associates
+an FPGA Manager and a bridge (or bridges) with a reprogrammable region of an
+FPGA or the whole FPGA.  The API provides a way to register a region and to
+program a region.
+
+Currently the only layer above fpga-region.c in the kernel is the Device Tree
+support (of-fpga-region.c) described in [1].  The DT support layer uses regions
+to program the FPGA and then DT to handle enumeration.  The common region code
+is intended to be used by other schemes that have other ways of accomplishing
+enumeration after programming.
+
+An fpga-region can be set up to know the following things:
+* which FPGA manager to use to do the programming
+* which bridges to disable before programming and enable afterwards.
+
+Additional info needed to program the FPGA image is passed in the struct
+fpga_image_info [2] including:
+* pointers to the image as either a scatter-gather buffer, a contiguous
+  buffer, or the name of firmware file
+* flags indicating specifics such as whether the image if for partial
+  reconfiguration.
+
+===================
+The FPGA region API
+===================
+
+To register or unregister a region:
+-----------------------------------
+
+	int fpga_region_register(struct device *dev,
+				 struct fpga_region *region);
+	int fpga_region_unregister(struct fpga_region *region);
+
+An example of usage can be seen in the probe function of [3]
+
+To program an FPGA:
+-------------------
+	int fpga_region_program_fpga(struct fpga_region *region);
+
+This function operates on info passed in the fpga_image_info
+(region->info).
+
+This function will attempt to:
+ * lock the region's mutex
+ * lock the region's FPGA manager
+ * build a list of FPGA bridges if a method has been specified to do so
+ * disable the bridges
+ * program the FPGA
+ * re-enable the bridges
+ * release the locks
+
+=============
+Usage example
+=============
+
+First, allocate the info struct:
+
+	info = fpga_image_info_alloc(dev);
+	if (!info)
+		return -ENOMEM;
+
+Set flags as needed, i.e.
+
+	info->flags |= FPGA_MGR_PARTIAL_RECONFIG;
+
+Point to your FPGA image, such as:
+
+	info->sgt = &sgt;
+
+Add info to region and do the programming:
+
+	region->info = info;
+	ret = fpga_region_program_fpga(region);
+
+Then enumerate whatever hardware has appeared in the FPGA.
+
+--
+[1] ../devicetree/bindings/fpga/fpga-region.txt
+[2] ./fpga-mgr.txt
+[3] ../../drivers/fpga/of-fpga-region.c
diff --git a/Documentation/fpga/overview.txt b/Documentation/fpga/overview.txt
new file mode 100644
index 000000000000..0f1236e7e675
--- /dev/null
+++ b/Documentation/fpga/overview.txt
@@ -0,0 +1,23 @@
+Linux kernel FPGA support
+
+Alan Tull 2017
+
+The main point of this project has been to separate the out the upper layers
+that know when to reprogram a FPGA from the lower layers that know how to
+reprogram a specific FPGA device.  The intention is to make this manufacturer
+agnostic, understanding that of course the FPGA images are very device specific
+themselves.
+
+The framework in the kernel includes:
+* low level FPGA manager drivers that know how to program a specific device
+* the fpga-mgr framework they are registered with
+* low level FPGA bridge drivers for hard/soft bridges which are intended to
+  be disable during FPGA programming
+* the fpga-bridge framework they are registered with
+* the fpga-region framework which associates and controls managers and bridges
+  as reconfigurable regions
+* the of-fpga-region support for reprogramming FPGAs when device tree overlays
+  are applied.
+
+I would encourage you the user to add code that creates FPGA regions rather
+that trying to control managers and bridges separately.
diff --git a/Documentation/gpio/board.txt b/Documentation/gpio/board.txt
index a0f61898d493..659bb19f5b3c 100644
--- a/Documentation/gpio/board.txt
+++ b/Documentation/gpio/board.txt
@@ -2,6 +2,7 @@ GPIO Mappings
 =============
 
 This document explains how GPIOs can be assigned to given devices and functions.
+
 Note that it only applies to the new descriptor-based interface. For a
 description of the deprecated integer-based GPIO interface please refer to
 gpio-legacy.txt (actually, there is no real mapping possible with the old
@@ -49,7 +50,7 @@ This property will make GPIOs 15, 16 and 17 available to the driver under the
 
 	power = gpiod_get(dev, "power", GPIOD_OUT_HIGH);
 
-The led GPIOs will be active-high, while the power GPIO will be active-low (i.e.
+The led GPIOs will be active high, while the power GPIO will be active low (i.e.
 gpiod_is_active_low(power) will be true).
 
 The second parameter of the gpiod_get() functions, the con_id string, has to be
@@ -122,9 +123,14 @@ where
 	can be NULL, in which case it will match any function.
   - idx is the index of the GPIO within the function.
   - flags is defined to specify the following properties:
-	* GPIOF_ACTIVE_LOW	- to configure the GPIO as active-low
-	* GPIOF_OPEN_DRAIN	- GPIO pin is open drain type.
-	* GPIOF_OPEN_SOURCE	- GPIO pin is open source type.
+	* GPIO_ACTIVE_HIGH	- GPIO line is active high
+	* GPIO_ACTIVE_LOW	- GPIO line is active low
+	* GPIO_OPEN_DRAIN	- GPIO line is set up as open drain
+	* GPIO_OPEN_SOURCE	- GPIO line is set up as open source
+	* GPIO_PERSISTENT	- GPIO line is persistent during
+				  suspend/resume and maintains its value
+	* GPIO_TRANSITORY	- GPIO line is transitory and may loose its
+				  electrical state during suspend/resume
 
 In the future, these flags might be extended to support more properties.
 
diff --git a/Documentation/gpio/consumer.txt b/Documentation/gpio/consumer.txt
index 63e1bd1d88e3..d53e5b5cfc9c 100644
--- a/Documentation/gpio/consumer.txt
+++ b/Documentation/gpio/consumer.txt
@@ -66,6 +66,15 @@ for the GPIO. Values can be:
 * GPIOD_IN to initialize the GPIO as input.
 * GPIOD_OUT_LOW to initialize the GPIO as output with a value of 0.
 * GPIOD_OUT_HIGH to initialize the GPIO as output with a value of 1.
+* GPIOD_OUT_LOW_OPEN_DRAIN same as GPIOD_OUT_LOW but also enforce the line
+  to be electrically used with open drain.
+* GPIOD_OUT_HIGH_OPEN_DRAIN same as GPIOD_OUT_HIGH but also enforce the line
+  to be electrically used with open drain.
+
+The two last flags are used for use cases where open drain is mandatory, such
+as I2C: if the line is not already configured as open drain in the mappings
+(see board.txt), then open drain will be enforced anyway and a warning will be
+printed that the board configuration needs to be updated to match the use case.
 
 Both functions return either a valid GPIO descriptor, or an error code checkable
 with IS_ERR() (they will never return a NULL pointer). -ENOENT will be returned
@@ -184,7 +193,7 @@ A driver can also query the current direction of a GPIO:
 
 	int gpiod_get_direction(const struct gpio_desc *desc)
 
-This function will return either GPIOF_DIR_IN or GPIOF_DIR_OUT.
+This function returns 0 for output, 1 for input, or an error code in case of error.
 
 Be aware that there is no default direction for GPIOs. Therefore, **using a GPIO
 without setting its direction first is illegal and will result in undefined
@@ -240,59 +249,71 @@ that can't be accessed from hardIRQ handlers, these calls act the same as the
 spinlock-safe calls.
 
 
-Active-low State and Raw GPIO Values
-------------------------------------
-Device drivers like to manage the logical state of a GPIO, i.e. the value their
-device will actually receive, no matter what lies between it and the GPIO line.
-In some cases, it might make sense to control the actual GPIO line value. The
-following set of calls ignore the active-low property of a GPIO and work on the
-raw line value:
-
-	int gpiod_get_raw_value(const struct gpio_desc *desc)
-	void gpiod_set_raw_value(struct gpio_desc *desc, int value)
-	int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc)
-	void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value)
-	int gpiod_direction_output_raw(struct gpio_desc *desc, int value)
-
-The active-low state of a GPIO can also be queried using the following call:
-
-	int gpiod_is_active_low(const struct gpio_desc *desc)
-
-Note that these functions should only be used with great moderation ; a driver
-should not have to care about the physical line level.
-
-
-The active-low property
------------------------
-
-As a driver should not have to care about the physical line level, all of the
+The active low and open drain semantics
+---------------------------------------
+As a consumer should not have to care about the physical line level, all of the
 gpiod_set_value_xxx() or gpiod_set_array_value_xxx() functions operate with
-the *logical* value. With this they take the active-low property into account.
-This means that they check whether the GPIO is configured to be active-low,
+the *logical* value. With this they take the active low property into account.
+This means that they check whether the GPIO is configured to be active low,
 and if so, they manipulate the passed value before the physical line level is
 driven.
 
+The same is applicable for open drain or open source output lines: those do not
+actively drive their output high (open drain) or low (open source), they just
+switch their output to a high impedance value. The consumer should not need to
+care. (For details read about open drain in driver.txt.)
+
 With this, all the gpiod_set_(array)_value_xxx() functions interpret the
-parameter "value" as "active" ("1") or "inactive" ("0"). The physical line
+parameter "value" as "asserted" ("1") or "de-asserted" ("0"). The physical line
 level will be driven accordingly.
 
-As an example, if the active-low property for a dedicated GPIO is set, and the
-gpiod_set_(array)_value_xxx() passes "active" ("1"), the physical line level
+As an example, if the active low property for a dedicated GPIO is set, and the
+gpiod_set_(array)_value_xxx() passes "asserted" ("1"), the physical line level
 will be driven low.
 
 To summarize:
 
-Function (example)               active-low property  physical line
-gpiod_set_raw_value(desc, 0);        don't care           low
-gpiod_set_raw_value(desc, 1);        don't care           high
-gpiod_set_value(desc, 0);       default (active-high)     low
-gpiod_set_value(desc, 1);       default (active-high)     high
-gpiod_set_value(desc, 0);             active-low          high
-gpiod_set_value(desc, 1);             active-low          low
-
-Please note again that the set_raw/get_raw functions should be avoided as much
-as possible, especially by drivers which should not care about the actual
-physical line level and worry about the logical value instead.
+Function (example)                 line property          physical line
+gpiod_set_raw_value(desc, 0);      don't care             low
+gpiod_set_raw_value(desc, 1);      don't care             high
+gpiod_set_value(desc, 0);          default (active high)  low
+gpiod_set_value(desc, 1);          default (active high)  high
+gpiod_set_value(desc, 0);          active low             high
+gpiod_set_value(desc, 1);          active low             low
+gpiod_set_value(desc, 0);          default (active high)  low
+gpiod_set_value(desc, 1);          default (active high)  high
+gpiod_set_value(desc, 0);          open drain             low
+gpiod_set_value(desc, 1);          open drain             high impedance
+gpiod_set_value(desc, 0);          open source            high impedance
+gpiod_set_value(desc, 1);          open source            high
+
+It is possible to override these semantics using the *set_raw/'get_raw functions
+but it should be avoided as much as possible, especially by system-agnostic drivers
+which should not need to care about the actual physical line level and worry about
+the logical value instead.
+
+
+Accessing raw GPIO values
+-------------------------
+Consumers exist that need to manage the logical state of a GPIO line, i.e. the value
+their device will actually receive, no matter what lies between it and the GPIO
+line.
+
+The following set of calls ignore the active-low or open drain property of a GPIO and
+work on the raw line value:
+
+	int gpiod_get_raw_value(const struct gpio_desc *desc)
+	void gpiod_set_raw_value(struct gpio_desc *desc, int value)
+	int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc)
+	void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value)
+	int gpiod_direction_output_raw(struct gpio_desc *desc, int value)
+
+The active low state of a GPIO can also be queried using the following call:
+
+	int gpiod_is_active_low(const struct gpio_desc *desc)
+
+Note that these functions should only be used with great moderation; a driver
+should not have to care about the physical line level or open drain semantics.
 
 
 Access multiple GPIOs with a single function call
diff --git a/Documentation/gpio/driver.txt b/Documentation/gpio/driver.txt
index d8de1c7de85a..3392a0fd4c23 100644
--- a/Documentation/gpio/driver.txt
+++ b/Documentation/gpio/driver.txt
@@ -88,6 +88,10 @@ ending up in the pin control back-end "behind" the GPIO controller, usually
 closer to the actual pins. This way the pin controller can manage the below
 listed GPIO configurations.
 
+If a pin controller back-end is used, the GPIO controller or hardware
+description needs to provide "GPIO ranges" mapping the GPIO line offsets to pin
+numbers on the pin controller so they can properly cross-reference each other.
+
 
 GPIOs with debounce support
 ---------------------------
diff --git a/Documentation/gpio/drivers-on-gpio.txt b/Documentation/gpio/drivers-on-gpio.txt
index 9a78d385b92e..a2ccbab12eb7 100644
--- a/Documentation/gpio/drivers-on-gpio.txt
+++ b/Documentation/gpio/drivers-on-gpio.txt
@@ -28,11 +28,6 @@ hardware descriptions such as device tree or ACPI:
 - gpio-beeper: drivers/input/misc/gpio-beeper.c is used to provide a beep from
   an external speaker connected to a GPIO line.
 
-- gpio-tilt-polled: drivers/input/misc/gpio_tilt_polled.c provides tilt
-  detection switches using GPIO, which is useful for your homebrewn pinball
-  machine if for nothing else. It can detect different tilt angles of the
-  monitored object.
-
 - extcon-gpio: drivers/extcon/extcon-gpio.c is used when you need to read an
   external connector status, such as a headset line for an audio driver or an
   HDMI connector. It will provide a better userspace sysfs interface than GPIO.
diff --git a/Documentation/gpio/sysfs.txt b/Documentation/gpio/sysfs.txt
index aeab01aa4d00..6cdeab8650cd 100644
--- a/Documentation/gpio/sysfs.txt
+++ b/Documentation/gpio/sysfs.txt
@@ -1,6 +1,17 @@
 GPIO Sysfs Interface for Userspace
 ==================================
 
+THIS ABI IS DEPRECATED, THE ABI DOCUMENTATION HAS BEEN MOVED TO
+Documentation/ABI/obsolete/sysfs-gpio AND NEW USERSPACE CONSUMERS
+ARE SUPPOSED TO USE THE CHARACTER DEVICE ABI. THIS OLD SYSFS ABI WILL
+NOT BE DEVELOPED (NO NEW FEATURES), IT WILL JUST BE MAINTAINED.
+
+Refer to the examples in tools/gpio/* for an introduction to the new
+character device ABI. Also see the userspace header in
+include/uapi/linux/gpio.h
+
+The deprecated sysfs ABI
+------------------------
 Platforms which use the "gpiolib" implementors framework may choose to
 configure a sysfs user interface to GPIOs. This is different from the
 debugfs interface, since it provides control over GPIO direction and
diff --git a/Documentation/gpu/drm-kms-helpers.rst b/Documentation/gpu/drm-kms-helpers.rst
index 13dd237418cc..e37557b30f62 100644
--- a/Documentation/gpu/drm-kms-helpers.rst
+++ b/Documentation/gpu/drm-kms-helpers.rst
@@ -74,15 +74,6 @@ Helper Functions Reference
 .. kernel-doc:: drivers/gpu/drm/drm_atomic_helper.c
    :export:
 
-Legacy CRTC/Modeset Helper Functions Reference
-==============================================
-
-.. kernel-doc:: drivers/gpu/drm/drm_crtc_helper.c
-   :doc: overview
-
-.. kernel-doc:: drivers/gpu/drm/drm_crtc_helper.c
-   :export:
-
 Simple KMS Helper Reference
 ===========================
 
@@ -163,6 +154,9 @@ Panel Helper Reference
 .. kernel-doc:: drivers/gpu/drm/drm_panel.c
    :export:
 
+.. kernel-doc:: drivers/gpu/drm/drm_panel_orientation_quirks.c
+   :export:
+
 Display Port Helper Functions Reference
 =======================================
 
@@ -279,15 +273,6 @@ Flip-work Helper Reference
 .. kernel-doc:: drivers/gpu/drm/drm_flip_work.c
    :export:
 
-Plane Helper Reference
-======================
-
-.. kernel-doc:: drivers/gpu/drm/drm_plane_helper.c
-   :doc: overview
-
-.. kernel-doc:: drivers/gpu/drm/drm_plane_helper.c
-   :export:
-
 Auxiliary Modeset Helpers
 =========================
 
@@ -305,3 +290,21 @@ Framebuffer GEM Helper Reference
 
 .. kernel-doc:: drivers/gpu/drm/drm_gem_framebuffer_helper.c
    :export:
+
+Legacy Plane Helper Reference
+=============================
+
+.. kernel-doc:: drivers/gpu/drm/drm_plane_helper.c
+   :doc: overview
+
+.. kernel-doc:: drivers/gpu/drm/drm_plane_helper.c
+   :export:
+
+Legacy CRTC/Modeset Helper Functions Reference
+==============================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_crtc_helper.c
+   :doc: overview
+
+.. kernel-doc:: drivers/gpu/drm/drm_crtc_helper.c
+   :export:
diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst
index 307284125d7a..2dcf5b42015d 100644
--- a/Documentation/gpu/drm-kms.rst
+++ b/Documentation/gpu/drm-kms.rst
@@ -263,14 +263,20 @@ Taken all together there's two consequences for the atomic design:
 
 - An atomic update is assembled and validated as an entirely free-standing pile
   of structures within the :c:type:`drm_atomic_state <drm_atomic_state>`
-  container. Again drivers can subclass that container for their own state
-  structure tracking needs. Only when a state is committed is it applied to the
-  driver and modeset objects. This way rolling back an update boils down to
-  releasing memory and unreferencing objects like framebuffers.
+  container. Driver private state structures are also tracked in the same
+  structure; see the next chapter.  Only when a state is committed is it applied
+  to the driver and modeset objects. This way rolling back an update boils down
+  to releasing memory and unreferencing objects like framebuffers.
 
 Read on in this chapter, and also in :ref:`drm_atomic_helper` for more detailed
 coverage of specific topics.
 
+Handling Driver Private State
+-----------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_atomic.c
+   :doc: handling driver private state
+
 Atomic Mode Setting Function Reference
 --------------------------------------
 
diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 2e7ee0313c1c..41dc881b00dc 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -341,19 +341,16 @@ GuC
 GuC-specific firmware loader
 ----------------------------
 
-.. kernel-doc:: drivers/gpu/drm/i915/intel_guc_loader.c
-   :doc: GuC-specific firmware loader
-
-.. kernel-doc:: drivers/gpu/drm/i915/intel_guc_loader.c
+.. kernel-doc:: drivers/gpu/drm/i915/intel_guc_fw.c
    :internal:
 
 GuC-based command submission
 ----------------------------
 
-.. kernel-doc:: drivers/gpu/drm/i915/i915_guc_submission.c
+.. kernel-doc:: drivers/gpu/drm/i915/intel_guc_submission.c
    :doc: GuC-based command submission
 
-.. kernel-doc:: drivers/gpu/drm/i915/i915_guc_submission.c
+.. kernel-doc:: drivers/gpu/drm/i915/intel_guc_submission.c
    :internal:
 
 GuC Firmware Layout
diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst
index 36625aa66c27..1e593370f64f 100644
--- a/Documentation/gpu/todo.rst
+++ b/Documentation/gpu/todo.rst
@@ -179,8 +179,39 @@ don't do this, drivers used dev_info/warn/err to make this differentiation. We
 now have DRM_DEV_* variants of the drm print macros, so we can start to convert
 those drivers back to using drm-formwatted specific log messages.
 
+Before you start this conversion please contact the relevant maintainers to make
+sure your work will be merged - not everyone agrees that the DRM dmesg macros
+are better.
+
 Contact: Sean Paul, Maintainer of the driver you plan to convert
 
+Convert drivers to use simple modeset suspend/resume
+----------------------------------------------------
+
+Most drivers (except i915 and nouveau) that use
+drm_atomic_helper_suspend/resume() can probably be converted to use
+drm_mode_config_helper_suspend/resume().
+
+Contact: Maintainer of the driver you plan to convert
+
+Convert drivers to use drm_fb_helper_fbdev_setup/teardown()
+-----------------------------------------------------------
+
+Most drivers can use drm_fb_helper_fbdev_setup() except maybe:
+
+- amdgpu which has special logic to decide whether to call
+  drm_helper_disable_unused_functions()
+
+- armada which isn't atomic and doesn't call
+  drm_helper_disable_unused_functions()
+
+- i915 which calls drm_fb_helper_initial_config() in a worker
+
+Drivers that use drm_framebuffer_remove() to clean up the fbdev framebuffer can
+probably use drm_fb_helper_fbdev_teardown().
+
+Contact: Maintainer of the driver you plan to convert
+
 Core refactorings
 =================
 
@@ -382,11 +413,6 @@ those drivers as simple as possible, so lots of room for refactoring:
   one of the ideas for having a shared dsi/dbi helper, abstracting away the
   transport details more.
 
-- tinydrm_lastclose could be drm_fb_helper_lastclose. Only thing we need
-  for that is to store the drm_fb_helper pointer somewhere in
-  drm_device->mode_config. And then we could roll that out to all the
-  drivers.
-
 - tinydrm_gem_cma_prime_import_sg_table should probably go into the cma
   helpers, as a _vmapped variant (since not every driver needs the vmap).
   And tinydrm_gem_cma_free_object could the be merged into
@@ -400,11 +426,6 @@ those drivers as simple as possible, so lots of room for refactoring:
   a drm_device wrong. Doesn't matter, since everyone else gets it wrong
   too :-)
 
-- With the fbdev pointer in dev->mode_config we could also make
-  suspend/resume helpers entirely generic, at least if we add a
-  dev->mode_config.suspend_state. We could even provide a generic pm_ops
-  structure with those.
-
 - also rework the drm_framebuffer_funcs->dirty hook wire-up, see above.
 
 Contact: Noralf Trønnes, Daniel Vetter
diff --git a/Documentation/hwmon/lm25066 b/Documentation/hwmon/lm25066
index 3fa6bf820c88..51b32aa203a8 100644
--- a/Documentation/hwmon/lm25066
+++ b/Documentation/hwmon/lm25066
@@ -8,11 +8,6 @@ Supported chips:
     Datasheets:
 	http://www.ti.com/lit/gpn/lm25056
 	http://www.ti.com/lit/gpn/lm25056a
-  * TI LM25063
-    Prefix: 'lm25063'
-    Addresses scanned: -
-    Datasheet:
-	To be announced
   * National Semiconductor LM25066
     Prefix: 'lm25066'
     Addresses scanned: -
@@ -42,7 +37,7 @@ Description
 -----------
 
 This driver supports hardware monitoring for National Semiconductor / TI LM25056,
-LM25063, LM25066, LM5064, and LM5066/LM5066I Power Management, Monitoring,
+LM25066, LM5064, and LM5066/LM5066I Power Management, Monitoring,
 Control, and Protection ICs.
 
 The driver is a client driver to the core PMBus driver. Please see
@@ -74,12 +69,8 @@ in1_input		Measured input voltage.
 in1_average		Average measured input voltage.
 in1_min			Minimum input voltage.
 in1_max			Maximum input voltage.
-in1_crit		Critical high input voltage (LM25063 only).
-in1_lcrit		Critical low input voltage (LM25063 only).
 in1_min_alarm		Input voltage low alarm.
 in1_max_alarm		Input voltage high alarm.
-in1_lcrit_alarm		Input voltage critical low alarm (LM25063 only).
-in1_crit_alarm		Input voltage critical high alarm. (LM25063 only).
 
 in2_label		"vmon"
 in2_input		Measured voltage on VAUX pin
@@ -94,16 +85,12 @@ in3_input		Measured output voltage.
 in3_average		Average measured output voltage.
 in3_min			Minimum output voltage.
 in3_min_alarm		Output voltage low alarm.
-in3_highest		Historical minimum output voltage (LM25063 only).
-in3_lowest		Historical maximum output voltage (LM25063 only).
 
 curr1_label		"iin"
 curr1_input		Measured input current.
 curr1_average		Average measured input current.
 curr1_max		Maximum input current.
-curr1_crit		Critical input current (LM25063 only).
 curr1_max_alarm		Input current high alarm.
-curr1_crit_alarm	Input current critical high alarm (LM25063 only).
 
 power1_label		"pin"
 power1_input		Measured input power.
@@ -113,11 +100,6 @@ power1_alarm		Input power alarm
 power1_input_highest	Historical maximum power.
 power1_reset_history	Write any value to reset maximum power history.
 
-power2_label		"pout". LM25063 only.
-power2_input		Measured output power.
-power2_max		Maximum output power limit.
-power2_crit		Critical output power limit.
-
 temp1_input		Measured temperature.
 temp1_max		Maximum temperature.
 temp1_crit		Critical high temperature.
diff --git a/Documentation/hwmon/max31785 b/Documentation/hwmon/max31785
index 45fb6093dec2..270c5f865261 100644
--- a/Documentation/hwmon/max31785
+++ b/Documentation/hwmon/max31785
@@ -17,8 +17,9 @@ management with temperature and remote voltage sensing. Various fan control
 features are provided, including PWM frequency control, temperature hysteresis,
 dual tachometer measurements, and fan health monitoring.
 
-For dual rotor fan configuration, the MAX31785 exposes the slowest rotor of the
-two in the fan[1-4]_input attributes.
+For dual-rotor configurations the MAX31785A exposes the second rotor tachometer
+readings in attributes fan[5-8]_input. By contrast the MAX31785 only exposes
+the slowest rotor measurement, and does so in the fan[1-4]_input attributes.
 
 Usage Notes
 -----------
@@ -31,7 +32,9 @@ Sysfs attributes
 
 fan[1-4]_alarm		Fan alarm.
 fan[1-4]_fault		Fan fault.
-fan[1-4]_input		Fan RPM.
+fan[1-8]_input		Fan RPM. On the MAX31785A, inputs 5-8 correspond to the
+			second rotor of fans 1-4
+fan[1-4]_target		Fan input target
 
 in[1-6]_crit		Critical maximum output voltage
 in[1-6]_crit_alarm	Output voltage critical high alarm
@@ -44,6 +47,12 @@ in[1-6]_max_alarm	Output voltage high alarm
 in[1-6]_min		Minimum output voltage
 in[1-6]_min_alarm	Output voltage low alarm
 
+pwm[1-4]		Fan target duty cycle (0..255)
+pwm[1-4]_enable		0: Full-speed
+			1: Manual PWM control
+			2: Automatic PWM (tach-feedback RPM fan-control)
+			3: Automatic closed-loop (temp-feedback fan-control)
+
 temp[1-11]_crit		Critical high temperature
 temp[1-11]_crit_alarm	Chip temperature critical high alarm
 temp[1-11]_input	Measured temperature
diff --git a/Documentation/hwmon/w83773g b/Documentation/hwmon/w83773g
new file mode 100644
index 000000000000..4cc6c0b8257f
--- /dev/null
+++ b/Documentation/hwmon/w83773g
@@ -0,0 +1,33 @@
+Kernel driver w83773g
+====================
+
+Supported chips:
+  * Nuvoton W83773G
+    Prefix: 'w83773g'
+    Addresses scanned: I2C 0x4c and 0x4d
+    Datasheet: https://www.nuvoton.com/resource-files/W83773G_SG_DatasheetV1_2.pdf
+
+Authors:
+	Lei YU <mine260309@gmail.com>
+
+Description
+-----------
+
+This driver implements support for Nuvoton W83773G temperature sensor
+chip. This chip implements one local and two remote sensors.
+The chip also features offsets for the two remote sensors which get added to
+the input readings. The chip does all the scaling by itself and the driver
+therefore reports true temperatures that don't need any user-space adjustments.
+Temperature is measured in degrees Celsius.
+The chip is wired over I2C/SMBus and specified over a temperature
+range of -40 to +125 degrees Celsius (for local sensor) and -40 to +127
+degrees Celsius (for remote sensors).
+Resolution for both the local and remote channels is 0.125 degree C.
+
+The chip supports only temperature measurement. The driver exports
+the temperature values via the following sysfs files:
+
+temp[1-3]_input
+temp[2-3]_fault
+temp[2-3]_offset
+update_interval
diff --git a/Documentation/i2c/dev-interface b/Documentation/i2c/dev-interface
index 5ff19447ac44..d04e6e4964ee 100644
--- a/Documentation/i2c/dev-interface
+++ b/Documentation/i2c/dev-interface
@@ -17,13 +17,16 @@ i2c-10, ...). All 256 minor device numbers are reserved for i2c.
 C example
 =========
 
-So let's say you want to access an i2c adapter from a C program. The
-first thing to do is "#include <linux/i2c-dev.h>". Please note that
-there are two files named "i2c-dev.h" out there, one is distributed
-with the Linux kernel and is meant to be included from kernel
-driver code, the other one is distributed with i2c-tools and is
-meant to be included from user-space programs. You obviously want
-the second one here.
+So let's say you want to access an i2c adapter from a C program.
+First, you need to include these two headers:
+
+  #include <linux/i2c-dev.h>
+  #include <i2c/smbus.h>
+
+(Please note that there are two files named "i2c-dev.h" out there. One is
+distributed with the Linux kernel and the other one is included in the
+source tree of i2c-tools. They used to be different in content but since 2012
+they're identical. You should use "linux/i2c-dev.h").
 
 Now, you have to decide which adapter you want to access. You should
 inspect /sys/class/i2c-dev/ or run "i2cdetect -l" to decide this.
diff --git a/Documentation/index.rst b/Documentation/index.rst
index cb7f1ba5b3b1..ef5080cbf009 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -13,6 +13,18 @@ documents into a coherent whole.  Please note that improvements to the
 documentation are welcome; join the linux-doc list at vger.kernel.org if
 you want to help out.
 
+Licensing documentation
+-----------------------
+
+The following describes the license of the Linux kernel source code
+(GPLv2), how to properly mark the license of individual files in the source
+tree, as well as links to the full license text.
+
+.. toctree::
+   :maxdepth: 2
+
+   process/license-rules.rst
+
 User-oriented documentation
 ---------------------------
 
@@ -52,6 +64,7 @@ merged much easier.
    dev-tools/index
    doc-guide/index
    kernel-hacking/index
+   maintainer/index
 
 Kernel API documentation
 ------------------------
diff --git a/Documentation/input/devices/gpio-tilt.rst b/Documentation/input/devices/gpio-tilt.rst
deleted file mode 100644
index fa6e64570aa7..000000000000
--- a/Documentation/input/devices/gpio-tilt.rst
+++ /dev/null
@@ -1,103 +0,0 @@
-Driver for tilt-switches connected via GPIOs
-============================================
-
-Generic driver to read data from tilt switches connected via gpios.
-Orientation can be provided by one or more than one tilt switches,
-i.e. each tilt switch providing one axis, and the number of axes
-is also not limited.
-
-
-Data structures
----------------
-
-The array of struct gpio in the gpios field is used to list the gpios
-that represent the current tilt state.
-
-The array of struct gpio_tilt_axis describes the axes that are reported
-to the input system. The values set therein are used for the
-input_set_abs_params calls needed to init the axes.
-
-The array of struct gpio_tilt_state maps gpio states to the corresponding
-values to report. The gpio state is represented as a bitfield where the
-bit-index corresponds to the index of the gpio in the struct gpio array.
-In the same manner the values stored in the axes array correspond to
-the elements of the gpio_tilt_axis-array.
-
-
-Example
--------
-
-Example configuration for a single TS1003 tilt switch that rotates around
-one axis in 4 steps and emits the current tilt via two GPIOs::
-
-    static int sg060_tilt_enable(struct device *dev) {
-	    /* code to enable the sensors */
-    };
-
-    static void sg060_tilt_disable(struct device *dev) {
-	    /* code to disable the sensors */
-    };
-
-    static struct gpio sg060_tilt_gpios[] = {
-	    { SG060_TILT_GPIO_SENSOR1, GPIOF_IN, "tilt_sensor1" },
-	    { SG060_TILT_GPIO_SENSOR2, GPIOF_IN, "tilt_sensor2" },
-    };
-
-    static struct gpio_tilt_state sg060_tilt_states[] = {
-	    {
-		    .gpios = (0 << 1) | (0 << 0),
-		    .axes = (int[]) {
-			    0,
-		    },
-	    }, {
-		    .gpios = (0 << 1) | (1 << 0),
-		    .axes = (int[]) {
-			    1, /* 90 degrees */
-		    },
-	    }, {
-		    .gpios = (1 << 1) | (1 << 0),
-		    .axes = (int[]) {
-			    2, /* 180 degrees */
-		    },
-	    }, {
-		    .gpios = (1 << 1) | (0 << 0),
-		    .axes = (int[]) {
-			    3, /* 270 degrees */
-		    },
-	    },
-    };
-
-    static struct gpio_tilt_axis sg060_tilt_axes[] = {
-	    {
-		    .axis = ABS_RY,
-		    .min = 0,
-		    .max = 3,
-		    .fuzz = 0,
-		    .flat = 0,
-	    },
-    };
-
-    static struct gpio_tilt_platform_data sg060_tilt_pdata= {
-	    .gpios = sg060_tilt_gpios,
-	    .nr_gpios = ARRAY_SIZE(sg060_tilt_gpios),
-
-	    .axes = sg060_tilt_axes,
-	    .nr_axes = ARRAY_SIZE(sg060_tilt_axes),
-
-	    .states = sg060_tilt_states,
-	    .nr_states = ARRAY_SIZE(sg060_tilt_states),
-
-	    .debounce_interval = 100,
-
-	    .poll_interval = 1000,
-	    .enable = sg060_tilt_enable,
-	    .disable = sg060_tilt_disable,
-    };
-
-    static struct platform_device sg060_device_tilt = {
-	    .name = "gpio-tilt-polled",
-	    .id = -1,
-	    .dev = {
-		    .platform_data = &sg060_tilt_pdata,
-	    },
-    };
diff --git a/Documentation/input/devices/rotary-encoder.rst b/Documentation/input/devices/rotary-encoder.rst
index b07b20a295ac..810ae02bdaa0 100644
--- a/Documentation/input/devices/rotary-encoder.rst
+++ b/Documentation/input/devices/rotary-encoder.rst
@@ -108,9 +108,9 @@ example below:
 	};
 
 	static const struct property_entry rotary_encoder_properties[] __initconst = {
-		PROPERTY_ENTRY_INTEGER("rotary-encoder,steps-per-period", u32, 24),
-		PROPERTY_ENTRY_INTEGER("linux,axis",			  u32, ABS_X),
-		PROPERTY_ENTRY_INTEGER("rotary-encoder,relative_axis",	  u32, 0),
+		PROPERTY_ENTRY_U32("rotary-encoder,steps-per-period", 24),
+		PROPERTY_ENTRY_U32("linux,axis",		      ABS_X),
+		PROPERTY_ENTRY_U32("rotary-encoder,relative_axis",    0),
 		{ },
 	};
 
diff --git a/Documentation/input/ff.rst b/Documentation/input/ff.rst
index 26d461998e08..0c02e87ee86d 100644
--- a/Documentation/input/ff.rst
+++ b/Documentation/input/ff.rst
@@ -31,7 +31,7 @@ To enable force feedback, you have to:
 
 Before you start, let me WARN you that some devices shake violently during the
 initialisation phase. This happens for example with my "AVB Top Shot Pegasus".
-To stop this annoying behaviour, move you joystick to its limits. Anyway, you
+To stop this annoying behaviour, move your joystick to its limits. Anyway, you
 should keep a hand on your device, in order to avoid it to break down if
 something goes wrong.
 
@@ -121,7 +121,7 @@ uploaded, but not played.
 The content of effect may be modified. In particular, its field "id" is set
 to the unique id assigned by the driver. This data is required for performing
 some operations (removing an effect, controlling the playback).
-This if field must be set to -1 by the user in order to tell the driver to
+The "id" field must be set to -1 by the user in order to tell the driver to
 allocate a new effect.
 
 Effects are file descriptor specific.
@@ -178,7 +178,7 @@ Control of playing is done with write(). Below is an example:
 	stop.code = effect.id;
 	stop.value = 0;
 
-	write(fd, (const void*) &play, sizeof(stop));
+	write(fd, (const void*) &stop, sizeof(stop));
 
 Setting the gain
 ----------------
diff --git a/Documentation/input/multi-touch-protocol.rst b/Documentation/input/multi-touch-protocol.rst
index 8035868c56bc..b51751a0cd5d 100644
--- a/Documentation/input/multi-touch-protocol.rst
+++ b/Documentation/input/multi-touch-protocol.rst
@@ -269,10 +269,11 @@ ABS_MT_ORIENTATION
     The orientation of the touching ellipse. The value should describe a signed
     quarter of a revolution clockwise around the touch center. The signed value
     range is arbitrary, but zero should be returned for an ellipse aligned with
-    the Y axis of the surface, a negative value when the ellipse is turned to
-    the left, and a positive value when the ellipse is turned to the
-    right. When completely aligned with the X axis, the range max should be
-    returned.
+    the Y axis (north) of the surface, a negative value when the ellipse is
+    turned to the left, and a positive value when the ellipse is turned to the
+    right. When aligned with the X axis in the positive direction, the range
+    max should be returned; when aligned with the X axis in the negative
+    direction, the range -max should be returned.
 
     Touch ellipsis are symmetrical by default. For devices capable of true 360
     degree orientation, the reported orientation must exceed the range max to
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 3e3fdae5f3ed..6501389d55b9 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -326,6 +326,7 @@ Code  Seq#(hex)	Include File		Comments
 0xB5	00-0F	uapi/linux/rpmsg.h	<mailto:linux-remoteproc@vger.kernel.org>
 0xC0	00-0F	linux/usb/iowarrior.h
 0xCA	00-0F	uapi/misc/cxl.h
+0xCA	10-2F	uapi/misc/ocxl.h
 0xCA	80-BF	uapi/scsi/cxlflash_ioctl.h
 0xCB	00-1F	CBM serial IEC bus	in development:
 					<mailto:michael.klein@puffin.lb.shuttle.de>
diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index 262722d8867b..f5b9493f04ad 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -77,6 +77,27 @@ applicable everywhere (see syntax).
   Optionally, dependencies only for this default value can be added with
   "if".
 
+ The default value deliberately defaults to 'n' in order to avoid bloating the
+ build. With few exceptions, new config options should not change this. The
+ intent is for "make oldconfig" to add as little as possible to the config from
+ release to release.
+
+ Note:
+	Things that merit "default y/m" include:
+
+	a) A new Kconfig option for something that used to always be built
+	   should be "default y".
+
+	b) A new gatekeeping Kconfig option that hides/shows other Kconfig
+	   options (but does not generate any code of its own), should be
+	   "default y" so people will see those other options.
+
+	c) Sub-driver behavior or similar options for a driver that is
+	   "default n". This allows you to provide sane defaults.
+
+	d) Hardware or infrastructure that everybody expects, such as CONFIG_NET
+	   or CONFIG_BLOCK. These are rare exceptions.
+
 - type definition + default value:
 	"def_bool"/"def_tristate" <expr> ["if" <expr>]
   This is a shorthand notation for a type definition plus a value.
@@ -200,10 +221,14 @@ module state. Dependency expressions have the following syntax:
 <expr> ::= <symbol>                             (1)
            <symbol> '=' <symbol>                (2)
            <symbol> '!=' <symbol>               (3)
-           '(' <expr> ')'                       (4)
-           '!' <expr>                           (5)
-           <expr> '&&' <expr>                   (6)
-           <expr> '||' <expr>                   (7)
+           <symbol1> '<' <symbol2>              (4)
+           <symbol1> '>' <symbol2>              (4)
+           <symbol1> '<=' <symbol2>             (4)
+           <symbol1> '>=' <symbol2>             (4)
+           '(' <expr> ')'                       (5)
+           '!' <expr>                           (6)
+           <expr> '&&' <expr>                   (7)
+           <expr> '||' <expr>                   (8)
 
 Expressions are listed in decreasing order of precedence. 
 
@@ -214,10 +239,13 @@ Expressions are listed in decreasing order of precedence.
     otherwise 'n'.
 (3) If the values of both symbols are equal, it returns 'n',
     otherwise 'y'.
-(4) Returns the value of the expression. Used to override precedence.
-(5) Returns the result of (2-/expr/).
-(6) Returns the result of min(/expr/, /expr/).
-(7) Returns the result of max(/expr/, /expr/).
+(4) If value of <symbol1> is respectively lower, greater, lower-or-equal,
+    or greater-or-equal than value of <symbol2>, it returns 'y',
+    otherwise 'n'.
+(5) Returns the value of the expression. Used to override precedence.
+(6) Returns the result of (2-/expr/).
+(7) Returns the result of min(/expr/, /expr/).
+(8) Returns the result of max(/expr/, /expr/).
 
 An expression can have a value of 'n', 'm' or 'y' (or 0, 1, 2
 respectively for calculations). A menu entry becomes visible when its
diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt
deleted file mode 100644
index c23e2c5ab80d..000000000000
--- a/Documentation/kernel-doc-nano-HOWTO.txt
+++ /dev/null
@@ -1,322 +0,0 @@
-NOTE: this document is outdated and will eventually be removed.  See
-Documentation/doc-guide/ for current information.
-
-kernel-doc nano-HOWTO
-=====================
-
-How to format kernel-doc comments
----------------------------------
-
-In order to provide embedded, 'C' friendly, easy to maintain,
-but consistent and extractable documentation of the functions and
-data structures in the Linux kernel, the Linux kernel has adopted
-a consistent style for documenting functions and their parameters,
-and structures and their members.
-
-The format for this documentation is called the kernel-doc format.
-It is documented in this Documentation/kernel-doc-nano-HOWTO.txt file.
-
-This style embeds the documentation within the source files, using
-a few simple conventions.  The scripts/kernel-doc perl script, the
-Documentation/sphinx/kerneldoc.py Sphinx extension and other tools understand
-these conventions, and are used to extract this embedded documentation
-into various documents.
-
-In order to provide good documentation of kernel functions and data
-structures, please use the following conventions to format your
-kernel-doc comments in Linux kernel source.
-
-We definitely need kernel-doc formatted documentation for functions
-that are exported to loadable modules using EXPORT_SYMBOL.
-
-We also look to provide kernel-doc formatted documentation for
-functions externally visible to other kernel files (not marked
-"static").
-
-We also recommend providing kernel-doc formatted documentation
-for private (file "static") routines, for consistency of kernel
-source code layout.  But this is lower priority and at the
-discretion of the MAINTAINER of that kernel source file.
-
-Data structures visible in kernel include files should also be
-documented using kernel-doc formatted comments.
-
-The opening comment mark "/**" is reserved for kernel-doc comments.
-Only comments so marked will be considered by the kernel-doc scripts,
-and any comment so marked must be in kernel-doc format.  Do not use
-"/**" to be begin a comment block unless the comment block contains
-kernel-doc formatted comments.  The closing comment marker for
-kernel-doc comments can be either "*/" or "**/", but "*/" is
-preferred in the Linux kernel tree.
-
-Kernel-doc comments should be placed just before the function
-or data structure being described.
-
-Example kernel-doc function comment:
-
-/**
- * foobar() - short function description of foobar
- * @arg1:	Describe the first argument to foobar.
- * @arg2:	Describe the second argument to foobar.
- *		One can provide multiple line descriptions
- *		for arguments.
- *
- * A longer description, with more discussion of the function foobar()
- * that might be useful to those using or modifying it.  Begins with
- * empty comment line, and may include additional embedded empty
- * comment lines.
- *
- * The longer description can have multiple paragraphs.
- *
- * Return: Describe the return value of foobar.
- */
-
-The short description following the subject can span multiple lines
-and ends with an @argument description, an empty line or the end of
-the comment block.
-
-The @argument descriptions must begin on the very next line following
-this opening short function description line, with no intervening
-empty comment lines.
-
-If a function parameter is "..." (varargs), it should be listed in
-kernel-doc notation as:
- * @...: description
-
-The return value, if any, should be described in a dedicated section
-named "Return".
-
-Example kernel-doc data structure comment.
-
-/**
- * struct blah - the basic blah structure
- * @mem1:	describe the first member of struct blah
- * @mem2:	describe the second member of struct blah,
- *		perhaps with more lines and words.
- *
- * Longer description of this structure.
- */
-
-The kernel-doc function comments describe each parameter to the
-function, in order, with the @name lines.
-
-The kernel-doc data structure comments describe each structure member
-in the data structure, with the @name lines.
-
-The longer description formatting is "reflowed", losing your line
-breaks.  So presenting carefully formatted lists within these
-descriptions won't work so well; derived documentation will lose
-the formatting.
-
-See the section below "How to add extractable documentation to your
-source files" for more details and notes on how to format kernel-doc
-comments.
-
-Components of the kernel-doc system
------------------------------------
-
-Many places in the source tree have extractable documentation in the
-form of block comments above functions.  The components of this system
-are:
-
-- scripts/kernel-doc
-
-  This is a perl script that hunts for the block comments and can mark
-  them up directly into DocBook, ReST, man, text, and HTML. (No, not
-  texinfo.)
-
-- scripts/docproc.c
-
-  This is a program for converting SGML template files into SGML
-  files. When a file is referenced it is searched for symbols
-  exported (EXPORT_SYMBOL), to be able to distinguish between internal
-  and external functions.
-  It invokes kernel-doc, giving it the list of functions that
-  are to be documented.
-  Additionally it is used to scan the SGML template files to locate
-  all the files referenced herein. This is used to generate dependency
-  information as used by make.
-
-- Makefile
-
-  The targets 'xmldocs', 'latexdocs', 'pdfdocs', 'epubdocs'and 'htmldocs'
-  are used to build XML DocBook files, LaTeX files, PDF files,
-  ePub files and html files in Documentation/.
-
-How to extract the documentation
---------------------------------
-
-If you just want to read the ready-made books on the various
-subsystems, just type 'make epubdocs', or 'make pdfdocs', or 'make htmldocs',
-depending on your preference.  If you would rather read a different format,
-you can type 'make xmldocs' and then use DocBook tools to convert
-Documentation/output/*.xml to a format of your choice (for example,
-'db2html ...' if 'make htmldocs' was not defined).
-
-If you want to see man pages instead, you can do this:
-
-$ cd linux
-$ scripts/kernel-doc -man $(find -name '*.c') | split-man.pl /tmp/man
-$ scripts/kernel-doc -man $(find -name '*.h') | split-man.pl /tmp/man
-
-Here is split-man.pl:
-
--->
-#!/usr/bin/perl
-
-if ($#ARGV < 0) {
-   die "where do I put the results?\n";
-}
-
-mkdir $ARGV[0],0777;
-$state = 0;
-while (<STDIN>) {
-    if (/^\.TH \"[^\"]*\" 9 \"([^\"]*)\"/) {
-	if ($state == 1) { close OUT }
-	$state = 1;
-	$fn = "$ARGV[0]/$1.9";
-	print STDERR "Creating $fn\n";
-	open OUT, ">$fn" or die "can't open $fn: $!\n";
-	print OUT $_;
-    } elsif ($state != 0) {
-	print OUT $_;
-    }
-}
-
-close OUT;
-<--
-
-If you just want to view the documentation for one function in one
-file, you can do this:
-
-$ scripts/kernel-doc -man -function fn file | nroff -man | less
-
-or this:
-
-$ scripts/kernel-doc -text -function fn file
-
-
-How to add extractable documentation to your source files
----------------------------------------------------------
-
-The format of the block comment is like this:
-
-/**
- * function_name(:)? (- short description)?
-(* @parameterx(space)*: (description of parameter x)?)*
-(* a blank line)?
- * (Description:)? (Description of function)?
- * (section header: (section description)? )*
-(*)?*/
-
-All "description" text can span multiple lines, although the
-function_name & its short description are traditionally on a single line.
-Description text may also contain blank lines (i.e., lines that contain
-only a "*").
-
-"section header:" names must be unique per function (or struct,
-union, typedef, enum).
-
-Use the section header "Return" for sections describing the return value
-of a function.
-
-Avoid putting a spurious blank line after the function name, or else the
-description will be repeated!
-
-All descriptive text is further processed, scanning for the following special
-patterns, which are highlighted appropriately.
-
-'funcname()' - function
-'$ENVVAR' - environment variable
-'&struct_name' - name of a structure (up to two words including 'struct')
-'@parameter' - name of a parameter
-'%CONST' - name of a constant.
-
-NOTE 1:  The multi-line descriptive text you provide does *not* recognize
-line breaks, so if you try to format some text nicely, as in:
-
-  Return:
-    0 - cool
-    1 - invalid arg
-    2 - out of memory
-
-this will all run together and produce:
-
-  Return: 0 - cool 1 - invalid arg 2 - out of memory
-
-NOTE 2:  If the descriptive text you provide has lines that begin with
-some phrase followed by a colon, each of those phrases will be taken as
-a new section heading, which means you should similarly try to avoid text
-like:
-
-  Return:
-    0: cool
-    1: invalid arg
-    2: out of memory
-
-every line of which would start a new section.  Again, probably not
-what you were after.
-
-Take a look around the source tree for examples.
-
-
-kernel-doc for structs, unions, enums, and typedefs
----------------------------------------------------
-
-Beside functions you can also write documentation for structs, unions,
-enums and typedefs. Instead of the function name you must write the name
-of the declaration;  the struct/union/enum/typedef must always precede
-the name. Nesting of declarations is not supported.
-Use the argument mechanism to document members or constants.
-
-Inside a struct description, you can use the "private:" and "public:"
-comment tags.  Structure fields that are inside a "private:" area
-are not listed in the generated output documentation.  The "private:"
-and "public:" tags must begin immediately following a "/*" comment
-marker.  They may optionally include comments between the ":" and the
-ending "*/" marker.
-
-Example:
-
-/**
- * struct my_struct - short description
- * @a: first member
- * @b: second member
- *
- * Longer description
- */
-struct my_struct {
-    int a;
-    int b;
-/* private: internal use only */
-    int c;
-};
-
-
-Including documentation blocks in source files
-----------------------------------------------
-
-To facilitate having source code and comments close together, you can
-include kernel-doc documentation blocks that are free-form comments
-instead of being kernel-doc for functions, structures, unions,
-enums, or typedefs.  This could be used for something like a
-theory of operation for a driver or library code, for example.
-
-This is done by using a DOC: section keyword with a section title.  E.g.:
-
-/**
- * DOC: Theory of Operation
- *
- * The whizbang foobar is a dilly of a gizmo.  It can do whatever you
- * want it to do, at any time.  It reads your mind.  Here's how it works.
- *
- * foo bar splat
- *
- * The only drawback to this gizmo is that is can sometimes damage
- * hardware, software, or its subject(s).
- */
-
-DOC: sections are used in ReST files.
-
-Tim.
-*/ <twaugh@redhat.com>
diff --git a/Documentation/kernel-hacking/hacking.rst b/Documentation/kernel-hacking/hacking.rst
index daf3883b2694..9999c8468293 100644
--- a/Documentation/kernel-hacking/hacking.rst
+++ b/Documentation/kernel-hacking/hacking.rst
@@ -523,7 +523,7 @@ this expression is true, or ``-ERESTARTSYS`` if a signal is received. The
 Waking Up Queued Tasks
 ----------------------
 
-Call :c:func:`wake_up()` (``include/linux/wait.h``);, which will wake
+Call :c:func:`wake_up()` (``include/linux/wait.h``), which will wake
 up every process in the queue. The exception is if one has
 ``TASK_EXCLUSIVE`` set, in which case the remainder of the queue will
 not be woken. There are other variants of this basic function available
@@ -690,8 +690,8 @@ not provide the necessary runtime environment and the include files are
 not tested for it. It is still possible, but not recommended. If you
 really want to do this, forget about exceptions at least.
 
-NUMif
------
+#if
+---
 
 It is generally considered cleaner to use macros in header files (or at
 the top of .c files) to abstract away functions rather than using \`#if'
diff --git a/Documentation/livepatch/livepatch.txt b/Documentation/livepatch/livepatch.txt
index ecdb18104ab0..1ae2de758c08 100644
--- a/Documentation/livepatch/livepatch.txt
+++ b/Documentation/livepatch/livepatch.txt
@@ -72,8 +72,7 @@ example, they add a NULL pointer or a boundary check, fix a race by adding
 a missing memory barrier, or add some locking around a critical section.
 Most of these changes are self contained and the function presents itself
 the same way to the rest of the system. In this case, the functions might
-be updated independently one by one.  (This can be done by setting the
-'immediate' flag in the klp_patch struct.)
+be updated independently one by one.
 
 But there are more complex fixes. For example, a patch might change
 ordering of locking in multiple functions at the same time. Or a patch
@@ -125,12 +124,6 @@ safe to patch tasks:
    b) Patching CPU-bound user tasks.  If the task is highly CPU-bound
       then it will get patched the next time it gets interrupted by an
       IRQ.
-   c) In the future it could be useful for applying patches for
-      architectures which don't yet have HAVE_RELIABLE_STACKTRACE.  In
-      this case you would have to signal most of the tasks on the
-      system.  However this isn't supported yet because there's
-      currently no way to patch kthreads without
-      HAVE_RELIABLE_STACKTRACE.
 
 3. For idle "swapper" tasks, since they don't ever exit the kernel, they
    instead have a klp_update_patch_state() call in the idle loop which
@@ -138,27 +131,16 @@ safe to patch tasks:
 
    (Note there's not yet such an approach for kthreads.)
 
-All the above approaches may be skipped by setting the 'immediate' flag
-in the 'klp_patch' struct, which will disable per-task consistency and
-patch all tasks immediately.  This can be useful if the patch doesn't
-change any function or data semantics.  Note that, even with this flag
-set, it's possible that some tasks may still be running with an old
-version of the function, until that function returns.
+Architectures which don't have HAVE_RELIABLE_STACKTRACE solely rely on
+the second approach. It's highly likely that some tasks may still be
+running with an old version of the function, until that function
+returns. In this case you would have to signal the tasks. This
+especially applies to kthreads. They may not be woken up and would need
+to be forced. See below for more information.
 
-There's also an 'immediate' flag in the 'klp_func' struct which allows
-you to specify that certain functions in the patch can be applied
-without per-task consistency.  This might be useful if you want to patch
-a common function like schedule(), and the function change doesn't need
-consistency but the rest of the patch does.
-
-For architectures which don't have HAVE_RELIABLE_STACKTRACE, the user
-must set patch->immediate which causes all tasks to be patched
-immediately.  This option should be used with care, only when the patch
-doesn't change any function or data semantics.
-
-In the future, architectures which don't have HAVE_RELIABLE_STACKTRACE
-may be allowed to use per-task consistency if we can come up with
-another way to patch kthreads.
+Unless we can come up with another way to patch kthreads, architectures
+without HAVE_RELIABLE_STACKTRACE are not considered fully supported by
+the kernel livepatching.
 
 The /sys/kernel/livepatch/<patch>/transition file shows whether a patch
 is in transition.  Only a single patch (the topmost patch on the stack)
@@ -176,8 +158,31 @@ If a patch is in transition, this file shows 0 to indicate the task is
 unpatched and 1 to indicate it's patched.  Otherwise, if no patch is in
 transition, it shows -1.  Any tasks which are blocking the transition
 can be signaled with SIGSTOP and SIGCONT to force them to change their
-patched state.
-
+patched state. This may be harmful to the system though.
+/sys/kernel/livepatch/<patch>/signal attribute provides a better alternative.
+Writing 1 to the attribute sends a fake signal to all remaining blocking
+tasks. No proper signal is actually delivered (there is no data in signal
+pending structures). Tasks are interrupted or woken up, and forced to change
+their patched state.
+
+Administrator can also affect a transition through
+/sys/kernel/livepatch/<patch>/force attribute. Writing 1 there clears
+TIF_PATCH_PENDING flag of all tasks and thus forces the tasks to the patched
+state. Important note! The force attribute is intended for cases when the
+transition gets stuck for a long time because of a blocking task. Administrator
+is expected to collect all necessary data (namely stack traces of such blocking
+tasks) and request a clearance from a patch distributor to force the transition.
+Unauthorized usage may cause harm to the system. It depends on the nature of the
+patch, which functions are (un)patched, and which functions the blocking tasks
+are sleeping in (/proc/<pid>/stack may help here). Removal (rmmod) of patch
+modules is permanently disabled when the force feature is used. It cannot be
+guaranteed there is no task sleeping in such module. It implies unbounded
+reference count if a patch module is disabled and enabled in a loop.
+
+Moreover, the usage of force may also affect future applications of live
+patches and cause even more harm to the system. Administrator should first
+consider to simply cancel a transition (see above). If force is used, reboot
+should be planned and no more live patches applied.
 
 3.1 Adding consistency model support to new architectures
 ---------------------------------------------------------
@@ -216,13 +221,6 @@ few options:
    a good backup option for those architectures which don't have
    reliable stack traces yet.
 
-In the meantime, patches for such architectures can bypass the
-consistency model by setting klp_patch.immediate to true.  This option
-is perfectly fine for patches which don't change the semantics of the
-patched functions.  In practice, this is usable for ~90% of security
-fixes.  Use of this option also means the patch can't be unloaded after
-it has been disabled.
-
 
 4. Livepatch module
 ===================
@@ -278,9 +276,6 @@ into three levels:
     only for a particular object ( vmlinux or a kernel module ). Note that
     kallsyms allows for searching symbols according to the object name.
 
-    There's also an 'immediate' flag which, when set, patches the
-    function immediately, bypassing the consistency model safety checks.
-
   + struct klp_object defines an array of patched functions (struct
     klp_func) in the same object. Where the object is either vmlinux
     (NULL) or a module name.
@@ -299,9 +294,6 @@ into three levels:
     symbols are found. The only exception are symbols from objects
     (kernel modules) that have not been loaded yet.
 
-    Setting the 'immediate' flag applies the patch to all tasks
-    immediately, bypassing the consistency model safety checks.
-
     For more details on how the patch is applied on a per-task basis,
     see the "Consistency model" section.
 
@@ -316,14 +308,12 @@ section "Livepatch life-cycle" below for more details about these
 two operations.
 
 Module removal is only safe when there are no users of the underlying
-functions. The immediate consistency model is not able to detect this. The
-code just redirects the functions at the very beginning and it does not
-check if the functions are in use. In other words, it knows when the
-functions get called but it does not know when the functions return.
-Therefore it cannot be decided when the livepatch module can be safely
-removed. This is solved by a hybrid consistency model. When the system is
-transitioned to a new patch state (patched/unpatched) it is guaranteed that
-no task sleeps or runs in the old code.
+functions. This is the reason why the force feature permanently disables
+the removal. The forced tasks entered the functions but we cannot say
+that they returned back.  Therefore it cannot be decided when the
+livepatch module can be safely removed. When the system is successfully
+transitioned to a new patch state (patched/unpatched) without being
+forced it is guaranteed that no task sleeps or runs in the old code.
 
 
 5. Livepatch life-cycle
@@ -337,19 +327,12 @@ First, the patch is applied only when all patched symbols for already
 loaded objects are found. The error handling is much easier if this
 check is done before particular functions get redirected.
 
-Second, the immediate consistency model does not guarantee that anyone is not
-sleeping in the new code after the patch is reverted. This means that the new
-code needs to stay around "forever". If the code is there, one could apply it
-again. Therefore it makes sense to separate the operations that might be done
-once and those that need to be repeated when the patch is enabled (applied)
-again.
-
-Third, it might take some time until the entire system is migrated
-when a more complex consistency model is used. The patch revert might
-block the livepatch module removal for too long. Therefore it is useful
-to revert the patch using a separate operation that might be called
-explicitly. But it does not make sense to remove all information
-until the livepatch module is really removed.
+Second, it might take some time until the entire system is migrated with
+the hybrid consistency model being used. The patch revert might block
+the livepatch module removal for too long. Therefore it is useful to
+revert the patch using a separate operation that might be called
+explicitly. But it does not make sense to remove all information until
+the livepatch module is really removed.
 
 
 5.1. Registration
@@ -435,6 +418,9 @@ Information about the registered patches can be found under
 /sys/kernel/livepatch. The patches could be enabled and disabled
 by writing there.
 
+/sys/kernel/livepatch/<patch>/signal and /sys/kernel/livepatch/<patch>/force
+attributes allow administrator to affect a patching operation.
+
 See Documentation/ABI/testing/sysfs-kernel-livepatch for more details.
 
 
diff --git a/Documentation/locking/crossrelease.txt b/Documentation/locking/crossrelease.txt
deleted file mode 100644
index bdf1423d5f99..000000000000
--- a/Documentation/locking/crossrelease.txt
+++ /dev/null
@@ -1,874 +0,0 @@
-Crossrelease
-============
-
-Started by Byungchul Park <byungchul.park@lge.com>
-
-Contents:
-
- (*) Background
-
-     - What causes deadlock
-     - How lockdep works
-
- (*) Limitation
-
-     - Limit lockdep
-     - Pros from the limitation
-     - Cons from the limitation
-     - Relax the limitation
-
- (*) Crossrelease
-
-     - Introduce crossrelease
-     - Introduce commit
-
- (*) Implementation
-
-     - Data structures
-     - How crossrelease works
-
- (*) Optimizations
-
-     - Avoid duplication
-     - Lockless for hot paths
-
- (*) APPENDIX A: What lockdep does to work aggresively
-
- (*) APPENDIX B: How to avoid adding false dependencies
-
-
-==========
-Background
-==========
-
-What causes deadlock
---------------------
-
-A deadlock occurs when a context is waiting for an event to happen,
-which is impossible because another (or the) context who can trigger the
-event is also waiting for another (or the) event to happen, which is
-also impossible due to the same reason.
-
-For example:
-
-   A context going to trigger event C is waiting for event A to happen.
-   A context going to trigger event A is waiting for event B to happen.
-   A context going to trigger event B is waiting for event C to happen.
-
-A deadlock occurs when these three wait operations run at the same time,
-because event C cannot be triggered if event A does not happen, which in
-turn cannot be triggered if event B does not happen, which in turn
-cannot be triggered if event C does not happen. After all, no event can
-be triggered since any of them never meets its condition to wake up.
-
-A dependency might exist between two waiters and a deadlock might happen
-due to an incorrect releationship between dependencies. Thus, we must
-define what a dependency is first. A dependency exists between them if:
-
-   1. There are two waiters waiting for each event at a given time.
-   2. The only way to wake up each waiter is to trigger its event.
-   3. Whether one can be woken up depends on whether the other can.
-
-Each wait in the example creates its dependency like:
-
-   Event C depends on event A.
-   Event A depends on event B.
-   Event B depends on event C.
-
-   NOTE: Precisely speaking, a dependency is one between whether a
-   waiter for an event can be woken up and whether another waiter for
-   another event can be woken up. However from now on, we will describe
-   a dependency as if it's one between an event and another event for
-   simplicity.
-
-And they form circular dependencies like:
-
-    -> C -> A -> B -
-   /                \
-   \                /
-    ----------------
-
-   where 'A -> B' means that event A depends on event B.
-
-Such circular dependencies lead to a deadlock since no waiter can meet
-its condition to wake up as described.
-
-CONCLUSION
-
-Circular dependencies cause a deadlock.
-
-
-How lockdep works
------------------
-
-Lockdep tries to detect a deadlock by checking dependencies created by
-lock operations, acquire and release. Waiting for a lock corresponds to
-waiting for an event, and releasing a lock corresponds to triggering an
-event in the previous section.
-
-In short, lockdep does:
-
-   1. Detect a new dependency.
-   2. Add the dependency into a global graph.
-   3. Check if that makes dependencies circular.
-   4. Report a deadlock or its possibility if so.
-
-For example, consider a graph built by lockdep that looks like:
-
-   A -> B -
-           \
-            -> E
-           /
-   C -> D -
-
-   where A, B,..., E are different lock classes.
-
-Lockdep will add a dependency into the graph on detection of a new
-dependency. For example, it will add a dependency 'E -> C' when a new
-dependency between lock E and lock C is detected. Then the graph will be:
-
-       A -> B -
-               \
-                -> E -
-               /      \
-    -> C -> D -        \
-   /                   /
-   \                  /
-    ------------------
-
-   where A, B,..., E are different lock classes.
-
-This graph contains a subgraph which demonstrates circular dependencies:
-
-                -> E -
-               /      \
-    -> C -> D -        \
-   /                   /
-   \                  /
-    ------------------
-
-   where C, D and E are different lock classes.
-
-This is the condition under which a deadlock might occur. Lockdep
-reports it on detection after adding a new dependency. This is the way
-how lockdep works.
-
-CONCLUSION
-
-Lockdep detects a deadlock or its possibility by checking if circular
-dependencies were created after adding each new dependency.
-
-
-==========
-Limitation
-==========
-
-Limit lockdep
--------------
-
-Limiting lockdep to work on only typical locks e.g. spin locks and
-mutexes, which are released within the acquire context, the
-implementation becomes simple but its capacity for detection becomes
-limited. Let's check pros and cons in next section.
-
-
-Pros from the limitation
-------------------------
-
-Given the limitation, when acquiring a lock, locks in a held_locks
-cannot be released if the context cannot acquire it so has to wait to
-acquire it, which means all waiters for the locks in the held_locks are
-stuck. It's an exact case to create dependencies between each lock in
-the held_locks and the lock to acquire.
-
-For example:
-
-   CONTEXT X
-   ---------
-   acquire A
-   acquire B /* Add a dependency 'A -> B' */
-   release B
-   release A
-
-   where A and B are different lock classes.
-
-When acquiring lock A, the held_locks of CONTEXT X is empty thus no
-dependency is added. But when acquiring lock B, lockdep detects and adds
-a new dependency 'A -> B' between lock A in the held_locks and lock B.
-They can be simply added whenever acquiring each lock.
-
-And data required by lockdep exists in a local structure, held_locks
-embedded in task_struct. Forcing to access the data within the context,
-lockdep can avoid racy problems without explicit locks while handling
-the local data.
-
-Lastly, lockdep only needs to keep locks currently being held, to build
-a dependency graph. However, relaxing the limitation, it needs to keep
-even locks already released, because a decision whether they created
-dependencies might be long-deferred.
-
-To sum up, we can expect several advantages from the limitation:
-
-   1. Lockdep can easily identify a dependency when acquiring a lock.
-   2. Races are avoidable while accessing local locks in a held_locks.
-   3. Lockdep only needs to keep locks currently being held.
-
-CONCLUSION
-
-Given the limitation, the implementation becomes simple and efficient.
-
-
-Cons from the limitation
-------------------------
-
-Given the limitation, lockdep is applicable only to typical locks. For
-example, page locks for page access or completions for synchronization
-cannot work with lockdep.
-
-Can we detect deadlocks below, under the limitation?
-
-Example 1:
-
-   CONTEXT X	   CONTEXT Y	   CONTEXT Z
-   ---------	   ---------	   ----------
-		   mutex_lock A
-   lock_page B
-		   lock_page B
-				   mutex_lock A /* DEADLOCK */
-				   unlock_page B held by X
-		   unlock_page B
-		   mutex_unlock A
-				   mutex_unlock A
-
-   where A and B are different lock classes.
-
-No, we cannot.
-
-Example 2:
-
-   CONTEXT X		   CONTEXT Y
-   ---------		   ---------
-			   mutex_lock A
-   mutex_lock A
-			   wait_for_complete B /* DEADLOCK */
-   complete B
-			   mutex_unlock A
-   mutex_unlock A
-
-   where A is a lock class and B is a completion variable.
-
-No, we cannot.
-
-CONCLUSION
-
-Given the limitation, lockdep cannot detect a deadlock or its
-possibility caused by page locks or completions.
-
-
-Relax the limitation
---------------------
-
-Under the limitation, things to create dependencies are limited to
-typical locks. However, synchronization primitives like page locks and
-completions, which are allowed to be released in any context, also
-create dependencies and can cause a deadlock. So lockdep should track
-these locks to do a better job. We have to relax the limitation for
-these locks to work with lockdep.
-
-Detecting dependencies is very important for lockdep to work because
-adding a dependency means adding an opportunity to check whether it
-causes a deadlock. The more lockdep adds dependencies, the more it
-thoroughly works. Thus Lockdep has to do its best to detect and add as
-many true dependencies into a graph as possible.
-
-For example, considering only typical locks, lockdep builds a graph like:
-
-   A -> B -
-           \
-            -> E
-           /
-   C -> D -
-
-   where A, B,..., E are different lock classes.
-
-On the other hand, under the relaxation, additional dependencies might
-be created and added. Assuming additional 'FX -> C' and 'E -> GX' are
-added thanks to the relaxation, the graph will be:
-
-         A -> B -
-                 \
-                  -> E -> GX
-                 /
-   FX -> C -> D -
-
-   where A, B,..., E, FX and GX are different lock classes, and a suffix
-   'X' is added on non-typical locks.
-
-The latter graph gives us more chances to check circular dependencies
-than the former. However, it might suffer performance degradation since
-relaxing the limitation, with which design and implementation of lockdep
-can be efficient, might introduce inefficiency inevitably. So lockdep
-should provide two options, strong detection and efficient detection.
-
-Choosing efficient detection:
-
-   Lockdep works with only locks restricted to be released within the
-   acquire context. However, lockdep works efficiently.
-
-Choosing strong detection:
-
-   Lockdep works with all synchronization primitives. However, lockdep
-   suffers performance degradation.
-
-CONCLUSION
-
-Relaxing the limitation, lockdep can add additional dependencies giving
-additional opportunities to check circular dependencies.
-
-
-============
-Crossrelease
-============
-
-Introduce crossrelease
-----------------------
-
-In order to allow lockdep to handle additional dependencies by what
-might be released in any context, namely 'crosslock', we have to be able
-to identify those created by crosslocks. The proposed 'crossrelease'
-feature provoides a way to do that.
-
-Crossrelease feature has to do:
-
-   1. Identify dependencies created by crosslocks.
-   2. Add the dependencies into a dependency graph.
-
-That's all. Once a meaningful dependency is added into graph, then
-lockdep would work with the graph as it did. The most important thing
-crossrelease feature has to do is to correctly identify and add true
-dependencies into the global graph.
-
-A dependency e.g. 'A -> B' can be identified only in the A's release
-context because a decision required to identify the dependency can be
-made only in the release context. That is to decide whether A can be
-released so that a waiter for A can be woken up. It cannot be made in
-other than the A's release context.
-
-It's no matter for typical locks because each acquire context is same as
-its release context, thus lockdep can decide whether a lock can be
-released in the acquire context. However for crosslocks, lockdep cannot
-make the decision in the acquire context but has to wait until the
-release context is identified.
-
-Therefore, deadlocks by crosslocks cannot be detected just when it
-happens, because those cannot be identified until the crosslocks are
-released. However, deadlock possibilities can be detected and it's very
-worth. See 'APPENDIX A' section to check why.
-
-CONCLUSION
-
-Using crossrelease feature, lockdep can work with what might be released
-in any context, namely crosslock.
-
-
-Introduce commit
-----------------
-
-Since crossrelease defers the work adding true dependencies of
-crosslocks until they are actually released, crossrelease has to queue
-all acquisitions which might create dependencies with the crosslocks.
-Then it identifies dependencies using the queued data in batches at a
-proper time. We call it 'commit'.
-
-There are four types of dependencies:
-
-1. TT type: 'typical lock A -> typical lock B'
-
-   Just when acquiring B, lockdep can see it's in the A's release
-   context. So the dependency between A and B can be identified
-   immediately. Commit is unnecessary.
-
-2. TC type: 'typical lock A -> crosslock BX'
-
-   Just when acquiring BX, lockdep can see it's in the A's release
-   context. So the dependency between A and BX can be identified
-   immediately. Commit is unnecessary, too.
-
-3. CT type: 'crosslock AX -> typical lock B'
-
-   When acquiring B, lockdep cannot identify the dependency because
-   there's no way to know if it's in the AX's release context. It has
-   to wait until the decision can be made. Commit is necessary.
-
-4. CC type: 'crosslock AX -> crosslock BX'
-
-   When acquiring BX, lockdep cannot identify the dependency because
-   there's no way to know if it's in the AX's release context. It has
-   to wait until the decision can be made. Commit is necessary.
-   But, handling CC type is not implemented yet. It's a future work.
-
-Lockdep can work without commit for typical locks, but commit step is
-necessary once crosslocks are involved. Introducing commit, lockdep
-performs three steps. What lockdep does in each step is:
-
-1. Acquisition: For typical locks, lockdep does what it originally did
-   and queues the lock so that CT type dependencies can be checked using
-   it at the commit step. For crosslocks, it saves data which will be
-   used at the commit step and increases a reference count for it.
-
-2. Commit: No action is reauired for typical locks. For crosslocks,
-   lockdep adds CT type dependencies using the data saved at the
-   acquisition step.
-
-3. Release: No changes are required for typical locks. When a crosslock
-   is released, it decreases a reference count for it.
-
-CONCLUSION
-
-Crossrelease introduces commit step to handle dependencies of crosslocks
-in batches at a proper time.
-
-
-==============
-Implementation
-==============
-
-Data structures
----------------
-
-Crossrelease introduces two main data structures.
-
-1. hist_lock
-
-   This is an array embedded in task_struct, for keeping lock history so
-   that dependencies can be added using them at the commit step. Since
-   it's local data, it can be accessed locklessly in the owner context.
-   The array is filled at the acquisition step and consumed at the
-   commit step. And it's managed in circular manner.
-
-2. cross_lock
-
-   One per lockdep_map exists. This is for keeping data of crosslocks
-   and used at the commit step.
-
-
-How crossrelease works
-----------------------
-
-It's the key of how crossrelease works, to defer necessary works to an
-appropriate point in time and perform in at once at the commit step.
-Let's take a look with examples step by step, starting from how lockdep
-works without crossrelease for typical locks.
-
-   acquire A /* Push A onto held_locks */
-   acquire B /* Push B onto held_locks and add 'A -> B' */
-   acquire C /* Push C onto held_locks and add 'B -> C' */
-   release C /* Pop C from held_locks */
-   release B /* Pop B from held_locks */
-   release A /* Pop A from held_locks */
-
-   where A, B and C are different lock classes.
-
-   NOTE: This document assumes that readers already understand how
-   lockdep works without crossrelease thus omits details. But there's
-   one thing to note. Lockdep pretends to pop a lock from held_locks
-   when releasing it. But it's subtly different from the original pop
-   operation because lockdep allows other than the top to be poped.
-
-In this case, lockdep adds 'the top of held_locks -> the lock to acquire'
-dependency every time acquiring a lock.
-
-After adding 'A -> B', a dependency graph will be:
-
-   A -> B
-
-   where A and B are different lock classes.
-
-And after adding 'B -> C', the graph will be:
-
-   A -> B -> C
-
-   where A, B and C are different lock classes.
-
-Let's performs commit step even for typical locks to add dependencies.
-Of course, commit step is not necessary for them, however, it would work
-well because this is a more general way.
-
-   acquire A
-   /*
-    * Queue A into hist_locks
-    *
-    * In hist_locks: A
-    * In graph: Empty
-    */
-
-   acquire B
-   /*
-    * Queue B into hist_locks
-    *
-    * In hist_locks: A, B
-    * In graph: Empty
-    */
-
-   acquire C
-   /*
-    * Queue C into hist_locks
-    *
-    * In hist_locks: A, B, C
-    * In graph: Empty
-    */
-
-   commit C
-   /*
-    * Add 'C -> ?'
-    * Answer the following to decide '?'
-    * What has been queued since acquire C: Nothing
-    *
-    * In hist_locks: A, B, C
-    * In graph: Empty
-    */
-
-   release C
-
-   commit B
-   /*
-    * Add 'B -> ?'
-    * Answer the following to decide '?'
-    * What has been queued since acquire B: C
-    *
-    * In hist_locks: A, B, C
-    * In graph: 'B -> C'
-    */
-
-   release B
-
-   commit A
-   /*
-    * Add 'A -> ?'
-    * Answer the following to decide '?'
-    * What has been queued since acquire A: B, C
-    *
-    * In hist_locks: A, B, C
-    * In graph: 'B -> C', 'A -> B', 'A -> C'
-    */
-
-   release A
-
-   where A, B and C are different lock classes.
-
-In this case, dependencies are added at the commit step as described.
-
-After commits for A, B and C, the graph will be:
-
-   A -> B -> C
-
-   where A, B and C are different lock classes.
-
-   NOTE: A dependency 'A -> C' is optimized out.
-
-We can see the former graph built without commit step is same as the
-latter graph built using commit steps. Of course the former way leads to
-earlier finish for building the graph, which means we can detect a
-deadlock or its possibility sooner. So the former way would be prefered
-when possible. But we cannot avoid using the latter way for crosslocks.
-
-Let's look at how commit steps work for crosslocks. In this case, the
-commit step is performed only on crosslock AX as real. And it assumes
-that the AX release context is different from the AX acquire context.
-
-   BX RELEASE CONTEXT		   BX ACQUIRE CONTEXT
-   ------------------		   ------------------
-				   acquire A
-				   /*
-				    * Push A onto held_locks
-				    * Queue A into hist_locks
-				    *
-				    * In held_locks: A
-				    * In hist_locks: A
-				    * In graph: Empty
-				    */
-
-				   acquire BX
-				   /*
-				    * Add 'the top of held_locks -> BX'
-				    *
-				    * In held_locks: A
-				    * In hist_locks: A
-				    * In graph: 'A -> BX'
-				    */
-
-   ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-   It must be guaranteed that the following operations are seen after
-   acquiring BX globally. It can be done by things like barrier.
-   ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-   acquire C
-   /*
-    * Push C onto held_locks
-    * Queue C into hist_locks
-    *
-    * In held_locks: C
-    * In hist_locks: C
-    * In graph: 'A -> BX'
-    */
-
-   release C
-   /*
-    * Pop C from held_locks
-    *
-    * In held_locks: Empty
-    * In hist_locks: C
-    * In graph: 'A -> BX'
-    */
-				   acquire D
-				   /*
-				    * Push D onto held_locks
-				    * Queue D into hist_locks
-				    * Add 'the top of held_locks -> D'
-				    *
-				    * In held_locks: A, D
-				    * In hist_locks: A, D
-				    * In graph: 'A -> BX', 'A -> D'
-				    */
-   acquire E
-   /*
-    * Push E onto held_locks
-    * Queue E into hist_locks
-    *
-    * In held_locks: E
-    * In hist_locks: C, E
-    * In graph: 'A -> BX', 'A -> D'
-    */
-
-   release E
-   /*
-    * Pop E from held_locks
-    *
-    * In held_locks: Empty
-    * In hist_locks: D, E
-    * In graph: 'A -> BX', 'A -> D'
-    */
-				   release D
-				   /*
-				    * Pop D from held_locks
-				    *
-				    * In held_locks: A
-				    * In hist_locks: A, D
-				    * In graph: 'A -> BX', 'A -> D'
-				    */
-   commit BX
-   /*
-    * Add 'BX -> ?'
-    * What has been queued since acquire BX: C, E
-    *
-    * In held_locks: Empty
-    * In hist_locks: D, E
-    * In graph: 'A -> BX', 'A -> D',
-    *           'BX -> C', 'BX -> E'
-    */
-
-   release BX
-   /*
-    * In held_locks: Empty
-    * In hist_locks: D, E
-    * In graph: 'A -> BX', 'A -> D',
-    *           'BX -> C', 'BX -> E'
-    */
-				   release A
-				   /*
-				    * Pop A from held_locks
-				    *
-				    * In held_locks: Empty
-				    * In hist_locks: A, D
-				    * In graph: 'A -> BX', 'A -> D',
-				    *           'BX -> C', 'BX -> E'
-				    */
-
-   where A, BX, C,..., E are different lock classes, and a suffix 'X' is
-   added on crosslocks.
-
-Crossrelease considers all acquisitions after acqiuring BX are
-candidates which might create dependencies with BX. True dependencies
-will be determined when identifying the release context of BX. Meanwhile,
-all typical locks are queued so that they can be used at the commit step.
-And then two dependencies 'BX -> C' and 'BX -> E' are added at the
-commit step when identifying the release context.
-
-The final graph will be, with crossrelease:
-
-               -> C
-              /
-       -> BX -
-      /       \
-   A -         -> E
-      \
-       -> D
-
-   where A, BX, C,..., E are different lock classes, and a suffix 'X' is
-   added on crosslocks.
-
-However, the final graph will be, without crossrelease:
-
-   A -> D
-
-   where A and D are different lock classes.
-
-The former graph has three more dependencies, 'A -> BX', 'BX -> C' and
-'BX -> E' giving additional opportunities to check if they cause
-deadlocks. This way lockdep can detect a deadlock or its possibility
-caused by crosslocks.
-
-CONCLUSION
-
-We checked how crossrelease works with several examples.
-
-
-=============
-Optimizations
-=============
-
-Avoid duplication
------------------
-
-Crossrelease feature uses a cache like what lockdep already uses for
-dependency chains, but this time it's for caching CT type dependencies.
-Once that dependency is cached, the same will never be added again.
-
-
-Lockless for hot paths
-----------------------
-
-To keep all locks for later use at the commit step, crossrelease adopts
-a local array embedded in task_struct, which makes access to the data
-lockless by forcing it to happen only within the owner context. It's
-like how lockdep handles held_locks. Lockless implmentation is important
-since typical locks are very frequently acquired and released.
-
-
-=================================================
-APPENDIX A: What lockdep does to work aggresively
-=================================================
-
-A deadlock actually occurs when all wait operations creating circular
-dependencies run at the same time. Even though they don't, a potential
-deadlock exists if the problematic dependencies exist. Thus it's
-meaningful to detect not only an actual deadlock but also its potential
-possibility. The latter is rather valuable. When a deadlock occurs
-actually, we can identify what happens in the system by some means or
-other even without lockdep. However, there's no way to detect possiblity
-without lockdep unless the whole code is parsed in head. It's terrible.
-Lockdep does the both, and crossrelease only focuses on the latter.
-
-Whether or not a deadlock actually occurs depends on several factors.
-For example, what order contexts are switched in is a factor. Assuming
-circular dependencies exist, a deadlock would occur when contexts are
-switched so that all wait operations creating the dependencies run
-simultaneously. Thus to detect a deadlock possibility even in the case
-that it has not occured yet, lockdep should consider all possible
-combinations of dependencies, trying to:
-
-1. Use a global dependency graph.
-
-   Lockdep combines all dependencies into one global graph and uses them,
-   regardless of which context generates them or what order contexts are
-   switched in. Aggregated dependencies are only considered so they are
-   prone to be circular if a problem exists.
-
-2. Check dependencies between classes instead of instances.
-
-   What actually causes a deadlock are instances of lock. However,
-   lockdep checks dependencies between classes instead of instances.
-   This way lockdep can detect a deadlock which has not happened but
-   might happen in future by others but the same class.
-
-3. Assume all acquisitions lead to waiting.
-
-   Although locks might be acquired without waiting which is essential
-   to create dependencies, lockdep assumes all acquisitions lead to
-   waiting since it might be true some time or another.
-
-CONCLUSION
-
-Lockdep detects not only an actual deadlock but also its possibility,
-and the latter is more valuable.
-
-
-==================================================
-APPENDIX B: How to avoid adding false dependencies
-==================================================
-
-Remind what a dependency is. A dependency exists if:
-
-   1. There are two waiters waiting for each event at a given time.
-   2. The only way to wake up each waiter is to trigger its event.
-   3. Whether one can be woken up depends on whether the other can.
-
-For example:
-
-   acquire A
-   acquire B /* A dependency 'A -> B' exists */
-   release B
-   release A
-
-   where A and B are different lock classes.
-
-A depedency 'A -> B' exists since:
-
-   1. A waiter for A and a waiter for B might exist when acquiring B.
-   2. Only way to wake up each is to release what it waits for.
-   3. Whether the waiter for A can be woken up depends on whether the
-      other can. IOW, TASK X cannot release A if it fails to acquire B.
-
-For another example:
-
-   TASK X			   TASK Y
-   ------			   ------
-				   acquire AX
-   acquire B /* A dependency 'AX -> B' exists */
-   release B
-   release AX held by Y
-
-   where AX and B are different lock classes, and a suffix 'X' is added
-   on crosslocks.
-
-Even in this case involving crosslocks, the same rule can be applied. A
-depedency 'AX -> B' exists since:
-
-   1. A waiter for AX and a waiter for B might exist when acquiring B.
-   2. Only way to wake up each is to release what it waits for.
-   3. Whether the waiter for AX can be woken up depends on whether the
-      other can. IOW, TASK X cannot release AX if it fails to acquire B.
-
-Let's take a look at more complicated example:
-
-   TASK X			   TASK Y
-   ------			   ------
-   acquire B
-   release B
-   fork Y
-				   acquire AX
-   acquire C /* A dependency 'AX -> C' exists */
-   release C
-   release AX held by Y
-
-   where AX, B and C are different lock classes, and a suffix 'X' is
-   added on crosslocks.
-
-Does a dependency 'AX -> B' exist? Nope.
-
-Two waiters are essential to create a dependency. However, waiters for
-AX and B to create 'AX -> B' cannot exist at the same time in this
-example. Thus the dependency 'AX -> B' cannot be created.
-
-It would be ideal if the full set of true ones can be considered. But
-we can ensure nothing but what actually happened. Relying on what
-actually happens at runtime, we can anyway add only true ones, though
-they might be a subset of true ones. It's similar to how lockdep works
-for typical locks. There might be more true dependencies than what
-lockdep has detected in runtime. Lockdep has no choice but to rely on
-what actually happens. Crossrelease also relies on it.
-
-CONCLUSION
-
-Relying on what actually happens, lockdep can avoid adding false
-dependencies.
diff --git a/Documentation/locking/locktorture.txt b/Documentation/locking/locktorture.txt
index a2ef3a929bf1..6a8df4cd19bf 100644
--- a/Documentation/locking/locktorture.txt
+++ b/Documentation/locking/locktorture.txt
@@ -57,11 +57,6 @@ torture_type	  Type of lock to torture. By default, only spinlocks will
 
 		     o "rwsem_lock": read/write down() and up() semaphore pairs.
 
-torture_runnable  Start locktorture at boot time in the case where the
-		  module is built into the kernel, otherwise wait for
-		  torture_runnable to be set via sysfs before starting.
-		  By default it will begin once the module is loaded.
-
 
 	    ** Torture-framework (RCU + locking) **
 
diff --git a/Documentation/maintainer/conf.py b/Documentation/maintainer/conf.py
new file mode 100644
index 000000000000..81e9eb7a7884
--- /dev/null
+++ b/Documentation/maintainer/conf.py
@@ -0,0 +1,10 @@
+# -*- coding: utf-8; mode: python -*-
+
+project = 'Linux Kernel Development Documentation'
+
+tags.add("subproject")
+
+latex_documents = [
+    ('index', 'maintainer.tex', 'Linux Kernel Development Documentation',
+     'The kernel development community', 'manual'),
+]
diff --git a/Documentation/maintainer/configure-git.rst b/Documentation/maintainer/configure-git.rst
new file mode 100644
index 000000000000..78bbbb0d2c84
--- /dev/null
+++ b/Documentation/maintainer/configure-git.rst
@@ -0,0 +1,34 @@
+.. _configuregit:
+
+Configure Git
+=============
+
+This chapter describes maintainer level git configuration.
+
+Tagged branches used in :ref:`Documentation/maintainer/pull-requests.rst
+<pullrequests>` should be signed with the developers public GPG key. Signed
+tags can be created by passing the ``-u`` flag to ``git tag``. However,
+since you would *usually* use the same key for the same project, you can
+set it once with
+::
+
+	git config user.signingkey "keyname"
+
+Alternatively, edit your ``.git/config`` or ``~/.gitconfig`` file by hand:
+::
+
+	[user]
+		name = Jane Developer
+		email = jd@domain.org
+		signingkey = jd@domain.org
+
+You may need to tell ``git`` to use ``gpg2``
+::
+
+	[gpg]
+		program = /path/to/gpg2
+
+You may also like to tell ``gpg`` which ``tty`` to use (add to your shell rc file)
+::
+
+	export GPG_TTY=$(tty)
diff --git a/Documentation/maintainer/index.rst b/Documentation/maintainer/index.rst
new file mode 100644
index 000000000000..2a14916930cb
--- /dev/null
+++ b/Documentation/maintainer/index.rst
@@ -0,0 +1,14 @@
+==========================
+Kernel Maintainer Handbook
+==========================
+
+This document is the humble beginning of a manual for kernel maintainers.
+There is a lot yet to go here!  Please feel free to propose (and write)
+additions to this manual.
+
+.. toctree::
+   :maxdepth: 2
+
+   configure-git
+   pull-requests
+
diff --git a/Documentation/maintainer/pull-requests.rst b/Documentation/maintainer/pull-requests.rst
new file mode 100644
index 000000000000..a19db3458b56
--- /dev/null
+++ b/Documentation/maintainer/pull-requests.rst
@@ -0,0 +1,178 @@
+.. _pullrequests:
+
+Creating Pull Requests
+======================
+
+This chapter describes how maintainers can create and submit pull requests
+to other maintainers. This is useful for transferring changes from one
+maintainers tree to another maintainers tree.
+
+This document was written by Tobin C. Harding (who at that time, was not an
+experienced maintainer) primarily from comments made by Greg Kroah-Hartman
+and Linus Torvalds on LKML. Suggestions and fixes by Jonathan Corbet and
+Mauro Carvalho Chehab.  Misrepresentation was unintentional but inevitable,
+please direct abuse to Tobin C. Harding <me@tobin.cc>.
+
+Original email thread::
+
+	http://lkml.kernel.org/r/20171114110500.GA21175@kroah.com
+
+
+Create Branch
+-------------
+
+To start with you will need to have all the changes you wish to include in
+the pull request on a separate branch. Typically you will base this branch
+off of a branch in the developers tree whom you intend to send the pull
+request to.
+
+In order to create the pull request you must first tag the branch that you
+have just created. It is recommended that you choose a meaningful tag name,
+in a way that you and others can understand, even after some time.  A good
+practice is to include in the name an indicator of the sybsystem of origin
+and the target kernel version.
+
+Greg offers the following. A pull request with miscellaneous stuff for
+drivers/char, to be applied at the Kernel version 4.15-rc1 could be named
+as ``char-misc-4.15-rc1``. If such tag would be produced from a branch
+named ``char-misc-next``, you would be using the following command::
+
+        git tag -s char-misc-4.15-rc1 char-misc-next
+
+that will create a signed tag called ``char-misc-4.15-rc1`` based on the
+last commit in the ``char-misc-next`` branch, and sign it with your gpg key
+(see :ref:`Documentation/maintainer/configure_git.rst <configuregit>`).
+
+Linus will only accept pull requests based on a signed tag. Other
+maintainers may differ.
+
+When you run the above command ``git`` will drop you into an editor and ask
+you to describe the tag.  In this case, you are describing a pull request,
+so outline what is contained here, why it should be merged, and what, if
+any, testing has been done.  All of this information will end up in the tag
+itself, and then in the merge commit that the maintainer makes if/when they
+merge the pull request. So write it up well, as it will be in the kernel
+tree for forever.
+
+As said by Linus::
+
+	Anyway, at least to me, the important part is the *message*. I want
+	to understand what I'm pulling, and why I should pull it. I also
+	want to use that message as the message for the merge, so it should
+	not just make sense to me, but make sense as a historical record
+	too.
+
+	Note that if there is something odd about the pull request, that
+	should very much be in the explanation. If you're touching files
+	that you don't maintain, explain _why_. I will see it in the
+	diffstat anyway, and if you didn't mention it, I'll just be extra
+	suspicious.  And when you send me new stuff after the merge window
+	(or even bug-fixes, but ones that look scary), explain not just
+	what they do and why they do it, but explain the _timing_. What
+	happened that this didn't go through the merge window..
+
+	I will take both what you write in the email pull request _and_ in
+	the signed tag, so depending on your workflow, you can either
+	describe your work in the signed tag (which will also automatically
+	make it into the pull request email), or you can make the signed
+	tag just a placeholder with nothing interesting in it, and describe
+	the work later when you actually send me the pull request.
+
+	And yes, I will edit the message. Partly because I tend to do just
+	trivial formatting (the whole indentation and quoting etc), but
+	partly because part of the message may make sense for me at pull
+	time (describing the conflicts and your personal issues for sending
+	it right now), but may not make sense in the context of a merge
+	commit message, so I will try to make it all make sense. I will
+	also fix any speeling mistaeks and bad grammar I notice,
+	particularly for non-native speakers (but also for native ones
+	;^). But I may miss some, or even add some.
+
+			Linus
+
+Greg gives, as an example pull request::
+
+	Char/Misc patches for 4.15-rc1
+
+	Here is the big char/misc patch set for the 4.15-rc1 merge window.
+	Contained in here is the normal set of new functions added to all
+	of these crazy drivers, as well as the following brand new
+	subsystems:
+		- time_travel_controller: Finally a set of drivers for the
+		  latest time travel bus architecture that provides i/o to
+		  the CPU before it asked for it, allowing uninterrupted
+		  processing
+		- relativity_shifters: due to the affect that the
+		  time_travel_controllers have on the overall system, there
+		  was a need for a new set of relativity shifter drivers to
+		  accommodate the newly formed black holes that would
+		  threaten to suck CPUs into them.  This subsystem handles
+		  this in a way to successfully neutralize the problems.
+		  There is a Kconfig option to force these to be enabled
+		  when needed, so problems should not occur.
+
+	All of these patches have been successfully tested in the latest
+	linux-next releases, and the original problems that it found have
+	all been resolved (apologies to anyone living near Canberra for the
+	lack of the Kconfig options in the earlier versions of the
+	linux-next tree creations.)
+
+	Signed-off-by: Your-name-here <your_email@domain>
+
+
+The tag message format is just like a git commit id.  One line at the top
+for a "summary subject" and be sure to sign-off at the bottom.
+
+Now that you have a local signed tag, you need to push it up to where it
+can be retrieved::
+
+	git push origin char-misc-4.15-rc1
+
+
+Create Pull Request
+-------------------
+
+The last thing to do is create the pull request message.  ``git`` handily
+will do this for you with the ``git request-pull`` command, but it needs a
+bit of help determining what you want to pull, and on what to base the pull
+against (to show the correct changes to be pulled and the diffstat). The
+following command(s) will generate a pull request::
+
+	git request-pull master git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git/ char-misc-4.15-rc1
+
+Quoting Greg::
+
+	This is asking git to compare the difference from the
+	'char-misc-4.15-rc1' tag location, to the head of the 'master'
+	branch (which in my case points to the last location in Linus's
+	tree that I diverged from, usually a -rc release) and to use the
+	git:// protocol to pull from.  If you wish to use https://, that
+	can be used here instead as well (but note that some people behind
+	firewalls will have problems with https git pulls).
+
+	If the char-misc-4.15-rc1 tag is not present in the repo that I am
+	asking to be pulled from, git will complain saying it is not there,
+	a handy way to remember to actually push it to a public location.
+
+	The output of 'git request-pull' will contain the location of the
+	git tree and specific tag to pull from, and the full text
+	description of that tag (which is why you need to provide good
+	information in that tag).  It will also create a diffstat of the
+	pull request, and a shortlog of the individual commits that the
+	pull request will provide.
+
+Linus responded that he tends to prefer the ``git://`` protocol. Other
+maintainers may have different preferences. Also, note that if you are
+creating pull requests without a signed tag then ``https://`` may be a
+better choice. Please see the original thread for the full discussion.
+
+
+Submit Pull Request
+-------------------
+
+A pull request is submitted in the same way as an ordinary patch. Send as
+inline email to the maintainer and CC LKML and any sub-system specific
+lists if required. Pull requests to Linus typically have a subject line
+something like::
+
+	[GIT PULL] <subsystem> changes for v4.15-rc1
diff --git a/Documentation/md/raid5-ppl.txt b/Documentation/md/raid5-ppl.txt
index 127072b09363..bfa092589e00 100644
--- a/Documentation/md/raid5-ppl.txt
+++ b/Documentation/md/raid5-ppl.txt
@@ -39,6 +39,7 @@ case the behavior is the same as in plain raid5.
 PPL is available for md version-1 metadata and external (specifically IMSM)
 metadata arrays. It can be enabled using mdadm option --consistency-policy=ppl.
 
-Currently, volatile write-back cache should be disabled on all member drives
-when using PPL. Otherwise it cannot guarantee consistency in case of power
-failure.
+There is a limitation of maximum 64 disks in the array for PPL. It allows to
+keep data structures and implementation simple. RAID5 arrays with so many disks
+are not likely due to high risk of multiple disks failure. Such restriction
+should not be a real life limitation.
diff --git a/Documentation/media/dvb-drivers/frontends.rst b/Documentation/media/dvb-drivers/frontends.rst
new file mode 100644
index 000000000000..1f5f57989196
--- /dev/null
+++ b/Documentation/media/dvb-drivers/frontends.rst
@@ -0,0 +1,30 @@
+****************
+Frontend drivers
+****************
+
+Frontend attach headers
+***********************
+
+.. Keep it on alphabetic order
+
+.. kernel-doc:: drivers/media/dvb-frontends/a8293.h
+.. kernel-doc:: drivers/media/dvb-frontends/af9013.h
+.. kernel-doc:: drivers/media/dvb-frontends/ascot2e.h
+.. kernel-doc:: drivers/media/dvb-frontends/cxd2820r.h
+.. kernel-doc:: drivers/media/dvb-frontends/drxk.h
+.. kernel-doc:: drivers/media/dvb-frontends/dvb-pll.h
+.. kernel-doc:: drivers/media/dvb-frontends/helene.h
+.. kernel-doc:: drivers/media/dvb-frontends/horus3a.h
+.. kernel-doc:: drivers/media/dvb-frontends/ix2505v.h
+.. kernel-doc:: drivers/media/dvb-frontends/m88ds3103.h
+.. kernel-doc:: drivers/media/dvb-frontends/mb86a20s.h
+.. kernel-doc:: drivers/media/dvb-frontends/mn88472.h
+.. kernel-doc:: drivers/media/dvb-frontends/rtl2830.h
+.. kernel-doc:: drivers/media/dvb-frontends/rtl2832.h
+.. kernel-doc:: drivers/media/dvb-frontends/rtl2832_sdr.h
+.. kernel-doc:: drivers/media/dvb-frontends/stb6000.h
+.. kernel-doc:: drivers/media/dvb-frontends/tda10071.h
+.. kernel-doc:: drivers/media/dvb-frontends/tda826x.h
+.. kernel-doc:: drivers/media/dvb-frontends/zd1301_demod.h
+.. kernel-doc:: drivers/media/dvb-frontends/zl10036.h
+
diff --git a/Documentation/media/dvb-drivers/index.rst b/Documentation/media/dvb-drivers/index.rst
index 376141143ae9..314e127d82e3 100644
--- a/Documentation/media/dvb-drivers/index.rst
+++ b/Documentation/media/dvb-drivers/index.rst
@@ -41,4 +41,5 @@ For more details see the file COPYING in the source distribution of Linux.
 	technisat
 	ttusb-dec
 	udev
+	frontends
 	contributors
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 479ecec80593..a863009849a3 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -227,17 +227,20 @@ There are some minimal guarantees that may be expected of a CPU:
  (*) On any given CPU, dependent memory accesses will be issued in order, with
      respect to itself.  This means that for:
 
-	Q = READ_ONCE(P); smp_read_barrier_depends(); D = READ_ONCE(*Q);
+	Q = READ_ONCE(P); D = READ_ONCE(*Q);
 
      the CPU will issue the following memory operations:
 
 	Q = LOAD P, D = LOAD *Q
 
-     and always in that order.  On most systems, smp_read_barrier_depends()
-     does nothing, but it is required for DEC Alpha.  The READ_ONCE()
-     is required to prevent compiler mischief.  Please note that you
-     should normally use something like rcu_dereference() instead of
-     open-coding smp_read_barrier_depends().
+     and always in that order.  However, on DEC Alpha, READ_ONCE() also
+     emits a memory-barrier instruction, so that a DEC Alpha CPU will
+     instead issue the following memory operations:
+
+	Q = LOAD P, MEMORY_BARRIER, D = LOAD *Q, MEMORY_BARRIER
+
+     Whether on DEC Alpha or not, the READ_ONCE() also prevents compiler
+     mischief.
 
  (*) Overlapping loads and stores within a particular CPU will appear to be
      ordered within that CPU.  This means that for:
@@ -1815,7 +1818,7 @@ The Linux kernel has eight basic CPU memory barriers:
 	GENERAL		mb()			smp_mb()
 	WRITE		wmb()			smp_wmb()
 	READ		rmb()			smp_rmb()
-	DATA DEPENDENCY	read_barrier_depends()	smp_read_barrier_depends()
+	DATA DEPENDENCY				READ_ONCE()
 
 
 All memory barriers except the data dependency barriers imply a compiler
@@ -2864,7 +2867,10 @@ access depends on a read, not all do, so it may not be relied on.
 
 Other CPUs may also have split caches, but must coordinate between the various
 cachelets for normal memory accesses.  The semantics of the Alpha removes the
-need for coordination in the absence of memory barriers.
+need for hardware coordination in the absence of memory barriers, which
+permitted Alpha to sport higher CPU clock rates back in the day.  However,
+please note that smp_read_barrier_depends() should not be used except in
+Alpha arch-specific code and within the READ_ONCE() macro.
 
 
 CACHE COHERENCY VS DMA
diff --git a/Documentation/mtd/spi-nor.txt b/Documentation/mtd/spi-nor.txt
index 548d6306ebca..da1fbff5a24c 100644
--- a/Documentation/mtd/spi-nor.txt
+++ b/Documentation/mtd/spi-nor.txt
@@ -60,3 +60,6 @@ The main API is spi_nor_scan(). Before you call the hook, a driver should
 initialize the necessary fields for spi_nor{}. Please see
 drivers/mtd/spi-nor/spi-nor.c for detail. Please also refer to fsl-quadspi.c
 when you want to write a new driver for a SPI NOR controller.
+Another API is spi_nor_restore(), this is used to restore the status of SPI
+flash chip such as addressing mode. Call it whenever detach the driver from
+device or reboot the system.
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index 7a79b3587dd3..2b89d91b376f 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -36,8 +36,6 @@ bonding.txt
 	- Linux Ethernet Bonding Driver HOWTO: link aggregation in Linux.
 bridge.txt
 	- where to get user space programs for ethernet bridging with Linux.
-can.txt
-	- documentation on CAN protocol family.
 cdc_mbim.txt
 	- 3G/LTE USB modem (Mobile Broadband Interface Model)
 checksum-offloads.txt
@@ -228,6 +226,8 @@ x25.txt
 	- general info on X.25 development.
 x25-iface.txt
 	- description of the X.25 Packet Layer to LAPB device interface.
+xfrm_device.txt
+	- description of XFRM offload API
 xfrm_proc.txt
 	- description of the statistics package for XFRM.
 xfrm_sync.txt
diff --git a/Documentation/networking/batman-adv.rst b/Documentation/networking/batman-adv.rst
index a342b2cc3dc6..245fb6c0ab6f 100644
--- a/Documentation/networking/batman-adv.rst
+++ b/Documentation/networking/batman-adv.rst
@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ==========
 batman-adv
 ==========
diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst
new file mode 100644
index 000000000000..d23c51abf8c6
--- /dev/null
+++ b/Documentation/networking/can.rst
@@ -0,0 +1,1437 @@
+===================================
+SocketCAN - Controller Area Network
+===================================
+
+Overview / What is SocketCAN
+============================
+
+The socketcan package is an implementation of CAN protocols
+(Controller Area Network) for Linux.  CAN is a networking technology
+which has widespread use in automation, embedded devices, and
+automotive fields.  While there have been other CAN implementations
+for Linux based on character devices, SocketCAN uses the Berkeley
+socket API, the Linux network stack and implements the CAN device
+drivers as network interfaces.  The CAN socket API has been designed
+as similar as possible to the TCP/IP protocols to allow programmers,
+familiar with network programming, to easily learn how to use CAN
+sockets.
+
+
+.. _socketcan-motivation:
+
+Motivation / Why Using the Socket API
+=====================================
+
+There have been CAN implementations for Linux before SocketCAN so the
+question arises, why we have started another project.  Most existing
+implementations come as a device driver for some CAN hardware, they
+are based on character devices and provide comparatively little
+functionality.  Usually, there is only a hardware-specific device
+driver which provides a character device interface to send and
+receive raw CAN frames, directly to/from the controller hardware.
+Queueing of frames and higher-level transport protocols like ISO-TP
+have to be implemented in user space applications.  Also, most
+character-device implementations support only one single process to
+open the device at a time, similar to a serial interface.  Exchanging
+the CAN controller requires employment of another device driver and
+often the need for adaption of large parts of the application to the
+new driver's API.
+
+SocketCAN was designed to overcome all of these limitations.  A new
+protocol family has been implemented which provides a socket interface
+to user space applications and which builds upon the Linux network
+layer, enabling use all of the provided queueing functionality.  A device
+driver for CAN controller hardware registers itself with the Linux
+network layer as a network device, so that CAN frames from the
+controller can be passed up to the network layer and on to the CAN
+protocol family module and also vice-versa.  Also, the protocol family
+module provides an API for transport protocol modules to register, so
+that any number of transport protocols can be loaded or unloaded
+dynamically.  In fact, the can core module alone does not provide any
+protocol and cannot be used without loading at least one additional
+protocol module.  Multiple sockets can be opened at the same time,
+on different or the same protocol module and they can listen/send
+frames on different or the same CAN IDs.  Several sockets listening on
+the same interface for frames with the same CAN ID are all passed the
+same received matching CAN frames.  An application wishing to
+communicate using a specific transport protocol, e.g. ISO-TP, just
+selects that protocol when opening the socket, and then can read and
+write application data byte streams, without having to deal with
+CAN-IDs, frames, etc.
+
+Similar functionality visible from user-space could be provided by a
+character device, too, but this would lead to a technically inelegant
+solution for a couple of reasons:
+
+* **Intricate usage:**  Instead of passing a protocol argument to
+  socket(2) and using bind(2) to select a CAN interface and CAN ID, an
+  application would have to do all these operations using ioctl(2)s.
+
+* **Code duplication:**  A character device cannot make use of the Linux
+  network queueing code, so all that code would have to be duplicated
+  for CAN networking.
+
+* **Abstraction:**  In most existing character-device implementations, the
+  hardware-specific device driver for a CAN controller directly
+  provides the character device for the application to work with.
+  This is at least very unusual in Unix systems for both, char and
+  block devices.  For example you don't have a character device for a
+  certain UART of a serial interface, a certain sound chip in your
+  computer, a SCSI or IDE controller providing access to your hard
+  disk or tape streamer device.  Instead, you have abstraction layers
+  which provide a unified character or block device interface to the
+  application on the one hand, and a interface for hardware-specific
+  device drivers on the other hand.  These abstractions are provided
+  by subsystems like the tty layer, the audio subsystem or the SCSI
+  and IDE subsystems for the devices mentioned above.
+
+  The easiest way to implement a CAN device driver is as a character
+  device without such a (complete) abstraction layer, as is done by most
+  existing drivers.  The right way, however, would be to add such a
+  layer with all the functionality like registering for certain CAN
+  IDs, supporting several open file descriptors and (de)multiplexing
+  CAN frames between them, (sophisticated) queueing of CAN frames, and
+  providing an API for device drivers to register with.  However, then
+  it would be no more difficult, or may be even easier, to use the
+  networking framework provided by the Linux kernel, and this is what
+  SocketCAN does.
+
+The use of the networking framework of the Linux kernel is just the
+natural and most appropriate way to implement CAN for Linux.
+
+
+.. _socketcan-concept:
+
+SocketCAN Concept
+=================
+
+As described in :ref:`socketcan-motivation` the main goal of SocketCAN is to
+provide a socket interface to user space applications which builds
+upon the Linux network layer. In contrast to the commonly known
+TCP/IP and ethernet networking, the CAN bus is a broadcast-only(!)
+medium that has no MAC-layer addressing like ethernet. The CAN-identifier
+(can_id) is used for arbitration on the CAN-bus. Therefore the CAN-IDs
+have to be chosen uniquely on the bus. When designing a CAN-ECU
+network the CAN-IDs are mapped to be sent by a specific ECU.
+For this reason a CAN-ID can be treated best as a kind of source address.
+
+
+.. _socketcan-receive-lists:
+
+Receive Lists
+-------------
+
+The network transparent access of multiple applications leads to the
+problem that different applications may be interested in the same
+CAN-IDs from the same CAN network interface. The SocketCAN core
+module - which implements the protocol family CAN - provides several
+high efficient receive lists for this reason. If e.g. a user space
+application opens a CAN RAW socket, the raw protocol module itself
+requests the (range of) CAN-IDs from the SocketCAN core that are
+requested by the user. The subscription and unsubscription of
+CAN-IDs can be done for specific CAN interfaces or for all(!) known
+CAN interfaces with the can_rx_(un)register() functions provided to
+CAN protocol modules by the SocketCAN core (see :ref:`socketcan-core-module`).
+To optimize the CPU usage at runtime the receive lists are split up
+into several specific lists per device that match the requested
+filter complexity for a given use-case.
+
+
+.. _socketcan-local-loopback1:
+
+Local Loopback of Sent Frames
+-----------------------------
+
+As known from other networking concepts the data exchanging
+applications may run on the same or different nodes without any
+change (except for the according addressing information):
+
+.. code::
+
+	 ___   ___   ___                   _______   ___
+	| _ | | _ | | _ |                 | _   _ | | _ |
+	||A|| ||B|| ||C||                 ||A| |B|| ||C||
+	|___| |___| |___|                 |_______| |___|
+	  |     |     |                       |       |
+	-----------------(1)- CAN bus -(2)---------------
+
+To ensure that application A receives the same information in the
+example (2) as it would receive in example (1) there is need for
+some kind of local loopback of the sent CAN frames on the appropriate
+node.
+
+The Linux network devices (by default) just can handle the
+transmission and reception of media dependent frames. Due to the
+arbitration on the CAN bus the transmission of a low prio CAN-ID
+may be delayed by the reception of a high prio CAN frame. To
+reflect the correct [*]_ traffic on the node the loopback of the sent
+data has to be performed right after a successful transmission. If
+the CAN network interface is not capable of performing the loopback for
+some reason the SocketCAN core can do this task as a fallback solution.
+See :ref:`socketcan-local-loopback1` for details (recommended).
+
+The loopback functionality is enabled by default to reflect standard
+networking behaviour for CAN applications. Due to some requests from
+the RT-SocketCAN group the loopback optionally may be disabled for each
+separate socket. See sockopts from the CAN RAW sockets in :ref:`socketcan-raw-sockets`.
+
+.. [*] you really like to have this when you're running analyser
+       tools like 'candump' or 'cansniffer' on the (same) node.
+
+
+.. _socketcan-network-problem-notifications:
+
+Network Problem Notifications
+-----------------------------
+
+The use of the CAN bus may lead to several problems on the physical
+and media access control layer. Detecting and logging of these lower
+layer problems is a vital requirement for CAN users to identify
+hardware issues on the physical transceiver layer as well as
+arbitration problems and error frames caused by the different
+ECUs. The occurrence of detected errors are important for diagnosis
+and have to be logged together with the exact timestamp. For this
+reason the CAN interface driver can generate so called Error Message
+Frames that can optionally be passed to the user application in the
+same way as other CAN frames. Whenever an error on the physical layer
+or the MAC layer is detected (e.g. by the CAN controller) the driver
+creates an appropriate error message frame. Error messages frames can
+be requested by the user application using the common CAN filter
+mechanisms. Inside this filter definition the (interested) type of
+errors may be selected. The reception of error messages is disabled
+by default. The format of the CAN error message frame is briefly
+described in the Linux header file "include/uapi/linux/can/error.h".
+
+
+How to use SocketCAN
+====================
+
+Like TCP/IP, you first need to open a socket for communicating over a
+CAN network. Since SocketCAN implements a new protocol family, you
+need to pass PF_CAN as the first argument to the socket(2) system
+call. Currently, there are two CAN protocols to choose from, the raw
+socket protocol and the broadcast manager (BCM). So to open a socket,
+you would write::
+
+    s = socket(PF_CAN, SOCK_RAW, CAN_RAW);
+
+and::
+
+    s = socket(PF_CAN, SOCK_DGRAM, CAN_BCM);
+
+respectively.  After the successful creation of the socket, you would
+normally use the bind(2) system call to bind the socket to a CAN
+interface (which is different from TCP/IP due to different addressing
+- see :ref:`socketcan-concept`). After binding (CAN_RAW) or connecting (CAN_BCM)
+the socket, you can read(2) and write(2) from/to the socket or use
+send(2), sendto(2), sendmsg(2) and the recv* counterpart operations
+on the socket as usual. There are also CAN specific socket options
+described below.
+
+The basic CAN frame structure and the sockaddr structure are defined
+in include/linux/can.h:
+
+.. code-block:: C
+
+    struct can_frame {
+            canid_t can_id;  /* 32 bit CAN_ID + EFF/RTR/ERR flags */
+            __u8    can_dlc; /* frame payload length in byte (0 .. 8) */
+            __u8    __pad;   /* padding */
+            __u8    __res0;  /* reserved / padding */
+            __u8    __res1;  /* reserved / padding */
+            __u8    data[8] __attribute__((aligned(8)));
+    };
+
+The alignment of the (linear) payload data[] to a 64bit boundary
+allows the user to define their own structs and unions to easily access
+the CAN payload. There is no given byteorder on the CAN bus by
+default. A read(2) system call on a CAN_RAW socket transfers a
+struct can_frame to the user space.
+
+The sockaddr_can structure has an interface index like the
+PF_PACKET socket, that also binds to a specific interface:
+
+.. code-block:: C
+
+    struct sockaddr_can {
+            sa_family_t can_family;
+            int         can_ifindex;
+            union {
+                    /* transport protocol class address info (e.g. ISOTP) */
+                    struct { canid_t rx_id, tx_id; } tp;
+
+                    /* reserved for future CAN protocols address information */
+            } can_addr;
+    };
+
+To determine the interface index an appropriate ioctl() has to
+be used (example for CAN_RAW sockets without error checking):
+
+.. code-block:: C
+
+    int s;
+    struct sockaddr_can addr;
+    struct ifreq ifr;
+
+    s = socket(PF_CAN, SOCK_RAW, CAN_RAW);
+
+    strcpy(ifr.ifr_name, "can0" );
+    ioctl(s, SIOCGIFINDEX, &ifr);
+
+    addr.can_family = AF_CAN;
+    addr.can_ifindex = ifr.ifr_ifindex;
+
+    bind(s, (struct sockaddr *)&addr, sizeof(addr));
+
+    (..)
+
+To bind a socket to all(!) CAN interfaces the interface index must
+be 0 (zero). In this case the socket receives CAN frames from every
+enabled CAN interface. To determine the originating CAN interface
+the system call recvfrom(2) may be used instead of read(2). To send
+on a socket that is bound to 'any' interface sendto(2) is needed to
+specify the outgoing interface.
+
+Reading CAN frames from a bound CAN_RAW socket (see above) consists
+of reading a struct can_frame:
+
+.. code-block:: C
+
+    struct can_frame frame;
+
+    nbytes = read(s, &frame, sizeof(struct can_frame));
+
+    if (nbytes < 0) {
+            perror("can raw socket read");
+            return 1;
+    }
+
+    /* paranoid check ... */
+    if (nbytes < sizeof(struct can_frame)) {
+            fprintf(stderr, "read: incomplete CAN frame\n");
+            return 1;
+    }
+
+    /* do something with the received CAN frame */
+
+Writing CAN frames can be done similarly, with the write(2) system call::
+
+    nbytes = write(s, &frame, sizeof(struct can_frame));
+
+When the CAN interface is bound to 'any' existing CAN interface
+(addr.can_ifindex = 0) it is recommended to use recvfrom(2) if the
+information about the originating CAN interface is needed:
+
+.. code-block:: C
+
+    struct sockaddr_can addr;
+    struct ifreq ifr;
+    socklen_t len = sizeof(addr);
+    struct can_frame frame;
+
+    nbytes = recvfrom(s, &frame, sizeof(struct can_frame),
+                      0, (struct sockaddr*)&addr, &len);
+
+    /* get interface name of the received CAN frame */
+    ifr.ifr_ifindex = addr.can_ifindex;
+    ioctl(s, SIOCGIFNAME, &ifr);
+    printf("Received a CAN frame from interface %s", ifr.ifr_name);
+
+To write CAN frames on sockets bound to 'any' CAN interface the
+outgoing interface has to be defined certainly:
+
+.. code-block:: C
+
+    strcpy(ifr.ifr_name, "can0");
+    ioctl(s, SIOCGIFINDEX, &ifr);
+    addr.can_ifindex = ifr.ifr_ifindex;
+    addr.can_family  = AF_CAN;
+
+    nbytes = sendto(s, &frame, sizeof(struct can_frame),
+                    0, (struct sockaddr*)&addr, sizeof(addr));
+
+An accurate timestamp can be obtained with an ioctl(2) call after reading
+a message from the socket:
+
+.. code-block:: C
+
+    struct timeval tv;
+    ioctl(s, SIOCGSTAMP, &tv);
+
+The timestamp has a resolution of one microsecond and is set automatically
+at the reception of a CAN frame.
+
+Remark about CAN FD (flexible data rate) support:
+
+Generally the handling of CAN FD is very similar to the formerly described
+examples. The new CAN FD capable CAN controllers support two different
+bitrates for the arbitration phase and the payload phase of the CAN FD frame
+and up to 64 bytes of payload. This extended payload length breaks all the
+kernel interfaces (ABI) which heavily rely on the CAN frame with fixed eight
+bytes of payload (struct can_frame) like the CAN_RAW socket. Therefore e.g.
+the CAN_RAW socket supports a new socket option CAN_RAW_FD_FRAMES that
+switches the socket into a mode that allows the handling of CAN FD frames
+and (legacy) CAN frames simultaneously (see :ref:`socketcan-rawfd`).
+
+The struct canfd_frame is defined in include/linux/can.h:
+
+.. code-block:: C
+
+    struct canfd_frame {
+            canid_t can_id;  /* 32 bit CAN_ID + EFF/RTR/ERR flags */
+            __u8    len;     /* frame payload length in byte (0 .. 64) */
+            __u8    flags;   /* additional flags for CAN FD */
+            __u8    __res0;  /* reserved / padding */
+            __u8    __res1;  /* reserved / padding */
+            __u8    data[64] __attribute__((aligned(8)));
+    };
+
+The struct canfd_frame and the existing struct can_frame have the can_id,
+the payload length and the payload data at the same offset inside their
+structures. This allows to handle the different structures very similar.
+When the content of a struct can_frame is copied into a struct canfd_frame
+all structure elements can be used as-is - only the data[] becomes extended.
+
+When introducing the struct canfd_frame it turned out that the data length
+code (DLC) of the struct can_frame was used as a length information as the
+length and the DLC has a 1:1 mapping in the range of 0 .. 8. To preserve
+the easy handling of the length information the canfd_frame.len element
+contains a plain length value from 0 .. 64. So both canfd_frame.len and
+can_frame.can_dlc are equal and contain a length information and no DLC.
+For details about the distinction of CAN and CAN FD capable devices and
+the mapping to the bus-relevant data length code (DLC), see :ref:`socketcan-can-fd-driver`.
+
+The length of the two CAN(FD) frame structures define the maximum transfer
+unit (MTU) of the CAN(FD) network interface and skbuff data length. Two
+definitions are specified for CAN specific MTUs in include/linux/can.h:
+
+.. code-block:: C
+
+  #define CAN_MTU   (sizeof(struct can_frame))   == 16  => 'legacy' CAN frame
+  #define CANFD_MTU (sizeof(struct canfd_frame)) == 72  => CAN FD frame
+
+
+.. _socketcan-raw-sockets:
+
+RAW Protocol Sockets with can_filters (SOCK_RAW)
+------------------------------------------------
+
+Using CAN_RAW sockets is extensively comparable to the commonly
+known access to CAN character devices. To meet the new possibilities
+provided by the multi user SocketCAN approach, some reasonable
+defaults are set at RAW socket binding time:
+
+- The filters are set to exactly one filter receiving everything
+- The socket only receives valid data frames (=> no error message frames)
+- The loopback of sent CAN frames is enabled (see :ref:`socketcan-local-loopback2`)
+- The socket does not receive its own sent frames (in loopback mode)
+
+These default settings may be changed before or after binding the socket.
+To use the referenced definitions of the socket options for CAN_RAW
+sockets, include <linux/can/raw.h>.
+
+
+.. _socketcan-rawfilter:
+
+RAW socket option CAN_RAW_FILTER
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The reception of CAN frames using CAN_RAW sockets can be controlled
+by defining 0 .. n filters with the CAN_RAW_FILTER socket option.
+
+The CAN filter structure is defined in include/linux/can.h:
+
+.. code-block:: C
+
+    struct can_filter {
+            canid_t can_id;
+            canid_t can_mask;
+    };
+
+A filter matches, when:
+
+.. code-block:: C
+
+    <received_can_id> & mask == can_id & mask
+
+which is analogous to known CAN controllers hardware filter semantics.
+The filter can be inverted in this semantic, when the CAN_INV_FILTER
+bit is set in can_id element of the can_filter structure. In
+contrast to CAN controller hardware filters the user may set 0 .. n
+receive filters for each open socket separately:
+
+.. code-block:: C
+
+    struct can_filter rfilter[2];
+
+    rfilter[0].can_id   = 0x123;
+    rfilter[0].can_mask = CAN_SFF_MASK;
+    rfilter[1].can_id   = 0x200;
+    rfilter[1].can_mask = 0x700;
+
+    setsockopt(s, SOL_CAN_RAW, CAN_RAW_FILTER, &rfilter, sizeof(rfilter));
+
+To disable the reception of CAN frames on the selected CAN_RAW socket:
+
+.. code-block:: C
+
+    setsockopt(s, SOL_CAN_RAW, CAN_RAW_FILTER, NULL, 0);
+
+To set the filters to zero filters is quite obsolete as to not read
+data causes the raw socket to discard the received CAN frames. But
+having this 'send only' use-case we may remove the receive list in the
+Kernel to save a little (really a very little!) CPU usage.
+
+CAN Filter Usage Optimisation
+.............................
+
+The CAN filters are processed in per-device filter lists at CAN frame
+reception time. To reduce the number of checks that need to be performed
+while walking through the filter lists the CAN core provides an optimized
+filter handling when the filter subscription focusses on a single CAN ID.
+
+For the possible 2048 SFF CAN identifiers the identifier is used as an index
+to access the corresponding subscription list without any further checks.
+For the 2^29 possible EFF CAN identifiers a 10 bit XOR folding is used as
+hash function to retrieve the EFF table index.
+
+To benefit from the optimized filters for single CAN identifiers the
+CAN_SFF_MASK or CAN_EFF_MASK have to be set into can_filter.mask together
+with set CAN_EFF_FLAG and CAN_RTR_FLAG bits. A set CAN_EFF_FLAG bit in the
+can_filter.mask makes clear that it matters whether a SFF or EFF CAN ID is
+subscribed. E.g. in the example from above:
+
+.. code-block:: C
+
+    rfilter[0].can_id   = 0x123;
+    rfilter[0].can_mask = CAN_SFF_MASK;
+
+both SFF frames with CAN ID 0x123 and EFF frames with 0xXXXXX123 can pass.
+
+To filter for only 0x123 (SFF) and 0x12345678 (EFF) CAN identifiers the
+filter has to be defined in this way to benefit from the optimized filters:
+
+.. code-block:: C
+
+    struct can_filter rfilter[2];
+
+    rfilter[0].can_id   = 0x123;
+    rfilter[0].can_mask = (CAN_EFF_FLAG | CAN_RTR_FLAG | CAN_SFF_MASK);
+    rfilter[1].can_id   = 0x12345678 | CAN_EFF_FLAG;
+    rfilter[1].can_mask = (CAN_EFF_FLAG | CAN_RTR_FLAG | CAN_EFF_MASK);
+
+    setsockopt(s, SOL_CAN_RAW, CAN_RAW_FILTER, &rfilter, sizeof(rfilter));
+
+
+RAW Socket Option CAN_RAW_ERR_FILTER
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As described in :ref:`socketcan-network-problem-notifications` the CAN interface driver can generate so
+called Error Message Frames that can optionally be passed to the user
+application in the same way as other CAN frames. The possible
+errors are divided into different error classes that may be filtered
+using the appropriate error mask. To register for every possible
+error condition CAN_ERR_MASK can be used as value for the error mask.
+The values for the error mask are defined in linux/can/error.h:
+
+.. code-block:: C
+
+    can_err_mask_t err_mask = ( CAN_ERR_TX_TIMEOUT | CAN_ERR_BUSOFF );
+
+    setsockopt(s, SOL_CAN_RAW, CAN_RAW_ERR_FILTER,
+               &err_mask, sizeof(err_mask));
+
+
+RAW Socket Option CAN_RAW_LOOPBACK
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+To meet multi user needs the local loopback is enabled by default
+(see :ref:`socketcan-local-loopback1` for details). But in some embedded use-cases
+(e.g. when only one application uses the CAN bus) this loopback
+functionality can be disabled (separately for each socket):
+
+.. code-block:: C
+
+    int loopback = 0; /* 0 = disabled, 1 = enabled (default) */
+
+    setsockopt(s, SOL_CAN_RAW, CAN_RAW_LOOPBACK, &loopback, sizeof(loopback));
+
+
+RAW socket option CAN_RAW_RECV_OWN_MSGS
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+When the local loopback is enabled, all the sent CAN frames are
+looped back to the open CAN sockets that registered for the CAN
+frames' CAN-ID on this given interface to meet the multi user
+needs. The reception of the CAN frames on the same socket that was
+sending the CAN frame is assumed to be unwanted and therefore
+disabled by default. This default behaviour may be changed on
+demand:
+
+.. code-block:: C
+
+    int recv_own_msgs = 1; /* 0 = disabled (default), 1 = enabled */
+
+    setsockopt(s, SOL_CAN_RAW, CAN_RAW_RECV_OWN_MSGS,
+               &recv_own_msgs, sizeof(recv_own_msgs));
+
+
+.. _socketcan-rawfd:
+
+RAW Socket Option CAN_RAW_FD_FRAMES
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+CAN FD support in CAN_RAW sockets can be enabled with a new socket option
+CAN_RAW_FD_FRAMES which is off by default. When the new socket option is
+not supported by the CAN_RAW socket (e.g. on older kernels), switching the
+CAN_RAW_FD_FRAMES option returns the error -ENOPROTOOPT.
+
+Once CAN_RAW_FD_FRAMES is enabled the application can send both CAN frames
+and CAN FD frames. OTOH the application has to handle CAN and CAN FD frames
+when reading from the socket:
+
+.. code-block:: C
+
+    CAN_RAW_FD_FRAMES enabled:  CAN_MTU and CANFD_MTU are allowed
+    CAN_RAW_FD_FRAMES disabled: only CAN_MTU is allowed (default)
+
+Example:
+
+.. code-block:: C
+
+    [ remember: CANFD_MTU == sizeof(struct canfd_frame) ]
+
+    struct canfd_frame cfd;
+
+    nbytes = read(s, &cfd, CANFD_MTU);
+
+    if (nbytes == CANFD_MTU) {
+            printf("got CAN FD frame with length %d\n", cfd.len);
+            /* cfd.flags contains valid data */
+    } else if (nbytes == CAN_MTU) {
+            printf("got legacy CAN frame with length %d\n", cfd.len);
+            /* cfd.flags is undefined */
+    } else {
+            fprintf(stderr, "read: invalid CAN(FD) frame\n");
+            return 1;
+    }
+
+    /* the content can be handled independently from the received MTU size */
+
+    printf("can_id: %X data length: %d data: ", cfd.can_id, cfd.len);
+    for (i = 0; i < cfd.len; i++)
+            printf("%02X ", cfd.data[i]);
+
+When reading with size CANFD_MTU only returns CAN_MTU bytes that have
+been received from the socket a legacy CAN frame has been read into the
+provided CAN FD structure. Note that the canfd_frame.flags data field is
+not specified in the struct can_frame and therefore it is only valid in
+CANFD_MTU sized CAN FD frames.
+
+Implementation hint for new CAN applications:
+
+To build a CAN FD aware application use struct canfd_frame as basic CAN
+data structure for CAN_RAW based applications. When the application is
+executed on an older Linux kernel and switching the CAN_RAW_FD_FRAMES
+socket option returns an error: No problem. You'll get legacy CAN frames
+or CAN FD frames and can process them the same way.
+
+When sending to CAN devices make sure that the device is capable to handle
+CAN FD frames by checking if the device maximum transfer unit is CANFD_MTU.
+The CAN device MTU can be retrieved e.g. with a SIOCGIFMTU ioctl() syscall.
+
+
+RAW socket option CAN_RAW_JOIN_FILTERS
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The CAN_RAW socket can set multiple CAN identifier specific filters that
+lead to multiple filters in the af_can.c filter processing. These filters
+are indenpendent from each other which leads to logical OR'ed filters when
+applied (see :ref:`socketcan-rawfilter`).
+
+This socket option joines the given CAN filters in the way that only CAN
+frames are passed to user space that matched *all* given CAN filters. The
+semantic for the applied filters is therefore changed to a logical AND.
+
+This is useful especially when the filterset is a combination of filters
+where the CAN_INV_FILTER flag is set in order to notch single CAN IDs or
+CAN ID ranges from the incoming traffic.
+
+
+RAW Socket Returned Message Flags
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+When using recvmsg() call, the msg->msg_flags may contain following flags:
+
+MSG_DONTROUTE:
+	set when the received frame was created on the local host.
+
+MSG_CONFIRM:
+	set when the frame was sent via the socket it is received on.
+	This flag can be interpreted as a 'transmission confirmation' when the
+	CAN driver supports the echo of frames on driver level, see
+	:ref:`socketcan-local-loopback1` and :ref:`socketcan-local-loopback2`.
+	In order to receive such messages, CAN_RAW_RECV_OWN_MSGS must be set.
+
+
+Broadcast Manager Protocol Sockets (SOCK_DGRAM)
+-----------------------------------------------
+
+The Broadcast Manager protocol provides a command based configuration
+interface to filter and send (e.g. cyclic) CAN messages in kernel space.
+
+Receive filters can be used to down sample frequent messages; detect events
+such as message contents changes, packet length changes, and do time-out
+monitoring of received messages.
+
+Periodic transmission tasks of CAN frames or a sequence of CAN frames can be
+created and modified at runtime; both the message content and the two
+possible transmit intervals can be altered.
+
+A BCM socket is not intended for sending individual CAN frames using the
+struct can_frame as known from the CAN_RAW socket. Instead a special BCM
+configuration message is defined. The basic BCM configuration message used
+to communicate with the broadcast manager and the available operations are
+defined in the linux/can/bcm.h include. The BCM message consists of a
+message header with a command ('opcode') followed by zero or more CAN frames.
+The broadcast manager sends responses to user space in the same form:
+
+.. code-block:: C
+
+    struct bcm_msg_head {
+            __u32 opcode;                   /* command */
+            __u32 flags;                    /* special flags */
+            __u32 count;                    /* run 'count' times with ival1 */
+            struct timeval ival1, ival2;    /* count and subsequent interval */
+            canid_t can_id;                 /* unique can_id for task */
+            __u32 nframes;                  /* number of can_frames following */
+            struct can_frame frames[0];
+    };
+
+The aligned payload 'frames' uses the same basic CAN frame structure defined
+at the beginning of :ref:`socketcan-rawfd` and in the include/linux/can.h include. All
+messages to the broadcast manager from user space have this structure.
+
+Note a CAN_BCM socket must be connected instead of bound after socket
+creation (example without error checking):
+
+.. code-block:: C
+
+    int s;
+    struct sockaddr_can addr;
+    struct ifreq ifr;
+
+    s = socket(PF_CAN, SOCK_DGRAM, CAN_BCM);
+
+    strcpy(ifr.ifr_name, "can0");
+    ioctl(s, SIOCGIFINDEX, &ifr);
+
+    addr.can_family = AF_CAN;
+    addr.can_ifindex = ifr.ifr_ifindex;
+
+    connect(s, (struct sockaddr *)&addr, sizeof(addr));
+
+    (..)
+
+The broadcast manager socket is able to handle any number of in flight
+transmissions or receive filters concurrently. The different RX/TX jobs are
+distinguished by the unique can_id in each BCM message. However additional
+CAN_BCM sockets are recommended to communicate on multiple CAN interfaces.
+When the broadcast manager socket is bound to 'any' CAN interface (=> the
+interface index is set to zero) the configured receive filters apply to any
+CAN interface unless the sendto() syscall is used to overrule the 'any' CAN
+interface index. When using recvfrom() instead of read() to retrieve BCM
+socket messages the originating CAN interface is provided in can_ifindex.
+
+
+Broadcast Manager Operations
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The opcode defines the operation for the broadcast manager to carry out,
+or details the broadcast managers response to several events, including
+user requests.
+
+Transmit Operations (user space to broadcast manager):
+
+TX_SETUP:
+	Create (cyclic) transmission task.
+
+TX_DELETE:
+	Remove (cyclic) transmission task, requires only can_id.
+
+TX_READ:
+	Read properties of (cyclic) transmission task for can_id.
+
+TX_SEND:
+	Send one CAN frame.
+
+Transmit Responses (broadcast manager to user space):
+
+TX_STATUS:
+	Reply to TX_READ request (transmission task configuration).
+
+TX_EXPIRED:
+	Notification when counter finishes sending at initial interval
+	'ival1'. Requires the TX_COUNTEVT flag to be set at TX_SETUP.
+
+Receive Operations (user space to broadcast manager):
+
+RX_SETUP:
+	Create RX content filter subscription.
+
+RX_DELETE:
+	Remove RX content filter subscription, requires only can_id.
+
+RX_READ:
+	Read properties of RX content filter subscription for can_id.
+
+Receive Responses (broadcast manager to user space):
+
+RX_STATUS:
+	Reply to RX_READ request (filter task configuration).
+
+RX_TIMEOUT:
+	Cyclic message is detected to be absent (timer ival1 expired).
+
+RX_CHANGED:
+	BCM message with updated CAN frame (detected content change).
+	Sent on first message received or on receipt of revised CAN messages.
+
+
+Broadcast Manager Message Flags
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+When sending a message to the broadcast manager the 'flags' element may
+contain the following flag definitions which influence the behaviour:
+
+SETTIMER:
+	Set the values of ival1, ival2 and count
+
+STARTTIMER:
+	Start the timer with the actual values of ival1, ival2
+	and count. Starting the timer leads simultaneously to emit a CAN frame.
+
+TX_COUNTEVT:
+	Create the message TX_EXPIRED when count expires
+
+TX_ANNOUNCE:
+	A change of data by the process is emitted immediately.
+
+TX_CP_CAN_ID:
+	Copies the can_id from the message header to each
+	subsequent frame in frames. This is intended as usage simplification. For
+	TX tasks the unique can_id from the message header may differ from the
+	can_id(s) stored for transmission in the subsequent struct can_frame(s).
+
+RX_FILTER_ID:
+	Filter by can_id alone, no frames required (nframes=0).
+
+RX_CHECK_DLC:
+	A change of the DLC leads to an RX_CHANGED.
+
+RX_NO_AUTOTIMER:
+	Prevent automatically starting the timeout monitor.
+
+RX_ANNOUNCE_RESUME:
+	If passed at RX_SETUP and a receive timeout occurred, a
+	RX_CHANGED message will be generated when the (cyclic) receive restarts.
+
+TX_RESET_MULTI_IDX:
+	Reset the index for the multiple frame transmission.
+
+RX_RTR_FRAME:
+	Send reply for RTR-request (placed in op->frames[0]).
+
+
+Broadcast Manager Transmission Timers
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Periodic transmission configurations may use up to two interval timers.
+In this case the BCM sends a number of messages ('count') at an interval
+'ival1', then continuing to send at another given interval 'ival2'. When
+only one timer is needed 'count' is set to zero and only 'ival2' is used.
+When SET_TIMER and START_TIMER flag were set the timers are activated.
+The timer values can be altered at runtime when only SET_TIMER is set.
+
+
+Broadcast Manager message sequence transmission
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Up to 256 CAN frames can be transmitted in a sequence in the case of a cyclic
+TX task configuration. The number of CAN frames is provided in the 'nframes'
+element of the BCM message head. The defined number of CAN frames are added
+as array to the TX_SETUP BCM configuration message:
+
+.. code-block:: C
+
+    /* create a struct to set up a sequence of four CAN frames */
+    struct {
+            struct bcm_msg_head msg_head;
+            struct can_frame frame[4];
+    } mytxmsg;
+
+    (..)
+    mytxmsg.msg_head.nframes = 4;
+    (..)
+
+    write(s, &mytxmsg, sizeof(mytxmsg));
+
+With every transmission the index in the array of CAN frames is increased
+and set to zero at index overflow.
+
+
+Broadcast Manager Receive Filter Timers
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The timer values ival1 or ival2 may be set to non-zero values at RX_SETUP.
+When the SET_TIMER flag is set the timers are enabled:
+
+ival1:
+	Send RX_TIMEOUT when a received message is not received again within
+	the given time. When START_TIMER is set at RX_SETUP the timeout detection
+	is activated directly - even without a former CAN frame reception.
+
+ival2:
+	Throttle the received message rate down to the value of ival2. This
+	is useful to reduce messages for the application when the signal inside the
+	CAN frame is stateless as state changes within the ival2 periode may get
+	lost.
+
+Broadcast Manager Multiplex Message Receive Filter
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+To filter for content changes in multiplex message sequences an array of more
+than one CAN frames can be passed in a RX_SETUP configuration message. The
+data bytes of the first CAN frame contain the mask of relevant bits that
+have to match in the subsequent CAN frames with the received CAN frame.
+If one of the subsequent CAN frames is matching the bits in that frame data
+mark the relevant content to be compared with the previous received content.
+Up to 257 CAN frames (multiplex filter bit mask CAN frame plus 256 CAN
+filters) can be added as array to the TX_SETUP BCM configuration message:
+
+.. code-block:: C
+
+    /* usually used to clear CAN frame data[] - beware of endian problems! */
+    #define U64_DATA(p) (*(unsigned long long*)(p)->data)
+
+    struct {
+            struct bcm_msg_head msg_head;
+            struct can_frame frame[5];
+    } msg;
+
+    msg.msg_head.opcode  = RX_SETUP;
+    msg.msg_head.can_id  = 0x42;
+    msg.msg_head.flags   = 0;
+    msg.msg_head.nframes = 5;
+    U64_DATA(&msg.frame[0]) = 0xFF00000000000000ULL; /* MUX mask */
+    U64_DATA(&msg.frame[1]) = 0x01000000000000FFULL; /* data mask (MUX 0x01) */
+    U64_DATA(&msg.frame[2]) = 0x0200FFFF000000FFULL; /* data mask (MUX 0x02) */
+    U64_DATA(&msg.frame[3]) = 0x330000FFFFFF0003ULL; /* data mask (MUX 0x33) */
+    U64_DATA(&msg.frame[4]) = 0x4F07FC0FF0000000ULL; /* data mask (MUX 0x4F) */
+
+    write(s, &msg, sizeof(msg));
+
+
+Broadcast Manager CAN FD Support
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The programming API of the CAN_BCM depends on struct can_frame which is
+given as array directly behind the bcm_msg_head structure. To follow this
+schema for the CAN FD frames a new flag 'CAN_FD_FRAME' in the bcm_msg_head
+flags indicates that the concatenated CAN frame structures behind the
+bcm_msg_head are defined as struct canfd_frame:
+
+.. code-block:: C
+
+    struct {
+            struct bcm_msg_head msg_head;
+            struct canfd_frame frame[5];
+    } msg;
+
+    msg.msg_head.opcode  = RX_SETUP;
+    msg.msg_head.can_id  = 0x42;
+    msg.msg_head.flags   = CAN_FD_FRAME;
+    msg.msg_head.nframes = 5;
+    (..)
+
+When using CAN FD frames for multiplex filtering the MUX mask is still
+expected in the first 64 bit of the struct canfd_frame data section.
+
+
+Connected Transport Protocols (SOCK_SEQPACKET)
+----------------------------------------------
+
+(to be written)
+
+
+Unconnected Transport Protocols (SOCK_DGRAM)
+--------------------------------------------
+
+(to be written)
+
+
+.. _socketcan-core-module:
+
+SocketCAN Core Module
+=====================
+
+The SocketCAN core module implements the protocol family
+PF_CAN. CAN protocol modules are loaded by the core module at
+runtime. The core module provides an interface for CAN protocol
+modules to subscribe needed CAN IDs (see :ref:`socketcan-receive-lists`).
+
+
+can.ko Module Params
+--------------------
+
+- **stats_timer**:
+  To calculate the SocketCAN core statistics
+  (e.g. current/maximum frames per second) this 1 second timer is
+  invoked at can.ko module start time by default. This timer can be
+  disabled by using stattimer=0 on the module commandline.
+
+- **debug**:
+  (removed since SocketCAN SVN r546)
+
+
+procfs content
+--------------
+
+As described in :ref:`socketcan-receive-lists` the SocketCAN core uses several filter
+lists to deliver received CAN frames to CAN protocol modules. These
+receive lists, their filters and the count of filter matches can be
+checked in the appropriate receive list. All entries contain the
+device and a protocol module identifier::
+
+    foo@bar:~$ cat /proc/net/can/rcvlist_all
+
+    receive list 'rx_all':
+      (vcan3: no entry)
+      (vcan2: no entry)
+      (vcan1: no entry)
+      device   can_id   can_mask  function  userdata   matches  ident
+       vcan0     000    00000000  f88e6370  f6c6f400         0  raw
+      (any: no entry)
+
+In this example an application requests any CAN traffic from vcan0::
+
+    rcvlist_all - list for unfiltered entries (no filter operations)
+    rcvlist_eff - list for single extended frame (EFF) entries
+    rcvlist_err - list for error message frames masks
+    rcvlist_fil - list for mask/value filters
+    rcvlist_inv - list for mask/value filters (inverse semantic)
+    rcvlist_sff - list for single standard frame (SFF) entries
+
+Additional procfs files in /proc/net/can::
+
+    stats       - SocketCAN core statistics (rx/tx frames, match ratios, ...)
+    reset_stats - manual statistic reset
+    version     - prints the SocketCAN core version and the ABI version
+
+
+Writing Own CAN Protocol Modules
+--------------------------------
+
+To implement a new protocol in the protocol family PF_CAN a new
+protocol has to be defined in include/linux/can.h .
+The prototypes and definitions to use the SocketCAN core can be
+accessed by including include/linux/can/core.h .
+In addition to functions that register the CAN protocol and the
+CAN device notifier chain there are functions to subscribe CAN
+frames received by CAN interfaces and to send CAN frames::
+
+    can_rx_register   - subscribe CAN frames from a specific interface
+    can_rx_unregister - unsubscribe CAN frames from a specific interface
+    can_send          - transmit a CAN frame (optional with local loopback)
+
+For details see the kerneldoc documentation in net/can/af_can.c or
+the source code of net/can/raw.c or net/can/bcm.c .
+
+
+CAN Network Drivers
+===================
+
+Writing a CAN network device driver is much easier than writing a
+CAN character device driver. Similar to other known network device
+drivers you mainly have to deal with:
+
+- TX: Put the CAN frame from the socket buffer to the CAN controller.
+- RX: Put the CAN frame from the CAN controller to the socket buffer.
+
+See e.g. at Documentation/networking/netdevices.txt . The differences
+for writing CAN network device driver are described below:
+
+
+General Settings
+----------------
+
+.. code-block:: C
+
+    dev->type  = ARPHRD_CAN; /* the netdevice hardware type */
+    dev->flags = IFF_NOARP;  /* CAN has no arp */
+
+    dev->mtu = CAN_MTU; /* sizeof(struct can_frame) -> legacy CAN interface */
+
+    or alternative, when the controller supports CAN with flexible data rate:
+    dev->mtu = CANFD_MTU; /* sizeof(struct canfd_frame) -> CAN FD interface */
+
+The struct can_frame or struct canfd_frame is the payload of each socket
+buffer (skbuff) in the protocol family PF_CAN.
+
+
+.. _socketcan-local-loopback2:
+
+Local Loopback of Sent Frames
+-----------------------------
+
+As described in :ref:`socketcan-local-loopback1` the CAN network device driver should
+support a local loopback functionality similar to the local echo
+e.g. of tty devices. In this case the driver flag IFF_ECHO has to be
+set to prevent the PF_CAN core from locally echoing sent frames
+(aka loopback) as fallback solution::
+
+    dev->flags = (IFF_NOARP | IFF_ECHO);
+
+
+CAN Controller Hardware Filters
+-------------------------------
+
+To reduce the interrupt load on deep embedded systems some CAN
+controllers support the filtering of CAN IDs or ranges of CAN IDs.
+These hardware filter capabilities vary from controller to
+controller and have to be identified as not feasible in a multi-user
+networking approach. The use of the very controller specific
+hardware filters could make sense in a very dedicated use-case, as a
+filter on driver level would affect all users in the multi-user
+system. The high efficient filter sets inside the PF_CAN core allow
+to set different multiple filters for each socket separately.
+Therefore the use of hardware filters goes to the category 'handmade
+tuning on deep embedded systems'. The author is running a MPC603e
+@133MHz with four SJA1000 CAN controllers from 2002 under heavy bus
+load without any problems ...
+
+
+The Virtual CAN Driver (vcan)
+-----------------------------
+
+Similar to the network loopback devices, vcan offers a virtual local
+CAN interface. A full qualified address on CAN consists of
+
+- a unique CAN Identifier (CAN ID)
+- the CAN bus this CAN ID is transmitted on (e.g. can0)
+
+so in common use cases more than one virtual CAN interface is needed.
+
+The virtual CAN interfaces allow the transmission and reception of CAN
+frames without real CAN controller hardware. Virtual CAN network
+devices are usually named 'vcanX', like vcan0 vcan1 vcan2 ...
+When compiled as a module the virtual CAN driver module is called vcan.ko
+
+Since Linux Kernel version 2.6.24 the vcan driver supports the Kernel
+netlink interface to create vcan network devices. The creation and
+removal of vcan network devices can be managed with the ip(8) tool::
+
+  - Create a virtual CAN network interface:
+       $ ip link add type vcan
+
+  - Create a virtual CAN network interface with a specific name 'vcan42':
+       $ ip link add dev vcan42 type vcan
+
+  - Remove a (virtual CAN) network interface 'vcan42':
+       $ ip link del vcan42
+
+
+The CAN Network Device Driver Interface
+---------------------------------------
+
+The CAN network device driver interface provides a generic interface
+to setup, configure and monitor CAN network devices. The user can then
+configure the CAN device, like setting the bit-timing parameters, via
+the netlink interface using the program "ip" from the "IPROUTE2"
+utility suite. The following chapter describes briefly how to use it.
+Furthermore, the interface uses a common data structure and exports a
+set of common functions, which all real CAN network device drivers
+should use. Please have a look to the SJA1000 or MSCAN driver to
+understand how to use them. The name of the module is can-dev.ko.
+
+
+Netlink interface to set/get devices properties
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The CAN device must be configured via netlink interface. The supported
+netlink message types are defined and briefly described in
+"include/linux/can/netlink.h". CAN link support for the program "ip"
+of the IPROUTE2 utility suite is available and it can be used as shown
+below:
+
+Setting CAN device properties::
+
+    $ ip link set can0 type can help
+    Usage: ip link set DEVICE type can
+        [ bitrate BITRATE [ sample-point SAMPLE-POINT] ] |
+        [ tq TQ prop-seg PROP_SEG phase-seg1 PHASE-SEG1
+          phase-seg2 PHASE-SEG2 [ sjw SJW ] ]
+
+        [ dbitrate BITRATE [ dsample-point SAMPLE-POINT] ] |
+        [ dtq TQ dprop-seg PROP_SEG dphase-seg1 PHASE-SEG1
+          dphase-seg2 PHASE-SEG2 [ dsjw SJW ] ]
+
+        [ loopback { on | off } ]
+        [ listen-only { on | off } ]
+        [ triple-sampling { on | off } ]
+        [ one-shot { on | off } ]
+        [ berr-reporting { on | off } ]
+        [ fd { on | off } ]
+        [ fd-non-iso { on | off } ]
+        [ presume-ack { on | off } ]
+
+        [ restart-ms TIME-MS ]
+        [ restart ]
+
+        Where: BITRATE       := { 1..1000000 }
+               SAMPLE-POINT  := { 0.000..0.999 }
+               TQ            := { NUMBER }
+               PROP-SEG      := { 1..8 }
+               PHASE-SEG1    := { 1..8 }
+               PHASE-SEG2    := { 1..8 }
+               SJW           := { 1..4 }
+               RESTART-MS    := { 0 | NUMBER }
+
+Display CAN device details and statistics::
+
+    $ ip -details -statistics link show can0
+    2: can0: <NOARP,UP,LOWER_UP,ECHO> mtu 16 qdisc pfifo_fast state UP qlen 10
+      link/can
+      can <TRIPLE-SAMPLING> state ERROR-ACTIVE restart-ms 100
+      bitrate 125000 sample_point 0.875
+      tq 125 prop-seg 6 phase-seg1 7 phase-seg2 2 sjw 1
+      sja1000: tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1
+      clock 8000000
+      re-started bus-errors arbit-lost error-warn error-pass bus-off
+      41         17457      0          41         42         41
+      RX: bytes  packets  errors  dropped overrun mcast
+      140859     17608    17457   0       0       0
+      TX: bytes  packets  errors  dropped carrier collsns
+      861        112      0       41      0       0
+
+More info to the above output:
+
+"<TRIPLE-SAMPLING>"
+	Shows the list of selected CAN controller modes: LOOPBACK,
+	LISTEN-ONLY, or TRIPLE-SAMPLING.
+
+"state ERROR-ACTIVE"
+	The current state of the CAN controller: "ERROR-ACTIVE",
+	"ERROR-WARNING", "ERROR-PASSIVE", "BUS-OFF" or "STOPPED"
+
+"restart-ms 100"
+	Automatic restart delay time. If set to a non-zero value, a
+	restart of the CAN controller will be triggered automatically
+	in case of a bus-off condition after the specified delay time
+	in milliseconds. By default it's off.
+
+"bitrate 125000 sample-point 0.875"
+	Shows the real bit-rate in bits/sec and the sample-point in the
+	range 0.000..0.999. If the calculation of bit-timing parameters
+	is enabled in the kernel (CONFIG_CAN_CALC_BITTIMING=y), the
+	bit-timing can be defined by setting the "bitrate" argument.
+	Optionally the "sample-point" can be specified. By default it's
+	0.000 assuming CIA-recommended sample-points.
+
+"tq 125 prop-seg 6 phase-seg1 7 phase-seg2 2 sjw 1"
+	Shows the time quanta in ns, propagation segment, phase buffer
+	segment 1 and 2 and the synchronisation jump width in units of
+	tq. They allow to define the CAN bit-timing in a hardware
+	independent format as proposed by the Bosch CAN 2.0 spec (see
+	chapter 8 of http://www.semiconductors.bosch.de/pdf/can2spec.pdf).
+
+"sja1000: tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1 clock 8000000"
+	Shows the bit-timing constants of the CAN controller, here the
+	"sja1000". The minimum and maximum values of the time segment 1
+	and 2, the synchronisation jump width in units of tq, the
+	bitrate pre-scaler and the CAN system clock frequency in Hz.
+	These constants could be used for user-defined (non-standard)
+	bit-timing calculation algorithms in user-space.
+
+"re-started bus-errors arbit-lost error-warn error-pass bus-off"
+	Shows the number of restarts, bus and arbitration lost errors,
+	and the state changes to the error-warning, error-passive and
+	bus-off state. RX overrun errors are listed in the "overrun"
+	field of the standard network statistics.
+
+Setting the CAN Bit-Timing
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The CAN bit-timing parameters can always be defined in a hardware
+independent format as proposed in the Bosch CAN 2.0 specification
+specifying the arguments "tq", "prop_seg", "phase_seg1", "phase_seg2"
+and "sjw"::
+
+    $ ip link set canX type can tq 125 prop-seg 6 \
+				phase-seg1 7 phase-seg2 2 sjw 1
+
+If the kernel option CONFIG_CAN_CALC_BITTIMING is enabled, CIA
+recommended CAN bit-timing parameters will be calculated if the bit-
+rate is specified with the argument "bitrate"::
+
+    $ ip link set canX type can bitrate 125000
+
+Note that this works fine for the most common CAN controllers with
+standard bit-rates but may *fail* for exotic bit-rates or CAN system
+clock frequencies. Disabling CONFIG_CAN_CALC_BITTIMING saves some
+space and allows user-space tools to solely determine and set the
+bit-timing parameters. The CAN controller specific bit-timing
+constants can be used for that purpose. They are listed by the
+following command::
+
+    $ ip -details link show can0
+    ...
+      sja1000: clock 8000000 tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1
+
+
+Starting and Stopping the CAN Network Device
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+A CAN network device is started or stopped as usual with the command
+"ifconfig canX up/down" or "ip link set canX up/down". Be aware that
+you *must* define proper bit-timing parameters for real CAN devices
+before you can start it to avoid error-prone default settings::
+
+    $ ip link set canX up type can bitrate 125000
+
+A device may enter the "bus-off" state if too many errors occurred on
+the CAN bus. Then no more messages are received or sent. An automatic
+bus-off recovery can be enabled by setting the "restart-ms" to a
+non-zero value, e.g.::
+
+    $ ip link set canX type can restart-ms 100
+
+Alternatively, the application may realize the "bus-off" condition
+by monitoring CAN error message frames and do a restart when
+appropriate with the command::
+
+    $ ip link set canX type can restart
+
+Note that a restart will also create a CAN error message frame (see
+also :ref:`socketcan-network-problem-notifications`).
+
+
+.. _socketcan-can-fd-driver:
+
+CAN FD (Flexible Data Rate) Driver Support
+------------------------------------------
+
+CAN FD capable CAN controllers support two different bitrates for the
+arbitration phase and the payload phase of the CAN FD frame. Therefore a
+second bit timing has to be specified in order to enable the CAN FD bitrate.
+
+Additionally CAN FD capable CAN controllers support up to 64 bytes of
+payload. The representation of this length in can_frame.can_dlc and
+canfd_frame.len for userspace applications and inside the Linux network
+layer is a plain value from 0 .. 64 instead of the CAN 'data length code'.
+The data length code was a 1:1 mapping to the payload length in the legacy
+CAN frames anyway. The payload length to the bus-relevant DLC mapping is
+only performed inside the CAN drivers, preferably with the helper
+functions can_dlc2len() and can_len2dlc().
+
+The CAN netdevice driver capabilities can be distinguished by the network
+devices maximum transfer unit (MTU)::
+
+  MTU = 16 (CAN_MTU)   => sizeof(struct can_frame)   => 'legacy' CAN device
+  MTU = 72 (CANFD_MTU) => sizeof(struct canfd_frame) => CAN FD capable device
+
+The CAN device MTU can be retrieved e.g. with a SIOCGIFMTU ioctl() syscall.
+N.B. CAN FD capable devices can also handle and send legacy CAN frames.
+
+When configuring CAN FD capable CAN controllers an additional 'data' bitrate
+has to be set. This bitrate for the data phase of the CAN FD frame has to be
+at least the bitrate which was configured for the arbitration phase. This
+second bitrate is specified analogue to the first bitrate but the bitrate
+setting keywords for the 'data' bitrate start with 'd' e.g. dbitrate,
+dsample-point, dsjw or dtq and similar settings. When a data bitrate is set
+within the configuration process the controller option "fd on" can be
+specified to enable the CAN FD mode in the CAN controller. This controller
+option also switches the device MTU to 72 (CANFD_MTU).
+
+The first CAN FD specification presented as whitepaper at the International
+CAN Conference 2012 needed to be improved for data integrity reasons.
+Therefore two CAN FD implementations have to be distinguished today:
+
+- ISO compliant:     The ISO 11898-1:2015 CAN FD implementation (default)
+- non-ISO compliant: The CAN FD implementation following the 2012 whitepaper
+
+Finally there are three types of CAN FD controllers:
+
+1. ISO compliant (fixed)
+2. non-ISO compliant (fixed, like the M_CAN IP core v3.0.1 in m_can.c)
+3. ISO/non-ISO CAN FD controllers (switchable, like the PEAK PCAN-USB FD)
+
+The current ISO/non-ISO mode is announced by the CAN controller driver via
+netlink and displayed by the 'ip' tool (controller option FD-NON-ISO).
+The ISO/non-ISO-mode can be altered by setting 'fd-non-iso {on|off}' for
+switchable CAN FD controllers only.
+
+Example configuring 500 kbit/s arbitration bitrate and 4 Mbit/s data bitrate::
+
+    $ ip link set can0 up type can bitrate 500000 sample-point 0.75 \
+                                   dbitrate 4000000 dsample-point 0.8 fd on
+    $ ip -details link show can0
+    5: can0: <NOARP,UP,LOWER_UP,ECHO> mtu 72 qdisc pfifo_fast state UNKNOWN \
+             mode DEFAULT group default qlen 10
+    link/can  promiscuity 0
+    can <FD> state ERROR-ACTIVE (berr-counter tx 0 rx 0) restart-ms 0
+          bitrate 500000 sample-point 0.750
+          tq 50 prop-seg 14 phase-seg1 15 phase-seg2 10 sjw 1
+          pcan_usb_pro_fd: tseg1 1..64 tseg2 1..16 sjw 1..16 brp 1..1024 \
+          brp-inc 1
+          dbitrate 4000000 dsample-point 0.800
+          dtq 12 dprop-seg 7 dphase-seg1 8 dphase-seg2 4 dsjw 1
+          pcan_usb_pro_fd: dtseg1 1..16 dtseg2 1..8 dsjw 1..4 dbrp 1..1024 \
+          dbrp-inc 1
+          clock 80000000
+
+Example when 'fd-non-iso on' is added on this switchable CAN FD adapter::
+
+   can <FD,FD-NON-ISO> state ERROR-ACTIVE (berr-counter tx 0 rx 0) restart-ms 0
+
+
+Supported CAN Hardware
+----------------------
+
+Please check the "Kconfig" file in "drivers/net/can" to get an actual
+list of the support CAN hardware. On the SocketCAN project website
+(see :ref:`socketcan-resources`) there might be further drivers available, also for
+older kernel versions.
+
+
+.. _socketcan-resources:
+
+SocketCAN Resources
+===================
+
+The Linux CAN / SocketCAN project resources (project site / mailing list)
+are referenced in the MAINTAINERS file in the Linux source tree.
+Search for CAN NETWORK [LAYERS|DRIVERS].
+
+Credits
+=======
+
+- Oliver Hartkopp (PF_CAN core, filters, drivers, bcm, SJA1000 driver)
+- Urs Thuermann (PF_CAN core, kernel integration, socket interfaces, raw, vcan)
+- Jan Kizka (RT-SocketCAN core, Socket-API reconciliation)
+- Wolfgang Grandegger (RT-SocketCAN core & drivers, Raw Socket-API reviews, CAN device driver interface, MSCAN driver)
+- Robert Schwebel (design reviews, PTXdist integration)
+- Marc Kleine-Budde (design reviews, Kernel 2.6 cleanups, drivers)
+- Benedikt Spranger (reviews)
+- Thomas Gleixner (LKML reviews, coding style, posting hints)
+- Andrey Volkov (kernel subtree structure, ioctls, MSCAN driver)
+- Matthias Brukner (first SJA1000 CAN netdevice implementation Q2/2003)
+- Klaus Hitschler (PEAK driver integration)
+- Uwe Koppe (CAN netdevices with PF_PACKET approach)
+- Michael Schulze (driver layer loopback requirement, RT CAN drivers review)
+- Pavel Pisa (Bit-timing calculation)
+- Sascha Hauer (SJA1000 platform driver)
+- Sebastian Haas (SJA1000 EMS PCI driver)
+- Markus Plessing (SJA1000 EMS PCI driver)
+- Per Dalen (SJA1000 Kvaser PCI driver)
+- Sam Ravnborg (reviews, coding style, kbuild help)
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
deleted file mode 100644
index aa15b9ee2e70..000000000000
--- a/Documentation/networking/can.txt
+++ /dev/null
@@ -1,1308 +0,0 @@
-============================================================================
-
-can.txt
-
-Readme file for the Controller Area Network Protocol Family (aka SocketCAN)
-
-This file contains
-
-  1 Overview / What is SocketCAN
-
-  2 Motivation / Why using the socket API
-
-  3 SocketCAN concept
-    3.1 receive lists
-    3.2 local loopback of sent frames
-    3.3 network problem notifications
-
-  4 How to use SocketCAN
-    4.1 RAW protocol sockets with can_filters (SOCK_RAW)
-      4.1.1 RAW socket option CAN_RAW_FILTER
-      4.1.2 RAW socket option CAN_RAW_ERR_FILTER
-      4.1.3 RAW socket option CAN_RAW_LOOPBACK
-      4.1.4 RAW socket option CAN_RAW_RECV_OWN_MSGS
-      4.1.5 RAW socket option CAN_RAW_FD_FRAMES
-      4.1.6 RAW socket option CAN_RAW_JOIN_FILTERS
-      4.1.7 RAW socket returned message flags
-    4.2 Broadcast Manager protocol sockets (SOCK_DGRAM)
-      4.2.1 Broadcast Manager operations
-      4.2.2 Broadcast Manager message flags
-      4.2.3 Broadcast Manager transmission timers
-      4.2.4 Broadcast Manager message sequence transmission
-      4.2.5 Broadcast Manager receive filter timers
-      4.2.6 Broadcast Manager multiplex message receive filter
-      4.2.7 Broadcast Manager CAN FD support
-    4.3 connected transport protocols (SOCK_SEQPACKET)
-    4.4 unconnected transport protocols (SOCK_DGRAM)
-
-  5 SocketCAN core module
-    5.1 can.ko module params
-    5.2 procfs content
-    5.3 writing own CAN protocol modules
-
-  6 CAN network drivers
-    6.1 general settings
-    6.2 local loopback of sent frames
-    6.3 CAN controller hardware filters
-    6.4 The virtual CAN driver (vcan)
-    6.5 The CAN network device driver interface
-      6.5.1 Netlink interface to set/get devices properties
-      6.5.2 Setting the CAN bit-timing
-      6.5.3 Starting and stopping the CAN network device
-    6.6 CAN FD (flexible data rate) driver support
-    6.7 supported CAN hardware
-
-  7 SocketCAN resources
-
-  8 Credits
-
-============================================================================
-
-1. Overview / What is SocketCAN
---------------------------------
-
-The socketcan package is an implementation of CAN protocols
-(Controller Area Network) for Linux.  CAN is a networking technology
-which has widespread use in automation, embedded devices, and
-automotive fields.  While there have been other CAN implementations
-for Linux based on character devices, SocketCAN uses the Berkeley
-socket API, the Linux network stack and implements the CAN device
-drivers as network interfaces.  The CAN socket API has been designed
-as similar as possible to the TCP/IP protocols to allow programmers,
-familiar with network programming, to easily learn how to use CAN
-sockets.
-
-2. Motivation / Why using the socket API
-----------------------------------------
-
-There have been CAN implementations for Linux before SocketCAN so the
-question arises, why we have started another project.  Most existing
-implementations come as a device driver for some CAN hardware, they
-are based on character devices and provide comparatively little
-functionality.  Usually, there is only a hardware-specific device
-driver which provides a character device interface to send and
-receive raw CAN frames, directly to/from the controller hardware.
-Queueing of frames and higher-level transport protocols like ISO-TP
-have to be implemented in user space applications.  Also, most
-character-device implementations support only one single process to
-open the device at a time, similar to a serial interface.  Exchanging
-the CAN controller requires employment of another device driver and
-often the need for adaption of large parts of the application to the
-new driver's API.
-
-SocketCAN was designed to overcome all of these limitations.  A new
-protocol family has been implemented which provides a socket interface
-to user space applications and which builds upon the Linux network
-layer, enabling use all of the provided queueing functionality.  A device
-driver for CAN controller hardware registers itself with the Linux
-network layer as a network device, so that CAN frames from the
-controller can be passed up to the network layer and on to the CAN
-protocol family module and also vice-versa.  Also, the protocol family
-module provides an API for transport protocol modules to register, so
-that any number of transport protocols can be loaded or unloaded
-dynamically.  In fact, the can core module alone does not provide any
-protocol and cannot be used without loading at least one additional
-protocol module.  Multiple sockets can be opened at the same time,
-on different or the same protocol module and they can listen/send
-frames on different or the same CAN IDs.  Several sockets listening on
-the same interface for frames with the same CAN ID are all passed the
-same received matching CAN frames.  An application wishing to
-communicate using a specific transport protocol, e.g. ISO-TP, just
-selects that protocol when opening the socket, and then can read and
-write application data byte streams, without having to deal with
-CAN-IDs, frames, etc.
-
-Similar functionality visible from user-space could be provided by a
-character device, too, but this would lead to a technically inelegant
-solution for a couple of reasons:
-
-* Intricate usage.  Instead of passing a protocol argument to
-  socket(2) and using bind(2) to select a CAN interface and CAN ID, an
-  application would have to do all these operations using ioctl(2)s.
-
-* Code duplication.  A character device cannot make use of the Linux
-  network queueing code, so all that code would have to be duplicated
-  for CAN networking.
-
-* Abstraction.  In most existing character-device implementations, the
-  hardware-specific device driver for a CAN controller directly
-  provides the character device for the application to work with.
-  This is at least very unusual in Unix systems for both, char and
-  block devices.  For example you don't have a character device for a
-  certain UART of a serial interface, a certain sound chip in your
-  computer, a SCSI or IDE controller providing access to your hard
-  disk or tape streamer device.  Instead, you have abstraction layers
-  which provide a unified character or block device interface to the
-  application on the one hand, and a interface for hardware-specific
-  device drivers on the other hand.  These abstractions are provided
-  by subsystems like the tty layer, the audio subsystem or the SCSI
-  and IDE subsystems for the devices mentioned above.
-
-  The easiest way to implement a CAN device driver is as a character
-  device without such a (complete) abstraction layer, as is done by most
-  existing drivers.  The right way, however, would be to add such a
-  layer with all the functionality like registering for certain CAN
-  IDs, supporting several open file descriptors and (de)multiplexing
-  CAN frames between them, (sophisticated) queueing of CAN frames, and
-  providing an API for device drivers to register with.  However, then
-  it would be no more difficult, or may be even easier, to use the
-  networking framework provided by the Linux kernel, and this is what
-  SocketCAN does.
-
-  The use of the networking framework of the Linux kernel is just the
-  natural and most appropriate way to implement CAN for Linux.
-
-3. SocketCAN concept
----------------------
-
-  As described in chapter 2 it is the main goal of SocketCAN to
-  provide a socket interface to user space applications which builds
-  upon the Linux network layer. In contrast to the commonly known
-  TCP/IP and ethernet networking, the CAN bus is a broadcast-only(!)
-  medium that has no MAC-layer addressing like ethernet. The CAN-identifier
-  (can_id) is used for arbitration on the CAN-bus. Therefore the CAN-IDs
-  have to be chosen uniquely on the bus. When designing a CAN-ECU
-  network the CAN-IDs are mapped to be sent by a specific ECU.
-  For this reason a CAN-ID can be treated best as a kind of source address.
-
-  3.1 receive lists
-
-  The network transparent access of multiple applications leads to the
-  problem that different applications may be interested in the same
-  CAN-IDs from the same CAN network interface. The SocketCAN core
-  module - which implements the protocol family CAN - provides several
-  high efficient receive lists for this reason. If e.g. a user space
-  application opens a CAN RAW socket, the raw protocol module itself
-  requests the (range of) CAN-IDs from the SocketCAN core that are
-  requested by the user. The subscription and unsubscription of
-  CAN-IDs can be done for specific CAN interfaces or for all(!) known
-  CAN interfaces with the can_rx_(un)register() functions provided to
-  CAN protocol modules by the SocketCAN core (see chapter 5).
-  To optimize the CPU usage at runtime the receive lists are split up
-  into several specific lists per device that match the requested
-  filter complexity for a given use-case.
-
-  3.2 local loopback of sent frames
-
-  As known from other networking concepts the data exchanging
-  applications may run on the same or different nodes without any
-  change (except for the according addressing information):
-
-         ___   ___   ___                   _______   ___
-        | _ | | _ | | _ |                 | _   _ | | _ |
-        ||A|| ||B|| ||C||                 ||A| |B|| ||C||
-        |___| |___| |___|                 |_______| |___|
-          |     |     |                       |       |
-        -----------------(1)- CAN bus -(2)---------------
-
-  To ensure that application A receives the same information in the
-  example (2) as it would receive in example (1) there is need for
-  some kind of local loopback of the sent CAN frames on the appropriate
-  node.
-
-  The Linux network devices (by default) just can handle the
-  transmission and reception of media dependent frames. Due to the
-  arbitration on the CAN bus the transmission of a low prio CAN-ID
-  may be delayed by the reception of a high prio CAN frame. To
-  reflect the correct* traffic on the node the loopback of the sent
-  data has to be performed right after a successful transmission. If
-  the CAN network interface is not capable of performing the loopback for
-  some reason the SocketCAN core can do this task as a fallback solution.
-  See chapter 6.2 for details (recommended).
-
-  The loopback functionality is enabled by default to reflect standard
-  networking behaviour for CAN applications. Due to some requests from
-  the RT-SocketCAN group the loopback optionally may be disabled for each
-  separate socket. See sockopts from the CAN RAW sockets in chapter 4.1.
-
-  * = you really like to have this when you're running analyser tools
-      like 'candump' or 'cansniffer' on the (same) node.
-
-  3.3 network problem notifications
-
-  The use of the CAN bus may lead to several problems on the physical
-  and media access control layer. Detecting and logging of these lower
-  layer problems is a vital requirement for CAN users to identify
-  hardware issues on the physical transceiver layer as well as
-  arbitration problems and error frames caused by the different
-  ECUs. The occurrence of detected errors are important for diagnosis
-  and have to be logged together with the exact timestamp. For this
-  reason the CAN interface driver can generate so called Error Message
-  Frames that can optionally be passed to the user application in the
-  same way as other CAN frames. Whenever an error on the physical layer
-  or the MAC layer is detected (e.g. by the CAN controller) the driver
-  creates an appropriate error message frame. Error messages frames can
-  be requested by the user application using the common CAN filter
-  mechanisms. Inside this filter definition the (interested) type of
-  errors may be selected. The reception of error messages is disabled
-  by default. The format of the CAN error message frame is briefly
-  described in the Linux header file "include/uapi/linux/can/error.h".
-
-4. How to use SocketCAN
-------------------------
-
-  Like TCP/IP, you first need to open a socket for communicating over a
-  CAN network. Since SocketCAN implements a new protocol family, you
-  need to pass PF_CAN as the first argument to the socket(2) system
-  call. Currently, there are two CAN protocols to choose from, the raw
-  socket protocol and the broadcast manager (BCM). So to open a socket,
-  you would write
-
-    s = socket(PF_CAN, SOCK_RAW, CAN_RAW);
-
-  and
-
-    s = socket(PF_CAN, SOCK_DGRAM, CAN_BCM);
-
-  respectively.  After the successful creation of the socket, you would
-  normally use the bind(2) system call to bind the socket to a CAN
-  interface (which is different from TCP/IP due to different addressing
-  - see chapter 3). After binding (CAN_RAW) or connecting (CAN_BCM)
-  the socket, you can read(2) and write(2) from/to the socket or use
-  send(2), sendto(2), sendmsg(2) and the recv* counterpart operations
-  on the socket as usual. There are also CAN specific socket options
-  described below.
-
-  The basic CAN frame structure and the sockaddr structure are defined
-  in include/linux/can.h:
-
-    struct can_frame {
-            canid_t can_id;  /* 32 bit CAN_ID + EFF/RTR/ERR flags */
-            __u8    can_dlc; /* frame payload length in byte (0 .. 8) */
-            __u8    __pad;   /* padding */
-            __u8    __res0;  /* reserved / padding */
-            __u8    __res1;  /* reserved / padding */
-            __u8    data[8] __attribute__((aligned(8)));
-    };
-
-  The alignment of the (linear) payload data[] to a 64bit boundary
-  allows the user to define their own structs and unions to easily access
-  the CAN payload. There is no given byteorder on the CAN bus by
-  default. A read(2) system call on a CAN_RAW socket transfers a
-  struct can_frame to the user space.
-
-  The sockaddr_can structure has an interface index like the
-  PF_PACKET socket, that also binds to a specific interface:
-
-    struct sockaddr_can {
-            sa_family_t can_family;
-            int         can_ifindex;
-            union {
-                    /* transport protocol class address info (e.g. ISOTP) */
-                    struct { canid_t rx_id, tx_id; } tp;
-
-                    /* reserved for future CAN protocols address information */
-            } can_addr;
-    };
-
-  To determine the interface index an appropriate ioctl() has to
-  be used (example for CAN_RAW sockets without error checking):
-
-    int s;
-    struct sockaddr_can addr;
-    struct ifreq ifr;
-
-    s = socket(PF_CAN, SOCK_RAW, CAN_RAW);
-
-    strcpy(ifr.ifr_name, "can0" );
-    ioctl(s, SIOCGIFINDEX, &ifr);
-
-    addr.can_family = AF_CAN;
-    addr.can_ifindex = ifr.ifr_ifindex;
-
-    bind(s, (struct sockaddr *)&addr, sizeof(addr));
-
-    (..)
-
-  To bind a socket to all(!) CAN interfaces the interface index must
-  be 0 (zero). In this case the socket receives CAN frames from every
-  enabled CAN interface. To determine the originating CAN interface
-  the system call recvfrom(2) may be used instead of read(2). To send
-  on a socket that is bound to 'any' interface sendto(2) is needed to
-  specify the outgoing interface.
-
-  Reading CAN frames from a bound CAN_RAW socket (see above) consists
-  of reading a struct can_frame:
-
-    struct can_frame frame;
-
-    nbytes = read(s, &frame, sizeof(struct can_frame));
-
-    if (nbytes < 0) {
-            perror("can raw socket read");
-            return 1;
-    }
-
-    /* paranoid check ... */
-    if (nbytes < sizeof(struct can_frame)) {
-            fprintf(stderr, "read: incomplete CAN frame\n");
-            return 1;
-    }
-
-    /* do something with the received CAN frame */
-
-  Writing CAN frames can be done similarly, with the write(2) system call:
-
-    nbytes = write(s, &frame, sizeof(struct can_frame));
-
-  When the CAN interface is bound to 'any' existing CAN interface
-  (addr.can_ifindex = 0) it is recommended to use recvfrom(2) if the
-  information about the originating CAN interface is needed:
-
-    struct sockaddr_can addr;
-    struct ifreq ifr;
-    socklen_t len = sizeof(addr);
-    struct can_frame frame;
-
-    nbytes = recvfrom(s, &frame, sizeof(struct can_frame),
-                      0, (struct sockaddr*)&addr, &len);
-
-    /* get interface name of the received CAN frame */
-    ifr.ifr_ifindex = addr.can_ifindex;
-    ioctl(s, SIOCGIFNAME, &ifr);
-    printf("Received a CAN frame from interface %s", ifr.ifr_name);
-
-  To write CAN frames on sockets bound to 'any' CAN interface the
-  outgoing interface has to be defined certainly.
-
-    strcpy(ifr.ifr_name, "can0");
-    ioctl(s, SIOCGIFINDEX, &ifr);
-    addr.can_ifindex = ifr.ifr_ifindex;
-    addr.can_family  = AF_CAN;
-
-    nbytes = sendto(s, &frame, sizeof(struct can_frame),
-                    0, (struct sockaddr*)&addr, sizeof(addr));
-
-  An accurate timestamp can be obtained with an ioctl(2) call after reading
-  a message from the socket:
-
-    struct timeval tv;
-    ioctl(s, SIOCGSTAMP, &tv);
-
-  The timestamp has a resolution of one microsecond and is set automatically
-  at the reception of a CAN frame.
-
-  Remark about CAN FD (flexible data rate) support:
-
-  Generally the handling of CAN FD is very similar to the formerly described
-  examples. The new CAN FD capable CAN controllers support two different
-  bitrates for the arbitration phase and the payload phase of the CAN FD frame
-  and up to 64 bytes of payload. This extended payload length breaks all the
-  kernel interfaces (ABI) which heavily rely on the CAN frame with fixed eight
-  bytes of payload (struct can_frame) like the CAN_RAW socket. Therefore e.g.
-  the CAN_RAW socket supports a new socket option CAN_RAW_FD_FRAMES that
-  switches the socket into a mode that allows the handling of CAN FD frames
-  and (legacy) CAN frames simultaneously (see section 4.1.5).
-
-  The struct canfd_frame is defined in include/linux/can.h:
-
-    struct canfd_frame {
-            canid_t can_id;  /* 32 bit CAN_ID + EFF/RTR/ERR flags */
-            __u8    len;     /* frame payload length in byte (0 .. 64) */
-            __u8    flags;   /* additional flags for CAN FD */
-            __u8    __res0;  /* reserved / padding */
-            __u8    __res1;  /* reserved / padding */
-            __u8    data[64] __attribute__((aligned(8)));
-    };
-
-  The struct canfd_frame and the existing struct can_frame have the can_id,
-  the payload length and the payload data at the same offset inside their
-  structures. This allows to handle the different structures very similar.
-  When the content of a struct can_frame is copied into a struct canfd_frame
-  all structure elements can be used as-is - only the data[] becomes extended.
-
-  When introducing the struct canfd_frame it turned out that the data length
-  code (DLC) of the struct can_frame was used as a length information as the
-  length and the DLC has a 1:1 mapping in the range of 0 .. 8. To preserve
-  the easy handling of the length information the canfd_frame.len element
-  contains a plain length value from 0 .. 64. So both canfd_frame.len and
-  can_frame.can_dlc are equal and contain a length information and no DLC.
-  For details about the distinction of CAN and CAN FD capable devices and
-  the mapping to the bus-relevant data length code (DLC), see chapter 6.6.
-
-  The length of the two CAN(FD) frame structures define the maximum transfer
-  unit (MTU) of the CAN(FD) network interface and skbuff data length. Two
-  definitions are specified for CAN specific MTUs in include/linux/can.h :
-
-  #define CAN_MTU   (sizeof(struct can_frame))   == 16  => 'legacy' CAN frame
-  #define CANFD_MTU (sizeof(struct canfd_frame)) == 72  => CAN FD frame
-
-  4.1 RAW protocol sockets with can_filters (SOCK_RAW)
-
-  Using CAN_RAW sockets is extensively comparable to the commonly
-  known access to CAN character devices. To meet the new possibilities
-  provided by the multi user SocketCAN approach, some reasonable
-  defaults are set at RAW socket binding time:
-
-  - The filters are set to exactly one filter receiving everything
-  - The socket only receives valid data frames (=> no error message frames)
-  - The loopback of sent CAN frames is enabled (see chapter 3.2)
-  - The socket does not receive its own sent frames (in loopback mode)
-
-  These default settings may be changed before or after binding the socket.
-  To use the referenced definitions of the socket options for CAN_RAW
-  sockets, include <linux/can/raw.h>.
-
-  4.1.1 RAW socket option CAN_RAW_FILTER
-
-  The reception of CAN frames using CAN_RAW sockets can be controlled
-  by defining 0 .. n filters with the CAN_RAW_FILTER socket option.
-
-  The CAN filter structure is defined in include/linux/can.h:
-
-    struct can_filter {
-            canid_t can_id;
-            canid_t can_mask;
-    };
-
-  A filter matches, when
-
-    <received_can_id> & mask == can_id & mask
-
-  which is analogous to known CAN controllers hardware filter semantics.
-  The filter can be inverted in this semantic, when the CAN_INV_FILTER
-  bit is set in can_id element of the can_filter structure. In
-  contrast to CAN controller hardware filters the user may set 0 .. n
-  receive filters for each open socket separately:
-
-    struct can_filter rfilter[2];
-
-    rfilter[0].can_id   = 0x123;
-    rfilter[0].can_mask = CAN_SFF_MASK;
-    rfilter[1].can_id   = 0x200;
-    rfilter[1].can_mask = 0x700;
-
-    setsockopt(s, SOL_CAN_RAW, CAN_RAW_FILTER, &rfilter, sizeof(rfilter));
-
-  To disable the reception of CAN frames on the selected CAN_RAW socket:
-
-    setsockopt(s, SOL_CAN_RAW, CAN_RAW_FILTER, NULL, 0);
-
-  To set the filters to zero filters is quite obsolete as to not read
-  data causes the raw socket to discard the received CAN frames. But
-  having this 'send only' use-case we may remove the receive list in the
-  Kernel to save a little (really a very little!) CPU usage.
-
-  4.1.1.1 CAN filter usage optimisation
-
-  The CAN filters are processed in per-device filter lists at CAN frame
-  reception time. To reduce the number of checks that need to be performed
-  while walking through the filter lists the CAN core provides an optimized
-  filter handling when the filter subscription focusses on a single CAN ID.
-
-  For the possible 2048 SFF CAN identifiers the identifier is used as an index
-  to access the corresponding subscription list without any further checks.
-  For the 2^29 possible EFF CAN identifiers a 10 bit XOR folding is used as
-  hash function to retrieve the EFF table index.
-
-  To benefit from the optimized filters for single CAN identifiers the
-  CAN_SFF_MASK or CAN_EFF_MASK have to be set into can_filter.mask together
-  with set CAN_EFF_FLAG and CAN_RTR_FLAG bits. A set CAN_EFF_FLAG bit in the
-  can_filter.mask makes clear that it matters whether a SFF or EFF CAN ID is
-  subscribed. E.g. in the example from above
-
-    rfilter[0].can_id   = 0x123;
-    rfilter[0].can_mask = CAN_SFF_MASK;
-
-  both SFF frames with CAN ID 0x123 and EFF frames with 0xXXXXX123 can pass.
-
-  To filter for only 0x123 (SFF) and 0x12345678 (EFF) CAN identifiers the
-  filter has to be defined in this way to benefit from the optimized filters:
-
-    struct can_filter rfilter[2];
-
-    rfilter[0].can_id   = 0x123;
-    rfilter[0].can_mask = (CAN_EFF_FLAG | CAN_RTR_FLAG | CAN_SFF_MASK);
-    rfilter[1].can_id   = 0x12345678 | CAN_EFF_FLAG;
-    rfilter[1].can_mask = (CAN_EFF_FLAG | CAN_RTR_FLAG | CAN_EFF_MASK);
-
-    setsockopt(s, SOL_CAN_RAW, CAN_RAW_FILTER, &rfilter, sizeof(rfilter));
-
-  4.1.2 RAW socket option CAN_RAW_ERR_FILTER
-
-  As described in chapter 3.3 the CAN interface driver can generate so
-  called Error Message Frames that can optionally be passed to the user
-  application in the same way as other CAN frames. The possible
-  errors are divided into different error classes that may be filtered
-  using the appropriate error mask. To register for every possible
-  error condition CAN_ERR_MASK can be used as value for the error mask.
-  The values for the error mask are defined in linux/can/error.h .
-
-    can_err_mask_t err_mask = ( CAN_ERR_TX_TIMEOUT | CAN_ERR_BUSOFF );
-
-    setsockopt(s, SOL_CAN_RAW, CAN_RAW_ERR_FILTER,
-               &err_mask, sizeof(err_mask));
-
-  4.1.3 RAW socket option CAN_RAW_LOOPBACK
-
-  To meet multi user needs the local loopback is enabled by default
-  (see chapter 3.2 for details). But in some embedded use-cases
-  (e.g. when only one application uses the CAN bus) this loopback
-  functionality can be disabled (separately for each socket):
-
-    int loopback = 0; /* 0 = disabled, 1 = enabled (default) */
-
-    setsockopt(s, SOL_CAN_RAW, CAN_RAW_LOOPBACK, &loopback, sizeof(loopback));
-
-  4.1.4 RAW socket option CAN_RAW_RECV_OWN_MSGS
-
-  When the local loopback is enabled, all the sent CAN frames are
-  looped back to the open CAN sockets that registered for the CAN
-  frames' CAN-ID on this given interface to meet the multi user
-  needs. The reception of the CAN frames on the same socket that was
-  sending the CAN frame is assumed to be unwanted and therefore
-  disabled by default. This default behaviour may be changed on
-  demand:
-
-    int recv_own_msgs = 1; /* 0 = disabled (default), 1 = enabled */
-
-    setsockopt(s, SOL_CAN_RAW, CAN_RAW_RECV_OWN_MSGS,
-               &recv_own_msgs, sizeof(recv_own_msgs));
-
-  4.1.5 RAW socket option CAN_RAW_FD_FRAMES
-
-  CAN FD support in CAN_RAW sockets can be enabled with a new socket option
-  CAN_RAW_FD_FRAMES which is off by default. When the new socket option is
-  not supported by the CAN_RAW socket (e.g. on older kernels), switching the
-  CAN_RAW_FD_FRAMES option returns the error -ENOPROTOOPT.
-
-  Once CAN_RAW_FD_FRAMES is enabled the application can send both CAN frames
-  and CAN FD frames. OTOH the application has to handle CAN and CAN FD frames
-  when reading from the socket.
-
-    CAN_RAW_FD_FRAMES enabled:  CAN_MTU and CANFD_MTU are allowed
-    CAN_RAW_FD_FRAMES disabled: only CAN_MTU is allowed (default)
-
-  Example:
-    [ remember: CANFD_MTU == sizeof(struct canfd_frame) ]
-
-    struct canfd_frame cfd;
-
-    nbytes = read(s, &cfd, CANFD_MTU);
-
-    if (nbytes == CANFD_MTU) {
-            printf("got CAN FD frame with length %d\n", cfd.len);
-	    /* cfd.flags contains valid data */
-    } else if (nbytes == CAN_MTU) {
-            printf("got legacy CAN frame with length %d\n", cfd.len);
-	    /* cfd.flags is undefined */
-    } else {
-            fprintf(stderr, "read: invalid CAN(FD) frame\n");
-            return 1;
-    }
-
-    /* the content can be handled independently from the received MTU size */
-
-    printf("can_id: %X data length: %d data: ", cfd.can_id, cfd.len);
-    for (i = 0; i < cfd.len; i++)
-            printf("%02X ", cfd.data[i]);
-
-  When reading with size CANFD_MTU only returns CAN_MTU bytes that have
-  been received from the socket a legacy CAN frame has been read into the
-  provided CAN FD structure. Note that the canfd_frame.flags data field is
-  not specified in the struct can_frame and therefore it is only valid in
-  CANFD_MTU sized CAN FD frames.
-
-  Implementation hint for new CAN applications:
-
-  To build a CAN FD aware application use struct canfd_frame as basic CAN
-  data structure for CAN_RAW based applications. When the application is
-  executed on an older Linux kernel and switching the CAN_RAW_FD_FRAMES
-  socket option returns an error: No problem. You'll get legacy CAN frames
-  or CAN FD frames and can process them the same way.
-
-  When sending to CAN devices make sure that the device is capable to handle
-  CAN FD frames by checking if the device maximum transfer unit is CANFD_MTU.
-  The CAN device MTU can be retrieved e.g. with a SIOCGIFMTU ioctl() syscall.
-
-  4.1.6 RAW socket option CAN_RAW_JOIN_FILTERS
-
-  The CAN_RAW socket can set multiple CAN identifier specific filters that
-  lead to multiple filters in the af_can.c filter processing. These filters
-  are indenpendent from each other which leads to logical OR'ed filters when
-  applied (see 4.1.1).
-
-  This socket option joines the given CAN filters in the way that only CAN
-  frames are passed to user space that matched *all* given CAN filters. The
-  semantic for the applied filters is therefore changed to a logical AND.
-
-  This is useful especially when the filterset is a combination of filters
-  where the CAN_INV_FILTER flag is set in order to notch single CAN IDs or
-  CAN ID ranges from the incoming traffic.
-
-  4.1.7 RAW socket returned message flags
-
-  When using recvmsg() call, the msg->msg_flags may contain following flags:
-
-    MSG_DONTROUTE: set when the received frame was created on the local host.
-
-    MSG_CONFIRM: set when the frame was sent via the socket it is received on.
-      This flag can be interpreted as a 'transmission confirmation' when the
-      CAN driver supports the echo of frames on driver level, see 3.2 and 6.2.
-      In order to receive such messages, CAN_RAW_RECV_OWN_MSGS must be set.
-
-  4.2 Broadcast Manager protocol sockets (SOCK_DGRAM)
-
-  The Broadcast Manager protocol provides a command based configuration
-  interface to filter and send (e.g. cyclic) CAN messages in kernel space.
-
-  Receive filters can be used to down sample frequent messages; detect events
-  such as message contents changes, packet length changes, and do time-out
-  monitoring of received messages.
-
-  Periodic transmission tasks of CAN frames or a sequence of CAN frames can be
-  created and modified at runtime; both the message content and the two
-  possible transmit intervals can be altered.
-
-  A BCM socket is not intended for sending individual CAN frames using the
-  struct can_frame as known from the CAN_RAW socket. Instead a special BCM
-  configuration message is defined. The basic BCM configuration message used
-  to communicate with the broadcast manager and the available operations are
-  defined in the linux/can/bcm.h include. The BCM message consists of a
-  message header with a command ('opcode') followed by zero or more CAN frames.
-  The broadcast manager sends responses to user space in the same form:
-
-    struct bcm_msg_head {
-            __u32 opcode;                   /* command */
-            __u32 flags;                    /* special flags */
-            __u32 count;                    /* run 'count' times with ival1 */
-            struct timeval ival1, ival2;    /* count and subsequent interval */
-            canid_t can_id;                 /* unique can_id for task */
-            __u32 nframes;                  /* number of can_frames following */
-            struct can_frame frames[0];
-    };
-
-  The aligned payload 'frames' uses the same basic CAN frame structure defined
-  at the beginning of section 4 and in the include/linux/can.h include. All
-  messages to the broadcast manager from user space have this structure.
-
-  Note a CAN_BCM socket must be connected instead of bound after socket
-  creation (example without error checking):
-
-    int s;
-    struct sockaddr_can addr;
-    struct ifreq ifr;
-
-    s = socket(PF_CAN, SOCK_DGRAM, CAN_BCM);
-
-    strcpy(ifr.ifr_name, "can0");
-    ioctl(s, SIOCGIFINDEX, &ifr);
-
-    addr.can_family = AF_CAN;
-    addr.can_ifindex = ifr.ifr_ifindex;
-
-    connect(s, (struct sockaddr *)&addr, sizeof(addr));
-
-    (..)
-
-  The broadcast manager socket is able to handle any number of in flight
-  transmissions or receive filters concurrently. The different RX/TX jobs are
-  distinguished by the unique can_id in each BCM message. However additional
-  CAN_BCM sockets are recommended to communicate on multiple CAN interfaces.
-  When the broadcast manager socket is bound to 'any' CAN interface (=> the
-  interface index is set to zero) the configured receive filters apply to any
-  CAN interface unless the sendto() syscall is used to overrule the 'any' CAN
-  interface index. When using recvfrom() instead of read() to retrieve BCM
-  socket messages the originating CAN interface is provided in can_ifindex.
-
-  4.2.1 Broadcast Manager operations
-
-  The opcode defines the operation for the broadcast manager to carry out,
-  or details the broadcast managers response to several events, including
-  user requests.
-
-  Transmit Operations (user space to broadcast manager):
-
-    TX_SETUP:   Create (cyclic) transmission task.
-
-    TX_DELETE:  Remove (cyclic) transmission task, requires only can_id.
-
-    TX_READ:    Read properties of (cyclic) transmission task for can_id.
-
-    TX_SEND:    Send one CAN frame.
-
-  Transmit Responses (broadcast manager to user space):
-
-    TX_STATUS:  Reply to TX_READ request (transmission task configuration).
-
-    TX_EXPIRED: Notification when counter finishes sending at initial interval
-      'ival1'. Requires the TX_COUNTEVT flag to be set at TX_SETUP.
-
-  Receive Operations (user space to broadcast manager):
-
-    RX_SETUP:   Create RX content filter subscription.
-
-    RX_DELETE:  Remove RX content filter subscription, requires only can_id.
-
-    RX_READ:    Read properties of RX content filter subscription for can_id.
-
-  Receive Responses (broadcast manager to user space):
-
-    RX_STATUS:  Reply to RX_READ request (filter task configuration).
-
-    RX_TIMEOUT: Cyclic message is detected to be absent (timer ival1 expired).
-
-    RX_CHANGED: BCM message with updated CAN frame (detected content change).
-      Sent on first message received or on receipt of revised CAN messages.
-
-  4.2.2 Broadcast Manager message flags
-
-  When sending a message to the broadcast manager the 'flags' element may
-  contain the following flag definitions which influence the behaviour:
-
-    SETTIMER:           Set the values of ival1, ival2 and count
-
-    STARTTIMER:         Start the timer with the actual values of ival1, ival2
-      and count. Starting the timer leads simultaneously to emit a CAN frame.
-
-    TX_COUNTEVT:        Create the message TX_EXPIRED when count expires
-
-    TX_ANNOUNCE:        A change of data by the process is emitted immediately.
-
-    TX_CP_CAN_ID:       Copies the can_id from the message header to each
-      subsequent frame in frames. This is intended as usage simplification. For
-      TX tasks the unique can_id from the message header may differ from the
-      can_id(s) stored for transmission in the subsequent struct can_frame(s).
-
-    RX_FILTER_ID:       Filter by can_id alone, no frames required (nframes=0).
-
-    RX_CHECK_DLC:       A change of the DLC leads to an RX_CHANGED.
-
-    RX_NO_AUTOTIMER:    Prevent automatically starting the timeout monitor.
-
-    RX_ANNOUNCE_RESUME: If passed at RX_SETUP and a receive timeout occurred, a
-      RX_CHANGED message will be generated when the (cyclic) receive restarts.
-
-    TX_RESET_MULTI_IDX: Reset the index for the multiple frame transmission.
-
-    RX_RTR_FRAME:       Send reply for RTR-request (placed in op->frames[0]).
-
-  4.2.3 Broadcast Manager transmission timers
-
-  Periodic transmission configurations may use up to two interval timers.
-  In this case the BCM sends a number of messages ('count') at an interval
-  'ival1', then continuing to send at another given interval 'ival2'. When
-  only one timer is needed 'count' is set to zero and only 'ival2' is used.
-  When SET_TIMER and START_TIMER flag were set the timers are activated.
-  The timer values can be altered at runtime when only SET_TIMER is set.
-
-  4.2.4 Broadcast Manager message sequence transmission
-
-  Up to 256 CAN frames can be transmitted in a sequence in the case of a cyclic
-  TX task configuration. The number of CAN frames is provided in the 'nframes'
-  element of the BCM message head. The defined number of CAN frames are added
-  as array to the TX_SETUP BCM configuration message.
-
-    /* create a struct to set up a sequence of four CAN frames */
-    struct {
-            struct bcm_msg_head msg_head;
-            struct can_frame frame[4];
-    } mytxmsg;
-
-    (..)
-    mytxmsg.msg_head.nframes = 4;
-    (..)
-
-    write(s, &mytxmsg, sizeof(mytxmsg));
-
-  With every transmission the index in the array of CAN frames is increased
-  and set to zero at index overflow.
-
-  4.2.5 Broadcast Manager receive filter timers
-
-  The timer values ival1 or ival2 may be set to non-zero values at RX_SETUP.
-  When the SET_TIMER flag is set the timers are enabled:
-
-  ival1: Send RX_TIMEOUT when a received message is not received again within
-    the given time. When START_TIMER is set at RX_SETUP the timeout detection
-    is activated directly - even without a former CAN frame reception.
-
-  ival2: Throttle the received message rate down to the value of ival2. This
-    is useful to reduce messages for the application when the signal inside the
-    CAN frame is stateless as state changes within the ival2 periode may get
-    lost.
-
-  4.2.6 Broadcast Manager multiplex message receive filter
-
-  To filter for content changes in multiplex message sequences an array of more
-  than one CAN frames can be passed in a RX_SETUP configuration message. The
-  data bytes of the first CAN frame contain the mask of relevant bits that
-  have to match in the subsequent CAN frames with the received CAN frame.
-  If one of the subsequent CAN frames is matching the bits in that frame data
-  mark the relevant content to be compared with the previous received content.
-  Up to 257 CAN frames (multiplex filter bit mask CAN frame plus 256 CAN
-  filters) can be added as array to the TX_SETUP BCM configuration message.
-
-    /* usually used to clear CAN frame data[] - beware of endian problems! */
-    #define U64_DATA(p) (*(unsigned long long*)(p)->data)
-
-    struct {
-            struct bcm_msg_head msg_head;
-            struct can_frame frame[5];
-    } msg;
-
-    msg.msg_head.opcode  = RX_SETUP;
-    msg.msg_head.can_id  = 0x42;
-    msg.msg_head.flags   = 0;
-    msg.msg_head.nframes = 5;
-    U64_DATA(&msg.frame[0]) = 0xFF00000000000000ULL; /* MUX mask */
-    U64_DATA(&msg.frame[1]) = 0x01000000000000FFULL; /* data mask (MUX 0x01) */
-    U64_DATA(&msg.frame[2]) = 0x0200FFFF000000FFULL; /* data mask (MUX 0x02) */
-    U64_DATA(&msg.frame[3]) = 0x330000FFFFFF0003ULL; /* data mask (MUX 0x33) */
-    U64_DATA(&msg.frame[4]) = 0x4F07FC0FF0000000ULL; /* data mask (MUX 0x4F) */
-
-    write(s, &msg, sizeof(msg));
-
-  4.2.7 Broadcast Manager CAN FD support
-
-  The programming API of the CAN_BCM depends on struct can_frame which is
-  given as array directly behind the bcm_msg_head structure. To follow this
-  schema for the CAN FD frames a new flag 'CAN_FD_FRAME' in the bcm_msg_head
-  flags indicates that the concatenated CAN frame structures behind the
-  bcm_msg_head are defined as struct canfd_frame.
-
-    struct {
-            struct bcm_msg_head msg_head;
-            struct canfd_frame frame[5];
-    } msg;
-
-    msg.msg_head.opcode  = RX_SETUP;
-    msg.msg_head.can_id  = 0x42;
-    msg.msg_head.flags   = CAN_FD_FRAME;
-    msg.msg_head.nframes = 5;
-    (..)
-
-  When using CAN FD frames for multiplex filtering the MUX mask is still
-  expected in the first 64 bit of the struct canfd_frame data section.
-
-  4.3 connected transport protocols (SOCK_SEQPACKET)
-  4.4 unconnected transport protocols (SOCK_DGRAM)
-
-
-5. SocketCAN core module
--------------------------
-
-  The SocketCAN core module implements the protocol family
-  PF_CAN. CAN protocol modules are loaded by the core module at
-  runtime. The core module provides an interface for CAN protocol
-  modules to subscribe needed CAN IDs (see chapter 3.1).
-
-  5.1 can.ko module params
-
-  - stats_timer: To calculate the SocketCAN core statistics
-    (e.g. current/maximum frames per second) this 1 second timer is
-    invoked at can.ko module start time by default. This timer can be
-    disabled by using stattimer=0 on the module commandline.
-
-  - debug: (removed since SocketCAN SVN r546)
-
-  5.2 procfs content
-
-  As described in chapter 3.1 the SocketCAN core uses several filter
-  lists to deliver received CAN frames to CAN protocol modules. These
-  receive lists, their filters and the count of filter matches can be
-  checked in the appropriate receive list. All entries contain the
-  device and a protocol module identifier:
-
-    foo@bar:~$ cat /proc/net/can/rcvlist_all
-
-    receive list 'rx_all':
-      (vcan3: no entry)
-      (vcan2: no entry)
-      (vcan1: no entry)
-      device   can_id   can_mask  function  userdata   matches  ident
-       vcan0     000    00000000  f88e6370  f6c6f400         0  raw
-      (any: no entry)
-
-  In this example an application requests any CAN traffic from vcan0.
-
-    rcvlist_all - list for unfiltered entries (no filter operations)
-    rcvlist_eff - list for single extended frame (EFF) entries
-    rcvlist_err - list for error message frames masks
-    rcvlist_fil - list for mask/value filters
-    rcvlist_inv - list for mask/value filters (inverse semantic)
-    rcvlist_sff - list for single standard frame (SFF) entries
-
-  Additional procfs files in /proc/net/can
-
-    stats       - SocketCAN core statistics (rx/tx frames, match ratios, ...)
-    reset_stats - manual statistic reset
-    version     - prints the SocketCAN core version and the ABI version
-
-  5.3 writing own CAN protocol modules
-
-  To implement a new protocol in the protocol family PF_CAN a new
-  protocol has to be defined in include/linux/can.h .
-  The prototypes and definitions to use the SocketCAN core can be
-  accessed by including include/linux/can/core.h .
-  In addition to functions that register the CAN protocol and the
-  CAN device notifier chain there are functions to subscribe CAN
-  frames received by CAN interfaces and to send CAN frames:
-
-    can_rx_register   - subscribe CAN frames from a specific interface
-    can_rx_unregister - unsubscribe CAN frames from a specific interface
-    can_send          - transmit a CAN frame (optional with local loopback)
-
-  For details see the kerneldoc documentation in net/can/af_can.c or
-  the source code of net/can/raw.c or net/can/bcm.c .
-
-6. CAN network drivers
-----------------------
-
-  Writing a CAN network device driver is much easier than writing a
-  CAN character device driver. Similar to other known network device
-  drivers you mainly have to deal with:
-
-  - TX: Put the CAN frame from the socket buffer to the CAN controller.
-  - RX: Put the CAN frame from the CAN controller to the socket buffer.
-
-  See e.g. at Documentation/networking/netdevices.txt . The differences
-  for writing CAN network device driver are described below:
-
-  6.1 general settings
-
-    dev->type  = ARPHRD_CAN; /* the netdevice hardware type */
-    dev->flags = IFF_NOARP;  /* CAN has no arp */
-
-    dev->mtu = CAN_MTU; /* sizeof(struct can_frame) -> legacy CAN interface */
-
-    or alternative, when the controller supports CAN with flexible data rate:
-    dev->mtu = CANFD_MTU; /* sizeof(struct canfd_frame) -> CAN FD interface */
-
-  The struct can_frame or struct canfd_frame is the payload of each socket
-  buffer (skbuff) in the protocol family PF_CAN.
-
-  6.2 local loopback of sent frames
-
-  As described in chapter 3.2 the CAN network device driver should
-  support a local loopback functionality similar to the local echo
-  e.g. of tty devices. In this case the driver flag IFF_ECHO has to be
-  set to prevent the PF_CAN core from locally echoing sent frames
-  (aka loopback) as fallback solution:
-
-    dev->flags = (IFF_NOARP | IFF_ECHO);
-
-  6.3 CAN controller hardware filters
-
-  To reduce the interrupt load on deep embedded systems some CAN
-  controllers support the filtering of CAN IDs or ranges of CAN IDs.
-  These hardware filter capabilities vary from controller to
-  controller and have to be identified as not feasible in a multi-user
-  networking approach. The use of the very controller specific
-  hardware filters could make sense in a very dedicated use-case, as a
-  filter on driver level would affect all users in the multi-user
-  system. The high efficient filter sets inside the PF_CAN core allow
-  to set different multiple filters for each socket separately.
-  Therefore the use of hardware filters goes to the category 'handmade
-  tuning on deep embedded systems'. The author is running a MPC603e
-  @133MHz with four SJA1000 CAN controllers from 2002 under heavy bus
-  load without any problems ...
-
-  6.4 The virtual CAN driver (vcan)
-
-  Similar to the network loopback devices, vcan offers a virtual local
-  CAN interface. A full qualified address on CAN consists of
-
-  - a unique CAN Identifier (CAN ID)
-  - the CAN bus this CAN ID is transmitted on (e.g. can0)
-
-  so in common use cases more than one virtual CAN interface is needed.
-
-  The virtual CAN interfaces allow the transmission and reception of CAN
-  frames without real CAN controller hardware. Virtual CAN network
-  devices are usually named 'vcanX', like vcan0 vcan1 vcan2 ...
-  When compiled as a module the virtual CAN driver module is called vcan.ko
-
-  Since Linux Kernel version 2.6.24 the vcan driver supports the Kernel
-  netlink interface to create vcan network devices. The creation and
-  removal of vcan network devices can be managed with the ip(8) tool:
-
-  - Create a virtual CAN network interface:
-       $ ip link add type vcan
-
-  - Create a virtual CAN network interface with a specific name 'vcan42':
-       $ ip link add dev vcan42 type vcan
-
-  - Remove a (virtual CAN) network interface 'vcan42':
-       $ ip link del vcan42
-
-  6.5 The CAN network device driver interface
-
-  The CAN network device driver interface provides a generic interface
-  to setup, configure and monitor CAN network devices. The user can then
-  configure the CAN device, like setting the bit-timing parameters, via
-  the netlink interface using the program "ip" from the "IPROUTE2"
-  utility suite. The following chapter describes briefly how to use it.
-  Furthermore, the interface uses a common data structure and exports a
-  set of common functions, which all real CAN network device drivers
-  should use. Please have a look to the SJA1000 or MSCAN driver to
-  understand how to use them. The name of the module is can-dev.ko.
-
-  6.5.1 Netlink interface to set/get devices properties
-
-  The CAN device must be configured via netlink interface. The supported
-  netlink message types are defined and briefly described in
-  "include/linux/can/netlink.h". CAN link support for the program "ip"
-  of the IPROUTE2 utility suite is available and it can be used as shown
-  below:
-
-  - Setting CAN device properties:
-
-    $ ip link set can0 type can help
-    Usage: ip link set DEVICE type can
-        [ bitrate BITRATE [ sample-point SAMPLE-POINT] ] |
-        [ tq TQ prop-seg PROP_SEG phase-seg1 PHASE-SEG1
-          phase-seg2 PHASE-SEG2 [ sjw SJW ] ]
-
-        [ dbitrate BITRATE [ dsample-point SAMPLE-POINT] ] |
-        [ dtq TQ dprop-seg PROP_SEG dphase-seg1 PHASE-SEG1
-          dphase-seg2 PHASE-SEG2 [ dsjw SJW ] ]
-
-        [ loopback { on | off } ]
-        [ listen-only { on | off } ]
-        [ triple-sampling { on | off } ]
-        [ one-shot { on | off } ]
-        [ berr-reporting { on | off } ]
-        [ fd { on | off } ]
-        [ fd-non-iso { on | off } ]
-        [ presume-ack { on | off } ]
-
-        [ restart-ms TIME-MS ]
-        [ restart ]
-
-        Where: BITRATE       := { 1..1000000 }
-               SAMPLE-POINT  := { 0.000..0.999 }
-               TQ            := { NUMBER }
-               PROP-SEG      := { 1..8 }
-               PHASE-SEG1    := { 1..8 }
-               PHASE-SEG2    := { 1..8 }
-               SJW           := { 1..4 }
-               RESTART-MS    := { 0 | NUMBER }
-
-  - Display CAN device details and statistics:
-
-    $ ip -details -statistics link show can0
-    2: can0: <NOARP,UP,LOWER_UP,ECHO> mtu 16 qdisc pfifo_fast state UP qlen 10
-      link/can
-      can <TRIPLE-SAMPLING> state ERROR-ACTIVE restart-ms 100
-      bitrate 125000 sample_point 0.875
-      tq 125 prop-seg 6 phase-seg1 7 phase-seg2 2 sjw 1
-      sja1000: tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1
-      clock 8000000
-      re-started bus-errors arbit-lost error-warn error-pass bus-off
-      41         17457      0          41         42         41
-      RX: bytes  packets  errors  dropped overrun mcast
-      140859     17608    17457   0       0       0
-      TX: bytes  packets  errors  dropped carrier collsns
-      861        112      0       41      0       0
-
-  More info to the above output:
-
-    "<TRIPLE-SAMPLING>"
-	Shows the list of selected CAN controller modes: LOOPBACK,
-	LISTEN-ONLY, or TRIPLE-SAMPLING.
-
-    "state ERROR-ACTIVE"
-	The current state of the CAN controller: "ERROR-ACTIVE",
-	"ERROR-WARNING", "ERROR-PASSIVE", "BUS-OFF" or "STOPPED"
-
-    "restart-ms 100"
-	Automatic restart delay time. If set to a non-zero value, a
-	restart of the CAN controller will be triggered automatically
-	in case of a bus-off condition after the specified delay time
-	in milliseconds. By default it's off.
-
-    "bitrate 125000 sample-point 0.875"
-	Shows the real bit-rate in bits/sec and the sample-point in the
-	range 0.000..0.999. If the calculation of bit-timing parameters
-	is enabled in the kernel (CONFIG_CAN_CALC_BITTIMING=y), the
-	bit-timing can be defined by setting the "bitrate" argument.
-	Optionally the "sample-point" can be specified. By default it's
-	0.000 assuming CIA-recommended sample-points.
-
-    "tq 125 prop-seg 6 phase-seg1 7 phase-seg2 2 sjw 1"
-	Shows the time quanta in ns, propagation segment, phase buffer
-	segment 1 and 2 and the synchronisation jump width in units of
-	tq. They allow to define the CAN bit-timing in a hardware
-	independent format as proposed by the Bosch CAN 2.0 spec (see
-	chapter 8 of http://www.semiconductors.bosch.de/pdf/can2spec.pdf).
-
-    "sja1000: tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1
-     clock 8000000"
-	Shows the bit-timing constants of the CAN controller, here the
-	"sja1000". The minimum and maximum values of the time segment 1
-	and 2, the synchronisation jump width in units of tq, the
-	bitrate pre-scaler and the CAN system clock frequency in Hz.
-	These constants could be used for user-defined (non-standard)
-	bit-timing calculation algorithms in user-space.
-
-    "re-started bus-errors arbit-lost error-warn error-pass bus-off"
-	Shows the number of restarts, bus and arbitration lost errors,
-	and the state changes to the error-warning, error-passive and
-	bus-off state. RX overrun errors are listed in the "overrun"
-	field of the standard network statistics.
-
-  6.5.2 Setting the CAN bit-timing
-
-  The CAN bit-timing parameters can always be defined in a hardware
-  independent format as proposed in the Bosch CAN 2.0 specification
-  specifying the arguments "tq", "prop_seg", "phase_seg1", "phase_seg2"
-  and "sjw":
-
-    $ ip link set canX type can tq 125 prop-seg 6 \
-				phase-seg1 7 phase-seg2 2 sjw 1
-
-  If the kernel option CONFIG_CAN_CALC_BITTIMING is enabled, CIA
-  recommended CAN bit-timing parameters will be calculated if the bit-
-  rate is specified with the argument "bitrate":
-
-    $ ip link set canX type can bitrate 125000
-
-  Note that this works fine for the most common CAN controllers with
-  standard bit-rates but may *fail* for exotic bit-rates or CAN system
-  clock frequencies. Disabling CONFIG_CAN_CALC_BITTIMING saves some
-  space and allows user-space tools to solely determine and set the
-  bit-timing parameters. The CAN controller specific bit-timing
-  constants can be used for that purpose. They are listed by the
-  following command:
-
-    $ ip -details link show can0
-    ...
-      sja1000: clock 8000000 tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1
-
-  6.5.3 Starting and stopping the CAN network device
-
-  A CAN network device is started or stopped as usual with the command
-  "ifconfig canX up/down" or "ip link set canX up/down". Be aware that
-  you *must* define proper bit-timing parameters for real CAN devices
-  before you can start it to avoid error-prone default settings:
-
-    $ ip link set canX up type can bitrate 125000
-
-  A device may enter the "bus-off" state if too many errors occurred on
-  the CAN bus. Then no more messages are received or sent. An automatic
-  bus-off recovery can be enabled by setting the "restart-ms" to a
-  non-zero value, e.g.:
-
-    $ ip link set canX type can restart-ms 100
-
-  Alternatively, the application may realize the "bus-off" condition
-  by monitoring CAN error message frames and do a restart when
-  appropriate with the command:
-
-    $ ip link set canX type can restart
-
-  Note that a restart will also create a CAN error message frame (see
-  also chapter 3.3).
-
-  6.6 CAN FD (flexible data rate) driver support
-
-  CAN FD capable CAN controllers support two different bitrates for the
-  arbitration phase and the payload phase of the CAN FD frame. Therefore a
-  second bit timing has to be specified in order to enable the CAN FD bitrate.
-
-  Additionally CAN FD capable CAN controllers support up to 64 bytes of
-  payload. The representation of this length in can_frame.can_dlc and
-  canfd_frame.len for userspace applications and inside the Linux network
-  layer is a plain value from 0 .. 64 instead of the CAN 'data length code'.
-  The data length code was a 1:1 mapping to the payload length in the legacy
-  CAN frames anyway. The payload length to the bus-relevant DLC mapping is
-  only performed inside the CAN drivers, preferably with the helper
-  functions can_dlc2len() and can_len2dlc().
-
-  The CAN netdevice driver capabilities can be distinguished by the network
-  devices maximum transfer unit (MTU):
-
-  MTU = 16 (CAN_MTU)   => sizeof(struct can_frame)   => 'legacy' CAN device
-  MTU = 72 (CANFD_MTU) => sizeof(struct canfd_frame) => CAN FD capable device
-
-  The CAN device MTU can be retrieved e.g. with a SIOCGIFMTU ioctl() syscall.
-  N.B. CAN FD capable devices can also handle and send legacy CAN frames.
-
-  When configuring CAN FD capable CAN controllers an additional 'data' bitrate
-  has to be set. This bitrate for the data phase of the CAN FD frame has to be
-  at least the bitrate which was configured for the arbitration phase. This
-  second bitrate is specified analogue to the first bitrate but the bitrate
-  setting keywords for the 'data' bitrate start with 'd' e.g. dbitrate,
-  dsample-point, dsjw or dtq and similar settings. When a data bitrate is set
-  within the configuration process the controller option "fd on" can be
-  specified to enable the CAN FD mode in the CAN controller. This controller
-  option also switches the device MTU to 72 (CANFD_MTU).
-
-  The first CAN FD specification presented as whitepaper at the International
-  CAN Conference 2012 needed to be improved for data integrity reasons.
-  Therefore two CAN FD implementations have to be distinguished today:
-
-  - ISO compliant:     The ISO 11898-1:2015 CAN FD implementation (default)
-  - non-ISO compliant: The CAN FD implementation following the 2012 whitepaper
-
-  Finally there are three types of CAN FD controllers:
-
-  1. ISO compliant (fixed)
-  2. non-ISO compliant (fixed, like the M_CAN IP core v3.0.1 in m_can.c)
-  3. ISO/non-ISO CAN FD controllers (switchable, like the PEAK PCAN-USB FD)
-
-  The current ISO/non-ISO mode is announced by the CAN controller driver via
-  netlink and displayed by the 'ip' tool (controller option FD-NON-ISO).
-  The ISO/non-ISO-mode can be altered by setting 'fd-non-iso {on|off}' for
-  switchable CAN FD controllers only.
-
-  Example configuring 500 kbit/s arbitration bitrate and 4 Mbit/s data bitrate:
-
-    $ ip link set can0 up type can bitrate 500000 sample-point 0.75 \
-                                   dbitrate 4000000 dsample-point 0.8 fd on
-    $ ip -details link show can0
-    5: can0: <NOARP,UP,LOWER_UP,ECHO> mtu 72 qdisc pfifo_fast state UNKNOWN \
-             mode DEFAULT group default qlen 10
-    link/can  promiscuity 0
-    can <FD> state ERROR-ACTIVE (berr-counter tx 0 rx 0) restart-ms 0
-          bitrate 500000 sample-point 0.750
-          tq 50 prop-seg 14 phase-seg1 15 phase-seg2 10 sjw 1
-          pcan_usb_pro_fd: tseg1 1..64 tseg2 1..16 sjw 1..16 brp 1..1024 \
-          brp-inc 1
-          dbitrate 4000000 dsample-point 0.800
-          dtq 12 dprop-seg 7 dphase-seg1 8 dphase-seg2 4 dsjw 1
-          pcan_usb_pro_fd: dtseg1 1..16 dtseg2 1..8 dsjw 1..4 dbrp 1..1024 \
-          dbrp-inc 1
-          clock 80000000
-
-  Example when 'fd-non-iso on' is added on this switchable CAN FD adapter:
-   can <FD,FD-NON-ISO> state ERROR-ACTIVE (berr-counter tx 0 rx 0) restart-ms 0
-
-  6.7 Supported CAN hardware
-
-  Please check the "Kconfig" file in "drivers/net/can" to get an actual
-  list of the support CAN hardware. On the SocketCAN project website
-  (see chapter 7) there might be further drivers available, also for
-  older kernel versions.
-
-7. SocketCAN resources
------------------------
-
-  The Linux CAN / SocketCAN project resources (project site / mailing list)
-  are referenced in the MAINTAINERS file in the Linux source tree.
-  Search for CAN NETWORK [LAYERS|DRIVERS].
-
-8. Credits
-----------
-
-  Oliver Hartkopp (PF_CAN core, filters, drivers, bcm, SJA1000 driver)
-  Urs Thuermann (PF_CAN core, kernel integration, socket interfaces, raw, vcan)
-  Jan Kizka (RT-SocketCAN core, Socket-API reconciliation)
-  Wolfgang Grandegger (RT-SocketCAN core & drivers, Raw Socket-API reviews,
-                       CAN device driver interface, MSCAN driver)
-  Robert Schwebel (design reviews, PTXdist integration)
-  Marc Kleine-Budde (design reviews, Kernel 2.6 cleanups, drivers)
-  Benedikt Spranger (reviews)
-  Thomas Gleixner (LKML reviews, coding style, posting hints)
-  Andrey Volkov (kernel subtree structure, ioctls, MSCAN driver)
-  Matthias Brukner (first SJA1000 CAN netdevice implementation Q2/2003)
-  Klaus Hitschler (PEAK driver integration)
-  Uwe Koppe (CAN netdevices with PF_PACKET approach)
-  Michael Schulze (driver layer loopback requirement, RT CAN drivers review)
-  Pavel Pisa (Bit-timing calculation)
-  Sascha Hauer (SJA1000 platform driver)
-  Sebastian Haas (SJA1000 EMS PCI driver)
-  Markus Plessing (SJA1000 EMS PCI driver)
-  Per Dalen (SJA1000 Kvaser PCI driver)
-  Sam Ravnborg (reviews, coding style, kbuild help)
diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt
index b8b40753133e..25170ad7d25b 100644
--- a/Documentation/networking/dsa/dsa.txt
+++ b/Documentation/networking/dsa/dsa.txt
@@ -385,11 +385,6 @@ Switch configuration
   avoid relying on what a previous software agent such as a bootloader/firmware
   may have previously configured.
 
-- set_addr: Some switches require the programming of the management interface's
-  Ethernet MAC address, switch drivers can also disable ageing of MAC addresses
-  on the management interface and "hardcode"/"force" this MAC address for the
-  CPU/management interface as an optimization
-
 PHY devices and link management
 -------------------------------
 
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index 87814859cfc2..a4508ec1816b 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -1134,7 +1134,7 @@ The verifier's knowledge about the variable offset consists of:
 mask and value; no bit should ever be 1 in both.  For example, if a byte is read
 into a register from memory, the register's top 56 bits are known zero, while
 the low 8 are unknown - which is represented as the tnum (0x0; 0xff).  If we
-then OR this with 0x40, we get (0x40; 0xcf), then if we add 1 we get (0x0;
+then OR this with 0x40, we get (0x40; 0xbf), then if we add 1 we get (0x0;
 0x1ff), because of potential carries.
 Besides arithmetic, the register state can also be updated by conditional
 branches.  For instance, if a SCALAR_VALUE is compared > 8, in the 'true' branch
diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt
index 057e9fdbfac9..e74d8e1da0e2 100644
--- a/Documentation/networking/ieee802154.txt
+++ b/Documentation/networking/ieee802154.txt
@@ -97,6 +97,46 @@ The include/net/mac802154.h defines following functions:
  - void ieee802154_unregister_hw(struct ieee802154_hw *hw):
    freeing registered PHY
 
+ - void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb,
+                              u8 lqi):
+   telling 802.15.4 module there is a new received frame in the skb with
+   the RF Link Quality Indicator (LQI) from the hardware device
+
+ - void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb,
+                                 bool ifs_handling):
+   telling 802.15.4 module the frame in the skb is or going to be
+   transmitted through the hardware device
+
+The device driver must implement the following callbacks in the IEEE 802.15.4
+operations structure at least:
+struct ieee802154_ops {
+	...
+	int	(*start)(struct ieee802154_hw *hw);
+	void	(*stop)(struct ieee802154_hw *hw);
+	...
+	int	(*xmit_async)(struct ieee802154_hw *hw, struct sk_buff *skb);
+	int	(*ed)(struct ieee802154_hw *hw, u8 *level);
+	int	(*set_channel)(struct ieee802154_hw *hw, u8 page, u8 channel);
+	...
+};
+
+ - int start(struct ieee802154_hw *hw):
+   handler that 802.15.4 module calls for the hardware device initialization.
+
+ - void stop(struct ieee802154_hw *hw):
+   handler that 802.15.4 module calls for the hardware device cleanup.
+
+ - int xmit_async(struct ieee802154_hw *hw, struct sk_buff *skb):
+   handler that 802.15.4 module calls for each frame in the skb going to be
+   transmitted through the hardware device.
+
+ - int ed(struct ieee802154_hw *hw, u8 *level):
+   handler that 802.15.4 module calls for Energy Detection from the hardware
+   device.
+
+ - int set_channel(struct ieee802154_hw *hw, u8 page, u8 channel):
+   set radio for listening on specific channel of the hardware device.
+
 Moreover IEEE 802.15.4 device operations structure should be filled.
 
 Fake drivers
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 66e620866245..90966c2692d8 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -7,8 +7,10 @@ Contents:
    :maxdepth: 2
 
    batman-adv
+   can
    kapi
    z8530book
+   msg_zerocopy
 
 .. only::  subproject
 
@@ -16,4 +18,3 @@ Contents:
    =======
 
    * :ref:`genindex`
-
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 46c7e1085efc..3f2c40d8e6aa 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -606,6 +606,7 @@ tcp_fastopen_blackhole_timeout_sec - INTEGER
 	This time period will grow exponentially when more blackhole issues
 	get detected right after Fastopen is re-enabled and will reset to
 	initial value when the blackhole issue goes away.
+	0 to disable the blackhole detection.
 	By default, it is set to 1hr.
 
 tcp_syn_retries - INTEGER
diff --git a/Documentation/networking/kapi.rst b/Documentation/networking/kapi.rst
index 580289f345da..f03ae64be8bc 100644
--- a/Documentation/networking/kapi.rst
+++ b/Documentation/networking/kapi.rst
@@ -145,3 +145,27 @@ PHY Support
 
 .. kernel-doc:: drivers/net/phy/mdio_bus.c
    :internal:
+
+PHYLINK
+-------
+
+  PHYLINK interfaces traditional network drivers with PHYLIB, fixed-links,
+  and SFF modules (eg, hot-pluggable SFP) that may contain PHYs.  PHYLINK
+  provides management of the link state and link modes.
+
+.. kernel-doc:: include/linux/phylink.h
+   :internal:
+
+.. kernel-doc:: drivers/net/phy/phylink.c
+
+SFP support
+-----------
+
+.. kernel-doc:: drivers/net/phy/sfp-bus.c
+   :internal:
+
+.. kernel-doc:: include/linux/sfp.h
+   :internal:
+
+.. kernel-doc:: drivers/net/phy/sfp-bus.c
+   :export:
diff --git a/Documentation/networking/msg_zerocopy.rst b/Documentation/networking/msg_zerocopy.rst
index 77f6d7e25cfd..291a01264967 100644
--- a/Documentation/networking/msg_zerocopy.rst
+++ b/Documentation/networking/msg_zerocopy.rst
@@ -72,6 +72,10 @@ this flag, a process must first signal intent by setting a socket option:
 	if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &one, sizeof(one)))
 		error(1, errno, "setsockopt zerocopy");
 
+Setting the socket option only works when the socket is in its initial
+(TCP_CLOSED) state.  Trying to set the option for a socket returned by accept(),
+for example, will lead to an EBUSY error. In this case, the option should be set
+to the listening socket and it will be inherited by the accepted sockets.
 
 Transmission
 ------------
diff --git a/Documentation/networking/netdev-features.txt b/Documentation/networking/netdev-features.txt
index 7413eb05223b..c77f9d57eb91 100644
--- a/Documentation/networking/netdev-features.txt
+++ b/Documentation/networking/netdev-features.txt
@@ -163,3 +163,12 @@ This requests that the NIC receive all possible frames, including errored
 frames (such as bad FCS, etc).  This can be helpful when sniffing a link with
 bad packets on it.  Some NICs may receive more packets if also put into normal
 PROMISC mode.
+
+*  rx-gro-hw
+
+This requests that the NIC enables Hardware GRO (generic receive offload).
+Hardware GRO is basically the exact reverse of TSO, and is generally
+stricter than Hardware LRO.  A packet stream merged by Hardware GRO must
+be re-segmentable by GSO or TSO back to the exact original packet stream.
+Hardware GRO is dependent on RXCSUM since every packet successfully merged
+by hardware must also have the checksum verified by hardware.
diff --git a/Documentation/networking/pktgen.txt b/Documentation/networking/pktgen.txt
index 2c4e3354e128..d2fd78f85aa4 100644
--- a/Documentation/networking/pktgen.txt
+++ b/Documentation/networking/pktgen.txt
@@ -12,8 +12,8 @@ suitable sample script and configure that.
 On a dual CPU:
 
 ps aux | grep pkt
-root       129  0.3  0.0     0    0 ?        SW    2003 523:20 [pktgen/0]
-root       130  0.3  0.0     0    0 ?        SW    2003 509:50 [pktgen/1]
+root       129  0.3  0.0     0    0 ?        SW    2003 523:20 [kpktgend_0]
+root       130  0.3  0.0     0    0 ?        SW    2003 509:50 [kpktgend_1]
 
 
 For monitoring and control pktgen creates:
@@ -113,9 +113,16 @@ Configuring devices
 ===================
 This is done via the /proc interface, and most easily done via pgset
 as defined in the sample scripts.
+You need to specify PGDEV environment variable to use functions from sample
+scripts, i.e.:
+export PGDEV=/proc/net/pktgen/eth4@0
+source samples/pktgen/functions.sh
 
 Examples:
 
+ pg_ctrl start           starts injection.
+ pg_ctrl stop            aborts injection. Also, ^C aborts generator.
+
  pgset "clone_skb 1"     sets the number of copies of the same packet
  pgset "clone_skb 0"     use single SKB for all transmits
  pgset "burst 8"         uses xmit_more API to queue 8 copies of the same
@@ -165,8 +172,12 @@ Examples:
                               IPSEC # IPsec encapsulation (needs CONFIG_XFRM)
                               NODE_ALLOC # node specific memory allocation
                               NO_TIMESTAMP # disable timestamping
+ pgset 'flag ![name]'    Clear a flag to determine behaviour.
+                         Note that you might need to use single quote in
+                         interactive mode, so that your shell wouldn't expand
+                         the specified flag as a history command.
 
- pgset spi SPI_VALUE     Set specific SA used to transform packet.
+ pgset "spi [SPI_VALUE]" Set specific SA used to transform packet.
 
  pgset "udp_src_min 9"   set UDP source port min, If < udp_src_max, then
                          cycle through the port range.
@@ -207,8 +218,6 @@ Examples:
  pgset "tos XX"           set former IPv4 TOS field (e.g. "tos 28" for AF11 no ECN, default 00)
  pgset "traffic_class XX" set former IPv6 TRAFFIC CLASS (e.g. "traffic_class B8" for EF no ECN, default 00)
 
- pgset stop    	          aborts injection. Also, ^C aborts generator.
-
  pgset "rate 300M"        set rate to 300 Mb/s
  pgset "ratep 1000000"    set rate to 1Mpps
 
diff --git a/Documentation/networking/xfrm_device.txt b/Documentation/networking/xfrm_device.txt
new file mode 100644
index 000000000000..50c34ca65efe
--- /dev/null
+++ b/Documentation/networking/xfrm_device.txt
@@ -0,0 +1,135 @@
+
+===============================================
+XFRM device - offloading the IPsec computations
+===============================================
+Shannon Nelson <shannon.nelson@oracle.com>
+
+
+Overview
+========
+
+IPsec is a useful feature for securing network traffic, but the
+computational cost is high: a 10Gbps link can easily be brought down
+to under 1Gbps, depending on the traffic and link configuration.
+Luckily, there are NICs that offer a hardware based IPsec offload which
+can radically increase throughput and decrease CPU utilization.  The XFRM
+Device interface allows NIC drivers to offer to the stack access to the
+hardware offload.
+
+Userland access to the offload is typically through a system such as
+libreswan or KAME/raccoon, but the iproute2 'ip xfrm' command set can
+be handy when experimenting.  An example command might look something
+like this:
+
+  ip x s add proto esp dst 14.0.0.70 src 14.0.0.52 spi 0x07 mode transport \
+     reqid 0x07 replay-window 32 \
+     aead 'rfc4106(gcm(aes))' 0x44434241343332312423222114131211f4f3f2f1 128 \
+     sel src 14.0.0.52/24 dst 14.0.0.70/24 proto tcp \
+     offload dev eth4 dir in
+
+Yes, that's ugly, but that's what shell scripts and/or libreswan are for.
+
+
+
+Callbacks to implement
+======================
+
+/* from include/linux/netdevice.h */
+struct xfrmdev_ops {
+	int	(*xdo_dev_state_add) (struct xfrm_state *x);
+	void	(*xdo_dev_state_delete) (struct xfrm_state *x);
+	void	(*xdo_dev_state_free) (struct xfrm_state *x);
+	bool	(*xdo_dev_offload_ok) (struct sk_buff *skb,
+				       struct xfrm_state *x);
+	void    (*xdo_dev_state_advance_esn) (struct xfrm_state *x);
+};
+
+The NIC driver offering ipsec offload will need to implement these
+callbacks to make the offload available to the network stack's
+XFRM subsytem.  Additionally, the feature bits NETIF_F_HW_ESP and
+NETIF_F_HW_ESP_TX_CSUM will signal the availability of the offload.
+
+
+
+Flow
+====
+
+At probe time and before the call to register_netdev(), the driver should
+set up local data structures and XFRM callbacks, and set the feature bits.
+The XFRM code's listener will finish the setup on NETDEV_REGISTER.
+
+		adapter->netdev->xfrmdev_ops = &ixgbe_xfrmdev_ops;
+		adapter->netdev->features |= NETIF_F_HW_ESP;
+		adapter->netdev->hw_enc_features |= NETIF_F_HW_ESP;
+
+When new SAs are set up with a request for "offload" feature, the
+driver's xdo_dev_state_add() will be given the new SA to be offloaded
+and an indication of whether it is for Rx or Tx.  The driver should
+	- verify the algorithm is supported for offloads
+	- store the SA information (key, salt, target-ip, protocol, etc)
+	- enable the HW offload of the SA
+
+The driver can also set an offload_handle in the SA, an opaque void pointer
+that can be used to convey context into the fast-path offload requests.
+
+		xs->xso.offload_handle = context;
+
+
+When the network stack is preparing an IPsec packet for an SA that has
+been setup for offload, it first calls into xdo_dev_offload_ok() with
+the skb and the intended offload state to ask the driver if the offload
+will serviceable.  This can check the packet information to be sure the
+offload can be supported (e.g. IPv4 or IPv6, no IPv4 options, etc) and
+return true of false to signify its support.
+
+When ready to send, the driver needs to inspect the Tx packet for the
+offload information, including the opaque context, and set up the packet
+send accordingly.
+
+		xs = xfrm_input_state(skb);
+		context = xs->xso.offload_handle;
+		set up HW for send
+
+The stack has already inserted the appropriate IPsec headers in the
+packet data, the offload just needs to do the encryption and fix up the
+header values.
+
+
+When a packet is received and the HW has indicated that it offloaded a
+decryption, the driver needs to add a reference to the decoded SA into
+the packet's skb.  At this point the data should be decrypted but the
+IPsec headers are still in the packet data; they are removed later up
+the stack in xfrm_input().
+
+	find and hold the SA that was used to the Rx skb
+		get spi, protocol, and destination IP from packet headers
+		xs = find xs from (spi, protocol, dest_IP)
+		xfrm_state_hold(xs);
+
+	store the state information into the skb
+		skb->sp = secpath_dup(skb->sp);
+		skb->sp->xvec[skb->sp->len++] = xs;
+		skb->sp->olen++;
+
+	indicate the success and/or error status of the offload
+		xo = xfrm_offload(skb);
+		xo->flags = CRYPTO_DONE;
+		xo->status = crypto_status;
+
+	hand the packet to napi_gro_receive() as usual
+
+In ESN mode, xdo_dev_state_advance_esn() is called from xfrm_replay_advance_esn().
+Driver will check packet seq number and update HW ESN state machine if needed.
+
+When the SA is removed by the user, the driver's xdo_dev_state_delete()
+is asked to disable the offload.  Later, xdo_dev_state_free() is called
+from a garbage collection routine after all reference counts to the state
+have been removed and any remaining resources can be cleared for the
+offload state.  How these are used by the driver will depend on specific
+hardware needs.
+
+As a netdev is set to DOWN the XFRM stack's netdev listener will call
+xdo_dev_state_delete() and xdo_dev_state_free() on any remaining offloaded
+states.
+
+
diff --git a/Documentation/networking/xfrm_proc.txt b/Documentation/networking/xfrm_proc.txt
index d0d8bafa9016..2eae619ab67b 100644
--- a/Documentation/networking/xfrm_proc.txt
+++ b/Documentation/networking/xfrm_proc.txt
@@ -5,13 +5,15 @@ Masahide NAKAMURA <nakam@linux-ipv6.org>
 
 Transformation Statistics
 -------------------------
-xfrm_proc is a statistics shown factor dropped by transformation
-for developer.
-It is a counter designed from current transformation source code
-and defined like linux private MIB.
 
-Inbound statistics
-~~~~~~~~~~~~~~~~~~
+The xfrm_proc code is a set of statistics showing numbers of packets
+dropped by the transformation code and why.  These counters are defined
+as part of the linux private MIB.  These counters can be viewed in
+/proc/net/xfrm_stat.
+
+
+Inbound errors
+~~~~~~~~~~~~~~
 XfrmInError:
 	All errors which is not matched others
 XfrmInBufferError:
@@ -46,6 +48,10 @@ XfrmInPolBlock:
 	Policy discards
 XfrmInPolError:
 	Policy error
+XfrmAcquireError:
+	State hasn't been fully acquired before use
+XfrmFwdHdrError:
+	Forward routing of a packet is not allowed
 
 Outbound errors
 ~~~~~~~~~~~~~~~
@@ -72,3 +78,5 @@ XfrmOutPolDead:
 	Policy is dead
 XfrmOutPolError:
 	Policy error
+XfrmOutStateInvalid:
+	State is invalid, perhaps expired
diff --git a/Documentation/perf/arm_dsu_pmu.txt b/Documentation/perf/arm_dsu_pmu.txt
new file mode 100644
index 000000000000..d611e15f5add
--- /dev/null
+++ b/Documentation/perf/arm_dsu_pmu.txt
@@ -0,0 +1,28 @@
+ARM DynamIQ Shared Unit (DSU) PMU
+==================================
+
+ARM DynamIQ Shared Unit integrates one or more cores with an L3 memory system,
+control logic and external interfaces to form a multicore cluster. The PMU
+allows counting the various events related to the L3 cache, Snoop Control Unit
+etc, using 32bit independent counters. It also provides a 64bit cycle counter.
+
+The PMU can only be accessed via CPU system registers and are common to the
+cores connected to the same DSU. Like most of the other uncore PMUs, DSU
+PMU doesn't support process specific events and cannot be used in sampling mode.
+
+The DSU provides a bitmap for a subset of implemented events via hardware
+registers. There is no way for the driver to determine if the other events
+are available or not. Hence the driver exposes only those events advertised
+by the DSU, in "events" directory under :
+
+  /sys/bus/event_sources/devices/arm_dsu_<N>/
+
+The user should refer to the TRM of the product to figure out the supported events
+and use the raw event code for the unlisted events.
+
+The driver also exposes the CPUs connected to the DSU instance in "associated_cpus".
+
+
+e.g usage :
+
+	perf stat -a -e arm_dsu_0/cycles/
diff --git a/Documentation/power/pci.txt b/Documentation/power/pci.txt
index 704cd36079b8..8eaf9ee24d43 100644
--- a/Documentation/power/pci.txt
+++ b/Documentation/power/pci.txt
@@ -994,6 +994,17 @@ into D0 going forward), but if it is in runtime suspend in pci_pm_thaw_noirq(),
 the function will set the power.direct_complete flag for it (to make the PM core
 skip the subsequent "thaw" callbacks for it) and return.
 
+Setting the DPM_FLAG_LEAVE_SUSPENDED flag means that the driver prefers the
+device to be left in suspend after system-wide transitions to the working state.
+This flag is checked by the PM core, but the PCI bus type informs the PM core
+which devices may be left in suspend from its perspective (that happens during
+the "noirq" phase of system-wide suspend and analogous transitions) and next it
+uses the dev_pm_may_skip_resume() helper to decide whether or not to return from
+pci_pm_resume_noirq() early, as the PM core will skip the remaining resume
+callbacks for the device during the transition under way and will set its
+runtime PM status to "suspended" if dev_pm_may_skip_resume() returns "true" for
+it.
+
 3.2. Device Runtime Power Management
 ------------------------------------
 In addition to providing device power management callbacks PCI device drivers
diff --git a/Documentation/power/regulator/machine.txt b/Documentation/power/regulator/machine.txt
index 757e3b53dc11..eff4dcaaa252 100644
--- a/Documentation/power/regulator/machine.txt
+++ b/Documentation/power/regulator/machine.txt
@@ -23,16 +23,12 @@ struct regulator_consumer_supply {
 e.g. for the machine above
 
 static struct regulator_consumer_supply regulator1_consumers[] = {
-{
-	.dev_name	= "dev_name(consumer B)",
-	.supply		= "Vcc",
-},};
+	REGULATOR_SUPPLY("Vcc", "consumer B"),
+};
 
 static struct regulator_consumer_supply regulator2_consumers[] = {
-{
-	.dev	= "dev_name(consumer A"),
-	.supply	= "Vcc",
-},};
+	REGULATOR_SUPPLY("Vcc", "consumer A"),
+};
 
 This maps Regulator-1 to the 'Vcc' supply for Consumer B and maps Regulator-2
 to the 'Vcc' supply for Consumer A.
@@ -78,20 +74,20 @@ static struct regulator_init_data regulator2_data = {
 Finally the regulator devices must be registered in the usual manner.
 
 static struct platform_device regulator_devices[] = {
-{
-	.name = "regulator",
-	.id = DCDC_1,
-	.dev = {
-		.platform_data = &regulator1_data,
+	{
+		.name = "regulator",
+		.id = DCDC_1,
+		.dev = {
+			.platform_data = &regulator1_data,
+		},
 	},
-},
-{
-	.name = "regulator",
-	.id = DCDC_2,
-	.dev = {
-		.platform_data = &regulator2_data,
+	{
+		.name = "regulator",
+		.id = DCDC_2,
+		.dev = {
+			.platform_data = &regulator2_data,
+		},
 	},
-},
 };
 /* register regulator 1 device */
 platform_device_register(&regulator_devices[0]);
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 560beaef5a7c..81cdb528ad46 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -32,6 +32,8 @@ you probably needn't concern yourself with isdn4k-utils.
 GNU C                  3.2              gcc --version
 GNU make               3.81             make --version
 binutils               2.20             ld -v
+flex                   2.5.35           flex --version
+bison                  2.0              bison --version
 util-linux             2.10o            fdformat --version
 module-init-tools      0.9.10           depmod -V
 e2fsprogs              1.41.4           e2fsck -V
@@ -79,6 +81,19 @@ The build system has, as of 4.13, switched to using thin archives (`ar T`)
 rather than incremental linking (`ld -r`) for built-in.o intermediate steps.
 This requires binutils 2.20 or newer.
 
+Flex
+----
+
+Since Linux 4.16, the build system generates lexical analyzers
+during build.  This requires flex 2.5.35 or later.
+
+
+Bison
+-----
+
+Since Linux 4.16, the build system generates parsers
+during build.  This requires bison 2.0 or later.
+
 Perl
 ----
 
@@ -333,6 +348,16 @@ Binutils
 
 - <https://www.kernel.org/pub/linux/devel/binutils/>
 
+Flex
+----
+
+- <https://github.com/westes/flex/releases>
+
+Bison
+-----
+
+- <ftp://ftp.gnu.org/gnu/bison/>
+
 OpenSSL
 -------
 
diff --git a/Documentation/process/kernel-enforcement-statement.rst b/Documentation/process/kernel-enforcement-statement.rst
index b3170671a1df..6816c12d6956 100644
--- a/Documentation/process/kernel-enforcement-statement.rst
+++ b/Documentation/process/kernel-enforcement-statement.rst
@@ -68,6 +68,7 @@ we might work for today, have in the past, or will in the future.
   - Paul Burton
   - Javier Martinez Canillas
   - Rob Clark
+  - Kees Cook (Google)
   - Jonathan Corbet
   - Dennis Dalessandro
   - Vivien Didelot (Savoir-faire Linux)
@@ -118,6 +119,7 @@ we might work for today, have in the past, or will in the future.
   - Mike Marshall
   - Chris Mason
   - Paul E. McKenney
+  - Arnaldo Carvalho de Melo
   - David S. Miller
   - Ingo Molnar
   - Kuninori Morimoto
@@ -136,6 +138,7 @@ we might work for today, have in the past, or will in the future.
   - Anna Schumaker
   - Jes Sorensen
   - K.Y. Srinivasan
+  - David Sterba (SUSE)
   - Heiko Stuebner
   - Jiri Kosina (SUSE)
   - Willy Tarreau
@@ -143,6 +146,7 @@ we might work for today, have in the past, or will in the future.
   - Linus Torvalds
   - Thierry Reding
   - Rik van Riel
+  - Luis R. Rodriguez
   - Geert Uytterhoeven (Glider bvba)
   - Eduardo Valentin (Amazon.com)
   - Daniel Vetter
diff --git a/Documentation/process/license-rules.rst b/Documentation/process/license-rules.rst
new file mode 100644
index 000000000000..408f77dc6157
--- /dev/null
+++ b/Documentation/process/license-rules.rst
@@ -0,0 +1,370 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Linux kernel licensing rules
+============================
+
+The Linux Kernel is provided under the terms of the GNU General Public
+License version 2 only (GPL-2.0), as published by the Free Software
+Foundation, and provided in the COPYING file.  This documentation file is
+not meant to replace the COPYING file, but provides a description of how
+each source file should be annotated to make the licensing it is governed
+under clear and unambiguous.
+
+The license in the COPYING file applies to the kernel source as a whole,
+though individual source files can have a different license which is
+required to be compatible with the GPL-2.0::
+
+    GPL-1.0+  :  GNU General Public License v1.0 or later
+    GPL-2.0+  :  GNU General Public License v2.0 or later
+    LGPL-2.0  :  GNU Library General Public License v2 only
+    LGPL-2.0+ :  GNU Library General Public License v2 or later
+    LGPL-2.1  :  GNU Lesser General Public License v2.1 only
+    LGPL-2.1+ :  GNU Lesser General Public License v2.1 or later
+
+Aside from that, individual files can be provided under a dual license,
+e.g. one of the compatible GPL variants and alternatively under a
+permissive license like BSD, MIT etc.
+
+The User-space API (UAPI) header files, which describe the interface of
+user-space programs to the kernel are a special case.  According to the
+note in the kernel COPYING file, the syscall interface is a clear boundary,
+which does not extend the GPL requirements to any software which uses it to
+communicate with the kernel.  Because the UAPI headers must be includable
+into any source files which create an executable running on the Linux
+kernel, the exception must be documented by a special license expression.
+
+The common way of expressing the license of a source file is to add the
+matching boilerplate text into the top comment of the file.  Due to
+formatting, typos etc. these "boilerplates" are hard to validate for
+tools which are used in the context of license compliance.
+
+An alternative to boilerplate text is the use of Software Package Data
+Exchange (SPDX) license identifiers in each source file.  SPDX license
+identifiers are machine parsable and precise shorthands for the license
+under which the content of the file is contributed.  SPDX license
+identifiers are managed by the SPDX Workgroup at the Linux Foundation and
+have been agreed on by partners throughout the industry, tool vendors, and
+legal teams.  For further information see https://spdx.org/
+
+The Linux kernel requires the precise SPDX identifier in all source files.
+The valid identifiers used in the kernel are explained in the section
+`License identifiers`_ and have been retrieved from the official SPDX
+license list at https://spdx.org/licenses/ along with the license texts.
+
+License identifier syntax
+-------------------------
+
+1. Placement:
+
+   The SPDX license identifier in kernel files shall be added at the first
+   possible line in a file which can contain a comment.  For the majority
+   or files this is the first line, except for scripts which require the
+   '#!PATH_TO_INTERPRETER' in the first line.  For those scripts the SPDX
+   identifier goes into the second line.
+
+|
+
+2. Style:
+
+   The SPDX license identifier is added in form of a comment.  The comment
+   style depends on the file type::
+
+      C source:	// SPDX-License-Identifier: <SPDX License Expression>
+      C header:	/* SPDX-License-Identifier: <SPDX License Expression> */
+      ASM:	/* SPDX-License-Identifier: <SPDX License Expression> */
+      scripts:	# SPDX-License-Identifier: <SPDX License Expression>
+      .rst:	.. SPDX-License-Identifier: <SPDX License Expression>
+      .dts{i}:	// SPDX-License-Identifier: <SPDX License Expression>
+
+   If a specific tool cannot handle the standard comment style, then the
+   appropriate comment mechanism which the tool accepts shall be used. This
+   is the reason for having the "/\* \*/" style comment in C header
+   files. There was build breakage observed with generated .lds files where
+   'ld' failed to parse the C++ comment. This has been fixed by now, but
+   there are still older assembler tools which cannot handle C++ style
+   comments.
+
+|
+
+3. Syntax:
+
+   A <SPDX License Expression> is either an SPDX short form license
+   identifier found on the SPDX License List, or the combination of two
+   SPDX short form license identifiers separated by "WITH" when a license
+   exception applies. When multiple licenses apply, an expression consists
+   of keywords "AND", "OR" separating sub-expressions and surrounded by
+   "(", ")" .
+
+   License identifiers for licenses like [L]GPL with the 'or later' option
+   are constructed by using a "+" for indicating the 'or later' option.::
+
+      // SPDX-License-Identifier: GPL-2.0+
+      // SPDX-License-Identifier: LGPL-2.1+
+
+   WITH should be used when there is a modifier to a license needed.
+   For example, the linux kernel UAPI files use the expression::
+
+      // SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+      // SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note
+
+   Other examples using WITH exceptions found in the kernel are::
+
+      // SPDX-License-Identifier: GPL-2.0 WITH mif-exception
+      // SPDX-License-Identifier: GPL-2.0+ WITH GCC-exception-2.0
+
+   Exceptions can only be used with particular License identifiers. The
+   valid License identifiers are listed in the tags of the exception text
+   file. For details see the point `Exceptions`_ in the chapter `License
+   identifiers`_.
+
+   OR should be used if the file is dual licensed and only one license is
+   to be selected.  For example, some dtsi files are available under dual
+   licenses::
+
+      // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+   Examples from the kernel for license expressions in dual licensed files::
+
+      // SPDX-License-Identifier: GPL-2.0 OR MIT
+      // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
+      // SPDX-License-Identifier: GPL-2.0 OR Apache-2.0
+      // SPDX-License-Identifier: GPL-2.0 OR MPL-1.1
+      // SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT
+      // SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause OR OpenSSL
+
+   AND should be used if the file has multiple licenses whose terms all
+   apply to use the file. For example, if code is inherited from another
+   project and permission has been given to put it in the kernel, but the
+   original license terms need to remain in effect::
+
+      // SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) AND MIT
+
+   Another other example where both sets of license terms need to be
+   adhered to is::
+
+      // SPDX-License-Identifier: GPL-1.0+ AND LGPL-2.1+
+
+License identifiers
+-------------------
+
+The licenses currently used, as well as the licenses for code added to the
+kernel, can be broken down into:
+
+1. _`Preferred licenses`:
+
+   Whenever possible these licenses should be used as they are known to be
+   fully compatible and widely used.  These licenses are available from the
+   directory::
+
+      LICENSES/preferred/
+
+   in the kernel source tree.
+
+   The files in this directory contain the full license text and
+   `Metatags`_.  The file names are identical to the SPDX license
+   identifier which shall be used for the license in source files.
+
+   Examples::
+
+      LICENSES/preferred/GPL-2.0
+
+   Contains the GPL version 2 license text and the required metatags::
+
+      LICENSES/preferred/MIT
+
+   Contains the MIT license text and the required metatags
+
+   _`Metatags`:
+
+   The following meta tags must be available in a license file:
+
+   - Valid-License-Identifier:
+
+     One or more lines which declare which License Identifiers are valid
+     inside the project to reference this particular license text.  Usually
+     this is a single valid identifier, but e.g. for licenses with the 'or
+     later' options two identifiers are valid.
+
+   - SPDX-URL:
+
+     The URL of the SPDX page which contains additional information related
+     to the license.
+
+   - Usage-Guidance:
+
+     Freeform text for usage advice. The text must include correct examples
+     for the SPDX license identifiers as they should be put into source
+     files according to the `License identifier syntax`_ guidelines.
+
+   - License-Text:
+
+     All text after this tag is treated as the original license text
+
+   File format examples::
+
+      Valid-License-Identifier: GPL-2.0
+      Valid-License-Identifier: GPL-2.0+
+      SPDX-URL: https://spdx.org/licenses/GPL-2.0.html
+      Usage-Guide:
+        To use this license in source code, put one of the following SPDX
+	tag/value pairs into a comment according to the placement
+	guidelines in the licensing rules documentation.
+	For 'GNU General Public License (GPL) version 2 only' use:
+	  SPDX-License-Identifier: GPL-2.0
+	For 'GNU General Public License (GPL) version 2 or any later version' use:
+	  SPDX-License-Identifier: GPL-2.0+
+      License-Text:
+        Full license text
+
+   ::
+
+      SPDX-License-Identifier: MIT
+      SPDX-URL: https://spdx.org/licenses/MIT.html
+      Usage-Guide:
+	To use this license in source code, put the following SPDX
+	tag/value pair into a comment according to the placement
+	guidelines in the licensing rules documentation.
+	  SPDX-License-Identifier: MIT
+      License-Text:
+        Full license text
+
+|
+
+2. Not recommended licenses:
+
+   These licenses should only be used for existing code or for importing
+   code from a different project.  These licenses are available from the
+   directory::
+
+      LICENSES/other/
+
+   in the kernel source tree.
+
+   The files in this directory contain the full license text and
+   `Metatags`_.  The file names are identical to the SPDX license
+   identifier which shall be used for the license in source files.
+
+   Examples::
+
+      LICENSES/other/ISC
+
+   Contains the Internet Systems Consortium license text and the required
+   metatags::
+
+      LICENSES/other/ZLib
+
+   Contains the ZLIB license text and the required metatags.
+
+   Metatags:
+
+   The metatag requirements for 'other' licenses are identical to the
+   requirements of the `Preferred licenses`_.
+
+   File format example::
+
+      Valid-License-Identifier: ISC
+      SPDX-URL: https://spdx.org/licenses/ISC.html
+      Usage-Guide:
+        Usage of this license in the kernel for new code is discouraged
+	and it should solely be used for importing code from an already
+	existing project.
+        To use this license in source code, put the following SPDX
+	tag/value pair into a comment according to the placement
+	guidelines in the licensing rules documentation.
+	  SPDX-License-Identifier: ISC
+      License-Text:
+        Full license text
+
+|
+
+3. _`Exceptions`:
+
+   Some licenses can be amended with exceptions which grant certain rights
+   which the original license does not.  These exceptions are available
+   from the directory::
+
+      LICENSES/exceptions/
+
+   in the kernel source tree.  The files in this directory contain the full
+   exception text and the required `Exception Metatags`_.
+
+   Examples::
+
+      LICENSES/exceptions/Linux-syscall-note
+
+   Contains the Linux syscall exception as documented in the COPYING
+   file of the Linux kernel, which is used for UAPI header files.
+   e.g. /\* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note \*/::
+
+      LICENSES/exceptions/GCC-exception-2.0
+
+   Contains the GCC 'linking exception' which allows to link any binary
+   independent of its license against the compiled version of a file marked
+   with this exception. This is required for creating runnable executables
+   from source code which is not compatible with the GPL.
+
+   _`Exception Metatags`:
+
+   The following meta tags must be available in an exception file:
+
+   - SPDX-Exception-Identifier:
+
+     One exception identifier which can be used with SPDX license
+     identifiers.
+
+   - SPDX-URL:
+
+     The URL of the SPDX page which contains additional information related
+     to the exception.
+
+   - SPDX-Licenses:
+
+     A comma separated list of SPDX license identifiers for which the
+     exception can be used.
+
+   - Usage-Guidance:
+
+     Freeform text for usage advice. The text must be followed by correct
+     examples for the SPDX license identifiers as they should be put into
+     source files according to the `License identifier syntax`_ guidelines.
+
+   - Exception-Text:
+
+     All text after this tag is treated as the original exception text
+
+   File format examples::
+
+      SPDX-Exception-Identifier: Linux-syscall-note
+      SPDX-URL: https://spdx.org/licenses/Linux-syscall-note.html
+      SPDX-Licenses: GPL-2.0, GPL-2.0+, GPL-1.0+, LGPL-2.0, LGPL-2.0+, LGPL-2.1, LGPL-2.1+
+      Usage-Guidance:
+        This exception is used together with one of the above SPDX-Licenses
+	to mark user-space API (uapi) header files so they can be included
+	into non GPL compliant user-space application code.
+        To use this exception add it with the keyword WITH to one of the
+	identifiers in the SPDX-Licenses tag:
+	  SPDX-License-Identifier: <SPDX-License> WITH Linux-syscall-note
+      Exception-Text:
+        Full exception text
+
+   ::
+
+      SPDX-Exception-Identifier: GCC-exception-2.0
+      SPDX-URL: https://spdx.org/licenses/GCC-exception-2.0.html
+      SPDX-Licenses: GPL-2.0, GPL-2.0+
+      Usage-Guidance:
+        The "GCC Runtime Library exception 2.0" is used together with one
+	of the above SPDX-Licenses for code imported from the GCC runtime
+	library.
+        To use this exception add it with the keyword WITH to one of the
+	identifiers in the SPDX-Licenses tag:
+	  SPDX-License-Identifier: <SPDX-License> WITH GCC-exception-2.0
+      Exception-Text:
+        Full exception text
+
+
+All SPDX license identifiers and exceptions must have a corresponding file
+in the LICENSE subdirectories. This is required to allow tool
+verification (e.g. checkpatch.pl) and to have the licenses ready to read
+and extract right from the source, which is recommended by various FOSS
+organizations, e.g. the `FSFE REUSE initiative <https://reuse.software/>`_.
diff --git a/Documentation/process/submit-checklist.rst b/Documentation/process/submit-checklist.rst
index a0d9d34bfb6d..367353c54949 100644
--- a/Documentation/process/submit-checklist.rst
+++ b/Documentation/process/submit-checklist.rst
@@ -37,7 +37,9 @@ and elsewhere regarding submitting Linux kernel patches.
    You should be able to justify all violations that remain in
    your patch.
 
-6) Any new or modified ``CONFIG`` options don't muck up the config menu.
+6) Any new or modified ``CONFIG`` options do not muck up the config menu and
+   default to off unless they meet the exception criteria documented in
+   ``Documentation/kbuild/kconfig-language.txt`` Menu attributes: default value.
 
 7) All new ``Kconfig`` options have help text.
 
diff --git a/Documentation/scsi/scsi_mid_low_api.txt b/Documentation/scsi/scsi_mid_low_api.txt
index 6338400eed73..2c31d9ee6776 100644
--- a/Documentation/scsi/scsi_mid_low_api.txt
+++ b/Documentation/scsi/scsi_mid_low_api.txt
@@ -319,12 +319,12 @@ struct Scsi_Host:
         instance. If the reference count reaches 0 then the given instance
         is freed
 
-The Scsi_device structure has had reference counting infrastructure added.
-This effectively spreads the ownership of struct Scsi_device instances
+The scsi_device structure has had reference counting infrastructure added.
+This effectively spreads the ownership of struct scsi_device instances
 across the various SCSI layers which use them. Previously such instances
 were exclusively owned by the mid level. See the access functions declared
 towards the end of include/scsi/scsi_device.h . If an LLD wants to keep
-a copy of a pointer to a Scsi_device instance it should use scsi_device_get()
+a copy of a pointer to a scsi_device instance it should use scsi_device_get()
 to bump its reference count. When it is finished with the pointer it can
 use scsi_device_put() to decrement its reference count (and potentially
 delete it).
diff --git a/Documentation/security/credentials.rst b/Documentation/security/credentials.rst
index 66a2e24939d8..5bb7125faeee 100644
--- a/Documentation/security/credentials.rst
+++ b/Documentation/security/credentials.rst
@@ -451,6 +451,13 @@ checks and hooks done.  Both the current and the proposed sets of credentials
 are available for this purpose as current_cred() will return the current set
 still at this point.
 
+When replacing the group list, the new list must be sorted before it
+is added to the credential, as a binary search is used to test for
+membership.  In practice, this means :c:func:`groups_sort` should be
+called before :c:func:`set_groups` or :c:func:`set_current_groups`.
+:c:func:`groups_sort)` must not be called on a ``struct group_list`` which
+is shared as it may permute elements as part of the sorting process
+even if the array is already sorted.
 
 When the credential set is ready, it should be committed to the current process
 by calling::
diff --git a/Documentation/security/self-protection.rst b/Documentation/security/self-protection.rst
index 60c8bd8b77bf..0f53826c78b9 100644
--- a/Documentation/security/self-protection.rst
+++ b/Documentation/security/self-protection.rst
@@ -270,6 +270,21 @@ attacks, it is important to defend against exposure of both kernel memory
 addresses and kernel memory contents (since they may contain kernel
 addresses or other sensitive things like canary values).
 
+Kernel addresses
+----------------
+
+Printing kernel addresses to userspace leaks sensitive information about
+the kernel memory layout. Care should be exercised when using any printk
+specifier that prints the raw address, currently %px, %p[ad], (and %p[sSb]
+in certain circumstances [*]).  Any file written to using one of these
+specifiers should be readable only by privileged processes.
+
+Kernels 4.14 and older printed the raw address using %p. As of 4.15-rc1
+addresses printed with the specifier %p are hashed before printing.
+
+[*] If KALLSYMS is enabled and symbol lookup fails, the raw address is
+printed. If KALLSYMS is not enabled the raw address is printed.
+
 Unique identifiers
 ------------------
 
diff --git a/Documentation/sparc/oradax/dax-hv-api.txt b/Documentation/sparc/oradax/dax-hv-api.txt
new file mode 100644
index 000000000000..73e8d506cf64
--- /dev/null
+++ b/Documentation/sparc/oradax/dax-hv-api.txt
@@ -0,0 +1,1433 @@
+Excerpt from UltraSPARC Virtual Machine Specification
+Compiled from version 3.0.20+15
+Publication date 2017-09-25 08:21
+Copyright © 2008, 2015 Oracle and/or its affiliates. All rights reserved.
+Extracted via "pdftotext -f 547 -l 572 -layout sun4v_20170925.pdf"
+Authors:
+	 Charles Kunzman
+	 Sam Glidden
+	 Mark Cianchetti
+
+
+Chapter 36. Coprocessor services
+        The following APIs provide access via the Hypervisor to hardware assisted data processing functionality.
+        These APIs may only be provided by certain platforms, and may not be available to all virtual machines
+        even on supported platforms. Restrictions on the use of these APIs may be imposed in order to support
+        live-migration and other system management activities.
+
+36.1. Data Analytics Accelerator
+        The Data Analytics Accelerator (DAX) functionality is a collection of hardware coprocessors that provide
+        high speed processoring of database-centric operations. The coprocessors may support one or more of
+        the following data query operations: search, extraction, compression, decompression, and translation. The
+        functionality offered may vary by virtual machine implementation.
+
+        The DAX is a virtual device to sun4v guests, with supported data operations indicated by the virtual device
+        compatibilty property. Functionality is accessed through the submission of Command Control Blocks
+        (CCBs) via the ccb_submit API function. The operations are processed asynchronously, with the status
+        of the submitted operations reported through a Completion Area linked to each CCB. Each CCB has a
+        separate Completion Area and, unless execution order is specifically restricted through the use of serial-
+        conditional flags, the execution order of submitted CCBs is arbitrary. Likewise, the time to completion
+        for a given CCB is never guaranteed.
+
+        Guest software may implement a software timeout on CCB operations, and if the timeout is exceeded, the
+        operation may be cancelled or killed via the ccb_kill API function. It is recommended for guest software
+        to implement a software timeout to account for certain RAS errors which may result in lost CCBs. It is
+        recommended such implementation use the ccb_info API function to check the status of a CCB prior to
+        killing it in order to determine if the CCB is still in queue, or may have been lost due to a RAS error.
+
+        There is no fixed limit on the number of outstanding CCBs guest software may have queued in the virtual
+        machine, however, internal resource limitations within the virtual machine can cause CCB submissions
+        to be temporarily rejected with EWOULDBLOCK. In such cases, guests should continue to attempt
+        submissions until they succeed; waiting for an outstanding CCB to complete is not necessary, and would
+        not be a guarantee that a future submission would succeed.
+
+        The availablility of DAX coprocessor command service is indicated by the presence of the DAX virtual
+        device node in the guest MD (Section 8.24.17, “Database Analytics Accelerators (DAX) virtual-device
+        node”).
+
+36.1.1. DAX Compatibility Property
+        The query functionality may vary based on the compatibility property of the virtual device:
+
+36.1.1.1. "ORCL,sun4v-dax" Device Compatibility
+        Available CCB commands:
+
+        • No-op/Sync
+
+        • Extract
+
+        • Scan Value
+
+        • Inverted Scan Value
+
+        • Scan Range
+
+
+                                                     509
+                                             Coprocessor services
+
+
+        • Inverted Scan Range
+
+        • Translate
+
+        • Inverted Translate
+
+        • Select
+
+        See Section 36.2.1, “Query CCB Command Formats” for the corresponding CCB input and output formats.
+
+        Only version 0 CCBs are available.
+
+36.1.1.2. "ORCL,sun4v-dax-fc" Device Compatibility
+        "ORCL,sun4v-dax-fc" is compatible with the "ORCL,sun4v-dax" interface, and includes additional CCB
+        bit fields and controls.
+
+36.1.1.3. "ORCL,sun4v-dax2" Device Compatibility
+        Available CCB commands:
+
+        • No-op/Sync
+
+        • Extract
+
+        • Scan Value
+
+        • Inverted Scan Value
+
+        • Scan Range
+
+        • Inverted Scan Range
+
+        • Translate
+
+        • Inverted Translate
+
+        • Select
+
+        See Section 36.2.1, “Query CCB Command Formats” for the corresponding CCB input and output formats.
+
+        Version 0 and 1 CCBs are available. Only version 0 CCBs may use Huffman encoded data, whereas only
+        version 1 CCBs may use OZIP.
+
+36.1.2. DAX Virtual Device Interrupts
+        The DAX virtual device has multiple interrupts associated with it which may be used by the guest if
+        desired. The number of device interrupts available to the guest is indicated in the virtual device node of the
+        guest MD (Section 8.24.17, “Database Analytics Accelerators (DAX) virtual-device node”). If the device
+        node indicates N interrupts available, the guest may use any value from 0 to N - 1 (inclusive) in a CCB
+        interrupt number field. Using values outside this range will result in the CCB being rejected for an invalid
+        field value.
+
+        The interrupts may be bound and managed using the standard sun4v device interrupts API (Chapter 16,
+        Device interrupt services). Sysino interrupts are not available for DAX devices.
+
+36.2. Coprocessor Control Block (CCB)
+        CCBs are either 64 or 128 bytes long, depending on the operation type. The exact contents of the CCB
+        are command specific, but all CCBs contain at least one memory buffer address. All memory locations
+
+
+                                                      510
+                                    Coprocessor services
+
+
+referenced by a CCB must be pinned in memory until the CCB either completes execution or is killed
+via the ccb_kill API call. Changes in virtual address mappings occurring after CCB submission are not
+guaranteed to be visible, and as such all virtual address updates need to be synchronized with CCB
+execution.
+
+All CCBs begin with a common 32-bit header.
+
+Table 36.1. CCB Header Format
+Bits          Field Description
+[31:28]       CCB version. For API version 2.0: set to 1 if CCB uses OZIP encoding; set to 0 if the CCB
+              uses Huffman encoding; otherwise either 0 or 1. For API version 1.0: always set to 0.
+[27]          When API version 2.0 is negotiated, this is the Pipeline Flag [512]. It is reserved in
+              API version 1.0
+[26]          Long CCB flag [512]
+[25]          Conditional synchronization flag [512]
+[24]          Serial synchronization flag
+[23:16]       CCB operation code:
+               0x00        No Operation (No-op) or Sync
+               0x01        Extract
+               0x02        Scan Value
+               0x12        Inverted Scan Value
+               0x03        Scan Range
+               0x13        Inverted Scan Range
+               0x04        Translate
+               0x14        Inverted Translate
+               0x05        Select
+[15:13]       Reserved
+[12:11]       Table address type
+               0b'00       No address
+               0b'01       Alternate context virtual address
+               0b'10       Real address
+               0b'11       Primary context virtual address
+[10:8]        Output/Destination address type
+               0b'000      No address
+               0b'001      Alternate context virtual address
+               0b'010      Real address
+               0b'011      Primary context virtual address
+               0b'100      Reserved
+               0b'101      Reserved
+               0b'110      Reserved
+               0b'111      Reserved
+[7:5]         Secondary source address type
+
+
+                                            511
+                                    Coprocessor services
+
+
+Bits           Field Description
+                0b'000       No address
+                0b'001       Alternate context virtual address
+                0b'010       Real address
+                0b'011       Primary context virtual address
+                0b'100       Reserved
+                0b'101       Reserved
+                0b'110       Reserved
+                0b'111       Reserved
+[4:2]          Primary source address type
+                0b'000       No address
+                0b'001       Alternate context virtual address
+                0b'010       Real address
+                0b'011       Primary context virtual address
+                0b'100       Reserved
+                0b'101       Reserved
+                0b'110       Reserved
+                0b'111       Reserved
+[1:0]          Completion area address type
+                0b'00        No address
+                0b'01        Alternate context virtual address
+                0b'10        Real address
+                0b'11        Primary context virtual address
+
+The Long CCB flag indicates whether the submitted CCB is 64 or 128 bytes long; value is 0 for 64 bytes
+and 1 for 128 bytes.
+
+The Serial and Conditional flags allow simple relative ordering between CCBs. Any CCB with the Serial
+flag set will execute sequentially relative to any previous CCB that is also marked as Serial in the same
+CCB submission. CCBs without the Serial flag set execute independently, even if they are between CCBs
+with the Serial flag set. CCBs marked solely with the Serial flag will execute upon the completion of the
+previous Serial CCB, regardless of the completion status of that CCB. The Conditional flag allows CCBs
+to conditionally execute based on the successful execution of the closest CCB marked with the Serial flag.
+A CCB may only be conditional on exactly one CCB, however, a CCB may be marked both Conditional
+and Serial to allow execution chaining. The flags do NOT allow fan-out chaining, where multiple CCBs
+execute in parallel based on the completion of another CCB.
+
+The Pipeline flag is an optimization that directs the output of one CCB (the "source" CCB) directly to
+the input of the next CCB (the "target" CCB). The target CCB thus does not need to read the input from
+memory. The Pipeline flag is advisory and may be dropped.
+
+Both the Pipeline and Serial bits must be set in the source CCB. The Conditional bit must be set in the
+target CCB. Exactly one CCB must be made conditional on the source CCB; either 0 or 2 target CCBs
+is invalid. However, Pipelines can be extended beyond two CCBs: the sequence would start with a CCB
+with both the Pipeline and Serial bits set, proceed through CCBs with the Pipeline, Serial, and Conditional
+bits set, and terminate at a CCB that has the Conditional bit set, but not the Pipeline bit.
+
+
+                                             512
+                                               Coprocessor services
+
+
+          The input of the target CCB must start within 64 bytes of the output of the source CCB or the pipeline flag
+          will be ignored. All CCBs in a pipeline must be submitted in the same call to ccb_submit.
+
+          The various address type fields indicate how the various address values used in the CCB should be
+          interpreted by the virtual machine. Not all of the types specified are used by every CCB format. Types
+          which are not applicable to the given CCB command should be indicated as type 0 (No address). Virtual
+          addresses used in the CCB must have translation entries present in either the TLB or a configured TSB
+          for the submitting virtual processor. Virtual addresses which cannot be translated by the virtual machine
+          will result in the CCB submission being rejected, with the causal virtual address indicated. The CCB
+          may be resubmitted after inserting the translation, or the address may be translated by guest software and
+          resubmitted using the real address translation.
+
+36.2.1. Query CCB Command Formats
+36.2.1.1. Supported Data Formats, Elements Sizes and Offsets
+          Data for query commands may be encoded in multiple possible formats. The data query commands use a
+          common set of values to indicate the encoding formats of the data being processed. Some encoding formats
+          require multiple data streams for processing, requiring the specification of both primary data formats (the
+          encoded data) and secondary data streams (meta-data for the encoded data).
+
+36.2.1.1.1. Primary Input Format
+
+          The primary input format code is a 4-bit field when it is used. There are 10 primary input formats available.
+          The packed formats are not endian neutral. Code values not listed below are reserved.
+
+          Code        Format                              Description
+          0x0         Fixed width byte packed             Up to 16 bytes
+          0x1         Fixed width bit packed              Up to 15 bits (CCB version 0) or 23 bits (CCB version
+                                                          1); bits are read most significant bit to least significant bit
+                                                          within a byte
+          0x2         Variable width byte packed          Data stream of lengths must be provided as a secondary
+                                                          input
+          0x4         Fixed width byte packed with run Up to 16 bytes; data stream of run lengths must be
+                      length encoding                  provided as a secondary input
+          0x5         Fixed width bit packed with run Up to 15 bits (CCB version 0) or 23 bits (CCB version
+                      length encoding                 1); bits are read most significant bit to least significant bit
+                                                      within a byte; data stream of run lengths must be provided
+                                                      as a secondary input
+          0x8         Fixed width byte packed with Up to 16 bytes before the encoding; compressed stream
+                      Huffman (CCB version 0) or bits are read most significant bit to least significant bit
+                      OZIP (CCB version 1) encoding within a byte; pointer to the encoding table must be
+                                                    provided
+          0x9         Fixed width bit packed with Up to 15 bits (CCB version 0) or 23 bits (CCB version
+                      Huffman (CCB version 0) or 1); compressed stream bits are read most significant bit to
+                      OZIP (CCB version 1) encoding least significant bit within a byte; pointer to the encoding
+                                                    table must be provided
+          0xA         Variable width byte packed with Up to 16 bytes before the encoding; compressed stream
+                      Huffman (CCB version 0) or bits are read most significant bit to least significant bit
+                      OZIP (CCB version 1) encoding within a byte; data stream of lengths must be provided as
+                                                      a secondary input; pointer to the encoding table must be
+                                                      provided
+
+
+                                                        513
+                                               Coprocessor services
+
+
+          Code        Format                              Description
+          0xC         Fixed width byte packed with        Up to 16 bytes before the encoding; compressed stream
+                      run length encoding, followed by    bits are read most significant bit to least significant bit
+                      Huffman (CCB version 0) or          within a byte; data stream of run lengths must be provided
+                      OZIP (CCB version 1) encoding       as a secondary input; pointer to the encoding table must
+                                                          be provided
+          0xD         Fixed width bit packed with         Up to 15 bits (CCB version 0) or 23 bits(CCB version 1)
+                      run length encoding, followed by    before the encoding; compressed stream bits are read most
+                      Huffman (CCB version 0) or          significant bit to least significant bit within a byte; data
+                      OZIP (CCB version 1) encoding       stream of run lengths must be provided as a secondary
+                                                          input; pointer to the encoding table must be provided
+
+          If OZIP encoding is used, there must be no reserved bytes in the table.
+
+36.2.1.1.2. Primary Input Element Size
+
+          For primary input data streams with fixed size elements, the element size must be indicated in the CCB
+          command. The size is encoded as the number of bits or bytes, minus one. The valid value range for this
+          field depends on the input format selected, as listed in the table above.
+
+36.2.1.1.3. Secondary Input Format
+
+          For primary input data streams which require a secondary input stream, the secondary input stream is
+          always encoded in a fixed width, bit-packed format. The bits are read from most significant bit to least
+          significant bit within a byte. There are two encoding options for the secondary input stream data elements,
+          depending on whether the value of 0 is needed:
+
+          Secondary           Input Description
+          Format Code
+          0                          Element is stored as value minus 1 (0 evalutes to 1, 1 evalutes
+                                     to 2, etc)
+          1                          Element is stored as value
+
+36.2.1.1.4. Secondary Input Element Size
+
+          Secondary input element size is encoded as a two bit field:
+
+          Secondary Input Size Description
+          Code
+          0x0                        1 bit
+          0x1                        2 bits
+          0x2                        4 bits
+          0x3                        8 bits
+
+36.2.1.1.5. Input Element Offsets
+
+          Bit-wise input data streams may have any alignment within the base addressed byte. The offset, specified
+          from most significant bit to least significant bit, is provided as a fixed 3 bit field for each input type. A
+          value of 0 indicates that the first input element begins at the most significant bit in the first byte, and a
+          value of 7 indicates it begins with the least significant bit.
+
+          This field should be zero for any byte-wise primary input data streams.
+
+
+                                                        514
+                                              Coprocessor services
+
+
+36.2.1.1.6. Output Format
+
+          Query commands support multiple sizes and encodings for output data streams. There are four possible
+          output encodings, and up to four supported element sizes per encoding. Not all output encodings are
+          supported for every command. The format is indicated by a 4-bit field in the CCB:
+
+           Output Format Code        Description
+           0x0                       Byte aligned, 1 byte elements
+           0x1                       Byte aligned, 2 byte elements
+           0x2                       Byte aligned, 4 byte elements
+           0x3                       Byte aligned, 8 byte elements
+           0x4                       16 byte aligned, 16 byte elements
+           0x5                       Reserved
+           0x6                       Reserved
+           0x7                       Reserved
+           0x8                       Packed vector of single bit elements
+           0x9                       Reserved
+           0xA                       Reserved
+           0xB                       Reserved
+           0xC                       Reserved
+           0xD                       2 byte elements where each element is the index value of a bit,
+                                     from an bit vector, which was 1.
+           0xE                       4 byte elements where each element is the index value of a bit,
+                                     from an bit vector, which was 1.
+           0xF                       Reserved
+
+36.2.1.1.7. Application Data Integrity (ADI)
+
+          On platforms which support ADI, the ADI version number may be specified for each separate memory
+          access type used in the CCB command. ADI checking only occurs when reading data. When writing data,
+          the specified ADI version number overwrites any existing ADI value in memory.
+
+          An ADI version value of 0 or 0xF indicates the ADI checking is disabled for that data access, even if it is
+          enabled in memory. By setting the appropriate flag in CCB_SUBMIT (Section 36.3.1, “ccb_submit”) it is
+          also an option to disable ADI checking for all inputs accessed via virtual address for all CCBs submitted
+          during that hypercall invocation.
+
+          The ADI value is only guaranteed to be checked on the first 64 bytes of each data access. Mismatches on
+          subsequent data chunks may not be detected, so guest software should be careful to use page size checking
+          to protect against buffer overruns.
+
+36.2.1.1.8. Page size checking
+
+          All data accesses used in CCB commands must be bounded within a single memory page. When addresses
+          are provided using a virtual address, the page size for checking is extracted from the TTE for that virtual
+          address. When using real addresses, the guest must supply the page size in the same field as the address
+          value. The page size must be one of the sizes supported by the underlying virtual machine. Using a value
+          that is not supported may result in the CCB submission being rejected or the generation of a CCB parsing
+          error in the completion area.
+
+
+                                                       515
+                                               Coprocessor services
+
+
+36.2.1.2. Extract command
+
+        Converts an input vector in one format to an output vector in another format. All input format types are
+        supported.
+
+        The only supported output format is a padded, byte-aligned output stream, using output codes 0x0 - 0x4.
+        When the specified output element size is larger than the extracted input element size, zeros are padded to
+        the extracted input element. First, if the decompressed input size is not a whole number of bytes, 0 bits are
+        padded to the most significant bit side till the next byte boundary. Next, if the output element size is larger
+        than the byte padded input element, bytes of value 0 are added based on the Padding Direction bit in the
+        CCB. If the output element size is smaller than the byte-padded input element size, the input element is
+        truncated by dropped from the least significant byte side until the selected output size is reached.
+
+        The return value of the CCB completion area is invalid. The “number of elements processed” field in the
+        CCB completion area will be valid.
+
+        The extract CCB is a 64-byte “short format” CCB.
+
+        The extract CCB command format can be specified by the following packed C structure for a big-endian
+        machine:
+
+
+                  struct extract_ccb {
+                         uint32_t header;
+                         uint32_t control;
+                         uint64_t completion;
+                         uint64_t primary_input;
+                         uint64_t data_access_control;
+                         uint64_t secondary_input;
+                         uint64_t reserved;
+                         uint64_t output;
+                         uint64_t table;
+                  };
+
+
+        The exact field offsets, sizes, and composition are as follows:
+
+         Offset         Size            Field Description
+         0              4               CCB header (Table 36.1, “CCB Header Format”)
+         4              4               Command control
+                                        Bits        Field Description
+                                        [31:28]     Primary Input Format (see Section 36.2.1.1.1, “Primary Input
+                                                    Format”)
+                                        [27:23]     Primary Input Element Size (see Section 36.2.1.1.2, “Primary
+                                                    Input Element Size”)
+                                        [22:20]     Primary Input Starting Offset (see Section 36.2.1.1.5, “Input
+                                                    Element Offsets”)
+                                        [19]        Secondary Input Format (see Section 36.2.1.1.3, “Secondary
+                                                    Input Format”)
+                                        [18:16]     Secondary Input Starting Offset (see Section 36.2.1.1.5, “Input
+                                                    Element Offsets”)
+
+
+                                                       516
+                        Coprocessor services
+
+
+Offset   Size   Field Description
+                Bits         Field Description
+                [15:14]      Secondary Input Element Size (see Section 36.2.1.1.4,
+                             “Secondary Input Element Size”
+                [13:10]      Output Format (see Section 36.2.1.1.6, “Output Format”)
+                [9]          Padding Direction selector: A value of 1 causes padding bytes
+                             to be added to the left side of output elements. A value of 0
+                             causes padding bytes to be added to the right side of output
+                             elements.
+                [8:0]        Reserved
+8        8      Completion
+                Bits         Field Description
+                [63:60]      ADI version (see Section 36.2.1.1.7, “Application Data
+                             Integrity (ADI)”)
+                [59]         If set to 1, a virtual device interrupt will be generated using
+                             the device interrupt number specified in the lower bits of this
+                             completion word. If 0, the lower bits of this completion word
+                             are ignored.
+                [58:6]       Completion area address bits [58:6]. Address type is
+                             determined by CCB header.
+                [5:0]        Virtual device interrupt number for completion interrupt, if
+                             enabled.
+16       8      Primary Input
+                Bits         Field Description
+                [63:60]      ADI version (see Section 36.2.1.1.7, “Application Data
+                             Integrity (ADI)”)
+                [59:56]      If using real address, these bits should be filled in with the
+                             page size code for the page boundary checking the guest wants
+                             the virtual machine to use when accessing this data stream
+                             (checking is only guaranteed to be performed when using API
+                             version 1.1 and later). If using a virtual address, this field will
+                             be used as as primary input address bits [59:56].
+                [55:0]       Primary input address bits [55:0]. Address type is determined
+                             by CCB header.
+24       8      Data Access Control
+                Bits         Field Description
+                [63:62]      Flow Control
+                             Value      Description
+                             0b'00      Disable flow control
+                             0b'01      Enable flow control (only valid with "ORCL,sun4v-
+                                        dax-fc" compatible virtual device variants)
+                             0b'10      Reserved
+                             0b'11      Reserved
+                [61:60]      Reserved (API 1.0)
+
+
+                                517
+                       Coprocessor services
+
+
+Offset   Size   Field Description
+                Bits        Field Description
+                            Pipeline target (API 2.0)
+                            Value      Description
+                            0b'00      Connect to primary input
+                            0b'01      Connect to secondary input
+                            0b'10      Reserved
+                            0b'11      Reserved
+                [59:40]     Output buffer size given in units of 64 bytes, minus 1. Value of
+                            0 means 64 bytes, value of 1 means 128 bytes, etc. Buffer size is
+                            only enforced if flow control is enabled in Flow Control field.
+                [39:32]     Reserved
+                [31:30]     Output Data Cache Allocation
+                            Value      Description
+                            0b'00      Do not allocate cache lines for output data stream.
+                            0b'01      Force cache lines for output data stream to be
+                                       allocated in the cache that is local to the submitting
+                                       virtual cpu.
+                            0b'10      Allocate cache lines for output data stream, but allow
+                                       existing cache lines associated with the data to remain
+                                       in their current cache instance. Any memory not
+                                       already in cache will be allocated in the cache local
+                                       to the submitting virtual cpu.
+                            0b'11      Reserved
+                [29:26]     Reserved
+                [25:24]     Primary Input Length Format
+                            Value      Description
+                            0b'00      Number of primary symbols
+                            0b'01      Number of primary bytes
+                            0b'10      Number of primary bits
+                            0b'11      Reserved
+                [23:0]      Primary Input Length
+                            Format                      Field Value
+                            # of primary symbols        Number of input elements to process,
+                                                        minus 1. Command execution stops
+                                                        once count is reached.
+                            # of primary bytes          Number of input bytes to process,
+                                                        minus 1. Command execution stops
+                                                        once count is reached. The count is
+                                                        done before any decompression or
+                                                        decoding.
+                            # of primary bits           Number of input bits to process,
+                                                        minus 1. Command execution stops
+
+
+
+                               518
+                                                Coprocessor services
+
+
+        Offset          Size           Field Description
+                                        Bits         Field Description
+                                                     Format                     Field Value
+                                                                                once count is reached. The count is
+                                                                                done before any decompression or
+                                                                                decoding, and does not include any
+                                                                                bits skipped by the Primary Input
+                                                                                Offset field value of the command
+                                                                                control word.
+        32              8              Secondary Input, if used by Primary Input Format. Same fields as Primary
+                                       Input.
+        40              8              Reserved
+        48              8              Output (same fields as Primary Input)
+        56              8              Symbol Table (if used by Primary Input)
+                                        Bits         Field Description
+                                        [63:60]      ADI version (see Section 36.2.1.1.7, “Application Data
+                                                     Integrity (ADI)”)
+                                        [59:56]      If using real address, these bits should be filled in with the
+                                                     page size code for the page boundary checking the guest wants
+                                                     the virtual machine to use when accessing this data stream
+                                                     (checking is only guaranteed to be performed when using API
+                                                     version 1.1 and later). If using a virtual address, this field will
+                                                     be used as as symbol table address bits [59:56].
+                                        [55:4]       Symbol table address bits [55:4]. Address type is determined
+                                                     by CCB header.
+                                        [3:0]        Symbol table version
+                                                     Value     Description
+                                                     0         Huffman encoding. Must use 64 byte aligned table
+                                                               address. (Only available when using version 0 CCBs)
+                                                     1         OZIP encoding. Must use 16 byte aligned table
+                                                               address. (Only available when using version 1 CCBs)
+
+
+36.2.1.3. Scan commands
+
+        The scan commands search a stream of input data elements for values which match the selection criteria.
+        All the input format types are supported. There are multiple formats for the scan commands, allowing the
+        scan to search for exact matches to one value, exact matches to either of two values, or any value within
+        a specified range. The specific type of scan is indicated by the command code in the CCB header. For the
+        scan range commands, the boundary conditions can be specified as greater-than-or-equal-to a value, less-
+        than-or-equal-to a value, or both by using two boundary values.
+
+        There are two supported formats for the output stream: the bit vector and index array formats (codes 0x8,
+        0xD, and 0xE). For the standard scan command using the bit vector output, for each input element there
+        exists one bit in the vector that is set if the input element matched the scan criteria, or clear if not. The
+        inverted scan command inverts the polarity of the bits in the output. The most significant bit of the first
+        byte of the output stream corresponds to the first element in the input stream. The standard index array
+        output format contains one array entry for each input element that matched the scan criteria. Each array
+
+
+
+                                                         519
+                                       Coprocessor services
+
+
+entry is the index of an input element that matched the scan criteria. An inverted scan command produces
+a similar array, but of all the input elements which did NOT match the scan criteria.
+
+The return value of the CCB completion area contains the number of input elements found which match
+the scan criteria (or number that did not match for the inverted scans). The “number of elements processed”
+field in the CCB completion area will be valid, indicating the number of input elements processed.
+
+These commands are 128-byte “long format” CCBs.
+
+The scan CCB command format can be specified by the following packed C structure for a big-endian
+machine:
+
+
+         struct scan_ccb         {
+                uint32_t         header;
+                uint32_t         control;
+                uint64_t         completion;
+                uint64_t         primary_input;
+                uint64_t         data_access_control;
+                uint64_t         secondary_input;
+                uint64_t         match_criteria0;
+                uint64_t         output;
+                uint64_t         table;
+                uint64_t         match_criteria1;
+                uint64_t         match_criteria2;
+                uint64_t         match_criteria3;
+                uint64_t         reserved[5];
+         };
+
+
+The exact field offsets, sizes, and composition are as follows:
+
+Offset         Size            Field Description
+0              4               CCB header (Table 36.1, “CCB Header Format”)
+4              4               Command control
+                               Bits         Field Description
+                               [31:28]      Primary Input Format (see Section 36.2.1.1.1, “Primary Input
+                                            Format”)
+                               [27:23]      Primary Input Element Size (see Section 36.2.1.1.2, “Primary
+                                            Input Element Size”)
+                               [22:20]      Primary Input Starting Offset (see Section 36.2.1.1.5, “Input
+                                            Element Offsets”)
+                               [19]         Secondary Input Format (see Section 36.2.1.1.3, “Secondary
+                                            Input Format”)
+                               [18:16]      Secondary Input Starting Offset (see Section 36.2.1.1.5, “Input
+                                            Element Offsets”)
+                               [15:14]      Secondary Input Element Size (see Section 36.2.1.1.4,
+                                            “Secondary Input Element Size”
+                               [13:10]      Output Format (see Section 36.2.1.1.6, “Output Format”)
+                               [9:5]        Operand size for first scan criteria value. In a scan value
+                                            operation, this is one of two potential extact match values.
+                                            In a scan range operation, this is the size of the upper range
+
+
+                                               520
+                        Coprocessor services
+
+
+Offset   Size   Field Description
+                Bits         Field Description
+                             boundary. The value of this field is the number of bytes in the
+                             operand, minus 1. Values 0xF-0x1E are reserved. A value of
+                             0x1F indicates this operand is not in use for this scan operation.
+                [4:0]        Operand size for second scan criteria value. In a scan value
+                             operation, this is one of two potential extact match values.
+                             In a scan range operation, this is the size of the lower range
+                             boundary. The value of this field is the number of bytes in the
+                             operand, minus 1. Values 0xF-0x1E are reserved. A value of
+                             0x1F indicates this operand is not in use for this scan operation.
+8        8      Completion (same fields as Section 36.2.1.2, “Extract command”)
+16       8      Primary Input (same fields as Section 36.2.1.2, “Extract command”)
+24       8      Data Access Control (same fields as Section 36.2.1.2, “Extract command”)
+32       8      Secondary Input, if used by Primary Input Format. Same fields as Primary
+                Input.
+40       4      Most significant 4 bytes of first scan criteria operand. If first operand is less
+                than 4 bytes, the value is left-aligned to the lowest address bytes.
+44       4      Most significant 4 bytes of second scan criteria operand. If second operand
+                is less than 4 bytes, the value is left-aligned to the lowest address bytes.
+48       8      Output (same fields as Primary Input)
+56       8      Symbol Table (if used by Primary Input). Same fields as Section 36.2.1.2,
+                “Extract command”
+64       4      Next 4 most significant bytes of first scan criteria operand occuring after the
+                bytes specified at offset 40, if needed by the operand size. If first operand
+                is less than 8 bytes, the valid bytes are left-aligned to the lowest address.
+68       4      Next 4 most significant bytes of second scan criteria operand occuring after
+                the bytes specified at offset 44, if needed by the operand size. If second
+                operand is less than 8 bytes, the valid bytes are left-aligned to the lowest
+                address.
+72       4      Next 4 most significant bytes of first scan criteria operand occuring after the
+                bytes specified at offset 64, if needed by the operand size. If first operand
+                is less than 12 bytes, the valid bytes are left-aligned to the lowest address.
+76       4      Next 4 most significant bytes of second scan criteria operand occuring after
+                the bytes specified at offset 68, if needed by the operand size. If second
+                operand is less than 12 bytes, the valid bytes are left-aligned to the lowest
+                address.
+80       4      Next 4 most significant bytes of first scan criteria operand occuring after the
+                bytes specified at offset 72, if needed by the operand size. If first operand
+                is less than 16 bytes, the valid bytes are left-aligned to the lowest address.
+84       4      Next 4 most significant bytes of second scan criteria operand occuring after
+                the bytes specified at offset 76, if needed by the operand size. If second
+                operand is less than 16 bytes, the valid bytes are left-aligned to the lowest
+                address.
+
+
+
+
+                                521
+                                               Coprocessor services
+
+
+36.2.1.4. Translate commands
+
+        The translate commands takes an input array of indicies, and a table of single bit values indexed by those
+        indicies, and outputs a bit vector or index array created by reading the tables bit value at each index in
+        the input array. The output should therefore contain exactly one bit per index in the input data stream,
+        when outputing as a bit vector. When outputing as an index array, the number of elements depends on the
+        values read in the bit table, but will always be less than, or equal to, the number of input elements. Only
+        a restricted subset of the possible input format types are supported. No variable width or Huffman/OZIP
+        encoded input streams are allowed. The primary input data element size must be 3 bytes or less.
+
+        The maximum table index size allowed is 15 bits, however, larger input elements may be used to provide
+        additional processing of the output values. If 2 or 3 byte values are used, the least significant 15 bits are
+        used as an index into the bit table. The most significant 9 bits (when using 3-byte input elements) or single
+        bit (when using 2-byte input elements) are compared against a fixed 9-bit test value provided in the CCB.
+        If the values match, the value from the bit table is used as the output element value. If the values do not
+        match, the output data element value is forced to 0.
+
+        In the inverted translate operation, the bit value read from bit table is inverted prior to its use. The additional
+        additional processing based on any additional non-index bits remains unchanged, and still forces the output
+        element value to 0 on a mismatch. The specific type of translate command is indicated by the command
+        code in the CCB header.
+
+        There are two supported formats for the output stream: the bit vector and index array formats (codes 0x8,
+        0xD, and 0xE). The index array format is an array of indicies of bits which would have been set if the
+        output format was a bit array.
+
+        The return value of the CCB completion area contains the number of bits set in the output bit vector,
+        or number of elements in the output index array. The “number of elements processed” field in the CCB
+        completion area will be valid, indicating the number of input elements processed.
+
+        These commands are 64-byte “short format” CCBs.
+
+        The translate CCB command format can be specified by the following packed C structure for a big-endian
+        machine:
+
+
+                 struct translate_ccb {
+                        uint32_t header;
+                        uint32_t control;
+                        uint64_t completion;
+                        uint64_t primary_input;
+                        uint64_t data_access_control;
+                        uint64_t secondary_input;
+                        uint64_t reserved;
+                        uint64_t output;
+                        uint64_t table;
+                 };
+
+
+        The exact field offsets, sizes, and composition are as follows:
+
+
+        Offset          Size             Field Description
+        0               4                CCB header (Table 36.1, “CCB Header Format”)
+
+
+                                                        522
+                        Coprocessor services
+
+
+Offset   Size   Field Description
+4        4      Command control
+                Bits         Field Description
+                [31:28]      Primary Input Format (see Section 36.2.1.1.1, “Primary Input
+                             Format”)
+                [27:23]      Primary Input Element Size (see Section 36.2.1.1.2, “Primary
+                             Input Element Size”)
+                [22:20]      Primary Input Starting Offset (see Section 36.2.1.1.5, “Input
+                             Element Offsets”)
+                [19]         Secondary Input Format (see Section 36.2.1.1.3, “Secondary
+                             Input Format”)
+                [18:16]      Secondary Input Starting Offset (see Section 36.2.1.1.5, “Input
+                             Element Offsets”)
+                [15:14]      Secondary Input Element Size (see Section 36.2.1.1.4,
+                             “Secondary Input Element Size”
+                [13:10]      Output Format (see Section 36.2.1.1.6, “Output Format”)
+                [9]          Reserved
+                [8:0]        Test value used for comparison against the most significant bits
+                             in the input values, when using 2 or 3 byte input elements.
+8        8      Completion (same fields as Section 36.2.1.2, “Extract command”
+16       8      Primary Input (same fields as Section 36.2.1.2, “Extract command”
+24       8      Data Access Control (same fields as Section 36.2.1.2, “Extract command”,
+                except Primary Input Length Format may not use the 0x0 value)
+32       8      Secondary Input, if used by Primary Input Format. Same fields as Primary
+                Input.
+40       8      Reserved
+48       8      Output (same fields as Primary Input)
+56       8      Bit Table
+                Bits         Field Description
+                [63:60]      ADI version (see Section 36.2.1.1.7, “Application Data
+                             Integrity (ADI)”)
+                [59:56]      If using real address, these bits should be filled in with the
+                             page size code for the page boundary checking the guest wants
+                             the virtual machine to use when accessing this data stream
+                             (checking is only guaranteed to be performed when using API
+                             version 1.1 and later). If using a virtual address, this field will
+                             be used as as bit table address bits [59:56]
+                [55:4]       Bit table address bits [55:4]. Address type is determined by
+                             CCB header. Address must be 64-byte aligned (CCB version
+                             0) or 16-byte aligned (CCB version 1).
+                [3:0]        Bit table version
+                             Value      Description
+                             0          4KB table size
+                             1          8KB table size
+
+
+
+                                 523
+                                              Coprocessor services
+
+
+36.2.1.5. Select command
+        The select command filters the primary input data stream by using a secondary input bit vector to determine
+        which input elements to include in the output. For each bit set at a given index N within the bit vector,
+        the Nth input element is included in the output. If the bit is not set, the element is not included. Only a
+        restricted subset of the possible input format types are supported. No variable width or run length encoded
+        input streams are allowed, since the secondary input stream is used for the filtering bit vector.
+
+        The only supported output format is a padded, byte-aligned output stream. The stream follows the same
+        rules and restrictions as padded output stream described in Section 36.2.1.2, “Extract command”.
+
+        The return value of the CCB completion area contains the number of bits set in the input bit vector. The
+        "number of elements processed" field in the CCB completion area will be valid, indicating the number
+        of input elements processed.
+
+        The select CCB is a 64-byte “short format” CCB.
+
+        The select CCB command format can be specified by the following packed C structure for a big-endian
+        machine:
+
+
+                  struct select_ccb {
+                         uint32_t header;
+                         uint32_t control;
+                         uint64_t completion;
+                         uint64_t primary_input;
+                         uint64_t data_access_control;
+                         uint64_t secondary_input;
+                         uint64_t reserved;
+                         uint64_t output;
+                         uint64_t table;
+                  };
+
+
+        The exact field offsets, sizes, and composition are as follows:
+
+         Offset        Size            Field Description
+         0             4               CCB header (Table 36.1, “CCB Header Format”)
+         4             4               Command control
+                                       Bits        Field Description
+                                       [31:28]     Primary Input Format (see Section 36.2.1.1.1, “Primary Input
+                                                   Format”)
+                                       [27:23]     Primary Input Element Size (see Section 36.2.1.1.2, “Primary
+                                                   Input Element Size”)
+                                       [22:20]     Primary Input Starting Offset (see Section 36.2.1.1.5, “Input
+                                                   Element Offsets”)
+                                       [19]        Secondary Input Format (see Section 36.2.1.1.3, “Secondary
+                                                   Input Format”)
+                                       [18:16]     Secondary Input Starting Offset (see Section 36.2.1.1.5, “Input
+                                                   Element Offsets”)
+                                       [15:14]     Secondary Input Element Size (see Section 36.2.1.1.4,
+                                                   “Secondary Input Element Size”
+
+
+                                                      524
+                                               Coprocessor services
+
+
+        Offset         Size            Field Description
+                                       Bits         Field Description
+                                       [13:10]      Output Format (see Section 36.2.1.1.6, “Output Format”)
+                                       [9]          Padding Direction selector: A value of 1 causes padding bytes
+                                                    to be added to the left side of output elements. A value of 0
+                                                    causes padding bytes to be added to the right side of output
+                                                    elements.
+                                       [8:0]        Reserved
+        8              8               Completion (same fields as Section 36.2.1.2, “Extract command”
+        16             8               Primary Input (same fields as Section 36.2.1.2, “Extract command”
+        24             8               Data Access Control (same fields as Section 36.2.1.2, “Extract command”)
+        32             8               Secondary Bit Vector Input. Same fields as Primary Input.
+        40             8               Reserved
+        48             8               Output (same fields as Primary Input)
+        56             8               Symbol Table (if used by Primary Input). Same fields as Section 36.2.1.2,
+                                       “Extract command”
+
+36.2.1.6. No-op and Sync commands
+        The no-op (no operation) command is a CCB which has no processing effect. The CCB, when processed
+        by the virtual machine, simply updates the completion area with its execution status. The CCB may have
+        the serial-conditional flags set in order to restrict when it executes.
+
+        The sync command is a variant of the no-op command which with restricted execution timing. A sync
+        command CCB will only execute when all previous commands submitted in the same request have
+        completed. This is stronger than the conditional flag sequencing, which is only dependent on a single
+        previous serial CCB. While the relative ordering is guaranteed, virtual machine implementations with
+        shared hardware resources may cause the sync command to wait for longer than the minimum required
+        time.
+
+        The return value of the CCB completion area is invalid for these CCBs. The “number of elements
+        processed” field is also invalid for these CCBs.
+
+        These commands are 64-byte “short format” CCBs.
+
+        The no-op CCB command format can be specified by the following packed C structure for a big-endian
+        machine:
+
+
+                 struct nop_ccb {
+                        uint32_t header;
+                        uint32_t control;
+                        uint64_t completion;
+                        uint64_t reserved[6];
+                 };
+
+
+        The exact field offsets, sizes, and composition are as follows:
+
+        Offset         Size            Field Description
+        0              4               CCB header (Table 36.1, “CCB Header Format”)
+
+
+                                                       525
+                                          Coprocessor services
+
+
+       Offset        Size          Field Description
+       4             4             Command control
+                                   Bits        Field Description
+                                   [31]        If set, this CCB functions as a Sync command. If clear, this
+                                               CCB functions as a No-op command.
+                                   [30:0]      Reserved
+       8             8             Completion (same fields as Section 36.2.1.2, “Extract command”
+       16            46            Reserved
+
+36.2.2. CCB Completion Area
+       All CCB commands use a common 128-byte Completion Area format, which can be specified by the
+       following packed C structure for a big-endian machine:
+
+
+                struct completion_area {
+                       uint8_t status_flag;
+                       uint8_t error_note;
+                       uint8_t rsvd0[2];
+                       uint32_t error_values;
+                       uint32_t output_size;
+                       uint32_t rsvd1;
+                       uint64_t run_time;
+                       uint64_t run_stats;
+                       uint32_t elements;
+                       uint8_t rsvd2[20];
+                       uint64_t return_value;
+                       uint64_t extra_return_value[8];
+                };
+
+
+       The Completion Area must be a 128-byte aligned memory location. The exact layout can be described
+       using byte offsets and sizes relative to the memory base:
+
+       Offset        Size          Field Description
+       0             1             CCB execution status
+                                   0x0                  Command not yet completed
+                                   0x1                  Command ran and succeeded
+                                   0x2                  Command ran and failed (partial results may be been
+                                                        produced)
+                                   0x3                  Command ran and was killed (partial execution may
+                                                        have occurred)
+                                   0x4                  Command was not run
+                                   0x5-0xF              Reserved
+       1             1             Error reason code
+                                   0x0                  Reserved
+                                   0x1                  Buffer overflow
+
+
+                                                  526
+                                      Coprocessor services
+
+
+Offset          Size           Field Description
+                                0x2                 CCB decoding error
+                                0x3                 Page overflow
+                                0x4-0x6             Reserved
+                                0x7                 Command was killed
+                                0x8                 Command execution timeout
+                                0x9                 ADI miscompare error
+                                0xA                 Data format error
+                                0xB-0xD             Reserved
+                                0xE                 Unexpected hardware error (Do not retry)
+                                0xF                 Unexpected hardware error (Retry is ok)
+                                0x10-0x7F           Reserved
+                                0x80                Partial Symbol Warning
+                                0x81-0xFF           Reserved
+2               2              Reserved
+4               4              If a partial symbol warning was generated, this field contains the number
+                               of remaining bits which were not decoded.
+8               4              Number of bytes of output produced
+12              4              Reserved
+16              8              Runtime of command (unspecified time units)
+24              8              Reserved
+32              4              Number of elements processed
+36              20             Reserved
+56              8              Return value
+64              64             Extended return value
+
+The CCB completion area should be treated as read-only by guest software. The CCB execution status
+byte will be cleared by the Hypervisor to reflect the pending execution status when the CCB is submitted
+successfully. All other fields are considered invalid upon CCB submission until the CCB execution status
+byte becomes non-zero.
+
+CCBs which complete with status 0x2 or 0x3 may produce partial results and/or side effects due to partial
+execution of the CCB command. Some valid data may be accessible depending on the fault type, however,
+it is recommended that guest software treat the destination buffer as being in an unknown state. If a CCB
+completes with a status byte of 0x2, the error reason code byte can be read to determine what corrective
+action should be taken.
+
+A buffer overflow indicates that the results of the operation exceeded the size of the output buffer indicated
+in the CCB. The operation can be retried by resubmitting the CCB with a larger output buffer.
+
+A CCB decoding error indicates that the CCB contained some invalid field values. It may be also be
+triggered if the CCB output is directed at a non-existent secondary input and the pipelining hint is followed.
+
+A page overflow error indicates that the operation required accessing a memory location beyond the page
+size associated with a given address. No data will have been read or written past the page boundary, but
+partial results may have been written to the destination buffer. The CCB can be resubmitted with a larger
+page size memory allocation to complete the operation.
+
+
+                                              527
+                                            Coprocessor services
+
+
+       In the case of pipelined CCBs, a page overflow error will be triggered if the output from the pipeline source
+       CCB ends before the input of the pipeline target CCB. Page boundaries are ignored when the pipeline
+       hint is followed.
+
+       Command kill indicates that the CCB execution was halted or prevented by use of the ccb_kill API call.
+
+       Command timeout indicates that the CCB execution began, but did not complete within a pre-determined
+       limit set by the virtual machine. The command may have produced some or no output. The CCB may be
+       resubmitted with no alterations.
+
+       ADI miscompare indicates that the memory buffer version specified in the CCB did not match the value
+       in memory when accessed by the virtual machine. Guest software should not attempt to resubmit the CCB
+       without determining the cause of the version mismatch.
+
+       A data format error indicates that the input data stream did not follow the specified data input formatting
+       selected in the CCB.
+
+       Some CCBs which encounter hardware errors may be resubmitted without change. Persistent hardware
+       errors may result in multiple failures until RAS software can identify and isolate the faulty component.
+
+       The output size field indicates the number of bytes of valid output in the destination buffer. This field is
+       not valid for all possible CCB commands.
+
+       The runtime field indicates the execution time of the CCB command once it leaves the internal virtual
+       machine queue. The time units are fixed, but unspecified, allowing only relative timing comparisons
+       by guest software. The time units may also vary by hardware platform, and should not be construed to
+       represent any absolute time value.
+
+       Some data query commands process data in units of elements. If applicable to the command, the number of
+       elements processed is indicated in the listed field. This field is not valid for all possible CCB commands.
+
+       The return value and extended return value fields are output locations for commands which do not use
+       a destination output buffer, or have secondary return results. The field is not valid for all possible CCB
+       commands.
+
+36.3. Hypervisor API Functions
+36.3.1. ccb_submit
+       trap#             FAST_TRAP
+       function#         CCB_SUBMIT
+       arg0              address
+       arg1              length
+       arg2              flags
+       arg3              reserved
+       ret0              status
+       ret1              length
+       ret2              status data
+       ret3              reserved
+
+       Submit one or more coprocessor control blocks (CCBs) for evaluation and processing by the virtual
+       machine. The CCBs are passed in a linear array indicated by address. length indicates the size of
+       the array in bytes.
+
+
+                                                     528
+                                      Coprocessor services
+
+
+The address should be aligned to the size indicated by length, rounded up to the nearest power of
+two. Virtual machines implementations may reject submissions which do not adhere to that alignment.
+length must be a multiple of 64 bytes. If length is zero, the maximum supported array length will be
+returned as length in ret1. In all other cases, the length value in ret1 will reflect the number of bytes
+successfully consumed from the input CCB array.
+
+      Implementation note
+      Virtual machines should never reject submissions based on the alignment of address if the
+      entire array is contained within a single memory page of the smallest page size supported by the
+      virtual machine.
+
+A guest may choose to submit addresses used in this API function, including the CCB array address,
+as either a real or virtual addresses, with the type of each address indicated in flags. Virtual addresses
+must be present in either the TLB or an active TSB to be processed. The translation context for virtual
+addresses is determined by a combination of CCB contents and the flags argument.
+
+The flags argument is divided into multiple fields defined as follows:
+
+
+Bits            Field Description
+[63:16]         Reserved
+[15]            Disable ADI for VA reads (in API 2.0)
+                Reserved (in API 1.0)
+[14]            Virtual addresses within CCBs are translated in privileged context
+[13:12]         Alternate translation context for virtual addresses within CCBs:
+                 0b'00        CCBs requesting alternate context are rejected
+                 0b'01        Reserved
+                 0b'10        CCBs requesting alternate context use secondary context
+                 0b'11        CCBs requesting alternate context use nucleus context
+[11:9]          Reserved
+[8]             Queue info flag
+[7]             All-or-nothing flag
+[6]             If address is a virtual address, treat its translation context as privileged
+[5:4]           Address type of address:
+                 0b'00        Real address
+                 0b'01        Virtual address in primary context
+                 0b'10        Virtual address in secondary context
+                 0b'11        Virtual address in nucleus context
+[3:2]           Reserved
+[1:0]           CCB command type:
+                 0b'00        Reserved
+                 0b'01        Reserved
+                 0b'10        Query command
+                 0b'11        Reserved
+
+
+
+                                              529
+                                             Coprocessor services
+
+
+         The CCB submission type and address type for the CCB array must be provided in the flags argument.
+         All other fields are optional values which change the default behavior of the CCB processing.
+
+         When set to one, the "Disable ADI for VA reads" bit will turn off ADI checking when using a virtual
+         address to load data. ADI checking will still be done when loading real-addressed memory. This bit is only
+         available when using major version 2 of the coprocessor API group; at major version 1 it is reserved. For
+         more information about using ADI and DAX, see Section 36.2.1.1.7, “Application Data Integrity (ADI)”.
+
+         By default, all virtual addresses are treated as user addresses. If the virtual address translations are
+         privileged, they must be marked as such in the appropriate flags field. The virtual addresses used within
+         the submitted CCBs must all be translated with the same privilege level.
+
+         By default, all virtual addresses used within the submitted CCBs are translated using the primary context
+         active at the time of the submission. The address type field within a CCB allows each address to request
+         translation in an alternate address context. The address context used when the alternate address context is
+         requested is selected in the flags argument.
+
+         The all-or-nothing flag specifies whether the virtual machine should allow partial submissions of the
+         input CCB array. When using CCBs with serial-conditional flags, it is strongly recommended to use
+         the all-or-nothing flag to avoid broken conditional chains. Using long CCB chains on a machine under
+         high coprocessor load may make this impractical, however, and require submitting without the flag.
+         When submitting serial-conditional CCBs without the all-or-nothing flag, guest software must manually
+         implement the serial-conditional behavior at any point where the chain was not submitted in a single API
+         call, and resubmission of the remaining CCBs should clear any conditional flag that might be set in the
+         first remaining CCB. Failure to do so will produce indeterminate CCB execution status and ordering.
+
+         When the all-or-nothing flag is not specified, callers should check the value of length in ret1 to determine
+         how many CCBs from the array were successfully submitted. Any remaining CCBs can be resubmitted
+         without modifications.
+
+         The value of length in ret1 is also valid when the API call returns an error, and callers should always
+         check its value to determine which CCBs in the array were already processed. This will additionally
+         identify which CCB encountered the processing error, and was not submitted successfully.
+
+         If the queue info flag is used during submission, and at least one CCB was successfully submitted, the
+         length value in ret1 will be a multi-field value defined as follows:
+          Bits          Field Description
+          [63:48]       DAX unit instance identifier
+          [47:32]       DAX queue instance identifier
+          [31:16]       Reserved
+          [15:0]        Number of CCB bytes successfully submitted
+
+         The value of status data depends on the status value. See error status code descriptions for details.
+         The value is undefined for status values that do not specifically list a value for the status data.
+
+         The API has a reserved input and output register which will be used in subsequent minor versions of this
+         API function. Guest software implementations should treat that register as voltile across the function call
+         in order to maintain forward compatibility.
+
+36.3.1.1. Errors
+          EOK                       One or more CCBs have been accepted and enqueued in the virtual machine
+                                    and no errors were been encountered during submission. Some submitted
+                                    CCBs may not have been enqueued due to internal virtual machine limitations,
+                                    and may be resubmitted without changes.
+
+
+                                                       530
+                        Coprocessor services
+
+
+EWOULDBLOCK    An internal resource conflict within the virtual machine has prevented it from
+               being able to complete the CCB submissions sufficiently quickly, requiring
+               it to abandon processing before it was complete. Some CCBs may have been
+               successfully enqueued prior to the block, and all remaining CCBs may be
+               resubmitted without changes.
+EBADALIGN      CCB array is not on a 64-byte boundary, or the array length is not a multiple
+               of 64 bytes.
+ENORADDR       A real address used either for the CCB array, or within one of the submitted
+               CCBs, is not valid for the guest. Some CCBs may have been enqueued prior
+               to the error being detected.
+ENOMAP         A virtual address used either for the CCB array, or within one of the submitted
+               CCBs, could not be translated by the virtual machine using either the TLB
+               or TSB contents. The submission may be retried after adding the required
+               mapping, or by converting the virtual address into a real address. Due to the
+               shared nature of address translation resources, there is no theoretical limit on
+               the number of times the translation may fail, and it is recommended all guests
+               implement some real address based backup. The virtual address which failed
+               translation is returned as status data in ret2. Some CCBs may have been
+               enqueued prior to the error being detected.
+EINVAL         The virtual machine detected an invalid CCB during submission, or invalid
+               input arguments, such as bad flag values. Note that not all invalid CCB values
+               will be detected during submission, and some may be reported as errors in the
+               completion area instead. Some CCBs may have been enqueued prior to the
+               error being detected. This error may be returned if the CCB version is invalid.
+ETOOMANY       The request was submitted with the all-or-nothing flag set, and the array size is
+               greater than the virtual machine can support in a single request. The maximum
+               supported size for the current virtual machine can be queried by submitting a
+               request with a zero length array, as described above.
+ENOACCESS      The guest does not have permission to submit CCBs, or an address used in a
+               CCBs lacks sufficient permissions to perform the required operation (no write
+               permission on the destination buffer address, for example). A virtual address
+               which fails permission checking is returned as status data in ret2. Some
+               CCBs may have been enqueued prior to the error being detected.
+EUNAVAILABLE   The requested CCB operation could not be performed at this time. The
+               restricted operation availability may apply only to the first unsuccessfully
+               submitted CCB, or may apply to a larger scope. The status should not be
+               interpreted as permanent, and the guest should attempt to submit CCBs in
+               the future which had previously been unable to be performed. The status
+               data provides additional information about scope of the retricted availability
+               as follows:
+               Value       Description
+               0           Processing for the exact CCB instance submitted was unavailable,
+                           and it is recommended the guest emulate the operation. The
+                           guest should continue to submit all other CCBs, and assume no
+                           restrictions beyond this exact CCB instance.
+               1           Processing is unavailable for all CCBs using the requested opcode,
+                           and it is recommended the guest emulate the operation. The
+                           guest should continue to submit all other CCBs that use different
+                           opcodes, but can expect continued rejections of CCBs using the
+                           same opcode in the near future.
+
+
+                                 531
+                                              Coprocessor services
+
+
+                                      Value     Description
+                                      2         Processing is unavailable for all CCBs using the requested CCB
+                                                version, and it is recommended the guest emulate the operation.
+                                                The guest should continue to submit all other CCBs that use
+                                                different CCB versions, but can expect continued rejections of
+                                                CCBs using the same CCB version in the near future.
+                                      3         Processing is unavailable for all CCBs on the submitting vcpu,
+                                                and it is recommended the guest emulate the operation or resubmit
+                                                the CCB on a different vcpu. The guest should continue to submit
+                                                CCBs on all other vcpus but can expect continued rejections of all
+                                                CCBs on this vcpu in the near future.
+                                      4         Processing is unavailable for all CCBs, and it is recommended
+                                                the guest emulate the operation. The guest should expect all CCB
+                                                submissions to be similarly rejected in the near future.
+
+
+36.3.2. ccb_info
+
+        trap#               FAST_TRAP
+        function#           CCB_INFO
+        arg0                address
+        ret0                status
+        ret1                CCB state
+        ret2                position
+        ret3                dax
+        ret4                queue
+
+       Requests status information on a previously submitted CCB. The previously submitted CCB is identified
+       by the 64-byte aligned real address of the CCBs completion area.
+
+       A CCB can be in one of 4 states:
+
+
+        State                     Value       Description
+        COMPLETED                 0           The CCB has been fetched and executed, and is no longer active in
+                                              the virtual machine.
+        ENQUEUED                  1           The requested CCB is current in a queue awaiting execution.
+        INPROGRESS                2           The CCB has been fetched and is currently being executed. It may still
+                                              be possible to stop the execution using the ccb_kill hypercall.
+        NOTFOUND                  3           The CCB could not be located in the virtual machine, and does not
+                                              appear to have been executed. This may occur if the CCB was lost
+                                              due to a hardware error, or the CCB may not have been successfully
+                                              submitted to the virtual machine in the first place.
+
+               Implementation note
+               Some platforms may not be able to report CCBs that are currently being processed, and therefore
+               guest software should invoke the ccb_kill hypercall prior to assuming the request CCB will never
+               be executed because it was in the NOTFOUND state.
+
+
+                                                       532
+                                             Coprocessor services
+
+
+         The position return value is only valid when the state is ENQUEUED. The value returned is the number
+         of other CCBs ahead of the requested CCB, to provide a relative estimate of when the CCB may execute.
+
+         The dax return value is only valid when the state is ENQUEUED. The value returned is the DAX unit
+         instance indentifier for the DAX unit processing the queue where the requested CCB is located. The value
+         matches the value that would have been, or was, returned by ccb_submit using the queue info flag.
+
+         The queue return value is only valid when the state is ENQUEUED. The value returned is the DAX
+         queue instance indentifier for the DAX unit processing the queue where the requested CCB is located. The
+         value matches the value that would have been, or was, returned by ccb_submit using the queue info flag.
+
+36.3.2.1. Errors
+
+          EOK                       The request was proccessed and the CCB state is valid.
+          EBADALIGN                 address is not on a 64-byte aligned.
+          ENORADDR                  The real address provided for address is not valid.
+          EINVAL                    The CCB completion area contents are not valid.
+          EWOULDBLOCK               Internal resource contraints prevented the CCB state from being queried at this
+                                    time. The guest should retry the request.
+          ENOACCESS                 The guest does not have permission to access the coprocessor virtual device
+                                    functionality.
+
+36.3.3. ccb_kill
+
+          trap#           FAST_TRAP
+          function#       CCB_KILL
+          arg0            address
+          ret0            status
+          ret1            result
+
+         Request to stop execution of a previously submitted CCB. The previously submitted CCB is identified by
+         the 64-byte aligned real address of the CCBs completion area.
+
+         The kill attempt can produce one of several values in the result return value, reflecting the CCB state
+         and actions taken by the Hypervisor:
+
+          Result                Value       Description
+          COMPLETED             0           The CCB has been fetched and executed, and is no longer active in
+                                            the virtual machine. It could not be killed and no action was taken.
+          DEQUEUED              1           The requested CCB was still enqueued when the kill request was
+                                            submitted, and has been removed from the queue. Since the CCB
+                                            never began execution, no memory modifications were produced by
+                                            it, and the completion area will never be updated. The same CCB may
+                                            be submitted again, if desired, with no modifications required.
+          KILLED                2           The CCB had been fetched and was being executed when the kill
+                                            request was submitted. The CCB execution was stopped, and the CCB
+                                            is no longer active in the virtual machine. The CCB completion area
+                                            will reflect the killed status, with the subsequent implications that
+                                            partial results may have been produced. Partial results may include full
+
+
+                                                      533
+                                              Coprocessor services
+
+
+          Result                 Value       Description
+                                             command execution if the command was stopped just prior to writing
+                                             to the completion area.
+          NOTFOUND               3           The CCB could not be located in the virtual machine, and does not
+                                             appear to have been executed. This may occur if the CCB was lost
+                                             due to a hardware error, or the CCB may not have been successfully
+                                             submitted to the virtual machine in the first place. CCBs in the state
+                                             are guaranteed to never execute in the future unless resubmitted.
+
+36.3.3.1. Interactions with Pipelined CCBs
+
+         If the pipeline target CCB is killed but the pipeline source CCB was skipped, the completion area of the
+         target CCB may contain status (4,0) "Command was skipped" instead of (3,7) "Command was killed".
+
+         If the pipeline source CCB is killed, the pipeline target CCB's completion status may read (1,0) "Success".
+         This does not mean the target CCB was processed; since the source CCB was killed, there was no
+         meaningful output on which the target CCB could operate.
+
+36.3.3.2. Errors
+
+          EOK                        The request was proccessed and the result is valid.
+          EBADALIGN                  address is not on a 64-byte aligned.
+          ENORADDR                   The real address provided for address is not valid.
+          EINVAL                     The CCB completion area contents are not valid.
+          EWOULDBLOCK                Internal resource contraints prevented the CCB from being killed at this time.
+                                     The guest should retry the request.
+          ENOACCESS                  The guest does not have permission to access the coprocessor virtual device
+                                     functionality.
+
+36.3.4. dax_info
+          trap#            FAST_TRAP
+          function#        DAX_INFO
+          ret0             status
+          ret1             Number of enabled DAX units
+          ret2             Number of disabled DAX units
+
+         Returns the number of DAX units that are enabled for the calling guest to submit CCBs. The number of
+         DAX units that are disabled for the calling guest are also returned. A disabled DAX unit would have been
+         available for CCB submission to the calling guest had it not been offlined.
+
+36.3.4.1. Errors
+
+          EOK                        The request was proccessed and the number of enabled/disabled DAX units
+                                     are valid.
+
+
+
+
+                                                       534
+
diff --git a/Documentation/sparc/oradax/oracle-dax.txt b/Documentation/sparc/oradax/oracle-dax.txt
new file mode 100644
index 000000000000..9d53ac93286f
--- /dev/null
+++ b/Documentation/sparc/oradax/oracle-dax.txt
@@ -0,0 +1,429 @@
+Oracle Data Analytics Accelerator (DAX)
+---------------------------------------
+
+DAX is a coprocessor which resides on the SPARC M7 (DAX1) and M8
+(DAX2) processor chips, and has direct access to the CPU's L3 caches
+as well as physical memory. It can perform several operations on data
+streams with various input and output formats.  A driver provides a
+transport mechanism and has limited knowledge of the various opcodes
+and data formats. A user space library provides high level services
+and translates these into low level commands which are then passed
+into the driver and subsequently the Hypervisor and the coprocessor.
+The library is the recommended way for applications to use the
+coprocessor, and the driver interface is not intended for general use.
+This document describes the general flow of the driver, its
+structures, and its programmatic interface. It also provides example
+code sufficient to write user or kernel applications that use DAX
+functionality.
+
+The user library is open source and available at:
+    https://oss.oracle.com/git/gitweb.cgi?p=libdax.git
+
+The Hypervisor interface to the coprocessor is described in detail in
+the accompanying document, dax-hv-api.txt, which is a plain text
+excerpt of the (Oracle internal) "UltraSPARC Virtual Machine
+Specification" version 3.0.20+15, dated 2017-09-25.
+
+
+High Level Overview
+-------------------
+
+A coprocessor request is described by a Command Control Block
+(CCB). The CCB contains an opcode and various parameters. The opcode
+specifies what operation is to be done, and the parameters specify
+options, flags, sizes, and addresses.  The CCB (or an array of CCBs)
+is passed to the Hypervisor, which handles queueing and scheduling of
+requests to the available coprocessor execution units. A status code
+returned indicates if the request was submitted successfully or if
+there was an error.  One of the addresses given in each CCB is a
+pointer to a "completion area", which is a 128 byte memory block that
+is written by the coprocessor to provide execution status. No
+interrupt is generated upon completion; the completion area must be
+polled by software to find out when a transaction has finished, but
+the M7 and later processors provide a mechanism to pause the virtual
+processor until the completion status has been updated by the
+coprocessor. This is done using the monitored load and mwait
+instructions, which are described in more detail later.  The DAX
+coprocessor was designed so that after a request is submitted, the
+kernel is no longer involved in the processing of it.  The polling is
+done at the user level, which results in almost zero latency between
+completion of a request and resumption of execution of the requesting
+thread.
+
+
+Addressing Memory
+-----------------
+
+The kernel does not have access to physical memory in the Sun4v
+architecture, as there is an additional level of memory virtualization
+present. This intermediate level is called "real" memory, and the
+kernel treats this as if it were physical.  The Hypervisor handles the
+translations between real memory and physical so that each logical
+domain (LDOM) can have a partition of physical memory that is isolated
+from that of other LDOMs.  When the kernel sets up a virtual mapping,
+it specifies a virtual address and the real address to which it should
+be mapped.
+
+The DAX coprocessor can only operate on physical memory, so before a
+request can be fed to the coprocessor, all the addresses in a CCB must
+be converted into physical addresses. The kernel cannot do this since
+it has no visibility into physical addresses. So a CCB may contain
+either the virtual or real addresses of the buffers or a combination
+of them. An "address type" field is available for each address that
+may be given in the CCB. In all cases, the Hypervisor will translate
+all the addresses to physical before dispatching to hardware. Address
+translations are performed using the context of the process initiating
+the request.
+
+
+The Driver API
+--------------
+
+An application makes requests to the driver via the write() system
+call, and gets results (if any) via read(). The completion areas are
+made accessible via mmap(), and are read-only for the application.
+
+The request may either be an immediate command or an array of CCBs to
+be submitted to the hardware.
+
+Each open instance of the device is exclusive to the thread that
+opened it, and must be used by that thread for all subsequent
+operations. The driver open function creates a new context for the
+thread and initializes it for use.  This context contains pointers and
+values used internally by the driver to keep track of submitted
+requests. The completion area buffer is also allocated, and this is
+large enough to contain the completion areas for many concurrent
+requests.  When the device is closed, any outstanding transactions are
+flushed and the context is cleaned up.
+
+On a DAX1 system (M7), the device will be called "oradax1", while on a
+DAX2 system (M8) it will be "oradax2". If an application requires one
+or the other, it should simply attempt to open the appropriate
+device. Only one of the devices will exist on any given system, so the
+name can be used to determine what the platform supports.
+
+The immediate commands are CCB_DEQUEUE, CCB_KILL, and CCB_INFO. For
+all of these, success is indicated by a return value from write()
+equal to the number of bytes given in the call. Otherwise -1 is
+returned and errno is set.
+
+CCB_DEQUEUE
+
+Tells the driver to clean up resources associated with past
+requests. Since no interrupt is generated upon the completion of a
+request, the driver must be told when it may reclaim resources.  No
+further status information is returned, so the user should not
+subsequently call read().
+
+CCB_KILL
+
+Kills a CCB during execution. The CCB is guaranteed to not continue
+executing once this call returns successfully. On success, read() must
+be called to retrieve the result of the action.
+
+CCB_INFO
+
+Retrieves information about a currently executing CCB. Note that some
+Hypervisors might return 'notfound' when the CCB is in 'inprogress'
+state. To ensure a CCB in the 'notfound' state will never be executed,
+CCB_KILL must be invoked on that CCB. Upon success, read() must be
+called to retrieve the details of the action.
+
+Submission of an array of CCBs for execution
+
+A write() whose length is a multiple of the CCB size is treated as a
+submit operation. The file offset is treated as the index of the
+completion area to use, and may be set via lseek() or using the
+pwrite() system call. If -1 is returned then errno is set to indicate
+the error. Otherwise, the return value is the length of the array that
+was actually accepted by the coprocessor. If the accepted length is
+equal to the requested length, then the submission was completely
+successful and there is no further status needed; hence, the user
+should not subsequently call read(). Partial acceptance of the CCB
+array is indicated by a return value less than the requested length,
+and read() must be called to retrieve further status information.  The
+status will reflect the error caused by the first CCB that was not
+accepted, and status_data will provide additional data in some cases.
+
+MMAP
+
+The mmap() function provides access to the completion area allocated
+in the driver.  Note that the completion area is not writeable by the
+user process, and the mmap call must not specify PROT_WRITE.
+
+
+Completion of a Request
+-----------------------
+
+The first byte in each completion area is the command status which is
+updated by the coprocessor hardware. Software may take advantage of
+new M7/M8 processor capabilities to efficiently poll this status byte.
+First, a "monitored load" is achieved via a Load from Alternate Space
+(ldxa, lduba, etc.) with ASI 0x84 (ASI_MONITOR_PRIMARY).  Second, a
+"monitored wait" is achieved via the mwait instruction (a write to
+%asr28). This instruction is like pause in that it suspends execution
+of the virtual processor for the given number of nanoseconds, but in
+addition will terminate early when one of several events occur. If the
+block of data containing the monitored location is modified, then the
+mwait terminates. This causes software to resume execution immediately
+(without a context switch or kernel to user transition) after a
+transaction completes. Thus the latency between transaction completion
+and resumption of execution may be just a few nanoseconds.
+
+
+Application Life Cycle of a DAX Submission
+------------------------------------------
+
+ - open dax device
+ - call mmap() to get the completion area address
+ - allocate a CCB and fill in the opcode, flags, parameters, addresses, etc.
+ - submit CCB via write() or pwrite()
+ - go into a loop executing monitored load + monitored wait and
+   terminate when the command status indicates the request is complete
+   (CCB_KILL or CCB_INFO may be used any time as necessary)
+ - perform a CCB_DEQUEUE
+ - call munmap() for completion area
+ - close the dax device
+
+
+Memory Constraints
+------------------
+
+The DAX hardware operates only on physical addresses. Therefore, it is
+not aware of virtual memory mappings and the discontiguities that may
+exist in the physical memory that a virtual buffer maps to. There is
+no I/O TLB or any scatter/gather mechanism. All buffers, whether input
+or output, must reside in a physically contiguous region of memory.
+
+The Hypervisor translates all addresses within a CCB to physical
+before handing off the CCB to DAX. The Hypervisor determines the
+virtual page size for each virtual address given, and uses this to
+program a size limit for each address. This prevents the coprocessor
+from reading or writing beyond the bound of the virtual page, even
+though it is accessing physical memory directly. A simpler way of
+saying this is that a DAX operation will never "cross" a virtual page
+boundary. If an 8k virtual page is used, then the data is strictly
+limited to 8k. If a user's buffer is larger than 8k, then a larger
+page size must be used, or the transaction size will be truncated to
+8k.
+
+Huge pages. A user may allocate huge pages using standard interfaces.
+Memory buffers residing on huge pages may be used to achieve much
+larger DAX transaction sizes, but the rules must still be followed,
+and no transaction will cross a page boundary, even a huge page.  A
+major caveat is that Linux on Sparc presents 8Mb as one of the huge
+page sizes. Sparc does not actually provide a 8Mb hardware page size,
+and this size is synthesized by pasting together two 4Mb pages. The
+reasons for this are historical, and it creates an issue because only
+half of this 8Mb page can actually be used for any given buffer in a
+DAX request, and it must be either the first half or the second half;
+it cannot be a 4Mb chunk in the middle, since that crosses a
+(hardware) page boundary. Note that this entire issue may be hidden by
+higher level libraries.
+
+
+CCB Structure
+-------------
+A CCB is an array of 8 64-bit words. Several of these words provide
+command opcodes, parameters, flags, etc., and the rest are addresses
+for the completion area, output buffer, and various inputs:
+
+   struct ccb {
+       u64   control;
+       u64   completion;
+       u64   input0;
+       u64   access;
+       u64   input1;
+       u64   op_data;
+       u64   output;
+       u64   table;
+   };
+
+See libdax/common/sys/dax1/dax1_ccb.h for a detailed description of
+each of these fields, and see dax-hv-api.txt for a complete description
+of the Hypervisor API available to the guest OS (ie, Linux kernel).
+
+The first word (control) is examined by the driver for the following:
+ - CCB version, which must be consistent with hardware version
+ - Opcode, which must be one of the documented allowable commands
+ - Address types, which must be set to "virtual" for all the addresses
+   given by the user, thereby ensuring that the application can
+   only access memory that it owns
+
+
+Example Code
+------------
+
+The DAX is accessible to both user and kernel code.  The kernel code
+can make hypercalls directly while the user code must use wrappers
+provided by the driver. The setup of the CCB is nearly identical for
+both; the only difference is in preparation of the completion area. An
+example of user code is given now, with kernel code afterwards.
+
+In order to program using the driver API, the file
+arch/sparc/include/uapi/asm/oradax.h must be included.
+
+First, the proper device must be opened. For M7 it will be
+/dev/oradax1 and for M8 it will be /dev/oradax2. The simplest
+procedure is to attempt to open both, as only one will succeed:
+
+	fd = open("/dev/oradax1", O_RDWR);
+	if (fd < 0)
+		fd = open("/dev/oradax2", O_RDWR);
+	if (fd < 0)
+	       /* No DAX found */
+
+Next, the completion area must be mapped:
+
+      completion_area = mmap(NULL, DAX_MMAP_LEN, PROT_READ, MAP_SHARED, fd, 0);
+
+All input and output buffers must be fully contained in one hardware
+page, since as explained above, the DAX is strictly constrained by
+virtual page boundaries.  In addition, the output buffer must be
+64-byte aligned and its size must be a multiple of 64 bytes because
+the coprocessor writes in units of cache lines.
+
+This example demonstrates the DAX Scan command, which takes as input a
+vector and a match value, and produces a bitmap as the output. For
+each input element that matches the value, the corresponding bit is
+set in the output.
+
+In this example, the input vector consists of a series of single bits,
+and the match value is 0. So each 0 bit in the input will produce a 1
+in the output, and vice versa, which produces an output bitmap which
+is the input bitmap inverted.
+
+For details of all the parameters and bits used in this CCB, please
+refer to section 36.2.1.3 of the DAX Hypervisor API document, which
+describes the Scan command in detail.
+
+	ccb->control =       /* Table 36.1, CCB Header Format */
+		  (2L << 48)     /* command = Scan Value */
+		| (3L << 40)     /* output address type = primary virtual */
+		| (3L << 34)     /* primary input address type = primary virtual */
+		             /* Section 36.2.1, Query CCB Command Formats */
+		| (1 << 28)     /* 36.2.1.1.1 primary input format = fixed width bit packed */
+		| (0 << 23)     /* 36.2.1.1.2 primary input element size = 0 (1 bit) */
+		| (8 << 10)     /* 36.2.1.1.6 output format = bit vector */
+		| (0 <<  5)	/* 36.2.1.3 First scan criteria size = 0 (1 byte) */
+		| (31 << 0);	/* 36.2.1.3 Disable second scan criteria */
+
+	ccb->completion = 0;    /* Completion area address, to be filled in by driver */
+
+	ccb->input0 = (unsigned long) input; /* primary input address */
+
+	ccb->access =       /* Section 36.2.1.2, Data Access Control */
+		  (2 << 24)    /* Primary input length format = bits */
+		| (nbits - 1); /* number of bits in primary input stream, minus 1 */
+
+	ccb->input1 = 0;       /* secondary input address, unused */
+
+	ccb->op_data = 0;      /* scan criteria (value to be matched) */
+
+	ccb->output = (unsigned long) output;	/* output address */
+
+	ccb->table = 0;	       /* table address, unused */
+
+The CCB submission is a write() or pwrite() system call to the
+driver. If the call fails, then a read() must be used to retrieve the
+status:
+
+	if (pwrite(fd, ccb, 64, 0) != 64) {
+		struct ccb_exec_result status;
+		read(fd, &status, sizeof(status));
+		/* bail out */
+	}
+
+After a successful submission of the CCB, the completion area may be
+polled to determine when the DAX is finished. Detailed information on
+the contents of the completion area can be found in section 36.2.2 of
+the DAX HV API document.
+
+	while (1) {
+		/* Monitored Load */
+		__asm__ __volatile__("lduba [%1] 0x84, %0\n"
+				     : "=r" (status)
+				     : "r"  (completion_area));
+
+		if (status)	     /* 0 indicates command in progress */
+			break;
+
+		/* MWAIT */
+		__asm__ __volatile__("wr %%g0, 1000, %%asr28\n" ::);    /* 1000 ns */
+	}
+
+A completion area status of 1 indicates successful completion of the
+CCB and validity of the output bitmap, which may be used immediately.
+All other non-zero values indicate error conditions which are
+described in section 36.2.2.
+
+	if (completion_area[0] != 1) {	/* section 36.2.2, 1 = command ran and succeeded */
+		/* completion_area[0] contains the completion status */
+		/* completion_area[1] contains an error code, see 36.2.2 */
+	}
+
+After the completion area has been processed, the driver must be
+notified that it can release any resources associated with the
+request. This is done via the dequeue operation:
+
+	struct dax_command cmd;
+	cmd.command = CCB_DEQUEUE;
+	if (write(fd, &cmd, sizeof(cmd)) != sizeof(cmd)) {
+		/* bail out */
+	}
+
+Finally, normal program cleanup should be done, i.e., unmapping
+completion area, closing the dax device, freeing memory etc.
+
+[Kernel example]
+
+The only difference in using the DAX in kernel code is the treatment
+of the completion area. Unlike user applications which mmap the
+completion area allocated by the driver, kernel code must allocate its
+own memory to use for the completion area, and this address and its
+type must be given in the CCB:
+
+	ccb->control |=      /* Table 36.1, CCB Header Format */
+	        (3L << 32);     /* completion area address type = primary virtual */
+
+	ccb->completion = (unsigned long) completion_area;   /* Completion area address */
+
+The dax submit hypercall is made directly. The flags used in the
+ccb_submit call are documented in the DAX HV API in section 36.3.1.
+
+#include <asm/hypervisor.h>
+
+	hv_rv = sun4v_ccb_submit((unsigned long)ccb, 64,
+				 HV_CCB_QUERY_CMD |
+				 HV_CCB_ARG0_PRIVILEGED | HV_CCB_ARG0_TYPE_PRIMARY |
+				 HV_CCB_VA_PRIVILEGED,
+				 0, &bytes_accepted, &status_data);
+
+	if (hv_rv != HV_EOK) {
+		/* hv_rv is an error code, status_data contains */
+		/* potential additional status, see 36.3.1.1 */
+	}
+
+After the submission, the completion area polling code is identical to
+that in user land:
+
+	while (1) {
+		/* Monitored Load */
+		__asm__ __volatile__("lduba [%1] 0x84, %0\n"
+				     : "=r" (status)
+				     : "r"  (completion_area));
+
+		if (status)	     /* 0 indicates command in progress */
+			break;
+
+		/* MWAIT */
+		__asm__ __volatile__("wr %%g0, 1000, %%asr28\n" ::);    /* 1000 ns */
+	}
+
+	if (completion_area[0] != 1) {	/* section 36.2.2, 1 = command ran and succeeded */
+		/* completion_area[0] contains the completion status */
+		/* completion_area[1] contains an error code, see 36.2.2 */
+	}
+
+The output bitmap is ready for consumption immediately after the
+completion status indicates success.
diff --git a/Documentation/sphinx/kfigure.py b/Documentation/sphinx/kfigure.py
index cef4ad19624c..b97228d2cc0e 100644
--- a/Documentation/sphinx/kfigure.py
+++ b/Documentation/sphinx/kfigure.py
@@ -81,7 +81,7 @@ __version__  = '1.0.0'
 # -------------
 
 def which(cmd):
-    """Searches the ``cmd`` in the ``PATH`` enviroment.
+    """Searches the ``cmd`` in the ``PATH`` environment.
 
     This *which* searches the PATH for executable ``cmd`` . First match is
     returned, if nothing is found, ``None` is returned.
@@ -419,7 +419,7 @@ def visit_kernel_render(self, node):
 
     tmp_ext = RENDER_MARKUP_EXT.get(srclang, None)
     if tmp_ext is None:
-        app.warn('kernel-render: "%s" unknow / include raw.' % (srclang))
+        app.warn('kernel-render: "%s" unknown / include raw.' % (srclang))
         return
 
     if not dot_cmd and tmp_ext == '.dot':
@@ -482,7 +482,7 @@ class KernelRender(Figure):
         srclang = self.arguments[0].strip()
         if srclang not in RENDER_MARKUP_EXT.keys():
             return [self.state_machine.reporter.warning(
-                'Unknow source language "%s", use one of: %s.' % (
+                'Unknown source language "%s", use one of: %s.' % (
                     srclang, ",".join(RENDER_MARKUP_EXT.keys())),
                 line=self.lineno)]
 
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 694968c7523c..412314eebda6 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -34,6 +34,7 @@ show up in /proc/sys/kernel:
 - hostname
 - hotplug
 - hardlockup_all_cpu_backtrace
+- hardlockup_panic
 - hung_task_panic
 - hung_task_check_count
 - hung_task_timeout_secs
@@ -313,6 +314,19 @@ will be initiated.
 1: on detection capture more debug information.
 ==============================================================
 
+hardlockup_panic:
+
+This parameter can be used to control whether the kernel panics
+when a hard lockup is detected.
+
+   0 - don't panic on hard lockup
+   1 - panic on hard lockup
+
+See Documentation/lockup-watchdogs.txt for more information.  This can
+also be set using the nmi_watchdog kernel parameter.
+
+==============================================================
+
 hotplug:
 
 Path for the hotplug policy agent.
@@ -377,7 +391,8 @@ kptr_restrict:
 This toggle indicates whether restrictions are placed on
 exposing kernel addresses via /proc and other interfaces.
 
-When kptr_restrict is set to (0), the default, there are no restrictions.
+When kptr_restrict is set to 0 (the default) the address is hashed before
+printing. (This is the equivalent to %p.)
 
 When kptr_restrict is set to (1), kernel pointers printed using the %pK
 format specifier will be replaced with 0's unless the user has CAP_SYSLOG
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index b67044a2575f..35c62f522754 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -95,7 +95,9 @@ dev_weight
 --------------
 
 The maximum number of packets that kernel can handle on a NAPI interrupt,
-it's a Per-CPU variable.
+it's a Per-CPU variable. For drivers that support LRO or GRO_HW, a hardware
+aggregated packet is counted as one packet in this context.
+
 Default: 64
 
 dev_weight_rx_bias
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index b920423f88cb..ff234d229cbb 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -30,7 +30,6 @@ Currently, these files are in /proc/sys/vm:
 - dirty_writeback_centisecs
 - drop_caches
 - extfrag_threshold
-- hugepages_treat_as_movable
 - hugetlb_shm_group
 - laptop_mode
 - legacy_va_layout
@@ -158,10 +157,6 @@ Note: the minimum value allowed for dirty_bytes is two pages (in bytes); any
 value lower than this limit will be ignored and the old configuration will be
 retained.
 
-Note: the value of dirty_bytes also must be set greater than
-dirty_background_bytes or the amount of memory corresponding to
-dirty_background_ratio.
-
 ==============================================================
 
 dirty_expire_centisecs
@@ -181,9 +176,6 @@ generating disk writes will itself start writing out dirty data.
 
 The total available memory is not equal to total system memory.
 
-Note: dirty_ratio must be set greater than dirty_background_ratio or
-ratio corresponding to dirty_background_bytes.
-
 ==============================================================
 
 dirty_writeback_centisecs
@@ -268,30 +260,6 @@ any throttling.
 
 ==============================================================
 
-hugepages_treat_as_movable
-
-This parameter controls whether we can allocate hugepages from ZONE_MOVABLE
-or not. If set to non-zero, hugepages can be allocated from ZONE_MOVABLE.
-ZONE_MOVABLE is created when kernel boot parameter kernelcore= is specified,
-so this parameter has no effect if used without kernelcore=.
-
-Hugepage migration is now available in some situations which depend on the
-architecture and/or the hugepage size. If a hugepage supports migration,
-allocation from ZONE_MOVABLE is always enabled for the hugepage regardless
-of the value of this parameter.
-IOW, this parameter affects only non-migratable hugepages.
-
-Assuming that hugepages are not migratable in your system, one usecase of
-this parameter is that users can make hugepage pool more extensible by
-enabling the allocation from ZONE_MOVABLE. This is because on ZONE_MOVABLE
-page reclaim/migration/compaction work more and you can get contiguous
-memory more likely. Note that using ZONE_MOVABLE for non-migratable
-hugepages can do harm to other features like memory hotremove (because
-memory hotremove expects that memory blocks on ZONE_MOVABLE are always
-removable,) so it's a trade-off responsible for the users.
-
-==============================================================
-
 hugetlb_shm_group
 
 hugetlb_shm_group contains group id that is allowed to create SysV
diff --git a/Documentation/thermal/cpu-cooling-api.txt b/Documentation/thermal/cpu-cooling-api.txt
index 71653584cd03..7df567eaea1a 100644
--- a/Documentation/thermal/cpu-cooling-api.txt
+++ b/Documentation/thermal/cpu-cooling-api.txt
@@ -26,39 +26,16 @@ the user. The registration APIs returns the cooling device pointer.
    clip_cpus: cpumask of cpus where the frequency constraints will happen.
 
 1.1.2 struct thermal_cooling_device *of_cpufreq_cooling_register(
-	struct device_node *np, const struct cpumask *clip_cpus)
+					struct cpufreq_policy *policy)
 
     This interface function registers the cpufreq cooling device with
     the name "thermal-cpufreq-%x" linking it with a device tree node, in
     order to bind it via the thermal DT code. This api can support multiple
     instances of cpufreq cooling devices.
 
-    np: pointer to the cooling device device tree node
-    clip_cpus: cpumask of cpus where the frequency constraints will happen.
+    policy: CPUFreq policy.
 
-1.1.3 struct thermal_cooling_device *cpufreq_power_cooling_register(
-    const struct cpumask *clip_cpus, u32 capacitance,
-    get_static_t plat_static_func)
-
-Similar to cpufreq_cooling_register, this function registers a cpufreq
-cooling device.  Using this function, the cooling device will
-implement the power extensions by using a simple cpu power model.  The
-cpus must have registered their OPPs using the OPP library.
-
-The additional parameters are needed for the power model (See 2. Power
-models).  "capacitance" is the dynamic power coefficient (See 2.1
-Dynamic power).  "plat_static_func" is a function to calculate the
-static power consumed by these cpus (See 2.2 Static power).
-
-1.1.4 struct thermal_cooling_device *of_cpufreq_power_cooling_register(
-    struct device_node *np, const struct cpumask *clip_cpus, u32 capacitance,
-    get_static_t plat_static_func)
-
-Similar to cpufreq_power_cooling_register, this function register a
-cpufreq cooling device with power extensions using the device tree
-information supplied by the np parameter.
-
-1.1.5 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
+1.1.3 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 
     This interface function unregisters the "thermal-cpufreq-%x" cooling device.
 
@@ -67,20 +44,14 @@ information supplied by the np parameter.
 2. Power models
 
 The power API registration functions provide a simple power model for
-CPUs.  The current power is calculated as dynamic + (optionally)
-static power.  This power model requires that the operating-points of
+CPUs.  The current power is calculated as dynamic power (static power isn't
+supported currently).  This power model requires that the operating-points of
 the CPUs are registered using the kernel's opp library and the
 `cpufreq_frequency_table` is assigned to the `struct device` of the
 cpu.  If you are using CONFIG_CPUFREQ_DT then the
 `cpufreq_frequency_table` should already be assigned to the cpu
 device.
 
-The `plat_static_func` parameter of `cpufreq_power_cooling_register()`
-and `of_cpufreq_power_cooling_register()` is optional.  If you don't
-provide it, only dynamic power will be considered.
-
-2.1 Dynamic power
-
 The dynamic power consumption of a processor depends on many factors.
 For a given processor implementation the primary factors are:
 
@@ -119,79 +90,3 @@ mW/MHz/uVolt^2.  Typical values for mobile CPUs might lie in range
 from 100 to 500.  For reference, the approximate values for the SoC in
 ARM's Juno Development Platform are 530 for the Cortex-A57 cluster and
 140 for the Cortex-A53 cluster.
-
-
-2.2 Static power
-
-Static leakage power consumption depends on a number of factors.  For a
-given circuit implementation the primary factors are:
-
-- Time the circuit spends in each 'power state'
-- Temperature
-- Operating voltage
-- Process grade
-
-The time the circuit spends in each 'power state' for a given
-evaluation period at first order means OFF or ON.  However,
-'retention' states can also be supported that reduce power during
-inactive periods without loss of context.
-
-Note: The visibility of state entries to the OS can vary, according to
-platform specifics, and this can then impact the accuracy of a model
-based on OS state information alone.  It might be possible in some
-cases to extract more accurate information from system resources.
-
-The temperature, operating voltage and process 'grade' (slow to fast)
-of the circuit are all significant factors in static leakage power
-consumption.  All of these have complex relationships to static power.
-
-Circuit implementation specific factors include the chosen silicon
-process as well as the type, number and size of transistors in both
-the logic gates and any RAM elements included.
-
-The static power consumption modelling must take into account the
-power managed regions that are implemented.  Taking the example of an
-ARM processor cluster, the modelling would take into account whether
-each CPU can be powered OFF separately or if only a single power
-region is implemented for the complete cluster.
-
-In one view, there are others, a static power consumption model can
-then start from a set of reference values for each power managed
-region (e.g. CPU, Cluster/L2) in each state (e.g. ON, OFF) at an
-arbitrary process grade, voltage and temperature point.  These values
-are then scaled for all of the following: the time in each state, the
-process grade, the current temperature and the operating voltage.
-However, since both implementation specific and complex relationships
-dominate the estimate, the appropriate interface to the model from the
-cpu cooling device is to provide a function callback that calculates
-the static power in this platform.  When registering the cpu cooling
-device pass a function pointer that follows the `get_static_t`
-prototype:
-
-    int plat_get_static(cpumask_t *cpumask, int interval,
-                        unsigned long voltage, u32 &power);
-
-`cpumask` is the cpumask of the cpus involved in the calculation.
-`voltage` is the voltage at which they are operating.  The function
-should calculate the average static power for the last `interval`
-milliseconds.  It returns 0 on success, -E* on error.  If it
-succeeds, it should store the static power in `power`.  Reading the
-temperature of the cpus described by `cpumask` is left for
-plat_get_static() to do as the platform knows best which thermal
-sensor is closest to the cpu.
-
-If `plat_static_func` is NULL, static power is considered to be
-negligible for this platform and only dynamic power is considered.
-
-The platform specific callback can then use any combination of tables
-and/or equations to permute the estimated value.  Process grade
-information is not passed to the model since access to such data, from
-on-chip measurement capability or manufacture time data, is platform
-specific.
-
-Note: the significance of static power for CPUs in comparison to
-dynamic power is highly dependent on implementation.  Given the
-potential complexity in implementation, the importance and accuracy of
-its inclusion when using cpu cooling devices should be assessed on a
-case by case basis.
-
diff --git a/Documentation/trace/ftrace-uses.rst b/Documentation/trace/ftrace-uses.rst
index 8494a801d341..3aed560a12ee 100644
--- a/Documentation/trace/ftrace-uses.rst
+++ b/Documentation/trace/ftrace-uses.rst
@@ -42,9 +42,9 @@ as well as what protections the callback will perform and not require
 ftrace to handle.
 
 There is only one field that is needed to be set when registering
-an ftrace_ops with ftrace::
+an ftrace_ops with ftrace:
 
-.. code-block: c
+.. code-block:: c
 
  struct ftrace_ops ops = {
        .func			= my_callback_func,
@@ -81,12 +81,12 @@ may take some time to finish.
 The callback function
 =====================
 
-The prototype of the callback function is as follows (as of v4.14)::
+The prototype of the callback function is as follows (as of v4.14):
 
-.. code-block: c
+.. code-block:: c
 
- void callback_func(unsigned long ip, unsigned long parent_ip,
-		    struct ftrace_ops *op, struct pt_regs *regs);
+   void callback_func(unsigned long ip, unsigned long parent_ip,
+                      struct ftrace_ops *op, struct pt_regs *regs);
 
 @ip
 	 This is the instruction pointer of the function that is being traced.
@@ -176,10 +176,10 @@ Filtering which functions to trace
 If a callback is only to be called from specific functions, a filter must be
 set up. The filters are added by name, or ip if it is known.
 
-.. code-block: c
+.. code-block:: c
 
- int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
-		       int len, int reset);
+   int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
+                         int len, int reset);
 
 @ops
 	The ops to set the filter with
@@ -202,9 +202,9 @@ See Filter Commands in :file:`Documentation/trace/ftrace.txt`.
 
 To just trace the schedule function::
 
-.. code-block: c
+.. code-block:: c
 
- ret = ftrace_set_filter(&ops, "schedule", strlen("schedule"), 0);
+   ret = ftrace_set_filter(&ops, "schedule", strlen("schedule"), 0);
 
 To add more functions, call the ftrace_set_filter() more than once with the
 @reset parameter set to zero. To remove the current filter set and replace it
@@ -212,17 +212,17 @@ with new functions defined by @buf, have @reset be non-zero.
 
 To remove all the filtered functions and trace all functions::
 
-.. code-block: c
+.. code-block:: c
 
-  ret = ftrace_set_filter(&ops, NULL, 0, 1);
+   ret = ftrace_set_filter(&ops, NULL, 0, 1);
 
 
 Sometimes more than one function has the same name. To trace just a specific
 function in this case, ftrace_set_filter_ip() can be used.
 
-.. code-block: c
+.. code-block:: c
 
- ret = ftrace_set_filter_ip(&ops, ip, 0, 0);
+   ret = ftrace_set_filter_ip(&ops, ip, 0, 0);
 
 Although the ip must be the address where the call to fentry or mcount is
 located in the function. This function is used by perf and kprobes that
@@ -237,10 +237,10 @@ be called by any function.
 An empty "notrace" list means to allow all functions defined by the filter
 to be traced.
 
-.. code-block: c
+.. code-block:: c
 
-  int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
-			 int len, int reset);
+   int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
+                          int len, int reset);
 
 This takes the same parameters as ftrace_set_filter() but will add the
 functions it finds to not be traced. This is a separate list from the
@@ -251,7 +251,7 @@ that match @buf to it.
 
 Clearing the "notrace" list is the same as clearing the filter list
 
-.. code-block: c
+.. code-block:: c
 
   ret = ftrace_set_notrace(&ops, NULL, 0, 1);
 
@@ -264,29 +264,29 @@ If a filter is in place, and the @reset is non-zero, and @buf contains a
 matching glob to functions, the switch will happen during the time of
 the ftrace_set_filter() call. At no time will all functions call the callback.
 
-.. code-block: c
+.. code-block:: c
 
-	ftrace_set_filter(&ops, "schedule", strlen("schedule"), 1);
+   ftrace_set_filter(&ops, "schedule", strlen("schedule"), 1);
 
-	register_ftrace_function(&ops);
+   register_ftrace_function(&ops);
 
-	msleep(10);
+   msleep(10);
 
-	ftrace_set_filter(&ops, "try_to_wake_up", strlen("try_to_wake_up"), 1);
+   ftrace_set_filter(&ops, "try_to_wake_up", strlen("try_to_wake_up"), 1);
 
 is not the same as:
 
-.. code-block: c
+.. code-block:: c
 
-	ftrace_set_filter(&ops, "schedule", strlen("schedule"), 1);
+   ftrace_set_filter(&ops, "schedule", strlen("schedule"), 1);
 
-	register_ftrace_function(&ops);
+   register_ftrace_function(&ops);
 
-	msleep(10);
+   msleep(10);
 
-	ftrace_set_filter(&ops, NULL, 0, 1);
+   ftrace_set_filter(&ops, NULL, 0, 1);
 
-	ftrace_set_filter(&ops, "try_to_wake_up", strlen("try_to_wake_up"), 0);
+   ftrace_set_filter(&ops, "try_to_wake_up", strlen("try_to_wake_up"), 0);
 
 As the latter will have a short time where all functions will call
 the callback, between the time of the reset, and the time of the
diff --git a/Documentation/translations/zh_CN/filesystems/sysfs.txt b/Documentation/translations/zh_CN/filesystems/sysfs.txt
index 7d3b05edb8ce..452271dda141 100644
--- a/Documentation/translations/zh_CN/filesystems/sysfs.txt
+++ b/Documentation/translations/zh_CN/filesystems/sysfs.txt
@@ -167,8 +167,8 @@ static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr,
         if (dev_attr->show)
                 ret = dev_attr->show(dev, dev_attr, buf);
         if (ret >= (ssize_t)PAGE_SIZE) {
-                print_symbol("dev_attr_show: %s returned bad count\n",
-                                (unsigned long)dev_attr->show);
+                printk("dev_attr_show: %pS returned bad count\n",
+                                dev_attr->show);
         }
         return ret;
 }
diff --git a/Documentation/usb/chipidea.txt b/Documentation/usb/chipidea.txt
index edf7cdfddc88..d1eedc01b00a 100644
--- a/Documentation/usb/chipidea.txt
+++ b/Documentation/usb/chipidea.txt
@@ -23,13 +23,13 @@ cat /sys/kernel/debug/ci_hdrc.0/registers
 2) Connect 2 boards with usb cable with one end is micro A plug, the other end
    is micro B plug.
 
-   The A-device(with micro A plug inserted) should enumrate B-device.
+   The A-device(with micro A plug inserted) should enumerate B-device.
 
 3) Role switch
    On B-device:
    echo 1 > /sys/bus/platform/devices/ci_hdrc.0/inputs/b_bus_req
 
-   B-device should take host role and enumrate A-device.
+   B-device should take host role and enumerate A-device.
 
 4) A-device switch back to host.
    On B-device:
@@ -40,13 +40,13 @@ cat /sys/kernel/debug/ci_hdrc.0/registers
    side by answering the polling from B-Host, this can be done on A-device:
    echo 1 > /sys/bus/platform/devices/ci_hdrc.0/inputs/a_bus_req
 
-   A-device should switch back to host and enumrate B-device.
+   A-device should switch back to host and enumerate B-device.
 
 5) Remove B-device(unplug micro B plug) and insert again in 10 seconds,
-   A-device should enumrate B-device again.
+   A-device should enumerate B-device again.
 
 6) Remove B-device(unplug micro B plug) and insert again after 10 seconds,
-   A-device should NOT enumrate B-device.
+   A-device should NOT enumerate B-device.
 
    if A-device wants to use bus:
    On A-device:
@@ -67,7 +67,7 @@ cat /sys/kernel/debug/ci_hdrc.0/registers
    On B-device:
    echo 1 > /sys/bus/platform/devices/ci_hdrc.0/inputs/b_bus_req
 
-   A-device should resume usb bus and enumrate B-device.
+   A-device should resume usb bus and enumerate B-device.
 
 1.3 Reference document
 ----------------------
diff --git a/Documentation/usb/gadget-testing.txt b/Documentation/usb/gadget-testing.txt
index 441a4b9b666f..5908a21fddb6 100644
--- a/Documentation/usb/gadget-testing.txt
+++ b/Documentation/usb/gadget-testing.txt
@@ -693,7 +693,7 @@ such specification consists of a number of lines with an inverval value
 in each line. The rules stated above are best illustrated with an example:
 
 # mkdir functions/uvc.usb0/control/header/h
-# cd functions/uvc.usb0/control/header/h
+# cd functions/uvc.usb0/control/
 # ln -s header/h class/fs
 # ln -s header/h class/ss
 # mkdir -p functions/uvc.usb0/streaming/uncompressed/u/360p
diff --git a/Documentation/usb/usbip_protocol.txt b/Documentation/usb/usbip_protocol.txt
index 16b6fe27284c..c7a0f4c7e7f1 100644
--- a/Documentation/usb/usbip_protocol.txt
+++ b/Documentation/usb/usbip_protocol.txt
@@ -274,7 +274,6 @@ USBIP_CMD_SUBMIT: Submit an URB
   URB_SHORT_NOT_OK        | 0x00000001 | only in | only in   | only in  | no
   URB_ISO_ASAP            | 0x00000002 | no      | no        | no       | yes
   URB_NO_TRANSFER_DMA_MAP | 0x00000004 | yes     | yes       | yes      | yes
-  URB_NO_FSBR             | 0x00000020 | yes     | no        | no       | no
   URB_ZERO_PACKET         | 0x00000040 | no      | no        | only out | no
   URB_NO_INTERRUPT        | 0x00000080 | yes     | yes       | yes      | yes
   URB_FREE_BUFFER         | 0x00000100 | yes     | yes       | yes      | yes
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index f670e4b9e7f3..fc3ae951bc07 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2901,14 +2901,19 @@ userspace buffer and its length:
 
 struct kvm_s390_irq_state {
 	__u64 buf;
-	__u32 flags;
+	__u32 flags;        /* will stay unused for compatibility reasons */
 	__u32 len;
-	__u32 reserved[4];
+	__u32 reserved[4];  /* will stay unused for compatibility reasons */
 };
 
 Userspace passes in the above struct and for each pending interrupt a
 struct kvm_s390_irq is copied to the provided buffer.
 
+The structure contains a flags and a reserved field for future extensions. As
+the kernel never checked for flags == 0 and QEMU never pre-zeroed flags and
+reserved, these fields can not be used in the future without breaking
+compatibility.
+
 If -ENOBUFS is returned the buffer provided was too small and userspace
 may retry with a bigger buffer.
 
@@ -2932,10 +2937,14 @@ containing a struct kvm_s390_irq_state:
 
 struct kvm_s390_irq_state {
 	__u64 buf;
+	__u32 flags;        /* will stay unused for compatibility reasons */
 	__u32 len;
-	__u32 pad;
+	__u32 reserved[4];  /* will stay unused for compatibility reasons */
 };
 
+The restrictions for flags and reserved apply as well.
+(see KVM_S390_GET_IRQ_STATE)
+
 The userspace memory referenced by buf contains a struct kvm_s390_irq
 for each interrupt to be injected into the guest.
 If one of the interrupts could not be injected for some reason the
@@ -3394,6 +3403,52 @@ invalid, if invalid pages are written to (e.g. after the end of memory)
 or if no page table is present for the addresses (e.g. when using
 hugepages).
 
+4.108 KVM_PPC_GET_CPU_CHAR
+
+Capability: KVM_CAP_PPC_GET_CPU_CHAR
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_ppc_cpu_char (out)
+Returns: 0 on successful completion
+	 -EFAULT if struct kvm_ppc_cpu_char cannot be written
+
+This ioctl gives userspace information about certain characteristics
+of the CPU relating to speculative execution of instructions and
+possible information leakage resulting from speculative execution (see
+CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754).  The information is
+returned in struct kvm_ppc_cpu_char, which looks like this:
+
+struct kvm_ppc_cpu_char {
+	__u64	character;		/* characteristics of the CPU */
+	__u64	behaviour;		/* recommended software behaviour */
+	__u64	character_mask;		/* valid bits in character */
+	__u64	behaviour_mask;		/* valid bits in behaviour */
+};
+
+For extensibility, the character_mask and behaviour_mask fields
+indicate which bits of character and behaviour have been filled in by
+the kernel.  If the set of defined bits is extended in future then
+userspace will be able to tell whether it is running on a kernel that
+knows about the new bits.
+
+The character field describes attributes of the CPU which can help
+with preventing inadvertent information disclosure - specifically,
+whether there is an instruction to flash-invalidate the L1 data cache
+(ori 30,30,0 or mtspr SPRN_TRIG2,rN), whether the L1 data cache is set
+to a mode where entries can only be used by the thread that created
+them, whether the bcctr[l] instruction prevents speculation, and
+whether a speculation barrier instruction (ori 31,31,0) is provided.
+
+The behaviour field describes actions that software should take to
+prevent inadvertent information disclosure, and thus describes which
+vulnerabilities the hardware is subject to; specifically whether the
+L1 data cache should be flushed when returning to user mode from the
+kernel, and whether a speculation barrier should be placed between an
+array bounds check and the array access.
+
+These fields use the same bit definitions as the new
+H_GET_CPU_CHARACTERISTICS hypercall.
+
 5. The kvm_run structure
 ------------------------
 
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index 59cbc803aad6..faf077d50d42 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -20,19 +20,20 @@ options.
 
 The /proc/meminfo file provides information about the total number of
 persistent hugetlb pages in the kernel's huge page pool.  It also displays
-information about the number of free, reserved and surplus huge pages and the
-default huge page size.  The huge page size is needed for generating the
-proper alignment and size of the arguments to system calls that map huge page
-regions.
+default huge page size and information about the number of free, reserved
+and surplus huge pages in the pool of huge pages of default size.
+The huge page size is needed for generating the proper alignment and
+size of the arguments to system calls that map huge page regions.
 
 The output of "cat /proc/meminfo" will include lines like:
 
 .....
-HugePages_Total: vvv
-HugePages_Free:  www
-HugePages_Rsvd:  xxx
-HugePages_Surp:  yyy
-Hugepagesize:    zzz kB
+HugePages_Total: uuu
+HugePages_Free:  vvv
+HugePages_Rsvd:  www
+HugePages_Surp:  xxx
+Hugepagesize:    yyy kB
+Hugetlb:         zzz kB
 
 where:
 HugePages_Total is the size of the pool of huge pages.
@@ -47,6 +48,14 @@ HugePages_Surp  is short for "surplus," and is the number of huge pages in
                 the pool above the value in /proc/sys/vm/nr_hugepages. The
                 maximum number of surplus huge pages is controlled by
                 /proc/sys/vm/nr_overcommit_hugepages.
+Hugepagesize    is the default hugepage size (in Kb).
+Hugetlb         is the total amount of memory (in kB), consumed by huge
+                pages of all sizes.
+                If huge pages of different sizes are in use, this number
+                will exceed HugePages_Total * Hugepagesize. To get more
+                detailed information, please, refer to
+                /sys/kernel/mm/hugepages (described below).
+
 
 /proc/filesystems should also show a filesystem of type "hugetlbfs" configured
 in the kernel.
diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt
index 6ae89a9edf2a..e912d7eee769 100644
--- a/Documentation/vm/hwpoison.txt
+++ b/Documentation/vm/hwpoison.txt
@@ -104,7 +104,7 @@ madvise(MADV_HWPOISON, ....)
 
 hwpoison-inject module through debugfs
 
-/sys/debug/hwpoison/
+/sys/kernel/debug/hwpoison/
 
 corrupt-pfn
 
diff --git a/Documentation/vm/zswap.txt b/Documentation/vm/zswap.txt
index 89fff7d611cc..0b3a1148f9f0 100644
--- a/Documentation/vm/zswap.txt
+++ b/Documentation/vm/zswap.txt
@@ -98,5 +98,25 @@ request is made for a page in an old zpool, it is uncompressed using its
 original compressor.  Once all pages are removed from an old zpool, the zpool
 and its compressor are freed.
 
+Some of the pages in zswap are same-value filled pages (i.e. contents of the
+page have same value or repetitive pattern). These pages include zero-filled
+pages and they are handled differently. During store operation, a page is
+checked if it is a same-value filled page before compressing it. If true, the
+compressed length of the page is set to zero and the pattern or same-filled
+value is stored.
+
+Same-value filled pages identification feature is enabled by default and can be
+disabled at boot time by setting the "same_filled_pages_enabled" attribute to 0,
+e.g. zswap.same_filled_pages_enabled=0. It can also be enabled and disabled at
+runtime using the sysfs "same_filled_pages_enabled" attribute, e.g.
+
+echo 1 > /sys/module/zswap/parameters/same_filled_pages_enabled
+
+When zswap same-filled page identification is disabled at runtime, it will stop
+checking for the same-value filled pages during store operation. However, the
+existing pages which are marked as same-value filled pages remain stored
+unchanged in zswap until they are either loaded or invalidated.
+
 A debugfs interface is provided for various statistic about pool size, number
-of pages stored, and various counters for the reasons pages are rejected.
+of pages stored, same-value filled pages and various counters for the reasons
+pages are rejected.
diff --git a/Documentation/w1/masters/w1-gpio b/Documentation/w1/masters/w1-gpio
index af5d3b4aa851..623961d9e83f 100644
--- a/Documentation/w1/masters/w1-gpio
+++ b/Documentation/w1/masters/w1-gpio
@@ -8,17 +8,27 @@ Description
 -----------
 
 GPIO 1-wire bus master driver. The driver uses the GPIO API to control the
-wire and the GPIO pin can be specified using platform data.
+wire and the GPIO pin can be specified using GPIO machine descriptor tables.
+It is also possible to define the master using device tree, see
+Documentation/devicetree/bindings/w1/w1-gpio.txt
 
 
 Example (mach-at91)
 -------------------
 
+#include <linux/gpio/machine.h>
 #include <linux/w1-gpio.h>
 
+static struct gpiod_lookup_table foo_w1_gpiod_table = {
+	.dev_id = "w1-gpio",
+	.table = {
+		GPIO_LOOKUP_IDX("at91-gpio", AT91_PIN_PB20, NULL, 0,
+			GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN),
+	},
+};
+
 static struct w1_gpio_platform_data foo_w1_gpio_pdata = {
-	.pin		= AT91_PIN_PB20,
-	.is_open_drain	= 1,
+	.ext_pullup_enable_pin	= -EINVAL,
 };
 
 static struct platform_device foo_w1_device = {
@@ -30,4 +40,5 @@ static struct platform_device foo_w1_device = {
 ...
 	at91_set_GPIO_periph(foo_w1_gpio_pdata.pin, 1);
 	at91_set_multi_drive(foo_w1_gpio_pdata.pin, 1);
+	gpiod_add_lookup_table(&foo_w1_gpiod_table);
 	platform_device_register(&foo_w1_device);
diff --git a/Documentation/w1/w1.generic b/Documentation/w1/w1.generic
index b3ffaf8cfab2..c51b1ab012d0 100644
--- a/Documentation/w1/w1.generic
+++ b/Documentation/w1/w1.generic
@@ -76,7 +76,7 @@ See struct w1_bus_master definition in w1.h for details.
 
 w1 master sysfs interface
 ------------------------------------------------------------------
-<xx-xxxxxxxxxxxxx> - A directory for a found device. The format is family-serial
+<xx-xxxxxxxxxxxx>  - A directory for a found device. The format is family-serial
 bus                - (standard) symlink to the w1 bus
 driver             - (standard) symlink to the w1 driver
 w1_master_add      - (rw) manually register a slave device
diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index 6851854cf69d..756fd76b78a6 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -7,15 +7,24 @@ Tony Luck <tony.luck@intel.com>
 Vikas Shivappa <vikas.shivappa@intel.com>
 
 This feature is enabled by the CONFIG_INTEL_RDT Kconfig and the
-X86 /proc/cpuinfo flag bits "rdt", "cqm", "cat_l3" and "cdp_l3".
+X86 /proc/cpuinfo flag bits:
+RDT (Resource Director Technology) Allocation - "rdt_a"
+CAT (Cache Allocation Technology) - "cat_l3", "cat_l2"
+CDP (Code and Data Prioritization ) - "cdp_l3", "cdp_l2"
+CQM (Cache QoS Monitoring) - "cqm_llc", "cqm_occup_llc"
+MBM (Memory Bandwidth Monitoring) - "cqm_mbm_total", "cqm_mbm_local"
+MBA (Memory Bandwidth Allocation) - "mba"
 
 To use the feature mount the file system:
 
- # mount -t resctrl resctrl [-o cdp] /sys/fs/resctrl
+ # mount -t resctrl resctrl [-o cdp[,cdpl2]] /sys/fs/resctrl
 
 mount options are:
 
 "cdp": Enable code/data prioritization in L3 cache allocations.
+"cdpl2": Enable code/data prioritization in L2 cache allocations.
+
+L2 and L3 CDP are controlled seperately.
 
 RDT features are orthogonal. A particular system may support only
 monitoring, only control, or both monitoring and control.
diff --git a/Documentation/x86/microcode.txt b/Documentation/x86/microcode.txt
index f57e1b45e628..79fdb4a8148a 100644
--- a/Documentation/x86/microcode.txt
+++ b/Documentation/x86/microcode.txt
@@ -108,12 +108,11 @@ packages already put them there.
 ====================
 
 The loader supports also loading of a builtin microcode supplied through
-the regular firmware builtin method CONFIG_FIRMWARE_IN_KERNEL. Only
-64-bit is currently supported.
+the regular builtin firmware method CONFIG_EXTRA_FIRMWARE. Only 64-bit is
+currently supported.
 
 Here's an example:
 
-CONFIG_FIRMWARE_IN_KERNEL=y
 CONFIG_EXTRA_FIRMWARE="intel-ucode/06-3a-09 amd-ucode/microcode_amd_fam15h.bin"
 CONFIG_EXTRA_FIRMWARE_DIR="/lib/firmware"
 
diff --git a/Documentation/x86/pti.txt b/Documentation/x86/pti.txt
new file mode 100644
index 000000000000..5cd58439ad2d
--- /dev/null
+++ b/Documentation/x86/pti.txt
@@ -0,0 +1,186 @@
+Overview
+========
+
+Page Table Isolation (pti, previously known as KAISER[1]) is a
+countermeasure against attacks on the shared user/kernel address
+space such as the "Meltdown" approach[2].
+
+To mitigate this class of attacks, we create an independent set of
+page tables for use only when running userspace applications.  When
+the kernel is entered via syscalls, interrupts or exceptions, the
+page tables are switched to the full "kernel" copy.  When the system
+switches back to user mode, the user copy is used again.
+
+The userspace page tables contain only a minimal amount of kernel
+data: only what is needed to enter/exit the kernel such as the
+entry/exit functions themselves and the interrupt descriptor table
+(IDT).  There are a few strictly unnecessary things that get mapped
+such as the first C function when entering an interrupt (see
+comments in pti.c).
+
+This approach helps to ensure that side-channel attacks leveraging
+the paging structures do not function when PTI is enabled.  It can be
+enabled by setting CONFIG_PAGE_TABLE_ISOLATION=y at compile time.
+Once enabled at compile-time, it can be disabled at boot with the
+'nopti' or 'pti=' kernel parameters (see kernel-parameters.txt).
+
+Page Table Management
+=====================
+
+When PTI is enabled, the kernel manages two sets of page tables.
+The first set is very similar to the single set which is present in
+kernels without PTI.  This includes a complete mapping of userspace
+that the kernel can use for things like copy_to_user().
+
+Although _complete_, the user portion of the kernel page tables is
+crippled by setting the NX bit in the top level.  This ensures
+that any missed kernel->user CR3 switch will immediately crash
+userspace upon executing its first instruction.
+
+The userspace page tables map only the kernel data needed to enter
+and exit the kernel.  This data is entirely contained in the 'struct
+cpu_entry_area' structure which is placed in the fixmap which gives
+each CPU's copy of the area a compile-time-fixed virtual address.
+
+For new userspace mappings, the kernel makes the entries in its
+page tables like normal.  The only difference is when the kernel
+makes entries in the top (PGD) level.  In addition to setting the
+entry in the main kernel PGD, a copy of the entry is made in the
+userspace page tables' PGD.
+
+This sharing at the PGD level also inherently shares all the lower
+layers of the page tables.  This leaves a single, shared set of
+userspace page tables to manage.  One PTE to lock, one set of
+accessed bits, dirty bits, etc...
+
+Overhead
+========
+
+Protection against side-channel attacks is important.  But,
+this protection comes at a cost:
+
+1. Increased Memory Use
+  a. Each process now needs an order-1 PGD instead of order-0.
+     (Consumes an additional 4k per process).
+  b. The 'cpu_entry_area' structure must be 2MB in size and 2MB
+     aligned so that it can be mapped by setting a single PMD
+     entry.  This consumes nearly 2MB of RAM once the kernel
+     is decompressed, but no space in the kernel image itself.
+
+2. Runtime Cost
+  a. CR3 manipulation to switch between the page table copies
+     must be done at interrupt, syscall, and exception entry
+     and exit (it can be skipped when the kernel is interrupted,
+     though.)  Moves to CR3 are on the order of a hundred
+     cycles, and are required at every entry and exit.
+  b. A "trampoline" must be used for SYSCALL entry.  This
+     trampoline depends on a smaller set of resources than the
+     non-PTI SYSCALL entry code, so requires mapping fewer
+     things into the userspace page tables.  The downside is
+     that stacks must be switched at entry time.
+  c. Global pages are disabled for all kernel structures not
+     mapped into both kernel and userspace page tables.  This
+     feature of the MMU allows different processes to share TLB
+     entries mapping the kernel.  Losing the feature means more
+     TLB misses after a context switch.  The actual loss of
+     performance is very small, however, never exceeding 1%.
+  d. Process Context IDentifiers (PCID) is a CPU feature that
+     allows us to skip flushing the entire TLB when switching page
+     tables by setting a special bit in CR3 when the page tables
+     are changed.  This makes switching the page tables (at context
+     switch, or kernel entry/exit) cheaper.  But, on systems with
+     PCID support, the context switch code must flush both the user
+     and kernel entries out of the TLB.  The user PCID TLB flush is
+     deferred until the exit to userspace, minimizing the cost.
+     See intel.com/sdm for the gory PCID/INVPCID details.
+  e. The userspace page tables must be populated for each new
+     process.  Even without PTI, the shared kernel mappings
+     are created by copying top-level (PGD) entries into each
+     new process.  But, with PTI, there are now *two* kernel
+     mappings: one in the kernel page tables that maps everything
+     and one for the entry/exit structures.  At fork(), we need to
+     copy both.
+  f. In addition to the fork()-time copying, there must also
+     be an update to the userspace PGD any time a set_pgd() is done
+     on a PGD used to map userspace.  This ensures that the kernel
+     and userspace copies always map the same userspace
+     memory.
+  g. On systems without PCID support, each CR3 write flushes
+     the entire TLB.  That means that each syscall, interrupt
+     or exception flushes the TLB.
+  h. INVPCID is a TLB-flushing instruction which allows flushing
+     of TLB entries for non-current PCIDs.  Some systems support
+     PCIDs, but do not support INVPCID.  On these systems, addresses
+     can only be flushed from the TLB for the current PCID.  When
+     flushing a kernel address, we need to flush all PCIDs, so a
+     single kernel address flush will require a TLB-flushing CR3
+     write upon the next use of every PCID.
+
+Possible Future Work
+====================
+1. We can be more careful about not actually writing to CR3
+   unless its value is actually changed.
+2. Allow PTI to be enabled/disabled at runtime in addition to the
+   boot-time switching.
+
+Testing
+========
+
+To test stability of PTI, the following test procedure is recommended,
+ideally doing all of these in parallel:
+
+1. Set CONFIG_DEBUG_ENTRY=y
+2. Run several copies of all of the tools/testing/selftests/x86/ tests
+   (excluding MPX and protection_keys) in a loop on multiple CPUs for
+   several minutes.  These tests frequently uncover corner cases in the
+   kernel entry code.  In general, old kernels might cause these tests
+   themselves to crash, but they should never crash the kernel.
+3. Run the 'perf' tool in a mode (top or record) that generates many
+   frequent performance monitoring non-maskable interrupts (see "NMI"
+   in /proc/interrupts).  This exercises the NMI entry/exit code which
+   is known to trigger bugs in code paths that did not expect to be
+   interrupted, including nested NMIs.  Using "-c" boosts the rate of
+   NMIs, and using two -c with separate counters encourages nested NMIs
+   and less deterministic behavior.
+
+	while true; do perf record -c 10000 -e instructions,cycles -a sleep 10; done
+
+4. Launch a KVM virtual machine.
+5. Run 32-bit binaries on systems supporting the SYSCALL instruction.
+   This has been a lightly-tested code path and needs extra scrutiny.
+
+Debugging
+=========
+
+Bugs in PTI cause a few different signatures of crashes
+that are worth noting here.
+
+ * Failures of the selftests/x86 code.  Usually a bug in one of the
+   more obscure corners of entry_64.S
+ * Crashes in early boot, especially around CPU bringup.  Bugs
+   in the trampoline code or mappings cause these.
+ * Crashes at the first interrupt.  Caused by bugs in entry_64.S,
+   like screwing up a page table switch.  Also caused by
+   incorrectly mapping the IRQ handler entry code.
+ * Crashes at the first NMI.  The NMI code is separate from main
+   interrupt handlers and can have bugs that do not affect
+   normal interrupts.  Also caused by incorrectly mapping NMI
+   code.  NMIs that interrupt the entry code must be very
+   careful and can be the cause of crashes that show up when
+   running perf.
+ * Kernel crashes at the first exit to userspace.  entry_64.S
+   bugs, or failing to map some of the exit code.
+ * Crashes at first interrupt that interrupts userspace. The paths
+   in entry_64.S that return to userspace are sometimes separate
+   from the ones that return to the kernel.
+ * Double faults: overflowing the kernel stack because of page
+   faults upon page faults.  Caused by touching non-pti-mapped
+   data in the entry code, or forgetting to switch to kernel
+   CR3 before calling into C functions which are not pti-mapped.
+ * Userspace segfaults early in boot, sometimes manifesting
+   as mount(8) failing to mount the rootfs.  These have
+   tended to be TLB invalidation issues.  Usually invalidating
+   the wrong PCID, or otherwise missing an invalidation.
+
+1. https://gruss.cc/files/kaiser.pdf
+2. https://meltdownattack.com/meltdown.pdf
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 3448e675b462..ea91cb61a602 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -1,6 +1,4 @@
 
-<previous description obsolete, deleted>
-
 Virtual memory map with 4 level page tables:
 
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
@@ -14,13 +12,17 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB)
 ... unused hole ...
+				    vaddr_end for KASLR
+fffffe0000000000 - fffffe7fffffffff (=39 bits) cpu_entry_area mapping
+fffffe8000000000 - fffffeffffffffff (=39 bits) LDT remap for PTI
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space (variable)
-ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffa0000000 - [fixmap start]   (~1526 MB) module mapping space (variable)
+[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
 Virtual memory map with 5 level page tables:
@@ -29,26 +31,31 @@ Virtual memory map with 5 level page tables:
 hole caused by [56:63] sign extension
 ff00000000000000 - ff0fffffffffffff (=52 bits) guard hole, reserved for hypervisor
 ff10000000000000 - ff8fffffffffffff (=55 bits) direct mapping of all phys. memory
-ff90000000000000 - ff91ffffffffffff (=49 bits) hole
-ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space
+ff90000000000000 - ff9fffffffffffff (=52 bits) LDT remap for PTI
+ffa0000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space (12800 TB)
 ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole
 ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
 ... unused hole ...
 ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB)
 ... unused hole ...
+				    vaddr_end for KASLR
+fffffe0000000000 - fffffe7fffffffff (=39 bits) cpu_entry_area mapping
+... unused hole ...
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space
-ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffa0000000 - fffffffffeffffff (1520 MB) module mapping space
+[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
 Architecture defines a 64-bit virtual address. Implementations can support
 less. Currently supported are 48- and 57-bit virtual addresses. Bits 63
-through to the most-significant implemented bit are set to either all ones
-or all zero. This causes hole between user space and kernel addresses.
+through to the most-significant implemented bit are sign extended.
+This causes hole between user space and kernel addresses if you interpret them
+as unsigned.
 
 The direct mapping covers all memory in the system up to the highest
 memory address (this means in some cases it can also include PCI memory
@@ -58,19 +65,15 @@ vmalloc space is lazily synchronized into the different PML4/PML5 pages of
 the processes using the page fault handler, with init_top_pgt as
 reference.
 
-Current X86-64 implementations support up to 46 bits of address space (64 TB),
-which is our current limit. This expands into MBZ space in the page tables.
-
 We map EFI runtime services in the 'efi_pgd' PGD in a 64Gb large virtual
 memory window (this size is arbitrary, it can be raised later if needed).
 The mappings are not part of any other kernel PGD and are only available
 during EFI runtime calls.
 
-The module mapping space size changes based on the CONFIG requirements for the
-following fixmap section.
-
 Note that if CONFIG_RANDOMIZE_MEMORY is enabled, the direct mapping of all
 physical memory, vmalloc/ioremap space and virtual memory map are randomized.
 Their order is preserved but their base will be offset early at boot time.
 
--Andi Kleen, Jul 2004
+Be very careful vs. KASLR when changing anything here. The KASLR address
+range must not overlap with anything except the KASAN shadow area, which is
+correct as KASAN disables KASLR.
diff --git a/Documentation/xtensa/mmu.txt b/Documentation/xtensa/mmu.txt
index 5de8715d5bec..318114de63f3 100644
--- a/Documentation/xtensa/mmu.txt
+++ b/Documentation/xtensa/mmu.txt
@@ -69,19 +69,10 @@ Default MMUv2-compatible layout.
 | Userspace        |                           0x00000000  TASK_SIZE
 +------------------+                           0x40000000
 +------------------+
-| Page table       |                           0x80000000
-+------------------+                           0x80400000
+| Page table       |  XCHAL_PAGE_TABLE_VADDR   0x80000000  XCHAL_PAGE_TABLE_SIZE
 +------------------+
-| KMAP area        |  PKMAP_BASE                           PTRS_PER_PTE *
-|                  |                                       DCACHE_N_COLORS *
-|                  |                                       PAGE_SIZE
-|                  |                                       (4MB * DCACHE_N_COLORS)
-+------------------+
-| Atomic KMAP area |  FIXADDR_START                        KM_TYPE_NR *
-|                  |                                       NR_CPUS *
-|                  |                                       DCACHE_N_COLORS *
-|                  |                                       PAGE_SIZE
-+------------------+  FIXADDR_TOP              0xbffff000
+| KASAN shadow map |  KASAN_SHADOW_START       0x80400000  KASAN_SHADOW_SIZE
++------------------+                           0x8e400000
 +------------------+
 | VMALLOC area     |  VMALLOC_START            0xc0000000  128MB - 64KB
 +------------------+  VMALLOC_END
@@ -92,6 +83,17 @@ Default MMUv2-compatible layout.
 | remap area 2     |
 +------------------+
 +------------------+
+| KMAP area        |  PKMAP_BASE                           PTRS_PER_PTE *
+|                  |                                       DCACHE_N_COLORS *
+|                  |                                       PAGE_SIZE
+|                  |                                       (4MB * DCACHE_N_COLORS)
++------------------+
+| Atomic KMAP area |  FIXADDR_START                        KM_TYPE_NR *
+|                  |                                       NR_CPUS *
+|                  |                                       DCACHE_N_COLORS *
+|                  |                                       PAGE_SIZE
++------------------+  FIXADDR_TOP              0xcffff000
++------------------+
 | Cached KSEG      |  XCHAL_KSEG_CACHED_VADDR  0xd0000000  128MB
 +------------------+
 | Uncached KSEG    |  XCHAL_KSEG_BYPASS_VADDR  0xd8000000  128MB
@@ -109,19 +111,10 @@ Default MMUv2-compatible layout.
 | Userspace        |                           0x00000000  TASK_SIZE
 +------------------+                           0x40000000
 +------------------+
-| Page table       |                           0x80000000
-+------------------+                           0x80400000
+| Page table       |  XCHAL_PAGE_TABLE_VADDR   0x80000000  XCHAL_PAGE_TABLE_SIZE
 +------------------+
-| KMAP area        |  PKMAP_BASE                           PTRS_PER_PTE *
-|                  |                                       DCACHE_N_COLORS *
-|                  |                                       PAGE_SIZE
-|                  |                                       (4MB * DCACHE_N_COLORS)
-+------------------+
-| Atomic KMAP area |  FIXADDR_START                        KM_TYPE_NR *
-|                  |                                       NR_CPUS *
-|                  |                                       DCACHE_N_COLORS *
-|                  |                                       PAGE_SIZE
-+------------------+  FIXADDR_TOP              0x9ffff000
+| KASAN shadow map |  KASAN_SHADOW_START       0x80400000  KASAN_SHADOW_SIZE
++------------------+                           0x8e400000
 +------------------+
 | VMALLOC area     |  VMALLOC_START            0xa0000000  128MB - 64KB
 +------------------+  VMALLOC_END
@@ -132,6 +125,17 @@ Default MMUv2-compatible layout.
 | remap area 2     |
 +------------------+
 +------------------+
+| KMAP area        |  PKMAP_BASE                           PTRS_PER_PTE *
+|                  |                                       DCACHE_N_COLORS *
+|                  |                                       PAGE_SIZE
+|                  |                                       (4MB * DCACHE_N_COLORS)
++------------------+
+| Atomic KMAP area |  FIXADDR_START                        KM_TYPE_NR *
+|                  |                                       NR_CPUS *
+|                  |                                       DCACHE_N_COLORS *
+|                  |                                       PAGE_SIZE
++------------------+  FIXADDR_TOP              0xaffff000
++------------------+
 | Cached KSEG      |  XCHAL_KSEG_CACHED_VADDR  0xb0000000  256MB
 +------------------+
 | Uncached KSEG    |  XCHAL_KSEG_BYPASS_VADDR  0xc0000000  256MB
@@ -150,19 +154,10 @@ Default MMUv2-compatible layout.
 | Userspace        |                           0x00000000  TASK_SIZE
 +------------------+                           0x40000000
 +------------------+
-| Page table       |                           0x80000000
-+------------------+                           0x80400000
+| Page table       |  XCHAL_PAGE_TABLE_VADDR   0x80000000  XCHAL_PAGE_TABLE_SIZE
 +------------------+
-| KMAP area        |  PKMAP_BASE                           PTRS_PER_PTE *
-|                  |                                       DCACHE_N_COLORS *
-|                  |                                       PAGE_SIZE
-|                  |                                       (4MB * DCACHE_N_COLORS)
-+------------------+
-| Atomic KMAP area |  FIXADDR_START                        KM_TYPE_NR *
-|                  |                                       NR_CPUS *
-|                  |                                       DCACHE_N_COLORS *
-|                  |                                       PAGE_SIZE
-+------------------+  FIXADDR_TOP              0x8ffff000
+| KASAN shadow map |  KASAN_SHADOW_START       0x80400000  KASAN_SHADOW_SIZE
++------------------+                           0x8e400000
 +------------------+
 | VMALLOC area     |  VMALLOC_START            0x90000000  128MB - 64KB
 +------------------+  VMALLOC_END
@@ -173,6 +168,17 @@ Default MMUv2-compatible layout.
 | remap area 2     |
 +------------------+
 +------------------+
+| KMAP area        |  PKMAP_BASE                           PTRS_PER_PTE *
+|                  |                                       DCACHE_N_COLORS *
+|                  |                                       PAGE_SIZE
+|                  |                                       (4MB * DCACHE_N_COLORS)
++------------------+
+| Atomic KMAP area |  FIXADDR_START                        KM_TYPE_NR *
+|                  |                                       NR_CPUS *
+|                  |                                       DCACHE_N_COLORS *
+|                  |                                       PAGE_SIZE
++------------------+  FIXADDR_TOP              0x9ffff000
++------------------+
 | Cached KSEG      |  XCHAL_KSEG_CACHED_VADDR  0xa0000000  512MB
 +------------------+
 | Uncached KSEG    |  XCHAL_KSEG_BYPASS_VADDR  0xc0000000  512MB
diff --git a/LICENSES/exceptions/Linux-syscall-note b/LICENSES/exceptions/Linux-syscall-note
new file mode 100644
index 000000000000..6b60b61be4e9
--- /dev/null
+++ b/LICENSES/exceptions/Linux-syscall-note
@@ -0,0 +1,25 @@
+SPDX-Exception-Identifier: Linux-syscall-note
+SPDX-URL: https://spdx.org/licenses/Linux-syscall-note.html
+SPDX-Licenses: GPL-2.0, GPL-2.0+, GPL-1.0+, LGPL-2.0, LGPL-2.0+, LGPL-2.1, LGPL-2.1+
+Usage-Guide:
+  This exception is used together with one of the above SPDX-Licenses
+  to mark user space API (uapi) header files so they can be included
+  into non GPL compliant user space application code.
+  To use this exception add it with the keyword WITH to one of the
+  identifiers in the SPDX-Licenses tag:
+    SPDX-License-Identifier: <SPDX-License> WITH Linux-syscall-note
+License-Text:
+
+   NOTE! This copyright does *not* cover user programs that use kernel
+ services by normal system calls - this is merely considered normal use
+ of the kernel, and does *not* fall under the heading of "derived work".
+ Also note that the GPL below is copyrighted by the Free Software
+ Foundation, but the instance of code that it refers to (the Linux
+ kernel) is copyrighted by me and others who actually wrote it.
+
+ Also note that the only valid version of the GPL as far as the kernel
+ is concerned is _this_ particular version of the license (ie v2, not
+ v2.2 or v3.x or whatever), unless explicitly otherwise stated.
+
+			Linus Torvalds
+
diff --git a/LICENSES/other/GPL-1.0 b/LICENSES/other/GPL-1.0
new file mode 100644
index 000000000000..3a4fa969e4c2
--- /dev/null
+++ b/LICENSES/other/GPL-1.0
@@ -0,0 +1,260 @@
+Valid-License-Identifier: GPL-1.0+
+SPDX-URL: https://spdx.org/licenses/GPL-1.0.html
+Usage-Guide:
+  The GNU General Public License (GPL) version 1 should not be used in new
+  code. For existing kernel code the 'or any later version' option is
+  required to be compatible with the general license of the project: GPLv2.
+  To use the license in source code, put the following SPDX tag/value pair
+  into a comment according to the placement guidelines in the licensing
+  rules documentation:
+    SPDX-License-Identifier: GPL-1.0+
+License-Text:
+
+	    GNU GENERAL PUBLIC LICENSE
+	     Version 1, February 1989
+
+ Copyright (C) 1989 Free Software Foundation, Inc.
+                    675 Mass Ave, Cambridge, MA 02139, USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+			    Preamble
+
+  The license agreements of most software companies try to keep users
+at the mercy of those companies.  By contrast, our General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  The
+General Public License applies to the Free Software Foundation's
+software and to any other program whose authors commit to using it.
+You can use it for your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Specifically, the General Public License is designed to make
+sure that you have the freedom to give away or sell copies of free
+software, that you receive source code or can get it if you want it,
+that you can change the software or use pieces of it in new free
+programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of a such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must tell them their rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+		    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License Agreement applies to any program or other work which
+contains a notice placed by the copyright holder saying it may be
+distributed under the terms of this General Public License.  The
+"Program", below, refers to any such program or work, and a "work based
+on the Program" means either the Program or any work containing the
+Program or a portion of it, either verbatim or with modifications.  Each
+licensee is addressed as "you".
+
+  1. You may copy and distribute verbatim copies of the Program's source
+code as you receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice and
+disclaimer of warranty; keep intact all the notices that refer to this
+General Public License and to the absence of any warranty; and give any
+other recipients of the Program a copy of this General Public License
+along with the Program.  You may charge a fee for the physical act of
+transferring a copy.
+
+  2. You may modify your copy or copies of the Program or any portion of
+it, and copy and distribute such modifications under the terms of Paragraph
+1 above, provided that you also do the following:
+
+    a) cause the modified files to carry prominent notices stating that
+    you changed the files and the date of any change; and
+
+    b) cause the whole of any work that you distribute or publish, that
+    in whole or in part contains the Program or any part thereof, either
+    with or without modifications, to be licensed at no charge to all
+    third parties under the terms of this General Public License (except
+    that you may choose to grant warranty protection to some or all
+    third parties, at your option).
+
+    c) If the modified program normally reads commands interactively when
+    run, you must cause it, when started running for such interactive use
+    in the simplest and most usual way, to print or display an
+    announcement including an appropriate copyright notice and a notice
+    that there is no warranty (or else, saying that you provide a
+    warranty) and that users may redistribute the program under these
+    conditions, and telling the user how to view a copy of this General
+    Public License.
+
+    d) You may charge a fee for the physical act of transferring a
+    copy, and you may at your option offer warranty protection in
+    exchange for a fee.
+
+Mere aggregation of another independent work with the Program (or its
+derivative) on a volume of a storage or distribution medium does not bring
+the other work under the scope of these terms.
+
+  3. You may copy and distribute the Program (or a portion or derivative of
+it, under Paragraph 2) in object code or executable form under the terms of
+Paragraphs 1 and 2 above provided that you also do one of the following:
+
+    a) accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of
+    Paragraphs 1 and 2 above; or,
+
+    b) accompany it with a written offer, valid for at least three
+    years, to give any third party free (except for a nominal charge
+    for the cost of distribution) a complete machine-readable copy of the
+    corresponding source code, to be distributed under the terms of
+    Paragraphs 1 and 2 above; or,
+
+    c) accompany it with the information you received as to where the
+    corresponding source code may be obtained.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form alone.)
+
+Source code for a work means the preferred form of the work for making
+modifications to it.  For an executable file, complete source code means
+all the source code for all modules it contains; but, as a special
+exception, it need not include source code for modules which are standard
+libraries that accompany the operating system on which the executable
+file runs, or for standard header files or definitions files that
+accompany that operating system.
+
+  4. You may not copy, modify, sublicense, distribute or transfer the
+Program except as expressly provided under this General Public License.
+Any attempt otherwise to copy, modify, sublicense, distribute or transfer
+the Program is void, and will automatically terminate your rights to use
+the Program under this License.  However, parties who have received
+copies, or rights to use copies, from you under this General Public
+License will not have their licenses terminated so long as such parties
+remain in full compliance.
+
+  5. By copying, distributing or modifying the Program (or any work based
+on the Program) you indicate your acceptance of this license to do so,
+and all its terms and conditions.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the original
+licensor to copy, distribute or modify the Program subject to these
+terms and conditions.  You may not impose any further restrictions on the
+recipients' exercise of the rights granted herein.
+
+  7. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of the license which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+the license, you may choose any version ever published by the Free Software
+Foundation.
+
+  8. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+			    NO WARRANTY
+
+  9. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  10. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+		     END OF TERMS AND CONDITIONS
+
+	Appendix: How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to humanity, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these
+terms.
+
+  To do so, attach the following notices to the program.  It is safest to
+attach them to the start of each source file to most effectively convey
+the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) 19yy  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 1, or (at your option)
+    any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) 19xx name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the
+appropriate parts of the General Public License.  Of course, the
+commands you use may be called something other than `show w' and `show
+c'; they could even be mouse-clicks or menu items--whatever suits your
+program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the
+  program `Gnomovision' (a program to direct compilers to make passes
+  at assemblers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+That's all there is to it!
diff --git a/LICENSES/other/MPL-1.1 b/LICENSES/other/MPL-1.1
new file mode 100644
index 000000000000..568b6049efe6
--- /dev/null
+++ b/LICENSES/other/MPL-1.1
@@ -0,0 +1,478 @@
+Valid-License-Identifier: MPL-1.1
+SPDX-URL: https://spdx.org/licenses/MPL-1.1.html
+Usage-Guide:
+  To use the Mozilla Public License version 1.1 put the following SPDX
+  tag/value pair into a comment according to the placement guidelines in
+  the licensing rules documentation:
+    SPDX-License-Identifier: MPL-1.1
+License-Text:
+
+                          MOZILLA PUBLIC LICENSE
+                                Version 1.1
+
+                              ---------------
+
+1. Definitions.
+
+     1.0.1. "Commercial Use" means distribution or otherwise making the
+     Covered Code available to a third party.
+
+     1.1. "Contributor" means each entity that creates or contributes to
+     the creation of Modifications.
+
+     1.2. "Contributor Version" means the combination of the Original
+     Code, prior Modifications used by a Contributor, and the Modifications
+     made by that particular Contributor.
+
+     1.3. "Covered Code" means the Original Code or Modifications or the
+     combination of the Original Code and Modifications, in each case
+     including portions thereof.
+
+     1.4. "Electronic Distribution Mechanism" means a mechanism generally
+     accepted in the software development community for the electronic
+     transfer of data.
+
+     1.5. "Executable" means Covered Code in any form other than Source
+     Code.
+
+     1.6. "Initial Developer" means the individual or entity identified
+     as the Initial Developer in the Source Code notice required by Exhibit
+     A.
+
+     1.7. "Larger Work" means a work which combines Covered Code or
+     portions thereof with code not governed by the terms of this License.
+
+     1.8. "License" means this document.
+
+     1.8.1. "Licensable" means having the right to grant, to the maximum
+     extent possible, whether at the time of the initial grant or
+     subsequently acquired, any and all of the rights conveyed herein.
+
+     1.9. "Modifications" means any addition to or deletion from the
+     substance or structure of either the Original Code or any previous
+     Modifications. When Covered Code is released as a series of files, a
+     Modification is:
+          A. Any addition to or deletion from the contents of a file
+          containing Original Code or previous Modifications.
+
+          B. Any new file that contains any part of the Original Code or
+          previous Modifications.
+
+     1.10. "Original Code" means Source Code of computer software code
+     which is described in the Source Code notice required by Exhibit A as
+     Original Code, and which, at the time of its release under this
+     License is not already Covered Code governed by this License.
+
+     1.10.1. "Patent Claims" means any patent claim(s), now owned or
+     hereafter acquired, including without limitation,  method, process,
+     and apparatus claims, in any patent Licensable by grantor.
+
+     1.11. "Source Code" means the preferred form of the Covered Code for
+     making modifications to it, including all modules it contains, plus
+     any associated interface definition files, scripts used to control
+     compilation and installation of an Executable, or source code
+     differential comparisons against either the Original Code or another
+     well known, available Covered Code of the Contributor's choice. The
+     Source Code can be in a compressed or archival form, provided the
+     appropriate decompression or de-archiving software is widely available
+     for no charge.
+
+     1.12. "You" (or "Your")  means an individual or a legal entity
+     exercising rights under, and complying with all of the terms of, this
+     License or a future version of this License issued under Section 6.1.
+     For legal entities, "You" includes any entity which controls, is
+     controlled by, or is under common control with You. For purposes of
+     this definition, "control" means (a) the power, direct or indirect,
+     to cause the direction or management of such entity, whether by
+     contract or otherwise, or (b) ownership of more than fifty percent
+     (50%) of the outstanding shares or beneficial ownership of such
+     entity.
+
+2. Source Code License.
+
+     2.1. The Initial Developer Grant.
+     The Initial Developer hereby grants You a world-wide, royalty-free,
+     non-exclusive license, subject to third party intellectual property
+     claims:
+          (a)  under intellectual property rights (other than patent or
+          trademark) Licensable by Initial Developer to use, reproduce,
+          modify, display, perform, sublicense and distribute the Original
+          Code (or portions thereof) with or without Modifications, and/or
+          as part of a Larger Work; and
+
+          (b) under Patents Claims infringed by the making, using or
+          selling of Original Code, to make, have made, use, practice,
+          sell, and offer for sale, and/or otherwise dispose of the
+          Original Code (or portions thereof).
+
+          (c) the licenses granted in this Section 2.1(a) and (b) are
+          effective on the date Initial Developer first distributes
+          Original Code under the terms of this License.
+
+          (d) Notwithstanding Section 2.1(b) above, no patent license is
+          granted: 1) for code that You delete from the Original Code; 2)
+          separate from the Original Code;  or 3) for infringements caused
+          by: i) the modification of the Original Code or ii) the
+          combination of the Original Code with other software or devices.
+
+     2.2. Contributor Grant.
+     Subject to third party intellectual property claims, each Contributor
+     hereby grants You a world-wide, royalty-free, non-exclusive license
+
+          (a)  under intellectual property rights (other than patent or
+          trademark) Licensable by Contributor, to use, reproduce, modify,
+          display, perform, sublicense and distribute the Modifications
+          created by such Contributor (or portions thereof) either on an
+          unmodified basis, with other Modifications, as Covered Code
+          and/or as part of a Larger Work; and
+
+          (b) under Patent Claims infringed by the making, using, or
+          selling of  Modifications made by that Contributor either alone
+          and/or in combination with its Contributor Version (or portions
+          of such combination), to make, use, sell, offer for sale, have
+          made, and/or otherwise dispose of: 1) Modifications made by that
+          Contributor (or portions thereof); and 2) the combination of
+          Modifications made by that Contributor with its Contributor
+          Version (or portions of such combination).
+
+          (c) the licenses granted in Sections 2.2(a) and 2.2(b) are
+          effective on the date Contributor first makes Commercial Use of
+          the Covered Code.
+
+          (d)    Notwithstanding Section 2.2(b) above, no patent license is
+          granted: 1) for any code that Contributor has deleted from the
+          Contributor Version; 2)  separate from the Contributor Version;
+          3)  for infringements caused by: i) third party modifications of
+          Contributor Version or ii)  the combination of Modifications made
+          by that Contributor with other software  (except as part of the
+          Contributor Version) or other devices; or 4) under Patent Claims
+          infringed by Covered Code in the absence of Modifications made by
+          that Contributor.
+
+3. Distribution Obligations.
+
+     3.1. Application of License.
+     The Modifications which You create or to which You contribute are
+     governed by the terms of this License, including without limitation
+     Section 2.2. The Source Code version of Covered Code may be
+     distributed only under the terms of this License or a future version
+     of this License released under Section 6.1, and You must include a
+     copy of this License with every copy of the Source Code You
+     distribute. You may not offer or impose any terms on any Source Code
+     version that alters or restricts the applicable version of this
+     License or the recipients' rights hereunder. However, You may include
+     an additional document offering the additional rights described in
+     Section 3.5.
+
+     3.2. Availability of Source Code.
+     Any Modification which You create or to which You contribute must be
+     made available in Source Code form under the terms of this License
+     either on the same media as an Executable version or via an accepted
+     Electronic Distribution Mechanism to anyone to whom you made an
+     Executable version available; and if made available via Electronic
+     Distribution Mechanism, must remain available for at least twelve (12)
+     months after the date it initially became available, or at least six
+     (6) months after a subsequent version of that particular Modification
+     has been made available to such recipients. You are responsible for
+     ensuring that the Source Code version remains available even if the
+     Electronic Distribution Mechanism is maintained by a third party.
+
+     3.3. Description of Modifications.
+     You must cause all Covered Code to which You contribute to contain a
+     file documenting the changes You made to create that Covered Code and
+     the date of any change. You must include a prominent statement that
+     the Modification is derived, directly or indirectly, from Original
+     Code provided by the Initial Developer and including the name of the
+     Initial Developer in (a) the Source Code, and (b) in any notice in an
+     Executable version or related documentation in which You describe the
+     origin or ownership of the Covered Code.
+
+     3.4. Intellectual Property Matters
+          (a) Third Party Claims.
+          If Contributor has knowledge that a license under a third party's
+          intellectual property rights is required to exercise the rights
+          granted by such Contributor under Sections 2.1 or 2.2,
+          Contributor must include a text file with the Source Code
+          distribution titled "LEGAL" which describes the claim and the
+          party making the claim in sufficient detail that a recipient will
+          know whom to contact. If Contributor obtains such knowledge after
+          the Modification is made available as described in Section 3.2,
+          Contributor shall promptly modify the LEGAL file in all copies
+          Contributor makes available thereafter and shall take other steps
+          (such as notifying appropriate mailing lists or newsgroups)
+          reasonably calculated to inform those who received the Covered
+          Code that new knowledge has been obtained.
+
+          (b) Contributor APIs.
+          If Contributor's Modifications include an application programming
+          interface and Contributor has knowledge of patent licenses which
+          are reasonably necessary to implement that API, Contributor must
+          also include this information in the LEGAL file.
+
+               (c)    Representations.
+          Contributor represents that, except as disclosed pursuant to
+          Section 3.4(a) above, Contributor believes that Contributor's
+          Modifications are Contributor's original creation(s) and/or
+          Contributor has sufficient rights to grant the rights conveyed by
+          this License.
+
+     3.5. Required Notices.
+     You must duplicate the notice in Exhibit A in each file of the Source
+     Code.  If it is not possible to put such notice in a particular Source
+     Code file due to its structure, then You must include such notice in a
+     location (such as a relevant directory) where a user would be likely
+     to look for such a notice.  If You created one or more Modification(s)
+     You may add your name as a Contributor to the notice described in
+     Exhibit A.  You must also duplicate this License in any documentation
+     for the Source Code where You describe recipients' rights or ownership
+     rights relating to Covered Code.  You may choose to offer, and to
+     charge a fee for, warranty, support, indemnity or liability
+     obligations to one or more recipients of Covered Code. However, You
+     may do so only on Your own behalf, and not on behalf of the Initial
+     Developer or any Contributor. You must make it absolutely clear than
+     any such warranty, support, indemnity or liability obligation is
+     offered by You alone, and You hereby agree to indemnify the Initial
+     Developer and every Contributor for any liability incurred by the
+     Initial Developer or such Contributor as a result of warranty,
+     support, indemnity or liability terms You offer.
+
+     3.6. Distribution of Executable Versions.
+     You may distribute Covered Code in Executable form only if the
+     requirements of Section 3.1-3.5 have been met for that Covered Code,
+     and if You include a notice stating that the Source Code version of
+     the Covered Code is available under the terms of this License,
+     including a description of how and where You have fulfilled the
+     obligations of Section 3.2. The notice must be conspicuously included
+     in any notice in an Executable version, related documentation or
+     collateral in which You describe recipients' rights relating to the
+     Covered Code. You may distribute the Executable version of Covered
+     Code or ownership rights under a license of Your choice, which may
+     contain terms different from this License, provided that You are in
+     compliance with the terms of this License and that the license for the
+     Executable version does not attempt to limit or alter the recipient's
+     rights in the Source Code version from the rights set forth in this
+     License. If You distribute the Executable version under a different
+     license You must make it absolutely clear that any terms which differ
+     from this License are offered by You alone, not by the Initial
+     Developer or any Contributor. You hereby agree to indemnify the
+     Initial Developer and every Contributor for any liability incurred by
+     the Initial Developer or such Contributor as a result of any such
+     terms You offer.
+
+     3.7. Larger Works.
+     You may create a Larger Work by combining Covered Code with other code
+     not governed by the terms of this License and distribute the Larger
+     Work as a single product. In such a case, You must make sure the
+     requirements of this License are fulfilled for the Covered Code.
+
+4. Inability to Comply Due to Statute or Regulation.
+
+     If it is impossible for You to comply with any of the terms of this
+     License with respect to some or all of the Covered Code due to
+     statute, judicial order, or regulation then You must: (a) comply with
+     the terms of this License to the maximum extent possible; and (b)
+     describe the limitations and the code they affect. Such description
+     must be included in the LEGAL file described in Section 3.4 and must
+     be included with all distributions of the Source Code. Except to the
+     extent prohibited by statute or regulation, such description must be
+     sufficiently detailed for a recipient of ordinary skill to be able to
+     understand it.
+
+5. Application of this License.
+
+     This License applies to code to which the Initial Developer has
+     attached the notice in Exhibit A and to related Covered Code.
+
+6. Versions of the License.
+
+     6.1. New Versions.
+     Netscape Communications Corporation ("Netscape") may publish revised
+     and/or new versions of the License from time to time. Each version
+     will be given a distinguishing version number.
+
+     6.2. Effect of New Versions.
+     Once Covered Code has been published under a particular version of the
+     License, You may always continue to use it under the terms of that
+     version. You may also choose to use such Covered Code under the terms
+     of any subsequent version of the License published by Netscape. No one
+     other than Netscape has the right to modify the terms applicable to
+     Covered Code created under this License.
+
+     6.3. Derivative Works.
+     If You create or use a modified version of this License (which you may
+     only do in order to apply it to code which is not already Covered Code
+     governed by this License), You must (a) rename Your license so that
+     the phrases "Mozilla", "MOZILLAPL", "MOZPL", "Netscape",
+     "MPL", "NPL" or any confusingly similar phrase do not appear in your
+     license (except to note that your license differs from this License)
+     and (b) otherwise make it clear that Your version of the license
+     contains terms which differ from the Mozilla Public License and
+     Netscape Public License. (Filling in the name of the Initial
+     Developer, Original Code or Contributor in the notice described in
+     Exhibit A shall not of themselves be deemed to be modifications of
+     this License.)
+
+7. DISCLAIMER OF WARRANTY.
+
+     COVERED CODE IS PROVIDED UNDER THIS LICENSE ON AN "AS IS" BASIS,
+     WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+     WITHOUT LIMITATION, WARRANTIES THAT THE COVERED CODE IS FREE OF
+     DEFECTS, MERCHANTABLE, FIT FOR A PARTICULAR PURPOSE OR NON-INFRINGING.
+     THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE COVERED CODE
+     IS WITH YOU. SHOULD ANY COVERED CODE PROVE DEFECTIVE IN ANY RESPECT,
+     YOU (NOT THE INITIAL DEVELOPER OR ANY OTHER CONTRIBUTOR) ASSUME THE
+     COST OF ANY NECESSARY SERVICING, REPAIR OR CORRECTION. THIS DISCLAIMER
+     OF WARRANTY CONSTITUTES AN ESSENTIAL PART OF THIS LICENSE. NO USE OF
+     ANY COVERED CODE IS AUTHORIZED HEREUNDER EXCEPT UNDER THIS DISCLAIMER.
+
+8. TERMINATION.
+
+     8.1.  This License and the rights granted hereunder will terminate
+     automatically if You fail to comply with terms herein and fail to cure
+     such breach within 30 days of becoming aware of the breach. All
+     sublicenses to the Covered Code which are properly granted shall
+     survive any termination of this License. Provisions which, by their
+     nature, must remain in effect beyond the termination of this License
+     shall survive.
+
+     8.2.  If You initiate litigation by asserting a patent infringement
+     claim (excluding declatory judgment actions) against Initial Developer
+     or a Contributor (the Initial Developer or Contributor against whom
+     You file such action is referred to as "Participant")  alleging that:
+
+     (a)  such Participant's Contributor Version directly or indirectly
+     infringes any patent, then any and all rights granted by such
+     Participant to You under Sections 2.1 and/or 2.2 of this License
+     shall, upon 60 days notice from Participant terminate prospectively,
+     unless if within 60 days after receipt of notice You either: (i)
+     agree in writing to pay Participant a mutually agreeable reasonable
+     royalty for Your past and future use of Modifications made by such
+     Participant, or (ii) withdraw Your litigation claim with respect to
+     the Contributor Version against such Participant.  If within 60 days
+     of notice, a reasonable royalty and payment arrangement are not
+     mutually agreed upon in writing by the parties or the litigation claim
+     is not withdrawn, the rights granted by Participant to You under
+     Sections 2.1 and/or 2.2 automatically terminate at the expiration of
+     the 60 day notice period specified above.
+
+     (b)  any software, hardware, or device, other than such Participant's
+     Contributor Version, directly or indirectly infringes any patent, then
+     any rights granted to You by such Participant under Sections 2.1(b)
+     and 2.2(b) are revoked effective as of the date You first made, used,
+     sold, distributed, or had made, Modifications made by that
+     Participant.
+
+     8.3.  If You assert a patent infringement claim against Participant
+     alleging that such Participant's Contributor Version directly or
+     indirectly infringes any patent where such claim is resolved (such as
+     by license or settlement) prior to the initiation of patent
+     infringement litigation, then the reasonable value of the licenses
+     granted by such Participant under Sections 2.1 or 2.2 shall be taken
+     into account in determining the amount or value of any payment or
+     license.
+
+     8.4.  In the event of termination under Sections 8.1 or 8.2 above,
+     all end user license agreements (excluding distributors and resellers)
+     which have been validly granted by You or any distributor hereunder
+     prior to termination shall survive termination.
+
+9. LIMITATION OF LIABILITY.
+
+     UNDER NO CIRCUMSTANCES AND UNDER NO LEGAL THEORY, WHETHER TORT
+     (INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE, SHALL YOU, THE INITIAL
+     DEVELOPER, ANY OTHER CONTRIBUTOR, OR ANY DISTRIBUTOR OF COVERED CODE,
+     OR ANY SUPPLIER OF ANY OF SUCH PARTIES, BE LIABLE TO ANY PERSON FOR
+     ANY INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES OF ANY
+     CHARACTER INCLUDING, WITHOUT LIMITATION, DAMAGES FOR LOSS OF GOODWILL,
+     WORK STOPPAGE, COMPUTER FAILURE OR MALFUNCTION, OR ANY AND ALL OTHER
+     COMMERCIAL DAMAGES OR LOSSES, EVEN IF SUCH PARTY SHALL HAVE BEEN
+     INFORMED OF THE POSSIBILITY OF SUCH DAMAGES. THIS LIMITATION OF
+     LIABILITY SHALL NOT APPLY TO LIABILITY FOR DEATH OR PERSONAL INJURY
+     RESULTING FROM SUCH PARTY'S NEGLIGENCE TO THE EXTENT APPLICABLE LAW
+     PROHIBITS SUCH LIMITATION. SOME JURISDICTIONS DO NOT ALLOW THE
+     EXCLUSION OR LIMITATION OF INCIDENTAL OR CONSEQUENTIAL DAMAGES, SO
+     THIS EXCLUSION AND LIMITATION MAY NOT APPLY TO YOU.
+
+10. U.S. GOVERNMENT END USERS.
+
+     The Covered Code is a "commercial item," as that term is defined in
+     48 C.F.R. 2.101 (Oct. 1995), consisting of "commercial computer
+     software" and "commercial computer software documentation," as such
+     terms are used in 48 C.F.R. 12.212 (Sept. 1995). Consistent with 48
+     C.F.R. 12.212 and 48 C.F.R. 227.7202-1 through 227.7202-4 (June 1995),
+     all U.S. Government End Users acquire Covered Code with only those
+     rights set forth herein.
+
+11. MISCELLANEOUS.
+
+     This License represents the complete agreement concerning subject
+     matter hereof. If any provision of this License is held to be
+     unenforceable, such provision shall be reformed only to the extent
+     necessary to make it enforceable. This License shall be governed by
+     California law provisions (except to the extent applicable law, if
+     any, provides otherwise), excluding its conflict-of-law provisions.
+     With respect to disputes in which at least one party is a citizen of,
+     or an entity chartered or registered to do business in the United
+     States of America, any litigation relating to this License shall be
+     subject to the jurisdiction of the Federal Courts of the Northern
+     District of California, with venue lying in Santa Clara County,
+     California, with the losing party responsible for costs, including
+     without limitation, court costs and reasonable attorneys' fees and
+     expenses. The application of the United Nations Convention on
+     Contracts for the International Sale of Goods is expressly excluded.
+     Any law or regulation which provides that the language of a contract
+     shall be construed against the drafter shall not apply to this
+     License.
+
+12. RESPONSIBILITY FOR CLAIMS.
+
+     As between Initial Developer and the Contributors, each party is
+     responsible for claims and damages arising, directly or indirectly,
+     out of its utilization of rights under this License and You agree to
+     work with Initial Developer and Contributors to distribute such
+     responsibility on an equitable basis. Nothing herein is intended or
+     shall be deemed to constitute any admission of liability.
+
+13. MULTIPLE-LICENSED CODE.
+
+     Initial Developer may designate portions of the Covered Code as
+     "Multiple-Licensed".  "Multiple-Licensed" means that the Initial
+     Developer permits you to utilize portions of the Covered Code under
+     Your choice of the MPL or the alternative licenses, if any, specified
+     by the Initial Developer in the file described in Exhibit A.
+
+EXHIBIT A -Mozilla Public License.
+
+     ``The contents of this file are subject to the Mozilla Public License
+     Version 1.1 (the "License"); you may not use this file except in
+     compliance with the License. You may obtain a copy of the License at
+     https://www.mozilla.org/MPL/
+
+     Software distributed under the License is distributed on an "AS IS"
+     basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
+     License for the specific language governing rights and limitations
+     under the License.
+
+     The Original Code is ______________________________________.
+
+     The Initial Developer of the Original Code is ________________________.
+     Portions created by ______________________ are Copyright (C) ______
+     _______________________. All Rights Reserved.
+
+     Contributor(s): ______________________________________.
+
+     Alternatively, the contents of this file may be used under the terms
+     of the _____ license (the  "[___] License"), in which case the
+     provisions of [______] License are applicable instead of those
+     above.  If you wish to allow use of your version of this file only
+     under the terms of the [____] License and not to allow others to use
+     your version of this file under the MPL, indicate your decision by
+     deleting  the provisions above and replace  them with the notice and
+     other provisions required by the [___] License.  If you do not delete
+     the provisions above, a recipient may use your version of this file
+     under either the MPL or the [___] License."
+
+     [NOTE: The text of this Exhibit A may differ slightly from the text of
+     the notices in the Source Code files of the Original Code. You should
+     use the text of this Exhibit A rather than the text found in the
+     Original Code Source Code for Your Modifications.]
diff --git a/LICENSES/preferred/BSD-2-Clause b/LICENSES/preferred/BSD-2-Clause
new file mode 100644
index 000000000000..da366e2ce50b
--- /dev/null
+++ b/LICENSES/preferred/BSD-2-Clause
@@ -0,0 +1,32 @@
+Valid-License-Identifier: BSD-2-Clause
+SPDX-URL: https://spdx.org/licenses/BSD-2-Clause.html
+Usage-Guide:
+  To use the BSD 2-clause "Simplified" License put the following SPDX
+  tag/value pair into a comment according to the placement guidelines in
+  the licensing rules documentation:
+    SPDX-License-Identifier: BSD-2-Clause
+License-Text:
+
+Copyright (c) <year> <owner> . All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice,
+   this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
diff --git a/LICENSES/preferred/BSD-3-Clause b/LICENSES/preferred/BSD-3-Clause
new file mode 100644
index 000000000000..34c7f057c8d5
--- /dev/null
+++ b/LICENSES/preferred/BSD-3-Clause
@@ -0,0 +1,36 @@
+Valid-License-Identifier: BSD-3-Clause
+SPDX-URL: https://spdx.org/licenses/BSD-3-Clause.html
+Usage-Guide:
+  To use the BSD 3-clause "New" or "Revised" License put the following SPDX
+  tag/value pair into a comment according to the placement guidelines in
+  the licensing rules documentation:
+    SPDX-License-Identifier: BSD-3-Clause
+License-Text:
+
+Copyright (c) <year> <owner> . All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice,
+   this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from this
+   software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
diff --git a/LICENSES/preferred/BSD-3-Clause-Clear b/LICENSES/preferred/BSD-3-Clause-Clear
new file mode 100644
index 000000000000..e53b56092b90
--- /dev/null
+++ b/LICENSES/preferred/BSD-3-Clause-Clear
@@ -0,0 +1,41 @@
+Valid-License-Identifier: BSD-3-Clause-Clear
+SPDX-URL: https://spdx.org/licenses/BSD-3-Clause-Clear.html
+Usage-Guide:
+  To use the BSD 3-clause "Clear" License put the following SPDX
+  tag/value pair into a comment according to the placement guidelines in
+  the licensing rules documentation:
+    SPDX-License-Identifier: BSD-3-Clause-Clear
+License-Text:
+
+The Clear BSD License
+
+Copyright (c) [xxxx]-[xxxx] [Owner Organization]
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted (subject to the limitations in the disclaimer
+below) provided that the following conditions are met:
+
+ * Redistributions of source code must retain the above copyright notice,
+   this list of conditions and the following disclaimer.
+
+ * Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+
+ * Neither the name of [Owner Organization] nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+NO EXPRESS OR IMPLIED LICENSES TO ANY PARTY'S PATENT RIGHTS ARE GRANTED BY
+THIS LICENSE. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT
+NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER
+OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
diff --git a/LICENSES/preferred/GPL-2.0 b/LICENSES/preferred/GPL-2.0
new file mode 100644
index 000000000000..b8db91d3a1cb
--- /dev/null
+++ b/LICENSES/preferred/GPL-2.0
@@ -0,0 +1,353 @@
+Valid-License-Identifier: GPL-2.0
+Valid-License-Identifier: GPL-2.0+
+SPDX-URL: https://spdx.org/licenses/GPL-2.0.html
+Usage-Guide:
+  To use this license in source code, put one of the following SPDX
+  tag/value pairs into a comment according to the placement
+  guidelines in the licensing rules documentation.
+  For 'GNU General Public License (GPL) version 2 only' use:
+    SPDX-License-Identifier: GPL-2.0
+  For 'GNU General Public License (GPL) version 2 or any later version' use:
+    SPDX-License-Identifier: GPL-2.0+
+License-Text:
+
+		    GNU GENERAL PUBLIC LICENSE
+		       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+                       51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+			    Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Library General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+		    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+			    NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+		     END OF TERMS AND CONDITIONS
+
+	    How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Library General
+Public License instead of this License.
diff --git a/LICENSES/preferred/LGPL-2.0 b/LICENSES/preferred/LGPL-2.0
new file mode 100644
index 000000000000..957d798fe037
--- /dev/null
+++ b/LICENSES/preferred/LGPL-2.0
@@ -0,0 +1,487 @@
+Valid-License-Identifier: LGPL-2.0
+Valid-License-Identifier: LGPL-2.0+
+SPDX-URL: https://spdx.org/licenses/LGPL-2.0.html
+Usage-Guide:
+  To use this license in source code, put one of the following SPDX
+  tag/value pairs into a comment according to the placement
+  guidelines in the licensing rules documentation.
+  For 'GNU Library General Public License (LGPL) version 2.0 only' use:
+    SPDX-License-Identifier: LGPL-2.0
+  For 'GNU Library General Public License (LGPL) version 2.0 or any later
+  version' use:
+    SPDX-License-Identifier: LGPL-2.0+
+License-Text:
+
+GNU LIBRARY GENERAL PUBLIC LICENSE
+Version 2, June 1991
+
+Copyright (C) 1991 Free Software Foundation, Inc.
+51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA
+
+Everyone is permitted to copy and distribute verbatim copies of this
+license document, but changing it is not allowed.
+
+[This is the first released version of the library GPL. It is numbered 2
+because it goes with version 2 of the ordinary GPL.]
+
+Preamble
+
+The licenses for most software are designed to take away your freedom to
+share and change it. By contrast, the GNU General Public Licenses are
+intended to guarantee your freedom to share and change free software--to
+make sure the software is free for all its users.
+
+This license, the Library General Public License, applies to some specially
+designated Free Software Foundation software, and to any other libraries
+whose authors decide to use it. You can use it for your libraries, too.
+
+When we speak of free software, we are referring to freedom, not price. Our
+General Public Licenses are designed to make sure that you have the freedom
+to distribute copies of free software (and charge for this service if you
+wish), that you receive source code or can get it if you want it, that you
+can change the software or use pieces of it in new free programs; and that
+you know you can do these things.
+
+To protect your rights, we need to make restrictions that forbid anyone to
+deny you these rights or to ask you to surrender the rights. These
+restrictions translate to certain responsibilities for you if you
+distribute copies of the library, or if you modify it.
+
+For example, if you distribute copies of the library, whether gratis or for
+a fee, you must give the recipients all the rights that we gave you. You
+must make sure that they, too, receive or can get the source code. If you
+link a program with the library, you must provide complete object files to
+the recipients so that they can relink them with the library, after making
+changes to the library and recompiling it. And you must show them these
+terms so they know their rights.
+
+Our method of protecting your rights has two steps: (1) copyright the
+library, and (2) offer you this license which gives you legal permission to
+copy, distribute and/or modify the library.
+
+Also, for each distributor's protection, we want to make certain that
+everyone understands that there is no warranty for this free library. If
+the library is modified by someone else and passed on, we want its
+recipients to know that what they have is not the original version, so that
+any problems introduced by others will not reflect on the original authors'
+reputations.
+
+Finally, any free program is threatened constantly by software patents. We
+wish to avoid the danger that companies distributing free software will
+individually obtain patent licenses, thus in effect transforming the
+program into proprietary software. To prevent this, we have made it clear
+that any patent must be licensed for everyone's free use or not licensed at
+all.
+
+Most GNU software, including some libraries, is covered by the ordinary GNU
+General Public License, which was designed for utility programs. This
+license, the GNU Library General Public License, applies to certain
+designated libraries. This license is quite different from the ordinary
+one; be sure to read it in full, and don't assume that anything in it is
+the same as in the ordinary license.
+
+The reason we have a separate public license for some libraries is that
+they blur the distinction we usually make between modifying or adding to a
+program and simply using it. Linking a program with a library, without
+changing the library, is in some sense simply using the library, and is
+analogous to running a utility program or application program. However, in
+a textual and legal sense, the linked executable is a combined work, a
+derivative of the original library, and the ordinary General Public License
+treats it as such.
+
+Because of this blurred distinction, using the ordinary General Public
+License for libraries did not effectively promote software sharing, because
+most developers did not use the libraries. We concluded that weaker
+conditions might promote sharing better.
+
+However, unrestricted linking of non-free programs would deprive the users
+of those programs of all benefit from the free status of the libraries
+themselves. This Library General Public License is intended to permit
+developers of non-free programs to use free libraries, while preserving
+your freedom as a user of such programs to change the free libraries that
+are incorporated in them. (We have not seen how to achieve this as regards
+changes in header files, but we have achieved it as regards changes in the
+actual functions of the Library.) The hope is that this will lead to faster
+development of free libraries.
+
+The precise terms and conditions for copying, distribution and modification
+follow. Pay close attention to the difference between a "work based on the
+library" and a "work that uses the library". The former contains code
+derived from the library, while the latter only works together with the
+library.
+
+Note that it is possible for a library to be covered by the ordinary
+General Public License rather than by this special one.
+
+TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+0. This License Agreement applies to any software library which contains a
+   notice placed by the copyright holder or other authorized party saying
+   it may be distributed under the terms of this Library General Public
+   License (also called "this License"). Each licensee is addressed as
+   "you".
+
+   A "library" means a collection of software functions and/or data
+   prepared so as to be conveniently linked with application programs
+   (which use some of those functions and data) to form executables.
+
+   The "Library", below, refers to any such software library or work which
+   has been distributed under these terms. A "work based on the Library"
+   means either the Library or any derivative work under copyright law:
+   that is to say, a work containing the Library or a portion of it, either
+   verbatim or with modifications and/or translated straightforwardly into
+   another language. (Hereinafter, translation is included without
+   limitation in the term "modification".)
+
+   "Source code" for a work means the preferred form of the work for making
+   modifications to it. For a library, complete source code means all the
+   source code for all modules it contains, plus any associated interface
+   definition files, plus the scripts used to control compilation and
+   installation of the library.
+
+   Activities other than copying, distribution and modification are not
+   covered by this License; they are outside its scope. The act of running
+   a program using the Library is not restricted, and output from such a
+   program is covered only if its contents constitute a work based on the
+   Library (independent of the use of the Library in a tool for writing
+   it). Whether that is true depends on what the Library does and what the
+   program that uses the Library does.
+
+1. You may copy and distribute verbatim copies of the Library's complete
+   source code as you receive it, in any medium, provided that you
+   conspicuously and appropriately publish on each copy an appropriate
+   copyright notice and disclaimer of warranty; keep intact all the notices
+   that refer to this License and to the absence of any warranty; and
+   distribute a copy of this License along with the Library.
+
+   You may charge a fee for the physical act of transferring a copy, and
+   you may at your option offer warranty protection in exchange for a fee.
+
+2. You may modify your copy or copies of the Library or any portion of it,
+   thus forming a work based on the Library, and copy and distribute such
+   modifications or work under the terms of Section 1 above, provided that
+   you also meet all of these conditions:
+
+   a) The modified work must itself be a software library.
+
+   b) You must cause the files modified to carry prominent notices stating
+      that you changed the files and the date of any change.
+
+   c) You must cause the whole of the work to be licensed at no charge to
+      all third parties under the terms of this License.
+
+   d) If a facility in the modified Library refers to a function or a table
+      of data to be supplied by an application program that uses the
+      facility, other than as an argument passed when the facility is
+      invoked, then you must make a good faith effort to ensure that, in
+      the event an application does not supply such function or table, the
+      facility still operates, and performs whatever part of its purpose
+      remains meaningful.
+
+   (For example, a function in a library to compute square roots has a
+   purpose that is entirely well-defined independent of the
+   application. Therefore, Subsection 2d requires that any
+   application-supplied function or table used by this function must be
+   optional: if the application does not supply it, the square root
+   function must still compute square roots.)
+
+   These requirements apply to the modified work as a whole. If
+   identifiable sections of that work are not derived from the Library, and
+   can be reasonably considered independent and separate works in
+   themselves, then this License, and its terms, do not apply to those
+   sections when you distribute them as separate works. But when you
+   distribute the same sections as part of a whole which is a work based on
+   the Library, the distribution of the whole must be on the terms of this
+   License, whose permissions for other licensees extend to the entire
+   whole, and thus to each and every part regardless of who wrote it.
+
+   Thus, it is not the intent of this section to claim rights or contest
+   your rights to work written entirely by you; rather, the intent is to
+   exercise the right to control the distribution of derivative or
+   collective works based on the Library.
+
+   In addition, mere aggregation of another work not based on the Library
+   with the Library (or with a work based on the Library) on a volume of a
+   storage or distribution medium does not bring the other work under the
+   scope of this License.
+
+3. You may opt to apply the terms of the ordinary GNU General Public
+   License instead of this License to a given copy of the Library. To do
+   this, you must alter all the notices that refer to this License, so that
+   they refer to the ordinary GNU General Public License, version 2,
+   instead of to this License. (If a newer version than version 2 of the
+   ordinary GNU General Public License has appeared, then you can specify
+   that version instead if you wish.) Do not make any other change in these
+   notices.
+
+   Once this change is made in a given copy, it is irreversible for that
+   copy, so the ordinary GNU General Public License applies to all
+   subsequent copies and derivative works made from that copy.
+
+   This option is useful when you wish to copy part of the code of the
+   Library into a program that is not a library.
+
+4. You may copy and distribute the Library (or a portion or derivative of
+   it, under Section 2) in object code or executable form under the terms
+   of Sections 1 and 2 above provided that you accompany it with the
+   complete corresponding machine-readable source code, which must be
+   distributed under the terms of Sections 1 and 2 above on a medium
+   customarily used for software interchange.
+
+   If distribution of object code is made by offering access to copy from a
+   designated place, then offering equivalent access to copy the source
+   code from the same place satisfies the requirement to distribute the
+   source code, even though third parties are not compelled to copy the
+   source along with the object code.
+
+5. A program that contains no derivative of any portion of the Library, but
+   is designed to work with the Library by being compiled or linked with
+   it, is called a "work that uses the Library". Such a work, in isolation,
+   is not a derivative work of the Library, and therefore falls outside the
+   scope of this License.
+
+   However, linking a "work that uses the Library" with the Library creates
+   an executable that is a derivative of the Library (because it contains
+   portions of the Library), rather than a "work that uses the
+   library". The executable is therefore covered by this License. Section 6
+   states terms for distribution of such executables.
+
+   When a "work that uses the Library" uses material from a header file
+   that is part of the Library, the object code for the work may be a
+   derivative work of the Library even though the source code is
+   not. Whether this is true is especially significant if the work can be
+   linked without the Library, or if the work is itself a library. The
+   threshold for this to be true is not precisely defined by law.
+
+   If such an object file uses only numerical parameters, data structure
+   layouts and accessors, and small macros and small inline functions (ten
+   lines or less in length), then the use of the object file is
+   unrestricted, regardless of whether it is legally a derivative
+   work. (Executables containing this object code plus portions of the
+   Library will still fall under Section 6.)
+
+   Otherwise, if the work is a derivative of the Library, you may
+   distribute the object code for the work under the terms of Section
+   6. Any executables containing that work also fall under Section 6,
+   whether or not they are linked directly with the Library itself.
+
+6. As an exception to the Sections above, you may also compile or link a
+   "work that uses the Library" with the Library to produce a work
+   containing portions of the Library, and distribute that work under terms
+   of your choice, provided that the terms permit modification of the work
+   for the customer's own use and reverse engineering for debugging such
+   modifications.
+
+   You must give prominent notice with each copy of the work that the
+   Library is used in it and that the Library and its use are covered by
+   this License. You must supply a copy of this License. If the work during
+   execution displays copyright notices, you must include the copyright
+   notice for the Library among them, as well as a reference directing the
+   user to the copy of this License. Also, you must do one of these things:
+
+   a) Accompany the work with the complete corresponding machine-readable
+      source code for the Library including whatever changes were used in
+      the work (which must be distributed under Sections 1 and 2 above);
+      and, if the work is an executable linked with the Library, with the
+      complete machine-readable "work that uses the Library", as object
+      code and/or source code, so that the user can modify the Library and
+      then relink to produce a modified executable containing the modified
+      Library. (It is understood that the user who changes the contents of
+      definitions files in the Library will not necessarily be able to
+      recompile the application to use the modified definitions.)
+
+   b) Accompany the work with a written offer, valid for at least three
+      years, to give the same user the materials specified in Subsection
+      6a, above, for a charge no more than the cost of performing this
+      distribution.
+
+   c) If distribution of the work is made by offering access to copy from a
+      designated place, offer equivalent access to copy the above specified
+      materials from the same place.
+
+   d) Verify that the user has already received a copy of these materials
+      or that you have already sent this user a copy.
+
+   For an executable, the required form of the "work that uses the Library"
+   must include any data and utility programs needed for reproducing the
+   executable from it. However, as a special exception, the source code
+   distributed need not include anything that is normally distributed (in
+   either source or binary form) with the major components (compiler,
+   kernel, and so on) of the operating system on which the executable runs,
+   unless that component itself accompanies the executable.
+
+   It may happen that this requirement contradicts the license restrictions
+   of other proprietary libraries that do not normally accompany the
+   operating system. Such a contradiction means you cannot use both them
+   and the Library together in an executable that you distribute.
+
+7. You may place library facilities that are a work based on the Library
+   side-by-side in a single library together with other library facilities
+   not covered by this License, and distribute such a combined library,
+   provided that the separate distribution of the work based on the Library
+   and of the other library facilities is otherwise permitted, and provided
+   that you do these two things:
+
+   a) Accompany the combined library with a copy of the same work based on
+      the Library, uncombined with any other library facilities. This must
+      be distributed under the terms of the Sections above.
+
+   b) Give prominent notice with the combined library of the fact that part
+      of it is a work based on the Library, and explaining where to find
+      the accompanying uncombined form of the same work.
+
+8. You may not copy, modify, sublicense, link with, or distribute the
+   Library except as expressly provided under this License. Any attempt
+   otherwise to copy, modify, sublicense, link with, or distribute the
+   Library is void, and will automatically terminate your rights under this
+   License. However, parties who have received copies, or rights, from you
+   under this License will not have their licenses terminated so long as
+   such parties remain in full compliance.
+
+9. You are not required to accept this License, since you have not signed
+   it. However, nothing else grants you permission to modify or distribute
+   the Library or its derivative works. These actions are prohibited by law
+   if you do not accept this License. Therefore, by modifying or
+   distributing the Library (or any work based on the Library), you
+   indicate your acceptance of this License to do so, and all its terms and
+   conditions for copying, distributing or modifying the Library or works
+   based on it.
+
+10. Each time you redistribute the Library (or any work based on the
+    Library), the recipient automatically receives a license from the
+    original licensor to copy, distribute, link with or modify the Library
+    subject to these terms and conditions. You may not impose any further
+    restrictions on the recipients' exercise of the rights granted
+    herein. You are not responsible for enforcing compliance by third
+    parties to this License.
+
+11. If, as a consequence of a court judgment or allegation of patent
+    infringement or for any other reason (not limited to patent issues),
+    conditions are imposed on you (whether by court order, agreement or
+    otherwise) that contradict the conditions of this License, they do not
+    excuse you from the conditions of this License. If you cannot
+    distribute so as to satisfy simultaneously your obligations under this
+    License and any other pertinent obligations, then as a consequence you
+    may not distribute the Library at all. For example, if a patent license
+    would not permit royalty-free redistribution of the Library by all
+    those who receive copies directly or indirectly through you, then the
+    only way you could satisfy both it and this License would be to refrain
+    entirely from distribution of the Library.
+
+    If any portion of this section is held invalid or unenforceable under
+    any particular circumstance, the balance of the section is intended to
+    apply, and the section as a whole is intended to apply in other
+    circumstances.
+
+    It is not the purpose of this section to induce you to infringe any
+    patents or other property right claims or to contest validity of any
+    such claims; this section has the sole purpose of protecting the
+    integrity of the free software distribution system which is implemented
+    by public license practices. Many people have made generous
+    contributions to the wide range of software distributed through that
+    system in reliance on consistent application of that system; it is up
+    to the author/donor to decide if he or she is willing to distribute
+    software through any other system and a licensee cannot impose that
+    choice.
+
+    This section is intended to make thoroughly clear what is believed to
+    be a consequence of the rest of this License.
+
+12. If the distribution and/or use of the Library is restricted in certain
+    countries either by patents or by copyrighted interfaces, the original
+    copyright holder who places the Library under this License may add an
+    explicit geographical distribution limitation excluding those
+    countries, so that distribution is permitted only in or among countries
+    not thus excluded. In such case, this License incorporates the
+    limitation as if written in the body of this License.
+
+13. The Free Software Foundation may publish revised and/or new versions of
+    the Library General Public License from time to time. Such new versions
+    will be similar in spirit to the present version, but may differ in
+    detail to address new problems or concerns.
+
+    Each version is given a distinguishing version number. If the Library
+    specifies a version number of this License which applies to it and "any
+    later version", you have the option of following the terms and
+    conditions either of that version or of any later version published by
+    the Free Software Foundation. If the Library does not specify a license
+    version number, you may choose any version ever published by the Free
+    Software Foundation.
+
+14. If you wish to incorporate parts of the Library into other free
+    programs whose distribution conditions are incompatible with these,
+    write to the author to ask for permission. For software which is
+    copyrighted by the Free Software Foundation, write to the Free Software
+    Foundation; we sometimes make exceptions for this. Our decision will be
+    guided by the two goals of preserving the free status of all
+    derivatives of our free software and of promoting the sharing and reuse
+    of software generally.
+
+NO WARRANTY
+
+15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+    FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
+    OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+    PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER
+    EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+    WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE
+    ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE LIBRARY IS WITH
+    YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL
+    NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+    WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+    REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU FOR
+    DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL
+    DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE LIBRARY
+    (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED
+    INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF
+    THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF SUCH HOLDER OR
+    OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
+
+END OF TERMS AND CONDITIONS
+
+How to Apply These Terms to Your New Libraries
+
+If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change. You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+To apply these terms, attach the following notices to the library. It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+one line to give the library's name and an idea of what it does.
+Copyright (C) year name of author
+
+This library is free software; you can redistribute it and/or modify it
+under the terms of the GNU Library General Public License as published by
+the Free Software Foundation; either version 2 of the License, or (at your
+option) any later version.
+
+This library is distributed in the hope that it will be useful, but WITHOUT
+ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+FITNESS FOR A PARTICULAR PURPOSE. See the GNU Library General Public
+License for more details.
+
+You should have received a copy of the GNU Library General Public License
+along with this library; if not, write to the Free Software Foundation,
+Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary. Here is a sample; alter the names:
+
+Yoyodyne, Inc., hereby disclaims all copyright interest in
+the library `Frob' (a library for tweaking knobs) written
+by James Random Hacker.
+
+signature of Ty Coon, 1 April 1990
+Ty Coon, President of Vice
+
+That's all there is to it!
diff --git a/LICENSES/preferred/LGPL-2.1 b/LICENSES/preferred/LGPL-2.1
new file mode 100644
index 000000000000..27bb4342a3e8
--- /dev/null
+++ b/LICENSES/preferred/LGPL-2.1
@@ -0,0 +1,503 @@
+Valid-License-Identifier: LGPL-2.1
+Valid-License-Identifier: LGPL-2.1+
+SPDX-URL: https://spdx.org/licenses/LGPL-2.1.html
+Usage-Guide:
+  To use this license in source code, put one of the following SPDX
+  tag/value pairs into a comment according to the placement
+  guidelines in the licensing rules documentation.
+  For 'GNU Lesser General Public License (LGPL) version 2.1 only' use:
+    SPDX-License-Identifier: LGPL-2.1
+  For 'GNU Lesser General Public License (LGPL) version 2.1 or any later
+  version' use:
+    SPDX-License-Identifier: LGPL-2.1+
+License-Text:
+
+GNU LESSER GENERAL PUBLIC LICENSE
+Version 2.1, February 1999
+
+Copyright (C) 1991, 1999 Free Software Foundation, Inc.
+51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+
+Everyone is permitted to copy and distribute verbatim copies of this
+license document, but changing it is not allowed.
+
+[This is the first released version of the Lesser GPL. It also counts as
+the successor of the GNU Library Public License, version 2, hence the
+version number 2.1.]
+
+Preamble
+
+The licenses for most software are designed to take away your freedom to
+share and change it. By contrast, the GNU General Public Licenses are
+intended to guarantee your freedom to share and change free software--to
+make sure the software is free for all its users.
+
+This license, the Lesser General Public License, applies to some specially
+designated software packages--typically libraries--of the Free Software
+Foundation and other authors who decide to use it. You can use it too, but
+we suggest you first think carefully about whether this license or the
+ordinary General Public License is the better strategy to use in any
+particular case, based on the explanations below.
+
+When we speak of free software, we are referring to freedom of use, not
+price. Our General Public Licenses are designed to make sure that you have
+the freedom to distribute copies of free software (and charge for this
+service if you wish); that you receive source code or can get it if you
+want it; that you can change the software and use pieces of it in new free
+programs; and that you are informed that you can do these things.
+
+To protect your rights, we need to make restrictions that forbid
+distributors to deny you these rights or to ask you to surrender these
+rights. These restrictions translate to certain responsibilities for you if
+you distribute copies of the library or if you modify it.
+
+For example, if you distribute copies of the library, whether gratis or for
+a fee, you must give the recipients all the rights that we gave you. You
+must make sure that they, too, receive or can get the source code. If you
+link other code with the library, you must provide complete object files to
+the recipients, so that they can relink them with the library after making
+changes to the library and recompiling it. And you must show them these
+terms so they know their rights.
+
+We protect your rights with a two-step method: (1) we copyright the
+library, and (2) we offer you this license, which gives you legal
+permission to copy, distribute and/or modify the library.
+
+To protect each distributor, we want to make it very clear that there is no
+warranty for the free library. Also, if the library is modified by someone
+else and passed on, the recipients should know that what they have is not
+the original version, so that the original author's reputation will not be
+affected by problems that might be introduced by others.
+
+Finally, software patents pose a constant threat to the existence of any
+free program. We wish to make sure that a company cannot effectively
+restrict the users of a free program by obtaining a restrictive license
+from a patent holder. Therefore, we insist that any patent license obtained
+for a version of the library must be consistent with the full freedom of
+use specified in this license.
+
+Most GNU software, including some libraries, is covered by the ordinary GNU
+General Public License. This license, the GNU Lesser General Public
+License, applies to certain designated libraries, and is quite different
+from the ordinary General Public License. We use this license for certain
+libraries in order to permit linking those libraries into non-free
+programs.
+
+When a program is linked with a library, whether statically or using a
+shared library, the combination of the two is legally speaking a combined
+work, a derivative of the original library. The ordinary General Public
+License therefore permits such linking only if the entire combination fits
+its criteria of freedom. The Lesser General Public License permits more lax
+criteria for linking other code with the library.
+
+We call this license the "Lesser" General Public License because it does
+Less to protect the user's freedom than the ordinary General Public
+License. It also provides other free software developers Less of an
+advantage over competing non-free programs. These disadvantages are the
+reason we use the ordinary General Public License for many
+libraries. However, the Lesser license provides advantages in certain
+special circumstances.
+
+For example, on rare occasions, there may be a special need to encourage
+the widest possible use of a certain library, so that it becomes a de-facto
+standard. To achieve this, non-free programs must be allowed to use the
+library. A more frequent case is that a free library does the same job as
+widely used non-free libraries. In this case, there is little to gain by
+limiting the free library to free software only, so we use the Lesser
+General Public License.
+
+In other cases, permission to use a particular library in non-free programs
+enables a greater number of people to use a large body of free
+software. For example, permission to use the GNU C Library in non-free
+programs enables many more people to use the whole GNU operating system, as
+well as its variant, the GNU/Linux operating system.
+
+Although the Lesser General Public License is Less protective of the users'
+freedom, it does ensure that the user of a program that is linked with the
+Library has the freedom and the wherewithal to run that program using a
+modified version of the Library.
+
+The precise terms and conditions for copying, distribution and modification
+follow. Pay close attention to the difference between a "work based on the
+library" and a "work that uses the library". The former contains code
+derived from the library, whereas the latter must be combined with the
+library in order to run.
+
+TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+0. This License Agreement applies to any software library or other program
+   which contains a notice placed by the copyright holder or other
+   authorized party saying it may be distributed under the terms of this
+   Lesser General Public License (also called "this License"). Each
+   licensee is addressed as "you".
+
+   A "library" means a collection of software functions and/or data
+   prepared so as to be conveniently linked with application programs
+   (which use some of those functions and data) to form executables.
+
+   The "Library", below, refers to any such software library or work which
+   has been distributed under these terms. A "work based on the Library"
+   means either the Library or any derivative work under copyright law:
+   that is to say, a work containing the Library or a portion of it, either
+   verbatim or with modifications and/or translated straightforwardly into
+   another language. (Hereinafter, translation is included without
+   limitation in the term "modification".)
+
+   "Source code" for a work means the preferred form of the work for making
+   modifications to it. For a library, complete source code means all the
+   source code for all modules it contains, plus any associated interface
+   definition files, plus the scripts used to control compilation and
+   installation of the library.
+
+    Activities other than copying, distribution and modification are not
+    covered by this License; they are outside its scope. The act of running
+    a program using the Library is not restricted, and output from such a
+    program is covered only if its contents constitute a work based on the
+    Library (independent of the use of the Library in a tool for writing
+    it). Whether that is true depends on what the Library does and what the
+    program that uses the Library does.
+
+1. You may copy and distribute verbatim copies of the Library's complete
+   source code as you receive it, in any medium, provided that you
+   conspicuously and appropriately publish on each copy an appropriate
+   copyright notice and disclaimer of warranty; keep intact all the notices
+   that refer to this License and to the absence of any warranty; and
+   distribute a copy of this License along with the Library.
+
+   You may charge a fee for the physical act of transferring a copy, and
+   you may at your option offer warranty protection in exchange for a fee.
+
+2. You may modify your copy or copies of the Library or any portion of it,
+   thus forming a work based on the Library, and copy and distribute such
+   modifications or work under the terms of Section 1 above, provided that
+   you also meet all of these conditions:
+
+   a) The modified work must itself be a software library.
+
+   b) You must cause the files modified to carry prominent notices stating
+      that you changed the files and the date of any change.
+
+   c) You must cause the whole of the work to be licensed at no charge to
+      all third parties under the terms of this License.
+
+   d) If a facility in the modified Library refers to a function or a table
+      of data to be supplied by an application program that uses the
+      facility, other than as an argument passed when the facility is
+      invoked, then you must make a good faith effort to ensure that, in
+      the event an application does not supply such function or table, the
+      facility still operates, and performs whatever part of its purpose
+      remains meaningful.
+
+   (For example, a function in a library to compute square roots has a
+    purpose that is entirely well-defined independent of the
+    application. Therefore, Subsection 2d requires that any
+    application-supplied function or table used by this function must be
+    optional: if the application does not supply it, the square root
+    function must still compute square roots.)
+
+   These requirements apply to the modified work as a whole. If
+   identifiable sections of that work are not derived from the Library, and
+   can be reasonably considered independent and separate works in
+   themselves, then this License, and its terms, do not apply to those
+   sections when you distribute them as separate works. But when you
+   distribute the same sections as part of a whole which is a work based on
+   the Library, the distribution of the whole must be on the terms of this
+   License, whose permissions for other licensees extend to the entire
+   whole, and thus to each and every part regardless of who wrote it.
+
+   Thus, it is not the intent of this section to claim rights or contest
+   your rights to work written entirely by you; rather, the intent is to
+   exercise the right to control the distribution of derivative or
+   collective works based on the Library.
+
+   In addition, mere aggregation of another work not based on the Library
+   with the Library (or with a work based on the Library) on a volume of a
+   storage or distribution medium does not bring the other work under the
+   scope of this License.
+
+3. You may opt to apply the terms of the ordinary GNU General Public
+   License instead of this License to a given copy of the Library. To do
+   this, you must alter all the notices that refer to this License, so that
+   they refer to the ordinary GNU General Public License, version 2,
+   instead of to this License. (If a newer version than version 2 of the
+   ordinary GNU General Public License has appeared, then you can specify
+   that version instead if you wish.) Do not make any other change in these
+   notices.
+
+   Once this change is made in a given copy, it is irreversible for that
+   copy, so the ordinary GNU General Public License applies to all
+   subsequent copies and derivative works made from that copy.
+
+   This option is useful when you wish to copy part of the code of the
+   Library into a program that is not a library.
+
+4. You may copy and distribute the Library (or a portion or derivative of
+   it, under Section 2) in object code or executable form under the terms
+   of Sections 1 and 2 above provided that you accompany it with the
+   complete corresponding machine-readable source code, which must be
+   distributed under the terms of Sections 1 and 2 above on a medium
+   customarily used for software interchange.
+
+   If distribution of object code is made by offering access to copy from a
+   designated place, then offering equivalent access to copy the source
+   code from the same place satisfies the requirement to distribute the
+   source code, even though third parties are not compelled to copy the
+   source along with the object code.
+
+5. A program that contains no derivative of any portion of the Library, but
+   is designed to work with the Library by being compiled or linked with
+   it, is called a "work that uses the Library". Such a work, in isolation,
+   is not a derivative work of the Library, and therefore falls outside the
+   scope of this License.
+
+   However, linking a "work that uses the Library" with the Library creates
+   an executable that is a derivative of the Library (because it contains
+   portions of the Library), rather than a "work that uses the
+   library". The executable is therefore covered by this License. Section 6
+   states terms for distribution of such executables.
+
+   When a "work that uses the Library" uses material from a header file
+   that is part of the Library, the object code for the work may be a
+   derivative work of the Library even though the source code is
+   not. Whether this is true is especially significant if the work can be
+   linked without the Library, or if the work is itself a library. The
+   threshold for this to be true is not precisely defined by law.
+
+   If such an object file uses only numerical parameters, data structure
+   layouts and accessors, and small macros and small inline functions (ten
+   lines or less in length), then the use of the object file is
+   unrestricted, regardless of whether it is legally a derivative
+   work. (Executables containing this object code plus portions of the
+   Library will still fall under Section 6.)
+
+   Otherwise, if the work is a derivative of the Library, you may
+   distribute the object code for the work under the terms of Section
+   6. Any executables containing that work also fall under Section 6,
+   whether or not they are linked directly with the Library itself.
+
+6. As an exception to the Sections above, you may also combine or link a
+   "work that uses the Library" with the Library to produce a work
+   containing portions of the Library, and distribute that work under terms
+   of your choice, provided that the terms permit modification of the work
+   for the customer's own use and reverse engineering for debugging such
+   modifications.
+
+   You must give prominent notice with each copy of the work that the
+   Library is used in it and that the Library and its use are covered by
+   this License. You must supply a copy of this License. If the work during
+   execution displays copyright notices, you must include the copyright
+   notice for the Library among them, as well as a reference directing the
+   user to the copy of this License. Also, you must do one of these things:
+
+   a) Accompany the work with the complete corresponding machine-readable
+      source code for the Library including whatever changes were used in
+      the work (which must be distributed under Sections 1 and 2 above);
+      and, if the work is an executable linked with the Library, with the
+      complete machine-readable "work that uses the Library", as object
+      code and/or source code, so that the user can modify the Library and
+      then relink to produce a modified executable containing the modified
+      Library. (It is understood that the user who changes the contents of
+      definitions files in the Library will not necessarily be able to
+      recompile the application to use the modified definitions.)
+
+   b) Use a suitable shared library mechanism for linking with the
+      Library. A suitable mechanism is one that (1) uses at run time a copy
+      of the library already present on the user's computer system, rather
+      than copying library functions into the executable, and (2) will
+      operate properly with a modified version of the library, if the user
+      installs one, as long as the modified version is interface-compatible
+      with the version that the work was made with.
+
+   c) Accompany the work with a written offer, valid for at least three
+      years, to give the same user the materials specified in Subsection
+      6a, above, for a charge no more than the cost of performing this
+      distribution.
+
+   d) If distribution of the work is made by offering access to copy from a
+      designated place, offer equivalent access to copy the above specified
+      materials from the same place.
+
+   e) Verify that the user has already received a copy of these materials
+      or that you have already sent this user a copy.
+
+   For an executable, the required form of the "work that uses the Library"
+   must include any data and utility programs needed for reproducing the
+   executable from it. However, as a special exception, the materials to be
+   distributed need not include anything that is normally distributed (in
+   either source or binary form) with the major components (compiler,
+   kernel, and so on) of the operating system on which the executable runs,
+   unless that component itself accompanies the executable.
+
+   It may happen that this requirement contradicts the license restrictions
+   of other proprietary libraries that do not normally accompany the
+   operating system. Such a contradiction means you cannot use both them
+   and the Library together in an executable that you distribute.
+
+7. You may place library facilities that are a work based on the Library
+   side-by-side in a single library together with other library facilities
+   not covered by this License, and distribute such a combined library,
+   provided that the separate distribution of the work based on the Library
+   and of the other library facilities is otherwise permitted, and provided
+   that you do these two things:
+
+   a) Accompany the combined library with a copy of the same work based on
+      the Library, uncombined with any other library facilities. This must
+      be distributed under the terms of the Sections above.
+
+   b) Give prominent notice with the combined library of the fact that part
+      of it is a work based on the Library, and explaining where to find
+      the accompanying uncombined form of the same work.
+
+8. You may not copy, modify, sublicense, link with, or distribute the
+   Library except as expressly provided under this License. Any attempt
+   otherwise to copy, modify, sublicense, link with, or distribute the
+   Library is void, and will automatically terminate your rights under this
+   License. However, parties who have received copies, or rights, from you
+   under this License will not have their licenses terminated so long as
+   such parties remain in full compliance.
+
+9. You are not required to accept this License, since you have not signed
+   it. However, nothing else grants you permission to modify or distribute
+   the Library or its derivative works. These actions are prohibited by law
+   if you do not accept this License. Therefore, by modifying or
+   distributing the Library (or any work based on the Library), you
+   indicate your acceptance of this License to do so, and all its terms and
+   conditions for copying, distributing or modifying the Library or works
+   based on it.
+
+10. Each time you redistribute the Library (or any work based on the
+    Library), the recipient automatically receives a license from the
+    original licensor to copy, distribute, link with or modify the Library
+    subject to these terms and conditions. You may not impose any further
+    restrictions on the recipients' exercise of the rights granted
+    herein. You are not responsible for enforcing compliance by third
+    parties with this License.
+
+11. If, as a consequence of a court judgment or allegation of patent
+    infringement or for any other reason (not limited to patent issues),
+    conditions are imposed on you (whether by court order, agreement or
+    otherwise) that contradict the conditions of this License, they do not
+    excuse you from the conditions of this License. If you cannot
+    distribute so as to satisfy simultaneously your obligations under this
+    License and any other pertinent obligations, then as a consequence you
+    may not distribute the Library at all. For example, if a patent license
+    would not permit royalty-free redistribution of the Library by all
+    those who receive copies directly or indirectly through you, then the
+    only way you could satisfy both it and this License would be to refrain
+    entirely from distribution of the Library.
+
+    If any portion of this section is held invalid or unenforceable under
+    any particular circumstance, the balance of the section is intended to
+    apply, and the section as a whole is intended to apply in other
+    circumstances.
+
+    It is not the purpose of this section to induce you to infringe any
+    patents or other property right claims or to contest validity of any
+    such claims; this section has the sole purpose of protecting the
+    integrity of the free software distribution system which is implemented
+    by public license practices. Many people have made generous
+    contributions to the wide range of software distributed through that
+    system in reliance on consistent application of that system; it is up
+    to the author/donor to decide if he or she is willing to distribute
+    software through any other system and a licensee cannot impose that
+    choice.
+
+    This section is intended to make thoroughly clear what is believed to
+    be a consequence of the rest of this License.
+
+12. If the distribution and/or use of the Library is restricted in certain
+    countries either by patents or by copyrighted interfaces, the original
+    copyright holder who places the Library under this License may add an
+    explicit geographical distribution limitation excluding those
+    countries, so that distribution is permitted only in or among countries
+    not thus excluded. In such case, this License incorporates the
+    limitation as if written in the body of this License.
+
+13. The Free Software Foundation may publish revised and/or new versions of
+    the Lesser General Public License from time to time. Such new versions
+    will be similar in spirit to the present version, but may differ in
+    detail to address new problems or concerns.
+
+    Each version is given a distinguishing version number. If the Library
+    specifies a version number of this License which applies to it and "any
+    later version", you have the option of following the terms and
+    conditions either of that version or of any later version published by
+    the Free Software Foundation. If the Library does not specify a license
+    version number, you may choose any version ever published by the Free
+    Software Foundation.
+
+14. If you wish to incorporate parts of the Library into other free
+    programs whose distribution conditions are incompatible with these,
+    write to the author to ask for permission. For software which is
+    copyrighted by the Free Software Foundation, write to the Free Software
+    Foundation; we sometimes make exceptions for this. Our decision will be
+    guided by the two goals of preserving the free status of all
+    derivatives of our free software and of promoting the sharing and reuse
+    of software generally.
+
+NO WARRANTY
+
+15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+    FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
+    OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+    PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER
+    EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+    WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE
+    ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE LIBRARY IS WITH
+    YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL
+    NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+    WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+    REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU FOR
+    DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL
+    DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE LIBRARY
+    (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED
+    INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF
+    THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF SUCH HOLDER OR
+    OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
+
+END OF TERMS AND CONDITIONS
+
+How to Apply These Terms to Your New Libraries
+
+If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change. You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+To apply these terms, attach the following notices to the library. It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+one line to give the library's name and an idea of what it does.
+Copyright (C) year name of author
+
+This library is free software; you can redistribute it and/or modify it
+under the terms of the GNU Lesser General Public License as published by
+the Free Software Foundation; either version 2.1 of the License, or (at
+your option) any later version.
+
+This library is distributed in the hope that it will be useful, but WITHOUT
+ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License
+for more details.
+
+You should have received a copy of the GNU Lesser General Public License
+along with this library; if not, write to the Free Software Foundation,
+Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA Also add
+information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary. Here is a sample; alter the names:
+
+Yoyodyne, Inc., hereby disclaims all copyright interest in
+the library `Frob' (a library for tweaking knobs) written
+by James Random Hacker.
+
+signature of Ty Coon, 1 April 1990
+Ty Coon, President of Vice
+That's all there is to it!
diff --git a/LICENSES/preferred/MIT b/LICENSES/preferred/MIT
new file mode 100644
index 000000000000..f33a68ceb3ea
--- /dev/null
+++ b/LICENSES/preferred/MIT
@@ -0,0 +1,30 @@
+Valid-License-Identifier: MIT
+SPDX-URL: https://spdx.org/licenses/MIT.html
+Usage-Guide:
+  To use the MIT License put the following SPDX tag/value pair into a
+  comment according to the placement guidelines in the licensing rules
+  documentation:
+    SPDX-License-Identifier: MIT
+License-Text:
+
+MIT License
+
+Copyright (c) <year> <copyright holders>
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of this software and associated documentation files (the "Software"),
+to deal in the Software without restriction, including without limitation
+the rights to use, copy, modify, merge, publish, distribute, sublicense,
+and/or sell copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
diff --git a/MAINTAINERS b/MAINTAINERS
index aa71ab52fd76..1dc846d0add6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -62,7 +62,15 @@ trivial patch so apply some common sense.
 
 7.	When sending security related changes or reports to a maintainer
 	please Cc: security@kernel.org, especially if the maintainer
-	does not respond.
+	does not respond. Please keep in mind that the security team is
+	a small set of people who can be efficient only when working on
+	verified bugs. Please only Cc: this list when you have identified
+	that the bug would present a short-term risk to other users if it
+	were publicly disclosed. For example, reports of address leaks do
+	not represent an immediate threat and are better handled publicly,
+	and ideally, should come with a patch proposal. Please do not send
+	automated reports to this list either. Such bugs will be handled
+	better and faster in the usual public places.
 
 8.	Happy hacking.
 
@@ -262,6 +270,7 @@ ACCES 104-QUAD-8 IIO DRIVER
 M:	William Breathitt Gray <vilhelm.gray@gmail.com>
 L:	linux-iio@vger.kernel.org
 S:	Maintained
+F:	Documentation/ABI/testing/sysfs-bus-iio-counter-104-quad-8
 F:	drivers/iio/counter/104-quad-8.c
 
 ACCES PCI-IDIO-16 GPIO DRIVER
@@ -270,6 +279,12 @@ L:	linux-gpio@vger.kernel.org
 S:	Maintained
 F:	drivers/gpio/gpio-pci-idio-16.c
 
+ACCES PCIe-IDIO-24 GPIO DRIVER
+M:	William Breathitt Gray <vilhelm.gray@gmail.com>
+L:	linux-gpio@vger.kernel.org
+S:	Maintained
+F:	drivers/gpio/gpio-pcie-idio-24.c
+
 ACENIC DRIVER
 M:	Jes Sorensen <jes@trained-monkey.org>
 L:	linux-acenic@sunsite.dk
@@ -321,7 +336,7 @@ F:	drivers/acpi/apei/
 
 ACPI COMPONENT ARCHITECTURE (ACPICA)
 M:	Robert Moore <robert.moore@intel.com>
-M:	Lv Zheng <lv.zheng@intel.com>
+M:	Erik Schmauss <erik.schmauss@intel.com>
 M:	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
 L:	linux-acpi@vger.kernel.org
 L:	devel@acpica.org
@@ -554,13 +569,13 @@ S:	Orphan
 F:	Documentation/filesystems/affs.txt
 F:	fs/affs/
 
-AFS FILESYSTEM & AF_RXRPC SOCKET DOMAIN
+AFS FILESYSTEM
 M:	David Howells <dhowells@redhat.com>
 L:	linux-afs@lists.infradead.org
 S:	Supported
 F:	fs/afs/
-F:	include/net/af_rxrpc.h
-F:	net/rxrpc/af_rxrpc.c
+F:	include/trace/events/afs.h
+F:	Documentation/filesystems/afs.txt
 W:	https://www.infradead.org/~dhowells/kafs/
 
 AGPGART DRIVER
@@ -845,6 +860,8 @@ M:	Michael Hennerich <Michael.Hennerich@analog.com>
 W:	http://wiki.analog.com/
 W:	http://ez.analog.com/community/linux-device-drivers
 S:	Supported
+F:	Documentation/ABI/testing/sysfs-bus-iio-frequency-ad9523
+F:	Documentation/ABI/testing/sysfs-bus-iio-frequency-adf4350
 F:	drivers/iio/*/ad*
 F:	drivers/iio/adc/ltc2497*
 X:	drivers/iio/*/adjd*
@@ -859,13 +876,20 @@ F:	kernel/configs/android*
 ANDROID DRIVERS
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 M:	Arve Hjønnevåg <arve@android.com>
-M:	Riley Andrews <riandrews@android.com>
+M:	Todd Kjos <tkjos@android.com>
+M:	Martijn Coenen <maco@android.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging.git
 L:	devel@driverdev.osuosl.org
 S:	Supported
 F:	drivers/android/
 F:	drivers/staging/android/
 
+ANDROID GOLDFISH PIC DRIVER
+M:	Miodrag Dinic <miodrag.dinic@mips.com>
+S:	Supported
+F:	Documentation/devicetree/bindings/interrupt-controller/google,goldfish-pic.txt
+F:	drivers/irqchip/irq-goldfish-pic.c
+
 ANDROID GOLDFISH RTC DRIVER
 M:	Miodrag Dinic <miodrag.dinic@mips.com>
 S:	Supported
@@ -1254,6 +1278,12 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/net/ethernet/cavium/thunder/
 
+ARM/CIRRUS LOGIC BK3 MACHINE SUPPORT
+M:	Lukasz Majewski <lukma@denx.de>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/mach-ep93xx/ts72xx.c
+
 ARM/CIRRUS LOGIC CLPS711X ARM ARCHITECTURE
 M:	Alexander Shiyan <shc_work@mail.ru>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1312,7 +1342,8 @@ F:	tools/perf/arch/arm/util/pmu.c
 F:	tools/perf/arch/arm/util/auxtrace.c
 F:	tools/perf/arch/arm/util/cs-etm.c
 F:	tools/perf/arch/arm/util/cs-etm.h
-F:	tools/perf/util/cs-etm.h
+F:	tools/perf/util/cs-etm.*
+F:	tools/perf/util/cs-etm-decoder/*
 
 ARM/CORGI MACHINE SUPPORT
 M:	Richard Purdie <rpurdie@rpsys.net>
@@ -1326,8 +1357,10 @@ T:	git git://github.com/ulli-kroll/linux.git
 S:	Maintained
 F:	Documentation/devicetree/bindings/arm/gemini.txt
 F:	Documentation/devicetree/bindings/pinctrl/cortina,gemini-pinctrl.txt
+F:	Documentation/devicetree/bindings/net/cortina,gemini-ethernet.txt
 F:	Documentation/devicetree/bindings/rtc/faraday,ftrtc010.txt
 F:	arch/arm/mach-gemini/
+F:	drivers/net/ethernet/cortina/gemini/*
 F:	drivers/pinctrl/pinctrl-gemini.c
 F:	drivers/rtc/rtc-ftrtc010.c
 
@@ -1582,6 +1615,7 @@ F:	arch/arm/boot/dts/kirkwood*
 F:	arch/arm/configs/mvebu_*_defconfig
 F:	arch/arm/mach-mvebu/
 F:	arch/arm64/boot/dts/marvell/armada*
+F:	drivers/cpufreq/armada-37xx-cpufreq.c
 F:	drivers/cpufreq/mvebu-cpufreq.c
 F:	drivers/irqchip/irq-armada-370-xp.c
 F:	drivers/irqchip/irq-mvebu-*
@@ -1634,14 +1668,38 @@ ARM/NEC MOBILEPRO 900/c MACHINE SUPPORT
 M:	Michael Petchkovsky <mkpetch@internode.on.net>
 S:	Maintained
 
-ARM/NOMADIK ARCHITECTURE
-M:	Alessandro Rubini <rubini@unipv.it>
+ARM/NOMADIK/U300/Ux500 ARCHITECTURES
 M:	Linus Walleij <linus.walleij@linaro.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-nomadik/
-F:	drivers/pinctrl/nomadik/
+F:	arch/arm/mach-u300/
+F:	arch/arm/mach-ux500/
+F:	arch/arm/boot/dts/ste-*
+F:	drivers/clk/clk-nomadik.c
+F:	drivers/clk/clk-u300.c
+F:	drivers/clocksource/clksrc-dbx500-prcmu.c
+F:	drivers/clocksource/timer-u300.c
+F:	drivers/dma/coh901318*
+F:	drivers/dma/ste_dma40*
+F:	drivers/hwspinlock/u8500_hsem.c
 F:	drivers/i2c/busses/i2c-nomadik.c
+F:	drivers/i2c/busses/i2c-stu300.c
+F:	drivers/mfd/ab3100*
+F:	drivers/mfd/ab8500*
+F:	drivers/mfd/abx500*
+F:	drivers/mfd/dbx500*
+F:	drivers/mfd/db8500*
+F:	drivers/pinctrl/nomadik/
+F:	drivers/pinctrl/pinctrl-coh901*
+F:	drivers/pinctrl/pinctrl-u300.c
+F:	drivers/rtc/rtc-ab3100.c
+F:	drivers/rtc/rtc-ab8500.c
+F:	drivers/rtc/rtc-coh901331.c
+F:	drivers/rtc/rtc-pl031.c
+F:	drivers/watchdog/coh901327_wdt.c
+F:	Documentation/devicetree/bindings/arm/ste-*
+F:	Documentation/devicetree/bindings/arm/ux500/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-nomadik.git
 
 ARM/NUVOTON W90X900 ARM ARCHITECTURE
@@ -1955,9 +2013,10 @@ N:	stm32
 F:	drivers/clocksource/armv7m_systick.c
 
 ARM/TANGO ARCHITECTURE
-M:	Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
+M:	Marc Gonzalez <marc.w.gonzalez@free.fr>
+M:	Mans Rullgard <mans@mansr.com>
 L:	linux-arm-kernel@lists.infradead.org
-S:	Maintained
+S:	Odd Fixes
 N:	tango
 
 ARM/TECHNOLOGIC SYSTEMS TS7250 MACHINE SUPPORT
@@ -2021,21 +2080,6 @@ M:	Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
 M:	Dirk Opfer <dirk@opfer-online.de>
 S:	Maintained
 
-ARM/U300 MACHINE SUPPORT
-M:	Linus Walleij <linus.walleij@linaro.org>
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
-F:	arch/arm/mach-u300/
-F:	drivers/clocksource/timer-u300.c
-F:	drivers/i2c/busses/i2c-stu300.c
-F:	drivers/rtc/rtc-coh901331.c
-F:	drivers/watchdog/coh901327_wdt.c
-F:	drivers/dma/coh901318*
-F:	drivers/mfd/ab3100*
-F:	drivers/rtc/rtc-ab3100.c
-F:	drivers/rtc/rtc-coh901331.c
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-stericsson.git
-
 ARM/UNIPHIER ARCHITECTURE
 M:	Masahiro Yamada <yamada.masahiro@socionext.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -2046,7 +2090,7 @@ F:	arch/arm/boot/dts/uniphier*
 F:	arch/arm/include/asm/hardware/cache-uniphier.h
 F:	arch/arm/mach-uniphier/
 F:	arch/arm/mm/cache-uniphier.c
-F:	arch/arm64/boot/dts/socionext/
+F:	arch/arm64/boot/dts/socionext/uniphier*
 F:	drivers/bus/uniphier-system-bus.c
 F:	drivers/clk/uniphier/
 F:	drivers/gpio/gpio-uniphier.c
@@ -2057,24 +2101,6 @@ F:	drivers/reset/reset-uniphier.c
 F:	drivers/tty/serial/8250/8250_uniphier.c
 N:	uniphier
 
-ARM/Ux500 ARM ARCHITECTURE
-M:	Linus Walleij <linus.walleij@linaro.org>
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Maintained
-F:	arch/arm/mach-ux500/
-F:	drivers/clocksource/clksrc-dbx500-prcmu.c
-F:	drivers/dma/ste_dma40*
-F:	drivers/hwspinlock/u8500_hsem.c
-F:	drivers/mfd/abx500*
-F:	drivers/mfd/ab8500*
-F:	drivers/mfd/dbx500*
-F:	drivers/mfd/db8500*
-F:	drivers/pinctrl/nomadik/pinctrl-ab*
-F:	drivers/pinctrl/nomadik/pinctrl-nomadik*
-F:	drivers/rtc/rtc-ab8500.c
-F:	drivers/rtc/rtc-pl031.c
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-stericsson.git
-
 ARM/Ux500 CLOCK FRAMEWORK SUPPORT
 M:	Ulf Hansson <ulf.hansson@linaro.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -2382,13 +2408,6 @@ F:	Documentation/devicetree/bindings/input/atmel,maxtouch.txt
 F:	drivers/input/touchscreen/atmel_mxt_ts.c
 F:	include/linux/platform_data/atmel_mxt_ts.h
 
-ATMEL NAND DRIVER
-M:	Wenyou Yang <wenyou.yang@atmel.com>
-M:	Josh Wu <rainyfeeling@outlook.com>
-L:	linux-mtd@lists.infradead.org
-S:	Supported
-F:	drivers/mtd/nand/atmel/*
-
 ATMEL SAMA5D2 ADC DRIVER
 M:	Ludovic Desroches <ludovic.desroches@microchip.com>
 L:	linux-iio@vger.kernel.org
@@ -2500,6 +2519,8 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	Documentation/devicetree/bindings/arm/axentia.txt
 F:	arch/arm/boot/dts/at91-linea.dtsi
+F:	arch/arm/boot/dts/at91-natte.dtsi
+F:	arch/arm/boot/dts/at91-nattis-2-natte-2.dts
 F:	arch/arm/boot/dts/at91-tse850-3.dts
 
 AXENTIA ASOC DRIVERS
@@ -2563,6 +2584,7 @@ S:	Maintained
 F:	Documentation/ABI/testing/sysfs-class-net-batman-adv
 F:	Documentation/ABI/testing/sysfs-class-net-mesh
 F:	Documentation/networking/batman-adv.rst
+F:	include/uapi/linux/batadv_packet.h
 F:	include/uapi/linux/batman_adv.h
 F:	net/batman-adv/
 
@@ -2620,24 +2642,22 @@ F:	fs/bfs/
 F:	include/uapi/linux/bfs_fs.h
 
 BLACKFIN ARCHITECTURE
-M:	Steven Miao <realmz6@gmail.com>
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 T:	git git://git.code.sf.net/p/adi-linux/code
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	arch/blackfin/
 
 BLACKFIN EMAC DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/net/ethernet/adi/
 
 BLACKFIN MEDIA DRIVER
-M:	Scott Jiang <scott.jiang.linux@gmail.com>
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org/
-S:	Supported
+S:	Orphan
 F:	drivers/media/platform/blackfin/
 F:	drivers/media/i2c/adv7183*
 F:	drivers/media/i2c/vs6624*
@@ -2645,25 +2665,25 @@ F:	drivers/media/i2c/vs6624*
 BLACKFIN RTC DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/rtc/rtc-bfin.c
 
 BLACKFIN SDH DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/mmc/host/bfin_sdh.c
 
 BLACKFIN SERIAL DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/tty/serial/bfin_uart.c
 
 BLACKFIN WATCHDOG DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/watchdog/bfin_wdt.c
 
 BLINKM RGB LED DRIVER
@@ -2688,7 +2708,6 @@ F:	drivers/mtd/devices/block2mtd.c
 
 BLUETOOTH DRIVERS
 M:	Marcel Holtmann <marcel@holtmann.org>
-M:	Gustavo Padovan <gustavo@padovan.org>
 M:	Johan Hedberg <johan.hedberg@gmail.com>
 L:	linux-bluetooth@vger.kernel.org
 W:	http://www.bluez.org/
@@ -2699,7 +2718,6 @@ F:	drivers/bluetooth/
 
 BLUETOOTH SUBSYSTEM
 M:	Marcel Holtmann <marcel@holtmann.org>
-M:	Gustavo Padovan <gustavo@padovan.org>
 M:	Johan Hedberg <johan.hedberg@gmail.com>
 L:	linux-bluetooth@vger.kernel.org
 W:	http://www.bluez.org/
@@ -2724,12 +2742,16 @@ M:	Alexei Starovoitov <ast@kernel.org>
 M:	Daniel Borkmann <daniel@iogearbox.net>
 L:	netdev@vger.kernel.org
 L:	linux-kernel@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
 S:	Supported
 F:	arch/x86/net/bpf_jit*
 F:	Documentation/networking/filter.txt
 F:	Documentation/bpf/
 F:	include/linux/bpf*
 F:	include/linux/filter.h
+F:	include/trace/events/bpf.h
+F:	include/trace/events/xdp.h
 F:	include/uapi/linux/bpf*
 F:	include/uapi/linux/filter.h
 F:	kernel/bpf/
@@ -2833,6 +2855,8 @@ S:	Maintained
 F:	arch/arm/mach-bcm/*brcmstb*
 F:	arch/arm/boot/dts/bcm7*.dts*
 F:	drivers/bus/brcmstb_gisb.c
+F:	arch/arm/mm/cache-b15-rac.c
+F:	arch/arm/include/asm/hardware/cache-b15-rac.h
 N:	brcmstb
 
 BROADCOM BMIPS CPUFREQ DRIVER
@@ -3194,7 +3218,7 @@ W:	https://github.com/linux-can
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next.git
 S:	Maintained
-F:	Documentation/networking/can.txt
+F:	Documentation/networking/can.rst
 F:	net/can/
 F:	include/linux/can/core.h
 F:	include/uapi/linux/can.h
@@ -3399,8 +3423,8 @@ M:	Arnd Bergmann <arnd@arndb.de>
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
 S:	Supported
-F:	drivers/char/*
-F:	drivers/misc/*
+F:	drivers/char/
+F:	drivers/misc/
 F:	include/linux/miscdevice.h
 
 CHECKPATCH
@@ -4126,6 +4150,7 @@ DEVANTECH SRF ULTRASONIC RANGER IIO DRIVER
 M:	Andreas Klinger <ak@it-klinger.de>
 L:	linux-iio@vger.kernel.org
 S:	Maintained
+F:	Documentation/ABI/testing/sysfs-bus-iio-distance-srf08
 F:	drivers/iio/proximity/srf*.c
 
 DEVICE COREDUMP (DEV_COREDUMP)
@@ -4335,10 +4360,12 @@ T:	git git://git.infradead.org/users/hch/dma-mapping.git
 W:	http://git.infradead.org/users/hch/dma-mapping.git
 S:	Supported
 F:	lib/dma-debug.c
-F:	lib/dma-noop.c
+F:	lib/dma-direct.c
 F:	lib/dma-virt.c
 F:	drivers/base/dma-mapping.c
 F:	drivers/base/dma-coherent.c
+F:	include/asm-generic/dma-mapping.h
+F:	include/linux/dma-direct.h
 F:	include/linux/dma-mapping.h
 
 DME1737 HARDWARE MONITOR DRIVER
@@ -4461,6 +4488,12 @@ T:	git git://anongit.freedesktop.org/drm/drm-misc
 S:	Maintained
 F:	drivers/gpu/drm/tve200/
 
+DRM DRIVER FOR ILITEK ILI9225 PANELS
+M:	David Lechner <david@lechnology.com>
+S:	Maintained
+F:	drivers/gpu/drm/tinydrm/ili9225.c
+F:	Documentation/devicetree/bindings/display/ili9225.txt
+
 DRM DRIVER FOR INTEL I810 VIDEO CARDS
 S:	Orphan / Obsolete
 F:	drivers/gpu/drm/i810/
@@ -4547,6 +4580,12 @@ S:	Maintained
 F:	drivers/gpu/drm/tinydrm/st7586.c
 F:	Documentation/devicetree/bindings/display/st7586.txt
 
+DRM DRIVER FOR SITRONIX ST7735R PANELS
+M:	David Lechner <david@lechnology.com>
+S:	Maintained
+F:	drivers/gpu/drm/tinydrm/st7735r.c
+F:	Documentation/devicetree/bindings/display/st7735r.txt
+
 DRM DRIVER FOR TDFX VIDEO CARDS
 S:	Orphan / Obsolete
 F:	drivers/gpu/drm/tdfx/
@@ -4586,7 +4625,7 @@ F:	include/linux/vga*
 
 DRM DRIVERS AND MISC GPU PATCHES
 M:	Daniel Vetter <daniel.vetter@intel.com>
-M:	Jani Nikula <jani.nikula@linux.intel.com>
+M:	Gustavo Padovan <gustavo@padovan.org>
 M:	Sean Paul <seanpaul@chromium.org>
 W:	https://01.org/linuxgraphics/gfx-docs/maintainer-tools/drm-misc.html
 S:	Maintained
@@ -4715,7 +4754,8 @@ F:	Documentation/devicetree/bindings/display/bridge/renesas,dw-hdmi.txt
 F:	Documentation/devicetree/bindings/display/renesas,du.txt
 
 DRM DRIVERS FOR ROCKCHIP
-M:	Mark Yao <mark.yao@rock-chips.com>
+M:	Sandy Huang <hjc@rock-chips.com>
+M:	Heiko Stübner <heiko@sntech.de>
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
 F:	drivers/gpu/drm/rockchip/
@@ -4803,6 +4843,15 @@ S:	Maintained
 F:	drivers/gpu/drm/tinydrm/
 F:	include/drm/tinydrm/
 
+DRM TTM SUBSYSTEM
+M:	Christian Koenig <christian.koenig@amd.com>
+M:	Roger He <Hongbo.He@amd.com>
+T:	git git://people.freedesktop.org/~agd5f/linux
+S:	Maintained
+L:	dri-devel@lists.freedesktop.org
+F:	include/drm/ttm/
+F:	drivers/gpu/drm/ttm/
+
 DSBR100 USB FM RADIO DRIVER
 M:	Alexey Klimov <klimov.linux@gmail.com>
 L:	linux-media@vger.kernel.org
@@ -4940,6 +4989,11 @@ S:	Maintained
 F:	lib/dynamic_debug.c
 F:	include/linux/dynamic_debug.h
 
+DYNAMIC INTERRUPT MODERATION
+M:	Tal Gilboa <talgi@mellanox.com>
+S:	Maintained
+F:	include/linux/net_dim.h
+
 DZ DECSTATION DZ11 SERIAL DRIVER
 M:	"Maciej W. Rozycki" <macro@linux-mips.org>
 S:	Maintained
@@ -5140,6 +5194,12 @@ L:	linux-edac@vger.kernel.org
 S:	Maintained
 F:	drivers/edac/skx_edac.c
 
+EDAC-TI
+M:	Tero Kristo <t-kristo@ti.com>
+L:	linux-edac@vger.kernel.org
+S:	Maintained
+F:	drivers/edac/ti_edac.c
+
 EDIROL UA-101/UA-1000 DRIVER
 M:	Clemens Ladisch <clemens@ladisch.de>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
@@ -5150,15 +5210,15 @@ F:	sound/usb/misc/ua101.c
 EFI TEST DRIVER
 L:	linux-efi@vger.kernel.org
 M:	Ivan Hu <ivan.hu@canonical.com>
-M:	Matt Fleming <matt@codeblueprint.co.uk>
+M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
 S:	Maintained
 F:	drivers/firmware/efi/test/
 
 EFI VARIABLE FILESYSTEM
 M:	Matthew Garrett <matthew.garrett@nebula.com>
 M:	Jeremy Kerr <jk@ozlabs.org>
-M:	Matt Fleming <matt@codeblueprint.co.uk>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git
+M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git
 L:	linux-efi@vger.kernel.org
 S:	Maintained
 F:	fs/efivarfs/
@@ -5319,7 +5379,6 @@ S:	Supported
 F:	security/integrity/evm/
 
 EXTENSIBLE FIRMWARE INTERFACE (EFI)
-M:	Matt Fleming <matt@codeblueprint.co.uk>
 M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
 L:	linux-efi@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git
@@ -5430,7 +5489,7 @@ F:	drivers/media/tuners/fc2580*
 
 FCOE SUBSYSTEM (libfc, libfcoe, fcoe)
 M:	Johannes Thumshirn <jth@kernel.org>
-L:	fcoe-devel@open-fcoe.org
+L:	linux-scsi@vger.kernel.org
 W:	www.Open-FCoE.org
 S:	Supported
 F:	drivers/scsi/libfc/
@@ -5964,6 +6023,7 @@ F:	drivers/media/rc/gpio-ir-tx.c
 
 GPIO MOCKUP DRIVER
 M:	Bamvor Jian Zhang <bamvor.zhangjian@linaro.org>
+R:	Bartosz Golaszewski <brgl@bgdev.pl>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained
 F:	drivers/gpio/gpio-mockup.c
@@ -6174,7 +6234,6 @@ M:	Jean Delvare <jdelvare@suse.com>
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 W:	http://hwmon.wiki.kernel.org/
-T:	quilt http://jdelvare.nerim.net/devel/linux/jdelvare-hwmon/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git
 S:	Maintained
 F:	Documentation/hwmon/
@@ -6612,16 +6671,6 @@ L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/i2c-stub.c
 
-i386 BOOT CODE
-M:	"H. Peter Anvin" <hpa@zytor.com>
-S:	Maintained
-F:	arch/x86/boot/
-
-i386 SETUP CODE / CPU ERRATA WORKAROUNDS
-M:	"H. Peter Anvin" <hpa@zytor.com>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hpa/linux-2.6-x86setup.git
-S:	Maintained
-
 IA64 (Itanium) PLATFORM
 M:	Tony Luck <tony.luck@intel.com>
 M:	Fenghua Yu <fenghua.yu@intel.com>
@@ -6829,6 +6878,8 @@ R:	Peter Meerwald-Stadler <pmeerw@pmeerw.net>
 L:	linux-iio@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jic23/iio.git
 S:	Maintained
+F:	Documentation/ABI/testing/configfs-iio*
+F:	Documentation/ABI/testing/sysfs-bus-iio*
 F:	Documentation/devicetree/bindings/iio/
 F:	drivers/iio/
 F:	drivers/staging/iio/
@@ -6888,7 +6939,7 @@ M:	Jason Gunthorpe <jgg@mellanox.com>
 L:	linux-rdma@vger.kernel.org
 W:	http://www.openfabrics.org/
 Q:	http://patchwork.kernel.org/project/linux-rdma/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git
 S:	Supported
 F:	Documentation/devicetree/bindings/infiniband/
 F:	Documentation/infiniband/
@@ -7029,7 +7080,7 @@ M:	Zhi Wang <zhi.a.wang@intel.com>
 L:	intel-gvt-dev@lists.freedesktop.org
 L:	intel-gfx@lists.freedesktop.org
 W:	https://01.org/igvt-g
-T:	git https://github.com/01org/gvt-linux.git
+T:	git https://github.com/intel/gvt-linux.git
 S:	Supported
 F:	drivers/gpu/drm/i915/gvt/
 
@@ -7310,17 +7361,16 @@ F:	drivers/tty/ipwireless/
 
 IPX NETWORK LAYER
 L:	netdev@vger.kernel.org
-S:	Odd fixes
-F:	include/net/ipx.h
+S:	Obsolete
 F:	include/uapi/linux/ipx.h
-F:	net/ipx/
+F:	drivers/staging/ipx/
 
 IRDA SUBSYSTEM
 M:	Samuel Ortiz <samuel@sortiz.org>
 L:	irda-users@lists.sourceforge.net (subscribers-only)
 L:	netdev@vger.kernel.org
 W:	http://irda.sourceforge.net/
-S:	Maintained
+S:	Obsolete
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sameo/irda-2.6.git
 F:	Documentation/networking/irda.txt
 F:	drivers/staging/irda/
@@ -7767,6 +7817,7 @@ F:	security/keys/
 
 KGDB / KDB /debug_core
 M:	Jason Wessel <jason.wessel@windriver.com>
+M:	Daniel Thompson <daniel.thompson@linaro.org>
 W:	http://kgdb.wiki.kernel.org/
 L:	kgdb-bugreport@lists.sourceforge.net
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/kgdb.git
@@ -8194,6 +8245,7 @@ F:	arch/*/include/asm/rwsem.h
 F:	include/linux/seqlock.h
 F:	lib/locking*.[ch]
 F:	kernel/locking/
+X:	kernel/locking/locktorture.c
 
 LOGICAL DISK MANAGER SUPPORT (LDM, Windows 2000/XP/Vista Dynamic Disks)
 M:	"Richard Russon (FlatCap)" <ldm@flatcap.org>
@@ -8409,6 +8461,13 @@ L:	linux-wireless@vger.kernel.org
 S:	Odd Fixes
 F:	drivers/net/wireless/marvell/mwl8k.c
 
+MARVELL NAND CONTROLLER DRIVER
+M:	Miquel Raynal <miquel.raynal@free-electrons.com>
+L:	linux-mtd@lists.infradead.org
+S:	Maintained
+F:	drivers/mtd/nand/marvell_nand.c
+F:	Documentation/devicetree/bindings/mtd/marvell-nand.txt
+
 MARVELL SOC MMC/SD/SDIO CONTROLLER DRIVER
 M:	Nicolas Pitre <nico@fluxnic.net>
 S:	Odd Fixes
@@ -8723,6 +8782,13 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/mediatek/
 
+MEDIATEK SWITCH DRIVER
+M:	Sean Wang <sean.wang@mediatek.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/dsa/mt7530.*
+F:	net/dsa/tag_mtk.c
+
 MEDIATEK JPEG DRIVER
 M:	Rick Chang <rick.chang@mediatek.com>
 M:	Bin Liu <bin.liu@mediatek.com>
@@ -8956,7 +9022,7 @@ L:	linux-mtd@lists.infradead.org
 W:	http://www.linux-mtd.infradead.org/
 Q:	http://patchwork.ozlabs.org/project/linux-mtd/list/
 T:	git git://git.infradead.org/linux-mtd.git master
-T:	git git://git.infradead.org/l2-mtd.git master
+T:	git git://git.infradead.org/linux-mtd.git mtd/next
 S:	Maintained
 F:	Documentation/devicetree/bindings/mtd/
 F:	drivers/mtd/
@@ -9045,6 +9111,14 @@ F:	drivers/media/platform/atmel/atmel-isc.c
 F:	drivers/media/platform/atmel/atmel-isc-regs.h
 F:	devicetree/bindings/media/atmel-isc.txt
 
+MICROCHIP / ATMEL NAND DRIVER
+M:	Wenyou Yang <wenyou.yang@microchip.com>
+M:	Josh Wu <rainyfeeling@outlook.com>
+L:	linux-mtd@lists.infradead.org
+S:	Supported
+F:	drivers/mtd/nand/atmel/*
+F:	Documentation/devicetree/bindings/mtd/atmel-nand.txt
+
 MICROCHIP KSZ SERIES ETHERNET SWITCH DRIVER
 M:	Woojung Huh <Woojung.Huh@microchip.com>
 M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
@@ -9087,6 +9161,7 @@ F:	drivers/usb/image/microtek.*
 
 MIPS
 M:	Ralf Baechle <ralf@linux-mips.org>
+M:	James Hogan <jhogan@kernel.org>
 L:	linux-mips@linux-mips.org
 W:	http://www.linux-mips.org/
 T:	git git://git.linux-mips.org/pub/scm/ralf/linux.git
@@ -9331,9 +9406,9 @@ F:	drivers/gpu/drm/mxsfb/
 F:	Documentation/devicetree/bindings/display/mxsfb-drm.txt
 
 MYRICOM MYRI-10G 10GbE DRIVER (MYRI10GE)
-M:	Hyong-Youb Kim <hykim@myri.com>
+M:	Chris Lee <christopher.lee@cspi.com>
 L:	netdev@vger.kernel.org
-W:	https://www.myricom.com/support/downloads/myri10ge.html
+W:	https://www.cspi.com/ethernet-products/support/downloads/
 S:	Supported
 F:	drivers/net/ethernet/myricom/myri10ge/
 
@@ -9344,7 +9419,7 @@ L:	linux-mtd@lists.infradead.org
 W:	http://www.linux-mtd.infradead.org/
 Q:	http://patchwork.ozlabs.org/project/linux-mtd/list/
 T:	git git://git.infradead.org/linux-mtd.git nand/fixes
-T:	git git://git.infradead.org/l2-mtd.git nand/next
+T:	git git://git.infradead.org/linux-mtd.git nand/next
 S:	Maintained
 F:	drivers/mtd/nand/
 F:	include/linux/mtd/*nand*.h
@@ -9362,8 +9437,8 @@ F:	drivers/net/ethernet/natsemi/natsemi.c
 
 NCP FILESYSTEM
 M:	Petr Vandrovec <petr@vandrovec.name>
-S:	Odd Fixes
-F:	fs/ncpfs/
+S:	Obsolete
+F:	drivers/staging/ncpfs/
 
 NCR 5380 SCSI DRIVERS
 M:	Finn Thain <fthain@telegraphics.com.au>
@@ -9599,6 +9674,11 @@ NETWORKING [WIRELESS]
 L:	linux-wireless@vger.kernel.org
 Q:	http://patchwork.kernel.org/project/linux-wireless/list/
 
+NETDEVSIM
+M:	Jakub Kicinski <jakub.kicinski@netronome.com>
+S:	Maintained
+F:	drivers/net/netdevsim/*
+
 NETXEN (1/10) GbE SUPPORT
 M:	Manish Chopra <manish.chopra@cavium.com>
 M:	Rahul Verma <rahul.verma@cavium.com>
@@ -9640,8 +9720,8 @@ F:	include/uapi/linux/sunrpc/
 NILFS2 FILESYSTEM
 M:	Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
 L:	linux-nilfs@vger.kernel.org
-W:	http://nilfs.sourceforge.net/
-W:	http://nilfs.osdn.jp/
+W:	https://nilfs.sourceforge.io/
+W:	https://nilfs.osdn.jp/
 T:	git git://github.com/konis/nilfs2.git
 S:	Supported
 F:	Documentation/filesystems/nilfs2.txt
@@ -9745,6 +9825,15 @@ S:	Supported
 F:	Documentation/filesystems/ntfs.txt
 F:	fs/ntfs/
 
+NUBUS SUBSYSTEM
+M:	Finn Thain <fthain@telegraphics.com.au>
+L:	linux-m68k@lists.linux-m68k.org
+S:	Maintained
+F:	arch/*/include/asm/nubus.h
+F:	drivers/nubus/
+F:	include/linux/nubus.h
+F:	include/uapi/linux/nubus.h
+
 NVIDIA (rivafb and nvidiafb) FRAMEBUFFER DRIVER
 M:	Antonino Daplas <adaplas@gmail.com>
 L:	linux-fbdev@vger.kernel.org
@@ -9805,6 +9894,7 @@ NXP TFA9879 DRIVER
 M:	Peter Rosin <peda@axentia.se>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Maintained
+F:	Documentation/devicetree/bindings/sound/tfa9879.txt
 F:	sound/soc/codecs/tfa9879*
 
 NXP-NCI NFC DRIVER
@@ -9819,6 +9909,18 @@ M:	Josh Poimboeuf <jpoimboe@redhat.com>
 S:	Supported
 F:	tools/objtool/
 
+OCXL (Open Coherent Accelerator Processor Interface OpenCAPI) DRIVER
+M:	Frederic Barrat <fbarrat@linux.vnet.ibm.com>
+M:	Andrew Donnellan <andrew.donnellan@au1.ibm.com>
+L:	linuxppc-dev@lists.ozlabs.org
+S:	Supported
+F:	arch/powerpc/platforms/powernv/ocxl.c
+F:	arch/powerpc/include/asm/pnv-ocxl.h
+F:	drivers/misc/ocxl/
+F:	include/misc/ocxl*
+F:	include/uapi/misc/ocxl.h
+F:	Documentation/accelerators/ocxl.txt
+
 OMAP AUDIO SUPPORT
 M:	Peter Ujfalusi <peter.ujfalusi@ti.com>
 M:	Jarkko Nikula <jarkko.nikula@bitmer.com>
@@ -10136,7 +10238,7 @@ F:	drivers/irqchip/irq-ompic.c
 F:	drivers/irqchip/irq-or1k-*
 
 OPENVSWITCH
-M:	Pravin Shelar <pshelar@nicira.com>
+M:	Pravin B Shelar <pshelar@ovn.org>
 L:	netdev@vger.kernel.org
 L:	dev@openvswitch.org
 W:	http://openvswitch.org
@@ -10891,6 +10993,7 @@ F:	include/linux/pm.h
 F:	include/linux/pm_*
 F:	include/linux/powercap.h
 F:	drivers/powercap/
+F:	kernel/configs/nopm.config
 
 POWER STATE COORDINATION INTERFACE (PSCI)
 M:	Mark Rutland <mark.rutland@arm.com>
@@ -11185,7 +11288,8 @@ S:	Maintained
 F:	drivers/firmware/qemu_fw_cfg.c
 
 QIB DRIVER
-M:	Mike Marciniszyn <infinipath@intel.com>
+M:	Dennis Dalessandro <dennis.dalessandro@intel.com>
+M:	Mike Marciniszyn <mike.marciniszyn@intel.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/hw/qib/
@@ -11212,7 +11316,6 @@ F:	include/linux/qed/
 F:	drivers/net/ethernet/qlogic/qede/
 
 QLOGIC QL4xxx RDMA DRIVER
-M:	Ram Amrani <Ram.Amrani@cavium.com>
 M:	Michal Kalderon <Michal.Kalderon@cavium.com>
 M:	Ariel Elior <Ariel.Elior@cavium.com>
 L:	linux-rdma@vger.kernel.org
@@ -11359,6 +11462,7 @@ F:	drivers/net/wireless/quantenna
 RADEON and AMDGPU DRM DRIVERS
 M:	Alex Deucher <alexander.deucher@amd.com>
 M:	Christian König <christian.koenig@amd.com>
+M:	David (ChunMing) Zhou <David1.Zhou@amd.com>
 L:	amd-gfx@lists.freedesktop.org
 T:	git git://people.freedesktop.org/~agd5f/linux
 S:	Supported
@@ -11451,15 +11555,6 @@ L:	linux-wireless@vger.kernel.org
 S:	Orphan
 F:	drivers/net/wireless/ray*
 
-RCUTORTURE MODULE
-M:	Josh Triplett <josh@joshtriplett.org>
-M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
-L:	linux-kernel@vger.kernel.org
-S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
-F:	Documentation/RCU/torture.txt
-F:	kernel/rcu/rcutorture.c
-
 RCUTORTURE TEST FRAMEWORK
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
@@ -11483,6 +11578,7 @@ F:	drivers/net/ethernet/rdc/r6040.c
 
 RDMAVT - RDMA verbs software
 M:	Dennis Dalessandro <dennis.dalessandro@intel.com>
+M:	Mike Marciniszyn <mike.marciniszyn@intel.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/sw/rdmavt
@@ -11652,8 +11748,8 @@ F:	drivers/mtd/nand/r852.h
 RISC-V ARCHITECTURE
 M:	Palmer Dabbelt <palmer@sifive.com>
 M:	Albert Ou <albert@sifive.com>
-L:	patches@groups.riscv.org
-T:	git https://github.com/riscv/riscv-linux
+L:	linux-riscv@lists.infradead.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux.git
 S:	Supported
 F:	arch/riscv/
 K:	riscv
@@ -11760,15 +11856,13 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.g
 S:	Maintained
 F:	drivers/net/wireless/realtek/rtl818x/rtl8187/
 
-RTL8192CE WIRELESS DRIVER
-M:	Larry Finger <Larry.Finger@lwfinger.net>
-M:	Chaoming Li <chaoming_li@realsil.com.cn>
+REALTEK WIRELESS DRIVER (rtlwifi family)
+M:	Ping-Ke Shih <pkshih@realtek.com>
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
 S:	Maintained
 F:	drivers/net/wireless/realtek/rtlwifi/
-F:	drivers/net/wireless/realtek/rtlwifi/rtl8192ce/
 
 RTL8XXXU WIRELESS DRIVER (rtl8xxxu)
 M:	Jes Sorensen <Jes.Sorensen@gmail.com>
@@ -11777,6 +11871,18 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jes/linux.git rtl8xxxu-deve
 S:	Maintained
 F:	drivers/net/wireless/realtek/rtl8xxxu/
 
+RXRPC SOCKETS (AF_RXRPC)
+M:	David Howells <dhowells@redhat.com>
+L:	linux-afs@lists.infradead.org
+S:	Supported
+F:	net/rxrpc/
+F:	include/keys/rxrpc-type.h
+F:	include/net/af_rxrpc.h
+F:	include/trace/events/rxrpc.h
+F:	include/uapi/linux/rxrpc.h
+F:	Documentation/networking/rxrpc.txt
+W:	https://www.infradead.org/~dhowells/kafs/
+
 S3 SAVAGE FRAMEBUFFER DRIVER
 M:	Antonino Daplas <adaplas@gmail.com>
 L:	linux-fbdev@vger.kernel.org
@@ -11920,6 +12026,13 @@ S:	Maintained
 F:	drivers/crypto/exynos-rng.c
 F:	Documentation/devicetree/bindings/crypto/samsung,exynos-rng4.txt
 
+SAMSUNG EXYNOS TRUE RANDOM NUMBER GENERATOR (TRNG) DRIVER
+M:	Łukasz Stelmach <l.stelmach@samsung.com>
+L:	linux-samsung-soc@vger.kernel.org
+S:	Maintained
+F:	drivers/char/hw_random/exynos-trng.c
+F:	Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.txt
+
 SAMSUNG FRAMEBUFFER DRIVER
 M:	Jingoo Han <jingoohan1@gmail.com>
 L:	linux-fbdev@vger.kernel.org
@@ -11982,6 +12095,7 @@ F:	drivers/media/i2c/s5k5baf.c
 SAMSUNG S5P Security SubSystem (SSS) DRIVER
 M:	Krzysztof Kozlowski <krzk@kernel.org>
 M:	Vladimir Zapolskiy <vz@mleia.com>
+M:	Kamil Konieczny <k.konieczny@partner.samsung.com>
 L:	linux-crypto@vger.kernel.org
 L:	linux-samsung-soc@vger.kernel.org
 S:	Maintained
@@ -12222,7 +12336,7 @@ M:	Security Officers <security@kernel.org>
 S:	Supported
 
 SECURITY SUBSYSTEM
-M:	James Morris <james.l.morris@oracle.com>
+M:	James Morris <jmorris@namei.org>
 M:	"Serge E. Hallyn" <serge@hallyn.com>
 L:	linux-security-module@vger.kernel.org (suggested Cc:)
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security.git
@@ -12449,6 +12563,13 @@ F:	lib/siphash.c
 F:	lib/test_siphash.c
 F:	include/linux/siphash.h
 
+SIOX
+M:	Gavin Schenk <g.schenk@eckelmann.de>
+M:	Uwe Kleine-König <kernel@pengutronix.de>
+S:	Supported
+F:	drivers/siox/*
+F:	include/trace/events/siox.h
+
 SIS 190 ETHERNET DRIVER
 M:	Francois Romieu <romieu@fr.zoreil.com>
 L:	netdev@vger.kernel.org
@@ -12500,6 +12621,14 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	include/linux/srcu.h
 F:	kernel/rcu/srcu.c
 
+SERIAL LOW-POWER INTER-CHIP MEDIA BUS (SLIMbus)
+M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+S:	Maintained
+F:	drivers/slimbus/
+F:	Documentation/devicetree/bindings/slimbus/
+F:	include/linux/slimbus.h
+
 SMACK SECURITY MODULE
 M:	Casey Schaufler <casey@schaufler-ca.com>
 L:	linux-security-module@vger.kernel.org
@@ -12581,6 +12710,12 @@ F:	include/media/soc*
 F:	drivers/media/i2c/soc_camera/
 F:	drivers/media/platform/soc_camera/
 
+SOCIONEXT UNIPHIER SOUND DRIVER
+M:	Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+S:	Maintained
+F:	sound/soc/uniphier/
+
 SOEKRIS NET48XX LED SUPPORT
 M:	Chris Boot <bootc@bootc.net>
 S:	Maintained
@@ -12605,6 +12740,15 @@ L:	linux-media@vger.kernel.org
 S:	Supported
 F:	drivers/media/pci/solo6x10/
 
+SOFTWARE DELEGATED EXCEPTION INTERFACE (SDEI)
+M:	James Morse <james.morse@arm.com>
+L:	linux-arm-kernel@lists.infradead.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/arm/firmware/sdei.txt
+F:	drivers/firmware/arm_sdei.c
+F:	include/linux/sdei.h
+F:	include/uapi/linux/sdei.h
+
 SOFTWARE RAID (Multiple Disks) SUPPORT
 M:	Shaohua Li <shli@kernel.org>
 L:	linux-raid@vger.kernel.org
@@ -12617,6 +12761,13 @@ F:	drivers/md/raid*
 F:	include/linux/raid/
 F:	include/uapi/linux/raid/
 
+SOCIONEXT (SNI) NETSEC NETWORK DRIVER
+M:	Jassi Brar <jaswinder.singh@linaro.org>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ethernet/socionext/netsec.c
+F:	Documentation/devicetree/bindings/net/socionext-netsec.txt
+
 SONIC NETWORK DRIVER
 M:	Thomas Bogendoerfer <tsbogend@alpha.franken.de>
 L:	netdev@vger.kernel.org
@@ -12630,6 +12781,14 @@ S:	Maintained
 F:	drivers/ssb/
 F:	include/linux/ssb/
 
+SONY IMX274 SENSOR DRIVER
+M:	Leon Luo <leonl@leopardimaging.com>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Maintained
+F:	drivers/media/i2c/imx274.c
+F:	Documentation/devicetree/bindings/media/i2c/imx274.txt
+
 SONY MEMORYSTICK CARD SUPPORT
 M:	Alex Dubov <oakad@yahoo.com>
 W:	http://tifmxx.berlios.de/
@@ -12695,6 +12854,16 @@ F:	Documentation/sound/alsa/soc/
 F:	sound/soc/
 F:	include/sound/soc*
 
+SOUNDWIRE SUBSYSTEM
+M:	Vinod Koul <vinod.koul@intel.com>
+M:	Sanyog Kale <sanyog.r.kale@intel.com>
+R:	Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+S:	Supported
+F:	Documentation/driver-api/soundwire/
+F:	drivers/soundwire/
+F:	include/linux/soundwire/
+
 SP2 MEDIA DRIVER
 M:	Olli Salonen <olli.salonen@iki.fi>
 L:	linux-media@vger.kernel.org
@@ -12761,7 +12930,7 @@ L:	linux-mtd@lists.infradead.org
 W:	http://www.linux-mtd.infradead.org/
 Q:	http://patchwork.ozlabs.org/project/linux-mtd/list/
 T:	git git://git.infradead.org/linux-mtd.git spi-nor/fixes
-T:	git git://git.infradead.org/l2-mtd.git spi-nor/next
+T:	git git://git.infradead.org/linux-mtd.git spi-nor/next
 S:	Maintained
 F:	drivers/mtd/spi-nor/
 F:	include/linux/mtd/spi-nor.h
@@ -13014,7 +13183,7 @@ F:	arch/x86/boot/video*
 
 SWIOTLB SUBSYSTEM
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
-L:	linux-kernel@vger.kernel.org
+L:	iommu@lists.linux-foundation.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb.git
 S:	Supported
 F:	lib/swiotlb.c
@@ -13079,6 +13248,11 @@ S:	Supported
 F:	drivers/reset/reset-axs10x.c
 F:	Documentation/devicetree/bindings/reset/snps,axs10x-reset.txt
 
+SYNOPSYS DESIGNWARE 8250 UART DRIVER
+R:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+S:	Maintained
+F:	drivers/tty/serial/8250/8250_dw.c
+
 SYNOPSYS DESIGNWARE APB GPIO DRIVER
 M:	Hoan Tran <hotran@apm.com>
 L:	linux-gpio@vger.kernel.org
@@ -13096,6 +13270,7 @@ F:	drivers/dma/dw/
 
 SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER
 M:	Jie Deng <jiedeng@synopsys.com>
+M:	Jose Abreu <Jose.Abreu@synopsys.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/synopsys/
@@ -13471,6 +13646,7 @@ M:	Mika Westerberg <mika.westerberg@linux.intel.com>
 M:	Yehezkel Bernat <yehezkel.bernat@intel.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git
 S:	Maintained
+F:	Documentation/admin-guide/thunderbolt.rst
 F:	drivers/thunderbolt/
 F:	include/linux/thunderbolt.h
 
@@ -13648,10 +13824,8 @@ F:	drivers/net/wireless/ti/
 F:	include/linux/wl12xx.h
 
 TILE ARCHITECTURE
-M:	Chris Metcalf <cmetcalf@mellanox.com>
 W:	http://www.mellanox.com/repository/solutions/tile-scm/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile.git
-S:	Supported
+S:	Orphan
 F:	arch/tile/
 F:	drivers/char/tile-srom.c
 F:	drivers/edac/tile_edac.c
@@ -13748,6 +13922,18 @@ L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	drivers/platform/x86/topstar-laptop.c
 
+TORTURE-TEST MODULES
+M:	Davidlohr Bueso <dave@stgolabs.net>
+M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
+M:	Josh Triplett <josh@joshtriplett.org>
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+F:	Documentation/RCU/torture.txt
+F:	kernel/torture.c
+F:	kernel/rcu/rcutorture.c
+F:	kernel/locking/locktorture.c
+
 TOSHIBA ACPI EXTRAS DRIVER
 M:	Azael Avalos <coproscefalo@gmail.com>
 L:	platform-driver-x86@vger.kernel.org
@@ -13790,9 +13976,10 @@ F:	drivers/platform/x86/toshiba-wmi.c
 TPM DEVICE DRIVER
 M:	Peter Huewe <peterhuewe@gmx.de>
 M:	Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
-R:	Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
+R:	Jason Gunthorpe <jgg@ziepe.ca>
 L:	linux-integrity@vger.kernel.org
 Q:	https://patchwork.kernel.org/project/linux-integrity/list/
+W:	https://kernsec.org/wiki/index.php/Linux_Kernel_Integrity
 T:	git git://git.infradead.org/users/jjs/linux-tpmdd.git
 S:	Maintained
 F:	drivers/char/tpm/
@@ -13831,6 +14018,13 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial.git
 S:	Maintained
 K:	^Subject:.*(?i)trivial
 
+TEMPO SEMICONDUCTOR DRIVERS
+M:	Steven Eckhoff <steven.eckhoff.opensource@gmail.com>
+S:	Maintained
+F:	sound/soc/codecs/tscs*.c
+F:	sound/soc/codecs/tscs*.h
+F:	Documentation/devicetree/bindings/sound/tscs*.txt
+
 TTY LAYER
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 M:	Jiri Slaby <jslaby@suse.com>
@@ -13992,6 +14186,8 @@ UNISYS S-PAR DRIVERS
 M:	David Kershner <david.kershner@unisys.com>
 L:	sparmaintainer@unisys.com (Unisys internal)
 S:	Supported
+F:	include/linux/visorbus.h
+F:	drivers/visorbus/
 F:	drivers/staging/unisys/
 
 UNIVERSAL FLASH STORAGE HOST CONTROLLER DRIVER
@@ -14538,6 +14734,15 @@ S:	Maintained
 F:	drivers/virtio/virtio_input.c
 F:	include/uapi/linux/virtio_input.h
 
+VIRTUAL BOX GUEST DEVICE DRIVER
+M:	Hans de Goede <hdegoede@redhat.com>
+M:	Arnd Bergmann <arnd@arndb.de>
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+S:	Maintained
+F:	include/linux/vbox_utils.h
+F:	include/uapi/linux/vbox*.h
+F:	drivers/virt/vboxguest/
+
 VIRTUAL SERIO DEVICE DRIVER
 M:	Stephen Chandler Paul <thatslyude@gmail.com>
 S:	Maintained
@@ -14629,6 +14834,7 @@ W:	http://www.slimlogic.co.uk/?p=48
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator.git
 S:	Supported
 F:	Documentation/devicetree/bindings/regulator/
+F:	Documentation/power/regulator/
 F:	drivers/regulator/
 F:	include/dt-bindings/regulator/
 F:	include/linux/regulator/
@@ -14726,9 +14932,9 @@ S:	Maintained
 F:	drivers/hid/hid-wiimote*
 
 WILOCITY WIL6210 WIRELESS DRIVER
-M:	Maya Erez <qca_merez@qca.qualcomm.com>
+M:	Maya Erez <merez@codeaurora.org>
 L:	linux-wireless@vger.kernel.org
-L:	wil6210@qca.qualcomm.com
+L:	wil6210@qti.qualcomm.com
 S:	Supported
 W:	http://wireless.kernel.org/en/users/Drivers/wil6210
 F:	drivers/net/wireless/ath/wil6210/
@@ -14822,6 +15028,12 @@ F:	include/linux/workqueue.h
 F:	kernel/workqueue.c
 F:	Documentation/core-api/workqueue.rst
 
+X-POWERS AXP288 PMIC DRIVERS
+M:	Hans de Goede <hdegoede@redhat.com>
+S:	Maintained
+N:	axp288
+F:	drivers/acpi/pmic/intel_pmic_xpower.c
+
 X-POWERS MULTIFUNCTION PMIC DEVICE DRIVERS
 M:	Chen-Yu Tsai <wens@csie.org>
 L:	linux-kernel@vger.kernel.org
@@ -14839,7 +15051,7 @@ F:	net/x25/
 X86 ARCHITECTURE (32-BIT AND 64-BIT)
 M:	Thomas Gleixner <tglx@linutronix.de>
 M:	Ingo Molnar <mingo@redhat.com>
-M:	"H. Peter Anvin" <hpa@zytor.com>
+R:	"H. Peter Anvin" <hpa@zytor.com>
 M:	x86@kernel.org
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
@@ -14949,6 +15161,7 @@ F:	include/xen/interface/io/vscsiif.h
 XEN SWIOTLB SUBSYSTEM
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
 L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
+L:	iommu@lists.linux-foundation.org
 S:	Supported
 F:	arch/x86/xen/*swiotlb*
 F:	drivers/xen/*swiotlb*
diff --git a/Makefile b/Makefile
index f761bf475ba5..11aff0f9e105 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION =
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
@@ -377,6 +377,8 @@ NM		= $(CROSS_COMPILE)nm
 STRIP		= $(CROSS_COMPILE)strip
 OBJCOPY		= $(CROSS_COMPILE)objcopy
 OBJDUMP		= $(CROSS_COMPILE)objdump
+LEX		= flex
+YACC		= bison
 AWK		= awk
 GENKSYMS	= scripts/genksyms/genksyms
 INSTALLKERNEL  := installkernel
@@ -428,7 +430,7 @@ GCC_PLUGINS_CFLAGS :=
 
 export ARCH SRCARCH CONFIG_SHELL HOSTCC HOSTCFLAGS CROSS_COMPILE AS LD CC
 export CPP AR NM STRIP OBJCOPY OBJDUMP HOSTLDFLAGS HOST_LOADLIBES
-export MAKE AWK GENKSYMS INSTALLKERNEL PERL PYTHON UTS_MACHINE
+export MAKE LEX YACC AWK GENKSYMS INSTALLKERNEL PERL PYTHON UTS_MACHINE
 export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS
 
 export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS LDFLAGS
@@ -484,26 +486,6 @@ CLANG_GCC_TC	:= --gcc-toolchain=$(GCC_TOOLCHAIN)
 endif
 KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
 KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
-KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
-KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable)
-KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
-KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
-KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
-# Quiet clang warning: comparison of unsigned expression < 0 is always false
-KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
-# CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the
-# source of a reference will be _MergedGlobals and not on of the whitelisted names.
-# See modpost pattern 2
-KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
-KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
-KBUILD_CFLAGS += $(call cc-option, -no-integrated-as)
-KBUILD_AFLAGS += $(call cc-option, -no-integrated-as)
-else
-
-# These warnings generated too much noise in a regular build.
-# Use make W=1 to enable them (see scripts/Makefile.extrawarn)
-KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
-KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
 endif
 
 ifeq ($(config-targets),1)
@@ -716,6 +698,29 @@ ifdef CONFIG_CC_STACKPROTECTOR
 endif
 KBUILD_CFLAGS += $(stackp-flag)
 
+ifeq ($(cc-name),clang)
+KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable)
+KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
+KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
+KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
+# Quiet clang warning: comparison of unsigned expression < 0 is always false
+KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
+# CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the
+# source of a reference will be _MergedGlobals and not on of the whitelisted names.
+# See modpost pattern 2
+KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
+KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
+KBUILD_CFLAGS += $(call cc-option, -no-integrated-as)
+KBUILD_AFLAGS += $(call cc-option, -no-integrated-as)
+else
+
+# These warnings generated too much noise in a regular build.
+# Use make W=1 to enable them (see scripts/Makefile.extrawarn)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
+endif
+
 ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS	+= -fno-omit-frame-pointer -fno-optimize-sibling-calls
 else
@@ -789,6 +794,9 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign)
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 
+# Make sure -fstack-check isn't enabled (like gentoo apparently did)
+KBUILD_CFLAGS  += $(call cc-option,-fno-stack-check,)
+
 # conserve stack if available
 KBUILD_CFLAGS   += $(call cc-option,-fconserve-stack)
 
diff --git a/arch/Kconfig b/arch/Kconfig
index 400b9e1b2f27..d007b2a15b22 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -196,6 +196,9 @@ config HAVE_OPTPROBES
 config HAVE_KPROBES_ON_FTRACE
 	bool
 
+config HAVE_FUNCTION_ERROR_INJECTION
+	bool
+
 config HAVE_NMI
 	bool
 
@@ -234,8 +237,8 @@ config ARCH_HAS_FORTIFY_SOURCE
 config ARCH_HAS_SET_MEMORY
 	bool
 
-# Select if arch init_task initializer is different to init/init_task.c
-config ARCH_INIT_TASK
+# Select if arch init_task must go in the __init_task_data section
+config ARCH_TASK_STRUCT_ON_STACK
        bool
 
 # Select if arch has its private alloc_task_struct() function
@@ -938,6 +941,10 @@ config STRICT_MODULE_RWX
 	  and non-text memory will be made non-executable. This provides
 	  protection against certain security exploits (e.g. writing to text)
 
+# select if the architecture provides an asm/dma-direct.h header
+config ARCH_HAS_PHYS_TO_DMA
+	bool
+
 config ARCH_HAS_REFCOUNT
 	bool
 	help
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index b31b974a03cb..e96adcbcab41 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -209,6 +209,7 @@ config ALPHA_EIGER
 
 config ALPHA_JENSEN
 	bool "Jensen"
+	depends on BROKEN
 	help
 	  DEC PC 150 AXP (aka Jensen): This is a very old Digital system - one
 	  of the first-generation Alpha systems. A number of these systems
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index 47f3fba3e41f..9b68790013e2 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
 
-generic-y += clkdev.h
 generic-y += exec.h
 generic-y += export.h
 generic-y += fb.h
diff --git a/arch/alpha/include/asm/asm-prototypes.h b/arch/alpha/include/asm/asm-prototypes.h
index d12c68ea340b..b34cc1f06720 100644
--- a/arch/alpha/include/asm/asm-prototypes.h
+++ b/arch/alpha/include/asm/asm-prototypes.h
@@ -4,7 +4,7 @@
 #include <asm/console.h>
 #include <asm/page.h>
 #include <asm/string.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm-generic/asm-prototypes.h>
 
diff --git a/arch/alpha/include/asm/futex.h b/arch/alpha/include/asm/futex.h
index d2e4da93e68c..ca3322536f72 100644
--- a/arch/alpha/include/asm/futex.h
+++ b/arch/alpha/include/asm/futex.h
@@ -20,8 +20,8 @@
 	"3:	.subsection 2\n"				\
 	"4:	br	1b\n"					\
 	"	.previous\n"					\
-	EXC(1b,3b,%1,$31)					\
-	EXC(2b,3b,%1,$31)					\
+	EXC(1b,3b,$31,%1)					\
+	EXC(2b,3b,$31,%1)					\
 	:	"=&r" (oldval), "=&r"(ret)			\
 	:	"r" (uaddr), "r"(oparg)				\
 	:	"memory")
@@ -82,8 +82,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	"3:	.subsection 2\n"
 	"4:	br	1b\n"
 	"	.previous\n"
-	EXC(1b,3b,%0,$31)
-	EXC(2b,3b,%0,$31)
+	EXC(1b,3b,$31,%0)
+	EXC(2b,3b,$31,%0)
 	:	"+r"(ret), "=&r"(prev), "=&r"(cmp)
 	:	"r"(uaddr), "r"((long)(int)oldval), "r"(newval)
 	:	"memory");
diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h
index bfe784f2d4af..cb05d045efe3 100644
--- a/arch/alpha/include/asm/processor.h
+++ b/arch/alpha/include/asm/processor.h
@@ -40,15 +40,12 @@ typedef struct {
 struct thread_struct { };
 #define INIT_THREAD  { }
 
-/* Return saved PC of a blocked thread.  */
-struct task_struct;
-extern unsigned long thread_saved_pc(struct task_struct *);
-
 /* Do necessary setup to start up a newly executed thread.  */
 struct pt_regs;
 extern void start_thread(struct pt_regs *, unsigned long, unsigned long);
 
 /* Free all resources held by a thread. */
+struct task_struct;
 extern void release_thread(struct task_struct *);
 
 unsigned long get_wchan(struct task_struct *p);
diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h
index 8c20c5e35432..807d7b9a1860 100644
--- a/arch/alpha/include/asm/thread_info.h
+++ b/arch/alpha/include/asm/thread_info.h
@@ -39,9 +39,6 @@ struct thread_info {
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* How to get the thread information struct from C.  */
 register struct thread_info *__current_thread_info __asm__("$8");
 #define current_thread_info()  __current_thread_info
diff --git a/arch/alpha/include/uapi/asm/Kbuild b/arch/alpha/include/uapi/asm/Kbuild
index b15bf6bc0e94..9afaba5e5503 100644
--- a/arch/alpha/include/uapi/asm/Kbuild
+++ b/arch/alpha/include/uapi/asm/Kbuild
@@ -1,2 +1,5 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
+
+generic-y += bpf_perf_event.h
+generic-y += poll.h
diff --git a/arch/alpha/include/uapi/asm/poll.h b/arch/alpha/include/uapi/asm/poll.h
deleted file mode 100644
index b7132a305a47..000000000000
--- a/arch/alpha/include/uapi/asm/poll.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/poll.h>
diff --git a/arch/alpha/include/uapi/asm/termbits.h b/arch/alpha/include/uapi/asm/termbits.h
index 05e0398a83a6..de6c8360fbe3 100644
--- a/arch/alpha/include/uapi/asm/termbits.h
+++ b/arch/alpha/include/uapi/asm/termbits.h
@@ -110,7 +110,11 @@ struct ktermios {
 #define VTDLY	00200000
 #define   VT0	00000000
 #define   VT1	00200000
-#define XTABS	01000000 /* Hmm.. Linux/i386 considers this part of TABDLY.. */
+/*
+ * Should be equivalent to TAB3, see description of TAB3 in
+ * POSIX.1-2008, Ch. 11.2.3 "Output Modes"
+ */
+#define XTABS	TAB3
 
 /* c_cflag bit meaning */
 #define CBAUD	0000037
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index ce3a675c0c4b..fa1a392ca9a2 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -950,22 +950,31 @@ struct itimerval32
 };
 
 static inline long
-get_tv32(struct timeval *o, struct timeval32 __user *i)
+get_tv32(struct timespec64 *o, struct timeval32 __user *i)
 {
 	struct timeval32 tv;
 	if (copy_from_user(&tv, i, sizeof(struct timeval32)))
 		return -EFAULT;
 	o->tv_sec = tv.tv_sec;
-	o->tv_usec = tv.tv_usec;
+	o->tv_nsec = tv.tv_usec * NSEC_PER_USEC;
 	return 0;
 }
 
 static inline long
-put_tv32(struct timeval32 __user *o, struct timeval *i)
+put_tv32(struct timeval32 __user *o, struct timespec64 *i)
 {
 	return copy_to_user(o, &(struct timeval32){
-				.tv_sec = o->tv_sec,
-				.tv_usec = o->tv_usec},
+				.tv_sec = i->tv_sec,
+				.tv_usec = i->tv_nsec / NSEC_PER_USEC},
+			    sizeof(struct timeval32));
+}
+
+static inline long
+put_tv_to_tv32(struct timeval32 __user *o, struct timeval *i)
+{
+	return copy_to_user(o, &(struct timeval32){
+				.tv_sec = i->tv_sec,
+				.tv_usec = i->tv_usec},
 			    sizeof(struct timeval32));
 }
 
@@ -1004,9 +1013,10 @@ SYSCALL_DEFINE2(osf_gettimeofday, struct timeval32 __user *, tv,
 		struct timezone __user *, tz)
 {
 	if (tv) {
-		struct timeval ktv;
-		do_gettimeofday(&ktv);
-		if (put_tv32(tv, &ktv))
+		struct timespec64 kts;
+
+		ktime_get_real_ts64(&kts);
+		if (put_tv32(tv, &kts))
 			return -EFAULT;
 	}
 	if (tz) {
@@ -1019,22 +1029,19 @@ SYSCALL_DEFINE2(osf_gettimeofday, struct timeval32 __user *, tv,
 SYSCALL_DEFINE2(osf_settimeofday, struct timeval32 __user *, tv,
 		struct timezone __user *, tz)
 {
-	struct timespec64 kts64;
-	struct timespec kts;
+	struct timespec64 kts;
 	struct timezone ktz;
 
  	if (tv) {
-		if (get_tv32((struct timeval *)&kts, tv))
+		if (get_tv32(&kts, tv))
 			return -EFAULT;
-		kts.tv_nsec *= 1000;
-		kts64 = timespec_to_timespec64(kts);
 	}
 	if (tz) {
 		if (copy_from_user(&ktz, tz, sizeof(*tz)))
 			return -EFAULT;
 	}
 
-	return do_sys_settimeofday64(tv ? &kts64 : NULL, tz ? &ktz : NULL);
+	return do_sys_settimeofday64(tv ? &kts : NULL, tz ? &ktz : NULL);
 }
 
 asmlinkage long sys_ni_posix_timers(void);
@@ -1083,22 +1090,16 @@ SYSCALL_DEFINE3(osf_setitimer, int, which, struct itimerval32 __user *, in,
 SYSCALL_DEFINE2(osf_utimes, const char __user *, filename,
 		struct timeval32 __user *, tvs)
 {
-	struct timespec tv[2];
+	struct timespec64 tv[2];
 
 	if (tvs) {
-		struct timeval ktvs[2];
-		if (get_tv32(&ktvs[0], &tvs[0]) ||
-		    get_tv32(&ktvs[1], &tvs[1]))
+		if (get_tv32(&tv[0], &tvs[0]) ||
+		    get_tv32(&tv[1], &tvs[1]))
 			return -EFAULT;
 
-		if (ktvs[0].tv_usec < 0 || ktvs[0].tv_usec >= 1000000 ||
-		    ktvs[1].tv_usec < 0 || ktvs[1].tv_usec >= 1000000)
+		if (tv[0].tv_nsec < 0 || tv[0].tv_nsec >= 1000000000 ||
+		    tv[1].tv_nsec < 0 || tv[1].tv_nsec >= 1000000000)
 			return -EINVAL;
-
-		tv[0].tv_sec = ktvs[0].tv_sec;
-		tv[0].tv_nsec = 1000 * ktvs[0].tv_usec;
-		tv[1].tv_sec = ktvs[1].tv_sec;
-		tv[1].tv_nsec = 1000 * ktvs[1].tv_usec;
 	}
 
 	return do_utimes(AT_FDCWD, filename, tvs ? tv : NULL, 0);
@@ -1107,19 +1108,18 @@ SYSCALL_DEFINE2(osf_utimes, const char __user *, filename,
 SYSCALL_DEFINE5(osf_select, int, n, fd_set __user *, inp, fd_set __user *, outp,
 		fd_set __user *, exp, struct timeval32 __user *, tvp)
 {
-	struct timespec end_time, *to = NULL;
+	struct timespec64 end_time, *to = NULL;
 	if (tvp) {
-		struct timeval tv;
+		struct timespec64 tv;
 		to = &end_time;
 
 		if (get_tv32(&tv, tvp))
 		    	return -EFAULT;
 
-		if (tv.tv_sec < 0 || tv.tv_usec < 0)
+		if (tv.tv_sec < 0 || tv.tv_nsec < 0)
 			return -EINVAL;
 
-		if (poll_select_set_timeout(to, tv.tv_sec,
-					    tv.tv_usec * NSEC_PER_USEC))
+		if (poll_select_set_timeout(to, tv.tv_sec, tv.tv_nsec))
 			return -EINVAL;		
 
 	}
@@ -1192,9 +1192,9 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 		return -EFAULT;
 	if (!ur)
 		return err;
-	if (put_tv32(&ur->ru_utime, &r.ru_utime))
+	if (put_tv_to_tv32(&ur->ru_utime, &r.ru_utime))
 		return -EFAULT;
-	if (put_tv32(&ur->ru_stime, &r.ru_stime))
+	if (put_tv_to_tv32(&ur->ru_stime, &r.ru_stime))
 		return -EFAULT;
 	if (copy_to_user(&ur->ru_maxrss, &r.ru_maxrss,
 	      sizeof(struct rusage32) - offsetof(struct rusage32, ru_maxrss)))
@@ -1210,18 +1210,18 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 SYSCALL_DEFINE2(osf_usleep_thread, struct timeval32 __user *, sleep,
 		struct timeval32 __user *, remain)
 {
-	struct timeval tmp;
+	struct timespec64 tmp;
 	unsigned long ticks;
 
 	if (get_tv32(&tmp, sleep))
 		goto fault;
 
-	ticks = timeval_to_jiffies(&tmp);
+	ticks = timespec64_to_jiffies(&tmp);
 
 	ticks = schedule_timeout_interruptible(ticks);
 
 	if (remain) {
-		jiffies_to_timeval(ticks, &tmp);
+		jiffies_to_timespec64(ticks, &tmp);
 		if (put_tv32(remain, &tmp))
 			goto fault;
 	}
@@ -1280,7 +1280,7 @@ SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p)
 	if (copy_to_user(txc_p, &txc, offsetof(struct timex32, time)) ||
 	    (copy_to_user(&txc_p->tick, &txc.tick, sizeof(struct timex32) - 
 			  offsetof(struct timex32, tick))) ||
-	    (put_tv32(&txc_p->time, &txc.time)))
+	    (put_tv_to_tv32(&txc_p->time, &txc.time)))
 	  return -EFAULT;
 
 	return ret;
diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c
index 87da00579946..2e86ebb680ae 100644
--- a/arch/alpha/kernel/pci.c
+++ b/arch/alpha/kernel/pci.c
@@ -425,7 +425,7 @@ sys_pciconfig_iobase(long which, unsigned long bus, unsigned long dfn)
 		if (bus == 0 && dfn == 0) {
 			hose = pci_isa_hose;
 		} else {
-			dev = pci_get_bus_and_slot(bus, dfn);
+			dev = pci_get_domain_bus_and_slot(0, bus, dfn);
 			if (!dev)
 				return -ENODEV;
 			hose = dev->sysdata;
diff --git a/arch/alpha/kernel/pci_impl.h b/arch/alpha/kernel/pci_impl.h
index 2e4cb74fdc41..18043af45e2b 100644
--- a/arch/alpha/kernel/pci_impl.h
+++ b/arch/alpha/kernel/pci_impl.h
@@ -144,7 +144,8 @@ struct pci_iommu_arena
 };
 
 #if defined(CONFIG_ALPHA_SRM) && \
-    (defined(CONFIG_ALPHA_CIA) || defined(CONFIG_ALPHA_LCA))
+    (defined(CONFIG_ALPHA_CIA) || defined(CONFIG_ALPHA_LCA) || \
+     defined(CONFIG_ALPHA_AVANTI))
 # define NEED_SRM_SAVE_RESTORE
 #else
 # undef NEED_SRM_SAVE_RESTORE
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 74bfb1f2d68e..48b81d015d8a 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -269,12 +269,13 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 	   application calling fork.  */
 	if (clone_flags & CLONE_SETTLS)
 		childti->pcb.unique = regs->r20;
+	else
+		regs->r20 = 0;	/* OSF/1 has some strange fork() semantics.  */
 	childti->pcb.usp = usp ?: rdusp();
 	*childregs = *regs;
 	childregs->r0 = 0;
 	childregs->r19 = 0;
 	childregs->r20 = 1;	/* OSF/1 has some strange fork() semantics.  */
-	regs->r20 = 0;
 	stack = ((struct switch_stack *) regs) - 1;
 	*childstack = *stack;
 	childstack->r26 = (unsigned long) ret_from_fork;
@@ -361,7 +362,7 @@ EXPORT_SYMBOL(dump_elf_task_fp);
  * all.  -- r~
  */
 
-unsigned long
+static unsigned long
 thread_saved_pc(struct task_struct *t)
 {
 	unsigned long base = (unsigned long)task_stack_page(t);
diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 239dc0e601d5..ff4f54b86c7f 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -237,7 +237,7 @@ nautilus_init_pci(void)
 	bus = hose->bus = bridge->bus;
 	pcibios_claim_one_bus(bus);
 
-	irongate = pci_get_bus_and_slot(0, 0);
+	irongate = pci_get_domain_bus_and_slot(pci_domain_nr(bus), 0, 0);
 	bus->self = irongate;
 	bus->resource[0] = &irongate_io;
 	bus->resource[1] = &irongate_mem;
diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c
index 37bd6d9b8eb9..a6bdc1da47ad 100644
--- a/arch/alpha/kernel/sys_sio.c
+++ b/arch/alpha/kernel/sys_sio.c
@@ -102,6 +102,15 @@ sio_pci_route(void)
 				   alpha_mv.sys.sio.route_tab);
 }
 
+static bool sio_pci_dev_irq_needs_level(const struct pci_dev *dev)
+{
+	if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) &&
+	    (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA))
+		return false;
+
+	return true;
+}
+
 static unsigned int __init
 sio_collect_irq_levels(void)
 {
@@ -110,8 +119,7 @@ sio_collect_irq_levels(void)
 
 	/* Iterate through the devices, collecting IRQ levels.  */
 	for_each_pci_dev(dev) {
-		if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) &&
-		    (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA))
+		if (!sio_pci_dev_irq_needs_level(dev))
 			continue;
 
 		if (dev->irq)
@@ -120,8 +128,7 @@ sio_collect_irq_levels(void)
 	return level_bits;
 }
 
-static void __init
-sio_fixup_irq_levels(unsigned int level_bits)
+static void __sio_fixup_irq_levels(unsigned int level_bits, bool reset)
 {
 	unsigned int old_level_bits;
 
@@ -139,12 +146,21 @@ sio_fixup_irq_levels(unsigned int level_bits)
 	 */
 	old_level_bits = inb(0x4d0) | (inb(0x4d1) << 8);
 
-	level_bits |= (old_level_bits & 0x71ff);
+	if (reset)
+		old_level_bits &= 0x71ff;
+
+	level_bits |= old_level_bits;
 
 	outb((level_bits >> 0) & 0xff, 0x4d0);
 	outb((level_bits >> 8) & 0xff, 0x4d1);
 }
 
+static inline void
+sio_fixup_irq_levels(unsigned int level_bits)
+{
+	__sio_fixup_irq_levels(level_bits, true);
+}
+
 static inline int
 noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
@@ -181,7 +197,14 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	const long min_idsel = 6, max_idsel = 14, irqs_per_slot = 5;
 	int irq = COMMON_TABLE_LOOKUP, tmp;
 	tmp = __kernel_extbl(alpha_mv.sys.sio.route_tab, irq);
-	return irq >= 0 ? tmp : -1;
+
+	irq = irq >= 0 ? tmp : -1;
+
+	/* Fixup IRQ level if an actual IRQ mapping is detected */
+	if (sio_pci_dev_irq_needs_level(dev) && irq >= 0)
+		__sio_fixup_irq_levels(1 << irq, false);
+
+	return irq;
 }
 
 static inline int
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index 4bd99a7b1c41..f43bd05dede2 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -160,11 +160,16 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 	for(i=0; i < kstack_depth_to_print; i++) {
 		if (((long) stack & (THREAD_SIZE-1)) == 0)
 			break;
-		if (i && ((i % 4) == 0))
-			printk("\n       ");
-		printk("%016lx ", *stack++);
+		if ((i % 4) == 0) {
+			if (i)
+				pr_cont("\n");
+			printk("       ");
+		} else {
+			pr_cont(" ");
+		}
+		pr_cont("%016lx", *stack++);
 	}
-	printk("\n");
+	pr_cont("\n");
 	dik_show_trace(sp);
 }
 
diff --git a/arch/alpha/lib/ev6-memset.S b/arch/alpha/lib/ev6-memset.S
index 316a99aa9efe..1cfcfbbea6f0 100644
--- a/arch/alpha/lib/ev6-memset.S
+++ b/arch/alpha/lib/ev6-memset.S
@@ -18,7 +18,7 @@
  * The algorithm for the leading and trailing quadwords remains the same,
  * however the loop has been unrolled to enable better memory throughput,
  * and the code has been replicated for each of the entry points: __memset
- * and __memsetw to permit better scheduling to eliminate the stalling
+ * and __memset16 to permit better scheduling to eliminate the stalling
  * encountered during the mask replication.
  * A future enhancement might be to put in a byte store loop for really
  * small (say < 32 bytes) memset()s.  Whether or not that change would be
@@ -34,7 +34,7 @@
 	.globl memset
 	.globl __memset
 	.globl ___memset
-	.globl __memsetw
+	.globl __memset16
 	.globl __constant_c_memset
 
 	.ent ___memset
@@ -415,9 +415,9 @@ end:
 	 * to mask stalls.  Note that entry point names also had to change
 	 */
 	.align 5
-	.ent __memsetw
+	.ent __memset16
 
-__memsetw:
+__memset16:
 	.frame $30,0,$26,0
 	.prologue 0
 
@@ -596,8 +596,8 @@ end_w:
 	nop
 	ret $31,($26),1		# L0 :
 
-	.end __memsetw
-	EXPORT_SYMBOL(__memsetw)
+	.end __memset16
+	EXPORT_SYMBOL(__memset16)
 
 memset = ___memset
 __memset = ___memset
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 9d5fd00d9e91..f3a80cf164cc 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -463,9 +463,6 @@ config ARCH_PHYS_ADDR_T_64BIT
 config ARCH_DMA_ADDR_T_64BIT
 	bool
 
-config ARC_PLAT_NEEDS_PHYS_TO_DMA
-	bool
-
 config ARC_KVADDR_SIZE
 	int "Kernel Virtual Address Space size (MB)"
 	range 0 512
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index 4e6e9f57e790..dc91c663bcc0 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -35,6 +35,14 @@
 			reg = <0x80 0x10>, <0x100 0x10>;
 			#clock-cells = <0>;
 			clocks = <&input_clk>;
+
+			/*
+			 * Set initial core pll output frequency to 90MHz.
+			 * It will be applied at the core pll driver probing
+			 * on early boot.
+			 */
+			assigned-clocks = <&core_clk>;
+			assigned-clock-rates = <90000000>;
 		};
 
 		core_intc: archs-intc@cpu {
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index 63954a8b0100..69ff4895f2ba 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -35,6 +35,14 @@
 			reg = <0x80 0x10>, <0x100 0x10>;
 			#clock-cells = <0>;
 			clocks = <&input_clk>;
+
+			/*
+			 * Set initial core pll output frequency to 100MHz.
+			 * It will be applied at the core pll driver probing
+			 * on early boot.
+			 */
+			assigned-clocks = <&core_clk>;
+			assigned-clock-rates = <100000000>;
 		};
 
 		core_intc: archs-intc@cpu {
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 8f627c200d60..006aa3de5348 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -114,6 +114,14 @@
 			reg = <0x00 0x10>, <0x14B8 0x4>;
 			#clock-cells = <0>;
 			clocks = <&input_clk>;
+
+			/*
+			 * Set initial core pll output frequency to 1GHz.
+			 * It will be applied at the core pll driver probing
+			 * on early boot.
+			 */
+			assigned-clocks = <&core_clk>;
+			assigned-clock-rates = <1000000000>;
 		};
 
 		serial: serial@5000 {
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index ec7c849a5c8e..09f85154c5a4 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -44,7 +44,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_NETDEVICES=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 63d3cf69e0b0..09fed3ef22b6 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -44,7 +44,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index f613ecac14a7..ea2f6d817d1a 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -45,7 +45,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig
index db04ea4dd2d9..ab231c040efe 100644
--- a/arch/arc/configs/haps_hs_defconfig
+++ b/arch/arc/configs/haps_hs_defconfig
@@ -40,7 +40,6 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
 # CONFIG_NET_VENDOR_ARC is not set
diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig
index 3507be2af6fe..cf449cbf440d 100644
--- a/arch/arc/configs/haps_hs_smp_defconfig
+++ b/arch/arc/configs/haps_hs_smp_defconfig
@@ -43,7 +43,6 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
 # CONFIG_NET_VENDOR_ARC is not set
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 7b8f8faf8a24..1b54c72f4296 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -32,7 +32,6 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_NETDEVICES=y
@@ -49,10 +48,11 @@ CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
+CONFIG_DRM=y
+# CONFIG_DRM_FBDEV_EMULATION is not set
+CONFIG_DRM_UDL=y
 CONFIG_FB=y
-CONFIG_FB_UDL=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_OHCI_HCD=y
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
index 6dff83a238b8..31c2c70b34a1 100644
--- a/arch/arc/configs/nsim_700_defconfig
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -36,7 +36,6 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
 CONFIG_ARC_EMAC=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index 31ee51b987e7..a578c721d50f 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -40,7 +40,6 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 # CONFIG_INPUT_KEYBOARD is not set
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index 8d3b1f67cae4..37d7395f3272 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -39,7 +39,6 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 # CONFIG_INPUT_KEYBOARD is not set
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 6168ce2ac2ef..1e1470e2a7f0 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -35,7 +35,6 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
 CONFIG_EZCHIP_NPS_MANAGEMENT_ENET=y
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index a70bdeb2b3fd..084a6e42685b 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -36,7 +36,6 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
 CONFIG_EZCHIP_NPS_MANAGEMENT_ENET=y
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index ef96406c446e..f36d47990415 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -39,7 +39,6 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
 # CONFIG_NET_VENDOR_ARC is not set
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
index f30182549395..1aca2e8fd1ba 100644
--- a/arch/arc/configs/tb10x_defconfig
+++ b/arch/arc/configs/tb10x_defconfig
@@ -42,7 +42,6 @@ CONFIG_IP_MULTICAST=y
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_NETDEVICES=y
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
index 4fcf4f2503f6..f629493929ea 100644
--- a/arch/arc/configs/vdk_hs38_defconfig
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -31,7 +31,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index 7b71464f6c2f..21f0ca26a05d 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -34,7 +34,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index cd8398daccee..4bd5d4369e05 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 generic-y += bugs.h
-generic-y += clkdev.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h
index 94285031c4fb..7a16824bfe98 100644
--- a/arch/arc/include/asm/dma-mapping.h
+++ b/arch/arc/include/asm/dma-mapping.h
@@ -11,13 +11,6 @@
 #ifndef ASM_ARC_DMA_MAPPING_H
 #define ASM_ARC_DMA_MAPPING_H
 
-#ifndef CONFIG_ARC_PLAT_NEEDS_PHYS_TO_DMA
-#define plat_dma_to_phys(dev, dma_handle) ((phys_addr_t)(dma_handle))
-#define plat_phys_to_dma(dev, paddr) ((dma_addr_t)(paddr))
-#else
-#include <plat/dma.h>
-#endif
-
 extern const struct dma_map_ops arc_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
index b18fcb606908..dc8ee011882f 100644
--- a/arch/arc/include/asm/hugepage.h
+++ b/arch/arc/include/asm/hugepage.h
@@ -74,4 +74,7 @@ extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 extern void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 				unsigned long end);
 
+/* We don't have hardware dirty/accessed bits, generic_pmdp_establish is fine.*/
+#define pmdp_establish generic_pmdp_establish
+
 #endif
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 2d79e527fa50..c85947bac5e5 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -62,9 +62,6 @@ struct thread_info {
 	.addr_limit = KERNEL_DS,		\
 }
 
-#define init_thread_info    (init_thread_union.thread_info)
-#define init_stack          (init_thread_union.stack)
-
 static inline __attribute_const__ struct thread_info *current_thread_info(void)
 {
 	register unsigned long sp asm("sp");
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index f35974ee7264..c9173c02081c 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -668,6 +668,7 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count)
 		return 0;
 
 	__asm__ __volatile__(
+	"	mov	lp_count, %5		\n"
 	"	lp	3f			\n"
 	"1:	ldb.ab  %3, [%2, 1]		\n"
 	"	breq.d	%3, 0, 3f               \n"
@@ -684,8 +685,8 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count)
 	"	.word   1b, 4b			\n"
 	"	.previous			\n"
 	: "+r"(res), "+r"(dst), "+r"(src), "=r"(val)
-	: "g"(-EFAULT), "l"(count)
-	: "memory");
+	: "g"(-EFAULT), "r"(count)
+	: "lp_count", "lp_start", "lp_end", "memory");
 
 	return res;
 }
diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild
index fa6d0ff4ff89..170b5db64afe 100644
--- a/arch/arc/include/uapi/asm/Kbuild
+++ b/arch/arc/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 7ef7d9a8ff89..9d27331fe69a 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -199,7 +199,7 @@ static void read_arc_build_cfg_regs(void)
 			unsigned int exec_ctrl;
 
 			READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
-			cpu->extn.dual_enb = exec_ctrl & 1;
+			cpu->extn.dual_enb = !(exec_ctrl & 1);
 
 			/* dual issue always present for this core */
 			cpu->extn.dual = 1;
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index 74315f302971..bf40e06f3fb8 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -163,7 +163,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
  */
 static int __print_sym(unsigned int address, void *unused)
 {
-	__print_symbol("  %s\n", address);
+	printk("  %pS\n", (void *)address);
 	return 0;
 }
 
diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c
index bcd7c9fc5d0f..b123558bf0bb 100644
--- a/arch/arc/kernel/traps.c
+++ b/arch/arc/kernel/traps.c
@@ -65,12 +65,14 @@ unhandled_exception(const char *str, struct pt_regs *regs, siginfo_t *info)
 #define DO_ERROR_INFO(signr, str, name, sicode) \
 int name(unsigned long address, struct pt_regs *regs) \
 {						\
-	siginfo_t info = {			\
-		.si_signo = signr,		\
-		.si_errno = 0,			\
-		.si_code  = sicode,		\
-		.si_addr = (void __user *)address,	\
-	};					\
+	siginfo_t info;				\
+						\
+	clear_siginfo(&info);			\
+	info.si_signo = signr;			\
+	info.si_errno = 0;			\
+	info.si_code  = sicode;			\
+	info.si_addr = (void __user *)address;	\
+						\
 	return unhandled_exception(str, regs, &info);\
 }
 
@@ -83,6 +85,7 @@ DO_ERROR_INFO(SIGILL, "Illegal Insn (or Seq)", insterror_is_error, ILL_ILLOPC)
 DO_ERROR_INFO(SIGBUS, "Invalid Mem Access", __weak do_memory_error, BUS_ADRERR)
 DO_ERROR_INFO(SIGTRAP, "Breakpoint Set", trap_is_brkpt, TRAP_BRKPT)
 DO_ERROR_INFO(SIGBUS, "Misaligned Access", do_misaligned_error, BUS_ADRALN)
+DO_ERROR_INFO(SIGSEGV, "gcc generated __builtin_trap", do_trap5_error, 0)
 
 /*
  * Entry Point for Misaligned Data access Exception, for emulating in software
@@ -115,6 +118,8 @@ void do_machine_check_fault(unsigned long address, struct pt_regs *regs)
  * Thus TRAP_S <n> can be used for specific purpose
  *  -1 used for software breakpointing (gdb)
  *  -2 used by kprobes
+ *  -5 __builtin_trap() generated by gcc (2018.03 onwards) for toggle such as
+ *     -fno-isolate-erroneous-paths-dereference
  */
 void do_non_swi_trap(unsigned long address, struct pt_regs *regs)
 {
@@ -134,6 +139,9 @@ void do_non_swi_trap(unsigned long address, struct pt_regs *regs)
 		kgdb_trap(regs);
 		break;
 
+	case 5:
+		do_trap5_error(address, regs);
+		break;
 	default:
 		break;
 	}
@@ -155,3 +163,11 @@ void do_insterror_or_kprobe(unsigned long address, struct pt_regs *regs)
 
 	insterror_is_error(address, regs);
 }
+
+/*
+ * abort() call generated by older gcc for __builtin_trap()
+ */
+void abort(void)
+{
+	__asm__ __volatile__("trap_s  5\n");
+}
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 7d8c1d6c2f60..6e9a0a9a6a04 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -163,6 +163,9 @@ static void show_ecr_verbose(struct pt_regs *regs)
 		else
 			pr_cont("Bus Error, check PRM\n");
 #endif
+	} else if (vec == ECR_V_TRAP) {
+		if (regs->ecr_param == 5)
+			pr_cont("gcc generated __builtin_trap\n");
 	} else {
 		pr_cont("Check Programmer's Manual\n");
 	}
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index e9d93604ad0f..1dcc404b5aec 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -60,7 +60,7 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
 	/* This is linear addr (0x8000_0000 based) */
 	paddr = page_to_phys(page);
 
-	*dma_handle = plat_phys_to_dma(dev, paddr);
+	*dma_handle = paddr;
 
 	/* This is kernel Virtual address (0x7000_0000 based) */
 	if (need_kvaddr) {
@@ -92,7 +92,7 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
 static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
-	phys_addr_t paddr = plat_dma_to_phys(dev, dma_handle);
+	phys_addr_t paddr = dma_handle;
 	struct page *page = virt_to_page(paddr);
 	int is_non_coh = 1;
 
@@ -111,7 +111,7 @@ static int arc_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 {
 	unsigned long user_count = vma_pages(vma);
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long pfn = __phys_to_pfn(plat_dma_to_phys(dev, dma_addr));
+	unsigned long pfn = __phys_to_pfn(dma_addr);
 	unsigned long off = vma->vm_pgoff;
 	int ret = -ENXIO;
 
@@ -175,7 +175,7 @@ static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page,
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		_dma_cache_sync(paddr, size, dir);
 
-	return plat_phys_to_dma(dev, paddr);
+	return paddr;
 }
 
 /*
@@ -190,7 +190,7 @@ static void arc_dma_unmap_page(struct device *dev, dma_addr_t handle,
 			       size_t size, enum dma_data_direction dir,
 			       unsigned long attrs)
 {
-	phys_addr_t paddr = plat_dma_to_phys(dev, handle);
+	phys_addr_t paddr = handle;
 
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		_dma_cache_sync(paddr, size, dir);
@@ -224,13 +224,13 @@ static void arc_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 static void arc_dma_sync_single_for_cpu(struct device *dev,
 		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
 {
-	_dma_cache_sync(plat_dma_to_phys(dev, dma_handle), size, DMA_FROM_DEVICE);
+	_dma_cache_sync(dma_handle, size, DMA_FROM_DEVICE);
 }
 
 static void arc_dma_sync_single_for_device(struct device *dev,
 		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
 {
-	_dma_cache_sync(plat_dma_to_phys(dev, dma_handle), size, DMA_TO_DEVICE);
+	_dma_cache_sync(dma_handle, size, DMA_TO_DEVICE);
 }
 
 static void arc_dma_sync_sg_for_cpu(struct device *dev,
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
index f1ac6790da5f..46544e88492d 100644
--- a/arch/arc/plat-axs10x/axs10x.c
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -317,25 +317,23 @@ static void __init axs103_early_init(void)
 	 * Instead of duplicating defconfig/DT for SMP/QUAD, add a small hack
 	 * of fudging the freq in DT
 	 */
+#define AXS103_QUAD_CORE_CPU_FREQ_HZ	50000000
+
 	unsigned int num_cores = (read_aux_reg(ARC_REG_MCIP_BCR) >> 16) & 0x3F;
 	if (num_cores > 2) {
-		u32 freq = 50, orig;
-		/*
-		 * TODO: use cpu node "cpu-freq" param instead of platform-specific
-		 * "/cpu_card/core_clk" as it works only if we use fixed-clock for cpu.
-		 */
+		u32 freq;
 		int off = fdt_path_offset(initial_boot_params, "/cpu_card/core_clk");
 		const struct fdt_property *prop;
 
 		prop = fdt_get_property(initial_boot_params, off,
-					"clock-frequency", NULL);
-		orig = be32_to_cpu(*(u32*)(prop->data)) / 1000000;
+					"assigned-clock-rates", NULL);
+		freq = be32_to_cpu(*(u32 *)(prop->data));
 
 		/* Patching .dtb in-place with new core clock value */
-		if (freq != orig ) {
-			freq = cpu_to_be32(freq * 1000000);
+		if (freq != AXS103_QUAD_CORE_CPU_FREQ_HZ) {
+			freq = cpu_to_be32(AXS103_QUAD_CORE_CPU_FREQ_HZ);
 			fdt_setprop_inplace(initial_boot_params, off,
-					    "clock-frequency", &freq, sizeof(freq));
+					    "assigned-clock-rates", &freq, sizeof(freq));
 		}
 	}
 #endif
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index fd0ae5e38639..2958aedb649a 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -38,42 +38,6 @@ static void __init hsdk_init_per_cpu(unsigned int cpu)
 #define CREG_PAE		(CREG_BASE + 0x180)
 #define CREG_PAE_UPDATE		(CREG_BASE + 0x194)
 
-#define CREG_CORE_IF_CLK_DIV	(CREG_BASE + 0x4B8)
-#define CREG_CORE_IF_CLK_DIV_2	0x1
-#define CGU_BASE		ARC_PERIPHERAL_BASE
-#define CGU_PLL_STATUS		(ARC_PERIPHERAL_BASE + 0x4)
-#define CGU_PLL_CTRL		(ARC_PERIPHERAL_BASE + 0x0)
-#define CGU_PLL_STATUS_LOCK	BIT(0)
-#define CGU_PLL_STATUS_ERR	BIT(1)
-#define CGU_PLL_CTRL_1GHZ	0x3A10
-#define HSDK_PLL_LOCK_TIMEOUT	500
-
-#define HSDK_PLL_LOCKED() \
-	!!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_LOCK)
-
-#define HSDK_PLL_ERR() \
-	!!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_ERR)
-
-static void __init hsdk_set_cpu_freq_1ghz(void)
-{
-	u32 timeout = HSDK_PLL_LOCK_TIMEOUT;
-
-	/*
-	 * As we set cpu clock which exceeds 500MHz, the divider for the interface
-	 * clock must be programmed to div-by-2.
-	 */
-	iowrite32(CREG_CORE_IF_CLK_DIV_2, (void __iomem *) CREG_CORE_IF_CLK_DIV);
-
-	/* Set cpu clock to 1GHz */
-	iowrite32(CGU_PLL_CTRL_1GHZ, (void __iomem *) CGU_PLL_CTRL);
-
-	while (!HSDK_PLL_LOCKED() && timeout--)
-		cpu_relax();
-
-	if (!HSDK_PLL_LOCKED() || HSDK_PLL_ERR())
-		pr_err("Failed to setup CPU frequency to 1GHz!");
-}
-
 #define SDIO_BASE		(ARC_PERIPHERAL_BASE + 0xA000)
 #define SDIO_UHS_REG_EXT	(SDIO_BASE + 0x108)
 #define SDIO_UHS_REG_EXT_DIV_2	(2 << 30)
@@ -98,12 +62,6 @@ static void __init hsdk_init_early(void)
 	 * minimum possible div-by-2.
 	 */
 	iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT);
-
-	/*
-	 * Setup CPU frequency to 1GHz.
-	 * TODO: remove it after smart hsdk pll driver will be introduced.
-	 */
-	hsdk_set_cpu_freq_1ghz();
 }
 
 static const char *hsdk_compat[] __initconst = {
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 51c8df561077..4daddc53e7bc 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -3,11 +3,12 @@ config ARM
 	bool
 	default y
 	select ARCH_CLOCKSOURCE_DATA
-	select ARCH_DISCARD_MEMBLOCK if !HAVE_ARCH_PFN_VALID
-	select ARCH_HAS_DEBUG_VIRTUAL
+	select ARCH_DISCARD_MEMBLOCK if !HAVE_ARCH_PFN_VALID && !KEXEC
+	select ARCH_HAS_DEBUG_VIRTUAL if MMU
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_SET_MEMORY
+	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
 	select ARCH_HAS_STRICT_MODULE_RWX if MMU
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
@@ -24,7 +25,7 @@ config ARM
 	select CLONE_BACKWARDS
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select DMA_NOOP_OPS if !MMU
+	select DMA_DIRECT_OPS if !MMU
 	select EDAC_SUPPORT
 	select EDAC_ATOMIC_SCRUB
 	select GENERIC_ALLOCATOR
@@ -99,6 +100,7 @@ config ARM
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
 	select PERF_USE_VMALLOC
+	select REFCOUNT_FULL
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
 	# Above selects are sorted alphabetically; please add new ones
@@ -595,6 +597,7 @@ config ARCH_S3C24XX
 	select MULTI_IRQ_HANDLER
 	select NEED_MACH_IO_H
 	select SAMSUNG_ATAGS
+	select USE_OF
 	help
 	  Samsung S3C2410, S3C2412, S3C2413, S3C2416, S3C2440, S3C2442, S3C2443
 	  and S3C2450 SoCs based systems, such as the Simtec Electronics BAST
@@ -1524,12 +1527,10 @@ config THUMB2_KERNEL
 	bool "Compile the kernel in Thumb-2 mode" if !CPU_THUMBONLY
 	depends on (CPU_V7 || CPU_V7M) && !CPU_V6 && !CPU_V6K
 	default y if CPU_THUMBONLY
-	select ARM_ASM_UNIFIED
 	select ARM_UNWIND
 	help
 	  By enabling this option, the kernel will be compiled in
-	  Thumb-2 mode. A compiler/assembler that understand the unified
-	  ARM-Thumb syntax is needed.
+	  Thumb-2 mode.
 
 	  If unsure, say N.
 
@@ -1564,9 +1565,6 @@ config THUMB2_AVOID_R_ARM_THM_JUMP11
 
 	  Unless you are sure your tools don't have this problem, say Y.
 
-config ARM_ASM_UNIFIED
-	bool
-
 config ARM_PATCH_IDIV
 	bool "Runtime patch udiv/sdiv instructions into __aeabi_{u}idiv()"
 	depends on CPU_32v7 && !XIP_KERNEL
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 17685e19aed8..78a647080ebc 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -3,10 +3,14 @@ menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
 
-config ARM_PTDUMP
+config ARM_PTDUMP_CORE
+	def_bool n
+
+config ARM_PTDUMP_DEBUGFS
 	bool "Export kernel pagetable layout to userspace via debugfs"
 	depends on DEBUG_KERNEL
 	depends on MMU
+	select ARM_PTDUMP_CORE
 	select DEBUG_FS
 	---help---
 	  Say Y here if you want to show the kernel pagetable layout in a
@@ -16,6 +20,33 @@ config ARM_PTDUMP
 	  kernel.
 	  If in doubt, say "N"
 
+config DEBUG_WX
+	bool "Warn on W+X mappings at boot"
+	select ARM_PTDUMP_CORE
+	---help---
+		Generate a warning if any W+X mappings are found at boot.
+
+		This is useful for discovering cases where the kernel is leaving
+		W+X mappings after applying NX, as such mappings are a security risk.
+
+		Look for a message in dmesg output like this:
+
+			arm/mm: Checked W+X mappings: passed, no W+X pages found.
+
+		or like this, if the check failed:
+
+			arm/mm: Checked W+X mappings: FAILED, <N> W+X pages found.
+
+		Note that even if the check fails, your kernel is possibly
+		still fine, as W+X mappings are not a security hole in
+		themselves, what they do is that they make the exploitation
+		of other unfixed kernel bugs easier.
+
+		There is no runtime or memory usage effect of this option
+		once the kernel has booted up - it's a one time check.
+
+		If in doubt, say "Y".
+
 # RMK wants arm kernels compiled with frame pointers or stack unwinding.
 # If you know what you are doing and are willing to live without stack
 # traces, you can get a slightly smaller kernel by setting this option to
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 80351e505fd5..e83f5161fdd8 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -115,9 +115,11 @@ ifeq ($(CONFIG_ARM_UNWIND),y)
 CFLAGS_ABI	+=-funwind-tables
 endif
 
+# Accept old syntax despite ".syntax unified"
+AFLAGS_NOWARN	:=$(call as-option,-Wa$(comma)-mno-warn-deprecated,-Wa$(comma)-W)
+
 ifeq ($(CONFIG_THUMB2_KERNEL),y)
 AFLAGS_AUTOIT	:=$(call as-option,-Wa$(comma)-mimplicit-it=always,-Wa$(comma)-mauto-it)
-AFLAGS_NOWARN	:=$(call as-option,-Wa$(comma)-mno-warn-deprecated,-Wa$(comma)-W)
 CFLAGS_ISA	:=-mthumb $(AFLAGS_AUTOIT) $(AFLAGS_NOWARN)
 AFLAGS_ISA	:=$(CFLAGS_ISA) -Wa$(comma)-mthumb
 # Work around buggy relocation from gas if requested:
@@ -125,7 +127,7 @@ ifeq ($(CONFIG_THUMB2_AVOID_R_ARM_THM_JUMP11),y)
 KBUILD_CFLAGS_MODULE	+=-fno-optimize-sibling-calls
 endif
 else
-CFLAGS_ISA	:=$(call cc-option,-marm,)
+CFLAGS_ISA	:=$(call cc-option,-marm,) $(AFLAGS_NOWARN)
 AFLAGS_ISA	:=$(CFLAGS_ISA)
 endif
 
diff --git a/arch/arm/boot/compressed/string.c b/arch/arm/boot/compressed/string.c
index 309e1bbad75d..13c90abc68d6 100644
--- a/arch/arm/boot/compressed/string.c
+++ b/arch/arm/boot/compressed/string.c
@@ -130,8 +130,3 @@ void *memset(void *s, int c, size_t count)
 		*xs++ = c;
 	return s;
 }
-
-void __memzero(void *s, size_t count)
-{
-	memset(s, 0, count);
-}
diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S
index e6bf6774c4bb..2b963d8e76dd 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.S
+++ b/arch/arm/boot/compressed/vmlinux.lds.S
@@ -56,6 +56,7 @@ SECTIONS
   .rodata : {
     *(.rodata)
     *(.rodata.*)
+    *(.data.rel.ro)
   }
   .piggydata : {
     *(.piggydata)
@@ -101,6 +102,12 @@ SECTIONS
    * this symbol allows further debug in the near future.
    */
   .image_end (NOLOAD) : {
+    /*
+     * EFI requires that the image is aligned to 512 bytes, and appended
+     * DTB requires that we know where the end of the image is.  Ensure
+     * that both are satisfied by ensuring that there are no additional
+     * sections emitted into the decompressor image.
+     */
     _edata_real = .;
   }
 
@@ -128,3 +135,4 @@ SECTIONS
   .stab.indexstr 0	: { *(.stab.indexstr) }
   .comment 0		: { *(.comment) }
 }
+ASSERT(_edata_real == _edata, "error: zImage file size is incorrect");
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index d0381e9caf21..ade7a38543dc 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -1,6 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-ifeq ($(CONFIG_OF),y)
-
 dtb-$(CONFIG_ARCH_ALPINE) += \
 	alpine-db.dtb
 dtb-$(CONFIG_MACH_ARTPEC6) += \
@@ -47,7 +45,9 @@ dtb-$(CONFIG_SOC_AT91SAM9) += \
 	at91sam9x35ek.dtb
 dtb-$(CONFIG_SOC_SAM_V7) += \
 	at91-kizbox2.dtb \
+	at91-nattis-2-natte-2.dtb \
 	at91-sama5d27_som1_ek.dtb \
+	at91-sama5d2_ptc_ek.dtb \
 	at91-sama5d2_xplained.dtb \
 	at91-sama5d3_xplained.dtb \
 	at91-tse850-3.dtb \
@@ -192,6 +192,7 @@ dtb-$(CONFIG_ARCH_EXYNOS5) += \
 	exynos5800-peach-pi.dtb
 dtb-$(CONFIG_ARCH_GEMINI) += \
 	gemini-dlink-dir-685.dtb \
+	gemini-dlink-dns-313.dtb \
 	gemini-nas4220b.dtb \
 	gemini-rut1xx.dtb \
 	gemini-sq201.dtb \
@@ -372,6 +373,8 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6dl-aristainetos2_7.dtb \
 	imx6dl-colibri-eval-v3.dtb \
 	imx6dl-cubox-i.dtb \
+	imx6dl-cubox-i-emmc-som-v15.dtb \
+	imx6dl-cubox-i-som-v15.dtb \
 	imx6dl-dfi-fs700-m60.dtb \
 	imx6dl-gw51xx.dtb \
 	imx6dl-gw52xx.dtb \
@@ -384,6 +387,11 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6dl-gw5903.dtb \
 	imx6dl-gw5904.dtb \
 	imx6dl-hummingboard.dtb \
+	imx6dl-hummingboard-emmc-som-v15.dtb \
+	imx6dl-hummingboard-som-v15.dtb \
+	imx6dl-hummingboard2.dtb \
+	imx6dl-hummingboard2-emmc-som-v15.dtb \
+	imx6dl-hummingboard2-som-v15.dtb \
 	imx6dl-icore.dtb \
 	imx6dl-icore-rqs.dtb \
 	imx6dl-nit6xlite.dtb \
@@ -396,6 +404,7 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6dl-sabresd.dtb \
 	imx6dl-savageboard.dtb \
 	imx6dl-ts4900.dtb \
+	imx6dl-ts7970.dtb \
 	imx6dl-tx6dl-comtft.dtb \
 	imx6dl-tx6s-8034.dtb \
 	imx6dl-tx6s-8034-mb7.dtb \
@@ -421,6 +430,8 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6q-b850v3.dtb \
 	imx6q-cm-fx6.dtb \
 	imx6q-cubox-i.dtb \
+	imx6q-cubox-i-emmc-som-v15.dtb \
+	imx6q-cubox-i-som-v15.dtb \
 	imx6q-dfi-fs700-m60.dtb \
 	imx6q-display5-tianma-tm070-1280x768.dtb \
 	imx6q-dmo-edmqmx6.dtb \
@@ -439,6 +450,11 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6q-gw5904.dtb \
 	imx6q-h100.dtb \
 	imx6q-hummingboard.dtb \
+	imx6q-hummingboard-emmc-som-v15.dtb \
+	imx6q-hummingboard-som-v15.dtb \
+	imx6q-hummingboard2.dtb \
+	imx6q-hummingboard2-emmc-som-v15.dtb \
+	imx6q-hummingboard2-som-v15.dtb \
 	imx6q-icore.dtb \
 	imx6q-icore-ofcap10.dtb \
 	imx6q-icore-ofcap12.dtb \
@@ -459,6 +475,7 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6q-sbc6x.dtb \
 	imx6q-tbs2910.dtb \
 	imx6q-ts4900.dtb \
+	imx6q-ts7970.dtb \
 	imx6q-tx6q-1010.dtb \
 	imx6q-tx6q-1010-comtft.dtb \
 	imx6q-tx6q-1020.dtb \
@@ -470,6 +487,7 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6q-tx6q-11x0-mb7.dtb \
 	imx6q-udoo.dtb \
 	imx6q-utilite-pro.dtb \
+	imx6q-var-dt6customboard.dtb \
 	imx6q-wandboard.dtb \
 	imx6q-wandboard-revb1.dtb \
 	imx6q-wandboard-revd1.dtb \
@@ -511,15 +529,17 @@ dtb-$(CONFIG_SOC_IMX6UL) += \
 	imx6ull-14x14-evk.dtb
 dtb-$(CONFIG_SOC_IMX7D) += \
 	imx7d-cl-som-imx7.dtb \
+	imx7d-colibri-emmc-eval-v3.dtb \
 	imx7d-colibri-eval-v3.dtb \
 	imx7d-nitrogen7.dtb \
-	imx7d-pico.dtb \
+	imx7d-pico-pi.dtb \
 	imx7d-sbc-imx7.dtb \
 	imx7d-sdb.dtb \
 	imx7d-sdb-sht11.dtb \
 	imx7s-colibri-eval-v3.dtb \
 	imx7s-warp.dtb
 dtb-$(CONFIG_SOC_LS1021A) += \
+	ls1021a-moxa-uc-8410a.dtb \
 	ls1021a-qds.dtb \
 	ls1021a-twr.dtb
 dtb-$(CONFIG_SOC_VF610) += \
@@ -558,6 +578,7 @@ dtb-$(CONFIG_ARCH_MXS) += \
 	imx28-m28cu3.dtb \
 	imx28-m28evk.dtb \
 	imx28-sps1.dtb \
+	imx28-ts4600.dtb \
 	imx28-tx28.dtb
 dtb-$(CONFIG_ARCH_NOMADIK) += \
 	ste-nomadik-s8815.dtb \
@@ -689,6 +710,7 @@ dtb-$(CONFIG_SOC_DRA7XX) += \
 	am57xx-sbc-am57x.dtb \
 	am572x-idk.dtb \
 	am571x-idk.dtb \
+	am574x-idk.dtb \
 	dra7-evm.dtb \
 	dra72-evm.dtb \
 	dra72-evm-revc.dtb \
@@ -707,12 +729,13 @@ dtb-$(CONFIG_ARCH_ORION5X) += \
 	orion5x-rd88f5182-nas.dtb
 dtb-$(CONFIG_ARCH_ACTIONS) += \
 	owl-s500-cubieboard6.dtb \
-	owl-s500-guitar-bb-rev-b.dtb
+	owl-s500-guitar-bb-rev-b.dtb \
+	owl-s500-sparky.dtb
 dtb-$(CONFIG_ARCH_PRIMA2) += \
 	prima2-evb.dtb
 dtb-$(CONFIG_ARCH_OXNAS) += \
-	wd-mbwe.dtb \
-	cloudengines-pogoplug-series-3.dtb
+	ox810se-wd-mbwe.dtb \
+	ox820-cloudengines-pogoplug-series-3.dtb
 dtb-$(CONFIG_ARCH_QCOM) += \
 	qcom-apq8060-dragonboard.dtb \
 	qcom-apq8064-arrow-sd-600eval.dtb \
@@ -756,6 +779,7 @@ dtb-$(CONFIG_ARCH_RENESAS) += \
 	r8a7743-iwg20d-q7-dbcm-ca.dtb \
 	r8a7743-sk-rzg1m.dtb \
 	r8a7745-iwg22d-sodimm.dtb \
+	r8a7745-iwg22d-sodimm-dbhd-ca.dtb \
 	r8a7745-sk-rzg1e.dtb \
 	r8a7778-bockw.dtb \
 	r8a7779-marzen.dtb \
@@ -949,9 +973,11 @@ dtb-$(CONFIG_MACH_SUN8I) += \
 	sun8i-a83t-bananapi-m3.dtb \
 	sun8i-a83t-cubietruck-plus.dtb \
 	sun8i-a83t-tbs-a711.dtb \
+	sun8i-h2-plus-orangepi-r1.dtb \
 	sun8i-h2-plus-orangepi-zero.dtb \
 	sun8i-h3-bananapi-m2-plus.dtb \
 	sun8i-h3-beelink-x2.dtb \
+	sun8i-h3-libretech-all-h3-cc.dtb \
 	sun8i-h3-nanopi-m1.dtb	\
 	sun8i-h3-nanopi-m1-plus.dtb \
 	sun8i-h3-nanopi-neo.dtb \
@@ -1101,7 +1127,10 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += \
 	mt8127-moose.dtb \
 	mt8135-evbp1.dtb
 dtb-$(CONFIG_ARCH_ZX) += zx296702-ad1.dtb
-dtb-$(CONFIG_ARCH_ASPEED) += aspeed-bmc-opp-palmetto.dtb \
+dtb-$(CONFIG_ARCH_ASPEED) += \
+	aspeed-ast2500-evb.dtb \
+	aspeed-bmc-opp-palmetto.dtb \
 	aspeed-bmc-opp-romulus.dtb \
-	aspeed-ast2500-evb.dtb
-endif
+	aspeed-bmc-opp-witherspoon.dtb \
+	aspeed-bmc-opp-zaius.dtb \
+	aspeed-bmc-quanta-q71l.dtb
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index 48a15fc641f2..e67b4d65c8d0 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -409,6 +409,6 @@
 };
 
 &rtc {
-	clocks = <&clk_32768_ck>, <&clkdiv32k_ick>;
+	clocks = <&clk_32768_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 	clock-names = "ext-clk", "int-clk";
 };
diff --git a/arch/arm/boot/dts/am335x-boneblue.dts b/arch/arm/boot/dts/am335x-boneblue.dts
index cdc1b2be792f..3f2480d05a3b 100644
--- a/arch/arm/boot/dts/am335x-boneblue.dts
+++ b/arch/arm/boot/dts/am335x-boneblue.dts
@@ -159,6 +159,7 @@
 		>;
 	};
 
+	/* UT0 */
 	uart0_pins: pinmux_uart0_pins {
 		pinctrl-single,pins = <
 			AM33XX_IOPAD(0x970, PIN_INPUT_PULLUP | MUX_MODE0)	/* (E15) uart0_rxd.uart0_rxd */
@@ -166,6 +167,37 @@
 		>;
 	};
 
+	/* UT1 */
+	uart1_pins: pinmux_uart1_pins {
+		pinctrl-single,pins = <
+			AM33XX_IOPAD(0x980, PIN_INPUT_PULLUP | MUX_MODE0)	/* (D16) uart1_rxd.uart1_rxd */
+			AM33XX_IOPAD(0x984, PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* (D15) uart1_txd.uart1_txd */
+		>;
+	};
+
+	/* GPS */
+	uart2_pins: pinmux_uart2_pins {
+		pinctrl-single,pins = <
+			AM33XX_IOPAD(0x950, PIN_INPUT_PULLUP | MUX_MODE1)	/* (A17) spi0_sclk.uart2_rxd */
+			AM33XX_IOPAD(0x954, PIN_OUTPUT_PULLDOWN | MUX_MODE1)	/* (B17) spi0_d0.uart2_txd */
+		>;
+	};
+
+	/* DSM2 */
+	uart4_pins: pinmux_uart4_pins {
+		pinctrl-single,pins = <
+			AM33XX_IOPAD(0x870, PIN_INPUT_PULLUP | MUX_MODE6)	/* (T17) gpmc_wait0.uart4_rxd */
+		>;
+	};
+
+	/* UT5 */
+	uart5_pins: pinmux_uart5_pins {
+		pinctrl-single,pins = <
+			AM33XX_IOPAD(0x8C4, PIN_INPUT_PULLUP | MUX_MODE4)	/* (U2) lcd_data9.uart5_rxd */
+			AM33XX_IOPAD(0x8C0, PIN_OUTPUT_PULLDOWN | MUX_MODE4)	/* (U1) lcd_data8.uart5_txd */
+		>;
+	};
+
 	mmc1_pins: pinmux_mmc1_pins {
 		pinctrl-single,pins = <
 			AM33XX_IOPAD(0x960, PIN_INPUT | MUX_MODE7)		/* (C15) spi0_cs1.gpio0[6] */
@@ -216,10 +248,19 @@
 	wl18xx_pins: pinmux_wl18xx_pins {
 		pinctrl-single,pins = <
 			AM33XX_IOPAD(0x92c, PIN_OUTPUT_PULLDOWN | MUX_MODE7)	/* (K18) gmii1_txclk.gpio3[9] - WL_EN */
-			AM33XX_IOPAD(0x944, PIN_INPUT_PULLDOWN | MUX_MODE7)	/* (H18) rmii1_refclk.gpio0[29] - WL_IRQ */
+			AM33XX_IOPAD(0x924, PIN_INPUT_PULLDOWN | MUX_MODE7)	/* (K16) gmii1_txd1.gpio0[21] - WL_IRQ */
 			AM33XX_IOPAD(0x930, PIN_OUTPUT_PULLUP | MUX_MODE7)	/* (L18) gmii1_rxclk.gpio3[10] - LS_BUF_EN */
 		>;
 	};
+
+	/* DCAN */
+	dcan1_pins: pinmux_dcan1_pins {
+		pinctrl-single,pins = <
+			AM33XX_IOPAD(0x96c, PIN_INPUT | MUX_MODE2)		/* (E17) uart0_rtsn.dcan1_rx */
+			AM33XX_IOPAD(0x968, PIN_OUTPUT | MUX_MODE2)		/* (E18) uart0_ctsn.dcan1_tx */
+			AM33XX_IOPAD(0x940, PIN_OUTPUT | MUX_MODE7)		/* (M16) gmii1_rxd0.gpio2[21] */
+		>;
+	};
 };
 
 &uart0 {
@@ -229,6 +270,34 @@
 	status = "okay";
 };
 
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart1_pins>;
+
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart2_pins>;
+
+	status = "okay";
+};
+
+&uart4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart4_pins>;
+
+	status = "okay";
+};
+
+&uart5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart5_pins>;
+
+	status = "okay";
+};
+
 &usb {
 	status = "okay";
 };
@@ -414,7 +483,7 @@
 		compatible = "ti,wl1835";
 		reg = <2>;
 		interrupt-parent = <&gpio0>;
-		interrupts = <29 IRQ_TYPE_EDGE_RISING>;
+		interrupts = <21 IRQ_TYPE_EDGE_RISING>;
 	};
 };
 
@@ -446,10 +515,16 @@
 
 &rtc {
 	system-power-controller;
-	clocks = <&clk_32768_ck>, <&clkdiv32k_ick>;
+	clocks = <&clk_32768_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 	clock-names = "ext-clk", "int-clk";
 };
 
+&dcan1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&dcan1_pins>;
+	status = "okay";
+};
+
 &gpio3 {
 	ls_buf_en {
 		gpio-hog;
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index ddd897556e03..fee6b3ee1741 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -790,6 +790,6 @@
 };
 
 &rtc {
-	clocks = <&clk_32768_ck>, <&clkdiv32k_ick>;
+	clocks = <&clk_32768_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 	clock-names = "ext-clk", "int-clk";
 };
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 9ba4b18c0cb2..fa608cd5dc14 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -722,6 +722,6 @@
 };
 
 &rtc {
-	clocks = <&clk_32768_ck>, <&clkdiv32k_ick>;
+	clocks = <&clk_32768_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 	clock-names = "ext-clk", "int-clk";
 };
diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts
index 03c7d77023c6..9fb7426070ce 100644
--- a/arch/arm/boot/dts/am335x-pepper.dts
+++ b/arch/arm/boot/dts/am335x-pepper.dts
@@ -139,7 +139,7 @@
 &audio_codec {
 	status = "okay";
 
-	gpio-reset = <&gpio1 16 GPIO_ACTIVE_LOW>;
+	reset-gpios = <&gpio1 16 GPIO_ACTIVE_LOW>;
 	AVDD-supply = <&ldo3_reg>;
 	IOVDD-supply = <&ldo3_reg>;
 	DRVDD-supply = <&ldo3_reg>;
diff --git a/arch/arm/boot/dts/am33xx-clocks.dtsi b/arch/arm/boot/dts/am33xx-clocks.dtsi
index 8d8319590cde..95d5c9d136c5 100644
--- a/arch/arm/boot/dts/am33xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am33xx-clocks.dtsi
@@ -292,14 +292,6 @@
 		clock-div = <4>;
 	};
 
-	cefuse_fck: cefuse_fck@a20 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_clkin_ck>;
-		ti,bit-shift = <1>;
-		reg = <0x0a20>;
-	};
-
 	clk_24mhz: clk_24mhz {
 		#clock-cells = <0>;
 		compatible = "fixed-factor-clock";
@@ -316,14 +308,6 @@
 		clock-div = <732>;
 	};
 
-	clkdiv32k_ick: clkdiv32k_ick@14c {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&clkdiv32k_ck>;
-		ti,bit-shift = <1>;
-		reg = <0x014c>;
-	};
-
 	l3_gclk: l3_gclk {
 		#clock-cells = <0>;
 		compatible = "fixed-factor-clock";
@@ -350,49 +334,49 @@
 	timer1_fck: timer1_fck@528 {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin_ck>, <&clkdiv32k_ick>, <&tclkin_ck>, <&clk_rc32k_ck>, <&clk_32768_ck>;
+		clocks = <&sys_clkin_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>, <&tclkin_ck>, <&clk_rc32k_ck>, <&clk_32768_ck>;
 		reg = <0x0528>;
 	};
 
 	timer2_fck: timer2_fck@508 {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&clkdiv32k_ick>;
+		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 		reg = <0x0508>;
 	};
 
 	timer3_fck: timer3_fck@50c {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&clkdiv32k_ick>;
+		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 		reg = <0x050c>;
 	};
 
 	timer4_fck: timer4_fck@510 {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&clkdiv32k_ick>;
+		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 		reg = <0x0510>;
 	};
 
 	timer5_fck: timer5_fck@518 {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&clkdiv32k_ick>;
+		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 		reg = <0x0518>;
 	};
 
 	timer6_fck: timer6_fck@51c {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&clkdiv32k_ick>;
+		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 		reg = <0x051c>;
 	};
 
 	timer7_fck: timer7_fck@504 {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&clkdiv32k_ick>;
+		clocks = <&tclkin_ck>, <&sys_clkin_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 		reg = <0x0504>;
 	};
 
@@ -423,7 +407,7 @@
 	wdt1_fck: wdt1_fck@538 {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&clk_rc32k_ck>, <&clkdiv32k_ick>;
+		clocks = <&clk_rc32k_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 		reg = <0x0538>;
 	};
 
@@ -493,42 +477,10 @@
 	gpio0_dbclk_mux_ck: gpio0_dbclk_mux_ck@53c {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&clk_rc32k_ck>, <&clk_32768_ck>, <&clkdiv32k_ick>;
+		clocks = <&clk_rc32k_ck>, <&clk_32768_ck>, <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 		reg = <0x053c>;
 	};
 
-	gpio0_dbclk: gpio0_dbclk@408 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&gpio0_dbclk_mux_ck>;
-		ti,bit-shift = <18>;
-		reg = <0x0408>;
-	};
-
-	gpio1_dbclk: gpio1_dbclk@ac {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&clkdiv32k_ick>;
-		ti,bit-shift = <18>;
-		reg = <0x00ac>;
-	};
-
-	gpio2_dbclk: gpio2_dbclk@b0 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&clkdiv32k_ick>;
-		ti,bit-shift = <18>;
-		reg = <0x00b0>;
-	};
-
-	gpio3_dbclk: gpio3_dbclk@b4 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&clkdiv32k_ick>;
-		ti,bit-shift = <18>;
-		reg = <0x00b4>;
-	};
-
 	lcd_gclk: lcd_gclk@534 {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
@@ -577,58 +529,6 @@
 		reg = <0x0700>;
 	};
 
-	dbg_sysclk_ck: dbg_sysclk_ck@414 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_clkin_ck>;
-		ti,bit-shift = <19>;
-		reg = <0x0414>;
-	};
-
-	dbg_clka_ck: dbg_clka_ck@414 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_core_m4_ck>;
-		ti,bit-shift = <30>;
-		reg = <0x0414>;
-	};
-
-	stm_pmd_clock_mux_ck: stm_pmd_clock_mux_ck@414 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&dbg_sysclk_ck>, <&dbg_clka_ck>;
-		ti,bit-shift = <22>;
-		reg = <0x0414>;
-	};
-
-	trace_pmd_clk_mux_ck: trace_pmd_clk_mux_ck@414 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&dbg_sysclk_ck>, <&dbg_clka_ck>;
-		ti,bit-shift = <20>;
-		reg = <0x0414>;
-	};
-
-	stm_clk_div_ck: stm_clk_div_ck@414 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&stm_pmd_clock_mux_ck>;
-		ti,bit-shift = <27>;
-		ti,max-div = <64>;
-		reg = <0x0414>;
-		ti,index-power-of-two;
-	};
-
-	trace_clk_div_ck: trace_clk_div_ck@414 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&trace_pmd_clk_mux_ck>;
-		ti,bit-shift = <24>;
-		ti,max-div = <64>;
-		reg = <0x0414>;
-		ti,index-power-of-two;
-	};
-
 	clkout2_ck: clkout2_ck@700 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
@@ -638,9 +538,88 @@
 	};
 };
 
-&prcm_clockdomains {
-	clk_24mhz_clkdm: clk_24mhz_clkdm {
-		compatible = "ti,clockdomain";
-		clocks = <&clkdiv32k_ick>;
+&prcm {
+	l4_per_cm: l4_per_cm@0 {
+		compatible = "ti,omap4-cm";
+		reg = <0x0 0x200>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x0 0x200>;
+
+		l4_per_clkctrl: clk@14 {
+			compatible = "ti,clkctrl";
+			reg = <0x14 0x13c>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l4_wkup_cm: l4_wkup_cm@400 {
+		compatible = "ti,omap4-cm";
+		reg = <0x400 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x400 0x100>;
+
+		l4_wkup_clkctrl: clk@4 {
+			compatible = "ti,clkctrl";
+			reg = <0x4 0xd4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	mpu_cm: mpu_cm@600 {
+		compatible = "ti,omap4-cm";
+		reg = <0x600 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x600 0x100>;
+
+		mpu_clkctrl: clk@4 {
+			compatible = "ti,clkctrl";
+			reg = <0x4 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l4_rtc_cm: l4_rtc_cm@800 {
+		compatible = "ti,omap4-cm";
+		reg = <0x800 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x800 0x100>;
+
+		l4_rtc_clkctrl: clk@0 {
+			compatible = "ti,clkctrl";
+			reg = <0x0 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	gfx_l3_cm: gfx_l3_cm@900 {
+		compatible = "ti,omap4-cm";
+		reg = <0x900 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x900 0x100>;
+
+		gfx_l3_clkctrl: clk@4 {
+			compatible = "ti,clkctrl";
+			reg = <0x4 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l4_cefuse_cm: l4_cefuse_cm@a00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xa00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xa00 0x100>;
+
+		l4_cefuse_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 1b81c4e75772..628c77b0b386 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -10,6 +10,7 @@
 
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/pinctrl/am33xx.h>
+#include <dt-bindings/clock/am3.h>
 
 / {
 	compatible = "ti,am33xx";
@@ -179,8 +180,11 @@
 			};
 
 			prcm: prcm@200000 {
-				compatible = "ti,am3-prcm";
+				compatible = "ti,am3-prcm", "simple-bus";
 				reg = <0x200000 0x4000>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 0x200000 0x4000>;
 
 				prcm_clocks: clocks {
 					#address-cells = <1>;
@@ -496,7 +500,7 @@
 			status = "disabled";
 		};
 
-		mailbox: mailbox@480C8000 {
+		mailbox: mailbox@480c8000 {
 			compatible = "ti,omap4-mailbox";
 			reg = <0x480C8000 0x200>;
 			interrupts = <77>;
@@ -517,6 +521,8 @@
 			interrupts = <67>;
 			ti,hwmods = "timer1";
 			ti,timer-alwon;
+			clocks = <&timer1_fck>;
+			clock-names = "fck";
 		};
 
 		timer2: timer@48040000 {
@@ -524,6 +530,8 @@
 			reg = <0x48040000 0x400>;
 			interrupts = <68>;
 			ti,hwmods = "timer2";
+			clocks = <&timer2_fck>;
+			clock-names = "fck";
 		};
 
 		timer3: timer@48042000 {
@@ -571,7 +579,7 @@
 			interrupts = <75
 				      76>;
 			ti,hwmods = "rtc";
-			clocks = <&clkdiv32k_ick>;
+			clocks = <&l4_per_clkctrl AM3_CLKDIV32K_CLKCTRL 0>;
 			clock-names = "int-clk";
 		};
 
@@ -630,6 +638,7 @@
 				reg-names = "phy";
 				status = "disabled";
 				ti,ctrl_mod = <&usb_ctrl_mod>;
+				#phy-cells = <0>;
 			};
 
 			usb0: usb@47401000 {
@@ -678,6 +687,7 @@
 				reg-names = "phy";
 				status = "disabled";
 				ti,ctrl_mod = <&usb_ctrl_mod>;
+				#phy-cells = <0>;
 			};
 
 			usb1: usb@47401800 {
@@ -989,7 +999,7 @@
 			dma-names = "tx", "rx";
 		};
 
-		mcasp1: mcasp@4803C000 {
+		mcasp1: mcasp@4803c000 {
 			compatible = "ti,am33xx-mcasp-audio";
 			ti,hwmods = "mcasp1";
 			reg = <0x4803C000 0x2000>,
@@ -1012,4 +1022,4 @@
 	};
 };
 
-/include/ "am33xx-clocks.dtsi"
+#include "am33xx-clocks.dtsi"
diff --git a/arch/arm/boot/dts/am3517.dtsi b/arch/arm/boot/dts/am3517.dtsi
index 00da3f2c4072..ca294914bbb1 100644
--- a/arch/arm/boot/dts/am3517.dtsi
+++ b/arch/arm/boot/dts/am3517.dtsi
@@ -26,7 +26,7 @@
 			interrupt-names = "mc";
 		};
 
-		davinci_emac: ethernet@0x5c000000 {
+		davinci_emac: ethernet@5c000000 {
 			compatible = "ti,am3517-emac";
 			ti,hwmods = "davinci_emac";
 			status = "disabled";
@@ -41,7 +41,7 @@
 			local-mac-address = [ 00 00 00 00 00 00 ];
 		};
 
-		davinci_mdio: ethernet@0x5c030000 {
+		davinci_mdio: ethernet@5c030000 {
 			compatible = "ti,davinci_mdio";
 			ti,hwmods = "davinci_mdio";
 			status = "disabled";
@@ -99,9 +99,5 @@
 	status = "disabled";
 };
 
-&smartreflex_mpu_iva {
-	status = "disabled";
-};
-
 /include/ "am35xx-clocks.dtsi"
 /include/ "omap36xx-am35xx-omap3430es2plus-clocks.dtsi"
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index e5b061469bf8..964f3ef79728 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -10,6 +10,7 @@
 
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/clock/am4.h>
 
 / {
 	compatible = "ti,am4372", "ti,am43";
@@ -163,9 +164,12 @@
 			};
 
 			prcm: prcm@1f0000 {
-				compatible = "ti,am4-prcm";
+				compatible = "ti,am4-prcm", "simple-bus";
 				reg = <0x1f0000 0x11000>;
 				interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 0x1f0000 0x11000>;
 
 				prcm_clocks: clocks {
 					#address-cells = <1>;
@@ -325,7 +329,7 @@
 			status = "disabled";
 		};
 
-		mailbox: mailbox@480C8000 {
+		mailbox: mailbox@480c8000 {
 			compatible = "ti,omap4-mailbox";
 			reg = <0x480C8000 0x200>;
 			interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
@@ -346,6 +350,8 @@
 			interrupts = <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>;
 			ti,timer-alwon;
 			ti,hwmods = "timer1";
+			clocks = <&timer1_fck>;
+			clock-names = "fck";
 		};
 
 		timer2: timer@48040000  {
@@ -353,6 +359,8 @@
 			reg = <0x48040000  0x400>;
 			interrupts = <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "timer2";
+			clocks = <&timer2_fck>;
+			clock-names = "fck";
 		};
 
 		timer3: timer@48042000 {
@@ -927,7 +935,8 @@
 			reg = <0x48038000 0x2000>,
 			      <0x46000000 0x400000>;
 			reg-names = "mpu", "dat";
-			interrupts = <80>, <81>;
+			interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "tx", "rx";
 			status = "disabled";
 			dmas = <&edma 8 2>,
@@ -935,13 +944,14 @@
 			dma-names = "tx", "rx";
 		};
 
-		mcasp1: mcasp@4803C000 {
+		mcasp1: mcasp@4803c000 {
 			compatible = "ti,am33xx-mcasp-audio";
 			ti,hwmods = "mcasp1";
 			reg = <0x4803C000 0x2000>,
 			      <0x46400000 0x400000>;
 			reg-names = "mpu", "dat";
-			interrupts = <82>, <83>;
+			interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "tx", "rx";
 			status = "disabled";
 			dmas = <&edma 10 2>,
@@ -991,7 +1001,7 @@
 				reg = <0x483a8000 0x8000>;
 				syscon-phy-power = <&scm_conf 0x620>;
 				clocks = <&usb_phy0_always_on_clk32k>,
-					 <&usb_otg_ss0_refclk960m>;
+					 <&l4_per_clkctrl AM4_USB_OTG_SS0_CLKCTRL 8>;
 				clock-names = "wkupclk", "refclk";
 				#phy-cells = <0>;
 				status = "disabled";
@@ -1010,7 +1020,7 @@
 				reg = <0x483e8000 0x8000>;
 				syscon-phy-power = <&scm_conf 0x628>;
 				clocks = <&usb_phy1_always_on_clk32k>,
-					 <&usb_otg_ss1_refclk960m>;
+					 <&l4_per_clkctrl AM4_USB_OTG_SS1_CLKCTRL 8>;
 				clock-names = "wkupclk", "refclk";
 				#phy-cells = <0>;
 				status = "disabled";
@@ -1173,4 +1183,4 @@
 	};
 };
 
-/include/ "am43xx-clocks.dtsi"
+#include "am43xx-clocks.dtsi"
diff --git a/arch/arm/boot/dts/am437x-cm-t43.dts b/arch/arm/boot/dts/am437x-cm-t43.dts
index 9e92d480576b..3b9a94c274a7 100644
--- a/arch/arm/boot/dts/am437x-cm-t43.dts
+++ b/arch/arm/boot/dts/am437x-cm-t43.dts
@@ -301,8 +301,8 @@
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&spi0_pins>;
-	dmas = <&edma 16
-		&edma 17>;
+	dmas = <&edma 16 0
+		&edma 17 0>;
 	dma-names = "tx0", "rx0";
 
 	flash: w25q64cvzpig@0 {
diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts
index afb8eb0a0a16..c3b1a3fb5a2e 100644
--- a/arch/arm/boot/dts/am437x-gp-evm.dts
+++ b/arch/arm/boot/dts/am437x-gp-evm.dts
@@ -55,7 +55,7 @@
 		enable-active-high;
 	};
 
-	backlight {
+	lcd_bl: backlight {
 		compatible = "pwm-backlight";
 		pwms = <&ecap0 0 50000 PWM_POLARITY_INVERTED>;
 		brightness-levels = <0 51 53 56 62 75 101 152 255>;
@@ -86,6 +86,8 @@
 		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
 		label = "lcd";
 
+		backlight = <&lcd_bl>;
+
 		panel-timing {
 			clock-frequency = <33000000>;
 			hactive = <800>;
diff --git a/arch/arm/boot/dts/am437x-idk-evm.dts b/arch/arm/boot/dts/am437x-idk-evm.dts
index 5e364473067f..20132477a871 100644
--- a/arch/arm/boot/dts/am437x-idk-evm.dts
+++ b/arch/arm/boot/dts/am437x-idk-evm.dts
@@ -519,3 +519,17 @@
 &cpu {
 	cpu0-supply = <&tps>;
 };
+
+&cpu0_opp_table {
+	/*
+	 * Supply voltage supervisor on board will not allow opp50 so
+	 * disable it and set opp100 as suspend OPP.
+	 */
+	opp50@300000000 {
+		status = "disabled";
+	};
+
+	opp100@600000000 {
+		opp-suspend;
+	};
+};
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index 2c6bf0684f50..3fa3b226995d 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -35,7 +35,7 @@
 		clock-frequency = <32768>;
 	};
 
-	backlight {
+	lcd_bl: backlight {
 		compatible = "pwm-backlight";
 		pwms = <&ecap0 0 50000 PWM_POLARITY_INVERTED>;
 		brightness-levels = <0 51 53 56 62 75 101 152 255>;
@@ -132,6 +132,8 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&lcd_pins>;
 
+		backlight = <&lcd_bl>;
+
 		enable-gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
 
 		panel-timing {
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index a04d79ec212a..00c3d1de384f 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -48,6 +48,8 @@
 		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
 		label = "lcd";
 
+		backlight = <&lcd_bl>;
+
 		panel-timing {
 			clock-frequency = <33000000>;
 			hactive = <800>;
@@ -107,7 +109,7 @@
 			0x03030069>;	/* LEFT */
 	};
 
-	backlight {
+	lcd_bl: backlight {
 		compatible = "pwm-backlight";
 		pwms = <&ecap0 0 50000 PWM_POLARITY_INVERTED>;
 		brightness-levels = <0 51 53 56 62 75 101 152 255>;
@@ -985,7 +987,11 @@
 	rx-num-evt = <32>;
 };
 
-&synctimer_32kclk {
+&mux_synctimer32k_ck {
 	assigned-clocks = <&mux_synctimer32k_ck>;
 	assigned-clock-parents = <&clkdiv32k_ick>;
 };
+
+&cpu {
+	cpu0-supply = <&dcdc2>;
+};
diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi
index 430be5829f8f..a7037a4b4fd4 100644
--- a/arch/arm/boot/dts/am43xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am43xx-clocks.dtsi
@@ -524,54 +524,6 @@
 		reg = <0x4240>;
 	};
 
-	gpio0_dbclk: gpio0_dbclk@2b68 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&gpio0_dbclk_mux_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x2b68>;
-	};
-
-	gpio1_dbclk: gpio1_dbclk@8c78 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&clkdiv32k_ick>;
-		ti,bit-shift = <8>;
-		reg = <0x8c78>;
-	};
-
-	gpio2_dbclk: gpio2_dbclk@8c80 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&clkdiv32k_ick>;
-		ti,bit-shift = <8>;
-		reg = <0x8c80>;
-	};
-
-	gpio3_dbclk: gpio3_dbclk@8c88 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&clkdiv32k_ick>;
-		ti,bit-shift = <8>;
-		reg = <0x8c88>;
-	};
-
-	gpio4_dbclk: gpio4_dbclk@8c90 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&clkdiv32k_ick>;
-		ti,bit-shift = <8>;
-		reg = <0x8c90>;
-	};
-
-	gpio5_dbclk: gpio5_dbclk@8c98 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&clkdiv32k_ick>;
-		ti,bit-shift = <8>;
-		reg = <0x8c98>;
-	};
-
 	mmc_clk: mmc_clk {
 		#clock-cells = <0>;
 		compatible = "fixed-factor-clock";
@@ -629,14 +581,6 @@
 		reg = <0x4230>;
 	};
 
-	synctimer_32kclk: synctimer_32kclk@2a30 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&mux_synctimer32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x2a30>;
-	};
-
 	timer8_fck: timer8_fck@421c {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
@@ -763,110 +707,76 @@
 		ti,bit-shift = <8>;
 		reg = <0x2a48>;
 	};
+};
 
-	usb_otg_ss0_refclk960m: usb_otg_ss0_refclk960m@8a60 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_clkdcoldo>;
-		ti,bit-shift = <8>;
-		reg = <0x8a60>;
-	};
-
-	usb_otg_ss1_refclk960m: usb_otg_ss1_refclk960m@8a68 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_clkdcoldo>;
-		ti,bit-shift = <8>;
-		reg = <0x8a68>;
-	};
-
-	clkout1_osc_div_ck: clkout1_osc_div_ck {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&sys_clkin_ck>;
-		ti,bit-shift = <20>;
-		ti,max-div = <4>;
-		reg = <0x4100>;
-	};
-
-	clkout1_src2_mux_ck: clkout1_src2_mux_ck {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&clk_rc32k_ck>, <&sysclk_div>, <&dpll_ddr_m2_ck>,
-			 <&dpll_per_m2_ck>, <&dpll_disp_m2_ck>,
-			 <&dpll_mpu_m2_ck>;
-		reg = <0x4100>;
-	};
-
-	clkout1_src2_pre_div_ck: clkout1_src2_pre_div_ck {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&clkout1_src2_mux_ck>;
-		ti,bit-shift = <4>;
-		ti,max-div = <8>;
-		reg = <0x4100>;
-	};
-
-	clkout1_src2_post_div_ck: clkout1_src2_post_div_ck {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&clkout1_src2_pre_div_ck>;
-		ti,bit-shift = <8>;
-		ti,max-div = <32>;
-		ti,index-power-of-two;
-		reg = <0x4100>;
-	};
-
-	clkout1_mux_ck: clkout1_mux_ck {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&clkout1_osc_div_ck>, <&clk_rc32k_ck>,
-			 <&clkout1_src2_post_div_ck>, <&dpll_extdev_m2_ck>;
-		ti,bit-shift = <16>;
-		reg = <0x4100>;
-	};
-
-	clkout1_ck: clkout1_ck {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&clkout1_mux_ck>;
-		ti,bit-shift = <23>;
-		reg = <0x4100>;
-	};
-
-	clkout2_src_mux_ck: clkout2_src_mux_ck {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&clk_rc32k_ck>, <&sysclk_div>, <&dpll_ddr_m2_ck>,
-			 <&dpll_per_m2_ck>, <&dpll_disp_m2_ck>,
-			 <&dpll_mpu_m2_ck>, <&dpll_extdev_ck>;
-		reg = <0x4108>;
-	};
-
-	clkout2_pre_div_ck: clkout2_pre_div_ck {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&clkout2_src_mux_ck>;
-		ti,bit-shift = <4>;
-		ti,max-div = <8>;
-		reg = <0x4108>;
-	};
-
-	clkout2_post_div_ck: clkout2_post_div_ck {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&clkout2_pre_div_ck>;
-		ti,bit-shift = <8>;
-		ti,max-div = <32>;
-		ti,index-power-of-two;
-		reg = <0x4108>;
-	};
-
-	clkout2_ck: clkout2_ck {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&clkout2_post_div_ck>;
-		ti,bit-shift = <16>;
-		reg = <0x4108>;
+&prcm {
+	l4_wkup_cm: l4_wkup_cm@2800 {
+		compatible = "ti,omap4-cm";
+		reg = <0x2800 0x400>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x2800 0x400>;
+
+		l4_wkup_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x34c>;
+			#clock-cells = <2>;
+		};
+	};
+
+	mpu_cm: mpu_cm@8300 {
+		compatible = "ti,omap4-cm";
+		reg = <0x8300 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x8300 0x100>;
+
+		mpu_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	gfx_l3_cm: gfx_l3_cm@8400 {
+		compatible = "ti,omap4-cm";
+		reg = <0x8400 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x8400 0x100>;
+
+		gfx_l3_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l4_rtc_cm: l4_rtc_cm@8500 {
+		compatible = "ti,omap4-cm";
+		reg = <0x8500 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x8500 0x100>;
+
+		l4_rtc_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l4_per_cm: l4_per_cm@8800 {
+		compatible = "ti,omap4-cm";
+		reg = <0x8800 0xc00>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x8800 0xc00>;
+
+		l4_per_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0xb04>;
+			#clock-cells = <2>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/am571x-idk.dts b/arch/arm/boot/dts/am571x-idk.dts
index debf9464403e..6d3c83743156 100644
--- a/arch/arm/boot/dts/am571x-idk.dts
+++ b/arch/arm/boot/dts/am571x-idk.dts
@@ -117,3 +117,7 @@
 	pinctrl-1 = <&mmc2_pins_hs>;
 	pinctrl-2 = <&mmc2_pins_ddr_rev20 &mmc2_iodelay_ddr_conf>;
 };
+
+&cpu0 {
+	vdd-supply = <&smps12_reg>;
+};
diff --git a/arch/arm/boot/dts/am572x-idk-common.dtsi b/arch/arm/boot/dts/am572x-idk-common.dtsi
new file mode 100644
index 000000000000..c6d858b31011
--- /dev/null
+++ b/arch/arm/boot/dts/am572x-idk-common.dtsi
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include "am57xx-idk-common.dtsi"
+
+/ {
+	memory@0 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x0 0x80000000>;
+	};
+
+	status-leds {
+		compatible = "gpio-leds";
+		cpu0-led {
+			label = "status0:red:cpu0";
+			gpios = <&gpio4 0 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+			linux,default-trigger = "cpu0";
+		};
+
+		usr0-led {
+			label = "status0:green:usr";
+			gpios = <&gpio3 11 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		heartbeat-led {
+			label = "status0:blue:heartbeat";
+			gpios = <&gpio3 12 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+			linux,default-trigger = "heartbeat";
+		};
+
+		cpu1-led {
+			label = "status1:red:cpu1";
+			gpios = <&gpio3 10 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+			linux,default-trigger = "cpu1";
+		};
+
+		usr1-led {
+			label = "status1:green:usr";
+			gpios = <&gpio7 23 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		mmc0-led {
+			label = "status1:blue:mmc0";
+			gpios = <&gpio7 22 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+			linux,default-trigger = "mmc0";
+		};
+	};
+};
+
+&omap_dwc3_2 {
+	extcon = <&extcon_usb2>;
+};
+
+&extcon_usb2 {
+	id-gpio = <&gpio3 16 GPIO_ACTIVE_HIGH>;
+	vbus-gpio = <&gpio3 26 GPIO_ACTIVE_HIGH>;
+};
+
+&sn65hvs882 {
+	load-gpios = <&gpio3 19 GPIO_ACTIVE_LOW>;
+};
+
+&pcie1_rc {
+	status = "okay";
+	gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
+};
+
+&pcie1_ep {
+	gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
+};
+
+&mailbox5 {
+	status = "okay";
+	mbox_ipu1_ipc3x: mbox_ipu1_ipc3x {
+		status = "okay";
+	};
+	mbox_dsp1_ipc3x: mbox_dsp1_ipc3x {
+		status = "okay";
+	};
+};
+
+&mailbox6 {
+	status = "okay";
+	mbox_ipu2_ipc3x: mbox_ipu2_ipc3x {
+		status = "okay";
+	};
+	mbox_dsp2_ipc3x: mbox_dsp2_ipc3x {
+		status = "okay";
+	};
+};
diff --git a/arch/arm/boot/dts/am572x-idk.dts b/arch/arm/boot/dts/am572x-idk.dts
index a578fe97ba3b..9ab0af5017df 100644
--- a/arch/arm/boot/dts/am572x-idk.dts
+++ b/arch/arm/boot/dts/am572x-idk.dts
@@ -9,8 +9,7 @@
 /dts-v1/;
 
 #include "dra74x.dtsi"
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/interrupt-controller/irq.h>
+#include "am572x-idk-common.dtsi"
 #include "am57xx-idk-common.dtsi"
 #include "dra74x-mmc-iodelay.dtsi"
 
@@ -18,54 +17,6 @@
 	model = "TI AM5728 IDK";
 	compatible = "ti,am5728-idk", "ti,am5728", "ti,dra742", "ti,dra74",
 		     "ti,dra7";
-
-	memory@0 {
-		device_type = "memory";
-		reg = <0x0 0x80000000 0x0 0x80000000>;
-	};
-
-	status-leds {
-		compatible = "gpio-leds";
-		cpu0-led {
-			label = "status0:red:cpu0";
-			gpios = <&gpio4 0 GPIO_ACTIVE_HIGH>;
-			default-state = "off";
-			linux,default-trigger = "cpu0";
-		};
-
-		usr0-led {
-			label = "status0:green:usr";
-			gpios = <&gpio3 11 GPIO_ACTIVE_HIGH>;
-			default-state = "off";
-		};
-
-		heartbeat-led {
-			label = "status0:blue:heartbeat";
-			gpios = <&gpio3 12 GPIO_ACTIVE_HIGH>;
-			default-state = "off";
-			linux,default-trigger = "heartbeat";
-		};
-
-		cpu1-led {
-			label = "status1:red:cpu1";
-			gpios = <&gpio3 10 GPIO_ACTIVE_HIGH>;
-			default-state = "off";
-			linux,default-trigger = "cpu1";
-		};
-
-		usr1-led {
-			label = "status1:green:usr";
-			gpios = <&gpio7 23 GPIO_ACTIVE_HIGH>;
-			default-state = "off";
-		};
-
-		mmc0-led {
-			label = "status1:blue:mmc0";
-			gpios = <&gpio7 22 GPIO_ACTIVE_HIGH>;
-			default-state = "off";
-			linux,default-trigger = "mmc0";
-		};
-	};
 };
 
 &mmc1 {
@@ -86,44 +37,6 @@
 	pinctrl-2 = <&mmc2_pins_ddr_rev20>;
 };
 
-&omap_dwc3_2 {
-	extcon = <&extcon_usb2>;
-};
-
-&extcon_usb2 {
-	id-gpio = <&gpio3 16 GPIO_ACTIVE_HIGH>;
-	vbus-gpio = <&gpio3 26 GPIO_ACTIVE_HIGH>;
-};
-
-&sn65hvs882 {
-	load-gpios = <&gpio3 19 GPIO_ACTIVE_LOW>;
-};
-
-&pcie1_rc {
-	status = "okay";
-	gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
-};
-
-&pcie1_ep {
-	gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
-};
-
-&mailbox5 {
-	status = "okay";
-	mbox_ipu1_ipc3x: mbox_ipu1_ipc3x {
-		status = "okay";
-	};
-	mbox_dsp1_ipc3x: mbox_dsp1_ipc3x {
-		status = "okay";
-	};
-};
-
-&mailbox6 {
-	status = "okay";
-	mbox_ipu2_ipc3x: mbox_ipu2_ipc3x {
-		status = "okay";
-	};
-	mbox_dsp2_ipc3x: mbox_dsp2_ipc3x {
-		status = "okay";
-	};
+&cpu0 {
+	vdd-supply = <&smps12_reg>;
 };
diff --git a/arch/arm/boot/dts/am574x-idk.dts b/arch/arm/boot/dts/am574x-idk.dts
new file mode 100644
index 000000000000..41e12a382d2f
--- /dev/null
+++ b/arch/arm/boot/dts/am574x-idk.dts
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/
+ */
+
+
+/dts-v1/;
+
+#include "dra76x.dtsi"
+#include "am572x-idk-common.dtsi"
+
+/ {
+	model = "TI AM5748 IDK";
+	compatible = "ti,am5728-idk", "ti,dra762", "ti,dra7";
+};
+
+&qspi {
+	spi-max-frequency = <96000000>;
+	m25p80@0 {
+		spi-max-frequency = <96000000>;
+	};
+};
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
index 49aeecd312b4..ab60035bc50c 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
@@ -388,7 +388,7 @@
 };
 
 &cpu0 {
-	cpu0-supply = <&smps12_reg>;
+	vdd-supply = <&smps12_reg>;
 	voltage-tolerance = <1>;
 };
 
@@ -554,7 +554,7 @@
 
 &mcasp3 {
 	#sound-dai-cells = <0>;
-	assigned-clocks = <&mcasp3_ahclkx_mux>;
+	assigned-clocks = <&l4per_clkctrl DRA7_MCASP3_CLKCTRL 24>;
 	assigned-clock-parents = <&sys_clkin2>;
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/animeo_ip.dts b/arch/arm/boot/dts/animeo_ip.dts
index 26ade8c0a960..b67a75179784 100644
--- a/arch/arm/boot/dts/animeo_ip.dts
+++ b/arch/arm/boot/dts/animeo_ip.dts
@@ -43,6 +43,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			usart0: serial@fffb0000 {
 				pinctrl-0 = <&pinctrl_usart0 &pinctrl_usart0_rts>;
 				linux,rs485-enabled-at-boot-time;
diff --git a/arch/arm/boot/dts/arm-realview-eb-mp.dtsi b/arch/arm/boot/dts/arm-realview-eb-mp.dtsi
index 7b8d90b7aeea..29b636fce23f 100644
--- a/arch/arm/boot/dts/arm-realview-eb-mp.dtsi
+++ b/arch/arm/boot/dts/arm-realview-eb-mp.dtsi
@@ -150,11 +150,6 @@
 	interrupts = <0 8 IRQ_TYPE_LEVEL_HIGH>;
 };
 
-&charlcd {
-	interrupt-parent = <&intc>;
-	interrupts = <0  IRQ_TYPE_LEVEL_HIGH>;
-};
-
 &serial0 {
 	interrupt-parent = <&intc>;
 	interrupts = <0 4 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/armada-385-db-ap.dts b/arch/arm/boot/dts/armada-385-db-ap.dts
index 25d2d720dc0e..678aa023335d 100644
--- a/arch/arm/boot/dts/armada-385-db-ap.dts
+++ b/arch/arm/boot/dts/armada-385-db-ap.dts
@@ -236,6 +236,7 @@
 	usb3_phy: usb3_phy {
 		compatible = "usb-nop-xceiv";
 		vcc-supply = <&reg_xhci0_vbus>;
+		#phy-cells = <0>;
 	};
 
 	reg_xhci0_vbus: xhci0-vbus {
diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi
index e1f355ffc8f7..434dc9aaa5e4 100644
--- a/arch/arm/boot/dts/armada-385-linksys.dtsi
+++ b/arch/arm/boot/dts/armada-385-linksys.dtsi
@@ -66,6 +66,7 @@
 	usb3_1_phy: usb3_1-phy {
 		compatible = "usb-nop-xceiv";
 		vcc-supply = <&usb3_1_vbus>;
+		#phy-cells = <0>;
 	};
 
 	usb3_1_vbus: usb3_1-vbus {
diff --git a/arch/arm/boot/dts/armada-385-synology-ds116.dts b/arch/arm/boot/dts/armada-385-synology-ds116.dts
index 36ad571e76f3..0a3552ebda3b 100644
--- a/arch/arm/boot/dts/armada-385-synology-ds116.dts
+++ b/arch/arm/boot/dts/armada-385-synology-ds116.dts
@@ -191,11 +191,13 @@
 	usb3_0_phy: usb3_0_phy {
 		compatible = "usb-nop-xceiv";
 		vcc-supply = <&reg_usb3_0_vbus>;
+		#phy-cells = <0>;
 	};
 
 	usb3_1_phy: usb3_1_phy {
 		compatible = "usb-nop-xceiv";
 		vcc-supply = <&reg_usb3_1_vbus>;
+		#phy-cells = <0>;
 	};
 
 	reg_usb3_0_vbus: usb3-vbus0 {
diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts
index f503955dbd3b..51b4ee6df130 100644
--- a/arch/arm/boot/dts/armada-388-gp.dts
+++ b/arch/arm/boot/dts/armada-388-gp.dts
@@ -276,11 +276,13 @@
 	usb2_1_phy: usb2_1_phy {
 		compatible = "usb-nop-xceiv";
 		vcc-supply = <&reg_usb2_1_vbus>;
+		#phy-cells = <0>;
 	};
 
 	usb3_phy: usb3_phy {
 		compatible = "usb-nop-xceiv";
 		vcc-supply = <&reg_usb3_vbus>;
+		#phy-cells = <0>;
 	};
 
 	reg_usb3_vbus: usb3-vbus {
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 00ff549d4e39..a6cc568f74f7 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -279,6 +279,11 @@
 					marvell,function = "dev";
 				};
 
+				nand_rb: nand-rb {
+					marvell,pins = "mpp41";
+					marvell,function = "nand";
+				};
+
 				uart0_pins: uart-pins-0 {
 					marvell,pins = "mpp0", "mpp1";
 					marvell,function = "ua0";
diff --git a/arch/arm/boot/dts/aspeed-ast2500-evb.dts b/arch/arm/boot/dts/aspeed-ast2500-evb.dts
index 602bc10fdaf4..91a36c1f029b 100644
--- a/arch/arm/boot/dts/aspeed-ast2500-evb.dts
+++ b/arch/arm/boot/dts/aspeed-ast2500-evb.dts
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0+
 /dts-v1/;
 
 #include "aspeed-g5.dtsi"
@@ -16,7 +16,7 @@
 		bootargs = "console=ttyS4,115200 earlyprintk";
 	};
 
-	memory {
+	memory@80000000 {
 		reg = <0x80000000 0x20000000>;
 	};
 };
diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-palmetto.dts b/arch/arm/boot/dts/aspeed-bmc-opp-palmetto.dts
index c786bc2f2919..4379d09a261f 100644
--- a/arch/arm/boot/dts/aspeed-bmc-opp-palmetto.dts
+++ b/arch/arm/boot/dts/aspeed-bmc-opp-palmetto.dts
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0+
 /dts-v1/;
 
 #include "aspeed-g4.dtsi"
@@ -12,7 +12,7 @@
 		bootargs = "console=ttyS4,115200 earlyprintk";
 	};
 
-	memory {
+	memory@40000000 {
 		reg = <0x40000000 0x20000000>;
 	};
 
@@ -34,6 +34,7 @@
 		status = "okay";
 		m25p,fast-read;
 		label = "bmc";
+#include "openbmc-flash-layout.dtsi"
 	};
 };
 
diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-romulus.dts b/arch/arm/boot/dts/aspeed-bmc-opp-romulus.dts
index 8067793129ea..623b6ab42021 100644
--- a/arch/arm/boot/dts/aspeed-bmc-opp-romulus.dts
+++ b/arch/arm/boot/dts/aspeed-bmc-opp-romulus.dts
@@ -1,23 +1,19 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0+
 /dts-v1/;
-
 #include "aspeed-g5.dtsi"
+#include <dt-bindings/gpio/aspeed-gpio.h>
 
 / {
 	model = "Romulus BMC";
 	compatible = "ibm,romulus-bmc", "aspeed,ast2500";
 
-	aliases {
-		serial4 = &uart5;
-	};
-
 	chosen {
 		stdout-path = &uart5;
 		bootargs = "console=ttyS4,115200 earlyprintk";
 	};
 
-	memory {
-		reg = <0x80000000 0x40000000>;
+	memory@80000000 {
+		reg = <0x80000000 0x20000000>;
 	};
 
 	reserved-memory {
@@ -29,6 +25,49 @@
 			no-map;
 			reg = <0xbf000000 0x01000000>; /* 16M */
 		};
+
+		flash_memory: region@98000000 {
+			no-map;
+			reg = <0x98000000 0x04000000>; /* 64M */
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		fault {
+			gpios = <&gpio ASPEED_GPIO(N, 2) GPIO_ACTIVE_LOW>;
+		};
+
+		identify {
+			gpios = <&gpio ASPEED_GPIO(N, 4) GPIO_ACTIVE_HIGH>;
+		};
+
+		power {
+			gpios = <&gpio ASPEED_GPIO(R, 5) GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	fsi: gpio-fsi {
+		compatible = "fsi-master-gpio", "fsi-master";
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		clock-gpios = <&gpio ASPEED_GPIO(AA, 0) GPIO_ACTIVE_HIGH>;
+		data-gpios = <&gpio ASPEED_GPIO(AA, 2) GPIO_ACTIVE_HIGH>;
+		mux-gpios = <&gpio ASPEED_GPIO(A, 6) GPIO_ACTIVE_HIGH>;
+		enable-gpios = <&gpio ASPEED_GPIO(D, 0) GPIO_ACTIVE_HIGH>;
+		trans-gpios = <&gpio ASPEED_GPIO(R, 2) GPIO_ACTIVE_HIGH>;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		checkstop {
+			label = "checkstop";
+			gpios = <&gpio ASPEED_GPIO(J, 2) GPIO_ACTIVE_LOW>;
+			linux,code = <ASPEED_GPIO(J, 2)>;
+		};
 	};
 };
 
@@ -38,6 +77,7 @@
 		status = "okay";
 		m25p,fast-read;
 		label = "bmc";
+#include "openbmc-flash-layout.dtsi"
 	};
 };
 
@@ -53,6 +93,12 @@
 	};
 };
 
+&lpc_ctrl {
+	status = "okay";
+	memory-region = <&flash_memory>;
+	flash = <&spi1>;
+};
+
 &uart1 {
 	/* Rear RS-232 connector */
 	status = "okay";
@@ -81,6 +127,10 @@
 	pinctrl-0 = <&pinctrl_rmii1_default>;
 };
 
+&i2c1 {
+	status = "okay";
+};
+
 &i2c2 {
 	status = "okay";
 };
@@ -133,8 +183,77 @@
 
 &i2c12 {
 	status = "okay";
+
+	max31785@52 {
+		compatible = "maxim,max31785";
+		reg = <0x52>;
+	};
+};
+
+&gpio {
+	nic_func_mode0 {
+		gpio-hog;
+		gpios = <ASPEED_GPIO(D, 3) GPIO_ACTIVE_HIGH>;
+		output-low;
+		line-name = "nic_func_mode0";
+	};
+	nic_func_mode1 {
+		gpio-hog;
+		gpios = <ASPEED_GPIO(D, 4) GPIO_ACTIVE_HIGH>;
+		output-low;
+		line-name = "nic_func_mode1";
+	};
 };
 
 &vuart {
 	status = "okay";
 };
+
+&gfx {
+	status = "okay";
+};
+
+&pinctrl {
+	aspeed,external-nodes = <&gfx &lhc>;
+};
+
+&pwm_tacho {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm0_default &pinctrl_pwm1_default>;
+
+	fan@0 {
+		reg = <0x00>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x08>;
+	};
+
+	fan@1 {
+		reg = <0x00>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x09>;
+	};
+
+	fan@2 {
+		reg = <0x01>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x0a>;
+	};
+
+	fan@3 {
+		reg = <0x01>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x0b>;
+	};
+
+	fan@4 {
+		reg = <0x00>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x0c>;
+	};
+
+	fan@5 {
+		reg = <0x00>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x0d>;
+	};
+
+	fan@6 {
+		reg = <0x01>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x0e>;
+	};
+};
diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-witherspoon.dts b/arch/arm/boot/dts/aspeed-bmc-opp-witherspoon.dts
new file mode 100644
index 000000000000..5f9049d2c4c3
--- /dev/null
+++ b/arch/arm/boot/dts/aspeed-bmc-opp-witherspoon.dts
@@ -0,0 +1,548 @@
+// SPDX-License-Identifier: GPL-2.0+
+/dts-v1/;
+#include "aspeed-g5.dtsi"
+#include <dt-bindings/gpio/aspeed-gpio.h>
+#include <dt-bindings/leds/leds-pca955x.h>
+
+/ {
+	model = "Witherspoon BMC";
+	compatible = "ibm,witherspoon-bmc", "aspeed,ast2500";
+
+	chosen {
+		stdout-path = &uart5;
+		bootargs = "console=ttyS4,115200 earlyprintk";
+	};
+
+	memory@80000000 {
+		reg = <0x80000000 0x20000000>;
+	};
+
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		flash_memory: region@98000000 {
+			no-map;
+			reg = <0x98000000 0x04000000>; /* 64M */
+		};
+	};
+
+	gpio-keys-polled {
+		compatible = "gpio-keys-polled";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		poll-interval = <1000>;
+
+		fan0-presence {
+			label = "fan0-presence";
+			gpios = <&pca0 4 GPIO_ACTIVE_LOW>;
+			linux,code = <4>;
+		};
+
+		fan1-presence {
+			label = "fan1-presence";
+			gpios = <&pca0 5 GPIO_ACTIVE_LOW>;
+			linux,code = <5>;
+		};
+
+		fan2-presence {
+			label = "fan2-presence";
+			gpios = <&pca0 6 GPIO_ACTIVE_LOW>;
+			linux,code = <6>;
+		};
+
+		fan3-presence {
+			label = "fan3-presence";
+			gpios = <&pca0 7 GPIO_ACTIVE_LOW>;
+			linux,code = <7>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		fan0 {
+			retain-state-shutdown;
+			default-state = "keep";
+			gpios = <&pca0 0 GPIO_ACTIVE_LOW>;
+		};
+
+		fan1 {
+			retain-state-shutdown;
+			default-state = "keep";
+			gpios = <&pca0 1 GPIO_ACTIVE_LOW>;
+		};
+
+		fan2 {
+			retain-state-shutdown;
+			default-state = "keep";
+			gpios = <&pca0 2 GPIO_ACTIVE_LOW>;
+		};
+
+		fan3 {
+			retain-state-shutdown;
+			default-state = "keep";
+			gpios = <&pca0 3 GPIO_ACTIVE_LOW>;
+		};
+
+		front-fault {
+			retain-state-shutdown;
+			default-state = "keep";
+			gpios = <&pca0 13 GPIO_ACTIVE_LOW>;
+		};
+
+		front-power {
+			retain-state-shutdown;
+			default-state = "keep";
+			gpios = <&pca0 14 GPIO_ACTIVE_LOW>;
+		};
+
+		front-id {
+			retain-state-shutdown;
+			default-state = "keep";
+			gpios = <&pca0 15 GPIO_ACTIVE_LOW>;
+		};
+
+		rear-fault {
+			gpios = <&gpio ASPEED_GPIO(N, 2) GPIO_ACTIVE_LOW>;
+		};
+
+		rear-id {
+			gpios = <&gpio ASPEED_GPIO(N, 4) GPIO_ACTIVE_LOW>;
+		};
+
+		rear-power {
+			gpios = <&gpio ASPEED_GPIO(N, 3) GPIO_ACTIVE_LOW>;
+		};
+
+		power-button {
+			gpios = <&gpio ASPEED_GPIO(R, 5) GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	fsi: gpio-fsi {
+		compatible = "fsi-master-gpio", "fsi-master";
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		clock-gpios = <&gpio ASPEED_GPIO(AA, 0) GPIO_ACTIVE_HIGH>;
+		data-gpios = <&gpio ASPEED_GPIO(E, 0) GPIO_ACTIVE_HIGH>;
+		mux-gpios = <&gpio ASPEED_GPIO(A, 6) GPIO_ACTIVE_HIGH>;
+		enable-gpios = <&gpio ASPEED_GPIO(D, 0) GPIO_ACTIVE_HIGH>;
+		trans-gpios = <&gpio ASPEED_GPIO(R, 2) GPIO_ACTIVE_HIGH>;
+	};
+
+	iio-hwmon-dps310 {
+		compatible = "iio-hwmon";
+		io-channels = <&dps 0>;
+	};
+
+	iio-hwmon-bmp280 {
+		compatible = "iio-hwmon";
+		io-channels = <&bmp 1>;
+	};
+
+};
+
+&fmc {
+	status = "okay";
+
+	flash@0 {
+		status = "okay";
+		label = "bmc";
+		m25p,fast-read;
+#include "openbmc-flash-layout.dtsi"
+	};
+
+	flash@1 {
+		status = "okay";
+		label = "alt";
+		m25p,fast-read;
+	};
+};
+
+&spi1 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_spi1_default>;
+
+	flash@0 {
+		status = "okay";
+		label = "pnor";
+		m25p,fast-read;
+	};
+};
+
+&uart1 {
+	/* Rear RS-232 connector */
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_txd1_default
+			&pinctrl_rxd1_default
+			&pinctrl_nrts1_default
+			&pinctrl_ndtr1_default
+			&pinctrl_ndsr1_default
+			&pinctrl_ncts1_default
+			&pinctrl_ndcd1_default
+			&pinctrl_nri1_default>;
+};
+
+&uart2 {
+	/* APSS */
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_txd2_default &pinctrl_rxd2_default>;
+};
+
+&uart5 {
+	status = "okay";
+};
+
+&lpc_ctrl {
+	status = "okay";
+	memory-region = <&flash_memory>;
+	flash = <&spi1>;
+};
+
+&mac0 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_rmii1_default>;
+	use-ncsi;
+};
+
+&i2c2 {
+	status = "okay";
+
+	/* MUX ->
+	 *    Samtec 1
+	 *    Samtec 2
+	 */
+};
+
+&i2c3 {
+	status = "okay";
+
+	bmp: bmp280@77 {
+		compatible = "bosch,bmp280";
+		reg = <0x77>;
+		#io-channel-cells = <1>;
+	};
+
+	max31785@52 {
+		compatible = "maxim,max31785a";
+		reg = <0x52>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+	};
+
+	dps: dps310@76 {
+		compatible = "infineon,dps310";
+		reg = <0x76>;
+		#io-channel-cells = <0>;
+	};
+
+	pca0: pca9552@60 {
+		compatible = "nxp,pca9552";
+		reg = <0x60>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		gpio@0 {
+			reg = <0>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@1 {
+			reg = <1>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@2 {
+			reg = <2>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@3 {
+			reg = <3>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@4 {
+			reg = <4>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@5 {
+			reg = <5>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@6 {
+			reg = <6>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@7 {
+			reg = <7>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@8 {
+			reg = <8>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@9 {
+			reg = <9>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@10 {
+			reg = <10>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@11 {
+			reg = <11>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@12 {
+			reg = <12>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@13 {
+			reg = <13>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@14 {
+			reg = <14>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@15 {
+			reg = <15>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+	};
+
+	power-supply@68 {
+		compatible = "ibm,cffps1";
+		reg = <0x68>;
+	};
+
+	power-supply@69 {
+		compatible = "ibm,cffps1";
+		reg = <0x69>;
+	};
+};
+
+&i2c4 {
+	status = "okay";
+
+	tmp423a@4c {
+		compatible = "ti,tmp423";
+		reg = <0x4c>;
+	};
+
+	ir35221@70 {
+		compatible = "infineon,ir35221";
+		reg = <0x70>;
+	};
+
+	ir35221@71 {
+		compatible = "infineon,ir35221";
+		reg = <0x71>;
+	};
+};
+
+
+&i2c5 {
+	status = "okay";
+
+	tmp423a@4c {
+		compatible = "ti,tmp423";
+		reg = <0x4c>;
+	};
+
+	ir35221@70 {
+		compatible = "infineon,ir35221";
+		reg = <0x70>;
+	};
+
+	ir35221@71 {
+		compatible = "infineon,ir35221";
+		reg = <0x71>;
+	};
+};
+
+&i2c9 {
+	status = "okay";
+
+	tmp275@4a {
+		compatible = "ti,tmp275";
+		reg = <0x4a>;
+	};
+};
+
+&i2c10 {
+	/* MUX
+	 *   -> PCIe Slot 3
+	 *   -> PCIe Slot 4
+	 */
+	status = "okay";
+};
+
+&i2c11 {
+	status = "okay";
+
+	pca9552: pca9552@60 {
+		compatible = "nxp,pca9552";
+		reg = <0x60>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		gpio-line-names = "PS_SMBUS_RESET_N", "APSS_RESET_N",
+			"GPU0_TH_OVERT_N_BUFF",	"GPU1_TH_OVERT_N_BUFF",
+			"GPU2_TH_OVERT_N_BUFF", "GPU3_TH_OVERT_N_BUFF",
+			"GPU4_TH_OVERT_N_BUFF",	"GPU5_TH_OVERT_N_BUFF",
+			"GPU0_PWR_GOOD_BUFF", "GPU1_PWR_GOOD_BUFF",
+			"GPU2_PWR_GOOD_BUFF", "GPU3_PWR_GOOD_BUFF",
+			"GPU4_PWR_GOOD_BUFF", "GPU5_PWR_GOOD_BUFF",
+			"12V_BREAKER_FLT_N", "THROTTLE_UNLATCHED_N";
+
+		gpio@0 {
+			reg = <0>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@1 {
+			reg = <1>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@2 {
+			reg = <2>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@3 {
+			reg = <3>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@4 {
+			reg = <4>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@5 {
+			reg = <5>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@6 {
+			reg = <6>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@7 {
+			reg = <7>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@8 {
+			reg = <8>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@9 {
+			reg = <9>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@10 {
+			reg = <10>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@11 {
+			reg = <11>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@12 {
+			reg = <12>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@13 {
+			reg = <13>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@14 {
+			reg = <14>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+
+		gpio@15 {
+			reg = <15>;
+			type = <PCA955X_TYPE_GPIO>;
+		};
+	};
+
+	rtc@32 {
+		compatible = "epson,rx8900";
+		reg = <0x32>;
+	};
+
+	eeprom@51 {
+		compatible = "atmel,24c64";
+		reg = <0x51>;
+	};
+
+	ucd90160@64 {
+		compatible = "ti,ucd90160";
+		reg = <0x64>;
+	};
+};
+
+&i2c12 {
+	status = "okay";
+};
+
+&i2c13 {
+	status = "okay";
+};
+
+&vuart {
+	status = "okay";
+};
+
+&gfx {
+	status = "okay";
+};
+
+&pinctrl {
+	aspeed,external-nodes = <&gfx &lhc>;
+};
+
+&wdt1 {
+	aspeed,reset-type = "none";
+	aspeed,external-signal;
+	aspeed,ext-push-pull;
+	aspeed,ext-active-high;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_wdtrst1_default>;
+};
diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-zaius.dts b/arch/arm/boot/dts/aspeed-bmc-opp-zaius.dts
new file mode 100644
index 000000000000..c881484a85cf
--- /dev/null
+++ b/arch/arm/boot/dts/aspeed-bmc-opp-zaius.dts
@@ -0,0 +1,426 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+#include "aspeed-g5.dtsi"
+#include <dt-bindings/gpio/aspeed-gpio.h>
+
+/ {
+	model = "Zaius BMC";
+	compatible = "ingrasys,zaius-bmc", "aspeed,ast2500";
+
+	chosen {
+		stdout-path = &uart5;
+		bootargs = "console=ttyS4,115200 earlyprintk";
+	};
+
+	memory@80000000 {
+		reg = <0x80000000 0x40000000>;
+	};
+
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		flash_memory: region@98000000 {
+			no-map;
+			reg = <0x98000000 0x04000000>; /* 64M */
+		};
+	};
+
+	onewire0 {
+		compatible = "w1-gpio";
+		gpios = <&gpio ASPEED_GPIO(H, 0) GPIO_ACTIVE_HIGH>;
+	};
+
+	onewire1 {
+		compatible = "w1-gpio";
+		gpios = <&gpio ASPEED_GPIO(H, 1) GPIO_ACTIVE_HIGH>;
+	};
+
+	onewire2 {
+		compatible = "w1-gpio";
+		gpios = <&gpio ASPEED_GPIO(H, 2) GPIO_ACTIVE_HIGH>;
+	};
+
+	onewire3 {
+		compatible = "w1-gpio";
+		gpios = <&gpio ASPEED_GPIO(H, 3) GPIO_ACTIVE_HIGH>;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		checkstop {
+			label = "checkstop";
+			gpios = <&gpio ASPEED_GPIO(F, 7) GPIO_ACTIVE_LOW>;
+			linux,code = <ASPEED_GPIO(F, 7)>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		sys_boot_status {
+			label = "System boot status";
+			gpios = <&gpio ASPEED_GPIO(D, 5) GPIO_ACTIVE_LOW>;
+		};
+
+		attention {
+			label = "Attention";
+			gpios = <&gpio ASPEED_GPIO(D, 6) GPIO_ACTIVE_LOW>;
+		};
+
+		plt_fault {
+			label = "Platform fault";
+			gpios = <&gpio ASPEED_GPIO(D, 7) GPIO_ACTIVE_LOW>;
+		};
+
+		hdd_fault {
+			label = "Onboard drive fault";
+			gpios = <&gpio ASPEED_GPIO(AA, 2) GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	fsi: gpio-fsi {
+		compatible = "fsi-master-gpio", "fsi-master";
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		trans-gpios = <&gpio ASPEED_GPIO(O, 6) GPIO_ACTIVE_HIGH>;
+		enable-gpios = <&gpio ASPEED_GPIO(D, 0) GPIO_ACTIVE_HIGH>;
+		clock-gpios = <&gpio ASPEED_GPIO(G, 0) GPIO_ACTIVE_HIGH>;
+		data-gpios = <&gpio ASPEED_GPIO(G, 1) GPIO_ACTIVE_HIGH>;
+		mux-gpios = <&gpio ASPEED_GPIO(P, 6) GPIO_ACTIVE_HIGH>;
+	};
+
+	iio-hwmon {
+		compatible = "iio-hwmon";
+		io-channels = <&adc 0>, <&adc 1>, <&adc 2>, <&adc 3>,
+			<&adc 4>, <&adc 5>, <&adc 6>, <&adc 7>,
+			<&adc 8>, <&adc 9>, <&adc 10>, <&adc 11>,
+			<&adc 13>, <&adc 14>, <&adc 15>;
+	};
+
+	iio-hwmon-battery {
+		compatible = "iio-hwmon";
+		io-channels = <&adc 12>;
+	};
+
+};
+
+&fmc {
+	status = "okay";
+
+	flash@0 {
+		status = "okay";
+		label = "bmc";
+		m25p,fast-read;
+#include "openbmc-flash-layout.dtsi"
+	};
+};
+
+&spi1 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_spi1_default>;
+
+	flash@0 {
+		status = "okay";
+		label = "pnor";
+		m25p,fast-read;
+	};
+};
+
+&spi2 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_spi2ck_default
+		     &pinctrl_spi2cs0_default
+		     &pinctrl_spi2cs1_default
+		     &pinctrl_spi2miso_default
+		     &pinctrl_spi2mosi_default>;
+
+	flash@0 {
+		status = "okay";
+	};
+};
+
+&uart1 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_txd1_default
+		     &pinctrl_rxd1_default>;
+};
+
+&lpc_ctrl {
+	status = "okay";
+	memory-region = <&flash_memory>;
+	flash = <&spi1>;
+};
+
+&lpc_snoop {
+	status = "okay";
+	snoop-ports = <0x80>;
+};
+
+
+&uart5 {
+	status = "okay";
+};
+
+&mac0 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_rmii1_default>;
+	use-ncsi;
+};
+
+&mac1 {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_rgmii2_default &pinctrl_mdio2_default>;
+};
+
+&i2c0 {
+	status = "okay";
+
+	eeprom@50 {
+		compatible = "atmel,24c64";
+		reg = <0x50>;
+		pagesize = <32>;
+	};
+
+	rtc@68 {
+		compatible = "nxp,pcf8523";
+		reg = <0x68>;
+	};
+
+	ucd90160@64 {
+		compatible = "ti,ucd90160";
+		reg = <0x64>;
+	};
+
+	/* Power sequencer UCD90160 PMBUS @64h
+	 * FRU AT24C64D @50h
+	 * RTC PCF8523 @68h
+	 * Clock buffer 9DBL04 @6dh
+	 */
+};
+
+&i2c1 {
+	status = "okay";
+
+	i2c-switch@71 {
+		compatible = "nxp,pca9546";
+		reg = <0x71>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+	};
+
+	/* MUX1 PCA9546A @71h
+	 *   PCIe 0
+	 *   PCIe 1
+	 *   PCIe 2
+	 *   TPM header
+	 */
+};
+
+&i2c2 {
+	status = "disabled";
+
+	/* OCP Mezz Connector A (OOB SMBUS) */
+};
+
+&i2c3 {
+	status = "disabled";
+
+	/* OCP Mezz Connector A (PCIe slot SMBUS) */
+};
+
+&i2c4 {
+	status = "okay";
+
+	i2c-switch@71 {
+		compatible = "nxp,pca9546";
+		reg = <0x71>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+	};
+
+	/* MUX1 PCA9546A @71h
+	 *   PCIe 3
+	 *   PCIe 4
+	 */
+};
+
+
+&i2c5 {
+	status = "disabled";
+
+	/* CPU0 PRM 0.7V */
+	/* CPU0 PRM 1.2V CH03 */
+	/* CPU0 PRM 0.8V */
+	/* CPU0 PRM 1.2V CH47 */
+};
+
+&i2c6 {
+	status = "disabled";
+
+	/* CPU1 PRM 0.7V */
+	/* CPU1 PRM 1.2V CH03 */
+	/* CPU1 PRM 0.8V */
+	/* CPU1 PRM 1.2V CH47 */
+};
+
+&i2c7 {
+	status = "okay";
+
+	pca9541a@70 {
+		compatible = "nxp,pca9541";
+		reg = <0x70>;
+
+		i2c-arb {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			hotswap@54 {
+				compatible = "ti,lm5066i";
+				reg = <0x54>;
+			};
+		};
+	};
+
+	/* Master selector PCA9541A @70h (other master: CPU0)
+	 *   LM5066I PMBUS @10h
+	 */
+
+	/* 12V Quarter Brick DC/DC Converter Q54SJ12050 @61h */
+	power-brick@61 {
+		compatible = "delta,dps800";
+		reg = <0x61>;
+	};
+
+	/* CPU0 VR ISL68137 0.7V, 0.96V PMBUS @64h */
+	/* CPU0 VR ISL68137 1.2V CH03 PMBUS @40h */
+	/* CPU0 VR ISL68137 0.8V PMBUS @60h */
+	/* CPU0 VR 1.0V IR38064 I2C @11h, PMBUS @41h */
+	/* CPU0 VR ISL68137 1.2V CH47 PMBUS @41h */
+};
+
+&i2c8 {
+	status = "okay";
+
+	/* CPU1 VR ISL68137 0.7V, 0.96V PMBUS @65h */
+	/* CPU1 VR ISL68137 1.2V CH03 PMBUS @44h */
+	/* CPU1 VR ISL68137 0.8V PMBUS @61h */
+	/* CPU1 VR 1.0V IR38064 I2C @12h, PMBUS @42h */
+	/* CPU0 VR ISL68137 1.2V CH47 PMBUS @45h */
+};
+
+
+&i2c9 {
+	status = "disabled";
+
+	/* Fan board */
+};
+
+&i2c10 {
+	status = "disabled";
+};
+
+&i2c11 {
+	status = "disabled";
+
+	/* GPU sideband */
+};
+
+&i2c12 {
+	status = "disabled";
+};
+
+&i2c13 {
+	status = "disabled";
+
+	/* MUX PI3USB102
+	 *   CPU0 debug
+	 *   CPU1 debug
+	 */
+};
+
+&pinctrl {
+	aspeed,external-nodes = <&gfx &lhc>;
+
+	pinctrl_gpioh_unbiased: gpioi_unbiased {
+		pins = "A8", "C7", "B7", "A7", "D7", "B6", "A6", "E7";
+		bias-disable;
+	};
+};
+
+&gpio {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_gpioh_unbiased>;
+
+	line_iso_u146_en {
+		gpio-hog;
+		gpios = <ASPEED_GPIO(O, 4) GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "iso_u164_en";
+	};
+
+	ncsi_mux_en_n {
+		gpio-hog;
+		gpios = <ASPEED_GPIO(P, 0) GPIO_ACTIVE_HIGH>;
+		output-low;
+		line-name = "ncsi_mux_en_n";
+	};
+
+	line_bmc_i2c2_sw_rst_n {
+		gpio-hog;
+		gpios = <ASPEED_GPIO(P, 1) GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "bmc_i2c2_sw_rst_n";
+	};
+
+	line_bmc_i2c5_sw_rst_n {
+		gpio-hog;
+		gpios = <ASPEED_GPIO(P, 3) GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "bmc_i2c5_sw_rst_n";
+	};
+};
+
+&vuart {
+	status = "okay";
+};
+
+&gfx {
+	status = "okay";
+};
+
+&pwm_tacho {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm0_default &pinctrl_pwm1_default
+		&pinctrl_pwm2_default &pinctrl_pwm3_default>;
+
+	fan@0 {
+		reg = <0x00>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x00>;
+	};
+
+	fan@1 {
+		reg = <0x01>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x01>;
+	};
+
+	fan@2 {
+		reg = <0x02>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x02>;
+	};
+
+	fan@3 {
+		reg = <0x03>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x03>;
+	};
+};
diff --git a/arch/arm/boot/dts/aspeed-bmc-quanta-q71l.dts b/arch/arm/boot/dts/aspeed-bmc-quanta-q71l.dts
new file mode 100644
index 000000000000..76aa6ea1f988
--- /dev/null
+++ b/arch/arm/boot/dts/aspeed-bmc-quanta-q71l.dts
@@ -0,0 +1,458 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+#include "aspeed-g4.dtsi"
+#include <dt-bindings/gpio/aspeed-gpio.h>
+
+/ {
+	model = "Quanta Q71L BMC";
+	compatible = "quanta,q71l-bmc", "aspeed,ast2400";
+
+	chosen {
+		stdout-path = &uart5;
+		bootargs = "console=ttyS4,115200 earlyprintk";
+	};
+
+	memory@40000000 {
+		reg = <0x40000000 0x8000000>;
+	};
+
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		vga_memory: framebuffer@47800000 {
+			no-map;
+			reg = <0x47800000 0x00800000>; /* 8MB */
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		heartbeat {
+			gpios = <&gpio ASPEED_GPIO(B, 0) GPIO_ACTIVE_LOW>;
+		};
+
+		power {
+			gpios = <&gpio ASPEED_GPIO(B, 2) GPIO_ACTIVE_LOW>;
+		};
+
+		identify {
+			gpios = <&gpio ASPEED_GPIO(B, 3) GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	iio-hwmon {
+		compatible = "iio-hwmon";
+		io-channels = <&adc 0>, <&adc 1>, <&adc 2>, <&adc 3>,
+			<&adc 4>, <&adc 5>, <&adc 6>, <&adc 7>,
+			<&adc 8>, <&adc 9>, <&adc 10>;
+	};
+
+	iio-hwmon-battery {
+		compatible = "iio-hwmon";
+		io-channels = <&adc 11>;
+	};
+
+	i2c1mux: i2cmux {
+		compatible = "i2c-mux-gpio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		/* mux-gpios = <&sgpio 10 GPIO_ACTIVE_HIGH> */
+		i2c-parent = <&i2c1>;
+	};
+};
+
+&fmc {
+	status = "okay";
+	flash@0 {
+		status = "okay";
+		label = "bmc";
+		m25p,fast-read;
+#include "openbmc-flash-layout.dtsi"
+	};
+};
+
+&spi {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_spi1_default>;
+
+	flash@0 {
+		status = "okay";
+		m25p,fast-read;
+		label = "pnor";
+	};
+};
+
+&pinctrl {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_vgahs_default &pinctrl_vgavs_default
+			&pinctrl_ddcclk_default &pinctrl_ddcdat_default>;
+};
+
+&lpc_snoop {
+	status = "okay";
+	snoop-ports = <0x80>;
+};
+
+&mac0 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_rmii1_default>;
+	use-ncsi;
+};
+
+&mac1 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_rgmii2_default &pinctrl_mdio2_default>;
+};
+
+&uart5 {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+};
+
+&i2c1 {
+	status = "okay";
+
+	/* temp2 inlet */
+	tmp75@4c {
+		compatible = "ti,tmp75";
+		reg = <0x4c>;
+	};
+
+	/* temp3 */
+	tmp75@4e {
+		compatible = "ti,tmp75";
+		reg = <0x4e>;
+	};
+
+	/* temp1 */
+	tmp75@4f {
+		compatible = "ti,tmp75";
+		reg = <0x4f>;
+	};
+
+	/* Baseboard FRU */
+	eeprom@54 {
+		compatible = "atmel,24c64";
+		reg = <0x54>;
+	};
+
+	/* FP FRU */
+	eeprom@57 {
+		compatible = "atmel,24c64";
+		reg = <0x57>;
+	};
+};
+
+&i2c2 {
+	status = "okay";
+
+	/* 0: PCIe Slot 2,
+	 *    Slot 3,
+	 *    Slot 6,
+	 *    Slot 7
+	 */
+	i2c-switch@74 {
+		compatible = "nxp,pca9546";
+		reg = <0x74>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		i2c-mux-idle-disconnect;  /* may use mux@77 next. */
+
+		i2c_pcie2: i2c@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+		};
+
+		i2c_pcie3: i2c@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+		};
+
+		i2c_pcie6: i2c@2 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <2>;
+		};
+
+		i2c_pcie7: i2c@3 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <3>;
+		};
+	};
+
+	/* 0: PCIe Slot 1,
+	 *    Slot 4,
+	 *    Slot 5,
+	 *    Slot 8,
+	 *    Slot 9,
+	 *    Slot 10,
+	 *    SSD 1,
+	 *    SSD 2
+	 */
+	i2c-switch@77 {
+		compatible = "nxp,pca9548";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x77>;
+		i2c-mux-idle-disconnect;  /* may use mux@74 next. */
+
+		i2c_pcie1: i2c@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+		};
+
+		i2c_pcie4: i2c@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+		};
+
+		i2c_pcie5: i2c@2 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <2>;
+		};
+
+		i2c_pcie8: i2c@3 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <3>;
+		};
+
+		i2c_pcie9: i2c@4 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <4>;
+		};
+
+		i2c_pcie10: i2c@5 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <5>;
+		};
+
+		i2c_ssd1: i2c@6 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <6>;
+		};
+
+		i2c_ssd2: i2c@7 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <7>;
+		};
+	};
+};
+
+&i2c3 {
+	status = "okay";
+
+	/* BIOS FRU */
+	eeprom@56 {
+		compatible = "atmel,24c64";
+		reg = <0x56>;
+	};
+};
+
+&i2c4 {
+	status = "okay";
+};
+
+&i2c5 {
+	status = "okay";
+};
+
+&i2c6 {
+	status = "okay";
+};
+
+&i2c7 {
+	status = "okay";
+
+	/* 0: PSU4
+	 *    PSU1
+	 *    PSU3
+	 *    PSU2
+	 */
+	i2c-switch@70 {
+		compatible = "nxp,pca9546";
+		reg = <0x70>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		i2c_psu4: i2c@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+		};
+
+		i2c_psu1: i2c@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+		};
+
+		i2c_psu3: i2c@2 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <2>;
+		};
+
+		i2c_psu2: i2c@3 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <3>;
+		};
+	};
+
+	/* PDB FRU */
+	eeprom@52 {
+		compatible = "atmel,24c64";
+		reg = <0x52>;
+	};
+};
+
+&i2c8 {
+	status = "okay";
+
+	/* BMC FRU */
+	eeprom@50 {
+		compatible = "atmel,24c64";
+		reg = <0x50>;
+	};
+};
+
+&vuart {
+	status = "okay";
+};
+
+&wdt2 {
+	status = "okay";
+};
+
+&pwm_tacho {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm0_default
+		&pinctrl_pwm1_default
+		&pinctrl_pwm2_default
+		&pinctrl_pwm3_default>;
+
+	fan@0 {
+		reg = <0x00>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x00>;
+	};
+
+	fan@1 {
+		reg = <0x01>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x01>;
+	};
+
+	fan@2 {
+		reg = <0x02>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x02>;
+	};
+
+	fan@3 {
+		reg = <0x03>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x03>;
+	};
+
+	fan@4 {
+		reg = <0x00>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x04>;
+	};
+
+	fan@5 {
+		reg = <0x01>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x05>;
+	};
+
+	fan@6 {
+		reg = <0x02>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x06>;
+	};
+
+	fan@7 {
+		reg = <0x03>;
+		aspeed,fan-tach-ch = /bits/ 8 <0x07>;
+	};
+};
+
+&i2c1mux {
+	i2c@0 {
+		reg = <0>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		/* Memory Riser 1 FRU */
+		eeprom@50 {
+			compatible = "atmel,24c02";
+			reg = <0x50>;
+		};
+
+		/* Memory Riser 2 FRU */
+		eeprom@51 {
+			compatible = "atmel,24c02";
+			reg = <0x51>;
+		};
+
+		/* Memory Riser 3 FRU */
+		eeprom@52 {
+			compatible = "atmel,24c02";
+			reg = <0x52>;
+		};
+
+		/* Memory Riser 4 FRU */
+		eeprom@53 {
+			compatible = "atmel,24c02";
+			reg = <0x53>;
+		};
+	};
+
+	i2c@1 {
+		reg = <1>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		/* Memory Riser 5 FRU */
+		eeprom@50 {
+			compatible = "atmel,24c02";
+			reg = <0x50>;
+		};
+
+		/* Memory Riser 6 FRU */
+		eeprom@51 {
+			compatible = "atmel,24c02";
+			reg = <0x51>;
+		};
+
+		/* Memory Riser 7 FRU */
+		eeprom@52 {
+			compatible = "atmel,24c02";
+			reg = <0x52>;
+		};
+
+		/* Memory Riser 8 FRU */
+		eeprom@53 {
+			compatible = "atmel,24c02";
+			reg = <0x53>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed-g4.dtsi
index 45d815a86d42..b0d8431a3700 100644
--- a/arch/arm/boot/dts/aspeed-g4.dtsi
+++ b/arch/arm/boot/dts/aspeed-g4.dtsi
@@ -1,5 +1,5 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "skeleton.dtsi"
+// SPDX-License-Identifier: GPL-2.0+
+#include <dt-bindings/clock/aspeed-clock.h>
 
 / {
 	model = "Aspeed BMC";
@@ -54,6 +54,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "aspeed,ast2400-fmc";
+			clocks = <&syscon ASPEED_CLK_AHB>;
 			status = "disabled";
 			interrupts = <19>;
 			flash@0 {
@@ -69,6 +70,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "aspeed,ast2400-spi";
+			clocks = <&syscon ASPEED_CLK_AHB>;
 			status = "disabled";
 			flash@0 {
 				reg = < 0 >;
@@ -89,6 +91,7 @@
 			compatible = "aspeed,ast2400-mac", "faraday,ftgmac100";
 			reg = <0x1e660000 0x180>;
 			interrupts = <2>;
+			clocks = <&syscon ASPEED_CLK_GATE_MAC1CLK>;
 			status = "disabled";
 		};
 
@@ -96,6 +99,7 @@
 			compatible = "aspeed,ast2400-mac", "faraday,ftgmac100";
 			reg = <0x1e680000 0x180>;
 			interrupts = <3>;
+			clocks = <&syscon ASPEED_CLK_GATE_MAC2CLK>;
 			status = "disabled";
 		};
 
@@ -106,47 +110,12 @@
 			ranges;
 
 			syscon: syscon@1e6e2000 {
-				compatible = "aspeed,g4-scu", "syscon", "simple-mfd";
+				compatible = "aspeed,ast2400-scu", "syscon", "simple-mfd";
 				reg = <0x1e6e2000 0x1a8>;
 				#address-cells = <1>;
 				#size-cells = <0>;
-
-                                clk_clkin: clk_clkin {
-                                        #clock-cells = <0>;
-                                        compatible = "fixed-clock";
-                                        clock-frequency = <48000000>;
-                                };
-
-                                clk_hpll: clk_hpll@70 {
-                                        #clock-cells = <0>;
-                                        compatible = "aspeed,g4-hpll-clock", "fixed-clock";
-                                        reg = <0x70>;
-                                        clocks = <&clk_clkin>;
-                                        clock-frequency = <384000000>;
-                                };
-
-                                clk_ahb: clk_ahb@70 {
-                                        #clock-cells = <0>;
-                                        compatible = "aspeed,g4-ahb-clock", "fixed-clock";
-                                        reg = <0x70>;
-                                        clocks = <&clk_hpll>;
-                                        clock-frequency = <192000000>;
-                                };
-
-                                clk_apb: clk_apb@8 {
-                                        #clock-cells = <0>;
-                                        compatible = "aspeed,g4-apb-clock", "fixed-clock";
-                                        reg = <0x08>;
-                                        clocks = <&clk_hpll>;
-                                        clock-frequency = <48000000>;
-                                };
-
-                                clk_uart: clk_uart@2c{
-                                        #clock-cells = <0>;
-                                        compatible = "aspeed,g4-uart-clock", "fixed-clock";
-                                        reg = <0x2c>;
-                                        clock-frequency = <24000000>;
-                                };
+				#clock-cells = <1>;
+				#reset-cells = <1>;
 
 				pinctrl: pinctrl {
 					compatible = "aspeed,g4-pinctrl";
@@ -156,7 +125,8 @@
 			adc: adc@1e6e9000 {
 				compatible = "aspeed,ast2400-adc";
 				reg = <0x1e6e9000 0xb0>;
-				clocks = <&clk_apb>;
+				clocks = <&syscon ASPEED_CLK_APB>;
+				resets = <&syscon ASPEED_RESET_ADC>;
 				#io-channel-cells = <1>;
 				status = "disabled";
 			};
@@ -173,6 +143,7 @@
 				reg = <0x1e780000 0x1000>;
 				interrupts = <20>;
 				gpio-ranges = <&pinctrl 0 0 220>;
+				clocks = <&syscon ASPEED_CLK_APB>;
 				interrupt-controller;
 			};
 
@@ -181,7 +152,7 @@
 				compatible = "aspeed,ast2400-timer";
 				reg = <0x1e782000 0x90>;
 				interrupts = <16 17 18 35 36 37 38 39>;
-				clocks = <&clk_apb>;
+				clocks = <&syscon ASPEED_CLK_APB>;
 				clock-names = "PCLK";
 			};
 
@@ -190,7 +161,7 @@
 				reg = <0x1e783000 0x20>;
 				reg-shift = <2>;
 				interrupts = <9>;
-				clocks = <&clk_uart>;
+				clocks = <&syscon ASPEED_CLK_GATE_UART1CLK>;
 				no-loopback-test;
 				status = "disabled";
 			};
@@ -200,7 +171,7 @@
 				reg = <0x1e784000 0x20>;
 				reg-shift = <2>;
 				interrupts = <10>;
-				clocks = <&clk_uart>;
+				clocks = <&syscon ASPEED_CLK_GATE_UART5CLK>;
 				no-loopback-test;
 				status = "disabled";
 			};
@@ -208,29 +179,83 @@
 			wdt1: watchdog@1e785000 {
 				compatible = "aspeed,ast2400-wdt";
 				reg = <0x1e785000 0x1c>;
+				clocks = <&syscon ASPEED_CLK_APB>;
 			};
 
 			wdt2: watchdog@1e785020 {
 				compatible = "aspeed,ast2400-wdt";
 				reg = <0x1e785020 0x1c>;
+				clocks = <&syscon ASPEED_CLK_APB>;
+			};
+
+			pwm_tacho: pwm-tacho-controller@1e786000 {
+				compatible = "aspeed,ast2400-pwm-tacho";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0x1e786000 0x1000>;
+				clocks = <&syscon ASPEED_CLK_APB>;
+				resets = <&syscon ASPEED_RESET_PWM>;
+				status = "disabled";
 			};
 
 			vuart: serial@1e787000 {
 				compatible = "aspeed,ast2400-vuart";
 				reg = <0x1e787000 0x40>;
 				reg-shift = <2>;
-				interrupts = <10>;
-				clocks = <&clk_uart>;
+				interrupts = <8>;
+				clocks = <&syscon ASPEED_CLK_APB>;
 				no-loopback-test;
 				status = "disabled";
 			};
 
+			lpc: lpc@1e789000 {
+				compatible = "aspeed,ast2400-lpc", "simple-mfd";
+				reg = <0x1e789000 0x1000>;
+
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0x0 0x1e789000 0x1000>;
+
+				lpc_bmc: lpc-bmc@0 {
+					compatible = "aspeed,ast2400-lpc-bmc";
+					reg = <0x0 0x80>;
+				};
+
+				lpc_host: lpc-host@80 {
+					compatible = "aspeed,ast2400-lpc-host", "simple-mfd", "syscon";
+					reg = <0x80 0x1e0>;
+					reg-io-width = <4>;
+
+					#address-cells = <1>;
+					#size-cells = <1>;
+					ranges = <0x0 0x80 0x1e0>;
+
+					lpc_ctrl: lpc-ctrl@0 {
+						compatible = "aspeed,ast2400-lpc-ctrl";
+						reg = <0x0 0x80>;
+						status = "disabled";
+					};
+
+					lpc_snoop: lpc-snoop@0 {
+						compatible = "aspeed,ast2400-lpc-snoop";
+						reg = <0x0 0x80>;
+						interrupts = <8>;
+						status = "disabled";
+					};
+
+					lhc: lhc@20 {
+						compatible = "aspeed,ast2400-lhc";
+						reg = <0x20 0x24 0x48 0x8>;
+					};
+				};
+			};
+
 			uart2: serial@1e78d000 {
 				compatible = "ns16550a";
 				reg = <0x1e78d000 0x20>;
 				reg-shift = <2>;
 				interrupts = <32>;
-				clocks = <&clk_uart>;
+				clocks = <&syscon ASPEED_CLK_GATE_UART2CLK>;
 				no-loopback-test;
 				status = "disabled";
 			};
@@ -240,7 +265,7 @@
 				reg = <0x1e78e000 0x20>;
 				reg-shift = <2>;
 				interrupts = <33>;
-				clocks = <&clk_uart>;
+				clocks = <&syscon ASPEED_CLK_GATE_UART3CLK>;
 				no-loopback-test;
 				status = "disabled";
 			};
@@ -250,7 +275,7 @@
 				reg = <0x1e78f000 0x20>;
 				reg-shift = <2>;
 				interrupts = <34>;
-				clocks = <&clk_uart>;
+				clocks = <&syscon ASPEED_CLK_GATE_UART4CLK>;
 				no-loopback-test;
 				status = "disabled";
 			};
@@ -281,7 +306,8 @@
 
 		reg = <0x40 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <0>;
 		interrupt-parent = <&i2c_ic>;
@@ -296,7 +322,8 @@
 
 		reg = <0x80 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <1>;
 		interrupt-parent = <&i2c_ic>;
@@ -311,7 +338,8 @@
 
 		reg = <0xc0 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <2>;
 		interrupt-parent = <&i2c_ic>;
@@ -327,7 +355,8 @@
 
 		reg = <0x100 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <3>;
 		interrupt-parent = <&i2c_ic>;
@@ -343,7 +372,8 @@
 
 		reg = <0x140 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <4>;
 		interrupt-parent = <&i2c_ic>;
@@ -359,7 +389,8 @@
 
 		reg = <0x180 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <5>;
 		interrupt-parent = <&i2c_ic>;
@@ -375,7 +406,8 @@
 
 		reg = <0x1c0 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <6>;
 		interrupt-parent = <&i2c_ic>;
@@ -391,7 +423,8 @@
 
 		reg = <0x300 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <7>;
 		interrupt-parent = <&i2c_ic>;
@@ -407,7 +440,8 @@
 
 		reg = <0x340 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <8>;
 		interrupt-parent = <&i2c_ic>;
@@ -423,7 +457,8 @@
 
 		reg = <0x380 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <9>;
 		interrupt-parent = <&i2c_ic>;
@@ -439,7 +474,8 @@
 
 		reg = <0x3c0 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <10>;
 		interrupt-parent = <&i2c_ic>;
@@ -455,7 +491,8 @@
 
 		reg = <0x400 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <11>;
 		interrupt-parent = <&i2c_ic>;
@@ -471,7 +508,8 @@
 
 		reg = <0x440 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <12>;
 		interrupt-parent = <&i2c_ic>;
@@ -487,7 +525,8 @@
 
 		reg = <0x480 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <13>;
 		interrupt-parent = <&i2c_ic>;
diff --git a/arch/arm/boot/dts/aspeed-g5.dtsi b/arch/arm/boot/dts/aspeed-g5.dtsi
index 5c4ecdba3a6b..40de3b66c33f 100644
--- a/arch/arm/boot/dts/aspeed-g5.dtsi
+++ b/arch/arm/boot/dts/aspeed-g5.dtsi
@@ -1,5 +1,5 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "skeleton.dtsi"
+// SPDX-License-Identifier: GPL-2.0+
+#include <dt-bindings/clock/aspeed-clock.h>
 
 / {
 	model = "Aspeed BMC";
@@ -54,6 +54,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "aspeed,ast2500-fmc";
+			clocks = <&syscon ASPEED_CLK_AHB>;
 			status = "disabled";
 			interrupts = <19>;
 			flash@0 {
@@ -79,6 +80,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "aspeed,ast2500-spi";
+			clocks = <&syscon ASPEED_CLK_AHB>;
 			status = "disabled";
 			flash@0 {
 				reg = < 0 >;
@@ -98,6 +100,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "aspeed,ast2500-spi";
+			clocks = <&syscon ASPEED_CLK_AHB>;
 			status = "disabled";
 			flash@0 {
 				reg = < 0 >;
@@ -123,6 +126,7 @@
 			compatible = "aspeed,ast2500-mac", "faraday,ftgmac100";
 			reg = <0x1e660000 0x180>;
 			interrupts = <2>;
+			clocks = <&syscon ASPEED_CLK_GATE_MAC1CLK>;
 			status = "disabled";
 		};
 
@@ -130,6 +134,7 @@
 			compatible = "aspeed,ast2500-mac", "faraday,ftgmac100";
 			reg = <0x1e680000 0x180>;
 			interrupts = <3>;
+			clocks = <&syscon ASPEED_CLK_GATE_MAC2CLK>;
 			status = "disabled";
 		};
 
@@ -140,55 +145,18 @@
 			ranges;
 
 			syscon: syscon@1e6e2000 {
-				compatible = "aspeed,g5-scu", "syscon", "simple-mfd";
+				compatible = "aspeed,ast2500-scu", "syscon", "simple-mfd";
 				reg = <0x1e6e2000 0x1a8>;
 				#address-cells = <1>;
 				#size-cells = <0>;
-
-				clk_clkin: clk_clkin@70 {
-					#clock-cells = <0>;
-					compatible = "aspeed,g5-clkin-clock", "fixed-clock";
-					reg = <0x70>;
-					clock-frequency = <24000000>;
-				};
-
-				clk_hpll: clk_hpll@24 {
-					#clock-cells = <0>;
-					compatible = "aspeed,g5-hpll-clock", "fixed-clock";
-					reg = <0x24>;
-					clocks = <&clk_clkin>;
-					clock-frequency = <792000000>;
-				};
-
-				clk_ahb: clk_ahb@70 {
-					#clock-cells = <0>;
-					compatible = "aspeed,g5-ahb-clock", "fixed-clock";
-					reg = <0x70>;
-					clocks = <&clk_hpll>;
-					clock-frequency = <198000000>;
-				};
-
-				clk_apb: clk_apb@8 {
-					#clock-cells = <0>;
-					compatible = "aspeed,g5-apb-clock", "fixed-clock";
-					reg = <0x08>;
-					clocks = <&clk_hpll>;
-					clock-frequency = <24750000>;
-				};
-
-				clk_uart: clk_uart@2c {
-					#clock-cells = <0>;
-					compatible = "aspeed,uart-clock", "fixed-clock";
-					reg = <0x2c>;
-					clock-frequency = <24000000>;
-				};
+				#clock-cells = <1>;
+				#reset-cells = <1>;
 
 				pinctrl: pinctrl {
 					compatible = "aspeed,g5-pinctrl";
 					aspeed,external-nodes = <&gfx &lhc>;
 
 				};
-
 			};
 
 			gfx: display@1e6e6000 {
@@ -200,7 +168,8 @@
 			adc: adc@1e6e9000 {
 				compatible = "aspeed,ast2500-adc";
 				reg = <0x1e6e9000 0xb0>;
-				clocks = <&clk_apb>;
+				clocks = <&syscon ASPEED_CLK_APB>;
+				resets = <&syscon ASPEED_RESET_ADC>;
 				#io-channel-cells = <1>;
 				status = "disabled";
 			};
@@ -217,6 +186,7 @@
 				reg = <0x1e780000 0x1000>;
 				interrupts = <20>;
 				gpio-ranges = <&pinctrl 0 0 220>;
+				clocks = <&syscon ASPEED_CLK_APB>;
 				interrupt-controller;
 			};
 
@@ -225,7 +195,7 @@
 				compatible = "aspeed,ast2400-timer";
 				reg = <0x1e782000 0x90>;
 				interrupts = <16 17 18 35 36 37 38 39>;
-				clocks = <&clk_apb>;
+				clocks = <&syscon ASPEED_CLK_APB>;
 				clock-names = "PCLK";
 			};
 
@@ -234,7 +204,7 @@
 				reg = <0x1e783000 0x20>;
 				reg-shift = <2>;
 				interrupts = <9>;
-				clocks = <&clk_uart>;
+				clocks = <&syscon ASPEED_CLK_GATE_UART1CLK>;
 				no-loopback-test;
 				status = "disabled";
 			};
@@ -244,7 +214,7 @@
 				reg = <0x1e784000 0x20>;
 				reg-shift = <2>;
 				interrupts = <10>;
-				clocks = <&clk_uart>;
+				clocks = <&syscon ASPEED_CLK_GATE_UART5CLK>;
 				no-loopback-test;
 				status = "disabled";
 			};
@@ -252,16 +222,39 @@
 			wdt1: watchdog@1e785000 {
 				compatible = "aspeed,ast2500-wdt";
 				reg = <0x1e785000 0x20>;
+				clocks = <&syscon ASPEED_CLK_APB>;
 			};
 
 			wdt2: watchdog@1e785020 {
 				compatible = "aspeed,ast2500-wdt";
 				reg = <0x1e785020 0x20>;
+				clocks = <&syscon ASPEED_CLK_APB>;
 			};
 
 			wdt3: watchdog@1e785040 {
 				compatible = "aspeed,ast2500-wdt";
 				reg = <0x1e785040 0x20>;
+				clocks = <&syscon ASPEED_CLK_APB>;
+				status = "disabled";
+			};
+
+			pwm_tacho: pwm-tacho-controller@1e786000 {
+				compatible = "aspeed,ast2500-pwm-tacho";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0x1e786000 0x1000>;
+				clocks = <&syscon ASPEED_CLK_APB>;
+				resets = <&syscon ASPEED_RESET_PWM>;
+				status = "disabled";
+			};
+
+			vuart: serial@1e787000 {
+				compatible = "aspeed,ast2500-vuart";
+				reg = <0x1e787000 0x40>;
+				reg-shift = <2>;
+				interrupts = <8>;
+				clocks = <&syscon ASPEED_CLK_APB>;
+				no-loopback-test;
 				status = "disabled";
 			};
 
@@ -288,6 +281,19 @@
 
 					reg-io-width = <4>;
 
+					lpc_ctrl: lpc-ctrl@0 {
+						compatible = "aspeed,ast2500-lpc-ctrl";
+						reg = <0x0 0x80>;
+						status = "disabled";
+					};
+
+					lpc_snoop: lpc-snoop@0 {
+						compatible = "aspeed,ast2500-lpc-snoop";
+						reg = <0x0 0x80>;
+						interrupts = <8>;
+						status = "disabled";
+					};
+
 					lhc: lhc@20 {
 						compatible = "aspeed,ast2500-lhc";
 						reg = <0x20 0x24 0x48 0x8>;
@@ -295,22 +301,12 @@
 				};
 			};
 
-			vuart: serial@1e787000 {
-				compatible = "aspeed,ast2500-vuart";
-				reg = <0x1e787000 0x40>;
-				reg-shift = <2>;
-				interrupts = <10>;
-				clocks = <&clk_uart>;
-				no-loopback-test;
-				status = "disabled";
-			};
-
 			uart2: serial@1e78d000 {
 				compatible = "ns16550a";
 				reg = <0x1e78d000 0x20>;
 				reg-shift = <2>;
 				interrupts = <32>;
-				clocks = <&clk_uart>;
+				clocks = <&syscon ASPEED_CLK_GATE_UART2CLK>;
 				no-loopback-test;
 				status = "disabled";
 			};
@@ -320,7 +316,7 @@
 				reg = <0x1e78e000 0x20>;
 				reg-shift = <2>;
 				interrupts = <33>;
-				clocks = <&clk_uart>;
+				clocks = <&syscon ASPEED_CLK_GATE_UART3CLK>;
 				no-loopback-test;
 				status = "disabled";
 			};
@@ -330,7 +326,7 @@
 				reg = <0x1e78f000 0x20>;
 				reg-shift = <2>;
 				interrupts = <34>;
-				clocks = <&clk_uart>;
+				clocks = <&syscon ASPEED_CLK_GATE_UART4CLK>;
 				no-loopback-test;
 				status = "disabled";
 			};
@@ -361,7 +357,8 @@
 
 		reg = <0x40 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <0>;
 		interrupt-parent = <&i2c_ic>;
@@ -376,7 +373,8 @@
 
 		reg = <0x80 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <1>;
 		interrupt-parent = <&i2c_ic>;
@@ -391,7 +389,8 @@
 
 		reg = <0xc0 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <2>;
 		interrupt-parent = <&i2c_ic>;
@@ -407,7 +406,8 @@
 
 		reg = <0x100 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <3>;
 		interrupt-parent = <&i2c_ic>;
@@ -423,7 +423,8 @@
 
 		reg = <0x140 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <4>;
 		interrupt-parent = <&i2c_ic>;
@@ -439,7 +440,8 @@
 
 		reg = <0x180 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <5>;
 		interrupt-parent = <&i2c_ic>;
@@ -455,7 +457,8 @@
 
 		reg = <0x1c0 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <6>;
 		interrupt-parent = <&i2c_ic>;
@@ -471,7 +474,8 @@
 
 		reg = <0x300 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <7>;
 		interrupt-parent = <&i2c_ic>;
@@ -487,7 +491,8 @@
 
 		reg = <0x340 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <8>;
 		interrupt-parent = <&i2c_ic>;
@@ -503,7 +508,8 @@
 
 		reg = <0x380 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <9>;
 		interrupt-parent = <&i2c_ic>;
@@ -519,7 +525,8 @@
 
 		reg = <0x3c0 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <10>;
 		interrupt-parent = <&i2c_ic>;
@@ -535,7 +542,8 @@
 
 		reg = <0x400 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <11>;
 		interrupt-parent = <&i2c_ic>;
@@ -551,7 +559,8 @@
 
 		reg = <0x440 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <12>;
 		interrupt-parent = <&i2c_ic>;
@@ -567,7 +576,8 @@
 
 		reg = <0x480 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
-		clocks = <&clk_apb>;
+		clocks = <&syscon ASPEED_CLK_APB>;
+		resets = <&syscon ASPEED_RESET_I2C>;
 		bus-frequency = <100000>;
 		interrupts = <13>;
 		interrupt-parent = <&i2c_ic>;
diff --git a/arch/arm/boot/dts/at91-ariag25.dts b/arch/arm/boot/dts/at91-ariag25.dts
index 1c86537a42a0..e3e14b7e25aa 100644
--- a/arch/arm/boot/dts/at91-ariag25.dts
+++ b/arch/arm/boot/dts/at91-ariag25.dts
@@ -58,6 +58,18 @@
 				};
 			};
 
+			tcb0: timer@f8008000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			i2c0: i2c@f8010000 {
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/at91-ariettag25.dts b/arch/arm/boot/dts/at91-ariettag25.dts
index f877f3430bcc..7a34c4dc05d2 100644
--- a/arch/arm/boot/dts/at91-ariettag25.dts
+++ b/arch/arm/boot/dts/at91-ariettag25.dts
@@ -46,6 +46,18 @@
 				};
 			};
 
+			tcb0: timer@f8008000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			usb2: gadget@f803c000 {
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/at91-cosino.dtsi b/arch/arm/boot/dts/at91-cosino.dtsi
index 89cde175154e..295a5a43fe01 100644
--- a/arch/arm/boot/dts/at91-cosino.dtsi
+++ b/arch/arm/boot/dts/at91-cosino.dtsi
@@ -37,6 +37,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@f8008000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			mmc0: mmc@f0008000 {
 				pinctrl-0 = <
 					&pinctrl_board_mmc0
diff --git a/arch/arm/boot/dts/at91-foxg20.dts b/arch/arm/boot/dts/at91-foxg20.dts
index 50d5e719b451..d413e2d9abdf 100644
--- a/arch/arm/boot/dts/at91-foxg20.dts
+++ b/arch/arm/boot/dts/at91-foxg20.dts
@@ -34,6 +34,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			usb1: gadget@fffa4000 {
 				atmel,vbus-gpio = <&pioC 6 GPIO_ACTIVE_HIGH>;
 				status = "okay";
diff --git a/arch/arm/boot/dts/at91-kizbox.dts b/arch/arm/boot/dts/at91-kizbox.dts
index 1f31df846d61..1003846679c1 100644
--- a/arch/arm/boot/dts/at91-kizbox.dts
+++ b/arch/arm/boot/dts/at91-kizbox.dts
@@ -31,6 +31,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			macb0: ethernet@fffc4000 {
 				phy-mode = "mii";
 				pinctrl-0 = <&pinctrl_macb_rmii
diff --git a/arch/arm/boot/dts/at91-kizbox2.dts b/arch/arm/boot/dts/at91-kizbox2.dts
index ec6c28c521a5..30041e8f12d5 100644
--- a/arch/arm/boot/dts/at91-kizbox2.dts
+++ b/arch/arm/boot/dts/at91-kizbox2.dts
@@ -94,6 +94,18 @@
 				};
 			};
 
+			tcb0: timer@f0010000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			usart0: serial@f001c000 {
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/at91-kizboxmini.dts b/arch/arm/boot/dts/at91-kizboxmini.dts
index fe1bc0a59a98..15b0746e44e2 100644
--- a/arch/arm/boot/dts/at91-kizboxmini.dts
+++ b/arch/arm/boot/dts/at91-kizboxmini.dts
@@ -34,6 +34,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@f8008000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			usart0: serial@f801c000 {
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/at91-linea.dtsi b/arch/arm/boot/dts/at91-linea.dtsi
index 87e5090fb4c4..c7b964e25321 100644
--- a/arch/arm/boot/dts/at91-linea.dtsi
+++ b/arch/arm/boot/dts/at91-linea.dtsi
@@ -27,6 +27,18 @@
 	clock-frequency = <12000000>;
 };
 
+&tcb0 {
+	timer@0 {
+		compatible = "atmel,tcb-timer";
+		reg = <0>;
+	};
+
+	timer@1 {
+		compatible = "atmel,tcb-timer";
+		reg = <1>;
+	};
+};
+
 &i2c0 {
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/at91-natte.dtsi b/arch/arm/boot/dts/at91-natte.dtsi
new file mode 100644
index 000000000000..49f0a0c46cde
--- /dev/null
+++ b/arch/arm/boot/dts/at91-natte.dtsi
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * at91-natte.dts - Device Tree include file for the Natte board
+ *
+ * Copyright (C) 2017 Axentia Technologies AB
+ *
+ * Author: Peter Rosin <peda@axentia.se>
+ */
+
+/ {
+	mux: mux-controller {
+		compatible = "gpio-mux";
+		#mux-control-cells = <0>;
+
+		mux-gpios = <&ioexp 0 GPIO_ACTIVE_HIGH>,
+			    <&ioexp 1 GPIO_ACTIVE_HIGH>,
+			    <&ioexp 2 GPIO_ACTIVE_HIGH>;
+	};
+
+	batntc-mux {
+		compatible = "io-channel-mux";
+		io-channels = <&adc 5>;
+		io-channel-names = "parent";
+		mux-controls = <&mux>;
+
+		channels =
+			"batntc0", "batntc1", "batntc2", "batntc3",
+			"batntc4", "batntc5", "batntc6", "batntc7";
+	};
+
+	batv-mux {
+		compatible = "io-channel-mux";
+		io-channels = <&adc 6>;
+		io-channel-names = "parent";
+		mux-controls = <&mux>;
+
+		channels =
+			"batv0", "batv1", "batv2", "batv3",
+			"batv4", "batv5", "batv6", "batv7";
+	};
+
+	iout-mux {
+		compatible = "io-channel-mux";
+		io-channels = <&adc 7>;
+		io-channel-names = "parent";
+		mux-controls = <&mux>;
+
+		channels =
+			"iout0", "iout1", "iout2", "iout3",
+			"iout4", "iout5", "iout6", "iout7";
+	};
+
+	i2c-mux {
+		compatible = "i2c-mux";
+		mux-locked;
+		i2c-parent = <&i2c0>;
+		mux-controls = <&mux>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		i2c@0 {
+			reg = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			charger@9 {
+				compatible = "ti,bq24735";
+				reg = <0x9>;
+
+				ti,charge-current = <2000>;
+				ti,charge-voltage = <16800>;
+
+				poll-interval = <20000>;
+			};
+		};
+
+		i2c@1 {
+			reg = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			charger@9 {
+				compatible = "ti,bq24735";
+				reg = <0x9>;
+
+				ti,charge-current = <2000>;
+				ti,charge-voltage = <16800>;
+
+				poll-interval = <20000>;
+			};
+		};
+
+		i2c@2 {
+			reg = <2>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			charger@9 {
+				compatible = "ti,bq24735";
+				reg = <0x9>;
+
+				ti,charge-current = <2000>;
+				ti,charge-voltage = <16800>;
+
+				poll-interval = <20000>;
+			};
+		};
+
+		i2c@3 {
+			reg = <3>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			charger@9 {
+				compatible = "ti,bq24735";
+				reg = <0x9>;
+
+				ti,charge-current = <2000>;
+				ti,charge-voltage = <16800>;
+
+				poll-interval = <20000>;
+			};
+		};
+
+		i2c@4 {
+			reg = <4>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			charger@9 {
+				compatible = "ti,bq24735";
+				reg = <0x9>;
+
+				ti,charge-current = <2000>;
+				ti,charge-voltage = <16800>;
+
+				poll-interval = <20000>;
+			};
+		};
+
+		i2c@5 {
+			reg = <5>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			charger@9 {
+				compatible = "ti,bq24735";
+				reg = <0x9>;
+
+				ti,charge-current = <2000>;
+				ti,charge-voltage = <16800>;
+
+				poll-interval = <20000>;
+			};
+		};
+
+		i2c@6 {
+			reg = <6>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			charger@9 {
+				compatible = "ti,bq24735";
+				reg = <0x9>;
+
+				ti,charge-current = <2000>;
+				ti,charge-voltage = <16800>;
+
+				poll-interval = <20000>;
+			};
+		};
+
+		i2c@7 {
+			reg = <7>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			charger@9 {
+				compatible = "ti,bq24735";
+				reg = <0x9>;
+
+				ti,charge-current = <2000>;
+				ti,charge-voltage = <16800>;
+
+				poll-interval = <20000>;
+			};
+		};
+	};
+};
+
+&i2c0 {
+	status = "okay";
+
+	ioexp: ioexp@20 {
+		#gpio-cells = <2>;
+		compatible = "semtech,sx1502q";
+		reg = <0x20>;
+
+		gpio-controller;
+		ngpios = <8>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&gpio3_cfg_pins>;
+
+		gpio3_cfg_pins: gpio3_cfg {
+			pins = "gpio3";
+			bias-pull-up;
+		};
+	};
+
+	adc: adc@48 {
+		compatible = "ti,ads1015";
+		reg = <0x48>;
+		#io-channel-cells = <1>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		channel@4 {
+			reg = <4>;
+			ti,gain = <2>;
+			ti,datarate = <4>;
+		};
+
+		channel@5 {
+			reg = <5>;
+			ti,gain = <2>;
+			ti,datarate = <4>;
+		};
+
+		channel@6 {
+			reg = <6>;
+			ti,gain = <1>;
+			ti,datarate = <4>;
+		};
+
+		channel@7 {
+			reg = <7>;
+			ti,gain = <3>;
+			ti,datarate = <4>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/at91-nattis-2-natte-2.dts b/arch/arm/boot/dts/at91-nattis-2-natte-2.dts
new file mode 100644
index 000000000000..3ea1d26e1c68
--- /dev/null
+++ b/arch/arm/boot/dts/at91-nattis-2-natte-2.dts
@@ -0,0 +1,258 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * at91-nattis-2-natte-2.dts - Device Tree file for the Linea/Nattis board
+ *
+ * Copyright (C) 2017 Axentia Technologies AB
+ *
+ * Author: Peter Rosin <peda@axentia.se>
+ */
+/dts-v1/;
+#include "at91-linea.dtsi"
+#include "sama5d3_lcd.dtsi"
+#include "at91-natte.dtsi"
+
+/ {
+	model = "Axentia Linea-Nattis v2 Natte v2";
+	compatible = "axentia,nattis-2", "axentia,natte-2", "axentia,linea",
+		     "atmel,sama5d31", "atmel,sama5d3", "atmel,sama5";
+
+	ahb {
+		apb {
+			pinctrl@fffff200 {
+				nattis {
+					pinctrl_usba_vbus: usba_vbus {
+						atmel,pins =
+							<AT91_PIOD 28
+							 AT91_PERIPH_GPIO
+							 AT91_PINCTRL_DEGLITCH>;
+					};
+
+					pinctrl_mmc0_cd: mmc0_cd {
+						atmel,pins =
+							<AT91_PIOD 5
+							 AT91_PERIPH_GPIO
+							 AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
+
+					pinctrl_lcd_prlud0: lcd_prlud0 {
+						atmel,pins =
+							<AT91_PIOA 21
+							 AT91_PERIPH_GPIO
+							 AT91_PINCTRL_OUTPUT_VAL(0)>;
+					};
+
+					pinctrl_lcd_hipow0: lcd_hipow0 {
+						atmel,pins =
+							<AT91_PIOA 23
+							 AT91_PERIPH_GPIO
+							 AT91_PINCTRL_OUTPUT_VAL(0)>;
+					};
+				};
+			};
+
+			watchdog@fffffe40 {
+				status = "okay";
+			};
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		wakeup {
+			label = "Wakeup";
+			linux,code = <10>;
+			gpio-key,wakeup;
+			gpios = <&pioB 27 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	panel_reg: panel-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "panel-VCC";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	bl_reg: backlight-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "panel-VDD";
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+	};
+
+	panel_bl: backlight {
+		compatible = "pwm-backlight";
+		pwms = <&hlcdc_pwm 0 100000 0>;
+
+		brightness-levels = < 0  1  2  3  4  5  6  7  8  9
+				     10 11 12 13 14 15 16 17 18 19
+				     20 21 22 23 24 25 26 27 28 29
+				     30 31 32 33 34 35 36 37 38 39
+				     40 41 42 43 44 45 46 47 48 49
+				     50 51 52 53 54 55 56 57 58 59
+				     60 61 62 63 64 65 66 67 68 69
+				     70 71 72 73 74 75 76 77 78 79
+				     80 81 82 83 84 85 86 87 88 89
+				     90 91 92 93 94 95 96 97 98 99
+				    100>;
+		default-brightness-level = <40>;
+
+		power-supply = <&bl_reg>;
+		enable-gpios = <&pioA 20 GPIO_ACTIVE_HIGH>;
+	};
+
+	panel: panel {
+		compatible = "sharp,lq150x1lg11";
+		backlight = <&panel_bl>;
+		power-supply = <&panel_reg>;
+
+		port {
+			panel_input: endpoint {
+				remote-endpoint = <&hlcdc_panel_output>;
+			};
+		};
+	};
+
+	sound {
+		compatible = "simple-audio-card";
+
+		simple-audio-card,name = "nattis-tfa9879";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,bitclock-master = <&cpu_dai>;
+		simple-audio-card,frame-master = <&cpu_dai>;
+		simple-audio-card,widgets = "Line", "Line Out Jack";
+		simple-audio-card,routing = "Line Out Jack", "LINEOUT";
+
+		cpu_dai: simple-audio-card,cpu {
+			sound-dai = <&ssc0>;
+		};
+
+		simple-audio-card,codec {
+			sound-dai = <&amp>;
+		};
+	};
+};
+
+&i2c0 {
+	status = "okay";
+
+	clock-frequency = <100000>;
+
+	temp@18 {
+		compatible = "nxp,se97b", "jedec,jc-42.4-temp";
+		reg = <0x18>;
+		smbus-timeout-disable;
+	};
+
+	eeprom@50 {
+		compatible = "nxp,24c02";
+		reg = <0x50>;
+		pagesize = <16>;
+	};
+
+	amp: amplifier@6c {
+		 compatible = "nxp,tfa9879";
+		 reg = <0x6c>;
+		 #sound-dai-cells = <0>;
+	};
+};
+
+&ssc0 {
+	status = "okay";
+
+	atmel,clk-from-rk-pin;
+	#sound-dai-cells = <0>;
+};
+
+&hlcdc {
+	status = "okay";
+
+	hlcdc-display-controller {
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_lcd_base
+			     &pinctrl_lcd_rgb565
+			     &pinctrl_lcd_prlud0
+			     &pinctrl_lcd_hipow0>;
+
+		port@0 {
+			hlcdc_panel_output: endpoint {
+				remote-endpoint = <&panel_input>;
+			};
+		};
+	};
+};
+
+&mmc0 {
+	status = "okay";
+
+	pinctrl-0 = <&pinctrl_mmc0_clk_cmd_dat0
+		     &pinctrl_mmc0_dat1_3
+		     &pinctrl_mmc0_cd>;
+
+	slot@0 {
+		reg = <0>;
+		bus-width = <4>;
+		cd-gpios = <&pioD 5 GPIO_ACTIVE_HIGH>;
+	};
+};
+
+&usart0 {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usart0>;
+	atmel,use-dma-rx;
+};
+
+&nand {
+	partitions {
+		compatible = "fixed-partitions";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		at91bootstrap@0 {
+			label = "at91bootstrap";
+			reg = <0x0 0x40000>;
+		};
+
+		bootloader@40000 {
+			label = "bootloader";
+			reg = <0x40000 0x80000>;
+		};
+
+		bootloaderenv@c0000 {
+			label = "bootloader env";
+			reg = <0xc0000 0xc0000>;
+		};
+
+		dtb@180000 {
+			label = "device tree";
+			reg = <0x180000 0x80000>;
+		};
+
+		kernel@200000 {
+			label = "kernel";
+			reg = <0x200000 0x600000>;
+		};
+
+		rootfs@800000 {
+			label = "rootfs";
+			reg = <0x800000 0x0f800000>;
+		};
+	};
+};
+
+&dbgu {
+	status = "okay";
+
+	atmel,use-dma-rx;
+};
+
+&usb0 {
+	status = "okay";
+
+	atmel,vbus-gpio = <&pioD 28 GPIO_ACTIVE_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usba_vbus>;
+};
diff --git a/arch/arm/boot/dts/at91-qil_a9260.dts b/arch/arm/boot/dts/at91-qil_a9260.dts
index f46352790a41..72e9148ca096 100644
--- a/arch/arm/boot/dts/at91-qil_a9260.dts
+++ b/arch/arm/boot/dts/at91-qil_a9260.dts
@@ -31,6 +31,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			usb1: gadget@fffa4000 {
 				atmel,vbus-gpio = <&pioC 5 GPIO_ACTIVE_HIGH>;
 				status = "okay";
diff --git a/arch/arm/boot/dts/at91-sam9_l9260.dts b/arch/arm/boot/dts/at91-sam9_l9260.dts
index 171243ca4f2f..70cb36f7a9d7 100644
--- a/arch/arm/boot/dts/at91-sam9_l9260.dts
+++ b/arch/arm/boot/dts/at91-sam9_l9260.dts
@@ -32,6 +32,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			mmc0: mmc@fffa8000 {
 				pinctrl-0 = <
 					&pinctrl_board_mmc0
diff --git a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts
index 6d87b4eb6c41..e86e0c00eb6b 100644
--- a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts
@@ -119,6 +119,18 @@
 				status = "okay";
 			};
 
+			tcb0: timer@f800c000 {
+				timer0: timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer1: timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			uart1: serial@f8020000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_uart1_default>;
diff --git a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
new file mode 100644
index 000000000000..e603a267bdf1
--- /dev/null
+++ b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
@@ -0,0 +1,413 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR X11)
+/*
+ * at91-sama5d2_ptc_ek.dts - Device Tree file for SAMA5D2 PTC EK board
+ *
+ *  Copyright (C) 2017 Microchip/Atmel,
+ *		  2017 Wenyou Yang <wenyou.yang@microchip.com>
+ *		  2017 Ludovic Desroches <ludovic.desroches@microchip.com>
+ */
+/dts-v1/;
+#include "sama5d2.dtsi"
+#include "sama5d2-pinfunc.h"
+#include <dt-bindings/mfd/atmel-flexcom.h>
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	model = "Atmel SAMA5D2 PTC EK";
+	compatible = "atmel,sama5d2-ptc_ek", "atmel,sama5d2", "atmel,sama5";
+
+	aliases {
+		serial0 = &uart0;
+		i2c0	= &i2c0;
+		i2c1	= &i2c1;
+		i2c2	= &i2c2;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	clocks {
+		slow_xtal {
+			clock-frequency = <32768>;
+		};
+
+		main_xtal {
+			clock-frequency = <24000000>;
+		};
+	};
+
+	ahb {
+		usb0: gadget@300000 {
+			atmel,vbus-gpio = <&pioA PIN_PA27 GPIO_ACTIVE_HIGH>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usba_vbus>;
+			status = "okay";
+		};
+
+		usb1: ohci@400000 {
+			num-ports = <3>;
+			atmel,vbus-gpio = <0
+					   &pioA PIN_PB12 GPIO_ACTIVE_HIGH
+					   0
+					  >;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usb_default>;
+			status = "okay";
+		};
+
+		usb2: ehci@500000 {
+			status = "okay";
+		};
+
+		ebi: ebi@10000000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_nand_default>;
+			status = "okay"; /* conflicts with sdmmc1 and qspi0 */
+
+			nand_controller: nand-controller {
+				status = "okay";
+
+				nand@3 {
+					reg = <0x3 0x0 0x2>;
+					atmel,rb = <0>;
+					nand-bus-width = <8>;
+					nand-ecc-mode = "hw";
+					nand-on-flash-bbt;
+					label = "atmel_nand";
+
+					partitions {
+						compatible = "fixed-partitions";
+						#address-cells = <1>;
+						#size-cells = <1>;
+
+						at91bootstrap@0 {
+							label = "bootstrap";
+							reg = <0x0 0x40000>;
+						};
+
+						bootloader@40000 {
+							label = "bootloader";
+							reg = <0x40000 0xc0000>;
+						};
+
+						bootloaderenv@0x100000 {
+							label = "bootloader env";
+							reg = <0x100000 0x40000>;
+						};
+
+						bootloaderenvred@0x140000 {
+							label = "bootloader env redundant";
+							reg = <0x140000 0x40000>;
+						};
+
+						dtb@180000 {
+							label = "device tree";
+							reg = <0x180000 0x80000>;
+						};
+
+						kernel@200000 {
+							label = "kernel";
+							reg = <0x200000 0x600000>;
+						};
+
+						rootfs@800000 {
+							label = "rootfs";
+							reg = <0x800000 0x1f800000>;
+						};
+					};
+				};
+			};
+		};
+
+		sdmmc0: sdio-host@a0000000 {
+			bus-width = <8>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_sdmmc0_default>;
+			non-removable;
+			mmc-ddr-1_8v;
+			status = "okay";
+		};
+
+		apb {
+			spi0: spi@f8000000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_spi0_default>;
+				status = "okay";
+			};
+
+			macb0: ethernet@f8008000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_macb0_default &pinctrl_macb0_phy_irq>;
+				phy-mode = "rmii";
+				status = "okay";
+
+				ethernet-phy@1 {
+					reg = <0x1>;
+					interrupt-parent = <&pioA>;
+					interrupts = <56 IRQ_TYPE_LEVEL_LOW>;
+				};
+			};
+
+			tcb0: timer@f800c000 {
+				timer0: timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer1: timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
+			uart0: serial@f801c000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_uart0_default>;
+				atmel,use-dma-rx;
+				atmel,use-dma-tx;
+				status = "okay";
+			};
+
+			uart2: serial@f8024000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_uart2_default>;
+				atmel,use-dma-rx;
+				atmel,use-dma-tx;
+				status = "okay";
+			};
+
+			i2c0: i2c@f8028000 {
+				dmas = <0>, <0>;
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_i2c0_default>;
+				status = "okay";
+			};
+
+			flx0: flexcom@f8034000 {
+				atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_TWI>;
+				status = "okay";
+
+				i2c2: i2c@600 {
+					compatible = "atmel,sama5d2-i2c";
+					reg = <0x600 0x200>;
+					interrupts = <19 IRQ_TYPE_LEVEL_HIGH 7>;
+					dmas = <0>, <0>;
+					dma-names = "tx", "rx";
+					#address-cells = <1>;
+					#size-cells = <0>;
+					clocks = <&flx0_clk>;
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_flx0_default>;
+					atmel,fifo-size = <16>;
+					status = "okay";
+				};
+			};
+
+			shdwc@f8048010 {
+				atmel,shdwc-debouncer = <976>;
+
+				input@0 {
+					reg = <0>;
+					atmel,wakeup-type = "low";
+				};
+			};
+
+			watchdog@f8048040 {
+				status = "okay";
+			};
+
+			spi1: spi@fc000000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_spi1_default>;
+				status = "okay";
+			};
+
+			i2c1: i2c@fc028000 {
+				dmas = <0>, <0>;
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_i2c1_default>;
+				status = "okay";
+
+				at24@50 {
+					compatible = "24c02";
+					reg = <0x50>;
+					pagesize = <8>;
+				};
+			};
+
+			pinctrl@fc038000 {
+				pinctrl_flx0_default: flx0_default {
+					pinmux = <PIN_PB28__FLEXCOM0_IO0>,
+						 <PIN_PB29__FLEXCOM0_IO1>;
+					bias-disable;
+				};
+
+				pinctrl_i2c0_default: i2c0_default {
+					pinmux = <PIN_PD21__TWD0>,
+						 <PIN_PD22__TWCK0>;
+					bias-disable;
+				};
+
+				pinctrl_i2c1_default: i2c1_default {
+					pinmux = <PIN_PC6__TWD1>,
+						 <PIN_PC7__TWCK1>;
+					bias-disable;
+				};
+
+				pinctrl_key_gpio_default: key_gpio_default {
+					pinmux = <PIN_PA10__GPIO>;
+					bias-pull-up;
+				};
+
+				pinctrl_led_gpio_default: led_gpio_default {
+					pinmux = <PIN_PB6__GPIO>,
+						 <PIN_PB8__GPIO>,
+						 <PIN_PB10__GPIO>;
+					bias-pull-up;
+				};
+
+				pinctrl_macb0_default: macb0_default {
+					pinmux = <PIN_PB14__GTXCK>,
+						 <PIN_PB15__GTXEN>,
+						 <PIN_PB16__GRXDV>,
+						 <PIN_PB17__GRXER>,
+						 <PIN_PB18__GRX0>,
+						 <PIN_PB19__GRX1>,
+						 <PIN_PB20__GTX0>,
+						 <PIN_PB21__GTX1>,
+						 <PIN_PB22__GMDC>,
+						 <PIN_PB23__GMDIO>;
+					bias-disable;
+				};
+
+				pinctrl_macb0_phy_irq: macb0_phy_irq {
+					pinmux = <PIN_PB24__GPIO>;
+					bias-disable;
+				};
+
+				pinctrl_nand_default: nand_default {
+					re_we_data {
+						pinmux = <PIN_PA22__D0>,
+							 <PIN_PA23__D1>,
+							 <PIN_PA24__D2>,
+							 <PIN_PA25__D3>,
+							 <PIN_PA26__D4>,
+							 <PIN_PA27__D5>,
+							 <PIN_PA28__D6>,
+							 <PIN_PA29__D7>,
+							 <PIN_PA30__NWE_NANDWE>,
+							 <PIN_PB2__NRD_NANDOE>;
+						bias-pull-up;
+					};
+
+					ale_cle_rdy_cs {
+						pinmux = <PIN_PB0__A21_NANDALE>,
+							 <PIN_PB1__A22_NANDCLE>,
+							 <PIN_PC8__NANDRDY>,
+							 <PIN_PA31__NCS3>;
+						bias-pull-up;
+					};
+				};
+
+				pinctrl_sdmmc0_default: sdmmc0_default {
+					cmd_data {
+						pinmux = <PIN_PA1__SDMMC0_CMD>,
+							 <PIN_PA2__SDMMC0_DAT0>,
+							 <PIN_PA3__SDMMC0_DAT1>,
+							 <PIN_PA4__SDMMC0_DAT2>,
+							 <PIN_PA5__SDMMC0_DAT3>,
+							 <PIN_PA6__SDMMC0_DAT4>,
+							 <PIN_PA7__SDMMC0_DAT5>,
+							 <PIN_PA8__SDMMC0_DAT6>,
+							 <PIN_PA9__SDMMC0_DAT7>;
+						bias-pull-up;
+					};
+
+					ck_cd_vddsel {
+						pinmux = <PIN_PA0__SDMMC0_CK>,
+							 <PIN_PA11__SDMMC0_VDDSEL>,
+							 <PIN_PA13__SDMMC0_CD>;
+						bias-disable;
+					};
+				};
+
+				pinctrl_spi0_default: spi0_default {
+					pinmux = <PIN_PA14__SPI0_SPCK>,
+						 <PIN_PA15__SPI0_MOSI>,
+						 <PIN_PA16__SPI0_MISO>,
+						 <PIN_PA17__SPI0_NPCS0>;
+					bias-disable;
+				};
+
+				pinctrl_spi1_default: spi1_default {
+					pinmux = <PIN_PC1__SPI1_SPCK>,
+						 <PIN_PC2__SPI1_MOSI>,
+						 <PIN_PC3__SPI1_MISO>,
+						 <PIN_PC4__SPI1_NPCS0>;
+					bias-disable;
+				};
+
+				pinctrl_uart0_default: uart0_default {
+					pinmux = <PIN_PB26__URXD0>,
+						 <PIN_PB27__UTXD0>;
+					bias-disable;
+				};
+
+				pinctrl_uart2_default: uart2_default {
+					pinmux = <PIN_PD23__URXD2>,
+						 <PIN_PD24__UTXD2>;
+					bias-disable;
+				};
+
+				pinctrl_usb_default: usb_default {
+					pinmux = <PIN_PB12__GPIO>;
+					bias-disable;
+				};
+
+				pinctrl_usba_vbus: usba_vbus {
+					pinmux = <PIN_PB11__GPIO>;
+					bias-disable;
+				};
+
+			};
+
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_key_gpio_default>;
+
+		bp1 {
+			label = "PB_USER";
+			gpios = <&pioA PIN_PA10 GPIO_ACTIVE_LOW>;
+			linux,code = <0x104>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_led_gpio_default>;
+		status = "okay";
+
+		red {
+			label = "red";
+			gpios = <&pioA PIN_PB10 GPIO_ACTIVE_HIGH>;
+		};
+
+		green {
+			label = "green";
+			gpios = <&pioA PIN_PB8 GPIO_ACTIVE_HIGH>;
+		};
+
+		blue {
+			label = "blue";
+			gpios = <&pioA PIN_PB6 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
index 56de21de2779..e4bbb7e0f793 100644
--- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
@@ -133,6 +133,18 @@
 				};
 			};
 
+			tcb0: timer@f800c000 {
+				timer0: timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer1: timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			pdmic@f8018000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_pdmic_default>;
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
index 40879aded680..02c1d2958d78 100644
--- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -65,6 +65,18 @@
 				status = "okay";
 			};
 
+			tcb0: timer@f0010000 {
+				timer0: timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer1: timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			i2c0: i2c@f0014000 {
 				pinctrl-0 = <&pinctrl_i2c0_pu>;
 				status = "okay";
diff --git a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi
index b813fdfa2842..d3e79fbf1944 100644
--- a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi
+++ b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi
@@ -89,6 +89,18 @@
 				};
 			};
 
+			tcb2: timer@fc024000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			adc0: adc@fc034000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <
diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
index 29ab17a97f9a..4b7c762d5f22 100644
--- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
@@ -130,6 +130,18 @@
 				status = "okay";
 			};
 
+			tcb2: timer@fc024000 {
+				timer0: timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer1: timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			adc0: adc@fc034000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <
diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts
index 5b7ee92e32a7..7887a7160a54 100644
--- a/arch/arm/boot/dts/at91-sama5d4ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d4ek.dts
@@ -174,6 +174,18 @@
 				status = "okay";
 			};
 
+			tcb2: timer@fc024000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			watchdog@fc068640 {
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/at91-tse850-3.dts b/arch/arm/boot/dts/at91-tse850-3.dts
index 5f29010cdbd8..9b82cc8843e1 100644
--- a/arch/arm/boot/dts/at91-tse850-3.dts
+++ b/arch/arm/boot/dts/at91-tse850-3.dts
@@ -221,6 +221,7 @@
 	jc42@18 {
 		compatible = "nxp,se97b", "jedec,jc-42.4-temp";
 		reg = <0x18>;
+		smbus-timeout-disable;
 	};
 
 	dpot: mcp4651-104@28 {
diff --git a/arch/arm/boot/dts/at91-vinco.dts b/arch/arm/boot/dts/at91-vinco.dts
index 9f6005708ea8..1be9889a2b3a 100644
--- a/arch/arm/boot/dts/at91-vinco.dts
+++ b/arch/arm/boot/dts/at91-vinco.dts
@@ -151,6 +151,18 @@
 				status = "okay";
 			};
 
+			tcb2: timer@fc024000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			macb1: ethernet@fc028000 {
 				phy-mode = "rmii";
 				status = "okay";
diff --git a/arch/arm/boot/dts/at91rm9200.dtsi b/arch/arm/boot/dts/at91rm9200.dtsi
index da622bf45b4a..ba61893a02a0 100644
--- a/arch/arm/boot/dts/at91rm9200.dtsi
+++ b/arch/arm/boot/dts/at91rm9200.dtsi
@@ -375,7 +375,9 @@
 			};
 
 			tcb0: timer@fffa0000 {
-				compatible = "atmel,at91rm9200-tcb";
+				compatible = "atmel,at91rm9200-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xfffa0000 0x100>;
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0
 					      18 IRQ_TYPE_LEVEL_HIGH 0
@@ -385,7 +387,9 @@
 			};
 
 			tcb1: timer@fffa4000 {
-				compatible = "atmel,at91rm9200-tcb";
+				compatible = "atmel,at91rm9200-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xfffa4000 0x100>;
 				interrupts = <20 IRQ_TYPE_LEVEL_HIGH 0
 					      21 IRQ_TYPE_LEVEL_HIGH 0
diff --git a/arch/arm/boot/dts/at91rm9200ek.dts b/arch/arm/boot/dts/at91rm9200ek.dts
index 33192d0cefee..81aaf8151c76 100644
--- a/arch/arm/boot/dts/at91rm9200ek.dts
+++ b/arch/arm/boot/dts/at91rm9200ek.dts
@@ -32,6 +32,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			usb1: gadget@fffb0000 {
 				atmel,vbus-gpio = <&pioD 4 GPIO_ACTIVE_HIGH>;
 				atmel,pullup-gpio = <&pioD 5 GPIO_ACTIVE_HIGH>;
diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi
index bc655e7332d6..655f06cd716a 100644
--- a/arch/arm/boot/dts/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/at91sam9260.dtsi
@@ -386,7 +386,9 @@
 			};
 
 			tcb0: timer@fffa0000 {
-				compatible = "atmel,at91rm9200-tcb";
+				compatible = "atmel,at91rm9200-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xfffa0000 0x100>;
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0
 					      18 IRQ_TYPE_LEVEL_HIGH 0
@@ -396,7 +398,9 @@
 			};
 
 			tcb1: timer@fffdc000 {
-				compatible = "atmel,at91rm9200-tcb";
+				compatible = "atmel,at91rm9200-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xfffdc000 0x100>;
 				interrupts = <26 IRQ_TYPE_LEVEL_HIGH 0
 					      27 IRQ_TYPE_LEVEL_HIGH 0
diff --git a/arch/arm/boot/dts/at91sam9260ek.dts b/arch/arm/boot/dts/at91sam9260ek.dts
index b2578feceb08..e16c706d91ef 100644
--- a/arch/arm/boot/dts/at91sam9260ek.dts
+++ b/arch/arm/boot/dts/at91sam9260ek.dts
@@ -69,6 +69,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			usb1: gadget@fffa4000 {
 				atmel,vbus-gpio = <&pioC 5 GPIO_ACTIVE_HIGH>;
 				status = "okay";
diff --git a/arch/arm/boot/dts/at91sam9261.dtsi b/arch/arm/boot/dts/at91sam9261.dtsi
index 66876019101d..ddfc63b8fd4e 100644
--- a/arch/arm/boot/dts/at91sam9261.dtsi
+++ b/arch/arm/boot/dts/at91sam9261.dtsi
@@ -80,7 +80,7 @@
 			status = "disabled";
 		};
 
-		fb0: fb@0x00600000 {
+		fb0: fb@600000 {
 			compatible = "atmel,at91sam9261-lcdc";
 			reg = <0x00600000 0x1000>;
 			interrupts = <21 IRQ_TYPE_LEVEL_HIGH 3>;
@@ -125,7 +125,9 @@
 			ranges;
 
 			tcb0: timer@fffa0000 {
-				compatible = "atmel,at91rm9200-tcb";
+				compatible = "atmel,at91rm9200-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xfffa0000 0x100>;
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0>,
 					     <18 IRQ_TYPE_LEVEL_HIGH 0>,
diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts
index 960d6940ebf6..a29fc0494076 100644
--- a/arch/arm/boot/dts/at91sam9261ek.dts
+++ b/arch/arm/boot/dts/at91sam9261ek.dts
@@ -15,6 +15,14 @@
 	chosen {
 		bootargs = "rootfstype=ubifs ubi.mtd=5 root=ubi0:rootfs rw";
 		stdout-path = "serial0:115200n8";
+
+		clocksource {
+			timer = <&timer0>;
+		};
+
+		clockevent {
+			timer = <&timer1>;
+		};
 	};
 
 	memory {
@@ -36,7 +44,7 @@
 			status = "okay";
 		};
 
-		fb0: fb@0x00600000 {
+		fb0: fb@600000 {
 			display = <&display0>;
 			atmel,power-control-gpio = <&pioA 12 GPIO_ACTIVE_LOW>;
 			status = "okay";
@@ -125,6 +133,18 @@
 		};
 
 		apb {
+			tcb0: timer@fffa0000 {
+				timer0: timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer1: timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			usb1: gadget@fffa4000 {
 				atmel,vbus-gpio = <&pioB 29 GPIO_ACTIVE_HIGH>;
 				status = "okay";
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index e54f14d36b6f..f2405671e3bd 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -389,7 +389,9 @@
 			};
 
 			tcb0: timer@fff7c000 {
-				compatible = "atmel,at91rm9200-tcb";
+				compatible = "atmel,at91rm9200-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xfff7c000 0x100>;
 				interrupts = <19 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb_clk>, <&slow_xtal>;
@@ -999,7 +1001,7 @@
 			};
 		};
 
-		fb0: fb@0x00700000 {
+		fb0: fb@700000 {
 			compatible = "atmel,at91sam9263-lcdc";
 			reg = <0x00700000 0x1000>;
 			interrupts = <26 IRQ_TYPE_LEVEL_HIGH 3>;
diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts
index 5a2e1af793f5..e9a7c70830a8 100644
--- a/arch/arm/boot/dts/at91sam9263ek.dts
+++ b/arch/arm/boot/dts/at91sam9263ek.dts
@@ -37,6 +37,18 @@
 				status = "okay";
 			};
 
+			tcb0: timer@fff7c000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			usart0: serial@fff8c000 {
 				pinctrl-0 = <
 					&pinctrl_usart0
@@ -95,7 +107,7 @@
 			};
 		};
 
-		fb0: fb@0x00700000 {
+		fb0: fb@700000 {
 			display = <&display0>;
 			status = "okay";
 
diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
index ac9a1511e239..50561b7b7939 100644
--- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
+++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
@@ -51,6 +51,18 @@
 				status = "okay";
 			};
 
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			usart0: serial@fffb0000 {
 				pinctrl-0 =
 					<&pinctrl_usart0
diff --git a/arch/arm/boot/dts/at91sam9g25ek.dts b/arch/arm/boot/dts/at91sam9g25ek.dts
index 91a71774472e..31fecc2cdaf9 100644
--- a/arch/arm/boot/dts/at91sam9g25ek.dts
+++ b/arch/arm/boot/dts/at91sam9g25ek.dts
@@ -25,7 +25,7 @@
 			};
 
 			i2c0: i2c@f8010000 {
-				ov2640: camera@0x30 {
+				ov2640: camera@30 {
 					compatible = "ovti,ov2640";
 					reg = <0x30>;
 					pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index 2b127ca7aaa0..3a30eec7f508 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -415,7 +415,9 @@
 			};
 
 			tcb0: timer@fff7c000 {
-				compatible = "atmel,at91rm9200-tcb";
+				compatible = "atmel,at91rm9200-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xfff7c000 0x100>;
 				interrupts = <18 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb0_clk>, <&tcb0_clk>, <&tcb0_clk>, <&clk32k>;
@@ -423,7 +425,9 @@
 			};
 
 			tcb1: timer@fffd4000 {
-				compatible = "atmel,at91rm9200-tcb";
+				compatible = "atmel,at91rm9200-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xfffd4000 0x100>;
 				interrupts = <18 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb0_clk>, <&tcb0_clk>, <&tcb0_clk>, <&clk32k>;
@@ -1302,7 +1306,7 @@
 			};
 		};
 
-		fb0: fb@0x00500000 {
+		fb0: fb@500000 {
 			compatible = "atmel,at91sam9g45-lcdc";
 			reg = <0x00500000 0x1000>;
 			interrupts = <23 IRQ_TYPE_LEVEL_HIGH 3>;
diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts
index e922552a04cb..25888339d8de 100644
--- a/arch/arm/boot/dts/at91sam9m10g45ek.dts
+++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts
@@ -39,6 +39,18 @@
 				status = "okay";
 			};
 
+			tcb0: timer@fff7c000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			usart1: serial@fff90000 {
 				pinctrl-0 =
 					<&pinctrl_usart1
@@ -220,7 +232,7 @@
 			};
 		};
 
-		fb0: fb@0x00500000 {
+		fb0: fb@500000 {
 			display = <&display0>;
 			status = "okay";
 
diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi
index e0ac824e0785..4b62f4f963f6 100644
--- a/arch/arm/boot/dts/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/at91sam9n12.dtsi
@@ -446,7 +446,9 @@
 			};
 
 			tcb0: timer@f8008000 {
-				compatible = "atmel,at91sam9x5-tcb";
+				compatible = "atmel,at91sam9x5-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xf8008000 0x100>;
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb_clk>, <&clk32k>;
@@ -454,7 +456,9 @@
 			};
 
 			tcb1: timer@f800c000 {
-				compatible = "atmel,at91sam9x5-tcb";
+				compatible = "atmel,at91sam9x5-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xf800c000 0x100>;
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb_clk>, <&clk32k>;
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index 212562aedf5e..c43095c5cb5c 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -42,6 +42,18 @@
 				status = "okay";
 			};
 
+			tcb0: timer@f8008000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			i2c0: i2c@f8010000 {
 				status = "okay";
 
diff --git a/arch/arm/boot/dts/at91sam9rl.dtsi b/arch/arm/boot/dts/at91sam9rl.dtsi
index 52f0e9ef8f67..3cae687dccbd 100644
--- a/arch/arm/boot/dts/at91sam9rl.dtsi
+++ b/arch/arm/boot/dts/at91sam9rl.dtsi
@@ -124,7 +124,9 @@
 			ranges;
 
 			tcb0: timer@fffa0000 {
-				compatible = "atmel,at91rm9200-tcb";
+				compatible = "atmel,at91rm9200-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xfffa0000 0x100>;
 				interrupts = <16 IRQ_TYPE_LEVEL_HIGH 0>,
 					     <17 IRQ_TYPE_LEVEL_HIGH 0>,
diff --git a/arch/arm/boot/dts/at91sam9rlek.dts b/arch/arm/boot/dts/at91sam9rlek.dts
index ea6ed98960c9..4bde9f245e61 100644
--- a/arch/arm/boot/dts/at91sam9rlek.dts
+++ b/arch/arm/boot/dts/at91sam9rlek.dts
@@ -124,6 +124,18 @@
 		};
 
 		apb {
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			mmc0: mmc@fffa4000 {
 				pinctrl-0 = <
 					&pinctrl_board_mmc0
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index ad779a7dfefd..fee4fe51a97e 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -433,7 +433,9 @@
 			};
 
 			tcb0: timer@f8008000 {
-				compatible = "atmel,at91sam9x5-tcb";
+				compatible = "atmel,at91sam9x5-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xf8008000 0x100>;
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb0_clk>, <&clk32k>;
@@ -441,7 +443,9 @@
 			};
 
 			tcb1: timer@f800c000 {
-				compatible = "atmel,at91sam9x5-tcb";
+				compatible = "atmel,at91sam9x5-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xf800c000 0x100>;
 				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb0_clk>, <&clk32k>;
diff --git a/arch/arm/boot/dts/at91sam9x5cm.dtsi b/arch/arm/boot/dts/at91sam9x5cm.dtsi
index bdeaa0b64a5b..4908ee07e628 100644
--- a/arch/arm/boot/dts/at91sam9x5cm.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5cm.dtsi
@@ -24,6 +24,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@f8008000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			pinctrl@fffff400 {
 				1wire_cm {
 					pinctrl_1wire_cm: 1wire_cm-0 {
diff --git a/arch/arm/boot/dts/axp81x.dtsi b/arch/arm/boot/dts/axp81x.dtsi
index 73b761f850c5..fd55b896afa1 100644
--- a/arch/arm/boot/dts/axp81x.dtsi
+++ b/arch/arm/boot/dts/axp81x.dtsi
@@ -48,6 +48,22 @@
 	interrupt-controller;
 	#interrupt-cells = <1>;
 
+	axp_gpio: axp-gpio {
+		compatible = "x-powers,axp813-gpio";
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		gpio0_ldo: gpio0-ldo {
+			pins = "GPIO0";
+			function = "ldo";
+		};
+
+		gpio1_ldo: gpio1-ldo {
+			pins = "GPIO1";
+			function = "ldo";
+		};
+	};
+
 	regulators {
 		/* Default work frequency for buck regulators */
 		x-powers,dcdc-freq = <3000>;
@@ -113,11 +129,15 @@
 		};
 
 		reg_ldo_io0: ldo-io0 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&gpio0_ldo>;
 			/* Disable by default to avoid conflicts with GPIO */
 			status = "disabled";
 		};
 
 		reg_ldo_io1: ldo-io1 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&gpio1_ldo>;
 			/* Disable by default to avoid conflicts with GPIO */
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index 528b9e3bc1da..dcc55aa84583 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -85,7 +85,7 @@
 		timer@20200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x20200 0x100>;
-			interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&periph_clk>;
 		};
 
@@ -93,7 +93,7 @@
 			compatible = "arm,cortex-a9-twd-timer";
 			reg = <0x20600 0x20>;
 			interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) |
-						  IRQ_TYPE_LEVEL_HIGH)>;
+						  IRQ_TYPE_EDGE_RISING)>;
 			clocks = <&periph_clk>;
 		};
 
diff --git a/arch/arm/boot/dts/bcm2835-rpi-a-plus.dts b/arch/arm/boot/dts/bcm2835-rpi-a-plus.dts
index f81ae0a10310..aa1fc7babfea 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-a-plus.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-a-plus.dts
@@ -10,12 +10,12 @@
 
 	leds {
 		act {
-			gpios = <&gpio 47 0>;
+			gpios = <&gpio 47 GPIO_ACTIVE_HIGH>;
 		};
 
 		pwr {
 			label = "PWR";
-			gpios = <&gpio 35 0>;
+			gpios = <&gpio 35 GPIO_ACTIVE_HIGH>;
 			default-state = "keep";
 			linux,default-trigger = "default-on";
 		};
diff --git a/arch/arm/boot/dts/bcm2835-rpi-a.dts b/arch/arm/boot/dts/bcm2835-rpi-a.dts
index 7a960a048204..425f6b0a5ef8 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-a.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-a.dts
@@ -10,7 +10,7 @@
 
 	leds {
 		act {
-			gpios = <&gpio 16 1>;
+			gpios = <&gpio 16 GPIO_ACTIVE_LOW>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/bcm2835-rpi-b-plus.dts b/arch/arm/boot/dts/bcm2835-rpi-b-plus.dts
index 0161a8483e39..effa195e7895 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-b-plus.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-b-plus.dts
@@ -11,12 +11,12 @@
 
 	leds {
 		act {
-			gpios = <&gpio 47 0>;
+			gpios = <&gpio 47 GPIO_ACTIVE_HIGH>;
 		};
 
 		pwr {
 			label = "PWR";
-			gpios = <&gpio 35 0>;
+			gpios = <&gpio 35 GPIO_ACTIVE_HIGH>;
 			default-state = "keep";
 			linux,default-trigger = "default-on";
 		};
diff --git a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts
index 4bc70efe43d6..772ec3b48231 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts
@@ -11,7 +11,7 @@
 
 	leds {
 		act {
-			gpios = <&gpio 16 1>;
+			gpios = <&gpio 16 GPIO_ACTIVE_LOW>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/bcm2835-rpi-b.dts b/arch/arm/boot/dts/bcm2835-rpi-b.dts
index cca4a75a5651..434483d6fc14 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-b.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-b.dts
@@ -11,7 +11,7 @@
 
 	leds {
 		act {
-			gpios = <&gpio 16 1>;
+			gpios = <&gpio 16 GPIO_ACTIVE_LOW>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/bcm2836-rpi-2-b.dts b/arch/arm/boot/dts/bcm2836-rpi-2-b.dts
index 6669355fd655..5c339adabdf0 100644
--- a/arch/arm/boot/dts/bcm2836-rpi-2-b.dts
+++ b/arch/arm/boot/dts/bcm2836-rpi-2-b.dts
@@ -15,12 +15,12 @@
 
 	leds {
 		act {
-			gpios = <&gpio 47 0>;
+			gpios = <&gpio 47 GPIO_ACTIVE_HIGH>;
 		};
 
 		pwr {
 			label = "PWR";
-			gpios = <&gpio 35 0>;
+			gpios = <&gpio 35 GPIO_ACTIVE_HIGH>;
 			default-state = "keep";
 			linux,default-trigger = "default-on";
 		};
diff --git a/arch/arm/boot/dts/bcm2836.dtsi b/arch/arm/boot/dts/bcm2836.dtsi
index 61e158003509..1dfd76442777 100644
--- a/arch/arm/boot/dts/bcm2836.dtsi
+++ b/arch/arm/boot/dts/bcm2836.dtsi
@@ -13,24 +13,24 @@
 			compatible = "brcm,bcm2836-l1-intc";
 			reg = <0x40000000 0x100>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 			interrupt-parent = <&local_intc>;
 		};
 
 		arm-pmu {
 			compatible = "arm,cortex-a7-pmu";
 			interrupt-parent = <&local_intc>;
-			interrupts = <9>;
+			interrupts = <9 IRQ_TYPE_LEVEL_HIGH>;
 		};
 	};
 
 	timer {
 		compatible = "arm,armv7-timer";
 		interrupt-parent = <&local_intc>;
-		interrupts = <0>, // PHYS_SECURE_PPI
-			     <1>, // PHYS_NONSECURE_PPI
-			     <3>, // VIRT_PPI
-			     <2>; // HYP_PPI
+		interrupts = <0 IRQ_TYPE_LEVEL_HIGH>, // PHYS_SECURE_PPI
+			     <1 IRQ_TYPE_LEVEL_HIGH>, // PHYS_NONSECURE_PPI
+			     <3 IRQ_TYPE_LEVEL_HIGH>, // VIRT_PPI
+			     <2 IRQ_TYPE_LEVEL_HIGH>; // HYP_PPI
 		always-on;
 	};
 
@@ -76,7 +76,7 @@
 	compatible = "brcm,bcm2836-armctrl-ic";
 	reg = <0x7e00b200 0x200>;
 	interrupt-parent = <&local_intc>;
-	interrupts = <8>;
+	interrupts = <8 IRQ_TYPE_LEVEL_HIGH>;
 };
 
 &cpu_thermal {
diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts
index a8844d033b3f..3e4ed7c5b0b3 100644
--- a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts
+++ b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts
@@ -20,7 +20,7 @@
 
 	leds {
 		act {
-			gpios = <&gpio 47 0>;
+			gpios = <&gpio 47 GPIO_ACTIVE_HIGH>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/bcm2837.dtsi b/arch/arm/boot/dts/bcm2837.dtsi
index bc1cca5cf43c..efa7d3387ab2 100644
--- a/arch/arm/boot/dts/bcm2837.dtsi
+++ b/arch/arm/boot/dts/bcm2837.dtsi
@@ -12,7 +12,7 @@
 			compatible = "brcm,bcm2836-l1-intc";
 			reg = <0x40000000 0x100>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 			interrupt-parent = <&local_intc>;
 		};
 	};
@@ -20,10 +20,10 @@
 	timer {
 		compatible = "arm,armv7-timer";
 		interrupt-parent = <&local_intc>;
-		interrupts = <0>, // PHYS_SECURE_PPI
-			     <1>, // PHYS_NONSECURE_PPI
-			     <3>, // VIRT_PPI
-			     <2>; // HYP_PPI
+		interrupts = <0 IRQ_TYPE_LEVEL_HIGH>, // PHYS_SECURE_PPI
+			     <1 IRQ_TYPE_LEVEL_HIGH>, // PHYS_NONSECURE_PPI
+			     <3 IRQ_TYPE_LEVEL_HIGH>, // VIRT_PPI
+			     <2 IRQ_TYPE_LEVEL_HIGH>; // HYP_PPI
 		always-on;
 	};
 
@@ -73,7 +73,7 @@
 	compatible = "brcm,bcm2836-armctrl-ic";
 	reg = <0x7e00b200 0x200>;
 	interrupt-parent = <&local_intc>;
-	interrupts = <8>;
+	interrupts = <8 IRQ_TYPE_LEVEL_HIGH>;
 };
 
 &cpu_thermal {
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index 013431e3d7c3..18db25a5a66e 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -2,6 +2,7 @@
 #include <dt-bindings/clock/bcm2835.h>
 #include <dt-bindings/clock/bcm2835-aux.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
 
 /* firmware-provided startup stubs live here, where the secondary CPUs are
  * spinning.
@@ -639,5 +640,6 @@
 
 	usbphy: phy {
 		compatible = "usb-nop-xceiv";
+		#phy-cells = <0>;
 	};
 };
diff --git a/arch/arm/boot/dts/bcm958623hr.dts b/arch/arm/boot/dts/bcm958623hr.dts
index 3bc50849d013..b8bde13de90a 100644
--- a/arch/arm/boot/dts/bcm958623hr.dts
+++ b/arch/arm/boot/dts/bcm958623hr.dts
@@ -141,10 +141,6 @@
 	status = "okay";
 };
 
-&sata {
-	status = "okay";
-};
-
 &qspi {
 	bspi-sel = <0>;
 	flash: m25p80@0 {
diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts
index d94d14b3c745..6a44b8021702 100644
--- a/arch/arm/boot/dts/bcm958625hr.dts
+++ b/arch/arm/boot/dts/bcm958625hr.dts
@@ -177,10 +177,6 @@
 	status = "okay";
 };
 
-&sata {
-	status = "okay";
-};
-
 &srab {
 	compatible = "brcm,bcm58625-srab", "brcm,nsp-srab";
 	status = "okay";
diff --git a/arch/arm/boot/dts/da850-lcdk.dts b/arch/arm/boot/dts/da850-lcdk.dts
index eed89e659143..a1f4d6d5a569 100644
--- a/arch/arm/boot/dts/da850-lcdk.dts
+++ b/arch/arm/boot/dts/da850-lcdk.dts
@@ -293,12 +293,12 @@
 					label = "u-boot env";
 					reg = <0 0x020000>;
 				};
-				partition@0x020000 {
+				partition@20000 {
 					/* The LCDK defaults to booting from this partition */
 					label = "u-boot";
 					reg = <0x020000 0x080000>;
 				};
-				partition@0x0a0000 {
+				partition@a0000 {
 					label = "free space";
 					reg = <0x0a0000 0>;
 				};
diff --git a/arch/arm/boot/dts/da850-lego-ev3.dts b/arch/arm/boot/dts/da850-lego-ev3.dts
index 413dbd5d9f64..81942ae83e1f 100644
--- a/arch/arm/boot/dts/da850-lego-ev3.dts
+++ b/arch/arm/boot/dts/da850-lego-ev3.dts
@@ -178,7 +178,7 @@
 	 */
 	battery {
 		pinctrl-names = "default";
-		pintctrl-0 = <&battery_pins>;
+		pinctrl-0 = <&battery_pins>;
 		compatible = "lego,ev3-battery";
 		io-channels = <&adc 4>, <&adc 3>;
 		io-channel-names = "voltage", "current";
@@ -392,7 +392,7 @@
 	batt_volt_en {
 		gpio-hog;
 		gpios = <6 GPIO_ACTIVE_HIGH>;
-		output-low;
+		output-high;
 	};
 };
 
diff --git a/arch/arm/boot/dts/dm814x-clocks.dtsi b/arch/arm/boot/dts/dm814x-clocks.dtsi
index c4671af0a28d..f80525a290bb 100644
--- a/arch/arm/boot/dts/dm814x-clocks.dtsi
+++ b/arch/arm/boot/dts/dm814x-clocks.dtsi
@@ -337,3 +337,33 @@
 		clock-frequency = <20000000>;
 	};
 };
+
+&prcm {
+	default_cm: default_cm@500 {
+		compatible = "ti,omap4-cm";
+		reg = <0x500 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x500 0x100>;
+
+		default_clkctrl: clk@0 {
+			compatible = "ti,clkctrl";
+			reg = <0x0 0x5c>;
+			#clock-cells = <2>;
+		};
+	};
+
+	alwon_cm: alwon_cm@1400 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1400 0x300>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1400 0x300>;
+
+		alwon_clkctrl: clk@0 {
+			compatible = "ti,clkctrl";
+			reg = <0x0 0x228>;
+			#clock-cells = <2>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index 9708157f5daf..601c57afd4fe 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -75,6 +75,7 @@
 				reg = <0x47401300 0x100>;
 				reg-names = "phy";
 				ti,ctrl_mod = <&usb_ctrl_mod>;
+				#phy-cells = <0>;
 			};
 
 			usb0: usb@47401000 {
@@ -249,6 +250,8 @@
 				interrupts = <67>;
 				ti,hwmods = "timer1";
 				ti,timer-alwon;
+				clocks = <&timer1_fck>;
+				clock-names = "fck";
 			};
 
 			uart1: uart@20000 {
@@ -286,6 +289,8 @@
 				reg = <0x40000 0x2000>;
 				interrupts = <68>;
 				ti,hwmods = "timer2";
+				clocks = <&timer2_fck>;
+				clock-names = "fck";
 			};
 
 			timer3: timer@42000 {
@@ -385,6 +390,7 @@
 					reg = <0x1b00 0x100>;
 					reg-names = "phy";
 					ti,ctrl_mod = <&usb_ctrl_mod>;
+					#phy-cells = <0>;
 				};
 			};
 
diff --git a/arch/arm/boot/dts/dm816x-clocks.dtsi b/arch/arm/boot/dts/dm816x-clocks.dtsi
index 51865eb84a80..1efd4e23e50d 100644
--- a/arch/arm/boot/dts/dm816x-clocks.dtsi
+++ b/arch/arm/boot/dts/dm816x-clocks.dtsi
@@ -248,3 +248,33 @@
 		reg = <0x03a8>;
 	};
 };
+
+&prcm {
+	default_cm: default_cm@500 {
+		compatible = "ti,omap4-cm";
+		reg = <0x500 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x500 0x100>;
+
+		default_clkctrl: clk@0 {
+			compatible = "ti,clkctrl";
+			reg = <0x0 0x5c>;
+			#clock-cells = <2>;
+		};
+	};
+
+	alwon_cm: alwon_cm@1400 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1400 0x300>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1400 0x300>;
+
+		alwon_clkctrl: clk@0 {
+			compatible = "ti,clkctrl";
+			reg = <0x0 0x208>;
+			#clock-cells = <2>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index 566b2a8c8b96..1edc2b48b254 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -67,8 +67,11 @@
 		ranges;
 
 		prcm: prcm@48180000 {
-			compatible = "ti,dm816-prcm";
+			compatible = "ti,dm816-prcm", "simple-bus";
 			reg = <0x48180000 0x4000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x48180000 0x4000>;
 
 			prcm_clocks: clocks {
 				#address-cells = <1>;
@@ -331,6 +334,8 @@
 			interrupts = <67>;
 			ti,hwmods = "timer1";
 			ti,timer-alwon;
+			clocks = <&timer1_fck>;
+			clock-names = "fck";
 		};
 
 		timer2: timer@48040000 {
@@ -338,6 +343,8 @@
 			reg = <0x48040000 0x2000>;
 			interrupts = <68>;
 			ti,hwmods = "timer2";
+			clocks = <&timer2_fck>;
+			clock-names = "fck";
 		};
 
 		timer3: timer@48042000 {
diff --git a/arch/arm/boot/dts/dra62x-j5eco-evm.dts b/arch/arm/boot/dts/dra62x-j5eco-evm.dts
index 155eb32ee213..fee0547f7302 100644
--- a/arch/arm/boot/dts/dra62x-j5eco-evm.dts
+++ b/arch/arm/boot/dts/dra62x-j5eco-evm.dts
@@ -74,19 +74,19 @@
 			label = "X-Loader";
 			reg = <0 0x80000>;
 		};
-		partition@0x80000 {
+		partition@80000 {
 			label = "U-Boot";
 			reg = <0x80000 0x1c0000>;
 		};
-		partition@0x1c0000 {
+		partition@1c0000 {
 			label = "Environment";
 			reg = <0x240000 0x40000>;
 		};
-		partition@0x280000 {
+		partition@280000 {
 			label = "Kernel";
 			reg = <0x280000 0x500000>;
 		};
-		partition@0x780000 {
+		partition@780000 {
 			label = "Filesystem";
 			reg = <0x780000 0xf880000>;
 		};
diff --git a/arch/arm/boot/dts/dra7-evm-common.dtsi b/arch/arm/boot/dts/dra7-evm-common.dtsi
index e088bb93636a..05a7b1a01bc3 100644
--- a/arch/arm/boot/dts/dra7-evm-common.dtsi
+++ b/arch/arm/boot/dts/dra7-evm-common.dtsi
@@ -204,7 +204,7 @@
 
 &atl {
 	assigned-clocks = <&abe_dpll_sys_clk_mux>,
-			  <&atl_gfclk_mux>,
+			  <&atl_clkctrl DRA7_ATL_CLKCTRL 26>,
 			  <&dpll_abe_ck>,
 			  <&dpll_abe_m2x2_ck>,
 			  <&atl_clkin2_ck>;
@@ -222,7 +222,7 @@
 &mcasp3 {
 	#sound-dai-cells = <0>;
 
-	assigned-clocks = <&mcasp3_ahclkx_mux>;
+	assigned-clocks = <&l4per_clkctrl DRA7_MCASP3_CLKCTRL 24>;
 	assigned-clock-parents = <&atl_clkin2_ck>;
 
 	status = "okay";
diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts
index ef9c90daa74b..a7385c338ee9 100644
--- a/arch/arm/boot/dts/dra7-evm.dts
+++ b/arch/arm/boot/dts/dra7-evm.dts
@@ -361,7 +361,7 @@
 };
 
 &cpu0 {
-	cpu0-supply = <&smps123_reg>;
+	vdd-supply = <&smps123_reg>;
 };
 
 &omap_dwc3_2 {
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index ac9216293b7c..e4a420f16800 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -7,8 +7,11 @@
  * Based on "omap4.dtsi"
  */
 
+#include <dt-bindings/bus/ti-sysc.h>
+#include <dt-bindings/clock/dra7.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/pinctrl/dra.h>
+#include <dt-bindings/clock/dra7.h>
 
 #define MAX_SOURCES 400
 
@@ -92,6 +95,8 @@
 			cooling-min-level = <0>;
 			cooling-max-level = <2>;
 			#cooling-cells = <2>; /* min followed by max */
+
+			vbb-supply = <&abb_mpu>;
 		};
 	};
 
@@ -101,16 +106,26 @@
 
 		opp_nom-1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
-			opp-microvolt = <1060000 850000 1150000>;
+			opp-microvolt = <1060000 850000 1150000>,
+					<1060000 850000 1150000>;
 			opp-supported-hw = <0xFF 0x01>;
 			opp-suspend;
 		};
 
 		opp_od-1176000000 {
 			opp-hz = /bits/ 64 <1176000000>;
-			opp-microvolt = <1160000 885000 1160000>;
+			opp-microvolt = <1160000 885000 1160000>,
+					<1160000 885000 1160000>;
+
 			opp-supported-hw = <0xFF 0x02>;
 		};
+
+		opp_high@1500000000 {
+			opp-hz = /bits/ 64 <1500000000>;
+			opp-microvolt = <1210000 950000 1250000>,
+					<1210000 950000 1250000>;
+			opp-supported-hw = <0xFF 0x04>;
+		};
 	};
 
 	/*
@@ -224,8 +239,12 @@
 			};
 
 			cm_core_aon: cm_core_aon@5000 {
-				compatible = "ti,dra7-cm-core-aon";
+				compatible = "ti,dra7-cm-core-aon",
+					      "simple-bus";
+				#address-cells = <1>;
+				#size-cells = <1>;
 				reg = <0x5000 0x2000>;
+				ranges = <0 0x5000 0x2000>;
 
 				cm_core_aon_clocks: clocks {
 					#address-cells = <1>;
@@ -237,8 +256,11 @@
 			};
 
 			cm_core: cm_core@8000 {
-				compatible = "ti,dra7-cm-core";
+				compatible = "ti,dra7-cm-core", "simple-bus";
+				#address-cells = <1>;
+				#size-cells = <1>;
 				reg = <0x8000 0x3000>;
+				ranges = <0 0x8000 0x3000>;
 
 				cm_core_clocks: clocks {
 					#address-cells = <1>;
@@ -263,9 +285,12 @@
 			};
 
 			prm: prm@6000 {
-				compatible = "ti,dra7-prm";
+				compatible = "ti,dra7-prm", "simple-bus";
 				reg = <0x6000 0x3000>;
 				interrupts = <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 0x6000 0x3000>;
 
 				prm_clocks: clocks {
 					#address-cells = <1>;
@@ -293,7 +318,6 @@
 			 * node and enable pcie1_ep mode.
 			 */
 			pcie1_rc: pcie@51000000 {
-				compatible = "ti,dra7-pcie";
 				reg = <0x51000000 0x2000>, <0x51002000 0x14c>, <0x1000 0x2000>;
 				reg-names = "rc_dbics", "ti_conf", "config";
 				interrupts = <0 232 0x4>, <0 233 0x4>;
@@ -323,7 +347,6 @@
 			};
 
 			pcie1_ep: pcie_ep@51000000 {
-				compatible = "ti,dra7-pcie-ep";
 				reg = <0x51000000 0x28>, <0x51002000 0x14c>, <0x51001000 0x28>, <0x1000 0x10000000>;
 				reg-names = "ep_dbics", "ti_conf", "ep_dbics2", "addr_space";
 				interrupts = <0 232 0x4>;
@@ -345,8 +368,7 @@
 			ranges = <0x51800000 0x51800000 0x3000
 				  0x0	     0x30000000 0x10000000>;
 			status = "disabled";
-			pcie@51800000 {
-				compatible = "ti,dra7-pcie";
+			pcie2_rc: pcie@51800000 {
 				reg = <0x51800000 0x2000>, <0x51802000 0x14c>, <0x1000 0x2000>;
 				reg-names = "rc_dbics", "ti_conf", "config";
 				interrupts = <0 355 0x4>, <0 356 0x4>;
@@ -876,6 +898,8 @@
 			interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "timer1";
 			ti,timer-alwon;
+			clock-names = "fck";
+			clocks = <&wkupaon_clkctrl DRA7_TIMER1_CLKCTRL 24>;
 		};
 
 		timer2: timer@48032000 {
@@ -1358,7 +1382,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			ti,hwmods = "qspi";
-			clocks = <&qspi_gfclk_div>;
+			clocks = <&l4per_clkctrl DRA7_QSPI_CLKCTRL 25>;
 			clock-names = "fck";
 			num-cs = <4>;
 			interrupts = <GIC_SPI 343 IRQ_TYPE_LEVEL_HIGH>;
@@ -1373,14 +1397,15 @@
 			ranges;
 			reg = <0x4a090000 0x20>;
 			ti,hwmods = "ocp2scp3";
-			sata_phy: phy@4A096000 {
+			sata_phy: phy@4a096000 {
 				compatible = "ti,phy-pipe3-sata";
 				reg = <0x4A096000 0x80>, /* phy_rx */
 				      <0x4A096400 0x64>, /* phy_tx */
 				      <0x4A096800 0x40>; /* pll_ctrl */
 				reg-names = "phy_rx", "phy_tx", "pll_ctrl";
 				syscon-phy-power = <&scm_conf 0x374>;
-				clocks = <&sys_clkin1>, <&sata_ref_clk>;
+				clocks = <&sys_clkin1>,
+					 <&l3init_clkctrl DRA7_SATA_CLKCTRL 8>;
 				clock-names = "sysclk", "refclk";
 				syscon-pllreset = <&scm_conf 0x3fc>;
 				#phy-cells = <0>;
@@ -1395,9 +1420,9 @@
 				syscon-pcs = <&scm_conf_pcie 0x10>;
 				clocks = <&dpll_pcie_ref_ck>,
 					 <&dpll_pcie_ref_m2ldo_ck>,
-					 <&optfclk_pciephy1_32khz>,
-					 <&optfclk_pciephy1_clk>,
-					 <&optfclk_pciephy1_div_clk>,
+					 <&l3init_clkctrl DRA7_PCIE1_CLKCTRL 8>,
+					 <&l3init_clkctrl DRA7_PCIE1_CLKCTRL 9>,
+					 <&l3init_clkctrl DRA7_PCIE1_CLKCTRL 10>,
 					 <&optfclk_pciephy_div>,
 					 <&sys_clkin1>;
 				clock-names = "dpll_ref", "dpll_ref_m2",
@@ -1415,9 +1440,9 @@
 				syscon-pcs = <&scm_conf_pcie 0x10>;
 				clocks = <&dpll_pcie_ref_ck>,
 					 <&dpll_pcie_ref_m2ldo_ck>,
-					 <&optfclk_pciephy2_32khz>,
-					 <&optfclk_pciephy2_clk>,
-					 <&optfclk_pciephy2_div_clk>,
+					 <&l3init_clkctrl DRA7_PCIE2_CLKCTRL 8>,
+					 <&l3init_clkctrl DRA7_PCIE2_CLKCTRL 9>,
+					 <&l3init_clkctrl DRA7_PCIE2_CLKCTRL 10>,
 					 <&optfclk_pciephy_div>,
 					 <&sys_clkin1>;
 				clock-names = "dpll_ref", "dpll_ref_m2",
@@ -1434,7 +1459,7 @@
 			interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
 			phys = <&sata_phy>;
 			phy-names = "sata-phy";
-			clocks = <&sata_ref_clk>;
+			clocks = <&l3init_clkctrl DRA7_SATA_CLKCTRL 8>;
 			ti,hwmods = "sata";
 			ports-implemented = <0x1>;
 		};
@@ -1462,7 +1487,7 @@
 				reg = <0x4a084000 0x400>;
 				syscon-phy-power = <&scm_conf 0x300>;
 				clocks = <&usb_phy1_always_on_clk32k>,
-					 <&usb_otg_ss1_refclk960m>;
+					 <&l3init_clkctrl DRA7_USB_OTG_SS1_CLKCTRL 8>;
 				clock-names =	"wkupclk",
 						"refclk";
 				#phy-cells = <0>;
@@ -1474,7 +1499,7 @@
 				reg = <0x4a085000 0x400>;
 				syscon-phy-power = <&scm_conf 0xe74>;
 				clocks = <&usb_phy2_always_on_clk32k>,
-					 <&usb_otg_ss2_refclk960m>;
+					 <&l3init_clkctrl DRA7_USB_OTG_SS2_CLKCTRL 8>;
 				clock-names =	"wkupclk",
 						"refclk";
 				#phy-cells = <0>;
@@ -1489,7 +1514,7 @@
 				syscon-phy-power = <&scm_conf 0x370>;
 				clocks = <&usb_phy3_always_on_clk32k>,
 					 <&sys_clkin1>,
-					 <&usb_otg_ss1_refclk960m>;
+					 <&l3init_clkctrl DRA7_USB_OTG_SS1_CLKCTRL 8>;
 				clock-names =	"wkupclk",
 						"sysclk",
 						"refclk";
@@ -1498,11 +1523,17 @@
 		};
 
 		target-module@4a0dd000 {
-			compatible = "ti,sysc-omap4-sr";
+			compatible = "ti,sysc-omap4-sr", "ti,sysc";
 			ti,hwmods = "smartreflex_core";
-			reg = <0x4a0dd000 0x4>,
-			      <0x4a0dd008 0x4>;
-			reg-names = "rev", "sysc";
+			reg = <0x4a0dd038 0x4>;
+			reg-names = "sysc";
+			ti,sysc-mask = <SYSC_OMAP3_SR_ENAWAKEUP>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			clocks = <&coreaon_clkctrl DRA7_SMARTREFLEX_CORE_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x4a0dd000 0x001000>;
@@ -1511,11 +1542,17 @@
 		};
 
 		target-module@4a0d9000 {
-			compatible = "ti,sysc-omap4-sr";
+			compatible = "ti,sysc-omap4-sr", "ti,sysc";
 			ti,hwmods = "smartreflex_mpu";
-			reg = <0x4a0d9000 0x4>,
-			      <0x4a0d9008 0x4>;
-			reg-names = "rev", "sysc";
+			reg = <0x4a0d9038 0x4>;
+			reg-names = "sysc";
+			ti,sysc-mask = <SYSC_OMAP3_SR_ENAWAKEUP>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			clocks = <&coreaon_clkctrl DRA7_SMARTREFLEX_MPU_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x4a0d9000 0x001000>;
@@ -1547,6 +1584,7 @@
 				dr_mode = "otg";
 				snps,dis_u3_susphy_quirk;
 				snps,dis_u2_susphy_quirk;
+				snps,dis_metastability_quirk;
 			};
 		};
 
@@ -1636,7 +1674,7 @@
 			ti,hwmods = "atl";
 			ti,provided-clocks = <&atl_clkin0_ck>, <&atl_clkin1_ck>,
 					     <&atl_clkin2_ck>, <&atl_clkin3_ck>;
-			clocks = <&atl_gfclk_mux>;
+			clocks = <&atl_clkctrl DRA7_ATL_CLKCTRL 26>;
 			clock-names = "fck";
 			status = "disabled";
 		};
@@ -1652,8 +1690,8 @@
 			interrupt-names = "tx", "rx";
 			dmas = <&edma_xbar 129 1>, <&edma_xbar 128 1>;
 			dma-names = "tx", "rx";
-			clocks = <&mcasp1_aux_gfclk_mux>, <&mcasp1_ahclkx_mux>,
-				 <&mcasp1_ahclkr_mux>;
+			clocks = <&ipu_clkctrl DRA7_MCASP1_CLKCTRL 22>, <&ipu_clkctrl DRA7_MCASP1_CLKCTRL 24>,
+				 <&ipu_clkctrl DRA7_MCASP1_CLKCTRL 28>;
 			clock-names = "fck", "ahclkx", "ahclkr";
 			status = "disabled";
 		};
@@ -1669,8 +1707,9 @@
 			interrupt-names = "tx", "rx";
 			dmas = <&edma_xbar 131 1>, <&edma_xbar 130 1>;
 			dma-names = "tx", "rx";
-			clocks = <&mcasp2_aux_gfclk_mux>, <&mcasp2_ahclkx_mux>,
-				 <&mcasp2_ahclkr_mux>;
+			clocks = <&l4per_clkctrl DRA7_MCASP2_CLKCTRL 22>,
+				 <&l4per_clkctrl DRA7_MCASP2_CLKCTRL 24>,
+				 <&l4per_clkctrl DRA7_MCASP2_CLKCTRL 28>;
 			clock-names = "fck", "ahclkx", "ahclkr";
 			status = "disabled";
 		};
@@ -1686,7 +1725,8 @@
 			interrupt-names = "tx", "rx";
 			dmas = <&edma_xbar 133 1>, <&edma_xbar 132 1>;
 			dma-names = "tx", "rx";
-			clocks = <&mcasp3_aux_gfclk_mux>, <&mcasp3_ahclkx_mux>;
+			clocks = <&l4per_clkctrl DRA7_MCASP3_CLKCTRL 22>,
+				 <&l4per_clkctrl DRA7_MCASP3_CLKCTRL 24>;
 			clock-names = "fck", "ahclkx";
 			status = "disabled";
 		};
@@ -1702,7 +1742,8 @@
 			interrupt-names = "tx", "rx";
 			dmas = <&edma_xbar 135 1>, <&edma_xbar 134 1>;
 			dma-names = "tx", "rx";
-			clocks = <&mcasp4_aux_gfclk_mux>, <&mcasp4_ahclkx_mux>;
+			clocks = <&l4per_clkctrl DRA7_MCASP4_CLKCTRL 22>,
+				 <&l4per_clkctrl DRA7_MCASP4_CLKCTRL 24>;
 			clock-names = "fck", "ahclkx";
 			status = "disabled";
 		};
@@ -1718,7 +1759,8 @@
 			interrupt-names = "tx", "rx";
 			dmas = <&edma_xbar 137 1>, <&edma_xbar 136 1>;
 			dma-names = "tx", "rx";
-			clocks = <&mcasp5_aux_gfclk_mux>, <&mcasp5_ahclkx_mux>;
+			clocks = <&l4per_clkctrl DRA7_MCASP5_CLKCTRL 22>,
+				 <&l4per_clkctrl DRA7_MCASP5_CLKCTRL 24>;
 			clock-names = "fck", "ahclkx";
 			status = "disabled";
 		};
@@ -1734,7 +1776,8 @@
 			interrupt-names = "tx", "rx";
 			dmas = <&edma_xbar 139 1>, <&edma_xbar 138 1>;
 			dma-names = "tx", "rx";
-			clocks = <&mcasp6_aux_gfclk_mux>, <&mcasp6_ahclkx_mux>;
+			clocks = <&l4per_clkctrl DRA7_MCASP6_CLKCTRL 22>,
+				 <&l4per_clkctrl DRA7_MCASP6_CLKCTRL 24>;
 			clock-names = "fck", "ahclkx";
 			status = "disabled";
 		};
@@ -1750,7 +1793,8 @@
 			interrupt-names = "tx", "rx";
 			dmas = <&edma_xbar 141 1>, <&edma_xbar 140 1>;
 			dma-names = "tx", "rx";
-			clocks = <&mcasp7_aux_gfclk_mux>, <&mcasp7_ahclkx_mux>;
+			clocks = <&l4per_clkctrl DRA7_MCASP7_CLKCTRL 22>,
+				 <&l4per_clkctrl DRA7_MCASP7_CLKCTRL 24>;
 			clock-names = "fck", "ahclkx";
 			status = "disabled";
 		};
@@ -1766,7 +1810,8 @@
 			interrupt-names = "tx", "rx";
 			dmas = <&edma_xbar 143 1>, <&edma_xbar 142 1>;
 			dma-names = "tx", "rx";
-			clocks = <&mcasp8_aux_gfclk_mux>, <&mcasp8_ahclkx_mux>;
+			clocks = <&l4per_clkctrl DRA7_MCASP8_CLKCTRL 22>,
+				 <&l4per_clkctrl DRA7_MCASP8_CLKCTRL 24>;
 			clock-names = "fck", "ahclkx";
 			status = "disabled";
 		};
@@ -1788,7 +1833,7 @@
 		mac: ethernet@48484000 {
 			compatible = "ti,dra7-cpsw","ti,cpsw";
 			ti,hwmods = "gmac";
-			clocks = <&gmac_main_clk>, <&gmac_rft_clk_mux>;
+			clocks = <&gmac_main_clk>, <&l3init_clkctrl DRA7_GMAC_CLKCTRL 25>;
 			clock-names = "fck", "cpts";
 			cpdma_channels = <8>;
 			ale_entries = <1024>;
@@ -1858,7 +1903,7 @@
 			reg = <0x4ae3c000 0x2000>;
 			syscon-raminit = <&scm_conf 0x558 0>;
 			interrupts = <GIC_SPI 222 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&dcan1_sys_clk_mux>;
+			clocks = <&wkupaon_clkctrl DRA7_DCAN1_CLKCTRL 24>;
 			status = "disabled";
 		};
 
@@ -1889,7 +1934,7 @@
 				reg = <0x58001000 0x1000>;
 				interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
 				ti,hwmods = "dss_dispc";
-				clocks = <&dss_dss_clk>;
+				clocks = <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 8>;
 				clock-names = "fck";
 				/* CTRL_CORE_SMA_SW_1 */
 				syscon-pol = <&scm_conf 0x534>;
@@ -1905,8 +1950,11 @@
 				interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 				ti,hwmods = "dss_hdmi";
-				clocks = <&dss_48mhz_clk>, <&dss_hdmi_clk>;
+				clocks = <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 9>,
+					 <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 10>;
 				clock-names = "fck", "sys_clk";
+				dmas = <&sdma_xbar 76>;
+				dma-names = "audio_tx";
 			};
 		};
 
@@ -2052,6 +2100,19 @@
 			clocks = <&l3_iclk_div>;
 			clock-names = "fck";
 		};
+
+		opp_supply_mpu: opp-supply@4a003b20 {
+			compatible = "ti,omap5-opp-supply";
+			reg = <0x4a003b20 0xc>;
+			ti,efuse-settings = <
+			/* uV   offset */
+			1060000 0x0
+			1160000 0x4
+			1210000 0x8
+			>;
+			ti,absolute-max-voltage-uv = <1500000>;
+		};
+
 	};
 
 	thermal_zones: thermal-zones {
@@ -2089,4 +2150,20 @@
 	temperature = <120000>; /* milli Celsius */
 };
 
-/include/ "dra7xx-clocks.dtsi"
+#include "dra7xx-clocks.dtsi"
+
+&core_crit {
+	temperature = <120000>; /* milli Celsius */
+};
+
+&gpu_crit {
+	temperature = <120000>; /* milli Celsius */
+};
+
+&dspeve_crit {
+	temperature = <120000>; /* milli Celsius */
+};
+
+&iva_crit {
+	temperature = <120000>; /* milli Celsius */
+};
diff --git a/arch/arm/boot/dts/dra72-evm-common.dtsi b/arch/arm/boot/dts/dra72-evm-common.dtsi
index 2e485a13dfd7..e85f560a2f78 100644
--- a/arch/arm/boot/dts/dra72-evm-common.dtsi
+++ b/arch/arm/boot/dts/dra72-evm-common.dtsi
@@ -514,7 +514,7 @@
 
 &atl {
 	assigned-clocks = <&abe_dpll_sys_clk_mux>,
-			  <&atl_gfclk_mux>,
+			  <&atl_clkctrl DRA7_ATL_CLKCTRL 26>,
 			  <&dpll_abe_ck>,
 			  <&dpll_abe_m2x2_ck>,
 			  <&atl_clkin2_ck>;
@@ -532,7 +532,7 @@
 &mcasp3 {
 	#sound-dai-cells = <0>;
 
-	assigned-clocks = <&mcasp3_ahclkx_mux>;
+	assigned-clocks = <&l4per_clkctrl DRA7_MCASP3_CLKCTRL 24>;
 	assigned-clock-parents = <&atl_clkin2_ck>;
 
 	status = "okay";
diff --git a/arch/arm/boot/dts/dra72-evm-tps65917.dtsi b/arch/arm/boot/dts/dra72-evm-tps65917.dtsi
index 57bfe5caf5e4..47bb90f41f3f 100644
--- a/arch/arm/boot/dts/dra72-evm-tps65917.dtsi
+++ b/arch/arm/boot/dts/dra72-evm-tps65917.dtsi
@@ -148,3 +148,7 @@
 &mmc1 {
 	vqmmc-supply = <&ldo1_reg>;
 };
+
+&cpu0 {
+	vdd-supply = <&smps1_reg>;
+};
diff --git a/arch/arm/boot/dts/dra72x.dtsi b/arch/arm/boot/dts/dra72x.dtsi
index 67107605fb4c..c011d2e64fef 100644
--- a/arch/arm/boot/dts/dra72x.dtsi
+++ b/arch/arm/boot/dts/dra72x.dtsi
@@ -25,8 +25,8 @@
 	      <0x58004300 0x20>;
 	reg-names = "dss", "pll1_clkctrl", "pll1";
 
-	clocks = <&dss_dss_clk>,
-		 <&dss_video1_clk>;
+	clocks = <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 8>,
+		 <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 12>;
 	clock-names = "fck", "video1_clk";
 };
 
@@ -50,3 +50,15 @@
 		status = "disabled";
 	};
 };
+
+&pcie1_rc {
+	compatible = "ti,dra726-pcie-rc", "ti,dra7-pcie";
+};
+
+&pcie1_ep {
+	compatible = "ti,dra726-pcie-ep", "ti,dra7-pcie-ep";
+};
+
+&pcie2_rc {
+	compatible = "ti,dra726-pcie-rc", "ti,dra7-pcie";
+};
diff --git a/arch/arm/boot/dts/dra74x.dtsi b/arch/arm/boot/dts/dra74x.dtsi
index 24e6746c5b26..91e93ab588ca 100644
--- a/arch/arm/boot/dts/dra74x.dtsi
+++ b/arch/arm/boot/dts/dra74x.dtsi
@@ -93,9 +93,9 @@
 	reg-names = "dss", "pll1_clkctrl", "pll1",
 		    "pll2_clkctrl", "pll2";
 
-	clocks = <&dss_dss_clk>,
-		 <&dss_video1_clk>,
-		 <&dss_video2_clk>;
+	clocks = <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 8>,
+		 <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 12>,
+		 <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 13>;
 	clock-names = "fck", "video1_clk", "video2_clk";
 };
 
@@ -124,3 +124,15 @@
 		status = "disabled";
 	};
 };
+
+&pcie1_rc {
+	compatible = "ti,dra746-pcie-rc", "ti,dra7-pcie";
+};
+
+&pcie1_ep {
+	compatible = "ti,dra746-pcie-ep", "ti,dra7-pcie-ep";
+};
+
+&pcie2_rc {
+	compatible = "ti,dra746-pcie-rc", "ti,dra7-pcie";
+};
diff --git a/arch/arm/boot/dts/dra76-evm.dts b/arch/arm/boot/dts/dra76-evm.dts
index b024a65c6e27..c4fe7f8ef72a 100644
--- a/arch/arm/boot/dts/dra76-evm.dts
+++ b/arch/arm/boot/dts/dra76-evm.dts
@@ -148,6 +148,7 @@
 		compatible = "ti,tps65917";
 		reg = <0x58>;
 		ti,system-power-controller;
+		ti,palmas-override-powerhold;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 
@@ -421,3 +422,19 @@
 		spi-max-frequency = <96000000>;
 	};
 };
+
+&pcie2_phy {
+	status = "okay";
+};
+
+&pcie1_rc {
+	num-lanes = <2>;
+	phys = <&pcie1_phy>, <&pcie2_phy>;
+	phy-names = "pcie-phy0", "pcie-phy1";
+};
+
+&pcie1_ep {
+	num-lanes = <2>;
+	phys = <&pcie1_phy>, <&pcie2_phy>;
+	phy-names = "pcie-phy0", "pcie-phy1";
+};
diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi
index e62b62875cba..69562cdbeada 100644
--- a/arch/arm/boot/dts/dra7xx-clocks.dtsi
+++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi
@@ -11,25 +11,25 @@
 	atl_clkin0_ck: atl_clkin0_ck {
 		#clock-cells = <0>;
 		compatible = "ti,dra7-atl-clock";
-		clocks = <&atl_gfclk_mux>;
+		clocks = <&atl_clkctrl DRA7_ATL_CLKCTRL 26>;
 	};
 
 	atl_clkin1_ck: atl_clkin1_ck {
 		#clock-cells = <0>;
 		compatible = "ti,dra7-atl-clock";
-		clocks = <&atl_gfclk_mux>;
+		clocks = <&atl_clkctrl DRA7_ATL_CLKCTRL 26>;
 	};
 
 	atl_clkin2_ck: atl_clkin2_ck {
 		#clock-cells = <0>;
 		compatible = "ti,dra7-atl-clock";
-		clocks = <&atl_gfclk_mux>;
+		clocks = <&atl_clkctrl DRA7_ATL_CLKCTRL 26>;
 	};
 
 	atl_clkin3_ck: atl_clkin3_ck {
 		#clock-cells = <0>;
 		compatible = "ti,dra7-atl-clock";
-		clocks = <&atl_gfclk_mux>;
+		clocks = <&atl_clkctrl DRA7_ATL_CLKCTRL 26>;
 	};
 
 	hdmi_clkin_ck: hdmi_clkin_ck {
@@ -809,70 +809,6 @@
 		assigned-clock-parents = <&dpll_core_h22x2_ck>;
 	};
 
-	mcasp1_ahclkr_mux: mcasp1_ahclkr_mux@550 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
-		ti,bit-shift = <28>;
-		reg = <0x0550>;
-	};
-
-	mcasp1_ahclkx_mux: mcasp1_ahclkx_mux@550 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x0550>;
-	};
-
-	mcasp1_aux_gfclk_mux: mcasp1_aux_gfclk_mux@550 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&per_abe_x1_gfclk2_div>, <&video1_clk2_div>, <&video2_clk2_div>, <&hdmi_clk2_div>;
-		ti,bit-shift = <22>;
-		reg = <0x0550>;
-	};
-
-	timer5_gfclk_mux: timer5_gfclk_mux@558 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>, <&clkoutmux0_clk_mux>;
-		ti,bit-shift = <24>;
-		reg = <0x0558>;
-	};
-
-	timer6_gfclk_mux: timer6_gfclk_mux@560 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>, <&clkoutmux0_clk_mux>;
-		ti,bit-shift = <24>;
-		reg = <0x0560>;
-	};
-
-	timer7_gfclk_mux: timer7_gfclk_mux@568 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>, <&clkoutmux0_clk_mux>;
-		ti,bit-shift = <24>;
-		reg = <0x0568>;
-	};
-
-	timer8_gfclk_mux: timer8_gfclk_mux@570 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>, <&clkoutmux0_clk_mux>;
-		ti,bit-shift = <24>;
-		reg = <0x0570>;
-	};
-
-	uart6_gfclk_mux: uart6_gfclk_mux@580 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x0580>;
-	};
-
 	dummy_ck: dummy_ck {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
@@ -1188,39 +1124,8 @@
 		clocks = <&sys_clkin1>, <&abe_lp_clk_div>;
 		reg = <0x0108>;
 	};
-
-	gpio1_dbclk: gpio1_dbclk@1838 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1838>;
-	};
-
-	dcan1_sys_clk_mux: dcan1_sys_clk_mux@1888 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin1>, <&sys_clkin2>;
-		ti,bit-shift = <24>;
-		reg = <0x1888>;
-	};
-
-	timer1_gfclk_mux: timer1_gfclk_mux@1840 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1840>;
-	};
-
-	uart10_gfclk_mux: uart10_gfclk_mux@1880 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1880>;
-	};
 };
+
 &cm_core_clocks {
 	dpll_pcie_ref_ck: dpll_pcie_ref_ck@200 {
 		#clock-cells = <0>;
@@ -1255,22 +1160,6 @@
 		reg = <0x021c>, <0x0220>;
 	};
 
-	optfclk_pciephy1_32khz: optfclk_pciephy1_32khz@4a0093b0 {
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		#clock-cells = <0>;
-		reg = <0x13b0>;
-		ti,bit-shift = <8>;
-	};
-
-	optfclk_pciephy2_32khz: optfclk_pciephy2_32khz@4a0093b8 {
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		#clock-cells = <0>;
-		reg = <0x13b8>;
-		ti,bit-shift = <8>;
-	};
-
 	optfclk_pciephy_div: optfclk_pciephy_div@4a00821c {
 		compatible = "ti,divider-clock";
 		clocks = <&apll_pcie_ck>;
@@ -1281,38 +1170,6 @@
 		ti,max-div = <2>;
 	};
 
-	optfclk_pciephy1_clk: optfclk_pciephy1_clk@4a0093b0 {
-		compatible = "ti,gate-clock";
-		clocks = <&apll_pcie_ck>;
-		#clock-cells = <0>;
-		reg = <0x13b0>;
-		ti,bit-shift = <9>;
-	};
-
-	optfclk_pciephy2_clk: optfclk_pciephy2_clk@4a0093b8 {
-		compatible = "ti,gate-clock";
-		clocks = <&apll_pcie_ck>;
-		#clock-cells = <0>;
-		reg = <0x13b8>;
-		ti,bit-shift = <9>;
-	};
-
-	optfclk_pciephy1_div_clk: optfclk_pciephy1_div_clk@4a0093b0 {
-		compatible = "ti,gate-clock";
-		clocks = <&optfclk_pciephy_div>;
-		#clock-cells = <0>;
-		reg = <0x13b0>;
-		ti,bit-shift = <10>;
-	};
-
-	optfclk_pciephy2_div_clk: optfclk_pciephy2_div_clk@4a0093b8 {
-		compatible = "ti,gate-clock";
-		clocks = <&optfclk_pciephy_div>;
-		#clock-cells = <0>;
-		reg = <0x13b8>;
-		ti,bit-shift = <10>;
-	};
-
 	apll_pcie_clkvcoldo: apll_pcie_clkvcoldo {
 		#clock-cells = <0>;
 		compatible = "fixed-factor-clock";
@@ -1541,167 +1398,6 @@
 		reg = <0x06c0>;
 	};
 
-	dss_32khz_clk: dss_32khz_clk@1120 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <11>;
-		reg = <0x1120>;
-	};
-
-	dss_48mhz_clk: dss_48mhz_clk@1120 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&func_48m_fclk>;
-		ti,bit-shift = <9>;
-		reg = <0x1120>;
-	};
-
-	dss_dss_clk: dss_dss_clk@1120 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_h12x2_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1120>;
-		ti,set-rate-parent;
-	};
-
-	dss_hdmi_clk: dss_hdmi_clk@1120 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&hdmi_dpll_clk_mux>;
-		ti,bit-shift = <10>;
-		reg = <0x1120>;
-	};
-
-	dss_video1_clk: dss_video1_clk@1120 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&video1_dpll_clk_mux>;
-		ti,bit-shift = <12>;
-		reg = <0x1120>;
-	};
-
-	dss_video2_clk: dss_video2_clk@1120 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&video2_dpll_clk_mux>;
-		ti,bit-shift = <13>;
-		reg = <0x1120>;
-	};
-
-	gpio2_dbclk: gpio2_dbclk@1760 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1760>;
-	};
-
-	gpio3_dbclk: gpio3_dbclk@1768 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1768>;
-	};
-
-	gpio4_dbclk: gpio4_dbclk@1770 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1770>;
-	};
-
-	gpio5_dbclk: gpio5_dbclk@1778 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1778>;
-	};
-
-	gpio6_dbclk: gpio6_dbclk@1780 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1780>;
-	};
-
-	gpio7_dbclk: gpio7_dbclk@1810 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1810>;
-	};
-
-	gpio8_dbclk: gpio8_dbclk@1818 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1818>;
-	};
-
-	mmc1_clk32k: mmc1_clk32k@1328 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1328>;
-	};
-
-	mmc2_clk32k: mmc2_clk32k@1330 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1330>;
-	};
-
-	mmc3_clk32k: mmc3_clk32k@1820 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1820>;
-	};
-
-	mmc4_clk32k: mmc4_clk32k@1828 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1828>;
-	};
-
-	sata_ref_clk: sata_ref_clk@1388 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_clkin1>;
-		ti,bit-shift = <8>;
-		reg = <0x1388>;
-	};
-
-	usb_otg_ss1_refclk960m: usb_otg_ss1_refclk960m@13f0 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l3init_960m_gfclk>;
-		ti,bit-shift = <8>;
-		reg = <0x13f0>;
-	};
-
-	usb_otg_ss2_refclk960m: usb_otg_ss2_refclk960m@1340 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l3init_960m_gfclk>;
-		ti,bit-shift = <8>;
-		reg = <0x1340>;
-	};
-
 	usb_phy1_always_on_clk32k: usb_phy1_always_on_clk32k@640 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
@@ -1726,38 +1422,6 @@
 		reg = <0x0698>;
 	};
 
-	atl_dpll_clk_mux: atl_dpll_clk_mux@c00 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_32k_ck>, <&video1_clkin_ck>, <&video2_clkin_ck>, <&hdmi_clkin_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x0c00>;
-	};
-
-	atl_gfclk_mux: atl_gfclk_mux@c00 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&l3_iclk_div>, <&dpll_abe_m2_ck>, <&atl_dpll_clk_mux>;
-		ti,bit-shift = <26>;
-		reg = <0x0c00>;
-	};
-
-	rmii_50mhz_clk_mux: rmii_50mhz_clk_mux@13d0 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&dpll_gmac_h11x2_ck>, <&rmii_clk_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x13d0>;
-	};
-
-	gmac_rft_clk_mux: gmac_rft_clk_mux@13d0 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&video1_clkin_ck>, <&video2_clkin_ck>, <&dpll_abe_m2_ck>, <&hdmi_clkin_ck>, <&l3_iclk_div>;
-		ti,bit-shift = <25>;
-		reg = <0x13d0>;
-	};
-
 	gpu_core_gclk_mux: gpu_core_gclk_mux@1220 {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
@@ -1787,362 +1451,6 @@
 		ti,dividers = <8>, <16>, <32>;
 	};
 
-	mcasp2_ahclkr_mux: mcasp2_ahclkr_mux@1860 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
-		ti,bit-shift = <28>;
-		reg = <0x1860>;
-	};
-
-	mcasp2_ahclkx_mux: mcasp2_ahclkx_mux@1860 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1860>;
-	};
-
-	mcasp2_aux_gfclk_mux: mcasp2_aux_gfclk_mux@1860 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&per_abe_x1_gfclk2_div>, <&video1_clk2_div>, <&video2_clk2_div>, <&hdmi_clk2_div>;
-		ti,bit-shift = <22>;
-		reg = <0x1860>;
-	};
-
-	mcasp3_ahclkx_mux: mcasp3_ahclkx_mux@1868 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1868>;
-		assigned-clocks = <&mcasp3_ahclkx_mux>;
-		assigned-clock-parents = <&abe_24m_fclk>;
-	};
-
-	mcasp3_aux_gfclk_mux: mcasp3_aux_gfclk_mux@1868 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&per_abe_x1_gfclk2_div>, <&video1_clk2_div>, <&video2_clk2_div>, <&hdmi_clk2_div>;
-		ti,bit-shift = <22>;
-		reg = <0x1868>;
-	};
-
-	mcasp4_ahclkx_mux: mcasp4_ahclkx_mux@1898 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1898>;
-	};
-
-	mcasp4_aux_gfclk_mux: mcasp4_aux_gfclk_mux@1898 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&per_abe_x1_gfclk2_div>, <&video1_clk2_div>, <&video2_clk2_div>, <&hdmi_clk2_div>;
-		ti,bit-shift = <22>;
-		reg = <0x1898>;
-	};
-
-	mcasp5_ahclkx_mux: mcasp5_ahclkx_mux@1878 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1878>;
-	};
-
-	mcasp5_aux_gfclk_mux: mcasp5_aux_gfclk_mux@1878 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&per_abe_x1_gfclk2_div>, <&video1_clk2_div>, <&video2_clk2_div>, <&hdmi_clk2_div>;
-		ti,bit-shift = <22>;
-		reg = <0x1878>;
-	};
-
-	mcasp6_ahclkx_mux: mcasp6_ahclkx_mux@1904 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1904>;
-	};
-
-	mcasp6_aux_gfclk_mux: mcasp6_aux_gfclk_mux@1904 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&per_abe_x1_gfclk2_div>, <&video1_clk2_div>, <&video2_clk2_div>, <&hdmi_clk2_div>;
-		ti,bit-shift = <22>;
-		reg = <0x1904>;
-	};
-
-	mcasp7_ahclkx_mux: mcasp7_ahclkx_mux@1908 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1908>;
-	};
-
-	mcasp7_aux_gfclk_mux: mcasp7_aux_gfclk_mux@1908 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&per_abe_x1_gfclk2_div>, <&video1_clk2_div>, <&video2_clk2_div>, <&hdmi_clk2_div>;
-		ti,bit-shift = <22>;
-		reg = <0x1908>;
-	};
-
-	mcasp8_ahclkx_mux: mcasp8_ahclkx_mux@1890 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
-		ti,bit-shift = <22>;
-		reg = <0x1890>;
-	};
-
-	mcasp8_aux_gfclk_mux: mcasp8_aux_gfclk_mux@1890 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&per_abe_x1_gfclk2_div>, <&video1_clk2_div>, <&video2_clk2_div>, <&hdmi_clk2_div>;
-		ti,bit-shift = <24>;
-		reg = <0x1890>;
-	};
-
-	mmc1_fclk_mux: mmc1_fclk_mux@1328 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_128m_clk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1328>;
-	};
-
-	mmc1_fclk_div: mmc1_fclk_div@1328 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&mmc1_fclk_mux>;
-		ti,bit-shift = <25>;
-		ti,max-div = <4>;
-		reg = <0x1328>;
-		ti,index-power-of-two;
-	};
-
-	mmc2_fclk_mux: mmc2_fclk_mux@1330 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_128m_clk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1330>;
-	};
-
-	mmc2_fclk_div: mmc2_fclk_div@1330 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&mmc2_fclk_mux>;
-		ti,bit-shift = <25>;
-		ti,max-div = <4>;
-		reg = <0x1330>;
-		ti,index-power-of-two;
-	};
-
-	mmc3_gfclk_mux: mmc3_gfclk_mux@1820 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1820>;
-	};
-
-	mmc3_gfclk_div: mmc3_gfclk_div@1820 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&mmc3_gfclk_mux>;
-		ti,bit-shift = <25>;
-		ti,max-div = <4>;
-		reg = <0x1820>;
-		ti,index-power-of-two;
-	};
-
-	mmc4_gfclk_mux: mmc4_gfclk_mux@1828 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1828>;
-	};
-
-	mmc4_gfclk_div: mmc4_gfclk_div@1828 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&mmc4_gfclk_mux>;
-		ti,bit-shift = <25>;
-		ti,max-div = <4>;
-		reg = <0x1828>;
-		ti,index-power-of-two;
-	};
-
-	qspi_gfclk_mux: qspi_gfclk_mux@1838 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_128m_clk>, <&dpll_per_h13x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1838>;
-	};
-
-	qspi_gfclk_div: qspi_gfclk_div@1838 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&qspi_gfclk_mux>;
-		ti,bit-shift = <25>;
-		ti,max-div = <4>;
-		reg = <0x1838>;
-		ti,index-power-of-two;
-	};
-
-	timer10_gfclk_mux: timer10_gfclk_mux@1728 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1728>;
-	};
-
-	timer11_gfclk_mux: timer11_gfclk_mux@1730 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1730>;
-	};
-
-	timer13_gfclk_mux: timer13_gfclk_mux@17c8 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x17c8>;
-	};
-
-	timer14_gfclk_mux: timer14_gfclk_mux@17d0 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x17d0>;
-	};
-
-	timer15_gfclk_mux: timer15_gfclk_mux@17d8 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x17d8>;
-	};
-
-	timer16_gfclk_mux: timer16_gfclk_mux@1830 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1830>;
-	};
-
-	timer2_gfclk_mux: timer2_gfclk_mux@1738 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1738>;
-	};
-
-	timer3_gfclk_mux: timer3_gfclk_mux@1740 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1740>;
-	};
-
-	timer4_gfclk_mux: timer4_gfclk_mux@1748 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1748>;
-	};
-
-	timer9_gfclk_mux: timer9_gfclk_mux@1750 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&timer_sys_clk_div>, <&sys_32k_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&abe_giclk_div>, <&video1_div_clk>, <&video2_div_clk>, <&hdmi_div_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x1750>;
-	};
-
-	uart1_gfclk_mux: uart1_gfclk_mux@1840 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1840>;
-	};
-
-	uart2_gfclk_mux: uart2_gfclk_mux@1848 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1848>;
-	};
-
-	uart3_gfclk_mux: uart3_gfclk_mux@1850 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1850>;
-	};
-
-	uart4_gfclk_mux: uart4_gfclk_mux@1858 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1858>;
-	};
-
-	uart5_gfclk_mux: uart5_gfclk_mux@1870 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1870>;
-	};
-
-	uart7_gfclk_mux: uart7_gfclk_mux@18d0 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x18d0>;
-	};
-
-	uart8_gfclk_mux: uart8_gfclk_mux@18e0 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x18e0>;
-	};
-
-	uart9_gfclk_mux: uart9_gfclk_mux@18e8 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_48m_fclk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x18e8>;
-	};
-
 	vip1_gclk_mux: vip1_gclk_mux@1020 {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
@@ -2216,3 +1524,210 @@
 		reg = <0x6c4>;
 	};
 };
+
+&cm_core_aon {
+	mpu_cm: mpu_cm@300 {
+		compatible = "ti,omap4-cm";
+		reg = <0x300 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x300 0x100>;
+
+		mpu_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	ipu_cm: ipu_cm@500 {
+		compatible = "ti,omap4-cm";
+		reg = <0x500 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x500 0x100>;
+
+		ipu_clkctrl: clk@40 {
+			compatible = "ti,clkctrl";
+			reg = <0x40 0x44>;
+			#clock-cells = <2>;
+		};
+	};
+
+	rtc_cm: rtc_cm@700 {
+		compatible = "ti,omap4-cm";
+		reg = <0x700 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x700 0x100>;
+
+		rtc_clkctrl: clk@40 {
+			compatible = "ti,clkctrl";
+			reg = <0x40 0x8>;
+			#clock-cells = <2>;
+		};
+	};
+
+};
+
+&cm_core {
+	coreaon_cm: coreaon_cm@600 {
+		compatible = "ti,omap4-cm";
+		reg = <0x600 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x600 0x100>;
+
+		coreaon_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x1c>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3main1_cm: l3main1_cm@700 {
+		compatible = "ti,omap4-cm";
+		reg = <0x700 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x700 0x100>;
+
+		l3main1_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x74>;
+			#clock-cells = <2>;
+		};
+	};
+
+	dma_cm: dma_cm@a00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xa00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xa00 0x100>;
+
+		dma_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	emif_cm: emif_cm@b00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xb00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xb00 0x100>;
+
+		emif_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	atl_cm: atl_cm@c00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xc00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xc00 0x100>;
+
+		atl_clkctrl: clk@0 {
+			compatible = "ti,clkctrl";
+			reg = <0x0 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l4cfg_cm: l4cfg_cm@d00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xd00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xd00 0x100>;
+
+		l4cfg_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x84>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3instr_cm: l3instr_cm@e00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xe00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xe00 0x100>;
+
+		l3instr_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0xc>;
+			#clock-cells = <2>;
+		};
+	};
+
+	dss_cm: dss_cm@1100 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1100 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1100 0x100>;
+
+		dss_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x14>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3init_cm: l3init_cm@1300 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1300 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1300 0x100>;
+
+		l3init_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0xd4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l4per_cm: l4per_cm@1700 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1700 0x300>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1700 0x300>;
+
+		l4per_clkctrl: clk@0 {
+			compatible = "ti,clkctrl";
+			reg = <0x0 0x20c>;
+			#clock-cells = <2>;
+
+			assigned-clocks = <&l4per_clkctrl DRA7_MCASP3_CLKCTRL 24>;
+			assigned-clock-parents = <&abe_24m_fclk>;
+		};
+	};
+
+};
+
+&prm {
+	wkupaon_cm: wkupaon_cm@1800 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1800 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1800 0x100>;
+
+		wkupaon_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x6c>;
+			#clock-cells = <2>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/efm32gg-dk3750.dts b/arch/arm/boot/dts/efm32gg-dk3750.dts
index c9f3ea29cf9e..adfa559a488b 100644
--- a/arch/arm/boot/dts/efm32gg-dk3750.dts
+++ b/arch/arm/boot/dts/efm32gg-dk3750.dts
@@ -37,7 +37,7 @@
 			};
 
 			eeprom@50 {
-				compatible = "microchip,24c02";
+				compatible = "microchip,24c02", "atmel,24c02";
 				reg = <0x50>;
 				pagesize = <16>;
 			};
diff --git a/arch/arm/boot/dts/ethernut5.dts b/arch/arm/boot/dts/ethernut5.dts
index 123b203be06c..b554f85add41 100644
--- a/arch/arm/boot/dts/ethernut5.dts
+++ b/arch/arm/boot/dts/ethernut5.dts
@@ -36,6 +36,18 @@
 				status = "okay";
 			};
 
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			usart0: serial@fffb0000 {
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/exynos3250-artik5-eval.dts b/arch/arm/boot/dts/exynos3250-artik5-eval.dts
index 4cbfa09c6c4e..20446a846a98 100644
--- a/arch/arm/boot/dts/exynos3250-artik5-eval.dts
+++ b/arch/arm/boot/dts/exynos3250-artik5-eval.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos3250 based ARTIK5 evaluation board device tree source
  *
@@ -6,10 +7,6 @@
  *
  * Device tree source file for Samsung's ARTIK5 evaluation board
  * which is based on Samsung Exynos3250 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/exynos3250-artik5.dtsi b/arch/arm/boot/dts/exynos3250-artik5.dtsi
index 152e0291d0da..0aa577fe9f95 100644
--- a/arch/arm/boot/dts/exynos3250-artik5.dtsi
+++ b/arch/arm/boot/dts/exynos3250-artik5.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos3250 based ARTIK5 module device tree source
  *
@@ -6,10 +7,6 @@
  *
  * Device tree source file for Samsung's ARTIK5 module which is based on
  * Samsung Exynos3250 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include "exynos3250.dtsi"
diff --git a/arch/arm/boot/dts/exynos3250-monk.dts b/arch/arm/boot/dts/exynos3250-monk.dts
index 029eb18590cf..6ffedf4ed9f2 100644
--- a/arch/arm/boot/dts/exynos3250-monk.dts
+++ b/arch/arm/boot/dts/exynos3250-monk.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos3250 based Monk board device tree source
  *
@@ -6,10 +7,6 @@
  *
  * Device tree source file for Samsung's Monk board which is based on
  * Samsung Exynos3250 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/exynos3250-pinctrl.dtsi b/arch/arm/boot/dts/exynos3250-pinctrl.dtsi
index a149f148e659..dff3c6e3aa1f 100644
--- a/arch/arm/boot/dts/exynos3250-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos3250-pinctrl.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos3250 SoCs pin-mux and pin-config device tree source
  *
@@ -6,11 +7,7 @@
  *
  * Samsung's Exynos3250 SoCs pin-mux and pin-config optiosn are listed as device
  * tree nodes are listed in this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/pinctrl/samsung.h>
 
diff --git a/arch/arm/boot/dts/exynos3250-rinato.dts b/arch/arm/boot/dts/exynos3250-rinato.dts
index 3743df4de390..2c3460781cc6 100644
--- a/arch/arm/boot/dts/exynos3250-rinato.dts
+++ b/arch/arm/boot/dts/exynos3250-rinato.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos3250 based Rinato board device tree source
  *
@@ -6,10 +7,6 @@
  *
  * Device tree source file for Samsung's Rinato board which is based on
  * Samsung Exynos3250 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index 2bd3872221a1..b8fb94f5daa8 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos3250 SoC device tree source
  *
@@ -11,10 +12,6 @@
  * Note: This file does not include device nodes for all the controllers in
  * Exynos3250 SoC. As device tree coverage for Exynos3250 increases, additional
  * nodes can be added to this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include "exynos4-cpu-thermal.dtsi"
@@ -164,31 +161,31 @@
 			syscon = <&pmu_system_controller>;
 		};
 
-		pd_cam: cam-power-domain@10023C00 {
+		pd_cam: cam-power-domain@10023c00 {
 			compatible = "samsung,exynos4210-pd";
 			reg = <0x10023C00 0x20>;
 			#power-domain-cells = <0>;
 		};
 
-		pd_mfc: mfc-power-domain@10023C40 {
+		pd_mfc: mfc-power-domain@10023c40 {
 			compatible = "samsung,exynos4210-pd";
 			reg = <0x10023C40 0x20>;
 			#power-domain-cells = <0>;
 		};
 
-		pd_g3d: g3d-power-domain@10023C60 {
+		pd_g3d: g3d-power-domain@10023c60 {
 			compatible = "samsung,exynos4210-pd";
 			reg = <0x10023C60 0x20>;
 			#power-domain-cells = <0>;
 		};
 
-		pd_lcd0: lcd0-power-domain@10023C80 {
+		pd_lcd0: lcd0-power-domain@10023c80 {
 			compatible = "samsung,exynos4210-pd";
 			reg = <0x10023C80 0x20>;
 			#power-domain-cells = <0>;
 		};
 
-		pd_isp: isp-power-domain@10023CA0 {
+		pd_isp: isp-power-domain@10023ca0 {
 			compatible = "samsung,exynos4210-pd";
 			reg = <0x10023CA0 0x20>;
 			#power-domain-cells = <0>;
@@ -204,7 +201,7 @@
 						 <&cmu CLK_FIN_PLL>;
 		};
 
-		cmu_dmc: clock-controller@105C0000 {
+		cmu_dmc: clock-controller@105c0000 {
 			compatible = "samsung,exynos3250-cmu-dmc";
 			reg = <0x105C0000 0x2000>;
 			#clock-cells = <1>;
@@ -219,7 +216,7 @@
 			status = "disabled";
 		};
 
-		tmu: tmu@100C0000 {
+		tmu: tmu@100c0000 {
 			compatible = "samsung,exynos3250-tmu";
 			reg = <0x100C0000 0x100>;
 			interrupts = <GIC_SPI 216 IRQ_TYPE_LEVEL_HIGH>;
@@ -287,7 +284,7 @@
 			status = "disabled";
 		};
 
-		sysmmu_jpeg: sysmmu@11A60000 {
+		sysmmu_jpeg: sysmmu@11a60000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x11a60000 0x1000>;
 			interrupts = <GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>,
@@ -313,7 +310,7 @@
 			status = "disabled";
 		};
 
-		dsi_0: dsi@11C80000 {
+		dsi_0: dsi@11c80000 {
 			compatible = "samsung,exynos3250-mipi-dsi";
 			reg = <0x11C80000 0x10000>;
 			interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
@@ -328,7 +325,7 @@
 			status = "disabled";
 		};
 
-		sysmmu_fimd0: sysmmu@11E20000 {
+		sysmmu_fimd0: sysmmu@11e20000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x11e20000 0x1000>;
 			interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>,
@@ -386,7 +383,7 @@
 			status = "disabled";
 		};
 
-		exynos_usbphy: exynos-usbphy@125B0000 {
+		exynos_usbphy: exynos-usbphy@125b0000 {
 			compatible = "samsung,exynos3250-usb2-phy";
 			reg = <0x125B0000 0x100>;
 			samsung,pmureg-phandle = <&pmu_system_controller>;
@@ -425,7 +422,7 @@
 			};
 		};
 
-		adc: adc@126C0000 {
+		adc: adc@126c0000 {
 			compatible = "samsung,exynos3250-adc",
 				     "samsung,exynos-adc-v2";
 			reg = <0x126C0000 0x100>;
@@ -544,7 +541,7 @@
 			status = "disabled";
 		};
 
-		i2c_4: i2c@138A0000 {
+		i2c_4: i2c@138a0000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "samsung,s3c2440-i2c";
@@ -557,7 +554,7 @@
 			status = "disabled";
 		};
 
-		i2c_5: i2c@138B0000 {
+		i2c_5: i2c@138b0000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "samsung,s3c2440-i2c";
@@ -570,7 +567,7 @@
 			status = "disabled";
 		};
 
-		i2c_6: i2c@138C0000 {
+		i2c_6: i2c@138c0000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "samsung,s3c2440-i2c";
@@ -583,7 +580,7 @@
 			status = "disabled";
 		};
 
-		i2c_7: i2c@138D0000 {
+		i2c_7: i2c@138d0000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "samsung,s3c2440-i2c";
@@ -641,7 +638,7 @@
 			status = "disabled";
 		};
 
-		pwm: pwm@139D0000 {
+		pwm: pwm@139d0000 {
 			compatible = "samsung,exynos4210-pwm";
 			reg = <0x139D0000 0x1000>;
 			interrupts = <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi b/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi
index 735cb2f10817..021d9fc1b492 100644
--- a/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi
+++ b/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device tree sources for Exynos4 thermal zone
  *
  * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #include <dt-bindings/thermal/thermal.h>
diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi
index 4768b086ed67..6d59cc827649 100644
--- a/arch/arm/boot/dts/exynos4.dtsi
+++ b/arch/arm/boot/dts/exynos4.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos4 SoC series common device tree source
  *
@@ -13,10 +14,6 @@
  * Note: This file does not include device nodes for all the controllers in
  * Exynos4 SoCs. As device tree coverage for Exynos4 increases, additional
  * nodes can be added to this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/clock/exynos4.h>
@@ -101,28 +98,28 @@
 		syscon = <&pmu_system_controller>;
 	};
 
-	pd_mfc: mfc-power-domain@10023C40 {
+	pd_mfc: mfc-power-domain@10023c40 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10023C40 0x20>;
 		#power-domain-cells = <0>;
 		label = "MFC";
 	};
 
-	pd_g3d: g3d-power-domain@10023C60 {
+	pd_g3d: g3d-power-domain@10023c60 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10023C60 0x20>;
 		#power-domain-cells = <0>;
 		label = "G3D";
 	};
 
-	pd_lcd0: lcd0-power-domain@10023C80 {
+	pd_lcd0: lcd0-power-domain@10023c80 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10023C80 0x20>;
 		#power-domain-cells = <0>;
 		label = "LCD0";
 	};
 
-	pd_tv: tv-power-domain@10023C20 {
+	pd_tv: tv-power-domain@10023c20 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10023C20 0x20>;
 		#power-domain-cells = <0>;
@@ -130,21 +127,21 @@
 		label = "TV";
 	};
 
-	pd_cam: cam-power-domain@10023C00 {
+	pd_cam: cam-power-domain@10023c00 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10023C00 0x20>;
 		#power-domain-cells = <0>;
 		label = "CAM";
 	};
 
-	pd_gps: gps-power-domain@10023CE0 {
+	pd_gps: gps-power-domain@10023ce0 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10023CE0 0x20>;
 		#power-domain-cells = <0>;
 		label = "GPS";
 	};
 
-	pd_gps_alive: gps-alive-power-domain@10023D00 {
+	pd_gps_alive: gps-alive-power-domain@10023d00 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10023D00 0x20>;
 		#power-domain-cells = <0>;
@@ -184,7 +181,7 @@
 		interrupt-parent = <&gic>;
 	};
 
-	dsi_0: dsi@11C80000 {
+	dsi_0: dsi@11c80000 {
 		compatible = "samsung,exynos4210-mipi-dsi";
 		reg = <0x11C80000 0x10000>;
 		interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
@@ -297,7 +294,7 @@
 		status = "disabled";
 	};
 
-	keypad: keypad@100A0000 {
+	keypad: keypad@100a0000 {
 		compatible = "samsung,s5pv210-keypad";
 		reg = <0x100A0000 0x100>;
 		interrupts = <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
@@ -342,7 +339,7 @@
 		status = "disabled";
 	};
 
-	exynos_usbphy: exynos-usbphy@125B0000 {
+	exynos_usbphy: exynos-usbphy@125b0000 {
 		compatible = "samsung,exynos4210-usb2-phy";
 		reg = <0x125B0000 0x100>;
 		samsung,pmureg-phandle = <&pmu_system_controller>;
@@ -538,7 +535,7 @@
 		status = "disabled";
 	};
 
-	i2c_4: i2c@138A0000 {
+	i2c_4: i2c@138a0000 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "samsung,s3c2440-i2c";
@@ -551,7 +548,7 @@
 		status = "disabled";
 	};
 
-	i2c_5: i2c@138B0000 {
+	i2c_5: i2c@138b0000 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "samsung,s3c2440-i2c";
@@ -564,7 +561,7 @@
 		status = "disabled";
 	};
 
-	i2c_6: i2c@138C0000 {
+	i2c_6: i2c@138c0000 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "samsung,s3c2440-i2c";
@@ -577,7 +574,7 @@
 		status = "disabled";
 	};
 
-	i2c_7: i2c@138D0000 {
+	i2c_7: i2c@138d0000 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "samsung,s3c2440-i2c";
@@ -590,7 +587,7 @@
 		status = "disabled";
 	};
 
-	i2c_8: i2c@138E0000 {
+	i2c_8: i2c@138e0000 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "samsung,s3c2440-hdmiphy-i2c";
@@ -651,7 +648,7 @@
 		status = "disabled";
 	};
 
-	pwm: pwm@139D0000 {
+	pwm: pwm@139d0000 {
 		compatible = "samsung,exynos4210-pwm";
 		reg = <0x139D0000 0x1000>;
 		interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
@@ -720,7 +717,7 @@
 		status = "disabled";
 	};
 
-	tmu: tmu@100C0000 {
+	tmu: tmu@100c0000 {
 		#include "exynos4412-tmu-sensor-conf.dtsi"
 	};
 
@@ -743,7 +740,7 @@
 		iommus = <&sysmmu_rotator>;
 	};
 
-	hdmi: hdmi@12D00000 {
+	hdmi: hdmi@12d00000 {
 		compatible = "samsung,exynos4210-hdmi";
 		reg = <0x12D00000 0x70000>;
 		interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>;
@@ -755,10 +752,11 @@
 		phy = <&hdmi_i2c_phy>;
 		power-domains = <&pd_tv>;
 		samsung,syscon-phandle = <&pmu_system_controller>;
+		#sound-dai-cells = <0>;
 		status = "disabled";
 	};
 
-	hdmicec: cec@100B0000 {
+	hdmicec: cec@100b0000 {
 		compatible = "samsung,s5p-cec";
 		reg = <0x100B0000 0x200>;
 		interrupts = <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>;
@@ -771,7 +769,7 @@
 		status = "disabled";
 	};
 
-	mixer: mixer@12C10000 {
+	mixer: mixer@12c10000 {
 		compatible = "samsung,exynos4210-mixer";
 		interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>;
 		reg = <0x12C10000 0x2100>, <0x12c00000 0x300>;
@@ -910,7 +908,7 @@
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_tv: sysmmu@12E20000 {
+	sysmmu_tv: sysmmu@12e20000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x12E20000 0x1000>;
 		interrupt-parent = <&combiner>;
@@ -921,7 +919,7 @@
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_fimc0: sysmmu@11A20000 {
+	sysmmu_fimc0: sysmmu@11a20000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x11A20000 0x1000>;
 		interrupt-parent = <&combiner>;
@@ -932,7 +930,7 @@
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_fimc1: sysmmu@11A30000 {
+	sysmmu_fimc1: sysmmu@11a30000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x11A30000 0x1000>;
 		interrupt-parent = <&combiner>;
@@ -943,7 +941,7 @@
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_fimc2: sysmmu@11A40000 {
+	sysmmu_fimc2: sysmmu@11a40000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x11A40000 0x1000>;
 		interrupt-parent = <&combiner>;
@@ -954,7 +952,7 @@
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_fimc3: sysmmu@11A50000 {
+	sysmmu_fimc3: sysmmu@11a50000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x11A50000 0x1000>;
 		interrupt-parent = <&combiner>;
@@ -965,7 +963,7 @@
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_jpeg: sysmmu@11A60000 {
+	sysmmu_jpeg: sysmmu@11a60000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x11A60000 0x1000>;
 		interrupt-parent = <&combiner>;
@@ -976,7 +974,7 @@
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_rotator: sysmmu@12A30000 {
+	sysmmu_rotator: sysmmu@12a30000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x12A30000 0x1000>;
 		interrupt-parent = <&combiner>;
@@ -986,7 +984,7 @@
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_fimd0: sysmmu@11E20000 {
+	sysmmu_fimd0: sysmmu@11e20000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x11E20000 0x1000>;
 		interrupt-parent = <&combiner>;
diff --git a/arch/arm/boot/dts/exynos4210-origen.dts b/arch/arm/boot/dts/exynos4210-origen.dts
index 084fcc5574ef..9a310e841d5d 100644
--- a/arch/arm/boot/dts/exynos4210-origen.dts
+++ b/arch/arm/boot/dts/exynos4210-origen.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos4210 based Origen board device tree source
  *
@@ -8,11 +9,7 @@
  *
  * Device tree source file for Insignal's Origen board which is based on
  * Samsung's Exynos4210 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos4210.dtsi"
diff --git a/arch/arm/boot/dts/exynos4210-pinctrl.dtsi b/arch/arm/boot/dts/exynos4210-pinctrl.dtsi
index 82c32d4d83d8..dbe6c052d8c1 100644
--- a/arch/arm/boot/dts/exynos4210-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos4210-pinctrl.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos4210 SoC pin-mux and pin-config device tree source
  *
@@ -8,11 +9,7 @@
  *
  * Samsung's Exynos4210 SoC pin-mux and pin-config optiosn are listed as device
  * tree nodes are listed in this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/pinctrl/samsung.h>
 
diff --git a/arch/arm/boot/dts/exynos4210-smdkv310.dts b/arch/arm/boot/dts/exynos4210-smdkv310.dts
index 9c98a3724396..7a3e621edede 100644
--- a/arch/arm/boot/dts/exynos4210-smdkv310.dts
+++ b/arch/arm/boot/dts/exynos4210-smdkv310.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos4210 based SMDKV310 board device tree source
  *
@@ -8,11 +9,7 @@
  *
  * Device tree source file for Samsung's SMDKV310 board which is based on
  * Samsung's Exynos4210 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos4210.dtsi"
diff --git a/arch/arm/boot/dts/exynos4210-trats.dts b/arch/arm/boot/dts/exynos4210-trats.dts
index 7b6ab7265110..aaade17b140e 100644
--- a/arch/arm/boot/dts/exynos4210-trats.dts
+++ b/arch/arm/boot/dts/exynos4210-trats.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos4210 based Trats board device tree source
  *
@@ -6,11 +7,7 @@
  *
  * Device tree source file for Samsung's Trats board which is based on
  * Samsung's Exynos4210 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos4210.dtsi"
diff --git a/arch/arm/boot/dts/exynos4210-universal_c210.dts b/arch/arm/boot/dts/exynos4210-universal_c210.dts
index acd2b2286ccb..21fff7cd3aa4 100644
--- a/arch/arm/boot/dts/exynos4210-universal_c210.dts
+++ b/arch/arm/boot/dts/exynos4210-universal_c210.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos4210 based Universal C210 board device tree source
  *
@@ -6,11 +7,7 @@
  *
  * Device tree source file for Samsung's Universal C210 board which is based on
  * Samsung's Exynos4210 rev0 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos4210.dtsi"
diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi
index 03dd61f64809..cc978cf28267 100644
--- a/arch/arm/boot/dts/exynos4210.dtsi
+++ b/arch/arm/boot/dts/exynos4210.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos4210 SoC device tree source
  *
@@ -13,11 +14,7 @@
  * Note: This file does not include device nodes for all the controllers in
  * Exynos4210 SoC. As device tree coverage for Exynos4210 increases, additional
  * nodes can be added to this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include "exynos4.dtsi"
 #include "exynos4210-pinctrl.dtsi"
@@ -82,7 +79,7 @@
 		};
 	};
 
-	pd_lcd1: lcd1-power-domain@10023CA0 {
+	pd_lcd1: lcd1-power-domain@10023ca0 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10023CA0 0x20>;
 		#power-domain-cells = <0>;
@@ -156,7 +153,7 @@
 		reg = <0x03860000 0x1000>;
 	};
 
-	tmu: tmu@100C0000 {
+	tmu: tmu@100c0000 {
 		compatible = "samsung,exynos4210-tmu";
 		interrupt-parent = <&combiner>;
 		reg = <0x100C0000 0x100>;
@@ -229,7 +226,7 @@
 		};
 	};
 
-	mixer: mixer@12C10000 {
+	mixer: mixer@12c10000 {
 		clock-names = "mixer", "hdmi", "sclk_hdmi", "vp", "mout_mixer",
 			"sclk_mixer";
 		clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>,
@@ -245,7 +242,7 @@
 		status = "disabled";
 	};
 
-	sysmmu_g2d: sysmmu@12A20000 {
+	sysmmu_g2d: sysmmu@12a20000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x12A20000 0x1000>;
 		interrupt-parent = <&combiner>;
diff --git a/arch/arm/boot/dts/exynos4412-itop-elite.dts b/arch/arm/boot/dts/exynos4412-itop-elite.dts
index d66093084dbb..a4cd4939fe9a 100644
--- a/arch/arm/boot/dts/exynos4412-itop-elite.dts
+++ b/arch/arm/boot/dts/exynos4412-itop-elite.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * TOPEET's Exynos4412 based itop board device tree source
  *
@@ -7,10 +8,6 @@
  *
  * Device tree source file for TOPEET iTop Exynos 4412 core board
  * which is based on Samsung's Exynos4412 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/exynos4412-itop-scp-core.dtsi b/arch/arm/boot/dts/exynos4412-itop-scp-core.dtsi
index bda49b232f7b..ab7affab7f1c 100644
--- a/arch/arm/boot/dts/exynos4412-itop-scp-core.dtsi
+++ b/arch/arm/boot/dts/exynos4412-itop-scp-core.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * TOPEET's Exynos4412 based itop board device tree source
  *
@@ -7,10 +8,6 @@
  *
  * Device tree source file for TOPEET iTop Exynos 4412 SCP package core
  * board which is based on Samsung's Exynos4412 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/clock/samsung,s2mps11.h>
diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
index a21be71000c1..556ea78b8e32 100644
--- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
+++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Common definition for Hardkernel's Exynos4412 based ODROID-X/X2/U2/U3 boards
  * device tree source
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
 */
 
 #include <dt-bindings/sound/samsung-i2s.h>
diff --git a/arch/arm/boot/dts/exynos4412-odroidu3.dts b/arch/arm/boot/dts/exynos4412-odroidu3.dts
index 44a4de08466b..bdcd4523cc1c 100644
--- a/arch/arm/boot/dts/exynos4412-odroidu3.dts
+++ b/arch/arm/boot/dts/exynos4412-odroidu3.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Hardkernel's Exynos4412 based ODROID-U3 board device tree source
  *
@@ -5,11 +6,7 @@
  *
  * Device tree source file for Hardkernel's ODROID-U3 board which is based
  * on Samsung's Exynos4412 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos4412-odroid-common.dtsi"
diff --git a/arch/arm/boot/dts/exynos4412-odroidx.dts b/arch/arm/boot/dts/exynos4412-odroidx.dts
index acf48a018e5e..2dff129bc2ad 100644
--- a/arch/arm/boot/dts/exynos4412-odroidx.dts
+++ b/arch/arm/boot/dts/exynos4412-odroidx.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Hardkernel's Exynos4412 based ODROID-X board device tree source
  *
@@ -5,11 +6,7 @@
  *
  * Device tree source file for Hardkernel's ODROID-X board which is based
  * on Samsung's Exynos4412 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos4412-odroid-common.dtsi"
diff --git a/arch/arm/boot/dts/exynos4412-odroidx2.dts b/arch/arm/boot/dts/exynos4412-odroidx2.dts
index d867b2ee95ca..f4b68c75c962 100644
--- a/arch/arm/boot/dts/exynos4412-odroidx2.dts
+++ b/arch/arm/boot/dts/exynos4412-odroidx2.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Hardkernel's Exynos4412 based ODROID-X2 board device tree source
  *
@@ -5,11 +6,7 @@
  *
  * Device tree source file for Hardkernel's ODROID-X2 board which is based
  * on Samsung's Exynos4412 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include "exynos4412-odroidx.dts"
 #include "exynos4412-prime.dtsi"
diff --git a/arch/arm/boot/dts/exynos4412-origen.dts b/arch/arm/boot/dts/exynos4412-origen.dts
index b0b5ec7903a5..1514f0dbaff8 100644
--- a/arch/arm/boot/dts/exynos4412-origen.dts
+++ b/arch/arm/boot/dts/exynos4412-origen.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Insignal's Exynos4412 based Origen board device tree source
  *
@@ -6,11 +7,7 @@
  *
  * Device tree source file for Insignal's Origen board which is based on
  * Samsung's Exynos4412 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos4412.dtsi"
diff --git a/arch/arm/boot/dts/exynos4412-pinctrl.dtsi b/arch/arm/boot/dts/exynos4412-pinctrl.dtsi
index 4eebd4721a5f..e8dd5f2d976f 100644
--- a/arch/arm/boot/dts/exynos4412-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos4412-pinctrl.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos4412 SoCs pin-mux and pin-config device tree source
  *
@@ -6,11 +7,7 @@
  *
  * Samsung's Exynos4412 SoCs pin-mux and pin-config optiosn are listed as device
  * tree nodes are listed in this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/pinctrl/samsung.h>
 
@@ -925,7 +922,7 @@
 		};
 	};
 
-	pinctrl_3: pinctrl@106E0000 {
+	pinctrl_3: pinctrl@106e0000 {
 		gpv0: gpv0 {
 			gpio-controller;
 			#gpio-cells = <2>;
diff --git a/arch/arm/boot/dts/exynos4412-ppmu-common.dtsi b/arch/arm/boot/dts/exynos4412-ppmu-common.dtsi
index 16e4b77d8cb1..3a3b2fafefdd 100644
--- a/arch/arm/boot/dts/exynos4412-ppmu-common.dtsi
+++ b/arch/arm/boot/dts/exynos4412-ppmu-common.dtsi
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device tree sources for Exynos4412 PPMU common device tree
  *
  * Copyright (C) 2015 Samsung Electronics
  * Author: Chanwoo Choi <cw00.choi@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 &ppmu_dmc0 {
diff --git a/arch/arm/boot/dts/exynos4412-prime.dtsi b/arch/arm/boot/dts/exynos4412-prime.dtsi
index a67bd953d754..8e7a7fb98124 100644
--- a/arch/arm/boot/dts/exynos4412-prime.dtsi
+++ b/arch/arm/boot/dts/exynos4412-prime.dtsi
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos4412 Prime SoC device tree source
  *
  * Copyright (c) 2016 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /*
diff --git a/arch/arm/boot/dts/exynos4412-smdk4412.dts b/arch/arm/boot/dts/exynos4412-smdk4412.dts
index 7fcb43431b59..5c5c2887c14f 100644
--- a/arch/arm/boot/dts/exynos4412-smdk4412.dts
+++ b/arch/arm/boot/dts/exynos4412-smdk4412.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos4412 based SMDK board device tree source
  *
@@ -6,11 +7,7 @@
  *
  * Device tree source file for Samsung's SMDK4412 board which is based on
  * Samsung's Exynos4412 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos4412.dtsi"
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index 220cdf109405..f285790e8e04 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -300,6 +300,13 @@
 
 	};
 
+	wlan_pwrseq: sdhci3-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		reset-gpios = <&gpj0 0 GPIO_ACTIVE_LOW>;
+		clocks = <&max77686 MAX77686_CLK_PMIC>;
+		clock-names = "ext_clock";
+	};
+
 	sound {
 		compatible = "samsung,trats2-audio";
 		samsung,i2s-controller = <&i2s0>;
@@ -454,7 +461,7 @@
 		reg = <0>;
 		vdd3-supply = <&lcd_vdd3_reg>;
 		vci-supply = <&ldo25_reg>;
-		reset-gpios = <&gpy4 5 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpf2 1 GPIO_ACTIVE_HIGH>;
 		power-on-delay= <50>;
 		reset-delay = <100>;
 		init-delay = <100>;
@@ -1350,6 +1357,26 @@
 	status = "okay";
 };
 
+&sdhci_3 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	non-removable;
+	bus-width = <4>;
+
+	mmc-pwrseq = <&wlan_pwrseq>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sd3_clk &sd3_cmd &sd3_bus4>;
+	status = "okay";
+
+	brcmf: wifi@1 {
+		reg = <1>;
+		compatible = "brcm,bcm4329-fmac";
+		interrupt-parent = <&gpx2>;
+		interrupts = <5 IRQ_TYPE_NONE>;
+		interrupt-names = "host-wake";
+	};
+};
+
 &serial_0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/exynos4412.dtsi b/arch/arm/boot/dts/exynos4412.dtsi
index b255ac55b1c1..e4ad2fc0329e 100644
--- a/arch/arm/boot/dts/exynos4412.dtsi
+++ b/arch/arm/boot/dts/exynos4412.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos4412 SoC device tree source
  *
@@ -11,11 +12,7 @@
  * Note: This file does not include device nodes for all the controllers in
  * Exynos4412 SoC. As device tree coverage for Exynos4412 increases, additional
  * nodes can be added to this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include "exynos4.dtsi"
 #include "exynos4412-pinctrl.dtsi"
@@ -38,7 +35,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu0: cpu@A00 {
+		cpu0: cpu@a00 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0xA00>;
@@ -50,21 +47,21 @@
 			#cooling-cells = <2>; /* min followed by max */
 		};
 
-		cpu@A01 {
+		cpu@a01 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0xA01>;
 			operating-points-v2 = <&cpu0_opp_table>;
 		};
 
-		cpu@A02 {
+		cpu@a02 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0xA02>;
 			operating-points-v2 = <&cpu0_opp_table>;
 		};
 
-		cpu@A03 {
+		cpu@a03 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0xA03>;
@@ -168,7 +165,7 @@
 		};
 	};
 
-	pd_isp: isp-power-domain@10023CA0 {
+	pd_isp: isp-power-domain@10023ca0 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10023CA0 0x20>;
 		#power-domain-cells = <0>;
@@ -191,10 +188,19 @@
 
 	clock: clock-controller@10030000 {
 		compatible = "samsung,exynos4412-clock";
-		reg = <0x10030000 0x20000>;
+		reg = <0x10030000 0x18000>;
 		#clock-cells = <1>;
 	};
 
+	isp_clock: clock-controller@10048000 {
+		compatible = "samsung,exynos4412-isp-clock";
+		reg = <0x10048000 0x1000>;
+		#clock-cells = <1>;
+		power-domains = <&pd_isp>;
+		clocks = <&clock CLK_ACLK200>, <&clock CLK_ACLK400_MCUISP>;
+		clock-names = "aclk200", "aclk400_mcuisp";
+	};
+
 	mct@10050000 {
 		compatible = "samsung,exynos4412-mct";
 		reg = <0x10050000 0x800>;
@@ -224,7 +230,7 @@
 		samsung,syscon-phandle = <&pmu_system_controller>;
 	};
 
-	adc: adc@126C0000 {
+	adc: adc@126c0000 {
 		compatible = "samsung,exynos-adc-v1";
 		reg = <0x126C0000 0x100>;
 		interrupt-parent = <&combiner>;
@@ -257,18 +263,18 @@
 			reg = <0x12390000 0x1000>;
 			interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
 			power-domains = <&pd_isp>;
-			clocks = <&clock CLK_FIMC_LITE0>;
+			clocks = <&isp_clock CLK_ISP_FIMC_LITE0>;
 			clock-names = "flite";
 			iommus = <&sysmmu_fimc_lite0>;
 			status = "disabled";
 		};
 
-		fimc_lite_1: fimc-lite@123A0000 {
+		fimc_lite_1: fimc-lite@123a0000 {
 			compatible = "samsung,exynos4212-fimc-lite";
 			reg = <0x123A0000 0x1000>;
 			interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
 			power-domains = <&pd_isp>;
-			clocks = <&clock CLK_FIMC_LITE1>;
+			clocks = <&isp_clock CLK_ISP_FIMC_LITE1>;
 			clock-names = "flite";
 			iommus = <&sysmmu_fimc_lite1>;
 			status = "disabled";
@@ -280,29 +286,35 @@
 			interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
 			power-domains = <&pd_isp>;
-			clocks = <&clock CLK_FIMC_LITE0>,
-				 <&clock CLK_FIMC_LITE1>, <&clock CLK_PPMUISPX>,
-				 <&clock CLK_PPMUISPMX>,
+			clocks = <&isp_clock CLK_ISP_FIMC_LITE0>,
+				 <&isp_clock CLK_ISP_FIMC_LITE1>,
+				 <&isp_clock CLK_ISP_PPMUISPX>,
+				 <&isp_clock CLK_ISP_PPMUISPMX>,
+				 <&isp_clock CLK_ISP_FIMC_ISP>,
+				 <&isp_clock CLK_ISP_FIMC_DRC>,
+				 <&isp_clock CLK_ISP_FIMC_FD>,
+				 <&isp_clock CLK_ISP_MCUISP>,
+				 <&isp_clock CLK_ISP_GICISP>,
+				 <&isp_clock CLK_ISP_MCUCTL_ISP>,
+				 <&isp_clock CLK_ISP_PWM_ISP>,
+				 <&isp_clock CLK_ISP_DIV_ISP0>,
+				 <&isp_clock CLK_ISP_DIV_ISP1>,
+				 <&isp_clock CLK_ISP_DIV_MCUISP0>,
+				 <&isp_clock CLK_ISP_DIV_MCUISP1>,
 				 <&clock CLK_MOUT_MPLL_USER_T>,
-				 <&clock CLK_FIMC_ISP>, <&clock CLK_FIMC_DRC>,
-				 <&clock CLK_FIMC_FD>, <&clock CLK_MCUISP>,
-				 <&clock CLK_GICISP>, <&clock CLK_MCUCTL_ISP>,
-				 <&clock CLK_PWM_ISP>,
-				 <&clock CLK_DIV_ISP0>, <&clock CLK_DIV_ISP1>,
-				 <&clock CLK_DIV_MCUISP0>,
-				 <&clock CLK_DIV_MCUISP1>,
-				 <&clock CLK_UART_ISP_SCLK>,
-				 <&clock CLK_ACLK200>, <&clock CLK_DIV_ACLK200>,
+				 <&clock CLK_ACLK200>,
 				 <&clock CLK_ACLK400_MCUISP>,
-				 <&clock CLK_DIV_ACLK400_MCUISP>;
+				 <&clock CLK_DIV_ACLK200>,
+				 <&clock CLK_DIV_ACLK400_MCUISP>,
+				 <&clock CLK_UART_ISP_SCLK>;
 			clock-names = "lite0", "lite1", "ppmuispx",
-				      "ppmuispmx", "mpll", "isp",
+				      "ppmuispmx", "isp",
 				      "drc", "fd", "mcuisp",
 				      "gicisp", "mcuctl_isp", "pwm_isp",
 				      "ispdiv0", "ispdiv1", "mcuispdiv0",
-				      "mcuispdiv1", "uart", "aclk200",
-				      "div_aclk200", "aclk400mcuisp",
-				      "div_aclk400mcuisp";
+				      "mcuispdiv1", "mpll", "aclk200",
+				      "aclk400mcuisp", "div_aclk200",
+				      "div_aclk400mcuisp", "uart";
 			iommus = <&sysmmu_fimc_isp>, <&sysmmu_fimc_drc>,
 				 <&sysmmu_fimc_fd>, <&sysmmu_fimc_mcuctl>;
 			iommu-names = "isp", "drc", "fd", "mcuctl";
@@ -318,7 +330,7 @@
 			i2c1_isp: i2c-isp@12140000 {
 				compatible = "samsung,exynos4212-i2c-isp";
 				reg = <0x12140000 0x100>;
-				clocks = <&clock CLK_I2C1_ISP>;
+				clocks = <&isp_clock CLK_ISP_I2C1_ISP>;
 				clock-names = "i2c_isp";
 				#address-cells = <1>;
 				#size-cells = <0>;
@@ -355,7 +367,7 @@
 		interrupts = <16 2>;
 		power-domains = <&pd_isp>;
 		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_ISP>;
+		clocks = <&isp_clock CLK_ISP_SMMU_ISP>;
 		#iommu-cells = <0>;
 	};
 
@@ -366,51 +378,53 @@
 		interrupts = <16 3>;
 		power-domains = <&pd_isp>;
 		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_DRC>;
+		clocks = <&isp_clock CLK_ISP_SMMU_DRC>;
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_fimc_fd: sysmmu@122A0000 {
+	sysmmu_fimc_fd: sysmmu@122a0000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x122A0000 0x1000>;
 		interrupt-parent = <&combiner>;
 		interrupts = <16 4>;
 		power-domains = <&pd_isp>;
 		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_FD>;
+		clocks = <&isp_clock CLK_ISP_SMMU_FD>;
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_fimc_mcuctl: sysmmu@122B0000 {
+	sysmmu_fimc_mcuctl: sysmmu@122b0000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x122B0000 0x1000>;
 		interrupt-parent = <&combiner>;
 		interrupts = <16 5>;
 		power-domains = <&pd_isp>;
 		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_ISPCX>;
+		clocks = <&isp_clock CLK_ISP_SMMU_ISPCX>;
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_fimc_lite0: sysmmu@123B0000 {
+	sysmmu_fimc_lite0: sysmmu@123b0000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x123B0000 0x1000>;
 		interrupt-parent = <&combiner>;
 		interrupts = <16 0>;
 		power-domains = <&pd_isp>;
 		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_LITE0>, <&clock CLK_FIMC_LITE0>;
+		clocks = <&isp_clock CLK_ISP_SMMU_LITE0>,
+			 <&isp_clock CLK_ISP_FIMC_LITE0>;
 		#iommu-cells = <0>;
 	};
 
-	sysmmu_fimc_lite1: sysmmu@123C0000 {
+	sysmmu_fimc_lite1: sysmmu@123c0000 {
 		compatible = "samsung,exynos-sysmmu";
 		reg = <0x123C0000 0x1000>;
 		interrupt-parent = <&combiner>;
 		interrupts = <16 1>;
 		power-domains = <&pd_isp>;
 		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_LITE1>, <&clock CLK_FIMC_LITE1>;
+		clocks = <&isp_clock CLK_ISP_SMMU_LITE1>,
+			 <&isp_clock CLK_ISP_FIMC_LITE1>;
 		#iommu-cells = <0>;
 	};
 
diff --git a/arch/arm/boot/dts/exynos5.dtsi b/arch/arm/boot/dts/exynos5.dtsi
index 66d22521c976..f8d7de1144f1 100644
--- a/arch/arm/boot/dts/exynos5.dtsi
+++ b/arch/arm/boot/dts/exynos5.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos5 SoC series common device tree source
  *
@@ -7,10 +8,6 @@
  * Samsung's Exynos5 SoC series device nodes are listed in this file. Particular
  * SoCs from Exynos5 series can include this file and provide values for SoCs
  * specfic bindings.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/interrupt-controller/arm-gic.h>
@@ -106,31 +103,31 @@
 			reg = <0x10050000 0x5000>;
 		};
 
-		serial_0: serial@12C00000 {
+		serial_0: serial@12c00000 {
 			compatible = "samsung,exynos4210-uart";
 			reg = <0x12C00000 0x100>;
 			interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
-		serial_1: serial@12C10000 {
+		serial_1: serial@12c10000 {
 			compatible = "samsung,exynos4210-uart";
 			reg = <0x12C10000 0x100>;
 			interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
-		serial_2: serial@12C20000 {
+		serial_2: serial@12c20000 {
 			compatible = "samsung,exynos4210-uart";
 			reg = <0x12C20000 0x100>;
 			interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
-		serial_3: serial@12C30000 {
+		serial_3: serial@12c30000 {
 			compatible = "samsung,exynos4210-uart";
 			reg = <0x12C30000 0x100>;
 			interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
-		i2c_0: i2c@12C60000 {
+		i2c_0: i2c@12c60000 {
 			compatible = "samsung,s3c2440-i2c";
 			reg = <0x12C60000 0x100>;
 			interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>;
@@ -140,7 +137,7 @@
 			status = "disabled";
 		};
 
-		i2c_1: i2c@12C70000 {
+		i2c_1: i2c@12c70000 {
 			compatible = "samsung,s3c2440-i2c";
 			reg = <0x12C70000 0x100>;
 			interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>;
@@ -150,7 +147,7 @@
 			status = "disabled";
 		};
 
-		i2c_2: i2c@12C80000 {
+		i2c_2: i2c@12c80000 {
 			compatible = "samsung,s3c2440-i2c";
 			reg = <0x12C80000 0x100>;
 			interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
@@ -160,7 +157,7 @@
 			status = "disabled";
 		};
 
-		i2c_3: i2c@12C90000 {
+		i2c_3: i2c@12c90000 {
 			compatible = "samsung,s3c2440-i2c";
 			reg = <0x12C90000 0x100>;
 			interrupts = <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>;
@@ -170,14 +167,14 @@
 			status = "disabled";
 		};
 
-		pwm: pwm@12DD0000 {
+		pwm: pwm@12dd0000 {
 			compatible = "samsung,exynos4210-pwm";
 			reg = <0x12DD0000 0x100>;
 			samsung,pwm-outputs = <0>, <1>, <2>, <3>;
 			#pwm-cells = <3>;
 		};
 
-		rtc: rtc@101E0000 {
+		rtc: rtc@101e0000 {
 			compatible = "samsung,s3c6410-rtc";
 			reg = <0x101E0000 0x100>;
 			interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>,
@@ -195,7 +192,7 @@
 			status = "disabled";
 		};
 
-		dp: dp-controller@145B0000 {
+		dp: dp-controller@145b0000 {
 			compatible = "samsung,exynos5-dp";
 			reg = <0x145B0000 0x1000>;
 			interrupts = <10 3>;
@@ -204,5 +201,28 @@
 			#size-cells = <0>;
 			status = "disabled";
 		};
+
+		sss: sss@10830000 {
+			compatible = "samsung,exynos4210-secss";
+			reg = <0x10830000 0x300>;
+			interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		prng: rng@10830400 {
+		      compatible = "samsung,exynos5250-prng";
+		      reg = <0x10830400 0x200>;
+		};
+
+		trng: rng@10830600 {
+		      compatible = "samsung,exynos5250-trng";
+		      reg = <0x10830600 0x100>;
+		};
+
+		g2d: g2d@10850000 {
+			compatible = "samsung,exynos5250-g2d";
+			reg = <0x10850000 0x1000>;
+			interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/exynos5250-arndale.dts b/arch/arm/boot/dts/exynos5250-arndale.dts
index 0efd678b8251..7a8a5c55701a 100644
--- a/arch/arm/boot/dts/exynos5250-arndale.dts
+++ b/arch/arm/boot/dts/exynos5250-arndale.dts
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos5250 based Arndale board device tree source
  *
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/exynos5250-pinctrl.dtsi b/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
index 1fd122db18e6..6ff6dea29d44 100644
--- a/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos5250 SoC pin-mux and pin-config device tree source
  *
@@ -6,11 +7,7 @@
  *
  * Samsung's Exynos5250 SoC pin-mux and pin-config optiosn are listed as device
  * tree nodes are listed in this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/pinctrl/samsung.h>
 
diff --git a/arch/arm/boot/dts/exynos5250-smdk5250.dts b/arch/arm/boot/dts/exynos5250-smdk5250.dts
index 1e3f9627766c..d5e66189ed2a 100644
--- a/arch/arm/boot/dts/exynos5250-smdk5250.dts
+++ b/arch/arm/boot/dts/exynos5250-smdk5250.dts
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG SMDK5250 board device tree source
  *
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/exynos5250-snow-common.dtsi b/arch/arm/boot/dts/exynos5250-snow-common.dtsi
index 2e7175d2b1b8..59cf1b202849 100644
--- a/arch/arm/boot/dts/exynos5250-snow-common.dtsi
+++ b/arch/arm/boot/dts/exynos5250-snow-common.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Google Snow board device tree source
  *
  * Copyright (c) 2012 Google, Inc
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/gpio/gpio.h>
diff --git a/arch/arm/boot/dts/exynos5250-snow-rev5.dts b/arch/arm/boot/dts/exynos5250-snow-rev5.dts
index 90560c316f64..0348b1c49a69 100644
--- a/arch/arm/boot/dts/exynos5250-snow-rev5.dts
+++ b/arch/arm/boot/dts/exynos5250-snow-rev5.dts
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Google Snow Rev 5+ board device tree source
  *
  * Copyright (c) 2012 Google, Inc
  * Copyright (c) 2015 Samsung Electronics Co., Ltd.
  *             http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/exynos5250-snow.dts b/arch/arm/boot/dts/exynos5250-snow.dts
index df48f2cc96f7..4827cb506fa3 100644
--- a/arch/arm/boot/dts/exynos5250-snow.dts
+++ b/arch/arm/boot/dts/exynos5250-snow.dts
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Google Snow board device tree source
  *
  * Copyright (c) 2012 Google, Inc
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/exynos5250-spring.dts b/arch/arm/boot/dts/exynos5250-spring.dts
index 47dbc50546c1..3d501926c227 100644
--- a/arch/arm/boot/dts/exynos5250-spring.dts
+++ b/arch/arm/boot/dts/exynos5250-spring.dts
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Google Spring board device tree source
  *
  * Copyright (c) 2013 Google, Inc
  * Copyright (c) 2014 SUSE LINUX Products GmbH
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index 5286084e1032..56626d1a4235 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG EXYNOS5250 SoC device tree source
  *
@@ -11,11 +12,7 @@
  * Note: This file does not include device nodes for all the controllers in
  * EXYNOS5250 SoC. As device tree coverage for EXYNOS5250 increases,
  * additional nodes can be added to this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/clock/exynos5250.h>
 #include "exynos5.dtsi"
@@ -111,21 +108,28 @@
 			};
 		};
 
-		pd_gsc: gsc-power-domain@10044000 {
+		pd_gsc: power-domain@10044000 {
 			compatible = "samsung,exynos4210-pd";
 			reg = <0x10044000 0x20>;
 			#power-domain-cells = <0>;
 			label = "GSC";
 		};
 
-		pd_mfc: mfc-power-domain@10044040 {
+		pd_mfc: power-domain@10044040 {
 			compatible = "samsung,exynos4210-pd";
 			reg = <0x10044040 0x20>;
 			#power-domain-cells = <0>;
 			label = "MFC";
 		};
 
-		pd_disp1: disp1-power-domain@100440A0 {
+		pd_g3d: power-domain@10044060 {
+			compatible = "samsung,exynos4210-pd";
+			reg = <0x10044060 0x20>;
+			#power-domain-cells = <0>;
+			label = "G3D";
+		};
+
+		pd_disp1: power-domain@100440a0 {
 			compatible = "samsung,exynos4210-pd";
 			reg = <0x100440A0 0x20>;
 			#power-domain-cells = <0>;
@@ -136,6 +140,13 @@
 			clock-names = "oscclk", "clk0", "clk1";
 		};
 
+		pd_mau: power-domain@100440c0 {
+			compatible = "samsung,exynos4210-pd";
+			reg = <0x100440C0 0x20>;
+			#power-domain-cells = <0>;
+			label = "MAU";
+		};
+
 		clock: clock-controller@10010000 {
 			compatible = "samsung,exynos5250-clock";
 			reg = <0x10010000 0x30000>;
@@ -149,6 +160,7 @@
 			clocks = <&clock CLK_FIN_PLL>, <&clock CLK_FOUT_EPLL>,
 				 <&clock CLK_SCLK_AUDIO0>, <&clock CLK_DIV_PCM0>;
 			clock-names = "pll_ref", "pll_in", "sclk_audio", "sclk_pcm_in";
+			power-domains = <&pd_mau>;
 		};
 
 		timer {
@@ -165,7 +177,7 @@
 			clock-frequency = <24000000>;
 		};
 
-		mct@101C0000 {
+		mct@101c0000 {
 			compatible = "samsung,exynos4210-mct";
 			reg = <0x101C0000 0x800>;
 			interrupt-controller;
@@ -223,6 +235,7 @@
 			compatible = "samsung,exynos5250-pinctrl";
 			reg = <0x03860000 0x1000>;
 			interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>;
+			power-domains = <&pd_mau>;
 		};
 
 		pmu_system_controller: system-controller@10040000 {
@@ -236,7 +249,7 @@
 			interrupt-parent = <&gic>;
 		};
 
-		watchdog@101D0000 {
+		watchdog@101d0000 {
 			compatible = "samsung,exynos5250-wdt";
 			reg = <0x101D0000 0x100>;
 			interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
@@ -245,15 +258,6 @@
 			samsung,syscon-phandle = <&pmu_system_controller>;
 		};
 
-		g2d@10850000 {
-			compatible = "samsung,exynos5250-g2d";
-			reg = <0x10850000 0x1000>;
-			interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&clock CLK_G2D>;
-			clock-names = "fimg2d";
-			iommus = <&sysmmu_g2d>;
-		};
-
 		mfc: codec@11000000 {
 			compatible = "samsung,mfc-v6";
 			reg = <0x11000000 0x10000>;
@@ -265,7 +269,7 @@
 			iommu-names = "left", "right";
 		};
 
-		rotator: rotator@11C00000 {
+		rotator: rotator@11c00000 {
 			compatible = "samsung,exynos5250-rotator";
 			reg = <0x11C00000 0x64>;
 			interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
@@ -283,7 +287,7 @@
 			#include "exynos4412-tmu-sensor-conf.dtsi"
 		};
 
-		sata: sata@122F0000 {
+		sata: sata@122f0000 {
 			compatible = "snps,dwc-ahci";
 			samsung,sata-freq = <66>;
 			reg = <0x122F0000 0x1ff>;
@@ -306,7 +310,7 @@
 		};
 
 		/* i2c_0-3 are defined in exynos5.dtsi */
-		i2c_4: i2c@12CA0000 {
+		i2c_4: i2c@12ca0000 {
 			compatible = "samsung,s3c2440-i2c";
 			reg = <0x12CA0000 0x100>;
 			interrupts = <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>;
@@ -319,7 +323,7 @@
 			status = "disabled";
 		};
 
-		i2c_5: i2c@12CB0000 {
+		i2c_5: i2c@12cb0000 {
 			compatible = "samsung,s3c2440-i2c";
 			reg = <0x12CB0000 0x100>;
 			interrupts = <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>;
@@ -332,7 +336,7 @@
 			status = "disabled";
 		};
 
-		i2c_6: i2c@12CC0000 {
+		i2c_6: i2c@12cc0000 {
 			compatible = "samsung,s3c2440-i2c";
 			reg = <0x12CC0000 0x100>;
 			interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
@@ -345,7 +349,7 @@
 			status = "disabled";
 		};
 
-		i2c_7: i2c@12CD0000 {
+		i2c_7: i2c@12cd0000 {
 			compatible = "samsung,s3c2440-i2c";
 			reg = <0x12CD0000 0x100>;
 			interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
@@ -358,7 +362,7 @@
 			status = "disabled";
 		};
 
-		i2c_8: i2c@12CE0000 {
+		i2c_8: i2c@12ce0000 {
 			compatible = "samsung,s3c2440-hdmiphy-i2c";
 			reg = <0x12CE0000 0x1000>;
 			interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
@@ -374,7 +378,7 @@
 			};
 		};
 
-		i2c_9: i2c@121D0000 {
+		i2c_9: i2c@121d0000 {
 			compatible = "samsung,exynos5-sata-phy-i2c";
 			reg = <0x121D0000 0x100>;
 			#address-cells = <1>;
@@ -495,9 +499,10 @@
 			samsung,idma-addr = <0x03000000>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&i2s0_bus>;
+			power-domains = <&pd_mau>;
 		};
 
-		i2s1: i2s@12D60000 {
+		i2s1: i2s@12d60000 {
 			compatible = "samsung,s3c6410-i2s";
 			status = "disabled";
 			reg = <0x12D60000 0x100>;
@@ -508,9 +513,10 @@
 			clock-names = "iis", "i2s_opclk0";
 			pinctrl-names = "default";
 			pinctrl-0 = <&i2s1_bus>;
+			power-domains = <&pd_mau>;
 		};
 
-		i2s2: i2s@12D70000 {
+		i2s2: i2s@12d70000 {
 			compatible = "samsung,s3c6410-i2s";
 			status = "disabled";
 			reg = <0x12D70000 0x100>;
@@ -521,6 +527,7 @@
 			clock-names = "iis", "i2s_opclk0";
 			pinctrl-names = "default";
 			pinctrl-0 = <&i2s2_bus>;
+			power-domains = <&pd_mau>;
 		};
 
 		usb_dwc3 {
@@ -596,7 +603,7 @@
 			interrupt-parent = <&gic>;
 			ranges;
 
-			pdma0: pdma@121A0000 {
+			pdma0: pdma@121a0000 {
 				compatible = "arm,pl330", "arm,primecell";
 				reg = <0x121A0000 0x1000>;
 				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
@@ -607,7 +614,7 @@
 				#dma-requests = <32>;
 			};
 
-			pdma1: pdma@121B0000 {
+			pdma1: pdma@121b0000 {
 				compatible = "arm,pl330", "arm,primecell";
 				reg = <0x121B0000 0x1000>;
 				interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
@@ -629,7 +636,7 @@
 				#dma-requests = <1>;
 			};
 
-			mdma1: mdma@11C10000 {
+			mdma1: mdma@11c10000 {
 				compatible = "arm,pl330", "arm,primecell";
 				reg = <0x11C10000 0x1000>;
 				interrupts = <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>;
@@ -696,7 +703,7 @@
 			status = "disabled";
 		};
 
-		hdmicec: cec@101B0000 {
+		hdmicec: cec@101b0000 {
 			compatible = "samsung,s5p-cec";
 			reg = <0x101B0000 0x200>;
 			interrupts = <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>;
@@ -727,7 +734,7 @@
 			#phy-cells = <0>;
 		};
 
-		adc: adc@12D10000 {
+		adc: adc@12d10000 {
 			compatible = "samsung,exynos-adc-v1";
 			reg = <0x12D10000 0x100>;
 			interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
@@ -739,15 +746,7 @@
 			status = "disabled";
 		};
 
-		sss@10830000 {
-			compatible = "samsung,exynos4210-secss";
-			reg = <0x10830000 0x300>;
-			interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&clock CLK_SSS>;
-			clock-names = "secss";
-		};
-
-		sysmmu_g2d: sysmmu@10A60000 {
+		sysmmu_g2d: sysmmu@10a60000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x10A60000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -779,7 +778,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_rotator: sysmmu@11D40000 {
+		sysmmu_rotator: sysmmu@11d40000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x11D40000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -789,7 +788,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_jpeg: sysmmu@11F20000 {
+		sysmmu_jpeg: sysmmu@11f20000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x11F20000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -820,7 +819,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_fimc_fd: sysmmu@132A0000 {
+		sysmmu_fimc_fd: sysmmu@132a0000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x132A0000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -850,7 +849,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_fimc_mcuctl: sysmmu@132B0000 {
+		sysmmu_fimc_mcuctl: sysmmu@132b0000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x132B0000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -860,7 +859,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_fimc_odc: sysmmu@132C0000 {
+		sysmmu_fimc_odc: sysmmu@132c0000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x132C0000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -870,7 +869,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_fimc_dis0: sysmmu@132D0000 {
+		sysmmu_fimc_dis0: sysmmu@132d0000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x132D0000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -890,7 +889,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_fimc_3dnr: sysmmu@132F0000 {
+		sysmmu_fimc_3dnr: sysmmu@132f0000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x132F0000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -900,7 +899,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_fimc_lite0: sysmmu@13C40000 {
+		sysmmu_fimc_lite0: sysmmu@13c40000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x13C40000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -911,7 +910,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_fimc_lite1: sysmmu@13C50000 {
+		sysmmu_fimc_lite1: sysmmu@13c50000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x13C50000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -922,7 +921,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_gsc0: sysmmu@13E80000 {
+		sysmmu_gsc0: sysmmu@13e80000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x13E80000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -933,7 +932,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_gsc1: sysmmu@13E90000 {
+		sysmmu_gsc1: sysmmu@13e90000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x13E90000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -944,7 +943,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_gsc2: sysmmu@13EA0000 {
+		sysmmu_gsc2: sysmmu@13ea0000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x13EA0000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -955,7 +954,7 @@
 			#iommu-cells = <0>;
 		};
 
-		sysmmu_gsc3: sysmmu@13EB0000 {
+		sysmmu_gsc3: sysmmu@13eb0000 {
 			compatible = "samsung,exynos-sysmmu";
 			reg = <0x13EB0000 0x1000>;
 			interrupt-parent = <&combiner>;
@@ -1024,6 +1023,13 @@
 	iommus = <&sysmmu_fimd1>;
 };
 
+&g2d {
+	iommus = <&sysmmu_g2d>;
+	clocks = <&clock CLK_G2D>;
+	clock-names = "fimg2d";
+	status = "okay";
+};
+
 &i2c_0 {
 	clocks = <&clock CLK_I2C0>;
 	clock-names = "i2c";
@@ -1052,6 +1058,11 @@
 	pinctrl-0 = <&i2c3_bus>;
 };
 
+&prng {
+	clocks = <&clock CLK_SSS>;
+	clock-names = "secss";
+};
+
 &pwm {
 	clocks = <&clock CLK_PWM>;
 	clock-names = "timers";
@@ -1092,4 +1103,14 @@
 	dma-names = "rx", "tx";
 };
 
+&sss {
+	clocks = <&clock CLK_SSS>;
+	clock-names = "secss";
+};
+
+&trng {
+	clocks = <&clock CLK_SSS>;
+	clock-names = "secss";
+};
+
 #include "exynos5250-pinctrl.dtsi"
diff --git a/arch/arm/boot/dts/exynos5260-pinctrl.dtsi b/arch/arm/boot/dts/exynos5260-pinctrl.dtsi
index 1b911a219a27..b1edb20b789e 100644
--- a/arch/arm/boot/dts/exynos5260-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5260-pinctrl.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos5260 SoC pin-mux and pin-config device tree source
  *
@@ -6,11 +7,7 @@
  *
  * Samsung's Exynos5260 SoC pin-mux and pin-config options are listed as device
  * tree nodes are listed in this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/pinctrl/samsung.h>
 
diff --git a/arch/arm/boot/dts/exynos5260-xyref5260.dts b/arch/arm/boot/dts/exynos5260-xyref5260.dts
index 73b7cdd5f522..442eb0353f29 100644
--- a/arch/arm/boot/dts/exynos5260-xyref5260.dts
+++ b/arch/arm/boot/dts/exynos5260-xyref5260.dts
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG XYREF5260 board device tree source
  *
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos5260.dtsi"
diff --git a/arch/arm/boot/dts/exynos5260.dtsi b/arch/arm/boot/dts/exynos5260.dtsi
index 5e88c9645975..55167850619c 100644
--- a/arch/arm/boot/dts/exynos5260.dtsi
+++ b/arch/arm/boot/dts/exynos5260.dtsi
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG EXYNOS5260 SoC device tree source
  *
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/clock/exynos5260-clk.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
@@ -106,13 +103,13 @@
 			#clock-cells = <1>;
 		};
 
-		clock_g2d: clock-controller@10A00000 {
+		clock_g2d: clock-controller@10a00000 {
 			compatible = "samsung,exynos5260-clock-g2d";
 			reg = <0x10A00000 0x10000>;
 			#clock-cells = <1>;
 		};
 
-		clock_mif: clock-controller@10CE0000 {
+		clock_mif: clock-controller@10ce0000 {
 			compatible = "samsung,exynos5260-clock-mif";
 			reg = <0x10CE0000 0x10000>;
 			#clock-cells = <1>;
@@ -130,25 +127,25 @@
 			#clock-cells = <1>;
 		};
 
-		clock_fsys: clock-controller@122E0000 {
+		clock_fsys: clock-controller@122e0000 {
 			compatible = "samsung,exynos5260-clock-fsys";
 			reg = <0x122E0000 0x10000>;
 			#clock-cells = <1>;
 		};
 
-		clock_aud: clock-controller@128C0000 {
+		clock_aud: clock-controller@128c0000 {
 			compatible = "samsung,exynos5260-clock-aud";
 			reg = <0x128C0000 0x10000>;
 			#clock-cells = <1>;
 		};
 
-		clock_isp: clock-controller@133C0000 {
+		clock_isp: clock-controller@133c0000 {
 			compatible = "samsung,exynos5260-clock-isp";
 			reg = <0x133C0000 0x10000>;
 			#clock-cells = <1>;
 		};
 
-		clock_gscl: clock-controller@13F00000 {
+		clock_gscl: clock-controller@13f00000 {
 			compatible = "samsung,exynos5260-clock-gscl";
 			reg = <0x13F00000 0x10000>;
 			#clock-cells = <1>;
@@ -179,7 +176,7 @@
 			reg = <0x10000000 0x100>;
 		};
 
-		mct: mct@100B0000 {
+		mct: mct@100b0000 {
 			compatible = "samsung,exynos4210-mct";
 			reg = <0x100B0000 0x1000>;
 			clocks = <&fin_pll>, <&clock_peri PERI_CLK_MCT>;
@@ -198,7 +195,7 @@
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
-		cci: cci@10F00000 {
+		cci: cci@10f00000 {
 			compatible = "arm,cci-400";
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -236,18 +233,18 @@
 			interrupts = <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
-		pinctrl_2: pinctrl@128B0000 {
+		pinctrl_2: pinctrl@128b0000 {
 			compatible = "samsung,exynos5260-pinctrl";
 			reg = <0x128B0000 0x1000>;
 			interrupts = <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
-		pmu_system_controller: system-controller@10D50000 {
+		pmu_system_controller: system-controller@10d50000 {
 			compatible = "samsung,exynos5260-pmu", "syscon";
 			reg = <0x10D50000 0x10000>;
 		};
 
-		uart0: serial@12C00000 {
+		uart0: serial@12c00000 {
 			compatible = "samsung,exynos4210-uart";
 			reg = <0x12C00000 0x100>;
 			interrupts = <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>;
@@ -256,7 +253,7 @@
 			status = "disabled";
 		};
 
-		uart1: serial@12C10000 {
+		uart1: serial@12c10000 {
 			compatible = "samsung,exynos4210-uart";
 			reg = <0x12C10000 0x100>;
 			interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
@@ -265,7 +262,7 @@
 			status = "disabled";
 		};
 
-		uart2: serial@12C20000 {
+		uart2: serial@12c20000 {
 			compatible = "samsung,exynos4210-uart";
 			reg = <0x12C20000 0x100>;
 			interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/exynos5410-odroidxu.dts b/arch/arm/boot/dts/exynos5410-odroidxu.dts
index a45eaae33f8f..a2046f5f998c 100644
--- a/arch/arm/boot/dts/exynos5410-odroidxu.dts
+++ b/arch/arm/boot/dts/exynos5410-odroidxu.dts
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Hardkernel Odroid XU board device tree source
  *
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  * Copyright (c) 2016 Krzysztof Kozlowski
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/exynos5410-pinctrl.dtsi b/arch/arm/boot/dts/exynos5410-pinctrl.dtsi
index ff46a1c27182..369a8a7f2105 100644
--- a/arch/arm/boot/dts/exynos5410-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5410-pinctrl.dtsi
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Exynos5410 SoC pin-mux and pin-config device tree source
  *
  * Copyright (c) 2013 Hardkernel Co., Ltd.
  *              http://www.hardkernel.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/pinctrl/samsung.h>
diff --git a/arch/arm/boot/dts/exynos5410-smdk5410.dts b/arch/arm/boot/dts/exynos5410-smdk5410.dts
index 25f21e9e7d58..8fc8c841d34b 100644
--- a/arch/arm/boot/dts/exynos5410-smdk5410.dts
+++ b/arch/arm/boot/dts/exynos5410-smdk5410.dts
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG SMDK5410 board device tree source
  *
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos5410.dtsi"
diff --git a/arch/arm/boot/dts/exynos5410.dtsi b/arch/arm/boot/dts/exynos5410.dtsi
index 06713ec86f0d..1886aa00b2db 100644
--- a/arch/arm/boot/dts/exynos5410.dtsi
+++ b/arch/arm/boot/dts/exynos5410.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG EXYNOS5410 SoC device tree source
  *
@@ -7,10 +8,6 @@
  * SAMSUNG EXYNOS5410 SoC device nodes are listed in this file.
  * EXYNOS5410 based board files can include this file and provide
  * values for board specfic bindings.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include "exynos54xx.dtsi"
@@ -264,6 +261,11 @@
 	};
 };
 
+&arm_a15_pmu {
+	interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
+	status = "okay";
+};
+
 &i2c_0 {
 	clocks = <&clock CLK_I2C0>;
 	clock-names = "i2c";
@@ -325,6 +327,11 @@
 	clock-names = "fin_pll", "mct";
 };
 
+&prng {
+	clocks = <&clock CLK_SSS>;
+	clock-names = "secss";
+};
+
 &pwm {
 	clocks = <&clock CLK_PWM>;
 	clock-names = "timers";
@@ -333,7 +340,6 @@
 &rtc {
 	clocks = <&clock CLK_RTC>;
 	clock-names = "rtc";
-	interrupt-parent = <&pmu_system_controller>;
 	status = "disabled";
 };
 
@@ -379,6 +385,11 @@
 		  3 0 0x07000000 0x20000>;
 };
 
+&trng {
+	clocks = <&clock CLK_SSS>;
+	clock-names = "secss";
+};
+
 &usbdrd3_0 {
 	clocks = <&clock CLK_USBD300>;
 	clock-names = "usbdrd30";
diff --git a/arch/arm/boot/dts/exynos5420-arndale-octa.dts b/arch/arm/boot/dts/exynos5420-arndale-octa.dts
index bc78575d8a4d..cdda614e417e 100644
--- a/arch/arm/boot/dts/exynos5420-arndale-octa.dts
+++ b/arch/arm/boot/dts/exynos5420-arndale-octa.dts
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos5420 based Arndale Octa board device tree source
  *
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos5420.dtsi"
diff --git a/arch/arm/boot/dts/exynos5420-cpus.dtsi b/arch/arm/boot/dts/exynos5420-cpus.dtsi
index d7d703aa1699..123f0cef658d 100644
--- a/arch/arm/boot/dts/exynos5420-cpus.dtsi
+++ b/arch/arm/boot/dts/exynos5420-cpus.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG EXYNOS5420 SoC cpu device tree source
  *
@@ -14,10 +15,6 @@
  * booting cluster (big or LITTLE) is chosen by IROM code by reading
  * the gpg2-1 GPIO. By default all Exynos5422 based boards choose booting
  * from the LITTLE: Cortex-A7.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 / {
@@ -132,3 +129,13 @@
 		};
 	};
 };
+
+&arm_a7_pmu {
+	interrupt-affinity = <&cpu4>, <&cpu5>, <&cpu6>, <&cpu7>;
+	status = "okay";
+};
+
+&arm_a15_pmu {
+	interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts
index 38af8769711c..5a76ed77dda1 100644
--- a/arch/arm/boot/dts/exynos5420-peach-pit.dts
+++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Google Peach Pit Rev 6+ board device tree source
  *
  * Copyright (c) 2014 Google, Inc
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/exynos5420-pinctrl.dtsi b/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
index 65aa0e300c23..dda8ca2d2324 100644
--- a/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos5420 SoC pin-mux and pin-config device tree source
  *
@@ -6,11 +7,7 @@
  *
  * Samsung's Exynos5420 SoC pin-mux and pin-config options are listed as device
  * tree nodes are listed in this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/pinctrl/samsung.h>
 
diff --git a/arch/arm/boot/dts/exynos5420-smdk5420.dts b/arch/arm/boot/dts/exynos5420-smdk5420.dts
index 310d8637ce9f..831c7336f237 100644
--- a/arch/arm/boot/dts/exynos5420-smdk5420.dts
+++ b/arch/arm/boot/dts/exynos5420-smdk5420.dts
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG SMDK5420 board device tree source
  *
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos5420.dtsi"
diff --git a/arch/arm/boot/dts/exynos5420-tmu-sensor-conf.dtsi b/arch/arm/boot/dts/exynos5420-tmu-sensor-conf.dtsi
index c8771c660550..fbc77cb58473 100644
--- a/arch/arm/boot/dts/exynos5420-tmu-sensor-conf.dtsi
+++ b/arch/arm/boot/dts/exynos5420-tmu-sensor-conf.dtsi
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device tree sources for Exynos5420 TMU sensor configuration
  *
  * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
  * Copyright (c) 2017 Krzysztof Kozlowski <krzk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #include <dt-bindings/thermal/thermal_exynos.h>
diff --git a/arch/arm/boot/dts/exynos5420-trip-points.dtsi b/arch/arm/boot/dts/exynos5420-trip-points.dtsi
index 2180a0152c9b..a67a380717ec 100644
--- a/arch/arm/boot/dts/exynos5420-trip-points.dtsi
+++ b/arch/arm/boot/dts/exynos5420-trip-points.dtsi
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device tree sources for default Exynos5420 thermal zone definition
  *
  * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 polling-delay-passive = <0>;
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index 8aa2cc7aa125..2f3cb2a97f71 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG EXYNOS5420 SoC device tree source
  *
@@ -7,10 +8,6 @@
  * SAMSUNG EXYNOS54200 SoC device nodes are listed in this file.
  * EXYNOS5420 based board files can include this file and provide
  * values for board specfic bindings.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include "exynos54xx.dtsi"
@@ -188,6 +185,7 @@
 			clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MAU_EPLL>,
 				 <&clock CLK_SCLK_MAUDIO0>, <&clock CLK_SCLK_MAUPCM0>;
 			clock-names = "pll_ref", "pll_in", "sclk_audio", "sclk_pcm_in";
+			power-domains = <&mau_pd>;
 		};
 
 		mfc: codec@11000000 {
@@ -237,37 +235,37 @@
 			status = "disabled";
 		};
 
-		nocp_mem0_0: nocp@10CA1000 {
+		nocp_mem0_0: nocp@10ca1000 {
 			compatible = "samsung,exynos5420-nocp";
 			reg = <0x10CA1000 0x200>;
 			status = "disabled";
 		};
 
-		nocp_mem0_1: nocp@10CA1400 {
+		nocp_mem0_1: nocp@10ca1400 {
 			compatible = "samsung,exynos5420-nocp";
 			reg = <0x10CA1400 0x200>;
 			status = "disabled";
 		};
 
-		nocp_mem1_0: nocp@10CA1800 {
+		nocp_mem1_0: nocp@10ca1800 {
 			compatible = "samsung,exynos5420-nocp";
 			reg = <0x10CA1800 0x200>;
 			status = "disabled";
 		};
 
-		nocp_mem1_1: nocp@10CA1C00 {
+		nocp_mem1_1: nocp@10ca1c00 {
 			compatible = "samsung,exynos5420-nocp";
 			reg = <0x10CA1C00 0x200>;
 			status = "disabled";
 		};
 
-		nocp_g3d_0: nocp@11A51000 {
+		nocp_g3d_0: nocp@11a51000 {
 			compatible = "samsung,exynos5420-nocp";
 			reg = <0x11A51000 0x200>;
 			status = "disabled";
 		};
 
-		nocp_g3d_1: nocp@11A51400 {
+		nocp_g3d_1: nocp@11a51400 {
 			compatible = "samsung,exynos5420-nocp";
 			reg = <0x11A51400 0x200>;
 			status = "disabled";
@@ -309,7 +307,7 @@
 			label = "MSC";
 		};
 
-		disp_pd: power-domain@100440C0 {
+		disp_pd: power-domain@100440c0 {
 			compatible = "samsung,exynos4210-pd";
 			reg = <0x100440C0 0x20>;
 			#power-domain-cells = <0>;
@@ -322,6 +320,13 @@
 			clock-names = "oscclk", "clk0", "clk1", "clk2", "asb0", "asb1";
 		};
 
+		mau_pd: power-domain@100440e0 {
+			compatible = "samsung,exynos4210-pd";
+			reg = <0x100440E0 0x20>;
+			#power-domain-cells = <0>;
+			label = "MAU";
+		};
+
 		pinctrl_0: pinctrl@13400000 {
 			compatible = "samsung,exynos5420-pinctrl";
 			reg = <0x13400000 0x1000>;
@@ -356,6 +361,7 @@
 			compatible = "samsung,exynos5420-pinctrl";
 			reg = <0x03860000 0x1000>;
 			interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>;
+			power-domains = <&mau_pd>;
 		};
 
 		amba {
@@ -374,9 +380,10 @@
 				#dma-cells = <1>;
 				#dma-channels = <6>;
 				#dma-requests = <16>;
+				power-domains = <&mau_pd>;
 			};
 
-			pdma0: pdma@121A0000 {
+			pdma0: pdma@121a0000 {
 				compatible = "arm,pl330", "arm,primecell";
 				reg = <0x121A0000 0x1000>;
 				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
@@ -387,7 +394,7 @@
 				#dma-requests = <32>;
 			};
 
-			pdma1: pdma@121B0000 {
+			pdma1: pdma@121b0000 {
 				compatible = "arm,pl330", "arm,primecell";
 				reg = <0x121B0000 0x1000>;
 				interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
@@ -409,7 +416,7 @@
 				#dma-requests = <1>;
 			};
 
-			mdma1: mdma@11C10000 {
+			mdma1: mdma@11c10000 {
 				compatible = "arm,pl330", "arm,primecell";
 				reg = <0x11C10000 0x1000>;
 				interrupts = <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>;
@@ -446,10 +453,11 @@
 			samsung,idma-addr = <0x03000000>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&i2s0_bus>;
+			power-domains = <&mau_pd>;
 			status = "disabled";
 		};
 
-		i2s1: i2s@12D60000 {
+		i2s1: i2s@12d60000 {
 			compatible = "samsung,exynos5420-i2s";
 			reg = <0x12D60000 0x100>;
 			dmas = <&pdma1 12
@@ -465,7 +473,7 @@
 			status = "disabled";
 		};
 
-		i2s2: i2s@12D70000 {
+		i2s2: i2s@12d70000 {
 			compatible = "samsung,exynos5420-i2s";
 			reg = <0x12D70000 0x100>;
 			dmas = <&pdma0 12
@@ -554,7 +562,7 @@
 			status = "disabled";
 		};
 
-		adc: adc@12D10000 {
+		adc: adc@12d10000 {
 			compatible = "samsung,exynos-adc-v2";
 			reg = <0x12D10000 0x100>;
 			interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
@@ -566,7 +574,7 @@
 			status = "disabled";
 		};
 
-		hsi2c_8: i2c@12E00000 {
+		hsi2c_8: i2c@12e00000 {
 			compatible = "samsung,exynos5250-hsi2c";
 			reg = <0x12E00000 0x1000>;
 			interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
@@ -579,7 +587,7 @@
 			status = "disabled";
 		};
 
-		hsi2c_9: i2c@12E10000 {
+		hsi2c_9: i2c@12e10000 {
 			compatible = "samsung,exynos5250-hsi2c";
 			reg = <0x12E10000 0x1000>;
 			interrupts = <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>;
@@ -592,7 +600,7 @@
 			status = "disabled";
 		};
 
-		hsi2c_10: i2c@12E20000 {
+		hsi2c_10: i2c@12e20000 {
 			compatible = "samsung,exynos5250-hsi2c";
 			reg = <0x12E20000 0x1000>;
 			interrupts = <GIC_SPI 203 IRQ_TYPE_LEVEL_HIGH>;
@@ -618,13 +626,14 @@
 			samsung,syscon-phandle = <&pmu_system_controller>;
 			status = "disabled";
 			power-domains = <&disp_pd>;
+			#sound-dai-cells = <0>;
 		};
 
-		hdmiphy: hdmiphy@145D0000 {
+		hdmiphy: hdmiphy@145d0000 {
 			reg = <0x145D0000 0x20>;
 		};
 
-		hdmicec: cec@101B0000 {
+		hdmicec: cec@101b0000 {
 			compatible = "samsung,s5p-cec";
 			reg = <0x101B0000 0x200>;
 			interrupts = <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>;
@@ -649,7 +658,7 @@
 			status = "disabled";
 		};
 
-		rotator: rotator@11C00000 {
+		rotator: rotator@11c00000 {
 			compatible = "samsung,exynos5250-rotator";
 			reg = <0x11C00000 0x64>;
 			interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
@@ -678,7 +687,7 @@
 			iommus = <&sysmmu_gscl1>;
 		};
 
-		jpeg_0: jpeg@11F50000 {
+		jpeg_0: jpeg@11f50000 {
 			compatible = "samsung,exynos5420-jpeg";
 			reg = <0x11F50000 0x1000>;
 			interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
@@ -687,7 +696,7 @@
 			iommus = <&sysmmu_jpeg0>;
 		};
 
-		jpeg_1: jpeg@11F60000 {
+		jpeg_1: jpeg@11f60000 {
 			compatible = "samsung,exynos5420-jpeg";
 			reg = <0x11F60000 0x1000>;
 			interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
@@ -1349,6 +1358,13 @@
 	iommu-names = "m0", "m1";
 };
 
+&g2d {
+	iommus = <&sysmmu_g2dr>, <&sysmmu_g2dw>;
+	clocks = <&clock CLK_G2D>;
+	clock-names = "fimg2d";
+	status = "okay";
+};
+
 &i2c_0 {
 	clocks = <&clock CLK_I2C0>;
 	clock-names = "i2c";
@@ -1410,6 +1426,11 @@
 	clock-names = "fin_pll", "mct";
 };
 
+&prng {
+	clocks = <&clock CLK_SSS>;
+	clock-names = "secss";
+};
+
 &pwm {
 	clocks = <&clock CLK_PWM>;
 	clock-names = "timers";
@@ -1455,6 +1476,11 @@
 	clock-names = "secss";
 };
 
+&trng {
+	clocks = <&clock CLK_SSS>;
+	clock-names = "secss";
+};
+
 &usbdrd3_0 {
 	clocks = <&clock CLK_USBD300>;
 	clock-names = "usbdrd30";
diff --git a/arch/arm/boot/dts/exynos5422-cpus.dtsi b/arch/arm/boot/dts/exynos5422-cpus.dtsi
index ec01d8020c2d..c593809c7f08 100644
--- a/arch/arm/boot/dts/exynos5422-cpus.dtsi
+++ b/arch/arm/boot/dts/exynos5422-cpus.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG EXYNOS5422 SoC cpu device tree source
  *
@@ -13,10 +14,6 @@
  * booting cluster (big or LITTLE) is chosen by IROM code by reading
  * the gpg2-1 GPIO. By default all Exynos5422 based boards choose booting
  * from the LITTLE: Cortex-A7.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 / {
@@ -131,3 +128,13 @@
 		};
 	};
 };
+
+&arm_a7_pmu {
+	interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
+	status = "okay";
+};
+
+&arm_a15_pmu {
+	interrupt-affinity = <&cpu4>, <&cpu5>, <&cpu6>, <&cpu7>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/exynos5422-odroid-core.dtsi b/arch/arm/boot/dts/exynos5422-odroid-core.dtsi
index a5b8d0f0877e..d31249f25ccf 100644
--- a/arch/arm/boot/dts/exynos5422-odroid-core.dtsi
+++ b/arch/arm/boot/dts/exynos5422-odroid-core.dtsi
@@ -1,14 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Hardkernel Odroid XU3/XU4/HC1 boards core device tree source
  *
  * Copyright (c) 2017 Marek Szyprowski
  * Copyright (c) 2013-2017 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/clock/samsung,s2mps11.h>
 #include <dt-bindings/interrupt-controller/irq.h>
@@ -233,8 +230,8 @@
 
 			ldo15_reg: LDO15 {
 				regulator-name = "vdd_ldo15";
-				regulator-min-microvolt = <3100000>;
-				regulator-max-microvolt = <3100000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
 				regulator-always-on;
 			};
 
@@ -246,7 +243,7 @@
 			};
 
 			ldo17_reg: LDO17 {
-				regulator-name = "tsp_avdd";
+				regulator-name = "vdd_ldo17";
 				regulator-min-microvolt = <3300000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-always-on;
diff --git a/arch/arm/boot/dts/exynos5422-odroidhc1.dts b/arch/arm/boot/dts/exynos5422-odroidhc1.dts
index fb8e8ae776e9..8f332be143f7 100644
--- a/arch/arm/boot/dts/exynos5422-odroidhc1.dts
+++ b/arch/arm/boot/dts/exynos5422-odroidhc1.dts
@@ -1,14 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Hardkernel Odroid HC1 board device tree source
  *
  * Copyright (c) 2017 Marek Szyprowski
  * Copyright (c) 2017 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos5422-odroid-core.dtsi"
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-audio.dtsi b/arch/arm/boot/dts/exynos5422-odroidxu3-audio.dtsi
index da3141a307d5..03611d50c5a9 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu3-audio.dtsi
+++ b/arch/arm/boot/dts/exynos5422-odroidxu3-audio.dtsi
@@ -1,27 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Hardkernel Odroid XU3 Audio Codec device tree source
+ * Hardkernel Odroid XU3 audio subsystem device tree source
  *
  * Copyright (c) 2015 Krzysztof Kozlowski
  * Copyright (c) 2014 Collabora Ltd.
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/sound/samsung-i2s.h>
 
 / {
 	sound: sound {
-		compatible = "simple-audio-card";
+		compatible = "samsung,odroid-xu3-audio";
+		model = "Odroid-XU3";
 
-		simple-audio-card,name = "Odroid-XU3";
-		simple-audio-card,widgets =
+		samsung,audio-widgets =
 			"Headphone", "Headphone Jack",
 			"Speakers", "Speakers";
-		simple-audio-card,routing =
+		samsung,audio-routing =
 			"Headphone Jack", "HPL",
 			"Headphone Jack", "HPR",
 			"Headphone Jack", "MICBIAS",
@@ -29,31 +26,47 @@
 			"Speakers", "SPKL",
 			"Speakers", "SPKR";
 
-		simple-audio-card,format = "i2s";
-		simple-audio-card,bitclock-master = <&link0_codec>;
-		simple-audio-card,frame-master = <&link0_codec>;
+		assigned-clocks = <&i2s0 CLK_I2S_RCLK_SRC>,
+				<&clock CLK_MOUT_EPLL>,
+				<&clock CLK_MOUT_MAU_EPLL>,
+				<&clock CLK_MOUT_USER_MAU_EPLL>,
+				<&clock_audss EXYNOS_MOUT_AUDSS>,
+				<&clock_audss EXYNOS_MOUT_I2S>,
+				<&clock_audss EXYNOS_DOUT_SRP>,
+				<&clock_audss EXYNOS_DOUT_AUD_BUS>,
+				<&clock_audss EXYNOS_DOUT_I2S>;
+
+		assigned-clock-parents = <&clock_audss EXYNOS_SCLK_I2S>,
+				<&clock CLK_FOUT_EPLL>,
+				<&clock CLK_MOUT_EPLL>,
+				<&clock CLK_MOUT_MAU_EPLL>,
+				<&clock CLK_MAU_EPLL>,
+				<&clock_audss EXYNOS_MOUT_AUDSS>;
 
-		simple-audio-card,cpu {
+		assigned-clock-rates = <0>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<196608001>,
+				<(196608002 / 2)>,
+				<196608000>;
+
+		cpu {
 			sound-dai = <&i2s0 0>;
-			system-clock-frequency = <19200000>;
 		};
-
-		link0_codec: simple-audio-card,codec {
-			sound-dai = <&max98090>;
-			clocks = <&i2s0 CLK_I2S_CDCLK>;
+		codec {
+			sound-dai = <&hdmi>, <&max98090>;
 		};
 	};
 };
 
 &clock_audss {
-	assigned-clocks = <&clock_audss EXYNOS_MOUT_AUDSS>,
-			<&clock_audss EXYNOS_MOUT_I2S>,
-			<&clock_audss EXYNOS_DOUT_AUD_BUS>;
-	assigned-clock-parents = <&clock CLK_FIN_PLL>,
-			<&clock_audss EXYNOS_MOUT_AUDSS>;
-	assigned-clock-rates = <0>,
-			<0>,
-			<19200000>;
+	assigned-clocks = <&clock_audss EXYNOS_DOUT_SRP>,
+			  <&clock CLK_FOUT_EPLL>;
+	assigned-clock-rates = <(196608000 / 256)>,
+			       <196608000>;
 };
 
 &hsi2c_5 {
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
index 445c6c5a1300..96e281c0a118 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
+++ b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Hardkernel Odroid XU3 board device tree source
  *
@@ -6,11 +7,7 @@
  * Copyright (c) 2014 Collabora Ltd.
  * Copyright (c) 2015 Lukasz Majewski <l.majewski@samsung.com>
  *                    Anand Moon <linux.amoon@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/input/input.h>
 #include "exynos5422-odroid-core.dtsi"
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-lite.dts b/arch/arm/boot/dts/exynos5422-odroidxu3-lite.dts
index 03fa88c45426..0db935f2b836 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu3-lite.dts
+++ b/arch/arm/boot/dts/exynos5422-odroidxu3-lite.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Hardkernel Odroid XU3-Lite board device tree source
  *
@@ -5,11 +6,7 @@
  * Copyright (c) 2014 Collabora Ltd.
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos5422-odroidxu3-common.dtsi"
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3.dts b/arch/arm/boot/dts/exynos5422-odroidxu3.dts
index 9ed6564acfb0..0322f281912c 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu3.dts
+++ b/arch/arm/boot/dts/exynos5422-odroidxu3.dts
@@ -1,14 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Hardkernel Odroid XU3 board device tree source
  *
  * Copyright (c) 2014 Collabora Ltd.
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos5422-odroidxu3-common.dtsi"
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu4.dts b/arch/arm/boot/dts/exynos5422-odroidxu4.dts
index 2faf88627a48..4a30cc849b00 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu4.dts
+++ b/arch/arm/boot/dts/exynos5422-odroidxu4.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Hardkernel Odroid XU4 board device tree source
  *
@@ -5,13 +6,10 @@
  * Copyright (c) 2014 Collabora Ltd.
  * Copyright (c) 2013-2015 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
+#include <dt-bindings/sound/samsung-i2s.h>
 #include "exynos5422-odroidxu3-common.dtsi"
 
 / {
@@ -30,6 +28,57 @@
 			linux,default-trigger = "heartbeat";
 		};
 	};
+
+	sound: sound {
+		compatible = "samsung,odroid-xu3-audio";
+		model = "Odroid-XU4";
+
+		assigned-clocks = <&i2s0 CLK_I2S_RCLK_SRC>,
+				<&clock CLK_MOUT_EPLL>,
+				<&clock CLK_MOUT_MAU_EPLL>,
+				<&clock CLK_MOUT_USER_MAU_EPLL>,
+				<&clock_audss EXYNOS_MOUT_AUDSS>,
+				<&clock_audss EXYNOS_MOUT_I2S>,
+				<&clock_audss EXYNOS_DOUT_SRP>,
+				<&clock_audss EXYNOS_DOUT_AUD_BUS>,
+				<&clock_audss EXYNOS_DOUT_I2S>;
+
+		assigned-clock-parents = <&clock_audss EXYNOS_SCLK_I2S>,
+				<&clock CLK_FOUT_EPLL>,
+				<&clock CLK_MOUT_EPLL>,
+				<&clock CLK_MOUT_MAU_EPLL>,
+				<&clock CLK_MAU_EPLL>,
+				<&clock_audss EXYNOS_MOUT_AUDSS>;
+
+		assigned-clock-rates = <0>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<196608001>,
+				<(196608002 / 2)>,
+				<196608000>;
+
+		cpu {
+			sound-dai = <&i2s0 0>;
+		};
+
+		codec {
+			sound-dai = <&hdmi>;
+		};
+	};
+};
+
+&clock_audss {
+	assigned-clocks = <&clock_audss EXYNOS_DOUT_SRP>,
+			  <&clock CLK_FOUT_EPLL>;
+	assigned-clock-rates = <(196608000 / 256)>,
+			       <196608000>;
+};
+
+&i2s0 {
+	status = "okay";
 };
 
 &pwm {
diff --git a/arch/arm/boot/dts/exynos5440-sd5v1.dts b/arch/arm/boot/dts/exynos5440-sd5v1.dts
index ad6f533b3f40..c4b8392d1ae1 100644
--- a/arch/arm/boot/dts/exynos5440-sd5v1.dts
+++ b/arch/arm/boot/dts/exynos5440-sd5v1.dts
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG SD5v1 board device tree source
  *
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos5440.dtsi"
diff --git a/arch/arm/boot/dts/exynos5440-ssdk5440.dts b/arch/arm/boot/dts/exynos5440-ssdk5440.dts
index 7eafad333bdb..a33c4fc29ae5 100644
--- a/arch/arm/boot/dts/exynos5440-ssdk5440.dts
+++ b/arch/arm/boot/dts/exynos5440-ssdk5440.dts
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG SSDK5440 board device tree source
  *
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos5440.dtsi"
diff --git a/arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi b/arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi
index 7b2fba0ae92b..0421c3d42905 100644
--- a/arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi
+++ b/arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device tree sources for Exynos5440 TMU sensor configuration
  *
  * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #include <dt-bindings/thermal/thermal_exynos.h>
diff --git a/arch/arm/boot/dts/exynos5440-trip-points.dtsi b/arch/arm/boot/dts/exynos5440-trip-points.dtsi
index 356e963edf11..a2b04fed7d0b 100644
--- a/arch/arm/boot/dts/exynos5440-trip-points.dtsi
+++ b/arch/arm/boot/dts/exynos5440-trip-points.dtsi
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device tree sources for default Exynos5440 thermal zone definition
  *
  * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 polling-delay-passive = <0>;
diff --git a/arch/arm/boot/dts/exynos5440.dtsi b/arch/arm/boot/dts/exynos5440.dtsi
index 9c3c75ae5e48..fce9e26b5930 100644
--- a/arch/arm/boot/dts/exynos5440.dtsi
+++ b/arch/arm/boot/dts/exynos5440.dtsi
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG EXYNOS5440 SoC device tree source
  *
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/clock/exynos5440.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
@@ -35,7 +32,7 @@
 		#clock-cells = <1>;
 	};
 
-	gic: interrupt-controller@2E0000 {
+	gic: interrupt-controller@2e0000 {
 		compatible = "arm,cortex-a15-gic";
 		#interrupt-cells = <3>;
 		interrupt-controller;
@@ -108,7 +105,7 @@
 		>;
 	};
 
-	serial_0: serial@B0000 {
+	serial_0: serial@b0000 {
 		compatible = "samsung,exynos4210-uart";
 		reg = <0xB0000 0x1000>;
 		interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
@@ -116,7 +113,7 @@
 		clock-names = "uart", "clk_uart_baud0";
 	};
 
-	serial_1: serial@C0000 {
+	serial_1: serial@c0000 {
 		compatible = "samsung,exynos4210-uart";
 		reg = <0xC0000 0x1000>;
 		interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>;
@@ -124,7 +121,7 @@
 		clock-names = "uart", "clk_uart_baud0";
 	};
 
-	spi_0: spi@D0000 {
+	spi_0: spi@d0000 {
 		compatible = "samsung,exynos5440-spi";
 		reg = <0xD0000 0x100>;
 		interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
@@ -136,7 +133,7 @@
 		clock-names = "spi", "spi_busclk0";
 	};
 
-	pin_ctrl: pinctrl@E0000 {
+	pin_ctrl: pinctrl@e0000 {
 		compatible = "samsung,exynos5440-pinctrl";
 		reg = <0xE0000 0x1000>;
 		interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
@@ -168,7 +165,7 @@
 		};
 	};
 
-	i2c@F0000 {
+	i2c@f0000 {
 		compatible = "samsung,exynos5440-i2c";
 		reg = <0xF0000 0x1000>;
 		interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
@@ -233,7 +230,7 @@
 		#include "exynos5440-tmu-sensor-conf.dtsi"
 	};
 
-	tmuctrl_1: tmuctrl@16011C {
+	tmuctrl_1: tmuctrl@16011c {
 		compatible = "samsung,exynos5440-tmu";
 		reg = <0x16011C 0x230>, <0x160368 0x10>;
 		interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/exynos54xx-odroidxu-leds.dtsi b/arch/arm/boot/dts/exynos54xx-odroidxu-leds.dtsi
index 0ed30206625c..56acd832f0b3 100644
--- a/arch/arm/boot/dts/exynos54xx-odroidxu-leds.dtsi
+++ b/arch/arm/boot/dts/exynos54xx-odroidxu-leds.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Hardkernel Odroid XU/XU3 LED device tree source
  *
@@ -5,11 +6,7 @@
  * Copyright (c) 2014 Collabora Ltd.
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/gpio/gpio.h>
 
diff --git a/arch/arm/boot/dts/exynos54xx.dtsi b/arch/arm/boot/dts/exynos54xx.dtsi
index a5007f182bc4..de26e5ee0d2d 100644
--- a/arch/arm/boot/dts/exynos54xx.dtsi
+++ b/arch/arm/boot/dts/exynos54xx.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos54xx SoC series common device tree source
  *
@@ -8,10 +9,6 @@
  * Device nodes common for Samsung Exynos5410/5420/5422/5800. Specific
  * Exynos 54xx SoCs should include this file and customize it further
  * (e.g. with clocks).
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include "exynos5.dtsi"
@@ -29,6 +26,26 @@
 	};
 
 	soc: soc {
+		arm_a7_pmu: arm-a7-pmu {
+			compatible = "arm,cortex-a7-pmu";
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 161 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 163 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		arm_a15_pmu: arm-a15-pmu {
+			compatible = "arm,cortex-a15-pmu";
+			interrupt-parent = <&combiner>;
+			interrupts = <1 2>,
+				     <7 0>,
+				     <16 6>,
+				     <19 2>;
+			status = "disabled";
+		};
+
 		sysram@2020000 {
 			compatible = "mmio-sram";
 			reg = <0x02020000 0x54000>;
@@ -79,12 +96,6 @@
 			interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
-		sss: sss@10830000 {
-			compatible = "samsung,exynos4210-secss";
-			reg = <0x10830000 0x300>;
-			interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>;
-		};
-
 		/* i2c_0-3 are defined in exynos5.dtsi */
 		hsi2c_4: i2c@12ca0000 {
 			compatible = "samsung,exynos5250-hsi2c";
diff --git a/arch/arm/boot/dts/exynos5800-peach-pi.dts b/arch/arm/boot/dts/exynos5800-peach-pi.dts
index b2b95ff205e8..0029ec27819c 100644
--- a/arch/arm/boot/dts/exynos5800-peach-pi.dts
+++ b/arch/arm/boot/dts/exynos5800-peach-pi.dts
@@ -664,6 +664,10 @@
 	status = "okay";
 };
 
+&mixer {
+	status = "okay";
+};
+
 /* eMMC flash */
 &mmc_0 {
 	status = "okay";
diff --git a/arch/arm/boot/dts/ge863-pro3.dtsi b/arch/arm/boot/dts/ge863-pro3.dtsi
index 6a9fdc0760f0..a7adbdc2f0c0 100644
--- a/arch/arm/boot/dts/ge863-pro3.dtsi
+++ b/arch/arm/boot/dts/ge863-pro3.dtsi
@@ -18,6 +18,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			dbgu: serial@fffff200 {
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/gemini-dlink-dir-685.dts b/arch/arm/boot/dts/gemini-dlink-dir-685.dts
index e75e2d44371c..cadde92bc6b5 100644
--- a/arch/arm/boot/dts/gemini-dlink-dir-685.dts
+++ b/arch/arm/boot/dts/gemini-dlink-dir-685.dts
@@ -45,6 +45,47 @@
 		};
 	};
 
+	vdisp: regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "display-power";
+		regulator-min-microvolt = <3600000>;
+		regulator-max-microvolt = <3600000>;
+		/* Collides with LCD E */
+		gpio = <&gpio0 16 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	spi {
+		compatible = "spi-gpio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		/* Collides with IDE pins, that's cool (we do not use them) */
+		gpio-sck = <&gpio1 5 GPIO_ACTIVE_HIGH>;
+		gpio-miso = <&gpio1 8 GPIO_ACTIVE_HIGH>;
+		gpio-mosi = <&gpio1 7 GPIO_ACTIVE_HIGH>;
+		/* Collides with pflash CE1, not so cool */
+		cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>;
+		num-chipselects = <1>;
+
+		panel: display@0 {
+			compatible = "dlink,dir-685-panel", "ilitek,ili9322";
+			reg = <0>;
+			/* 50 ns min period = 20 MHz */
+			spi-max-frequency = <20000000>;
+			spi-cpol; /* Clock active low */
+			vcc-supply = <&vdisp>;
+			iovcc-supply = <&vdisp>;
+			vci-supply = <&vdisp>;
+
+			port {
+				panel_in: endpoint {
+					remote-endpoint = <&display_out>;
+				};
+			};
+		};
+	};
+
 	leds {
 		compatible = "gpio-leds";
 		led-wps {
@@ -99,8 +140,8 @@
 	gpio-i2c {
 		compatible = "i2c-gpio";
 		/* Collides with ICE */
-		gpios = <&gpio0 5 0>, /* SDA */
-			<&gpio0 6 0>; /* SCL */
+		sda-gpios = <&gpio0 5 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>;
+		scl-gpios = <&gpio0 6 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 
@@ -115,7 +156,16 @@
 
 	soc {
 		flash@30000000 {
-			status = "okay";
+			/*
+			 * Flash access is by default disabled, because it
+			 * collides with the Chip Enable signal for the display
+			 * panel, that reuse the parallel flash Chip Select 1
+			 * (CS1). Enabling flash makes graphics stop working.
+			 *
+			 * We might be able to hack around this by letting
+			 * GPIO poke around in the flash controller registers.
+			 */
+			/* status = "okay"; */
 			/* 32MB of flash */
 			reg = <0x30000000 0x02000000>;
 
@@ -242,5 +292,16 @@
 		ata@63000000 {
 			status = "okay";
 		};
+
+		display-controller@6a000000 {
+			status = "okay";
+
+			port@0 {
+				reg = <0>;
+				display_out: endpoint {
+					remote-endpoint = <&panel_in>;
+				};
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/gemini-dlink-dns-313.dts b/arch/arm/boot/dts/gemini-dlink-dns-313.dts
new file mode 100644
index 000000000000..08568ce24d06
--- /dev/null
+++ b/arch/arm/boot/dts/gemini-dlink-dns-313.dts
@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Device Tree file for D-Link DNS-313 1-Bay Network Storage Enclosure
+ */
+
+/dts-v1/;
+
+#include "gemini.dtsi"
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/thermal/thermal.h>
+
+/ {
+	model = "D-Link DNS-313 1-Bay Network Storage Enclosure";
+	compatible = "dlink,dir-313", "cortina,gemini";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	memory {
+		/* 64 MB SDRAM in a Nanya NT5DS32M16BS-6K package */
+		device_type = "memory";
+		reg = <0x00000000 0x4000000>;
+	};
+
+	aliases {
+		mdio-gpio0 = &mdio0;
+	};
+
+	chosen {
+		stdout-path = "uart0:19200n8";
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		button-esc {
+			debounce_interval = <50>;
+			wakeup-source;
+			linux,code = <KEY_ESC>;
+			label = "reset";
+			gpios = <&gpio1 31 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		led-power {
+			label = "dns313:blue:power";
+			gpios = <&gpio0 1 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+			linux,default-trigger = "heartbeat";
+		};
+		led-disk-blue {
+			label = "dns313:blue:disk";
+			gpios = <&gpio0 2 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+		led-disk-green {
+			label = "dns313:green:disk";
+			gpios = <&gpio0 3 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+			linux,default-trigger = "ide-disk";
+			/* Ideally should activate while reading */
+		};
+		led-disk-red {
+			label = "dns313:red:disk";
+			gpios = <&gpio0 4 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+			/* Ideally should activate while writing */
+		};
+	};
+
+	/*
+	 * This is a ADDA AD0405GB-G73 fan @3000 and 6000 RPM.
+	 */
+	fan0: gpio-fan {
+		compatible = "gpio-fan";
+		gpios = <&gpio0 11 GPIO_ACTIVE_HIGH>,
+			<&gpio0 12 GPIO_ACTIVE_HIGH>;
+		gpio-fan,speed-map = <0 0>, <3000 1>, <6000 2>;
+		cooling-min-level = <0>;
+		cooling-max-level = <2>;
+		#cooling-cells = <2>;
+	};
+
+
+	/* Global Mixed-Mode Technology G751 mounted on GPIO I2C */
+	gpio-i2c {
+		compatible = "i2c-gpio";
+		sda-gpios = <&gpio0 15 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>;
+		scl-gpios = <&gpio0 16 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		g751: temperature-sensor@48 {
+			compatible = "gmt,g751";
+			reg = <0x48>;
+			#thermal-sensor-cells = <0>;
+		};
+	};
+
+	thermal-zones {
+		chassis-thermal {
+			/* Poll every 20 seconds */
+			polling-delay = <20000>;
+			/* Poll every 2nd second when cooling */
+			polling-delay-passive = <2000>;
+
+			thermal-sensors = <&g751>;
+
+			/* Tripping points from the fan.script in the rootfs */
+			trips {
+				chassis_alert0: chassis-alert0 {
+					/* At 43 degrees turn on low speed */
+					temperature = <43000>;
+					hysteresis = <3000>;
+					type = "active";
+				};
+				chassis_alert1: chassis-alert1 {
+					/* At 47 degrees turn on high speed */
+					temperature = <47000>;
+					hysteresis = <3000>;
+					type = "active";
+				};
+				chassis_crit: chassis-crit {
+					/* Just shut down at 60 degrees */
+					temperature = <60000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&chassis_alert0>;
+					cooling-device = <&fan0 1 1>;
+				};
+				map1 {
+					trip = <&chassis_alert1>;
+					cooling-device = <&fan0 2 2>;
+				};
+			};
+		};
+	};
+
+	mdio0: ethernet-phy {
+		compatible = "virtual,mdio-gpio";
+		/* Uses MDC and MDIO */
+		gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>, /* MDC */
+			<&gpio0 21 GPIO_ACTIVE_HIGH>; /* MDIO */
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		/* This is a Realtek RTL8211B Gigabit ethernet transceiver */
+		phy0: ethernet-phy@1 {
+			reg = <1>;
+			device_type = "ethernet-phy";
+		};
+	};
+
+	soc {
+		flash@30000000 {
+			status = "okay";
+			/* 512KB of flash */
+			reg = <0x30000000 0x00080000>;
+
+			/*
+			 * This "RedBoot" is the Storlink derivative.
+			 */
+			partition@0 {
+				label = "RedBoot";
+				reg = <0x00000000 0x00040000>;
+				read-only;
+			};
+			partition@40000 {
+				label = "MTD1";
+				reg = <0x00040000 0x00020000>;
+				read-only;
+			};
+			partition@60000 {
+				label = "MTD2";
+				reg = <0x00060000 0x00020000>;
+				read-only;
+			};
+		};
+
+		syscon: syscon@40000000 {
+			pinctrl {
+				/*
+				 */
+				gpio0_default_pins: pinctrl-gpio0 {
+					mux {
+						function = "gpio0";
+						groups =
+						/* Used by LEDs conflicts ICE */
+						"gpio0bgrp",
+						/* Used by ? conflicts ICE */
+						"gpio0cgrp",
+						/*
+						 * Used by fan & G751, conflicts LPC,
+						 * UART modem lines, SSP
+						 */
+						"gpio0egrp",
+						/* Used by G751 */
+						"gpio0fgrp",
+						/* Used by MDIO */
+						"gpio0igrp";
+					};
+				};
+				gpio1_default_pins: pinctrl-gpio1 {
+					mux {
+						function = "gpio1";
+						/* Used by "reset" button */
+						groups = "gpio1dgrp";
+					};
+				};
+				pinctrl-gmii {
+					mux {
+						function = "gmii";
+						groups = "gmii_gmac0_grp";
+					};
+					/*
+					 * In the vendor Linux tree, these values are set for the C3
+					 * version of the SL3512 ASIC with the comment "benson suggest"
+					 */
+					conf0 {
+						pins = "R8 GMAC0 RXDV", "U11 GMAC1 RXDV";
+						skew-delay = <0>;
+					};
+					conf1 {
+						pins = "T8 GMAC0 RXC";
+						skew-delay = <10>;
+					};
+					conf2 {
+						pins = "T11 GMAC1 RXC";
+						skew-delay = <15>;
+					};
+					conf3 {
+						pins = "P8 GMAC0 TXEN", "V11 GMAC1 TXEN";
+						skew-delay = <7>;
+					};
+					conf4 {
+						pins = "V7 GMAC0 TXC", "P10 GMAC1 TXC";
+						skew-delay = <10>;
+					};
+					conf5 {
+						/* The data lines all have default skew */
+						pins = "U8 GMAC0 RXD0", "V8 GMAC0 RXD1",
+						       "P9 GMAC0 RXD2", "R9 GMAC0 RXD3",
+						       "R11 GMAC1 RXD0", "P11 GMAC1 RXD1",
+						       "V12 GMAC1 RXD2", "U12 GMAC1 RXD3",
+						       "R10 GMAC1 TXD0", "T10 GMAC1 TXD1",
+						       "U10 GMAC1 TXD2", "V10 GMAC1 TXD3";
+						skew-delay = <7>;
+					};
+					conf6 {
+						pins = "U7 GMAC0 TXD0", "T7 GMAC0 TXD1",
+						       "R7 GMAC0 TXD2", "P7 GMAC0 TXD3";
+						skew-delay = <5>;
+					};
+					/* Set up drive strength on GMAC0 to 16 mA */
+					conf7 {
+						groups = "gmii_gmac0_grp";
+						drive-strength = <16>;
+					};
+				};
+			};
+		};
+
+		sata: sata@46000000 {
+			/* The ROM uses this muxmode */
+			cortina,gemini-ata-muxmode = <3>;
+			cortina,gemini-enable-sata-bridge;
+			status = "okay";
+		};
+
+		gpio0: gpio@4d000000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&gpio0_default_pins>;
+		};
+
+		gpio1: gpio@4e000000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&gpio1_default_pins>;
+		};
+
+		ethernet@60000000 {
+			status = "okay";
+
+			ethernet-port@0 {
+				phy-mode = "rgmii";
+				phy-handle = <&phy0>;
+			};
+			ethernet-port@1 {
+				/* Not used in this platform */
+			};
+		};
+
+		ata@63000000 {
+			status = "okay";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/gemini-nas4220b.dts b/arch/arm/boot/dts/gemini-nas4220b.dts
index d6a22e677c7a..8bbb6f85d161 100644
--- a/arch/arm/boot/dts/gemini-nas4220b.dts
+++ b/arch/arm/boot/dts/gemini-nas4220b.dts
@@ -64,6 +64,19 @@
 		};
 	};
 
+	mdio0: ethernet-phy {
+		compatible = "virtual,mdio-gpio";
+		gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>, /* MDC */
+			<&gpio0 21 GPIO_ACTIVE_HIGH>; /* MDIO */
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		phy0: ethernet-phy@1 {
+			reg = <1>;
+			device_type = "ethernet-phy";
+		};
+	};
+
 	soc {
 		flash@30000000 {
 			status = "okay";
@@ -116,6 +129,50 @@
 						groups = "gpio1dgrp";
 					};
 				};
+				pinctrl-gmii {
+					mux {
+						function = "gmii";
+						groups = "gmii_gmac0_grp";
+					};
+					/* Settings come from OpenWRT */
+					conf0 {
+						pins = "R8 GMAC0 RXDV", "U11 GMAC1 RXDV";
+						skew-delay = <0>;
+					};
+					conf1 {
+						pins = "T8 GMAC0 RXC", "T11 GMAC1 RXC";
+						skew-delay = <15>;
+					};
+					conf2 {
+						pins = "P8 GMAC0 TXEN", "V11 GMAC1 TXEN";
+						skew-delay = <7>;
+					};
+					conf3 {
+						pins = "V7 GMAC0 TXC";
+						skew-delay = <11>;
+					};
+					conf4 {
+						pins = "P10 GMAC1 TXC";
+						skew-delay = <10>;
+					};
+					conf5 {
+						/* The data lines all have default skew */
+						pins = "U8 GMAC0 RXD0", "V8 GMAC0 RXD1",
+						       "P9 GMAC0 RXD2", "R9 GMAC0 RXD3",
+						       "U7 GMAC0 TXD0", "T7 GMAC0 TXD1",
+						       "R7 GMAC0 TXD2", "P7 GMAC0 TXD3",
+						       "R11 GMAC1 RXD0", "P11 GMAC1 RXD1",
+						       "V12 GMAC1 RXD2", "U12 GMAC1 RXD3",
+						       "R10 GMAC1 TXD0", "T10 GMAC1 TXD1",
+						       "U10 GMAC1 TXD2", "V10 GMAC1 TXD3";
+						skew-delay = <7>;
+					};
+					/* Set up drive strength on GMAC0 to 16 mA */
+					conf6 {
+						groups = "gmii_gmac0_grp";
+						drive-strength = <16>;
+					};
+				};
 			};
 		};
 
@@ -130,6 +187,18 @@
 			pinctrl-0 = <&gpio1_default_pins>;
 		};
 
+		ethernet@60000000 {
+			status = "okay";
+
+			ethernet-port@0 {
+				phy-mode = "rgmii";
+				phy-handle = <&phy0>;
+			};
+			ethernet-port@1 {
+				/* Not used in this platform */
+			};
+		};
+
 		ata@63000000 {
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/gemini-rut1xx.dts b/arch/arm/boot/dts/gemini-rut1xx.dts
index 500057b6570e..15f20178642c 100644
--- a/arch/arm/boot/dts/gemini-rut1xx.dts
+++ b/arch/arm/boot/dts/gemini-rut1xx.dts
@@ -58,6 +58,19 @@
 		};
 	};
 
+	mdio0: ethernet-phy {
+		compatible = "virtual,mdio-gpio";
+		gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>, /* MDC */
+			<&gpio0 21 GPIO_ACTIVE_HIGH>; /* MDIO */
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		phy0: ethernet-phy@1 {
+			reg = <1>;
+			device_type = "ethernet-phy";
+		};
+	};
+
 	soc {
 		flash@30000000 {
 			status = "okay";
@@ -101,5 +114,17 @@
 			pinctrl-names = "default";
 			pinctrl-0 = <&gpio1_default_pins>;
 		};
+
+		ethernet@60000000 {
+			status = "okay";
+
+			ethernet-port@0 {
+				phy-mode = "rgmii";
+				phy-handle = <&phy0>;
+			};
+			ethernet-port@1 {
+				/* Not used in this platform */
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/gemini-wbd111.dts b/arch/arm/boot/dts/gemini-wbd111.dts
index b413fd12c5ba..b4ec9ad85d72 100644
--- a/arch/arm/boot/dts/gemini-wbd111.dts
+++ b/arch/arm/boot/dts/gemini-wbd111.dts
@@ -69,6 +69,19 @@
 		};
 	};
 
+	mdio0: ethernet-phy {
+		compatible = "virtual,mdio-gpio";
+		gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>, /* MDC */
+			<&gpio0 21 GPIO_ACTIVE_HIGH>; /* MDIO */
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		phy0: ethernet-phy@1 {
+			reg = <1>;
+			device_type = "ethernet-phy";
+		};
+	};
+
 	soc {
 		flash@30000000 {
 			status = "okay";
@@ -125,5 +138,39 @@
 			pinctrl-names = "default";
 			pinctrl-0 = <&gpio0_default_pins>;
 		};
+
+		pci@50000000 {
+			status = "okay";
+			interrupt-map-mask = <0xf800 0 0 7>;
+			interrupt-map =
+				<0x4800 0 0 1 &pci_intc 0>, /* Slot 9 */
+				<0x4800 0 0 2 &pci_intc 1>,
+				<0x4800 0 0 3 &pci_intc 2>,
+				<0x4800 0 0 4 &pci_intc 3>,
+				<0x5000 0 0 1 &pci_intc 1>, /* Slot 10 */
+				<0x5000 0 0 2 &pci_intc 2>,
+				<0x5000 0 0 3 &pci_intc 3>,
+				<0x5000 0 0 4 &pci_intc 0>,
+				<0x5800 0 0 1 &pci_intc 2>, /* Slot 11 */
+				<0x5800 0 0 2 &pci_intc 3>,
+				<0x5800 0 0 3 &pci_intc 0>,
+				<0x5800 0 0 4 &pci_intc 1>,
+				<0x6000 0 0 1 &pci_intc 3>, /* Slot 12 */
+				<0x6000 0 0 2 &pci_intc 0>,
+				<0x6000 0 0 3 &pci_intc 1>,
+				<0x6000 0 0 4 &pci_intc 2>;
+		};
+
+		ethernet@60000000 {
+			status = "okay";
+
+			ethernet-port@0 {
+				phy-mode = "rgmii";
+				phy-handle = <&phy0>;
+			};
+			ethernet-port@1 {
+				/* Not used in this platform */
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/gemini-wbd222.dts b/arch/arm/boot/dts/gemini-wbd222.dts
index 3ba710538662..6d25bcc046e7 100644
--- a/arch/arm/boot/dts/gemini-wbd222.dts
+++ b/arch/arm/boot/dts/gemini-wbd222.dts
@@ -69,6 +69,24 @@
 		};
 	};
 
+	mdio0: ethernet-phy {
+		compatible = "virtual,mdio-gpio";
+		gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>, /* MDC */
+			<&gpio0 21 GPIO_ACTIVE_HIGH>; /* MDIO */
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		phy0: ethernet-phy@1 {
+			reg = <1>;
+			device_type = "ethernet-phy";
+		};
+
+		phy1: ethernet-phy@3 {
+			reg = <3>;
+			device_type = "ethernet-phy";
+		};
+	};
+
 	soc {
 		flash@30000000 {
 			status = "okay";
@@ -118,6 +136,13 @@
 						"gpio0bgrp";
 					};
 				};
+				pinctrl-gmii {
+					/* This platform use both the ethernet ports */
+					mux {
+						function = "gmii";
+						groups = "gmii_gmac0_grp", "gmii_gmac1_grp";
+					};
+				};
 			};
 		};
 
@@ -125,5 +150,40 @@
 			pinctrl-names = "default";
 			pinctrl-0 = <&gpio0_default_pins>;
 		};
+
+		pci@50000000 {
+			status = "okay";
+			interrupt-map-mask = <0xf800 0 0 7>;
+			interrupt-map =
+				<0x4800 0 0 1 &pci_intc 0>, /* Slot 9 */
+				<0x4800 0 0 2 &pci_intc 1>,
+				<0x4800 0 0 3 &pci_intc 2>,
+				<0x4800 0 0 4 &pci_intc 3>,
+				<0x5000 0 0 1 &pci_intc 1>, /* Slot 10 */
+				<0x5000 0 0 2 &pci_intc 2>,
+				<0x5000 0 0 3 &pci_intc 3>,
+				<0x5000 0 0 4 &pci_intc 0>,
+				<0x5800 0 0 1 &pci_intc 2>, /* Slot 11 */
+				<0x5800 0 0 2 &pci_intc 3>,
+				<0x5800 0 0 3 &pci_intc 0>,
+				<0x5800 0 0 4 &pci_intc 1>,
+				<0x6000 0 0 1 &pci_intc 3>, /* Slot 12 */
+				<0x6000 0 0 2 &pci_intc 0>,
+				<0x6000 0 0 3 &pci_intc 1>,
+				<0x6000 0 0 4 &pci_intc 2>;
+		};
+
+		ethernet@60000000 {
+			status = "okay";
+
+			ethernet-port@0 {
+				phy-mode = "rgmii";
+				phy-handle = <&phy0>;
+			};
+			ethernet-port@1 {
+				phy-mode = "rgmii";
+				phy-handle = <&phy1>;
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/gemini.dtsi b/arch/arm/boot/dts/gemini.dtsi
index cb5c925bd597..0568baca500a 100644
--- a/arch/arm/boot/dts/gemini.dtsi
+++ b/arch/arm/boot/dts/gemini.dtsi
@@ -114,9 +114,16 @@
 					};
 				};
 				gmii_default_pins: pinctrl-gmii {
+					/*
+					 * Only activate GMAC0 by default since
+					 * GMAC1 will overlap with 8 GPIO lines
+					 * gpio2a, gpio2b. Overlay groups with
+					 * "gmii_gmac0_grp", "gmii_gmac1_grp" for
+					 * both ethernet interfaces.
+					 */
 					mux {
 						function = "gmii";
-						groups = "gmiigrp";
+						groups = "gmii_gmac0_grp";
 					};
 				};
 				pci_default_pins: pinctrl-pci {
@@ -316,6 +323,41 @@
 			};
 		};
 
+		ethernet@60000000 {
+			compatible = "cortina,gemini-ethernet";
+			reg = <0x60000000 0x4000>, /* Global registers, queue */
+			      <0x60004000 0x2000>, /* V-bit */
+			      <0x60006000 0x2000>; /* A-bit */
+			pinctrl-names = "default";
+			pinctrl-0 = <&gmii_default_pins>;
+			status = "disabled";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			gmac0: ethernet-port@0 {
+				compatible = "cortina,gemini-ethernet-port";
+				reg = <0x60008000 0x2000>, /* Port 0 DMA/TOE */
+				      <0x6000a000 0x2000>; /* Port 0 GMAC */
+				interrupt-parent = <&intcon>;
+				interrupts = <1 IRQ_TYPE_LEVEL_HIGH>;
+				resets = <&syscon GEMINI_RESET_GMAC0>;
+				clocks = <&syscon GEMINI_CLK_GATE_GMAC0>;
+				clock-names = "PCLK";
+			};
+
+			gmac1: ethernet-port@1 {
+				compatible = "cortina,gemini-ethernet-port";
+				reg = <0x6000c000 0x2000>, /* Port 1 DMA/TOE */
+				      <0x6000e000 0x2000>; /* Port 1 GMAC */
+				interrupt-parent = <&intcon>;
+				interrupts = <2 IRQ_TYPE_LEVEL_HIGH>;
+				resets = <&syscon GEMINI_RESET_GMAC1>;
+				clocks = <&syscon GEMINI_CLK_GATE_GMAC1>;
+				clock-names = "PCLK";
+			};
+		};
+
 		ata@63000000 {
 			compatible = "cortina,gemini-pata", "faraday,ftide010";
 			reg = <0x63000000 0x1000>;
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index 09ce8b81fafa..9445f8e1473c 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -122,7 +122,7 @@
 			};
 
 			can1: can@43f88000 {
-				compatible = "fsl,imx25-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx25-flexcan";
 				reg = <0x43f88000 0x4000>;
 				interrupts = <43>;
 				clocks = <&clks 75>, <&clks 75>;
@@ -131,7 +131,7 @@
 			};
 
 			can2: can@43f8c000 {
-				compatible = "fsl,imx25-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx25-flexcan";
 				reg = <0x43f8c000 0x4000>;
 				interrupts = <44>;
 				clocks = <&clks 76>, <&clks 76>;
@@ -628,11 +628,13 @@
 		usbphy0: usb-phy@0 {
 			reg = <0>;
 			compatible = "usb-nop-xceiv";
+			#phy-cells = <0>;
 		};
 
 		usbphy1: usb-phy@1 {
 			reg = <1>;
 			compatible = "usb-nop-xceiv";
+			#phy-cells = <0>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx27-pdk.dts b/arch/arm/boot/dts/imx27-pdk.dts
index 96f442ba6d22..2a140c8ae6d2 100644
--- a/arch/arm/boot/dts/imx27-pdk.dts
+++ b/arch/arm/boot/dts/imx27-pdk.dts
@@ -30,6 +30,7 @@
 			reg = <0>;
 			clocks = <&clks IMX27_CLK_DUMMY>;
 			clock-names = "main_clk";
+			#phy-cells = <0>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts
index 2a9198f99a8d..2ed2d73b087e 100644
--- a/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts
+++ b/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts
@@ -63,6 +63,7 @@
 			vcc-supply = <&reg_5v0>;
 			clocks = <&clks IMX27_CLK_DUMMY>;
 			clock-names = "main_clk";
+			#phy-cells = <0>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi b/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi
index c973c5d91875..c9095b7654c6 100644
--- a/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi
+++ b/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi
@@ -53,6 +53,7 @@
 			vcc-supply = <&sw3_reg>;
 			clocks = <&clks IMX27_CLK_DUMMY>;
 			clock-names = "main_clk";
+			#phy-cells = <0>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx28-ts4600.dts b/arch/arm/boot/dts/imx28-ts4600.dts
new file mode 100644
index 000000000000..1e391c9f1b7a
--- /dev/null
+++ b/arch/arm/boot/dts/imx28-ts4600.dts
@@ -0,0 +1,79 @@
+/*
+ * Copyright (C) 2016 Savoir-Faire Linux
+ * Author: Sebastien Bourdelin <sebastien.bourdelin@savoirfairelinux.com>
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+#include "imx28.dtsi"
+#include "dt-bindings/gpio/gpio.h"
+
+/ {
+
+	model = "Technologic Systems i.MX28 TS-4600";
+	compatible = "technologic,imx28-ts4600", "fsl,imx28";
+
+	memory {
+		reg = <0x40000000 0x10000000>;   /* 256MB */
+	};
+
+	apb@80000000 {
+		apbh@80000000 {
+			ssp0: ssp@80010000 {
+				compatible = "fsl,imx28-mmc";
+				pinctrl-names = "default";
+				pinctrl-0 = <&mmc0_4bit_pins_a
+					     &mmc0_sck_cfg
+					     &en_sd_pwr>;
+				broken-cd = <1>;
+				bus-width = <4>;
+				vmmc-supply = <&reg_vddio_sd0>;
+				status = "okay";
+			};
+
+			pinctrl@80018000 {
+
+				en_sd_pwr: en-sd-pwr@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						MX28_PAD_PWM3__GPIO_3_28
+					>;
+					fsl,drive-strength = <MXS_DRIVE_4mA>;
+					fsl,voltage = <MXS_VOLTAGE_HIGH>;
+					fsl,pull-up = <MXS_PULL_DISABLE>;
+				};
+
+			};
+		};
+
+		apbx@80040000 {
+			pwm: pwm@80064000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&pwm2_pins_a>;
+				status = "okay";
+			};
+
+			duart: serial@80074000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&duart_pins_a>;
+				status = "okay";
+			};
+		};
+	};
+
+	reg_vddio_sd0: regulator-vddio-sd0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vddio-sd0";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-boot-on;
+		gpio = <&gpio3 28 GPIO_ACTIVE_LOW>;
+	};
+
+};
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index 2f4ebe0318d3..e52e05c0fe56 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -1038,7 +1038,7 @@
 			};
 
 			can0: can@80032000 {
-				compatible = "fsl,imx28-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx28-flexcan";
 				reg = <0x80032000 0x2000>;
 				interrupts = <8>;
 				clocks = <&clks 58>, <&clks 58>;
@@ -1047,7 +1047,7 @@
 			};
 
 			can1: can@80034000 {
-				compatible = "fsl,imx28-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx28-flexcan";
 				reg = <0x80034000 0x2000>;
 				interrupts = <9>;
 				clocks = <&clks 59>, <&clks 59>;
diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi
index 6d5e6a60bee7..e08c0c193767 100644
--- a/arch/arm/boot/dts/imx35.dtsi
+++ b/arch/arm/boot/dts/imx35.dtsi
@@ -303,7 +303,7 @@
 			};
 
 			can1: can@53fe4000 {
-				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx35-flexcan";
 				reg = <0x53fe4000 0x1000>;
 				clocks = <&clks 33>, <&clks 33>;
 				clock-names = "ipg", "per";
@@ -312,7 +312,7 @@
 			};
 
 			can2: can@53fe8000 {
-				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx35-flexcan";
 				reg = <0x53fe8000 0x1000>;
 				clocks = <&clks 34>, <&clks 34>;
 				clock-names = "ipg", "per";
@@ -402,11 +402,13 @@
 		usbphy0: usb-phy@0 {
 			reg = <0>;
 			compatible = "usb-nop-xceiv";
+			#phy-cells = <0>;
 		};
 
 		usbphy1: usb-phy@1 {
 			reg = <1>;
 			compatible = "usb-nop-xceiv";
+			#phy-cells = <0>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx51-babbage.dts b/arch/arm/boot/dts/imx51-babbage.dts
index 2a694c5cc8ae..4ac5ab614a7f 100644
--- a/arch/arm/boot/dts/imx51-babbage.dts
+++ b/arch/arm/boot/dts/imx51-babbage.dts
@@ -25,18 +25,41 @@
 		reg = <0x90000000 0x20000000>;
 	};
 
-	clocks {
-		ckih1 {
-			clock-frequency = <22579200>;
-		};
+	ckih1 {
+		clock-frequency = <22579200>;
+	};
 
-		clk_26M: codec_clock {
-			compatible = "fixed-clock";
-			reg=<0>;
-			#clock-cells = <0>;
-			clock-frequency = <26000000>;
-			gpios = <&gpio4 26 GPIO_ACTIVE_LOW>;
-		};
+	clk_osc: clk-osc {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <26000000>;
+	};
+
+	clk_osc_gate: clk-osc-gate {
+		compatible = "gpio-gate-clock";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_clk26mhz_osc>;
+		clocks = <&clk_osc>;
+		#clock-cells = <0>;
+		enable-gpios = <&gpio3 1 GPIO_ACTIVE_HIGH>;
+	};
+
+	clk_audio: clk-audio {
+		compatible = "gpio-gate-clock";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_clk26mhz_audio>;
+		clocks = <&clk_osc_gate>;
+		#clock-cells = <0>;
+		enable-gpios = <&gpio4 26 GPIO_ACTIVE_LOW>;
+	};
+
+	clk_usb: clk-usb {
+		compatible = "gpio-gate-clock";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_clk26mhz_usb>;
+		clocks = <&clk_osc_gate>;
+		#clock-cells = <0>;
+		enable-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>;
 	};
 
 	display1: disp1 {
@@ -162,9 +185,11 @@
 		usbh1phy: usbh1phy@0 {
 			compatible = "usb-nop-xceiv";
 			reg = <0>;
-			clocks = <&clks IMX5_CLK_DUMMY>;
+			clocks = <&clk_usb>;
 			clock-names = "main_clk";
 			reset-gpios = <&gpio2 5 GPIO_ACTIVE_LOW>;
+			vcc-supply = <&vusb_reg>;
+			#phy-cells = <0>;
 		};
 	};
 };
@@ -240,6 +265,10 @@
 				regulator-max-microvolt = <3150000>;
 			};
 
+			vusb_reg: vusb {
+				regulator-boot-on;
+			};
+
 			vusb2_reg: vusb2 {
 				regulator-min-microvolt = <2400000>;
 				regulator-max-microvolt = <2775000>;
@@ -339,10 +368,8 @@
 
 	sgtl5000: codec@a {
 		compatible = "fsl,sgtl5000";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_clkcodec>;
 		reg = <0x0a>;
-		clocks = <&clk_26M>;
+		clocks = <&clk_audio>;
 		VDDA-supply = <&vdig_reg>;
 		VDDIO-supply = <&vvideo_reg>;
 	};
@@ -413,6 +440,10 @@
 	status = "okay";
 };
 
+&usbphy0 {
+	vcc-supply = <&vusb_reg>;
+};
+
 &usbotg {
 	dr_mode = "otg";
 	disable-over-current;
@@ -431,9 +462,21 @@
 			>;
 		};
 
-		pinctrl_clkcodec: clkcodecgrp {
+		pinctrl_clk26mhz_audio: clk26mhzaudiocgrp {
+			fsl,pins = <
+				MX51_PAD_CSPI1_RDY__GPIO4_26		0x85
+			>;
+		};
+
+		pinctrl_clk26mhz_osc: clk26mhzoscgrp {
+			fsl,pins = <
+				MX51_PAD_DI1_PIN12__GPIO3_1		0x85
+			>;
+		};
+
+		pinctrl_clk26mhz_usb: clk26mhzusbgrp {
 			fsl,pins = <
-				MX51_PAD_CSPI1_RDY__GPIO4_26		0x80000000
+				MX51_PAD_EIM_D17__GPIO2_1		0x85
 			>;
 		};
 
diff --git a/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts b/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts
index 1305b05c7ed9..b3d952f37cdc 100644
--- a/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts
+++ b/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts
@@ -94,6 +94,7 @@
 			clocks = <&clks IMX5_CLK_USB_PHY_GATE>;
 			clock-names = "main_clk";
 			clock-frequency = <19200000>;
+			#phy-cells = <0>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx51-ts4800.dts b/arch/arm/boot/dts/imx51-ts4800.dts
index 564233e97412..f59b02bae68d 100644
--- a/arch/arm/boot/dts/imx51-ts4800.dts
+++ b/arch/arm/boot/dts/imx51-ts4800.dts
@@ -149,18 +149,18 @@
 		#size-cells = <1>;
 		ranges = <0 0 0 0x1d000>;
 
-		syscon: syscon@b0010000 {
+		syscon: syscon@10000 {
 			compatible = "syscon", "simple-mfd";
 			reg = <0x10000 0x3d>;
 			reg-io-width = <2>;
 
-			wdt@e {
+			wdt {
 				compatible = "technologic,ts4800-wdt";
 				syscon = <&syscon 0xe>;
 			};
 		};
 
-		touchscreen {
+		touchscreen@12000 {
 			compatible = "technologic,ts4800-ts";
 			reg = <0x12000 0x1000>;
 			syscon = <&syscon 0x10 6>;
diff --git a/arch/arm/boot/dts/imx51-zii-rdu1.dts b/arch/arm/boot/dts/imx51-zii-rdu1.dts
index 49be0e1c812d..5306b78de0ca 100644
--- a/arch/arm/boot/dts/imx51-zii-rdu1.dts
+++ b/arch/arm/boot/dts/imx51-zii-rdu1.dts
@@ -242,7 +242,7 @@
 
 	sound {
 		compatible = "simple-audio-card";
-		simple-audio-card,name = "RDU1 audio";
+		simple-audio-card,name = "Front";
 		simple-audio-card,format = "i2s";
 		simple-audio-card,bitclock-master = <&sound_codec>;
 		simple-audio-card,frame-master = <&sound_codec>;
@@ -251,7 +251,7 @@
 		simple-audio-card,routing =
 			"Headphone Jack", "HPLEFT",
 			"Headphone Jack", "HPRIGHT";
-		simple-audio-card,aux-devs = <&tpa6130a2>;
+		simple-audio-card,aux-devs = <&hpa1>;
 
 		sound_cpu: simple-audio-card,cpu {
 			sound-dai = <&ssi2>;
@@ -271,6 +271,7 @@
 		clock-names = "main_clk";
 		reset-gpios = <&gpio4 8 GPIO_ACTIVE_LOW>;
 		vcc-supply = <&vusb_reg>;
+		#phy-cells = <0>;
 	};
 
 	usbh2phy: usbphy2 {
@@ -281,6 +282,7 @@
 		clock-names = "main_clk";
 		reset-gpios = <&gpio4 7 GPIO_ACTIVE_LOW>;
 		vcc-supply = <&vusb_reg>;
+		#phy-cells = <0>;
 	};
 };
 
@@ -428,13 +430,13 @@
 			#size-cells = <0>;
 			led-control = <0x0 0x0 0x3f83f8 0x0>;
 
-			sysled0 {
+			sysled0@3 {
 				reg = <3>;
 				label = "system:green:status";
 				linux,default-trigger = "default-on";
 			};
 
-			sysled1 {
+			sysled1@4 {
 				reg = <4>;
 				label = "system:green:act";
 				linux,default-trigger = "heartbeat";
@@ -479,7 +481,7 @@
 		reg = <0x50>;
 	};
 
-	tpa6130a2: amp@60 {
+	hpa1: amp@60 {
 		compatible = "ti,tpa6130a2";
 		reg = <0x60>;
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/imx51.dtsi b/arch/arm/boot/dts/imx51.dtsi
index 378be720b3c7..00d30bd70068 100644
--- a/arch/arm/boot/dts/imx51.dtsi
+++ b/arch/arm/boot/dts/imx51.dtsi
@@ -113,6 +113,7 @@
 			reg = <0>;
 			clocks = <&clks IMX5_CLK_USB_PHY_GATE>;
 			clock-names = "main_clk";
+			#phy-cells = <0>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/imx53-cx9020.dts b/arch/arm/boot/dts/imx53-cx9020.dts
index 4f54fd4418a3..5e67e43004e7 100644
--- a/arch/arm/boot/dts/imx53-cx9020.dts
+++ b/arch/arm/boot/dts/imx53-cx9020.dts
@@ -152,7 +152,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_fec>;
 	phy-mode = "rmii";
-	phy-reset-gpios = <&gpio7 6 GPIO_ACTIVE_HIGH>;
+	phy-reset-gpios = <&gpio7 6 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx53-m53.dtsi b/arch/arm/boot/dts/imx53-m53.dtsi
index ec390aa562c3..7ce69c63510c 100644
--- a/arch/arm/boot/dts/imx53-m53.dtsi
+++ b/arch/arm/boot/dts/imx53-m53.dtsi
@@ -64,7 +64,6 @@
 
 		stmpe_touchscreen {
 			compatible = "st,stmpe-ts";
-			reg = <0>;
 			st,sample-time = <4>;
 			st,mod-12b = <1>;
 			st,ref-sel = <0>;
diff --git a/arch/arm/boot/dts/imx53-tx53-x03x.dts b/arch/arm/boot/dts/imx53-tx53-x03x.dts
index 7eb53e48c2f4..fe15c9555d6e 100644
--- a/arch/arm/boot/dts/imx53-tx53-x03x.dts
+++ b/arch/arm/boot/dts/imx53-tx53-x03x.dts
@@ -53,132 +53,130 @@
 		display = &display;
 	};
 
-	soc {
-		display: disp0 {
-			compatible = "fsl,imx-parallel-display";
-			interface-pix-fmt = "rgb24";
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_rgb24_vga1>;
-			status = "okay";
+	display: disp0 {
+		compatible = "fsl,imx-parallel-display";
+		interface-pix-fmt = "rgb24";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_rgb24_vga1>;
+		status = "okay";
 
-			port {
-				display0_in: endpoint {
-					remote-endpoint = <&ipu_di0_disp0>;
-				};
+		port {
+			display0_in: endpoint {
+				remote-endpoint = <&ipu_di0_disp0>;
 			};
+		};
 
-			display-timings {
-				VGA {
-					clock-frequency = <25200000>;
-					hactive = <640>;
-					vactive = <480>;
-					hback-porch = <48>;
-					hsync-len = <96>;
-					hfront-porch = <16>;
-					vback-porch = <31>;
-					vsync-len = <2>;
-					vfront-porch = <12>;
-					hsync-active = <0>;
-					vsync-active = <0>;
-					de-active = <1>;
-					pixelclk-active = <0>;
-				};
+		display-timings {
+			VGA {
+				clock-frequency = <25200000>;
+				hactive = <640>;
+				vactive = <480>;
+				hback-porch = <48>;
+				hsync-len = <96>;
+				hfront-porch = <16>;
+				vback-porch = <31>;
+				vsync-len = <2>;
+				vfront-porch = <12>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+				de-active = <1>;
+				pixelclk-active = <0>;
+			};
 
-				ETV570 {
-					clock-frequency = <25200000>;
-					hactive = <640>;
-					vactive = <480>;
-					hback-porch = <114>;
-					hsync-len = <30>;
-					hfront-porch = <16>;
-					vback-porch = <32>;
-					vsync-len = <3>;
-					vfront-porch = <10>;
-					hsync-active = <0>;
-					vsync-active = <0>;
-					de-active = <1>;
-					pixelclk-active = <0>;
-				};
+			ETV570 {
+				clock-frequency = <25200000>;
+				hactive = <640>;
+				vactive = <480>;
+				hback-porch = <114>;
+				hsync-len = <30>;
+				hfront-porch = <16>;
+				vback-porch = <32>;
+				vsync-len = <3>;
+				vfront-porch = <10>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+				de-active = <1>;
+				pixelclk-active = <0>;
+			};
 
-				ET0350 {
-					clock-frequency = <6413760>;
-					hactive = <320>;
-					vactive = <240>;
-					hback-porch = <34>;
-					hsync-len = <34>;
-					hfront-porch = <20>;
-					vback-porch = <15>;
-					vsync-len = <3>;
-					vfront-porch = <4>;
-					hsync-active = <0>;
-					vsync-active = <0>;
-					de-active = <1>;
-					pixelclk-active = <0>;
-				};
+			ET0350 {
+				clock-frequency = <6413760>;
+				hactive = <320>;
+				vactive = <240>;
+				hback-porch = <34>;
+				hsync-len = <34>;
+				hfront-porch = <20>;
+				vback-porch = <15>;
+				vsync-len = <3>;
+				vfront-porch = <4>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+				de-active = <1>;
+				pixelclk-active = <0>;
+			};
 
-				ET0430 {
-					clock-frequency = <9009000>;
-					hactive = <480>;
-					vactive = <272>;
-					hback-porch = <2>;
-					hsync-len = <41>;
-					hfront-porch = <2>;
-					vback-porch = <2>;
-					vsync-len = <10>;
-					vfront-porch = <2>;
-					hsync-active = <0>;
-					vsync-active = <0>;
-					de-active = <1>;
-					pixelclk-active = <1>;
-				};
+			ET0430 {
+				clock-frequency = <9009000>;
+				hactive = <480>;
+				vactive = <272>;
+				hback-porch = <2>;
+				hsync-len = <41>;
+				hfront-porch = <2>;
+				vback-porch = <2>;
+				vsync-len = <10>;
+				vfront-porch = <2>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+				de-active = <1>;
+				pixelclk-active = <1>;
+			};
 
-				ET0500 {
-					clock-frequency = <33264000>;
-					hactive = <800>;
-					vactive = <480>;
-					hback-porch = <88>;
-					hsync-len = <128>;
-					hfront-porch = <40>;
-					vback-porch = <33>;
-					vsync-len = <2>;
-					vfront-porch = <10>;
-					hsync-active = <0>;
-					vsync-active = <0>;
-					de-active = <1>;
-					pixelclk-active = <0>;
-				};
+			ET0500 {
+				clock-frequency = <33264000>;
+				hactive = <800>;
+				vactive = <480>;
+				hback-porch = <88>;
+				hsync-len = <128>;
+				hfront-porch = <40>;
+				vback-porch = <33>;
+				vsync-len = <2>;
+				vfront-porch = <10>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+				de-active = <1>;
+				pixelclk-active = <0>;
+			};
 
-				ET0700 { /* same as ET0500 */
-					clock-frequency = <33264000>;
-					hactive = <800>;
-					vactive = <480>;
-					hback-porch = <88>;
-					hsync-len = <128>;
-					hfront-porch = <40>;
-					vback-porch = <33>;
-					vsync-len = <2>;
-					vfront-porch = <10>;
-					hsync-active = <0>;
-					vsync-active = <0>;
-					de-active = <1>;
-					pixelclk-active = <0>;
-				};
+			ET0700 { /* same as ET0500 */
+				clock-frequency = <33264000>;
+				hactive = <800>;
+				vactive = <480>;
+				hback-porch = <88>;
+				hsync-len = <128>;
+				hfront-porch = <40>;
+				vback-porch = <33>;
+				vsync-len = <2>;
+				vfront-porch = <10>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+				de-active = <1>;
+				pixelclk-active = <0>;
+			};
 
-				ETQ570 {
-					clock-frequency = <6596040>;
-					hactive = <320>;
-					vactive = <240>;
-					hback-porch = <38>;
-					hsync-len = <30>;
-					hfront-porch = <30>;
-					vback-porch = <16>;
-					vsync-len = <3>;
-					vfront-porch = <4>;
-					hsync-active = <0>;
-					vsync-active = <0>;
-					de-active = <1>;
-					pixelclk-active = <0>;
-				};
+			ETQ570 {
+				clock-frequency = <6596040>;
+				hactive = <320>;
+				vactive = <240>;
+				hback-porch = <38>;
+				hsync-len = <30>;
+				hfront-porch = <30>;
+				vback-porch = <16>;
+				vsync-len = <3>;
+				vfront-porch = <4>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+				de-active = <1>;
+				pixelclk-active = <0>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/imx53-tx53.dtsi b/arch/arm/boot/dts/imx53-tx53.dtsi
index 71b58b6933e1..a22e461fc168 100644
--- a/arch/arm/boot/dts/imx53-tx53.dtsi
+++ b/arch/arm/boot/dts/imx53-tx53.dtsi
@@ -225,10 +225,16 @@
 	mac-address = [000000000000]; /* placeholder; will be overwritten by bootloader */
 	status = "okay";
 
-	phy0: ethernet-phy@0 {
-		interrupt-parent = <&gpio2>;
-		interrupts = <4 IRQ_TYPE_EDGE_FALLING>;
-		device_type = "ethernet-phy";
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		phy0: ethernet-phy@0 {
+			reg = <0>;
+			interrupt-parent = <&gpio2>;
+			interrupts = <4 IRQ_TYPE_EDGE_FALLING>;
+			device_type = "ethernet-phy";
+		};
 	};
 };
 
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index 589a67c5f796..1040251f2951 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -116,6 +116,28 @@
 		};
 	};
 
+	pmu {
+		compatible = "arm,cortex-a8-pmu";
+		interrupt-parent = <&tzic>;
+		interrupts = <77>;
+	};
+
+	usbphy0: usbphy-0 {
+		compatible = "usb-nop-xceiv";
+		clocks = <&clks IMX5_CLK_USB_PHY1_GATE>;
+		clock-names = "main_clk";
+		#phy-cells = <0>;
+		status = "okay";
+	};
+
+	usbphy1: usbphy-1 {
+		compatible = "usb-nop-xceiv";
+		clocks = <&clks IMX5_CLK_USB_PHY2_GATE>;
+		clock-names = "main_clk";
+		#phy-cells = <0>;
+		status = "okay";
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -299,20 +321,6 @@
 				reg = <0x53f00000 0x60>;
 			};
 
-			usbphy0: usbphy-0 {
-				compatible = "usb-nop-xceiv";
-				clocks = <&clks IMX5_CLK_USB_PHY1_GATE>;
-				clock-names = "main_clk";
-				status = "okay";
-			};
-
-			usbphy1: usbphy-1 {
-				compatible = "usb-nop-xceiv";
-				clocks = <&clks IMX5_CLK_USB_PHY2_GATE>;
-				clock-names = "main_clk";
-				status = "okay";
-			};
-
 			usbotg: usb@53f80000 {
 				compatible = "fsl,imx53-usb", "fsl,imx27-usb";
 				reg = <0x53f80000 0x0200>;
@@ -433,13 +441,11 @@
 				clock-names = "ipg", "per";
 			};
 
-			srtc: srtc@53fa4000 {
-				compatible = "fsl,imx53-rtc", "fsl,imx25-rtc";
+			srtc: rtc@53fa4000 {
+				compatible = "fsl,imx53-rtc";
 				reg = <0x53fa4000 0x4000>;
 				interrupts = <24>;
-				interrupt-parent = <&tzic>;
 				clocks = <&clks IMX5_CLK_SRTC_GATE>;
-				clock-names = "ipg";
 			};
 
 			iomuxc: iomuxc@53fa8000 {
@@ -545,7 +551,7 @@
 			};
 
 			can1: can@53fc8000 {
-				compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx53-flexcan";
 				reg = <0x53fc8000 0x4000>;
 				interrupts = <82>;
 				clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>,
@@ -555,7 +561,7 @@
 			};
 
 			can2: can@53fcc000 {
-				compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx53-flexcan";
 				reg = <0x53fcc000 0x4000>;
 				interrupts = <83>;
 				clocks = <&clks IMX5_CLK_CAN2_IPG_GATE>,
@@ -822,10 +828,5 @@
 			reg = <0xf8000000 0x20000>;
 			clocks = <&clks IMX5_CLK_OCRAM>;
 		};
-
-		pmu {
-			compatible = "arm,cortex-a8-pmu";
-			interrupts = <77>;
-		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx6dl-aristainetos_4.dts b/arch/arm/boot/dts/imx6dl-aristainetos_4.dts
index cc418cecabdb..3c9f4af9e9ff 100644
--- a/arch/arm/boot/dts/imx6dl-aristainetos_4.dts
+++ b/arch/arm/boot/dts/imx6dl-aristainetos_4.dts
@@ -31,35 +31,33 @@
 		reg = <0x10000000 0x40000000>;
 	};
 
-	soc {
-		display0: disp0 {
-			compatible = "fsl,imx-parallel-display";
-			interface-pix-fmt = "rgb24";
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_ipu_disp>;
-			status = "okay";
+	display0: disp0 {
+		compatible = "fsl,imx-parallel-display";
+		interface-pix-fmt = "rgb24";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_ipu_disp>;
+		status = "okay";
 
-			display-timings {
-				480x800p60 {
-					native-mode;
-					clock-frequency = <30000000>;
-					hactive = <480>;
-					vactive = <800>;
-					hfront-porch = <59>;
-					hback-porch = <10>;
-					hsync-len = <10>;
-					vback-porch = <15>;
-					vfront-porch = <15>;
-					vsync-len = <15>;
-					hsync-active = <1>;
-					vsync-active = <1>;
-				};
+		display-timings {
+			480x800p60 {
+				native-mode;
+				clock-frequency = <30000000>;
+				hactive = <480>;
+				vactive = <800>;
+				hfront-porch = <59>;
+				hback-porch = <10>;
+				hsync-len = <10>;
+				vback-porch = <15>;
+				vfront-porch = <15>;
+				vsync-len = <15>;
+				hsync-active = <1>;
+				vsync-active = <1>;
 			};
+		};
 
-			port {
-				display0_in: endpoint {
-					remote-endpoint = <&ipu1_di0_disp0>;
-				};
+		port {
+			display0_in: endpoint {
+				remote-endpoint = <&ipu1_di0_disp0>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/imx6dl-aristainetos_7.dts b/arch/arm/boot/dts/imx6dl-aristainetos_7.dts
index 126ff964eded..96cd835ccbf6 100644
--- a/arch/arm/boot/dts/imx6dl-aristainetos_7.dts
+++ b/arch/arm/boot/dts/imx6dl-aristainetos_7.dts
@@ -20,34 +20,32 @@
 		reg = <0x10000000 0x40000000>;
 	};
 
-	soc {
-		display0: disp0 {
-			compatible = "fsl,imx-parallel-display";
-			interface-pix-fmt = "rgb24";
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_ipu_disp>;
-			status = "okay";
+	display0: disp0 {
+		compatible = "fsl,imx-parallel-display";
+		interface-pix-fmt = "rgb24";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_ipu_disp>;
+		status = "okay";
 
-			display-timings {
-				800x480p60 {
-					native-mode;
-					clock-frequency = <33246000>;
-					hactive = <800>;
-					vactive = <480>;
-					hfront-porch = <88>;
-					hback-porch = <88>;
-					hsync-len = <80>;
-					vback-porch = <10>;
-					vfront-porch = <10>;
-					vsync-len = <25>;
-					vsync-active = <1>;
-				};
+		display-timings {
+			800x480p60 {
+				native-mode;
+				clock-frequency = <33246000>;
+				hactive = <800>;
+				vactive = <480>;
+				hfront-porch = <88>;
+				hback-porch = <88>;
+				hsync-len = <80>;
+				vback-porch = <10>;
+				vfront-porch = <10>;
+				vsync-len = <25>;
+				vsync-active = <1>;
 			};
+		};
 
-			port {
-				display0_in: endpoint {
-					remote-endpoint = <&ipu1_di0_disp0>;
-				};
+		port {
+			display0_in: endpoint {
+				remote-endpoint = <&ipu1_di0_disp0>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts b/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts
index 5705ebee0595..dcf9206f3e0d 100644
--- a/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts
+++ b/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts
@@ -163,7 +163,7 @@
 
 	/* M41T0M6 real time clock on carrier board */
 	rtc_i2c: rtc@68 {
-		compatible = "st,m41t00";
+		compatible = "st,m41t0";
 		reg = <0x68>;
 	};
 };
diff --git a/arch/arm/boot/dts/imx6dl-cubox-i-emmc-som-v15.dts b/arch/arm/boot/dts/imx6dl-cubox-i-emmc-som-v15.dts
new file mode 100644
index 000000000000..2b2fc360b865
--- /dev/null
+++ b/arch/arm/boot/dts/imx6dl-cubox-i-emmc-som-v15.dts
@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2014 Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6dl.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-sr-som-emmc.dtsi"
+#include "imx6qdl-cubox-i.dtsi"
+
+/ {
+	model = "SolidRun Cubox-i Solo/DualLite (1.5som+emmc)";
+	compatible = "solidrun,cubox-i/dl", "fsl,imx6dl";
+};
diff --git a/arch/arm/boot/dts/imx6dl-cubox-i-som-v15.dts b/arch/arm/boot/dts/imx6dl-cubox-i-som-v15.dts
new file mode 100644
index 000000000000..e09c565d1d1f
--- /dev/null
+++ b/arch/arm/boot/dts/imx6dl-cubox-i-som-v15.dts
@@ -0,0 +1,51 @@
+/*
+ * Copyright (C) 2014 Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6dl.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-cubox-i.dtsi"
+
+/ {
+	model = "SolidRun Cubox-i Solo/DualLite (1.5som)";
+	compatible = "solidrun,cubox-i/dl", "fsl,imx6dl";
+};
diff --git a/arch/arm/boot/dts/imx6dl-cubox-i.dts b/arch/arm/boot/dts/imx6dl-cubox-i.dts
index f10a36b8647d..2b1b3e193f53 100644
--- a/arch/arm/boot/dts/imx6dl-cubox-i.dts
+++ b/arch/arm/boot/dts/imx6dl-cubox-i.dts
@@ -41,6 +41,8 @@
 /dts-v1/;
 
 #include "imx6dl.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-brcm.dtsi"
 #include "imx6qdl-cubox-i.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/imx6dl-hummingboard-emmc-som-v15.dts b/arch/arm/boot/dts/imx6dl-hummingboard-emmc-som-v15.dts
new file mode 100644
index 000000000000..a63f742f20d9
--- /dev/null
+++ b/arch/arm/boot/dts/imx6dl-hummingboard-emmc-som-v15.dts
@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2014 Rabeeh Khoury (rabeeh@solid-run.com)
+ * Based on dt work by Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6dl.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-sr-som-emmc.dtsi"
+#include "imx6qdl-hummingboard.dtsi"
+
+/ {
+	model = "SolidRun HummingBoard Solo/DualLite (1.5som+emmc)";
+	compatible = "solidrun,hummingboard/dl", "fsl,imx6dl";
+};
diff --git a/arch/arm/boot/dts/imx6dl-hummingboard-som-v15.dts b/arch/arm/boot/dts/imx6dl-hummingboard-som-v15.dts
new file mode 100644
index 000000000000..66a06cf3cdf3
--- /dev/null
+++ b/arch/arm/boot/dts/imx6dl-hummingboard-som-v15.dts
@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2014 Rabeeh Khoury (rabeeh@solid-run.com)
+ * Based on dt work by Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6dl.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-hummingboard.dtsi"
+
+/ {
+	model = "SolidRun HummingBoard Solo/DualLite (1.5som)";
+	compatible = "solidrun,hummingboard/dl", "fsl,imx6dl";
+};
diff --git a/arch/arm/boot/dts/imx6dl-hummingboard.dts b/arch/arm/boot/dts/imx6dl-hummingboard.dts
index 39c2602fa87c..cbd02eb486e1 100644
--- a/arch/arm/boot/dts/imx6dl-hummingboard.dts
+++ b/arch/arm/boot/dts/imx6dl-hummingboard.dts
@@ -42,6 +42,8 @@
 /dts-v1/;
 
 #include "imx6dl.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-brcm.dtsi"
 #include "imx6qdl-hummingboard.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/imx6dl-hummingboard2-emmc-som-v15.dts b/arch/arm/boot/dts/imx6dl-hummingboard2-emmc-som-v15.dts
new file mode 100644
index 000000000000..80313c13bcdb
--- /dev/null
+++ b/arch/arm/boot/dts/imx6dl-hummingboard2-emmc-som-v15.dts
@@ -0,0 +1,55 @@
+/*
+ * Device Tree file for SolidRun HummingBoard2
+ * Copyright (C) 2015 Rabeeh Khoury <rabeeh@solid-run.com>
+ * Based on work by Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License.
+ *
+ *     This file is distributed in the hope that it will be useful
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED , WITHOUT WARRANTY OF ANY KIND
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6dl.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-emmc.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-hummingboard2.dtsi"
+
+/ {
+	model = "SolidRun HummingBoard2 Solo/DualLite (1.5som+emmc)";
+	compatible = "solidrun,hummingboard2/dl", "fsl,imx6dl";
+};
diff --git a/arch/arm/boot/dts/imx6dl-hummingboard2-som-v15.dts b/arch/arm/boot/dts/imx6dl-hummingboard2-som-v15.dts
new file mode 100644
index 000000000000..e61ef1156f8b
--- /dev/null
+++ b/arch/arm/boot/dts/imx6dl-hummingboard2-som-v15.dts
@@ -0,0 +1,54 @@
+/*
+ * Device Tree file for SolidRun HummingBoard2
+ * Copyright (C) 2015 Rabeeh Khoury <rabeeh@solid-run.com>
+ * Based on work by Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License.
+ *
+ *     This file is distributed in the hope that it will be useful
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED , WITHOUT WARRANTY OF ANY KIND
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6dl.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-hummingboard2.dtsi"
+
+/ {
+	model = "SolidRun HummingBoard2 Solo/DualLite (1.5som)";
+	compatible = "solidrun,hummingboard2/dl", "fsl,imx6dl";
+};
diff --git a/arch/arm/boot/dts/imx6dl-hummingboard2.dts b/arch/arm/boot/dts/imx6dl-hummingboard2.dts
new file mode 100644
index 000000000000..b12cd87f3f94
--- /dev/null
+++ b/arch/arm/boot/dts/imx6dl-hummingboard2.dts
@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2015 Rabeeh Khoury <rabeeh@solid-run.com>
+ * Based on dt work by Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6dl.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-brcm.dtsi"
+#include "imx6qdl-hummingboard2.dtsi"
+#include "imx6qdl-hummingboard2-emmc.dtsi"
+
+/ {
+	model = "SolidRun HummingBoard2 Solo/DualLite";
+	compatible = "solidrun,hummingboard2/dl", "fsl,imx6dl";
+};
diff --git a/arch/arm/boot/dts/imx6dl-pinfunc.h b/arch/arm/boot/dts/imx6dl-pinfunc.h
index 0ead323fdbd2..37e430a261de 100644
--- a/arch/arm/boot/dts/imx6dl-pinfunc.h
+++ b/arch/arm/boot/dts/imx6dl-pinfunc.h
@@ -668,6 +668,7 @@
 #define MX6QDL_PAD_ENET_RX_ER__SPDIF_IN             0x1f4 0x5c4 0x8f0 0x3 0x1
 #define MX6QDL_PAD_ENET_RX_ER__ENET_1588_EVENT2_OUT 0x1f4 0x5c4 0x000 0x4 0x0
 #define MX6QDL_PAD_ENET_RX_ER__GPIO1_IO24           0x1f4 0x5c4 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_RXD0__OSC32K_32K_OUT        0x1f8 0x5c8 0x000 0x0 0x0
 #define MX6QDL_PAD_ENET_RXD0__ENET_RX_DATA0         0x1f8 0x5c8 0x818 0x1 0x0
 #define MX6QDL_PAD_ENET_RXD0__ESAI_TX_HF_CLK        0x1f8 0x5c8 0x838 0x2 0x0
 #define MX6QDL_PAD_ENET_RXD0__SPDIF_OUT             0x1f8 0x5c8 0x000 0x3 0x0
diff --git a/arch/arm/boot/dts/imx6dl-ts7970.dts b/arch/arm/boot/dts/imx6dl-ts7970.dts
new file mode 100644
index 000000000000..d104daf305d9
--- /dev/null
+++ b/arch/arm/boot/dts/imx6dl-ts7970.dts
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2015 Technologic Systems
+ * Copyright 2017 Savoir-faire Linux
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "imx6dl.dtsi"
+#include "imx6qdl-ts7970.dtsi"
+
+/ {
+	model = "Technologic Systems i.MX6 Solo/DualLite TS-7970 (Default Device Tree)";
+	compatible = "technologic,imx6dl-ts7970", "fsl,imx6dl";
+};
diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi
index 4d693a75ce98..c01674fa098a 100644
--- a/arch/arm/boot/dts/imx6dl.dtsi
+++ b/arch/arm/boot/dts/imx6dl.dtsi
@@ -170,7 +170,7 @@
 };
 
 &gpr {
-	ipu1_csi0_mux: ipu1_csi0_mux@34 {
+	ipu1_csi0_mux {
 		compatible = "video-mux";
 		mux-controls = <&mux 0>;
 		#address-cells = <1>;
@@ -224,7 +224,7 @@
 		};
 	};
 
-	ipu1_csi1_mux: ipu1_csi1_mux@34 {
+	ipu1_csi1_mux {
 		compatible = "video-mux";
 		mux-controls = <&mux 1>;
 		#address-cells = <1>;
@@ -309,10 +309,12 @@
 		#size-cells = <0>;
 
 		mipi_vc0_to_ipu1_csi0_mux: endpoint@0 {
+			reg = <0>;
 			remote-endpoint = <&ipu1_csi0_mux_from_mipi_vc0>;
 		};
 
 		mipi_vc0_to_ipu1_csi1_mux: endpoint@1 {
+			reg = <1>;
 			remote-endpoint = <&ipu1_csi1_mux_from_mipi_vc0>;
 		};
 	};
@@ -323,10 +325,12 @@
 		#size-cells = <0>;
 
 		mipi_vc1_to_ipu1_csi0_mux: endpoint@0 {
+			reg = <0>;
 			remote-endpoint = <&ipu1_csi0_mux_from_mipi_vc1>;
 		};
 
 		mipi_vc1_to_ipu1_csi1_mux: endpoint@1 {
+			reg = <1>;
 			remote-endpoint = <&ipu1_csi1_mux_from_mipi_vc1>;
 		};
 	};
@@ -337,10 +341,12 @@
 		#size-cells = <0>;
 
 		mipi_vc2_to_ipu1_csi0_mux: endpoint@0 {
+			reg = <0>;
 			remote-endpoint = <&ipu1_csi0_mux_from_mipi_vc2>;
 		};
 
 		mipi_vc2_to_ipu1_csi1_mux: endpoint@1 {
+			reg = <1>;
 			remote-endpoint = <&ipu1_csi1_mux_from_mipi_vc2>;
 		};
 	};
@@ -351,10 +357,12 @@
 		#size-cells = <0>;
 
 		mipi_vc3_to_ipu1_csi0_mux: endpoint@0 {
+			reg = <0>;
 			remote-endpoint = <&ipu1_csi0_mux_from_mipi_vc3>;
 		};
 
 		mipi_vc3_to_ipu1_csi1_mux: endpoint@1 {
+			reg = <1>;
 			remote-endpoint = <&ipu1_csi1_mux_from_mipi_vc3>;
 		};
 	};
diff --git a/arch/arm/boot/dts/imx6q-apalis-eval.dts b/arch/arm/boot/dts/imx6q-apalis-eval.dts
index 8b56656e53da..aa0e631f3c0a 100644
--- a/arch/arm/boot/dts/imx6q-apalis-eval.dts
+++ b/arch/arm/boot/dts/imx6q-apalis-eval.dts
@@ -158,7 +158,7 @@
 
 	/* M41T0M6 real time clock on carrier board */
 	rtc_i2c: rtc@68 {
-		compatible = "st,m41t00";
+		compatible = "st,m41t0";
 		reg = <0x68>;
 	};
 };
diff --git a/arch/arm/boot/dts/imx6q-apalis-ixora-v1.1.dts b/arch/arm/boot/dts/imx6q-apalis-ixora-v1.1.dts
index 27dc0fc686a9..e8dccf552122 100644
--- a/arch/arm/boot/dts/imx6q-apalis-ixora-v1.1.dts
+++ b/arch/arm/boot/dts/imx6q-apalis-ixora-v1.1.dts
@@ -170,7 +170,7 @@
 
 	/* M41T0M6 real time clock on carrier board */
 	rtc_i2c: rtc@68 {
-		compatible = "st,m41t00";
+		compatible = "st,m41t0";
 		reg = <0x68>;
 	};
 };
diff --git a/arch/arm/boot/dts/imx6q-apalis-ixora.dts b/arch/arm/boot/dts/imx6q-apalis-ixora.dts
index 40b2c67fe7af..6831dfd24cc1 100644
--- a/arch/arm/boot/dts/imx6q-apalis-ixora.dts
+++ b/arch/arm/boot/dts/imx6q-apalis-ixora.dts
@@ -174,7 +174,7 @@
 
 	/* M41T0M6 real time clock on carrier board */
 	rtc_i2c: rtc@68 {
-		compatible = "st,m41t00";
+		compatible = "st,m41t0";
 		reg = <0x68>;
 	};
 };
diff --git a/arch/arm/boot/dts/imx6q-b450v3.dts b/arch/arm/boot/dts/imx6q-b450v3.dts
index 404a93d9596b..3ec58500e9c2 100644
--- a/arch/arm/boot/dts/imx6q-b450v3.dts
+++ b/arch/arm/boot/dts/imx6q-b450v3.dts
@@ -112,3 +112,55 @@
                 line-name = "PCA9539-P07";
         };
 };
+
+&pci_root {
+	/* Intel Corporation I210 Gigabit Network Connection */
+	switch_nic: ethernet@3,0 {
+		compatible = "pci8086,1533";
+		reg = <0x00010000 0 0 0 0>;
+	};
+};
+
+&switch_ports {
+	port@0 {
+		reg = <0>;
+		label = "enacq";
+		phy-handle = <&switchphy0>;
+	};
+
+	port@1 {
+		reg = <1>;
+		label = "eneport1";
+		phy-handle = <&switchphy1>;
+	};
+
+	port@2 {
+		reg = <2>;
+		label = "enix";
+		phy-handle = <&switchphy2>;
+	};
+
+	port@3 {
+		reg = <3>;
+		label = "enid";
+		phy-handle = <&switchphy3>;
+	};
+
+	port@4 {
+		reg = <4>;
+		label = "cpu";
+		ethernet = <&switch_nic>;
+		phy-handle = <&switchphy4>;
+	};
+
+	port@5 {
+		reg = <5>;
+		label = "enembc";
+
+		/* connected to Ethernet MAC of AT91RM9200 in MII mode */
+		fixed-link {
+			speed = <100>;
+			full-duplex;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/imx6q-b650v3.dts b/arch/arm/boot/dts/imx6q-b650v3.dts
index 7f9f176901d4..5650a9b11091 100644
--- a/arch/arm/boot/dts/imx6q-b650v3.dts
+++ b/arch/arm/boot/dts/imx6q-b650v3.dts
@@ -111,3 +111,55 @@
 	fsl,tx-cal-45-dp-ohms = <55>;
 	fsl,tx-d-cal = <100>;
 };
+
+&pci_root {
+	/* Intel Corporation I210 Gigabit Network Connection */
+	switch_nic: ethernet@3,0 {
+		compatible = "pci8086,1533";
+		reg = <0x00010000 0 0 0 0>;
+	};
+};
+
+&switch_ports {
+	port@0 {
+		reg = <0>;
+		label = "enacq";
+		phy-handle = <&switchphy0>;
+	};
+
+	port@1 {
+		reg = <1>;
+		label = "eneport1";
+		phy-handle = <&switchphy1>;
+	};
+
+	port@2 {
+		reg = <2>;
+		label = "enix";
+		phy-handle = <&switchphy2>;
+	};
+
+	port@3 {
+		reg = <3>;
+		label = "enid";
+		phy-handle = <&switchphy3>;
+	};
+
+	port@4 {
+		reg = <4>;
+		label = "cpu";
+		ethernet = <&switch_nic>;
+		phy-handle = <&switchphy4>;
+	};
+
+	port@5 {
+		reg = <5>;
+		label = "enembc";
+
+		/* connected to Ethernet MAC of AT91RM9200 in MII mode */
+		fixed-link {
+			speed = <100>;
+			full-duplex;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/imx6q-b850v3.dts b/arch/arm/boot/dts/imx6q-b850v3.dts
index 46bdc6722715..35edbdc7bcd1 100644
--- a/arch/arm/boot/dts/imx6q-b850v3.dts
+++ b/arch/arm/boot/dts/imx6q-b850v3.dts
@@ -212,3 +212,78 @@
 		};
 	};
 };
+
+&pci_root {
+	/* PLX Technology, Inc. PEX 8605 PCI Express 4-port Gen2 Switch */
+	bridge@1,0 {
+		compatible = "pci10b5,8605";
+		reg = <0x00010000 0 0 0 0>;
+
+		#address-cells = <3>;
+		#size-cells = <2>;
+		#interrupt-cells = <1>;
+
+		bridge@2,1 {
+			compatible = "pci10b5,8605";
+			reg = <0x00020800 0 0 0 0>;
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+			#interrupt-cells = <1>;
+
+			/* Intel Corporation I210 Gigabit Network Connection */
+			ethernet@3,0 {
+				compatible = "pci8086,1533";
+				reg = <0x00030000 0 0 0 0>;
+			};
+		};
+
+		bridge@2,2 {
+			compatible = "pci10b5,8605";
+			reg = <0x00021000 0 0 0 0>;
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+			#interrupt-cells = <1>;
+
+			/* Intel Corporation I210 Gigabit Network Connection */
+			switch_nic: ethernet@4,0 {
+				compatible = "pci8086,1533";
+				reg = <0x00040000 0 0 0 0>;
+			};
+		};
+	};
+};
+
+&switch_ports {
+	port@0 {
+		reg = <0>;
+		label = "eneport1";
+		phy-handle = <&switchphy0>;
+	};
+
+	port@1 {
+		reg = <1>;
+		label = "eneport2";
+		phy-handle = <&switchphy1>;
+	};
+
+	port@2 {
+		reg = <2>;
+		label = "enix";
+		phy-handle = <&switchphy2>;
+	};
+
+	port@3 {
+		reg = <3>;
+		label = "enid";
+		phy-handle = <&switchphy3>;
+	};
+
+	port@4 {
+		reg = <4>;
+		label = "cpu";
+		ethernet = <&switch_nic>;
+		phy-handle = <&switchphy4>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
index b915837bbb5f..916ea94d75ca 100644
--- a/arch/arm/boot/dts/imx6q-bx50v3.dtsi
+++ b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
@@ -92,6 +92,56 @@
 		mux-int-port = <1>;
 		mux-ext-port = <4>;
 	};
+
+	aliases {
+		mdio-gpio0 = &mdio0;
+	};
+
+	mdio0: mdio-gpio {
+		compatible = "virtual,mdio-gpio";
+		gpios = <&gpio2 5 GPIO_ACTIVE_HIGH>, /* mdc */
+			<&gpio2 7 GPIO_ACTIVE_HIGH>; /* mdio */
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		switch@0 {
+			compatible = "marvell,mv88e6085"; /* 88e6240*/
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+
+			switch_ports: ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+
+			mdio {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				switchphy0: switchphy@0 {
+					reg = <0>;
+				};
+
+				switchphy1: switchphy@1 {
+					reg = <1>;
+				};
+
+				switchphy2: switchphy@2 {
+					reg = <2>;
+				};
+
+				switchphy3: switchphy@3 {
+					reg = <3>;
+				};
+
+				switchphy4: switchphy@4 {
+					reg = <4>;
+				};
+			};
+		};
+	};
 };
 
 &ecspi5 {
@@ -326,3 +376,15 @@
 		tcxo-clock-frequency = <26000000>;
 	};
 };
+
+&pcie {
+	/* Synopsys, Inc. Device */
+	pci_root: root@0,0 {
+		compatible = "pci16c3,abcd";
+		reg = <0x00000000 0 0 0 0>;
+
+		#address-cells = <3>;
+		#size-cells = <2>;
+		#interrupt-cells = <1>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx6q-cubox-i-emmc-som-v15.dts b/arch/arm/boot/dts/imx6q-cubox-i-emmc-som-v15.dts
new file mode 100644
index 000000000000..3e59ebbb3608
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-cubox-i-emmc-som-v15.dts
@@ -0,0 +1,60 @@
+/*
+ * Copyright (C) 2014 Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6q.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-sr-som-emmc.dtsi"
+#include "imx6qdl-cubox-i.dtsi"
+
+/ {
+	model = "SolidRun Cubox-i Dual/Quad (1.5som+emmc)";
+	compatible = "solidrun,cubox-i/q", "fsl,imx6q";
+};
+
+&sata {
+	status = "okay";
+	fsl,transmit-level-mV = <1104>;
+	fsl,transmit-boost-mdB = <0>;
+	fsl,transmit-atten-16ths = <9>;
+	fsl,no-spread-spectrum;
+};
diff --git a/arch/arm/boot/dts/imx6q-cubox-i-som-v15.dts b/arch/arm/boot/dts/imx6q-cubox-i-som-v15.dts
new file mode 100644
index 000000000000..dab70d1230a2
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-cubox-i-som-v15.dts
@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) 2014 Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6q.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-cubox-i.dtsi"
+
+/ {
+	model = "SolidRun Cubox-i Dual/Quad (1.5som)";
+	compatible = "solidrun,cubox-i/q", "fsl,imx6q";
+};
+
+&sata {
+	status = "okay";
+	fsl,transmit-level-mV = <1104>;
+	fsl,transmit-boost-mdB = <0>;
+	fsl,transmit-atten-16ths = <9>;
+	fsl,no-spread-spectrum;
+};
diff --git a/arch/arm/boot/dts/imx6q-cubox-i.dts b/arch/arm/boot/dts/imx6q-cubox-i.dts
index b68aa0e57f20..1c7b262e3709 100644
--- a/arch/arm/boot/dts/imx6q-cubox-i.dts
+++ b/arch/arm/boot/dts/imx6q-cubox-i.dts
@@ -41,6 +41,8 @@
 /dts-v1/;
 
 #include "imx6q.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-brcm.dtsi"
 #include "imx6qdl-cubox-i.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/imx6q-display5.dtsi b/arch/arm/boot/dts/imx6q-display5.dtsi
index 4084de43d4d9..09085fde3341 100644
--- a/arch/arm/boot/dts/imx6q-display5.dtsi
+++ b/arch/arm/boot/dts/imx6q-display5.dtsi
@@ -255,7 +255,7 @@
 	pinctrl-0 = <&pinctrl_i2c1>;
 	status = "okay";
 
-	codec: tfa9879@6C {
+	codec: tfa9879@6c {
 		#sound-dai-cells = <0>;
 		compatible = "nxp,tfa9879";
 		reg = <0x6C>;
diff --git a/arch/arm/boot/dts/imx6q-h100.dts b/arch/arm/boot/dts/imx6q-h100.dts
index a3269f57df2b..8a2ea6c58902 100644
--- a/arch/arm/boot/dts/imx6q-h100.dts
+++ b/arch/arm/boot/dts/imx6q-h100.dts
@@ -42,8 +42,8 @@
 /dts-v1/;
 
 #include "imx6q.dtsi"
-#include "imx6qdl-microsom.dtsi"
-#include "imx6qdl-microsom-ar8035.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-brcm.dtsi"
 
 / {
 	model = "Auvidea H100";
@@ -108,21 +108,6 @@
 		regulator-always-on;
 	};
 
-	reg_nvcc_sd2: regulator-nvcc-sd2 {
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_h100_reg_nvcc_sd2>;
-		compatible = "regulator-gpio";
-		regulator-name = "NVCC_SD2";
-		regulator-min-microvolt = <1800000>;
-		regulator-max-microvolt = <3300000>;
-		regulator-type = "voltage";
-		regulator-boot-on;
-		regulator-always-on;
-		gpios = <&gpio4 9 GPIO_ACTIVE_HIGH>;
-		states = <1800000 0x1
-			  3300000 0x0>;
-	};
-
 	reg_usbh1_vbus: regulator-usb-h1-vbus {
 		compatible = "regulator-fixed";
 		enable-active-high;
@@ -205,7 +190,7 @@
 		reset-gpios = <&gpio6 15 GPIO_ACTIVE_LOW>;
 		/* IRQ has a wrong pull resistor which renders it useless  */
 
-		port@0 {
+		port {
 			tc358743_out: endpoint {
 				remote-endpoint = <&mipi_csi2_in>;
 				data-lanes = <1 2 3 4>;
@@ -260,12 +245,6 @@
 			>;
 		};
 
-		pinctrl_h100_reg_nvcc_sd2: h100-reg-nvcc-sd2 {
-			fsl,pins = <
-				MX6QDL_PAD_KEY_ROW1__GPIO4_IO09		0x1b0b0
-			>;
-		};
-
 		pinctrl_h100_sgtl5000: h100-sgtl5000 {
 			fsl,pins = <
 				MX6QDL_PAD_DISP0_DAT19__AUD5_RXD	0x130b0
@@ -316,6 +295,7 @@
 				MX6QDL_PAD_SD2_DAT1__SD2_DATA1		0x17059
 				MX6QDL_PAD_SD2_DAT2__SD2_DATA2		0x17059
 				MX6QDL_PAD_SD2_DAT3__SD2_DATA3		0x13059
+				MX6QDL_PAD_KEY_ROW1__SD2_VSELECT	0x1b0b0
 			>;
 		};
 
@@ -328,6 +308,7 @@
 				MX6QDL_PAD_SD2_DAT1__SD2_DATA1		0x170b9
 				MX6QDL_PAD_SD2_DAT2__SD2_DATA2		0x170b9
 				MX6QDL_PAD_SD2_DAT3__SD2_DATA3		0x170b9
+				MX6QDL_PAD_KEY_ROW1__SD2_VSELECT	0x1b0b0
 			>;
 		};
 
@@ -340,6 +321,7 @@
 				MX6QDL_PAD_SD2_DAT1__SD2_DATA1		0x170f9
 				MX6QDL_PAD_SD2_DAT2__SD2_DATA2		0x170f9
 				MX6QDL_PAD_SD2_DAT3__SD2_DATA3		0x170f9
+				MX6QDL_PAD_KEY_ROW1__SD2_VSELECT	0x1b0b0
 			>;
 		};
 	};
@@ -348,7 +330,7 @@
 &mipi_csi {
 	status = "okay";
 
-	port@0 {
+	port {
 		mipi_csi2_in: endpoint {
 			remote-endpoint = <&tc358743_out>;
 			data-lanes = <1 2 3 4>;
@@ -389,7 +371,6 @@
 	pinctrl-1 = <&pinctrl_h100_usdhc2_100mhz>;
 	pinctrl-2 = <&pinctrl_h100_usdhc2_200mhz>;
 	vmmc-supply = <&reg_3p3v>;
-	vqmmc-supply = <&reg_nvcc_sd2>;
 	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6q-hummingboard-emmc-som-v15.dts b/arch/arm/boot/dts/imx6q-hummingboard-emmc-som-v15.dts
new file mode 100644
index 000000000000..c51b4e4fd71e
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-hummingboard-emmc-som-v15.dts
@@ -0,0 +1,61 @@
+/*
+ * Copyright (C) 2014 Rabeeh Khoury (rabeeh@solid-run.com)
+ * Based on dt work by Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6q.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-sr-som-emmc.dtsi"
+#include "imx6qdl-hummingboard.dtsi"
+
+/ {
+	model = "SolidRun HummingBoard Dual/Quad (1.5som+emmc)";
+	compatible = "solidrun,hummingboard/q", "fsl,imx6q";
+};
+
+&sata {
+	status = "okay";
+	fsl,transmit-level-mV = <1025>;
+	fsl,transmit-boost-mdB = <3330>;
+	fsl,transmit-atten-16ths = <9>;
+	fsl,receive-eq-mdB = <3000>;
+};
diff --git a/arch/arm/boot/dts/imx6q-hummingboard-som-v15.dts b/arch/arm/boot/dts/imx6q-hummingboard-som-v15.dts
new file mode 100644
index 000000000000..e4132d62ffa2
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-hummingboard-som-v15.dts
@@ -0,0 +1,60 @@
+/*
+ * Copyright (C) 2014 Rabeeh Khoury (rabeeh@solid-run.com)
+ * Based on dt work by Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6q.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-hummingboard.dtsi"
+
+/ {
+	model = "SolidRun HummingBoard Dual/Quad (1.5som)";
+	compatible = "solidrun,hummingboard/q", "fsl,imx6q";
+};
+
+&sata {
+	status = "okay";
+	fsl,transmit-level-mV = <1025>;
+	fsl,transmit-boost-mdB = <3330>;
+	fsl,transmit-atten-16ths = <9>;
+	fsl,receive-eq-mdB = <3000>;
+};
diff --git a/arch/arm/boot/dts/imx6q-hummingboard.dts b/arch/arm/boot/dts/imx6q-hummingboard.dts
index 69a7a0a1cb21..8c9e94e648a7 100644
--- a/arch/arm/boot/dts/imx6q-hummingboard.dts
+++ b/arch/arm/boot/dts/imx6q-hummingboard.dts
@@ -42,6 +42,8 @@
 /dts-v1/;
 
 #include "imx6q.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-brcm.dtsi"
 #include "imx6qdl-hummingboard.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/imx6q-hummingboard2-emmc-som-v15.dts b/arch/arm/boot/dts/imx6q-hummingboard2-emmc-som-v15.dts
new file mode 100644
index 000000000000..1998ebfa0fe0
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-hummingboard2-emmc-som-v15.dts
@@ -0,0 +1,63 @@
+/*
+ * Device Tree file for SolidRun HummingBoard2
+ * Copyright (C) 2015 Rabeeh Khoury <rabeeh@solid-run.com>
+ * Based on work by Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License.
+ *
+ *     This file is distributed in the hope that it will be useful
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED , WITHOUT WARRANTY OF ANY KIND
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6q.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-emmc.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-hummingboard2.dtsi"
+
+/ {
+	model = "SolidRun HummingBoard2 Dual/Quad (1.5som+emmc)";
+	compatible = "solidrun,hummingboard2/q", "fsl,imx6q";
+};
+
+&sata {
+	status = "okay";
+	fsl,transmit-level-mV = <1104>;
+	fsl,transmit-boost-mdB = <0>;
+	fsl,transmit-atten-16ths = <9>;
+	fsl,no-spread-spectrum;
+};
diff --git a/arch/arm/boot/dts/imx6q-hummingboard2-som-v15.dts b/arch/arm/boot/dts/imx6q-hummingboard2-som-v15.dts
new file mode 100644
index 000000000000..d3ad7329cd6d
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-hummingboard2-som-v15.dts
@@ -0,0 +1,62 @@
+/*
+ * Device Tree file for SolidRun HummingBoard2
+ * Copyright (C) 2015 Rabeeh Khoury <rabeeh@solid-run.com>
+ * Based on work by Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License.
+ *
+ *     This file is distributed in the hope that it will be useful
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED , WITHOUT WARRANTY OF ANY KIND
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6q.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-ti.dtsi"
+#include "imx6qdl-hummingboard2.dtsi"
+
+/ {
+	model = "SolidRun HummingBoard2 Dual/Quad (1.5som)";
+	compatible = "solidrun,hummingboard2/q", "fsl,imx6q";
+};
+
+&sata {
+	status = "okay";
+	fsl,transmit-level-mV = <1104>;
+	fsl,transmit-boost-mdB = <0>;
+	fsl,transmit-atten-16ths = <9>;
+	fsl,no-spread-spectrum;
+};
diff --git a/arch/arm/boot/dts/imx6q-hummingboard2.dts b/arch/arm/boot/dts/imx6q-hummingboard2.dts
new file mode 100644
index 000000000000..5249f53dcdbc
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-hummingboard2.dts
@@ -0,0 +1,61 @@
+/*
+ * Copyright (C) 2015 Rabeeh Khoury <rabeeh@solid-run.com>
+ * Based on dt work by Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+
+#include "imx6q.dtsi"
+#include "imx6qdl-sr-som.dtsi"
+#include "imx6qdl-sr-som-brcm.dtsi"
+#include "imx6qdl-hummingboard2.dtsi"
+#include "imx6qdl-hummingboard2-emmc.dtsi"
+
+/ {
+	model = "SolidRun HummingBoard2 Dual/Quad";
+	compatible = "solidrun,hummingboard2/q", "fsl,imx6q";
+};
+
+&sata {
+	status = "okay";
+	fsl,transmit-level-mV = <1104>;
+	fsl,transmit-boost-mdB = <0>;
+	fsl,transmit-atten-16ths = <9>;
+	fsl,no-spread-spectrum;
+};
diff --git a/arch/arm/boot/dts/imx6q-pinfunc.h b/arch/arm/boot/dts/imx6q-pinfunc.h
index 9fc6120a1853..cfb11d3e739c 100644
--- a/arch/arm/boot/dts/imx6q-pinfunc.h
+++ b/arch/arm/boot/dts/imx6q-pinfunc.h
@@ -551,6 +551,7 @@
 #define MX6QDL_PAD_ENET_RXD1__ESAI_TX_FS            0x1e0 0x4f4 0x860 0x2 0x0
 #define MX6QDL_PAD_ENET_RXD1__ENET_1588_EVENT3_OUT  0x1e0 0x4f4 0x000 0x4 0x0
 #define MX6QDL_PAD_ENET_RXD1__GPIO1_IO26            0x1e0 0x4f4 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_RXD0__OSC32K_32K_OUT        0x1e4 0x4f8 0x000 0x0 0x0
 #define MX6QDL_PAD_ENET_RXD0__ENET_RX_DATA0         0x1e4 0x4f8 0x848 0x1 0x1
 #define MX6QDL_PAD_ENET_RXD0__ESAI_TX_HF_CLK        0x1e4 0x4f8 0x868 0x2 0x0
 #define MX6QDL_PAD_ENET_RXD0__SPDIF_OUT             0x1e4 0x4f8 0x000 0x3 0x0
diff --git a/arch/arm/boot/dts/imx6q-ts7970.dts b/arch/arm/boot/dts/imx6q-ts7970.dts
new file mode 100644
index 000000000000..f19e18995e68
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-ts7970.dts
@@ -0,0 +1,54 @@
+/*
+ * Copyright 2015 Technologic Systems
+ * Copyright 2017 Savoir-faire Linux
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "imx6q.dtsi"
+#include "imx6qdl-ts7970.dtsi"
+
+/ {
+	model = "Technologic Systems i.MX6 Quad TS-7970 (Default Device Tree)";
+	compatible = "technologic,imx6q-ts7970", "fsl,imx6q";
+};
+
+&sata {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6q-var-dt6customboard.dts b/arch/arm/boot/dts/imx6q-var-dt6customboard.dts
new file mode 100644
index 000000000000..e0728d475f6f
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-var-dt6customboard.dts
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Support for Variscite DART-MX6 Carrier-board
+ *
+ * Copyright 2017 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+/dts-v1/;
+
+#include "imx6q.dtsi"
+#include "imx6qdl-var-dart.dtsi"
+#include <dt-bindings/input/linux-event-codes.h>
+
+/ {
+	model = "Variscite DART-MX6 Carrier-board";
+	compatible = "variscite,dt6customboard", "fsl,imx6q";
+
+	backlight_lvds: backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm2 0 50000>;
+		brightness-levels = <0 4 8 16 32 64 128 248>;
+		default-brightness-level = <7>;
+		status = "okay";
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		autorepeat;
+
+		back {
+			gpios = <&gpio4 26 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_BACK>;
+			label = "Key Back";
+			linux,input-type = <1>;
+			debounce-interval = <100>;
+			wakeup-source;
+		};
+
+		home {
+			gpios = <&gpio5 11 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_HOME>;
+			label = "Key Home";
+			linux,input-type = <1>;
+			debounce-interval = <100>;
+			wakeup-source;
+		};
+
+		menu {
+			gpios = <&gpio4 25 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_MENU>;
+			label = "Key Menu";
+			linux,input-type = <1>;
+			debounce-interval = <100>;
+			wakeup-source;
+		};
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		led1 {
+			gpios = <&gpio4 27 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+
+		led2 {
+			gpios = <&gpio4 28 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "default-on";
+		};
+	};
+
+	panel1: lvds-panel {
+		compatible = "sgd,gktw70sdae4se", "panel-lvds";
+		backlight = <&backlight_lvds>;
+		width-mm = <153>;
+		height-mm = <86>;
+		label = "gktw70sdae4se";
+		data-mapping = "jeida-18";
+
+		panel-timing {
+			clock-frequency = <32000000>;
+			hactive = <800>;
+			vactive = <480>;
+			hback-porch = <39>;
+			hfront-porch = <39>;
+			vback-porch = <29>;
+			vfront-porch = <13>;
+			hsync-len = <47>;
+			vsync-len = <2>;
+		};
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&lvds1_out>;
+			};
+		};
+	};
+
+	reg_usb_h1_vbus: regulator-usbh1vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "usb_h1_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio1 28 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_usb_otg_vbus: regulator-usbotgvbus {
+		compatible = "regulator-fixed";
+		regulator-name = "usb_otg_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio4 15 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "dt6-customboard-audio";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,bitclock-master = <&sound_codec>;
+		simple-audio-card,frame-master = <&sound_codec>;
+		simple-audio-card,widgets = "Headphone", "Headphone Jack",
+					    "Line", "Line In";
+		simple-audio-card,routing = "Headphone Jack", "HPLOUT",
+					    "Headphone Jack", "HPROUT",
+					    "LINE1L", "Line In",
+					    "LINE1R", "Line In";
+
+		sound_cpu: simple-audio-card,cpu {
+			sound-dai = <&ssi2>;
+		};
+
+		sound_codec: simple-audio-card,codec {
+			sound-dai = <&tlv320aic3106>;
+			clocks = <&clks IMX6QDL_CLK_CKO>;
+		};
+	};
+};
+
+&can1 {
+	status = "okay";
+};
+
+&ecspi1 {
+	cs-gpios = <&gpio4 9 GPIO_ACTIVE_HIGH>,
+		   <&gpio4 10 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+};
+
+&fec {
+	status = "okay";
+	phy-mode = "rgmii";
+	phy-reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>;
+};
+
+&hdmi {
+	status = "okay";
+};
+
+&i2c1 {
+	clock-frequency = <100000>;
+	status = "okay";
+};
+
+&i2c3 {
+	clock-frequency = <100000>;
+	status = "okay";
+
+	touchscreen@38 {
+		compatible = "edt,edt-ft5x06";
+		reg = <0x38>;
+		interrupt-parent = <&gpio1>;
+		interrupts = <4 IRQ_TYPE_EDGE_FALLING>;
+		touchscreen-size-x = <800>;
+		touchscreen-size-y = <480>;
+		touchscreen-inverted-x;
+		touchscreen-inverted-y;
+	};
+
+	rtc@68 {
+		compatible = "isil,isl12057";
+		reg = <0x68>;
+	};
+};
+
+&ldb {
+	status = "okay";
+
+	lvds-channel@1 {
+		status = "okay";
+
+		port@4 {
+			reg = <4>;
+
+			lvds1_out: endpoint {
+				remote-endpoint = <&panel_in>;
+			};
+		};
+	};
+};
+
+&pwm2 {
+	status = "okay";
+};
+
+&uart1 {
+	status = "okay";
+};
+
+&uart3 {
+	status = "okay";
+};
+
+&usbh1 {
+	vbus-supply = <&reg_usb_h1_vbus>;
+	status = "okay";
+};
+
+&usbotg {
+	vbus-supply = <&reg_usb_otg_vbus>;
+	dr_mode = "otg";
+	srp-disable;
+	hnp-disable;
+	adp-disable;
+	status = "okay";
+};
+
+&usdhc2 {
+	cd-gpios = <&gpio1 6 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/imx6qdl-apalis.dtsi
index e80fdca585f8..4e776e036cbc 100644
--- a/arch/arm/boot/dts/imx6qdl-apalis.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-apalis.dtsi
@@ -338,7 +338,6 @@
 
 		stmpe_touchscreen {
 			compatible = "st,stmpe-ts";
-			reg = <0>;
 			/* 3.25 MHz ADC clock speed */
 			st,adc-freq = <1>;
 			/* 8 sample average control */
diff --git a/arch/arm/boot/dts/imx6qdl-apf6dev.dtsi b/arch/arm/boot/dts/imx6qdl-apf6dev.dtsi
index 829a47938179..9fc1fa449f64 100644
--- a/arch/arm/boot/dts/imx6qdl-apf6dev.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-apf6dev.dtsi
@@ -111,32 +111,28 @@
 		};
 	};
 
-	regulators {
-		compatible = "simple-bus";
-
-		reg_3p3v: 3p3v {
-			compatible = "regulator-fixed";
-			regulator-name = "3P3V";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			regulator-always-on;
-		};
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "3P3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
 
-		reg_usbh1_vbus: usb-h1-vbus {
-			compatible = "regulator-fixed";
-			regulator-name = "usb_h1_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-			regulator-always-on;
-		};
+	reg_usbh1_vbus: regulator-usb-h1-vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "usb_h1_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+	};
 
-		reg_usb_otg_vbus: usb-otg-vbus {
-			compatible = "regulator-fixed";
-			regulator-name = "usb_otg_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-			regulator-always-on;
-		};
+	reg_usb_otg_vbus: regulator-usb-otg-vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "usb_otg_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
 	};
 
 	sound {
diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
index 7d64075204ae..ee4d0f84eeb2 100644
--- a/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
@@ -12,48 +12,43 @@
 #include <dt-bindings/gpio/gpio.h>
 
 / {
-	regulators {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		reg_2p5v: regulator@0 {
-			compatible = "regulator-fixed";
-			regulator-name = "2P5V";
-			regulator-min-microvolt = <2500000>;
-			regulator-max-microvolt = <2500000>;
-			regulator-always-on;
-		};
 
-		reg_3p3v: regulator@1 {
-			compatible = "regulator-fixed";
-			regulator-name = "3P3V";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			regulator-always-on;
-		};
+	reg_2p5v: regulator-2p5v {
+		compatible = "regulator-fixed";
+		regulator-name = "2P5V";
+		regulator-min-microvolt = <2500000>;
+		regulator-max-microvolt = <2500000>;
+		regulator-always-on;
+	};
 
-		reg_usbh1_vbus: regulator@2 {
-			compatible = "regulator-fixed";
-			enable-active-high;
-			gpio = <&gpio3 31 GPIO_ACTIVE_HIGH>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_aristainetos_usbh1_vbus>;
-			regulator-name = "usb_h1_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-		};
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "3P3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
 
-		reg_usbotg_vbus: regulator@3 {
-			compatible = "regulator-fixed";
-			enable-active-high;
-			gpio = <&gpio4 15 GPIO_ACTIVE_HIGH>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_aristainetos_usbotg_vbus>;
-			regulator-name = "usb_otg_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-		};
+	reg_usbh1_vbus: regulator-usbh1-vbus {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio3 31 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_aristainetos_usbh1_vbus>;
+		regulator-name = "usb_h1_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	reg_usbotg_vbus: regulator-usbotg-vbus {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio4 15 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_aristainetos_usbotg_vbus>;
+		regulator-name = "usb_otg_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
index 1b1872873207..376750882ed3 100644
--- a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
@@ -52,46 +52,42 @@
 		enable-gpios = <&gpio6 31 GPIO_ACTIVE_HIGH>;
 	};
 
-	regulators {
-		compatible = "simple-bus";
-
-		reg_2p5v: 2p5v {
-			compatible = "regulator-fixed";
-			regulator-name = "2P5V";
-			regulator-min-microvolt = <2500000>;
-			regulator-max-microvolt = <2500000>;
-			regulator-always-on;
-		};
-
-		reg_3p3v: 3p3v {
-			compatible = "regulator-fixed";
-			regulator-name = "3P3V";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			regulator-always-on;
-		};
-
-		reg_usbh1_vbus: usb-h1-vbus {
-			compatible = "regulator-fixed";
-			enable-active-high;
-			gpio = <&gpio1 0 GPIO_ACTIVE_HIGH>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_aristainetos2_usbh1_vbus>;
-			regulator-name = "usb_h1_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-		};
-
-		reg_usbotg_vbus: usb-otg-vbus {
-			compatible = "regulator-fixed";
-			enable-active-high;
-			gpio = <&gpio4 15 GPIO_ACTIVE_HIGH>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_aristainetos2_usbotg_vbus>;
-			regulator-name = "usb_otg_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-		};
+	reg_2p5v: regulator-2p5v {
+		compatible = "regulator-fixed";
+		regulator-name = "2P5V";
+		regulator-min-microvolt = <2500000>;
+		regulator-max-microvolt = <2500000>;
+		regulator-always-on;
+	};
+
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "3P3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+
+	reg_usbh1_vbus: regulator-usbh1-vbus {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio1 0 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_aristainetos2_usbh1_vbus>;
+		regulator-name = "usb_h1_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	reg_usbotg_vbus: regulator-usbotg-vbus {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio4 15 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_aristainetos2_usbotg_vbus>;
+		regulator-name = "usb_otg_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-colibri.dtsi b/arch/arm/boot/dts/imx6qdl-colibri.dtsi
index fc66bbfd6796..e4eb300549d4 100644
--- a/arch/arm/boot/dts/imx6qdl-colibri.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-colibri.dtsi
@@ -274,7 +274,6 @@
 
 		stmpe_touchscreen {
 			compatible = "st,stmpe-ts";
-			reg = <0>;
 			/* 3.25 MHz ADC clock speed */
 			st,adc-freq = <1>;
 			/* 8 sample average control */
diff --git a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
index 14fff4ee6516..d1cfdc264126 100644
--- a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
@@ -38,8 +38,6 @@
  *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  *     OTHER DEALINGS IN THE SOFTWARE.
  */
-#include "imx6qdl-microsom.dtsi"
-#include "imx6qdl-microsom-ar8035.dtsi"
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/gpio/gpio.h>
 
@@ -64,38 +62,36 @@
 		};
 	};
 
-	regulators {
-		compatible = "simple-bus";
-
-		reg_3p3v: 3p3v {
-			compatible = "regulator-fixed";
-			regulator-name = "3P3V";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			regulator-always-on;
-		};
+	v_5v0: regulator-v-5v0 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "v_5v0";
+	};
 
-		reg_usbh1_vbus: usb-h1-vbus {
-			compatible = "regulator-fixed";
-			enable-active-high;
-			gpio = <&gpio1 0 0>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_cubox_i_usbh1_vbus>;
-			regulator-name = "usb_h1_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-		};
+	v_usb2: regulator-v-usb2 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio1 0 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_cubox_i_usbh1_vbus>;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "v_usb2";
+		vin-supply = <&v_5v0>;
+	};
 
-		reg_usbotg_vbus: usb-otg-vbus {
-			compatible = "regulator-fixed";
-			enable-active-high;
-			gpio = <&gpio3 22 0>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_cubox_i_usbotg_vbus>;
-			regulator-name = "usb_otg_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-		};
+	v_usb1: regulator-v-usb1 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio3 22 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_cubox_i_usbotg_vbus>;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "v_usb1";
+		vin-supply = <&v_5v0>;
 	};
 
 	sound-spdif {
@@ -139,7 +135,7 @@
 
 	status = "okay";
 
-	rtc: pcf8523@68 {
+	rtc@68 {
 		compatible = "nxp,pcf8523";
 		reg = <0x68>;
 	};
@@ -243,21 +239,25 @@
 &usbh1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_cubox_i_usbh1>;
-	vbus-supply = <&reg_usbh1_vbus>;
+	vbus-supply = <&v_usb2>;
 	status = "okay";
 };
 
 &usbotg {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_cubox_i_usbotg>;
-	vbus-supply = <&reg_usbotg_vbus>;
+	vbus-supply = <&v_usb1>;
 	status = "okay";
 };
 
 &usdhc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_cubox_i_usdhc2_aux &pinctrl_cubox_i_usdhc2>;
-	vmmc-supply = <&reg_3p3v>;
+	vmmc-supply = <&vcc_3v3>;
 	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
+
+&vcc_3v3 {
+	vin-supply = <&v_5v0>;
+};
diff --git a/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi b/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi
index 37c07c0748aa..92583238ca4a 100644
--- a/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi
@@ -38,8 +38,6 @@
  *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  *     OTHER DEALINGS IN THE SOFTWARE.
  */
-#include "imx6qdl-microsom.dtsi"
-#include "imx6qdl-microsom-ar8035.dtsi"
 
 / {
 	chosen {
@@ -53,38 +51,58 @@
 		pinctrl-0 = <&pinctrl_hummingboard_gpio3_5>;
 	};
 
-	regulators {
-		compatible = "simple-bus";
+	v_3v2: regulator-v-3v2 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "v_3v2";
+		vin-supply = <&v_5v0>;
+	};
 
-		reg_3p3v: 3p3v {
-			compatible = "regulator-fixed";
-			regulator-name = "3P3V";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			regulator-always-on;
-		};
+	v_5v0: regulator-v-5v0 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "v_5v0";
+	};
 
-		reg_usbh1_vbus: usb-h1-vbus {
-			compatible = "regulator-fixed";
-			enable-active-high;
-			gpio = <&gpio1 0 GPIO_ACTIVE_HIGH>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_hummingboard_usbh1_vbus>;
-			regulator-name = "usb_h1_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-		};
+	v_sd: regulator-v-sd {
+		compatible = "regulator-fixed";
+		gpio = <&gpio4 30 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_hummingboard_vmmc>;
+		regulator-boot-on;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "v_sd";
+		startup-delay-us = <1000>;
+		vin-supply = <&v_3v2>;
+	};
 
-		reg_usbotg_vbus: usb-otg-vbus {
-			compatible = "regulator-fixed";
-			enable-active-high;
-			gpio = <&gpio3 22 GPIO_ACTIVE_HIGH>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_hummingboard_usbotg_vbus>;
-			regulator-name = "usb_otg_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-		};
+	v_usb2: regulator-v-usb2 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio1 0 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_hummingboard_usbh1_vbus>;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "v_usb2";
+		vin-supply = <&v_5v0>;
+	};
+
+	v_usb1: regulator-v-usb1 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio3 22 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_hummingboard_usbotg_vbus>;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "v_usb1";
+		vin-supply = <&v_5v0>;
 	};
 
 	sound-sgtl5000 {
@@ -132,20 +150,20 @@
 	status = "okay";
 
 	/* Pro baseboard model */
-	rtc: pcf8523@68 {
+	rtc@68 {
 		compatible = "nxp,pcf8523";
 		reg = <0x68>;
 	};
 
 	/* Pro baseboard model */
-	sgtl5000: sgtl5000@a {
+	sgtl5000: codec@a {
 		clocks = <&clks IMX6QDL_CLK_CKO>;
 		compatible = "fsl,sgtl5000";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_hummingboard_sgtl5000>;
 		reg = <0x0a>;
-		VDDA-supply = <&reg_3p3v>;
-		VDDIO-supply = <&reg_3p3v>;
+		VDDA-supply = <&v_3v2>;
+		VDDIO-supply = <&v_3v2>;
 	};
 };
 
@@ -247,6 +265,11 @@
 				MX6QDL_PAD_SD2_DAT3__SD2_DATA3 0x13059
 			>;
 		};
+		pinctrl_hummingboard_vmmc: hummingboard-vmmc {
+			fsl,pins = <
+				MX6QDL_PAD_DISP0_DAT9__GPIO4_IO30 0x1b0b0
+			>;
+		};
 	};
 };
 
@@ -280,7 +303,7 @@
 
 &usbh1 {
 	disable-over-current;
-	vbus-supply = <&reg_usbh1_vbus>;
+	vbus-supply = <&v_usb2>;
 	status = "okay";
 };
 
@@ -288,7 +311,7 @@
 	disable-over-current;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_hummingboard_usbotg_id>;
-	vbus-supply = <&reg_usbotg_vbus>;
+	vbus-supply = <&v_usb1>;
 	status = "okay";
 };
 
@@ -298,7 +321,11 @@
 		&pinctrl_hummingboard_usdhc2_aux
 		&pinctrl_hummingboard_usdhc2
 	>;
-	vmmc-supply = <&reg_3p3v>;
+	vmmc-supply = <&v_sd>;
 	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
+
+&vcc_3v3 {
+	vin-supply = <&v_3v2>;
+};
diff --git a/arch/arm/boot/dts/imx6qdl-hummingboard2-emmc.dtsi b/arch/arm/boot/dts/imx6qdl-hummingboard2-emmc.dtsi
new file mode 100644
index 000000000000..f400405381a7
--- /dev/null
+++ b/arch/arm/boot/dts/imx6qdl-hummingboard2-emmc.dtsi
@@ -0,0 +1,72 @@
+/*
+ * Device Tree file for SolidRun HummingBoard2
+ * Copyright (C) 2015 Rabeeh Khoury <rabeeh@solid-run.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+&iomuxc {
+	hummingboard2 {
+		pinctrl_hummingboard2_usdhc3: hummingboard2-usdhc3 {
+			fsl,pins = <
+				MX6QDL_PAD_SD3_CMD__SD3_CMD    0x17059
+				MX6QDL_PAD_SD3_CLK__SD3_CLK    0x10059
+				MX6QDL_PAD_SD3_DAT0__SD3_DATA0 0x17059
+				MX6QDL_PAD_SD3_DAT1__SD3_DATA1 0x17059
+				MX6QDL_PAD_SD3_DAT2__SD3_DATA2 0x17059
+				MX6QDL_PAD_SD3_DAT3__SD3_DATA3 0x17059
+				MX6QDL_PAD_SD3_DAT4__SD3_DATA4 0x17059
+				MX6QDL_PAD_SD3_DAT5__SD3_DATA5 0x17059
+				MX6QDL_PAD_SD3_DAT6__SD3_DATA6 0x17059
+				MX6QDL_PAD_SD3_DAT7__SD3_DATA7 0x17059
+				MX6QDL_PAD_SD3_RST__SD3_RESET  0x17059
+			>;
+		};
+	};
+};
+
+&usdhc3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard2_usdhc3>;
+	vmmc-supply = <&v_3v2>;
+	vqmmc-supply = <&v_3v2>;
+	bus-width = <8>;
+	non-removable;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6qdl-hummingboard2.dtsi b/arch/arm/boot/dts/imx6qdl-hummingboard2.dtsi
new file mode 100644
index 000000000000..dffbc92e0023
--- /dev/null
+++ b/arch/arm/boot/dts/imx6qdl-hummingboard2.dtsi
@@ -0,0 +1,540 @@
+/*
+ * Copyright (C) 2015 Rabeeh Khoury <rabeeh@solid-run.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/ {
+	chosen {
+		stdout-path = &uart1;
+	};
+
+	ir_recv: ir-receiver {
+		compatible = "gpio-ir-receiver";
+		gpios = <&gpio7 9 GPIO_ACTIVE_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_hummingboard2_gpio7_9>;
+		linux,rc-map-name = "rc-rc6-mce";
+	};
+
+	v_3v2: regulator-v-3v2 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "v_3v2";
+	};
+
+	v_5v0: regulator-v-5v0 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "v_5v0";
+	};
+
+	vcc_1p8: regulator-vcc-1p8 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-max-microvolt = <1800000>;
+		regulator-min-microvolt = <1800000>;
+		regulator-name = "vcc_1p8";
+		vin-supply = <&v_3v2>;
+	};
+
+	v_sd: regulator-v-sd {
+		compatible = "regulator-fixed";
+		gpio = <&gpio4 30 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_hummingboard2_vmmc>;
+		regulator-boot-on;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "v_sd";
+		startup-delay-us = <1000>;
+		vin-supply = <&v_3v2>;
+	};
+
+	v_usb1: regulator-v-usb1 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio3 22 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_hummingboard2_usbotg_vbus>;
+		regulator-always-on;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "v_usb1";
+		vin-supply = <&v_5v0>;
+	};
+
+	v_usb2: regulator-v-usb2 {
+		/* USB hub port 1 */
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio1 0 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_hummingboard2_usbh1_vbus>;
+		regulator-always-on;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "v_usb2";
+		vin-supply = <&v_5v0>;
+	};
+
+	v_usb3: regulator-v-usb3 {
+		/* USB hub port 3 */
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 13 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_hummingboard2_usbh2_vbus>;
+		regulator-always-on;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "v_usb3";
+		vin-supply = <&v_5v0>;
+	};
+
+	v_usb4: regulator-v-usb4 {
+		/* USB hub port 4 */
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio7 10 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_hummingboard2_usbh3_vbus>;
+		regulator-always-on;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "v_usb4";
+		vin-supply = <&v_5v0>;
+	};
+
+	sound-sgtl5000 {
+		audio-codec = <&sgtl5000>;
+		audio-routing =
+			"MIC_IN", "Mic Jack",
+			"Mic Jack", "Mic Bias",
+			"Headphone Jack", "HP_OUT";
+		compatible = "fsl,imx-audio-sgtl5000";
+		model = "On-board Codec";
+		mux-ext-port = <5>;
+		mux-int-port = <1>;
+		ssi-controller = <&ssi1>;
+	};
+};
+
+&audmux {
+	status = "okay";
+};
+
+&ecspi2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard2_ecspi2>;
+	cs-gpios = <&gpio2 26 0>;
+	status = "okay";
+};
+
+&hdmi {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard2_hdmi>;
+	ddc-i2c-bus = <&i2c2>;
+	status = "okay";
+};
+
+&i2c1 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard2_i2c1>;
+	status = "okay";
+
+	pcf8523: rtc@68 {
+		compatible = "nxp,pcf8523";
+		reg = <0x68>;
+	};
+
+	sgtl5000: codec@a {
+		clocks = <&clks IMX6QDL_CLK_CKO>;
+		compatible = "fsl,sgtl5000";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_hummingboard2_sgtl5000>;
+		reg = <0x0a>;
+		VDDA-supply = <&v_3v2>;
+		VDDD-supply = <&vcc_1p8>;
+		VDDIO-supply = <&v_3v2>;
+	};
+};
+
+&i2c2 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard2_i2c2>;
+	status = "okay";
+};
+
+&i2c3 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard2_i2c3>;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hog>;
+
+	hummingboard2 {
+		pinctrl_hog: hoggrp {
+		fsl,pins = <
+				/*
+				 * 36 pin headers GPIO description. The pins
+				 * numbering as following -
+				 *
+				 * 	3.2v	5v	74	75
+				 *	73	72	71	70
+				 *	69	68	67	66
+				 *
+				 *	77	78	79	76
+				 *	65	64	61	60
+				 *	53	52	51	50
+				 *	49	48	166	132
+				 *	95	94	90	91
+				 *	GND	54	24	204
+				 *
+				 * The GPIO numbers can be extracted using
+				 * signal name from below.
+				 * Example -
+				 * MX6QDL_PAD_EIM_DA10__GPIO3_IO10 is
+				 * GPIO(3,10) which is (3-1)*32+10 = gpio 74
+				 *
+				 * i.e. The mapping of GPIO(X,Y) to Linux gpio
+				 * number is : gpio number = (X-1) * 32 + Y
+				 */
+				/* DI1_PIN15 */
+				MX6QDL_PAD_EIM_DA10__GPIO3_IO10 0x400130b1
+				/* DI1_PIN02 */
+				MX6QDL_PAD_EIM_DA11__GPIO3_IO11 0x400130b1
+				/* DISP1_DATA00 */
+				MX6QDL_PAD_EIM_DA9__GPIO3_IO09 0x400130b1
+				/* DISP1_DATA01 */
+				MX6QDL_PAD_EIM_DA8__GPIO3_IO08 0x400130b1
+				/* DISP1_DATA02 */
+				MX6QDL_PAD_EIM_DA7__GPIO3_IO07 0x400130b1
+				/* DISP1_DATA03 */
+				MX6QDL_PAD_EIM_DA6__GPIO3_IO06 0x400130b1
+				/* DISP1_DATA04 */
+				MX6QDL_PAD_EIM_DA5__GPIO3_IO05 0x400130b1
+				/* DISP1_DATA05 */
+				MX6QDL_PAD_EIM_DA4__GPIO3_IO04 0x400130b1
+				/* DISP1_DATA06 */
+				MX6QDL_PAD_EIM_DA3__GPIO3_IO03 0x400130b1
+				/* DISP1_DATA07 */
+				MX6QDL_PAD_EIM_DA2__GPIO3_IO02 0x400130b1
+				/* DI1_D0_CS */
+				MX6QDL_PAD_EIM_DA13__GPIO3_IO13 0x400130b1
+				/* DI1_D1_CS */
+				MX6QDL_PAD_EIM_DA14__GPIO3_IO14 0x400130b1
+				/* DI1_PIN01 */
+				MX6QDL_PAD_EIM_DA15__GPIO3_IO15 0x400130b1
+				/* DI1_PIN03 */
+				MX6QDL_PAD_EIM_DA12__GPIO3_IO12 0x400130b1
+				/* DISP1_DATA08 */
+				MX6QDL_PAD_EIM_DA1__GPIO3_IO01 0x400130b1
+				/* DISP1_DATA09 */
+				MX6QDL_PAD_EIM_DA0__GPIO3_IO00 0x400130b1
+				/* DISP1_DATA10 */
+				MX6QDL_PAD_EIM_EB1__GPIO2_IO29 0x400130b1
+				/* DISP1_DATA11 */
+				MX6QDL_PAD_EIM_EB0__GPIO2_IO28 0x400130b1
+				/* DISP1_DATA12 */
+				MX6QDL_PAD_EIM_A17__GPIO2_IO21 0x400130b1
+				/* DISP1_DATA13 */
+				MX6QDL_PAD_EIM_A18__GPIO2_IO20 0x400130b1
+				/* DISP1_DATA14 */
+				MX6QDL_PAD_EIM_A19__GPIO2_IO19 0x400130b1
+				/* DISP1_DATA15 */
+				MX6QDL_PAD_EIM_A20__GPIO2_IO18 0x400130b1
+				/* DISP1_DATA16 */
+				MX6QDL_PAD_EIM_A21__GPIO2_IO17 0x400130b1
+				/* DISP1_DATA17 */
+				MX6QDL_PAD_EIM_A22__GPIO2_IO16 0x400130b1
+				/* DISP1_DATA18 */
+				MX6QDL_PAD_EIM_A23__GPIO6_IO06 0x400130b1
+				/* DISP1_DATA19 */
+				MX6QDL_PAD_EIM_A24__GPIO5_IO04 0x400130b1
+				/* DISP1_DATA20 */
+				MX6QDL_PAD_EIM_D31__GPIO3_IO31 0x400130b1
+				/* DISP1_DATA21 */
+				MX6QDL_PAD_EIM_D30__GPIO3_IO30 0x400130b1
+				/* DISP1_DATA22 */
+				MX6QDL_PAD_EIM_D26__GPIO3_IO26 0x400130b1
+				/* DISP1_DATA23 */
+				MX6QDL_PAD_EIM_D27__GPIO3_IO27 0x400130b1
+				/* DI1_DISP_CLK */
+				MX6QDL_PAD_EIM_A16__GPIO2_IO22 0x400130b1
+				/* SPDIF_IN */
+				MX6QDL_PAD_ENET_RX_ER__GPIO1_IO24 0x400130b1
+				/* SPDIF_OUT */
+				MX6QDL_PAD_GPIO_17__GPIO7_IO12 0x400130b1
+
+				/* MikroBUS GPIO pin number 10 */
+				MX6QDL_PAD_EIM_LBA__GPIO2_IO27 0x400130b1
+			>;
+		};
+
+		pinctrl_hummingboard2_ecspi2: hummingboard2-ecspi2grp {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_OE__ECSPI2_MISO	0x100b1
+				MX6QDL_PAD_EIM_CS1__ECSPI2_MOSI	0x100b1
+				MX6QDL_PAD_EIM_CS0__ECSPI2_SCLK	0x100b1
+				MX6QDL_PAD_EIM_RW__GPIO2_IO26	0x000b1 /* CS */
+			>;
+		};
+
+		pinctrl_hummingboard2_gpio7_9: hummingboard2-gpio7_9 {
+			fsl,pins = <
+				MX6QDL_PAD_SD4_CMD__GPIO7_IO09 0x80000000
+			>;
+		};
+
+		pinctrl_hummingboard2_hdmi: hummingboard2-hdmi {
+			fsl,pins = <
+				MX6QDL_PAD_KEY_ROW2__HDMI_TX_CEC_LINE 0x1f8b0
+			>;
+		};
+
+		pinctrl_hummingboard2_i2c1: hummingboard2-i2c1 {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_D21__I2C1_SCL 0x4001b8b1
+				MX6QDL_PAD_EIM_D28__I2C1_SDA 0x4001b8b1
+			>;
+		};
+
+		pinctrl_hummingboard2_i2c2: hummingboard2-i2c2 {
+			fsl,pins = <
+				MX6QDL_PAD_KEY_COL3__I2C2_SCL 0x4001b8b1
+				MX6QDL_PAD_KEY_ROW3__I2C2_SDA 0x4001b8b1
+			>;
+		};
+
+		pinctrl_hummingboard2_i2c3: hummingboard2-i2c3 {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_D17__I2C3_SCL 0x4001b8b1
+				MX6QDL_PAD_EIM_D18__I2C3_SDA 0x4001b8b1
+			>;
+		};
+
+		pinctrl_hummingboard2_mipi: hummingboard2_mipi {
+			fsl,pins = <
+				MX6QDL_PAD_SD4_DAT2__GPIO2_IO10 0x4001b8b1
+				MX6QDL_PAD_KEY_COL4__GPIO4_IO14 0x4001b8b1
+				MX6QDL_PAD_NANDF_CS2__CCM_CLKO2 0x130b0
+			>;
+		};
+
+		pinctrl_hummingboard2_pcie_reset: hummingboard2-pcie-reset {
+			fsl,pins = <
+				MX6QDL_PAD_SD4_DAT3__GPIO2_IO11 0x1b0b1
+			>;
+		};
+
+		pinctrl_hummingboard2_pwm1: pwm1grp {
+			fsl,pins = <
+				MX6QDL_PAD_DISP0_DAT8__PWM1_OUT 0x1b0b1
+			>;
+		};
+
+		pinctrl_hummingboard2_pwm3: pwm3grp {
+			fsl,pins = <
+				MX6QDL_PAD_SD4_DAT1__PWM3_OUT 0x1b0b1
+			>;
+		};
+
+		pinctrl_hummingboard2_sgtl5000: hummingboard2-sgtl5000 {
+			fsl,pins = <
+				MX6QDL_PAD_DISP0_DAT19__AUD5_RXD 0x130b0
+				MX6QDL_PAD_KEY_COL0__AUD5_TXC 0x130b0
+				MX6QDL_PAD_KEY_ROW0__AUD5_TXD 0x110b0
+				MX6QDL_PAD_KEY_COL1__AUD5_TXFS 0x130b0
+				MX6QDL_PAD_GPIO_5__CCM_CLKO1 0x130b0
+			>;
+		};
+
+		pinctrl_hummingboard2_usbh1_vbus: hummingboard2-usbh1-vbus {
+			fsl,pins = <MX6QDL_PAD_GPIO_0__GPIO1_IO00 0x1b0b0>;
+		};
+
+		pinctrl_hummingboard2_usbh2_vbus: hummingboard2-usbh2-vbus {
+			fsl,pins = <MX6QDL_PAD_SD4_DAT5__GPIO2_IO13 0x1b0b0>;
+		};
+
+		pinctrl_hummingboard2_usbh3_vbus: hummingboard2-usbh3-vbus {
+			fsl,pins = <MX6QDL_PAD_SD4_CLK__GPIO7_IO10 0x1b0b0>;
+		};
+
+		pinctrl_hummingboard2_usbotg_id: hummingboard2-usbotg-id {
+			/*
+			 * Similar to pinctrl_usbotg_2, but we want it
+			 * pulled down for a fixed host connection.
+			 */
+			fsl,pins = <MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x13059>;
+		};
+
+		pinctrl_hummingboard2_usbotg_vbus: hummingboard2-usbotg-vbus {
+			fsl,pins = <MX6QDL_PAD_EIM_D22__GPIO3_IO22 0x1b0b0>;
+		};
+
+		pinctrl_hummingboard2_usdhc2_aux: hummingboard2-usdhc2-aux {
+			fsl,pins = <
+				MX6QDL_PAD_GPIO_4__GPIO1_IO04    0x1f071
+				MX6QDL_PAD_KEY_ROW1__SD2_VSELECT 0x1b071
+			>;
+		};
+
+		pinctrl_hummingboard2_usdhc2: hummingboard2-usdhc2 {
+			fsl,pins = <
+				MX6QDL_PAD_SD2_CMD__SD2_CMD    0x17059
+				MX6QDL_PAD_SD2_CLK__SD2_CLK    0x10059
+				MX6QDL_PAD_SD2_DAT0__SD2_DATA0 0x17059
+				MX6QDL_PAD_SD2_DAT1__SD2_DATA1 0x17059
+				MX6QDL_PAD_SD2_DAT2__SD2_DATA2 0x17059
+				MX6QDL_PAD_SD2_DAT3__SD2_DATA3 0x13059
+			>;
+		};
+
+		pinctrl_hummingboard2_usdhc2_100mhz: hummingboard2-usdhc2-100mhz {
+			fsl,pins = <
+				MX6QDL_PAD_SD2_CMD__SD2_CMD    0x170b9
+				MX6QDL_PAD_SD2_CLK__SD2_CLK    0x100b9
+				MX6QDL_PAD_SD2_DAT0__SD2_DATA0 0x170b9
+				MX6QDL_PAD_SD2_DAT1__SD2_DATA1 0x170b9
+				MX6QDL_PAD_SD2_DAT2__SD2_DATA2 0x170b9
+				MX6QDL_PAD_SD2_DAT3__SD2_DATA3 0x130b9
+			>;
+		};
+
+		pinctrl_hummingboard2_usdhc2_200mhz: hummingboard2-usdhc2-200mhz {
+			fsl,pins = <
+				MX6QDL_PAD_SD2_CMD__SD2_CMD    0x170f9
+				MX6QDL_PAD_SD2_CLK__SD2_CLK    0x100f9
+				MX6QDL_PAD_SD2_DAT0__SD2_DATA0 0x170f9
+				MX6QDL_PAD_SD2_DAT1__SD2_DATA1 0x170f9
+				MX6QDL_PAD_SD2_DAT2__SD2_DATA2 0x170f9
+				MX6QDL_PAD_SD2_DAT3__SD2_DATA3 0x130f9
+			>;
+		};
+
+		pinctrl_hummingboard2_vmmc: hummingboard2-vmmc {
+			fsl,pins = <
+				MX6QDL_PAD_DISP0_DAT9__GPIO4_IO30 0x1b0b0
+			>;
+		};
+
+		pinctrl_hummingboard2_uart3: hummingboard2-uart3 {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_D25__UART3_TX_DATA	0x1b0b1
+				MX6QDL_PAD_EIM_D24__UART3_RX_DATA	0x40013000
+			>;
+		};
+	};
+};
+
+&pcie {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard2_pcie_reset>;
+	reset-gpio = <&gpio2 11 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
+
+&pwm1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard2_pwm1>;
+	status = "okay";
+};
+
+&pwm3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard2_pwm3>;
+	status = "okay";
+};
+
+&ssi1 {
+	status = "okay";
+};
+
+&usbh1 {
+	disable-over-current;
+	status = "okay";
+};
+
+&usbotg {
+	disable-over-current;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard2_usbotg_id>;
+	vbus-supply = <&v_usb1>;
+	status = "okay";
+};
+
+&usdhc2 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <
+		&pinctrl_hummingboard2_usdhc2_aux
+		&pinctrl_hummingboard2_usdhc2
+	>;
+	pinctrl-1 = <
+		&pinctrl_hummingboard2_usdhc2_aux
+		&pinctrl_hummingboard2_usdhc2_100mhz
+	>;
+	pinctrl-2 = <
+		&pinctrl_hummingboard2_usdhc2_aux
+		&pinctrl_hummingboard2_usdhc2_200mhz
+	>;
+	vmmc-supply = <&v_sd>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
+
+&uart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard2_uart3>;
+	status = "okay";
+};
+
+&vcc_3v3 {
+	vin-supply = <&v_3v2>;
+};
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
index 3a77f0fedfce..fd05f7caa472 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
@@ -172,7 +172,7 @@
 		};
 	};
 
-	i2cmux@2 {
+	i2c2mux {
 		compatible = "i2c-mux-gpio";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_i2c2mux>;
@@ -183,20 +183,20 @@
 		i2c-parent = <&i2c2>;
 		idle-state = <0>;
 
-		i2c2@1 {
+		i2c2mux@1 {
 			reg = <1>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 		};
 
-		i2c2@2 {
+		i2c2mux@2 {
 			reg = <2>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 		};
 	};
 
-	i2cmux@3 {
+	i2c3mux {
 		compatible = "i2c-mux-gpio";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_i2c3mux>;
@@ -206,7 +206,7 @@
 		i2c-parent = <&i2c3>;
 		idle-state = <0>;
 
-		i2c3@1 {
+		i2c3mux@1 {
 			reg = <1>;
 			#address-cells = <1>;
 			#size-cells = <0>;
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
index 4bdf29169d2a..919b6b7619a4 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
@@ -276,6 +276,23 @@
 		compatible = "sst,sst25vf016b", "jedec,spi-nor";
 		spi-max-frequency = <20000000>;
 		reg = <0>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		partition@0 {
+			label = "bootloader";
+			reg = <0x0 0xc0000>;
+		};
+
+		partition@c0000 {
+			label = "env";
+			reg = <0xc0000 0x2000>;
+		};
+
+		partition@c2000 {
+			label = "splash";
+			reg = <0xc2000 0x13e000>;
+		};
 	};
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
index 4fa2fac3877b..82d6ccb46982 100644
--- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
@@ -235,6 +235,9 @@
 };
 
 &hdmi {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hdmi_cec>;
+	ddc-i2c-bus = <&i2c2>;
 	status = "okay";
 };
 
@@ -453,6 +456,12 @@
 			>;
 		};
 
+		pinctrl_hdmi_cec: hdmicecgrp {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_A25__HDMI_TX_CEC_LINE	0x1f8b0
+			>;
+		};
+
 		pinctrl_i2c2: i2c2grp {
 			fsl,pins = <
 				MX6QDL_PAD_EIM_EB2__I2C2_SCL	0x4001b8b1
diff --git a/arch/arm/boot/dts/imx6qdl-microsom.dtsi b/arch/arm/boot/dts/imx6qdl-sr-som-brcm.dtsi
index 6a410160c9ee..b55af61dfeca 100644
--- a/arch/arm/boot/dts/imx6qdl-microsom.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sr-som-brcm.dtsi
@@ -40,7 +40,7 @@
  */
 #include <dt-bindings/gpio/gpio.h>
 / {
-	clk_sdio: sdio-clock {
+	clk_brcm: brcm-clock {
 		compatible = "gpio-gate-clock";
 		#clock-cells = <0>;
 		pinctrl-names = "default";
@@ -48,27 +48,23 @@
 		enable-gpios = <&gpio5 5 GPIO_ACTIVE_HIGH>;
 	};
 
-	regulators {
-		compatible = "simple-bus";
-
-		reg_brcm: brcm-reg {
-			compatible = "regulator-fixed";
-			enable-active-high;
-			gpio = <&gpio3 19 0>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_microsom_brcm_reg>;
-			regulator-name = "brcm_reg";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			startup-delay-us = <200000>;
-		};
+	reg_brcm: brcm-reg {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio3 19 0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_microsom_brcm_reg>;
+		regulator-name = "brcm_reg";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <200000>;
 	};
 
 	usdhc1_pwrseq: usdhc1_pwrseq {
 		compatible = "mmc-pwrseq-simple";
 		reset-gpios = <&gpio5 26 GPIO_ACTIVE_LOW>,
 			      <&gpio6 0 GPIO_ACTIVE_LOW>;
-		clocks = <&clk_sdio>;
+		clocks = <&clk_brcm>;
 		clock-names = "ext_clock";
 	};
 };
@@ -104,13 +100,6 @@
 			>;
 		};
 
-		pinctrl_microsom_uart1: microsom-uart1 {
-			fsl,pins = <
-				MX6QDL_PAD_CSI0_DAT10__UART1_TX_DATA	0x1b0b1
-				MX6QDL_PAD_CSI0_DAT11__UART1_RX_DATA	0x1b0b1
-			>;
-		};
-
 		pinctrl_microsom_uart4: microsom-uart4 {
 			fsl,pins = <
 				MX6QDL_PAD_CSI0_DAT12__UART4_TX_DATA 0x1b0b1
@@ -133,12 +122,6 @@
 	};
 };
 
-&uart1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_microsom_uart1>;
-	status = "okay";
-};
-
 /* UART4 - Connected to optional BRCM Wifi/BT/FM */
 &uart4 {
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/imx6qdl-sr-som-emmc.dtsi b/arch/arm/boot/dts/imx6qdl-sr-som-emmc.dtsi
new file mode 100644
index 000000000000..5f3b8baab20f
--- /dev/null
+++ b/arch/arm/boot/dts/imx6qdl-sr-som-emmc.dtsi
@@ -0,0 +1,70 @@
+/*
+ * Copyright (C) 2013,2014 Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+&iomuxc {
+	microsom {
+		pinctrl_microsom_usdhc3: microsom-usdhc3 {
+			fsl,pins = <
+				MX6QDL_PAD_SD3_CMD__SD3_CMD    0x17059
+				MX6QDL_PAD_SD3_CLK__SD3_CLK    0x10059
+				MX6QDL_PAD_SD3_DAT0__SD3_DATA0 0x17059
+				MX6QDL_PAD_SD3_DAT1__SD3_DATA1 0x17059
+				MX6QDL_PAD_SD3_DAT2__SD3_DATA2 0x17059
+				MX6QDL_PAD_SD3_DAT3__SD3_DATA3 0x17059
+				MX6QDL_PAD_SD3_DAT4__SD3_DATA4 0x17059
+				MX6QDL_PAD_SD3_DAT5__SD3_DATA5 0x17059
+				MX6QDL_PAD_SD3_DAT6__SD3_DATA6 0x17059
+				MX6QDL_PAD_SD3_DAT7__SD3_DATA7 0x17059
+				MX6QDL_PAD_SD3_RST__SD3_RESET  0x17059
+			>;
+		};
+	};
+};
+
+/* USDHC3 - eMMC */
+&usdhc3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_microsom_usdhc3>;
+	bus-width = <8>;
+	non-removable;
+	vmmc-supply = <&vcc_3v3>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6qdl-sr-som-ti.dtsi b/arch/arm/boot/dts/imx6qdl-sr-som-ti.dtsi
new file mode 100644
index 000000000000..44a97ba93a95
--- /dev/null
+++ b/arch/arm/boot/dts/imx6qdl-sr-som-ti.dtsi
@@ -0,0 +1,170 @@
+/*
+ * Copyright (C) 2013,2014 Russell King
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	nvcc_sd1: regulator-nvcc-sd1 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-name = "nvcc_sd1";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&vcc_3v3>;
+	};
+
+	clk_ti_wifi: ti-wifi-clock {
+		/* This is a hack around the kernel - using "fixed clock"
+		 * results in the "pinctrl" properties being ignored, and
+		 * the clock not being output.  Instead, use a gated clock
+		 * and the unrouted WL_XTAL_PU gpio.
+		 */
+		compatible = "gpio-gate-clock";
+		#clock-cells = <0>;
+		clock-frequency = <32768>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_microsom_ti_clk>;
+		enable-gpios = <&gpio5 5 GPIO_ACTIVE_HIGH>;
+	};
+
+	pwrseq_ti_wifi: ti-wifi-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_microsom_ti_wifi_en>;
+		reset-gpios = <&gpio5 26 GPIO_ACTIVE_LOW>;
+		post-power-on-delay-ms = <200>;
+		clocks = <&clk_ti_wifi>;
+		clock-names = "ext_clock";
+	};
+};
+
+&iomuxc {
+	microsom {
+		pinctrl_microsom_ti_bt: microsom-ti-bt {
+			fsl,pins = <
+				/* BT_EN_SOC */
+				MX6QDL_PAD_CSI0_DAT14__GPIO6_IO00	0x40013070
+			>;
+		};
+
+		pinctrl_microsom_ti_clk: microsom-ti-clk {
+			fsl,pins = <
+				/* EXT_32K */
+				MX6QDL_PAD_GPIO_8__XTALOSC_REF_CLK_32K	0x1b0b0
+				/* WL_XTAL_PU (unrouted) */
+				MX6QDL_PAD_DISP0_DAT11__GPIO5_IO05 0x40013070
+			>;
+		};
+
+		pinctrl_microsom_ti_wifi_en: microsom-ti-wifi-en {
+			fsl,pins = <
+				/* WLAN_EN_SOC */
+				MX6QDL_PAD_CSI0_DAT8__GPIO5_IO26	0x40013070
+			>;
+		};
+
+		pinctrl_microsom_ti_wifi_irq: microsom-ti-wifi-irq {
+			fsl,pins = <
+				/* WLAN_IRQ */
+				MX6QDL_PAD_CSI0_DAT18__GPIO6_IO04	0x40013070
+			>;
+		};
+
+		pinctrl_microsom_uart4: microsom-uart4 {
+			fsl,pins = <
+				MX6QDL_PAD_CSI0_DAT12__UART4_TX_DATA 0x1b0b1
+				MX6QDL_PAD_CSI0_DAT13__UART4_RX_DATA 0x1b0b1
+				MX6QDL_PAD_CSI0_DAT16__UART4_RTS_B 0x1b0b1
+				MX6QDL_PAD_CSI0_DAT17__UART4_CTS_B 0x1b0b1
+			>;
+		};
+
+		pinctrl_microsom_usdhc1: microsom-usdhc1 {
+			fsl,pins = <
+				MX6QDL_PAD_SD1_CMD__SD1_CMD    0x17059
+				MX6QDL_PAD_SD1_CLK__SD1_CLK    0x10059
+				MX6QDL_PAD_SD1_DAT0__SD1_DATA0 0x17059
+				MX6QDL_PAD_SD1_DAT1__SD1_DATA1 0x17059
+				MX6QDL_PAD_SD1_DAT2__SD1_DATA2 0x17059
+				MX6QDL_PAD_SD1_DAT3__SD1_DATA3 0x17059
+			>;
+		};
+	};
+};
+
+/* UART4 - Connected to optional TI Wi-Fi/BT/FM */
+&uart4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_microsom_uart4>;
+	uart-has-rtscts;
+	status = "okay";
+
+	bluetooth {
+		compatible = "ti,wl1837-st";
+		clocks = <&clk_ti_wifi>;
+		clock-names = "ext_clock";
+		enable-gpios = <&gpio6 0 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_microsom_ti_bt>;
+	};
+};
+
+/* USDHC1 - Connected to optional TI Wi-Fi/BT/FM */
+&usdhc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_microsom_usdhc1>;
+	bus-width = <4>;
+	keep-power-in-suspend;
+	mmc-pwrseq = <&pwrseq_ti_wifi>;
+	non-removable;
+	vmmc-supply = <&vcc_3v3>;
+	/* vqmmc-supply = <&nvcc_sd1>; - MMC layer doesn't like it! */
+	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	wlcore@2 {
+		compatible = "ti,wl1837";
+		reg = <2>;
+		interrupts-extended = <&gpio6 4 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_microsom_ti_wifi_irq>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx6qdl-microsom-ar8035.dtsi b/arch/arm/boot/dts/imx6qdl-sr-som.dtsi
index 900e8c781f91..4ccb7afc4b35 100644
--- a/arch/arm/boot/dts/imx6qdl-microsom-ar8035.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sr-som.dtsi
@@ -1,9 +1,6 @@
 /*
  * Copyright (C) 2013,2014 Russell King
  *
- * This describes the hookup for an AR8035 to the iMX6 on the SolidRun
- * MicroSOM.
- *
  * This file is dual-licensed: you can use it either under the terms
  * of the GPL or the X11 license, at your option. Note that this dual
  * licensing only applies to this file, and not this project as a
@@ -41,6 +38,18 @@
  *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  *     OTHER DEALINGS IN THE SOFTWARE.
  */
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	vcc_3v3: regulator-vcc-3v3 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-name = "vcc_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+};
+
 &fec {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_microsom_enet_ar8035>;
@@ -51,7 +60,7 @@
 };
 
 &iomuxc {
-	enet {
+	microsom {
 		pinctrl_microsom_enet_ar8035: microsom-enet-ar8035 {
 			fsl,pins = <
 				MX6QDL_PAD_ENET_MDIO__ENET_MDIO		0x1b8b0
@@ -59,10 +68,10 @@
 				/* AR8035 reset */
 				MX6QDL_PAD_KEY_ROW4__GPIO4_IO15		0x130b0
 				/* AR8035 interrupt */
-				MX6QDL_PAD_DI0_PIN2__GPIO4_IO18		0x80000000
+				MX6QDL_PAD_DI0_PIN2__GPIO4_IO18		0x1b0b0
 				/* GPIO16 -> AR8035 25MHz */
-				MX6QDL_PAD_GPIO_16__ENET_REF_CLK	0xc0000000
-				MX6QDL_PAD_RGMII_TXC__RGMII_TXC		0x80000000
+				MX6QDL_PAD_GPIO_16__ENET_REF_CLK	0x4001b0b0
+				MX6QDL_PAD_RGMII_TXC__RGMII_TXC		0x13030
 				MX6QDL_PAD_RGMII_TD0__RGMII_TD0		0x1b030
 				MX6QDL_PAD_RGMII_TD1__RGMII_TD1		0x1b030
 				MX6QDL_PAD_RGMII_TD2__RGMII_TD2		0x1b030
@@ -95,5 +104,18 @@
 				MX6QDL_PAD_ENET_RXD1__GPIO1_IO26	0x03000
 			>;
 		};
+
+		pinctrl_microsom_uart1: microsom-uart1 {
+			fsl,pins = <
+				MX6QDL_PAD_CSI0_DAT10__UART1_TX_DATA	0x1b0b1
+				MX6QDL_PAD_CSI0_DAT11__UART1_RX_DATA	0x1b0b1
+			>;
+		};
 	};
 };
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_microsom_uart1>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6qdl-ts7970.dtsi b/arch/arm/boot/dts/imx6qdl-ts7970.dtsi
new file mode 100644
index 000000000000..f0be516dc28e
--- /dev/null
+++ b/arch/arm/boot/dts/imx6qdl-ts7970.dtsi
@@ -0,0 +1,594 @@
+/*
+ * Copyright 2015 Technologic Systems
+ * Copyright 2017 Savoir-Faire Linux
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/ {
+	leds {
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_leds1>;
+		compatible = "gpio-leds";
+
+		green-led {
+			label = "green-led";
+			gpios = <&gpio3 27 GPIO_ACTIVE_LOW>;
+			default-state = "on";
+		};
+
+		red-led {
+			label = "red-led";
+			gpios = <&gpio1 2 GPIO_ACTIVE_LOW>;
+			default-state = "off";
+		};
+
+		yel-led {
+			label = "yellow-led";
+			gpios = <&gpio1 9 GPIO_ACTIVE_LOW>;
+			default-state = "off";
+		};
+
+		blue-led {
+			label = "blue-led";
+			gpios = <&gpio4 25 GPIO_ACTIVE_LOW>;
+			default-state = "off";
+		};
+
+		en-usb-5v {
+			label = "en-usb-5v";
+			gpios = <&gpio2 22 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+		};
+
+		sel_dc_usb {
+			label = "sel_dc_usb";
+			gpios = <&gpio5 17 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+	};
+
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "3p3v";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+
+	reg_can1_3v3: reg_can1_3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "reg_can1_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio4 21 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_can2_3v3: en-reg_can2_3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "reg_can2_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio6 31 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_usb_otg_vbus: regulator-usb-otg-vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "usb_otg_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio3 22 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_wlan_vmmc: regulator_wlan_vmmc {
+		compatible = "regulator-fixed";
+		regulator-name = "wlan_vmmc";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		gpio = <&gpio8 14 GPIO_ACTIVE_HIGH>;
+		startup-delay-us = <70000>;
+		enable-active-high;
+	};
+
+	sound-sgtl5000 {
+		audio-codec = <&sgtl5000>;
+		audio-routing =
+			"MIC_IN", "Mic Jack",
+			"Mic Jack", "Mic Bias",
+			"Headphone Jack", "HP_OUT";
+		compatible = "fsl,imx-audio-sgtl5000";
+		model = "On-board Codec";
+		mux-ext-port = <3>;
+		mux-int-port = <1>;
+		ssi-controller = <&ssi1>;
+	};
+};
+
+&audmux {
+	status = "okay";
+};
+
+&can1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan1>;
+	xceiver-supply = <&reg_can1_3v3>;
+	status = "okay";
+};
+
+&can2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan2>;
+	xceiver-supply = <&reg_can2_3v3>;
+	status = "okay";
+};
+
+&ecspi1 {
+	cs-gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi1>;
+	status = "okay";
+
+	n25q064: flash@0 {
+		compatible = "micron,n25q064", "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <20000000>;
+	};
+};
+
+&ecspi2 {
+	cs-gpios = <
+		&gpio5 31 GPIO_ACTIVE_HIGH
+		&gpio7 12 GPIO_ACTIVE_HIGH
+		&gpio5 18 GPIO_ACTIVE_HIGH
+	>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi2>;
+	status = "okay";
+};
+
+&fec {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_enet>;
+	phy-mode = "rgmii";
+	interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_HIGH>,
+			      <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
+	fsl,err006687-workaround-present;
+	status = "okay";
+};
+
+&hdmi {
+	status = "okay";
+};
+
+&i2c1 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&pinctrl_i2c1>;
+	pinctrl-1 = <&pinctrl_i2c1_gpio>;
+	scl-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+	sda-gpios = <&gpio3 28 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+
+	m41t00s: rtc@68 {
+		compatible = "m41t00";
+		reg = <0x68>;
+	};
+
+	isl12022: rtc@6f {
+		compatible = "isl,isl12022";
+		reg = <0x6f>;
+	};
+
+	gpio8: gpio@28 {
+		compatible = "technologic,ts7970-gpio";
+		reg = <0x28>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		ngpio = <32>;
+	};
+
+	sgtl5000: codec@a {
+		compatible = "fsl,sgtl5000";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_sgtl5000>;
+		reg = <0x0a>;
+		clocks = <&clks IMX6QDL_CLK_CKO>;
+		VDDA-supply = <&reg_3p3v>;
+		VDDIO-supply = <&reg_3p3v>;
+	};
+};
+
+&i2c2 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&pinctrl_i2c2>;
+	pinctrl-1 = <&pinctrl_i2c2_gpio>;
+	scl-gpios = <&gpio4 12 GPIO_ACTIVE_HIGH>;
+	sda-gpios = <&gpio4 13 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hog>;
+
+	pinctrl_ecspi1: ecspi1grp {
+		fsl,pins = <
+			MX6QDL_PAD_EIM_D17__ECSPI1_MISO		0x100b1
+			MX6QDL_PAD_EIM_D18__ECSPI1_MOSI		0x100b1
+			MX6QDL_PAD_EIM_D16__ECSPI1_SCLK		0x100b1
+			MX6QDL_PAD_EIM_D19__GPIO3_IO19		0x100b1 /* Onboard Flash CS */
+		>;
+	};
+
+	pinctrl_ecspi2: ecspi2 {
+		fsl,pins = <
+			MX6QDL_PAD_CSI0_DAT8__ECSPI2_SCLK      0x100b1
+			MX6QDL_PAD_CSI0_DAT9__ECSPI2_MOSI      0x100b1
+			MX6QDL_PAD_CSI0_DAT10__ECSPI2_MISO     0x100b1
+			MX6QDL_PAD_CSI0_DAT13__GPIO5_IO31      0x100b1 /* FPGA_SPI_CS0 */
+			MX6QDL_PAD_GPIO_17__GPIO7_IO12         0x100b1 /* FPGA_SPI_CS1 */
+			MX6QDL_PAD_CSI0_PIXCLK__GPIO5_IO18     0x100b1 /* HD1_SPI_CS */
+			MX6QDL_PAD_CSI0_VSYNC__GPIO5_IO21      0x1b088 /* FPGA_RESET */
+			MX6QDL_PAD_GPIO_3__XTALOSC_REF_CLK_24M 0x10    /* FPGA 24MHZ */
+			MX6QDL_PAD_CSI0_DATA_EN__GPIO5_IO20    0x1b088 /* FPGA_IRQ_0 */
+			MX6QDL_PAD_GPIO_4__GPIO1_IO04          0x1b088 /* FPGA_IRQ_1 */
+		>;
+	};
+
+	pinctrl_enet: enet {
+		fsl,pins = <
+			MX6QDL_PAD_ENET_MDIO__ENET_MDIO		0x1b0b0
+			MX6QDL_PAD_ENET_MDC__ENET_MDC		0x1b0b0
+			MX6QDL_PAD_RGMII_TXC__RGMII_TXC		0x1b0b0
+			MX6QDL_PAD_RGMII_TD0__RGMII_TD0		0x1b0b0
+			MX6QDL_PAD_RGMII_TD1__RGMII_TD1		0x1b0b0
+			MX6QDL_PAD_RGMII_TD2__RGMII_TD2		0x1b0b0
+			MX6QDL_PAD_RGMII_TD3__RGMII_TD3		0x1b0b0
+			MX6QDL_PAD_RGMII_TX_CTL__RGMII_TX_CTL	0x1b0b0
+			MX6QDL_PAD_RGMII_RXC__RGMII_RXC		0x1b0b0
+			MX6QDL_PAD_RGMII_RD0__RGMII_RD0		0x1b0b0
+			MX6QDL_PAD_RGMII_RD1__RGMII_RD1		0x1b0b0
+			MX6QDL_PAD_RGMII_RD2__RGMII_RD2		0x1b0b0
+			MX6QDL_PAD_RGMII_RD3__RGMII_RD3		0x1b0b0
+			MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL	0x1b0b0
+			MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK	0x1b0b0
+			MX6QDL_PAD_ENET_TX_EN__GPIO1_IO28	0x1b088
+			MX6QDL_PAD_DI0_PIN4__GPIO4_IO20		0x1b088 /* ETH_PHY_RESET */
+			MX6QDL_PAD_GPIO_6__ENET_IRQ		0x000b1
+		>;
+	};
+
+	pinctrl_flexcan1: flexcan1grp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_ROW2__FLEXCAN1_RX	0x1b088
+			MX6QDL_PAD_KEY_COL2__FLEXCAN1_TX	0x1b088
+			MX6QDL_PAD_DISP0_DAT0__GPIO4_IO21	0x1b088 /* EN_CAN_1 */
+		>;
+	};
+
+	pinctrl_flexcan2: flexcan2grp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL4__FLEXCAN2_TX	0x1b088
+			MX6QDL_PAD_KEY_ROW4__FLEXCAN2_RX	0x1b088
+			MX6QDL_PAD_EIM_BCLK__GPIO6_IO31		0x1b088 /* EN_CAN_2 */
+		>;
+	};
+
+	pinctrl_hog: hoggrp {
+		fsl,pins = <
+			/* Onboard */
+			MX6QDL_PAD_SD4_DAT3__GPIO2_IO11		0x1b088 /* USB_HUB_RESET */
+			MX6QDL_PAD_DISP0_DAT23__GPIO5_IO17	0x1b088 /* SEL_DC_USB */
+			MX6QDL_PAD_EIM_A16__GPIO2_IO22		0x1b088 /* EN_USB_5V */
+			MX6QDL_PAD_DISP0_DAT14__GPIO5_IO08	0x1b088 /* JTAG_FPGA_TMS */
+			MX6QDL_PAD_DISP0_DAT17__GPIO5_IO11	0x1b088 /* JTAG_FPGA_TCK */
+			MX6QDL_PAD_DISP0_DAT18__GPIO5_IO12	0x1b088 /* JTAG_FPGA_TDO */
+			MX6QDL_PAD_DISP0_DAT22__GPIO5_IO16	0x1b088 /* JTAG_FPGA_TDI */
+			MX6QDL_PAD_DISP0_DAT20__GPIO5_IO14	0x1b088 /* GYRO_INT */
+			MX6QDL_PAD_EIM_OE__GPIO2_IO25		0x1b088 /* MODBUS_FAULT */
+			MX6QDL_PAD_EIM_RW__GPIO2_IO26		0x1b088 /* BUS_DIR/JP_SD_BOOT */
+			MX6QDL_PAD_EIM_A19__GPIO2_IO19		0x1b088 /* EN_MODBUS_24V */
+			MX6QDL_PAD_DISP0_DAT5__GPIO4_IO26	0x1b088 /* EN_MODBUS_3V */
+			MX6QDL_PAD_EIM_A17__GPIO2_IO21		0x1b088 /* I210_RESET */
+			MX6QDL_PAD_EIM_D23__GPIO3_IO23		0x1b088 /* EN_RTC_PWR */
+			MX6QDL_PAD_SD3_DAT4__GPIO7_IO01		0x1b088 /* REVSTRAP1 */
+
+			/* Offboard */
+			MX6QDL_PAD_DISP0_DAT7__GPIO4_IO28	0x1b088 /* LCD_D09 */
+			MX6QDL_PAD_DISP0_DAT9__GPIO4_IO30	0x1b088 /* HD1_IRQ */
+			MX6QDL_PAD_DISP0_DAT10__GPIO4_IO31	0x1b088 /* LCD_D10 */
+			MX6QDL_PAD_DISP0_DAT11__GPIO5_IO05	0x1b088 /* LCD_D11 */
+			MX6QDL_PAD_EIM_EB1__GPIO2_IO29		0x1b088 /* BUS_BHE */
+			MX6QDL_PAD_EIM_LBA__GPIO2_IO27		0x1b088 /* BUS_ALE */
+			MX6QDL_PAD_EIM_CS0__GPIO2_IO23		0x1b088 /* BUS_CS */
+			MX6QDL_PAD_EIM_A24__GPIO5_IO04		0x1b088 /* DIO_20 */
+			MX6QDL_PAD_EIM_WAIT__GPIO5_IO00		0x1b088 /* BUS_WAIT */
+			MX6QDL_PAD_EIM_DA0__GPIO3_IO00		0x1b088 /* MUX_AD_00 */
+			MX6QDL_PAD_EIM_DA1__GPIO3_IO01		0x1b088 /* MUX_AD_01 */
+			MX6QDL_PAD_EIM_DA2__GPIO3_IO02		0x1b088 /* MUX_AD_02 */
+			MX6QDL_PAD_EIM_DA3__GPIO3_IO03		0x1b088 /* MUX_AD_03 */
+			MX6QDL_PAD_EIM_DA4__GPIO3_IO04		0x1b088 /* MUX_AD_04 */
+			MX6QDL_PAD_EIM_DA5__GPIO3_IO05		0x1b088 /* MUX_AD_05 */
+			MX6QDL_PAD_EIM_DA6__GPIO3_IO06		0x1b088 /* MUX_AD_06 */
+			MX6QDL_PAD_EIM_DA7__GPIO3_IO07		0x1b088 /* MUX_AD_07 */
+			MX6QDL_PAD_EIM_DA8__GPIO3_IO08		0x1b088 /* MUX_AD_08 */
+			MX6QDL_PAD_EIM_DA9__GPIO3_IO09		0x1b088 /* MUX_AD_09 */
+			MX6QDL_PAD_EIM_DA10__GPIO3_IO10		0x1b088 /* MUX_AD_10 */
+			MX6QDL_PAD_EIM_DA11__GPIO3_IO11		0x1b088 /* MUX_AD_11 */
+			MX6QDL_PAD_EIM_DA12__GPIO3_IO12		0x1b088 /* MUX_AD_12 */
+			MX6QDL_PAD_EIM_DA13__GPIO3_IO13		0x1b088 /* MUX_AD_13 */
+			MX6QDL_PAD_EIM_DA14__GPIO3_IO14		0x1b088 /* MUX_AD_14 */
+			MX6QDL_PAD_EIM_DA15__GPIO3_IO15		0x1b088 /* MUX_AD_15 */
+
+			/* Strapping only */
+			MX6QDL_PAD_EIM_A18__GPIO2_IO20		0x1b088
+			MX6QDL_PAD_EIM_A21__GPIO2_IO17		0x1b088
+		>;
+	};
+
+	pinctrl_i2c1: i2c1grp {
+		fsl,pins = <
+			MX6QDL_PAD_EIM_D21__I2C1_SCL		0x4001b8b1
+			MX6QDL_PAD_EIM_D28__I2C1_SDA		0x4001b8b1
+		>;
+	};
+
+	pinctrl_i2c1_gpio: i2c1gpiogrp {
+		fsl,pins = <
+			MX6QDL_PAD_EIM_D21__GPIO3_IO21		0x4001b8b1
+			MX6QDL_PAD_EIM_D28__GPIO3_IO28		0x4001b8b1
+		>;
+	};
+
+	pinctrl_i2c2: i2c2grp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL3__I2C2_SCL		0x4001b8b1
+			MX6QDL_PAD_KEY_ROW3__I2C2_SDA		0x4001b8b1
+		>;
+	};
+
+	pinctrl_i2c2_gpio: i2c2gpiogrp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL3__GPIO4_IO12		0x4001b8b1
+			MX6QDL_PAD_KEY_ROW3__GPIO4_IO13		0x4001b8b1
+		>;
+	};
+
+	pinctrl_leds1: leds1grp {
+		fsl,pins = <
+			MX6QDL_PAD_EIM_D27__GPIO3_IO27		0x1b088 /* GREEN_LED */
+			MX6QDL_PAD_GPIO_2__GPIO1_IO02		0x1b088 /* RED_LED */
+			MX6QDL_PAD_GPIO_9__GPIO1_IO09		0x1b088 /* YEL_LED */
+			MX6QDL_PAD_DISP0_DAT4__GPIO4_IO25	0x1b088 /* IMX6_BLUE_LED */
+		>;
+	};
+
+	pinctrl_sgtl5000: sgtl5000grp {
+		fsl,pins = <
+			MX6QDL_PAD_CSI0_DAT7__AUD3_RXD		0x130b0
+			MX6QDL_PAD_CSI0_DAT4__AUD3_TXC		0x130b0
+			MX6QDL_PAD_CSI0_DAT5__AUD3_TXD		0x110b0
+			MX6QDL_PAD_CSI0_DAT6__AUD3_TXFS		0x130b0
+			MX6QDL_PAD_GPIO_0__CCM_CLKO1		0x130b0 /* Audio CLK */
+		>;
+	};
+
+	pinctrl_uart1: uart1grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD3_DAT7__UART1_TX_DATA	0x1b088
+			MX6QDL_PAD_SD3_DAT6__UART1_RX_DATA	0x1b088
+		>;
+	};
+
+	pinctrl_uart2: uart2grp {
+		fsl,pins = <
+			MX6QDL_PAD_GPIO_7__UART2_TX_DATA	0x1b088
+			MX6QDL_PAD_GPIO_8__UART2_RX_DATA	0x1b088
+			MX6QDL_PAD_SD4_DAT6__UART2_CTS_B	0x1b088
+			MX6QDL_PAD_SD4_DAT5__UART2_RTS_B	0x1b088
+		>;
+	};
+
+	pinctrl_uart3: uart3grp {
+		fsl,pins = <
+			MX6QDL_PAD_EIM_D24__UART3_TX_DATA	0x1b088
+			MX6QDL_PAD_EIM_D25__UART3_RX_DATA	0x1b088
+			MX6QDL_PAD_EIM_D30__UART3_RTS_B		0x1b088
+			MX6QDL_PAD_EIM_D31__UART3_CTS_B		0x1b088
+		>;
+	};
+
+	pinctrl_uart4: uart4grp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL0__UART4_TX_DATA	0x1b088
+			MX6QDL_PAD_KEY_ROW0__UART4_RX_DATA	0x1b088
+		>;
+	};
+
+	pinctrl_uart5: uart5grp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL1__UART5_TX_DATA	0x1b088
+			MX6QDL_PAD_KEY_ROW1__UART5_RX_DATA	0x1b088
+		>;
+	};
+
+	pinctrl_usbotg: usbotggrp {
+		fsl,pins = <
+			MX6QDL_PAD_GPIO_1__USB_OTG_ID		0x17059
+		>;
+	};
+
+	pinctrl_usdhc1: usdhc1grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD1_CMD__SD1_CMD		0x17059
+			MX6QDL_PAD_SD1_CLK__SD1_CLK		0x10059
+			MX6QDL_PAD_SD1_DAT0__SD1_DATA0		0x17059
+			MX6QDL_PAD_SD1_DAT1__SD1_DATA1		0x17059
+			MX6QDL_PAD_SD1_DAT2__SD1_DATA2		0x17059
+			MX6QDL_PAD_SD1_DAT3__SD1_DATA3		0x17059
+			MX6QDL_PAD_ENET_RXD1__GPIO1_IO26	0x17059 /* WIFI IRQ */
+		>;
+	};
+
+	pinctrl_usdhc2: usdhc2grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD2_CMD__SD2_CMD		0x17059
+			MX6QDL_PAD_SD2_CLK__SD2_CLK		0x10059
+			MX6QDL_PAD_SD2_DAT0__SD2_DATA0		0x17059
+			MX6QDL_PAD_SD2_DAT1__SD2_DATA1		0x17059
+			MX6QDL_PAD_SD2_DAT2__SD2_DATA2		0x17059
+			MX6QDL_PAD_SD2_DAT3__SD2_DATA3		0x17059
+			MX6QDL_PAD_EIM_EB0__GPIO2_IO28		0x1b088 /* EN_SD_POWER */
+		>;
+	};
+
+	pinctrl_usdhc3: usdhc3grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD3_CMD__SD3_CMD		0x17059
+			MX6QDL_PAD_SD3_CLK__SD3_CLK		0x10059
+			MX6QDL_PAD_SD3_DAT0__SD3_DATA0		0x17059
+			MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x17059
+			MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x17059
+			MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x17059
+		>;
+	};
+};
+
+&pcie {
+	status = "okay";
+};
+
+&snvs_rtc {
+	status = "disabled";
+};
+
+&ssi1 {
+	fsl,mode = "i2s-slave";
+	status = "okay";
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1>;
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2>;
+	uart-has-rtscts;
+	status = "okay";
+};
+
+&uart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart3>;
+	status = "okay";
+};
+
+&uart4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart4>;
+	status = "okay";
+};
+
+&uart5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart5>;
+	status = "okay";
+};
+
+&usbh1 {
+	status = "okay";
+};
+
+&usbotg {
+	vbus-supply = <&reg_usb_otg_vbus>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usbotg>;
+	disable-over-current;
+	status = "okay";
+};
+
+/* WIFI */
+&usdhc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc1>;
+	vmmc-supply = <&reg_wlan_vmmc>;
+	bus-width = <4>;
+	non-removable;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	wlcore: wlcore@2 {
+		compatible = "ti,wl1271";
+		reg = <2>;
+		interrupt-parent = <&gpio1>;
+		interrupts = <26 IRQ_TYPE_LEVEL_HIGH>;
+		ref-clock-frequency = <38400000>;
+	};
+};
+
+/* SD */
+&usdhc2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc2>;
+	vmmc-supply = <&reg_3p3v>;
+	bus-width = <4>;
+	fsl,wp-controller;
+	status = "okay";
+};
+
+/* eMMC */
+&usdhc3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc3>;
+	vmmc-supply = <&reg_3p3v>;
+	bus-width = <4>;
+	non-removable;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6qdl-udoo.dtsi b/arch/arm/boot/dts/imx6qdl-udoo.dtsi
index c96c91d83678..4161b7d4323a 100644
--- a/arch/arm/boot/dts/imx6qdl-udoo.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-udoo.dtsi
@@ -28,6 +28,13 @@
 		status = "disabled";
 	};
 
+	gpio-poweroff {
+		compatible = "gpio-poweroff";
+		gpios = <&gpio2 4 0>;
+		pinctrl-0 = <&pinctrl_power_off>;
+		pinctrl-names = "default";
+	};
+
 	memory {
 		reg = <0x10000000 0x40000000>;
 	};
@@ -172,6 +179,12 @@
 			>;
 		};
 
+		pinctrl_power_off: poweroffgrp {
+			fsl,pins = <
+				MX6QDL_PAD_NANDF_D4__GPIO2_IO04		0x30
+			>;
+		};
+
 		pinctrl_touchscreenp7: touchscreenp7grp {
 			fsl,pins = <
 				MX6QDL_PAD_SD2_DAT0__GPIO1_IO15		0x70
@@ -208,8 +221,8 @@
 			fsl,pins = <
 				MX6QDL_PAD_DI0_PIN2__AUD6_TXD		0x1b0b0
 				MX6QDL_PAD_DI0_PIN3__AUD6_TXFS		0x1b0b0
-				MX6QDL_PAD_DI0_PIN4__AUD6_RXD		0x1b0b0
-				MX6QDL_PAD_DI0_PIN15__AUD6_TXC		0x1b0b0
+				MX6QDL_PAD_DI0_PIN4__AUD6_RXD		0x13080
+				MX6QDL_PAD_DI0_PIN15__AUD6_TXC		0x13080
 				MX6QDL_PAD_EIM_EB2__GPIO2_IO30		0x1b0b0
 			>;
 		};
@@ -218,8 +231,8 @@
 			fsl,pins = <
 				MX6QDL_PAD_DI0_PIN2__AUD6_TXD		0x1b0b0
 				MX6QDL_PAD_DI0_PIN3__GPIO4_IO19		0x1b0b0
-				MX6QDL_PAD_DI0_PIN4__AUD6_RXD		0x1b0b0
-				MX6QDL_PAD_DI0_PIN15__AUD6_TXC		0x1b0b0
+				MX6QDL_PAD_DI0_PIN4__AUD6_RXD		0x13080
+				MX6QDL_PAD_DI0_PIN15__AUD6_TXC		0x13080
 				MX6QDL_PAD_EIM_EB2__GPIO2_IO30		0x1b0b0
 			>;
 		};
@@ -228,8 +241,8 @@
 			fsl,pins = <
 				MX6QDL_PAD_DI0_PIN2__GPIO4_IO18		0x1b0b0
 				MX6QDL_PAD_DI0_PIN3__GPIO4_IO19		0x1b0b0
-				MX6QDL_PAD_DI0_PIN4__AUD6_RXD		0x1b0b0
-				MX6QDL_PAD_DI0_PIN15__AUD6_TXC		0x1b0b0
+				MX6QDL_PAD_DI0_PIN4__AUD6_RXD		0x13080
+				MX6QDL_PAD_DI0_PIN15__AUD6_TXC		0x13080
 				MX6QDL_PAD_EIM_EB2__GPIO2_IO30		0x1b0b0
 			>;
 		};
diff --git a/arch/arm/boot/dts/imx6qdl-var-dart.dtsi b/arch/arm/boot/dts/imx6qdl-var-dart.dtsi
new file mode 100644
index 000000000000..421d6f527609
--- /dev/null
+++ b/arch/arm/boot/dts/imx6qdl-var-dart.dtsi
@@ -0,0 +1,503 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Support for Variscite DART-MX6 Module
+ *
+ * Copyright 2017 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/sound/fsl-imx-audmux.h>
+
+/ {
+	memory {
+		reg = <0x10000000 0x40000000>;
+	};
+
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "3P3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+
+	reg_wl18xx_vmmc: regulator-wl18xx {
+		compatible = "regulator-fixed";
+		regulator-name = "vwl1807";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		gpio = <&gpio7 8 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		startup-delay-us = <70000>;
+	};
+};
+
+&audmux {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_audmux>;
+	status = "okay";
+
+	ssi2 {
+		fsl,audmux-port = <1>;
+		fsl,port-config = <
+			(IMX_AUDMUX_V2_PTCR_SYN |
+			IMX_AUDMUX_V2_PTCR_TFSDIR |
+			IMX_AUDMUX_V2_PTCR_TFSEL(2) |
+			IMX_AUDMUX_V2_PTCR_TCLKDIR |
+			IMX_AUDMUX_V2_PTCR_TCSEL(2))
+			IMX_AUDMUX_V2_PDCR_RXDSEL(2)
+		>;
+	};
+
+	aud3 {
+		fsl,audmux-port = <2>;
+		fsl,port-config = <
+			IMX_AUDMUX_V2_PTCR_SYN
+			IMX_AUDMUX_V2_PDCR_RXDSEL(1)
+		>;
+	};
+};
+
+&can1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan1>;
+	status = "disabled";
+};
+
+&can2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan2>;
+	status = "disabled";
+};
+
+&ecspi1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi1>;
+	status = "disabled";
+};
+
+&fec {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_enet>;
+	phy-mode = "rgmii";
+	status = "disabled";
+};
+
+&hdmi {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hdmicec>;
+	ddc-i2c-bus = <&i2c1>;
+	status = "disabled";
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c1>;
+	status = "disabled";
+};
+
+&i2c2 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c2>;
+	status = "okay";
+
+	pmic@8 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_pmic>;
+		compatible = "fsl,pfuze100";
+		reg = <0x08>;
+
+		regulators {
+			sw1a_reg: sw1ab {
+				regulator-min-microvolt = <300000>;
+				regulator-max-microvolt = <1875000>;
+				regulator-boot-on;
+				regulator-always-on;
+				regulator-ramp-delay = <6250>;
+			};
+
+			sw1c_reg: sw1c {
+				regulator-min-microvolt = <300000>;
+				regulator-max-microvolt = <1875000>;
+				regulator-boot-on;
+				regulator-always-on;
+				regulator-ramp-delay = <6250>;
+			};
+
+			sw2_reg: sw2 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw3a_reg: sw3a {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <3950000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw3b_reg: sw3b {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <3950000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw4_reg: sw4 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <3950000>;
+			};
+
+			snvs_reg: vsnvs {
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vref_reg: vrefddr {
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vgen6_reg: vgen6 {
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+		};
+	};
+
+	tlv320aic3106: codec@1b {
+		compatible = "ti,tlv320aic3106";
+		reg = <0x1b>;
+		#sound-dai-cells = <0>;
+		DRVDD-supply = <&reg_3p3v>;
+		AVDD-supply = <&reg_3p3v>;
+		IOVDD-supply = <&reg_3p3v>;
+		DVDD-supply = <&reg_3p3v>;
+		ai3x-ocmv = <0>;
+		gpio-reset = <&gpio5 5 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&i2c3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c3>;
+	status = "disabled";
+};
+
+&iomuxc {
+	pinctrl_audmux: audmux {
+		fsl,pins = <
+			MX6QDL_PAD_CSI0_DAT7__AUD3_RXD		0x130b0
+			MX6QDL_PAD_CSI0_DAT4__AUD3_TXC		0x130b0
+			MX6QDL_PAD_CSI0_DAT5__AUD3_TXD		0x110b0
+			MX6QDL_PAD_CSI0_DAT6__AUD3_TXFS		0x130b0
+			/* Audio Clock */
+			MX6QDL_PAD_GPIO_0__CCM_CLKO1		0x130b0
+		>;
+	};
+
+	pinctrl_bt: bt {
+		fsl,pins = <
+			/* Bluetooth enable */
+			MX6QDL_PAD_SD3_DAT6__GPIO6_IO18		0x1b0b1
+			/* Bluetooth Slow Clock */
+			MX6QDL_PAD_ENET_RXD0__OSC32K_32K_OUT	0x000b0
+		>;
+	};
+
+	pinctrl_ecspi1: ecspi1grp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL1__ECSPI1_MISO	0x100b1
+			MX6QDL_PAD_KEY_ROW0__ECSPI1_MOSI	0x100b1
+			MX6QDL_PAD_KEY_COL0__ECSPI1_SCLK	0x100b1
+			/* SPI1 CS0 */
+			MX6QDL_PAD_KEY_ROW1__GPIO4_IO09		0x1b0b0
+			/* SPI1 CS1 */
+			MX6QDL_PAD_KEY_COL2__GPIO4_IO10		0x1b0b0
+		>;
+	};
+
+	pinctrl_enet: enetgrp {
+		fsl,pins = <
+			MX6QDL_PAD_ENET_MDIO__ENET_MDIO		0x100b0
+			MX6QDL_PAD_ENET_MDC__ENET_MDC		0x100b0
+			MX6QDL_PAD_RGMII_TXC__RGMII_TXC		0x10030
+			MX6QDL_PAD_RGMII_TD0__RGMII_TD0		0x10030
+			MX6QDL_PAD_RGMII_TD1__RGMII_TD1		0x10030
+			MX6QDL_PAD_RGMII_TD2__RGMII_TD2		0x10030
+			MX6QDL_PAD_RGMII_TD3__RGMII_TD3		0x10030
+			MX6QDL_PAD_RGMII_TX_CTL__RGMII_TX_CTL	0x10030
+			MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK	0x100b0
+			MX6QDL_PAD_RGMII_RXC__RGMII_RXC		0x1b030
+			MX6QDL_PAD_RGMII_RD0__RGMII_RD0		0x1b030
+			MX6QDL_PAD_RGMII_RD1__RGMII_RD1		0x1b030
+			MX6QDL_PAD_RGMII_RD2__RGMII_RD2		0x1b030
+			MX6QDL_PAD_RGMII_RD3__RGMII_RD3		0x1b030
+			MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL	0x1b030
+		>;
+	};
+
+	pinctrl_flexcan1: flexcan1grp {
+		fsl,pins = <
+			MX6QDL_PAD_GPIO_7__FLEXCAN1_TX	0x1b0b0
+			MX6QDL_PAD_GPIO_8__FLEXCAN1_RX	0x1b0b0
+		>;
+	};
+
+	pinctrl_flexcan2: flexcan2grp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL4__FLEXCAN2_TX	0x1b0b0
+			MX6QDL_PAD_KEY_ROW4__FLEXCAN2_RX	0x1b0b0
+		>;
+	};
+
+	pinctrl_hdmicec: hdmicecgrp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_ROW2__HDMI_TX_CEC_LINE	0x1f8b0
+		>;
+	};
+
+	pinctrl_i2c1: i2c1grp {
+		fsl,pins = <
+			MX6QDL_PAD_CSI0_DAT8__I2C1_SDA	0x4001b8b1
+			MX6QDL_PAD_CSI0_DAT9__I2C1_SCL	0x4001b8b1
+		>;
+	};
+
+	pinctrl_i2c2: i2c2grp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL3__I2C2_SCL	0x4001b8b1
+			MX6QDL_PAD_KEY_ROW3__I2C2_SDA	0x4001b8b1
+		>;
+	};
+
+	pinctrl_i2c3: i2c3grp {
+		fsl,pins = <
+			MX6QDL_PAD_GPIO_5__I2C3_SCL	0x4001b8b1
+			MX6QDL_PAD_GPIO_16__I2C3_SDA	0x4001b8b1
+		>;
+	};
+
+	pinctrl_pmic: pmicgrp {
+		fsl,pins = <
+			/* PMIC INT */
+			MX6QDL_PAD_GPIO_17__GPIO7_IO12	0x1b0b1
+		>;
+	};
+
+	pinctrl_pwm2: pwm2grp {
+		fsl,pins = <
+			MX6QDL_PAD_DISP0_DAT9__PWM2_OUT	0x1b0b1
+		>;
+	};
+
+	pinctrl_uart1: uart1grp {
+		fsl,pins = <
+			MX6QDL_PAD_CSI0_DAT11__UART1_RX_DATA 0x1b0b1
+			MX6QDL_PAD_CSI0_DAT10__UART1_TX_DATA 0x1b0b1
+		>;
+	};
+
+	pinctrl_uart2: uart2grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD3_DAT4__UART2_RX_DATA	0x1b0b1
+			MX6QDL_PAD_SD3_DAT5__UART2_TX_DATA	0x1b0b1
+			MX6QDL_PAD_SD4_DAT6__UART2_CTS_B	0x1b0b1
+			MX6QDL_PAD_SD4_DAT5__UART2_RTS_B	0x1b0b1
+		>;
+	};
+
+	pinctrl_uart3: uart3grp {
+		fsl,pins = <
+			MX6QDL_PAD_EIM_D25__UART3_RX_DATA 0x1b0b1
+			MX6QDL_PAD_EIM_D24__UART3_TX_DATA 0x1b0b1
+			MX6QDL_PAD_EIM_D23__UART3_CTS_B   0x1b0b1
+			MX6QDL_PAD_EIM_EB3__UART3_RTS_B   0x1b0b1
+		>;
+	};
+
+	pinctrl_usbotg: usbotggrp {
+		fsl,pins = <
+			MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059
+		>;
+	};
+
+	pinctrl_usdhc1: usdhc1grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD1_CMD__SD1_CMD	0x17059
+			MX6QDL_PAD_SD1_CLK__SD1_CLK	0x10059
+			MX6QDL_PAD_SD1_DAT0__SD1_DATA0	0x17059
+			MX6QDL_PAD_SD1_DAT1__SD1_DATA1	0x17059
+			MX6QDL_PAD_SD1_DAT2__SD1_DATA2	0x17059
+			MX6QDL_PAD_SD1_DAT3__SD1_DATA3	0x17059
+			/* WL_EN */
+			MX6QDL_PAD_SD3_DAT7__GPIO6_IO17 0x17071
+			/* WL_IRQ */
+			MX6QDL_PAD_SD3_RST__GPIO7_IO08  0x17071
+		>;
+	};
+
+	pinctrl_usdhc1_100mhz: usdhc1grp100mhz {
+		fsl,pins = <
+			MX6QDL_PAD_SD1_CMD__SD1_CMD	0x170B9
+			MX6QDL_PAD_SD1_CLK__SD1_CLK	0x100B9
+			MX6QDL_PAD_SD1_DAT0__SD1_DATA0	0x170B9
+			MX6QDL_PAD_SD1_DAT1__SD1_DATA1	0x170B9
+			MX6QDL_PAD_SD1_DAT2__SD1_DATA2	0x170B9
+			MX6QDL_PAD_SD1_DAT3__SD1_DATA3	0x170B9
+		>;
+	};
+
+	pinctrl_usdhc1_200mhz: usdhc1grp200mhz {
+		fsl,pins = <
+			MX6QDL_PAD_SD1_CMD__SD1_CMD	0x170F9
+			MX6QDL_PAD_SD1_CLK__SD1_CLK	0x100F9
+			MX6QDL_PAD_SD1_DAT0__SD1_DATA0	0x170F9
+			MX6QDL_PAD_SD1_DAT1__SD1_DATA1	0x170F9
+			MX6QDL_PAD_SD1_DAT2__SD1_DATA2	0x170F9
+			MX6QDL_PAD_SD1_DAT3__SD1_DATA3	0x170F9
+		>;
+	};
+
+	pinctrl_usdhc2: usdhc2grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD2_CMD__SD2_CMD	0x17059
+			MX6QDL_PAD_SD2_CLK__SD2_CLK	0x10059
+			MX6QDL_PAD_SD2_DAT0__SD2_DATA0	0x17059
+			MX6QDL_PAD_SD2_DAT1__SD2_DATA1	0x17059
+			MX6QDL_PAD_SD2_DAT2__SD2_DATA2	0x17059
+			MX6QDL_PAD_SD2_DAT3__SD2_DATA3	0x17059
+		>;
+	};
+
+	pinctrl_usdhc3: usdhc3grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD3_CMD__SD3_CMD	0x17059
+			MX6QDL_PAD_SD3_CLK__SD3_CLK	0x10059
+			MX6QDL_PAD_SD3_DAT0__SD3_DATA0	0x17059
+			MX6QDL_PAD_SD3_DAT1__SD3_DATA1	0x17059
+			MX6QDL_PAD_SD3_DAT2__SD3_DATA2	0x17059
+			MX6QDL_PAD_SD3_DAT3__SD3_DATA3	0x17059
+		>;
+	};
+};
+
+&pcie {
+	fsl,tx-swing-full = <103>;
+	fsl,tx-swing-low = <103>;
+	reset-gpio = <&gpio4 11 GPIO_ACTIVE_LOW>;
+	status = "disabled";
+};
+
+&pwm2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm2>;
+	status = "disabled";
+};
+
+&reg_arm {
+	vin-supply = <&sw1a_reg>;
+};
+
+&reg_pu {
+	vin-supply = <&sw1c_reg>;
+};
+
+&reg_soc {
+	vin-supply = <&sw1c_reg>;
+};
+
+&snvs_poweroff {
+	status = "okay";
+};
+
+&ssi2 {
+	status = "okay";
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1>;
+	status = "disabled";
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2 &pinctrl_bt>;
+	uart-has-rtscts;
+	status = "okay";
+
+	bluetooth {
+		compatible = "ti,wl1835-st";
+		enable-gpios = <&gpio6 18 GPIO_ACTIVE_HIGH>;
+	};
+};
+
+&uart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart3>;
+	uart-has-rtscts;
+	status = "disabled";
+};
+
+&usbh1 {
+	status = "disabled";
+};
+
+&usbotg {
+	vbus-supply = <&reg_usb_otg_vbus>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usbotg>;
+	disable-over-current;
+	status = "disabled";
+};
+
+&usdhc1 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc1>;
+	pinctrl-1 = <&pinctrl_usdhc1_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc1_200mhz>;
+	bus-width = <4>;
+	vmmc-supply = <&reg_wl18xx_vmmc>;
+	non-removable;
+	wakeup-source;
+	keep-power-in-suspend;
+	cap-power-off-card;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	wlcore: wlcore@2 {
+		compatible = "ti,wl1835";
+		reg = <2>;
+		interrupt-parent = <&gpio6>;
+		interrupts = <17 IRQ_TYPE_LEVEL_HIGH>;
+		ref-clock-frequency = <38400000>;
+	};
+};
+
+&usdhc2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc2>;
+	no-1-8-v;
+	keep-power-in-suspend;
+	wakeup-source;
+	status = "disabled";
+};
+
+&usdhc3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc3>;
+	non-removable;
+	keep-power-in-suspend;
+	wakeup-source;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi b/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi
index 6d8d9ca96646..3a8a4952d45e 100644
--- a/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi
@@ -21,6 +21,11 @@
 	};
 };
 
+&hdmi {
+	ddc-i2c-bus = <&i2c2>;
+	status = "okay";
+};
+
 &i2c3 {
 	clock-frequency = <100000>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
index 7812fbac963c..72f52fcecee1 100644
--- a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
@@ -49,6 +49,7 @@
 
 	aliases {
 		mdio-gpio0 = &mdio1;
+		rtc0 = &ds1341;
 	};
 
 	mdio1: mdio {
@@ -501,7 +502,7 @@
 		reg = <0x54>;
 	};
 
-	rtc@68 {
+	ds1341: rtc@68 {
 		compatible = "dallas,ds1341";
 		reg = <0x68>;
 	};
@@ -580,6 +581,17 @@
 	pinctrl-0 = <&pinctrl_pcie>;
 	reset-gpio = <&gpio7 12 GPIO_ACTIVE_LOW>;
 	status = "okay";
+
+	host@0 {
+		reg = <0 0 0 0 0>;
+
+		#address-cells = <3>;
+		#size-cells = <2>;
+
+		i210: i210@0 {
+			reg = <0 0 0 0 0>;
+		};
+	};
 };
 
 &usdhc2 {
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index 1ce4eabf0590..59ff86695a14 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -80,6 +80,75 @@
 		};
 	};
 
+	tempmon: tempmon {
+		compatible = "fsl,imx6q-tempmon";
+		interrupt-parent = <&gpc>;
+		interrupts = <0 49 IRQ_TYPE_LEVEL_HIGH>;
+		fsl,tempmon = <&anatop>;
+		fsl,tempmon-data = <&ocotp>;
+		clocks = <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
+	};
+
+	ldb: ldb {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "fsl,imx6q-ldb", "fsl,imx53-ldb";
+		gpr = <&gpr>;
+		status = "disabled";
+
+		lvds-channel@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+			status = "disabled";
+
+			port@0 {
+				reg = <0>;
+
+				lvds0_mux_0: endpoint {
+					remote-endpoint = <&ipu1_di0_lvds0>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				lvds0_mux_1: endpoint {
+					remote-endpoint = <&ipu1_di1_lvds0>;
+				};
+			};
+		};
+
+		lvds-channel@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+			status = "disabled";
+
+			port@0 {
+				reg = <0>;
+
+				lvds1_mux_0: endpoint {
+					remote-endpoint = <&ipu1_di0_lvds1>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				lvds1_mux_1: endpoint {
+					remote-endpoint = <&ipu1_di1_lvds1>;
+				};
+			};
+		};
+	};
+
+	pmu {
+		compatible = "arm,cortex-a9-pmu";
+		interrupt-parent = <&gpc>;
+		interrupts = <0 94 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -224,11 +293,6 @@
 			status = "disabled";
 		};
 
-		pmu {
-			compatible = "arm,cortex-a9-pmu";
-			interrupts = <0 94 IRQ_TYPE_LEVEL_HIGH>;
-		};
-
 		aips-bus@2000000 { /* AIPS1 */
 			compatible = "fsl,aips-bus", "simple-bus";
 			#address-cells = <1>;
@@ -631,8 +695,11 @@
 				interrupts = <0 49 IRQ_TYPE_LEVEL_HIGH>,
 					     <0 54 IRQ_TYPE_LEVEL_HIGH>,
 					     <0 127 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <1>;
+				#size-cells = <0>;
 
-				regulator-1p1 {
+				regulator-1p1@20c8110 {
+					reg = <0x20c8110>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd1p1";
 					regulator-min-microvolt = <1000000>;
@@ -647,7 +714,8 @@
 					anatop-enable-bit = <0>;
 				};
 
-				regulator-3p0 {
+				regulator-3p0@20c8120 {
+					reg = <0x20c8120>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd3p0";
 					regulator-min-microvolt = <2800000>;
@@ -662,7 +730,8 @@
 					anatop-enable-bit = <0>;
 				};
 
-				regulator-2p5 {
+				regulator-2p5@20c8130 {
+					reg = <0x20c8130>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd2p5";
 					regulator-min-microvolt = <2250000>;
@@ -677,7 +746,8 @@
 					anatop-enable-bit = <0>;
 				};
 
-				reg_arm: regulator-vddcore {
+				reg_arm: regulator-vddcore@20c8140 {
+					reg = <0x20c8140>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddarm";
 					regulator-min-microvolt = <725000>;
@@ -694,7 +764,8 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_pu: regulator-vddpu {
+				reg_pu: regulator-vddpu@20c8140 {
+					reg = <0x20c8140>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddpu";
 					regulator-min-microvolt = <725000>;
@@ -711,7 +782,8 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_soc: regulator-vddsoc {
+				reg_soc: regulator-vddsoc@20c8140 {
+					reg = <0x20c8140>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddsoc";
 					regulator-min-microvolt = <725000>;
@@ -729,14 +801,6 @@
 				};
 			};
 
-			tempmon: tempmon {
-				compatible = "fsl,imx6q-tempmon";
-				interrupts = <0 49 IRQ_TYPE_LEVEL_HIGH>;
-				fsl,tempmon = <&anatop>;
-				fsl,tempmon-data = <&ocotp>;
-				clocks = <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
-			};
-
 			usbphy1: usbphy@20c9000 {
 				compatible = "fsl,imx6q-usbphy", "fsl,imx23-usbphy";
 				reg = <0x020c9000 0x1000>;
@@ -773,6 +837,10 @@
 					mask = <0x60>;
 					status = "disabled";
 				};
+
+				snvs_lpgpr: snvs-lpgpr {
+					compatible = "fsl,imx6q-snvs-lpgpr";
+				};
 			};
 
 			epit1: epit@20d0000 { /* EPIT1 */
@@ -841,60 +909,6 @@
 				reg = <0x20e0000 0x4000>;
 			};
 
-			ldb: ldb {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,imx6q-ldb", "fsl,imx53-ldb";
-				gpr = <&gpr>;
-				status = "disabled";
-
-				lvds-channel@0 {
-					#address-cells = <1>;
-					#size-cells = <0>;
-					reg = <0>;
-					status = "disabled";
-
-					port@0 {
-						reg = <0>;
-
-						lvds0_mux_0: endpoint {
-							remote-endpoint = <&ipu1_di0_lvds0>;
-						};
-					};
-
-					port@1 {
-						reg = <1>;
-
-						lvds0_mux_1: endpoint {
-							remote-endpoint = <&ipu1_di1_lvds0>;
-						};
-					};
-				};
-
-				lvds-channel@1 {
-					#address-cells = <1>;
-					#size-cells = <0>;
-					reg = <1>;
-					status = "disabled";
-
-					port@0 {
-						reg = <0>;
-
-						lvds1_mux_0: endpoint {
-							remote-endpoint = <&ipu1_di0_lvds1>;
-						};
-					};
-
-					port@1 {
-						reg = <1>;
-
-						lvds1_mux_1: endpoint {
-							remote-endpoint = <&ipu1_di1_lvds1>;
-						};
-					};
-				};
-			};
-
 			dcic1: dcic@20e4000 {
 				reg = <0x020e4000 0x4000>;
 				interrupts = <0 124 IRQ_TYPE_LEVEL_HIGH>;
@@ -1017,6 +1031,7 @@
 			fec: ethernet@2188000 {
 				compatible = "fsl,imx6q-fec";
 				reg = <0x02188000 0x4000>;
+				interrupt-names = "int0", "pps";
 				interrupts-extended =
 					<&intc 0 118 IRQ_TYPE_LEVEL_HIGH>,
 					<&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/imx6sl-evk.dts b/arch/arm/boot/dts/imx6sl-evk.dts
index 60600b4cf5fe..2844ab541759 100644
--- a/arch/arm/boot/dts/imx6sl-evk.dts
+++ b/arch/arm/boot/dts/imx6sl-evk.dts
@@ -20,7 +20,7 @@
 		reg = <0x80000000 0x40000000>;
 	};
 
-	backlight {
+	backlight_display: backlight_display {
 		compatible = "pwm-backlight";
 		pwms = <&pwm1 0 5000000>;
 		brightness-levels = <0 4 8 16 32 64 128 255>;
@@ -39,58 +39,54 @@
 		};
 	};
 
-	regulators {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		reg_usb_otg1_vbus: regulator@0 {
-			compatible = "regulator-fixed";
-			reg = <0>;
-			regulator-name = "usb_otg1_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-			gpio = <&gpio4 0 0>;
-			enable-active-high;
-			vin-supply = <&swbst_reg>;
-		};
+	reg_usb_otg1_vbus: regulator-usb-otg1-vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "usb_otg1_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio4 0 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&swbst_reg>;
+	};
 
-		reg_usb_otg2_vbus: regulator@1 {
-			compatible = "regulator-fixed";
-			reg = <1>;
-			regulator-name = "usb_otg2_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-			gpio = <&gpio4 2 0>;
-			enable-active-high;
-			vin-supply = <&swbst_reg>;
-		};
+	reg_usb_otg2_vbus: regulator-usb-otg2-vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "usb_otg2_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio4 2 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&swbst_reg>;
+	};
 
-		reg_aud3v: regulator@2 {
-			compatible = "regulator-fixed";
-			reg = <2>;
-			regulator-name = "wm8962-supply-3v15";
-			regulator-min-microvolt = <3150000>;
-			regulator-max-microvolt = <3150000>;
-			regulator-boot-on;
-		};
+	reg_aud3v: regulator-aud3v {
+		compatible = "regulator-fixed";
+		regulator-name = "wm8962-supply-3v15";
+		regulator-min-microvolt = <3150000>;
+		regulator-max-microvolt = <3150000>;
+		regulator-boot-on;
+	};
 
-		reg_aud4v: regulator@3 {
-			compatible = "regulator-fixed";
-			reg = <3>;
-			regulator-name = "wm8962-supply-4v2";
-			regulator-min-microvolt = <4325000>;
-			regulator-max-microvolt = <4325000>;
-			regulator-boot-on;
-		};
+	reg_aud4v: regulator-aud4v {
+		compatible = "regulator-fixed";
+		regulator-name = "wm8962-supply-4v2";
+		regulator-min-microvolt = <4325000>;
+		regulator-max-microvolt = <4325000>;
+		regulator-boot-on;
+	};
 
-		reg_lcd_3v3: regulator@4 {
-			compatible = "regulator-fixed";
-			reg = <4>;
-			regulator-name = "lcd-3v3";
-			gpio = <&gpio4 3 0>;
-			enable-active-high;
-		};
+	reg_lcd_3v3: regulator-lcd-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "lcd-3v3";
+		gpio = <&gpio4 3 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_lcd_5v: regulator-lcd-5v {
+		compatible = "regulator-fixed";
+		regulator-name = "lcd-5v0";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
 	};
 
 	sound {
@@ -108,6 +104,19 @@
 		mux-int-port = <2>;
 		mux-ext-port = <3>;
 	};
+
+	panel {
+		compatible = "sii,43wvf1g";
+		backlight = <&backlight_display>;
+		dvdd-supply = <&reg_lcd_3v3>;
+		avdd-supply = <&reg_lcd_5v>;
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&display_out>;
+			};
+		};
+	};
 };
 
 &audmux {
@@ -546,31 +555,11 @@
 &lcdif {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_lcd>;
-	lcd-supply = <&reg_lcd_3v3>;
-	display = <&display0>;
 	status = "okay";
 
-	display0: display0 {
-		bits-per-pixel = <32>;
-		bus-width = <24>;
-
-		display-timings {
-			native-mode = <&timing0>;
-			timing0: timing0 {
-				clock-frequency = <33500000>;
-				hactive = <800>;
-				vactive = <480>;
-				hback-porch = <89>;
-				hfront-porch = <164>;
-				vback-porch = <23>;
-				vfront-porch = <10>;
-				hsync-len = <10>;
-				vsync-len = <10>;
-				hsync-active = <0>;
-				vsync-active = <0>;
-				de-active = <1>;
-				pixelclk-active = <0>;
-			};
+	port {
+		display_out: endpoint {
+			remote-endpoint = <&panel_in>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi
index 3ea1a41893c8..ae8df3cf687e 100644
--- a/arch/arm/boot/dts/imx6sl.dtsi
+++ b/arch/arm/boot/dts/imx6sl.dtsi
@@ -102,6 +102,21 @@
 		};
 	};
 
+	tempmon: tempmon {
+		compatible = "fsl,imx6q-tempmon";
+		interrupts = <0 49 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-parent = <&gpc>;
+		fsl,tempmon = <&anatop>;
+		fsl,tempmon-data = <&ocotp>;
+		clocks = <&clks IMX6SL_CLK_PLL3_USB_OTG>;
+	};
+
+	pmu {
+		compatible = "arm,cortex-a9-pmu";
+		interrupt-parent = <&gpc>;
+		interrupts = <0 94 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -125,11 +140,6 @@
 			arm,data-latency = <4 2 3>;
 		};
 
-		pmu {
-			compatible = "arm,cortex-a9-pmu";
-			interrupts = <0 94 IRQ_TYPE_LEVEL_HIGH>;
-		};
-
 		aips1: aips-bus@2000000 {
 			compatible = "fsl,aips-bus", "simple-bus";
 			#address-cells = <1>;
@@ -517,8 +527,11 @@
 				interrupts = <0 49 IRQ_TYPE_LEVEL_HIGH>,
 					     <0 54 IRQ_TYPE_LEVEL_HIGH>,
 					     <0 127 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <1>;
+				#size-cells = <0>;
 
-				regulator-1p1 {
+				regulator-1p1@20c8110 {
+					reg = <0x20c8110>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd1p1";
 					regulator-min-microvolt = <800000>;
@@ -533,7 +546,8 @@
 					anatop-enable-bit = <0>;
 				};
 
-				regulator-3p0 {
+				regulator-3p0@20c8120 {
+					reg = <0x20c8120>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd3p0";
 					regulator-min-microvolt = <2800000>;
@@ -548,7 +562,8 @@
 					anatop-enable-bit = <0>;
 				};
 
-				regulator-2p5 {
+				regulator-2p5@20c8130 {
+					reg = <0x20c8130>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd2p5";
 					regulator-min-microvolt = <2100000>;
@@ -563,7 +578,8 @@
 					anatop-enable-bit = <0>;
 				};
 
-				reg_arm: regulator-vddcore {
+				reg_arm: regulator-vddcore@20c8140 {
+					reg = <0x20c8140>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddarm";
 					regulator-min-microvolt = <725000>;
@@ -580,7 +596,8 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_pu: regulator-vddpu {
+				reg_pu: regulator-vddpu@20c8140 {
+					reg = <0x20c8140>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddpu";
 					regulator-min-microvolt = <725000>;
@@ -597,7 +614,8 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_soc: regulator-vddsoc {
+				reg_soc: regulator-vddsoc@20c8140 {
+					reg = <0x20c8140>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddsoc";
 					regulator-min-microvolt = <725000>;
@@ -615,14 +633,6 @@
 				};
 			};
 
-			tempmon: tempmon {
-				compatible = "fsl,imx6q-tempmon";
-				interrupts = <0 49 IRQ_TYPE_LEVEL_HIGH>;
-				fsl,tempmon = <&anatop>;
-				fsl,tempmon-data = <&ocotp>;
-				clocks = <&clks IMX6SL_CLK_PLL3_USB_OTG>;
-			};
-
 			usbphy1: usbphy@20c9000 {
 				compatible = "fsl,imx6sl-usbphy", "fsl,imx23-usbphy";
 				reg = <0x020c9000 0x1000>;
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi
index da815527a7f8..d35aa858f9db 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dtsi
+++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi
@@ -24,7 +24,7 @@
 		reg = <0x80000000 0x40000000>;
 	};
 
-	backlight {
+	backlight_display: backlight-display {
 		compatible = "pwm-backlight";
 		pwms = <&pwm3 0 5000000>;
 		brightness-levels = <0 4 8 16 32 64 128 255>;
@@ -49,86 +49,91 @@
 		};
 	};
 
-	regulators {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <0>;
+	vcc_sd3: regulator-vcc-sd3 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_vcc_sd3>;
+		regulator-name = "VCC_SD3";
+		regulator-min-microvolt = <3000000>;
+		regulator-max-microvolt = <3000000>;
+		gpio = <&gpio2 11 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
 
-		vcc_sd3: regulator@0 {
-			compatible = "regulator-fixed";
-			reg = <0>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_vcc_sd3>;
-			regulator-name = "VCC_SD3";
-			regulator-min-microvolt = <3000000>;
-			regulator-max-microvolt = <3000000>;
-			gpio = <&gpio2 11 GPIO_ACTIVE_HIGH>;
-			enable-active-high;
-		};
+	reg_usb_otg1_vbus: regulator-usb-otg1-vbus {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usb_otg1>;
+		regulator-name = "usb_otg1_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio1 9 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
 
-		reg_usb_otg1_vbus: regulator@1 {
-			compatible = "regulator-fixed";
-			reg = <1>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_usb_otg1>;
-			regulator-name = "usb_otg1_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-			gpio = <&gpio1 9 GPIO_ACTIVE_HIGH>;
-			enable-active-high;
-		};
+	reg_usb_otg2_vbus: regulator-usb-otg2-vbus {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usb_otg2>;
+		regulator-name = "usb_otg2_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio1 12 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
 
-		reg_usb_otg2_vbus: regulator@2 {
-			compatible = "regulator-fixed";
-			reg = <2>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_usb_otg2>;
-			regulator-name = "usb_otg2_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-			gpio = <&gpio1 12 GPIO_ACTIVE_HIGH>;
-			enable-active-high;
-		};
-
-		reg_psu_5v: regulator@3 {
-			compatible = "regulator-fixed";
-			reg = <3>;
-			regulator-name = "PSU-5V0";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-		};
-
-		reg_lcd_3v3: regulator@4 {
-			compatible = "regulator-fixed";
-			reg = <4>;
-			regulator-name = "lcd-3v3";
-			gpio = <&gpio3 27 0>;
-			enable-active-high;
-		};
-
-		reg_peri_3v3: regulator@5 {
-			compatible = "regulator-fixed";
-			reg = <5>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_peri_3v3>;
-			regulator-name = "peri_3v3";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			gpio = <&gpio4 16 GPIO_ACTIVE_HIGH>;
-			enable-active-high;
-			regulator-always-on;
-		};
-
-		reg_enet_3v3: regulator@6 {
-			compatible = "regulator-fixed";
-			reg = <6>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_enet_3v3>;
-			regulator-name = "enet_3v3";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			gpios = <&gpio2 6 GPIO_ACTIVE_LOW>;
-		};
+	reg_psu_5v: regulator-psu-5v {
+		compatible = "regulator-fixed";
+		regulator-name = "PSU-5V0";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	reg_lcd_3v3: regulator-lcd-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "lcd-3v3";
+		gpio = <&gpio3 27 0>;
+		enable-active-high;
+	};
+
+	reg_peri_3v3: regulator-peri-3v3 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_peri_3v3>;
+		regulator-name = "peri_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio4 16 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
+	};
+
+	reg_enet_3v3: regulator-enet-3v3 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_enet_3v3>;
+		regulator-name = "enet_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpios = <&gpio2 6 GPIO_ACTIVE_LOW>;
+	};
+
+	reg_pcie_gpio: regulator-pcie-gpio {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_pcie_reg>;
+		regulator-name = "MPCIE_3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio2 1 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_lcd_5v: regulator-lcd-5v {
+		compatible = "regulator-fixed";
+		regulator-name = "lcd-5v0";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
 	};
 
 	sound {
@@ -146,6 +151,19 @@
 		mux-int-port = <2>;
 		mux-ext-port = <6>;
 	};
+
+	panel {
+		compatible = "sii,43wvf1g";
+		backlight = <&backlight_display>;
+		dvdd-supply = <&reg_lcd_3v3>;
+		avdd-supply = <&reg_lcd_5v>;
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&display_out>;
+			};
+		};
+	};
 };
 
 &audmux {
@@ -212,34 +230,22 @@
 	};
 };
 
+&pcie {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pcie>;
+	reset-gpio = <&gpio2 0 GPIO_ACTIVE_LOW>;
+	vpcie-supply = <&reg_pcie_gpio>;
+	status = "okay";
+};
+
 &lcdif1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_lcd>;
-	lcd-supply = <&reg_lcd_3v3>;
-	display = <&display0>;
 	status = "okay";
 
-	display0: display0 {
-		bits-per-pixel = <16>;
-		bus-width = <24>;
-
-		display-timings {
-			native-mode = <&timing0>;
-			timing0: timing0 {
-				clock-frequency = <33500000>;
-				hactive = <800>;
-				vactive = <480>;
-				hback-porch = <89>;
-				hfront-porch = <164>;
-				vback-porch = <23>;
-				vfront-porch = <10>;
-				hsync-len = <10>;
-				vsync-len = <10>;
-				hsync-active = <0>;
-				vsync-active = <0>;
-				de-active = <1>;
-				pixelclk-active = <0>;
-			};
+	port {
+		display_out: endpoint {
+			remote-endpoint = <&panel_in>;
 		};
 	};
 };
@@ -453,6 +459,18 @@
 			>;
 		};
 
+		pinctrl_pcie: pciegrp {
+			fsl,pins = <
+				MX6SX_PAD_ENET1_COL__GPIO2_IO_0 0x10b0
+			>;
+		};
+
+		pinctrl_pcie_reg: pciereggrp {
+			fsl,pins = <
+				MX6SX_PAD_ENET1_CRS__GPIO2_IO_1	0x10b0
+			>;
+		};
+
 		pinctrl_peri_3v3: peri3v3grp {
 			fsl,pins = <
 				MX6SX_PAD_QSPI1A_DATA0__GPIO4_IO_16	0x80000000
diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi
index 5b03ba3beda9..fd7879342d0d 100644
--- a/arch/arm/boot/dts/imx6sx.dtsi
+++ b/arch/arm/boot/dts/imx6sx.dtsi
@@ -141,6 +141,22 @@
 		};
 	};
 
+	tempmon: tempmon {
+		compatible = "fsl,imx6sx-tempmon", "fsl,imx6q-tempmon";
+		interrupt-parent = <&gpc>;
+		interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
+		fsl,tempmon = <&anatop>;
+		nvmem-cells = <&tempmon_calib>, <&tempmon_temp_grade>;
+		nvmem-cell-names = "calib", "temp_grade";
+		clocks = <&clks IMX6SX_CLK_PLL3_USB_OTG>;
+	};
+
+	pmu {
+		compatible = "arm,cortex-a9-pmu";
+		interrupt-parent = <&gpc>;
+		interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -148,11 +164,6 @@
 		interrupt-parent = <&gpc>;
 		ranges;
 
-		pmu {
-			compatible = "arm,cortex-a9-pmu";
-			interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
-		};
-
 		ocram: sram@900000 {
 			compatible = "mmio-sram";
 			reg = <0x00900000 0x20000>;
@@ -574,8 +585,11 @@
 				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <1>;
+				#size-cells = <0>;
 
-				regulator-1p1 {
+				regulator-1p1@20c8110 {
+					reg = <0x20c8110>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd1p1";
 					regulator-min-microvolt = <800000>;
@@ -590,7 +604,8 @@
 					anatop-enable-bit = <0>;
 				};
 
-				regulator-3p0 {
+				regulator-3p0@20c8120 {
+					reg = <0x20c8120>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd3p0";
 					regulator-min-microvolt = <2800000>;
@@ -605,7 +620,8 @@
 					anatop-enable-bit = <0>;
 				};
 
-				regulator-2p5 {
+				regulator-2p5@20c8130 {
+					reg = <0x20c8130>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd2p5";
 					regulator-min-microvolt = <2100000>;
@@ -620,7 +636,8 @@
 					anatop-enable-bit = <0>;
 				};
 
-				reg_arm: regulator-vddcore {
+				reg_arm: regulator-vddcore@20c8140 {
+					reg = <0x20c8140>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddarm";
 					regulator-min-microvolt = <725000>;
@@ -637,7 +654,8 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_pcie: regulator-vddpcie {
+				reg_pcie: regulator-vddpcie@20c8140 {
+					reg = <0x20c8140>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddpcie";
 					regulator-min-microvolt = <725000>;
@@ -653,7 +671,8 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_soc: regulator-vddsoc {
+				reg_soc: regulator-vddsoc@20c8140 {
+					reg = <0x20c8140>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddsoc";
 					regulator-min-microvolt = <725000>;
@@ -671,15 +690,6 @@
 				};
 			};
 
-			tempmon: tempmon {
-				compatible = "fsl,imx6sx-tempmon", "fsl,imx6q-tempmon";
-				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
-				fsl,tempmon = <&anatop>;
-				nvmem-cells = <&tempmon_calib>, <&tempmon_temp_grade>;
-				nvmem-cell-names = "calib", "temp_grade";
-				clocks = <&clks IMX6SX_CLK_PLL3_USB_OTG>;
-			};
-
 			usbphy1: usbphy@20c9000 {
 				compatible = "fsl,imx6sx-usbphy", "fsl,imx23-usbphy";
 				reg = <0x020c9000 0x1000>;
@@ -750,6 +760,19 @@
 				#interrupt-cells = <3>;
 				interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
 				interrupt-parent = <&intc>;
+				clocks = <&clks IMX6SX_CLK_IPG>;
+				clock-names = "ipg";
+
+				pgc {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					pd_pci: power-domain@3 {
+						reg = <3>;
+						#power-domain-cells = <0>;
+						power-supply = <&reg_pcie>;
+					};
+				};
 			};
 
 			iomuxc: iomuxc@20e0000 {
@@ -862,6 +885,7 @@
 			fec1: ethernet@2188000 {
 				compatible = "fsl,imx6sx-fec", "fsl,imx6q-fec";
 				reg = <0x02188000 0x4000>;
+				interrupt-names = "int0", "pps";
 				interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6SX_CLK_ENET>,
@@ -971,6 +995,7 @@
 			fec2: ethernet@21b4000 {
 				compatible = "fsl,imx6sx-fec", "fsl,imx6q-fec";
 				reg = <0x021b4000 0x4000>;
+				interrupt-names = "int0", "pps";
 				interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6SX_CLK_ENET>,
@@ -1138,7 +1163,7 @@
 			reg = <0x02200000 0x100000>;
 			ranges;
 
-			spba-bus@2200000 {
+			spba-bus@2240000 {
 				compatible = "fsl,spba-bus", "simple-bus";
 				#address-cells = <1>;
 				#size-cells = <1>;
@@ -1304,25 +1329,29 @@
 
 		pcie: pcie@8ffc000 {
 			compatible = "fsl,imx6sx-pcie", "snps,dw-pcie";
-			reg = <0x08ffc000 0x4000>; /* DBI */
+			reg = <0x08ffc000 0x04000>, <0x08f00000 0x80000>;
+			reg-names = "dbi", "config";
 			#address-cells = <3>;
 			#size-cells = <2>;
 			device_type = "pci";
-				  /* configuration space */
-			ranges = <0x00000800 0 0x08f00000 0x08f00000 0 0x00080000
-				  /* downstream I/O */
-				  0x81000000 0 0          0x08f80000 0 0x00010000
-				  /* non-prefetchable memory */
-				  0x82000000 0 0x08000000 0x08000000 0 0x00f00000>;
 			bus-range = <0x00 0xff>;
+			ranges = <0x81000000 0 0          0x08f80000 0 0x00010000 /* downstream I/O */
+				  0x82000000 0 0x08000000 0x08000000 0 0x00f00000>; /* non-prefetchable memory */
 			num-lanes = <1>;
 			interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&clks IMX6SX_CLK_PCIE_REF_125M>,
-				 <&clks IMX6SX_CLK_PCIE_AXI>,
+			interrupt-names = "msi";
+			#interrupt-cells = <1>;
+			interrupt-map-mask = <0 0 0 0x7>;
+			interrupt-map = <0 0 0 1 &gpc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 2 &gpc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 3 &gpc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 4 &gpc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clks IMX6SX_CLK_PCIE_AXI>,
 				 <&clks IMX6SX_CLK_LVDS1_OUT>,
+				 <&clks IMX6SX_CLK_PCIE_REF_125M>,
 				 <&clks IMX6SX_CLK_DISPLAY_AXI>;
-			clock-names = "pcie_ref_125m", "pcie_axi",
-				      "lvds_gate", "display_axi";
+			clock-names = "pcie", "pcie_bus", "pcie_phy", "pcie_inbound_axi";
+			power-domains = <&pd_pci>;
 			status = "disabled";
 		};
 	};
diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dts b/arch/arm/boot/dts/imx6ul-14x14-evk.dts
index e5d3ef88be60..18fdb088ba1e 100644
--- a/arch/arm/boot/dts/imx6ul-14x14-evk.dts
+++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dts
@@ -30,19 +30,14 @@
 		status = "okay";
 	};
 
-	regulators {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
-		reg_sd1_vmmc: sd1_regulator {
-			compatible = "regulator-fixed";
-			regulator-name = "VSD_3V3";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			gpio = <&gpio1 9 GPIO_ACTIVE_HIGH>;
-			enable-active-high;
-		};
+	reg_sd1_vmmc: regulator-sd1-vmmc {
+		compatible = "regulator-fixed";
+		regulator-name = "VSD_3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio1 9 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
 	};
 
 	sound {
diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi
index d5181f85ca9c..5d6c3ba36cd1 100644
--- a/arch/arm/boot/dts/imx6ul.dtsi
+++ b/arch/arm/boot/dts/imx6ul.dtsi
@@ -68,12 +68,14 @@
 			clock-latency = <61036>; /* two CLK32 periods */
 			operating-points = <
 				/* kHz	uV */
+				696000	1275000
 				528000	1175000
 				396000	1025000
 				198000	950000
 			>;
 			fsl,soc-operating-points = <
 				/* KHz	uV */
+				696000	1275000
 				528000	1175000
 				396000	1175000
 				198000	1175000
@@ -136,6 +138,23 @@
 		clock-output-names = "ipp_di1";
 	};
 
+	tempmon: tempmon {
+		compatible = "fsl,imx6ul-tempmon", "fsl,imx6sx-tempmon";
+		interrupt-parent = <&gpc>;
+		interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
+		fsl,tempmon = <&anatop>;
+		nvmem-cells = <&tempmon_calib>, <&tempmon_temp_grade>;
+		nvmem-cell-names = "calib", "temp_grade";
+		clocks = <&clks IMX6UL_CLK_PLL3_USB_OTG>;
+	};
+
+	pmu {
+		compatible = "arm,cortex-a7-pmu";
+		interrupt-parent = <&gpc>;
+		interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
+		status = "disabled";
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -143,12 +162,6 @@
 		interrupt-parent = <&gpc>;
 		ranges;
 
-		pmu {
-			compatible = "arm,cortex-a7-pmu";
-			interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
-			status = "disabled";
-		};
-
 		ocram: sram@900000 {
 			compatible = "mmio-sram";
 			reg = <0x00900000 0x20000>;
@@ -476,6 +489,7 @@
 			fec2: ethernet@20b4000 {
 				compatible = "fsl,imx6ul-fec", "fsl,imx6q-fec";
 				reg = <0x020b4000 0x4000>;
+				interrupt-names = "int0", "pps";
 				interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6UL_CLK_ENET>,
@@ -530,8 +544,11 @@
 				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <1>;
+				#size-cells = <0>;
 
-				reg_3p0: regulator-3p0 {
+				reg_3p0: regulator-3p0@20c8110 {
+					reg = <0x20c8110>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd3p0";
 					regulator-min-microvolt = <2625000>;
@@ -545,7 +562,8 @@
 					anatop-enable-bit = <0>;
 				};
 
-				reg_arm: regulator-vddcore {
+				reg_arm: regulator-vddcore@20c8140 {
+					reg = <0x20c8140>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "cpu";
 					regulator-min-microvolt = <725000>;
@@ -562,7 +580,8 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_soc: regulator-vddsoc {
+				reg_soc: regulator-vddsoc@20c8140 {
+					reg = <0x20c8140>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddsoc";
 					regulator-min-microvolt = <725000>;
@@ -598,15 +617,6 @@
 				fsl,anatop = <&anatop>;
 			};
 
-			tempmon: tempmon {
-				compatible = "fsl,imx6ul-tempmon", "fsl,imx6sx-tempmon";
-				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
-				fsl,tempmon = <&anatop>;
-				nvmem-cells = <&tempmon_calib>, <&tempmon_temp_grade>;
-				nvmem-cell-names = "calib", "temp_grade";
-				clocks = <&clks IMX6UL_CLK_PLL3_USB_OTG>;
-			};
-
 			snvs: snvs@20cc000 {
 				compatible = "fsl,sec-v4.0-mon", "syscon", "simple-mfd";
 				reg = <0x020cc000 0x4000>;
@@ -635,6 +645,10 @@
 					linux,keycode = <KEY_POWER>;
 					wakeup-source;
 				};
+
+				snvs_lpgpr: snvs-lpgpr {
+					compatible = "fsl,imx6ul-snvs-lpgpr";
+				};
 			};
 
 			epit1: epit@20d0000 {
@@ -784,6 +798,7 @@
 			fec1: ethernet@2188000 {
 				compatible = "fsl,imx6ul-fec", "fsl,imx6q-fec";
 				reg = <0x02188000 0x4000>;
+				interrupt-names = "int0", "pps";
 				interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6UL_CLK_ENET>,
diff --git a/arch/arm/boot/dts/imx7-colibri-eval-v3.dtsi b/arch/arm/boot/dts/imx7-colibri-eval-v3.dtsi
index 18bebd6d8d47..3f2746169181 100644
--- a/arch/arm/boot/dts/imx7-colibri-eval-v3.dtsi
+++ b/arch/arm/boot/dts/imx7-colibri-eval-v3.dtsi
@@ -45,6 +45,13 @@
 		stdout-path = "serial0:115200n8";
 	};
 
+	/* fixed crystal dedicated to mpc258x */
+	clk16m: clk16m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <16000000>;
+	};
+
 	panel: panel {
 		compatible = "edt,et057090dhu";
 		backlight = <&bl>;
@@ -70,6 +77,17 @@
 		regulator-min-microvolt = <5000000>;
 		regulator-max-microvolt = <5000000>;
 	};
+
+	reg_usbh_vbus: regulator-usbh-vbus {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usbh_reg>;
+		regulator-name = "VCC_USB[1-4]";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio4 7 GPIO_ACTIVE_LOW>;
+		vin-supply = <&reg_5v0>;
+	};
 };
 
 &bl {
@@ -88,6 +106,24 @@
 	status = "okay";
 };
 
+&ecspi3 {
+	status = "okay";
+
+	mcp2515: can@0 {
+		compatible = "microchip,mcp2515";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_can_int>;
+		reg = <0>;
+		clocks = <&clk16m>;
+		interrupt-parent = <&gpio5>;
+		interrupts = <2 IRQ_TYPE_EDGE_FALLING>;
+		spi-max-frequency = <10000000>;
+		vdd-supply = <&reg_3v3>;
+		xceiver-supply = <&reg_5v0>;
+		status = "okay";
+	};
+};
+
 &fec1 {
 	status = "okay";
 };
@@ -97,7 +133,7 @@
 
 	/* M41T0M6 real time clock on carrier board */
 	rtc: m41t0m6@68 {
-		compatible = "st,m41t00";
+		compatible = "st,m41t0";
 		reg = <0x68>;
 	};
 };
@@ -147,5 +183,6 @@
 &usdhc1 {
 	keep-power-in-suspend;
 	wakeup-source;
+	vmmc-supply = <&reg_3v3>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx7-colibri.dtsi b/arch/arm/boot/dts/imx7-colibri.dtsi
index bb5bf94f1a32..895fbde4d433 100644
--- a/arch/arm/boot/dts/imx7-colibri.dtsi
+++ b/arch/arm/boot/dts/imx7-colibri.dtsi
@@ -43,7 +43,10 @@
 / {
 	bl: backlight {
 		compatible = "pwm-backlight";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_bl_on>;
 		pwms = <&pwm1 0 5000000 0>;
+		enable-gpios = <&gpio5 1 GPIO_ACTIVE_HIGH>;
 	};
 
 	reg_module_3v3: regulator-module-3v3 {
@@ -86,7 +89,13 @@
 };
 
 &cpu0 {
-	arm-supply = <&reg_DCDC2>;
+	cpu-supply = <&reg_DCDC2>;
+};
+
+&ecspi3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi3 &pinctrl_ecspi3_cs>;
+	cs-gpios = <&gpio4 11 GPIO_ACTIVE_HIGH>;
 };
 
 &fec1 {
@@ -112,7 +121,6 @@
 	fsl,use-minimum-ecc;
 	nand-on-flash-bbt;
 	nand-ecc-mode = "hw";
-	status = "okay";
 };
 
 &i2c1 {
@@ -299,6 +307,22 @@
 	no-1-8-v;
 	cd-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
 	disable-wp;
+	vqmmc-supply = <&reg_LDO2>;
+};
+
+&usdhc3 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc3>;
+	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
+	assigned-clocks = <&clks IMX7D_USDHC3_ROOT_CLK>;
+	assigned-clock-rates = <400000000>;
+	bus-width = <8>;
+	fsl,tuning-step = <2>;
+	max-frequency = <100000000>;
+	vmmc-supply = <&reg_module_3v3>;
+	vqmmc-supply = <&reg_DCDC3>;
+	non-removable;
 };
 
 &iomuxc {
@@ -307,17 +331,16 @@
 
 	pinctrl_gpio1: gpio1-grp {
 		fsl,pins = <
-			MX7D_PAD_ENET1_RGMII_RD3__GPIO7_IO3	0x14 /* SODIMM 55 */
-			MX7D_PAD_ENET1_RGMII_RD2__GPIO7_IO2	0x14 /* SODIMM 63 */
-			MX7D_PAD_SD1_RESET_B__GPIO5_IO2		0X14 /* SODIMM 73 */
-			MX7D_PAD_SAI1_RX_SYNC__GPIO6_IO16	0X14 /* SODIMM 77 */
+			MX7D_PAD_ENET1_RGMII_RD3__GPIO7_IO3	0x74 /* SODIMM 55 */
+			MX7D_PAD_ENET1_RGMII_RD2__GPIO7_IO2	0x74 /* SODIMM 63 */
+			MX7D_PAD_SAI1_RX_SYNC__GPIO6_IO16	0x14 /* SODIMM 77 */
 			MX7D_PAD_EPDC_DATA09__GPIO2_IO9		0x14 /* SODIMM 89 */
-			MX7D_PAD_EPDC_DATA08__GPIO2_IO8		0x14 /* SODIMM 91 */
+			MX7D_PAD_EPDC_DATA08__GPIO2_IO8		0x74 /* SODIMM 91 */
 			MX7D_PAD_LCD_RESET__GPIO3_IO4		0x14 /* SODIMM 93 */
 			MX7D_PAD_EPDC_DATA13__GPIO2_IO13	0x14 /* SODIMM 95 */
 			MX7D_PAD_ENET1_RGMII_TXC__GPIO7_IO11	0x14 /* SODIMM 99 */
-			MX7D_PAD_EPDC_DATA10__GPIO2_IO10	0x14 /* SODIMM 105 */
-			MX7D_PAD_EPDC_DATA15__GPIO2_IO15	0x14 /* SODIMM 107 */
+			MX7D_PAD_EPDC_DATA10__GPIO2_IO10	0x74 /* SODIMM 105 */
+			MX7D_PAD_EPDC_DATA15__GPIO2_IO15	0x74 /* SODIMM 107 */
 			MX7D_PAD_EPDC_DATA00__GPIO2_IO0		0x14 /* SODIMM 111 */
 			MX7D_PAD_EPDC_DATA01__GPIO2_IO1		0x14 /* SODIMM 113 */
 			MX7D_PAD_EPDC_DATA02__GPIO2_IO2		0x14 /* SODIMM 115 */
@@ -329,11 +352,12 @@
 			MX7D_PAD_EPDC_SDCE2__GPIO2_IO22		0x14 /* SODIMM 127 */
 			MX7D_PAD_UART3_RTS_B__GPIO4_IO6		0x14 /* SODIMM 131 */
 			MX7D_PAD_EPDC_GDRL__GPIO2_IO26		0x14 /* SODIMM 133 */
+			MX7D_PAD_SAI1_RX_DATA__GPIO6_IO12	0x14 /* SODIMM 169 */
 			MX7D_PAD_SAI1_RX_BCLK__GPIO6_IO17	0x14 /* SODIMM 24 */
 			MX7D_PAD_SD2_DATA2__GPIO5_IO16		0x14 /* SODIMM 100 */
 			MX7D_PAD_SD2_DATA3__GPIO5_IO17		0x14 /* SODIMM 102 */
 			MX7D_PAD_EPDC_GDSP__GPIO2_IO27		0x14 /* SODIMM 104 */
-			MX7D_PAD_EPDC_BDR0__GPIO2_IO28		0x14 /* SODIMM 106 */
+			MX7D_PAD_EPDC_BDR0__GPIO2_IO28		0x74 /* SODIMM 106 */
 			MX7D_PAD_EPDC_BDR1__GPIO2_IO29		0x14 /* SODIMM 110 */
 			MX7D_PAD_EPDC_PWR_COM__GPIO2_IO30	0x14 /* SODIMM 112 */
 			MX7D_PAD_EPDC_SDCLK__GPIO2_IO16		0x14 /* SODIMM 114 */
@@ -357,8 +381,7 @@
 	pinctrl_gpio2: gpio2-grp { /* On X22 Camera interface */
 		fsl,pins = <
 			MX7D_PAD_ECSPI2_SS0__GPIO4_IO23		0x14 /* SODIMM 65 */
-			MX7D_PAD_SD1_CD_B__GPIO5_IO0		0x14 /* SODIMM 69 */
-			MX7D_PAD_SD1_WP__GPIO5_IO1		0x14 /* SODIMM 71 */
+			MX7D_PAD_SD1_CD_B__GPIO5_IO0		0x74 /* SODIMM 69 */
 			MX7D_PAD_I2C4_SDA__GPIO4_IO15		0x14 /* SODIMM 75 */
 			MX7D_PAD_ECSPI1_MISO__GPIO4_IO18	0x14 /* SODIMM 79 */
 			MX7D_PAD_I2C3_SCL__GPIO4_IO12		0x14 /* SODIMM 81 */
@@ -378,8 +401,8 @@
 			MX7D_PAD_LCD_DATA19__GPIO3_IO24		0x14 /* SODIMM 138 */
 			MX7D_PAD_LCD_DATA20__GPIO3_IO25		0x14 /* SODIMM 140 */
 			MX7D_PAD_LCD_DATA21__GPIO3_IO26		0x14 /* SODIMM 142 */
-			MX7D_PAD_LCD_DATA22__GPIO3_IO27		0x14 /* SODIMM 146 */
-			MX7D_PAD_LCD_DATA23__GPIO3_IO28		0x14 /* SODIMM 148 */
+			MX7D_PAD_LCD_DATA22__GPIO3_IO27		0x74 /* SODIMM 144 */
+			MX7D_PAD_LCD_DATA23__GPIO3_IO28		0x74 /* SODIMM 146 */
 		>;
 	};
 
@@ -396,6 +419,12 @@
 		>;
 	};
 
+	pinctrl_can_int: can-int-grp {
+		fsl,pins = <
+			MX7D_PAD_SD1_RESET_B__GPIO5_IO2		0X14 /* SODIMM 73 */
+		>;
+	};
+
 	pinctrl_enet1: enet1grp {
 		fsl,pins = <
 			MX7D_PAD_ENET1_CRS__GPIO7_IO14			0x14
@@ -434,12 +463,17 @@
 		>;
 	};
 
+	pinctrl_gpio_bl_on: gpio-bl-on {
+		fsl,pins = <
+			MX7D_PAD_SD1_WP__GPIO5_IO1		0x14 /* SODIMM 71 */
+		>;
+	};
+
 	pinctrl_gpmi_nand: gpmi-nand-grp {
 		fsl,pins = <
 			MX7D_PAD_SD3_CLK__NAND_CLE		0x71
 			MX7D_PAD_SD3_CMD__NAND_ALE		0x71
 			MX7D_PAD_SAI1_TX_BCLK__NAND_CE0_B	0x71
-			MX7D_PAD_SAI1_RX_DATA__NAND_CE1_B	0x71
 			MX7D_PAD_SAI1_TX_DATA__NAND_READY_B	0x74
 			MX7D_PAD_SD3_STROBE__NAND_RE_B		0x71
 			MX7D_PAD_SD3_RESET_B__NAND_WE_B		0x71
@@ -507,6 +541,7 @@
 	pinctrl_pwm1: pwm1-grp {
 		fsl,pins = <
 			MX7D_PAD_GPIO1_IO08__PWM1_OUT		0x79
+			MX7D_PAD_ECSPI2_MOSI__GPIO4_IO21	0x4
 		>;
 	};
 
@@ -525,6 +560,7 @@
 	pinctrl_pwm4: pwm4-grp {
 		fsl,pins = <
 			MX7D_PAD_GPIO1_IO11__PWM4_OUT		0x79
+			MX7D_PAD_ECSPI2_SCLK__GPIO4_IO20	0x4
 		>;
 	};
 
@@ -559,7 +595,7 @@
 		>;
 	};
 
-	pinctrl_usbotg2_reg: gpio-usbotg2-vbus {
+	pinctrl_usbh_reg: gpio-usbh-vbus {
 		fsl,pins = <
 			MX7D_PAD_UART3_CTS_B__GPIO4_IO7	0x14 /* SODIMM 129 USBH PEN */
 		>;
@@ -576,6 +612,54 @@
 		>;
 	};
 
+	pinctrl_usdhc3: usdhc3grp {
+		fsl,pins = <
+			MX7D_PAD_SD3_CMD__SD3_CMD		0x59
+			MX7D_PAD_SD3_CLK__SD3_CLK		0x19
+			MX7D_PAD_SD3_DATA0__SD3_DATA0		0x59
+			MX7D_PAD_SD3_DATA1__SD3_DATA1		0x59
+			MX7D_PAD_SD3_DATA2__SD3_DATA2		0x59
+			MX7D_PAD_SD3_DATA3__SD3_DATA3		0x59
+			MX7D_PAD_SD3_DATA4__SD3_DATA4		0x59
+			MX7D_PAD_SD3_DATA5__SD3_DATA5		0x59
+			MX7D_PAD_SD3_DATA6__SD3_DATA6		0x59
+			MX7D_PAD_SD3_DATA7__SD3_DATA7		0x59
+			MX7D_PAD_SD3_STROBE__SD3_STROBE         0x19
+		>;
+	};
+
+	pinctrl_usdhc3_100mhz: usdhc3grp_100mhz {
+		fsl,pins = <
+			MX7D_PAD_SD3_CMD__SD3_CMD		0x5a
+			MX7D_PAD_SD3_CLK__SD3_CLK		0x1a
+			MX7D_PAD_SD3_DATA0__SD3_DATA0		0x5a
+			MX7D_PAD_SD3_DATA1__SD3_DATA1		0x5a
+			MX7D_PAD_SD3_DATA2__SD3_DATA2		0x5a
+			MX7D_PAD_SD3_DATA3__SD3_DATA3		0x5a
+			MX7D_PAD_SD3_DATA4__SD3_DATA4		0x5a
+			MX7D_PAD_SD3_DATA5__SD3_DATA5		0x5a
+			MX7D_PAD_SD3_DATA6__SD3_DATA6		0x5a
+			MX7D_PAD_SD3_DATA7__SD3_DATA7		0x5a
+			MX7D_PAD_SD3_STROBE__SD3_STROBE         0x1a
+		>;
+	};
+
+	pinctrl_usdhc3_200mhz: usdhc3grp_200mhz {
+		fsl,pins = <
+			MX7D_PAD_SD3_CMD__SD3_CMD		0x5b
+			MX7D_PAD_SD3_CLK__SD3_CLK		0x1b
+			MX7D_PAD_SD3_DATA0__SD3_DATA0		0x5b
+			MX7D_PAD_SD3_DATA1__SD3_DATA1		0x5b
+			MX7D_PAD_SD3_DATA2__SD3_DATA2		0x5b
+			MX7D_PAD_SD3_DATA3__SD3_DATA3		0x5b
+			MX7D_PAD_SD3_DATA4__SD3_DATA4		0x5b
+			MX7D_PAD_SD3_DATA5__SD3_DATA5		0x5b
+			MX7D_PAD_SD3_DATA6__SD3_DATA6		0x5b
+			MX7D_PAD_SD3_DATA7__SD3_DATA7		0x5b
+			MX7D_PAD_SD3_STROBE__SD3_STROBE         0x1b
+		>;
+	};
+
 	pinctrl_sai1: sai1-grp {
 		fsl,pins = <
 			MX7D_PAD_ENET1_RX_CLK__SAI1_TX_BCLK     0x1f
diff --git a/arch/arm/boot/dts/imx7d-colibri-emmc-eval-v3.dts b/arch/arm/boot/dts/imx7d-colibri-emmc-eval-v3.dts
new file mode 100644
index 000000000000..8ee73c870b12
--- /dev/null
+++ b/arch/arm/boot/dts/imx7d-colibri-emmc-eval-v3.dts
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2017 Toradex AG
+ */
+
+/dts-v1/;
+#include "imx7d-colibri-emmc.dtsi"
+#include "imx7-colibri-eval-v3.dtsi"
+
+/ {
+	model = "Toradex Colibri iMX7D 1GB (eMMC) on Colibri Evaluation Board V3";
+	compatible = "toradex,colibri-imx7d-emmc-eval-v3",
+		     "toradex,colibri-imx7d-emmc", "fsl,imx7d";
+};
+
+&usbotg2 {
+	vbus-supply = <&reg_usbh_vbus>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx7d-colibri-emmc.dtsi b/arch/arm/boot/dts/imx7d-colibri-emmc.dtsi
new file mode 100644
index 000000000000..9b63b9c89e4b
--- /dev/null
+++ b/arch/arm/boot/dts/imx7d-colibri-emmc.dtsi
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2017 Toradex AG
+ */
+
+#include "imx7d.dtsi"
+#include "imx7-colibri.dtsi"
+
+/ {
+	memory {
+		reg = <0x80000000 0x40000000>;
+	};
+};
+
+&usbotg2 {
+	dr_mode = "host";
+};
+
+&usdhc3 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx7d-colibri-eval-v3.dts b/arch/arm/boot/dts/imx7d-colibri-eval-v3.dts
index a608a14d8c85..136e11ab4893 100644
--- a/arch/arm/boot/dts/imx7d-colibri-eval-v3.dts
+++ b/arch/arm/boot/dts/imx7d-colibri-eval-v3.dts
@@ -48,20 +48,9 @@
 	model = "Toradex Colibri iMX7D on Colibri Evaluation Board V3";
 	compatible = "toradex,colibri-imx7d-eval-v3", "toradex,colibri-imx7d",
 		     "fsl,imx7d";
-
-	reg_usb_otg2_vbus: regulator-usb-otg2-vbus {
-		compatible = "regulator-fixed";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_usbotg2_reg>;
-		regulator-name = "VCC_USB[1-4]";
-		regulator-min-microvolt = <5000000>;
-		regulator-max-microvolt = <5000000>;
-		gpio = <&gpio4 7 GPIO_ACTIVE_LOW>;
-		vin-supply = <&reg_5v0>;
-	};
 };
 
 &usbotg2 {
-	vbus-supply = <&reg_usb_otg2_vbus>;
+	vbus-supply = <&reg_usbh_vbus>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx7d-colibri.dtsi b/arch/arm/boot/dts/imx7d-colibri.dtsi
index 3c2cb502b388..6f2bb70c1fbd 100644
--- a/arch/arm/boot/dts/imx7d-colibri.dtsi
+++ b/arch/arm/boot/dts/imx7d-colibri.dtsi
@@ -49,6 +49,10 @@
 	};
 };
 
+&gpmi {
+	status = "okay";
+};
+
 &usbotg2 {
 	dr_mode = "host";
 };
diff --git a/arch/arm/boot/dts/imx7d-pico-pi.dts b/arch/arm/boot/dts/imx7d-pico-pi.dts
new file mode 100644
index 000000000000..ee02d931cf49
--- /dev/null
+++ b/arch/arm/boot/dts/imx7d-pico-pi.dts
@@ -0,0 +1,181 @@
+/*
+ * Copyright 2017 NXP
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include "imx7d-pico.dtsi"
+
+/ {
+	sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "imx7-sgtl5000";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,bitclock-master = <&dailink_master>;
+		simple-audio-card,frame-master = <&dailink_master>;
+		simple-audio-card,cpu {
+			sound-dai = <&sai1>;
+		};
+
+		dailink_master: simple-audio-card,codec {
+			sound-dai = <&codec>;
+			clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+		};
+	};
+};
+
+&fec1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_enet1>;
+	assigned-clocks = <&clks IMX7D_ENET1_TIME_ROOT_SRC>,
+			  <&clks IMX7D_ENET1_TIME_ROOT_CLK>;
+	assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>;
+	assigned-clock-rates = <0>, <100000000>;
+	phy-mode = "rgmii";
+	phy-handle = <&ethphy0>;
+	fsl,magic-packet;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy0: ethernet-phy@1 {
+			compatible = "ethernet-phy-ieee802.3-c22";
+			reg = <1>;
+			status = "okay";
+		};
+	};
+};
+
+&i2c1 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c1>;
+	status = "okay";
+
+	codec: sgtl5000@a {
+		#sound-dai-cells = <0>;
+		reg = <0x0a>;
+		compatible = "fsl,sgtl5000";
+		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+		VDDA-supply = <&reg_2p5v>;
+		VDDIO-supply = <&reg_vref_1v8>;
+	};
+};
+
+
+&sai1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_sai1>;
+	assigned-clocks = <&clks IMX7D_SAI1_ROOT_SRC>,
+			  <&clks IMX7D_SAI1_ROOT_CLK>;
+	assigned-clock-parents = <&clks IMX7D_PLL_AUDIO_POST_DIV>;
+	assigned-clock-rates = <0>, <24576000>;
+	status = "okay";
+};
+
+&uart5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart5>;
+	assigned-clocks = <&clks IMX7D_UART5_ROOT_SRC>;
+	assigned-clock-parents = <&clks IMX7D_PLL_SYS_MAIN_240M_CLK>;
+	status = "okay";
+};
+
+&usbotg1 {
+	vbus-supply = <&reg_usb_otg1_vbus>;
+	status = "okay";
+};
+
+&usbotg2 {
+	vbus-supply = <&reg_usb_otg2_vbus>;
+	dr_mode = "host";
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_enet1: enet1grp {
+		fsl,pins = <
+			MX7D_PAD_SD2_CD_B__ENET1_MDIO			0x3
+			MX7D_PAD_SD2_WP__ENET1_MDC			0x3
+			MX7D_PAD_ENET1_RGMII_TXC__ENET1_RGMII_TXC	0x1
+			MX7D_PAD_ENET1_RGMII_TD0__ENET1_RGMII_TD0	0x1
+			MX7D_PAD_ENET1_RGMII_TD1__ENET1_RGMII_TD1	0x1
+			MX7D_PAD_ENET1_RGMII_TD2__ENET1_RGMII_TD2	0x1
+			MX7D_PAD_ENET1_RGMII_TD3__ENET1_RGMII_TD3	0x1
+			MX7D_PAD_ENET1_RGMII_TX_CTL__ENET1_RGMII_TX_CTL	0x1
+			MX7D_PAD_ENET1_RGMII_RXC__ENET1_RGMII_RXC	0x1
+			MX7D_PAD_ENET1_RGMII_RD0__ENET1_RGMII_RD0	0x1
+			MX7D_PAD_ENET1_RGMII_RD1__ENET1_RGMII_RD1	0x1
+			MX7D_PAD_ENET1_RGMII_RD2__ENET1_RGMII_RD2	0x1
+			MX7D_PAD_ENET1_RGMII_RD3__ENET1_RGMII_RD3	0x1
+			MX7D_PAD_ENET1_RGMII_RX_CTL__ENET1_RGMII_RX_CTL	0x1
+		>;
+	};
+
+	pinctrl_i2c1: i2c1grp {
+		fsl,pins = <
+			MX7D_PAD_UART1_TX_DATA__I2C1_SDA	0x4000007f
+			MX7D_PAD_UART1_RX_DATA__I2C1_SCL	0x4000007f
+		>;
+	};
+
+	pinctrl_sai1: sai1grp {
+		fsl,pins = <
+			MX7D_PAD_ENET1_RX_CLK__SAI1_TX_BCLK	0x1f
+			MX7D_PAD_ENET1_CRS__SAI1_TX_SYNC	0x1f
+			MX7D_PAD_ENET1_COL__SAI1_TX_DATA0	0x30
+			MX7D_PAD_ENET1_TX_CLK__SAI1_RX_DATA0	0x1f
+		>;
+	};
+
+	pinctrl_uart5: uart5grp {
+		fsl,pins = <
+			MX7D_PAD_I2C4_SDA__UART5_DCE_TX		0x79
+			MX7D_PAD_I2C4_SCL__UART5_DCE_RX		0x79
+		>;
+	};
+
+	pinctrl_usbotg1_pwr: usbotg_pwr {
+		fsl,pins = <
+			MX7D_PAD_UART3_TX_DATA__GPIO4_IO5	0x14
+		>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx7d-pico.dts b/arch/arm/boot/dts/imx7d-pico.dtsi
index 508328b2a6bf..e307462a48ec 100644
--- a/arch/arm/boot/dts/imx7d-pico.dts
+++ b/arch/arm/boot/dts/imx7d-pico.dtsi
@@ -100,62 +100,6 @@
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
-
-	sound {
-		compatible = "simple-audio-card";
-		simple-audio-card,name = "imx7-sgtl5000";
-		simple-audio-card,format = "i2s";
-		simple-audio-card,bitclock-master = <&dailink_master>;
-		simple-audio-card,frame-master = <&dailink_master>;
-		simple-audio-card,cpu {
-			sound-dai = <&sai1>;
-		};
-
-		dailink_master: simple-audio-card,codec {
-			sound-dai = <&codec>;
-			clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
-		};
-	};
-};
-
-&fec1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_enet1>;
-	assigned-clocks = <&clks IMX7D_ENET1_TIME_ROOT_SRC>,
-			  <&clks IMX7D_ENET1_TIME_ROOT_CLK>;
-	assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>;
-	assigned-clock-rates = <0>, <100000000>;
-	phy-mode = "rgmii";
-	phy-handle = <&ethphy0>;
-	fsl,magic-packet;
-	status = "okay";
-
-	mdio {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		ethphy0: ethernet-phy@1 {
-			compatible = "ethernet-phy-ieee802.3-c22";
-			reg = <1>;
-			status = "okay";
-		};
-	};
-};
-
-&i2c1 {
-	clock-frequency = <100000>;
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_i2c1>;
-	status = "okay";
-
-	codec: sgtl5000@a {
-		#sound-dai-cells = <0>;
-		reg = <0x0a>;
-		compatible = "fsl,sgtl5000";
-		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
-		VDDA-supply = <&reg_2p5v>;
-		VDDIO-supply = <&reg_vref_1v8>;
-	};
 };
 
 &i2c4 {
@@ -253,35 +197,6 @@
 	};
 };
 
-&sai1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_sai1>;
-	assigned-clocks = <&clks IMX7D_SAI1_ROOT_SRC>,
-			  <&clks IMX7D_SAI1_ROOT_CLK>;
-	assigned-clock-parents = <&clks IMX7D_PLL_AUDIO_POST_DIV>;
-	assigned-clock-rates = <0>, <24576000>;
-	status = "okay";
-};
-
-&uart5 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_uart5>;
-	assigned-clocks = <&clks IMX7D_UART5_ROOT_SRC>;
-	assigned-clock-parents = <&clks IMX7D_PLL_SYS_MAIN_240M_CLK>;
-	status = "okay";
-};
-
-&usbotg1 {
-	vbus-supply = <&reg_usb_otg1_vbus>;
-	status = "okay";
-};
-
-&usbotg2 {
-	vbus-supply = <&reg_usb_otg2_vbus>;
-	dr_mode = "host";
-	status = "okay";
-};
-
 &usdhc2 { /* Wifi SDIO */
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
@@ -315,32 +230,6 @@
 };
 
 &iomuxc {
-	pinctrl_enet1: enet1grp {
-		fsl,pins = <
-			MX7D_PAD_SD2_CD_B__ENET1_MDIO			0x3
-			MX7D_PAD_SD2_WP__ENET1_MDC			0x3
-			MX7D_PAD_ENET1_RGMII_TXC__ENET1_RGMII_TXC	0x1
-			MX7D_PAD_ENET1_RGMII_TD0__ENET1_RGMII_TD0	0x1
-			MX7D_PAD_ENET1_RGMII_TD1__ENET1_RGMII_TD1	0x1
-			MX7D_PAD_ENET1_RGMII_TD2__ENET1_RGMII_TD2	0x1
-			MX7D_PAD_ENET1_RGMII_TD3__ENET1_RGMII_TD3	0x1
-			MX7D_PAD_ENET1_RGMII_TX_CTL__ENET1_RGMII_TX_CTL	0x1
-			MX7D_PAD_ENET1_RGMII_RXC__ENET1_RGMII_RXC	0x1
-			MX7D_PAD_ENET1_RGMII_RD0__ENET1_RGMII_RD0	0x1
-			MX7D_PAD_ENET1_RGMII_RD1__ENET1_RGMII_RD1	0x1
-			MX7D_PAD_ENET1_RGMII_RD2__ENET1_RGMII_RD2	0x1
-			MX7D_PAD_ENET1_RGMII_RD3__ENET1_RGMII_RD3	0x1
-			MX7D_PAD_ENET1_RGMII_RX_CTL__ENET1_RGMII_RX_CTL	0x1
-		>;
-	};
-
-	pinctrl_i2c1: i2c1grp {
-		fsl,pins = <
-			MX7D_PAD_UART1_TX_DATA__I2C1_SDA	0x4000007f
-			MX7D_PAD_UART1_RX_DATA__I2C1_SCL	0x4000007f
-		>;
-	};
-
 	pinctrl_i2c4: i2c4grp {
 		fsl,pins = <
 			MX7D_PAD_SAI1_RX_BCLK__I2C4_SDA		0x4000007f
@@ -354,28 +243,6 @@
 		>;
 	};
 
-	pinctrl_sai1: sai1grp {
-		fsl,pins = <
-			MX7D_PAD_ENET1_RX_CLK__SAI1_TX_BCLK	0x1f
-			MX7D_PAD_ENET1_CRS__SAI1_TX_SYNC	0x1f
-			MX7D_PAD_ENET1_COL__SAI1_TX_DATA0	0x30
-			MX7D_PAD_ENET1_TX_CLK__SAI1_RX_DATA0	0x1f
-		>;
-	};
-
-	pinctrl_uart5: uart5grp {
-		fsl,pins = <
-			MX7D_PAD_I2C4_SDA__UART5_DCE_TX		0x79
-			MX7D_PAD_I2C4_SCL__UART5_DCE_RX		0x79
-		>;
-	};
-
-	pinctrl_usbotg1_pwr: usbotg_pwr {
-		fsl,pins = <
-			MX7D_PAD_UART3_TX_DATA__GPIO4_IO5	0x14
-		>;
-	};
-
 	pinctrl_usdhc2: usdhc2grp {
 		fsl,pins = <
 			MX7D_PAD_SD2_CMD__SD2_CMD		0x59
diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi
index 4d308d17f040..200714e3feea 100644
--- a/arch/arm/boot/dts/imx7d.dtsi
+++ b/arch/arm/boot/dts/imx7d.dtsi
@@ -63,6 +63,13 @@
 		};
 	};
 
+	usbphynop2: usbphynop2 {
+		compatible = "usb-nop-xceiv";
+		clocks = <&clks IMX7D_USB_PHY2_CLK>;
+		clock-names = "main_clk";
+		#phy-cells = <0>;
+	};
+
 	soc {
 		etm@3007d000 {
 			compatible = "arm,coresight-etm3x", "arm,primecell";
@@ -105,18 +112,14 @@
 		reg = <0x30b20200 0x200>;
 	};
 
-	usbphynop2: usbphynop2 {
-		compatible = "usb-nop-xceiv";
-		clocks = <&clks IMX7D_USB_PHY2_CLK>;
-		clock-names = "main_clk";
-	};
-
 	fec2: ethernet@30bf0000 {
 		compatible = "fsl,imx7d-fec", "fsl,imx6sx-fec";
 		reg = <0x30bf0000 0x10000>;
-		interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
+		interrupt-names = "int0", "int1", "int2", "pps";
+		interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
 			<GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
-			<GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>;
+			<GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&clks IMX7D_ENET_AXI_ROOT_CLK>,
 			<&clks IMX7D_ENET_AXI_ROOT_CLK>,
 			<&clks IMX7D_ENET2_TIME_ROOT_CLK>,
@@ -129,7 +132,7 @@
 		status = "disabled";
 	};
 
-	pcie: pcie@0x33800000 {
+	pcie: pcie@33800000 {
 		compatible = "fsl,imx7d-pcie", "snps,dw-pcie";
 		reg = <0x33800000 0x4000>,
 		      <0x4ff00000 0x80000>;
@@ -137,6 +140,7 @@
 		#address-cells = <3>;
 		#size-cells = <2>;
 		device_type = "pci";
+		bus-range = <0x00 0xff>;
 		ranges = <0x81000000 0 0          0x4ff80000 0 0x00010000   /* downstream I/O */
 			  0x82000000 0 0x40000000 0x40000000 0 0x0ff00000>; /* non-prefetchable memory */
 		num-lanes = <1>;
diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi
index 82ad26e766eb..9aa2bb998552 100644
--- a/arch/arm/boot/dts/imx7s.dtsi
+++ b/arch/arm/boot/dts/imx7s.dtsi
@@ -116,6 +116,66 @@
 		clock-output-names = "osc";
 	};
 
+	usbphynop1: usbphynop1 {
+		compatible = "usb-nop-xceiv";
+		clocks = <&clks IMX7D_USB_PHY1_CLK>;
+		clock-names = "main_clk";
+		#phy-cells = <0>;
+	};
+
+	usbphynop3: usbphynop3 {
+		compatible = "usb-nop-xceiv";
+		clocks = <&clks IMX7D_USB_HSIC_ROOT_CLK>;
+		clock-names = "main_clk";
+		#phy-cells = <0>;
+	};
+
+
+	replicator {
+		/*
+		 * non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell"
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+				/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator_out_port0: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator_out_port1: endpoint {
+					remote-endpoint = <&etr_in_port>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&etf_out_port>;
+				};
+			};
+		};
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupt-parent = <&intc>;
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -260,43 +320,6 @@
 			};
 		};
 
-		replicator {
-			/*
-			 * non-configurable replicators don't show up on the
-			 * AMBA bus.  As such no need to add "arm,primecell"
-			 */
-			compatible = "arm,coresight-replicator";
-
-			ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				/* replicator output ports */
-				port@0 {
-					reg = <0>;
-					replicator_out_port0: endpoint {
-						remote-endpoint = <&tpiu_in_port>;
-					};
-				};
-
-				port@1 {
-					reg = <1>;
-					replicator_out_port1: endpoint {
-						remote-endpoint = <&etr_in_port>;
-					};
-				};
-
-				/* replicator input port */
-				port@2 {
-					reg = <0>;
-					replicator_in_port0: endpoint {
-						slave-mode;
-						remote-endpoint = <&etf_out_port>;
-					};
-				};
-			};
-		};
-
 		intc: interrupt-controller@31001000 {
 			compatible = "arm,cortex-a7-gic";
 			interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
@@ -309,15 +332,6 @@
 			      <0x31006000 0x2000>;
 		};
 
-		timer {
-			compatible = "arm,armv7-timer";
-			interrupt-parent = <&intc>;
-			interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
-		};
-
 		aips1: aips-bus@30000000 {
 			compatible = "fsl,aips-bus", "simple-bus";
 			#address-cells = <1>;
@@ -508,8 +522,11 @@
 				reg = <0x30360000 0x10000>;
 				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
 					<GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <1>;
+				#size-cells = <0>;
 
-				reg_1p0d: regulator-vdd1p0d {
+				reg_1p0d: regulator-vdd1p0d@30360210 {
+					reg = <0x30360210>;
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd1p0d";
 					regulator-min-microvolt = <800000>;
@@ -583,9 +600,9 @@
 					#address-cells = <1>;
 					#size-cells = <0>;
 
-					pgc_pcie_phy: pgc-power-domain@IMX7_POWER_DOMAIN_PCIE_PHY {
+					pgc_pcie_phy: pgc-power-domain@1 {
 						#power-domain-cells = <0>;
-						reg = <IMX7_POWER_DOMAIN_PCIE_PHY>;
+						reg = <1>;
 						power-supply = <&reg_1p0d>;
 					};
 				};
@@ -945,18 +962,6 @@
 				reg = <0x30b30200 0x200>;
 			};
 
-			usbphynop1: usbphynop1 {
-				compatible = "usb-nop-xceiv";
-				clocks = <&clks IMX7D_USB_PHY1_CLK>;
-				clock-names = "main_clk";
-			};
-
-			usbphynop3: usbphynop3 {
-				compatible = "usb-nop-xceiv";
-				clocks = <&clks IMX7D_USB_HSIC_ROOT_CLK>;
-				clock-names = "main_clk";
-			};
-
 			usdhc1: usdhc@30b40000 {
 				compatible = "fsl,imx7d-usdhc", "fsl,imx6sl-usdhc";
 				reg = <0x30b40000 0x10000>;
@@ -1007,9 +1012,11 @@
 			fec1: ethernet@30be0000 {
 				compatible = "fsl,imx7d-fec", "fsl,imx6sx-fec";
 				reg = <0x30be0000 0x10000>;
-				interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
+				interrupt-names = "int0", "int1", "int2", "pps";
+				interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
 					<GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>,
-					<GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
+					<GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX7D_ENET_AXI_ROOT_CLK>,
 					<&clks IMX7D_ENET_AXI_ROOT_CLK>,
 					<&clks IMX7D_ENET1_TIME_ROOT_CLK>,
diff --git a/arch/arm/boot/dts/iwg20d-q7-common.dtsi b/arch/arm/boot/dts/iwg20d-q7-common.dtsi
index efd8af9242d1..66954aaf2c47 100644
--- a/arch/arm/boot/dts/iwg20d-q7-common.dtsi
+++ b/arch/arm/boot/dts/iwg20d-q7-common.dtsi
@@ -8,9 +8,33 @@
  * kind, whether express or implied.
  */
 
+/*
+ * SSI-SGTL5000
+ *
+ * This command is required when Playback/Capture
+ *
+ *      amixer set "DVC Out" 100%
+ *      amixer set "DVC In" 100%
+ *
+ * You can use Mute
+ *
+ *      amixer set "DVC Out Mute" on
+ *      amixer set "DVC In Mute" on
+ *
+ * You can use Volume Ramp
+ *
+ *      amixer set "DVC Out Ramp Up Rate"   "0.125 dB/64 steps"
+ *      amixer set "DVC Out Ramp Down Rate" "0.125 dB/512 steps"
+ *      amixer set "DVC Out Ramp" on
+ *      aplay xxx.wav &
+ *      amixer set "DVC Out"  80%  // Volume Down
+ *      amixer set "DVC Out" 100%  // Volume Up
+ */
+
 / {
 	aliases {
 		serial0 = &scif0;
+		serial3 = &scifb1;
 		ethernet0 = &avb;
 	};
 
@@ -19,6 +43,36 @@
 		stdout-path = "serial0:115200n8";
 	};
 
+	audio_clock: audio_clock {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <26000000>;
+	};
+
+	reg_1p5v: 1p5v {
+		compatible = "regulator-fixed";
+		regulator-name = "1P5V";
+		regulator-min-microvolt = <1500000>;
+		regulator-max-microvolt = <1500000>;
+		regulator-always-on;
+	};
+
+	rsnd_sgtl5000: sound {
+		compatible = "simple-audio-card";
+
+		simple-audio-card,format = "i2s";
+		simple-audio-card,bitclock-master = <&sndcodec>;
+		simple-audio-card,frame-master = <&sndcodec>;
+
+		sndcpu: simple-audio-card,cpu {
+			sound-dai = <&rcar_sound>;
+		};
+
+		sndcodec: simple-audio-card,codec {
+			sound-dai = <&sgtl5000>;
+		};
+	};
+
 	vcc_sdhi1: regulator-vcc-sdhi1 {
 		compatible = "regulator-fixed";
 
@@ -58,6 +112,13 @@
 	};
 };
 
+&can0 {
+	pinctrl-0 = <&can0_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
 &hsusb {
 	status = "okay";
 	pinctrl-0 = <&usb0_pins>;
@@ -75,6 +136,16 @@
 		compatible = "ti,bq32000";
 		reg = <0x68>;
 	};
+
+	sgtl5000: codec@a {
+		compatible = "fsl,sgtl5000";
+		#sound-dai-cells = <0>;
+		reg = <0x0a>;
+		clocks = <&audio_clock>;
+		VDDA-supply = <&reg_3p3v>;
+		VDDIO-supply = <&reg_3p3v>;
+		VDDD-supply = <&reg_1p5v>;
+	};
 };
 
 &pci0 {
@@ -88,7 +159,20 @@
 	pinctrl-names = "default";
 };
 
+&pcie_bus_clk {
+	clock-frequency = <100000000>;
+};
+
+&pciec {
+	status = "okay";
+};
+
 &pfc {
+	can0_pins: can0 {
+		groups = "can0_data_d";
+		function = "can0";
+	};
+
 	avb_pins: avb {
 		groups = "avb_mdio", "avb_gmii";
 		function = "avb";
@@ -104,6 +188,11 @@
 		function = "scif0";
 	};
 
+	scifb1_pins: scifb1 {
+		groups = "scifb1_data_d", "scifb1_ctrl";
+		function = "scifb1";
+	};
+
 	sdhi1_pins: sd1 {
 		groups = "sdhi1_data4", "sdhi1_ctrl";
 		function = "sdhi1";
@@ -116,6 +205,11 @@
 		power-source = <1800>;
 	};
 
+	sound_pins: sound {
+		groups = "ssi0129_ctrl", "ssi0_data", "ssi1_data";
+		function = "ssi";
+	};
+
 	usb0_pins: usb0 {
 		groups = "usb0";
 		function = "usb0";
@@ -127,6 +221,22 @@
 	};
 };
 
+&rcar_sound {
+	pinctrl-0 = <&sound_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	/* Single DAI */
+	#sound-dai-cells = <0>;
+
+	rcar_sound,dai {
+		dai0 {
+			playback = <&ssi1 &src3 &dvc1>;
+			capture = <&ssi0 &src2 &dvc0>;
+		};
+	};
+};
+
 &scif0 {
 	pinctrl-0 = <&scif0_pins>;
 	pinctrl-names = "default";
@@ -134,6 +244,14 @@
 	status = "okay";
 };
 
+&scifb1 {
+	pinctrl-0 = <&scifb1_pins>;
+	pinctrl-names = "default";
+
+	uart-has-rtscts;
+	status = "okay";
+};
+
 &sdhi1 {
 	pinctrl-0 = <&sdhi1_pins>;
 	pinctrl-1 = <&sdhi1_pins_uhs>;
@@ -147,6 +265,10 @@
 	status = "okay";
 };
 
+&ssi1 {
+	shared-pin;
+};
+
 &usbphy {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi b/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi
index 31fab5f183a9..476273b3f994 100644
--- a/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi
+++ b/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi
@@ -13,6 +13,44 @@
 		serial1 = &scif1;
 		serial4 = &hscif1;
 	};
+
+	cec_clock: cec-clock {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <12000000>;
+	};
+
+	hdmi-out {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con_out: endpoint {
+				remote-endpoint = <&adv7511_out>;
+			};
+		};
+	};
+};
+
+&can1 {
+	pinctrl-0 = <&can1_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&du {
+	pinctrl-0 = <&du_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	ports {
+		port@0 {
+			endpoint {
+				remote-endpoint = <&adv7511_in>;
+			};
+		};
+	};
 };
 
 &hscif1 {
@@ -23,7 +61,56 @@
 	status = "okay";
 };
 
+&i2c5 {
+	status = "okay";
+	clock-frequency = <400000>;
+
+	hdmi@39 {
+		compatible = "adi,adv7511w";
+		reg = <0x39>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <13 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&cec_clock>;
+		clock-names = "cec";
+
+		adi,input-depth = <8>;
+		adi,input-colorspace = "rgb";
+		adi,input-clock = "1x";
+		adi,input-style = <1>;
+		adi,input-justification = "evenly";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				adv7511_in: endpoint {
+					remote-endpoint = <&du_out_rgb>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				adv7511_out: endpoint {
+					remote-endpoint = <&hdmi_con_out>;
+				};
+			};
+		};
+	};
+};
+
 &pfc {
+	can1_pins: can1 {
+		groups = "can1_data_d";
+		function = "can1";
+	};
+
+	du_pins: du {
+		groups = "du_rgb888", "du_sync", "du_oddf", "du_clk_out_0";
+		function = "du";
+	};
+
 	hscif1_pins: hscif1 {
 		groups = "hscif1_data_c", "hscif1_ctrl_c";
 		function = "hscif1";
diff --git a/arch/arm/boot/dts/keystone-clocks.dtsi b/arch/arm/boot/dts/keystone-clocks.dtsi
index 0c334b25781e..457515b0736a 100644
--- a/arch/arm/boot/dts/keystone-clocks.dtsi
+++ b/arch/arm/boot/dts/keystone-clocks.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device Tree Source for Keystone 2 clock tree
  *
- * Copyright (C) 2013 Texas Instruments, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 clocks {
@@ -51,7 +48,7 @@ clocks {
 		clock-output-names = "gemtraceclk";
 	};
 
-	chipstmxptclk: chipstmxptclk {
+	chipstmxptclk: chipstmxptclk@2310164 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,pll-divider-clock";
 		clocks = <&mainmuxclk>;
@@ -160,7 +157,7 @@ clocks {
 		clock-output-names = "chipclk1rstiso112";
 	};
 
-	clkmodrst0: clkmodrst0 {
+	clkmodrst0: clkmodrst0@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk16>;
@@ -171,7 +168,7 @@ clocks {
 	};
 
 
-	clkusb: clkusb {
+	clkusb: clkusb@2350008 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk16>;
@@ -181,7 +178,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkaemifspi: clkaemifspi {
+	clkaemifspi: clkaemifspi@235000c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk16>;
@@ -192,7 +189,7 @@ clocks {
 	};
 
 
-	clkdebugsstrc: clkdebugsstrc {
+	clkdebugsstrc: clkdebugsstrc@2350014 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -202,7 +199,7 @@ clocks {
 		domain-id = <1>;
 	};
 
-	clktetbtrc: clktetbtrc {
+	clktetbtrc: clktetbtrc@2350018 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -212,7 +209,7 @@ clocks {
 		domain-id = <1>;
 	};
 
-	clkpa: clkpa {
+	clkpa: clkpa@235001c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&paclk13>;
@@ -222,7 +219,7 @@ clocks {
 		domain-id = <2>;
 	};
 
-	clkcpgmac: clkcpgmac {
+	clkcpgmac: clkcpgmac@2350020 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkpa>;
@@ -232,7 +229,7 @@ clocks {
 		domain-id = <2>;
 	};
 
-	clksa: clksa {
+	clksa: clksa@2350024 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkpa>;
@@ -242,7 +239,7 @@ clocks {
 		domain-id = <2>;
 	};
 
-	clkpcie: clkpcie {
+	clkpcie: clkpcie@2350028 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk12>;
@@ -252,7 +249,7 @@ clocks {
 		domain-id = <3>;
 	};
 
-	clksr: clksr {
+	clksr: clksr@2350034 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1rstiso112>;
@@ -262,7 +259,7 @@ clocks {
 		domain-id = <6>;
 	};
 
-	clkgem0: clkgem0 {
+	clkgem0: clkgem0@235003c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1>;
@@ -272,7 +269,7 @@ clocks {
 		domain-id = <8>;
 	};
 
-	clkddr30: clkddr30 {
+	clkddr30: clkddr30@235005c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk12>;
@@ -282,7 +279,7 @@ clocks {
 		domain-id = <16>;
 	};
 
-	clkwdtimer0: clkwdtimer0 {
+	clkwdtimer0: clkwdtimer0@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
@@ -292,7 +289,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkwdtimer1: clkwdtimer1 {
+	clkwdtimer1: clkwdtimer1@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
@@ -302,7 +299,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkwdtimer2: clkwdtimer2 {
+	clkwdtimer2: clkwdtimer2@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
@@ -312,7 +309,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkwdtimer3: clkwdtimer3 {
+	clkwdtimer3: clkwdtimer3@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
@@ -322,7 +319,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clktimer15: clktimer15 {
+	clktimer15: clktimer15@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
@@ -332,7 +329,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkuart0: clkuart0 {
+	clkuart0: clkuart0@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
@@ -342,7 +339,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkuart1: clkuart1 {
+	clkuart1: clkuart1@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
@@ -352,7 +349,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkaemif: clkaemif {
+	clkaemif: clkaemif@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkaemifspi>;
@@ -362,7 +359,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkusim: clkusim {
+	clkusim: clkusim@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
@@ -372,7 +369,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clki2c: clki2c {
+	clki2c: clki2c@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
@@ -382,7 +379,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkspi: clkspi {
+	clkspi: clkspi@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkaemifspi>;
@@ -392,7 +389,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkgpio: clkgpio {
+	clkgpio: clkgpio@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
@@ -402,7 +399,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkkeymgr: clkkeymgr {
+	clkkeymgr: clkkeymgr@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
diff --git a/arch/arm/boot/dts/keystone-k2e-clocks.dtsi b/arch/arm/boot/dts/keystone-k2e-clocks.dtsi
index d56d68fe7ffc..5e0e7d232161 100644
--- a/arch/arm/boot/dts/keystone-k2e-clocks.dtsi
+++ b/arch/arm/boot/dts/keystone-k2e-clocks.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright 2014 Texas Instruments, Inc.
- *
  * Keystone 2 Edison SoC specific device tree
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2014-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 clocks {
@@ -35,7 +32,7 @@ clocks {
 		reg-names = "control";
 	};
 
-	clkusb1: clkusb1 {
+	clkusb1: clkusb1@2350004 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk16>;
@@ -45,7 +42,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkhyperlink0: clkhyperlink0 {
+	clkhyperlink0: clkhyperlink02350030 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk12>;
@@ -55,7 +52,7 @@ clocks {
 		domain-id = <5>;
 	};
 
-	clkpcie1: clkpcie1 {
+	clkpcie1: clkpcie1@235006c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk12>;
@@ -65,7 +62,7 @@ clocks {
 		domain-id = <18>;
 	};
 
-	clkxge: clkxge {
+	clkxge: clkxge@23500c8 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
diff --git a/arch/arm/boot/dts/keystone-k2e-evm.dts b/arch/arm/boot/dts/keystone-k2e-evm.dts
index f1f32c54e72f..66fec5f5d081 100644
--- a/arch/arm/boot/dts/keystone-k2e-evm.dts
+++ b/arch/arm/boot/dts/keystone-k2e-evm.dts
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright 2013-2014 Texas Instruments, Inc.
- *
  * Keystone 2 Edison EVM device tree
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 /dts-v1/;
 
@@ -28,8 +25,9 @@
 			status = "okay";
 		};
 	};
+};
 
-	soc {
+&soc0 {
 
 		clocks {
 			refclksys: refclksys {
@@ -53,7 +51,6 @@
 				clock-output-names = "refclk-ddr3a";
 			};
 		};
-	};
 };
 
 &usb_phy {
@@ -82,7 +79,7 @@
 
 &i2c0 {
 	dtt@50 {
-		compatible = "at,24c1024";
+		compatible = "atmel,24c1024";
 		reg = <0x50>;
 	};
 };
diff --git a/arch/arm/boot/dts/keystone-k2e-netcp.dtsi b/arch/arm/boot/dts/keystone-k2e-netcp.dtsi
index ba828cb59587..a17311c602aa 100644
--- a/arch/arm/boot/dts/keystone-k2e-netcp.dtsi
+++ b/arch/arm/boot/dts/keystone-k2e-netcp.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device Tree Source for Keystone 2 Edison Netcp driver
  *
- * Copyright 2015 Texas Instruments, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2015-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 qmss: qmss@2a40000 {
diff --git a/arch/arm/boot/dts/keystone-k2e.dtsi b/arch/arm/boot/dts/keystone-k2e.dtsi
index 6b796b52ff4f..0bcd3f8a9c45 100644
--- a/arch/arm/boot/dts/keystone-k2e.dtsi
+++ b/arch/arm/boot/dts/keystone-k2e.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright 2013-2014 Texas Instruments, Inc.
- *
  * Keystone 2 Edison soc device tree
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 #include <dt-bindings/reset/ti-syscon.h>
@@ -48,8 +45,9 @@
 	aliases {
 		rproc0 = &dsp0;
 	};
+};
 
-	soc {
+&soc0 {
 		/include/ "keystone-k2e-clocks.dtsi"
 
 		usb: usb@2680000 {
@@ -194,5 +192,4 @@
 			bus_freq	= <2500000>;
 		};
 		/include/ "keystone-k2e-netcp.dtsi"
-	};
 };
diff --git a/arch/arm/boot/dts/keystone-k2g-evm.dts b/arch/arm/boot/dts/keystone-k2g-evm.dts
index 656af194a518..6a4657799b99 100644
--- a/arch/arm/boot/dts/keystone-k2g-evm.dts
+++ b/arch/arm/boot/dts/keystone-k2g-evm.dts
@@ -1,16 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device Tree Source for K2G EVM
  *
- * Copyright (C) 2016 Texas Instruments Incorporated - http://www.ti.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2016-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 /dts-v1/;
 
@@ -45,22 +37,6 @@
 		regulator-max-microvolt = <3300000>;
 		regulator-always-on;
 	};
-
-	ecap0_pins: ecap0_pins {
-		pinctrl-single,pins = <
-			K2G_CORE_IOPAD(0x1374) (BUFFER_CLASS_B | MUX_MODE4)	/* pr1_mdio_data.ecap0_in_apwm0_out */
-		>;
-	};
-
-	spi1_pins: pinmux_spi1_pins {
-		pinctrl-single,pins = <
-			K2G_CORE_IOPAD(0x11a4) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0)	/* spi1_scs0.spi1_scs0 */
-			K2G_CORE_IOPAD(0x11ac) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0)	/* spi1_clk.spi1_clk */
-			K2G_CORE_IOPAD(0x11b0) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0)	/* spi1_miso.spi1_miso */
-			K2G_CORE_IOPAD(0x11b4) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0)	/* spi1_mosi.spi1_mosi */
-		>;
-	};
-
 };
 
 &k2g_pinctrl {
@@ -105,6 +81,39 @@
 		>;
 	};
 
+	ecap0_pins: ecap0_pins {
+		pinctrl-single,pins = <
+			K2G_CORE_IOPAD(0x1374) (BUFFER_CLASS_B | MUX_MODE4)	/* pr1_mdio_data.ecap0_in_apwm0_out */
+		>;
+	};
+
+	spi1_pins: pinmux_spi1_pins {
+		pinctrl-single,pins = <
+			K2G_CORE_IOPAD(0x11a4) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0)	/* spi1_scs0.spi1_scs0 */
+			K2G_CORE_IOPAD(0x11ac) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0)	/* spi1_clk.spi1_clk */
+			K2G_CORE_IOPAD(0x11b0) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0)	/* spi1_miso.spi1_miso */
+			K2G_CORE_IOPAD(0x11b4) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0)	/* spi1_mosi.spi1_mosi */
+		>;
+	};
+
+	qspi_pins: pinmux_qspi_pins {
+		pinctrl-single,pins = <
+			K2G_CORE_IOPAD(0x1204) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_clk.qspi_clk */
+			K2G_CORE_IOPAD(0x1208) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_rclk.qspi_rclk */
+			K2G_CORE_IOPAD(0x120c) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_d0.qspi_d0 */
+			K2G_CORE_IOPAD(0x1210) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_d1.qspi_d1 */
+			K2G_CORE_IOPAD(0x1214) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_d2.qspi_d2 */
+			K2G_CORE_IOPAD(0x1218) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_d3.qspi_d3 */
+			K2G_CORE_IOPAD(0x121c) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_csn0.qspi_csn0 */
+		>;
+	};
+
+	uart2_pins: pinmux_uart2_pins {
+		pinctrl-single,pins = <
+			K2G_CORE_IOPAD(0x11ec) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0)      /* uart2_rxd.uart2_rxd */
+			K2G_CORE_IOPAD(0x11f0) (BUFFER_CLASS_B | PIN_PULLDOWN | MUX_MODE0)      /* uart2_txd.uart2_txd */
+		>;
+	};
 };
 
 &uart0 {
@@ -129,6 +138,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc1_pins>;
 	vmmc-supply = <&vcc3v3_dcin_reg>; /* VCC3V3_EMMC is connected to VCC3V3_DCIN */
+	ti,non-removable;
 	status = "okay";
 };
 
@@ -205,3 +215,56 @@
 		};
 	};
 };
+
+&qspi {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&qspi_pins>;
+	cdns,rclk-en;
+
+	flash0: m25p80@0 {
+		compatible = "s25fl512s", "jedec,spi-nor";
+		reg = <0>;
+		spi-tx-bus-width = <1>;
+		spi-rx-bus-width = <4>;
+		spi-max-frequency = <96000000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		cdns,read-delay = <5>;
+		cdns,tshsl-ns = <500>;
+		cdns,tsd2d-ns = <500>;
+		cdns,tchsh-ns = <119>;
+		cdns,tslch-ns = <119>;
+
+		partition@0 {
+			label = "QSPI.u-boot-spl-os";
+			reg = <0x00000000 0x00100000>;
+		};
+		partition@1 {
+			label = "QSPI.u-boot-env";
+			reg = <0x00100000 0x00040000>;
+		};
+		partition@2 {
+			label = "QSPI.skern";
+			reg = <0x00140000 0x0040000>;
+		};
+		partition@3 {
+			label = "QSPI.pmmc-firmware";
+			reg = <0x00180000 0x0040000>;
+		};
+		partition@4 {
+			label = "QSPI.kernel";
+			reg = <0x001C0000 0x0800000>;
+		};
+		partition@5 {
+			label = "QSPI.file-system";
+			reg = <0x009C0000 0x3640000>;
+		};
+	};
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart2_pins>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/keystone-k2g-ice.dts b/arch/arm/boot/dts/keystone-k2g-ice.dts
index 78692745e0af..d820ed2474bb 100644
--- a/arch/arm/boot/dts/keystone-k2g-ice.dts
+++ b/arch/arm/boot/dts/keystone-k2g-ice.dts
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device Tree Source for K2G Industrial Communication Engine EVM
  *
  * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/
- *
- * SPDX-License-Identifier: GPL-2.0
  */
 /dts-v1/;
 
@@ -30,6 +29,191 @@
 			status = "okay";
 		};
 	};
+
+	vmain: fixedregulator-vmain {
+		compatible = "regulator-fixed";
+		regulator-name = "vmain_fixed";
+		regulator-min-microvolt = <24000000>;
+		regulator-max-microvolt = <24000000>;
+		regulator-always-on;
+	};
+
+	v5_0: fixedregulator-v5_0 {
+		/* TPS54531 */
+		compatible = "regulator-fixed";
+		regulator-name = "v5_0_fixed";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vmain>;
+		regulator-always-on;
+	};
+
+	vdd_3v3: fixedregulator-vdd_3v3 {
+		/* TLV62084 */
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_3v3_fixed";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&v5_0>;
+		regulator-always-on;
+	};
+
+	vdd_1v8: fixedregulator-vdd_1v8 {
+		/* TLV62084 */
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_1v8_fixed";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&v5_0>;
+		regulator-always-on;
+	};
+
+	vdds_ddr: fixedregulator-vdds_ddr {
+		/* TLV62080 */
+		compatible = "regulator-fixed";
+		regulator-name = "vdds_ddr_fixed";
+		regulator-min-microvolt = <1350000>;
+		regulator-max-microvolt = <1350000>;
+		vin-supply = <&v5_0>;
+		regulator-always-on;
+	};
+
+	vref_ddr: fixedregulator-vref_ddr {
+		/* LP2996A */
+		compatible = "regulator-fixed";
+		regulator-name = "vref_ddr_fixed";
+		regulator-min-microvolt = <675000>;
+		regulator-max-microvolt = <675000>;
+		vin-supply = <&vdd_3v3>;
+		regulator-always-on;
+	};
+
+	vtt_ddr: fixedregulator-vtt_ddr {
+		/* LP2996A */
+		compatible = "regulator-fixed";
+		regulator-name = "vtt_ddr_fixed";
+		regulator-min-microvolt = <675000>;
+		regulator-max-microvolt = <675000>;
+		vin-supply = <&vdd_3v3>;
+		regulator-always-on;
+	};
+
+	vdd_0v9: fixedregulator-vdd_0v9 {
+		/* TPS62180 */
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_0v9_fixed";
+		regulator-min-microvolt = <900000>;
+		regulator-max-microvolt = <900000>;
+		vin-supply = <&v5_0>;
+		regulator-always-on;
+	};
+
+	vddb: fixedregulator-vddb {
+		/* TPS22945 */
+		compatible = "regulator-fixed";
+		regulator-name = "vddb_fixed";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+
+		gpio = <&gpio1 53 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	gpio-decoder {
+		compatible = "gpio-decoder";
+		gpios = <&pca9536 3 GPIO_ACTIVE_HIGH>,
+			<&pca9536 2 GPIO_ACTIVE_HIGH>,
+			<&pca9536 1 GPIO_ACTIVE_HIGH>,
+			<&pca9536 0 GPIO_ACTIVE_HIGH>;
+		linux,axis = <0>; /* ABS_X */
+		decoder-max-value = <9>;
+	};
+
+	leds1 {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&user_leds>;
+
+		led0 {
+			label = "status0:red:cpu0";
+			gpios = <&gpio0 11 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+			linux,default-trigger = "cpu0";
+		};
+
+		led1 {
+			label = "status0:green:usr";
+			gpios = <&gpio0 12 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led2 {
+			label = "status0:yellow:usr";
+			gpios = <&gpio0 13 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led3 {
+			label = "status1:red:mmc0";
+			gpios = <&gpio0 14 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+			linux,default-trigger = "mmc0";
+		};
+
+		led4 {
+			label = "status1:green:usr";
+			gpios = <&gpio0 15 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led5 {
+			label = "status1:yellow:usr";
+			gpios = <&gpio0 16 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led6 {
+			label = "status2:red:usr";
+			gpios = <&gpio0 44 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led7 {
+			label = "status2:green:usr";
+			gpios = <&gpio0 43 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led8 {
+			label = "status2:yellow:usr";
+			gpios = <&gpio0 42 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led9 {
+			label = "status3:red:usr";
+			gpios = <&gpio0 41 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led10 {
+			label = "status3:green:usr";
+			gpios = <&gpio0 101 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led11 {
+			label = "status3:yellow:usr";
+			gpios = <&gpio0 102 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led12 {
+			label = "status4:green:heartbeat";
+			gpios = <&gpio0 19 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
 };
 
 &k2g_pinctrl {
@@ -39,6 +223,64 @@
 			K2G_CORE_IOPAD(0x11d0) (BUFFER_CLASS_B | PIN_PULLDOWN | MUX_MODE0)	/* uart0_txd.uart0_txd */
 		>;
 	};
+
+	qspi_pins: pinmux_qspi_pins {
+		pinctrl-single,pins = <
+			K2G_CORE_IOPAD(0x1204) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_clk.qspi_clk */
+			K2G_CORE_IOPAD(0x1208) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_rclk.qspi_rclk */
+			K2G_CORE_IOPAD(0x120c) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_d0.qspi_d0 */
+			K2G_CORE_IOPAD(0x1210) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_d1.qspi_d1 */
+			K2G_CORE_IOPAD(0x1214) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_d2.qspi_d2 */
+			K2G_CORE_IOPAD(0x1218) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_d3.qspi_d3 */
+			K2G_CORE_IOPAD(0x121c) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* qspi_csn0.qspi_csn0 */
+		>;
+	};
+
+	mmc1_pins: pinmux_mmc1_pins {
+		pinctrl-single,pins = <
+			K2G_CORE_IOPAD(0x10FC) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* mmc1_dat3.mmc1_dat3 */
+			K2G_CORE_IOPAD(0x1100) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* mmc1_dat2.mmc1_dat2 */
+			K2G_CORE_IOPAD(0x1104) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* mmc1_dat1.mmc1_dat1 */
+			K2G_CORE_IOPAD(0x1108) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* mmc1_dat0.mmc1_dat0 */
+			K2G_CORE_IOPAD(0x110C) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* mmc1_clk.mmc1_clk */
+			K2G_CORE_IOPAD(0x1110) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* mmc1_cmd.mmc1_cmd */
+			K2G_CORE_IOPAD(0x1114) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* mmc1_sdcd.gpio0_69 */
+			K2G_CORE_IOPAD(0x1118) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* mmc1_sdwp.mmc1_sdwp */
+			K2G_CORE_IOPAD(0x111C) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* mmc1_pow.mmc1_pow */
+		>;
+	};
+
+	i2c0_pins: pinmux_i2c0_pins {
+		pinctrl-single,pins = <
+			K2G_CORE_IOPAD(0x137c) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* i2c0_scl.i2c0_scl */
+			K2G_CORE_IOPAD(0x1380) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* i2c0_sda.i2c0_sda */
+		>;
+	};
+
+	i2c1_pins: pinmux_i2c1_pins {
+		pinctrl-single,pins = <
+			K2G_CORE_IOPAD(0x1384) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* i2c1_scl.i2c1_scl */
+			K2G_CORE_IOPAD(0x1388) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE0)	/* i2c1_sda.i2c1_sda */
+		>;
+	};
+
+	user_leds: pinmux_user_leds {
+		pinctrl-single,pins = <
+			K2G_CORE_IOPAD(0x102c) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* gpmc_ad11.gpio0_11 */
+			K2G_CORE_IOPAD(0x1030) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* gpmc_ad12.gpio0_12 */
+			K2G_CORE_IOPAD(0x1034) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* gpmc_ad13.gpio0_13 */
+			K2G_CORE_IOPAD(0x1038) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* gpmc_ad14.gpio0_14 */
+			K2G_CORE_IOPAD(0x103c) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* gpmc_ad15.gpio0_15 */
+			K2G_CORE_IOPAD(0x1040) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* gpmc_clk.gpio0_16 */
+			K2G_CORE_IOPAD(0x104c) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* gpmc_wen.gpio0_19 */
+			K2G_CORE_IOPAD(0x10b0) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* dss_data9.gpio0_44 */
+			K2G_CORE_IOPAD(0x10ac) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* dss_data10.gpio0_43 */
+			K2G_CORE_IOPAD(0x10a8) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* dss_data11.gpio0_42 */
+			K2G_CORE_IOPAD(0x10a4) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* dss_data12.gpio0_41 */
+			K2G_CORE_IOPAD(0x11b8) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* spi2_scsn0.gpio0_101 */
+			K2G_CORE_IOPAD(0x11bc) (BUFFER_CLASS_B | PIN_PULLUP | MUX_MODE3)	/* spi2_scsn1.gpio0_102 */
+		>;
+	};
 };
 
 &uart0 {
@@ -51,3 +293,96 @@
 	memory-region = <&dsp_common_memory>;
 	status = "okay";
 };
+
+&qspi {
+	pinctrl-names = "default";
+	pinctrl-0 = <&qspi_pins>;
+	cdns,rclk-en;
+	status = "okay";
+
+	flash0: m25p80@0 {
+		compatible = "s25fl256s1", "jedec,spi-nor";
+		reg = <0>;
+		spi-tx-bus-width = <1>;
+		spi-rx-bus-width = <4>;
+		spi-max-frequency = <96000000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		cdns,read-delay = <5>;
+		cdns,tshsl-ns = <500>;
+		cdns,tsd2d-ns = <500>;
+		cdns,tchsh-ns = <119>;
+		cdns,tslch-ns = <119>;
+
+		partition@0 {
+			label = "QSPI.u-boot";
+			reg = <0x00000000 0x00100000>;
+		};
+		partition@1 {
+			label = "QSPI.u-boot-env";
+			reg = <0x00100000 0x00040000>;
+		};
+		partition@2 {
+			label = "QSPI.skern";
+			reg = <0x00140000 0x0040000>;
+		};
+		partition@3 {
+			label = "QSPI.pmmc-firmware";
+			reg = <0x00180000 0x0040000>;
+		};
+		partition@4 {
+			label = "QSPI.kernel";
+			reg = <0x001c0000 0x0800000>;
+		};
+		partition@5 {
+			label = "QSPI.u-boot-spl-os";
+			reg = <0x009c0000 0x0040000>;
+		};
+		partition@6 {
+			label = "QSPI.file-system";
+			reg = <0x00a00000 0x1600000>;
+		};
+	};
+};
+
+&gpio0 {
+	status = "okay";
+};
+
+&gpio1 {
+	status = "okay";
+};
+
+&mmc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc1_pins>;
+	vmmc-supply = <&vdd_3v3>;
+	cd-gpios = <&gpio0 69 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins>;
+	status = "okay";
+
+	eeprom@50 {
+		compatible = "atmel,24c256";
+		reg = <0x50>;
+	};
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
+	status = "okay";
+	clock-frequency = <400000>;
+
+	pca9536: gpio@41 {
+		compatible = "ti,pca9536";
+		reg = <0x41>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		vcc-supply = <&vdd_3v3>;
+	};
+};
diff --git a/arch/arm/boot/dts/keystone-k2g.dtsi b/arch/arm/boot/dts/keystone-k2g.dtsi
index 8f313ff406b9..fd061718dc0a 100644
--- a/arch/arm/boot/dts/keystone-k2g.dtsi
+++ b/arch/arm/boot/dts/keystone-k2g.dtsi
@@ -1,16 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device Tree Source for K2G SOC
  *
- * Copyright (C) 2016 Texas Instruments Incorporated - http://www.ti.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2016-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 #include <dt-bindings/interrupt-controller/arm-gic.h>
@@ -28,6 +20,8 @@
 
 	aliases {
 		serial0 = &uart0;
+		serial1 = &uart1;
+		serial2 = &uart2;
 		i2c0 = &i2c0;
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
@@ -75,7 +69,7 @@
 		interrupts = <GIC_SPI 4 IRQ_TYPE_EDGE_RISING>;
 	};
 
-	soc {
+	soc0: soc@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		#pinctrl-cells = <1>;
@@ -114,7 +108,32 @@
 			reg-io-width = <4>;
 			reg = <0x02530c00 0x100>;
 			interrupts = <GIC_SPI 164 IRQ_TYPE_EDGE_RISING>;
-			clock-frequency = <200000000>;
+			clocks = <&k2g_clks 0x2c 0>;
+			power-domains = <&k2g_pds 0x2c>;
+			status = "disabled";
+		};
+
+		uart1: serial@02531000 {
+			compatible = "ti,da830-uart", "ns16550a";
+			current-speed = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			reg = <0x02531000 0x100>;
+			interrupts = <GIC_SPI 165 IRQ_TYPE_EDGE_RISING>;
+			clocks = <&k2g_clks 0x2d 0>;
+			power-domains = <&k2g_pds 0x2d>;
+			status = "disabled";
+		};
+
+		uart2: serial@02531400 {
+			compatible = "ti,da830-uart", "ns16550a";
+			current-speed = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			reg = <0x02531400 0x100>;
+			interrupts = <GIC_SPI 166 IRQ_TYPE_EDGE_RISING>;
+			clocks = <&k2g_clks 0x2e 0>;
+			power-domains = <&k2g_pds 0x2e>;
 			status = "disabled";
 		};
 
@@ -372,11 +391,24 @@
 			dma-names = "tx", "rx";
 			bus-width = <8>;
 			ti,needs-special-reset;
-			ti,non-removable;
 			max-frequency = <96000000>;
 			power-domains = <&k2g_pds 0xc>;
 			clocks = <&k2g_clks 0xc 1>, <&k2g_clks 0xc 2>;
 			clock-names = "fck", "mmchsdb_fck";
+		};
+
+		qspi: qspi@2940000 {
+			compatible = "ti,k2g-qspi", "cdns,qspi-nor";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x02940000 0x1000>,
+			      <0x24000000 0x4000000>;
+			interrupts = <GIC_SPI 198 IRQ_TYPE_EDGE_RISING>;
+			cdns,fifo-depth = <256>;
+			cdns,fifo-width = <4>;
+			cdns,trigger-address = <0x24000000>;
+			clocks = <&k2g_clks 0x43 0x0>;
+			power-domains = <&k2g_pds 0x43>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/keystone-k2hk-clocks.dtsi b/arch/arm/boot/dts/keystone-k2hk-clocks.dtsi
index af9b7190533a..4ba6912176ef 100644
--- a/arch/arm/boot/dts/keystone-k2hk-clocks.dtsi
+++ b/arch/arm/boot/dts/keystone-k2hk-clocks.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright 2013-2014 Texas Instruments, Inc.
- *
  * Keystone 2 Kepler/Hawking SoC clock nodes
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 clocks {
@@ -53,7 +50,7 @@ clocks {
 		reg-names = "control";
 	};
 
-	clktsip: clktsip {
+	clktsip: clktsip@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk16>;
@@ -63,7 +60,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clksrio: clksrio {
+	clksrio: clksrio@235002c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1rstiso13>;
@@ -73,7 +70,7 @@ clocks {
 		domain-id = <4>;
 	};
 
-	clkhyperlink0: clkhyperlink0 {
+	clkhyperlink0: clkhyperlink0@2350030 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk12>;
@@ -83,7 +80,7 @@ clocks {
 		domain-id = <5>;
 	};
 
-	clkgem1: clkgem1 {
+	clkgem1: clkgem1@2350040 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1>;
@@ -93,7 +90,7 @@ clocks {
 		domain-id = <9>;
 	};
 
-	clkgem2: clkgem2 {
+	clkgem2: clkgem2@2350044 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1>;
@@ -103,7 +100,7 @@ clocks {
 		domain-id = <10>;
 	};
 
-	clkgem3: clkgem3 {
+	clkgem3: clkgem3@2350048 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1>;
@@ -113,7 +110,7 @@ clocks {
 		domain-id = <11>;
 	};
 
-	clkgem4: clkgem4 {
+	clkgem4: clkgem4@235004c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1>;
@@ -123,7 +120,7 @@ clocks {
 		domain-id = <12>;
 	};
 
-	clkgem5: clkgem5 {
+	clkgem5: clkgem5@2350050 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1>;
@@ -133,7 +130,7 @@ clocks {
 		domain-id = <13>;
 	};
 
-	clkgem6: clkgem6 {
+	clkgem6: clkgem6@2350054 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1>;
@@ -143,7 +140,7 @@ clocks {
 		domain-id = <14>;
 	};
 
-	clkgem7: clkgem7 {
+	clkgem7: clkgem7@2350058 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1>;
@@ -153,7 +150,7 @@ clocks {
 		domain-id = <15>;
 	};
 
-	clkddr31: clkddr31 {
+	clkddr31: clkddr31@2350060 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -163,7 +160,7 @@ clocks {
 		domain-id = <16>;
 	};
 
-	clktac: clktac {
+	clktac: clktac@2350064 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -173,7 +170,7 @@ clocks {
 		domain-id = <17>;
 	};
 
-	clkrac01: clkrac01 {
+	clkrac01: clkrac01@2350068 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -183,7 +180,7 @@ clocks {
 		domain-id = <17>;
 	};
 
-	clkrac23: clkrac23 {
+	clkrac23: clkrac23@235006c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -193,7 +190,7 @@ clocks {
 		domain-id = <18>;
 	};
 
-	clkfftc0: clkfftc0 {
+	clkfftc0: clkfftc0@2350070 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -203,7 +200,7 @@ clocks {
 		domain-id = <19>;
 	};
 
-	clkfftc1: clkfftc1 {
+	clkfftc1: clkfftc1@2350074 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -213,7 +210,7 @@ clocks {
 		domain-id = <19>;
 	};
 
-	clkfftc2: clkfftc2 {
+	clkfftc2: clkfftc2@2350078 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -223,7 +220,7 @@ clocks {
 		domain-id = <20>;
 	};
 
-	clkfftc3: clkfftc3 {
+	clkfftc3: clkfftc3@235007c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -233,7 +230,7 @@ clocks {
 		domain-id = <20>;
 	};
 
-	clkfftc4: clkfftc4 {
+	clkfftc4: clkfftc4@2350080 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -243,7 +240,7 @@ clocks {
 		domain-id = <20>;
 	};
 
-	clkfftc5: clkfftc5 {
+	clkfftc5: clkfftc5@2350084 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -253,7 +250,7 @@ clocks {
 		domain-id = <20>;
 	};
 
-	clkaif: clkaif {
+	clkaif: clkaif@2350088 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -263,7 +260,7 @@ clocks {
 		domain-id = <21>;
 	};
 
-	clktcp3d0: clktcp3d0 {
+	clktcp3d0: clktcp3d0@235008c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -273,7 +270,7 @@ clocks {
 		domain-id = <22>;
 	};
 
-	clktcp3d1: clktcp3d1 {
+	clktcp3d1: clktcp3d1@2350090 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -283,7 +280,7 @@ clocks {
 		domain-id = <22>;
 	};
 
-	clktcp3d2: clktcp3d2 {
+	clktcp3d2: clktcp3d2@2350094 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -293,7 +290,7 @@ clocks {
 		domain-id = <23>;
 	};
 
-	clktcp3d3: clktcp3d3 {
+	clktcp3d3: clktcp3d3@2350098 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -303,7 +300,7 @@ clocks {
 		domain-id = <23>;
 	};
 
-	clkvcp0: clkvcp0 {
+	clkvcp0: clkvcp0@235009c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -313,7 +310,7 @@ clocks {
 		domain-id = <24>;
 	};
 
-	clkvcp1: clkvcp1 {
+	clkvcp1: clkvcp1@23500a0 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -323,7 +320,7 @@ clocks {
 		domain-id = <24>;
 	};
 
-	clkvcp2: clkvcp2 {
+	clkvcp2: clkvcp2@23500a4 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -333,7 +330,7 @@ clocks {
 		domain-id = <24>;
 	};
 
-	clkvcp3: clkvcp3 {
+	clkvcp3: clkvcp3@23500a8 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -343,7 +340,7 @@ clocks {
 		domain-id = <24>;
 	};
 
-	clkvcp4: clkvcp4 {
+	clkvcp4: clkvcp4@23500ac {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -353,7 +350,7 @@ clocks {
 		domain-id = <25>;
 	};
 
-	clkvcp5: clkvcp5 {
+	clkvcp5: clkvcp5@23500b0 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -363,7 +360,7 @@ clocks {
 		domain-id = <25>;
 	};
 
-	clkvcp6: clkvcp6 {
+	clkvcp6: clkvcp6@23500b4 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -373,7 +370,7 @@ clocks {
 		domain-id = <25>;
 	};
 
-	clkvcp7: clkvcp7 {
+	clkvcp7: clkvcp7@23500b8 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -383,7 +380,7 @@ clocks {
 		domain-id = <25>;
 	};
 
-	clkbcp: clkbcp {
+	clkbcp: clkbcp@23500bc {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -393,7 +390,7 @@ clocks {
 		domain-id = <26>;
 	};
 
-	clkdxb: clkdxb {
+	clkdxb: clkdxb@23500c0 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -403,7 +400,7 @@ clocks {
 		domain-id = <27>;
 	};
 
-	clkhyperlink1: clkhyperlink1 {
+	clkhyperlink1: clkhyperlink1@23500c4 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk12>;
@@ -413,7 +410,7 @@ clocks {
 		domain-id = <28>;
 	};
 
-	clkxge: clkxge {
+	clkxge: clkxge@23500c8 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
diff --git a/arch/arm/boot/dts/keystone-k2hk-evm.dts b/arch/arm/boot/dts/keystone-k2hk-evm.dts
index 6dd13b98aaba..ad4e22afe133 100644
--- a/arch/arm/boot/dts/keystone-k2hk-evm.dts
+++ b/arch/arm/boot/dts/keystone-k2hk-evm.dts
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright 2013-2014 Texas Instruments, Inc.
- *
  * Keystone 2 Kepler/Hawking EVM device tree
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 /dts-v1/;
 
@@ -29,7 +26,31 @@
 		};
 	};
 
-	soc {
+	leds {
+		compatible = "gpio-leds";
+		debug1_1 {
+			label = "keystone:green:debug1";
+			gpios = <&gpio0 12 GPIO_ACTIVE_HIGH>; /* 12 */
+		};
+
+		debug1_2 {
+			label = "keystone:red:debug1";
+			gpios = <&gpio0 13 GPIO_ACTIVE_HIGH>; /* 13 */
+		};
+
+		debug2 {
+			label = "keystone:blue:debug2";
+			gpios = <&gpio0 14 GPIO_ACTIVE_HIGH>; /* 14 */
+		};
+
+		debug3 {
+			label = "keystone:blue:debug3";
+			gpios = <&gpio0 15 GPIO_ACTIVE_HIGH>; /* 15 */
+		};
+	};
+};
+
+&soc0 {
 		clocks {
 			refclksys: refclksys {
 				#clock-cells = <0>;
@@ -66,30 +87,6 @@
 				clock-output-names = "refclk-ddr3b";
 			};
 		};
-	};
-
-	leds {
-		compatible = "gpio-leds";
-		debug1_1 {
-			label = "keystone:green:debug1";
-			gpios = <&gpio0 12 GPIO_ACTIVE_HIGH>; /* 12 */
-		};
-
-		debug1_2 {
-			label = "keystone:red:debug1";
-			gpios = <&gpio0 13 GPIO_ACTIVE_HIGH>; /* 13 */
-		};
-
-		debug2 {
-			label = "keystone:blue:debug2";
-			gpios = <&gpio0 14 GPIO_ACTIVE_HIGH>; /* 14 */
-		};
-
-		debug3 {
-			label = "keystone:blue:debug3";
-			gpios = <&gpio0 15 GPIO_ACTIVE_HIGH>; /* 15 */
-		};
-	};
 };
 
 &usb_phy {
@@ -158,7 +155,7 @@
 
 &i2c0 {
 	dtt@50 {
-		compatible = "at,24c1024";
+		compatible = "atmel,24c1024";
 		reg = <0x50>;
 	};
 };
diff --git a/arch/arm/boot/dts/keystone-k2hk-netcp.dtsi b/arch/arm/boot/dts/keystone-k2hk-netcp.dtsi
index a5ac845464bf..b88c0689c285 100644
--- a/arch/arm/boot/dts/keystone-k2hk-netcp.dtsi
+++ b/arch/arm/boot/dts/keystone-k2hk-netcp.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device Tree Source for Keystone 2 Hawking Netcp driver
  *
- * Copyright 2015 Texas Instruments, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2015-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 qmss: qmss@2a40000 {
diff --git a/arch/arm/boot/dts/keystone-k2hk.dtsi b/arch/arm/boot/dts/keystone-k2hk.dtsi
index 7c486d9dc90e..ed59474522cb 100644
--- a/arch/arm/boot/dts/keystone-k2hk.dtsi
+++ b/arch/arm/boot/dts/keystone-k2hk.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright 2013-2014 Texas Instruments, Inc.
- *
  * Keystone 2 Kepler/Hawking soc specific device tree
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 #include <dt-bindings/reset/ti-syscon.h>
@@ -55,8 +52,9 @@
 		rproc6 = &dsp6;
 		rproc7 = &dsp7;
 	};
+};
 
-	soc {
+&soc0 {
 		/include/ "keystone-k2hk-clocks.dtsi"
 
 		msm_ram: msmram@c000000 {
@@ -284,5 +282,4 @@
 			bus_freq	= <2500000>;
 		};
 		/include/ "keystone-k2hk-netcp.dtsi"
-	};
 };
diff --git a/arch/arm/boot/dts/keystone-k2l-clocks.dtsi b/arch/arm/boot/dts/keystone-k2l-clocks.dtsi
index ef8464bb11ff..635528064dea 100644
--- a/arch/arm/boot/dts/keystone-k2l-clocks.dtsi
+++ b/arch/arm/boot/dts/keystone-k2l-clocks.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright 2013-2014 Texas Instruments, Inc.
- *
  * Keystone 2 lamarr SoC clock nodes
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 clocks {
@@ -44,7 +41,7 @@ clocks {
 		reg-names = "control";
 	};
 
-	clkdfeiqnsys: clkdfeiqnsys {
+	clkdfeiqnsys: clkdfeiqnsys@2350004 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk12>;
@@ -54,7 +51,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkpcie1: clkpcie1 {
+	clkpcie1: clkpcie1@235002c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk12>;
@@ -64,7 +61,7 @@ clocks {
 		domain-id = <4>;
 	};
 
-	clkgem1: clkgem1 {
+	clkgem1: clkgem1@2350040 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1>;
@@ -74,7 +71,7 @@ clocks {
 		domain-id = <9>;
 	};
 
-	clkgem2: clkgem2 {
+	clkgem2: clkgem2@2350044 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1>;
@@ -84,7 +81,7 @@ clocks {
 		domain-id = <10>;
 	};
 
-	clkgem3: clkgem3 {
+	clkgem3: clkgem3@2350048 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk1>;
@@ -94,7 +91,7 @@ clocks {
 		domain-id = <11>;
 	};
 
-	clktac: clktac {
+	clktac: clktac@2350064 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -104,7 +101,7 @@ clocks {
 		domain-id = <17>;
 	};
 
-	clkrac: clkrac {
+	clkrac: clkrac@2350068 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -114,7 +111,7 @@ clocks {
 		domain-id = <17>;
 	};
 
-	clkdfepd0: clkdfepd0 {
+	clkdfepd0: clkdfepd0@235006c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -124,7 +121,7 @@ clocks {
 		domain-id = <18>;
 	};
 
-	clkfftc0: clkfftc0 {
+	clkfftc0: clkfftc0@2350070 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -134,7 +131,7 @@ clocks {
 		domain-id = <19>;
 	};
 
-	clkosr: clkosr {
+	clkosr: clkosr@2350088 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -144,7 +141,7 @@ clocks {
 		domain-id = <21>;
 	};
 
-	clktcp3d0: clktcp3d0 {
+	clktcp3d0: clktcp3d0@235008c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -154,7 +151,7 @@ clocks {
 		domain-id = <22>;
 	};
 
-	clktcp3d1: clktcp3d1 {
+	clktcp3d1: clktcp3d1@2350094 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -164,7 +161,7 @@ clocks {
 		domain-id = <23>;
 	};
 
-	clkvcp0: clkvcp0 {
+	clkvcp0: clkvcp0@235009c {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -174,7 +171,7 @@ clocks {
 		domain-id = <24>;
 	};
 
-	clkvcp1: clkvcp1 {
+	clkvcp1: clkvcp1@23500a0 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -184,7 +181,7 @@ clocks {
 		domain-id = <24>;
 	};
 
-	clkvcp2: clkvcp2 {
+	clkvcp2: clkvcp2@23500a4 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -194,7 +191,7 @@ clocks {
 		domain-id = <24>;
 	};
 
-	clkvcp3: clkvcp3 {
+	clkvcp3: clkvcp3@23500a8 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -204,7 +201,7 @@ clocks {
 		domain-id = <24>;
 	};
 
-	clkbcp: clkbcp {
+	clkbcp: clkbcp@23500bc {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -214,7 +211,7 @@ clocks {
 		domain-id = <26>;
 	};
 
-	clkdfepd1: clkdfepd1 {
+	clkdfepd1: clkdfepd1@23500c0 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -224,7 +221,7 @@ clocks {
 		domain-id = <27>;
 	};
 
-	clkfftc1: clkfftc1 {
+	clkfftc1: clkfftc1@23500c4 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -234,7 +231,7 @@ clocks {
 		domain-id = <28>;
 	};
 
-	clkiqnail: clkiqnail {
+	clkiqnail: clkiqnail@23500c8 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
@@ -244,7 +241,7 @@ clocks {
 		domain-id = <29>;
 	};
 
-	clkuart2: clkuart2 {
+	clkuart2: clkuart2@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
@@ -254,7 +251,7 @@ clocks {
 		domain-id = <0>;
 	};
 
-	clkuart3: clkuart3 {
+	clkuart3: clkuart3@2350000 {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&clkmodrst0>;
diff --git a/arch/arm/boot/dts/keystone-k2l-evm.dts b/arch/arm/boot/dts/keystone-k2l-evm.dts
index 528667618db4..e200533d26a4 100644
--- a/arch/arm/boot/dts/keystone-k2l-evm.dts
+++ b/arch/arm/boot/dts/keystone-k2l-evm.dts
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright 2014 Texas Instruments, Inc.
- *
  * Keystone 2 Lamarr EVM device tree
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2014-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 /dts-v1/;
 
@@ -28,8 +25,9 @@
 			status = "okay";
 		};
 	};
+};
 
-	soc {
+&soc0 {
 		clocks {
 			refclksys: refclksys {
 				#clock-cells = <0>;
@@ -38,7 +36,6 @@
 				clock-output-names = "refclk-sys";
 			};
 		};
-	};
 };
 
 &usb_phy {
@@ -55,7 +52,7 @@
 
 &i2c0 {
 	dtt@50 {
-		compatible = "at,24c1024";
+		compatible = "atmel,24c1024";
 		reg = <0x50>;
 	};
 };
diff --git a/arch/arm/boot/dts/keystone-k2l-netcp.dtsi b/arch/arm/boot/dts/keystone-k2l-netcp.dtsi
index 66f615a74118..9ec84228bc16 100644
--- a/arch/arm/boot/dts/keystone-k2l-netcp.dtsi
+++ b/arch/arm/boot/dts/keystone-k2l-netcp.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device Tree Source for Keystone 2 Lamarr Netcp driver
  *
- * Copyright 2015 Texas Instruments, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2015-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 qmss: qmss@2a40000 {
diff --git a/arch/arm/boot/dts/keystone-k2l.dtsi b/arch/arm/boot/dts/keystone-k2l.dtsi
index 4370e6513aa4..b61a830f4a4d 100644
--- a/arch/arm/boot/dts/keystone-k2l.dtsi
+++ b/arch/arm/boot/dts/keystone-k2l.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright 2014 Texas Instruments, Inc.
- *
  * Keystone 2 Lamarr SoC specific device tree
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2014-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 #include <dt-bindings/reset/ti-syscon.h>
@@ -39,8 +36,9 @@
 		rproc2 = &dsp2;
 		rproc3 = &dsp3;
 	};
+};
 
-	soc {
+&soc0 {
 		/include/ "keystone-k2l-clocks.dtsi"
 
 		uart2: serial@2348400 {
@@ -63,6 +61,50 @@
 			interrupts = <GIC_SPI 435 IRQ_TYPE_EDGE_RISING>;
 		};
 
+		gpio1: gpio@2348000 {
+			compatible = "ti,keystone-gpio";
+			reg = <0x02348000 0x100>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			/* HW Interrupts mapped to GPIO pins */
+			interrupts = <GIC_SPI 152 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 153 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 154 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 155 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 156 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 157 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 158 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 159 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 160 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 161 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 162 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 163 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 164 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 165 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 166 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 167 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 168 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 169 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 170 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 171 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 172 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 173 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 174 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 175 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 176 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 401 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 402 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 403 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 404 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 405 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 406 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 407 IRQ_TYPE_EDGE_RISING>;
+			clocks = <&clkgpio>;
+			clock-names = "gpio";
+			ti,ngpio = <32>;
+			ti,davinci-gpio-unbanked = <32>;
+		};
+
 		k2l_pmx: pinmux@2620690 {
 			compatible = "pinctrl-single";
 			reg = <0x02620690 0xc>;
@@ -350,7 +392,6 @@
 			bus_freq	= <2500000>;
 		};
 		/include/ "keystone-k2l-netcp.dtsi"
-	};
 };
 
 &spi0 {
diff --git a/arch/arm/boot/dts/keystone.dtsi b/arch/arm/boot/dts/keystone.dtsi
index 06e10544f9b1..93ea5c69ea77 100644
--- a/arch/arm/boot/dts/keystone.dtsi
+++ b/arch/arm/boot/dts/keystone.dtsi
@@ -1,16 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright 2013 Texas Instruments, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
  */
 
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/gpio/gpio.h>
 
-#include "skeleton.dtsi"
-
 / {
 	compatible = "ti,keystone";
 	model = "Texas Instruments Keystone 2 SoC";
@@ -25,11 +20,14 @@
 		spi2 = &spi2;
 	};
 
-	memory {
+	chosen { };
+
+	memory: memory@80000000 {
+		device_type = "memory";
 		reg = <0x00000000 0x80000000 0x00000000 0x40000000>;
 	};
 
-	gic: interrupt-controller {
+	gic: interrupt-controller@2561000 {
 		compatible = "arm,gic-400", "arm,cortex-a15-gic";
 		#interrupt-cells = <3>;
 		interrupt-controller;
@@ -70,7 +68,7 @@
 		cpu_on		= <0x84000003>;
 	};
 
-	soc {
+	soc0: soc@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "ti,keystone","simple-bus";
diff --git a/arch/arm/boot/dts/kirkwood-linksys-viper.dts b/arch/arm/boot/dts/kirkwood-linksys-viper.dts
index df7851820507..f21a50dd9869 100644
--- a/arch/arm/boot/dts/kirkwood-linksys-viper.dts
+++ b/arch/arm/boot/dts/kirkwood-linksys-viper.dts
@@ -157,7 +157,7 @@
 			reg = <0x80000 0x20000>;
 		};
 
-		partition@A0000 {
+		partition@a0000 {
 			label = "s_env";
 			reg = <0xA0000 0x20000>;
 		};
@@ -167,17 +167,17 @@
 			reg = <0x200000 0x2A0000>;
 		};
 
-		partition@4A0000 {
+		partition@4a0000 {
 			label = "rootfs";
 			reg = <0x4A0000 0x1760000>;
 		};
 
-		partition@1C00000 {
+		partition@1c00000 {
 			label = "alt_kernel";
 			reg = <0x1C00000 0x2A0000>;
 		};
 
-		partition@1EA0000 {
+		partition@1ea0000 {
 			label = "alt_rootfs";
 			reg = <0x1EA0000 0x1760000>;
 		};
@@ -187,7 +187,7 @@
 			reg = <0x3600000 0x4A00000>;
 		};
 
-		partition@C0000 {
+		partition@c0000 {
 			label = "unused";
 			reg = <0xC0000 0x140000>;
 		};
diff --git a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
index cf2f5240e176..27cc913ca0f5 100644
--- a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
+++ b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
@@ -53,7 +53,8 @@
 		};
 
 		pinctrl: pin-controller@10000 {
-			pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header>;
+			pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header
+				     &pmx_gpio_header_gpo>;
 			pinctrl-names = "default";
 
 			pmx_uart0: pmx-uart0 {
@@ -85,11 +86,16 @@
 			 * ground.
 			 */
 			pmx_gpio_header: pmx-gpio-header {
-				marvell,pins = "mpp17", "mpp7", "mpp29", "mpp28",
+				marvell,pins = "mpp17", "mpp29", "mpp28",
 					       "mpp35", "mpp34", "mpp40";
 				marvell,function = "gpio";
 			};
 
+			pmx_gpio_header_gpo: pxm-gpio-header-gpo {
+				marvell,pins = "mpp7";
+				marvell,function = "gpo";
+			};
+
 			pmx_gpio_init: pmx-init {
 				marvell,pins = "mpp38";
 				marvell,function = "gpio";
diff --git a/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts
new file mode 100644
index 000000000000..32d0dc371fc3
--- /dev/null
+++ b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts
@@ -0,0 +1,17 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/dts-v1/;
+
+#include "omap34xx.dtsi"
+#include "logicpd-som-lv.dtsi"
+#include "logicpd-som-lv-baseboard.dtsi"
+#include "omap-gpmc-smsc9221.dtsi"
+
+/ {
+	model = "LogicPD Zoom OMAP35xx SOM-LV Development Kit";
+	compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3";
+};
diff --git a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
index 38faa90007d7..24283739526c 100644
--- a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
+++ b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
@@ -8,256 +8,10 @@
 
 #include "omap36xx.dtsi"
 #include "logicpd-som-lv.dtsi"
+#include "logicpd-som-lv-baseboard.dtsi"
 #include "omap-gpmc-smsc9221.dtsi"
 
 / {
 	model = "LogicPD Zoom DM3730 SOM-LV Development Kit";
 	compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3630", "ti,omap3";
-
-	gpio_keys {
-		compatible = "gpio-keys";
-		pinctrl-names = "default";
-		pinctrl-0 = <&gpio_key_pins>;
-
-		sysboot2 {
-			label = "gpio3";
-			gpios = <&gpio4 15 GPIO_ACTIVE_LOW>;	/* gpio_111 / uP_GPIO_3 */
-			linux,code = <BTN_0>;
-			wakeup-source;
-		};
-	};
-
-	sound {
-		compatible = "ti,omap-twl4030";
-		ti,model = "omap3logic";
-		ti,mcbsp = <&mcbsp2>;
-	};
-
-	leds {
-		compatible = "gpio-leds";
-		pinctrl-names = "default";
-		pinctrl-0 = <&led_pins &led_pins_wkup>;
-
-		led1 {
-			label = "led1";
-			gpios = <&gpio5 5 GPIO_ACTIVE_LOW>;	/* gpio133 */
-			linux,default-trigger = "cpu0";
-		};
-
-		led2 {
-			label = "led2";
-			gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;	/* gpio11 */
-			linux,default-trigger = "none";
-		};
-	};
-};
-
-&vaux1 {
-	regulator-min-microvolt = <3000000>;
-	regulator-max-microvolt = <3000000>;
-};
-
-&vaux4 {
-	regulator-min-microvolt = <1800000>;
-	regulator-max-microvolt = <1800000>;
-};
-
-&mcbsp2 {
-	status = "okay";
-};
-
-&charger {
-	ti,bb-uvolt = <3200000>;
-	ti,bb-uamp = <150>;
-};
-
-&gpmc {
-	ranges = <1 0 0x08000000 0x1000000>;	/* CS1: 16MB for LAN9221 */
-
-	ethernet@gpmc {
-		pinctrl-names = "default";
-		pinctrl-0 = <&lan9221_pins>;
-		interrupt-parent = <&gpio5>;
-		interrupts = <24 IRQ_TYPE_LEVEL_LOW>;		/* gpio_152 */
-		reg = <1 0 0xff>;
-	};
-};
-
-&vpll2 {
-	regulator-always-on;
-};
-
-&dss {
-	status = "ok";
-	vdds_dsi-supply = <&vpll2>;
-	vdda_video-supply = <&video_reg>;
-	pinctrl-names = "default";
-	pinctrl-0 = <&dss_dpi_pins1>;
-	port {
-		dpi_out: endpoint {
-			remote-endpoint = <&lcd_in>;
-			data-lines = <16>;
-		};
-	};
-};
-
-/ {
-	aliases {
-		display0 = &lcd0;
-	};
-
-	video_reg: video_reg {
-		compatible = "regulator-fixed";
-		regulator-name = "fixed-supply";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-	};
-
-	lcd0: display@0 {
-		compatible = "panel-dpi";
-		label = "28";
-		status = "okay";
-		/* default-on; */
-		pinctrl-names = "default";
-		pinctrl-0 = <&lcd_enable_pin>;
-		enable-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>;	/* gpio155, lcd INI */
-		port {
-			lcd_in: endpoint {
-				remote-endpoint = <&dpi_out>;
-			};
-		};
-
-		panel-timing {
-			clock-frequency = <9000000>;
-			hactive = <480>;
-			vactive = <272>;
-			hfront-porch = <3>;
-			hback-porch = <2>;
-			hsync-len = <42>;
-			vback-porch = <3>;
-			vfront-porch = <2>;
-			vsync-len = <11>;
-			hsync-active = <1>;
-			vsync-active = <1>;
-			de-active = <1>;
-			pixelclk-active = <0>;
-		};
-	};
-
-	bl: backlight {
-		compatible = "pwm-backlight";
-		pinctrl-names = "default";
-		pinctrl-0 = <&backlight_pins>;
-		pwms = <&twl_pwm 0 5000000>;
-		brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>;
-		default-brightness-level = <7>;
-		enable-gpios = <&gpio1 8 GPIO_ACTIVE_HIGH>; /* gpio_8 */
-	};
-};
-
-&mmc1 {
-	interrupts-extended = <&intc 83 &omap3_pmx_core 0x11a>;
-	pinctrl-names = "default";
-	pinctrl-0 = <&mmc1_pins>;
-	wp-gpios = <&gpio4 30 GPIO_ACTIVE_HIGH>;		/* gpio_126 */
-	cd-gpios = <&gpio4 14 IRQ_TYPE_LEVEL_LOW>;		/* gpio_110 */
-	vmmc-supply = <&vmmc1>;
-	bus-width = <4>;
-	cap-power-off-card;
-};
-
-&omap3_pmx_core {
-	gpio_key_pins: pinmux_gpio_key_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x212e, PIN_INPUT_PULLUP | MUX_MODE4)	/* cam_xclkb.gpio_111 / uP_GPIO_3*/
-		>;
-	};
-
-	led_pins: pinmux_led_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x215e, PIN_OUTPUT_PULLUP | MUX_MODE4)	/* sdmmc2_dat1.gpio_133 / uP_GPIO_0 */
-		>;
-	};
-
-	lan9221_pins: pinmux_lan9221_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT_PULLUP | MUX_MODE4)	/* mcbsp4_clkx.gpio_152 */
-		>;
-	};
-
-	mmc1_pins: pinmux_mmc1_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x2144, PIN_OUTPUT | MUX_MODE0)	/* sdmmc1_clk.sdmmc1_clk */
-			OMAP3_CORE1_IOPAD(0x2146, PIN_INPUT | MUX_MODE0)	/* sdmmc1_cmd.sdmmc1_cmd */
-			OMAP3_CORE1_IOPAD(0x2148, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat0.sdmmc1_dat0 */
-			OMAP3_CORE1_IOPAD(0x214a, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat1.sdmmc1_dat1 */
-			OMAP3_CORE1_IOPAD(0x214c, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat2.sdmmc1_dat2 */
-			OMAP3_CORE1_IOPAD(0x214e, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat3.sdmmc1_dat3 */
-			OMAP3_CORE1_IOPAD(0x2132, PIN_INPUT_PULLUP | MUX_MODE4)	/* cam_strobe.gpio_126 */
-			OMAP3_CORE1_IOPAD(0x212c, PIN_INPUT_PULLUP | MUX_MODE4)	/* cam_d11.gpio_110 */
-		>;
-	};
-
-	lcd_enable_pin: pinmux_lcd_enable_pin {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x218a, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE4)       /* mcbsp4_fs.gpio_155 */
-		>;
-	};
-
-	dss_dpi_pins1: pinmux_dss_dpi_pins1 {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_pclk.dss_pclk */
-			OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_hsync.dss_hsync */
-			OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_vsync.dss_vsync */
-			OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_acbias.dss_acbias */
-
-			OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data0.dss_data0 */
-			OMAP3_CORE1_IOPAD(0x20de, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data1.dss_data1 */
-			OMAP3_CORE1_IOPAD(0x20e0, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data2.dss_data2 */
-			OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data3.dss_data3 */
-			OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data4.dss_data4 */
-			OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data5.dss_data5 */
-			OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data6.dss_data6 */
-			OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data7.dss_data7 */
-			OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data8.dss_data8 */
-			OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data9.dss_data9 */
-			OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data10.dss_data10 */
-			OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data11.dss_data11 */
-			OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data12.dss_data12 */
-			OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data13.dss_data13 */
-			OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data14.dss_data14 */
-			OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data15.dss_data15 */
-		>;
-	};
-};
-
-&omap3_pmx_wkup {
-	led_pins_wkup: pinmux_led_pins_wkup {
-		pinctrl-single,pins = <
-			OMAP3_WKUP_IOPAD(0x2a24, PIN_OUTPUT_PULLUP | MUX_MODE4)	/* jtag_emu0.gpio_11 / uP_GPIO_1 */
-		>;
-	};
-
-	backlight_pins: pinmux_backlight_pins {
-		pinctrl-single,pins = <
-			OMAP3_WKUP_IOPAD(0x2a16, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE4)       /* sys_boot6.gpio_8 */
-		>;
-	};
-};
-
-
-&uart1 {
-	interrupts-extended = <&intc 72 &omap3_pmx_core OMAP3_UART1_RX>;
-};
-
-/* Wired to the tps65950 on the SOM, only the USB connector is on the devkit */
-&usb_otg_hs {
-	pinctrl-names = "default";
-	pinctrl-0 = <&hsusb_otg_pins>;
-	interface-type = <0>;
-	usb-phy = <&usb2_phy>;
-	phys = <&usb2_phy>;
-	phy-names = "usb2-phy";
-	mode = <3>;
-	power = <50>;
 };
diff --git a/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi
new file mode 100644
index 000000000000..4990ed90dcea
--- /dev/null
+++ b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi
@@ -0,0 +1,256 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/ {
+	gpio_keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&gpio_key_pins>;
+
+		sysboot2 {
+			label = "gpio3";
+			gpios = <&gpio4 15 GPIO_ACTIVE_LOW>;	/* gpio_111 / uP_GPIO_3 */
+			linux,code = <BTN_0>;
+			wakeup-source;
+		};
+	};
+
+	sound {
+		compatible = "ti,omap-twl4030";
+		ti,model = "omap3logic";
+		ti,mcbsp = <&mcbsp2>;
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led_pins &led_pins_wkup>;
+
+		led1 {
+			label = "led1";
+			gpios = <&gpio5 5 GPIO_ACTIVE_LOW>;	/* gpio133 */
+			linux,default-trigger = "cpu0";
+		};
+
+		led2 {
+			label = "led2";
+			gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;	/* gpio11 */
+			linux,default-trigger = "none";
+		};
+	};
+};
+
+&vaux1 {
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+};
+
+&vaux4 {
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
+};
+
+&mcbsp2 {
+	status = "okay";
+};
+
+&charger {
+	ti,bb-uvolt = <3200000>;
+	ti,bb-uamp = <150>;
+};
+
+&gpmc {
+	ranges = <0 0 0x30000000 0x1000000	/* CS0: 16MB for NAND */
+		  1 0 0x2c000000 0x1000000	/* CS1: 16MB for LAN9221 */
+		  2 0 0x10000000 0x2000000>;    /* CS2: 32MB for NOR */
+
+	ethernet@gpmc {
+		pinctrl-names = "default";
+		pinctrl-0 = <&lan9221_pins>;
+		interrupt-parent = <&gpio5>;
+		interrupts = <24 IRQ_TYPE_LEVEL_LOW>;		/* gpio_152 */
+		reg = <1 0 0xff>;
+	};
+};
+
+&vpll2 {
+	regulator-always-on;
+};
+
+&dss {
+	status = "ok";
+	vdds_dsi-supply = <&vpll2>;
+	vdda_video-supply = <&video_reg>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&dss_dpi_pins1>;
+	port {
+		dpi_out: endpoint {
+			remote-endpoint = <&lcd_in>;
+			data-lines = <16>;
+		};
+	};
+};
+
+/ {
+	aliases {
+		display0 = &lcd0;
+	};
+
+	video_reg: video_reg {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-supply";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	lcd0: display@0 {
+		compatible = "panel-dpi";
+		label = "28";
+		status = "okay";
+		/* default-on; */
+		pinctrl-names = "default";
+		pinctrl-0 = <&lcd_enable_pin>;
+		enable-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>;	/* gpio155, lcd INI */
+		port {
+			lcd_in: endpoint {
+				remote-endpoint = <&dpi_out>;
+			};
+		};
+
+		panel-timing {
+			clock-frequency = <9000000>;
+			hactive = <480>;
+			vactive = <272>;
+			hfront-porch = <3>;
+			hback-porch = <2>;
+			hsync-len = <42>;
+			vback-porch = <3>;
+			vfront-porch = <2>;
+			vsync-len = <11>;
+			hsync-active = <1>;
+			vsync-active = <1>;
+			de-active = <1>;
+			pixelclk-active = <0>;
+		};
+	};
+
+	bl: backlight {
+		compatible = "pwm-backlight";
+		pinctrl-names = "default";
+		pinctrl-0 = <&backlight_pins>;
+		pwms = <&twl_pwm 0 5000000>;
+		brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>;
+		default-brightness-level = <7>;
+		enable-gpios = <&gpio1 8 GPIO_ACTIVE_HIGH>; /* gpio_8 */
+	};
+};
+
+&mmc1 {
+	interrupts-extended = <&intc 83 &omap3_pmx_core 0x11a>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc1_pins>;
+	wp-gpios = <&gpio4 30 GPIO_ACTIVE_HIGH>;		/* gpio_126 */
+	cd-gpios = <&gpio4 14 IRQ_TYPE_LEVEL_LOW>;		/* gpio_110 */
+	vmmc-supply = <&vmmc1>;
+	bus-width = <4>;
+	cap-power-off-card;
+};
+
+&omap3_pmx_core {
+	gpio_key_pins: pinmux_gpio_key_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x212e, PIN_INPUT_PULLUP | MUX_MODE4)	/* cam_xclkb.gpio_111 / uP_GPIO_3*/
+		>;
+	};
+
+	led_pins: pinmux_led_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x215e, PIN_OUTPUT_PULLUP | MUX_MODE4)	/* sdmmc2_dat1.gpio_133 / uP_GPIO_0 */
+		>;
+	};
+
+	lan9221_pins: pinmux_lan9221_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT_PULLUP | MUX_MODE4)	/* mcbsp4_clkx.gpio_152 */
+		>;
+	};
+
+	mmc1_pins: pinmux_mmc1_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2144, PIN_OUTPUT | MUX_MODE0)	/* sdmmc1_clk.sdmmc1_clk */
+			OMAP3_CORE1_IOPAD(0x2146, PIN_INPUT | MUX_MODE0)	/* sdmmc1_cmd.sdmmc1_cmd */
+			OMAP3_CORE1_IOPAD(0x2148, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat0.sdmmc1_dat0 */
+			OMAP3_CORE1_IOPAD(0x214a, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat1.sdmmc1_dat1 */
+			OMAP3_CORE1_IOPAD(0x214c, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat2.sdmmc1_dat2 */
+			OMAP3_CORE1_IOPAD(0x214e, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat3.sdmmc1_dat3 */
+			OMAP3_CORE1_IOPAD(0x2132, PIN_INPUT_PULLUP | MUX_MODE4)	/* cam_strobe.gpio_126 */
+			OMAP3_CORE1_IOPAD(0x212c, PIN_INPUT_PULLUP | MUX_MODE4)	/* cam_d11.gpio_110 */
+		>;
+	};
+
+	lcd_enable_pin: pinmux_lcd_enable_pin {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x218a, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE4)       /* mcbsp4_fs.gpio_155 */
+		>;
+	};
+
+	dss_dpi_pins1: pinmux_dss_dpi_pins1 {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_pclk.dss_pclk */
+			OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_hsync.dss_hsync */
+			OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_vsync.dss_vsync */
+			OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_acbias.dss_acbias */
+
+			OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data0.dss_data0 */
+			OMAP3_CORE1_IOPAD(0x20de, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data1.dss_data1 */
+			OMAP3_CORE1_IOPAD(0x20e0, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data2.dss_data2 */
+			OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data3.dss_data3 */
+			OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data4.dss_data4 */
+			OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data5.dss_data5 */
+			OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data6.dss_data6 */
+			OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data7.dss_data7 */
+			OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data8.dss_data8 */
+			OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data9.dss_data9 */
+			OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data10.dss_data10 */
+			OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data11.dss_data11 */
+			OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data12.dss_data12 */
+			OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data13.dss_data13 */
+			OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data14.dss_data14 */
+			OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data15.dss_data15 */
+		>;
+	};
+};
+
+&omap3_pmx_wkup {
+	led_pins_wkup: pinmux_led_pins_wkup {
+		pinctrl-single,pins = <
+			OMAP3_WKUP_IOPAD(0x2a24, PIN_OUTPUT_PULLUP | MUX_MODE4)	/* jtag_emu0.gpio_11 / uP_GPIO_1 */
+		>;
+	};
+
+	backlight_pins: pinmux_backlight_pins {
+		pinctrl-single,pins = <
+			OMAP3_WKUP_IOPAD(0x2a16, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE4)       /* sys_boot6.gpio_8 */
+		>;
+	};
+};
+
+
+&uart1 {
+	interrupts-extended = <&intc 72 &omap3_pmx_core OMAP3_UART1_RX>;
+};
+
+/* Wired to the tps65950 on the SOM, only the USB connector is on the devkit */
+&usb_otg_hs {
+	pinctrl-names = "default";
+	pinctrl-0 = <&hsusb_otg_pins>;
+	interface-type = <0>;
+	usb-phy = <&usb2_phy>;
+	phys = <&usb2_phy>;
+	phy-names = "usb2-phy";
+	mode = <3>;
+	power = <50>;
+};
diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index 26cce4d18405..c1aa7a4518fb 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -33,11 +33,12 @@
 	hsusb2_phy: hsusb2_phy {
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>; /* gpio_4 */
+		#phy-cells = <0>;
 	};
 };
 
 &gpmc {
-	ranges = <0 0 0x00000000 0x1000000>;	/* CS0: 16MB for NAND */
+	ranges = <0 0 0x30000000 0x1000000>;	/* CS0: 16MB for NAND */
 
 	nand@0,0 {
 		compatible = "ti,omap2-nand";
@@ -66,33 +67,6 @@
 		gpmc,device-width = <2>;
 		#address-cells = <1>;
 		#size-cells = <1>;
-
-		/* u-boot uses mtdparts=omap2-nand.0:512k(x-loader),1920k(u-boot),128k(u-boot-env),4m(kernel),-(fs) */
-
-		x-loader@0 {
-			label = "x-loader";
-			reg = <0 0x80000>;
-		};
-
-		bootloaders@80000 {
-			label = "u-boot";
-			reg = <0x80000 0x1e0000>;
-		};
-
-		bootloaders_env@260000 {
-			label = "u-boot-env";
-			reg = <0x260000 0x20000>;
-		};
-
-		kernel@280000 {
-			label = "kernel";
-			reg = <0x280000 0x400000>;
-		};
-
-		filesystem@680000 {
-			label = "fs";
-			reg = <0x680000 0>;	/* 0 = MTDPART_SIZ_FULL */
-		};
 	};
 };
 
@@ -121,7 +95,7 @@
 
 &mmc3 {
 	interrupts-extended = <&intc 94 &omap3_pmx_core2 0x46>;
-	pinctrl-0 = <&mmc3_pins>;
+	pinctrl-0 = <&mmc3_pins &wl127x_gpio>;
 	pinctrl-names = "default";
 	vmmc-supply = <&wl12xx_vmmc>;
 	non-removable;
@@ -132,8 +106,8 @@
 	wlcore: wlcore@2 {
 		compatible = "ti,wl1273";
 		reg = <2>;
-		interrupt-parent = <&gpio5>;
-		interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */
+		interrupt-parent = <&gpio1>;
+		interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; /* gpio 2 */
 		ref-clock-frequency = <26000000>;
 	};
 };
@@ -157,8 +131,6 @@
 			OMAP3_CORE1_IOPAD(0x2166, PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc2_dat5.sdmmc3_dat1 */
 			OMAP3_CORE1_IOPAD(0x2168, PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc2_dat6.sdmmc3_dat2 */
 			OMAP3_CORE1_IOPAD(0x216a, PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc2_dat6.sdmmc3_dat3 */
-			OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT_PULLUP | MUX_MODE4)	/* mcbsp4_clkx.gpio_152 */
-			OMAP3_CORE1_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4)	/* sys_boot1.gpio_3 */
 			OMAP3_CORE1_IOPAD(0x21d0, PIN_INPUT_PULLUP | MUX_MODE3) /* mcspi1_cs1.sdmmc3_cmd */
 			OMAP3_CORE1_IOPAD(0x21d2, PIN_INPUT_PULLUP | MUX_MODE3)	/* mcspi1_cs2.sdmmc_clk */
 		>;
@@ -228,6 +200,12 @@
 			OMAP3_WKUP_IOPAD(0x2a0e, PIN_OUTPUT | MUX_MODE4)	/* sys_boot2.gpio_4 */
 		>;
 	};
+	wl127x_gpio: pinmux_wl127x_gpio_pin {
+		pinctrl-single,pins = <
+			OMAP3_WKUP_IOPAD(0x2a0c, PIN_INPUT | MUX_MODE4)		/* sys_boot0.gpio_2 */
+			OMAP3_WKUP_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4)	/* sys_boot1.gpio_3 */
+		>;
+	};
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/logicpd-torpedo-35xx-devkit.dts b/arch/arm/boot/dts/logicpd-torpedo-35xx-devkit.dts
new file mode 100644
index 000000000000..d7cb659656ce
--- /dev/null
+++ b/arch/arm/boot/dts/logicpd-torpedo-35xx-devkit.dts
@@ -0,0 +1,17 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/dts-v1/;
+
+#include "omap34xx.dtsi"
+#include "logicpd-torpedo-som.dtsi"
+#include "logicpd-torpedo-baseboard.dtsi"
+#include "omap-gpmc-smsc9221.dtsi"
+
+/ {
+	model = "LogicPD Zoom OMAP35xx Torpedo Development Kit";
+	compatible = "logicpd,dm3730-torpedo-devkit", "ti,omap3";
+};
diff --git a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
index b4575bbaf085..234afd6d60ec 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
+++ b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
@@ -9,396 +9,69 @@
 #include "omap36xx.dtsi"
 #include "logicpd-torpedo-som.dtsi"
 #include "omap-gpmc-smsc9221.dtsi"
+#include "logicpd-torpedo-baseboard.dtsi"
 
 / {
 	model = "LogicPD Zoom DM3730 Torpedo + Wireless Development Kit";
 	compatible = "logicpd,dm3730-torpedo-devkit", "ti,omap3630", "ti,omap3";
 
-	gpio_keys {
-		compatible = "gpio-keys";
-		pinctrl-names = "default";
-		pinctrl-0 = <&gpio_key_pins &gpio_key_pins_wkup>;
-
-		sysboot2 {
-			label = "sysboot2";
-			gpios = <&gpio1 2 GPIO_ACTIVE_LOW>;	/* gpio2 */
-			linux,code = <BTN_0>;
-			wakeup-source;
-		};
-
-		sysboot5 {
-			label = "sysboot5";
-			gpios = <&gpio1 7 GPIO_ACTIVE_LOW>;	/* gpio7 */
-			linux,code = <BTN_1>;
-			wakeup-source;
-		};
-
-		gpio1 {
-			label = "gpio1";
-			gpios = <&gpio6 21 GPIO_ACTIVE_LOW>;	/* gpio181 */
-			linux,code = <BTN_2>;
-			wakeup-source;
-		};
-
-		gpio2 {
-			label = "gpio2";
-			gpios = <&gpio6 18 GPIO_ACTIVE_LOW>;	/* gpio178 */
-			linux,code = <BTN_3>;
-			wakeup-source;
-		};
-	};
-
-	sound {
-		compatible = "ti,omap-twl4030";
-		ti,model = "omap3logic";
-		ti,mcbsp = <&mcbsp2>;
-	};
-
-	leds {
-		compatible = "gpio-leds";
-		pinctrl-names = "default";
-		pinctrl-0 = <&led_pins>;
-
-		led1 {
-			label = "led1";
-			gpios = <&gpio6 20 GPIO_ACTIVE_HIGH>;	/* gpio180 */
-			linux,default-trigger = "cpu0";
-		};
-
-		led2 {
-			label = "led2";
-			gpios = <&gpio6 19 GPIO_ACTIVE_HIGH>;	/* gpio179 */
-			linux,default-trigger = "none";
-		};
-	};
-
-	pwm10: dmtimer-pwm {
-		compatible = "ti,omap-dmtimer-pwm";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pwm_pins>;
-		ti,timers = <&timer10>;
-		#pwm-cells = <3>;
-	};
-
-};
-
-&vaux1 {
-	regulator-min-microvolt = <3000000>;
-	regulator-max-microvolt = <3000000>;
-};
-
-&vaux4 {
-	regulator-min-microvolt = <1800000>;
-	regulator-max-microvolt = <1800000>;
-};
-
-&mcbsp2 {
-	status = "okay";
-};
-
-&charger {
-	ti,bb-uvolt = <3200000>;
-	ti,bb-uamp = <150>;
-};
-
-&gpmc {
-	ranges = <0 0 0x30000000 0x1000000	/* CS0: 16MB for NAND */
-		  1 0 0x2c000000 0x1000000>;	/* CS1: 16MB for LAN9221 */
-
-	ethernet@gpmc {
-		pinctrl-names = "default";
-		pinctrl-0 = <&lan9221_pins>;
-		interrupt-parent = <&gpio5>;
-		interrupts = <1 IRQ_TYPE_LEVEL_LOW>;		/* gpio129 */
-		reg = <1 0 0xff>;
-	};
-};
-
-&vpll2 {
-	regulator-always-on;
-};
-
-&dss {
-	status = "ok";
-	vdds_dsi-supply = <&vpll2>;
-	vdda_video-supply = <&video_reg>;
-	pinctrl-names = "default";
-	pinctrl-0 = <&dss_dpi_pins1>;
-	port {
-		dpi_out: endpoint {
-			remote-endpoint = <&lcd_in>;
-			data-lines = <16>;
-		};
-	};
-};
-
-/ {
-	aliases {
-		display0 = &lcd0;
-	};
-
-	video_reg: video_reg {
-		pinctrl-names = "default";
-		pinctrl-0 = <&panel_pwr_pins>;
+	wl12xx_vmmc: wl12xx_vmmc {
 		compatible = "regulator-fixed";
-		regulator-name = "fixed-supply";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		gpio = <&gpio5 27 GPIO_ACTIVE_HIGH>;	/* gpio155, lcd INI */
-	};
-
-	lcd0: display {
-		compatible = "panel-dpi";
-		label = "15";
-		status = "okay";
-		/* default-on; */
-		pinctrl-names = "default";
-
-		port {
-			lcd_in: endpoint {
-				remote-endpoint = <&dpi_out>;
-			};
-		};
-
-		panel-timing {
-			clock-frequency = <9000000>;
-			hactive = <480>;
-			vactive = <272>;
-			hfront-porch = <3>;
-			hback-porch = <2>;
-			hsync-len = <42>;
-			vback-porch = <3>;
-			vfront-porch = <4>;
-			vsync-len = <11>;
-			hsync-active = <0>;
-			vsync-active = <0>;
-			de-active = <1>;
-			pixelclk-active = <1>;
-		};
-	};
-
-	bl: backlight {
-		compatible = "pwm-backlight";
-		pinctrl-names = "default";
-		pinctrl-0 = <&backlight_pins>;
-		pwms = <&pwm10 0 5000000 0>;
-		brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>;
-		default-brightness-level = <7>;
-		enable-gpios = <&gpio5 26 GPIO_ACTIVE_HIGH>; /* gpio_154 */
+		regulator-name = "vwl1271";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		gpio = <&gpio5 29 0>;   /* gpio157 */
+		startup-delay-us = <70000>;
+		enable-active-high;
+		vin-supply = <&vmmc2>;
 	};
 };
 
-&mmc1 {
-	interrupts-extended = <&intc 83 &omap3_pmx_core 0x11a>;
+/*
+ * Only found on the wireless SOM. For the SOM without wireless, the pins for
+ * MMC3 can be routed with jumpers to the second MMC slot on the devkit and
+ * gpio157 is not connected. So this should be OK to keep common for now,
+ * probably device tree overlays is the way to go with the various SOM and
+ * jumpering combinations for the long run.
+ */
+&mmc3 {
+	interrupts-extended = <&intc 94 &omap3_pmx_core2 0x46>;
+	pinctrl-0 = <&mmc3_pins &mmc3_core2_pins>;
 	pinctrl-names = "default";
-	pinctrl-0 = <&mmc1_pins &mmc1_cd>;
-	cd-gpios = <&gpio4 31 GPIO_ACTIVE_LOW>;		/* gpio127 */
-	vmmc-supply = <&vmmc1>;
+	vmmc-supply = <&wl12xx_vmmc>;
+	non-removable;
 	bus-width = <4>;
 	cap-power-off-card;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	wlcore: wlcore@2 {
+		compatible = "ti,wl1283";
+		reg = <2>;
+		interrupt-parent = <&gpio5>;
+		interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */
+		ref-clock-frequency = <26000000>;
+		tcxo-clock-frequency = <26000000>;
+	};
 };
 
 &omap3_pmx_core {
-	gpio_key_pins: pinmux_gpio_key_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x21d6, PIN_INPUT_PULLUP | MUX_MODE4)	/* mcspi2_clk.gpio_178 */
-			OMAP3_CORE1_IOPAD(0x21dc, PIN_INPUT_PULLUP | MUX_MODE4)	/* mcspi2_cs0.gpio_181 */
-		>;
-	};
-
-	pwm_pins: pinmux_pwm_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x20B8, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE3)       /* gpmc_ncs5.gpt_10_pwm_evt */
-		>;
-	};
-
-	led_pins: pinmux_led_pins {
+	mmc3_pins: pinmux_mm3_pins {
 		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x21d8, PIN_OUTPUT | MUX_MODE4)	/* gpio_179 */
-			OMAP3_CORE1_IOPAD(0x21da, PIN_OUTPUT | MUX_MODE4)	/* gpio_180 */
-		>;
-	};
-
-	mmc1_pins: pinmux_mmc1_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x2144, PIN_OUTPUT | MUX_MODE0)	/* sdmmc1_clk.sdmmc1_clk */
-			OMAP3_CORE1_IOPAD(0x2146, PIN_INPUT | MUX_MODE0)	/* sdmmc1_cmd.sdmmc1_cmd */
-			OMAP3_CORE1_IOPAD(0x2148, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat0.sdmmc1_dat0 */
-			OMAP3_CORE1_IOPAD(0x214a, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat1.sdmmc1_dat1 */
-			OMAP3_CORE1_IOPAD(0x214c, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat2.sdmmc1_dat2 */
-			OMAP3_CORE1_IOPAD(0x214e, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat3.sdmmc1_dat3 */
-		>;
-	};
-
-	tsc2004_pins: pinmux_tsc2004_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE4)	/* mcbsp4_dr.gpio_153 */
-		>;
-	};
-
-	backlight_pins: pinmux_backlight_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE4)       /* mcbsp4_dx.gpio_154 */
-		>;
-	};
-
-	isp_pins: pinmux_isp_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x210c, PIN_INPUT | MUX_MODE0)   /* cam_hs.cam_hs */
-			OMAP3_CORE1_IOPAD(0x210e, PIN_INPUT | MUX_MODE0)   /* cam_vs.cam_vs */
-			OMAP3_CORE1_IOPAD(0x2110, PIN_INPUT | MUX_MODE0)   /* cam_xclka.cam_xclka */
-			OMAP3_CORE1_IOPAD(0x2112, PIN_INPUT | MUX_MODE0)   /* cam_pclk.cam_pclk */
-
-			OMAP3_CORE1_IOPAD(0x2116, PIN_INPUT | MUX_MODE0)   /* cam_d0.cam_d0 */
-			OMAP3_CORE1_IOPAD(0x2118, PIN_INPUT | MUX_MODE0)   /* cam_d1.cam_d1 */
-			OMAP3_CORE1_IOPAD(0x211a, PIN_INPUT | MUX_MODE0)   /* cam_d2.cam_d2 */
-			OMAP3_CORE1_IOPAD(0x211c, PIN_INPUT | MUX_MODE0)   /* cam_d3.cam_d3 */
-			OMAP3_CORE1_IOPAD(0x211e, PIN_INPUT | MUX_MODE0)   /* cam_d4.cam_d4 */
-			OMAP3_CORE1_IOPAD(0x2120, PIN_INPUT | MUX_MODE0)   /* cam_d5.cam_d5 */
-			OMAP3_CORE1_IOPAD(0x2122, PIN_INPUT | MUX_MODE0)   /* cam_d6.cam_d6 */
-			OMAP3_CORE1_IOPAD(0x2124, PIN_INPUT | MUX_MODE0)   /* cam_d7.cam_d7 */
-		>;
-	};
-
-	panel_pwr_pins: pinmux_panel_pwr_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x218a, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE4)       /* mcbsp4_fs.gpio_155 */
-		>;
-	};
-
-	dss_dpi_pins1: pinmux_dss_dpi_pins1 {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_pclk.dss_pclk */
-			OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_hsync.dss_hsync */
-			OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_vsync.dss_vsync */
-			OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_acbias.dss_acbias */
-
-			OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data6.dss_data6 */
-			OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data7.dss_data7 */
-			OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data8.dss_data8 */
-			OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data9.dss_data9 */
-			OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data10.dss_data10 */
-			OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data11.dss_data11 */
-			OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data12.dss_data12 */
-			OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data13.dss_data13 */
-			OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data14.dss_data14 */
-			OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data15.dss_data15 */
-			OMAP3_CORE1_IOPAD(0x20fc, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data16.dss_data16 */
-			OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data17.dss_data17 */
-
-			OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data18.dss_data0 */
-			OMAP3_CORE1_IOPAD(0x2102, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data19.dss_data1 */
-			OMAP3_CORE1_IOPAD(0x2104, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data20.dss_data2 */
-			OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data21.dss_data3 */
-			OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data22.dss_data4 */
-			OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data23.dss_data5 */
+			OMAP3_CORE1_IOPAD(0x2164, PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc2_dat4.sdmmc3_dat0 */
+			OMAP3_CORE1_IOPAD(0x2166, PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc2_dat5.sdmmc3_dat1 */
+			OMAP3_CORE1_IOPAD(0x2168, PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc2_dat6.sdmmc3_dat2 */
+			OMAP3_CORE1_IOPAD(0x216a, PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc2_dat6.sdmmc3_dat3 */
+			OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT_PULLUP | MUX_MODE4)	/* mcbsp4_clkx.gpio_152 */
+			OMAP3_CORE1_IOPAD(0x218e, PIN_OUTPUT | MUX_MODE4)	/* mcbsp1_fsr.gpio_157 */
 		>;
 	};
 };
 
-&omap3_pmx_wkup {
-	gpio_key_pins_wkup: pinmux_gpio_key_pins_wkup {
-		pinctrl-single,pins = <
-			OMAP3_WKUP_IOPAD(0x2a0a, PIN_INPUT_PULLUP | MUX_MODE4)	/* sys_boot0.gpio_2 */
-			OMAP3_WKUP_IOPAD(0x2a14, PIN_INPUT_PULLUP | MUX_MODE4)	/* sys_boot5.gpio_7 */
-		>;
-	};
-
-	lan9221_pins: pinmux_lan9221_pins {
-		pinctrl-single,pins = <
-			OMAP3_WKUP_IOPAD(0x2a5a, PIN_INPUT | MUX_MODE4)		/* reserved.gpio_129 */
-		>;
-	};
-
-	mmc1_cd: pinmux_mmc1_cd {
+&omap3_pmx_core2 {
+	mmc3_core2_pins: pinmux_mmc3_core2_pins {
 		pinctrl-single,pins = <
-			OMAP3_WKUP_IOPAD(0x2a54, PIN_INPUT_PULLUP | MUX_MODE4)	/* reserved.gpio_127 */
+			OMAP3630_CORE2_IOPAD(0x25d8, PIN_INPUT_PULLUP | MUX_MODE2)   /* etk_clk.sdmmc3_clk */
+			OMAP3630_CORE2_IOPAD(0x25da, PIN_INPUT_PULLUP | MUX_MODE2)   /* etk_ctl.sdmmc3_cmd */
 		>;
 	};
 };
-
-&i2c2 {
-	mt9p031@48 {
-		compatible = "aptina,mt9p031";
-		reg = <0x48>;
-		clocks = <&isp 0>;
-		vaa-supply = <&vaux4>;
-		vdd-supply = <&vaux4>;
-		vdd_io-supply = <&vaux4>;
-		port {
-			mt9p031_out: endpoint {
-				input-clock-frequency = <24000000>;
-				pixel-clock-frequency = <72000000>;
-				remote-endpoint = <&ccdc_ep>;
-			};
-		};
-	};
-};
-
-&i2c3 {
-	touchscreen: tsc2004@48 {
-		compatible = "ti,tsc2004";
-		reg = <0x48>;
-		vio-supply = <&vaux1>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&tsc2004_pins>;
-		interrupts-extended = <&gpio5 25 IRQ_TYPE_EDGE_RISING>; /* gpio 153 */
-
-		touchscreen-fuzz-x = <4>;
-		touchscreen-fuzz-y = <7>;
-		touchscreen-fuzz-pressure = <2>;
-		touchscreen-size-x = <4096>;
-		touchscreen-size-y = <4096>;
-		touchscreen-max-pressure = <2048>;
-
-		ti,x-plate-ohms = <280>;
-		ti,esd-recovery-timeout-ms = <8000>;
-	};
-};
-
-&mcspi1 {
-	at25@0 {
-		compatible = "atmel,at25";
-		reg = <0>;
-		spi-max-frequency = <5000000>;
-		spi-cpha;
-		spi-cpol;
-
-		pagesize = <64>;
-		size = <32768>;
-		address-width = <16>;
-	};
-};
-
-&isp {
-	pinctrl-names = "default";
-	pinctrl-0 = <&isp_pins>;
-	ports {
-		port@0 {
-			reg = <0>;
-			ccdc_ep: endpoint {
-				remote-endpoint = <&mt9p031_out>;
-				bus-width = <8>;
-				hsync-active = <1>;
-				vsync-active = <1>;
-				pclk-sample = <0>;
-			};
-		};
-	};
-};
-
-&uart1 {
-	interrupts-extended = <&intc 72 &omap3_pmx_core OMAP3_UART1_RX>;
-};
-
-/* Wired to the tps65950 on the SOM, only the USB connector is on the devkit */
-&usb_otg_hs {
-	pinctrl-names = "default";
-	pinctrl-0 = <&hsusb_otg_pins>;
-	interface-type = <0>;
-	usb-phy = <&usb2_phy>;
-	phys = <&usb2_phy>;
-	phy-names = "usb2-phy";
-	mode = <3>;
-	power = <50>;
-};
diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
new file mode 100644
index 000000000000..86c5644f558c
--- /dev/null
+++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
@@ -0,0 +1,395 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/ {
+	gpio_keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&gpio_key_pins &gpio_key_pins_wkup>;
+
+		sysboot2 {
+			label = "sysboot2";
+			gpios = <&gpio1 2 GPIO_ACTIVE_LOW>;	/* gpio2 */
+			linux,code = <BTN_0>;
+			wakeup-source;
+		};
+
+		sysboot5 {
+			label = "sysboot5";
+			gpios = <&gpio1 7 GPIO_ACTIVE_LOW>;	/* gpio7 */
+			linux,code = <BTN_1>;
+			wakeup-source;
+		};
+
+		gpio1 {
+			label = "gpio1";
+			gpios = <&gpio6 21 GPIO_ACTIVE_LOW>;	/* gpio181 */
+			linux,code = <BTN_2>;
+			wakeup-source;
+		};
+
+		gpio2 {
+			label = "gpio2";
+			gpios = <&gpio6 18 GPIO_ACTIVE_LOW>;	/* gpio178 */
+			linux,code = <BTN_3>;
+			wakeup-source;
+		};
+	};
+
+	sound {
+		compatible = "ti,omap-twl4030";
+		ti,model = "omap3logic";
+		ti,mcbsp = <&mcbsp2>;
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led_pins>;
+
+		led1 {
+			label = "led1";
+			gpios = <&gpio6 20 GPIO_ACTIVE_HIGH>;	/* gpio180 */
+			linux,default-trigger = "cpu0";
+		};
+
+		led2 {
+			label = "led2";
+			gpios = <&gpio6 19 GPIO_ACTIVE_HIGH>;	/* gpio179 */
+			linux,default-trigger = "none";
+		};
+	};
+
+	pwm10: dmtimer-pwm {
+		compatible = "ti,omap-dmtimer-pwm";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pwm_pins>;
+		ti,timers = <&timer10>;
+		#pwm-cells = <3>;
+	};
+
+};
+
+&vaux1 {
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+};
+
+&vaux4 {
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
+};
+
+&mcbsp2 {
+	status = "okay";
+};
+
+&charger {
+	ti,bb-uvolt = <3200000>;
+	ti,bb-uamp = <150>;
+};
+
+&gpmc {
+	ranges = <0 0 0x30000000 0x1000000	/* CS0: 16MB for NAND */
+		  1 0 0x2c000000 0x1000000>;	/* CS1: 16MB for LAN9221 */
+
+	ethernet@gpmc {
+		pinctrl-names = "default";
+		pinctrl-0 = <&lan9221_pins>;
+		interrupt-parent = <&gpio5>;
+		interrupts = <1 IRQ_TYPE_LEVEL_LOW>;		/* gpio129 */
+		reg = <1 0 0xff>;
+	};
+};
+
+&vpll2 {
+	regulator-always-on;
+};
+
+&dss {
+	status = "ok";
+	vdds_dsi-supply = <&vpll2>;
+	vdda_video-supply = <&video_reg>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&dss_dpi_pins1>;
+	port {
+		dpi_out: endpoint {
+			remote-endpoint = <&lcd_in>;
+			data-lines = <16>;
+		};
+	};
+};
+
+/ {
+	aliases {
+		display0 = &lcd0;
+	};
+
+	video_reg: video_reg {
+		pinctrl-names = "default";
+		pinctrl-0 = <&panel_pwr_pins>;
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-supply";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio5 27 GPIO_ACTIVE_HIGH>;	/* gpio155, lcd INI */
+	};
+
+	lcd0: display {
+		compatible = "panel-dpi";
+		label = "15";
+		status = "okay";
+		/* default-on; */
+		pinctrl-names = "default";
+
+		port {
+			lcd_in: endpoint {
+				remote-endpoint = <&dpi_out>;
+			};
+		};
+
+		panel-timing {
+			clock-frequency = <9000000>;
+			hactive = <480>;
+			vactive = <272>;
+			hfront-porch = <3>;
+			hback-porch = <2>;
+			hsync-len = <42>;
+			vback-porch = <3>;
+			vfront-porch = <4>;
+			vsync-len = <11>;
+			hsync-active = <0>;
+			vsync-active = <0>;
+			de-active = <1>;
+			pixelclk-active = <1>;
+		};
+	};
+
+	bl: backlight {
+		compatible = "pwm-backlight";
+		pinctrl-names = "default";
+		pinctrl-0 = <&backlight_pins>;
+		pwms = <&pwm10 0 5000000 0>;
+		brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>;
+		default-brightness-level = <7>;
+		enable-gpios = <&gpio5 26 GPIO_ACTIVE_HIGH>; /* gpio_154 */
+	};
+};
+
+&mmc1 {
+	interrupts-extended = <&intc 83 &omap3_pmx_core 0x11a>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc1_pins &mmc1_cd>;
+	cd-gpios = <&gpio4 31 GPIO_ACTIVE_LOW>;		/* gpio127 */
+	vmmc-supply = <&vmmc1>;
+	bus-width = <4>;
+	cap-power-off-card;
+};
+
+&omap3_pmx_core {
+	gpio_key_pins: pinmux_gpio_key_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21d6, PIN_INPUT_PULLUP | MUX_MODE4)	/* mcspi2_clk.gpio_178 */
+			OMAP3_CORE1_IOPAD(0x21dc, PIN_INPUT_PULLUP | MUX_MODE4)	/* mcspi2_cs0.gpio_181 */
+		>;
+	};
+
+	pwm_pins: pinmux_pwm_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20B8, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE3)       /* gpmc_ncs5.gpt_10_pwm_evt */
+		>;
+	};
+
+	led_pins: pinmux_led_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21d8, PIN_OUTPUT | MUX_MODE4)	/* gpio_179 */
+			OMAP3_CORE1_IOPAD(0x21da, PIN_OUTPUT | MUX_MODE4)	/* gpio_180 */
+		>;
+	};
+
+	mmc1_pins: pinmux_mmc1_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2144, PIN_OUTPUT | MUX_MODE0)	/* sdmmc1_clk.sdmmc1_clk */
+			OMAP3_CORE1_IOPAD(0x2146, PIN_INPUT | MUX_MODE0)	/* sdmmc1_cmd.sdmmc1_cmd */
+			OMAP3_CORE1_IOPAD(0x2148, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat0.sdmmc1_dat0 */
+			OMAP3_CORE1_IOPAD(0x214a, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat1.sdmmc1_dat1 */
+			OMAP3_CORE1_IOPAD(0x214c, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat2.sdmmc1_dat2 */
+			OMAP3_CORE1_IOPAD(0x214e, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat3.sdmmc1_dat3 */
+		>;
+	};
+
+	tsc2004_pins: pinmux_tsc2004_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE4)	/* mcbsp4_dr.gpio_153 */
+		>;
+	};
+
+	backlight_pins: pinmux_backlight_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE4)       /* mcbsp4_dx.gpio_154 */
+		>;
+	};
+
+	isp_pins: pinmux_isp_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x210c, PIN_INPUT | MUX_MODE0)   /* cam_hs.cam_hs */
+			OMAP3_CORE1_IOPAD(0x210e, PIN_INPUT | MUX_MODE0)   /* cam_vs.cam_vs */
+			OMAP3_CORE1_IOPAD(0x2110, PIN_INPUT | MUX_MODE0)   /* cam_xclka.cam_xclka */
+			OMAP3_CORE1_IOPAD(0x2112, PIN_INPUT | MUX_MODE0)   /* cam_pclk.cam_pclk */
+
+			OMAP3_CORE1_IOPAD(0x2116, PIN_INPUT | MUX_MODE0)   /* cam_d0.cam_d0 */
+			OMAP3_CORE1_IOPAD(0x2118, PIN_INPUT | MUX_MODE0)   /* cam_d1.cam_d1 */
+			OMAP3_CORE1_IOPAD(0x211a, PIN_INPUT | MUX_MODE0)   /* cam_d2.cam_d2 */
+			OMAP3_CORE1_IOPAD(0x211c, PIN_INPUT | MUX_MODE0)   /* cam_d3.cam_d3 */
+			OMAP3_CORE1_IOPAD(0x211e, PIN_INPUT | MUX_MODE0)   /* cam_d4.cam_d4 */
+			OMAP3_CORE1_IOPAD(0x2120, PIN_INPUT | MUX_MODE0)   /* cam_d5.cam_d5 */
+			OMAP3_CORE1_IOPAD(0x2122, PIN_INPUT | MUX_MODE0)   /* cam_d6.cam_d6 */
+			OMAP3_CORE1_IOPAD(0x2124, PIN_INPUT | MUX_MODE0)   /* cam_d7.cam_d7 */
+		>;
+	};
+
+	panel_pwr_pins: pinmux_panel_pwr_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x218a, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE4)       /* mcbsp4_fs.gpio_155 */
+		>;
+	};
+
+	dss_dpi_pins1: pinmux_dss_dpi_pins1 {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_pclk.dss_pclk */
+			OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_hsync.dss_hsync */
+			OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_vsync.dss_vsync */
+			OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_acbias.dss_acbias */
+
+			OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data6.dss_data6 */
+			OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data7.dss_data7 */
+			OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data8.dss_data8 */
+			OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data9.dss_data9 */
+			OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data10.dss_data10 */
+			OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data11.dss_data11 */
+			OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data12.dss_data12 */
+			OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data13.dss_data13 */
+			OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data14.dss_data14 */
+			OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data15.dss_data15 */
+			OMAP3_CORE1_IOPAD(0x20fc, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data16.dss_data16 */
+			OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE0)   /* dss_data17.dss_data17 */
+
+			OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data18.dss_data0 */
+			OMAP3_CORE1_IOPAD(0x2102, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data19.dss_data1 */
+			OMAP3_CORE1_IOPAD(0x2104, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data20.dss_data2 */
+			OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data21.dss_data3 */
+			OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data22.dss_data4 */
+			OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT_PULLDOWN | PIN_OFF_OUTPUT_LOW | MUX_MODE3)   /* dss_data23.dss_data5 */
+		>;
+	};
+};
+
+&omap3_pmx_wkup {
+	gpio_key_pins_wkup: pinmux_gpio_key_pins_wkup {
+		pinctrl-single,pins = <
+			OMAP3_WKUP_IOPAD(0x2a0a, PIN_INPUT_PULLUP | MUX_MODE4)	/* sys_boot0.gpio_2 */
+			OMAP3_WKUP_IOPAD(0x2a14, PIN_INPUT_PULLUP | MUX_MODE4)	/* sys_boot5.gpio_7 */
+		>;
+	};
+
+	lan9221_pins: pinmux_lan9221_pins {
+		pinctrl-single,pins = <
+			OMAP3_WKUP_IOPAD(0x2a5a, PIN_INPUT | MUX_MODE4)		/* reserved.gpio_129 */
+		>;
+	};
+
+	mmc1_cd: pinmux_mmc1_cd {
+		pinctrl-single,pins = <
+			OMAP3_WKUP_IOPAD(0x2a54, PIN_INPUT_PULLUP | MUX_MODE4)	/* reserved.gpio_127 */
+		>;
+	};
+};
+
+&i2c2 {
+	mt9p031@48 {
+		compatible = "aptina,mt9p031";
+		reg = <0x48>;
+		clocks = <&isp 0>;
+		vaa-supply = <&vaux4>;
+		vdd-supply = <&vaux4>;
+		vdd_io-supply = <&vaux4>;
+		port {
+			mt9p031_out: endpoint {
+				input-clock-frequency = <24000000>;
+				pixel-clock-frequency = <72000000>;
+				remote-endpoint = <&ccdc_ep>;
+			};
+		};
+	};
+};
+
+&i2c3 {
+	touchscreen: tsc2004@48 {
+		compatible = "ti,tsc2004";
+		reg = <0x48>;
+		vio-supply = <&vaux1>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&tsc2004_pins>;
+		interrupts-extended = <&gpio5 25 IRQ_TYPE_EDGE_RISING>; /* gpio 153 */
+
+		touchscreen-fuzz-x = <4>;
+		touchscreen-fuzz-y = <7>;
+		touchscreen-fuzz-pressure = <2>;
+		touchscreen-size-x = <4096>;
+		touchscreen-size-y = <4096>;
+		touchscreen-max-pressure = <2048>;
+
+		ti,x-plate-ohms = <280>;
+		ti,esd-recovery-timeout-ms = <8000>;
+	};
+};
+
+&mcspi1 {
+	at25@0 {
+		compatible = "atmel,at25";
+		reg = <0>;
+		spi-max-frequency = <5000000>;
+		spi-cpha;
+		spi-cpol;
+
+		pagesize = <64>;
+		size = <32768>;
+		address-width = <16>;
+	};
+};
+
+&isp {
+	pinctrl-names = "default";
+	pinctrl-0 = <&isp_pins>;
+	ports {
+		port@0 {
+			reg = <0>;
+			ccdc_ep: endpoint {
+				remote-endpoint = <&mt9p031_out>;
+				bus-width = <8>;
+				hsync-active = <1>;
+				vsync-active = <1>;
+				pclk-sample = <0>;
+			};
+		};
+	};
+};
+
+&uart1 {
+	interrupts-extended = <&intc 72 &omap3_pmx_core OMAP3_UART1_RX>;
+};
+
+/* Wired to the tps65950 on the SOM, only the USB connector is on the devkit */
+&usb_otg_hs {
+	pinctrl-names = "default";
+	pinctrl-0 = <&hsusb_otg_pins>;
+	interface-type = <0>;
+	usb-phy = <&usb2_phy>;
+	phys = <&usb2_phy>;
+	phy-names = "usb2-phy";
+	mode = <3>;
+	power = <50>;
+};
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 6d89736c7b44..b50b796e15c7 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -30,17 +30,6 @@
 			linux,default-trigger = "none";
 		};
 	};
-
-	wl12xx_vmmc: wl12xx_vmmc {
-		compatible = "regulator-fixed";
-		regulator-name = "vwl1271";
-		regulator-min-microvolt = <1800000>;
-		regulator-max-microvolt = <1800000>;
-		gpio = <&gpio5 29 0>;   /* gpio157 */
-		startup-delay-us = <70000>;
-		enable-active-high;
-		vin-supply = <&vmmc2>;
-	};
 };
 
 &gpmc {
@@ -73,33 +62,6 @@
 		gpmc,device-width = <2>;
 		#address-cells = <1>;
 		#size-cells = <1>;
-
-		/* u-boot uses mtdparts=omap2-nand.0:512k(x-loader),1920k(u-boot),128k(u-boot-env),4m(kernel),-(fs) */
-
-		x-loader@0 {
-			label = "x-loader";
-			reg = <0 0x80000>;
-		};
-
-		bootloaders@80000 {
-			label = "u-boot";
-			reg = <0x80000 0x1e0000>;
-		};
-
-		bootloaders_env@260000 {
-			label = "u-boot-env";
-			reg = <0x260000 0x20000>;
-		};
-
-		kernel@280000 {
-			label = "kernel";
-			reg = <0x280000 0x400000>;
-		};
-
-		filesystem@680000 {
-			label = "fs";
-			reg = <0x680000 0>;	/* 0 = MTDPART_SIZ_FULL */
-		};
 	};
 };
 
@@ -131,44 +93,7 @@
 	};
 };
 
-/*
- * Only found on the wireless SOM. For the SOM without wireless, the pins for
- * MMC3 can be routed with jumpers to the second MMC slot on the devkit and
- * gpio157 is not connected. So this should be OK to keep common for now,
- * probably device tree overlays is the way to go with the various SOM and
- * jumpering combinations for the long run.
- */
-&mmc3 {
-	interrupts-extended = <&intc 94 &omap3_pmx_core2 0x46>;
-	pinctrl-0 = <&mmc3_pins &mmc3_core2_pins>;
-	pinctrl-names = "default";
-	vmmc-supply = <&wl12xx_vmmc>;
-	non-removable;
-	bus-width = <4>;
-	cap-power-off-card;
-	#address-cells = <1>;
-	#size-cells = <0>;
-	wlcore: wlcore@2 {
-		compatible = "ti,wl1283";
-		reg = <2>;
-		interrupt-parent = <&gpio5>;
-		interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */
-		ref-clock-frequency = <26000000>;
-		tcxo-clock-frequency = <26000000>;
-	};
-};
-
 &omap3_pmx_core {
-	mmc3_pins: pinmux_mm3_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x2164, PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc2_dat4.sdmmc3_dat0 */
-			OMAP3_CORE1_IOPAD(0x2166, PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc2_dat5.sdmmc3_dat1 */
-			OMAP3_CORE1_IOPAD(0x2168, PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc2_dat6.sdmmc3_dat2 */
-			OMAP3_CORE1_IOPAD(0x216a, PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc2_dat6.sdmmc3_dat3 */
-			OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT_PULLUP | MUX_MODE4)	/* mcbsp4_clkx.gpio_152 */
-			OMAP3_CORE1_IOPAD(0x218e, PIN_OUTPUT | MUX_MODE4)	/* mcbsp1_fsr.gpio_157 */
-		>;
-	};
 	mcbsp2_pins: pinmux_mcbsp2_pins {
 		pinctrl-single,pins = <
 			OMAP3_CORE1_IOPAD(0x213c, PIN_INPUT | MUX_MODE0)        /* mcbsp2_fsx */
@@ -224,15 +149,6 @@
 	pinctrl-0 = <&mcspi1_pins>;
 };
 
-&omap3_pmx_core2 {
-	mmc3_core2_pins: pinmux_mmc3_core2_pins {
-		pinctrl-single,pins = <
-			OMAP3630_CORE2_IOPAD(0x25d8, PIN_INPUT_PULLUP | MUX_MODE2)   /* etk_clk.sdmmc3_clk */
-			OMAP3630_CORE2_IOPAD(0x25da, PIN_INPUT_PULLUP | MUX_MODE2)   /* etk_ctl.sdmmc3_cmd */
-		>;
-	};
-};
-
 #include "twl4030.dtsi"
 #include "twl4030_omap3.dtsi"
 
diff --git a/arch/arm/boot/dts/lpc3250-ea3250.dts b/arch/arm/boot/dts/lpc3250-ea3250.dts
index c43adb7b4d7c..58ea0a4e7afa 100644
--- a/arch/arm/boot/dts/lpc3250-ea3250.dts
+++ b/arch/arm/boot/dts/lpc3250-ea3250.dts
@@ -156,8 +156,8 @@
 	uda1380: uda1380@18 {
 		compatible = "nxp,uda1380";
 		reg = <0x18>;
-		power-gpio = <&gpio 0x59 0>;
-		reset-gpio = <&gpio 0x51 0>;
+		power-gpio = <&gpio 3 10 0>;
+		reset-gpio = <&gpio 3 2 0>;
 		dac-clk = "wspll";
 	};
 
diff --git a/arch/arm/boot/dts/lpc3250-phy3250.dts b/arch/arm/boot/dts/lpc3250-phy3250.dts
index c72eb9845603..1e1c2f517a82 100644
--- a/arch/arm/boot/dts/lpc3250-phy3250.dts
+++ b/arch/arm/boot/dts/lpc3250-phy3250.dts
@@ -81,8 +81,8 @@
 	uda1380: uda1380@18 {
 		compatible = "nxp,uda1380";
 		reg = <0x18>;
-		power-gpio = <&gpio 0x59 0>;
-		reset-gpio = <&gpio 0x51 0>;
+		power-gpio = <&gpio 3 10 0>;
+		reset-gpio = <&gpio 3 2 0>;
 		dac-clk = "wspll";
 	};
 
diff --git a/arch/arm/boot/dts/lpc4337-ciaa.dts b/arch/arm/boot/dts/lpc4337-ciaa.dts
index 7c16d639a1b4..beddaba85393 100644
--- a/arch/arm/boot/dts/lpc4337-ciaa.dts
+++ b/arch/arm/boot/dts/lpc4337-ciaa.dts
@@ -174,17 +174,17 @@
 	clock-frequency = <400000>;
 
 	eeprom@50 {
-		compatible = "microchip,24c512";
+		compatible = "microchip,24c512", "atmel,24c512";
 		reg = <0x50>;
 	};
 
 	eeprom@51 {
-		compatible = "microchip,24c02";
+		compatible = "microchip,24c02", "atmel,24c02";
 		reg = <0x51>;
 	};
 
 	eeprom@54 {
-		compatible = "microchip,24c512";
+		compatible = "microchip,24c512", "atmel,24c512";
 		reg = <0x54>;
 	};
 };
diff --git a/arch/arm/boot/dts/lpc4350-hitex-eval.dts b/arch/arm/boot/dts/lpc4350-hitex-eval.dts
index 874c75d44013..8b973f537d3a 100644
--- a/arch/arm/boot/dts/lpc4350-hitex-eval.dts
+++ b/arch/arm/boot/dts/lpc4350-hitex-eval.dts
@@ -429,7 +429,7 @@
 	};
 
 	eeprom@50 {
-		compatible = "nxp,24c02";
+		compatible = "nxp,24c02", "atmel,24c02";
 		reg = <0x50>;
 	};
 
diff --git a/arch/arm/boot/dts/lpc4357-ea4357-devkit.dts b/arch/arm/boot/dts/lpc4357-ea4357-devkit.dts
index 9b5fad622522..02b23fa29d75 100644
--- a/arch/arm/boot/dts/lpc4357-ea4357-devkit.dts
+++ b/arch/arm/boot/dts/lpc4357-ea4357-devkit.dts
@@ -490,7 +490,7 @@
 	};
 
 	eeprom@57 {
-		compatible = "microchip,24c64";
+		compatible = "microchip,24c64", "atmel,24c64";
 		reg = <0x57>;
 	};
 };
diff --git a/arch/arm/boot/dts/ls1021a-moxa-uc-8410a.dts b/arch/arm/boot/dts/ls1021a-moxa-uc-8410a.dts
new file mode 100644
index 000000000000..d01f64b252b1
--- /dev/null
+++ b/arch/arm/boot/dts/ls1021a-moxa-uc-8410a.dts
@@ -0,0 +1,241 @@
+/*
+ * Copyright (C) 2017 Moxa Inc. - https://www.moxa.com/
+ *
+ * Author: Harry YJ Jhou (周亞諄) <harryyj.jhou@moxa.com>
+ *         Jimmy Chen (陳永達)    <jimmy.chen@moxa.com>
+ *         SZ Lin (林上智)        <sz.lin@moxa.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include "ls1021a.dtsi"
+
+/ {
+	model = "Moxa UC-8410A";
+
+	aliases {
+		enet0_rgmii_phy = &rgmii_phy0;
+		enet1_rgmii_phy = &rgmii_phy1;
+		enet2_rgmii_phy = &rgmii_phy2;
+	};
+
+	sys_mclk: clock-mclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24576000>;
+	};
+
+	reg_3p3v: regulator-3p3v {
+		  compatible = "regulator-fixed";
+		  regulator-name = "3P3V";
+		  regulator-min-microvolt = <3300000>;
+		  regulator-max-microvolt = <3300000>;
+		  regulator-always-on;
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		cel-pwr {
+			label = "UC8410A:CEL-PWR";
+			gpios = <&gpio3 27 GPIO_ACTIVE_LOW>;
+			default-state = "off";
+		};
+
+		cel-reset {
+			label = "UC8410A:CEL-RESET";
+			gpios = <&gpio3 28 GPIO_ACTIVE_LOW>;
+			default-state = "off";
+		};
+
+		str-led {
+			label = "UC8410A:RED:PROG";
+			gpios = <&gpio0 16 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "mmc0";
+		};
+
+		sw-ready {
+			label = "UC8410A:GREEN:SWRDY";
+			gpios = <&gpio0 18 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+		};
+
+		beeper {
+			label = "UC8410A:BEEP";
+			gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		prog-led0 {
+			label = "UC8410A:GREEN:PROG2";
+			gpios = <&gpio3 14 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		prog-led1 {
+			label = "UC8410A:GREEN:PROG1";
+			gpios = <&gpio3 15 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		prog-led2 {
+			label = "UC8410A:GREEN:PROG0";
+			gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		wifi-signal0 {
+			label = "UC8410A:GREEN:CEL2";
+			gpios = <&gpio3 17 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		wifi-signal1 {
+			label = "UC8410A:GREEN:CEL1";
+			gpios = <&gpio3 18 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		wifi-signal2 {
+			label = "UC8410A:GREEN:CEL0";
+			gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		cpu-diag-red {
+			label = "UC8410A:RED:DIA";
+			gpios = <&gpio3 20 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		cpu-diag-green {
+			label = "UC8410A:GREEN:DIA";
+			gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		cpu-diag-yellow {
+			label = "UC8410A:YELLOW:DIA";
+			gpios = <&gpio3 22 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		pushbtn-key {
+			label = "push button key";
+			gpios = <&gpio1 21 GPIO_ACTIVE_LOW>;
+			linux,code = <BTN_MISC>;
+			default-state = "on";
+		};
+	};
+};
+
+&enet0 {
+	phy-handle = <&rgmii_phy0>;
+	phy-connection-type = "rgmii-id";
+	status = "okay";
+};
+
+&enet1 {
+	phy-handle = <&rgmii_phy1>;
+	phy-connection-type = "rgmii-id";
+	status = "okay";
+};
+
+&enet2 {
+	phy-handle = <&rgmii_phy2>;
+	phy-connection-type = "rgmii-id";
+	status = "okay";
+};
+
+&i2c0 {
+	clock-frequency = <100000>;
+	status = "okay";
+
+	tpm@20 {
+		compatible = "infineon,slb9635tt";
+		reg = <0x20>;
+	};
+
+	rtc@68 {
+		compatible = "dallas,ds1374";
+		reg = <0x68>;
+	};
+};
+
+&lpuart0 {
+	status = "okay";
+};
+
+&mdio0 {
+	rgmii_phy0: ethernet-phy@0 {
+		compatible = "marvell,88e1118";
+		reg = <0x0>;
+		marvell,reg-init =
+			<3 0x11 0 0x4415>, /* Reg 3,17 */
+			<3 0x10 0 0x77>; /* Reg 3,16 */
+	};
+
+	rgmii_phy1: ethernet-phy@1 {
+		compatible = "marvell,88e1118";
+		reg = <0x1>;
+		marvell,reg-init =
+			<3 0x11 0 0x4415>, /* Reg 3,17 */
+			<3 0x10 0 0x77>; /* Reg 3,16 */
+	};
+
+	rgmii_phy2: ethernet-phy@2 {
+		compatible = "marvell,88e1118";
+		reg = <0x2>;
+		marvell,reg-init =
+			<3 0x11 0 0x4415>, /* Reg 3,17 */
+			<3 0x10 0 0x77>; /* Reg 3,16 */
+	};
+};
+
+&qspi {
+	bus-num = <0>;
+	fsl,spi-num-chipselects = <2>;
+	fsl,spi-flash-chipselects = <0>;
+	fsl,qspi-has-second-chip;
+	status = "okay";
+
+	flash: flash@0 {
+		compatible = "spansion,s25fl064l", "spansion,s25fl164k";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		spi-max-frequency = <20000000>;
+		reg = <0>;
+
+		partitions@0 {
+			label = "U-Boot";
+			reg = <0x0 0x180000>;
+		};
+
+		partitions@180000 {
+			label = "U-Boot Env";
+			reg = <0x180000 0x680000>;
+		};
+	};
+};
+
+&sata {
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&uart1 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/ls1021a-qds.dts b/arch/arm/boot/dts/ls1021a-qds.dts
index 940875316d0f..499f41a2c6f0 100644
--- a/arch/arm/boot/dts/ls1021a-qds.dts
+++ b/arch/arm/boot/dts/ls1021a-qds.dts
@@ -215,7 +215,7 @@
 				reg = <0x2a>;
 				VDDA-supply = <&reg_3p3v>;
 				VDDIO-supply = <&reg_3p3v>;
-				clocks = <&sys_mclk 1>;
+				clocks = <&sys_mclk>;
 			};
 		};
 	};
@@ -239,6 +239,11 @@
 		device-width = <1>;
 	};
 
+	nand@2,0 {
+		compatible = "fsl,ifc-nand";
+		reg = <0x2 0x0 0x10000>;
+	};
+
 	fpga: board-control@3,0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -331,3 +336,19 @@
 &uart1 {
 	status = "okay";
 };
+
+&can0 {
+	status = "okay";
+};
+
+&can1 {
+	status = "okay";
+};
+
+&can2 {
+	status = "disabled";
+};
+
+&can3 {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/ls1021a-twr.dts b/arch/arm/boot/dts/ls1021a-twr.dts
index a8b148ad1dd2..f0c949d74833 100644
--- a/arch/arm/boot/dts/ls1021a-twr.dts
+++ b/arch/arm/boot/dts/ls1021a-twr.dts
@@ -187,7 +187,7 @@
 		reg = <0x0a>;
 		VDDA-supply = <&reg_3p3v>;
 		VDDIO-supply = <&reg_3p3v>;
-		clocks = <&sys_mclk 1>;
+		clocks = <&sys_mclk>;
 	};
 };
 
@@ -228,6 +228,10 @@
 	};
 };
 
+&esdhc {
+        status = "okay";
+};
+
 &sai1 {
 	status = "okay";
 };
@@ -243,3 +247,19 @@
 &uart1 {
 	status = "okay";
 };
+
+&can0 {
+	status = "okay";
+};
+
+&can1 {
+	status = "okay";
+};
+
+&can2 {
+	status = "disabled";
+};
+
+&can3 {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi
index 9319e1f0f1d8..c31dad98f989 100644
--- a/arch/arm/boot/dts/ls1021a.dtsi
+++ b/arch/arm/boot/dts/ls1021a.dtsi
@@ -106,6 +106,14 @@
 		compatible = "arm,cortex-a7-pmu";
 		interrupts = <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>, <&cpu1>;
+	};
+
+	reboot {
+		compatible = "syscon-reboot";
+		regmap = <&dcfg>;
+		offset = <0xb0>;
+		mask = <0x02>;
 	};
 
 	soc {
@@ -154,8 +162,22 @@
 			big-endian;
 		};
 
+		qspi: quadspi@1550000 {
+			compatible = "fsl,ls1021a-qspi";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x0 0x1550000 0x0 0x10000>,
+			      <0x0 0x40000000 0x0 0x40000000>;
+			reg-names = "QuadSPI", "QuadSPI-memory";
+			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
+			clock-names = "qspi_en", "qspi";
+			clocks = <&clockgen 4 1>, <&clockgen 4 1>;
+			big-endian;
+			status = "disabled";
+		};
+
 		esdhc: esdhc@1560000 {
-			compatible = "fsl,esdhc";
+			compatible = "fsl,ls1021a-esdhc", "fsl,esdhc";
 			reg = <0x0 0x1560000 0x0 0x10000>;
 			interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <0>;
@@ -575,7 +597,7 @@
 			fsl,tclk-period = <5>;
 			fsl,tmr-prsc    = <2>;
 			fsl,tmr-add     = <0xaaaaaaab>;
-			fsl,tmr-fiper1  = <999999990>;
+			fsl,tmr-fiper1  = <999999995>;
 			fsl,tmr-fiper2  = <99990>;
 			fsl,max-adj     = <499999999>;
 		};
@@ -668,7 +690,7 @@
 			};
 		};
 
-		usb@8600000 {
+		usb2: usb@8600000 {
 			compatible = "fsl-usb2-dr-v2.5", "fsl-usb2-dr";
 			reg = <0x0 0x8600000 0x0 0x1000>;
 			interrupts = <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>;
@@ -676,7 +698,7 @@
 			phy_type = "ulpi";
 		};
 
-		usb3@3100000 {
+		usb3: usb3@3100000 {
 			compatible = "snps,dwc3";
 			reg = <0x0 0x3100000 0x0 0x10000>;
 			interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>;
@@ -730,5 +752,41 @@
 					<0000 0 0 3 &gic GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>,
 					<0000 0 0 4 &gic GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH>;
 		};
+
+		can0: can@2a70000 {
+			compatible = "fsl,ls1021ar2-flexcan";
+			reg = <0x0 0x2a70000 0x0 0x1000>;
+			interrupts = <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clockgen 4 1>, <&clockgen 4 1>;
+			clock-names = "ipg", "per";
+			big-endian;
+		};
+
+		can1: can@2a80000 {
+			compatible = "fsl,ls1021ar2-flexcan";
+			reg = <0x0 0x2a80000 0x0 0x1000>;
+			interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clockgen 4 1>, <&clockgen 4 1>;
+			clock-names = "ipg", "per";
+			big-endian;
+		};
+
+		can2: can@2a90000 {
+			compatible = "fsl,ls1021ar2-flexcan";
+			reg = <0x0 0x2a90000 0x0 0x1000>;
+			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clockgen 4 1>, <&clockgen 4 1>;
+			clock-names = "ipg", "per";
+			big-endian;
+		};
+
+		can3: can@2aa0000 {
+			compatible = "fsl,ls1021ar2-flexcan";
+			reg = <0x0 0x2aa0000 0x0 0x1000>;
+			interrupts = <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clockgen 4 1>, <&clockgen 4 1>;
+			clock-names = "ipg", "per";
+			big-endian;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi
index 4926133077b3..0d9faf1a51ea 100644
--- a/arch/arm/boot/dts/meson.dtsi
+++ b/arch/arm/boot/dts/meson.dtsi
@@ -85,15 +85,6 @@
 				reg = <0x7c00 0x200>;
 			};
 
-			gpio_intc: interrupt-controller@9880 {
-				compatible = "amlogic,meson-gpio-intc";
-				reg = <0xc1109880 0x10>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-				amlogic,channel-interrupts = <64 65 66 67 68 69 70 71>;
-				status = "disabled";
-			};
-
 			hwrng: rng@8100 {
 				compatible = "amlogic,meson-rng";
 				reg = <0x8100 0x8>;
@@ -191,6 +182,15 @@
 				status = "disabled";
 			};
 
+			gpio_intc: interrupt-controller@9880 {
+				compatible = "amlogic,meson-gpio-intc";
+				reg = <0x9880 0x10>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				amlogic,channel-interrupts = <64 65 66 67 68 69 70 71>;
+				status = "disabled";
+			};
+
 			wdt: watchdog@9900 {
 				compatible = "amlogic,meson6-wdt";
 				reg = <0x9900 0x8>;
diff --git a/arch/arm/boot/dts/meson8.dtsi b/arch/arm/boot/dts/meson8.dtsi
index 2d7a0752a460..d2e3eeaa1a5f 100644
--- a/arch/arm/boot/dts/meson8.dtsi
+++ b/arch/arm/boot/dts/meson8.dtsi
@@ -286,6 +286,11 @@
 	clock-names = "stmmaceth";
 };
 
+&gpio_intc {
+	compatible = "amlogic,meson8-gpio-intc", "amlogic,meson-gpio-intc";
+	status = "okay";
+};
+
 &hwrng {
 	compatible = "amlogic,meson8-rng", "amlogic,meson-rng";
 	clocks = <&clkc CLKID_RNG0>;
@@ -308,6 +313,9 @@
 	arm,data-latency = <3 3 3>;
 	arm,tag-latency = <2 2 2>;
 	arm,filter-ranges = <0x100000 0xc0000000>;
+	prefetch-data = <1>;
+	prefetch-instr = <1>;
+	arm,shared-override;
 };
 
 &pwm_ab {
@@ -321,9 +329,8 @@
 &saradc {
 	compatible = "amlogic,meson8-saradc", "amlogic,meson-saradc";
 	clocks = <&clkc CLKID_XTAL>,
-		<&clkc CLKID_SAR_ADC>,
-		<&clkc CLKID_SANA>;
-	clock-names = "clkin", "core", "sana";
+		<&clkc CLKID_SAR_ADC>;
+	clock-names = "clkin", "core";
 };
 
 &sdio {
@@ -337,19 +344,27 @@
 };
 
 &uart_AO {
-	clocks = <&clkc CLKID_CLK81>;
+	compatible = "amlogic,meson8-uart", "amlogic,meson-uart";
+	clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_XTAL>, <&clkc CLKID_CLK81>;
+	clock-names = "baud", "xtal", "pclk";
 };
 
 &uart_A {
-	clocks = <&clkc CLKID_CLK81>;
+	compatible = "amlogic,meson8-uart", "amlogic,meson-uart";
+	clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_XTAL>, <&clkc CLKID_UART0>;
+	clock-names = "baud", "xtal", "pclk";
 };
 
 &uart_B {
-	clocks = <&clkc CLKID_CLK81>;
+	compatible = "amlogic,meson8-uart", "amlogic,meson-uart";
+	clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_XTAL>, <&clkc CLKID_UART1>;
+	clock-names = "baud", "xtal", "pclk";
 };
 
 &uart_C {
-	clocks = <&clkc CLKID_CLK81>;
+	compatible = "amlogic,meson8-uart", "amlogic,meson-uart";
+	clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_XTAL>, <&clkc CLKID_UART2>;
+	clock-names = "baud", "xtal", "pclk";
 };
 
 &usb0 {
diff --git a/arch/arm/boot/dts/meson8b.dtsi b/arch/arm/boot/dts/meson8b.dtsi
index d75e0ceda8bb..7cd03ed3742e 100644
--- a/arch/arm/boot/dts/meson8b.dtsi
+++ b/arch/arm/boot/dts/meson8b.dtsi
@@ -223,6 +223,9 @@
 	arm,data-latency = <3 3 3>;
 	arm,tag-latency = <2 2 2>;
 	arm,filter-ranges = <0x100000 0xc0000000>;
+	prefetch-data = <1>;
+	prefetch-instr = <1>;
+	arm,shared-override;
 };
 
 &pwm_ab {
@@ -236,9 +239,8 @@
 &saradc {
 	compatible = "amlogic,meson8b-saradc", "amlogic,meson-saradc";
 	clocks = <&clkc CLKID_XTAL>,
-		<&clkc CLKID_SAR_ADC>,
-		<&clkc CLKID_SANA>;
-	clock-names = "clkin", "core", "sana";
+		<&clkc CLKID_SAR_ADC>;
+	clock-names = "clkin", "core";
 };
 
 &sdio {
@@ -248,19 +250,27 @@
 };
 
 &uart_AO {
-	clocks = <&clkc CLKID_CLK81>;
+	compatible = "amlogic,meson8b-uart", "amlogic,meson-uart";
+	clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_XTAL>, <&clkc CLKID_CLK81>;
+	clock-names = "baud", "xtal", "pclk";
 };
 
 &uart_A {
-	clocks = <&clkc CLKID_CLK81>;
+	compatible = "amlogic,meson8b-uart", "amlogic,meson-uart";
+	clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_XTAL>, <&clkc CLKID_UART0>;
+	clock-names = "baud", "xtal", "pclk";
 };
 
 &uart_B {
-	clocks = <&clkc CLKID_CLK81>;
+	compatible = "amlogic,meson8b-uart", "amlogic,meson-uart";
+	clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_XTAL>, <&clkc CLKID_UART1>;
+	clock-names = "baud", "xtal", "pclk";
 };
 
 &uart_C {
-	clocks = <&clkc CLKID_CLK81>;
+	compatible = "amlogic,meson8b-uart", "amlogic,meson-uart";
+	clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_XTAL>, <&clkc CLKID_UART2>;
+	clock-names = "baud", "xtal", "pclk";
 };
 
 &usb0 {
diff --git a/arch/arm/boot/dts/mpa1600.dts b/arch/arm/boot/dts/mpa1600.dts
index 36cfa215620d..43aaa67fcd87 100644
--- a/arch/arm/boot/dts/mpa1600.dts
+++ b/arch/arm/boot/dts/mpa1600.dts
@@ -32,6 +32,18 @@
 				status = "okay";
 			};
 
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			macb0: ethernet@fffbc000 {
 				phy-mode = "rmii";
 				status = "okay";
diff --git a/arch/arm/boot/dts/mt2701.dtsi b/arch/arm/boot/dts/mt2701.dtsi
index 965ddfbc9953..05557fce0f1d 100644
--- a/arch/arm/boot/dts/mt2701.dtsi
+++ b/arch/arm/boot/dts/mt2701.dtsi
@@ -604,6 +604,7 @@
 		compatible = "mediatek,mt2701-hifsys", "syscon";
 		reg = <0 0x1a000000 0 0x1000>;
 		#clock-cells = <1>;
+		#reset-cells = <1>;
 	};
 
 	usb0: usb@1a1c0000 {
@@ -688,6 +689,7 @@
 		compatible = "mediatek,mt2701-ethsys", "syscon";
 		reg = <0 0x1b000000 0 0x1000>;
 		#clock-cells = <1>;
+		#reset-cells = <1>;
 	};
 
 	eth: ethernet@1b100000 {
diff --git a/arch/arm/boot/dts/mt7623.dtsi b/arch/arm/boot/dts/mt7623.dtsi
index 0640fb75bf59..b750da5362f7 100644
--- a/arch/arm/boot/dts/mt7623.dtsi
+++ b/arch/arm/boot/dts/mt7623.dtsi
@@ -641,7 +641,7 @@
 
 	mmc0: mmc@11230000 {
 		compatible = "mediatek,mt7623-mmc",
-			     "mediatek,mt8135-mmc";
+			     "mediatek,mt2701-mmc";
 		reg = <0 0x11230000 0 0x1000>;
 		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_LOW>;
 		clocks = <&pericfg CLK_PERI_MSDC30_0>,
@@ -652,7 +652,7 @@
 
 	mmc1: mmc@11240000 {
 		compatible = "mediatek,mt7623-mmc",
-			     "mediatek,mt8135-mmc";
+			     "mediatek,mt2701-mmc";
 		reg = <0 0x11240000 0 0x1000>;
 		interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_LOW>;
 		clocks = <&pericfg CLK_PERI_MSDC30_1>,
@@ -758,6 +758,7 @@
 			     "syscon";
 		reg = <0 0x1b000000 0 0x1000>;
 		#clock-cells = <1>;
+		#reset-cells = <1>;
 	};
 
 	eth: ethernet@1b100000 {
diff --git a/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts b/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts
index 688a86378cee..7bf5aa2237c9 100644
--- a/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts
+++ b/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts
@@ -204,7 +204,7 @@
 	bus-width = <4>;
 	max-frequency = <50000000>;
 	cap-sd-highspeed;
-	cd-gpios = <&pio 261 0>;
+	cd-gpios = <&pio 261 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&mt6323_vmch_reg>;
 	vqmmc-supply = <&mt6323_vio18_reg>;
 };
diff --git a/arch/arm/boot/dts/mt7623n-rfb-nand.dts b/arch/arm/boot/dts/mt7623n-rfb-nand.dts
index 17c578f0d261..e66de8611650 100644
--- a/arch/arm/boot/dts/mt7623n-rfb-nand.dts
+++ b/arch/arm/boot/dts/mt7623n-rfb-nand.dts
@@ -51,7 +51,7 @@
 				reg = <0x40000 0x80000>;
 			};
 
-			partition@C0000 {
+			partition@c0000 {
 				label = "uboot-env";
 				reg = <0xC0000 0x40000>;
 			};
diff --git a/arch/arm/boot/dts/nspire.dtsi b/arch/arm/boot/dts/nspire.dtsi
index ec2283b1a638..1a5ae4cd107f 100644
--- a/arch/arm/boot/dts/nspire.dtsi
+++ b/arch/arm/boot/dts/nspire.dtsi
@@ -56,6 +56,7 @@
 
 	usb_phy: usb_phy {
 		compatible = "usb-nop-xceiv";
+		#phy-cells = <0>;
 	};
 
 	vbus_reg: vbus_reg {
diff --git a/arch/arm/boot/dts/omap2420-n8x0-common.dtsi b/arch/arm/boot/dts/omap2420-n8x0-common.dtsi
index 1df3ace3af92..63b0b4921e4e 100644
--- a/arch/arm/boot/dts/omap2420-n8x0-common.dtsi
+++ b/arch/arm/boot/dts/omap2420-n8x0-common.dtsi
@@ -52,6 +52,7 @@
 	onenand@0,0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
+		compatible = "ti,omap2-onenand";
 		reg = <0 0 0x20000>;	/* CS0, offset 0, IO size 128K */
 
 		gpmc,sync-read;
diff --git a/arch/arm/boot/dts/omap3-beagle-xm.dts b/arch/arm/boot/dts/omap3-beagle-xm.dts
index 683b96a8f73e..0349fcc9dc26 100644
--- a/arch/arm/boot/dts/omap3-beagle-xm.dts
+++ b/arch/arm/boot/dts/omap3-beagle-xm.dts
@@ -90,6 +90,7 @@
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio5 19 GPIO_ACTIVE_LOW>; /* gpio_147 */
 		vcc-supply = <&hsusb2_power>;
+		#phy-cells = <0>;
 	};
 
 	tfp410: encoder0 {
diff --git a/arch/arm/boot/dts/omap3-beagle.dts b/arch/arm/boot/dts/omap3-beagle.dts
index 4d2eaf843fa9..3ca8991a6c3e 100644
--- a/arch/arm/boot/dts/omap3-beagle.dts
+++ b/arch/arm/boot/dts/omap3-beagle.dts
@@ -64,6 +64,7 @@
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio5 19 GPIO_ACTIVE_LOW>;	/* gpio_147 */
 		vcc-supply = <&hsusb2_power>;
+		#phy-cells = <0>;
 	};
 
 	sound {
diff --git a/arch/arm/boot/dts/omap3-cm-t3x.dtsi b/arch/arm/boot/dts/omap3-cm-t3x.dtsi
index 31d5ebf38892..9dcb18d22cde 100644
--- a/arch/arm/boot/dts/omap3-cm-t3x.dtsi
+++ b/arch/arm/boot/dts/omap3-cm-t3x.dtsi
@@ -43,12 +43,14 @@
 	hsusb1_phy: hsusb1_phy {
 		compatible = "usb-nop-xceiv";
 		vcc-supply = <&hsusb1_power>;
+		#phy-cells = <0>;
 	};
 
 	/* HS USB Host PHY on PORT 2 */
 	hsusb2_phy: hsusb2_phy {
 		compatible = "usb-nop-xceiv";
 		vcc-supply = <&hsusb2_power>;
+		#phy-cells = <0>;
 	};
 
 	ads7846reg: ads7846-reg {
@@ -304,19 +306,19 @@
 			label = "xloader";
 			reg = <0 0x80000>;
 		};
-		partition@0x80000 {
+		partition@80000 {
 			label = "uboot";
 			reg = <0x80000 0x1e0000>;
 		};
-		partition@0x260000 {
+		partition@260000 {
 			label = "uboot environment";
 			reg = <0x260000 0x40000>;
 		};
-		partition@0x2a0000 {
+		partition@2a0000 {
 			label = "linux";
 			reg = <0x2a0000 0x400000>;
 		};
-		partition@0x6a0000 {
+		partition@6a0000 {
 			label = "rootfs";
 			reg = <0x6a0000 0x1f880000>;
 		};
diff --git a/arch/arm/boot/dts/omap3-evm-37xx.dts b/arch/arm/boot/dts/omap3-evm-37xx.dts
index 5a4ba0aea447..a14303b09ae2 100644
--- a/arch/arm/boot/dts/omap3-evm-37xx.dts
+++ b/arch/arm/boot/dts/omap3-evm-37xx.dts
@@ -90,19 +90,19 @@
 			label = "X-Loader";
 			reg = <0 0x80000>;
 		};
-		partition@0x80000 {
+		partition@80000 {
 			label = "U-Boot";
 			reg = <0x80000 0x1c0000>;
 		};
-		partition@0x1c0000 {
+		partition@1c0000 {
 			label = "Environment";
 			reg = <0x240000 0x40000>;
 		};
-		partition@0x280000 {
+		partition@280000 {
 			label = "Kernel";
 			reg = <0x280000 0x500000>;
 		};
-		partition@0x780000 {
+		partition@780000 {
 			label = "Filesystem";
 			reg = <0x780000 0x1f880000>;
 		};
diff --git a/arch/arm/boot/dts/omap3-evm-common.dtsi b/arch/arm/boot/dts/omap3-evm-common.dtsi
index dbc3f030a16c..ee64191e41ca 100644
--- a/arch/arm/boot/dts/omap3-evm-common.dtsi
+++ b/arch/arm/boot/dts/omap3-evm-common.dtsi
@@ -29,6 +29,7 @@
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio1 21 GPIO_ACTIVE_LOW>; /* gpio_21 */
 		vcc-supply = <&hsusb2_power>;
+		#phy-cells = <0>;
 	};
 
 	leds {
diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi
index 4504908c23fe..4170be70460e 100644
--- a/arch/arm/boot/dts/omap3-gta04.dtsi
+++ b/arch/arm/boot/dts/omap3-gta04.dtsi
@@ -86,7 +86,7 @@
 
 		/* lcd panel */
 		lcd: td028ttec1@0 {
-			compatible = "toppoly,td028ttec1";
+			compatible = "tpo,td028ttec1";
 			reg = <0>;
 			spi-max-frequency = <100000>;
 			spi-cpol;
@@ -120,6 +120,7 @@
 	hsusb2_phy: hsusb2_phy {
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio6 14 GPIO_ACTIVE_LOW>;
+		#phy-cells = <0>;
 	};
 
 	tv0: connector {
diff --git a/arch/arm/boot/dts/omap3-igep.dtsi b/arch/arm/boot/dts/omap3-igep.dtsi
index 4ad7d5565906..f33cc80c9dbc 100644
--- a/arch/arm/boot/dts/omap3-igep.dtsi
+++ b/arch/arm/boot/dts/omap3-igep.dtsi
@@ -147,32 +147,32 @@
 		gpmc,sync-read;
 		gpmc,sync-write;
 		gpmc,burst-length = <16>;
-		gpmc,burst-read;
 		gpmc,burst-wrap;
+		gpmc,burst-read;
 		gpmc,burst-write;
 		gpmc,device-width = <2>; /* GPMC_DEVWIDTH_16BIT */
 		gpmc,mux-add-data = <2>; /* GPMC_MUX_AD */
 		gpmc,cs-on-ns = <0>;
-		gpmc,cs-rd-off-ns = <87>;
-		gpmc,cs-wr-off-ns = <87>;
+		gpmc,cs-rd-off-ns = <96>;
+		gpmc,cs-wr-off-ns = <96>;
 		gpmc,adv-on-ns = <0>;
-		gpmc,adv-rd-off-ns = <10>;
-		gpmc,adv-wr-off-ns = <10>;
-		gpmc,oe-on-ns = <15>;
-		gpmc,oe-off-ns = <87>;
+		gpmc,adv-rd-off-ns = <12>;
+		gpmc,adv-wr-off-ns = <12>;
+		gpmc,oe-on-ns = <18>;
+		gpmc,oe-off-ns = <96>;
 		gpmc,we-on-ns = <0>;
-		gpmc,we-off-ns = <87>;
-		gpmc,rd-cycle-ns = <112>;
-		gpmc,wr-cycle-ns = <112>;
-		gpmc,access-ns = <81>;
-		gpmc,page-burst-access-ns = <15>;
+		gpmc,we-off-ns = <96>;
+		gpmc,rd-cycle-ns = <114>;
+		gpmc,wr-cycle-ns = <114>;
+		gpmc,access-ns = <90>;
+		gpmc,page-burst-access-ns = <12>;
 		gpmc,bus-turnaround-ns = <0>;
 		gpmc,cycle2cycle-delay-ns = <0>;
 		gpmc,wait-monitoring-ns = <0>;
-		gpmc,clk-activation-ns = <5>;
+		gpmc,clk-activation-ns = <6>;
 		gpmc,wr-data-mux-bus-ns = <30>;
-		gpmc,wr-access-ns = <81>;
-		gpmc,sync-clk-ps = <15000>;
+		gpmc,wr-access-ns = <90>;
+		gpmc,sync-clk-ps = <12000>;
 
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/arm/boot/dts/omap3-igep0020-common.dtsi b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
index 667f96245729..ecbec23af49f 100644
--- a/arch/arm/boot/dts/omap3-igep0020-common.dtsi
+++ b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
@@ -58,6 +58,7 @@
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio1 24 GPIO_ACTIVE_LOW>; /* gpio_24 */
 		vcc-supply = <&hsusb1_power>;
+		#phy-cells = <0>;
 	};
 
 	tfp410: encoder {
diff --git a/arch/arm/boot/dts/omap3-igep0030-common.dtsi b/arch/arm/boot/dts/omap3-igep0030-common.dtsi
index e94d9427450c..443f71707437 100644
--- a/arch/arm/boot/dts/omap3-igep0030-common.dtsi
+++ b/arch/arm/boot/dts/omap3-igep0030-common.dtsi
@@ -37,6 +37,7 @@
 	hsusb2_phy: hsusb2_phy {
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio2 22 GPIO_ACTIVE_LOW>;		/* gpio_54 */
+		#phy-cells = <0>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
index 343a36d8031d..cf7a2a72348d 100644
--- a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
+++ b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
@@ -51,6 +51,7 @@
 	hsusb1_phy: hsusb1_phy {
 		compatible = "usb-nop-xceiv";
 		vcc-supply = <&reg_vcc3>;
+		#phy-cells = <0>;
 	};
 };
 
@@ -404,22 +405,22 @@
 			reg = <0 0x80000>;
 		};
 
-		partition@0x80000 {
+		partition@80000 {
 			label = "u-boot";
 			reg = <0x80000 0x1e0000>;
 		};
 
-		partition@0x260000 {
+		partition@260000 {
 			label = "u-boot-environment";
 			reg = <0x260000 0x20000>;
 		};
 
-		partition@0x280000 {
+		partition@280000 {
 			label = "kernel";
 			reg = <0x280000 0x500000>;
 		};
 
-		partition@0x780000 {
+		partition@780000 {
 			label = "filesystem";
 			reg = <0x780000 0xf880000>;
 		};
diff --git a/arch/arm/boot/dts/omap3-n9.dts b/arch/arm/boot/dts/omap3-n9.dts
index 39e35f8b8206..e44d93fc644c 100644
--- a/arch/arm/boot/dts/omap3-n9.dts
+++ b/arch/arm/boot/dts/omap3-n9.dts
@@ -11,6 +11,7 @@
 /dts-v1/;
 
 #include "omap3-n950-n9.dtsi"
+#include <dt-bindings/input/input.h>
 
 / {
 	model = "Nokia N9";
@@ -72,3 +73,9 @@
 	st,max-limit-y = <46>;
 	st,max-limit-z = <46>;
 };
+
+&twl_keypad {
+	linux,keymap = < MATRIX_KEY(6, 8, KEY_VOLUMEUP)
+			 MATRIX_KEY(7, 8, KEY_VOLUMEDOWN)
+			 >;
+};
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 669c51c00c00..72c765a3b354 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -35,6 +35,8 @@
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
 		i2c3 = &i2c3;
+		display0 = &lcd;
+		display1 = &tv;
 	};
 
 	cpus {
@@ -558,7 +560,7 @@
 	tlv320aic3x: tlv320aic3x@18 {
 		compatible = "ti,tlv320aic3x";
 		reg = <0x18>;
-		gpio-reset = <&gpio2 28 GPIO_ACTIVE_HIGH>; /* 60 */
+		reset-gpios = <&gpio2 28 GPIO_ACTIVE_LOW>; /* 60 */
 		ai3x-gpio-func = <
 			0 /* AIC3X_GPIO1_FUNC_DISABLED */
 			5 /* AIC3X_GPIO2_FUNC_DIGITAL_MIC_INPUT */
@@ -575,7 +577,7 @@
 	tlv320aic3x_aux: tlv320aic3x@19 {
 		compatible = "ti,tlv320aic3x";
 		reg = <0x19>;
-		gpio-reset = <&gpio2 28 GPIO_ACTIVE_HIGH>; /* 60 */
+		reset-gpios = <&gpio2 28 GPIO_ACTIVE_LOW>; /* 60 */
 
 		AVDD-supply = <&vmmc2>;
 		DRVDD-supply = <&vmmc2>;
@@ -838,6 +840,7 @@
 	onenand@0,0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
+		compatible = "ti,omap2-onenand";
 		reg = <0 0 0x20000>;	/* CS0, offset 0, IO size 128K */
 
 		gpmc,sync-read;
@@ -965,7 +968,7 @@
 		ti,esd-recovery-timeout-ms = <8000>;
 	};
 
-	acx565akm@2 {
+	lcd: acx565akm@2 {
 		compatible = "sony,acx565akm";
 		spi-max-frequency = <6000000>;
 		reg = <2>;
diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index 12fbb3da5fce..0d9b85317529 100644
--- a/arch/arm/boot/dts/omap3-n950-n9.dtsi
+++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi
@@ -367,6 +367,7 @@
 	onenand@0,0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
+		compatible = "ti,omap2-onenand";
 		reg = <0 0 0x20000>;	/* CS0, offset 0, IO size 128K */
 
 		gpmc,sync-read;
diff --git a/arch/arm/boot/dts/omap3-n950.dts b/arch/arm/boot/dts/omap3-n950.dts
index c354a1ed1e70..2354e09343f3 100644
--- a/arch/arm/boot/dts/omap3-n950.dts
+++ b/arch/arm/boot/dts/omap3-n950.dts
@@ -51,6 +51,26 @@
 	};
 };
 
+&omap3_pmx_core {
+	dsi_pins: pinmux_dsi_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE1) /* dsi_dx0 - data0+ */
+			OMAP3_CORE1_IOPAD(0x20de, PIN_OUTPUT | MUX_MODE1) /* dsi_dy0 - data0- */
+			OMAP3_CORE1_IOPAD(0x20e0, PIN_OUTPUT | MUX_MODE1) /* dsi_dx1 - clk+   */
+			OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE1) /* dsi_dy1 - clk-   */
+			OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE1) /* dsi_dx2 - data1+ */
+			OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE1) /* dsi_dy2 - data1- */
+		>;
+	};
+
+	display_pins: pinmux_display_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20ca, PIN_INPUT | MUX_MODE4) /* gpio 62 - display te */
+			OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT | MUX_MODE4) /* gpio 87 - display reset */
+		>;
+	};
+};
+
 &i2c2 {
 	smia_1: camera@10 {
 		compatible = "nokia,smia";
@@ -186,3 +206,71 @@
 	st,max-limit-y = <32>;
 	st,max-limit-z = <32>;
 };
+
+&dss {
+	status = "ok";
+
+	vdda_video-supply = <&vdac>;
+};
+
+&dsi {
+	status = "ok";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&dsi_pins>;
+
+	vdd-supply = <&vpll2>;
+
+	port {
+		dsi_out_ep: endpoint {
+			remote-endpoint = <&lcd0_in>;
+			lanes = <2 3 0 1 4 5>;
+		};
+	};
+
+	lcd0: display {
+		compatible = "nokia,himalaya", "panel-dsi-cm";
+		label = "lcd0";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&display_pins>;
+
+		vpnl-supply = <&vmmc2>;
+		vddi-supply = <&vio>;
+
+		reset-gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;	/* 87 */
+		te-gpios = <&gpio2 30 GPIO_ACTIVE_HIGH>;	/* 62 */
+
+		width-mm = <49>; /* 48.960 mm */
+		height-mm = <88>; /* 88.128 mm */
+
+		/* TODO:
+		 * - panel is upside-down
+		 * - top + bottom 5px are not visible
+		 */
+		panel-timing {
+			clock-frequency = <0>;          /* Calculated by dsi */
+
+			hback-porch = <2>;
+			hactive = <480>;
+			hfront-porch = <0>;
+			hsync-len = <2>;
+
+			vback-porch = <1>;
+			vactive = <864>;
+			vfront-porch = <0>;
+			vsync-len = <1>;
+
+			hsync-active = <0>;
+			vsync-active = <0>;
+			de-active = <1>;
+			pixelclk-active = <1>;
+		};
+
+		port {
+			lcd0_in: endpoint {
+				remote-endpoint = <&dsi_out_ep>;
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-overo-base.dtsi b/arch/arm/boot/dts/omap3-overo-base.dtsi
index f25e158e7163..ac141fcd1742 100644
--- a/arch/arm/boot/dts/omap3-overo-base.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-base.dtsi
@@ -51,6 +51,7 @@
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio6 23 GPIO_ACTIVE_LOW>;	/* gpio_183 */
 		vcc-supply = <&hsusb2_power>;
+		#phy-cells = <0>;
 	};
 
 	/* Regulator to trigger the nPoweron signal of the Wifi module */
diff --git a/arch/arm/boot/dts/omap3-pandora-common.dtsi b/arch/arm/boot/dts/omap3-pandora-common.dtsi
index 53e007abdc71..f83b1029b3b7 100644
--- a/arch/arm/boot/dts/omap3-pandora-common.dtsi
+++ b/arch/arm/boot/dts/omap3-pandora-common.dtsi
@@ -205,6 +205,7 @@
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio1 16 GPIO_ACTIVE_LOW>; /* GPIO_16 */
 		vcc-supply = <&vaux2>;
+		#phy-cells = <0>;
 	};
 
 	/* HS USB Host VBUS supply
@@ -626,7 +627,7 @@
 
 	lcd: lcd@1 {
 		reg = <1>;	/* CS1 */
-		compatible =	"omapdss,tpo,td043mtea1";
+		compatible =	"tpo,td043mtea1";
 		spi-max-frequency = <100000>;
 		spi-cpol;
 		spi-cpha;
diff --git a/arch/arm/boot/dts/omap3-tao3530.dtsi b/arch/arm/boot/dts/omap3-tao3530.dtsi
index 9a601d15247b..6f5bd027b717 100644
--- a/arch/arm/boot/dts/omap3-tao3530.dtsi
+++ b/arch/arm/boot/dts/omap3-tao3530.dtsi
@@ -46,6 +46,7 @@
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio6 2 GPIO_ACTIVE_LOW>;	/* gpio_162 */
 		vcc-supply = <&hsusb2_power>;
+		#phy-cells = <0>;
 	};
 
 	sound {
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index 90b5c7148feb..a005802cd52b 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -587,20 +587,6 @@
 			dma-names = "rx";
 		};
 
-		smartreflex_core: smartreflex@480cb000 {
-			compatible = "ti,omap3-smartreflex-core";
-			ti,hwmods = "smartreflex_core";
-			reg = <0x480cb000 0x400>;
-			interrupts = <19>;
-		};
-
-		smartreflex_mpu_iva: smartreflex@480c9000 {
-			compatible = "ti,omap3-smartreflex-iva";
-			ti,hwmods = "smartreflex_mpu_iva";
-			reg = <0x480c9000 0x400>;
-			interrupts = <18>;
-		};
-
 		timer1: timer@48318000 {
 			compatible = "ti,omap3430-timer";
 			reg = <0x48318000 0x400>;
@@ -715,6 +701,7 @@
 				compatible = "ti,ohci-omap3";
 				reg = <0x48064400 0x400>;
 				interrupts = <76>;
+				remote-wakeup-connected;
 			};
 
 			usbhsehci: ehci@48064800 {
diff --git a/arch/arm/boot/dts/omap3430-sdp.dts b/arch/arm/boot/dts/omap3430-sdp.dts
index 908951eb5943..d652708f6bef 100644
--- a/arch/arm/boot/dts/omap3430-sdp.dts
+++ b/arch/arm/boot/dts/omap3430-sdp.dts
@@ -154,6 +154,7 @@
 		linux,mtd-name= "samsung,kfm2g16q2m-deb8";
 		#address-cells = <1>;
 		#size-cells = <1>;
+		compatible = "ti,omap2-onenand";
 		reg = <2 0 0x20000>;	/* CS2, offset 0, IO size 4 */
 
 		gpmc,device-width = <2>;
diff --git a/arch/arm/boot/dts/omap34xx.dtsi b/arch/arm/boot/dts/omap34xx.dtsi
index ac4f8795b756..f572a477f74c 100644
--- a/arch/arm/boot/dts/omap34xx.dtsi
+++ b/arch/arm/boot/dts/omap34xx.dtsi
@@ -8,6 +8,7 @@
  * kind, whether express or implied.
  */
 
+#include <dt-bindings/bus/ti-sysc.h>
 #include <dt-bindings/media/omap3-isp.h>
 
 #include "omap3.dtsi"
@@ -61,6 +62,44 @@
 			compatible = "ti,omap34xx-bandgap";
 			#thermal-sensor-cells = <0>;
 		};
+
+		target-module@480cb000 {
+			compatible = "ti,sysc-omap3430-sr", "ti,sysc";
+			ti,hwmods = "smartreflex_core";
+			reg = <0x480cb024 0x4>;
+			reg-names = "sysc";
+			ti,sysc-mask = <SYSC_OMAP2_CLOCKACTIVITY>;
+			clocks = <&sr2_fck>;
+			clock-names = "fck";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x480cb000 0x001000>;
+
+			smartreflex_core: smartreflex@0 {
+				compatible = "ti,omap3-smartreflex-core";
+				reg = <0 0x400>;
+				interrupts = <19>;
+			};
+		};
+
+		target-module@480c9000 {
+			compatible = "ti,sysc-omap3430-sr", "ti,sysc";
+			ti,hwmods = "smartreflex_mpu_iva";
+			reg = <0x480c9024 0x4>;
+			reg-names = "sysc";
+			ti,sysc-mask = <SYSC_OMAP2_CLOCKACTIVITY>;
+			clocks = <&sr1_fck>;
+			clock-names = "fck";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x480c9000 0x001000>;
+
+			smartreflex_mpu_iva: smartreflex@480c9000 {
+				compatible = "ti,omap3-smartreflex-mpu-iva";
+				reg = <0 0x400>;
+				interrupts = <18>;
+			};
+		};
 	};
 
 	thermal_zones: thermal-zones {
diff --git a/arch/arm/boot/dts/omap36xx.dtsi b/arch/arm/boot/dts/omap36xx.dtsi
index ade31d74c70c..6fb23ada1f64 100644
--- a/arch/arm/boot/dts/omap36xx.dtsi
+++ b/arch/arm/boot/dts/omap36xx.dtsi
@@ -8,6 +8,7 @@
  * kind, whether express or implied.
  */
 
+#include <dt-bindings/bus/ti-sysc.h>
 #include <dt-bindings/media/omap3-isp.h>
 
 #include "omap3.dtsi"
@@ -93,6 +94,51 @@
 			compatible = "ti,omap36xx-bandgap";
 			#thermal-sensor-cells = <0>;
 		};
+
+		target-module@480cb000 {
+			compatible = "ti,sysc-omap3630-sr", "ti,sysc";
+			ti,hwmods = "smartreflex_core";
+			reg = <0x480cb038 0x4>;
+			reg-names = "sysc";
+			ti,sysc-mask = <SYSC_OMAP3_SR_ENAWAKEUP>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>;
+			clocks = <&sr2_fck>;
+			clock-names = "fck";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x480cb000 0x001000>;
+
+			smartreflex_core: smartreflex@0 {
+				compatible = "ti,omap3-smartreflex-core";
+				reg = <0 0x400>;
+				interrupts = <19>;
+			};
+		};
+
+		target-module@480c9000 {
+			compatible = "ti,sysc-omap3630-sr", "ti,sysc";
+			ti,hwmods = "smartreflex_mpu_iva";
+			reg = <0x480c9038 0x4>;
+			reg-names = "sysc";
+			ti,sysc-mask = <SYSC_OMAP3_SR_ENAWAKEUP>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>;
+			clocks = <&sr1_fck>;
+			clock-names = "fck";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x480c9000 0x001000>;
+
+
+			smartreflex_mpu_iva: smartreflex@480c9000 {
+				compatible = "ti,omap3-smartreflex-mpu-iva";
+				reg = <0 0x400>;
+				interrupts = <18>;
+			};
+		};
 	};
 
 	thermal_zones: thermal-zones {
diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts
index 8b93d37310f2..b21084da490b 100644
--- a/arch/arm/boot/dts/omap4-droid4-xt894.dts
+++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts
@@ -73,6 +73,7 @@
 	/* HS USB Host PHY on PORT 1 */
 	hsusb1_phy: hsusb1_phy {
 		compatible = "usb-nop-xceiv";
+		#phy-cells = <0>;
 	};
 
 	/* LCD regulator from sw5 source */
@@ -176,6 +177,10 @@
 		vddi-supply = <&lcd_regulator>;
 		reset-gpios = <&gpio4 5 GPIO_ACTIVE_HIGH>;	/* gpio101 */
 
+		width-mm = <50>;
+		height-mm = <89>;
+		backlight = <&lcd_backlight>;
+
 		panel-timing {
 			clock-frequency = <0>;		/* Calculated by dsi */
 
@@ -345,7 +350,7 @@
 
 		enable-gpios = <&gpio6 12 GPIO_ACTIVE_HIGH>;
 
-		backlight {
+		lcd_backlight: backlight {
 			compatible = "ti,lm3532-backlight";
 
 			lcd {
diff --git a/arch/arm/boot/dts/omap4-duovero.dtsi b/arch/arm/boot/dts/omap4-duovero.dtsi
index 6e6810c258eb..eb123b24c8e3 100644
--- a/arch/arm/boot/dts/omap4-duovero.dtsi
+++ b/arch/arm/boot/dts/omap4-duovero.dtsi
@@ -43,6 +43,7 @@
 	hsusb1_phy: hsusb1_phy {
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio2 30 GPIO_ACTIVE_LOW>;	/* gpio_62 */
+		#phy-cells = <0>;
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&hsusb1phy_pins>;
diff --git a/arch/arm/boot/dts/omap4-panda-common.dtsi b/arch/arm/boot/dts/omap4-panda-common.dtsi
index 22c1eee9b07a..5501d1b4e6cd 100644
--- a/arch/arm/boot/dts/omap4-panda-common.dtsi
+++ b/arch/arm/boot/dts/omap4-panda-common.dtsi
@@ -89,6 +89,7 @@
 	hsusb1_phy: hsusb1_phy {
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio2 30 GPIO_ACTIVE_LOW>;   /* gpio_62 */
+		#phy-cells = <0>;
 		vcc-supply = <&hsusb1_power>;
 		clocks = <&auxclk3_ck>;
 		clock-names = "main_clk";
diff --git a/arch/arm/boot/dts/omap4-var-som-om44.dtsi b/arch/arm/boot/dts/omap4-var-som-om44.dtsi
index 6500bfc8d130..10fce28ceb5b 100644
--- a/arch/arm/boot/dts/omap4-var-som-om44.dtsi
+++ b/arch/arm/boot/dts/omap4-var-som-om44.dtsi
@@ -44,6 +44,7 @@
 
 		reset-gpios = <&gpio6 17 GPIO_ACTIVE_LOW>; /* gpio 177 */
 		vcc-supply = <&vbat>;
+		#phy-cells = <0>;
 
 		clocks = <&auxclk3_ck>;
 		clock-names = "main_clk";
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 1dc5a76b3c71..475904894b86 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -6,9 +6,12 @@
  * published by the Free Software Foundation.
  */
 
+#include <dt-bindings/bus/ti-sysc.h>
+#include <dt-bindings/clock/omap4.h>
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/pinctrl/omap.h>
+#include <dt-bindings/clock/omap4.h>
 
 / {
 	compatible = "ti,omap4430", "ti,omap4";
@@ -143,8 +146,11 @@
 			ranges = <0 0x4a000000 0x1000000>;
 
 			cm1: cm1@4000 {
-				compatible = "ti,omap4-cm1";
+				compatible = "ti,omap4-cm1", "simple-bus";
 				reg = <0x4000 0x2000>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 0x4000 0x2000>;
 
 				cm1_clocks: clocks {
 					#address-cells = <1>;
@@ -156,8 +162,11 @@
 			};
 
 			cm2: cm2@8000 {
-				compatible = "ti,omap4-cm2";
+				compatible = "ti,omap4-cm2", "simple-bus";
 				reg = <0x8000 0x3000>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 0x8000 0x3000>;
 
 				cm2_clocks: clocks {
 					#address-cells = <1>;
@@ -243,6 +252,9 @@
 					compatible = "ti,omap4-prm";
 					reg = <0x6000 0x3000>;
 					interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
+					#address-cells = <1>;
+					#size-cells = <1>;
+					ranges = <0 0x6000 0x3000>;
 
 					prm_clocks: clocks {
 						#address-cells = <1>;
@@ -383,11 +395,18 @@
 		};
 
 		target-module@48076000 {
-			compatible = "ti,sysc-omap4";
+			compatible = "ti,sysc-omap4", "ti,sysc";
 			ti,hwmods = "slimbus2";
 			reg = <0x48076000 0x4>,
 			      <0x48076010 0x4>;
 			reg-names = "rev", "sysc";
+			ti,sysc-mask = <SYSC_OMAP4_SOFTRESET>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			clocks = <&l4_per_clkctrl OMAP4_SLIMBUS2_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x48076000 0x001000>;
@@ -398,7 +417,7 @@
 		elm: elm@48078000 {
 			compatible = "ti,am3352-elm";
 			reg = <0x48078000 0x2000>;
-			interrupts = <4>;
+			interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "elm";
 			status = "disabled";
 		};
@@ -456,11 +475,17 @@
 		};
 
 		target-module@4a0db000 {
-			compatible = "ti,sysc-sr";
+			compatible = "ti,sysc-omap4-sr", "ti,sysc";
 			ti,hwmods = "smartreflex_iva";
-			reg = <0x4a0db000 0x4>,
-			      <0x4a0db008 0x4>;
-			reg-names = "rev", "sysc";
+			reg = <0x4a0db038 0x4>;
+			reg-names = "sysc";
+			ti,sysc-mask = <SYSC_OMAP3_SR_ENAWAKEUP>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			clocks = <&l4_ao_clkctrl OMAP4_SMARTREFLEX_IVA_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x4a0db000 0x001000>;
@@ -473,11 +498,17 @@
 		};
 
 		target-module@4a0dd000 {
-			compatible = "ti,sysc-sr";
+			compatible = "ti,sysc-omap4-sr", "ti,sysc";
 			ti,hwmods = "smartreflex_core";
-			reg = <0x4a0dd000 0x4>,
-			      <0x4a0dd008 0x4>;
-			reg-names = "rev", "sysc";
+			reg = <0x4a0dd038 0x4>;
+			reg-names = "sysc";
+			ti,sysc-mask = <SYSC_OMAP3_SR_ENAWAKEUP>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			clocks = <&l4_ao_clkctrl OMAP4_SMARTREFLEX_CORE_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x4a0dd000 0x001000>;
@@ -490,11 +521,17 @@
 		};
 
 		target-module@4a0d9000 {
-			compatible = "ti,sysc-sr";
+			compatible = "ti,sysc-omap4-sr", "ti,sysc";
 			ti,hwmods = "smartreflex_mpu";
-			reg = <0x4a0d9000 0x4>,
-			      <0x4a0d9008 0x4>;
-			reg-names = "rev", "sysc";
+			reg = <0x4a0d9038 0x4>;
+			reg-names = "sysc";
+			ti,sysc-mask = <SYSC_OMAP3_SR_ENAWAKEUP>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			clocks = <&l4_ao_clkctrl OMAP4_SMARTREFLEX_MPU_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x4a0d9000 0x001000>;
@@ -674,7 +711,7 @@
 			reg-names = "sys", "gdd";
 			ti,hwmods = "hsi";
 
-			clocks = <&hsi_fck>;
+			clocks = <&l3_init_clkctrl OMAP4_HSI_CLKCTRL 0>;
 			clock-names = "hsi_fck";
 
 			interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
@@ -710,11 +747,23 @@
 		};
 
 		target-module@52000000 {
-			compatible = "ti,sysc-omap4";
+			compatible = "ti,sysc-omap4", "ti,sysc";
 			ti,hwmods = "iss";
 			reg = <0x52000000 0x4>,
 			      <0x52000010 0x4>;
 			reg-names = "rev", "sysc";
+			ti,sysc-mask = <SYSC_OMAP4_SOFTRESET>;
+			ti,sysc-midle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			ti,sysc-delay-us = <2>;
+			clocks = <&iss_clkctrl OMAP4_ISS_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x52000000 0x1000000>;
@@ -817,10 +866,17 @@
 		};
 
 		target-module@40128000 {
-			compatible = "ti,sysc-mcasp";
+			compatible = "ti,sysc-mcasp", "ti,sysc";
 			ti,hwmods = "mcasp";
-			reg = <0x40128004 0x4>;
-			reg-names = "sysc";
+			reg = <0x40128000 0x4>,
+			      <0x40128004 0x4>;
+			reg-names = "rev", "sysc";
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			clocks = <&abe_clkctrl OMAP4_MCASP_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x00000000 0x40128000 0x1000>, /* MPU */
@@ -835,11 +891,18 @@
 		};
 
 		target-module@4012c000 {
-			compatible = "ti,sysc-omap4";
+			compatible = "ti,sysc-omap4", "ti,sysc";
 			ti,hwmods = "slimbus1";
 			reg = <0x4012c000 0x4>,
 			      <0x4012c010 0x4>;
 			reg-names = "rev", "sysc";
+			ti,sysc-mask = <SYSC_OMAP4_SOFTRESET>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			clocks = <&abe_clkctrl OMAP4_SLIMBUS1_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x00000000 0x4012c000 0x1000>, /* MPU */
@@ -849,11 +912,20 @@
 		};
 
 		target-module@401f1000 {
-			compatible = "ti,sysc-omap4";
+			compatible = "ti,sysc-omap4", "ti,sysc";
 			ti,hwmods = "aess";
 			reg = <0x401f1000 0x4>,
 			      <0x401f1010 0x4>;
 			reg-names = "rev", "sysc";
+			ti,sysc-midle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>;
+			clocks = <&abe_clkctrl OMAP4_AESS_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x00000000 0x401f1000 0x1000>, /* MPU */
@@ -955,11 +1027,21 @@
 		};
 
 		target-module@4a10a000 {
-			compatible = "ti,sysc-omap4";
+			compatible = "ti,sysc-omap4", "ti,sysc";
 			ti,hwmods = "fdif";
 			reg = <0x4a10a000 0x4>,
 			      <0x4a10a010 0x4>;
 			reg-names = "rev", "sysc";
+			ti,sysc-mask = <SYSC_OMAP4_SOFTRESET>;
+			ti,sysc-midle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>;
+			ti,sysc-delay-us = <2>;
+			clocks = <&iss_clkctrl OMAP4_FDIF_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x4a10a000 0x1000>;
@@ -973,6 +1055,8 @@
 			interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "timer1";
 			ti,timer-alwon;
+			clocks = <&l4_wkup_clkctrl OMAP4_TIMER1_CLKCTRL 24>;
+			clock-names = "fck";
 		};
 
 		timer2: timer@48032000 {
@@ -1081,14 +1165,13 @@
 			usbhsohci: ohci@4a064800 {
 				compatible = "ti,ohci-omap3";
 				reg = <0x4a064800 0x400>;
-				interrupt-parent = <&gic>;
 				interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>;
+				remote-wakeup-connected;
 			};
 
 			usbhsehci: ehci@4a064c00 {
 				compatible = "ti,ehci-omap";
 				reg = <0x4a064c00 0x400>;
-				interrupt-parent = <&gic>;
 				interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
@@ -1183,11 +1266,21 @@
 		};
 
 		target-module@56000000 {
-			compatible = "ti,sysc-omap4";
+			compatible = "ti,sysc-omap4", "ti,sysc";
 			ti,hwmods = "gpu";
 			reg = <0x5601fc00 0x4>,
 			      <0x5601fc10 0x4>;
 			reg-names = "rev", "sysc";
+			ti,sysc-midle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
+			clocks = <&l3_gfx_clkctrl OMAP4_GPU_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x56000000 0x2000000>;
@@ -1203,7 +1296,7 @@
 			reg = <0x58000000 0x80>;
 			status = "disabled";
 			ti,hwmods = "dss_core";
-			clocks = <&dss_dss_clk>;
+			clocks = <&l3_dss_clkctrl OMAP4_DSS_CORE_CLKCTRL 8>;
 			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -1214,7 +1307,7 @@
 				reg = <0x58001000 0x1000>;
 				interrupts = <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>;
 				ti,hwmods = "dss_dispc";
-				clocks = <&dss_dss_clk>;
+				clocks = <&l3_dss_clkctrl OMAP4_DSS_CORE_CLKCTRL 8>;
 				clock-names = "fck";
 			};
 
@@ -1223,7 +1316,7 @@
 				reg = <0x58002000 0x1000>;
 				status = "disabled";
 				ti,hwmods = "dss_rfbi";
-				clocks = <&dss_dss_clk>, <&l3_div_ck>;
+				clocks = <&l3_dss_clkctrl OMAP4_DSS_CORE_CLKCTRL 8>, <&l3_div_ck>;
 				clock-names = "fck", "ick";
 			};
 
@@ -1232,7 +1325,7 @@
 				reg = <0x58003000 0x1000>;
 				status = "disabled";
 				ti,hwmods = "dss_venc";
-				clocks = <&dss_tv_clk>;
+				clocks = <&l3_dss_clkctrl OMAP4_DSS_CORE_CLKCTRL 11>;
 				clock-names = "fck";
 			};
 
@@ -1245,7 +1338,8 @@
 				interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 				ti,hwmods = "dss_dsi1";
-				clocks = <&dss_dss_clk>, <&dss_sys_clk>;
+				clocks = <&l3_dss_clkctrl OMAP4_DSS_CORE_CLKCTRL 8>,
+					 <&l3_dss_clkctrl OMAP4_DSS_CORE_CLKCTRL 10>;
 				clock-names = "fck", "sys_clk";
 			};
 
@@ -1258,7 +1352,8 @@
 				interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 				ti,hwmods = "dss_dsi2";
-				clocks = <&dss_dss_clk>, <&dss_sys_clk>;
+				clocks = <&l3_dss_clkctrl OMAP4_DSS_CORE_CLKCTRL 8>,
+					 <&l3_dss_clkctrl OMAP4_DSS_CORE_CLKCTRL 10>;
 				clock-names = "fck", "sys_clk";
 			};
 
@@ -1272,7 +1367,8 @@
 				interrupts = <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 				ti,hwmods = "dss_hdmi";
-				clocks = <&dss_48mhz_clk>, <&dss_sys_clk>;
+				clocks = <&l3_dss_clkctrl OMAP4_DSS_CORE_CLKCTRL 9>,
+					 <&l3_dss_clkctrl OMAP4_DSS_CORE_CLKCTRL 10>;
 				clock-names = "fck", "sys_clk";
 				dmas = <&sdma 76>;
 				dma-names = "audio_tx";
@@ -1281,4 +1377,4 @@
 	};
 };
 
-/include/ "omap44xx-clocks.dtsi"
+#include "omap44xx-clocks.dtsi"
diff --git a/arch/arm/boot/dts/omap44xx-clocks.dtsi b/arch/arm/boot/dts/omap44xx-clocks.dtsi
index 05732ed4f50f..279ff2f419df 100644
--- a/arch/arm/boot/dts/omap44xx-clocks.dtsi
+++ b/arch/arm/boot/dts/omap44xx-clocks.dtsi
@@ -174,14 +174,6 @@
 		ti,index-power-of-two;
 	};
 
-	aess_fclk: aess_fclk@528 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&abe_clk>;
-		ti,bit-shift = <24>;
-		ti,max-div = <2>;
-		reg = <0x0528>;
-	};
 
 	dpll_abe_m3x2_ck: dpll_abe_m3x2_ck@1f4 {
 		#clock-cells = <0>;
@@ -464,7 +456,7 @@
 	ocp_abe_iclk: ocp_abe_iclk@528 {
 		#clock-cells = <0>;
 		compatible = "ti,divider-clock";
-		clocks = <&aess_fclk>;
+		clocks = <&abe_clkctrl OMAP4_AESS_CLKCTRL 24>;
 		ti,bit-shift = <24>;
 		reg = <0x0528>;
 		ti,dividers = <2>, <1>;
@@ -478,156 +470,13 @@
 		clock-div = <4>;
 	};
 
-	dmic_sync_mux_ck: dmic_sync_mux_ck@538 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&syc_clk_div_ck>, <&func_24m_clk>;
-		ti,bit-shift = <25>;
-		reg = <0x0538>;
-	};
-
-	func_dmic_abe_gfclk: func_dmic_abe_gfclk@538 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&dmic_sync_mux_ck>, <&pad_clks_ck>, <&slimbus_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x0538>;
-	};
-
-	mcasp_sync_mux_ck: mcasp_sync_mux_ck@540 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&syc_clk_div_ck>, <&func_24m_clk>;
-		ti,bit-shift = <25>;
-		reg = <0x0540>;
-	};
-
-	func_mcasp_abe_gfclk: func_mcasp_abe_gfclk@540 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&mcasp_sync_mux_ck>, <&pad_clks_ck>, <&slimbus_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x0540>;
-	};
-
-	mcbsp1_sync_mux_ck: mcbsp1_sync_mux_ck@548 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&syc_clk_div_ck>, <&func_24m_clk>;
-		ti,bit-shift = <25>;
-		reg = <0x0548>;
-	};
-
-	func_mcbsp1_gfclk: func_mcbsp1_gfclk@548 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&mcbsp1_sync_mux_ck>, <&pad_clks_ck>, <&slimbus_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x0548>;
-	};
-
-	mcbsp2_sync_mux_ck: mcbsp2_sync_mux_ck@550 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&syc_clk_div_ck>, <&func_24m_clk>;
-		ti,bit-shift = <25>;
-		reg = <0x0550>;
-	};
-
-	func_mcbsp2_gfclk: func_mcbsp2_gfclk@550 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&mcbsp2_sync_mux_ck>, <&pad_clks_ck>, <&slimbus_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x0550>;
-	};
-
-	mcbsp3_sync_mux_ck: mcbsp3_sync_mux_ck@558 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&syc_clk_div_ck>, <&func_24m_clk>;
-		ti,bit-shift = <25>;
-		reg = <0x0558>;
-	};
-
-	func_mcbsp3_gfclk: func_mcbsp3_gfclk@558 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&mcbsp3_sync_mux_ck>, <&pad_clks_ck>, <&slimbus_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x0558>;
-	};
-
-	slimbus1_fclk_1: slimbus1_fclk_1@560 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&func_24m_clk>;
-		ti,bit-shift = <9>;
-		reg = <0x0560>;
-	};
-
-	slimbus1_fclk_0: slimbus1_fclk_0@560 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&abe_24m_fclk>;
-		ti,bit-shift = <8>;
-		reg = <0x0560>;
-	};
-
-	slimbus1_fclk_2: slimbus1_fclk_2@560 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&pad_clks_ck>;
-		ti,bit-shift = <10>;
-		reg = <0x0560>;
-	};
-
-	slimbus1_slimbus_clk: slimbus1_slimbus_clk@560 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&slimbus_clk>;
-		ti,bit-shift = <11>;
-		reg = <0x0560>;
-	};
-
-	timer5_sync_mux: timer5_sync_mux@568 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&syc_clk_div_ck>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x0568>;
-	};
-
-	timer6_sync_mux: timer6_sync_mux@570 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&syc_clk_div_ck>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x0570>;
-	};
-
-	timer7_sync_mux: timer7_sync_mux@578 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&syc_clk_div_ck>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x0578>;
-	};
-
-	timer8_sync_mux: timer8_sync_mux@580 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&syc_clk_div_ck>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x0580>;
-	};
-
 	dummy_ck: dummy_ck {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
 		clock-frequency = <0>;
 	};
 };
+
 &prm_clocks {
 	sys_clkin_ck: sys_clkin_ck@110 {
 		#clock-cells = <0>;
@@ -675,22 +524,6 @@
 		ti,max-div = <2>;
 	};
 
-	gpio1_dbclk: gpio1_dbclk@1838 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1838>;
-	};
-
-	dmt1_clk_mux: dmt1_clk_mux@1840 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin_ck>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1840>;
-	};
-
 	usim_ck: usim_ck@1858 {
 		#clock-cells = <0>;
 		compatible = "ti,divider-clock";
@@ -708,45 +541,10 @@
 		reg = <0x1858>;
 	};
 
-	pmd_stm_clock_mux_ck: pmd_stm_clock_mux_ck@1a20 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin_ck>, <&dpll_core_m6x2_ck>, <&tie_low_clock_ck>;
-		ti,bit-shift = <20>;
-		reg = <0x1a20>;
-	};
-
-	pmd_trace_clk_mux_ck: pmd_trace_clk_mux_ck@1a20 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin_ck>, <&dpll_core_m6x2_ck>, <&tie_low_clock_ck>;
-		ti,bit-shift = <22>;
-		reg = <0x1a20>;
-	};
-
-	stm_clk_div_ck: stm_clk_div_ck@1a20 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&pmd_stm_clock_mux_ck>;
-		ti,bit-shift = <27>;
-		ti,max-div = <64>;
-		reg = <0x1a20>;
-		ti,index-power-of-two;
-	};
-
-	trace_clk_div_div_ck: trace_clk_div_div_ck@1a20 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&pmd_trace_clk_mux_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1a20>;
-		ti,dividers = <0>, <1>, <2>, <0>, <4>;
-	};
-
 	trace_clk_div_ck: trace_clk_div_ck {
 		#clock-cells = <0>;
 		compatible = "ti,clkdm-gate-clock";
-		clocks = <&trace_clk_div_div_ck>;
+		clocks = <&emu_sys_clkctrl OMAP4_DEBUGSS_CLKCTRL 24>;
 	};
 };
 
@@ -975,155 +773,6 @@
 		ti,max-div = <2>;
 	};
 
-	dss_sys_clk: dss_sys_clk@1120 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&syc_clk_div_ck>;
-		ti,bit-shift = <10>;
-		reg = <0x1120>;
-	};
-
-	dss_tv_clk: dss_tv_clk@1120 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&extalt_clkin_ck>;
-		ti,bit-shift = <11>;
-		reg = <0x1120>;
-	};
-
-	dss_dss_clk: dss_dss_clk@1120 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m5x2_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1120>;
-		ti,set-rate-parent;
-	};
-
-	dss_48mhz_clk: dss_48mhz_clk@1120 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&func_48mc_fclk>;
-		ti,bit-shift = <9>;
-		reg = <0x1120>;
-	};
-
-	fdif_fck: fdif_fck@1028 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&dpll_per_m4x2_ck>;
-		ti,bit-shift = <24>;
-		ti,max-div = <4>;
-		reg = <0x1028>;
-		ti,index-power-of-two;
-	};
-
-	gpio2_dbclk: gpio2_dbclk@1460 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1460>;
-	};
-
-	gpio3_dbclk: gpio3_dbclk@1468 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1468>;
-	};
-
-	gpio4_dbclk: gpio4_dbclk@1470 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1470>;
-	};
-
-	gpio5_dbclk: gpio5_dbclk@1478 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1478>;
-	};
-
-	gpio6_dbclk: gpio6_dbclk@1480 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1480>;
-	};
-
-	sgx_clk_mux: sgx_clk_mux@1220 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&dpll_core_m7x2_ck>, <&dpll_per_m7x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1220>;
-	};
-
-	hsi_fck: hsi_fck@1338 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		ti,max-div = <4>;
-		reg = <0x1338>;
-		ti,index-power-of-two;
-	};
-
-	iss_ctrlclk: iss_ctrlclk@1020 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&func_96m_fclk>;
-		ti,bit-shift = <8>;
-		reg = <0x1020>;
-	};
-
-	mcbsp4_sync_mux_ck: mcbsp4_sync_mux_ck@14e0 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_96m_fclk>, <&per_abe_nc_fclk>;
-		ti,bit-shift = <25>;
-		reg = <0x14e0>;
-	};
-
-	per_mcbsp4_gfclk: per_mcbsp4_gfclk@14e0 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&mcbsp4_sync_mux_ck>, <&pad_clks_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x14e0>;
-	};
-
-	hsmmc1_fclk: hsmmc1_fclk@1328 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_64m_fclk>, <&func_96m_fclk>;
-		ti,bit-shift = <24>;
-		reg = <0x1328>;
-	};
-
-	hsmmc2_fclk: hsmmc2_fclk@1330 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_64m_fclk>, <&func_96m_fclk>;
-		ti,bit-shift = <24>;
-		reg = <0x1330>;
-	};
-
-	ocp2scp_usb_phy_phy_48m: ocp2scp_usb_phy_phy_48m@13e0 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&func_48m_fclk>;
-		ti,bit-shift = <8>;
-		reg = <0x13e0>;
-	};
-
 	sha2md5_fck: sha2md5_fck@15c8 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
@@ -1132,222 +781,6 @@
 		reg = <0x15c8>;
 	};
 
-	slimbus2_fclk_1: slimbus2_fclk_1@1538 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&per_abe_24m_fclk>;
-		ti,bit-shift = <9>;
-		reg = <0x1538>;
-	};
-
-	slimbus2_fclk_0: slimbus2_fclk_0@1538 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&func_24mc_fclk>;
-		ti,bit-shift = <8>;
-		reg = <0x1538>;
-	};
-
-	slimbus2_slimbus_clk: slimbus2_slimbus_clk@1538 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&pad_slimbus_core_clks_ck>;
-		ti,bit-shift = <10>;
-		reg = <0x1538>;
-	};
-
-	smartreflex_core_fck: smartreflex_core_fck@638 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l4_wkup_clk_mux_ck>;
-		ti,bit-shift = <1>;
-		reg = <0x0638>;
-	};
-
-	smartreflex_iva_fck: smartreflex_iva_fck@630 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l4_wkup_clk_mux_ck>;
-		ti,bit-shift = <1>;
-		reg = <0x0630>;
-	};
-
-	smartreflex_mpu_fck: smartreflex_mpu_fck@628 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l4_wkup_clk_mux_ck>;
-		ti,bit-shift = <1>;
-		reg = <0x0628>;
-	};
-
-	cm2_dm10_mux: cm2_dm10_mux@1428 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin_ck>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1428>;
-	};
-
-	cm2_dm11_mux: cm2_dm11_mux@1430 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin_ck>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1430>;
-	};
-
-	cm2_dm2_mux: cm2_dm2_mux@1438 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin_ck>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1438>;
-	};
-
-	cm2_dm3_mux: cm2_dm3_mux@1440 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin_ck>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1440>;
-	};
-
-	cm2_dm4_mux: cm2_dm4_mux@1448 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin_ck>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1448>;
-	};
-
-	cm2_dm9_mux: cm2_dm9_mux@1450 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin_ck>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1450>;
-	};
-
-	usb_host_fs_fck: usb_host_fs_fck@13d0 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&func_48mc_fclk>;
-		ti,bit-shift = <1>;
-		reg = <0x13d0>;
-	};
-
-	utmi_p1_gfclk: utmi_p1_gfclk@1358 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&init_60m_fclk>, <&xclk60mhsp1_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1358>;
-	};
-
-	usb_host_hs_utmi_p1_clk: usb_host_hs_utmi_p1_clk@1358 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&utmi_p1_gfclk>;
-		ti,bit-shift = <8>;
-		reg = <0x1358>;
-	};
-
-	utmi_p2_gfclk: utmi_p2_gfclk@1358 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&init_60m_fclk>, <&xclk60mhsp2_ck>;
-		ti,bit-shift = <25>;
-		reg = <0x1358>;
-	};
-
-	usb_host_hs_utmi_p2_clk: usb_host_hs_utmi_p2_clk@1358 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&utmi_p2_gfclk>;
-		ti,bit-shift = <9>;
-		reg = <0x1358>;
-	};
-
-	usb_host_hs_utmi_p3_clk: usb_host_hs_utmi_p3_clk@1358 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&init_60m_fclk>;
-		ti,bit-shift = <10>;
-		reg = <0x1358>;
-	};
-
-	usb_host_hs_hsic480m_p1_clk: usb_host_hs_hsic480m_p1_clk@1358 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_usb_m2_ck>;
-		ti,bit-shift = <13>;
-		reg = <0x1358>;
-	};
-
-	usb_host_hs_hsic60m_p1_clk: usb_host_hs_hsic60m_p1_clk@1358 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&init_60m_fclk>;
-		ti,bit-shift = <11>;
-		reg = <0x1358>;
-	};
-
-	usb_host_hs_hsic60m_p2_clk: usb_host_hs_hsic60m_p2_clk@1358 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&init_60m_fclk>;
-		ti,bit-shift = <12>;
-		reg = <0x1358>;
-	};
-
-	usb_host_hs_hsic480m_p2_clk: usb_host_hs_hsic480m_p2_clk@1358 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_usb_m2_ck>;
-		ti,bit-shift = <14>;
-		reg = <0x1358>;
-	};
-
-	usb_host_hs_func48mclk: usb_host_hs_func48mclk@1358 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&func_48mc_fclk>;
-		ti,bit-shift = <15>;
-		reg = <0x1358>;
-	};
-
-	usb_host_hs_fck: usb_host_hs_fck@1358 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&init_60m_fclk>;
-		ti,bit-shift = <1>;
-		reg = <0x1358>;
-	};
-
-	otg_60m_gfclk: otg_60m_gfclk@1360 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&utmi_phy_clkout_ck>, <&xclk60motg_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1360>;
-	};
-
-	usb_otg_hs_xclk: usb_otg_hs_xclk@1360 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&otg_60m_gfclk>;
-		ti,bit-shift = <8>;
-		reg = <0x1360>;
-	};
-
-	usb_otg_hs_ick: usb_otg_hs_ick@1360 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l3_div_ck>;
-		ti,bit-shift = <0>;
-		reg = <0x1360>;
-	};
-
 	usb_phy_cm_clk32k: usb_phy_cm_clk32k@640 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
@@ -1355,44 +788,12 @@
 		ti,bit-shift = <8>;
 		reg = <0x0640>;
 	};
-
-	usb_tll_hs_usb_ch2_clk: usb_tll_hs_usb_ch2_clk@1368 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&init_60m_fclk>;
-		ti,bit-shift = <10>;
-		reg = <0x1368>;
-	};
-
-	usb_tll_hs_usb_ch0_clk: usb_tll_hs_usb_ch0_clk@1368 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&init_60m_fclk>;
-		ti,bit-shift = <8>;
-		reg = <0x1368>;
-	};
-
-	usb_tll_hs_usb_ch1_clk: usb_tll_hs_usb_ch1_clk@1368 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&init_60m_fclk>;
-		ti,bit-shift = <9>;
-		reg = <0x1368>;
-	};
-
-	usb_tll_hs_ick: usb_tll_hs_ick@1368 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l4_div_ck>;
-		ti,bit-shift = <0>;
-		reg = <0x1368>;
-	};
 };
 
 &cm2_clockdomains {
 	l3_init_clkdm: l3_init_clkdm {
 		compatible = "ti,clockdomain";
-		clocks = <&dpll_usb_ck>, <&usb_host_fs_fck>;
+		clocks = <&dpll_usb_ck>;
 	};
 };
 
@@ -1631,3 +1032,291 @@
 		reg = <0x0224>;
 	};
 };
+
+&cm1 {
+	mpuss_cm: mpuss_cm@300 {
+		compatible = "ti,omap4-cm";
+		reg = <0x300 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x300 0x100>;
+
+		mpuss_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	tesla_cm: tesla_cm@400 {
+		compatible = "ti,omap4-cm";
+		reg = <0x400 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x400 0x100>;
+
+		tesla_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	abe_cm: abe_cm@500 {
+		compatible = "ti,omap4-cm";
+		reg = <0x500 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x500 0x100>;
+
+		abe_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x6c>;
+			#clock-cells = <2>;
+		};
+	};
+
+};
+
+&cm2 {
+	l4_ao_cm: l4_ao_cm@600 {
+		compatible = "ti,omap4-cm";
+		reg = <0x600 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x600 0x100>;
+
+		l4_ao_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x1c>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3_1_cm: l3_1_cm@700 {
+		compatible = "ti,omap4-cm";
+		reg = <0x700 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x700 0x100>;
+
+		l3_1_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3_2_cm: l3_2_cm@800 {
+		compatible = "ti,omap4-cm";
+		reg = <0x800 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x800 0x100>;
+
+		l3_2_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x14>;
+			#clock-cells = <2>;
+		};
+	};
+
+	ducati_cm: ducati_cm@900 {
+		compatible = "ti,omap4-cm";
+		reg = <0x900 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x900 0x100>;
+
+		ducati_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3_dma_cm: l3_dma_cm@a00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xa00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xa00 0x100>;
+
+		l3_dma_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3_emif_cm: l3_emif_cm@b00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xb00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xb00 0x100>;
+
+		l3_emif_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x1c>;
+			#clock-cells = <2>;
+		};
+	};
+
+	d2d_cm: d2d_cm@c00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xc00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xc00 0x100>;
+
+		d2d_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l4_cfg_cm: l4_cfg_cm@d00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xd00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xd00 0x100>;
+
+		l4_cfg_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x14>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3_instr_cm: l3_instr_cm@e00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xe00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xe00 0x100>;
+
+		l3_instr_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x24>;
+			#clock-cells = <2>;
+		};
+	};
+
+	ivahd_cm: ivahd_cm@f00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xf00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xf00 0x100>;
+
+		ivahd_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0xc>;
+			#clock-cells = <2>;
+		};
+	};
+
+	iss_cm: iss_cm@1000 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1000 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1000 0x100>;
+
+		iss_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0xc>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3_dss_cm: l3_dss_cm@1100 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1100 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1100 0x100>;
+
+		l3_dss_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3_gfx_cm: l3_gfx_cm@1200 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1200 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1200 0x100>;
+
+		l3_gfx_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3_init_cm: l3_init_cm@1300 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1300 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1300 0x100>;
+
+		l3_init_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0xc4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l4_per_cm: l4_per_cm@1400 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1400 0x200>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1400 0x200>;
+
+		l4_per_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x144>;
+			#clock-cells = <2>;
+		};
+	};
+
+};
+
+&prm {
+	l4_wkup_cm: l4_wkup_cm@1800 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1800 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1800 0x100>;
+
+		l4_wkup_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x5c>;
+			#clock-cells = <2>;
+		};
+	};
+
+	emu_sys_cm: emu_sys_cm@1a00 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1a00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1a00 0x100>;
+
+		emu_sys_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi
index 575ecffb0e9e..1b20838bb9a4 100644
--- a/arch/arm/boot/dts/omap5-board-common.dtsi
+++ b/arch/arm/boot/dts/omap5-board-common.dtsi
@@ -73,12 +73,14 @@
 		clocks = <&auxclk1_ck>;
 		clock-names = "main_clk";
 		clock-frequency = <19200000>;
+		#phy-cells = <0>;
 	};
 
 	/* HS USB Host PHY on PORT 3 */
 	hsusb3_phy: hsusb3_phy {
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio3 15 GPIO_ACTIVE_LOW>; /* gpio3_79 ETH_NRESET */
+		#phy-cells = <0>;
 	};
 
 	tpd12s015: encoder {
diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts
index 5b172a04b6f1..5e21fb430a65 100644
--- a/arch/arm/boot/dts/omap5-cm-t54.dts
+++ b/arch/arm/boot/dts/omap5-cm-t54.dts
@@ -63,12 +63,14 @@
 	hsusb2_phy: hsusb2_phy {
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio3 12 GPIO_ACTIVE_LOW>; /* gpio3_76 HUB_RESET */
+		#phy-cells = <0>;
 	};
 
 	/* HS USB Host PHY on PORT 3 */
 	hsusb3_phy: hsusb3_phy {
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio3 19 GPIO_ACTIVE_LOW>; /* gpio3_83 ETH_RESET */
+		#phy-cells = <0>;
 	};
 
 	leds {
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 4cd0005e462f..35d4298da83d 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -10,6 +10,7 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/pinctrl/omap.h>
+#include <dt-bindings/clock/omap5.h>
 
 / {
 	#address-cells = <2>;
@@ -201,8 +202,12 @@
 			};
 
 			cm_core_aon: cm_core_aon@4000 {
-				compatible = "ti,omap5-cm-core-aon";
+				compatible = "ti,omap5-cm-core-aon",
+					     "simple-bus";
 				reg = <0x4000 0x2000>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 0x4000 0x2000>;
 
 				cm_core_aon_clocks: clocks {
 					#address-cells = <1>;
@@ -214,8 +219,11 @@
 			};
 
 			cm_core: cm_core@8000 {
-				compatible = "ti,omap5-cm-core";
+				compatible = "ti,omap5-cm-core", "simple-bus";
 				reg = <0x8000 0x3000>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 0x8000 0x3000>;
 
 				cm_core_clocks: clocks {
 					#address-cells = <1>;
@@ -240,9 +248,12 @@
 			};
 
 			prm: prm@6000 {
-				compatible = "ti,omap5-prm";
+				compatible = "ti,omap5-prm", "simple-bus";
 				reg = <0x6000 0x3000>;
 				interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 0x6000 0x3000>;
 
 				prm_clocks: clocks {
 					#address-cells = <1>;
@@ -734,6 +745,8 @@
 			interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "timer1";
 			ti,timer-alwon;
+			clocks = <&wkupaon_clkctrl OMAP5_TIMER1_CLKCTRL 24>;
+			clock-names = "fck";
 		};
 
 		timer2: timer@48032000 {
@@ -893,7 +906,8 @@
 				compatible = "ti,omap-usb2";
 				reg = <0x4a084000 0x7c>;
 				syscon-phy-power = <&scm_conf 0x300>;
-				clocks = <&usb_phy_cm_clk32k>, <&usb_otg_ss_refclk960m>;
+				clocks = <&usb_phy_cm_clk32k>,
+					 <&l3init_clkctrl OMAP5_USB_OTG_SS_CLKCTRL 8>;
 				clock-names = "wkupclk", "refclk";
 				#phy-cells = <0>;
 			};
@@ -907,7 +921,7 @@
 				syscon-phy-power = <&scm_conf 0x370>;
 				clocks = <&usb_phy_cm_clk32k>,
 					 <&sys_clkin>,
-					 <&usb_otg_ss_refclk960m>;
+					 <&l3init_clkctrl OMAP5_USB_OTG_SS_CLKCTRL 8>;
 				clock-names =	"wkupclk",
 						"sysclk",
 						"refclk";
@@ -940,6 +954,7 @@
 				compatible = "ti,ohci-omap3";
 				reg = <0x4a064800 0x400>;
 				interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>;
+				remote-wakeup-connected;
 			};
 
 			usbhsehci: ehci@4a064c00 {
@@ -975,7 +990,8 @@
 				      <0x4A096800 0x40>; /* pll_ctrl */
 				reg-names = "phy_rx", "phy_tx", "pll_ctrl";
 				syscon-phy-power = <&scm_conf 0x374>;
-				clocks = <&sys_clkin>, <&sata_ref_clk>;
+				clocks = <&sys_clkin>,
+					 <&l3init_clkctrl OMAP5_SATA_CLKCTRL 8>;
 				clock-names = "sysclk", "refclk";
 				#phy-cells = <0>;
 			};
@@ -987,7 +1003,7 @@
 			interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>;
 			phys = <&sata_phy>;
 			phy-names = "sata-phy";
-			clocks = <&sata_ref_clk>;
+			clocks = <&l3init_clkctrl OMAP5_SATA_CLKCTRL 8>;
 			ti,hwmods = "sata";
 			ports-implemented = <0x1>;
 		};
@@ -997,7 +1013,7 @@
 			reg = <0x58000000 0x80>;
 			status = "disabled";
 			ti,hwmods = "dss_core";
-			clocks = <&dss_dss_clk>;
+			clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>;
 			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -1008,7 +1024,7 @@
 				reg = <0x58001000 0x1000>;
 				interrupts = <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>;
 				ti,hwmods = "dss_dispc";
-				clocks = <&dss_dss_clk>;
+				clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>;
 				clock-names = "fck";
 			};
 
@@ -1017,7 +1033,7 @@
 				reg = <0x58002000 0x100>;
 				status = "disabled";
 				ti,hwmods = "dss_rfbi";
-				clocks = <&dss_dss_clk>, <&l3_iclk_div>;
+				clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>, <&l3_iclk_div>;
 				clock-names = "fck", "ick";
 			};
 
@@ -1030,7 +1046,8 @@
 				interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 				ti,hwmods = "dss_dsi1";
-				clocks = <&dss_dss_clk>, <&dss_sys_clk>;
+				clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>,
+					 <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 10>;
 				clock-names = "fck", "sys_clk";
 			};
 
@@ -1043,7 +1060,8 @@
 				interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 				ti,hwmods = "dss_dsi2";
-				clocks = <&dss_dss_clk>, <&dss_sys_clk>;
+				clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>,
+					 <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 10>;
 				clock-names = "fck", "sys_clk";
 			};
 
@@ -1057,7 +1075,8 @@
 				interrupts = <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 				ti,hwmods = "dss_hdmi";
-				clocks = <&dss_48mhz_clk>, <&dss_sys_clk>;
+				clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 9>,
+					 <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 10>;
 				clock-names = "fck", "sys_clk";
 				dmas = <&sdma 76>;
 				dma-names = "audio_tx";
@@ -1131,7 +1150,7 @@
 	coefficients = <65 (-1791)>;
 };
 
-/include/ "omap54xx-clocks.dtsi"
+#include "omap54xx-clocks.dtsi"
 
 &gpu_thermal {
 	coefficients = <117 (-2992)>;
diff --git a/arch/arm/boot/dts/omap54xx-clocks.dtsi b/arch/arm/boot/dts/omap54xx-clocks.dtsi
index 529193442620..9619a746d657 100644
--- a/arch/arm/boot/dts/omap54xx-clocks.dtsi
+++ b/arch/arm/boot/dts/omap54xx-clocks.dtsi
@@ -432,22 +432,6 @@
 		reg = <0x0528>;
 	};
 
-	dmic_sync_mux_ck: dmic_sync_mux_ck@538 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&dss_syc_gfclk_div>, <&func_24m_clk>;
-		ti,bit-shift = <26>;
-		reg = <0x0538>;
-	};
-
-	dmic_gfclk: dmic_gfclk@538 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&dmic_sync_mux_ck>, <&pad_clks_ck>, <&slimbus_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x0538>;
-	};
-
 	mcasp_sync_mux_ck: mcasp_sync_mux_ck@540 {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
@@ -464,86 +448,6 @@
 		reg = <0x0540>;
 	};
 
-	mcbsp1_sync_mux_ck: mcbsp1_sync_mux_ck@548 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&dss_syc_gfclk_div>, <&func_24m_clk>;
-		ti,bit-shift = <26>;
-		reg = <0x0548>;
-	};
-
-	mcbsp1_gfclk: mcbsp1_gfclk@548 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&mcbsp1_sync_mux_ck>, <&pad_clks_ck>, <&slimbus_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x0548>;
-	};
-
-	mcbsp2_sync_mux_ck: mcbsp2_sync_mux_ck@550 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&dss_syc_gfclk_div>, <&func_24m_clk>;
-		ti,bit-shift = <26>;
-		reg = <0x0550>;
-	};
-
-	mcbsp2_gfclk: mcbsp2_gfclk@550 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&mcbsp2_sync_mux_ck>, <&pad_clks_ck>, <&slimbus_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x0550>;
-	};
-
-	mcbsp3_sync_mux_ck: mcbsp3_sync_mux_ck@558 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&dss_syc_gfclk_div>, <&func_24m_clk>;
-		ti,bit-shift = <26>;
-		reg = <0x0558>;
-	};
-
-	mcbsp3_gfclk: mcbsp3_gfclk@558 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&mcbsp3_sync_mux_ck>, <&pad_clks_ck>, <&slimbus_clk>;
-		ti,bit-shift = <24>;
-		reg = <0x0558>;
-	};
-
-	timer5_gfclk_mux: timer5_gfclk_mux@568 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&dss_syc_gfclk_div>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x0568>;
-	};
-
-	timer6_gfclk_mux: timer6_gfclk_mux@570 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&dss_syc_gfclk_div>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x0570>;
-	};
-
-	timer7_gfclk_mux: timer7_gfclk_mux@578 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&dss_syc_gfclk_div>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x0578>;
-	};
-
-	timer8_gfclk_mux: timer8_gfclk_mux@580 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&dss_syc_gfclk_div>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x0580>;
-	};
-
 	dummy_ck: dummy_ck {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
@@ -603,23 +507,8 @@
 		clock-mult = <1>;
 		clock-div = <1>;
 	};
-
-	gpio1_dbclk: gpio1_dbclk@1938 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1938>;
-	};
-
-	timer1_gfclk_mux: timer1_gfclk_mux@1940 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1940>;
-	};
 };
+
 &cm_core_clocks {
 
 	dpll_per_byp_mux: dpll_per_byp_mux@14c {
@@ -825,95 +714,6 @@
 		ti,dividers = <1>, <8>;
 	};
 
-	dss_32khz_clk: dss_32khz_clk@1420 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <11>;
-		reg = <0x1420>;
-	};
-
-	dss_48mhz_clk: dss_48mhz_clk@1420 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&func_48m_fclk>;
-		ti,bit-shift = <9>;
-		reg = <0x1420>;
-	};
-
-	dss_dss_clk: dss_dss_clk@1420 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_h12x2_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1420>;
-		ti,set-rate-parent;
-	};
-
-	dss_sys_clk: dss_sys_clk@1420 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dss_syc_gfclk_div>;
-		ti,bit-shift = <10>;
-		reg = <0x1420>;
-	};
-
-	gpio2_dbclk: gpio2_dbclk@1060 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1060>;
-	};
-
-	gpio3_dbclk: gpio3_dbclk@1068 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1068>;
-	};
-
-	gpio4_dbclk: gpio4_dbclk@1070 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1070>;
-	};
-
-	gpio5_dbclk: gpio5_dbclk@1078 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1078>;
-	};
-
-	gpio6_dbclk: gpio6_dbclk@1080 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1080>;
-	};
-
-	gpio7_dbclk: gpio7_dbclk@1110 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1110>;
-	};
-
-	gpio8_dbclk: gpio8_dbclk@1118 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1118>;
-	};
-
 	iss_ctrlclk: iss_ctrlclk@1320 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
@@ -938,118 +738,6 @@
 		reg = <0x0f20>;
 	};
 
-	mmc1_32khz_clk: mmc1_32khz_clk@1628 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_32k_ck>;
-		ti,bit-shift = <8>;
-		reg = <0x1628>;
-	};
-
-	sata_ref_clk: sata_ref_clk@1688 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&sys_clkin>;
-		ti,bit-shift = <8>;
-		reg = <0x1688>;
-	};
-
-	usb_host_hs_hsic480m_p1_clk: usb_host_hs_hsic480m_p1_clk@1658 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_usb_m2_ck>;
-		ti,bit-shift = <13>;
-		reg = <0x1658>;
-	};
-
-	usb_host_hs_hsic480m_p2_clk: usb_host_hs_hsic480m_p2_clk@1658 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_usb_m2_ck>;
-		ti,bit-shift = <14>;
-		reg = <0x1658>;
-	};
-
-	usb_host_hs_hsic480m_p3_clk: usb_host_hs_hsic480m_p3_clk@1658 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_usb_m2_ck>;
-		ti,bit-shift = <7>;
-		reg = <0x1658>;
-	};
-
-	usb_host_hs_hsic60m_p1_clk: usb_host_hs_hsic60m_p1_clk@1658 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l3init_60m_fclk>;
-		ti,bit-shift = <11>;
-		reg = <0x1658>;
-	};
-
-	usb_host_hs_hsic60m_p2_clk: usb_host_hs_hsic60m_p2_clk@1658 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l3init_60m_fclk>;
-		ti,bit-shift = <12>;
-		reg = <0x1658>;
-	};
-
-	usb_host_hs_hsic60m_p3_clk: usb_host_hs_hsic60m_p3_clk@1658 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l3init_60m_fclk>;
-		ti,bit-shift = <6>;
-		reg = <0x1658>;
-	};
-
-	utmi_p1_gfclk: utmi_p1_gfclk@1658 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&l3init_60m_fclk>, <&xclk60mhsp1_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1658>;
-	};
-
-	usb_host_hs_utmi_p1_clk: usb_host_hs_utmi_p1_clk@1658 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&utmi_p1_gfclk>;
-		ti,bit-shift = <8>;
-		reg = <0x1658>;
-	};
-
-	utmi_p2_gfclk: utmi_p2_gfclk@1658 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&l3init_60m_fclk>, <&xclk60mhsp2_ck>;
-		ti,bit-shift = <25>;
-		reg = <0x1658>;
-	};
-
-	usb_host_hs_utmi_p2_clk: usb_host_hs_utmi_p2_clk@1658 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&utmi_p2_gfclk>;
-		ti,bit-shift = <9>;
-		reg = <0x1658>;
-	};
-
-	usb_host_hs_utmi_p3_clk: usb_host_hs_utmi_p3_clk@1658 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l3init_60m_fclk>;
-		ti,bit-shift = <10>;
-		reg = <0x1658>;
-	};
-
-	usb_otg_ss_refclk960m: usb_otg_ss_refclk960m@16f0 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&dpll_usb_clkdcoldo>;
-		ti,bit-shift = <8>;
-		reg = <0x16f0>;
-	};
-
 	usb_phy_cm_clk32k: usb_phy_cm_clk32k@640 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
@@ -1058,30 +746,6 @@
 		reg = <0x0640>;
 	};
 
-	usb_tll_hs_usb_ch0_clk: usb_tll_hs_usb_ch0_clk@1668 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l3init_60m_fclk>;
-		ti,bit-shift = <8>;
-		reg = <0x1668>;
-	};
-
-	usb_tll_hs_usb_ch1_clk: usb_tll_hs_usb_ch1_clk@1668 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l3init_60m_fclk>;
-		ti,bit-shift = <9>;
-		reg = <0x1668>;
-	};
-
-	usb_tll_hs_usb_ch2_clk: usb_tll_hs_usb_ch2_clk@1668 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l3init_60m_fclk>;
-		ti,bit-shift = <10>;
-		reg = <0x1668>;
-	};
-
 	fdif_fclk: fdif_fclk@1328 {
 		#clock-cells = <0>;
 		compatible = "ti,divider-clock";
@@ -1115,88 +779,6 @@
 		ti,max-div = <2>;
 		reg = <0x1638>;
 	};
-
-	mmc1_fclk_mux: mmc1_fclk_mux@1628 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_128m_clk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1628>;
-	};
-
-	mmc1_fclk: mmc1_fclk@1628 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&mmc1_fclk_mux>;
-		ti,bit-shift = <25>;
-		ti,max-div = <2>;
-		reg = <0x1628>;
-	};
-
-	mmc2_fclk_mux: mmc2_fclk_mux@1630 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&func_128m_clk>, <&dpll_per_m2x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1630>;
-	};
-
-	mmc2_fclk: mmc2_fclk@1630 {
-		#clock-cells = <0>;
-		compatible = "ti,divider-clock";
-		clocks = <&mmc2_fclk_mux>;
-		ti,bit-shift = <25>;
-		ti,max-div = <2>;
-		reg = <0x1630>;
-	};
-
-	timer10_gfclk_mux: timer10_gfclk_mux@1028 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1028>;
-	};
-
-	timer11_gfclk_mux: timer11_gfclk_mux@1030 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1030>;
-	};
-
-	timer2_gfclk_mux: timer2_gfclk_mux@1038 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1038>;
-	};
-
-	timer3_gfclk_mux: timer3_gfclk_mux@1040 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1040>;
-	};
-
-	timer4_gfclk_mux: timer4_gfclk_mux@1048 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1048>;
-	};
-
-	timer9_gfclk_mux: timer9_gfclk_mux@1050 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&sys_clkin>, <&sys_32k_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x1050>;
-	};
 };
 
 &cm_core_clockdomains {
@@ -1394,3 +976,206 @@
 		reg = <0x021c>;
 	};
 };
+
+&cm_core_aon {
+	mpu_cm: mpu_cm@300 {
+		compatible = "ti,omap4-cm";
+		reg = <0x300 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x300 0x100>;
+
+		mpu_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	dsp_cm: dsp_cm@400 {
+		compatible = "ti,omap4-cm";
+		reg = <0x400 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x400 0x100>;
+
+		dsp_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	abe_cm: abe_cm@500 {
+		compatible = "ti,omap4-cm";
+		reg = <0x500 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x500 0x100>;
+
+		abe_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x64>;
+			#clock-cells = <2>;
+		};
+	};
+
+};
+
+&cm_core {
+	l3main1_cm: l3main1_cm@700 {
+		compatible = "ti,omap4-cm";
+		reg = <0x700 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x700 0x100>;
+
+		l3main1_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3main2_cm: l3main2_cm@800 {
+		compatible = "ti,omap4-cm";
+		reg = <0x800 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x800 0x100>;
+
+		l3main2_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	ipu_cm: ipu_cm@900 {
+		compatible = "ti,omap4-cm";
+		reg = <0x900 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x900 0x100>;
+
+		ipu_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	dma_cm: dma_cm@a00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xa00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xa00 0x100>;
+
+		dma_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	emif_cm: emif_cm@b00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xb00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xb00 0x100>;
+
+		emif_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x1c>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l4cfg_cm: l4cfg_cm@d00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xd00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xd00 0x100>;
+
+		l4cfg_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x14>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3instr_cm: l3instr_cm@e00 {
+		compatible = "ti,omap4-cm";
+		reg = <0xe00 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0xe00 0x100>;
+
+		l3instr_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0xc>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l4per_cm: l4per_cm@1000 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1000 0x200>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1000 0x200>;
+
+		l4per_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x15c>;
+			#clock-cells = <2>;
+		};
+	};
+
+	dss_cm: dss_cm@1400 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1400 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1400 0x100>;
+
+		dss_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
+	l3init_cm: l3init_cm@1600 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1600 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1600 0x100>;
+
+		l3init_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0xd4>;
+			#clock-cells = <2>;
+		};
+	};
+};
+
+&prm {
+	wkupaon_cm: wkupaon_cm@1900 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1900 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1900 0x100>;
+
+		wkupaon_clkctrl: clk@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x5c>;
+			#clock-cells = <2>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/openbmc-flash-layout.dtsi b/arch/arm/boot/dts/openbmc-flash-layout.dtsi
new file mode 100644
index 000000000000..6c26524e93e1
--- /dev/null
+++ b/arch/arm/boot/dts/openbmc-flash-layout.dtsi
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+partitions {
+	compatible = "fixed-partitions";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	u-boot@0 {
+		reg = <0x0 0x60000>;
+		label = "u-boot";
+	};
+
+	u-boot-env@60000 {
+		reg = <0x60000 0x20000>;
+		label = "u-boot-env";
+	};
+
+	kernel@80000 {
+		reg = <0x80000 0x440000>;
+		label = "kernel";
+	};
+
+	rofs@c0000 {
+		reg = <0x4c0000 0x1740000>;
+		label = "rofs";
+	};
+
+	rwfs@1c00000 {
+		reg = <0x1c00000 0x400000>;
+		label = "rwfs";
+	};
+};
diff --git a/arch/arm/boot/dts/owl-s500-sparky.dts b/arch/arm/boot/dts/owl-s500-sparky.dts
new file mode 100644
index 000000000000..c665ce8b88b4
--- /dev/null
+++ b/arch/arm/boot/dts/owl-s500-sparky.dts
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Allo.com Sparky
+ *
+ * Copyright (c) 2017 Andreas Färber
+ */
+
+/dts-v1/;
+
+#include "owl-s500.dtsi"
+
+/ {
+	compatible = "allo,sparky", "actions,s500";
+	model = "Allo.com Sparky";
+
+	aliases {
+		serial3 = &uart3;
+	};
+
+	chosen {
+		stdout-path = "serial3:115200n8";
+	};
+
+	memory@0 {
+		device_type = "memory";
+		reg = <0x0 0x40000000>; /* 1 or 2 GiB */
+	};
+
+	uart3_clk: uart3-clk {
+		compatible = "fixed-clock";
+		clock-frequency = <921600>;
+		#clock-cells = <0>;
+	};
+};
+
+&timer {
+	clocks = <&hosc>;
+};
+
+&uart3 {
+	status = "okay";
+	clocks = <&uart3_clk>;
+};
diff --git a/arch/arm/boot/dts/wd-mbwe.dts b/arch/arm/boot/dts/ox810se-wd-mbwe.dts
index ac3250ae8fc4..ac3250ae8fc4 100644
--- a/arch/arm/boot/dts/wd-mbwe.dts
+++ b/arch/arm/boot/dts/ox810se-wd-mbwe.dts
diff --git a/arch/arm/boot/dts/cloudengines-pogoplug-series-3.dts b/arch/arm/boot/dts/ox820-cloudengines-pogoplug-series-3.dts
index bfde32e37123..bfde32e37123 100644
--- a/arch/arm/boot/dts/cloudengines-pogoplug-series-3.dts
+++ b/arch/arm/boot/dts/ox820-cloudengines-pogoplug-series-3.dts
diff --git a/arch/arm/boot/dts/pm9g45.dts b/arch/arm/boot/dts/pm9g45.dts
index be5177221cbb..927d00cab014 100644
--- a/arch/arm/boot/dts/pm9g45.dts
+++ b/arch/arm/boot/dts/pm9g45.dts
@@ -52,6 +52,18 @@
 				};
 			};
 
+			tcb0: timer@fff7c000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			mmc0: mmc@fff80000 {
 				pinctrl-0 = <
 					&pinctrl_board_mmc
diff --git a/arch/arm/boot/dts/qcom-msm8974-fairphone-fp2.dts b/arch/arm/boot/dts/qcom-msm8974-fairphone-fp2.dts
index d0a5df90b543..643c57f84818 100644
--- a/arch/arm/boot/dts/qcom-msm8974-fairphone-fp2.dts
+++ b/arch/arm/boot/dts/qcom-msm8974-fairphone-fp2.dts
@@ -265,6 +265,28 @@
 				bias-pull-up;
 			};
 		};
+
+		sdhc2_cd_pin_a: sdhc2-cd-pin-active {
+			pins = "gpio62";
+			function = "gpio";
+
+			drive-strength = <2>;
+			bias-disable;
+		};
+
+		sdhc2_pin_a: sdhc2-pin-active {
+			clk {
+				pins = "sdc2_clk";
+				drive-strength = <10>;
+				bias-disable;
+			};
+
+			cmd-data {
+				pins = "sdc2_cmd", "sdc2_data";
+				drive-strength = <6>;
+				bias-pull-up;
+			};
+		};
 	};
 
 	sdhci@f9824900 {
@@ -280,6 +302,18 @@
 		pinctrl-0 = <&sdhc1_pin_a>;
 	};
 
+	sdhci@f98a4900 {
+		status = "ok";
+
+		vmmc-supply = <&pm8941_l21>;
+		vqmmc-supply = <&pm8941_l13>;
+
+		bus-width = <4>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&sdhc2_pin_a>, <&sdhc2_cd_pin_a>;
+	};
+
 	usb@f9a55000 {
 		status = "ok";
 
diff --git a/arch/arm/boot/dts/r7s72100-genmai.dts b/arch/arm/boot/dts/r7s72100-genmai.dts
index cd4d5ff7749e..5af2a0116ff2 100644
--- a/arch/arm/boot/dts/r7s72100-genmai.dts
+++ b/arch/arm/boot/dts/r7s72100-genmai.dts
@@ -123,7 +123,7 @@
 	pinctrl-0 = <&i2c2_pins>;
 
 	eeprom@50 {
-		compatible = "renesas,24c128", "atmel,24c128";
+		compatible = "renesas,r1ex24128", "atmel,24c128";
 		reg = <0x50>;
 		pagesize = <64>;
 	};
diff --git a/arch/arm/boot/dts/r8a73a4.dtsi b/arch/arm/boot/dts/r8a73a4.dtsi
index dd4d09712a2a..8e48090e4fdc 100644
--- a/arch/arm/boot/dts/r8a73a4.dtsi
+++ b/arch/arm/boot/dts/r8a73a4.dtsi
@@ -132,15 +132,12 @@
 	};
 
 	cmt1: timer@e6130000 {
-		compatible = "renesas,cmt-48-r8a73a4", "renesas,cmt-48-gen2";
+		compatible = "renesas,r8a73a4-cmt1", "renesas,rcar-gen2-cmt1";
 		reg = <0 0xe6130000 0 0x1004>;
 		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A73A4_CLK_CMT1>;
 		clock-names = "fck";
 		power-domains = <&pd_c5>;
-
-		renesas,channels-mask = <0xff>;
-
 		status = "disabled";
 	};
 
diff --git a/arch/arm/boot/dts/r8a7740-armadillo800eva.dts b/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
index 1788e186a512..03b00d87b39b 100644
--- a/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
+++ b/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
@@ -131,9 +131,8 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "i2c-gpio";
-		gpios = <&pfc 208 GPIO_ACTIVE_HIGH /* sda */
-			 &pfc 91 GPIO_ACTIVE_HIGH /* scl */
-			>;
+		sda-gpios = <&pfc 208 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		scl-gpios = <&pfc 91 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 		i2c-gpio,delay-us = <5>;
 	};
 
diff --git a/arch/arm/boot/dts/r8a7740.dtsi b/arch/arm/boot/dts/r8a7740.dtsi
index d37d22682a63..afd3bc5e6cf2 100644
--- a/arch/arm/boot/dts/r8a7740.dtsi
+++ b/arch/arm/boot/dts/r8a7740.dtsi
@@ -74,9 +74,6 @@
 		clocks = <&mstp3_clks R8A7740_CLK_CMT1>;
 		clock-names = "fck";
 		power-domains = <&pd_c5>;
-
-		renesas,channels-mask = <0x3f>;
-
 		status = "disabled";
 	};
 
@@ -320,7 +317,7 @@
 
 	tpu: pwm@e6600000 {
 		compatible = "renesas,tpu-r8a7740", "renesas,tpu";
-		reg = <0xe6600000 0x100>;
+		reg = <0xe6600000 0x148>;
 		clocks = <&mstp3_clks R8A7740_CLK_TPU0>;
 		power-domains = <&pd_a3sp>;
 		status = "disabled";
diff --git a/arch/arm/boot/dts/r8a7743.dtsi b/arch/arm/boot/dts/r8a7743.dtsi
index 7bbba4a36f31..0b74c6c7d21d 100644
--- a/arch/arm/boot/dts/r8a7743.dtsi
+++ b/arch/arm/boot/dts/r8a7743.dtsi
@@ -32,6 +32,40 @@
 		spi1 = &msiof0;
 		spi2 = &msiof1;
 		spi3 = &msiof2;
+		vin0 = &vin0;
+		vin1 = &vin1;
+		vin2 = &vin2;
+	};
+
+	/*
+	 * The external audio clocks are configured as 0 Hz fixed frequency
+	 * clocks by default.
+	 * Boards that provide audio clocks should override them.
+	 */
+	audio_clk_a: audio_clk_a {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	audio_clk_b: audio_clk_b {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	audio_clk_c: audio_clk_c {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	/* External CAN clock */
+	can_clk: can {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board. */
+		clock-frequency = <0>;
 	};
 
 	cpus {
@@ -76,6 +110,29 @@
 		};
 	};
 
+	/* External root clock */
+	extal_clk: extal {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board. */
+		clock-frequency = <0>;
+	};
+
+	/* External PCIe clock - can be overridden by the board */
+	pcie_bus_clk: pcie_bus {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	/* External SCIF clock */
+	scif_clk: scif {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board. */
+		clock-frequency = <0>;
+	};
+
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
@@ -247,16 +304,48 @@
 			resets = <&cpg 407>;
 		};
 
-		timer {
-			compatible = "arm,armv7-timer";
-			interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) |
-						  IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) |
-						  IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) |
-						  IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) |
-						  IRQ_TYPE_LEVEL_LOW)>;
+		thermal: thermal@e61f0000 {
+			compatible = "renesas,thermal-r8a7743",
+				     "renesas,rcar-gen2-thermal",
+				     "renesas,rcar-thermal";
+			reg = <0 0xe61f0000 0 0x10>, <0 0xe61f0100 0 0x38>;
+			interrupts = <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 522>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 522>;
+			#thermal-sensor-cells = <0>;
+		};
+
+		cmt0: timer@ffca0000 {
+			compatible = "renesas,r8a7743-cmt0",
+				     "renesas,rcar-gen2-cmt0";
+			reg = <0 0xffca0000 0 0x1004>;
+			interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 124>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 124>;
+			status = "disabled";
+		};
+
+		cmt1: timer@e6130000 {
+			compatible = "renesas,r8a7743-cmt1",
+				     "renesas,rcar-gen2-cmt1";
+			reg = <0 0xe6130000 0 0x1004>;
+			interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 329>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 329>;
+			status = "disabled";
 		};
 
 		cpg: clock-controller@e6150000 {
@@ -356,6 +445,68 @@
 			dma-channels = <15>;
 		};
 
+		audma0: dma-controller@ec700000 {
+			compatible = "renesas,dmac-r8a7743",
+				     "renesas,rcar-dmac";
+			reg = <0 0xec700000 0 0x10000>;
+			interrupts = <GIC_SPI 346 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 320 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 321 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 322 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 323 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 324 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 325 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 326 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 327 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 328 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 329 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 330 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 331 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 332 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12";
+			clocks = <&cpg CPG_MOD 502>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 502>;
+			#dma-cells = <1>;
+			dma-channels = <13>;
+		};
+
+		audma1: dma-controller@ec720000 {
+			compatible = "renesas,dmac-r8a7743",
+				     "renesas,rcar-dmac";
+			reg = <0 0xec720000 0 0x10000>;
+			interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 333 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 334 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 336 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 337 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 338 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 340 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 343 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 344 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 345 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12";
+			clocks = <&cpg CPG_MOD 501>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 501>;
+			#dma-cells = <1>;
+			dma-channels = <13>;
+		};
+
 		usb_dmac0: dma-controller@e65a0000 {
 			compatible = "renesas,r8a7743-usb-dmac",
 				     "renesas,usb-dmac";
@@ -827,7 +978,8 @@
 		};
 
 		ether: ethernet@ee700000 {
-			compatible = "renesas,ether-r8a7743";
+			compatible = "renesas,ether-r8a7743",
+				     "renesas,rcar-gen2-ether";
 			reg = <0 0xee700000 0 0x400>;
 			interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 813>;
@@ -952,8 +1104,89 @@
 			status = "disabled";
 		};
 
+		pwm0: pwm@e6e30000 {
+			compatible = "renesas,pwm-r8a7743", "renesas,pwm-rcar";
+			reg = <0 0xe6e30000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm1: pwm@e6e31000 {
+			compatible = "renesas,pwm-r8a7743", "renesas,pwm-rcar";
+			reg = <0 0xe6e31000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm2: pwm@e6e32000 {
+			compatible = "renesas,pwm-r8a7743", "renesas,pwm-rcar";
+			reg = <0 0xe6e32000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm3: pwm@e6e33000 {
+			compatible = "renesas,pwm-r8a7743", "renesas,pwm-rcar";
+			reg = <0 0xe6e33000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm4: pwm@e6e34000 {
+			compatible = "renesas,pwm-r8a7743", "renesas,pwm-rcar";
+			reg = <0 0xe6e34000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm5: pwm@e6e35000 {
+			compatible = "renesas,pwm-r8a7743", "renesas,pwm-rcar";
+			reg = <0 0xe6e35000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm6: pwm@e6e36000 {
+			compatible = "renesas,pwm-r8a7743", "renesas,pwm-rcar";
+			reg = <0 0xe6e36000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		tpu: pwm@e60f0000 {
+			compatible = "renesas,tpu-r8a7743", "renesas,tpu";
+			reg = <0 0xe60f0000 0 0x148>;
+			clocks = <&cpg CPG_MOD 304>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 304>;
+			#pwm-cells = <3>;
+			status = "disabled";
+		};
+
 		sdhi0: sd@ee100000 {
-			compatible = "renesas,sdhi-r8a7743";
+			compatible = "renesas,sdhi-r8a7743",
+				     "renesas,rcar-gen2-sdhi";
 			reg = <0 0xee100000 0 0x328>;
 			interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 314>;
@@ -967,7 +1200,8 @@
 		};
 
 		sdhi1: sd@ee140000 {
-			compatible = "renesas,sdhi-r8a7743";
+			compatible = "renesas,sdhi-r8a7743",
+				     "renesas,rcar-gen2-sdhi";
 			reg = <0 0xee140000 0 0x100>;
 			interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 312>;
@@ -981,7 +1215,8 @@
 		};
 
 		sdhi2: sd@ee160000 {
-			compatible = "renesas,sdhi-r8a7743";
+			compatible = "renesas,sdhi-r8a7743",
+				     "renesas,rcar-gen2-sdhi";
 			reg = <0 0xee160000 0 0x100>;
 			interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 311>;
@@ -1033,6 +1268,97 @@
 			};
 		};
 
+		vin0: video@e6ef0000 {
+			compatible = "renesas,vin-r8a7743",
+				     "renesas,rcar-gen2-vin";
+			reg = <0 0xe6ef0000 0 0x1000>;
+			interrupts = <GIC_SPI 188 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 811>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 811>;
+			status = "disabled";
+		};
+
+		vin1: video@e6ef1000 {
+			compatible = "renesas,vin-r8a7743",
+				     "renesas,rcar-gen2-vin";
+			reg = <0 0xe6ef1000 0 0x1000>;
+			interrupts = <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 810>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 810>;
+			status = "disabled";
+		};
+
+		vin2: video@e6ef2000 {
+			compatible = "renesas,vin-r8a7743",
+				     "renesas,rcar-gen2-vin";
+			reg = <0 0xe6ef2000 0 0x1000>;
+			interrupts = <GIC_SPI 190 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 809>;
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 809>;
+			status = "disabled";
+		};
+
+		du: display@feb00000 {
+			compatible = "renesas,du-r8a7743";
+			reg = <0 0xfeb00000 0 0x40000>,
+			      <0 0xfeb90000 0 0x1c>;
+			reg-names = "du", "lvds.0";
+			interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 724>,
+				 <&cpg CPG_MOD 723>,
+				 <&cpg CPG_MOD 726>;
+			clock-names = "du.0", "du.1", "lvds.0";
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					du_out_rgb: endpoint {
+					};
+				};
+				port@1 {
+					reg = <1>;
+					du_out_lvds0: endpoint {
+					};
+				};
+			};
+		};
+
+		can0: can@e6e80000 {
+			compatible = "renesas,can-r8a7743",
+				     "renesas,rcar-gen2-can";
+			reg = <0 0xe6e80000 0 0x1000>;
+			interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 916>,
+				 <&cpg CPG_CORE R8A7743_CLK_RCAN>,
+				 <&can_clk>;
+			clock-names = "clkp1", "clkp2", "can_clk";
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 916>;
+			status = "disabled";
+		};
+
+		can1: can@e6e88000 {
+			compatible = "renesas,can-r8a7743",
+				     "renesas,rcar-gen2-can";
+			reg = <0 0xe6e88000 0 0x1000>;
+			interrupts = <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 915>,
+				 <&cpg CPG_CORE R8A7743_CLK_RCAN>,
+				 <&can_clk>;
+			clock-names = "clkp1", "clkp2", "can_clk";
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 915>;
+			status = "disabled";
+		};
+
 		pci0: pci@ee090000 {
 			compatible = "renesas,pci-r8a7743",
 				     "renesas,pci-rcar-gen2";
@@ -1102,14 +1428,247 @@
 				phy-names = "usb";
 			};
 		};
+
+		pciec: pcie@fe000000 {
+			compatible = "renesas,pcie-r8a7743",
+				     "renesas,pcie-rcar-gen2";
+			reg = <0 0xfe000000 0 0x80000>;
+			#address-cells = <3>;
+			#size-cells = <2>;
+			bus-range = <0x00 0xff>;
+			device_type = "pci";
+			ranges = <0x01000000 0 0x00000000 0 0xfe100000 0 0x00100000
+				  0x02000000 0 0xfe200000 0 0xfe200000 0 0x00200000
+				  0x02000000 0 0x30000000 0 0x30000000 0 0x08000000
+				  0x42000000 0 0x38000000 0 0x38000000 0 0x08000000>;
+			/* Map all possible DDR as inbound ranges */
+			dma-ranges = <0x42000000 0 0x40000000 0 0x40000000 0 0x80000000
+				      0x43000000 2 0x00000000 2 0x00000000 1 0x00000000>;
+			interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>;
+			#interrupt-cells = <1>;
+			interrupt-map-mask = <0 0 0 0>;
+			interrupt-map = <0 0 0 0 &gic GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 319>, <&pcie_bus_clk>;
+			clock-names = "pcie", "pcie_bus";
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 319>;
+			status = "disabled";
+		};
+
+		rcar_sound: sound@ec500000 {
+			/*
+			 * #sound-dai-cells is required
+			 *
+			 * Single DAI : #sound-dai-cells = <0>;         <&rcar_sound>;
+			 * Multi  DAI : #sound-dai-cells = <1>;         <&rcar_sound N>;
+			 */
+			compatible = "renesas,rcar_sound-r8a7743",
+				     "renesas,rcar_sound-gen2";
+			reg = <0 0xec500000 0 0x1000>, /* SCU */
+			      <0 0xec5a0000 0 0x100>,  /* ADG */
+			      <0 0xec540000 0 0x1000>, /* SSIU */
+			      <0 0xec541000 0 0x280>,  /* SSI */
+			      <0 0xec740000 0 0x200>;  /* Audio DMAC peri peri*/
+			reg-names = "scu", "adg", "ssiu", "ssi", "audmapp";
+
+			clocks = <&cpg CPG_MOD 1005>,
+				 <&cpg CPG_MOD 1006>, <&cpg CPG_MOD 1007>,
+				 <&cpg CPG_MOD 1008>, <&cpg CPG_MOD 1009>,
+				 <&cpg CPG_MOD 1010>, <&cpg CPG_MOD 1011>,
+				 <&cpg CPG_MOD 1012>, <&cpg CPG_MOD 1013>,
+				 <&cpg CPG_MOD 1014>, <&cpg CPG_MOD 1015>,
+				 <&cpg CPG_MOD 1022>, <&cpg CPG_MOD 1023>,
+				 <&cpg CPG_MOD 1024>, <&cpg CPG_MOD 1025>,
+				 <&cpg CPG_MOD 1026>, <&cpg CPG_MOD 1027>,
+				 <&cpg CPG_MOD 1028>, <&cpg CPG_MOD 1029>,
+				 <&cpg CPG_MOD 1030>, <&cpg CPG_MOD 1031>,
+				 <&cpg CPG_MOD 1021>, <&cpg CPG_MOD 1020>,
+				 <&cpg CPG_MOD 1021>, <&cpg CPG_MOD 1020>,
+				 <&cpg CPG_MOD 1019>, <&cpg CPG_MOD 1018>,
+				 <&audio_clk_a>, <&audio_clk_b>, <&audio_clk_c>,
+				 <&cpg CPG_CORE R8A7743_CLK_M2>;
+			clock-names = "ssi-all",
+				      "ssi.9", "ssi.8", "ssi.7", "ssi.6", "ssi.5",
+				      "ssi.4", "ssi.3", "ssi.2", "ssi.1", "ssi.0",
+				      "src.9", "src.8", "src.7", "src.6", "src.5",
+				      "src.4", "src.3", "src.2", "src.1", "src.0",
+				      "ctu.0", "ctu.1",
+				      "mix.0", "mix.1",
+				      "dvc.0", "dvc.1",
+				      "clk_a", "clk_b", "clk_c", "clk_i";
+			power-domains = <&sysc R8A7743_PD_ALWAYS_ON>;
+			resets = <&cpg 1005>,
+				 <&cpg 1006>, <&cpg 1007>, <&cpg 1008>, <&cpg 1009>,
+				 <&cpg 1010>, <&cpg 1011>, <&cpg 1012>, <&cpg 1013>,
+				 <&cpg 1014>, <&cpg 1015>;
+			reset-names = "ssi-all",
+				      "ssi.9", "ssi.8", "ssi.7", "ssi.6", "ssi.5",
+				      "ssi.4", "ssi.3", "ssi.2", "ssi.1", "ssi.0";
+			status = "disabled";
+
+			rcar_sound,dvc {
+				dvc0: dvc-0 {
+					dmas = <&audma1 0xbc>;
+					dma-names = "tx";
+				};
+				dvc1: dvc-1 {
+					dmas = <&audma1 0xbe>;
+					dma-names = "tx";
+				};
+			};
+
+			rcar_sound,mix {
+				mix0: mix-0 { };
+				mix1: mix-1 { };
+			};
+
+			rcar_sound,ctu {
+				ctu00: ctu-0 { };
+				ctu01: ctu-1 { };
+				ctu02: ctu-2 { };
+				ctu03: ctu-3 { };
+				ctu10: ctu-4 { };
+				ctu11: ctu-5 { };
+				ctu12: ctu-6 { };
+				ctu13: ctu-7 { };
+			};
+
+			rcar_sound,src {
+				src0: src-0 {
+					interrupts = <GIC_SPI 352 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x85>, <&audma1 0x9a>;
+					dma-names = "rx", "tx";
+				};
+				src1: src-1 {
+					interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x87>, <&audma1 0x9c>;
+					dma-names = "rx", "tx";
+				};
+				src2: src-2 {
+					interrupts = <GIC_SPI 354 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x89>, <&audma1 0x9e>;
+					dma-names = "rx", "tx";
+				};
+				src3: src-3 {
+					interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x8b>, <&audma1 0xa0>;
+					dma-names = "rx", "tx";
+				};
+				src4: src-4 {
+					interrupts = <GIC_SPI 356 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x8d>, <&audma1 0xb0>;
+					dma-names = "rx", "tx";
+				};
+				src5: src-5 {
+					interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x8f>, <&audma1 0xb2>;
+					dma-names = "rx", "tx";
+				};
+				src6: src-6 {
+					interrupts = <GIC_SPI 358 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x91>, <&audma1 0xb4>;
+					dma-names = "rx", "tx";
+				};
+				src7: src-7 {
+					interrupts = <GIC_SPI 359 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x93>, <&audma1 0xb6>;
+					dma-names = "rx", "tx";
+				};
+				src8: src-8 {
+					interrupts = <GIC_SPI 360 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x95>, <&audma1 0xb8>;
+					dma-names = "rx", "tx";
+				};
+				src9: src-9 {
+					interrupts = <GIC_SPI 361 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x97>, <&audma1 0xba>;
+					dma-names = "rx", "tx";
+				};
+			};
+
+			rcar_sound,ssi {
+				ssi0: ssi-0 {
+					interrupts = <GIC_SPI 370 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x01>, <&audma1 0x02>, <&audma0 0x15>, <&audma1 0x16>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi1: ssi-1 {
+					interrupts = <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x03>, <&audma1 0x04>, <&audma0 0x49>, <&audma1 0x4a>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi2: ssi-2 {
+					interrupts = <GIC_SPI 372 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x05>, <&audma1 0x06>, <&audma0 0x63>, <&audma1 0x64>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi3: ssi-3 {
+					interrupts = <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x07>, <&audma1 0x08>, <&audma0 0x6f>, <&audma1 0x70>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi4: ssi-4 {
+					interrupts = <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x09>, <&audma1 0x0a>, <&audma0 0x71>, <&audma1 0x72>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi5: ssi-5 {
+					interrupts = <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x0b>, <&audma1 0x0c>, <&audma0 0x73>, <&audma1 0x74>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi6: ssi-6 {
+					interrupts = <GIC_SPI 376 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x0d>, <&audma1 0x0e>, <&audma0 0x75>, <&audma1 0x76>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi7: ssi-7 {
+					interrupts = <GIC_SPI 377 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x0f>, <&audma1 0x10>, <&audma0 0x79>, <&audma1 0x7a>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi8: ssi-8 {
+					interrupts = <GIC_SPI 378 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x11>, <&audma1 0x12>, <&audma0 0x7b>, <&audma1 0x7c>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi9: ssi-9 {
+					interrupts = <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x13>, <&audma1 0x14>, <&audma0 0x7d>, <&audma1 0x7e>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+			};
+		};
 	};
 
-	/* External root clock */
-	extal_clk: extal {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		/* This value must be overridden by the board. */
-		clock-frequency = <0>;
+	thermal-zones {
+		cpu_thermal: cpu-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&thermal>;
+
+			trips {
+				cpu-crit {
+					temperature = <95000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+			};
+		};
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
 	};
 
 	/* External USB clock - can be overridden by the board */
@@ -1118,12 +1677,4 @@
 		#clock-cells = <0>;
 		clock-frequency = <48000000>;
 	};
-
-	/* External SCIF clock */
-	scif_clk: scif {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		/* This value must be overridden by the board. */
-		clock-frequency = <0>;
-	};
 };
diff --git a/arch/arm/boot/dts/r8a7745-iwg22d-sodimm-dbhd-ca.dts b/arch/arm/boot/dts/r8a7745-iwg22d-sodimm-dbhd-ca.dts
new file mode 100644
index 000000000000..d34de8266ccd
--- /dev/null
+++ b/arch/arm/boot/dts/r8a7745-iwg22d-sodimm-dbhd-ca.dts
@@ -0,0 +1,158 @@
+/*
+ * Device Tree Source for the iWave-RZG1E SODIMM carrier board + HDMI daughter
+ * board
+ *
+ * Copyright (C) 2017 Renesas Electronics Corp.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include "r8a7745-iwg22d-sodimm.dts"
+
+/ {
+	model = "iWave RainboW-G22D-SODIMM RZ/G1E based board with HDMI add-on";
+	compatible = "iwave,g22d", "iwave,g22m", "renesas,r8a7745";
+
+	aliases {
+		serial0 = &scif1;
+		serial4 = &scif5;
+		serial6 = &hscif2;
+	};
+
+	cec_clock: cec-clock {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <12000000>;
+	};
+
+	hdmi-out {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con: endpoint {
+				remote-endpoint = <&adv7511_out>;
+			};
+		};
+	};
+};
+
+&du {
+	pinctrl-0 = <&du0_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+
+	ports {
+		port@0 {
+			endpoint {
+				remote-endpoint = <&adv7511_in>;
+			};
+		};
+	};
+};
+
+&can1 {
+	pinctrl-0 = <&can1_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&hscif2 {
+	pinctrl-0 = <&hscif2_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&i2c1 {
+	pinctrl-0 = <&i2c1_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+	clock-frequency = <400000>;
+
+	hdmi@39 {
+		compatible = "adi,adv7511w";
+		reg = <0x39>;
+		interrupt-parent = <&gpio1>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&cec_clock>;
+		clock-names = "cec";
+		pd-gpios = <&gpio2 24 GPIO_ACTIVE_HIGH>;
+
+		adi,input-depth = <8>;
+		adi,input-colorspace = "rgb";
+		adi,input-clock = "1x";
+		adi,input-style = <1>;
+		adi,input-justification = "evenly";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				adv7511_in: endpoint {
+					remote-endpoint = <&du_out_rgb0>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				adv7511_out: endpoint {
+					remote-endpoint = <&hdmi_con>;
+				};
+			};
+		};
+	};
+};
+
+&pfc {
+	can1_pins: can1 {
+		groups = "can1_data_b";
+		function = "can1";
+	};
+
+	du0_pins: du0 {
+		groups = "du0_rgb888", "du0_sync", "du0_disp", "du0_clk0_out";
+		function = "du0";
+	};
+
+	hscif2_pins: hscif2 {
+		groups = "hscif2_data";
+		function = "hscif2";
+	};
+
+	i2c1_pins: i2c1 {
+		groups = "i2c1_d";
+		function = "i2c1";
+	};
+
+	scif1_pins: scif1 {
+		groups = "scif1_data";
+		function = "scif1";
+	};
+
+	scif5_pins: scif5 {
+		groups = "scif5_data_d";
+		function = "scif5";
+	};
+};
+
+&scif1 {
+	pinctrl-0 = <&scif1_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&scif5 {
+	pinctrl-0 = <&scif5_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/r8a7745-iwg22d-sodimm.dts b/arch/arm/boot/dts/r8a7745-iwg22d-sodimm.dts
index 52153ec3638c..a4058f4cfbcd 100644
--- a/arch/arm/boot/dts/r8a7745-iwg22d-sodimm.dts
+++ b/arch/arm/boot/dts/r8a7745-iwg22d-sodimm.dts
@@ -8,6 +8,29 @@
  * kind, whether express or implied.
  */
 
+/*
+ * SSI-SGTL5000
+ *
+ * This command is required when Playback/Capture
+ *
+ *      amixer set "DVC Out" 100%
+ *      amixer set "DVC In" 100%
+ *
+ * You can use Mute
+ *
+ *      amixer set "DVC Out Mute" on
+ *      amixer set "DVC In Mute" on
+ *
+ * You can use Volume Ramp
+ *
+ *      amixer set "DVC Out Ramp Up Rate"   "0.125 dB/64 steps"
+ *      amixer set "DVC Out Ramp Down Rate" "0.125 dB/512 steps"
+ *      amixer set "DVC Out Ramp" on
+ *      aplay xxx.wav &
+ *      amixer set "DVC Out"  80%  // Volume Down
+ *      amixer set "DVC Out" 100%  // Volume Up
+ */
+
 /dts-v1/;
 #include "r8a7745-iwg22m.dtsi"
 
@@ -16,13 +39,35 @@
 	compatible = "iwave,g22d", "iwave,g22m", "renesas,r8a7745";
 
 	aliases {
-		serial0 = &scif4;
 		ethernet0 = &avb;
+		serial3 = &scif4;
+		serial5 = &hscif1;
 	};
 
 	chosen {
 		bootargs = "ignore_loglevel rw root=/dev/nfs ip=dhcp";
-		stdout-path = "serial0:115200n8";
+		stdout-path = "serial3:115200n8";
+	};
+
+	audio_clock: audio_clock {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <26000000>;
+	};
+
+	rsnd_sgtl5000: sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,bitclock-master = <&sndcodec>;
+		simple-audio-card,frame-master = <&sndcodec>;
+
+		sndcpu: simple-audio-card,cpu {
+			sound-dai = <&rcar_sound>;
+		};
+
+		sndcodec: simple-audio-card,codec {
+			sound-dai = <&sgtl5000>;
+		};
 	};
 
 	vccq_sdhi0: regulator-vccq-sdhi0 {
@@ -39,53 +84,139 @@
 	};
 };
 
-&pfc {
-	scif4_pins: scif4 {
-		groups = "scif4_data_b";
-		function = "scif4";
+&avb {
+	pinctrl-0 = <&avb_pins>;
+	pinctrl-names = "default";
+
+	phy-handle = <&phy3>;
+	phy-mode = "gmii";
+	renesas,no-ether-link;
+	status = "okay";
+
+	phy3: ethernet-phy@3 {
+	/*
+	 * On some older versions of the platform (before R4.0) the phy address
+	 * may be 1 or 3. The address is fixed to 3 for R4.0 onwards.
+	 */
+		reg = <3>;
+		micrel,led-mode = <1>;
 	};
+};
+
+&can0 {
+	pinctrl-0 = <&can0_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&hscif1 {
+	pinctrl-0 = <&hscif1_pins>;
+	pinctrl-names = "default";
 
+	uart-has-rtscts;
+	status = "okay";
+};
+
+&hsusb {
+	status = "okay";
+	pinctrl-0 = <&usb0_pins>;
+	pinctrl-names = "default";
+};
+
+&i2c5 {
+	pinctrl-0 = <&i2c5_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+	clock-frequency = <400000>;
+
+	sgtl5000: codec@a {
+		compatible = "fsl,sgtl5000";
+		#sound-dai-cells = <0>;
+		reg = <0x0a>;
+		clocks = <&audio_clock>;
+		VDDA-supply = <&reg_3p3v>;
+		VDDIO-supply = <&reg_3p3v>;
+	};
+};
+
+&pci1 {
+	status = "okay";
+	pinctrl-0 = <&usb1_pins>;
+	pinctrl-names = "default";
+};
+
+&pfc {
 	avb_pins: avb {
 		groups = "avb_mdio", "avb_gmii";
 		function = "avb";
 	};
 
+	can0_pins: can0 {
+		groups = "can0_data";
+		function = "can0";
+	};
+
+	hscif1_pins: hscif1 {
+		groups = "hscif1_data", "hscif1_ctrl";
+		function = "hscif1";
+	};
+
+	i2c5_pins: i2c5 {
+		groups = "i2c5_b";
+		function = "i2c5";
+	};
+
+	scif4_pins: scif4 {
+		groups = "scif4_data_b";
+		function = "scif4";
+	};
+
 	sdhi0_pins: sd0 {
 		groups = "sdhi0_data4", "sdhi0_ctrl";
 		function = "sdhi0";
 		power-source = <3300>;
 	};
 
+	sound_pins: sound {
+		groups = "ssi34_ctrl", "ssi3_data", "ssi4_data";
+		function = "ssi";
+	};
+
+	usb0_pins: usb0 {
+		groups = "usb0";
+		function = "usb0";
+	};
+
 	usb1_pins: usb1 {
 		groups = "usb1";
 		function = "usb1";
 	};
 };
 
-&scif4 {
-	pinctrl-0 = <&scif4_pins>;
+&rcar_sound {
+	pinctrl-0 = <&sound_pins>;
 	pinctrl-names = "default";
-
 	status = "okay";
+
+	/* Single DAI */
+
+	#sound-dai-cells = <0>;
+
+	rcar_sound,dai {
+		dai0 {
+			playback = <&ssi3 &src3 &dvc0>;
+			capture = <&ssi4 &src4 &dvc1>;
+		};
+	};
 };
 
-&avb {
-	pinctrl-0 = <&avb_pins>;
+&scif4 {
+	pinctrl-0 = <&scif4_pins>;
 	pinctrl-names = "default";
 
-	phy-handle = <&phy3>;
-	phy-mode = "gmii";
-	renesas,no-ether-link;
 	status = "okay";
-
-	phy3: ethernet-phy@3 {
-	/*
-	 * On some older versions of the platform (before R4.0) the phy address
-	 * may be 1 or 3. The address is fixed to 3 for R4.0 onwards.
-	 */
-		reg = <3>;
-		micrel,led-mode = <1>;
-	};
 };
 
 &sdhi0 {
@@ -98,10 +229,8 @@
 	status = "okay";
 };
 
-&pci1 {
-	status = "okay";
-	pinctrl-0 = <&usb1_pins>;
-	pinctrl-names = "default";
+&ssi4 {
+	shared-pin;
 };
 
 &usbphy {
diff --git a/arch/arm/boot/dts/r8a7745.dtsi b/arch/arm/boot/dts/r8a7745.dtsi
index 3a50f703601c..ae918e9cce21 100644
--- a/arch/arm/boot/dts/r8a7745.dtsi
+++ b/arch/arm/boot/dts/r8a7745.dtsi
@@ -25,15 +25,49 @@
 		i2c3 = &i2c3;
 		i2c4 = &i2c4;
 		i2c5 = &i2c5;
+		i2c6 = &iic0;
+		i2c7 = &iic1;
 		spi0 = &qspi;
 		spi1 = &msiof0;
 		spi2 = &msiof1;
 		spi3 = &msiof2;
+		vin0 = &vin0;
+		vin1 = &vin1;
+	};
+
+	/*
+	 * The external audio clocks are configured  as 0 Hz fixed
+	 * frequency clocks by default.  Boards that provide audio
+	 * clocks should override them.
+	 */
+	audio_clka: audio_clka {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+	audio_clkb: audio_clkb {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+	audio_clkc: audio_clkc {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	/* External CAN clock */
+	can_clk: can {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board. */
+		clock-frequency = <0>;
 	};
 
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
+		enable-method = "renesas,apmu";
 
 		cpu0: cpu@0 {
 			device_type = "cpu";
@@ -45,6 +79,16 @@
 			next-level-cache = <&L2_CA7>;
 		};
 
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <1>;
+			clock-frequency = <1000000000>;
+			clocks = <&cpg CPG_CORE R8A7745_CLK_Z2>;
+			power-domains = <&sysc R8A7745_PD_CA7_CPU1>;
+			next-level-cache = <&L2_CA7>;
+		};
+
 		L2_CA7: cache-controller-0 {
 			compatible = "cache";
 			cache-unified;
@@ -53,6 +97,22 @@
 		};
 	};
 
+	/* External root clock */
+	extal_clk: extal {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board. */
+		clock-frequency = <0>;
+	};
+
+	/* External SCIF clock */
+	scif_clk: scif {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board. */
+		clock-frequency = <0>;
+	};
+
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
@@ -61,6 +121,12 @@
 		#size-cells = <2>;
 		ranges;
 
+		apmu@e6151000 {
+			compatible = "renesas,r8a7745-apmu", "renesas,apmu";
+			reg = <0 0xe6151000 0 0x188>;
+			cpus = <&cpu0 &cpu1>;
+		};
+
 		gic: interrupt-controller@f1001000 {
 			compatible = "arm,gic-400";
 			#interrupt-cells = <3>;
@@ -203,16 +269,36 @@
 			resets = <&cpg 407>;
 		};
 
-		timer {
-			compatible = "arm,armv7-timer";
-			interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) |
-						  IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) |
-						  IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) |
-						  IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) |
-						  IRQ_TYPE_LEVEL_LOW)>;
+		cmt0: timer@ffca0000 {
+			compatible = "renesas,r8a7745-cmt0",
+				     "renesas,rcar-gen2-cmt0";
+			reg = <0 0xffca0000 0 0x1004>;
+			interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 124>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 124>;
+			status = "disabled";
+		};
+
+		cmt1: timer@e6130000 {
+			compatible = "renesas,r8a7745-cmt1",
+				     "renesas,rcar-gen2-cmt1";
+			reg = <0 0xe6130000 0 0x1004>;
+			interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 329>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 329>;
+			status = "disabled";
 		};
 
 		cpg: clock-controller@e6150000 {
@@ -312,6 +398,65 @@
 			dma-channels = <15>;
 		};
 
+		audma0: dma-controller@ec700000 {
+			compatible = "renesas,dmac-r8a7745",
+				     "renesas,rcar-dmac";
+			reg = <0 0xec700000 0 0x10000>;
+			interrupts = <GIC_SPI 346 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 320 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 321 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 322 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 323 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 324 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 325 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 326 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 327 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 328 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 329 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 330 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 331 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 332 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12";
+			clocks = <&cpg CPG_MOD 502>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 502>;
+			#dma-cells = <1>;
+			dma-channels = <13>;
+		};
+
+		usb_dmac0: dma-controller@e65a0000 {
+			compatible = "renesas,r8a7745-usb-dmac",
+				     "renesas,usb-dmac";
+			reg = <0 0xe65a0000 0 0x100>;
+			interrupts = <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "ch0", "ch1";
+			clocks = <&cpg CPG_MOD 330>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 330>;
+			#dma-cells = <1>;
+			dma-channels = <2>;
+		};
+
+		usb_dmac1: dma-controller@e65b0000 {
+			compatible = "renesas,r8a7745-usb-dmac",
+				     "renesas,usb-dmac";
+			reg = <0 0xe65b0000 0 0x100>;
+			interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "ch0", "ch1";
+			clocks = <&cpg CPG_MOD 331>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 331>;
+			#dma-cells = <1>;
+			dma-channels = <2>;
+		};
+
 		scifa0: serial@e6c40000 {
 			compatible = "renesas,scifa-r8a7745",
 				     "renesas,rcar-gen2-scifa", "renesas,scifa";
@@ -615,7 +760,8 @@
 		};
 
 		ether: ethernet@ee700000 {
-			compatible = "renesas,ether-r8a7745";
+			compatible = "renesas,ether-r8a7745",
+				     "renesas,rcar-gen2-ether";
 			reg = <0 0xee700000 0 0x400>;
 			interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 813>;
@@ -724,6 +870,40 @@
 			status = "disabled";
 		};
 
+		iic0: i2c@e6500000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "renesas,iic-r8a7745",
+				     "renesas,rcar-gen2-iic",
+				     "renesas,rmobile-iic";
+			reg = <0 0xe6500000 0 0x425>;
+			interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 318>;
+			dmas = <&dmac0 0x61>, <&dmac0 0x62>,
+			       <&dmac1 0x61>, <&dmac1 0x62>;
+			dma-names = "tx", "rx", "tx", "rx";
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 318>;
+			status = "disabled";
+		};
+
+		iic1: i2c@e6510000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "renesas,iic-r8a7745",
+				     "renesas,rcar-gen2-iic",
+				     "renesas,rmobile-iic";
+			reg = <0 0xe6510000 0 0x425>;
+			interrupts = <GIC_SPI 175 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 323>;
+			dmas = <&dmac0 0x65>, <&dmac0 0x66>,
+			       <&dmac1 0x65>, <&dmac1 0x66>;
+			dma-names = "tx", "rx", "tx", "rx";
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 323>;
+			status = "disabled";
+		};
+
 		mmcif0: mmc@ee200000 {
 			compatible = "renesas,mmcif-r8a7745",
 				     "renesas,sh-mmcif";
@@ -756,6 +936,55 @@
 			status = "disabled";
 		};
 
+		vin0: video@e6ef0000 {
+			compatible = "renesas,vin-r8a7745",
+				     "renesas,rcar-gen2-vin";
+			reg = <0 0xe6ef0000 0 0x1000>;
+			interrupts = <GIC_SPI 188 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 811>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 811>;
+			status = "disabled";
+		};
+
+		vin1: video@e6ef1000 {
+			compatible = "renesas,vin-r8a7745",
+				     "renesas,rcar-gen2-vin";
+			reg = <0 0xe6ef1000 0 0x1000>;
+			interrupts = <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 810>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 810>;
+			status = "disabled";
+		};
+
+		du: display@feb00000 {
+			compatible = "renesas,du-r8a7745";
+			reg = <0 0xfeb00000 0 0x40000>;
+			reg-names = "du";
+			interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>;
+			clock-names = "du.0", "du.1";
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					du_out_rgb0: endpoint {
+					};
+				};
+				port@1 {
+					reg = <1>;
+					du_out_rgb1: endpoint {
+					};
+				};
+			};
+		};
+
 		msiof0: spi@e6e20000 {
 			compatible = "renesas,msiof-r8a7745",
 				     "renesas,rcar-gen2-msiof";
@@ -804,8 +1033,89 @@
 			status = "disabled";
 		};
 
+		pwm0: pwm@e6e30000 {
+			compatible = "renesas,pwm-r8a7745", "renesas,pwm-rcar";
+			reg = <0 0xe6e30000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm1: pwm@e6e31000 {
+			compatible = "renesas,pwm-r8a7745", "renesas,pwm-rcar";
+			reg = <0 0xe6e31000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm2: pwm@e6e32000 {
+			compatible = "renesas,pwm-r8a7745", "renesas,pwm-rcar";
+			reg = <0 0xe6e32000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm3: pwm@e6e33000 {
+			compatible = "renesas,pwm-r8a7745", "renesas,pwm-rcar";
+			reg = <0 0xe6e33000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm4: pwm@e6e34000 {
+			compatible = "renesas,pwm-r8a7745", "renesas,pwm-rcar";
+			reg = <0 0xe6e34000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm5: pwm@e6e35000 {
+			compatible = "renesas,pwm-r8a7745", "renesas,pwm-rcar";
+			reg = <0 0xe6e35000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		pwm6: pwm@e6e36000 {
+			compatible = "renesas,pwm-r8a7745", "renesas,pwm-rcar";
+			reg = <0 0xe6e36000 0 0x8>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 523>;
+			#pwm-cells = <2>;
+			status = "disabled";
+		};
+
+		tpu: pwm@e60f0000 {
+			compatible = "renesas,tpu-r8a7745", "renesas,tpu";
+			reg = <0 0xe60f0000 0 0x148>;
+			clocks = <&cpg CPG_MOD 304>;
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 304>;
+			#pwm-cells = <3>;
+			status = "disabled";
+		};
+
 		sdhi0: sd@ee100000 {
-			compatible = "renesas,sdhi-r8a7745";
+			compatible = "renesas,sdhi-r8a7745",
+				     "renesas,rcar-gen2-sdhi";
 			reg = <0 0xee100000 0 0x328>;
 			interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 314>;
@@ -819,7 +1129,8 @@
 		};
 
 		sdhi1: sd@ee140000 {
-			compatible = "renesas,sdhi-r8a7745";
+			compatible = "renesas,sdhi-r8a7745",
+				     "renesas,rcar-gen2-sdhi";
 			reg = <0 0xee140000 0 0x100>;
 			interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 312>;
@@ -833,7 +1144,8 @@
 		};
 
 		sdhi2: sd@ee160000 {
-			compatible = "renesas,sdhi-r8a7745";
+			compatible = "renesas,sdhi-r8a7745",
+				     "renesas,rcar-gen2-sdhi";
 			reg = <0 0xee160000 0 0x100>;
 			interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 311>;
@@ -916,6 +1228,23 @@
 			};
 		};
 
+		hsusb: usb@e6590000 {
+			compatible = "renesas,usbhs-r8a7745",
+				     "renesas,rcar-gen2-usbhs";
+			reg = <0 0xe6590000 0 0x100>;
+			interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 704>;
+			dmas = <&usb_dmac0 0>, <&usb_dmac0 1>,
+			       <&usb_dmac1 0>, <&usb_dmac1 1>;
+			dma-names = "ch0", "ch1", "ch2", "ch3";
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 704>;
+			renesas,buswait = <4>;
+			phys = <&usb0 1>;
+			phy-names = "usb";
+			status = "disabled";
+		};
+
 		usbphy: usb-phy@e6590100 {
 			compatible = "renesas,usb-phy-r8a7745",
 				     "renesas,rcar-gen2-usb-phy";
@@ -937,14 +1266,222 @@
 				#phy-cells = <1>;
 			};
 		};
+
+		can0: can@e6e80000 {
+			compatible = "renesas,can-r8a7745",
+				     "renesas,rcar-gen2-can";
+			reg = <0 0xe6e80000 0 0x1000>;
+			interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 916>,
+				 <&cpg CPG_CORE R8A7745_CLK_RCAN>,
+				 <&can_clk>;
+			clock-names = "clkp1", "clkp2", "can_clk";
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 916>;
+			status = "disabled";
+		};
+
+		can1: can@e6e88000 {
+			compatible = "renesas,can-r8a7745",
+				     "renesas,rcar-gen2-can";
+			reg = <0 0xe6e88000 0 0x1000>;
+			interrupts = <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 915>,
+				 <&cpg CPG_CORE R8A7745_CLK_RCAN>,
+				 <&can_clk>;
+			clock-names = "clkp1", "clkp2", "can_clk";
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 915>;
+			status = "disabled";
+		};
+
+		rcar_sound: sound@ec500000 {
+			/*
+			 * #sound-dai-cells is required
+			 *
+			 * Single DAI : #sound-dai-cells = <0>; <&rcar_sound>;
+			 * Multi  DAI : #sound-dai-cells = <1>; <&rcar_sound N>;
+			 */
+			compatible = "renesas,rcar_sound-r8a7745",
+				     "renesas,rcar_sound-gen2";
+			reg = <0 0xec500000 0 0x1000>, /* SCU */
+			      <0 0xec5a0000 0 0x100>,  /* ADG */
+			      <0 0xec540000 0 0x1000>, /* SSIU */
+			      <0 0xec541000 0 0x280>,  /* SSI */
+			      <0 0xec740000 0 0x200>;  /* Audio DMAC peri peri */
+			reg-names = "scu", "adg", "ssiu", "ssi", "audmapp";
+
+			clocks = <&cpg CPG_MOD 1005>,
+				 <&cpg CPG_MOD 1006>, <&cpg CPG_MOD 1007>,
+				 <&cpg CPG_MOD 1008>, <&cpg CPG_MOD 1009>,
+				 <&cpg CPG_MOD 1010>, <&cpg CPG_MOD 1011>,
+				 <&cpg CPG_MOD 1012>, <&cpg CPG_MOD 1013>,
+				 <&cpg CPG_MOD 1014>, <&cpg CPG_MOD 1015>,
+				 <&cpg CPG_MOD 1025>, <&cpg CPG_MOD 1026>,
+				 <&cpg CPG_MOD 1027>, <&cpg CPG_MOD 1028>,
+				 <&cpg CPG_MOD 1029>, <&cpg CPG_MOD 1030>,
+				 <&cpg CPG_MOD 1021>, <&cpg CPG_MOD 1020>,
+				 <&cpg CPG_MOD 1021>, <&cpg CPG_MOD 1020>,
+				 <&cpg CPG_MOD 1019>, <&cpg CPG_MOD 1018>,
+				 <&audio_clka>, <&audio_clkb>, <&audio_clkc>,
+				 <&cpg CPG_CORE R8A7745_CLK_M2>;
+			clock-names = "ssi-all",
+				      "ssi.9", "ssi.8", "ssi.7", "ssi.6",
+				      "ssi.5", "ssi.4", "ssi.3", "ssi.2",
+				      "ssi.1", "ssi.0",
+				      "src.6", "src.5", "src.4", "src.3",
+				      "src.2", "src.1",
+				      "ctu.0", "ctu.1",
+				      "mix.0", "mix.1",
+				      "dvc.0", "dvc.1",
+				      "clk_a", "clk_b", "clk_c", "clk_i";
+			power-domains = <&sysc R8A7745_PD_ALWAYS_ON>;
+			resets = <&cpg 1005>,
+				 <&cpg 1006>, <&cpg 1007>, <&cpg 1008>,
+				 <&cpg 1009>, <&cpg 1010>, <&cpg 1011>,
+				 <&cpg 1012>, <&cpg 1013>, <&cpg 1014>,
+				 <&cpg 1015>;
+			reset-names = "ssi-all",
+				      "ssi.9", "ssi.8", "ssi.7", "ssi.6",
+				      "ssi.5", "ssi.4", "ssi.3", "ssi.2",
+				      "ssi.1", "ssi.0";
+
+			status = "disabled";
+
+			rcar_sound,dvc {
+				dvc0: dvc-0 {
+					dmas = <&audma0 0xbc>;
+					dma-names = "tx";
+				};
+				dvc1: dvc-1 {
+					dmas = <&audma0 0xbe>;
+					dma-names = "tx";
+				};
+			};
+
+			rcar_sound,mix {
+				mix0: mix-0 { };
+				mix1: mix-1 { };
+			};
+
+			rcar_sound,ctu {
+				ctu00: ctu-0 { };
+				ctu01: ctu-1 { };
+				ctu02: ctu-2 { };
+				ctu03: ctu-3 { };
+				ctu10: ctu-4 { };
+				ctu11: ctu-5 { };
+				ctu12: ctu-6 { };
+				ctu13: ctu-7 { };
+			};
+
+			rcar_sound,src {
+				src-0 {
+					status = "disabled";
+				};
+				src1: src-1 {
+					interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x87>, <&audma0 0x9c>;
+					dma-names = "rx", "tx";
+				};
+				src2: src-2 {
+					interrupts = <GIC_SPI 354 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x89>, <&audma0 0x9e>;
+					dma-names = "rx", "tx";
+				};
+				src3: src-3 {
+					interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x8b>, <&audma0 0xa0>;
+					dma-names = "rx", "tx";
+				};
+				src4: src-4 {
+					interrupts = <GIC_SPI 356 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x8d>, <&audma0 0xb0>;
+					dma-names = "rx", "tx";
+				};
+				src5: src-5 {
+					interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x8f>, <&audma0 0xb2>;
+					dma-names = "rx", "tx";
+				};
+				src6: src-6 {
+					interrupts = <GIC_SPI 358 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x91>, <&audma0 0xb4>;
+					dma-names = "rx", "tx";
+				};
+			};
+
+			rcar_sound,ssi {
+				ssi0: ssi-0 {
+					interrupts = <GIC_SPI 370 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x01>, <&audma0 0x02>,
+					       <&audma0 0x15>, <&audma0 0x16>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi1: ssi-1 {
+					interrupts = <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x03>, <&audma0 0x04>,
+					       <&audma0 0x49>, <&audma0 0x4a>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi2: ssi-2 {
+					interrupts = <GIC_SPI 372 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x05>, <&audma0 0x06>,
+					       <&audma0 0x63>, <&audma0 0x64>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi3: ssi-3 {
+					interrupts = <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x07>, <&audma0 0x08>,
+					       <&audma0 0x6f>, <&audma0 0x70>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi4: ssi-4 {
+					interrupts = <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x09>, <&audma0 0x0a>,
+					       <&audma0 0x71>, <&audma0 0x72>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi5: ssi-5 {
+					interrupts = <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x0b>, <&audma0 0x0c>,
+					       <&audma0 0x73>, <&audma0 0x74>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi6: ssi-6 {
+					interrupts = <GIC_SPI 376 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x0d>, <&audma0 0x0e>,
+					       <&audma0 0x75>, <&audma0 0x76>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi7: ssi-7 {
+					interrupts = <GIC_SPI 377 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x0f>, <&audma0 0x10>,
+					       <&audma0 0x79>, <&audma0 0x7a>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi8: ssi-8 {
+					interrupts = <GIC_SPI 378 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x11>, <&audma0 0x12>,
+					       <&audma0 0x7b>, <&audma0 0x7c>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+				ssi9: ssi-9 {
+					interrupts = <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH>;
+					dmas = <&audma0 0x13>, <&audma0 0x14>,
+					       <&audma0 0x7d>, <&audma0 0x7e>;
+					dma-names = "rx", "tx", "rxu", "txu";
+				};
+			};
+		};
 	};
 
-	/* External root clock */
-	extal_clk: extal {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		/* This value must be overridden by the board. */
-		clock-frequency = <0>;
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
 	};
 
 	/* External USB clock - can be overridden by the board */
@@ -953,12 +1490,4 @@
 		#clock-cells = <0>;
 		clock-frequency = <48000000>;
 	};
-
-	/* External SCIF clock */
-	scif_clk: scif {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		/* This value must be overridden by the board. */
-		clock-frequency = <0>;
-	};
 };
diff --git a/arch/arm/boot/dts/r8a7778.dtsi b/arch/arm/boot/dts/r8a7778.dtsi
index a39472aab867..3b49f9ed2e2b 100644
--- a/arch/arm/boot/dts/r8a7778.dtsi
+++ b/arch/arm/boot/dts/r8a7778.dtsi
@@ -51,7 +51,8 @@
 	};
 
 	ether: ethernet@fde00000 {
-		compatible = "renesas,ether-r8a7778";
+		compatible = "renesas,ether-r8a7778",
+			     "renesas,rcar-gen1-ether";
 		reg = <0xfde00000 0x400>;
 		interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7778_CLK_ETHER>;
@@ -379,7 +380,8 @@
 	};
 
 	sdhi0: sd@ffe4c000 {
-		compatible = "renesas,sdhi-r8a7778";
+		compatible = "renesas,sdhi-r8a7778",
+			     "renesas,rcar-gen1-sdhi";
 		reg = <0xffe4c000 0x100>;
 		interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7778_CLK_SDHI0>;
@@ -388,7 +390,8 @@
 	};
 
 	sdhi1: sd@ffe4d000 {
-		compatible = "renesas,sdhi-r8a7778";
+		compatible = "renesas,sdhi-r8a7778",
+			     "renesas,rcar-gen1-sdhi";
 		reg = <0xffe4d000 0x100>;
 		interrupts = <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7778_CLK_SDHI1>;
@@ -397,7 +400,8 @@
 	};
 
 	sdhi2: sd@ffe4f000 {
-		compatible = "renesas,sdhi-r8a7778";
+		compatible = "renesas,sdhi-r8a7778",
+			     "renesas,rcar-gen1-sdhi";
 		reg = <0xffe4f000 0x100>;
 		interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7778_CLK_SDHI2>;
diff --git a/arch/arm/boot/dts/r8a7779.dtsi b/arch/arm/boot/dts/r8a7779.dtsi
index e8eb94748b27..e79ae306eedd 100644
--- a/arch/arm/boot/dts/r8a7779.dtsi
+++ b/arch/arm/boot/dts/r8a7779.dtsi
@@ -355,7 +355,8 @@
 	};
 
 	sdhi0: sd@ffe4c000 {
-		compatible = "renesas,sdhi-r8a7779";
+		compatible = "renesas,sdhi-r8a7779",
+			     "renesas,rcar-gen1-sdhi";
 		reg = <0xffe4c000 0x100>;
 		interrupts = <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7779_CLK_SDHI0>;
@@ -364,7 +365,8 @@
 	};
 
 	sdhi1: sd@ffe4d000 {
-		compatible = "renesas,sdhi-r8a7779";
+		compatible = "renesas,sdhi-r8a7779",
+			     "renesas,rcar-gen1-sdhi";
 		reg = <0xffe4d000 0x100>;
 		interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7779_CLK_SDHI1>;
@@ -373,7 +375,8 @@
 	};
 
 	sdhi2: sd@ffe4e000 {
-		compatible = "renesas,sdhi-r8a7779";
+		compatible = "renesas,sdhi-r8a7779",
+			     "renesas,rcar-gen1-sdhi";
 		reg = <0xffe4e000 0x100>;
 		interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7779_CLK_SDHI2>;
@@ -382,7 +385,8 @@
 	};
 
 	sdhi3: sd@ffe4f000 {
-		compatible = "renesas,sdhi-r8a7779";
+		compatible = "renesas,sdhi-r8a7779",
+			     "renesas,rcar-gen1-sdhi";
 		reg = <0xffe4f000 0x100>;
 		interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7779_CLK_SDHI3>;
diff --git a/arch/arm/boot/dts/r8a7790-lager.dts b/arch/arm/boot/dts/r8a7790-lager.dts
index e3d27783b6b5..f2ea632381e7 100644
--- a/arch/arm/boot/dts/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/r8a7790-lager.dts
@@ -272,9 +272,8 @@
 		#size-cells = <0>;
 		compatible = "i2c-gpio";
 		status = "disabled";
-		gpios = <&gpio1 17 GPIO_ACTIVE_HIGH /* sda */
-			 &gpio1 16 GPIO_ACTIVE_HIGH /* scl */
-			>;
+		sda-gpios = <&gpio1 17 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		scl-gpios = <&gpio1 16 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 		i2c-gpio,delay-us = <5>;
 	};
 
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 2f017fee4009..ed9a68538a55 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -168,7 +168,7 @@
 
 			trips {
 				cpu-crit {
-					temperature	= <115000>;
+					temperature	= <95000>;
 					hysteresis	= <0>;
 					type		= "critical";
 				};
@@ -311,7 +311,7 @@
 	};
 
 	cmt0: timer@ffca0000 {
-		compatible = "renesas,cmt-48-r8a7790", "renesas,cmt-48-gen2";
+		compatible = "renesas,r8a7790-cmt0", "renesas,rcar-gen2-cmt0";
 		reg = <0 0xffca0000 0 0x1004>;
 		interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
@@ -320,13 +320,11 @@
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		resets = <&cpg 124>;
 
-		renesas,channels-mask = <0x60>;
-
 		status = "disabled";
 	};
 
 	cmt1: timer@e6130000 {
-		compatible = "renesas,cmt-48-r8a7790", "renesas,cmt-48-gen2";
+		compatible = "renesas,r8a7790-cmt1", "renesas,rcar-gen2-cmt1";
 		reg = <0 0xe6130000 0 0x1004>;
 		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
@@ -341,8 +339,6 @@
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		resets = <&cpg 329>;
 
-		renesas,channels-mask = <0xff>;
-
 		status = "disabled";
 	};
 
@@ -662,7 +658,8 @@
 	};
 
 	sdhi0: sd@ee100000 {
-		compatible = "renesas,sdhi-r8a7790";
+		compatible = "renesas,sdhi-r8a7790",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee100000 0 0x328>;
 		interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 314>;
@@ -676,7 +673,8 @@
 	};
 
 	sdhi1: sd@ee120000 {
-		compatible = "renesas,sdhi-r8a7790";
+		compatible = "renesas,sdhi-r8a7790",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee120000 0 0x328>;
 		interrupts = <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 313>;
@@ -690,7 +688,8 @@
 	};
 
 	sdhi2: sd@ee140000 {
-		compatible = "renesas,sdhi-r8a7790";
+		compatible = "renesas,sdhi-r8a7790",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee140000 0 0x100>;
 		interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 312>;
@@ -704,7 +703,8 @@
 	};
 
 	sdhi3: sd@ee160000 {
-		compatible = "renesas,sdhi-r8a7790";
+		compatible = "renesas,sdhi-r8a7790",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee160000 0 0x100>;
 		interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 311>;
@@ -906,7 +906,8 @@
 	};
 
 	ether: ethernet@ee700000 {
-		compatible = "renesas,ether-r8a7790";
+		compatible = "renesas,ether-r8a7790",
+			     "renesas,rcar-gen2-ether";
 		reg = <0 0xee700000 0 0x400>;
 		interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 813>;
@@ -1201,6 +1202,7 @@
 		clock-names = "extal", "usb_extal";
 		#clock-cells = <2>;
 		#power-domain-cells = <0>;
+		#reset-cells = <1>;
 	};
 
 	prr: chipid@ff000044 {
diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts
index e164eda69baf..a50924d12b6f 100644
--- a/arch/arm/boot/dts/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/r8a7791-koelsch.dts
@@ -278,6 +278,12 @@
 		};
 	};
 
+	cec_clock: cec-clock {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <12000000>;
+	};
+
 	hdmi-out {
 		compatible = "hdmi-connector";
 		type = "a";
@@ -306,9 +312,8 @@
 		#size-cells = <0>;
 		compatible = "i2c-gpio";
 		status = "disabled";
-		gpios = <&gpio7 16 GPIO_ACTIVE_HIGH /* sda */
-			 &gpio7 15 GPIO_ACTIVE_HIGH /* scl */
-			>;
+		sda-gpios = <&gpio7 16 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		scl-gpios = <&gpio7 15 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 		i2c-gpio,delay-us = <5>;
 	};
 
@@ -640,12 +645,6 @@
 		};
 	};
 
-	cec_clock: cec-clock {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <12000000>;
-	};
-
 	hdmi@39 {
 		compatible = "adi,adv7511w";
 		reg = <0x39>;
@@ -708,7 +707,7 @@
 	};
 
 	eeprom@50 {
-		compatible = "renesas,24c02", "atmel,24c02";
+		compatible = "renesas,r1ex24002", "atmel,24c02";
 		reg = <0x50>;
 		pagesize = <16>;
 	};
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index 67831d0405f3..008a260f86a5 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -92,7 +92,7 @@
 
 			trips {
 				cpu-crit {
-					temperature	= <115000>;
+					temperature	= <95000>;
 					hysteresis	= <0>;
 					type		= "critical";
 				};
@@ -257,7 +257,7 @@
 	};
 
 	cmt0: timer@ffca0000 {
-		compatible = "renesas,cmt-48-r8a7791", "renesas,cmt-48-gen2";
+		compatible = "renesas,r8a7791-cmt0", "renesas,rcar-gen2-cmt0";
 		reg = <0 0xffca0000 0 0x1004>;
 		interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
@@ -266,13 +266,11 @@
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		resets = <&cpg 124>;
 
-		renesas,channels-mask = <0x60>;
-
 		status = "disabled";
 	};
 
 	cmt1: timer@e6130000 {
-		compatible = "renesas,cmt-48-r8a7791", "renesas,cmt-48-gen2";
+		compatible = "renesas,r8a7791-cmt1", "renesas,rcar-gen2-cmt1";
 		reg = <0 0xe6130000 0 0x1004>;
 		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
@@ -287,8 +285,6 @@
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		resets = <&cpg 329>;
 
-		renesas,channels-mask = <0xff>;
-
 		status = "disabled";
 	};
 
@@ -612,7 +608,8 @@
 	};
 
 	sdhi0: sd@ee100000 {
-		compatible = "renesas,sdhi-r8a7791";
+		compatible = "renesas,sdhi-r8a7791",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee100000 0 0x328>;
 		interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 314>;
@@ -626,7 +623,8 @@
 	};
 
 	sdhi1: sd@ee140000 {
-		compatible = "renesas,sdhi-r8a7791";
+		compatible = "renesas,sdhi-r8a7791",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee140000 0 0x100>;
 		interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 312>;
@@ -640,7 +638,8 @@
 	};
 
 	sdhi2: sd@ee160000 {
-		compatible = "renesas,sdhi-r8a7791";
+		compatible = "renesas,sdhi-r8a7791",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee160000 0 0x100>;
 		interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 311>;
@@ -961,7 +960,8 @@
 	};
 
 	ether: ethernet@ee700000 {
-		compatible = "renesas,ether-r8a7791";
+		compatible = "renesas,ether-r8a7791",
+			     "renesas,rcar-gen2-ether";
 		reg = <0 0xee700000 0 0x400>;
 		interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 813>;
diff --git a/arch/arm/boot/dts/r8a7792.dtsi b/arch/arm/boot/dts/r8a7792.dtsi
index 131f65b0426e..3be15a158bad 100644
--- a/arch/arm/boot/dts/r8a7792.dtsi
+++ b/arch/arm/boot/dts/r8a7792.dtsi
@@ -36,6 +36,14 @@
 		vin5 = &vin5;
 	};
 
+	/* External CAN clock */
+	can_clk: can {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board. */
+		clock-frequency = <0>;
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -69,6 +77,22 @@
 		};
 	};
 
+	/* External root clock */
+	extal_clk: extal {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board. */
+		clock-frequency = <0>;
+	};
+
+	/* External SCIF clock */
+	scif_clk: scif {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board. */
+		clock-frequency = <0>;
+	};
+
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
@@ -113,18 +137,6 @@
 			resets = <&cpg 407>;
 		};
 
-		timer {
-			compatible = "arm,armv7-timer";
-			interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) |
-				      IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) |
-				      IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) |
-				      IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) |
-				      IRQ_TYPE_LEVEL_LOW)>;
-		};
-
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a7792-rst";
 			reg = <0 0xe6160000 0 0x0100>;
@@ -507,7 +519,8 @@
 		};
 
 		sdhi0: sd@ee100000 {
-			compatible = "renesas,sdhi-r8a7792";
+			compatible = "renesas,sdhi-r8a7792",
+				     "renesas,rcar-gen2-sdhi";
 			reg = <0 0xee100000 0 0x328>;
 			interrupts = <0 165 IRQ_TYPE_LEVEL_HIGH>;
 			dmas = <&dmac0 0xcd>, <&dmac0 0xce>,
@@ -829,30 +842,15 @@
 			clock-names = "extal";
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
+			#reset-cells = <1>;
 		};
 	};
 
-	/* External root clock */
-	extal_clk: extal {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		/* This value must be overridden by the board. */
-		clock-frequency = <0>;
-	};
-
-	/* External SCIF clock */
-	scif_clk: scif {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		/* This value must be overridden by the board. */
-		clock-frequency = <0>;
-	};
-
-	/* External CAN clock */
-	can_clk: can {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		/* This value must be overridden by the board. */
-		clock-frequency = <0>;
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
 	};
 };
diff --git a/arch/arm/boot/dts/r8a7793.dtsi b/arch/arm/boot/dts/r8a7793.dtsi
index 58eae569b4e0..039b22517526 100644
--- a/arch/arm/boot/dts/r8a7793.dtsi
+++ b/arch/arm/boot/dts/r8a7793.dtsi
@@ -89,7 +89,7 @@
 
 			trips {
 				cpu-crit {
-					temperature	= <115000>;
+					temperature	= <95000>;
 					hysteresis	= <0>;
 					type		= "critical";
 				};
@@ -248,7 +248,7 @@
 	};
 
 	cmt0: timer@ffca0000 {
-		compatible = "renesas,cmt-48-r8a7793", "renesas,cmt-48-gen2";
+		compatible = "renesas,r8a7793-cmt0", "renesas,rcar-gen2-cmt0";
 		reg = <0 0xffca0000 0 0x1004>;
 		interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
@@ -257,13 +257,11 @@
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		resets = <&cpg 124>;
 
-		renesas,channels-mask = <0x60>;
-
 		status = "disabled";
 	};
 
 	cmt1: timer@e6130000 {
-		compatible = "renesas,cmt-48-r8a7793", "renesas,cmt-48-gen2";
+		compatible = "renesas,r8a7793-cmt1", "renesas,rcar-gen2-cmt1";
 		reg = <0 0xe6130000 0 0x1004>;
 		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
@@ -278,8 +276,6 @@
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		resets = <&cpg 329>;
 
-		renesas,channels-mask = <0xff>;
-
 		status = "disabled";
 	};
 
@@ -562,7 +558,8 @@
 	};
 
 	sdhi0: sd@ee100000 {
-		compatible = "renesas,sdhi-r8a7793";
+		compatible = "renesas,sdhi-r8a7793",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee100000 0 0x328>;
 		interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 314>;
@@ -576,7 +573,8 @@
 	};
 
 	sdhi1: sd@ee140000 {
-		compatible = "renesas,sdhi-r8a7793";
+		compatible = "renesas,sdhi-r8a7793",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee140000 0 0x100>;
 		interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 312>;
@@ -590,7 +588,8 @@
 	};
 
 	sdhi2: sd@ee160000 {
-		compatible = "renesas,sdhi-r8a7793";
+		compatible = "renesas,sdhi-r8a7793",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee160000 0 0x100>;
 		interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 311>;
@@ -916,7 +915,8 @@
 	};
 
 	ether: ethernet@ee700000 {
-		compatible = "renesas,ether-r8a7793";
+		compatible = "renesas,ether-r8a7793",
+			     "renesas,rcar-gen2-ether";
 		reg = <0 0xee700000 0 0x400>;
 		interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 813>;
@@ -1088,6 +1088,7 @@
 		clock-names = "extal", "usb_extal";
 		#clock-cells = <2>;
 		#power-domain-cells = <0>;
+		#reset-cells = <1>;
 	};
 
 	rst: reset-controller@e6160000 {
diff --git a/arch/arm/boot/dts/r8a7794-alt.dts b/arch/arm/boot/dts/r8a7794-alt.dts
index bd98790d964e..60c6515c4996 100644
--- a/arch/arm/boot/dts/r8a7794-alt.dts
+++ b/arch/arm/boot/dts/r8a7794-alt.dts
@@ -143,9 +143,8 @@
 		#size-cells = <0>;
 		compatible = "i2c-gpio";
 		status = "disabled";
-		gpios = <&gpio4 9 GPIO_ACTIVE_HIGH /* sda */
-			 &gpio4 8 GPIO_ACTIVE_HIGH /* scl */
-			>;
+		sda-gpios = <&gpio4 9 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		scl-gpios = <&gpio4 8 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 		i2c-gpio,delay-us = <5>;
 	};
 
diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
index 905e50c9b524..106b4e1649ff 100644
--- a/arch/arm/boot/dts/r8a7794.dtsi
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -37,6 +37,7 @@
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
+		enable-method = "renesas,apmu";
 
 		cpu0: cpu@0 {
 			device_type = "cpu";
@@ -66,6 +67,12 @@
 		};
 	};
 
+	apmu@e6151000 {
+		compatible = "renesas,r8a7794-apmu", "renesas,apmu";
+		reg = <0 0xe6151000 0 0x188>;
+		cpus = <&cpu0 &cpu1>;
+	};
+
 	gic: interrupt-controller@f1001000 {
 		compatible = "arm,gic-400";
 		#interrupt-cells = <3>;
@@ -181,7 +188,7 @@
 	};
 
 	cmt0: timer@ffca0000 {
-		compatible = "renesas,cmt-48-gen2";
+		compatible = "renesas,r8a7794-cmt0", "renesas,rcar-gen2-cmt0";
 		reg = <0 0xffca0000 0 0x1004>;
 		interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
@@ -190,13 +197,11 @@
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		resets = <&cpg 124>;
 
-		renesas,channels-mask = <0x60>;
-
 		status = "disabled";
 	};
 
 	cmt1: timer@e6130000 {
-		compatible = "renesas,cmt-48-gen2";
+		compatible = "renesas,r8a7794-cmt1", "renesas,rcar-gen2-cmt1";
 		reg = <0 0xe6130000 0 0x1004>;
 		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
@@ -211,8 +216,6 @@
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		resets = <&cpg 329>;
 
-		renesas,channels-mask = <0xff>;
-
 		status = "disabled";
 	};
 
@@ -640,7 +643,8 @@
 	};
 
 	ether: ethernet@ee700000 {
-		compatible = "renesas,ether-r8a7794";
+		compatible = "renesas,ether-r8a7794",
+			     "renesas,rcar-gen2-ether";
 		reg = <0 0xee700000 0 0x400>;
 		interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 813>;
@@ -791,7 +795,8 @@
 	};
 
 	sdhi0: sd@ee100000 {
-		compatible = "renesas,sdhi-r8a7794";
+		compatible = "renesas,sdhi-r8a7794",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee100000 0 0x328>;
 		interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 314>;
@@ -805,7 +810,8 @@
 	};
 
 	sdhi1: sd@ee140000 {
-		compatible = "renesas,sdhi-r8a7794";
+		compatible = "renesas,sdhi-r8a7794",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee140000 0 0x100>;
 		interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 312>;
@@ -819,7 +825,8 @@
 	};
 
 	sdhi2: sd@ee160000 {
-		compatible = "renesas,sdhi-r8a7794";
+		compatible = "renesas,sdhi-r8a7794",
+			     "renesas,rcar-gen2-sdhi";
 		reg = <0 0xee160000 0 0x100>;
 		interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cpg CPG_MOD 311>;
@@ -1099,6 +1106,7 @@
 		clock-names = "extal", "usb_extal";
 		#clock-cells = <2>;
 		#power-domain-cells = <0>;
+		#reset-cells = <1>;
 	};
 
 	rst: reset-controller@e6160000 {
diff --git a/arch/arm/boot/dts/rk3066a-marsboard.dts b/arch/arm/boot/dts/rk3066a-marsboard.dts
index c6d92c25df42..d23ee6d911ac 100644
--- a/arch/arm/boot/dts/rk3066a-marsboard.dts
+++ b/arch/arm/boot/dts/rk3066a-marsboard.dts
@@ -83,6 +83,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&vdd_arm>;
+};
+
 &i2c1 {
 	status = "okay";
 	clock-frequency = <400000>;
diff --git a/arch/arm/boot/dts/rk3066a-rayeager.dts b/arch/arm/boot/dts/rk3066a-rayeager.dts
index cdf301f5778b..4d7057a10a4c 100644
--- a/arch/arm/boot/dts/rk3066a-rayeager.dts
+++ b/arch/arm/boot/dts/rk3066a-rayeager.dts
@@ -177,6 +177,7 @@
 
 	phy0: ethernet-phy@0 {
 		reg = <0>;
+		reset-gpios = <&gpio1 RK_PD6 GPIO_ACTIVE_LOW>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index cd24894ee5c6..6102e4e7f35c 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -956,7 +956,7 @@
 	iep_mmu: iommu@ff900800 {
 		compatible = "rockchip,iommu";
 		reg = <0x0 0xff900800 0x0 0x40>;
-		interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "iep_mmu";
 		#iommu-cells = <0>;
 		status = "disabled";
diff --git a/arch/arm/boot/dts/s3c2416-pinctrl.dtsi b/arch/arm/boot/dts/s3c2416-pinctrl.dtsi
index 6274359fb323..92439ee5d7de 100644
--- a/arch/arm/boot/dts/s3c2416-pinctrl.dtsi
+++ b/arch/arm/boot/dts/s3c2416-pinctrl.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung S3C2416 pinctrl settings
  *
  * Copyright (c) 2013 Heiko Stuebner <heiko@sntech.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/pinctrl/samsung.h>
diff --git a/arch/arm/boot/dts/s3c2416-smdk2416.dts b/arch/arm/boot/dts/s3c2416-smdk2416.dts
index f257926c13b7..a1c9d8c695cc 100644
--- a/arch/arm/boot/dts/s3c2416-smdk2416.dts
+++ b/arch/arm/boot/dts/s3c2416-smdk2416.dts
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG SMDK2416 board device tree source
  *
  * Copyright (c) 2013 Heiko Stuebner <heiko@sntech.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/s3c2416.dtsi b/arch/arm/boot/dts/s3c2416.dtsi
index 80f007550324..3c7385cab248 100644
--- a/arch/arm/boot/dts/s3c2416.dtsi
+++ b/arch/arm/boot/dts/s3c2416.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S3C2416 SoC device tree source
  *
  * Copyright (c) 2013 Heiko Stuebner <heiko@sntech.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/clock/s3c2443.h>
diff --git a/arch/arm/boot/dts/s3c24xx.dtsi b/arch/arm/boot/dts/s3c24xx.dtsi
index 5ed43b857cc4..34c7fe6751cf 100644
--- a/arch/arm/boot/dts/s3c24xx.dtsi
+++ b/arch/arm/boot/dts/s3c24xx.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S3C24XX family device tree source
  *
  * Copyright (c) 2013 Heiko Stuebner <heiko@sntech.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include "skeleton.dtsi"
diff --git a/arch/arm/boot/dts/s3c6400.dtsi b/arch/arm/boot/dts/s3c6400.dtsi
index a7d1c8ec150d..8c28e8a0c824 100644
--- a/arch/arm/boot/dts/s3c6400.dtsi
+++ b/arch/arm/boot/dts/s3c6400.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S3C6400 SoC device tree source
  *
@@ -10,11 +11,7 @@
  * Note: This file does not include device nodes for all the controllers in
  * S3C6400 SoC. As device tree coverage for S3C6400 increases, additional
  * nodes can be added to this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include "s3c64xx.dtsi"
 
diff --git a/arch/arm/boot/dts/s3c6410-mini6410.dts b/arch/arm/boot/dts/s3c6410-mini6410.dts
index f4afda3594f8..f68601bd9c91 100644
--- a/arch/arm/boot/dts/s3c6410-mini6410.dts
+++ b/arch/arm/boot/dts/s3c6410-mini6410.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S3C6410 based Mini6410 board device tree source
  *
@@ -5,11 +6,7 @@
  *
  * Device tree source file for FriendlyARM Mini6410 board which is based on
  * Samsung's S3C6410 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/s3c6410-smdk6410.dts b/arch/arm/boot/dts/s3c6410-smdk6410.dts
index ecf35ec466f7..b6b5afcd7602 100644
--- a/arch/arm/boot/dts/s3c6410-smdk6410.dts
+++ b/arch/arm/boot/dts/s3c6410-smdk6410.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung S3C6410 based SMDK6410 board device tree source.
  *
@@ -5,11 +6,7 @@
  *
  * Device tree source file for SAMSUNG SMDK6410 board which is based on
  * Samsung's S3C6410 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/s3c6410.dtsi b/arch/arm/boot/dts/s3c6410.dtsi
index eb4226b3407c..a766d6de696c 100644
--- a/arch/arm/boot/dts/s3c6410.dtsi
+++ b/arch/arm/boot/dts/s3c6410.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S3C6410 SoC device tree source
  *
@@ -10,11 +11,7 @@
  * Note: This file does not include device nodes for all the controllers in
  * S3C6410 SoC. As device tree coverage for S3C6410 increases, additional
  * nodes can be added to this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include "s3c64xx.dtsi"
 
diff --git a/arch/arm/boot/dts/s3c64xx-pinctrl.dtsi b/arch/arm/boot/dts/s3c64xx-pinctrl.dtsi
index 4e8e802b4ee1..8e9594d64b57 100644
--- a/arch/arm/boot/dts/s3c64xx-pinctrl.dtsi
+++ b/arch/arm/boot/dts/s3c64xx-pinctrl.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S3C64xx SoC series common device tree source
  * - pin control-related definitions
@@ -6,10 +7,6 @@
  *
  * Samsung's S3C64xx SoCs pin banks, pin-mux and pin-config options are
  * listed as device tree nodes in this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/pinctrl/samsung.h>
diff --git a/arch/arm/boot/dts/s3c64xx.dtsi b/arch/arm/boot/dts/s3c64xx.dtsi
index c55cbb3af2c0..e2be3fbdd3f3 100644
--- a/arch/arm/boot/dts/s3c64xx.dtsi
+++ b/arch/arm/boot/dts/s3c64xx.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S3C64xx SoC series common device tree source
  *
@@ -10,10 +11,6 @@
  * Note: This file does not include device nodes for all the controllers in
  * S3C64xx SoCs. As device tree coverage for S3C64xx increases, additional
  * nodes can be added to this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include "skeleton.dtsi"
diff --git a/arch/arm/boot/dts/s5pv210-aquila.dts b/arch/arm/boot/dts/s5pv210-aquila.dts
index 40139923eef0..14969b6529e8 100644
--- a/arch/arm/boot/dts/s5pv210-aquila.dts
+++ b/arch/arm/boot/dts/s5pv210-aquila.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S5PV210 SoC device tree source
  *
@@ -7,10 +8,6 @@
  * Tomasz Figa <t.figa@samsung.com>
  *
  * Board device tree source for Samsung Aquila board.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/s5pv210-goni.dts b/arch/arm/boot/dts/s5pv210-goni.dts
index c56f51ee7897..eb6d1926c0d6 100644
--- a/arch/arm/boot/dts/s5pv210-goni.dts
+++ b/arch/arm/boot/dts/s5pv210-goni.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S5PV210 SoC device tree source
  *
@@ -7,10 +8,6 @@
  * Tomasz Figa <t.figa@samsung.com>
  *
  * Board device tree source for Samsung Goni board.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/s5pv210-pinctrl.dtsi b/arch/arm/boot/dts/s5pv210-pinctrl.dtsi
index 9a3e851e2e22..3a79feab11c3 100644
--- a/arch/arm/boot/dts/s5pv210-pinctrl.dtsi
+++ b/arch/arm/boot/dts/s5pv210-pinctrl.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S5PV210 SoC device tree source
  *
@@ -13,10 +14,6 @@
  * Note: This file does not include device nodes for all the controllers in
  * S5PV210 SoC. As device tree coverage for S5PV210 increases, additional
  * nodes can be added to this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/pinctrl/samsung.h>
diff --git a/arch/arm/boot/dts/s5pv210-smdkc110.dts b/arch/arm/boot/dts/s5pv210-smdkc110.dts
index 5d14da911aa5..e5aec6c526fb 100644
--- a/arch/arm/boot/dts/s5pv210-smdkc110.dts
+++ b/arch/arm/boot/dts/s5pv210-smdkc110.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S5PV210 SoC device tree source
  *
@@ -11,10 +12,6 @@
  * NOTE: This file is completely based on original board file for mach-smdkc110
  * available in Linux 3.15 and intends to provide equivalent level of hardware
  * support. Due to lack of hardware, _no_ testing has been performed.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/s5pv210-smdkv210.dts b/arch/arm/boot/dts/s5pv210-smdkv210.dts
index 75398318ed57..84b38f185199 100644
--- a/arch/arm/boot/dts/s5pv210-smdkv210.dts
+++ b/arch/arm/boot/dts/s5pv210-smdkv210.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S5PV210 SoC device tree source
  *
@@ -11,10 +12,6 @@
  * NOTE: This file is completely based on original board file for mach-smdkv210
  * available in Linux 3.15 and intends to provide equivalent level of hardware
  * support. Due to lack of hardware, _no_ testing has been performed.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/s5pv210-torbreck.dts b/arch/arm/boot/dts/s5pv210-torbreck.dts
index 7cb50bcee888..cd25e72ccd84 100644
--- a/arch/arm/boot/dts/s5pv210-torbreck.dts
+++ b/arch/arm/boot/dts/s5pv210-torbreck.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S5PV210 SoC device tree source
  *
@@ -11,10 +12,6 @@
  * NOTE: This file is completely based on original board file for mach-torbreck
  * available in Linux 3.15 and intends to provide equivalent level of hardware
  * support. Due to lack of hardware, _no_ testing has been performed.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/s5pv210.dtsi b/arch/arm/boot/dts/s5pv210.dtsi
index 726c5d0dbd5b..67358562a6ea 100644
--- a/arch/arm/boot/dts/s5pv210.dtsi
+++ b/arch/arm/boot/dts/s5pv210.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's S5PV210 SoC device tree source
  *
@@ -13,11 +14,7 @@
  * Note: This file does not include device nodes for all the controllers in
  * S5PV210 SoC. As device tree coverage for S5PV210 increases, additional
  * nodes can be added to this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/clock/s5pv210.h>
 #include <dt-bindings/clock/s5pv210-audss.h>
@@ -463,6 +460,7 @@
 			compatible = "samsung,exynos4210-ohci";
 			reg = <0xec300000 0x100>;
 			interrupts = <23>;
+			interrupt-parent = <&vic1>;
 			clocks = <&clocks CLK_USB_HOST>;
 			clock-names = "usbhost";
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi
index b44e63995583..61f68e5c48e9 100644
--- a/arch/arm/boot/dts/sama5d2.dtsi
+++ b/arch/arm/boot/dts/sama5d2.dtsi
@@ -1094,7 +1094,9 @@
 			};
 
 			tcb0: timer@f800c000 {
-				compatible = "atmel,at91sam9x5-tcb";
+				compatible = "atmel,at91sam9x5-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xf800c000 0x100>;
 				interrupts = <35 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb0_clk>, <&clk32k>;
@@ -1102,7 +1104,9 @@
 			};
 
 			tcb1: timer@f8010000 {
-				compatible = "atmel,at91sam9x5-tcb";
+				compatible = "atmel,at91sam9x5-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xf8010000 0x100>;
 				interrupts = <36 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb1_clk>, <&clk32k>;
@@ -1427,6 +1431,8 @@
 				interrupts = <40 IRQ_TYPE_LEVEL_HIGH 7>;
 				clocks = <&adc_clk>;
 				clock-names = "adc_clk";
+				dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | AT91_XDMAC_DT_PERID(25))>;
+				dma-names = "rx";
 				atmel,min-sample-rate-hz = <200000>;
 				atmel,max-sample-rate-hz = <20000000>;
 				atmel,startup-time-ms = <4>;
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 1889b4dea066..b9c05b57735e 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -142,7 +142,9 @@
 			};
 
 			tcb0: timer@f0010000 {
-				compatible = "atmel,at91sam9x5-tcb";
+				compatible = "atmel,at91sam9x5-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xf0010000 0x100>;
 				interrupts = <26 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb0_clk>, <&clk32k>;
diff --git a/arch/arm/boot/dts/sama5d3_tcb1.dtsi b/arch/arm/boot/dts/sama5d3_tcb1.dtsi
index 801f9745e82f..cb30bdb1a9ca 100644
--- a/arch/arm/boot/dts/sama5d3_tcb1.dtsi
+++ b/arch/arm/boot/dts/sama5d3_tcb1.dtsi
@@ -28,7 +28,9 @@
 			};
 
 			tcb1: timer@f8014000 {
-				compatible = "atmel,at91sam9x5-tcb";
+				compatible = "atmel,at91sam9x5-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xf8014000 0x100>;
 				interrupts = <27 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb1_clk>, <&clk32k>;
diff --git a/arch/arm/boot/dts/sama5d3xcm.dtsi b/arch/arm/boot/dts/sama5d3xcm.dtsi
index 9506daf5efb6..3311a882458b 100644
--- a/arch/arm/boot/dts/sama5d3xcm.dtsi
+++ b/arch/arm/boot/dts/sama5d3xcm.dtsi
@@ -34,6 +34,18 @@
 			spi0: spi@f0004000 {
 				cs-gpios = <&pioD 13 0>, <0>, <0>, <0>;
 			};
+
+			tcb0: timer@f0010000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
 		};
 
 		ebi@10000000 {
diff --git a/arch/arm/boot/dts/sama5d3xcm_cmp.dtsi b/arch/arm/boot/dts/sama5d3xcm_cmp.dtsi
index 75cbf4d4ab1a..a02f59021364 100644
--- a/arch/arm/boot/dts/sama5d3xcm_cmp.dtsi
+++ b/arch/arm/boot/dts/sama5d3xcm_cmp.dtsi
@@ -69,6 +69,18 @@
 				cs-gpios = <&pioD 13 0>, <0>, <0>, <0>;
 			};
 
+			tcb0: timer@f0010000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>;
+				};
+
+				timer@1 {
+					compatible = "atmel,tcb-timer";
+					reg = <1>;
+				};
+			};
+
 			macb0: ethernet@f0028000 {
 				phy-mode = "rgmii";
 				#address-cells = <1>;
diff --git a/arch/arm/boot/dts/sama5d3xmb.dtsi b/arch/arm/boot/dts/sama5d3xmb.dtsi
index 7f55050dd405..ef0f2d049e15 100644
--- a/arch/arm/boot/dts/sama5d3xmb.dtsi
+++ b/arch/arm/boot/dts/sama5d3xmb.dtsi
@@ -53,7 +53,7 @@
 			};
 
 			i2c1: i2c@f0018000 {
-				ov2640: camera@0x30 {
+				ov2640: camera@30 {
 					compatible = "ovti,ov2640";
 					reg = <0x30>;
 					pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi b/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi
index 83e3d3e08fd4..97e171db5970 100644
--- a/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi
+++ b/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi
@@ -88,7 +88,7 @@
 			};
 
 			i2c1: i2c@f0018000 {
-				ov2640: camera@0x30 {
+				ov2640: camera@30 {
 					compatible = "ovti,ov2640";
 					reg = <0x30>;
 					pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi
index b069644ed238..373b3621b536 100644
--- a/arch/arm/boot/dts/sama5d4.dtsi
+++ b/arch/arm/boot/dts/sama5d4.dtsi
@@ -960,7 +960,9 @@
 			};
 
 			tcb0: timer@f801c000 {
-				compatible = "atmel,at91sam9x5-tcb";
+				compatible = "atmel,at91sam9x5-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xf801c000 0x100>;
 				interrupts = <40 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb0_clk>, <&clk32k>;
@@ -1188,13 +1190,25 @@
 			};
 
 			tcb1: timer@fc020000 {
-				compatible = "atmel,at91sam9x5-tcb";
+				compatible = "atmel,at91sam9x5-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0xfc020000 0x100>;
 				interrupts = <41 IRQ_TYPE_LEVEL_HIGH 0>;
 				clocks = <&tcb1_clk>, <&clk32k>;
 				clock-names = "t0_clk", "slow_clk";
 			};
 
+			tcb2: timer@fc024000 {
+				compatible = "atmel,at91sam9x5-tcb", "simple-mfd", "syscon";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0xfc024000 0x100>;
+				interrupts = <42 IRQ_TYPE_LEVEL_HIGH 0>;
+				clocks = <&tcb2_clk>, <&clk32k>;
+				clock-names = "t0_clk", "slow_clk";
+			};
+
 			macb1: ethernet@fc028000 {
 				compatible = "atmel,sama5d4-gem";
 				reg = <0xfc028000 0x100>;
diff --git a/arch/arm/boot/dts/sh73a0.dtsi b/arch/arm/boot/dts/sh73a0.dtsi
index 88d7e5631d34..914a7c2a584f 100644
--- a/arch/arm/boot/dts/sh73a0.dtsi
+++ b/arch/arm/boot/dts/sh73a0.dtsi
@@ -100,9 +100,6 @@
 		clocks = <&mstp3_clks SH73A0_CLK_CMT1>;
 		clock-names = "fck";
 		power-domains = <&pd_c5>;
-
-		renesas,channels-mask = <0x3f>;
-
 		status = "disabled";
 	};
 
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index 7e24dc8e82d4..c42ca7022e8c 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/arch/arm/boot/dts/socfpga.dtsi
@@ -651,6 +651,7 @@
 			#size-cells = <0>;
 			compatible = "snps,designware-i2c";
 			reg = <0xffc04000 0x1000>;
+			resets = <&rst I2C0_RESET>;
 			clocks = <&l4_sp_clk>;
 			interrupts = <0 158 0x4>;
 			status = "disabled";
@@ -661,6 +662,7 @@
 			#size-cells = <0>;
 			compatible = "snps,designware-i2c";
 			reg = <0xffc05000 0x1000>;
+			resets = <&rst I2C1_RESET>;
 			clocks = <&l4_sp_clk>;
 			interrupts = <0 159 0x4>;
 			status = "disabled";
@@ -671,6 +673,7 @@
 			#size-cells = <0>;
 			compatible = "snps,designware-i2c";
 			reg = <0xffc06000 0x1000>;
+			resets = <&rst I2C2_RESET>;
 			clocks = <&l4_sp_clk>;
 			interrupts = <0 160 0x4>;
 			status = "disabled";
@@ -681,6 +684,7 @@
 			#size-cells = <0>;
 			compatible = "snps,designware-i2c";
 			reg = <0xffc07000 0x1000>;
+			resets = <&rst I2C3_RESET>;
 			clocks = <&l4_sp_clk>;
 			interrupts = <0 161 0x4>;
 			status = "disabled";
diff --git a/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi b/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi
index 3a32de9ded3b..64cc86a98771 100644
--- a/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi
@@ -163,6 +163,7 @@
 
 &usb0 {
 	status = "okay";
+	disable-over-current;
 };
 
 &watchdog1 {
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
index 655fe87e272d..2459d133f1be 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
@@ -237,7 +237,7 @@
 	clock-frequency = <100000>;
 
 	at24@50 {
-		compatible = "at24,24c02";
+		compatible = "atmel,24c02";
 		pagesize = <8>;
 		reg = <0x50>;
 	};
diff --git a/arch/arm/boot/dts/spear1310-evb.dts b/arch/arm/boot/dts/spear1310-evb.dts
index 84101e4eebbf..0f5f379323a8 100644
--- a/arch/arm/boot/dts/spear1310-evb.dts
+++ b/arch/arm/boot/dts/spear1310-evb.dts
@@ -349,7 +349,7 @@
 			spi0: spi@e0100000 {
 				status = "okay";
 				num-cs = <3>;
-				cs-gpios = <&gpio1 7 0>, <&spics 0>, <&spics 1>;
+				cs-gpios = <&gpio1 7 0>, <&spics 0 0>, <&spics 1 0>;
 
 				stmpe610@0 {
 					compatible = "st,stmpe610";
diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi
index 5f347054527d..d4dbc4098653 100644
--- a/arch/arm/boot/dts/spear1340.dtsi
+++ b/arch/arm/boot/dts/spear1340.dtsi
@@ -142,8 +142,8 @@
 				reg = <0xb4100000 0x1000>;
 				interrupts = <0 105 0x4>;
 				status = "disabled";
-				dmas = <&dwdma0 0x600 0 0 1>, /* 0xC << 11 */
-					<&dwdma0 0x680 0 1 0>; /* 0xD << 7 */
+				dmas = <&dwdma0 12 0 1>,
+					<&dwdma0 13 1 0>;
 				dma-names = "tx", "rx";
 			};
 
diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi
index 17ea0abcdbd7..086b4b333249 100644
--- a/arch/arm/boot/dts/spear13xx.dtsi
+++ b/arch/arm/boot/dts/spear13xx.dtsi
@@ -100,7 +100,7 @@
 			reg = <0xb2800000 0x1000>;
 			interrupts = <0 29 0x4>;
 			status = "disabled";
-			dmas = <&dwdma0 0 0 0 0>;
+			dmas = <&dwdma0 0 0 0>;
 			dma-names = "data";
 		};
 
@@ -290,8 +290,8 @@
 				#size-cells = <0>;
 				interrupts = <0 31 0x4>;
 				status = "disabled";
-				dmas = <&dwdma0 0x2000 0 0 0>, /* 0x4 << 11 */
-					<&dwdma0 0x0280 0 0 0>;  /* 0x5 << 7 */
+				dmas = <&dwdma0 4 0 0>,
+					<&dwdma0 5 0 0>;
 				dma-names = "tx", "rx";
 			};
 
diff --git a/arch/arm/boot/dts/spear600.dtsi b/arch/arm/boot/dts/spear600.dtsi
index 6b32d20acc9f..00166eb9be86 100644
--- a/arch/arm/boot/dts/spear600.dtsi
+++ b/arch/arm/boot/dts/spear600.dtsi
@@ -194,6 +194,7 @@
 			rtc: rtc@fc900000 {
 				compatible = "st,spear600-rtc";
 				reg = <0xfc900000 0x1000>;
+				interrupt-parent = <&vic0>;
 				interrupts = <10>;
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
index 68aab50a73ab..733678b75b88 100644
--- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
@@ -750,6 +750,7 @@
 			reg = <0x10120000 0x1000>;
 			interrupt-names = "combined";
 			interrupts = <14>;
+			interrupt-parent = <&vica>;
 			clocks = <&clcdclk>, <&hclkclcd>;
 			clock-names = "clcdclk", "apb_pclk";
 			status = "disabled";
diff --git a/arch/arm/boot/dts/stih407.dtsi b/arch/arm/boot/dts/stih407.dtsi
index fa149837df14..11fdecd9312e 100644
--- a/arch/arm/boot/dts/stih407.dtsi
+++ b/arch/arm/boot/dts/stih407.dtsi
@@ -8,6 +8,7 @@
  */
 #include "stih407-clock.dtsi"
 #include "stih407-family.dtsi"
+#include <dt-bindings/gpio/gpio.h>
 / {
 	soc {
 		sti-display-subsystem {
@@ -122,7 +123,7 @@
 					 <&clk_s_d2_quadfs 0>,
 					 <&clk_s_d2_quadfs 1>;
 
-				hdmi,hpd-gpio = <&pio5 3>;
+				hdmi,hpd-gpio = <&pio5 3 GPIO_ACTIVE_LOW>;
 				reset-names = "hdmi";
 				resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
 				ddc = <&hdmiddc>;
diff --git a/arch/arm/boot/dts/stih410.dtsi b/arch/arm/boot/dts/stih410.dtsi
index cffa50db5d72..68b5ff91d6a7 100644
--- a/arch/arm/boot/dts/stih410.dtsi
+++ b/arch/arm/boot/dts/stih410.dtsi
@@ -9,6 +9,7 @@
 #include "stih410-clock.dtsi"
 #include "stih407-family.dtsi"
 #include "stih410-pinctrl.dtsi"
+#include <dt-bindings/gpio/gpio.h>
 / {
 	aliases {
 		bdisp0 = &bdisp0;
@@ -213,7 +214,7 @@
 					 <&clk_s_d2_quadfs 0>,
 					 <&clk_s_d2_quadfs 1>;
 
-				hdmi,hpd-gpio = <&pio5 3>;
+				hdmi,hpd-gpio = <&pio5 3 GPIO_ACTIVE_LOW>;
 				reset-names = "hdmi";
 				resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
 				ddc = <&hdmiddc>;
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index b91300d49a31..4f2f2eea0755 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -502,8 +502,8 @@
 			reg = <0x01c16000 0x1000>;
 			interrupts = <58>;
 			clocks = <&ccu CLK_AHB_HDMI0>, <&ccu CLK_HDMI>,
-				 <&ccu 9>,
-				 <&ccu 18>;
+				 <&ccu CLK_PLL_VIDEO0_2X>,
+				 <&ccu CLK_PLL_VIDEO1_2X>;
 			clock-names = "ahb", "mod", "pll-0", "pll-1";
 			dmas = <&dma SUN4I_DMA_NORMAL 16>,
 			       <&dma SUN4I_DMA_NORMAL 16>,
@@ -1104,7 +1104,7 @@
 
 					be1_out_tcon0: endpoint@0 {
 						reg = <0>;
-						remote-endpoint = <&tcon1_in_be0>;
+						remote-endpoint = <&tcon0_in_be1>;
 					};
 
 					be1_out_tcon1: endpoint@1 {
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index 6ae4d95e230e..316cb8b2945b 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -82,8 +82,8 @@
 			reg = <0x01c16000 0x1000>;
 			interrupts = <58>;
 			clocks = <&ccu CLK_AHB_HDMI>, <&ccu CLK_HDMI>,
-				 <&ccu 9>,
-				 <&ccu 16>;
+				 <&ccu CLK_PLL_VIDEO0_2X>,
+				 <&ccu CLK_PLL_VIDEO1_2X>;
 			clock-names = "ahb", "mod", "pll-0", "pll-1";
 			dmas = <&dma SUN4I_DMA_NORMAL 16>,
 			       <&dma SUN4I_DMA_NORMAL 16>,
diff --git a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
index 38072c7e10e2..4b9af423c6d5 100644
--- a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
+++ b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
@@ -114,6 +114,10 @@
 	status = "okay";
 };
 
+&codec {
+	status = "okay";
+};
+
 &ehci0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi
index 8bfa12b548e0..72d3fe44ecaf 100644
--- a/arch/arm/boot/dts/sun6i-a31.dtsi
+++ b/arch/arm/boot/dts/sun6i-a31.dtsi
@@ -429,8 +429,8 @@
 			interrupts = <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_AHB1_HDMI>, <&ccu CLK_HDMI>,
 				 <&ccu CLK_HDMI_DDC>,
-				 <&ccu 7>,
-				 <&ccu 13>;
+				 <&ccu CLK_PLL_VIDEO0_2X>,
+				 <&ccu CLK_PLL_VIDEO1_2X>;
 			clock-names = "ahb", "mod", "ddc", "pll-0", "pll-1";
 			resets = <&ccu RST_AHB1_HDMI>;
 			reset-names = "ahb";
diff --git a/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts b/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts
index 39bc73db72e5..fb591f32252c 100644
--- a/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts
+++ b/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts
@@ -58,6 +58,17 @@
 		stdout-path = "serial0:115200n8";
 	};
 
+	hdmi-connector {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con_in: endpoint {
+				remote-endpoint = <&hdmi_out_con>;
+			};
+		};
+	};
+
 	leds {
 		compatible = "gpio-leds";
 		pinctrl-names = "default";
@@ -90,6 +101,10 @@
 	cpu-supply = <&reg_dcdc2>;
 };
 
+&de {
+	status = "okay";
+};
+
 &ehci0 {
 	status = "okay";
 };
@@ -110,6 +125,16 @@
 	};
 };
 
+&hdmi {
+	status = "okay";
+};
+
+&hdmi_out {
+	hdmi_out_con: endpoint {
+		remote-endpoint = <&hdmi_con_in>;
+	};
+};
+
 &i2c0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c0_pins_a>;
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 68dfa82544fc..bd0cd3204273 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -581,8 +581,8 @@
 			reg = <0x01c16000 0x1000>;
 			interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_AHB_HDMI0>, <&ccu CLK_HDMI>,
-				 <&ccu 9>,
-				 <&ccu 18>;
+				 <&ccu CLK_PLL_VIDEO0_2X>,
+				 <&ccu CLK_PLL_VIDEO1_2X>;
 			clock-names = "ahb", "mod", "pll-0", "pll-1";
 			dmas = <&dma SUN4I_DMA_NORMAL 16>,
 			       <&dma SUN4I_DMA_NORMAL 16>,
@@ -1354,7 +1354,7 @@
 
 					be1_out_tcon0: endpoint@0 {
 						reg = <0>;
-						remote-endpoint = <&tcon1_in_be0>;
+						remote-endpoint = <&tcon0_in_be1>;
 					};
 
 					be1_out_tcon1: endpoint@1 {
diff --git a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts
index c606af3dbfed..6550bf0e594b 100644
--- a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts
@@ -52,6 +52,7 @@
 	compatible = "sinovoip,bpi-m3", "allwinner,sun8i-a83t";
 
 	aliases {
+		ethernet0 = &emac;
 		serial0 = &uart0;
 	};
 
@@ -88,6 +89,24 @@
 	/* TODO GL830 USB-to-SATA bridge downstream w/ GPIO power controls */
 };
 
+&emac {
+	pinctrl-names = "default";
+	pinctrl-0 = <&emac_rgmii_pins>;
+	phy-supply = <&reg_sw>;
+	phy-handle = <&rgmii_phy>;
+	phy-mode = "rgmii";
+	allwinner,rx-delay-ps = <700>;
+	allwinner,tx-delay-ps = <700>;
+	status = "okay";
+};
+
+&mdio {
+	rgmii_phy: ethernet-phy@1 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <1>;
+	};
+};
+
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins>;
diff --git a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
index 7f0a3f6d0cf2..6da08cd0e107 100644
--- a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
@@ -52,6 +52,7 @@
 	compatible = "cubietech,cubietruck-plus", "allwinner,sun8i-a83t";
 
 	aliases {
+		ethernet0 = &emac;
 		serial0 = &uart0;
 	};
 
@@ -154,6 +155,22 @@
 	status = "okay";
 };
 
+&emac {
+	pinctrl-names = "default";
+	pinctrl-0 = <&emac_rgmii_pins>;
+	phy-supply = <&reg_dldo4>;
+	phy-handle = <&rgmii_phy>;
+	phy-mode = "rgmii";
+	status = "okay";
+};
+
+&mdio {
+	rgmii_phy: ethernet-phy@1 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <1>;
+	};
+};
+
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins>;
diff --git a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
index 98715538932f..511fca491fe8 100644
--- a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
@@ -45,6 +45,7 @@
 #include "sun8i-a83t.dtsi"
 
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pwm/pwm.h>
 
 / {
 	model = "TBS A711 Tablet";
@@ -59,6 +60,44 @@
 		stdout-path = "serial0:115200n8";
 	};
 
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm 0 50000 PWM_POLARITY_INVERTED>;
+		enable-gpios = <&pio 3 29 GPIO_ACTIVE_HIGH>;
+
+		brightness-levels = <0 1 2 4 8 16 32 64 128 255>;
+		default-brightness-level = <9>;
+	};
+
+	panel {
+		compatible = "tbs,a711-panel", "panel-lvds";
+		backlight = <&backlight>;
+		power-supply = <&reg_sw>;
+
+		width-mm = <153>;
+		height-mm = <90>;
+		data-mapping = "vesa-24";
+
+		panel-timing {
+			/* 1024x600 @60Hz */
+			clock-frequency = <52000000>;
+			hactive = <1024>;
+			vactive = <600>;
+			hsync-len = <20>;
+			hfront-porch = <180>;
+			hback-porch = <160>;
+			vfront-porch = <12>;
+			vback-porch = <23>;
+			vsync-len = <5>;
+		};
+
+		port {
+			panel_input: endpoint {
+				remote-endpoint = <&tcon0_out_lcd>;
+			};
+		};
+	};
+
 	reg_vbat: reg-vbat {
 		compatible = "regulator-fixed";
 		regulator-name = "vbat";
@@ -89,6 +128,10 @@
 	};
 };
 
+&de {
+	status = "okay";
+};
+
 /*
  * An USB-2 hub is connected here, which also means we don't need to
  * enable the OHCI controller.
@@ -142,10 +185,17 @@
 	status = "okay";
 };
 
+&pwm {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pwm_pin>;
+	status = "okay";
+};
+
 &r_rsb {
 	status = "okay";
 
 	axp81x: pmic@3a3 {
+		compatible = "x-powers,axp813";
 		reg = <0x3a3>;
 		interrupt-parent = <&r_intc>;
 		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
@@ -322,6 +372,18 @@
 	regulator-name = "vcc-lcd";
 };
 
+&tcon0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&lcd_lvds_pins>;
+};
+
+&tcon0_out {
+	tcon0_out_lcd: endpoint@0 {
+		reg = <0>;
+		remote-endpoint = <&panel_input>;
+	};
+};
+
 &uart0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart0_pb_pins>;
diff --git a/arch/arm/boot/dts/sun8i-a83t.dtsi b/arch/arm/boot/dts/sun8i-a83t.dtsi
index 19acae1b4089..7f4955a5fab7 100644
--- a/arch/arm/boot/dts/sun8i-a83t.dtsi
+++ b/arch/arm/boot/dts/sun8i-a83t.dtsi
@@ -45,8 +45,10 @@
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 
 #include <dt-bindings/clock/sun8i-a83t-ccu.h>
+#include <dt-bindings/clock/sun8i-de2.h>
 #include <dt-bindings/clock/sun8i-r-ccu.h>
 #include <dt-bindings/reset/sun8i-a83t-ccu.h>
+#include <dt-bindings/reset/sun8i-de2.h>
 #include <dt-bindings/reset/sun8i-r-ccu.h>
 
 / {
@@ -151,6 +153,12 @@
 		};
 	};
 
+	de: display-engine {
+		compatible = "allwinner,sun8i-a83t-display-engine";
+		allwinner,pipelines = <&mixer0>;
+		status = "disabled";
+	};
+
 	memory {
 		reg = <0x40000000 0x80000000>;
 		device_type = "memory";
@@ -162,6 +170,44 @@
 		#size-cells = <1>;
 		ranges;
 
+		display_clocks: clock@1000000 {
+			compatible = "allwinner,sun8i-a83t-de2-clk";
+			reg = <0x01000000 0x100000>;
+			clocks = <&ccu CLK_PLL_DE>,
+				 <&ccu CLK_BUS_DE>;
+			clock-names = "mod",
+				      "bus";
+			resets = <&ccu RST_BUS_DE>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
+		mixer0: mixer@1100000 {
+			compatible = "allwinner,sun8i-a83t-de2-mixer-0";
+			reg = <0x01100000 0x100000>;
+			clocks = <&display_clocks CLK_BUS_MIXER0>,
+				 <&display_clocks CLK_MIXER0>;
+			clock-names = "bus",
+				      "mod";
+			resets = <&display_clocks RST_MIXER0>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				mixer0_out: port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+
+					mixer0_out_tcon0: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&tcon0_in_mixer0>;
+					};
+				};
+			};
+		};
+
 		syscon: syscon@1c00000 {
 			compatible = "allwinner,sun8i-a83t-system-controller",
 				"syscon";
@@ -177,6 +223,39 @@
 			#dma-cells = <1>;
 		};
 
+		tcon0: lcd-controller@1c0c000 {
+			compatible = "allwinner,sun8i-a83t-tcon-lcd";
+			reg = <0x01c0c000 0x1000>;
+			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_TCON0>, <&ccu CLK_TCON0>;
+			clock-names = "ahb", "tcon-ch0";
+			clock-output-names = "tcon-pixel-clock";
+			resets = <&ccu RST_BUS_TCON0>, <&ccu RST_BUS_LVDS>;
+			reset-names = "lcd", "lvds";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				tcon0_in: port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+
+					tcon0_in_mixer0: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&mixer0_out_tcon0>;
+					};
+				};
+
+				tcon0_out: port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+				};
+			};
+		};
+
 		mmc0: mmc@1c0f000 {
 			compatible = "allwinner,sun8i-a83t-mmc",
 				     "allwinner,sun7i-a20-mmc";
@@ -336,6 +415,45 @@
 			#interrupt-cells = <3>;
 			#gpio-cells = <3>;
 
+			emac_rgmii_pins: emac-rgmii-pins {
+				pins = "PD2", "PD3", "PD4", "PD5", "PD6", "PD7",
+				       "PD11", "PD12", "PD13", "PD14", "PD18",
+				       "PD19", "PD21", "PD22", "PD23";
+				function = "gmac";
+				/*
+				 * data lines in RGMII mode use DDR mode
+				 * and need a higher signal drive strength
+				 */
+				drive-strength = <40>;
+			};
+
+			i2c0_pins: i2c0-pins {
+				pins = "PH0", "PH1";
+				function = "i2c0";
+			};
+
+			i2c1_pins: i2c1-pins {
+				pins = "PH2", "PH3";
+				function = "i2c1";
+			};
+
+			i2c2_ph_pins: i2c2-ph-pins {
+				pins = "PH4", "PH5";
+				function = "i2c2";
+			};
+
+			i2s1_pins: i2s1-pins {
+				/* I2S1 does not have external MCLK pin */
+				pins = "PG10", "PG11", "PG12", "PG13";
+				function = "i2s1";
+			};
+
+			lcd_lvds_pins: lcd-lvds-pins {
+				pins = "PD18", "PD19", "PD20", "PD21", "PD22",
+				       "PD23", "PD24", "PD25", "PD26", "PD27";
+				function = "lvds0";
+			};
+
 			mmc0_pins: mmc0-pins {
 				pins = "PF0", "PF1", "PF2",
 				       "PF3", "PF4", "PF5";
@@ -361,6 +479,11 @@
 				bias-pull-up;
 			};
 
+			pwm_pin: pwm-pin {
+				pins = "PD28";
+				function = "pwm";
+			};
+
 			spdif_tx_pin: spdif-tx-pin {
 				pins = "PE18";
 				function = "spdif";
@@ -418,6 +541,56 @@
 			status = "disabled";
 		};
 
+		i2s0: i2s@1c22000 {
+			#sound-dai-cells = <0>;
+			compatible = "allwinner,sun8i-a83t-i2s";
+			reg = <0x01c22000 0x400>;
+			interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_I2S0>, <&ccu CLK_I2S0>;
+			clock-names = "apb", "mod";
+			dmas = <&dma 3>, <&dma 3>;
+			resets = <&ccu RST_BUS_I2S0>;
+			dma-names = "rx", "tx";
+			status = "disabled";
+		};
+
+		i2s1: i2s@1c22400 {
+			#sound-dai-cells = <0>;
+			compatible = "allwinner,sun8i-a83t-i2s";
+			reg = <0x01c22400 0x400>;
+			interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_I2S1>, <&ccu CLK_I2S1>;
+			clock-names = "apb", "mod";
+			dmas = <&dma 4>, <&dma 4>;
+			resets = <&ccu RST_BUS_I2S1>;
+			dma-names = "rx", "tx";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2s1_pins>;
+			status = "disabled";
+		};
+
+		i2s2: i2s@1c22800 {
+			#sound-dai-cells = <0>;
+			compatible = "allwinner,sun8i-a83t-i2s";
+			reg = <0x01c22800 0x400>;
+			interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_I2S2>, <&ccu CLK_I2S2>;
+			clock-names = "apb", "mod";
+			dmas = <&dma 27>;
+			resets = <&ccu RST_BUS_I2S2>;
+			dma-names = "tx";
+			status = "disabled";
+		};
+
+		pwm: pwm@1c21400 {
+			compatible = "allwinner,sun8i-a83t-pwm",
+				     "allwinner,sun8i-h3-pwm";
+			reg = <0x01c21400 0x400>;
+			clocks = <&osc24M>;
+			#pwm-cells = <3>;
+			status = "disabled";
+		};
+
 		uart0: serial@1c28000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x01c28000 0x400>;
@@ -440,6 +613,67 @@
 			status = "disabled";
 		};
 
+		i2c0: i2c@1c2ac00 {
+			compatible = "allwinner,sun8i-a83t-i2c",
+				     "allwinner,sun6i-a31-i2c";
+			reg = <0x01c2ac00 0x400>;
+			interrupts = <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_I2C0>;
+			resets = <&ccu RST_BUS_I2C0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c0_pins>;
+			status = "disabled";
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		i2c1: i2c@1c2b000 {
+			compatible = "allwinner,sun8i-a83t-i2c",
+				     "allwinner,sun6i-a31-i2c";
+			reg = <0x01c2b000 0x400>;
+			interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_I2C1>;
+			resets = <&ccu RST_BUS_I2C1>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c1_pins>;
+			status = "disabled";
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		i2c2: i2c@1c2b400 {
+			compatible = "allwinner,sun8i-a83t-i2c",
+				     "allwinner,sun6i-a31-i2c";
+			reg = <0x01c2b400 0x400>;
+			interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_I2C2>;
+			resets = <&ccu RST_BUS_I2C2>;
+			status = "disabled";
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		emac: ethernet@1c30000 {
+			compatible = "allwinner,sun8i-a83t-emac";
+			syscon = <&syscon>;
+			reg = <0x01c30000 0x104>;
+			interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "macirq";
+			resets = <&ccu 13>;
+			reset-names = "stmmaceth";
+			clocks = <&ccu 27>;
+			clock-names = "stmmaceth";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+
+			mdio: mdio {
+				compatible = "snps,dwmac-mdio";
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
 		gic: interrupt-controller@1c81000 {
 			compatible = "arm,cortex-a7-gic", "arm,cortex-a15-gic";
 			reg = <0x01c81000 0x1000>,
diff --git a/arch/arm/boot/dts/sun8i-h2-plus-orangepi-r1.dts b/arch/arm/boot/dts/sun8i-h2-plus-orangepi-r1.dts
new file mode 100644
index 000000000000..112f09c67d67
--- /dev/null
+++ b/arch/arm/boot/dts/sun8i-h2-plus-orangepi-r1.dts
@@ -0,0 +1,91 @@
+/*
+ * Copyright (C) 2017 Icenowy Zheng <icenowy@aosc.xyz>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/* Orange Pi R1 is based on Orange Pi Zero design */
+#include "sun8i-h2-plus-orangepi-zero.dts"
+
+/ {
+	model = "Xunlong Orange Pi R1";
+	compatible = "xunlong,orangepi-r1", "allwinner,sun8i-h2-plus";
+
+	/delete-node/ reg_vcc_wifi;
+
+	/*
+	 * Ths pin of this regulator is the same with the Wi-Fi extra
+	 * regulator on the original Zero. However it's used for USB
+	 * Ethernet rather than the Wi-Fi now.
+	 */
+	reg_vcc_usb_eth: reg-vcc-usb-ethernet {
+		compatible = "regulator-fixed";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "vcc-usb-ethernet";
+		enable-active-high;
+		gpio = <&pio 0 20 GPIO_ACTIVE_HIGH>;
+	};
+
+	aliases {
+		ethernet1 = &rtl8189etv;
+	};
+};
+
+&ohci1 {
+	/*
+	 * RTL8152B USB-Ethernet adapter is connected to USB1,
+	 * and it's a USB 2.0 device. So the OHCI1 controller
+	 * can be left disabled.
+	 */
+	status = "disabled";
+};
+
+&mmc1 {
+	vmmc-supply = <&reg_vcc3v3>;
+	vqmmc-supply = <&reg_vcc3v3>;
+
+	rtl8189etv: sdio_wifi@1 {
+		reg = <1>;
+	};
+};
+
+&usbphy {
+	usb1_vbus-supply = <&reg_vcc_usb_eth>;
+};
diff --git a/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts b/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts
index f2292deaa590..f1c3f1cc4d97 100644
--- a/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts
+++ b/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts
@@ -119,7 +119,6 @@
 	phy-handle = <&ext_rgmii_phy>;
 	phy-mode = "rgmii";
 
-	allwinner,leds-active-low;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/sun8i-h3-libretech-all-h3-cc.dts b/arch/arm/boot/dts/sun8i-h3-libretech-all-h3-cc.dts
new file mode 100644
index 000000000000..d406571a0dd6
--- /dev/null
+++ b/arch/arm/boot/dts/sun8i-h3-libretech-all-h3-cc.dts
@@ -0,0 +1,196 @@
+/*
+ * Copyright (C) 2017 Chen-Yu Tsai <wens@csie.org>
+ *
+ * SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+ */
+
+/dts-v1/;
+#include "sun8i-h3.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+
+/ {
+	model = "Libre Computer Board ALL-H3-CC H3";
+	compatible = "libretech,all-h3-cc-h3", "allwinner,sun8i-h3";
+
+	aliases {
+		ethernet0 = &emac;
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		pwr_led {
+			label = "librecomputer:green:pwr";
+			gpios = <&r_pio 0 10 GPIO_ACTIVE_HIGH>; /* PL10 */
+			default-state = "on";
+		};
+
+		status_led {
+			label = "librecomputer:blue:status";
+			gpios = <&pio 0 7 GPIO_ACTIVE_HIGH>; /* PA7 */
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+
+		power {
+			label = "power";
+			linux,code = <KEY_POWER>;
+			gpios = <&r_pio 0 2 GPIO_ACTIVE_LOW>; /* PL2 */
+		};
+	};
+
+	reg_vcc1v2: vcc1v2 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc1v2";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&reg_vcc5v0>;
+		gpio = <&r_pio 0 8 GPIO_ACTIVE_HIGH>; /* PL8 */
+		enable-active-high;
+	};
+
+	reg_vcc3v3: vcc3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&reg_vcc5v0>;
+	};
+
+	/* This represents the board's 5V input */
+	reg_vcc5v0: vcc5v0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	reg_vcc_dram: vcc-dram {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc-dram";
+		regulator-min-microvolt = <1500000>;
+		regulator-max-microvolt = <1500000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&reg_vcc5v0>;
+		gpio = <&r_pio 0 9 GPIO_ACTIVE_HIGH>; /* PL9 */
+		enable-active-high;
+	};
+
+	reg_vcc_io: vcc-io {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc-io";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&reg_vcc3v3>;
+		gpio = <&r_pio 0 5 GPIO_ACTIVE_LOW>; /* PL5 */
+	};
+
+	reg_vdd_cpux: vdd-cpux {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd-cpux";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&reg_vcc5v0>;
+		gpio = <&r_pio 0 8 GPIO_ACTIVE_HIGH>; /* PL8 */
+		enable-active-high;
+	};
+};
+
+&codec {
+	allwinner,audio-routing =
+		"Line Out", "LINEOUT",
+		"MIC1", "Mic",
+		"Mic",  "MBIAS";
+	status = "okay";
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&ehci1 {
+	status = "okay";
+};
+
+&ehci2 {
+	status = "okay";
+};
+
+&ehci3 {
+	status = "okay";
+};
+
+&emac {
+	phy-handle = <&int_mii_phy>;
+	phy-mode = "mii";
+	allwinner,leds-active-low;
+	status = "okay";
+};
+
+&ir {
+	pinctrl-names = "default";
+	pinctrl-0 = <&ir_pins_a>;
+	status = "okay";
+};
+
+&mmc0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc0_pins_a>;
+	vmmc-supply = <&reg_vcc_io>;
+	bus-width = <4>;
+	cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>; /* PF6 */
+	cd-inverted;
+	status = "okay";
+};
+
+&ohci0 {
+	status = "okay";
+};
+
+&ohci1 {
+	status = "okay";
+};
+
+&ohci2 {
+	status = "okay";
+};
+
+&ohci3 {
+	status = "okay";
+};
+
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_pins_a>;
+	status = "okay";
+};
+
+&usb_otg {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&usbphy {
+	/* VBUS on USB ports are always on */
+	usb0_vbus-supply = <&reg_vcc5v0>;
+	usb1_vbus-supply = <&reg_vcc5v0>;
+	usb2_vbus-supply = <&reg_vcc5v0>;
+	usb3_vbus-supply = <&reg_vcc5v0>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/sun8i-h3-nanopi-m1-plus.dts b/arch/arm/boot/dts/sun8i-h3-nanopi-m1-plus.dts
index 0a8b79cf5954..a6e61915d648 100644
--- a/arch/arm/boot/dts/sun8i-h3-nanopi-m1-plus.dts
+++ b/arch/arm/boot/dts/sun8i-h3-nanopi-m1-plus.dts
@@ -48,6 +48,7 @@
 
 	aliases {
 		serial1 = &uart3;
+		ethernet0 = &emac;
 		ethernet1 = &sdio_wifi;
 	};
 
@@ -83,8 +84,6 @@
 	phy-handle = <&ext_rgmii_phy>;
 	phy-mode = "rgmii";
 
-	allwinner,leds-active-low;
-
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/sun8i-h3-nanopi-m1.dts b/arch/arm/boot/dts/sun8i-h3-nanopi-m1.dts
index 3a2ccdb28afd..c77fbca4f227 100644
--- a/arch/arm/boot/dts/sun8i-h3-nanopi-m1.dts
+++ b/arch/arm/boot/dts/sun8i-h3-nanopi-m1.dts
@@ -45,6 +45,10 @@
 / {
 	model = "FriendlyArm NanoPi M1";
 	compatible = "friendlyarm,nanopi-m1", "allwinner,sun8i-h3";
+
+	aliases {
+		ethernet0 = &emac;
+	};
 };
 
 &ehci1 {
@@ -55,6 +59,13 @@
 	status = "okay";
 };
 
+&emac {
+	phy-handle = <&int_mii_phy>;
+	phy-mode = "mii";
+	allwinner,leds-active-low;
+	status = "okay";
+};
+
 &ir {
 	pinctrl-names = "default";
 	pinctrl-0 = <&ir_pins_a>;
diff --git a/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts b/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts
index 78f6c24952dd..9f33f6fae595 100644
--- a/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts
+++ b/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts
@@ -47,9 +47,26 @@
 	compatible = "friendlyarm,nanopi-neo", "allwinner,sun8i-h3";
 };
 
+&ehci0 {
+	status = "okay";
+};
+
 &emac {
 	phy-handle = <&int_mii_phy>;
 	phy-mode = "mii";
 	allwinner,leds-active-low;
 	status = "okay";
 };
+
+&ohci0 {
+	status = "okay";
+};
+
+&usb_otg {
+	status = "okay";
+	dr_mode = "peripheral";
+};
+
+&usbphy {
+	usb0_id_det-gpios = <&pio 6 12 GPIO_ACTIVE_HIGH>; /* PG12 */
+};
diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-plus.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-plus.dts
index cbc499b04de4..b403e5d787cb 100644
--- a/arch/arm/boot/dts/sun8i-h3-orangepi-plus.dts
+++ b/arch/arm/boot/dts/sun8i-h3-orangepi-plus.dts
@@ -85,7 +85,6 @@
 	phy-handle = <&ext_rgmii_phy>;
 	phy-mode = "rgmii";
 
-	allwinner,leds-active-low;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/sun8i-h3.dtsi b/arch/arm/boot/dts/sun8i-h3.dtsi
index b36f9f423c39..8495deecedad 100644
--- a/arch/arm/boot/dts/sun8i-h3.dtsi
+++ b/arch/arm/boot/dts/sun8i-h3.dtsi
@@ -85,6 +85,10 @@
 	compatible = "allwinner,sun8i-h3-ccu";
 };
 
+&display_clocks {
+	compatible = "allwinner,sun8i-h3-de2-clk";
+};
+
 &mmc0 {
 	compatible = "allwinner,sun7i-a20-mmc";
 	clocks = <&ccu CLK_BUS_MMC0>,
diff --git a/arch/arm/boot/dts/sunxi-h3-h5.dtsi b/arch/arm/boot/dts/sunxi-h3-h5.dtsi
index 8d40c00d64bb..7a83b15225c7 100644
--- a/arch/arm/boot/dts/sunxi-h3-h5.dtsi
+++ b/arch/arm/boot/dts/sunxi-h3-h5.dtsi
@@ -40,9 +40,11 @@
  *     OTHER DEALINGS IN THE SOFTWARE.
  */
 
+#include <dt-bindings/clock/sun8i-de2.h>
 #include <dt-bindings/clock/sun8i-h3-ccu.h>
 #include <dt-bindings/clock/sun8i-r-ccu.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/reset/sun8i-de2.h>
 #include <dt-bindings/reset/sun8i-h3-ccu.h>
 #include <dt-bindings/reset/sun8i-r-ccu.h>
 
@@ -51,6 +53,30 @@
 	#address-cells = <1>;
 	#size-cells = <1>;
 
+	chosen {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		framebuffer-hdmi {
+			compatible = "allwinner,simple-framebuffer",
+				     "simple-framebuffer";
+			allwinner,pipeline = "mixer0-lcd0-hdmi";
+			clocks = <&display_clocks CLK_MIXER0>,
+				 <&ccu CLK_TCON0>, <&ccu CLK_HDMI>;
+			status = "disabled";
+		};
+
+		framebuffer-tve {
+			compatible = "allwinner,simple-framebuffer",
+				     "simple-framebuffer";
+			allwinner,pipeline = "mixer1-lcd1-tve";
+			clocks = <&display_clocks CLK_MIXER1>,
+				 <&ccu CLK_TVE>;
+			status = "disabled";
+		};
+	};
+
 	clocks {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -85,6 +111,18 @@
 		#size-cells = <1>;
 		ranges;
 
+		display_clocks: clock@1000000 {
+			/* compatible is in per SoC .dtsi file */
+			reg = <0x01000000 0x100000>;
+			clocks = <&ccu CLK_DE>,
+				 <&ccu CLK_BUS_DE>;
+			clock-names = "mod",
+				      "bus";
+			resets = <&ccu RST_BUS_DE>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
 		syscon: syscon@1c00000 {
 			compatible = "allwinner,sun8i-h3-system-controller",
 				"syscon";
diff --git a/arch/arm/boot/dts/tango4-common.dtsi b/arch/arm/boot/dts/tango4-common.dtsi
index 0ec1b0a317b4..ff72a8efb73d 100644
--- a/arch/arm/boot/dts/tango4-common.dtsi
+++ b/arch/arm/boot/dts/tango4-common.dtsi
@@ -156,7 +156,6 @@
 			reg = <0x6e000 0x400>;
 			ranges = <0 0x6e000 0x400>;
 			interrupt-parent = <&gic>;
-			interrupt-controller;
 			#address-cells = <1>;
 			#size-cells = <1>;
 
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index 914f59166a99..864a95872b8d 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -10,6 +10,19 @@
 	compatible = "nvidia,tegra20";
 	interrupt-parent = <&lic>;
 
+	iram@40000000 {
+		compatible = "mmio-sram";
+		reg = <0x40000000 0x40000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x40000000 0x40000>;
+
+		vde_pool: vde {
+			reg = <0x400 0x3fc00>;
+			pool;
+		};
+	};
+
 	host1x@50000000 {
 		compatible = "nvidia,tegra20-host1x", "simple-bus";
 		reg = <0x50000000 0x00024000>;
@@ -250,6 +263,28 @@
 		*/
 	};
 
+	vde@6001a000 {
+		compatible = "nvidia,tegra20-vde";
+		reg = <0x6001a000 0x1000   /* Syntax Engine */
+		       0x6001b000 0x1000   /* Video Bitstream Engine */
+		       0x6001c000  0x100   /* Macroblock Engine */
+		       0x6001c200  0x100   /* Post-processing Engine */
+		       0x6001c400  0x100   /* Motion Compensation Engine */
+		       0x6001c600  0x100   /* Transform Engine */
+		       0x6001c800  0x100   /* Pixel prediction block */
+		       0x6001ca00  0x100   /* Video DMA */
+		       0x6001d800  0x300>; /* Video frame controls */
+		reg-names = "sxe", "bsev", "mbe", "ppe", "mce",
+			    "tfe", "ppb", "vdma", "frameid";
+		iram = <&vde_pool>; /* IRAM region */
+		interrupts = <GIC_SPI  9 IRQ_TYPE_LEVEL_HIGH>, /* Sync token interrupt */
+			     <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>, /* BSE-V interrupt */
+			     <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; /* SXE interrupt */
+		interrupt-names = "sync-token", "bsev", "sxe";
+		clocks = <&tegra_car TEGRA20_CLK_VDE>;
+		resets = <&tegra_car 61>;
+	};
+
 	apbmisc@70000800 {
 		compatible = "nvidia,tegra20-apbmisc";
 		reg = <0x70000800 0x64   /* Chip revision */
diff --git a/arch/arm/boot/dts/tny_a9260_common.dtsi b/arch/arm/boot/dts/tny_a9260_common.dtsi
index 5d83df4675a1..8e3cf5109f98 100644
--- a/arch/arm/boot/dts/tny_a9260_common.dtsi
+++ b/arch/arm/boot/dts/tny_a9260_common.dtsi
@@ -27,6 +27,18 @@
 
 	ahb {
 		apb {
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			dbgu: serial@fffff200 {
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/tny_a9263.dts b/arch/arm/boot/dts/tny_a9263.dts
index 8cf0a9e08571..7b403db4cd34 100644
--- a/arch/arm/boot/dts/tny_a9263.dts
+++ b/arch/arm/boot/dts/tny_a9263.dts
@@ -36,6 +36,18 @@
 				status = "okay";
 			};
 
+			tcb0: timer@fff7c000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			usb1: gadget@fff78000 {
 				atmel,vbus-gpio = <&pioB 11 GPIO_ACTIVE_HIGH>;
 				status = "okay";
diff --git a/arch/arm/boot/dts/uniphier-ld4-ref.dts b/arch/arm/boot/dts/uniphier-ld4-ref.dts
index 0056852c4fb0..a3afd0cda42f 100644
--- a/arch/arm/boot/dts/uniphier-ld4-ref.dts
+++ b/arch/arm/boot/dts/uniphier-ld4-ref.dts
@@ -56,7 +56,7 @@
 &gpio {
 	xirq1 {
 		gpio-hog;
-		gpios = <121 0>;
+		gpios = <UNIPHIER_GPIO_IRQ(1) 0>;
 		input;
 	};
 };
diff --git a/arch/arm/boot/dts/uniphier-ld4.dtsi b/arch/arm/boot/dts/uniphier-ld4.dtsi
index 01fc3e16e2bd..0459e84d4d8e 100644
--- a/arch/arm/boot/dts/uniphier-ld4.dtsi
+++ b/arch/arm/boot/dts/uniphier-ld4.dtsi
@@ -7,6 +7,8 @@
  * SPDX-License-Identifier: (GPL-2.0+ OR MIT)
  */
 
+#include <dt-bindings/gpio/uniphier-gpio.h>
+
 / {
 	compatible = "socionext,uniphier-ld4";
 	#address-cells = <1>;
@@ -235,6 +237,7 @@
 				 <&mio_clk 12>;
 			resets = <&sys_rst 8>, <&mio_rst 7>, <&mio_rst 8>,
 				 <&mio_rst 12>;
+			has-transaction-translator;
 		};
 
 		usb1: usb@5a810100 {
@@ -248,6 +251,7 @@
 				 <&mio_clk 13>;
 			resets = <&sys_rst 8>, <&mio_rst 7>, <&mio_rst 9>,
 				 <&mio_rst 13>;
+			has-transaction-translator;
 		};
 
 		usb2: usb@5a820100 {
@@ -261,6 +265,7 @@
 				 <&mio_clk 14>;
 			resets = <&sys_rst 8>, <&mio_rst 7>, <&mio_rst 10>,
 				 <&mio_rst 14>;
+			has-transaction-translator;
 		};
 
 		soc-glue@5f800000 {
@@ -273,6 +278,24 @@
 			};
 		};
 
+		soc-glue@5f900000 {
+			compatible = "socionext,uniphier-ld4-soc-glue-debug",
+				     "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x5f900000 0x2000>;
+
+			efuse@100 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x100 0x28>;
+			};
+
+			efuse@130 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x130 0x8>;
+			};
+		};
+
 		timer@60000200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x60000200 0x20>;
diff --git a/arch/arm/boot/dts/uniphier-ld6b-ref.dts b/arch/arm/boot/dts/uniphier-ld6b-ref.dts
index 0e510a725976..811b999800ed 100644
--- a/arch/arm/boot/dts/uniphier-ld6b-ref.dts
+++ b/arch/arm/boot/dts/uniphier-ld6b-ref.dts
@@ -58,7 +58,7 @@
 &gpio {
 	xirq4 {
 		gpio-hog;
-		gpios = <124 0>;
+		gpios = <UNIPHIER_GPIO_IRQ(4) 0>;
 		input;
 	};
 };
diff --git a/arch/arm/boot/dts/uniphier-pro4-ref.dts b/arch/arm/boot/dts/uniphier-pro4-ref.dts
index be99467ac6bb..6a004e5cf786 100644
--- a/arch/arm/boot/dts/uniphier-pro4-ref.dts
+++ b/arch/arm/boot/dts/uniphier-pro4-ref.dts
@@ -58,7 +58,7 @@
 &gpio {
 	xirq2 {
 		gpio-hog;
-		gpios = <122 0>;
+		gpios = <UNIPHIER_GPIO_IRQ(2) 0>;
 		input;
 	};
 };
diff --git a/arch/arm/boot/dts/uniphier-pro4.dtsi b/arch/arm/boot/dts/uniphier-pro4.dtsi
index 7955c3a49e65..1a29a8619856 100644
--- a/arch/arm/boot/dts/uniphier-pro4.dtsi
+++ b/arch/arm/boot/dts/uniphier-pro4.dtsi
@@ -7,6 +7,8 @@
  * SPDX-License-Identifier: (GPL-2.0+ OR MIT)
  */
 
+#include <dt-bindings/gpio/uniphier-gpio.h>
+
 / {
 	compatible = "socionext,uniphier-pro4";
 	#address-cells = <1>;
@@ -269,6 +271,7 @@
 				 <&mio_clk 12>;
 			resets = <&sys_rst 8>, <&mio_rst 7>, <&mio_rst 8>,
 				 <&mio_rst 12>;
+			has-transaction-translator;
 		};
 
 		usb3: usb@5a810100 {
@@ -282,6 +285,7 @@
 				 <&mio_clk 13>;
 			resets = <&sys_rst 8>, <&mio_rst 7>, <&mio_rst 9>,
 				 <&mio_rst 13>;
+			has-transaction-translator;
 		};
 
 		soc-glue@5f800000 {
@@ -294,6 +298,29 @@
 			};
 		};
 
+		soc-glue@5f900000 {
+			compatible = "socionext,uniphier-pro4-soc-glue-debug",
+				     "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x5f900000 0x2000>;
+
+			efuse@100 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x100 0x28>;
+			};
+
+			efuse@130 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x130 0x8>;
+			};
+
+			efuse@200 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x200 0x14>;
+			};
+		};
+
 		aidet: aidet@5fc20000 {
 			compatible = "socionext,uniphier-pro4-aidet";
 			reg = <0x5fc20000 0x200>;
diff --git a/arch/arm/boot/dts/uniphier-pro5.dtsi b/arch/arm/boot/dts/uniphier-pro5.dtsi
index 6589b8a2c65c..f291dd63de9c 100644
--- a/arch/arm/boot/dts/uniphier-pro5.dtsi
+++ b/arch/arm/boot/dts/uniphier-pro5.dtsi
@@ -355,6 +355,39 @@
 			};
 		};
 
+		soc-glue@5f900000 {
+			compatible = "socionext,uniphier-pro5-soc-glue-debug",
+				     "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x5f900000 0x2000>;
+
+			efuse@100 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x100 0x28>;
+			};
+
+			efuse@130 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x130 0x8>;
+			};
+
+			efuse@200 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x200 0x28>;
+			};
+
+			efuse@300 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x300 0x14>;
+			};
+
+			efuse@400 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x400 0x8>;
+			};
+		};
+
 		aidet: aidet@5fc20000 {
 			compatible = "socionext,uniphier-pro5-aidet";
 			reg = <0x5fc20000 0x200>;
diff --git a/arch/arm/boot/dts/uniphier-pxs2.dtsi b/arch/arm/boot/dts/uniphier-pxs2.dtsi
index d82d6d872131..c083468c17db 100644
--- a/arch/arm/boot/dts/uniphier-pxs2.dtsi
+++ b/arch/arm/boot/dts/uniphier-pxs2.dtsi
@@ -7,6 +7,7 @@
  * SPDX-License-Identifier: (GPL-2.0+ OR MIT)
  */
 
+#include <dt-bindings/gpio/uniphier-gpio.h>
 #include <dt-bindings/thermal/thermal.h>
 
 / {
@@ -375,6 +376,24 @@
 			};
 		};
 
+		soc-glue@5f900000 {
+			compatible = "socionext,uniphier-pxs2-soc-glue-debug",
+				     "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x5f900000 0x2000>;
+
+			efuse@100 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x100 0x28>;
+			};
+
+			efuse@200 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x200 0x58>;
+			};
+		};
+
 		aidet: aidet@5fc20000 {
 			compatible = "socionext,uniphier-pxs2-aidet";
 			reg = <0x5fc20000 0x200>;
diff --git a/arch/arm/boot/dts/uniphier-sld8-ref.dts b/arch/arm/boot/dts/uniphier-sld8-ref.dts
index 1c0e7077a560..e052ea3b4020 100644
--- a/arch/arm/boot/dts/uniphier-sld8-ref.dts
+++ b/arch/arm/boot/dts/uniphier-sld8-ref.dts
@@ -56,7 +56,7 @@
 &gpio {
 	xirq0 {
 		gpio-hog;
-		gpios = <120 0>;
+		gpios = <UNIPHIER_GPIO_IRQ(0) 0>;
 		input;
 	};
 };
diff --git a/arch/arm/boot/dts/uniphier-sld8.dtsi b/arch/arm/boot/dts/uniphier-sld8.dtsi
index 71885366cd23..bc8c24078faa 100644
--- a/arch/arm/boot/dts/uniphier-sld8.dtsi
+++ b/arch/arm/boot/dts/uniphier-sld8.dtsi
@@ -7,6 +7,8 @@
  * SPDX-License-Identifier: (GPL-2.0+ OR MIT)
  */
 
+#include <dt-bindings/gpio/uniphier-gpio.h>
+
 / {
 	compatible = "socionext,uniphier-sld8";
 	#address-cells = <1>;
@@ -239,6 +241,7 @@
 				 <&mio_clk 12>;
 			resets = <&sys_rst 8>, <&mio_rst 7>, <&mio_rst 8>,
 				 <&mio_rst 12>;
+			has-transaction-translator;
 		};
 
 		usb1: usb@5a810100 {
@@ -252,6 +255,7 @@
 				 <&mio_clk 13>;
 			resets = <&sys_rst 8>, <&mio_rst 7>, <&mio_rst 9>,
 				 <&mio_rst 13>;
+			has-transaction-translator;
 		};
 
 		usb2: usb@5a820100 {
@@ -265,6 +269,7 @@
 				 <&mio_clk 14>;
 			resets = <&sys_rst 8>, <&mio_rst 7>, <&mio_rst 10>,
 				 <&mio_rst 14>;
+			has-transaction-translator;
 		};
 
 		soc-glue@5f800000 {
@@ -277,6 +282,24 @@
 			};
 		};
 
+		soc-glue@5f900000 {
+			compatible = "socionext,uniphier-sld8-soc-glue-debug",
+				     "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x5f900000 0x2000>;
+
+			efuse@100 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x100 0x28>;
+			};
+
+			efuse@200 {
+				compatible = "socionext,uniphier-efuse";
+				reg = <0x200 0x14>;
+			};
+		};
+
 		timer@60000200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x60000200 0x20>;
diff --git a/arch/arm/boot/dts/usb_a9260_common.dtsi b/arch/arm/boot/dts/usb_a9260_common.dtsi
index 34a49995eda3..de3fa3ab34d6 100644
--- a/arch/arm/boot/dts/usb_a9260_common.dtsi
+++ b/arch/arm/boot/dts/usb_a9260_common.dtsi
@@ -23,6 +23,18 @@
 				status = "okay";
 			};
 
+			tcb0: timer@fffa0000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			macb0: ethernet@fffc4000 {
 				phy-mode = "rmii";
 				status = "okay";
diff --git a/arch/arm/boot/dts/usb_a9263.dts b/arch/arm/boot/dts/usb_a9263.dts
index 7b1125be99c4..0a753b4c74e7 100644
--- a/arch/arm/boot/dts/usb_a9263.dts
+++ b/arch/arm/boot/dts/usb_a9263.dts
@@ -36,6 +36,18 @@
 				status = "okay";
 			};
 
+			tcb0: timer@fff7c000 {
+				timer@0 {
+					compatible = "atmel,tcb-timer";
+					reg = <0>, <1>;
+				};
+
+				timer@2 {
+					compatible = "atmel,tcb-timer";
+					reg = <2>;
+				};
+			};
+
 			macb0: ethernet@fffbc000 {
 				phy-mode = "rmii";
 				status = "okay";
diff --git a/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi b/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi
index 091b738041a0..d8b2972527eb 100644
--- a/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi
+++ b/arch/arm/boot/dts/vf-colibri-eval-v3.dtsi
@@ -140,7 +140,7 @@
 
 	/* M41T0M6 real time clock on carrier board */
 	rtc: m41t0m6@68 {
-		compatible = "st,m41t00";
+		compatible = "st,m41t0";
 		reg = <0x68>;
 	};
 };
diff --git a/arch/arm/boot/dts/vf500.dtsi b/arch/arm/boot/dts/vf500.dtsi
index 3d9896171bfc..348bcd30c0f7 100644
--- a/arch/arm/boot/dts/vf500.dtsi
+++ b/arch/arm/boot/dts/vf500.dtsi
@@ -58,7 +58,7 @@
 	soc {
 		aips-bus@40000000 {
 
-			intc: interrupt-controller@40002000 {
+			intc: interrupt-controller@40003000 {
 				compatible = "arm,cortex-a9-gic";
 				#interrupt-cells = <3>;
 				interrupt-controller;
diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
index acdf12ad0622..782b69a3acdf 100644
--- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
+++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
@@ -255,16 +255,19 @@
 					port@0 {
 						reg = <0>;
 						label = "lan6";
+						phy-handle = <&switch2phy0>;
 					};
 
 					port@1 {
 						reg = <1>;
 						label = "lan7";
+						phy-handle = <&switch2phy1>;
 					};
 
 					port@2 {
 						reg = <2>;
 						label = "lan8";
+						phy-handle = <&switch2phy2>;
 					};
 
 					port@3 {
@@ -304,6 +307,20 @@
 						};
 					};
 				};
+				mdio {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					switch2phy0: phy@0 {
+						reg = <0>;
+					};
+					switch2phy1: phy@1 {
+						reg = <1>;
+					};
+					switch2phy2: phy@2 {
+						reg = <2>;
+					};
+				};
 			};
 		};
 
@@ -371,7 +388,8 @@
 		reg = <0x22>;
 		gpio-controller;
 		#gpio-cells = <2>;
-		interrupt-parent = <&gpio2>;
+		interrupt-controller;
+		interrupt-parent = <&gpio3>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 	};
 };
diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts
index 02a6227c717c..c6f134c78303 100644
--- a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts
+++ b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts
@@ -73,7 +73,7 @@
 				#size-cells = <0>;
 				reg = <0>;
 				dsa,member = <0 0>;
-				eeprom-length = <512>;
+				eeprom-length = <65536>;
 				interrupt-parent = <&gpio0>;
 				interrupts = <27 IRQ_TYPE_LEVEL_LOW>;
 				interrupt-controller;
@@ -121,7 +121,7 @@
 					switch0port10: port@10 {
 						reg = <10>;
 						label = "dsa";
-						phy-mode = "xgmii";
+						phy-mode = "xaui";
 						link = <&switch1port10>;
 					};
 				};
@@ -170,7 +170,7 @@
 				#size-cells = <0>;
 				reg = <0>;
 				dsa,member = <0 1>;
-				eeprom-length = <512>;
+				eeprom-length = <65536>;
 				interrupt-parent = <&gpio0>;
 				interrupts = <26 IRQ_TYPE_LEVEL_LOW>;
 				interrupt-controller;
@@ -208,7 +208,7 @@
 					switch1port10: port@10 {
 						reg = <10>;
 						label = "dsa";
-						phy-mode = "xgmii";
+						phy-mode = "xaui";
 						link = <&switch0port10>;
 					};
 				};
@@ -359,7 +359,7 @@
 };
 
 &i2c1 {
-	at24mac602@0 {
+	at24mac602@50 {
 		compatible = "atmel,24c02";
 		reg = <0x50>;
 		read-only;
diff --git a/arch/arm/boot/dts/vf610-zii-dev.dtsi b/arch/arm/boot/dts/vf610-zii-dev.dtsi
index 6b58d3a97992..aadd36db0092 100644
--- a/arch/arm/boot/dts/vf610-zii-dev.dtsi
+++ b/arch/arm/boot/dts/vf610-zii-dev.dtsi
@@ -96,6 +96,10 @@
 	status = "okay";
 };
 
+&edma1 {
+	status = "okay";
+};
+
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index 5d654b5b4ce6..c3f09b737924 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -84,6 +84,11 @@
 		mask = <0x1000>;
 	};
 
+	iio-hwmon {
+		compatible = "iio-hwmon";
+		io-channels = <&adc0 16>, <&adc1 16>;
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -762,10 +767,5 @@
 				status = "disabled";
 			};
 		};
-
-		iio-hwmon {
-			compatible = "iio-hwmon";
-			io-channels = <&adc0 16>, <&adc1 16>;
-		};
 	};
 };
diff --git a/arch/arm/common/bL_switcher_dummy_if.c b/arch/arm/common/bL_switcher_dummy_if.c
index 4c10c6452678..f4dc1714a79e 100644
--- a/arch/arm/common/bL_switcher_dummy_if.c
+++ b/arch/arm/common/bL_switcher_dummy_if.c
@@ -57,3 +57,7 @@ static struct miscdevice bL_switcher_device = {
 	&bL_switcher_fops
 };
 module_misc_device(bL_switcher_device);
+
+MODULE_AUTHOR("Nicolas Pitre <nico@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("big.LITTLE switcher dummy user interface");
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 4ecd5120fce7..a2c878769eaf 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -108,6 +108,7 @@ struct sa1111 {
 	spinlock_t	lock;
 	void __iomem	*base;
 	struct sa1111_platform_data *pdata;
+	struct irq_domain *irqdomain;
 	struct gpio_chip gc;
 #ifdef CONFIG_PM
 	void		*saved_state;
@@ -125,7 +126,7 @@ struct sa1111_dev_info {
 	unsigned long	skpcr_mask;
 	bool		dma;
 	unsigned int	devid;
-	unsigned int	irq[6];
+	unsigned int	hwirq[6];
 };
 
 static struct sa1111_dev_info sa1111_devices[] = {
@@ -134,7 +135,7 @@ static struct sa1111_dev_info sa1111_devices[] = {
 		.skpcr_mask	= SKPCR_UCLKEN,
 		.dma		= true,
 		.devid		= SA1111_DEVID_USB,
-		.irq = {
+		.hwirq = {
 			IRQ_USBPWR,
 			IRQ_HCIM,
 			IRQ_HCIBUFFACC,
@@ -148,7 +149,7 @@ static struct sa1111_dev_info sa1111_devices[] = {
 		.skpcr_mask	= SKPCR_I2SCLKEN | SKPCR_L3CLKEN,
 		.dma		= true,
 		.devid		= SA1111_DEVID_SAC,
-		.irq = {
+		.hwirq = {
 			AUDXMTDMADONEA,
 			AUDXMTDMADONEB,
 			AUDRCVDMADONEA,
@@ -164,7 +165,7 @@ static struct sa1111_dev_info sa1111_devices[] = {
 		.offset		= SA1111_KBD,
 		.skpcr_mask	= SKPCR_PTCLKEN,
 		.devid		= SA1111_DEVID_PS2_KBD,
-		.irq = {
+		.hwirq = {
 			IRQ_TPRXINT,
 			IRQ_TPTXINT
 		},
@@ -173,7 +174,7 @@ static struct sa1111_dev_info sa1111_devices[] = {
 		.offset		= SA1111_MSE,
 		.skpcr_mask	= SKPCR_PMCLKEN,
 		.devid		= SA1111_DEVID_PS2_MSE,
-		.irq = {
+		.hwirq = {
 			IRQ_MSRXINT,
 			IRQ_MSTXINT
 		},
@@ -182,7 +183,7 @@ static struct sa1111_dev_info sa1111_devices[] = {
 		.offset		= 0x1800,
 		.skpcr_mask	= 0,
 		.devid		= SA1111_DEVID_PCMCIA,
-		.irq = {
+		.hwirq = {
 			IRQ_S0_READY_NINT,
 			IRQ_S0_CD_VALID,
 			IRQ_S0_BVD1_STSCHG,
@@ -193,6 +194,19 @@ static struct sa1111_dev_info sa1111_devices[] = {
 	},
 };
 
+static int sa1111_map_irq(struct sa1111 *sachip, irq_hw_number_t hwirq)
+{
+	return irq_create_mapping(sachip->irqdomain, hwirq);
+}
+
+static void sa1111_handle_irqdomain(struct irq_domain *irqdomain, int irq)
+{
+	struct irq_desc *d = irq_to_desc(irq_linear_revmap(irqdomain, irq));
+
+	if (d)
+		generic_handle_irq_desc(d);
+}
+
 /*
  * SA1111 interrupt support.  Since clearing an IRQ while there are
  * active IRQs causes the interrupt output to pulse, the upper levels
@@ -202,49 +216,45 @@ static void sa1111_irq_handler(struct irq_desc *desc)
 {
 	unsigned int stat0, stat1, i;
 	struct sa1111 *sachip = irq_desc_get_handler_data(desc);
+	struct irq_domain *irqdomain;
 	void __iomem *mapbase = sachip->base + SA1111_INTC;
 
-	stat0 = sa1111_readl(mapbase + SA1111_INTSTATCLR0);
-	stat1 = sa1111_readl(mapbase + SA1111_INTSTATCLR1);
+	stat0 = readl_relaxed(mapbase + SA1111_INTSTATCLR0);
+	stat1 = readl_relaxed(mapbase + SA1111_INTSTATCLR1);
 
-	sa1111_writel(stat0, mapbase + SA1111_INTSTATCLR0);
+	writel_relaxed(stat0, mapbase + SA1111_INTSTATCLR0);
 
 	desc->irq_data.chip->irq_ack(&desc->irq_data);
 
-	sa1111_writel(stat1, mapbase + SA1111_INTSTATCLR1);
+	writel_relaxed(stat1, mapbase + SA1111_INTSTATCLR1);
 
 	if (stat0 == 0 && stat1 == 0) {
 		do_bad_IRQ(desc);
 		return;
 	}
 
+	irqdomain = sachip->irqdomain;
+
 	for (i = 0; stat0; i++, stat0 >>= 1)
 		if (stat0 & 1)
-			generic_handle_irq(i + sachip->irq_base);
+			sa1111_handle_irqdomain(irqdomain, i);
 
 	for (i = 32; stat1; i++, stat1 >>= 1)
 		if (stat1 & 1)
-			generic_handle_irq(i + sachip->irq_base);
+			sa1111_handle_irqdomain(irqdomain, i);
 
 	/* For level-based interrupts */
 	desc->irq_data.chip->irq_unmask(&desc->irq_data);
 }
 
-#define SA1111_IRQMASK_LO(x)	(1 << (x - sachip->irq_base))
-#define SA1111_IRQMASK_HI(x)	(1 << (x - sachip->irq_base - 32))
-
 static u32 sa1111_irqmask(struct irq_data *d)
 {
-	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-
-	return BIT((d->irq - sachip->irq_base) & 31);
+	return BIT(irqd_to_hwirq(d) & 31);
 }
 
 static int sa1111_irqbank(struct irq_data *d)
 {
-	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-
-	return ((d->irq - sachip->irq_base) / 32) * 4;
+	return (irqd_to_hwirq(d) / 32) * 4;
 }
 
 static void sa1111_ack_irq(struct irq_data *d)
@@ -257,9 +267,9 @@ static void sa1111_mask_irq(struct irq_data *d)
 	void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d);
 	u32 ie;
 
-	ie = sa1111_readl(mapbase + SA1111_INTEN0);
+	ie = readl_relaxed(mapbase + SA1111_INTEN0);
 	ie &= ~sa1111_irqmask(d);
-	sa1111_writel(ie, mapbase + SA1111_INTEN0);
+	writel(ie, mapbase + SA1111_INTEN0);
 }
 
 static void sa1111_unmask_irq(struct irq_data *d)
@@ -268,9 +278,9 @@ static void sa1111_unmask_irq(struct irq_data *d)
 	void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d);
 	u32 ie;
 
-	ie = sa1111_readl(mapbase + SA1111_INTEN0);
+	ie = readl_relaxed(mapbase + SA1111_INTEN0);
 	ie |= sa1111_irqmask(d);
-	sa1111_writel(ie, mapbase + SA1111_INTEN0);
+	writel_relaxed(ie, mapbase + SA1111_INTEN0);
 }
 
 /*
@@ -287,11 +297,11 @@ static int sa1111_retrigger_irq(struct irq_data *d)
 	u32 ip, mask = sa1111_irqmask(d);
 	int i;
 
-	ip = sa1111_readl(mapbase + SA1111_INTPOL0);
+	ip = readl_relaxed(mapbase + SA1111_INTPOL0);
 	for (i = 0; i < 8; i++) {
-		sa1111_writel(ip ^ mask, mapbase + SA1111_INTPOL0);
-		sa1111_writel(ip, mapbase + SA1111_INTPOL0);
-		if (sa1111_readl(mapbase + SA1111_INTSTATCLR0) & mask)
+		writel_relaxed(ip ^ mask, mapbase + SA1111_INTPOL0);
+		writel_relaxed(ip, mapbase + SA1111_INTPOL0);
+		if (readl_relaxed(mapbase + SA1111_INTSTATCLR0) & mask)
 			break;
 	}
 
@@ -313,13 +323,13 @@ static int sa1111_type_irq(struct irq_data *d, unsigned int flags)
 	if ((!(flags & IRQ_TYPE_EDGE_RISING) ^ !(flags & IRQ_TYPE_EDGE_FALLING)) == 0)
 		return -EINVAL;
 
-	ip = sa1111_readl(mapbase + SA1111_INTPOL0);
+	ip = readl_relaxed(mapbase + SA1111_INTPOL0);
 	if (flags & IRQ_TYPE_EDGE_RISING)
 		ip &= ~mask;
 	else
 		ip |= mask;
-	sa1111_writel(ip, mapbase + SA1111_INTPOL0);
-	sa1111_writel(ip, mapbase + SA1111_WAKEPOL0);
+	writel_relaxed(ip, mapbase + SA1111_INTPOL0);
+	writel_relaxed(ip, mapbase + SA1111_WAKEPOL0);
 
 	return 0;
 }
@@ -330,12 +340,12 @@ static int sa1111_wake_irq(struct irq_data *d, unsigned int on)
 	void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d);
 	u32 we, mask = sa1111_irqmask(d);
 
-	we = sa1111_readl(mapbase + SA1111_WAKEEN0);
+	we = readl_relaxed(mapbase + SA1111_WAKEEN0);
 	if (on)
 		we |= mask;
 	else
 		we &= ~mask;
-	sa1111_writel(we, mapbase + SA1111_WAKEEN0);
+	writel_relaxed(we, mapbase + SA1111_WAKEEN0);
 
 	return 0;
 }
@@ -350,10 +360,30 @@ static struct irq_chip sa1111_irq_chip = {
 	.irq_set_wake	= sa1111_wake_irq,
 };
 
+static int sa1111_irqdomain_map(struct irq_domain *d, unsigned int irq,
+	irq_hw_number_t hwirq)
+{
+	struct sa1111 *sachip = d->host_data;
+
+	/* Disallow unavailable interrupts */
+	if (hwirq > SSPROR && hwirq < AUDXMTDMADONEA)
+		return -EINVAL;
+
+	irq_set_chip_data(irq, sachip);
+	irq_set_chip_and_handler(irq, &sa1111_irq_chip, handle_edge_irq);
+	irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
+
+	return 0;
+}
+
+static const struct irq_domain_ops sa1111_irqdomain_ops = {
+	.map = sa1111_irqdomain_map,
+	.xlate = irq_domain_xlate_twocell,
+};
+
 static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 {
 	void __iomem *irqbase = sachip->base + SA1111_INTC;
-	unsigned i, irq;
 	int ret;
 
 	/*
@@ -373,38 +403,40 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 	sachip->irq_base = ret;
 
 	/* disable all IRQs */
-	sa1111_writel(0, irqbase + SA1111_INTEN0);
-	sa1111_writel(0, irqbase + SA1111_INTEN1);
-	sa1111_writel(0, irqbase + SA1111_WAKEEN0);
-	sa1111_writel(0, irqbase + SA1111_WAKEEN1);
+	writel_relaxed(0, irqbase + SA1111_INTEN0);
+	writel_relaxed(0, irqbase + SA1111_INTEN1);
+	writel_relaxed(0, irqbase + SA1111_WAKEEN0);
+	writel_relaxed(0, irqbase + SA1111_WAKEEN1);
 
 	/*
 	 * detect on rising edge.  Note: Feb 2001 Errata for SA1111
 	 * specifies that S0ReadyInt and S1ReadyInt should be '1'.
 	 */
-	sa1111_writel(0, irqbase + SA1111_INTPOL0);
-	sa1111_writel(BIT(IRQ_S0_READY_NINT & 31) |
-		      BIT(IRQ_S1_READY_NINT & 31),
-		      irqbase + SA1111_INTPOL1);
+	writel_relaxed(0, irqbase + SA1111_INTPOL0);
+	writel_relaxed(BIT(IRQ_S0_READY_NINT & 31) |
+		       BIT(IRQ_S1_READY_NINT & 31),
+		       irqbase + SA1111_INTPOL1);
 
 	/* clear all IRQs */
-	sa1111_writel(~0, irqbase + SA1111_INTSTATCLR0);
-	sa1111_writel(~0, irqbase + SA1111_INTSTATCLR1);
-
-	for (i = IRQ_GPAIN0; i <= SSPROR; i++) {
-		irq = sachip->irq_base + i;
-		irq_set_chip_and_handler(irq, &sa1111_irq_chip, handle_edge_irq);
-		irq_set_chip_data(irq, sachip);
-		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
-	}
+	writel_relaxed(~0, irqbase + SA1111_INTSTATCLR0);
+	writel_relaxed(~0, irqbase + SA1111_INTSTATCLR1);
 
-	for (i = AUDXMTDMADONEA; i <= IRQ_S1_BVD1_STSCHG; i++) {
-		irq = sachip->irq_base + i;
-		irq_set_chip_and_handler(irq, &sa1111_irq_chip, handle_edge_irq);
-		irq_set_chip_data(irq, sachip);
-		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
+	sachip->irqdomain = irq_domain_add_linear(NULL, SA1111_IRQ_NR,
+						  &sa1111_irqdomain_ops,
+						  sachip);
+	if (!sachip->irqdomain) {
+		irq_free_descs(sachip->irq_base, SA1111_IRQ_NR);
+		return -ENOMEM;
 	}
 
+	irq_domain_associate_many(sachip->irqdomain,
+				  sachip->irq_base + IRQ_GPAIN0,
+				  IRQ_GPAIN0, SSPROR + 1 - IRQ_GPAIN0);
+	irq_domain_associate_many(sachip->irqdomain,
+				  sachip->irq_base + AUDXMTDMADONEA,
+				  AUDXMTDMADONEA,
+				  IRQ_S1_BVD1_STSCHG + 1 - AUDXMTDMADONEA);
+
 	/*
 	 * Register SA1111 interrupt
 	 */
@@ -420,20 +452,22 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 
 static void sa1111_remove_irq(struct sa1111 *sachip)
 {
+	struct irq_domain *domain = sachip->irqdomain;
 	void __iomem *irqbase = sachip->base + SA1111_INTC;
+	int i;
 
 	/* disable all IRQs */
-	sa1111_writel(0, irqbase + SA1111_INTEN0);
-	sa1111_writel(0, irqbase + SA1111_INTEN1);
-	sa1111_writel(0, irqbase + SA1111_WAKEEN0);
-	sa1111_writel(0, irqbase + SA1111_WAKEEN1);
+	writel_relaxed(0, irqbase + SA1111_INTEN0);
+	writel_relaxed(0, irqbase + SA1111_INTEN1);
+	writel_relaxed(0, irqbase + SA1111_WAKEEN0);
+	writel_relaxed(0, irqbase + SA1111_WAKEEN1);
 
-	if (sachip->irq != NO_IRQ) {
-		irq_set_chained_handler_and_data(sachip->irq, NULL, NULL);
-		irq_free_descs(sachip->irq_base, SA1111_IRQ_NR);
+	irq_set_chained_handler_and_data(sachip->irq, NULL, NULL);
+	for (i = 0; i < SA1111_IRQ_NR; i++)
+		irq_dispose_mapping(irq_find_mapping(domain, i));
+	irq_domain_remove(domain);
 
-		release_mem_region(sachip->phys + SA1111_INTC, 512);
-	}
+	release_mem_region(sachip->phys + SA1111_INTC, 512);
 }
 
 enum {
@@ -572,7 +606,7 @@ static int sa1111_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
 {
 	struct sa1111 *sachip = gc_to_sa1111(gc);
 
-	return sachip->irq_base + offset;
+	return sa1111_map_irq(sachip, offset);
 }
 
 static int sa1111_setup_gpios(struct sa1111 *sachip)
@@ -618,11 +652,11 @@ static void sa1111_wake(struct sa1111 *sachip)
 	/*
 	 * Turn VCO on, and disable PLL Bypass.
 	 */
-	r = sa1111_readl(sachip->base + SA1111_SKCR);
+	r = readl_relaxed(sachip->base + SA1111_SKCR);
 	r &= ~SKCR_VCO_OFF;
-	sa1111_writel(r, sachip->base + SA1111_SKCR);
+	writel_relaxed(r, sachip->base + SA1111_SKCR);
 	r |= SKCR_PLL_BYPASS | SKCR_OE_EN;
-	sa1111_writel(r, sachip->base + SA1111_SKCR);
+	writel_relaxed(r, sachip->base + SA1111_SKCR);
 
 	/*
 	 * Wait lock time.  SA1111 manual _doesn't_
@@ -634,7 +668,7 @@ static void sa1111_wake(struct sa1111 *sachip)
 	 * Enable RCLK.  We also ensure that RDYEN is set.
 	 */
 	r |= SKCR_RCLKEN | SKCR_RDYEN;
-	sa1111_writel(r, sachip->base + SA1111_SKCR);
+	writel_relaxed(r, sachip->base + SA1111_SKCR);
 
 	/*
 	 * Wait 14 RCLK cycles for the chip to finish coming out
@@ -645,7 +679,7 @@ static void sa1111_wake(struct sa1111 *sachip)
 	/*
 	 * Ensure all clocks are initially off.
 	 */
-	sa1111_writel(0, sachip->base + SA1111_SKPCR);
+	writel_relaxed(0, sachip->base + SA1111_SKPCR);
 
 	spin_unlock_irqrestore(&sachip->lock, flags);
 }
@@ -675,7 +709,7 @@ sa1111_configure_smc(struct sa1111 *sachip, int sdram, unsigned int drac,
 	if (cas_latency == 3)
 		smcr |= SMCR_CLAT;
 
-	sa1111_writel(smcr, sachip->base + SA1111_SMCR);
+	writel_relaxed(smcr, sachip->base + SA1111_SMCR);
 
 	/*
 	 * Now clear the bits in the DMA mask to work around the SA1111
@@ -723,8 +757,8 @@ sa1111_init_one_child(struct sa1111 *sachip, struct resource *parent,
 	dev->mapbase     = sachip->base + info->offset;
 	dev->skpcr_mask  = info->skpcr_mask;
 
-	for (i = 0; i < ARRAY_SIZE(info->irq); i++)
-		dev->irq[i] = sachip->irq_base + info->irq[i];
+	for (i = 0; i < ARRAY_SIZE(info->hwirq); i++)
+		dev->hwirq[i] = info->hwirq[i];
 
 	/*
 	 * If the parent device has a DMA mask associated with it, and
@@ -814,7 +848,7 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq)
 	/*
 	 * Probe for the chip.  Only touch the SBI registers.
 	 */
-	id = sa1111_readl(sachip->base + SA1111_SKID);
+	id = readl_relaxed(sachip->base + SA1111_SKID);
 	if ((id & SKID_ID_MASK) != SKID_SA1111_ID) {
 		printk(KERN_DEBUG "SA1111 not detected: ID = %08lx\n", id);
 		ret = -ENODEV;
@@ -833,11 +867,9 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq)
 	 * The interrupt controller must be initialised before any
 	 * other device to ensure that the interrupts are available.
 	 */
-	if (sachip->irq != NO_IRQ) {
-		ret = sa1111_setup_irq(sachip, pd->irq_base);
-		if (ret)
-			goto err_clk;
-	}
+	ret = sa1111_setup_irq(sachip, pd->irq_base);
+	if (ret)
+		goto err_clk;
 
 	/* Setup the GPIOs - should really be done after the IRQ setup */
 	ret = sa1111_setup_gpios(sachip);
@@ -864,8 +896,8 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq)
 	 * DMA.  It can otherwise be held firmly in the off position.
 	 * (currently, we always enable it.)
 	 */
-	val = sa1111_readl(sachip->base + SA1111_SKPCR);
-	sa1111_writel(val | SKPCR_DCLKEN, sachip->base + SA1111_SKPCR);
+	val = readl_relaxed(sachip->base + SA1111_SKPCR);
+	writel_relaxed(val | SKPCR_DCLKEN, sachip->base + SA1111_SKPCR);
 
 	/*
 	 * Enable the SA1110 memory bus request and grant signals.
@@ -962,31 +994,31 @@ static int sa1111_suspend_noirq(struct device *dev)
 	 * Save state.
 	 */
 	base = sachip->base;
-	save->skcr     = sa1111_readl(base + SA1111_SKCR);
-	save->skpcr    = sa1111_readl(base + SA1111_SKPCR);
-	save->skcdr    = sa1111_readl(base + SA1111_SKCDR);
-	save->skaud    = sa1111_readl(base + SA1111_SKAUD);
-	save->skpwm0   = sa1111_readl(base + SA1111_SKPWM0);
-	save->skpwm1   = sa1111_readl(base + SA1111_SKPWM1);
+	save->skcr     = readl_relaxed(base + SA1111_SKCR);
+	save->skpcr    = readl_relaxed(base + SA1111_SKPCR);
+	save->skcdr    = readl_relaxed(base + SA1111_SKCDR);
+	save->skaud    = readl_relaxed(base + SA1111_SKAUD);
+	save->skpwm0   = readl_relaxed(base + SA1111_SKPWM0);
+	save->skpwm1   = readl_relaxed(base + SA1111_SKPWM1);
 
-	sa1111_writel(0, sachip->base + SA1111_SKPWM0);
-	sa1111_writel(0, sachip->base + SA1111_SKPWM1);
+	writel_relaxed(0, sachip->base + SA1111_SKPWM0);
+	writel_relaxed(0, sachip->base + SA1111_SKPWM1);
 
 	base = sachip->base + SA1111_INTC;
-	save->intpol0  = sa1111_readl(base + SA1111_INTPOL0);
-	save->intpol1  = sa1111_readl(base + SA1111_INTPOL1);
-	save->inten0   = sa1111_readl(base + SA1111_INTEN0);
-	save->inten1   = sa1111_readl(base + SA1111_INTEN1);
-	save->wakepol0 = sa1111_readl(base + SA1111_WAKEPOL0);
-	save->wakepol1 = sa1111_readl(base + SA1111_WAKEPOL1);
-	save->wakeen0  = sa1111_readl(base + SA1111_WAKEEN0);
-	save->wakeen1  = sa1111_readl(base + SA1111_WAKEEN1);
+	save->intpol0  = readl_relaxed(base + SA1111_INTPOL0);
+	save->intpol1  = readl_relaxed(base + SA1111_INTPOL1);
+	save->inten0   = readl_relaxed(base + SA1111_INTEN0);
+	save->inten1   = readl_relaxed(base + SA1111_INTEN1);
+	save->wakepol0 = readl_relaxed(base + SA1111_WAKEPOL0);
+	save->wakepol1 = readl_relaxed(base + SA1111_WAKEPOL1);
+	save->wakeen0  = readl_relaxed(base + SA1111_WAKEEN0);
+	save->wakeen1  = readl_relaxed(base + SA1111_WAKEEN1);
 
 	/*
 	 * Disable.
 	 */
-	val = sa1111_readl(sachip->base + SA1111_SKCR);
-	sa1111_writel(val | SKCR_SLEEP, sachip->base + SA1111_SKCR);
+	val = readl_relaxed(sachip->base + SA1111_SKCR);
+	writel_relaxed(val | SKCR_SLEEP, sachip->base + SA1111_SKCR);
 
 	clk_disable(sachip->clk);
 
@@ -1023,7 +1055,7 @@ static int sa1111_resume_noirq(struct device *dev)
 	 * Ensure that the SA1111 is still here.
 	 * FIXME: shouldn't do this here.
 	 */
-	id = sa1111_readl(sachip->base + SA1111_SKID);
+	id = readl_relaxed(sachip->base + SA1111_SKID);
 	if ((id & SKID_ID_MASK) != SKID_SA1111_ID) {
 		__sa1111_remove(sachip);
 		dev_set_drvdata(dev, NULL);
@@ -1047,26 +1079,26 @@ static int sa1111_resume_noirq(struct device *dev)
 	 */
 	spin_lock_irqsave(&sachip->lock, flags);
 
-	sa1111_writel(0, sachip->base + SA1111_INTC + SA1111_INTEN0);
-	sa1111_writel(0, sachip->base + SA1111_INTC + SA1111_INTEN1);
+	writel_relaxed(0, sachip->base + SA1111_INTC + SA1111_INTEN0);
+	writel_relaxed(0, sachip->base + SA1111_INTC + SA1111_INTEN1);
 
 	base = sachip->base;
-	sa1111_writel(save->skcr,     base + SA1111_SKCR);
-	sa1111_writel(save->skpcr,    base + SA1111_SKPCR);
-	sa1111_writel(save->skcdr,    base + SA1111_SKCDR);
-	sa1111_writel(save->skaud,    base + SA1111_SKAUD);
-	sa1111_writel(save->skpwm0,   base + SA1111_SKPWM0);
-	sa1111_writel(save->skpwm1,   base + SA1111_SKPWM1);
+	writel_relaxed(save->skcr,     base + SA1111_SKCR);
+	writel_relaxed(save->skpcr,    base + SA1111_SKPCR);
+	writel_relaxed(save->skcdr,    base + SA1111_SKCDR);
+	writel_relaxed(save->skaud,    base + SA1111_SKAUD);
+	writel_relaxed(save->skpwm0,   base + SA1111_SKPWM0);
+	writel_relaxed(save->skpwm1,   base + SA1111_SKPWM1);
 
 	base = sachip->base + SA1111_INTC;
-	sa1111_writel(save->intpol0,  base + SA1111_INTPOL0);
-	sa1111_writel(save->intpol1,  base + SA1111_INTPOL1);
-	sa1111_writel(save->inten0,   base + SA1111_INTEN0);
-	sa1111_writel(save->inten1,   base + SA1111_INTEN1);
-	sa1111_writel(save->wakepol0, base + SA1111_WAKEPOL0);
-	sa1111_writel(save->wakepol1, base + SA1111_WAKEPOL1);
-	sa1111_writel(save->wakeen0,  base + SA1111_WAKEEN0);
-	sa1111_writel(save->wakeen1,  base + SA1111_WAKEEN1);
+	writel_relaxed(save->intpol0,  base + SA1111_INTPOL0);
+	writel_relaxed(save->intpol1,  base + SA1111_INTPOL1);
+	writel_relaxed(save->inten0,   base + SA1111_INTEN0);
+	writel_relaxed(save->inten1,   base + SA1111_INTEN1);
+	writel_relaxed(save->wakepol0, base + SA1111_WAKEPOL0);
+	writel_relaxed(save->wakepol1, base + SA1111_WAKEPOL1);
+	writel_relaxed(save->wakeen0,  base + SA1111_WAKEEN0);
+	writel_relaxed(save->wakeen1,  base + SA1111_WAKEEN1);
 
 	spin_unlock_irqrestore(&sachip->lock, flags);
 
@@ -1153,7 +1185,7 @@ static unsigned int __sa1111_pll_clock(struct sa1111 *sachip)
 {
 	unsigned int skcdr, fbdiv, ipdiv, opdiv;
 
-	skcdr = sa1111_readl(sachip->base + SA1111_SKCDR);
+	skcdr = readl_relaxed(sachip->base + SA1111_SKCDR);
 
 	fbdiv = (skcdr & 0x007f) + 2;
 	ipdiv = ((skcdr & 0x0f80) >> 7) + 2;
@@ -1195,13 +1227,13 @@ void sa1111_select_audio_mode(struct sa1111_dev *sadev, int mode)
 
 	spin_lock_irqsave(&sachip->lock, flags);
 
-	val = sa1111_readl(sachip->base + SA1111_SKCR);
+	val = readl_relaxed(sachip->base + SA1111_SKCR);
 	if (mode == SA1111_AUDIO_I2S) {
 		val &= ~SKCR_SELAC;
 	} else {
 		val |= SKCR_SELAC;
 	}
-	sa1111_writel(val, sachip->base + SA1111_SKCR);
+	writel_relaxed(val, sachip->base + SA1111_SKCR);
 
 	spin_unlock_irqrestore(&sachip->lock, flags);
 }
@@ -1226,7 +1258,7 @@ int sa1111_set_audio_rate(struct sa1111_dev *sadev, int rate)
 	if (div > 128)
 		div = 128;
 
-	sa1111_writel(div - 1, sachip->base + SA1111_SKAUD);
+	writel_relaxed(div - 1, sachip->base + SA1111_SKAUD);
 
 	return 0;
 }
@@ -1244,7 +1276,7 @@ int sa1111_get_audio_rate(struct sa1111_dev *sadev)
 	if (sadev->devid != SA1111_DEVID_SAC)
 		return -EINVAL;
 
-	div = sa1111_readl(sachip->base + SA1111_SKAUD) + 1;
+	div = readl_relaxed(sachip->base + SA1111_SKAUD) + 1;
 
 	return __sa1111_pll_clock(sachip) / (256 * div);
 }
@@ -1261,10 +1293,10 @@ void sa1111_set_io_dir(struct sa1111_dev *sadev,
 
 #define MODIFY_BITS(port, mask, dir)		\
 	if (mask) {				\
-		val = sa1111_readl(port);	\
+		val = readl_relaxed(port);	\
 		val &= ~(mask);			\
 		val |= (dir) & (mask);		\
-		sa1111_writel(val, port);	\
+		writel_relaxed(val, port);	\
 	}
 
 	spin_lock_irqsave(&sachip->lock, flags);
@@ -1329,8 +1361,8 @@ int sa1111_enable_device(struct sa1111_dev *sadev)
 
 	if (ret == 0) {
 		spin_lock_irqsave(&sachip->lock, flags);
-		val = sa1111_readl(sachip->base + SA1111_SKPCR);
-		sa1111_writel(val | sadev->skpcr_mask, sachip->base + SA1111_SKPCR);
+		val = readl_relaxed(sachip->base + SA1111_SKPCR);
+		writel_relaxed(val | sadev->skpcr_mask, sachip->base + SA1111_SKPCR);
 		spin_unlock_irqrestore(&sachip->lock, flags);
 	}
 	return ret;
@@ -1348,8 +1380,8 @@ void sa1111_disable_device(struct sa1111_dev *sadev)
 	unsigned int val;
 
 	spin_lock_irqsave(&sachip->lock, flags);
-	val = sa1111_readl(sachip->base + SA1111_SKPCR);
-	sa1111_writel(val & ~sadev->skpcr_mask, sachip->base + SA1111_SKPCR);
+	val = readl_relaxed(sachip->base + SA1111_SKPCR);
+	writel_relaxed(val & ~sadev->skpcr_mask, sachip->base + SA1111_SKPCR);
 	spin_unlock_irqrestore(&sachip->lock, flags);
 
 	if (sachip->pdata && sachip->pdata->disable)
@@ -1359,9 +1391,10 @@ EXPORT_SYMBOL(sa1111_disable_device);
 
 int sa1111_get_irq(struct sa1111_dev *sadev, unsigned num)
 {
-	if (num >= ARRAY_SIZE(sadev->irq))
+	struct sa1111 *sachip = sa1111_chip_driver(sadev);
+	if (num >= ARRAY_SIZE(sadev->hwirq))
 		return -EINVAL;
-	return sadev->irq[num];
+	return sa1111_map_irq(sachip, sadev->hwirq[num]);
 }
 EXPORT_SYMBOL_GPL(sa1111_get_irq);
 
@@ -1379,36 +1412,6 @@ static int sa1111_match(struct device *_dev, struct device_driver *_drv)
 	return !!(dev->devid & drv->devid);
 }
 
-static int sa1111_bus_suspend(struct device *dev, pm_message_t state)
-{
-	struct sa1111_dev *sadev = to_sa1111_device(dev);
-	struct sa1111_driver *drv = SA1111_DRV(dev->driver);
-	int ret = 0;
-
-	if (drv && drv->suspend)
-		ret = drv->suspend(sadev, state);
-	return ret;
-}
-
-static int sa1111_bus_resume(struct device *dev)
-{
-	struct sa1111_dev *sadev = to_sa1111_device(dev);
-	struct sa1111_driver *drv = SA1111_DRV(dev->driver);
-	int ret = 0;
-
-	if (drv && drv->resume)
-		ret = drv->resume(sadev);
-	return ret;
-}
-
-static void sa1111_bus_shutdown(struct device *dev)
-{
-	struct sa1111_driver *drv = SA1111_DRV(dev->driver);
-
-	if (drv && drv->shutdown)
-		drv->shutdown(to_sa1111_device(dev));
-}
-
 static int sa1111_bus_probe(struct device *dev)
 {
 	struct sa1111_dev *sadev = to_sa1111_device(dev);
@@ -1436,9 +1439,6 @@ struct bus_type sa1111_bus_type = {
 	.match		= sa1111_match,
 	.probe		= sa1111_bus_probe,
 	.remove		= sa1111_bus_remove,
-	.suspend	= sa1111_bus_suspend,
-	.resume		= sa1111_bus_resume,
-	.shutdown	= sa1111_bus_shutdown,
 };
 EXPORT_SYMBOL(sa1111_bus_type);
 
diff --git a/arch/arm/configs/aspeed_g4_defconfig b/arch/arm/configs/aspeed_g4_defconfig
index d23b9d56a88b..95946dee9c77 100644
--- a/arch/arm/configs/aspeed_g4_defconfig
+++ b/arch/arm/configs/aspeed_g4_defconfig
@@ -1,7 +1,6 @@
 CONFIG_KERNEL_XZ=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_LOG_BUF_SHIFT=14
diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig
index c0ad7b82086b..8c7ea033cdc2 100644
--- a/arch/arm/configs/aspeed_g5_defconfig
+++ b/arch/arm/configs/aspeed_g5_defconfig
@@ -1,7 +1,6 @@
 CONFIG_KERNEL_XZ=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_LOG_BUF_SHIFT=14
diff --git a/arch/arm/configs/cns3420vb_defconfig b/arch/arm/configs/cns3420vb_defconfig
index 63a953d855a6..c6dcd6e4f4e6 100644
--- a/arch/arm/configs/cns3420vb_defconfig
+++ b/arch/arm/configs/cns3420vb_defconfig
@@ -28,7 +28,6 @@ CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="console=ttyS0,38400 mem=128M root=/dev/mmcblk0p1 ro rootwait"
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index bd0cf22f9ceb..026154c1d55a 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -94,6 +94,7 @@ CONFIG_PPP=m
 CONFIG_PPP_DEFLATE=m
 CONFIG_PPP_ASYNC=m
 CONFIG_PPP_SYNC_TTY=m
+CONFIG_USB_USBNET=m
 CONFIG_INPUT_EVDEV=m
 CONFIG_INPUT_EVBUG=m
 CONFIG_KEYBOARD_ATKBD=m
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index f1d7834990ec..629189c62fd1 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -3,6 +3,7 @@ CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_CGROUPS=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_PERF_EVENTS=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_PARTITION_ADVANCED=y
@@ -179,6 +180,7 @@ CONFIG_REGULATOR_TPS65090=y
 CONFIG_REGULATOR_WM8994=y
 CONFIG_MEDIA_SUPPORT=m
 CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_MEDIA_CEC_SUPPORT=y
 CONFIG_MEDIA_CONTROLLER=y
 CONFIG_VIDEO_V4L2_SUBDEV_API=y
 CONFIG_MEDIA_USB_SUPPORT=y
@@ -195,6 +197,8 @@ CONFIG_VIDEO_SAMSUNG_S5P_MFC=m
 CONFIG_VIDEO_SAMSUNG_EXYNOS_GSC=m
 CONFIG_V4L_TEST_DRIVERS=y
 CONFIG_VIDEO_VIVID=m
+CONFIG_CEC_PLATFORM_DRIVERS=y
+CONFIG_VIDEO_SAMSUNG_S5P_CEC=m
 CONFIG_DRM=y
 CONFIG_DRM_EXYNOS=y
 CONFIG_DRM_EXYNOS_FIMD=y
@@ -207,6 +211,7 @@ CONFIG_DRM_PANEL_SAMSUNG_LD9040=y
 CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0=y
 CONFIG_DRM_NXP_PTN3460=y
 CONFIG_DRM_PARADE_PS8622=y
+CONFIG_DRM_SII9234=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_PLATFORM=y
 CONFIG_BACKLIGHT_PWM=y
@@ -218,6 +223,7 @@ CONFIG_SND_SOC_SAMSUNG=y
 CONFIG_SND_SOC_SAMSUNG_SMDK_WM8994=y
 CONFIG_SND_SOC_SMDK_WM8994_PCM=y
 CONFIG_SND_SOC_SNOW=y
+CONFIG_SND_SOC_ODROID=y
 CONFIG_SND_SIMPLE_CARD=y
 CONFIG_USB=y
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
@@ -281,6 +287,7 @@ CONFIG_DEVFREQ_GOV_POWERSAVE=y
 CONFIG_DEVFREQ_GOV_USERSPACE=y
 CONFIG_ARM_EXYNOS_BUS_DEVFREQ=y
 CONFIG_DEVFREQ_EVENT_EXYNOS_NOCP=y
+CONFIG_EXYNOS_IOMMU=y
 CONFIG_EXTCON=y
 CONFIG_EXTCON_MAX14577=y
 CONFIG_EXTCON_MAX77693=y
diff --git a/arch/arm/configs/hisi_defconfig b/arch/arm/configs/hisi_defconfig
index b2e340b272ee..74d611e41e02 100644
--- a/arch/arm/configs/hisi_defconfig
+++ b/arch/arm/configs/hisi_defconfig
@@ -1,4 +1,3 @@
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BLK_DEV_INITRD=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 0d4494922561..4cb9829fccd1 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -55,6 +55,7 @@ CONFIG_FORCE_MAX_ZONEORDER=14
 CONFIG_CMDLINE="noinitrd console=ttymxc0,115200"
 CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
@@ -80,6 +81,7 @@ CONFIG_CAN=y
 CONFIG_CAN_FLEXCAN=y
 CONFIG_BT=y
 CONFIG_BT_HCIUART=y
+CONFIG_BT_HCIUART_SERDEV=y
 CONFIG_BT_HCIUART_H4=y
 CONFIG_BT_HCIUART_LL=y
 CONFIG_CFG80211=y
@@ -155,6 +157,7 @@ CONFIG_USB_USBNET=y
 CONFIG_USB_NET_CDC_EEM=m
 CONFIG_BRCMFMAC=m
 CONFIG_WL12XX=m
+CONFIG_WL18XX=m
 CONFIG_WLCORE_SDIO=m
 # CONFIG_WILINK_PLATFORM_DATA is not set
 CONFIG_INPUT_EVDEV=y
@@ -185,6 +188,8 @@ CONFIG_SERIAL_IMX=y
 CONFIG_SERIAL_IMX_CONSOLE=y
 CONFIG_SERIAL_FSL_LPUART=y
 CONFIG_SERIAL_FSL_LPUART_CONSOLE=y
+CONFIG_SERIAL_DEV_BUS=y
+CONFIG_SERIAL_DEV_CTRL_TTYPORT=y
 # CONFIG_I2C_COMPAT is not set
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MUX=y
@@ -248,6 +253,7 @@ CONFIG_VIDEO_OV5640=m
 CONFIG_SOC_CAMERA_OV2640=y
 CONFIG_IMX_IPUV3_CORE=y
 CONFIG_DRM=y
+CONFIG_DRM_PANEL_LVDS=y
 CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_DRM_DW_HDMI_AHB_AUDIO=m
 CONFIG_DRM_DW_HDMI_CEC=y
@@ -340,6 +346,7 @@ CONFIG_LEDS_TRIGGER_ONESHOT=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_BACKLIGHT=y
 CONFIG_LEDS_TRIGGER_GPIO=y
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_INTF_DEV_UIE_EMUL=y
 CONFIG_RTC_DRV_DS1307=y
@@ -349,6 +356,7 @@ CONFIG_RTC_DRV_PCF8563=y
 CONFIG_RTC_DRV_M41T80=y
 CONFIG_RTC_DRV_MC13XXX=y
 CONFIG_RTC_DRV_MXC=y
+CONFIG_RTC_DRV_MXC_V2=y
 CONFIG_RTC_DRV_SNVS=y
 CONFIG_DMADEVICES=y
 CONFIG_FSL_EDMA=y
diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig
index f710c192b33a..2536c231eea1 100644
--- a/arch/arm/configs/keystone_defconfig
+++ b/arch/arm/configs/keystone_defconfig
@@ -228,3 +228,10 @@ CONFIG_CRYPTO_DES=y
 CONFIG_CRYPTO_ANSI_CPRNG=y
 CONFIG_CRYPTO_USER_API_HASH=y
 CONFIG_CRYPTO_USER_API_SKCIPHER=y
+CONFIG_SPI_CADENCE_QUADSPI=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_EVDEV=m
+CONFIG_INPUT_GPIO_DECODER=m
+CONFIG_GPIO_PCA953X=m
+CONFIG_LEDS_TRIGGER_ACTIVITY=y
+CONFIG_LEDS_TRIGGER_CPU=y
diff --git a/arch/arm/configs/magician_defconfig b/arch/arm/configs/magician_defconfig
index ec5674c229a3..de5be2fc7306 100644
--- a/arch/arm/configs/magician_defconfig
+++ b/arch/arm/configs/magician_defconfig
@@ -54,7 +54,6 @@ CONFIG_BT_BNEP_PROTO_FILTER=y
 CONFIG_BT_HIDP=m
 CONFIG_BT_HCIBTUSB=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/arm/configs/mini2440_defconfig b/arch/arm/configs/mini2440_defconfig
index cf7dcb2c86e6..88ea02e7ba19 100644
--- a/arch/arm/configs/mini2440_defconfig
+++ b/arch/arm/configs/mini2440_defconfig
@@ -77,7 +77,6 @@ CONFIG_MAC80211=m
 CONFIG_MAC80211_MESH=y
 CONFIG_MAC80211_LEDS=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_CONNECTOR=m
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 61509c4b769f..da7387689b88 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -1,6 +1,5 @@
 CONFIG_SYSVIPC=y
 CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_CGROUPS=y
@@ -116,6 +115,8 @@ CONFIG_ARCH_ZYNQ=y
 CONFIG_TRUSTED_FOUNDATIONS=y
 CONFIG_PCI=y
 CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCI_DRA7XX=y
+CONFIG_PCI_DRA7XX_EP=y
 CONFIG_PCI_KEYSTONE=y
 CONFIG_PCI_MSI=y
 CONFIG_PCI_MVEBU=y
@@ -123,6 +124,9 @@ CONFIG_PCI_TEGRA=y
 CONFIG_PCI_RCAR_GEN2=y
 CONFIG_PCIE_RCAR=y
 CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_ENDPOINT=y
+CONFIG_PCI_ENDPOINT_CONFIGFS=y
+CONFIG_PCI_EPF_TEST=m
 CONFIG_SMP=y
 CONFIG_NR_CPUS=16
 CONFIG_HIGHPTE=y
@@ -222,6 +226,7 @@ CONFIG_ATMEL_SSC=m
 CONFIG_QCOM_COINCELL=m
 CONFIG_APDS9802ALS=y
 CONFIG_ISL29003=y
+CONFIG_PCI_ENDPOINT_TEST=m
 CONFIG_EEPROM_AT24=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BLK_DEV_SR=y
@@ -557,6 +562,7 @@ CONFIG_REGULATOR_VEXPRESS=y
 CONFIG_REGULATOR_WM8994=m
 CONFIG_MEDIA_SUPPORT=m
 CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_MEDIA_CEC_SUPPORT=y
 CONFIG_MEDIA_CONTROLLER=y
 CONFIG_VIDEO_V4L2_SUBDEV_API=y
 CONFIG_MEDIA_USB_SUPPORT=y
@@ -582,6 +588,8 @@ CONFIG_VIDEO_STI_DELTA=m
 CONFIG_VIDEO_RENESAS_JPU=m
 CONFIG_VIDEO_RENESAS_VSP1=m
 CONFIG_V4L_TEST_DRIVERS=y
+CONFIG_CEC_PLATFORM_DRIVERS=y
+CONFIG_VIDEO_SAMSUNG_S5P_CEC=m
 # CONFIG_MEDIA_SUBDRV_AUTOSELECT is not set
 CONFIG_VIDEO_ADV7180=m
 CONFIG_VIDEO_ML86V7667=m
@@ -613,6 +621,7 @@ CONFIG_DRM_TEGRA=y
 CONFIG_DRM_PANEL_SAMSUNG_LD9040=m
 CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0=m
 CONFIG_DRM_PANEL_SIMPLE=y
+CONFIG_DRM_SII9234=m
 CONFIG_DRM_STI=m
 CONFIG_DRM_VC4=y
 CONFIG_FB_ARMCLCD=y
@@ -651,6 +660,7 @@ CONFIG_SND_SOC_SAMSUNG=m
 CONFIG_SND_SOC_SAMSUNG_SMDK_WM8994=m
 CONFIG_SND_SOC_SMDK_WM8994_PCM=m
 CONFIG_SND_SOC_SNOW=m
+CONFIG_SND_SOC_ODROID=m
 CONFIG_SND_SOC_SH4_FSI=m
 CONFIG_SND_SOC_RCAR=m
 CONFIG_SND_SIMPLE_SCU_CARD=m
@@ -879,6 +889,7 @@ CONFIG_PWM_ATMEL=m
 CONFIG_PWM_ATMEL_HLCDC_PWM=m
 CONFIG_PWM_ATMEL_TCB=m
 CONFIG_PWM_FSL_FTM=m
+CONFIG_PWM_RCAR=m
 CONFIG_PWM_RENESAS_TPU=y
 CONFIG_PWM_ROCKCHIP=m
 CONFIG_PWM_SAMSUNG=m
diff --git a/arch/arm/configs/mv78xx0_defconfig b/arch/arm/configs/mv78xx0_defconfig
index 752e2e74de5b..0448bd8075ac 100644
--- a/arch/arm/configs/mv78xx0_defconfig
+++ b/arch/arm/configs/mv78xx0_defconfig
@@ -37,7 +37,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_IPV6 is not set
 CONFIG_NET_PKTGEN=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/arm/configs/mvebu_v7_defconfig b/arch/arm/configs/mvebu_v7_defconfig
index 69553704f2dc..ddaeda4f2e82 100644
--- a/arch/arm/configs/mvebu_v7_defconfig
+++ b/arch/arm/configs/mvebu_v7_defconfig
@@ -1,6 +1,5 @@
 CONFIG_SYSVIPC=y
 CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
@@ -57,7 +56,7 @@ CONFIG_MTD_CFI_STAA=y
 CONFIG_MTD_PHYSMAP_OF=y
 CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_PXA3xx=y
+CONFIG_MTD_NAND_MARVELL=y
 CONFIG_MTD_SPI_NOR=y
 CONFIG_SRAM=y
 CONFIG_MTD_UBI=y
diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index e5822ab01b7d..bbfb6759447b 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -46,7 +46,6 @@ CONFIG_CAN_FLEXCAN=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 7b97200c1d64..2f145c4af93a 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -48,6 +48,13 @@ CONFIG_SOC_AM43XX=y
 CONFIG_SOC_DRA7XX=y
 CONFIG_ARM_THUMBEE=y
 CONFIG_ARM_ERRATA_411920=y
+CONFIG_PCI=y
+CONFIG_PCI_MSI=y
+CONFIG_PCI_DRA7XX=y
+CONFIG_PCI_DRA7XX_EP=y
+CONFIG_PCI_ENDPOINT=y
+CONFIG_PCI_ENDPOINT_CONFIGFS=y
+CONFIG_PCI_EPF_TEST=m
 CONFIG_SMP=y
 CONFIG_NR_CPUS=2
 CONFIG_CMA=y
@@ -137,6 +144,7 @@ CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=16384
 CONFIG_SENSORS_TSL2550=m
 CONFIG_SRAM=y
+CONFIG_PCI_ENDPOINT_TEST=m
 CONFIG_EEPROM_AT24=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_SCSI_SCAN_ASYNC=y
@@ -468,6 +476,7 @@ CONFIG_PWM_TIECAP=m
 CONFIG_PWM_TIEHRPWM=m
 CONFIG_PWM_TWL=m
 CONFIG_PWM_TWL_LED=m
+CONFIG_PHY_CPCAP_USB=m
 CONFIG_PHY_DM816X_USB=m
 CONFIG_OMAP_USB2=m
 CONFIG_TI_PIPE3=y
@@ -516,3 +525,13 @@ CONFIG_LIBCRC32C=y
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
 CONFIG_FONT_8x16=y
+CONFIG_KERNEL_MODE_NEON=y
+CONFIG_ARM_CRYPTO=y
+CONFIG_CRYPTO_SHA1_ARM=m
+CONFIG_CRYPTO_SHA1_ARM_NEON=m
+CONFIG_CRYPTO_SHA256_ARM=m
+CONFIG_CRYPTO_SHA512_ARM=m
+CONFIG_CRYPTO_AES_ARM=m
+CONFIG_CRYPTO_AES_ARM_BS=m
+CONFIG_CRYPTO_CHACHA20_NEON=m
+CONFIG_CRYPTO_GHASH_ARM_CE=m
diff --git a/arch/arm/configs/orion5x_defconfig b/arch/arm/configs/orion5x_defconfig
index b831baddae02..bf9046331f6e 100644
--- a/arch/arm/configs/orion5x_defconfig
+++ b/arch/arm/configs/orion5x_defconfig
@@ -60,7 +60,6 @@ CONFIG_IP_PNP_BOOTP=y
 CONFIG_NET_DSA=y
 CONFIG_NET_PKTGEN=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index 830e817a028a..837d0c9c8b0e 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BSD_PROCESS_ACCT=y
diff --git a/arch/arm/configs/qcom_defconfig b/arch/arm/configs/qcom_defconfig
index c784d04e2ab7..dd2a089f939f 100644
--- a/arch/arm/configs/qcom_defconfig
+++ b/arch/arm/configs/qcom_defconfig
@@ -136,7 +136,9 @@ CONFIG_REGULATOR_QCOM_RPM=y
 CONFIG_REGULATOR_QCOM_SMD_RPM=y
 CONFIG_REGULATOR_QCOM_SPMI=y
 CONFIG_MEDIA_SUPPORT=y
+CONFIG_DRM=y
 CONFIG_FB=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
@@ -200,6 +202,7 @@ CONFIG_MSM_LCC_8960=y
 CONFIG_MDM_LCC_9615=y
 CONFIG_MSM_MMCC_8960=y
 CONFIG_MSM_MMCC_8974=y
+CONFIG_MSM_IOMMU=y
 CONFIG_HWSPINLOCK=y
 CONFIG_HWSPINLOCK_QCOM=y
 CONFIG_REMOTEPROC=y
diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig
index 6529cb43e0fd..2080025556b5 100644
--- a/arch/arm/configs/sama5_defconfig
+++ b/arch/arm/configs/sama5_defconfig
@@ -2,7 +2,6 @@
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_LOG_BUF_SHIFT=14
diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig
index 7b4fc0143148..578434cfd1a0 100644
--- a/arch/arm/configs/shmobile_defconfig
+++ b/arch/arm/configs/shmobile_defconfig
@@ -173,6 +173,7 @@ CONFIG_SND_SOC=y
 CONFIG_SND_SOC_SH4_FSI=y
 CONFIG_SND_SOC_RCAR=y
 CONFIG_SND_SOC_AK4642=y
+CONFIG_SND_SOC_SGTL5000=y
 CONFIG_SND_SOC_WM8978=y
 CONFIG_SND_SIMPLE_SCU_CARD=y
 CONFIG_USB=y
@@ -207,6 +208,7 @@ CONFIG_STAGING_BOARD=y
 CONFIG_IIO=y
 CONFIG_AK8975=y
 CONFIG_PWM=y
+CONFIG_PWM_RCAR=y
 CONFIG_PWM_RENESAS_TPU=y
 CONFIG_GENERIC_PHY=y
 CONFIG_PHY_RCAR_GEN2=y
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 5caaf971fb50..df433abfcb02 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -10,6 +10,7 @@ CONFIG_SMP=y
 CONFIG_NR_CPUS=8
 CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
+CONFIG_CMA=y
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CPU_FREQ=y
@@ -33,6 +34,7 @@ CONFIG_CAN_SUN4I=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DMA_CMA=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_ATA=y
 CONFIG_AHCI_SUNXI=y
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index 6678f2929356..c7b99ebf5fcf 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -1,5 +1,4 @@
 CONFIG_SYSVIPC=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
@@ -76,7 +75,6 @@ CONFIG_RFKILL_INPUT=y
 CONFIG_RFKILL_GPIO=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=64
 CONFIG_TEGRA_GMI=y
diff --git a/arch/arm/configs/vf610m4_defconfig b/arch/arm/configs/vf610m4_defconfig
index b7ecb83a95b6..a89f035c3b01 100644
--- a/arch/arm/configs/vf610m4_defconfig
+++ b/arch/arm/configs/vf610m4_defconfig
@@ -23,7 +23,6 @@ CONFIG_BINFMT_SHARED_FLAT=y
 # CONFIG_UEVENT_HELPER is not set
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_ALLOW_DEV_COREDUMP is not set
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_COUNT=4
diff --git a/arch/arm/configs/vt8500_v6_v7_defconfig b/arch/arm/configs/vt8500_v6_v7_defconfig
index 1bfaa7bfc392..9b85326ba287 100644
--- a/arch/arm/configs/vt8500_v6_v7_defconfig
+++ b/arch/arm/configs/vt8500_v6_v7_defconfig
@@ -1,4 +1,3 @@
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BLK_DEV_INITRD=y
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index 18768f330449..07e31941dc67 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -181,9 +181,8 @@ static int cbc_init(struct crypto_tfm *tfm)
 	struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	ctx->enc_tfm = crypto_alloc_cipher("aes", 0, 0);
-	if (IS_ERR(ctx->enc_tfm))
-		return PTR_ERR(ctx->enc_tfm);
-	return 0;
+
+	return PTR_ERR_OR_ZERO(ctx->enc_tfm);
 }
 
 static void cbc_exit(struct crypto_tfm *tfm)
@@ -258,9 +257,8 @@ static int xts_init(struct crypto_tfm *tfm)
 	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	ctx->tweak_tfm = crypto_alloc_cipher("aes", 0, 0);
-	if (IS_ERR(ctx->tweak_tfm))
-		return PTR_ERR(ctx->tweak_tfm);
-	return 0;
+
+	return PTR_ERR_OR_ZERO(ctx->tweak_tfm);
 }
 
 static void xts_exit(struct crypto_tfm *tfm)
diff --git a/arch/arm/crypto/crc32-ce-glue.c b/arch/arm/crypto/crc32-ce-glue.c
index 1b0e0e86ee9c..96e62ec105d0 100644
--- a/arch/arm/crypto/crc32-ce-glue.c
+++ b/arch/arm/crypto/crc32-ce-glue.c
@@ -188,6 +188,7 @@ static struct shash_alg crc32_pmull_algs[] = { {
 	.base.cra_name		= "crc32",
 	.base.cra_driver_name	= "crc32-arm-ce",
 	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 	.base.cra_blocksize	= 1,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -203,6 +204,7 @@ static struct shash_alg crc32_pmull_algs[] = { {
 	.base.cra_name		= "crc32c",
 	.base.cra_driver_name	= "crc32c-arm-ce",
 	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 	.base.cra_blocksize	= 1,
 	.base.cra_module	= THIS_MODULE,
 } };
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 0f2c8a2a8131..873e3c189279 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -1,4 +1,3 @@
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += early_ioremap.h
 generic-y += emergency-restart.h
diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
new file mode 100644
index 000000000000..5b0a8a421894
--- /dev/null
+++ b/arch/arm/include/asm/dma-direct.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ASM_ARM_DMA_DIRECT_H
+#define ASM_ARM_DMA_DIRECT_H 1
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	unsigned int offset = paddr & ~PAGE_MASK;
+	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+{
+	unsigned int offset = dev_addr & ~PAGE_MASK;
+	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
+}
+
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	u64 limit, mask;
+
+	if (!dev->dma_mask)
+		return 0;
+
+	mask = *dev->dma_mask;
+
+	limit = (mask + 1) & ~mask;
+	if (limit && size > limit)
+		return 0;
+
+	if ((addr | (addr + size - 1)) & ~mask)
+		return 0;
+
+	return 1;
+}
+
+#endif /* ASM_ARM_DMA_DIRECT_H */
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index daf837423a76..8436f6ade57d 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -18,7 +18,7 @@ extern const struct dma_map_ops arm_coherent_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_noop_ops;
+	return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_direct_ops;
 }
 
 #ifdef __arch_page_to_dma
@@ -109,39 +109,6 @@ static inline bool is_device_dma_coherent(struct device *dev)
 	return dev->archdata.dma_coherent;
 }
 
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	unsigned int offset = paddr & ~PAGE_MASK;
-	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
-{
-	unsigned int offset = dev_addr & ~PAGE_MASK;
-	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
-}
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	u64 limit, mask;
-
-	if (!dev->dma_mask)
-		return 0;
-
-	mask = *dev->dma_mask;
-
-	limit = (mask + 1) & ~mask;
-	if (limit && size > limit)
-		return 0;
-
-	if ((addr | (addr + size - 1)) & ~mask)
-		return 0;
-
-	return 1;
-}
-
-static inline void dma_mark_clean(void *addr, size_t size) { }
-
 /**
  * arm_dma_alloc - allocate consistent memory for DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
diff --git a/arch/arm/include/asm/exception.h b/arch/arm/include/asm/exception.h
index a7273ad9587a..58e039a851af 100644
--- a/arch/arm/include/asm/exception.h
+++ b/arch/arm/include/asm/exception.h
@@ -10,11 +10,10 @@
 
 #include <linux/interrupt.h>
 
-#define __exception	__attribute__((section(".exception.text")))
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 #define __exception_irq_entry	__irq_entry
 #else
-#define __exception_irq_entry	__exception
+#define __exception_irq_entry
 #endif
 
 #endif /* __ASM_ARM_EXCEPTION_H */
diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
index 01c3d92624e5..8d1f498e5dd8 100644
--- a/arch/arm/include/asm/glue-cache.h
+++ b/arch/arm/include/asm/glue-cache.h
@@ -117,6 +117,10 @@
 # endif
 #endif
 
+#if defined(CONFIG_CACHE_B15_RAC)
+# define MULTI_CACHE 1
+#endif
+
 #if defined(CONFIG_CPU_V7M)
 #  define MULTI_CACHE 1
 #endif
diff --git a/arch/arm/include/asm/hardware/cache-b15-rac.h b/arch/arm/include/asm/hardware/cache-b15-rac.h
new file mode 100644
index 000000000000..3d43ec06fd35
--- /dev/null
+++ b/arch/arm/include/asm/hardware/cache-b15-rac.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_ARM_HARDWARE_CACHE_B15_RAC_H
+#define __ASM_ARM_HARDWARE_CACHE_B15_RAC_H
+
+#ifndef __ASSEMBLY__
+
+void b15_flush_kern_cache_all(void);
+
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/hardware/sa1111.h b/arch/arm/include/asm/hardware/sa1111.h
index 0bbf163d1ed3..798e520e8a49 100644
--- a/arch/arm/include/asm/hardware/sa1111.h
+++ b/arch/arm/include/asm/hardware/sa1111.h
@@ -16,33 +16,6 @@
 #include <mach/bitfield.h>
 
 /*
- * The SA1111 is always located at virtual 0xf4000000, and is always
- * "native" endian.
- */
-
-#define SA1111_VBASE		0xf4000000
-
-/* Don't use these! */
-#define SA1111_p2v( x )         ((x) - SA1111_BASE + SA1111_VBASE)
-#define SA1111_v2p( x )         ((x) - SA1111_VBASE + SA1111_BASE)
-
-#ifndef __ASSEMBLY__
-#define _SA1111(x)	((x) + sa1111->resource.start)
-#endif
-
-#define sa1111_writel(val,addr)	__raw_writel(val, addr)
-#define sa1111_readl(addr)	__raw_readl(addr)
-
-/*
- * 26 bits of the SA-1110 address bus are available to the SA-1111.
- * Use these when feeding target addresses to the DMA engines.
- */
-
-#define SA1111_ADDR_WIDTH	(26)
-#define SA1111_ADDR_MASK	((1<<SA1111_ADDR_WIDTH)-1)
-#define SA1111_DMA_ADDR(x)	((x)&SA1111_ADDR_MASK)
-
-/*
  * Don't ask the (SAC) DMA engines to move less than this amount.
  */
 
@@ -417,7 +390,7 @@ struct sa1111_dev {
 	struct resource	res;
 	void __iomem	*mapbase;
 	unsigned int	skpcr_mask;
-	unsigned int	irq[6];
+	unsigned int	hwirq[6];
 	u64		dma_mask;
 };
 
@@ -431,9 +404,6 @@ struct sa1111_driver {
 	unsigned int		devid;
 	int (*probe)(struct sa1111_dev *);
 	int (*remove)(struct sa1111_dev *);
-	int (*suspend)(struct sa1111_dev *, pm_message_t);
-	int (*resume)(struct sa1111_dev *);
-	void (*shutdown)(struct sa1111_dev *);
 };
 
 #define SA1111_DRV(_d)	container_of((_d), struct sa1111_driver, drv)
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index c8781450905b..3ab8b3781bfe 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -161,8 +161,7 @@
 #else
 #define VTTBR_X		(5 - KVM_T0SZ)
 #endif
-#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK  (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_X)
 #define VTTBR_VMID_SHIFT  _AC(48, ULL)
 #define VTTBR_VMID_MASK(size)	(_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 242151ea6908..acbf9ec7b396 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -238,6 +238,9 @@ int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		int exception_index);
 
+static inline void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				     int exception_index) {}
+
 static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 				       unsigned long hyp_stack_ptr,
 				       unsigned long vector_ptr)
@@ -285,6 +288,11 @@ static inline void kvm_arm_init_debug(void) {}
 static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {}
+static inline bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu,
+					     struct kvm_run *run)
+{
+	return false;
+}
 
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
@@ -296,4 +304,6 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 /* All host FP/SIMD state is restored on guest exit, so nothing to save: */
 static inline void kvm_fpsimd_flush_cpu_state(void) {}
 
+static inline void kvm_arm_vhe_guest_enter(void) {}
+static inline void kvm_arm_vhe_guest_exit(void) {}
 #endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index fa6f2174276b..a2d176a308bd 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -211,6 +211,11 @@ static inline bool __kvm_cpu_uses_extended_idmap(void)
 	return false;
 }
 
+static inline unsigned long __kvm_idmap_ptrs_per_pgd(void)
+{
+	return PTRS_PER_PGD;
+}
+
 static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
 				       pgd_t *hyp_pgd,
 				       pgd_t *merged_hyp_pgd,
@@ -221,6 +226,18 @@ static inline unsigned int kvm_get_vmid_bits(void)
 	return 8;
 }
 
+static inline void *kvm_get_hyp_vector(void)
+{
+	return kvm_ksym_ref(__kvm_hyp_vector);
+}
+
+static inline int kvm_map_vectors(void)
+{
+	return 0;
+}
+
+#define kvm_phys_to_vttbr(addr)		(addr)
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 1f54e4e98c1e..496667703693 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -88,6 +88,7 @@
 #else /* CONFIG_MMU */
 
 #ifndef __ASSEMBLY__
+extern unsigned long setup_vectors_base(void);
 extern unsigned long vectors_base;
 #define VECTORS_BASE		vectors_base
 #endif
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 2a029bceaf2f..2a4836087358 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -221,7 +221,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
 }
 #define	__HAVE_ARCH_PTE_SPECIAL
 
-#define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		(pmd_isclear((pmd), L_PMD_SECT_RDONLY))
 #define pmd_dirty(pmd)		(pmd_isset((pmd), L_PMD_SECT_DIRTY))
 #define pud_page(pud)		pmd_page(__pmd(pud_val(pud)))
@@ -250,6 +249,9 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 #define pfn_pmd(pfn,prot)	(__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
+/* No hardware dirty/accessed bits -- generic_pmdp_establish() fits */
+#define pmdp_establish generic_pmdp_establish
+
 /* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */
 static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 {
diff --git a/arch/arm/include/asm/ptdump.h b/arch/arm/include/asm/ptdump.h
new file mode 100644
index 000000000000..3ebf9718288d
--- /dev/null
+++ b/arch/arm/include/asm/ptdump.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2014 ARM Ltd. */
+#ifndef __ASM_PTDUMP_H
+#define __ASM_PTDUMP_H
+
+#ifdef CONFIG_ARM_PTDUMP_CORE
+
+#include <linux/mm_types.h>
+#include <linux/seq_file.h>
+
+struct addr_marker {
+	unsigned long start_address;
+	char *name;
+};
+
+struct ptdump_info {
+	struct mm_struct		*mm;
+	const struct addr_marker	*markers;
+	unsigned long			base_addr;
+};
+
+void ptdump_walk_pgd(struct seq_file *s, struct ptdump_info *info);
+#ifdef CONFIG_ARM_PTDUMP_DEBUGFS
+int ptdump_debugfs_register(struct ptdump_info *info, const char *name);
+#else
+static inline int ptdump_debugfs_register(struct ptdump_info *info,
+					const char *name)
+{
+	return 0;
+}
+#endif /* CONFIG_ARM_PTDUMP_DEBUGFS */
+
+void ptdump_check_wx(void);
+
+#endif /* CONFIG_ARM_PTDUMP_CORE */
+
+#ifdef CONFIG_DEBUG_WX
+#define debug_checkwx() ptdump_check_wx()
+#else
+#define debug_checkwx() do { } while (0)
+#endif
+
+#endif /* __ASM_PTDUMP_H */
diff --git a/arch/arm/include/asm/sections.h b/arch/arm/include/asm/sections.h
index 63dfe1f10335..4ceb4f757d4d 100644
--- a/arch/arm/include/asm/sections.h
+++ b/arch/arm/include/asm/sections.h
@@ -6,4 +6,25 @@
 
 extern char _exiprom[];
 
+extern char __idmap_text_start[];
+extern char __idmap_text_end[];
+extern char __entry_text_start[];
+extern char __entry_text_end[];
+extern char __hyp_idmap_text_start[];
+extern char __hyp_idmap_text_end[];
+
+static inline bool in_entry_text(unsigned long addr)
+{
+	return memory_contains(__entry_text_start, __entry_text_end,
+			       (void *)addr, 1);
+}
+
+static inline bool in_idmap_text(unsigned long addr)
+{
+	void *a = (void *)addr;
+	return memory_contains(__idmap_text_start, __idmap_text_end, a, 1) ||
+	       memory_contains(__hyp_idmap_text_start, __hyp_idmap_text_end,
+			       a, 1);
+}
+
 #endif	/* _ASM_ARM_SECTIONS_H */
diff --git a/arch/arm/include/asm/string.h b/arch/arm/include/asm/string.h
index f54a3136aac6..111a1d8a41dd 100644
--- a/arch/arm/include/asm/string.h
+++ b/arch/arm/include/asm/string.h
@@ -39,18 +39,4 @@ static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n)
 	return __memset64(p, v, n * 8, v >> 32);
 }
 
-extern void __memzero(void *ptr, __kernel_size_t n);
-
-#define memset(p,v,n)							\
-	({								\
-	 	void *__p = (p); size_t __n = n;			\
-		if ((__n) != 0) {					\
-			if (__builtin_constant_p((v)) && (v) == 0)	\
-				__memzero((__p),(__n));			\
-			else						\
-				memset((__p),(v),(__n));		\
-		}							\
-		(__p);							\
-	})
-
 #endif
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 776757d1604a..e71cc35de163 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -75,9 +75,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,					\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /*
  * how to get the current stack pointer in C
  */
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index f9a6c5fc3fd1..a00288d75ee6 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -28,18 +28,6 @@ static inline int __in_irqentry_text(unsigned long ptr)
 	       ptr < (unsigned long)&__irqentry_text_end;
 }
 
-static inline int in_exception_text(unsigned long ptr)
-{
-	extern char __exception_text_start[];
-	extern char __exception_text_end[];
-	int in;
-
-	in = ptr >= (unsigned long)&__exception_text_start &&
-	     ptr < (unsigned long)&__exception_text_end;
-
-	return in ? : __in_irqentry_text(ptr);
-}
-
 extern void __init early_trap_init(void *);
 extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
 extern void ptrace_break(struct task_struct *tsk, struct pt_regs *regs);
diff --git a/arch/arm/include/asm/unified.h b/arch/arm/include/asm/unified.h
index a91ae499614c..2c3b952be63e 100644
--- a/arch/arm/include/asm/unified.h
+++ b/arch/arm/include/asm/unified.h
@@ -20,8 +20,10 @@
 #ifndef __ASM_UNIFIED_H
 #define __ASM_UNIFIED_H
 
-#if defined(__ASSEMBLY__) && defined(CONFIG_ARM_ASM_UNIFIED)
+#if defined(__ASSEMBLY__)
 	.syntax unified
+#else
+__asm__(".syntax unified");
 #endif
 
 #ifdef CONFIG_CPU_V7M
@@ -64,77 +66,4 @@
 
 #endif	/* CONFIG_THUMB2_KERNEL */
 
-#ifndef CONFIG_ARM_ASM_UNIFIED
-
-/*
- * If the unified assembly syntax isn't used (in ARM mode), these
- * macros expand to an empty string
- */
-#ifdef __ASSEMBLY__
-	.macro	it, cond
-	.endm
-	.macro	itt, cond
-	.endm
-	.macro	ite, cond
-	.endm
-	.macro	ittt, cond
-	.endm
-	.macro	itte, cond
-	.endm
-	.macro	itet, cond
-	.endm
-	.macro	itee, cond
-	.endm
-	.macro	itttt, cond
-	.endm
-	.macro	ittte, cond
-	.endm
-	.macro	ittet, cond
-	.endm
-	.macro	ittee, cond
-	.endm
-	.macro	itett, cond
-	.endm
-	.macro	itete, cond
-	.endm
-	.macro	iteet, cond
-	.endm
-	.macro	iteee, cond
-	.endm
-#else	/* !__ASSEMBLY__ */
-__asm__(
-"	.macro	it, cond\n"
-"	.endm\n"
-"	.macro	itt, cond\n"
-"	.endm\n"
-"	.macro	ite, cond\n"
-"	.endm\n"
-"	.macro	ittt, cond\n"
-"	.endm\n"
-"	.macro	itte, cond\n"
-"	.endm\n"
-"	.macro	itet, cond\n"
-"	.endm\n"
-"	.macro	itee, cond\n"
-"	.endm\n"
-"	.macro	itttt, cond\n"
-"	.endm\n"
-"	.macro	ittte, cond\n"
-"	.endm\n"
-"	.macro	ittet, cond\n"
-"	.endm\n"
-"	.macro	ittee, cond\n"
-"	.endm\n"
-"	.macro	itett, cond\n"
-"	.endm\n"
-"	.macro	itete, cond\n"
-"	.endm\n"
-"	.macro	iteet, cond\n"
-"	.endm\n"
-"	.macro	iteee, cond\n"
-"	.endm\n");
-#endif	/* __ASSEMBLY__ */
-
-#endif	/* CONFIG_ARM_ASM_UNIFIED */
-
 #endif	/* !__ASM_UNIFIED_H */
diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild
index 4d53de308ee0..4d1cc1847edf 100644
--- a/arch/arm/include/uapi/asm/Kbuild
+++ b/arch/arm/include/uapi/asm/Kbuild
@@ -7,6 +7,7 @@ generated-y += unistd-oabi.h
 generated-y += unistd-eabi.h
 
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
diff --git a/arch/arm/include/uapi/asm/siginfo.h b/arch/arm/include/uapi/asm/siginfo.h
new file mode 100644
index 000000000000..d0513880be21
--- /dev/null
+++ b/arch/arm/include/uapi/asm/siginfo.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_SIGINFO_H
+#define __ASM_SIGINFO_H
+
+#include <asm-generic/siginfo.h>
+
+/*
+ * SIGFPE si_codes
+ */
+#ifdef __KERNEL__
+#define FPE_FIXME	0	/* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 5266fd9ad6b4..783fbb4de5f9 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -92,7 +92,6 @@ EXPORT_SYMBOL(__memset64);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memchr);
-EXPORT_SYMBOL(__memzero);
 
 EXPORT_SYMBOL(mmioset);
 EXPORT_SYMBOL(mmiocpy);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index fbc707626b3e..1752033b0070 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -82,11 +82,7 @@
 #endif
 	.endm
 
-#ifdef CONFIG_KPROBES
-	.section	.kprobes.text,"ax",%progbits
-#else
-	.text
-#endif
+	.section	.entry.text,"ax",%progbits
 
 /*
  * Invalid mode handlers
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index e655dcd0a933..3c4f88701f22 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -37,6 +37,7 @@ saved_pc	.req	lr
 #define TRACE(x...)
 #endif
 
+	.section .entry.text,"ax",%progbits
 	.align	5
 #if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING))
 /*
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 7f4d80c2db6b..0f07579af472 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -300,7 +300,7 @@
 	mov	r2, sp
 	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
-	tst	r1, #0xcf
+	tst	r1, #PSR_I_BIT | 0x0f
 	bne	1f
 	msr	spsr_cxsf, r1			@ save in spsr_svc
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
@@ -332,7 +332,7 @@
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [sp, #\offset + S_PC]	@ get pc
 	add	sp, sp, #\offset + S_SP
-	tst	r1, #0xcf
+	tst	r1, #PSR_I_BIT | 0x0f
 	bne	1f
 	msr	spsr_cxsf, r1			@ save in spsr_svc
 
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 21dde771a7dd..6e0375e7db05 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -105,8 +105,9 @@ __mmap_switched:
    ARM(	ldmia	r4!, {r0, r1, sp} )
  THUMB(	ldmia	r4!, {r0, r1, r3} )
  THUMB(	mov	sp, r3 )
-	sub	r1, r1, r0
-	bl	__memzero			@ clear .bss
+	sub	r2, r1, r0
+	mov	r1, #0
+	bl	memset				@ clear .bss
 
 	ldmia	r4, {r0, r1, r2, r3}
 	str	r9, [r0]			@ Save processor ID
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index af2a7f1e3103..629e25152c0d 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -44,17 +44,17 @@ static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
 static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[ARM_MAX_WRP]);
 
 /* Number of BRP/WRP registers on this CPU. */
-static int core_num_brps;
-static int core_num_wrps;
+static int core_num_brps __ro_after_init;
+static int core_num_wrps __ro_after_init;
 
 /* Debug architecture version. */
-static u8 debug_arch;
+static u8 debug_arch __ro_after_init;
 
 /* Does debug architecture support OS Save and Restore? */
-static bool has_ossr;
+static bool has_ossr __ro_after_init;
 
 /* Maximum supported watchpoint length. */
-static u8 max_watchpoint_len;
+static u8 max_watchpoint_len __ro_after_init;
 
 #define READ_WB_REG_CASE(OP2, M, VAL)			\
 	case ((OP2 << 4) + M):				\
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index d96714e1858c..1523cb18b109 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -21,7 +21,6 @@
 #include <linux/unistd.h>
 #include <linux/user.h>
 #include <linux/interrupt.h>
-#include <linux/kallsyms.h>
 #include <linux/init.h>
 #include <linux/elfcore.h>
 #include <linux/pm.h>
@@ -121,8 +120,8 @@ void __show_regs(struct pt_regs *regs)
 
 	show_regs_print_info(KERN_DEFAULT);
 
-	print_symbol("PC is at %s\n", instruction_pointer(regs));
-	print_symbol("LR is at %s\n", regs->ARM_lr);
+	printk("PC is at %pS\n", (void *)instruction_pointer(regs));
+	printk("LR is at %pS\n", (void *)regs->ARM_lr);
 	printk("pc : [<%08lx>]    lr : [<%08lx>]    psr: %08lx\n",
 	       regs->ARM_pc, regs->ARM_lr, regs->ARM_cpsr);
 	printk("sp : %08lx  ip : %08lx  fp : %08lx\n",
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 58e3771e4c5b..7724b0f661b3 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -390,7 +390,6 @@ static void ptrace_hbptriggered(struct perf_event *bp,
 	struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
 	long num;
 	int i;
-	siginfo_t info;
 
 	for (i = 0; i < ARM_MAX_HBP_SLOTS; ++i)
 		if (current->thread.debug.hbp[i] == bp)
@@ -398,12 +397,7 @@ static void ptrace_hbptriggered(struct perf_event *bp,
 
 	num = (i == ARM_MAX_HBP_SLOTS) ? 0 : ptrace_hbp_idx_to_num(i);
 
-	info.si_signo	= SIGTRAP;
-	info.si_errno	= (int)num;
-	info.si_code	= TRAP_HWBKPT;
-	info.si_addr	= (void __user *)(bkpt->trigger);
-
-	force_sig_info(SIGTRAP, &info, current);
+	force_sig_ptrace_errno_trap((int)num, (void __user *)(bkpt->trigger));
 }
 
 /*
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index b4fbf00ee4ad..2da087926ebe 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -379,6 +379,9 @@ asmlinkage void secondary_start_kernel(void)
 
 	cpu_init();
 
+#ifndef CONFIG_MMU
+	setup_vectors_base();
+#endif
 	pr_debug("CPU%u: Booted secondary processor\n", cpu);
 
 	preempt_disable();
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 65228bf4c6df..a56e7c856ab5 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -3,6 +3,7 @@
 #include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 
+#include <asm/sections.h>
 #include <asm/stacktrace.h>
 #include <asm/traps.h>
 
@@ -63,7 +64,6 @@ EXPORT_SYMBOL(walk_stackframe);
 #ifdef CONFIG_STACKTRACE
 struct stack_trace_data {
 	struct stack_trace *trace;
-	unsigned long last_pc;
 	unsigned int no_sched_functions;
 	unsigned int skip;
 };
@@ -87,16 +87,7 @@ static int save_trace(struct stackframe *frame, void *d)
 	if (trace->nr_entries >= trace->max_entries)
 		return 1;
 
-	/*
-	 * in_exception_text() is designed to test if the PC is one of
-	 * the functions which has an exception stack above it, but
-	 * unfortunately what is in frame->pc is the return LR value,
-	 * not the saved PC value.  So, we need to track the previous
-	 * frame PC value when doing this.
-	 */
-	addr = data->last_pc;
-	data->last_pc = frame->pc;
-	if (!in_exception_text(addr))
+	if (!in_entry_text(frame->pc))
 		return 0;
 
 	regs = (struct pt_regs *)frame->sp;
@@ -114,7 +105,6 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 	struct stackframe frame;
 
 	data.trace = trace;
-	data.last_pc = ULONG_MAX;
 	data.skip = trace->skip;
 	data.no_sched_functions = nosched;
 
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 5cf04888c581..5e3633c24e63 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -72,7 +72,7 @@ void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long
 	printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from);
 #endif
 
-	if (in_exception_text(where))
+	if (in_entry_text(from))
 		dump_mem("", "Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs));
 }
 
@@ -433,7 +433,7 @@ static int call_undef_hook(struct pt_regs *regs, unsigned int instr)
 	return fn ? fn(regs, instr) : 1;
 }
 
-asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
+asmlinkage void do_undefinstr(struct pt_regs *regs)
 {
 	unsigned int instr;
 	siginfo_t info;
@@ -793,7 +793,6 @@ void abort(void)
 	/* if that doesn't kill us, halt */
 	panic("Oops failed to kill thread");
 }
-EXPORT_SYMBOL(abort);
 
 void __init trap_init(void)
 {
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index ec4b3f94ad80..12b87591eb7c 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -96,9 +96,9 @@ SECTIONS
 	.text : {			/* Real text segment		*/
 		_stext = .;		/* Text and read-only data	*/
 			IDMAP_TEXT
-			__exception_text_start = .;
-			*(.exception.text)
-			__exception_text_end = .;
+			__entry_text_start = .;
+			*(.entry.text)
+			__entry_text_end = .;
 			IRQENTRY_TEXT
 			TEXT_TEXT
 			SCHED_TEXT
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index ee53f6518872..84a1ae3ce46e 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -105,9 +105,9 @@ SECTIONS
 	.text : {			/* Real text segment		*/
 		_stext = .;		/* Text and read-only data	*/
 			IDMAP_TEXT
-			__exception_text_start = .;
-			*(.exception.text)
-			__exception_text_end = .;
+			__entry_text_start = .;
+			*(.entry.text)
+			__entry_text_end = .;
 			IRQENTRY_TEXT
 			SOFTIRQENTRY_TEXT
 			TEXT_TEXT
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 4cb0b9624d8f..ad25fd1872c7 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -8,7 +8,7 @@
 lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 		   csumpartialcopy.o csumpartialcopyuser.o clearbit.o \
 		   delay.o delay-loop.o findbit.o memchr.o memcpy.o   \
-		   memmove.o memset.o memzero.o setbit.o              \
+		   memmove.o memset.o setbit.o                        \
 		   strchr.o strrchr.o                                 \
 		   testchangebit.o testclearbit.o testsetbit.o        \
 		   ashldi3.o ashrdi3.o lshrdi3.o muldi3.o             \
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 1712f132b80d..b83fdc06286a 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -85,7 +85,11 @@
 		.pushsection .text.fixup,"ax"
 		.align	4
 9001:		mov	r4, #-EFAULT
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		ldr	r5, [sp, #9*4]		@ *err_ptr
+#else
 		ldr	r5, [sp, #8*4]		@ *err_ptr
+#endif
 		str	r4, [r5]
 		ldmia	sp, {r1, r2}		@ retrieve dst, len
 		add	r2, r2, r1
diff --git a/arch/arm/lib/memzero.S b/arch/arm/lib/memzero.S
deleted file mode 100644
index 0eded952e089..000000000000
--- a/arch/arm/lib/memzero.S
+++ /dev/null
@@ -1,137 +0,0 @@
-/*
- *  linux/arch/arm/lib/memzero.S
- *
- *  Copyright (C) 1995-2000 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/unwind.h>
-
-	.text
-	.align	5
-	.word	0
-/*
- * Align the pointer in r0.  r3 contains the number of bytes that we are
- * mis-aligned by, and r1 is the number of bytes.  If r1 < 4, then we
- * don't bother; we use byte stores instead.
- */
-UNWIND(	.fnstart			)
-1:	subs	r1, r1, #4		@ 1 do we have enough
-	blt	5f			@ 1 bytes to align with?
-	cmp	r3, #2			@ 1
-	strltb	r2, [r0], #1		@ 1
-	strleb	r2, [r0], #1		@ 1
-	strb	r2, [r0], #1		@ 1
-	add	r1, r1, r3		@ 1 (r1 = r1 - (4 - r3))
-/*
- * The pointer is now aligned and the length is adjusted.  Try doing the
- * memzero again.
- */
-
-ENTRY(__memzero)
-	mov	r2, #0			@ 1
-	ands	r3, r0, #3		@ 1 unaligned?
-	bne	1b			@ 1
-/*
- * r3 = 0, and we know that the pointer in r0 is aligned to a word boundary.
- */
-	cmp	r1, #16			@ 1 we can skip this chunk if we
-	blt	4f			@ 1 have < 16 bytes
-
-#if ! CALGN(1)+0
-
-/*
- * We need an extra register for this loop - save the return address and
- * use the LR
- */
-	str	lr, [sp, #-4]!		@ 1
-UNWIND(	.fnend				)
-UNWIND(	.fnstart			)
-UNWIND(	.save 	{lr}			)
-	mov	ip, r2			@ 1
-	mov	lr, r2			@ 1
-
-3:	subs	r1, r1, #64		@ 1 write 32 bytes out per loop
-	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
-	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
-	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
-	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
-	bgt	3b			@ 1
-	ldmeqfd	sp!, {pc}		@ 1/2 quick exit
-/*
- * No need to correct the count; we're only testing bits from now on
- */
-	tst	r1, #32			@ 1
-	stmneia	r0!, {r2, r3, ip, lr}	@ 4
-	stmneia	r0!, {r2, r3, ip, lr}	@ 4
-	tst	r1, #16			@ 1 16 bytes or more?
-	stmneia	r0!, {r2, r3, ip, lr}	@ 4
-	ldr	lr, [sp], #4		@ 1
-UNWIND(	.fnend				)
-
-#else
-
-/*
- * This version aligns the destination pointer in order to write
- * whole cache lines at once.
- */
-
-	stmfd	sp!, {r4-r7, lr}
-UNWIND(	.fnend		       )
-UNWIND(	.fnstart	       )
-UNWIND(	.save 	{r4-r7, lr}    )
-	mov	r4, r2
-	mov	r5, r2
-	mov	r6, r2
-	mov	r7, r2
-	mov	ip, r2
-	mov	lr, r2
-
-	cmp	r1, #96
-	andgts	ip, r0, #31
-	ble	3f
-
-	rsb	ip, ip, #32
-	sub	r1, r1, ip
-	movs	ip, ip, lsl #(32 - 4)
-	stmcsia	r0!, {r4, r5, r6, r7}
-	stmmiia	r0!, {r4, r5}
-	movs	ip, ip, lsl #2
-	strcs	r2, [r0], #4
-
-3:	subs	r1, r1, #64
-	stmgeia	r0!, {r2-r7, ip, lr}
-	stmgeia	r0!, {r2-r7, ip, lr}
-	bgt	3b
-	ldmeqfd	sp!, {r4-r7, pc}
-
-	tst	r1, #32
-	stmneia	r0!, {r2-r7, ip, lr}
-	tst	r1, #16
-	stmneia	r0!, {r4-r7}
-	ldmfd	sp!, {r4-r7, lr}
-UNWIND(	.fnend		       )
-
-#endif
-
-UNWIND(	.fnstart			)
-4:	tst	r1, #8			@ 1 8 bytes or more?
-	stmneia	r0!, {r2, r3}		@ 2
-	tst	r1, #4			@ 1 4 bytes or more?
-	strne	r2, [r0], #4		@ 1
-/*
- * When we get here, we've got less than 4 bytes to zero.  We
- * may have an unaligned pointer as well.
- */
-5:	tst	r1, #2			@ 1 2 bytes or more?
-	strneb	r2, [r0], #1		@ 1
-	strneb	r2, [r0], #1		@ 1
-	tst	r1, #1			@ 1 a byte left over
-	strneb	r2, [r0], #1		@ 1
-	ret	lr			@ 1
-UNWIND(	.fnend				)
-ENDPROC(__memzero)
diff --git a/arch/arm/mach-bcm/brcmstb.c b/arch/arm/mach-bcm/brcmstb.c
index 07e3a86c6466..5f127d5f1045 100644
--- a/arch/arm/mach-bcm/brcmstb.c
+++ b/arch/arm/mach-bcm/brcmstb.c
@@ -14,7 +14,6 @@
 #include <linux/init.h>
 #include <linux/irqchip.h>
 #include <linux/of_platform.h>
-#include <linux/soc/brcmstb/brcmstb.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -38,7 +37,6 @@ u32 brcmstb_uart_config[3] = {
 static void __init brcmstb_init_irq(void)
 {
 	irqchip_init();
-	brcmstb_biuctrl_init();
 }
 
 static const char *const brcmstb_match[] __initconst = {
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index cbde0030c092..d898a94f6eae 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -798,11 +798,11 @@ static int da850_lcd_hw_init(void)
 {
 	int status;
 
-	status = gpio_request(DA850_LCD_BL_PIN, "lcd bl\n");
+	status = gpio_request(DA850_LCD_BL_PIN, "lcd bl");
 	if (status < 0)
 		return status;
 
-	status = gpio_request(DA850_LCD_PWR_PIN, "lcd pwr\n");
+	status = gpio_request(DA850_LCD_PWR_PIN, "lcd pwr");
 	if (status < 0) {
 		gpio_free(DA850_LCD_BL_PIN);
 		return status;
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index 0c02aaad0539..4da210a1a110 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -128,7 +128,7 @@ static struct platform_device davinci_fb_device = {
 	.num_resources = 0,
 };
 
-static struct gpio_led ntosd2_leds[] = {
+static const struct gpio_led ntosd2_leds[] = {
 	{ .name = "led1_green", .gpio = GPIO(10), },
 	{ .name = "led1_red",   .gpio = GPIO(11), },
 	{ .name = "led2_green", .gpio = GPIO(12), },
diff --git a/arch/arm/mach-davinci/common.c b/arch/arm/mach-davinci/common.c
index 9f9fbfa6da0d..bcb6a7ba84e9 100644
--- a/arch/arm/mach-davinci/common.c
+++ b/arch/arm/mach-davinci/common.c
@@ -77,7 +77,7 @@ static int __init davinci_init_id(struct davinci_soc_info *soc_info)
 	return -EINVAL;
 }
 
-void __init davinci_common_init(struct davinci_soc_info *soc_info)
+void __init davinci_common_init(const struct davinci_soc_info *soc_info)
 {
 	int ret;
 
diff --git a/arch/arm/mach-davinci/da830.c b/arch/arm/mach-davinci/da830.c
index bd88470f3e5c..57ab18cf2a89 100644
--- a/arch/arm/mach-davinci/da830.c
+++ b/arch/arm/mach-davinci/da830.c
@@ -417,7 +417,7 @@ static struct clk_lookup da830_clks[] = {
 	CLK("davinci-mcasp.0",	NULL,		&mcasp0_clk),
 	CLK("davinci-mcasp.1",	NULL,		&mcasp1_clk),
 	CLK("davinci-mcasp.2",	NULL,		&mcasp2_clk),
-	CLK("musb-da8xx",	"usb20",	&usb20_clk),
+	CLK("musb-da8xx",	NULL,		&usb20_clk),
 	CLK("cppi41-dmaengine",	NULL,		&cppi41_clk),
 	CLK(NULL,		"aemif",	&aemif_clk),
 	CLK(NULL,		"aintc",	&aintc_clk),
@@ -426,7 +426,7 @@ static struct clk_lookup da830_clks[] = {
 	CLK("davinci_mdio.0",   "fck",          &emac_clk),
 	CLK(NULL,		"gpio",		&gpio_clk),
 	CLK("i2c_davinci.2",	NULL,		&i2c1_clk),
-	CLK("ohci-da8xx",	"usb11",	&usb11_clk),
+	CLK("ohci-da8xx",	NULL,	&usb11_clk),
 	CLK(NULL,		"emif3",	&emif3_clk),
 	CLK(NULL,		"arm",		&arm_clk),
 	CLK(NULL,		"rmii",		&rmii_clk),
@@ -1194,7 +1194,7 @@ static struct davinci_timer_info da830_timer_info = {
 	.clocksource_id	= T0_BOT,
 };
 
-static struct davinci_soc_info davinci_soc_info_da830 = {
+static const struct davinci_soc_info davinci_soc_info_da830 = {
 	.io_desc		= da830_io_desc,
 	.io_desc_num		= ARRAY_SIZE(da830_io_desc),
 	.jtag_id_reg		= DA8XX_SYSCFG0_BASE + DA8XX_JTAG_ID_REG,
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index 07d6f0eb8c82..aa37cbdf7d4d 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -563,8 +563,8 @@ static struct clk_lookup da850_clks[] = {
 	CLK("da830-mmc.1",	NULL,		&mmcsd1_clk),
 	CLK("ti-aemif",		NULL,		&aemif_clk),
 	CLK("davinci-nand.0",	"aemif",	&aemif_nand_clk),
-	CLK("ohci-da8xx",	"usb11",	&usb11_clk),
-	CLK("musb-da8xx",	"usb20",	&usb20_clk),
+	CLK("ohci-da8xx",	NULL,		&usb11_clk),
+	CLK("musb-da8xx",	NULL,		&usb20_clk),
 	CLK("cppi41-dmaengine",	NULL,		&cppi41_clk),
 	CLK("spi_davinci.0",	NULL,		&spi0_clk),
 	CLK("spi_davinci.1",	NULL,		&spi1_clk),
@@ -1347,7 +1347,7 @@ int __init da850_register_gpio(void)
 	return da8xx_register_gpio(&da850_gpio_platform_data);
 }
 
-static struct davinci_soc_info davinci_soc_info_da850 = {
+static const struct davinci_soc_info davinci_soc_info_da850 = {
 	.io_desc		= da850_io_desc,
 	.io_desc_num		= ARRAY_SIZE(da850_io_desc),
 	.jtag_id_reg		= DA8XX_SYSCFG0_BASE + DA8XX_JTAG_ID_REG,
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 22440c05d66a..e1c40e73d30a 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -252,7 +252,7 @@ int __init da830_register_edma(struct edma_rsv_info *rsv)
 	da8xx_edma0_pdata.slavecnt = ARRAY_SIZE(da830_edma_map);
 
 	edma_pdev = platform_device_register_full(&da8xx_edma0_device);
-	return IS_ERR(edma_pdev) ? PTR_ERR(edma_pdev) : 0;
+	return PTR_ERR_OR_ZERO(edma_pdev);
 }
 
 static const struct dma_slave_map da850_edma0_map[] = {
@@ -297,7 +297,7 @@ int __init da850_register_edma(struct edma_rsv_info *rsv[2])
 	da850_edma1_pdata.slavecnt = ARRAY_SIZE(da850_edma1_map);
 
 	edma_pdev = platform_device_register_full(&da850_edma1_device);
-	return IS_ERR(edma_pdev) ? PTR_ERR(edma_pdev) : 0;
+	return PTR_ERR_OR_ZERO(edma_pdev);
 }
 
 static struct resource da8xx_i2c_resources0[] = {
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index bd50367f654e..938747f20c22 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -1006,7 +1006,7 @@ struct platform_device dm355_serial_device[] = {
 	}
 };
 
-static struct davinci_soc_info davinci_soc_info_dm355 = {
+static const struct davinci_soc_info davinci_soc_info_dm355 = {
 	.io_desc		= dm355_io_desc,
 	.io_desc_num		= ARRAY_SIZE(dm355_io_desc),
 	.jtag_id_reg		= 0x01c40028,
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 8be04ec95adf..5d9f96df08e9 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -868,10 +868,10 @@ static const struct dma_slave_map dm365_edma_map[] = {
 	{ "spi_davinci.0", "rx", EDMA_FILTER_PARAM(0, 17) },
 	{ "spi_davinci.3", "tx", EDMA_FILTER_PARAM(0, 18) },
 	{ "spi_davinci.3", "rx", EDMA_FILTER_PARAM(0, 19) },
-	{ "dm6441-mmc.0", "rx", EDMA_FILTER_PARAM(0, 26) },
-	{ "dm6441-mmc.0", "tx", EDMA_FILTER_PARAM(0, 27) },
-	{ "dm6441-mmc.1", "rx", EDMA_FILTER_PARAM(0, 30) },
-	{ "dm6441-mmc.1", "tx", EDMA_FILTER_PARAM(0, 31) },
+	{ "da830-mmc.0", "rx", EDMA_FILTER_PARAM(0, 26) },
+	{ "da830-mmc.0", "tx", EDMA_FILTER_PARAM(0, 27) },
+	{ "da830-mmc.1", "rx", EDMA_FILTER_PARAM(0, 30) },
+	{ "da830-mmc.1", "tx", EDMA_FILTER_PARAM(0, 31) },
 };
 
 static struct edma_soc_info dm365_edma_pdata = {
@@ -925,12 +925,14 @@ static struct resource edma_resources[] = {
 	/* not using TC*_ERR */
 };
 
-static struct platform_device dm365_edma_device = {
-	.name			= "edma",
-	.id			= 0,
-	.dev.platform_data	= &dm365_edma_pdata,
-	.num_resources		= ARRAY_SIZE(edma_resources),
-	.resource		= edma_resources,
+static const struct platform_device_info dm365_edma_device __initconst = {
+	.name		= "edma",
+	.id		= 0,
+	.dma_mask	= DMA_BIT_MASK(32),
+	.res		= edma_resources,
+	.num_res	= ARRAY_SIZE(edma_resources),
+	.data		= &dm365_edma_pdata,
+	.size_data	= sizeof(dm365_edma_pdata),
 };
 
 static struct resource dm365_asp_resources[] = {
@@ -1108,7 +1110,7 @@ struct platform_device dm365_serial_device[] = {
 	}
 };
 
-static struct davinci_soc_info davinci_soc_info_dm365 = {
+static const struct davinci_soc_info davinci_soc_info_dm365 = {
 	.io_desc		= dm365_io_desc,
 	.io_desc_num		= ARRAY_SIZE(dm365_io_desc),
 	.jtag_id_reg		= 0x01c40028,
@@ -1428,13 +1430,18 @@ int __init dm365_init_video(struct vpfe_config *vpfe_cfg,
 
 static int __init dm365_init_devices(void)
 {
+	struct platform_device *edma_pdev;
 	int ret = 0;
 
 	if (!cpu_is_davinci_dm365())
 		return 0;
 
 	davinci_cfg_reg(DM365_INT_EDMA_CC);
-	platform_device_register(&dm365_edma_device);
+	edma_pdev = platform_device_register_full(&dm365_edma_device);
+	if (IS_ERR(edma_pdev)) {
+		pr_warn("%s: Failed to register eDMA\n", __func__);
+		return PTR_ERR(edma_pdev);
+	}
 
 	platform_device_register(&dm365_mdio_device);
 	platform_device_register(&dm365_emac_device);
diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c
index b437c3730f65..6b41e1ca511e 100644
--- a/arch/arm/mach-davinci/dm644x.c
+++ b/arch/arm/mach-davinci/dm644x.c
@@ -899,7 +899,7 @@ struct platform_device dm644x_serial_device[] = {
 	}
 };
 
-static struct davinci_soc_info davinci_soc_info_dm644x = {
+static const struct davinci_soc_info davinci_soc_info_dm644x = {
 	.io_desc		= dm644x_io_desc,
 	.io_desc_num		= ARRAY_SIZE(dm644x_io_desc),
 	.jtag_id_reg		= 0x01c40028,
diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c
index da21353cac45..6fc06a6ad4f8 100644
--- a/arch/arm/mach-davinci/dm646x.c
+++ b/arch/arm/mach-davinci/dm646x.c
@@ -882,7 +882,7 @@ struct platform_device dm646x_serial_device[] = {
 	}
 };
 
-static struct davinci_soc_info davinci_soc_info_dm646x = {
+static const struct davinci_soc_info davinci_soc_info_dm646x = {
 	.io_desc		= dm646x_io_desc,
 	.io_desc_num		= ARRAY_SIZE(dm646x_io_desc),
 	.jtag_id_reg		= 0x01c40028,
@@ -949,7 +949,7 @@ int __init dm646x_init_edma(struct edma_rsv_info *rsv)
 	dm646x_edma_pdata.rsv = rsv;
 
 	edma_pdev = platform_device_register_full(&dm646x_edma_device);
-	return IS_ERR(edma_pdev) ? PTR_ERR(edma_pdev) : 0;
+	return PTR_ERR_OR_ZERO(edma_pdev);
 }
 
 void __init dm646x_init(void)
diff --git a/arch/arm/mach-davinci/include/mach/common.h b/arch/arm/mach-davinci/include/mach/common.h
index 037aa66bcac1..433a008ff796 100644
--- a/arch/arm/mach-davinci/include/mach/common.h
+++ b/arch/arm/mach-davinci/include/mach/common.h
@@ -79,7 +79,7 @@ struct davinci_soc_info {
 
 extern struct davinci_soc_info davinci_soc_info;
 
-extern void davinci_common_init(struct davinci_soc_info *soc_info);
+extern void davinci_common_init(const struct davinci_soc_info *soc_info);
 extern void davinci_init_ide(void);
 void davinci_restart(enum reboot_mode mode, const char *cmd);
 void davinci_init_late(void);
diff --git a/arch/arm/mach-ep93xx/Kconfig b/arch/arm/mach-ep93xx/Kconfig
index 61a75ca3684e..c095236d7ff8 100644
--- a/arch/arm/mach-ep93xx/Kconfig
+++ b/arch/arm/mach-ep93xx/Kconfig
@@ -21,6 +21,13 @@ config MACH_ADSSPHERE
 	  Say 'Y' here if you want your kernel to support the ADS
 	  Sphere board.
 
+config MACH_BK3
+	bool "Support Liebherr BK3.1"
+	select MACH_TS72XX
+	help
+	  Say 'Y' here if you want your kernel to support the
+	  Liebherr controller BK3.1.
+
 config MACH_EDB93XX
 	bool
 
diff --git a/arch/arm/mach-ep93xx/ts72xx.c b/arch/arm/mach-ep93xx/ts72xx.c
index f386ebae0163..c089a2a4fe30 100644
--- a/arch/arm/mach-ep93xx/ts72xx.c
+++ b/arch/arm/mach-ep93xx/ts72xx.c
@@ -19,10 +19,15 @@
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
 #include <linux/spi/spi.h>
+#include <linux/spi/flash.h>
+#include <linux/spi/mmc_spi.h>
+#include <linux/mmc/host.h>
 #include <linux/platform_data/spi-ep93xx.h>
 
 #include <mach/gpio-ep93xx.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
+#include <mach/gpio-ep93xx.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/map.h>
@@ -31,6 +36,9 @@
 #include "soc.h"
 #include "ts72xx.h"
 
+/*************************************************************************
+ * IO map
+ *************************************************************************/
 static struct map_desc ts72xx_io_desc[] __initdata = {
 	{
 		.virtual	= (unsigned long)TS72XX_MODEL_VIRT_BASE,
@@ -47,6 +55,11 @@ static struct map_desc ts72xx_io_desc[] __initdata = {
 		.pfn		= __phys_to_pfn(TS72XX_OPTIONS2_PHYS_BASE),
 		.length		= TS72XX_OPTIONS2_SIZE,
 		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)TS72XX_CPLDVER_VIRT_BASE,
+		.pfn		= __phys_to_pfn(TS72XX_CPLDVER_PHYS_BASE),
+		.length		= TS72XX_CPLDVER_SIZE,
+		.type		= MT_DEVICE,
 	}
 };
 
@@ -123,8 +136,6 @@ static struct platform_nand_data ts72xx_nand_data = {
 		.nr_chips	= 1,
 		.chip_offset	= 0,
 		.chip_delay	= 15,
-		.partitions	= ts72xx_nand_parts,
-		.nr_partitions	= ARRAY_SIZE(ts72xx_nand_parts),
 	},
 	.ctrl = {
 		.cmd_ctrl	= ts72xx_nand_hwcontrol,
@@ -148,8 +159,8 @@ static struct platform_device ts72xx_nand_flash = {
 	.num_resources		= ARRAY_SIZE(ts72xx_nand_resource),
 };
 
-
-static void __init ts72xx_register_flash(void)
+void __init ts72xx_register_flash(struct mtd_partition *parts, int n,
+				  resource_size_t start)
 {
 	/*
 	 * TS7200 has NOR flash all other TS72xx board have NAND flash.
@@ -157,16 +168,12 @@ static void __init ts72xx_register_flash(void)
 	if (board_is_ts7200()) {
 		ep93xx_register_flash(2, EP93XX_CS6_PHYS_BASE, SZ_16M);
 	} else {
-		resource_size_t start;
-
-		if (is_ts9420_installed())
-			start = EP93XX_CS7_PHYS_BASE;
-		else
-			start = EP93XX_CS6_PHYS_BASE;
-
 		ts72xx_nand_resource[0].start = start;
 		ts72xx_nand_resource[0].end = start + SZ_16M - 1;
 
+		ts72xx_nand_data.chip.partitions = parts;
+		ts72xx_nand_data.chip.nr_partitions = n;
+
 		platform_device_register(&ts72xx_nand_flash);
 	}
 }
@@ -207,10 +214,79 @@ static struct platform_device ts72xx_wdt_device = {
 	.num_resources	= ARRAY_SIZE(ts72xx_wdt_resources),
 };
 
+/*************************************************************************
+ * ETH
+ *************************************************************************/
 static struct ep93xx_eth_data __initdata ts72xx_eth_data = {
 	.phy_id		= 1,
 };
 
+/*************************************************************************
+ * SPI SD/MMC host
+ *************************************************************************/
+#define BK3_EN_SDCARD_PHYS_BASE         0x12400000
+#define BK3_EN_SDCARD_PWR 0x0
+#define BK3_DIS_SDCARD_PWR 0x0C
+static void bk3_mmc_spi_setpower(struct device *dev, unsigned int vdd)
+{
+	void __iomem *pwr_sd = ioremap(BK3_EN_SDCARD_PHYS_BASE, SZ_4K);
+
+	if (!pwr_sd) {
+		pr_err("Failed to enable SD card power!");
+		return;
+	}
+
+	pr_debug("%s: SD card pwr %s VDD:0x%x\n", __func__,
+		 !!vdd ? "ON" : "OFF", vdd);
+
+	if (!!vdd)
+		__raw_writeb(BK3_EN_SDCARD_PWR, pwr_sd);
+	else
+		__raw_writeb(BK3_DIS_SDCARD_PWR, pwr_sd);
+
+	iounmap(pwr_sd);
+}
+
+static struct mmc_spi_platform_data bk3_spi_mmc_data = {
+	.detect_delay	= 500,
+	.powerup_msecs	= 100,
+	.ocr_mask	= MMC_VDD_32_33 | MMC_VDD_33_34,
+	.caps		= MMC_CAP_NONREMOVABLE,
+	.setpower       = bk3_mmc_spi_setpower,
+};
+
+/*************************************************************************
+ * SPI Bus - SD card access
+ *************************************************************************/
+static struct spi_board_info bk3_spi_board_info[] __initdata = {
+	{
+		.modalias		= "mmc_spi",
+		.platform_data		= &bk3_spi_mmc_data,
+		.max_speed_hz		= 7.4E6,
+		.bus_num		= 0,
+		.chip_select		= 0,
+		.mode			= SPI_MODE_0,
+	},
+};
+
+/*
+ * This is a stub -> the FGPIO[3] pin is not connected on the schematic
+ * The all work is performed automatically by !SPI_FRAME (SFRM1) and
+ * goes through CPLD
+ */
+static int bk3_spi_chipselects[] __initdata = {
+	EP93XX_GPIO_LINE_F(3),
+};
+
+static struct ep93xx_spi_info bk3_spi_master __initdata = {
+	.chipselect	= bk3_spi_chipselects,
+	.num_chipselect = ARRAY_SIZE(bk3_spi_chipselects),
+	.use_dma	= 1,
+};
+
+/*************************************************************************
+ * TS72XX support code
+ *************************************************************************/
 #if IS_ENABLED(CONFIG_FPGA_MGR_TS73XX)
 
 /* Relative to EP93XX_CS1_PHYS_BASE */
@@ -257,7 +333,9 @@ static struct ep93xx_spi_info ts72xx_spi_info __initdata = {
 static void __init ts72xx_init_machine(void)
 {
 	ep93xx_init_devices();
-	ts72xx_register_flash();
+	ts72xx_register_flash(ts72xx_nand_parts, ARRAY_SIZE(ts72xx_nand_parts),
+			      is_ts9420_installed() ?
+			      EP93XX_CS7_PHYS_BASE : EP93XX_CS6_PHYS_BASE);
 	platform_device_register(&ts72xx_rtc_device);
 	platform_device_register(&ts72xx_wdt_device);
 
@@ -280,3 +358,66 @@ MACHINE_START(TS72XX, "Technologic Systems TS-72xx SBC")
 	.init_late	= ep93xx_init_late,
 	.restart	= ep93xx_restart,
 MACHINE_END
+
+/*************************************************************************
+ * EP93xx I2S audio peripheral handling
+ *************************************************************************/
+static struct resource ep93xx_i2s_resource[] = {
+	DEFINE_RES_MEM(EP93XX_I2S_PHYS_BASE, 0x100),
+	DEFINE_RES_IRQ_NAMED(IRQ_EP93XX_SAI, "spilink i2s slave"),
+};
+
+static struct platform_device ep93xx_i2s_device = {
+	.name		= "ep93xx-spilink-i2s",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(ep93xx_i2s_resource),
+	.resource	= ep93xx_i2s_resource,
+};
+
+/*************************************************************************
+ * BK3 support code
+ *************************************************************************/
+static struct mtd_partition bk3_nand_parts[] = {
+	{
+		.name		= "System",
+		.offset	= 0x00000000,
+		.size		= 0x01e00000,
+	}, {
+		.name		= "Data",
+		.offset	= 0x01e00000,
+		.size		= 0x05f20000
+	}, {
+		.name		= "RedBoot",
+		.offset	= 0x07d20000,
+		.size		= 0x002e0000,
+		.mask_flags	= MTD_WRITEABLE,	/* force RO */
+	},
+};
+
+static void __init bk3_init_machine(void)
+{
+	ep93xx_init_devices();
+
+	ts72xx_register_flash(bk3_nand_parts, ARRAY_SIZE(bk3_nand_parts),
+			      EP93XX_CS6_PHYS_BASE);
+
+	ep93xx_register_eth(&ts72xx_eth_data, 1);
+
+	ep93xx_register_spi(&bk3_spi_master, bk3_spi_board_info,
+			    ARRAY_SIZE(bk3_spi_board_info));
+
+	/* Configure ep93xx's I2S to use AC97 pins */
+	ep93xx_devcfg_set_bits(EP93XX_SYSCON_DEVCFG_I2SONAC97);
+	platform_device_register(&ep93xx_i2s_device);
+}
+
+MACHINE_START(BK3, "Liebherr controller BK3.1")
+	/* Maintainer: Lukasz Majewski <lukma@denx.de> */
+	.atag_offset	= 0x100,
+	.map_io		= ts72xx_map_io,
+	.init_irq	= ep93xx_init_irq,
+	.init_time	= ep93xx_timer_init,
+	.init_machine	= bk3_init_machine,
+	.init_late	= ep93xx_init_late,
+	.restart	= ep93xx_restart,
+MACHINE_END
diff --git a/arch/arm/mach-ep93xx/ts72xx.h b/arch/arm/mach-ep93xx/ts72xx.h
index 8a3206a54b39..00b4941d29c9 100644
--- a/arch/arm/mach-ep93xx/ts72xx.h
+++ b/arch/arm/mach-ep93xx/ts72xx.h
@@ -10,8 +10,12 @@
  * febff000	22000000	4K	model number register (bits 0-2)
  * febfe000	22400000	4K	options register
  * febfd000	22800000	4K	options register #2
+ * febfc000     23400000        4K      CPLD version register
  */
 
+#ifndef __TS72XX_H_
+#define __TS72XX_H_
+
 #define TS72XX_MODEL_PHYS_BASE		0x22000000
 #define TS72XX_MODEL_VIRT_BASE		IOMEM(0xfebff000)
 #define TS72XX_MODEL_SIZE		0x00001000
@@ -39,6 +43,10 @@
 #define TS72XX_OPTIONS2_TS9420		0x04
 #define TS72XX_OPTIONS2_TS9420_BOOT	0x02
 
+#define TS72XX_CPLDVER_PHYS_BASE	0x23400000
+#define TS72XX_CPLDVER_VIRT_BASE	IOMEM(0xfebfc000)
+#define TS72XX_CPLDVER_SIZE		0x00001000
+
 #ifndef __ASSEMBLY__
 
 static inline int ts72xx_model(void)
@@ -83,3 +91,4 @@ static inline int is_ts9420_installed(void)
 					TS72XX_OPTIONS2_TS9420);
 }
 #endif
+#endif /* __TS72XX_H_ */
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 44fa753bd79c..647c319f9f5f 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -1,9 +1,7 @@
-# arch/arm/mach-exynos/Kconfig
+# SPDX-License-Identifier: GPL-2.0
 #
 # Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
 #		http://www.samsung.com/
-#
-# Licensed under GPLv2
 
 # Configuration options for the EXYNOS
 
diff --git a/arch/arm/mach-exynos/Makefile b/arch/arm/mach-exynos/Makefile
index 9ea6c54645ad..cd00c82a1add 100644
--- a/arch/arm/mach-exynos/Makefile
+++ b/arch/arm/mach-exynos/Makefile
@@ -1,9 +1,7 @@
-# arch/arm/mach-exynos/Makefile
+# SPDX-License-Identifier: GPL-2.0
 #
 # Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
 #		http://www.samsung.com/
-#
-# Licensed under GPLv2
 
 ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include
 
diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h
index 3f715524c9d6..098f84a149a3 100644
--- a/arch/arm/mach-exynos/common.h
+++ b/arch/arm/mach-exynos/common.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Common Header for EXYNOS machines
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __ARCH_ARM_MACH_EXYNOS_COMMON_H
diff --git a/arch/arm/mach-exynos/exynos-smc.S b/arch/arm/mach-exynos/exynos-smc.S
index 2e27aa3813fd..d259532ba937 100644
--- a/arch/arm/mach-exynos/exynos-smc.S
+++ b/arch/arm/mach-exynos/exynos-smc.S
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2012 Samsung Electronics.
  *
  * Copied from omap-smc.S Copyright (C) 2010 Texas Instruments, Inc.
- *
- * This program is free software,you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/linkage.h>
diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c
index 9a9caac1125a..fbd108ce8745 100644
--- a/arch/arm/mach-exynos/exynos.c
+++ b/arch/arm/mach-exynos/exynos.c
@@ -1,13 +1,9 @@
-/*
- * SAMSUNG EXYNOS Flattened Device Tree enabled machine
- *
- * Copyright (c) 2010-2014 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// SAMSUNG EXYNOS Flattened Device Tree enabled machine
+//
+// Copyright (c) 2010-2014 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
 
 #include <linux/init.h>
 #include <linux/io.h>
diff --git a/arch/arm/mach-exynos/firmware.c b/arch/arm/mach-exynos/firmware.c
index 2a51e4603a6f..be1f20fe28f4 100644
--- a/arch/arm/mach-exynos/firmware.c
+++ b/arch/arm/mach-exynos/firmware.c
@@ -1,12 +1,8 @@
-/*
- * Copyright (C) 2012 Samsung Electronics.
- * Kyungmin Park <kyungmin.park@samsung.com>
- * Tomasz Figa <t.figa@samsung.com>
- *
- * This program is free software,you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2012 Samsung Electronics.
+// Kyungmin Park <kyungmin.park@samsung.com>
+// Tomasz Figa <t.figa@samsung.com>
 
 #include <linux/kernel.h>
 #include <linux/io.h>
diff --git a/arch/arm/mach-exynos/headsmp.S b/arch/arm/mach-exynos/headsmp.S
index d3d24ab351ae..005695c9bf40 100644
--- a/arch/arm/mach-exynos/headsmp.S
+++ b/arch/arm/mach-exynos/headsmp.S
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- *
  *  Cloned from linux/arch/arm/mach-realview/headsmp.S
  *
  *  Copyright (c) 2003 ARM Limited
  *  All Rights Reserved
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mach-exynos/include/mach/map.h b/arch/arm/mach-exynos/include/mach/map.h
index 5fb0040cc6d3..37a5ea5e2602 100644
--- a/arch/arm/mach-exynos/include/mach/map.h
+++ b/arch/arm/mach-exynos/include/mach/map.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com/
  *
  * EXYNOS - Memory map definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_ARCH_MAP_H
 #define __ASM_ARCH_MAP_H __FILE__
diff --git a/arch/arm/mach-exynos/mcpm-exynos.c b/arch/arm/mach-exynos/mcpm-exynos.c
index b42622562ea7..72bc035bedbe 100644
--- a/arch/arm/mach-exynos/mcpm-exynos.c
+++ b/arch/arm/mach-exynos/mcpm-exynos.c
@@ -1,15 +1,8 @@
-/*
- * Copyright (c) 2014 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * arch/arm/mach-exynos/mcpm-exynos.c
- *
- * Based on arch/arm/mach-vexpress/dcscb.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2014 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
+//
+// Based on arch/arm/mach-vexpress/dcscb.c
 
 #include <linux/arm-cci.h>
 #include <linux/delay.h>
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index 5a03bffe7226..5156fe70e030 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -1,16 +1,11 @@
- /*
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * Cloned from linux/arch/arm/mach-vexpress/platsmp.c
- *
- *  Copyright (C) 2002 ARM Ltd.
- *  All Rights Reserved
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
+//
+// Cloned from linux/arch/arm/mach-vexpress/platsmp.c
+//
+//  Copyright (C) 2002 ARM Ltd.
+//  All Rights Reserved
 
 #include <linux/init.h>
 #include <linux/errno.h>
diff --git a/arch/arm/mach-exynos/pm.c b/arch/arm/mach-exynos/pm.c
index c9740d96db9e..dc4346ecf16d 100644
--- a/arch/arm/mach-exynos/pm.c
+++ b/arch/arm/mach-exynos/pm.c
@@ -1,17 +1,13 @@
-/*
- * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * EXYNOS - Power Management support
- *
- * Based on arch/arm/mach-s3c2410/pm.c
- * Copyright (c) 2006 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2011-2014 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
+//
+// EXYNOS - Power Management support
+//
+// Based on arch/arm/mach-s3c2410/pm.c
+// Copyright (c) 2006 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
 
 #include <linux/init.h>
 #include <linux/suspend.h>
diff --git a/arch/arm/mach-exynos/sleep.S b/arch/arm/mach-exynos/sleep.S
index 4292cae43f3c..2783c3a0c06a 100644
--- a/arch/arm/mach-exynos/sleep.S
+++ b/arch/arm/mach-exynos/sleep.S
@@ -1,18 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Exynos low-level resume code
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/linkage.h>
diff --git a/arch/arm/mach-exynos/smc.h b/arch/arm/mach-exynos/smc.h
index c2845717bc8f..f355185d4239 100644
--- a/arch/arm/mach-exynos/smc.h
+++ b/arch/arm/mach-exynos/smc.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  Copyright (c) 2012 Samsung Electronics.
  *
  * EXYNOS - SMC Call
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __ASM_ARCH_EXYNOS_SMC_H
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index 370d37ded7e7..c2ed997fedef 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -1,17 +1,13 @@
-/*
- * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * EXYNOS - Suspend support
- *
- * Based on arch/arm/mach-s3c2410/pm.c
- * Copyright (c) 2006 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2011-2014 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
+//
+// EXYNOS - Suspend support
+//
+// Based on arch/arm/mach-s3c2410/pm.c
+// Copyright (c) 2006 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
 
 #include <linux/init.h>
 #include <linux/suspend.h>
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index b09a2ec19267..c8d68e918b2f 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -71,15 +71,6 @@ enum mxc_cpu_pwr_mode {
 	STOP_POWER_OFF,		/* STOP + SRPG */
 };
 
-enum mx3_cpu_pwr_mode {
-	MX3_RUN,
-	MX3_WAIT,
-	MX3_DOZE,
-	MX3_SLEEP,
-};
-
-void mx3_cpu_lp_set(enum mx3_cpu_pwr_mode mode);
-
 void imx_enable_cpu(int cpu, bool enable);
 void imx_set_cpu_jump(int cpu, void *jump_addr);
 u32 imx_get_cpu_arg(int cpu);
diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index 78262899a590..5fb1d2254b5e 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -547,7 +547,6 @@ static int imx_mmdc_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	void __iomem *mmdc_base, *reg;
 	u32 val;
-	int timeout = 0x400;
 
 	mmdc_base = of_iomap(np, 0);
 	WARN_ON(!mmdc_base);
@@ -565,16 +564,6 @@ static int imx_mmdc_probe(struct platform_device *pdev)
 	val &= ~(1 << BP_MMDC_MAPSR_PSD);
 	writel_relaxed(val, reg);
 
-	/* Ensure it's successfully enabled */
-	while (!(readl_relaxed(reg) & 1 << BP_MMDC_MAPSR_PSS) && --timeout)
-		cpu_relax();
-
-	if (unlikely(!timeout)) {
-		pr_warn("%s: failed to enable automatic power saving\n",
-			__func__);
-		return -EBUSY;
-	}
-
 	return imx_mmdc_perf_init(pdev, mmdc_base);
 }
 
diff --git a/arch/arm/mach-ixp4xx/vulcan-setup.c b/arch/arm/mach-ixp4xx/vulcan-setup.c
index 731fb2019ecb..2c03d2f6b647 100644
--- a/arch/arm/mach-ixp4xx/vulcan-setup.c
+++ b/arch/arm/mach-ixp4xx/vulcan-setup.c
@@ -16,6 +16,7 @@
 #include <linux/serial_8250.h>
 #include <linux/io.h>
 #include <linux/w1-gpio.h>
+#include <linux/gpio/machine.h>
 #include <linux/mtd/plat-ram.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -162,9 +163,16 @@ static struct platform_device vulcan_max6369 = {
 	.num_resources		= 1,
 };
 
+static struct gpiod_lookup_table vulcan_w1_gpiod_table = {
+	.dev_id = "w1-gpio",
+	.table = {
+		GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", 14, NULL, 0,
+				GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
+	},
+};
+
 static struct w1_gpio_platform_data vulcan_w1_gpio_pdata = {
-	.pin			= 14,
-	.ext_pullup_enable_pin	= -EINVAL,
+	/* Intentionally left blank */
 };
 
 static struct platform_device vulcan_w1_gpio = {
@@ -233,6 +241,7 @@ static void __init vulcan_init(void)
 			  IXP4XX_EXP_BUS_WR_EN		|
 			  IXP4XX_EXP_BUS_BYTE_EN;
 
+	gpiod_add_lookup_table(&vulcan_w1_gpiod_table);
 	platform_add_devices(vulcan_devices, ARRAY_SIZE(vulcan_devices));
 }
 
diff --git a/arch/arm/mach-mediatek/Kconfig b/arch/arm/mach-mediatek/Kconfig
index 70e49d54434e..91cc461f7b04 100644
--- a/arch/arm/mach-mediatek/Kconfig
+++ b/arch/arm/mach-mediatek/Kconfig
@@ -1,5 +1,5 @@
 menuconfig ARCH_MEDIATEK
-	bool "Mediatek MT65xx & MT81xx SoC"
+	bool "MediaTek SoC Support"
 	depends on ARCH_MULTI_V7
 	select ARM_GIC
 	select PINCTRL
diff --git a/arch/arm/mach-meson/Kconfig b/arch/arm/mach-meson/Kconfig
index aff6164b2083..d90f61e6254f 100644
--- a/arch/arm/mach-meson/Kconfig
+++ b/arch/arm/mach-meson/Kconfig
@@ -23,6 +23,7 @@ config MACH_MESON8
 	default ARCH_MESON
 	select MESON6_TIMER
 	select COMMON_CLK_MESON8B
+	select MESON_IRQ_GPIO
 
 config MACH_MESON8B
 	bool "Amlogic Meson8b SoCs support"
diff --git a/arch/arm/mach-meson/platsmp.c b/arch/arm/mach-meson/platsmp.c
index 2555f9056a33..cad7ee8f0d6b 100644
--- a/arch/arm/mach-meson/platsmp.c
+++ b/arch/arm/mach-meson/platsmp.c
@@ -102,7 +102,7 @@ static void __init meson_smp_prepare_cpus(const char *scu_compatible,
 
 	scu_base = of_iomap(node, 0);
 	if (!scu_base) {
-		pr_err("Couln't map SCU registers\n");
+		pr_err("Couldn't map SCU registers\n");
 		return;
 	}
 
diff --git a/arch/arm/mach-mmp/mmp2.h b/arch/arm/mach-mmp/mmp2.h
index a4b82f719de1..adafc4fba8f4 100644
--- a/arch/arm/mach-mmp/mmp2.h
+++ b/arch/arm/mach-mmp/mmp2.h
@@ -10,7 +10,7 @@ extern void __init mmp2_init_irq(void);
 extern void mmp2_clear_pmic_int(void);
 
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/dma-mmp_tdma.h>
 
 #include "devices.h"
diff --git a/arch/arm/mach-mmp/pxa168.h b/arch/arm/mach-mmp/pxa168.h
index b39bff37ff11..0331c58b07a2 100644
--- a/arch/arm/mach-mmp/pxa168.h
+++ b/arch/arm/mach-mmp/pxa168.h
@@ -11,7 +11,7 @@ extern void pxa168_restart(enum reboot_mode, const char *);
 extern void pxa168_clear_keypad_wakeup(void);
 
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/mtd-nand-pxa3xx.h>
 #include <video/pxa168fb.h>
 #include <linux/platform_data/keypad-pxa27x.h>
diff --git a/arch/arm/mach-mmp/pxa910.h b/arch/arm/mach-mmp/pxa910.h
index cb3923dcf580..42009c349eae 100644
--- a/arch/arm/mach-mmp/pxa910.h
+++ b/arch/arm/mach-mmp/pxa910.h
@@ -7,7 +7,7 @@ extern void __init icu_init_irq(void);
 extern void __init pxa910_init_irq(void);
 
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/mtd-nand-pxa3xx.h>
 #include <video/mmp_disp.h>
 
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 2f722a805948..c15bbcad5f67 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -232,6 +232,3 @@ obj-y					+= $(omap-hsmmc-m) $(omap-hsmmc-y)
 obj-y					+= omap_phy_internal.o
 
 obj-$(CONFIG_MACH_OMAP2_TUSB6010)	+= usb-tusb6010.o
-
-onenand-$(CONFIG_MTD_ONENAND_OMAP2)	:= gpmc-onenand.o
-obj-y					+= $(onenand-m) $(onenand-y)
diff --git a/arch/arm/mach-omap2/clockdomain.c b/arch/arm/mach-omap2/clockdomain.c
index 518926410b62..b79b1ca9aee9 100644
--- a/arch/arm/mach-omap2/clockdomain.c
+++ b/arch/arm/mach-omap2/clockdomain.c
@@ -1224,14 +1224,6 @@ ccd_exit:
 	return 0;
 }
 
-u32 clkdm_xlate_address(struct clockdomain *clkdm)
-{
-	if (arch_clkdm->clkdm_xlate_address)
-		return arch_clkdm->clkdm_xlate_address(clkdm);
-
-	return 0;
-}
-
 /**
  * clkdm_hwmod_enable - add an enabled downstream hwmod to this clkdm
  * @clkdm: struct clockdomain *
diff --git a/arch/arm/mach-omap2/clockdomain.h b/arch/arm/mach-omap2/clockdomain.h
index 827f01e2d0af..24667a5a9dc0 100644
--- a/arch/arm/mach-omap2/clockdomain.h
+++ b/arch/arm/mach-omap2/clockdomain.h
@@ -175,7 +175,6 @@ struct clkdm_ops {
 	void	(*clkdm_deny_idle)(struct clockdomain *clkdm);
 	int	(*clkdm_clk_enable)(struct clockdomain *clkdm);
 	int	(*clkdm_clk_disable)(struct clockdomain *clkdm);
-	u32	(*clkdm_xlate_address)(struct clockdomain *clkdm);
 };
 
 int clkdm_register_platform_funcs(struct clkdm_ops *co);
@@ -214,7 +213,6 @@ int clkdm_clk_enable(struct clockdomain *clkdm, struct clk *clk);
 int clkdm_clk_disable(struct clockdomain *clkdm, struct clk *clk);
 int clkdm_hwmod_enable(struct clockdomain *clkdm, struct omap_hwmod *oh);
 int clkdm_hwmod_disable(struct clockdomain *clkdm, struct omap_hwmod *oh);
-u32 clkdm_xlate_address(struct clockdomain *clkdm);
 
 extern void __init omap242x_clockdomains_init(void);
 extern void __init omap243x_clockdomains_init(void);
diff --git a/arch/arm/mach-omap2/cm-regbits-24xx.h b/arch/arm/mach-omap2/cm-regbits-24xx.h
index d7a5d11cbcbf..9ff0fc70f152 100644
--- a/arch/arm/mach-omap2/cm-regbits-24xx.h
+++ b/arch/arm/mach-omap2/cm-regbits-24xx.h
@@ -14,38 +14,8 @@
  * published by the Free Software Foundation.
  */
 
-#define OMAP24XX_EN_CAM_SHIFT				31
-#define OMAP24XX_EN_WDT4_SHIFT				29
-#define OMAP2420_EN_WDT3_SHIFT				28
-#define OMAP24XX_EN_MSPRO_SHIFT				27
-#define OMAP24XX_EN_FAC_SHIFT				25
-#define OMAP2420_EN_EAC_SHIFT				24
-#define OMAP24XX_EN_HDQ_SHIFT				23
-#define OMAP2420_EN_I2C2_SHIFT				20
-#define OMAP2420_EN_I2C1_SHIFT				19
-#define OMAP2430_EN_MCBSP5_SHIFT			5
-#define OMAP2430_EN_MCBSP4_SHIFT			4
-#define OMAP2430_EN_MCBSP3_SHIFT			3
-#define OMAP24XX_EN_SSI_SHIFT				1
-#define OMAP24XX_EN_MPU_WDT_SHIFT			3
-#define OMAP24XX_CLKSEL_MPU_SHIFT			0
-#define OMAP24XX_CLKSEL_MPU_WIDTH			5
 #define OMAP24XX_AUTOSTATE_MPU_MASK			(1 << 0)
-#define OMAP24XX_EN_TV_SHIFT				2
-#define OMAP24XX_EN_DSS2_SHIFT				1
-#define OMAP24XX_EN_DSS1_SHIFT				0
 #define OMAP24XX_EN_DSS1_MASK				(1 << 0)
-#define OMAP2430_EN_I2CHS2_SHIFT			20
-#define OMAP2430_EN_I2CHS1_SHIFT			19
-#define OMAP2430_EN_MMCHSDB2_SHIFT			17
-#define OMAP2430_EN_MMCHSDB1_SHIFT			16
-#define OMAP24XX_EN_MAILBOXES_SHIFT			30
-#define OMAP2430_EN_SDRC_SHIFT				2
-#define OMAP24XX_EN_PKA_SHIFT				4
-#define OMAP24XX_EN_AES_SHIFT				3
-#define OMAP24XX_EN_RNG_SHIFT				2
-#define OMAP24XX_EN_SHA_SHIFT				1
-#define OMAP24XX_EN_DES_SHIFT				0
 #define OMAP24XX_ST_MAILBOXES_SHIFT			30
 #define OMAP24XX_ST_HDQ_SHIFT				23
 #define OMAP2420_ST_I2C2_SHIFT				20
@@ -54,81 +24,30 @@
 #define OMAP2430_ST_I2CHS2_SHIFT			20
 #define OMAP24XX_ST_MCBSP2_SHIFT			16
 #define OMAP24XX_ST_MCBSP1_SHIFT			15
-#define OMAP24XX_ST_DSS_SHIFT				0
 #define OMAP2430_ST_MCBSP5_SHIFT			5
 #define OMAP2430_ST_MCBSP4_SHIFT			4
 #define OMAP2430_ST_MCBSP3_SHIFT			3
 #define OMAP24XX_ST_AES_SHIFT				3
 #define OMAP24XX_ST_RNG_SHIFT				2
 #define OMAP24XX_ST_SHA_SHIFT				1
-#define OMAP24XX_AUTO_SDRC_SHIFT			2
-#define OMAP24XX_AUTO_GPMC_SHIFT			1
-#define OMAP24XX_AUTO_SDMA_SHIFT			0
-#define OMAP24XX_CLKSEL_USB_MASK			(0x7 << 25)
-#define OMAP24XX_CLKSEL_SSI_MASK			(0x1f << 20)
-#define OMAP2420_CLKSEL_VLYNQ_MASK			(0x1f << 15)
 #define OMAP24XX_CLKSEL_DSS2_MASK			(0x1 << 13)
-#define OMAP24XX_CLKSEL_DSS1_MASK			(0x1f << 8)
-#define OMAP24XX_CLKSEL_L4_SHIFT			5
-#define OMAP24XX_CLKSEL_L4_WIDTH			2
-#define OMAP24XX_CLKSEL_L3_SHIFT			0
-#define OMAP24XX_CLKSEL_L3_WIDTH			5
-#define OMAP24XX_CLKSEL_GPT12_MASK			(0x3 << 22)
-#define OMAP24XX_CLKSEL_GPT11_MASK			(0x3 << 20)
-#define OMAP24XX_CLKSEL_GPT10_MASK			(0x3 << 18)
-#define OMAP24XX_CLKSEL_GPT9_MASK			(0x3 << 16)
-#define OMAP24XX_CLKSEL_GPT8_MASK			(0x3 << 14)
-#define OMAP24XX_CLKSEL_GPT7_MASK			(0x3 << 12)
-#define OMAP24XX_CLKSEL_GPT6_MASK			(0x3 << 10)
-#define OMAP24XX_CLKSEL_GPT5_MASK			(0x3 << 8)
-#define OMAP24XX_CLKSEL_GPT4_MASK			(0x3 << 6)
-#define OMAP24XX_CLKSEL_GPT3_MASK			(0x3 << 4)
-#define OMAP24XX_CLKSEL_GPT2_MASK			(0x3 << 2)
 #define OMAP24XX_AUTOSTATE_DSS_MASK			(1 << 2)
 #define OMAP24XX_AUTOSTATE_L4_MASK			(1 << 1)
 #define OMAP24XX_AUTOSTATE_L3_MASK			(1 << 0)
-#define OMAP24XX_EN_3D_SHIFT				2
-#define OMAP24XX_EN_2D_SHIFT				1
 #define OMAP24XX_AUTOSTATE_GFX_MASK			(1 << 0)
-#define OMAP2430_EN_ICR_SHIFT				6
-#define OMAP24XX_EN_OMAPCTRL_SHIFT			5
-#define OMAP24XX_EN_WDT1_SHIFT				4
-#define OMAP24XX_EN_32KSYNC_SHIFT			1
 #define OMAP24XX_ST_MPU_WDT_SHIFT			3
 #define OMAP24XX_ST_32KSYNC_SHIFT			1
-#define OMAP24XX_CLKSEL_GPT1_MASK			(0x3 << 0)
 #define OMAP24XX_EN_54M_PLL_SHIFT			6
 #define OMAP24XX_EN_96M_PLL_SHIFT			2
-#define OMAP24XX_EN_DPLL_MASK				(0x3 << 0)
 #define OMAP24XX_ST_54M_APLL_SHIFT			9
 #define OMAP24XX_ST_96M_APLL_SHIFT			8
 #define OMAP24XX_AUTO_54M_MASK				(0x3 << 6)
 #define OMAP24XX_AUTO_96M_MASK				(0x3 << 2)
 #define OMAP24XX_AUTO_DPLL_SHIFT			0
 #define OMAP24XX_AUTO_DPLL_MASK				(0x3 << 0)
-#define OMAP24XX_APLLS_CLKIN_SHIFT			23
-#define OMAP24XX_APLLS_CLKIN_WIDTH			3
-#define OMAP24XX_APLLS_CLKIN_MASK			(0x7 << 23)
-#define OMAP24XX_DPLL_MULT_MASK				(0x3ff << 12)
-#define OMAP24XX_DPLL_DIV_MASK				(0xf << 8)
-#define OMAP24XX_54M_SOURCE_SHIFT			5
-#define OMAP24XX_54M_SOURCE_WIDTH			1
-#define OMAP2430_96M_SOURCE_SHIFT			4
-#define OMAP2430_96M_SOURCE_WIDTH			1
-#define OMAP24XX_48M_SOURCE_MASK			(1 << 3)
 #define OMAP24XX_CORE_CLK_SRC_MASK			(0x3 << 0)
-#define OMAP2420_EN_IVA_COP_SHIFT			10
-#define OMAP2420_EN_IVA_MPU_SHIFT			8
-#define OMAP24XX_CM_FCLKEN_DSP_EN_DSP_SHIFT		0
-#define OMAP2420_EN_DSP_IPI_SHIFT			1
-#define OMAP2420_CLKSEL_IVA_MASK			(0x1f << 8)
-#define OMAP24XX_CLKSEL_DSP_IF_MASK			(0x3 << 5)
-#define OMAP24XX_CLKSEL_DSP_MASK			(0x1f << 0)
 #define OMAP2420_AUTOSTATE_IVA_MASK			(1 << 8)
 #define OMAP24XX_AUTOSTATE_DSP_MASK			(1 << 0)
-#define OMAP2430_EN_OSC_SHIFT				1
-#define OMAP2430_CM_ICLKEN_MDM_EN_MDM_SHIFT		0
-#define OMAP2430_CLKSEL_MDM_MASK			(0xf << 0)
 #define OMAP2430_AUTOSTATE_MDM_MASK			(1 << 0)
 #define OMAP24XX_CLKSTCTRL_DISABLE_AUTO		0x0
 #define OMAP24XX_CLKSTCTRL_ENABLE_AUTO		0x1
diff --git a/arch/arm/mach-omap2/cm-regbits-34xx.h b/arch/arm/mach-omap2/cm-regbits-34xx.h
index ee6c784cd6b7..38656ce2432c 100644
--- a/arch/arm/mach-omap2/cm-regbits-34xx.h
+++ b/arch/arm/mach-omap2/cm-regbits-34xx.h
@@ -14,68 +14,11 @@
  * published by the Free Software Foundation.
  */
 
-#define OMAP3430ES2_EN_MMC3_SHIFT			30
-#define OMAP3430_EN_MSPRO_SHIFT				23
-#define OMAP3430_EN_HDQ_SHIFT				22
-#define OMAP3430ES1_EN_FSHOSTUSB_SHIFT			5
-#define OMAP3430ES1_EN_D2D_SHIFT			3
-#define OMAP3430_EN_SSI_SHIFT				0
-#define OMAP3430ES2_EN_USBTLL_SHIFT			2
-#define OMAP3430_EN_WDT2_SHIFT				5
-#define OMAP3430_EN_CAM_SHIFT				0
-#define OMAP3430_EN_WDT3_SHIFT				12
 #define OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_MASK		(1 << 0)
-#define OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_SHIFT		0
-#define OMAP3430_IVA2_DPLL_FREQSEL_SHIFT		4
-#define OMAP3430_IVA2_DPLL_FREQSEL_MASK			(0xf << 4)
-#define OMAP3430_EN_IVA2_DPLL_DRIFTGUARD_SHIFT		3
-#define OMAP3430_EN_IVA2_DPLL_SHIFT			0
-#define OMAP3430_EN_IVA2_DPLL_MASK			(0x7 << 0)
 #define OMAP3430_ST_IVA2_SHIFT				0
-#define OMAP3430_ST_IVA2_CLK_MASK			(1 << 0)
-#define OMAP3430_AUTO_IVA2_DPLL_SHIFT			0
-#define OMAP3430_AUTO_IVA2_DPLL_MASK			(0x7 << 0)
-#define OMAP3430_IVA2_CLK_SRC_SHIFT			19
-#define OMAP3430_IVA2_CLK_SRC_WIDTH			3
-#define OMAP3430_IVA2_DPLL_MULT_MASK			(0x7ff << 8)
-#define OMAP3430_IVA2_DPLL_DIV_MASK			(0x7f << 0)
-#define OMAP3430_IVA2_DPLL_CLKOUT_DIV_SHIFT		0
-#define OMAP3430_IVA2_DPLL_CLKOUT_DIV_WIDTH		5
 #define OMAP3430_CLKTRCTRL_IVA2_MASK			(0x3 << 0)
 #define OMAP3430_CLKACTIVITY_IVA2_MASK			(1 << 0)
-#define OMAP3430_MPU_DPLL_FREQSEL_MASK			(0xf << 4)
-#define OMAP3430_EN_MPU_DPLL_DRIFTGUARD_SHIFT		3
-#define OMAP3430_EN_MPU_DPLL_MASK			(0x7 << 0)
-#define OMAP3430_ST_MPU_CLK_SHIFT			0
-#define OMAP3430_ST_MPU_CLK_MASK			(1 << 0)
-#define OMAP3430_ST_MPU_CLK_WIDTH			1
-#define OMAP3430_AUTO_MPU_DPLL_MASK			(0x7 << 0)
-#define OMAP3430_MPU_CLK_SRC_SHIFT			19
-#define OMAP3430_MPU_CLK_SRC_WIDTH			3
-#define OMAP3430_MPU_DPLL_MULT_MASK			(0x7ff << 8)
-#define OMAP3430_MPU_DPLL_DIV_MASK			(0x7f << 0)
-#define OMAP3430_MPU_DPLL_CLKOUT_DIV_SHIFT		0
-#define OMAP3430_MPU_DPLL_CLKOUT_DIV_WIDTH		5
 #define OMAP3430_CLKTRCTRL_MPU_MASK			(0x3 << 0)
-#define OMAP3430_EN_MODEM_SHIFT				31
-#define OMAP3430_EN_ICR_SHIFT				29
-#define OMAP3430_EN_AES2_SHIFT				28
-#define OMAP3430_EN_SHA12_SHIFT				27
-#define OMAP3430_EN_DES2_SHIFT				26
-#define OMAP3430ES1_EN_FAC_SHIFT			8
-#define OMAP3430_EN_MAILBOXES_SHIFT			7
-#define OMAP3430_EN_OMAPCTRL_SHIFT			6
-#define OMAP3430_EN_SAD2D_SHIFT				3
-#define OMAP3430_EN_SDRC_SHIFT				1
-#define AM35XX_EN_IPSS_SHIFT				4
-#define OMAP3430_EN_PKA_SHIFT				4
-#define OMAP3430_EN_AES1_SHIFT				3
-#define OMAP3430_EN_RNG_SHIFT				2
-#define OMAP3430_EN_SHA11_SHIFT				1
-#define OMAP3430_EN_DES1_SHIFT				0
-#define OMAP3430_EN_MAD2D_SHIFT				3
-#define OMAP3430ES2_EN_TS_SHIFT				1
-#define OMAP3430ES2_EN_CPEFUSE_SHIFT			0
 #define OMAP3430_ST_AES2_SHIFT				28
 #define OMAP3430_ST_SHA12_SHIFT				27
 #define AM35XX_ST_UART4_SHIFT				23
@@ -84,131 +27,26 @@
 #define OMAP3430_ST_MAILBOXES_SHIFT			7
 #define OMAP3430_ST_SAD2D_SHIFT				3
 #define OMAP3430_ST_SDMA_SHIFT				2
-#define AM35XX_ST_IPSS_SHIFT				5
 #define OMAP3430ES2_ST_USBTLL_SHIFT			2
-#define OMAP3430_CLKSEL_SSI_MASK			(0xf << 8)
-#define OMAP3430_CLKSEL_GPT11_MASK			(1 << 7)
-#define OMAP3430_CLKSEL_GPT10_MASK			(1 << 6)
-#define OMAP3430ES1_CLKSEL_FSHOSTUSB_MASK		(0x3 << 4)
-#define OMAP3430_CLKSEL_L4_SHIFT			2
-#define OMAP3430_CLKSEL_L4_WIDTH			2
-#define OMAP3430_CLKSEL_L3_SHIFT			0
-#define OMAP3430_CLKSEL_L3_WIDTH			2
-#define OMAP3630_CLKSEL_96M_MASK			(0x3 << 12)
 #define OMAP3430ES1_CLKTRCTRL_D2D_MASK			(0x3 << 4)
 #define OMAP3430_CLKTRCTRL_L4_MASK			(0x3 << 2)
 #define OMAP3430_CLKTRCTRL_L3_MASK			(0x3 << 0)
-#define OMAP3430ES1_EN_3D_SHIFT				2
-#define OMAP3430ES1_EN_2D_SHIFT				1
 #define OMAP3430ES1_CLKTRCTRL_GFX_MASK			(0x3 << 0)
-#define OMAP3430ES2_CM_FCLKEN_SGX_EN_SGX_SHIFT		1
-#define OMAP3430ES2_CM_ICLKEN_SGX_EN_SGX_SHIFT		0
-#define OMAP3430ES2_CLKSEL_SGX_MASK			(0x7 << 0)
 #define OMAP3430ES2_CLKTRCTRL_SGX_MASK			(0x3 << 0)
-#define OMAP3430ES2_EN_USIMOCP_SHIFT			9
-#define OMAP3430_EN_WDT1_SHIFT				4
-#define OMAP3430_EN_32KSYNC_SHIFT			2
 #define OMAP3430_ST_WDT2_SHIFT				5
 #define OMAP3430_ST_32KSYNC_SHIFT			2
-#define OMAP3430ES2_CLKSEL_USIMOCP_MASK			(0xf << 3)
-#define OMAP3430_CLKSEL_RM_SHIFT			1
-#define OMAP3430_CLKSEL_RM_WIDTH			2
-#define OMAP3430_CLKSEL_GPT1_MASK			(1 << 0)
-#define OMAP3430_PWRDN_EMU_PERIPH_SHIFT			31
-#define OMAP3430_PWRDN_CAM_SHIFT			30
-#define OMAP3430_PWRDN_DSS1_SHIFT			29
-#define OMAP3430_PWRDN_TV_SHIFT				28
-#define OMAP3430_PWRDN_96M_SHIFT			27
-#define OMAP3430_PERIPH_DPLL_FREQSEL_MASK		(0xf << 20)
-#define OMAP3430_EN_PERIPH_DPLL_DRIFTGUARD_SHIFT	19
-#define OMAP3430_EN_PERIPH_DPLL_MASK			(0x7 << 16)
-#define OMAP3430_PWRDN_EMU_CORE_SHIFT			12
-#define OMAP3430_CORE_DPLL_FREQSEL_MASK			(0xf << 4)
-#define OMAP3430_EN_CORE_DPLL_DRIFTGUARD_SHIFT		3
-#define OMAP3430_EN_CORE_DPLL_MASK			(0x7 << 0)
-#define OMAP3430ES2_PERIPH2_DPLL_FREQSEL_MASK		(0xf << 4)
-#define OMAP3430ES2_EN_PERIPH2_DPLL_DRIFTGUARD_SHIFT	3
-#define OMAP3430ES2_EN_PERIPH2_DPLL_MASK		(0x7 << 0)
-#define OMAP3430_ST_PERIPH_CLK_MASK			(1 << 1)
-#define OMAP3430_ST_CORE_CLK_MASK			(1 << 0)
-#define OMAP3430ES2_ST_PERIPH2_CLK_MASK			(1 << 0)
 #define OMAP3430_AUTO_PERIPH_DPLL_MASK			(0x7 << 3)
-#define OMAP3430_AUTO_CORE_DPLL_MASK			(0x7 << 0)
-#define OMAP3430ES2_AUTO_PERIPH2_DPLL_MASK		(0x7 << 0)
-#define OMAP3430_CORE_DPLL_CLKOUT_DIV_SHIFT		27
-#define OMAP3430_CORE_DPLL_CLKOUT_DIV_WIDTH		5
-#define OMAP3430_CORE_DPLL_MULT_MASK			(0x7ff << 16)
-#define OMAP3430_CORE_DPLL_DIV_MASK			(0x7f << 8)
-#define OMAP3430_SOURCE_96M_SHIFT			6
-#define OMAP3430_SOURCE_96M_WIDTH			1
-#define OMAP3430_SOURCE_54M_SHIFT			5
-#define OMAP3430_SOURCE_54M_WIDTH			1
-#define OMAP3430_SOURCE_48M_MASK			(1 << 3)
-#define OMAP3430_PERIPH_DPLL_MULT_MASK			(0x7ff << 8)
-#define OMAP3630_PERIPH_DPLL_MULT_MASK			(0xfff << 8)
-#define OMAP3430_PERIPH_DPLL_DIV_MASK			(0x7f << 0)
-#define OMAP3630_PERIPH_DPLL_DCO_SEL_MASK		(0x7 << 21)
-#define OMAP3630_PERIPH_DPLL_SD_DIV_MASK		(0xff << 24)
-#define OMAP3430_DIV_96M_SHIFT				0
-#define OMAP3630_DIV_96M_WIDTH				6
-#define OMAP3430ES2_PERIPH2_DPLL_MULT_MASK		(0x7ff << 8)
-#define OMAP3430ES2_PERIPH2_DPLL_DIV_MASK		(0x7f << 0)
-#define OMAP3430ES2_DIV_120M_SHIFT			0
-#define OMAP3430ES2_DIV_120M_WIDTH			5
-#define OMAP3430_CLKOUT2_EN_SHIFT			7
-#define OMAP3430_CLKOUT2_DIV_SHIFT			3
-#define OMAP3430_CLKOUT2_DIV_WIDTH			3
-#define OMAP3430_CLKOUT2SOURCE_MASK			(0x3 << 0)
-#define OMAP3430_EN_TV_SHIFT				2
-#define OMAP3430_EN_DSS2_SHIFT				1
-#define OMAP3430_EN_DSS1_SHIFT				0
-#define OMAP3430_CM_ICLKEN_DSS_EN_DSS_SHIFT		0
 #define OMAP3430ES2_ST_DSS_IDLE_SHIFT			1
-#define OMAP3430ES2_ST_DSS_STDBY_SHIFT			0
-#define OMAP3430ES1_ST_DSS_SHIFT			0
-#define OMAP3430_CLKSEL_TV_SHIFT			8
-#define OMAP3630_CLKSEL_TV_WIDTH			6
-#define OMAP3430_CLKSEL_DSS1_SHIFT			0
-#define OMAP3630_CLKSEL_DSS1_WIDTH			6
 #define OMAP3430_CLKTRCTRL_DSS_MASK			(0x3 << 0)
-#define OMAP3430_EN_CSI2_SHIFT				1
-#define OMAP3430_CLKSEL_CAM_SHIFT			0
-#define OMAP3630_CLKSEL_CAM_WIDTH			6
 #define OMAP3430_CLKTRCTRL_CAM_MASK			(0x3 << 0)
 #define OMAP3430_ST_MCBSP4_SHIFT			2
 #define OMAP3430_ST_MCBSP3_SHIFT			1
 #define OMAP3430_ST_MCBSP2_SHIFT			0
-#define OMAP3430_CLKSEL_GPT9_MASK			(1 << 7)
-#define OMAP3430_CLKSEL_GPT8_MASK			(1 << 6)
-#define OMAP3430_CLKSEL_GPT7_MASK			(1 << 5)
-#define OMAP3430_CLKSEL_GPT6_MASK			(1 << 4)
-#define OMAP3430_CLKSEL_GPT5_MASK			(1 << 3)
-#define OMAP3430_CLKSEL_GPT4_MASK			(1 << 2)
-#define OMAP3430_CLKSEL_GPT3_MASK			(1 << 1)
-#define OMAP3430_CLKSEL_GPT2_MASK			(1 << 0)
 #define OMAP3430_CLKTRCTRL_PER_MASK			(0x3 << 0)
-#define OMAP3430_DIV_DPLL4_SHIFT			24
-#define OMAP3630_DIV_DPLL4_WIDTH			6
-#define OMAP3430_DIV_DPLL3_SHIFT			16
-#define OMAP3430_DIV_DPLL3_WIDTH			5
-#define OMAP3430_CLKSEL_TRACECLK_SHIFT			11
-#define OMAP3430_CLKSEL_TRACECLK_WIDTH			3
-#define OMAP3430_CLKSEL_PCLK_SHIFT			8
-#define OMAP3430_CLKSEL_PCLK_WIDTH			3
-#define OMAP3430_CLKSEL_PCLKX2_SHIFT			6
-#define OMAP3430_CLKSEL_PCLKX2_WIDTH			2
-#define OMAP3430_CLKSEL_ATCLK_SHIFT			4
-#define OMAP3430_CLKSEL_ATCLK_WIDTH			2
-#define OMAP3430_TRACE_MUX_CTRL_SHIFT			2
-#define OMAP3430_TRACE_MUX_CTRL_WIDTH			2
-#define OMAP3430_MUX_CTRL_MASK				(0x3 << 0)
 #define OMAP3430_CLKTRCTRL_EMU_MASK			(0x3 << 0)
 #define OMAP3430_CLKTRCTRL_NEON_MASK			(0x3 << 0)
 #define OMAP3430ES2_EN_USBHOST2_SHIFT			1
-#define OMAP3430ES2_EN_USBHOST1_SHIFT			0
-#define OMAP3430ES2_EN_USBHOST_SHIFT			0
 #define OMAP3430ES2_ST_USBHOST_IDLE_SHIFT		1
-#define OMAP3430ES2_ST_USBHOST_STDBY_SHIFT		0
 #define OMAP3430ES2_CLKTRCTRL_USBHOST_MASK		(3 << 0)
 #define OMAP34XX_CLKSTCTRL_DISABLE_AUTO		0x0
 #define OMAP34XX_CLKSTCTRL_FORCE_SLEEP		0x1
diff --git a/arch/arm/mach-omap2/cm.h b/arch/arm/mach-omap2/cm.h
index e833984cc85e..b19e83d53501 100644
--- a/arch/arm/mach-omap2/cm.h
+++ b/arch/arm/mach-omap2/cm.h
@@ -52,6 +52,7 @@ extern void omap2_set_globals_cm(void __iomem *cm, void __iomem *cm2);
  * @wait_module_idle: ptr to the SoC CM-specific wait_module_idle impl
  * @module_enable: ptr to the SoC CM-specific module_enable impl
  * @module_disable: ptr to the SoC CM-specific module_disable impl
+ * @xlate_clkctrl: ptr to the SoC CM-specific clkctrl xlate addr impl
  */
 struct cm_ll_data {
 	int (*split_idlest_reg)(struct clk_omap_reg *idlest_reg, s16 *prcm_inst,
@@ -62,6 +63,7 @@ struct cm_ll_data {
 				u8 idlest_shift);
 	void (*module_enable)(u8 mode, u8 part, u16 inst, u16 clkctrl_offs);
 	void (*module_disable)(u8 part, u16 inst, u16 clkctrl_offs);
+	u32 (*xlate_clkctrl)(u8 part, u16 inst, u16 clkctrl_offs);
 };
 
 extern int cm_split_idlest_reg(struct clk_omap_reg *idlest_reg, s16 *prcm_inst,
@@ -72,8 +74,9 @@ int omap_cm_wait_module_idle(u8 part, s16 prcm_mod, u16 idlest_reg,
 			     u8 idlest_shift);
 int omap_cm_module_enable(u8 mode, u8 part, u16 inst, u16 clkctrl_offs);
 int omap_cm_module_disable(u8 part, u16 inst, u16 clkctrl_offs);
-extern int cm_register(struct cm_ll_data *cld);
-extern int cm_unregister(struct cm_ll_data *cld);
+u32 omap_cm_xlate_clkctrl(u8 part, u16 inst, u16 clkctrl_offs);
+extern int cm_register(const struct cm_ll_data *cld);
+extern int cm_unregister(const struct cm_ll_data *cld);
 int omap_cm_init(void);
 int omap2_cm_base_init(void);
 
diff --git a/arch/arm/mach-omap2/cm2xxx.c b/arch/arm/mach-omap2/cm2xxx.c
index cd90b4c6a06b..d5b87f42a96e 100644
--- a/arch/arm/mach-omap2/cm2xxx.c
+++ b/arch/arm/mach-omap2/cm2xxx.c
@@ -385,7 +385,7 @@ void omap2xxx_cm_set_mod_dividers(u32 mpu, u32 dsp, u32 gfx, u32 core, u32 mdm)
  *
  */
 
-static struct cm_ll_data omap2xxx_cm_ll_data = {
+static const struct cm_ll_data omap2xxx_cm_ll_data = {
 	.split_idlest_reg	= &omap2xxx_cm_split_idlest_reg,
 	.wait_module_ready	= &omap2xxx_cm_wait_module_ready,
 };
diff --git a/arch/arm/mach-omap2/cm33xx.c b/arch/arm/mach-omap2/cm33xx.c
index a9e08d89104e..1cc0247a2cb5 100644
--- a/arch/arm/mach-omap2/cm33xx.c
+++ b/arch/arm/mach-omap2/cm33xx.c
@@ -333,6 +333,11 @@ static int am33xx_clkdm_clk_disable(struct clockdomain *clkdm)
 	return 0;
 }
 
+static u32 am33xx_cm_xlate_clkctrl(u8 part, u16 inst, u16 offset)
+{
+	return cm_base.pa + inst + offset;
+}
+
 struct clkdm_ops am33xx_clkdm_operations = {
 	.clkdm_sleep		= am33xx_clkdm_sleep,
 	.clkdm_wakeup		= am33xx_clkdm_wakeup,
@@ -342,11 +347,12 @@ struct clkdm_ops am33xx_clkdm_operations = {
 	.clkdm_clk_disable	= am33xx_clkdm_clk_disable,
 };
 
-static struct cm_ll_data am33xx_cm_ll_data = {
+static const struct cm_ll_data am33xx_cm_ll_data = {
 	.wait_module_ready	= &am33xx_cm_wait_module_ready,
 	.wait_module_idle	= &am33xx_cm_wait_module_idle,
 	.module_enable		= &am33xx_cm_module_enable,
 	.module_disable		= &am33xx_cm_module_disable,
+	.xlate_clkctrl		= &am33xx_cm_xlate_clkctrl,
 };
 
 int __init am33xx_cm_init(const struct omap_prcm_init_data *data)
diff --git a/arch/arm/mach-omap2/cm3xxx.c b/arch/arm/mach-omap2/cm3xxx.c
index 961bc478b9de..ec580fd094a6 100644
--- a/arch/arm/mach-omap2/cm3xxx.c
+++ b/arch/arm/mach-omap2/cm3xxx.c
@@ -662,7 +662,7 @@ void omap3_cm_save_scratchpad_contents(u32 *ptr)
  *
  */
 
-static struct cm_ll_data omap3xxx_cm_ll_data = {
+static const struct cm_ll_data omap3xxx_cm_ll_data = {
 	.split_idlest_reg	= &omap3xxx_cm_split_idlest_reg,
 	.wait_module_ready	= &omap3xxx_cm_wait_module_ready,
 };
diff --git a/arch/arm/mach-omap2/cm_common.c b/arch/arm/mach-omap2/cm_common.c
index d555791cf349..aff747ecad51 100644
--- a/arch/arm/mach-omap2/cm_common.c
+++ b/arch/arm/mach-omap2/cm_common.c
@@ -29,7 +29,7 @@
  * common CM functions
  */
 static struct cm_ll_data null_cm_ll_data;
-static struct cm_ll_data *cm_ll_data = &null_cm_ll_data;
+static const struct cm_ll_data *cm_ll_data = &null_cm_ll_data;
 
 /* cm_base: base virtual address of the CM IP block */
 struct omap_domain_base cm_base;
@@ -68,14 +68,17 @@ void __init omap2_set_globals_cm(void __iomem *cm, void __iomem *cm2)
 int cm_split_idlest_reg(struct clk_omap_reg *idlest_reg, s16 *prcm_inst,
 			u8 *idlest_reg_id)
 {
+	int ret;
 	if (!cm_ll_data->split_idlest_reg) {
 		WARN_ONCE(1, "cm: %s: no low-level function defined\n",
 			  __func__);
 		return -EINVAL;
 	}
 
-	return cm_ll_data->split_idlest_reg(idlest_reg, prcm_inst,
+	ret = cm_ll_data->split_idlest_reg(idlest_reg, prcm_inst,
 					   idlest_reg_id);
+	*prcm_inst -= cm_base.offset;
+	return ret;
 }
 
 /**
@@ -175,6 +178,16 @@ int omap_cm_module_disable(u8 part, u16 inst, u16 clkctrl_offs)
 	return 0;
 }
 
+u32 omap_cm_xlate_clkctrl(u8 part, u16 inst, u16 clkctrl_offs)
+{
+	if (!cm_ll_data->xlate_clkctrl) {
+		WARN_ONCE(1, "cm: %s: no low-level function defined\n",
+			  __func__);
+		return 0;
+	}
+	return cm_ll_data->xlate_clkctrl(part, inst, clkctrl_offs);
+}
+
 /**
  * cm_register - register per-SoC low-level data with the CM
  * @cld: low-level per-SoC OMAP CM data & function pointers to register
@@ -186,7 +199,7 @@ int omap_cm_module_disable(u8 part, u16 inst, u16 clkctrl_offs)
  * is NULL, or -EEXIST if cm_register() has already been called
  * without an intervening cm_unregister().
  */
-int cm_register(struct cm_ll_data *cld)
+int cm_register(const struct cm_ll_data *cld)
 {
 	if (!cld)
 		return -EINVAL;
@@ -210,7 +223,7 @@ int cm_register(struct cm_ll_data *cld)
  * -EINVAL if @cld is NULL or if @cld does not match the struct
  * cm_ll_data * previously registered by cm_register().
  */
-int cm_unregister(struct cm_ll_data *cld)
+int cm_unregister(const struct cm_ll_data *cld)
 {
 	if (!cld || cm_ll_data != cld)
 		return -EINVAL;
@@ -337,6 +350,7 @@ int __init omap2_cm_base_init(void)
 		if (mem) {
 			mem->pa = res.start + data->offset;
 			mem->va = data->mem + data->offset;
+			mem->offset = data->offset;
 		}
 
 		data->np = np;
diff --git a/arch/arm/mach-omap2/cminst44xx.c b/arch/arm/mach-omap2/cminst44xx.c
index 8774e983bea1..7deefee49fc3 100644
--- a/arch/arm/mach-omap2/cminst44xx.c
+++ b/arch/arm/mach-omap2/cminst44xx.c
@@ -476,12 +476,9 @@ static int omap4_clkdm_clk_disable(struct clockdomain *clkdm)
 	return 0;
 }
 
-static u32 omap4_clkdm_xlate_address(struct clockdomain *clkdm)
+static u32 omap4_cminst_xlate_clkctrl(u8 part, u16 inst, u16 offset)
 {
-	u32 addr = _cm_bases[clkdm->prcm_partition].pa + clkdm->cm_inst +
-		clkdm->clkdm_offs;
-
-	return addr;
+	return _cm_bases[part].pa + inst + offset;
 }
 
 struct clkdm_ops omap4_clkdm_operations = {
@@ -499,7 +496,6 @@ struct clkdm_ops omap4_clkdm_operations = {
 	.clkdm_deny_idle	= omap4_clkdm_deny_idle,
 	.clkdm_clk_enable	= omap4_clkdm_clk_enable,
 	.clkdm_clk_disable	= omap4_clkdm_clk_disable,
-	.clkdm_xlate_address	= omap4_clkdm_xlate_address,
 };
 
 struct clkdm_ops am43xx_clkdm_operations = {
@@ -509,14 +505,14 @@ struct clkdm_ops am43xx_clkdm_operations = {
 	.clkdm_deny_idle	= omap4_clkdm_deny_idle,
 	.clkdm_clk_enable	= omap4_clkdm_clk_enable,
 	.clkdm_clk_disable	= omap4_clkdm_clk_disable,
-	.clkdm_xlate_address	= omap4_clkdm_xlate_address,
 };
 
-static struct cm_ll_data omap4xxx_cm_ll_data = {
+static const struct cm_ll_data omap4xxx_cm_ll_data = {
 	.wait_module_ready	= &omap4_cminst_wait_module_ready,
 	.wait_module_idle	= &omap4_cminst_wait_module_idle,
 	.module_enable		= &omap4_cminst_module_enable,
 	.module_disable		= &omap4_cminst_module_disable,
+	.xlate_clkctrl		= &omap4_cminst_xlate_clkctrl,
 };
 
 int __init omap4_cm_init(const struct omap_prcm_init_data *data)
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
deleted file mode 100644
index 2944af820558..000000000000
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ /dev/null
@@ -1,409 +0,0 @@
-/*
- * linux/arch/arm/mach-omap2/gpmc-onenand.c
- *
- * Copyright (C) 2006 - 2009 Nokia Corporation
- * Contacts:	Juha Yrjola
- *		Tony Lindgren
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/onenand_regs.h>
-#include <linux/io.h>
-#include <linux/omap-gpmc.h>
-#include <linux/platform_data/mtd-onenand-omap2.h>
-#include <linux/err.h>
-
-#include <asm/mach/flash.h>
-
-#include "soc.h"
-
-#define	ONENAND_IO_SIZE	SZ_128K
-
-#define	ONENAND_FLAG_SYNCREAD	(1 << 0)
-#define	ONENAND_FLAG_SYNCWRITE	(1 << 1)
-#define	ONENAND_FLAG_HF		(1 << 2)
-#define	ONENAND_FLAG_VHF	(1 << 3)
-
-static unsigned onenand_flags;
-static unsigned latency;
-
-static struct omap_onenand_platform_data *gpmc_onenand_data;
-
-static struct resource gpmc_onenand_resource = {
-	.flags		= IORESOURCE_MEM,
-};
-
-static struct platform_device gpmc_onenand_device = {
-	.name		= "omap2-onenand",
-	.id		= -1,
-	.num_resources	= 1,
-	.resource	= &gpmc_onenand_resource,
-};
-
-static struct gpmc_settings onenand_async = {
-	.device_width	= GPMC_DEVWIDTH_16BIT,
-	.mux_add_data	= GPMC_MUX_AD,
-};
-
-static struct gpmc_settings onenand_sync = {
-	.burst_read	= true,
-	.burst_wrap	= true,
-	.burst_len	= GPMC_BURST_16,
-	.device_width	= GPMC_DEVWIDTH_16BIT,
-	.mux_add_data	= GPMC_MUX_AD,
-	.wait_pin	= 0,
-};
-
-static void omap2_onenand_calc_async_timings(struct gpmc_timings *t)
-{
-	struct gpmc_device_timings dev_t;
-	const int t_cer = 15;
-	const int t_avdp = 12;
-	const int t_aavdh = 7;
-	const int t_ce = 76;
-	const int t_aa = 76;
-	const int t_oe = 20;
-	const int t_cez = 20; /* max of t_cez, t_oez */
-	const int t_wpl = 40;
-	const int t_wph = 30;
-
-	memset(&dev_t, 0, sizeof(dev_t));
-
-	dev_t.t_avdp_r = max_t(int, t_avdp, t_cer) * 1000;
-	dev_t.t_avdp_w = dev_t.t_avdp_r;
-	dev_t.t_aavdh = t_aavdh * 1000;
-	dev_t.t_aa = t_aa * 1000;
-	dev_t.t_ce = t_ce * 1000;
-	dev_t.t_oe = t_oe * 1000;
-	dev_t.t_cez_r = t_cez * 1000;
-	dev_t.t_cez_w = dev_t.t_cez_r;
-	dev_t.t_wpl = t_wpl * 1000;
-	dev_t.t_wph = t_wph * 1000;
-
-	gpmc_calc_timings(t, &onenand_async, &dev_t);
-}
-
-static void omap2_onenand_set_async_mode(void __iomem *onenand_base)
-{
-	u32 reg;
-
-	/* Ensure sync read and sync write are disabled */
-	reg = readw(onenand_base + ONENAND_REG_SYS_CFG1);
-	reg &= ~ONENAND_SYS_CFG1_SYNC_READ & ~ONENAND_SYS_CFG1_SYNC_WRITE;
-	writew(reg, onenand_base + ONENAND_REG_SYS_CFG1);
-}
-
-static void set_onenand_cfg(void __iomem *onenand_base)
-{
-	u32 reg = ONENAND_SYS_CFG1_RDY | ONENAND_SYS_CFG1_INT;
-
-	reg |=	(latency << ONENAND_SYS_CFG1_BRL_SHIFT) |
-		ONENAND_SYS_CFG1_BL_16;
-	if (onenand_flags & ONENAND_FLAG_SYNCREAD)
-		reg |= ONENAND_SYS_CFG1_SYNC_READ;
-	else
-		reg &= ~ONENAND_SYS_CFG1_SYNC_READ;
-	if (onenand_flags & ONENAND_FLAG_SYNCWRITE)
-		reg |= ONENAND_SYS_CFG1_SYNC_WRITE;
-	else
-		reg &= ~ONENAND_SYS_CFG1_SYNC_WRITE;
-	if (onenand_flags & ONENAND_FLAG_HF)
-		reg |= ONENAND_SYS_CFG1_HF;
-	else
-		reg &= ~ONENAND_SYS_CFG1_HF;
-	if (onenand_flags & ONENAND_FLAG_VHF)
-		reg |= ONENAND_SYS_CFG1_VHF;
-	else
-		reg &= ~ONENAND_SYS_CFG1_VHF;
-
-	writew(reg, onenand_base + ONENAND_REG_SYS_CFG1);
-}
-
-static int omap2_onenand_get_freq(struct omap_onenand_platform_data *cfg,
-				  void __iomem *onenand_base)
-{
-	u16 ver = readw(onenand_base + ONENAND_REG_VERSION_ID);
-	int freq;
-
-	switch ((ver >> 4) & 0xf) {
-	case 0:
-		freq = 40;
-		break;
-	case 1:
-		freq = 54;
-		break;
-	case 2:
-		freq = 66;
-		break;
-	case 3:
-		freq = 83;
-		break;
-	case 4:
-		freq = 104;
-		break;
-	default:
-		pr_err("onenand rate not detected, bad GPMC async timings?\n");
-		freq = 0;
-	}
-
-	return freq;
-}
-
-static void omap2_onenand_calc_sync_timings(struct gpmc_timings *t,
-					    unsigned int flags,
-					    int freq)
-{
-	struct gpmc_device_timings dev_t;
-	const int t_cer  = 15;
-	const int t_avdp = 12;
-	const int t_cez  = 20; /* max of t_cez, t_oez */
-	const int t_wpl  = 40;
-	const int t_wph  = 30;
-	int min_gpmc_clk_period, t_ces, t_avds, t_avdh, t_ach, t_aavdh, t_rdyo;
-	int div, gpmc_clk_ns;
-
-	if (flags & ONENAND_SYNC_READ)
-		onenand_flags = ONENAND_FLAG_SYNCREAD;
-	else if (flags & ONENAND_SYNC_READWRITE)
-		onenand_flags = ONENAND_FLAG_SYNCREAD | ONENAND_FLAG_SYNCWRITE;
-
-	switch (freq) {
-	case 104:
-		min_gpmc_clk_period = 9600; /* 104 MHz */
-		t_ces   = 3;
-		t_avds  = 4;
-		t_avdh  = 2;
-		t_ach   = 3;
-		t_aavdh = 6;
-		t_rdyo  = 6;
-		break;
-	case 83:
-		min_gpmc_clk_period = 12000; /* 83 MHz */
-		t_ces   = 5;
-		t_avds  = 4;
-		t_avdh  = 2;
-		t_ach   = 6;
-		t_aavdh = 6;
-		t_rdyo  = 9;
-		break;
-	case 66:
-		min_gpmc_clk_period = 15000; /* 66 MHz */
-		t_ces   = 6;
-		t_avds  = 5;
-		t_avdh  = 2;
-		t_ach   = 6;
-		t_aavdh = 6;
-		t_rdyo  = 11;
-		break;
-	default:
-		min_gpmc_clk_period = 18500; /* 54 MHz */
-		t_ces   = 7;
-		t_avds  = 7;
-		t_avdh  = 7;
-		t_ach   = 9;
-		t_aavdh = 7;
-		t_rdyo  = 15;
-		onenand_flags &= ~ONENAND_FLAG_SYNCWRITE;
-		break;
-	}
-
-	div = gpmc_calc_divider(min_gpmc_clk_period);
-	gpmc_clk_ns = gpmc_ticks_to_ns(div);
-	if (gpmc_clk_ns < 15) /* >66MHz */
-		onenand_flags |= ONENAND_FLAG_HF;
-	else
-		onenand_flags &= ~ONENAND_FLAG_HF;
-	if (gpmc_clk_ns < 12) /* >83MHz */
-		onenand_flags |= ONENAND_FLAG_VHF;
-	else
-		onenand_flags &= ~ONENAND_FLAG_VHF;
-	if (onenand_flags & ONENAND_FLAG_VHF)
-		latency = 8;
-	else if (onenand_flags & ONENAND_FLAG_HF)
-		latency = 6;
-	else if (gpmc_clk_ns >= 25) /* 40 MHz*/
-		latency = 3;
-	else
-		latency = 4;
-
-	/* Set synchronous read timings */
-	memset(&dev_t, 0, sizeof(dev_t));
-
-	if (onenand_flags & ONENAND_FLAG_SYNCREAD)
-		onenand_sync.sync_read = true;
-	if (onenand_flags & ONENAND_FLAG_SYNCWRITE) {
-		onenand_sync.sync_write = true;
-		onenand_sync.burst_write = true;
-	} else {
-		dev_t.t_avdp_w = max(t_avdp, t_cer) * 1000;
-		dev_t.t_wpl = t_wpl * 1000;
-		dev_t.t_wph = t_wph * 1000;
-		dev_t.t_aavdh = t_aavdh * 1000;
-	}
-	dev_t.ce_xdelay = true;
-	dev_t.avd_xdelay = true;
-	dev_t.oe_xdelay = true;
-	dev_t.we_xdelay = true;
-	dev_t.clk = min_gpmc_clk_period;
-	dev_t.t_bacc = dev_t.clk;
-	dev_t.t_ces = t_ces * 1000;
-	dev_t.t_avds = t_avds * 1000;
-	dev_t.t_avdh = t_avdh * 1000;
-	dev_t.t_ach = t_ach * 1000;
-	dev_t.cyc_iaa = (latency + 1);
-	dev_t.t_cez_r = t_cez * 1000;
-	dev_t.t_cez_w = dev_t.t_cez_r;
-	dev_t.cyc_aavdh_oe = 1;
-	dev_t.t_rdyo = t_rdyo * 1000 + min_gpmc_clk_period;
-
-	gpmc_calc_timings(t, &onenand_sync, &dev_t);
-}
-
-static int omap2_onenand_setup_async(void __iomem *onenand_base)
-{
-	struct gpmc_timings t;
-	int ret;
-
-	/*
-	 * Note that we need to keep sync_write set for the call to
-	 * omap2_onenand_set_async_mode() to work to detect the onenand
-	 * supported clock rate for the sync timings.
-	 */
-	if (gpmc_onenand_data->of_node) {
-		gpmc_read_settings_dt(gpmc_onenand_data->of_node,
-				      &onenand_async);
-		if (onenand_async.sync_read || onenand_async.sync_write) {
-			if (onenand_async.sync_write)
-				gpmc_onenand_data->flags |=
-					ONENAND_SYNC_READWRITE;
-			else
-				gpmc_onenand_data->flags |= ONENAND_SYNC_READ;
-			onenand_async.sync_read = false;
-		}
-	}
-
-	onenand_async.sync_write = true;
-	omap2_onenand_calc_async_timings(&t);
-
-	ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async);
-	if (ret < 0)
-		return ret;
-
-	ret = gpmc_cs_set_timings(gpmc_onenand_data->cs, &t, &onenand_async);
-	if (ret < 0)
-		return ret;
-
-	omap2_onenand_set_async_mode(onenand_base);
-
-	return 0;
-}
-
-static int omap2_onenand_setup_sync(void __iomem *onenand_base, int *freq_ptr)
-{
-	int ret, freq = *freq_ptr;
-	struct gpmc_timings t;
-
-	if (!freq) {
-		/* Very first call freq is not known */
-		freq = omap2_onenand_get_freq(gpmc_onenand_data, onenand_base);
-		if (!freq)
-			return -ENODEV;
-		set_onenand_cfg(onenand_base);
-	}
-
-	if (gpmc_onenand_data->of_node) {
-		gpmc_read_settings_dt(gpmc_onenand_data->of_node,
-				      &onenand_sync);
-	} else {
-		/*
-		 * FIXME: Appears to be legacy code from initial ONENAND commit.
-		 * Unclear what boards this is for and if this can be removed.
-		 */
-		if (!cpu_is_omap34xx())
-			onenand_sync.wait_on_read = true;
-	}
-
-	omap2_onenand_calc_sync_timings(&t, gpmc_onenand_data->flags, freq);
-
-	ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_sync);
-	if (ret < 0)
-		return ret;
-
-	ret = gpmc_cs_set_timings(gpmc_onenand_data->cs, &t, &onenand_sync);
-	if (ret < 0)
-		return ret;
-
-	set_onenand_cfg(onenand_base);
-
-	*freq_ptr = freq;
-
-	return 0;
-}
-
-static int gpmc_onenand_setup(void __iomem *onenand_base, int *freq_ptr)
-{
-	struct device *dev = &gpmc_onenand_device.dev;
-	unsigned l = ONENAND_SYNC_READ | ONENAND_SYNC_READWRITE;
-	int ret;
-
-	ret = omap2_onenand_setup_async(onenand_base);
-	if (ret) {
-		dev_err(dev, "unable to set to async mode\n");
-		return ret;
-	}
-
-	if (!(gpmc_onenand_data->flags & l))
-		return 0;
-
-	ret = omap2_onenand_setup_sync(onenand_base, freq_ptr);
-	if (ret)
-		dev_err(dev, "unable to set to sync mode\n");
-	return ret;
-}
-
-int gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
-{
-	int err;
-	struct device *dev = &gpmc_onenand_device.dev;
-
-	gpmc_onenand_data = _onenand_data;
-	gpmc_onenand_data->onenand_setup = gpmc_onenand_setup;
-	gpmc_onenand_device.dev.platform_data = gpmc_onenand_data;
-
-	if (cpu_is_omap24xx() &&
-			(gpmc_onenand_data->flags & ONENAND_SYNC_READWRITE)) {
-		dev_warn(dev, "OneNAND using only SYNC_READ on 24xx\n");
-		gpmc_onenand_data->flags &= ~ONENAND_SYNC_READWRITE;
-		gpmc_onenand_data->flags |= ONENAND_SYNC_READ;
-	}
-
-	if (cpu_is_omap34xx())
-		gpmc_onenand_data->flags |= ONENAND_IN_OMAP34XX;
-	else
-		gpmc_onenand_data->flags &= ~ONENAND_IN_OMAP34XX;
-
-	err = gpmc_cs_request(gpmc_onenand_data->cs, ONENAND_IO_SIZE,
-				(unsigned long *)&gpmc_onenand_resource.start);
-	if (err < 0) {
-		dev_err(dev, "Cannot request GPMC CS %d, error %d\n",
-			gpmc_onenand_data->cs, err);
-		return err;
-	}
-
-	gpmc_onenand_resource.end = gpmc_onenand_resource.start +
-							ONENAND_IO_SIZE - 1;
-
-	err = platform_device_register(&gpmc_onenand_device);
-	if (err) {
-		dev_err(dev, "Unable to register OneNAND device\n");
-		gpmc_cs_free(gpmc_onenand_data->cs);
-	}
-
-	return err;
-}
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index df2c29edbbcd..68ba5f472f6b 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -657,8 +657,11 @@ void __init dra7xxx_check_revision(void)
 {
 	u32 idcode;
 	u16 hawkeye;
-	u8 rev;
+	u8 rev, package;
+	struct omap_die_id odi;
 
+	omap_get_die_id(&odi);
+	package = (odi.id_2 >> 16) & 0x3;
 	idcode = read_tap_reg(OMAP_TAP_IDCODE);
 	hawkeye = (idcode >> 12) & 0xffff;
 	rev = (idcode >> 28) & 0xff;
@@ -667,7 +670,17 @@ void __init dra7xxx_check_revision(void)
 		switch (rev) {
 		case 0:
 		default:
-			omap_revision = DRA762_REV_ES1_0;
+			switch (package) {
+			case 0x2:
+				omap_revision = DRA762_ABZ_REV_ES1_0;
+				break;
+			case 0x3:
+				omap_revision = DRA762_ACD_REV_ES1_0;
+				break;
+			default:
+				omap_revision = DRA762_REV_ES1_0;
+				break;
+			}
 			break;
 		}
 		break;
diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c
index 5ac122e88f67..fa7f308c9027 100644
--- a/arch/arm/mach-omap2/omap-secure.c
+++ b/arch/arm/mach-omap2/omap-secure.c
@@ -73,6 +73,27 @@ phys_addr_t omap_secure_ram_mempool_base(void)
 	return omap_secure_memblock_base;
 }
 
+#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_PM)
+u32 omap3_save_secure_ram(void __iomem *addr, int size)
+{
+	u32 ret;
+	u32 param[5];
+
+	if (size != OMAP3_SAVE_SECURE_RAM_SZ)
+		return OMAP3_SAVE_SECURE_RAM_SZ;
+
+	param[0] = 4;		/* Number of arguments */
+	param[1] = __pa(addr);	/* Physical address for saving */
+	param[2] = 0;
+	param[3] = 1;
+	param[4] = 1;
+
+	ret = save_secure_ram_context(__pa(param));
+
+	return ret;
+}
+#endif
+
 /**
  * rx51_secure_dispatcher: Routine to dispatch secure PPA API calls
  * @idx: The PPA API index
diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h
index bae263fba640..c509cde71f93 100644
--- a/arch/arm/mach-omap2/omap-secure.h
+++ b/arch/arm/mach-omap2/omap-secure.h
@@ -31,6 +31,8 @@
 /* Maximum Secure memory storage size */
 #define OMAP_SECURE_RAM_STORAGE	(88 * SZ_1K)
 
+#define OMAP3_SAVE_SECURE_RAM_SZ	0x803F
+
 /* Secure low power HAL API index */
 #define OMAP4_HAL_SAVESECURERAM_INDEX	0x1a
 #define OMAP4_HAL_SAVEHW_INDEX		0x1b
@@ -65,6 +67,8 @@ extern u32 omap_smc2(u32 id, u32 falg, u32 pargs);
 extern u32 omap_smc3(u32 id, u32 process, u32 flag, u32 pargs);
 extern phys_addr_t omap_secure_ram_mempool_base(void);
 extern int omap_secure_ram_reserve_memblock(void);
+extern u32 save_secure_ram_context(u32 args_pa);
+extern u32 omap3_save_secure_ram(void __iomem *save_regs, int size);
 
 extern u32 rx51_secure_dispatcher(u32 idx, u32 process, u32 flag, u32 nargs,
 				  u32 arg1, u32 arg2, u32 arg3, u32 arg4);
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index d45cbfdb4be6..f0388058b7da 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -391,10 +391,8 @@ omap_device_copy_resources(struct omap_hwmod *oh,
 	const char *name;
 	int error, irq = 0;
 
-	if (!oh || !oh->od || !oh->od->pdev) {
-		error = -EINVAL;
-		goto error;
-	}
+	if (!oh || !oh->od || !oh->od->pdev)
+		return -EINVAL;
 
 	np = oh->od->pdev->dev.of_node;
 	if (!np) {
@@ -516,8 +514,10 @@ struct platform_device __init *omap_device_build(const char *pdev_name,
 		goto odbs_exit1;
 
 	od = omap_device_alloc(pdev, &oh, 1);
-	if (IS_ERR(od))
+	if (IS_ERR(od)) {
+		ret = PTR_ERR(od);
 		goto odbs_exit1;
+	}
 
 	ret = platform_device_add_data(pdev, pdata, pdata_len);
 	if (ret)
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 104256a5f0f7..124f9af34a15 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -143,6 +143,8 @@
 #include <linux/of_address.h>
 #include <linux/bootmem.h>
 
+#include <linux/platform_data/ti-sysc.h>
+
 #include <asm/system_misc.h>
 
 #include "clock.h"
@@ -185,15 +187,15 @@
 /**
  * struct clkctrl_provider - clkctrl provider mapping data
  * @addr: base address for the provider
- * @offset: base offset for the provider
- * @clkdm: base clockdomain for provider
+ * @size: size of the provider address space
+ * @offset: offset of the provider from PRCM instance base
  * @node: device node associated with the provider
  * @link: list link
  */
 struct clkctrl_provider {
 	u32			addr;
+	u32			size;
 	u16			offset;
-	struct clockdomain	*clkdm;
 	struct device_node	*node;
 	struct list_head	link;
 };
@@ -223,8 +225,7 @@ struct omap_hwmod_soc_ops {
 	void (*update_context_lost)(struct omap_hwmod *oh);
 	int (*get_context_lost)(struct omap_hwmod *oh);
 	int (*disable_direct_prcm)(struct omap_hwmod *oh);
-	u32 (*xlate_clkctrl)(struct omap_hwmod *oh,
-			     struct clkctrl_provider *provider);
+	u32 (*xlate_clkctrl)(struct omap_hwmod *oh);
 };
 
 /* soc_ops: adapts the omap_hwmod code to the currently-booted SoC */
@@ -716,52 +717,35 @@ static const struct of_device_id ti_clkctrl_match_table[] __initconst = {
 	{ }
 };
 
-static int _match_clkdm(struct clockdomain *clkdm, void *user)
-{
-	struct clkctrl_provider *provider = user;
-
-	if (clkdm_xlate_address(clkdm) == provider->addr) {
-		pr_debug("%s: Matched clkdm %s for addr %x (%s)\n", __func__,
-			 clkdm->name, provider->addr,
-			 provider->node->parent->name);
-		provider->clkdm = clkdm;
-
-		return -1;
-	}
-
-	return 0;
-}
-
-static int _setup_clkctrl_provider(struct device_node *np)
+static int __init _setup_clkctrl_provider(struct device_node *np)
 {
 	const __be32 *addrp;
 	struct clkctrl_provider *provider;
+	u64 size;
 
 	provider = memblock_virt_alloc(sizeof(*provider), 0);
 	if (!provider)
 		return -ENOMEM;
 
-	addrp = of_get_address(np, 0, NULL, NULL);
+	addrp = of_get_address(np, 0, &size, NULL);
 	provider->addr = (u32)of_translate_address(np, addrp);
-	provider->offset = provider->addr & 0xff;
+	addrp = of_get_address(np->parent, 0, NULL, NULL);
+	provider->offset = provider->addr -
+			   (u32)of_translate_address(np->parent, addrp);
 	provider->addr &= ~0xff;
+	provider->size = size | 0xff;
 	provider->node = np;
 
-	clkdm_for_each(_match_clkdm, provider);
-
-	if (!provider->clkdm) {
-		pr_err("%s: nothing matched for node %s (%x)\n",
-		       __func__, np->parent->name, provider->addr);
-		memblock_free_early(__pa(provider), sizeof(*provider));
-		return -EINVAL;
-	}
+	pr_debug("%s: %s: %x...%x [+%x]\n", __func__, np->parent->name,
+		 provider->addr, provider->addr + provider->size,
+		 provider->offset);
 
 	list_add(&provider->link, &clkctrl_providers);
 
 	return 0;
 }
 
-static int _init_clkctrl_providers(void)
+static int __init _init_clkctrl_providers(void)
 {
 	struct device_node *np;
 	int ret = 0;
@@ -775,32 +759,48 @@ static int _init_clkctrl_providers(void)
 	return ret;
 }
 
-static u32 _omap4_xlate_clkctrl(struct omap_hwmod *oh,
-				struct clkctrl_provider *provider)
+static u32 _omap4_xlate_clkctrl(struct omap_hwmod *oh)
 {
-	return oh->prcm.omap4.clkctrl_offs -
-	       provider->offset - provider->clkdm->clkdm_offs;
+	if (!oh->prcm.omap4.modulemode)
+		return 0;
+
+	return omap_cm_xlate_clkctrl(oh->clkdm->prcm_partition,
+				     oh->clkdm->cm_inst,
+				     oh->prcm.omap4.clkctrl_offs);
 }
 
 static struct clk *_lookup_clkctrl_clk(struct omap_hwmod *oh)
 {
 	struct clkctrl_provider *provider;
 	struct clk *clk;
+	u32 addr;
 
 	if (!soc_ops.xlate_clkctrl)
 		return NULL;
 
+	addr = soc_ops.xlate_clkctrl(oh);
+	if (!addr)
+		return NULL;
+
+	pr_debug("%s: %s: addr=%x\n", __func__, oh->name, addr);
+
 	list_for_each_entry(provider, &clkctrl_providers, link) {
-		if (provider->clkdm == oh->clkdm) {
+		if (provider->addr <= addr &&
+		    provider->addr + provider->size >= addr) {
 			struct of_phandle_args clkspec;
 
 			clkspec.np = provider->node;
 			clkspec.args_count = 2;
-			clkspec.args[0] = soc_ops.xlate_clkctrl(oh, provider);
+			clkspec.args[0] = addr - provider->addr -
+					  provider->offset;
 			clkspec.args[1] = 0;
 
 			clk = of_clk_get_from_provider(&clkspec);
 
+			pr_debug("%s: %s got %p (offset=%x, provider=%s)\n",
+				 __func__, oh->name, clk, clkspec.args[0],
+				 provider->node->parent->name);
+
 			return clk;
 		}
 	}
@@ -3521,6 +3521,7 @@ void __init omap_hwmod_init(void)
 		soc_ops.is_hardreset_asserted = _omap4_is_hardreset_asserted;
 		soc_ops.init_clkdm = _init_clkdm;
 		soc_ops.disable_direct_prcm = _omap4_disable_direct_prcm;
+		soc_ops.xlate_clkctrl = _omap4_xlate_clkctrl;
 	} else {
 		WARN(1, "omap_hwmod: unknown SoC type\n");
 	}
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index df2239a58555..0b8e19f40402 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -37,9 +37,15 @@
 
 struct omap_device;
 
-extern struct omap_hwmod_sysc_fields omap_hwmod_sysc_type1;
-extern struct omap_hwmod_sysc_fields omap_hwmod_sysc_type2;
-extern struct omap_hwmod_sysc_fields omap_hwmod_sysc_type3;
+extern struct sysc_regbits omap_hwmod_sysc_type1;
+extern struct sysc_regbits omap_hwmod_sysc_type2;
+extern struct sysc_regbits omap_hwmod_sysc_type3;
+extern struct sysc_regbits omap34xx_sr_sysc_fields;
+extern struct sysc_regbits omap36xx_sr_sysc_fields;
+extern struct sysc_regbits omap3_sham_sysc_fields;
+extern struct sysc_regbits omap3xxx_aes_sysc_fields;
+extern struct sysc_regbits omap_hwmod_sysc_type_mcasp;
+extern struct sysc_regbits omap_hwmod_sysc_type_usb_host_fs;
 
 /*
  * OCP SYSCONFIG bit shifts/masks TYPE1. These are for IPs compliant
@@ -285,26 +291,6 @@ struct omap_hwmod_ocp_if {
 #define CLOCKACT_TEST_NONE	0x3
 
 /**
- * struct omap_hwmod_sysc_fields - hwmod OCP_SYSCONFIG register field offsets.
- * @midle_shift: Offset of the midle bit
- * @clkact_shift: Offset of the clockactivity bit
- * @sidle_shift: Offset of the sidle bit
- * @enwkup_shift: Offset of the enawakeup bit
- * @srst_shift: Offset of the softreset bit
- * @autoidle_shift: Offset of the autoidle bit
- * @dmadisable_shift: Offset of the dmadisable bit
- */
-struct omap_hwmod_sysc_fields {
-	u8 midle_shift;
-	u8 clkact_shift;
-	u8 sidle_shift;
-	u8 enwkup_shift;
-	u8 srst_shift;
-	u8 autoidle_shift;
-	u8 dmadisable_shift;
-};
-
-/**
  * struct omap_hwmod_class_sysconfig - hwmod class OCP_SYS* data
  * @rev_offs: IP block revision register offset (from module base addr)
  * @sysc_offs: OCP_SYSCONFIG register offset (from module base addr)
@@ -335,7 +321,7 @@ struct omap_hwmod_class_sysconfig {
 	u32 sysc_offs;
 	u32 syss_offs;
 	u16 sysc_flags;
-	struct omap_hwmod_sysc_fields *sysc_fields;
+	struct sysc_regbits *sysc_fields;
 	u8 srst_udelay;
 	u8 idlemodes;
 };
@@ -343,11 +329,8 @@ struct omap_hwmod_class_sysconfig {
 /**
  * struct omap_hwmod_omap2_prcm - OMAP2/3-specific PRCM data
  * @module_offs: PRCM submodule offset from the start of the PRM/CM
- * @prcm_reg_id: PRCM register ID (e.g., 3 for CM_AUTOIDLE3)
- * @module_bit: register bit shift for AUTOIDLE, WKST, WKEN, GRPSEL regs
  * @idlest_reg_id: IDLEST register ID (e.g., 3 for CM_IDLEST3)
  * @idlest_idle_bit: register bit shift for CM_IDLEST slave idle bit
- * @idlest_stdby_bit: register bit shift for CM_IDLEST master standby bit
  *
  * @prcm_reg_id and @module_bit are specific to the AUTOIDLE, WKST,
  * WKEN, GRPSEL registers.  In an ideal world, no extra information
@@ -357,11 +340,8 @@ struct omap_hwmod_class_sysconfig {
  */
 struct omap_hwmod_omap2_prcm {
 	s16 module_offs;
-	u8 prcm_reg_id;
-	u8 module_bit;
 	u8 idlest_reg_id;
 	u8 idlest_idle_bit;
-	u8 idlest_stdby_bit;
 };
 
 /*
diff --git a/arch/arm/mach-omap2/omap_hwmod_2420_data.c b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
index 1a15a347945a..0afb014b211f 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2420_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
@@ -111,8 +111,6 @@ static struct omap_hwmod omap2420_i2c1_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP2420_EN_I2C1_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP2420_ST_I2C1_SHIFT,
 		},
@@ -134,8 +132,6 @@ static struct omap_hwmod omap2420_i2c2_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP2420_EN_I2C2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP2420_ST_I2C2_SHIFT,
 		},
@@ -167,8 +163,6 @@ static struct omap_hwmod omap2420_mailbox_hwmod = {
 	.main_clk	= "mailboxes_ick",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_MAILBOXES_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_MAILBOXES_SHIFT,
@@ -197,8 +191,6 @@ static struct omap_hwmod omap2420_mcbsp1_hwmod = {
 	.main_clk	= "mcbsp1_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_MCBSP1_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_MCBSP1_SHIFT,
@@ -215,8 +207,6 @@ static struct omap_hwmod omap2420_mcbsp2_hwmod = {
 	.main_clk	= "mcbsp2_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_MCBSP2_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_MCBSP2_SHIFT,
@@ -247,8 +237,6 @@ static struct omap_hwmod omap2420_msdi1_hwmod = {
 	.main_clk	= "mmc_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP2420_EN_MMC_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP2420_ST_MMC_SHIFT,
@@ -264,8 +252,6 @@ static struct omap_hwmod omap2420_hdq1w_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_HDQ_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_HDQ_SHIFT,
 		},
diff --git a/arch/arm/mach-omap2/omap_hwmod_2430_data.c b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
index 3801850bccec..013b26b305d2 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2430_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
@@ -97,8 +97,6 @@ static struct omap_hwmod omap2430_i2c1_hwmod = {
 			 * to hwmod framework.
 			 */
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP2430_EN_I2CHS1_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP2430_ST_I2CHS1_SHIFT,
 		},
@@ -115,8 +113,6 @@ static struct omap_hwmod omap2430_i2c2_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP2430_EN_I2CHS2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP2430_ST_I2CHS2_SHIFT,
 		},
@@ -132,8 +128,6 @@ static struct omap_hwmod omap2430_gpio5_hwmod = {
 	.main_clk	= "gpio5_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 2,
-			.module_bit = OMAP2430_EN_GPIO5_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 2,
 			.idlest_idle_bit = OMAP2430_ST_GPIO5_SHIFT,
@@ -165,8 +159,6 @@ static struct omap_hwmod omap2430_mailbox_hwmod = {
 	.main_clk	= "mailboxes_ick",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_MAILBOXES_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_MAILBOXES_SHIFT,
@@ -185,8 +177,6 @@ static struct omap_hwmod omap2430_mcspi3_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 2,
-			.module_bit = OMAP2430_EN_MCSPI3_SHIFT,
 			.idlest_reg_id = 2,
 			.idlest_idle_bit = OMAP2430_ST_MCSPI3_SHIFT,
 		},
@@ -219,8 +209,6 @@ static struct omap_hwmod omap2430_usbhsotg_hwmod = {
 	.main_clk	= "usbhs_ick",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP2430_EN_USBHS_MASK,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP2430_ST_USBHS_SHIFT,
@@ -266,8 +254,6 @@ static struct omap_hwmod omap2430_mcbsp1_hwmod = {
 	.main_clk	= "mcbsp1_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_MCBSP1_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_MCBSP1_SHIFT,
@@ -284,8 +270,6 @@ static struct omap_hwmod omap2430_mcbsp2_hwmod = {
 	.main_clk	= "mcbsp2_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_MCBSP2_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_MCBSP2_SHIFT,
@@ -302,8 +286,6 @@ static struct omap_hwmod omap2430_mcbsp3_hwmod = {
 	.main_clk	= "mcbsp3_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP2430_EN_MCBSP3_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 2,
 			.idlest_idle_bit = OMAP2430_ST_MCBSP3_SHIFT,
@@ -320,8 +302,6 @@ static struct omap_hwmod omap2430_mcbsp4_hwmod = {
 	.main_clk	= "mcbsp4_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP2430_EN_MCBSP4_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 2,
 			.idlest_idle_bit = OMAP2430_ST_MCBSP4_SHIFT,
@@ -338,8 +318,6 @@ static struct omap_hwmod omap2430_mcbsp5_hwmod = {
 	.main_clk	= "mcbsp5_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP2430_EN_MCBSP5_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 2,
 			.idlest_idle_bit = OMAP2430_ST_MCBSP5_SHIFT,
@@ -384,8 +362,6 @@ static struct omap_hwmod omap2430_mmc1_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 2,
-			.module_bit  = OMAP2430_EN_MMCHS1_SHIFT,
 			.idlest_reg_id = 2,
 			.idlest_idle_bit = OMAP2430_ST_MMCHS1_SHIFT,
 		},
@@ -408,8 +384,6 @@ static struct omap_hwmod omap2430_mmc2_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 2,
-			.module_bit  = OMAP2430_EN_MMCHS2_SHIFT,
 			.idlest_reg_id = 2,
 			.idlest_idle_bit = OMAP2430_ST_MMCHS2_SHIFT,
 		},
@@ -424,8 +398,6 @@ static struct omap_hwmod omap2430_hdq1w_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_HDQ_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_HDQ_SHIFT,
 		},
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
index beec4cd617b1..4b094cb384cb 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
@@ -242,8 +242,6 @@ struct omap_hwmod omap2xxx_timer1_hwmod = {
 	.main_clk	= "gpt1_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT1_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT1_SHIFT,
@@ -261,8 +259,6 @@ struct omap_hwmod omap2xxx_timer2_hwmod = {
 	.main_clk	= "gpt2_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT2_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT2_SHIFT,
@@ -279,8 +275,6 @@ struct omap_hwmod omap2xxx_timer3_hwmod = {
 	.main_clk	= "gpt3_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT3_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT3_SHIFT,
@@ -297,8 +291,6 @@ struct omap_hwmod omap2xxx_timer4_hwmod = {
 	.main_clk	= "gpt4_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT4_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT4_SHIFT,
@@ -315,8 +307,6 @@ struct omap_hwmod omap2xxx_timer5_hwmod = {
 	.main_clk	= "gpt5_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT5_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT5_SHIFT,
@@ -334,8 +324,6 @@ struct omap_hwmod omap2xxx_timer6_hwmod = {
 	.main_clk	= "gpt6_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT6_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT6_SHIFT,
@@ -353,8 +341,6 @@ struct omap_hwmod omap2xxx_timer7_hwmod = {
 	.main_clk	= "gpt7_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT7_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT7_SHIFT,
@@ -372,8 +358,6 @@ struct omap_hwmod omap2xxx_timer8_hwmod = {
 	.main_clk	= "gpt8_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT8_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT8_SHIFT,
@@ -391,8 +375,6 @@ struct omap_hwmod omap2xxx_timer9_hwmod = {
 	.main_clk	= "gpt9_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT9_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT9_SHIFT,
@@ -410,8 +392,6 @@ struct omap_hwmod omap2xxx_timer10_hwmod = {
 	.main_clk	= "gpt10_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT10_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT10_SHIFT,
@@ -429,8 +409,6 @@ struct omap_hwmod omap2xxx_timer11_hwmod = {
 	.main_clk	= "gpt11_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT11_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT11_SHIFT,
@@ -448,8 +426,6 @@ struct omap_hwmod omap2xxx_timer12_hwmod = {
 	.main_clk	= "gpt12_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPT12_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPT12_SHIFT,
@@ -467,8 +443,6 @@ struct omap_hwmod omap2xxx_wd_timer2_hwmod = {
 	.main_clk	= "mpu_wdt_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_MPU_WDT_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_MPU_WDT_SHIFT,
@@ -485,8 +459,6 @@ struct omap_hwmod omap2xxx_uart1_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_UART1_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_EN_UART1_SHIFT,
 		},
@@ -503,8 +475,6 @@ struct omap_hwmod omap2xxx_uart2_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_UART2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_EN_UART2_SHIFT,
 		},
@@ -521,8 +491,6 @@ struct omap_hwmod omap2xxx_uart3_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 2,
-			.module_bit = OMAP24XX_EN_UART3_SHIFT,
 			.idlest_reg_id = 2,
 			.idlest_idle_bit = OMAP24XX_EN_UART3_SHIFT,
 		},
@@ -547,11 +515,8 @@ struct omap_hwmod omap2xxx_dss_core_hwmod = {
 	.main_clk	= "dss1_fck", /* instead of dss_fck */
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_DSS1_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
-			.idlest_stdby_bit = OMAP24XX_ST_DSS_SHIFT,
 		},
 	},
 	.opt_clks	= dss_opt_clks,
@@ -565,11 +530,8 @@ struct omap_hwmod omap2xxx_dss_dispc_hwmod = {
 	.main_clk	= "dss1_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_DSS1_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
-			.idlest_stdby_bit = OMAP24XX_ST_DSS_SHIFT,
 		},
 	},
 	.flags		= HWMOD_NO_IDLEST,
@@ -586,8 +548,6 @@ struct omap_hwmod omap2xxx_dss_rfbi_hwmod = {
 	.main_clk	= "dss1_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_DSS1_SHIFT,
 			.module_offs = CORE_MOD,
 		},
 	},
@@ -602,8 +562,6 @@ struct omap_hwmod omap2xxx_dss_venc_hwmod = {
 	.main_clk	= "dss_54m_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_DSS1_SHIFT,
 			.module_offs = CORE_MOD,
 		},
 	},
@@ -623,8 +581,6 @@ struct omap_hwmod omap2xxx_gpio1_hwmod = {
 	.main_clk	= "gpios_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPIOS_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPIOS_SHIFT,
@@ -641,8 +597,6 @@ struct omap_hwmod omap2xxx_gpio2_hwmod = {
 	.main_clk	= "gpios_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPIOS_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPIOS_SHIFT,
@@ -659,8 +613,6 @@ struct omap_hwmod omap2xxx_gpio3_hwmod = {
 	.main_clk	= "gpios_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPIOS_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPIOS_SHIFT,
@@ -677,8 +629,6 @@ struct omap_hwmod omap2xxx_gpio4_hwmod = {
 	.main_clk	= "gpios_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_GPIOS_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_GPIOS_SHIFT,
@@ -699,8 +649,6 @@ struct omap_hwmod omap2xxx_mcspi1_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_MCSPI1_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_MCSPI1_SHIFT,
 		},
@@ -720,8 +668,6 @@ struct omap_hwmod omap2xxx_mcspi2_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_EN_MCSPI2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_MCSPI2_SHIFT,
 		},
@@ -740,8 +686,6 @@ struct omap_hwmod omap2xxx_counter_32k_hwmod = {
 	.prcm		= {
 		.omap2	= {
 			.module_offs = WKUP_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP24XX_ST_32KSYNC_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP24XX_ST_32KSYNC_SHIFT,
 		},
@@ -758,8 +702,6 @@ struct omap_hwmod omap2xxx_gpmc_hwmod = {
 	.flags		= HWMOD_NO_IDLEST | DEBUG_OMAP_GPMC_HWMOD_FLAGS,
 	.prcm		= {
 		.omap2	= {
-			.prcm_reg_id = 3,
-			.module_bit = OMAP24XX_EN_GPMC_MASK,
 			.module_offs = CORE_MOD,
 		},
 	},
@@ -787,8 +729,6 @@ struct omap_hwmod omap2xxx_rng_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 4,
-			.module_bit = OMAP24XX_EN_RNG_SHIFT,
 			.idlest_reg_id = 4,
 			.idlest_idle_bit = OMAP24XX_ST_RNG_SHIFT,
 		},
@@ -825,8 +765,6 @@ struct omap_hwmod omap2xxx_sham_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 4,
-			.module_bit = OMAP24XX_EN_SHA_SHIFT,
 			.idlest_reg_id = 4,
 			.idlest_idle_bit = OMAP24XX_ST_SHA_SHIFT,
 		},
@@ -856,8 +794,6 @@ struct omap_hwmod omap2xxx_aes_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 4,
-			.module_bit = OMAP24XX_EN_AES_SHIFT,
 			.idlest_reg_id = 4,
 			.idlest_idle_bit = OMAP24XX_ST_AES_SHIFT,
 		},
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index d2106ae4410a..1a2f2242e31b 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -113,8 +113,6 @@ static struct omap_hwmod omap3xxx_iva_hwmod = {
 	.prcm = {
 		.omap2 = {
 			.module_offs = OMAP3430_IVA2_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_IVA2_SHIFT,
 		},
@@ -188,8 +186,6 @@ static struct omap_hwmod omap3xxx_timer1_hwmod = {
 	.main_clk	= "gpt1_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT1_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT1_SHIFT,
@@ -206,8 +202,6 @@ static struct omap_hwmod omap3xxx_timer2_hwmod = {
 	.main_clk	= "gpt2_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT2_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT2_SHIFT,
@@ -223,8 +217,6 @@ static struct omap_hwmod omap3xxx_timer3_hwmod = {
 	.main_clk	= "gpt3_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT3_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT3_SHIFT,
@@ -240,8 +232,6 @@ static struct omap_hwmod omap3xxx_timer4_hwmod = {
 	.main_clk	= "gpt4_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT4_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT4_SHIFT,
@@ -257,8 +247,6 @@ static struct omap_hwmod omap3xxx_timer5_hwmod = {
 	.main_clk	= "gpt5_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT5_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT5_SHIFT,
@@ -275,8 +263,6 @@ static struct omap_hwmod omap3xxx_timer6_hwmod = {
 	.main_clk	= "gpt6_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT6_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT6_SHIFT,
@@ -293,8 +279,6 @@ static struct omap_hwmod omap3xxx_timer7_hwmod = {
 	.main_clk	= "gpt7_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT7_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT7_SHIFT,
@@ -311,8 +295,6 @@ static struct omap_hwmod omap3xxx_timer8_hwmod = {
 	.main_clk	= "gpt8_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT8_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT8_SHIFT,
@@ -329,8 +311,6 @@ static struct omap_hwmod omap3xxx_timer9_hwmod = {
 	.main_clk	= "gpt9_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT9_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT9_SHIFT,
@@ -347,8 +327,6 @@ static struct omap_hwmod omap3xxx_timer10_hwmod = {
 	.main_clk	= "gpt10_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT10_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT10_SHIFT,
@@ -365,8 +343,6 @@ static struct omap_hwmod omap3xxx_timer11_hwmod = {
 	.main_clk	= "gpt11_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT11_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT11_SHIFT,
@@ -384,8 +360,6 @@ static struct omap_hwmod omap3xxx_timer12_hwmod = {
 	.main_clk	= "gpt12_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPT12_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPT12_SHIFT,
@@ -439,8 +413,6 @@ static struct omap_hwmod omap3xxx_wd_timer2_hwmod = {
 	.main_clk	= "wdt2_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_WDT2_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_WDT2_SHIFT,
@@ -461,8 +433,6 @@ static struct omap_hwmod omap3xxx_uart1_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_UART1_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_EN_UART1_SHIFT,
 		},
@@ -478,8 +448,6 @@ static struct omap_hwmod omap3xxx_uart2_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_UART2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_EN_UART2_SHIFT,
 		},
@@ -496,8 +464,6 @@ static struct omap_hwmod omap3xxx_uart3_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = OMAP3430_PER_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_UART3_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_EN_UART3_SHIFT,
 		},
@@ -515,8 +481,6 @@ static struct omap_hwmod omap36xx_uart4_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = OMAP3430_PER_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3630_EN_UART4_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3630_EN_UART4_SHIFT,
 		},
@@ -546,8 +510,6 @@ static struct omap_hwmod am35xx_uart4_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = AM35XX_EN_UART4_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = AM35XX_ST_UART4_SHIFT,
 		},
@@ -583,11 +545,8 @@ static struct omap_hwmod omap3430es1_dss_core_hwmod = {
 	.main_clk	= "dss1_alwon_fck", /* instead of dss_fck */
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_DSS1_SHIFT,
 			.module_offs = OMAP3430_DSS_MOD,
 			.idlest_reg_id = 1,
-			.idlest_stdby_bit = OMAP3430ES1_ST_DSS_SHIFT,
 		},
 	},
 	.opt_clks	= dss_opt_clks,
@@ -602,12 +561,9 @@ static struct omap_hwmod omap3xxx_dss_core_hwmod = {
 	.main_clk	= "dss1_alwon_fck", /* instead of dss_fck */
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_DSS1_SHIFT,
 			.module_offs = OMAP3430_DSS_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430ES2_ST_DSS_IDLE_SHIFT,
-			.idlest_stdby_bit = OMAP3430ES2_ST_DSS_STDBY_SHIFT,
 		},
 	},
 	.opt_clks	= dss_opt_clks,
@@ -642,8 +598,6 @@ static struct omap_hwmod omap3xxx_dss_dispc_hwmod = {
 	.main_clk	= "dss1_alwon_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_DSS1_SHIFT,
 			.module_offs = OMAP3430_DSS_MOD,
 		},
 	},
@@ -683,8 +637,6 @@ static struct omap_hwmod omap3xxx_dss_dsi1_hwmod = {
 	.main_clk	= "dss1_alwon_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_DSS1_SHIFT,
 			.module_offs = OMAP3430_DSS_MOD,
 		},
 	},
@@ -703,8 +655,6 @@ static struct omap_hwmod omap3xxx_dss_rfbi_hwmod = {
 	.main_clk	= "dss1_alwon_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_DSS1_SHIFT,
 			.module_offs = OMAP3430_DSS_MOD,
 		},
 	},
@@ -724,8 +674,6 @@ static struct omap_hwmod omap3xxx_dss_venc_hwmod = {
 	.main_clk	= "dss_tv_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_DSS1_SHIFT,
 			.module_offs = OMAP3430_DSS_MOD,
 		},
 	},
@@ -747,8 +695,6 @@ static struct omap_hwmod omap3xxx_i2c1_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_I2C1_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_I2C1_SHIFT,
 		},
@@ -770,8 +716,6 @@ static struct omap_hwmod omap3xxx_i2c2_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_I2C2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_I2C2_SHIFT,
 		},
@@ -795,8 +739,6 @@ static struct omap_hwmod omap3xxx_i2c3_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_I2C3_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_I2C3_SHIFT,
 		},
@@ -846,8 +788,6 @@ static struct omap_hwmod omap3xxx_gpio1_hwmod = {
 	.opt_clks_cnt	= ARRAY_SIZE(gpio1_opt_clks),
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPIO1_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPIO1_SHIFT,
@@ -870,8 +810,6 @@ static struct omap_hwmod omap3xxx_gpio2_hwmod = {
 	.opt_clks_cnt	= ARRAY_SIZE(gpio2_opt_clks),
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPIO2_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPIO2_SHIFT,
@@ -894,8 +832,6 @@ static struct omap_hwmod omap3xxx_gpio3_hwmod = {
 	.opt_clks_cnt	= ARRAY_SIZE(gpio3_opt_clks),
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPIO3_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPIO3_SHIFT,
@@ -918,8 +854,6 @@ static struct omap_hwmod omap3xxx_gpio4_hwmod = {
 	.opt_clks_cnt	= ARRAY_SIZE(gpio4_opt_clks),
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPIO4_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPIO4_SHIFT,
@@ -943,8 +877,6 @@ static struct omap_hwmod omap3xxx_gpio5_hwmod = {
 	.opt_clks_cnt	= ARRAY_SIZE(gpio5_opt_clks),
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPIO5_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPIO5_SHIFT,
@@ -968,8 +900,6 @@ static struct omap_hwmod omap3xxx_gpio6_hwmod = {
 	.opt_clks_cnt	= ARRAY_SIZE(gpio6_opt_clks),
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_GPIO6_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_GPIO6_SHIFT,
@@ -1012,8 +942,6 @@ static struct omap_hwmod omap3xxx_dma_system_hwmod = {
 	.prcm = {
 		.omap2 = {
 			.module_offs		= CORE_MOD,
-			.prcm_reg_id		= 1,
-			.module_bit		= OMAP3430_ST_SDMA_SHIFT,
 			.idlest_reg_id		= 1,
 			.idlest_idle_bit	= OMAP3430_ST_SDMA_SHIFT,
 		},
@@ -1060,8 +988,6 @@ static struct omap_hwmod omap3xxx_mcbsp1_hwmod = {
 	.main_clk	= "mcbsp1_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MCBSP1_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MCBSP1_SHIFT,
@@ -1083,8 +1009,6 @@ static struct omap_hwmod omap3xxx_mcbsp2_hwmod = {
 	.main_clk	= "mcbsp2_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MCBSP2_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MCBSP2_SHIFT,
@@ -1107,8 +1031,6 @@ static struct omap_hwmod omap3xxx_mcbsp3_hwmod = {
 	.main_clk	= "mcbsp3_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MCBSP3_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MCBSP3_SHIFT,
@@ -1128,8 +1050,6 @@ static struct omap_hwmod omap3xxx_mcbsp4_hwmod = {
 	.main_clk	= "mcbsp4_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MCBSP4_SHIFT,
 			.module_offs = OMAP3430_PER_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MCBSP4_SHIFT,
@@ -1148,8 +1068,6 @@ static struct omap_hwmod omap3xxx_mcbsp5_hwmod = {
 	.main_clk	= "mcbsp5_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MCBSP5_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MCBSP5_SHIFT,
@@ -1190,10 +1108,6 @@ static struct omap_hwmod omap3xxx_mcbsp3_sidetone_hwmod = {
 };
 
 /* SR common */
-static struct omap_hwmod_sysc_fields omap34xx_sr_sysc_fields = {
-	.clkact_shift	= 20,
-};
-
 static struct omap_hwmod_class_sysconfig omap34xx_sr_sysc = {
 	.sysc_offs	= 0x24,
 	.sysc_flags	= (SYSC_HAS_CLOCKACTIVITY | SYSC_NO_CACHE),
@@ -1206,11 +1120,6 @@ static struct omap_hwmod_class omap34xx_smartreflex_hwmod_class = {
 	.rev  = 1,
 };
 
-static struct omap_hwmod_sysc_fields omap36xx_sr_sysc_fields = {
-	.sidle_shift	= 24,
-	.enwkup_shift	= 26,
-};
-
 static struct omap_hwmod_class_sysconfig omap36xx_sr_sysc = {
 	.sysc_offs	= 0x38,
 	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
@@ -1237,8 +1146,6 @@ static struct omap_hwmod omap34xx_sr1_hwmod = {
 	.main_clk	= "sr1_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_SR1_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_EN_SR1_SHIFT,
@@ -1254,8 +1161,6 @@ static struct omap_hwmod omap36xx_sr1_hwmod = {
 	.main_clk	= "sr1_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_SR1_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_EN_SR1_SHIFT,
@@ -1276,8 +1181,6 @@ static struct omap_hwmod omap34xx_sr2_hwmod = {
 	.main_clk	= "sr2_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_SR2_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_EN_SR2_SHIFT,
@@ -1293,8 +1196,6 @@ static struct omap_hwmod omap36xx_sr2_hwmod = {
 	.main_clk	= "sr2_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_SR2_SHIFT,
 			.module_offs = WKUP_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_EN_SR2_SHIFT,
@@ -1330,8 +1231,6 @@ static struct omap_hwmod omap3xxx_mailbox_hwmod = {
 	.main_clk	= "mailboxes_ick",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MAILBOXES_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MAILBOXES_SHIFT,
@@ -1373,8 +1272,6 @@ static struct omap_hwmod omap34xx_mcspi1 = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MCSPI1_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MCSPI1_SHIFT,
 		},
@@ -1394,8 +1291,6 @@ static struct omap_hwmod omap34xx_mcspi2 = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MCSPI2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MCSPI2_SHIFT,
 		},
@@ -1417,8 +1312,6 @@ static struct omap_hwmod omap34xx_mcspi3 = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MCSPI3_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MCSPI3_SHIFT,
 		},
@@ -1440,8 +1333,6 @@ static struct omap_hwmod omap34xx_mcspi4 = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MCSPI4_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MCSPI4_SHIFT,
 		},
@@ -1475,12 +1366,9 @@ static struct omap_hwmod omap3xxx_usbhsotg_hwmod = {
 	.main_clk	= "hsotgusb_ick",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_HSOTGUSB_SHIFT,
 			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430ES2_ST_HSOTGUSB_IDLE_SHIFT,
-			.idlest_stdby_bit = OMAP3430ES2_ST_HSOTGUSB_STDBY_SHIFT,
 		},
 	},
 	.class		= &usbotg_class,
@@ -1555,8 +1443,6 @@ static struct omap_hwmod omap3xxx_pre_es3_mmc1_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MMC1_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MMC1_SHIFT,
 		},
@@ -1573,8 +1459,6 @@ static struct omap_hwmod omap3xxx_es3plus_mmc1_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MMC1_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MMC1_SHIFT,
 		},
@@ -1604,8 +1488,6 @@ static struct omap_hwmod omap3xxx_pre_es3_mmc2_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MMC2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MMC2_SHIFT,
 		},
@@ -1622,8 +1504,6 @@ static struct omap_hwmod omap3xxx_es3plus_mmc2_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MMC2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MMC2_SHIFT,
 		},
@@ -1646,8 +1526,7 @@ static struct omap_hwmod omap3xxx_mmc3_hwmod = {
 	.main_clk	= "mmchs3_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MMC3_SHIFT,
+			.module_offs = CORE_MOD,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_MMC3_SHIFT,
 		},
@@ -1687,11 +1566,8 @@ static struct omap_hwmod omap3xxx_usb_host_hs_hwmod = {
 	.prcm = {
 		.omap2 = {
 			.module_offs = OMAP3430ES2_USBHOST_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430ES2_EN_USBHOST1_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430ES2_ST_USBHOST_IDLE_SHIFT,
-			.idlest_stdby_bit = OMAP3430ES2_ST_USBHOST_STDBY_SHIFT,
 		},
 	},
 
@@ -1765,8 +1641,6 @@ static struct omap_hwmod omap3xxx_usb_tll_hs_hwmod = {
 	.prcm = {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 3,
-			.module_bit = OMAP3430ES2_EN_USBTLL_SHIFT,
 			.idlest_reg_id = 3,
 			.idlest_idle_bit = OMAP3430ES2_ST_USBTLL_SHIFT,
 		},
@@ -1779,8 +1653,6 @@ static struct omap_hwmod omap3xxx_hdq1w_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_HDQ_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_HDQ_SHIFT,
 		},
@@ -1806,8 +1678,6 @@ static struct omap_hwmod omap3xxx_sad2d_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_SAD2D_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_SAD2D_SHIFT,
 		},
@@ -1841,8 +1711,6 @@ static struct omap_hwmod omap3xxx_counter_32k_hwmod = {
 	.prcm		= {
 		.omap2	= {
 			.module_offs = WKUP_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_ST_32KSYNC_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_32KSYNC_SHIFT,
 		},
@@ -2453,7 +2321,6 @@ static struct omap_hwmod omap3xxx_mmu_iva_hwmod = {
 	.prcm = {
 		.omap2 = {
 			.module_offs = OMAP3430_IVA2_MOD,
-			.module_bit = OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_IVA2_SHIFT,
 		},
@@ -2731,12 +2598,6 @@ static struct omap_hwmod_ocp_if omap3xxx_l3_main__gpmc = {
 };
 
 /* l4_core -> SHAM2 (SHA1/MD5) (similar to omap24xx) */
-static struct omap_hwmod_sysc_fields omap3_sham_sysc_fields = {
-	.sidle_shift	= 4,
-	.srst_shift	= 1,
-	.autoidle_shift	= 0,
-};
-
 static struct omap_hwmod_class_sysconfig omap3_sham_sysc = {
 	.rev_offs	= 0x5c,
 	.sysc_offs	= 0x60,
@@ -2759,8 +2620,6 @@ static struct omap_hwmod omap3xxx_sham_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_SHA12_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_SHA12_SHIFT,
 		},
@@ -2777,12 +2636,6 @@ static struct omap_hwmod_ocp_if omap3xxx_l4_core__sham = {
 };
 
 /* l4_core -> AES */
-static struct omap_hwmod_sysc_fields omap3xxx_aes_sysc_fields = {
-	.sidle_shift	= 6,
-	.srst_shift	= 1,
-	.autoidle_shift	= 0,
-};
-
 static struct omap_hwmod_class_sysconfig omap3_aes_sysc = {
 	.rev_offs	= 0x44,
 	.sysc_offs	= 0x48,
@@ -2805,8 +2658,6 @@ static struct omap_hwmod omap3xxx_aes_hwmod = {
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_AES2_SHIFT,
 			.idlest_reg_id = 1,
 			.idlest_idle_bit = OMAP3430_ST_AES2_SHIFT,
 		},
@@ -2849,8 +2700,6 @@ static struct omap_hwmod omap3xxx_ssi_hwmod = {
 	.main_clk	= "ssi_ssr_fck",
 	.prcm		= {
 		.omap2 = {
-			.prcm_reg_id		= 1,
-			.module_bit		= OMAP3430_EN_SSI_SHIFT,
 			.module_offs		= CORE_MOD,
 			.idlest_reg_id		= 1,
 			.idlest_idle_bit	= OMAP3430ES2_ST_SSI_IDLE_SHIFT,
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index c47709659a54..a1901c22a0f0 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -1658,10 +1658,6 @@ static struct omap_hwmod omap44xx_mailbox_hwmod = {
  */
 
 /* The IP is not compliant to type1 / type2 scheme */
-static struct omap_hwmod_sysc_fields omap_hwmod_sysc_type_mcasp = {
-	.sidle_shift	= 0,
-};
-
 static struct omap_hwmod_class_sysconfig omap44xx_mcasp_sysc = {
 	.sysc_offs	= 0x0004,
 	.sysc_flags	= SYSC_HAS_SIDLEMODE,
@@ -2403,17 +2399,12 @@ static struct omap_hwmod omap44xx_slimbus2_hwmod = {
  */
 
 /* The IP is not compliant to type1 / type2 scheme */
-static struct omap_hwmod_sysc_fields omap_hwmod_sysc_type_smartreflex = {
-	.sidle_shift	= 24,
-	.enwkup_shift	= 26,
-};
-
 static struct omap_hwmod_class_sysconfig omap44xx_smartreflex_sysc = {
 	.sysc_offs	= 0x0038,
 	.sysc_flags	= (SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE),
 	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
 			   SIDLE_SMART_WKUP),
-	.sysc_fields	= &omap_hwmod_sysc_type_smartreflex,
+	.sysc_fields	= &omap36xx_sr_sysc_fields,
 };
 
 static struct omap_hwmod_class omap44xx_smartreflex_hwmod_class = {
@@ -2844,12 +2835,6 @@ static struct omap_hwmod omap44xx_uart4_hwmod = {
  */
 
 /* The IP is not compliant to type1 / type2 scheme */
-static struct omap_hwmod_sysc_fields omap_hwmod_sysc_type_usb_host_fs = {
-	.midle_shift	= 4,
-	.sidle_shift	= 2,
-	.srst_shift	= 1,
-};
-
 static struct omap_hwmod_class_sysconfig omap44xx_usb_host_fs_sysc = {
 	.rev_offs	= 0x0000,
 	.sysc_offs	= 0x0210,
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index d05e553d6346..4c2a05b1bd19 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -2055,17 +2055,12 @@ static struct omap_hwmod dra7xx_sata_hwmod = {
  */
 
 /* The IP is not compliant to type1 / type2 scheme */
-static struct omap_hwmod_sysc_fields omap_hwmod_sysc_type_smartreflex = {
-	.sidle_shift	= 24,
-	.enwkup_shift	= 26,
-};
-
 static struct omap_hwmod_class_sysconfig dra7xx_smartreflex_sysc = {
 	.sysc_offs	= 0x0038,
 	.sysc_flags	= (SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE),
 	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
 			   SIDLE_SMART_WKUP),
-	.sysc_fields	= &omap_hwmod_sysc_type_smartreflex,
+	.sysc_fields	= &omap36xx_sr_sysc_fields,
 };
 
 static struct omap_hwmod_class dra7xx_smartreflex_hwmod_class = {
@@ -4019,6 +4014,10 @@ static struct omap_hwmod_ocp_if *dra76x_hwmod_ocp_ifs[] __initdata = {
 	NULL,
 };
 
+static struct omap_hwmod_ocp_if *acd_76x_hwmod_ocp_ifs[] __initdata = {
+	NULL,
+};
+
 static struct omap_hwmod_ocp_if *dra74x_hwmod_ocp_ifs[] __initdata = {
 	&dra7xx_l4_per3__usb_otg_ss4,
 	NULL,
@@ -4028,7 +4027,7 @@ static struct omap_hwmod_ocp_if *dra72x_hwmod_ocp_ifs[] __initdata = {
 	NULL,
 };
 
-static struct omap_hwmod_ocp_if *dra74x_dra72x_hwmod_ocp_ifs[] __initdata = {
+static struct omap_hwmod_ocp_if *rtc_hwmod_ocp_ifs[] __initdata = {
 	&dra7xx_l4_per3__rtcss,
 	NULL,
 };
@@ -4040,19 +4039,26 @@ int __init dra7xx_hwmod_init(void)
 	omap_hwmod_init();
 	ret = omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs);
 
-	if (!ret && soc_is_dra74x())
+	if (!ret && soc_is_dra74x()) {
 		ret = omap_hwmod_register_links(dra74x_hwmod_ocp_ifs);
-	else if (!ret && soc_is_dra72x())
+		if (!ret)
+			ret = omap_hwmod_register_links(rtc_hwmod_ocp_ifs);
+	} else if (!ret && soc_is_dra72x()) {
 		ret = omap_hwmod_register_links(dra72x_hwmod_ocp_ifs);
-	else if (!ret && soc_is_dra76x())
+		if (!ret && !of_machine_is_compatible("ti,dra718"))
+			ret = omap_hwmod_register_links(rtc_hwmod_ocp_ifs);
+	} else if (!ret && soc_is_dra76x()) {
 		ret = omap_hwmod_register_links(dra76x_hwmod_ocp_ifs);
 
+		if (!ret && soc_is_dra76x_acd()) {
+			ret = omap_hwmod_register_links(acd_76x_hwmod_ocp_ifs);
+		} else if (!ret && soc_is_dra76x_abz()) {
+			ret = omap_hwmod_register_links(rtc_hwmod_ocp_ifs);
+		}
+	}
+
 	if (!ret && omap_type() == OMAP2_DEVICE_TYPE_GP)
 		ret = omap_hwmod_register_links(dra7xx_gp_hwmod_ocp_ifs);
 
-	/* now for the IPs available only in dra74 and dra72 */
-	if (!ret && !of_machine_is_compatible("ti,dra718") && !soc_is_dra76x())
-		ret = omap_hwmod_register_links(dra74x_dra72x_hwmod_ocp_ifs);
-
 	return ret;
 }
diff --git a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
index 77a515b11ec2..84f118280a0e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
@@ -988,7 +988,7 @@ static struct omap_hwmod_class dm81xx_sata_hwmod_class = {
 
 static struct omap_hwmod dm81xx_sata_hwmod = {
 	.name		= "sata",
-	.clkdm_name	= "default_sata_clkdm",
+	.clkdm_name	= "default_clkdm",
 	.flags		= HWMOD_NO_IDLEST,
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm/mach-omap2/omap_hwmod_common_data.c b/arch/arm/mach-omap2/omap_hwmod_common_data.c
index 79d623b83e49..77c0b7618ea2 100644
--- a/arch/arm/mach-omap2/omap_hwmod_common_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_common_data.c
@@ -16,6 +16,9 @@
  * data and their integration with other OMAP modules and Linux.
  */
 
+#include <linux/types.h>
+#include <linux/platform_data/ti-sysc.h>
+
 #include "omap_hwmod.h"
 
 #include "omap_hwmod_common_data.h"
@@ -27,7 +30,7 @@
  * if the device ip is compliant with the original PRCM protocol
  * defined for OMAP2420.
  */
-struct omap_hwmod_sysc_fields omap_hwmod_sysc_type1 = {
+struct sysc_regbits omap_hwmod_sysc_type1 = {
 	.midle_shift	= SYSC_TYPE1_MIDLEMODE_SHIFT,
 	.clkact_shift	= SYSC_TYPE1_CLOCKACTIVITY_SHIFT,
 	.sidle_shift	= SYSC_TYPE1_SIDLEMODE_SHIFT,
@@ -43,7 +46,7 @@ struct omap_hwmod_sysc_fields omap_hwmod_sysc_type1 = {
  * device ip is compliant with the new PRCM protocol defined for new
  * OMAP4 IPs.
  */
-struct omap_hwmod_sysc_fields omap_hwmod_sysc_type2 = {
+struct sysc_regbits omap_hwmod_sysc_type2 = {
 	.midle_shift	= SYSC_TYPE2_MIDLEMODE_SHIFT,
 	.sidle_shift	= SYSC_TYPE2_SIDLEMODE_SHIFT,
 	.srst_shift	= SYSC_TYPE2_SOFTRESET_SHIFT,
@@ -54,7 +57,7 @@ struct omap_hwmod_sysc_fields omap_hwmod_sysc_type2 = {
  * struct omap_hwmod_sysc_type3 - TYPE3 sysconfig scheme.
  * Used by some IPs on AM33xx
  */
-struct omap_hwmod_sysc_fields omap_hwmod_sysc_type3 = {
+struct sysc_regbits omap_hwmod_sysc_type3 = {
 	.midle_shift	= SYSC_TYPE3_MIDLEMODE_SHIFT,
 	.sidle_shift	= SYSC_TYPE3_SIDLEMODE_SHIFT,
 };
@@ -63,3 +66,34 @@ struct omap_dss_dispc_dev_attr omap2_3_dss_dispc_dev_attr = {
 	.manager_count		= 2,
 	.has_framedonetv_irq	= 0
 };
+
+struct sysc_regbits omap34xx_sr_sysc_fields = {
+	.clkact_shift	= 20,
+};
+
+struct sysc_regbits omap36xx_sr_sysc_fields = {
+	.sidle_shift	= 24,
+	.enwkup_shift	= 26,
+};
+
+struct sysc_regbits omap3_sham_sysc_fields = {
+	.sidle_shift	= 4,
+	.srst_shift	= 1,
+	.autoidle_shift	= 0,
+};
+
+struct sysc_regbits omap3xxx_aes_sysc_fields = {
+	.sidle_shift	= 6,
+	.srst_shift	= 1,
+	.autoidle_shift	= 0,
+};
+
+struct sysc_regbits omap_hwmod_sysc_type_mcasp = {
+	.sidle_shift	= 0,
+};
+
+struct sysc_regbits omap_hwmod_sysc_type_usb_host_fs = {
+	.midle_shift	= 4,
+	.sidle_shift	= 2,
+	.srst_shift	= 1,
+};
diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h
index b668719b9b25..8e30772cfe32 100644
--- a/arch/arm/mach-omap2/pm.h
+++ b/arch/arm/mach-omap2/pm.h
@@ -81,10 +81,6 @@ extern unsigned int omap3_do_wfi_sz;
 /* ... and its pointer from SRAM after copy */
 extern void (*omap3_do_wfi_sram)(void);
 
-/* save_secure_ram_context function pointer and size, for copy to SRAM */
-extern int save_secure_ram_context(u32 *addr);
-extern unsigned int save_secure_ram_context_sz;
-
 extern void omap3_save_scratchpad_contents(void);
 
 #define PM_RTA_ERRATUM_i608		(1 << 0)
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 841ba19d64a6..36c55547137c 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -48,6 +48,7 @@
 #include "prm3xxx.h"
 #include "pm.h"
 #include "sdrc.h"
+#include "omap-secure.h"
 #include "sram.h"
 #include "control.h"
 #include "vc.h"
@@ -66,7 +67,6 @@ struct power_state {
 
 static LIST_HEAD(pwrst_list);
 
-static int (*_omap_save_secure_sram)(u32 *addr);
 void (*omap3_do_wfi_sram)(void);
 
 static struct powerdomain *mpu_pwrdm, *neon_pwrdm;
@@ -121,8 +121,8 @@ static void omap3_save_secure_ram_context(void)
 		 * will hang the system.
 		 */
 		pwrdm_set_next_pwrst(mpu_pwrdm, PWRDM_POWER_ON);
-		ret = _omap_save_secure_sram((u32 *)(unsigned long)
-				__pa(omap3_secure_ram_storage));
+		ret = omap3_save_secure_ram(omap3_secure_ram_storage,
+					    OMAP3_SAVE_SECURE_RAM_SZ);
 		pwrdm_set_next_pwrst(mpu_pwrdm, mpu_next_state);
 		/* Following is for error tracking, it should not happen */
 		if (ret) {
@@ -434,15 +434,10 @@ static int __init pwrdms_setup(struct powerdomain *pwrdm, void *unused)
  *
  * The minimum set of functions is pushed to SRAM for execution:
  * - omap3_do_wfi for erratum i581 WA,
- * - save_secure_ram_context for security extensions.
  */
 void omap_push_sram_idle(void)
 {
 	omap3_do_wfi_sram = omap_sram_push(omap3_do_wfi, omap3_do_wfi_sz);
-
-	if (omap_type() != OMAP2_DEVICE_TYPE_GP)
-		_omap_save_secure_sram = omap_sram_push(save_secure_ram_context,
-				save_secure_ram_context_sz);
 }
 
 static void __init pm_errata_configure(void)
@@ -553,7 +548,7 @@ int __init omap3_pm_init(void)
 	clkdm_add_wkdep(neon_clkdm, mpu_clkdm);
 	if (omap_type() != OMAP2_DEVICE_TYPE_GP) {
 		omap3_secure_ram_storage =
-			kmalloc(0x803F, GFP_KERNEL);
+			kmalloc(OMAP3_SAVE_SECURE_RAM_SZ, GFP_KERNEL);
 		if (!omap3_secure_ram_storage)
 			pr_err("Memory allocation failed when allocating for secure sram context\n");
 
diff --git a/arch/arm/mach-omap2/prcm-common.h b/arch/arm/mach-omap2/prcm-common.h
index 0592b23902c6..0977da0dab76 100644
--- a/arch/arm/mach-omap2/prcm-common.h
+++ b/arch/arm/mach-omap2/prcm-common.h
@@ -528,6 +528,7 @@ struct omap_prcm_irq_setup {
 struct omap_domain_base {
 	u32 pa;
 	void __iomem *va;
+	s16 offset;
 };
 
 /**
diff --git a/arch/arm/mach-omap2/prm33xx.c b/arch/arm/mach-omap2/prm33xx.c
index d2c5bcabdbeb..ebaf80d72a10 100644
--- a/arch/arm/mach-omap2/prm33xx.c
+++ b/arch/arm/mach-omap2/prm33xx.c
@@ -176,17 +176,6 @@ static int am33xx_pwrdm_read_pwrst(struct powerdomain *pwrdm)
 	return v;
 }
 
-static int am33xx_pwrdm_read_prev_pwrst(struct powerdomain *pwrdm)
-{
-	u32 v;
-
-	v = am33xx_prm_read_reg(pwrdm->prcm_offs, pwrdm->pwrstst_offs);
-	v &= AM33XX_LASTPOWERSTATEENTERED_MASK;
-	v >>= AM33XX_LASTPOWERSTATEENTERED_SHIFT;
-
-	return v;
-}
-
 static int am33xx_pwrdm_set_lowpwrstchange(struct powerdomain *pwrdm)
 {
 	am33xx_prm_rmw_reg_bits(AM33XX_LOWPOWERSTATECHANGE_MASK,
@@ -357,7 +346,6 @@ struct pwrdm_ops am33xx_pwrdm_operations = {
 	.pwrdm_set_next_pwrst		= am33xx_pwrdm_set_next_pwrst,
 	.pwrdm_read_next_pwrst		= am33xx_pwrdm_read_next_pwrst,
 	.pwrdm_read_pwrst		= am33xx_pwrdm_read_pwrst,
-	.pwrdm_read_prev_pwrst		= am33xx_pwrdm_read_prev_pwrst,
 	.pwrdm_set_logic_retst		= am33xx_pwrdm_set_logic_retst,
 	.pwrdm_read_logic_pwrst		= am33xx_pwrdm_read_logic_pwrst,
 	.pwrdm_read_logic_retst		= am33xx_pwrdm_read_logic_retst,
diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index fa5fd24f524c..22daf4efed68 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -93,20 +93,13 @@ ENTRY(enable_omap3630_toggle_l2_on_restore)
 ENDPROC(enable_omap3630_toggle_l2_on_restore)
 
 /*
- * Function to call rom code to save secure ram context. This gets
- * relocated to SRAM, so it can be all in .data section. Otherwise
- * we need to initialize api_params separately.
+ * Function to call rom code to save secure ram context.
+ *
+ * r0 = physical address of the parameters
  */
-	.data
-	.align	3
 ENTRY(save_secure_ram_context)
 	stmfd	sp!, {r4 - r11, lr}	@ save registers on stack
-	adr	r3, api_params		@ r3 points to parameters
-	str	r0, [r3,#0x4]		@ r0 has sdram address
-	ldr	r12, high_mask
-	and	r3, r3, r12
-	ldr	r12, sram_phy_addr_mask
-	orr	r3, r3, r12
+	mov	r3, r0			@ physical address of parameters
 	mov	r0, #25			@ set service ID for PPA
 	mov	r12, r0			@ copy secure service ID in r12
 	mov	r1, #0			@ set task id for ROM code in r1
@@ -120,18 +113,7 @@ ENTRY(save_secure_ram_context)
 	nop
 	nop
 	ldmfd	sp!, {r4 - r11, pc}
-	.align
-sram_phy_addr_mask:
-	.word	SRAM_BASE_P
-high_mask:
-	.word	0xffff
-api_params:
-	.word	0x4, 0x0, 0x0, 0x1, 0x1
 ENDPROC(save_secure_ram_context)
-ENTRY(save_secure_ram_context_sz)
-	.word	. - save_secure_ram_context
-
-	.text
 
 /*
  * ======================
diff --git a/arch/arm/mach-omap2/soc.h b/arch/arm/mach-omap2/soc.h
index 28fa1f8d8363..050891e055a4 100644
--- a/arch/arm/mach-omap2/soc.h
+++ b/arch/arm/mach-omap2/soc.h
@@ -143,6 +143,14 @@ static inline int is_dra ##subclass (void)		\
 	return (GET_OMAP_SUBCLASS == (id)) ? 1 : 0;	\
 }
 
+#define GET_DRA_PACKAGE		(omap_rev() & 0xff)
+
+#define IS_DRA_SUBCLASS_PACKAGE(subclass, package, id)			\
+static inline int is_dra ##subclass ##_ ##package (void)		\
+{									\
+	return (is_dra ##subclass () && GET_DRA_PACKAGE == id) ? 1 : 0;	\
+}
+
 IS_OMAP_CLASS(24xx, 0x24)
 IS_OMAP_CLASS(34xx, 0x34)
 IS_OMAP_CLASS(44xx, 0x44)
@@ -168,6 +176,8 @@ IS_TI_SUBCLASS(814x, 0x814)
 IS_AM_SUBCLASS(335x, 0x335)
 IS_AM_SUBCLASS(437x, 0x437)
 IS_DRA_SUBCLASS(76x, 0x76)
+IS_DRA_SUBCLASS_PACKAGE(76x, abz, 2)
+IS_DRA_SUBCLASS_PACKAGE(76x, acd, 3)
 IS_DRA_SUBCLASS(75x, 0x75)
 IS_DRA_SUBCLASS(72x, 0x72)
 
@@ -317,10 +327,14 @@ IS_OMAP_TYPE(3430, 0x3430)
 #if defined(CONFIG_SOC_DRA7XX)
 #undef soc_is_dra7xx
 #undef soc_is_dra76x
+#undef soc_is_dra76x_abz
+#undef soc_is_dra76x_acd
 #undef soc_is_dra74x
 #undef soc_is_dra72x
 #define soc_is_dra7xx()	is_dra7xx()
 #define soc_is_dra76x()	is_dra76x()
+#define soc_is_dra76x_abz()	is_dra76x_abz()
+#define soc_is_dra76x_acd()	is_dra76x_acd()
 #define soc_is_dra74x()	is_dra75x()
 #define soc_is_dra72x()	is_dra72x()
 #endif
@@ -391,6 +405,8 @@ IS_OMAP_TYPE(3430, 0x3430)
 
 #define DRA7XX_CLASS		0x07000000
 #define DRA762_REV_ES1_0	(DRA7XX_CLASS | (0x62 << 16) | (0x10 << 8))
+#define DRA762_ABZ_REV_ES1_0	(DRA762_REV_ES1_0 | (2 << 0))
+#define DRA762_ACD_REV_ES1_0	(DRA762_REV_ES1_0 | (3 << 0))
 #define DRA752_REV_ES1_0	(DRA7XX_CLASS | (0x52 << 16) | (0x10 << 8))
 #define DRA752_REV_ES1_1	(DRA7XX_CLASS | (0x52 << 16) | (0x11 << 8))
 #define DRA752_REV_ES2_0	(DRA7XX_CLASS | (0x52 << 16) | (0x20 << 8))
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index ce7d97babb0f..a68b34183107 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -40,6 +40,7 @@ config MACH_PXA3XX_DT
 
 config ARCH_LUBBOCK
 	bool "Intel DBPXA250 Development Platform (aka Lubbock)"
+	select GPIO_REG
 	select PXA25x
 	select SA1111
 
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index d6d92f388f14..f4f8f23bda8c 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -28,7 +28,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/types.h>
 #include <linux/platform_data/pcf857x.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/physmap.h>
 #include <linux/regulator/max1586.h>
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index 868448d2cd82..c487401b6fdb 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -31,7 +31,7 @@
 
 #include <linux/i2c.h>
 #include <linux/platform_data/pca953x.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <linux/mfd/da903x.h>
 #include <linux/regulator/machine.h>
diff --git a/arch/arm/mach-pxa/colibri-evalboard.c b/arch/arm/mach-pxa/colibri-evalboard.c
index dc44fbbe5073..10e2278b7a28 100644
--- a/arch/arm/mach-pxa/colibri-evalboard.c
+++ b/arch/arm/mach-pxa/colibri-evalboard.c
@@ -19,7 +19,7 @@
 #include <mach/hardware.h>
 #include <asm/mach/arch.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <asm/io.h>
 
 #include "pxa27x.h"
diff --git a/arch/arm/mach-pxa/colibri-pxa270-income.c b/arch/arm/mach-pxa/colibri-pxa270-income.c
index d7cf47d03618..3ccf2a95569b 100644
--- a/arch/arm/mach-pxa/colibri-pxa270-income.c
+++ b/arch/arm/mach-pxa/colibri-pxa270-income.c
@@ -23,7 +23,7 @@
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/pwm_backlight.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index 7270f0db3432..9a5a35e90769 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -26,7 +26,7 @@
 #include <linux/gpio.h>
 #include <linux/backlight.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/io.h>
 #include <linux/regulator/machine.h>
 #include <linux/spi/spi.h>
@@ -606,24 +606,6 @@ static void __init corgi_init_spi(void)
 static inline void corgi_init_spi(void) {}
 #endif
 
-static struct mtd_partition sharpsl_nand_partitions[] = {
-	{
-		.name = "System Area",
-		.offset = 0,
-		.size = 7 * 1024 * 1024,
-	},
-	{
-		.name = "Root Filesystem",
-		.offset = 7 * 1024 * 1024,
-		.size = 25 * 1024 * 1024,
-	},
-	{
-		.name = "Home Filesystem",
-		.offset = MTDPART_OFS_APPEND,
-		.size = MTDPART_SIZ_FULL,
-	},
-};
-
 static uint8_t scan_ff_pattern[] = { 0xff, 0xff };
 
 static struct nand_bbt_descr sharpsl_bbt = {
@@ -633,10 +615,16 @@ static struct nand_bbt_descr sharpsl_bbt = {
 	.pattern = scan_ff_pattern
 };
 
+static const char * const probes[] = {
+	"cmdlinepart",
+	"ofpart",
+	"sharpslpart",
+	NULL,
+};
+
 static struct sharpsl_nand_platform_data sharpsl_nand_platform_data = {
 	.badblock_pattern	= &sharpsl_bbt,
-	.partitions		= sharpsl_nand_partitions,
-	.nr_partitions		= ARRAY_SIZE(sharpsl_nand_partitions),
+	.part_parsers		= probes,
 };
 
 static struct resource sharpsl_nand_resources[] = {
@@ -750,9 +738,6 @@ static void __init corgi_init(void)
 
 	platform_scoop_config = &corgi_pcmcia_config;
 
-	if (machine_is_husky())
-		sharpsl_nand_partitions[1].size = 53 * 1024 * 1024;
-
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
 	regulator_has_full_constraints();
diff --git a/arch/arm/mach-pxa/csb726.c b/arch/arm/mach-pxa/csb726.c
index bf19b8426d2c..271aedae7542 100644
--- a/arch/arm/mach-pxa/csb726.c
+++ b/arch/arm/mach-pxa/csb726.c
@@ -17,7 +17,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/sm501.h>
 #include <linux/smsc911x.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index 5a72456a19ce..d7c9a8476d57 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -5,7 +5,7 @@
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/spi/pxa2xx_spi.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include "udc.h"
 #include <linux/platform_data/usb-pxa3xx-ulpi.h>
diff --git a/arch/arm/mach-pxa/devices.h b/arch/arm/mach-pxa/devices.h
index 905628dfbbbb..11263f7c455b 100644
--- a/arch/arm/mach-pxa/devices.h
+++ b/arch/arm/mach-pxa/devices.h
@@ -56,3 +56,12 @@ extern struct platform_device pxa93x_device_gpio;
 
 void __init pxa_register_device(struct platform_device *dev, void *data);
 void __init pxa2xx_set_dmac_info(int nb_channels, int nb_requestors);
+
+struct i2c_pxa_platform_data;
+extern void pxa_set_i2c_info(struct i2c_pxa_platform_data *info);
+#ifdef CONFIG_PXA27x
+extern void pxa27x_set_i2c_power_info(struct i2c_pxa_platform_data *info);
+#endif
+#ifdef CONFIG_PXA3xx
+extern void pxa3xx_set_i2c_power_info(struct i2c_pxa_platform_data *info);
+#endif
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index 6d28035ebba5..49022ad338e9 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -32,7 +32,7 @@
 #include <linux/apm-emulation.h>
 #include <linux/i2c.h>
 #include <linux/platform_data/pca953x.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/regulator/userspace-consumer.h>
 
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c
index a057cf9c0e7b..2c90b58f347d 100644
--- a/arch/arm/mach-pxa/ezx.c
+++ b/arch/arm/mach-pxa/ezx.c
@@ -23,7 +23,7 @@
 #include <linux/gpio.h>
 #include <linux/gpio_keys.h>
 #include <linux/leds-lp3944.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <asm/setup.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index 66184f5cbe40..e2e7f247a645 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -38,7 +38,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/usb/gpio_vbus.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/littleton.c b/arch/arm/mach-pxa/littleton.c
index fae38fdc8d8e..4105614cc38e 100644
--- a/arch/arm/mach-pxa/littleton.c
+++ b/arch/arm/mach-pxa/littleton.c
@@ -28,7 +28,7 @@
 #include <linux/leds.h>
 #include <linux/mfd/da903x.h>
 #include <linux/platform_data/max732x.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <asm/types.h>
 #include <asm/setup.h>
@@ -42,6 +42,7 @@
 #include <asm/mach/irq.h>
 
 #include "pxa300.h"
+#include "devices.h"
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/keypad-pxa27x.h>
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index df45682e99a5..fe2ef9b78602 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -13,6 +13,7 @@
  */
 #include <linux/clkdev.h>
 #include <linux/gpio.h>
+#include <linux/gpio/gpio-reg.h>
 #include <linux/gpio/machine.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -110,20 +111,18 @@ static unsigned long lubbock_pin_config[] __initdata = {
 };
 
 #define LUB_HEXLED		__LUB_REG(LUBBOCK_FPGA_PHYS + 0x010)
-#define LUB_MISC_WR		__LUB_REG(LUBBOCK_FPGA_PHYS + 0x080)
 
 void lubbock_set_hexled(uint32_t value)
 {
 	LUB_HEXLED = value;
 }
 
+static struct gpio_chip *lubbock_misc_wr_gc;
+
 void lubbock_set_misc_wr(unsigned int mask, unsigned int set)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	LUB_MISC_WR = (LUB_MISC_WR & ~mask) | (set & mask);
-	local_irq_restore(flags);
+	unsigned long m = mask, v = set;
+	lubbock_misc_wr_gc->set_multiple(lubbock_misc_wr_gc, &m, &v);
 }
 EXPORT_SYMBOL(lubbock_set_misc_wr);
 
@@ -452,9 +451,9 @@ static void lubbock_irda_transceiver_mode(struct device *dev, int mode)
 
 	local_irq_save(flags);
 	if (mode & IR_SIRMODE) {
-		LUB_MISC_WR &= ~(1 << 4);
+		lubbock_set_misc_wr(BIT(4), 0);
 	} else if (mode & IR_FIRMODE) {
-		LUB_MISC_WR |= 1 << 4;
+		lubbock_set_misc_wr(BIT(4), BIT(4));
 	}
 	pxa2xx_transceiver_mode(dev, mode);
 	local_irq_restore(flags);
@@ -472,6 +471,15 @@ static void __init lubbock_init(void)
 
 	pxa2xx_mfp_config(ARRAY_AND_SIZE(lubbock_pin_config));
 
+	lubbock_misc_wr_gc = gpio_reg_init(NULL, (void *)&LUB_MISC_WR,
+					   -1, 16, "lubbock", 0, LUB_MISC_WR,
+					   NULL, NULL, NULL);
+	if (IS_ERR(lubbock_misc_wr_gc)) {
+		pr_err("Lubbock: unable to register lubbock GPIOs: %ld\n",
+		       PTR_ERR(lubbock_misc_wr_gc));
+		lubbock_misc_wr_gc = NULL;
+	}
+
 	pxa_set_ffuart_info(NULL);
 	pxa_set_btuart_info(NULL);
 	pxa_set_stuart_info(NULL);
diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c
index 7f3566c93733..c5325d1ae77b 100644
--- a/arch/arm/mach-pxa/magician.c
+++ b/arch/arm/mach-pxa/magician.c
@@ -31,7 +31,7 @@
 #include <linux/regulator/gpio-regulator.h>
 #include <linux/regulator/machine.h>
 #include <linux/usb/gpio_vbus.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index a2d851a3a546..afd62a94fdbf 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -29,7 +29,7 @@
 #include <linux/pwm.h>
 #include <linux/pwm_backlight.h>
 #include <linux/smc91x.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/slab.h>
 #include <linux/leds.h>
 
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index 8a5d0491e73c..9b6c7ea45a40 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -42,7 +42,7 @@
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/max1586.h>
 #include <linux/slab.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/mxm8x10.c b/arch/arm/mach-pxa/mxm8x10.c
index 9a22ae0ad8c9..f9e3d41a4609 100644
--- a/arch/arm/mach-pxa/mxm8x10.c
+++ b/arch/arm/mach-pxa/mxm8x10.c
@@ -22,7 +22,7 @@
 #include <linux/serial_8250.h>
 #include <linux/dm9000.h>
 #include <linux/gpio.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <linux/platform_data/mtd-nand-pxa3xx.h>
 
diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c
index e5ae99db1de4..1efe9bcf07fa 100644
--- a/arch/arm/mach-pxa/palm27x.c
+++ b/arch/arm/mach-pxa/palm27x.c
@@ -22,7 +22,7 @@
 #include <linux/power_supply.h>
 #include <linux/usb/gpio_vbus.h>
 #include <linux/regulator/max1586.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c
index 0bd5959ef7d5..973568d4b9ec 100644
--- a/arch/arm/mach-pxa/pcm990-baseboard.c
+++ b/arch/arm/mach-pxa/pcm990-baseboard.c
@@ -23,7 +23,7 @@
 #include <linux/irq.h>
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/pwm.h>
 #include <linux/pwm_backlight.h>
 
diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
index 62a119137be7..1adde1251e2b 100644
--- a/arch/arm/mach-pxa/poodle.c
+++ b/arch/arm/mach-pxa/poodle.c
@@ -24,7 +24,7 @@
 #include <linux/mtd/physmap.h>
 #include <linux/gpio.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/regulator/machine.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
@@ -333,24 +333,6 @@ static struct pxafb_mach_info poodle_fb_info = {
 	.lcd_conn	= LCD_COLOR_TFT_16BPP,
 };
 
-static struct mtd_partition sharpsl_nand_partitions[] = {
-	{
-		.name = "System Area",
-		.offset = 0,
-		.size = 7 * 1024 * 1024,
-	},
-	{
-		.name = "Root Filesystem",
-		.offset = 7 * 1024 * 1024,
-		.size = 22 * 1024 * 1024,
-	},
-	{
-		.name = "Home Filesystem",
-		.offset = MTDPART_OFS_APPEND,
-		.size = MTDPART_SIZ_FULL,
-	},
-};
-
 static uint8_t scan_ff_pattern[] = { 0xff, 0xff };
 
 static struct nand_bbt_descr sharpsl_bbt = {
@@ -360,10 +342,16 @@ static struct nand_bbt_descr sharpsl_bbt = {
 	.pattern = scan_ff_pattern
 };
 
+static const char * const probes[] = {
+	"cmdlinepart",
+	"ofpart",
+	"sharpslpart",
+	NULL,
+};
+
 static struct sharpsl_nand_platform_data sharpsl_nand_platform_data = {
 	.badblock_pattern	= &sharpsl_bbt,
-	.partitions		= sharpsl_nand_partitions,
-	.nr_partitions		= ARRAY_SIZE(sharpsl_nand_partitions),
+	.part_parsers		= probes,
 };
 
 static struct resource sharpsl_nand_resources[] = {
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index 9b69be4e9fe3..0c06f383ad52 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -22,7 +22,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/io.h>
 #include <linux/irq.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <asm/mach/map.h>
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index 0cc9f124c9ac..4b8a0df8ea57 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -23,7 +23,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/syscore_ops.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <asm/mach/map.h>
 #include <asm/suspend.h>
diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c
index 9d662fed03ec..4d5d05cf87d6 100644
--- a/arch/arm/mach-pxa/raumfeld.c
+++ b/arch/arm/mach-pxa/raumfeld.c
@@ -32,7 +32,7 @@
 #include <linux/pwm.h>
 #include <linux/pwm_backlight.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_gpio.h>
 #include <linux/lis3lv02d.h>
@@ -506,11 +506,16 @@ static void w1_enable_external_pullup(int enable)
 	msleep(100);
 }
 
+static struct gpiod_lookup_table raumfeld_w1_gpiod_table = {
+	.dev_id = "w1-gpio",
+	.table = {
+		GPIO_LOOKUP_IDX("gpio-pxa", GPIO_ONE_WIRE, NULL, 0,
+				GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
+	},
+};
+
 static struct w1_gpio_platform_data w1_gpio_platform_data = {
-	.pin			= GPIO_ONE_WIRE,
-	.is_open_drain		= 0,
-	.enable_external_pullup	= w1_enable_external_pullup,
-	.ext_pullup_enable_pin	= -EINVAL,
+	.enable_external_pullup = w1_enable_external_pullup,
 };
 
 static struct platform_device raumfeld_w1_gpio_device = {
@@ -523,13 +528,14 @@ static struct platform_device raumfeld_w1_gpio_device = {
 static void __init raumfeld_w1_init(void)
 {
 	int ret = gpio_request(GPIO_W1_PULLUP_ENABLE,
-				"W1 external pullup enable");
+			        "W1 external pullup enable");
 
 	if (ret < 0)
 		pr_warn("Unable to request GPIO_W1_PULLUP_ENABLE\n");
 	else
 		gpio_direction_output(GPIO_W1_PULLUP_ENABLE, 0);
 
+	gpiod_add_lookup_table(&raumfeld_w1_gpiod_table);
 	platform_device_register(&raumfeld_w1_gpio_device);
 }
 
diff --git a/arch/arm/mach-pxa/saar.c b/arch/arm/mach-pxa/saar.c
index 1414b5f29114..834991034f30 100644
--- a/arch/arm/mach-pxa/saar.c
+++ b/arch/arm/mach-pxa/saar.c
@@ -20,7 +20,7 @@
 #include <linux/delay.h>
 #include <linux/fb.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/smc91x.h>
 #include <linux/mfd/da903x.h>
 #include <linux/mtd/mtd.h>
diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c
index 398ba9ba2632..ef9fd9b759cb 100644
--- a/arch/arm/mach-pxa/sharpsl_pm.c
+++ b/arch/arm/mach-pxa/sharpsl_pm.c
@@ -802,8 +802,8 @@ static ssize_t battery_voltage_show(struct device *dev, struct device_attribute
 	return sprintf(buf, "%d\n", sharpsl_pm.battstat.mainbat_voltage);
 }
 
-static DEVICE_ATTR(battery_percentage, 0444, battery_percentage_show, NULL);
-static DEVICE_ATTR(battery_voltage, 0444, battery_voltage_show, NULL);
+static DEVICE_ATTR_RO(battery_percentage);
+static DEVICE_ATTR_RO(battery_voltage);
 
 extern void (*apm_get_power_status)(struct apm_power_info *);
 
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index 67d66c702574..5d50025492b7 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -20,7 +20,7 @@
 #include <linux/gpio.h>
 #include <linux/leds.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/pca953x.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
@@ -739,21 +739,6 @@ static inline void spitz_lcd_init(void) {}
  * NAND Flash
  ******************************************************************************/
 #if defined(CONFIG_MTD_NAND_SHARPSL) || defined(CONFIG_MTD_NAND_SHARPSL_MODULE)
-static struct mtd_partition spitz_nand_partitions[] = {
-	{
-		.name = "System Area",
-		.offset = 0,
-		.size = 7 * 1024 * 1024,
-	}, {
-		.name = "Root Filesystem",
-		.offset = 7 * 1024 * 1024,
-	}, {
-		.name = "Home Filesystem",
-		.offset = MTDPART_OFS_APPEND,
-		.size = MTDPART_SIZ_FULL,
-	},
-};
-
 static uint8_t scan_ff_pattern[] = { 0xff, 0xff };
 
 static struct nand_bbt_descr spitz_nand_bbt = {
@@ -808,10 +793,16 @@ static const struct mtd_ooblayout_ops akita_ooblayout_ops = {
 	.free = akita_ooblayout_free,
 };
 
+static const char * const probes[] = {
+	"cmdlinepart",
+	"ofpart",
+	"sharpslpart",
+	NULL,
+};
+
 static struct sharpsl_nand_platform_data spitz_nand_pdata = {
 	.badblock_pattern	= &spitz_nand_bbt,
-	.partitions		= spitz_nand_partitions,
-	.nr_partitions		= ARRAY_SIZE(spitz_nand_partitions),
+	.part_parsers		= probes,
 };
 
 static struct resource spitz_nand_resources[] = {
@@ -834,14 +825,7 @@ static struct platform_device spitz_nand_device = {
 
 static void __init spitz_nand_init(void)
 {
-	if (machine_is_spitz()) {
-		spitz_nand_partitions[1].size = 5 * 1024 * 1024;
-	} else if (machine_is_akita()) {
-		spitz_nand_partitions[1].size = 58 * 1024 * 1024;
-		spitz_nand_bbt.len = 1;
-		spitz_nand_pdata.ecc_layout = &akita_ooblayout_ops;
-	} else if (machine_is_borzoi()) {
-		spitz_nand_partitions[1].size = 32 * 1024 * 1024;
+	if (machine_is_akita() || machine_is_borzoi()) {
 		spitz_nand_bbt.len = 1;
 		spitz_nand_pdata.ecc_layout = &akita_ooblayout_ops;
 	}
diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c
index 6b7df6fd2448..df62bb23dbee 100644
--- a/arch/arm/mach-pxa/stargate2.c
+++ b/arch/arm/mach-pxa/stargate2.c
@@ -25,7 +25,7 @@
 #include <linux/mtd/plat-ram.h>
 #include <linux/mtd/partitions.h>
 
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/pcf857x.h>
 #include <linux/platform_data/at24.h>
 #include <linux/smc91x.h>
diff --git a/arch/arm/mach-pxa/tosa-bt.c b/arch/arm/mach-pxa/tosa-bt.c
index 107f37210fb9..83606087edc7 100644
--- a/arch/arm/mach-pxa/tosa-bt.c
+++ b/arch/arm/mach-pxa/tosa-bt.c
@@ -132,3 +132,7 @@ static struct platform_driver tosa_bt_driver = {
 	},
 };
 module_platform_driver(tosa_bt_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dmitry Baryshkov");
+MODULE_DESCRIPTION("Bluetooth built-in chip control");
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 6a386fd6363e..cb5cd8e78c94 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -35,7 +35,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/input/matrix_keypad.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/usb/gpio_vbus.h>
 #include <linux/reboot.h>
 #include <linux/memblock.h>
@@ -673,24 +673,6 @@ static int tosa_tc6393xb_suspend(struct platform_device *dev)
 	return 0;
 }
 
-static struct mtd_partition tosa_nand_partition[] = {
-	{
-		.name	= "smf",
-		.offset	= 0,
-		.size	= 7 * 1024 * 1024,
-	},
-	{
-		.name	= "root",
-		.offset	= MTDPART_OFS_APPEND,
-		.size	= 28 * 1024 * 1024,
-	},
-	{
-		.name	= "home",
-		.offset	= MTDPART_OFS_APPEND,
-		.size	= MTDPART_SIZ_FULL,
-	},
-};
-
 static uint8_t scan_ff_pattern[] = { 0xff, 0xff };
 
 static struct nand_bbt_descr tosa_tc6393xb_nand_bbt = {
@@ -700,10 +682,16 @@ static struct nand_bbt_descr tosa_tc6393xb_nand_bbt = {
 	.pattern	= scan_ff_pattern
 };
 
+static const char * const probes[] = {
+	"cmdlinepart",
+	"ofpart",
+	"sharpslpart",
+	NULL,
+};
+
 static struct tmio_nand_data tosa_tc6393xb_nand_config = {
-	.num_partitions	= ARRAY_SIZE(tosa_nand_partition),
-	.partition	= tosa_nand_partition,
 	.badblock_pattern = &tosa_tc6393xb_nand_bbt,
+	.part_parsers = probes,
 };
 
 static int tosa_tc6393xb_setup(struct platform_device *dev)
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index 3dd13b44c311..55b8c501b6fc 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -28,7 +28,7 @@
 #include <linux/mtd/physmap.h>
 #include <linux/mtd/partitions.h>
 #include <linux/regulator/machine.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <asm/types.h>
 #include <asm/setup.h>
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index 4185e7ff073f..90d0f277de55 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -37,7 +37,7 @@
 #include <linux/jiffies.h>
 #include <linux/i2c-gpio.h>
 #include <linux/gpio/machine.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/serial_8250.h>
 #include <linux/smc91x.h>
 #include <linux/pwm.h>
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index 70ab3ad28237..f65dfb6e20e2 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -27,7 +27,7 @@
 #include <linux/ata_platform.h>
 #include <linux/regulator/machine.h>
 #include <linux/regulator/max1586.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c
index 056369ef250e..c368c98584c0 100644
--- a/arch/arm/mach-pxa/xcep.c
+++ b/arch/arm/mach-pxa/xcep.c
@@ -16,7 +16,7 @@
 
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/smc91x.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
@@ -32,6 +32,7 @@
 #include <mach/smemc.h>
 
 #include "generic.h"
+#include "devices.h"
 
 #define XCEP_ETH_PHYS		(PXA_CS3_PHYS + 0x00000300)
 #define XCEP_ETH_PHYS_END	(PXA_CS3_PHYS + 0x000fffff)
diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c
index 510e533871f3..6fffcfc4621e 100644
--- a/arch/arm/mach-pxa/z2.c
+++ b/arch/arm/mach-pxa/z2.c
@@ -30,7 +30,7 @@
 #include <linux/gpio_keys.h>
 #include <linux/delay.h>
 #include <linux/regulator/machine.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index ecbcaee5a2d5..e3851795d6d7 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -26,7 +26,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/pca953x.h>
 #include <linux/apm-emulation.h>
 #include <linux/can/platform/mcp251x.h>
@@ -40,6 +40,7 @@
 #include <asm/mach/map.h>
 
 #include "pxa27x.h"
+#include "devices.h"
 #include <mach/regs-uart.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include <linux/platform_data/mmc-pxamci.h>
diff --git a/arch/arm/mach-pxa/zylonite_pxa300.c b/arch/arm/mach-pxa/zylonite_pxa300.c
index e247acf1400a..0ff4e218080f 100644
--- a/arch/arm/mach-pxa/zylonite_pxa300.c
+++ b/arch/arm/mach-pxa/zylonite_pxa300.c
@@ -17,11 +17,12 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pxa-i2c.h>
+#include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/pca953x.h>
 #include <linux/gpio.h>
 
 #include "pxa300.h"
+#include "devices.h"
 #include "zylonite.h"
 
 #include "generic.h"
diff --git a/arch/arm/mach-s3c24xx/Kconfig b/arch/arm/mach-s3c24xx/Kconfig
index b198be7d32b6..686f0bbde998 100644
--- a/arch/arm/mach-s3c24xx/Kconfig
+++ b/arch/arm/mach-s3c24xx/Kconfig
@@ -1,11 +1,9 @@
-# arch/arm/mach-s3c24xx/Kconfig
+# SPDX-License-Identifier: GPL-2.0
 #
 # Copyright (c) 2012 Samsung Electronics Co., Ltd.
 #		http://www.samsung.com/
 #
 # Copyright 2007 Simtec Electronics
-#
-# Licensed under GPLv2
 
 if ARCH_S3C24XX
 
diff --git a/arch/arm/mach-s3c24xx/Makefile b/arch/arm/mach-s3c24xx/Makefile
index 8ac2f58a3480..6692f2de71b2 100644
--- a/arch/arm/mach-s3c24xx/Makefile
+++ b/arch/arm/mach-s3c24xx/Makefile
@@ -1,11 +1,9 @@
-# arch/arm/mach-s3c24xx/Makefile
+# SPDX-License-Identifier: GPL-2.0
 #
 # Copyright (c) 2012 Samsung Electronics Co., Ltd.
 #		http://www.samsung.com/
 #
 # Copyright 2007 Simtec Electronics
-#
-# Licensed under GPLv2
 
 # core
 
diff --git a/arch/arm/mach-s3c24xx/Makefile.boot b/arch/arm/mach-s3c24xx/Makefile.boot
index 4457605ba04a..7f19e226035e 100644
--- a/arch/arm/mach-s3c24xx/Makefile.boot
+++ b/arch/arm/mach-s3c24xx/Makefile.boot
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
 ifeq ($(CONFIG_PM_H1940),y)
 	zreladdr-y	+= 0x30108000
 	params_phys-y	:= 0x30100100
diff --git a/arch/arm/mach-s3c24xx/anubis.h b/arch/arm/mach-s3c24xx/anubis.h
index 2691665f27d9..13847292e6c7 100644
--- a/arch/arm/mach-s3c24xx/anubis.h
+++ b/arch/arm/mach-s3c24xx/anubis.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2005 Simtec Electronics
  *	http://www.simtec.co.uk/products/
@@ -6,11 +7,7 @@
  * ANUBIS - CPLD control constants
  * ANUBIS - IRQ Number definitions
  * ANUBIS - Memory map definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __MACH_S3C24XX_ANUBIS_H
 #define __MACH_S3C24XX_ANUBIS_H __FILE__
diff --git a/arch/arm/mach-s3c24xx/bast-ide.c b/arch/arm/mach-s3c24xx/bast-ide.c
index 3f0288f2f542..067944398f46 100644
--- a/arch/arm/mach-s3c24xx/bast-ide.c
+++ b/arch/arm/mach-s3c24xx/bast-ide.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/mach-s3c2410/bast-ide.c
- *
- * Copyright 2007 Simtec Electronics
- *	http://www.simtec.co.uk/products/EB2410ITX/
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2007 Simtec Electronics
+//	http://www.simtec.co.uk/products/EB2410ITX/
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/bast-irq.c b/arch/arm/mach-s3c24xx/bast-irq.c
index ad8f4cd7c327..03728058d58d 100644
--- a/arch/arm/mach-s3c24xx/bast-irq.c
+++ b/arch/arm/mach-s3c24xx/bast-irq.c
@@ -1,25 +1,9 @@
-/* linux/arch/arm/mach-s3c2410/bast-irq.c
- *
- * Copyright 2003-2005 Simtec Electronics
- *   Ben Dooks <ben@simtec.co.uk>
- *
- * http://www.simtec.co.uk/products/EB2410ITX/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-*/
-
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2003-2005 Simtec Electronics
+//   Ben Dooks <ben@simtec.co.uk>
+//
+// http://www.simtec.co.uk/products/EB2410ITX/
 
 #include <linux/init.h>
 #include <linux/module.h>
diff --git a/arch/arm/mach-s3c24xx/bast.h b/arch/arm/mach-s3c24xx/bast.h
index 5c7534bae92d..a7726f93f5eb 100644
--- a/arch/arm/mach-s3c24xx/bast.h
+++ b/arch/arm/mach-s3c24xx/bast.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2003-2004 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
@@ -5,11 +6,7 @@
  * BAST - CPLD control constants
  * BAST - IRQ Number definitions
  * BAST - Memory map definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __MACH_S3C24XX_BAST_H
 #define __MACH_S3C24XX_BAST_H __FILE__
diff --git a/arch/arm/mach-s3c24xx/common-smdk.c b/arch/arm/mach-s3c24xx/common-smdk.c
index 0e116c92bf01..58e30cad386c 100644
--- a/arch/arm/mach-s3c24xx/common-smdk.c
+++ b/arch/arm/mach-s3c24xx/common-smdk.c
@@ -1,16 +1,11 @@
-/* linux/arch/arm/plat-s3c24xx/common-smdk.c
- *
- * Copyright (c) 2006 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Common code for SMDK2410 and SMDK2440 boards
- *
- * http://www.fluff.org/ben/smdk2440/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2006 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// Common code for SMDK2410 and SMDK2440 boards
+//
+// http://www.fluff.org/ben/smdk2440/
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/common-smdk.h b/arch/arm/mach-s3c24xx/common-smdk.h
index 98f733e1cb42..c0352b06e435 100644
--- a/arch/arm/mach-s3c24xx/common-smdk.h
+++ b/arch/arm/mach-s3c24xx/common-smdk.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2006 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
@@ -5,10 +6,6 @@
  * Common code for SMDK2410 and SMDK2440 boards
  *
  * http://www.fluff.org/ben/smdk2440/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 extern void smdk_machine_init(void);
diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c
index 5b6b94ef41e2..3dc029c2d2cb 100644
--- a/arch/arm/mach-s3c24xx/common.c
+++ b/arch/arm/mach-s3c24xx/common.c
@@ -1,25 +1,10 @@
-/* linux/arch/arm/plat-s3c24xx/cpu.c
- *
- * Copyright (c) 2004-2005 Simtec Electronics
- *	http://www.simtec.co.uk/products/SWLINUX/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Common code for S3C24XX machines
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-*/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2004-2005 Simtec Electronics
+//	http://www.simtec.co.uk/products/SWLINUX/
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// Common code for S3C24XX machines
 
 #include <linux/dma-mapping.h>
 #include <linux/init.h>
diff --git a/arch/arm/mach-s3c24xx/common.h b/arch/arm/mach-s3c24xx/common.h
index c7ac7e61a22e..d087b20e8857 100644
--- a/arch/arm/mach-s3c24xx/common.h
+++ b/arch/arm/mach-s3c24xx/common.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Common Header for S3C24XX SoCs
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __ARCH_ARM_MACH_S3C24XX_COMMON_H
diff --git a/arch/arm/mach-s3c24xx/cpufreq-utils.c b/arch/arm/mach-s3c24xx/cpufreq-utils.c
index d4d9514335f4..1a7f38d085dd 100644
--- a/arch/arm/mach-s3c24xx/cpufreq-utils.c
+++ b/arch/arm/mach-s3c24xx/cpufreq-utils.c
@@ -1,14 +1,10 @@
-/*
- * Copyright (c) 2009 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C24XX CPU Frequency scaling - utils for S3C2410/S3C2440/S3C2442
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2009 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// S3C24XX CPU Frequency scaling - utils for S3C2410/S3C2440/S3C2442
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
diff --git a/arch/arm/mach-s3c24xx/fb-core.h b/arch/arm/mach-s3c24xx/fb-core.h
index 103bdbaddd55..1821e820262c 100644
--- a/arch/arm/mach-s3c24xx/fb-core.h
+++ b/arch/arm/mach-s3c24xx/fb-core.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2010 Samsung Electronics Co., Ltd.
  *	Pawel Osciak <p.osciak@samsung.com>
  *
  * Samsung framebuffer driver core functions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #ifndef __ASM_PLAT_FB_CORE_H
 #define __ASM_PLAT_FB_CORE_H __FILE__
diff --git a/arch/arm/mach-s3c24xx/gta02.h b/arch/arm/mach-s3c24xx/gta02.h
index 9430a71e9184..d5610ba829a4 100644
--- a/arch/arm/mach-s3c24xx/gta02.h
+++ b/arch/arm/mach-s3c24xx/gta02.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * GTA02 header
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __MACH_S3C24XX_GTA02_H
 #define __MACH_S3C24XX_GTA02_H __FILE__
diff --git a/arch/arm/mach-s3c24xx/h1940-bluetooth.c b/arch/arm/mach-s3c24xx/h1940-bluetooth.c
index 9c8b1279a4ba..46ad20ea87d1 100644
--- a/arch/arm/mach-s3c24xx/h1940-bluetooth.c
+++ b/arch/arm/mach-s3c24xx/h1940-bluetooth.c
@@ -1,14 +1,8 @@
-/*
- * arch/arm/mach-s3c2410/h1940-bluetooth.c
- * Copyright (c) Arnaud Patard <arnaud.patard@rtp-net.org>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive for
- * more details.
- *
- *	    S3C2410 bluetooth "driver"
- *
- */
+// SPDX-License-Identifier: GPL-1.0
+//
+// Copyright (c) Arnaud Patard <arnaud.patard@rtp-net.org>
+//
+//	    S3C2410 bluetooth "driver"
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
diff --git a/arch/arm/mach-s3c24xx/h1940.h b/arch/arm/mach-s3c24xx/h1940.h
index 596d9f64c5b6..5dfe9d10cd15 100644
--- a/arch/arm/mach-s3c24xx/h1940.h
+++ b/arch/arm/mach-s3c24xx/h1940.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2006 Ben Dooks <ben-linux@fluff.org>
  *
@@ -6,11 +7,7 @@
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * iPAQ H1940 series definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __MACH_S3C24XX_H1940_H
 #define __MACH_S3C24XX_H1940_H __FILE__
diff --git a/arch/arm/mach-s3c24xx/include/mach/dma.h b/arch/arm/mach-s3c24xx/include/mach/dma.h
index 9e8117198e0c..25fc9c258fc1 100644
--- a/arch/arm/mach-s3c24xx/include/mach/dma.h
+++ b/arch/arm/mach-s3c24xx/include/mach/dma.h
@@ -1,14 +1,10 @@
-/* arch/arm/mach-s3c2410/include/mach/dma.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (C) 2003-2006 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * Samsung S3C24XX DMA support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_ARCH_DMA_H
 #define __ASM_ARCH_DMA_H __FILE__
diff --git a/arch/arm/mach-s3c24xx/include/mach/fb.h b/arch/arm/mach-s3c24xx/include/mach/fb.h
index a957bc8ed44f..4e539cb8b884 100644
--- a/arch/arm/mach-s3c24xx/include/mach/fb.h
+++ b/arch/arm/mach-s3c24xx/include/mach/fb.h
@@ -1 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <plat/fb-s3c2410.h>
diff --git a/arch/arm/mach-s3c24xx/include/mach/gpio-samsung.h b/arch/arm/mach-s3c24xx/include/mach/gpio-samsung.h
index 528fcdc4f63e..2ad22b2d459b 100644
--- a/arch/arm/mach-s3c24xx/include/mach/gpio-samsung.h
+++ b/arch/arm/mach-s3c24xx/include/mach/gpio-samsung.h
@@ -1,14 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2008 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C2410 - GPIO lib support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /* some boards require extra gpio capacity to support external
  * devices that need GPIO.
diff --git a/arch/arm/mach-s3c24xx/include/mach/hardware.h b/arch/arm/mach-s3c24xx/include/mach/hardware.h
index dedd3837c193..1b2975708e3f 100644
--- a/arch/arm/mach-s3c24xx/include/mach/hardware.h
+++ b/arch/arm/mach-s3c24xx/include/mach/hardware.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2003 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C2410 - hardware
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_ARCH_HARDWARE_H
 #define __ASM_ARCH_HARDWARE_H
diff --git a/arch/arm/mach-s3c24xx/include/mach/irqs.h b/arch/arm/mach-s3c24xx/include/mach/irqs.h
index b6dd4cb5a2ec..aaf3bae08b52 100644
--- a/arch/arm/mach-s3c24xx/include/mach/irqs.h
+++ b/arch/arm/mach-s3c24xx/include/mach/irqs.h
@@ -1,12 +1,8 @@
-/* arch/arm/mach-s3c2410/include/mach/irqs.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2003-2005 Simtec Electronics
  *   Ben Dooks <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 
 #ifndef __ASM_ARCH_IRQS_H
diff --git a/arch/arm/mach-s3c24xx/include/mach/map.h b/arch/arm/mach-s3c24xx/include/mach/map.h
index adc39043aa21..bca93112f57d 100644
--- a/arch/arm/mach-s3c24xx/include/mach/map.h
+++ b/arch/arm/mach-s3c24xx/include/mach/map.h
@@ -1,14 +1,10 @@
-/* arch/arm/mach-s3c2410/include/mach/map.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2003 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C2410 - Memory map definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_ARCH_MAP_H
 #define __ASM_ARCH_MAP_H
diff --git a/arch/arm/mach-s3c24xx/include/mach/pm-core.h b/arch/arm/mach-s3c24xx/include/mach/pm-core.h
index 712333fec589..5e4ce89d0158 100644
--- a/arch/arm/mach-s3c24xx/include/mach/pm-core.h
+++ b/arch/arm/mach-s3c24xx/include/mach/pm-core.h
@@ -1,15 +1,12 @@
-/* linux/arch/arm/mach-s3c2410/include/pm-core.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2008 Simtec Electronics
  *      Ben Dooks <ben@simtec.co.uk>
  *      http://armlinux.simtec.co.uk/
  *
  * S3C24xx - PM core support for arch/arm/plat-s3c/pm.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
+
 #include <linux/delay.h>
 #include <linux/io.h>
 
diff --git a/arch/arm/mach-s3c24xx/include/mach/regs-clock.h b/arch/arm/mach-s3c24xx/include/mach/regs-clock.h
index ae4a3e0f3ba2..7ca3dd4f13c0 100644
--- a/arch/arm/mach-s3c24xx/include/mach/regs-clock.h
+++ b/arch/arm/mach-s3c24xx/include/mach/regs-clock.h
@@ -1,14 +1,10 @@
-/* arch/arm/mach-s3c2410/include/mach/regs-clock.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2003-2006 Simtec Electronics <linux@simtec.co.uk>
  *	http://armlinux.simtec.co.uk/
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * S3C2410 clock register definitions
-*/
+ */
 
 #ifndef __ASM_ARM_REGS_CLOCK
 #define __ASM_ARM_REGS_CLOCK
diff --git a/arch/arm/mach-s3c24xx/include/mach/regs-gpio.h b/arch/arm/mach-s3c24xx/include/mach/regs-gpio.h
index 0d622f3b57a5..594e967c0673 100644
--- a/arch/arm/mach-s3c24xx/include/mach/regs-gpio.h
+++ b/arch/arm/mach-s3c24xx/include/mach/regs-gpio.h
@@ -1,14 +1,10 @@
-/* arch/arm/mach-s3c2410/include/mach/regs-gpio.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2003-2004 Simtec Electronics <linux@simtec.co.uk>
  *	http://www.simtec.co.uk/products/SWLINUX/
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * S3C2410 GPIO register definitions
-*/
+ */
 
 
 #ifndef __ASM_ARCH_REGS_GPIO_H
diff --git a/arch/arm/mach-s3c24xx/include/mach/regs-irq.h b/arch/arm/mach-s3c24xx/include/mach/regs-irq.h
index 0f07ba30b1fb..8d8e669e3903 100644
--- a/arch/arm/mach-s3c24xx/include/mach/regs-irq.h
+++ b/arch/arm/mach-s3c24xx/include/mach/regs-irq.h
@@ -1,12 +1,8 @@
-/* arch/arm/mach-s3c2410/include/mach/regs-irq.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2003 Simtec Electronics <linux@simtec.co.uk>
  *		      http://www.simtec.co.uk/products/SWLINUX/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 
 #ifndef ___ASM_ARCH_REGS_IRQ_H
diff --git a/arch/arm/mach-s3c24xx/include/mach/regs-lcd.h b/arch/arm/mach-s3c24xx/include/mach/regs-lcd.h
index ee8f040aff5f..4c3434f261bb 100644
--- a/arch/arm/mach-s3c24xx/include/mach/regs-lcd.h
+++ b/arch/arm/mach-s3c24xx/include/mach/regs-lcd.h
@@ -1,13 +1,8 @@
-/* arch/arm/mach-s3c2410/include/mach/regs-lcd.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2003 Simtec Electronics <linux@simtec.co.uk>
  *		      http://www.simtec.co.uk/products/SWLINUX/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
+ */
 
 #ifndef ___ASM_ARCH_REGS_LCD_H
 #define ___ASM_ARCH_REGS_LCD_H
diff --git a/arch/arm/mach-s3c24xx/include/mach/regs-s3c2443-clock.h b/arch/arm/mach-s3c24xx/include/mach/regs-s3c2443-clock.h
index ffe37bdb9f59..6bf924612b06 100644
--- a/arch/arm/mach-s3c24xx/include/mach/regs-s3c2443-clock.h
+++ b/arch/arm/mach-s3c24xx/include/mach/regs-s3c2443-clock.h
@@ -1,15 +1,11 @@
-/* arch/arm/mach-s3c2410/include/mach/regs-s3c2443-clock.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2007 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *	http://armlinux.simtec.co.uk/
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * S3C2443 clock register definitions
-*/
+ */
 
 #ifndef __ASM_ARM_REGS_S3C2443_CLOCK
 #define __ASM_ARM_REGS_S3C2443_CLOCK
diff --git a/arch/arm/mach-s3c24xx/include/mach/rtc-core.h b/arch/arm/mach-s3c24xx/include/mach/rtc-core.h
index 4d5f5768f700..88510333b96b 100644
--- a/arch/arm/mach-s3c24xx/include/mach/rtc-core.h
+++ b/arch/arm/mach-s3c24xx/include/mach/rtc-core.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2011 Heiko Stuebner <heiko@sntech.de>
  *
  * Samsung RTC Controller core functions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __RTC_CORE_H
 #define __RTC_CORE_H __FILE__
diff --git a/arch/arm/mach-s3c24xx/include/mach/s3c2412.h b/arch/arm/mach-s3c24xx/include/mach/s3c2412.h
index 548ced42cbb7..b6b32724ace8 100644
--- a/arch/arm/mach-s3c24xx/include/mach/s3c2412.h
+++ b/arch/arm/mach-s3c24xx/include/mach/s3c2412.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2008 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *	http://armlinux.simtec.co.uk/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __ARCH_ARM_MACH_S3C24XX_S3C2412_H
diff --git a/arch/arm/mach-s3c24xx/iotiming-s3c2410.c b/arch/arm/mach-s3c24xx/iotiming-s3c2410.c
index d5f1f06e4811..9f90aaf70bf3 100644
--- a/arch/arm/mach-s3c24xx/iotiming-s3c2410.c
+++ b/arch/arm/mach-s3c24xx/iotiming-s3c2410.c
@@ -1,14 +1,10 @@
-/*
- * Copyright (c) 2006-2009 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C24XX CPU Frequency scaling - IO timing for S3C2410/S3C2440/S3C2442
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2006-2009 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// S3C24XX CPU Frequency scaling - IO timing for S3C2410/S3C2440/S3C2442
 
 #include <linux/init.h>
 #include <linux/kernel.h>
diff --git a/arch/arm/mach-s3c24xx/iotiming-s3c2412.c b/arch/arm/mach-s3c24xx/iotiming-s3c2412.c
index c5b12f6b02b5..59356d10fbcf 100644
--- a/arch/arm/mach-s3c24xx/iotiming-s3c2412.c
+++ b/arch/arm/mach-s3c24xx/iotiming-s3c2412.c
@@ -1,14 +1,10 @@
-/*
- * Copyright (c) 2006-2008 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C2412/S3C2443 (PL093 based) IO timing support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2006-2008 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// S3C2412/S3C2443 (PL093 based) IO timing support
 
 #include <linux/init.h>
 #include <linux/module.h>
diff --git a/arch/arm/mach-s3c24xx/irq-pm.c b/arch/arm/mach-s3c24xx/irq-pm.c
index 417b7a20c2d1..e0131b16a4af 100644
--- a/arch/arm/mach-s3c24xx/irq-pm.c
+++ b/arch/arm/mach-s3c24xx/irq-pm.c
@@ -1,15 +1,10 @@
-/* linux/arch/arm/plat-s3c24xx/irq-om.c
- *
- * Copyright (c) 2003-2004 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * S3C24XX - IRQ PM code
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2003-2004 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// S3C24XX - IRQ PM code
 
 #include <linux/init.h>
 #include <linux/module.h>
diff --git a/arch/arm/mach-s3c24xx/mach-amlm5900.c b/arch/arm/mach-s3c24xx/mach-amlm5900.c
index 3e63777a109f..9a9daf526d0c 100644
--- a/arch/arm/mach-s3c24xx/mach-amlm5900.c
+++ b/arch/arm/mach-s3c24xx/mach-amlm5900.c
@@ -1,30 +1,11 @@
-/* linux/arch/arm/mach-s3c2410/mach-amlm5900.c
- *
- * linux/arch/arm/mach-s3c2410/mach-amlm5900.c
- *
- * Copyright (c) 2006 American Microsystems Limited
- *	David Anders <danders@amltd.com>
-
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
- *
- * @History:
- * derived from linux/arch/arm/mach-s3c2410/mach-bast.c, written by
- * Ben Dooks <ben@simtec.co.uk>
- *
- ***********************************************************************/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2006 American Microsystems Limited
+//	David Anders <danders@amltd.com>
+//
+// @History:
+// derived from linux/arch/arm/mach-s3c2410/mach-bast.c, written by
+// Ben Dooks <ben@simtec.co.uk>
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-anubis.c b/arch/arm/mach-s3c24xx/mach-anubis.c
index c14cab361922..072966dcad78 100644
--- a/arch/arm/mach-s3c24xx/mach-anubis.c
+++ b/arch/arm/mach-s3c24xx/mach-anubis.c
@@ -1,13 +1,8 @@
-/* linux/arch/arm/mach-s3c2440/mach-anubis.c
- *
- * Copyright 2003-2009 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2003-2009 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-at2440evb.c b/arch/arm/mach-s3c24xx/mach-at2440evb.c
index ebdbafb9382a..68a4fa94257a 100644
--- a/arch/arm/mach-s3c24xx/mach-at2440evb.c
+++ b/arch/arm/mach-s3c24xx/mach-at2440evb.c
@@ -1,16 +1,11 @@
-/* linux/arch/arm/mach-s3c2440/mach-at2440evb.c
- *
- * Copyright (c) 2008 Ramax Lo <ramaxlo@gmail.com>
- *      Based on mach-anubis.c by Ben Dooks <ben@simtec.co.uk>
- *      and modifications by SBZ <sbz@spgui.org> and
- *      Weibing <http://weibing.blogbus.com>
- *
- * For product information, visit http://www.arm.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2008 Ramax Lo <ramaxlo@gmail.com>
+//      Based on mach-anubis.c by Ben Dooks <ben@simtec.co.uk>
+//      and modifications by SBZ <sbz@spgui.org> and
+//      Weibing <http://weibing.blogbus.com>
+//
+// For product information, visit http://www.arm.com/
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-bast.c b/arch/arm/mach-s3c24xx/mach-bast.c
index 704dc84b3480..a7c3955ae8f6 100644
--- a/arch/arm/mach-s3c24xx/mach-bast.c
+++ b/arch/arm/mach-s3c24xx/mach-bast.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/mach-s3c2410/mach-bast.c
- *
- * Copyright 2003-2008 Simtec Electronics
- *   Ben Dooks <ben@simtec.co.uk>
- *
- * http://www.simtec.co.uk/products/EB2410ITX/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2003-2008 Simtec Electronics
+//   Ben Dooks <ben@simtec.co.uk>
+//
+// http://www.simtec.co.uk/products/EB2410ITX/
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-gta02.c b/arch/arm/mach-s3c24xx/mach-gta02.c
index afe18baf0c84..9d5595c4ad99 100644
--- a/arch/arm/mach-s3c24xx/mach-gta02.c
+++ b/arch/arm/mach-s3c24xx/mach-gta02.c
@@ -1,27 +1,12 @@
-/*
- * S3C2442 Machine Support for Openmoko GTA02 / FreeRunner.
- *
- * Copyright (C) 2006-2009 by Openmoko, Inc.
- * Authors: Harald Welte <laforge@openmoko.org>
- *          Andy Green <andy@openmoko.org>
- *          Werner Almesberger <werner@openmoko.org>
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// S3C2442 Machine Support for Openmoko GTA02 / FreeRunner.
+//
+// Copyright (C) 2006-2009 by Openmoko, Inc.
+// Authors: Harald Welte <laforge@openmoko.org>
+//          Andy Green <andy@openmoko.org>
+//          Werner Almesberger <werner@openmoko.org>
+// All rights reserved.
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-h1940.c b/arch/arm/mach-s3c24xx/mach-h1940.c
index 7ed78619217c..e064c73a57d3 100644
--- a/arch/arm/mach-s3c24xx/mach-h1940.c
+++ b/arch/arm/mach-s3c24xx/mach-h1940.c
@@ -1,14 +1,9 @@
-/*
- * Copyright (c) 2003-2005 Simtec Electronics
- *   Ben Dooks <ben@simtec.co.uk>
- *
- * http://www.handhelds.org/projects/h1940.html
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2003-2005 Simtec Electronics
+//   Ben Dooks <ben@simtec.co.uk>
+//
+// http://www.handhelds.org/projects/h1940.html
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-jive.c b/arch/arm/mach-s3c24xx/mach-jive.c
index 17821976f769..a3ddbbbd6d92 100644
--- a/arch/arm/mach-s3c24xx/mach-jive.c
+++ b/arch/arm/mach-s3c24xx/mach-jive.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/mach-s3c2410/mach-jive.c
- *
- * Copyright 2007 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * http://armlinux.simtec.co.uk/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2007 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// http://armlinux.simtec.co.uk/
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c
index 04c9f488c498..95753e0bc073 100644
--- a/arch/arm/mach-s3c24xx/mach-mini2440.c
+++ b/arch/arm/mach-s3c24xx/mach-mini2440.c
@@ -1,17 +1,12 @@
-/* linux/arch/arm/mach-s3c2440/mach-mini2440.c
- *
- * Copyright (c) 2008 Ramax Lo <ramaxlo@gmail.com>
- *      Based on mach-anubis.c by Ben Dooks <ben@simtec.co.uk>
- *      and modifications by SBZ <sbz@spgui.org> and
- *      Weibing <http://weibing.blogbus.com> and
- *      Michel Pollet <buserror@gmail.com>
- *
- * For product information, visit http://code.google.com/p/mini2440/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2008 Ramax Lo <ramaxlo@gmail.com>
+//      Based on mach-anubis.c by Ben Dooks <ben@simtec.co.uk>
+//      and modifications by SBZ <sbz@spgui.org> and
+//      Weibing <http://weibing.blogbus.com> and
+//      Michel Pollet <buserror@gmail.com>
+//
+// For product information, visit http://code.google.com/p/mini2440/
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-n30.c b/arch/arm/mach-s3c24xx/mach-n30.c
index 070a0d0714a5..eec51fadb14a 100644
--- a/arch/arm/mach-s3c24xx/mach-n30.c
+++ b/arch/arm/mach-s3c24xx/mach-n30.c
@@ -1,18 +1,15 @@
-/* Machine specific code for the Acer n30, Acer N35, Navman PiN 570,
- * Yakumo AlphaX and Airis NC05 PDAs.
- *
- * Copyright (c) 2003-2005 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Copyright (c) 2005-2008 Christer Weinigel <christer@weinigel.se>
- *
- * There is a wiki with more information about the n30 port at
- * http://handhelds.org/moin/moin.cgi/AcerN30Documentation .
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Machine specific code for the Acer n30, Acer N35, Navman PiN 570,
+// Yakumo AlphaX and Airis NC05 PDAs.
+//
+// Copyright (c) 2003-2005 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// Copyright (c) 2005-2008 Christer Weinigel <christer@weinigel.se>
+//
+// There is a wiki with more information about the n30 port at
+// http://handhelds.org/moin/moin.cgi/AcerN30Documentation .
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-nexcoder.c b/arch/arm/mach-s3c24xx/mach-nexcoder.c
index 2a61d13dcd6c..c2f34758ccb6 100644
--- a/arch/arm/mach-s3c24xx/mach-nexcoder.c
+++ b/arch/arm/mach-s3c24xx/mach-nexcoder.c
@@ -1,16 +1,12 @@
-/* linux/arch/arm/mach-s3c2440/mach-nexcoder.c
- *
- * Copyright (c) 2004 Nex Vision
- *   Guillaume GOURAT <guillaume.gourat@nexvision.tv>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Modifications:
- *     15-10-2004 GG  Created initial version
- *     12-03-2005 BJD Updated for release
- */
+// SPDX-License-Identifier: GPL-2.0
+// linux/arch/arm/mach-s3c2440/mach-nexcoder.c
+//
+// Copyright (c) 2004 Nex Vision
+//   Guillaume GOURAT <guillaume.gourat@nexvision.tv>
+//
+// Modifications:
+//     15-10-2004 GG  Created initial version
+//     12-03-2005 BJD Updated for release
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
index 6cac7da15e2b..058ce73137e8 100644
--- a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
+++ b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
@@ -1,15 +1,10 @@
-/* linux/arch/arm/mach-s3c2440/mach-osiris-dvs.c
- *
- * Copyright (c) 2009 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Simtec Osiris Dynamic Voltage Scaling support.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2009 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// Simtec Osiris Dynamic Voltage Scaling support.
 
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/arch/arm/mach-s3c24xx/mach-osiris.c b/arch/arm/mach-s3c24xx/mach-osiris.c
index ed3b22ceef06..ee3630cb236a 100644
--- a/arch/arm/mach-s3c24xx/mach-osiris.c
+++ b/arch/arm/mach-s3c24xx/mach-osiris.c
@@ -1,12 +1,8 @@
-/*
- * Copyright (c) 2005-2008 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2005-2008 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-otom.c b/arch/arm/mach-s3c24xx/mach-otom.c
index 345a484b93cc..4e24d89e870b 100644
--- a/arch/arm/mach-s3c24xx/mach-otom.c
+++ b/arch/arm/mach-s3c24xx/mach-otom.c
@@ -1,12 +1,7 @@
-/*
- *
- * Copyright (c) 2004 Nex Vision
- *   Guillaume GOURAT <guillaume.gourat@nexvision.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2004 Nex Vision
+//   Guillaume GOURAT <guillaume.gourat@nexvision.fr>
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-qt2410.c b/arch/arm/mach-s3c24xx/mach-qt2410.c
index 84e3a9c53184..9c8373b8d9c3 100644
--- a/arch/arm/mach-s3c24xx/mach-qt2410.c
+++ b/arch/arm/mach-s3c24xx/mach-qt2410.c
@@ -1,25 +1,8 @@
-/* linux/arch/arm/mach-s3c2410/mach-qt2410.c
- *
- * Copyright (C) 2006 by OpenMoko, Inc.
- * Author: Harald Welte <laforge@openmoko.org>
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (C) 2006 by OpenMoko, Inc.
+// Author: Harald Welte <laforge@openmoko.org>
+// All rights reserved.
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-rx1950.c b/arch/arm/mach-s3c24xx/mach-rx1950.c
index e86ad6a68a0b..7f5a18fa305b 100644
--- a/arch/arm/mach-s3c24xx/mach-rx1950.c
+++ b/arch/arm/mach-s3c24xx/mach-rx1950.c
@@ -1,14 +1,9 @@
-/*
- * Copyright (c) 2006-2009 Victor Chukhantsev, Denis Grigoriev,
- * Copyright (c) 2007-2010 Vasily Khoruzhick
- *
- * based on smdk2440 written by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2006-2009 Victor Chukhantsev, Denis Grigoriev,
+// Copyright (c) 2007-2010 Vasily Khoruzhick
+//
+// based on smdk2440 written by Ben Dooks
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-rx3715.c b/arch/arm/mach-s3c24xx/mach-rx3715.c
index b5ba615cf9dd..529c6faf862f 100644
--- a/arch/arm/mach-s3c24xx/mach-rx3715.c
+++ b/arch/arm/mach-s3c24xx/mach-rx3715.c
@@ -1,15 +1,9 @@
-/* linux/arch/arm/mach-s3c2440/mach-rx3715.c
- *
- * Copyright (c) 2003-2004 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * http://www.handhelds.org/projects/rx3715.html
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2003-2004 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// http://www.handhelds.org/projects/rx3715.html
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c b/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c
index c83c076578dd..aa7102713b37 100644
--- a/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c
+++ b/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c
@@ -1,19 +1,15 @@
-/*
- * Samsung's S3C2416 flattened device tree enabled machine
- *
- * Copyright (c) 2012 Heiko Stuebner <heiko@sntech.de>
- *
- * based on mach-exynos/mach-exynos4-dt.c
- *
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- * Copyright (c) 2010-2011 Linaro Ltd.
- *		www.linaro.org
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Samsung's S3C2416 flattened device tree enabled machine
+//
+// Copyright (c) 2012 Heiko Stuebner <heiko@sntech.de>
+//
+// based on mach-exynos/mach-exynos4-dt.c
+//
+// Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
+// Copyright (c) 2010-2011 Linaro Ltd.
+//		www.linaro.org
 
 #include <linux/clocksource.h>
 #include <linux/irqchip.h>
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2410.c b/arch/arm/mach-s3c24xx/mach-smdk2410.c
index 27dd6605e395..18dfef52c8bf 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2410.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2410.c
@@ -1,32 +1,13 @@
-/* linux/arch/arm/mach-s3c2410/mach-smdk2410.c
- *
- * linux/arch/arm/mach-s3c2410/mach-smdk2410.c
- *
- * Copyright (C) 2004 by FS Forth-Systeme GmbH
- * All rights reserved.
- *
- * @Author: Jonas Dietsche
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
- *
- * @History:
- * derived from linux/arch/arm/mach-s3c2410/mach-bast.c, written by
- * Ben Dooks <ben@simtec.co.uk>
- *
- ***********************************************************************/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (C) 2004 by FS Forth-Systeme GmbH
+// All rights reserved.
+//
+// @Author: Jonas Dietsche
+//
+// @History:
+// derived from linux/arch/arm/mach-s3c2410/mach-bast.c, written by
+// Ben Dooks <ben@simtec.co.uk>
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2413.c b/arch/arm/mach-s3c24xx/mach-smdk2413.c
index 586e4a3b8d5d..ca80167f268d 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2413.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2413.c
@@ -1,15 +1,10 @@
-/* linux/arch/arm/mach-s3c2412/mach-smdk2413.c
- *
- * Copyright (c) 2006 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Thanks to Dimity Andric (TomTom) and Steven Ryu (Samsung) for the
- * loans of SMDK2413 to work with.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2006 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// Thanks to Dimity Andric (TomTom) and Steven Ryu (Samsung) for the
+// loans of SMDK2413 to work with.
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2416.c b/arch/arm/mach-s3c24xx/mach-smdk2416.c
index 86394f72d29e..61c3e45898d3 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2416.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2416.c
@@ -1,15 +1,9 @@
-/* linux/arch/arm/mach-s3c2416/mach-hanlin_v3c.c
- *
- * Copyright (c) 2009 Yauhen Kharuzhy <jekhor@gmail.com>,
- *	as part of OpenInkpot project
- * Copyright (c) 2009 Promwad Innovation Company
- *	Yauhen Kharuzhy <yauhen.kharuzhy@promwad.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2009 Yauhen Kharuzhy <jekhor@gmail.com>,
+//	as part of OpenInkpot project
+// Copyright (c) 2009 Promwad Innovation Company
+//	Yauhen Kharuzhy <yauhen.kharuzhy@promwad.com>
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2440.c b/arch/arm/mach-s3c24xx/mach-smdk2440.c
index 9bb96bfbb420..7bafcd8ea104 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2440.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2440.c
@@ -1,17 +1,12 @@
-/* linux/arch/arm/mach-s3c2440/mach-smdk2440.c
- *
- * Copyright (c) 2004-2005 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * http://www.fluff.org/ben/smdk2440/
- *
- * Thanks to Dimity Andric and TomTom for the loan of an SMDK2440.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+// linux/arch/arm/mach-s3c2440/mach-smdk2440.c
+//
+// Copyright (c) 2004-2005 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// http://www.fluff.org/ben/smdk2440/
+//
+// Thanks to Dimity Andric and TomTom for the loan of an SMDK2440.
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2443.c b/arch/arm/mach-s3c24xx/mach-smdk2443.c
index 474cd81aa8ad..2358ed5ed7be 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2443.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2443.c
@@ -1,17 +1,11 @@
-/* linux/arch/arm/mach-s3c2443/mach-smdk2443.c
- *
- * Copyright (c) 2007 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * http://www.fluff.org/ben/smdk2443/
- *
- * Thanks to Samsung for the loan of an SMDK2443
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2007 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// http://www.fluff.org/ben/smdk2443/
+//
+// Thanks to Samsung for the loan of an SMDK2443
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-tct_hammer.c b/arch/arm/mach-s3c24xx/mach-tct_hammer.c
index 2deb62f92fb2..8d8ddd6ea305 100644
--- a/arch/arm/mach-s3c24xx/mach-tct_hammer.c
+++ b/arch/arm/mach-s3c24xx/mach-tct_hammer.c
@@ -1,28 +1,11 @@
-/* linux/arch/arm/mach-s3c2410/mach-tct_hammer.c
- *
- * Copyright (c) 2007 TinCanTools
- *	David Anders <danders@amltd.com>
-
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
- *
- * @History:
- * derived from linux/arch/arm/mach-s3c2410/mach-bast.c, written by
- * Ben Dooks <ben@simtec.co.uk>
- *
- ***********************************************************************/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2007 TinCanTools
+//	David Anders <danders@amltd.com>
+//
+// @History:
+// derived from linux/arch/arm/mach-s3c2410/mach-bast.c, written by
+// Ben Dooks <ben@simtec.co.uk>
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-vr1000.c b/arch/arm/mach-s3c24xx/mach-vr1000.c
index 89f32bd3f01b..853e74f9b8b5 100644
--- a/arch/arm/mach-s3c24xx/mach-vr1000.c
+++ b/arch/arm/mach-s3c24xx/mach-vr1000.c
@@ -1,15 +1,10 @@
-/*
- * Copyright (c) 2003-2008 Simtec Electronics
- *   Ben Dooks <ben@simtec.co.uk>
- *
- * Machine support for Thorcom VR1000 board. Designed for Thorcom by
- * Simtec Electronics, http://www.simtec.co.uk/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2003-2008 Simtec Electronics
+//   Ben Dooks <ben@simtec.co.uk>
+//
+// Machine support for Thorcom VR1000 board. Designed for Thorcom by
+// Simtec Electronics, http://www.simtec.co.uk/
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/mach-vstms.c b/arch/arm/mach-s3c24xx/mach-vstms.c
index 1adc957edf0f..d76b28b65e65 100644
--- a/arch/arm/mach-s3c24xx/mach-vstms.c
+++ b/arch/arm/mach-s3c24xx/mach-vstms.c
@@ -1,13 +1,8 @@
-/* linux/arch/arm/mach-s3c2412/mach-vstms.c
- *
- * (C) 2006 Thomas Gleixner <tglx@linutronix.de>
- *
- * Derived from mach-smdk2413.c - (C) 2006 Simtec Electronics
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// (C) 2006 Thomas Gleixner <tglx@linutronix.de>
+//
+// Derived from mach-smdk2413.c - (C) 2006 Simtec Electronics
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/nand-core.h b/arch/arm/mach-s3c24xx/nand-core.h
index 7e811fe1cf41..8de633d416ae 100644
--- a/arch/arm/mach-s3c24xx/nand-core.h
+++ b/arch/arm/mach-s3c24xx/nand-core.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2010 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com/
  *
  * S3C -  Nand Controller core functions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_ARCH_NAND_CORE_H
 #define __ASM_ARCH_NAND_CORE_H __FILE__
diff --git a/arch/arm/mach-s3c24xx/osiris.h b/arch/arm/mach-s3c24xx/osiris.h
index b8d56074abac..b6c9c5ed2ba7 100644
--- a/arch/arm/mach-s3c24xx/osiris.h
+++ b/arch/arm/mach-s3c24xx/osiris.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2005 Simtec Electronics
  *	http://www.simtec.co.uk/products/
@@ -5,11 +6,7 @@
  *
  * OSIRIS - CPLD control constants
  * OSIRIS - Memory map definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __MACH_S3C24XX_OSIRIS_H
 #define __MACH_S3C24XX_OSIRIS_H __FILE__
diff --git a/arch/arm/mach-s3c24xx/otom.h b/arch/arm/mach-s3c24xx/otom.h
index 321b7be1c0f7..c800f67d03d4 100644
--- a/arch/arm/mach-s3c24xx/otom.h
+++ b/arch/arm/mach-s3c24xx/otom.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * (c) 2005 Guillaume GOURAT / NexVision
  *          guillaume.gourat@nexvision.fr
  *
  * NexVision OTOM board memory map definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /*
  * ok, we've used up to 0x01300000, now we need to find space for the
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2410.c b/arch/arm/mach-s3c24xx/pll-s3c2410.c
index 7ee4924a543d..0561f79ddce8 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2410.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2410.c
@@ -1,25 +1,11 @@
-/*
- * Copyright (c) 2006-2007 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *	Vincent Sanders <vince@arm.linux.org.uk>
- *
- * S3C2410 CPU PLL tables
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-*/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2006-2007 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
+//	Vincent Sanders <vince@arm.linux.org.uk>
+//
+// S3C2410 CPU PLL tables
 
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
index a3fbfed75e28..2ec3a2f9a6a5 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
@@ -1,15 +1,11 @@
-/*
- * Copyright (c) 2006-2007 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *	Vincent Sanders <vince@arm.linux.org.uk>
- *
- * S3C2440/S3C2442 CPU PLL tables (12MHz Crystal)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2006-2007 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
+//	Vincent Sanders <vince@arm.linux.org.uk>
+//
+// S3C2440/S3C2442 CPU PLL tables (12MHz Crystal)
 
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
index bcff89fd9871..4b3d9e36c6bb 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
@@ -1,15 +1,11 @@
-/*
- * Copyright (c) 2006-2008 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *	Vincent Sanders <vince@arm.linux.org.uk>
- *
- * S3C2440/S3C2442 CPU PLL tables (16.93444MHz Crystal)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2006-2008 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
+//	Vincent Sanders <vince@arm.linux.org.uk>
+//
+// S3C2440/S3C2442 CPU PLL tables (16.93444MHz Crystal)
 
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/arch/arm/mach-s3c24xx/pm-h1940.S b/arch/arm/mach-s3c24xx/pm-h1940.S
index 6183a688012b..a7bbe336ac6b 100644
--- a/arch/arm/mach-s3c24xx/pm-h1940.S
+++ b/arch/arm/mach-s3c24xx/pm-h1940.S
@@ -1,22 +1,9 @@
-/* linux/arch/arm/mach-s3c2410/pm-h1940.S
- *
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
  * Copyright (c) 2006 Ben Dooks <ben-linux@fluff.org>
  *
  * H1940 Suspend to RAM
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-*/
+ */
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
diff --git a/arch/arm/mach-s3c24xx/pm-s3c2410.c b/arch/arm/mach-s3c24xx/pm-s3c2410.c
index a4588daeddb0..2d8ea701380a 100644
--- a/arch/arm/mach-s3c24xx/pm-s3c2410.c
+++ b/arch/arm/mach-s3c24xx/pm-s3c2410.c
@@ -1,24 +1,9 @@
-/* linux/arch/arm/mach-s3c2410/pm.c
- *
- * Copyright (c) 2006 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C2410 (and compatible) Power Manager (Suspend-To-RAM) support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-*/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2006 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// S3C2410 (and compatible) Power Manager (Suspend-To-RAM) support
 
 #include <linux/init.h>
 #include <linux/suspend.h>
diff --git a/arch/arm/mach-s3c24xx/pm-s3c2412.c b/arch/arm/mach-s3c24xx/pm-s3c2412.c
index 0ae4d47a4663..2dfdaab0aa1f 100644
--- a/arch/arm/mach-s3c24xx/pm-s3c2412.c
+++ b/arch/arm/mach-s3c24xx/pm-s3c2412.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/mach-s3c2412/pm.c
- *
- * Copyright (c) 2006 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * http://armlinux.simtec.co.uk/.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2006 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// http://armlinux.simtec.co.uk/.
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/pm-s3c2416.c b/arch/arm/mach-s3c24xx/pm-s3c2416.c
index b5bbf0d5985c..9a2f05e279d4 100644
--- a/arch/arm/mach-s3c24xx/pm-s3c2416.c
+++ b/arch/arm/mach-s3c24xx/pm-s3c2416.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/mach-s3c2416/pm.c
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * S3C2416 - PM support (Based on Ben Dooks' S3C2412 PM support)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2010 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
+//
+// S3C2416 - PM support (Based on Ben Dooks' S3C2412 PM support)
 
 #include <linux/device.h>
 #include <linux/syscore_ops.h>
diff --git a/arch/arm/mach-s3c24xx/pm.c b/arch/arm/mach-s3c24xx/pm.c
index 5d510bca0844..adcb90645460 100644
--- a/arch/arm/mach-s3c24xx/pm.c
+++ b/arch/arm/mach-s3c24xx/pm.c
@@ -1,30 +1,15 @@
-/* linux/arch/arm/plat-s3c24xx/pm.c
- *
- * Copyright (c) 2004-2006 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C24XX Power Manager (Suspend-To-RAM) support
- *
- * See Documentation/arm/Samsung-S3C24XX/Suspend.txt for more information
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * Parts based on arch/arm/mach-pxa/pm.c
- *
- * Thanks to Dimitry Andric for debugging
-*/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2004-2006 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// S3C24XX Power Manager (Suspend-To-RAM) support
+//
+// See Documentation/arm/Samsung-S3C24XX/Suspend.txt for more information
+//
+// Parts based on arch/arm/mach-pxa/pm.c
+//
+// Thanks to Dimitry Andric for debugging
 
 #include <linux/init.h>
 #include <linux/suspend.h>
diff --git a/arch/arm/mach-s3c24xx/regs-dsc.h b/arch/arm/mach-s3c24xx/regs-dsc.h
index 61b3d1387d76..b500636276f2 100644
--- a/arch/arm/mach-s3c24xx/regs-dsc.h
+++ b/arch/arm/mach-s3c24xx/regs-dsc.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2004 Simtec Electronics <linux@simtec.co.uk>
  *		      http://www.simtec.co.uk/products/SWLINUX/
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * S3C2440/S3C2412 Signal Drive Strength Control
-*/
+ */
 
 
 #ifndef __ASM_ARCH_REGS_DSC_H
diff --git a/arch/arm/mach-s3c24xx/regs-mem.h b/arch/arm/mach-s3c24xx/regs-mem.h
index 86b1258368c2..2f3bc48b5890 100644
--- a/arch/arm/mach-s3c24xx/regs-mem.h
+++ b/arch/arm/mach-s3c24xx/regs-mem.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2004 Simtec Electronics <linux@simtec.co.uk>
  *		http://www.simtec.co.uk/products/SWLINUX/
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * S3C2410 Memory Control register definitions
  */
 
diff --git a/arch/arm/mach-s3c24xx/s3c2410.c b/arch/arm/mach-s3c24xx/s3c2410.c
index 5061d66ca10c..21fd5404bc98 100644
--- a/arch/arm/mach-s3c24xx/s3c2410.c
+++ b/arch/arm/mach-s3c24xx/s3c2410.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/mach-s3c2410/s3c2410.c
- *
- * Copyright (c) 2003-2005 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * http://www.simtec.co.uk/products/EB2410ITX/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2003-2005 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// http://www.simtec.co.uk/products/EB2410ITX/
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/s3c2412-power.h b/arch/arm/mach-s3c24xx/s3c2412-power.h
index 1b02c5ddb31b..0031cfaa1d76 100644
--- a/arch/arm/mach-s3c24xx/s3c2412-power.h
+++ b/arch/arm/mach-s3c24xx/s3c2412-power.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2003-2006 Simtec Electronics <linux@simtec.co.uk>
  *	http://armlinux.simtec.co.uk/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __ARCH_ARM_MACH_S3C24XX_S3C2412_POWER_H
diff --git a/arch/arm/mach-s3c24xx/s3c2412.c b/arch/arm/mach-s3c24xx/s3c2412.c
index fb5ee8d38913..8fe4d4670dcb 100644
--- a/arch/arm/mach-s3c24xx/s3c2412.c
+++ b/arch/arm/mach-s3c24xx/s3c2412.c
@@ -1,13 +1,9 @@
-/*
- * Copyright (c) 2006 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * http://armlinux.simtec.co.uk/.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2006 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// http://armlinux.simtec.co.uk/.
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/s3c2416.c b/arch/arm/mach-s3c24xx/s3c2416.c
index 621b8648a7ef..1cdb7bd3e713 100644
--- a/arch/arm/mach-s3c24xx/s3c2416.c
+++ b/arch/arm/mach-s3c24xx/s3c2416.c
@@ -1,26 +1,11 @@
-/* linux/arch/arm/mach-s3c2416/s3c2416.c
- *
- * Copyright (c) 2009 Yauhen Kharuzhy <jekhor@gmail.com>,
- *	as part of OpenInkpot project
- * Copyright (c) 2009 Promwad Innovation Company
- *	Yauhen Kharuzhy <yauhen.kharuzhy@promwad.com>
- *
- * Samsung S3C2416 Mobile CPU support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-*/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2009 Yauhen Kharuzhy <jekhor@gmail.com>,
+//	as part of OpenInkpot project
+// Copyright (c) 2009 Promwad Innovation Company
+//	Yauhen Kharuzhy <yauhen.kharuzhy@promwad.com>
+//
+// Samsung S3C2416 Mobile CPU support
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/s3c2440.c b/arch/arm/mach-s3c24xx/s3c2440.c
index eb733555fab5..451d9851b0a7 100644
--- a/arch/arm/mach-s3c24xx/s3c2440.c
+++ b/arch/arm/mach-s3c24xx/s3c2440.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/mach-s3c2440/s3c2440.c
- *
- * Copyright (c) 2004-2006 Simtec Electronics
- *   Ben Dooks <ben@simtec.co.uk>
- *
- * Samsung S3C2440 Mobile CPU support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2004-2006 Simtec Electronics
+//   Ben Dooks <ben@simtec.co.uk>
+//
+// Samsung S3C2440 Mobile CPU support
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/s3c2442.c b/arch/arm/mach-s3c24xx/s3c2442.c
index 893998ede022..432d68325c9d 100644
--- a/arch/arm/mach-s3c24xx/s3c2442.c
+++ b/arch/arm/mach-s3c24xx/s3c2442.c
@@ -1,25 +1,10 @@
-/* linux/arch/arm/mach-s3c2442/s3c2442.c
- *
- * Copyright (c) 2004-2005 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C2442 core and lock support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-*/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2004-2005 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// S3C2442 core and lock support
 
 #include <linux/init.h>
 #include <linux/module.h>
diff --git a/arch/arm/mach-s3c24xx/s3c2443.c b/arch/arm/mach-s3c24xx/s3c2443.c
index b559d378cf43..313e369c3ddd 100644
--- a/arch/arm/mach-s3c24xx/s3c2443.c
+++ b/arch/arm/mach-s3c24xx/s3c2443.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/mach-s3c2443/s3c2443.c
- *
- * Copyright (c) 2007 Simtec Electronics
- *   Ben Dooks <ben@simtec.co.uk>
- *
- * Samsung S3C2443 Mobile CPU support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2007 Simtec Electronics
+//   Ben Dooks <ben@simtec.co.uk>
+//
+// Samsung S3C2443 Mobile CPU support
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/s3c244x.c b/arch/arm/mach-s3c24xx/s3c244x.c
index 31fd273269c2..a75f588b9d45 100644
--- a/arch/arm/mach-s3c24xx/s3c244x.c
+++ b/arch/arm/mach-s3c24xx/s3c244x.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/plat-s3c24xx/s3c244x.c
- *
- * Copyright (c) 2004-2006 Simtec Electronics
- *   Ben Dooks <ben@simtec.co.uk>
- *
- * Samsung S3C2440 and S3C2442 Mobile CPU support (not S3C2443)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2004-2006 Simtec Electronics
+//   Ben Dooks <ben@simtec.co.uk>
+//
+// Samsung S3C2440 and S3C2442 Mobile CPU support (not S3C2443)
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/setup-camif.c b/arch/arm/mach-s3c24xx/setup-camif.c
index 72d8edb8927a..2b262fae3f61 100644
--- a/arch/arm/mach-s3c24xx/setup-camif.c
+++ b/arch/arm/mach-s3c24xx/setup-camif.c
@@ -1,12 +1,8 @@
-/*
- * Copyright (C) 2012 Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
- *
- * Helper functions for S3C24XX/S3C64XX SoC series CAMIF driver
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2012 Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
+//
+// Helper functions for S3C24XX/S3C64XX SoC series CAMIF driver
 
 #include <linux/gpio.h>
 #include <plat/gpio-cfg.h>
diff --git a/arch/arm/mach-s3c24xx/setup-i2c.c b/arch/arm/mach-s3c24xx/setup-i2c.c
index 1852696ca16e..1a01d44b5910 100644
--- a/arch/arm/mach-s3c24xx/setup-i2c.c
+++ b/arch/arm/mach-s3c24xx/setup-i2c.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/plat-s3c24xx/setup-i2c.c
- *
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C24XX Base setup for i2c device
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// S3C24XX Base setup for i2c device
 
 #include <linux/kernel.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-s3c24xx/setup-sdhci-gpio.c b/arch/arm/mach-s3c24xx/setup-sdhci-gpio.c
index c99b0f664db7..218346a36d1e 100644
--- a/arch/arm/mach-s3c24xx/setup-sdhci-gpio.c
+++ b/arch/arm/mach-s3c24xx/setup-sdhci-gpio.c
@@ -1,16 +1,11 @@
-/* linux/arch/arm/plat-s3c2416/setup-sdhci-gpio.c
- *
- * Copyright 2010 Promwad Innovation Company
- *	Yauhen Kharuzhy <yauhen.kharuzhy@promwad.com>
- *
- * S3C2416 - Helper functions for setting up SDHCI device(s) GPIO (HSMMC)
- *
- * Based on mach-s3c64xx/setup-sdhci-gpio.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2010 Promwad Innovation Company
+//	Yauhen Kharuzhy <yauhen.kharuzhy@promwad.com>
+//
+// S3C2416 - Helper functions for setting up SDHCI device(s) GPIO (HSMMC)
+//
+// Based on mach-s3c64xx/setup-sdhci-gpio.c
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/setup-spi.c b/arch/arm/mach-s3c24xx/setup-spi.c
index 3d47e023ce94..6c2b96a82da5 100644
--- a/arch/arm/mach-s3c24xx/setup-spi.c
+++ b/arch/arm/mach-s3c24xx/setup-spi.c
@@ -1,13 +1,9 @@
-/*
- * HS-SPI device setup for S3C2443/S3C2416
- *
- * Copyright (C) 2011 Samsung Electronics Ltd.
- *		http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// HS-SPI device setup for S3C2443/S3C2416
+//
+// Copyright (C) 2011 Samsung Electronics Ltd.
+//		http://www.samsung.com/
 
 #include <linux/gpio.h>
 #include <linux/platform_device.h>
diff --git a/arch/arm/mach-s3c24xx/setup-ts.c b/arch/arm/mach-s3c24xx/setup-ts.c
index 46466d20257e..53a14d4f4852 100644
--- a/arch/arm/mach-s3c24xx/setup-ts.c
+++ b/arch/arm/mach-s3c24xx/setup-ts.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/plat-s3c24xx/setup-ts.c
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *                     http://www.samsung.com/
- *
- * Based on S3C24XX setup for i2c device
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2010 Samsung Electronics Co., Ltd.
+//                     http://www.samsung.com/
+//
+// Based on S3C24XX setup for i2c device
 
 #include <linux/kernel.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-s3c24xx/simtec-audio.c b/arch/arm/mach-s3c24xx/simtec-audio.c
index 67cb5120dfeb..12e17f82dae3 100644
--- a/arch/arm/mach-s3c24xx/simtec-audio.c
+++ b/arch/arm/mach-s3c24xx/simtec-audio.c
@@ -1,15 +1,10 @@
-/* linux/arch/arm/plat-s3c24xx/simtec-audio.c
- *
- * Copyright (c) 2009 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Audio setup for various Simtec S3C24XX implementations
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2009 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// Audio setup for various Simtec S3C24XX implementations
 
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
diff --git a/arch/arm/mach-s3c24xx/simtec-nor.c b/arch/arm/mach-s3c24xx/simtec-nor.c
index 8884bffa619a..26b18497e959 100644
--- a/arch/arm/mach-s3c24xx/simtec-nor.c
+++ b/arch/arm/mach-s3c24xx/simtec-nor.c
@@ -1,15 +1,10 @@
-/* linux/arch/arm/mach-s3c2410/nor-simtec.c
- *
- * Copyright (c) 2008 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Simtec NOR mapping
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2008 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// Simtec NOR mapping
 
 #include <linux/module.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/simtec-pm.c b/arch/arm/mach-s3c24xx/simtec-pm.c
index 38a2f1fdebab..c19074d81389 100644
--- a/arch/arm/mach-s3c24xx/simtec-pm.c
+++ b/arch/arm/mach-s3c24xx/simtec-pm.c
@@ -1,16 +1,11 @@
-/* linux/arch/arm/plat-s3c24xx/pm-simtec.c
- *
- * Copyright 2004 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * http://armlinux.simtec.co.uk/
- *
- * Power Management helpers for Simtec S3C24XX implementations
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2004 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// http://armlinux.simtec.co.uk/
+//
+// Power Management helpers for Simtec S3C24XX implementations
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c24xx/simtec-usb.c b/arch/arm/mach-s3c24xx/simtec-usb.c
index b70aa66efebe..dc1016ffed94 100644
--- a/arch/arm/mach-s3c24xx/simtec-usb.c
+++ b/arch/arm/mach-s3c24xx/simtec-usb.c
@@ -1,16 +1,11 @@
-/* linux/arch/arm/mach-s3c2410/usb-simtec.c
- *
- * Copyright 2004-2005 Simtec Electronics
- *   Ben Dooks <ben@simtec.co.uk>
- *
- * http://www.simtec.co.uk/products/EB2410ITX/
- *
- * Simtec BAST and Thorcom VR1000 USB port support functions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2004-2005 Simtec Electronics
+//   Ben Dooks <ben@simtec.co.uk>
+//
+// http://www.simtec.co.uk/products/EB2410ITX/
+//
+// Simtec BAST and Thorcom VR1000 USB port support functions
 
 #define DEBUG
 
diff --git a/arch/arm/mach-s3c24xx/simtec.h b/arch/arm/mach-s3c24xx/simtec.h
index ae8f4f9ad2ee..d96bd60872b8 100644
--- a/arch/arm/mach-s3c24xx/simtec.h
+++ b/arch/arm/mach-s3c24xx/simtec.h
@@ -1,15 +1,11 @@
-/* linux/arch/arm/mach-s3c2410/nor-simtec.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2008 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * Simtec common functions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 struct s3c24xx_audio_simtec_pdata;
 
diff --git a/arch/arm/mach-s3c24xx/sleep-s3c2410.S b/arch/arm/mach-s3c24xx/sleep-s3c2410.S
index 875ba8911127..659f9eff9de2 100644
--- a/arch/arm/mach-s3c24xx/sleep-s3c2410.S
+++ b/arch/arm/mach-s3c24xx/sleep-s3c2410.S
@@ -1,5 +1,5 @@
-/* linux/arch/arm/mach-s3c2410/sleep.S
- *
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
  * Copyright (c) 2004 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
@@ -8,21 +8,7 @@
  * Based on PXA/SA1100 sleep code by:
  *	Nicolas Pitre, (c) 2002 Monta Vista Software Inc
  *	Cliff Brake, (c) 2001
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-*/
+ */
 
 #include <linux/linkage.h>
 #include <linux/serial_s3c.h>
diff --git a/arch/arm/mach-s3c24xx/sleep-s3c2412.S b/arch/arm/mach-s3c24xx/sleep-s3c2412.S
index 6bf5b4d8743c..c373f1ca862b 100644
--- a/arch/arm/mach-s3c24xx/sleep-s3c2412.S
+++ b/arch/arm/mach-s3c24xx/sleep-s3c2412.S
@@ -1,24 +1,10 @@
-/* linux/arch/arm/mach-s3c2412/sleep.S
- *
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
  * Copyright (c) 2007 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C2412 Power Manager low-level sleep support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-*/
+ */
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
diff --git a/arch/arm/mach-s3c24xx/sleep.S b/arch/arm/mach-s3c24xx/sleep.S
index b859268fa8da..f0f11ad60c52 100644
--- a/arch/arm/mach-s3c24xx/sleep.S
+++ b/arch/arm/mach-s3c24xx/sleep.S
@@ -1,5 +1,5 @@
-/* linux/arch/arm/plat-s3c24xx/sleep.S
- *
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
  * Copyright (c) 2004 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
@@ -8,21 +8,7 @@
  * Based on PXA/SA1100 sleep code by:
  *	Nicolas Pitre, (c) 2002 Monta Vista Software Inc
  *	Cliff Brake, (c) 2001
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-*/
+ */
 
 #include <linux/linkage.h>
 #include <linux/serial_s3c.h>
diff --git a/arch/arm/mach-s3c24xx/spi-core.h b/arch/arm/mach-s3c24xx/spi-core.h
index 0b9428ab3fc3..bb555ccbe057 100644
--- a/arch/arm/mach-s3c24xx/spi-core.h
+++ b/arch/arm/mach-s3c24xx/spi-core.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2012 Heiko Stuebner <heiko@sntech.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __PLAT_S3C_SPI_CORE_H
diff --git a/arch/arm/mach-s3c24xx/vr1000.h b/arch/arm/mach-s3c24xx/vr1000.h
index 7fcd2c2f183c..3cfa296bec2a 100644
--- a/arch/arm/mach-s3c24xx/vr1000.h
+++ b/arch/arm/mach-s3c24xx/vr1000.h
@@ -1,17 +1,12 @@
-
-/* arch/arm/mach-s3c2410/include/mach/vr1000-cpld.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2003 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * VR1000 - CPLD control constants
  * Machine VR1000 - IRQ Number definitions
  * Machine VR1000 - Memory map definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __MACH_S3C24XX_VR1000_H
 #define __MACH_S3C24XX_VR1000_H __FILE__
diff --git a/arch/arm/mach-s3c64xx/Kconfig b/arch/arm/mach-s3c64xx/Kconfig
index afd1f20be49e..5700822e3c74 100644
--- a/arch/arm/mach-s3c64xx/Kconfig
+++ b/arch/arm/mach-s3c64xx/Kconfig
@@ -1,7 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+#
 # Copyright 2008 Openmoko, Inc.
 #	Simtec Electronics, Ben Dooks <ben@simtec.co.uk>
-#
-# Licensed under GPLv2
+
 menuconfig ARCH_S3C64XX
 	bool "Samsung S3C64XX"
 	depends on ARCH_MULTI_V6
diff --git a/arch/arm/mach-s3c64xx/Makefile b/arch/arm/mach-s3c64xx/Makefile
index 256cd5b40c60..8caeb4ad17e9 100644
--- a/arch/arm/mach-s3c64xx/Makefile
+++ b/arch/arm/mach-s3c64xx/Makefile
@@ -1,9 +1,7 @@
-# arch/arm/mach-s3c64xx/Makefile
+# SPDX-License-Identifier: GPL-2.0
 #
 # Copyright 2008 Openmoko, Inc.
 # Copyright 2008 Simtec Electronics
-#
-# Licensed under GPLv2
 
 ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include
 asflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include
diff --git a/arch/arm/mach-s3c64xx/ata-core.h b/arch/arm/mach-s3c64xx/ata-core.h
index 5951f24a9ec8..6d9a81f759e6 100644
--- a/arch/arm/mach-s3c64xx/ata-core.h
+++ b/arch/arm/mach-s3c64xx/ata-core.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2010 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Samsung CF-ATA Controller core functions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_PLAT_ATA_CORE_H
 #define __ASM_PLAT_ATA_CORE_H __FILE__
diff --git a/arch/arm/mach-s3c64xx/backlight.h b/arch/arm/mach-s3c64xx/backlight.h
index 8dcacac523a2..028663f1cacc 100644
--- a/arch/arm/mach-s3c64xx/backlight.h
+++ b/arch/arm/mach-s3c64xx/backlight.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  *              http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __ASM_PLAT_BACKLIGHT_H
diff --git a/arch/arm/mach-s3c64xx/common.c b/arch/arm/mach-s3c64xx/common.c
index 9843eb4dd04e..13e91074308a 100644
--- a/arch/arm/mach-s3c64xx/common.c
+++ b/arch/arm/mach-s3c64xx/common.c
@@ -1,18 +1,14 @@
-/*
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * Common Codes for S3C64XX machines
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2011 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// Common Codes for S3C64XX machines
 
 /*
  * NOTE: Code in this file is not used when booting with Device Tree support.
diff --git a/arch/arm/mach-s3c64xx/common.h b/arch/arm/mach-s3c64xx/common.h
index 4f204668f00e..03670887a764 100644
--- a/arch/arm/mach-s3c64xx/common.h
+++ b/arch/arm/mach-s3c64xx/common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
@@ -8,10 +9,6 @@
  *	http://armlinux.simtec.co.uk/
  *
  * Common Header for S3C64XX machines
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __ARCH_ARM_MACH_S3C64XX_COMMON_H
diff --git a/arch/arm/mach-s3c64xx/cpuidle.c b/arch/arm/mach-s3c64xx/cpuidle.c
index 5322db51150e..0bac6f6413b0 100644
--- a/arch/arm/mach-s3c64xx/cpuidle.c
+++ b/arch/arm/mach-s3c64xx/cpuidle.c
@@ -1,13 +1,8 @@
-/* linux/arch/arm/mach-s3c64xx/cpuidle.c
- *
- * Copyright (c) 2011 Wolfson Microelectronics, plc
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2011 Wolfson Microelectronics, plc
+// Copyright (c) 2011 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
 
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/arch/arm/mach-s3c64xx/crag6410.h b/arch/arm/mach-s3c64xx/crag6410.h
index dcbe17f5e5f8..00d9aa114aa7 100644
--- a/arch/arm/mach-s3c64xx/crag6410.h
+++ b/arch/arm/mach-s3c64xx/crag6410.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /* Cragganmore 6410 shared definitions
  *
  * Copyright 2011 Wolfson Microelectronics plc
  *	Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef MACH_CRAG6410_H
diff --git a/arch/arm/mach-s3c64xx/dev-audio.c b/arch/arm/mach-s3c64xx/dev-audio.c
index cb953e238b2a..e3c49b5d1355 100644
--- a/arch/arm/mach-s3c64xx/dev-audio.c
+++ b/arch/arm/mach-s3c64xx/dev-audio.c
@@ -1,12 +1,7 @@
-/* linux/arch/arm/plat-s3c/dev-audio.c
- *
- * Copyright 2009 Wolfson Microelectronics
- *      Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2009 Wolfson Microelectronics
+//      Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/kernel.h>
 #include <linux/string.h>
diff --git a/arch/arm/mach-s3c64xx/dev-backlight.c b/arch/arm/mach-s3c64xx/dev-backlight.c
index 7ef8b9019344..799cfdf0606b 100644
--- a/arch/arm/mach-s3c64xx/dev-backlight.c
+++ b/arch/arm/mach-s3c64xx/dev-backlight.c
@@ -1,13 +1,9 @@
-/*
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- *              http://www.samsung.com
- *
- * Common infrastructure for PWM Backlight for Samsung boards
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2011 Samsung Electronics Co., Ltd.
+//              http://www.samsung.com
+//
+// Common infrastructure for PWM Backlight for Samsung boards
 
 #include <linux/gpio.h>
 #include <linux/platform_device.h>
diff --git a/arch/arm/mach-s3c64xx/dev-uart.c b/arch/arm/mach-s3c64xx/dev-uart.c
index a0b4f0329811..5fb59ad30008 100644
--- a/arch/arm/mach-s3c64xx/dev-uart.c
+++ b/arch/arm/mach-s3c64xx/dev-uart.c
@@ -1,17 +1,11 @@
-/* linux/arch/arm/plat-s3c64xx/dev-uart.c
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * Base S3C64XX UART resource and device definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// Base S3C64XX UART resource and device definitions
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c64xx/include/mach/gpio-samsung.h b/arch/arm/mach-s3c64xx/include/mach/gpio-samsung.h
index 1d3636512e33..8ed144a0d474 100644
--- a/arch/arm/mach-s3c64xx/include/mach/gpio-samsung.h
+++ b/arch/arm/mach-s3c64xx/include/mach/gpio-samsung.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
@@ -5,11 +6,7 @@
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C6400 - GPIO lib support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef GPIO_SAMSUNG_S3C64XX_H
 #define GPIO_SAMSUNG_S3C64XX_H
diff --git a/arch/arm/mach-s3c64xx/include/mach/hardware.h b/arch/arm/mach-s3c64xx/include/mach/hardware.h
index 862d033e57a4..c4ed359474de 100644
--- a/arch/arm/mach-s3c64xx/include/mach/hardware.h
+++ b/arch/arm/mach-s3c64xx/include/mach/hardware.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /* linux/arch/arm/mach-s3c6400/include/mach/hardware.h
  *
  * Copyright 2008 Openmoko, Inc.
diff --git a/arch/arm/mach-s3c64xx/include/mach/map.h b/arch/arm/mach-s3c64xx/include/mach/map.h
index d51873e8f63f..9372a535b7ba 100644
--- a/arch/arm/mach-s3c64xx/include/mach/map.h
+++ b/arch/arm/mach-s3c64xx/include/mach/map.h
@@ -1,16 +1,12 @@
-/* linux/arch/arm/mach-s3c6400/include/mach/map.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C64XX - Memory map definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_ARCH_MAP_H
 #define __ASM_ARCH_MAP_H __FILE__
diff --git a/arch/arm/mach-s3c64xx/include/mach/pm-core.h b/arch/arm/mach-s3c64xx/include/mach/pm-core.h
index 4a285e97afff..bbf79ed28583 100644
--- a/arch/arm/mach-s3c64xx/include/mach/pm-core.h
+++ b/arch/arm/mach-s3c64xx/include/mach/pm-core.h
@@ -1,15 +1,11 @@
-/* linux/arch/arm/mach-s3c64xx/include/mach/pm-core.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
  *      Ben Dooks <ben@simtec.co.uk>
  *      http://armlinux.simtec.co.uk/
  *
  * S3C64XX - PM core support for arch/arm/plat-s3c/pm.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __MACH_S3C64XX_PM_CORE_H
diff --git a/arch/arm/mach-s3c64xx/include/mach/regs-clock.h b/arch/arm/mach-s3c64xx/include/mach/regs-clock.h
index 4f44aac77092..35a68767b318 100644
--- a/arch/arm/mach-s3c64xx/include/mach/regs-clock.h
+++ b/arch/arm/mach-s3c64xx/include/mach/regs-clock.h
@@ -1,16 +1,12 @@
-/* arch/arm/plat-s3c64xx/include/plat/regs-clock.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *	http://armlinux.simtec.co.uk/
  *
  * S3C64XX clock register definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __PLAT_REGS_CLOCK_H
 #define __PLAT_REGS_CLOCK_H __FILE__
diff --git a/arch/arm/mach-s3c64xx/include/mach/regs-irq.h b/arch/arm/mach-s3c64xx/include/mach/regs-irq.h
index 6a1127891c87..b18c7bcb61c5 100644
--- a/arch/arm/mach-s3c64xx/include/mach/regs-irq.h
+++ b/arch/arm/mach-s3c64xx/include/mach/regs-irq.h
@@ -1,16 +1,12 @@
-/* linux/arch/arm/mach-s3c6400/include/mach/regs-irq.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C64XX - IRQ register definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_ARCH_REGS_IRQ_H
 #define __ASM_ARCH_REGS_IRQ_H __FILE__
diff --git a/arch/arm/mach-s3c64xx/irq-pm.c b/arch/arm/mach-s3c64xx/irq-pm.c
index 0bbf1faaee42..31b221190479 100644
--- a/arch/arm/mach-s3c64xx/irq-pm.c
+++ b/arch/arm/mach-s3c64xx/irq-pm.c
@@ -1,16 +1,11 @@
-/* arch/arm/plat-s3c64xx/irq-pm.c
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *      Ben Dooks <ben@simtec.co.uk>
- *      http://armlinux.simtec.co.uk/
- *
- * S3C64XX - Interrupt handling Power Management
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//      Ben Dooks <ben@simtec.co.uk>
+//      http://armlinux.simtec.co.uk/
+//
+// S3C64XX - Interrupt handling Power Management
 
 /*
  * NOTE: Code in this file is not used when booting with Device Tree support.
diff --git a/arch/arm/mach-s3c64xx/irq-uart.h b/arch/arm/mach-s3c64xx/irq-uart.h
index 4b296132962f..78eccdce95a7 100644
--- a/arch/arm/mach-s3c64xx/irq-uart.h
+++ b/arch/arm/mach-s3c64xx/irq-uart.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2010 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * Header file for Samsung SoC UART IRQ demux for S3C64XX and later
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 struct s3c_uart_irq {
 	void __iomem	*regs;
diff --git a/arch/arm/mach-s3c64xx/mach-anw6410.c b/arch/arm/mach-s3c64xx/mach-anw6410.c
index 347ce6009a8c..0d3d5befb806 100644
--- a/arch/arm/mach-s3c64xx/mach-anw6410.c
+++ b/arch/arm/mach-s3c64xx/mach-anw6410.c
@@ -1,17 +1,11 @@
-/* linux/arch/arm/mach-s3c64xx/mach-anw6410.c
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- * Copyright 2009 Kwangwoo Lee
- * 	Kwangwoo Lee <kwangwoo.lee@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+// Copyright 2009 Kwangwoo Lee
+//	Kwangwoo Lee <kwangwoo.lee@gmail.com>
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c64xx/mach-crag6410-module.c b/arch/arm/mach-s3c64xx/mach-crag6410-module.c
index ea5f2169c850..f00988705408 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410-module.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410-module.c
@@ -1,12 +1,9 @@
-/* Speyside modules for Cragganmore - board data probing
- *
- * Copyright 2011 Wolfson Microelectronics plc
- *	Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Speyside modules for Cragganmore - board data probing
+//
+// Copyright 2011 Wolfson Microelectronics plc
+//	Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/export.h>
 #include <linux/interrupt.h>
diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c
index d9d0440aed78..f04650297487 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410.c
@@ -1,15 +1,10 @@
-/* linux/arch/arm/mach-s3c64xx/mach-crag6410.c
- *
- * Copyright 2011 Wolfson Microelectronics plc
- *	Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * Copyright 2011 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2011 Wolfson Microelectronics plc
+//	Mark Brown <broonie@opensource.wolfsonmicro.com>
+//
+// Copyright 2011 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
 
 #include <linux/kernel.h>
 #include <linux/list.h>
diff --git a/arch/arm/mach-s3c64xx/mach-hmt.c b/arch/arm/mach-s3c64xx/mach-hmt.c
index 59b5531f1987..bfe9881d12cc 100644
--- a/arch/arm/mach-s3c64xx/mach-hmt.c
+++ b/arch/arm/mach-s3c64xx/mach-hmt.c
@@ -1,12 +1,8 @@
-/* mach-hmt.c - Platform code for Airgoo HMT
- *
- * Copyright 2009 Peter Korsgaard <jacmet@sunsite.dk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// mach-hmt.c - Platform code for Airgoo HMT
+//
+// Copyright 2009 Peter Korsgaard <jacmet@sunsite.dk>
 
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/arch/arm/mach-s3c64xx/mach-mini6410.c b/arch/arm/mach-s3c64xx/mach-mini6410.c
index a3e3e25728b4..0dd36ae49e6a 100644
--- a/arch/arm/mach-s3c64xx/mach-mini6410.c
+++ b/arch/arm/mach-s3c64xx/mach-mini6410.c
@@ -1,16 +1,10 @@
-/* linux/arch/arm/mach-s3c64xx/mach-mini6410.c
- *
- * Copyright 2010 Darius Augulis <augulis.darius@gmail.com>
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2010 Darius Augulis <augulis.darius@gmail.com>
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
 
 #include <linux/init.h>
 #include <linux/interrupt.h>
diff --git a/arch/arm/mach-s3c64xx/mach-ncp.c b/arch/arm/mach-s3c64xx/mach-ncp.c
index 23baaa04318c..13fea5c86ca3 100644
--- a/arch/arm/mach-s3c64xx/mach-ncp.c
+++ b/arch/arm/mach-s3c64xx/mach-ncp.c
@@ -1,13 +1,6 @@
-/*
- * linux/arch/arm/mach-s3c64xx/mach-ncp.c
- *
- * Copyright (C) 2008-2009 Samsung Electronics
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2008-2009 Samsung Electronics
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c64xx/mach-real6410.c b/arch/arm/mach-s3c64xx/mach-real6410.c
index d6b3ffd7704b..0ff88b6859c4 100644
--- a/arch/arm/mach-s3c64xx/mach-real6410.c
+++ b/arch/arm/mach-s3c64xx/mach-real6410.c
@@ -1,16 +1,10 @@
-/* linux/arch/arm/mach-s3c64xx/mach-real6410.c
- *
- * Copyright 2010 Darius Augulis <augulis.darius@gmail.com>
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2010 Darius Augulis <augulis.darius@gmail.com>
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
 
 #include <linux/init.h>
 #include <linux/interrupt.h>
diff --git a/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c b/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
index 5bf9afae752d..1724f5ea5c46 100644
--- a/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
+++ b/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
@@ -1,12 +1,8 @@
-/*
- * Samsung's S3C64XX flattened device tree enabled machine
- *
- * Copyright (c) 2013 Tomasz Figa <tomasz.figa@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Samsung's S3C64XX flattened device tree enabled machine
+//
+// Copyright (c) 2013 Tomasz Figa <tomasz.figa@gmail.com>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-s3c64xx/mach-smartq.c b/arch/arm/mach-s3c64xx/mach-smartq.c
index e0e1a729ef98..5655fe968b1f 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq.c
@@ -1,13 +1,6 @@
-/*
- * linux/arch/arm/mach-s3c64xx/mach-smartq.c
- *
- * Copyright (C) 2010 Maurus Cuelenaere
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2010 Maurus Cuelenaere
 
 #include <linux/delay.h>
 #include <linux/fb.h>
diff --git a/arch/arm/mach-s3c64xx/mach-smartq.h b/arch/arm/mach-s3c64xx/mach-smartq.h
index 8e8b693db3af..f98132f4f430 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq.h
+++ b/arch/arm/mach-s3c64xx/mach-smartq.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * linux/arch/arm/mach-s3c64xx/mach-smartq.h
  *
  * Copyright (C) 2010 Maurus Cuelenaere
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #ifndef __MACH_SMARTQ_H
diff --git a/arch/arm/mach-s3c64xx/mach-smartq5.c b/arch/arm/mach-s3c64xx/mach-smartq5.c
index 0972b6ce0ef6..44e9edb144fa 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq5.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq5.c
@@ -1,13 +1,6 @@
-/*
- * linux/arch/arm/mach-s3c64xx/mach-smartq5.c
- *
- * Copyright (C) 2010 Maurus Cuelenaere
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2010 Maurus Cuelenaere
 
 #include <linux/fb.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-s3c64xx/mach-smartq7.c b/arch/arm/mach-s3c64xx/mach-smartq7.c
index 51ac1c6c654a..815ee7d0b5e3 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq7.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq7.c
@@ -1,13 +1,6 @@
-/*
- * linux/arch/arm/mach-s3c64xx/mach-smartq7.c
- *
- * Copyright (C) 2010 Maurus Cuelenaere
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2010 Maurus Cuelenaere
 
 #include <linux/fb.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6400.c b/arch/arm/mach-s3c64xx/mach-smdk6400.c
index 7d8a74fd8915..cbd16843c7d1 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6400.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6400.c
@@ -1,13 +1,8 @@
-/* linux/arch/arm/mach-s3c64xx/mach-smdk6400.c
- *
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c
index 92ec8c3b42b9..c46fa5dfd2e0 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6410.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c
@@ -1,15 +1,9 @@
-/* linux/arch/arm/mach-s3c64xx/mach-smdk6410.c
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c64xx/onenand-core.h b/arch/arm/mach-s3c64xx/onenand-core.h
index 925eb13bbb60..0cf6b5e76b24 100644
--- a/arch/arm/mach-s3c64xx/onenand-core.h
+++ b/arch/arm/mach-s3c64xx/onenand-core.h
@@ -1,14 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  Copyright (c) 2010 Samsung Electronics
  *  Kyungmin Park <kyungmin.park@samsung.com>
  *  Marek Szyprowski <m.szyprowski@samsung.com>
  *
  * Samsung OneNAD Controller core functions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_ARCH_ONENAND_CORE_H
 #define __ASM_ARCH_ONENAND_CORE_H __FILE__
diff --git a/arch/arm/mach-s3c64xx/pl080.c b/arch/arm/mach-s3c64xx/pl080.c
index 66fc774b70ec..152edbeea0c7 100644
--- a/arch/arm/mach-s3c64xx/pl080.c
+++ b/arch/arm/mach-s3c64xx/pl080.c
@@ -1,12 +1,8 @@
-/*
- * Samsung's S3C64XX generic DMA support using amba-pl08x driver.
- *
- * Copyright (c) 2013 Tomasz Figa <tomasz.figa@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Samsung's S3C64XX generic DMA support using amba-pl08x driver.
+//
+// Copyright (c) 2013 Tomasz Figa <tomasz.figa@gmail.com>
 
 #include <linux/kernel.h>
 #include <linux/amba/bus.h>
diff --git a/arch/arm/mach-s3c64xx/pm.c b/arch/arm/mach-s3c64xx/pm.c
index 2f579be8fe67..fd6dbb263ed5 100644
--- a/arch/arm/mach-s3c64xx/pm.c
+++ b/arch/arm/mach-s3c64xx/pm.c
@@ -1,16 +1,11 @@
-/* linux/arch/arm/plat-s3c64xx/pm.c
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * S3C64XX CPU PM support.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// S3C64XX CPU PM support.
 
 #include <linux/init.h>
 #include <linux/suspend.h>
diff --git a/arch/arm/mach-s3c64xx/regs-modem.h b/arch/arm/mach-s3c64xx/regs-modem.h
index 073cdd3a03be..136ad44291bf 100644
--- a/arch/arm/mach-s3c64xx/regs-modem.h
+++ b/arch/arm/mach-s3c64xx/regs-modem.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
@@ -5,11 +6,7 @@
  *      Ben Dooks <ben@simtec.co.uk>
  *
  * S3C64XX - modem block registers
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __MACH_S3C64XX_REGS_MODEM_H
 #define __MACH_S3C64XX_REGS_MODEM_H __FILE__
diff --git a/arch/arm/mach-s3c64xx/regs-srom.h b/arch/arm/mach-s3c64xx/regs-srom.h
index d56f3386eb00..2b37988bdf94 100644
--- a/arch/arm/mach-s3c64xx/regs-srom.h
+++ b/arch/arm/mach-s3c64xx/regs-srom.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2009 Andy Green <andy@warmcat.com>
  *
  * S3C64XX SROM definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __MACH_S3C64XX_REGS_SROM_H
 #define __MACH_S3C64XX_REGS_SROM_H __FILE__
diff --git a/arch/arm/mach-s3c64xx/s3c6400.c b/arch/arm/mach-s3c64xx/s3c6400.c
index 5ea82accc773..545eea716db8 100644
--- a/arch/arm/mach-s3c64xx/s3c6400.c
+++ b/arch/arm/mach-s3c64xx/s3c6400.c
@@ -1,13 +1,8 @@
-/* linux/arch/arm/mach-s3c64xx/cpu.c
- *
- * Copyright 2009 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2009 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
 
 /*
  * NOTE: Code in this file is not used when booting with Device Tree support.
diff --git a/arch/arm/mach-s3c64xx/s3c6410.c b/arch/arm/mach-s3c64xx/s3c6410.c
index 92bb927c4478..47e04e019624 100644
--- a/arch/arm/mach-s3c64xx/s3c6410.c
+++ b/arch/arm/mach-s3c64xx/s3c6410.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/mach-s3c64xx/s3c6410.c
- *
- * Copyright 2008 Simtec Electronics
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Simtec Electronics
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
 
 /*
  * NOTE: Code in this file is not used when booting with Device Tree support.
diff --git a/arch/arm/mach-s3c64xx/setup-fb-24bpp.c b/arch/arm/mach-s3c64xx/setup-fb-24bpp.c
index 9d17bff12d4d..2c7178b26ebb 100644
--- a/arch/arm/mach-s3c64xx/setup-fb-24bpp.c
+++ b/arch/arm/mach-s3c64xx/setup-fb-24bpp.c
@@ -1,16 +1,11 @@
-/* linux/arch/arm/plat-s3c64xx/setup-fb-24bpp.c
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * Base S3C64XX setup information for 24bpp LCD framebuffer
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// Base S3C64XX setup information for 24bpp LCD framebuffer
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c64xx/setup-i2c0.c b/arch/arm/mach-s3c64xx/setup-i2c0.c
index 4b8c1cfdd1fc..552eb50da38c 100644
--- a/arch/arm/mach-s3c64xx/setup-i2c0.c
+++ b/arch/arm/mach-s3c64xx/setup-i2c0.c
@@ -1,16 +1,11 @@
-/* linux/arch/arm/plat-s3c64xx/setup-i2c0.c
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * Base S3C64XX I2C bus 0 gpio configuration
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// Base S3C64XX I2C bus 0 gpio configuration
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c64xx/setup-i2c1.c b/arch/arm/mach-s3c64xx/setup-i2c1.c
index cd1df71ee13b..d231f0fc508d 100644
--- a/arch/arm/mach-s3c64xx/setup-i2c1.c
+++ b/arch/arm/mach-s3c64xx/setup-i2c1.c
@@ -1,16 +1,11 @@
-/* linux/arch/arm/plat-s3c64xx/setup-i2c1.c
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * Base S3C64XX I2C bus 1 gpio configuration
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// Base S3C64XX I2C bus 1 gpio configuration
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c64xx/setup-ide.c b/arch/arm/mach-s3c64xx/setup-ide.c
index 689fb72e715c..810139a807ce 100644
--- a/arch/arm/mach-s3c64xx/setup-ide.c
+++ b/arch/arm/mach-s3c64xx/setup-ide.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/mach-s3c64xx/setup-ide.c
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S3C64XX setup information for IDE
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2010 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com/
+//
+// S3C64XX setup information for IDE
 
 #include <linux/kernel.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-s3c64xx/setup-keypad.c b/arch/arm/mach-s3c64xx/setup-keypad.c
index 6ad9a89dfddf..351961025273 100644
--- a/arch/arm/mach-s3c64xx/setup-keypad.c
+++ b/arch/arm/mach-s3c64xx/setup-keypad.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/mach-s3c64xx/setup-keypad.c
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * GPIO configuration for S3C64XX KeyPad device
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2010 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com/
+//
+// GPIO configuration for S3C64XX KeyPad device
 
 #include <linux/gpio.h>
 #include <plat/gpio-cfg.h>
diff --git a/arch/arm/mach-s3c64xx/setup-sdhci-gpio.c b/arch/arm/mach-s3c64xx/setup-sdhci-gpio.c
index f426b7a16c16..138455af4937 100644
--- a/arch/arm/mach-s3c64xx/setup-sdhci-gpio.c
+++ b/arch/arm/mach-s3c64xx/setup-sdhci-gpio.c
@@ -1,15 +1,10 @@
-/* linux/arch/arm/plat-s3c64xx/setup-sdhci-gpio.c
- *
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * S3C64XX - Helper functions for setting up SDHCI device(s) GPIO (HSMMC)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// S3C64XX - Helper functions for setting up SDHCI device(s) GPIO (HSMMC)
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-s3c64xx/setup-spi.c b/arch/arm/mach-s3c64xx/setup-spi.c
index 5fd1a315c901..39dfae1f46e7 100644
--- a/arch/arm/mach-s3c64xx/setup-spi.c
+++ b/arch/arm/mach-s3c64xx/setup-spi.c
@@ -1,12 +1,7 @@
-/* linux/arch/arm/mach-s3c64xx/setup-spi.c
- *
- * Copyright (C) 2011 Samsung Electronics Ltd.
- *		http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2011 Samsung Electronics Ltd.
+//		http://www.samsung.com/
 
 #include <linux/gpio.h>
 #include <plat/gpio-cfg.h>
diff --git a/arch/arm/mach-s3c64xx/setup-usb-phy.c b/arch/arm/mach-s3c64xx/setup-usb-phy.c
index 2b17b7f5152f..46a9e955607f 100644
--- a/arch/arm/mach-s3c64xx/setup-usb-phy.c
+++ b/arch/arm/mach-s3c64xx/setup-usb-phy.c
@@ -1,13 +1,7 @@
-/*
- * Copyright (C) 2011 Samsung Electronics Co.Ltd
- * Author: Joonyoung Shim <jy0922.shim@samsung.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (C) 2011 Samsung Electronics Co.Ltd
+// Author: Joonyoung Shim <jy0922.shim@samsung.com>
 
 #include <linux/clk.h>
 #include <linux/delay.h>
diff --git a/arch/arm/mach-s3c64xx/sleep.S b/arch/arm/mach-s3c64xx/sleep.S
index 34313f9c8792..39e16a07a5e4 100644
--- a/arch/arm/mach-s3c64xx/sleep.S
+++ b/arch/arm/mach-s3c64xx/sleep.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /* linux/arch/arm/plat-s3c64xx/sleep.S
  *
  * Copyright 2008 Openmoko, Inc.
@@ -6,11 +7,7 @@
  *	http://armlinux.simtec.co.uk/
  *
  * S3C64XX CPU sleep code
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
diff --git a/arch/arm/mach-s3c64xx/watchdog-reset.h b/arch/arm/mach-s3c64xx/watchdog-reset.h
index 42707dfbda9c..1042d6c463dc 100644
--- a/arch/arm/mach-s3c64xx/watchdog-reset.h
+++ b/arch/arm/mach-s3c64xx/watchdog-reset.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2008 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C2410 - System define for arch_reset() function
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __PLAT_SAMSUNG_WATCHDOG_RESET_H
 #define __PLAT_SAMSUNG_WATCHDOG_RESET_H
diff --git a/arch/arm/mach-s5pv210/Kconfig b/arch/arm/mach-s5pv210/Kconfig
index 4cec11cf5e6f..03984a791879 100644
--- a/arch/arm/mach-s5pv210/Kconfig
+++ b/arch/arm/mach-s5pv210/Kconfig
@@ -1,9 +1,7 @@
-# arch/arm/mach-s5pv210/Kconfig
+# SPDX-License-Identifier: GPL-2.0
 #
 # Copyright (c) 2010 Samsung Electronics Co., Ltd.
 #		http://www.samsung.com/
-#
-# Licensed under GPLv2
 
 # Configuration options for the S5PV210/S5PC110
 
diff --git a/arch/arm/mach-s5pv210/Makefile b/arch/arm/mach-s5pv210/Makefile
index fa7fb716e388..e7b551e18e5c 100644
--- a/arch/arm/mach-s5pv210/Makefile
+++ b/arch/arm/mach-s5pv210/Makefile
@@ -1,9 +1,7 @@
-# arch/arm/mach-s5pv210/Makefile
+# SPDX-License-Identifier: GPL-2.0
 #
 # Copyright (c) 2010 Samsung Electronics Co., Ltd.
 # 		http://www.samsung.com/
-#
-# Licensed under GPLv2
 
 ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/arch/arm/plat-samsung/include
 
diff --git a/arch/arm/mach-s5pv210/common.h b/arch/arm/mach-s5pv210/common.h
index 2ad387c1ecf0..0a188134deae 100644
--- a/arch/arm/mach-s5pv210/common.h
+++ b/arch/arm/mach-s5pv210/common.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Common Header for S5PV210 machines
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __ARCH_ARM_MACH_S5PV210_COMMON_H
diff --git a/arch/arm/mach-s5pv210/pm.c b/arch/arm/mach-s5pv210/pm.c
index 07cee14a363b..f491249ab658 100644
--- a/arch/arm/mach-s5pv210/pm.c
+++ b/arch/arm/mach-s5pv210/pm.c
@@ -1,18 +1,13 @@
-/* linux/arch/arm/mach-s5pv210/pm.c
- *
- * Copyright (c) 2010-2014 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * S5PV210 - Power Management support
- *
- * Based on arch/arm/mach-s3c2410/pm.c
- * Copyright (c) 2006 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2010-2014 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
+//
+// S5PV210 - Power Management support
+//
+// Based on arch/arm/mach-s3c2410/pm.c
+// Copyright (c) 2006 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
 
 #include <linux/init.h>
 #include <linux/suspend.h>
diff --git a/arch/arm/mach-s5pv210/regs-clock.h b/arch/arm/mach-s5pv210/regs-clock.h
index fb3eb77412db..2a35c831a9b0 100644
--- a/arch/arm/mach-s5pv210/regs-clock.h
+++ b/arch/arm/mach-s5pv210/regs-clock.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2010 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com/
  *
  * S5PV210 - Clock register definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_ARCH_REGS_CLOCK_H
 #define __ASM_ARCH_REGS_CLOCK_H __FILE__
diff --git a/arch/arm/mach-s5pv210/s5pv210.c b/arch/arm/mach-s5pv210/s5pv210.c
index 83e656ea95ae..868f9c20419d 100644
--- a/arch/arm/mach-s5pv210/s5pv210.c
+++ b/arch/arm/mach-s5pv210/s5pv210.c
@@ -1,14 +1,10 @@
-/*
- * Samsung's S5PC110/S5PV210 flattened device tree enabled machine.
- *
- * Copyright (c) 2013-2014 Samsung Electronics Co., Ltd.
- * Mateusz Krawczuk <m.krawczuk@partner.samsung.com>
- * Tomasz Figa <t.figa@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Samsung's S5PC110/S5PV210 flattened device tree enabled machine.
+//
+// Copyright (c) 2013-2014 Samsung Electronics Co., Ltd.
+// Mateusz Krawczuk <m.krawczuk@partner.samsung.com>
+// Tomasz Figa <t.figa@samsung.com>
 
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
diff --git a/arch/arm/mach-s5pv210/sleep.S b/arch/arm/mach-s5pv210/sleep.S
index dfbfc0f7f8b8..81568767f30a 100644
--- a/arch/arm/mach-s5pv210/sleep.S
+++ b/arch/arm/mach-s5pv210/sleep.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
@@ -5,11 +6,6 @@
  * S5PV210 Sleep Code
  * Based on S3C64XX sleep code by:
  *	Ben Dooks, (c) 2008 Simtec Electronics
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/linkage.h>
diff --git a/arch/arm/mach-sa1100/Kconfig b/arch/arm/mach-sa1100/Kconfig
index 36e3c79f4973..07df3a59b13f 100644
--- a/arch/arm/mach-sa1100/Kconfig
+++ b/arch/arm/mach-sa1100/Kconfig
@@ -5,6 +5,7 @@ menu "SA11x0 Implementations"
 config SA1100_ASSABET
 	bool "Assabet"
 	select ARM_SA1110_CPUFREQ
+	select GPIO_REG
 	help
 	  Say Y here if you are using the Intel(R) StrongARM(R) SA-1110
 	  Microprocessor Development Board (also known as the Assabet).
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index d28ecb9ef172..f68241d995f2 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/errno.h>
+#include <linux/gpio/gpio-reg.h>
 #include <linux/ioport.h>
 #include <linux/platform_data/sa11x0-serial.h>
 #include <linux/serial_core.h>
@@ -61,20 +62,45 @@
 unsigned long SCR_value = ASSABET_SCR_INIT;
 EXPORT_SYMBOL(SCR_value);
 
-static unsigned long BCR_value = ASSABET_BCR_DB1110;
+static struct gpio_chip *assabet_bcr_gc;
+
+static const char *assabet_names[] = {
+	"cf_pwr", "cf_gfx_reset", "nsoft_reset", "irda_fsel",
+	"irda_md0", "irda_md1", "stereo_loopback", "ncf_bus_on",
+	"audio_pwr_on", "light_pwr_on", "lcd16data", "lcd_pwr_on",
+	"rs232_on", "nred_led", "ngreen_led", "vib_on",
+	"com_dtr", "com_rts", "radio_wake_mod", "i2c_enab",
+	"tvir_enab", "qmute", "radio_pwr_on", "spkr_off",
+	"rs232_valid", "com_dcd", "com_cts", "com_dsr",
+	"radio_cts", "radio_dsr", "radio_dcd", "radio_ri",
+};
 
+/* The old deprecated interface */
 void ASSABET_BCR_frob(unsigned int mask, unsigned int val)
 {
-	unsigned long flags;
+	unsigned long m = mask, v = val;
 
-	local_irq_save(flags);
-	BCR_value = (BCR_value & ~mask) | val;
-	ASSABET_BCR = BCR_value;
-	local_irq_restore(flags);
+	assabet_bcr_gc->set_multiple(assabet_bcr_gc, &m, &v);
 }
-
 EXPORT_SYMBOL(ASSABET_BCR_frob);
 
+static int __init assabet_init_gpio(void __iomem *reg, u32 def_val)
+{
+	struct gpio_chip *gc;
+
+	writel_relaxed(def_val, reg);
+
+	gc = gpio_reg_init(NULL, reg, -1, 32, "assabet", 0xff000000, def_val,
+			   assabet_names, NULL, NULL);
+
+	if (IS_ERR(gc))
+		return PTR_ERR(gc);
+
+	assabet_bcr_gc = gc;
+
+	return gc->base;
+}
+
 /*
  * The codec reset goes to three devices, so we need to release
  * the rest when any one of these requests it.  However, that
@@ -146,7 +172,7 @@ static void adv7171_write(unsigned reg, unsigned val)
 	unsigned gpdr = GPDR;
 	unsigned gplr = GPLR;
 
-	ASSABET_BCR = BCR_value | ASSABET_BCR_AUDIO_ON;
+	ASSABET_BCR_frob(ASSABET_BCR_AUDIO_ON, ASSABET_BCR_AUDIO_ON);
 	udelay(100);
 
 	GPCR = SDA | SCK | MOD; /* clear L3 mode to ensure UDA1341 doesn't respond */
@@ -457,14 +483,6 @@ static void __init assabet_init(void)
 	sa11x0_ppc_configure_mcp();
 
 	if (machine_has_neponset()) {
-		/*
-		 * Angel sets this, but other bootloaders may not.
-		 *
-		 * This must precede any driver calls to BCR_set()
-		 * or BCR_clear().
-		 */
-		ASSABET_BCR = BCR_value = ASSABET_BCR_DB1111;
-
 #ifndef CONFIG_ASSABET_NEPONSET
 		printk( "Warning: Neponset detected but full support "
 			"hasn't been configured in the kernel\n" );
@@ -748,12 +766,31 @@ static int __init assabet_leds_init(void)
 fs_initcall(assabet_leds_init);
 #endif
 
+void __init assabet_init_irq(void)
+{
+	u32 def_val;
+
+	sa1100_init_irq();
+
+	if (machine_has_neponset())
+		def_val = ASSABET_BCR_DB1111;
+	else
+		def_val = ASSABET_BCR_DB1110;
+
+	/*
+	 * Angel sets this, but other bootloaders may not.
+	 *
+	 * This must precede any driver calls to BCR_set() or BCR_clear().
+	 */
+	assabet_init_gpio((void *)&ASSABET_BCR, def_val);
+}
+
 MACHINE_START(ASSABET, "Intel-Assabet")
 	.atag_offset	= 0x100,
 	.fixup		= fixup_assabet,
 	.map_io		= assabet_map_io,
 	.nr_irqs	= SA1100_NR_IRQS,
-	.init_irq	= sa1100_init_irq,
+	.init_irq	= assabet_init_irq,
 	.init_time	= sa1100_timer_init,
 	.init_machine	= assabet_init,
 	.init_late	= sa11x0_init_late,
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index a61a2432766b..b1823f445358 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -3,6 +3,8 @@
  * linux/arch/arm/mach-sa1100/neponset.c
  */
 #include <linux/err.h>
+#include <linux/gpio/driver.h>
+#include <linux/gpio/gpio-reg.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/irq.h>
@@ -45,10 +47,13 @@
 #define IRR_USAR	(1 << 1)
 #define IRR_SA1111	(1 << 2)
 
+#define NCR_NGPIO	7
+
 #define MDM_CTL0_RTS1	(1 << 0)
 #define MDM_CTL0_DTR1	(1 << 1)
 #define MDM_CTL0_RTS2	(1 << 2)
 #define MDM_CTL0_DTR2	(1 << 3)
+#define MDM_CTL0_NGPIO	4
 
 #define MDM_CTL1_CTS1	(1 << 0)
 #define MDM_CTL1_DSR1	(1 << 1)
@@ -56,80 +61,87 @@
 #define MDM_CTL1_CTS2	(1 << 3)
 #define MDM_CTL1_DSR2	(1 << 4)
 #define MDM_CTL1_DCD2	(1 << 5)
+#define MDM_CTL1_NGPIO	6
 
 #define AUD_SEL_1341	(1 << 0)
 #define AUD_MUTE_1341	(1 << 1)
+#define AUD_NGPIO	2
 
 extern void sa1110_mb_disable(void);
 
+#define to_neponset_gpio_chip(x) container_of(x, struct neponset_gpio_chip, gc)
+
+static const char *neponset_ncr_names[] = {
+	"gp01_off", "tp_power", "ms_power", "enet_osc",
+	"spi_kb_wk_up", "a0vpp", "a1vpp"
+};
+
+static const char *neponset_mdmctl0_names[] = {
+	"rts3", "dtr3", "rts1", "dtr1",
+};
+
+static const char *neponset_mdmctl1_names[] = {
+	"cts3", "dsr3", "dcd3", "cts1", "dsr1", "dcd1"
+};
+
+static const char *neponset_aud_names[] = {
+	"sel_1341", "mute_1341",
+};
+
 struct neponset_drvdata {
 	void __iomem *base;
 	struct platform_device *sa1111;
 	struct platform_device *smc91x;
 	unsigned irq_base;
-#ifdef CONFIG_PM_SLEEP
-	u32 ncr0;
-	u32 mdm_ctl_0;
-#endif
+	struct gpio_chip *gpio[4];
 };
 
-static void __iomem *nep_base;
+static struct neponset_drvdata *nep;
 
 void neponset_ncr_frob(unsigned int mask, unsigned int val)
 {
-	void __iomem *base = nep_base;
-
-	if (base) {
-		unsigned long flags;
-		unsigned v;
-
-		local_irq_save(flags);
-		v = readb_relaxed(base + NCR_0);
-		writeb_relaxed((v & ~mask) | val, base + NCR_0);
-		local_irq_restore(flags);
-	} else {
-		WARN(1, "nep_base unset\n");
-	}
+	struct neponset_drvdata *n = nep;
+	unsigned long m = mask, v = val;
+
+	if (nep)
+		n->gpio[0]->set_multiple(n->gpio[0], &m, &v);
+	else
+		WARN(1, "nep unset\n");
 }
 EXPORT_SYMBOL(neponset_ncr_frob);
 
 static void neponset_set_mctrl(struct uart_port *port, u_int mctrl)
 {
-	void __iomem *base = nep_base;
-	u_int mdm_ctl0;
+	struct neponset_drvdata *n = nep;
+	unsigned long mask, val = 0;
 
-	if (!base)
+	if (!n)
 		return;
 
-	mdm_ctl0 = readb_relaxed(base + MDM_CTL_0);
 	if (port->mapbase == _Ser1UTCR0) {
-		if (mctrl & TIOCM_RTS)
-			mdm_ctl0 &= ~MDM_CTL0_RTS2;
-		else
-			mdm_ctl0 |= MDM_CTL0_RTS2;
-
-		if (mctrl & TIOCM_DTR)
-			mdm_ctl0 &= ~MDM_CTL0_DTR2;
-		else
-			mdm_ctl0 |= MDM_CTL0_DTR2;
+		mask = MDM_CTL0_RTS2 | MDM_CTL0_DTR2;
+
+		if (!(mctrl & TIOCM_RTS))
+			val |= MDM_CTL0_RTS2;
+
+		if (!(mctrl & TIOCM_DTR))
+			val |= MDM_CTL0_DTR2;
 	} else if (port->mapbase == _Ser3UTCR0) {
-		if (mctrl & TIOCM_RTS)
-			mdm_ctl0 &= ~MDM_CTL0_RTS1;
-		else
-			mdm_ctl0 |= MDM_CTL0_RTS1;
-
-		if (mctrl & TIOCM_DTR)
-			mdm_ctl0 &= ~MDM_CTL0_DTR1;
-		else
-			mdm_ctl0 |= MDM_CTL0_DTR1;
+		mask = MDM_CTL0_RTS1 | MDM_CTL0_DTR1;
+
+		if (!(mctrl & TIOCM_RTS))
+			val |= MDM_CTL0_RTS1;
+
+		if (!(mctrl & TIOCM_DTR))
+			val |= MDM_CTL0_DTR1;
 	}
 
-	writeb_relaxed(mdm_ctl0, base + MDM_CTL_0);
+	n->gpio[1]->set_multiple(n->gpio[1], &mask, &val);
 }
 
 static u_int neponset_get_mctrl(struct uart_port *port)
 {
-	void __iomem *base = nep_base;
+	void __iomem *base = nep->base;
 	u_int ret = TIOCM_CD | TIOCM_CTS | TIOCM_DSR;
 	u_int mdm_ctl1;
 
@@ -231,6 +243,22 @@ static struct irq_chip nochip = {
 	.irq_unmask = nochip_noop,
 };
 
+static int neponset_init_gpio(struct gpio_chip **gcp,
+	struct device *dev, const char *label, void __iomem *reg,
+	unsigned num, bool in, const char *const * names)
+{
+	struct gpio_chip *gc;
+
+	gc = gpio_reg_init(dev, reg, -1, num, label, in ? 0xffffffff : 0,
+			   readl_relaxed(reg), names, NULL, NULL);
+	if (IS_ERR(gc))
+		return PTR_ERR(gc);
+
+	*gcp = gc;
+
+	return 0;
+}
+
 static struct sa1111_platform_data sa1111_info = {
 	.disable_devs	= SA1111_DEVID_PS2_MSE,
 };
@@ -274,7 +302,7 @@ static int neponset_probe(struct platform_device *dev)
 	};
 	int ret, irq;
 
-	if (nep_base)
+	if (nep)
 		return -EBUSY;
 
 	irq = ret = platform_get_irq(dev, 0);
@@ -330,6 +358,22 @@ static int neponset_probe(struct platform_device *dev)
 	irq_set_irq_type(irq, IRQ_TYPE_EDGE_RISING);
 	irq_set_chained_handler_and_data(irq, neponset_irq_handler, d);
 
+	/* Disable GPIO 0/1 drivers so the buttons work on the Assabet */
+	writeb_relaxed(NCR_GP01_OFF, d->base + NCR_0);
+
+	neponset_init_gpio(&d->gpio[0], &dev->dev, "neponset-ncr",
+			   d->base + NCR_0, NCR_NGPIO, false,
+			   neponset_ncr_names);
+	neponset_init_gpio(&d->gpio[1], &dev->dev, "neponset-mdm-ctl0",
+			   d->base + MDM_CTL_0, MDM_CTL0_NGPIO, false,
+			   neponset_mdmctl0_names);
+	neponset_init_gpio(&d->gpio[2], &dev->dev, "neponset-mdm-ctl1",
+			   d->base + MDM_CTL_1, MDM_CTL1_NGPIO, true,
+			   neponset_mdmctl1_names);
+	neponset_init_gpio(&d->gpio[3], &dev->dev, "neponset-aud-ctl",
+			   d->base + AUD_CTL, AUD_NGPIO, false,
+			   neponset_aud_names);
+
 	/*
 	 * We would set IRQ_GPIO25 to be a wake-up IRQ, but unfortunately
 	 * something on the Neponset activates this IRQ on sleep (eth?)
@@ -340,16 +384,13 @@ static int neponset_probe(struct platform_device *dev)
 
 	dev_info(&dev->dev, "Neponset daughter board, providing IRQ%u-%u\n",
 		 d->irq_base, d->irq_base + NEP_IRQ_NR - 1);
-	nep_base = d->base;
+	nep = d;
 
 	sa1100_register_uart_fns(&neponset_port_fns);
 
 	/* Ensure that the memory bus request/grant signals are setup */
 	sa1110_mb_disable();
 
-	/* Disable GPIO 0/1 drivers so the buttons work on the Assabet */
-	writeb_relaxed(NCR_GP01_OFF, d->base + NCR_0);
-
 	sa1111_resources[0].parent = sa1111_res;
 	sa1111_resources[1].start = d->irq_base + NEP_IRQ_SA1111;
 	sa1111_resources[1].end = d->irq_base + NEP_IRQ_SA1111;
@@ -385,7 +426,7 @@ static int neponset_remove(struct platform_device *dev)
 		platform_device_unregister(d->smc91x);
 	irq_set_chained_handler(irq, NULL);
 	irq_free_descs(d->irq_base, NEP_IRQ_NR);
-	nep_base = NULL;
+	nep = NULL;
 	iounmap(d->base);
 	kfree(d);
 
@@ -393,30 +434,22 @@ static int neponset_remove(struct platform_device *dev)
 }
 
 #ifdef CONFIG_PM_SLEEP
-static int neponset_suspend(struct device *dev)
-{
-	struct neponset_drvdata *d = dev_get_drvdata(dev);
-
-	d->ncr0 = readb_relaxed(d->base + NCR_0);
-	d->mdm_ctl_0 = readb_relaxed(d->base + MDM_CTL_0);
-
-	return 0;
-}
-
 static int neponset_resume(struct device *dev)
 {
 	struct neponset_drvdata *d = dev_get_drvdata(dev);
+	int i, ret = 0;
 
-	writeb_relaxed(d->ncr0, d->base + NCR_0);
-	writeb_relaxed(d->mdm_ctl_0, d->base + MDM_CTL_0);
+	for (i = 0; i < ARRAY_SIZE(d->gpio); i++) {
+		ret = gpio_reg_resume(d->gpio[i]);
+		if (ret)
+			break;
+	}
 
-	return 0;
+	return ret;
 }
 
 static const struct dev_pm_ops neponset_pm_ops = {
-	.suspend_noirq = neponset_suspend,
 	.resume_noirq = neponset_resume,
-	.freeze_noirq = neponset_suspend,
 	.restore_noirq = neponset_resume,
 };
 #define PM_OPS &neponset_pm_ops
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index fd9077a74fce..7f14acf67caf 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -909,6 +909,14 @@ config OUTER_CACHE_SYNC
 	  The outer cache has a outer_cache_fns.sync function pointer
 	  that can be used to drain the write buffer of the outer cache.
 
+config CACHE_B15_RAC
+	bool "Enable the Broadcom Brahma-B15 read-ahead cache controller"
+	depends on ARCH_BRCMSTB
+	default y
+	help
+	  This option enables the Broadcom Brahma-B15 read-ahead cache
+	  controller. If disabled, the read-ahead cache remains off.
+
 config CACHE_FEROCEON_L2
 	bool "Enable the Feroceon L2 cache controller"
 	depends on ARCH_MV78XX0 || ARCH_MVEBU
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 01bcc33f59e3..9dbb84923e12 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -13,7 +13,8 @@ obj-y				+= nommu.o
 obj-$(CONFIG_ARM_MPU)		+= pmsa-v7.o
 endif
 
-obj-$(CONFIG_ARM_PTDUMP)	+= dump.o
+obj-$(CONFIG_ARM_PTDUMP_CORE)	+= dump.o
+obj-$(CONFIG_ARM_PTDUMP_DEBUGFS)	+= ptdump_debugfs.o
 obj-$(CONFIG_MODULES)		+= proc-syms.o
 obj-$(CONFIG_DEBUG_VIRTUAL)	+= physaddr.o
 
@@ -103,6 +104,7 @@ AFLAGS_proc-v6.o	:=-Wa,-march=armv6
 AFLAGS_proc-v7.o	:=-Wa,-march=armv7-a
 
 obj-$(CONFIG_OUTER_CACHE)	+= l2c-common.o
+obj-$(CONFIG_CACHE_B15_RAC)	+= cache-b15-rac.o
 obj-$(CONFIG_CACHE_FEROCEON_L2)	+= cache-feroceon-l2.o
 obj-$(CONFIG_CACHE_L2X0)	+= cache-l2x0.o l2c-l2x0-resume.o
 obj-$(CONFIG_CACHE_L2X0_PMU)	+= cache-l2x0-pmu.o
diff --git a/arch/arm/mm/cache-b15-rac.c b/arch/arm/mm/cache-b15-rac.c
new file mode 100644
index 000000000000..d9586ba2e63c
--- /dev/null
+++ b/arch/arm/mm/cache-b15-rac.c
@@ -0,0 +1,356 @@
+/*
+ * Broadcom Brahma-B15 CPU read-ahead cache management functions
+ *
+ * Copyright (C) 2015-2016 Broadcom
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/io.h>
+#include <linux/bitops.h>
+#include <linux/of_address.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/syscore_ops.h>
+#include <linux/reboot.h>
+
+#include <asm/cacheflush.h>
+#include <asm/hardware/cache-b15-rac.h>
+
+extern void v7_flush_kern_cache_all(void);
+
+/* RAC register offsets, relative to the HIF_CPU_BIUCTRL register base */
+#define RAC_CONFIG0_REG			(0x78)
+#define  RACENPREF_MASK			(0x3)
+#define  RACPREFINST_SHIFT		(0)
+#define  RACENINST_SHIFT		(2)
+#define  RACPREFDATA_SHIFT		(4)
+#define  RACENDATA_SHIFT		(6)
+#define  RAC_CPU_SHIFT			(8)
+#define  RACCFG_MASK			(0xff)
+#define RAC_CONFIG1_REG			(0x7c)
+#define RAC_FLUSH_REG			(0x80)
+#define  FLUSH_RAC			(1 << 0)
+
+/* Bitmask to enable instruction and data prefetching with a 256-bytes stride */
+#define RAC_DATA_INST_EN_MASK		(1 << RACPREFINST_SHIFT | \
+					 RACENPREF_MASK << RACENINST_SHIFT | \
+					 1 << RACPREFDATA_SHIFT | \
+					 RACENPREF_MASK << RACENDATA_SHIFT)
+
+#define RAC_ENABLED			0
+/* Special state where we want to bypass the spinlock and call directly
+ * into the v7 cache maintenance operations during suspend/resume
+ */
+#define RAC_SUSPENDED			1
+
+static void __iomem *b15_rac_base;
+static DEFINE_SPINLOCK(rac_lock);
+
+static u32 rac_config0_reg;
+
+/* Initialization flag to avoid checking for b15_rac_base, and to prevent
+ * multi-platform kernels from crashing here as well.
+ */
+static unsigned long b15_rac_flags;
+
+static inline u32 __b15_rac_disable(void)
+{
+	u32 val = __raw_readl(b15_rac_base + RAC_CONFIG0_REG);
+	__raw_writel(0, b15_rac_base + RAC_CONFIG0_REG);
+	dmb();
+	return val;
+}
+
+static inline void __b15_rac_flush(void)
+{
+	u32 reg;
+
+	__raw_writel(FLUSH_RAC, b15_rac_base + RAC_FLUSH_REG);
+	do {
+		/* This dmb() is required to force the Bus Interface Unit
+		 * to clean oustanding writes, and forces an idle cycle
+		 * to be inserted.
+		 */
+		dmb();
+		reg = __raw_readl(b15_rac_base + RAC_FLUSH_REG);
+	} while (reg & FLUSH_RAC);
+}
+
+static inline u32 b15_rac_disable_and_flush(void)
+{
+	u32 reg;
+
+	reg = __b15_rac_disable();
+	__b15_rac_flush();
+	return reg;
+}
+
+static inline void __b15_rac_enable(u32 val)
+{
+	__raw_writel(val, b15_rac_base + RAC_CONFIG0_REG);
+	/* dsb() is required here to be consistent with __flush_icache_all() */
+	dsb();
+}
+
+#define BUILD_RAC_CACHE_OP(name, bar)				\
+void b15_flush_##name(void)					\
+{								\
+	unsigned int do_flush;					\
+	u32 val = 0;						\
+								\
+	if (test_bit(RAC_SUSPENDED, &b15_rac_flags)) {		\
+		v7_flush_##name();				\
+		bar;						\
+		return;						\
+	}							\
+								\
+	spin_lock(&rac_lock);					\
+	do_flush = test_bit(RAC_ENABLED, &b15_rac_flags);	\
+	if (do_flush)						\
+		val = b15_rac_disable_and_flush();		\
+	v7_flush_##name();					\
+	if (!do_flush)						\
+		bar;						\
+	else							\
+		__b15_rac_enable(val);				\
+	spin_unlock(&rac_lock);					\
+}
+
+#define nobarrier
+
+/* The readahead cache present in the Brahma-B15 CPU is a special piece of
+ * hardware after the integrated L2 cache of the B15 CPU complex whose purpose
+ * is to prefetch instruction and/or data with a line size of either 64 bytes
+ * or 256 bytes. The rationale is that the data-bus of the CPU interface is
+ * optimized for 256-bytes transactions, and enabling the readahead cache
+ * provides a significant performance boost we want it enabled (typically
+ * twice the performance for a memcpy benchmark application).
+ *
+ * The readahead cache is transparent for Modified Virtual Addresses
+ * cache maintenance operations: ICIMVAU, DCIMVAC, DCCMVAC, DCCMVAU and
+ * DCCIMVAC.
+ *
+ * It is however not transparent for the following cache maintenance
+ * operations: DCISW, DCCSW, DCCISW, ICIALLUIS and ICIALLU which is precisely
+ * what we are patching here with our BUILD_RAC_CACHE_OP here.
+ */
+BUILD_RAC_CACHE_OP(kern_cache_all, nobarrier);
+
+static void b15_rac_enable(void)
+{
+	unsigned int cpu;
+	u32 enable = 0;
+
+	for_each_possible_cpu(cpu)
+		enable |= (RAC_DATA_INST_EN_MASK << (cpu * RAC_CPU_SHIFT));
+
+	b15_rac_disable_and_flush();
+	__b15_rac_enable(enable);
+}
+
+static int b15_rac_reboot_notifier(struct notifier_block *nb,
+				   unsigned long action,
+				   void *data)
+{
+	/* During kexec, we are not yet migrated on the boot CPU, so we need to
+	 * make sure we are SMP safe here. Once the RAC is disabled, flag it as
+	 * suspended such that the hotplug notifier returns early.
+	 */
+	if (action == SYS_RESTART) {
+		spin_lock(&rac_lock);
+		b15_rac_disable_and_flush();
+		clear_bit(RAC_ENABLED, &b15_rac_flags);
+		set_bit(RAC_SUSPENDED, &b15_rac_flags);
+		spin_unlock(&rac_lock);
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block b15_rac_reboot_nb = {
+	.notifier_call	= b15_rac_reboot_notifier,
+};
+
+/* The CPU hotplug case is the most interesting one, we basically need to make
+ * sure that the RAC is disabled for the entire system prior to having a CPU
+ * die, in particular prior to this dying CPU having exited the coherency
+ * domain.
+ *
+ * Once this CPU is marked dead, we can safely re-enable the RAC for the
+ * remaining CPUs in the system which are still online.
+ *
+ * Offlining a CPU is the problematic case, onlining a CPU is not much of an
+ * issue since the CPU and its cache-level hierarchy will start filling with
+ * the RAC disabled, so L1 and L2 only.
+ *
+ * In this function, we should NOT have to verify any unsafe setting/condition
+ * b15_rac_base:
+ *
+ *   It is protected by the RAC_ENABLED flag which is cleared by default, and
+ *   being cleared when initial procedure is done. b15_rac_base had been set at
+ *   that time.
+ *
+ * RAC_ENABLED:
+ *   There is a small timing windows, in b15_rac_init(), between
+ *      cpuhp_setup_state_*()
+ *      ...
+ *      set RAC_ENABLED
+ *   However, there is no hotplug activity based on the Linux booting procedure.
+ *
+ * Since we have to disable RAC for all cores, we keep RAC on as long as as
+ * possible (disable it as late as possible) to gain the cache benefit.
+ *
+ * Thus, dying/dead states are chosen here
+ *
+ * We are choosing not do disable the RAC on a per-CPU basis, here, if we did
+ * we would want to consider disabling it as early as possible to benefit the
+ * other active CPUs.
+ */
+
+/* Running on the dying CPU */
+static int b15_rac_dying_cpu(unsigned int cpu)
+{
+	/* During kexec/reboot, the RAC is disabled via the reboot notifier
+	 * return early here.
+	 */
+	if (test_bit(RAC_SUSPENDED, &b15_rac_flags))
+		return 0;
+
+	spin_lock(&rac_lock);
+
+	/* Indicate that we are starting a hotplug procedure */
+	__clear_bit(RAC_ENABLED, &b15_rac_flags);
+
+	/* Disable the readahead cache and save its value to a global */
+	rac_config0_reg = b15_rac_disable_and_flush();
+
+	spin_unlock(&rac_lock);
+
+	return 0;
+}
+
+/* Running on a non-dying CPU */
+static int b15_rac_dead_cpu(unsigned int cpu)
+{
+	/* During kexec/reboot, the RAC is disabled via the reboot notifier
+	 * return early here.
+	 */
+	if (test_bit(RAC_SUSPENDED, &b15_rac_flags))
+		return 0;
+
+	spin_lock(&rac_lock);
+
+	/* And enable it */
+	__b15_rac_enable(rac_config0_reg);
+	__set_bit(RAC_ENABLED, &b15_rac_flags);
+
+	spin_unlock(&rac_lock);
+
+	return 0;
+}
+
+static int b15_rac_suspend(void)
+{
+	/* Suspend the read-ahead cache oeprations, forcing our cache
+	 * implementation to fallback to the regular ARMv7 calls.
+	 *
+	 * We are guaranteed to be running on the boot CPU at this point and
+	 * with every other CPU quiesced, so setting RAC_SUSPENDED is not racy
+	 * here.
+	 */
+	rac_config0_reg = b15_rac_disable_and_flush();
+	set_bit(RAC_SUSPENDED, &b15_rac_flags);
+
+	return 0;
+}
+
+static void b15_rac_resume(void)
+{
+	/* Coming out of a S3 suspend/resume cycle, the read-ahead cache
+	 * register RAC_CONFIG0_REG will be restored to its default value, make
+	 * sure we re-enable it and set the enable flag, we are also guaranteed
+	 * to run on the boot CPU, so not racy again.
+	 */
+	__b15_rac_enable(rac_config0_reg);
+	clear_bit(RAC_SUSPENDED, &b15_rac_flags);
+}
+
+static struct syscore_ops b15_rac_syscore_ops = {
+	.suspend	= b15_rac_suspend,
+	.resume		= b15_rac_resume,
+};
+
+static int __init b15_rac_init(void)
+{
+	struct device_node *dn;
+	int ret = 0, cpu;
+	u32 reg, en_mask = 0;
+
+	dn = of_find_compatible_node(NULL, NULL, "brcm,brcmstb-cpu-biu-ctrl");
+	if (!dn)
+		return -ENODEV;
+
+	if (WARN(num_possible_cpus() > 4, "RAC only supports 4 CPUs\n"))
+		goto out;
+
+	b15_rac_base = of_iomap(dn, 0);
+	if (!b15_rac_base) {
+		pr_err("failed to remap BIU control base\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = register_reboot_notifier(&b15_rac_reboot_nb);
+	if (ret) {
+		pr_err("failed to register reboot notifier\n");
+		iounmap(b15_rac_base);
+		goto out;
+	}
+
+	if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
+		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CACHE_B15_RAC_DEAD,
+					"arm/cache-b15-rac:dead",
+					NULL, b15_rac_dead_cpu);
+		if (ret)
+			goto out_unmap;
+
+		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CACHE_B15_RAC_DYING,
+					"arm/cache-b15-rac:dying",
+					NULL, b15_rac_dying_cpu);
+		if (ret)
+			goto out_cpu_dead;
+	}
+
+	if (IS_ENABLED(CONFIG_PM_SLEEP))
+		register_syscore_ops(&b15_rac_syscore_ops);
+
+	spin_lock(&rac_lock);
+	reg = __raw_readl(b15_rac_base + RAC_CONFIG0_REG);
+	for_each_possible_cpu(cpu)
+		en_mask |= ((1 << RACPREFDATA_SHIFT) << (cpu * RAC_CPU_SHIFT));
+	WARN(reg & en_mask, "Read-ahead cache not previously disabled\n");
+
+	b15_rac_enable();
+	set_bit(RAC_ENABLED, &b15_rac_flags);
+	spin_unlock(&rac_lock);
+
+	pr_info("Broadcom Brahma-B15 readahead cache at: 0x%p\n",
+		b15_rac_base + RAC_CONFIG0_REG);
+
+	goto out;
+
+out_cpu_dead:
+	cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CACHE_B15_RAC_DYING);
+out_unmap:
+	unregister_reboot_notifier(&b15_rac_reboot_nb);
+	iounmap(b15_rac_base);
+out:
+	of_node_put(dn);
+	return ret;
+}
+arch_initcall(b15_rac_init);
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index de78109d002d..215df435bfb9 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -15,6 +15,7 @@
 #include <asm/assembler.h>
 #include <asm/errno.h>
 #include <asm/unwind.h>
+#include <asm/hardware/cache-b15-rac.h>
 
 #include "proc-macros.S"
 
@@ -446,3 +447,23 @@ ENDPROC(v7_dma_unmap_area)
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions v7
+
+	/* The Broadcom Brahma-B15 read-ahead cache requires some modifications
+	 * to the v7_cache_fns, we only override the ones we need
+	 */
+#ifndef CONFIG_CACHE_B15_RAC
+	globl_equ	b15_flush_kern_cache_all,	v7_flush_kern_cache_all
+#endif
+	globl_equ	b15_flush_icache_all,		v7_flush_icache_all
+	globl_equ	b15_flush_kern_cache_louis,	v7_flush_kern_cache_louis
+	globl_equ	b15_flush_user_cache_all,	v7_flush_user_cache_all
+	globl_equ	b15_flush_user_cache_range,	v7_flush_user_cache_range
+	globl_equ	b15_coherent_kern_range,	v7_coherent_kern_range
+	globl_equ	b15_coherent_user_range,	v7_coherent_user_range
+	globl_equ	b15_flush_kern_dcache_area,	v7_flush_kern_dcache_area
+
+	globl_equ	b15_dma_map_area,		v7_dma_map_area
+	globl_equ	b15_dma_unmap_area,		v7_dma_unmap_area
+	globl_equ	b15_dma_flush_range,		v7_dma_flush_range
+
+	define_cache_functions b15
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 6db5fc26d154..619f24a42d09 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -11,7 +11,7 @@
 
 #include <linux/export.h>
 #include <linux/mm.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/scatterlist.h>
 
 #include <asm/cachetype.h>
@@ -22,7 +22,7 @@
 #include "dma.h"
 
 /*
- *  dma_noop_ops is used if
+ *  dma_direct_ops is used if
  *   - MMU/MPU is off
  *   - cpu is v7m w/o cache support
  *   - device is coherent
@@ -39,7 +39,6 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
 				 unsigned long attrs)
 
 {
-	const struct dma_map_ops *ops = &dma_noop_ops;
 	void *ret;
 
 	/*
@@ -48,7 +47,7 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
 	 */
 
 	if (attrs & DMA_ATTR_NON_CONSISTENT)
-		return ops->alloc(dev, size, dma_handle, gfp, attrs);
+		return dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
 
 	ret = dma_alloc_from_global_coherent(size, dma_handle);
 
@@ -70,10 +69,8 @@ static void arm_nommu_dma_free(struct device *dev, size_t size,
 			       void *cpu_addr, dma_addr_t dma_addr,
 			       unsigned long attrs)
 {
-	const struct dma_map_ops *ops = &dma_noop_ops;
-
 	if (attrs & DMA_ATTR_NON_CONSISTENT) {
-		ops->free(dev, size, cpu_addr, dma_addr, attrs);
+		dma_direct_free(dev, size, cpu_addr, dma_addr, attrs);
 	} else {
 		int ret = dma_release_from_global_coherent(get_order(size),
 							   cpu_addr);
@@ -213,7 +210,7 @@ EXPORT_SYMBOL(arm_nommu_dma_ops);
 
 static const struct dma_map_ops *arm_nommu_get_dma_map_ops(bool coherent)
 {
-	return coherent ? &dma_noop_ops : &arm_nommu_dma_ops;
+	return coherent ? &dma_direct_ops : &arm_nommu_dma_ops;
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index fc3b44028cfb..084779c5c893 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -21,11 +21,7 @@
 #include <asm/fixmap.h>
 #include <asm/memory.h>
 #include <asm/pgtable.h>
-
-struct addr_marker {
-	unsigned long start_address;
-	const char *name;
-};
+#include <asm/ptdump.h>
 
 static struct addr_marker address_markers[] = {
 	{ MODULES_VADDR,	"Modules" },
@@ -38,12 +34,26 @@ static struct addr_marker address_markers[] = {
 	{ -1,			NULL },
 };
 
+#define pt_dump_seq_printf(m, fmt, args...) \
+({                      \
+	if (m)					\
+		seq_printf(m, fmt, ##args);	\
+})
+
+#define pt_dump_seq_puts(m, fmt)    \
+({						\
+	if (m)					\
+		seq_printf(m, fmt);	\
+})
+
 struct pg_state {
 	struct seq_file *seq;
 	const struct addr_marker *marker;
 	unsigned long start_address;
 	unsigned level;
 	u64 current_prot;
+	bool check_wx;
+	unsigned long wx_pages;
 	const char *current_domain;
 };
 
@@ -52,6 +62,8 @@ struct prot_bits {
 	u64		val;
 	const char	*set;
 	const char	*clear;
+	bool		ro_bit;
+	bool		nx_bit;
 };
 
 static const struct prot_bits pte_bits[] = {
@@ -65,11 +77,13 @@ static const struct prot_bits pte_bits[] = {
 		.val	= L_PTE_RDONLY,
 		.set	= "ro",
 		.clear	= "RW",
+		.ro_bit	= true,
 	}, {
 		.mask	= L_PTE_XN,
 		.val	= L_PTE_XN,
 		.set	= "NX",
 		.clear	= "x ",
+		.nx_bit	= true,
 	}, {
 		.mask	= L_PTE_SHARED,
 		.val	= L_PTE_SHARED,
@@ -133,11 +147,13 @@ static const struct prot_bits section_bits[] = {
 		.val	= L_PMD_SECT_RDONLY | PMD_SECT_AP2,
 		.set	= "ro",
 		.clear	= "RW",
+		.ro_bit	= true,
 #elif __LINUX_ARM_ARCH__ >= 6
 	{
 		.mask	= PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
 		.val	= PMD_SECT_APX | PMD_SECT_AP_WRITE,
 		.set	= "    ro",
+		.ro_bit	= true,
 	}, {
 		.mask	= PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
 		.val	= PMD_SECT_AP_WRITE,
@@ -156,6 +172,7 @@ static const struct prot_bits section_bits[] = {
 		.mask   = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
 		.val    = 0,
 		.set    = "    ro",
+		.ro_bit	= true,
 	}, {
 		.mask   = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
 		.val    = PMD_SECT_AP_WRITE,
@@ -174,6 +191,7 @@ static const struct prot_bits section_bits[] = {
 		.val	= PMD_SECT_XN,
 		.set	= "NX",
 		.clear	= "x ",
+		.nx_bit	= true,
 	}, {
 		.mask	= PMD_SECT_S,
 		.val	= PMD_SECT_S,
@@ -186,6 +204,8 @@ struct pg_level {
 	const struct prot_bits *bits;
 	size_t num;
 	u64 mask;
+	const struct prot_bits *ro_bit;
+	const struct prot_bits *nx_bit;
 };
 
 static struct pg_level pg_level[] = {
@@ -214,10 +234,27 @@ static void dump_prot(struct pg_state *st, const struct prot_bits *bits, size_t
 			s = bits->clear;
 
 		if (s)
-			seq_printf(st->seq, " %s", s);
+			pt_dump_seq_printf(st->seq, " %s", s);
 	}
 }
 
+static void note_prot_wx(struct pg_state *st, unsigned long addr)
+{
+	if (!st->check_wx)
+		return;
+	if ((st->current_prot & pg_level[st->level].ro_bit->mask) ==
+				pg_level[st->level].ro_bit->val)
+		return;
+	if ((st->current_prot & pg_level[st->level].nx_bit->mask) ==
+				pg_level[st->level].nx_bit->val)
+		return;
+
+	WARN_ONCE(1, "arm/mm: Found insecure W+X mapping at address %pS\n",
+			(void *)st->start_address);
+
+	st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
+}
+
 static void note_page(struct pg_state *st, unsigned long addr,
 		      unsigned int level, u64 val, const char *domain)
 {
@@ -228,7 +265,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
 		st->level = level;
 		st->current_prot = prot;
 		st->current_domain = domain;
-		seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+		pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
 	} else if (prot != st->current_prot || level != st->level ||
 		   domain != st->current_domain ||
 		   addr >= st->marker[1].start_address) {
@@ -236,7 +273,8 @@ static void note_page(struct pg_state *st, unsigned long addr,
 		unsigned long delta;
 
 		if (st->current_prot) {
-			seq_printf(st->seq, "0x%08lx-0x%08lx   ",
+			note_prot_wx(st, addr);
+			pt_dump_seq_printf(st->seq, "0x%08lx-0x%08lx   ",
 				   st->start_address, addr);
 
 			delta = (addr - st->start_address) >> 10;
@@ -244,17 +282,19 @@ static void note_page(struct pg_state *st, unsigned long addr,
 				delta >>= 10;
 				unit++;
 			}
-			seq_printf(st->seq, "%9lu%c", delta, *unit);
+			pt_dump_seq_printf(st->seq, "%9lu%c", delta, *unit);
 			if (st->current_domain)
-				seq_printf(st->seq, " %s", st->current_domain);
+				pt_dump_seq_printf(st->seq, " %s",
+							st->current_domain);
 			if (pg_level[st->level].bits)
 				dump_prot(st, pg_level[st->level].bits, pg_level[st->level].num);
-			seq_printf(st->seq, "\n");
+			pt_dump_seq_printf(st->seq, "\n");
 		}
 
 		if (addr >= st->marker[1].start_address) {
 			st->marker++;
-			seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+			pt_dump_seq_printf(st->seq, "---[ %s ]---\n",
+							st->marker->name);
 		}
 		st->start_address = addr;
 		st->current_prot = prot;
@@ -335,61 +375,82 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
 	}
 }
 
-static void walk_pgd(struct seq_file *m)
+static void walk_pgd(struct pg_state *st, struct mm_struct *mm,
+			unsigned long start)
 {
-	pgd_t *pgd = swapper_pg_dir;
-	struct pg_state st;
-	unsigned long addr;
+	pgd_t *pgd = pgd_offset(mm, 0UL);
 	unsigned i;
-
-	memset(&st, 0, sizeof(st));
-	st.seq = m;
-	st.marker = address_markers;
+	unsigned long addr;
 
 	for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
-		addr = i * PGDIR_SIZE;
+		addr = start + i * PGDIR_SIZE;
 		if (!pgd_none(*pgd)) {
-			walk_pud(&st, pgd, addr);
+			walk_pud(st, pgd, addr);
 		} else {
-			note_page(&st, addr, 1, pgd_val(*pgd), NULL);
+			note_page(st, addr, 1, pgd_val(*pgd), NULL);
 		}
 	}
-
-	note_page(&st, 0, 0, 0, NULL);
 }
 
-static int ptdump_show(struct seq_file *m, void *v)
+void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info)
 {
-	walk_pgd(m);
-	return 0;
-}
+	struct pg_state st = {
+		.seq = m,
+		.marker = info->markers,
+		.check_wx = false,
+	};
 
-static int ptdump_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ptdump_show, NULL);
+	walk_pgd(&st, info->mm, info->base_addr);
+	note_page(&st, 0, 0, 0, NULL);
 }
 
-static const struct file_operations ptdump_fops = {
-	.open		= ptdump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int ptdump_init(void)
+static void ptdump_initialize(void)
 {
-	struct dentry *pe;
 	unsigned i, j;
 
 	for (i = 0; i < ARRAY_SIZE(pg_level); i++)
 		if (pg_level[i].bits)
-			for (j = 0; j < pg_level[i].num; j++)
+			for (j = 0; j < pg_level[i].num; j++) {
 				pg_level[i].mask |= pg_level[i].bits[j].mask;
+				if (pg_level[i].bits[j].ro_bit)
+					pg_level[i].ro_bit = &pg_level[i].bits[j];
+				if (pg_level[i].bits[j].nx_bit)
+					pg_level[i].nx_bit = &pg_level[i].bits[j];
+			}
 
 	address_markers[2].start_address = VMALLOC_START;
+}
+
+static struct ptdump_info kernel_ptdump_info = {
+	.mm = &init_mm,
+	.markers = address_markers,
+	.base_addr = 0,
+};
 
-	pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
-				 &ptdump_fops);
-	return pe ? 0 : -ENOMEM;
+void ptdump_check_wx(void)
+{
+	struct pg_state st = {
+		.seq = NULL,
+		.marker = (struct addr_marker[]) {
+			{ 0, NULL},
+			{ -1, NULL},
+		},
+		.check_wx = true,
+	};
+
+	walk_pgd(&st, &init_mm, 0);
+	note_page(&st, 0, 0, 0, NULL);
+	if (st.wx_pages)
+		pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n",
+			st.wx_pages);
+	else
+		pr_info("Checked W+X mappings: passed, no W+X pages found\n");
+}
+
+static int ptdump_init(void)
+{
+	ptdump_initialize();
+	return ptdump_debugfs_register(&kernel_ptdump_info,
+					"kernel_page_tables");
 }
 __initcall(ptdump_init);
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 42f585379e19..b75eada23d0a 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -21,7 +21,6 @@
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 
-#include <asm/exception.h>
 #include <asm/pgtable.h>
 #include <asm/system_misc.h>
 #include <asm/system_info.h>
@@ -545,7 +544,7 @@ hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *)
 /*
  * Dispatch a data abort to the relevant handler.
  */
-asmlinkage void __exception
+asmlinkage void
 do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
 	const struct fsr_info *inf = fsr_info + fsr_fs(fsr);
@@ -578,7 +577,7 @@ hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *
 	ifsr_info[nr].name = name;
 }
 
-asmlinkage void __exception
+asmlinkage void
 do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
 {
 	const struct fsr_info *inf = ifsr_info + fsr_fs(ifsr);
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 10bfba85eb96..1d1edd064199 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -16,8 +16,8 @@
  * are not supported on any CPU using the idmap tables as its current
  * page tables.
  */
-pgd_t *idmap_pgd;
-long long arch_phys_to_idmap_offset;
+pgd_t *idmap_pgd __ro_after_init;
+long long arch_phys_to_idmap_offset __ro_after_init;
 
 #ifdef CONFIG_ARM_LPAE
 static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index a1f11a7ee81b..bd6f4513539a 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -36,6 +36,7 @@
 #include <asm/system_info.h>
 #include <asm/tlb.h>
 #include <asm/fixmap.h>
+#include <asm/ptdump.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -738,6 +739,7 @@ static int __mark_rodata_ro(void *unused)
 void mark_rodata_ro(void)
 {
 	stop_machine(__mark_rodata_ro, NULL, NULL);
+	debug_checkwx();
 }
 
 void set_kernel_text_rw(void)
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index e4370810f4f1..7c087961b7ce 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -31,7 +31,7 @@ struct mpu_rgn_info mpu_rgn_info;
 
 #ifdef CONFIG_CPU_CP15
 #ifdef CONFIG_CPU_HIGH_VECTOR
-static unsigned long __init setup_vectors_base(void)
+unsigned long setup_vectors_base(void)
 {
 	unsigned long reg = get_cr();
 
@@ -57,7 +57,7 @@ static inline bool security_extensions_enabled(void)
 	return 0;
 }
 
-static unsigned long __init setup_vectors_base(void)
+unsigned long setup_vectors_base(void)
 {
 	unsigned long base = 0, reg = get_cr();
 
diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c
index 976df60ac426..e2853bfff74e 100644
--- a/arch/arm/mm/pmsa-v7.c
+++ b/arch/arm/mm/pmsa-v7.c
@@ -6,6 +6,7 @@
 
 #include <linux/bitops.h>
 #include <linux/memblock.h>
+#include <linux/string.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cp15.h>
@@ -296,6 +297,7 @@ void __init adjust_lowmem_bounds_mpu(void)
 		}
 	}
 
+	memset(mem, 0, sizeof(mem));
 	num = allocate_region(mem_start, specified_mem_size, mem_max_regions, mem);
 
 	for (i = 0; i < num; i++) {
@@ -433,7 +435,7 @@ void __init mpu_setup(void)
 
 	/* Background */
 	err |= mpu_setup_region(region++, 0, 32,
-				MPU_ACR_XN | MPU_RGN_STRONGLY_ORDERED | MPU_AP_PL1RW_PL0NA,
+				MPU_ACR_XN | MPU_RGN_STRONGLY_ORDERED | MPU_AP_PL1RW_PL0RW,
 				0, false);
 
 #ifdef CONFIG_XIP_KERNEL
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 01d64c0b2563..d55d493f9a1e 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -567,7 +567,7 @@ __v7_setup_stack:
 	/*
 	 * Standard v7 proc info content
 	 */
-.macro __v7_proc name, initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0, proc_fns = v7_processor_functions
+.macro __v7_proc name, initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0, proc_fns = v7_processor_functions, cache_fns = v7_cache_fns
 	ALT_SMP(.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
 			PMD_SECT_AF | PMD_FLAGS_SMP | \mm_mmuflags)
 	ALT_UP(.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
@@ -583,7 +583,7 @@ __v7_setup_stack:
 	.long	\proc_fns
 	.long	v7wbi_tlb_fns
 	.long	v6_user_fns
-	.long	v7_cache_fns
+	.long	\cache_fns
 .endm
 
 #ifndef CONFIG_ARM_LPAE
@@ -678,7 +678,7 @@ __v7_ca15mp_proc_info:
 __v7_b15mp_proc_info:
 	.long	0x420f00f0
 	.long	0xff0ffff0
-	__v7_proc __v7_b15mp_proc_info, __v7_b15mp_setup
+	__v7_proc __v7_b15mp_proc_info, __v7_b15mp_setup, cache_fns = b15_cache_fns
 	.size	__v7_b15mp_proc_info, . - __v7_b15mp_proc_info
 
 	/*
diff --git a/arch/arm/mm/ptdump_debugfs.c b/arch/arm/mm/ptdump_debugfs.c
new file mode 100644
index 000000000000..be8d87be4b93
--- /dev/null
+++ b/arch/arm/mm/ptdump_debugfs.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include <asm/ptdump.h>
+
+static int ptdump_show(struct seq_file *m, void *v)
+{
+	struct ptdump_info *info = m->private;
+
+	ptdump_walk_pgd(m, info);
+	return 0;
+}
+
+static int ptdump_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ptdump_show, inode->i_private);
+}
+
+static const struct file_operations ptdump_fops = {
+	.open		= ptdump_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+int ptdump_debugfs_register(struct ptdump_info *info, const char *name)
+{
+	struct dentry *pe;
+
+	pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
+	return pe ? 0 : -ENOMEM;
+
+}
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index c199990e12b6..b5030e1a41d8 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -25,16 +25,58 @@
 
 #include "bpf_jit_32.h"
 
-int bpf_jit_enable __read_mostly;
+/*
+ * eBPF prog stack layout:
+ *
+ *                         high
+ * original ARM_SP =>     +-----+
+ *                        |     | callee saved registers
+ *                        +-----+ <= (BPF_FP + SCRATCH_SIZE)
+ *                        | ... | eBPF JIT scratch space
+ * eBPF fp register =>    +-----+
+ *   (BPF_FP)             | ... | eBPF prog stack
+ *                        +-----+
+ *                        |RSVD | JIT scratchpad
+ * current ARM_SP =>      +-----+ <= (BPF_FP - STACK_SIZE + SCRATCH_SIZE)
+ *                        |     |
+ *                        | ... | Function call stack
+ *                        |     |
+ *                        +-----+
+ *                          low
+ *
+ * The callee saved registers depends on whether frame pointers are enabled.
+ * With frame pointers (to be compliant with the ABI):
+ *
+ *                                high
+ * original ARM_SP =>     +------------------+ \
+ *                        |        pc        | |
+ * current ARM_FP =>      +------------------+ } callee saved registers
+ *                        |r4-r8,r10,fp,ip,lr| |
+ *                        +------------------+ /
+ *                                low
+ *
+ * Without frame pointers:
+ *
+ *                                high
+ * original ARM_SP =>     +------------------+
+ *                        | r4-r8,r10,fp,lr  | callee saved registers
+ * current ARM_FP =>      +------------------+
+ *                                low
+ *
+ * When popping registers off the stack at the end of a BPF function, we
+ * reference them via the current ARM_FP register.
+ */
+#define CALLEE_MASK	(1 << ARM_R4 | 1 << ARM_R5 | 1 << ARM_R6 | \
+			 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R10 | \
+			 1 << ARM_FP)
+#define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR)
+#define CALLEE_POP_MASK  (CALLEE_MASK | 1 << ARM_PC)
 
 #define STACK_OFFSET(k)	(k)
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)	/* TEMP Register 1 */
 #define TMP_REG_2	(MAX_BPF_JIT_REG + 1)	/* TEMP Register 2 */
 #define TCALL_CNT	(MAX_BPF_JIT_REG + 2)	/* Tail Call Count */
 
-/* Flags used for JIT optimization */
-#define SEEN_CALL	(1 << 0)
-
 #define FLAG_IMM_OVERFLOW	(1 << 0)
 
 /*
@@ -95,7 +137,6 @@ static const u8 bpf2a32[][2] = {
  * idx			:	index of current last JITed instruction.
  * prologue_bytes	:	bytes used in prologue.
  * epilogue_offset	:	offset of epilogue starting.
- * seen			:	bit mask used for JIT optimization.
  * offsets		:	array of eBPF instruction offsets in
  *				JITed code.
  * target		:	final JITed code.
@@ -110,7 +151,6 @@ struct jit_ctx {
 	unsigned int idx;
 	unsigned int prologue_bytes;
 	unsigned int epilogue_offset;
-	u32 seen;
 	u32 flags;
 	u32 *offsets;
 	u32 *target;
@@ -179,8 +219,13 @@ static void jit_fill_hole(void *area, unsigned int size)
 		*ptr++ = __opcode_to_mem_arm(ARM_INST_UDF);
 }
 
-/* Stack must be multiples of 16 Bytes */
-#define STACK_ALIGN(sz) (((sz) + 3) & ~3)
+#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
+/* EABI requires the stack to be aligned to 64-bit boundaries */
+#define STACK_ALIGNMENT	8
+#else
+/* Stack must be aligned to 32-bit boundaries */
+#define STACK_ALIGNMENT	4
+#endif
 
 /* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4,
  * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9,
@@ -194,7 +239,7 @@ static void jit_fill_hole(void *area, unsigned int size)
 	 + SCRATCH_SIZE + \
 	 + 4 /* extra for skb_copy_bits buffer */)
 
-#define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
+#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
 
 /* Get the offset of eBPF REGISTERs stored on scratch space. */
 #define STACK_VAR(off) (STACK_SIZE-off-4)
@@ -285,16 +330,19 @@ static inline void emit_mov_i(const u8 rd, u32 val, struct jit_ctx *ctx)
 		emit_mov_i_no8m(rd, val, ctx);
 }
 
-static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+static void emit_bx_r(u8 tgt_reg, struct jit_ctx *ctx)
 {
-	ctx->seen |= SEEN_CALL;
-#if __LINUX_ARM_ARCH__ < 5
-	emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
-
 	if (elf_hwcap & HWCAP_THUMB)
 		emit(ARM_BX(tgt_reg), ctx);
 	else
 		emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx);
+}
+
+static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 5
+	emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
+	emit_bx_r(tgt_reg, ctx);
 #else
 	emit(ARM_BLX_R(tgt_reg), ctx);
 #endif
@@ -315,15 +363,7 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 {
 	const u8 *tmp = bpf2a32[TMP_REG_1];
-	s32 jmp_offset;
 
-	/* checks if divisor is zero or not. If it is, then
-	 * exit directly.
-	 */
-	emit(ARM_CMP_I(rn, 0), ctx);
-	_emit(ARM_COND_EQ, ARM_MOV_I(ARM_R0, 0), ctx);
-	jmp_offset = epilogue_offset(ctx);
-	_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
 #if __LINUX_ARM_ARCH__ == 7
 	if (elf_hwcap & HWCAP_IDIVA) {
 		if (op == BPF_DIV)
@@ -354,7 +394,6 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 	}
 
 	/* Call appropriate function */
-	ctx->seen |= SEEN_CALL;
 	emit_mov_i(ARM_IP, op == BPF_DIV ?
 		   (u32)jit_udiv32 : (u32)jit_mod32, ctx);
 	emit_blx_r(ARM_IP, ctx);
@@ -620,8 +659,6 @@ static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk,
 	/* Do LSH operation */
 	emit(ARM_SUB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_RSB_I(tmp2[0], rt, 32), ctx);
-	/* As we are using ARM_LR */
-	ctx->seen |= SEEN_CALL;
 	emit(ARM_MOV_SR(ARM_LR, rm, SRTYPE_ASL, rt), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd, SRTYPE_ASL, ARM_IP), ctx);
 	emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx);
@@ -656,8 +693,6 @@ static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk,
 	/* Do the ARSH operation */
 	emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
-	/* As we are using ARM_LR */
-	ctx->seen |= SEEN_CALL;
 	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
 	_emit(ARM_COND_MI, ARM_B(0), ctx);
@@ -692,8 +727,6 @@ static inline void emit_a32_lsr_r64(const u8 dst[], const u8 src[], bool dstk,
 	/* Do LSH operation */
 	emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
-	/* As we are using ARM_LR */
-	ctx->seen |= SEEN_CALL;
 	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx);
@@ -828,8 +861,6 @@ static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk,
 	/* Do Multiplication */
 	emit(ARM_MUL(ARM_IP, rd, rn), ctx);
 	emit(ARM_MUL(ARM_LR, rm, rt), ctx);
-	/* As we are using ARM_LR */
-	ctx->seen |= SEEN_CALL;
 	emit(ARM_ADD_R(ARM_LR, ARM_IP, ARM_LR), ctx);
 
 	emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx);
@@ -872,33 +903,53 @@ static inline void emit_str_r(const u8 dst, const u8 src, bool dstk,
 }
 
 /* dst = *(size*)(src + off) */
-static inline void emit_ldx_r(const u8 dst, const u8 src, bool dstk,
-			      const s32 off, struct jit_ctx *ctx, const u8 sz){
+static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk,
+			      s32 off, struct jit_ctx *ctx, const u8 sz){
 	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rd = dstk ? tmp[1] : dst;
+	const u8 *rd = dstk ? tmp : dst;
 	u8 rm = src;
+	s32 off_max;
 
-	if (off) {
+	if (sz == BPF_H)
+		off_max = 0xff;
+	else
+		off_max = 0xfff;
+
+	if (off < 0 || off > off_max) {
 		emit_a32_mov_i(tmp[0], off, false, ctx);
 		emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
 		rm = tmp[0];
+		off = 0;
+	} else if (rd[1] == rm) {
+		emit(ARM_MOV_R(tmp[0], rm), ctx);
+		rm = tmp[0];
 	}
 	switch (sz) {
-	case BPF_W:
-		/* Load a Word */
-		emit(ARM_LDR_I(rd, rm, 0), ctx);
+	case BPF_B:
+		/* Load a Byte */
+		emit(ARM_LDRB_I(rd[1], rm, off), ctx);
+		emit_a32_mov_i(dst[0], 0, dstk, ctx);
 		break;
 	case BPF_H:
 		/* Load a HalfWord */
-		emit(ARM_LDRH_I(rd, rm, 0), ctx);
+		emit(ARM_LDRH_I(rd[1], rm, off), ctx);
+		emit_a32_mov_i(dst[0], 0, dstk, ctx);
 		break;
-	case BPF_B:
-		/* Load a Byte */
-		emit(ARM_LDRB_I(rd, rm, 0), ctx);
+	case BPF_W:
+		/* Load a Word */
+		emit(ARM_LDR_I(rd[1], rm, off), ctx);
+		emit_a32_mov_i(dst[0], 0, dstk, ctx);
+		break;
+	case BPF_DW:
+		/* Load a Double Word */
+		emit(ARM_LDR_I(rd[1], rm, off), ctx);
+		emit(ARM_LDR_I(rd[0], rm, off + 4), ctx);
 		break;
 	}
 	if (dstk)
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+		emit(ARM_STR_I(rd[1], ARM_SP, STACK_VAR(dst[1])), ctx);
+	if (dstk && sz == BPF_DW)
+		emit(ARM_STR_I(rd[0], ARM_SP, STACK_VAR(dst[0])), ctx);
 }
 
 /* Arithmatic Operation */
@@ -906,7 +957,6 @@ static inline void emit_ar_r(const u8 rd, const u8 rt, const u8 rm,
 			     const u8 rn, struct jit_ctx *ctx, u8 op) {
 	switch (op) {
 	case BPF_JSET:
-		ctx->seen |= SEEN_CALL;
 		emit(ARM_AND_R(ARM_IP, rt, rn), ctx);
 		emit(ARM_AND_R(ARM_LR, rd, rm), ctx);
 		emit(ARM_ORRS_R(ARM_IP, ARM_LR, ARM_IP), ctx);
@@ -945,7 +995,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	const u8 *tcc = bpf2a32[TCALL_CNT];
 	const int idx0 = ctx->idx;
 #define cur_offset (ctx->idx - idx0)
-#define jmp_offset (out_offset - (cur_offset))
+#define jmp_offset (out_offset - (cur_offset) - 2)
 	u32 off, lo, hi;
 
 	/* if (index >= array->map.max_entries)
@@ -956,7 +1006,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	emit_a32_mov_i(tmp[1], off, false, ctx);
 	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
 	emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx);
-	/* index (64 bit) */
+	/* index is 32-bit for arrays */
 	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
 	/* index >= array->map.max_entries */
 	emit(ARM_CMP_R(tmp2[1], tmp[1]), ctx);
@@ -997,7 +1047,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	emit_a32_mov_i(tmp2[1], off, false, ctx);
 	emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx);
 	emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx);
-	emit(ARM_BX(tmp[1]), ctx);
+	emit_bx_r(tmp[1], ctx);
 
 	/* out: */
 	if (out_offset == -1)
@@ -1070,54 +1120,22 @@ static void build_prologue(struct jit_ctx *ctx)
 	const u8 r2 = bpf2a32[BPF_REG_1][1];
 	const u8 r3 = bpf2a32[BPF_REG_1][0];
 	const u8 r4 = bpf2a32[BPF_REG_6][1];
-	const u8 r5 = bpf2a32[BPF_REG_6][0];
-	const u8 r6 = bpf2a32[TMP_REG_1][1];
-	const u8 r7 = bpf2a32[TMP_REG_1][0];
-	const u8 r8 = bpf2a32[TMP_REG_2][1];
-	const u8 r10 = bpf2a32[TMP_REG_2][0];
 	const u8 fplo = bpf2a32[BPF_REG_FP][1];
 	const u8 fphi = bpf2a32[BPF_REG_FP][0];
-	const u8 sp = ARM_SP;
 	const u8 *tcc = bpf2a32[TCALL_CNT];
 
-	u16 reg_set = 0;
-
-	/*
-	 * eBPF prog stack layout
-	 *
-	 *                         high
-	 * original ARM_SP =>     +-----+ eBPF prologue
-	 *                        |FP/LR|
-	 * current ARM_FP =>      +-----+
-	 *                        | ... | callee saved registers
-	 * eBPF fp register =>    +-----+ <= (BPF_FP)
-	 *                        | ... | eBPF JIT scratch space
-	 *                        |     | eBPF prog stack
-	 *                        +-----+
-	 *			  |RSVD | JIT scratchpad
-	 * current A64_SP =>      +-----+ <= (BPF_FP - STACK_SIZE)
-	 *                        |     |
-	 *                        | ... | Function call stack
-	 *                        |     |
-	 *                        +-----+
-	 *                          low
-	 */
-
 	/* Save callee saved registers. */
-	reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10);
 #ifdef CONFIG_FRAME_POINTER
-	reg_set |= (1<<ARM_FP) | (1<<ARM_IP) | (1<<ARM_LR) | (1<<ARM_PC);
-	emit(ARM_MOV_R(ARM_IP, sp), ctx);
+	u16 reg_set = CALLEE_PUSH_MASK | 1 << ARM_IP | 1 << ARM_PC;
+	emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx);
 	emit(ARM_PUSH(reg_set), ctx);
 	emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx);
 #else
-	/* Check if call instruction exists in BPF body */
-	if (ctx->seen & SEEN_CALL)
-		reg_set |= (1<<ARM_LR);
-	emit(ARM_PUSH(reg_set), ctx);
+	emit(ARM_PUSH(CALLEE_PUSH_MASK), ctx);
+	emit(ARM_MOV_R(ARM_FP, ARM_SP), ctx);
 #endif
 	/* Save frame pointer for later */
-	emit(ARM_SUB_I(ARM_IP, sp, SCRATCH_SIZE), ctx);
+	emit(ARM_SUB_I(ARM_IP, ARM_SP, SCRATCH_SIZE), ctx);
 
 	ctx->stack_size = imm8m(STACK_SIZE);
 
@@ -1140,33 +1158,19 @@ static void build_prologue(struct jit_ctx *ctx)
 	/* end of prologue */
 }
 
+/* restore callee saved registers. */
 static void build_epilogue(struct jit_ctx *ctx)
 {
-	const u8 r4 = bpf2a32[BPF_REG_6][1];
-	const u8 r5 = bpf2a32[BPF_REG_6][0];
-	const u8 r6 = bpf2a32[TMP_REG_1][1];
-	const u8 r7 = bpf2a32[TMP_REG_1][0];
-	const u8 r8 = bpf2a32[TMP_REG_2][1];
-	const u8 r10 = bpf2a32[TMP_REG_2][0];
-	u16 reg_set = 0;
-
-	/* unwind function call stack */
-	emit(ARM_ADD_I(ARM_SP, ARM_SP, ctx->stack_size), ctx);
-
-	/* restore callee saved registers. */
-	reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10);
 #ifdef CONFIG_FRAME_POINTER
-	/* the first instruction of the prologue was: mov ip, sp */
-	reg_set |= (1<<ARM_FP) | (1<<ARM_SP) | (1<<ARM_PC);
+	/* When using frame pointers, some additional registers need to
+	 * be loaded. */
+	u16 reg_set = CALLEE_POP_MASK | 1 << ARM_SP;
+	emit(ARM_SUB_I(ARM_SP, ARM_FP, hweight16(reg_set) * 4), ctx);
 	emit(ARM_LDM(ARM_SP, reg_set), ctx);
 #else
-	if (ctx->seen & SEEN_CALL)
-		reg_set |= (1<<ARM_PC);
 	/* Restore callee saved registers. */
-	emit(ARM_POP(reg_set), ctx);
-	/* Return back to the callee function */
-	if (!(ctx->seen & SEEN_CALL))
-		emit(ARM_BX(ARM_LR), ctx);
+	emit(ARM_MOV_R(ARM_SP, ARM_FP), ctx);
+	emit(ARM_POP(CALLEE_POP_MASK), ctx);
 #endif
 }
 
@@ -1394,8 +1398,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			emit_rev32(rt, rt, ctx);
 			goto emit_bswap_uxt;
 		case 64:
-			/* Because of the usage of ARM_LR */
-			ctx->seen |= SEEN_CALL;
 			emit_rev32(ARM_LR, rt, ctx);
 			emit_rev32(rt, rd, ctx);
 			emit(ARM_MOV_R(rd, ARM_LR), ctx);
@@ -1448,22 +1450,7 @@ exit:
 		rn = sstk ? tmp2[1] : src_lo;
 		if (sstk)
 			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
-		switch (BPF_SIZE(code)) {
-		case BPF_W:
-			/* Load a Word */
-		case BPF_H:
-			/* Load a Half-Word */
-		case BPF_B:
-			/* Load a Byte */
-			emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_SIZE(code));
-			emit_a32_mov_i(dst_hi, 0, dstk, ctx);
-			break;
-		case BPF_DW:
-			/* Load a double word */
-			emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_W);
-			emit_ldx_r(dst_hi, rn, dstk, off+4, ctx, BPF_W);
-			break;
-		}
+		emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code));
 		break;
 	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
 	case BPF_LD | BPF_ABS | BPF_W:
@@ -1824,7 +1811,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* If BPF JIT was not enabled then we must fall back to
 	 * the interpreter.
 	 */
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	/* If constant blinding was enabled and we failed during blinding
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index 8d4a64cc644c..b600e38364eb 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -1,8 +1,6 @@
-# arch/arm/plat-samsung/Kconfig
+# SPDX-License-Identifier: GPL-2.0
 #
 # Copyright 2009 Simtec Electronics
-#
-# Licensed under GPLv2
 
 config PLAT_SAMSUNG
 	bool
diff --git a/arch/arm/plat-samsung/Makefile b/arch/arm/plat-samsung/Makefile
index be172efec15c..3db9d2c38258 100644
--- a/arch/arm/plat-samsung/Makefile
+++ b/arch/arm/plat-samsung/Makefile
@@ -1,8 +1,6 @@
-# arch/arm/plat-samsung/Makefile
+# SPDX-License-Identifier: GPL-2.0
 #
 # Copyright 2009 Simtec Electronics
-#
-# Licensed under GPLv2
 
 ccflags-$(CONFIG_ARCH_S3C64XX) := -I$(srctree)/arch/arm/mach-s3c64xx/include
 ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include
diff --git a/arch/arm/plat-samsung/adc.c b/arch/arm/plat-samsung/adc.c
index e9de9e92ce01..42bac8d5ab5d 100644
--- a/arch/arm/plat-samsung/adc.c
+++ b/arch/arm/plat-samsung/adc.c
@@ -1,15 +1,10 @@
-/* arch/arm/plat-samsung/adc.c
- *
- * Copyright (c) 2008 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>, <ben-linux@fluff.org>
- *
- * Samsung ADC device core
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License.
-*/
+// SPDX-License-Identifier: GPL-1.0+
+//
+// Copyright (c) 2008 Simtec Electronics
+//	http://armlinux.simtec.co.uk/
+//	Ben Dooks <ben@simtec.co.uk>, <ben-linux@fluff.org>
+//
+// Samsung ADC device core
 
 #include <linux/module.h>
 #include <linux/kernel.h>
diff --git a/arch/arm/plat-samsung/cpu.c b/arch/arm/plat-samsung/cpu.c
index a107b3a0b095..e1ba88ba31d8 100644
--- a/arch/arm/plat-samsung/cpu.c
+++ b/arch/arm/plat-samsung/cpu.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/plat-samsung/cpu.c
- *
- * Copyright (c) 2009-2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * Samsung CPU Support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2009-2011 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
+//
+// Samsung CPU Support
 
 #include <linux/module.h>
 #include <linux/kernel.h>
diff --git a/arch/arm/plat-samsung/dev-uart.c b/arch/arm/plat-samsung/dev-uart.c
index 5928105490fa..7476a5dbae77 100644
--- a/arch/arm/plat-samsung/dev-uart.c
+++ b/arch/arm/plat-samsung/dev-uart.c
@@ -1,16 +1,11 @@
-/* linux/arch/arm/plat-samsung/dev-uart.c
- *	originally from arch/arm/plat-s3c24xx/devs.c
- *x
- * Copyright (c) 2004 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Base S3C24XX platform device definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+//	originally from arch/arm/plat-s3c24xx/devs.c
+//
+// Copyright (c) 2004 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// Base S3C24XX platform device definitions
 
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 5668e4eb03df..1d1fa068d228 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -1,14 +1,9 @@
-/* linux/arch/arm/plat-samsung/devs.c
- *
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * Base SAMSUNG platform device definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2011 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com
+//
+// Base SAMSUNG platform device definitions
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/arm/plat-samsung/gpio-samsung.c b/arch/arm/plat-samsung/gpio-samsung.c
index 7861488f7ca0..f66c820cd82b 100644
--- a/arch/arm/plat-samsung/gpio-samsung.c
+++ b/arch/arm/plat-samsung/gpio-samsung.c
@@ -1,18 +1,14 @@
-/*
- * Copyright (c) 2009-2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *      Ben Dooks <ben@simtec.co.uk>
- *      http://armlinux.simtec.co.uk/
- *
- * SAMSUNG - GPIOlib support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2009-2011 Samsung Electronics Co., Ltd.
+//		http://www.samsung.com/
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//      Ben Dooks <ben@simtec.co.uk>
+//      http://armlinux.simtec.co.uk/
+//
+// SAMSUNG - GPIOlib support
 
 #include <linux/kernel.h>
 #include <linux/irq.h>
diff --git a/arch/arm/plat-samsung/include/plat/adc-core.h b/arch/arm/plat-samsung/include/plat/adc-core.h
index a927bee55359..039f6862b6a7 100644
--- a/arch/arm/plat-samsung/include/plat/adc-core.h
+++ b/arch/arm/plat-samsung/include/plat/adc-core.h
@@ -1,14 +1,10 @@
-/* linux/arch/arm/plat-samsung/include/plat/adc-core.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2010 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com/
  *
  * Samsung ADC Controller core functions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_PLAT_ADC_CORE_H
 #define __ASM_PLAT_ADC_CORE_H __FILE__
diff --git a/arch/arm/plat-samsung/include/plat/adc.h b/arch/arm/plat-samsung/include/plat/adc.h
index 2fc89315553f..74d1a46408c1 100644
--- a/arch/arm/plat-samsung/include/plat/adc.h
+++ b/arch/arm/plat-samsung/include/plat/adc.h
@@ -1,15 +1,11 @@
-/* arch/arm/plat-samsung/include/plat/adc.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2008 Simtec Electronics
  *	http://armlinux.simtec.co.uk/	
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C ADC driver information
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_PLAT_ADC_H
 #define __ASM_PLAT_ADC_H __FILE__
diff --git a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h b/arch/arm/plat-samsung/include/plat/cpu-freq-core.h
index 37cf20e04aff..2c7cf2665634 100644
--- a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h
+++ b/arch/arm/plat-samsung/include/plat/cpu-freq-core.h
@@ -1,15 +1,11 @@
-/* arch/arm/plat-samsung/include/plat/cpu-freq-core.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2006-2009 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C CPU frequency scaling support - core support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <plat/cpu-freq.h>
 
diff --git a/arch/arm/plat-samsung/include/plat/cpu-freq.h b/arch/arm/plat-samsung/include/plat/cpu-freq.h
index 85517ab962ae..558892bcf9b6 100644
--- a/arch/arm/plat-samsung/include/plat/cpu-freq.h
+++ b/arch/arm/plat-samsung/include/plat/cpu-freq.h
@@ -1,15 +1,11 @@
-/* arch/arm/plat-samsung/include/plat/cpu-freq.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2006-2007 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C CPU frequency scaling support - driver and board
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <linux/cpufreq.h>
 
diff --git a/arch/arm/plat-samsung/include/plat/cpu.h b/arch/arm/plat-samsung/include/plat/cpu.h
index b7b702a72cac..fadcddbea064 100644
--- a/arch/arm/plat-samsung/include/plat/cpu.h
+++ b/arch/arm/plat-samsung/include/plat/cpu.h
@@ -1,5 +1,5 @@
-/* linux/arch/arm/plat-samsung/include/plat/cpu.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com/
  *
@@ -7,11 +7,7 @@
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * Header file for Samsung CPU support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /* todo - fix when rmk changes iodescs to use `void __iomem *` */
 
diff --git a/arch/arm/plat-samsung/include/plat/devs.h b/arch/arm/plat-samsung/include/plat/devs.h
index e23fed311e5f..02b0c5750572 100644
--- a/arch/arm/plat-samsung/include/plat/devs.h
+++ b/arch/arm/plat-samsung/include/plat/devs.h
@@ -1,5 +1,5 @@
-/* arch/arm/plat-samsung/include/plat/devs.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
@@ -7,11 +7,7 @@
  * Ben Dooks <ben@simtec.co.uk>
  *
  * Header file for s3c2410 standard platform devices
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __PLAT_DEVS_H
 #define __PLAT_DEVS_H __FILE__
diff --git a/arch/arm/plat-samsung/include/plat/fb-s3c2410.h b/arch/arm/plat-samsung/include/plat/fb-s3c2410.h
index 1f2972a74e9f..614240d768b4 100644
--- a/arch/arm/plat-samsung/include/plat/fb-s3c2410.h
+++ b/arch/arm/plat-samsung/include/plat/fb-s3c2410.h
@@ -1,12 +1,8 @@
-/* arch/arm/plat-samsung/include/plat/fb-s3c2410.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2004 Arnaud Patard <arnaud.patard@rtp-net.org>
  *
  * Inspired by pxafb.h
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
 */
 
 #ifndef __ASM_PLAT_FB_S3C2410_H
diff --git a/arch/arm/plat-samsung/include/plat/fb.h b/arch/arm/plat-samsung/include/plat/fb.h
index b89f8f208515..615d381ae32e 100644
--- a/arch/arm/plat-samsung/include/plat/fb.h
+++ b/arch/arm/plat-samsung/include/plat/fb.h
@@ -1,16 +1,12 @@
-/* arch/arm/plat-samsung/include/plat/fb.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C - FB platform data definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __PLAT_S3C_FB_H
 #define __PLAT_S3C_FB_H __FILE__
diff --git a/arch/arm/plat-samsung/include/plat/gpio-cfg-helpers.h b/arch/arm/plat-samsung/include/plat/gpio-cfg-helpers.h
index a181d7ce81cf..db0c56f5ca15 100644
--- a/arch/arm/plat-samsung/include/plat/gpio-cfg-helpers.h
+++ b/arch/arm/plat-samsung/include/plat/gpio-cfg-helpers.h
@@ -1,16 +1,12 @@
-/* linux/arch/arm/plat-samsung/include/plat/gpio-cfg-helper.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * Samsung Platform - GPIO pin configuration helper definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /* This is meant for core cpu support, machine or other driver files
  * should not be including this header.
diff --git a/arch/arm/plat-samsung/include/plat/gpio-cfg.h b/arch/arm/plat-samsung/include/plat/gpio-cfg.h
index e55d1f597db8..469c220e092b 100644
--- a/arch/arm/plat-samsung/include/plat/gpio-cfg.h
+++ b/arch/arm/plat-samsung/include/plat/gpio-cfg.h
@@ -1,16 +1,12 @@
-/* linux/arch/arm/plat-s3c/include/plat/gpio-cfg.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C Platform - GPIO pin configuration
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /* This file contains the necessary definitions to get the basic gpio
  * pin configuration done such as setting a pin to input or output or
diff --git a/arch/arm/plat-samsung/include/plat/gpio-core.h b/arch/arm/plat-samsung/include/plat/gpio-core.h
index 6ce11bfdc37e..51e721f5e491 100644
--- a/arch/arm/plat-samsung/include/plat/gpio-core.h
+++ b/arch/arm/plat-samsung/include/plat/gpio-core.h
@@ -1,15 +1,11 @@
-/* linux/arch/arm/plat-s3c/include/plat/gpio-core.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2008 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C Platform - GPIO core
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __PLAT_SAMSUNG_GPIO_CORE_H
 #define __PLAT_SAMSUNG_GPIO_CORE_H
diff --git a/arch/arm/plat-samsung/include/plat/iic-core.h b/arch/arm/plat-samsung/include/plat/iic-core.h
index f182669b8e8e..c5cfd5af3874 100644
--- a/arch/arm/plat-samsung/include/plat/iic-core.h
+++ b/arch/arm/plat-samsung/include/plat/iic-core.h
@@ -1,15 +1,11 @@
-/* arch/arm/mach-s3c2410/include/mach/iic-core.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C - I2C Controller core functions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_ARCH_IIC_CORE_H
 #define __ASM_ARCH_IIC_CORE_H __FILE__
diff --git a/arch/arm/plat-samsung/include/plat/keypad.h b/arch/arm/plat-samsung/include/plat/keypad.h
index c81ace332a1e..9754b9a29945 100644
--- a/arch/arm/plat-samsung/include/plat/keypad.h
+++ b/arch/arm/plat-samsung/include/plat/keypad.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Samsung Platform - Keypad platform data definitions
  *
  * Copyright (C) 2010 Samsung Electronics Co.Ltd
  * Author: Joonyoung Shim <jy0922.shim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #ifndef __PLAT_SAMSUNG_KEYPAD_H
diff --git a/arch/arm/plat-samsung/include/plat/map-base.h b/arch/arm/plat-samsung/include/plat/map-base.h
index 3ffac4d2e4f0..34b39ded0e2e 100644
--- a/arch/arm/plat-samsung/include/plat/map-base.h
+++ b/arch/arm/plat-samsung/include/plat/map-base.h
@@ -1,15 +1,11 @@
-/* linux/include/asm-arm/plat-s3c/map.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2003, 2007 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C - Memory map definitions (virtual addresses)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_PLAT_MAP_H
 #define __ASM_PLAT_MAP_H __FILE__
diff --git a/arch/arm/plat-samsung/include/plat/map-s3c.h b/arch/arm/plat-samsung/include/plat/map-s3c.h
index 33104911862e..4244acbf4b65 100644
--- a/arch/arm/plat-samsung/include/plat/map-s3c.h
+++ b/arch/arm/plat-samsung/include/plat/map-s3c.h
@@ -1,14 +1,10 @@
-/* linux/arch/arm/plat-samsung/include/plat/map-s3c.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2008 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C24XX - Memory map definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_PLAT_MAP_S3C_H
 #define __ASM_PLAT_MAP_S3C_H __FILE__
diff --git a/arch/arm/plat-samsung/include/plat/map-s5p.h b/arch/arm/plat-samsung/include/plat/map-s5p.h
index 0fe2828f9354..f5769e93544a 100644
--- a/arch/arm/plat-samsung/include/plat/map-s5p.h
+++ b/arch/arm/plat-samsung/include/plat/map-s5p.h
@@ -1,14 +1,10 @@
-/* linux/arch/arm/plat-samsung/include/plat/map-s5p.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2010 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com/
  *
  * S5P - Memory map definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_PLAT_MAP_S5P_H
 #define __ASM_PLAT_MAP_S5P_H __FILE__
diff --git a/arch/arm/plat-samsung/include/plat/pm-common.h b/arch/arm/plat-samsung/include/plat/pm-common.h
index 8705f9e0e288..1268bae04234 100644
--- a/arch/arm/plat-samsung/include/plat/pm-common.h
+++ b/arch/arm/plat-samsung/include/plat/pm-common.h
@@ -1,14 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *	Tomasz Figa <t.figa@samsung.com>
  * Copyright (c) 2004 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Written by Ben Dooks, <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __PLAT_SAMSUNG_PM_COMMON_H
 #define __PLAT_SAMSUNG_PM_COMMON_H __FILE__
diff --git a/arch/arm/plat-samsung/include/plat/pm.h b/arch/arm/plat-samsung/include/plat/pm.h
index 9dd562ab0841..2746137f9794 100644
--- a/arch/arm/plat-samsung/include/plat/pm.h
+++ b/arch/arm/plat-samsung/include/plat/pm.h
@@ -1,13 +1,9 @@
-/* arch/arm/plat-samsung/include/plat/pm.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2004 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Written by Ben Dooks, <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /* s3c_pm_init
  *
diff --git a/arch/arm/plat-samsung/include/plat/pwm-core.h b/arch/arm/plat-samsung/include/plat/pwm-core.h
index 5bff1facb672..05e3448642a1 100644
--- a/arch/arm/plat-samsung/include/plat/pwm-core.h
+++ b/arch/arm/plat-samsung/include/plat/pwm-core.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2013 Tomasz Figa <tomasz.figa@gmail.com>
  *
  * Samsung PWM controller platform data helpers.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __ASM_ARCH_PWM_CORE_H
diff --git a/arch/arm/plat-samsung/include/plat/regs-adc.h b/arch/arm/plat-samsung/include/plat/regs-adc.h
index 70612100120f..58953c7381dd 100644
--- a/arch/arm/plat-samsung/include/plat/regs-adc.h
+++ b/arch/arm/plat-samsung/include/plat/regs-adc.h
@@ -1,13 +1,9 @@
-/* arch/arm/mach-s3c2410/include/mach/regs-adc.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2004 Shannon Holland <holland@loser.net>
  *
- * This program is free software; yosu can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * S3C2410 ADC registers
-*/
+ */
 
 #ifndef __ASM_ARCH_REGS_ADC_H
 #define __ASM_ARCH_REGS_ADC_H "regs-adc.h"
diff --git a/arch/arm/plat-samsung/include/plat/regs-irqtype.h b/arch/arm/plat-samsung/include/plat/regs-irqtype.h
index c63cd3fc5ad3..ec5c4c5fdd8f 100644
--- a/arch/arm/plat-samsung/include/plat/regs-irqtype.h
+++ b/arch/arm/plat-samsung/include/plat/regs-irqtype.h
@@ -1,14 +1,10 @@
-/* arch/arm/plat-s3c/include/plat/regs-irqtype.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2008 Simtec Electronics
  *      Ben Dooks <ben@simtec.co.uk>
  *      http://armlinux.simtec.co.uk/
  *
  * S3C - IRQ detection types.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /* values for S3C2410_EXTINT0/1/2 and other cpus in the series, including
diff --git a/arch/arm/plat-samsung/include/plat/regs-spi.h b/arch/arm/plat-samsung/include/plat/regs-spi.h
index 552fe7cfe281..607844311566 100644
--- a/arch/arm/plat-samsung/include/plat/regs-spi.h
+++ b/arch/arm/plat-samsung/include/plat/regs-spi.h
@@ -1,13 +1,9 @@
-/* arch/arm/plat-samsung/include/plat/regs-spi.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2004 Fetron GmbH
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * S3C2410 SPI register definition
-*/
+ */
 
 #ifndef __ASM_ARCH_REGS_SPI_H
 #define __ASM_ARCH_REGS_SPI_H
diff --git a/arch/arm/plat-samsung/include/plat/regs-udc.h b/arch/arm/plat-samsung/include/plat/regs-udc.h
index 4003d3dab4e7..d8d2eeaca088 100644
--- a/arch/arm/plat-samsung/include/plat/regs-udc.h
+++ b/arch/arm/plat-samsung/include/plat/regs-udc.h
@@ -1,12 +1,7 @@
-/* arch/arm/plat-samsung/include/plat/regs-udc.h
- *
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
  * Copyright (C) 2004 Herbert Poetzl <herbert@13thfloor.at>
- *
- * This include file is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
-*/
+ */
 
 #ifndef __ASM_ARCH_REGS_UDC_H
 #define __ASM_ARCH_REGS_UDC_H
diff --git a/arch/arm/plat-samsung/include/plat/samsung-time.h b/arch/arm/plat-samsung/include/plat/samsung-time.h
index 209464adef97..d16eefe9ae78 100644
--- a/arch/arm/plat-samsung/include/plat/samsung-time.h
+++ b/arch/arm/plat-samsung/include/plat/samsung-time.h
@@ -1,14 +1,10 @@
-/* linux/arch/arm/plat-samsung/include/plat/samsung-time.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2011 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com/
  *
  * Header file for samsung s3c and s5p time support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __ASM_PLAT_SAMSUNG_TIME_H
 #define __ASM_PLAT_SAMSUNG_TIME_H __FILE__
diff --git a/arch/arm/plat-samsung/include/plat/sdhci.h b/arch/arm/plat-samsung/include/plat/sdhci.h
index 2787553c3ae2..5731e42ea208 100644
--- a/arch/arm/plat-samsung/include/plat/sdhci.h
+++ b/arch/arm/plat-samsung/include/plat/sdhci.h
@@ -1,5 +1,5 @@
-/* linux/arch/arm/plat-samsung/include/plat/sdhci.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
@@ -9,11 +9,7 @@
  *	Ben Dooks <ben@simtec.co.uk>
  *
  * S3C Platform - SDHCI (HSMMC) platform data definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __PLAT_S3C_SDHCI_H
 #define __PLAT_S3C_SDHCI_H __FILE__
diff --git a/arch/arm/plat-samsung/include/plat/usb-phy.h b/arch/arm/plat-samsung/include/plat/usb-phy.h
index ab34dfadb7f9..6d0c788beb9d 100644
--- a/arch/arm/plat-samsung/include/plat/usb-phy.h
+++ b/arch/arm/plat-samsung/include/plat/usb-phy.h
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Copyright (C) 2011 Samsung Electronics Co.Ltd
  * Author: Joonyoung Shim <jy0922.shim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #ifndef __PLAT_SAMSUNG_USB_PHY_H
diff --git a/arch/arm/plat-samsung/include/plat/wakeup-mask.h b/arch/arm/plat-samsung/include/plat/wakeup-mask.h
index bbfa84b0505a..630909e6630b 100644
--- a/arch/arm/plat-samsung/include/plat/wakeup-mask.h
+++ b/arch/arm/plat-samsung/include/plat/wakeup-mask.h
@@ -1,14 +1,9 @@
-/* arch/arm/plat-samsung/include/plat/wakeup-mask.h
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Copyright 2010 Ben Dooks <ben-linux@fluff.org>
  *
  * Support for wakeup mask interrupts on newer SoCs
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
+ */
 
 #ifndef __PLAT_WAKEUP_MASK_H
 #define __PLAT_WAKEUP_MASK_H __file__
diff --git a/arch/arm/plat-samsung/init.c b/arch/arm/plat-samsung/init.c
index 3776f7e752f0..e9acf02ef3c3 100644
--- a/arch/arm/plat-samsung/init.c
+++ b/arch/arm/plat-samsung/init.c
@@ -1,15 +1,10 @@
-/* linux/arch/arm/plat-s3c/init.c
- *
- * Copyright (c) 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * S3C series CPU initialisation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// S3C series CPU initialisation
 
 /*
  * NOTE: Code in this file is not used on S3C64xx when booting with
diff --git a/arch/arm/plat-samsung/platformdata.c b/arch/arm/plat-samsung/platformdata.c
index 6cf52ee7eeec..cbc3b4b45c74 100644
--- a/arch/arm/plat-samsung/platformdata.c
+++ b/arch/arm/plat-samsung/platformdata.c
@@ -1,13 +1,8 @@
-/* linux/arch/arm/plat-samsung/platformdata.c
- *
- * Copyright 2010 Ben Dooks <ben-linux <at> fluff.org>
- *
- * Helper for platform data setting
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2010 Ben Dooks <ben-linux <at> fluff.org>
+//
+// Helper for platform data setting
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
diff --git a/arch/arm/plat-samsung/pm-check.c b/arch/arm/plat-samsung/pm-check.c
index d63516374f7c..cd2c02c68bc3 100644
--- a/arch/arm/plat-samsung/pm-check.c
+++ b/arch/arm/plat-samsung/pm-check.c
@@ -1,16 +1,12 @@
-/* linux/arch/arm/plat-s3c/pm-check.c
- *  originally in linux/arch/arm/plat-s3c24xx/pm.c
- *
- * Copyright (c) 2004-2008 Simtec Electronics
- *	http://armlinux.simtec.co.uk
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C Power Mangament - suspend/resume memory corruption check.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// originally in linux/arch/arm/plat-s3c24xx/pm.c
+//
+// Copyright (c) 2004-2008 Simtec Electronics
+//	http://armlinux.simtec.co.uk
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// S3C Power Mangament - suspend/resume memory corruption check.
 
 #include <linux/kernel.h>
 #include <linux/suspend.h>
diff --git a/arch/arm/plat-samsung/pm-common.c b/arch/arm/plat-samsung/pm-common.c
index 6534c3ff9fe2..59a10c6dcba1 100644
--- a/arch/arm/plat-samsung/pm-common.c
+++ b/arch/arm/plat-samsung/pm-common.c
@@ -1,17 +1,13 @@
-/*
- * Copyright (C) 2013 Samsung Electronics Co., Ltd.
- *	Tomasz Figa <t.figa@samsung.com>
- * Copyright (C) 2008 Openmoko, Inc.
- * Copyright (C) 2004-2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * Samsung common power management helper functions.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2013 Samsung Electronics Co., Ltd.
+//	Tomasz Figa <t.figa@samsung.com>
+// Copyright (C) 2008 Openmoko, Inc.
+// Copyright (C) 2004-2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// Samsung common power management helper functions.
 
 #include <linux/io.h>
 #include <linux/kernel.h>
diff --git a/arch/arm/plat-samsung/pm-debug.c b/arch/arm/plat-samsung/pm-debug.c
index 64e15da33b42..b76b1e9ba4ae 100644
--- a/arch/arm/plat-samsung/pm-debug.c
+++ b/arch/arm/plat-samsung/pm-debug.c
@@ -1,17 +1,13 @@
-/*
- * Copyright (C) 2013 Samsung Electronics Co., Ltd.
- *	Tomasz Figa <t.figa@samsung.com>
- * Copyright (C) 2008 Openmoko, Inc.
- * Copyright (C) 2004-2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * Samsung common power management (suspend to RAM) debug support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2013 Samsung Electronics Co., Ltd.
+//	Tomasz Figa <t.figa@samsung.com>
+// Copyright (C) 2008 Openmoko, Inc.
+// Copyright (C) 2004-2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// Samsung common power management (suspend to RAM) debug support
 
 #include <linux/serial_core.h>
 #include <linux/serial_s3c.h>
diff --git a/arch/arm/plat-samsung/pm-gpio.c b/arch/arm/plat-samsung/pm-gpio.c
index f9a09262f2fa..cb2e3bc79336 100644
--- a/arch/arm/plat-samsung/pm-gpio.c
+++ b/arch/arm/plat-samsung/pm-gpio.c
@@ -1,17 +1,11 @@
-
-/* linux/arch/arm/plat-s3c/pm-gpio.c
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * S3C series GPIO PM code
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// S3C series GPIO PM code
 
 #include <linux/kernel.h>
 #include <linux/device.h>
diff --git a/arch/arm/plat-samsung/pm.c b/arch/arm/plat-samsung/pm.c
index d7803b434732..d6bfd66592b0 100644
--- a/arch/arm/plat-samsung/pm.c
+++ b/arch/arm/plat-samsung/pm.c
@@ -1,16 +1,11 @@
-/* linux/arch/arm/plat-s3c/pm.c
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2004-2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *	http://armlinux.simtec.co.uk/
- *
- * S3C common power management (suspend to ram) support.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2008 Openmoko, Inc.
+// Copyright 2004-2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// S3C common power management (suspend to ram) support.
 
 #include <linux/init.h>
 #include <linux/suspend.h>
diff --git a/arch/arm/plat-samsung/wakeup-mask.c b/arch/arm/plat-samsung/wakeup-mask.c
index b9de6b543330..24f96fb80738 100644
--- a/arch/arm/plat-samsung/wakeup-mask.c
+++ b/arch/arm/plat-samsung/wakeup-mask.c
@@ -1,13 +1,8 @@
-/* arch/arm/plat-samsung/wakeup-mask.c
- *
- * Copyright 2010 Ben Dooks <ben-linux@fluff.org>
- *
- * Support for wakeup mask interrupts on newer SoCs
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2010 Ben Dooks <ben-linux@fluff.org>
+//
+// Support for wakeup mask interrupts on newer SoCs
 
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
diff --git a/arch/arm/plat-samsung/watchdog-reset.c b/arch/arm/plat-samsung/watchdog-reset.c
index 307d8ad96a78..ce42cc640a61 100644
--- a/arch/arm/plat-samsung/watchdog-reset.c
+++ b/arch/arm/plat-samsung/watchdog-reset.c
@@ -1,16 +1,11 @@
-/* arch/arm/plat-samsung/watchdog-reset.c
- *
- * Copyright (c) 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Copyright (c) 2013 Tomasz Figa <tomasz.figa@gmail.com>
- *
- * Watchdog reset support for Samsung SoCs.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// Copyright (c) 2013 Tomasz Figa <tomasz.figa@gmail.com>
+//
+// Watchdog reset support for Samsung SoCs.
 
 #include <linux/clk.h>
 #include <linux/err.h>
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index 52d1cd14fda4..e90cc8a08186 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -32,6 +32,7 @@
 #include <linux/percpu.h>
 #include <linux/bug.h>
 #include <asm/patch.h>
+#include <asm/sections.h>
 
 #include "../decode-arm.h"
 #include "../decode-thumb.h"
@@ -64,9 +65,6 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	int is;
 	const struct decode_checker **checkers;
 
-	if (in_exception_text(addr))
-		return -EINVAL;
-
 #ifdef CONFIG_THUMB2_KERNEL
 	thumb = true;
 	addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */
@@ -680,3 +678,13 @@ int __init arch_init_kprobes()
 #endif
 	return 0;
 }
+
+bool arch_within_kprobe_blacklist(unsigned long addr)
+{
+	void *a = (void *)addr;
+
+	return __in_irqentry_text(addr) ||
+	       in_entry_text(addr) ||
+	       in_idmap_text(addr) ||
+	       memory_contains(__kprobes_text_start, __kprobes_text_end, a, 1);
+}
diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types
index a9313b66f770..4eac94c1eb6f 100644
--- a/arch/arm/tools/mach-types
+++ b/arch/arm/tools/mach-types
@@ -345,6 +345,7 @@ mxlads			MACH_MXLADS		MXLADS			1851
 linkstation_mini	MACH_LINKSTATION_MINI	LINKSTATION_MINI	1858
 afeb9260		MACH_AFEB9260		AFEB9260		1859
 imx27ipcam		MACH_IMX27IPCAM		IMX27IPCAM		1871
+bk3			MACH_BK3		BK3			1880
 rd88f6183ap_ge		MACH_RD88F6183AP_GE	RD88F6183AP_GE		1894
 realview_pba8		MACH_REALVIEW_PBA8	REALVIEW_PBA8		1897
 realview_pbx		MACH_REALVIEW_PBX	REALVIEW_PBX		1901
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index a71a48e71fff..03c6a3c72f9c 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -257,7 +257,7 @@ static void vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr, struct pt_
 
 	if (exceptions == VFP_EXCEPTION_ERROR) {
 		vfp_panic("unhandled bounce", inst);
-		vfp_raise_sigfpe(0, regs);
+		vfp_raise_sigfpe(FPE_FIXME, regs);
 		return;
 	}
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a93339f5178f..b2b95f79c746 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -59,6 +59,7 @@ config ARM64
 	select COMMON_CLK
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS
+	select DMA_DIRECT_OPS
 	select EDAC_SUPPORT
 	select FRAME_POINTER
 	select GENERIC_ALLOCATOR
@@ -227,7 +228,7 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
-config ZONE_DMA
+config ZONE_DMA32
 	def_bool y
 
 config HAVE_GENERIC_GUP
@@ -522,20 +523,13 @@ config CAVIUM_ERRATUM_30115
 config QCOM_FALKOR_ERRATUM_1003
 	bool "Falkor E1003: Incorrect translation due to ASID change"
 	default y
-	select ARM64_PAN if ARM64_SW_TTBR0_PAN
 	help
 	  On Falkor v1, an incorrect ASID may be cached in the TLB when ASID
-	  and BADDR are changed together in TTBRx_EL1. The workaround for this
-	  issue is to use a reserved ASID in cpu_do_switch_mm() before
-	  switching to the new ASID. Saying Y here selects ARM64_PAN if
-	  ARM64_SW_TTBR0_PAN is selected. This is done because implementing and
-	  maintaining the E1003 workaround in the software PAN emulation code
-	  would be an unnecessary complication. The affected Falkor v1 CPU
-	  implements ARMv8.1 hardware PAN support and using hardware PAN
-	  support versus software PAN emulation is mutually exclusive at
-	  runtime.
-
-	  If unsure, say Y.
+	  and BADDR are changed together in TTBRx_EL1. Since we keep the ASID
+	  in TTBR1_EL1, this situation only occurs in the entry trampoline and
+	  then only for entries in the walk cache, since the leaf translation
+	  is unchanged. Work around the erratum by invalidating the walk cache
+	  entries for the trampoline before entering the kernel proper.
 
 config QCOM_FALKOR_ERRATUM_1009
 	bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
@@ -557,7 +551,6 @@ config QCOM_QDF2400_ERRATUM_0065
 
 	  If unsure, say Y.
 
-
 config SOCIONEXT_SYNQUACER_PREITS
 	bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
 	default y
@@ -576,6 +569,17 @@ config HISILICON_ERRATUM_161600802
 	  a 128kB offset to be applied to the target address in this commands.
 
 	  If unsure, say Y.
+
+config QCOM_FALKOR_ERRATUM_E1041
+	bool "Falkor E1041: Speculative instruction fetches might cause errant memory access"
+	default y
+	help
+	  Falkor CPU may speculatively fetch instructions from an improper
+	  memory location when MMU translation is changed from SCTLR_ELn[M]=1
+	  to SCTLR_ELn[M]=0. Prefix an ISB instruction to fix the problem.
+
+	  If unsure, say Y.
+
 endmenu
 
 
@@ -646,6 +650,35 @@ config ARM64_VA_BITS
 	default 47 if ARM64_VA_BITS_47
 	default 48 if ARM64_VA_BITS_48
 
+choice
+	prompt "Physical address space size"
+	default ARM64_PA_BITS_48
+	help
+	  Choose the maximum physical address range that the kernel will
+	  support.
+
+config ARM64_PA_BITS_48
+	bool "48-bit"
+
+config ARM64_PA_BITS_52
+	bool "52-bit (ARMv8.2)"
+	depends on ARM64_64K_PAGES
+	depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN
+	help
+	  Enable support for a 52-bit physical address space, introduced as
+	  part of the ARMv8.2-LPA extension.
+
+	  With this enabled, the kernel will also continue to work on CPUs that
+	  do not support ARMv8.2-LPA, but with some added memory overhead (and
+	  minor performance overhead).
+
+endchoice
+
+config ARM64_PA_BITS
+	int
+	default 48 if ARM64_PA_BITS_48
+	default 52 if ARM64_PA_BITS_52
+
 config CPU_BIG_ENDIAN
        bool "Build big-endian kernel"
        help
@@ -840,6 +873,35 @@ config FORCE_MAX_ZONEORDER
 	  However for 4K, we choose a higher default value, 11 as opposed to 10, giving us
 	  4M allocations matching the default size used by generic code.
 
+config UNMAP_KERNEL_AT_EL0
+	bool "Unmap kernel when running in userspace (aka \"KAISER\")" if EXPERT
+	default y
+	help
+	  Speculation attacks against some high-performance processors can
+	  be used to bypass MMU permission checks and leak kernel data to
+	  userspace. This can be defended against by unmapping the kernel
+	  when running in userspace, mapping it back in on exception entry
+	  via a trampoline page in the vector table.
+
+	  If unsure, say Y.
+
+config HARDEN_BRANCH_PREDICTOR
+	bool "Harden the branch predictor against aliasing attacks" if EXPERT
+	default y
+	help
+	  Speculation attacks against some high-performance processors rely on
+	  being able to manipulate the branch predictor for a victim context by
+	  executing aliasing branches in the attacker context.  Such attacks
+	  can be partially mitigated against by clearing internal branch
+	  predictor state and limiting the prediction logic in some situations.
+
+	  This config option will take CPU-specific actions to harden the
+	  branch predictor against aliasing attacks and may rely on specific
+	  instruction sequences or control bits being set by the system
+	  firmware.
+
+	  If unsure, say Y.
+
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
 	depends on COMPAT
@@ -1011,6 +1073,22 @@ config ARM64_PMEM
 	  operations if DC CVAP is not supported (following the behaviour of
 	  DC CVAP itself if the system does not define a point of persistence).
 
+config ARM64_RAS_EXTN
+	bool "Enable support for RAS CPU Extensions"
+	default y
+	help
+	  CPUs that support the Reliability, Availability and Serviceability
+	  (RAS) Extensions, part of ARMv8.2 are able to track faults and
+	  errors, classify them and report them to software.
+
+	  On CPUs with these extensions system software can use additional
+	  barriers to determine if faults are pending and read the
+	  classification from a new set of registers.
+
+	  Selecting this feature will allow the kernel to use these barriers
+	  and access the new registers if the system supports the extension.
+	  Platform RAS features may additionally depend on firmware support.
+
 endmenu
 
 config ARM64_SVE
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index 2401373565ff..fbedbd8f619a 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -105,6 +105,7 @@ config ARCH_MESON
 	select PINCTRL_MESON
 	select COMMON_CLK_AMLOGIC
 	select COMMON_CLK_GXBB
+	select COMMON_CLK_AXG
 	select MESON_IRQ_GPIO
 	help
 	  This enables support for the Amlogic S905 SoCs.
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index b35788c909f1..b481b4a7c011 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -83,9 +83,6 @@ endif
 
 ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
 KBUILD_LDFLAGS_MODULE	+= -T $(srctree)/arch/arm64/kernel/module.lds
-ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
-KBUILD_LDFLAGS_MODULE	+= $(objtree)/arch/arm64/kernel/ftrace-mod.o
-endif
 endif
 
 # Default value
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index d7c22d51bc50..4aa50b9b26bc 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -12,6 +12,7 @@ subdir-y += cavium
 subdir-y += exynos
 subdir-y += freescale
 subdir-y += hisilicon
+subdir-y += lg
 subdir-y += marvell
 subdir-y += mediatek
 subdir-y += nvidia
@@ -22,5 +23,4 @@ subdir-y += rockchip
 subdir-y += socionext
 subdir-y += sprd
 subdir-y += xilinx
-subdir-y += lg
 subdir-y += zte
diff --git a/arch/arm64/boot/dts/actions/Makefile b/arch/arm64/boot/dts/actions/Makefile
index cc4661256356..d8b923480f5a 100644
--- a/arch/arm64/boot/dts/actions/Makefile
+++ b/arch/arm64/boot/dts/actions/Makefile
@@ -1 +1,3 @@
+dtb-$(CONFIG_ARCH_ACTIONS) += s700-cubieboard7.dtb
+
 dtb-$(CONFIG_ARCH_ACTIONS) += s900-bubblegum-96.dtb
diff --git a/arch/arm64/boot/dts/actions/s700-cubieboard7.dts b/arch/arm64/boot/dts/actions/s700-cubieboard7.dts
new file mode 100644
index 000000000000..ef79d7905f44
--- /dev/null
+++ b/arch/arm64/boot/dts/actions/s700-cubieboard7.dts
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2017 Andreas Färber
+ */
+
+/dts-v1/;
+
+#include "s700.dtsi"
+
+/ {
+	compatible = "cubietech,cubieboard7", "actions,s700";
+	model = "CubieBoard7";
+
+	aliases {
+		serial3 = &uart3;
+	};
+
+	chosen {
+		stdout-path = "serial3:115200n8";
+	};
+
+	memory@0 {
+		device_type = "memory";
+		reg = <0x0 0x0 0x0 0x80000000>;
+	};
+
+	memory@1,e0000000 {
+		device_type = "memory";
+		reg = <0x1 0xe0000000 0x0 0x0>;
+	};
+
+	uart3_clk: uart3-clk {
+		compatible = "fixed-clock";
+		clock-frequency = <921600>;
+		#clock-cells = <0>;
+	};
+};
+
+&timer {
+	clocks = <&hosc>;
+};
+
+&uart3 {
+	status = "okay";
+	clocks = <&uart3_clk>;
+};
diff --git a/arch/arm64/boot/dts/actions/s700.dtsi b/arch/arm64/boot/dts/actions/s700.dtsi
new file mode 100644
index 000000000000..66dd5309f0a2
--- /dev/null
+++ b/arch/arm64/boot/dts/actions/s700.dtsi
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2017 Andreas Färber
+ */
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	compatible = "actions,s700";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x1>;
+			enable-method = "psci";
+		};
+
+		cpu2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x2>;
+			enable-method = "psci";
+		};
+
+		cpu3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x3>;
+			enable-method = "psci";
+		};
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		secmon@1f000000 {
+			reg = <0x0 0x1f000000 0x0 0x1000000>;
+			no-map;
+		};
+	};
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	arm-pmu {
+		compatible = "arm,cortex-a53-pmu";
+		interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+		             <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>,
+		             <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>,
+		             <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13
+			(GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14
+			(GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11
+			(GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10
+			(GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	hosc: hosc {
+		compatible = "fixed-clock";
+		clock-frequency = <24000000>;
+		#clock-cells = <0>;
+	};
+
+	soc {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		gic: interrupt-controller@e00f1000 {
+			compatible = "arm,gic-400";
+			reg = <0x0 0xe00f1000 0x0 0x1000>,
+			      <0x0 0xe00f2000 0x0 0x2000>,
+			      <0x0 0xe00f4000 0x0 0x2000>,
+			      <0x0 0xe00f6000 0x0 0x2000>;
+			interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+		};
+
+		uart0: serial@e0120000 {
+			compatible = "actions,s900-uart", "actions,owl-uart";
+			reg = <0x0 0xe0120000 0x0 0x2000>;
+			interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		uart1: serial@e0122000 {
+			compatible = "actions,s900-uart", "actions,owl-uart";
+			reg = <0x0 0xe0122000 0x0 0x2000>;
+			interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		uart2: serial@e0124000 {
+			compatible = "actions,s900-uart", "actions,owl-uart";
+			reg = <0x0 0xe0124000 0x0 0x2000>;
+			interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		uart3: serial@e0126000 {
+			compatible = "actions,s900-uart", "actions,owl-uart";
+			reg = <0x0 0xe0126000 0x0 0x2000>;
+			interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		uart4: serial@e0128000 {
+			compatible = "actions,s900-uart", "actions,owl-uart";
+			reg = <0x0 0xe0128000 0x0 0x2000>;
+			interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		uart5: serial@e012a000 {
+			compatible = "actions,s900-uart", "actions,owl-uart";
+			reg = <0x0 0xe012a000 0x0 0x2000>;
+			interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		uart6: serial@e012c000 {
+			compatible = "actions,s900-uart", "actions,owl-uart";
+			reg = <0x0 0xe012c000 0x0 0x2000>;
+			interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		sps: power-controller@e01b0100 {
+			compatible = "actions,s700-sps";
+			reg = <0x0 0xe01b0100 0x0 0x100>;
+			#power-domain-cells = <1>;
+		};
+
+		timer: timer@e024c000 {
+			compatible = "actions,s700-timer";
+			reg = <0x0 0xe024c000 0x0 0x4000>;
+			interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "timer1";
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
index 45bdbfb96126..a6975670cd1c 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
@@ -60,6 +60,26 @@
 		stdout-path = "serial0:115200n8";
 	};
 
+	leds {
+		compatible = "gpio-leds";
+
+		pwr-led {
+			label = "bananapi-m64:red:pwr";
+			gpios = <&pio 3 24 GPIO_ACTIVE_HIGH>; /* PD24 */
+			default-state = "on";
+		};
+
+		green {
+			label = "bananapi-m64:green:user";
+			gpios = <&pio 4 14 GPIO_ACTIVE_HIGH>; /* PE14 */
+		};
+
+		blue {
+			label = "bananapi-m64:blue:user";
+			gpios = <&pio 4 15 GPIO_ACTIVE_HIGH>; /* PE15 */
+		};
+	};
+
 	wifi_pwrseq: wifi_pwrseq {
 		compatible = "mmc-pwrseq-simple";
 		reset-gpios = <&r_pio 0 2 GPIO_ACTIVE_LOW>; /* PL2 */
@@ -75,6 +95,7 @@
 	pinctrl-0 = <&rgmii_pins>;
 	phy-mode = "rgmii";
 	phy-handle = <&ext_rgmii_phy>;
+	phy-supply = <&reg_dc1sw>;
 	status = "okay";
 };
 
@@ -152,6 +173,17 @@
 
 #include "axp803.dtsi"
 
+&reg_aldo1 {
+	/*
+	 * This regulator also drives the PE pingroup GPIOs,
+	 * which also controls two LEDs.
+	 */
+	regulator-always-on;
+	regulator-min-microvolt = <2800000>;
+	regulator-max-microvolt = <2800000>;
+	regulator-name = "afvcc-csi";
+};
+
 &reg_aldo2 {
 	regulator-always-on;
 	regulator-min-microvolt = <1800000>;
@@ -167,6 +199,11 @@
 };
 
 &reg_dc1sw {
+	/*
+	 * This regulator also indirectly drives the PD pingroup GPIOs,
+	 * which also controls the power LED.
+	 */
+	regulator-always-on;
 	regulator-name = "vcc-phy";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts
index 338e786155b1..8807664f363a 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts
@@ -57,6 +57,11 @@
 	chosen {
 		stdout-path = "serial0:115200n8";
 	};
+
+	wifi_pwrseq: wifi_pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		reset-gpios = <&r_pio 0 2 GPIO_ACTIVE_LOW>; /* PL2 */
+	};
 };
 
 &mmc0 {
@@ -70,6 +75,24 @@
 	status = "okay";
 };
 
+&mmc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc1_pins>;
+	vmmc-supply = <&reg_aldo2>;
+	vqmmc-supply = <&reg_dldo4>;
+	mmc-pwrseq = <&wifi_pwrseq>;
+	bus-width = <4>;
+	non-removable;
+	status = "okay";
+
+	rtl8723bs: wifi@1 {
+		reg = <1>;
+		interrupt-parent = <&r_pio>;
+		interrupts = <0 3 IRQ_TYPE_LEVEL_LOW>; /* PL3 */
+		interrupt-names = "host-wake";
+	};
+};
+
 &r_rsb {
 	status = "okay";
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
index 5f8ff4017d45..240d35731d10 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
@@ -57,13 +57,6 @@
 	chosen {
 		stdout-path = "serial0:115200n8";
 	};
-
-	reg_vcc3v3: vcc3v3 {
-		compatible = "regulator-fixed";
-		regulator-name = "vcc3v3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-	};
 };
 
 &ehci1 {
@@ -73,7 +66,7 @@
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins>;
-	vmmc-supply = <&reg_vcc3v3>;
+	vmmc-supply = <&reg_dcdc1>;
 	cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>;
 	cd-inverted;
 	status = "okay";
@@ -83,6 +76,122 @@
 	status = "okay";
 };
 
+&r_rsb {
+	status = "okay";
+
+	axp803: pmic@3a3 {
+		compatible = "x-powers,axp803";
+		reg = <0x3a3>;
+		interrupt-parent = <&r_intc>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
+
+#include "axp803.dtsi"
+
+&reg_aldo1 {
+	regulator-always-on;
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "afvcc-csi";
+};
+
+&reg_aldo2 {
+	regulator-always-on;
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-pl";
+};
+
+&reg_aldo3 {
+	regulator-always-on;
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "vcc-pll-avcc";
+};
+
+&reg_dcdc1 {
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-3v3";
+};
+
+&reg_dcdc2 {
+	regulator-always-on;
+	regulator-min-microvolt = <1040000>;
+	regulator-max-microvolt = <1300000>;
+	regulator-name = "vdd-cpux";
+};
+
+/* DCDC3 is polyphased with DCDC2 */
+
+&reg_dcdc5 {
+	regulator-always-on;
+	regulator-min-microvolt = <1500000>;
+	regulator-max-microvolt = <1500000>;
+	regulator-name = "vcc-dram";
+};
+
+&reg_dcdc6 {
+	regulator-always-on;
+	regulator-min-microvolt = <1100000>;
+	regulator-max-microvolt = <1100000>;
+	regulator-name = "vdd-sys";
+};
+
+&reg_dldo1 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-hdmi-dsi";
+};
+
+&reg_dldo2 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi";
+};
+
+&reg_dldo3 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "avdd-csi";
+};
+
+&reg_dldo4 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi-io";
+};
+
+&reg_eldo1 {
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
+	regulator-name = "cpvdd";
+};
+
+&reg_fldo1 {
+	regulator-min-microvolt = <1200000>;
+	regulator-max-microvolt = <1200000>;
+	regulator-name = "vcc-1v2-hsic";
+};
+
+/*
+ * The A64 chip cannot work without this regulator off, although
+ * it seems to be only driving the AR100 core.
+ * Maybe we don't still know well about CPUs domain.
+ */
+&reg_fldo2 {
+	regulator-always-on;
+	regulator-min-microvolt = <1100000>;
+	regulator-max-microvolt = <1100000>;
+	regulator-name = "vdd-cpus";
+};
+
+&reg_rtc_ldo {
+	regulator-name = "vcc-rtc";
+};
+
 &uart0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart0_pins_a>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
index 806442d3e846..604cdaedac38 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
@@ -77,6 +77,7 @@
 	pinctrl-0 = <&rmii_pins>;
 	phy-mode = "rmii";
 	phy-handle = <&ext_rmii_phy1>;
+	phy-supply = <&reg_dc1sw>;
 	status = "okay";
 
 };
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
index 0eb2acedf8c3..abe179de35d7 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
@@ -82,6 +82,7 @@
 	pinctrl-0 = <&rgmii_pins>;
 	phy-mode = "rgmii";
 	phy-handle = <&ext_rgmii_phy>;
+	phy-supply = <&reg_dc1sw>;
 	status = "okay";
 };
 
@@ -95,7 +96,7 @@
 &mmc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc2_pins>;
-	vmmc-supply = <&reg_vcc3v3>;
+	vmmc-supply = <&reg_dcdc1>;
 	vqmmc-supply = <&reg_vcc1v8>;
 	bus-width = <8>;
 	non-removable;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi
index a5da18a6f286..43418bd881d8 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi
@@ -45,19 +45,10 @@
 
 #include "sun50i-a64.dtsi"
 
-/ {
-	reg_vcc3v3: vcc3v3 {
-		compatible = "regulator-fixed";
-		regulator-name = "vcc3v3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-	};
-};
-
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins>;
-	vmmc-supply = <&reg_vcc3v3>;
+	vmmc-supply = <&reg_dcdc1>;
 	non-removable;
 	disable-wp;
 	bus-width = <4>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts
index 7c028af58f47..1ed9f219deaf 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts
@@ -53,6 +53,7 @@
 	compatible = "friendlyarm,nanopi-neo-plus2", "allwinner,sun50i-h5";
 
 	aliases {
+		ethernet0 = &emac;
 		serial0 = &uart0;
 	};
 
@@ -133,9 +134,25 @@
 	status = "okay";
 };
 
+&emac {
+	pinctrl-names = "default";
+	pinctrl-0 = <&emac_rgmii_pins>;
+	phy-supply = <&reg_gmac_3v3>;
+	phy-handle = <&ext_rgmii_phy>;
+	phy-mode = "rgmii";
+	status = "okay";
+};
+
+&external_mdio {
+	ext_rgmii_phy: ethernet-phy@7 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <7>;
+	};
+};
+
 &mmc0 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
+	pinctrl-0 = <&mmc0_pins_a>;
 	vmmc-supply = <&reg_vcc3v3>;
 	bus-width = <4>;
 	cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 */
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
index 6eb8092d8e57..f1447003ea3c 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
@@ -127,7 +127,7 @@
 
 &mmc0 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
+	pinctrl-0 = <&mmc0_pins_a>;
 	vmmc-supply = <&reg_vcc3v3>;
 	bus-width = <4>;
 	cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 */
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
index a0ca925175aa..9e51d3a5f4e6 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
@@ -161,7 +161,7 @@
 
 &mmc0 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
+	pinctrl-0 = <&mmc0_pins_a>;
 	vmmc-supply = <&reg_vcc3v3>;
 	bus-width = <4>;
 	cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 */
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
index b47790650144..0f25c4a6f15d 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
@@ -168,7 +168,7 @@
 
 &mmc0 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
+	pinctrl-0 = <&mmc0_pins_a>;
 	vmmc-supply = <&reg_vcc3v3>;
 	bus-width = <4>;
 	cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 */
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus2.dts
index b6b7a561df8c..af43533c7134 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus2.dts
@@ -64,17 +64,43 @@
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
+
+	wifi_pwrseq: wifi_pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		pinctrl-names = "default";
+		reset-gpios = <&pio 0 9 GPIO_ACTIVE_LOW>; /* PA9 */
+		post-power-on-delay-ms = <200>;
+	};
 };
 
 &mmc0 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
+	pinctrl-0 = <&mmc0_pins_a>;
 	vmmc-supply = <&reg_vcc3v3>;
 	bus-width = <4>;
-	cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
+&mmc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc1_pins_a>;
+	vmmc-supply = <&reg_vcc3v3>;
+	vqmmc-supply = <&reg_vcc3v3>;
+	mmc-pwrseq = <&wifi_pwrseq>;
+	bus-width = <4>;
+	non-removable;
+	status = "okay";
+
+	brcmf: wifi@1 {
+		reg = <1>;
+		compatible = "brcm,bcm4329-fmac";
+		interrupt-parent = <&r_pio>;
+		interrupts = <0 7 IRQ_TYPE_LEVEL_LOW>;	/* PL7 */
+		interrupt-names = "host-wake";
+	};
+};
+
 &mmc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc2_8bit_pins>;
@@ -90,3 +116,9 @@
 	pinctrl-0 = <&uart0_pins_a>;
 	status = "okay";
 };
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart1_pins>, <&uart1_rts_cts_pins>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi
index d9a720bff05d..e237c05cfdb4 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi
@@ -98,6 +98,10 @@
 	compatible = "allwinner,sun50i-h5-ccu";
 };
 
+&display_clocks {
+	compatible = "allwinner,sun50i-h5-de2-clk";
+};
+
 &mmc0 {
 	compatible = "allwinner,sun50i-h5-mmc",
 		     "allwinner,sun50i-a64-mmc";
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index 7c9bdc7ab50b..c89d0c307f8d 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -66,6 +66,7 @@
 				     <&cpu1>,
 				     <&cpu2>,
 				     <&cpu3>;
+		interrupt-parent = <&intc>;
 	};
 
 	psci {
@@ -248,7 +249,9 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0xffda4000 0x1000>;
-			interrupts = <0 101 4>;
+			interrupts = <0 99 4>;
+			resets = <&rst SPIM0_RESET>;
+			reg-io-width = <4>;
 			num-chipselect = <4>;
 			bus-num = <0>;
 			status = "disabled";
@@ -259,7 +262,9 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0xffda5000 0x1000>;
-			interrupts = <0 102 4>;
+			interrupts = <0 100 4>;
+			resets = <&rst SPIM1_RESET>;
+			reg-io-width = <4>;
 			num-chipselect = <4>;
 			bus-num = <0>;
 			status = "disabled";
@@ -335,8 +340,8 @@
 			interrupts = <0 93 4>;
 			phys = <&usbphy0>;
 			phy-names = "usb2-phy";
-			resets = <&rst USB0_RESET>;
-			reset-names = "dwc2";
+			resets = <&rst USB0_RESET>, <&rst USB0_OCP_RESET>;
+			reset-names = "dwc2", "dwc2-ecc";
 			status = "disabled";
 		};
 
@@ -346,8 +351,8 @@
 			interrupts = <0 94 4>;
 			phys = <&usbphy0>;
 			phy-names = "usb2-phy";
-			resets = <&rst USB1_RESET>;
-			reset-names = "dwc2";
+			resets = <&rst USB1_RESET>, <&rst USB1_OCP_RESET>;
+			reset-names = "dwc2", "dwc2-ecc";
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
index a37c46112876..000756429b77 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
@@ -97,3 +97,7 @@
 &uart0 {
 	status = "okay";
 };
+
+&usb0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
index 70eca1f8736a..447b98d30921 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
@@ -17,6 +17,19 @@
 	};
 };
 
+&ethmac {
+	status = "okay";
+	phy-mode = "rgmii";
+	pinctrl-0 = <&eth_rgmii_y_pins>;
+	pinctrl-names = "default";
+};
+
 &uart_AO {
 	status = "okay";
 };
+
+&ir {
+	status = "okay";
+	pinctrl-0 = <&remote_input_ao_pins>;
+	pinctrl-names = "default";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
index b932a784b02a..a80632641b39 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
@@ -7,6 +7,7 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/clock/axg-clkc.h>
 
 / {
 	compatible = "amlogic,meson-axg";
@@ -113,13 +114,55 @@
 		#size-cells = <2>;
 		ranges;
 
-		cbus: cbus@ffd00000 {
+		cbus: bus@ffd00000 {
 			compatible = "simple-bus";
 			reg = <0x0 0xffd00000 0x0 0x25000>;
 			#address-cells = <2>;
 			#size-cells = <2>;
 			ranges = <0x0 0x0 0x0 0xffd00000 0x0 0x25000>;
 
+			pwm_ab: pwm@1b000 {
+				compatible = "amlogic,meson-axg-ee-pwm";
+				reg = <0x0 0x1b000 0x0 0x20>;
+				#pwm-cells = <3>;
+				status = "disabled";
+			};
+
+			pwm_cd: pwm@1a000 {
+				compatible = "amlogic,meson-axg-ee-pwm";
+				reg = <0x0 0x1a000 0x0 0x20>;
+				#pwm-cells = <3>;
+				status = "disabled";
+			};
+
+			reset: reset-controller@1004 {
+				compatible = "amlogic,meson-axg-reset";
+				reg = <0x0 0x01004 0x0 0x9c>;
+				#reset-cells = <1>;
+			};
+
+			spicc0: spi@13000 {
+				compatible = "amlogic,meson-axg-spicc";
+				reg = <0x0 0x13000 0x0 0x3c>;
+				interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clkc CLKID_SPICC0>;
+				clock-names = "core";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			spicc1: spi@15000 {
+				compatible = "amlogic,meson-axg-spicc";
+				reg = <0x0 0x15000 0x0 0x3c>;
+				interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clkc CLKID_SPICC1>;
+				clock-names = "core";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
 			uart_A: serial@24000 {
 				compatible = "amlogic,meson-gx-uart", "amlogic,meson-uart";
 				reg = <0x0 0x24000 0x0 0x14>;
@@ -135,6 +178,19 @@
 			};
 		};
 
+		ethmac: ethernet@ff3f0000 {
+			compatible = "amlogic,meson-gxbb-dwmac", "snps,dwmac";
+			reg = <0x0 0xff3f0000 0x0 0x10000
+				0x0 0xff634540 0x0 0x8>;
+			interrupts = <GIC_SPI 8 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "macirq";
+			clocks = <&clkc CLKID_ETH>,
+				 <&clkc CLKID_FCLK_DIV2>,
+				 <&clkc CLKID_MPLL2>;
+			clock-names = "stmmaceth", "clkin0", "clkin1";
+			status = "disabled";
+		};
+
 		gic: interrupt-controller@ffc01000 {
 			compatible = "arm,gic-400";
 			reg = <0x0 0xffc01000 0 0x1000>,
@@ -148,6 +204,20 @@
 			#address-cells = <0>;
 		};
 
+		hiubus: bus@ff63c000 {
+			compatible = "simple-bus";
+			reg = <0x0 0xff63c000 0x0 0x1c00>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges = <0x0 0x0 0x0 0xff63c000 0x0 0x1c00>;
+
+			clkc: clock-controller@0 {
+				compatible = "amlogic,axg-clkc";
+				#clock-cells = <1>;
+				reg = <0x0 0x0 0x0 0x320>;
+			};
+		};
+
 		mailbox: mailbox@ff63dc00 {
 			compatible = "amlogic,meson-gx-mhu", "amlogic,meson-gxbb-mhu";
 			reg = <0 0xff63dc00 0 0x400>;
@@ -157,6 +227,226 @@
 			#mbox-cells = <1>;
 		};
 
+		periphs: periphs@ff634000 {
+			compatible = "simple-bus";
+			reg = <0x0 0xff634000 0x0 0x2000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges = <0x0 0x0 0x0 0xff634000 0x0 0x2000>;
+
+			pinctrl_periphs: pinctrl@480 {
+				compatible = "amlogic,meson-axg-periphs-pinctrl";
+				#address-cells = <2>;
+				#size-cells = <2>;
+				ranges;
+
+				gpio: bank@480 {
+					reg = <0x0 0x00480 0x0 0x40>,
+						<0x0 0x004e8 0x0 0x14>,
+						<0x0 0x00520 0x0 0x14>,
+						<0x0 0x00430 0x0 0x3c>;
+					reg-names = "mux", "pull", "pull-enable", "gpio";
+					gpio-controller;
+					#gpio-cells = <2>;
+					gpio-ranges = <&pinctrl_periphs 0 0 86>;
+				};
+
+				eth_rgmii_x_pins: eth-x-rgmii {
+					mux {
+						groups = "eth_mdio_x",
+						       "eth_mdc_x",
+						       "eth_rgmii_rx_clk_x",
+						       "eth_rx_dv_x",
+						       "eth_rxd0_x",
+						       "eth_rxd1_x",
+						       "eth_rxd2_rgmii",
+						       "eth_rxd3_rgmii",
+						       "eth_rgmii_tx_clk",
+						       "eth_txen_x",
+						       "eth_txd0_x",
+						       "eth_txd1_x",
+						       "eth_txd2_rgmii",
+						       "eth_txd3_rgmii";
+						function = "eth";
+					};
+				};
+
+				eth_rgmii_y_pins: eth-y-rgmii {
+					mux {
+						groups = "eth_mdio_y",
+						       "eth_mdc_y",
+						       "eth_rgmii_rx_clk_y",
+						       "eth_rx_dv_y",
+						       "eth_rxd0_y",
+						       "eth_rxd1_y",
+						       "eth_rxd2_rgmii",
+						       "eth_rxd3_rgmii",
+						       "eth_rgmii_tx_clk",
+						       "eth_txen_y",
+						       "eth_txd0_y",
+						       "eth_txd1_y",
+						       "eth_txd2_rgmii",
+						       "eth_txd3_rgmii";
+						function = "eth";
+					};
+				};
+
+				pwm_a_a_pins: pwm_a_a {
+					mux {
+						groups = "pwm_a_a";
+						function = "pwm_a";
+					};
+				};
+
+				pwm_a_x18_pins: pwm_a_x18 {
+					mux {
+						groups = "pwm_a_x18";
+						function = "pwm_a";
+					};
+				};
+
+				pwm_a_x20_pins: pwm_a_x20 {
+					mux {
+						groups = "pwm_a_x20";
+						function = "pwm_a";
+					};
+				};
+
+				pwm_a_z_pins: pwm_a_z {
+					mux {
+						groups = "pwm_a_z";
+						function = "pwm_a";
+					};
+				};
+
+				pwm_b_a_pins: pwm_b_a {
+					mux {
+						groups = "pwm_b_a";
+						function = "pwm_b";
+					};
+				};
+
+				pwm_b_x_pins: pwm_b_x {
+					mux {
+						groups = "pwm_b_x";
+						function = "pwm_b";
+					};
+				};
+
+				pwm_b_z_pins: pwm_b_z {
+					mux {
+						groups = "pwm_b_z";
+						function = "pwm_b";
+					};
+				};
+
+				pwm_c_a_pins: pwm_c_a {
+					mux {
+						groups = "pwm_c_a";
+						function = "pwm_c";
+					};
+				};
+
+				pwm_c_x10_pins: pwm_c_x10 {
+					mux {
+						groups = "pwm_c_x10";
+						function = "pwm_c";
+					};
+				};
+
+				pwm_c_x17_pins: pwm_c_x17 {
+					mux {
+						groups = "pwm_c_x17";
+						function = "pwm_c";
+					};
+				};
+
+				pwm_d_x11_pins: pwm_d_x11 {
+					mux {
+						groups = "pwm_d_x11";
+						function = "pwm_d";
+					};
+				};
+
+				pwm_d_x16_pins: pwm_d_x16 {
+					mux {
+						groups = "pwm_d_x16";
+						function = "pwm_d";
+					};
+				};
+
+				spi0_pins: spi0 {
+					mux {
+						groups = "spi0_miso",
+							"spi0_mosi",
+							"spi0_clk";
+						function = "spi0";
+					};
+				};
+
+				spi0_ss0_pins: spi0_ss0 {
+					mux {
+						groups = "spi0_ss0";
+						function = "spi0";
+					};
+				};
+
+				spi0_ss1_pins: spi0_ss1 {
+					mux {
+						groups = "spi0_ss1";
+						function = "spi0";
+					};
+				};
+
+				spi0_ss2_pins: spi0_ss2 {
+					mux {
+						groups = "spi0_ss2";
+						function = "spi0";
+					};
+				};
+
+
+				spi1_a_pins: spi1_a {
+					mux {
+						groups = "spi1_miso_a",
+							"spi1_mosi_a",
+							"spi1_clk_a";
+						function = "spi1";
+					};
+				};
+
+				spi1_ss0_a_pins: spi1_ss0_a {
+					mux {
+						groups = "spi1_ss0_a";
+						function = "spi1";
+					};
+				};
+
+				spi1_ss1_pins: spi1_ss1 {
+					mux {
+						groups = "spi1_ss1";
+						function = "spi1";
+					};
+				};
+
+				spi1_x_pins: spi1_x {
+					mux {
+						groups = "spi1_miso_x",
+							"spi1_mosi_x",
+							"spi1_clk_x";
+						function = "spi1";
+					};
+				};
+
+				spi1_ss0_x_pins: spi1_ss0_x {
+					mux {
+						groups = "spi1_ss0_x";
+						function = "spi1";
+					};
+				};
+			};
+		};
+
 		sram: sram@fffc0000 {
 			compatible = "amlogic,meson-axg-sram", "mmio-sram";
 			reg = <0x0 0xfffc0000 0x0 0x20000>;
@@ -175,18 +465,56 @@
 			};
 		};
 
-		aobus: aobus@ff800000 {
+		aobus: bus@ff800000 {
 			compatible = "simple-bus";
 			reg = <0x0 0xff800000 0x0 0x100000>;
 			#address-cells = <2>;
 			#size-cells = <2>;
 			ranges = <0x0 0x0 0x0 0xff800000 0x0 0x100000>;
 
+			pinctrl_aobus: pinctrl@14 {
+				compatible = "amlogic,meson-axg-aobus-pinctrl";
+				#address-cells = <2>;
+				#size-cells = <2>;
+				ranges;
+
+				gpio_ao: bank@14 {
+					reg = <0x0 0x00014 0x0 0x8>,
+						<0x0 0x0002c 0x0 0x4>,
+						<0x0 0x00024 0x0 0x8>;
+					reg-names = "mux", "pull", "gpio";
+					gpio-controller;
+					#gpio-cells = <2>;
+					gpio-ranges = <&pinctrl_aobus 0 0 15>;
+				};
+
+				remote_input_ao_pins: remote_input_ao {
+					mux {
+						groups = "remote_input_ao";
+						function = "remote_input_ao";
+					};
+				};
+			};
+
+			pwm_AO_ab: pwm@7000 {
+				compatible = "amlogic,meson-axg-ao-pwm";
+				reg = <0x0 0x07000 0x0 0x20>;
+				#pwm-cells = <3>;
+				status = "disabled";
+			};
+
+			pwm_AO_cd: pwm@2000 {
+				compatible = "amlogic,axg-ao-pwm";
+				reg = <0x0 0x02000  0x0 0x20>;
+				#pwm-cells = <3>;
+				status = "disabled";
+			};
+
 			uart_AO: serial@3000 {
 				compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart";
 				reg = <0x0 0x3000 0x0 0x18>;
 				interrupts = <GIC_SPI 193 IRQ_TYPE_EDGE_RISING>;
-				clocks = <&xtal>, <&xtal>, <&xtal>;
+				clocks = <&xtal>, <&clkc CLKID_CLK81>, <&xtal>;
 				clock-names = "xtal", "pclk", "baud";
 				status = "disabled";
 			};
@@ -195,10 +523,17 @@
 				compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart";
 				reg = <0x0 0x4000 0x0 0x18>;
 				interrupts = <GIC_SPI 197 IRQ_TYPE_EDGE_RISING>;
-				clocks = <&xtal>, <&xtal>, <&xtal>;
+				clocks = <&xtal>, <&clkc CLKID_CLK81>, <&xtal>;
 				clock-names = "xtal", "pclk", "baud";
 				status = "disabled";
 			};
+
+			ir: ir@8000 {
+				compatible = "amlogic,meson-gxbb-ir";
+				reg = <0x0 0x8000 0x0 0x20>;
+				interrupts = <GIC_SPI 196 IRQ_TYPE_EDGE_RISING>;
+				status = "disabled";
+			};
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
index 7d4b95e49993..aeb6d21a3bec 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
@@ -59,6 +59,18 @@
 		reg = <0x0 0x0 0x0 0x80000000>;
 	};
 
+	hdmi_5v: regulator-hdmi-5v {
+		compatible = "regulator-fixed";
+
+		regulator-name = "HDMI_5V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+
+		gpio = <&gpio GPIOH_3 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
+	};
+
 	vddio_boot: regulator-vddio_boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index ab7ce1644cdc..6cb3c2a52baf 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -211,7 +211,7 @@
 		#size-cells = <2>;
 		ranges;
 
-		cbus: cbus@c1100000 {
+		cbus: bus@c1100000 {
 			compatible = "simple-bus";
 			reg = <0x0 0xc1100000 0x0 0x100000>;
 			#address-cells = <2>;
@@ -229,7 +229,7 @@
 
 			reset: reset-controller@4404 {
 				compatible = "amlogic,meson-gx-reset", "amlogic,meson-gxbb-reset";
-				reg = <0x0 0x04404 0x0 0x20>;
+				reg = <0x0 0x04404 0x0 0x9c>;
 				#reset-cells = <1>;
 			};
 
@@ -366,7 +366,7 @@
 			};
 		};
 
-		aobus: aobus@c8100000 {
+		aobus: bus@c8100000 {
 			compatible = "simple-bus";
 			reg = <0x0 0xc8100000 0x0 0x100000>;
 			#address-cells = <2>;
@@ -377,6 +377,12 @@
 				compatible = "amlogic,meson-gx-ao-sysctrl", "syscon", "simple-mfd";
 				reg =  <0x0 0x0 0x0 0x100>;
 
+				pwrc_vpu: power-controller-vpu {
+					compatible = "amlogic,meson-gx-pwrc-vpu";
+					#power-domain-cells = <0>;
+					amlogic,hhi-sysctrl = <&sysctrl>;
+				};
+
 				clkc_AO: clock-controller {
 					compatible = "amlogic,meson-gx-aoclkc";
 					#clock-cells = <1>;
@@ -447,13 +453,18 @@
 			};
 		};
 
-		hiubus: hiubus@c883c000 {
+		hiubus: bus@c883c000 {
 			compatible = "simple-bus";
 			reg = <0x0 0xc883c000 0x0 0x2000>;
 			#address-cells = <2>;
 			#size-cells = <2>;
 			ranges = <0x0 0x0 0x0 0xc883c000 0x0 0x2000>;
 
+			sysctrl: system-controller@0 {
+				compatible = "amlogic,meson-gx-hhi-sysctrl", "syscon", "simple-mfd";
+				reg = <0 0 0 0x400>;
+			};
+
 			mailbox: mailbox@404 {
 				compatible = "amlogic,meson-gx-mhu", "amlogic,meson-gxbb-mhu";
 				reg = <0 0x404 0 0x4c>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts
index 4a4251001bfd..011e8e08e429 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts
@@ -169,6 +169,7 @@
 			/* Realtek RTL8211F (0x001cc916) */
 			reg = <0>;
 			interrupt-parent = <&gpio_intc>;
+			/* MAC_INTR on GPIOZ_15 */
 			interrupts = <29 IRQ_TYPE_LEVEL_LOW>;
 		};
 	};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
index f8d221463c60..ee4ada61c59c 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
@@ -135,6 +135,24 @@
 		compatible = "mmc-pwrseq-emmc";
 		reset-gpios = <&gpio BOOT_9 GPIO_ACTIVE_LOW>;
 	};
+
+	hdmi-connector {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_connector_in: endpoint {
+				remote-endpoint = <&hdmi_tx_tmds_out>;
+			};
+		};
+	};
+};
+
+&cec_AO {
+	status = "okay";
+	pinctrl-0 = <&ao_cec_pins>;
+	pinctrl-names = "default";
+	hdmi-phandle = <&hdmi_tx>;
 };
 
 &ethmac {
@@ -156,8 +174,10 @@
 		#size-cells = <0>;
 
 		eth_phy0: ethernet-phy@0 {
+			/* Realtek RTL8211F (0x001cc916) */
 			reg = <0>;
 			interrupt-parent = <&gpio_intc>;
+			/* MAC_INTR on GPIOZ_15 */
 			interrupts = <29 IRQ_TYPE_LEVEL_LOW>;
 			eee-broken-1000t;
 		};
@@ -179,6 +199,18 @@
 	};
 };
 
+&hdmi_tx {
+	status = "okay";
+	pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>;
+	pinctrl-names = "default";
+};
+
+&hdmi_tx_tmds_port {
+	hdmi_tx_tmds_out: endpoint {
+		remote-endpoint = <&hdmi_connector_in>;
+	};
+};
+
 &i2c_A {
 	status = "okay";
 	pinctrl-0 = <&i2c_a_pins>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
index 9bf16bb7c491..09f34f7ef084 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
@@ -118,6 +118,7 @@
 			/* Micrel KSZ9031 (0x00221620) */
 			reg = <3>;
 			interrupt-parent = <&gpio_intc>;
+			/* MAC_INTR on GPIOZ_15 */
 			interrupts = <29 IRQ_TYPE_LEVEL_LOW>;
 		};
 	};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index ead895a4e9a5..3290a4dc3522 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -694,14 +694,55 @@
 	};
 };
 
+&pwrc_vpu {
+	resets = <&reset RESET_VIU>,
+		 <&reset RESET_VENC>,
+		 <&reset RESET_VCBUS>,
+		 <&reset RESET_BT656>,
+		 <&reset RESET_DVIN_RESET>,
+		 <&reset RESET_RDMA>,
+		 <&reset RESET_VENCI>,
+		 <&reset RESET_VENCP>,
+		 <&reset RESET_VDAC>,
+		 <&reset RESET_VDI6>,
+		 <&reset RESET_VENCL>,
+		 <&reset RESET_VID_LOCK>;
+	clocks = <&clkc CLKID_VPU>,
+	         <&clkc CLKID_VAPB>;
+	clock-names = "vpu", "vapb";
+	/*
+	 * VPU clocking is provided by two identical clock paths
+	 * VPU_0 and VPU_1 muxed to a single clock by a glitch
+	 * free mux to safely change frequency while running.
+	 * Same for VAPB but with a final gate after the glitch free mux.
+	 */
+	assigned-clocks = <&clkc CLKID_VPU_0_SEL>,
+			  <&clkc CLKID_VPU_0>,
+			  <&clkc CLKID_VPU>, /* Glitch free mux */
+			  <&clkc CLKID_VAPB_0_SEL>,
+			  <&clkc CLKID_VAPB_0>,
+			  <&clkc CLKID_VAPB_SEL>; /* Glitch free mux */
+	assigned-clock-parents = <&clkc CLKID_FCLK_DIV3>,
+				 <0>, /* Do Nothing */
+				 <&clkc CLKID_VPU_0>,
+				 <&clkc CLKID_FCLK_DIV4>,
+				 <0>, /* Do Nothing */
+				 <&clkc CLKID_VAPB_0>;
+	assigned-clock-rates = <0>, /* Do Nothing */
+			       <666666666>,
+			       <0>, /* Do Nothing */
+			       <0>, /* Do Nothing */
+			       <250000000>,
+			       <0>; /* Do Nothing */
+};
+
 &saradc {
 	compatible = "amlogic,meson-gxbb-saradc", "amlogic,meson-saradc";
 	clocks = <&xtal>,
 		 <&clkc CLKID_SAR_ADC>,
-		 <&clkc CLKID_SANA>,
 		 <&clkc CLKID_SAR_ADC_CLK>,
 		 <&clkc CLKID_SAR_ADC_SEL>;
-	clock-names = "clkin", "core", "sana", "adc_clk", "adc_sel";
+	clock-names = "clkin", "core", "adc_clk", "adc_sel";
 };
 
 &sd_emmc_a {
@@ -753,14 +794,15 @@
 
 &uart_B {
 	clocks = <&xtal>, <&clkc CLKID_UART1>, <&xtal>;
-	clock-names = "xtal", "core", "baud";
+	clock-names = "xtal", "pclk", "baud";
 };
 
 &uart_C {
 	clocks = <&xtal>, <&clkc CLKID_UART2>, <&xtal>;
-	clock-names = "xtal", "core", "baud";
+	clock-names = "xtal", "pclk", "baud";
 };
 
 &vpu {
 	compatible = "amlogic,meson-gxbb-vpu", "amlogic,meson-gx-vpu";
+	power-domains = <&pwrc_vpu>;
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
index dc9c3b8216c2..9671f1e3c74a 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
@@ -72,6 +72,18 @@
 		reg = <0x0 0x0 0x0 0x80000000>;
 	};
 
+	hdmi_5v: regulator-hdmi-5v {
+		compatible = "regulator-fixed";
+
+		regulator-name = "HDMI_5V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+
+		gpio = <&gpio GPIOH_3 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
+	};
+
 	vcc_3v3: regulator-vcc_3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
index ff09df1fd5a3..7005068346a0 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
@@ -28,6 +28,18 @@
 		reg = <0x0 0x0 0x0 0x80000000>;
 	};
 
+	hdmi_5v: regulator-hdmi-5v {
+		compatible = "regulator-fixed";
+
+		regulator-name = "HDMI_5V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+
+		gpio = <&gpio GPIOH_3 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
+	};
+
 	vddio_boot: regulator-vddio_boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 8ed981f59e5a..4f355f17eed6 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -644,14 +644,55 @@
 	};
 };
 
+&pwrc_vpu {
+	resets = <&reset RESET_VIU>,
+		 <&reset RESET_VENC>,
+		 <&reset RESET_VCBUS>,
+		 <&reset RESET_BT656>,
+		 <&reset RESET_DVIN_RESET>,
+		 <&reset RESET_RDMA>,
+		 <&reset RESET_VENCI>,
+		 <&reset RESET_VENCP>,
+		 <&reset RESET_VDAC>,
+		 <&reset RESET_VDI6>,
+		 <&reset RESET_VENCL>,
+		 <&reset RESET_VID_LOCK>;
+	clocks = <&clkc CLKID_VPU>,
+	         <&clkc CLKID_VAPB>;
+	clock-names = "vpu", "vapb";
+	/*
+	 * VPU clocking is provided by two identical clock paths
+	 * VPU_0 and VPU_1 muxed to a single clock by a glitch
+	 * free mux to safely change frequency while running.
+	 * Same for VAPB but with a final gate after the glitch free mux.
+	 */
+	assigned-clocks = <&clkc CLKID_VPU_0_SEL>,
+			  <&clkc CLKID_VPU_0>,
+			  <&clkc CLKID_VPU>, /* Glitch free mux */
+			  <&clkc CLKID_VAPB_0_SEL>,
+			  <&clkc CLKID_VAPB_0>,
+			  <&clkc CLKID_VAPB_SEL>; /* Glitch free mux */
+	assigned-clock-parents = <&clkc CLKID_FCLK_DIV3>,
+				 <0>, /* Do Nothing */
+				 <&clkc CLKID_VPU_0>,
+				 <&clkc CLKID_FCLK_DIV4>,
+				 <0>, /* Do Nothing */
+				 <&clkc CLKID_VAPB_0>;
+	assigned-clock-rates = <0>, /* Do Nothing */
+			       <666666666>,
+			       <0>, /* Do Nothing */
+			       <0>, /* Do Nothing */
+			       <250000000>,
+			       <0>; /* Do Nothing */
+};
+
 &saradc {
 	compatible = "amlogic,meson-gxl-saradc", "amlogic,meson-saradc";
 	clocks = <&xtal>,
 		 <&clkc CLKID_SAR_ADC>,
-		 <&clkc CLKID_SANA>,
 		 <&clkc CLKID_SAR_ADC_CLK>,
 		 <&clkc CLKID_SAR_ADC_SEL>;
-	clock-names = "clkin", "core", "sana", "adc_clk", "adc_sel";
+	clock-names = "clkin", "core", "adc_clk", "adc_sel";
 };
 
 &sd_emmc_a {
@@ -688,7 +729,7 @@
 
 &uart_A {
 	clocks = <&xtal>, <&clkc CLKID_UART0>, <&xtal>;
-	clock-names = "xtal", "core", "baud";
+	clock-names = "xtal", "pclk", "baud";
 };
 
 &uart_AO {
@@ -703,14 +744,15 @@
 
 &uart_B {
 	clocks = <&xtal>, <&clkc CLKID_UART1>, <&xtal>;
-	clock-names = "xtal", "core", "baud";
+	clock-names = "xtal", "pclk", "baud";
 };
 
 &uart_C {
 	clocks = <&xtal>, <&clkc CLKID_UART2>, <&xtal>;
-	clock-names = "xtal", "core", "baud";
+	clock-names = "xtal", "pclk", "baud";
 };
 
 &vpu {
 	compatible = "amlogic,meson-gxl-vpu", "amlogic,meson-gx-vpu";
+	power-domains = <&pwrc_vpu>;
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
index 34a41b26a4ed..1448c3dba08e 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
@@ -153,6 +153,18 @@
 		};
 	};
 
+	hdmi_5v: regulator-hdmi-5v {
+		compatible = "regulator-fixed";
+
+		regulator-name = "HDMI_5V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+
+		gpio = <&gpio GPIOH_3 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
+	};
+
 	vcc_3v3: regulator-vcc_3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
@@ -232,6 +244,9 @@
 	external_phy: ethernet-phy@0 {
 		/* Realtek RTL8211F (0x001cc916) */
 		reg = <0>;
+		interrupt-parent = <&gpio_intc>;
+		/* MAC_INTR on GPIOZ_15 */
+		interrupts = <25 IRQ_TYPE_LEVEL_LOW>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-q200.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-q200.dts
index 66c6da7e112c..388fac4f2d97 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-q200.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-q200.dts
@@ -111,7 +111,8 @@
 		reg = <0>;
 		max-speed = <1000>;
 		interrupt-parent = <&gpio_intc>;
-		interrupts = <29 IRQ_TYPE_LEVEL_LOW>;
+		/* MAC_INTR on GPIOZ_15 */
+		interrupts = <25 IRQ_TYPE_LEVEL_LOW>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/exynos/exynos5433-bus.dtsi b/arch/arm64/boot/dts/exynos/exynos5433-bus.dtsi
index ec11343dc528..d77b88af9582 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-bus.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433-bus.dtsi
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos5433 SoC Memory interface and AMBA bus device tree source
  *
  * Copyright (c) 2016 Samsung Electronics Co., Ltd.
  * Chanwoo Choi <cw00.choi@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 &soc {
diff --git a/arch/arm64/boot/dts/exynos/exynos5433-pinctrl.dtsi b/arch/arm64/boot/dts/exynos/exynos5433-pinctrl.dtsi
index 50403700274b..9df7c65593a1 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-pinctrl.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433-pinctrl.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos5433 SoC pin-mux and pin-config device tree source
  *
@@ -6,10 +7,6 @@
  *
  * Samsung's Exynos5433 SoC pin-mux and pin-config options are listed as device
  * tree nodes are listed in this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/pinctrl/samsung.h>
diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi
index 297597442c44..a77462da4a36 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG Exynos5433 TM2 board device tree source
  *
@@ -5,10 +6,6 @@
  *
  * Common device tree source file for Samsung's TM2 and TM2E boards
  * which are based on Samsung Exynos5433 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
@@ -741,6 +738,19 @@
 	};
 };
 
+&hsi2c_4 {
+	status = "okay";
+
+	s3fwrn5: nfc@27 {
+		compatible = "samsung,s3fwrn5-i2c";
+		reg = <0x27>;
+		interrupt-parent = <&gpa1>;
+		interrupts = <3 IRQ_TYPE_LEVEL_HIGH>;
+		s3fwrn5,en-gpios = <&gpf1 4 GPIO_ACTIVE_HIGH>;
+		s3fwrn5,fw-gpios = <&gpj0 2 GPIO_ACTIVE_HIGH>;
+	};
+};
+
 &hsi2c_5 {
 	status = "okay";
 
@@ -756,6 +766,7 @@
 
 &hsi2c_7 {
 	status = "okay";
+	clock-frequency = <1000000>;
 
 	sii8620@39 {
 		reg = <0x39>;
diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts b/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts
index 23191eb9397c..3d7e0a782243 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts
+++ b/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG Exynos5433 TM2 board device tree source
  *
@@ -5,10 +6,6 @@
  *
  * Device tree source file for Samsung's TM2 board which is based on
  * Samsung Exynos5433 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include "exynos5433-tm2-common.dtsi"
diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tm2e.dts b/arch/arm64/boot/dts/exynos/exynos5433-tm2e.dts
index b73e1231a86f..1e207ce8b97b 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-tm2e.dts
+++ b/arch/arm64/boot/dts/exynos/exynos5433-tm2e.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG Exynos5433 TM2E board device tree source
  *
@@ -5,10 +6,6 @@
  *
  * Device tree source file for Samsung's TM2E(TM2 EDGE) board which is based on
  * Samsung Exynos5433 SoC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include "exynos5433-tm2-common.dtsi"
diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tmu-g3d-sensor-conf.dtsi b/arch/arm64/boot/dts/exynos/exynos5433-tmu-g3d-sensor-conf.dtsi
index 9be2978f1b9a..f0803575fd9f 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-tmu-g3d-sensor-conf.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433-tmu-g3d-sensor-conf.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device tree sources for Exynos5433 TMU sensor configuration
  *
  * Copyright (c) 2016 Jonghwa Lee <jonghwa3.lee@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/thermal/thermal_exynos.h>
diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tmu-sensor-conf.dtsi b/arch/arm64/boot/dts/exynos/exynos5433-tmu-sensor-conf.dtsi
index 125fe58d77ce..cccae662228a 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-tmu-sensor-conf.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433-tmu-sensor-conf.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device tree sources for Exynos5433 TMU sensor configuration
  *
  * Copyright (c) 2016 Chanwoo Choi <cw00.choi@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/thermal/thermal_exynos.h>
diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tmu.dtsi b/arch/arm64/boot/dts/exynos/exynos5433-tmu.dtsi
index ceaa05145b8a..fe3a0b14bee6 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-tmu.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433-tmu.dtsi
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device tree sources for Exynos5433 thermal zone
  *
  * Copyright (c) 2016 Chanwoo Choi <cw00.choi@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/thermal/thermal.h>
diff --git a/arch/arm64/boot/dts/exynos/exynos5433.dtsi b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
index 7fe994b750da..62f276970174 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos5433 SoC device tree source
  *
@@ -10,10 +11,6 @@
  * Note: This file does not include device nodes for all the controllers in
  * Exynos5433 SoC. As device tree coverage for Exynos5433 increases,
  * additional nodes can be added to this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/clock/exynos5433.h>
@@ -247,6 +244,24 @@
 		#size-cells = <1>;
 		ranges = <0x0 0x0 0x0 0x18000000>;
 
+		arm_a53_pmu {
+			compatible = "arm,cortex-a53-pmu", "arm,armv8-pmuv3";
+			interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
+		};
+
+		arm_a57_pmu {
+			compatible = "arm,cortex-a57-pmu", "arm,armv8-pmuv3";
+			interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-affinity = <&cpu4>, <&cpu5>, <&cpu6>, <&cpu7>;
+		};
+
 		chipid@10000000 {
 			compatible = "samsung,exynos4210-chipid";
 			reg = <0x10000000 0x100>;
@@ -343,6 +358,7 @@
 			clocks = <&xxti>,
 				<&cmu_top CLK_ACLK_G2D_266>,
 				<&cmu_top CLK_ACLK_G2D_400>;
+			power-domains = <&pd_g2d>;
 		};
 
 		cmu_disp: clock-controller@13b90000 {
@@ -368,6 +384,7 @@
 				<&cmu_mif CLK_SCLK_DECON_ECLK_DISP>,
 				<&cmu_mif CLK_SCLK_DECON_TV_VCLK_DISP>,
 				<&cmu_mif CLK_ACLK_DISP_333>;
+			power-domains = <&pd_disp>;
 		};
 
 		cmu_aud: clock-controller@114c0000 {
@@ -376,6 +393,7 @@
 			#clock-cells = <1>;
 			clock-names = "oscclk", "fout_aud_pll";
 			clocks = <&xxti>, <&cmu_top CLK_FOUT_AUD_PLL>;
+			power-domains = <&pd_aud>;
 		};
 
 		cmu_bus0: clock-controller@13600000 {
@@ -412,6 +430,7 @@
 
 			clock-names = "oscclk", "aclk_g3d_400";
 			clocks = <&xxti>, <&cmu_top CLK_ACLK_G3D_400>;
+			power-domains = <&pd_g3d>;
 		};
 
 		cmu_gscl: clock-controller@13cf0000 {
@@ -425,6 +444,7 @@
 			clocks = <&xxti>,
 				<&cmu_top CLK_ACLK_GSCL_111>,
 				<&cmu_top CLK_ACLK_GSCL_333>;
+			power-domains = <&pd_gscl>;
 		};
 
 		cmu_apollo: clock-controller@11900000 {
@@ -445,7 +465,7 @@
 			clocks = <&xxti>, <&cmu_mif CLK_SCLK_BUS_PLL_ATLAS>;
 		};
 
-		cmu_mscl: clock-controller@105d0000 {
+		cmu_mscl: clock-controller@150d0000 {
 			compatible = "samsung,exynos5433-cmu-mscl";
 			reg = <0x150d0000 0x1000>;
 			#clock-cells = <1>;
@@ -456,6 +476,7 @@
 			clocks = <&xxti>,
 				<&cmu_top CLK_SCLK_JPEG_MSCL>,
 				<&cmu_top CLK_ACLK_MSCL_400>;
+			power-domains = <&pd_mscl>;
 		};
 
 		cmu_mfc: clock-controller@15280000 {
@@ -465,6 +486,7 @@
 
 			clock-names = "oscclk", "aclk_mfc_400";
 			clocks = <&xxti>, <&cmu_top CLK_ACLK_MFC_400>;
+			power-domains = <&pd_mfc>;
 		};
 
 		cmu_hevc: clock-controller@14f80000 {
@@ -474,6 +496,7 @@
 
 			clock-names = "oscclk", "aclk_hevc_400";
 			clocks = <&xxti>, <&cmu_top CLK_ACLK_HEVC_400>;
+			power-domains = <&pd_hevc>;
 		};
 
 		cmu_isp: clock-controller@146d0000 {
@@ -487,6 +510,7 @@
 			clocks = <&xxti>,
 				<&cmu_top CLK_ACLK_ISP_DIS_400>,
 				<&cmu_top CLK_ACLK_ISP_400>;
+			power-domains = <&pd_isp>;
 		};
 
 		cmu_cam0: clock-controller@120d0000 {
@@ -502,6 +526,7 @@
 				<&cmu_top CLK_ACLK_CAM0_333>,
 				<&cmu_top CLK_ACLK_CAM0_400>,
 				<&cmu_top CLK_ACLK_CAM0_552>;
+			power-domains = <&pd_cam0>;
 		};
 
 		cmu_cam1: clock-controller@145d0000 {
@@ -523,6 +548,86 @@
 				<&cmu_top CLK_ACLK_CAM1_333>,
 				<&cmu_top CLK_ACLK_CAM1_400>,
 				<&cmu_top CLK_ACLK_CAM1_552>;
+			power-domains = <&pd_cam1>;
+		};
+
+		pd_gscl: power-domain@105c4000 {
+			compatible = "samsung,exynos5433-pd";
+			reg = <0x105c4000 0x20>;
+			#power-domain-cells = <0>;
+			label = "GSCL";
+		};
+
+		pd_cam0: power-domain@105c4020 {
+			compatible = "samsung,exynos5433-pd";
+			reg = <0x105c4020 0x20>;
+			#power-domain-cells = <0>;
+			power-domains = <&pd_cam1>;
+			label = "CAM0";
+		};
+
+		pd_mscl: power-domain@105c4040 {
+			compatible = "samsung,exynos5433-pd";
+			reg = <0x105c4040 0x20>;
+			#power-domain-cells = <0>;
+			label = "MSCL";
+		};
+
+		pd_g3d: power-domain@105c4060 {
+			compatible = "samsung,exynos5433-pd";
+			reg = <0x105c4060 0x20>;
+			#power-domain-cells = <0>;
+			label = "G3D";
+		};
+
+		pd_disp: power-domain@105c4080 {
+			compatible = "samsung,exynos5433-pd";
+			reg = <0x105c4080 0x20>;
+			#power-domain-cells = <0>;
+			label = "DISP";
+		};
+
+		pd_cam1: power-domain@105c40a0 {
+			compatible = "samsung,exynos5433-pd";
+			reg = <0x105c40a0 0x20>;
+			#power-domain-cells = <0>;
+			label = "CAM1";
+		};
+
+		pd_aud: power-domain@105c40c0 {
+			compatible = "samsung,exynos5433-pd";
+			reg = <0x105c40c0 0x20>;
+			#power-domain-cells = <0>;
+			label = "AUD";
+		};
+
+		pd_g2d: power-domain@105c4120 {
+			compatible = "samsung,exynos5433-pd";
+			reg = <0x105c4120 0x20>;
+			#power-domain-cells = <0>;
+			label = "G2D";
+		};
+
+		pd_isp: power-domain@105c4140 {
+			compatible = "samsung,exynos5433-pd";
+			reg = <0x105c4140 0x20>;
+			#power-domain-cells = <0>;
+			power-domains = <&pd_cam0>;
+			label = "ISP";
+		};
+
+		pd_mfc: power-domain@105c4180 {
+			compatible = "samsung,exynos5433-pd";
+			reg = <0x105c4180 0x20>;
+			#power-domain-cells = <0>;
+			label = "MFC";
+		};
+
+		pd_hevc: power-domain@105c41c0 {
+			compatible = "samsung,exynos5433-pd";
+			reg = <0x105c41c0 0x20>;
+			#power-domain-cells = <0>;
+			label = "HEVC";
 		};
 
 		tmu_atlas0: tmu@10060000 {
@@ -637,6 +742,7 @@
 			compatible = "samsung,exynos5433-pinctrl";
 			reg = <0x114b0000 0x1000>;
 			interrupts = <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>;
+			power-domains = <&pd_aud>;
 		};
 
 		pinctrl_cpif: pinctrl@10fe0000 {
@@ -728,6 +834,7 @@
 			clock-names = "pclk", "aclk_decon", "aclk_smmu_decon0x",
 				"aclk_xiu_decon0x", "pclk_smmu_decon0x",
 				"sclk_decon_vclk", "sclk_decon_eclk";
+			power-domains = <&pd_disp>;
 			interrupt-names = "fifo", "vsync", "lcd_sys";
 			interrupts = <GIC_SPI 201 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 202 IRQ_TYPE_LEVEL_HIGH>,
@@ -765,6 +872,7 @@
 				      "aclk_xiu_decon0x", "pclk_smmu_decon0x",
 				      "sclk_decon_vclk", "sclk_decon_eclk";
 			samsung,disp-sysreg = <&syscon_disp>;
+			power-domains = <&pd_disp>;
 			interrupt-names = "fifo", "vsync", "lcd_sys";
 			interrupts = <GIC_SPI 210 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 211 IRQ_TYPE_LEVEL_HIGH>,
@@ -790,6 +898,7 @@
 					"phyclk_mipidphy0_rxclkesc0",
 					"sclk_rgb_vclk_to_dsim0",
 					"sclk_mipi";
+			power-domains = <&pd_disp>;
 			status = "disabled";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -813,6 +922,7 @@
 			clocks = <&cmu_disp CLK_PCLK_MIC0>,
 				<&cmu_disp CLK_SCLK_RGB_VCLK_TO_MIC0>;
 			clock-names = "pclk_mic0", "sclk_rgb_vclk_to_mic0";
+			power-domains = <&pd_disp>;
 			samsung,disp-syscon = <&syscon_disp>;
 			status = "disabled";
 
@@ -881,7 +991,7 @@
 			reg = <0x145f0000 0x1038>;
 		};
 
-		gsc_0: video-scaler@13C00000 {
+		gsc_0: video-scaler@13c00000 {
 			compatible = "samsung,exynos5433-gsc";
 			reg = <0x13c00000 0x1000>;
 			interrupts = <GIC_SPI 297 IRQ_TYPE_LEVEL_HIGH>;
@@ -892,9 +1002,10 @@
 				 <&cmu_gscl CLK_ACLK_XIU_GSCLX>,
 				 <&cmu_gscl CLK_ACLK_GSCLBEND_333>;
 			iommus = <&sysmmu_gscl0>;
+			power-domains = <&pd_gscl>;
 		};
 
-		gsc_1: video-scaler@13C10000 {
+		gsc_1: video-scaler@13c10000 {
 			compatible = "samsung,exynos5433-gsc";
 			reg = <0x13c10000 0x1000>;
 			interrupts = <GIC_SPI 298 IRQ_TYPE_LEVEL_HIGH>;
@@ -905,9 +1016,10 @@
 				 <&cmu_gscl CLK_ACLK_XIU_GSCLX>,
 				 <&cmu_gscl CLK_ACLK_GSCLBEND_333>;
 			iommus = <&sysmmu_gscl1>;
+			power-domains = <&pd_gscl>;
 		};
 
-		gsc_2: video-scaler@13C20000 {
+		gsc_2: video-scaler@13c20000 {
 			compatible = "samsung,exynos5433-gsc";
 			reg = <0x13c20000 0x1000>;
 			interrupts = <GIC_SPI 299 IRQ_TYPE_LEVEL_HIGH>;
@@ -918,6 +1030,7 @@
 				 <&cmu_gscl CLK_ACLK_XIU_GSCLX>,
 				 <&cmu_gscl CLK_ACLK_GSCLBEND_333>;
 			iommus = <&sysmmu_gscl2>;
+			power-domains = <&pd_gscl>;
 		};
 
 		jpeg: codec@15020000 {
@@ -930,9 +1043,10 @@
 				 <&cmu_mscl CLK_ACLK_XIU_MSCLX>,
 				 <&cmu_mscl CLK_SCLK_JPEG>;
 			iommus = <&sysmmu_jpeg>;
+			power-domains = <&pd_mscl>;
 		};
 
-		mfc: codec@152E0000 {
+		mfc: codec@152e0000 {
 			compatible = "samsung,exynos5433-mfc";
 			reg = <0x152E0000 0x10000>;
 			interrupts = <GIC_SPI 358 IRQ_TYPE_LEVEL_HIGH>;
@@ -942,6 +1056,7 @@
 				 <&cmu_mfc CLK_ACLK_XIU_MFCX>;
 			iommus = <&sysmmu_mfc_0>, <&sysmmu_mfc_1>;
 			iommu-names = "left", "right";
+			power-domains = <&pd_mfc>;
 		};
 
 		sysmmu_decon0x: sysmmu@13a00000 {
@@ -951,6 +1066,7 @@
 			clock-names = "pclk", "aclk";
 			clocks = <&cmu_disp CLK_PCLK_SMMU_DECON0X>,
 				<&cmu_disp CLK_ACLK_SMMU_DECON0X>;
+			power-domains = <&pd_disp>;
 			#iommu-cells = <0>;
 		};
 
@@ -962,6 +1078,7 @@
 			clocks = <&cmu_disp CLK_PCLK_SMMU_DECON1X>,
 				<&cmu_disp CLK_ACLK_SMMU_DECON1X>;
 			#iommu-cells = <0>;
+			power-domains = <&pd_disp>;
 		};
 
 		sysmmu_tv0x: sysmmu@13a20000 {
@@ -972,6 +1089,7 @@
 			clocks = <&cmu_disp CLK_PCLK_SMMU_TV0X>,
 				<&cmu_disp CLK_ACLK_SMMU_TV0X>;
 			#iommu-cells = <0>;
+			power-domains = <&pd_disp>;
 		};
 
 		sysmmu_tv1x: sysmmu@13a30000 {
@@ -982,6 +1100,7 @@
 			clocks = <&cmu_disp CLK_PCLK_SMMU_TV1X>,
 				<&cmu_disp CLK_ACLK_SMMU_TV1X>;
 			#iommu-cells = <0>;
+			power-domains = <&pd_disp>;
 		};
 
 		sysmmu_gscl0: sysmmu@13c80000 {
@@ -992,6 +1111,7 @@
 			clocks = <&cmu_gscl CLK_ACLK_SMMU_GSCL0>,
 				 <&cmu_gscl CLK_PCLK_SMMU_GSCL0>;
 			#iommu-cells = <0>;
+			power-domains = <&pd_gscl>;
 		};
 
 		sysmmu_gscl1: sysmmu@13c90000 {
@@ -1002,6 +1122,7 @@
 			clocks = <&cmu_gscl CLK_ACLK_SMMU_GSCL1>,
 				 <&cmu_gscl CLK_PCLK_SMMU_GSCL1>;
 			#iommu-cells = <0>;
+			power-domains = <&pd_gscl>;
 		};
 
 		sysmmu_gscl2: sysmmu@13ca0000 {
@@ -1012,6 +1133,7 @@
 			clocks = <&cmu_gscl CLK_ACLK_SMMU_GSCL2>,
 				 <&cmu_gscl CLK_PCLK_SMMU_GSCL2>;
 			#iommu-cells = <0>;
+			power-domains = <&pd_gscl>;
 		};
 
 		sysmmu_jpeg: sysmmu@15060000 {
@@ -1022,6 +1144,7 @@
 			clocks = <&cmu_mscl CLK_PCLK_SMMU_JPEG>,
 				 <&cmu_mscl CLK_ACLK_SMMU_JPEG>;
 			#iommu-cells = <0>;
+			power-domains = <&pd_mscl>;
 		};
 
 		sysmmu_mfc_0: sysmmu@15200000 {
@@ -1032,6 +1155,7 @@
 			clocks = <&cmu_mfc CLK_PCLK_SMMU_MFC_0>,
 				 <&cmu_mfc CLK_ACLK_SMMU_MFC_0>;
 			#iommu-cells = <0>;
+			power-domains = <&pd_mfc>;
 		};
 
 		sysmmu_mfc_1: sysmmu@15210000 {
@@ -1042,6 +1166,7 @@
 			clocks = <&cmu_mfc CLK_PCLK_SMMU_MFC_1>,
 				 <&cmu_mfc CLK_ACLK_SMMU_MFC_1>;
 			#iommu-cells = <0>;
+			power-domains = <&pd_mfc>;
 		};
 
 		serial_0: serial@14c10000 {
@@ -1497,6 +1622,7 @@
 			clocks = <&cmu_aud CLK_PCLK_SFR0_CTRL>;
 			clock-names = "sfr0_ctrl";
 			samsung,pmu-syscon = <&pmu_system_controller>;
+			power-domains = <&pd_aud>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
@@ -1510,6 +1636,7 @@
 				#dma-cells = <1>;
 				#dma-channels = <8>;
 				#dma-requests = <32>;
+				power-domains = <&pd_aud>;
 			};
 
 			i2s0: i2s0@11440000 {
@@ -1526,6 +1653,7 @@
 				clock-names = "iis", "i2s_opclk0", "i2s_opclk1";
 				pinctrl-names = "default";
 				pinctrl-0 = <&i2s0_bus>;
+				power-domains = <&pd_aud>;
 				status = "disabled";
 			};
 
@@ -1538,6 +1666,7 @@
 				clock-names = "uart", "clk_uart_baud0";
 				pinctrl-names = "default";
 				pinctrl-0 = <&uart_aud_bus>;
+				power-domains = <&pd_aud>;
 				status = "disabled";
 			};
 		};
diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
index 4a8b1fb51243..22723527e626 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
+++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG Exynos7 Espresso board device tree source
  *
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 /dts-v1/;
 #include "exynos7.dtsi"
diff --git a/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi b/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi
index 8f58850cd28c..472dd649aa7e 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Samsung's Exynos7 SoC pin-mux and pin-config device tree source
  *
@@ -6,11 +7,7 @@
  *
  * Samsung's Exynos7 SoC pin-mux and pin-config options are listed as
  * device tree nodes in this file.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #include <dt-bindings/pinctrl/samsung.h>
 
diff --git a/arch/arm64/boot/dts/exynos/exynos7-tmu-sensor-conf.dtsi b/arch/arm64/boot/dts/exynos/exynos7-tmu-sensor-conf.dtsi
index 1d6dcf2aadba..48494710b7b2 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-tmu-sensor-conf.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7-tmu-sensor-conf.dtsi
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device tree sources for Exynos7 TMU sensor configuration
  *
  * Copyright (c) 2016 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #include <dt-bindings/thermal/thermal_exynos.h>
diff --git a/arch/arm64/boot/dts/exynos/exynos7-trip-points.dtsi b/arch/arm64/boot/dts/exynos/exynos7-trip-points.dtsi
index 062358355a53..d3301b8bd364 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-trip-points.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7-trip-points.dtsi
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device tree sources for default Exynos7 thermal zone definition
  *
  * Copyright (c) 2016 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 trips {
diff --git a/arch/arm64/boot/dts/exynos/exynos7.dtsi b/arch/arm64/boot/dts/exynos/exynos7.dtsi
index 9a3fbed1765a..ad9dce6894ce 100644
--- a/arch/arm64/boot/dts/exynos/exynos7.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7.dtsi
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SAMSUNG EXYNOS7 SoC device tree source
  *
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <dt-bindings/clock/exynos7-clk.h>
@@ -103,7 +100,7 @@
 			#size-cells = <1>;
 			ranges;
 
-			pdma0: pdma@10E10000 {
+			pdma0: pdma@10e10000 {
 				compatible = "arm,pl330", "arm,primecell";
 				reg = <0x10E10000 0x1000>;
 				interrupts = <GIC_SPI 225 IRQ_TYPE_LEVEL_HIGH>;
@@ -114,7 +111,7 @@
 				#dma-requests = <32>;
 			};
 
-			pdma1: pdma@10EB0000 {
+			pdma1: pdma@10eb0000 {
 				compatible = "arm,pl330", "arm,primecell";
 				reg = <0x10EB0000 0x1000>;
 				interrupts = <GIC_SPI 226 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts
index 0f6fcda36b9e..4f17601b919c 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts
@@ -125,3 +125,11 @@
 &sata {
 	status = "okay";
 };
+
+&usb0 {
+	status = "okay";
+};
+
+&usb1 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
index bd80e9a2e67c..4fc150cd4ca5 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
@@ -166,6 +166,77 @@
 			     <1 10 IRQ_TYPE_LEVEL_LOW>;/* Hypervisor PPI */
 	};
 
+	fsl_mc: fsl-mc@80c000000 {
+		compatible = "fsl,qoriq-mc";
+		reg = <0x00000008 0x0c000000 0 0x40>,	 /* MC portal base */
+		      <0x00000000 0x08340000 0 0x40000>; /* MC control reg */
+		msi-parent = <&its>;
+		#address-cells = <3>;
+		#size-cells = <1>;
+
+		/*
+		 * Region type 0x0 - MC portals
+		 * Region type 0x1 - QBMAN portals
+		 */
+		ranges = <0x0 0x0 0x0 0x8 0x0c000000 0x4000000
+			  0x1 0x0 0x0 0x8 0x18000000 0x8000000>;
+
+		dpmacs {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			dpmac1: dpmac@1 {
+				compatible = "fsl,qoriq-mc-dpmac";
+				reg = <1>;
+			};
+
+			dpmac2: dpmac@2 {
+				compatible = "fsl,qoriq-mc-dpmac";
+				reg = <2>;
+			};
+
+			dpmac3: dpmac@3 {
+				compatible = "fsl,qoriq-mc-dpmac";
+				reg = <3>;
+			};
+
+			dpmac4: dpmac@4 {
+				compatible = "fsl,qoriq-mc-dpmac";
+				reg = <4>;
+			};
+
+			dpmac5: dpmac@5 {
+				compatible = "fsl,qoriq-mc-dpmac";
+				reg = <5>;
+			};
+
+			dpmac6: dpmac@6 {
+				compatible = "fsl,qoriq-mc-dpmac";
+				reg = <6>;
+			};
+
+			dpmac7: dpmac@7 {
+				compatible = "fsl,qoriq-mc-dpmac";
+				reg = <7>;
+			};
+
+			dpmac8: dpmac@8 {
+				compatible = "fsl,qoriq-mc-dpmac";
+				reg = <8>;
+			};
+
+			dpmac9: dpmac@9 {
+				compatible = "fsl,qoriq-mc-dpmac";
+				reg = <9>;
+			};
+
+			dpmac10: dpmac@a {
+				compatible = "fsl,qoriq-mc-dpmac";
+				reg = <0xa>;
+			};
+		};
+	};
+
 	psci {
 		compatible = "arm,psci-0.2";
 		method = "smc";
@@ -191,6 +262,12 @@
 			clocks = <&sysclk>;
 		};
 
+		dcfg: dcfg@1e00000 {
+			compatible = "fsl,ls1088a-dcfg", "syscon";
+			reg = <0x0 0x1e00000 0x0 0x10000>;
+			little-endian;
+		};
+
 		tmu: tmu@1f80000 {
 			compatible = "fsl,qoriq-tmu";
 			reg = <0x0 0x1f80000 0x0 0x10000>;
@@ -394,6 +471,26 @@
 			status = "disabled";
 		};
 
+		usb0: usb3@3100000 {
+			compatible = "snps,dwc3";
+			reg = <0x0 0x3100000 0x0 0x10000>;
+			interrupts = <0 80 IRQ_TYPE_LEVEL_HIGH>;
+			dr_mode = "host";
+			snps,quirk-frame-length-adjustment = <0x20>;
+			snps,dis_rxdet_inp3_quirk;
+			status = "disabled";
+		};
+
+		usb1: usb3@3110000 {
+			compatible = "snps,dwc3";
+			reg = <0x0 0x3110000 0x0 0x10000>;
+			interrupts = <0 81 IRQ_TYPE_LEVEL_HIGH>;
+			dr_mode = "host";
+			snps,quirk-frame-length-adjustment = <0x20>;
+			snps,dis_rxdet_inp3_quirk;
+			status = "disabled";
+		};
+
 		sata: sata@3200000 {
 			compatible = "fsl,ls1088a-ahci";
 			reg = <0x0 0x3200000 0x0 0x10000>,
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi
index 9a1d0d2ab1c3..5498c705ae6a 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi
@@ -95,6 +95,18 @@
 			};
 		};
 
+		i2c@2 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x02>;
+
+			ina220@40 {
+				compatible = "ti,ina220";
+				reg = <0x40>;
+				shunt-resistor = <500>;
+			};
+		};
+
 		i2c@3 {
 			#address-cells = <1>;
 			#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
index 97d768730952..c6999624ed8a 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
@@ -109,6 +109,7 @@
 			label = "user_led4";
 			/* gpio_190_user_led4 */
 			gpios = <&gpio23 6 0>;
+			panic-indicator;
 			linux,default-trigger = "cpu0";
 		};
 
diff --git a/arch/arm64/boot/dts/hisilicon/hi3660.dtsi b/arch/arm64/boot/dts/hisilicon/hi3660.dtsi
index ab0b95ba5ae5..63d4f9dca77f 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3660.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hi3660.dtsi
@@ -61,6 +61,7 @@
 			enable-method = "psci";
 			next-level-cache = <&A53_L2>;
 			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_0>;
+			capacity-dmips-mhz = <592>;
 		};
 
 		cpu1: cpu@1 {
@@ -70,6 +71,7 @@
 			enable-method = "psci";
 			next-level-cache = <&A53_L2>;
 			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_0>;
+			capacity-dmips-mhz = <592>;
 		};
 
 		cpu2: cpu@2 {
@@ -79,6 +81,7 @@
 			enable-method = "psci";
 			next-level-cache = <&A53_L2>;
 			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_0>;
+			capacity-dmips-mhz = <592>;
 		};
 
 		cpu3: cpu@3 {
@@ -88,6 +91,7 @@
 			enable-method = "psci";
 			next-level-cache = <&A53_L2>;
 			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_0>;
+			capacity-dmips-mhz = <592>;
 		};
 
 		cpu4: cpu@100 {
@@ -101,6 +105,7 @@
 					&CPU_SLEEP
 					&CLUSTER_SLEEP_1
 			>;
+			capacity-dmips-mhz = <1024>;
 		};
 
 		cpu5: cpu@101 {
@@ -114,6 +119,7 @@
 					&CPU_SLEEP
 					&CLUSTER_SLEEP_1
 			>;
+			capacity-dmips-mhz = <1024>;
 		};
 
 		cpu6: cpu@102 {
@@ -127,6 +133,7 @@
 					&CPU_SLEEP
 					&CLUSTER_SLEEP_1
 			>;
+			capacity-dmips-mhz = <1024>;
 		};
 
 		cpu7: cpu@103 {
@@ -140,6 +147,7 @@
 					&CPU_SLEEP
 					&CLUSTER_SLEEP_1
 			>;
+			capacity-dmips-mhz = <1024>;
 		};
 
 		idle-states {
@@ -203,21 +211,25 @@
 					 IRQ_TYPE_LEVEL_HIGH)>;
 	};
 
-	pmu {
-		compatible = "arm,armv8-pmuv3";
+	a53-pmu {
+		compatible = "arm,cortex-a53-pmu";
 		interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
+			     <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-affinity = <&cpu0>,
 				     <&cpu1>,
 				     <&cpu2>,
-				     <&cpu3>,
-				     <&cpu4>,
+				     <&cpu3>;
+	};
+
+	a73-pmu {
+		compatible = "arm,cortex-a73-pmu";
+		interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu4>,
 				     <&cpu5>,
 				     <&cpu6>,
 				     <&cpu7>;
diff --git a/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts b/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts
index a6fd13389f8d..4d5d644abb12 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts
@@ -146,6 +146,12 @@
 	status = "okay";
 };
 
+&sd0 {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	status = "okay";
+};
+
 &spi0 {
 	status = "okay";
 	label = "LS-SPI0";
diff --git a/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi b/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi
index 75865f8a862a..962bd79139e4 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi
@@ -192,6 +192,18 @@
 			status = "disabled";
 		};
 
+		sd0: mmc@9820000 {
+			compatible = "snps,dw-mshc";
+			reg = <0x9820000 0x10000>;
+			interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&crg HISTB_SDIO0_CIU_CLK>,
+				 <&crg HISTB_SDIO0_BIU_CLK>;
+			clock-names = "ciu", "biu";
+			resets = <&crg 0x9c 4>;
+			reset-names = "reset";
+			status = "disabled";
+		};
+
 		emmc: mmc@9830000 {
 			compatible = "snps,dw-mshc";
 			reg = <0x9830000 0x10000>;
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index 3aee6123d161..e94fa1a53192 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -359,6 +359,7 @@
 		user_led1 {
 			label = "user_led1";
 			gpios = <&gpio4 3 0>; /* <&gpio_user_led_4>; */
+			panic-indicator;
 			linux,default-trigger = "cpu0";
 		};
 
diff --git a/arch/arm64/boot/dts/marvell/armada-372x.dtsi b/arch/arm64/boot/dts/marvell/armada-372x.dtsi
index 59d7557d3b1b..2554e0baea6b 100644
--- a/arch/arm64/boot/dts/marvell/armada-372x.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-372x.dtsi
@@ -56,6 +56,7 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a53","arm,armv8";
 			reg = <0x1>;
+			clocks = <&nb_periph_clk 16>;
 			enable-method = "psci";
 		};
 	};
diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
index 90c26d616a54..375026867342 100644
--- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
@@ -65,6 +65,7 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0>;
+			clocks = <&nb_periph_clk 16>;
 			enable-method = "psci";
 		};
 	};
@@ -234,6 +235,12 @@
 				};
 			};
 
+			nb_pm: syscon@14000 {
+				compatible = "marvell,armada-3700-nb-pm",
+					     "syscon";
+				reg = <0x14000 0x60>;
+			};
+
 			pinctrl_sb: pinctrl@18800 {
 				compatible = "marvell,armada3710-sb-pinctrl",
 					     "syscon", "simple-mfd";
@@ -309,6 +316,20 @@
 				};
 			};
 
+			crypto: crypto@90000 {
+				compatible = "inside-secure,safexcel-eip97";
+				reg = <0x90000 0x20000>;
+				interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "mem", "ring0", "ring1",
+						  "ring2", "ring3", "eip";
+				clocks = <&nb_periph_clk 15>;
+			};
+
 			sdhci1: sdhci@d0000 {
 				compatible = "marvell,armada-3700-sdhci",
 					     "marvell,sdhci-xenon";
diff --git a/arch/arm64/boot/dts/marvell/armada-7040-db.dts b/arch/arm64/boot/dts/marvell/armada-7040-db.dts
index 52b5341cb270..3ae05eee2c9a 100644
--- a/arch/arm64/boot/dts/marvell/armada-7040-db.dts
+++ b/arch/arm64/boot/dts/marvell/armada-7040-db.dts
@@ -61,7 +61,13 @@
 		reg = <0x0 0x0 0x0 0x80000000>;
 	};
 
-	cpm_reg_usb3_0_vbus: cpm-usb3-0-vbus {
+	aliases {
+		ethernet0 = &cp0_eth0;
+		ethernet1 = &cp0_eth1;
+		ethernet2 = &cp0_eth2;
+	};
+
+	cp0_reg_usb3_0_vbus: cp0-usb3-0-vbus {
 		compatible = "regulator-fixed";
 		regulator-name = "usb3h0-vbus";
 		regulator-min-microvolt = <5000000>;
@@ -70,7 +76,7 @@
 		gpio = <&expander0 0 GPIO_ACTIVE_HIGH>;
 	};
 
-	cpm_reg_usb3_1_vbus: cpm-usb3-1-vbus {
+	cp0_reg_usb3_1_vbus: cp0-usb3-1-vbus {
 		compatible = "regulator-fixed";
 		regulator-name = "usb3h1-vbus";
 		regulator-min-microvolt = <5000000>;
@@ -79,14 +85,14 @@
 		gpio = <&expander0 1 GPIO_ACTIVE_HIGH>;
 	};
 
-	cpm_usb3_0_phy: cpm-usb3-0-phy {
+	cp0_usb3_0_phy: cp0-usb3-0-phy {
 		compatible = "usb-nop-xceiv";
-		vcc-supply = <&cpm_reg_usb3_0_vbus>;
+		vcc-supply = <&cp0_reg_usb3_0_vbus>;
 	};
 
-	cpm_usb3_1_phy: cpm-usb3-1-phy {
+	cp0_usb3_1_phy: cp0-usb3-1-phy {
 		compatible = "usb-nop-xceiv";
-		vcc-supply = <&cpm_reg_usb3_1_vbus>;
+		vcc-supply = <&cp0_reg_usb3_1_vbus>;
 	};
 };
 
@@ -129,11 +135,11 @@
 };
 
 
-&cpm_pcie2 {
+&cp0_pcie2 {
 	status = "okay";
 };
 
-&cpm_i2c0 {
+&cp0_i2c0 {
 	status = "okay";
 	clock-frequency = <100000>;
 
@@ -156,7 +162,7 @@
 	};
 };
 
-&cpm_nand {
+&cp0_nand {
 	/*
 	 * SPI on CPM and NAND have common pins on this board. We can
 	 * use only one at a time. To enable the NAND (whihch will
@@ -186,7 +192,7 @@
 };
 
 
-&cpm_spi1 {
+&cp0_spi1 {
 	status = "okay";
 
 	spi-flash@0 {
@@ -214,17 +220,17 @@
 	};
 };
 
-&cpm_sata0 {
+&cp0_sata0 {
 	status = "okay";
 };
 
-&cpm_usb3_0 {
-	usb-phy = <&cpm_usb3_0_phy>;
+&cp0_usb3_0 {
+	usb-phy = <&cp0_usb3_0_phy>;
 	status = "okay";
 };
 
-&cpm_usb3_1 {
-	usb-phy = <&cpm_usb3_1_phy>;
+&cp0_usb3_1 {
+	usb-phy = <&cp0_usb3_1_phy>;
 	status = "okay";
 };
 
@@ -235,14 +241,14 @@
 	non-removable;
 };
 
-&cpm_sdhci0 {
+&cp0_sdhci0 {
 	status = "okay";
 	bus-width = <4>;
 	no-1-8-v;
 	cd-gpios = <&expander0 12 GPIO_ACTIVE_LOW>;
 };
 
-&cpm_mdio {
+&cp0_mdio {
 	status = "okay";
 
 	phy0: ethernet-phy@0 {
@@ -253,28 +259,28 @@
 	};
 };
 
-&cpm_ethernet {
+&cp0_ethernet {
 	status = "okay";
 };
 
-&cpm_eth0 {
+&cp0_eth0 {
 	status = "okay";
 	/* Network PHY */
 	phy-mode = "10gbase-kr";
 	/* Generic PHY, providing serdes lanes */
-	phys = <&cpm_comphy2 0>;
+	phys = <&cp0_comphy2 0>;
 };
 
-&cpm_eth1 {
+&cp0_eth1 {
 	status = "okay";
 	/* Network PHY */
 	phy = <&phy0>;
 	phy-mode = "sgmii";
 	/* Generic PHY, providing serdes lanes */
-	phys = <&cpm_comphy0 1>;
+	phys = <&cp0_comphy0 1>;
 };
 
-&cpm_eth2 {
+&cp0_eth2 {
 	status = "okay";
 	phy = <&phy1>;
 	phy-mode = "rgmii-id";
diff --git a/arch/arm64/boot/dts/marvell/armada-70x0.dtsi b/arch/arm64/boot/dts/marvell/armada-70x0.dtsi
index 0e1a1e5be399..f63b4fbd642b 100644
--- a/arch/arm64/boot/dts/marvell/armada-70x0.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-70x0.dtsi
@@ -44,25 +44,46 @@
  * Device Tree file for the Armada 70x0 SoC
  */
 
-#include "armada-cp110-master.dtsi"
-
 / {
 	aliases {
-		gpio1 = &cpm_gpio1;
-		gpio2 = &cpm_gpio2;
+		gpio1 = &cp0_gpio1;
+		gpio2 = &cp0_gpio2;
+		spi1 = &cp0_spi0;
+		spi2 = &cp0_spi1;
 	};
 };
 
-&cpm_gpio1 {
+/*
+ * Instantiate the CP110
+ */
+#define CP110_NAME		cp0
+#define CP110_BASE		f2000000
+#define CP110_PCIE_IO_BASE	0xf9000000
+#define CP110_PCIE_MEM_BASE	0xf6000000
+#define CP110_PCIE0_BASE	f2600000
+#define CP110_PCIE1_BASE	f2620000
+#define CP110_PCIE2_BASE	f2640000
+
+#include "armada-cp110.dtsi"
+
+#undef CP110_NAME
+#undef CP110_BASE
+#undef CP110_PCIE_IO_BASE
+#undef CP110_PCIE_MEM_BASE
+#undef CP110_PCIE0_BASE
+#undef CP110_PCIE1_BASE
+#undef CP110_PCIE2_BASE
+
+&cp0_gpio1 {
 	status = "okay";
 };
 
-&cpm_gpio2 {
+&cp0_gpio2 {
 	status = "okay";
 };
 
-&cpm_syscon0 {
-	cpm_pinctrl: pinctrl {
+&cp0_syscon0 {
+	cp0_pinctrl: pinctrl {
 		compatible = "marvell,armada-7k-pinctrl";
 
 		nand_pins: nand-pins {
diff --git a/arch/arm64/boot/dts/marvell/armada-8020.dtsi b/arch/arm64/boot/dts/marvell/armada-8020.dtsi
index 0ba0bc942598..3318d6b0214b 100644
--- a/arch/arm64/boot/dts/marvell/armada-8020.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-8020.dtsi
@@ -60,6 +60,6 @@
  * oscillator so this one is let enabled.
  */
 
-&cpm_rtc {
+&cp0_rtc {
 	status = "disabled";
 };
diff --git a/arch/arm64/boot/dts/marvell/armada-8040-db.dts b/arch/arm64/boot/dts/marvell/armada-8040-db.dts
index d97b72bed662..dba55baff20f 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040-db.dts
+++ b/arch/arm64/boot/dts/marvell/armada-8040-db.dts
@@ -61,46 +61,53 @@
 		reg = <0x0 0x0 0x0 0x80000000>;
 	};
 
-	cpm_reg_usb3_0_vbus: cpm-usb3-0-vbus {
+	aliases {
+		ethernet0 = &cp0_eth0;
+		ethernet1 = &cp0_eth2;
+		ethernet2 = &cp1_eth0;
+		ethernet3 = &cp1_eth1;
+	};
+
+	cp0_reg_usb3_0_vbus: cp0-usb3-0-vbus {
 		compatible = "regulator-fixed";
-		regulator-name = "cpm-usb3h0-vbus";
+		regulator-name = "cp0-usb3h0-vbus";
 		regulator-min-microvolt = <5000000>;
 		regulator-max-microvolt = <5000000>;
 		enable-active-high;
 		gpio = <&expander0 0 GPIO_ACTIVE_HIGH>;
 	};
 
-	cpm_reg_usb3_1_vbus: cpm-usb3-1-vbus {
+	cp0_reg_usb3_1_vbus: cp0-usb3-1-vbus {
 		compatible = "regulator-fixed";
-		regulator-name = "cpm-usb3h1-vbus";
+		regulator-name = "cp0-usb3h1-vbus";
 		regulator-min-microvolt = <5000000>;
 		regulator-max-microvolt = <5000000>;
 		enable-active-high;
 		gpio = <&expander0 1 GPIO_ACTIVE_HIGH>;
 	};
 
-	cpm_usb3_0_phy: cpm-usb3-0-phy {
+	cp0_usb3_0_phy: cp0-usb3-0-phy {
 		compatible = "usb-nop-xceiv";
-		vcc-supply = <&cpm_reg_usb3_0_vbus>;
+		vcc-supply = <&cp0_reg_usb3_0_vbus>;
 	};
 
-	cpm_usb3_1_phy: cpm-usb3-1-phy {
+	cp0_usb3_1_phy: cp0-usb3-1-phy {
 		compatible = "usb-nop-xceiv";
-		vcc-supply = <&cpm_reg_usb3_1_vbus>;
+		vcc-supply = <&cp0_reg_usb3_1_vbus>;
 	};
 
-	cps_reg_usb3_0_vbus: cps-usb3-0-vbus {
+	cp1_reg_usb3_0_vbus: cp1-usb3-0-vbus {
 		compatible = "regulator-fixed";
-		regulator-name = "cps-usb3h0-vbus";
+		regulator-name = "cp1-usb3h0-vbus";
 		regulator-min-microvolt = <5000000>;
 		regulator-max-microvolt = <5000000>;
 		enable-active-high;
 		gpio = <&expander1 0 GPIO_ACTIVE_HIGH>;
 	};
 
-	cps_usb3_0_phy: cps-usb3-0-phy {
+	cp1_usb3_0_phy: cp1-usb3-0-phy {
 		compatible = "usb-nop-xceiv";
-		vcc-supply = <&cps_reg_usb3_0_vbus>;
+		vcc-supply = <&cp1_reg_usb3_0_vbus>;
 	};
 };
 
@@ -144,16 +151,16 @@
 };
 
 /* CON6 on CP0 expansion */
-&cpm_pcie0 {
+&cp0_pcie0 {
 	status = "okay";
 };
 
 /* CON5 on CP0 expansion */
-&cpm_pcie2 {
+&cp0_pcie2 {
 	status = "okay";
 };
 
-&cpm_i2c0 {
+&cp0_i2c0 {
 	status = "okay";
 	clock-frequency = <100000>;
 
@@ -178,23 +185,23 @@
 };
 
 /* CON4 on CP0 expansion */
-&cpm_sata0 {
+&cp0_sata0 {
 	status = "okay";
 };
 
 /* CON9 on CP0 expansion */
-&cpm_usb3_0 {
-	usb-phy = <&cpm_usb3_0_phy>;
+&cp0_usb3_0 {
+	usb-phy = <&cp0_usb3_0_phy>;
 	status = "okay";
 };
 
 /* CON10 on CP0 expansion */
-&cpm_usb3_1 {
-	usb-phy = <&cpm_usb3_1_phy>;
+&cp0_usb3_1 {
+	usb-phy = <&cp0_usb3_1_phy>;
 	status = "okay";
 };
 
-&cpm_mdio {
+&cp0_mdio {
 	status = "okay";
 
 	phy1: ethernet-phy@1 {
@@ -202,42 +209,42 @@
 	};
 };
 
-&cpm_ethernet {
+&cp0_ethernet {
 	status = "okay";
 };
 
-&cpm_eth0 {
+&cp0_eth0 {
 	status = "okay";
 	phy-mode = "10gbase-kr";
 };
 
-&cpm_eth2 {
+&cp0_eth2 {
 	status = "okay";
 	phy = <&phy1>;
 	phy-mode = "rgmii-id";
 };
 
 /* CON6 on CP1 expansion */
-&cps_pcie0 {
+&cp1_pcie0 {
 	status = "okay";
 };
 
 /* CON7 on CP1 expansion */
-&cps_pcie1 {
+&cp1_pcie1 {
 	status = "okay";
 };
 
 /* CON5 on CP1 expansion */
-&cps_pcie2 {
+&cp1_pcie2 {
 	status = "okay";
 };
 
-&cps_i2c0 {
+&cp1_i2c0 {
 	status = "okay";
 	clock-frequency = <100000>;
 };
 
-&cps_spi1 {
+&cp1_spi1 {
 	status = "okay";
 
 	spi-flash@0 {
@@ -268,23 +275,51 @@
 	};
 };
 
+/*
+ * Proper NAND usage will require DPR-76 to be in position 1-2, which disables
+ * MDIO signal of CP1.
+ */
+&cp1_nand {
+	num-cs = <1>;
+	pinctrl-0 = <&nand_pins>, <&nand_rb>;
+	pinctrl-names = "default";
+	nand-ecc-strength = <4>;
+	nand-ecc-step-size = <512>;
+	marvell,nand-enable-arbiter;
+	marvell,system-controller = <&cp1_syscon0>;
+	nand-on-flash-bbt;
+
+	partition@0 {
+		label = "U-Boot";
+		reg = <0 0x200000>;
+	};
+	partition@200000 {
+		label = "Linux";
+		reg = <0x200000 0xe00000>;
+	};
+	partition@1000000 {
+		label = "Filesystem";
+		reg = <0x1000000 0x3f000000>;
+	};
+};
+
 /* CON4 on CP1 expansion */
-&cps_sata0 {
+&cp1_sata0 {
 	status = "okay";
 };
 
 /* CON9 on CP1 expansion */
-&cps_usb3_0 {
-	usb-phy = <&cps_usb3_0_phy>;
+&cp1_usb3_0 {
+	usb-phy = <&cp1_usb3_0_phy>;
 	status = "okay";
 };
 
 /* CON10 on CP1 expansion */
-&cps_usb3_1 {
+&cp1_usb3_1 {
 	status = "okay";
 };
 
-&cps_mdio {
+&cp1_mdio {
 	status = "okay";
 
 	phy0: ethernet-phy@0 {
@@ -292,16 +327,16 @@
 	};
 };
 
-&cps_ethernet {
+&cp1_ethernet {
 	status = "okay";
 };
 
-&cps_eth0 {
+&cp1_eth0 {
 	status = "okay";
 	phy-mode = "10gbase-kr";
 };
 
-&cps_eth1 {
+&cp1_eth1 {
 	status = "okay";
 	phy = <&phy0>;
 	phy-mode = "rgmii-id";
@@ -313,7 +348,7 @@
 	non-removable;
 };
 
-&cpm_sdhci0 {
+&cp0_sdhci0 {
 	status = "okay";
 	bus-width = <8>;
 	non-removable;
diff --git a/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts b/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts
index b3350827ee55..626e9d0462c3 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts
+++ b/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts
@@ -62,6 +62,12 @@
 		reg = <0x0 0x0 0x0 0x80000000>;
 	};
 
+	aliases {
+		ethernet0 = &cp0_eth0;
+		ethernet1 = &cp1_eth0;
+		ethernet2 = &cp1_eth1;
+	};
+
 	/* Regulator labels correspond with schematics */
 	v_3_3: regulator-3-3v {
 		compatible = "regulator-fixed";
@@ -84,9 +90,9 @@
 	v_5v0_usb3_hst_vbus: regulator-usb3-vbus0 {
 		compatible = "regulator-fixed";
 		enable-active-high;
-		gpio = <&cpm_gpio2 15 GPIO_ACTIVE_HIGH>;
+		gpio = <&cp0_gpio2 15 GPIO_ACTIVE_HIGH>;
 		pinctrl-names = "default";
-		pinctrl-0 = <&cpm_xhci_vbus_pins>;
+		pinctrl-0 = <&cp0_xhci_vbus_pins>;
 		regulator-name = "v_5v0_usb3_hst_vbus";
 		regulator-min-microvolt = <5000000>;
 		regulator-max-microvolt = <5000000>;
@@ -120,17 +126,17 @@
 	vqmmc-supply = <&v_vddo_h>;
 };
 
-&cpm_i2c0 {
+&cp0_i2c0 {
 	clock-frequency = <100000>;
 	pinctrl-names = "default";
-	pinctrl-0 = <&cpm_i2c0_pins>;
+	pinctrl-0 = <&cp0_i2c0_pins>;
 	status = "okay";
 };
 
-&cpm_i2c1 {
+&cp0_i2c1 {
 	clock-frequency = <100000>;
 	pinctrl-names = "default";
-	pinctrl-0 = <&cpm_i2c1_pins>;
+	pinctrl-0 = <&cp0_i2c1_pins>;
 	status = "okay";
 
 	i2c-switch@70 {
@@ -157,9 +163,9 @@
 	};
 };
 
-&cpm_mdio {
+&cp0_mdio {
 	pinctrl-names = "default";
-	pinctrl-0 = <&cpm_ge_mdio_pins>;
+	pinctrl-0 = <&cp0_ge_mdio_pins>;
 	status = "okay";
 
 	ge_phy: ethernet-phy@0 {
@@ -167,44 +173,44 @@
 	};
 };
 
-&cpm_pcie0 {
+&cp0_pcie0 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&cpm_pcie_pins>;
+	pinctrl-0 = <&cp0_pcie_pins>;
 	num-lanes = <4>;
 	num-viewport = <8>;
-	reset-gpio = <&cpm_gpio1 20 GPIO_ACTIVE_LOW>;
+	reset-gpio = <&cp0_gpio1 20 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
-&cpm_pinctrl {
-	cpm_ge_mdio_pins: ge-mdio-pins {
+&cp0_pinctrl {
+	cp0_ge_mdio_pins: ge-mdio-pins {
 		marvell,pins = "mpp32", "mpp34";
 		marvell,function = "ge";
 	};
-	cpm_i2c1_pins: i2c1-pins {
+	cp0_i2c1_pins: i2c1-pins {
 		marvell,pins = "mpp35", "mpp36";
 		marvell,function = "i2c1";
 	};
-	cpm_i2c0_pins: i2c0-pins {
+	cp0_i2c0_pins: i2c0-pins {
 		marvell,pins = "mpp37", "mpp38";
 		marvell,function = "i2c0";
 	};
-	cpm_xhci_vbus_pins: xhci0-vbus-pins {
+	cp0_xhci_vbus_pins: xhci0-vbus-pins {
 		marvell,pins = "mpp47";
 		marvell,function = "gpio";
 	};
-	cpm_pcie_pins: pcie-pins {
+	cp0_pcie_pins: pcie-pins {
 		marvell,pins = "mpp52";
 		marvell,function = "gpio";
 	};
-	cpm_sdhci_pins: sdhci-pins {
+	cp0_sdhci_pins: sdhci-pins {
 		marvell,pins = "mpp55", "mpp56", "mpp57", "mpp58", "mpp59",
 			       "mpp60", "mpp61";
 		marvell,function = "sdio";
 	};
 };
 
-&cpm_xmdio {
+&cp0_xmdio {
 	status = "okay";
 
 	phy0: ethernet-phy@0 {
@@ -218,83 +224,83 @@
 	};
 };
 
-&cpm_ethernet {
+&cp0_ethernet {
 	status = "okay";
 };
 
-&cpm_eth0 {
+&cp0_eth0 {
 	status = "okay";
 	/* Network PHY */
 	phy = <&phy0>;
 	phy-mode = "10gbase-kr";
 	/* Generic PHY, providing serdes lanes */
-	phys = <&cpm_comphy4 0>;
+	phys = <&cp0_comphy4 0>;
 };
 
-&cpm_sata0 {
+&cp0_sata0 {
 	/* CPM Lane 0 - U29 */
 	status = "okay";
 };
 
-&cpm_sdhci0 {
+&cp0_sdhci0 {
 	/* U6 */
 	broken-cd;
 	bus-width = <4>;
 	pinctrl-names = "default";
-	pinctrl-0 = <&cpm_sdhci_pins>;
+	pinctrl-0 = <&cp0_sdhci_pins>;
 	status = "okay";
 	vqmmc-supply = <&v_3_3>;
 };
 
-&cpm_usb3_0 {
+&cp0_usb3_0 {
 	/* J38? - USB2.0 only */
 	status = "okay";
 };
 
-&cpm_usb3_1 {
+&cp0_usb3_1 {
 	/* J38? - USB2.0 only */
 	status = "okay";
 };
 
-&cps_ethernet {
+&cp1_ethernet {
 	status = "okay";
 };
 
-&cps_eth0 {
+&cp1_eth0 {
 	status = "okay";
 	/* Network PHY */
 	phy = <&phy8>;
 	phy-mode = "10gbase-kr";
 	/* Generic PHY, providing serdes lanes */
-	phys = <&cps_comphy4 0>;
+	phys = <&cp1_comphy4 0>;
 };
 
-&cps_eth1 {
+&cp1_eth1 {
 	/* CPS Lane 0 - J5 (Gigabit RJ45) */
 	status = "okay";
 	/* Network PHY */
 	phy = <&ge_phy>;
 	phy-mode = "sgmii";
 	/* Generic PHY, providing serdes lanes */
-	phys = <&cps_comphy0 1>;
+	phys = <&cp1_comphy0 1>;
 };
 
-&cps_pinctrl {
-	cps_spi1_pins: spi1-pins {
+&cp1_pinctrl {
+	cp1_spi1_pins: spi1-pins {
 		marvell,pins = "mpp12", "mpp13", "mpp14", "mpp15", "mpp16";
 		marvell,function = "spi1";
 	};
 };
 
-&cps_sata0 {
+&cp1_sata0 {
 	/* CPS Lane 1 - U32 */
 	/* CPS Lane 3 - U31 */
 	status = "okay";
 };
 
-&cps_spi1 {
+&cp1_spi1 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&cps_spi1_pins>;
+	pinctrl-0 = <&cp1_spi1_pins>;
 	status = "okay";
 
 	spi-flash@0 {
@@ -304,7 +310,7 @@
 	};
 };
 
-&cps_usb3_0 {
+&cp1_usb3_0 {
 	/* CPS Lane 2 - CON7 */
 	usb-phy = <&usb3h0_phy>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/marvell/armada-8040.dtsi b/arch/arm64/boot/dts/marvell/armada-8040.dtsi
index 60fe84f5cbcc..83d2b40e5981 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-8040.dtsi
@@ -59,6 +59,6 @@
  * disable it. However, the RTC clock in CP slave is connected to the
  * oscillator so this one is let enabled.
  */
-&cpm_rtc {
+&cp0_rtc {
 	status = "disabled";
 };
diff --git a/arch/arm64/boot/dts/marvell/armada-80x0.dtsi b/arch/arm64/boot/dts/marvell/armada-80x0.dtsi
index 666ebe96ba0d..e9c84a1d3c4d 100644
--- a/arch/arm64/boot/dts/marvell/armada-80x0.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-80x0.dtsi
@@ -44,33 +44,104 @@
  * Device Tree file for the Armada 80x0 SoC family
  */
 
-#include "armada-cp110-master.dtsi"
-#include "armada-cp110-slave.dtsi"
-
 / {
 	aliases {
-		gpio1 = &cps_gpio1;
-		gpio2 = &cpm_gpio2;
+		gpio1 = &cp1_gpio1;
+		gpio2 = &cp0_gpio2;
+		spi1 = &cp0_spi0;
+		spi2 = &cp0_spi1;
+		spi3 = &cp1_spi0;
+		spi4 = &cp1_spi1;
 	};
 };
 
+/*
+ * Instantiate the master CP110
+ */
+#define CP110_NAME		cp0
+#define CP110_BASE		f2000000
+#define CP110_PCIE_IO_BASE	0xf9000000
+#define CP110_PCIE_MEM_BASE	0xf6000000
+#define CP110_PCIE0_BASE	f2600000
+#define CP110_PCIE1_BASE	f2620000
+#define CP110_PCIE2_BASE	f2640000
+
+#include "armada-cp110.dtsi"
+
+#undef CP110_NAME
+#undef CP110_BASE
+#undef CP110_PCIE_IO_BASE
+#undef CP110_PCIE_MEM_BASE
+#undef CP110_PCIE0_BASE
+#undef CP110_PCIE1_BASE
+#undef CP110_PCIE2_BASE
+
+/*
+ * Instantiate the slave CP110
+ */
+#define CP110_NAME		cp1
+#define CP110_BASE		f4000000
+#define CP110_PCIE_IO_BASE	0xfd000000
+#define CP110_PCIE_MEM_BASE	0xfa000000
+#define CP110_PCIE0_BASE	f4600000
+#define CP110_PCIE1_BASE	f4620000
+#define CP110_PCIE2_BASE	f4640000
+
+#include "armada-cp110.dtsi"
+
+#undef CP110_NAME
+#undef CP110_BASE
+#undef CP110_PCIE_IO_BASE
+#undef CP110_PCIE_MEM_BASE
+#undef CP110_PCIE0_BASE
+#undef CP110_PCIE1_BASE
+#undef CP110_PCIE2_BASE
+
 /* The 80x0 has two CP blocks, but uses only one block from each. */
-&cps_gpio1 {
+&cp1_gpio1 {
 	status = "okay";
 };
 
-&cpm_gpio2 {
+&cp0_gpio2 {
 	status = "okay";
 };
 
-&cpm_syscon0 {
-	cpm_pinctrl: pinctrl {
+&cp0_syscon0 {
+	cp0_pinctrl: pinctrl {
 		compatible = "marvell,armada-8k-cpm-pinctrl";
 	};
 };
 
-&cps_syscon0 {
-	cps_pinctrl: pinctrl {
+&cp1_syscon0 {
+	cp1_pinctrl: pinctrl {
 		compatible = "marvell,armada-8k-cps-pinctrl";
+
+		nand_pins: nand-pins {
+			marvell,pins =
+			"mpp0", "mpp1", "mpp2", "mpp3",
+			"mpp4", "mpp5", "mpp6", "mpp7",
+			"mpp8", "mpp9", "mpp10", "mpp11",
+			"mpp15", "mpp16", "mpp17", "mpp18",
+			"mpp19", "mpp20", "mpp21", "mpp22",
+			"mpp23", "mpp24", "mpp25", "mpp26",
+			"mpp27";
+			marvell,function = "dev";
+		};
+
+		nand_rb: nand-rb {
+			marvell,pins = "mpp13", "mpp12";
+			marvell,function = "nf";
+		};
 	};
 };
+
+&cp1_crypto {
+	/*
+	 * The cryptographic engine found on the cp110
+	 * master is enabled by default at the SoC
+	 * level. Because it is not possible as of now
+	 * to enable two cryptographic engines in
+	 * parallel, disable this one by default.
+	 */
+	status = "disabled";
+};
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
index 1c4dd8ab9ad5..f9b66b81f9fc 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
@@ -58,6 +58,7 @@
 		serial0 = &uart0;
 		serial1 = &uart1;
 		gpio0 = &ap_gpio;
+		spi0 = &spi0;
 	};
 
 	psci {
@@ -203,7 +204,6 @@
 				reg = <0x510600 0x50>;
 				#address-cells = <1>;
 				#size-cells = <0>;
-				cell-index = <0>;
 				interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&ap_clk 3>;
 				status = "disabled";
@@ -241,7 +241,7 @@
 
 			};
 
-			watchdog: watchdog@600000 {
+			watchdog: watchdog@610000 {
 				compatible = "arm,sbsa-gwdt";
 				reg = <0x610000 0x1000>, <0x600000 0x1000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
@@ -285,6 +285,12 @@
 					gpio-ranges = <&ap_pinctrl 0 0 20>;
 				};
 			};
+
+			ap_thermal: thermal@6f808c {
+				compatible = "marvell,armada-ap806-thermal";
+				reg = <0x6f808c 0x4>,
+				      <0x6f8084 0x8>;
+			};
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/marvell/armada-common.dtsi b/arch/arm64/boot/dts/marvell/armada-common.dtsi
new file mode 100644
index 000000000000..c6dd1d81c68d
--- /dev/null
+++ b/arch/arm64/boot/dts/marvell/armada-common.dtsi
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR X11)
+/*
+ * Copyright (C) 2016 Marvell Technology Group Ltd.
+ */
+
+/* Common definitions used by Armada 7K/8K DTs */
+#define PASTER(x, y) x ## y
+#define EVALUATOR(x, y) PASTER(x, y)
+#define CP110_LABEL(name) EVALUATOR(CP110_NAME, EVALUATOR(_, name))
+#define ADDRESSIFY(addr) EVALUATOR(0x, addr)
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
deleted file mode 100644
index e3b64d03fbd8..000000000000
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ /dev/null
@@ -1,443 +0,0 @@
-/*
- * Copyright (C) 2016 Marvell Technology Group Ltd.
- *
- * This file is dual-licensed: you can use it either under the terms
- * of the GPLv2 or the X11 license, at your option. Note that this dual
- * licensing only applies to this file, and not this project as a
- * whole.
- *
- *  a) This library is free software; you can redistribute it and/or
- *     modify it under the terms of the GNU General Public License as
- *     published by the Free Software Foundation; either version 2 of the
- *     License, or (at your option) any later version.
- *
- *     This library is distributed in the hope that it will be useful,
- *     but WITHOUT ANY WARRANTY; without even the implied warranty of
- *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *     GNU General Public License for more details.
- *
- * Or, alternatively,
- *
- *  b) Permission is hereby granted, free of charge, to any person
- *     obtaining a copy of this software and associated documentation
- *     files (the "Software"), to deal in the Software without
- *     restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or
- *     sell copies of the Software, and to permit persons to whom the
- *     Software is furnished to do so, subject to the following
- *     conditions:
- *
- *     The above copyright notice and this permission notice shall be
- *     included in all copies or substantial portions of the Software.
- *
- *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
- *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
- *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
- *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- *     OTHER DEALINGS IN THE SOFTWARE.
- */
-
-/*
- * Device Tree file for Marvell Armada CP110 Master.
- */
-
-#define ICU_GRP_NSR 0x0
-
-/ {
-	cp110-master {
-		#address-cells = <2>;
-		#size-cells = <2>;
-		compatible = "simple-bus";
-		interrupt-parent = <&cpm_icu>;
-		ranges;
-
-		config-space@f2000000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "simple-bus";
-			ranges = <0x0 0x0 0xf2000000 0x2000000>;
-
-			cpm_ethernet: ethernet@0 {
-				compatible = "marvell,armada-7k-pp22";
-				reg = <0x0 0x100000>, <0x129000 0xb000>;
-				clocks = <&cpm_clk 1 3>, <&cpm_clk 1 9>, <&cpm_clk 1 5>;
-				clock-names = "pp_clk", "gop_clk", "mg_clk";
-				marvell,system-controller = <&cpm_syscon0>;
-				status = "disabled";
-				dma-coherent;
-
-				cpm_eth0: eth0 {
-					interrupts = <ICU_GRP_NSR 39 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 43 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 47 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 51 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 55 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 129 IRQ_TYPE_LEVEL_HIGH>;
-					interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2",
-							  "tx-cpu3", "rx-shared", "link";
-					port-id = <0>;
-					gop-port-id = <0>;
-					status = "disabled";
-				};
-
-				cpm_eth1: eth1 {
-					interrupts = <ICU_GRP_NSR 40 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 44 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 48 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 52 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 56 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 128 IRQ_TYPE_LEVEL_HIGH>;
-					interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2",
-							  "tx-cpu3", "rx-shared", "link";
-					port-id = <1>;
-					gop-port-id = <2>;
-					status = "disabled";
-				};
-
-				cpm_eth2: eth2 {
-					interrupts = <ICU_GRP_NSR 41 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 45 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 49 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 53 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 57 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 127 IRQ_TYPE_LEVEL_HIGH>;
-					interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2",
-							  "tx-cpu3", "rx-shared", "link";
-					port-id = <2>;
-					gop-port-id = <3>;
-					status = "disabled";
-				};
-			};
-
-			cpm_comphy: phy@120000 {
-				compatible = "marvell,comphy-cp110";
-				reg = <0x120000 0x6000>;
-				marvell,system-controller = <&cpm_syscon0>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				cpm_comphy0: phy@0 {
-					reg = <0>;
-					#phy-cells = <1>;
-				};
-
-				cpm_comphy1: phy@1 {
-					reg = <1>;
-					#phy-cells = <1>;
-				};
-
-				cpm_comphy2: phy@2 {
-					reg = <2>;
-					#phy-cells = <1>;
-				};
-
-				cpm_comphy3: phy@3 {
-					reg = <3>;
-					#phy-cells = <1>;
-				};
-
-				cpm_comphy4: phy@4 {
-					reg = <4>;
-					#phy-cells = <1>;
-				};
-
-				cpm_comphy5: phy@5 {
-					reg = <5>;
-					#phy-cells = <1>;
-				};
-			};
-
-			cpm_mdio: mdio@12a200 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "marvell,orion-mdio";
-				reg = <0x12a200 0x10>;
-				clocks = <&cpm_clk 1 9>, <&cpm_clk 1 5>;
-				status = "disabled";
-			};
-
-			cpm_xmdio: mdio@12a600 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "marvell,xmdio";
-				reg = <0x12a600 0x10>;
-				status = "disabled";
-			};
-
-			cpm_icu: interrupt-controller@1e0000 {
-				compatible = "marvell,cp110-icu";
-				reg = <0x1e0000 0x10>;
-				#interrupt-cells = <3>;
-				interrupt-controller;
-				msi-parent = <&gicp>;
-			};
-
-			cpm_rtc: rtc@284000 {
-				compatible = "marvell,armada-8k-rtc";
-				reg = <0x284000 0x20>, <0x284080 0x24>;
-				reg-names = "rtc", "rtc-soc";
-				interrupts = <ICU_GRP_NSR 77 IRQ_TYPE_LEVEL_HIGH>;
-			};
-
-			cpm_syscon0: system-controller@440000 {
-				compatible = "syscon", "simple-mfd";
-				reg = <0x440000 0x2000>;
-
-				cpm_clk: clock {
-					compatible = "marvell,cp110-clock";
-					#clock-cells = <2>;
-				};
-
-				cpm_gpio1: gpio@100 {
-					compatible = "marvell,armada-8k-gpio";
-					offset = <0x100>;
-					ngpios = <32>;
-					gpio-controller;
-					#gpio-cells = <2>;
-					gpio-ranges = <&cpm_pinctrl 0 0 32>;
-					interrupt-controller;
-					interrupts = <ICU_GRP_NSR 86 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 85 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 84 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 83 IRQ_TYPE_LEVEL_HIGH>;
-					status = "disabled";
-				};
-
-				cpm_gpio2: gpio@140 {
-					compatible = "marvell,armada-8k-gpio";
-					offset = <0x140>;
-					ngpios = <31>;
-					gpio-controller;
-					#gpio-cells = <2>;
-					gpio-ranges = <&cpm_pinctrl 0 32 31>;
-					interrupt-controller;
-					interrupts = <ICU_GRP_NSR 82 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 81 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 80 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 79 IRQ_TYPE_LEVEL_HIGH>;
-					status = "disabled";
-				};
-			};
-
-			cpm_usb3_0: usb3@500000 {
-				compatible = "marvell,armada-8k-xhci",
-					     "generic-xhci";
-				reg = <0x500000 0x4000>;
-				dma-coherent;
-				interrupts = <ICU_GRP_NSR 106 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cpm_clk 1 22>;
-				status = "disabled";
-			};
-
-			cpm_usb3_1: usb3@510000 {
-				compatible = "marvell,armada-8k-xhci",
-					     "generic-xhci";
-				reg = <0x510000 0x4000>;
-				dma-coherent;
-				interrupts = <ICU_GRP_NSR 105 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cpm_clk 1 23>;
-				status = "disabled";
-			};
-
-			cpm_sata0: sata@540000 {
-				compatible = "marvell,armada-8k-ahci",
-					     "generic-ahci";
-				reg = <0x540000 0x30000>;
-				interrupts = <ICU_GRP_NSR 107 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cpm_clk 1 15>;
-				status = "disabled";
-			};
-
-			cpm_xor0: xor@6a0000 {
-				compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
-				reg = <0x6a0000 0x1000>,
-				      <0x6b0000 0x1000>;
-				dma-coherent;
-				msi-parent = <&gic_v2m0>;
-				clocks = <&cpm_clk 1 8>;
-			};
-
-			cpm_xor1: xor@6c0000 {
-				compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
-				reg = <0x6c0000 0x1000>,
-				      <0x6d0000 0x1000>;
-				dma-coherent;
-				msi-parent = <&gic_v2m0>;
-				clocks = <&cpm_clk 1 7>;
-			};
-
-			cpm_spi0: spi@700600 {
-				compatible = "marvell,armada-380-spi";
-				reg = <0x700600 0x50>;
-				#address-cells = <0x1>;
-				#size-cells = <0x0>;
-				cell-index = <1>;
-				clocks = <&cpm_clk 1 21>;
-				status = "disabled";
-			};
-
-			cpm_spi1: spi@700680 {
-				compatible = "marvell,armada-380-spi";
-				reg = <0x700680 0x50>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-				cell-index = <2>;
-				clocks = <&cpm_clk 1 21>;
-				status = "disabled";
-			};
-
-			cpm_i2c0: i2c@701000 {
-				compatible = "marvell,mv78230-i2c";
-				reg = <0x701000 0x20>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-				interrupts = <ICU_GRP_NSR 120 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cpm_clk 1 21>;
-				status = "disabled";
-			};
-
-			cpm_i2c1: i2c@701100 {
-				compatible = "marvell,mv78230-i2c";
-				reg = <0x701100 0x20>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-				interrupts = <ICU_GRP_NSR 121 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cpm_clk 1 21>;
-				status = "disabled";
-			};
-
-			cpm_nand: nand@720000 {
-				/*
-				 * Due to the limiation of the pin available
-				 * this controller is only usable on the CPM
-				 * for A7K and on the CPS for A8K.
-				 */
-				compatible = "marvell,armada-8k-nand",
-					     "marvell,armada370-nand";
-				reg = <0x720000 0x54>;
-				#address-cells = <1>;
-				#size-cells = <1>;
-				interrupts = <ICU_GRP_NSR 115 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cpm_clk 1 2>;
-				marvell,system-controller = <&cpm_syscon0>;
-				status = "disabled";
-			};
-
-			cpm_trng: trng@760000 {
-				compatible = "marvell,armada-8k-rng", "inside-secure,safexcel-eip76";
-				reg = <0x760000 0x7d>;
-				interrupts = <ICU_GRP_NSR 95 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cpm_clk 1 25>;
-				status = "okay";
-			};
-
-			cpm_sdhci0: sdhci@780000 {
-				compatible = "marvell,armada-cp110-sdhci";
-				reg = <0x780000 0x300>;
-				interrupts = <ICU_GRP_NSR 27 IRQ_TYPE_LEVEL_HIGH>;
-				clock-names = "core";
-				clocks = <&cpm_clk 1 4>;
-				dma-coherent;
-				status = "disabled";
-			};
-
-			cpm_crypto: crypto@800000 {
-				compatible = "inside-secure,safexcel-eip197";
-				reg = <0x800000 0x200000>;
-				interrupts = <ICU_GRP_NSR 87 IRQ_TYPE_LEVEL_HIGH>,
-					     <ICU_GRP_NSR 88 IRQ_TYPE_LEVEL_HIGH>,
-					     <ICU_GRP_NSR 89 IRQ_TYPE_LEVEL_HIGH>,
-					     <ICU_GRP_NSR 90 IRQ_TYPE_LEVEL_HIGH>,
-					     <ICU_GRP_NSR 91 IRQ_TYPE_LEVEL_HIGH>,
-					     <ICU_GRP_NSR 92 IRQ_TYPE_LEVEL_HIGH>;
-				interrupt-names = "mem", "ring0", "ring1",
-				"ring2", "ring3", "eip";
-				clocks = <&cpm_clk 1 26>;
-				dma-coherent;
-			};
-		};
-
-		cpm_pcie0: pcie@f2600000 {
-			compatible = "marvell,armada8k-pcie", "snps,dw-pcie";
-			reg = <0 0xf2600000 0 0x10000>,
-			      <0 0xf6f00000 0 0x80000>;
-			reg-names = "ctrl", "config";
-			#address-cells = <3>;
-			#size-cells = <2>;
-			#interrupt-cells = <1>;
-			device_type = "pci";
-			dma-coherent;
-			msi-parent = <&gic_v2m0>;
-
-			bus-range = <0 0xff>;
-			ranges =
-				/* downstream I/O */
-				<0x81000000 0 0xf9000000 0  0xf9000000 0 0x10000
-				/* non-prefetchable memory */
-				0x82000000 0 0xf6000000 0  0xf6000000 0 0xf00000>;
-			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts = <ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
-			num-lanes = <1>;
-			clocks = <&cpm_clk 1 13>;
-			status = "disabled";
-		};
-
-		cpm_pcie1: pcie@f2620000 {
-			compatible = "marvell,armada8k-pcie", "snps,dw-pcie";
-			reg = <0 0xf2620000 0 0x10000>,
-			      <0 0xf7f00000 0 0x80000>;
-			reg-names = "ctrl", "config";
-			#address-cells = <3>;
-			#size-cells = <2>;
-			#interrupt-cells = <1>;
-			device_type = "pci";
-			dma-coherent;
-			msi-parent = <&gic_v2m0>;
-
-			bus-range = <0 0xff>;
-			ranges =
-				/* downstream I/O */
-				<0x81000000 0 0xf9010000 0  0xf9010000 0 0x10000
-				/* non-prefetchable memory */
-				0x82000000 0 0xf7000000 0  0xf7000000 0 0xf00000>;
-			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts = <ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
-
-			num-lanes = <1>;
-			clocks = <&cpm_clk 1 11>;
-			status = "disabled";
-		};
-
-		cpm_pcie2: pcie@f2640000 {
-			compatible = "marvell,armada8k-pcie", "snps,dw-pcie";
-			reg = <0 0xf2640000 0 0x10000>,
-			      <0 0xf8f00000 0 0x80000>;
-			reg-names = "ctrl", "config";
-			#address-cells = <3>;
-			#size-cells = <2>;
-			#interrupt-cells = <1>;
-			device_type = "pci";
-			dma-coherent;
-			msi-parent = <&gic_v2m0>;
-
-			bus-range = <0 0xff>;
-			ranges =
-				/* downstream I/O */
-				<0x81000000 0 0xf9020000 0  0xf9020000 0 0x10000
-				/* non-prefetchable memory */
-				0x82000000 0 0xf8000000 0  0xf8000000 0 0xf00000>;
-			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts = <ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
-
-			num-lanes = <1>;
-			clocks = <&cpm_clk 1 12>;
-			status = "disabled";
-		};
-	};
-};
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
deleted file mode 100644
index 0d51096c69f8..000000000000
--- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
+++ /dev/null
@@ -1,441 +0,0 @@
-/*
- * Copyright (C) 2016 Marvell Technology Group Ltd.
- *
- * This file is dual-licensed: you can use it either under the terms
- * of the GPLv2 or the X11 license, at your option. Note that this dual
- * licensing only applies to this file, and not this project as a
- * whole.
- *
- *  a) This library is free software; you can redistribute it and/or
- *     modify it under the terms of the GNU General Public License as
- *     published by the Free Software Foundation; either version 2 of the
- *     License, or (at your option) any later version.
- *
- *     This library is distributed in the hope that it will be useful,
- *     but WITHOUT ANY WARRANTY; without even the implied warranty of
- *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *     GNU General Public License for more details.
- *
- * Or, alternatively,
- *
- *  b) Permission is hereby granted, free of charge, to any person
- *     obtaining a copy of this software and associated documentation
- *     files (the "Software"), to deal in the Software without
- *     restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or
- *     sell copies of the Software, and to permit persons to whom the
- *     Software is furnished to do so, subject to the following
- *     conditions:
- *
- *     The above copyright notice and this permission notice shall be
- *     included in all copies or substantial portions of the Software.
- *
- *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
- *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
- *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
- *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- *     OTHER DEALINGS IN THE SOFTWARE.
- */
-
-/*
- * Device Tree file for Marvell Armada CP110 Slave.
- */
-
-#define ICU_GRP_NSR 0x0
-
-/ {
-	cp110-slave {
-		#address-cells = <2>;
-		#size-cells = <2>;
-		compatible = "simple-bus";
-		interrupt-parent = <&cps_icu>;
-		ranges;
-
-		config-space@f4000000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "simple-bus";
-			ranges = <0x0 0x0 0xf4000000 0x2000000>;
-
-			cps_ethernet: ethernet@0 {
-				compatible = "marvell,armada-7k-pp22";
-				reg = <0x0 0x100000>, <0x129000 0xb000>;
-				clocks = <&cps_clk 1 3>, <&cps_clk 1 9>, <&cps_clk 1 5>;
-				clock-names = "pp_clk", "gop_clk", "mg_clk";
-				marvell,system-controller = <&cps_syscon0>;
-				status = "disabled";
-				dma-coherent;
-
-				cps_eth0: eth0 {
-					interrupts = <ICU_GRP_NSR 39 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 43 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 47 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 51 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 55 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 129 IRQ_TYPE_LEVEL_HIGH>;
-					interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2",
-							  "tx-cpu3", "rx-shared", "link";
-					port-id = <0>;
-					gop-port-id = <0>;
-					status = "disabled";
-				};
-
-				cps_eth1: eth1 {
-					interrupts = <ICU_GRP_NSR 40 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 44 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 48 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 52 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 56 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 128 IRQ_TYPE_LEVEL_HIGH>;
-					interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2",
-							  "tx-cpu3", "rx-shared", "link";
-					port-id = <1>;
-					gop-port-id = <2>;
-					status = "disabled";
-				};
-
-				cps_eth2: eth2 {
-					interrupts = <ICU_GRP_NSR 41 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 45 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 49 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 53 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 57 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 127 IRQ_TYPE_LEVEL_HIGH>;
-					interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2",
-							  "tx-cpu3", "rx-shared", "link";
-					port-id = <2>;
-					gop-port-id = <3>;
-					status = "disabled";
-				};
-			};
-
-			cps_comphy: phy@120000 {
-				compatible = "marvell,comphy-cp110";
-				reg = <0x120000 0x6000>;
-				marvell,system-controller = <&cps_syscon0>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				cps_comphy0: phy@0 {
-					reg = <0>;
-					#phy-cells = <1>;
-				};
-
-				cps_comphy1: phy@1 {
-					reg = <1>;
-					#phy-cells = <1>;
-				};
-
-				cps_comphy2: phy@2 {
-					reg = <2>;
-					#phy-cells = <1>;
-				};
-
-				cps_comphy3: phy@3 {
-					reg = <3>;
-					#phy-cells = <1>;
-				};
-
-				cps_comphy4: phy@4 {
-					reg = <4>;
-					#phy-cells = <1>;
-				};
-
-				cps_comphy5: phy@5 {
-					reg = <5>;
-					#phy-cells = <1>;
-				};
-			};
-
-			cps_mdio: mdio@12a200 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "marvell,orion-mdio";
-				reg = <0x12a200 0x10>;
-				clocks = <&cps_clk 1 9>, <&cps_clk 1 5>;
-				status = "disabled";
-			};
-
-			cps_xmdio: mdio@12a600 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "marvell,xmdio";
-				reg = <0x12a600 0x10>;
-				status = "disabled";
-			};
-
-			cps_icu: interrupt-controller@1e0000 {
-				compatible = "marvell,cp110-icu";
-				reg = <0x1e0000 0x10>;
-				#interrupt-cells = <3>;
-				interrupt-controller;
-				msi-parent = <&gicp>;
-			};
-
-			cps_rtc: rtc@284000 {
-				compatible = "marvell,armada-8k-rtc";
-				reg = <0x284000 0x20>, <0x284080 0x24>;
-				reg-names = "rtc", "rtc-soc";
-				interrupts = <ICU_GRP_NSR 77 IRQ_TYPE_LEVEL_HIGH>;
-			};
-
-			cps_syscon0: system-controller@440000 {
-				compatible = "syscon", "simple-mfd";
-				reg = <0x440000 0x2000>;
-
-				cps_clk: clock {
-					compatible = "marvell,cp110-clock";
-					#clock-cells = <2>;
-				};
-
-				cps_gpio1: gpio@100 {
-					compatible = "marvell,armada-8k-gpio";
-					offset = <0x100>;
-					ngpios = <32>;
-					gpio-controller;
-					#gpio-cells = <2>;
-					gpio-ranges = <&cps_pinctrl 0 0 32>;
-					interrupt-controller;
-					interrupts = <ICU_GRP_NSR 86 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 85 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 84 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 83 IRQ_TYPE_LEVEL_HIGH>;
-					status = "disabled";
-				};
-
-				cps_gpio2: gpio@140 {
-					compatible = "marvell,armada-8k-gpio";
-					offset = <0x140>;
-					ngpios = <31>;
-					gpio-controller;
-					#gpio-cells = <2>;
-					gpio-ranges = <&cps_pinctrl 0 32 31>;
-					interrupt-controller;
-					interrupts = <ICU_GRP_NSR 82 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 81 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 80 IRQ_TYPE_LEVEL_HIGH>,
-						     <ICU_GRP_NSR 79 IRQ_TYPE_LEVEL_HIGH>;
-					status = "disabled";
-				};
-
-			};
-
-			cps_usb3_0: usb3@500000 {
-				compatible = "marvell,armada-8k-xhci",
-					     "generic-xhci";
-				reg = <0x500000 0x4000>;
-				dma-coherent;
-				interrupts = <ICU_GRP_NSR 106 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cps_clk 1 22>;
-				status = "disabled";
-			};
-
-			cps_usb3_1: usb3@510000 {
-				compatible = "marvell,armada-8k-xhci",
-					     "generic-xhci";
-				reg = <0x510000 0x4000>;
-				dma-coherent;
-				interrupts = <ICU_GRP_NSR 105 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cps_clk 1 23>;
-				status = "disabled";
-			};
-
-			cps_sata0: sata@540000 {
-				compatible = "marvell,armada-8k-ahci",
-					     "generic-ahci";
-				reg = <0x540000 0x30000>;
-				interrupts = <ICU_GRP_NSR 107 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cps_clk 1 15>;
-				status = "disabled";
-			};
-
-			cps_xor0: xor@6a0000 {
-				compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
-				reg = <0x6a0000 0x1000>,
-				      <0x6b0000 0x1000>;
-				dma-coherent;
-				msi-parent = <&gic_v2m0>;
-				clocks = <&cps_clk 1 8>;
-			};
-
-			cps_xor1: xor@6c0000 {
-				compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
-				reg = <0x6c0000 0x1000>,
-				      <0x6d0000 0x1000>;
-				dma-coherent;
-				msi-parent = <&gic_v2m0>;
-				clocks = <&cps_clk 1 7>;
-			};
-
-			cps_spi0: spi@700600 {
-				compatible = "marvell,armada-380-spi";
-				reg = <0x700600 0x50>;
-				#address-cells = <0x1>;
-				#size-cells = <0x0>;
-				cell-index = <3>;
-				clocks = <&cps_clk 1 21>;
-				status = "disabled";
-			};
-
-			cps_spi1: spi@700680 {
-				compatible = "marvell,armada-380-spi";
-				reg = <0x700680 0x50>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-				cell-index = <4>;
-				clocks = <&cps_clk 1 21>;
-				status = "disabled";
-			};
-
-			cps_i2c0: i2c@701000 {
-				compatible = "marvell,mv78230-i2c";
-				reg = <0x701000 0x20>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-				interrupts = <ICU_GRP_NSR 120 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cps_clk 1 21>;
-				status = "disabled";
-			};
-
-			cps_i2c1: i2c@701100 {
-				compatible = "marvell,mv78230-i2c";
-				reg = <0x701100 0x20>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-				interrupts = <ICU_GRP_NSR 121 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cps_clk 1 21>;
-				status = "disabled";
-			};
-
-			cps_nand: nand@720000 {
-				/*
-				 * Due to the limiation of the pin available
-				 * this controller is only usable on the CPM
-				 * for A7K and on the CPS for A8K.
-				 */
-				compatible = "marvell,armada370-nand",
-					     "marvell,armada370-nand";
-				reg = <0x720000 0x54>;
-				#address-cells = <1>;
-				#size-cells = <1>;
-				interrupts = <ICU_GRP_NSR 115 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cps_clk 1 2>;
-				status = "disabled";
-			};
-
-			cps_trng: trng@760000 {
-				compatible = "marvell,armada-8k-rng", "inside-secure,safexcel-eip76";
-				reg = <0x760000 0x7d>;
-				interrupts = <ICU_GRP_NSR 95 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&cps_clk 1 25>;
-				status = "okay";
-			};
-
-			cps_crypto: crypto@800000 {
-				compatible = "inside-secure,safexcel-eip197";
-				reg = <0x800000 0x200000>;
-				interrupts = <ICU_GRP_NSR 87 IRQ_TYPE_LEVEL_HIGH>,
-					     <ICU_GRP_NSR 88 IRQ_TYPE_LEVEL_HIGH>,
-					     <ICU_GRP_NSR 89 IRQ_TYPE_LEVEL_HIGH>,
-					     <ICU_GRP_NSR 90 IRQ_TYPE_LEVEL_HIGH>,
-					     <ICU_GRP_NSR 91 IRQ_TYPE_LEVEL_HIGH>,
-					     <ICU_GRP_NSR 92 IRQ_TYPE_LEVEL_HIGH>;
-				interrupt-names = "mem", "ring0", "ring1",
-						  "ring2", "ring3", "eip";
-				clocks = <&cps_clk 1 26>;
-				dma-coherent;
-				/*
-				 * The cryptographic engine found on the cp110
-				 * master is enabled by default at the SoC
-				 * level. Because it is not possible as of now
-				 * to enable two cryptographic engines in
-				 * parallel, disable this one by default.
-				 */
-				status = "disabled";
-			};
-		};
-
-		cps_pcie0: pcie@f4600000 {
-			compatible = "marvell,armada8k-pcie", "snps,dw-pcie";
-			reg = <0 0xf4600000 0 0x10000>,
-			      <0 0xfaf00000 0 0x80000>;
-			reg-names = "ctrl", "config";
-			#address-cells = <3>;
-			#size-cells = <2>;
-			#interrupt-cells = <1>;
-			device_type = "pci";
-			dma-coherent;
-			msi-parent = <&gic_v2m0>;
-
-			bus-range = <0 0xff>;
-			ranges =
-				/* downstream I/O */
-				<0x81000000 0 0xfd000000 0  0xfd000000 0 0x10000
-				/* non-prefetchable memory */
-				0x82000000 0 0xfa000000 0  0xfa000000 0 0xf00000>;
-			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts = <ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
-			num-lanes = <1>;
-			clocks = <&cps_clk 1 13>;
-			status = "disabled";
-		};
-
-		cps_pcie1: pcie@f4620000 {
-			compatible = "marvell,armada8k-pcie", "snps,dw-pcie";
-			reg = <0 0xf4620000 0 0x10000>,
-			      <0 0xfbf00000 0 0x80000>;
-			reg-names = "ctrl", "config";
-			#address-cells = <3>;
-			#size-cells = <2>;
-			#interrupt-cells = <1>;
-			device_type = "pci";
-			dma-coherent;
-			msi-parent = <&gic_v2m0>;
-
-			bus-range = <0 0xff>;
-			ranges =
-				/* downstream I/O */
-				<0x81000000 0 0xfd010000 0  0xfd010000 0 0x10000
-				/* non-prefetchable memory */
-				0x82000000 0 0xfb000000 0  0xfb000000 0 0xf00000>;
-			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts = <ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
-
-			num-lanes = <1>;
-			clocks = <&cps_clk 1 11>;
-			status = "disabled";
-		};
-
-		cps_pcie2: pcie@f4640000 {
-			compatible = "marvell,armada8k-pcie", "snps,dw-pcie";
-			reg = <0 0xf4640000 0 0x10000>,
-			      <0 0xfcf00000 0 0x80000>;
-			reg-names = "ctrl", "config";
-			#address-cells = <3>;
-			#size-cells = <2>;
-			#interrupt-cells = <1>;
-			device_type = "pci";
-			dma-coherent;
-			msi-parent = <&gic_v2m0>;
-
-			bus-range = <0 0xff>;
-			ranges =
-				/* downstream I/O */
-				<0x81000000 0 0xfd020000 0  0xfd020000 0 0x10000
-				/* non-prefetchable memory */
-				0x82000000 0 0xfc000000 0  0xfc000000 0 0xf00000>;
-			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts = <ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
-
-			num-lanes = <1>;
-			clocks = <&cps_clk 1 12>;
-			status = "disabled";
-		};
-	};
-};
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
new file mode 100644
index 000000000000..a8af4136dbe7
--- /dev/null
+++ b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
@@ -0,0 +1,424 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR X11)
+/*
+ * Copyright (C) 2016 Marvell Technology Group Ltd.
+ */
+
+/*
+ * Device Tree file for Marvell Armada CP110.
+ */
+
+#include <dt-bindings/interrupt-controller/mvebu-icu.h>
+
+#include "armada-common.dtsi"
+
+#define CP110_PCIEx_IO_BASE(iface)	(CP110_PCIE_IO_BASE + (iface *  0x10000))
+#define CP110_PCIEx_MEM_BASE(iface)	(CP110_PCIE_MEM_BASE + (iface *  0x1000000))
+#define CP110_PCIEx_CONF_BASE(iface)	(CP110_PCIEx_MEM_BASE(iface) + 0xf00000)
+
+/ {
+	/*
+	 * The contents of the node are defined below, in order to
+	 * save one indentation level
+	 */
+	CP110_NAME: CP110_NAME { };
+};
+
+&CP110_NAME {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	compatible = "simple-bus";
+	interrupt-parent = <&CP110_LABEL(icu)>;
+	ranges;
+
+	config-space@CP110_BASE {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		ranges = <0x0 0x0 ADDRESSIFY(CP110_BASE) 0x2000000>;
+
+		CP110_LABEL(ethernet): ethernet@0 {
+			compatible = "marvell,armada-7k-pp22";
+			reg = <0x0 0x100000>, <0x129000 0xb000>;
+			clocks = <&CP110_LABEL(clk) 1 3>, <&CP110_LABEL(clk) 1 9>,
+				 <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 18>;
+			clock-names = "pp_clk", "gop_clk",
+				      "mg_clk", "axi_clk";
+			marvell,system-controller = <&CP110_LABEL(syscon0)>;
+			status = "disabled";
+			dma-coherent;
+
+			CP110_LABEL(eth0): eth0 {
+				interrupts = <ICU_GRP_NSR 39 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 43 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 47 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 51 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 55 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 129 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2",
+					"tx-cpu3", "rx-shared", "link";
+				port-id = <0>;
+				gop-port-id = <0>;
+				status = "disabled";
+			};
+
+			CP110_LABEL(eth1): eth1 {
+				interrupts = <ICU_GRP_NSR 40 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 44 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 48 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 52 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 56 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 128 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2",
+					"tx-cpu3", "rx-shared", "link";
+				port-id = <1>;
+				gop-port-id = <2>;
+				status = "disabled";
+			};
+
+			CP110_LABEL(eth2): eth2 {
+				interrupts = <ICU_GRP_NSR 41 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 45 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 49 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 53 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 57 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 127 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2",
+					"tx-cpu3", "rx-shared", "link";
+				port-id = <2>;
+				gop-port-id = <3>;
+				status = "disabled";
+			};
+		};
+
+		CP110_LABEL(comphy): phy@120000 {
+			compatible = "marvell,comphy-cp110";
+			reg = <0x120000 0x6000>;
+			marvell,system-controller = <&CP110_LABEL(syscon0)>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			CP110_LABEL(comphy0): phy@0 {
+				reg = <0>;
+				#phy-cells = <1>;
+			};
+
+			CP110_LABEL(comphy1): phy@1 {
+				reg = <1>;
+				#phy-cells = <1>;
+			};
+
+			CP110_LABEL(comphy2): phy@2 {
+				reg = <2>;
+				#phy-cells = <1>;
+			};
+
+			CP110_LABEL(comphy3): phy@3 {
+				reg = <3>;
+				#phy-cells = <1>;
+			};
+
+			CP110_LABEL(comphy4): phy@4 {
+				reg = <4>;
+				#phy-cells = <1>;
+			};
+
+			CP110_LABEL(comphy5): phy@5 {
+				reg = <5>;
+				#phy-cells = <1>;
+			};
+		};
+
+		CP110_LABEL(mdio): mdio@12a200 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "marvell,orion-mdio";
+			reg = <0x12a200 0x10>;
+			clocks = <&CP110_LABEL(clk) 1 9>, <&CP110_LABEL(clk) 1 5>,
+				 <&CP110_LABEL(clk) 1 6>, <&CP110_LABEL(clk) 1 18>;
+			status = "disabled";
+		};
+
+		CP110_LABEL(xmdio): mdio@12a600 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "marvell,xmdio";
+			reg = <0x12a600 0x10>;
+			status = "disabled";
+		};
+
+		CP110_LABEL(icu): interrupt-controller@1e0000 {
+			compatible = "marvell,cp110-icu";
+			reg = <0x1e0000 0x10>;
+			#interrupt-cells = <3>;
+			interrupt-controller;
+			msi-parent = <&gicp>;
+		};
+
+		CP110_LABEL(rtc): rtc@284000 {
+			compatible = "marvell,armada-8k-rtc";
+			reg = <0x284000 0x20>, <0x284080 0x24>;
+			reg-names = "rtc", "rtc-soc";
+			interrupts = <ICU_GRP_NSR 77 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		CP110_LABEL(thermal): thermal@400078 {
+			compatible = "marvell,armada-cp110-thermal";
+			reg = <0x400078 0x4>,
+			<0x400070 0x8>;
+		};
+
+		CP110_LABEL(syscon0): system-controller@440000 {
+			compatible = "syscon", "simple-mfd";
+			reg = <0x440000 0x2000>;
+
+			CP110_LABEL(clk): clock {
+				compatible = "marvell,cp110-clock";
+				#clock-cells = <2>;
+			};
+
+			CP110_LABEL(gpio1): gpio@100 {
+				compatible = "marvell,armada-8k-gpio";
+				offset = <0x100>;
+				ngpios = <32>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				gpio-ranges = <&CP110_LABEL(pinctrl) 0 0 32>;
+				interrupt-controller;
+				interrupts = <ICU_GRP_NSR 86 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 85 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 84 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 83 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+
+			CP110_LABEL(gpio2): gpio@140 {
+				compatible = "marvell,armada-8k-gpio";
+				offset = <0x140>;
+				ngpios = <31>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				gpio-ranges = <&CP110_LABEL(pinctrl) 0 32 31>;
+				interrupt-controller;
+				interrupts = <ICU_GRP_NSR 82 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 81 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 80 IRQ_TYPE_LEVEL_HIGH>,
+					<ICU_GRP_NSR 79 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+		};
+
+		CP110_LABEL(usb3_0): usb3@500000 {
+			compatible = "marvell,armada-8k-xhci",
+			"generic-xhci";
+			reg = <0x500000 0x4000>;
+			dma-coherent;
+			interrupts = <ICU_GRP_NSR 106 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&CP110_LABEL(clk) 1 22>;
+			status = "disabled";
+		};
+
+		CP110_LABEL(usb3_1): usb3@510000 {
+			compatible = "marvell,armada-8k-xhci",
+			"generic-xhci";
+			reg = <0x510000 0x4000>;
+			dma-coherent;
+			interrupts = <ICU_GRP_NSR 105 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&CP110_LABEL(clk) 1 23>;
+			status = "disabled";
+		};
+
+		CP110_LABEL(sata0): sata@540000 {
+			compatible = "marvell,armada-8k-ahci",
+			"generic-ahci";
+			reg = <0x540000 0x30000>;
+			interrupts = <ICU_GRP_NSR 107 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&CP110_LABEL(clk) 1 15>;
+			status = "disabled";
+		};
+
+		CP110_LABEL(xor0): xor@6a0000 {
+			compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
+			reg = <0x6a0000 0x1000>, <0x6b0000 0x1000>;
+			dma-coherent;
+			msi-parent = <&gic_v2m0>;
+			clocks = <&CP110_LABEL(clk) 1 8>;
+		};
+
+		CP110_LABEL(xor1): xor@6c0000 {
+			compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
+			reg = <0x6c0000 0x1000>, <0x6d0000 0x1000>;
+			dma-coherent;
+			msi-parent = <&gic_v2m0>;
+			clocks = <&CP110_LABEL(clk) 1 7>;
+		};
+
+		CP110_LABEL(spi0): spi@700600 {
+			compatible = "marvell,armada-380-spi";
+			reg = <0x700600 0x50>;
+			#address-cells = <0x1>;
+			#size-cells = <0x0>;
+			clocks = <&CP110_LABEL(clk) 1 21>;
+			status = "disabled";
+		};
+
+		CP110_LABEL(spi1): spi@700680 {
+			compatible = "marvell,armada-380-spi";
+			reg = <0x700680 0x50>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&CP110_LABEL(clk) 1 21>;
+			status = "disabled";
+		};
+
+		CP110_LABEL(i2c0): i2c@701000 {
+			compatible = "marvell,mv78230-i2c";
+			reg = <0x701000 0x20>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <ICU_GRP_NSR 120 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&CP110_LABEL(clk) 1 21>;
+			status = "disabled";
+		};
+
+		CP110_LABEL(i2c1): i2c@701100 {
+			compatible = "marvell,mv78230-i2c";
+			reg = <0x701100 0x20>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <ICU_GRP_NSR 121 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&CP110_LABEL(clk) 1 21>;
+			status = "disabled";
+		};
+
+		CP110_LABEL(nand): nand@720000 {
+			/*
+			* Due to the limitation of the pins available
+			* this controller is only usable on the CPM
+			* for A7K and on the CPS for A8K.
+			*/
+			compatible = "marvell,armada-8k-nand",
+			"marvell,armada370-nand";
+			reg = <0x720000 0x54>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			interrupts = <ICU_GRP_NSR 115 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&CP110_LABEL(clk) 1 2>;
+			marvell,system-controller = <&CP110_LABEL(syscon0)>;
+			status = "disabled";
+		};
+
+		CP110_LABEL(trng): trng@760000 {
+			compatible = "marvell,armada-8k-rng",
+			"inside-secure,safexcel-eip76";
+			reg = <0x760000 0x7d>;
+			interrupts = <ICU_GRP_NSR 95 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&CP110_LABEL(clk) 1 25>;
+			status = "okay";
+		};
+
+		CP110_LABEL(sdhci0): sdhci@780000 {
+			compatible = "marvell,armada-cp110-sdhci";
+			reg = <0x780000 0x300>;
+			interrupts = <ICU_GRP_NSR 27 IRQ_TYPE_LEVEL_HIGH>;
+			clock-names = "core", "axi";
+			clocks = <&CP110_LABEL(clk) 1 4>, <&CP110_LABEL(clk) 1 18>;
+			dma-coherent;
+			status = "disabled";
+		};
+
+		CP110_LABEL(crypto): crypto@800000 {
+			compatible = "inside-secure,safexcel-eip197";
+			reg = <0x800000 0x200000>;
+			interrupts = <ICU_GRP_NSR 87 IRQ_TYPE_LEVEL_HIGH>,
+				<ICU_GRP_NSR 88 IRQ_TYPE_LEVEL_HIGH>,
+				<ICU_GRP_NSR 89 IRQ_TYPE_LEVEL_HIGH>,
+				<ICU_GRP_NSR 90 IRQ_TYPE_LEVEL_HIGH>,
+				<ICU_GRP_NSR 91 IRQ_TYPE_LEVEL_HIGH>,
+				<ICU_GRP_NSR 92 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mem", "ring0", "ring1",
+				"ring2", "ring3", "eip";
+			clocks = <&CP110_LABEL(clk) 1 26>;
+			dma-coherent;
+		};
+	};
+
+	CP110_LABEL(pcie0): pcie@CP110_PCIE0_BASE {
+		compatible = "marvell,armada8k-pcie", "snps,dw-pcie";
+		reg = <0 ADDRESSIFY(CP110_PCIE0_BASE) 0 0x10000>,
+		      <0 CP110_PCIEx_CONF_BASE(0) 0 0x80000>;
+		reg-names = "ctrl", "config";
+		#address-cells = <3>;
+		#size-cells = <2>;
+		#interrupt-cells = <1>;
+		device_type = "pci";
+		dma-coherent;
+		msi-parent = <&gic_v2m0>;
+
+		bus-range = <0 0xff>;
+		ranges =
+		/* downstream I/O */
+		<0x81000000 0 CP110_PCIEx_IO_BASE(0) 0  CP110_PCIEx_IO_BASE(0) 0 0x10000
+		/* non-prefetchable memory */
+		0x82000000 0 CP110_PCIEx_MEM_BASE(0) 0  CP110_PCIEx_MEM_BASE(0) 0 0xf00000>;
+		interrupt-map-mask = <0 0 0 0>;
+		interrupt-map = <0 0 0 0 &CP110_LABEL(icu) ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
+		num-lanes = <1>;
+		clocks = <&CP110_LABEL(clk) 1 13>;
+		status = "disabled";
+	};
+
+	CP110_LABEL(pcie1): pcie@CP110_PCIE1_BASE {
+		compatible = "marvell,armada8k-pcie", "snps,dw-pcie";
+		reg = <0 ADDRESSIFY(CP110_PCIE1_BASE) 0 0x10000>,
+		      <0 CP110_PCIEx_CONF_BASE(1) 0 0x80000>;
+		reg-names = "ctrl", "config";
+		#address-cells = <3>;
+		#size-cells = <2>;
+		#interrupt-cells = <1>;
+		device_type = "pci";
+		dma-coherent;
+		msi-parent = <&gic_v2m0>;
+
+		bus-range = <0 0xff>;
+		ranges =
+		/* downstream I/O */
+		<0x81000000 0 CP110_PCIEx_IO_BASE(1) 0  CP110_PCIEx_IO_BASE(1) 0 0x10000
+		/* non-prefetchable memory */
+		0x82000000 0 CP110_PCIEx_MEM_BASE(1) 0  CP110_PCIEx_MEM_BASE(1) 0 0xf00000>;
+		interrupt-map-mask = <0 0 0 0>;
+		interrupt-map = <0 0 0 0 &CP110_LABEL(icu) ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
+
+		num-lanes = <1>;
+		clocks = <&CP110_LABEL(clk) 1 11>;
+		status = "disabled";
+	};
+
+	CP110_LABEL(pcie2): pcie@CP110_PCIE2_BASE {
+		compatible = "marvell,armada8k-pcie", "snps,dw-pcie";
+		reg = <0 ADDRESSIFY(CP110_PCIE2_BASE) 0 0x10000>,
+		      <0 CP110_PCIEx_CONF_BASE(2) 0 0x80000>;
+		reg-names = "ctrl", "config";
+		#address-cells = <3>;
+		#size-cells = <2>;
+		#interrupt-cells = <1>;
+		device_type = "pci";
+		dma-coherent;
+		msi-parent = <&gic_v2m0>;
+
+		bus-range = <0 0xff>;
+		ranges =
+		/* downstream I/O */
+		<0x81000000 0 CP110_PCIEx_IO_BASE(2) 0  CP110_PCIEx_IO_BASE(2) 0 0x10000
+		/* non-prefetchable memory */
+		0x82000000 0 CP110_PCIEx_MEM_BASE(2) 0  CP110_PCIEx_MEM_BASE(2) 0 0xf00000>;
+		interrupt-map-mask = <0 0 0 0>;
+		interrupt-map = <0 0 0 0 &CP110_LABEL(icu) ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
+
+		num-lanes = <1>;
+		clocks = <&CP110_LABEL(clk) 1 12>;
+		status = "disabled";
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts
index 8c804df3da4e..10f9c76cd105 100644
--- a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts
@@ -24,6 +24,33 @@
 	chosen {
 		stdout-path = "serial0:921600n8";
 	};
+
+	cpus_fixed_vproc0: fixedregulator@0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vproc_buck0";
+		regulator-min-microvolt = <1000000>;
+		regulator-max-microvolt = <1000000>;
+	};
+
+	cpus_fixed_vproc1: fixedregulator@1 {
+		compatible = "regulator-fixed";
+		regulator-name = "vproc_buck1";
+		regulator-min-microvolt = <1000000>;
+		regulator-max-microvolt = <1000000>;
+	};
+
+};
+
+&cpu0 {
+	proc-supply = <&cpus_fixed_vproc0>;
+};
+
+&cpu1 {
+	proc-supply = <&cpus_fixed_vproc0>;
+};
+
+&cpu2 {
+	proc-supply = <&cpus_fixed_vproc1>;
 };
 
 &uart0 {
diff --git a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi
index 5d4e406bb35d..fdf66f4fe7c3 100644
--- a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi
@@ -5,8 +5,10 @@
  * SPDX-License-Identifier: (GPL-2.0 OR MIT)
  */
 
+#include <dt-bindings/clock/mt2712-clk.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/power/mt2712-power.h>
 
 / {
 	compatible = "mediatek,mt2712";
@@ -14,6 +16,48 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
+	cluster0_opp: opp_table0 {
+		compatible = "operating-points-v2";
+		opp-shared;
+		opp00 {
+			opp-hz = /bits/ 64 <598000000>;
+			opp-microvolt = <1000000>;
+		};
+		opp01 {
+			opp-hz = /bits/ 64 <702000000>;
+			opp-microvolt = <1000000>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <793000000>;
+			opp-microvolt = <1000000>;
+		};
+	};
+
+	cluster1_opp: opp_table1 {
+		compatible = "operating-points-v2";
+		opp-shared;
+		opp00 {
+			opp-hz = /bits/ 64 <598000000>;
+			opp-microvolt = <1000000>;
+		};
+		opp01 {
+			opp-hz = /bits/ 64 <702000000>;
+			opp-microvolt = <1000000>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <793000000>;
+			opp-microvolt = <1000000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <897000000>;
+			opp-microvolt = <1000000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <1001000000>;
+			opp-microvolt = <1000000>;
+		};
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -39,6 +83,11 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a35";
 			reg = <0x000>;
+			clocks = <&mcucfg CLK_MCU_MP0_SEL>,
+				<&topckgen CLK_TOP_F_MP0_PLL1>;
+			clock-names = "cpu", "intermediate";
+			proc-supply = <&cpus_fixed_vproc0>;
+			operating-points-v2 = <&cluster0_opp>;
 			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
 		};
 
@@ -47,6 +96,11 @@
 			compatible = "arm,cortex-a35";
 			reg = <0x001>;
 			enable-method = "psci";
+			clocks = <&mcucfg CLK_MCU_MP0_SEL>,
+				<&topckgen CLK_TOP_F_MP0_PLL1>;
+			clock-names = "cpu", "intermediate";
+			proc-supply = <&cpus_fixed_vproc0>;
+			operating-points-v2 = <&cluster0_opp>;
 			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
 		};
 
@@ -55,6 +109,11 @@
 			compatible = "arm,cortex-a72";
 			reg = <0x200>;
 			enable-method = "psci";
+			clocks = <&mcucfg CLK_MCU_MP2_SEL>,
+				<&topckgen CLK_TOP_F_BIG_PLL1>;
+			clock-names = "cpu", "intermediate";
+			proc-supply = <&cpus_fixed_vproc1>;
+			operating-points-v2 = <&cluster1_opp>;
 			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
 		};
 
@@ -98,6 +157,48 @@
 		#clock-cells = <0>;
 	};
 
+	clk26m: oscillator@0 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <26000000>;
+		clock-output-names = "clk26m";
+	};
+
+	clk32k: oscillator@1 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <32768>;
+		clock-output-names = "clk32k";
+	};
+
+	clkfpc: oscillator@2 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <50000000>;
+		clock-output-names = "clkfpc";
+	};
+
+	clkaud_ext_i_0: oscillator@3 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <6500000>;
+		clock-output-names = "clkaud_ext_i_0";
+	};
+
+	clkaud_ext_i_1: oscillator@4 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <196608000>;
+		clock-output-names = "clkaud_ext_i_1";
+	};
+
+	clkaud_ext_i_2: oscillator@5 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <180633600>;
+		clock-output-names = "clkaud_ext_i_2";
+	};
+
 	timer {
 		compatible = "arm,armv8-timer";
 		interrupt-parent = <&gic>;
@@ -111,6 +212,39 @@
 			      (GIC_CPU_MASK_RAW(0x13) | IRQ_TYPE_LEVEL_LOW)>;
 	};
 
+	topckgen: syscon@10000000 {
+		compatible = "mediatek,mt2712-topckgen", "syscon";
+		reg = <0 0x10000000 0 0x1000>;
+		#clock-cells = <1>;
+	};
+
+	infracfg: syscon@10001000 {
+		compatible = "mediatek,mt2712-infracfg", "syscon";
+		reg = <0 0x10001000 0 0x1000>;
+		#clock-cells = <1>;
+	};
+
+	pericfg: syscon@10003000 {
+		compatible = "mediatek,mt2712-pericfg", "syscon";
+		reg = <0 0x10003000 0 0x1000>;
+		#clock-cells = <1>;
+	};
+
+	scpsys: scpsys@10006000 {
+		compatible = "mediatek,mt2712-scpsys", "syscon";
+		#power-domain-cells = <1>;
+		reg = <0 0x10006000 0 0x1000>;
+		clocks = <&topckgen CLK_TOP_MM_SEL>,
+			 <&topckgen CLK_TOP_MFG_SEL>,
+			 <&topckgen CLK_TOP_VENC_SEL>,
+			 <&topckgen CLK_TOP_JPGDEC_SEL>,
+			 <&topckgen CLK_TOP_A1SYS_HP_SEL>,
+			 <&topckgen CLK_TOP_VDEC_SEL>;
+		clock-names = "mm", "mfg", "venc",
+			"jpgdec", "audio", "vdec";
+		infracfg = <&infracfg>;
+	};
+
 	uart5: serial@1000f000 {
 		compatible = "mediatek,mt2712-uart",
 			     "mediatek,mt6577-uart";
@@ -121,6 +255,18 @@
 		status = "disabled";
 	};
 
+	apmixedsys: syscon@10209000 {
+		compatible = "mediatek,mt2712-apmixedsys", "syscon";
+		reg = <0 0x10209000 0 0x1000>;
+		#clock-cells = <1>;
+	};
+
+	mcucfg: syscon@10220000 {
+		compatible = "mediatek,mt2712-mcucfg", "syscon";
+		reg = <0 0x10220000 0 0x1000>;
+		#clock-cells = <1>;
+	};
+
 	sysirq: interrupt-controller@10220a80 {
 		compatible = "mediatek,mt2712-sysirq",
 			     "mediatek,mt6577-sysirq";
@@ -192,5 +338,47 @@
 		clock-names = "baud", "bus";
 		status = "disabled";
 	};
+
+	mfgcfg: syscon@13000000 {
+		compatible = "mediatek,mt2712-mfgcfg", "syscon";
+		reg = <0 0x13000000 0 0x1000>;
+		#clock-cells = <1>;
+	};
+
+	mmsys: syscon@14000000 {
+		compatible = "mediatek,mt2712-mmsys", "syscon";
+		reg = <0 0x14000000 0 0x1000>;
+		#clock-cells = <1>;
+	};
+
+	imgsys: syscon@15000000 {
+		compatible = "mediatek,mt2712-imgsys", "syscon";
+		reg = <0 0x15000000 0 0x1000>;
+		#clock-cells = <1>;
+	};
+
+	bdpsys: syscon@15010000 {
+		compatible = "mediatek,mt2712-bdpsys", "syscon";
+		reg = <0 0x15010000 0 0x1000>;
+		#clock-cells = <1>;
+	};
+
+	vdecsys: syscon@16000000 {
+		compatible = "mediatek,mt2712-vdecsys", "syscon";
+		reg = <0 0x16000000 0 0x1000>;
+		#clock-cells = <1>;
+	};
+
+	vencsys: syscon@18000000 {
+		compatible = "mediatek,mt2712-vencsys", "syscon";
+		reg = <0 0x18000000 0 0x1000>;
+		#clock-cells = <1>;
+	};
+
+	jpgdecsys: syscon@19000000 {
+		compatible = "mediatek,mt2712-jpgdecsys", "syscon";
+		reg = <0 0x19000000 0 0x1000>;
+		#clock-cells = <1>;
+	};
 };
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
index 1c3634fa94bf..8e6ada20e6db 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
@@ -74,6 +74,24 @@
 	status = "okay";
 };
 
+&cpu0 {
+	proc-supply = <&mt6397_vpca15_reg>;
+};
+
+&cpu1 {
+	proc-supply = <&mt6397_vpca15_reg>;
+};
+
+&cpu2 {
+	proc-supply = <&da9211_vcpu_reg>;
+	sram-supply = <&mt6397_vsramca7_reg>;
+};
+
+&cpu3 {
+	proc-supply = <&da9211_vcpu_reg>;
+	sram-supply = <&mt6397_vsramca7_reg>;
+};
+
 &dpi0 {
 	status = "okay";
 };
@@ -505,7 +523,7 @@
 	vbus-supply = <&usb_p0_vbus>;
 	extcon = <&extcon_usb>;
 	dr_mode = "otg";
-	mediatek,enable-wakeup;
+	wakeup-source;
 	pinctrl-names = "default", "id_float", "id_ground";
 	pinctrl-0 = <&usb_id_pins_float>;
 	pinctrl-1 = <&usb_id_pins_float>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 26396ef53bde..9fbe4705ee88 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -51,6 +51,80 @@
 		mdp_wrot1 = &mdp_wrot1;
 	};
 
+	cluster0_opp: opp_table0 {
+		compatible = "operating-points-v2";
+		opp-shared;
+		opp-507000000 {
+			opp-hz = /bits/ 64 <507000000>;
+			opp-microvolt = <859000>;
+		};
+		opp-702000000 {
+			opp-hz = /bits/ 64 <702000000>;
+			opp-microvolt = <908000>;
+		};
+		opp-1001000000 {
+			opp-hz = /bits/ 64 <1001000000>;
+			opp-microvolt = <983000>;
+		};
+		opp-1105000000 {
+			opp-hz = /bits/ 64 <1105000000>;
+			opp-microvolt = <1009000>;
+		};
+		opp-1209000000 {
+			opp-hz = /bits/ 64 <1209000000>;
+			opp-microvolt = <1034000>;
+		};
+		opp-1300000000 {
+			opp-hz = /bits/ 64 <1300000000>;
+			opp-microvolt = <1057000>;
+		};
+		opp-1508000000 {
+			opp-hz = /bits/ 64 <1508000000>;
+			opp-microvolt = <1109000>;
+		};
+		opp-1703000000 {
+			opp-hz = /bits/ 64 <1703000000>;
+			opp-microvolt = <1125000>;
+		};
+	};
+
+	cluster1_opp: opp_table1 {
+		compatible = "operating-points-v2";
+		opp-shared;
+		opp-507000000 {
+			opp-hz = /bits/ 64 <507000000>;
+			opp-microvolt = <828000>;
+		};
+		opp-702000000 {
+			opp-hz = /bits/ 64 <702000000>;
+			opp-microvolt = <867000>;
+		};
+		opp-1001000000 {
+			opp-hz = /bits/ 64 <1001000000>;
+			opp-microvolt = <927000>;
+		};
+		opp-1209000000 {
+			opp-hz = /bits/ 64 <1209000000>;
+			opp-microvolt = <968000>;
+		};
+		opp-1404000000 {
+			opp-hz = /bits/ 64 <1404000000>;
+			opp-microvolt = <1007000>;
+		};
+		opp-1612000000 {
+			opp-hz = /bits/ 64 <1612000000>;
+			opp-microvolt = <1049000>;
+		};
+		opp-1807000000 {
+			opp-hz = /bits/ 64 <1807000000>;
+			opp-microvolt = <1089000>;
+		};
+		opp-2106000000 {
+			opp-hz = /bits/ 64 <2106000000>;
+			opp-microvolt = <1125000>;
+		};
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -81,6 +155,11 @@
 			reg = <0x000>;
 			enable-method = "psci";
 			cpu-idle-states = <&CPU_SLEEP_0>;
+			#cooling-cells = <2>;
+			clocks = <&infracfg CLK_INFRA_CA53SEL>,
+				 <&apmixedsys CLK_APMIXED_MAINPLL>;
+			clock-names = "cpu", "intermediate";
+			operating-points-v2 = <&cluster0_opp>;
 		};
 
 		cpu1: cpu@1 {
@@ -89,6 +168,10 @@
 			reg = <0x001>;
 			enable-method = "psci";
 			cpu-idle-states = <&CPU_SLEEP_0>;
+			clocks = <&infracfg CLK_INFRA_CA53SEL>,
+				 <&apmixedsys CLK_APMIXED_MAINPLL>;
+			clock-names = "cpu", "intermediate";
+			operating-points-v2 = <&cluster0_opp>;
 		};
 
 		cpu2: cpu@100 {
@@ -97,6 +180,11 @@
 			reg = <0x100>;
 			enable-method = "psci";
 			cpu-idle-states = <&CPU_SLEEP_0>;
+			#cooling-cells = <2>;
+			clocks = <&infracfg CLK_INFRA_CA57SEL>,
+				 <&apmixedsys CLK_APMIXED_MAINPLL>;
+			clock-names = "cpu", "intermediate";
+			operating-points-v2 = <&cluster1_opp>;
 		};
 
 		cpu3: cpu@101 {
@@ -105,6 +193,10 @@
 			reg = <0x101>;
 			enable-method = "psci";
 			cpu-idle-states = <&CPU_SLEEP_0>;
+			clocks = <&infracfg CLK_INFRA_CA57SEL>,
+				 <&apmixedsys CLK_APMIXED_MAINPLL>;
+			clock-names = "cpu", "intermediate";
+			operating-points-v2 = <&cluster1_opp>;
 		};
 
 		idle-states {
@@ -731,15 +823,9 @@
 			       <&u3port0 PHY_TYPE_USB3>,
 			       <&u2port1 PHY_TYPE_USB2>;
 			power-domains = <&scpsys MT8173_POWER_DOMAIN_USB>;
-			clocks = <&topckgen CLK_TOP_USB30_SEL>,
-				 <&clk26m>,
-				 <&pericfg CLK_PERI_USB0>,
-				 <&pericfg CLK_PERI_USB1>;
-			clock-names = "sys_ck",
-				      "ref_ck",
-				      "wakeup_deb_p0",
-				      "wakeup_deb_p1";
-			mediatek,syscon-wakeup = <&pericfg>;
+			clocks = <&topckgen CLK_TOP_USB30_SEL>, <&clk26m>;
+			clock-names = "sys_ck", "ref_ck";
+			mediatek,syscon-wakeup = <&pericfg 0x400 1>;
 			#address-cells = <2>;
 			#size-cells = <2>;
 			ranges;
diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts
index 42a23997dcdb..bd5305a634b1 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts
@@ -74,6 +74,43 @@
 		};
 	};
 
+	host1x@13e00000 {
+		status = "okay";
+
+		dpaux@15040000 {
+			status = "okay";
+		};
+
+		display-hub@15200000 {
+			status = "okay";
+		};
+
+		dsi@15300000 {
+			status = "disabled";
+		};
+
+		sor@15540000 {
+			status = "disabled";
+
+			nvidia,dpaux = <&dpaux1>;
+		};
+
+		sor@15580000 {
+			status = "okay";
+
+			avdd-io-supply = <&vdd_hdmi_1v05>;
+			vdd-pll-supply = <&vdd_1v8_ap>;
+			hdmi-supply = <&vdd_hdmi>;
+
+			nvidia,ddc-i2c-bus = <&ddc>;
+			nvidia,hpd-gpio = <&gpio TEGRA_MAIN_GPIO(P, 1) GPIO_ACTIVE_LOW>;
+		};
+
+		dpaux@155c0000 {
+			status = "okay";
+		};
+	};
+
 	gpio-keys {
 		compatible = "gpio-keys";
 
@@ -120,5 +157,19 @@
 
 			vin-supply = <&vdd_3v3_sys>;
 		};
+
+		vdd_hdmi: regulator@101 {
+			compatible = "regulator-fixed";
+			reg = <101>;
+
+			regulator-name = "VDD_HDMI_5V0";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+
+			gpio = <&exp1 14 GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+
+			vin-supply = <&vdd_5v0_sys>;
+		};
 	};
 };
diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
index 54f418d05e15..a8baad7b80df 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
@@ -51,6 +51,10 @@
 		};
 	};
 
+	memory-controller@2c00000 {
+		status = "okay";
+	};
+
 	serial@3100000 {
 		status = "okay";
 	};
@@ -73,7 +77,7 @@
 		status = "okay";
 	};
 
-	i2c@3190000 {
+	ddc: i2c@3190000 {
 		status = "okay";
 	};
 
@@ -88,7 +92,7 @@
 	/* SDMMC1 (SD/MMC) */
 	sdhci@3400000 {
 		cd-gpios = <&gpio TEGRA_MAIN_GPIO(P, 5) GPIO_ACTIVE_LOW>;
-		wp-gpios = <&gpio TEGRA_MAIN_GPIO(P, 4) GPIO_ACTIVE_LOW>;
+		wp-gpios = <&gpio TEGRA_MAIN_GPIO(P, 4) GPIO_ACTIVE_HIGH>;
 
 		vqmmc-supply = <&vddio_sdmmc1>;
 	};
@@ -317,7 +321,7 @@
 						regulator-max-microvolt = <2800000>;
 					};
 
-					avdd_1v05: ldo7 {
+					vdd_hdmi_1v05: ldo7 {
 						regulator-name = "VDD_HDMI_1V05";
 						regulator-min-microvolt = <1050000>;
 						regulator-max-microvolt = <1050000>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
index 46d1f287fb0f..b762227f6aa1 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
@@ -3,6 +3,7 @@
 #include <dt-bindings/gpio/tegra186-gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/mailbox/tegra186-hsp.h>
+#include <dt-bindings/memory/tegra186-mc.h>
 #include <dt-bindings/power/tegra186-powergate.h>
 #include <dt-bindings/reset/tegra186-reset.h>
 #include <dt-bindings/thermal/tegra186-bpmp-thermal.h>
@@ -13,6 +14,12 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
+	misc@100000 {
+		compatible = "nvidia,tegra186-misc";
+		reg = <0x0 0x00100000 0x0 0xf000>,
+		      <0x0 0x0010f000 0x0 0x1000>;
+	};
+
 	gpio: gpio@2200000 {
 		compatible = "nvidia,tegra186-gpio";
 		reg-names = "security", "gpio";
@@ -61,6 +68,12 @@
 		snps,rxpbl = <8>;
 	};
 
+	memory-controller@2c00000 {
+		compatible = "nvidia,tegra186-mc";
+		reg = <0x0 0x02c00000 0x0 0xb0000>;
+		status = "disabled";
+	};
+
 	uarta: serial@3100000 {
 		compatible = "nvidia,tegra186-uart", "nvidia,tegra20-uart";
 		reg = <0x0 0x03100000 0x0 0x40>;
@@ -259,6 +272,13 @@
 		status = "disabled";
 	};
 
+	fuse@3820000 {
+		compatible = "nvidia,tegra186-efuse";
+		reg = <0x0 0x03820000 0x0 0x10000>;
+		clocks = <&bpmp TEGRA186_CLK_FUSE>;
+		clock-names = "fuse";
+	};
+
 	gic: interrupt-controller@3881000 {
 		compatible = "arm,gic-400";
 		#interrupt-cells = <3>;
@@ -437,6 +457,79 @@
 		};
 	};
 
+	smmu: iommu@12000000 {
+		compatible = "arm,mmu-500";
+		reg = <0 0x12000000 0 0x800000>;
+		interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
+		stream-match-mask = <0x7f80>;
+		#global-interrupts = <1>;
+		#iommu-cells = <1>;
+	};
+
 	host1x@13e00000 {
 		compatible = "nvidia,tegra186-host1x", "simple-bus";
 		reg = <0x0 0x13e00000 0x0 0x10000>,
@@ -453,6 +546,129 @@
 		#size-cells = <1>;
 
 		ranges = <0x15000000 0x0 0x15000000 0x01000000>;
+		iommus = <&smmu TEGRA186_SID_HOST1X>;
+
+		dpaux1: dpaux@15040000 {
+			compatible = "nvidia,tegra186-dpaux";
+			reg = <0x15040000 0x10000>;
+			interrupts = <GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&bpmp TEGRA186_CLK_DPAUX1>,
+				 <&bpmp TEGRA186_CLK_PLLDP>;
+			clock-names = "dpaux", "parent";
+			resets = <&bpmp TEGRA186_RESET_DPAUX1>;
+			reset-names = "dpaux";
+			status = "disabled";
+
+			power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISP>;
+
+			state_dpaux1_aux: pinmux-aux {
+				groups = "dpaux-io";
+				function = "aux";
+			};
+
+			state_dpaux1_i2c: pinmux-i2c {
+				groups = "dpaux-io";
+				function = "i2c";
+			};
+
+			state_dpaux1_off: pinmux-off {
+				groups = "dpaux-io";
+				function = "off";
+			};
+
+			i2c-bus {
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
+		display-hub@15200000 {
+			compatible = "nvidia,tegra186-display", "simple-bus";
+			resets = <&bpmp TEGRA186_RESET_NVDISPLAY0_MISC>,
+				 <&bpmp TEGRA186_RESET_NVDISPLAY0_WGRP0>,
+				 <&bpmp TEGRA186_RESET_NVDISPLAY0_WGRP1>,
+				 <&bpmp TEGRA186_RESET_NVDISPLAY0_WGRP2>,
+				 <&bpmp TEGRA186_RESET_NVDISPLAY0_WGRP3>,
+				 <&bpmp TEGRA186_RESET_NVDISPLAY0_WGRP4>,
+				 <&bpmp TEGRA186_RESET_NVDISPLAY0_WGRP5>;
+			reset-names = "misc", "wgrp0", "wgrp1", "wgrp2",
+				      "wgrp3", "wgrp4", "wgrp5";
+			clocks = <&bpmp TEGRA186_CLK_NVDISPLAY_DISP>,
+				 <&bpmp TEGRA186_CLK_NVDISPLAY_DSC>,
+				 <&bpmp TEGRA186_CLK_NVDISPLAYHUB>;
+			clock-names = "disp", "dsc", "hub";
+			status = "disabled";
+
+			power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISP>;
+
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			ranges = <0x15200000 0x15200000 0x40000>;
+
+			display@15200000 {
+				compatible = "nvidia,tegra186-dc";
+				reg = <0x15200000 0x10000>;
+				interrupts = <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&bpmp TEGRA186_CLK_NVDISPLAY_P0>;
+				clock-names = "dc";
+				resets = <&bpmp TEGRA186_RESET_NVDISPLAY0_HEAD0>;
+				reset-names = "dc";
+
+				power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISP>;
+				iommus = <&smmu TEGRA186_SID_NVDISPLAY>;
+
+				nvidia,outputs = <&dsia &dsib &sor0 &sor1>;
+				nvidia,head = <0>;
+			};
+
+			display@15210000 {
+				compatible = "nvidia,tegra186-dc";
+				reg = <0x15210000 0x10000>;
+				interrupts = <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&bpmp TEGRA186_CLK_NVDISPLAY_P1>;
+				clock-names = "dc";
+				resets = <&bpmp TEGRA186_RESET_NVDISPLAY0_HEAD1>;
+				reset-names = "dc";
+
+				power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISPB>;
+				iommus = <&smmu TEGRA186_SID_NVDISPLAY>;
+
+				nvidia,outputs = <&dsia &dsib &sor0 &sor1>;
+				nvidia,head = <1>;
+			};
+
+			display@15220000 {
+				compatible = "nvidia,tegra186-dc";
+				reg = <0x15220000 0x10000>;
+				interrupts = <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&bpmp TEGRA186_CLK_NVDISPLAY_P2>;
+				clock-names = "dc";
+				resets = <&bpmp TEGRA186_RESET_NVDISPLAY0_HEAD2>;
+				reset-names = "dc";
+
+				power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISPC>;
+				iommus = <&smmu TEGRA186_SID_NVDISPLAY>;
+
+				nvidia,outputs = <&sor0 &sor1>;
+				nvidia,head = <2>;
+			};
+		};
+
+		dsia: dsi@15300000 {
+			compatible = "nvidia,tegra186-dsi";
+			reg = <0x15300000 0x10000>;
+			interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&bpmp TEGRA186_CLK_DSI>,
+				 <&bpmp TEGRA186_CLK_DSIA_LP>,
+				 <&bpmp TEGRA186_CLK_PLLD>;
+			clock-names = "dsi", "lp", "parent";
+			resets = <&bpmp TEGRA186_RESET_DSI>;
+			reset-names = "dsi";
+			status = "disabled";
+
+			power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISP>;
+		};
 
 		vic@15340000 {
 			compatible = "nvidia,tegra186-vic";
@@ -465,6 +681,141 @@
 
 			power-domains = <&bpmp TEGRA186_POWER_DOMAIN_VIC>;
 		};
+
+		dsib: dsi@15400000 {
+			compatible = "nvidia,tegra186-dsi";
+			reg = <0x15400000 0x10000>;
+			interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&bpmp TEGRA186_CLK_DSIB>,
+				 <&bpmp TEGRA186_CLK_DSIB_LP>,
+				 <&bpmp TEGRA186_CLK_PLLD>;
+			clock-names = "dsi", "lp", "parent";
+			resets = <&bpmp TEGRA186_RESET_DSIB>;
+			reset-names = "dsi";
+			status = "disabled";
+
+			power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISP>;
+		};
+
+		sor0: sor@15540000 {
+			compatible = "nvidia,tegra186-sor";
+			reg = <0x15540000 0x10000>;
+			interrupts = <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&bpmp TEGRA186_CLK_SOR0>,
+				 <&bpmp TEGRA186_CLK_SOR0_OUT>,
+				 <&bpmp TEGRA186_CLK_PLLD2>,
+				 <&bpmp TEGRA186_CLK_PLLDP>,
+				 <&bpmp TEGRA186_CLK_SOR_SAFE>,
+				 <&bpmp TEGRA186_CLK_SOR0_PAD_CLKOUT>;
+			clock-names = "sor", "out", "parent", "dp", "safe",
+				      "pad";
+			resets = <&bpmp TEGRA186_RESET_SOR0>;
+			reset-names = "sor";
+			pinctrl-0 = <&state_dpaux_aux>;
+			pinctrl-1 = <&state_dpaux_i2c>;
+			pinctrl-2 = <&state_dpaux_off>;
+			pinctrl-names = "aux", "i2c", "off";
+			status = "disabled";
+
+			power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISP>;
+			nvidia,interface = <0>;
+		};
+
+		sor1: sor@15580000 {
+			compatible = "nvidia,tegra186-sor1";
+			reg = <0x15580000 0x10000>;
+			interrupts = <GIC_SPI 158 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&bpmp TEGRA186_CLK_SOR1>,
+				 <&bpmp TEGRA186_CLK_SOR1_OUT>,
+				 <&bpmp TEGRA186_CLK_PLLD3>,
+				 <&bpmp TEGRA186_CLK_PLLDP>,
+				 <&bpmp TEGRA186_CLK_SOR_SAFE>,
+				 <&bpmp TEGRA186_CLK_SOR1_PAD_CLKOUT>;
+			clock-names = "sor", "out", "parent", "dp", "safe",
+				      "pad";
+			resets = <&bpmp TEGRA186_RESET_SOR1>;
+			reset-names = "sor";
+			pinctrl-0 = <&state_dpaux1_aux>;
+			pinctrl-1 = <&state_dpaux1_i2c>;
+			pinctrl-2 = <&state_dpaux1_off>;
+			pinctrl-names = "aux", "i2c", "off";
+			status = "disabled";
+
+			power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISP>;
+			nvidia,interface = <1>;
+		};
+
+		dpaux: dpaux@155c0000 {
+			compatible = "nvidia,tegra186-dpaux";
+			reg = <0x155c0000 0x10000>;
+			interrupts = <GIC_SPI 159 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&bpmp TEGRA186_CLK_DPAUX>,
+				 <&bpmp TEGRA186_CLK_PLLDP>;
+			clock-names = "dpaux", "parent";
+			resets = <&bpmp TEGRA186_RESET_DPAUX>;
+			reset-names = "dpaux";
+			status = "disabled";
+
+			power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISP>;
+
+			state_dpaux_aux: pinmux-aux {
+				groups = "dpaux-io";
+				function = "aux";
+			};
+
+			state_dpaux_i2c: pinmux-i2c {
+				groups = "dpaux-io";
+				function = "i2c";
+			};
+
+			state_dpaux_off: pinmux-off {
+				groups = "dpaux-io";
+				function = "off";
+			};
+
+			i2c-bus {
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
+		padctl@15880000 {
+			compatible = "nvidia,tegra186-dsi-padctl";
+			reg = <0x15880000 0x10000>;
+			resets = <&bpmp TEGRA186_RESET_DSI>;
+			reset-names = "dsi";
+			status = "disabled";
+		};
+
+		dsic: dsi@15900000 {
+			compatible = "nvidia,tegra186-dsi";
+			reg = <0x15900000 0x10000>;
+			interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&bpmp TEGRA186_CLK_DSIC>,
+				 <&bpmp TEGRA186_CLK_DSIC_LP>,
+				 <&bpmp TEGRA186_CLK_PLLD>;
+			clock-names = "dsi", "lp", "parent";
+			resets = <&bpmp TEGRA186_RESET_DSIC>;
+			reset-names = "dsi";
+			status = "disabled";
+
+			power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISP>;
+		};
+
+		dsid: dsi@15940000 {
+			compatible = "nvidia,tegra186-dsi";
+			reg = <0x15940000 0x10000>;
+			interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&bpmp TEGRA186_CLK_DSID>,
+				 <&bpmp TEGRA186_CLK_DSID_LP>,
+				 <&bpmp TEGRA186_CLK_PLLD>;
+			clock-names = "dsi", "lp", "parent";
+			resets = <&bpmp TEGRA186_RESET_DSID>;
+			reset-names = "dsi";
+			status = "disabled";
+
+			power-domains = <&bpmp TEGRA186_POWER_DOMAIN_DISP>;
+		};
 	};
 
 	gpu@17000000 {
diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi
index d10d4430537a..212e6634c9ba 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi
@@ -297,6 +297,29 @@
 		};
 	};
 
+	cpus {
+		cpu@0 {
+			enable-method = "psci";
+		};
+
+		cpu@1 {
+			enable-method = "psci";
+		};
+
+		cpu@2 {
+			enable-method = "psci";
+		};
+
+		cpu@3 {
+			enable-method = "psci";
+		};
+	};
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
 	regulators {
 		vdd_gpu: regulator@100 {
 			compatible = "pwm-regulator";
diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2530.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2530.dtsi
index be6066ff97c9..d0dc03923723 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210-p2530.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210-p2530.dtsi
@@ -52,4 +52,27 @@
 			clock-frequency = <32768>;
 		};
 	};
+
+	cpus {
+		cpu@0 {
+			enable-method = "psci";
+		};
+
+		cpu@1 {
+			enable-method = "psci";
+		};
+
+		cpu@2 {
+			enable-method = "psci";
+		};
+
+		cpu@3 {
+			enable-method = "psci";
+		};
+	};
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
 };
diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
index 9bdf19f2cca7..9c2402108772 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
@@ -266,11 +266,11 @@
 			reg = <0x0 0x54580000 0x0 0x00040000>;
 			interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&tegra_car TEGRA210_CLK_SOR1>,
-				 <&tegra_car TEGRA210_CLK_SOR1_SRC>,
+				 <&tegra_car TEGRA210_CLK_SOR1_OUT>,
 				 <&tegra_car TEGRA210_CLK_PLL_D2_OUT0>,
 				 <&tegra_car TEGRA210_CLK_PLL_DP>,
 				 <&tegra_car TEGRA210_CLK_SOR_SAFE>;
-			clock-names = "sor", "source", "parent", "dp", "safe";
+			clock-names = "sor", "out", "parent", "dp", "safe";
 			resets = <&tegra_car 183>;
 			reset-names = "sor";
 			pinctrl-0 = <&state_dpaux1_aux>;
diff --git a/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi b/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi
index 33a3297eb284..9ff848792712 100644
--- a/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi
@@ -324,6 +324,7 @@
 				label = "apq8016-sbc:green:user4";
 				gpios = <&pm8916_gpios 2 GPIO_ACTIVE_HIGH>;
 				linux,default-trigger = "none";
+				panic-indicator;
 				default-state = "off";
 			};
 
diff --git a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi
index 4cb0b5834143..390a2fa28514 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi
@@ -278,7 +278,7 @@
 		pinconf {
 			pins = "gpio6", "gpio7";
 			drive-strength = <16>;
-			bias-disable = <0>;
+			bias-disable;
 		};
 	};
 
@@ -290,7 +290,7 @@
 		pinconf {
 			pins = "gpio6", "gpio7";
 			drive-strength = <2>;
-			bias-disable = <0>;
+			bias-disable;
 		};
 	};
 
@@ -302,7 +302,7 @@
 		pinconf {
 			pins = "gpio14", "gpio15";
 			drive-strength = <16>;
-			bias-disable = <0>;
+			bias-disable;
 		};
 	};
 
@@ -314,7 +314,7 @@
 		pinconf {
 			pins = "gpio14", "gpio15";
 			drive-strength = <2>;
-			bias-disable = <0>;
+			bias-disable;
 		};
 	};
 
@@ -326,7 +326,7 @@
 		pinconf {
 			pins = "gpio22", "gpio23";
 			drive-strength = <16>;
-			bias-disable = <0>;
+			bias-disable;
 		};
 	};
 
@@ -338,32 +338,7 @@
 		pinconf {
 			pins = "gpio22", "gpio23";
 			drive-strength = <2>;
-			bias-disable = <0>;
-		};
-	};
-
-	sdhc2_cd_pin {
-		sdc2_cd_on: cd_on {
-			pinmux {
-				function = "gpio";
-				pins = "gpio38";
-			};
-			pinconf {
-				pins = "gpio38";
-				drive-strength = <2>;
-				bias-pull-up;
-			};
-		};
-		sdc2_cd_off: cd_off {
-			pinmux {
-				function = "gpio";
-				pins = "gpio38";
-			};
-			pinconf {
-				pins = "gpio38";
-				drive-strength = <2>;
-				bias-disable;
-			};
+			bias-disable;
 		};
 	};
 
@@ -505,26 +480,25 @@
 		};
 	};
 
-	ext-codec-lines {
-		ext_codec_lines_act: lines_on {
+	pmx_sdc2_cd_pin {
+		sdc2_cd_on: cd_on {
 			pinmux {
 				function = "gpio";
-				pins = "gpio67";
+				pins = "gpio38";
 			};
 			pinconf {
-				pins = "gpio67";
-				drive-strength = <8>;
-				bias-disable;
-				output-high;
+				pins = "gpio38";
+				drive-strength = <2>;
+				bias-pull-up;
 			};
 		};
-		ext_codec_lines_sus: lines_off {
+		sdc2_cd_off: cd_off {
 			pinmux {
 				function = "gpio";
-				pins = "gpio67";
+				pins = "gpio38";
 			};
 			pinconf {
-				pins = "gpio67";
+				pins = "gpio38";
 				drive-strength = <2>;
 				bias-disable;
 			};
@@ -687,34 +661,16 @@
 			};
 		};
 		cdc_dmic_lines_sus: dmic_lines_off {
-			pinconf {
-				pins = "gpio0", "gpio1";
-				drive-strength = <2>;
-				bias-disable;
-			};
-		};
-	};
-
-	cross-conn-det {
-		cross_conn_det_act: lines_on {
-			pinmux {
-				function = "gpio";
-				pins = "gpio120";
-			};
-			pinconf {
-				pins = "gpio120";
-				drive-strength = <8>;
-				output-low;
-				bias-pull-down;
+			pinmux_dmic0_clk {
+				function = "dmic0_clk";
+				pins = "gpio0";
 			};
-		};
-		cross_conn_det_sus: lines_off {
-			pinmux {
-				function = "gpio";
-				pins = "gpio120";
+			pinmux_dmic0_data {
+				function = "dmic0_data";
+				pins = "gpio1";
 			};
 			pinconf {
-				pins = "gpio120";
+				pins = "gpio0", "gpio1";
 				drive-strength = <2>;
 				bias-disable;
 			};
diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi
index 6b2127a6ced1..e51b04900726 100644
--- a/arch/arm64/boot/dts/qcom/msm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi
@@ -355,7 +355,7 @@
 
 		blsp_spi1: spi@78b5000 {
 			compatible = "qcom,spi-qup-v2.2.1";
-			reg = <0x078b5000 0x600>;
+			reg = <0x078b5000 0x500>;
 			interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc GCC_BLSP1_QUP1_SPI_APPS_CLK>,
 				 <&gcc GCC_BLSP1_AHB_CLK>;
@@ -372,7 +372,7 @@
 
 		blsp_spi2: spi@78b6000 {
 			compatible = "qcom,spi-qup-v2.2.1";
-			reg = <0x078b6000 0x600>;
+			reg = <0x078b6000 0x500>;
 			interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc GCC_BLSP1_QUP2_SPI_APPS_CLK>,
 				 <&gcc GCC_BLSP1_AHB_CLK>;
@@ -389,7 +389,7 @@
 
 		blsp_spi3: spi@78b7000 {
 			compatible = "qcom,spi-qup-v2.2.1";
-			reg = <0x078b7000 0x600>;
+			reg = <0x078b7000 0x500>;
 			interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc GCC_BLSP1_QUP3_SPI_APPS_CLK>,
 				 <&gcc GCC_BLSP1_AHB_CLK>;
@@ -406,7 +406,7 @@
 
 		blsp_spi4: spi@78b8000 {
 			compatible = "qcom,spi-qup-v2.2.1";
-			reg = <0x078b8000 0x600>;
+			reg = <0x078b8000 0x500>;
 			interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc GCC_BLSP1_QUP4_SPI_APPS_CLK>,
 				 <&gcc GCC_BLSP1_AHB_CLK>;
@@ -423,7 +423,7 @@
 
 		blsp_spi5: spi@78b9000 {
 			compatible = "qcom,spi-qup-v2.2.1";
-			reg = <0x078b9000 0x600>;
+			reg = <0x078b9000 0x500>;
 			interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc GCC_BLSP1_QUP5_SPI_APPS_CLK>,
 				 <&gcc GCC_BLSP1_AHB_CLK>;
@@ -440,7 +440,7 @@
 
 		blsp_spi6: spi@78ba000 {
 			compatible = "qcom,spi-qup-v2.2.1";
-			reg = <0x078ba000 0x600>;
+			reg = <0x078ba000 0x500>;
 			interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc GCC_BLSP1_QUP6_SPI_APPS_CLK>,
 				 <&gcc GCC_BLSP1_AHB_CLK>;
@@ -457,10 +457,10 @@
 
 		blsp_i2c2: i2c@78b6000 {
 			compatible = "qcom,i2c-qup-v2.2.1";
-			reg = <0x78b6000 0x1000>;
+			reg = <0x078b6000 0x500>;
 			interrupts = <GIC_SPI 96 0>;
 			clocks = <&gcc GCC_BLSP1_AHB_CLK>,
-				<&gcc GCC_BLSP1_QUP2_I2C_APPS_CLK>;
+				 <&gcc GCC_BLSP1_QUP2_I2C_APPS_CLK>;
 			clock-names = "iface", "core";
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&i2c2_default>;
@@ -472,10 +472,10 @@
 
 		blsp_i2c4: i2c@78b8000 {
 			compatible = "qcom,i2c-qup-v2.2.1";
-			reg = <0x78b8000 0x1000>;
+			reg = <0x078b8000 0x500>;
 			interrupts = <GIC_SPI 98 0>;
 			clocks = <&gcc GCC_BLSP1_AHB_CLK>,
-				<&gcc GCC_BLSP1_QUP4_I2C_APPS_CLK>;
+				 <&gcc GCC_BLSP1_QUP4_I2C_APPS_CLK>;
 			clock-names = "iface", "core";
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&i2c4_default>;
@@ -487,10 +487,10 @@
 
 		blsp_i2c6: i2c@78ba000 {
 			compatible = "qcom,i2c-qup-v2.2.1";
-			reg = <0x78ba000 0x1000>;
+			reg = <0x078ba000 0x500>;
 			interrupts = <GIC_SPI 100 0>;
 			clocks = <&gcc GCC_BLSP1_AHB_CLK>,
-				<&gcc GCC_BLSP1_QUP6_I2C_APPS_CLK>;
+				 <&gcc GCC_BLSP1_QUP6_I2C_APPS_CLK>;
 			clock-names = "iface", "core";
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&i2c6_default>;
@@ -906,6 +906,7 @@
 					    "dsi_phy_regulator";
 
 				#clock-cells = <1>;
+				#phy-cells = <0>;
 
 				clocks = <&gcc GCC_MDSS_AHB_CLK>;
 				clock-names = "iface_clk";
@@ -1435,8 +1436,8 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		qcom,ipc-1 = <&apcs 0 13>;
-		qcom,ipc-6 = <&apcs 0 19>;
+		qcom,ipc-1 = <&apcs 8 13>;
+		qcom,ipc-3 = <&apcs 8 19>;
 
 		apps_smsm: apps@0 {
 			reg = <0>;
diff --git a/arch/arm64/boot/dts/qcom/pm8916.dtsi b/arch/arm64/boot/dts/qcom/pm8916.dtsi
index 0223e60d8b6a..196b1c0ceb9b 100644
--- a/arch/arm64/boot/dts/qcom/pm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/pm8916.dtsi
@@ -97,47 +97,45 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-                wcd_codec: codec@f000 {
-                       compatible = "qcom,pm8916-wcd-analog-codec";
-	               reg = <0xf000 0x200>;
-	               reg-names = "pmic-codec-core";
-	               clocks = <&gcc GCC_CODEC_DIGCODEC_CLK>;
-	               clock-names = "mclk";
-	               interrupt-parent = <&spmi_bus>;
-	               interrupts = <0x1 0xf0 0x0 IRQ_TYPE_NONE>,
-	                            <0x1 0xf0 0x1 IRQ_TYPE_NONE>,
-	                            <0x1 0xf0 0x2 IRQ_TYPE_NONE>,
-	                            <0x1 0xf0 0x3 IRQ_TYPE_NONE>,
-	                            <0x1 0xf0 0x4 IRQ_TYPE_NONE>,
-	                            <0x1 0xf0 0x5 IRQ_TYPE_NONE>,
-	                            <0x1 0xf0 0x6 IRQ_TYPE_NONE>,
-	                            <0x1 0xf0 0x7 IRQ_TYPE_NONE>,
-	                            <0x1 0xf1 0x0 IRQ_TYPE_NONE>,
-	                            <0x1 0xf1 0x1 IRQ_TYPE_NONE>,
-	                            <0x1 0xf1 0x2 IRQ_TYPE_NONE>,
-	                            <0x1 0xf1 0x3 IRQ_TYPE_NONE>,
-	                            <0x1 0xf1 0x4 IRQ_TYPE_NONE>,
-	                            <0x1 0xf1 0x5 IRQ_TYPE_NONE>;
-	               interrupt-names = "cdc_spk_cnp_int",
-	                                 "cdc_spk_clip_int",
-	                                 "cdc_spk_ocp_int",
-	                                 "mbhc_ins_rem_det1",
-	                                 "mbhc_but_rel_det",
-	                                 "mbhc_but_press_det",
-	                                 "mbhc_ins_rem_det",
-	                                 "mbhc_switch_int",
-	                                 "cdc_ear_ocp_int",
-	                                 "cdc_hphr_ocp_int",
-	                                 "cdc_hphl_ocp_det",
-	                                 "cdc_ear_cnp_int",
-	                                 "cdc_hphr_cnp_int",
-	                                 "cdc_hphl_cnp_int";
-	               vdd-cdc-io-supply = <&pm8916_l5>;
-	               vdd-cdc-tx-rx-cx-supply = <&pm8916_l5>;
-	               vdd-micbias-supply = <&pm8916_l13>;
-	               #sound-dai-cells = <1>;
-
-                };
-
+		wcd_codec: codec@f000 {
+			compatible = "qcom,pm8916-wcd-analog-codec";
+			reg = <0xf000 0x200>;
+			reg-names = "pmic-codec-core";
+			clocks = <&gcc GCC_CODEC_DIGCODEC_CLK>;
+			clock-names = "mclk";
+			interrupt-parent = <&spmi_bus>;
+			interrupts = <0x1 0xf0 0x0 IRQ_TYPE_NONE>,
+				     <0x1 0xf0 0x1 IRQ_TYPE_NONE>,
+				     <0x1 0xf0 0x2 IRQ_TYPE_NONE>,
+				     <0x1 0xf0 0x3 IRQ_TYPE_NONE>,
+				     <0x1 0xf0 0x4 IRQ_TYPE_NONE>,
+				     <0x1 0xf0 0x5 IRQ_TYPE_NONE>,
+				     <0x1 0xf0 0x6 IRQ_TYPE_NONE>,
+				     <0x1 0xf0 0x7 IRQ_TYPE_NONE>,
+				     <0x1 0xf1 0x0 IRQ_TYPE_NONE>,
+				     <0x1 0xf1 0x1 IRQ_TYPE_NONE>,
+				     <0x1 0xf1 0x2 IRQ_TYPE_NONE>,
+				     <0x1 0xf1 0x3 IRQ_TYPE_NONE>,
+				     <0x1 0xf1 0x4 IRQ_TYPE_NONE>,
+				     <0x1 0xf1 0x5 IRQ_TYPE_NONE>;
+			interrupt-names = "cdc_spk_cnp_int",
+					  "cdc_spk_clip_int",
+					  "cdc_spk_ocp_int",
+					  "mbhc_ins_rem_det1",
+					  "mbhc_but_rel_det",
+					  "mbhc_but_press_det",
+					  "mbhc_ins_rem_det",
+					  "mbhc_switch_int",
+					  "cdc_ear_ocp_int",
+					  "cdc_hphr_ocp_int",
+					  "cdc_hphl_ocp_det",
+					  "cdc_ear_cnp_int",
+					  "cdc_hphr_cnp_int",
+					  "cdc_hphl_cnp_int";
+			vdd-cdc-io-supply = <&pm8916_l5>;
+			vdd-cdc-tx-rx-cx-supply = <&pm8916_l5>;
+			vdd-micbias-supply = <&pm8916_l13>;
+			#sound-dai-cells = <1>;
+		};
 	};
 };
diff --git a/arch/arm64/boot/dts/renesas/Makefile b/arch/arm64/boot/dts/renesas/Makefile
index 646198d82903..2186d0193b73 100644
--- a/arch/arm64/boot/dts/renesas/Makefile
+++ b/arch/arm64/boot/dts/renesas/Makefile
@@ -6,5 +6,6 @@ dtb-$(CONFIG_ARCH_R8A7795) += r8a7795-es1-salvator-x.dtb r8a7795-es1-h3ulcb.dtb
 dtb-$(CONFIG_ARCH_R8A7795) += r8a7795-es1-h3ulcb-kf.dtb
 dtb-$(CONFIG_ARCH_R8A7796) += r8a7796-salvator-x.dtb r8a7796-m3ulcb.dtb
 dtb-$(CONFIG_ARCH_R8A7796) += r8a7796-m3ulcb-kf.dtb
-dtb-$(CONFIG_ARCH_R8A77970) += r8a77970-eagle.dtb
+dtb-$(CONFIG_ARCH_R8A7796) += r8a7796-salvator-xs.dtb
+dtb-$(CONFIG_ARCH_R8A77970) += r8a77970-eagle.dtb r8a77970-v3msk.dtb
 dtb-$(CONFIG_ARCH_R8A77995) += r8a77995-draak.dtb
diff --git a/arch/arm64/boot/dts/renesas/r8a7795-es1-salvator-x.dts b/arch/arm64/boot/dts/renesas/r8a7795-es1-salvator-x.dts
index 3f7d5f51e428..7f2a3d923f21 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795-es1-salvator-x.dts
+++ b/arch/arm64/boot/dts/renesas/r8a7795-es1-salvator-x.dts
@@ -1,5 +1,5 @@
 /*
- * Device Tree Source for the Salvator-X board
+ * Device Tree Source for the Salvator-X board with R-Car H3 ES1.x
  *
  * Copyright (C) 2015 Renesas Electronics Corp.
  *
diff --git a/arch/arm64/boot/dts/renesas/r8a7795-es1.dtsi b/arch/arm64/boot/dts/renesas/r8a7795-es1.dtsi
index 655dd30639c5..26769a11a190 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795-es1.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a7795-es1.dtsi
@@ -21,6 +21,26 @@
 		status = "disabled";
 	};
 
+	/delete-node/ mmu@febe0000;
+	/delete-node/ mmu@fe980000;
+	/delete-node/ mmu@fd960000;
+	/delete-node/ mmu@fd970000;
+
+	ipmmu_mp1: mmu@ec680000 {
+		compatible = "renesas,ipmmu-r8a7795";
+		reg = <0 0xec680000 0 0x1000>;
+		renesas,ipmmu-main = <&ipmmu_mm 5>;
+		#iommu-cells = <1>;
+	};
+
+	ipmmu_sy: mmu@e7730000 {
+		compatible = "renesas,ipmmu-r8a7795";
+		reg = <0 0xe7730000 0 0x1000>;
+		renesas,ipmmu-main = <&ipmmu_mm 8>;
+		#iommu-cells = <1>;
+		status = "disabled";
+	};
+
 	/delete-node/ usb-phy@ee0e0200;
 	/delete-node/ usb@ee0e0100;
 	/delete-node/ usb@ee0e0000;
@@ -35,6 +55,7 @@
 		clocks = <&cpg CPG_MOD 613>;
 		power-domains = <&sysc R8A7795_PD_A3VP>;
 		resets = <&cpg 613>;
+		iommus = <&ipmmu_vp0 2>;
 	};
 
 	vspi2: vsp@fe9c0000 {
@@ -54,6 +75,7 @@
 		clocks = <&cpg CPG_MOD 609>;
 		power-domains = <&sysc R8A7795_PD_A3VP>;
 		resets = <&cpg 609>;
+		iommus = <&ipmmu_vp0 10>;
 	};
 
 	vspd3: vsp@fea38000 {
@@ -73,6 +95,7 @@
 		clocks = <&cpg CPG_MOD 600>;
 		power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
 		resets = <&cpg 600>;
+		iommus = <&ipmmu_vi0 11>;
 	};
 
 	fdp1@fe948000 {
@@ -86,6 +109,68 @@
 	};
 };
 
+&gpio1 {
+	gpio-ranges = <&pfc 0 32 28>;
+};
+
+&ipmmu_vi0 {
+	renesas,ipmmu-main = <&ipmmu_mm 11>;
+};
+
+&ipmmu_vp0 {
+	renesas,ipmmu-main = <&ipmmu_mm 12>;
+};
+
+&ipmmu_vc0 {
+	renesas,ipmmu-main = <&ipmmu_mm 9>;
+};
+
+&ipmmu_vc1 {
+	renesas,ipmmu-main = <&ipmmu_mm 10>;
+};
+
+&ipmmu_rt {
+	renesas,ipmmu-main = <&ipmmu_mm 7>;
+};
+
+&audma0 {
+	iommus = <&ipmmu_mp1 0>, <&ipmmu_mp1 1>,
+	       <&ipmmu_mp1 2>, <&ipmmu_mp1 3>,
+	       <&ipmmu_mp1 4>, <&ipmmu_mp1 5>,
+	       <&ipmmu_mp1 6>, <&ipmmu_mp1 7>,
+	       <&ipmmu_mp1 8>, <&ipmmu_mp1 9>,
+	       <&ipmmu_mp1 10>, <&ipmmu_mp1 11>,
+	       <&ipmmu_mp1 12>, <&ipmmu_mp1 13>,
+	       <&ipmmu_mp1 14>, <&ipmmu_mp1 15>;
+};
+
+&audma1 {
+	iommus = <&ipmmu_mp1 16>, <&ipmmu_mp1 17>,
+	       <&ipmmu_mp1 18>, <&ipmmu_mp1 19>,
+	       <&ipmmu_mp1 20>, <&ipmmu_mp1 21>,
+	       <&ipmmu_mp1 22>, <&ipmmu_mp1 23>,
+	       <&ipmmu_mp1 24>, <&ipmmu_mp1 25>,
+	       <&ipmmu_mp1 26>, <&ipmmu_mp1 27>,
+	       <&ipmmu_mp1 28>, <&ipmmu_mp1 29>,
+	       <&ipmmu_mp1 30>, <&ipmmu_mp1 31>;
+};
+
+&fcpvb1 {
+	iommus = <&ipmmu_vp0 7>;
+};
+
+&fcpf1 {
+	iommus = <&ipmmu_vp0 1>;
+};
+
+&fcpvi1 {
+	iommus = <&ipmmu_vp0 9>;
+};
+
+&fcpvd2 {
+	iommus = <&ipmmu_vi0 10>;
+};
+
 &du {
 	vsps = <&vspd0 &vspd1 &vspd2 &vspd3>;
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts b/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
index 17953070f38d..af467419266a 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
+++ b/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
@@ -1,5 +1,5 @@
 /*
- * Device Tree Source for the Salvator-X board
+ * Device Tree Source for the Salvator-X board with R-Car H3 ES2.0
  *
  * Copyright (C) 2015 Renesas Electronics Corp.
  *
diff --git a/arch/arm64/boot/dts/renesas/r8a7795-salvator-xs.dts b/arch/arm64/boot/dts/renesas/r8a7795-salvator-xs.dts
index 7675de5d4f2c..8b50ceb746e8 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795-salvator-xs.dts
+++ b/arch/arm64/boot/dts/renesas/r8a7795-salvator-xs.dts
@@ -1,5 +1,5 @@
 /*
- * Device Tree Source for the Salvator-X 2nd version board
+ * Device Tree Source for the Salvator-X 2nd version board with R-Car H3 ES2.0
  *
  * Copyright (C) 2015-2017 Renesas Electronics Corp.
  *
diff --git a/arch/arm64/boot/dts/renesas/r8a7795.dtsi b/arch/arm64/boot/dts/renesas/r8a7795.dtsi
index 15ef292a8d9f..d12df6f2ff09 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a7795.dtsi
@@ -30,11 +30,6 @@
 		i2c7 = &i2c_dvfs;
 	};
 
-	psci {
-		compatible = "arm,psci-1.0", "arm,psci-0.2";
-		method = "smc";
-	};
-
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -184,6 +179,35 @@
 		clock-frequency = <0>;
 	};
 
+	pmu_a57 {
+		compatible = "arm,cortex-a57-pmu";
+		interrupts-extended = <&gic GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,
+		                      <&gic GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>,
+				      <&gic GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>,
+				      <&gic GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&a57_0>,
+				     <&a57_1>,
+				     <&a57_2>,
+				     <&a57_3>;
+	};
+
+	pmu_a53 {
+		compatible = "arm,cortex-a53-pmu";
+		interrupts-extended = <&gic GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>,
+				      <&gic GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
+				      <&gic GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>,
+				      <&gic GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&a53_0>,
+				     <&a53_1>,
+				     <&a53_2>,
+				     <&a53_3>;
+	};
+
+	psci {
+		compatible = "arm,psci-1.0", "arm,psci-0.2";
+		method = "smc";
+	};
+
 	soc: soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
@@ -240,7 +264,7 @@
 			interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
 			#gpio-cells = <2>;
 			gpio-controller;
-			gpio-ranges = <&pfc 0 32 28>;
+			gpio-ranges = <&pfc 0 32 29>;
 			#interrupt-cells = <2>;
 			interrupt-controller;
 			clocks = <&cpg CPG_MOD 911>;
@@ -338,42 +362,6 @@
 			resets = <&cpg 905>;
 		};
 
-		pmu_a57 {
-			compatible = "arm,cortex-a57-pmu";
-			interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-affinity = <&a57_0>,
-					     <&a57_1>,
-					     <&a57_2>,
-					     <&a57_3>;
-		};
-
-		pmu_a53 {
-			compatible = "arm,cortex-a53-pmu";
-			interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-affinity = <&a53_0>,
-					     <&a53_1>,
-					     <&a53_2>,
-					     <&a53_3>;
-		};
-
-		timer {
-			compatible = "arm,armv8-timer";
-			interrupts = <GIC_PPI 13
-					(GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 14
-					(GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 11
-					(GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 10
-					(GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>;
-		};
-
 		cpg: clock-controller@e6150000 {
 			compatible = "renesas,r8a7795-cpg-mssr";
 			reg = <0 0xe6150000 0 0x1000>;
@@ -421,6 +409,146 @@
 			resets = <&cpg 407>;
 		};
 
+		ipmmu_vi0: mmu@febd0000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xfebd0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 14>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
+		ipmmu_vi1: mmu@febe0000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xfebe0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 15>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_vp0: mmu@fe990000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xfe990000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 16>;
+			power-domains = <&sysc R8A7795_PD_A3VP>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_vp1: mmu@fe980000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xfe980000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 17>;
+			power-domains = <&sysc R8A7795_PD_A3VP>;
+			#iommu-cells = <1>;
+		};
+
+		ipmmu_vc0: mmu@fe6b0000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xfe6b0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 12>;
+			power-domains = <&sysc R8A7795_PD_A3VC>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_vc1: mmu@fe6f0000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xfe6f0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 13>;
+			power-domains = <&sysc R8A7795_PD_A3VC>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_pv0: mmu@fd800000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xfd800000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 6>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_pv2: mmu@fd960000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xfd960000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 8>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_pv3: mmu@fd970000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xfd970000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 9>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_ir: mmu@ff8b0000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xff8b0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 3>;
+			power-domains = <&sysc R8A7795_PD_A3IR>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_hc: mmu@e6570000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xe6570000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 2>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_rt: mmu@ffc80000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xffc80000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 10>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_mp0: mmu@ec670000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xec670000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 4>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_ds0: mmu@e6740000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xe6740000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 0>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
+		ipmmu_ds1: mmu@e7740000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xe7740000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 1>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
+		ipmmu_mm: mmu@e67b0000 {
+			compatible = "renesas,ipmmu-r8a7795";
+			reg = <0 0xe67b0000 0 0x1000>;
+			interrupts = <GIC_SPI 196 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 197 IRQ_TYPE_LEVEL_HIGH>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
 		dmac0: dma-controller@e6700000 {
 			compatible = "renesas,dmac-r8a7795",
 				     "renesas,rcar-dmac";
@@ -453,6 +581,14 @@
 			resets = <&cpg 219>;
 			#dma-cells = <1>;
 			dma-channels = <16>;
+			iommus = <&ipmmu_ds0 0>, <&ipmmu_ds0 1>,
+			       <&ipmmu_ds0 2>, <&ipmmu_ds0 3>,
+			       <&ipmmu_ds0 4>, <&ipmmu_ds0 5>,
+			       <&ipmmu_ds0 6>, <&ipmmu_ds0 7>,
+			       <&ipmmu_ds0 8>, <&ipmmu_ds0 9>,
+			       <&ipmmu_ds0 10>, <&ipmmu_ds0 11>,
+			       <&ipmmu_ds0 12>, <&ipmmu_ds0 13>,
+			       <&ipmmu_ds0 14>, <&ipmmu_ds0 15>;
 		};
 
 		dmac1: dma-controller@e7300000 {
@@ -487,6 +623,14 @@
 			resets = <&cpg 218>;
 			#dma-cells = <1>;
 			dma-channels = <16>;
+			iommus = <&ipmmu_ds1 0>, <&ipmmu_ds1 1>,
+			       <&ipmmu_ds1 2>, <&ipmmu_ds1 3>,
+			       <&ipmmu_ds1 4>, <&ipmmu_ds1 5>,
+			       <&ipmmu_ds1 6>, <&ipmmu_ds1 7>,
+			       <&ipmmu_ds1 8>, <&ipmmu_ds1 9>,
+			       <&ipmmu_ds1 10>, <&ipmmu_ds1 11>,
+			       <&ipmmu_ds1 12>, <&ipmmu_ds1 13>,
+			       <&ipmmu_ds1 14>, <&ipmmu_ds1 15>;
 		};
 
 		dmac2: dma-controller@e7310000 {
@@ -521,6 +665,14 @@
 			resets = <&cpg 217>;
 			#dma-cells = <1>;
 			dma-channels = <16>;
+			iommus = <&ipmmu_ds1 16>, <&ipmmu_ds1 17>,
+			       <&ipmmu_ds1 18>, <&ipmmu_ds1 19>,
+			       <&ipmmu_ds1 20>, <&ipmmu_ds1 21>,
+			       <&ipmmu_ds1 22>, <&ipmmu_ds1 23>,
+			       <&ipmmu_ds1 24>, <&ipmmu_ds1 25>,
+			       <&ipmmu_ds1 26>, <&ipmmu_ds1 27>,
+			       <&ipmmu_ds1 28>, <&ipmmu_ds1 29>,
+			       <&ipmmu_ds1 30>, <&ipmmu_ds1 31>;
 		};
 
 		audma0: dma-controller@ec700000 {
@@ -555,6 +707,14 @@
 			resets = <&cpg 502>;
 			#dma-cells = <1>;
 			dma-channels = <16>;
+			iommus = <&ipmmu_mp0 0>, <&ipmmu_mp0 1>,
+			       <&ipmmu_mp0 2>, <&ipmmu_mp0 3>,
+			       <&ipmmu_mp0 4>, <&ipmmu_mp0 5>,
+			       <&ipmmu_mp0 6>, <&ipmmu_mp0 7>,
+			       <&ipmmu_mp0 8>, <&ipmmu_mp0 9>,
+			       <&ipmmu_mp0 10>, <&ipmmu_mp0 11>,
+			       <&ipmmu_mp0 12>, <&ipmmu_mp0 13>,
+			       <&ipmmu_mp0 14>, <&ipmmu_mp0 15>;
 		};
 
 		audma1: dma-controller@ec720000 {
@@ -589,6 +749,14 @@
 			resets = <&cpg 501>;
 			#dma-cells = <1>;
 			dma-channels = <16>;
+			iommus = <&ipmmu_mp0 16>, <&ipmmu_mp0 17>,
+			       <&ipmmu_mp0 18>, <&ipmmu_mp0 19>,
+			       <&ipmmu_mp0 20>, <&ipmmu_mp0 21>,
+			       <&ipmmu_mp0 22>, <&ipmmu_mp0 23>,
+			       <&ipmmu_mp0 24>, <&ipmmu_mp0 25>,
+			       <&ipmmu_mp0 26>, <&ipmmu_mp0 27>,
+			       <&ipmmu_mp0 28>, <&ipmmu_mp0 29>,
+			       <&ipmmu_mp0 30>, <&ipmmu_mp0 31>;
 		};
 
 		avb: ethernet@e6800000 {
@@ -631,6 +799,7 @@
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
 			resets = <&cpg 812>;
 			phy-mode = "rgmii-txid";
+			iommus = <&ipmmu_ds0 16>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";
@@ -1459,6 +1628,20 @@
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
 			resets = <&cpg 815>;
 			status = "disabled";
+			iommus = <&ipmmu_hc 2>;
+		};
+
+		usb3_phy0: usb-phy@e65ee000 {
+			compatible = "renesas,r8a7795-usb3-phy",
+				     "renesas,rcar-gen3-usb3-phy";
+			reg = <0 0xe65ee000 0 0x90>;
+			clocks = <&cpg CPG_MOD 328>, <&usb3s0_clk>,
+				 <&usb_extal_clk>;
+			clock-names = "usb3-if", "usb3s_clk", "usb_extal";
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			resets = <&cpg 328>;
+			#phy-cells = <0>;
+			status = "disabled";
 		};
 
 		xhci0: usb@ee000000 {
@@ -1539,7 +1722,8 @@
 		};
 
 		sdhi0: sd@ee100000 {
-			compatible = "renesas,sdhi-r8a7795";
+			compatible = "renesas,sdhi-r8a7795",
+				     "renesas,rcar-gen3-sdhi";
 			reg = <0 0xee100000 0 0x2000>;
 			interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 314>;
@@ -1550,7 +1734,8 @@
 		};
 
 		sdhi1: sd@ee120000 {
-			compatible = "renesas,sdhi-r8a7795";
+			compatible = "renesas,sdhi-r8a7795",
+				     "renesas,rcar-gen3-sdhi";
 			reg = <0 0xee120000 0 0x2000>;
 			interrupts = <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 313>;
@@ -1561,7 +1746,8 @@
 		};
 
 		sdhi2: sd@ee140000 {
-			compatible = "renesas,sdhi-r8a7795";
+			compatible = "renesas,sdhi-r8a7795",
+				     "renesas,rcar-gen3-sdhi";
 			reg = <0 0xee140000 0 0x2000>;
 			interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 312>;
@@ -1572,7 +1758,8 @@
 		};
 
 		sdhi3: sd@ee160000 {
-			compatible = "renesas,sdhi-r8a7795";
+			compatible = "renesas,sdhi-r8a7795",
+				     "renesas,rcar-gen3-sdhi";
 			reg = <0 0xee160000 0 0x2000>;
 			interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 311>;
@@ -1873,6 +2060,7 @@
 			clocks = <&cpg CPG_MOD 606>;
 			power-domains = <&sysc R8A7795_PD_A3VP>;
 			resets = <&cpg 606>;
+			iommus = <&ipmmu_vp1 7>;
 		};
 
 		fcpf0: fcp@fe950000 {
@@ -1881,6 +2069,7 @@
 			clocks = <&cpg CPG_MOD 615>;
 			power-domains = <&sysc R8A7795_PD_A3VP>;
 			resets = <&cpg 615>;
+			iommus = <&ipmmu_vp0 0>;
 		};
 
 		fcpf1: fcp@fe951000 {
@@ -1889,6 +2078,7 @@
 			clocks = <&cpg CPG_MOD 614>;
 			power-domains = <&sysc R8A7795_PD_A3VP>;
 			resets = <&cpg 614>;
+			iommus = <&ipmmu_vp1 1>;
 		};
 
 		vspbd: vsp@fe960000 {
@@ -1908,6 +2098,7 @@
 			clocks = <&cpg CPG_MOD 607>;
 			power-domains = <&sysc R8A7795_PD_A3VP>;
 			resets = <&cpg 607>;
+			iommus = <&ipmmu_vp0 5>;
 		};
 
 		vspi0: vsp@fe9a0000 {
@@ -1927,6 +2118,7 @@
 			clocks = <&cpg CPG_MOD 611>;
 			power-domains = <&sysc R8A7795_PD_A3VP>;
 			resets = <&cpg 611>;
+			iommus = <&ipmmu_vp0 8>;
 		};
 
 		vspi1: vsp@fe9b0000 {
@@ -1946,6 +2138,7 @@
 			clocks = <&cpg CPG_MOD 610>;
 			power-domains = <&sysc R8A7795_PD_A3VP>;
 			resets = <&cpg 610>;
+			iommus = <&ipmmu_vp1 9>;
 		};
 
 		vspd0: vsp@fea20000 {
@@ -1965,6 +2158,7 @@
 			clocks = <&cpg CPG_MOD 603>;
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
 			resets = <&cpg 603>;
+			iommus = <&ipmmu_vi0 8>;
 		};
 
 		vspd1: vsp@fea28000 {
@@ -1984,6 +2178,7 @@
 			clocks = <&cpg CPG_MOD 602>;
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
 			resets = <&cpg 602>;
+			iommus = <&ipmmu_vi0 9>;
 		};
 
 		vspd2: vsp@fea30000 {
@@ -2003,6 +2198,7 @@
 			clocks = <&cpg CPG_MOD 601>;
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
 			resets = <&cpg 601>;
+			iommus = <&ipmmu_vi1 10>;
 		};
 
 		fdp1@fe940000 {
@@ -2136,49 +2332,78 @@
 			#thermal-sensor-cells = <1>;
 			status = "okay";
 		};
+	};
 
-		thermal-zones {
-			sensor_thermal1: sensor-thermal1 {
-				polling-delay-passive = <250>;
-				polling-delay = <1000>;
-				thermal-sensors = <&tsc 0>;
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts-extended = <&gic GIC_PPI 13
+				       (GIC_CPU_MASK_SIMPLE(8) |
+				       IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 14
+				       (GIC_CPU_MASK_SIMPLE(8) |
+				       IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 11
+				       (GIC_CPU_MASK_SIMPLE(8) |
+				       IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 10
+				       (GIC_CPU_MASK_SIMPLE(8) |
+				       IRQ_TYPE_LEVEL_LOW)>;
+	};
 
-				trips {
-					sensor1_crit: sensor1-crit {
-						temperature = <120000>;
-						hysteresis = <2000>;
-						type = "critical";
-					};
+	thermal-zones {
+		sensor_thermal1: sensor-thermal1 {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsc 0>;
+
+			trips {
+				sensor1_crit: sensor1-crit {
+					temperature = <120000>;
+					hysteresis = <2000>;
+					type = "critical";
 				};
 			};
+		};
 
-			sensor_thermal2: sensor-thermal2 {
-				polling-delay-passive = <250>;
-				polling-delay = <1000>;
-				thermal-sensors = <&tsc 1>;
+		sensor_thermal2: sensor-thermal2 {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsc 1>;
 
-				trips {
-					sensor2_crit: sensor2-crit {
-						temperature = <120000>;
-						hysteresis = <2000>;
-						type = "critical";
-					};
+			trips {
+				sensor2_crit: sensor2-crit {
+					temperature = <120000>;
+					hysteresis = <2000>;
+					type = "critical";
 				};
 			};
+		};
 
-			sensor_thermal3: sensor-thermal3 {
-				polling-delay-passive = <250>;
-				polling-delay = <1000>;
-				thermal-sensors = <&tsc 2>;
+		sensor_thermal3: sensor-thermal3 {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsc 2>;
 
-				trips {
-					sensor3_crit: sensor3-crit {
-						temperature = <120000>;
-						hysteresis = <2000>;
-						type = "critical";
-					};
+			trips {
+				sensor3_crit: sensor3-crit {
+					temperature = <120000>;
+					hysteresis = <2000>;
+					type = "critical";
 				};
 			};
 		};
 	};
+
+	/* External USB clocks - can be overridden by the board */
+	usb3s0_clk: usb3s0 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	usb_extal_clk: usb_extal {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a7796-salvator-x.dts b/arch/arm64/boot/dts/renesas/r8a7796-salvator-x.dts
index b317be03306e..498c9e807dc4 100644
--- a/arch/arm64/boot/dts/renesas/r8a7796-salvator-x.dts
+++ b/arch/arm64/boot/dts/renesas/r8a7796-salvator-x.dts
@@ -1,5 +1,5 @@
 /*
- * Device Tree Source for the Salvator-X board
+ * Device Tree Source for the Salvator-X board with R-Car M3-W
  *
  * Copyright (C) 2016 Renesas Electronics Corp.
  *
diff --git a/arch/arm64/boot/dts/renesas/r8a7796-salvator-xs.dts b/arch/arm64/boot/dts/renesas/r8a7796-salvator-xs.dts
new file mode 100644
index 000000000000..2c37055efa94
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r8a7796-salvator-xs.dts
@@ -0,0 +1,58 @@
+/*
+ * Device Tree Source for the Salvator-X 2nd version board with R-Car M3-W
+ *
+ * Copyright (C) 2015-2017 Renesas Electronics Corp.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/dts-v1/;
+#include "r8a7796.dtsi"
+#include "salvator-xs.dtsi"
+
+/ {
+	model = "Renesas Salvator-X 2nd version board based on r8a7796";
+	compatible = "renesas,salvator-xs", "renesas,r8a7796";
+
+	memory@48000000 {
+		device_type = "memory";
+		/* first 128MB is reserved for secure area. */
+		reg = <0x0 0x48000000 0x0 0x78000000>;
+	};
+
+	memory@600000000 {
+		device_type = "memory";
+		reg = <0x6 0x00000000 0x0 0x80000000>;
+	};
+};
+
+&du {
+	clocks = <&cpg CPG_MOD 724>,
+		 <&cpg CPG_MOD 723>,
+		 <&cpg CPG_MOD 722>,
+		 <&cpg CPG_MOD 727>,
+		 <&versaclock6 1>,
+		 <&x21_clk>,
+		 <&versaclock6 2>;
+	clock-names = "du.0", "du.1", "du.2", "lvds.0",
+		      "dclkin.0", "dclkin.1", "dclkin.2";
+};
+
+&hdmi0 {
+	status = "okay";
+
+	ports {
+		port@1 {
+			reg = <1>;
+			rcar_dw_hdmi0_out: endpoint {
+				remote-endpoint = <&hdmi0_con>;
+			};
+		};
+	};
+};
+
+&hdmi0_con {
+	remote-endpoint = <&rcar_dw_hdmi0_out>;
+};
diff --git a/arch/arm64/boot/dts/renesas/r8a7796.dtsi b/arch/arm64/boot/dts/renesas/r8a7796.dtsi
index f2b2e40c655e..c5192d513d7d 100644
--- a/arch/arm64/boot/dts/renesas/r8a7796.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a7796.dtsi
@@ -30,9 +30,34 @@
 		i2c7 = &i2c_dvfs;
 	};
 
-	psci {
-		compatible = "arm,psci-1.0", "arm,psci-0.2";
-		method = "smc";
+	/*
+	 * The external audio clocks are configured as 0 Hz fixed frequency
+	 * clocks by default.
+	 * Boards that provide audio clocks should override them.
+	 */
+	audio_clk_a: audio_clk_a {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	audio_clk_b: audio_clk_b {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	audio_clk_c: audio_clk_c {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	/* External CAN clock - to be overridden by boards that provide it */
+	can_clk: can {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
 	};
 
 	cpus {
@@ -122,34 +147,32 @@
 		clock-frequency = <0>;
 	};
 
-	/*
-	 * The external audio clocks are configured as 0 Hz fixed frequency
-	 * clocks by default.
-	 * Boards that provide audio clocks should override them.
-	 */
-	audio_clk_a: audio_clk_a {
+	/* External PCIe clock - can be overridden by the board */
+	pcie_bus_clk: pcie_bus {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <0>;
 	};
 
-	audio_clk_b: audio_clk_b {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <0>;
+	pmu_a57 {
+		compatible = "arm,cortex-a57-pmu";
+		interrupts-extended = <&gic GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,
+				      <&gic GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&a57_0>, <&a57_1>;
 	};
 
-	audio_clk_c: audio_clk_c {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <0>;
+	pmu_a53 {
+		compatible = "arm,cortex-a53-pmu";
+		interrupts-extended = <&gic GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>,
+				      <&gic GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
+				      <&gic GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>,
+				      <&gic GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&a53_0>, <&a53_1>, <&a53_2>, <&a53_3>;
 	};
 
-	/* External CAN clock - to be overridden by boards that provide it */
-	can_clk: can {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <0>;
+	psci {
+		compatible = "arm,psci-1.0", "arm,psci-0.2";
+		method = "smc";
 	};
 
 	/* External SCIF clock - to be overridden by boards that provide it */
@@ -159,13 +182,6 @@
 		clock-frequency = <0>;
 	};
 
-	/* External PCIe clock - can be overridden by the board */
-	pcie_bus_clk: pcie_bus {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <0>;
-	};
-
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
@@ -190,18 +206,6 @@
 			resets = <&cpg 408>;
 		};
 
-		timer {
-			compatible = "arm,armv8-timer";
-			interrupts = <GIC_PPI 13
-					(GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 14
-					(GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 11
-					(GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>,
-				     <GIC_PPI 10
-					(GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>;
-		};
-
 		wdt0: watchdog@e6020000 {
 			compatible = "renesas,r8a7796-wdt",
 				     "renesas,rcar-gen3-wdt";
@@ -337,24 +341,98 @@
 			reg = <0 0xe6060000 0 0x50c>;
 		};
 
-		pmu_a57 {
-			compatible = "arm,cortex-a57-pmu";
-			interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-affinity = <&a57_0>,
-					     <&a57_1>;
+		ipmmu_vi0: mmu@febd0000 {
+			compatible = "renesas,ipmmu-r8a7796";
+			reg = <0 0xfebd0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 9>;
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
+		ipmmu_vc0: mmu@fe6b0000 {
+			compatible = "renesas,ipmmu-r8a7796";
+			reg = <0 0xfe6b0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 8>;
+			power-domains = <&sysc R8A7796_PD_A3VC>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_pv0: mmu@fd800000 {
+			compatible = "renesas,ipmmu-r8a7796";
+			reg = <0 0xfd800000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 5>;
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
+		ipmmu_pv1: mmu@fd950000 {
+			compatible = "renesas,ipmmu-r8a7796";
+			reg = <0 0xfd950000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 6>;
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_ir: mmu@ff8b0000 {
+			compatible = "renesas,ipmmu-r8a7796";
+			reg = <0 0xff8b0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 3>;
+			power-domains = <&sysc R8A7796_PD_A3IR>;
+			#iommu-cells = <1>;
+			status = "disabled";
 		};
 
-		pmu_a53 {
-			compatible = "arm,cortex-a53-pmu";
-			interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-affinity = <&a53_0>,
-					     <&a53_1>,
-					     <&a53_2>,
-					     <&a53_3>;
+		ipmmu_hc: mmu@e6570000 {
+			compatible = "renesas,ipmmu-r8a7796";
+			reg = <0 0xe6570000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 2>;
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_rt: mmu@ffc80000 {
+			compatible = "renesas,ipmmu-r8a7796";
+			reg = <0 0xffc80000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 7>;
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_mp: mmu@ec670000 {
+			compatible = "renesas,ipmmu-r8a7796";
+			reg = <0 0xec670000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 4>;
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
+		ipmmu_ds0: mmu@e6740000 {
+			compatible = "renesas,ipmmu-r8a7796";
+			reg = <0 0xe6740000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 0>;
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
+		ipmmu_ds1: mmu@e7740000 {
+			compatible = "renesas,ipmmu-r8a7796";
+			reg = <0 0xe7740000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 1>;
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
+		ipmmu_mm: mmu@e67b0000 {
+			compatible = "renesas,ipmmu-r8a7796";
+			reg = <0 0xe67b0000 0 0x1000>;
+			interrupts = <GIC_SPI 196 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 197 IRQ_TYPE_LEVEL_HIGH>;
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
 		};
 
 		cpg: clock-controller@e6150000 {
@@ -817,6 +895,7 @@
 			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
 			resets = <&cpg 812>;
 			phy-mode = "rgmii-txid";
+			iommus = <&ipmmu_ds0 16>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";
@@ -1101,6 +1180,14 @@
 			resets = <&cpg 219>;
 			#dma-cells = <1>;
 			dma-channels = <16>;
+			iommus = <&ipmmu_ds0 0>, <&ipmmu_ds0 1>,
+			       <&ipmmu_ds0 2>, <&ipmmu_ds0 3>,
+			       <&ipmmu_ds0 4>, <&ipmmu_ds0 5>,
+			       <&ipmmu_ds0 6>, <&ipmmu_ds0 7>,
+			       <&ipmmu_ds0 8>, <&ipmmu_ds0 9>,
+			       <&ipmmu_ds0 10>, <&ipmmu_ds0 11>,
+			       <&ipmmu_ds0 12>, <&ipmmu_ds0 13>,
+			       <&ipmmu_ds0 14>, <&ipmmu_ds0 15>;
 		};
 
 		dmac1: dma-controller@e7300000 {
@@ -1135,6 +1222,14 @@
 			resets = <&cpg 218>;
 			#dma-cells = <1>;
 			dma-channels = <16>;
+			iommus = <&ipmmu_ds1 0>, <&ipmmu_ds1 1>,
+			       <&ipmmu_ds1 2>, <&ipmmu_ds1 3>,
+			       <&ipmmu_ds1 4>, <&ipmmu_ds1 5>,
+			       <&ipmmu_ds1 6>, <&ipmmu_ds1 7>,
+			       <&ipmmu_ds1 8>, <&ipmmu_ds1 9>,
+			       <&ipmmu_ds1 10>, <&ipmmu_ds1 11>,
+			       <&ipmmu_ds1 12>, <&ipmmu_ds1 13>,
+			       <&ipmmu_ds1 14>, <&ipmmu_ds1 15>;
 		};
 
 		dmac2: dma-controller@e7310000 {
@@ -1169,6 +1264,14 @@
 			resets = <&cpg 217>;
 			#dma-cells = <1>;
 			dma-channels = <16>;
+			iommus = <&ipmmu_ds1 16>, <&ipmmu_ds1 17>,
+			       <&ipmmu_ds1 18>, <&ipmmu_ds1 19>,
+			       <&ipmmu_ds1 20>, <&ipmmu_ds1 21>,
+			       <&ipmmu_ds1 22>, <&ipmmu_ds1 23>,
+			       <&ipmmu_ds1 24>, <&ipmmu_ds1 25>,
+			       <&ipmmu_ds1 26>, <&ipmmu_ds1 27>,
+			       <&ipmmu_ds1 28>, <&ipmmu_ds1 29>,
+			       <&ipmmu_ds1 30>, <&ipmmu_ds1 31>;
 		};
 
 		audma0: dma-controller@ec700000 {
@@ -1203,6 +1306,14 @@
 			resets = <&cpg 502>;
 			#dma-cells = <1>;
 			dma-channels = <16>;
+			iommus = <&ipmmu_mp 0>, <&ipmmu_mp 1>,
+			       <&ipmmu_mp 2>, <&ipmmu_mp 3>,
+			       <&ipmmu_mp 4>, <&ipmmu_mp 5>,
+			       <&ipmmu_mp 6>, <&ipmmu_mp 7>,
+			       <&ipmmu_mp 8>, <&ipmmu_mp 9>,
+			       <&ipmmu_mp 10>, <&ipmmu_mp 11>,
+			       <&ipmmu_mp 12>, <&ipmmu_mp 13>,
+			       <&ipmmu_mp 14>, <&ipmmu_mp 15>;
 		};
 
 		audma1: dma-controller@ec720000 {
@@ -1237,6 +1348,14 @@
 			resets = <&cpg 501>;
 			#dma-cells = <1>;
 			dma-channels = <16>;
+			iommus = <&ipmmu_mp 16>, <&ipmmu_mp 17>,
+			       <&ipmmu_mp 18>, <&ipmmu_mp 19>,
+			       <&ipmmu_mp 20>, <&ipmmu_mp 21>,
+			       <&ipmmu_mp 22>, <&ipmmu_mp 23>,
+			       <&ipmmu_mp 24>, <&ipmmu_mp 25>,
+			       <&ipmmu_mp 26>, <&ipmmu_mp 27>,
+			       <&ipmmu_mp 28>, <&ipmmu_mp 29>,
+			       <&ipmmu_mp 30>, <&ipmmu_mp 31>;
 		};
 
 		usb_dmac0: dma-controller@e65a0000 {
@@ -1284,6 +1403,19 @@
 			status = "disabled";
 		};
 
+		usb3_phy0: usb-phy@e65ee000 {
+			compatible = "renesas,r8a7796-usb3-phy",
+				     "renesas,rcar-gen3-usb3-phy";
+			reg = <0 0xe65ee000 0 0x90>;
+			clocks = <&cpg CPG_MOD 328>, <&usb3s0_clk>,
+				 <&usb_extal_clk>;
+			clock-names = "usb3-if", "usb3s_clk", "usb_extal";
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			resets = <&cpg 328>;
+			#phy-cells = <0>;
+			status = "disabled";
+		};
+
 		xhci0: usb@ee000000 {
 			compatible = "renesas,xhci-r8a7796",
 				     "renesas,rcar-gen3-xhci";
@@ -1380,7 +1512,8 @@
 		};
 
 		sdhi0: sd@ee100000 {
-			compatible = "renesas,sdhi-r8a7796";
+			compatible = "renesas,sdhi-r8a7796",
+				     "renesas,rcar-gen3-sdhi";
 			reg = <0 0xee100000 0 0x2000>;
 			interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 314>;
@@ -1391,7 +1524,8 @@
 		};
 
 		sdhi1: sd@ee120000 {
-			compatible = "renesas,sdhi-r8a7796";
+			compatible = "renesas,sdhi-r8a7796",
+				     "renesas,rcar-gen3-sdhi";
 			reg = <0 0xee120000 0 0x2000>;
 			interrupts = <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 313>;
@@ -1402,7 +1536,8 @@
 		};
 
 		sdhi2: sd@ee140000 {
-			compatible = "renesas,sdhi-r8a7796";
+			compatible = "renesas,sdhi-r8a7796",
+				     "renesas,rcar-gen3-sdhi";
 			reg = <0 0xee140000 0 0x2000>;
 			interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 312>;
@@ -1413,7 +1548,8 @@
 		};
 
 		sdhi3: sd@ee160000 {
-			compatible = "renesas,sdhi-r8a7796";
+			compatible = "renesas,sdhi-r8a7796",
+				     "renesas,rcar-gen3-sdhi";
 			reg = <0 0xee160000 0 0x2000>;
 			interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 311>;
@@ -1438,50 +1574,6 @@
 			status = "okay";
 		};
 
-		thermal-zones {
-			sensor_thermal1: sensor-thermal1 {
-				polling-delay-passive = <250>;
-				polling-delay = <1000>;
-				thermal-sensors = <&tsc 0>;
-
-				trips {
-					sensor1_crit: sensor1-crit {
-						temperature = <120000>;
-						hysteresis = <2000>;
-						type = "critical";
-					};
-				};
-			};
-
-			sensor_thermal2: sensor-thermal2 {
-				polling-delay-passive = <250>;
-				polling-delay = <1000>;
-				thermal-sensors = <&tsc 1>;
-
-				trips {
-					sensor2_crit: sensor2-crit {
-						temperature = <120000>;
-						hysteresis = <2000>;
-						type = "critical";
-					};
-				};
-			};
-
-			sensor_thermal3: sensor-thermal3 {
-				polling-delay-passive = <250>;
-				polling-delay = <1000>;
-				thermal-sensors = <&tsc 2>;
-
-				trips {
-					sensor3_crit: sensor3-crit {
-						temperature = <120000>;
-						hysteresis = <2000>;
-						type = "critical";
-					};
-				};
-			};
-		};
-
 		rcar_sound: sound@ec500000 {
 			/*
 			 * #sound-dai-cells is required
@@ -1679,10 +1771,12 @@
 		};
 
 		pciec0: pcie@fe000000 {
+			reg = <0 0xfe000000 0 0x80000>;
 			/* placeholder */
 		};
 
 		pciec1: pcie@ee800000 {
+			reg = <0 0xee800000 0 0x80000>;
 			/* placeholder */
 		};
 
@@ -1740,6 +1834,7 @@
 			clocks = <&cpg CPG_MOD 611>;
 			power-domains = <&sysc R8A7796_PD_A3VC>;
 			resets = <&cpg 611>;
+			iommus = <&ipmmu_vc0 19>;
 		};
 
 		vspd0: vsp@fea20000 {
@@ -1759,6 +1854,7 @@
 			clocks = <&cpg CPG_MOD 603>;
 			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
 			resets = <&cpg 603>;
+			iommus = <&ipmmu_vi0 8>;
 		};
 
 		vspd1: vsp@fea28000 {
@@ -1778,6 +1874,7 @@
 			clocks = <&cpg CPG_MOD 602>;
 			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
 			resets = <&cpg 602>;
+			iommus = <&ipmmu_vi0 9>;
 		};
 
 		vspd2: vsp@fea30000 {
@@ -1797,6 +1894,7 @@
 			clocks = <&cpg CPG_MOD 601>;
 			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
 			resets = <&cpg 601>;
+			iommus = <&ipmmu_vi0 10>;
 		};
 
 		hdmi0: hdmi@fead0000 {
@@ -1884,4 +1982,69 @@
 			resets = <&cpg 822>;
 		};
 	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>,
+				      <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	thermal-zones {
+		sensor_thermal1: sensor-thermal1 {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsc 0>;
+
+			trips {
+				sensor1_crit: sensor1-crit {
+					temperature = <120000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+
+		sensor_thermal2: sensor-thermal2 {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsc 1>;
+
+			trips {
+				sensor2_crit: sensor2-crit {
+					temperature = <120000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+
+		sensor_thermal3: sensor-thermal3 {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsc 2>;
+
+			trips {
+				sensor3_crit: sensor3-crit {
+					temperature = <120000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+	};
+
+	/* External USB clocks - can be overridden by the board */
+	usb3s0_clk: usb3s0 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	usb_extal_clk: usb_extal {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
index a711e77cc6a5..8fe5c193e049 100644
--- a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
@@ -33,6 +33,17 @@
 	};
 };
 
+&avb {
+	renesas,no-ether-link;
+	phy-handle = <&phy0>;
+	status = "okay";
+
+	phy0: ethernet-phy@0 {
+		rxc-skew-ps = <1500>;
+		reg = <0>;
+	};
+};
+
 &extal_clk {
 	clock-frequency = <16666666>;
 };
@@ -41,17 +52,11 @@
 	clock-frequency = <32768>;
 };
 
-&scif0 {
+&rwdt {
+	timeout-sec = <60>;
 	status = "okay";
 };
 
-&avb {
-	renesas,no-ether-link;
-	phy-handle = <&phy0>;
+&scif0 {
 	status = "okay";
-
-	phy0: ethernet-phy@0 {
-		rxc-skew-ps = <1500>;
-		reg = <0>;
-	};
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts b/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts
new file mode 100644
index 000000000000..8624ca87d6b2
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts
@@ -0,0 +1,55 @@
+/*
+ * Device Tree Source for the V3M Starter Kit board
+ *
+ * Copyright (C) 2017 Renesas Electronics Corp.
+ * Copyright (C) 2017 Cogent Embedded, Inc.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/dts-v1/;
+#include "r8a77970.dtsi"
+
+/ {
+	model = "Renesas V3M Starter Kit board";
+	compatible = "renesas,v3msk", "renesas,r8a77970";
+
+	aliases {
+		serial0 = &scif0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@48000000 {
+		device_type = "memory";
+		/* first 128MB is reserved for secure area. */
+		reg = <0x0 0x48000000 0x0 0x38000000>;
+	};
+};
+
+&avb {
+	renesas,no-ether-link;
+	phy-handle = <&phy0>;
+	status = "okay";
+
+	phy0: ethernet-phy@0 {
+		rxc-skew-ps = <1500>;
+		reg = <0>;
+	};
+};
+
+&extal_clk {
+	clock-frequency = <16666666>;
+};
+
+&extalr_clk {
+	clock-frequency = <32768>;
+};
+
+&scif0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/renesas/r8a77970.dtsi b/arch/arm64/boot/dts/renesas/r8a77970.dtsi
index 97e6981938e7..c35a117fc447 100644
--- a/arch/arm64/boot/dts/renesas/r8a77970.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77970.dtsi
@@ -9,9 +9,10 @@
  * kind, whether express or implied.
  */
 
-#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/clock/r8a77970-cpg-mssr.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
-#include <dt-bindings/clock/renesas-cpg-mssr.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/power/r8a77970-sysc.h>
 
 / {
 	compatible = "renesas,r8a77970";
@@ -31,15 +32,15 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0>;
-			clocks = <&cpg CPG_CORE 0>;
-			power-domains = <&sysc 5>;
+			clocks = <&cpg CPG_CORE R8A77970_CLK_Z2>;
+			power-domains = <&sysc R8A77970_PD_CA53_CPU0>;
 			next-level-cache = <&L2_CA53>;
 			enable-method = "psci";
 		};
 
 		L2_CA53: cache-controller {
 			compatible = "cache";
-			power-domains = <&sysc 21>;
+			power-domains = <&sysc R8A77970_PD_CA53_SCU>;
 			cache-unified;
 			cache-level = <2>;
 		};
@@ -87,7 +88,7 @@
 				      IRQ_TYPE_LEVEL_HIGH)>;
 			clocks = <&cpg CPG_MOD 408>;
 			clock-names = "clk";
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 408>;
 		};
 
@@ -103,6 +104,16 @@
 						  IRQ_TYPE_LEVEL_LOW)>;
 		};
 
+		rwdt: watchdog@e6020000 {
+			compatible = "renesas,r8a77970-wdt",
+				     "renesas,rcar-gen3-wdt";
+			reg = <0 0xe6020000 0 0x0c>;
+			clocks = <&cpg CPG_MOD 402>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
+			resets = <&cpg 402>;
+			status = "disabled";
+		};
+
 		cpg: clock-controller@e6150000 {
 			compatible = "renesas,r8a77970-cpg-mssr";
 			reg = <0 0xe6150000 0 0x1000>;
@@ -124,6 +135,49 @@
 			#power-domain-cells = <1>;
 		};
 
+		ipmmu_vi0: mmu@febd0000 {
+			compatible = "renesas,ipmmu-r8a77970";
+			reg = <0 0xfebd0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 9>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_ir: mmu@ff8b0000 {
+			compatible = "renesas,ipmmu-r8a77970";
+			reg = <0 0xff8b0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 3>;
+			power-domains = <&sysc R8A77970_PD_A3IR>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_rt: mmu@ffc80000 {
+			compatible = "renesas,ipmmu-r8a77970";
+			reg = <0 0xffc80000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 7>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
+		ipmmu_ds1: mmu@e7740000 {
+			compatible = "renesas,ipmmu-r8a77970";
+			reg = <0 0xe7740000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 1>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
+		ipmmu_mm: mmu@e67b0000 {
+			compatible = "renesas,ipmmu-r8a77970";
+			reg = <0 0xe67b0000 0 0x1000>;
+			interrupts = <GIC_SPI 196 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 197 IRQ_TYPE_LEVEL_HIGH>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
+			#iommu-cells = <1>;
+		};
+
 		intc_ex: interrupt-controller@e61c0000 {
 			compatible = "renesas,intc-ex-r8a77970", "renesas,irqc";
 			#interrupt-cells = <2>;
@@ -136,7 +190,7 @@
 				      GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH
 				      GIC_SPI 161 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 407>;
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 407>;
 		};
 
@@ -163,10 +217,14 @@
 					  "ch4", "ch5", "ch6", "ch7";
 			clocks = <&cpg CPG_MOD 218>;
 			clock-names = "fck";
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 218>;
 			#dma-cells = <1>;
 			dma-channels = <8>;
+			iommus = <&ipmmu_ds1 0>, <&ipmmu_ds1 1>,
+			       <&ipmmu_ds1 2>, <&ipmmu_ds1 3>,
+			       <&ipmmu_ds1 4>, <&ipmmu_ds1 5>,
+			       <&ipmmu_ds1 6>, <&ipmmu_ds1 7>;
 		};
 
 		dmac2: dma-controller@e7310000 {
@@ -187,10 +245,14 @@
 					  "ch4", "ch5", "ch6", "ch7";
 			clocks = <&cpg CPG_MOD 217>;
 			clock-names = "fck";
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 217>;
 			#dma-cells = <1>;
 			dma-channels = <8>;
+			iommus = <&ipmmu_ds1 16>, <&ipmmu_ds1 17>,
+			       <&ipmmu_ds1 18>, <&ipmmu_ds1 19>,
+			       <&ipmmu_ds1 20>, <&ipmmu_ds1 21>,
+			       <&ipmmu_ds1 22>, <&ipmmu_ds1 23>;
 		};
 
 		hscif0: serial@e6540000 {
@@ -200,13 +262,13 @@
 			reg = <0 0xe6540000 0 96>;
 			interrupts = <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 520>,
-				 <&cpg CPG_CORE 9>,
+				 <&cpg CPG_CORE R8A77970_CLK_S2D1>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			dmas = <&dmac1 0x31>, <&dmac1 0x30>,
 			       <&dmac2 0x31>, <&dmac2 0x30>;
 			dma-names = "tx", "rx", "tx", "rx";
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 520>;
 			status = "disabled";
 		};
@@ -218,13 +280,13 @@
 			reg = <0 0xe6550000 0 96>;
 			interrupts = <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 519>,
-				 <&cpg CPG_CORE 9>,
+				 <&cpg CPG_CORE R8A77970_CLK_S2D1>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			dmas = <&dmac1 0x33>, <&dmac1 0x32>,
 			       <&dmac2 0x33>, <&dmac2 0x32>;
 			dma-names = "tx", "rx", "tx", "rx";
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 519>;
 			status = "disabled";
 		};
@@ -236,13 +298,13 @@
 			reg = <0 0xe6560000 0 96>;
 			interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 518>,
-				 <&cpg CPG_CORE 9>,
+				 <&cpg CPG_CORE R8A77970_CLK_S2D1>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			dmas = <&dmac1 0x35>, <&dmac1 0x34>,
 			       <&dmac2 0x35>, <&dmac2 0x34>;
 			dma-names = "tx", "rx", "tx", "rx";
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 518>;
 			status = "disabled";
 		};
@@ -253,13 +315,13 @@
 			reg = <0 0xe66a0000 0 96>;
 			interrupts = <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 517>,
-				 <&cpg CPG_CORE 9>,
+				 <&cpg CPG_CORE R8A77970_CLK_S2D1>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			dmas = <&dmac1 0x37>, <&dmac1 0x36>,
 			       <&dmac2 0x37>, <&dmac2 0x36>;
 			dma-names = "tx", "rx", "tx", "rx";
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 517>;
 			status = "disabled";
 		};
@@ -271,13 +333,13 @@
 			reg = <0 0xe6e60000 0 64>;
 			interrupts = <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 207>,
-				 <&cpg CPG_CORE 9>,
+				 <&cpg CPG_CORE R8A77970_CLK_S2D1>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			dmas = <&dmac1 0x51>, <&dmac1 0x50>,
 			       <&dmac2 0x51>, <&dmac2 0x50>;
 			dma-names = "tx", "rx", "tx", "rx";
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 207>;
 			status = "disabled";
 		};
@@ -289,13 +351,13 @@
 			reg = <0 0xe6e68000 0 64>;
 			interrupts = <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 206>,
-				 <&cpg CPG_CORE 9>,
+				 <&cpg CPG_CORE R8A77970_CLK_S2D1>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			dmas = <&dmac1 0x53>, <&dmac1 0x52>,
 			       <&dmac2 0x53>, <&dmac2 0x52>;
 			dma-names = "tx", "rx", "tx", "rx";
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 206>;
 			status = "disabled";
 		};
@@ -307,13 +369,13 @@
 			reg = <0 0xe6c50000 0 64>;
 			interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 204>,
-				 <&cpg CPG_CORE 9>,
+				 <&cpg CPG_CORE R8A77970_CLK_S2D1>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			dmas = <&dmac1 0x57>, <&dmac1 0x56>,
 			       <&dmac2 0x57>, <&dmac2 0x56>;
 			dma-names = "tx", "rx", "tx", "rx";
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 204>;
 			status = "disabled";
 		};
@@ -324,13 +386,13 @@
 			reg = <0 0xe6c40000 0 64>;
 			interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 203>,
-				 <&cpg CPG_CORE 9>,
+				 <&cpg CPG_CORE R8A77970_CLK_S2D1>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			dmas = <&dmac1 0x59>, <&dmac1 0x58>,
 			       <&dmac2 0x59>, <&dmac2 0x58>;
 			dma-names = "tx", "rx", "tx", "rx";
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 203>;
 			status = "disabled";
 		};
@@ -372,9 +434,10 @@
 					  "ch20", "ch21", "ch22", "ch23",
 					  "ch24";
 			clocks = <&cpg CPG_MOD 812>;
-			power-domains = <&sysc 32>;
+			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
 			resets = <&cpg 812>;
 			phy-mode = "rgmii-id";
+			iommus = <&ipmmu_rt 3>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 		};
diff --git a/arch/arm64/boot/dts/renesas/r8a77995.dtsi b/arch/arm64/boot/dts/renesas/r8a77995.dtsi
index 788e3afae6e3..cff42cd1a6c8 100644
--- a/arch/arm64/boot/dts/renesas/r8a77995.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77995.dtsi
@@ -51,6 +51,13 @@
 		clock-frequency = <0>;
 	};
 
+	/* External CAN clock - to be overridden by boards that provide it */
+	can_clk: can {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
 	scif_clk: scif {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
@@ -108,6 +115,88 @@
 			interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
+		ipmmu_vi0: mmu@febd0000 {
+			compatible = "renesas,ipmmu-r8a77995";
+			reg = <0 0xfebd0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 14>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_vp0: mmu@fe990000 {
+			compatible = "renesas,ipmmu-r8a77995";
+			reg = <0 0xfe990000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 16>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_vc0: mmu@fe6b0000 {
+			compatible = "renesas,ipmmu-r8a77995";
+			reg = <0 0xfe6b0000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 12>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_pv0: mmu@fd800000 {
+			compatible = "renesas,ipmmu-r8a77995";
+			reg = <0 0xfd800000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 6>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_hc: mmu@e6570000 {
+			compatible = "renesas,ipmmu-r8a77995";
+			reg = <0 0xe6570000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 2>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_rt: mmu@ffc80000 {
+			compatible = "renesas,ipmmu-r8a77995";
+			reg = <0 0xffc80000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 10>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_mp: mmu@ec670000 {
+			compatible = "renesas,ipmmu-r8a77995";
+			reg = <0 0xec670000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 4>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_ds0: mmu@e6740000 {
+			compatible = "renesas,ipmmu-r8a77995";
+			reg = <0 0xe6740000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 0>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_ds1: mmu@e7740000 {
+			compatible = "renesas,ipmmu-r8a77995";
+			reg = <0 0xe7740000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 1>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+		ipmmu_mm: mmu@e67b0000 {
+			compatible = "renesas,ipmmu-r8a77995";
+			reg = <0 0xe67b0000 0 0x1000>;
+			interrupts = <GIC_SPI 196 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 197 IRQ_TYPE_LEVEL_HIGH>;
+			#iommu-cells = <1>;
+			status = "disabled";
+		};
+
+
 		cpg: clock-controller@e6150000 {
 			compatible = "renesas,r8a77995-cpg-mssr";
 			reg = <0 0xe6150000 0 0x1000>;
@@ -155,6 +244,78 @@
 			resets = <&cpg 407>;
 		};
 
+		dmac0: dma-controller@e6700000 {
+			compatible = "renesas,dmac-r8a77995",
+				     "renesas,rcar-dmac";
+			reg = <0 0xe6700000 0 0x10000>;
+			interrupts = <GIC_SPI 199 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 200 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 201 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 202 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 203 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 204 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 205 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 206 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 207 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "error",
+					"ch0", "ch1", "ch2", "ch3",
+					"ch4", "ch5", "ch6", "ch7";
+			clocks = <&cpg CPG_MOD 219>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
+			resets = <&cpg 219>;
+			#dma-cells = <1>;
+			dma-channels = <8>;
+		};
+
+		dmac1: dma-controller@e7300000 {
+			compatible = "renesas,dmac-r8a77995",
+				     "renesas,rcar-dmac";
+			reg = <0 0xe7300000 0 0x10000>;
+			interrupts = <GIC_SPI 220 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 216 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 217 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 218 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 219 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 309 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 310 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 311 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "error",
+					"ch0", "ch1", "ch2", "ch3",
+					"ch4", "ch5", "ch6", "ch7";
+			clocks = <&cpg CPG_MOD 218>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
+			resets = <&cpg 218>;
+			#dma-cells = <1>;
+			dma-channels = <8>;
+		};
+
+		dmac2: dma-controller@e7310000 {
+			compatible = "renesas,dmac-r8a77995",
+				     "renesas,rcar-dmac";
+			reg = <0 0xe7310000 0 0x10000>;
+			interrupts = <GIC_SPI 416 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 417 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 418 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 419 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 420 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 423 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "error",
+					"ch0", "ch1", "ch2", "ch3",
+					"ch4", "ch5", "ch6", "ch7";
+			clocks = <&cpg CPG_MOD 217>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
+			resets = <&cpg 217>;
+			#dma-cells = <1>;
+			dma-channels = <8>;
+		};
+
 		gpio0: gpio@e6050000 {
 			compatible = "renesas,gpio-r8a77995",
 				     "renesas,rcar-gen3-gpio",
@@ -267,6 +428,63 @@
 			resets = <&cpg 906>;
 		};
 
+		can0: can@e6c30000 {
+			compatible = "renesas,can-r8a77995",
+				     "renesas,rcar-gen3-can";
+			reg = <0 0xe6c30000 0 0x1000>;
+			interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 916>,
+			       <&cpg CPG_CORE R8A77995_CLK_CANFD>,
+			       <&can_clk>;
+			clock-names = "clkp1", "clkp2", "can_clk";
+			assigned-clocks = <&cpg CPG_CORE R8A77995_CLK_CANFD>;
+			assigned-clock-rates = <40000000>;
+			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
+			resets = <&cpg 916>;
+			status = "disabled";
+		};
+
+		can1: can@e6c38000 {
+			compatible = "renesas,can-r8a77995",
+				     "renesas,rcar-gen3-can";
+			reg = <0 0xe6c38000 0 0x1000>;
+			interrupts = <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 915>,
+			       <&cpg CPG_CORE R8A77995_CLK_CANFD>,
+			       <&can_clk>;
+			clock-names = "clkp1", "clkp2", "can_clk";
+			assigned-clocks = <&cpg CPG_CORE R8A77995_CLK_CANFD>;
+			assigned-clock-rates = <40000000>;
+			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
+			resets = <&cpg 915>;
+			status = "disabled";
+		};
+
+		canfd: can@e66c0000 {
+			compatible = "renesas,r8a77995-canfd",
+				     "renesas,rcar-gen3-canfd";
+			reg = <0 0xe66c0000 0 0x8000>;
+			interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+				   <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 914>,
+			       <&cpg CPG_CORE R8A77995_CLK_CANFD>,
+			       <&can_clk>;
+			clock-names = "fck", "canfd", "can_clk";
+			assigned-clocks = <&cpg CPG_CORE R8A77995_CLK_CANFD>;
+			assigned-clock-rates = <40000000>;
+			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
+			resets = <&cpg 914>;
+			status = "disabled";
+
+			channel0 {
+				status = "disabled";
+			};
+
+			channel1 {
+				status = "disabled";
+			};
+		};
+
 		avb: ethernet@e6800000 {
 			compatible = "renesas,etheravb-r8a77995",
 				     "renesas,etheravb-rcar-gen3";
@@ -307,6 +525,7 @@
 			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
 			resets = <&cpg 812>;
 			phy-mode = "rgmii-txid";
+			iommus = <&ipmmu_ds0 16>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";
@@ -321,6 +540,9 @@
 				 <&cpg CPG_CORE R8A77995_CLK_S3D1C>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
+			dmas = <&dmac1 0x13>, <&dmac1 0x12>,
+			       <&dmac2 0x13>, <&dmac2 0x12>;
+			dma-names = "tx", "rx", "tx", "rx";
 			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
 			resets = <&cpg 310>;
 			status = "disabled";
@@ -366,6 +588,18 @@
 			status = "disabled";
 		};
 
+		sdhi2: sd@ee140000 {
+			compatible = "renesas,sdhi-r8a77995",
+				     "renesas,rcar-gen3-sdhi";
+			reg = <0 0xee140000 0 0x2000>;
+			interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 312>;
+			max-frequency = <200000000>;
+			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
+			resets = <&cpg 312>;
+			status = "disabled";
+		};
+
 		ehci0: usb@ee080100 {
 			compatible = "generic-ehci";
 			reg = <0 0xee080100 0 0x100>;
diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
index a298df74ca6c..c3fafb6025b3 100644
--- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
@@ -255,7 +255,6 @@
 &avb {
 	pinctrl-0 = <&avb_pins>;
 	pinctrl-names = "default";
-	renesas,no-ether-link;
 	phy-handle = <&phy0>;
 	status = "okay";
 
@@ -264,6 +263,7 @@
 		reg = <0>;
 		interrupt-parent = <&gpio2>;
 		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
+		reset-gpios = <&gpio2 10 GPIO_ACTIVE_LOW>;
 	};
 };
 
@@ -355,6 +355,30 @@
 
 &i2c_dvfs {
 	status = "okay";
+
+	pmic: pmic@30 {
+		pinctrl-0 = <&irq0_pins>;
+		pinctrl-names = "default";
+
+		compatible = "rohm,bd9571mwv";
+		reg = <0x30>;
+		interrupt-parent = <&intc_ex>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		regulators {
+			dvfs: dvfs {
+				regulator-name = "dvfs";
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <1030000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
 };
 
 &ohci0 {
@@ -410,6 +434,11 @@
 		function = "i2c2";
 	};
 
+	irq0_pins: irq0 {
+		groups = "intc_ex_irq0";
+		function = "intc_ex";
+	};
+
 	pwm1_pins: pwm1 {
 		groups = "pwm1_a";
 		function = "pwm1";
@@ -596,6 +625,7 @@
 	bus-width = <8>;
 	mmc-hs200-1_8v;
 	non-removable;
+	fixed-emmc-driver-type = <1>;
 	status = "okay";
 };
 
@@ -617,6 +647,10 @@
 	shared-pin;
 };
 
+&usb_extal_clk {
+	clock-frequency = <50000000>;
+};
+
 &usb2_phy0 {
 	pinctrl-0 = <&usb0_pins>;
 	pinctrl-names = "default";
@@ -632,6 +666,21 @@
 	status = "okay";
 };
 
+&usb3_peri0 {
+	phys = <&usb3_phy0>;
+	phy-names = "usb";
+
+	status = "okay";
+};
+
+&usb3_phy0 {
+	status = "okay";
+};
+
+&usb3s0_clk {
+	clock-frequency = <100000000>;
+};
+
 &wdt0 {
 	timeout-sec = <60>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi
index 657ad1041965..a4e715cbde87 100644
--- a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi
@@ -29,6 +29,7 @@
 };
 
 &ehci0 {
+	dr_mode = "otg";
 	status = "okay";
 };
 
@@ -41,6 +42,7 @@
 };
 
 &hsusb {
+	dr_mode = "otg";
 	status = "okay";
 };
 
@@ -67,6 +69,20 @@
 			output-high;
 			line-name = "HUB rst";
 		};
+
+		otg_offvbusn {
+			gpio-hog;
+			gpios = <8 GPIO_ACTIVE_HIGH>;
+			output-low;
+			line-name = "OTG OFFVBUSn";
+		};
+
+		otg_extlpn {
+			gpio-hog;
+			gpios = <9 GPIO_ACTIVE_HIGH>;
+			output-high;
+			line-name = "OTG EXTLPn";
+		};
 	};
 
 	gpio_exp_75: gpio@75 {
@@ -119,6 +135,7 @@
 };
 
 &ohci0 {
+	dr_mode = "otg";
 	status = "okay";
 };
 
@@ -154,6 +171,11 @@
 		groups = "scif1_data_b", "scif1_ctrl";
 		function = "scif1";
 	};
+
+	usb0_pins: usb0 {
+		groups = "usb0";
+		function = "usb0";
+	};
 };
 
 &scif1 {
@@ -164,6 +186,13 @@
 	status = "okay";
 };
 
+&usb2_phy0 {
+	pinctrl-0 = <&usb0_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
 &xhci0 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi
index 0d85b315ce71..3e7a6b94e9f8 100644
--- a/arch/arm64/boot/dts/renesas/ulcb.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi
@@ -145,7 +145,6 @@
 &avb {
 	pinctrl-0 = <&avb_pins>;
 	pinctrl-names = "default";
-	renesas,no-ether-link;
 	phy-handle = <&phy0>;
 	status = "okay";
 
@@ -154,6 +153,7 @@
 		reg = <0>;
 		interrupt-parent = <&gpio2>;
 		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
+		reset-gpios = <&gpio2 10 GPIO_ACTIVE_LOW>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
index d4f80786e7c2..3890468678ce 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
@@ -132,6 +132,8 @@
 	assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>;
 	assigned-clock-parents = <&gmac_clkin>, <&gmac_clkin>;
 	clock_in_out = "input";
+	/* shows instability at 1GBit right now */
+	max-speed = <100>;
 	phy-supply = <&vcc_io>;
 	phy-mode = "rgmii";
 	pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index 41d61840fb99..a037ee56fead 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -514,7 +514,7 @@
 	tsadc: tsadc@ff250000 {
 		compatible = "rockchip,rk3328-tsadc";
 		reg = <0x0 0xff250000 0x0 0x100>;
-		interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
 		assigned-clocks = <&cru SCLK_TSADC>;
 		assigned-clock-rates = <50000>;
 		clocks = <&cru SCLK_TSADC>, <&cru PCLK_TSADC>;
@@ -531,6 +531,31 @@
 		status = "disabled";
 	};
 
+	efuse: efuse@ff260000 {
+		compatible = "rockchip,rk3328-efuse";
+		reg = <0x0 0xff260000 0x0 0x50>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		clocks = <&cru SCLK_EFUSE>;
+		clock-names = "pclk_efuse";
+		rockchip,efuse-size = <0x20>;
+
+		/* Data cells */
+		efuse_id: id@7 {
+			reg = <0x07 0x10>;
+		};
+		cpu_leakage: cpu-leakage@17 {
+			reg = <0x17 0x1>;
+		};
+		logic_leakage: logic-leakage@19 {
+			reg = <0x19 0x1>;
+		};
+		efuse_cpu_version: cpu-version@1a {
+			reg = <0x1a 0x1>;
+			bits = <3 3>;
+		};
+	};
+
 	saradc: adc@ff280000 {
 		compatible = "rockchip,rk3328-saradc", "rockchip,rk3399-saradc";
 		reg = <0x0 0xff280000 0x0 0x100>;
@@ -543,6 +568,28 @@
 		status = "disabled";
 	};
 
+	gpu: gpu@ff300000 {
+		compatible = "rockchip,rk3328-mali", "arm,mali-450";
+		reg = <0x0 0xff300000 0x0 0x40000>;
+		interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "gp",
+				  "gpmmu",
+				  "pp",
+				  "pp0",
+				  "ppmmu0",
+				  "pp1",
+				  "ppmmu1";
+		clocks = <&cru ACLK_GPU>, <&cru ACLK_GPU>;
+		clock-names = "bus", "core";
+		resets = <&cru SRST_GPU_A>;
+	};
+
 	h265e_mmu: iommu@ff330200 {
 		compatible = "rockchip,iommu";
 		reg = <0x0 0xff330200 0 0x100>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts
index 0384e3121f18..191a6bcb1704 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts
@@ -93,6 +93,18 @@
 		pwm-delay-us = <10000>;
 	};
 
+	edp_panel: edp-panel {
+		compatible = "sharp,lq123p1jx31", "simple-panel";
+		backlight = <&backlight>;
+		power-supply = <&pp3300_disp>;
+
+		ports {
+			panel_in_edp: endpoint {
+				remote-endpoint = <&edp_out_panel>;
+			};
+		};
+	};
+
 	thermistor_ppvar_bigcpu: thermistor-ppvar-bigcpu {
 		compatible = "murata,ncp15wb473";
 		pullup-uv = <1800000>;
@@ -268,6 +280,23 @@ ap_i2c_dig: &i2c2 {
 	};
 };
 
+&edp {
+	status = "okay";
+
+	ports {
+		edp_out: port@1 {
+			reg = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			edp_out_panel: endpoint@0 {
+				reg = <0>;
+				remote-endpoint = <&panel_in_edp>;
+			};
+		};
+	};
+};
+
 &ppvar_bigcpu_pwm {
 	regulator-min-microvolt = <798674>;
 	regulator-max-microvolt = <1302172>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
index 5772c52fbfd3..03f195025390 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
@@ -855,6 +855,20 @@ ap_i2c_audio: &i2c8 {
 			compatible = "google,cros-ec-pwm";
 			#pwm-cells = <1>;
 		};
+
+		usbc_extcon0: extcon@0 {
+			compatible = "google,extcon-usbc-cros-ec";
+			google,usb-port-id = <0>;
+
+			#extcon-cells = <0>;
+		};
+
+		usbc_extcon1: extcon@1 {
+			compatible = "google,extcon-usbc-cros-ec";
+			google,usb-port-id = <1>;
+
+			#extcon-cells = <0>;
+		};
 	};
 };
 
@@ -865,6 +879,16 @@ ap_i2c_audio: &i2c8 {
 	rockchip,hw-tshut-polarity = <1>; /* tshut polarity 0:LOW 1:HIGH */
 };
 
+&tcphy0 {
+	status = "okay";
+	extcon = <&usbc_extcon0>;
+};
+
+&tcphy1 {
+	status = "okay";
+	extcon = <&usbc_extcon1>;
+};
+
 &u2phy0 {
 	status = "okay";
 };
@@ -911,6 +935,7 @@ ap_i2c_audio: &i2c8 {
 
 &usbdrd3_0 {
 	status = "okay";
+	extcon = <&usbc_extcon0>;
 };
 
 &usbdrd_dwc3_0 {
@@ -920,6 +945,7 @@ ap_i2c_audio: &i2c8 {
 
 &usbdrd3_1 {
 	status = "okay";
+	extcon = <&usbc_extcon1>;
 };
 
 &usbdrd_dwc3_1 {
@@ -927,6 +953,22 @@ ap_i2c_audio: &i2c8 {
 	dr_mode = "host";
 };
 
+&vopb {
+	status = "okay";
+};
+
+&vopb_mmu {
+	status = "okay";
+};
+
+&vopl {
+	status = "okay";
+};
+
+&vopl_mmu {
+	status = "okay";
+};
+
 #include <arm/cros-ec-keyboard.dtsi>
 #include <arm/cros-ec-sbs.dtsi>
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
index 910628d18add..1fc5060d7027 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
@@ -155,17 +155,6 @@
 		regulator-min-microvolt = <5000000>;
 		regulator-max-microvolt = <5000000>;
 	};
-
-	vdd_log: vdd-log {
-		compatible = "pwm-regulator";
-		pwms = <&pwm2 0 25000 0>;
-		regulator-name = "vdd_log";
-		regulator-min-microvolt = <800000>;
-		regulator-max-microvolt = <1400000>;
-		regulator-always-on;
-		regulator-boot-on;
-		status = "okay";
-	};
 };
 
 &cpu_b0 {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index d340b58ab184..7aa2144e0d47 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -397,9 +397,13 @@
 		#size-cells = <2>;
 		ranges;
 		clocks = <&cru SCLK_USB3OTG0_REF>, <&cru SCLK_USB3OTG0_SUSPEND>,
-			 <&cru ACLK_USB3OTG0>, <&cru ACLK_USB3_GRF>;
+			 <&cru ACLK_USB3OTG0>, <&cru ACLK_USB3_RKSOC_AXI_PERF>,
+			 <&cru ACLK_USB3>, <&cru ACLK_USB3_GRF>;
 		clock-names = "ref_clk", "suspend_clk",
-			      "bus_clk", "grf_clk";
+			      "bus_clk", "aclk_usb3_rksoc_axi_perf",
+			      "aclk_usb3", "grf_clk";
+		resets = <&cru SRST_A_USB3_OTG0>;
+		reset-names = "usb3-otg";
 		status = "disabled";
 
 		usbdrd_dwc3_0: dwc3 {
@@ -407,14 +411,15 @@
 			reg = <0x0 0xfe800000 0x0 0x100000>;
 			interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH 0>;
 			dr_mode = "otg";
-			phys = <&u2phy0_otg>;
-			phy-names = "usb2-phy";
+			phys = <&u2phy0_otg>, <&tcphy0_usb3>;
+			phy-names = "usb2-phy", "usb3-phy";
 			phy_type = "utmi_wide";
 			snps,dis_enblslpm_quirk;
 			snps,dis-u2-freeclk-exists-quirk;
 			snps,dis_u2_susphy_quirk;
 			snps,dis-del-phy-power-chg-quirk;
 			snps,dis-tx-ipgap-linecheck-quirk;
+			power-domains = <&power RK3399_PD_USB3>;
 			status = "disabled";
 		};
 	};
@@ -425,9 +430,13 @@
 		#size-cells = <2>;
 		ranges;
 		clocks = <&cru SCLK_USB3OTG1_REF>, <&cru SCLK_USB3OTG1_SUSPEND>,
-			 <&cru ACLK_USB3OTG1>, <&cru ACLK_USB3_GRF>;
+			 <&cru ACLK_USB3OTG1>, <&cru ACLK_USB3_RKSOC_AXI_PERF>,
+			 <&cru ACLK_USB3>, <&cru ACLK_USB3_GRF>;
 		clock-names = "ref_clk", "suspend_clk",
-			      "bus_clk", "grf_clk";
+			      "bus_clk", "aclk_usb3_rksoc_axi_perf",
+			      "aclk_usb3", "grf_clk";
+		resets = <&cru SRST_A_USB3_OTG1>;
+		reset-names = "usb3-otg";
 		status = "disabled";
 
 		usbdrd_dwc3_1: dwc3 {
@@ -435,14 +444,15 @@
 			reg = <0x0 0xfe900000 0x0 0x100000>;
 			interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH 0>;
 			dr_mode = "otg";
-			phys = <&u2phy1_otg>;
-			phy-names = "usb2-phy";
+			phys = <&u2phy1_otg>, <&tcphy1_usb3>;
+			phy-names = "usb2-phy", "usb3-phy";
 			phy_type = "utmi_wide";
 			snps,dis_enblslpm_quirk;
 			snps,dis-u2-freeclk-exists-quirk;
 			snps,dis_u2_susphy_quirk;
 			snps,dis-del-phy-power-chg-quirk;
 			snps,dis-tx-ipgap-linecheck-quirk;
+			power-domains = <&power RK3399_PD_USB3>;
 			status = "disabled";
 		};
 	};
@@ -991,6 +1001,12 @@
 				clocks = <&cru HCLK_SDIO>;
 				pm_qos = <&qos_sdioaudio>;
 			};
+			pd_usb3@RK3399_PD_USB3 {
+				reg = <RK3399_PD_USB3>;
+				clocks = <&cru ACLK_USB3>;
+				pm_qos = <&qos_usb_otg0>,
+					 <&qos_usb_otg1>;
+			};
 			pd_vio@RK3399_PD_VIO {
 				reg = <RK3399_PD_VIO>;
 				#address-cells = <1>;
@@ -1526,6 +1542,11 @@
 				reg = <2>;
 				remote-endpoint = <&hdmi_in_vopl>;
 			};
+
+			vopl_out_mipi1: endpoint@3 {
+				reg = <3>;
+				remote-endpoint = <&mipi1_in_vopl>;
+			};
 		};
 	};
 
@@ -1573,6 +1594,11 @@
 				reg = <2>;
 				remote-endpoint = <&hdmi_in_vopb>;
 			};
+
+			vopb_out_mipi1: endpoint@3 {
+				reg = <3>;
+				remote-endpoint = <&mipi1_in_vopb>;
+			};
 		};
 	};
 
@@ -1648,11 +1674,17 @@
 			 <&cru SCLK_DPHY_TX0_CFG>, <&cru PCLK_VIO_GRF>;
 		clock-names = "ref", "pclk", "phy_cfg", "grf";
 		power-domains = <&power RK3399_PD_VIO>;
+		resets = <&cru SRST_P_MIPI_DSI0>;
+		reset-names = "apb";
 		rockchip,grf = <&grf>;
 		status = "disabled";
 
 		ports {
-			mipi_in: port {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			mipi_in: port@0 {
+				reg = <0>;
 				#address-cells = <1>;
 				#size-cells = <0>;
 
@@ -1668,6 +1700,41 @@
 		};
 	};
 
+	mipi_dsi1: mipi@ff968000 {
+		compatible = "rockchip,rk3399-mipi-dsi", "snps,dw-mipi-dsi";
+		reg = <0x0 0xff968000 0x0 0x8000>;
+		interrupts = <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH 0>;
+		clocks = <&cru SCLK_DPHY_PLL>, <&cru PCLK_MIPI_DSI1>,
+			 <&cru SCLK_DPHY_TX1RX1_CFG>, <&cru PCLK_VIO_GRF>;
+		clock-names = "ref", "pclk", "phy_cfg", "grf";
+		power-domains = <&power RK3399_PD_VIO>;
+		resets = <&cru SRST_P_MIPI_DSI1>;
+		reset-names = "apb";
+		rockchip,grf = <&grf>;
+		status = "disabled";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			mipi1_in: port@0 {
+				reg = <0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				mipi1_in_vopb: endpoint@0 {
+					reg = <0>;
+					remote-endpoint = <&vopb_out_mipi1>;
+				};
+
+				mipi1_in_vopl: endpoint@1 {
+					reg = <1>;
+					remote-endpoint = <&vopl_out_mipi1>;
+				};
+			};
+		};
+	};
+
 	edp: edp@ff970000 {
 		compatible = "rockchip,rk3399-edp";
 		reg = <0x0 0xff970000 0x0 0x8000>;
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts
index dd7193acc7df..54c53170699a 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts
@@ -40,7 +40,6 @@
 };
 
 &ethsc {
-	interrupt-parent = <&gpio>;
 	interrupts = <0 8>;
 };
 
@@ -51,7 +50,7 @@
 &gpio {
 	xirq0 {
 		gpio-hog;
-		gpios = <120 0>;
+		gpios = <UNIPHIER_GPIO_IRQ(0) 0>;
 		input;
 	};
 };
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
index 1c63d0ab8a58..cd7c2d0a1f64 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
@@ -8,6 +8,7 @@
  */
 
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/gpio/uniphier-gpio.h>
 
 /memreserve/ 0x80000000 0x02000000;
 
@@ -100,7 +101,7 @@
 
 	emmc_pwrseq: emmc-pwrseq {
 		compatible = "mmc-pwrseq-emmc";
-		reset-gpios = <&gpio 26 GPIO_ACTIVE_LOW>;
+		reset-gpios = <&gpio UNIPHIER_GPIO_PORT(3, 2) GPIO_ACTIVE_LOW>;
 	};
 
 	timer {
@@ -347,6 +348,7 @@
 				 <&mio_clk 12>;
 			resets = <&sys_rst 8>, <&mio_rst 7>, <&mio_rst 8>,
 				 <&mio_rst 12>;
+			has-transaction-translator;
 		};
 
 		usb1: usb@5a810100 {
@@ -360,6 +362,7 @@
 				 <&mio_clk 13>;
 			resets = <&sys_rst 8>, <&mio_rst 7>, <&mio_rst 9>,
 				 <&mio_rst 13>;
+			has-transaction-translator;
 		};
 
 		usb2: usb@5a820100 {
@@ -373,6 +376,7 @@
 				 <&mio_clk 14>;
 			resets = <&sys_rst 8>, <&mio_rst 7>, <&mio_rst 10>,
 				 <&mio_rst 14>;
+			has-transaction-translator;
 		};
 
 		mioctrl@5b3e0000 {
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
index d99e3731358c..693371033c90 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
@@ -40,7 +40,6 @@
 };
 
 &ethsc {
-	interrupt-parent = <&gpio>;
 	interrupts = <0 8>;
 };
 
@@ -51,7 +50,7 @@
 &gpio {
 	xirq0 {
 		gpio-hog;
-		gpios = <120 0>;
+		gpios = <UNIPHIER_GPIO_IRQ(0) 0>;
 		input;
 	};
 };
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
index 5c81070944cc..8a3276ba2da1 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
@@ -8,6 +8,7 @@
  */
 
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/gpio/uniphier-gpio.h>
 #include <dt-bindings/thermal/thermal.h>
 
 /memreserve/ 0x80000000 0x02000000;
@@ -172,7 +173,7 @@
 
 	emmc_pwrseq: emmc-pwrseq {
 		compatible = "mmc-pwrseq-emmc";
-		reset-gpios = <&gpio 26 GPIO_ACTIVE_LOW>;
+		reset-gpios = <&gpio UNIPHIER_GPIO_PORT(3, 2) GPIO_ACTIVE_LOW>;
 	};
 
 	timer {
diff --git a/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts
index 864feeb35180..3c7108729827 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts
+++ b/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts
@@ -38,14 +38,29 @@
 };
 
 &ethsc {
-	interrupt-parent = <&gpio>;
-	interrupts = <0 8>;
+	interrupts = <4 8>;
 };
 
 &serial0 {
 	status = "okay";
 };
 
+&serial2 {
+	status = "okay";
+};
+
+&serial3 {
+	status = "okay";
+};
+
+&gpio {
+	xirq4 {
+		gpio-hog;
+		gpios = <UNIPHIER_GPIO_IRQ(4) 0>;
+		input;
+	};
+};
+
 &i2c0 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
index 48e733136db4..234fc58cc599 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
@@ -8,6 +8,7 @@
  */
 
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/gpio/uniphier-gpio.h>
 
 /memreserve/ 0x80000000 0x02000000;
 
@@ -128,7 +129,7 @@
 
 	emmc_pwrseq: emmc-pwrseq {
 		compatible = "mmc-pwrseq-emmc";
-		reset-gpios = <&gpio 47 GPIO_ACTIVE_LOW>;
+		reset-gpios = <&gpio UNIPHIER_GPIO_PORT(5, 7) GPIO_ACTIVE_LOW>;
 	};
 
 	timer {
@@ -198,8 +199,8 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-ranges = <&pinctrl 0 0 0>,
-				      <&pinctrl 96 0 0>,
-				      <&pinctrl 160 0 0>;
+				      <&pinctrl 104 0 0>,
+				      <&pinctrl 168 0 0>;
 			gpio-ranges-group-names = "gpio_range0",
 						  "gpio_range1",
 						  "gpio_range2";
diff --git a/arch/arm64/boot/dts/sprd/sc9860.dtsi b/arch/arm64/boot/dts/sprd/sc9860.dtsi
index 7b7d8cedacda..5dbfb796d9f9 100644
--- a/arch/arm64/boot/dts/sprd/sc9860.dtsi
+++ b/arch/arm64/boot/dts/sprd/sc9860.dtsi
@@ -183,6 +183,120 @@
 	};
 
 	soc {
+		pmu_gate: pmu-gate {
+			compatible = "sprd,sc9860-pmu-gate";
+			sprd,syscon = <&pmu_regs>; /* 0x402b0000 */
+			clocks = <&ext_26m>;
+			#clock-cells = <1>;
+		};
+
+		pll: pll {
+			compatible = "sprd,sc9860-pll";
+			sprd,syscon = <&ana_regs>; /* 0x40400000 */
+			clocks = <&pmu_gate 0>;
+			#clock-cells = <1>;
+		};
+
+		ap_clk: clock-controller@20000000 {
+			compatible = "sprd,sc9860-ap-clk";
+			reg = <0 0x20000000 0 0x400>;
+			clocks = <&ext_26m>, <&pll 0>,
+				 <&pmu_gate 0>;
+			#clock-cells = <1>;
+		};
+
+		aon_prediv: aon-prediv {
+			compatible = "sprd,sc9860-aon-prediv";
+			reg = <0 0x402d0000 0 0x400>;
+			clocks = <&ext_26m>, <&pll 0>,
+				 <&pmu_gate 0>;
+			#clock-cells = <1>;
+		};
+
+		apahb_gate: apahb-gate {
+			compatible = "sprd,sc9860-apahb-gate";
+			sprd,syscon = <&ap_ahb_regs>; /* 0x20210000 */
+			clocks = <&aon_prediv 0>;
+			#clock-cells = <1>;
+		};
+
+		aon_gate: aon-gate {
+			compatible = "sprd,sc9860-aon-gate";
+			sprd,syscon = <&aon_regs>; /* 0x402e0000 */
+			clocks = <&aon_prediv 0>;
+			#clock-cells = <1>;
+		};
+
+		aonsecure_clk: clock-controller@40880000 {
+			compatible = "sprd,sc9860-aonsecure-clk";
+			reg = <0 0x40880000 0 0x400>;
+			clocks = <&ext_26m>, <&pll 0>;
+			#clock-cells = <1>;
+		};
+
+		agcp_gate: agcp-gate {
+			compatible = "sprd,sc9860-agcp-gate";
+			sprd,syscon = <&agcp_regs>; /* 0x415e0000 */
+			clocks = <&aon_prediv 0>;
+			#clock-cells = <1>;
+		};
+
+		gpu_clk: clock-controller@60200000 {
+			compatible = "sprd,sc9860-gpu-clk";
+			reg = <0 0x60200000 0 0x400>;
+			clocks = <&pll 0>;
+			#clock-cells = <1>;
+		};
+
+		vsp_clk: clock-controller@61000000 {
+			compatible = "sprd,sc9860-vsp-clk";
+			reg = <0 0x61000000 0 0x400>;
+			clocks = <&ext_26m>, <&pll 0>;
+			#clock-cells = <1>;
+		};
+
+		vsp_gate: vsp-gate {
+			compatible = "sprd,sc9860-vsp-gate";
+			sprd,syscon = <&vsp_regs>; /* 0x61100000 */
+			clocks = <&vsp_clk 0>;
+			#clock-cells = <1>;
+		};
+
+		cam_clk: clock-controller@62000000 {
+			compatible = "sprd,sc9860-cam-clk";
+			reg = <0 0x62000000 0 0x4000>;
+			clocks = <&ext_26m>, <&pll 0>;
+			#clock-cells = <1>;
+		};
+
+		cam_gate: cam-gate {
+			compatible = "sprd,sc9860-cam-gate";
+			sprd,syscon = <&cam_regs>; /* 0x62100000 */
+			clocks = <&cam_clk 0>;
+			#clock-cells = <1>;
+		};
+
+		disp_clk: clock-controller@63000000 {
+			compatible = "sprd,sc9860-disp-clk";
+			reg = <0 0x63000000 0 0x400>;
+			clocks = <&ext_26m>, <&pll 0>;
+			#clock-cells = <1>;
+		};
+
+		disp_gate: disp-gate {
+			compatible = "sprd,sc9860-disp-gate";
+			sprd,syscon = <&disp_regs>; /* 0x63100000 */
+			clocks = <&disp_clk 0>;
+			#clock-cells = <1>;
+		};
+
+		apapb_gate: apapb-gate {
+			compatible = "sprd,sc9860-apapb-gate";
+			sprd,syscon = <&ap_apb_regs>; /* 0x70b00000 */
+			clocks = <&ap_clk 0>;
+			#clock-cells = <1>;
+		};
+
 		funnel@10001000 { /* SoC Funnel */
 			compatible = "arm,coresight-funnel", "arm,primecell";
 			reg = <0 0x10001000 0 0x1000>;
diff --git a/arch/arm64/boot/dts/sprd/whale2.dtsi b/arch/arm64/boot/dts/sprd/whale2.dtsi
index 7c217c547f85..328009c4638c 100644
--- a/arch/arm64/boot/dts/sprd/whale2.dtsi
+++ b/arch/arm64/boot/dts/sprd/whale2.dtsi
@@ -17,6 +17,51 @@
 		#size-cells = <2>;
 		ranges;
 
+		ap_ahb_regs: syscon@20210000 {
+			compatible = "syscon";
+			reg = <0 0x20210000 0 0x10000>;
+		};
+
+		pmu_regs: syscon@402b0000 {
+			compatible = "syscon";
+			reg = <0 0x402b0000 0 0x10000>;
+		};
+
+		aon_regs: syscon@402e0000 {
+			compatible = "syscon";
+			reg = <0 0x402e0000 0 0x10000>;
+		};
+
+		ana_regs: syscon@40400000 {
+			compatible = "syscon";
+			reg = <0 0x40400000 0 0x10000>;
+		};
+
+		agcp_regs: syscon@415e0000 {
+			compatible = "syscon";
+			reg = <0 0x415e0000 0 0x1000000>;
+		};
+
+		vsp_regs: syscon@61100000 {
+			compatible = "syscon";
+			reg = <0 0x61100000 0 0x10000>;
+		};
+
+		cam_regs: syscon@62100000 {
+			compatible = "syscon";
+			reg = <0 0x62100000 0 0x10000>;
+		};
+
+		disp_regs: syscon@63100000 {
+			compatible = "syscon";
+			reg = <0 0x63100000 0 0x10000>;
+		};
+
+		ap_apb_regs: syscon@70b00000 {
+			compatible = "syscon";
+			reg = <0 0x70b00000 0 0x40000>;
+		};
+
 		ap-apb {
 			compatible = "simple-bus";
 			#address-cells = <1>;
@@ -59,13 +104,26 @@
 				status = "disabled";
 			};
 		};
+	};
 
+	ext_32k: ext_32k {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <32768>;
+		clock-output-names = "ext-32k";
 	};
 
-	ext_26m: ext-26m {
+	ext_26m: ext_26m {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <26000000>;
-		clock-output-names = "ext_26m";
+		clock-output-names = "ext-26m";
+	};
+
+	ext_rco_100m: ext_rco_100m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <100000000>;
+		clock-output-names = "ext-rco-100m";
 	};
 };
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 6356c6da34ea..634b373785c4 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -86,6 +86,7 @@ CONFIG_SCHED_MC=y
 CONFIG_NUMA=y
 CONFIG_PREEMPT=y
 CONFIG_KSM=y
+CONFIG_MEMORY_FAILURE=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA=y
 CONFIG_SECCOMP=y
@@ -99,6 +100,7 @@ CONFIG_WQ_POWER_EFFICIENT_DEFAULT=y
 CONFIG_ARM_CPUIDLE=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPUFREQ_DT=y
+CONFIG_ARM_ARMADA_37XX_CPUFREQ=y
 CONFIG_ARM_BIG_LITTLE_CPUFREQ=y
 CONFIG_ARM_SCPI_CPUFREQ=y
 CONFIG_ACPI_CPPC_CPUFREQ=m
@@ -161,7 +163,7 @@ CONFIG_MTD_BLOCK=y
 CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_DENALI_DT=y
-CONFIG_MTD_NAND_PXA3xx=y
+CONFIG_MTD_NAND_MARVELL=y
 CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_NBD=m
@@ -421,7 +423,6 @@ CONFIG_USB_OTG=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_XHCI_TEGRA=y
 CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_MSM=y
 CONFIG_USB_EHCI_EXYNOS=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_OHCI_HCD=y
@@ -429,6 +430,8 @@ CONFIG_USB_OHCI_EXYNOS=y
 CONFIG_USB_OHCI_HCD_PLATFORM=y
 CONFIG_USB_RENESAS_USBHS=m
 CONFIG_USB_STORAGE=y
+CONFIG_USB_MUSB_HDRC=y
+CONFIG_USB_MUSB_SUNXI=y
 CONFIG_USB_DWC3=y
 CONFIG_USB_DWC2=y
 CONFIG_USB_CHIPIDEA=y
@@ -438,8 +441,6 @@ CONFIG_USB_CHIPIDEA_ULPI=y
 CONFIG_USB_ISP1760=y
 CONFIG_USB_HSIC_USB3503=y
 CONFIG_NOP_USB_XCEIV=y
-CONFIG_USB_MSM_OTG=y
-CONFIG_USB_QCOM_8X16_PHY=y
 CONFIG_USB_ULPI=y
 CONFIG_USB_GADGET=y
 CONFIG_USB_RENESAS_USBHS_UDC=m
@@ -473,7 +474,10 @@ CONFIG_LEDS_SYSCON=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_CPU=y
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
+CONFIG_LEDS_TRIGGER_PANIC=y
+CONFIG_LEDS_TRIGGER_DISK=y
 CONFIG_EDAC=y
+CONFIG_EDAC_GHES=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_MAX77686=y
 CONFIG_RTC_DRV_RK808=m
@@ -558,6 +562,7 @@ CONFIG_PHY_XGENE=y
 CONFIG_PHY_TEGRA_XUSB=y
 CONFIG_QCOM_L2_PMU=y
 CONFIG_QCOM_L3_PMU=y
+CONFIG_UNIPHIER_EFUSE=y
 CONFIG_TEE=y
 CONFIG_OPTEE=y
 CONFIG_ARM_SCPI_PROTOCOL=y
@@ -567,6 +572,8 @@ CONFIG_ACPI=y
 CONFIG_ACPI_APEI=y
 CONFIG_ACPI_APEI_GHES=y
 CONFIG_ACPI_APEI_PCIEAER=y
+CONFIG_ACPI_APEI_MEMORY_FAILURE=y
+CONFIG_ACPI_APEI_EINJ=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 70c517aa4501..285c36c7b408 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -29,6 +29,24 @@ config CRYPTO_SHA2_ARM64_CE
 	select CRYPTO_HASH
 	select CRYPTO_SHA256_ARM64
 
+config CRYPTO_SHA512_ARM64_CE
+	tristate "SHA-384/SHA-512 digest algorithm (ARMv8 Crypto Extensions)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_HASH
+	select CRYPTO_SHA512_ARM64
+
+config CRYPTO_SHA3_ARM64
+	tristate "SHA3 digest algorithm (ARMv8.2 Crypto Extensions)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_HASH
+	select CRYPTO_SHA3
+
+config CRYPTO_SM3_ARM64_CE
+	tristate "SM3 digest algorithm (ARMv8.2 Crypto Extensions)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_HASH
+	select CRYPTO_SM3
+
 config CRYPTO_GHASH_ARM64_CE
 	tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions"
 	depends on KERNEL_MODE_NEON
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index b5edc5918c28..cee9b8d9830b 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -14,6 +14,15 @@ sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o
 obj-$(CONFIG_CRYPTO_SHA2_ARM64_CE) += sha2-ce.o
 sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o
 
+obj-$(CONFIG_CRYPTO_SHA512_ARM64_CE) += sha512-ce.o
+sha512-ce-y := sha512-ce-glue.o sha512-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SHA3_ARM64) += sha3-ce.o
+sha3-ce-y := sha3-ce-glue.o sha3-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SM3_ARM64_CE) += sm3-ce.o
+sm3-ce-y := sm3-ce-glue.o sm3-ce-core.o
+
 obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
 ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
 
@@ -24,7 +33,7 @@ obj-$(CONFIG_CRYPTO_CRC32_ARM64_CE) += crc32-ce.o
 crc32-ce-y:= crc32-ce-core.o crc32-ce-glue.o
 
 obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
-CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
+aes-ce-cipher-y := aes-ce-core.o aes-ce-glue.o
 
 obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
 aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o
diff --git a/arch/arm64/crypto/aes-ce-core.S b/arch/arm64/crypto/aes-ce-core.S
new file mode 100644
index 000000000000..8efdfdade393
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-core.S
@@ -0,0 +1,87 @@
+/*
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.arch		armv8-a+crypto
+
+ENTRY(__aes_ce_encrypt)
+	sub		w3, w3, #2
+	ld1		{v0.16b}, [x2]
+	ld1		{v1.4s}, [x0], #16
+	cmp		w3, #10
+	bmi		0f
+	bne		3f
+	mov		v3.16b, v1.16b
+	b		2f
+0:	mov		v2.16b, v1.16b
+	ld1		{v3.4s}, [x0], #16
+1:	aese		v0.16b, v2.16b
+	aesmc		v0.16b, v0.16b
+2:	ld1		{v1.4s}, [x0], #16
+	aese		v0.16b, v3.16b
+	aesmc		v0.16b, v0.16b
+3:	ld1		{v2.4s}, [x0], #16
+	subs		w3, w3, #3
+	aese		v0.16b, v1.16b
+	aesmc		v0.16b, v0.16b
+	ld1		{v3.4s}, [x0], #16
+	bpl		1b
+	aese		v0.16b, v2.16b
+	eor		v0.16b, v0.16b, v3.16b
+	st1		{v0.16b}, [x1]
+	ret
+ENDPROC(__aes_ce_encrypt)
+
+ENTRY(__aes_ce_decrypt)
+	sub		w3, w3, #2
+	ld1		{v0.16b}, [x2]
+	ld1		{v1.4s}, [x0], #16
+	cmp		w3, #10
+	bmi		0f
+	bne		3f
+	mov		v3.16b, v1.16b
+	b		2f
+0:	mov		v2.16b, v1.16b
+	ld1		{v3.4s}, [x0], #16
+1:	aesd		v0.16b, v2.16b
+	aesimc		v0.16b, v0.16b
+2:	ld1		{v1.4s}, [x0], #16
+	aesd		v0.16b, v3.16b
+	aesimc		v0.16b, v0.16b
+3:	ld1		{v2.4s}, [x0], #16
+	subs		w3, w3, #3
+	aesd		v0.16b, v1.16b
+	aesimc		v0.16b, v0.16b
+	ld1		{v3.4s}, [x0], #16
+	bpl		1b
+	aesd		v0.16b, v2.16b
+	eor		v0.16b, v0.16b, v3.16b
+	st1		{v0.16b}, [x1]
+	ret
+ENDPROC(__aes_ce_decrypt)
+
+/*
+ * __aes_ce_sub() - use the aese instruction to perform the AES sbox
+ *                  substitution on each byte in 'input'
+ */
+ENTRY(__aes_ce_sub)
+	dup		v1.4s, w0
+	movi		v0.16b, #0
+	aese		v0.16b, v1.16b
+	umov		w0, v0.s[0]
+	ret
+ENDPROC(__aes_ce_sub)
+
+ENTRY(__aes_ce_invert)
+	ld1		{v0.4s}, [x1]
+	aesimc		v1.16b, v0.16b
+	st1		{v1.4s}, [x0]
+	ret
+ENDPROC(__aes_ce_invert)
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-glue.c
index 6a75cd75ed11..e6b3227bbf57 100644
--- a/arch/arm64/crypto/aes-ce-cipher.c
+++ b/arch/arm64/crypto/aes-ce-glue.c
@@ -29,6 +29,13 @@ struct aes_block {
 	u8 b[AES_BLOCK_SIZE];
 };
 
+asmlinkage void __aes_ce_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+asmlinkage void __aes_ce_decrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+
+asmlinkage u32 __aes_ce_sub(u32 l);
+asmlinkage void __aes_ce_invert(struct aes_block *out,
+				const struct aes_block *in);
+
 static int num_rounds(struct crypto_aes_ctx *ctx)
 {
 	/*
@@ -44,10 +51,6 @@ static int num_rounds(struct crypto_aes_ctx *ctx)
 static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 {
 	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct aes_block *out = (struct aes_block *)dst;
-	struct aes_block const *in = (struct aes_block *)src;
-	void *dummy0;
-	int dummy1;
 
 	if (!may_use_simd()) {
 		__aes_arm64_encrypt(ctx->key_enc, dst, src, num_rounds(ctx));
@@ -55,49 +58,13 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	}
 
 	kernel_neon_begin();
-
-	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.4s}, [%[key]], #16		;"
-		"	cmp	%w[rounds], #10			;"
-		"	bmi	0f				;"
-		"	bne	3f				;"
-		"	mov	v3.16b, v1.16b			;"
-		"	b	2f				;"
-		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"1:	aese	v0.16b, v2.16b			;"
-		"	aesmc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.4s}, [%[key]], #16		;"
-		"	aese	v0.16b, v3.16b			;"
-		"	aesmc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.4s}, [%[key]], #16		;"
-		"	subs	%w[rounds], %w[rounds], #3	;"
-		"	aese	v0.16b, v1.16b			;"
-		"	aesmc	v0.16b, v0.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"	bpl	1b				;"
-		"	aese	v0.16b, v2.16b			;"
-		"	eor	v0.16b, v0.16b, v3.16b		;"
-		"	st1	{v0.16b}, %[out]		;"
-
-	:	[out]		"=Q"(*out),
-		[key]		"=r"(dummy0),
-		[rounds]	"=r"(dummy1)
-	:	[in]		"Q"(*in),
-				"1"(ctx->key_enc),
-				"2"(num_rounds(ctx) - 2)
-	:	"cc");
-
+	__aes_ce_encrypt(ctx->key_enc, dst, src, num_rounds(ctx));
 	kernel_neon_end();
 }
 
 static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 {
 	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct aes_block *out = (struct aes_block *)dst;
-	struct aes_block const *in = (struct aes_block *)src;
-	void *dummy0;
-	int dummy1;
 
 	if (!may_use_simd()) {
 		__aes_arm64_decrypt(ctx->key_dec, dst, src, num_rounds(ctx));
@@ -105,62 +72,10 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	}
 
 	kernel_neon_begin();
-
-	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.4s}, [%[key]], #16		;"
-		"	cmp	%w[rounds], #10			;"
-		"	bmi	0f				;"
-		"	bne	3f				;"
-		"	mov	v3.16b, v1.16b			;"
-		"	b	2f				;"
-		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"1:	aesd	v0.16b, v2.16b			;"
-		"	aesimc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.4s}, [%[key]], #16		;"
-		"	aesd	v0.16b, v3.16b			;"
-		"	aesimc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.4s}, [%[key]], #16		;"
-		"	subs	%w[rounds], %w[rounds], #3	;"
-		"	aesd	v0.16b, v1.16b			;"
-		"	aesimc	v0.16b, v0.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"	bpl	1b				;"
-		"	aesd	v0.16b, v2.16b			;"
-		"	eor	v0.16b, v0.16b, v3.16b		;"
-		"	st1	{v0.16b}, %[out]		;"
-
-	:	[out]		"=Q"(*out),
-		[key]		"=r"(dummy0),
-		[rounds]	"=r"(dummy1)
-	:	[in]		"Q"(*in),
-				"1"(ctx->key_dec),
-				"2"(num_rounds(ctx) - 2)
-	:	"cc");
-
+	__aes_ce_decrypt(ctx->key_dec, dst, src, num_rounds(ctx));
 	kernel_neon_end();
 }
 
-/*
- * aes_sub() - use the aese instruction to perform the AES sbox substitution
- *             on each byte in 'input'
- */
-static u32 aes_sub(u32 input)
-{
-	u32 ret;
-
-	__asm__("dup	v1.4s, %w[in]		;"
-		"movi	v0.16b, #0		;"
-		"aese	v0.16b, v1.16b		;"
-		"umov	%w[out], v0.4s[0]	;"
-
-	:	[out]	"=r"(ret)
-	:	[in]	"r"(input)
-	:		"v0","v1");
-
-	return ret;
-}
-
 int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		     unsigned int key_len)
 {
@@ -189,7 +104,7 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		u32 *rki = ctx->key_enc + (i * kwords);
 		u32 *rko = rki + kwords;
 
-		rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
+		rko[0] = ror32(__aes_ce_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
 		rko[1] = rko[0] ^ rki[1];
 		rko[2] = rko[1] ^ rki[2];
 		rko[3] = rko[2] ^ rki[3];
@@ -202,7 +117,7 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		} else if (key_len == AES_KEYSIZE_256) {
 			if (i >= 6)
 				break;
-			rko[4] = aes_sub(rko[3]) ^ rki[4];
+			rko[4] = __aes_ce_sub(rko[3]) ^ rki[4];
 			rko[5] = rko[4] ^ rki[5];
 			rko[6] = rko[5] ^ rki[6];
 			rko[7] = rko[6] ^ rki[7];
@@ -221,13 +136,7 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 
 	key_dec[0] = key_enc[j];
 	for (i = 1, j--; j > 0; i++, j--)
-		__asm__("ld1	{v0.4s}, %[in]		;"
-			"aesimc	v1.16b, v0.16b		;"
-			"st1	{v1.4s}, %[out]	;"
-
-		:	[out]	"=Q"(key_dec[i])
-		:	[in]	"Q"(key_enc[j])
-		:		"v0","v1");
+		__aes_ce_invert(key_dec + i, key_enc + j);
 	key_dec[i] = key_enc[0];
 
 	kernel_neon_end();
diff --git a/arch/arm64/crypto/aes-cipher-core.S b/arch/arm64/crypto/aes-cipher-core.S
index 6d2445d603cc..3a44eada2347 100644
--- a/arch/arm64/crypto/aes-cipher-core.S
+++ b/arch/arm64/crypto/aes-cipher-core.S
@@ -125,6 +125,16 @@ CPU_BE(	rev		w7, w7		)
 	ret
 	.endm
 
+ENTRY(__aes_arm64_encrypt)
+	do_crypt	fround, crypto_ft_tab, crypto_ft_tab + 1, 2
+ENDPROC(__aes_arm64_encrypt)
+
+	.align		5
+ENTRY(__aes_arm64_decrypt)
+	do_crypt	iround, crypto_it_tab, __aes_arm64_inverse_sbox, 0
+ENDPROC(__aes_arm64_decrypt)
+
+	.section	".rodata", "a"
 	.align		L1_CACHE_SHIFT
 	.type		__aes_arm64_inverse_sbox, %object
 __aes_arm64_inverse_sbox:
@@ -161,12 +171,3 @@ __aes_arm64_inverse_sbox:
 	.byte		0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
 	.byte		0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
 	.size		__aes_arm64_inverse_sbox, . - __aes_arm64_inverse_sbox
-
-ENTRY(__aes_arm64_encrypt)
-	do_crypt	fround, crypto_ft_tab, crypto_ft_tab + 1, 2
-ENDPROC(__aes_arm64_encrypt)
-
-	.align		5
-ENTRY(__aes_arm64_decrypt)
-	do_crypt	iround, crypto_it_tab, __aes_arm64_inverse_sbox, 0
-ENDPROC(__aes_arm64_decrypt)
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 998ba519a026..2fa850e86aa8 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -665,6 +665,7 @@ static int __init aes_init(void)
 
 unregister_simds:
 	aes_exit();
+	return err;
 unregister_ciphers:
 	crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
 	return err;
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
index f1e3aa2732f9..1c7b45b7268e 100644
--- a/arch/arm64/crypto/aes-neon.S
+++ b/arch/arm64/crypto/aes-neon.S
@@ -32,10 +32,10 @@
 
 	/* preload the entire Sbox */
 	.macro		prepare, sbox, shiftrows, temp
-	adr		\temp, \sbox
 	movi		v12.16b, #0x1b
-	ldr		q13, \shiftrows
-	ldr		q14, .Lror32by8
+	ldr_l		q13, \shiftrows, \temp
+	ldr_l		q14, .Lror32by8, \temp
+	adr_l		\temp, \sbox
 	ld1		{v16.16b-v19.16b}, [\temp], #64
 	ld1		{v20.16b-v23.16b}, [\temp], #64
 	ld1		{v24.16b-v27.16b}, [\temp], #64
@@ -272,7 +272,7 @@
 
 #include "aes-modes.S"
 
-	.text
+	.section	".rodata", "a"
 	.align		6
 .LForward_Sbox:
 	.byte		0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
diff --git a/arch/arm64/crypto/crc32-ce-core.S b/arch/arm64/crypto/crc32-ce-core.S
index 18f5a8442276..16ed3c7ebd37 100644
--- a/arch/arm64/crypto/crc32-ce-core.S
+++ b/arch/arm64/crypto/crc32-ce-core.S
@@ -50,7 +50,7 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-	.text
+	.section	".rodata", "a"
 	.align		6
 	.cpu		generic+crypto+crc
 
@@ -115,12 +115,13 @@
 	 * uint crc32_pmull_le(unsigned char const *buffer,
 	 *                     size_t len, uint crc32)
 	 */
+	.text
 ENTRY(crc32_pmull_le)
-	adr		x3, .Lcrc32_constants
+	adr_l		x3, .Lcrc32_constants
 	b		0f
 
 ENTRY(crc32c_pmull_le)
-	adr		x3, .Lcrc32c_constants
+	adr_l		x3, .Lcrc32c_constants
 
 0:	bic		LEN, LEN, #15
 	ld1		{v1.16b-v4.16b}, [BUF], #0x40
diff --git a/arch/arm64/crypto/crc32-ce-glue.c b/arch/arm64/crypto/crc32-ce-glue.c
index 624f4137918c..34b4e3d46aab 100644
--- a/arch/arm64/crypto/crc32-ce-glue.c
+++ b/arch/arm64/crypto/crc32-ce-glue.c
@@ -185,6 +185,7 @@ static struct shash_alg crc32_pmull_algs[] = { {
 	.base.cra_name		= "crc32",
 	.base.cra_driver_name	= "crc32-arm64-ce",
 	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 	.base.cra_blocksize	= 1,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -200,6 +201,7 @@ static struct shash_alg crc32_pmull_algs[] = { {
 	.base.cra_name		= "crc32c",
 	.base.cra_driver_name	= "crc32c-arm64-ce",
 	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 	.base.cra_blocksize	= 1,
 	.base.cra_module	= THIS_MODULE,
 } };
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S
index d5b5a8c038c8..f179c01bd55c 100644
--- a/arch/arm64/crypto/crct10dif-ce-core.S
+++ b/arch/arm64/crypto/crct10dif-ce-core.S
@@ -128,7 +128,7 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 	// XOR the initial_crc value
 	eor		v0.16b, v0.16b, v10.16b
 
-	ldr		q10, rk3	// xmm10 has rk3 and rk4
+	ldr_l		q10, rk3, x8	// xmm10 has rk3 and rk4
 					// type of pmull instruction
 					// will determine which constant to use
 
@@ -184,13 +184,13 @@ CPU_LE(	ext		v12.16b, v12.16b, v12.16b, #8	)
 	// fold the 8 vector registers to 1 vector register with different
 	// constants
 
-	ldr		q10, rk9
+	ldr_l		q10, rk9, x8
 
 	.macro		fold16, reg, rk
 	pmull		v8.1q, \reg\().1d, v10.1d
 	pmull2		\reg\().1q, \reg\().2d, v10.2d
 	.ifnb		\rk
-	ldr		q10, \rk
+	ldr_l		q10, \rk, x8
 	.endif
 	eor		v7.16b, v7.16b, v8.16b
 	eor		v7.16b, v7.16b, \reg\().16b
@@ -251,7 +251,7 @@ CPU_LE(	ext		v1.16b, v1.16b, v1.16b, #8	)
 
 	// get rid of the extra data that was loaded before
 	// load the shift constant
-	adr		x4, tbl_shf_table + 16
+	adr_l		x4, tbl_shf_table + 16
 	sub		x4, x4, arg3
 	ld1		{v0.16b}, [x4]
 
@@ -275,7 +275,7 @@ CPU_LE(	ext		v1.16b, v1.16b, v1.16b, #8	)
 
 _128_done:
 	// compute crc of a 128-bit value
-	ldr		q10, rk5		// rk5 and rk6 in xmm10
+	ldr_l		q10, rk5, x8		// rk5 and rk6 in xmm10
 
 	// 64b fold
 	ext		v0.16b, vzr.16b, v7.16b, #8
@@ -291,7 +291,7 @@ _128_done:
 
 	// barrett reduction
 _barrett:
-	ldr		q10, rk7
+	ldr_l		q10, rk7, x8
 	mov		v0.d[0], v7.d[1]
 
 	pmull		v0.1q, v0.1d, v10.1d
@@ -321,7 +321,7 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 	b.eq		_128_done		// exactly 16 left
 	b.lt		_less_than_16_left
 
-	ldr		q10, rk1		// rk1 and rk2 in xmm10
+	ldr_l		q10, rk1, x8		// rk1 and rk2 in xmm10
 
 	// update the counter. subtract 32 instead of 16 to save one
 	// instruction from the loop
@@ -333,7 +333,7 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 
 _less_than_16_left:
 	// shl r9, 4
-	adr		x0, tbl_shf_table + 16
+	adr_l		x0, tbl_shf_table + 16
 	sub		x0, x0, arg3
 	ld1		{v0.16b}, [x0]
 	movi		v9.16b, #0x80
@@ -345,6 +345,7 @@ ENDPROC(crc_t10dif_pmull)
 // precomputed constants
 // these constants are precomputed from the poly:
 // 0x8bb70000 (0x8bb7 scaled to 32 bits)
+	.section	".rodata", "a"
 	.align		4
 // Q = 0x18BB70000
 // rk1 = 2^(32*3) mod Q << 32
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 8550408735a0..46049850727d 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -58,12 +58,11 @@
 	sha1su1		v\s0\().4s, v\s3\().4s
 	.endm
 
-	/*
-	 * The SHA1 round constants
-	 */
-	.align		4
-.Lsha1_rcon:
-	.word		0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
+	.macro		loadrc, k, val, tmp
+	movz		\tmp, :abs_g0_nc:\val
+	movk		\tmp, :abs_g1:\val
+	dup		\k, \tmp
+	.endm
 
 	/*
 	 * void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
@@ -71,11 +70,10 @@
 	 */
 ENTRY(sha1_ce_transform)
 	/* load round constants */
-	adr		x6, .Lsha1_rcon
-	ld1r		{k0.4s}, [x6], #4
-	ld1r		{k1.4s}, [x6], #4
-	ld1r		{k2.4s}, [x6], #4
-	ld1r		{k3.4s}, [x6]
+	loadrc		k0.4s, 0x5a827999, w6
+	loadrc		k1.4s, 0x6ed9eba1, w6
+	loadrc		k2.4s, 0x8f1bbcdc, w6
+	loadrc		k3.4s, 0xca62c1d6, w6
 
 	/* load state */
 	ld1		{dgav.4s}, [x0]
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 679c6c002f4f..4c3c89b812ce 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -53,6 +53,7 @@
 	/*
 	 * The SHA-256 round constants
 	 */
+	.section	".rodata", "a"
 	.align		4
 .Lsha2_rcon:
 	.word		0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
@@ -76,9 +77,10 @@
 	 * void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
 	 *			  int blocks)
 	 */
+	.text
 ENTRY(sha2_ce_transform)
 	/* load round constants */
-	adr		x8, .Lsha2_rcon
+	adr_l		x8, .Lsha2_rcon
 	ld1		{ v0.4s- v3.4s}, [x8], #64
 	ld1		{ v4.4s- v7.4s}, [x8], #64
 	ld1		{ v8.4s-v11.4s}, [x8], #64
diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S
new file mode 100644
index 000000000000..332ad7530690
--- /dev/null
+++ b/arch/arm64/crypto/sha3-ce-core.S
@@ -0,0 +1,210 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sha3-ce-core.S - core SHA-3 transform using v8.2 Crypto Extensions
+ *
+ * Copyright (C) 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.irp	b,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
+	.set	.Lv\b\().2d, \b
+	.set	.Lv\b\().16b, \b
+	.endr
+
+	/*
+	 * ARMv8.2 Crypto Extensions instructions
+	 */
+	.macro	eor3, rd, rn, rm, ra
+	.inst	0xce000000 | .L\rd | (.L\rn << 5) | (.L\ra << 10) | (.L\rm << 16)
+	.endm
+
+	.macro	rax1, rd, rn, rm
+	.inst	0xce608c00 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	.macro	bcax, rd, rn, rm, ra
+	.inst	0xce200000 | .L\rd | (.L\rn << 5) | (.L\ra << 10) | (.L\rm << 16)
+	.endm
+
+	.macro	xar, rd, rn, rm, imm6
+	.inst	0xce800000 | .L\rd | (.L\rn << 5) | ((\imm6) << 10) | (.L\rm << 16)
+	.endm
+
+	/*
+	 * sha3_ce_transform(u64 *st, const u8 *data, int blocks, int dg_size)
+	 */
+	.text
+ENTRY(sha3_ce_transform)
+	/* load state */
+	add	x8, x0, #32
+	ld1	{ v0.1d- v3.1d}, [x0]
+	ld1	{ v4.1d- v7.1d}, [x8], #32
+	ld1	{ v8.1d-v11.1d}, [x8], #32
+	ld1	{v12.1d-v15.1d}, [x8], #32
+	ld1	{v16.1d-v19.1d}, [x8], #32
+	ld1	{v20.1d-v23.1d}, [x8], #32
+	ld1	{v24.1d}, [x8]
+
+0:	sub	w2, w2, #1
+	mov	w8, #24
+	adr_l	x9, .Lsha3_rcon
+
+	/* load input */
+	ld1	{v25.8b-v28.8b}, [x1], #32
+	ld1	{v29.8b-v31.8b}, [x1], #24
+	eor	v0.8b, v0.8b, v25.8b
+	eor	v1.8b, v1.8b, v26.8b
+	eor	v2.8b, v2.8b, v27.8b
+	eor	v3.8b, v3.8b, v28.8b
+	eor	v4.8b, v4.8b, v29.8b
+	eor	v5.8b, v5.8b, v30.8b
+	eor	v6.8b, v6.8b, v31.8b
+
+	tbnz	x3, #6, 2f		// SHA3-512
+
+	ld1	{v25.8b-v28.8b}, [x1], #32
+	ld1	{v29.8b-v30.8b}, [x1], #16
+	eor	 v7.8b,  v7.8b, v25.8b
+	eor	 v8.8b,  v8.8b, v26.8b
+	eor	 v9.8b,  v9.8b, v27.8b
+	eor	v10.8b, v10.8b, v28.8b
+	eor	v11.8b, v11.8b, v29.8b
+	eor	v12.8b, v12.8b, v30.8b
+
+	tbnz	x3, #4, 1f		// SHA3-384 or SHA3-224
+
+	// SHA3-256
+	ld1	{v25.8b-v28.8b}, [x1], #32
+	eor	v13.8b, v13.8b, v25.8b
+	eor	v14.8b, v14.8b, v26.8b
+	eor	v15.8b, v15.8b, v27.8b
+	eor	v16.8b, v16.8b, v28.8b
+	b	3f
+
+1:	tbz	x3, #2, 3f		// bit 2 cleared? SHA-384
+
+	// SHA3-224
+	ld1	{v25.8b-v28.8b}, [x1], #32
+	ld1	{v29.8b}, [x1], #8
+	eor	v13.8b, v13.8b, v25.8b
+	eor	v14.8b, v14.8b, v26.8b
+	eor	v15.8b, v15.8b, v27.8b
+	eor	v16.8b, v16.8b, v28.8b
+	eor	v17.8b, v17.8b, v29.8b
+	b	3f
+
+	// SHA3-512
+2:	ld1	{v25.8b-v26.8b}, [x1], #16
+	eor	 v7.8b,  v7.8b, v25.8b
+	eor	 v8.8b,  v8.8b, v26.8b
+
+3:	sub	w8, w8, #1
+
+	eor3	v29.16b,  v4.16b,  v9.16b, v14.16b
+	eor3	v26.16b,  v1.16b,  v6.16b, v11.16b
+	eor3	v28.16b,  v3.16b,  v8.16b, v13.16b
+	eor3	v25.16b,  v0.16b,  v5.16b, v10.16b
+	eor3	v27.16b,  v2.16b,  v7.16b, v12.16b
+	eor3	v29.16b, v29.16b, v19.16b, v24.16b
+	eor3	v26.16b, v26.16b, v16.16b, v21.16b
+	eor3	v28.16b, v28.16b, v18.16b, v23.16b
+	eor3	v25.16b, v25.16b, v15.16b, v20.16b
+	eor3	v27.16b, v27.16b, v17.16b, v22.16b
+
+	rax1	v30.2d, v29.2d, v26.2d	// bc[0]
+	rax1	v26.2d, v26.2d, v28.2d	// bc[2]
+	rax1	v28.2d, v28.2d, v25.2d	// bc[4]
+	rax1	v25.2d, v25.2d, v27.2d	// bc[1]
+	rax1	v27.2d, v27.2d, v29.2d	// bc[3]
+
+	eor	 v0.16b,  v0.16b, v30.16b
+	xar	 v29.2d,   v1.2d,  v25.2d, (64 - 1)
+	xar	  v1.2d,   v6.2d,  v25.2d, (64 - 44)
+	xar	  v6.2d,   v9.2d,  v28.2d, (64 - 20)
+	xar	  v9.2d,  v22.2d,  v26.2d, (64 - 61)
+	xar	 v22.2d,  v14.2d,  v28.2d, (64 - 39)
+	xar	 v14.2d,  v20.2d,  v30.2d, (64 - 18)
+	xar	 v31.2d,   v2.2d,  v26.2d, (64 - 62)
+	xar	  v2.2d,  v12.2d,  v26.2d, (64 - 43)
+	xar	 v12.2d,  v13.2d,  v27.2d, (64 - 25)
+	xar	 v13.2d,  v19.2d,  v28.2d, (64 - 8)
+	xar	 v19.2d,  v23.2d,  v27.2d, (64 - 56)
+	xar	 v23.2d,  v15.2d,  v30.2d, (64 - 41)
+	xar	 v15.2d,   v4.2d,  v28.2d, (64 - 27)
+	xar	 v28.2d,  v24.2d,  v28.2d, (64 - 14)
+	xar	 v24.2d,  v21.2d,  v25.2d, (64 - 2)
+	xar	  v8.2d,   v8.2d,  v27.2d, (64 - 55)
+	xar	  v4.2d,  v16.2d,  v25.2d, (64 - 45)
+	xar	 v16.2d,   v5.2d,  v30.2d, (64 - 36)
+	xar	  v5.2d,   v3.2d,  v27.2d, (64 - 28)
+	xar	 v27.2d,  v18.2d,  v27.2d, (64 - 21)
+	xar	  v3.2d,  v17.2d,  v26.2d, (64 - 15)
+	xar	 v25.2d,  v11.2d,  v25.2d, (64 - 10)
+	xar	 v26.2d,   v7.2d,  v26.2d, (64 - 6)
+	xar	 v30.2d,  v10.2d,  v30.2d, (64 - 3)
+
+	bcax	v20.16b, v31.16b, v22.16b,  v8.16b
+	bcax	v21.16b,  v8.16b, v23.16b, v22.16b
+	bcax	v22.16b, v22.16b, v24.16b, v23.16b
+	bcax	v23.16b, v23.16b, v31.16b, v24.16b
+	bcax	v24.16b, v24.16b,  v8.16b, v31.16b
+
+	ld1r	{v31.2d}, [x9], #8
+
+	bcax	v17.16b, v25.16b, v19.16b,  v3.16b
+	bcax	v18.16b,  v3.16b, v15.16b, v19.16b
+	bcax	v19.16b, v19.16b, v16.16b, v15.16b
+	bcax	v15.16b, v15.16b, v25.16b, v16.16b
+	bcax	v16.16b, v16.16b,  v3.16b, v25.16b
+
+	bcax	v10.16b, v29.16b, v12.16b, v26.16b
+	bcax	v11.16b, v26.16b, v13.16b, v12.16b
+	bcax	v12.16b, v12.16b, v14.16b, v13.16b
+	bcax	v13.16b, v13.16b, v29.16b, v14.16b
+	bcax	v14.16b, v14.16b, v26.16b, v29.16b
+
+	bcax	 v7.16b, v30.16b,  v9.16b,  v4.16b
+	bcax	 v8.16b,  v4.16b,  v5.16b,  v9.16b
+	bcax	 v9.16b,  v9.16b,  v6.16b,  v5.16b
+	bcax	 v5.16b,  v5.16b, v30.16b,  v6.16b
+	bcax	 v6.16b,  v6.16b,  v4.16b, v30.16b
+
+	bcax	 v3.16b, v27.16b,  v0.16b, v28.16b
+	bcax	 v4.16b, v28.16b,  v1.16b,  v0.16b
+	bcax	 v0.16b,  v0.16b,  v2.16b,  v1.16b
+	bcax	 v1.16b,  v1.16b, v27.16b,  v2.16b
+	bcax	 v2.16b,  v2.16b, v28.16b, v27.16b
+
+	eor	 v0.16b,  v0.16b, v31.16b
+
+	cbnz	w8, 3b
+	cbnz	w2, 0b
+
+	/* save state */
+	st1	{ v0.1d- v3.1d}, [x0], #32
+	st1	{ v4.1d- v7.1d}, [x0], #32
+	st1	{ v8.1d-v11.1d}, [x0], #32
+	st1	{v12.1d-v15.1d}, [x0], #32
+	st1	{v16.1d-v19.1d}, [x0], #32
+	st1	{v20.1d-v23.1d}, [x0], #32
+	st1	{v24.1d}, [x0]
+	ret
+ENDPROC(sha3_ce_transform)
+
+	.section	".rodata", "a"
+	.align		8
+.Lsha3_rcon:
+	.quad	0x0000000000000001, 0x0000000000008082, 0x800000000000808a
+	.quad	0x8000000080008000, 0x000000000000808b, 0x0000000080000001
+	.quad	0x8000000080008081, 0x8000000000008009, 0x000000000000008a
+	.quad	0x0000000000000088, 0x0000000080008009, 0x000000008000000a
+	.quad	0x000000008000808b, 0x800000000000008b, 0x8000000000008089
+	.quad	0x8000000000008003, 0x8000000000008002, 0x8000000000000080
+	.quad	0x000000000000800a, 0x800000008000000a, 0x8000000080008081
+	.quad	0x8000000000008080, 0x0000000080000001, 0x8000000080008008
diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c
new file mode 100644
index 000000000000..da8222e528bd
--- /dev/null
+++ b/arch/arm64/crypto/sha3-ce-glue.c
@@ -0,0 +1,161 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sha3-ce-glue.c - core SHA-3 transform using v8.2 Crypto Extensions
+ *
+ * Copyright (C) 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha3.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA3 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sha3_ce_transform(u64 *st, const u8 *data, int blocks,
+				  int md_len);
+
+static int sha3_update(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+	unsigned int digest_size = crypto_shash_digestsize(desc->tfm);
+
+	if (!may_use_simd())
+		return crypto_sha3_update(desc, data, len);
+
+	if ((sctx->partial + len) >= sctx->rsiz) {
+		int blocks;
+
+		if (sctx->partial) {
+			int p = sctx->rsiz - sctx->partial;
+
+			memcpy(sctx->buf + sctx->partial, data, p);
+			kernel_neon_begin();
+			sha3_ce_transform(sctx->st, sctx->buf, 1, digest_size);
+			kernel_neon_end();
+
+			data += p;
+			len -= p;
+			sctx->partial = 0;
+		}
+
+		blocks = len / sctx->rsiz;
+		len %= sctx->rsiz;
+
+		if (blocks) {
+			kernel_neon_begin();
+			sha3_ce_transform(sctx->st, data, blocks, digest_size);
+			kernel_neon_end();
+			data += blocks * sctx->rsiz;
+		}
+	}
+
+	if (len) {
+		memcpy(sctx->buf + sctx->partial, data, len);
+		sctx->partial += len;
+	}
+	return 0;
+}
+
+static int sha3_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+	unsigned int digest_size = crypto_shash_digestsize(desc->tfm);
+	__le64 *digest = (__le64 *)out;
+	int i;
+
+	if (!may_use_simd())
+		return crypto_sha3_final(desc, out);
+
+	sctx->buf[sctx->partial++] = 0x06;
+	memset(sctx->buf + sctx->partial, 0, sctx->rsiz - sctx->partial);
+	sctx->buf[sctx->rsiz - 1] |= 0x80;
+
+	kernel_neon_begin();
+	sha3_ce_transform(sctx->st, sctx->buf, 1, digest_size);
+	kernel_neon_end();
+
+	for (i = 0; i < digest_size / 8; i++)
+		put_unaligned_le64(sctx->st[i], digest++);
+
+	if (digest_size & 4)
+		put_unaligned_le32(sctx->st[i], (__le32 *)digest);
+
+	*sctx = (struct sha3_state){};
+	return 0;
+}
+
+static struct shash_alg algs[] = { {
+	.digestsize		= SHA3_224_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= sha3_update,
+	.final			= sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-224",
+	.base.cra_driver_name	= "sha3-224-ce",
+	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+	.base.cra_blocksize	= SHA3_224_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_priority	= 200,
+}, {
+	.digestsize		= SHA3_256_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= sha3_update,
+	.final			= sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-256",
+	.base.cra_driver_name	= "sha3-256-ce",
+	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+	.base.cra_blocksize	= SHA3_256_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_priority	= 200,
+}, {
+	.digestsize		= SHA3_384_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= sha3_update,
+	.final			= sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-384",
+	.base.cra_driver_name	= "sha3-384-ce",
+	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+	.base.cra_blocksize	= SHA3_384_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_priority	= 200,
+}, {
+	.digestsize		= SHA3_512_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= sha3_update,
+	.final			= sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-512",
+	.base.cra_driver_name	= "sha3-512-ce",
+	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+	.base.cra_blocksize	= SHA3_512_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_priority	= 200,
+} };
+
+static int __init sha3_neon_mod_init(void)
+{
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha3_neon_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(SHA3, sha3_neon_mod_init);
+module_exit(sha3_neon_mod_fini);
diff --git a/arch/arm64/crypto/sha512-ce-core.S b/arch/arm64/crypto/sha512-ce-core.S
new file mode 100644
index 000000000000..7f3bca5c59a2
--- /dev/null
+++ b/arch/arm64/crypto/sha512-ce-core.S
@@ -0,0 +1,204 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sha512-ce-core.S - core SHA-384/SHA-512 transform using v8 Crypto Extensions
+ *
+ * Copyright (C) 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.irp		b,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19
+	.set		.Lq\b, \b
+	.set		.Lv\b\().2d, \b
+	.endr
+
+	.macro		sha512h, rd, rn, rm
+	.inst		0xce608000 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	.macro		sha512h2, rd, rn, rm
+	.inst		0xce608400 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	.macro		sha512su0, rd, rn
+	.inst		0xcec08000 | .L\rd | (.L\rn << 5)
+	.endm
+
+	.macro		sha512su1, rd, rn, rm
+	.inst		0xce608800 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	/*
+	 * The SHA-512 round constants
+	 */
+	.section	".rodata", "a"
+	.align		4
+.Lsha512_rcon:
+	.quad		0x428a2f98d728ae22, 0x7137449123ef65cd
+	.quad		0xb5c0fbcfec4d3b2f, 0xe9b5dba58189dbbc
+	.quad		0x3956c25bf348b538, 0x59f111f1b605d019
+	.quad		0x923f82a4af194f9b, 0xab1c5ed5da6d8118
+	.quad		0xd807aa98a3030242, 0x12835b0145706fbe
+	.quad		0x243185be4ee4b28c, 0x550c7dc3d5ffb4e2
+	.quad		0x72be5d74f27b896f, 0x80deb1fe3b1696b1
+	.quad		0x9bdc06a725c71235, 0xc19bf174cf692694
+	.quad		0xe49b69c19ef14ad2, 0xefbe4786384f25e3
+	.quad		0x0fc19dc68b8cd5b5, 0x240ca1cc77ac9c65
+	.quad		0x2de92c6f592b0275, 0x4a7484aa6ea6e483
+	.quad		0x5cb0a9dcbd41fbd4, 0x76f988da831153b5
+	.quad		0x983e5152ee66dfab, 0xa831c66d2db43210
+	.quad		0xb00327c898fb213f, 0xbf597fc7beef0ee4
+	.quad		0xc6e00bf33da88fc2, 0xd5a79147930aa725
+	.quad		0x06ca6351e003826f, 0x142929670a0e6e70
+	.quad		0x27b70a8546d22ffc, 0x2e1b21385c26c926
+	.quad		0x4d2c6dfc5ac42aed, 0x53380d139d95b3df
+	.quad		0x650a73548baf63de, 0x766a0abb3c77b2a8
+	.quad		0x81c2c92e47edaee6, 0x92722c851482353b
+	.quad		0xa2bfe8a14cf10364, 0xa81a664bbc423001
+	.quad		0xc24b8b70d0f89791, 0xc76c51a30654be30
+	.quad		0xd192e819d6ef5218, 0xd69906245565a910
+	.quad		0xf40e35855771202a, 0x106aa07032bbd1b8
+	.quad		0x19a4c116b8d2d0c8, 0x1e376c085141ab53
+	.quad		0x2748774cdf8eeb99, 0x34b0bcb5e19b48a8
+	.quad		0x391c0cb3c5c95a63, 0x4ed8aa4ae3418acb
+	.quad		0x5b9cca4f7763e373, 0x682e6ff3d6b2b8a3
+	.quad		0x748f82ee5defb2fc, 0x78a5636f43172f60
+	.quad		0x84c87814a1f0ab72, 0x8cc702081a6439ec
+	.quad		0x90befffa23631e28, 0xa4506cebde82bde9
+	.quad		0xbef9a3f7b2c67915, 0xc67178f2e372532b
+	.quad		0xca273eceea26619c, 0xd186b8c721c0c207
+	.quad		0xeada7dd6cde0eb1e, 0xf57d4f7fee6ed178
+	.quad		0x06f067aa72176fba, 0x0a637dc5a2c898a6
+	.quad		0x113f9804bef90dae, 0x1b710b35131c471b
+	.quad		0x28db77f523047d84, 0x32caab7b40c72493
+	.quad		0x3c9ebe0a15c9bebc, 0x431d67c49c100d4c
+	.quad		0x4cc5d4becb3e42b6, 0x597f299cfc657e2a
+	.quad		0x5fcb6fab3ad6faec, 0x6c44198c4a475817
+
+	.macro		dround, i0, i1, i2, i3, i4, rc0, rc1, in0, in1, in2, in3, in4
+	.ifnb		\rc1
+	ld1		{v\rc1\().2d}, [x4], #16
+	.endif
+	add		v5.2d, v\rc0\().2d, v\in0\().2d
+	ext		v6.16b, v\i2\().16b, v\i3\().16b, #8
+	ext		v5.16b, v5.16b, v5.16b, #8
+	ext		v7.16b, v\i1\().16b, v\i2\().16b, #8
+	add		v\i3\().2d, v\i3\().2d, v5.2d
+	.ifnb		\in1
+	ext		v5.16b, v\in3\().16b, v\in4\().16b, #8
+	sha512su0	v\in0\().2d, v\in1\().2d
+	.endif
+	sha512h		q\i3, q6, v7.2d
+	.ifnb		\in1
+	sha512su1	v\in0\().2d, v\in2\().2d, v5.2d
+	.endif
+	add		v\i4\().2d, v\i1\().2d, v\i3\().2d
+	sha512h2	q\i3, q\i1, v\i0\().2d
+	.endm
+
+	/*
+	 * void sha512_ce_transform(struct sha512_state *sst, u8 const *src,
+	 *			  int blocks)
+	 */
+	.text
+ENTRY(sha512_ce_transform)
+	/* load state */
+	ld1		{v8.2d-v11.2d}, [x0]
+
+	/* load first 4 round constants */
+	adr_l		x3, .Lsha512_rcon
+	ld1		{v20.2d-v23.2d}, [x3], #64
+
+	/* load input */
+0:	ld1		{v12.2d-v15.2d}, [x1], #64
+	ld1		{v16.2d-v19.2d}, [x1], #64
+	sub		w2, w2, #1
+
+CPU_LE(	rev64		v12.16b, v12.16b	)
+CPU_LE(	rev64		v13.16b, v13.16b	)
+CPU_LE(	rev64		v14.16b, v14.16b	)
+CPU_LE(	rev64		v15.16b, v15.16b	)
+CPU_LE(	rev64		v16.16b, v16.16b	)
+CPU_LE(	rev64		v17.16b, v17.16b	)
+CPU_LE(	rev64		v18.16b, v18.16b	)
+CPU_LE(	rev64		v19.16b, v19.16b	)
+
+	mov		x4, x3				// rc pointer
+
+	mov		v0.16b, v8.16b
+	mov		v1.16b, v9.16b
+	mov		v2.16b, v10.16b
+	mov		v3.16b, v11.16b
+
+	// v0  ab  cd  --  ef  gh  ab
+	// v1  cd  --  ef  gh  ab  cd
+	// v2  ef  gh  ab  cd  --  ef
+	// v3  gh  ab  cd  --  ef  gh
+	// v4  --  ef  gh  ab  cd  --
+
+	dround		0, 1, 2, 3, 4, 20, 24, 12, 13, 19, 16, 17
+	dround		3, 0, 4, 2, 1, 21, 25, 13, 14, 12, 17, 18
+	dround		2, 3, 1, 4, 0, 22, 26, 14, 15, 13, 18, 19
+	dround		4, 2, 0, 1, 3, 23, 27, 15, 16, 14, 19, 12
+	dround		1, 4, 3, 0, 2, 24, 28, 16, 17, 15, 12, 13
+
+	dround		0, 1, 2, 3, 4, 25, 29, 17, 18, 16, 13, 14
+	dround		3, 0, 4, 2, 1, 26, 30, 18, 19, 17, 14, 15
+	dround		2, 3, 1, 4, 0, 27, 31, 19, 12, 18, 15, 16
+	dround		4, 2, 0, 1, 3, 28, 24, 12, 13, 19, 16, 17
+	dround		1, 4, 3, 0, 2, 29, 25, 13, 14, 12, 17, 18
+
+	dround		0, 1, 2, 3, 4, 30, 26, 14, 15, 13, 18, 19
+	dround		3, 0, 4, 2, 1, 31, 27, 15, 16, 14, 19, 12
+	dround		2, 3, 1, 4, 0, 24, 28, 16, 17, 15, 12, 13
+	dround		4, 2, 0, 1, 3, 25, 29, 17, 18, 16, 13, 14
+	dround		1, 4, 3, 0, 2, 26, 30, 18, 19, 17, 14, 15
+
+	dround		0, 1, 2, 3, 4, 27, 31, 19, 12, 18, 15, 16
+	dround		3, 0, 4, 2, 1, 28, 24, 12, 13, 19, 16, 17
+	dround		2, 3, 1, 4, 0, 29, 25, 13, 14, 12, 17, 18
+	dround		4, 2, 0, 1, 3, 30, 26, 14, 15, 13, 18, 19
+	dround		1, 4, 3, 0, 2, 31, 27, 15, 16, 14, 19, 12
+
+	dround		0, 1, 2, 3, 4, 24, 28, 16, 17, 15, 12, 13
+	dround		3, 0, 4, 2, 1, 25, 29, 17, 18, 16, 13, 14
+	dround		2, 3, 1, 4, 0, 26, 30, 18, 19, 17, 14, 15
+	dround		4, 2, 0, 1, 3, 27, 31, 19, 12, 18, 15, 16
+	dround		1, 4, 3, 0, 2, 28, 24, 12, 13, 19, 16, 17
+
+	dround		0, 1, 2, 3, 4, 29, 25, 13, 14, 12, 17, 18
+	dround		3, 0, 4, 2, 1, 30, 26, 14, 15, 13, 18, 19
+	dround		2, 3, 1, 4, 0, 31, 27, 15, 16, 14, 19, 12
+	dround		4, 2, 0, 1, 3, 24, 28, 16, 17, 15, 12, 13
+	dround		1, 4, 3, 0, 2, 25, 29, 17, 18, 16, 13, 14
+
+	dround		0, 1, 2, 3, 4, 26, 30, 18, 19, 17, 14, 15
+	dround		3, 0, 4, 2, 1, 27, 31, 19, 12, 18, 15, 16
+	dround		2, 3, 1, 4, 0, 28, 24, 12
+	dround		4, 2, 0, 1, 3, 29, 25, 13
+	dround		1, 4, 3, 0, 2, 30, 26, 14
+
+	dround		0, 1, 2, 3, 4, 31, 27, 15
+	dround		3, 0, 4, 2, 1, 24,   , 16
+	dround		2, 3, 1, 4, 0, 25,   , 17
+	dround		4, 2, 0, 1, 3, 26,   , 18
+	dround		1, 4, 3, 0, 2, 27,   , 19
+
+	/* update state */
+	add		v8.2d, v8.2d, v0.2d
+	add		v9.2d, v9.2d, v1.2d
+	add		v10.2d, v10.2d, v2.2d
+	add		v11.2d, v11.2d, v3.2d
+
+	/* handled all input blocks? */
+	cbnz		w2, 0b
+
+	/* store new state */
+3:	st1		{v8.2d-v11.2d}, [x0]
+	ret
+ENDPROC(sha512_ce_transform)
diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c
new file mode 100644
index 000000000000..a77c8632a589
--- /dev/null
+++ b/arch/arm64/crypto/sha512-ce-glue.c
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sha512-ce-glue.c - SHA-384/SHA-512 using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA-384/SHA-512 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sha512_ce_transform(struct sha512_state *sst, u8 const *src,
+				    int blocks);
+
+asmlinkage void sha512_block_data_order(u64 *digest, u8 const *src, int blocks);
+
+static int sha512_ce_update(struct shash_desc *desc, const u8 *data,
+			    unsigned int len)
+{
+	if (!may_use_simd())
+		return sha512_base_do_update(desc, data, len,
+				(sha512_block_fn *)sha512_block_data_order);
+
+	kernel_neon_begin();
+	sha512_base_do_update(desc, data, len,
+			      (sha512_block_fn *)sha512_ce_transform);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int sha512_ce_finup(struct shash_desc *desc, const u8 *data,
+			   unsigned int len, u8 *out)
+{
+	if (!may_use_simd()) {
+		if (len)
+			sha512_base_do_update(desc, data, len,
+				(sha512_block_fn *)sha512_block_data_order);
+		sha512_base_do_finalize(desc,
+				(sha512_block_fn *)sha512_block_data_order);
+		return sha512_base_finish(desc, out);
+	}
+
+	kernel_neon_begin();
+	sha512_base_do_update(desc, data, len,
+			      (sha512_block_fn *)sha512_ce_transform);
+	sha512_base_do_finalize(desc, (sha512_block_fn *)sha512_ce_transform);
+	kernel_neon_end();
+	return sha512_base_finish(desc, out);
+}
+
+static int sha512_ce_final(struct shash_desc *desc, u8 *out)
+{
+	if (!may_use_simd()) {
+		sha512_base_do_finalize(desc,
+				(sha512_block_fn *)sha512_block_data_order);
+		return sha512_base_finish(desc, out);
+	}
+
+	kernel_neon_begin();
+	sha512_base_do_finalize(desc, (sha512_block_fn *)sha512_ce_transform);
+	kernel_neon_end();
+	return sha512_base_finish(desc, out);
+}
+
+static struct shash_alg algs[] = { {
+	.init			= sha384_base_init,
+	.update			= sha512_ce_update,
+	.final			= sha512_ce_final,
+	.finup			= sha512_ce_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA384_DIGEST_SIZE,
+	.base.cra_name		= "sha384",
+	.base.cra_driver_name	= "sha384-ce",
+	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+	.base.cra_blocksize	= SHA512_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.init			= sha512_base_init,
+	.update			= sha512_ce_update,
+	.final			= sha512_ce_final,
+	.finup			= sha512_ce_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA512_DIGEST_SIZE,
+	.base.cra_name		= "sha512",
+	.base.cra_driver_name	= "sha512-ce",
+	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+	.base.cra_blocksize	= SHA512_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+} };
+
+static int __init sha512_ce_mod_init(void)
+{
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha512_ce_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(SHA512, sha512_ce_mod_init);
+module_exit(sha512_ce_mod_fini);
diff --git a/arch/arm64/crypto/sha512-glue.c b/arch/arm64/crypto/sha512-glue.c
index aff35c9992a4..27db4851e380 100644
--- a/arch/arm64/crypto/sha512-glue.c
+++ b/arch/arm64/crypto/sha512-glue.c
@@ -27,6 +27,7 @@ MODULE_ALIAS_CRYPTO("sha512");
 
 asmlinkage void sha512_block_data_order(u32 *digest, const void *data,
 					unsigned int num_blks);
+EXPORT_SYMBOL(sha512_block_data_order);
 
 static int sha512_update(struct shash_desc *desc, const u8 *data,
 			 unsigned int len)
diff --git a/arch/arm64/crypto/sm3-ce-core.S b/arch/arm64/crypto/sm3-ce-core.S
new file mode 100644
index 000000000000..27169fe07a68
--- /dev/null
+++ b/arch/arm64/crypto/sm3-ce-core.S
@@ -0,0 +1,141 @@
+/*
+ * sm3-ce-core.S - SM3 secure hash using ARMv8.2 Crypto Extensions
+ *
+ * Copyright (C) 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.irp		b, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
+	.set		.Lv\b\().4s, \b
+	.endr
+
+	.macro		sm3partw1, rd, rn, rm
+	.inst		0xce60c000 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3partw2, rd, rn, rm
+	.inst		0xce60c400 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3ss1, rd, rn, rm, ra
+	.inst		0xce400000 | .L\rd | (.L\rn << 5) | (.L\ra << 10) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3tt1a, rd, rn, rm, imm2
+	.inst		0xce408000 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3tt1b, rd, rn, rm, imm2
+	.inst		0xce408400 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3tt2a, rd, rn, rm, imm2
+	.inst		0xce408800 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3tt2b, rd, rn, rm, imm2
+	.inst		0xce408c00 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
+	.endm
+
+	.macro		round, ab, s0, t0, t1, i
+	sm3ss1		v5.4s, v8.4s, \t0\().4s, v9.4s
+	shl		\t1\().4s, \t0\().4s, #1
+	sri		\t1\().4s, \t0\().4s, #31
+	sm3tt1\ab	v8.4s, v5.4s, v10.4s, \i
+	sm3tt2\ab	v9.4s, v5.4s, \s0\().4s, \i
+	.endm
+
+	.macro		qround, ab, s0, s1, s2, s3, s4
+	.ifnb		\s4
+	ext		\s4\().16b, \s1\().16b, \s2\().16b, #12
+	ext		v6.16b, \s0\().16b, \s1\().16b, #12
+	ext		v7.16b, \s2\().16b, \s3\().16b, #8
+	sm3partw1	\s4\().4s, \s0\().4s, \s3\().4s
+	.endif
+
+	eor		v10.16b, \s0\().16b, \s1\().16b
+
+	round		\ab, \s0, v11, v12, 0
+	round		\ab, \s0, v12, v11, 1
+	round		\ab, \s0, v11, v12, 2
+	round		\ab, \s0, v12, v11, 3
+
+	.ifnb		\s4
+	sm3partw2	\s4\().4s, v7.4s, v6.4s
+	.endif
+	.endm
+
+	/*
+	 * void sm3_ce_transform(struct sm3_state *sst, u8 const *src,
+	 *                       int blocks)
+	 */
+	.text
+ENTRY(sm3_ce_transform)
+	/* load state */
+	ld1		{v8.4s-v9.4s}, [x0]
+	rev64		v8.4s, v8.4s
+	rev64		v9.4s, v9.4s
+	ext		v8.16b, v8.16b, v8.16b, #8
+	ext		v9.16b, v9.16b, v9.16b, #8
+
+	adr_l		x8, .Lt
+	ldp		s13, s14, [x8]
+
+	/* load input */
+0:	ld1		{v0.16b-v3.16b}, [x1], #64
+	sub		w2, w2, #1
+
+	mov		v15.16b, v8.16b
+	mov		v16.16b, v9.16b
+
+CPU_LE(	rev32		v0.16b, v0.16b		)
+CPU_LE(	rev32		v1.16b, v1.16b		)
+CPU_LE(	rev32		v2.16b, v2.16b		)
+CPU_LE(	rev32		v3.16b, v3.16b		)
+
+	ext		v11.16b, v13.16b, v13.16b, #4
+
+	qround		a, v0, v1, v2, v3, v4
+	qround		a, v1, v2, v3, v4, v0
+	qround		a, v2, v3, v4, v0, v1
+	qround		a, v3, v4, v0, v1, v2
+
+	ext		v11.16b, v14.16b, v14.16b, #4
+
+	qround		b, v4, v0, v1, v2, v3
+	qround		b, v0, v1, v2, v3, v4
+	qround		b, v1, v2, v3, v4, v0
+	qround		b, v2, v3, v4, v0, v1
+	qround		b, v3, v4, v0, v1, v2
+	qround		b, v4, v0, v1, v2, v3
+	qround		b, v0, v1, v2, v3, v4
+	qround		b, v1, v2, v3, v4, v0
+	qround		b, v2, v3, v4, v0, v1
+	qround		b, v3, v4
+	qround		b, v4, v0
+	qround		b, v0, v1
+
+	eor		v8.16b, v8.16b, v15.16b
+	eor		v9.16b, v9.16b, v16.16b
+
+	/* handled all input blocks? */
+	cbnz		w2, 0b
+
+	/* save state */
+	rev64		v8.4s, v8.4s
+	rev64		v9.4s, v9.4s
+	ext		v8.16b, v8.16b, v8.16b, #8
+	ext		v9.16b, v9.16b, v9.16b, #8
+	st1		{v8.4s-v9.4s}, [x0]
+	ret
+ENDPROC(sm3_ce_transform)
+
+	.section	".rodata", "a"
+	.align		3
+.Lt:	.word		0x79cc4519, 0x9d8a7a87
diff --git a/arch/arm64/crypto/sm3-ce-glue.c b/arch/arm64/crypto/sm3-ce-glue.c
new file mode 100644
index 000000000000..3b4948f7e26f
--- /dev/null
+++ b/arch/arm64/crypto/sm3-ce-glue.c
@@ -0,0 +1,92 @@
+/*
+ * sm3-ce-glue.c - SM3 secure hash using ARMv8.2 Crypto Extensions
+ *
+ * Copyright (C) 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sm3.h>
+#include <crypto/sm3_base.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SM3 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sm3_ce_transform(struct sm3_state *sst, u8 const *src,
+				 int blocks);
+
+static int sm3_ce_update(struct shash_desc *desc, const u8 *data,
+			 unsigned int len)
+{
+	if (!may_use_simd())
+		return crypto_sm3_update(desc, data, len);
+
+	kernel_neon_begin();
+	sm3_base_do_update(desc, data, len, sm3_ce_transform);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int sm3_ce_final(struct shash_desc *desc, u8 *out)
+{
+	if (!may_use_simd())
+		return crypto_sm3_finup(desc, NULL, 0, out);
+
+	kernel_neon_begin();
+	sm3_base_do_finalize(desc, sm3_ce_transform);
+	kernel_neon_end();
+
+	return sm3_base_finish(desc, out);
+}
+
+static int sm3_ce_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	if (!may_use_simd())
+		return crypto_sm3_finup(desc, data, len, out);
+
+	kernel_neon_begin();
+	sm3_base_do_update(desc, data, len, sm3_ce_transform);
+	kernel_neon_end();
+
+	return sm3_ce_final(desc, out);
+}
+
+static struct shash_alg sm3_alg = {
+	.digestsize		= SM3_DIGEST_SIZE,
+	.init			= sm3_base_init,
+	.update			= sm3_ce_update,
+	.final			= sm3_ce_final,
+	.finup			= sm3_ce_finup,
+	.descsize		= sizeof(struct sm3_state),
+	.base.cra_name		= "sm3",
+	.base.cra_driver_name	= "sm3-ce",
+	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+	.base.cra_blocksize	= SM3_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_priority	= 200,
+};
+
+static int __init sm3_ce_mod_init(void)
+{
+	return crypto_register_shash(&sm3_alg);
+}
+
+static void __exit sm3_ce_mod_fini(void)
+{
+	crypto_unregister_shash(&sm3_alg);
+}
+
+module_cpu_feature_match(SM3, sm3_ce_mod_init);
+module_exit(sm3_ce_mod_fini);
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index e63d0a8312de..3a9b84d39d71 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,5 +1,4 @@
 generic-y += bugs.h
-generic-y += clkdev.h
 generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 4a85c6952a22..669028172fd6 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -12,6 +12,8 @@
 #include <linux/stddef.h>
 #include <linux/stringify.h>
 
+extern int alternatives_applied;
+
 struct alt_instr {
 	s32 orig_offset;	/* offset to original instruction */
 	s32 alt_offset;		/* offset to replacement instruction */
diff --git a/arch/arm64/include/asm/arm_dsu_pmu.h b/arch/arm64/include/asm/arm_dsu_pmu.h
new file mode 100644
index 000000000000..82e5cc3356bf
--- /dev/null
+++ b/arch/arm64/include/asm/arm_dsu_pmu.h
@@ -0,0 +1,129 @@
+/*
+ * ARM DynamIQ Shared Unit (DSU) PMU Low level register access routines.
+ *
+ * Copyright (C) ARM Limited, 2017.
+ *
+ * Author: Suzuki K Poulose <suzuki.poulose@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2, as published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/build_bug.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/barrier.h>
+#include <asm/sysreg.h>
+
+
+#define CLUSTERPMCR_EL1			sys_reg(3, 0, 15, 5, 0)
+#define CLUSTERPMCNTENSET_EL1		sys_reg(3, 0, 15, 5, 1)
+#define CLUSTERPMCNTENCLR_EL1		sys_reg(3, 0, 15, 5, 2)
+#define CLUSTERPMOVSSET_EL1		sys_reg(3, 0, 15, 5, 3)
+#define CLUSTERPMOVSCLR_EL1		sys_reg(3, 0, 15, 5, 4)
+#define CLUSTERPMSELR_EL1		sys_reg(3, 0, 15, 5, 5)
+#define CLUSTERPMINTENSET_EL1		sys_reg(3, 0, 15, 5, 6)
+#define CLUSTERPMINTENCLR_EL1		sys_reg(3, 0, 15, 5, 7)
+#define CLUSTERPMCCNTR_EL1		sys_reg(3, 0, 15, 6, 0)
+#define CLUSTERPMXEVTYPER_EL1		sys_reg(3, 0, 15, 6, 1)
+#define CLUSTERPMXEVCNTR_EL1		sys_reg(3, 0, 15, 6, 2)
+#define CLUSTERPMMDCR_EL1		sys_reg(3, 0, 15, 6, 3)
+#define CLUSTERPMCEID0_EL1		sys_reg(3, 0, 15, 6, 4)
+#define CLUSTERPMCEID1_EL1		sys_reg(3, 0, 15, 6, 5)
+
+static inline u32 __dsu_pmu_read_pmcr(void)
+{
+	return read_sysreg_s(CLUSTERPMCR_EL1);
+}
+
+static inline void __dsu_pmu_write_pmcr(u32 val)
+{
+	write_sysreg_s(val, CLUSTERPMCR_EL1);
+	isb();
+}
+
+static inline u32 __dsu_pmu_get_reset_overflow(void)
+{
+	u32 val = read_sysreg_s(CLUSTERPMOVSCLR_EL1);
+	/* Clear the bit */
+	write_sysreg_s(val, CLUSTERPMOVSCLR_EL1);
+	isb();
+	return val;
+}
+
+static inline void __dsu_pmu_select_counter(int counter)
+{
+	write_sysreg_s(counter, CLUSTERPMSELR_EL1);
+	isb();
+}
+
+static inline u64 __dsu_pmu_read_counter(int counter)
+{
+	__dsu_pmu_select_counter(counter);
+	return read_sysreg_s(CLUSTERPMXEVCNTR_EL1);
+}
+
+static inline void __dsu_pmu_write_counter(int counter, u64 val)
+{
+	__dsu_pmu_select_counter(counter);
+	write_sysreg_s(val, CLUSTERPMXEVCNTR_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_set_event(int counter, u32 event)
+{
+	__dsu_pmu_select_counter(counter);
+	write_sysreg_s(event, CLUSTERPMXEVTYPER_EL1);
+	isb();
+}
+
+static inline u64 __dsu_pmu_read_pmccntr(void)
+{
+	return read_sysreg_s(CLUSTERPMCCNTR_EL1);
+}
+
+static inline void __dsu_pmu_write_pmccntr(u64 val)
+{
+	write_sysreg_s(val, CLUSTERPMCCNTR_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_disable_counter(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMCNTENCLR_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_enable_counter(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMCNTENSET_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_counter_interrupt_enable(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMINTENSET_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_counter_interrupt_disable(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMINTENCLR_EL1);
+	isb();
+}
+
+
+static inline u32 __dsu_pmu_read_pmceid(int n)
+{
+	switch (n) {
+	case 0:
+		return read_sysreg_s(CLUSTERPMCEID0_EL1);
+	case 1:
+		return read_sysreg_s(CLUSTERPMCEID1_EL1);
+	default:
+		BUILD_BUG();
+		return 0;
+	}
+}
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index b3da6c886835..4128bec033f6 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -4,6 +4,7 @@
 
 #include <asm/alternative.h>
 #include <asm/kernel-pgtable.h>
+#include <asm/mmu.h>
 #include <asm/sysreg.h>
 #include <asm/assembler.h>
 
@@ -12,52 +13,63 @@
  */
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	.macro	__uaccess_ttbr0_disable, tmp1
-	mrs	\tmp1, ttbr1_el1		// swapper_pg_dir
-	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
-	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
+	mrs	\tmp1, ttbr1_el1			// swapper_pg_dir
+	bic	\tmp1, \tmp1, #TTBR_ASID_MASK
+	sub	\tmp1, \tmp1, #RESERVED_TTBR0_SIZE	// reserved_ttbr0 just before swapper_pg_dir
+	msr	ttbr0_el1, \tmp1			// set reserved TTBR0_EL1
+	isb
+	add	\tmp1, \tmp1, #RESERVED_TTBR0_SIZE
+	msr	ttbr1_el1, \tmp1		// set reserved ASID
 	isb
 	.endm
 
-	.macro	__uaccess_ttbr0_enable, tmp1
+	.macro	__uaccess_ttbr0_enable, tmp1, tmp2
 	get_thread_info \tmp1
 	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
+	mrs	\tmp2, ttbr1_el1
+	extr    \tmp2, \tmp2, \tmp1, #48
+	ror     \tmp2, \tmp2, #16
+	msr	ttbr1_el1, \tmp2		// set the active ASID
+	isb
 	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
 	isb
 	.endm
 
-	.macro	uaccess_ttbr0_disable, tmp1
+	.macro	uaccess_ttbr0_disable, tmp1, tmp2
 alternative_if_not ARM64_HAS_PAN
+	save_and_disable_irq \tmp2		// avoid preemption
 	__uaccess_ttbr0_disable \tmp1
+	restore_irq \tmp2
 alternative_else_nop_endif
 	.endm
 
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2, tmp3
 alternative_if_not ARM64_HAS_PAN
-	save_and_disable_irq \tmp2		// avoid preemption
-	__uaccess_ttbr0_enable \tmp1
-	restore_irq \tmp2
+	save_and_disable_irq \tmp3		// avoid preemption
+	__uaccess_ttbr0_enable \tmp1, \tmp2
+	restore_irq \tmp3
 alternative_else_nop_endif
 	.endm
 #else
-	.macro	uaccess_ttbr0_disable, tmp1
+	.macro	uaccess_ttbr0_disable, tmp1, tmp2
 	.endm
 
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2, tmp3
 	.endm
 #endif
 
 /*
  * These macros are no-ops when UAO is present.
  */
-	.macro	uaccess_disable_not_uao, tmp1
-	uaccess_ttbr0_disable \tmp1
+	.macro	uaccess_disable_not_uao, tmp1, tmp2
+	uaccess_ttbr0_disable \tmp1, \tmp2
 alternative_if ARM64_ALT_PAN_NOT_UAO
 	SET_PSTATE_PAN(1)
 alternative_else_nop_endif
 	.endm
 
-	.macro	uaccess_enable_not_uao, tmp1, tmp2
-	uaccess_ttbr0_enable \tmp1, \tmp2
+	.macro	uaccess_enable_not_uao, tmp1, tmp2, tmp3
+	uaccess_ttbr0_enable \tmp1, \tmp2, \tmp3
 alternative_if ARM64_ALT_PAN_NOT_UAO
 	SET_PSTATE_PAN(0)
 alternative_else_nop_endif
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index aef72d886677..3873dd7b5a32 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -26,7 +26,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
-#include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/ptrace.h>
@@ -110,6 +109,13 @@
 	.endm
 
 /*
+ * RAS Error Synchronization barrier
+ */
+	.macro  esb
+	hint    #16
+	.endm
+
+/*
  * NOP sequence
  */
 	.macro	nops, num
@@ -255,7 +261,11 @@ lr	.req	x30		// link register
 #else
 	adr_l	\dst, \sym
 #endif
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	mrs	\tmp, tpidr_el1
+alternative_else
+	mrs	\tmp, tpidr_el2
+alternative_endif
 	add	\dst, \dst, \tmp
 	.endm
 
@@ -266,7 +276,11 @@ lr	.req	x30		// link register
 	 */
 	.macro ldr_this_cpu dst, sym, tmp
 	adr_l	\dst, \sym
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	mrs	\tmp, tpidr_el1
+alternative_else
+	mrs	\tmp, tpidr_el2
+alternative_endif
 	ldr	\dst, [\dst, \tmp]
 	.endm
 
@@ -344,10 +358,26 @@ alternative_endif
  * tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map
  */
 	.macro	tcr_set_idmap_t0sz, valreg, tmpreg
-#ifndef CONFIG_ARM64_VA_BITS_48
 	ldr_l	\tmpreg, idmap_t0sz
 	bfi	\valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
-#endif
+	.endm
+
+/*
+ * tcr_compute_pa_size - set TCR.(I)PS to the highest supported
+ * ID_AA64MMFR0_EL1.PARange value
+ *
+ *	tcr:		register with the TCR_ELx value to be updated
+ *	pos:		IPS or PS bitfield position
+ *	tmp{0,1}:	temporary registers
+ */
+	.macro	tcr_compute_pa_size, tcr, pos, tmp0, tmp1
+	mrs	\tmp0, ID_AA64MMFR0_EL1
+	// Narrow PARange to fit the PS field in TCR_ELx
+	ubfx	\tmp0, \tmp0, #ID_AA64MMFR0_PARANGE_SHIFT, #3
+	mov	\tmp1, #ID_AA64MMFR0_PARANGE_MAX
+	cmp	\tmp0, \tmp1
+	csel	\tmp0, \tmp1, \tmp0, hi
+	bfi	\tcr, \tmp0, \pos, #3
 	.endm
 
 /*
@@ -478,37 +508,28 @@ alternative_endif
 	.endm
 
 /*
- * Errata workaround prior to TTBR0_EL1 update
+ * Arrange a physical address in a TTBR register, taking care of 52-bit
+ * addresses.
  *
- * 	val:	TTBR value with new BADDR, preserved
- * 	tmp0:	temporary register, clobbered
- * 	tmp1:	other temporary register, clobbered
+ * 	phys:	physical address, preserved
+ * 	ttbr:	returns the TTBR value
  */
-	.macro	pre_ttbr0_update_workaround, val, tmp0, tmp1
-#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
-alternative_if ARM64_WORKAROUND_QCOM_FALKOR_E1003
-	mrs	\tmp0, ttbr0_el1
-	mov	\tmp1, #FALKOR_RESERVED_ASID
-	bfi	\tmp0, \tmp1, #48, #16		// reserved ASID + old BADDR
-	msr	ttbr0_el1, \tmp0
-	isb
-	bfi	\tmp0, \val, #0, #48		// reserved ASID + new BADDR
-	msr	ttbr0_el1, \tmp0
-	isb
-alternative_else_nop_endif
+	.macro	phys_to_ttbr, phys, ttbr
+#ifdef CONFIG_ARM64_PA_BITS_52
+	orr	\ttbr, \phys, \phys, lsr #46
+	and	\ttbr, \ttbr, #TTBR_BADDR_MASK_52
+#else
+	mov	\ttbr, \phys
 #endif
 	.endm
 
-/*
- * Errata workaround post TTBR0_EL1 update.
+/**
+ * Errata workaround prior to disable MMU. Insert an ISB immediately prior
+ * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0.
  */
-	.macro	post_ttbr0_update_workaround
-#ifdef CONFIG_CAVIUM_ERRATUM_27456
-alternative_if ARM64_WORKAROUND_CAVIUM_27456
-	ic	iallu
-	dsb	nsh
+	.macro pre_disable_mmu_workaround
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_E1041
 	isb
-alternative_else_nop_endif
 #endif
 	.endm
 
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 76d1cc85d5b1..955130762a3c 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -38,7 +38,7 @@
  *
  *	See Documentation/cachetlb.txt for more information. Please note that
  *	the implementation assumes non-aliasing VIPT D-cache and (aliasing)
- *	VIPT or ASID-tagged VIVT I-cache.
+ *	VIPT I-cache.
  *
  *	flush_cache_mm(mm)
  *
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index a3c7f271ad4c..c00c62e1a4a3 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -150,70 +150,6 @@ typedef u32		compat_old_sigset_t;
 
 typedef u32		compat_sigset_word;
 
-typedef union compat_sigval {
-	compat_int_t	sival_int;
-	compat_uptr_t	sival_ptr;
-} compat_sigval_t;
-
-typedef struct compat_siginfo {
-	int si_signo;
-	int si_errno;
-	int si_code;
-
-	union {
-		int _pad[128/sizeof(int) - 3];
-
-		/* kill() */
-		struct {
-			compat_pid_t _pid;	/* sender's pid */
-			__compat_uid32_t _uid;	/* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			compat_timer_t _tid;	/* timer id */
-			int _overrun;		/* overrun count */
-			compat_sigval_t _sigval;	/* same as below */
-			int _sys_private;       /* not to be passed to user */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			compat_pid_t _pid;	/* sender's pid */
-			__compat_uid32_t _uid;	/* sender's uid */
-			compat_sigval_t _sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			compat_pid_t _pid;	/* which child */
-			__compat_uid32_t _uid;	/* sender's uid */
-			int _status;		/* exit code */
-			compat_clock_t _utime;
-			compat_clock_t _stime;
-		} _sigchld;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
-		struct {
-			compat_uptr_t _addr; /* faulting insn/memory ref. */
-			short _addr_lsb; /* LSB of the reported address */
-		} _sigfault;
-
-		/* SIGPOLL */
-		struct {
-			compat_long_t _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
-			int _fd;
-		} _sigpoll;
-
-		/* SIGSYS */
-		struct {
-			compat_uptr_t _call_addr; /* calling user insn */
-			int _syscall;	/* triggering system call number */
-			compat_uint_t _arch;	/* AUDIT_ARCH_* of syscall */
-		} _sigsys;
-	} _sifields;
-} compat_siginfo_t;
-
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
 /*
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 2ff7c5e8efab..bb263820de13 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -41,7 +41,11 @@
 #define ARM64_WORKAROUND_CAVIUM_30115		20
 #define ARM64_HAS_DCPOP				21
 #define ARM64_SVE				22
+#define ARM64_UNMAP_KERNEL_AT_EL0		23
+#define ARM64_HARDEN_BRANCH_PREDICTOR		24
+#define ARM64_HARDEN_BP_POST_GUEST_EXIT		25
+#define ARM64_HAS_RAS_EXTN			26
 
-#define ARM64_NCAPS				23
+#define ARM64_NCAPS				27
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index ac67cfc2585a..060e3a4008ab 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -60,6 +60,9 @@ enum ftr_type {
 #define FTR_VISIBLE	true	/* Feature visible to the user space */
 #define FTR_HIDDEN	false	/* Feature is hidden from the user */
 
+#define FTR_VISIBLE_IF_IS_ENABLED(config)		\
+	(IS_ENABLED(config) ? FTR_VISIBLE : FTR_HIDDEN)
+
 struct arm64_ftr_bits {
 	bool		sign;	/* Value is signed ? */
 	bool		visible;
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 235e77d98261..be7bd19c87ec 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -79,26 +79,37 @@
 #define ARM_CPU_PART_AEM_V8		0xD0F
 #define ARM_CPU_PART_FOUNDATION		0xD00
 #define ARM_CPU_PART_CORTEX_A57		0xD07
+#define ARM_CPU_PART_CORTEX_A72		0xD08
 #define ARM_CPU_PART_CORTEX_A53		0xD03
 #define ARM_CPU_PART_CORTEX_A73		0xD09
+#define ARM_CPU_PART_CORTEX_A75		0xD0A
 
 #define APM_CPU_PART_POTENZA		0x000
 
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
 #define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2
 #define CAVIUM_CPU_PART_THUNDERX_83XX	0x0A3
+#define CAVIUM_CPU_PART_THUNDERX2	0x0AF
 
 #define BRCM_CPU_PART_VULCAN		0x516
 
 #define QCOM_CPU_PART_FALKOR_V1		0x800
+#define QCOM_CPU_PART_FALKOR		0xC00
+#define QCOM_CPU_PART_KRYO		0x200
 
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
+#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
 #define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73)
+#define MIDR_CORTEX_A75 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A75)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
+#define MIDR_CAVIUM_THUNDERX2 MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX2)
+#define MIDR_BRCM_VULCAN MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_VULCAN)
 #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
+#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
+#define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 0df756b24863..b7847eb8a7bb 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -50,40 +50,5 @@ static inline bool is_device_dma_coherent(struct device *dev)
 	return dev->archdata.dma_coherent;
 }
 
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	dma_addr_t dev_addr = (dma_addr_t)paddr;
-
-	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
-{
-	phys_addr_t paddr = (phys_addr_t)dev_addr;
-
-	return paddr + ((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
-}
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-static inline void dma_mark_clean(void *addr, size_t size)
-{
-}
-
-/* Override for dma_max_pfn() */
-static inline unsigned long dma_max_pfn(struct device *dev)
-{
-	dma_addr_t dma_max = (dma_addr_t)*dev->dma_mask;
-
-	return (ulong)dma_to_phys(dev, dma_max) >> PAGE_SHIFT;
-}
-#define dma_max_pfn(dev) dma_max_pfn(dev)
-
 #endif	/* __KERNEL__ */
 #endif	/* __ASM_DMA_MAPPING_H */
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 650344d01124..8389050328bb 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -121,22 +121,22 @@ static inline void efi_set_pgd(struct mm_struct *mm)
 		if (mm != current->active_mm) {
 			/*
 			 * Update the current thread's saved ttbr0 since it is
-			 * restored as part of a return from exception. Set
-			 * the hardware TTBR0_EL1 using cpu_switch_mm()
-			 * directly to enable potential errata workarounds.
+			 * restored as part of a return from exception. Enable
+			 * access to the valid TTBR0_EL1 and invoke the errata
+			 * workaround directly since there is no return from
+			 * exception when invoking the EFI run-time services.
 			 */
 			update_saved_ttbr0(current, mm);
-			cpu_switch_mm(mm->pgd, mm);
+			uaccess_ttbr0_enable();
+			post_ttbr_update_workaround();
 		} else {
 			/*
 			 * Defer the switch to the current thread's TTBR0_EL1
 			 * until uaccess_enable(). Restore the current
 			 * thread's saved ttbr0 corresponding to its active_mm
-			 * (if different from init_mm).
 			 */
-			cpu_set_reserved_ttbr0();
-			if (current->active_mm != &init_mm)
-				update_saved_ttbr0(current, current->active_mm);
+			uaccess_ttbr0_disable();
+			update_saved_ttbr0(current, current->active_mm);
 		}
 	}
 }
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 014d7d8edcf9..803443d74926 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -86,6 +86,18 @@
 #define ESR_ELx_WNR_SHIFT	(6)
 #define ESR_ELx_WNR		(UL(1) << ESR_ELx_WNR_SHIFT)
 
+/* Asynchronous Error Type */
+#define ESR_ELx_IDS_SHIFT	(24)
+#define ESR_ELx_IDS		(UL(1) << ESR_ELx_IDS_SHIFT)
+#define ESR_ELx_AET_SHIFT	(10)
+#define ESR_ELx_AET		(UL(0x7) << ESR_ELx_AET_SHIFT)
+
+#define ESR_ELx_AET_UC		(UL(0) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_UEU		(UL(1) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_UEO		(UL(2) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_UER		(UL(3) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_CE		(UL(6) << ESR_ELx_AET_SHIFT)
+
 /* Shared ISS field definitions for Data/Instruction aborts */
 #define ESR_ELx_SET_SHIFT	(11)
 #define ESR_ELx_SET_MASK	(UL(3) << ESR_ELx_SET_SHIFT)
@@ -100,6 +112,7 @@
 #define ESR_ELx_FSC		(0x3F)
 #define ESR_ELx_FSC_TYPE	(0x3C)
 #define ESR_ELx_FSC_EXTABT	(0x10)
+#define ESR_ELx_FSC_SERROR	(0x11)
 #define ESR_ELx_FSC_ACCESS	(0x08)
 #define ESR_ELx_FSC_FAULT	(0x04)
 #define ESR_ELx_FSC_PERM	(0x0C)
@@ -127,6 +140,13 @@
 #define ESR_ELx_WFx_ISS_WFE	(UL(1) << 0)
 #define ESR_ELx_xVC_IMM_MASK	((1UL << 16) - 1)
 
+#define DISR_EL1_IDS		(UL(1) << 24)
+/*
+ * DISR_EL1 and ESR_ELx share the bottom 13 bits, but the RES0 bits may mean
+ * different things in the future...
+ */
+#define DISR_EL1_ESR_MASK	(ESR_ELx_AET | ESR_ELx_EA | ESR_ELx_FSC)
+
 /* ESR value templates for specific events */
 
 /* BRK instruction trap from AArch64 state */
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 0c2eec490abf..bc30429d8e91 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -18,6 +18,8 @@
 #ifndef __ASM_EXCEPTION_H
 #define __ASM_EXCEPTION_H
 
+#include <asm/esr.h>
+
 #include <linux/interrupt.h>
 
 #define __exception	__attribute__((section(".exception.text")))
@@ -27,4 +29,16 @@
 #define __exception_irq_entry	__exception
 #endif
 
+static inline u32 disr_to_esr(u64 disr)
+{
+	unsigned int esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT;
+
+	if ((disr & DISR_EL1_IDS) == 0)
+		esr |= (disr & DISR_EL1_ESR_MASK);
+	else
+		esr |= (disr & ESR_ELx_ISS_MASK);
+
+	return esr;
+}
+
 #endif	/* __ASM_EXCEPTION_H */
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 4052ec39e8db..ec1e6d6fa14c 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -58,6 +58,11 @@ enum fixed_addresses {
 	FIX_APEI_GHES_NMI,
 #endif /* CONFIG_ACPI_APEI_GHES */
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	FIX_ENTRY_TRAMP_DATA,
+	FIX_ENTRY_TRAMP_TEXT,
+#define TRAMP_VALIAS		(__fix_to_virt(FIX_ENTRY_TRAMP_TEXT))
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 	__end_of_permanent_fixed_addresses,
 
 	/*
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 74f34392a531..8857a0f0d0f7 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -71,7 +71,7 @@ extern void fpsimd_flush_thread(void);
 extern void fpsimd_signal_preserve_current_state(void);
 extern void fpsimd_preserve_current_state(void);
 extern void fpsimd_restore_current_state(void);
-extern void fpsimd_update_current_state(struct fpsimd_state *state);
+extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void sve_flush_cpu_state(void);
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 7803343e5881..82386e860dd2 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -52,7 +52,52 @@
 #define IDMAP_PGTABLE_LEVELS	(ARM64_HW_PGTABLE_LEVELS(PHYS_MASK_SHIFT))
 #endif
 
-#define SWAPPER_DIR_SIZE	(SWAPPER_PGTABLE_LEVELS * PAGE_SIZE)
+
+/*
+ * If KASLR is enabled, then an offset K is added to the kernel address
+ * space. The bottom 21 bits of this offset are zero to guarantee 2MB
+ * alignment for PA and VA.
+ *
+ * For each pagetable level of the swapper, we know that the shift will
+ * be larger than 21 (for the 4KB granule case we use section maps thus
+ * the smallest shift is actually 30) thus there is the possibility that
+ * KASLR can increase the number of pagetable entries by 1, so we make
+ * room for this extra entry.
+ *
+ * Note KASLR cannot increase the number of required entries for a level
+ * by more than one because it increments both the virtual start and end
+ * addresses equally (the extra entry comes from the case where the end
+ * address is just pushed over a boundary and the start address isn't).
+ */
+
+#ifdef CONFIG_RANDOMIZE_BASE
+#define EARLY_KASLR	(1)
+#else
+#define EARLY_KASLR	(0)
+#endif
+
+#define EARLY_ENTRIES(vstart, vend, shift) (((vend) >> (shift)) \
+					- ((vstart) >> (shift)) + 1 + EARLY_KASLR)
+
+#define EARLY_PGDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT))
+
+#if SWAPPER_PGTABLE_LEVELS > 3
+#define EARLY_PUDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, PUD_SHIFT))
+#else
+#define EARLY_PUDS(vstart, vend) (0)
+#endif
+
+#if SWAPPER_PGTABLE_LEVELS > 2
+#define EARLY_PMDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, SWAPPER_TABLE_SHIFT))
+#else
+#define EARLY_PMDS(vstart, vend) (0)
+#endif
+
+#define EARLY_PAGES(vstart, vend) ( 1 			/* PGDIR page */				\
+			+ EARLY_PGDS((vstart), (vend)) 	/* each PGDIR needs a next level page table */	\
+			+ EARLY_PUDS((vstart), (vend))	/* each PUD needs a next level page table */	\
+			+ EARLY_PMDS((vstart), (vend)))	/* each PMD needs a next level page table */
+#define SWAPPER_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR + TEXT_OFFSET, _end))
 #define IDMAP_DIR_SIZE		(IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
 
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
@@ -78,8 +123,16 @@
 /*
  * Initial memory map attributes.
  */
-#define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#define _SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define _SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define SWAPPER_PTE_FLAGS	(_SWAPPER_PTE_FLAGS | PTE_NG)
+#define SWAPPER_PMD_FLAGS	(_SWAPPER_PMD_FLAGS | PMD_SECT_NG)
+#else
+#define SWAPPER_PTE_FLAGS	_SWAPPER_PTE_FLAGS
+#define SWAPPER_PMD_FLAGS	_SWAPPER_PMD_FLAGS
+#endif
 
 #if ARM64_SWAPPER_USES_SECTION_MAPS
 #define SWAPPER_MM_MMUFLAGS	(PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 7f069ff37f06..b0c84171e6a3 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -23,6 +23,8 @@
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
+#define HCR_TEA		(UL(1) << 37)
+#define HCR_TERR	(UL(1) << 36)
 #define HCR_E2H		(UL(1) << 34)
 #define HCR_ID		(UL(1) << 33)
 #define HCR_CD		(UL(1) << 32)
@@ -170,8 +172,7 @@
 #define VTCR_EL2_FLAGS			(VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS)
 #define VTTBR_X				(VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA)
 
-#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_X)
 #define VTTBR_VMID_SHIFT  (UL(48))
 #define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index ab4d0a926043..24961b732e65 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -68,6 +68,8 @@ extern u32 __kvm_get_mdcr_el2(void);
 
 extern u32 __init_stage2_translation(void);
 
+extern void __qcom_hyp_sanitize_btac_predictors(void);
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 5f28dfa14cee..413dc82b1e89 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -50,6 +50,13 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
 	if (is_kernel_in_hyp_mode())
 		vcpu->arch.hcr_el2 |= HCR_E2H;
+	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) {
+		/* route synchronous external abort exceptions to EL2 */
+		vcpu->arch.hcr_el2 |= HCR_TEA;
+		/* trap error record accesses */
+		vcpu->arch.hcr_el2 |= HCR_TERR;
+	}
+
 	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
 		vcpu->arch.hcr_el2 &= ~HCR_RW;
 }
@@ -64,6 +71,11 @@ static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr)
 	vcpu->arch.hcr_el2 = hcr;
 }
 
+static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr)
+{
+	vcpu->arch.vsesr_el2 = vsesr;
+}
+
 static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
 {
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
@@ -171,6 +183,11 @@ static inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu)
 	return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8;
 }
 
+static inline u64 kvm_vcpu_get_disr(const struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.disr_el1;
+}
+
 static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 674912d7a571..4485ae8e98de 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -25,6 +25,7 @@
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <asm/cpufeature.h>
+#include <asm/daifflags.h>
 #include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
@@ -89,6 +90,7 @@ struct kvm_vcpu_fault_info {
 	u32 esr_el2;		/* Hyp Syndrom Register */
 	u64 far_el2;		/* Hyp Fault Address Register */
 	u64 hpfar_el2;		/* Hyp IPA Fault Address Register */
+	u64 disr_el1;		/* Deferred [SError] Status Register */
 };
 
 /*
@@ -120,6 +122,7 @@ enum vcpu_sysreg {
 	PAR_EL1,	/* Physical Address Register */
 	MDSCR_EL1,	/* Monitor Debug System Control Register */
 	MDCCINT_EL1,	/* Monitor Debug Comms Channel Interrupt Enable Reg */
+	DISR_EL1,	/* Deferred Interrupt Status Register */
 
 	/* Performance Monitors Registers */
 	PMCR_EL0,	/* Control Register */
@@ -192,6 +195,8 @@ struct kvm_cpu_context {
 		u64 sys_regs[NR_SYS_REGS];
 		u32 copro[NR_COPRO_REGS];
 	};
+
+	struct kvm_vcpu *__hyp_running_vcpu;
 };
 
 typedef struct kvm_cpu_context kvm_cpu_context_t;
@@ -277,6 +282,9 @@ struct kvm_vcpu_arch {
 
 	/* Detect first run of a vcpu */
 	bool has_run_once;
+
+	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
+	u64 vsesr_el2;
 };
 
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
@@ -340,6 +348,8 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		int exception_index);
+void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		       int exception_index);
 
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
@@ -370,6 +380,7 @@ void kvm_arm_init_debug(void);
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
+bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
@@ -395,4 +406,13 @@ static inline void kvm_fpsimd_flush_cpu_state(void)
 		sve_flush_cpu_state();
 }
 
+static inline void kvm_arm_vhe_guest_enter(void)
+{
+	local_daif_mask();
+}
+
+static inline void kvm_arm_vhe_guest_exit(void)
+{
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+}
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 672c8684d5c2..72e279dbae5f 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -273,15 +273,26 @@ void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
 
 static inline bool __kvm_cpu_uses_extended_idmap(void)
 {
-	return __cpu_uses_extended_idmap();
+	return __cpu_uses_extended_idmap_level();
 }
 
+static inline unsigned long __kvm_idmap_ptrs_per_pgd(void)
+{
+	return idmap_ptrs_per_pgd;
+}
+
+/*
+ * Can't use pgd_populate here, because the extended idmap adds an extra level
+ * above CONFIG_PGTABLE_LEVELS (which is 2 or 3 if we're using the extended
+ * idmap), and pgd_populate is only available if CONFIG_PGTABLE_LEVELS = 4.
+ */
 static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
 				       pgd_t *hyp_pgd,
 				       pgd_t *merged_hyp_pgd,
 				       unsigned long hyp_idmap_start)
 {
 	int idmap_idx;
+	u64 pgd_addr;
 
 	/*
 	 * Use the first entry to access the HYP mappings. It is
@@ -289,7 +300,8 @@ static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
 	 * extended idmap.
 	 */
 	VM_BUG_ON(pgd_val(merged_hyp_pgd[0]));
-	merged_hyp_pgd[0] = __pgd(__pa(hyp_pgd) | PMD_TYPE_TABLE);
+	pgd_addr = __phys_to_pgd_val(__pa(hyp_pgd));
+	merged_hyp_pgd[0] = __pgd(pgd_addr | PMD_TYPE_TABLE);
 
 	/*
 	 * Create another extended level entry that points to the boot HYP map,
@@ -299,7 +311,8 @@ static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
 	 */
 	idmap_idx = hyp_idmap_start >> VA_BITS;
 	VM_BUG_ON(pgd_val(merged_hyp_pgd[idmap_idx]));
-	merged_hyp_pgd[idmap_idx] = __pgd(__pa(boot_hyp_pgd) | PMD_TYPE_TABLE);
+	pgd_addr = __phys_to_pgd_val(__pa(boot_hyp_pgd));
+	merged_hyp_pgd[idmap_idx] = __pgd(pgd_addr | PMD_TYPE_TABLE);
 }
 
 static inline unsigned int kvm_get_vmid_bits(void)
@@ -309,5 +322,45 @@ static inline unsigned int kvm_get_vmid_bits(void)
 	return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
 }
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+#include <asm/mmu.h>
+
+static inline void *kvm_get_hyp_vector(void)
+{
+	struct bp_hardening_data *data = arm64_get_bp_hardening_data();
+	void *vect = kvm_ksym_ref(__kvm_hyp_vector);
+
+	if (data->fn) {
+		vect = __bp_harden_hyp_vecs_start +
+		       data->hyp_vectors_slot * SZ_2K;
+
+		if (!has_vhe())
+			vect = lm_alias(vect);
+	}
+
+	return vect;
+}
+
+static inline int kvm_map_vectors(void)
+{
+	return create_hyp_mappings(kvm_ksym_ref(__bp_harden_hyp_vecs_start),
+				   kvm_ksym_ref(__bp_harden_hyp_vecs_end),
+				   PAGE_HYP_EXEC);
+}
+
+#else
+static inline void *kvm_get_hyp_vector(void)
+{
+	return kvm_ksym_ref(__kvm_hyp_vector);
+}
+
+static inline int kvm_map_vectors(void)
+{
+	return 0;
+}
+#endif
+
+#define kvm_phys_to_vttbr(addr)		phys_to_ttbr(addr)
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 0d34bf0a89c7..a050d4f3615d 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -17,6 +17,11 @@
 #define __ASM_MMU_H
 
 #define MMCF_AARCH32	0x1	/* mm context flag for AArch32 executables */
+#define USER_ASID_BIT	48
+#define USER_ASID_FLAG	(UL(1) << USER_ASID_BIT)
+#define TTBR_ASID_MASK	(UL(0xffff) << 48)
+
+#ifndef __ASSEMBLY__
 
 typedef struct {
 	atomic64_t	id;
@@ -31,6 +36,49 @@ typedef struct {
  */
 #define ASID(mm)	((mm)->context.id.counter & 0xffff)
 
+static inline bool arm64_kernel_unmapped_at_el0(void)
+{
+	return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) &&
+	       cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0);
+}
+
+typedef void (*bp_hardening_cb_t)(void);
+
+struct bp_hardening_data {
+	int			hyp_vectors_slot;
+	bp_hardening_cb_t	fn;
+};
+
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+extern char __bp_harden_hyp_vecs_start[], __bp_harden_hyp_vecs_end[];
+
+DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
+
+static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
+{
+	return this_cpu_ptr(&bp_hardening_data);
+}
+
+static inline void arm64_apply_bp_hardening(void)
+{
+	struct bp_hardening_data *d;
+
+	if (!cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR))
+		return;
+
+	d = arm64_get_bp_hardening_data();
+	if (d->fn)
+		d->fn();
+}
+#else
+static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
+{
+	return NULL;
+}
+
+static inline void arm64_apply_bp_hardening(void)	{ }
+#endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
+
 extern void paging_init(void);
 extern void bootmem_init(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
@@ -41,4 +89,5 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
 extern void mark_linear_text_alias_ro(void);
 
+#endif	/* !__ASSEMBLY__ */
 #endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 3257895a9b5e..8d3331985d2e 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -19,8 +19,6 @@
 #ifndef __ASM_MMU_CONTEXT_H
 #define __ASM_MMU_CONTEXT_H
 
-#define FALKOR_RESERVED_ASID	1
-
 #ifndef __ASSEMBLY__
 
 #include <linux/compiler.h>
@@ -51,23 +49,39 @@ static inline void contextidr_thread_switch(struct task_struct *next)
  */
 static inline void cpu_set_reserved_ttbr0(void)
 {
-	unsigned long ttbr = __pa_symbol(empty_zero_page);
+	unsigned long ttbr = phys_to_ttbr(__pa_symbol(empty_zero_page));
 
 	write_sysreg(ttbr, ttbr0_el1);
 	isb();
 }
 
+static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
+{
+	BUG_ON(pgd == swapper_pg_dir);
+	cpu_set_reserved_ttbr0();
+	cpu_do_switch_mm(virt_to_phys(pgd),mm);
+}
+
 /*
  * TCR.T0SZ value to use when the ID map is active. Usually equals
  * TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in
  * physical memory, in which case it will be smaller.
  */
 extern u64 idmap_t0sz;
+extern u64 idmap_ptrs_per_pgd;
 
 static inline bool __cpu_uses_extended_idmap(void)
 {
-	return (!IS_ENABLED(CONFIG_ARM64_VA_BITS_48) &&
-		unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS)));
+	return unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS));
+}
+
+/*
+ * True if the extended ID map requires an extra level of translation table
+ * to be configured.
+ */
+static inline bool __cpu_uses_extended_idmap_level(void)
+{
+	return ARM64_HW_PGTABLE_LEVELS(64 - idmap_t0sz) > CONFIG_PGTABLE_LEVELS;
 }
 
 /*
@@ -156,29 +170,21 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
 
 #define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
-/*
- * This is called when "tsk" is about to enter lazy TLB mode.
- *
- * mm:  describes the currently active mm context
- * tsk: task which is entering lazy tlb
- * cpu: cpu number which is entering lazy tlb
- *
- * tsk->mm will be NULL
- */
-static inline void
-enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
-
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 static inline void update_saved_ttbr0(struct task_struct *tsk,
 				      struct mm_struct *mm)
 {
-	if (system_uses_ttbr0_pan()) {
-		BUG_ON(mm->pgd == swapper_pg_dir);
-		task_thread_info(tsk)->ttbr0 =
-			virt_to_phys(mm->pgd) | ASID(mm) << 48;
-	}
+	u64 ttbr;
+
+	if (!system_uses_ttbr0_pan())
+		return;
+
+	if (mm == &init_mm)
+		ttbr = __pa_symbol(empty_zero_page);
+	else
+		ttbr = virt_to_phys(mm->pgd) | ASID(mm) << 48;
+
+	WRITE_ONCE(task_thread_info(tsk)->ttbr0, ttbr);
 }
 #else
 static inline void update_saved_ttbr0(struct task_struct *tsk,
@@ -187,6 +193,16 @@ static inline void update_saved_ttbr0(struct task_struct *tsk,
 }
 #endif
 
+static inline void
+enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+	/*
+	 * We don't actually care about the ttbr0 mapping, so point it at the
+	 * zero page.
+	 */
+	update_saved_ttbr0(tsk, &init_mm);
+}
+
 static inline void __switch_mm(struct mm_struct *next)
 {
 	unsigned int cpu = smp_processor_id();
@@ -214,17 +230,16 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	 * Update the saved TTBR0_EL1 of the scheduled-in task as the previous
 	 * value may have not been initialised yet (activate_mm caller) or the
 	 * ASID has changed since the last run (following the context switch
-	 * of another thread of the same process). Avoid setting the reserved
-	 * TTBR0_EL1 to swapper_pg_dir (init_mm; e.g. via idle_task_exit).
+	 * of another thread of the same process).
 	 */
-	if (next != &init_mm)
-		update_saved_ttbr0(tsk, next);
+	update_saved_ttbr0(tsk, next);
 }
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
 #define activate_mm(prev,next)	switch_mm(prev, next, current)
 
 void verify_cpu_asid_bits(void);
+void post_ttbr_update_workaround(void);
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index 19bd97671bb8..4f766178fa6f 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -32,7 +32,7 @@ struct mod_arch_specific {
 	struct mod_plt_sec	init;
 
 	/* for CONFIG_DYNAMIC_FTRACE */
-	void			*ftrace_trampoline;
+	struct plt_entry 	*ftrace_trampoline;
 };
 #endif
 
@@ -45,4 +45,48 @@ extern u64 module_alloc_base;
 #define module_alloc_base	((u64)_etext - MODULES_VSIZE)
 #endif
 
+struct plt_entry {
+	/*
+	 * A program that conforms to the AArch64 Procedure Call Standard
+	 * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
+	 * IP1 (x17) may be inserted at any branch instruction that is
+	 * exposed to a relocation that supports long branches. Since that
+	 * is exactly what we are dealing with here, we are free to use x16
+	 * as a scratch register in the PLT veneers.
+	 */
+	__le32	mov0;	/* movn	x16, #0x....			*/
+	__le32	mov1;	/* movk	x16, #0x...., lsl #16		*/
+	__le32	mov2;	/* movk	x16, #0x...., lsl #32		*/
+	__le32	br;	/* br	x16				*/
+};
+
+static inline struct plt_entry get_plt_entry(u64 val)
+{
+	/*
+	 * MOVK/MOVN/MOVZ opcode:
+	 * +--------+------------+--------+-----------+-------------+---------+
+	 * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
+	 * +--------+------------+--------+-----------+-------------+---------+
+	 *
+	 * Rd     := 0x10 (x16)
+	 * hw     := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32)
+	 * opc    := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ)
+	 * sf     := 1 (64-bit variant)
+	 */
+	return (struct plt_entry){
+		cpu_to_le32(0x92800010 | (((~val      ) & 0xffff)) << 5),
+		cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
+		cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
+		cpu_to_le32(0xd61f0200)
+	};
+}
+
+static inline bool plt_entries_equal(const struct plt_entry *a,
+				     const struct plt_entry *b)
+{
+	return a->mov0 == b->mov0 &&
+	       a->mov1 == b->mov1 &&
+	       a->mov2 == b->mov2;
+}
+
 #endif /* __ASM_MODULE_H */
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 3bd498e4de4c..43393208229e 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -16,11 +16,15 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
+#include <asm/alternative.h>
 #include <asm/stack_pointer.h>
 
 static inline void set_my_cpu_offset(unsigned long off)
 {
-	asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
+	asm volatile(ALTERNATIVE("msr tpidr_el1, %0",
+				 "msr tpidr_el2, %0",
+				 ARM64_HAS_VIRT_HOST_EXTN)
+			:: "r" (off) : "memory");
 }
 
 static inline unsigned long __my_cpu_offset(void)
@@ -31,7 +35,10 @@ static inline unsigned long __my_cpu_offset(void)
 	 * We want to allow caching the value, so avoid using volatile and
 	 * instead use a fake stack read to hazard against barrier().
 	 */
-	asm("mrs %0, tpidr_el1" : "=r" (off) :
+	asm(ALTERNATIVE("mrs %0, tpidr_el1",
+			"mrs %0, tpidr_el2",
+			ARM64_HAS_VIRT_HOST_EXTN)
+		: "=r" (off) :
 		"Q" (*(const unsigned long *)current_stack_pointer));
 
 	return off;
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 8d5cbec17d80..f9ccc36d3dc3 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -18,6 +18,7 @@
 #define __ASM_PERF_EVENT_H
 
 #include <asm/stack_pointer.h>
+#include <asm/ptrace.h>
 
 #define	ARMV8_PMU_MAX_COUNTERS	32
 #define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
@@ -79,6 +80,7 @@ struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)	perf_misc_flags(regs)
+#define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
 #endif
 
 #define perf_arch_fetch_caller_regs(regs, __ip) { \
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 5ca6a573a701..e9d9f1b006ef 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -44,7 +44,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 
 static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot)
 {
-	set_pud(pud, __pud(pmd | prot));
+	set_pud(pud, __pud(__phys_to_pud_val(pmd) | prot));
 }
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
@@ -73,7 +73,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 
 static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot)
 {
-	set_pgd(pgdp, __pgd(pud | prot));
+	set_pgd(pgdp, __pgd(__phys_to_pgd_val(pud) | prot));
 }
 
 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
@@ -129,7 +129,7 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
 				  pmdval_t prot)
 {
-	set_pmd(pmdp, __pmd(pte | prot));
+	set_pmd(pmdp, __pmd(__phys_to_pmd_val(pte) | prot));
 }
 
 /*
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index eb0c2bd90de9..f42836da8723 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PGTABLE_HWDEF_H
 #define __ASM_PGTABLE_HWDEF_H
 
+#include <asm/memory.h>
+
 /*
  * Number of page-table levels required to address 'va_bits' wide
  * address, without section mapping. We resolve the top (va_bits - PAGE_SHIFT)
@@ -116,9 +118,9 @@
  * Level 1 descriptor (PUD).
  */
 #define PUD_TYPE_TABLE		(_AT(pudval_t, 3) << 0)
-#define PUD_TABLE_BIT		(_AT(pgdval_t, 1) << 1)
-#define PUD_TYPE_MASK		(_AT(pgdval_t, 3) << 0)
-#define PUD_TYPE_SECT		(_AT(pgdval_t, 1) << 0)
+#define PUD_TABLE_BIT		(_AT(pudval_t, 1) << 1)
+#define PUD_TYPE_MASK		(_AT(pudval_t, 3) << 0)
+#define PUD_TYPE_SECT		(_AT(pudval_t, 1) << 0)
 
 /*
  * Level 2 descriptor (PMD).
@@ -166,6 +168,14 @@
 #define PTE_UXN			(_AT(pteval_t, 1) << 54)	/* User XN */
 #define PTE_HYP_XN		(_AT(pteval_t, 1) << 54)	/* HYP XN */
 
+#define PTE_ADDR_LOW		(((_AT(pteval_t, 1) << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT)
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define PTE_ADDR_HIGH		(_AT(pteval_t, 0xf) << 12)
+#define PTE_ADDR_MASK		(PTE_ADDR_LOW | PTE_ADDR_HIGH)
+#else
+#define PTE_ADDR_MASK		PTE_ADDR_LOW
+#endif
+
 /*
  * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
  */
@@ -196,7 +206,7 @@
 /*
  * Highest possible physical address supported.
  */
-#define PHYS_MASK_SHIFT		(48)
+#define PHYS_MASK_SHIFT		(CONFIG_ARM64_PA_BITS)
 #define PHYS_MASK		((UL(1) << PHYS_MASK_SHIFT) - 1)
 
 /*
@@ -272,9 +282,23 @@
 #define TCR_TG1_4K		(UL(2) << TCR_TG1_SHIFT)
 #define TCR_TG1_64K		(UL(3) << TCR_TG1_SHIFT)
 
+#define TCR_IPS_SHIFT		32
+#define TCR_IPS_MASK		(UL(7) << TCR_IPS_SHIFT)
+#define TCR_A1			(UL(1) << 22)
 #define TCR_ASID16		(UL(1) << 36)
 #define TCR_TBI0		(UL(1) << 37)
 #define TCR_HA			(UL(1) << 39)
 #define TCR_HD			(UL(1) << 40)
 
+/*
+ * TTBR.
+ */
+#ifdef CONFIG_ARM64_PA_BITS_52
+/*
+ * This should be GENMASK_ULL(47, 2).
+ * TTBR_ELx[1] is RES0 in this configuration.
+ */
+#define TTBR_BADDR_MASK_52	(((UL(1) << 46) - 1) << 2)
+#endif
+
 #endif
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 0a5635fb0ef9..22a926825e3f 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -34,8 +34,16 @@
 
 #include <asm/pgtable-types.h>
 
-#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#define _PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define _PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define PROT_DEFAULT		(_PROT_DEFAULT | PTE_NG)
+#define PROT_SECT_DEFAULT	(_PROT_SECT_DEFAULT | PMD_SECT_NG)
+#else
+#define PROT_DEFAULT		_PROT_DEFAULT
+#define PROT_SECT_DEFAULT	_PROT_SECT_DEFAULT
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 #define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
 #define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
@@ -48,6 +56,7 @@
 #define PROT_SECT_NORMAL_EXEC	(PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
 
 #define _PAGE_DEFAULT		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
+#define _HYP_PAGE_DEFAULT	(_PAGE_DEFAULT & ~PTE_NG)
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
@@ -55,15 +64,15 @@
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 
-#define PAGE_HYP		__pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
-#define PAGE_HYP_EXEC		__pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
-#define PAGE_HYP_RO		__pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
+#define PAGE_HYP		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
+#define PAGE_HYP_EXEC		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
+#define PAGE_HYP_RO		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
 
 #define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
 #define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
 
-#define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_PXN | PTE_UXN)
+#define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
 #define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
 #define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index c9530b5b5ca8..094374c82db0 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -42,6 +42,8 @@
 #include <asm/cmpxchg.h>
 #include <asm/fixmap.h>
 #include <linux/mmdebug.h>
+#include <linux/mm_types.h>
+#include <linux/sched.h>
 
 extern void __pte_error(const char *file, int line, unsigned long val);
 extern void __pmd_error(const char *file, int line, unsigned long val);
@@ -57,9 +59,22 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
 #define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
 
-#define pte_pfn(pte)		((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT)
+/*
+ * Macros to convert between a physical address and its placement in a
+ * page table entry, taking care of 52-bit addresses.
+ */
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define __pte_to_phys(pte)	\
+	((pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << 36))
+#define __phys_to_pte_val(phys)	(((phys) | ((phys) >> 36)) & PTE_ADDR_MASK)
+#else
+#define __pte_to_phys(pte)	(pte_val(pte) & PTE_ADDR_MASK)
+#define __phys_to_pte_val(phys)	(phys)
+#endif
 
-#define pfn_pte(pfn,prot)	(__pte(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pte_pfn(pte)		(__pte_to_phys(pte) >> PAGE_SHIFT)
+#define pfn_pte(pfn,prot)	\
+	__pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
 #define pte_none(pte)		(!pte_val(pte))
 #define pte_clear(mm,addr,ptep)	set_pte(ptep, __pte(0))
@@ -149,12 +164,20 @@ static inline pte_t pte_mkwrite(pte_t pte)
 
 static inline pte_t pte_mkclean(pte_t pte)
 {
-	return clear_pte_bit(pte, __pgprot(PTE_DIRTY));
+	pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY));
+	pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
+
+	return pte;
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-	return set_pte_bit(pte, __pgprot(PTE_DIRTY));
+	pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
+
+	if (pte_write(pte))
+		pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+
+	return pte;
 }
 
 static inline pte_t pte_mkold(pte_t pte)
@@ -207,9 +230,6 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 	}
 }
 
-struct mm_struct;
-struct vm_area_struct;
-
 extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
 
 /*
@@ -238,7 +258,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * hardware updates of the pte (ptep_set_access_flags safely changes
 	 * valid ptes without going through an invalid entry).
 	 */
-	if (pte_valid(*ptep) && pte_valid(pte)) {
+	if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(*ptep) && pte_valid(pte) &&
+	   (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) {
 		VM_WARN_ONCE(!pte_young(pte),
 			     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
 			     __func__, pte_val(*ptep), pte_val(pte));
@@ -284,6 +305,11 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
 
 #define __HAVE_ARCH_PTE_SPECIAL
 
+static inline pte_t pgd_pte(pgd_t pgd)
+{
+	return __pte(pgd_val(pgd));
+}
+
 static inline pte_t pud_pte(pud_t pud)
 {
 	return __pte(pud_val(pud));
@@ -345,20 +371,28 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
 
-#define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
 
-#define pmd_pfn(pmd)		(((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
-#define pfn_pmd(pfn,prot)	(__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define __pmd_to_phys(pmd)	__pte_to_phys(pmd_pte(pmd))
+#define __phys_to_pmd_val(phys)	__phys_to_pte_val(phys)
+#define pmd_pfn(pmd)		((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot)	__pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
 #define pud_write(pud)		pte_write(pud_pte(pud))
-#define pud_pfn(pud)		(((pud_val(pud) & PUD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
+
+#define __pud_to_phys(pud)	__pte_to_phys(pud_pte(pud))
+#define __phys_to_pud_val(phys)	__phys_to_pte_val(phys)
+#define pud_pfn(pud)		((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
+#define pfn_pud(pfn,prot)	__pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
 #define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
 
+#define __pgd_to_phys(pgd)	__pte_to_phys(pgd_pte(pgd))
+#define __phys_to_pgd_val(phys)	__phys_to_pte_val(phys)
+
 #define __pgprot_modify(prot,mask,bits) \
 	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
 
@@ -409,7 +443,7 @@ static inline void pmd_clear(pmd_t *pmdp)
 
 static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 {
-	return pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK;
+	return __pmd_to_phys(pmd);
 }
 
 /* Find an entry in the third-level page table. */
@@ -427,7 +461,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 #define pte_set_fixmap_offset(pmd, addr)	pte_set_fixmap(pte_offset_phys(pmd, addr))
 #define pte_clear_fixmap()		clear_fixmap(FIX_PTE)
 
-#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
+#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(__pmd_to_phys(pmd)))
 
 /* use ONLY for statically allocated translation tables */
 #define pte_offset_kimg(dir,addr)	((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr))))
@@ -460,7 +494,7 @@ static inline void pud_clear(pud_t *pudp)
 
 static inline phys_addr_t pud_page_paddr(pud_t pud)
 {
-	return pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK;
+	return __pud_to_phys(pud);
 }
 
 /* Find an entry in the second-level page table. */
@@ -473,7 +507,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud)
 #define pmd_set_fixmap_offset(pud, addr)	pmd_set_fixmap(pmd_offset_phys(pud, addr))
 #define pmd_clear_fixmap()		clear_fixmap(FIX_PMD)
 
-#define pud_page(pud)		pfn_to_page(__phys_to_pfn(pud_val(pud) & PHYS_MASK))
+#define pud_page(pud)		pfn_to_page(__phys_to_pfn(__pud_to_phys(pud)))
 
 /* use ONLY for statically allocated translation tables */
 #define pmd_offset_kimg(dir,addr)	((pmd_t *)__phys_to_kimg(pmd_offset_phys((dir), (addr))))
@@ -512,7 +546,7 @@ static inline void pgd_clear(pgd_t *pgdp)
 
 static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
 {
-	return pgd_val(pgd) & PHYS_MASK & (s32)PAGE_MASK;
+	return __pgd_to_phys(pgd);
 }
 
 /* Find an entry in the frst-level page table. */
@@ -525,7 +559,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
 #define pud_set_fixmap_offset(pgd, addr)	pud_set_fixmap(pud_offset_phys(pgd, addr))
 #define pud_clear_fixmap()		clear_fixmap(FIX_PUD)
 
-#define pgd_page(pgd)		pfn_to_page(__phys_to_pfn(pgd_val(pgd) & PHYS_MASK))
+#define pgd_page(pgd)		pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd)))
 
 /* use ONLY for statically allocated translation tables */
 #define pud_offset_kimg(dir,addr)	((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr))))
@@ -642,28 +676,23 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /*
- * ptep_set_wrprotect - mark read-only while preserving the hardware update of
- * the Access Flag.
+ * ptep_set_wrprotect - mark read-only while trasferring potential hardware
+ * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit.
  */
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
 {
 	pte_t old_pte, pte;
 
-	/*
-	 * ptep_set_wrprotect() is only called on CoW mappings which are
-	 * private (!VM_SHARED) with the pte either read-only (!PTE_WRITE &&
-	 * PTE_RDONLY) or writable and software-dirty (PTE_WRITE &&
-	 * !PTE_RDONLY && PTE_DIRTY); see is_cow_mapping() and
-	 * protection_map[]. There is no race with the hardware update of the
-	 * dirty state: clearing of PTE_RDONLY when PTE_WRITE (a.k.a. PTE_DBM)
-	 * is set.
-	 */
-	VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(*ptep),
-		     "%s: potential race with hardware DBM", __func__);
 	pte = READ_ONCE(*ptep);
 	do {
 		old_pte = pte;
+		/*
+		 * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY
+		 * clear), set the PTE_DIRTY bit.
+		 */
+		if (pte_hw_dirty(pte))
+			pte = pte_mkdirty(pte);
 		pte = pte_wrprotect(pte);
 		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
 					       pte_val(old_pte), pte_val(pte));
@@ -677,10 +706,19 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 {
 	ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
 }
+
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd)));
+}
 #endif
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+extern pgd_t swapper_pg_end[];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
+extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
 
 /*
  * Encode and decode a swap entry:
@@ -734,6 +772,12 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 #define kc_vaddr_to_offset(v)	((v) & ~VA_START)
 #define kc_offset_to_vaddr(o)	((o) | VA_START)
 
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define phys_to_ttbr(addr)	(((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52)
+#else
+#define phys_to_ttbr(addr)	(addr)
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 14ad6e4e87d1..16cef2e8449e 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -35,12 +35,6 @@ extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
 #include <asm/memory.h>
 
-#define cpu_switch_mm(pgd,mm)				\
-do {							\
-	BUG_ON(pgd == swapper_pg_dir);			\
-	cpu_do_switch_mm(virt_to_phys(pgd),mm);		\
-} while (0)
-
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* __ASM_PROCFNS_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 023cacb946c3..cee4ae25a5d1 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -216,6 +216,7 @@ static inline void spin_lock_prefetch(const void *ptr)
 
 int cpu_enable_pan(void *__unused);
 int cpu_enable_cache_maint_trap(void *__unused);
+int cpu_clear_disr(void *__unused);
 
 /* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */
 #define SVE_SET_VL(arg)	sve_set_current_vl(arg)
diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h
new file mode 100644
index 000000000000..e073e6886685
--- /dev/null
+++ b/arch/arm64/include/asm/sdei.h
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2017 Arm Ltd.
+#ifndef __ASM_SDEI_H
+#define __ASM_SDEI_H
+
+/* Values for sdei_exit_mode */
+#define SDEI_EXIT_HVC  0
+#define SDEI_EXIT_SMC  1
+
+#define SDEI_STACK_SIZE		IRQ_STACK_SIZE
+
+#ifndef __ASSEMBLY__
+
+#include <linux/linkage.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#include <asm/virt.h>
+
+extern unsigned long sdei_exit_mode;
+
+/* Software Delegated Exception entry point from firmware*/
+asmlinkage void __sdei_asm_handler(unsigned long event_num, unsigned long arg,
+				   unsigned long pc, unsigned long pstate);
+
+/* and its CONFIG_UNMAP_KERNEL_AT_EL0 trampoline */
+asmlinkage void __sdei_asm_entry_trampoline(unsigned long event_num,
+						   unsigned long arg,
+						   unsigned long pc,
+						   unsigned long pstate);
+
+/*
+ * The above entry point does the minimum to call C code. This function does
+ * anything else, before calling the driver.
+ */
+struct sdei_registered_event;
+asmlinkage unsigned long __sdei_handler(struct pt_regs *regs,
+					struct sdei_registered_event *arg);
+
+unsigned long sdei_arch_get_entry_point(int conduit);
+#define sdei_arch_get_entry_point(x)	sdei_arch_get_entry_point(x)
+
+bool _on_sdei_stack(unsigned long sp);
+static inline bool on_sdei_stack(unsigned long sp)
+{
+	if (!IS_ENABLED(CONFIG_VMAP_STACK))
+		return false;
+	if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE))
+		return false;
+	if (in_nmi())
+		return _on_sdei_stack(sp);
+
+	return false;
+}
+
+#endif /* __ASSEMBLY__ */
+#endif	/* __ASM_SDEI_H */
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 941267caa39c..caab039d6305 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -28,5 +28,6 @@ extern char __initdata_begin[], __initdata_end[];
 extern char __inittext_begin[], __inittext_end[];
 extern char __irqentry_text_start[], __irqentry_text_end[];
 extern char __mmuoff_data_start[], __mmuoff_data_end[];
+extern char __entry_tramp_text_start[], __entry_tramp_text_end[];
 
 #endif /* __ASM_SECTIONS_H */
diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h
index 74a9d301819f..b299929fe56c 100644
--- a/arch/arm64/include/asm/sparsemem.h
+++ b/arch/arm64/include/asm/sparsemem.h
@@ -17,7 +17,7 @@
 #define __ASM_SPARSEMEM_H
 
 #ifdef CONFIG_SPARSEMEM
-#define MAX_PHYSMEM_BITS	48
+#define MAX_PHYSMEM_BITS	CONFIG_ARM64_PA_BITS
 #define SECTION_SIZE_BITS	30
 #endif
 
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 6ad30776e984..472ef944e932 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -22,6 +22,7 @@
 
 #include <asm/memory.h>
 #include <asm/ptrace.h>
+#include <asm/sdei.h>
 
 struct stackframe {
 	unsigned long fp;
@@ -85,6 +86,8 @@ static inline bool on_accessible_stack(struct task_struct *tsk, unsigned long sp
 		return true;
 	if (on_overflow_stack(sp))
 		return true;
+	if (on_sdei_stack(sp))
+		return true;
 
 	return false;
 }
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 08cc88574659..0e1960c59197 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -20,6 +20,7 @@
 #ifndef __ASM_SYSREG_H
 #define __ASM_SYSREG_H
 
+#include <asm/compiler.h>
 #include <linux/stringify.h>
 
 /*
@@ -175,6 +176,16 @@
 #define SYS_AFSR0_EL1			sys_reg(3, 0, 5, 1, 0)
 #define SYS_AFSR1_EL1			sys_reg(3, 0, 5, 1, 1)
 #define SYS_ESR_EL1			sys_reg(3, 0, 5, 2, 0)
+
+#define SYS_ERRIDR_EL1			sys_reg(3, 0, 5, 3, 0)
+#define SYS_ERRSELR_EL1			sys_reg(3, 0, 5, 3, 1)
+#define SYS_ERXFR_EL1			sys_reg(3, 0, 5, 4, 0)
+#define SYS_ERXCTLR_EL1			sys_reg(3, 0, 5, 4, 1)
+#define SYS_ERXSTATUS_EL1		sys_reg(3, 0, 5, 4, 2)
+#define SYS_ERXADDR_EL1			sys_reg(3, 0, 5, 4, 3)
+#define SYS_ERXMISC0_EL1		sys_reg(3, 0, 5, 5, 0)
+#define SYS_ERXMISC1_EL1		sys_reg(3, 0, 5, 5, 1)
+
 #define SYS_FAR_EL1			sys_reg(3, 0, 6, 0, 0)
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
 
@@ -278,6 +289,7 @@
 #define SYS_AMAIR_EL1			sys_reg(3, 0, 10, 3, 0)
 
 #define SYS_VBAR_EL1			sys_reg(3, 0, 12, 0, 0)
+#define SYS_DISR_EL1			sys_reg(3, 0, 12, 1, 1)
 
 #define SYS_ICC_IAR0_EL1		sys_reg(3, 0, 12, 8, 0)
 #define SYS_ICC_EOIR0_EL1		sys_reg(3, 0, 12, 8, 1)
@@ -353,8 +365,10 @@
 
 #define SYS_DACR32_EL2			sys_reg(3, 4, 3, 0, 0)
 #define SYS_IFSR32_EL2			sys_reg(3, 4, 5, 0, 1)
+#define SYS_VSESR_EL2			sys_reg(3, 4, 5, 2, 3)
 #define SYS_FPEXC32_EL2			sys_reg(3, 4, 5, 3, 0)
 
+#define SYS_VDISR_EL2			sys_reg(3, 4, 12, 1,  1)
 #define __SYS__AP0Rx_EL2(x)		sys_reg(3, 4, 12, 8, x)
 #define SYS_ICH_AP0R0_EL2		__SYS__AP0Rx_EL2(0)
 #define SYS_ICH_AP0R1_EL2		__SYS__AP0Rx_EL2(1)
@@ -398,27 +412,85 @@
 
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_EE    (1 << 25)
+#define SCTLR_ELx_IESB	(1 << 21)
+#define SCTLR_ELx_WXN	(1 << 19)
 #define SCTLR_ELx_I	(1 << 12)
 #define SCTLR_ELx_SA	(1 << 3)
 #define SCTLR_ELx_C	(1 << 2)
 #define SCTLR_ELx_A	(1 << 1)
 #define SCTLR_ELx_M	1
 
+#define SCTLR_ELx_FLAGS	(SCTLR_ELx_M  | SCTLR_ELx_A | SCTLR_ELx_C | \
+			 SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_IESB)
+
+/* SCTLR_EL2 specific flags. */
 #define SCTLR_EL2_RES1	((1 << 4)  | (1 << 5)  | (1 << 11) | (1 << 16) | \
 			 (1 << 18) | (1 << 22) | (1 << 23) | (1 << 28) | \
 			 (1 << 29))
+#define SCTLR_EL2_RES0	((1 << 6)  | (1 << 7)  | (1 << 8)  | (1 << 9)  | \
+			 (1 << 10) | (1 << 13) | (1 << 14) | (1 << 15) | \
+			 (1 << 17) | (1 << 20) | (1 << 24) | (1 << 26) | \
+			 (1 << 27) | (1 << 30) | (1 << 31))
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define ENDIAN_SET_EL2		SCTLR_ELx_EE
+#define ENDIAN_CLEAR_EL2	0
+#else
+#define ENDIAN_SET_EL2		0
+#define ENDIAN_CLEAR_EL2	SCTLR_ELx_EE
+#endif
+
+/* SCTLR_EL2 value used for the hyp-stub */
+#define SCTLR_EL2_SET	(SCTLR_ELx_IESB   | ENDIAN_SET_EL2   | SCTLR_EL2_RES1)
+#define SCTLR_EL2_CLEAR	(SCTLR_ELx_M      | SCTLR_ELx_A    | SCTLR_ELx_C   | \
+			 SCTLR_ELx_SA     | SCTLR_ELx_I    | SCTLR_ELx_WXN | \
+			 ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0)
+
+/* Check all the bits are accounted for */
+#define SCTLR_EL2_BUILD_BUG_ON_MISSING_BITS	BUILD_BUG_ON((SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != ~0)
 
-#define SCTLR_ELx_FLAGS	(SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
-			 SCTLR_ELx_SA | SCTLR_ELx_I)
 
 /* SCTLR_EL1 specific flags. */
 #define SCTLR_EL1_UCI		(1 << 26)
+#define SCTLR_EL1_E0E		(1 << 24)
 #define SCTLR_EL1_SPAN		(1 << 23)
+#define SCTLR_EL1_NTWE		(1 << 18)
+#define SCTLR_EL1_NTWI		(1 << 16)
 #define SCTLR_EL1_UCT		(1 << 15)
+#define SCTLR_EL1_DZE		(1 << 14)
+#define SCTLR_EL1_UMA		(1 << 9)
 #define SCTLR_EL1_SED		(1 << 8)
+#define SCTLR_EL1_ITD		(1 << 7)
 #define SCTLR_EL1_CP15BEN	(1 << 5)
+#define SCTLR_EL1_SA0		(1 << 4)
+
+#define SCTLR_EL1_RES1	((1 << 11) | (1 << 20) | (1 << 22) | (1 << 28) | \
+			 (1 << 29))
+#define SCTLR_EL1_RES0  ((1 << 6)  | (1 << 10) | (1 << 13) | (1 << 17) | \
+			 (1 << 27) | (1 << 30) | (1 << 31))
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define ENDIAN_SET_EL1		(SCTLR_EL1_E0E | SCTLR_ELx_EE)
+#define ENDIAN_CLEAR_EL1	0
+#else
+#define ENDIAN_SET_EL1		0
+#define ENDIAN_CLEAR_EL1	(SCTLR_EL1_E0E | SCTLR_ELx_EE)
+#endif
+
+#define SCTLR_EL1_SET	(SCTLR_ELx_M    | SCTLR_ELx_C    | SCTLR_ELx_SA   |\
+			 SCTLR_EL1_SA0  | SCTLR_EL1_SED  | SCTLR_ELx_I    |\
+			 SCTLR_EL1_DZE  | SCTLR_EL1_UCT  | SCTLR_EL1_NTWI |\
+			 SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN |\
+			 ENDIAN_SET_EL1 | SCTLR_EL1_UCI  | SCTLR_EL1_RES1)
+#define SCTLR_EL1_CLEAR	(SCTLR_ELx_A   | SCTLR_EL1_CP15BEN | SCTLR_EL1_ITD    |\
+			 SCTLR_EL1_UMA | SCTLR_ELx_WXN     | ENDIAN_CLEAR_EL1 |\
+			 SCTLR_EL1_RES0)
+
+/* Check all the bits are accounted for */
+#define SCTLR_EL1_BUILD_BUG_ON_MISSING_BITS	BUILD_BUG_ON((SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != ~0)
 
 /* id_aa64isar0 */
+#define ID_AA64ISAR0_FHM_SHIFT		48
 #define ID_AA64ISAR0_DP_SHIFT		44
 #define ID_AA64ISAR0_SM4_SHIFT		40
 #define ID_AA64ISAR0_SM3_SHIFT		36
@@ -437,7 +509,10 @@
 #define ID_AA64ISAR1_DPB_SHIFT		0
 
 /* id_aa64pfr0 */
+#define ID_AA64PFR0_CSV3_SHIFT		60
+#define ID_AA64PFR0_CSV2_SHIFT		56
 #define ID_AA64PFR0_SVE_SHIFT		32
+#define ID_AA64PFR0_RAS_SHIFT		28
 #define ID_AA64PFR0_GIC_SHIFT		24
 #define ID_AA64PFR0_ASIMD_SHIFT		20
 #define ID_AA64PFR0_FP_SHIFT		16
@@ -447,6 +522,7 @@
 #define ID_AA64PFR0_EL0_SHIFT		0
 
 #define ID_AA64PFR0_SVE			0x1
+#define ID_AA64PFR0_RAS_V1		0x1
 #define ID_AA64PFR0_FP_NI		0xf
 #define ID_AA64PFR0_FP_SUPPORTED	0x0
 #define ID_AA64PFR0_ASIMD_NI		0xf
@@ -471,6 +547,14 @@
 #define ID_AA64MMFR0_TGRAN64_SUPPORTED	0x0
 #define ID_AA64MMFR0_TGRAN16_NI		0x0
 #define ID_AA64MMFR0_TGRAN16_SUPPORTED	0x1
+#define ID_AA64MMFR0_PARANGE_48		0x5
+#define ID_AA64MMFR0_PARANGE_52		0x6
+
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define ID_AA64MMFR0_PARANGE_MAX	ID_AA64MMFR0_PARANGE_52
+#else
+#define ID_AA64MMFR0_PARANGE_MAX	ID_AA64MMFR0_PARANGE_48
+#endif
 
 /* id_aa64mmfr1 */
 #define ID_AA64MMFR1_PAN_SHIFT		20
@@ -582,6 +666,7 @@
 
 #else
 
+#include <linux/build_bug.h>
 #include <linux/types.h>
 
 asm(
@@ -638,6 +723,9 @@ static inline void config_sctlr_el1(u32 clear, u32 set)
 {
 	u32 val;
 
+	SCTLR_EL2_BUILD_BUG_ON_MISSING_BITS;
+	SCTLR_EL1_BUILD_BUG_ON_MISSING_BITS;
+
 	val = read_sysreg(sctlr_el1);
 	val &= ~clear;
 	val |= set;
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index eb431286bacd..740aa03c5f0d 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -51,8 +51,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,					\
 }
 
-#define init_stack		(init_thread_union.stack)
-
 #define thread_saved_pc(tsk)	\
 	((unsigned long)(tsk->thread.cpu_context.pc))
 #define thread_saved_sp(tsk)	\
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index af1c76981911..9e82dd79c7db 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -23,6 +23,7 @@
 
 #include <linux/sched.h>
 #include <asm/cputype.h>
+#include <asm/mmu.h>
 
 /*
  * Raw TLBI operations.
@@ -54,6 +55,11 @@
 
 #define __tlbi(op, ...)		__TLBI_N(op, ##__VA_ARGS__, 1, 0)
 
+#define __tlbi_user(op, arg) do {						\
+	if (arm64_kernel_unmapped_at_el0())					\
+		__tlbi(op, (arg) | USER_ASID_FLAG);				\
+} while (0)
+
 /*
  *	TLB Management
  *	==============
@@ -115,6 +121,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 
 	dsb(ishst);
 	__tlbi(aside1is, asid);
+	__tlbi_user(aside1is, asid);
 	dsb(ish);
 }
 
@@ -125,6 +132,7 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 
 	dsb(ishst);
 	__tlbi(vale1is, addr);
+	__tlbi_user(vale1is, addr);
 	dsb(ish);
 }
 
@@ -151,10 +159,13 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 
 	dsb(ishst);
 	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
-		if (last_level)
+		if (last_level) {
 			__tlbi(vale1is, addr);
-		else
+			__tlbi_user(vale1is, addr);
+		} else {
 			__tlbi(vae1is, addr);
+			__tlbi_user(vae1is, addr);
+		}
 	}
 	dsb(ish);
 }
@@ -194,6 +205,7 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm,
 	unsigned long addr = uaddr >> 12 | (ASID(mm) << 48);
 
 	__tlbi(vae1is, addr);
+	__tlbi_user(vae1is, addr);
 	dsb(ish);
 }
 
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 1696f9de9359..178e338d2889 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -19,6 +19,7 @@
 #define __ASM_TRAP_H
 
 #include <linux/list.h>
+#include <asm/esr.h>
 #include <asm/sections.h>
 
 struct pt_regs;
@@ -66,4 +67,57 @@ static inline int in_entry_text(unsigned long ptr)
 	return ptr >= (unsigned long)&__entry_text_start &&
 	       ptr < (unsigned long)&__entry_text_end;
 }
+
+/*
+ * CPUs with the RAS extensions have an Implementation-Defined-Syndrome bit
+ * to indicate whether this ESR has a RAS encoding. CPUs without this feature
+ * have a ISS-Valid bit in the same position.
+ * If this bit is set, we know its not a RAS SError.
+ * If its clear, we need to know if the CPU supports RAS. Uncategorized RAS
+ * errors share the same encoding as an all-zeros encoding from a CPU that
+ * doesn't support RAS.
+ */
+static inline bool arm64_is_ras_serror(u32 esr)
+{
+	WARN_ON(preemptible());
+
+	if (esr & ESR_ELx_IDS)
+		return false;
+
+	if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN))
+		return true;
+	else
+		return false;
+}
+
+/*
+ * Return the AET bits from a RAS SError's ESR.
+ *
+ * It is implementation defined whether Uncategorized errors are containable.
+ * We treat them as Uncontainable.
+ * Non-RAS SError's are reported as Uncontained/Uncategorized.
+ */
+static inline u32 arm64_ras_serror_get_severity(u32 esr)
+{
+	u32 aet = esr & ESR_ELx_AET;
+
+	if (!arm64_is_ras_serror(esr)) {
+		/* Not a RAS error, we can't interpret the ESR. */
+		return ESR_ELx_AET_UC;
+	}
+
+	/*
+	 * AET is RES0 if 'the value returned in the DFSC field is not
+	 * [ESR_ELx_FSC_SERROR]'
+	 */
+	if ((esr & ESR_ELx_FSC) != ESR_ELx_FSC_SERROR) {
+		/* No severity information : Uncategorized */
+		return ESR_ELx_AET_UC;
+	}
+
+	return aet;
+}
+
+bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr);
+void __noreturn arm64_serror_panic(struct pt_regs *regs, u32 esr);
 #endif
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index fc0f9eb66039..59fda5292936 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -105,17 +105,23 @@ static inline void set_fs(mm_segment_t fs)
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 static inline void __uaccess_ttbr0_disable(void)
 {
-	unsigned long ttbr;
+	unsigned long flags, ttbr;
 
-	/* reserved_ttbr0 placed at the end of swapper_pg_dir */
-	ttbr = read_sysreg(ttbr1_el1) + SWAPPER_DIR_SIZE;
-	write_sysreg(ttbr, ttbr0_el1);
+	local_irq_save(flags);
+	ttbr = read_sysreg(ttbr1_el1);
+	ttbr &= ~TTBR_ASID_MASK;
+	/* reserved_ttbr0 placed before swapper_pg_dir */
+	write_sysreg(ttbr - RESERVED_TTBR0_SIZE, ttbr0_el1);
+	isb();
+	/* Set reserved ASID */
+	write_sysreg(ttbr, ttbr1_el1);
 	isb();
+	local_irq_restore(flags);
 }
 
 static inline void __uaccess_ttbr0_enable(void)
 {
-	unsigned long flags;
+	unsigned long flags, ttbr0, ttbr1;
 
 	/*
 	 * Disable interrupts to avoid preemption between reading the 'ttbr0'
@@ -123,7 +129,17 @@ static inline void __uaccess_ttbr0_enable(void)
 	 * roll-over and an update of 'ttbr0'.
 	 */
 	local_irq_save(flags);
-	write_sysreg(current_thread_info()->ttbr0, ttbr0_el1);
+	ttbr0 = READ_ONCE(current_thread_info()->ttbr0);
+
+	/* Restore active ASID */
+	ttbr1 = read_sysreg(ttbr1_el1);
+	ttbr1 &= ~TTBR_ASID_MASK;		/* safety measure */
+	ttbr1 |= ttbr0 & TTBR_ASID_MASK;
+	write_sysreg(ttbr1, ttbr1_el1);
+	isb();
+
+	/* Restore user page table */
+	write_sysreg(ttbr0, ttbr0_el1);
 	isb();
 	local_irq_restore(flags);
 }
@@ -155,6 +171,18 @@ static inline bool uaccess_ttbr0_enable(void)
 }
 #endif
 
+static inline void __uaccess_disable_hw_pan(void)
+{
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,
+			CONFIG_ARM64_PAN));
+}
+
+static inline void __uaccess_enable_hw_pan(void)
+{
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+			CONFIG_ARM64_PAN));
+}
+
 #define __uaccess_disable(alt)						\
 do {									\
 	if (!uaccess_ttbr0_disable())					\
diff --git a/arch/arm64/include/asm/vmap_stack.h b/arch/arm64/include/asm/vmap_stack.h
new file mode 100644
index 000000000000..0b5ec6e08c10
--- /dev/null
+++ b/arch/arm64/include/asm/vmap_stack.h
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2017 Arm Ltd.
+#ifndef __ASM_VMAP_STACK_H
+#define __ASM_VMAP_STACK_H
+
+#include <linux/bug.h>
+#include <linux/gfp.h>
+#include <linux/kconfig.h>
+#include <linux/vmalloc.h>
+#include <asm/memory.h>
+#include <asm/pgtable.h>
+#include <asm/thread_info.h>
+
+/*
+ * To ensure that VMAP'd stack overflow detection works correctly, all VMAP'd
+ * stacks need to have the same alignment.
+ */
+static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node)
+{
+	BUILD_BUG_ON(!IS_ENABLED(CONFIG_VMAP_STACK));
+
+	return __vmalloc_node_range(stack_size, THREAD_ALIGN,
+				    VMALLOC_START, VMALLOC_END,
+				    THREADINFO_GFP, PAGE_KERNEL, 0, node,
+				    __builtin_return_address(0));
+}
+
+#endif /* __ASM_VMAP_STACK_H */
diff --git a/arch/arm64/include/uapi/asm/bpf_perf_event.h b/arch/arm64/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 000000000000..b551b741653d
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index cda76fa8b9b2..f018c3deea3b 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -43,5 +43,6 @@
 #define HWCAP_ASIMDDP		(1 << 20)
 #define HWCAP_SHA512		(1 << 21)
 #define HWCAP_SVE		(1 << 22)
+#define HWCAP_ASIMDFHM		(1 << 23)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/siginfo.h b/arch/arm64/include/uapi/asm/siginfo.h
index 574d12f86039..9b4d91277742 100644
--- a/arch/arm64/include/uapi/asm/siginfo.h
+++ b/arch/arm64/include/uapi/asm/siginfo.h
@@ -21,4 +21,25 @@
 
 #include <asm-generic/siginfo.h>
 
+/*
+ * SIGFPE si_codes
+ */
+#ifdef __KERNEL__
+#define FPE_FIXME	0	/* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
+/*
+ * SIGBUS si_codes
+ */
+#ifdef __KERNEL__
+#define BUS_FIXME	0	/* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
+/*
+ * SIGTRAP si_codes
+ */
+#ifdef __KERNEL__
+#define TRAP_FIXME	0	/* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
 #endif
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 8265dd790895..b87541360f43 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -52,6 +52,11 @@ arm64-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o	\
 arm64-obj-$(CONFIG_ARM64_RELOC_TEST)	+= arm64-reloc-test.o
 arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
 arm64-obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
+arm64-obj-$(CONFIG_ARM_SDE_INTERFACE)	+= sdei.o
+
+ifeq ($(CONFIG_KVM),y)
+arm64-obj-$(CONFIG_HARDEN_BRANCH_PREDICTOR)	+= bpi.o
+endif
 
 obj-y					+= $(arm64-obj-y) vdso/ probes/
 obj-m					+= $(arm64-obj-m)
@@ -61,6 +66,3 @@ extra-y					+= $(head-y) vmlinux.lds
 ifeq ($(CONFIG_DEBUG_EFI),y)
 AFLAGS_head.o += -DVMLINUX_PATH="\"$(realpath $(objtree)/vmlinux)\""
 endif
-
-# will be included by each individual module but not by the core kernel itself
-extra-$(CONFIG_DYNAMIC_FTRACE) += ftrace-mod.o
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index b3162715ed78..252396a96c78 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -117,7 +117,7 @@ bool __init acpi_psci_present(void)
 }
 
 /* Whether HVC must be used instead of SMC as the PSCI conduit */
-bool __init acpi_psci_use_hvc(void)
+bool acpi_psci_use_hvc(void)
 {
 	return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC;
 }
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 6dd0a3a3e5c9..414288a558c8 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -32,6 +32,8 @@
 #define ALT_ORIG_PTR(a)		__ALT_PTR(a, orig_offset)
 #define ALT_REPL_PTR(a)		__ALT_PTR(a, alt_offset)
 
+int alternatives_applied;
+
 struct alt_region {
 	struct alt_instr *begin;
 	struct alt_instr *end;
@@ -143,7 +145,6 @@ static void __apply_alternatives(void *alt_region, bool use_linear_alias)
  */
 static int __apply_alternatives_multi_stop(void *unused)
 {
-	static int patched = 0;
 	struct alt_region region = {
 		.begin	= (struct alt_instr *)__alt_instructions,
 		.end	= (struct alt_instr *)__alt_instructions_end,
@@ -151,14 +152,14 @@ static int __apply_alternatives_multi_stop(void *unused)
 
 	/* We always have a CPU 0 at this point (__init) */
 	if (smp_processor_id()) {
-		while (!READ_ONCE(patched))
+		while (!READ_ONCE(alternatives_applied))
 			cpu_relax();
 		isb();
 	} else {
-		BUG_ON(patched);
+		BUG_ON(alternatives_applied);
 		__apply_alternatives(&region, true);
 		/* Barriers provided by the cache flushing */
-		WRITE_ONCE(patched, 1);
+		WRITE_ONCE(alternatives_applied, 1);
 	}
 
 	return 0;
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 71bf088f1e4b..1303e04110cd 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -18,12 +18,14 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/arm_sdei.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/kvm_host.h>
 #include <linux/suspend.h>
 #include <asm/cpufeature.h>
+#include <asm/fixmap.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/smp_plat.h>
@@ -130,6 +132,7 @@ int main(void)
   BLANK();
 #ifdef CONFIG_KVM_ARM_HOST
   DEFINE(VCPU_CONTEXT,		offsetof(struct kvm_vcpu, arch.ctxt));
+  DEFINE(VCPU_FAULT_DISR,	offsetof(struct kvm_vcpu, arch.fault.disr_el1));
   DEFINE(CPU_GP_REGS,		offsetof(struct kvm_cpu_context, gp_regs));
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(CPU_FP_REGS,		offsetof(struct kvm_regs, fp_regs));
@@ -148,11 +151,18 @@ int main(void)
   DEFINE(ARM_SMCCC_RES_X2_OFFS,		offsetof(struct arm_smccc_res, a2));
   DEFINE(ARM_SMCCC_QUIRK_ID_OFFS,	offsetof(struct arm_smccc_quirk, id));
   DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS,	offsetof(struct arm_smccc_quirk, state));
-
   BLANK();
   DEFINE(HIBERN_PBE_ORIG,	offsetof(struct pbe, orig_address));
   DEFINE(HIBERN_PBE_ADDR,	offsetof(struct pbe, address));
   DEFINE(HIBERN_PBE_NEXT,	offsetof(struct pbe, next));
   DEFINE(ARM64_FTR_SYSVAL,	offsetof(struct arm64_ftr_reg, sys_val));
+  BLANK();
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+  DEFINE(TRAMP_VALIAS,		TRAMP_VALIAS);
+#endif
+#ifdef CONFIG_ARM_SDE_INTERFACE
+  DEFINE(SDEI_EVENT_INTREGS,	offsetof(struct sdei_registered_event, interrupted_regs));
+  DEFINE(SDEI_EVENT_PRIORITY,	offsetof(struct sdei_registered_event, priority));
+#endif
   return 0;
 }
diff --git a/arch/arm64/kernel/bpi.S b/arch/arm64/kernel/bpi.S
new file mode 100644
index 000000000000..76225c2611ea
--- /dev/null
+++ b/arch/arm64/kernel/bpi.S
@@ -0,0 +1,87 @@
+/*
+ * Contains CPU specific branch predictor invalidation sequences
+ *
+ * Copyright (C) 2018 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+
+.macro ventry target
+	.rept 31
+	nop
+	.endr
+	b	\target
+.endm
+
+.macro vectors target
+	ventry \target + 0x000
+	ventry \target + 0x080
+	ventry \target + 0x100
+	ventry \target + 0x180
+
+	ventry \target + 0x200
+	ventry \target + 0x280
+	ventry \target + 0x300
+	ventry \target + 0x380
+
+	ventry \target + 0x400
+	ventry \target + 0x480
+	ventry \target + 0x500
+	ventry \target + 0x580
+
+	ventry \target + 0x600
+	ventry \target + 0x680
+	ventry \target + 0x700
+	ventry \target + 0x780
+.endm
+
+	.align	11
+ENTRY(__bp_harden_hyp_vecs_start)
+	.rept 4
+	vectors __kvm_hyp_vector
+	.endr
+ENTRY(__bp_harden_hyp_vecs_end)
+ENTRY(__psci_hyp_bp_inval_start)
+	sub	sp, sp, #(8 * 18)
+	stp	x16, x17, [sp, #(16 * 0)]
+	stp	x14, x15, [sp, #(16 * 1)]
+	stp	x12, x13, [sp, #(16 * 2)]
+	stp	x10, x11, [sp, #(16 * 3)]
+	stp	x8, x9, [sp, #(16 * 4)]
+	stp	x6, x7, [sp, #(16 * 5)]
+	stp	x4, x5, [sp, #(16 * 6)]
+	stp	x2, x3, [sp, #(16 * 7)]
+	stp	x0, x1, [sp, #(16 * 8)]
+	mov	x0, #0x84000000
+	smc	#0
+	ldp	x16, x17, [sp, #(16 * 0)]
+	ldp	x14, x15, [sp, #(16 * 1)]
+	ldp	x12, x13, [sp, #(16 * 2)]
+	ldp	x10, x11, [sp, #(16 * 3)]
+	ldp	x8, x9, [sp, #(16 * 4)]
+	ldp	x6, x7, [sp, #(16 * 5)]
+	ldp	x4, x5, [sp, #(16 * 6)]
+	ldp	x2, x3, [sp, #(16 * 7)]
+	ldp	x0, x1, [sp, #(16 * 8)]
+	add	sp, sp, #(8 * 18)
+ENTRY(__psci_hyp_bp_inval_end)
+
+ENTRY(__qcom_hyp_sanitize_link_stack_start)
+	stp     x29, x30, [sp, #-16]!
+	.rept	16
+	bl	. + 4
+	.endr
+	ldp	x29, x30, [sp], #16
+ENTRY(__qcom_hyp_sanitize_link_stack_end)
diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S
index 65f42d257414..2a752cb2a0f3 100644
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -37,6 +37,7 @@ ENTRY(__cpu_soft_restart)
 	mrs	x12, sctlr_el1
 	ldr	x13, =SCTLR_ELx_FLAGS
 	bic	x12, x12, x13
+	pre_disable_mmu_workaround
 	msr	sctlr_el1, x12
 	isb
 
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 0e27f86ee709..ed6881882231 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -30,6 +30,20 @@ is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
 				       entry->midr_range_max);
 }
 
+static bool __maybe_unused
+is_kryo_midr(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	u32 model;
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+
+	model = read_cpuid_id();
+	model &= MIDR_IMPLEMENTOR_MASK | (0xf00 << MIDR_PARTNUM_SHIFT) |
+		 MIDR_ARCHITECTURE_MASK;
+
+	return model == entry->midr_model;
+}
+
 static bool
 has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
 				int scope)
@@ -46,6 +60,127 @@ static int cpu_enable_trap_ctr_access(void *__unused)
 	return 0;
 }
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+#include <asm/mmu_context.h>
+#include <asm/cacheflush.h>
+
+DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
+
+#ifdef CONFIG_KVM
+extern char __psci_hyp_bp_inval_start[], __psci_hyp_bp_inval_end[];
+extern char __qcom_hyp_sanitize_link_stack_start[];
+extern char __qcom_hyp_sanitize_link_stack_end[];
+
+static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
+				const char *hyp_vecs_end)
+{
+	void *dst = lm_alias(__bp_harden_hyp_vecs_start + slot * SZ_2K);
+	int i;
+
+	for (i = 0; i < SZ_2K; i += 0x80)
+		memcpy(dst + i, hyp_vecs_start, hyp_vecs_end - hyp_vecs_start);
+
+	flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
+}
+
+static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
+				      const char *hyp_vecs_start,
+				      const char *hyp_vecs_end)
+{
+	static int last_slot = -1;
+	static DEFINE_SPINLOCK(bp_lock);
+	int cpu, slot = -1;
+
+	spin_lock(&bp_lock);
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(bp_hardening_data.fn, cpu) == fn) {
+			slot = per_cpu(bp_hardening_data.hyp_vectors_slot, cpu);
+			break;
+		}
+	}
+
+	if (slot == -1) {
+		last_slot++;
+		BUG_ON(((__bp_harden_hyp_vecs_end - __bp_harden_hyp_vecs_start)
+			/ SZ_2K) <= last_slot);
+		slot = last_slot;
+		__copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end);
+	}
+
+	__this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot);
+	__this_cpu_write(bp_hardening_data.fn, fn);
+	spin_unlock(&bp_lock);
+}
+#else
+#define __psci_hyp_bp_inval_start		NULL
+#define __psci_hyp_bp_inval_end			NULL
+#define __qcom_hyp_sanitize_link_stack_start	NULL
+#define __qcom_hyp_sanitize_link_stack_end	NULL
+
+static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
+				      const char *hyp_vecs_start,
+				      const char *hyp_vecs_end)
+{
+	__this_cpu_write(bp_hardening_data.fn, fn);
+}
+#endif	/* CONFIG_KVM */
+
+static void  install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry,
+				     bp_hardening_cb_t fn,
+				     const char *hyp_vecs_start,
+				     const char *hyp_vecs_end)
+{
+	u64 pfr0;
+
+	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
+		return;
+
+	pfr0 = read_cpuid(ID_AA64PFR0_EL1);
+	if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_CSV2_SHIFT))
+		return;
+
+	__install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end);
+}
+
+#include <linux/psci.h>
+
+static int enable_psci_bp_hardening(void *data)
+{
+	const struct arm64_cpu_capabilities *entry = data;
+
+	if (psci_ops.get_version)
+		install_bp_hardening_cb(entry,
+				       (bp_hardening_cb_t)psci_ops.get_version,
+				       __psci_hyp_bp_inval_start,
+				       __psci_hyp_bp_inval_end);
+
+	return 0;
+}
+
+static void qcom_link_stack_sanitization(void)
+{
+	u64 tmp;
+
+	asm volatile("mov	%0, x30		\n"
+		     ".rept	16		\n"
+		     "bl	. + 4		\n"
+		     ".endr			\n"
+		     "mov	x30, %0		\n"
+		     : "=&r" (tmp));
+}
+
+static int qcom_enable_link_stack_sanitization(void *data)
+{
+	const struct arm64_cpu_capabilities *entry = data;
+
+	install_bp_hardening_cb(entry, qcom_link_stack_sanitization,
+				__qcom_hyp_sanitize_link_stack_start,
+				__qcom_hyp_sanitize_link_stack_end);
+
+	return 0;
+}
+#endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
+
 #define MIDR_RANGE(model, min, max) \
 	.def_scope = SCOPE_LOCAL_CPU, \
 	.matches = is_affected_midr_range, \
@@ -169,6 +304,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 			   MIDR_CPU_VAR_REV(0, 0),
 			   MIDR_CPU_VAR_REV(0, 0)),
 	},
+	{
+		.desc = "Qualcomm Technologies Kryo erratum 1003",
+		.capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003,
+		.def_scope = SCOPE_LOCAL_CPU,
+		.midr_model = MIDR_QCOM_KRYO,
+		.matches = is_kryo_midr,
+	},
 #endif
 #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009
 	{
@@ -187,6 +329,47 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 	},
 #endif
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
+		.enable = enable_psci_bp_hardening,
+	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
+		.enable = enable_psci_bp_hardening,
+	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
+		.enable = enable_psci_bp_hardening,
+	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
+		.enable = enable_psci_bp_hardening,
+	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
+		.enable = qcom_enable_link_stack_sanitization,
+	},
+	{
+		.capability = ARM64_HARDEN_BP_POST_GUEST_EXIT,
+		MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
+	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
+		.enable = enable_psci_bp_hardening,
+	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
+		.enable = enable_psci_bp_hardening,
+	},
+#endif
 	{
 	}
 };
@@ -200,15 +383,18 @@ void verify_local_cpu_errata_workarounds(void)
 {
 	const struct arm64_cpu_capabilities *caps = arm64_errata;
 
-	for (; caps->matches; caps++)
-		if (!cpus_have_cap(caps->capability) &&
-			caps->matches(caps, SCOPE_LOCAL_CPU)) {
+	for (; caps->matches; caps++) {
+		if (cpus_have_cap(caps->capability)) {
+			if (caps->enable)
+				caps->enable((void *)caps);
+		} else if (caps->matches(caps, SCOPE_LOCAL_CPU)) {
 			pr_crit("CPU%d: Requires work around for %s, not detected"
 					" at boot time\n",
 				smp_processor_id(),
 				caps->desc ? : "an erratum");
 			cpu_die_early();
 		}
+	}
 }
 
 void update_cpu_errata_workarounds(void)
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index d16978213c5b..ea001241bdd4 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -31,13 +31,13 @@ extern const struct cpu_operations cpu_psci_ops;
 
 const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
 
-static const struct cpu_operations *dt_supported_cpu_ops[] __initconst = {
+static const struct cpu_operations *const dt_supported_cpu_ops[] __initconst = {
 	&smp_spin_table_ops,
 	&cpu_psci_ops,
 	NULL,
 };
 
-static const struct cpu_operations *acpi_supported_cpu_ops[] __initconst = {
+static const struct cpu_operations *const acpi_supported_cpu_ops[] __initconst = {
 #ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
 	&acpi_parking_protocol_ops,
 #endif
@@ -47,7 +47,7 @@ static const struct cpu_operations *acpi_supported_cpu_ops[] __initconst = {
 
 static const struct cpu_operations * __init cpu_get_ops(const char *name)
 {
-	const struct cpu_operations **ops;
+	const struct cpu_operations *const *ops;
 
 	ops = acpi_disabled ? dt_supported_cpu_ops : acpi_supported_cpu_ops;
 
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index c5ba0097887f..0fb6a3151443 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -123,6 +123,7 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused)
  * sync with the documentation of the CPU feature register ABI.
  */
 static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_FHM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM4_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM3_SHIFT, 4, 0),
@@ -145,7 +146,11 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+				   FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_RAS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
@@ -845,6 +850,67 @@ static bool has_no_fpsimd(const struct arm64_cpu_capabilities *entry, int __unus
 					ID_AA64PFR0_FP_SHIFT) < 0;
 }
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */
+
+static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
+				int __unused)
+{
+	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+	/* Forced on command line? */
+	if (__kpti_forced) {
+		pr_info_once("kernel page table isolation forced %s by command line option\n",
+			     __kpti_forced > 0 ? "ON" : "OFF");
+		return __kpti_forced > 0;
+	}
+
+	/* Useful for KASLR robustness */
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+		return true;
+
+	/* Don't force KPTI for CPUs that are not vulnerable */
+	switch (read_cpuid_id() & MIDR_CPU_MODEL_MASK) {
+	case MIDR_CAVIUM_THUNDERX2:
+	case MIDR_BRCM_VULCAN:
+		return false;
+	}
+
+	/* Defer to CPU feature registers */
+	return !cpuid_feature_extract_unsigned_field(pfr0,
+						     ID_AA64PFR0_CSV3_SHIFT);
+}
+
+static int __init parse_kpti(char *str)
+{
+	bool enabled;
+	int ret = strtobool(str, &enabled);
+
+	if (ret)
+		return ret;
+
+	__kpti_forced = enabled ? 1 : -1;
+	return 0;
+}
+__setup("kpti=", parse_kpti);
+#endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
+
+static int cpu_copy_el2regs(void *__unused)
+{
+	/*
+	 * Copy register values that aren't redirected by hardware.
+	 *
+	 * Before code patching, we only set tpidr_el1, all CPUs need to copy
+	 * this value to tpidr_el2 before we patch the code. Once we've done
+	 * that, freshly-onlined CPUs will set tpidr_el2, so we don't need to
+	 * do anything here.
+	 */
+	if (!alternatives_applied)
+		write_sysreg(read_sysreg(tpidr_el1), tpidr_el2);
+
+	return 0;
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
@@ -914,6 +980,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.capability = ARM64_HAS_VIRT_HOST_EXTN,
 		.def_scope = SCOPE_SYSTEM,
 		.matches = runs_at_el2,
+		.enable = cpu_copy_el2regs,
 	},
 	{
 		.desc = "32-bit EL0 Support",
@@ -931,6 +998,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.def_scope = SCOPE_SYSTEM,
 		.matches = hyp_offset_low,
 	},
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	{
+		.desc = "Kernel page table isolation (KPTI)",
+		.capability = ARM64_UNMAP_KERNEL_AT_EL0,
+		.def_scope = SCOPE_SYSTEM,
+		.matches = unmap_kernel_at_el0,
+	},
+#endif
 	{
 		/* FP/SIMD is not implemented */
 		.capability = ARM64_HAS_NO_FPSIMD,
@@ -962,6 +1037,19 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.enable = sve_kernel_enable,
 	},
 #endif /* CONFIG_ARM64_SVE */
+#ifdef CONFIG_ARM64_RAS_EXTN
+	{
+		.desc = "RAS Extension Support",
+		.capability = ARM64_HAS_RAS_EXTN,
+		.def_scope = SCOPE_SYSTEM,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64PFR0_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64PFR0_RAS_SHIFT,
+		.min_field_value = ID_AA64PFR0_RAS_V1,
+		.enable = cpu_clear_disr,
+	},
+#endif /* CONFIG_ARM64_RAS_EXTN */
 	{},
 };
 
@@ -991,6 +1079,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDFHM),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD),
@@ -1070,6 +1159,25 @@ static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
 			cap_set_elf_hwcap(hwcaps);
 }
 
+/*
+ * Check if the current CPU has a given feature capability.
+ * Should be called from non-preemptible context.
+ */
+static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array,
+			       unsigned int cap)
+{
+	const struct arm64_cpu_capabilities *caps;
+
+	if (WARN_ON(preemptible()))
+		return false;
+
+	for (caps = cap_array; caps->matches; caps++)
+		if (caps->capability == cap &&
+		    caps->matches(caps, SCOPE_LOCAL_CPU))
+			return true;
+	return false;
+}
+
 void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			    const char *info)
 {
@@ -1105,7 +1213,7 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 			 * uses an IPI, giving us a PSTATE that disappears when
 			 * we return.
 			 */
-			stop_machine(caps->enable, NULL, cpu_online_mask);
+			stop_machine(caps->enable, (void *)caps, cpu_online_mask);
 		}
 	}
 }
@@ -1133,8 +1241,9 @@ verify_local_elf_hwcaps(const struct arm64_cpu_capabilities *caps)
 }
 
 static void
-verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
+verify_local_cpu_features(const struct arm64_cpu_capabilities *caps_list)
 {
+	const struct arm64_cpu_capabilities *caps = caps_list;
 	for (; caps->matches; caps++) {
 		if (!cpus_have_cap(caps->capability))
 			continue;
@@ -1142,13 +1251,13 @@ verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
 		 * If the new CPU misses an advertised feature, we cannot proceed
 		 * further, park the cpu.
 		 */
-		if (!caps->matches(caps, SCOPE_LOCAL_CPU)) {
+		if (!__this_cpu_has_cap(caps_list, caps->capability)) {
 			pr_crit("CPU%d: missing feature: %s\n",
 					smp_processor_id(), caps->desc);
 			cpu_die_early();
 		}
 		if (caps->enable)
-			caps->enable(NULL);
+			caps->enable((void *)caps);
 	}
 }
 
@@ -1188,6 +1297,9 @@ static void verify_local_cpu_capabilities(void)
 
 	if (system_supports_sve())
 		verify_sve_features();
+
+	if (system_uses_ttbr0_pan())
+		pr_info("Emulating Privileged Access Never (PAN) using TTBR0_EL1 switching\n");
 }
 
 void check_local_cpu_capabilities(void)
@@ -1224,25 +1336,6 @@ static void __init mark_const_caps_ready(void)
 	static_branch_enable(&arm64_const_caps_ready);
 }
 
-/*
- * Check if the current CPU has a given feature capability.
- * Should be called from non-preemptible context.
- */
-static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array,
-			       unsigned int cap)
-{
-	const struct arm64_cpu_capabilities *caps;
-
-	if (WARN_ON(preemptible()))
-		return false;
-
-	for (caps = cap_array; caps->desc; caps++)
-		if (caps->capability == cap && caps->matches)
-			return caps->matches(caps, SCOPE_LOCAL_CPU);
-
-	return false;
-}
-
 extern const struct arm64_cpu_capabilities arm64_errata[];
 
 bool this_cpu_has_cap(unsigned int cap)
@@ -1386,3 +1479,11 @@ static int __init enable_mrs_emulation(void)
 }
 
 core_initcall(enable_mrs_emulation);
+
+int cpu_clear_disr(void *__unused)
+{
+	/* Firmware may have left a deferred SError in this register. */
+	write_sysreg_s(0, SYS_DISR_EL1);
+
+	return 0;
+}
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index fd691087dc9a..f2d13810daa8 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -47,6 +47,8 @@ int arm_cpuidle_suspend(int index)
 
 #include <acpi/processor.h>
 
+#define ARM64_LPI_IS_RETENTION_STATE(arch_flags) (!(arch_flags))
+
 int acpi_processor_ffh_lpi_probe(unsigned int cpu)
 {
 	return arm_cpuidle_init(cpu);
@@ -54,6 +56,10 @@ int acpi_processor_ffh_lpi_probe(unsigned int cpu)
 
 int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
 {
-	return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index);
+	if (ARM64_LPI_IS_RETENTION_STATE(lpi->arch_flags))
+		return CPU_PM_CPU_IDLE_ENTER_RETENTION(arm_cpuidle_suspend,
+						lpi->index);
+	else
+		return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index);
 }
 #endif
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 1e2554543506..7f94623df8a5 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -76,6 +76,7 @@ static const char *const hwcap_str[] = {
 	"asimddp",
 	"sha512",
 	"sve",
+	"asimdfhm",
 	NULL
 };
 
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index a88b6ccebbb4..53781f5687c5 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -209,12 +209,13 @@ NOKPROBE_SYMBOL(call_step_hook);
 static void send_user_sigtrap(int si_code)
 {
 	struct pt_regs *regs = current_pt_regs();
-	siginfo_t info = {
-		.si_signo	= SIGTRAP,
-		.si_errno	= 0,
-		.si_code	= si_code,
-		.si_addr	= (void __user *)instruction_pointer(regs),
-	};
+	siginfo_t info;
+
+	clear_siginfo(&info);
+	info.si_signo	= SIGTRAP;
+	info.si_errno	= 0;
+	info.si_code	= si_code;
+	info.si_addr	= (void __user *)instruction_pointer(regs);
 
 	if (WARN_ON(!user_mode(regs)))
 		return;
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
index 4e6ad355bd05..6b9736c3fb56 100644
--- a/arch/arm64/kernel/efi-entry.S
+++ b/arch/arm64/kernel/efi-entry.S
@@ -96,6 +96,7 @@ ENTRY(entry)
 	mrs	x0, sctlr_el2
 	bic	x0, x0, #1 << 0	// clear SCTLR.M
 	bic	x0, x0, #1 << 2	// clear SCTLR.C
+	pre_disable_mmu_workaround
 	msr	sctlr_el2, x0
 	isb
 	b	2f
@@ -103,6 +104,7 @@ ENTRY(entry)
 	mrs	x0, sctlr_el1
 	bic	x0, x0, #1 << 0	// clear SCTLR.M
 	bic	x0, x0, #1 << 2	// clear SCTLR.C
+	pre_disable_mmu_workaround
 	msr	sctlr_el1, x0
 	isb
 2:
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 82cd07592519..f85ac58d08a3 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -48,7 +48,9 @@ static __init pteval_t create_mapping_protection(efi_memory_desc_t *md)
 		return pgprot_val(PAGE_KERNEL_ROX);
 
 	/* RW- */
-	if (attr & EFI_MEMORY_XP || type != EFI_RUNTIME_SERVICES_CODE)
+	if (((attr & (EFI_MEMORY_RP | EFI_MEMORY_WP | EFI_MEMORY_XP)) ==
+	     EFI_MEMORY_XP) ||
+	    type != EFI_RUNTIME_SERVICES_CODE)
 		return pgprot_val(PAGE_KERNEL);
 
 	/* RWX */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 6d14b8f29b5f..b34e717d7597 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -28,6 +28,8 @@
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/irq.h>
+#include <asm/memory.h>
+#include <asm/mmu.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
@@ -69,8 +71,21 @@
 #define BAD_FIQ		2
 #define BAD_ERROR	3
 
-	.macro kernel_ventry	label
+	.macro kernel_ventry, el, label, regsize = 64
 	.align 7
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+alternative_if ARM64_UNMAP_KERNEL_AT_EL0
+	.if	\el == 0
+	.if	\regsize == 64
+	mrs	x30, tpidrro_el0
+	msr	tpidrro_el0, xzr
+	.else
+	mov	x30, xzr
+	.endif
+	.endif
+alternative_else_nop_endif
+#endif
+
 	sub	sp, sp, #S_FRAME_SIZE
 #ifdef CONFIG_VMAP_STACK
 	/*
@@ -82,7 +97,7 @@
 	tbnz	x0, #THREAD_SHIFT, 0f
 	sub	x0, sp, x0			// x0'' = sp' - x0' = (sp + x0) - sp = x0
 	sub	sp, sp, x0			// sp'' = sp' - x0 = (sp + x0) - x0 = sp
-	b	\label
+	b	el\()\el\()_\label
 
 0:
 	/*
@@ -114,7 +129,12 @@
 	sub	sp, sp, x0
 	mrs	x0, tpidrro_el0
 #endif
-	b	\label
+	b	el\()\el\()_\label
+	.endm
+
+	.macro tramp_alias, dst, sym
+	mov_q	\dst, TRAMP_VALIAS
+	add	\dst, \dst, #(\sym - .entry.tramp.text)
 	.endm
 
 	.macro	kernel_entry, el, regsize = 64
@@ -185,7 +205,7 @@ alternative_else_nop_endif
 
 	.if	\el != 0
 	mrs	x21, ttbr0_el1
-	tst	x21, #0xffff << 48		// Check for the reserved ASID
+	tst	x21, #TTBR_ASID_MASK		// Check for the reserved ASID
 	orr	x23, x23, #PSR_PAN_BIT		// Set the emulated PAN in the saved SPSR
 	b.eq	1f				// TTBR0 access already disabled
 	and	x23, x23, #~PSR_PAN_BIT		// Clear the emulated PAN in the saved SPSR
@@ -248,7 +268,7 @@ alternative_else_nop_endif
 	tbnz	x22, #22, 1f			// Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set
 	.endif
 
-	__uaccess_ttbr0_enable x0
+	__uaccess_ttbr0_enable x0, x1
 
 	.if	\el == 0
 	/*
@@ -257,7 +277,7 @@ alternative_else_nop_endif
 	 * Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache
 	 * corruption).
 	 */
-	post_ttbr0_update_workaround
+	bl	post_ttbr_update_workaround
 	.endif
 1:
 	.if	\el != 0
@@ -269,18 +289,20 @@ alternative_else_nop_endif
 	.if	\el == 0
 	ldr	x23, [sp, #S_SP]		// load return stack pointer
 	msr	sp_el0, x23
+	tst	x22, #PSR_MODE32_BIT		// native task?
+	b.eq	3f
+
 #ifdef CONFIG_ARM64_ERRATUM_845719
 alternative_if ARM64_WORKAROUND_845719
-	tbz	x22, #4, 1f
 #ifdef CONFIG_PID_IN_CONTEXTIDR
 	mrs	x29, contextidr_el1
 	msr	contextidr_el1, x29
 #else
 	msr contextidr_el1, xzr
 #endif
-1:
 alternative_else_nop_endif
 #endif
+3:
 	.endif
 
 	msr	elr_el1, x21			// set up the return data
@@ -302,7 +324,21 @@ alternative_else_nop_endif
 	ldp	x28, x29, [sp, #16 * 14]
 	ldr	lr, [sp, #S_LR]
 	add	sp, sp, #S_FRAME_SIZE		// restore sp
-	eret					// return to kernel
+
+	.if	\el == 0
+alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	bne	4f
+	msr	far_el1, x30
+	tramp_alias	x30, tramp_exit_native
+	br	x30
+4:
+	tramp_alias	x30, tramp_exit_compat
+	br	x30
+#endif
+	.else
+	eret
+	.endif
 	.endm
 
 	.macro	irq_stack_entry
@@ -367,31 +403,31 @@ tsk	.req	x28		// current thread_info
 
 	.align	11
 ENTRY(vectors)
-	kernel_ventry	el1_sync_invalid		// Synchronous EL1t
-	kernel_ventry	el1_irq_invalid			// IRQ EL1t
-	kernel_ventry	el1_fiq_invalid			// FIQ EL1t
-	kernel_ventry	el1_error_invalid		// Error EL1t
+	kernel_ventry	1, sync_invalid			// Synchronous EL1t
+	kernel_ventry	1, irq_invalid			// IRQ EL1t
+	kernel_ventry	1, fiq_invalid			// FIQ EL1t
+	kernel_ventry	1, error_invalid		// Error EL1t
 
-	kernel_ventry	el1_sync			// Synchronous EL1h
-	kernel_ventry	el1_irq				// IRQ EL1h
-	kernel_ventry	el1_fiq_invalid			// FIQ EL1h
-	kernel_ventry	el1_error			// Error EL1h
+	kernel_ventry	1, sync				// Synchronous EL1h
+	kernel_ventry	1, irq				// IRQ EL1h
+	kernel_ventry	1, fiq_invalid			// FIQ EL1h
+	kernel_ventry	1, error			// Error EL1h
 
-	kernel_ventry	el0_sync			// Synchronous 64-bit EL0
-	kernel_ventry	el0_irq				// IRQ 64-bit EL0
-	kernel_ventry	el0_fiq_invalid			// FIQ 64-bit EL0
-	kernel_ventry	el0_error			// Error 64-bit EL0
+	kernel_ventry	0, sync				// Synchronous 64-bit EL0
+	kernel_ventry	0, irq				// IRQ 64-bit EL0
+	kernel_ventry	0, fiq_invalid			// FIQ 64-bit EL0
+	kernel_ventry	0, error			// Error 64-bit EL0
 
 #ifdef CONFIG_COMPAT
-	kernel_ventry	el0_sync_compat			// Synchronous 32-bit EL0
-	kernel_ventry	el0_irq_compat			// IRQ 32-bit EL0
-	kernel_ventry	el0_fiq_invalid_compat		// FIQ 32-bit EL0
-	kernel_ventry	el0_error_compat		// Error 32-bit EL0
+	kernel_ventry	0, sync_compat, 32		// Synchronous 32-bit EL0
+	kernel_ventry	0, irq_compat, 32		// IRQ 32-bit EL0
+	kernel_ventry	0, fiq_invalid_compat, 32	// FIQ 32-bit EL0
+	kernel_ventry	0, error_compat, 32		// Error 32-bit EL0
 #else
-	kernel_ventry	el0_sync_invalid		// Synchronous 32-bit EL0
-	kernel_ventry	el0_irq_invalid			// IRQ 32-bit EL0
-	kernel_ventry	el0_fiq_invalid			// FIQ 32-bit EL0
-	kernel_ventry	el0_error_invalid		// Error 32-bit EL0
+	kernel_ventry	0, sync_invalid, 32		// Synchronous 32-bit EL0
+	kernel_ventry	0, irq_invalid, 32		// IRQ 32-bit EL0
+	kernel_ventry	0, fiq_invalid, 32		// FIQ 32-bit EL0
+	kernel_ventry	0, error_invalid, 32		// Error 32-bit EL0
 #endif
 END(vectors)
 
@@ -685,12 +721,15 @@ el0_ia:
 	 * Instruction abort handling
 	 */
 	mrs	x26, far_el1
-	enable_daif
+	enable_da_f
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_off
+#endif
 	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
-	bl	do_mem_abort
+	bl	do_el0_ia_bp_hardening
 	b	ret_to_user
 el0_fpsimd_acc:
 	/*
@@ -943,6 +982,124 @@ __ni_sys_trace:
 
 	.popsection				// .entry.text
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+/*
+ * Exception vectors trampoline.
+ */
+	.pushsection ".entry.tramp.text", "ax"
+
+	.macro tramp_map_kernel, tmp
+	mrs	\tmp, ttbr1_el1
+	add	\tmp, \tmp, #(PAGE_SIZE + RESERVED_TTBR0_SIZE)
+	bic	\tmp, \tmp, #USER_ASID_FLAG
+	msr	ttbr1_el1, \tmp
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
+alternative_if ARM64_WORKAROUND_QCOM_FALKOR_E1003
+	/* ASID already in \tmp[63:48] */
+	movk	\tmp, #:abs_g2_nc:(TRAMP_VALIAS >> 12)
+	movk	\tmp, #:abs_g1_nc:(TRAMP_VALIAS >> 12)
+	/* 2MB boundary containing the vectors, so we nobble the walk cache */
+	movk	\tmp, #:abs_g0_nc:((TRAMP_VALIAS & ~(SZ_2M - 1)) >> 12)
+	isb
+	tlbi	vae1, \tmp
+	dsb	nsh
+alternative_else_nop_endif
+#endif /* CONFIG_QCOM_FALKOR_ERRATUM_1003 */
+	.endm
+
+	.macro tramp_unmap_kernel, tmp
+	mrs	\tmp, ttbr1_el1
+	sub	\tmp, \tmp, #(PAGE_SIZE + RESERVED_TTBR0_SIZE)
+	orr	\tmp, \tmp, #USER_ASID_FLAG
+	msr	ttbr1_el1, \tmp
+	/*
+	 * We avoid running the post_ttbr_update_workaround here because the
+	 * user and kernel ASIDs don't have conflicting mappings, so any
+	 * "blessing" as described in:
+	 *
+	 *   http://lkml.kernel.org/r/56BB848A.6060603@caviumnetworks.com
+	 *
+	 * will not hurt correctness. Whilst this may partially defeat the
+	 * point of using split ASIDs in the first place, it avoids
+	 * the hit of invalidating the entire I-cache on every return to
+	 * userspace.
+	 */
+	.endm
+
+	.macro tramp_ventry, regsize = 64
+	.align	7
+1:
+	.if	\regsize == 64
+	msr	tpidrro_el0, x30	// Restored in kernel_ventry
+	.endif
+	/*
+	 * Defend against branch aliasing attacks by pushing a dummy
+	 * entry onto the return stack and using a RET instruction to
+	 * enter the full-fat kernel vectors.
+	 */
+	bl	2f
+	b	.
+2:
+	tramp_map_kernel	x30
+#ifdef CONFIG_RANDOMIZE_BASE
+	adr	x30, tramp_vectors + PAGE_SIZE
+alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003
+	ldr	x30, [x30]
+#else
+	ldr	x30, =vectors
+#endif
+	prfm	plil1strm, [x30, #(1b - tramp_vectors)]
+	msr	vbar_el1, x30
+	add	x30, x30, #(1b - tramp_vectors)
+	isb
+	ret
+	.endm
+
+	.macro tramp_exit, regsize = 64
+	adr	x30, tramp_vectors
+	msr	vbar_el1, x30
+	tramp_unmap_kernel	x30
+	.if	\regsize == 64
+	mrs	x30, far_el1
+	.endif
+	eret
+	.endm
+
+	.align	11
+ENTRY(tramp_vectors)
+	.space	0x400
+
+	tramp_ventry
+	tramp_ventry
+	tramp_ventry
+	tramp_ventry
+
+	tramp_ventry	32
+	tramp_ventry	32
+	tramp_ventry	32
+	tramp_ventry	32
+END(tramp_vectors)
+
+ENTRY(tramp_exit_native)
+	tramp_exit
+END(tramp_exit_native)
+
+ENTRY(tramp_exit_compat)
+	tramp_exit	32
+END(tramp_exit_compat)
+
+	.ltorg
+	.popsection				// .entry.tramp.text
+#ifdef CONFIG_RANDOMIZE_BASE
+	.pushsection ".rodata", "a"
+	.align PAGE_SHIFT
+	.globl	__entry_tramp_data_start
+__entry_tramp_data_start:
+	.quad	vectors
+	.popsection				// .rodata
+#endif /* CONFIG_RANDOMIZE_BASE */
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+
 /*
  * Special system call wrappers.
  */
@@ -996,3 +1153,180 @@ ENTRY(ret_from_fork)
 	b	ret_to_user
 ENDPROC(ret_from_fork)
 NOKPROBE(ret_from_fork)
+
+#ifdef CONFIG_ARM_SDE_INTERFACE
+
+#include <asm/sdei.h>
+#include <uapi/linux/arm_sdei.h>
+
+.macro sdei_handler_exit exit_mode
+	/* On success, this call never returns... */
+	cmp	\exit_mode, #SDEI_EXIT_SMC
+	b.ne	99f
+	smc	#0
+	b	.
+99:	hvc	#0
+	b	.
+.endm
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+/*
+ * The regular SDEI entry point may have been unmapped along with the rest of
+ * the kernel. This trampoline restores the kernel mapping to make the x1 memory
+ * argument accessible.
+ *
+ * This clobbers x4, __sdei_handler() will restore this from firmware's
+ * copy.
+ */
+.ltorg
+.pushsection ".entry.tramp.text", "ax"
+ENTRY(__sdei_asm_entry_trampoline)
+	mrs	x4, ttbr1_el1
+	tbz	x4, #USER_ASID_BIT, 1f
+
+	tramp_map_kernel tmp=x4
+	isb
+	mov	x4, xzr
+
+	/*
+	 * Use reg->interrupted_regs.addr_limit to remember whether to unmap
+	 * the kernel on exit.
+	 */
+1:	str	x4, [x1, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)]
+
+#ifdef CONFIG_RANDOMIZE_BASE
+	adr	x4, tramp_vectors + PAGE_SIZE
+	add	x4, x4, #:lo12:__sdei_asm_trampoline_next_handler
+	ldr	x4, [x4]
+#else
+	ldr	x4, =__sdei_asm_handler
+#endif
+	br	x4
+ENDPROC(__sdei_asm_entry_trampoline)
+NOKPROBE(__sdei_asm_entry_trampoline)
+
+/*
+ * Make the exit call and restore the original ttbr1_el1
+ *
+ * x0 & x1: setup for the exit API call
+ * x2: exit_mode
+ * x4: struct sdei_registered_event argument from registration time.
+ */
+ENTRY(__sdei_asm_exit_trampoline)
+	ldr	x4, [x4, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)]
+	cbnz	x4, 1f
+
+	tramp_unmap_kernel	tmp=x4
+
+1:	sdei_handler_exit exit_mode=x2
+ENDPROC(__sdei_asm_exit_trampoline)
+NOKPROBE(__sdei_asm_exit_trampoline)
+	.ltorg
+.popsection		// .entry.tramp.text
+#ifdef CONFIG_RANDOMIZE_BASE
+.pushsection ".rodata", "a"
+__sdei_asm_trampoline_next_handler:
+	.quad	__sdei_asm_handler
+.popsection		// .rodata
+#endif /* CONFIG_RANDOMIZE_BASE */
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+
+/*
+ * Software Delegated Exception entry point.
+ *
+ * x0: Event number
+ * x1: struct sdei_registered_event argument from registration time.
+ * x2: interrupted PC
+ * x3: interrupted PSTATE
+ * x4: maybe clobbered by the trampoline
+ *
+ * Firmware has preserved x0->x17 for us, we must save/restore the rest to
+ * follow SMC-CC. We save (or retrieve) all the registers as the handler may
+ * want them.
+ */
+ENTRY(__sdei_asm_handler)
+	stp     x2, x3, [x1, #SDEI_EVENT_INTREGS + S_PC]
+	stp     x4, x5, [x1, #SDEI_EVENT_INTREGS + 16 * 2]
+	stp     x6, x7, [x1, #SDEI_EVENT_INTREGS + 16 * 3]
+	stp     x8, x9, [x1, #SDEI_EVENT_INTREGS + 16 * 4]
+	stp     x10, x11, [x1, #SDEI_EVENT_INTREGS + 16 * 5]
+	stp     x12, x13, [x1, #SDEI_EVENT_INTREGS + 16 * 6]
+	stp     x14, x15, [x1, #SDEI_EVENT_INTREGS + 16 * 7]
+	stp     x16, x17, [x1, #SDEI_EVENT_INTREGS + 16 * 8]
+	stp     x18, x19, [x1, #SDEI_EVENT_INTREGS + 16 * 9]
+	stp     x20, x21, [x1, #SDEI_EVENT_INTREGS + 16 * 10]
+	stp     x22, x23, [x1, #SDEI_EVENT_INTREGS + 16 * 11]
+	stp     x24, x25, [x1, #SDEI_EVENT_INTREGS + 16 * 12]
+	stp     x26, x27, [x1, #SDEI_EVENT_INTREGS + 16 * 13]
+	stp     x28, x29, [x1, #SDEI_EVENT_INTREGS + 16 * 14]
+	mov	x4, sp
+	stp     lr, x4, [x1, #SDEI_EVENT_INTREGS + S_LR]
+
+	mov	x19, x1
+
+#ifdef CONFIG_VMAP_STACK
+	/*
+	 * entry.S may have been using sp as a scratch register, find whether
+	 * this is a normal or critical event and switch to the appropriate
+	 * stack for this CPU.
+	 */
+	ldrb	w4, [x19, #SDEI_EVENT_PRIORITY]
+	cbnz	w4, 1f
+	ldr_this_cpu dst=x5, sym=sdei_stack_normal_ptr, tmp=x6
+	b	2f
+1:	ldr_this_cpu dst=x5, sym=sdei_stack_critical_ptr, tmp=x6
+2:	mov	x6, #SDEI_STACK_SIZE
+	add	x5, x5, x6
+	mov	sp, x5
+#endif
+
+	/*
+	 * We may have interrupted userspace, or a guest, or exit-from or
+	 * return-to either of these. We can't trust sp_el0, restore it.
+	 */
+	mrs	x28, sp_el0
+	ldr_this_cpu	dst=x0, sym=__entry_task, tmp=x1
+	msr	sp_el0, x0
+
+	/* If we interrupted the kernel point to the previous stack/frame. */
+	and     x0, x3, #0xc
+	mrs     x1, CurrentEL
+	cmp     x0, x1
+	csel	x29, x29, xzr, eq	// fp, or zero
+	csel	x4, x2, xzr, eq		// elr, or zero
+
+	stp	x29, x4, [sp, #-16]!
+	mov	x29, sp
+
+	add	x0, x19, #SDEI_EVENT_INTREGS
+	mov	x1, x19
+	bl	__sdei_handler
+
+	msr	sp_el0, x28
+	/* restore regs >x17 that we clobbered */
+	mov	x4, x19         // keep x4 for __sdei_asm_exit_trampoline
+	ldp	x28, x29, [x4, #SDEI_EVENT_INTREGS + 16 * 14]
+	ldp	x18, x19, [x4, #SDEI_EVENT_INTREGS + 16 * 9]
+	ldp	lr, x1, [x4, #SDEI_EVENT_INTREGS + S_LR]
+	mov	sp, x1
+
+	mov	x1, x0			// address to complete_and_resume
+	/* x0 = (x0 <= 1) ? EVENT_COMPLETE:EVENT_COMPLETE_AND_RESUME */
+	cmp	x0, #1
+	mov_q	x2, SDEI_1_0_FN_SDEI_EVENT_COMPLETE
+	mov_q	x3, SDEI_1_0_FN_SDEI_EVENT_COMPLETE_AND_RESUME
+	csel	x0, x2, x3, ls
+
+	ldr_l	x2, sdei_exit_mode
+
+alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
+	sdei_handler_exit exit_mode=x2
+alternative_else_nop_endif
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	tramp_alias	dst=x5, sym=__sdei_asm_exit_trampoline
+	br	x5
+#endif
+ENDPROC(__sdei_asm_handler)
+NOKPROBE(__sdei_asm_handler)
+#endif /* CONFIG_ARM_SDE_INTERFACE */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 143b3e72c25e..e7226c4c7493 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -114,7 +114,12 @@
  *   returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
  *   whatever is in the FPSIMD registers is not saved to memory, but discarded.
  */
-static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state);
+struct fpsimd_last_state_struct {
+	struct fpsimd_state *st;
+	bool sve_in_use;
+};
+
+static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
 
 /* Default VL for tasks that don't set it explicitly: */
 static int sve_default_vl = -1;
@@ -862,7 +867,7 @@ asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 {
 	siginfo_t info;
-	unsigned int si_code = 0;
+	unsigned int si_code = FPE_FIXME;
 
 	if (esr & FPEXC_IOF)
 		si_code = FPE_FLTINV;
@@ -905,7 +910,7 @@ void fpsimd_thread_switch(struct task_struct *next)
 		 */
 		struct fpsimd_state *st = &next->thread.fpsimd_state;
 
-		if (__this_cpu_read(fpsimd_last_state) == st
+		if (__this_cpu_read(fpsimd_last_state.st) == st
 		    && st->cpu == smp_processor_id())
 			clear_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE);
 		else
@@ -992,6 +997,21 @@ void fpsimd_signal_preserve_current_state(void)
 }
 
 /*
+ * Associate current's FPSIMD context with this cpu
+ * Preemption must be disabled when calling this function.
+ */
+static void fpsimd_bind_to_cpu(void)
+{
+	struct fpsimd_last_state_struct *last =
+		this_cpu_ptr(&fpsimd_last_state);
+	struct fpsimd_state *st = &current->thread.fpsimd_state;
+
+	last->st = st;
+	last->sve_in_use = test_thread_flag(TIF_SVE);
+	st->cpu = smp_processor_id();
+}
+
+/*
  * Load the userland FPSIMD state of 'current' from memory, but only if the
  * FPSIMD state already held in the registers is /not/ the most recent FPSIMD
  * state of 'current'
@@ -1004,11 +1024,8 @@ void fpsimd_restore_current_state(void)
 	local_bh_disable();
 
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
-		struct fpsimd_state *st = &current->thread.fpsimd_state;
-
 		task_fpsimd_load();
-		__this_cpu_write(fpsimd_last_state, st);
-		st->cpu = smp_processor_id();
+		fpsimd_bind_to_cpu();
 	}
 
 	local_bh_enable();
@@ -1019,25 +1036,21 @@ void fpsimd_restore_current_state(void)
  * flag that indicates that the FPSIMD register contents are the most recent
  * FPSIMD state of 'current'
  */
-void fpsimd_update_current_state(struct fpsimd_state *state)
+void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 {
 	if (!system_supports_fpsimd())
 		return;
 
 	local_bh_disable();
 
-	if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
-		current->thread.fpsimd_state = *state;
+	current->thread.fpsimd_state.user_fpsimd = *state;
+	if (system_supports_sve() && test_thread_flag(TIF_SVE))
 		fpsimd_to_sve(current);
-	}
-	task_fpsimd_load();
 
-	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
-		struct fpsimd_state *st = &current->thread.fpsimd_state;
+	task_fpsimd_load();
 
-		__this_cpu_write(fpsimd_last_state, st);
-		st->cpu = smp_processor_id();
-	}
+	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE))
+		fpsimd_bind_to_cpu();
 
 	local_bh_enable();
 }
@@ -1052,7 +1065,7 @@ void fpsimd_flush_task_state(struct task_struct *t)
 
 static inline void fpsimd_flush_cpu_state(void)
 {
-	__this_cpu_write(fpsimd_last_state, NULL);
+	__this_cpu_write(fpsimd_last_state.st, NULL);
 }
 
 /*
@@ -1065,14 +1078,10 @@ static inline void fpsimd_flush_cpu_state(void)
 #ifdef CONFIG_ARM64_SVE
 void sve_flush_cpu_state(void)
 {
-	struct fpsimd_state *const fpstate = __this_cpu_read(fpsimd_last_state);
-	struct task_struct *tsk;
-
-	if (!fpstate)
-		return;
+	struct fpsimd_last_state_struct const *last =
+		this_cpu_ptr(&fpsimd_last_state);
 
-	tsk = container_of(fpstate, struct task_struct, thread.fpsimd_state);
-	if (test_tsk_thread_flag(tsk, TIF_SVE))
+	if (last->st && last->sve_in_use)
 		fpsimd_flush_cpu_state();
 }
 #endif /* CONFIG_ARM64_SVE */
@@ -1267,7 +1276,7 @@ static inline void fpsimd_pm_init(void) { }
 #ifdef CONFIG_HOTPLUG_CPU
 static int fpsimd_cpu_dead(unsigned int cpu)
 {
-	per_cpu(fpsimd_last_state, cpu) = NULL;
+	per_cpu(fpsimd_last_state.st, cpu) = NULL;
 	return 0;
 }
 
diff --git a/arch/arm64/kernel/ftrace-mod.S b/arch/arm64/kernel/ftrace-mod.S
deleted file mode 100644
index 00c4025be4ff..000000000000
--- a/arch/arm64/kernel/ftrace-mod.S
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
-	.section	".text.ftrace_trampoline", "ax"
-	.align		3
-0:	.quad		0
-__ftrace_trampoline:
-	ldr		x16, 0b
-	br		x16
-ENDPROC(__ftrace_trampoline)
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index c13b1fca0e5b..50986e388d2b 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -76,7 +76,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
 #ifdef CONFIG_ARM64_MODULE_PLTS
-		unsigned long *trampoline;
+		struct plt_entry trampoline;
 		struct module *mod;
 
 		/*
@@ -104,22 +104,24 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		 * is added in the future, but for now, the pr_err() below
 		 * deals with a theoretical issue only.
 		 */
-		trampoline = (unsigned long *)mod->arch.ftrace_trampoline;
-		if (trampoline[0] != addr) {
-			if (trampoline[0] != 0) {
+		trampoline = get_plt_entry(addr);
+		if (!plt_entries_equal(mod->arch.ftrace_trampoline,
+				       &trampoline)) {
+			if (!plt_entries_equal(mod->arch.ftrace_trampoline,
+					       &(struct plt_entry){})) {
 				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
 				return -EINVAL;
 			}
 
 			/* point the trampoline to our ftrace entry point */
 			module_disable_ro(mod);
-			trampoline[0] = addr;
+			*mod->arch.ftrace_trampoline = trampoline;
 			module_enable_ro(mod, true);
 
 			/* update trampoline before patching in the branch */
 			smp_wmb();
 		}
-		addr = (unsigned long)&trampoline[1];
+		addr = (unsigned long)(void *)mod->arch.ftrace_trampoline;
 #else /* CONFIG_ARM64_MODULE_PLTS */
 		return -EINVAL;
 #endif /* CONFIG_ARM64_MODULE_PLTS */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 67e86a0f57ac..ba3ab04788dc 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -148,6 +148,26 @@ preserve_boot_args:
 ENDPROC(preserve_boot_args)
 
 /*
+ * Macro to arrange a physical address in a page table entry, taking care of
+ * 52-bit addresses.
+ *
+ * Preserves:	phys
+ * Returns:	pte
+ */
+	.macro	phys_to_pte, phys, pte
+#ifdef CONFIG_ARM64_PA_BITS_52
+	/*
+	 * We assume \phys is 64K aligned and this is guaranteed by only
+	 * supporting this configuration with 64K pages.
+	 */
+	orr	\pte, \phys, \phys, lsr #36
+	and	\pte, \pte, #PTE_ADDR_MASK
+#else
+	mov	\pte, \phys
+#endif
+	.endm
+
+/*
  * Macro to create a table entry to the next page.
  *
  *	tbl:	page table address
@@ -156,54 +176,124 @@ ENDPROC(preserve_boot_args)
  *	ptrs:	#imm pointers per table page
  *
  * Preserves:	virt
- * Corrupts:	tmp1, tmp2
+ * Corrupts:	ptrs, tmp1, tmp2
  * Returns:	tbl -> next level table page address
  */
 	.macro	create_table_entry, tbl, virt, shift, ptrs, tmp1, tmp2
-	lsr	\tmp1, \virt, #\shift
-	and	\tmp1, \tmp1, #\ptrs - 1	// table index
-	add	\tmp2, \tbl, #PAGE_SIZE
+	add	\tmp1, \tbl, #PAGE_SIZE
+	phys_to_pte \tmp1, \tmp2
 	orr	\tmp2, \tmp2, #PMD_TYPE_TABLE	// address of next table and entry type
+	lsr	\tmp1, \virt, #\shift
+	sub	\ptrs, \ptrs, #1
+	and	\tmp1, \tmp1, \ptrs		// table index
 	str	\tmp2, [\tbl, \tmp1, lsl #3]
 	add	\tbl, \tbl, #PAGE_SIZE		// next level table page
 	.endm
 
 /*
- * Macro to populate the PGD (and possibily PUD) for the corresponding
- * block entry in the next level (tbl) for the given virtual address.
+ * Macro to populate page table entries, these entries can be pointers to the next level
+ * or last level entries pointing to physical memory.
+ *
+ *	tbl:	page table address
+ *	rtbl:	pointer to page table or physical memory
+ *	index:	start index to write
+ *	eindex:	end index to write - [index, eindex] written to
+ *	flags:	flags for pagetable entry to or in
+ *	inc:	increment to rtbl between each entry
+ *	tmp1:	temporary variable
  *
- * Preserves:	tbl, next, virt
- * Corrupts:	tmp1, tmp2
+ * Preserves:	tbl, eindex, flags, inc
+ * Corrupts:	index, tmp1
+ * Returns:	rtbl
  */
-	.macro	create_pgd_entry, tbl, virt, tmp1, tmp2
-	create_table_entry \tbl, \virt, PGDIR_SHIFT, PTRS_PER_PGD, \tmp1, \tmp2
-#if SWAPPER_PGTABLE_LEVELS > 3
-	create_table_entry \tbl, \virt, PUD_SHIFT, PTRS_PER_PUD, \tmp1, \tmp2
-#endif
-#if SWAPPER_PGTABLE_LEVELS > 2
-	create_table_entry \tbl, \virt, SWAPPER_TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2
-#endif
+	.macro populate_entries, tbl, rtbl, index, eindex, flags, inc, tmp1
+.Lpe\@:	phys_to_pte \rtbl, \tmp1
+	orr	\tmp1, \tmp1, \flags	// tmp1 = table entry
+	str	\tmp1, [\tbl, \index, lsl #3]
+	add	\rtbl, \rtbl, \inc	// rtbl = pa next level
+	add	\index, \index, #1
+	cmp	\index, \eindex
+	b.ls	.Lpe\@
+	.endm
+
+/*
+ * Compute indices of table entries from virtual address range. If multiple entries
+ * were needed in the previous page table level then the next page table level is assumed
+ * to be composed of multiple pages. (This effectively scales the end index).
+ *
+ *	vstart:	virtual address of start of range
+ *	vend:	virtual address of end of range
+ *	shift:	shift used to transform virtual address into index
+ *	ptrs:	number of entries in page table
+ *	istart:	index in table corresponding to vstart
+ *	iend:	index in table corresponding to vend
+ *	count:	On entry: how many extra entries were required in previous level, scales
+ *			  our end index.
+ *		On exit: returns how many extra entries required for next page table level
+ *
+ * Preserves:	vstart, vend, shift, ptrs
+ * Returns:	istart, iend, count
+ */
+	.macro compute_indices, vstart, vend, shift, ptrs, istart, iend, count
+	lsr	\iend, \vend, \shift
+	mov	\istart, \ptrs
+	sub	\istart, \istart, #1
+	and	\iend, \iend, \istart	// iend = (vend >> shift) & (ptrs - 1)
+	mov	\istart, \ptrs
+	mul	\istart, \istart, \count
+	add	\iend, \iend, \istart	// iend += (count - 1) * ptrs
+					// our entries span multiple tables
+
+	lsr	\istart, \vstart, \shift
+	mov	\count, \ptrs
+	sub	\count, \count, #1
+	and	\istart, \istart, \count
+
+	sub	\count, \iend, \istart
 	.endm
 
 /*
- * Macro to populate block entries in the page table for the start..end
- * virtual range (inclusive).
+ * Map memory for specified virtual address range. Each level of page table needed supports
+ * multiple entries. If a level requires n entries the next page table level is assumed to be
+ * formed from n pages.
+ *
+ *	tbl:	location of page table
+ *	rtbl:	address to be used for first level page table entry (typically tbl + PAGE_SIZE)
+ *	vstart:	start address to map
+ *	vend:	end address to map - we map [vstart, vend]
+ *	flags:	flags to use to map last level entries
+ *	phys:	physical address corresponding to vstart - physical memory is contiguous
+ *	pgds:	the number of pgd entries
  *
- * Preserves:	tbl, flags
- * Corrupts:	phys, start, end, pstate
+ * Temporaries:	istart, iend, tmp, count, sv - these need to be different registers
+ * Preserves:	vstart, vend, flags
+ * Corrupts:	tbl, rtbl, istart, iend, tmp, count, sv
  */
-	.macro	create_block_map, tbl, flags, phys, start, end
-	lsr	\phys, \phys, #SWAPPER_BLOCK_SHIFT
-	lsr	\start, \start, #SWAPPER_BLOCK_SHIFT
-	and	\start, \start, #PTRS_PER_PTE - 1	// table index
-	orr	\phys, \flags, \phys, lsl #SWAPPER_BLOCK_SHIFT	// table entry
-	lsr	\end, \end, #SWAPPER_BLOCK_SHIFT
-	and	\end, \end, #PTRS_PER_PTE - 1		// table end index
-9999:	str	\phys, [\tbl, \start, lsl #3]		// store the entry
-	add	\start, \start, #1			// next entry
-	add	\phys, \phys, #SWAPPER_BLOCK_SIZE		// next block
-	cmp	\start, \end
-	b.ls	9999b
+	.macro map_memory, tbl, rtbl, vstart, vend, flags, phys, pgds, istart, iend, tmp, count, sv
+	add \rtbl, \tbl, #PAGE_SIZE
+	mov \sv, \rtbl
+	mov \count, #0
+	compute_indices \vstart, \vend, #PGDIR_SHIFT, \pgds, \istart, \iend, \count
+	populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp
+	mov \tbl, \sv
+	mov \sv, \rtbl
+
+#if SWAPPER_PGTABLE_LEVELS > 3
+	compute_indices \vstart, \vend, #PUD_SHIFT, #PTRS_PER_PUD, \istart, \iend, \count
+	populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp
+	mov \tbl, \sv
+	mov \sv, \rtbl
+#endif
+
+#if SWAPPER_PGTABLE_LEVELS > 2
+	compute_indices \vstart, \vend, #SWAPPER_TABLE_SHIFT, #PTRS_PER_PMD, \istart, \iend, \count
+	populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp
+	mov \tbl, \sv
+#endif
+
+	compute_indices \vstart, \vend, #SWAPPER_BLOCK_SHIFT, #PTRS_PER_PTE, \istart, \iend, \count
+	bic \count, \phys, #SWAPPER_BLOCK_SIZE - 1
+	populate_entries \tbl, \count, \istart, \iend, \flags, #SWAPPER_BLOCK_SIZE, \tmp
 	.endm
 
 /*
@@ -221,14 +311,16 @@ __create_page_tables:
 	 * dirty cache lines being evicted.
 	 */
 	adrp	x0, idmap_pg_dir
-	ldr	x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+	adrp	x1, swapper_pg_end
+	sub	x1, x1, x0
 	bl	__inval_dcache_area
 
 	/*
 	 * Clear the idmap and swapper page tables.
 	 */
 	adrp	x0, idmap_pg_dir
-	ldr	x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+	adrp	x1, swapper_pg_end
+	sub	x1, x1, x0
 1:	stp	xzr, xzr, [x0], #16
 	stp	xzr, xzr, [x0], #16
 	stp	xzr, xzr, [x0], #16
@@ -244,26 +336,13 @@ __create_page_tables:
 	adrp	x0, idmap_pg_dir
 	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
 
-#ifndef CONFIG_ARM64_VA_BITS_48
-#define EXTRA_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
-#define EXTRA_PTRS	(1 << (48 - EXTRA_SHIFT))
-
-	/*
-	 * If VA_BITS < 48, it may be too small to allow for an ID mapping to be
-	 * created that covers system RAM if that is located sufficiently high
-	 * in the physical address space. So for the ID map, use an extended
-	 * virtual range in that case, by configuring an additional translation
-	 * level.
-	 * First, we have to verify our assumption that the current value of
-	 * VA_BITS was chosen such that all translation levels are fully
-	 * utilised, and that lowering T0SZ will always result in an additional
-	 * translation level to be configured.
-	 */
-#if VA_BITS != EXTRA_SHIFT
-#error "Mismatch between VA_BITS and page size/number of translation levels"
-#endif
-
 	/*
+	 * VA_BITS may be too small to allow for an ID mapping to be created
+	 * that covers system RAM if that is located sufficiently high in the
+	 * physical address space. So for the ID map, use an extended virtual
+	 * range in that case, and configure an additional translation level
+	 * if needed.
+	 *
 	 * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
 	 * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
 	 * this number conveniently equals the number of leading zeroes in
@@ -272,21 +351,44 @@ __create_page_tables:
 	adrp	x5, __idmap_text_end
 	clz	x5, x5
 	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
-	b.ge	1f			// .. then skip additional level
+	b.ge	1f			// .. then skip VA range extension
 
 	adr_l	x6, idmap_t0sz
 	str	x5, [x6]
 	dmb	sy
 	dc	ivac, x6		// Invalidate potentially stale cache line
 
-	create_table_entry x0, x3, EXTRA_SHIFT, EXTRA_PTRS, x5, x6
-1:
+#if (VA_BITS < 48)
+#define EXTRA_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
+#define EXTRA_PTRS	(1 << (PHYS_MASK_SHIFT - EXTRA_SHIFT))
+
+	/*
+	 * If VA_BITS < 48, we have to configure an additional table level.
+	 * First, we have to verify our assumption that the current value of
+	 * VA_BITS was chosen such that all translation levels are fully
+	 * utilised, and that lowering T0SZ will always result in an additional
+	 * translation level to be configured.
+	 */
+#if VA_BITS != EXTRA_SHIFT
+#error "Mismatch between VA_BITS and page size/number of translation levels"
 #endif
 
-	create_pgd_entry x0, x3, x5, x6
+	mov	x4, EXTRA_PTRS
+	create_table_entry x0, x3, EXTRA_SHIFT, x4, x5, x6
+#else
+	/*
+	 * If VA_BITS == 48, we don't have to configure an additional
+	 * translation level, but the top-level table has more entries.
+	 */
+	mov	x4, #1 << (PHYS_MASK_SHIFT - PGDIR_SHIFT)
+	str_l	x4, idmap_ptrs_per_pgd, x5
+#endif
+1:
+	ldr_l	x4, idmap_ptrs_per_pgd
 	mov	x5, x3				// __pa(__idmap_text_start)
 	adr_l	x6, __idmap_text_end		// __pa(__idmap_text_end)
-	create_block_map x0, x7, x3, x5, x6
+
+	map_memory x0, x1, x3, x6, x7, x3, x4, x10, x11, x12, x13, x14
 
 	/*
 	 * Map the kernel image (starting with PHYS_OFFSET).
@@ -294,12 +396,13 @@ __create_page_tables:
 	adrp	x0, swapper_pg_dir
 	mov_q	x5, KIMAGE_VADDR + TEXT_OFFSET	// compile time __va(_text)
 	add	x5, x5, x23			// add KASLR displacement
-	create_pgd_entry x0, x5, x3, x6
+	mov	x4, PTRS_PER_PGD
 	adrp	x6, _end			// runtime __pa(_end)
 	adrp	x3, _text			// runtime __pa(_text)
 	sub	x6, x6, x3			// _end - _text
 	add	x6, x6, x5			// runtime __va(_end)
-	create_block_map x0, x7, x3, x5, x6
+
+	map_memory x0, x1, x5, x6, x7, x3, x4, x10, x11, x12, x13, x14
 
 	/*
 	 * Since the page tables have been populated with non-cacheable
@@ -307,7 +410,8 @@ __create_page_tables:
 	 * tables again to remove any speculatively loaded cache lines.
 	 */
 	adrp	x0, idmap_pg_dir
-	ldr	x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+	adrp	x1, swapper_pg_end
+	sub	x1, x1, x0
 	dmb	sy
 	bl	__inval_dcache_area
 
@@ -388,17 +492,13 @@ ENTRY(el2_setup)
 	mrs	x0, CurrentEL
 	cmp	x0, #CurrentEL_EL2
 	b.eq	1f
-	mrs	x0, sctlr_el1
-CPU_BE(	orr	x0, x0, #(3 << 24)	)	// Set the EE and E0E bits for EL1
-CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
+	mov_q	x0, (SCTLR_EL1_RES1 | ENDIAN_SET_EL1)
 	msr	sctlr_el1, x0
 	mov	w0, #BOOT_CPU_MODE_EL1		// This cpu booted in EL1
 	isb
 	ret
 
-1:	mrs	x0, sctlr_el2
-CPU_BE(	orr	x0, x0, #(1 << 25)	)	// Set the EE bit for EL2
-CPU_LE(	bic	x0, x0, #(1 << 25)	)	// Clear the EE bit for EL2
+1:	mov_q	x0, (SCTLR_EL2_RES1 | ENDIAN_SET_EL2)
 	msr	sctlr_el2, x0
 
 #ifdef CONFIG_ARM64_VHE
@@ -514,10 +614,7 @@ install_el2_stub:
 	 * requires no configuration, and all non-hyp-specific EL2 setup
 	 * will be done via the _EL1 system register aliases in __cpu_setup.
 	 */
-	/* sctlr_el1 */
-	mov	x0, #0x0800			// Set/clear RES{1,0} bits
-CPU_BE(	movk	x0, #0x33d0, lsl #16	)	// Set EE and E0E on BE systems
-CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
+	mov_q	x0, (SCTLR_EL1_RES1 | ENDIAN_SET_EL1)
 	msr	sctlr_el1, x0
 
 	/* Coprocessor traps. */
@@ -679,8 +776,10 @@ ENTRY(__enable_mmu)
 	update_early_cpu_boot_status 0, x1, x2
 	adrp	x1, idmap_pg_dir
 	adrp	x2, swapper_pg_dir
-	msr	ttbr0_el1, x1			// load TTBR0
-	msr	ttbr1_el1, x2			// load TTBR1
+	phys_to_ttbr x1, x3
+	phys_to_ttbr x2, x4
+	msr	ttbr0_el1, x3			// load TTBR0
+	msr	ttbr1_el1, x4			// load TTBR1
 	isb
 	msr	sctlr_el1, x0
 	isb
@@ -750,6 +849,7 @@ __primary_switch:
 	 * to take into account by discarding the current kernel mapping and
 	 * creating a new one.
 	 */
+	pre_disable_mmu_workaround
 	msr	sctlr_el1, x20			// disable the MMU
 	isb
 	bl	__create_page_tables		// recreate kernel mapping
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index e56d848b6466..84f5d52fddda 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -33,12 +33,14 @@
  * Even switching to our copied tables will cause a changed output address at
  * each stage of the walk.
  */
-.macro break_before_make_ttbr_switch zero_page, page_table
-	msr	ttbr1_el1, \zero_page
+.macro break_before_make_ttbr_switch zero_page, page_table, tmp
+	phys_to_ttbr \zero_page, \tmp
+	msr	ttbr1_el1, \tmp
 	isb
 	tlbi	vmalle1
 	dsb	nsh
-	msr	ttbr1_el1, \page_table
+	phys_to_ttbr \page_table, \tmp
+	msr	ttbr1_el1, \tmp
 	isb
 .endm
 
@@ -78,7 +80,7 @@ ENTRY(swsusp_arch_suspend_exit)
 	 * We execute from ttbr0, change ttbr1 to our copied linear map tables
 	 * with a break-before-make via the zero page
 	 */
-	break_before_make_ttbr_switch	x5, x0
+	break_before_make_ttbr_switch	x5, x0, x6
 
 	mov	x21, x1
 	mov	x30, x2
@@ -109,7 +111,7 @@ ENTRY(swsusp_arch_suspend_exit)
 	dsb	ish		/* wait for PoU cleaning to finish */
 
 	/* switch to the restored kernels page tables */
-	break_before_make_ttbr_switch	x25, x21
+	break_before_make_ttbr_switch	x25, x21, x6
 
 	ic	ialluis
 	dsb	ish
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 3009b8b80f08..f20cf7e99249 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -247,8 +247,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	}
 
 	pte = pte_offset_kernel(pmd, dst_addr);
-	set_pte(pte, __pte(virt_to_phys((void *)dst) |
-			 pgprot_val(PAGE_KERNEL_EXEC)));
+	set_pte(pte, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC));
 
 	/*
 	 * Load our new page tables. A strict BBM approach requires that we
@@ -264,7 +263,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	 */
 	cpu_set_reserved_ttbr0();
 	local_flush_tlb_all();
-	write_sysreg(virt_to_phys(pgd), ttbr0_el1);
+	write_sysreg(phys_to_ttbr(virt_to_phys(pgd)), ttbr0_el1);
 	isb();
 
 	*phys_dst_addr = virt_to_phys((void *)dst);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 749f81779420..74bb56f656ef 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -28,6 +28,7 @@
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/smp.h>
+#include <linux/uaccess.h>
 
 #include <asm/compat.h>
 #include <asm/current.h>
@@ -36,7 +37,6 @@
 #include <asm/traps.h>
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
-#include <asm/uaccess.h>
 
 /* Breakpoint currently in use for each BRP. */
 static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 713561e5bcab..60e5fc661f74 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -29,6 +29,7 @@
 #include <linux/irqchip.h>
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
+#include <asm/vmap_stack.h>
 
 unsigned long irq_err_count;
 
@@ -58,17 +59,7 @@ static void init_irq_stacks(void)
 	unsigned long *p;
 
 	for_each_possible_cpu(cpu) {
-		/*
-		* To ensure that VMAP'd stack overflow detection works
-		* correctly, the IRQ stacks need to have the same
-		* alignment as other stacks.
-		*/
-		p = __vmalloc_node_range(IRQ_STACK_SIZE, THREAD_ALIGN,
-					 VMALLOC_START, VMALLOC_END,
-					 THREADINFO_GFP, PAGE_KERNEL,
-					 0, cpu_to_node(cpu),
-					 __builtin_return_address(0));
-
+		p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu));
 		per_cpu(irq_stack_ptr, cpu) = p;
 	}
 }
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index d05dbe658409..ea640f92fe5a 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -11,21 +11,6 @@
 #include <linux/module.h>
 #include <linux/sort.h>
 
-struct plt_entry {
-	/*
-	 * A program that conforms to the AArch64 Procedure Call Standard
-	 * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
-	 * IP1 (x17) may be inserted at any branch instruction that is
-	 * exposed to a relocation that supports long branches. Since that
-	 * is exactly what we are dealing with here, we are free to use x16
-	 * as a scratch register in the PLT veneers.
-	 */
-	__le32	mov0;	/* movn	x16, #0x....			*/
-	__le32	mov1;	/* movk	x16, #0x...., lsl #16		*/
-	__le32	mov2;	/* movk	x16, #0x...., lsl #32		*/
-	__le32	br;	/* br	x16				*/
-};
-
 static bool in_init(const struct module *mod, void *loc)
 {
 	return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size;
@@ -40,33 +25,14 @@ u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
 	int i = pltsec->plt_num_entries;
 	u64 val = sym->st_value + rela->r_addend;
 
-	/*
-	 * MOVK/MOVN/MOVZ opcode:
-	 * +--------+------------+--------+-----------+-------------+---------+
-	 * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
-	 * +--------+------------+--------+-----------+-------------+---------+
-	 *
-	 * Rd     := 0x10 (x16)
-	 * hw     := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32)
-	 * opc    := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ)
-	 * sf     := 1 (64-bit variant)
-	 */
-	plt[i] = (struct plt_entry){
-		cpu_to_le32(0x92800010 | (((~val      ) & 0xffff)) << 5),
-		cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
-		cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
-		cpu_to_le32(0xd61f0200)
-	};
+	plt[i] = get_plt_entry(val);
 
 	/*
 	 * Check if the entry we just created is a duplicate. Given that the
 	 * relocations are sorted, this will be the last entry we allocated.
 	 * (if one exists).
 	 */
-	if (i > 0 &&
-	    plt[i].mov0 == plt[i - 1].mov0 &&
-	    plt[i].mov1 == plt[i - 1].mov1 &&
-	    plt[i].mov2 == plt[i - 1].mov2)
+	if (i > 0 && plt_entries_equal(plt + i, plt + i - 1))
 		return (u64)&plt[i - 1];
 
 	pltsec->plt_num_entries++;
@@ -154,6 +120,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	unsigned long core_plts = 0;
 	unsigned long init_plts = 0;
 	Elf64_Sym *syms = NULL;
+	Elf_Shdr *tramp = NULL;
 	int i;
 
 	/*
@@ -165,6 +132,10 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			mod->arch.core.plt = sechdrs + i;
 		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
 			mod->arch.init.plt = sechdrs + i;
+		else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
+			 !strcmp(secstrings + sechdrs[i].sh_name,
+				 ".text.ftrace_trampoline"))
+			tramp = sechdrs + i;
 		else if (sechdrs[i].sh_type == SHT_SYMTAB)
 			syms = (Elf64_Sym *)sechdrs[i].sh_addr;
 	}
@@ -215,5 +186,12 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	mod->arch.init.plt_num_entries = 0;
 	mod->arch.init.plt_max_entries = init_plts;
 
+	if (tramp) {
+		tramp->sh_type = SHT_NOBITS;
+		tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+		tramp->sh_addralign = __alignof__(struct plt_entry);
+		tramp->sh_size = sizeof(struct plt_entry);
+	}
+
 	return 0;
 }
diff --git a/arch/arm64/kernel/module.lds b/arch/arm64/kernel/module.lds
index f7c9781a9d48..22e36a21c113 100644
--- a/arch/arm64/kernel/module.lds
+++ b/arch/arm64/kernel/module.lds
@@ -1,4 +1,5 @@
 SECTIONS {
 	.plt (NOLOAD) : { BYTE(0) }
 	.init.plt (NOLOAD) : { BYTE(0) }
+	.text.ftrace_trampoline (NOLOAD) : { BYTE(0) }
 }
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 9eaef51f83ff..3affca3dd96a 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -262,12 +262,6 @@ static const unsigned armv8_a73_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 
 	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD,
 	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
-
-	[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
-	[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
-
-	[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
-	[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
 };
 
 static const unsigned armv8_thunder_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index b2adcce7bc18..ad8aeb098b31 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -35,7 +35,6 @@
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/interrupt.h>
-#include <linux/kallsyms.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/elfcore.h>
@@ -221,8 +220,8 @@ void __show_regs(struct pt_regs *regs)
 
 	show_regs_print_info(KERN_DEFAULT);
 	print_pstate(regs);
-	print_symbol("pc : %s\n", regs->pc);
-	print_symbol("lr : %s\n", lr);
+	printk("pc : %pS\n", (void *)regs->pc);
+	printk("lr : %pS\n", (void *)lr);
 	printk("sp : %016llx\n", sp);
 
 	i = top_reg;
@@ -314,6 +313,15 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	clear_tsk_thread_flag(p, TIF_SVE);
 	p->thread.sve_state = NULL;
 
+	/*
+	 * In case p was allocated the same task_struct pointer as some
+	 * other recently-exited task, make sure p is disassociated from
+	 * any cpu that may have run that now-exited task recently.
+	 * Otherwise we could erroneously skip reloading the FPSIMD
+	 * registers for p.
+	 */
+	fpsimd_flush_task_state(p);
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;
@@ -361,16 +369,14 @@ void tls_preserve_current_state(void)
 
 static void tls_thread_switch(struct task_struct *next)
 {
-	unsigned long tpidr, tpidrro;
-
 	tls_preserve_current_state();
 
-	tpidr = *task_user_tls(next);
-	tpidrro = is_compat_thread(task_thread_info(next)) ?
-		  next->thread.tp_value : 0;
+	if (is_compat_thread(task_thread_info(next)))
+		write_sysreg(next->thread.tp_value, tpidrro_el0);
+	else if (!arm64_kernel_unmapped_at_el0())
+		write_sysreg(0, tpidrro_el0);
 
-	write_sysreg(tpidr, tpidr_el0);
-	write_sysreg(tpidrro, tpidrro_el0);
+	write_sysreg(*task_user_tls(next), tpidr_el0);
 }
 
 /* Restore the UAO state depending on next's addr_limit */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 7c44658b316d..6618036ae6d4 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -180,34 +180,34 @@ static void ptrace_hbptriggered(struct perf_event *bp,
 				struct pt_regs *regs)
 {
 	struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
-	siginfo_t info = {
-		.si_signo	= SIGTRAP,
-		.si_errno	= 0,
-		.si_code	= TRAP_HWBKPT,
-		.si_addr	= (void __user *)(bkpt->trigger),
-	};
+	siginfo_t info;
 
-#ifdef CONFIG_COMPAT
-	int i;
+	clear_siginfo(&info);
+	info.si_signo	= SIGTRAP;
+	info.si_errno	= 0;
+	info.si_code	= TRAP_HWBKPT;
+	info.si_addr	= (void __user *)(bkpt->trigger);
 
-	if (!is_compat_task())
-		goto send_sig;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task()) {
+		int si_errno = 0;
+		int i;
 
-	for (i = 0; i < ARM_MAX_BRP; ++i) {
-		if (current->thread.debug.hbp_break[i] == bp) {
-			info.si_errno = (i << 1) + 1;
-			break;
+		for (i = 0; i < ARM_MAX_BRP; ++i) {
+			if (current->thread.debug.hbp_break[i] == bp) {
+				si_errno = (i << 1) + 1;
+				break;
+			}
 		}
-	}
 
-	for (i = 0; i < ARM_MAX_WRP; ++i) {
-		if (current->thread.debug.hbp_watch[i] == bp) {
-			info.si_errno = -((i << 1) + 1);
-			break;
+		for (i = 0; i < ARM_MAX_WRP; ++i) {
+			if (current->thread.debug.hbp_watch[i] == bp) {
+				si_errno = -((i << 1) + 1);
+				break;
+			}
 		}
+		force_sig_ptrace_errno_trap(si_errno, (void __user *)bkpt->trigger);
 	}
-
-send_sig:
 #endif
 	force_sig_info(SIGTRAP, &info, current);
 }
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index ce704a4aeadd..f407e422a720 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -45,6 +45,7 @@ ENTRY(arm64_relocate_new_kernel)
 	mrs	x0, sctlr_el2
 	ldr	x1, =SCTLR_ELx_FLAGS
 	bic	x0, x0, x1
+	pre_disable_mmu_workaround
 	msr	sctlr_el2, x0
 	isb
 1:
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
new file mode 100644
index 000000000000..6b8d90d5ceae
--- /dev/null
+++ b/arch/arm64/kernel/sdei.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2017 Arm Ltd.
+#define pr_fmt(fmt) "sdei: " fmt
+
+#include <linux/arm_sdei.h>
+#include <linux/hardirq.h>
+#include <linux/irqflags.h>
+#include <linux/sched/task_stack.h>
+#include <linux/uaccess.h>
+
+#include <asm/alternative.h>
+#include <asm/kprobes.h>
+#include <asm/mmu.h>
+#include <asm/ptrace.h>
+#include <asm/sections.h>
+#include <asm/sysreg.h>
+#include <asm/vmap_stack.h>
+
+unsigned long sdei_exit_mode;
+
+/*
+ * VMAP'd stacks checking for stack overflow on exception using sp as a scratch
+ * register, meaning SDEI has to switch to its own stack. We need two stacks as
+ * a critical event may interrupt a normal event that has just taken a
+ * synchronous exception, and is using sp as scratch register. For a critical
+ * event interrupting a normal event, we can't reliably tell if we were on the
+ * sdei stack.
+ * For now, we allocate stacks when the driver is probed.
+ */
+DECLARE_PER_CPU(unsigned long *, sdei_stack_normal_ptr);
+DECLARE_PER_CPU(unsigned long *, sdei_stack_critical_ptr);
+
+#ifdef CONFIG_VMAP_STACK
+DEFINE_PER_CPU(unsigned long *, sdei_stack_normal_ptr);
+DEFINE_PER_CPU(unsigned long *, sdei_stack_critical_ptr);
+#endif
+
+static void _free_sdei_stack(unsigned long * __percpu *ptr, int cpu)
+{
+	unsigned long *p;
+
+	p = per_cpu(*ptr, cpu);
+	if (p) {
+		per_cpu(*ptr, cpu) = NULL;
+		vfree(p);
+	}
+}
+
+static void free_sdei_stacks(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		_free_sdei_stack(&sdei_stack_normal_ptr, cpu);
+		_free_sdei_stack(&sdei_stack_critical_ptr, cpu);
+	}
+}
+
+static int _init_sdei_stack(unsigned long * __percpu *ptr, int cpu)
+{
+	unsigned long *p;
+
+	p = arch_alloc_vmap_stack(SDEI_STACK_SIZE, cpu_to_node(cpu));
+	if (!p)
+		return -ENOMEM;
+	per_cpu(*ptr, cpu) = p;
+
+	return 0;
+}
+
+static int init_sdei_stacks(void)
+{
+	int cpu;
+	int err = 0;
+
+	for_each_possible_cpu(cpu) {
+		err = _init_sdei_stack(&sdei_stack_normal_ptr, cpu);
+		if (err)
+			break;
+		err = _init_sdei_stack(&sdei_stack_critical_ptr, cpu);
+		if (err)
+			break;
+	}
+
+	if (err)
+		free_sdei_stacks();
+
+	return err;
+}
+
+bool _on_sdei_stack(unsigned long sp)
+{
+	unsigned long low, high;
+
+	if (!IS_ENABLED(CONFIG_VMAP_STACK))
+		return false;
+
+	low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
+	high = low + SDEI_STACK_SIZE;
+
+	if (low <= sp && sp < high)
+		return true;
+
+	low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
+	high = low + SDEI_STACK_SIZE;
+
+	return (low <= sp && sp < high);
+}
+
+unsigned long sdei_arch_get_entry_point(int conduit)
+{
+	/*
+	 * SDEI works between adjacent exception levels. If we booted at EL1 we
+	 * assume a hypervisor is marshalling events. If we booted at EL2 and
+	 * dropped to EL1 because we don't support VHE, then we can't support
+	 * SDEI.
+	 */
+	if (is_hyp_mode_available() && !is_kernel_in_hyp_mode()) {
+		pr_err("Not supported on this hardware/boot configuration\n");
+		return 0;
+	}
+
+	if (IS_ENABLED(CONFIG_VMAP_STACK)) {
+		if (init_sdei_stacks())
+			return 0;
+	}
+
+	sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	if (arm64_kernel_unmapped_at_el0()) {
+		unsigned long offset;
+
+		offset = (unsigned long)__sdei_asm_entry_trampoline -
+			 (unsigned long)__entry_tramp_text_start;
+		return TRAMP_VALIAS + offset;
+	} else
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+		return (unsigned long)__sdei_asm_handler;
+
+}
+
+/*
+ * __sdei_handler() returns one of:
+ *  SDEI_EV_HANDLED -  success, return to the interrupted context.
+ *  SDEI_EV_FAILED  -  failure, return this error code to firmare.
+ *  virtual-address -  success, return to this address.
+ */
+static __kprobes unsigned long _sdei_handler(struct pt_regs *regs,
+					     struct sdei_registered_event *arg)
+{
+	u32 mode;
+	int i, err = 0;
+	int clobbered_registers = 4;
+	u64 elr = read_sysreg(elr_el1);
+	u32 kernel_mode = read_sysreg(CurrentEL) | 1;	/* +SPSel */
+	unsigned long vbar = read_sysreg(vbar_el1);
+
+	if (arm64_kernel_unmapped_at_el0())
+		clobbered_registers++;
+
+	/* Retrieve the missing registers values */
+	for (i = 0; i < clobbered_registers; i++) {
+		/* from within the handler, this call always succeeds */
+		sdei_api_event_context(i, &regs->regs[i]);
+	}
+
+	/*
+	 * We didn't take an exception to get here, set PAN. UAO will be cleared
+	 * by sdei_event_handler()s set_fs(USER_DS) call.
+	 */
+	__uaccess_enable_hw_pan();
+
+	err = sdei_event_handler(regs, arg);
+	if (err)
+		return SDEI_EV_FAILED;
+
+	if (elr != read_sysreg(elr_el1)) {
+		/*
+		 * We took a synchronous exception from the SDEI handler.
+		 * This could deadlock, and if you interrupt KVM it will
+		 * hyp-panic instead.
+		 */
+		pr_warn("unsafe: exception during handler\n");
+	}
+
+	mode = regs->pstate & (PSR_MODE32_BIT | PSR_MODE_MASK);
+
+	/*
+	 * If we interrupted the kernel with interrupts masked, we always go
+	 * back to wherever we came from.
+	 */
+	if (mode == kernel_mode && !interrupts_enabled(regs))
+		return SDEI_EV_HANDLED;
+
+	/*
+	 * Otherwise, we pretend this was an IRQ. This lets user space tasks
+	 * receive signals before we return to them, and KVM to invoke it's
+	 * world switch to do the same.
+	 *
+	 * See DDI0487B.a Table D1-7 'Vector offsets from vector table base
+	 * address'.
+	 */
+	if (mode == kernel_mode)
+		return vbar + 0x280;
+	else if (mode & PSR_MODE32_BIT)
+		return vbar + 0x680;
+
+	return vbar + 0x480;
+}
+
+
+asmlinkage __kprobes notrace unsigned long
+__sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
+{
+	unsigned long ret;
+	bool do_nmi_exit = false;
+
+	/*
+	 * nmi_enter() deals with printk() re-entrance and use of RCU when
+	 * RCU believed this CPU was idle. Because critical events can
+	 * interrupt normal events, we may already be in_nmi().
+	 */
+	if (!in_nmi()) {
+		nmi_enter();
+		do_nmi_exit = true;
+	}
+
+	ret = _sdei_handler(regs, arg);
+
+	if (do_nmi_exit)
+		nmi_exit();
+
+	return ret;
+}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index b120111a46be..f60c052e8d1c 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -178,7 +178,8 @@ static void __user *apply_user_offset(
 
 static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 {
-	struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;
+	struct user_fpsimd_state const *fpsimd =
+		&current->thread.fpsimd_state.user_fpsimd;
 	int err;
 
 	/* copy the FP and status/control registers */
@@ -195,7 +196,7 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 
 static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 {
-	struct fpsimd_state fpsimd;
+	struct user_fpsimd_state fpsimd;
 	__u32 magic, size;
 	int err = 0;
 
@@ -266,7 +267,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 {
 	int err;
 	unsigned int vq;
-	struct fpsimd_state fpsimd;
+	struct user_fpsimd_state fpsimd;
 	struct sve_context sve;
 
 	if (__copy_from_user(&sve, user->sve, sizeof(sve)))
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 22711ee8e36c..79feb861929b 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -125,86 +125,6 @@ static inline int get_sigset_t(sigset_t *set,
 	return 0;
 }
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
-{
-	int err;
-
-	if (!access_ok(VERIFY_WRITE, to, sizeof(*to)))
-		return -EFAULT;
-
-	/* If you change siginfo_t structure, please be sure
-	 * this code is fixed accordingly.
-	 * It should never copy any pad contained in the structure
-	 * to avoid security leaks, but must copy the generic
-	 * 3 ints plus the relevant union member.
-	 * This routine must convert siginfo from 64bit to 32bit as well
-	 * at the same time.
-	 */
-	err = __put_user(from->si_signo, &to->si_signo);
-	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user(from->si_code, &to->si_code);
-	if (from->si_code < 0)
-		err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad,
-				      SI_PAD_SIZE);
-	else switch (siginfo_layout(from->si_signo, from->si_code)) {
-	case SIL_KILL:
-		err |= __put_user(from->si_pid, &to->si_pid);
-		err |= __put_user(from->si_uid, &to->si_uid);
-		break;
-	case SIL_TIMER:
-		 err |= __put_user(from->si_tid, &to->si_tid);
-		 err |= __put_user(from->si_overrun, &to->si_overrun);
-		 err |= __put_user(from->si_int, &to->si_int);
-		break;
-	case SIL_POLL:
-		err |= __put_user(from->si_band, &to->si_band);
-		err |= __put_user(from->si_fd, &to->si_fd);
-		break;
-	case SIL_FAULT:
-		err |= __put_user((compat_uptr_t)(unsigned long)from->si_addr,
-				  &to->si_addr);
-#ifdef BUS_MCEERR_AO
-		/*
-		 * Other callers might not initialize the si_lsb field,
-		 * so check explicitly for the right codes here.
-		 */
-		if (from->si_signo == SIGBUS &&
-		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
-			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
-#endif
-		break;
-	case SIL_CHLD:
-		err |= __put_user(from->si_pid, &to->si_pid);
-		err |= __put_user(from->si_uid, &to->si_uid);
-		err |= __put_user(from->si_status, &to->si_status);
-		err |= __put_user(from->si_utime, &to->si_utime);
-		err |= __put_user(from->si_stime, &to->si_stime);
-		break;
-	case SIL_RT:
-		err |= __put_user(from->si_pid, &to->si_pid);
-		err |= __put_user(from->si_uid, &to->si_uid);
-		err |= __put_user(from->si_int, &to->si_int);
-		break;
-	case SIL_SYS:
-		err |= __put_user((compat_uptr_t)(unsigned long)
-				from->si_call_addr, &to->si_call_addr);
-		err |= __put_user(from->si_syscall, &to->si_syscall);
-		err |= __put_user(from->si_arch, &to->si_arch);
-		break;
-	}
-	return err;
-}
-
-int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
-{
-	if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) ||
-	    copy_from_user(to->_sifields._pad,
-			   from->_sifields._pad, SI_PAD_SIZE))
-		return -EFAULT;
-
-	return 0;
-}
-
 /*
  * VFP save/restore code.
  *
@@ -228,7 +148,8 @@ union __fpsimd_vreg {
 
 static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
 {
-	struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;
+	struct user_fpsimd_state const *fpsimd =
+		&current->thread.fpsimd_state.user_fpsimd;
 	compat_ulong_t magic = VFP_MAGIC;
 	compat_ulong_t size = VFP_STORAGE_SIZE;
 	compat_ulong_t fpscr, fpexc;
@@ -277,7 +198,7 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
 
 static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame)
 {
-	struct fpsimd_state fpsimd;
+	struct user_fpsimd_state fpsimd;
 	compat_ulong_t magic = VFP_MAGIC;
 	compat_ulong_t size = VFP_STORAGE_SIZE;
 	compat_ulong_t fpscr;
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 551eb07c53b6..3b8ad7be9c33 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/arm_sdei.h>
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
@@ -836,6 +837,7 @@ static void ipi_cpu_stop(unsigned int cpu)
 	set_cpu_online(cpu, false);
 
 	local_daif_mask();
+	sdei_mask_local_cpu();
 
 	while (1)
 		cpu_relax();
@@ -853,6 +855,7 @@ static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
 	atomic_dec(&waiting_for_crash_ipi);
 
 	local_irq_disable();
+	sdei_mask_local_cpu();
 
 #ifdef CONFIG_HOTPLUG_CPU
 	if (cpu_ops[cpu]->cpu_die)
@@ -972,6 +975,8 @@ void smp_send_stop(void)
 	if (num_online_cpus() > 1)
 		pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
 			   cpumask_pr_args(cpu_online_mask));
+
+	sdei_mask_local_cpu();
 }
 
 #ifdef CONFIG_KEXEC_CORE
@@ -990,8 +995,10 @@ void crash_smp_send_stop(void)
 
 	cpus_stopped = 1;
 
-	if (num_online_cpus() == 1)
+	if (num_online_cpus() == 1) {
+		sdei_mask_local_cpu();
 		return;
+	}
 
 	cpumask_copy(&mask, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &mask);
@@ -1009,6 +1016,8 @@ void crash_smp_send_stop(void)
 	if (atomic_read(&waiting_for_crash_ipi) > 0)
 		pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
 			   cpumask_pr_args(&mask));
+
+	sdei_mask_local_cpu();
 }
 
 bool smp_crash_stop_failed(void)
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 3fe5ad884418..a307b9e13392 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -2,6 +2,7 @@
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
+#include <linux/uaccess.h>
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
@@ -51,8 +52,7 @@ void notrace __cpu_suspend_exit(void)
 	 * PSTATE was not saved over suspend/resume, re-enable any detected
 	 * features that might not have been set correctly.
 	 */
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
-			CONFIG_ARM64_PAN));
+	__uaccess_enable_hw_pan();
 	uao_thread_switch(current);
 
 	/*
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 8d48b233e6ce..21868530018e 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -37,18 +37,14 @@ static int __init get_cpu_for_node(struct device_node *node)
 	if (!cpu_node)
 		return -1;
 
-	for_each_possible_cpu(cpu) {
-		if (of_get_cpu_node(cpu, NULL) == cpu_node) {
-			topology_parse_cpu_capacity(cpu_node, cpu);
-			of_node_put(cpu_node);
-			return cpu;
-		}
-	}
-
-	pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
+	cpu = of_cpu_node_to_id(cpu_node);
+	if (cpu >= 0)
+		topology_parse_cpu_capacity(cpu_node, cpu);
+	else
+		pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
 
 	of_node_put(cpu_node);
-	return -1;
+	return cpu;
 }
 
 static int __init parse_core(struct device_node *core, int cluster_id,
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 3d3588fcd1c7..bbb0fde2780e 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -662,17 +662,58 @@ asmlinkage void handle_bad_stack(struct pt_regs *regs)
 }
 #endif
 
-asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
+void __noreturn arm64_serror_panic(struct pt_regs *regs, u32 esr)
 {
-	nmi_enter();
-
 	console_verbose();
 
 	pr_crit("SError Interrupt on CPU%d, code 0x%08x -- %s\n",
 		smp_processor_id(), esr, esr_get_class_string(esr));
-	__show_regs(regs);
+	if (regs)
+		__show_regs(regs);
+
+	nmi_panic(regs, "Asynchronous SError Interrupt");
+
+	cpu_park_loop();
+	unreachable();
+}
+
+bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr)
+{
+	u32 aet = arm64_ras_serror_get_severity(esr);
+
+	switch (aet) {
+	case ESR_ELx_AET_CE:	/* corrected error */
+	case ESR_ELx_AET_UEO:	/* restartable, not yet consumed */
+		/*
+		 * The CPU can make progress. We may take UEO again as
+		 * a more severe error.
+		 */
+		return false;
+
+	case ESR_ELx_AET_UEU:	/* Uncorrected Unrecoverable */
+	case ESR_ELx_AET_UER:	/* Uncorrected Recoverable */
+		/*
+		 * The CPU can't make progress. The exception may have
+		 * been imprecise.
+		 */
+		return true;
+
+	case ESR_ELx_AET_UC:	/* Uncontainable or Uncategorized error */
+	default:
+		/* Error has been silently propagated */
+		arm64_serror_panic(regs, esr);
+	}
+}
+
+asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
+{
+	nmi_enter();
+
+	/* non-RAS errors are not containable */
+	if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr))
+		arm64_serror_panic(regs, esr);
 
-	panic("Asynchronous SError Interrupt");
+	nmi_exit();
 }
 
 void __pte_error(const char *file, int line, unsigned long val)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 7da3e5c366a0..0221aca6493d 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -57,6 +57,17 @@ jiffies = jiffies_64;
 #define HIBERNATE_TEXT
 #endif
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define TRAMP_TEXT					\
+	. = ALIGN(PAGE_SIZE);				\
+	VMLINUX_SYMBOL(__entry_tramp_text_start) = .;	\
+	*(.entry.tramp.text)				\
+	. = ALIGN(PAGE_SIZE);				\
+	VMLINUX_SYMBOL(__entry_tramp_text_end) = .;
+#else
+#define TRAMP_TEXT
+#endif
+
 /*
  * The size of the PE/COFF section that covers the kernel image, which
  * runs from stext to _edata, must be a round multiple of the PE/COFF
@@ -113,6 +124,7 @@ SECTIONS
 			HYPERVISOR_TEXT
 			IDMAP_TEXT
 			HIBERNATE_TEXT
+			TRAMP_TEXT
 			*(.fixup)
 			*(.gnu.warning)
 		. = ALIGN(16);
@@ -206,13 +218,19 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	idmap_pg_dir = .;
 	. += IDMAP_DIR_SIZE;
-	swapper_pg_dir = .;
-	. += SWAPPER_DIR_SIZE;
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	tramp_pg_dir = .;
+	. += PAGE_SIZE;
+#endif
 
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	reserved_ttbr0 = .;
 	. += RESERVED_TTBR0_SIZE;
 #endif
+	swapper_pg_dir = .;
+	. += SWAPPER_DIR_SIZE;
+	swapper_pg_end = .;
 
 	__pecoff_data_size = ABSOLUTE(. - __initdata_begin);
 	_end = .;
@@ -234,7 +252,10 @@ ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
 ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1))
 	<= SZ_4K, "Hibernate exit text too big or misaligned")
 #endif
-
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) == PAGE_SIZE,
+	"Entry trampoline text too big")
+#endif
 /*
  * If padding is applied before .head.text, virt<->phys conversions will fail.
  */
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index dbadfaf850a7..fa63b28c65e0 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -221,3 +221,24 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
 		}
 	}
 }
+
+
+/*
+ * After successfully emulating an instruction, we might want to
+ * return to user space with a KVM_EXIT_DEBUG. We can only do this
+ * once the emulation is complete, though, so for userspace emulations
+ * we have to wait until we have re-entered KVM before calling this
+ * helper.
+ *
+ * Return true (and set exit_reason) to return to userspace or false
+ * if no further action is required.
+ */
+bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+		run->exit_reason = KVM_EXIT_DEBUG;
+		run->debug.arch.hsr = ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT;
+		return true;
+	}
+	return false;
+}
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index b71247995469..520b0dad3c62 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -23,17 +23,26 @@
 #include <linux/kvm_host.h>
 
 #include <asm/esr.h>
+#include <asm/exception.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_psci.h>
+#include <asm/debug-monitors.h>
+#include <asm/traps.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
 typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
 
+static void kvm_handle_guest_serror(struct kvm_vcpu *vcpu, u32 esr)
+{
+	if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(NULL, esr))
+		kvm_inject_vabt(vcpu);
+}
+
 static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int ret;
@@ -44,7 +53,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	ret = kvm_psci_call(vcpu);
 	if (ret < 0) {
-		kvm_inject_undefined(vcpu);
+		vcpu_set_reg(vcpu, 0, ~0UL);
 		return 1;
 	}
 
@@ -53,7 +62,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	kvm_inject_undefined(vcpu);
+	vcpu_set_reg(vcpu, 0, ~0UL);
 	return 1;
 }
 
@@ -187,14 +196,46 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 }
 
 /*
+ * We may be single-stepping an emulated instruction. If the emulation
+ * has been completed in the kernel, we can return to userspace with a
+ * KVM_EXIT_DEBUG, otherwise userspace needs to complete its
+ * emulation first.
+ */
+static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	int handled;
+
+	/*
+	 * See ARM ARM B1.14.1: "Hyp traps on instructions
+	 * that fail their condition code check"
+	 */
+	if (!kvm_condition_valid(vcpu)) {
+		kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+		handled = 1;
+	} else {
+		exit_handle_fn exit_handler;
+
+		exit_handler = kvm_get_exit_handler(vcpu);
+		handled = exit_handler(vcpu, run);
+	}
+
+	/*
+	 * kvm_arm_handle_step_debug() sets the exit_reason on the kvm_run
+	 * structure if we need to return to userspace.
+	 */
+	if (handled > 0 && kvm_arm_handle_step_debug(vcpu, run))
+		handled = 0;
+
+	return handled;
+}
+
+/*
  * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
  * proper exit to userspace.
  */
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		       int exception_index)
 {
-	exit_handle_fn exit_handler;
-
 	if (ARM_SERROR_PENDING(exception_index)) {
 		u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
 
@@ -209,7 +250,6 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 			*vcpu_pc(vcpu) -= adj;
 		}
 
-		kvm_inject_vabt(vcpu);
 		return 1;
 	}
 
@@ -219,21 +259,14 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	case ARM_EXCEPTION_IRQ:
 		return 1;
 	case ARM_EXCEPTION_EL1_SERROR:
-		kvm_inject_vabt(vcpu);
-		return 1;
-	case ARM_EXCEPTION_TRAP:
-		/*
-		 * See ARM ARM B1.14.1: "Hyp traps on instructions
-		 * that fail their condition code check"
-		 */
-		if (!kvm_condition_valid(vcpu)) {
-			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+		/* We may still need to return for single-step */
+		if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)
+			&& kvm_arm_handle_step_debug(vcpu, run))
+			return 0;
+		else
 			return 1;
-		}
-
-		exit_handler = kvm_get_exit_handler(vcpu);
-
-		return exit_handler(vcpu, run);
+	case ARM_EXCEPTION_TRAP:
+		return handle_trap_exceptions(vcpu, run);
 	case ARM_EXCEPTION_HYP_GONE:
 		/*
 		 * EL2 has been reset to the hyp-stub. This happens when a guest
@@ -248,3 +281,25 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		return 0;
 	}
 }
+
+/* For exit types that need handling before we can be preempted */
+void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		       int exception_index)
+{
+	if (ARM_SERROR_PENDING(exception_index)) {
+		if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN)) {
+			u64 disr = kvm_vcpu_get_disr(vcpu);
+
+			kvm_handle_guest_serror(vcpu, disr_to_esr(disr));
+		} else {
+			kvm_inject_vabt(vcpu);
+		}
+
+		return;
+	}
+
+	exception_index = ARM_EXCEPTION_CODE(exception_index);
+
+	if (exception_index == ARM_EXCEPTION_EL1_SERROR)
+		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_hsr(vcpu));
+}
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 3f9615582377..e086c6eff8c6 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -63,7 +63,8 @@ __do_hyp_init:
 	cmp	x0, #HVC_STUB_HCALL_NR
 	b.lo	__kvm_handle_stub_hvc
 
-	msr	ttbr0_el2, x0
+	phys_to_ttbr x0, x4
+	msr	ttbr0_el2, x4
 
 	mrs	x4, tcr_el1
 	ldr	x5, =TCR_EL2_MASK
@@ -71,30 +72,27 @@ __do_hyp_init:
 	mov	x5, #TCR_EL2_RES1
 	orr	x4, x4, x5
 
-#ifndef CONFIG_ARM64_VA_BITS_48
 	/*
-	 * If we are running with VA_BITS < 48, we may be running with an extra
-	 * level of translation in the ID map. This is only the case if system
-	 * RAM is out of range for the currently configured page size and number
-	 * of translation levels, in which case we will also need the extra
-	 * level for the HYP ID map, or we won't be able to enable the EL2 MMU.
+	 * The ID map may be configured to use an extended virtual address
+	 * range. This is only the case if system RAM is out of range for the
+	 * currently configured page size and VA_BITS, in which case we will
+	 * also need the extended virtual range for the HYP ID map, or we won't
+	 * be able to enable the EL2 MMU.
 	 *
 	 * However, at EL2, there is only one TTBR register, and we can't switch
 	 * between translation tables *and* update TCR_EL2.T0SZ at the same
-	 * time. Bottom line: we need the extra level in *both* our translation
-	 * tables.
+	 * time. Bottom line: we need to use the extended range with *both* our
+	 * translation tables.
 	 *
 	 * So use the same T0SZ value we use for the ID map.
 	 */
 	ldr_l	x5, idmap_t0sz
 	bfi	x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
-#endif
+
 	/*
-	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
-	 * TCR_EL2.
+	 * Set the PS bits in TCR_EL2.
 	 */
-	mrs	x5, ID_AA64MMFR0_EL1
-	bfi	x4, x5, #16, #3
+	tcr_compute_pa_size x4, #TCR_EL2_PS_SHIFT, x5, x6
 
 	msr	tcr_el2, x4
 
@@ -122,6 +120,10 @@ CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
 	kern_hyp_va	x2
 	msr	vbar_el2, x2
 
+	/* copy tpidr_el1 into tpidr_el2 for use by HYP */
+	mrs	x1, tpidr_el1
+	msr	tpidr_el2, x1
+
 	/* Hello, World! */
 	eret
 ENDPROC(__kvm_hyp_init)
@@ -151,6 +153,7 @@ reset:
 	mrs	x5, sctlr_el2
 	ldr	x6, =SCTLR_ELx_FLAGS
 	bic	x5, x5, x6		// Clear SCTL_M and etc
+	pre_disable_mmu_workaround
 	msr	sctlr_el2, x5
 	isb
 
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
index 321c9c05dd9e..f4363d40e2cd 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@@ -74,6 +74,9 @@ static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
 {
 	u64 reg;
 
+	/* Clear pmscr in case of early return */
+	*pmscr_el1 = 0;
+
 	/* SPE present on this CPU? */
 	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
 						  ID_AA64DFR0_PMSVER_SHIFT))
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index 12ee62d6d410..fdd1068ee3a5 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -62,8 +62,8 @@ ENTRY(__guest_enter)
 	// Store the host regs
 	save_callee_saved_regs x1
 
-	// Store the host_ctxt for use at exit time
-	str	x1, [sp, #-16]!
+	// Store host_ctxt and vcpu for use at exit time
+	stp	x1, x0, [sp, #-16]!
 
 	add	x18, x0, #VCPU_CONTEXT
 
@@ -124,6 +124,17 @@ ENTRY(__guest_exit)
 	// Now restore the host regs
 	restore_callee_saved_regs x2
 
+alternative_if ARM64_HAS_RAS_EXTN
+	// If we have the RAS extensions we can consume a pending error
+	// without an unmask-SError and isb.
+	esb
+	mrs_s	x2, SYS_DISR_EL1
+	str	x2, [x1, #(VCPU_FAULT_DISR - VCPU_CONTEXT)]
+	cbz	x2, 1f
+	msr_s	SYS_DISR_EL1, xzr
+	orr	x0, x0, #(1<<ARM_EXIT_WITH_SERROR_BIT)
+1:	ret
+alternative_else
 	// If we have a pending asynchronous abort, now is the
 	// time to find out. From your VAXorcist book, page 666:
 	// "Threaten me not, oh Evil one!  For I speak with
@@ -134,7 +145,9 @@ ENTRY(__guest_exit)
 	mov	x5, x0
 
 	dsb	sy		// Synchronize against in-flight ld/st
+	nop
 	msr	daifclr, #4	// Unmask aborts
+alternative_endif
 
 	// This is our single instruction exception window. A pending
 	// SError is guaranteed to occur at the earliest when we unmask
@@ -159,6 +172,10 @@ abort_guest_exit_end:
 ENDPROC(__guest_exit)
 
 ENTRY(__fpsimd_guest_restore)
+	// x0: esr
+	// x1: vcpu
+	// x2-x29,lr: vcpu regs
+	// vcpu x0-x1 on the stack
 	stp	x2, x3, [sp, #-16]!
 	stp	x4, lr, [sp, #-16]!
 
@@ -173,7 +190,7 @@ alternative_else
 alternative_endif
 	isb
 
-	mrs	x3, tpidr_el2
+	mov	x3, x1
 
 	ldr	x0, [x3, #VCPU_HOST_CONTEXT]
 	kern_hyp_va x0
@@ -196,3 +213,15 @@ alternative_endif
 
 	eret
 ENDPROC(__fpsimd_guest_restore)
+
+ENTRY(__qcom_hyp_sanitize_btac_predictors)
+	/**
+	 * Call SMC64 with Silicon provider serviceID 23<<8 (0xc2001700)
+	 * 0xC2000000-0xC200FFFF: assigned to SiP Service Calls
+	 * b15-b0: contains SiP functionID
+	 */
+	movz    x0, #0x1700
+	movk    x0, #0xc200, lsl #16
+	smc     #0
+	ret
+ENDPROC(__qcom_hyp_sanitize_btac_predictors)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 5170ce1021da..e4f37b9dd47c 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -104,6 +104,7 @@ el1_trap:
 	/*
 	 * x0: ESR_EC
 	 */
+	ldr	x1, [sp, #16 + 8]	// vcpu stored by __guest_enter
 
 	/*
 	 * We trap the first access to the FP/SIMD to save the host context
@@ -116,19 +117,18 @@ alternative_if_not ARM64_HAS_NO_FPSIMD
 	b.eq	__fpsimd_guest_restore
 alternative_else_nop_endif
 
-	mrs	x1, tpidr_el2
 	mov	x0, #ARM_EXCEPTION_TRAP
 	b	__guest_exit
 
 el1_irq:
 	stp     x0, x1, [sp, #-16]!
-	mrs	x1, tpidr_el2
+	ldr	x1, [sp, #16 + 8]
 	mov	x0, #ARM_EXCEPTION_IRQ
 	b	__guest_exit
 
 el1_error:
 	stp     x0, x1, [sp, #-16]!
-	mrs	x1, tpidr_el2
+	ldr	x1, [sp, #16 + 8]
 	mov	x0, #ARM_EXCEPTION_EL1_SERROR
 	b	__guest_exit
 
@@ -163,6 +163,18 @@ ENTRY(__hyp_do_panic)
 	eret
 ENDPROC(__hyp_do_panic)
 
+ENTRY(__hyp_panic)
+	/*
+	 * '=kvm_host_cpu_state' is a host VA from the constant pool, it may
+	 * not be accessible by this address from EL2, hyp_panic() converts
+	 * it with kern_hyp_va() before use.
+	 */
+	ldr	x0, =kvm_host_cpu_state
+	mrs	x1, tpidr_el2
+	add	x0, x0, x1
+	b	hyp_panic
+ENDPROC(__hyp_panic)
+
 .macro invalid_vector	label, target = __hyp_panic
 	.align	2
 \label:
diff --git a/arch/arm64/kvm/hyp/s2-setup.c b/arch/arm64/kvm/hyp/s2-setup.c
index a81f5e10fc8c..603e1ee83e89 100644
--- a/arch/arm64/kvm/hyp/s2-setup.c
+++ b/arch/arm64/kvm/hyp/s2-setup.c
@@ -32,6 +32,8 @@ u32 __hyp_text __init_stage2_translation(void)
 	 * PS is only 3. Fortunately, bit 19 is RES0 in VTCR_EL2...
 	 */
 	parange = read_sysreg(id_aa64mmfr0_el1) & 7;
+	if (parange > ID_AA64MMFR0_PARANGE_MAX)
+		parange = ID_AA64MMFR0_PARANGE_MAX;
 	val |= parange << 16;
 
 	/* Compute the actual PARange... */
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 525c01f48867..036e1f3d77a6 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -17,11 +17,13 @@
 
 #include <linux/types.h>
 #include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
 
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 #include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
 
 static bool __hyp_text __fpsimd_enabled_nvhe(void)
 {
@@ -51,7 +53,7 @@ static void __hyp_text __activate_traps_vhe(void)
 	val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN);
 	write_sysreg(val, cpacr_el1);
 
-	write_sysreg(__kvm_hyp_vector, vbar_el1);
+	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
 }
 
 static void __hyp_text __activate_traps_nvhe(void)
@@ -92,6 +94,9 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 
 	write_sysreg(val, hcr_el2);
 
+	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (val & HCR_VSE))
+		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
+
 	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
 	/*
@@ -234,11 +239,12 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
 
 static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 {
-	u64 esr = read_sysreg_el2(esr);
-	u8 ec = ESR_ELx_EC(esr);
+	u8 ec;
+	u64 esr;
 	u64 hpfar, far;
 
-	vcpu->arch.fault.esr_el2 = esr;
+	esr = vcpu->arch.fault.esr_el2;
+	ec = ESR_ELx_EC(esr);
 
 	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
 		return true;
@@ -269,7 +275,11 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
+/* Skip an instruction which has been emulated. Returns true if
+ * execution can continue or false if we need to exit hyp mode because
+ * single-step was in effect.
+ */
+static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
 {
 	*vcpu_pc(vcpu) = read_sysreg_el2(elr);
 
@@ -282,6 +292,14 @@ static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
 	}
 
 	write_sysreg_el2(*vcpu_pc(vcpu), elr);
+
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+		vcpu->arch.fault.esr_el2 =
+			(ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT) | 0x22;
+		return false;
+	} else {
+		return true;
+	}
 }
 
 int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
@@ -292,9 +310,9 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	u64 exit_code;
 
 	vcpu = kern_hyp_va(vcpu);
-	write_sysreg(vcpu, tpidr_el2);
 
 	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+	host_ctxt->__hyp_running_vcpu = vcpu;
 	guest_ctxt = &vcpu->arch.ctxt;
 
 	__sysreg_save_host_state(host_ctxt);
@@ -319,6 +337,8 @@ again:
 	exit_code = __guest_enter(vcpu, host_ctxt);
 	/* And we're baaack! */
 
+	if (ARM_EXCEPTION_CODE(exit_code) != ARM_EXCEPTION_IRQ)
+		vcpu->arch.fault.esr_el2 = read_sysreg_el2(esr);
 	/*
 	 * We're using the raw exception code in order to only process
 	 * the trap if no SError is pending. We will come back to the
@@ -328,6 +348,18 @@ again:
 	if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
 		goto again;
 
+	if (exit_code == ARM_EXCEPTION_TRAP &&
+	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC64 ||
+	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32) &&
+	    vcpu_get_reg(vcpu, 0) == PSCI_0_2_FN_PSCI_VERSION) {
+		u64 val = PSCI_RET_NOT_SUPPORTED;
+		if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+			val = 2;
+
+		vcpu_set_reg(vcpu, 0, val);
+		goto again;
+	}
+
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
 	    exit_code == ARM_EXCEPTION_TRAP) {
 		bool valid;
@@ -342,13 +374,21 @@ again:
 			int ret = __vgic_v2_perform_cpuif_access(vcpu);
 
 			if (ret == 1) {
-				__skip_instr(vcpu);
-				goto again;
+				if (__skip_instr(vcpu))
+					goto again;
+				else
+					exit_code = ARM_EXCEPTION_TRAP;
 			}
 
 			if (ret == -1) {
-				/* Promote an illegal access to an SError */
-				__skip_instr(vcpu);
+				/* Promote an illegal access to an
+				 * SError. If we would be returning
+				 * due to single-step clear the SS
+				 * bit so handle_exit knows what to
+				 * do after dealing with the error.
+				 */
+				if (!__skip_instr(vcpu))
+					*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
 				exit_code = ARM_EXCEPTION_EL1_SERROR;
 			}
 
@@ -363,13 +403,23 @@ again:
 		int ret = __vgic_v3_perform_cpuif_access(vcpu);
 
 		if (ret == 1) {
-			__skip_instr(vcpu);
-			goto again;
+			if (__skip_instr(vcpu))
+				goto again;
+			else
+				exit_code = ARM_EXCEPTION_TRAP;
 		}
 
 		/* 0 falls through to be handled out of EL2 */
 	}
 
+	if (cpus_have_const_cap(ARM64_HARDEN_BP_POST_GUEST_EXIT)) {
+		u32 midr = read_cpuid_id();
+
+		/* Apply BTAC predictors mitigation to all Falkor chips */
+		if ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)
+			__qcom_hyp_sanitize_btac_predictors();
+	}
+
 	fp_enabled = __fpsimd_enabled();
 
 	__sysreg_save_guest_state(guest_ctxt);
@@ -399,7 +449,8 @@ again:
 
 static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
 
-static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par)
+static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
+					     struct kvm_vcpu *vcpu)
 {
 	unsigned long str_va;
 
@@ -413,35 +464,35 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par)
 	__hyp_do_panic(str_va,
 		       spsr,  elr,
 		       read_sysreg(esr_el2),   read_sysreg_el2(far),
-		       read_sysreg(hpfar_el2), par,
-		       (void *)read_sysreg(tpidr_el2));
+		       read_sysreg(hpfar_el2), par, vcpu);
 }
 
-static void __hyp_text __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par)
+static void __hyp_text __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par,
+					    struct kvm_vcpu *vcpu)
 {
 	panic(__hyp_panic_string,
 	      spsr,  elr,
 	      read_sysreg_el2(esr),   read_sysreg_el2(far),
-	      read_sysreg(hpfar_el2), par,
-	      (void *)read_sysreg(tpidr_el2));
+	      read_sysreg(hpfar_el2), par, vcpu);
 }
 
 static hyp_alternate_select(__hyp_call_panic,
 			    __hyp_call_panic_nvhe, __hyp_call_panic_vhe,
 			    ARM64_HAS_VIRT_HOST_EXTN);
 
-void __hyp_text __noreturn __hyp_panic(void)
+void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *__host_ctxt)
 {
+	struct kvm_vcpu *vcpu = NULL;
+
 	u64 spsr = read_sysreg_el2(spsr);
 	u64 elr = read_sysreg_el2(elr);
 	u64 par = read_sysreg(par_el1);
 
 	if (read_sysreg(vttbr_el2)) {
-		struct kvm_vcpu *vcpu;
 		struct kvm_cpu_context *host_ctxt;
 
-		vcpu = (struct kvm_vcpu *)read_sysreg(tpidr_el2);
-		host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+		host_ctxt = kern_hyp_va(__host_ctxt);
+		vcpu = host_ctxt->__hyp_running_vcpu;
 		__timer_disable_traps(vcpu);
 		__deactivate_traps(vcpu);
 		__deactivate_vm(vcpu);
@@ -449,7 +500,7 @@ void __hyp_text __noreturn __hyp_panic(void)
 	}
 
 	/* Call panic for real */
-	__hyp_call_panic()(spsr, elr, par);
+	__hyp_call_panic()(spsr, elr, par, vcpu);
 
 	unreachable();
 }
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 934137647837..2c17afd2be96 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -27,8 +27,8 @@ static void __hyp_text __sysreg_do_nothing(struct kvm_cpu_context *ctxt) { }
 /*
  * Non-VHE: Both host and guest must save everything.
  *
- * VHE: Host must save tpidr*_el[01], actlr_el1, mdscr_el1, sp0, pc,
- * pstate, and guest must save everything.
+ * VHE: Host must save tpidr*_el0, actlr_el1, mdscr_el1, sp_el0,
+ * and guest must save everything.
  */
 
 static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
@@ -36,11 +36,8 @@ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 	ctxt->sys_regs[ACTLR_EL1]	= read_sysreg(actlr_el1);
 	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
 	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
-	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
 	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
-	ctxt->gp_regs.regs.pc		= read_sysreg_el2(elr);
-	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(spsr);
 }
 
 static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
@@ -62,10 +59,16 @@ static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
 	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg_el1(amair);
 	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg_el1(cntkctl);
 	ctxt->sys_regs[PAR_EL1]		= read_sysreg(par_el1);
+	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
 
 	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
 	ctxt->gp_regs.elr_el1		= read_sysreg_el1(elr);
 	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(spsr);
+	ctxt->gp_regs.regs.pc		= read_sysreg_el2(elr);
+	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(spsr);
+
+	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
+		ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
 }
 
 static hyp_alternate_select(__sysreg_call_save_host_state,
@@ -89,11 +92,8 @@ static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctx
 	write_sysreg(ctxt->sys_regs[ACTLR_EL1],	  actlr_el1);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL0],	  tpidr_el0);
 	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
-	write_sysreg(ctxt->sys_regs[TPIDR_EL1],	  tpidr_el1);
 	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
 	write_sysreg(ctxt->gp_regs.regs.sp,	  sp_el0);
-	write_sysreg_el2(ctxt->gp_regs.regs.pc,	  elr);
-	write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr);
 }
 
 static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
@@ -115,10 +115,16 @@ static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
 	write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1],	amair);
 	write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], 	cntkctl);
 	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
+	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
 
 	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
 	write_sysreg_el1(ctxt->gp_regs.elr_el1,		elr);
 	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],spsr);
+	write_sysreg_el2(ctxt->gp_regs.regs.pc,		elr);
+	write_sysreg_el2(ctxt->gp_regs.regs.pstate,	spsr);
+
+	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
+		write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
 }
 
 static hyp_alternate_select(__sysreg_call_restore_host_state,
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 8ecbcb40e317..60666a056944 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -164,14 +164,25 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 		inject_undef64(vcpu);
 }
 
+static void pend_guest_serror(struct kvm_vcpu *vcpu, u64 esr)
+{
+	vcpu_set_vsesr(vcpu, esr);
+	vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) | HCR_VSE);
+}
+
 /**
  * kvm_inject_vabt - inject an async abort / SError into the guest
  * @vcpu: The VCPU to receive the exception
  *
  * It is assumed that this code is called from the VCPU thread and that the
  * VCPU therefore is not currently executing guest code.
+ *
+ * Systems with the RAS Extensions specify an imp-def ESR (ISV/IDS = 1) with
+ * the remaining ISS all-zeros so that this error is not interpreted as an
+ * uncategorized RAS error. Without the RAS Extensions we can't specify an ESR
+ * value, so the CPU generates an imp-def value.
  */
 void kvm_inject_vabt(struct kvm_vcpu *vcpu)
 {
-	vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) | HCR_VSE);
+	pend_guest_serror(vcpu, ESR_ELx_ISV);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 1830ebc227d1..50a43c7b97ca 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1159,6 +1159,16 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_AFSR0_EL1), access_vm_reg, reset_unknown, AFSR0_EL1 },
 	{ SYS_DESC(SYS_AFSR1_EL1), access_vm_reg, reset_unknown, AFSR1_EL1 },
 	{ SYS_DESC(SYS_ESR_EL1), access_vm_reg, reset_unknown, ESR_EL1 },
+
+	{ SYS_DESC(SYS_ERRIDR_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_ERRSELR_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_ERXFR_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_ERXCTLR_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_ERXSTATUS_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_ERXADDR_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi },
+
 	{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
 	{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
 
@@ -1169,6 +1179,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
 
 	{ SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 },
+	{ SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 },
 
 	{ SYS_DESC(SYS_ICC_IAR0_EL1), write_to_read_only },
 	{ SYS_DESC(SYS_ICC_EOIR0_EL1), read_from_write_only },
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index e88fb99c1561..3d69a8d41fa5 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -30,7 +30,7 @@
  * Alignment fixed up by hardware.
  */
 ENTRY(__clear_user)
-	uaccess_enable_not_uao x2, x3
+	uaccess_enable_not_uao x2, x3, x4
 	mov	x2, x1			// save the size for fixup return
 	subs	x1, x1, #8
 	b.mi	2f
@@ -50,7 +50,7 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2
 	b.mi	5f
 uao_user_alternative 9f, strb, sttrb, wzr, x0, 0
 5:	mov	x0, #0
-	uaccess_disable_not_uao x2
+	uaccess_disable_not_uao x2, x3
 	ret
 ENDPROC(__clear_user)
 
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 4b5d826895ff..20305d485046 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -64,10 +64,10 @@
 
 end	.req	x5
 ENTRY(__arch_copy_from_user)
-	uaccess_enable_not_uao x3, x4
+	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3
+	uaccess_disable_not_uao x3, x4
 	mov	x0, #0				// Nothing to copy
 	ret
 ENDPROC(__arch_copy_from_user)
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index b24a830419ad..fbb090f431a5 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -65,10 +65,10 @@
 
 end	.req	x5
 ENTRY(raw_copy_in_user)
-	uaccess_enable_not_uao x3, x4
+	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3
+	uaccess_disable_not_uao x3, x4
 	mov	x0, #0
 	ret
 ENDPROC(raw_copy_in_user)
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 351f0766f7a6..fda6172d6b88 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -63,10 +63,10 @@
 
 end	.req	x5
 ENTRY(__arch_copy_to_user)
-	uaccess_enable_not_uao x3, x4
+	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3
+	uaccess_disable_not_uao x3, x4
 	mov	x0, #0
 	ret
 ENDPROC(__arch_copy_to_user)
diff --git a/arch/arm64/lib/tishift.S b/arch/arm64/lib/tishift.S
index 0179a43cc045..d3db9b2cd479 100644
--- a/arch/arm64/lib/tishift.S
+++ b/arch/arm64/lib/tishift.S
@@ -38,19 +38,19 @@ ENTRY(__ashlti3)
 ENDPROC(__ashlti3)
 
 ENTRY(__ashrti3)
-	cbz	x2, 3f
+	cbz	x2, 1f
 	mov	x3, #64
 	sub	x3, x3, x2
 	cmp	x3, #0
-	b.le	4f
+	b.le	2f
 	lsr	x0, x0, x2
 	lsl	x3, x1, x3
 	asr	x2, x1, x2
 	orr	x0, x0, x3
 	mov	x1, x2
-3:
+1:
 	ret
-4:
+2:
 	neg	w0, w3
 	asr	x2, x1, #63
 	asr	x0, x1, x0
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 7f1dbe962cf5..91464e7f77cc 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -49,7 +49,7 @@ ENTRY(flush_icache_range)
  *	- end     - virtual end address of region
  */
 ENTRY(__flush_cache_user_range)
-	uaccess_ttbr0_enable x2, x3
+	uaccess_ttbr0_enable x2, x3, x4
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x4, x0, x3
@@ -72,7 +72,7 @@ USER(9f, ic	ivau, x4	)		// invalidate I line PoU
 	isb
 	mov	x0, #0
 1:
-	uaccess_ttbr0_disable x1
+	uaccess_ttbr0_disable x1, x2
 	ret
 9:
 	mov	x0, #-EFAULT
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index ab9f5f0fb2c7..301417ae2ba8 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -39,7 +39,16 @@ static cpumask_t tlb_flush_pending;
 
 #define ASID_MASK		(~GENMASK(asid_bits - 1, 0))
 #define ASID_FIRST_VERSION	(1UL << asid_bits)
-#define NUM_USER_ASIDS		ASID_FIRST_VERSION
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define NUM_USER_ASIDS		(ASID_FIRST_VERSION >> 1)
+#define asid2idx(asid)		(((asid) & ~ASID_MASK) >> 1)
+#define idx2asid(idx)		(((idx) << 1) & ~ASID_MASK)
+#else
+#define NUM_USER_ASIDS		(ASID_FIRST_VERSION)
+#define asid2idx(asid)		((asid) & ~ASID_MASK)
+#define idx2asid(idx)		asid2idx(idx)
+#endif
 
 /* Get the ASIDBits supported by the current CPU */
 static u32 get_cpu_asid_bits(void)
@@ -79,13 +88,6 @@ void verify_cpu_asid_bits(void)
 	}
 }
 
-static void set_reserved_asid_bits(void)
-{
-	if (IS_ENABLED(CONFIG_QCOM_FALKOR_ERRATUM_1003) &&
-	    cpus_have_const_cap(ARM64_WORKAROUND_QCOM_FALKOR_E1003))
-		__set_bit(FALKOR_RESERVED_ASID, asid_map);
-}
-
 static void flush_context(unsigned int cpu)
 {
 	int i;
@@ -94,14 +96,6 @@ static void flush_context(unsigned int cpu)
 	/* Update the list of reserved ASIDs and the ASID bitmap. */
 	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
 
-	set_reserved_asid_bits();
-
-	/*
-	 * Ensure the generation bump is observed before we xchg the
-	 * active_asids.
-	 */
-	smp_wmb();
-
 	for_each_possible_cpu(i) {
 		asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
 		/*
@@ -113,11 +107,14 @@ static void flush_context(unsigned int cpu)
 		 */
 		if (asid == 0)
 			asid = per_cpu(reserved_asids, i);
-		__set_bit(asid & ~ASID_MASK, asid_map);
+		__set_bit(asid2idx(asid), asid_map);
 		per_cpu(reserved_asids, i) = asid;
 	}
 
-	/* Queue a TLB invalidate and flush the I-cache if necessary. */
+	/*
+	 * Queue a TLB invalidation for each CPU to perform on next
+	 * context-switch
+	 */
 	cpumask_setall(&tlb_flush_pending);
 }
 
@@ -165,16 +162,16 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 		 * We had a valid ASID in a previous life, so try to re-use
 		 * it if possible.
 		 */
-		asid &= ~ASID_MASK;
-		if (!__test_and_set_bit(asid, asid_map))
+		if (!__test_and_set_bit(asid2idx(asid), asid_map))
 			return newasid;
 	}
 
 	/*
 	 * Allocate a free ASID. If we can't find one, take a note of the
-	 * currently active ASIDs and mark the TLBs as requiring flushes.
-	 * We always count from ASID #1, as we use ASID #0 when setting a
-	 * reserved TTBR0 for the init_mm.
+	 * currently active ASIDs and mark the TLBs as requiring flushes.  We
+	 * always count from ASID #2 (index 1), as we use ASID #0 when setting
+	 * a reserved TTBR0 for the init_mm and we allocate ASIDs in even/odd
+	 * pairs.
 	 */
 	asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx);
 	if (asid != NUM_USER_ASIDS)
@@ -191,25 +188,35 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 set_asid:
 	__set_bit(asid, asid_map);
 	cur_idx = asid;
-	return asid | generation;
+	return idx2asid(asid) | generation;
 }
 
 void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
 {
 	unsigned long flags;
-	u64 asid;
+	u64 asid, old_active_asid;
 
 	asid = atomic64_read(&mm->context.id);
 
 	/*
-	 * The memory ordering here is subtle. We rely on the control
-	 * dependency between the generation read and the update of
-	 * active_asids to ensure that we are synchronised with a
-	 * parallel rollover (i.e. this pairs with the smp_wmb() in
-	 * flush_context).
+	 * The memory ordering here is subtle.
+	 * If our active_asids is non-zero and the ASID matches the current
+	 * generation, then we update the active_asids entry with a relaxed
+	 * cmpxchg. Racing with a concurrent rollover means that either:
+	 *
+	 * - We get a zero back from the cmpxchg and end up waiting on the
+	 *   lock. Taking the lock synchronises with the rollover and so
+	 *   we are forced to see the updated generation.
+	 *
+	 * - We get a valid ASID back from the cmpxchg, which means the
+	 *   relaxed xchg in flush_context will treat us as reserved
+	 *   because atomic RmWs are totally ordered for a given location.
 	 */
-	if (!((asid ^ atomic64_read(&asid_generation)) >> asid_bits)
-	    && atomic64_xchg_relaxed(&per_cpu(active_asids, cpu), asid))
+	old_active_asid = atomic64_read(&per_cpu(active_asids, cpu));
+	if (old_active_asid &&
+	    !((asid ^ atomic64_read(&asid_generation)) >> asid_bits) &&
+	    atomic64_cmpxchg_relaxed(&per_cpu(active_asids, cpu),
+				     old_active_asid, asid))
 		goto switch_mm_fastpath;
 
 	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
@@ -227,6 +234,9 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
 	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
 
 switch_mm_fastpath:
+
+	arm64_apply_bp_hardening();
+
 	/*
 	 * Defer TTBR0_EL1 setting for user threads to uaccess_enable() when
 	 * emulating PAN.
@@ -235,6 +245,15 @@ switch_mm_fastpath:
 		cpu_switch_mm(mm->pgd, mm);
 }
 
+/* Errata workaround post TTBRx_EL1 update. */
+asmlinkage void post_ttbr_update_workaround(void)
+{
+	asm(ALTERNATIVE("nop; nop; nop",
+			"ic iallu; dsb nsh; isb",
+			ARM64_WORKAROUND_CAVIUM_27456,
+			CONFIG_CAVIUM_ERRATUM_27456));
+}
+
 static int asids_init(void)
 {
 	asid_bits = get_cpu_asid_bits();
@@ -250,8 +269,6 @@ static int asids_init(void)
 		panic("Failed to allocate bitmap for %lu ASIDs\n",
 		      NUM_USER_ASIDS);
 
-	set_reserved_asid_bits();
-
 	pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS);
 	return 0;
 }
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index b45c5bcaeccb..a96ec0181818 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -24,7 +24,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/genalloc.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-contiguous.h>
 #include <linux/vmalloc.h>
 #include <linux/swiotlb.h>
@@ -91,46 +91,6 @@ static int __free_from_pool(void *start, size_t size)
 	return 1;
 }
 
-static void *__dma_alloc_coherent(struct device *dev, size_t size,
-				  dma_addr_t *dma_handle, gfp_t flags,
-				  unsigned long attrs)
-{
-	if (IS_ENABLED(CONFIG_ZONE_DMA) &&
-	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
-		flags |= GFP_DMA;
-	if (dev_get_cma_area(dev) && gfpflags_allow_blocking(flags)) {
-		struct page *page;
-		void *addr;
-
-		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
-						 get_order(size), flags);
-		if (!page)
-			return NULL;
-
-		*dma_handle = phys_to_dma(dev, page_to_phys(page));
-		addr = page_address(page);
-		memset(addr, 0, size);
-		return addr;
-	} else {
-		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
-	}
-}
-
-static void __dma_free_coherent(struct device *dev, size_t size,
-				void *vaddr, dma_addr_t dma_handle,
-				unsigned long attrs)
-{
-	bool freed;
-	phys_addr_t paddr = dma_to_phys(dev, dma_handle);
-
-
-	freed = dma_release_from_contiguous(dev,
-					phys_to_page(paddr),
-					size >> PAGE_SHIFT);
-	if (!freed)
-		swiotlb_free_coherent(dev, size, vaddr, dma_handle);
-}
-
 static void *__dma_alloc(struct device *dev, size_t size,
 			 dma_addr_t *dma_handle, gfp_t flags,
 			 unsigned long attrs)
@@ -152,7 +112,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 		return addr;
 	}
 
-	ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
+	ptr = swiotlb_alloc(dev, size, dma_handle, flags, attrs);
 	if (!ptr)
 		goto no_mem;
 
@@ -173,7 +133,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 	return coherent_ptr;
 
 no_map:
-	__dma_free_coherent(dev, size, ptr, *dma_handle, attrs);
+	swiotlb_free(dev, size, ptr, *dma_handle, attrs);
 no_mem:
 	return NULL;
 }
@@ -191,7 +151,7 @@ static void __dma_free(struct device *dev, size_t size,
 			return;
 		vunmap(vaddr);
 	}
-	__dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
+	swiotlb_free(dev, size, swiotlb_addr, dma_handle, attrs);
 }
 
 static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
@@ -368,7 +328,7 @@ static int __swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t addr)
 	return 0;
 }
 
-static const struct dma_map_ops swiotlb_dma_ops = {
+static const struct dma_map_ops arm64_swiotlb_dma_ops = {
 	.alloc = __dma_alloc,
 	.free = __dma_free,
 	.mmap = __swiotlb_mmap,
@@ -397,7 +357,7 @@ static int __init atomic_pool_init(void)
 		page = dma_alloc_from_contiguous(NULL, nr_pages,
 						 pool_size_order, GFP_KERNEL);
 	else
-		page = alloc_pages(GFP_DMA, pool_size_order);
+		page = alloc_pages(GFP_DMA32, pool_size_order);
 
 	if (page) {
 		int ret;
@@ -923,7 +883,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
 	if (!dev->dma_ops)
-		dev->dma_ops = &swiotlb_dma_ops;
+		dev->dma_ops = &arm64_swiotlb_dma_ops;
 
 	dev->archdata.dma_coherent = coherent;
 	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index ca74a2aace42..7b60d62ac593 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -389,7 +389,7 @@ void ptdump_check_wx(void)
 		.check_wx = true,
 	};
 
-	walk_pgd(&st, &init_mm, 0);
+	walk_pgd(&st, &init_mm, VA_START);
 	note_page(&st, 0, 0, 0);
 	if (st.wx_pages || st.uxn_pages)
 		pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n",
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 22168cd0dde7..ce441d29e7f6 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -574,7 +574,6 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
 	struct siginfo info;
 	const struct fault_info *inf;
-	int ret = 0;
 
 	inf = esr_to_fault_info(esr);
 	pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n",
@@ -589,7 +588,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 		if (interrupts_enabled(regs))
 			nmi_enter();
 
-		ret = ghes_notify_sea();
+		ghes_notify_sea();
 
 		if (interrupts_enabled(regs))
 			nmi_exit();
@@ -597,81 +596,81 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 
 	info.si_signo = SIGBUS;
 	info.si_errno = 0;
-	info.si_code  = 0;
+	info.si_code  = BUS_FIXME;
 	if (esr & ESR_ELx_FnV)
 		info.si_addr = NULL;
 	else
 		info.si_addr  = (void __user *)addr;
 	arm64_notify_die("", regs, &info, esr);
 
-	return ret;
+	return 0;
 }
 
 static const struct fault_info fault_info[] = {
-	{ do_bad,		SIGBUS,  0,		"ttbr address size fault"	},
-	{ do_bad,		SIGBUS,  0,		"level 1 address size fault"	},
-	{ do_bad,		SIGBUS,  0,		"level 2 address size fault"	},
-	{ do_bad,		SIGBUS,  0,		"level 3 address size fault"	},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"ttbr address size fault"	},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"level 1 address size fault"	},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"level 2 address size fault"	},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"level 3 address size fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 0 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
-	{ do_bad,		SIGBUS,  0,		"unknown 8"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 8"			},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
-	{ do_bad,		SIGBUS,  0,		"unknown 12"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 12"			},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
-	{ do_sea,		SIGBUS,  0,		"synchronous external abort"	},
-	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
-	{ do_sea,		SIGBUS,  0,		"level 0 (translation table walk)"	},
-	{ do_sea,		SIGBUS,  0,		"level 1 (translation table walk)"	},
-	{ do_sea,		SIGBUS,  0,		"level 2 (translation table walk)"	},
-	{ do_sea,		SIGBUS,  0,		"level 3 (translation table walk)"	},
-	{ do_sea,		SIGBUS,  0,		"synchronous parity or ECC error" },	// Reserved when RAS is implemented
-	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
-	{ do_sea,		SIGBUS,  0,		"level 0 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
-	{ do_sea,		SIGBUS,  0,		"level 1 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
-	{ do_sea,		SIGBUS,  0,		"level 2 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
-	{ do_sea,		SIGBUS,  0,		"level 3 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
-	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
+	{ do_sea,		SIGBUS,  BUS_FIXME,	"synchronous external abort"	},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 17"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 18"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 19"			},
+	{ do_sea,		SIGBUS,  BUS_FIXME,	"level 0 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  BUS_FIXME,	"level 1 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  BUS_FIXME,	"level 2 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  BUS_FIXME,	"level 3 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  BUS_FIXME,	"synchronous parity or ECC error" },	// Reserved when RAS is implemented
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 25"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 26"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 27"			},
+	{ do_sea,		SIGBUS,  BUS_FIXME,	"level 0 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
+	{ do_sea,		SIGBUS,  BUS_FIXME,	"level 1 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
+	{ do_sea,		SIGBUS,  BUS_FIXME,	"level 2 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
+	{ do_sea,		SIGBUS,  BUS_FIXME,	"level 3 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 32"			},
 	{ do_alignment_fault,	SIGBUS,  BUS_ADRALN,	"alignment fault"		},
-	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 37"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 38"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 39"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 40"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 41"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 42"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 43"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 44"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 45"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 46"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 47"			},
-	{ do_bad,		SIGBUS,  0,		"TLB conflict abort"		},
-	{ do_bad,		SIGBUS,  0,		"Unsupported atomic hardware update fault"	},
-	{ do_bad,		SIGBUS,  0,		"unknown 50"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 51"			},
-	{ do_bad,		SIGBUS,  0,		"implementation fault (lockdown abort)" },
-	{ do_bad,		SIGBUS,  0,		"implementation fault (unsupported exclusive)" },
-	{ do_bad,		SIGBUS,  0,		"unknown 54"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 55"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 56"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 57"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 58" 			},
-	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
-	{ do_bad,		SIGBUS,  0,		"section domain fault"		},
-	{ do_bad,		SIGBUS,  0,		"page domain fault"		},
-	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 34"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 35"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 36"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 37"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 38"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 39"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 40"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 41"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 42"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 43"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 44"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 45"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 46"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 47"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"TLB conflict abort"		},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"Unsupported atomic hardware update fault"	},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 50"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 51"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"implementation fault (lockdown abort)" },
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"implementation fault (unsupported exclusive)" },
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 54"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 55"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 56"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 57"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 58" 			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 59"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 60"			},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"section domain fault"		},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"page domain fault"		},
+	{ do_bad,		SIGBUS,  BUS_FIXME,	"unknown 63"			},
 };
 
 int handle_guest_sea(phys_addr_t addr, unsigned int esr)
@@ -708,6 +707,23 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 	arm64_notify_die("", regs, &info, esr);
 }
 
+asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
+						   unsigned int esr,
+						   struct pt_regs *regs)
+{
+	/*
+	 * We've taken an instruction abort from userspace and not yet
+	 * re-enabled IRQs. If the address is a kernel address, apply
+	 * BP hardening prior to enabling IRQs and pre-emption.
+	 */
+	if (addr > TASK_SIZE)
+		arm64_apply_bp_hardening();
+
+	local_irq_enable();
+	do_mem_abort(addr, esr, regs);
+}
+
+
 asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
 					   unsigned int esr,
 					   struct pt_regs *regs)
@@ -740,11 +756,11 @@ static struct fault_info __refdata debug_fault_info[] = {
 	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware breakpoint"	},
 	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware single-step"	},
 	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware watchpoint"	},
-	{ do_bad,	SIGBUS,		0,		"unknown 3"		},
+	{ do_bad,	SIGBUS,		BUS_FIXME,	"unknown 3"		},
 	{ do_bad,	SIGTRAP,	TRAP_BRKPT,	"aarch32 BKPT"		},
-	{ do_bad,	SIGTRAP,	0,		"aarch32 vector catch"	},
+	{ do_bad,	SIGTRAP,	TRAP_FIXME,	"aarch32 vector catch"	},
 	{ early_brk64,	SIGTRAP,	TRAP_BRKPT,	"aarch64 BRK"		},
-	{ do_bad,	SIGBUS,		0,		"unknown 7"		},
+	{ do_bad,	SIGBUS,		BUS_FIXME,	"unknown 7"		},
 };
 
 void __init hook_debug_fault_code(int nr,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 5960bef0170d..9f3c47acf8ff 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -217,7 +217,7 @@ static void __init reserve_elfcorehdr(void)
 }
 #endif /* CONFIG_CRASH_DUMP */
 /*
- * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It
+ * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It
  * currently assumes that for memory starting above 4G, 32-bit devices will
  * use a DMA offset.
  */
@@ -233,8 +233,8 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA))
-		max_zone_pfns[ZONE_DMA] = PFN_DOWN(max_zone_dma_phys());
+	if (IS_ENABLED(CONFIG_ZONE_DMA32))
+		max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init_nodes(max_zone_pfns);
@@ -251,9 +251,9 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	memset(zone_size, 0, sizeof(zone_size));
 
 	/* 4GB maximum for 32-bit only capable devices */
-#ifdef CONFIG_ZONE_DMA
+#ifdef CONFIG_ZONE_DMA32
 	max_dma = PFN_DOWN(arm64_dma_phys_limit);
-	zone_size[ZONE_DMA] = max_dma - min;
+	zone_size[ZONE_DMA32] = max_dma - min;
 #endif
 	zone_size[ZONE_NORMAL] = max - max_dma;
 
@@ -266,10 +266,10 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 		if (start >= max)
 			continue;
 
-#ifdef CONFIG_ZONE_DMA
+#ifdef CONFIG_ZONE_DMA32
 		if (start < max_dma) {
 			unsigned long dma_end = min(end, max_dma);
-			zhole_size[ZONE_DMA] -= dma_end - start;
+			zhole_size[ZONE_DMA32] -= dma_end - start;
 		}
 #endif
 		if (end > max_dma) {
@@ -366,6 +366,9 @@ void __init arm64_memblock_init(void)
 	/* Handle linux,usable-memory-range property */
 	fdt_enforce_memory_region();
 
+	/* Remove memory above our supported physical address size */
+	memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);
+
 	/*
 	 * Ensure that the linear region takes up exactly half of the kernel
 	 * virtual address space. This way, we can distinguish a linear address
@@ -467,7 +470,7 @@ void __init arm64_memblock_init(void)
 	early_init_fdt_scan_reserved_mem();
 
 	/* 4GB maximum for 32-bit only capable devices */
-	if (IS_ENABLED(CONFIG_ZONE_DMA))
+	if (IS_ENABLED(CONFIG_ZONE_DMA32))
 		arm64_dma_phys_limit = max_zone_dma_phys();
 	else
 		arm64_dma_phys_limit = PHYS_MASK + 1;
@@ -476,6 +479,8 @@ void __init arm64_memblock_init(void)
 
 	reserve_elfcorehdr();
 
+	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
+
 	dma_contiguous_reserve(arm64_dma_phys_limit);
 
 	memblock_allow_resize();
@@ -502,7 +507,6 @@ void __init bootmem_init(void)
 	sparse_init();
 	zone_sizes_init(min, max);
 
-	high_memory = __va((max << PAGE_SHIFT) - 1) + 1;
 	memblock_dump_all();
 }
 
@@ -599,49 +603,6 @@ void __init mem_init(void)
 
 	mem_init_print_info(NULL);
 
-#define MLK(b, t) b, t, ((t) - (b)) >> 10
-#define MLM(b, t) b, t, ((t) - (b)) >> 20
-#define MLG(b, t) b, t, ((t) - (b)) >> 30
-#define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K)
-
-	pr_notice("Virtual kernel memory layout:\n");
-#ifdef CONFIG_KASAN
-	pr_notice("    kasan   : 0x%16lx - 0x%16lx   (%6ld GB)\n",
-		MLG(KASAN_SHADOW_START, KASAN_SHADOW_END));
-#endif
-	pr_notice("    modules : 0x%16lx - 0x%16lx   (%6ld MB)\n",
-		MLM(MODULES_VADDR, MODULES_END));
-	pr_notice("    vmalloc : 0x%16lx - 0x%16lx   (%6ld GB)\n",
-		MLG(VMALLOC_START, VMALLOC_END));
-	pr_notice("      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n",
-		MLK_ROUNDUP(_text, _etext));
-	pr_notice("    .rodata : 0x%p" " - 0x%p" "   (%6ld KB)\n",
-		MLK_ROUNDUP(__start_rodata, __init_begin));
-	pr_notice("      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n",
-		MLK_ROUNDUP(__init_begin, __init_end));
-	pr_notice("      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
-		MLK_ROUNDUP(_sdata, _edata));
-	pr_notice("       .bss : 0x%p" " - 0x%p" "   (%6ld KB)\n",
-		MLK_ROUNDUP(__bss_start, __bss_stop));
-	pr_notice("    fixed   : 0x%16lx - 0x%16lx   (%6ld KB)\n",
-		MLK(FIXADDR_START, FIXADDR_TOP));
-	pr_notice("    PCI I/O : 0x%16lx - 0x%16lx   (%6ld MB)\n",
-		MLM(PCI_IO_START, PCI_IO_END));
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-	pr_notice("    vmemmap : 0x%16lx - 0x%16lx   (%6ld GB maximum)\n",
-		MLG(VMEMMAP_START, VMEMMAP_START + VMEMMAP_SIZE));
-	pr_notice("              0x%16lx - 0x%16lx   (%6ld MB actual)\n",
-		MLM((unsigned long)phys_to_page(memblock_start_of_DRAM()),
-		    (unsigned long)virt_to_page(high_memory)));
-#endif
-	pr_notice("    memory  : 0x%16lx - 0x%16lx   (%6ld MB)\n",
-		MLM(__phys_to_virt(memblock_start_of_DRAM()),
-		    (unsigned long)high_memory));
-
-#undef MLK
-#undef MLM
-#undef MLK_ROUNDUP
-
 	/*
 	 * Check boundaries twice: Some fundamental inconsistencies can be
 	 * detected at build time already.
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 267d2b79d52d..b44992ec9643 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -50,6 +50,7 @@
 #define NO_CONT_MAPPINGS	BIT(1)
 
 u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
+u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
 
 u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);
@@ -525,6 +526,35 @@ static int __init parse_rodata(char *arg)
 }
 early_param("rodata", parse_rodata);
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static int __init map_entry_trampoline(void)
+{
+	pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+	phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
+
+	/* The trampoline is always mapped and can therefore be global */
+	pgprot_val(prot) &= ~PTE_NG;
+
+	/* Map only the text into the trampoline page table */
+	memset(tramp_pg_dir, 0, PGD_SIZE);
+	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
+			     prot, pgd_pgtable_alloc, 0);
+
+	/* Map both the text and data into the kernel page table */
+	__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+		extern char __entry_tramp_data_start[];
+
+		__set_fixmap(FIX_ENTRY_TRAMP_DATA,
+			     __pa_symbol(__entry_tramp_data_start),
+			     PAGE_KERNEL_RO);
+	}
+
+	return 0;
+}
+core_initcall(map_entry_trampoline);
+#endif
+
 /*
  * Create fine-grained mappings for the kernel.
  */
@@ -570,8 +600,8 @@ static void __init map_kernel(pgd_t *pgd)
 		 * entry instead.
 		 */
 		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
-		set_pud(pud_set_fixmap_offset(pgd, FIXADDR_START),
-			__pud(__pa_symbol(bm_pmd) | PUD_TYPE_TABLE));
+		pud_populate(&init_mm, pud_set_fixmap_offset(pgd, FIXADDR_START),
+			     lm_alias(bm_pmd));
 		pud_clear_fixmap();
 	} else {
 		BUG();
@@ -612,7 +642,8 @@ void __init paging_init(void)
 	 * allocated with it.
 	 */
 	memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE,
-		      SWAPPER_DIR_SIZE - PAGE_SIZE);
+		      __pa_symbol(swapper_pg_end) - __pa_symbol(swapper_pg_dir)
+		      - PAGE_SIZE);
 }
 
 /*
@@ -686,7 +717,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 			if (!p)
 				return -ENOMEM;
 
-			set_pmd(pmd, __pmd(__pa(p) | PROT_SECT_NORMAL));
+			pmd_set_huge(pmd, __pa(p), __pgprot(PROT_SECT_NORMAL));
 		} else
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
 	} while (addr = next, addr != end);
@@ -879,15 +910,19 @@ int __init arch_ioremap_pmd_supported(void)
 
 int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
 {
+	pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
+					pgprot_val(mk_sect_prot(prot)));
 	BUG_ON(phys & ~PUD_MASK);
-	set_pud(pud, __pud(phys | PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))));
+	set_pud(pud, pfn_pud(__phys_to_pfn(phys), sect_prot));
 	return 1;
 }
 
 int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
 {
+	pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
+					pgprot_val(mk_sect_prot(prot)));
 	BUG_ON(phys & ~PMD_MASK);
-	set_pmd(pmd, __pmd(phys | PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))));
+	set_pmd(pmd, pfn_pmd(__phys_to_pfn(phys), sect_prot));
 	return 1;
 }
 
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index 371c5f03a170..289f9113a27a 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -26,7 +26,7 @@
 #include <asm/page.h>
 #include <asm/tlbflush.h>
 
-static struct kmem_cache *pgd_cache;
+static struct kmem_cache *pgd_cache __ro_after_init;
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
@@ -49,6 +49,14 @@ void __init pgd_cache_init(void)
 	if (PGD_SIZE == PAGE_SIZE)
 		return;
 
+#ifdef CONFIG_ARM64_PA_BITS_52
+	/*
+	 * With 52-bit physical addresses, the architecture requires the
+	 * top-level table to be aligned to at least 64 bytes.
+	 */
+	BUILD_BUG_ON(PGD_SIZE < 64);
+#endif
+
 	/*
 	 * Naturally aligned pgds required by the architecture.
 	 */
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 95233dfc4c39..9f177aac6390 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -70,7 +70,11 @@ ENTRY(cpu_do_suspend)
 	mrs	x8, mdscr_el1
 	mrs	x9, oslsr_el1
 	mrs	x10, sctlr_el1
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	mrs	x11, tpidr_el1
+alternative_else
+	mrs	x11, tpidr_el2
+alternative_endif
 	mrs	x12, sp_el0
 	stp	x2, x3, [x0]
 	stp	x4, xzr, [x0, #16]
@@ -116,7 +120,11 @@ ENTRY(cpu_do_resume)
 	msr	mdscr_el1, x10
 
 	msr	sctlr_el1, x12
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	msr	tpidr_el1, x13
+alternative_else
+	msr	tpidr_el2, x13
+alternative_endif
 	msr	sp_el0, x14
 	/*
 	 * Restore oslsr_el1 by writing oslar_el1
@@ -124,6 +132,11 @@ ENTRY(cpu_do_resume)
 	ubfx	x11, x11, #1, #1
 	msr	oslar_el1, x11
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
+
+alternative_if ARM64_HAS_RAS_EXTN
+	msr_s	SYS_DISR_EL1, xzr
+alternative_else_nop_endif
+
 	isb
 	ret
 ENDPROC(cpu_do_resume)
@@ -138,13 +151,18 @@ ENDPROC(cpu_do_resume)
  *	- pgd_phys - physical address of new TTB
  */
 ENTRY(cpu_do_switch_mm)
-	pre_ttbr0_update_workaround x0, x2, x3
+	mrs	x2, ttbr1_el1
 	mmid	x1, x1				// get mm->context.id
-	bfi	x0, x1, #48, #16		// set the ASID
-	msr	ttbr0_el1, x0			// set TTBR0
+	phys_to_ttbr x0, x3
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	bfi	x3, x1, #48, #16		// set the ASID field in TTBR0
+#endif
+	bfi	x2, x1, #48, #16		// set the ASID
+	msr	ttbr1_el1, x2			// in TTBR1 (since TCR.A1 is set)
 	isb
-	post_ttbr0_update_workaround
-	ret
+	msr	ttbr0_el1, x3			// now update TTBR0
+	isb
+	b	post_ttbr_update_workaround	// Back to C code...
 ENDPROC(cpu_do_switch_mm)
 
 	.pushsection ".idmap.text", "ax"
@@ -158,14 +176,16 @@ ENTRY(idmap_cpu_replace_ttbr1)
 	save_and_disable_daif flags=x2
 
 	adrp	x1, empty_zero_page
-	msr	ttbr1_el1, x1
+	phys_to_ttbr x1, x3
+	msr	ttbr1_el1, x3
 	isb
 
 	tlbi	vmalle1
 	dsb	nsh
 	isb
 
-	msr	ttbr1_el1, x0
+	phys_to_ttbr x0, x3
+	msr	ttbr1_el1, x3
 	isb
 
 	restore_daif x2
@@ -214,25 +234,19 @@ ENTRY(__cpu_setup)
 	/*
 	 * Prepare SCTLR
 	 */
-	adr	x5, crval
-	ldp	w5, w6, [x5]
-	mrs	x0, sctlr_el1
-	bic	x0, x0, x5			// clear bits
-	orr	x0, x0, x6			// set bits
+	mov_q	x0, SCTLR_EL1_SET
 	/*
 	 * Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
 	 * both user and kernel.
 	 */
 	ldr	x10, =TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
-			TCR_TG_FLAGS | TCR_ASID16 | TCR_TBI0
+			TCR_TG_FLAGS | TCR_ASID16 | TCR_TBI0 | TCR_A1
 	tcr_set_idmap_t0sz	x10, x9
 
 	/*
-	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the IPS bits in
-	 * TCR_EL1.
+	 * Set the IPS bits in TCR_EL1.
 	 */
-	mrs	x9, ID_AA64MMFR0_EL1
-	bfi	x10, x9, #32, #3
+	tcr_compute_pa_size x10, #TCR_IPS_SHIFT, x5, x6
 #ifdef CONFIG_ARM64_HW_AFDBM
 	/*
 	 * Hardware update of the Access and Dirty bits.
@@ -249,21 +263,3 @@ ENTRY(__cpu_setup)
 	msr	tcr_el1, x10
 	ret					// return to head.S
 ENDPROC(__cpu_setup)
-
-	/*
-	 * We set the desired value explicitly, including those of the
-	 * reserved bits. The values of bits EE & E0E were set early in
-	 * el2_setup, which are left untouched below.
-	 *
-	 *                 n n            T
-	 *       U E      WT T UD     US IHBS
-	 *       CE0      XWHW CZ     ME TEEA S
-	 * .... .IEE .... NEAI TE.I ..AD DEN0 ACAM
-	 * 0011 0... 1101 ..0. ..0. 10.. .0.. .... < hardware reserved
-	 * .... .1.. .... 01.1 11.1 ..01 0.01 1101 < software settings
-	 */
-	.type	crval, #object
-crval:
-	.word	0xfcffffff			// clear
-	.word	0x34d5d91d			// set
-	.popsection
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index ba38d403abb2..1d4f1da7c58f 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -31,8 +31,6 @@
 
 #include "bpf_jit.h"
 
-int bpf_jit_enable __read_mostly;
-
 #define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
 #define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
 #define TCALL_CNT (MAX_BPF_JIT_REG + 2)
@@ -99,6 +97,20 @@ static inline void emit_a64_mov_i64(const int reg, const u64 val,
 	}
 }
 
+static inline void emit_addr_mov_i64(const int reg, const u64 val,
+				     struct jit_ctx *ctx)
+{
+	u64 tmp = val;
+	int shift = 0;
+
+	emit(A64_MOVZ(1, reg, tmp & 0xffff, shift), ctx);
+	for (;shift < 48;) {
+		tmp >>= 16;
+		shift += 16;
+		emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx);
+	}
+}
+
 static inline void emit_a64_mov_i(const int is64, const int reg,
 				  const s32 val, struct jit_ctx *ctx)
 {
@@ -148,7 +160,8 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 /* Stack must be multiples of 16B */
 #define STACK_ALIGN(sz) (((sz) + 15) & ~15)
 
-#define PROLOGUE_OFFSET 8
+/* Tail call offset to jump into */
+#define PROLOGUE_OFFSET 7
 
 static int build_prologue(struct jit_ctx *ctx)
 {
@@ -200,19 +213,19 @@ static int build_prologue(struct jit_ctx *ctx)
 	/* Initialize tail_call_cnt */
 	emit(A64_MOVZ(1, tcc, 0, 0), ctx);
 
-	/* 4 byte extra for skb_copy_bits buffer */
-	ctx->stack_size = prog->aux->stack_depth + 4;
-	ctx->stack_size = STACK_ALIGN(ctx->stack_size);
-
-	/* Set up function call stack */
-	emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
-
 	cur_offset = ctx->idx - idx0;
 	if (cur_offset != PROLOGUE_OFFSET) {
 		pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
 			    cur_offset, PROLOGUE_OFFSET);
 		return -1;
 	}
+
+	/* 4 byte extra for skb_copy_bits buffer */
+	ctx->stack_size = prog->aux->stack_depth + 4;
+	ctx->stack_size = STACK_ALIGN(ctx->stack_size);
+
+	/* Set up function call stack */
+	emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
 	return 0;
 }
 
@@ -260,11 +273,12 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	emit(A64_LDR64(prg, tmp, prg), ctx);
 	emit(A64_CBZ(1, prg, jmp_offset), ctx);
 
-	/* goto *(prog->bpf_func + prologue_size); */
+	/* goto *(prog->bpf_func + prologue_offset); */
 	off = offsetof(struct bpf_prog, bpf_func);
 	emit_a64_mov_i64(tmp, off, ctx);
 	emit(A64_LDR64(tmp, prg, tmp), ctx);
 	emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx);
+	emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
 	emit(A64_BR(tmp), ctx);
 
 	/* out: */
@@ -376,18 +390,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_DIV | BPF_X:
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
-	{
-		const u8 r0 = bpf2a64[BPF_REG_0];
-
-		/* if (src == 0) return 0 */
-		jmp_offset = 3; /* skip ahead to else path */
-		check_imm19(jmp_offset);
-		emit(A64_CBNZ(is64, src, jmp_offset), ctx);
-		emit(A64_MOVZ(1, r0, 0, 0), ctx);
-		jmp_offset = epilogue_offset(ctx);
-		check_imm26(jmp_offset);
-		emit(A64_B(jmp_offset), ctx);
-		/* else */
 		switch (BPF_OP(code)) {
 		case BPF_DIV:
 			emit(A64_UDIV(is64, dst, dst, src), ctx);
@@ -399,7 +401,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			break;
 		}
 		break;
-	}
 	case BPF_ALU | BPF_LSH | BPF_X:
 	case BPF_ALU64 | BPF_LSH | BPF_X:
 		emit(A64_LSLV(is64, dst, dst, src), ctx);
@@ -603,7 +604,10 @@ emit_cond_jmp:
 		const u8 r0 = bpf2a64[BPF_REG_0];
 		const u64 func = (u64)__bpf_call_base + imm;
 
-		emit_a64_mov_i64(tmp, func, ctx);
+		if (ctx->prog->is_func)
+			emit_addr_mov_i64(tmp, func, ctx);
+		else
+			emit_a64_mov_i64(tmp, func, ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
 		break;
@@ -835,16 +839,24 @@ static inline void bpf_flush_icache(void *start, void *end)
 	flush_icache_range((unsigned long)start, (unsigned long)end);
 }
 
+struct arm64_jit_data {
+	struct bpf_binary_header *header;
+	u8 *image;
+	struct jit_ctx ctx;
+};
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_prog *tmp, *orig_prog = prog;
 	struct bpf_binary_header *header;
+	struct arm64_jit_data *jit_data;
 	bool tmp_blinded = false;
+	bool extra_pass = false;
 	struct jit_ctx ctx;
 	int image_size;
 	u8 *image_ptr;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
@@ -858,13 +870,30 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = tmp;
 	}
 
+	jit_data = prog->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			prog = orig_prog;
+			goto out;
+		}
+		prog->aux->jit_data = jit_data;
+	}
+	if (jit_data->ctx.offset) {
+		ctx = jit_data->ctx;
+		image_ptr = jit_data->image;
+		header = jit_data->header;
+		extra_pass = true;
+		image_size = sizeof(u32) * ctx.idx;
+		goto skip_init_ctx;
+	}
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
 
 	ctx.offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
 	if (ctx.offset == NULL) {
 		prog = orig_prog;
-		goto out;
+		goto out_off;
 	}
 
 	/* 1. Initial fake pass to compute ctx->idx. */
@@ -895,6 +924,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* 2. Now, the actual pass. */
 
 	ctx.image = (__le32 *)image_ptr;
+skip_init_ctx:
 	ctx.idx = 0;
 
 	build_prologue(&ctx);
@@ -920,13 +950,31 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	bpf_flush_icache(header, ctx.image + ctx.idx);
 
-	bpf_jit_binary_lock_ro(header);
+	if (!prog->is_func || extra_pass) {
+		if (extra_pass && ctx.idx != jit_data->ctx.idx) {
+			pr_err_once("multi-func JIT bug %d != %d\n",
+				    ctx.idx, jit_data->ctx.idx);
+			bpf_jit_binary_free(header);
+			prog->bpf_func = NULL;
+			prog->jited = 0;
+			goto out_off;
+		}
+		bpf_jit_binary_lock_ro(header);
+	} else {
+		jit_data->ctx = ctx;
+		jit_data->image = image_ptr;
+		jit_data->header = header;
+	}
 	prog->bpf_func = (void *)ctx.image;
 	prog->jited = 1;
 	prog->jited_len = image_size;
 
+	if (!prog->is_func || extra_pass) {
 out_off:
-	kfree(ctx.offset);
+		kfree(ctx.offset);
+		kfree(jit_data);
+		prog->aux->jit_data = NULL;
+	}
 out:
 	if (tmp_blinded)
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?
diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S
index 401ceb71540c..c5f05c4a4d00 100644
--- a/arch/arm64/xen/hypercall.S
+++ b/arch/arm64/xen/hypercall.S
@@ -101,12 +101,12 @@ ENTRY(privcmd_call)
 	 * need the explicit uaccess_enable/disable if the TTBR0 PAN emulation
 	 * is enabled (it implies that hardware UAO and PAN disabled).
 	 */
-	uaccess_ttbr0_enable x6, x7
+	uaccess_ttbr0_enable x6, x7, x8
 	hvc XEN_IMM
 
 	/*
 	 * Disable userspace access from kernel once the hyp call completed.
 	 */
-	uaccess_ttbr0_disable x6
+	uaccess_ttbr0_disable x6, x7
 	ret
 ENDPROC(privcmd_call);
diff --git a/arch/blackfin/include/asm/clkdev.h b/arch/blackfin/include/asm/clkdev.h
deleted file mode 100644
index ded0209348c7..000000000000
--- a/arch/blackfin/include/asm/clkdev.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_CLKDEV__H_
-#define __ASM_CLKDEV__H_
-
-#include <linux/slab.h>
-
-static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size)
-{
-	return kzalloc(size, GFP_KERNEL);
-}
-
-#ifndef CONFIG_COMMON_CLK
-#define __clk_put(clk)
-#define __clk_get(clk) ({ 1; })
-#endif
-
-#endif
diff --git a/arch/blackfin/include/asm/thread_info.h b/arch/blackfin/include/asm/thread_info.h
index 2966b93850a1..a5aeab4e5f2d 100644
--- a/arch/blackfin/include/asm/thread_info.h
+++ b/arch/blackfin/include/asm/thread_info.h
@@ -56,8 +56,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 }
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
 
 /* Given a task stack pointer, you can find its corresponding
  * thread_info structure just by masking it to the THREAD_SIZE
diff --git a/arch/blackfin/include/uapi/asm/Kbuild b/arch/blackfin/include/uapi/asm/Kbuild
index aa624b4ab655..2240b38c2915 100644
--- a/arch/blackfin/include/uapi/asm/Kbuild
+++ b/arch/blackfin/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
diff --git a/arch/blackfin/include/uapi/asm/poll.h b/arch/blackfin/include/uapi/asm/poll.h
index 8b094d43e9b7..3b162f2d2970 100644
--- a/arch/blackfin/include/uapi/asm/poll.h
+++ b/arch/blackfin/include/uapi/asm/poll.h
@@ -9,8 +9,25 @@
 #ifndef _UAPI__BFIN_POLL_H
 #define _UAPI__BFIN_POLL_H
 
-#define POLLWRNORM	4 /* POLLOUT */
-#define POLLWRBAND	256
+#ifndef __KERNEL__
+#define POLLWRNORM	POLLOUT
+#define POLLWRBAND	(__force __poll_t)256
+#else
+#define __ARCH_HAS_MANGLED_POLL
+static inline __u16 mangle_poll(__poll_t val)
+{
+	__u16 v = (__force __u16)val;
+	/* bit 9 -> bit 8, bit 8 -> bit 2 */
+	return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6);
+}
+
+static inline __poll_t demangle_poll(__u16 v)
+{
+        /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
+	return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
+				((v & 4) << 6));
+}
+#endif
 
 #include <asm-generic/poll.h>
 
diff --git a/arch/blackfin/include/uapi/asm/siginfo.h b/arch/blackfin/include/uapi/asm/siginfo.h
index b1db506c8d2e..2dd8c9c39248 100644
--- a/arch/blackfin/include/uapi/asm/siginfo.h
+++ b/arch/blackfin/include/uapi/asm/siginfo.h
@@ -11,40 +11,6 @@
 #include <linux/types.h>
 #include <asm-generic/siginfo.h>
 
-#define UID16_SIGINFO_COMPAT_NEEDED
-
 #define si_uid16	_sifields._kill._uid
 
-#define ILL_ILLPARAOP	2	/* illegal opcode combine ********** */
-#define ILL_ILLEXCPT	4	/* unrecoverable exception ********** */
-#define ILL_CPLB_VI	9	/* D/I CPLB protect violation ******** */
-#define ILL_CPLB_MISS	10	/* D/I CPLB miss ******** */
-#define ILL_CPLB_MULHIT	11	/* D/I CPLB multiple hit ******** */
-#undef NSIGILL
-#define NSIGILL         11
-
-/*
- * SIGBUS si_codes
- */
-#define BUS_OPFETCH	4	/* error from instruction fetch ******** */
-#undef NSIGBUS
-#define NSIGBUS		4
-
-/*
- * SIGTRAP si_codes
- */
-#define TRAP_STEP	1	/* single-step breakpoint************* */
-#define TRAP_TRACEFLOW	2	/* trace buffer overflow ************* */
-#define TRAP_WATCHPT	3	/* watchpoint match      ************* */
-#define TRAP_ILLTRAP	4	/* illegal trap          ************* */
-#undef NSIGTRAP
-#define NSIGTRAP	4
-
-/*
- * SIGSEGV si_codes
- */
-#define SEGV_STACKFLOW	3	/* stack overflow */
-#undef NSIGSEGV
-#define NSIGSEGV	3
-
 #endif /* _UAPI_BFIN_SIGINFO_H */
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index d717329c8cf9..fd4c840de837 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -1,7 +1,6 @@
 generic-y += atomic.h
 generic-y += barrier.h
 generic-y += bugs.h
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/c6x/include/asm/thread_info.h b/arch/c6x/include/asm/thread_info.h
index acc70c135ab8..59a5697fe0f3 100644
--- a/arch/c6x/include/asm/thread_info.h
+++ b/arch/c6x/include/asm/thread_info.h
@@ -60,9 +60,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* get the thread information struct of current task */
 static inline __attribute__((const))
 struct thread_info *current_thread_info(void)
diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild
index 67ee896a76a7..26644e15d854 100644
--- a/arch/c6x/include/uapi/asm/Kbuild
+++ b/arch/c6x/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/c6x/kernel/traps.c b/arch/c6x/kernel/traps.c
index 09b8a40d5680..4c1d4b84dd2b 100644
--- a/arch/c6x/kernel/traps.c
+++ b/arch/c6x/kernel/traps.c
@@ -11,7 +11,6 @@
 #include <linux/module.h>
 #include <linux/ptrace.h>
 #include <linux/sched/debug.h>
-#include <linux/kallsyms.h>
 #include <linux/bug.h>
 
 #include <asm/soc.h>
@@ -375,8 +374,7 @@ static void show_trace(unsigned long *stack, unsigned long *endstack)
 			if (i % 5 == 0)
 				pr_debug("\n	    ");
 #endif
-			pr_debug(" [<%08lx>]", addr);
-			print_symbol(" %s\n", addr);
+			pr_debug(" [<%08lx>] %pS\n", addr, (void *)addr);
 			i++;
 		}
 	}
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index 54d3f426763b..cd5a0865c97f 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -33,6 +33,9 @@ config GENERIC_CALIBRATE_DELAY
 config NO_IOPORT_MAP
 	def_bool y if !PCI
 
+config NO_DMA
+	def_bool y if !PCI
+
 config FORCE_MAX_ZONEORDER
 	int
 	default 6
@@ -72,6 +75,7 @@ config CRIS
 	select GENERIC_SCHED_CLOCK if ETRAX_ARCH_V32
 	select HAVE_DEBUG_BUGVERBOSE if ETRAX_ARCH_V32
 	select HAVE_NMI
+	select DMA_DIRECT_OPS if PCI
 
 config HZ
 	int
diff --git a/arch/cris/arch-v10/drivers/gpio.c b/arch/cris/arch-v10/drivers/gpio.c
index 68dbe261dc57..a2986c60aaac 100644
--- a/arch/cris/arch-v10/drivers/gpio.c
+++ b/arch/cris/arch-v10/drivers/gpio.c
@@ -50,7 +50,7 @@ static ssize_t gpio_write(struct file *file, const char __user *buf,
 	size_t count, loff_t *off);
 static int gpio_open(struct inode *inode, struct file *filp);
 static int gpio_release(struct inode *inode, struct file *filp);
-static unsigned int gpio_poll(struct file *filp, struct poll_table_struct *wait);
+static __poll_t gpio_poll(struct file *filp, struct poll_table_struct *wait);
 
 /* private data per open() of this driver */
 
@@ -141,9 +141,9 @@ static unsigned long dir_g_shadow; /* 1=output */
 #define USE_PORTS(priv) ((priv)->minor <= GPIO_MINOR_B)
 
 
-static unsigned int gpio_poll(struct file *file, poll_table *wait)
+static __poll_t gpio_poll(struct file *file, poll_table *wait)
 {
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 	struct gpio_private *priv = file->private_data;
 	unsigned long data;
 	unsigned long flags;
diff --git a/arch/cris/arch-v10/drivers/sync_serial.c b/arch/cris/arch-v10/drivers/sync_serial.c
index cfe9176f2205..177843c64071 100644
--- a/arch/cris/arch-v10/drivers/sync_serial.c
+++ b/arch/cris/arch-v10/drivers/sync_serial.c
@@ -157,7 +157,7 @@ static inline int sync_data_avail(struct sync_port *port);
 
 static int sync_serial_open(struct inode *inode, struct file *file);
 static int sync_serial_release(struct inode *inode, struct file *file);
-static unsigned int sync_serial_poll(struct file *filp, poll_table *wait);
+static __poll_t sync_serial_poll(struct file *filp, poll_table *wait);
 
 static long sync_serial_ioctl(struct file *file,
 	unsigned int cmd, unsigned long arg);
@@ -654,12 +654,12 @@ static int sync_serial_release(struct inode *inode, struct file *file)
 
 
 
-static unsigned int sync_serial_poll(struct file *file, poll_table *wait)
+static __poll_t sync_serial_poll(struct file *file, poll_table *wait)
 {
 	int dev = MINOR(file_inode(file)->i_rdev);
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 	struct sync_port *port;
-	DEBUGPOLL(static unsigned int prev_mask = 0);
+	DEBUGPOLL(static __poll_t prev_mask = 0);
 
 	port = &ports[dev];
 	poll_wait(file, &port->out_wait_q, wait);
diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c
index d688fe117dca..a3c353472a8c 100644
--- a/arch/cris/arch-v32/drivers/cryptocop.c
+++ b/arch/cris/arch-v32/drivers/cryptocop.c
@@ -2717,37 +2717,28 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
 		}
 	}
 
-	/* Acquire the mm page semaphore. */
-	down_read(&current->mm->mmap_sem);
-
-	err = get_user_pages((unsigned long int)(oper.indata + prev_ix),
+	err = get_user_pages_fast((unsigned long)(oper.indata + prev_ix),
 			     noinpages,
-			     0,  /* read access only for in data */
-			     inpages,
-			     NULL);
+			     false,  /* read access only for in data */
+			     inpages);
 
 	if (err < 0) {
-		up_read(&current->mm->mmap_sem);
 		nooutpages = noinpages = 0;
 		DEBUG_API(printk("cryptocop_ioctl_process: get_user_pages indata\n"));
 		goto error_cleanup;
 	}
 	noinpages = err;
-	if (oper.do_cipher){
-		err = get_user_pages((unsigned long int)oper.cipher_outdata,
+	if (oper.do_cipher) {
+		err = get_user_pages_fast((unsigned long)oper.cipher_outdata,
 				     nooutpages,
-				     FOLL_WRITE, /* write access for out data */
-				     outpages,
-				     NULL);
-		up_read(&current->mm->mmap_sem);
+				     true, /* write access for out data */
+				     outpages);
 		if (err < 0) {
 			nooutpages = 0;
 			DEBUG_API(printk("cryptocop_ioctl_process: get_user_pages outdata\n"));
 			goto error_cleanup;
 		}
 		nooutpages = err;
-	} else {
-		up_read(&current->mm->mmap_sem);
 	}
 
 	/* Add 6 to nooutpages to make room for possibly inserted buffers for storing digest and
diff --git a/arch/cris/arch-v32/drivers/pci/Makefile b/arch/cris/arch-v32/drivers/pci/Makefile
index bff7482f2444..93c8be6170b1 100644
--- a/arch/cris/arch-v32/drivers/pci/Makefile
+++ b/arch/cris/arch-v32/drivers/pci/Makefile
@@ -2,4 +2,4 @@
 # Makefile for Etrax cardbus driver
 #
 
-obj-$(CONFIG_ETRAX_CARDBUS)        += bios.o dma.o
+obj-$(CONFIG_ETRAX_CARDBUS)        += bios.o
diff --git a/arch/cris/arch-v32/drivers/pci/dma.c b/arch/cris/arch-v32/drivers/pci/dma.c
deleted file mode 100644
index dbbd3816cc0b..000000000000
--- a/arch/cris/arch-v32/drivers/pci/dma.c
+++ /dev/null
@@ -1,80 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Dynamic DMA mapping support.
- *
- * On cris there is no hardware dynamic DMA address translation,
- * so consistent alloc/free are merely page allocation/freeing.
- * The rest of the dynamic DMA mapping interface is implemented
- * in asm/pci.h.
- *
- * Borrowed from i386.
- */
-
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-#include <linux/pci.h>
-#include <linux/gfp.h>
-#include <asm/io.h>
-
-static void *v32_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret;
-
-	/* ignore region specifiers */
-	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
-
-	if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
-		gfp |= GFP_DMA;
-
-	ret = (void *)__get_free_pages(gfp,  get_order(size));
-
-	if (ret != NULL) {
-		memset(ret, 0, size);
-		*dma_handle = virt_to_phys(ret);
-	}
-	return ret;
-}
-
-static void v32_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-}
-
-static inline dma_addr_t v32_dma_map_page(struct device *dev,
-		struct page *page, unsigned long offset, size_t size,
-		enum dma_data_direction direction, unsigned long attrs)
-{
-	return page_to_phys(page) + offset;
-}
-
-static inline int v32_dma_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	printk("Map sg\n");
-	return nents;
-}
-
-static inline int v32_dma_supported(struct device *dev, u64 mask)
-{
-        /*
-         * we fall back to GFP_DMA when the mask isn't all 1s,
-         * so we can't guarantee allocations that must be
-         * within a tighter range than GFP_DMA..
-         */
-        if (mask < 0x00ffffff)
-                return 0;
-	return 1;
-}
-
-const struct dma_map_ops v32_dma_ops = {
-	.alloc			= v32_dma_alloc,
-	.free			= v32_dma_free,
-	.map_page		= v32_dma_map_page,
-	.map_sg                 = v32_dma_map_sg,
-	.dma_supported		= v32_dma_supported,
-};
-EXPORT_SYMBOL(v32_dma_ops);
diff --git a/arch/cris/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c
index 8efcc1a899a8..e20e0b9a3a5c 100644
--- a/arch/cris/arch-v32/drivers/sync_serial.c
+++ b/arch/cris/arch-v32/drivers/sync_serial.c
@@ -178,7 +178,7 @@ static inline int sync_data_avail(struct sync_port *port);
 
 static int sync_serial_open(struct inode *, struct file *);
 static int sync_serial_release(struct inode *, struct file *);
-static unsigned int sync_serial_poll(struct file *filp, poll_table *wait);
+static __poll_t sync_serial_poll(struct file *filp, poll_table *wait);
 
 static long sync_serial_ioctl(struct file *file,
 			      unsigned int cmd, unsigned long arg);
@@ -555,13 +555,13 @@ static int sync_serial_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static unsigned int sync_serial_poll(struct file *file, poll_table *wait)
+static __poll_t sync_serial_poll(struct file *file, poll_table *wait)
 {
 	int dev = iminor(file_inode(file));
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 	struct sync_port *port;
 	DEBUGPOLL(
-	static unsigned int prev_mask;
+	static __poll_t prev_mask;
 	);
 
 	port = &ports[dev];
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index 460349cb147f..6a547fe8752b 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -1,10 +1,10 @@
 generic-y += atomic.h
 generic-y += barrier.h
-generic-y += clkdev.h
 generic-y += cmpxchg.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/cris/include/asm/dma-mapping.h b/arch/cris/include/asm/dma-mapping.h
deleted file mode 100644
index 1553bdb30a0c..000000000000
--- a/arch/cris/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_CRIS_DMA_MAPPING_H
-#define _ASM_CRIS_DMA_MAPPING_H
-
-#ifdef CONFIG_PCI
-extern const struct dma_map_ops v32_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &v32_dma_ops;
-}
-#else
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	BUG();
-	return NULL;
-}
-#endif
-
-#endif
diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h
index 124dd5ec7f65..ee4d8b03d048 100644
--- a/arch/cris/include/asm/processor.h
+++ b/arch/cris/include/asm/processor.h
@@ -26,13 +26,6 @@ struct task_struct;
  */
 #define TASK_UNMAPPED_BASE      (PAGE_ALIGN(TASK_SIZE / 3))
 
-/* THREAD_SIZE is the size of the thread_info/kernel_stack combo.
- * normally, the stack is found by doing something like p + THREAD_SIZE
- * in CRIS, a page is 8192 bytes, which seems like a sane size
- */
-#define THREAD_SIZE       PAGE_SIZE
-#define THREAD_SIZE_ORDER (0)
-
 /*
  * At user->kernel entry, the pt_regs struct is stacked on the top of the kernel-stack.
  * This macro allows us to find those regs for a task.
@@ -59,8 +52,6 @@ static inline void release_thread(struct task_struct *dead_task)
         /* Nothing needs to be done.  */
 }
 
-#define init_stack      (init_thread_union.stack)
-
 #define cpu_relax()     barrier()
 
 void default_idle(void);
diff --git a/arch/cris/include/asm/thread_info.h b/arch/cris/include/asm/thread_info.h
index 472830c90997..996fef3be1d5 100644
--- a/arch/cris/include/asm/thread_info.h
+++ b/arch/cris/include/asm/thread_info.h
@@ -20,6 +20,13 @@
 #endif
 
 
+/* THREAD_SIZE is the size of the thread_info/kernel_stack combo.
+ * normally, the stack is found by doing something like p + THREAD_SIZE
+ * in CRIS, a page is 8192 bytes, which seems like a sane size
+ */
+#define THREAD_SIZE       PAGE_SIZE
+#define THREAD_SIZE_ORDER (0)
+
 /*
  * low level task data that entry.S needs immediate access to
  * - this struct should fit entirely inside of one cache line
@@ -56,8 +63,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,			\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-
 #endif /* !__ASSEMBLY__ */
 
 /*
diff --git a/arch/cris/include/uapi/asm/Kbuild b/arch/cris/include/uapi/asm/Kbuild
index 3687b54bb18e..3470c6e9c7b9 100644
--- a/arch/cris/include/uapi/asm/Kbuild
+++ b/arch/cris/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/cris/kernel/Makefile b/arch/cris/kernel/Makefile
index af075a5fb9aa..e69de29bb2d1 100644
--- a/arch/cris/kernel/Makefile
+++ b/arch/cris/kernel/Makefile
@@ -1,19 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-# $Id: Makefile,v 1.12 2004/10/19 13:07:43 starvik Exp $
-#
-# Makefile for the linux kernel.
-#
-
-CPPFLAGS_vmlinux.lds := -DDRAM_VIRTUAL_BASE=0x$(CONFIG_ETRAX_DRAM_VIRTUAL_BASE)
-extra-y	:= vmlinux.lds
-
-obj-y   := process.o traps.o irq.o ptrace.o setup.o time.o sys_cris.o
-obj-y += devicetree.o
-obj-y += stacktrace.o
-
-obj-$(CONFIG_MODULES)    += crisksyms.o
-obj-$(CONFIG_MODULES)	 += module.o
-obj-$(CONFIG_SYSTEM_PROFILER)   += profile.o
-
-clean:
-
diff --git a/arch/cris/kernel/devicetree.c b/arch/cris/kernel/devicetree.c
deleted file mode 100644
index 36e1c658229f..000000000000
--- a/arch/cris/kernel/devicetree.c
+++ /dev/null
@@ -1,15 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/printk.h>
-
-void __init early_init_dt_add_memory_arch(u64 base, u64 size)
-{
-	pr_err("%s(%llx, %llx)\n",
-	       __func__, base, size);
-}
-
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return alloc_bootmem_align(size, align);
-}
diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S
index 6d1dbc1ba767..9b232e0f673e 100644
--- a/arch/cris/kernel/vmlinux.lds.S
+++ b/arch/cris/kernel/vmlinux.lds.S
@@ -11,6 +11,7 @@
 
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/page.h>
+#include <asm/thread_info.h>
 
 #ifdef CONFIG_ETRAX_VMEM_SIZE
 #define __CONFIG_ETRAX_VMEM_SIZE CONFIG_ETRAX_VMEM_SIZE
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 2cf7648787b2..b16b9c48ea09 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -1,5 +1,4 @@
 
-generic-y += clkdev.h
 generic-y += device.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/frv/include/asm/thread_info.h b/arch/frv/include/asm/thread_info.h
index ccba3b6ce918..0f950845fad9 100644
--- a/arch/frv/include/asm/thread_info.h
+++ b/arch/frv/include/asm/thread_info.h
@@ -64,9 +64,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* how to get the thread information struct from C */
 register struct thread_info *__current_thread_info asm("gr15");
 
diff --git a/arch/frv/include/uapi/asm/Kbuild b/arch/frv/include/uapi/asm/Kbuild
index b15bf6bc0e94..5354b0f84d41 100644
--- a/arch/frv/include/uapi/asm/Kbuild
+++ b/arch/frv/include/uapi/asm/Kbuild
@@ -1,2 +1,5 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
+
+generic-y += siginfo.h
+generic-y += bpf_perf_event.h
diff --git a/arch/frv/include/uapi/asm/poll.h b/arch/frv/include/uapi/asm/poll.h
index 887b67288340..a44c8f0ebee7 100644
--- a/arch/frv/include/uapi/asm/poll.h
+++ b/arch/frv/include/uapi/asm/poll.h
@@ -2,12 +2,27 @@
 #ifndef _ASM_POLL_H
 #define _ASM_POLL_H
 
+#ifndef __KERNEL__
 #define POLLWRNORM	POLLOUT
-#define POLLWRBAND	256
+#define POLLWRBAND	(__force __poll_t)256
+#else
+#define __ARCH_HAS_MANGLED_POLL
+static inline __u16 mangle_poll(__poll_t val)
+{
+	__u16 v = (__force __u16)val;
+	/* bit 9 -> bit 8, bit 8 -> bit 2 */
+	return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6);
+}
 
-#include <asm-generic/poll.h>
+static inline __poll_t demangle_poll(__u16 v)
+{
+        /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
+	return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
+				((v & 4) << 6));
+}
+#endif
 
+#include <asm-generic/poll.h>
 #undef POLLREMOVE
 
 #endif
-
diff --git a/arch/frv/include/uapi/asm/siginfo.h b/arch/frv/include/uapi/asm/siginfo.h
deleted file mode 100644
index 4c8c975747ac..000000000000
--- a/arch/frv/include/uapi/asm/siginfo.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_SIGINFO_H
-#define _ASM_SIGINFO_H
-
-#include <linux/types.h>
-#include <asm-generic/siginfo.h>
-
-#define FPE_MDAOVF	9	/* media overflow */
-#undef NSIGFPE
-#define NSIGFPE		9
-
-#endif
-
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index f8d3fde08190..091d6d04b5e5 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -23,6 +23,7 @@ config H8300
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_HASH
 	select CPU_NO_EFFICIENT_FFS
+	select DMA_DIRECT_OPS
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index bc077491d299..14bac06b7116 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -3,12 +3,12 @@ generic-y += barrier.h
 generic-y += bugs.h
 generic-y += cacheflush.h
 generic-y += checksum.h
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += dma.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/h8300/include/asm/dma-mapping.h b/arch/h8300/include/asm/dma-mapping.h
deleted file mode 100644
index 21bb1fc3a6f1..000000000000
--- a/arch/h8300/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _H8300_DMA_MAPPING_H
-#define _H8300_DMA_MAPPING_H
-
-extern const struct dma_map_ops h8300_dma_map_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &h8300_dma_map_ops;
-}
-
-#endif
diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h
index 072b92c0d8b5..0cdaa302d3d2 100644
--- a/arch/h8300/include/asm/thread_info.h
+++ b/arch/h8300/include/asm/thread_info.h
@@ -46,9 +46,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* how to get the thread information struct from C */
 static inline struct thread_info *current_thread_info(void)
 {
diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild
index 187aed820e71..2f65f78792cb 100644
--- a/arch/h8300/include/uapi/asm/Kbuild
+++ b/arch/h8300/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/h8300/kernel/Makefile b/arch/h8300/kernel/Makefile
index b62e830525c6..307aa51576dd 100644
--- a/arch/h8300/kernel/Makefile
+++ b/arch/h8300/kernel/Makefile
@@ -7,7 +7,7 @@ extra-y := vmlinux.lds
 
 obj-y := process.o traps.o ptrace.o \
 	 signal.o setup.o syscalls.o \
-	 irq.o entry.o dma.o
+	 irq.o entry.o
 
 obj-$(CONFIG_ROMKERNEL) += head_rom.o
 obj-$(CONFIG_RAMKERNEL) += head_ram.o
diff --git a/arch/h8300/kernel/dma.c b/arch/h8300/kernel/dma.c
deleted file mode 100644
index 225dd0a188dc..000000000000
--- a/arch/h8300/kernel/dma.c
+++ /dev/null
@@ -1,69 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-
-#include <linux/dma-mapping.h>
-#include <linux/kernel.h>
-#include <linux/scatterlist.h>
-#include <linux/module.h>
-#include <asm/pgalloc.h>
-
-static void *dma_alloc(struct device *dev, size_t size,
-		       dma_addr_t *dma_handle, gfp_t gfp,
-		       unsigned long attrs)
-{
-	void *ret;
-
-	/* ignore region specifiers */
-	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
-
-	if (dev == NULL || (*dev->dma_mask < 0xffffffff))
-		gfp |= GFP_DMA;
-	ret = (void *)__get_free_pages(gfp, get_order(size));
-
-	if (ret != NULL) {
-		memset(ret, 0, size);
-		*dma_handle = virt_to_phys(ret);
-	}
-	return ret;
-}
-
-static void dma_free(struct device *dev, size_t size,
-		     void *vaddr, dma_addr_t dma_handle,
-		     unsigned long attrs)
-
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-}
-
-static dma_addr_t map_page(struct device *dev, struct page *page,
-				  unsigned long offset, size_t size,
-				  enum dma_data_direction direction,
-				  unsigned long attrs)
-{
-	return page_to_phys(page) + offset;
-}
-
-static int map_sg(struct device *dev, struct scatterlist *sgl,
-		  int nents, enum dma_data_direction direction,
-		  unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i) {
-		sg->dma_address = sg_phys(sg);
-	}
-
-	return nents;
-}
-
-const struct dma_map_ops h8300_dma_map_ops = {
-	.alloc = dma_alloc,
-	.free = dma_free,
-	.map_page = map_page,
-	.map_sg = map_sg,
-};
-EXPORT_SYMBOL(h8300_dma_map_ops);
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 4a23e527d651..e9743f689fb8 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -2,7 +2,6 @@
 generic-y += barrier.h
 generic-y += bug.h
 generic-y += bugs.h
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/hexagon/include/asm/dma-mapping.h b/arch/hexagon/include/asm/dma-mapping.h
index 5208de242e79..263f6acbfb0f 100644
--- a/arch/hexagon/include/asm/dma-mapping.h
+++ b/arch/hexagon/include/asm/dma-mapping.h
@@ -37,11 +37,4 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return dma_ops;
 }
 
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return 0;
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
 #endif
diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h
index 66f5e9a61efc..9e8621d94ee9 100644
--- a/arch/hexagon/include/asm/io.h
+++ b/arch/hexagon/include/asm/io.h
@@ -330,8 +330,6 @@ static inline void outsl(unsigned long port, const void *buffer, int count)
 	}
 }
 
-#define flush_write_buffers() do { } while (0)
-
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/arch/hexagon/include/asm/thread_info.h b/arch/hexagon/include/asm/thread_info.h
index b80fe1db7b64..f41f9c6f0e31 100644
--- a/arch/hexagon/include/asm/thread_info.h
+++ b/arch/hexagon/include/asm/thread_info.h
@@ -84,9 +84,6 @@ struct thread_info {
 	.regs = NULL,			\
 }
 
-#define init_thread_info        (init_thread_union.thread_info)
-#define init_stack              (init_thread_union.stack)
-
 /* Tacky preprocessor trickery */
 #define	qqstr(s) qstr(s)
 #define qstr(s) #s
diff --git a/arch/hexagon/include/uapi/asm/Kbuild b/arch/hexagon/include/uapi/asm/Kbuild
index cb5df3aad3a8..41a176dbb53e 100644
--- a/arch/hexagon/include/uapi/asm/Kbuild
+++ b/arch/hexagon/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index 546792d176a4..ad8347c29dcf 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/bootmem.h>
 #include <linux/genalloc.h>
 #include <asm/dma-mapping.h>
diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S
index ec87e67feb19..ad69d181c939 100644
--- a/arch/hexagon/kernel/vmlinux.lds.S
+++ b/arch/hexagon/kernel/vmlinux.lds.S
@@ -22,6 +22,8 @@
 #include <asm/asm-offsets.h>	/*  Most of the kernel defines are here  */
 #include <asm/mem-layout.h>	/*  except for page_offset  */
 #include <asm/cache.h>		/*  and now we're pulling cache line size  */
+#include <asm/thread_info.h>	/*  and we need THREAD_SIZE too */
+
 OUTPUT_ARCH(hexagon)
 ENTRY(stext)
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 49583c5a5d44..bbe12a038d21 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -33,6 +33,7 @@ config IA64
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_VIRT_CPU_ACCOUNTING
+	select ARCH_HAS_DMA_MARK_CLEAN
 	select ARCH_HAS_SG_CHAIN
 	select VIRT_TO_BUS
 	select ARCH_DISCARD_MEMBLOCK
@@ -43,7 +44,7 @@ config IA64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_IOMAP
 	select GENERIC_SMP_IDLE_THREAD
-	select ARCH_INIT_TASK
+	select ARCH_TASK_STRUCT_ON_STACK
 	select ARCH_TASK_STRUCT_ALLOCATOR
 	select ARCH_THREAD_STACK_ALLOCATOR
 	select ARCH_CLOCKSOURCE_DATA
@@ -65,7 +66,7 @@ config 64BIT
 	select ATA_NONSTANDARD if ATA
 	default y
 
-config ZONE_DMA
+config ZONE_DMA32
 	def_bool y
 	depends on !IA64_SGI_SN2
 
@@ -145,6 +146,7 @@ config IA64_GENERIC
 	bool "generic"
 	select NUMA
 	select ACPI_NUMA
+	select DMA_DIRECT_OPS
 	select SWIOTLB
 	select PCI_MSI
 	help
@@ -165,6 +167,7 @@ config IA64_GENERIC
 
 config IA64_DIG
 	bool "DIG-compliant"
+	select DMA_DIRECT_OPS
 	select SWIOTLB
 
 config IA64_DIG_VTD
@@ -180,6 +183,7 @@ config IA64_HP_ZX1
 
 config IA64_HP_ZX1_SWIOTLB
 	bool "HP-zx1/sx1000 with software I/O TLB"
+	select DMA_DIRECT_OPS
 	select SWIOTLB
 	help
 	  Build a kernel that runs on HP zx1 and sx1000 systems even when they
@@ -203,6 +207,7 @@ config IA64_SGI_UV
 	bool "SGI-UV"
 	select NUMA
 	select ACPI_NUMA
+	select DMA_DIRECT_OPS
 	select SWIOTLB
 	help
 	  Selecting this option will optimize the kernel for use on UV based
@@ -213,6 +218,7 @@ config IA64_SGI_UV
 
 config IA64_HP_SIM
 	bool "Ski-simulator"
+	select DMA_DIRECT_OPS
 	select SWIOTLB
 	depends on !PM
 
diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index c100d780f1eb..2dd7f519ad0b 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -42,7 +42,7 @@ $(error Sorry, you need a newer version of the assember, one that is built from
 endif
 
 KBUILD_CFLAGS += $(cflags-y)
-head-y := arch/ia64/kernel/head.o arch/ia64/kernel/init_task.o
+head-y := arch/ia64/kernel/head.o
 
 libs-y				+= arch/ia64/lib/
 core-y				+= arch/ia64/kernel/ arch/ia64/mm/
diff --git a/arch/ia64/hp/common/hwsw_iommu.c b/arch/ia64/hp/common/hwsw_iommu.c
index 63d8e1d2477f..58969039bed2 100644
--- a/arch/ia64/hp/common/hwsw_iommu.c
+++ b/arch/ia64/hp/common/hwsw_iommu.c
@@ -19,7 +19,7 @@
 #include <linux/export.h>
 #include <asm/machvec.h>
 
-extern const struct dma_map_ops sba_dma_ops, swiotlb_dma_ops;
+extern const struct dma_map_ops sba_dma_ops;
 
 /* swiotlb declarations & definitions: */
 extern int swiotlb_late_init_with_default_size (size_t size);
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 1d7641f891e1..6dd867873364 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -1,4 +1,3 @@
-generic-y += clkdev.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
diff --git a/arch/ia64/include/asm/asm-prototypes.h b/arch/ia64/include/asm/asm-prototypes.h
index c711536674e3..a96689447a74 100644
--- a/arch/ia64/include/asm/asm-prototypes.h
+++ b/arch/ia64/include/asm/asm-prototypes.h
@@ -9,7 +9,7 @@
 #include <asm/page.h>
 #include <asm/pal.h>
 #include <asm/string.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unwind.h>
 #include <asm/xor.h>
 
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 28e02c99be6d..762eeb0fcc1d 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -65,29 +65,30 @@ ia64_atomic_fetch_##op (int i, atomic_t *v)				\
 ATOMIC_OPS(add, +)
 ATOMIC_OPS(sub, -)
 
-#define atomic_add_return(i,v)						\
+#ifdef __OPTIMIZE__
+#define __ia64_atomic_const(i)	__builtin_constant_p(i) ?		\
+		((i) == 1 || (i) == 4 || (i) == 8 || (i) == 16 ||	\
+		 (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0
+
+#define atomic_add_return(i, v)						\
 ({									\
-	int __ia64_aar_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
-		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
-		: ia64_atomic_add(__ia64_aar_i, v);			\
+	int __i = (i);							\
+	static const int __ia64_atomic_p = __ia64_atomic_const(i);	\
+	__ia64_atomic_p ? ia64_fetch_and_add(__i, &(v)->counter) :	\
+				ia64_atomic_add(__i, v);		\
 })
 
-#define atomic_sub_return(i,v)						\
+#define atomic_sub_return(i, v)						\
 ({									\
-	int __ia64_asr_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
-		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
-		: ia64_atomic_sub(__ia64_asr_i, v);			\
+	int __i = (i);							\
+	static const int __ia64_atomic_p = __ia64_atomic_const(i);	\
+	__ia64_atomic_p ? ia64_fetch_and_add(-__i, &(v)->counter) :	\
+				ia64_atomic_sub(__i, v);		\
 })
+#else
+#define atomic_add_return(i, v)	ia64_atomic_add(i, v)
+#define atomic_sub_return(i, v)	ia64_atomic_sub(i, v)
+#endif
 
 #define atomic_fetch_add(i,v)						\
 ({									\
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index c1bab526a046..76e4d6632d68 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -8,7 +8,6 @@
  */
 #include <asm/machvec.h>
 #include <linux/scatterlist.h>
-#include <asm/swiotlb.h>
 #include <linux/dma-debug.h>
 
 #define ARCH_HAS_DMA_GET_REQUIRED_MASK
@@ -27,22 +26,4 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return platform_dma_get_ops(NULL);
 }
 
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return 0;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return paddr;
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return daddr;
-}
-
 #endif /* _ASM_IA64_DMA_MAPPING_H */
diff --git a/arch/ia64/include/asm/dma.h b/arch/ia64/include/asm/dma.h
index 186850eec934..23604d6a2cb2 100644
--- a/arch/ia64/include/asm/dma.h
+++ b/arch/ia64/include/asm/dma.h
@@ -20,6 +20,4 @@ extern unsigned long MAX_DMA_ADDRESS;
 
 #define free_dma(x)
 
-void dma_mark_clean(void *addr, size_t size);
-
 #endif /* _ASM_IA64_DMA_H */
diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h
index f3481408594e..cea15f2dd38d 100644
--- a/arch/ia64/include/asm/sections.h
+++ b/arch/ia64/include/asm/sections.h
@@ -27,6 +27,8 @@ extern char __start_gate_brl_fsys_bubble_down_patchlist[], __end_gate_brl_fsys_b
 extern char __start_unwind[], __end_unwind[];
 extern char __start_ivt_text[], __end_ivt_text[];
 
+#define HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR 1
+
 #undef dereference_function_descriptor
 static inline void *dereference_function_descriptor(void *ptr)
 {
@@ -38,6 +40,12 @@ static inline void *dereference_function_descriptor(void *ptr)
 	return ptr;
 }
 
+#undef dereference_kernel_function_descriptor
+static inline void *dereference_kernel_function_descriptor(void *ptr)
+{
+	if (ptr < (void *)__start_opd || ptr >= (void *)__end_opd)
+		return ptr;
+	return dereference_function_descriptor(ptr);
+}
 
 #endif /* _ASM_IA64_SECTIONS_H */
-
diff --git a/arch/ia64/include/asm/swiotlb.h b/arch/ia64/include/asm/swiotlb.h
deleted file mode 100644
index 841e2c7d0b21..000000000000
--- a/arch/ia64/include/asm/swiotlb.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_IA64__SWIOTLB_H
-#define ASM_IA64__SWIOTLB_H
-
-#include <linux/dma-mapping.h>
-#include <linux/swiotlb.h>
-
-#ifdef CONFIG_SWIOTLB
-extern int swiotlb;
-extern void pci_swiotlb_init(void);
-#else
-#define swiotlb 0
-static inline void pci_swiotlb_init(void)
-{
-}
-#endif
-
-#endif /* ASM_IA64__SWIOTLB_H */
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index 1d172a4119a7..64a1011f6812 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -12,6 +12,8 @@
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 
+#define THREAD_SIZE			KERNEL_STACK_SIZE
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -41,8 +43,6 @@ struct thread_info {
 #endif
 };
 
-#define THREAD_SIZE			KERNEL_STACK_SIZE
-
 #define INIT_THREAD_INFO(tsk)			\
 {						\
 	.task		= &tsk,			\
diff --git a/arch/ia64/include/uapi/asm/Kbuild b/arch/ia64/include/uapi/asm/Kbuild
index 13a97aa2285f..c0527cfc48f0 100644
--- a/arch/ia64/include/uapi/asm/Kbuild
+++ b/arch/ia64/include/uapi/asm/Kbuild
@@ -1,4 +1,6 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += kvm_para.h
+generic-y += poll.h
diff --git a/arch/ia64/include/uapi/asm/poll.h b/arch/ia64/include/uapi/asm/poll.h
deleted file mode 100644
index b7132a305a47..000000000000
--- a/arch/ia64/include/uapi/asm/poll.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/poll.h>
diff --git a/arch/ia64/include/uapi/asm/siginfo.h b/arch/ia64/include/uapi/asm/siginfo.h
index f3a02a10c3a3..5aa454ed89db 100644
--- a/arch/ia64/include/uapi/asm/siginfo.h
+++ b/arch/ia64/include/uapi/asm/siginfo.h
@@ -11,77 +11,8 @@
 
 #define __ARCH_SI_PREAMBLE_SIZE	(4 * sizeof(int))
 
-#define HAVE_ARCH_SIGINFO_T
-#define HAVE_ARCH_COPY_SIGINFO_TO_USER
-
 #include <asm-generic/siginfo.h>
 
-typedef struct siginfo {
-	int si_signo;
-	int si_errno;
-	int si_code;
-	int __pad0;
-
-	union {
-		int _pad[SI_PAD_SIZE];
-
-		/* kill() */
-		struct {
-			pid_t _pid;		/* sender's pid */
-			uid_t _uid;		/* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			timer_t _tid;		/* timer id */
-			int _overrun;		/* overrun count */
-			char _pad[sizeof(__ARCH_SI_UID_T) - sizeof(int)];
-			sigval_t _sigval;	/* must overlay ._rt._sigval! */
-			int _sys_private;	/* not to be passed to user */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			pid_t _pid;		/* sender's pid */
-			uid_t _uid;		/* sender's uid */
-			sigval_t _sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			pid_t _pid;		/* which child */
-			uid_t _uid;		/* sender's uid */
-			int _status;		/* exit code */
-			clock_t _utime;
-			clock_t _stime;
-		} _sigchld;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
-		struct {
-			void __user *_addr;	/* faulting insn/memory ref. */
-			int _imm;		/* immediate value for "break" */
-			unsigned int _flags;	/* see below */
-			unsigned long _isr;	/* isr */
-			short _addr_lsb;	/* lsb of faulting address */
-			union {
-				/* used when si_code=SEGV_BNDERR */
-				struct {
-					void __user *_lower;
-					void __user *_upper;
-				} _addr_bnd;
-				/* used when si_code=SEGV_PKUERR */
-				__u32 _pkey;
-			};
-		} _sigfault;
-
-		/* SIGPOLL */
-		struct {
-			long _band;	/* POLL_IN, POLL_OUT, POLL_MSG (XPG requires a "long") */
-			int _fd;
-		} _sigpoll;
-	} _sifields;
-} siginfo_t;
-
 #define si_imm		_sifields._sigfault._imm	/* as per UNIX SysV ABI spec */
 #define si_flags	_sifields._sigfault._flags
 /*
@@ -97,37 +28,10 @@ typedef struct siginfo {
 #define __ISR_VALID	(1 << __ISR_VALID_BIT)
 
 /*
- * SIGILL si_codes
- */
-#define ILL_BADIADDR	9	/* unimplemented instruction address */
-#define __ILL_BREAK	10	/* illegal break */
-#define __ILL_BNDMOD	11	/* bundle-update (modification) in progress */
-#undef NSIGILL
-#define NSIGILL		11
-
-/*
  * SIGFPE si_codes
  */
 #ifdef __KERNEL__
 #define FPE_FIXME	0	/* Broken dup of SI_USER */
 #endif /* __KERNEL__ */
-#define __FPE_DECOVF	9	/* decimal overflow */
-#define __FPE_DECDIV	10	/* decimal division by zero */
-#define __FPE_DECERR	11	/* packed decimal error */
-#define __FPE_INVASC	12	/* invalid ASCII digit */
-#define __FPE_INVDEC	13	/* invalid decimal digit */
-#undef NSIGFPE
-#define NSIGFPE		13
-
-/*
- * SIGSEGV si_codes
- */
-#define __SEGV_PSTKOVF	4	/* paragraph stack overflow */
-#undef NSIGSEGV
-#define NSIGSEGV	4
-
-#undef NSIGTRAP
-#define NSIGTRAP	4
-
 
 #endif /* _UAPI_ASM_IA64_SIGINFO_H */
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 14ad79f394e5..0b4c65a1af25 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -7,7 +7,7 @@ ifdef CONFIG_DYNAMIC_FTRACE
 CFLAGS_REMOVE_ftrace.o = -pg
 endif
 
-extra-y	:= head.o init_task.o vmlinux.lds
+extra-y	:= head.o vmlinux.lds
 
 obj-y := entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o	\
 	 irq_lsapic.o ivt.o machvec.o pal.o patch.o process.o perfmon.o ptrace.o sal.o		\
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 1d29b2f8726b..1dacbf5e9e09 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -504,6 +504,11 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 	if (!(ma->flags & ACPI_SRAT_MEM_ENABLED))
 		return -1;
 
+	if (num_node_memblks >= NR_NODE_MEMBLKS) {
+		pr_err("NUMA: too many memblk ranges\n");
+		return -EINVAL;
+	}
+
 	/* record this node in proximity bitmap */
 	pxm_bit_set(pxm);
 
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index 7a82c9259609..f2d57e66fd86 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-mapping.h>
+#include <linux/swiotlb.h>
 #include <linux/export.h>
 
 /* Set this to 1 if there is a HW IOMMU in the system */
@@ -23,3 +24,11 @@ const struct dma_map_ops *dma_get_ops(struct device *dev)
 	return dma_ops;
 }
 EXPORT_SYMBOL(dma_get_ops);
+
+#ifdef CONFIG_SWIOTLB
+void __init swiotlb_dma_init(void)
+{
+	dma_ops = &swiotlb_dma_ops;
+	swiotlb_init(1);
+}
+#endif
diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c
deleted file mode 100644
index 8df9245e29d9..000000000000
--- a/arch/ia64/kernel/init_task.c
+++ /dev/null
@@ -1,44 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * This is where we statically allocate and initialize the initial
- * task.
- *
- * Copyright (C) 1999, 2002-2003 Hewlett-Packard Co
- *	David Mosberger-Tang <davidm@hpl.hp.com>
- */
-
-#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/init_task.h>
-#include <linux/mqueue.h>
-
-#include <linux/uaccess.h>
-#include <asm/pgtable.h>
-
-static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
-static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
-/*
- * Initial task structure.
- *
- * We need to make sure that this is properly aligned due to the way process stacks are
- * handled. This is done by having a special ".data..init_task" section...
- */
-#define init_thread_info	init_task_mem.s.thread_info
-#define init_stack		init_task_mem.stack
-
-union {
-	struct {
-		struct task_struct task;
-		struct thread_info thread_info;
-	} s;
-	unsigned long stack[KERNEL_STACK_SIZE/sizeof (unsigned long)];
-} init_task_mem asm ("init_task") __init_task_data =
-	{{
-	.task =		INIT_TASK(init_task_mem.s.task),
-	.thread_info =	INIT_THREAD_INFO(init_task_mem.s.task)
-}};
-
-EXPORT_SYMBOL(init_task);
diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index 853b5611a894..326448f9df16 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -36,6 +36,7 @@
 
 #include <asm/patch.h>
 #include <asm/unaligned.h>
+#include <asm/sections.h>
 
 #define ARCH_MODULE_DEBUG 0
 
@@ -918,3 +919,14 @@ module_arch_cleanup (struct module *mod)
 	if (mod->arch.core_unw_table)
 		unw_remove_unwind_table(mod->arch.core_unw_table);
 }
+
+void *dereference_module_function_descriptor(struct module *mod, void *ptr)
+{
+	Elf64_Shdr *opd = mod->arch.opd;
+
+	if (ptr < (void *)opd->sh_addr ||
+			ptr >= (void *)(opd->sh_addr + opd->sh_size))
+		return ptr;
+
+	return dereference_function_descriptor(ptr);
+}
diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c
index 3ba87c22dfbc..b5df084c0af4 100644
--- a/arch/ia64/kernel/pci-dma.c
+++ b/arch/ia64/kernel/pci-dma.c
@@ -12,12 +12,7 @@
 #include <asm/iommu.h>
 #include <asm/machvec.h>
 #include <linux/dma-mapping.h>
-
-
-#ifdef CONFIG_INTEL_IOMMU
-
 #include <linux/kernel.h>
-
 #include <asm/page.h>
 
 dma_addr_t bad_dma_address __read_mostly;
@@ -104,8 +99,14 @@ void __init pci_iommu_alloc(void)
 	detect_intel_iommu();
 
 #ifdef CONFIG_SWIOTLB
-	pci_swiotlb_init();
-#endif
+	if (!iommu_detected) {
+#ifdef CONFIG_IA64_GENERIC
+		printk(KERN_INFO "PCI-DMA: Re-initialize machine vector.\n");
+		machvec_init("dig");
+		swiotlb_dma_init();
+#else
+		panic("Unable to find Intel IOMMU");
+#endif /* CONFIG_IA64_GENERIC */
+	}
+#endif /* CONFIG_SWIOTLB */
 }
-
-#endif
diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c
deleted file mode 100644
index 5e50939aa03e..000000000000
--- a/arch/ia64/kernel/pci-swiotlb.c
+++ /dev/null
@@ -1,68 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Glue code to lib/swiotlb.c */
-
-#include <linux/pci.h>
-#include <linux/gfp.h>
-#include <linux/cache.h>
-#include <linux/module.h>
-#include <linux/dma-mapping.h>
-
-#include <asm/swiotlb.h>
-#include <asm/dma.h>
-#include <asm/iommu.h>
-#include <asm/machvec.h>
-
-int swiotlb __read_mostly;
-EXPORT_SYMBOL(swiotlb);
-
-static void *ia64_swiotlb_alloc_coherent(struct device *dev, size_t size,
-					 dma_addr_t *dma_handle, gfp_t gfp,
-					 unsigned long attrs)
-{
-	if (dev->coherent_dma_mask != DMA_BIT_MASK(64))
-		gfp |= GFP_DMA;
-	return swiotlb_alloc_coherent(dev, size, dma_handle, gfp);
-}
-
-static void ia64_swiotlb_free_coherent(struct device *dev, size_t size,
-				       void *vaddr, dma_addr_t dma_addr,
-				       unsigned long attrs)
-{
-	swiotlb_free_coherent(dev, size, vaddr, dma_addr);
-}
-
-const struct dma_map_ops swiotlb_dma_ops = {
-	.alloc = ia64_swiotlb_alloc_coherent,
-	.free = ia64_swiotlb_free_coherent,
-	.map_page = swiotlb_map_page,
-	.unmap_page = swiotlb_unmap_page,
-	.map_sg = swiotlb_map_sg_attrs,
-	.unmap_sg = swiotlb_unmap_sg_attrs,
-	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = swiotlb_sync_sg_for_device,
-	.dma_supported = swiotlb_dma_supported,
-	.mapping_error = swiotlb_dma_mapping_error,
-};
-
-void __init swiotlb_dma_init(void)
-{
-	dma_ops = &swiotlb_dma_ops;
-	swiotlb_init(1);
-}
-
-void __init pci_swiotlb_init(void)
-{
-	if (!iommu_detected) {
-#ifdef CONFIG_IA64_GENERIC
-		swiotlb = 1;
-		printk(KERN_INFO "PCI-DMA: Re-initialize machine vector.\n");
-		machvec_init("dig");
-		swiotlb_init(1);
-		dma_ops = &swiotlb_dma_ops;
-#else
-		panic("Unable to find Intel IOMMU");
-#endif
-	}
-}
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 09f86ebfcc7b..c44f002e8f6b 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -1644,12 +1644,12 @@ pfm_write(struct file *file, const char __user *ubuf,
 	return -EINVAL;
 }
 
-static unsigned int
+static __poll_t
 pfm_poll(struct file *filp, poll_table * wait)
 {
 	pfm_context_t *ctx;
 	unsigned long flags;
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 
 	if (PFM_IS_FILE(filp) == 0) {
 		printk(KERN_ERR "perfmon: pfm_poll: bad magic [%d]\n", task_pid_nr(current));
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index dda0082056b3..968b5f33e725 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -13,7 +13,6 @@
 #include <linux/pm.h>
 #include <linux/elf.h>
 #include <linux/errno.h>
-#include <linux/kallsyms.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
@@ -69,7 +68,6 @@ void
 ia64_do_show_stack (struct unw_frame_info *info, void *arg)
 {
 	unsigned long ip, sp, bsp;
-	char buf[128];			/* don't make it so big that it overflows the stack! */
 
 	printk("\nCall Trace:\n");
 	do {
@@ -79,11 +77,9 @@ ia64_do_show_stack (struct unw_frame_info *info, void *arg)
 
 		unw_get_sp(info, &sp);
 		unw_get_bsp(info, &bsp);
-		snprintf(buf, sizeof(buf),
-			 " [<%016lx>] %%s\n"
+		printk(" [<%016lx>] %pS\n"
 			 "                                sp=%016lx bsp=%016lx\n",
-			 ip, sp, bsp);
-		print_symbol(buf, ip);
+			 ip, (void *)ip, sp, bsp);
 	} while (unw_unwind(info) >= 0);
 }
 
@@ -111,7 +107,7 @@ show_regs (struct pt_regs *regs)
 	printk("psr : %016lx ifs : %016lx ip  : [<%016lx>]    %s (%s)\n",
 	       regs->cr_ipsr, regs->cr_ifs, ip, print_tainted(),
 	       init_utsname()->release);
-	print_symbol("ip is at %s\n", ip);
+	printk("ip is at %pS\n", (void *)ip);
 	printk("unat: %016lx pfs : %016lx rsc : %016lx\n",
 	       regs->ar_unat, regs->ar_pfs, regs->ar_rsc);
 	printk("rnat: %016lx bsps: %016lx pr  : %016lx\n",
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index a254cc98f95c..54547c7cf8a2 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -105,58 +105,6 @@ restore_sigcontext (struct sigcontext __user *sc, struct sigscratch *scr)
 	return err;
 }
 
-int
-copy_siginfo_to_user (siginfo_t __user *to, const siginfo_t *from)
-{
-	if (!access_ok(VERIFY_WRITE, to, sizeof(siginfo_t)))
-		return -EFAULT;
-	if (from->si_code < 0) {
-		if (__copy_to_user(to, from, sizeof(siginfo_t)))
-			return -EFAULT;
-		return 0;
-	} else {
-		int err;
-
-		/*
-		 * If you change siginfo_t structure, please be sure this code is fixed
-		 * accordingly.  It should never copy any pad contained in the structure
-		 * to avoid security leaks, but must copy the generic 3 ints plus the
-		 * relevant union member.
-		 */
-		err = __put_user(from->si_signo, &to->si_signo);
-		err |= __put_user(from->si_errno, &to->si_errno);
-		err |= __put_user(from->si_code, &to->si_code);
-		switch (siginfo_layout(from->si_signo, from->si_code)) {
-		      case SIL_FAULT:
-			err |= __put_user(from->si_flags, &to->si_flags);
-			err |= __put_user(from->si_isr, &to->si_isr);
-		      case SIL_POLL:
-			err |= __put_user(from->si_addr, &to->si_addr);
-			err |= __put_user(from->si_imm, &to->si_imm);
-			break;
-		      case SIL_TIMER:
-			err |= __put_user(from->si_tid, &to->si_tid);
-			err |= __put_user(from->si_overrun, &to->si_overrun);
-			err |= __put_user(from->si_ptr, &to->si_ptr);
-			break;
-		      case SIL_RT:
-			err |= __put_user(from->si_uid, &to->si_uid);
-			err |= __put_user(from->si_pid, &to->si_pid);
-			err |= __put_user(from->si_ptr, &to->si_ptr);
-			break;
-		      case SIL_CHLD:
-			err |= __put_user(from->si_utime, &to->si_utime);
-			err |= __put_user(from->si_stime, &to->si_stime);
-			err |= __put_user(from->si_status, &to->si_status);
-		      case SIL_KILL:
-			err |= __put_user(from->si_uid, &to->si_uid);
-			err |= __put_user(from->si_pid, &to->si_pid);
-			break;
-		}
-		return err;
-	}
-}
-
 long
 ia64_rt_sigreturn (struct sigscratch *scr)
 {
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index c6ecb97151a2..9025699049ca 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -88,7 +88,7 @@ void vtime_flush(struct task_struct *tsk)
 	}
 
 	if (ti->softirq_time) {
-		delta = cycle_to_nsec(ti->softirq_time));
+		delta = cycle_to_nsec(ti->softirq_time);
 		account_system_index_time(tsk, delta, CPUTIME_SOFTIRQ);
 	}
 
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 58db59da0bd8..0da58cf8e213 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -3,6 +3,7 @@
 #include <asm/cache.h>
 #include <asm/ptrace.h>
 #include <asm/pgtable.h>
+#include <asm/thread_info.h>
 
 #include <asm-generic/vmlinux.lds.h>
 
@@ -108,7 +109,9 @@ SECTIONS {
 	RODATA
 
 	.opd : AT(ADDR(.opd) - LOAD_OFFSET) {
+		__start_opd = .;
 		*(.opd)
+		__end_opd = .;
 	}
 
 	/*
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 52715a71aede..7d64b30913d1 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -237,9 +237,9 @@ paging_init (void)
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
 
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-#ifdef CONFIG_ZONE_DMA
+#ifdef CONFIG_ZONE_DMA32
 	max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
-	max_zone_pfns[ZONE_DMA] = max_dma;
+	max_zone_pfns[ZONE_DMA32] = max_dma;
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 9b2d994cddf6..ac46f0d60b66 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -38,7 +38,7 @@ struct early_node_data {
 	struct ia64_node_data *node_data;
 	unsigned long pernode_addr;
 	unsigned long pernode_size;
-#ifdef CONFIG_ZONE_DMA
+#ifdef CONFIG_ZONE_DMA32
 	unsigned long num_dma_physpages;
 #endif
 	unsigned long min_pfn;
@@ -669,7 +669,7 @@ static __init int count_node_pages(unsigned long start, unsigned long len, int n
 {
 	unsigned long end = start + len;
 
-#ifdef CONFIG_ZONE_DMA
+#ifdef CONFIG_ZONE_DMA32
 	if (start <= __pa(MAX_DMA_ADDRESS))
 		mem_data[node].num_dma_physpages +=
 			(min(end, __pa(MAX_DMA_ADDRESS)) - start) >>PAGE_SHIFT;
@@ -724,8 +724,8 @@ void __init paging_init(void)
 	}
 
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-#ifdef CONFIG_ZONE_DMA
-	max_zone_pfns[ZONE_DMA] = max_dma;
+#ifdef CONFIG_ZONE_DMA32
+	max_zone_pfns[ZONE_DMA32] = max_dma;
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max_pfn;
 	free_area_init_nodes(max_zone_pfns);
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 498398d915c1..dd84ee194579 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -19,7 +19,7 @@ config M32R
 	select MODULES_USE_ELF_RELA
 	select HAVE_DEBUG_STACKOVERFLOW
 	select CPU_NO_EFFICIENT_FFS
-	select DMA_NOOP_OPS
+	select DMA_DIRECT_OPS
 	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
 
 config SBUS
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index 7e11b125c35e..985ef1d9f556 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -1,5 +1,5 @@
-generic-y += clkdev.h
 generic-y += current.h
+generic-y += dma-mapping.h
 generic-y += exec.h
 generic-y += extable.h
 generic-y += irq_work.h
diff --git a/arch/m32r/include/asm/dma-mapping.h b/arch/m32r/include/asm/dma-mapping.h
deleted file mode 100644
index 336ffe60814b..000000000000
--- a/arch/m32r/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_M32R_DMA_MAPPING_H
-#define _ASM_M32R_DMA_MAPPING_H
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
-#include <linux/io.h>
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &dma_noop_ops;
-}
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-#endif /* _ASM_M32R_DMA_MAPPING_H */
diff --git a/arch/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h
index 1b653bb16f9a..a4272d8f0d9c 100644
--- a/arch/m32r/include/asm/io.h
+++ b/arch/m32r/include/asm/io.h
@@ -191,8 +191,6 @@ static inline void _writel(unsigned long l, unsigned long addr)
 
 #define mmiowb()
 
-#define flush_write_buffers() do { } while (0)  /* M32R_FIXME */
-
 static inline void
 memset_io(volatile void __iomem *addr, unsigned char val, int count)
 {
diff --git a/arch/m32r/include/asm/thread_info.h b/arch/m32r/include/asm/thread_info.h
index b3a215b0ce0a..ba00f1032587 100644
--- a/arch/m32r/include/asm/thread_info.h
+++ b/arch/m32r/include/asm/thread_info.h
@@ -56,9 +56,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* how to get the thread information struct from C */
 static inline struct thread_info *current_thread_info(void)
 {
diff --git a/arch/m32r/include/uapi/asm/Kbuild b/arch/m32r/include/uapi/asm/Kbuild
index 1c44d3b3eba0..c3df55aeefe7 100644
--- a/arch/m32r/include/uapi/asm/Kbuild
+++ b/arch/m32r/include/uapi/asm/Kbuild
@@ -1,5 +1,7 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += kvm_para.h
+generic-y += poll.h
 generic-y += siginfo.h
diff --git a/arch/m32r/include/uapi/asm/poll.h b/arch/m32r/include/uapi/asm/poll.h
deleted file mode 100644
index b7132a305a47..000000000000
--- a/arch/m32r/include/uapi/asm/poll.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/poll.h>
diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c
index cb79fba79d43..a6f300a208bd 100644
--- a/arch/m32r/kernel/traps.c
+++ b/arch/m32r/kernel/traps.c
@@ -115,15 +115,6 @@ static void set_eit_vector_entries(void)
 	_flush_cache_copyback_all();
 }
 
-void abort(void)
-{
-	BUG();
-
-	/* if that doesn't kill us, halt */
-	panic("Oops failed to kill thread");
-}
-EXPORT_SYMBOL(abort);
-
 void __init trap_init(void)
 {
 	set_eit_vector_entries();
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 5b5fa9831b4d..52fa7fbdefa2 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -313,7 +313,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
@@ -454,7 +453,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PPS_CLIENT_PARPORT=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_FB=y
 CONFIG_FB_CIRRUS=y
 CONFIG_FB_AMIGA=y
@@ -595,6 +593,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -624,6 +623,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -653,3 +653,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 72a7764b74ed..b00fe19e1c04 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -311,7 +311,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
@@ -422,7 +421,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
@@ -554,6 +552,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -583,6 +582,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -612,3 +612,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 884b43a2f0d9..2871d75b912f 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -311,7 +311,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
@@ -437,7 +436,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PPS_CLIENT_PARPORT=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_FB=y
 CONFIG_FB_ATARI=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
@@ -576,6 +574,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -605,6 +604,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -634,3 +634,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index fcfa60d31499..2c90328433bf 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -309,7 +309,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
@@ -420,7 +419,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
@@ -546,6 +544,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -575,6 +574,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -604,3 +604,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 9d597bbbbbfe..177c91d63826 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -311,7 +311,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
@@ -425,7 +424,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
@@ -556,6 +554,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -585,6 +584,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -614,3 +614,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 45da20d1286c..efbcaffa30ed 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -313,7 +313,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_SWIM=m
@@ -447,7 +446,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_FB=y
 CONFIG_FB_VALKYRIE=y
 CONFIG_FB_MAC=y
@@ -578,6 +576,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -607,6 +606,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -636,3 +636,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index fda880c10861..e78a205d266a 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -323,7 +323,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
@@ -504,7 +503,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PPS_CLIENT_PARPORT=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_FB=y
 CONFIG_FB_CIRRUS=y
 CONFIG_FB_AMIGA=y
@@ -658,6 +656,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -687,6 +686,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -716,3 +716,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 7d5e4863efec..0d42ecacfd7a 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -308,7 +308,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
@@ -420,7 +419,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
@@ -546,6 +544,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -575,6 +574,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -604,3 +604,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 7763b71a9c49..8dc609c5b8aa 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -309,7 +309,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
@@ -420,7 +419,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
@@ -546,6 +544,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -575,6 +574,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -604,3 +604,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 17eaebfa3e19..11c96087fc5d 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -309,7 +309,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
@@ -437,7 +436,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PPS_CLIENT_PARPORT=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
@@ -569,6 +567,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -598,6 +597,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -627,3 +627,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/stmark2_defconfig b/arch/m68k/configs/stmark2_defconfig
index 55e55dbc2fb6..3d07b1de7eb0 100644
--- a/arch/m68k/configs/stmark2_defconfig
+++ b/arch/m68k/configs/stmark2_defconfig
@@ -5,7 +5,6 @@ CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_NAMESPACES=y
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../uClinux-dist/romfs"
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
 # CONFIG_RD_XZ is not set
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index d1cb7a04ae1d..ddba205ee1aa 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -306,7 +306,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
@@ -419,7 +418,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
@@ -548,6 +546,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -576,6 +575,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -605,3 +605,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index ea3a331c62d5..88d09a14c684 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -306,7 +306,6 @@ CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
@@ -419,7 +418,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
 CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
@@ -548,6 +546,7 @@ CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_SYSCTL=m
 CONFIG_TEST_UDELAY=m
@@ -577,6 +576,7 @@ CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -606,3 +606,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC32_SELFTEST=m
 CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 59d6d0d38f67..88a9d27df1ac 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,5 +1,4 @@
 generic-y += barrier.h
-generic-y += clkdev.h
 generic-y += device.h
 generic-y += emergency-restart.h
 generic-y += exec.h
diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h
index f42c27400dbc..9b840c03ebb7 100644
--- a/arch/m68k/include/asm/macintosh.h
+++ b/arch/m68k/include/asm/macintosh.h
@@ -33,7 +33,7 @@ struct mac_model
 	char ide_type;
 	char scc_type;
 	char ether_type;
-	char nubus_type;
+	char expansion_type;
 	char floppy_type;
 };
 
@@ -73,8 +73,11 @@ struct mac_model
 #define MAC_ETHER_SONIC		1
 #define MAC_ETHER_MACE		2
 
-#define MAC_NO_NUBUS		0
-#define MAC_NUBUS		1
+#define MAC_EXP_NONE		0
+#define MAC_EXP_PDS		1 /* Accepts only a PDS card */
+#define MAC_EXP_NUBUS		2 /* Accepts only NuBus card(s) */
+#define MAC_EXP_PDS_NUBUS	3 /* Accepts PDS card and/or NuBus card(s) */
+#define MAC_EXP_PDS_COMM	4 /* Accepts PDS card or Comm Slot card */
 
 #define MAC_FLOPPY_IWM		0
 #define MAC_FLOPPY_SWIM_ADDR1	1
diff --git a/arch/m68k/include/asm/thread_info.h b/arch/m68k/include/asm/thread_info.h
index 928035591f2e..015f1ca38305 100644
--- a/arch/m68k/include/asm/thread_info.h
+++ b/arch/m68k/include/asm/thread_info.h
@@ -41,8 +41,6 @@ struct thread_info {
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 }
 
-#define init_stack		(init_thread_union.stack)
-
 #ifndef __ASSEMBLY__
 /* how to get the thread information struct from C */
 static inline struct thread_info *current_thread_info(void)
@@ -58,8 +56,6 @@ static inline struct thread_info *current_thread_info(void)
 }
 #endif
 
-#define init_thread_info	(init_thread_union.thread_info)
-
 /* entry.S relies on these definitions!
  * bits 0-7 are tested at every exception exit
  * bits 8-15 are also tested at syscall exit
diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild
index 3717b64a620d..c2e26a44c482 100644
--- a/arch/m68k/include/uapi/asm/Kbuild
+++ b/arch/m68k/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
diff --git a/arch/m68k/include/uapi/asm/poll.h b/arch/m68k/include/uapi/asm/poll.h
index c3e3fcc15e1d..d8be239e8141 100644
--- a/arch/m68k/include/uapi/asm/poll.h
+++ b/arch/m68k/include/uapi/asm/poll.h
@@ -2,8 +2,25 @@
 #ifndef __m68k_POLL_H
 #define __m68k_POLL_H
 
+#ifndef __KERNEL__
 #define POLLWRNORM	POLLOUT
-#define POLLWRBAND	256
+#define POLLWRBAND	(__force __poll_t)256
+#else
+#define __ARCH_HAS_MANGLED_POLL
+static inline __u16 mangle_poll(__poll_t val)
+{
+	__u16 v = (__force __u16)val;
+	/* bit 9 -> bit 8, bit 8 -> bit 2 */
+	return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6);
+}
+
+static inline __poll_t demangle_poll(__u16 v)
+{
+        /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
+	return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
+				((v & 4) << 6));
+}
+#endif
 
 #include <asm-generic/poll.h>
 
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index 87ef73a93856..c01b9b8f97bf 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -76,8 +76,6 @@ static void *m68k_dma_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	void *ret;
-	/* ignore region specifiers */
-	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
 
 	if (dev == NULL || (*dev->dma_mask < 0xffffffff))
 		gfp |= GFP_DMA;
diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds
index 3aa571a513b5..cf6edda38971 100644
--- a/arch/m68k/kernel/vmlinux-nommu.lds
+++ b/arch/m68k/kernel/vmlinux-nommu.lds
@@ -45,6 +45,8 @@ SECTIONS {
 	.text : {
 		HEAD_TEXT
 		TEXT_TEXT
+		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		SCHED_TEXT
 		CPUIDLE_TEXT
 		LOCK_TEXT
diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds
index 89172b8974b9..625a5785804f 100644
--- a/arch/m68k/kernel/vmlinux-std.lds
+++ b/arch/m68k/kernel/vmlinux-std.lds
@@ -16,6 +16,8 @@ SECTIONS
   .text : {
 	HEAD_TEXT
 	TEXT_TEXT
+	IRQENTRY_TEXT
+	SOFTIRQENTRY_TEXT
 	SCHED_TEXT
 	CPUIDLE_TEXT
 	LOCK_TEXT
diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds
index 293990efc917..9868270b0984 100644
--- a/arch/m68k/kernel/vmlinux-sun3.lds
+++ b/arch/m68k/kernel/vmlinux-sun3.lds
@@ -16,6 +16,8 @@ SECTIONS
   .text : {
 	HEAD_TEXT
 	TEXT_TEXT
+	IRQENTRY_TEXT
+	SOFTIRQENTRY_TEXT
 	SCHED_TEXT
 	CPUIDLE_TEXT
 	LOCK_TEXT
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 16cd5cea5207..d3d435248a24 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -212,7 +212,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_II,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_IWM,
 	},
 
@@ -227,7 +227,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_II,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_IWM,
 	}, {
 		.ident		= MAC_MODEL_IIX,
@@ -236,7 +236,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_II,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_IICX,
@@ -245,7 +245,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_II,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_SE30,
@@ -254,7 +254,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_II,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	},
 
@@ -272,7 +272,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_IIFX,
@@ -281,7 +281,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_IIFX,
 		.scc_type	= MAC_SCC_IOP,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_IOP,
 	}, {
 		.ident		= MAC_MODEL_IISI,
@@ -290,7 +290,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_IIVI,
@@ -299,7 +299,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_IIVX,
@@ -308,7 +308,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	},
 
@@ -323,7 +323,6 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_CCL,
@@ -332,7 +331,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_CCLII,
@@ -341,7 +340,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	},
 
@@ -356,7 +355,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_LCII,
@@ -365,7 +364,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_LCIII,
@@ -374,7 +373,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	},
 
@@ -395,7 +394,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_Q605_ACC,
@@ -404,7 +403,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_Q610,
@@ -414,7 +413,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_Q630,
@@ -424,8 +423,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.ide_type	= MAC_IDE_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
-		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_COMM,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_Q650,
@@ -435,7 +433,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	},
 	/* The Q700 does have a NS Sonic */
@@ -447,7 +445,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA2,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_Q800,
@@ -457,7 +455,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_Q840,
@@ -467,7 +465,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA3,
 		.scc_type	= MAC_SCC_PSC,
 		.ether_type	= MAC_ETHER_MACE,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_AV,
 	}, {
 		.ident		= MAC_MODEL_Q900,
@@ -477,7 +475,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA2,
 		.scc_type	= MAC_SCC_IOP,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_IOP,
 	}, {
 		.ident		= MAC_MODEL_Q950,
@@ -487,7 +485,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA2,
 		.scc_type	= MAC_SCC_IOP,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_IOP,
 	},
 
@@ -502,7 +500,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_P475,
@@ -511,7 +509,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_P475F,
@@ -520,7 +518,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_P520,
@@ -529,7 +527,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_P550,
@@ -538,7 +536,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	},
 	/* These have the comm slot, and therefore possibly SONIC ethernet */
@@ -549,8 +547,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_II,
-		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_COMM,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_P588,
@@ -560,8 +557,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.ide_type	= MAC_IDE_QUADRA,
 		.scc_type	= MAC_SCC_II,
-		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_COMM,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_TV,
@@ -570,7 +566,6 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_P600,
@@ -579,7 +574,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_LC,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	},
 
@@ -596,7 +591,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_C650,
@@ -606,7 +601,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1,
 	}, {
 		.ident		= MAC_MODEL_C660,
@@ -616,7 +611,7 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA3,
 		.scc_type	= MAC_SCC_PSC,
 		.ether_type	= MAC_ETHER_MACE,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_PDS_NUBUS,
 		.floppy_type	= MAC_FLOPPY_AV,
 	},
 
@@ -633,7 +628,6 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB145,
@@ -642,7 +636,6 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB150,
@@ -652,7 +645,6 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_OLD,
 		.ide_type	= MAC_IDE_PB,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB160,
@@ -661,7 +653,6 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB165,
@@ -670,7 +661,6 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB165C,
@@ -679,7 +669,6 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB170,
@@ -688,7 +677,6 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB180,
@@ -697,7 +685,6 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB180C,
@@ -706,7 +693,6 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB190,
@@ -716,7 +702,6 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_LATE,
 		.ide_type	= MAC_IDE_BABOON,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB520,
@@ -726,7 +711,6 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_LATE,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	},
 
@@ -743,7 +727,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_DUO,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB230,
@@ -752,7 +736,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_DUO,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB250,
@@ -761,7 +745,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_DUO,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB270C,
@@ -770,7 +754,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_DUO,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB280,
@@ -779,7 +763,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_DUO,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	}, {
 		.ident		= MAC_MODEL_PB280C,
@@ -788,7 +772,7 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IICI,
 		.scsi_type	= MAC_SCSI_DUO,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS,
+		.expansion_type	= MAC_EXP_NUBUS,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
 	},
 
@@ -1100,14 +1084,12 @@ int __init mac_platform_init(void)
 	 * Ethernet device
 	 */
 
-	switch (macintosh_config->ether_type) {
-	case MAC_ETHER_SONIC:
+	if (macintosh_config->ether_type == MAC_ETHER_SONIC ||
+	    macintosh_config->expansion_type == MAC_EXP_PDS_COMM)
 		platform_device_register_simple("macsonic", -1, NULL, 0);
-		break;
-	case MAC_ETHER_MACE:
+
+	if (macintosh_config->ether_type == MAC_ETHER_MACE)
 		platform_device_register_simple("macmace", -1, NULL, 0);
-		break;
-	}
 
 	return 0;
 }
diff --git a/arch/m68k/mac/oss.c b/arch/m68k/mac/oss.c
index 3f81892527ad..921e6c092f2c 100644
--- a/arch/m68k/mac/oss.c
+++ b/arch/m68k/mac/oss.c
@@ -53,56 +53,41 @@ void __init oss_init(void)
 }
 
 /*
- * Handle miscellaneous OSS interrupts.
+ * Handle OSS interrupts.
+ * XXX how do you clear a pending IRQ? is it even necessary?
  */
 
-static void oss_irq(struct irq_desc *desc)
+static void oss_iopism_irq(struct irq_desc *desc)
 {
-	int events = oss->irq_pending &
-		(OSS_IP_IOPSCC | OSS_IP_SCSI | OSS_IP_IOPISM);
-
-	if (events & OSS_IP_IOPSCC) {
-		oss->irq_pending &= ~OSS_IP_IOPSCC;
-		generic_handle_irq(IRQ_MAC_SCC);
-	}
-
-	if (events & OSS_IP_SCSI) {
-		oss->irq_pending &= ~OSS_IP_SCSI;
-		generic_handle_irq(IRQ_MAC_SCSI);
-	}
-
-	if (events & OSS_IP_IOPISM) {
-		oss->irq_pending &= ~OSS_IP_IOPISM;
-		generic_handle_irq(IRQ_MAC_ADB);
-	}
+	generic_handle_irq(IRQ_MAC_ADB);
 }
 
-/*
- * Nubus IRQ handler, OSS style
- *
- * Unlike the VIA/RBV this is on its own autovector interrupt level.
- */
+static void oss_scsi_irq(struct irq_desc *desc)
+{
+	generic_handle_irq(IRQ_MAC_SCSI);
+}
 
 static void oss_nubus_irq(struct irq_desc *desc)
 {
-	int events, irq_bit, i;
+	u16 events, irq_bit;
+	int irq_num;
 
 	events = oss->irq_pending & OSS_IP_NUBUS;
-	if (!events)
-		return;
-
-	/* There are only six slots on the OSS, not seven */
-
-	i = 6;
-	irq_bit = 0x40;
+	irq_num = NUBUS_SOURCE_BASE + 5;
+	irq_bit = OSS_IP_NUBUS5;
 	do {
-		--i;
-		irq_bit >>= 1;
 		if (events & irq_bit) {
-			oss->irq_pending &= ~irq_bit;
-			generic_handle_irq(NUBUS_SOURCE_BASE + i);
+			events &= ~irq_bit;
+			generic_handle_irq(irq_num);
 		}
-	} while(events & (irq_bit - 1));
+		--irq_num;
+		irq_bit >>= 1;
+	} while (events);
+}
+
+static void oss_iopscc_irq(struct irq_desc *desc)
+{
+	generic_handle_irq(IRQ_MAC_SCC);
 }
 
 /*
@@ -122,14 +107,14 @@ static void oss_nubus_irq(struct irq_desc *desc)
 
 void __init oss_register_interrupts(void)
 {
-	irq_set_chained_handler(OSS_IRQLEV_IOPISM, oss_irq);
-	irq_set_chained_handler(OSS_IRQLEV_SCSI,   oss_irq);
+	irq_set_chained_handler(OSS_IRQLEV_IOPISM, oss_iopism_irq);
+	irq_set_chained_handler(OSS_IRQLEV_SCSI,   oss_scsi_irq);
 	irq_set_chained_handler(OSS_IRQLEV_NUBUS,  oss_nubus_irq);
-	irq_set_chained_handler(OSS_IRQLEV_IOPSCC, oss_irq);
+	irq_set_chained_handler(OSS_IRQLEV_IOPSCC, oss_iopscc_irq);
 	irq_set_chained_handler(OSS_IRQLEV_VIA1,   via1_irq);
 
 	/* OSS_VIA1 gets enabled here because it has no machspec interrupt. */
-	oss->irq_level[OSS_VIA1] = IRQ_AUTO_6;
+	oss->irq_level[OSS_VIA1] = OSS_IRQLEV_VIA1;
 }
 
 /*
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 127d7c1f2090..03253c4f8e6a 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -21,8 +21,9 @@ extern void die_if_kernel(char *, struct pt_regs *, long);
 
 int send_fault_sig(struct pt_regs *regs)
 {
-	siginfo_t siginfo = { 0, 0, 0, };
+	siginfo_t siginfo;
 
+	clear_siginfo(&siginfo);
 	siginfo.si_signo = current->thread.signo;
 	siginfo.si_code = current->thread.code;
 	siginfo.si_addr = (void *)current->thread.faddr;
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index 3fba97ed9bb2..913c779979df 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -1,5 +1,4 @@
 generic-y += bugs.h
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += device.h
 generic-y += dma.h
diff --git a/arch/metag/include/asm/thread_info.h b/arch/metag/include/asm/thread_info.h
index 554f73a77e6e..a1a9c7f5ca8c 100644
--- a/arch/metag/include/asm/thread_info.h
+++ b/arch/metag/include/asm/thread_info.h
@@ -74,9 +74,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* how to get the current stack pointer from C */
 register unsigned long current_stack_pointer asm("A0StP") __used;
 
diff --git a/arch/metag/include/uapi/asm/Kbuild b/arch/metag/include/uapi/asm/Kbuild
index 6ac763d9a3e3..f9eaf07d29f8 100644
--- a/arch/metag/include/uapi/asm/Kbuild
+++ b/arch/metag/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/metag/include/uapi/asm/siginfo.h b/arch/metag/include/uapi/asm/siginfo.h
index b54ef7186ca3..9a3f6cde9487 100644
--- a/arch/metag/include/uapi/asm/siginfo.h
+++ b/arch/metag/include/uapi/asm/siginfo.h
@@ -6,4 +6,11 @@
 
 #include <asm-generic/siginfo.h>
 
+/*
+ * SIGFPE si_codes
+ */
+#ifdef __KERNEL__
+#define FPE_FIXME      0       /* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
 #endif
diff --git a/arch/metag/kernel/devtree.c b/arch/metag/kernel/devtree.c
index 18dd7aea9fdc..6af749a64438 100644
--- a/arch/metag/kernel/devtree.c
+++ b/arch/metag/kernel/devtree.c
@@ -14,26 +14,12 @@
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/types.h>
-#include <linux/bootmem.h>
-#include <linux/memblock.h>
-#include <linux/of.h>
 #include <linux/of_fdt.h>
 
 #include <asm/setup.h>
 #include <asm/page.h>
 #include <asm/mach/arch.h>
 
-void __init early_init_dt_add_memory_arch(u64 base, u64 size)
-{
-	pr_err("%s(%llx, %llx)\n",
-	       __func__, base, size);
-}
-
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return alloc_bootmem_align(size, align);
-}
-
 static const void * __init arch_get_next_mach(const char *const **match)
 {
 	static const struct machine_desc *mdesc = __arch_info_begin;
diff --git a/arch/metag/kernel/traps.c b/arch/metag/kernel/traps.c
index 444851e510d5..3b62b1b0c0b5 100644
--- a/arch/metag/kernel/traps.c
+++ b/arch/metag/kernel/traps.c
@@ -735,7 +735,7 @@ TBIRES fpe_handler(TBIRES State, int SigNum, int Triggers, int Inst, PTBI pTBI)
 	else if (error_state & TXSTAT_FPE_INEXACT_BIT)
 		info.si_code = FPE_FLTRES;
 	else
-		info.si_code = 0;
+		info.si_code = FPE_FIXME;
 	info.si_errno = 0;
 	info.si_addr = (__force void __user *)regs->ctx.CurrPC;
 	force_sig_info(SIGFPE, &info, current);
diff --git a/arch/microblaze/Kconfig.platform b/arch/microblaze/Kconfig.platform
index 1b3d8c849101..6996f397c16c 100644
--- a/arch/microblaze/Kconfig.platform
+++ b/arch/microblaze/Kconfig.platform
@@ -8,6 +8,7 @@ menu "Platform options"
 
 config OPT_LIB_FUNCTION
 	bool "Optimalized lib function"
+	depends on CPU_LITTLE_ENDIAN
 	default y
 	help
 	  Allows turn on optimalized library function (memcpy and memmove).
diff --git a/arch/microblaze/Makefile b/arch/microblaze/Makefile
index 830ee7d42fa0..d269dd4b8279 100644
--- a/arch/microblaze/Makefile
+++ b/arch/microblaze/Makefile
@@ -36,16 +36,21 @@ endif
 CPUFLAGS-$(CONFIG_XILINX_MICROBLAZE0_USE_DIV) += -mno-xl-soft-div
 CPUFLAGS-$(CONFIG_XILINX_MICROBLAZE0_USE_BARREL) += -mxl-barrel-shift
 CPUFLAGS-$(CONFIG_XILINX_MICROBLAZE0_USE_PCMP_INSTR) += -mxl-pattern-compare
-CPUFLAGS-$(CONFIG_BIG_ENDIAN) += -mbig-endian
-CPUFLAGS-$(CONFIG_LITTLE_ENDIAN) += -mlittle-endian
+
+ifdef CONFIG_CPU_BIG_ENDIAN
+KBUILD_CFLAGS += -mbig-endian
+KBUILD_AFLAGS += -mbig-endian
+LD += -EB
+else
+KBUILD_CFLAGS += -mlittle-endian
+KBUILD_AFLAGS += -mlittle-endian
+LD += -EL
+endif
 
 CPUFLAGS-1 += $(call cc-option,-mcpu=v$(CPU_VER))
 
 # r31 holds current when in kernel mode
-KBUILD_CFLAGS += -ffixed-r31 $(CPUFLAGS-1) $(CPUFLAGS-2)
-
-LDFLAGS		:=
-LDFLAGS_vmlinux	:=
+KBUILD_CFLAGS += -ffixed-r31 $(CPUFLAGS-y) $(CPUFLAGS-1) $(CPUFLAGS-2)
 
 head-y := arch/microblaze/kernel/head.o
 libs-y += arch/microblaze/lib/
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 9d66f7793841..3c80a5a308ed 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -2,7 +2,6 @@ generic-y += barrier.h
 generic-y += bitops.h
 generic-y += bug.h
 generic-y += bugs.h
-generic-y += clkdev.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
diff --git a/arch/microblaze/include/asm/dma-mapping.h b/arch/microblaze/include/asm/dma-mapping.h
index 6b9ea39405b8..add50c1373bf 100644
--- a/arch/microblaze/include/asm/dma-mapping.h
+++ b/arch/microblaze/include/asm/dma-mapping.h
@@ -18,11 +18,11 @@
 /*
  * Available generic sets of operations
  */
-extern const struct dma_map_ops dma_direct_ops;
+extern const struct dma_map_ops dma_nommu_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return &dma_direct_ops;
+	return &dma_nommu_ops;
 }
 
 #endif	/* _ASM_MICROBLAZE_DMA_MAPPING_H */
diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h
index 39b6315db82e..c7968139486f 100644
--- a/arch/microblaze/include/asm/io.h
+++ b/arch/microblaze/include/asm/io.h
@@ -36,7 +36,7 @@ extern resource_size_t isa_mem_base;
 #ifdef CONFIG_MMU
 #define page_to_bus(page)	(page_to_phys(page))
 
-extern void iounmap(void __iomem *addr);
+extern void iounmap(volatile void __iomem *addr);
 
 extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
 #define ioremap_nocache(addr, size)		ioremap((addr), (size))
diff --git a/arch/microblaze/include/asm/mmu_context_mm.h b/arch/microblaze/include/asm/mmu_context_mm.h
index 99472d2ca340..97559fe0b953 100644
--- a/arch/microblaze/include/asm/mmu_context_mm.h
+++ b/arch/microblaze/include/asm/mmu_context_mm.h
@@ -13,6 +13,7 @@
 
 #include <linux/atomic.h>
 #include <linux/mm_types.h>
+#include <linux/sched.h>
 
 #include <asm/bitops.h>
 #include <asm/mmu.h>
diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h
index e7e8954e9815..9afe4b5bd6c8 100644
--- a/arch/microblaze/include/asm/thread_info.h
+++ b/arch/microblaze/include/asm/thread_info.h
@@ -86,9 +86,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* how to get the thread information struct from C */
 static inline struct thread_info *current_thread_info(void)
 {
diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild
index 06609ca36115..2c6a6bffea32 100644
--- a/arch/microblaze/include/uapi/asm/Kbuild
+++ b/arch/microblaze/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index 990bf9ea0ec6..c91e8cef98dd 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -15,42 +15,18 @@
 #include <linux/bug.h>
 #include <asm/cacheflush.h>
 
-#define NOT_COHERENT_CACHE
-
-static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
+static void *dma_nommu_alloc_coherent(struct device *dev, size_t size,
 				       dma_addr_t *dma_handle, gfp_t flag,
 				       unsigned long attrs)
 {
-#ifdef NOT_COHERENT_CACHE
 	return consistent_alloc(flag, size, dma_handle);
-#else
-	void *ret;
-	struct page *page;
-	int node = dev_to_node(dev);
-
-	/* ignore region specifiers */
-	flag  &= ~(__GFP_HIGHMEM);
-
-	page = alloc_pages_node(node, flag, get_order(size));
-	if (page == NULL)
-		return NULL;
-	ret = page_address(page);
-	memset(ret, 0, size);
-	*dma_handle = virt_to_phys(ret);
-
-	return ret;
-#endif
 }
 
-static void dma_direct_free_coherent(struct device *dev, size_t size,
+static void dma_nommu_free_coherent(struct device *dev, size_t size,
 				     void *vaddr, dma_addr_t dma_handle,
 				     unsigned long attrs)
 {
-#ifdef NOT_COHERENT_CACHE
 	consistent_free(size, vaddr);
-#else
-	free_pages((unsigned long)vaddr, get_order(size));
-#endif
 }
 
 static inline void __dma_sync(unsigned long paddr,
@@ -69,7 +45,7 @@ static inline void __dma_sync(unsigned long paddr,
 	}
 }
 
-static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
+static int dma_nommu_map_sg(struct device *dev, struct scatterlist *sgl,
 			     int nents, enum dma_data_direction direction,
 			     unsigned long attrs)
 {
@@ -89,12 +65,7 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 	return nents;
 }
 
-static int dma_direct_dma_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
-static inline dma_addr_t dma_direct_map_page(struct device *dev,
+static inline dma_addr_t dma_nommu_map_page(struct device *dev,
 					     struct page *page,
 					     unsigned long offset,
 					     size_t size,
@@ -106,7 +77,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 	return page_to_phys(page) + offset;
 }
 
-static inline void dma_direct_unmap_page(struct device *dev,
+static inline void dma_nommu_unmap_page(struct device *dev,
 					 dma_addr_t dma_address,
 					 size_t size,
 					 enum dma_data_direction direction,
@@ -122,7 +93,7 @@ static inline void dma_direct_unmap_page(struct device *dev,
 }
 
 static inline void
-dma_direct_sync_single_for_cpu(struct device *dev,
+dma_nommu_sync_single_for_cpu(struct device *dev,
 			       dma_addr_t dma_handle, size_t size,
 			       enum dma_data_direction direction)
 {
@@ -136,7 +107,7 @@ dma_direct_sync_single_for_cpu(struct device *dev,
 }
 
 static inline void
-dma_direct_sync_single_for_device(struct device *dev,
+dma_nommu_sync_single_for_device(struct device *dev,
 				  dma_addr_t dma_handle, size_t size,
 				  enum dma_data_direction direction)
 {
@@ -150,7 +121,7 @@ dma_direct_sync_single_for_device(struct device *dev,
 }
 
 static inline void
-dma_direct_sync_sg_for_cpu(struct device *dev,
+dma_nommu_sync_sg_for_cpu(struct device *dev,
 			   struct scatterlist *sgl, int nents,
 			   enum dma_data_direction direction)
 {
@@ -164,7 +135,7 @@ dma_direct_sync_sg_for_cpu(struct device *dev,
 }
 
 static inline void
-dma_direct_sync_sg_for_device(struct device *dev,
+dma_nommu_sync_sg_for_device(struct device *dev,
 			      struct scatterlist *sgl, int nents,
 			      enum dma_data_direction direction)
 {
@@ -178,7 +149,7 @@ dma_direct_sync_sg_for_device(struct device *dev,
 }
 
 static
-int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
+int dma_nommu_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
 			     void *cpu_addr, dma_addr_t handle, size_t size,
 			     unsigned long attrs)
 {
@@ -191,12 +162,8 @@ int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
 	if (off >= count || user_count > (count - off))
 		return -ENXIO;
 
-#ifdef NOT_COHERENT_CACHE
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	pfn = consistent_virt_to_pfn(cpu_addr);
-#else
-	pfn = virt_to_pfn(cpu_addr);
-#endif
 	return remap_pfn_range(vma, vma->vm_start, pfn + off,
 			       vma->vm_end - vma->vm_start, vma->vm_page_prot);
 #else
@@ -204,20 +171,19 @@ int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
 #endif
 }
 
-const struct dma_map_ops dma_direct_ops = {
-	.alloc		= dma_direct_alloc_coherent,
-	.free		= dma_direct_free_coherent,
-	.mmap		= dma_direct_mmap_coherent,
-	.map_sg		= dma_direct_map_sg,
-	.dma_supported	= dma_direct_dma_supported,
-	.map_page	= dma_direct_map_page,
-	.unmap_page	= dma_direct_unmap_page,
-	.sync_single_for_cpu		= dma_direct_sync_single_for_cpu,
-	.sync_single_for_device		= dma_direct_sync_single_for_device,
-	.sync_sg_for_cpu		= dma_direct_sync_sg_for_cpu,
-	.sync_sg_for_device		= dma_direct_sync_sg_for_device,
+const struct dma_map_ops dma_nommu_ops = {
+	.alloc			= dma_nommu_alloc_coherent,
+	.free			= dma_nommu_free_coherent,
+	.mmap			= dma_nommu_mmap_coherent,
+	.map_sg			= dma_nommu_map_sg,
+	.map_page		= dma_nommu_map_page,
+	.unmap_page		= dma_nommu_unmap_page,
+	.sync_single_for_cpu	= dma_nommu_sync_single_for_cpu,
+	.sync_single_for_device	= dma_nommu_sync_single_for_device,
+	.sync_sg_for_cpu	= dma_nommu_sync_sg_for_cpu,
+	.sync_sg_for_device	= dma_nommu_sync_sg_for_device,
 };
-EXPORT_SYMBOL(dma_direct_ops);
+EXPORT_SYMBOL(dma_nommu_ops);
 
 /* Number of entries preallocated for DMA-API debugging */
 #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index 4c0599239915..7f525962cdfa 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -127,7 +127,7 @@ void __iomem *ioremap(phys_addr_t addr, unsigned long size)
 }
 EXPORT_SYMBOL(ioremap);
 
-void iounmap(void __iomem *addr)
+void iounmap(volatile void __iomem *addr)
 {
 	if ((__force void *)addr > high_memory &&
 					(unsigned long) addr < ioremap_bot)
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 350a990fc719..ab98569994f0 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -259,6 +259,7 @@ config BCM47XX
 	select LEDS_GPIO_REGISTER
 	select BCM47XX_NVRAM
 	select BCM47XX_SPROM
+	select BCM47XX_SSB if !BCM47XX_BCMA
 	help
 	 Support for BCM47XX based boards
 
@@ -389,6 +390,7 @@ config LANTIQ
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_MIPS16
 	select SYS_SUPPORTS_MULTITHREADING
+	select SYS_SUPPORTS_VPE_LOADER
 	select SYS_HAS_EARLY_PRINTK
 	select GPIOLIB
 	select SWAP_IO_SPACE
@@ -429,6 +431,7 @@ config MACH_LOONGSON32
 
 config MACH_LOONGSON64
 	bool "Loongson-2/3 family of machines"
+	select ARCH_HAS_PHYS_TO_DMA
 	select SYS_SUPPORTS_ZBOOT
 	help
 	  This enables the support of Loongson-2/3 family of machines.
@@ -516,6 +519,7 @@ config MIPS_MALTA
 	select SYS_SUPPORTS_MIPS16
 	select SYS_SUPPORTS_MULTITHREADING
 	select SYS_SUPPORTS_SMARTMIPS
+	select SYS_SUPPORTS_VPE_LOADER
 	select SYS_SUPPORTS_ZBOOT
 	select SYS_SUPPORTS_RELOCATABLE
 	select USE_OF
@@ -877,6 +881,7 @@ config MIKROTIK_RB532
 config CAVIUM_OCTEON_SOC
 	bool "Cavium Networks Octeon SoC based boards"
 	select CEVT_R4K
+	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_PHYS_ADDR_T_64BIT
 	select DMA_COHERENT
 	select SYS_SUPPORTS_64BIT_KERNEL
@@ -2281,9 +2286,16 @@ config MIPSR2_TO_R6_EMULATOR
 	  The only reason this is a build-time option is to save ~14K from the
 	  final kernel image.
 
+config SYS_SUPPORTS_VPE_LOADER
+	bool
+	depends on SYS_SUPPORTS_MULTITHREADING
+	help
+	  Indicates that the platform supports the VPE loader, and provides
+	  physical_memsize.
+
 config MIPS_VPE_LOADER
 	bool "VPE loader support."
-	depends on SYS_SUPPORTS_MULTITHREADING && MODULES
+	depends on SYS_SUPPORTS_VPE_LOADER && MODULES
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select MIPS_MT
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index 464af5e025d6..0749c3724543 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -124,30 +124,36 @@ config SCACHE_DEBUGFS
 
 	  If unsure, say N.
 
-menuconfig MIPS_CPS_NS16550
+menuconfig MIPS_CPS_NS16550_BOOL
 	bool "CPS SMP NS16550 UART output"
 	depends on MIPS_CPS
 	help
 	  Output debug information via an ns16550 compatible UART if exceptions
 	  occur early in the boot process of a secondary core.
 
-if MIPS_CPS_NS16550
+if MIPS_CPS_NS16550_BOOL
+
+config MIPS_CPS_NS16550
+	def_bool MIPS_CPS_NS16550_BASE != 0
 
 config MIPS_CPS_NS16550_BASE
 	hex "UART Base Address"
 	default 0x1b0003f8 if MIPS_MALTA
+	default 0
 	help
 	  The base address of the ns16550 compatible UART on which to output
 	  debug information from the early stages of core startup.
 
+	  This is only used if non-zero.
+
 config MIPS_CPS_NS16550_SHIFT
 	int "UART Register Shift"
-	default 0 if MIPS_MALTA
+	default 0
 	help
 	  The number of bits to shift ns16550 register indices by in order to
 	  form their addresses. That is, log base 2 of the span between
 	  adjacent ns16550 registers in the system.
 
-endif # MIPS_CPS_NS16550
+endif # MIPS_CPS_NS16550_BOOL
 
 endmenu
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
index 4674f1efbe7a..e1675c25d5d4 100644
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@@ -575,7 +575,7 @@ static int __init ar7_register_uarts(void)
 	uart_port.type		= PORT_AR7;
 	uart_port.uartclk	= clk_get_rate(bus_clk) / 2;
 	uart_port.iotype	= UPIO_MEM32;
-	uart_port.flags		= UPF_FIXED_TYPE;
+	uart_port.flags		= UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF;
 	uart_port.regshift	= 2;
 
 	uart_port.line		= 0;
diff --git a/arch/mips/ath25/devices.c b/arch/mips/ath25/devices.c
index e1156347da53..301a9028273c 100644
--- a/arch/mips/ath25/devices.c
+++ b/arch/mips/ath25/devices.c
@@ -73,6 +73,7 @@ const char *get_system_type(void)
 
 void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk)
 {
+#ifdef CONFIG_SERIAL_8250_CONSOLE
 	struct uart_port s;
 
 	memset(&s, 0, sizeof(s));
@@ -85,6 +86,7 @@ void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk)
 	s.uartclk = uartclk;
 
 	early_serial_setup(&s);
+#endif /* CONFIG_SERIAL_8250_CONSOLE */
 }
 
 int __init ath25_add_wmac(int nr, u32 base, int irq)
diff --git a/arch/mips/bcm63xx/dev-enet.c b/arch/mips/bcm63xx/dev-enet.c
index e8284771d620..07b4c65a88a4 100644
--- a/arch/mips/bcm63xx/dev-enet.c
+++ b/arch/mips/bcm63xx/dev-enet.c
@@ -265,6 +265,14 @@ int __init bcm63xx_enet_register(int unit,
 		dpd->dma_chan_width = ENETDMA_CHAN_WIDTH;
 	}
 
+	if (unit == 0) {
+		dpd->rx_chan = 0;
+		dpd->tx_chan = 1;
+	} else {
+		dpd->rx_chan = 2;
+		dpd->tx_chan = 3;
+	}
+
 	ret = platform_device_register(pdev);
 	if (ret)
 		return ret;
diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig
index 204a1670fd9b..b5eee1a57d6c 100644
--- a/arch/mips/cavium-octeon/Kconfig
+++ b/arch/mips/cavium-octeon/Kconfig
@@ -75,6 +75,7 @@ config NEED_SG_DMA_LENGTH
 
 config SWIOTLB
 	def_bool y
+	select DMA_DIRECT_OPS
 	select IOMMU_HELPER
 	select NEED_SG_DMA_LENGTH
 
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index c64bd87f0b6e..c7bb8a407041 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -159,36 +159,13 @@ static void octeon_dma_sync_sg_for_device(struct device *dev,
 static void *octeon_dma_alloc_coherent(struct device *dev, size_t size,
 	dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
-	void *ret;
-
-	/* ignore region specifiers */
-	gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
-
-	if (IS_ENABLED(CONFIG_ZONE_DMA) && dev == NULL)
-		gfp |= __GFP_DMA;
-	else if (IS_ENABLED(CONFIG_ZONE_DMA) &&
-		 dev->coherent_dma_mask <= DMA_BIT_MASK(24))
-		gfp |= __GFP_DMA;
-	else if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
-		 dev->coherent_dma_mask <= DMA_BIT_MASK(32))
-		gfp |= __GFP_DMA32;
-
-	/* Don't invoke OOM killer */
-	gfp |= __GFP_NORETRY;
-
-	ret = swiotlb_alloc_coherent(dev, size, dma_handle, gfp);
+	void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
 
 	mb();
 
 	return ret;
 }
 
-static void octeon_dma_free_coherent(struct device *dev, size_t size,
-	void *vaddr, dma_addr_t dma_handle, unsigned long attrs)
-{
-	swiotlb_free_coherent(dev, size, vaddr, dma_handle);
-}
-
 static dma_addr_t octeon_unity_phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr;
@@ -228,7 +205,7 @@ EXPORT_SYMBOL(dma_to_phys);
 static struct octeon_dma_map_ops octeon_linear_dma_map_ops = {
 	.dma_map_ops = {
 		.alloc = octeon_dma_alloc_coherent,
-		.free = octeon_dma_free_coherent,
+		.free = swiotlb_free,
 		.map_page = octeon_dma_map_page,
 		.unmap_page = swiotlb_unmap_page,
 		.map_sg = octeon_dma_map_sg,
@@ -314,7 +291,7 @@ void __init plat_swiotlb_setup(void)
 static struct octeon_dma_map_ops _octeon_pci_dma_map_ops = {
 	.dma_map_ops = {
 		.alloc = octeon_dma_alloc_coherent,
-		.free = octeon_dma_free_coherent,
+		.free = swiotlb_free,
 		.map_page = octeon_dma_map_page,
 		.unmap_page = swiotlb_unmap_page,
 		.map_sg = octeon_dma_map_sg,
diff --git a/arch/mips/configs/ar7_defconfig b/arch/mips/configs/ar7_defconfig
index 92fca3c42eac..5651f4d8f45c 100644
--- a/arch/mips/configs/ar7_defconfig
+++ b/arch/mips/configs/ar7_defconfig
@@ -82,7 +82,6 @@ CONFIG_MAC80211=m
 CONFIG_MAC80211_RC_PID=y
 CONFIG_MAC80211_RC_DEFAULT_PID=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
diff --git a/arch/mips/configs/ath25_defconfig b/arch/mips/configs/ath25_defconfig
index 2c829950be17..b8d48038e74f 100644
--- a/arch/mips/configs/ath25_defconfig
+++ b/arch/mips/configs/ath25_defconfig
@@ -38,7 +38,6 @@ CONFIG_CFG80211=m
 CONFIG_MAC80211=m
 CONFIG_MAC80211_DEBUGFS=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_REDBOOT_PARTS=y
 CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-2
diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig
index 25ed914933e5..951c4231bdb8 100644
--- a/arch/mips/configs/ath79_defconfig
+++ b/arch/mips/configs/ath79_defconfig
@@ -39,7 +39,6 @@ CONFIG_CFG80211=m
 CONFIG_MAC80211=m
 CONFIG_MAC80211_DEBUGFS=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_REDBOOT_PARTS=y
 CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-2
diff --git a/arch/mips/configs/pic32mzda_defconfig b/arch/mips/configs/pic32mzda_defconfig
index 52192c632ae8..41190c2036e6 100644
--- a/arch/mips/configs/pic32mzda_defconfig
+++ b/arch/mips/configs/pic32mzda_defconfig
@@ -26,7 +26,6 @@ CONFIG_BINFMT_MISC=m
 # CONFIG_SUSPEND is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_ALLOW_DEV_COREDUMP is not set
 CONFIG_BLK_DEV_LOOP=m
 CONFIG_SCSI=y
diff --git a/arch/mips/configs/qi_lb60_defconfig b/arch/mips/configs/qi_lb60_defconfig
index 3f1333517405..3b02ff9a7c64 100644
--- a/arch/mips/configs/qi_lb60_defconfig
+++ b/arch/mips/configs/qi_lb60_defconfig
@@ -42,7 +42,6 @@ CONFIG_TCP_CONG_WESTWOOD=y
 # CONFIG_TCP_CONG_HTCP is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_NAND=y
diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig
index 99679e514042..5f71aa598b06 100644
--- a/arch/mips/configs/rm200_defconfig
+++ b/arch/mips/configs/rm200_defconfig
@@ -325,15 +325,6 @@ CONFIG_USB_SERIAL_EDGEPORT=m
 CONFIG_USB_SERIAL_EDGEPORT_TI=m
 CONFIG_USB_SERIAL_KEYSPAN_PDA=m
 CONFIG_USB_SERIAL_KEYSPAN=m
-CONFIG_USB_SERIAL_KEYSPAN_MPR=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28X=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28XA=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28XB=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19W=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19QW=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19QI=y
-CONFIG_USB_SERIAL_KEYSPAN_USA49W=y
-CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y
 CONFIG_USB_SERIAL_KLSI=m
 CONFIG_USB_SERIAL_KOBIL_SCT=m
 CONFIG_USB_SERIAL_MCT_U232=m
diff --git a/arch/mips/configs/rt305x_defconfig b/arch/mips/configs/rt305x_defconfig
index c695b7b1c4ae..dbe6a4639d05 100644
--- a/arch/mips/configs/rt305x_defconfig
+++ b/arch/mips/configs/rt305x_defconfig
@@ -76,7 +76,6 @@ CONFIG_VLAN_8021Q=y
 CONFIG_NET_SCHED=y
 CONFIG_HAMRADIO=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/mips/configs/xway_defconfig b/arch/mips/configs/xway_defconfig
index 4365108bef77..fa750d501c11 100644
--- a/arch/mips/configs/xway_defconfig
+++ b/arch/mips/configs/xway_defconfig
@@ -75,7 +75,6 @@ CONFIG_VLAN_8021Q=y
 CONFIG_NET_SCHED=y
 CONFIG_HAMRADIO=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 7c8aab23bce8..45d541baf359 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -1,6 +1,5 @@
 # MIPS headers
 generic-(CONFIG_GENERIC_CSUM) += checksum.h
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += dma-contiguous.h
 generic-y += emergency-restart.h
@@ -16,7 +15,6 @@ generic-y += qrwlock.h
 generic-y += qspinlock.h
 generic-y += sections.h
 generic-y += segment.h
-generic-y += serial.h
 generic-y += trace_clock.h
 generic-y += unaligned.h
 generic-y += user.h
diff --git a/arch/mips/include/asm/asm-prototypes.h b/arch/mips/include/asm/asm-prototypes.h
index d60b57f34e92..576f1a62dea9 100644
--- a/arch/mips/include/asm/asm-prototypes.h
+++ b/arch/mips/include/asm/asm-prototypes.h
@@ -3,5 +3,5 @@
 #include <asm/page.h>
 #include <asm/fpu.h>
 #include <asm-generic/asm-prototypes.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ftrace.h>
diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h
index 49691331ada4..946681db8dc3 100644
--- a/arch/mips/include/asm/compat.h
+++ b/arch/mips/include/asm/compat.h
@@ -126,79 +126,6 @@ typedef u32		compat_old_sigset_t;	/* at least 32 bits */
 
 typedef u32		compat_sigset_word;
 
-typedef union compat_sigval {
-	compat_int_t	sival_int;
-	compat_uptr_t	sival_ptr;
-} compat_sigval_t;
-
-/* Can't use the generic version because si_code and si_errno are swapped */
-
-#define SI_PAD_SIZE32	(128/sizeof(int) - 3)
-
-typedef struct compat_siginfo {
-	int si_signo;
-	int si_code;
-	int si_errno;
-
-	union {
-		int _pad[128 / sizeof(int) - 3];
-
-		/* kill() */
-		struct {
-			compat_pid_t _pid;	/* sender's pid */
-			__compat_uid32_t _uid;	/* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			compat_timer_t _tid;	/* timer id */
-			int _overrun;		/* overrun count */
-			compat_sigval_t _sigval;	/* same as below */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			compat_pid_t _pid;	/* sender's pid */
-			__compat_uid32_t _uid;	/* sender's uid */
-			compat_sigval_t _sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			compat_pid_t _pid;	/* which child */
-			__compat_uid32_t _uid;	/* sender's uid */
-			int _status;		/* exit code */
-			compat_clock_t _utime;
-			compat_clock_t _stime;
-		} _sigchld;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
-		struct {
-			compat_uptr_t _addr;	/* faulting insn/memory ref. */
-#ifdef __ARCH_SI_TRAPNO
-			int _trapno;	/* TRAP # which caused the signal */
-#endif
-			short _addr_lsb; /* LSB of the reported address */
-			struct {
-				compat_uptr_t _lower;
-				compat_uptr_t _upper;
-			} _addr_bnd;
-		} _sigfault;
-
-		/* SIGPOLL */
-		struct {
-			compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */
-			int _fd;
-		} _sigpoll;
-
-		struct {
-			compat_uptr_t _call_addr; /* calling insn */
-			int _syscall;	/* triggering system call number */
-			compat_uint_t _arch;	/* AUDIT_ARCH_* of syscall */
-		} _sigsys;
-	} _sifields;
-} compat_siginfo_t;
-
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
 /*
diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h
new file mode 100644
index 000000000000..f32f15530aba
--- /dev/null
+++ b/arch/mips/include/asm/dma-direct.h
@@ -0,0 +1 @@
+#include <asm/dma-coherence.h>
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index 0d9418d264f9..886e75a383f2 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -17,16 +17,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return mips_dma_map_ops;
 }
 
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size <= *dev->dma_mask;
-}
-
-static inline void dma_mark_clean(void *addr, size_t size) {}
-
 #define arch_setup_dma_ops arch_setup_dma_ops
 static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
 				      u64 size, const struct iommu_ops *iommu,
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h
index c0bd47444cff..da39e4d326ba 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h
@@ -55,6 +55,10 @@ struct bcm63xx_enet_platform_data {
 
 	/* DMA descriptor shift */
 	unsigned int dma_desc_shift;
+
+	/* dma channel ids */
+	int rx_chan;
+	int tx_chan;
 };
 
 /*
diff --git a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
index 9110988b92a1..138edf6b5b48 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
@@ -61,6 +61,14 @@ static inline void plat_post_dma_flush(struct device *dev)
 {
 }
 
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	if (!dev->dma_mask)
+		return false;
+
+	return addr + size - 1 <= *dev->dma_mask;
+}
+
 dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
 phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
 
diff --git a/arch/mips/include/asm/mach-generic/dma-coherence.h b/arch/mips/include/asm/mach-generic/dma-coherence.h
index 61addb1677e9..8ad7a40ca786 100644
--- a/arch/mips/include/asm/mach-generic/dma-coherence.h
+++ b/arch/mips/include/asm/mach-generic/dma-coherence.h
@@ -70,16 +70,4 @@ static inline void plat_post_dma_flush(struct device *dev)
 }
 #endif
 
-#ifdef CONFIG_SWIOTLB
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return paddr;
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return daddr;
-}
-#endif
-
 #endif /* __ASM_MACH_GENERIC_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-loongson64/dma-coherence.h b/arch/mips/include/asm/mach-loongson64/dma-coherence.h
index 1602a9e9e8c2..b1b575f5c6c1 100644
--- a/arch/mips/include/asm/mach-loongson64/dma-coherence.h
+++ b/arch/mips/include/asm/mach-loongson64/dma-coherence.h
@@ -17,6 +17,14 @@
 
 struct device;
 
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	if (!dev->dma_mask)
+		return false;
+
+	return addr + size - 1 <= *dev->dma_mask;
+}
+
 extern dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
 extern phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
 static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
diff --git a/arch/mips/include/asm/netlogic/common.h b/arch/mips/include/asm/netlogic/common.h
index a6e6cbebe046..57616649b4f3 100644
--- a/arch/mips/include/asm/netlogic/common.h
+++ b/arch/mips/include/asm/netlogic/common.h
@@ -87,9 +87,6 @@ unsigned int nlm_get_cpu_frequency(void);
 extern const struct plat_smp_ops nlm_smp_ops;
 extern char nlm_reset_entry[], nlm_reset_entry_end[];
 
-/* SWIOTLB */
-extern const struct dma_map_ops nlm_swiotlb_dma_ops;
-
 extern unsigned int nlm_threads_per_core;
 extern cpumask_t nlm_cpumask;
 
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 9e9e94415d08..129e0328367f 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -534,6 +534,9 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
+/* We don't have hardware dirty/accessed bits, generic_pmdp_establish is fine.*/
+#define pmdp_establish generic_pmdp_establish
+
 #define has_transparent_hugepage has_transparent_hugepage
 extern int has_transparent_hugepage(void);
 
@@ -552,7 +555,7 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t pmd);
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_WRITE);
diff --git a/arch/mips/include/asm/serial.h b/arch/mips/include/asm/serial.h
new file mode 100644
index 000000000000..1d830c6666c2
--- /dev/null
+++ b/arch/mips/include/asm/serial.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2017 MIPS Tech, LLC
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#ifndef __ASM__SERIAL_H
+#define __ASM__SERIAL_H
+
+#ifdef CONFIG_MIPS_GENERIC
+/*
+ * Generic kernels cannot know a correct value for all platforms at
+ * compile time. Set it to 0 to prevent 8250_early using it
+ */
+#define BASE_BAUD 0
+#else
+#include <asm-generic/serial.h>
+#endif
+
+#endif /* __ASM__SERIAL_H */
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 5e8927f99a76..4993db40482c 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -49,9 +49,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* How to get the thread information struct from C.  */
 register struct thread_info *__current_thread_info __asm__("$28");
 
diff --git a/arch/mips/include/uapi/asm/Kbuild b/arch/mips/include/uapi/asm/Kbuild
index a0266feba9e6..7a4becd8963a 100644
--- a/arch/mips/include/uapi/asm/Kbuild
+++ b/arch/mips/include/uapi/asm/Kbuild
@@ -1,4 +1,5 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += ipcbuf.h
diff --git a/arch/mips/include/uapi/asm/poll.h b/arch/mips/include/uapi/asm/poll.h
index ad289d7b7434..3173f8917128 100644
--- a/arch/mips/include/uapi/asm/poll.h
+++ b/arch/mips/include/uapi/asm/poll.h
@@ -2,8 +2,25 @@
 #ifndef __ASM_POLL_H
 #define __ASM_POLL_H
 
+#ifndef __KERNEL__
 #define POLLWRNORM	POLLOUT
-#define POLLWRBAND	0x0100
+#define POLLWRBAND	(__force __poll_t)0x0100
+#else
+#define __ARCH_HAS_MANGLED_POLL
+static inline __u16 mangle_poll(__poll_t val)
+{
+	__u16 v = (__force __u16)val;
+	/* bit 9 -> bit 8, bit 8 -> bit 2 */
+	return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6);
+}
+
+static inline __poll_t demangle_poll(__u16 v)
+{
+        /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
+	return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
+				((v & 4) << 6));
+}
+#endif
 
 #include <asm-generic/poll.h>
 
diff --git a/arch/mips/include/uapi/asm/siginfo.h b/arch/mips/include/uapi/asm/siginfo.h
index f17d8163dec6..262504bd59a5 100644
--- a/arch/mips/include/uapi/asm/siginfo.h
+++ b/arch/mips/include/uapi/asm/siginfo.h
@@ -14,8 +14,6 @@
 #define __ARCH_SIGEV_PREAMBLE_SIZE (sizeof(long) + 2*sizeof(int))
 #undef __ARCH_SI_TRAPNO /* exception code needs to fill this ...  */
 
-#define HAVE_ARCH_SIGINFO_T
-
 /*
  * Careful to keep union _sifields from shifting ...
  */
@@ -27,92 +25,10 @@
 #error _MIPS_SZLONG neither 32 nor 64
 #endif
 
-#define __ARCH_SIGSYS
+#define __ARCH_HAS_SWAPPED_SIGINFO
 
 #include <asm-generic/siginfo.h>
 
-/* We can't use generic siginfo_t, because our si_code and si_errno are swapped */
-typedef struct siginfo {
-	int si_signo;
-	int si_code;
-	int si_errno;
-	int __pad0[SI_MAX_SIZE / sizeof(int) - SI_PAD_SIZE - 3];
-
-	union {
-		int _pad[SI_PAD_SIZE];
-
-		/* kill() */
-		struct {
-			__kernel_pid_t _pid;	/* sender's pid */
-			__ARCH_SI_UID_T _uid;	/* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			__kernel_timer_t _tid;	/* timer id */
-			int _overrun;		/* overrun count */
-			char _pad[sizeof( __ARCH_SI_UID_T) - sizeof(int)];
-			sigval_t _sigval;	/* same as below */
-			int _sys_private;	/* not to be passed to user */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			__kernel_pid_t _pid;	/* sender's pid */
-			__ARCH_SI_UID_T _uid;	/* sender's uid */
-			sigval_t _sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			__kernel_pid_t _pid;	/* which child */
-			__ARCH_SI_UID_T _uid;	/* sender's uid */
-			int _status;		/* exit code */
-			__kernel_clock_t _utime;
-			__kernel_clock_t _stime;
-		} _sigchld;
-
-		/* IRIX SIGCHLD */
-		struct {
-			__kernel_pid_t _pid;	/* which child */
-			__kernel_clock_t _utime;
-			int _status;		/* exit code */
-			__kernel_clock_t _stime;
-		} _irix_sigchld;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
-		struct {
-			void __user *_addr; /* faulting insn/memory ref. */
-#ifdef __ARCH_SI_TRAPNO
-			int _trapno;	/* TRAP # which caused the signal */
-#endif
-			short _addr_lsb;
-			union {
-				/* used when si_code=SEGV_BNDERR */
-				struct {
-					void __user *_lower;
-					void __user *_upper;
-				} _addr_bnd;
-				/* used when si_code=SEGV_PKUERR */
-				__u32 _pkey;
-			};
-		} _sigfault;
-
-		/* SIGPOLL, SIGXFSZ (To do ...)	 */
-		struct {
-			__ARCH_SI_BAND_T _band; /* POLL_IN, POLL_OUT, POLL_MSG */
-			int _fd;
-		} _sigpoll;
-
-		/* SIGSYS */
-		struct {
-			void __user *_call_addr; /* calling user insn */
-			int _syscall;	/* triggering system call number */
-			unsigned int _arch;	/* AUDIT_ARCH_* of syscall */
-		} _sigsys;
-	} _sifields;
-} siginfo_t;
-
 /*
  * si_code values
  * Again these have been chosen to be IRIX compatible.
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index c7ed26029cbb..e68e6e04063a 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -235,6 +235,7 @@ LEAF(mips_cps_core_init)
 	has_mt	t0, 3f
 
 	.set	push
+	.set	MIPS_ISA_LEVEL_RAW
 	.set	mt
 
 	/* Only allow 1 TC per VPE to execute... */
@@ -388,6 +389,7 @@ LEAF(mips_cps_boot_vpes)
 #elif defined(CONFIG_MIPS_MT)
 
 	.set	push
+	.set	MIPS_ISA_LEVEL_RAW
 	.set	mt
 
 	/* If the core doesn't support MT then return */
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index dd5567b1e305..8f5bd04f320a 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -292,7 +292,6 @@ void mips_cm_lock_other(unsigned int cluster, unsigned int core,
 				  *this_cpu_ptr(&cm_core_lock_flags));
 	} else {
 		WARN_ON(cluster != 0);
-		WARN_ON(vp != 0);
 		WARN_ON(block != CM_GCR_Cx_OTHER_BLOCK_LOCAL);
 
 		/*
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 45d0b6b037ee..57028d49c202 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -705,6 +705,18 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 	struct task_struct *t;
 	int max_users;
 
+	/* If nothing to change, return right away, successfully.  */
+	if (value == mips_get_process_fp_mode(task))
+		return 0;
+
+	/* Only accept a mode change if 64-bit FP enabled for o32.  */
+	if (!IS_ENABLED(CONFIG_MIPS_O32_FP64_SUPPORT))
+		return -EOPNOTSUPP;
+
+	/* And only for o32 tasks.  */
+	if (IS_ENABLED(CONFIG_64BIT) && !test_thread_flag(TIF_32BIT_REGS))
+		return -EOPNOTSUPP;
+
 	/* Check the value is valid */
 	if (value & ~known_bits)
 		return -EOPNOTSUPP;
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index 0dbcd152a1a9..89950b7bf536 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -44,11 +44,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	return add_memory_region(base, size, BOOT_MEM_RAM);
 }
 
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
-}
-
 int __init early_init_dt_reserve_memory_arch(phys_addr_t base,
 					phys_addr_t size, bool nomap)
 {
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index efbd8df8b665..0b23b1ad99e6 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -419,63 +419,160 @@ static int gpr64_set(struct task_struct *target,
 
 #endif /* CONFIG_64BIT */
 
+/*
+ * Copy the floating-point context to the supplied NT_PRFPREG buffer,
+ * !CONFIG_CPU_HAS_MSA variant.  FP context's general register slots
+ * correspond 1:1 to buffer slots.  Only general registers are copied.
+ */
+static int fpr_get_fpa(struct task_struct *target,
+		       unsigned int *pos, unsigned int *count,
+		       void **kbuf, void __user **ubuf)
+{
+	return user_regset_copyout(pos, count, kbuf, ubuf,
+				   &target->thread.fpu,
+				   0, NUM_FPU_REGS * sizeof(elf_fpreg_t));
+}
+
+/*
+ * Copy the floating-point context to the supplied NT_PRFPREG buffer,
+ * CONFIG_CPU_HAS_MSA variant.  Only lower 64 bits of FP context's
+ * general register slots are copied to buffer slots.  Only general
+ * registers are copied.
+ */
+static int fpr_get_msa(struct task_struct *target,
+		       unsigned int *pos, unsigned int *count,
+		       void **kbuf, void __user **ubuf)
+{
+	unsigned int i;
+	u64 fpr_val;
+	int err;
+
+	BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
+	for (i = 0; i < NUM_FPU_REGS; i++) {
+		fpr_val = get_fpr64(&target->thread.fpu.fpr[i], 0);
+		err = user_regset_copyout(pos, count, kbuf, ubuf,
+					  &fpr_val, i * sizeof(elf_fpreg_t),
+					  (i + 1) * sizeof(elf_fpreg_t));
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/*
+ * Copy the floating-point context to the supplied NT_PRFPREG buffer.
+ * Choose the appropriate helper for general registers, and then copy
+ * the FCSR register separately.
+ */
 static int fpr_get(struct task_struct *target,
 		   const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
 		   void *kbuf, void __user *ubuf)
 {
-	unsigned i;
+	const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
 	int err;
-	u64 fpr_val;
 
-	/* XXX fcr31  */
+	if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t))
+		err = fpr_get_fpa(target, &pos, &count, &kbuf, &ubuf);
+	else
+		err = fpr_get_msa(target, &pos, &count, &kbuf, &ubuf);
+	if (err)
+		return err;
 
-	if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t))
-		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					   &target->thread.fpu,
-					   0, sizeof(elf_fpregset_t));
+	err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.fpu.fcr31,
+				  fcr31_pos, fcr31_pos + sizeof(u32));
 
-	for (i = 0; i < NUM_FPU_REGS; i++) {
-		fpr_val = get_fpr64(&target->thread.fpu.fpr[i], 0);
-		err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					  &fpr_val, i * sizeof(elf_fpreg_t),
-					  (i + 1) * sizeof(elf_fpreg_t));
+	return err;
+}
+
+/*
+ * Copy the supplied NT_PRFPREG buffer to the floating-point context,
+ * !CONFIG_CPU_HAS_MSA variant.   Buffer slots correspond 1:1 to FP
+ * context's general register slots.  Only general registers are copied.
+ */
+static int fpr_set_fpa(struct task_struct *target,
+		       unsigned int *pos, unsigned int *count,
+		       const void **kbuf, const void __user **ubuf)
+{
+	return user_regset_copyin(pos, count, kbuf, ubuf,
+				  &target->thread.fpu,
+				  0, NUM_FPU_REGS * sizeof(elf_fpreg_t));
+}
+
+/*
+ * Copy the supplied NT_PRFPREG buffer to the floating-point context,
+ * CONFIG_CPU_HAS_MSA variant.  Buffer slots are copied to lower 64
+ * bits only of FP context's general register slots.  Only general
+ * registers are copied.
+ */
+static int fpr_set_msa(struct task_struct *target,
+		       unsigned int *pos, unsigned int *count,
+		       const void **kbuf, const void __user **ubuf)
+{
+	unsigned int i;
+	u64 fpr_val;
+	int err;
+
+	BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
+	for (i = 0; i < NUM_FPU_REGS && *count > 0; i++) {
+		err = user_regset_copyin(pos, count, kbuf, ubuf,
+					 &fpr_val, i * sizeof(elf_fpreg_t),
+					 (i + 1) * sizeof(elf_fpreg_t));
 		if (err)
 			return err;
+		set_fpr64(&target->thread.fpu.fpr[i], 0, fpr_val);
 	}
 
 	return 0;
 }
 
+/*
+ * Copy the supplied NT_PRFPREG buffer to the floating-point context.
+ * Choose the appropriate helper for general registers, and then copy
+ * the FCSR register separately.
+ *
+ * We optimize for the case where `count % sizeof(elf_fpreg_t) == 0',
+ * which is supposed to have been guaranteed by the kernel before
+ * calling us, e.g. in `ptrace_regset'.  We enforce that requirement,
+ * so that we can safely avoid preinitializing temporaries for
+ * partial register writes.
+ */
 static int fpr_set(struct task_struct *target,
 		   const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
 		   const void *kbuf, const void __user *ubuf)
 {
-	unsigned i;
+	const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
+	u32 fcr31;
 	int err;
-	u64 fpr_val;
 
-	/* XXX fcr31  */
+	BUG_ON(count % sizeof(elf_fpreg_t));
+
+	if (pos + count > sizeof(elf_fpregset_t))
+		return -EIO;
 
 	init_fp_ctx(target);
 
-	if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t))
-		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					  &target->thread.fpu,
-					  0, sizeof(elf_fpregset_t));
+	if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t))
+		err = fpr_set_fpa(target, &pos, &count, &kbuf, &ubuf);
+	else
+		err = fpr_set_msa(target, &pos, &count, &kbuf, &ubuf);
+	if (err)
+		return err;
 
-	BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
-	for (i = 0; i < NUM_FPU_REGS && count >= sizeof(elf_fpreg_t); i++) {
+	if (count > 0) {
 		err = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					 &fpr_val, i * sizeof(elf_fpreg_t),
-					 (i + 1) * sizeof(elf_fpreg_t));
+					 &fcr31,
+					 fcr31_pos, fcr31_pos + sizeof(u32));
 		if (err)
 			return err;
-		set_fpr64(&target->thread.fpu.fpr[i], 0, fpr_val);
+
+		ptrace_setfcr31(target, fcr31);
 	}
 
-	return 0;
+	return err;
 }
 
 enum mips_regset {
diff --git a/arch/mips/kernel/rtlx.c b/arch/mips/kernel/rtlx.c
index b80dd8b17a76..bbb0f4770c0d 100644
--- a/arch/mips/kernel/rtlx.c
+++ b/arch/mips/kernel/rtlx.c
@@ -336,10 +336,10 @@ static int file_release(struct inode *inode, struct file *filp)
 	return rtlx_release(iminor(inode));
 }
 
-static unsigned int file_poll(struct file *file, poll_table *wait)
+static __poll_t file_poll(struct file *file, poll_table *wait)
 {
 	int minor = iminor(file_inode(file));
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 
 	poll_wait(file, &channel_wqs[minor].rt_queue, wait);
 	poll_wait(file, &channel_wqs[minor].lx_queue, wait);
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index cf5c7c05e5a3..c4db910a8794 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -76,70 +76,3 @@ SYSCALL_DEFINE3(32_sigaction, long, sig, const struct compat_sigaction __user *,
 
 	return ret;
 }
-
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
-{
-	int err;
-
-	if (!access_ok (VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
-		return -EFAULT;
-
-	/* If you change siginfo_t structure, please be sure
-	   this code is fixed accordingly.
-	   It should never copy any pad contained in the structure
-	   to avoid security leaks, but must copy the generic
-	   3 ints plus the relevant union member.
-	   This routine must convert siginfo from 64bit to 32bit as well
-	   at the same time.  */
-	err = __put_user(from->si_signo, &to->si_signo);
-	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user(from->si_code, &to->si_code);
-	if (from->si_code < 0)
-		err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
-	else {
-		switch (siginfo_layout(from->si_signo, from->si_code)) {
-		case SIL_TIMER:
-			err |= __put_user(from->si_tid, &to->si_tid);
-			err |= __put_user(from->si_overrun, &to->si_overrun);
-			err |= __put_user(from->si_int, &to->si_int);
-			break;
-		case SIL_CHLD:
-			err |= __put_user(from->si_utime, &to->si_utime);
-			err |= __put_user(from->si_stime, &to->si_stime);
-			err |= __put_user(from->si_status, &to->si_status);
-		case SIL_KILL:
-			err |= __put_user(from->si_pid, &to->si_pid);
-			err |= __put_user(from->si_uid, &to->si_uid);
-			break;
-		case SIL_FAULT:
-			err |= __put_user((unsigned long)from->si_addr, &to->si_addr);
-			break;
-		case SIL_POLL:
-			err |= __put_user(from->si_band, &to->si_band);
-			err |= __put_user(from->si_fd, &to->si_fd);
-			break;
-		case SIL_RT:
-			err |= __put_user(from->si_pid, &to->si_pid);
-			err |= __put_user(from->si_uid, &to->si_uid);
-			err |= __put_user(from->si_int, &to->si_int);
-			break;
-		case SIL_SYS:
-			err |= __copy_to_user(&to->si_call_addr, &from->si_call_addr,
-					      sizeof(compat_uptr_t));
-			err |= __put_user(from->si_syscall, &to->si_syscall);
-			err |= __put_user(from->si_arch, &to->si_arch);
-			break;
-		}
-	}
-	return err;
-}
-
-int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
-{
-	if (copy_from_user(to, from, 3*sizeof(int)) ||
-	    copy_from_user(to->_sifields._pad,
-			   from->_sifields._pad, SI_PAD_SIZE32))
-		return -EFAULT;
-
-	return 0;
-}
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 5d19ed07e99d..0ae4a731cc12 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -699,11 +699,12 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode)
 asmlinkage void do_ov(struct pt_regs *regs)
 {
 	enum ctx_state prev_state;
-	siginfo_t info = {
-		.si_signo = SIGFPE,
-		.si_code = FPE_INTOVF,
-		.si_addr = (void __user *)regs->cp0_epc,
-	};
+	siginfo_t info;
+
+	clear_siginfo(&info);
+	info.si_signo = SIGFPE;
+	info.si_code = FPE_INTOVF;
+	info.si_addr = (void __user *)regs->cp0_epc;
 
 	prev_state = exception_enter();
 	die_if_kernel("Integer overflow", regs);
@@ -721,7 +722,11 @@ asmlinkage void do_ov(struct pt_regs *regs)
 void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr,
 		     struct task_struct *tsk)
 {
-	struct siginfo si = { .si_addr = fault_addr, .si_signo = SIGFPE };
+	struct siginfo si;
+
+	clear_siginfo(&si);
+	si.si_addr = fault_addr;
+	si.si_signo = SIGFPE;
 
 	if (fcr31 & FPU_CSR_INV_X)
 		si.si_code = FPE_FLTINV;
@@ -739,9 +744,10 @@ void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr,
 
 int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
 {
-	struct siginfo si = { 0 };
+	struct siginfo si;
 	struct vm_area_struct *vma;
 
+	clear_siginfo(&si);
 	switch (sig) {
 	case 0:
 		return 0;
@@ -890,9 +896,10 @@ out:
 void do_trap_or_bp(struct pt_regs *regs, unsigned int code, int si_code,
 	const char *str)
 {
-	siginfo_t info = { 0 };
+	siginfo_t info;
 	char b[40];
 
+	clear_siginfo(&info);
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_TRAP, str, regs, code, current->thread.trap_nr,
 			 SIGTRAP) == NOTIFY_STOP)
@@ -1499,9 +1506,13 @@ asmlinkage void do_mdmx(struct pt_regs *regs)
  */
 asmlinkage void do_watch(struct pt_regs *regs)
 {
-	siginfo_t info = { .si_signo = SIGTRAP, .si_code = TRAP_HWBKPT };
+	siginfo_t info;
 	enum ctx_state prev_state;
 
+	clear_siginfo(&info);
+	info.si_signo = SIGTRAP;
+	info.si_code = TRAP_HWBKPT;
+
 	prev_state = exception_enter();
 	/*
 	 * Clear WP (bit 22) bit of cause register so we don't loop
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index d535edc01434..75fdeaa8c62f 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -445,10 +445,8 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int r = -EINTR;
-	sigset_t sigsaved;
 
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+	kvm_sigset_activate(vcpu);
 
 	if (vcpu->mmio_needed) {
 		if (!vcpu->mmio_is_write)
@@ -480,8 +478,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	local_irq_enable();
 
 out:
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+	kvm_sigset_deactivate(vcpu);
 
 	return r;
 }
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index 78c2affeabf8..e84e12655fa8 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -16,4 +16,5 @@ obj-$(CONFIG_CPU_R3000)		+= r3k_dump_tlb.o
 obj-$(CONFIG_CPU_TX39XX)	+= r3k_dump_tlb.o
 
 # libgcc-style stuff needed in the kernel
-obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o ucmpdi2.o
+obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o multi3.o \
+	 ucmpdi2.o
diff --git a/arch/mips/lib/libgcc.h b/arch/mips/lib/libgcc.h
index 28002ed90c2c..199a7f96282f 100644
--- a/arch/mips/lib/libgcc.h
+++ b/arch/mips/lib/libgcc.h
@@ -10,10 +10,18 @@ typedef int word_type __attribute__ ((mode (__word__)));
 struct DWstruct {
 	int high, low;
 };
+
+struct TWstruct {
+	long long high, low;
+};
 #elif defined(__LITTLE_ENDIAN)
 struct DWstruct {
 	int low, high;
 };
+
+struct TWstruct {
+	long long low, high;
+};
 #else
 #error I feel sick.
 #endif
@@ -23,4 +31,13 @@ typedef union {
 	long long ll;
 } DWunion;
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6)
+typedef int ti_type __attribute__((mode(TI)));
+
+typedef union {
+	struct TWstruct s;
+	ti_type ti;
+} TWunion;
+#endif
+
 #endif /* __ASM_LIBGCC_H */
diff --git a/arch/mips/lib/multi3.c b/arch/mips/lib/multi3.c
new file mode 100644
index 000000000000..111ad475aa0c
--- /dev/null
+++ b/arch/mips/lib/multi3.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+
+#include "libgcc.h"
+
+/*
+ * GCC 7 suboptimally generates __multi3 calls for mips64r6, so for that
+ * specific case only we'll implement it here.
+ *
+ * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82981
+ */
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ == 7)
+
+/* multiply 64-bit values, low 64-bits returned */
+static inline long long notrace dmulu(long long a, long long b)
+{
+	long long res;
+
+	asm ("dmulu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+	return res;
+}
+
+/* multiply 64-bit unsigned values, high 64-bits of 128-bit result returned */
+static inline long long notrace dmuhu(long long a, long long b)
+{
+	long long res;
+
+	asm ("dmuhu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+	return res;
+}
+
+/* multiply 128-bit values, low 128-bits returned */
+ti_type notrace __multi3(ti_type a, ti_type b)
+{
+	TWunion res, aa, bb;
+
+	aa.ti = a;
+	bb.ti = b;
+
+	/*
+	 * a * b =           (a.lo * b.lo)
+	 *         + 2^64  * (a.hi * b.lo + a.lo * b.hi)
+	 *        [+ 2^128 * (a.hi * b.hi)]
+	 */
+	res.s.low = dmulu(aa.s.low, bb.s.low);
+	res.s.high = dmuhu(aa.s.low, bb.s.low);
+	res.s.high += dmulu(aa.s.high, bb.s.low);
+	res.s.high += dmulu(aa.s.low, bb.s.high);
+
+	return res.ti;
+}
+EXPORT_SYMBOL(__multi3);
+
+#endif /* 64BIT && CPU_MIPSR6 && GCC7 */
diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig
index 0d249fc3cfe9..6f109bb54cdb 100644
--- a/arch/mips/loongson64/Kconfig
+++ b/arch/mips/loongson64/Kconfig
@@ -136,6 +136,7 @@ config SWIOTLB
 	bool "Soft IOMMU Support for All-Memory DMA"
 	default y
 	depends on CPU_LOONGSON3
+	select DMA_DIRECT_OPS
 	select IOMMU_HELPER
 	select NEED_SG_DMA_LENGTH
 	select NEED_DMA_MAP_STATE
diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c
index ef07740cee61..7bbcf89475f3 100644
--- a/arch/mips/loongson64/common/dma-swiotlb.c
+++ b/arch/mips/loongson64/common/dma-swiotlb.c
@@ -13,32 +13,12 @@
 static void *loongson_dma_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
-	void *ret;
+	void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
 
-	/* ignore region specifiers */
-	gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
-
-	if ((IS_ENABLED(CONFIG_ISA) && dev == NULL) ||
-	    (IS_ENABLED(CONFIG_ZONE_DMA) &&
-	     dev->coherent_dma_mask < DMA_BIT_MASK(32)))
-		gfp |= __GFP_DMA;
-	else if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
-		 dev->coherent_dma_mask < DMA_BIT_MASK(40))
-		gfp |= __GFP_DMA32;
-
-	gfp |= __GFP_NORETRY;
-
-	ret = swiotlb_alloc_coherent(dev, size, dma_handle, gfp);
 	mb();
 	return ret;
 }
 
-static void loongson_dma_free_coherent(struct device *dev, size_t size,
-		void *vaddr, dma_addr_t dma_handle, unsigned long attrs)
-{
-	swiotlb_free_coherent(dev, size, vaddr, dma_handle);
-}
-
 static dma_addr_t loongson_dma_map_page(struct device *dev, struct page *page,
 				unsigned long offset, size_t size,
 				enum dma_data_direction dir,
@@ -109,7 +89,7 @@ phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 
 static const struct dma_map_ops loongson_dma_map_ops = {
 	.alloc = loongson_dma_alloc_coherent,
-	.free = loongson_dma_free_coherent,
+	.free = swiotlb_free,
 	.map_page = loongson_dma_map_page,
 	.unmap_page = swiotlb_unmap_page,
 	.map_sg = loongson_dma_map_sg,
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index e3e94d05f0fd..237532e89919 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -93,9 +93,6 @@ static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
 {
 	gfp_t dma_flag;
 
-	/* ignore region specifiers */
-	gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
-
 #ifdef CONFIG_ISA
 	if (dev == NULL)
 		dma_flag = __GFP_DMA;
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index cdb5a191b9d5..9bb6baa45da3 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -40,7 +40,7 @@
 
 #include "uasm.c"
 
-static const struct insn const insn_table_MM[insn_invalid] = {
+static const struct insn insn_table_MM[insn_invalid] = {
 	[insn_addu]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD},
 	[insn_addiu]	= {M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
 	[insn_and]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD},
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 44b925005dd3..4d8cb9bb8365 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -1207,8 +1207,6 @@ jmp_cmp:
 	return 0;
 }
 
-int bpf_jit_enable __read_mostly;
-
 void bpf_jit_compile(struct bpf_prog *fp)
 {
 	struct jit_ctx ctx;
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 962b0259b4b6..3e2798bfea4f 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -177,8 +177,6 @@ static u32 b_imm(unsigned int tgt, struct jit_ctx *ctx)
 		(ctx->idx * 4) - 4;
 }
 
-int bpf_jit_enable __read_mostly;
-
 enum which_ebpf_reg {
 	src_reg,
 	src_reg_no_fp,
@@ -743,16 +741,11 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		break;
 	case BPF_ALU | BPF_DIV | BPF_K: /* ALU_IMM */
 	case BPF_ALU | BPF_MOD | BPF_K: /* ALU_IMM */
+		if (insn->imm == 0)
+			return -EINVAL;
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
 		if (dst < 0)
 			return dst;
-		if (insn->imm == 0) { /* Div by zero */
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO);
-		}
 		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
 		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX)
 			/* sign extend */
@@ -772,19 +765,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K: /* ALU_IMM */
 	case BPF_ALU64 | BPF_MOD | BPF_K: /* ALU_IMM */
+		if (insn->imm == 0)
+			return -EINVAL;
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
 		if (dst < 0)
 			return dst;
-		if (insn->imm == 0) { /* Div by zero */
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO);
-		}
 		if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT)
 			emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32);
-
 		if (insn->imm == 1) {
 			/* div by 1 is a nop, mod by 1 is zero */
 			if (bpf_op == BPF_MOD)
@@ -862,11 +849,6 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		case BPF_DIV:
 		case BPF_MOD:
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src);
 			emit_instr(ctx, ddivu, dst, src);
 			if (bpf_op == BPF_DIV)
 				emit_instr(ctx, mflo, dst);
@@ -945,11 +927,6 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		case BPF_DIV:
 		case BPF_MOD:
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src);
 			emit_instr(ctx, divu, dst, src);
 			if (bpf_op == BPF_DIV)
 				emit_instr(ctx, mflo, dst);
@@ -1869,7 +1846,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	unsigned int image_size;
 	u8 *image_ptr;
 
-	if (!bpf_jit_enable || !cpu_has_mips64r2)
+	if (!prog->jit_requested || !cpu_has_mips64r2)
 		return prog;
 
 	tmp = bpf_jit_blind_constants(prog);
diff --git a/arch/mips/netlogic/Kconfig b/arch/mips/netlogic/Kconfig
index 8296b13affd2..7fcfc7fe9f14 100644
--- a/arch/mips/netlogic/Kconfig
+++ b/arch/mips/netlogic/Kconfig
@@ -89,9 +89,4 @@ config IOMMU_HELPER
 config NEED_SG_DMA_LENGTH
 	bool
 
-config SWIOTLB
-	def_bool y
-	select NEED_SG_DMA_LENGTH
-	select IOMMU_HELPER
-
 endif
diff --git a/arch/mips/netlogic/common/Makefile b/arch/mips/netlogic/common/Makefile
index 60d00b5d748e..89f6e3f39fed 100644
--- a/arch/mips/netlogic/common/Makefile
+++ b/arch/mips/netlogic/common/Makefile
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-y				+= irq.o time.o
-obj-y				+= nlm-dma.o
 obj-y				+= reset.o
 obj-$(CONFIG_SMP)		+= smp.o smpboot.o
 obj-$(CONFIG_EARLY_PRINTK)	+= earlycons.o
diff --git a/arch/mips/netlogic/common/nlm-dma.c b/arch/mips/netlogic/common/nlm-dma.c
deleted file mode 100644
index 0ec9d9da6d51..000000000000
--- a/arch/mips/netlogic/common/nlm-dma.c
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
-*  Copyright (C) 2003-2013 Broadcom Corporation
-*  All Rights Reserved
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the Broadcom
- * license below:
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in
- *    the documentation and/or other materials provided with the
- *    distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR
- * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
- * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
- * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
- * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-#include <linux/dma-mapping.h>
-#include <linux/scatterlist.h>
-#include <linux/bootmem.h>
-#include <linux/export.h>
-#include <linux/swiotlb.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/mm.h>
-
-#include <asm/bootinfo.h>
-
-static char *nlm_swiotlb;
-
-static void *nlm_dma_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	/* ignore region specifiers */
-	gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
-
-#ifdef CONFIG_ZONE_DMA32
-	if (dev->coherent_dma_mask <= DMA_BIT_MASK(32))
-		gfp |= __GFP_DMA32;
-#endif
-
-	/* Don't invoke OOM killer */
-	gfp |= __GFP_NORETRY;
-
-	return swiotlb_alloc_coherent(dev, size, dma_handle, gfp);
-}
-
-static void nlm_dma_free_coherent(struct device *dev, size_t size,
-	void *vaddr, dma_addr_t dma_handle, unsigned long attrs)
-{
-	swiotlb_free_coherent(dev, size, vaddr, dma_handle);
-}
-
-const struct dma_map_ops nlm_swiotlb_dma_ops = {
-	.alloc = nlm_dma_alloc_coherent,
-	.free = nlm_dma_free_coherent,
-	.map_page = swiotlb_map_page,
-	.unmap_page = swiotlb_unmap_page,
-	.map_sg = swiotlb_map_sg_attrs,
-	.unmap_sg = swiotlb_unmap_sg_attrs,
-	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = swiotlb_sync_sg_for_device,
-	.mapping_error = swiotlb_dma_mapping_error,
-	.dma_supported = swiotlb_dma_supported
-};
-
-void __init plat_swiotlb_setup(void)
-{
-	size_t swiotlbsize;
-	unsigned long swiotlb_nslabs;
-
-	swiotlbsize = 1 << 20; /* 1 MB for now */
-	swiotlb_nslabs = swiotlbsize >> IO_TLB_SHIFT;
-	swiotlb_nslabs = ALIGN(swiotlb_nslabs, IO_TLB_SEGSIZE);
-	swiotlbsize = swiotlb_nslabs << IO_TLB_SHIFT;
-
-	nlm_swiotlb = alloc_bootmem_low_pages(swiotlbsize);
-	swiotlb_init_with_tbl(nlm_swiotlb, swiotlb_nslabs, 1);
-}
diff --git a/arch/mips/ralink/timer.c b/arch/mips/ralink/timer.c
index d4469b20d176..4f46a4509f79 100644
--- a/arch/mips/ralink/timer.c
+++ b/arch/mips/ralink/timer.c
@@ -109,9 +109,9 @@ static int rt_timer_probe(struct platform_device *pdev)
 	}
 
 	rt->irq = platform_get_irq(pdev, 0);
-	if (!rt->irq) {
+	if (rt->irq < 0) {
 		dev_err(&pdev->dev, "failed to load irq\n");
-		return -ENOENT;
+		return rt->irq;
 	}
 
 	rt->membase = devm_ioremap_resource(&pdev->dev, res);
diff --git a/arch/mips/rb532/Makefile b/arch/mips/rb532/Makefile
index efdecdb6e3ea..8186afca2234 100644
--- a/arch/mips/rb532/Makefile
+++ b/arch/mips/rb532/Makefile
@@ -2,4 +2,6 @@
 # Makefile for the RB532 board specific parts of the kernel
 #
 
-obj-y	 += irq.o time.o setup.o serial.o prom.o gpio.o devices.o
+obj-$(CONFIG_SERIAL_8250_CONSOLE) += serial.o
+
+obj-y	 += irq.o time.o setup.o prom.o gpio.o devices.o
diff --git a/arch/mips/rb532/devices.c b/arch/mips/rb532/devices.c
index 32ea3e6731d6..354d258396ff 100644
--- a/arch/mips/rb532/devices.c
+++ b/arch/mips/rb532/devices.c
@@ -310,6 +310,8 @@ static int __init plat_setup_devices(void)
 	return platform_add_devices(rb532_devs, ARRAY_SIZE(rb532_devs));
 }
 
+#ifdef CONFIG_NET
+
 static int __init setup_kmac(char *s)
 {
 	printk(KERN_INFO "korina mac = %s\n", s);
@@ -322,4 +324,6 @@ static int __init setup_kmac(char *s)
 
 __setup("kmac=", setup_kmac);
 
+#endif /* CONFIG_NET */
+
 arch_initcall(plat_setup_devices);
diff --git a/arch/mn10300/configs/asb2364_defconfig b/arch/mn10300/configs/asb2364_defconfig
index b1d80cee97ee..a84c3153f22a 100644
--- a/arch/mn10300/configs/asb2364_defconfig
+++ b/arch/mn10300/configs/asb2364_defconfig
@@ -44,7 +44,6 @@ CONFIG_IPV6=y
 # CONFIG_INET6_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET6_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET6_XFRM_MODE_BEET is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_DEBUG=y
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index db5b57829a81..509c45a75d1f 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -1,6 +1,5 @@
 
 generic-y += barrier.h
-generic-y += clkdev.h
 generic-y += device.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h
index f5f90bbf019d..1748a7b25bf8 100644
--- a/arch/mn10300/include/asm/thread_info.h
+++ b/arch/mn10300/include/asm/thread_info.h
@@ -79,8 +79,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
 #define init_uregs							\
 	((struct pt_regs *)						\
 	 ((unsigned long) init_stack + THREAD_SIZE - sizeof(struct pt_regs)))
diff --git a/arch/mn10300/include/uapi/asm/Kbuild b/arch/mn10300/include/uapi/asm/Kbuild
index c94ee54210bc..b04fd1632051 100644
--- a/arch/mn10300/include/uapi/asm/Kbuild
+++ b/arch/mn10300/include/uapi/asm/Kbuild
@@ -1,4 +1,6 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y	+= bpf_perf_event.h
+generic-y	+= poll.h
 generic-y	+= siginfo.h
diff --git a/arch/mn10300/include/uapi/asm/poll.h b/arch/mn10300/include/uapi/asm/poll.h
deleted file mode 100644
index b7132a305a47..000000000000
--- a/arch/mn10300/include/uapi/asm/poll.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/poll.h>
diff --git a/arch/mn10300/kernel/mn10300-serial.c b/arch/mn10300/kernel/mn10300-serial.c
index d7ef1232a82a..4994b570dfd9 100644
--- a/arch/mn10300/kernel/mn10300-serial.c
+++ b/arch/mn10300/kernel/mn10300-serial.c
@@ -550,7 +550,7 @@ try_again:
 		return;
 	}
 
-	smp_read_barrier_depends();
+	/* READ_ONCE() enforces dependency, but dangerous through integer!!! */
 	ch = port->rx_buffer[ix++];
 	st = port->rx_buffer[ix++];
 	smp_mb();
@@ -1728,7 +1728,10 @@ static int mn10300_serial_poll_get_char(struct uart_port *_port)
 			if (CIRC_CNT(port->rx_inp, ix, MNSC_BUFFER_SIZE) == 0)
 				return NO_POLL_CHAR;
 
-			smp_read_barrier_depends();
+			/*
+			 * READ_ONCE() enforces dependency, but dangerous
+			 * through integer!!!
+			 */
 			ch = port->rx_buffer[ix++];
 			st = port->rx_buffer[ix++];
 			smp_mb();
diff --git a/arch/mn10300/kernel/traps.c b/arch/mn10300/kernel/traps.c
index 800fd0801969..72d1015b2ae7 100644
--- a/arch/mn10300/kernel/traps.c
+++ b/arch/mn10300/kernel/traps.c
@@ -22,7 +22,6 @@
 #include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
-#include <linux/kallsyms.h>
 #include <linux/pci.h>
 #include <linux/kdebug.h>
 #include <linux/bug.h>
@@ -262,8 +261,7 @@ void show_trace(unsigned long *sp)
 				raslot = ULONG_MAX;
 			else
 				printk(" ?");
-			print_symbol(" %s", addr);
-			printk("\n");
+			printk(" %pS\n", (void *)addr);
 		}
 	}
 
diff --git a/arch/mn10300/mm/dma-alloc.c b/arch/mn10300/mm/dma-alloc.c
index 86108d2496b3..e3910d4db102 100644
--- a/arch/mn10300/mm/dma-alloc.c
+++ b/arch/mn10300/mm/dma-alloc.c
@@ -37,9 +37,6 @@ static void *mn10300_dma_alloc(struct device *dev, size_t size,
 		goto done;
 	}
 
-	/* ignore region specifiers */
-	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
-
 	if (dev == NULL || dev->coherent_dma_mask < 0xffffffff)
 		gfp |= GFP_DMA;
 
diff --git a/arch/mn10300/mm/misalignment.c b/arch/mn10300/mm/misalignment.c
index b39a388825ae..8ace89617c1c 100644
--- a/arch/mn10300/mm/misalignment.c
+++ b/arch/mn10300/mm/misalignment.c
@@ -437,7 +437,7 @@ transfer_failed:
 
 	info.si_signo	= SIGSEGV;
 	info.si_errno	= 0;
-	info.si_code	= 0;
+	info.si_code	= SEGV_MAPERR;
 	info.si_addr	= (void *) regs->pc;
 	force_sig_info(SIGSEGV, &info, current);
 	return;
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index 896c26ae0da9..d232da2cbb38 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -3,7 +3,6 @@ generic-y += barrier.h
 generic-y += bitops.h
 generic-y += bug.h
 generic-y += bugs.h
-generic-y += clkdev.h
 generic-y += cmpxchg.h
 generic-y += current.h
 generic-y += device.h
diff --git a/arch/nios2/include/asm/thread_info.h b/arch/nios2/include/asm/thread_info.h
index d69c338bd19c..7349a4fa635b 100644
--- a/arch/nios2/include/asm/thread_info.h
+++ b/arch/nios2/include/asm/thread_info.h
@@ -63,9 +63,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* how to get the thread information struct from C */
 static inline struct thread_info *current_thread_info(void)
 {
diff --git a/arch/nios2/include/uapi/asm/Kbuild b/arch/nios2/include/uapi/asm/Kbuild
index ffca24da7647..13a3d77b4d7b 100644
--- a/arch/nios2/include/uapi/asm/Kbuild
+++ b/arch/nios2/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c
index 6688576b3a47..8d7446a4b475 100644
--- a/arch/nios2/kernel/prom.c
+++ b/arch/nios2/kernel/prom.c
@@ -42,11 +42,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 
 }
 
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return alloc_bootmem_align(size, align);
-}
-
 int __init early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
 					     bool nomap)
 {
diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
index 7040c1adbb5e..4be815519dd4 100644
--- a/arch/nios2/mm/dma-mapping.c
+++ b/arch/nios2/mm/dma-mapping.c
@@ -63,9 +63,6 @@ static void *nios2_dma_alloc(struct device *dev, size_t size,
 {
 	void *ret;
 
-	/* ignore region specifiers */
-	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
-
 	/* optimized page clearing */
 	gfp |= __GFP_ZERO;
 
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 6eb16719549e..f05c722a21f8 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -2,7 +2,6 @@ generic-y += barrier.h
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += checksum.h
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h
index 396d8f306c21..af31a9fe736a 100644
--- a/arch/openrisc/include/asm/processor.h
+++ b/arch/openrisc/include/asm/processor.h
@@ -84,8 +84,6 @@ void start_thread(struct pt_regs *regs, unsigned long nip, unsigned long sp);
 void release_thread(struct task_struct *);
 unsigned long get_wchan(struct task_struct *p);
 
-#define init_stack      (init_thread_union.stack)
-
 #define cpu_relax()     barrier()
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/openrisc/include/asm/thread_info.h b/arch/openrisc/include/asm/thread_info.h
index c229aa6bb502..5c15dfa2fd4f 100644
--- a/arch/openrisc/include/asm/thread_info.h
+++ b/arch/openrisc/include/asm/thread_info.h
@@ -79,8 +79,6 @@ struct thread_info {
 	.ksp            = 0,                            \
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-
 /* how to get the thread information struct from C */
 register struct thread_info *current_thread_info_reg asm("r10");
 #define current_thread_info()   (current_thread_info_reg)
diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild
index 62286dbeb904..130c16ccba0a 100644
--- a/arch/openrisc/include/uapi/asm/Kbuild
+++ b/arch/openrisc/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index 4085d72fa5ae..113c175fe469 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -39,8 +39,7 @@
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/unwinder.h>
-
-extern char _etext, _stext;
+#include <asm/sections.h>
 
 int kstack_depth_to_print = 0x180;
 int lwa_flag;
@@ -266,12 +265,12 @@ asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address)
 	siginfo_t info;
 
 	if (user_mode(regs)) {
-		/* Send a SIGSEGV */
-		info.si_signo = SIGSEGV;
+		/* Send a SIGBUS */
+		info.si_signo = SIGBUS;
 		info.si_errno = 0;
-		/* info.si_code has been set above */
-		info.si_addr = (void *)address;
-		force_sig_info(SIGSEGV, &info, current);
+		info.si_code = BUS_ADRALN;
+		info.si_addr = (void __user *)address;
+		force_sig_info(SIGBUS, &info, current);
 	} else {
 		printk("KERNEL: Unaligned Access 0x%.8lx\n", address);
 		show_registers(regs);
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index 00ddb7804be4..953bdcd54efe 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -28,6 +28,7 @@
 
 #include <asm/page.h>
 #include <asm/cache.h>
+#include <asm/thread_info.h>
 #include <asm-generic/vmlinux.lds.h>
 
 #ifdef __OR1K__
diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c
index 9345b44b86f0..f57118e1f6b4 100644
--- a/arch/parisc/boot/compressed/misc.c
+++ b/arch/parisc/boot/compressed/misc.c
@@ -123,8 +123,8 @@ int puts(const char *s)
 	while ((nuline = strchr(s, '\n')) != NULL) {
 		if (nuline != s)
 			pdc_iodc_print(s, nuline - s);
-			pdc_iodc_print("\r\n", 2);
-			s = nuline + 1;
+		pdc_iodc_print("\r\n", 2);
+		s = nuline + 1;
 	}
 	if (*s != '\0')
 		pdc_iodc_print(s, strlen(s));
diff --git a/arch/parisc/boot/compressed/vmlinux.lds.S b/arch/parisc/boot/compressed/vmlinux.lds.S
index a4ce3314e78e..4ebd4e65524c 100644
--- a/arch/parisc/boot/compressed/vmlinux.lds.S
+++ b/arch/parisc/boot/compressed/vmlinux.lds.S
@@ -29,7 +29,9 @@ SECTIONS
 	. = ALIGN(16);
 	/* Linkage tables */
 	.opd : {
+		__start_opd = .;
 		*(.opd)
+		__end_opd = .;
 	} PROVIDE (__gp = .);
 	.plt : {
 		*(.plt)
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index a41139575ab4..2013d639e735 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -1,5 +1,4 @@
 generic-y += barrier.h
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h
index acf8aa07cbe0..c22db5323244 100644
--- a/arch/parisc/include/asm/compat.h
+++ b/arch/parisc/include/asm/compat.h
@@ -130,70 +130,6 @@ typedef u32		compat_old_sigset_t;	/* at least 32 bits */
 
 typedef u32		compat_sigset_word;
 
-typedef union compat_sigval {
-	compat_int_t	sival_int;
-	compat_uptr_t	sival_ptr;
-} compat_sigval_t;
-
-typedef struct compat_siginfo {
-	int si_signo;
-	int si_errno;
-	int si_code;
-
-	union {
-		int _pad[128/sizeof(int) - 3];
-
-		/* kill() */
-		struct {
-			unsigned int _pid;      /* sender's pid */
-			unsigned int _uid;      /* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			compat_timer_t _tid;            /* timer id */
-			int _overrun;           /* overrun count */
-			char _pad[sizeof(unsigned int) - sizeof(int)];
-			compat_sigval_t _sigval;        /* same as below */
-			int _sys_private;       /* not to be passed to user */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			unsigned int _pid;      /* sender's pid */
-			unsigned int _uid;      /* sender's uid */
-			compat_sigval_t _sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			unsigned int _pid;      /* which child */
-			unsigned int _uid;      /* sender's uid */
-			int _status;            /* exit code */
-			compat_clock_t _utime;
-			compat_clock_t _stime;
-		} _sigchld;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
-		struct {
-			unsigned int _addr;     /* faulting insn/memory ref. */
-		} _sigfault;
-
-		/* SIGPOLL */
-		struct {
-			int _band;      /* POLL_IN, POLL_OUT, POLL_MSG */
-			int _fd;
-		} _sigpoll;
-
-		/* SIGSYS */
-		struct {
-			compat_uptr_t _call_addr; /* calling user insn */
-			int _syscall;	/* triggering system call number */
-			compat_uint_t _arch;	/* AUDIT_ARCH_* of syscall */
-		} _sigsys;
-	} _sifields;
-} compat_siginfo_t;
-
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
 struct compat_ipc64_perm {
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
index dd5a08aaa4da..3eb4bfc1fb36 100644
--- a/arch/parisc/include/asm/ldcw.h
+++ b/arch/parisc/include/asm/ldcw.h
@@ -12,6 +12,7 @@
    for the semaphore.  */
 
 #define __PA_LDCW_ALIGNMENT	16
+#define __PA_LDCW_ALIGN_ORDER	4
 #define __ldcw_align(a) ({					\
 	unsigned long __ret = (unsigned long) &(a)->lock[0];	\
 	__ret = (__ret + __PA_LDCW_ALIGNMENT - 1)		\
@@ -29,6 +30,7 @@
    ldcd). */
 
 #define __PA_LDCW_ALIGNMENT	4
+#define __PA_LDCW_ALIGN_ORDER	2
 #define __ldcw_align(a) (&(a)->slock)
 #define __LDCW	"ldcw,co"
 
diff --git a/arch/parisc/include/asm/sections.h b/arch/parisc/include/asm/sections.h
index accdf40aa5b7..5a40b51df80c 100644
--- a/arch/parisc/include/asm/sections.h
+++ b/arch/parisc/include/asm/sections.h
@@ -6,8 +6,14 @@
 #include <asm-generic/sections.h>
 
 #ifdef CONFIG_64BIT
+
+#define HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR 1
+
 #undef dereference_function_descriptor
 void *dereference_function_descriptor(void *);
+
+#undef dereference_kernel_function_descriptor
+void *dereference_kernel_function_descriptor(void *);
 #endif
 
 #endif
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index c980a02a52bc..285757544cca 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -25,9 +25,6 @@ struct thread_info {
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 }
 
-#define init_thread_info        (init_thread_union.thread_info)
-#define init_stack              (init_thread_union.stack)
-
 /* how to get the thread information struct from C */
 #define current_thread_info()	((struct thread_info *)mfctl(30))
 
@@ -35,7 +32,12 @@ struct thread_info {
 
 /* thread information allocation */
 
+#ifdef CONFIG_IRQSTACKS
+#define THREAD_SIZE_ORDER	2 /* PA-RISC requires at least 16k stack */
+#else
 #define THREAD_SIZE_ORDER	3 /* PA-RISC requires at least 32k stack */
+#endif
+
 /* Be sure to hunt all references to this down when you change the size of
  * the kernel stack */
 #define THREAD_SIZE             (PAGE_SIZE << THREAD_SIZE_ORDER)
diff --git a/arch/parisc/include/uapi/asm/Kbuild b/arch/parisc/include/uapi/asm/Kbuild
index 196d2a4efb31..286ef5a5904b 100644
--- a/arch/parisc/include/uapi/asm/Kbuild
+++ b/arch/parisc/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
+generic-y += bpf_perf_event.h
 generic-y += kvm_para.h
 generic-y += param.h
 generic-y += poll.h
diff --git a/arch/parisc/include/uapi/asm/siginfo.h b/arch/parisc/include/uapi/asm/siginfo.h
index 4a1062e05aaf..be40331f757d 100644
--- a/arch/parisc/include/uapi/asm/siginfo.h
+++ b/arch/parisc/include/uapi/asm/siginfo.h
@@ -8,4 +8,11 @@
 
 #include <asm-generic/siginfo.h>
 
+/*
+ * SIGFPE si_codes
+ */
+#ifdef __KERNEL__
+#define FPE_FIXME	0	/* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
 #endif
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index d8f77358e2ba..29b99b8964aa 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -870,7 +870,7 @@ static void print_parisc_device(struct parisc_device *dev)
 	static int count;
 
 	print_pa_hwpath(dev, hw_path);
-	printk(KERN_INFO "%d. %s at 0x%p [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
+	printk(KERN_INFO "%d. %s at 0x%px [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
 		++count, dev->name, (void*) dev->hpa.start, hw_path, dev->id.hw_type,
 		dev->id.hversion_rev, dev->id.hversion, dev->id.sversion);
 
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index a4fd296c958e..e95207c0565e 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -35,6 +35,7 @@
 #include <asm/pgtable.h>
 #include <asm/signal.h>
 #include <asm/unistd.h>
+#include <asm/ldcw.h>
 #include <asm/thread_info.h>
 
 #include <linux/linkage.h>
@@ -46,6 +47,14 @@
 #endif
 
 	.import		pa_tlb_lock,data
+	.macro  load_pa_tlb_lock reg
+#if __PA_LDCW_ALIGNMENT > 4
+	load32	PA(pa_tlb_lock) + __PA_LDCW_ALIGNMENT-1, \reg
+	depi	0,31,__PA_LDCW_ALIGN_ORDER, \reg
+#else
+	load32	PA(pa_tlb_lock), \reg
+#endif
+	.endm
 
 	/* space_to_prot macro creates a prot id from a space id */
 
@@ -457,7 +466,7 @@
 	.macro		tlb_lock	spc,ptp,pte,tmp,tmp1,fault
 #ifdef CONFIG_SMP
 	cmpib,COND(=),n	0,\spc,2f
-	load32		PA(pa_tlb_lock),\tmp
+	load_pa_tlb_lock \tmp
 1:	LDCW		0(\tmp),\tmp1
 	cmpib,COND(=)	0,\tmp1,1b
 	nop
@@ -480,7 +489,7 @@
 	/* Release pa_tlb_lock lock. */
 	.macro		tlb_unlock1	spc,tmp
 #ifdef CONFIG_SMP
-	load32		PA(pa_tlb_lock),\tmp
+	load_pa_tlb_lock \tmp
 	tlb_unlock0	\spc,\tmp
 #endif
 	.endm
@@ -878,9 +887,6 @@ ENTRY_CFI(syscall_exit_rfi)
 	STREG   %r19,PT_SR7(%r16)
 
 intr_return:
-	/* NOTE: Need to enable interrupts incase we schedule. */
-	ssm     PSW_SM_I, %r0
-
 	/* check for reschedule */
 	mfctl   %cr30,%r1
 	LDREG   TI_FLAGS(%r1),%r19	/* sched.h: TIF_NEED_RESCHED */
@@ -907,6 +913,11 @@ intr_check_sig:
 	LDREG	PT_IASQ1(%r16), %r20
 	cmpib,COND(=),n 0,%r20,intr_restore /* backward */
 
+	/* NOTE: We need to enable interrupts if we have to deliver
+	 * signals. We used to do this earlier but it caused kernel
+	 * stack overflows. */
+	ssm     PSW_SM_I, %r0
+
 	copy	%r0, %r25			/* long in_syscall = 0 */
 #ifdef CONFIG_64BIT
 	ldo	-16(%r30),%r29			/* Reference param save area */
@@ -958,6 +969,10 @@ intr_do_resched:
 	cmpib,COND(=)	0, %r20, intr_do_preempt
 	nop
 
+	/* NOTE: We need to enable interrupts if we schedule.  We used
+	 * to do this earlier but it caused kernel stack overflows. */
+	ssm     PSW_SM_I, %r0
+
 #ifdef CONFIG_64BIT
 	ldo	-16(%r30),%r29		/* Reference param save area */
 #endif
diff --git a/arch/parisc/kernel/hpmc.S b/arch/parisc/kernel/hpmc.S
index e3a8e5e4d5de..8d072c44f300 100644
--- a/arch/parisc/kernel/hpmc.S
+++ b/arch/parisc/kernel/hpmc.S
@@ -305,6 +305,7 @@ ENDPROC_CFI(os_hpmc)
 
 
 	__INITRODATA
+	.align 4
 	.export os_hpmc_size
 os_hpmc_size:
 	.word .os_hpmc_end-.os_hpmc
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index f1a76935a314..b5b3cb00f1fb 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -66,6 +66,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/unwind.h>
+#include <asm/sections.h>
 
 #if 0
 #define DEBUGP printk
@@ -954,3 +955,18 @@ void module_arch_cleanup(struct module *mod)
 {
 	deregister_unwind_table(mod);
 }
+
+#ifdef CONFIG_64BIT
+void *dereference_module_function_descriptor(struct module *mod, void *ptr)
+{
+	unsigned long start_opd = (Elf64_Addr)mod->core_layout.base +
+				   mod->arch.fdesc_offset;
+	unsigned long end_opd = start_opd +
+				mod->arch.fdesc_count * sizeof(Elf64_Fdesc);
+
+	if (ptr < (void *)start_opd || ptr >= (void *)end_opd)
+		return ptr;
+
+	return dereference_function_descriptor(ptr);
+}
+#endif
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index adf7187f8951..2d40c4ff3f69 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -36,6 +36,7 @@
 #include <asm/assembly.h>
 #include <asm/pgtable.h>
 #include <asm/cache.h>
+#include <asm/ldcw.h>
 #include <linux/linkage.h>
 
 	.text
@@ -333,8 +334,12 @@ ENDPROC_CFI(flush_data_cache_local)
 
 	.macro	tlb_lock	la,flags,tmp
 #ifdef CONFIG_SMP
-	ldil		L%pa_tlb_lock,%r1
-	ldo		R%pa_tlb_lock(%r1),\la
+#if __PA_LDCW_ALIGNMENT > 4
+	load32		pa_tlb_lock + __PA_LDCW_ALIGNMENT-1, \la
+	depi		0,31,__PA_LDCW_ALIGN_ORDER, \la
+#else
+	load32		pa_tlb_lock, \la
+#endif
 	rsm		PSW_SM_I,\flags
 1:	LDCW		0(\la),\tmp
 	cmpib,<>,n	0,\tmp,3f
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index c0dfd892f70c..91bc0cac03a1 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -75,11 +75,6 @@ void dump_resmap(void)
 static inline void dump_resmap(void) {;}
 #endif
 
-static int pa11_dma_supported( struct device *dev, u64 mask)
-{
-	return 1;
-}
-
 static inline int map_pte_uncached(pte_t * pte,
 		unsigned long vaddr,
 		unsigned long size, unsigned long *paddr_ptr)
@@ -579,7 +574,6 @@ static void pa11_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 }
 
 const struct dma_map_ops pcxl_dma_ops = {
-	.dma_supported =	pa11_dma_supported,
 	.alloc =		pa11_dma_alloc,
 	.free =			pa11_dma_free,
 	.map_page =		pa11_dma_map_page,
@@ -616,7 +610,6 @@ static void pcx_dma_free(struct device *dev, size_t size, void *vaddr,
 }
 
 const struct dma_map_ops pcx_dma_ops = {
-	.dma_supported =	pa11_dma_supported,
 	.alloc =		pcx_dma_alloc,
 	.free =			pcx_dma_free,
 	.map_page =		pa11_dma_map_page,
diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c
index e07eb34c8750..36434d4da381 100644
--- a/arch/parisc/kernel/pdt.c
+++ b/arch/parisc/kernel/pdt.c
@@ -325,7 +325,7 @@ static int pdt_mainloop(void *unused)
 #ifdef CONFIG_MEMORY_FAILURE
 			if ((pde & PDT_ADDR_PERM_ERR) ||
 			    ((pde & PDT_ADDR_SINGLE_ERR) == 0))
-				memory_failure(pde >> PAGE_SHIFT, 0, 0);
+				memory_failure(pde >> PAGE_SHIFT, 0);
 			else
 				soft_offline_page(
 					pfn_to_page(pde >> PAGE_SHIFT), 0);
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 30f92391a93e..6975a0627078 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -39,6 +39,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
+#include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/personality.h>
 #include <linux/ptrace.h>
@@ -184,6 +185,44 @@ int dump_task_fpu (struct task_struct *tsk, elf_fpregset_t *r)
 }
 
 /*
+ * Idle thread support
+ *
+ * Detect when running on QEMU with SeaBIOS PDC Firmware and let
+ * QEMU idle the host too.
+ */
+
+int running_on_qemu __read_mostly;
+
+void __cpuidle arch_cpu_idle_dead(void)
+{
+	/* nop on real hardware, qemu will offline CPU. */
+	asm volatile("or %%r31,%%r31,%%r31\n":::);
+}
+
+void __cpuidle arch_cpu_idle(void)
+{
+	local_irq_enable();
+
+	/* nop on real hardware, qemu will idle sleep. */
+	asm volatile("or %%r10,%%r10,%%r10\n":::);
+}
+
+static int __init parisc_idle_init(void)
+{
+	const char *marker;
+
+	/* check QEMU/SeaBIOS marker in PAGE0 */
+	marker = (char *) &PAGE0->pad0;
+	running_on_qemu = (memcmp(marker, "SeaBIOS", 8) == 0);
+
+	if (!running_on_qemu)
+		cpu_idle_poll_ctrl(1);
+
+	return 0;
+}
+arch_initcall(parisc_idle_init);
+
+/*
  * Copy architecture-specific thread state
  */
 int
@@ -276,6 +315,15 @@ void *dereference_function_descriptor(void *ptr)
 		ptr = p;
 	return ptr;
 }
+
+void *dereference_kernel_function_descriptor(void *ptr)
+{
+	if (ptr < (void *)__start_opd ||
+			ptr >= (void *)__end_opd)
+		return ptr;
+
+	return dereference_function_descriptor(ptr);
+}
 #endif
 
 static inline unsigned long brk_rnd(void)
diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c
index 41afa9cd1f55..e8ef3eb69449 100644
--- a/arch/parisc/kernel/signal32.c
+++ b/arch/parisc/kernel/signal32.c
@@ -260,109 +260,3 @@ setup_sigcontext32(struct compat_sigcontext __user *sc, struct compat_regfile __
 
 	return err;
 }
-
-int
-copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from)
-{
-	compat_uptr_t addr;
-	int err;
-
-	if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t)))
-		return -EFAULT;
-
-	err = __get_user(to->si_signo, &from->si_signo);
-	err |= __get_user(to->si_errno, &from->si_errno);
-	err |= __get_user(to->si_code, &from->si_code);
-
-	if (to->si_code < 0)
-		err |= __copy_from_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
-	else {
-		switch (siginfo_layout(to->si_signo, to->si_code)) {
-		      case SIL_CHLD:
-			err |= __get_user(to->si_utime, &from->si_utime);
-			err |= __get_user(to->si_stime, &from->si_stime);
-			err |= __get_user(to->si_status, &from->si_status);
-		      default:
-		      case SIL_KILL:
-			err |= __get_user(to->si_pid, &from->si_pid);
-			err |= __get_user(to->si_uid, &from->si_uid);
-			break;
-		      case SIL_FAULT:
-			err |= __get_user(addr, &from->si_addr);
-			to->si_addr = compat_ptr(addr);
-			break;
-		      case SIL_POLL:
-			err |= __get_user(to->si_band, &from->si_band);
-			err |= __get_user(to->si_fd, &from->si_fd);
-			break;
-		      case SIL_RT:
-			err |= __get_user(to->si_pid, &from->si_pid);
-			err |= __get_user(to->si_uid, &from->si_uid);
-			err |= __get_user(to->si_int, &from->si_int);
-			break;
-		}
-	}
-	return err;
-}
-
-int
-copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from)
-{
-	compat_uptr_t addr;
-	compat_int_t val;
-	int err;
-
-	if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
-		return -EFAULT;
-
-	/* If you change siginfo_t structure, please be sure
-	   this code is fixed accordingly.
-	   It should never copy any pad contained in the structure
-	   to avoid security leaks, but must copy the generic
-	   3 ints plus the relevant union member.
-	   This routine must convert siginfo from 64bit to 32bit as well
-	   at the same time.  */
-	err = __put_user(from->si_signo, &to->si_signo);
-	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user(from->si_code, &to->si_code);
-	if (from->si_code < 0)
-		err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
-	else {
-		switch (siginfo_layout(from->si_signo, from->si_code)) {
-		case SIL_CHLD:
-			err |= __put_user(from->si_utime, &to->si_utime);
-			err |= __put_user(from->si_stime, &to->si_stime);
-			err |= __put_user(from->si_status, &to->si_status);
-		case SIL_KILL:
-			err |= __put_user(from->si_pid, &to->si_pid);
-			err |= __put_user(from->si_uid, &to->si_uid);
-			break;
-		case SIL_FAULT:
-			addr = ptr_to_compat(from->si_addr);
-			err |= __put_user(addr, &to->si_addr);
-			break;
-		case SIL_POLL:
-			err |= __put_user(from->si_band, &to->si_band);
-			err |= __put_user(from->si_fd, &to->si_fd);
-			break;
-		case SIL_TIMER:
-			err |= __put_user(from->si_tid, &to->si_tid);
-			err |= __put_user(from->si_overrun, &to->si_overrun);
-			val = (compat_int_t)from->si_int;
-			err |= __put_user(val, &to->si_int);
-			break;
-		case SIL_RT:
-			err |= __put_user(from->si_uid, &to->si_uid);
-			err |= __put_user(from->si_pid, &to->si_pid);
-			val = (compat_int_t)from->si_int;
-			err |= __put_user(val, &to->si_int);
-			break;
-		case SIL_SYS:
-			err |= __put_user(ptr_to_compat(from->si_call_addr), &to->si_call_addr);
-			err |= __put_user(from->si_syscall, &to->si_syscall);
-			err |= __put_user(from->si_arch, &to->si_arch);
-			break;
-		}
-	}
-	return err;
-}
diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h
index 719e7417732c..a271dc0976ce 100644
--- a/arch/parisc/kernel/signal32.h
+++ b/arch/parisc/kernel/signal32.h
@@ -34,9 +34,6 @@ struct compat_ucontext {
 
 /* ELF32 signal handling */
 
-int copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from);
-int copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from);
-
 /* In a deft move of uber-hackery, we decide to carry the top half of all
  * 64-bit registers in a non-portable, non-ABI, hidden structure.
  * Userspace can read the hidden structure if it *wants* but is never
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 8453724b8009..c919e6c0a687 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -629,7 +629,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 			si.si_signo = SIGFPE;
 			/* Set to zero, and let the userspace app figure it out from
 			   the insn pointed to by si_addr */
-			si.si_code = 0;
+			si.si_code = FPE_FIXME;
 			si.si_addr = (void __user *) regs->iaoq[0];
 			force_sig_info(SIGFPE, &si, current);
 			return;
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index 5a657986ebbf..143f90e2f9f3 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -15,7 +15,6 @@
 #include <linux/slab.h>
 #include <linux/kallsyms.h>
 #include <linux/sort.h>
-#include <linux/sched.h>
 
 #include <linux/uaccess.h>
 #include <asm/assembly.h>
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 159a2ec0b4e0..da2e31190efa 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -100,7 +100,9 @@ SECTIONS
 	. = ALIGN(16);
 	/* Linkage tables */
 	.opd : {
+		__start_opd = .;
 		*(.opd)
+		__end_opd = .;
 	} PROVIDE (__gp = .);
 	.plt : {
 		*(.plt)
diff --git a/arch/parisc/lib/delay.c b/arch/parisc/lib/delay.c
index 7eab4bb8abe6..66e506520505 100644
--- a/arch/parisc/lib/delay.c
+++ b/arch/parisc/lib/delay.c
@@ -16,9 +16,7 @@
 #include <linux/preempt.h>
 #include <linux/init.h>
 
-#include <asm/processor.h>
 #include <asm/delay.h>
-
 #include <asm/special_insns.h>    /* for mfctl() */
 #include <asm/processor.h> /* for boot_cpu_data */
 
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 13f7854e0d49..48f41399fc0b 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -631,11 +631,11 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 #ifdef CONFIG_DEBUG_KERNEL /* double-sanity-check paranoia */
 	printk("virtual kernel memory layout:\n"
-	       "    vmalloc : 0x%p - 0x%p   (%4ld MB)\n"
-	       "    memory  : 0x%p - 0x%p   (%4ld MB)\n"
-	       "      .init : 0x%p - 0x%p   (%4ld kB)\n"
-	       "      .data : 0x%p - 0x%p   (%4ld kB)\n"
-	       "      .text : 0x%p - 0x%p   (%4ld kB)\n",
+	       "    vmalloc : 0x%px - 0x%px   (%4ld MB)\n"
+	       "    memory  : 0x%px - 0x%px   (%4ld MB)\n"
+	       "      .init : 0x%px - 0x%px   (%4ld kB)\n"
+	       "      .data : 0x%px - 0x%px   (%4ld kB)\n"
+	       "      .text : 0x%px - 0x%px   (%4ld kB)\n",
 
 	       (void*)VMALLOC_START, (void*)VMALLOC_END,
 	       (VMALLOC_END - VMALLOC_START) >> 20,
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c51e6ce42e7a..9d3329811cc1 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -139,9 +139,11 @@ config PPC
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API                if PPC64
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE
 	select ARCH_HAS_SG_CHAIN
+	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if PPC64
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
@@ -149,8 +151,8 @@ config PPC
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_OPTIONAL_KERNEL_RWX		if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -166,6 +168,7 @@ config PPC
 	select GENERIC_CLOCKEVENTS_BROADCAST	if SMP
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_VULNERABILITIES	if PPC_BOOK3S_64
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_SMP_IDLE_THREAD
@@ -179,8 +182,6 @@ config PPC
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if COMPAT
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
-	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)
-	select ARCH_OPTIONAL_KERNEL_RWX		if ARCH_HAS_STRICT_KERNEL_RWX
 	select HAVE_CBPF_JIT			if !PPC64
 	select HAVE_CONTEXT_TRACKING		if PPC64
 	select HAVE_DEBUG_KMEMLEAK
@@ -867,6 +868,21 @@ config SECCOMP
 
 	  If unsure, say Y. Only embedded should say N here.
 
+config PPC_MEM_KEYS
+	prompt "PowerPC Memory Protection Keys"
+	def_bool y
+	depends on PPC_BOOK3S_64
+	select ARCH_USES_HIGH_VMA_FLAGS
+	select ARCH_HAS_PKEYS
+	help
+	  Memory Protection Keys provides a mechanism for enforcing
+	  page-based protections, but without requiring modification of the
+	  page tables when an application changes protection domains.
+
+	  For details, see Documentation/vm/protection-keys.txt
+
+	  If unsure, say y.
+
 endmenu
 
 config ISA_DMA_API
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 657c33cd4eee..c45424c64e19 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -90,6 +90,10 @@ config MSI_BITMAP_SELFTEST
 	depends on DEBUG_KERNEL
 	default n
 
+config PPC_IRQ_SOFT_MASK_DEBUG
+	bool "Include extra checks for powerpc irq soft masking"
+	default n
+
 config XMON
 	bool "Include xmon kernel debugger"
 	depends on DEBUG_KERNEL
@@ -368,7 +372,7 @@ config PPC_PTDUMP
 
 config PPC_HTDUMP
 	def_bool y
-	depends on PPC_PTDUMP && PPC_BOOK3S
+	depends on PPC_PTDUMP && PPC_BOOK3S_64
 
 config PPC_FAST_ENDIAN_SWITCH
 	bool "Deprecated fast endian-switch syscall"
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 1381693a4a51..ccd2556bdb53 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -63,6 +63,7 @@ UTS_MACHINE := $(subst $(space),,$(machine-y))
 ifdef CONFIG_PPC32
 KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
 else
+KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/powerpc/kernel/module.lds
 ifeq ($(call ld-ifversion, -ge, 225000000, y),y)
 # Have the linker provide sfpr if possible.
 # There is a corresponding test in arch/powerpc/lib/Makefile
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 08782f55b89f..ef6549e57157 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -108,10 +108,10 @@ src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \
 		$(libfdt) libfdt-wrapper.c \
 		ns16550.c serial.c simple_alloc.c div64.S util.S \
 		elf_util.c $(zlib-y) devtree.c stdlib.c \
-		oflib.c ofconsole.c cuboot.c cpm-serial.c \
-		uartlite.c opal.c
+		oflib.c ofconsole.c cuboot.c
+
 src-wlib-$(CONFIG_PPC_MPC52XX) += mpc52xx-psc.c
-src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) +=  opal-calls.S
+src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S opal.c
 ifndef CONFIG_PPC64_BOOT_WRAPPER
 src-wlib-y += crtsavres.S
 endif
@@ -120,6 +120,8 @@ src-wlib-$(CONFIG_44x) += 4xx.c ebony.c bamboo.c
 src-wlib-$(CONFIG_PPC_8xx) += mpc8xx.c planetcore.c fsl-soc.c
 src-wlib-$(CONFIG_PPC_82xx) += pq2.c fsl-soc.c planetcore.c
 src-wlib-$(CONFIG_EMBEDDED6xx) += mpsc.c mv64x60.c mv64x60_i2c.c ugecon.c fsl-soc.c
+src-wlib-$(CONFIG_XILINX_VIRTEX) += uartlite.c
+src-wlib-$(CONFIG_CPM) += cpm-serial.c
 
 src-plat-y := of.c epapr.c
 src-plat-$(CONFIG_40x) += fixed-head.S ep405.c cuboot-hotfoot.c \
diff --git a/arch/powerpc/boot/dts/a3m071.dts b/arch/powerpc/boot/dts/a3m071.dts
index bf81b8f9704c..187ce458d03a 100644
--- a/arch/powerpc/boot/dts/a3m071.dts
+++ b/arch/powerpc/boot/dts/a3m071.dts
@@ -105,24 +105,24 @@
 			reg = <0 0x0 0x02000000>;
 			compatible = "cfi-flash";
 			bank-width = <2>;
-			partition@0x0 {
+			partition@0 {
 				label = "u-boot";
 				reg = <0x00000000 0x00040000>;
 				read-only;
 			};
-			partition@0x00040000 {
+			partition@40000 {
 				label = "env";
 				reg = <0x00040000 0x00020000>;
 			};
-			partition@0x00060000 {
+			partition@60000 {
 				label = "dtb";
 				reg = <0x00060000 0x00020000>;
 			};
-			partition@0x00080000 {
+			partition@80000 {
 				label = "kernel";
 				reg = <0x00080000 0x00500000>;
 			};
-			partition@0x00580000 {
+			partition@580000 {
 				label = "root";
 				reg = <0x00580000 0x00A80000>;
 			};
diff --git a/arch/powerpc/boot/dts/akebono.dts b/arch/powerpc/boot/dts/akebono.dts
index e61d5dc598c1..746779202a12 100644
--- a/arch/powerpc/boot/dts/akebono.dts
+++ b/arch/powerpc/boot/dts/akebono.dts
@@ -216,7 +216,7 @@
 				interrupts = <39 2>;
 			};
 
-			IIC0: i2c@00000000 {
+			IIC0: i2c@0 {
 				compatible = "ibm,iic-476gtr", "ibm,iic";
 				reg = <0x0 0x00000020>;
 				interrupt-parent = <&MPIC>;
@@ -229,7 +229,7 @@
 				};
 			};
 
-			IIC1: i2c@00000100 {
+			IIC1: i2c@100 {
 				compatible = "ibm,iic-476gtr", "ibm,iic";
 				reg = <0x100 0x00000020>;
 				interrupt-parent = <&MPIC>;
diff --git a/arch/powerpc/boot/dts/c2k.dts b/arch/powerpc/boot/dts/c2k.dts
index 1e32903cb0a8..27f169e3ade9 100644
--- a/arch/powerpc/boot/dts/c2k.dts
+++ b/arch/powerpc/boot/dts/c2k.dts
@@ -276,14 +276,14 @@
 			>;
 		};
 
-		cpu-error@0070 {
+		cpu-error@70 {
 			compatible = "marvell,mv64360-cpu-error";
 			reg = <0x0070 0x10 0x0128 0x28>;
 			interrupts = <3>;
 			interrupt-parent = <&PIC>;
 		};
 
-		sram-ctrl@0380 {
+		sram-ctrl@380 {
 			compatible = "marvell,mv64360-sram-ctrl";
 			reg = <0x0380 0x80>;
 			interrupts = <13>;
@@ -311,7 +311,7 @@
 			interrupt-parent = <&PIC>;
 		};
 		/* Devices attached to the device controller */
-		devicebus@045c {
+		devicebus@45c {
 			#address-cells = <2>;
 			#size-cells = <1>;
 			compatible = "marvell,mv64306-devctrl";
diff --git a/arch/powerpc/boot/dts/currituck.dts b/arch/powerpc/boot/dts/currituck.dts
index 4191e1850ea1..f2ad5815f08d 100644
--- a/arch/powerpc/boot/dts/currituck.dts
+++ b/arch/powerpc/boot/dts/currituck.dts
@@ -108,7 +108,7 @@
 				reg = <0x50000000 0x4>;
 			};
 
-			IIC0: i2c@00000000 {
+			IIC0: i2c@0 {
 				compatible = "ibm,iic-currituck", "ibm,iic";
 				reg = <0x0 0x00000014>;
 				interrupt-parent = <&MPIC>;
diff --git a/arch/powerpc/boot/dts/fsl/mpc8568mds.dts b/arch/powerpc/boot/dts/fsl/mpc8568mds.dts
index 01706a339603..bc3e8039bdc7 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8568mds.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8568mds.dts
@@ -126,7 +126,7 @@
 		par_io@e0100 {
 			num-ports = <7>;
 
-			pio1: ucc_pin@01 {
+			pio1: ucc_pin@1 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					0x4  0xa  0x1  0x0  0x2  0x0 	/* TxD0 */
@@ -154,7 +154,7 @@
 					0x1  0x1f  0x2  0x0  0x3  0x0>;	/* GTX125 */
 			};
 
-			pio2: ucc_pin@02 {
+			pio2: ucc_pin@2 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					0x5  0xa 0x1  0x0  0x2  0x0   /* TxD0 */
@@ -228,22 +228,22 @@
 
 			/* These are the same PHYs as on
 			 * gianfar's MDIO bus */
-			qe_phy0: ethernet-phy@07 {
+			qe_phy0: ethernet-phy@7 {
 				interrupt-parent = <&mpic>;
 				interrupts = <1 1 0 0>;
 				reg = <0x7>;
 			};
-			qe_phy1: ethernet-phy@01 {
+			qe_phy1: ethernet-phy@1 {
 				interrupt-parent = <&mpic>;
 				interrupts = <2 1 0 0>;
 				reg = <0x1>;
 			};
-			qe_phy2: ethernet-phy@02 {
+			qe_phy2: ethernet-phy@2 {
 				interrupt-parent = <&mpic>;
 				interrupts = <1 1 0 0>;
 				reg = <0x2>;
 			};
-			qe_phy3: ethernet-phy@03 {
+			qe_phy3: ethernet-phy@3 {
 				interrupt-parent = <&mpic>;
 				interrupts = <2 1 0 0>;
 				reg = <0x3>;
diff --git a/arch/powerpc/boot/dts/fsl/mpc8569mds.dts b/arch/powerpc/boot/dts/fsl/mpc8569mds.dts
index 76b2bd6f7742..d8367ceddea6 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8569mds.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8569mds.dts
@@ -141,7 +141,7 @@
 				gpio-controller;
 			};
 
-			pio1: ucc_pin@01 {
+			pio1: ucc_pin@1 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					0x2  0x1f 0x1  0x0  0x1  0x0	/* QE_MUX_MDC */
@@ -161,7 +161,7 @@
 					0x2  0x14 0x1  0x0  0x2  0x0>;	/* ENET1_GTXCLK	*/
 			};
 
-			pio2: ucc_pin@02 {
+			pio2: ucc_pin@2 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					0x2  0x1f 0x1  0x0  0x1  0x0	/* QE_MUX_MDC */
@@ -181,7 +181,7 @@
 					0x2  0x2 0x1  0x0  0x2  0x0>;	/* ENET2_GTXCLK	*/
 			};
 
-			pio3: ucc_pin@03 {
+			pio3: ucc_pin@3 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					0x2  0x1f 0x1  0x0  0x1  0x0	/* QE_MUX_MDC */
@@ -201,7 +201,7 @@
 					0x2  0x19 0x1  0x0  0x2  0x0>;	/* ENET3_GTXCLK	*/
 			};
 
-			pio4: ucc_pin@04 {
+			pio4: ucc_pin@4 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					0x2  0x1f 0x1  0x0  0x1  0x0	/* QE_MUX_MDC */
@@ -272,30 +272,30 @@
 			reg = <0x2120 0x18>;
 			compatible = "fsl,ucc-mdio";
 
-			qe_phy0: ethernet-phy@07 {
+			qe_phy0: ethernet-phy@7 {
 				interrupt-parent = <&mpic>;
 				interrupts = <1 1 0 0>;
 				reg = <0x7>;
 			};
-			qe_phy1: ethernet-phy@01 {
+			qe_phy1: ethernet-phy@1 {
 				interrupt-parent = <&mpic>;
 				interrupts = <2 1 0 0>;
 				reg = <0x1>;
 			};
-			qe_phy2: ethernet-phy@02 {
+			qe_phy2: ethernet-phy@2 {
 				interrupt-parent = <&mpic>;
 				interrupts = <3 1 0 0>;
 				reg = <0x2>;
 			};
-			qe_phy3: ethernet-phy@03 {
+			qe_phy3: ethernet-phy@3 {
 				interrupt-parent = <&mpic>;
 				interrupts = <4 1 0 0>;
 				reg = <0x3>;
 			};
-			qe_phy5: ethernet-phy@04 {
+			qe_phy5: ethernet-phy@4 {
 				reg = <0x04>;
 			};
-			qe_phy7: ethernet-phy@06 {
+			qe_phy7: ethernet-phy@6 {
 				reg = <0x6>;
 			};
 			tbi1: tbi-phy@11 {
diff --git a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
index af12ead88c5f..1b4aafc1f6a2 100644
--- a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
@@ -137,12 +137,14 @@
 		compatible = "fsl,p1010-flexcan";
 		reg = <0x1c000 0x1000>;
 		interrupts = <48 0x2 0 0>;
+		big-endian;
 	};
 
 	can1: can@1d000 {
 		compatible = "fsl,p1010-flexcan";
 		reg = <0x1d000 0x1000>;
 		interrupts = <61 0x2 0 0>;
+		big-endian;
 	};
 
 	L2: l2-cache-controller@20000 {
diff --git a/arch/powerpc/boot/dts/fsl/p1021mds.dts b/arch/powerpc/boot/dts/fsl/p1021mds.dts
index 291454c75dda..1047802f4d2a 100644
--- a/arch/powerpc/boot/dts/fsl/p1021mds.dts
+++ b/arch/powerpc/boot/dts/fsl/p1021mds.dts
@@ -202,7 +202,7 @@
 			ranges = <0x0 0xe0100 0x60>;
 			device_type = "par_io";
 			num-ports = <3>;
-			pio1: ucc_pin@01 {
+			pio1: ucc_pin@1 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					0x1  0x13 0x1  0x0  0x1  0x0    /* QE_MUX_MDC */
@@ -225,7 +225,7 @@
 					0x0  0x10 0x2  0x0  0x2  0x0>;    /* ENET1_COL */
 			};
 
-			pio2: ucc_pin@02 {
+			pio2: ucc_pin@2 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					0x1  0x13 0x1  0x0  0x1  0x0    /* QE_MUX_MDC */
@@ -296,7 +296,7 @@
 				interrupts = <4 1 0 0>;
 				reg = <0x0>;
 			};
-			qe_phy1: ethernet-phy@03 {
+			qe_phy1: ethernet-phy@3 {
 				interrupt-parent = <&mpic>;
 				interrupts = <5 1 0 0>;
 				reg = <0x3>;
diff --git a/arch/powerpc/boot/dts/fsl/p1025rdb.dtsi b/arch/powerpc/boot/dts/fsl/p1025rdb.dtsi
index d44bb12debb0..0a5434a631c3 100644
--- a/arch/powerpc/boot/dts/fsl/p1025rdb.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1025rdb.dtsi
@@ -245,7 +245,7 @@
 		ranges = <0x0 0xe0100 0x60>;
 		device_type = "par_io";
 		num-ports = <3>;
-		pio1: ucc_pin@01 {
+		pio1: ucc_pin@1 {
 			pio-map = <
 		/* port  pin  dir  open_drain  assignment  has_irq */
 				0x1  0x13 0x1  0x0  0x1  0x0    /* QE_MUX_MDC */
@@ -268,7 +268,7 @@
 				0x0  0x10 0x2  0x0  0x2  0x0>;    /* ENET1_COL */
 		};
 
-		pio2: ucc_pin@02 {
+		pio2: ucc_pin@2 {
 			pio-map = <
 		/* port  pin  dir  open_drain  assignment  has_irq */
 				0x1  0x13 0x1  0x0  0x1  0x0    /* QE_MUX_MDC */
@@ -283,7 +283,7 @@
 				0x1  0x8  0x2  0x0  0x2  0x0>;    /* ENET5_RX_ER_SER5_CD_B */
 		};
 
-		pio3: ucc_pin@03 {
+		pio3: ucc_pin@3 {
 			pio-map = <
 		/* port  pin  dir  open_drain  assignment  has_irq */
 				0x0  0x16 0x2  0x0  0x2  0x0    /* SER7_CD_B*/
@@ -293,7 +293,7 @@
 				0x0  0x15 0x1  0x0  0x2  0x0>;    /* SER7_TXD0*/
 		};
 
-		pio4: ucc_pin@04 {
+		pio4: ucc_pin@4 {
 			pio-map = <
 		/* port  pin  dir  open_drain  assignment  has_irq */
 				0x1  0x0  0x2  0x0  0x2  0x0    /* SER3_CD_B*/
diff --git a/arch/powerpc/boot/dts/fsl/p1025rdb_32b.dts b/arch/powerpc/boot/dts/fsl/p1025rdb_32b.dts
index b15acbaea34b..ea33b57f8774 100644
--- a/arch/powerpc/boot/dts/fsl/p1025rdb_32b.dts
+++ b/arch/powerpc/boot/dts/fsl/p1025rdb_32b.dts
@@ -106,7 +106,7 @@
 				interrupts = <4 1 0 0>;
 				reg = <0x6>;
 			};
-			qe_phy1: ethernet-phy@03 {
+			qe_phy1: ethernet-phy@3 {
 				interrupt-parent = <&mpic>;
 				interrupts = <5 1 0 0>;
 				reg = <0x3>;
diff --git a/arch/powerpc/boot/dts/fsl/p1025twr.dtsi b/arch/powerpc/boot/dts/fsl/p1025twr.dtsi
index 08816fb474f5..ab75b8f29ae2 100644
--- a/arch/powerpc/boot/dts/fsl/p1025twr.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1025twr.dtsi
@@ -172,7 +172,7 @@
 		ranges = <0x0 0xe0100 0x60>;
 		device_type = "par_io";
 		num-ports = <3>;
-		pio1: ucc_pin@01 {
+		pio1: ucc_pin@1 {
 			pio-map = <
 		/* port  pin  dir  open_drain  assignment  has_irq */
 				0x1  0x13 0x1  0x0  0x1  0x0    /* QE_MUX_MDC */
@@ -195,7 +195,7 @@
 				0x0  0x10 0x2  0x0  0x2  0x0>;    /* ENET1_COL */
 		};
 
-		pio2: ucc_pin@02 {
+		pio2: ucc_pin@2 {
 			pio-map = <
 		/* port  pin  dir  open_drain  assignment  has_irq */
 				0x1  0x13 0x1  0x0  0x1  0x0    /* QE_MUX_MDC */
@@ -210,7 +210,7 @@
 				0x1  0x8  0x2  0x0  0x2  0x0>;    /* ENET5_RX_ER_SER5_CD_B */
 		};
 
-		pio3: ucc_pin@03 {
+		pio3: ucc_pin@3 {
 			pio-map = <
 		/* port  pin  dir  open_drain  assignment  has_irq */
 				0x0  0x16 0x2  0x0  0x2  0x0    /* SER7_CD_B*/
@@ -220,7 +220,7 @@
 				0x0  0x15 0x1  0x0  0x2  0x0>;    /* SER7_TXD0*/
 		};
 
-		pio4: ucc_pin@04 {
+		pio4: ucc_pin@4 {
 			pio-map = <
 		/* port  pin  dir  open_drain  assignment  has_irq */
 				0x1  0x0  0x2  0x0  0x2  0x0    /* SER3_CD_B*/
diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb.dts b/arch/powerpc/boot/dts/fsl/t1040rdb.dts
index 621f2c6ee6ad..65ff34c49025 100644
--- a/arch/powerpc/boot/dts/fsl/t1040rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1040rdb.dts
@@ -61,7 +61,7 @@
 			};
 
 			mdio@fc000 {
-				phy_sgmii_2: ethernet-phy@03 {
+				phy_sgmii_2: ethernet-phy@3 {
 					reg = <0x03>;
 				};
 			};
diff --git a/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts b/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts
index fcd2aeb5b8ac..4fa15f48a4c3 100644
--- a/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts
@@ -77,23 +77,23 @@
 			};
 
 			mdio0: mdio@fc000 {
-				phy_sgmii_0: ethernet-phy@02 {
+				phy_sgmii_0: ethernet-phy@2 {
 					reg = <0x02>;
 				};
 
-				phy_sgmii_1: ethernet-phy@03 {
+				phy_sgmii_1: ethernet-phy@3 {
 					reg = <0x03>;
 				};
 
-				phy_sgmii_2: ethernet-phy@01 {
+				phy_sgmii_2: ethernet-phy@1 {
 					reg = <0x01>;
 				};
 
-				phy_rgmii_0: ethernet-phy@04 {
+				phy_rgmii_0: ethernet-phy@4 {
 					reg = <0x04>;
 				};
 
-				phy_rgmii_1: ethernet-phy@05 {
+				phy_rgmii_1: ethernet-phy@5 {
 					reg = <0x05>;
 				};
 			};
diff --git a/arch/powerpc/boot/dts/fsl/t1042rdb.dts b/arch/powerpc/boot/dts/fsl/t1042rdb.dts
index 2c138627b1b4..3ebb712224cb 100644
--- a/arch/powerpc/boot/dts/fsl/t1042rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1042rdb.dts
@@ -59,7 +59,7 @@
 			};
 
 			mdio@fc000 {
-				phy_sgmii_2: ethernet-phy@03 {
+				phy_sgmii_2: ethernet-phy@3 {
 					reg = <0x03>;
 				};
 			};
diff --git a/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi b/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
index 5fdddbd2a62b..099a598c74c0 100644
--- a/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
@@ -148,15 +148,15 @@
 			};
 
 			mdio0: mdio@fc000 {
-				phy_sgmii_2: ethernet-phy@03 {
+				phy_sgmii_2: ethernet-phy@3 {
 					reg = <0x03>;
 				};
 
-				phy_rgmii_0: ethernet-phy@01 {
+				phy_rgmii_0: ethernet-phy@1 {
 					reg = <0x01>;
 				};
 
-				phy_rgmii_1: ethernet-phy@02 {
+				phy_rgmii_1: ethernet-phy@2 {
 					reg = <0x02>;
 				};
 			};
diff --git a/arch/powerpc/boot/dts/fsp2.dts b/arch/powerpc/boot/dts/fsp2.dts
index f10a64aeb83b..6560283c5aec 100644
--- a/arch/powerpc/boot/dts/fsp2.dts
+++ b/arch/powerpc/boot/dts/fsp2.dts
@@ -583,21 +583,21 @@
 			};
 		};
 
-		OHCI1: ohci@02040000 {
+		OHCI1: ohci@2040000 {
 			compatible = "ohci-le";
 			reg = <0x02040000 0xa0>;
 			interrupt-parent = <&UIC1_3>;
 			interrupts = <28 0x8 29 0x8>;
 		};
 
-		OHCI2: ohci@02080000 {
+		OHCI2: ohci@2080000 {
 			compatible = "ohci-le";
 			reg = <0x02080000 0xa0>;
 			interrupt-parent = <&UIC1_3>;
 			interrupts = <30 0x8 31 0x8>;
 		};
 
-		EHCI: ehci@02000000 {
+		EHCI: ehci@2000000 {
 			compatible = "usb-ehci";
 			reg = <0x02000000 0xa4>;
 			interrupt-parent = <&UIC1_3>;
diff --git a/arch/powerpc/boot/dts/gamecube.dts b/arch/powerpc/boot/dts/gamecube.dts
index ef3be0e58b02..58d06c9ee08b 100644
--- a/arch/powerpc/boot/dts/gamecube.dts
+++ b/arch/powerpc/boot/dts/gamecube.dts
@@ -54,13 +54,13 @@
 		ranges = <0x0c000000 0x0c000000 0x00010000>;
 		interrupt-parent = <&PIC>;
 
-		video@0c002000 {
+		video@c002000 {
 			compatible = "nintendo,flipper-vi";
 			reg = <0x0c002000 0x100>;
 			interrupts = <8>;
 		};
 
-		processor-interface@0c003000 {
+		processor-interface@c003000 {
 			compatible = "nintendo,flipper-pi";
 			reg = <0x0c003000 0x100>;
 
@@ -71,7 +71,7 @@
 			};
 		};
 
-		dsp@0c005000 {
+		dsp@c005000 {
 			#address-cells = <1>;
 			#size-cells = <1>;
 			compatible = "nintendo,flipper-dsp";
@@ -84,26 +84,26 @@
 			};
 		};
 
-		disk@0c006000 {
+		disk@c006000 {
 			compatible = "nintendo,flipper-di";
 			reg = <0x0c006000 0x40>;
 			interrupts = <2>;
 		};
 
-		audio@0c006c00 {
+		audio@c006c00 {
 			compatible = "nintendo,flipper-ai";
 			reg = <0x0c006c00 0x20>;
 			interrupts = <6>;
 		};
 
-		gamepad-controller@0c006400 {
+		gamepad-controller@c006400 {
 			compatible = "nintendo,flipper-si";
 			reg = <0x0c006400 0x100>;
 			interrupts = <3>;
 		};
 
 		/* External Interface bus */
-		exi@0c006800 {
+		exi@c006800 {
 			compatible = "nintendo,flipper-exi";
 			reg = <0x0c006800 0x40>;
 			virtual-reg = <0x0c006800>;
diff --git a/arch/powerpc/boot/dts/haleakala.dts b/arch/powerpc/boot/dts/haleakala.dts
index 2b256694eca6..cb16dad43c92 100644
--- a/arch/powerpc/boot/dts/haleakala.dts
+++ b/arch/powerpc/boot/dts/haleakala.dts
@@ -237,7 +237,7 @@
 			};
 		};
 
-		PCIE0: pciex@0a0000000 {
+		PCIE0: pciex@a0000000 {
 			device_type = "pci";
 			#interrupt-cells = <1>;
 			#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/kilauea.dts b/arch/powerpc/boot/dts/kilauea.dts
index 5ba7f01e2a29..2a3413221cc1 100644
--- a/arch/powerpc/boot/dts/kilauea.dts
+++ b/arch/powerpc/boot/dts/kilauea.dts
@@ -322,7 +322,7 @@
 			};
 		};
 
-		PCIE0: pciex@0a0000000 {
+		PCIE0: pciex@a0000000 {
 			device_type = "pci";
 			#interrupt-cells = <1>;
 			#size-cells = <2>;
@@ -363,7 +363,7 @@
 				0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>;
 		};
 
-		PCIE1: pciex@0c0000000 {
+		PCIE1: pciex@c0000000 {
 			device_type = "pci";
 			#interrupt-cells = <1>;
 			#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/kmeter1.dts b/arch/powerpc/boot/dts/kmeter1.dts
index 983aee185793..9fa33d9ba966 100644
--- a/arch/powerpc/boot/dts/kmeter1.dts
+++ b/arch/powerpc/boot/dts/kmeter1.dts
@@ -434,27 +434,27 @@
 				compatible = "fsl,ucc-mdio";
 
 				/* Piggy2 (UCC4, MDIO 0x00, RMII) */
-				phy_piggy2: ethernet-phy@00 {
+				phy_piggy2: ethernet-phy@0 {
 					reg = <0x0>;
 				};
 
 				/* Eth-1 (UCC5, MDIO 0x08, RMII) */
-				phy_eth1: ethernet-phy@08 {
+				phy_eth1: ethernet-phy@8 {
 					reg = <0x08>;
 				};
 
 				/* Eth-2 (UCC6, MDIO 0x09, RMII) */
-				phy_eth2: ethernet-phy@09 {
+				phy_eth2: ethernet-phy@9 {
 					reg = <0x09>;
 				};
 
 				/* Eth-3 (UCC7, MDIO 0x0a, RMII) */
-				phy_eth3: ethernet-phy@0a {
+				phy_eth3: ethernet-phy@a {
 					reg = <0x0a>;
 				};
 
 				/* Eth-4 (UCC8, MDIO 0x0b, RMII) */
-				phy_eth4: ethernet-phy@0b {
+				phy_eth4: ethernet-phy@b {
 					reg = <0x0b>;
 				};
 
diff --git a/arch/powerpc/boot/dts/makalu.dts b/arch/powerpc/boot/dts/makalu.dts
index 63d48b632c84..bf8fe1629392 100644
--- a/arch/powerpc/boot/dts/makalu.dts
+++ b/arch/powerpc/boot/dts/makalu.dts
@@ -268,7 +268,7 @@
 			};
 		};
 
-		PCIE0: pciex@0a0000000 {
+		PCIE0: pciex@a0000000 {
 			device_type = "pci";
 			#interrupt-cells = <1>;
 			#size-cells = <2>;
@@ -309,7 +309,7 @@
 				0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>;
 		};
 
-		PCIE1: pciex@0c0000000 {
+		PCIE1: pciex@c0000000 {
 			device_type = "pci";
 			#interrupt-cells = <1>;
 			#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/mpc832x_mds.dts b/arch/powerpc/boot/dts/mpc832x_mds.dts
index 0793cdf0d46e..49c7d657118a 100644
--- a/arch/powerpc/boot/dts/mpc832x_mds.dts
+++ b/arch/powerpc/boot/dts/mpc832x_mds.dts
@@ -186,7 +186,7 @@
 			device_type = "par_io";
 			num-ports = <7>;
 
-			pio3: ucc_pin@03 {
+			pio3: ucc_pin@3 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					3  4  3  0  2  0  /* MDIO */
@@ -208,7 +208,7 @@
 					1 12  1  0  1  0 	/* TX_EN */
 					1 13  2  0  1  0>;	/* CRS */
 			};
-			pio4: ucc_pin@04 {
+			pio4: ucc_pin@4 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					3 31  2  0  1  0 	/* RX_CLK (CLK7) */
@@ -228,7 +228,7 @@
 					1 30  1  0  1  0 	/* TX_EN */
 					1 31  2  0  1  0>;	/* CRS */
 			};
-			pio5: ucc_pin@05 {
+			pio5: ucc_pin@5 {
 				pio-map = <
 				/*
 				 *    		      open       has
@@ -352,12 +352,12 @@
 			reg = <0x2320 0x18>;
 			compatible = "fsl,ucc-mdio";
 
-			phy3: ethernet-phy@03 {
+			phy3: ethernet-phy@3 {
 				interrupt-parent = <&ipic>;
 				interrupts = <17 0x8>;
 				reg = <0x3>;
 			};
-			phy4: ethernet-phy@04 {
+			phy4: ethernet-phy@4 {
 				interrupt-parent = <&ipic>;
 				interrupts = <18 0x8>;
 				reg = <0x4>;
diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts
index 91df1eb16667..647cae14c16d 100644
--- a/arch/powerpc/boot/dts/mpc832x_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc832x_rdb.dts
@@ -175,7 +175,7 @@
 				gpio-controller;
 			};
 
-			ucc2pio:ucc_pin@02 {
+			ucc2pio:ucc_pin@2 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					3  4  3  0  2  0 	/* MDIO */
@@ -197,7 +197,7 @@
 					0 30  1  0  1  0 	/* TX_EN */
 					0 31  2  0  1  0>;      /* CRS */
 			};
-			ucc3pio:ucc_pin@03 {
+			ucc3pio:ucc_pin@3 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					0 13  2  0  1  0 	/* RX_CLK (CLK9) */
@@ -310,12 +310,12 @@
 			reg = <0x3120 0x18>;
 			compatible = "fsl,ucc-mdio";
 
-			phy00:ethernet-phy@00 {
+			phy00:ethernet-phy@0 {
 				interrupt-parent = <&ipic>;
 				interrupts = <0>;
 				reg = <0x0>;
 			};
-			phy04:ethernet-phy@04 {
+			phy04:ethernet-phy@4 {
 				interrupt-parent = <&ipic>;
 				interrupts = <0>;
 				reg = <0x4>;
diff --git a/arch/powerpc/boot/dts/mpc836x_mds.dts b/arch/powerpc/boot/dts/mpc836x_mds.dts
index ecb6ccd3a6aa..539fd9f72eda 100644
--- a/arch/powerpc/boot/dts/mpc836x_mds.dts
+++ b/arch/powerpc/boot/dts/mpc836x_mds.dts
@@ -228,7 +228,7 @@
 				gpio-controller;
 			};
 
-			pio1: ucc_pin@01 {
+			pio1: ucc_pin@1 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					0  3  1  0  1  0 	/* TxD0 */
@@ -255,7 +255,7 @@
 					2  9  1  0  3  0 	/* GTX_CLK - CLK10 */
 					2  8  2  0  1  0>;	/* GTX125 - CLK9 */
 			};
-			pio2: ucc_pin@02 {
+			pio2: ucc_pin@2 {
 				pio-map = <
 			/* port  pin  dir  open_drain  assignment  has_irq */
 					0  17 1  0  1  0   /* TxD0 */
@@ -393,12 +393,12 @@
 			reg = <0x2120 0x18>;
 			compatible = "fsl,ucc-mdio";
 
-			phy0: ethernet-phy@00 {
+			phy0: ethernet-phy@0 {
 				interrupt-parent = <&ipic>;
 				interrupts = <17 0x8>;
 				reg = <0x0>;
 			};
-			phy1: ethernet-phy@01 {
+			phy1: ethernet-phy@1 {
 				interrupt-parent = <&ipic>;
 				interrupts = <18 0x8>;
 				reg = <0x1>;
diff --git a/arch/powerpc/boot/dts/sbc8548-altflash.dts b/arch/powerpc/boot/dts/sbc8548-altflash.dts
index 0b38a0defd2c..8967a56adad4 100644
--- a/arch/powerpc/boot/dts/sbc8548-altflash.dts
+++ b/arch/powerpc/boot/dts/sbc8548-altflash.dts
@@ -40,12 +40,12 @@
 			compatible = "intel,JS28F128", "cfi-flash";
 			bank-width = <4>;
 			device-width = <1>;
-			partition@0x0 {
+			partition@0 {
 				label = "space";
 				/* FC000000 -> FFEFFFFF */
 				reg = <0x00000000 0x03f00000>;
 			};
-			partition@0x03f00000 {
+			partition@3f00000 {
 				label = "bootloader";
 				/* FFF00000 -> FFFFFFFF */
 				reg = <0x03f00000 0x00100000>;
@@ -95,12 +95,12 @@
 			reg = <0x6 0x0 0x800000>;
 			bank-width = <1>;
 			device-width = <1>;
-			partition@0x0 {
+			partition@0 {
 				label = "space";
 				/* EF800000 -> EFF9FFFF */
 				reg = <0x00000000 0x007a0000>;
 			};
-			partition@0x7a0000 {
+			partition@7a0000 {
 				label = "bootloader";
 				/* EFFA0000 -> EFFFFFFF */
 				reg = <0x007a0000 0x00060000>;
diff --git a/arch/powerpc/boot/dts/sbc8548.dts b/arch/powerpc/boot/dts/sbc8548.dts
index 1df2a0955668..9bdb828a504e 100644
--- a/arch/powerpc/boot/dts/sbc8548.dts
+++ b/arch/powerpc/boot/dts/sbc8548.dts
@@ -38,12 +38,12 @@
 			reg = <0x0 0x0 0x800000>;
 			bank-width = <1>;
 			device-width = <1>;
-			partition@0x0 {
+			partition@0 {
 				label = "space";
 				/* FF800000 -> FFF9FFFF */
 				reg = <0x00000000 0x007a0000>;
 			};
-			partition@0x7a0000 {
+			partition@7a0000 {
 				label = "bootloader";
 				/* FFFA0000 -> FFFFFFFF */
 				reg = <0x007a0000 0x00060000>;
@@ -92,12 +92,12 @@
 			compatible = "intel,JS28F128", "cfi-flash";
 			bank-width = <4>;
 			device-width = <1>;
-			partition@0x0 {
+			partition@0 {
 				label = "space";
 				/* EC000000 -> EFEFFFFF */
 				reg = <0x00000000 0x03f00000>;
 			};
-			partition@0x03f00000 {
+			partition@3f00000 {
 				label = "bootloader";
 				/* EFF00000 -> EFFFFFFF */
 				reg = <0x03f00000 0x00100000>;
diff --git a/arch/powerpc/boot/dts/wii.dts b/arch/powerpc/boot/dts/wii.dts
index 77528c9a8dbd..17a5babb098d 100644
--- a/arch/powerpc/boot/dts/wii.dts
+++ b/arch/powerpc/boot/dts/wii.dts
@@ -65,14 +65,14 @@
 			  0x0d800000 0x0d800000 0x00800000>;
 		interrupt-parent = <&PIC0>;
 
-		video@0c002000 {
+		video@c002000 {
 			compatible = "nintendo,hollywood-vi",
 					"nintendo,flipper-vi";
 			reg = <0x0c002000 0x100>;
 			interrupts = <8>;
 		};
 
-		processor-interface@0c003000 {
+		processor-interface@c003000 {
 			compatible = "nintendo,hollywood-pi",
 					"nintendo,flipper-pi";
 			reg = <0x0c003000 0x100>;
@@ -84,7 +84,7 @@
 			};
 		};
 
-		dsp@0c005000 {
+		dsp@c005000 {
 			#address-cells = <1>;
 			#size-cells = <1>;
 			compatible = "nintendo,hollywood-dsp",
@@ -93,14 +93,14 @@
 			interrupts = <6>;
 		};
 
-		gamepad-controller@0d006400 {
+		gamepad-controller@d006400 {
 			compatible = "nintendo,hollywood-si",
 					"nintendo,flipper-si";
 			reg = <0x0d006400 0x100>;
 			interrupts = <3>;
 		};
 
-		audio@0c006c00 {
+		audio@c006c00 {
 			compatible = "nintendo,hollywood-ai",
 					"nintendo,flipper-ai";
 			reg = <0x0d006c00 0x20>;
@@ -108,7 +108,7 @@
 		};
 
 		/* External Interface bus */
-		exi@0d006800 {
+		exi@d006800 {
 			compatible = "nintendo,hollywood-exi",
 					"nintendo,flipper-exi";
 			reg = <0x0d006800 0x40>;
@@ -116,7 +116,7 @@
 			interrupts = <4>;
 		};
 
-		usb@0d040000 {
+		usb@d040000 {
 			compatible = "nintendo,hollywood-usb-ehci",
 					"usb-ehci";
 			reg = <0x0d040000 0x100>;
@@ -124,7 +124,7 @@
 			interrupt-parent = <&PIC1>;
 		};
 
-		usb@0d050000 {
+		usb@d050000 {
 			compatible = "nintendo,hollywood-usb-ohci",
 					"usb-ohci";
 			reg = <0x0d050000 0x100>;
@@ -132,7 +132,7 @@
 			interrupt-parent = <&PIC1>;
 		};
 
-		usb@0d060000 {
+		usb@d060000 {
 			compatible = "nintendo,hollywood-usb-ohci",
 					"usb-ohci";
 			reg = <0x0d060000 0x100>;
@@ -140,7 +140,7 @@
 			interrupt-parent = <&PIC1>;
 		};
 
-		sd@0d070000 {
+		sd@d070000 {
 			compatible = "nintendo,hollywood-sdhci",
 					"sdhci";
 			reg = <0x0d070000 0x200>;
@@ -148,7 +148,7 @@
 			interrupt-parent = <&PIC1>;
 		};
 
-		sdio@0d080000 {
+		sdio@d080000 {
 			compatible = "nintendo,hollywood-sdhci",
 					"sdhci";
 			reg = <0x0d080000 0x200>;
@@ -156,14 +156,14 @@
 			interrupt-parent = <&PIC1>;
 		};
 
-		ipc@0d000000 {
+		ipc@d000000 {
 			compatible = "nintendo,hollywood-ipc";
 			reg = <0x0d000000 0x10>;
 			interrupts = <30>;
 			interrupt-parent = <&PIC1>;
 		};
 
-		PIC1: pic1@0d800030 {
+		PIC1: pic1@d800030 {
 			#interrupt-cells = <1>;
 			compatible = "nintendo,hollywood-pic";
 			reg = <0x0d800030 0x10>;
@@ -171,7 +171,7 @@
 			interrupts = <14>;
 		};
 
-		GPIO: gpio@0d8000c0 {
+		GPIO: gpio@d8000c0 {
 			#gpio-cells = <2>;
 			compatible = "nintendo,hollywood-gpio";
 			reg = <0x0d8000c0 0x40>;
@@ -203,12 +203,12 @@
 			*/
 		};
 
-		control@0d800100 {
+		control@d800100 {
 			compatible = "nintendo,hollywood-control";
 			reg = <0x0d800100 0x300>;
 		};
 
-		disk@0d806000 {
+		disk@d806000 {
 			compatible = "nintendo,hollywood-di";
 			reg = <0x0d806000 0x40>;
 			interrupts = <2>;
diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c
index 7b5c02b1afd0..88955095ec07 100644
--- a/arch/powerpc/boot/serial.c
+++ b/arch/powerpc/boot/serial.c
@@ -124,20 +124,26 @@ int serial_console_init(void)
 	else if (dt_is_compatible(devp, "marvell,mv64360-mpsc"))
 		rc = mpsc_console_init(devp, &serial_cd);
 #endif
+#ifdef CONFIG_CPM
 	else if (dt_is_compatible(devp, "fsl,cpm1-scc-uart") ||
 	         dt_is_compatible(devp, "fsl,cpm1-smc-uart") ||
 	         dt_is_compatible(devp, "fsl,cpm2-scc-uart") ||
 	         dt_is_compatible(devp, "fsl,cpm2-smc-uart"))
 		rc = cpm_console_init(devp, &serial_cd);
+#endif
 #ifdef CONFIG_PPC_MPC52XX
 	else if (dt_is_compatible(devp, "fsl,mpc5200-psc-uart"))
 		rc = mpc5200_psc_console_init(devp, &serial_cd);
 #endif
+#ifdef CONFIG_XILINX_VIRTEX
 	else if (dt_is_compatible(devp, "xlnx,opb-uartlite-1.00.b") ||
 		 dt_is_compatible(devp, "xlnx,xps-uartlite-1.00.a"))
 		rc = uartlite_console_init(devp, &serial_cd);
+#endif
+#ifdef CONFIG_PPC64_BOOT_WRAPPER
 	else if (dt_is_compatible(devp, "ibm,opal-console-raw"))
 		rc = opal_console_init(devp, &serial_cd);
+#endif
 
 	/* Add other serial console driver calls here */
 
diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig
index b5c866073efd..6c02f53271cd 100644
--- a/arch/powerpc/configs/44x/warp_defconfig
+++ b/arch/powerpc/configs/44x/warp_defconfig
@@ -28,7 +28,6 @@ CONFIG_NETFILTER=y
 CONFIG_VLAN_8021Q=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_STANDALONE is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/c2k_defconfig b/arch/powerpc/configs/c2k_defconfig
index f1552af9eecc..4bb832a41d55 100644
--- a/arch/powerpc/configs/c2k_defconfig
+++ b/arch/powerpc/configs/c2k_defconfig
@@ -272,18 +272,6 @@ CONFIG_USB_SERIAL_EDGEPORT=m
 CONFIG_USB_SERIAL_EDGEPORT_TI=m
 CONFIG_USB_SERIAL_KEYSPAN_PDA=m
 CONFIG_USB_SERIAL_KEYSPAN=m
-CONFIG_USB_SERIAL_KEYSPAN_MPR=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28X=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28XA=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28XB=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19=y
-CONFIG_USB_SERIAL_KEYSPAN_USA18X=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19W=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19QW=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19QI=y
-CONFIG_USB_SERIAL_KEYSPAN_USA49W=y
-CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y
 CONFIG_USB_SERIAL_KLSI=m
 CONFIG_USB_SERIAL_KOBIL_SCT=m
 CONFIG_USB_SERIAL_MCT_U232=m
diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config
index cc49c95494da..e0567dc41968 100644
--- a/arch/powerpc/configs/fsl-emb-nonhw.config
+++ b/arch/powerpc/configs/fsl-emb-nonhw.config
@@ -71,7 +71,6 @@ CONFIG_IP_ROUTE_MULTIPATH=y
 CONFIG_IP_ROUTE_VERBOSE=y
 CONFIG_IP_SCTP=m
 CONFIG_IPV6=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_ISO9660_FS=m
 CONFIG_JFFS2_FS_DEBUG=1
 CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig
index 063817fee61c..67c39f4acede 100644
--- a/arch/powerpc/configs/g5_defconfig
+++ b/arch/powerpc/configs/g5_defconfig
@@ -189,18 +189,6 @@ CONFIG_USB_SERIAL_GARMIN=m
 CONFIG_USB_SERIAL_IPW=m
 CONFIG_USB_SERIAL_KEYSPAN_PDA=m
 CONFIG_USB_SERIAL_KEYSPAN=m
-CONFIG_USB_SERIAL_KEYSPAN_MPR=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28X=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28XA=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28XB=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19=y
-CONFIG_USB_SERIAL_KEYSPAN_USA18X=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19W=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19QW=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19QI=y
-CONFIG_USB_SERIAL_KEYSPAN_USA49W=y
-CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y
 CONFIG_USB_SERIAL_KLSI=m
 CONFIG_USB_SERIAL_KOBIL_SCT=m
 CONFIG_USB_SERIAL_MCT_U232=m
diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig
index 078cdb427fc9..59e47ec85336 100644
--- a/arch/powerpc/configs/maple_defconfig
+++ b/arch/powerpc/configs/maple_defconfig
@@ -82,18 +82,6 @@ CONFIG_USB_SERIAL_CYPRESS_M8=m
 CONFIG_USB_SERIAL_GARMIN=m
 CONFIG_USB_SERIAL_IPW=m
 CONFIG_USB_SERIAL_KEYSPAN=y
-CONFIG_USB_SERIAL_KEYSPAN_MPR=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28X=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28XA=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28XB=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19=y
-CONFIG_USB_SERIAL_KEYSPAN_USA18X=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19W=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19QW=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19QI=y
-CONFIG_USB_SERIAL_KEYSPAN_USA49W=y
-CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y
 CONFIG_USB_SERIAL_TI=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig
index 10be5773ad5d..c2b1c4404683 100644
--- a/arch/powerpc/configs/mpc512x_defconfig
+++ b/arch/powerpc/configs/mpc512x_defconfig
@@ -39,7 +39,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/mpc866_ads_defconfig b/arch/powerpc/configs/mpc866_ads_defconfig
index f1f176c29fa3..5320735395e7 100644
--- a/arch/powerpc/configs/mpc866_ads_defconfig
+++ b/arch/powerpc/configs/mpc866_ads_defconfig
@@ -13,7 +13,6 @@ CONFIG_EXPERT=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_MPC86XADS=y
 CONFIG_8xx_COPYBACK=y
-CONFIG_8xx_CPU6=y
 CONFIG_GEN_RTC=y
 CONFIG_HZ_1000=y
 CONFIG_MATH_EMULATION=y
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig
index 1aab9a62a681..62948d198d7f 100644
--- a/arch/powerpc/configs/pmac32_defconfig
+++ b/arch/powerpc/configs/pmac32_defconfig
@@ -264,18 +264,6 @@ CONFIG_USB_SERIAL_VISOR=m
 CONFIG_USB_SERIAL_IPAQ=m
 CONFIG_USB_SERIAL_KEYSPAN_PDA=m
 CONFIG_USB_SERIAL_KEYSPAN=m
-CONFIG_USB_SERIAL_KEYSPAN_MPR=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28X=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28XA=y
-CONFIG_USB_SERIAL_KEYSPAN_USA28XB=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19=y
-CONFIG_USB_SERIAL_KEYSPAN_USA18X=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19W=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19QW=y
-CONFIG_USB_SERIAL_KEYSPAN_USA19QI=y
-CONFIG_USB_SERIAL_KEYSPAN_USA49W=y
-CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y
 CONFIG_USB_APPLEDISPLAY=m
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_EXT2_FS=y
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index 4891bbed6258..9e92aa6a52ba 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -4,7 +4,6 @@ CONFIG_CPU_LITTLE_ENDIAN=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_AUDIT=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_TASKSTATS=y
@@ -97,6 +96,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=65536
 CONFIG_VIRTIO_BLK=m
+CONFIG_BLK_DEV_NVME=y
 CONFIG_IDE=y
 CONFIG_BLK_DEV_IDECD=y
 CONFIG_BLK_DEV_GENERIC=y
@@ -113,6 +113,7 @@ CONFIG_SCSI_CXGB3_ISCSI=m
 CONFIG_SCSI_CXGB4_ISCSI=m
 CONFIG_SCSI_BNX2_ISCSI=m
 CONFIG_BE2ISCSI=m
+CONFIG_SCSI_AACRAID=y
 CONFIG_SCSI_MPT2SAS=m
 CONFIG_SCSI_SYM53C8XX_2=m
 CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 6ddca80c52c3..5033e630afea 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -1,7 +1,6 @@
 CONFIG_PPC64=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_TASKSTATS=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index da0e8d535eb8..7ee736f20774 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -347,7 +347,6 @@ CONFIG_MAC80211_DEBUGFS=y
 CONFIG_NET_9P=m
 CONFIG_NET_9P_VIRTIO=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_DEBUG_DEVRES=y
 CONFIG_CONNECTOR=y
 CONFIG_PARPORT=m
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index 2efa025bf483..187e2f7c12c8 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -64,7 +64,6 @@ CONFIG_CFG80211_WEXT=y
 CONFIG_MAC80211=m
 # CONFIG_MAC80211_RC_MINSTREL is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=65535
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index bde2cd1005a2..0dd5cf7b566d 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -3,7 +3,6 @@ CONFIG_NR_CPUS=2048
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_AUDIT=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_TASKSTATS=y
diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig
index 9c7400a19e9d..0b0f78823a1b 100644
--- a/arch/powerpc/configs/wii_defconfig
+++ b/arch/powerpc/configs/wii_defconfig
@@ -43,7 +43,6 @@ CONFIG_CFG80211=y
 CONFIG_MAC80211=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_STANDALONE is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_COUNT=2
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
index f058e0c3e4d4..fd1d6c83f0c0 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -141,6 +141,7 @@ static struct shash_alg alg = {
 		.cra_name		= "crc32c",
 		.cra_driver_name	= "crc32c-vpmsum",
 		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(u32),
 		.cra_module		= THIS_MODULE,
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 2542ea15d338..3196d227e351 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -1,4 +1,3 @@
-generic-y += clkdev.h
 generic-y += div64.h
 generic-y += export.h
 generic-y += irq_regs.h
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 016579ef16d3..30a155c0a6b0 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -311,6 +311,29 @@ static inline int pte_present(pte_t pte)
 	return pte_val(pte) & _PAGE_PRESENT;
 }
 
+/*
+ * We only find page table entry in the last level
+ * Hence no need for other accessors
+ */
+#define pte_access_permitted pte_access_permitted
+static inline bool pte_access_permitted(pte_t pte, bool write)
+{
+	unsigned long pteval = pte_val(pte);
+	/*
+	 * A read-only access is controlled by _PAGE_USER bit.
+	 * We have _PAGE_READ set for WRITE and EXECUTE
+	 */
+	unsigned long need_pte_bits = _PAGE_PRESENT | _PAGE_USER;
+
+	if (write)
+		need_pte_bits |= _PAGE_WRITE;
+
+	if ((pteval & need_pte_bits) != need_pte_bits)
+		return false;
+
+	return true;
+}
+
 /* Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
  *
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 197ced1eaaa0..949d691094a4 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -17,6 +17,12 @@
 #define H_PUD_TABLE_SIZE	(sizeof(pud_t) << H_PUD_INDEX_SIZE)
 #define H_PGD_TABLE_SIZE	(sizeof(pgd_t) << H_PGD_INDEX_SIZE)
 
+#define H_PAGE_F_GIX_SHIFT	53
+#define H_PAGE_F_SECOND	_RPAGE_RPN44	/* HPTE is in 2ndary HPTEG */
+#define H_PAGE_F_GIX	(_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41)
+#define H_PAGE_BUSY	_RPAGE_RSV1     /* software: PTE & hash are busy */
+#define H_PAGE_HASHPTE	_RPAGE_RSV2     /* software: PTE & hash are busy */
+
 /* PTE flags to conserve for HPTE identification */
 #define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | \
 			 H_PAGE_F_SECOND | H_PAGE_F_GIX)
@@ -49,6 +55,20 @@ static inline int hash__hugepd_ok(hugepd_t hpd)
 }
 #endif
 
+/*
+ * 4K PTE format is different from 64K PTE format. Saving the hash_slot is just
+ * a matter of returning the PTE bits that need to be modified. On 64K PTE,
+ * things are a little more involved and hence needs many more parameters to
+ * accomplish the same. However we want to abstract this out from the caller by
+ * keeping the prototype consistent across the two formats.
+ */
+static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte,
+			unsigned int subpg_index, unsigned long hidx)
+{
+	return (hidx << H_PAGE_F_GIX_SHIFT) &
+		(H_PAGE_F_SECOND | H_PAGE_F_GIX);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
 static inline char *get_hpte_slot_array(pmd_t *pmdp)
@@ -101,8 +121,6 @@ extern pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma,
 extern void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 					 pgtable_t pgtable);
 extern pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
-extern void hash__pmdp_huge_split_prepare(struct vm_area_struct *vma,
-				      unsigned long address, pmd_t *pmdp);
 extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 				       unsigned long addr, pmd_t *pmdp);
 extern int hash__has_transparent_hugepage(void);
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 8d40cf03cb67..338b7da468ce 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -13,21 +13,17 @@
  */
 #define H_PAGE_COMBO	_RPAGE_RPN0 /* this is a combo 4k page */
 #define H_PAGE_4K_PFN	_RPAGE_RPN1 /* PFN is for a single 4k page */
+#define H_PAGE_BUSY	_RPAGE_RPN44     /* software: PTE & hash are busy */
+#define H_PAGE_HASHPTE	_RPAGE_RPN43	/* PTE has associated HPTE */
+
 /*
  * We need to differentiate between explicit huge page and THP huge
  * page, since THP huge page also need to track real subpage details
  */
 #define H_PAGE_THP_HUGE  H_PAGE_4K_PFN
 
-/*
- * Used to track subpage group valid if H_PAGE_COMBO is set
- * This overloads H_PAGE_F_GIX and H_PAGE_F_SECOND
- */
-#define H_PAGE_COMBO_VALID	(H_PAGE_F_GIX | H_PAGE_F_SECOND)
-
 /* PTE flags to conserve for HPTE identification */
-#define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_F_SECOND | \
-			 H_PAGE_F_GIX | H_PAGE_HASHPTE | H_PAGE_COMBO)
+#define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | H_PAGE_COMBO)
 /*
  * we support 16 fragments per PTE page of 64K size.
  */
@@ -55,24 +51,57 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
 	unsigned long *hidxp;
 
 	rpte.pte = pte;
-	rpte.hidx = 0;
-	if (pte_val(pte) & H_PAGE_COMBO) {
-		/*
-		 * Make sure we order the hidx load against the H_PAGE_COMBO
-		 * check. The store side ordering is done in __hash_page_4K
-		 */
-		smp_rmb();
-		hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
-		rpte.hidx = *hidxp;
-	}
+
+	/*
+	 * Ensure that we do not read the hidx before we read the PTE. Because
+	 * the writer side is expected to finish writing the hidx first followed
+	 * by the PTE, by using smp_wmb(). pte_set_hash_slot() ensures that.
+	 */
+	smp_rmb();
+
+	hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
+	rpte.hidx = *hidxp;
 	return rpte;
 }
 
+/*
+ * shift the hidx representation by one-modulo-0xf; i.e hidx 0 is respresented
+ * as 1, 1 as 2,... , and 0xf as 0.  This convention lets us represent a
+ * invalid hidx 0xf with a 0x0 bit value. PTEs are anyway zero'd when
+ * allocated. We dont have to zero them gain; thus save on the initialization.
+ */
+#define HIDX_UNSHIFT_BY_ONE(x) ((x + 0xfUL) & 0xfUL) /* shift backward by one */
+#define HIDX_SHIFT_BY_ONE(x) ((x + 0x1UL) & 0xfUL)   /* shift forward by one */
+#define HIDX_BITS(x, index)  (x << (index << 2))
+#define BITS_TO_HIDX(x, index)  ((x >> (index << 2)) & 0xfUL)
+#define INVALID_RPTE_HIDX  0x0UL
+
 static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
 {
-	if ((pte_val(rpte.pte) & H_PAGE_COMBO))
-		return (rpte.hidx >> (index<<2)) & 0xf;
-	return (pte_val(rpte.pte) >> H_PAGE_F_GIX_SHIFT) & 0xf;
+	return HIDX_UNSHIFT_BY_ONE(BITS_TO_HIDX(rpte.hidx, index));
+}
+
+/*
+ * Commit the hidx and return PTE bits that needs to be modified. The caller is
+ * expected to modify the PTE bits accordingly and commit the PTE to memory.
+ */
+static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte,
+		unsigned int subpg_index, unsigned long hidx)
+{
+	unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
+
+	rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index);
+	*hidxp = rpte.hidx  | HIDX_BITS(HIDX_SHIFT_BY_ONE(hidx), subpg_index);
+
+	/*
+	 * Anyone reading PTE must ensure hidx bits are read after reading the
+	 * PTE by using the read-side barrier smp_rmb(). __real_pte() can be
+	 * used for that.
+	 */
+	smp_wmb();
+
+	/* No PTE bits to be modified, return 0x0UL */
+	return 0x0UL;
 }
 
 #define __rpte_to_pte(r)	((r).pte)
@@ -203,8 +232,6 @@ extern pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma,
 extern void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 					 pgtable_t pgtable);
 extern pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
-extern void hash__pmdp_huge_split_prepare(struct vm_area_struct *vma,
-				      unsigned long address, pmd_t *pmdp);
 extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 				       unsigned long addr, pmd_t *pmdp);
 extern int hash__has_transparent_hugepage(void);
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index ecb1239d74f4..0920eff731b3 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -9,11 +9,6 @@
  *
  */
 #define H_PTE_NONE_MASK		_PAGE_HPTEFLAGS
-#define H_PAGE_F_GIX_SHIFT	56
-#define H_PAGE_BUSY		_RPAGE_RSV1 /* software: PTE & hash are busy */
-#define H_PAGE_F_SECOND		_RPAGE_RSV2	/* HPTE is in 2ndary HPTEG */
-#define H_PAGE_F_GIX		(_RPAGE_RSV3 | _RPAGE_RSV4 | _RPAGE_RPN44)
-#define H_PAGE_HASHPTE		_RPAGE_RPN43	/* PTE has associated HPTE */
 
 #ifdef CONFIG_PPC_64K_PAGES
 #include <asm/book3s/64/hash-64k.h>
@@ -167,6 +162,9 @@ static inline int hash__pte_none(pte_t pte)
 	return (pte_val(pte) & ~H_PTE_NONE_MASK) == 0;
 }
 
+unsigned long pte_get_hash_gslot(unsigned long vpn, unsigned long shift,
+		int ssize, real_pte_t rpte, unsigned int subpg_index);
+
 /* This low level function performs the actual PTE insertion
  * Setting the PTE depends on the MMU type and other factors. It's
  * an horrible mess that I'm not going to try to clean up now but
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index e91e115a816f..50ed64fba4ae 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -90,6 +90,8 @@
 #define HPTE_R_PP0		ASM_CONST(0x8000000000000000)
 #define HPTE_R_TS		ASM_CONST(0x4000000000000000)
 #define HPTE_R_KEY_HI		ASM_CONST(0x3000000000000000)
+#define HPTE_R_KEY_BIT0		ASM_CONST(0x2000000000000000)
+#define HPTE_R_KEY_BIT1		ASM_CONST(0x1000000000000000)
 #define HPTE_R_RPN_SHIFT	12
 #define HPTE_R_RPN		ASM_CONST(0x0ffffffffffff000)
 #define HPTE_R_RPN_3_0		ASM_CONST(0x01fffffffffff000)
@@ -104,6 +106,9 @@
 #define HPTE_R_C		ASM_CONST(0x0000000000000080)
 #define HPTE_R_R		ASM_CONST(0x0000000000000100)
 #define HPTE_R_KEY_LO		ASM_CONST(0x0000000000000e00)
+#define HPTE_R_KEY_BIT2		ASM_CONST(0x0000000000000800)
+#define HPTE_R_KEY_BIT3		ASM_CONST(0x0000000000000400)
+#define HPTE_R_KEY_BIT4		ASM_CONST(0x0000000000000200)
 #define HPTE_R_KEY		(HPTE_R_KEY_LO | HPTE_R_KEY_HI)
 
 #define HPTE_V_1TB_SEG		ASM_CONST(0x4000000000000000)
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index c9448e19847a..0abeb0e2d616 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -108,6 +108,16 @@ typedef struct {
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 	struct list_head iommu_group_mem_list;
 #endif
+
+#ifdef CONFIG_PPC_MEM_KEYS
+	/*
+	 * Each bit represents one protection key.
+	 * bit set   -> key allocated
+	 * bit unset -> key available for allocation
+	 */
+	u32 pkey_allocation_map;
+	s16 execute_only_pkey; /* key holding execute-only protection */
+#endif
 } mm_context_t;
 
 /*
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 9a677cd5997f..51017726d495 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -14,8 +14,9 @@
  */
 #define _PAGE_BIT_SWAP_TYPE	0
 
+#define _PAGE_NA		0
 #define _PAGE_RO		0
-#define _PAGE_SHARED		0
+#define _PAGE_USER		0
 
 #define _PAGE_EXEC		0x00001 /* execute permission */
 #define _PAGE_WRITE		0x00002 /* write access allowed */
@@ -39,6 +40,7 @@
 #define _RPAGE_RSV2		0x0800000000000000UL
 #define _RPAGE_RSV3		0x0400000000000000UL
 #define _RPAGE_RSV4		0x0200000000000000UL
+#define _RPAGE_RSV5		0x00040UL
 
 #define _PAGE_PTE		0x4000000000000000UL	/* distinguishes PTEs from pointers */
 #define _PAGE_PRESENT		0x8000000000000000UL	/* pte contains a translation */
@@ -58,6 +60,25 @@
 /* Max physical address bit as per radix table */
 #define _RPAGE_PA_MAX		57
 
+#ifdef CONFIG_PPC_MEM_KEYS
+#ifdef CONFIG_PPC_64K_PAGES
+#define H_PTE_PKEY_BIT0	_RPAGE_RSV1
+#define H_PTE_PKEY_BIT1	_RPAGE_RSV2
+#else /* CONFIG_PPC_64K_PAGES */
+#define H_PTE_PKEY_BIT0	0 /* _RPAGE_RSV1 is not available */
+#define H_PTE_PKEY_BIT1	0 /* _RPAGE_RSV2 is not available */
+#endif /* CONFIG_PPC_64K_PAGES */
+#define H_PTE_PKEY_BIT2	_RPAGE_RSV3
+#define H_PTE_PKEY_BIT3	_RPAGE_RSV4
+#define H_PTE_PKEY_BIT4	_RPAGE_RSV5
+#else /*  CONFIG_PPC_MEM_KEYS */
+#define H_PTE_PKEY_BIT0	0
+#define H_PTE_PKEY_BIT1	0
+#define H_PTE_PKEY_BIT2	0
+#define H_PTE_PKEY_BIT3	0
+#define H_PTE_PKEY_BIT4	0
+#endif /*  CONFIG_PPC_MEM_KEYS */
+
 /*
  * Max physical address bit we will use for now.
  *
@@ -121,13 +142,16 @@
 #define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
 			 _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE |	\
 			 _PAGE_SOFT_DIRTY)
+
+#define H_PTE_PKEY  (H_PTE_PKEY_BIT0 | H_PTE_PKEY_BIT1 | H_PTE_PKEY_BIT2 | \
+		     H_PTE_PKEY_BIT3 | H_PTE_PKEY_BIT4)
 /*
  * Mask of bits returned by pte_pgprot()
  */
 #define PAGE_PROT_BITS  (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT | \
 			 H_PAGE_4K_PFN | _PAGE_PRIVILEGED | _PAGE_ACCESSED | \
 			 _PAGE_READ | _PAGE_WRITE |  _PAGE_DIRTY | _PAGE_EXEC | \
-			 _PAGE_SOFT_DIRTY)
+			 _PAGE_SOFT_DIRTY | H_PTE_PKEY)
 /*
  * We define 2 sets of base prot bits, one for basic pages (ie,
  * cacheable kernel and user pages) and one for non cacheable
@@ -546,6 +570,40 @@ static inline int pte_present(pte_t pte)
 {
 	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT));
 }
+
+#ifdef CONFIG_PPC_MEM_KEYS
+extern bool arch_pte_access_permitted(u64 pte, bool write, bool execute);
+#else
+static inline bool arch_pte_access_permitted(u64 pte, bool write, bool execute)
+{
+	return true;
+}
+#endif /* CONFIG_PPC_MEM_KEYS */
+
+#define pte_access_permitted pte_access_permitted
+static inline bool pte_access_permitted(pte_t pte, bool write)
+{
+	unsigned long pteval = pte_val(pte);
+	/* Also check for pte_user */
+	unsigned long clear_pte_bits = _PAGE_PRIVILEGED;
+	/*
+	 * _PAGE_READ is needed for any access and will be
+	 * cleared for PROT_NONE
+	 */
+	unsigned long need_pte_bits = _PAGE_PRESENT | _PAGE_READ;
+
+	if (write)
+		need_pte_bits |= _PAGE_WRITE;
+
+	if ((pteval & need_pte_bits) != need_pte_bits)
+		return false;
+
+	if ((pteval & clear_pte_bits) == clear_pte_bits)
+		return false;
+
+	return arch_pte_access_permitted(pte_val(pte), write, 0);
+}
+
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
@@ -850,6 +908,11 @@ static inline int pud_bad(pud_t pud)
 	return hash__pud_bad(pud);
 }
 
+#define pud_access_permitted pud_access_permitted
+static inline bool pud_access_permitted(pud_t pud, bool write)
+{
+	return pte_access_permitted(pud_pte(pud), write);
+}
 
 #define pgd_write(pgd)		pte_write(pgd_pte(pgd))
 static inline void pgd_set(pgd_t *pgdp, unsigned long val)
@@ -889,6 +952,12 @@ static inline int pgd_bad(pgd_t pgd)
 	return hash__pgd_bad(pgd);
 }
 
+#define pgd_access_permitted pgd_access_permitted
+static inline bool pgd_access_permitted(pgd_t pgd, bool write)
+{
+	return pte_access_permitted(pgd_pte(pgd), write);
+}
+
 extern struct page *pgd_page(pgd_t pgd);
 
 /* Pointers in the page table tree are physical addresses */
@@ -1005,11 +1074,16 @@ static inline int pmd_protnone(pmd_t pmd)
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
-#define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 #define __pmd_write(pmd)	__pte_write(pmd_pte(pmd))
 #define pmd_savedwrite(pmd)	pte_savedwrite(pmd_pte(pmd))
 
+#define pmd_access_permitted pmd_access_permitted
+static inline bool pmd_access_permitted(pmd_t pmd, bool write)
+{
+	return pte_access_permitted(pmd_pte(pmd), write);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
 extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
@@ -1138,17 +1212,8 @@ static inline pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm,
 }
 
 #define __HAVE_ARCH_PMDP_INVALIDATE
-extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
-			    pmd_t *pmdp);
-
-#define __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
-static inline void pmdp_huge_split_prepare(struct vm_area_struct *vma,
-					   unsigned long address, pmd_t *pmdp)
-{
-	if (radix_enabled())
-		return radix__pmdp_huge_split_prepare(vma, address, pmdp);
-	return hash__pmdp_huge_split_prepare(vma, address, pmdp);
-}
+extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			     pmd_t *pmdp);
 
 #define pmd_move_must_withdraw pmd_move_must_withdraw
 struct spinlock;
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 19c44e1495ae..365010f66570 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -269,12 +269,6 @@ static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
 		return __pmd(pmd_val(pmd) | _PAGE_PTE | R_PAGE_LARGE);
 	return __pmd(pmd_val(pmd) | _PAGE_PTE);
 }
-static inline void radix__pmdp_huge_split_prepare(struct vm_area_struct *vma,
-					    unsigned long address, pmd_t *pmdp)
-{
-	/* Nothing to do for radix. */
-	return;
-}
 
 extern unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
 					  pmd_t *pmdp, unsigned long clr,
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
index 849ecaae9e79..64d02a704bcb 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
@@ -51,6 +51,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
 
 #define arch_flush_lazy_mmu_mode()      do {} while (0)
 
+extern void hash__tlbiel_all(unsigned int action);
 
 extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
 			    int ssize, unsigned long flags);
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 6a9e68003387..8eea90f80e45 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -11,6 +11,12 @@ static inline int mmu_get_ap(int psize)
 	return mmu_psize_defs[psize].ap;
 }
 
+#ifdef CONFIG_PPC_RADIX_MMU
+extern void radix__tlbiel_all(unsigned int action);
+#else
+static inline void radix__tlbiel_all(unsigned int action) { WARN_ON(1); };
+#endif
+
 extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma,
 					   unsigned long start, unsigned long end);
 extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
@@ -47,4 +53,5 @@ extern void radix__flush_tlb_lpid(unsigned long lpid);
 extern void radix__flush_tlb_all(void);
 extern void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
 					unsigned long address);
+
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index 58b576f654b3..0cac17253513 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -8,6 +8,44 @@
 #include <asm/book3s/64/tlbflush-hash.h>
 #include <asm/book3s/64/tlbflush-radix.h>
 
+/* TLB flush actions. Used as argument to tlbiel_all() */
+enum {
+	TLB_INVAL_SCOPE_GLOBAL = 0,	/* invalidate all TLBs */
+	TLB_INVAL_SCOPE_LPID = 1,	/* invalidate TLBs for current LPID */
+};
+
+#ifdef CONFIG_PPC_NATIVE
+static inline void tlbiel_all(void)
+{
+	/*
+	 * This is used for host machine check and bootup.
+	 *
+	 * This uses early_radix_enabled and implementations use
+	 * early_cpu_has_feature etc because that works early in boot
+	 * and this is the machine check path which is not performance
+	 * critical.
+	 */
+	if (early_radix_enabled())
+		radix__tlbiel_all(TLB_INVAL_SCOPE_GLOBAL);
+	else
+		hash__tlbiel_all(TLB_INVAL_SCOPE_GLOBAL);
+}
+#else
+static inline void tlbiel_all(void) { BUG(); };
+#endif
+
+static inline void tlbiel_all_lpid(bool radix)
+{
+	/*
+	 * This is used for guest machine check.
+	 */
+	if (radix)
+		radix__tlbiel_all(TLB_INVAL_SCOPE_LPID);
+	else
+		hash__tlbiel_all(TLB_INVAL_SCOPE_LPID);
+}
+
+
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 static inline void flush_pmd_tlb_range(struct vm_area_struct *vma,
 				       unsigned long start, unsigned long end)
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 3c04249bcf39..fd06dbe7d7d3 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -133,9 +133,11 @@ struct pt_regs;
 extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long);
 extern void bad_page_fault(struct pt_regs *, unsigned long, int);
 extern void _exception(int, struct pt_regs *, int, unsigned long);
+extern void _exception_pkey(int, struct pt_regs *, int, unsigned long, int);
 extern void die(const char *, struct pt_regs *, long);
 extern bool die_will_crash(void);
-
+extern void panic_flush_kmsg_start(void);
+extern void panic_flush_kmsg_end(void);
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index abef812de7f8..812535f40124 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -31,8 +31,10 @@ unsigned int create_cond_branch(const unsigned int *addr,
 				unsigned long target, int flags);
 int patch_branch(unsigned int *addr, unsigned long target, int flags);
 int patch_instruction(unsigned int *addr, unsigned int instr);
+int raw_patch_instruction(unsigned int *addr, unsigned int instr);
 
 int instr_is_relative_branch(unsigned int instr);
+int instr_is_relative_link_branch(unsigned int instr);
 int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr);
 unsigned long branch_target(const unsigned int *instr);
 unsigned int translate_branch(const unsigned int *dest,
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 8a2aecfe9b02..62168e1158f1 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -119,71 +119,6 @@ typedef u32		compat_old_sigset_t;
 
 typedef u32		compat_sigset_word;
 
-typedef union compat_sigval {
-	compat_int_t	sival_int;
-	compat_uptr_t	sival_ptr;
-} compat_sigval_t;
-
-#define SI_PAD_SIZE32	(128/sizeof(int) - 3)
-
-typedef struct compat_siginfo {
-	int si_signo;
-	int si_errno;
-	int si_code;
-
-	union {
-		int _pad[SI_PAD_SIZE32];
-
-		/* kill() */
-		struct {
-			compat_pid_t _pid;		/* sender's pid */
-			__compat_uid_t _uid;		/* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			compat_timer_t _tid;		/* timer id */
-			int _overrun;			/* overrun count */
-			compat_sigval_t _sigval;	/* same as below */
-			int _sys_private;	/* not to be passed to user */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			compat_pid_t _pid;		/* sender's pid */
-			__compat_uid_t _uid;		/* sender's uid */
-			compat_sigval_t _sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			compat_pid_t _pid;		/* which child */
-			__compat_uid_t _uid;		/* sender's uid */
-			int _status;			/* exit code */
-			compat_clock_t _utime;
-			compat_clock_t _stime;
-		} _sigchld;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */
-		struct {
-			unsigned int _addr; /* faulting insn/memory ref. */
-		} _sigfault;
-
-		/* SIGPOLL */
-		struct {
-			int _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
-			int _fd;
-		} _sigpoll;
-
-		/* SIGSYS */
-		struct {
-			unsigned int _call_addr; /* calling insn */
-			int _syscall;		 /* triggering system call number */
-			unsigned int _arch;	 /* AUDIT_ARCH_* of syscall */
-		} _sigsys;
-	} _sifields;
-} compat_siginfo_t;
-
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
 /*
diff --git a/arch/powerpc/include/asm/cpm.h b/arch/powerpc/include/asm/cpm.h
index b925df1b87d0..4c24ea8209bb 100644
--- a/arch/powerpc/include/asm/cpm.h
+++ b/arch/powerpc/include/asm/cpm.h
@@ -166,6 +166,6 @@ static inline int cpm_command(u32 command, u8 opcode)
 }
 #endif /* CONFIG_CPM */
 
-int cpm2_gpiochip_add32(struct device_node *np);
+int cpm2_gpiochip_add32(struct device *dev);
 
 #endif
diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h
index 3db821876d48..a116fe931789 100644
--- a/arch/powerpc/include/asm/cpm1.h
+++ b/arch/powerpc/include/asm/cpm1.h
@@ -605,5 +605,7 @@ enum cpm_clk {
 };
 
 int cpm1_clk_setup(enum cpm_clk_target target, int clock, int mode);
+int cpm1_gpiochip_add16(struct device *dev);
+int cpm1_gpiochip_add32(struct device *dev);
 
 #endif /* __CPM1__ */
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 0546663a98db..a2c5c95882cf 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -107,12 +107,6 @@ struct cpu_spec {
 	 * called in real mode to handle SLB and TLB errors.
 	 */
 	long		(*machine_check_early)(struct pt_regs *regs);
-
-	/*
-	 * Processor specific routine to flush tlbs.
-	 */
-	void		(*flush_tlb)(unsigned int action);
-
 };
 
 extern struct cpu_spec		*cur_cpu_spec;
@@ -133,12 +127,6 @@ extern void cpu_feature_keys_init(void);
 static inline void cpu_feature_keys_init(void) { }
 #endif
 
-/* TLB flush actions. Used as argument to cpu_spec.flush_tlb() hook */
-enum {
-	TLB_INVAL_SCOPE_GLOBAL = 0,	/* invalidate all TLBs */
-	TLB_INVAL_SCOPE_LPID = 1,	/* invalidate TLBs for current LPID */
-};
-
 #endif /* __ASSEMBLY__ */
 
 /* CPU kernel features */
@@ -207,7 +195,7 @@ enum {
 #define CPU_FTR_STCX_CHECKS_ADDRESS	LONG_ASM_CONST(0x0004000000000000)
 #define CPU_FTR_POPCNTB			LONG_ASM_CONST(0x0008000000000000)
 #define CPU_FTR_POPCNTD			LONG_ASM_CONST(0x0010000000000000)
-/* Free					LONG_ASM_CONST(0x0020000000000000) */
+#define CPU_FTR_PKEY			LONG_ASM_CONST(0x0020000000000000)
 #define CPU_FTR_VMX_COPY		LONG_ASM_CONST(0x0040000000000000)
 #define CPU_FTR_TM			LONG_ASM_CONST(0x0080000000000000)
 #define CPU_FTR_CFAR			LONG_ASM_CONST(0x0100000000000000)
@@ -454,7 +442,7 @@ enum {
 	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | \
-	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX)
+	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX | CPU_FTR_PKEY)
 #define CPU_FTRS_POWER8 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -464,7 +452,7 @@ enum {
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
-	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
+	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_PKEY)
 #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
 #define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
 #define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
@@ -476,7 +464,8 @@ enum {
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
-	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300)
+	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | \
+	    CPU_FTR_PKEY)
 #define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \
 			     (~CPU_FTR_SAO))
 #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9
diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h
index 14e71ff6579e..fc97404de0a3 100644
--- a/arch/powerpc/include/asm/debug.h
+++ b/arch/powerpc/include/asm/debug.h
@@ -49,7 +49,7 @@ void set_breakpoint(struct arch_hw_breakpoint *brk);
 void __set_breakpoint(struct arch_hw_breakpoint *brk);
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 extern void do_send_trap(struct pt_regs *regs, unsigned long address,
-			 unsigned long error_code, int signal_code, int brkpt);
+			 unsigned long error_code, int brkpt);
 #else
 
 extern void do_break(struct pt_regs *regs, unsigned long address,
diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h
new file mode 100644
index 000000000000..a5b59c765426
--- /dev/null
+++ b/arch/powerpc/include/asm/dma-direct.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ASM_POWERPC_DMA_DIRECT_H
+#define ASM_POWERPC_DMA_DIRECT_H 1
+
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+#ifdef CONFIG_SWIOTLB
+	struct dev_archdata *sd = &dev->archdata;
+
+	if (sd->max_direct_dma_addr && addr + size > sd->max_direct_dma_addr)
+		return false;
+#endif
+
+	if (!dev->dma_mask)
+		return false;
+
+	return addr + size - 1 <= *dev->dma_mask;
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return paddr + get_dma_offset(dev);
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+	return daddr - get_dma_offset(dev);
+}
+#endif /* ASM_POWERPC_DMA_DIRECT_H */
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 5a6cbe11db6f..8fa394520af6 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -19,13 +19,13 @@
 #include <asm/swiotlb.h>
 
 /* Some dma direct funcs must be visible for use in other dma_ops */
-extern void *__dma_direct_alloc_coherent(struct device *dev, size_t size,
+extern void *__dma_nommu_alloc_coherent(struct device *dev, size_t size,
 					 dma_addr_t *dma_handle, gfp_t flag,
 					 unsigned long attrs);
-extern void __dma_direct_free_coherent(struct device *dev, size_t size,
+extern void __dma_nommu_free_coherent(struct device *dev, size_t size,
 				       void *vaddr, dma_addr_t dma_handle,
 				       unsigned long attrs);
-extern int dma_direct_mmap_coherent(struct device *dev,
+extern int dma_nommu_mmap_coherent(struct device *dev,
 				    struct vm_area_struct *vma,
 				    void *cpu_addr, dma_addr_t handle,
 				    size_t size, unsigned long attrs);
@@ -73,7 +73,7 @@ static inline unsigned long device_to_mask(struct device *dev)
 #ifdef CONFIG_PPC64
 extern struct dma_map_ops dma_iommu_ops;
 #endif
-extern const struct dma_map_ops dma_direct_ops;
+extern const struct dma_map_ops dma_nommu_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
@@ -107,39 +107,11 @@ static inline void set_dma_offset(struct device *dev, dma_addr_t off)
 		dev->archdata.dma_offset = off;
 }
 
-/* this will be removed soon */
-#define flush_write_buffers()
-
 #define HAVE_ARCH_DMA_SET_MASK 1
 extern int dma_set_mask(struct device *dev, u64 dma_mask);
 
 extern u64 __dma_get_required_mask(struct device *dev);
 
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-#ifdef CONFIG_SWIOTLB
-	struct dev_archdata *sd = &dev->archdata;
-
-	if (sd->max_direct_dma_addr && addr + size > sd->max_direct_dma_addr)
-		return false;
-#endif
-
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return paddr + get_dma_offset(dev);
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return daddr - get_dma_offset(dev);
-}
-
 #define ARCH_HAS_DMA_MMAP_COHERENT
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h
new file mode 100644
index 000000000000..ce242b9ea8c6
--- /dev/null
+++ b/arch/powerpc/include/asm/drmem.h
@@ -0,0 +1,102 @@
+/*
+ * drmem.h: Power specific logical memory block representation
+ *
+ * Copyright 2017 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_POWERPC_LMB_H
+#define _ASM_POWERPC_LMB_H
+
+struct drmem_lmb {
+	u64     base_addr;
+	u32     drc_index;
+	u32     aa_index;
+	u32     flags;
+};
+
+struct drmem_lmb_info {
+	struct drmem_lmb        *lmbs;
+	int                     n_lmbs;
+	u32                     lmb_size;
+};
+
+extern struct drmem_lmb_info *drmem_info;
+
+#define for_each_drmem_lmb_in_range(lmb, start, end)		\
+	for ((lmb) = (start); (lmb) <= (end); (lmb)++)
+
+#define for_each_drmem_lmb(lmb)					\
+	for_each_drmem_lmb_in_range((lmb),			\
+		&drmem_info->lmbs[0],				\
+		&drmem_info->lmbs[drmem_info->n_lmbs - 1])
+
+/*
+ * The of_drconf_cell_v1 struct defines the layout of the LMB data
+ * specified in the ibm,dynamic-memory device tree property.
+ * The property itself is a 32-bit value specifying the number of
+ * LMBs followed by an array of of_drconf_cell_v1 entries, one
+ * per LMB.
+ */
+struct of_drconf_cell_v1 {
+	__be64	base_addr;
+	__be32	drc_index;
+	__be32	reserved;
+	__be32	aa_index;
+	__be32	flags;
+};
+
+/*
+ * Version 2 of the ibm,dynamic-memory property is defined as a
+ * 32-bit value specifying the number of LMB sets followed by an
+ * array of of_drconf_cell_v2 entries, one per LMB set.
+ */
+struct of_drconf_cell_v2 {
+	u32	seq_lmbs;
+	u64	base_addr;
+	u32	drc_index;
+	u32	aa_index;
+	u32	flags;
+} __packed;
+
+#define DRCONF_MEM_ASSIGNED	0x00000008
+#define DRCONF_MEM_AI_INVALID	0x00000040
+#define DRCONF_MEM_RESERVED	0x00000080
+
+static inline u32 drmem_lmb_size(void)
+{
+	return drmem_info->lmb_size;
+}
+
+#define DRMEM_LMB_RESERVED	0x80000000
+
+static inline void drmem_mark_lmb_reserved(struct drmem_lmb *lmb)
+{
+	lmb->flags |= DRMEM_LMB_RESERVED;
+}
+
+static inline void drmem_remove_lmb_reservation(struct drmem_lmb *lmb)
+{
+	lmb->flags &= ~DRMEM_LMB_RESERVED;
+}
+
+static inline bool drmem_lmb_reserved(struct drmem_lmb *lmb)
+{
+	return lmb->flags & DRMEM_LMB_RESERVED;
+}
+
+u64 drmem_lmb_memory_max(void);
+void __init walk_drmem_lmbs(struct device_node *dn,
+			void (*func)(struct drmem_lmb *, const __be32 **));
+int drmem_update_dt(void);
+
+#ifdef CONFIG_PPC_PSERIES
+void __init walk_drmem_lmbs_early(unsigned long node,
+			void (*func)(struct drmem_lmb *, const __be32 **));
+#endif
+
+#endif /* _ASM_POWERPC_LMB_H */
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 5161c37dd039..fd37cc101f4f 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -214,6 +214,7 @@ struct eeh_ops {
 	int (*write_config)(struct pci_dn *pdn, int where, int size, u32 val);
 	int (*next_error)(struct eeh_pe **pe);
 	int (*restore_config)(struct pci_dn *pdn);
+	int (*notify_resume)(struct pci_dn *pdn);
 };
 
 extern int eeh_subsystem_flags;
@@ -297,6 +298,7 @@ int eeh_pe_reset(struct eeh_pe *pe, int option);
 int eeh_pe_configure(struct eeh_pe *pe);
 int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
 		      unsigned long addr, unsigned long mask);
+int eeh_restore_vf_config(struct pci_dn *pdn);
 
 /**
  * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h
index a703452d67b6..555e22d5e07f 100644
--- a/arch/powerpc/include/asm/exception-64e.h
+++ b/arch/powerpc/include/asm/exception-64e.h
@@ -209,5 +209,11 @@ exc_##label##_book3e:
 	ori	r3,r3,vector_offset@l;		\
 	mtspr	SPRN_IVOR##vector_number,r3;
 
+#define RFI_TO_KERNEL							\
+	rfi
+
+#define RFI_TO_USER							\
+	rfi
+
 #endif /* _ASM_POWERPC_EXCEPTION_64E_H */
 
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index b27205297e1d..176dfb73d42c 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -74,6 +74,59 @@
  */
 #define EX_R3		EX_DAR
 
+/*
+ * Macros for annotating the expected destination of (h)rfid
+ *
+ * The nop instructions allow us to insert one or more instructions to flush the
+ * L1-D cache when returning to userspace or a guest.
+ */
+#define RFI_FLUSH_SLOT							\
+	RFI_FLUSH_FIXUP_SECTION;					\
+	nop;								\
+	nop;								\
+	nop
+
+#define RFI_TO_KERNEL							\
+	rfid
+
+#define RFI_TO_USER							\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define RFI_TO_USER_OR_KERNEL						\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define RFI_TO_GUEST							\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define HRFI_TO_KERNEL							\
+	hrfid
+
+#define HRFI_TO_USER							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_USER_OR_KERNEL						\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_GUEST							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_UNKNOWN							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
 #ifdef CONFIG_RELOCATABLE
 #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)			\
 	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
@@ -198,18 +251,40 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	std	r10,area+EX_R10(r13);	/* save r10 - r12 */		\
 	OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR)
 
-#define __EXCEPTION_PROLOG_1(area, extra, vec)				\
+#define __EXCEPTION_PROLOG_1_PRE(area)					\
 	OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR);		\
 	OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR);		\
 	SAVE_CTR(r10, area);						\
-	mfcr	r9;							\
-	extra(vec);							\
+	mfcr	r9;
+
+#define __EXCEPTION_PROLOG_1_POST(area)					\
 	std	r11,area+EX_R11(r13);					\
 	std	r12,area+EX_R12(r13);					\
 	GET_SCRATCH0(r10);						\
 	std	r10,area+EX_R13(r13)
+
+/*
+ * This version of the EXCEPTION_PROLOG_1 will carry
+ * addition parameter called "bitmask" to support
+ * checking of the interrupt maskable level in the SOFTEN_TEST.
+ * Intended to be used in MASKABLE_EXCPETION_* macros.
+ */
+#define MASKABLE_EXCEPTION_PROLOG_1(area, extra, vec, bitmask)			\
+	__EXCEPTION_PROLOG_1_PRE(area);					\
+	extra(vec, bitmask);						\
+	__EXCEPTION_PROLOG_1_POST(area);
+
+/*
+ * This version of the EXCEPTION_PROLOG_1 is intended
+ * to be used in STD_EXCEPTION* macros
+ */
+#define _EXCEPTION_PROLOG_1(area, extra, vec)				\
+	__EXCEPTION_PROLOG_1_PRE(area);					\
+	extra(vec);							\
+	__EXCEPTION_PROLOG_1_POST(area);
+
 #define EXCEPTION_PROLOG_1(area, extra, vec)				\
-	__EXCEPTION_PROLOG_1(area, extra, vec)
+	_EXCEPTION_PROLOG_1(area, extra, vec)
 
 #define __EXCEPTION_PROLOG_PSERIES_1(label, h)				\
 	ld	r10,PACAKMSR(r13);	/* get MSR value for kernel */	\
@@ -218,7 +293,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	mtspr	SPRN_##h##SRR0,r12;					\
 	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
 	mtspr	SPRN_##h##SRR1,r10;					\
-	h##rfid;							\
+	h##RFI_TO_KERNEL;						\
 	b	.	/* prevent speculative execution */
 #define EXCEPTION_PROLOG_PSERIES_1(label, h)				\
 	__EXCEPTION_PROLOG_PSERIES_1(label, h)
@@ -232,7 +307,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	mtspr	SPRN_##h##SRR0,r12;					\
 	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
 	mtspr	SPRN_##h##SRR1,r10;					\
-	h##rfid;							\
+	h##RFI_TO_KERNEL;						\
 	b	.	/* prevent speculative execution */
 
 #define EXCEPTION_PROLOG_PSERIES_1_NORI(label, h)			\
@@ -432,7 +507,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	mflr	r9;			/* Get LR, later save to stack	*/ \
 	ld	r2,PACATOC(r13);	/* get kernel TOC into r2	*/ \
 	std	r9,_LINK(r1);						   \
-	lbz	r10,PACASOFTIRQEN(r13);				   \
+	lbz	r10,PACAIRQSOFTMASK(r13);				   \
 	mfspr	r11,SPRN_XER;		/* save XER in stackframe	*/ \
 	std	r10,SOFTE(r1);						   \
 	std	r11,_XER(r1);						   \
@@ -496,22 +571,23 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 #define SOFTEN_VALUE_0xe80	PACA_IRQ_DBELL
 #define SOFTEN_VALUE_0xe60	PACA_IRQ_HMI
 #define SOFTEN_VALUE_0xea0	PACA_IRQ_EE
+#define SOFTEN_VALUE_0xf00	PACA_IRQ_PMI
 
-#define __SOFTEN_TEST(h, vec)						\
-	lbz	r10,PACASOFTIRQEN(r13);					\
-	cmpwi	r10,0;							\
+#define __SOFTEN_TEST(h, vec, bitmask)					\
+	lbz	r10,PACAIRQSOFTMASK(r13);				\
+	andi.	r10,r10,bitmask;					\
 	li	r10,SOFTEN_VALUE_##vec;					\
-	beq	masked_##h##interrupt
+	bne	masked_##h##interrupt
 
-#define _SOFTEN_TEST(h, vec)	__SOFTEN_TEST(h, vec)
+#define _SOFTEN_TEST(h, vec, bitmask)	__SOFTEN_TEST(h, vec, bitmask)
 
-#define SOFTEN_TEST_PR(vec)						\
+#define SOFTEN_TEST_PR(vec, bitmask)					\
 	KVMTEST(EXC_STD, vec);						\
-	_SOFTEN_TEST(EXC_STD, vec)
+	_SOFTEN_TEST(EXC_STD, vec, bitmask)
 
-#define SOFTEN_TEST_HV(vec)						\
+#define SOFTEN_TEST_HV(vec, bitmask)					\
 	KVMTEST(EXC_HV, vec);						\
-	_SOFTEN_TEST(EXC_HV, vec)
+	_SOFTEN_TEST(EXC_HV, vec, bitmask)
 
 #define KVMTEST_PR(vec)							\
 	KVMTEST(EXC_STD, vec)
@@ -519,53 +595,57 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 #define KVMTEST_HV(vec)							\
 	KVMTEST(EXC_HV, vec)
 
-#define SOFTEN_NOTEST_PR(vec)		_SOFTEN_TEST(EXC_STD, vec)
-#define SOFTEN_NOTEST_HV(vec)		_SOFTEN_TEST(EXC_HV, vec)
+#define SOFTEN_NOTEST_PR(vec, bitmask)	_SOFTEN_TEST(EXC_STD, vec, bitmask)
+#define SOFTEN_NOTEST_HV(vec, bitmask)	_SOFTEN_TEST(EXC_HV, vec, bitmask)
 
-#define __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra)		\
+#define __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra, bitmask)	\
 	SET_SCRATCH0(r13);    /* save r13 */				\
 	EXCEPTION_PROLOG_0(PACA_EXGEN);					\
-	__EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec);			\
+	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec, bitmask);	\
 	EXCEPTION_PROLOG_PSERIES_1(label, h);
 
-#define _MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra)		\
-	__MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra)
+#define _MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra, bitmask)	\
+	__MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra, bitmask)
 
-#define MASKABLE_EXCEPTION_PSERIES(loc, vec, label)			\
+#define MASKABLE_EXCEPTION_PSERIES(loc, vec, label, bitmask)		\
 	_MASKABLE_EXCEPTION_PSERIES(vec, label,				\
-				    EXC_STD, SOFTEN_TEST_PR)
+				    EXC_STD, SOFTEN_TEST_PR, bitmask)
 
-#define MASKABLE_EXCEPTION_PSERIES_OOL(vec, label)			\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_PR, vec);		\
+#define MASKABLE_EXCEPTION_PSERIES_OOL(vec, label, bitmask)		\
+	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_PR, vec, bitmask);\
 	EXCEPTION_PROLOG_PSERIES_1(label, EXC_STD)
 
-#define MASKABLE_EXCEPTION_HV(loc, vec, label)				\
+#define MASKABLE_EXCEPTION_HV(loc, vec, label, bitmask)			\
 	_MASKABLE_EXCEPTION_PSERIES(vec, label,				\
-				    EXC_HV, SOFTEN_TEST_HV)
+				    EXC_HV, SOFTEN_TEST_HV, bitmask)
 
-#define MASKABLE_EXCEPTION_HV_OOL(vec, label)				\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec);		\
+#define MASKABLE_EXCEPTION_HV_OOL(vec, label, bitmask)			\
+	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\
 	EXCEPTION_PROLOG_PSERIES_1(label, EXC_HV)
 
-#define __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra)	\
+#define __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra, bitmask) \
 	SET_SCRATCH0(r13);    /* save r13 */				\
 	EXCEPTION_PROLOG_0(PACA_EXGEN);					\
-	__EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec);			\
+	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec, bitmask);	\
 	EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)
 
-#define _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra)		\
-	__MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra)
+#define _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra, bitmask)\
+	__MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra, bitmask)
 
-#define MASKABLE_RELON_EXCEPTION_PSERIES(loc, vec, label)		\
+#define MASKABLE_RELON_EXCEPTION_PSERIES(loc, vec, label, bitmask)	\
 	_MASKABLE_RELON_EXCEPTION_PSERIES(vec, label,			\
-					  EXC_STD, SOFTEN_NOTEST_PR)
+					  EXC_STD, SOFTEN_NOTEST_PR, bitmask)
+
+#define MASKABLE_RELON_EXCEPTION_PSERIES_OOL(vec, label, bitmask)	\
+	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_PR, vec, bitmask);\
+	EXCEPTION_PROLOG_PSERIES_1(label, EXC_STD);
 
-#define MASKABLE_RELON_EXCEPTION_HV(loc, vec, label)			\
+#define MASKABLE_RELON_EXCEPTION_HV(loc, vec, label, bitmask)		\
 	_MASKABLE_RELON_EXCEPTION_PSERIES(vec, label,			\
-					  EXC_HV, SOFTEN_TEST_HV)
+					  EXC_HV, SOFTEN_TEST_HV, bitmask)
 
-#define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label)			\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec);		\
+#define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label, bitmask)		\
+	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_HV, vec, bitmask);\
 	EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV)
 
 /*
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index 8f88f771cc55..1e82eb3caabd 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -187,7 +187,20 @@ label##3:					       	\
 	FTR_ENTRY_OFFSET label##1b-label##3b;		\
 	.popsection;
 
+#define RFI_FLUSH_FIXUP_SECTION				\
+951:							\
+	.pushsection __rfi_flush_fixup,"a";		\
+	.align 2;					\
+952:							\
+	FTR_ENTRY_OFFSET 951b-952b;			\
+	.popsection;
+
+
 #ifndef __ASSEMBLY__
+#include <linux/types.h>
+
+extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
+
 void apply_feature_fixups(void);
 void setup_feature_keys(void);
 #endif
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 8645897472b1..511acfd7ab0d 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -51,6 +51,8 @@
 #define FW_FEATURE_BEST_ENERGY	ASM_CONST(0x0000000080000000)
 #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
 #define FW_FEATURE_PRRN		ASM_CONST(0x0000000200000000)
+#define FW_FEATURE_DRMEM_V2	ASM_CONST(0x0000000400000000)
+#define FW_FEATURE_DRC_INFO	ASM_CONST(0x0000000400000000)
 
 #ifndef __ASSEMBLY__
 
@@ -67,7 +69,8 @@ enum {
 		FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO |
 		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
 		FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN |
-		FW_FEATURE_HPT_RESIZE,
+		FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 |
+		FW_FEATURE_DRC_INFO,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
 	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL,
 	FW_FEATURE_POWERNV_ALWAYS = 0,
diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h
index 456f9e7b8d83..5986d473722b 100644
--- a/arch/powerpc/include/asm/hardirq.h
+++ b/arch/powerpc/include/asm/hardirq.h
@@ -29,6 +29,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 #define local_softirq_pending()	__this_cpu_read(irq_stat.__softirq_pending)
 
 #define __ARCH_SET_SOFTIRQ_PENDING
+#define __ARCH_IRQ_EXIT_IRQS_DISABLED
 
 #define set_softirq_pending(x) __this_cpu_write(irq_stat.__softirq_pending, (x))
 #define or_softirq_pending(x) __this_cpu_or(irq_stat.__softirq_pending, (x))
diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h
index fdcff76e9a25..7e0e93f24cb7 100644
--- a/arch/powerpc/include/asm/head-64.h
+++ b/arch/powerpc/include/asm/head-64.h
@@ -178,7 +178,7 @@ name:
  * TRAMP_REAL_*   - real, unrelocated helpers (virt can call these)
  * TRAMP_VIRT_*   - virt, unreloc helpers (in practice, real can use)
  * TRAMP_KVM      - KVM handlers that get put into real, unrelocated
- * EXC_COMMON_*   - virt, relocated common handlers
+ * EXC_COMMON     - virt, relocated common handlers
  *
  * The EXC handlers are given a name, and branch to name_common, or the
  * appropriate KVM or masking function. Vector handler verieties are as
@@ -211,7 +211,6 @@ name:
  * EXC_COMMON_BEGIN/END - used to open-code the handler
  * EXC_COMMON
  * EXC_COMMON_ASYNC
- * EXC_COMMON_HV
  *
  * TRAMP_REAL and TRAMP_VIRT can be used with BEGIN/END. KVM
  * and OOL handlers are implemented as types of TRAMP and TRAMP_VIRT handlers.
@@ -269,14 +268,14 @@ name:
 	STD_RELON_EXCEPTION_PSERIES(start, realvec, name##_common);	\
 	EXC_VIRT_END(name, start, size);
 
-#define EXC_REAL_MASKABLE(name, start, size)				\
+#define EXC_REAL_MASKABLE(name, start, size, bitmask)			\
 	EXC_REAL_BEGIN(name, start, size);				\
-	MASKABLE_EXCEPTION_PSERIES(start, start, name##_common);	\
+	MASKABLE_EXCEPTION_PSERIES(start, start, name##_common, bitmask);\
 	EXC_REAL_END(name, start, size);
 
-#define EXC_VIRT_MASKABLE(name, start, size, realvec)			\
+#define EXC_VIRT_MASKABLE(name, start, size, realvec, bitmask)		\
 	EXC_VIRT_BEGIN(name, start, size);				\
-	MASKABLE_RELON_EXCEPTION_PSERIES(start, realvec, name##_common); \
+	MASKABLE_RELON_EXCEPTION_PSERIES(start, realvec, name##_common, bitmask);\
 	EXC_VIRT_END(name, start, size);
 
 #define EXC_REAL_HV(name, start, size)					\
@@ -305,13 +304,13 @@ name:
 #define __EXC_REAL_OOL_MASKABLE(name, start, size)			\
 	__EXC_REAL_OOL(name, start, size);
 
-#define __TRAMP_REAL_OOL_MASKABLE(name, vec)				\
+#define __TRAMP_REAL_OOL_MASKABLE(name, vec, bitmask)			\
 	TRAMP_REAL_BEGIN(tramp_real_##name);				\
-	MASKABLE_EXCEPTION_PSERIES_OOL(vec, name##_common);		\
+	MASKABLE_EXCEPTION_PSERIES_OOL(vec, name##_common, bitmask);	\
 
-#define EXC_REAL_OOL_MASKABLE(name, start, size)			\
+#define EXC_REAL_OOL_MASKABLE(name, start, size, bitmask)		\
 	__EXC_REAL_OOL_MASKABLE(name, start, size);			\
-	__TRAMP_REAL_OOL_MASKABLE(name, start);
+	__TRAMP_REAL_OOL_MASKABLE(name, start, bitmask);
 
 #define __EXC_REAL_OOL_HV_DIRECT(name, start, size, handler)		\
 	EXC_REAL_BEGIN(name, start, size);				\
@@ -332,13 +331,13 @@ name:
 #define __EXC_REAL_OOL_MASKABLE_HV(name, start, size)			\
 	__EXC_REAL_OOL(name, start, size);
 
-#define __TRAMP_REAL_OOL_MASKABLE_HV(name, vec)				\
+#define __TRAMP_REAL_OOL_MASKABLE_HV(name, vec, bitmask)		\
 	TRAMP_REAL_BEGIN(tramp_real_##name);				\
-	MASKABLE_EXCEPTION_HV_OOL(vec, name##_common);			\
+	MASKABLE_EXCEPTION_HV_OOL(vec, name##_common, bitmask);		\
 
-#define EXC_REAL_OOL_MASKABLE_HV(name, start, size)			\
+#define EXC_REAL_OOL_MASKABLE_HV(name, start, size, bitmask)		\
 	__EXC_REAL_OOL_MASKABLE_HV(name, start, size);			\
-	__TRAMP_REAL_OOL_MASKABLE_HV(name, start);
+	__TRAMP_REAL_OOL_MASKABLE_HV(name, start, bitmask);
 
 #define __EXC_VIRT_OOL(name, start, size)				\
 	EXC_VIRT_BEGIN(name, start, size);				\
@@ -356,13 +355,13 @@ name:
 #define __EXC_VIRT_OOL_MASKABLE(name, start, size)			\
 	__EXC_VIRT_OOL(name, start, size);
 
-#define __TRAMP_VIRT_OOL_MASKABLE(name, realvec)			\
+#define __TRAMP_VIRT_OOL_MASKABLE(name, realvec, bitmask)		\
 	TRAMP_VIRT_BEGIN(tramp_virt_##name);				\
-	MASKABLE_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common);	\
+	MASKABLE_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common, bitmask);\
 
-#define EXC_VIRT_OOL_MASKABLE(name, start, size, realvec)		\
+#define EXC_VIRT_OOL_MASKABLE(name, start, size, realvec, bitmask)	\
 	__EXC_VIRT_OOL_MASKABLE(name, start, size);			\
-	__TRAMP_VIRT_OOL_MASKABLE(name, realvec);
+	__TRAMP_VIRT_OOL_MASKABLE(name, realvec, bitmask);
 
 #define __EXC_VIRT_OOL_HV(name, start, size)				\
 	__EXC_VIRT_OOL(name, start, size);
@@ -378,13 +377,13 @@ name:
 #define __EXC_VIRT_OOL_MASKABLE_HV(name, start, size)			\
 	__EXC_VIRT_OOL(name, start, size);
 
-#define __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec)			\
+#define __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec, bitmask)		\
 	TRAMP_VIRT_BEGIN(tramp_virt_##name);				\
-	MASKABLE_RELON_EXCEPTION_HV_OOL(realvec, name##_common);	\
+	MASKABLE_RELON_EXCEPTION_HV_OOL(realvec, name##_common, bitmask);\
 
-#define EXC_VIRT_OOL_MASKABLE_HV(name, start, size, realvec)		\
+#define EXC_VIRT_OOL_MASKABLE_HV(name, start, size, realvec, bitmask)	\
 	__EXC_VIRT_OOL_MASKABLE_HV(name, start, size);			\
-	__TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec);
+	__TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec, bitmask);
 
 #define TRAMP_KVM(area, n)						\
 	TRAMP_KVM_BEGIN(do_kvm_##n);					\
@@ -413,10 +412,6 @@ name:
 	EXC_COMMON_BEGIN(name);						\
 	STD_EXCEPTION_COMMON_ASYNC(realvec, name, hdlr);		\
 
-#define EXC_COMMON_HV(name, realvec, hdlr)				\
-	EXC_COMMON_BEGIN(name);						\
-	STD_EXCEPTION_COMMON(realvec + 0x2, name, hdlr);		\
-
 #endif /* __ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_HEAD_64_H */
diff --git a/arch/powerpc/include/asm/hmi.h b/arch/powerpc/include/asm/hmi.h
index 85b7a1a21e22..9c14f7b5c46c 100644
--- a/arch/powerpc/include/asm/hmi.h
+++ b/arch/powerpc/include/asm/hmi.h
@@ -42,4 +42,8 @@ extern void wait_for_tb_resync(void);
 static inline void wait_for_subcore_guest_exit(void) { }
 static inline void wait_for_tb_resync(void) { }
 #endif
+
+struct pt_regs;
+extern long hmi_handle_debugtrig(struct pt_regs *regs);
+
 #endif /* __ASM_PPC64_HMI_H__ */
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 14c9d44f355b..1a4847f67ea8 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -47,8 +47,7 @@ static inline pte_t *hugepd_page(hugepd_t hpd)
 {
 	BUG_ON(!hugepd_ok(hpd));
 #ifdef CONFIG_PPC_8xx
-	return (pte_t *)__va(hpd_val(hpd) &
-			     ~(_PMD_PAGE_MASK | _PMD_PRESENT_MASK));
+	return (pte_t *)__va(hpd_val(hpd) & ~HUGEPD_SHIFT_MASK);
 #else
 	return (pte_t *)((hpd_val(hpd) &
 			  ~HUGEPD_SHIFT_MASK) | PD_HUGE);
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index a409177be8bd..eca3f9c68907 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -241,6 +241,7 @@
 #define H_GET_HCA_INFO          0x1B8
 #define H_GET_PERF_COUNT        0x1BC
 #define H_MANAGE_TRACE          0x1C0
+#define H_GET_CPU_CHARACTERISTICS 0x1C8
 #define H_FREE_LOGICAL_LAN_BUFFER 0x1D4
 #define H_QUERY_INT_STATE       0x1E4
 #define H_POLL_PENDING		0x1D8
@@ -330,6 +331,17 @@
 #define H_SIGNAL_SYS_RESET_ALL_OTHERS		-2
 /* >= 0 values are CPU number */
 
+/* H_GET_CPU_CHARACTERISTICS return values */
+#define H_CPU_CHAR_SPEC_BAR_ORI31	(1ull << 63) // IBM bit 0
+#define H_CPU_CHAR_BCCTRL_SERIALISED	(1ull << 62) // IBM bit 1
+#define H_CPU_CHAR_L1D_FLUSH_ORI30	(1ull << 61) // IBM bit 2
+#define H_CPU_CHAR_L1D_FLUSH_TRIG2	(1ull << 60) // IBM bit 3
+#define H_CPU_CHAR_L1D_THREAD_PRIV	(1ull << 59) // IBM bit 4
+
+#define H_CPU_BEHAV_FAVOUR_SECURITY	(1ull << 63) // IBM bit 0
+#define H_CPU_BEHAV_L1D_FLUSH_PR	(1ull << 62) // IBM bit 1
+#define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ull << 61) // IBM bit 2
+
 /* Flag values used in H_REGISTER_PROC_TBL hcall */
 #define PROC_TABLE_OP_MASK	0x18
 #define PROC_TABLE_DEREG	0x10
@@ -341,6 +353,7 @@
 #define PROC_TABLE_GTSE		0x01
 
 #ifndef __ASSEMBLY__
+#include <linux/types.h>
 
 /**
  * plpar_hcall_norets: - Make a pseries hypervisor call with no return arguments
@@ -436,6 +449,11 @@ static inline unsigned int get_longbusy_msecs(int longbusy_rc)
 	}
 }
 
+struct h_cpu_char_result {
+	u64 character;
+	u64 behaviour;
+};
+
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_HVCALL_H */
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 3818fa0164f0..88e5e8f17e98 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -27,6 +27,15 @@
 #define PACA_IRQ_DEC		0x08 /* Or FIT */
 #define PACA_IRQ_EE_EDGE	0x10 /* BookE only */
 #define PACA_IRQ_HMI		0x20
+#define PACA_IRQ_PMI		0x40
+
+/*
+ * flags for paca->irq_soft_mask
+ */
+#define IRQS_ENABLED		0
+#define IRQS_DISABLED		1 /* local_irq_disable() interrupts */
+#define IRQS_PMI_DISABLED	2
+#define IRQS_ALL_DISABLED	(IRQS_DISABLED | IRQS_PMI_DISABLED)
 
 #endif /* CONFIG_PPC64 */
 
@@ -43,46 +52,112 @@ extern void unknown_exception(struct pt_regs *regs);
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 
-static inline unsigned long arch_local_save_flags(void)
+static inline notrace unsigned long irq_soft_mask_return(void)
 {
 	unsigned long flags;
 
 	asm volatile(
 		"lbz %0,%1(13)"
 		: "=r" (flags)
-		: "i" (offsetof(struct paca_struct, soft_enabled)));
+		: "i" (offsetof(struct paca_struct, irq_soft_mask)));
+
+	return flags;
+}
+
+/*
+ * The "memory" clobber acts as both a compiler barrier
+ * for the critical section and as a clobber because
+ * we changed paca->irq_soft_mask
+ */
+static inline notrace void irq_soft_mask_set(unsigned long mask)
+{
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+	/*
+	 * The irq mask must always include the STD bit if any are set.
+	 *
+	 * and interrupts don't get replayed until the standard
+	 * interrupt (local_irq_disable()) is unmasked.
+	 *
+	 * Other masks must only provide additional masking beyond
+	 * the standard, and they are also not replayed until the
+	 * standard interrupt becomes unmasked.
+	 *
+	 * This could be changed, but it will require partial
+	 * unmasks to be replayed, among other things. For now, take
+	 * the simple approach.
+	 */
+	WARN_ON(mask && !(mask & IRQS_DISABLED));
+#endif
+
+	asm volatile(
+		"stb %0,%1(13)"
+		:
+		: "r" (mask),
+		  "i" (offsetof(struct paca_struct, irq_soft_mask))
+		: "memory");
+}
+
+static inline notrace unsigned long irq_soft_mask_set_return(unsigned long mask)
+{
+	unsigned long flags;
+
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+	WARN_ON(mask && !(mask & IRQS_DISABLED));
+#endif
+
+	asm volatile(
+		"lbz %0,%1(13); stb %2,%1(13)"
+		: "=&r" (flags)
+		: "i" (offsetof(struct paca_struct, irq_soft_mask)),
+		  "r" (mask)
+		: "memory");
 
 	return flags;
 }
 
-static inline unsigned long arch_local_irq_disable(void)
+static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask)
 {
-	unsigned long flags, zero;
+	unsigned long flags, tmp;
 
 	asm volatile(
-		"li %1,0; lbz %0,%2(13); stb %1,%2(13)"
-		: "=r" (flags), "=&r" (zero)
-		: "i" (offsetof(struct paca_struct, soft_enabled))
+		"lbz %0,%2(13); or %1,%0,%3; stb %1,%2(13)"
+		: "=&r" (flags), "=r" (tmp)
+		: "i" (offsetof(struct paca_struct, irq_soft_mask)),
+		  "r" (mask)
 		: "memory");
 
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+	WARN_ON((mask | flags) && !((mask | flags) & IRQS_DISABLED));
+#endif
+
 	return flags;
 }
 
+static inline unsigned long arch_local_save_flags(void)
+{
+	return irq_soft_mask_return();
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	irq_soft_mask_set(IRQS_DISABLED);
+}
+
 extern void arch_local_irq_restore(unsigned long);
 
 static inline void arch_local_irq_enable(void)
 {
-	arch_local_irq_restore(1);
+	arch_local_irq_restore(IRQS_ENABLED);
 }
 
 static inline unsigned long arch_local_irq_save(void)
 {
-	return arch_local_irq_disable();
+	return irq_soft_mask_set_return(IRQS_DISABLED);
 }
 
 static inline bool arch_irqs_disabled_flags(unsigned long flags)
 {
-	return flags == 0;
+	return flags & IRQS_DISABLED;
 }
 
 static inline bool arch_irqs_disabled(void)
@@ -90,6 +165,55 @@ static inline bool arch_irqs_disabled(void)
 	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
 
+#ifdef CONFIG_PPC_BOOK3S
+/*
+ * To support disabling and enabling of irq with PMI, set of
+ * new powerpc_local_irq_pmu_save() and powerpc_local_irq_restore()
+ * functions are added. These macros are implemented using generic
+ * linux local_irq_* code from include/linux/irqflags.h.
+ */
+#define raw_local_irq_pmu_save(flags)					\
+	do {								\
+		typecheck(unsigned long, flags);			\
+		flags = irq_soft_mask_or_return(IRQS_DISABLED |	\
+				IRQS_PMI_DISABLED);			\
+	} while(0)
+
+#define raw_local_irq_pmu_restore(flags)				\
+	do {								\
+		typecheck(unsigned long, flags);			\
+		arch_local_irq_restore(flags);				\
+	} while(0)
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+#define powerpc_local_irq_pmu_save(flags)			\
+	 do {							\
+		raw_local_irq_pmu_save(flags);			\
+		trace_hardirqs_off();				\
+	} while(0)
+#define powerpc_local_irq_pmu_restore(flags)			\
+	do {							\
+		if (raw_irqs_disabled_flags(flags)) {		\
+			raw_local_irq_pmu_restore(flags);	\
+			trace_hardirqs_off();			\
+		} else {					\
+			trace_hardirqs_on();			\
+			raw_local_irq_pmu_restore(flags);	\
+		}						\
+	} while(0)
+#else
+#define powerpc_local_irq_pmu_save(flags)			\
+	do {							\
+		raw_local_irq_pmu_save(flags);			\
+	} while(0)
+#define powerpc_local_irq_pmu_restore(flags)			\
+	do {							\
+		raw_local_irq_pmu_restore(flags);		\
+	} while (0)
+#endif  /* CONFIG_TRACE_IRQFLAGS */
+
+#endif /* CONFIG_PPC_BOOK3S */
+
 #ifdef CONFIG_PPC_BOOK3E
 #define __hard_irq_enable()	asm volatile("wrteei 1" : : : "memory")
 #define __hard_irq_disable()	asm volatile("wrteei 0" : : : "memory")
@@ -98,14 +222,13 @@ static inline bool arch_irqs_disabled(void)
 #define __hard_irq_disable()	__mtmsrd(local_paca->kernel_msr, 1)
 #endif
 
-#define hard_irq_disable()	do {			\
-	u8 _was_enabled;				\
-	__hard_irq_disable();				\
-	_was_enabled = local_paca->soft_enabled;	\
-	local_paca->soft_enabled = 0;			\
-	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;	\
-	if (_was_enabled)				\
-		trace_hardirqs_off();			\
+#define hard_irq_disable()	do {					\
+	unsigned long flags;						\
+	__hard_irq_disable();						\
+	flags = irq_soft_mask_set_return(IRQS_ALL_DISABLED);		\
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;			\
+	if (!arch_irqs_disabled_flags(flags))				\
+		trace_hardirqs_off();					\
 } while(0)
 
 static inline bool lazy_irq_pending(void)
@@ -127,7 +250,7 @@ static inline void may_hard_irq_enable(void)
 
 static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
 {
-	return !regs->softe;
+	return (regs->softe & IRQS_DISABLED);
 }
 
 extern bool prep_irq_for_idle(void);
diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h
index fad0e6ff460f..d76cb11be3e3 100644
--- a/arch/powerpc/include/asm/imc-pmu.h
+++ b/arch/powerpc/include/asm/imc-pmu.h
@@ -35,6 +35,13 @@
 #define THREAD_IMC_ENABLE               0x8000000000000000ULL
 
 /*
+ * For debugfs interface for imc-mode and imc-command
+ */
+#define IMC_CNTL_BLK_OFFSET		0x3FC00
+#define IMC_CNTL_BLK_CMD_OFFSET		8
+#define IMC_CNTL_BLK_MODE_OFFSET	32
+
+/*
  * Structure to hold memory address information for imc units.
  */
 struct imc_mem_info {
@@ -71,7 +78,7 @@ struct imc_events {
 struct imc_pmu {
 	struct pmu pmu;
 	struct imc_mem_info *mem_info;
-	struct imc_events **events;
+	struct imc_events *events;
 	/*
 	 * Attribute groups for the PMU. Slot 0 used for
 	 * format attribute, slot 1 used for cpusmask attribute,
diff --git a/arch/powerpc/include/asm/irqflags.h b/arch/powerpc/include/asm/irqflags.h
index 1aeb5f13b8c4..1a6c1ce17735 100644
--- a/arch/powerpc/include/asm/irqflags.h
+++ b/arch/powerpc/include/asm/irqflags.h
@@ -47,14 +47,14 @@
  * be clobbered.
  */
 #define RECONCILE_IRQ_STATE(__rA, __rB)		\
-	lbz	__rA,PACASOFTIRQEN(r13);	\
+	lbz	__rA,PACAIRQSOFTMASK(r13);	\
 	lbz	__rB,PACAIRQHAPPENED(r13);	\
-	cmpwi	cr0,__rA,0;			\
-	li	__rA,0;				\
+	andi.	__rA,__rA,IRQS_DISABLED;	\
+	li	__rA,IRQS_DISABLED;		\
 	ori	__rB,__rB,PACA_IRQ_HARD_DIS;	\
 	stb	__rB,PACAIRQHAPPENED(r13);	\
-	beq	44f;				\
-	stb	__rA,PACASOFTIRQEN(r13);	\
+	bne	44f;				\
+	stb	__rA,PACAIRQSOFTMASK(r13);	\
 	TRACE_DISABLE_INTS;			\
 44:
 
@@ -64,9 +64,9 @@
 
 #define RECONCILE_IRQ_STATE(__rA, __rB)		\
 	lbz	__rA,PACAIRQHAPPENED(r13);	\
-	li	__rB,0;				\
+	li	__rB,IRQS_DISABLED;		\
 	ori	__rA,__rA,PACA_IRQ_HARD_DIS;	\
-	stb	__rB,PACASOFTIRQEN(r13);	\
+	stb	__rB,PACAIRQSOFTMASK(r13);	\
 	stb	__rA,PACAIRQHAPPENED(r13)
 #endif
 #endif
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 4419d435639a..9dcbfa6bbb91 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -73,6 +73,8 @@ extern void kexec_smp_wait(void);	/* get and clear naca physid, wait for
 					  master to copy new code to 0 */
 extern int crashing_cpu;
 extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *));
+extern void crash_ipi_callback(struct pt_regs *);
+extern int crash_wake_offline;
 
 struct kimage;
 struct pt_regs;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 96753f3aac6d..9db18287b5f4 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -180,6 +180,7 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
 		struct iommu_group *grp);
 extern int kvmppc_switch_mmu_to_hpt(struct kvm *kvm);
 extern int kvmppc_switch_mmu_to_radix(struct kvm *kvm);
+extern void kvmppc_setup_partition_table(struct kvm *kvm);
 
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce_64 *args);
@@ -872,7 +873,7 @@ static inline void kvmppc_fix_ee_before_entry(void)
 
 	/* Only need to enable IRQs by hard enabling them after this */
 	local_paca->irq_happened = 0;
-	local_paca->soft_enabled = 1;
+	irq_soft_mask_set(IRQS_ENABLED);
 #endif
 }
 
diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h
index 600a68bd77f5..fdd00939270b 100644
--- a/arch/powerpc/include/asm/local.h
+++ b/arch/powerpc/include/asm/local.h
@@ -2,76 +2,64 @@
 #ifndef _ARCH_POWERPC_LOCAL_H
 #define _ARCH_POWERPC_LOCAL_H
 
+#ifdef CONFIG_PPC_BOOK3S_64
+
 #include <linux/percpu.h>
 #include <linux/atomic.h>
+#include <linux/irqflags.h>
+
+#include <asm/hw_irq.h>
 
 typedef struct
 {
-	atomic_long_t a;
+	long v;
 } local_t;
 
-#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
-
-#define local_read(l)	atomic_long_read(&(l)->a)
-#define local_set(l,i)	atomic_long_set(&(l)->a, (i))
+#define LOCAL_INIT(i)	{ (i) }
 
-#define local_add(i,l)	atomic_long_add((i),(&(l)->a))
-#define local_sub(i,l)	atomic_long_sub((i),(&(l)->a))
-#define local_inc(l)	atomic_long_inc(&(l)->a)
-#define local_dec(l)	atomic_long_dec(&(l)->a)
-
-static __inline__ long local_add_return(long a, local_t *l)
+static __inline__ long local_read(local_t *l)
 {
-	long t;
-
-	__asm__ __volatile__(
-"1:"	PPC_LLARX(%0,0,%2,0) "			# local_add_return\n\
-	add	%0,%1,%0\n"
-	PPC405_ERR77(0,%2)
-	PPC_STLCX	"%0,0,%2 \n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (a), "r" (&(l->a.counter))
-	: "cc", "memory");
-
-	return t;
+	return READ_ONCE(l->v);
 }
 
-#define local_add_negative(a, l)	(local_add_return((a), (l)) < 0)
-
-static __inline__ long local_sub_return(long a, local_t *l)
+static __inline__ void local_set(local_t *l, long i)
 {
-	long t;
+	WRITE_ONCE(l->v, i);
+}
 
-	__asm__ __volatile__(
-"1:"	PPC_LLARX(%0,0,%2,0) "			# local_sub_return\n\
-	subf	%0,%1,%0\n"
-	PPC405_ERR77(0,%2)
-	PPC_STLCX	"%0,0,%2 \n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (a), "r" (&(l->a.counter))
-	: "cc", "memory");
+#define LOCAL_OP(op, c_op)						\
+static __inline__ void local_##op(long i, local_t *l)			\
+{									\
+	unsigned long flags;						\
+									\
+	powerpc_local_irq_pmu_save(flags);				\
+	l->v c_op i;						\
+	powerpc_local_irq_pmu_restore(flags);				\
+}
 
-	return t;
+#define LOCAL_OP_RETURN(op, c_op)					\
+static __inline__ long local_##op##_return(long a, local_t *l)		\
+{									\
+	long t;								\
+	unsigned long flags;						\
+									\
+	powerpc_local_irq_pmu_save(flags);				\
+	t = (l->v c_op a);						\
+	powerpc_local_irq_pmu_restore(flags);				\
+									\
+	return t;							\
 }
 
-static __inline__ long local_inc_return(local_t *l)
-{
-	long t;
+#define LOCAL_OPS(op, c_op)		\
+	LOCAL_OP(op, c_op)		\
+	LOCAL_OP_RETURN(op, c_op)
 
-	__asm__ __volatile__(
-"1:"	PPC_LLARX(%0,0,%1,0) "			# local_inc_return\n\
-	addic	%0,%0,1\n"
-	PPC405_ERR77(0,%1)
-	PPC_STLCX	"%0,0,%1 \n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (&(l->a.counter))
-	: "cc", "xer", "memory");
+LOCAL_OPS(add, +=)
+LOCAL_OPS(sub, -=)
 
-	return t;
-}
+#define local_add_negative(a, l)	(local_add_return((a), (l)) < 0)
+#define local_inc_return(l)		local_add_return(1LL, l)
+#define local_inc(l)			local_inc_return(l)
 
 /*
  * local_inc_and_test - increment and test
@@ -81,28 +69,39 @@ static __inline__ long local_inc_return(local_t *l)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-#define local_inc_and_test(l) (local_inc_return(l) == 0)
+#define local_inc_and_test(l)		(local_inc_return(l) == 0)
 
-static __inline__ long local_dec_return(local_t *l)
+#define local_dec_return(l)		local_sub_return(1LL, l)
+#define local_dec(l)			local_dec_return(l)
+#define local_sub_and_test(a, l)	(local_sub_return((a), (l)) == 0)
+#define local_dec_and_test(l)		(local_dec_return((l)) == 0)
+
+static __inline__ long local_cmpxchg(local_t *l, long o, long n)
 {
 	long t;
+	unsigned long flags;
 
-	__asm__ __volatile__(
-"1:"	PPC_LLARX(%0,0,%1,0) "			# local_dec_return\n\
-	addic	%0,%0,-1\n"
-	PPC405_ERR77(0,%1)
-	PPC_STLCX	"%0,0,%1\n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (&(l->a.counter))
-	: "cc", "xer", "memory");
+	powerpc_local_irq_pmu_save(flags);
+	t = l->v;
+	if (t == o)
+		l->v = n;
+	powerpc_local_irq_pmu_restore(flags);
 
 	return t;
 }
 
-#define local_cmpxchg(l, o, n) \
-	(cmpxchg_local(&((l)->a.counter), (o), (n)))
-#define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n)))
+static __inline__ long local_xchg(local_t *l, long n)
+{
+	long t;
+	unsigned long flags;
+
+	powerpc_local_irq_pmu_save(flags);
+	t = l->v;
+	l->v = n;
+	powerpc_local_irq_pmu_restore(flags);
+
+	return t;
+}
 
 /**
  * local_add_unless - add unless the number is a given value
@@ -115,62 +114,35 @@ static __inline__ long local_dec_return(local_t *l)
  */
 static __inline__ int local_add_unless(local_t *l, long a, long u)
 {
-	long t;
-
-	__asm__ __volatile__ (
-"1:"	PPC_LLARX(%0,0,%1,0) "			# local_add_unless\n\
-	cmpw	0,%0,%3 \n\
-	beq-	2f \n\
-	add	%0,%2,%0 \n"
-	PPC405_ERR77(0,%2)
-	PPC_STLCX	"%0,0,%1 \n\
-	bne-	1b \n"
-"	subf	%0,%2,%0 \n\
-2:"
-	: "=&r" (t)
-	: "r" (&(l->a.counter)), "r" (a), "r" (u)
-	: "cc", "memory");
-
-	return t != u;
-}
-
-#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
-
-#define local_sub_and_test(a, l)	(local_sub_return((a), (l)) == 0)
-#define local_dec_and_test(l)		(local_dec_return((l)) == 0)
-
-/*
- * Atomically test *l and decrement if it is greater than 0.
- * The function returns the old value of *l minus 1.
- */
-static __inline__ long local_dec_if_positive(local_t *l)
-{
-	long t;
+	unsigned long flags;
+	int ret = 0;
 
-	__asm__ __volatile__(
-"1:"	PPC_LLARX(%0,0,%1,0) "			# local_dec_if_positive\n\
-	cmpwi	%0,1\n\
-	addi	%0,%0,-1\n\
-	blt-	2f\n"
-	PPC405_ERR77(0,%1)
-	PPC_STLCX	"%0,0,%1\n\
-	bne-	1b"
-	"\n\
-2:"	: "=&b" (t)
-	: "r" (&(l->a.counter))
-	: "cc", "memory");
+	powerpc_local_irq_pmu_save(flags);
+	if (l->v != u) {
+		l->v += a;
+		ret = 1;
+	}
+	powerpc_local_irq_pmu_restore(flags);
 
-	return t;
+	return ret;
 }
 
+#define local_inc_not_zero(l)		local_add_unless((l), 1, 0)
+
 /* Use these for per-cpu local_t variables: on some archs they are
  * much more efficient than these naive implementations.  Note they take
  * a variable, not an address.
  */
 
-#define __local_inc(l)		((l)->a.counter++)
-#define __local_dec(l)		((l)->a.counter++)
-#define __local_add(i,l)	((l)->a.counter+=(i))
-#define __local_sub(i,l)	((l)->a.counter-=(i))
+#define __local_inc(l)		((l)->v++)
+#define __local_dec(l)		((l)->v++)
+#define __local_add(i,l)	((l)->v+=(i))
+#define __local_sub(i,l)	((l)->v-=(i))
+
+#else /* CONFIG_PPC64 */
+
+#include <asm-generic/local.h>
+
+#endif /* CONFIG_PPC64 */
 
 #endif /* _ARCH_POWERPC_LOCAL_H */
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 73b92017b6d7..ffe7c71e1132 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -76,6 +76,7 @@ struct machdep_calls {
 
 	void __noreturn	(*restart)(char *cmd);
 	void __noreturn (*halt)(void);
+	void		(*panic)(char *str);
 	void		(*cpu_die)(void);
 
 	long		(*time_init)(void); /* Optional, may be NULL */
@@ -172,11 +173,19 @@ struct machdep_calls {
 	/* Called after scan and before resource survey */
 	void (*pcibios_fixup_phb)(struct pci_controller *hose);
 
+	/*
+	 * Called after device has been added to bus and
+	 * before sysfs has been created.
+	 */
+	void (*pcibios_bus_add_device)(struct pci_dev *pdev);
+
 	resource_size_t (*pcibios_default_alignment)(void);
 
 #ifdef CONFIG_PCI_IOV
 	void (*pcibios_fixup_sriov)(struct pci_dev *pdev);
 	resource_size_t (*pcibios_iov_resource_alignment)(struct pci_dev *, int resno);
+	int (*pcibios_sriov_enable)(struct pci_dev *pdev, u16 num_vfs);
+	int (*pcibios_sriov_disable)(struct pci_dev *pdev);
 #endif /* CONFIG_PCI_IOV */
 
 	/* Called to shutdown machine specific hardware not already controlled
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index 30922f699341..07e3f54de9e3 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -13,6 +13,7 @@
 
 #include <asm/cputable.h>
 #include <linux/mm.h>
+#include <linux/pkeys.h>
 #include <asm/cpu_has_feature.h>
 
 /*
@@ -22,13 +23,23 @@
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 		unsigned long pkey)
 {
-	return (prot & PROT_SAO) ? VM_SAO : 0;
+#ifdef CONFIG_PPC_MEM_KEYS
+	return (((prot & PROT_SAO) ? VM_SAO : 0) | pkey_to_vmflag_bits(pkey));
+#else
+	return ((prot & PROT_SAO) ? VM_SAO : 0);
+#endif
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
 static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
 {
+#ifdef CONFIG_PPC_MEM_KEYS
+	return (vm_flags & VM_SAO) ?
+		__pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) :
+		__pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags));
+#else
 	return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0);
+#endif
 }
 #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
 
diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h
index 5bb3dbede41a..2f806e329648 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/mmu-8xx.h
@@ -29,17 +29,25 @@
 #define MI_Kp		0x40000000	/* Should always be set */
 
 /*
- * All pages' PP exec bits are set to 000, which means Execute for Supervisor
- * and no Execute for User.
- * Then we use the APG to say whether accesses are according to Page rules,
- * "all Supervisor" rules (Exec for all) and "all User" rules (Exec for noone)
- * Therefore, we define 4 APG groups. msb is _PAGE_EXEC, lsb is _PAGE_USER
- * 0 (00) => Not User, no exec => 11 (all accesses performed as user)
- * 1 (01) => User but no exec => 11 (all accesses performed as user)
- * 2 (10) => Not User, exec => 01 (rights according to page definition)
- * 3 (11) => User, exec => 00 (all accesses performed as supervisor)
- */
-#define MI_APG_INIT	0xf4ffffff
+ * All pages' PP data bits are set to either 001 or 011 by copying _PAGE_EXEC
+ * into bit 21 in the ITLBmiss handler (bit 21 is the middle bit), which means
+ * respectively NA for All or X for Supervisor and no access for User.
+ * Then we use the APG to say whether accesses are according to Page rules or
+ * "all Supervisor" rules (Access to all)
+ * We also use the 2nd APG bit for _PAGE_ACCESSED when having SWAP:
+ * When that bit is not set access is done iaw "all user"
+ * which means no access iaw page rules.
+ * Therefore, we define 4 APG groups. lsb is _PMD_USER, 2nd is _PAGE_ACCESSED
+ * 0x => No access => 11 (all accesses performed as user iaw page definition)
+ * 10 => No user => 01 (all accesses performed according to page definition)
+ * 11 => User => 00 (all accesses performed as supervisor iaw page definition)
+ * We define all 16 groups so that all other bits of APG can take any value
+ */
+#ifdef CONFIG_SWAP
+#define MI_APG_INIT	0xf4f4f4f4
+#else
+#define MI_APG_INIT	0x44444444
+#endif
 
 /* The effective page number register.  When read, contains the information
  * about the last instruction TLB miss.  When MI_RPN is written, bits in
@@ -102,17 +110,25 @@
 #define MD_Kp		0x40000000	/* Should always be set */
 
 /*
- * All pages' PP data bits are set to either 000 or 011, which means
+ * All pages' PP data bits are set to either 000 or 011 or 001, which means
  * respectively RW for Supervisor and no access for User, or RO for
- * Supervisor and no access for user.
+ * Supervisor and no access for user and NA for ALL.
  * Then we use the APG to say whether accesses are according to Page rules or
  * "all Supervisor" rules (Access to all)
- * Therefore, we define 2 APG groups. lsb is _PAGE_USER
- * 0 => No user => 01 (all accesses performed according to page definition)
- * 1 => User => 00 (all accesses performed as supervisor
- *                                 according to page definition)
- */
-#define MD_APG_INIT	0x4fffffff
+ * We also use the 2nd APG bit for _PAGE_ACCESSED when having SWAP:
+ * When that bit is not set access is done iaw "all user"
+ * which means no access iaw page rules.
+ * Therefore, we define 4 APG groups. lsb is _PMD_USER, 2nd is _PAGE_ACCESSED
+ * 0x => No access => 11 (all accesses performed as user iaw page definition)
+ * 10 => No user => 01 (all accesses performed according to page definition)
+ * 11 => User => 00 (all accesses performed as supervisor iaw page definition)
+ * We define all 16 groups so that all other bits of APG can take any value
+ */
+#ifdef CONFIG_SWAP
+#define MD_APG_INIT	0xf4f4f4f4
+#else
+#define MD_APG_INIT	0x44444444
+#endif
 
 /* The effective page number register.  When read, contains the information
  * about the last instruction TLB miss.  When MD_RPN is written, bits in
@@ -164,6 +180,12 @@
  */
 #define SPRN_M_TW	799
 
+/* APGs */
+#define M_APG0		0x00000000
+#define M_APG1		0x00000020
+#define M_APG2		0x00000040
+#define M_APG3		0x00000060
+
 #ifndef __ASSEMBLY__
 typedef struct {
 	unsigned int id;
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 6364f5c2cc3e..bb38312cff28 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -260,6 +260,15 @@ static inline bool early_radix_enabled(void)
 }
 #endif
 
+#ifdef CONFIG_PPC_MEM_KEYS
+extern u16 get_mm_addr_key(struct mm_struct *mm, unsigned long address);
+#else
+static inline u16 get_mm_addr_key(struct mm_struct *mm, unsigned long address)
+{
+	return 0;
+}
+#endif /* CONFIG_PPC_MEM_KEYS */
+
 #endif /* !__ASSEMBLY__ */
 
 /* The kernel use the constants below to index in the page sizes array.
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 6177d43f0ce8..051b3d63afe3 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -160,9 +160,10 @@ static inline void enter_lazy_tlb(struct mm_struct *mm,
 #endif
 }
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+				struct mm_struct *mm)
 {
+	return 0;
 }
 
 #ifndef CONFIG_PPC_BOOK3S_64
@@ -186,11 +187,33 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 {
 }
 
+#ifdef CONFIG_PPC_MEM_KEYS
+bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
+			       bool execute, bool foreign);
+#else /* CONFIG_PPC_MEM_KEYS */
 static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 		bool write, bool execute, bool foreign)
 {
 	/* by default, allow everything */
 	return true;
 }
+
+#define pkey_mm_init(mm)
+#define thread_pkey_regs_save(thread)
+#define thread_pkey_regs_restore(new_thread, old_thread)
+#define thread_pkey_regs_init(thread)
+
+static inline int vma_pkey(struct vm_area_struct *vma)
+{
+	return 0;
+}
+
+static inline u64 pte_to_hpte_pkey_bits(u64 pteflags)
+{
+	return 0x0UL;
+}
+
+#endif /* CONFIG_PPC_MEM_KEYS */
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_MMU_CONTEXT_H */
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index 6c0132c7212f..7e28442827f1 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -45,6 +45,9 @@ struct mod_arch_specific {
 	unsigned long tramp;
 #endif
 
+	/* For module function descriptor dereference */
+	unsigned long start_opd;
+	unsigned long end_opd;
 #else /* powerpc64 */
 	/* Indices of PLT sections within module. */
 	unsigned int core_plt_section;
diff --git a/arch/powerpc/include/asm/mpic_timer.h b/arch/powerpc/include/asm/mpic_timer.h
index 0e23cd4ac8aa..13e6702ec458 100644
--- a/arch/powerpc/include/asm/mpic_timer.h
+++ b/arch/powerpc/include/asm/mpic_timer.h
@@ -29,17 +29,17 @@ struct mpic_timer {
 
 #ifdef CONFIG_MPIC_TIMER
 struct mpic_timer *mpic_request_timer(irq_handler_t fn,  void *dev,
-		const struct timeval *time);
+		time64_t time);
 void mpic_start_timer(struct mpic_timer *handle);
 void mpic_stop_timer(struct mpic_timer *handle);
-void mpic_get_remain_time(struct mpic_timer *handle, struct timeval *time);
+void mpic_get_remain_time(struct mpic_timer *handle, time64_t *time);
 void mpic_free_timer(struct mpic_timer *handle);
 #else
 struct mpic_timer *mpic_request_timer(irq_handler_t fn,  void *dev,
-		const struct timeval *time) { return NULL; }
+		time64_t time) { return NULL; }
 void mpic_start_timer(struct mpic_timer *handle) { }
 void mpic_stop_timer(struct mpic_timer *handle) { }
-void mpic_get_remain_time(struct mpic_timer *handle, struct timeval *time) { }
+void mpic_get_remain_time(struct mpic_timer *handle, time64_t *time) { }
 void mpic_free_timer(struct mpic_timer *handle) { }
 #endif
 
diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h
index e97f58689ca7..9c80939b4d14 100644
--- a/arch/powerpc/include/asm/nmi.h
+++ b/arch/powerpc/include/asm/nmi.h
@@ -4,10 +4,6 @@
 
 #ifdef CONFIG_PPC_WATCHDOG
 extern void arch_touch_nmi_watchdog(void);
-extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
-					   bool exclude_self);
-#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
-
 #else
 static inline void arch_touch_nmi_watchdog(void) {}
 #endif
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index d072139ff2e5..29d37bd1f3b3 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -61,7 +61,8 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp,
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
 				pgtable_t pte_page)
 {
-	*pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_PRESENT);
+	*pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_USER |
+		      _PMD_PRESENT);
 }
 
 #define pmd_pgtable(pmd) pmd_page(pmd)
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index cc2bfec3aa3b..504a3c36ce5c 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -282,7 +282,7 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm,
 {
 	unsigned long set = pte_val(entry) &
 		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
-	unsigned long clr = ~pte_val(entry) & _PAGE_RO;
+	unsigned long clr = ~pte_val(entry) & (_PAGE_RO | _PAGE_NA);
 
 	pte_update(ptep, clr, set);
 }
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index 6dc0180fd5c7..f04cb46ae8a1 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -31,37 +31,34 @@
 /* Definitions for 8xx embedded chips. */
 #define _PAGE_PRESENT	0x0001	/* Page is valid */
 #define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
-#define _PAGE_SHARED	0x0004	/* No ASID (context) compare */
-#define _PAGE_SPECIAL	0x0008	/* SW entry, forced to 0 by the TLB miss */
+#define _PAGE_PRIVILEGED	0x0004	/* No ASID (context) compare */
+#define _PAGE_HUGE	0x0008	/* SPS: Small Page Size (1 if 16k, 512k or 8M)*/
 #define _PAGE_DIRTY	0x0100	/* C: page changed */
 
 /* These 4 software bits must be masked out when the L2 entry is loaded
  * into the TLB.
  */
 #define _PAGE_GUARDED	0x0010	/* Copied to L1 G entry in DTLB */
-#define _PAGE_USER	0x0020	/* Copied to L1 APG lsb */
-#define _PAGE_EXEC	0x0040	/* Copied to L1 APG */
-#define _PAGE_WRITETHRU	0x0080	/* software: caching is write through */
-#define _PAGE_ACCESSED	0x0800	/* software: page referenced */
+#define _PAGE_SPECIAL	0x0020	/* SW entry */
+#define _PAGE_EXEC	0x0040	/* Copied to PP (bit 21) in ITLB */
+#define _PAGE_ACCESSED	0x0080	/* software: page referenced */
 
+#define _PAGE_NA	0x0200	/* Supervisor NA, User no access */
 #define _PAGE_RO	0x0600	/* Supervisor RO, User no access */
 
 #define _PMD_PRESENT	0x0001
-#define _PMD_BAD	0x0ff0
+#define _PMD_BAD	0x0fd0
 #define _PMD_PAGE_MASK	0x000c
 #define _PMD_PAGE_8M	0x000c
 #define _PMD_PAGE_512K	0x0004
+#define _PMD_USER	0x0020	/* APG 1 */
 
 /* Until my rework is finished, 8xx still needs atomic PTE updates */
 #define PTE_ATOMIC_UPDATES	1
 
-/* We need to add _PAGE_SHARED to kernel pages */
-#define _PAGE_KERNEL_RO		(_PAGE_SHARED | _PAGE_RO)
-#define _PAGE_KERNEL_ROX	(_PAGE_SHARED | _PAGE_RO | _PAGE_EXEC)
-#define _PAGE_KERNEL_RW		(_PAGE_SHARED | _PAGE_DIRTY | _PAGE_RW | \
-				 _PAGE_HWWRITE)
-#define _PAGE_KERNEL_RWX	(_PAGE_SHARED | _PAGE_DIRTY | _PAGE_RW | \
-				 _PAGE_HWWRITE | _PAGE_EXEC)
+#ifdef CONFIG_PPC_16K_PAGES
+#define _PAGE_PSIZE	_PAGE_HUGE
+#endif
 
 #endif /* __KERNEL__ */
 #endif /*  _ASM_POWERPC_NOHASH_32_PTE_8xx_H */
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 5c68f4a59f75..c56de1e8026f 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -45,6 +45,29 @@ static inline int pte_present(pte_t pte)
 	return pte_val(pte) & _PAGE_PRESENT;
 }
 
+/*
+ * We only find page table entry in the last level
+ * Hence no need for other accessors
+ */
+#define pte_access_permitted pte_access_permitted
+static inline bool pte_access_permitted(pte_t pte, bool write)
+{
+	unsigned long pteval = pte_val(pte);
+	/*
+	 * A read-only access is controlled by _PAGE_USER bit.
+	 * We have _PAGE_READ set for WRITE and EXECUTE
+	 */
+	unsigned long need_pte_bits = _PAGE_PRESENT | _PAGE_USER;
+
+	if (write)
+		need_pte_bits |= _PAGE_WRITE;
+
+	if ((pteval & need_pte_bits) != need_pte_bits)
+		return false;
+
+	return true;
+}
+
 /* Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
  *
@@ -103,7 +126,7 @@ static inline pte_t pte_mkspecial(pte_t pte)
 
 static inline pte_t pte_mkhuge(pte_t pte)
 {
-	return pte;
+	return __pte(pte_val(pte) | _PAGE_HUGE);
 }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
@@ -212,8 +235,10 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addre
 #define pgprot_cached(prot)       (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
 				            _PAGE_COHERENT))
 
+#if _PAGE_WRITETHRU != 0
 #define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
 				            _PAGE_COHERENT | _PAGE_WRITETHRU))
+#endif
 
 #define pgprot_cached_noncoherent(prot) \
 		(__pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL))
diff --git a/arch/powerpc/include/asm/nohash/pte-book3e.h b/arch/powerpc/include/asm/nohash/pte-book3e.h
index 2da4532ca377..ccee8eb509bb 100644
--- a/arch/powerpc/include/asm/nohash/pte-book3e.h
+++ b/arch/powerpc/include/asm/nohash/pte-book3e.h
@@ -55,6 +55,7 @@
 #define _PAGE_KERNEL_RWX	(_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY | _PAGE_BAP_SX)
 #define _PAGE_KERNEL_ROX	(_PAGE_BAP_SR | _PAGE_BAP_SX)
 #define _PAGE_USER		(_PAGE_BAP_UR | _PAGE_BAP_SR) /* Can be read */
+#define _PAGE_PRIVILEGED	(_PAGE_BAP_SR)
 
 #define _PAGE_HASHPTE	0
 #define _PAGE_BUSY	0
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index 233c7504b1f2..24c73f5575ee 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -201,7 +201,10 @@
 #define OPAL_SET_POWER_SHIFT_RATIO		155
 #define OPAL_SENSOR_GROUP_CLEAR			156
 #define OPAL_PCI_SET_P2P			157
-#define OPAL_LAST				157
+#define OPAL_NPU_SPA_SETUP			159
+#define OPAL_NPU_SPA_CLEAR_CACHE		160
+#define OPAL_NPU_TL_SET				161
+#define OPAL_LAST				161
 
 /* Device tree flags */
 
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 0c545f7fc77b..12e70fb58700 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -34,6 +34,12 @@ int64_t opal_npu_init_context(uint64_t phb_id, int pasid, uint64_t msr,
 			uint64_t bdf);
 int64_t opal_npu_map_lpar(uint64_t phb_id, uint64_t bdf, uint64_t lparid,
 			uint64_t lpcr);
+int64_t opal_npu_spa_setup(uint64_t phb_id, uint32_t bdfn,
+			uint64_t addr, uint64_t PE_mask);
+int64_t opal_npu_spa_clear_cache(uint64_t phb_id, uint32_t bdfn,
+				uint64_t PE_handle);
+int64_t opal_npu_tl_set(uint64_t phb_id, uint32_t bdfn, long cap,
+			uint64_t rate_phys, uint32_t size);
 int64_t opal_console_write(int64_t term_number, __be64 *length,
 			   const uint8_t *buffer);
 int64_t opal_console_read(int64_t term_number, __be64 *length,
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 3892db93b837..b62c31037cad 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -159,7 +159,7 @@ struct paca_struct {
 	u64 saved_r1;			/* r1 save for RTAS calls or PM */
 	u64 saved_msr;			/* MSR saved here by enter_rtas */
 	u16 trap_save;			/* Used when bad stack is encountered */
-	u8 soft_enabled;		/* irq soft-enable flag */
+	u8 irq_soft_mask;		/* mask for irq soft masking */
 	u8 irq_happened;		/* irq happened while soft-disabled */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
 	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
@@ -232,6 +232,15 @@ struct paca_struct {
 	struct sibling_subcore_state *sibling_subcore_state;
 #endif
 #endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * rfi fallback flush must be in its own cacheline to prevent
+	 * other paca data leaking into the L1d
+	 */
+	u64 exrfi[EX_SIZE] __aligned(0x80);
+	void *rfi_flush_fallback_area;
+	u64 l1d_flush_size;
+#endif
 };
 
 extern void copy_mm_to_paca(struct mm_struct *mm);
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 62ed83db04ae..94d449031b18 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -197,25 +197,22 @@ struct pci_dn {
 	struct	iommu_table_group *table_group;	/* for phb's or bridges */
 
 	int	pci_ext_config_space;	/* for pci devices */
-
-	struct	pci_dev *pcidev;	/* back-pointer to the pci device */
 #ifdef CONFIG_EEH
 	struct eeh_dev *edev;		/* eeh device */
 #endif
 #define IODA_INVALID_PE		0xFFFFFFFF
-#ifdef CONFIG_PPC_POWERNV
 	unsigned int pe_number;
-	int     vf_index;		/* VF index in the PF */
 #ifdef CONFIG_PCI_IOV
+	int     vf_index;		/* VF index in the PF */
 	u16     vfs_expanded;		/* number of VFs IOV BAR expanded */
 	u16     num_vfs;		/* number of VFs enabled*/
 	unsigned int *pe_num_map;	/* PE# for the first VF PE or array */
 	bool    m64_single_mode;	/* Use M64 BAR in Single Mode */
 #define IODA_INVALID_M64        (-1)
-	int     (*m64_map)[PCI_SRIOV_NUM_BARS];
+	int     (*m64_map)[PCI_SRIOV_NUM_BARS];	/* Only used on powernv */
+	int     last_allow_rc;			/* Only used on pseries */
 #endif /* CONFIG_PCI_IOV */
 	int	mps;			/* Maximum Payload Size */
-#endif
 	struct list_head child_list;
 	struct list_head list;
 	struct resource holes[PCI_SRIOV_NUM_BARS];
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 8dc32eacc97c..d82802ff5088 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -121,6 +121,8 @@ extern int remove_phb_dynamic(struct pci_controller *phb);
 extern struct pci_dev *of_create_pci_dev(struct device_node *node,
 					struct pci_bus *bus, int devfn);
 
+extern unsigned int pci_parse_of_flags(u32 addr0, int bridge);
+
 extern void of_scan_pci_bridge(struct pci_dev *dev);
 
 extern void of_scan_bus(struct device_node *node, struct pci_bus *bus);
diff --git a/arch/powerpc/include/asm/pkeys.h b/arch/powerpc/include/asm/pkeys.h
new file mode 100644
index 000000000000..0409c80c32c0
--- /dev/null
+++ b/arch/powerpc/include/asm/pkeys.h
@@ -0,0 +1,218 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * PowerPC Memory Protection Keys management
+ *
+ * Copyright 2017, Ram Pai, IBM Corporation.
+ */
+
+#ifndef _ASM_POWERPC_KEYS_H
+#define _ASM_POWERPC_KEYS_H
+
+#include <linux/jump_label.h>
+#include <asm/firmware.h>
+
+DECLARE_STATIC_KEY_TRUE(pkey_disabled);
+extern int pkeys_total; /* total pkeys as per device tree */
+extern u32 initial_allocation_mask; /* bits set for reserved keys */
+
+/*
+ * Define these here temporarily so we're not dependent on patching linux/mm.h.
+ * Once it's updated we can drop these.
+ */
+#ifndef VM_PKEY_BIT0
+# define VM_PKEY_SHIFT	VM_HIGH_ARCH_BIT_0
+# define VM_PKEY_BIT0	VM_HIGH_ARCH_0
+# define VM_PKEY_BIT1	VM_HIGH_ARCH_1
+# define VM_PKEY_BIT2	VM_HIGH_ARCH_2
+# define VM_PKEY_BIT3	VM_HIGH_ARCH_3
+# define VM_PKEY_BIT4	VM_HIGH_ARCH_4
+#endif
+
+#define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | \
+			    VM_PKEY_BIT3 | VM_PKEY_BIT4)
+
+/* Override any generic PKEY permission defines */
+#define PKEY_DISABLE_EXECUTE   0x4
+#define PKEY_ACCESS_MASK       (PKEY_DISABLE_ACCESS | \
+				PKEY_DISABLE_WRITE  | \
+				PKEY_DISABLE_EXECUTE)
+
+static inline u64 pkey_to_vmflag_bits(u16 pkey)
+{
+	return (((u64)pkey << VM_PKEY_SHIFT) & ARCH_VM_PKEY_FLAGS);
+}
+
+static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return 0x0UL;
+
+	return (((vm_flags & VM_PKEY_BIT0) ? H_PTE_PKEY_BIT4 : 0x0UL) |
+		((vm_flags & VM_PKEY_BIT1) ? H_PTE_PKEY_BIT3 : 0x0UL) |
+		((vm_flags & VM_PKEY_BIT2) ? H_PTE_PKEY_BIT2 : 0x0UL) |
+		((vm_flags & VM_PKEY_BIT3) ? H_PTE_PKEY_BIT1 : 0x0UL) |
+		((vm_flags & VM_PKEY_BIT4) ? H_PTE_PKEY_BIT0 : 0x0UL));
+}
+
+static inline int vma_pkey(struct vm_area_struct *vma)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return 0;
+	return (vma->vm_flags & ARCH_VM_PKEY_FLAGS) >> VM_PKEY_SHIFT;
+}
+
+#define arch_max_pkey() pkeys_total
+
+static inline u64 pte_to_hpte_pkey_bits(u64 pteflags)
+{
+	return (((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT2) ? HPTE_R_KEY_BIT2 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT3) ? HPTE_R_KEY_BIT3 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL));
+}
+
+static inline u16 pte_to_pkey_bits(u64 pteflags)
+{
+	return (((pteflags & H_PTE_PKEY_BIT0) ? 0x10 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT1) ? 0x8 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT2) ? 0x4 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT3) ? 0x2 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT4) ? 0x1 : 0x0UL));
+}
+
+#define pkey_alloc_mask(pkey) (0x1 << pkey)
+
+#define mm_pkey_allocation_map(mm) (mm->context.pkey_allocation_map)
+
+#define __mm_pkey_allocated(mm, pkey) {	\
+	mm_pkey_allocation_map(mm) |= pkey_alloc_mask(pkey); \
+}
+
+#define __mm_pkey_free(mm, pkey) {	\
+	mm_pkey_allocation_map(mm) &= ~pkey_alloc_mask(pkey);	\
+}
+
+#define __mm_pkey_is_allocated(mm, pkey)	\
+	(mm_pkey_allocation_map(mm) & pkey_alloc_mask(pkey))
+
+#define __mm_pkey_is_reserved(pkey) (initial_allocation_mask & \
+				       pkey_alloc_mask(pkey))
+
+static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
+{
+	/* A reserved key is never considered as 'explicitly allocated' */
+	return ((pkey < arch_max_pkey()) &&
+		!__mm_pkey_is_reserved(pkey) &&
+		__mm_pkey_is_allocated(mm, pkey));
+}
+
+extern void __arch_activate_pkey(int pkey);
+extern void __arch_deactivate_pkey(int pkey);
+/*
+ * Returns a positive, 5-bit key on success, or -1 on failure.
+ * Relies on the mmap_sem to protect against concurrency in mm_pkey_alloc() and
+ * mm_pkey_free().
+ */
+static inline int mm_pkey_alloc(struct mm_struct *mm)
+{
+	/*
+	 * Note: this is the one and only place we make sure that the pkey is
+	 * valid as far as the hardware is concerned. The rest of the kernel
+	 * trusts that only good, valid pkeys come out of here.
+	 */
+	u32 all_pkeys_mask = (u32)(~(0x0));
+	int ret;
+
+	if (static_branch_likely(&pkey_disabled))
+		return -1;
+
+	/*
+	 * Are we out of pkeys? We must handle this specially because ffz()
+	 * behavior is undefined if there are no zeros.
+	 */
+	if (mm_pkey_allocation_map(mm) == all_pkeys_mask)
+		return -1;
+
+	ret = ffz((u32)mm_pkey_allocation_map(mm));
+	__mm_pkey_allocated(mm, ret);
+
+	/*
+	 * Enable the key in the hardware
+	 */
+	if (ret > 0)
+		__arch_activate_pkey(ret);
+	return ret;
+}
+
+static inline int mm_pkey_free(struct mm_struct *mm, int pkey)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return -1;
+
+	if (!mm_pkey_is_allocated(mm, pkey))
+		return -EINVAL;
+
+	/*
+	 * Disable the key in the hardware
+	 */
+	__arch_deactivate_pkey(pkey);
+	__mm_pkey_free(mm, pkey);
+
+	return 0;
+}
+
+/*
+ * Try to dedicate one of the protection keys to be used as an
+ * execute-only protection key.
+ */
+extern int __execute_only_pkey(struct mm_struct *mm);
+static inline int execute_only_pkey(struct mm_struct *mm)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return -1;
+
+	return __execute_only_pkey(mm);
+}
+
+extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma,
+					 int prot, int pkey);
+static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma,
+					      int prot, int pkey)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return 0;
+
+	/*
+	 * Is this an mprotect_pkey() call? If so, never override the value that
+	 * came from the user.
+	 */
+	if (pkey != -1)
+		return pkey;
+
+	return __arch_override_mprotect_pkey(vma, prot, pkey);
+}
+
+extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+				       unsigned long init_val);
+static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+					    unsigned long init_val)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return -EINVAL;
+	return __arch_set_user_pkey_access(tsk, pkey, init_val);
+}
+
+static inline bool arch_pkeys_enabled(void)
+{
+	return !static_branch_likely(&pkey_disabled);
+}
+
+extern void pkey_mm_init(struct mm_struct *mm);
+extern bool arch_supports_pkeys(int cap);
+extern unsigned int arch_usable_pkeys(void);
+extern void thread_pkey_regs_save(struct thread_struct *thread);
+extern void thread_pkey_regs_restore(struct thread_struct *new_thread,
+				     struct thread_struct *old_thread);
+extern void thread_pkey_regs_init(struct thread_struct *thread);
+#endif /*_ASM_POWERPC_KEYS_H */
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index 7f01b22fa6cb..55eddf50d149 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -326,4 +326,18 @@ static inline long plapr_signal_sys_reset(long cpu)
 	return plpar_hcall_norets(H_SIGNAL_SYS_RESET, cpu);
 }
 
+static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	rc = plpar_hcall(H_GET_CPU_CHARACTERISTICS, retbuf);
+	if (rc == H_SUCCESS) {
+		p->character = retbuf[0];
+		p->behaviour = retbuf[1];
+	}
+
+	return rc;
+}
+
 #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */
diff --git a/arch/powerpc/include/asm/pnv-ocxl.h b/arch/powerpc/include/asm/pnv-ocxl.h
new file mode 100644
index 000000000000..f6945d3bc971
--- /dev/null
+++ b/arch/powerpc/include/asm/pnv-ocxl.h
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2017 IBM Corp.
+#ifndef _ASM_PNV_OCXL_H
+#define _ASM_PNV_OCXL_H
+
+#include <linux/pci.h>
+
+#define PNV_OCXL_TL_MAX_TEMPLATE        63
+#define PNV_OCXL_TL_BITS_PER_RATE       4
+#define PNV_OCXL_TL_RATE_BUF_SIZE       ((PNV_OCXL_TL_MAX_TEMPLATE+1) * PNV_OCXL_TL_BITS_PER_RATE / 8)
+
+extern int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled,
+			u16 *supported);
+extern int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count);
+
+extern int pnv_ocxl_get_tl_cap(struct pci_dev *dev, long *cap,
+			char *rate_buf, int rate_buf_size);
+extern int pnv_ocxl_set_tl_conf(struct pci_dev *dev, long cap,
+			uint64_t rate_buf_phys, int rate_buf_size);
+
+extern int pnv_ocxl_get_xsl_irq(struct pci_dev *dev, int *hwirq);
+extern void pnv_ocxl_unmap_xsl_regs(void __iomem *dsisr, void __iomem *dar,
+				void __iomem *tfc, void __iomem *pe_handle);
+extern int pnv_ocxl_map_xsl_regs(struct pci_dev *dev, void __iomem **dsisr,
+				void __iomem **dar, void __iomem **tfc,
+				void __iomem **pe_handle);
+
+extern int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask,
+			void **platform_data);
+extern void pnv_ocxl_spa_release(void *platform_data);
+extern int pnv_ocxl_spa_remove_pe(void *platform_data, int pe_handle);
+
+extern int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr);
+extern void pnv_ocxl_free_xive_irq(u32 irq);
+
+#endif /* _ASM_PNV_OCXL_H */
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index ce0930d68857..ab5c1588b487 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -236,6 +236,7 @@
 #define PPC_INST_RFCI			0x4c000066
 #define PPC_INST_RFDI			0x4c00004e
 #define PPC_INST_RFMCI			0x4c00004c
+#define PPC_INST_MFSPR			0x7c0002a6
 #define PPC_INST_MFSPR_DSCR		0x7c1102a6
 #define PPC_INST_MFSPR_DSCR_MASK	0xfc1ffffe
 #define PPC_INST_MTSPR_DSCR		0x7c1103a6
@@ -383,6 +384,7 @@
 #define __PPC_ME64(s)	__PPC_MB64(s)
 #define __PPC_BI(s)	(((s) & 0x1f) << 16)
 #define __PPC_CT(t)	(((t) & 0x0f) << 21)
+#define __PPC_SPR(r)	((((r) & 0x1f) << 16) | ((((r) >> 5) & 0x1f) << 11))
 
 /*
  * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index bdab3b74eb98..01299cdc9806 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -309,6 +309,11 @@ struct thread_struct {
 	struct thread_vr_state ckvr_state; /* Checkpointed VR state */
 	unsigned long	ckvrsave; /* Checkpointed VRSAVE */
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+#ifdef CONFIG_PPC_MEM_KEYS
+	unsigned long	amr;
+	unsigned long	iamr;
+	unsigned long	uamor;
+#endif
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	void*		kvm_shadow_vcpu; /* KVM internal data */
 #endif /* CONFIG_KVM_BOOK3S_32_HANDLER */
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 825bd5998701..b04c5ce8191b 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -80,21 +80,20 @@ extern void of_instantiate_rtc(void);
 
 extern int of_get_ibm_chip_id(struct device_node *np);
 
-/* The of_drconf_cell struct defines the layout of the LMB array
- * specified in the device tree property
- * ibm,dynamic-reconfiguration-memory/ibm,dynamic-memory
- */
-struct of_drconf_cell {
-	u64	base_addr;
-	u32	drc_index;
-	u32	reserved;
-	u32	aa_index;
-	u32	flags;
+struct of_drc_info {
+	char *drc_type;
+	char *drc_name_prefix;
+	u32 drc_index_start;
+	u32 drc_name_suffix_start;
+	u32 num_sequential_elems;
+	u32 sequential_inc;
+	u32 drc_power_domain;
+	u32 last_drc_index;
 };
 
-#define DRCONF_MEM_ASSIGNED	0x00000008
-#define DRCONF_MEM_AI_INVALID	0x00000040
-#define DRCONF_MEM_RESERVED	0x00000080
+extern int of_read_drc_info_cell(struct property **prop,
+			const __be32 **curval, struct of_drc_info *data);
+
 
 /*
  * There are two methods for telling firmware what our capabilities are.
@@ -159,6 +158,7 @@ struct of_drconf_cell {
 #define OV5_PFO_HW_842		0x1140	/* PFO Compression Accelerator */
 #define OV5_PFO_HW_ENCR		0x1120	/* PFO Encryption Accelerator */
 #define OV5_SUB_PROCESSORS	0x1501	/* 1,2,or 4 Sub-Processors supported */
+#define OV5_DRMEM_V2		0x1680	/* ibm,dynamic-reconfiguration-v2 */
 #define OV5_XIVE_SUPPORT	0x17C0	/* XIVE Exploitation Support Mask */
 #define OV5_XIVE_LEGACY		0x1700	/* XIVE legacy mode Only */
 #define OV5_XIVE_EXPLOIT	0x1740	/* XIVE exploitation mode Only */
@@ -175,6 +175,7 @@ struct of_drconf_cell {
 #define OV5_HASH_GTSE		0x1940	/* Guest Translation Shoot Down Avail */
 /* Radix Table Extensions */
 #define OV5_RADIX_GTSE		0x1A40	/* Guest Translation Shoot Down Avail */
+#define OV5_DRC_INFO		0x1640	/* Redef Prop Structures: drc-info   */
 
 /* Option Vector 6: IBM PAPR hints */
 #define OV6_LINUX		0x02	/* Linux is our OS */
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index ce142ef99ba7..c4a72c7a8c83 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -8,9 +8,6 @@
 #ifndef _PAGE_HASHPTE
 #define _PAGE_HASHPTE	0
 #endif
-#ifndef _PAGE_SHARED
-#define _PAGE_SHARED	0
-#endif
 #ifndef _PAGE_HWWRITE
 #define _PAGE_HWWRITE	0
 #endif
@@ -45,6 +42,20 @@
 #ifndef _PAGE_PTE
 #define _PAGE_PTE 0
 #endif
+/* At least one of _PAGE_PRIVILEGED or _PAGE_USER must be defined */
+#ifndef _PAGE_PRIVILEGED
+#define _PAGE_PRIVILEGED 0
+#else
+#ifndef _PAGE_USER
+#define _PAGE_USER 0
+#endif
+#endif
+#ifndef _PAGE_NA
+#define _PAGE_NA 0
+#endif
+#ifndef _PAGE_HUGE
+#define _PAGE_HUGE 0
+#endif
 
 #ifndef _PMD_PRESENT_MASK
 #define _PMD_PRESENT_MASK	_PMD_PRESENT
@@ -53,17 +64,22 @@
 #define _PMD_SIZE	0
 #define PMD_PAGE_SIZE(pmd)	bad_call_to_PMD_PAGE_SIZE()
 #endif
+#ifndef _PMD_USER
+#define _PMD_USER	0
+#endif
 #ifndef _PAGE_KERNEL_RO
-#define _PAGE_KERNEL_RO		(_PAGE_RO)
+#define _PAGE_KERNEL_RO		(_PAGE_PRIVILEGED | _PAGE_RO)
 #endif
 #ifndef _PAGE_KERNEL_ROX
-#define _PAGE_KERNEL_ROX	(_PAGE_EXEC | _PAGE_RO)
+#define _PAGE_KERNEL_ROX	(_PAGE_PRIVILEGED | _PAGE_RO | _PAGE_EXEC)
 #endif
 #ifndef _PAGE_KERNEL_RW
-#define _PAGE_KERNEL_RW		(_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE)
+#define _PAGE_KERNEL_RW		(_PAGE_PRIVILEGED | _PAGE_DIRTY | _PAGE_RW | \
+				 _PAGE_HWWRITE)
 #endif
 #ifndef _PAGE_KERNEL_RWX
-#define _PAGE_KERNEL_RWX	(_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE | _PAGE_EXEC)
+#define _PAGE_KERNEL_RWX	(_PAGE_PRIVILEGED | _PAGE_DIRTY | _PAGE_RW | \
+				 _PAGE_HWWRITE | _PAGE_EXEC)
 #endif
 #ifndef _PAGE_HPTEFLAGS
 #define _PAGE_HPTEFLAGS _PAGE_HASHPTE
@@ -85,7 +101,7 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
  */
 static inline bool pte_user(pte_t pte)
 {
-	return (pte_val(pte) & _PAGE_USER) == _PAGE_USER;
+	return (pte_val(pte) & (_PAGE_USER | _PAGE_PRIVILEGED)) == _PAGE_USER;
 }
 #endif /* __ASSEMBLY__ */
 
@@ -115,7 +131,8 @@ static inline bool pte_user(pte_t pte)
 /* Mask of bits returned by pte_pgprot() */
 #define PAGE_PROT_BITS	(_PAGE_GUARDED | _PAGE_COHERENT | _PAGE_NO_CACHE | \
 			 _PAGE_WRITETHRU | _PAGE_ENDIAN | _PAGE_4K_PFN | \
-			 _PAGE_USER | _PAGE_ACCESSED | _PAGE_RO | \
+			 _PAGE_USER | _PAGE_ACCESSED | _PAGE_RO | _PAGE_NA | \
+			 _PAGE_PRIVILEGED | \
 			 _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | _PAGE_EXEC)
 
 /*
@@ -142,7 +159,7 @@ static inline bool pte_user(pte_t pte)
  *
  * Note due to the way vm flags are laid out, the bits are XWR
  */
-#define PAGE_NONE	__pgprot(_PAGE_BASE)
+#define PAGE_NONE	__pgprot(_PAGE_BASE | _PAGE_NA)
 #define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW)
 #define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | \
 				 _PAGE_EXEC)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index b779f3ccd412..e6c7eadf6bce 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -312,7 +312,6 @@
 				 DSISR_BAD_EXT_CTRL)
 #define	  DSISR_BAD_FAULT_64S	(DSISR_BAD_FAULT_32S	| \
 				 DSISR_ATTR_CONFLICT	| \
-				 DSISR_KEYFAULT		| \
 				 DSISR_UNSUPP_MMU	| \
 				 DSISR_PRTABLE_FAULT	| \
 				 DSISR_ICSWX_NO_CT	| \
@@ -432,8 +431,9 @@
 #define SPRN_LPID	0x13F	/* Logical Partition Identifier */
 #endif
 #define   LPID_RSVD	0x3ff		/* Reserved LPID for partn switching */
-#define	SPRN_HMER	0x150	/* Hardware m? error recovery */
-#define	SPRN_HMEER	0x151	/* Hardware m? enable error recovery */
+#define	SPRN_HMER	0x150	/* Hypervisor maintenance exception reg */
+#define   HMER_DEBUG_TRIG	(1ul << (63 - 17)) /* Debug trigger */
+#define	SPRN_HMEER	0x151	/* Hyp maintenance exception enable reg */
 #define SPRN_PCR	0x152	/* Processor compatibility register */
 #define   PCR_VEC_DIS	(1ul << (63-0))	/* Vec. disable (bit NA since POWER8) */
 #define   PCR_VSX_DIS	(1ul << (63-1))	/* VSX disable (bit NA since POWER8) */
diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h
index 53a7e2955d3e..7192eece6c3e 100644
--- a/arch/powerpc/include/asm/reg_8xx.h
+++ b/arch/powerpc/include/asm/reg_8xx.h
@@ -66,86 +66,4 @@
 #define DC_DFWT		0x40000000	/* Data cache is forced write through */
 #define DC_LES		0x20000000	/* Caches are little endian mode */
 
-#ifdef CONFIG_8xx_CPU6
-#define do_mtspr_cpu6(rn, rn_addr, v)	\
-	do {								\
-		int _reg_cpu6 = rn_addr, _tmp_cpu6;		\
-		asm volatile("stw %0, %1;"				\
-			     "lwz %0, %1;"				\
-			     "mtspr " __stringify(rn) ",%2" :		\
-			     : "r" (_reg_cpu6), "m"(_tmp_cpu6),		\
-			       "r" ((unsigned long)(v))			\
-			     : "memory");				\
-	} while (0)
-
-#define do_mtspr(rn, v)	asm volatile("mtspr " __stringify(rn) ",%0" :	\
-				     : "r" ((unsigned long)(v))		\
-				     : "memory")
-#define mtspr(rn, v) \
-	do {								\
-		if (rn == SPRN_IMMR)					\
-			do_mtspr_cpu6(rn, 0x3d30, v);			\
-		else if (rn == SPRN_IC_CST)				\
-			do_mtspr_cpu6(rn, 0x2110, v);			\
-		else if (rn == SPRN_IC_ADR)				\
-			do_mtspr_cpu6(rn, 0x2310, v);			\
-		else if (rn == SPRN_IC_DAT)				\
-			do_mtspr_cpu6(rn, 0x2510, v);			\
-		else if (rn == SPRN_DC_CST)				\
-			do_mtspr_cpu6(rn, 0x3110, v);			\
-		else if (rn == SPRN_DC_ADR)				\
-			do_mtspr_cpu6(rn, 0x3310, v);			\
-		else if (rn == SPRN_DC_DAT)				\
-			do_mtspr_cpu6(rn, 0x3510, v);			\
-		else if (rn == SPRN_MI_CTR)				\
-			do_mtspr_cpu6(rn, 0x2180, v);			\
-		else if (rn == SPRN_MI_AP)				\
-			do_mtspr_cpu6(rn, 0x2580, v);			\
-		else if (rn == SPRN_MI_EPN)				\
-			do_mtspr_cpu6(rn, 0x2780, v);			\
-		else if (rn == SPRN_MI_TWC)				\
-			do_mtspr_cpu6(rn, 0x2b80, v);			\
-		else if (rn == SPRN_MI_RPN)				\
-			do_mtspr_cpu6(rn, 0x2d80, v);			\
-		else if (rn == SPRN_MI_CAM)				\
-			do_mtspr_cpu6(rn, 0x2190, v);			\
-		else if (rn == SPRN_MI_RAM0)				\
-			do_mtspr_cpu6(rn, 0x2390, v);			\
-		else if (rn == SPRN_MI_RAM1)				\
-			do_mtspr_cpu6(rn, 0x2590, v);			\
-		else if (rn == SPRN_MD_CTR)				\
-			do_mtspr_cpu6(rn, 0x3180, v);			\
-		else if (rn == SPRN_M_CASID)				\
-			do_mtspr_cpu6(rn, 0x3380, v);			\
-		else if (rn == SPRN_MD_AP)				\
-			do_mtspr_cpu6(rn, 0x3580, v);			\
-		else if (rn == SPRN_MD_EPN)				\
-			do_mtspr_cpu6(rn, 0x3780, v);			\
-		else if (rn == SPRN_M_TWB)				\
-			do_mtspr_cpu6(rn, 0x3980, v);			\
-		else if (rn == SPRN_MD_TWC)				\
-			do_mtspr_cpu6(rn, 0x3b80, v);			\
-		else if (rn == SPRN_MD_RPN)				\
-			do_mtspr_cpu6(rn, 0x3d80, v);			\
-		else if (rn == SPRN_M_TW)				\
-			do_mtspr_cpu6(rn, 0x3f80, v);			\
-		else if (rn == SPRN_MD_CAM)				\
-			do_mtspr_cpu6(rn, 0x3190, v);			\
-		else if (rn == SPRN_MD_RAM0)				\
-			do_mtspr_cpu6(rn, 0x3390, v);			\
-		else if (rn == SPRN_MD_RAM1)				\
-			do_mtspr_cpu6(rn, 0x3590, v);			\
-		else if (rn == SPRN_DEC)				\
-			do_mtspr_cpu6(rn, 0x2c00, v);			\
-		else if (rn == SPRN_TBWL)				\
-			do_mtspr_cpu6(rn, 0x3880, v);			\
-		else if (rn == SPRN_TBWU)				\
-			do_mtspr_cpu6(rn, 0x3a80, v);			\
-		else if (rn == SPRN_DPDR)				\
-			do_mtspr_cpu6(rn, 0x2d30, v);			\
-		else							\
-			do_mtspr(rn, v);				\
-	} while (0)
-#endif
-
 #endif /* _ASM_POWERPC_REG_8xx_H */
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 82bec63bbd4f..e335a8f846af 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -66,6 +66,9 @@ static inline int overlaps_kvm_tmp(unsigned long start, unsigned long end)
 }
 
 #ifdef PPC64_ELF_ABI_v1
+
+#define HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR 1
+
 #undef dereference_function_descriptor
 static inline void *dereference_function_descriptor(void *ptr)
 {
@@ -76,6 +79,15 @@ static inline void *dereference_function_descriptor(void *ptr)
 		ptr = p;
 	return ptr;
 }
+
+#undef dereference_kernel_function_descriptor
+static inline void *dereference_kernel_function_descriptor(void *ptr)
+{
+	if (ptr < (void *)__start_opd || ptr >= (void *)__end_opd)
+		return ptr;
+
+	return dereference_function_descriptor(ptr);
+}
 #endif /* PPC64_ELF_ABI_v1 */
 
 #endif
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 257d23dbf55d..469b7fdc9be4 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -24,6 +24,7 @@ extern void reloc_got2(unsigned long);
 
 void check_for_initrd(void);
 void initmem_init(void);
+void setup_panic(void);
 #define ARCH_PANIC_TIMEOUT 180
 
 #ifdef CONFIG_PPC_PSERIES
@@ -38,6 +39,19 @@ static inline void pseries_big_endian_exceptions(void) {}
 static inline void pseries_little_endian_exceptions(void) {}
 #endif /* CONFIG_PPC_PSERIES */
 
+void rfi_flush_enable(bool enable);
+
+/* These are bit flags */
+enum l1d_flush_type {
+	L1D_FLUSH_NONE		= 0x1,
+	L1D_FLUSH_FALLBACK	= 0x2,
+	L1D_FLUSH_ORI		= 0x4,
+	L1D_FLUSH_MTTRIG	= 0x8,
+};
+
+void __init setup_rfi_flush(enum l1d_flush_type, bool enable);
+void do_rfi_flush_fixups(enum l1d_flush_type types);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_SETUP_H */
diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h
index 01d45a5fd00b..f65ecf57b66c 100644
--- a/arch/powerpc/include/asm/swiotlb.h
+++ b/arch/powerpc/include/asm/swiotlb.h
@@ -13,9 +13,7 @@
 
 #include <linux/swiotlb.h>
 
-extern const struct dma_map_ops swiotlb_dma_ops;
-
-static inline void dma_mark_clean(void *addr, size_t size) {}
+extern const struct dma_map_ops powerpc_swiotlb_dma_ops;
 
 extern unsigned int ppc_swiotlb_enable;
 int __init swiotlb_setup_bus_notifier(void);
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 449912f057f6..d61f9c96d916 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -389,3 +389,6 @@ COMPAT_SYS_SPU(preadv2)
 COMPAT_SYS_SPU(pwritev2)
 SYSCALL(kexec_file_load)
 SYSCALL(statx)
+SYSCALL(pkey_alloc)
+SYSCALL(pkey_free)
+SYSCALL(pkey_mprotect)
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index a264c3ad366b..4a12c00f8de3 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -58,9 +58,6 @@ struct thread_info {
 	.flags =	0,			\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 #define THREAD_SIZE_ORDER	(THREAD_SHIFT - PAGE_SHIFT)
 
 /* how to get the thread information struct from C */
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 9ba11dbcaca9..daf1ba97a00c 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,14 +12,10 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		384
+#define NR_syscalls		387
 
 #define __NR__exit __NR_exit
 
-#define __IGNORE_pkey_mprotect
-#define __IGNORE_pkey_alloc
-#define __IGNORE_pkey_free
-
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h
index 1d3f2be5ae39..fa4288822b68 100644
--- a/arch/powerpc/include/asm/xive-regs.h
+++ b/arch/powerpc/include/asm/xive-regs.h
@@ -10,6 +10,41 @@
 #define _ASM_POWERPC_XIVE_REGS_H
 
 /*
+ * "magic" Event State Buffer (ESB) MMIO offsets.
+ *
+ * Each interrupt source has a 2-bit state machine called ESB
+ * which can be controlled by MMIO. It's made of 2 bits, P and
+ * Q. P indicates that an interrupt is pending (has been sent
+ * to a queue and is waiting for an EOI). Q indicates that the
+ * interrupt has been triggered while pending.
+ *
+ * This acts as a coalescing mechanism in order to guarantee
+ * that a given interrupt only occurs at most once in a queue.
+ *
+ * When doing an EOI, the Q bit will indicate if the interrupt
+ * needs to be re-triggered.
+ *
+ * The following offsets into the ESB MMIO allow to read or
+ * manipulate the PQ bits. They must be used with an 8-bytes
+ * load instruction. They all return the previous state of the
+ * interrupt (atomically).
+ *
+ * Additionally, some ESB pages support doing an EOI via a
+ * store at 0 and some ESBs support doing a trigger via a
+ * separate trigger page.
+ */
+#define XIVE_ESB_STORE_EOI	0x400 /* Store */
+#define XIVE_ESB_LOAD_EOI	0x000 /* Load */
+#define XIVE_ESB_GET		0x800 /* Load */
+#define XIVE_ESB_SET_PQ_00	0xc00 /* Load */
+#define XIVE_ESB_SET_PQ_01	0xd00 /* Load */
+#define XIVE_ESB_SET_PQ_10	0xe00 /* Load */
+#define XIVE_ESB_SET_PQ_11	0xf00 /* Load */
+
+#define XIVE_ESB_VAL_P		0x2
+#define XIVE_ESB_VAL_Q		0x1
+
+/*
  * Thread Management (aka "TM") registers
  */
 
diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h
index 371fbebf1ec9..7624e22f5045 100644
--- a/arch/powerpc/include/asm/xive.h
+++ b/arch/powerpc/include/asm/xive.h
@@ -58,6 +58,9 @@ struct xive_irq_data {
 #define XIVE_IRQ_FLAG_EOI_FW	0x10
 #define XIVE_IRQ_FLAG_H_INT_ESB	0x20
 
+/* Special flag set by KVM for excalation interrupts */
+#define XIVE_IRQ_NO_EOI		0x80
+
 #define XIVE_INVALID_CHIP_ID	-1
 
 /* A queue tracking structure in a CPU */
@@ -72,41 +75,6 @@ struct xive_q {
 	atomic_t		pending_count;
 };
 
-/*
- * "magic" Event State Buffer (ESB) MMIO offsets.
- *
- * Each interrupt source has a 2-bit state machine called ESB
- * which can be controlled by MMIO. It's made of 2 bits, P and
- * Q. P indicates that an interrupt is pending (has been sent
- * to a queue and is waiting for an EOI). Q indicates that the
- * interrupt has been triggered while pending.
- *
- * This acts as a coalescing mechanism in order to guarantee
- * that a given interrupt only occurs at most once in a queue.
- *
- * When doing an EOI, the Q bit will indicate if the interrupt
- * needs to be re-triggered.
- *
- * The following offsets into the ESB MMIO allow to read or
- * manipulate the PQ bits. They must be used with an 8-bytes
- * load instruction. They all return the previous state of the
- * interrupt (atomically).
- *
- * Additionally, some ESB pages support doing an EOI via a
- * store at 0 and some ESBs support doing a trigger via a
- * separate trigger page.
- */
-#define XIVE_ESB_STORE_EOI	0x400 /* Store */
-#define XIVE_ESB_LOAD_EOI	0x000 /* Load */
-#define XIVE_ESB_GET		0x800 /* Load */
-#define XIVE_ESB_SET_PQ_00	0xc00 /* Load */
-#define XIVE_ESB_SET_PQ_01	0xd00 /* Load */
-#define XIVE_ESB_SET_PQ_10	0xe00 /* Load */
-#define XIVE_ESB_SET_PQ_11	0xf00 /* Load */
-
-#define XIVE_ESB_VAL_P		0x2
-#define XIVE_ESB_VAL_Q		0x1
-
 /* Global enable flags for the XIVE support */
 extern bool __xive_enabled;
 
@@ -154,7 +122,7 @@ static inline bool xive_enabled(void) { return false; }
 static inline bool xive_spapr_init(void) { return false; }
 static inline bool xive_native_init(void) { return false; }
 static inline void xive_smp_probe(void) { }
-extern inline int  xive_smp_prepare_cpu(unsigned int cpu) { return -EINVAL; }
+static inline int  xive_smp_prepare_cpu(unsigned int cpu) { return -EINVAL; }
 static inline void xive_smp_setup_cpu(void) { }
 static inline void xive_smp_disable_cpu(void) { }
 static inline void xive_kexec_teardown_cpu(int secondary) { }
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index 0d960ef78a9a..1a6ed5919ffd 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -1,6 +1,7 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += param.h
 generic-y += poll.h
 generic-y += resource.h
diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h
index 5f201d40bcca..860c59291bfc 100644
--- a/arch/powerpc/include/uapi/asm/elf.h
+++ b/arch/powerpc/include/uapi/asm/elf.h
@@ -97,6 +97,7 @@
 #define ELF_NTMSPRREG	3	/* include tfhar, tfiar, texasr */
 #define ELF_NEBB	3	/* includes ebbrr, ebbhr, bescr */
 #define ELF_NPMU	5	/* includes siar, sdar, sier, mmcr2, mmcr0 */
+#define ELF_NPKEY	3	/* includes amr, iamr, uamor */
 
 typedef unsigned long elf_greg_t64;
 typedef elf_greg_t64 elf_gregset_t64[ELF_NGREG];
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 61d6049f4c1e..637b7263cb86 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -443,6 +443,31 @@ struct kvm_ppc_rmmu_info {
 	__u32	ap_encodings[8];
 };
 
+/* For KVM_PPC_GET_CPU_CHAR */
+struct kvm_ppc_cpu_char {
+	__u64	character;		/* characteristics of the CPU */
+	__u64	behaviour;		/* recommended software behaviour */
+	__u64	character_mask;		/* valid bits in character */
+	__u64	behaviour_mask;		/* valid bits in behaviour */
+};
+
+/*
+ * Values for character and character_mask.
+ * These are identical to the values used by H_GET_CPU_CHARACTERISTICS.
+ */
+#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31		(1ULL << 63)
+#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED	(1ULL << 62)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30	(1ULL << 61)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2	(1ULL << 60)
+#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV	(1ULL << 59)
+#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED	(1ULL << 58)
+#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF	(1ULL << 57)
+#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS	(1ULL << 56)
+
+#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY	(1ULL << 63)
+#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR		(1ULL << 62)
+#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ULL << 61)
+
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
 
diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
index e63bc37e33af..65065ce32814 100644
--- a/arch/powerpc/include/uapi/asm/mman.h
+++ b/arch/powerpc/include/uapi/asm/mman.h
@@ -30,4 +30,10 @@
 #define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB	0x40000		/* create a huge page mapping */
 
+/* Override any generic PKEY permission defines */
+#define PKEY_DISABLE_EXECUTE   0x4
+#undef PKEY_ACCESS_MASK
+#define PKEY_ACCESS_MASK       (PKEY_DISABLE_ACCESS |\
+				PKEY_DISABLE_WRITE  |\
+				PKEY_DISABLE_EXECUTE)
 #endif /* _UAPI_ASM_POWERPC_MMAN_H */
diff --git a/arch/powerpc/include/uapi/asm/siginfo.h b/arch/powerpc/include/uapi/asm/siginfo.h
index 1a691141e49f..9f142451a01f 100644
--- a/arch/powerpc/include/uapi/asm/siginfo.h
+++ b/arch/powerpc/include/uapi/asm/siginfo.h
@@ -15,7 +15,19 @@
 
 #include <asm-generic/siginfo.h>
 
-#undef NSIGTRAP
-#define NSIGTRAP	4
+/*
+ * SIGFPE si_codes
+ */
+#ifdef __KERNEL__
+#define FPE_FIXME	0	/* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
+/*
+ * SIGTRAP si_codes
+ */
+#ifdef __KERNEL__
+#define TRAP_FIXME	0	/* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
 
 #endif	/* _ASM_POWERPC_SIGINFO_H */
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index df8684f31919..389c36fd8299 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -395,5 +395,8 @@
 #define __NR_pwritev2		381
 #define __NR_kexec_file_load	382
 #define __NR_statx		383
+#define __NR_pkey_alloc		384
+#define __NR_pkey_free		385
+#define __NR_pkey_mprotect	386
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6b958414b4e0..88b84ac76b53 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -178,7 +178,7 @@ int main(void)
 	OFFSET(PACATOC, paca_struct, kernel_toc);
 	OFFSET(PACAKBASE, paca_struct, kernelbase);
 	OFFSET(PACAKMSR, paca_struct, kernel_msr);
-	OFFSET(PACASOFTIRQEN, paca_struct, soft_enabled);
+	OFFSET(PACAIRQSOFTMASK, paca_struct, irq_soft_mask);
 	OFFSET(PACAIRQHAPPENED, paca_struct, irq_happened);
 #ifdef CONFIG_PPC_BOOK3S
 	OFFSET(PACACONTEXTID, paca_struct, mm_ctx_id);
@@ -237,6 +237,10 @@ int main(void)
 	OFFSET(PACA_NMI_EMERG_SP, paca_struct, nmi_emergency_sp);
 	OFFSET(PACA_IN_MCE, paca_struct, in_mce);
 	OFFSET(PACA_IN_NMI, paca_struct, in_nmi);
+	OFFSET(PACA_RFI_FLUSH_FALLBACK_AREA, paca_struct, rfi_flush_fallback_area);
+	OFFSET(PACA_EXRFI, paca_struct, exrfi);
+	OFFSET(PACA_L1D_FLUSH_SIZE, paca_struct, l1d_flush_size);
+
 #endif
 	OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id);
 	OFFSET(PACAKEXECSTATE, paca_struct, kexec_state);
@@ -396,6 +400,8 @@ int main(void)
 	/* Other bits used by the vdso */
 	DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
 	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
+	DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
+	DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
 	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
 	DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
 
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 610955fe8b81..3f30c994e931 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -31,7 +31,6 @@ _GLOBAL(__setup_cpu_power7)
 	mfspr	r3,SPRN_LPCR
 	li	r4,(LPCR_LPES1 >> LPCR_LPES_SH)
 	bl	__init_LPCR_ISA206
-	bl	__init_tlb_power7
 	mtlr	r11
 	blr
 
@@ -45,7 +44,6 @@ _GLOBAL(__restore_cpu_power7)
 	mfspr	r3,SPRN_LPCR
 	li	r4,(LPCR_LPES1 >> LPCR_LPES_SH)
 	bl	__init_LPCR_ISA206
-	bl	__init_tlb_power7
 	mtlr	r11
 	blr
 
@@ -64,7 +62,6 @@ _GLOBAL(__setup_cpu_power8)
 	li	r4,0 /* LPES = 0 */
 	bl	__init_LPCR_ISA206
 	bl	__init_HFSCR
-	bl	__init_tlb_power8
 	bl	__init_PMU_HV
 	bl	__init_PMU_HV_ISA207
 	mtlr	r11
@@ -86,7 +83,6 @@ _GLOBAL(__restore_cpu_power8)
 	li	r4,0 /* LPES = 0 */
 	bl	__init_LPCR_ISA206
 	bl	__init_HFSCR
-	bl	__init_tlb_power8
 	bl	__init_PMU_HV
 	bl	__init_PMU_HV_ISA207
 	mtlr	r11
@@ -102,6 +98,7 @@ _GLOBAL(__setup_cpu_power9)
 	li	r0,0
 	mtspr	SPRN_PSSCR,r0
 	mtspr	SPRN_LPID,r0
+	mtspr	SPRN_PID,r0
 	mfspr	r3,SPRN_LPCR
 	LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE  | LPCR_HEIC)
 	or	r3, r3, r4
@@ -110,7 +107,6 @@ _GLOBAL(__setup_cpu_power9)
 	li	r4,0 /* LPES = 0 */
 	bl	__init_LPCR_ISA300
 	bl	__init_HFSCR
-	bl	__init_tlb_power9
 	bl	__init_PMU_HV
 	mtlr	r11
 	blr
@@ -126,6 +122,7 @@ _GLOBAL(__restore_cpu_power9)
 	li	r0,0
 	mtspr	SPRN_PSSCR,r0
 	mtspr	SPRN_LPID,r0
+	mtspr	SPRN_PID,r0
 	mfspr   r3,SPRN_LPCR
 	LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
 	or	r3, r3, r4
@@ -134,7 +131,6 @@ _GLOBAL(__restore_cpu_power9)
 	li	r4,0 /* LPES = 0 */
 	bl	__init_LPCR_ISA300
 	bl	__init_HFSCR
-	bl	__init_tlb_power9
 	bl	__init_PMU_HV
 	mtlr	r11
 	blr
@@ -192,50 +188,6 @@ __init_HFSCR:
 	mtspr	SPRN_HFSCR,r3
 	blr
 
-/*
- * Clear the TLB using the specified IS form of tlbiel instruction
- * (invalidate by congruence class). P7 has 128 CCs., P8 has 512.
- */
-__init_tlb_power7:
-	li	r6,POWER7_TLB_SETS
-	mtctr	r6
-	li	r7,0xc00	/* IS field = 0b11 */
-	ptesync
-2:	tlbiel	r7
-	addi	r7,r7,0x1000
-	bdnz	2b
-	ptesync
-1:	blr
-
-__init_tlb_power8:
-	li	r6,POWER8_TLB_SETS
-	mtctr	r6
-	li	r7,0xc00	/* IS field = 0b11 */
-	ptesync
-2:	tlbiel	r7
-	addi	r7,r7,0x1000
-	bdnz	2b
-	ptesync
-1:	blr
-
-/*
- * Flush the TLB in hash mode. Hash must flush with RIC=2 once for process
- * and one for partition scope to clear process and partition table entries.
- */
-__init_tlb_power9:
-	li	r6,POWER9_TLB_SETS_HASH - 1
-	mtctr	r6
-	li	r7,0xc00	/* IS field = 0b11 */
-	li	r8,0
-	ptesync
-	PPC_TLBIEL(7, 8, 2, 1, 0)
-	PPC_TLBIEL(7, 8, 2, 0, 0)
-2:	addi	r7,r7,0x1000
-	PPC_TLBIEL(7, 8, 0, 0, 0)
-	bdnz	2b
-	ptesync
-1:	blr
-
 __init_PMU_HV:
 	li	r5,0
 	mtspr	SPRN_MMCRC,r5
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 1350f49d81a8..c40a9fc1e5d1 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -74,9 +74,6 @@ extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power8(void);
 extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power9(void);
-extern void __flush_tlb_power7(unsigned int action);
-extern void __flush_tlb_power8(unsigned int action);
-extern void __flush_tlb_power9(unsigned int action);
 extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
 extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
 extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
@@ -368,7 +365,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
 		.cpu_setup		= __setup_cpu_power7,
 		.cpu_restore		= __restore_cpu_power7,
-		.flush_tlb		= __flush_tlb_power7,
 		.machine_check_early	= __machine_check_early_realmode_p7,
 		.platform		= "power7",
 	},
@@ -386,7 +382,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
-		.flush_tlb		= __flush_tlb_power8,
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
@@ -404,7 +399,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
-		.flush_tlb		= __flush_tlb_power9,
 		.platform		= "power9",
 	},
 	{	/* Power7 */
@@ -423,7 +417,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_POWER4,
 		.cpu_setup		= __setup_cpu_power7,
 		.cpu_restore		= __restore_cpu_power7,
-		.flush_tlb		= __flush_tlb_power7,
 		.machine_check_early	= __machine_check_early_realmode_p7,
 		.platform		= "power7",
 	},
@@ -443,7 +436,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_POWER4,
 		.cpu_setup		= __setup_cpu_power7,
 		.cpu_restore		= __restore_cpu_power7,
-		.flush_tlb		= __flush_tlb_power7,
 		.machine_check_early	= __machine_check_early_realmode_p7,
 		.platform		= "power7+",
 	},
@@ -463,7 +455,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
-		.flush_tlb		= __flush_tlb_power8,
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
@@ -483,7 +474,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
-		.flush_tlb		= __flush_tlb_power8,
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
@@ -503,7 +493,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
-		.flush_tlb		= __flush_tlb_power8,
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
@@ -523,7 +512,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
-		.flush_tlb		= __flush_tlb_power8,
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
@@ -543,7 +531,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
-		.flush_tlb		= __flush_tlb_power9,
 		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
@@ -563,7 +550,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
-		.flush_tlb		= __flush_tlb_power9,
 		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
@@ -583,7 +569,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
-		.flush_tlb		= __flush_tlb_power9,
 		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index cbabb5adccd9..00b215125d3e 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -44,6 +44,14 @@
 #define REAL_MODE_TIMEOUT	10000
 
 static int time_to_dump;
+/*
+ * crash_wake_offline should be set to 1 by platforms that intend to wake
+ * up offline cpus prior to jumping to a kdump kernel. Currently powernv
+ * sets it to 1, since we want to avoid things from happening when an
+ * offline CPU wakes up due to something like an HMI (malfunction error),
+ * which propagates to all threads.
+ */
+int crash_wake_offline;
 
 #define CRASH_HANDLER_MAX 3
 /* List of shutdown handles */
@@ -63,15 +71,12 @@ static int handle_fault(struct pt_regs *regs)
 #ifdef CONFIG_SMP
 
 static atomic_t cpus_in_crash;
-static void crash_ipi_callback(struct pt_regs *regs)
+void crash_ipi_callback(struct pt_regs *regs)
 {
 	static cpumask_t cpus_state_saved = CPU_MASK_NONE;
 
 	int cpu = smp_processor_id();
 
-	if (!cpu_online(cpu))
-		return;
-
 	hard_irq_disable();
 	if (!cpumask_test_cpu(cpu, &cpus_state_saved)) {
 		crash_save_cpu(regs, cpu);
@@ -109,6 +114,9 @@ static void crash_kexec_prepare_cpus(int cpu)
 
 	printk(KERN_EMERG "Sending IPI to other CPUs\n");
 
+	if (crash_wake_offline)
+		ncpus = num_present_cpus() - 1;
+
 	crash_send_ipi(crash_ipi_callback);
 	smp_wmb();
 
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 66f33e7f8d40..f9fe2080ceb9 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -114,7 +114,7 @@ int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
 struct dma_map_ops dma_iommu_ops = {
 	.alloc			= dma_iommu_alloc_coherent,
 	.free			= dma_iommu_free_coherent,
-	.mmap			= dma_direct_mmap_coherent,
+	.mmap			= dma_nommu_mmap_coherent,
 	.map_sg			= dma_iommu_map_sg,
 	.unmap_sg		= dma_iommu_unmap_sg,
 	.dma_supported		= dma_iommu_dma_supported,
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index d0ea7860e02b..88f3963ca30f 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -46,10 +46,10 @@ static u64 swiotlb_powerpc_get_required(struct device *dev)
  * map_page, and unmap_page on highmem, use normal dma_ops
  * for everything else.
  */
-const struct dma_map_ops swiotlb_dma_ops = {
-	.alloc = __dma_direct_alloc_coherent,
-	.free = __dma_direct_free_coherent,
-	.mmap = dma_direct_mmap_coherent,
+const struct dma_map_ops powerpc_swiotlb_dma_ops = {
+	.alloc = __dma_nommu_alloc_coherent,
+	.free = __dma_nommu_free_coherent,
+	.mmap = dma_nommu_mmap_coherent,
 	.map_sg = swiotlb_map_sg_attrs,
 	.unmap_sg = swiotlb_unmap_sg_attrs,
 	.dma_supported = swiotlb_dma_supported,
@@ -89,7 +89,7 @@ static int ppc_swiotlb_bus_notify(struct notifier_block *nb,
 
 	/* May need to bounce if the device can't address all of DRAM */
 	if ((dma_get_mask(dev) + 1) < memblock_end_of_DRAM())
-		set_dma_ops(dev, &swiotlb_dma_ops);
+		set_dma_ops(dev, &powerpc_swiotlb_dma_ops);
 
 	return NOTIFY_DONE;
 }
@@ -121,7 +121,7 @@ static int __init check_swiotlb_enabled(void)
 	if (ppc_swiotlb_enable)
 		swiotlb_print_info();
 	else
-		swiotlb_free();
+		swiotlb_exit();
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 4194bbbbdb10..da20569de9d4 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -33,14 +33,14 @@ static u64 __maybe_unused get_pfn_limit(struct device *dev)
 	struct dev_archdata __maybe_unused *sd = &dev->archdata;
 
 #ifdef CONFIG_SWIOTLB
-	if (sd->max_direct_dma_addr && dev->dma_ops == &swiotlb_dma_ops)
+	if (sd->max_direct_dma_addr && dev->dma_ops == &powerpc_swiotlb_dma_ops)
 		pfn = min_t(u64, pfn, sd->max_direct_dma_addr >> PAGE_SHIFT);
 #endif
 
 	return pfn;
 }
 
-static int dma_direct_dma_supported(struct device *dev, u64 mask)
+static int dma_nommu_dma_supported(struct device *dev, u64 mask)
 {
 #ifdef CONFIG_PPC64
 	u64 limit = get_dma_offset(dev) + (memblock_end_of_DRAM() - 1);
@@ -62,7 +62,7 @@ static int dma_direct_dma_supported(struct device *dev, u64 mask)
 #endif
 }
 
-void *__dma_direct_alloc_coherent(struct device *dev, size_t size,
+void *__dma_nommu_alloc_coherent(struct device *dev, size_t size,
 				  dma_addr_t *dma_handle, gfp_t flag,
 				  unsigned long attrs)
 {
@@ -105,9 +105,6 @@ void *__dma_direct_alloc_coherent(struct device *dev, size_t size,
 	};
 #endif /* CONFIG_FSL_SOC */
 
-	/* ignore region specifiers */
-	flag  &= ~(__GFP_HIGHMEM);
-
 	page = alloc_pages_node(node, flag, get_order(size));
 	if (page == NULL)
 		return NULL;
@@ -119,7 +116,7 @@ void *__dma_direct_alloc_coherent(struct device *dev, size_t size,
 #endif
 }
 
-void __dma_direct_free_coherent(struct device *dev, size_t size,
+void __dma_nommu_free_coherent(struct device *dev, size_t size,
 				void *vaddr, dma_addr_t dma_handle,
 				unsigned long attrs)
 {
@@ -130,7 +127,7 @@ void __dma_direct_free_coherent(struct device *dev, size_t size,
 #endif
 }
 
-static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
+static void *dma_nommu_alloc_coherent(struct device *dev, size_t size,
 				       dma_addr_t *dma_handle, gfp_t flag,
 				       unsigned long attrs)
 {
@@ -139,8 +136,8 @@ static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 	/* The coherent mask may be smaller than the real mask, check if
 	 * we can really use the direct ops
 	 */
-	if (dma_direct_dma_supported(dev, dev->coherent_dma_mask))
-		return __dma_direct_alloc_coherent(dev, size, dma_handle,
+	if (dma_nommu_dma_supported(dev, dev->coherent_dma_mask))
+		return __dma_nommu_alloc_coherent(dev, size, dma_handle,
 						   flag, attrs);
 
 	/* Ok we can't ... do we have an iommu ? If not, fail */
@@ -154,15 +151,15 @@ static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 				    dev_to_node(dev));
 }
 
-static void dma_direct_free_coherent(struct device *dev, size_t size,
+static void dma_nommu_free_coherent(struct device *dev, size_t size,
 				     void *vaddr, dma_addr_t dma_handle,
 				     unsigned long attrs)
 {
 	struct iommu_table *iommu;
 
-	/* See comments in dma_direct_alloc_coherent() */
-	if (dma_direct_dma_supported(dev, dev->coherent_dma_mask))
-		return __dma_direct_free_coherent(dev, size, vaddr, dma_handle,
+	/* See comments in dma_nommu_alloc_coherent() */
+	if (dma_nommu_dma_supported(dev, dev->coherent_dma_mask))
+		return __dma_nommu_free_coherent(dev, size, vaddr, dma_handle,
 						  attrs);
 	/* Maybe we used an iommu ... */
 	iommu = get_iommu_table_base(dev);
@@ -175,7 +172,7 @@ static void dma_direct_free_coherent(struct device *dev, size_t size,
 	iommu_free_coherent(iommu, size, vaddr, dma_handle);
 }
 
-int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
+int dma_nommu_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
 			     void *cpu_addr, dma_addr_t handle, size_t size,
 			     unsigned long attrs)
 {
@@ -193,7 +190,7 @@ int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
 			       vma->vm_page_prot);
 }
 
-static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
+static int dma_nommu_map_sg(struct device *dev, struct scatterlist *sgl,
 			     int nents, enum dma_data_direction direction,
 			     unsigned long attrs)
 {
@@ -213,13 +210,13 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 	return nents;
 }
 
-static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
+static void dma_nommu_unmap_sg(struct device *dev, struct scatterlist *sg,
 				int nents, enum dma_data_direction direction,
 				unsigned long attrs)
 {
 }
 
-static u64 dma_direct_get_required_mask(struct device *dev)
+static u64 dma_nommu_get_required_mask(struct device *dev)
 {
 	u64 end, mask;
 
@@ -231,7 +228,7 @@ static u64 dma_direct_get_required_mask(struct device *dev)
 	return mask;
 }
 
-static inline dma_addr_t dma_direct_map_page(struct device *dev,
+static inline dma_addr_t dma_nommu_map_page(struct device *dev,
 					     struct page *page,
 					     unsigned long offset,
 					     size_t size,
@@ -246,7 +243,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 	return page_to_phys(page) + offset + get_dma_offset(dev);
 }
 
-static inline void dma_direct_unmap_page(struct device *dev,
+static inline void dma_nommu_unmap_page(struct device *dev,
 					 dma_addr_t dma_address,
 					 size_t size,
 					 enum dma_data_direction direction,
@@ -255,7 +252,7 @@ static inline void dma_direct_unmap_page(struct device *dev,
 }
 
 #ifdef CONFIG_NOT_COHERENT_CACHE
-static inline void dma_direct_sync_sg(struct device *dev,
+static inline void dma_nommu_sync_sg(struct device *dev,
 		struct scatterlist *sgl, int nents,
 		enum dma_data_direction direction)
 {
@@ -266,7 +263,7 @@ static inline void dma_direct_sync_sg(struct device *dev,
 		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
 }
 
-static inline void dma_direct_sync_single(struct device *dev,
+static inline void dma_nommu_sync_single(struct device *dev,
 					  dma_addr_t dma_handle, size_t size,
 					  enum dma_data_direction direction)
 {
@@ -274,24 +271,24 @@ static inline void dma_direct_sync_single(struct device *dev,
 }
 #endif
 
-const struct dma_map_ops dma_direct_ops = {
-	.alloc				= dma_direct_alloc_coherent,
-	.free				= dma_direct_free_coherent,
-	.mmap				= dma_direct_mmap_coherent,
-	.map_sg				= dma_direct_map_sg,
-	.unmap_sg			= dma_direct_unmap_sg,
-	.dma_supported			= dma_direct_dma_supported,
-	.map_page			= dma_direct_map_page,
-	.unmap_page			= dma_direct_unmap_page,
-	.get_required_mask		= dma_direct_get_required_mask,
+const struct dma_map_ops dma_nommu_ops = {
+	.alloc				= dma_nommu_alloc_coherent,
+	.free				= dma_nommu_free_coherent,
+	.mmap				= dma_nommu_mmap_coherent,
+	.map_sg				= dma_nommu_map_sg,
+	.unmap_sg			= dma_nommu_unmap_sg,
+	.dma_supported			= dma_nommu_dma_supported,
+	.map_page			= dma_nommu_map_page,
+	.unmap_page			= dma_nommu_unmap_page,
+	.get_required_mask		= dma_nommu_get_required_mask,
 #ifdef CONFIG_NOT_COHERENT_CACHE
-	.sync_single_for_cpu 		= dma_direct_sync_single,
-	.sync_single_for_device 	= dma_direct_sync_single,
-	.sync_sg_for_cpu 		= dma_direct_sync_sg,
-	.sync_sg_for_device 		= dma_direct_sync_sg,
+	.sync_single_for_cpu 		= dma_nommu_sync_single,
+	.sync_single_for_device 	= dma_nommu_sync_single,
+	.sync_sg_for_cpu 		= dma_nommu_sync_sg,
+	.sync_sg_for_device 		= dma_nommu_sync_sg,
 #endif
 };
-EXPORT_SYMBOL(dma_direct_ops);
+EXPORT_SYMBOL(dma_nommu_ops);
 
 int dma_set_coherent_mask(struct device *dev, u64 mask)
 {
@@ -302,7 +299,7 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 		 * is no dma_op->set_coherent_mask() so we have to do
 		 * things the hard way:
 		 */
-		if (get_dma_ops(dev) != &dma_direct_ops ||
+		if (get_dma_ops(dev) != &dma_nommu_ops ||
 		    get_iommu_table_base(dev) == NULL ||
 		    !dma_iommu_dma_supported(dev, mask))
 			return -EIO;
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 8bdc2f96c5d6..945e2c29ad2d 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -77,8 +77,6 @@ struct dt_cpu_feature {
  * Set up the base CPU
  */
 
-extern void __flush_tlb_power8(unsigned int action);
-extern void __flush_tlb_power9(unsigned int action);
 extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
 extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
 
@@ -92,27 +90,6 @@ static struct {
 
 static void (*init_pmu_registers)(void);
 
-static void cpufeatures_flush_tlb(void)
-{
-	/*
-	 * This is a temporary measure to keep equivalent TLB flush as the
-	 * cputable based setup code.
-	 */
-	switch (PVR_VER(mfspr(SPRN_PVR))) {
-	case PVR_POWER8:
-	case PVR_POWER8E:
-	case PVR_POWER8NVL:
-		__flush_tlb_power8(TLB_INVAL_SCOPE_GLOBAL);
-		break;
-	case PVR_POWER9:
-		__flush_tlb_power9(TLB_INVAL_SCOPE_GLOBAL);
-		break;
-	default:
-		pr_err("unknown CPU version for boot TLB flush\n");
-		break;
-	}
-}
-
 static void __restore_cpu_cpufeatures(void)
 {
 	/*
@@ -137,8 +114,6 @@ static void __restore_cpu_cpufeatures(void)
 
 	if (init_pmu_registers)
 		init_pmu_registers();
-
-	cpufeatures_flush_tlb();
 }
 
 static char dt_cpu_name[64];
@@ -157,7 +132,6 @@ static struct cpu_spec __initdata base_cpu_spec = {
 	.oprofile_type		= PPC_OPROFILE_INVALID,
 	.cpu_setup		= NULL,
 	.cpu_restore		= __restore_cpu_cpufeatures,
-	.flush_tlb		= NULL,
 	.machine_check_early	= NULL,
 	.platform		= NULL,
 };
@@ -412,7 +386,6 @@ static void init_pmu_power8(void)
 static int __init feat_enable_mce_power8(struct dt_cpu_feature *f)
 {
 	cur_cpu_spec->platform = "power8";
-	cur_cpu_spec->flush_tlb = __flush_tlb_power8;
 	cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p8;
 
 	return 1;
@@ -451,7 +424,6 @@ static void init_pmu_power9(void)
 static int __init feat_enable_mce_power9(struct dt_cpu_feature *f)
 {
 	cur_cpu_spec->platform = "power9";
-	cur_cpu_spec->flush_tlb = __flush_tlb_power9;
 	cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p9;
 
 	return 1;
@@ -752,8 +724,6 @@ static void __init cpufeatures_setup_finished(void)
 	system_registers.hfscr = mfspr(SPRN_HFSCR);
 	system_registers.fscr = mfspr(SPRN_FSCR);
 
-	cpufeatures_flush_tlb();
-
 	pr_info("final cpu/mmu features = 0x%016lx 0x%08x\n",
 		cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features);
 }
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index cbca0a667682..cc649809885e 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -740,6 +740,65 @@ static void *eeh_restore_dev_state(void *data, void *userdata)
 	return NULL;
 }
 
+int eeh_restore_vf_config(struct pci_dn *pdn)
+{
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+	u32 devctl, cmd, cap2, aer_capctl;
+	int old_mps;
+
+	if (edev->pcie_cap) {
+		/* Restore MPS */
+		old_mps = (ffs(pdn->mps) - 8) << 5;
+		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				     2, &devctl);
+		devctl &= ~PCI_EXP_DEVCTL_PAYLOAD;
+		devctl |= old_mps;
+		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				      2, devctl);
+
+		/* Disable Completion Timeout */
+		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP2,
+				     4, &cap2);
+		if (cap2 & 0x10) {
+			eeh_ops->read_config(pdn,
+					     edev->pcie_cap + PCI_EXP_DEVCTL2,
+					     4, &cap2);
+			cap2 |= 0x10;
+			eeh_ops->write_config(pdn,
+					      edev->pcie_cap + PCI_EXP_DEVCTL2,
+					      4, cap2);
+		}
+	}
+
+	/* Enable SERR and parity checking */
+	eeh_ops->read_config(pdn, PCI_COMMAND, 2, &cmd);
+	cmd |= (PCI_COMMAND_PARITY | PCI_COMMAND_SERR);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 2, cmd);
+
+	/* Enable report various errors */
+	if (edev->pcie_cap) {
+		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				     2, &devctl);
+		devctl &= ~PCI_EXP_DEVCTL_CERE;
+		devctl |= (PCI_EXP_DEVCTL_NFERE |
+			   PCI_EXP_DEVCTL_FERE |
+			   PCI_EXP_DEVCTL_URRE);
+		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				      2, devctl);
+	}
+
+	/* Enable ECRC generation and check */
+	if (edev->pcie_cap && edev->aer_cap) {
+		eeh_ops->read_config(pdn, edev->aer_cap + PCI_ERR_CAP,
+				     4, &aer_capctl);
+		aer_capctl |= (PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE);
+		eeh_ops->write_config(pdn, edev->aer_cap + PCI_ERR_CAP,
+				      4, aer_capctl);
+	}
+
+	return 0;
+}
+
 /**
  * pcibios_set_pcie_reset_state - Set PCI-E reset state
  * @dev: pci device struct
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 4f71e4c9beb7..beea2182d754 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -228,6 +228,7 @@ static void *eeh_report_error(void *data, void *userdata)
 
 	edev->in_error = true;
 	eeh_pcid_put(dev);
+	pci_uevent_ers(dev, PCI_ERS_RESULT_NONE);
 	return NULL;
 }
 
@@ -381,6 +382,10 @@ static void *eeh_report_resume(void *data, void *userdata)
 	driver->err_handler->resume(dev);
 
 	eeh_pcid_put(dev);
+	pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED);
+#ifdef CONFIG_PCI_IOV
+	eeh_ops->notify_resume(eeh_dev_to_pdn(edev));
+#endif
 	return NULL;
 }
 
@@ -416,6 +421,7 @@ static void *eeh_report_failure(void *data, void *userdata)
 	driver->err_handler->error_detected(dev, pci_channel_io_perm_failure);
 
 	eeh_pcid_put(dev);
+	pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT);
 	return NULL;
 }
 
@@ -440,7 +446,7 @@ static void *eeh_add_virt_device(void *data, void *userdata)
 			return NULL;
 	}
 
-#ifdef CONFIG_PPC_POWERNV
+#ifdef CONFIG_PCI_IOV
 	pci_iov_add_virtfn(edev->physfn, pdn->vf_index);
 #endif
 	return NULL;
@@ -496,7 +502,7 @@ static void *eeh_rmv_device(void *data, void *userdata)
 		(*removed)++;
 
 	if (edev->physfn) {
-#ifdef CONFIG_PPC_POWERNV
+#ifdef CONFIG_PCI_IOV
 		struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
 		pci_iov_remove_virtfn(edev->physfn, pdn->vf_index);
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index 797549289798..deed906dd8f1 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -48,7 +48,7 @@ static ssize_t eeh_show_##_name(struct device *dev,      \
 	                                                      \
 	return sprintf(buf, _format "\n", edev->_memb);       \
 }                                                        \
-static DEVICE_ATTR(_name, S_IRUGO, eeh_show_##_name, NULL);
+static DEVICE_ATTR(_name, 0444, eeh_show_##_name, NULL);
 
 EEH_SHOW_ATTR(eeh_mode,            mode,            "0x%x");
 EEH_SHOW_ATTR(eeh_pe_config_addr,  pe_config_addr,  "0x%x");
@@ -90,6 +90,65 @@ static ssize_t eeh_pe_state_store(struct device *dev,
 
 static DEVICE_ATTR_RW(eeh_pe_state);
 
+#ifdef CONFIG_PCI_IOV
+static ssize_t eeh_notify_resume_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+
+	if (!edev || !edev->pe)
+		return -ENODEV;
+
+	pdn = pci_get_pdn(pdev);
+	return sprintf(buf, "%d\n", pdn->last_allow_rc);
+}
+
+static ssize_t eeh_notify_resume_store(struct device *dev,
+				       struct device_attribute *attr,
+				       const char *buf, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+
+	if (!edev || !edev->pe || !eeh_ops->notify_resume)
+		return -ENODEV;
+
+	if (eeh_ops->notify_resume(pci_get_pdn(pdev)))
+		return -EIO;
+
+	return count;
+}
+static DEVICE_ATTR_RW(eeh_notify_resume);
+
+static int eeh_notify_resume_add(struct pci_dev *pdev)
+{
+	struct device_node *np;
+	int rc = 0;
+
+	np = pci_device_to_OF_node(pdev->is_physfn ? pdev : pdev->physfn);
+
+	if (of_property_read_bool(np, "ibm,is-open-sriov-pf"))
+		rc = device_create_file(&pdev->dev, &dev_attr_eeh_notify_resume);
+
+	return rc;
+}
+
+static void eeh_notify_resume_remove(struct pci_dev *pdev)
+{
+	struct device_node *np;
+
+	np = pci_device_to_OF_node(pdev->is_physfn ? pdev : pdev->physfn);
+
+	if (of_property_read_bool(np, "ibm,is-open-sriov-pf"))
+		device_remove_file(&pdev->dev, &dev_attr_eeh_notify_resume);
+}
+#else
+static inline int eeh_notify_resume_add(struct pci_dev *pdev) { return 0; }
+static inline void eeh_notify_resume_remove(struct pci_dev *pdev) { }
+#endif /* CONFIG_PCI_IOV */
+
 void eeh_sysfs_add_device(struct pci_dev *pdev)
 {
 	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
@@ -104,6 +163,7 @@ void eeh_sysfs_add_device(struct pci_dev *pdev)
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode);
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_state);
+	rc += eeh_notify_resume_add(pdev);
 
 	if (rc)
 		pr_warn("EEH: Unable to create sysfs entries\n");
@@ -129,6 +189,8 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev)
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_state);
 
+	eeh_notify_resume_remove(pdev);
+
 	if (edev)
 		edev->mode &= ~EEH_DEV_SYSFS;
 }
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e780e1fbf6c2..eb8d01bae8c6 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -211,7 +211,7 @@ transfer_to_handler_cont:
 	mflr	r9
 	lwz	r11,0(r9)		/* virtual address of handler */
 	lwz	r9,4(r9)		/* where to go when done */
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
 	mtspr	SPRN_NRI, r0
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -301,7 +301,7 @@ stack_ovf:
 	lis	r9,StackOverflow@ha
 	addi	r9,r9,StackOverflow@l
 	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
 	mtspr	SPRN_NRI, r0
 #endif
 	mtspr	SPRN_SRR0,r9
@@ -430,7 +430,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	lwz	r7,_NIP(r1)
 	lwz	r2,GPR2(r1)
 	lwz	r1,GPR1(r1)
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
 	mtspr	SPRN_NRI, r0
 #endif
 	mtspr	SPRN_SRR0,r7
@@ -727,7 +727,7 @@ fast_exception_return:
 	lwz	r10,_LINK(r11)
 	mtlr	r10
 	REST_GPR(10, r11)
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
 	mtspr	SPRN_NRI, r0
 #endif
 	mtspr	SPRN_SRR1,r9
@@ -978,7 +978,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	.globl exc_exit_restart
 exc_exit_restart:
 	lwz	r12,_NIP(r1)
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
 	mtspr	SPRN_NRI, r0
 #endif
 	mtspr	SPRN_SRR0,r12
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 3320bcac7192..2cb5109a7ea3 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -37,6 +37,11 @@
 #include <asm/tm.h>
 #include <asm/ppc-opcode.h>
 #include <asm/export.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/exception-64s.h>
+#else
+#include <asm/exception-64e.h>
+#endif
 
 /*
  * System calls.
@@ -128,10 +133,9 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 	 * of irq tracing is used, we additionally check that condition
 	 * is correct
 	 */
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_BUG)
-	lbz	r10,PACASOFTIRQEN(r13)
-	xori	r10,r10,1
-1:	tdnei	r10,0
+#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
+	lbz	r10,PACAIRQSOFTMASK(r13)
+1:	tdnei	r10,IRQS_ENABLED
 	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
 #endif
 
@@ -147,7 +151,7 @@ system_call:			/* label this so stack traces look sane */
 	/* We do need to set SOFTE in the stack frame or the return
 	 * from interrupt will be painful
 	 */
-	li	r10,1
+	li	r10,IRQS_ENABLED
 	std	r10,SOFTE(r1)
 
 	CURRENT_THREAD_INFO(r11, r1)
@@ -262,13 +266,23 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
+	ld	r2,GPR2(r1)
+	ld	r1,GPR1(r1)
+	mtlr	r4
+	mtcr	r5
+	mtspr	SPRN_SRR0,r7
+	mtspr	SPRN_SRR1,r8
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
+
+	/* exit to kernel */
 1:	ld	r2,GPR2(r1)
 	ld	r1,GPR1(r1)
 	mtlr	r4
 	mtcr	r5
 	mtspr	SPRN_SRR0,r7
 	mtspr	SPRN_SRR1,r8
-	RFI
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 .Lsyscall_error:
@@ -397,8 +411,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	mtmsrd	r10, 1
 	mtspr	SPRN_SRR0, r11
 	mtspr	SPRN_SRR1, r12
-
-	rfid
+	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 #endif
 _ASM_NOKPROBE_SYMBOL(system_call_common);
@@ -741,10 +754,10 @@ resume_kernel:
 	beq+	restore
 	/* Check that preempt_count() == 0 and interrupts are enabled */
 	lwz	r8,TI_PREEMPT(r9)
-	cmpwi	cr1,r8,0
+	cmpwi	cr0,r8,0
+	bne	restore
 	ld	r0,SOFTE(r1)
-	cmpdi	r0,0
-	crandc	eq,cr1*4+eq,eq
+	andi.	r0,r0,IRQS_DISABLED
 	bne	restore
 
 	/*
@@ -782,12 +795,12 @@ restore:
 	 * are about to re-enable interrupts
 	 */
 	ld	r5,SOFTE(r1)
-	lbz	r6,PACASOFTIRQEN(r13)
-	cmpwi	cr0,r5,0
-	beq	.Lrestore_irq_off
+	lbz	r6,PACAIRQSOFTMASK(r13)
+	andi.	r5,r5,IRQS_DISABLED
+	bne	.Lrestore_irq_off
 
 	/* We are enabling, were we already enabled ? Yes, just return */
-	cmpwi	cr0,r6,1
+	andi.	r6,r6,IRQS_DISABLED
 	beq	cr0,.Ldo_restore
 
 	/*
@@ -806,8 +819,8 @@ restore:
 	 */
 .Lrestore_no_replay:
 	TRACE_ENABLE_INTS
-	li	r0,1
-	stb	r0,PACASOFTIRQEN(r13);
+	li	r0,IRQS_ENABLED
+	stb	r0,PACAIRQSOFTMASK(r13);
 
 	/*
 	 * Final return path. BookE is handled in a different file
@@ -878,7 +891,7 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
 	REST_GPR(13, r1)
-1:
+
 	mtspr	SPRN_SRR1,r3
 
 	ld	r2,_CCR(r1)
@@ -891,8 +904,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ld	r3,GPR3(r1)
 	ld	r4,GPR4(r1)
 	ld	r1,GPR1(r1)
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
+
+1:	mtspr	SPRN_SRR1,r3
 
-	rfid
+	ld	r2,_CCR(r1)
+	mtcrf	0xFF,r2
+	ld	r2,_NIP(r1)
+	mtspr	SPRN_SRR0,r2
+
+	ld	r0,GPR0(r1)
+	ld	r2,GPR2(r1)
+	ld	r3,GPR3(r1)
+	ld	r4,GPR4(r1)
+	ld	r1,GPR1(r1)
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 #endif /* CONFIG_PPC_BOOK3E */
@@ -911,9 +938,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	beq	1f
 	rlwinm	r7,r7,0,~PACA_IRQ_HARD_DIS
 	stb	r7,PACAIRQHAPPENED(r13)
-1:	li	r0,0
-	stb	r0,PACASOFTIRQEN(r13);
-	TRACE_DISABLE_INTS
+1:
+#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
+	/* The interrupt should not have soft enabled. */
+	lbz	r7,PACAIRQSOFTMASK(r13)
+1:	tdeqi	r7,IRQS_ENABLED
+	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
+#endif
 	b	.Ldo_restore
 
 	/*
@@ -951,6 +982,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
  	bl	do_IRQ
 	b	ret_from_except
+1:	cmpwi	cr0,r3,0xf00
+	bne	1f
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	bl	performance_monitor_exception
+	b	ret_from_except
 1:	cmpwi	cr0,r3,0xe60
 	bne	1f
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
@@ -1027,15 +1063,15 @@ _GLOBAL(enter_rtas)
 	li	r0,0
 	mtcr	r0
 
-#ifdef CONFIG_BUG	
+#ifdef CONFIG_BUG
 	/* There is no way it is acceptable to get here with interrupts enabled,
 	 * check it with the asm equivalent of WARN_ON
 	 */
-	lbz	r0,PACASOFTIRQEN(r13)
-1:	tdnei	r0,0
+	lbz	r0,PACAIRQSOFTMASK(r13)
+1:	tdeqi	r0,IRQS_ENABLED
 	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
 #endif
-	
+
 	/* Hard-disable interrupts */
 	mfmsr	r6
 	rldicl	r7,r6,48,1
@@ -1073,12 +1109,23 @@ __enter_rtas:
 	
 	mtspr	SPRN_SRR0,r5
 	mtspr	SPRN_SRR1,r6
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 rtas_return_loc:
 	FIXUP_ENDIAN
 
+	/*
+	 * Clear RI and set SF before anything.
+	 */
+	mfmsr   r6
+	li	r0,MSR_RI
+	andc	r6,r6,r0
+	sldi	r0,r0,(MSR_SF_LG - MSR_RI_LG)
+	or	r6,r6,r0
+	sync
+	mtmsrd  r6
+
 	/* relocation is off at this point */
 	GET_PACA(r4)
 	clrldi	r4,r4,2			/* convert to realmode address */
@@ -1087,18 +1134,12 @@ rtas_return_loc:
 0:	mflr	r3
 	ld	r3,(1f-0b)(r3)		/* get &rtas_restore_regs */
 
-	mfmsr   r6
-	li	r0,MSR_RI
-	andc	r6,r6,r0
-	sync	
-	mtmsrd  r6
-        
         ld	r1,PACAR1(r4)           /* Restore our SP */
         ld	r4,PACASAVEDMSR(r4)     /* Restore our MSR */
 
 	mtspr	SPRN_SRR0,r3
 	mtspr	SPRN_SRR1,r4
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 _ASM_NOKPROBE_SYMBOL(__enter_rtas)
 _ASM_NOKPROBE_SYMBOL(rtas_return_loc)
@@ -1171,7 +1212,7 @@ _GLOBAL(enter_prom)
 	LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE)
 	andc	r11,r11,r12
 	mtsrr1	r11
-	rfid
+	RFI_TO_KERNEL
 #endif /* CONFIG_PPC_BOOK3E */
 
 1:	/* Return from OF */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index acd8ca76233e..ee832d344a5a 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -139,7 +139,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 	mfspr	r10,SPRN_ESR
 	SPECIAL_EXC_STORE(r10,ESR)
 
-	lbz	r10,PACASOFTIRQEN(r13)
+	lbz	r10,PACAIRQSOFTMASK(r13)
 	SPECIAL_EXC_STORE(r10,SOFTE)
 	ld	r10,_NIP(r1)
 	SPECIAL_EXC_STORE(r10,CSRR0)
@@ -206,17 +206,17 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_MAS8,r10
 END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 
-	lbz	r6,PACASOFTIRQEN(r13)
+	lbz	r6,PACAIRQSOFTMASK(r13)
 	ld	r5,SOFTE(r1)
 
 	/* Interrupts had better not already be enabled... */
-	twnei	r6,0
+	tweqi	r6,IRQS_ENABLED
 
-	cmpwi	cr0,r5,0
-	beq	1f
+	andi.	r6,r5,IRQS_DISABLED
+	bne	1f
 
 	TRACE_ENABLE_INTS
-	stb	r5,PACASOFTIRQEN(r13)
+	stb	r5,PACAIRQSOFTMASK(r13)
 1:
 	/*
 	 * Restore PACAIRQHAPPENED rather than setting it based on
@@ -351,9 +351,9 @@ ret_from_mc_except:
 #define PROLOG_ADDITION_NONE_MC(n)
 
 #define PROLOG_ADDITION_MASKABLE_GEN(n)					    \
-	lbz	r10,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */	    \
-	cmpwi	cr0,r10,0;		/* yes -> go out of line */	    \
-	beq	masked_interrupt_book3e_##n
+	lbz	r10,PACAIRQSOFTMASK(r13);	/* are irqs soft-masked? */ \
+	andi.	r10,r10,IRQS_DISABLED;	/* yes -> go out of line */ \
+	bne	masked_interrupt_book3e_##n
 
 #define PROLOG_ADDITION_2REGS_GEN(n)					    \
 	std	r14,PACA_EXGEN+EX_R14(r13);				    \
@@ -397,7 +397,7 @@ exc_##n##_common:							    \
 	mfspr	r8,SPRN_XER;		/* save XER in stackframe */	    \
 	ld	r9,excf+EX_R1(r13);	/* load orig r1 back from PACA */   \
 	lwz	r10,excf+EX_CR(r13);	/* load orig CR back from PACA	*/  \
-	lbz	r11,PACASOFTIRQEN(r13);	/* get current IRQ softe */	    \
+	lbz	r11,PACAIRQSOFTMASK(r13); /* get current IRQ softe */	    \
 	ld	r12,exception_marker@toc(r2);				    \
 	li	r0,0;							    \
 	std	r3,GPR10(r1);		/* save r10 to stackframe */	    \
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e441b469dc8f..243d072a225a 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -256,7 +256,7 @@ BEGIN_FTR_SECTION
 	LOAD_HANDLER(r12, machine_check_handle_early)
 1:	mtspr	SPRN_SRR0,r12
 	mtspr	SPRN_SRR1,r11
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 2:
 	/* Stack overflow. Stay on emergency stack and panic.
@@ -445,7 +445,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	li	r3,MSR_ME
 	andc	r10,r10,r3		/* Turn off MSR_ME */
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 2:
 	/*
@@ -463,7 +463,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	 */
 	bl	machine_check_queue_event
 	MACHINE_CHECK_HANDLER_WINDUP
-	rfid
+	RFI_TO_USER_OR_KERNEL
 9:
 	/* Deliver the machine check to host kernel in V mode. */
 	MACHINE_CHECK_HANDLER_WINDUP
@@ -598,6 +598,9 @@ EXC_COMMON_BEGIN(slb_miss_common)
 	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
 	std	r10,PACA_EXSLB+EX_LR(r13)	/* save LR */
 
+	andi.	r9,r11,MSR_PR	// Check for exception from userspace
+	cmpdi	cr4,r9,MSR_PR	// And save the result in CR4 for later
+
 	/*
 	 * Test MSR_RI before calling slb_allocate_realmode, because the
 	 * MSR in r11 gets clobbered. However we still want to allocate
@@ -624,9 +627,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 
 	/* All done -- return from exception. */
 
+	bne	cr4,1f		/* returning to kernel */
+
 .machine	push
 .machine	"power4"
 	mtcrf	0x80,r9
+	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
 	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
 	mtcrf	0x02,r9		/* I/D indication is in cr6 */
 	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
@@ -640,8 +646,29 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	ld	r11,PACA_EXSLB+EX_R11(r13)
 	ld	r12,PACA_EXSLB+EX_R12(r13)
 	ld	r13,PACA_EXSLB+EX_R13(r13)
-	rfid
+	RFI_TO_USER
 	b	.	/* prevent speculative execution */
+1:
+.machine	push
+.machine	"power4"
+	mtcrf	0x80,r9
+	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
+	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
+	mtcrf	0x02,r9		/* I/D indication is in cr6 */
+	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
+.machine	pop
+
+	RESTORE_CTR(r9, PACA_EXSLB)
+	RESTORE_PPR_PACA(PACA_EXSLB, r9)
+	mr	r3,r12
+	ld	r9,PACA_EXSLB+EX_R9(r13)
+	ld	r10,PACA_EXSLB+EX_R10(r13)
+	ld	r11,PACA_EXSLB+EX_R11(r13)
+	ld	r12,PACA_EXSLB+EX_R12(r13)
+	ld	r13,PACA_EXSLB+EX_R13(r13)
+	RFI_TO_KERNEL
+	b	.	/* prevent speculative execution */
+
 
 2:	std     r3,PACA_EXSLB+EX_DAR(r13)
 	mr	r3,r12
@@ -651,7 +678,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	mtspr	SPRN_SRR0,r10
 	ld	r10,PACAKMSR(r13)
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 8:	std     r3,PACA_EXSLB+EX_DAR(r13)
@@ -662,7 +689,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	mtspr	SPRN_SRR0,r10
 	ld	r10,PACAKMSR(r13)
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 EXC_COMMON_BEGIN(unrecov_slb)
@@ -691,10 +718,12 @@ EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100)
 hardware_interrupt_hv:
 	BEGIN_FTR_SECTION
 		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common,
-					    EXC_HV, SOFTEN_TEST_HV)
+					    EXC_HV, SOFTEN_TEST_HV,
+					    IRQS_DISABLED)
 	FTR_SECTION_ELSE
 		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common,
-					    EXC_STD, SOFTEN_TEST_PR)
+					    EXC_STD, SOFTEN_TEST_PR,
+					    IRQS_DISABLED)
 	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 EXC_REAL_END(hardware_interrupt, 0x500, 0x100)
 
@@ -702,9 +731,13 @@ EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100)
 	.globl hardware_interrupt_relon_hv;
 hardware_interrupt_relon_hv:
 	BEGIN_FTR_SECTION
-		_MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_HV, SOFTEN_TEST_HV)
+		_MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common,
+						  EXC_HV, SOFTEN_TEST_HV,
+						  IRQS_DISABLED)
 	FTR_SECTION_ELSE
-		_MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_STD, SOFTEN_TEST_PR)
+		_MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common,
+						  EXC_STD, SOFTEN_TEST_PR,
+						  IRQS_DISABLED)
 	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
 EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
 
@@ -800,8 +833,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 
 
-EXC_REAL_MASKABLE(decrementer, 0x900, 0x80)
-EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900)
+EXC_REAL_MASKABLE(decrementer, 0x900, 0x80, IRQS_DISABLED)
+EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900, IRQS_DISABLED)
 TRAMP_KVM(PACA_EXGEN, 0x900)
 EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt)
 
@@ -812,8 +845,8 @@ TRAMP_KVM_HV(PACA_EXGEN, 0x980)
 EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt)
 
 
-EXC_REAL_MASKABLE(doorbell_super, 0xa00, 0x100)
-EXC_VIRT_MASKABLE(doorbell_super, 0x4a00, 0x100, 0xa00)
+EXC_REAL_MASKABLE(doorbell_super, 0xa00, 0x100, IRQS_DISABLED)
+EXC_VIRT_MASKABLE(doorbell_super, 0x4a00, 0x100, 0xa00, IRQS_DISABLED)
 TRAMP_KVM(PACA_EXGEN, 0xa00)
 #ifdef CONFIG_PPC_DOORBELL
 EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, doorbell_exception)
@@ -901,7 +934,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception)
 	mtspr	SPRN_SRR0,r10 ; 				\
 	ld	r10,PACAKMSR(r13) ;				\
 	mtspr	SPRN_SRR1,r10 ; 				\
-	rfid ; 							\
+	RFI_TO_KERNEL ;						\
 	b	. ;	/* prevent speculative execution */
 
 #ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH
@@ -917,7 +950,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)				\
 	xori	r12,r12,MSR_LE ;				\
 	mtspr	SPRN_SRR1,r12 ;					\
 	mr	r13,r9 ;					\
-	rfid ;		/* return to userspace */		\
+	RFI_TO_USER ;	/* return to userspace */		\
 	b	. ;	/* prevent speculative execution */
 #else
 #define SYSCALL_FASTENDIAN_TEST
@@ -1025,7 +1058,7 @@ EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt)
  * mode.
  */
 __EXC_REAL_OOL_HV_DIRECT(hmi_exception, 0xe60, 0x20, hmi_exception_early)
-__TRAMP_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60)
+__TRAMP_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60, IRQS_DISABLED)
 EXC_VIRT_NONE(0x4e60, 0x20)
 TRAMP_KVM_HV(PACA_EXGEN, 0xe60)
 TRAMP_REAL_BEGIN(hmi_exception_early)
@@ -1063,7 +1096,7 @@ TRAMP_REAL_BEGIN(hmi_exception_early)
 	mtcr	r11
 	REST_GPR(11, r1)
 	ld	r1,GPR1(r1)
-	hrfid
+	HRFI_TO_USER_OR_KERNEL
 
 1:	mtcr	r11
 	REST_GPR(11, r1)
@@ -1083,8 +1116,8 @@ EXC_COMMON_BEGIN(hmi_exception_common)
 EXCEPTION_COMMON(PACA_EXGEN, 0xe60, hmi_exception_common, handle_hmi_exception,
         ret_from_except, FINISH_NAP;ADD_NVGPRS;ADD_RECONCILE;RUNLATCH_ON)
 
-EXC_REAL_OOL_MASKABLE_HV(h_doorbell, 0xe80, 0x20)
-EXC_VIRT_OOL_MASKABLE_HV(h_doorbell, 0x4e80, 0x20, 0xe80)
+EXC_REAL_OOL_MASKABLE_HV(h_doorbell, 0xe80, 0x20, IRQS_DISABLED)
+EXC_VIRT_OOL_MASKABLE_HV(h_doorbell, 0x4e80, 0x20, 0xe80, IRQS_DISABLED)
 TRAMP_KVM_HV(PACA_EXGEN, 0xe80)
 #ifdef CONFIG_PPC_DOORBELL
 EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, doorbell_exception)
@@ -1093,8 +1126,8 @@ EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, unknown_exception)
 #endif
 
 
-EXC_REAL_OOL_MASKABLE_HV(h_virt_irq, 0xea0, 0x20)
-EXC_VIRT_OOL_MASKABLE_HV(h_virt_irq, 0x4ea0, 0x20, 0xea0)
+EXC_REAL_OOL_MASKABLE_HV(h_virt_irq, 0xea0, 0x20, IRQS_DISABLED)
+EXC_VIRT_OOL_MASKABLE_HV(h_virt_irq, 0x4ea0, 0x20, 0xea0, IRQS_DISABLED)
 TRAMP_KVM_HV(PACA_EXGEN, 0xea0)
 EXC_COMMON_ASYNC(h_virt_irq_common, 0xea0, do_IRQ)
 
@@ -1105,8 +1138,8 @@ EXC_REAL_NONE(0xee0, 0x20)
 EXC_VIRT_NONE(0x4ee0, 0x20)
 
 
-EXC_REAL_OOL(performance_monitor, 0xf00, 0x20)
-EXC_VIRT_OOL(performance_monitor, 0x4f00, 0x20, 0xf00)
+EXC_REAL_OOL_MASKABLE(performance_monitor, 0xf00, 0x20, IRQS_PMI_DISABLED)
+EXC_VIRT_OOL_MASKABLE(performance_monitor, 0x4f00, 0x20, 0xf00, IRQS_PMI_DISABLED)
 TRAMP_KVM(PACA_EXGEN, 0xf00)
 EXC_COMMON_ASYNC(performance_monitor_common, 0xf00, performance_monitor_exception)
 
@@ -1314,11 +1347,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	ld	r11,PACA_EXGEN+EX_R11(r13)
 	ld	r12,PACA_EXGEN+EX_R12(r13)
 	ld	r13,PACA_EXGEN+EX_R13(r13)
-	HRFID
+	HRFI_TO_UNKNOWN
 	b	.
 #endif
 
-EXC_COMMON_HV(denorm_common, 0x1500, unknown_exception)
+EXC_COMMON(denorm_common, 0x1500, unknown_exception)
 
 
 #ifdef CONFIG_CBE_RAS
@@ -1418,10 +1451,90 @@ masked_##_H##interrupt:					\
 	ld	r10,PACA_EXGEN+EX_R10(r13);		\
 	ld	r11,PACA_EXGEN+EX_R11(r13);		\
 	/* returns to kernel where r13 must be set up, so don't restore it */ \
-	##_H##rfid;					\
+	##_H##RFI_TO_KERNEL;				\
 	b	.;					\
 	MASKED_DEC_HANDLER(_H)
 
+TRAMP_REAL_BEGIN(rfi_flush_fallback)
+	SET_SCRATCH0(r13);
+	GET_PACA(r13);
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	mfctr	r9
+	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
+	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
+	mtctr	r11
+	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+	/* order ld/st prior to dcbt stop all streams with flushing */
+	sync
+
+	/*
+	 * The load adresses are at staggered offsets within cachelines,
+	 * which suits some pipelines better (on others it should not
+	 * hurt).
+	 */
+1:
+	ld	r11,(0x80 + 8)*0(r10)
+	ld	r11,(0x80 + 8)*1(r10)
+	ld	r11,(0x80 + 8)*2(r10)
+	ld	r11,(0x80 + 8)*3(r10)
+	ld	r11,(0x80 + 8)*4(r10)
+	ld	r11,(0x80 + 8)*5(r10)
+	ld	r11,(0x80 + 8)*6(r10)
+	ld	r11,(0x80 + 8)*7(r10)
+	addi	r10,r10,0x80*8
+	bdnz	1b
+
+	mtctr	r9
+	ld	r9,PACA_EXRFI+EX_R9(r13)
+	ld	r10,PACA_EXRFI+EX_R10(r13)
+	ld	r11,PACA_EXRFI+EX_R11(r13)
+	GET_SCRATCH0(r13);
+	rfid
+
+TRAMP_REAL_BEGIN(hrfi_flush_fallback)
+	SET_SCRATCH0(r13);
+	GET_PACA(r13);
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	mfctr	r9
+	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
+	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
+	mtctr	r11
+	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+	/* order ld/st prior to dcbt stop all streams with flushing */
+	sync
+
+	/*
+	 * The load adresses are at staggered offsets within cachelines,
+	 * which suits some pipelines better (on others it should not
+	 * hurt).
+	 */
+1:
+	ld	r11,(0x80 + 8)*0(r10)
+	ld	r11,(0x80 + 8)*1(r10)
+	ld	r11,(0x80 + 8)*2(r10)
+	ld	r11,(0x80 + 8)*3(r10)
+	ld	r11,(0x80 + 8)*4(r10)
+	ld	r11,(0x80 + 8)*5(r10)
+	ld	r11,(0x80 + 8)*6(r10)
+	ld	r11,(0x80 + 8)*7(r10)
+	addi	r10,r10,0x80*8
+	bdnz	1b
+
+	mtctr	r9
+	ld	r9,PACA_EXRFI+EX_R9(r13)
+	ld	r10,PACA_EXRFI+EX_R10(r13)
+	ld	r11,PACA_EXRFI+EX_R11(r13)
+	GET_SCRATCH0(r13);
+	hrfid
+
 /*
  * Real mode exceptions actually use this too, but alternate
  * instruction code patches (which end up in the common .text area)
@@ -1441,7 +1554,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_interrupt)
 	addi	r13, r13, 4
 	mtspr	SPRN_SRR0, r13
 	GET_SCRATCH0(r13)
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
@@ -1453,7 +1566,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
 	addi	r13, r13, 4
 	mtspr	SPRN_HSRR0, r13
 	GET_SCRATCH0(r13)
-	hrfid
+	HRFI_TO_KERNEL
 	b	.
 #endif
 
@@ -1521,7 +1634,7 @@ USE_TEXT_SECTION()
 	.balign	IFETCH_ALIGN_BYTES
 do_hash_page:
 #ifdef CONFIG_PPC_BOOK3S_64
-	lis	r0,(DSISR_BAD_FAULT_64S|DSISR_DABRMATCH)@h
+	lis	r0,(DSISR_BAD_FAULT_64S | DSISR_DABRMATCH | DSISR_KEYFAULT)@h
 	ori	r0,r0,DSISR_BAD_FAULT_64S@l
 	and.	r0,r4,r0		/* weird error? */
 	bne-	handle_page_fault	/* if not, try to insert a HPTE */
@@ -1717,6 +1830,8 @@ BEGIN_FTR_SECTION
 FTR_SECTION_ELSE
 	beq	hardware_interrupt_common
 ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_300)
+	cmpwi	r3,0xf00
+	beq	performance_monitor_common
 BEGIN_FTR_SECTION
 	cmpwi	r3,0xa00
 	beq	h_doorbell_common_msgclr
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 04ea5c04fd24..3c2c2688918f 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -1462,25 +1462,6 @@ static void fadump_init_files(void)
 	return;
 }
 
-static int fadump_panic_event(struct notifier_block *this,
-			      unsigned long event, void *ptr)
-{
-	/*
-	 * If firmware-assisted dump has been registered then trigger
-	 * firmware-assisted dump and let firmware handle everything
-	 * else. If this returns, then fadump was not registered, so
-	 * go through the rest of the panic path.
-	 */
-	crash_fadump(NULL, ptr);
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block fadump_panic_block = {
-	.notifier_call = fadump_panic_event,
-	.priority = INT_MIN /* may not return; must be done last */
-};
-
 /*
  * Prepare for firmware-assisted dump.
  */
@@ -1513,9 +1494,6 @@ int __init setup_fadump(void)
 		init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
 	fadump_init_files();
 
-	atomic_notifier_chain_register(&panic_notifier_list,
-					&fadump_panic_block);
-
 	return 1;
 }
 subsys_initcall(setup_fadump);
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index aa71a90f5222..a61151a6ea5e 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -765,8 +765,8 @@ _GLOBAL(pmac_secondary_start)
 	/* Mark interrupts soft and hard disabled (they might be enabled
 	 * in the PACA when doing hotplug)
 	 */
-	li	r0,0
-	stb	r0,PACASOFTIRQEN(r13)
+	li	r0,IRQS_DISABLED
+	stb	r0,PACAIRQSOFTMASK(r13)
 	li	r0,PACA_IRQ_HARD_DIS
 	stb	r0,PACAIRQHAPPENED(r13)
 
@@ -822,7 +822,8 @@ __secondary_start:
 	/* Mark interrupts soft and hard disabled (they might be enabled
 	 * in the PACA when doing hotplug)
 	 */
-	stb	r7,PACASOFTIRQEN(r13)
+	li	r7,IRQS_DISABLED
+	stb	r7,PACAIRQSOFTMASK(r13)
 	li	r0,PACA_IRQ_HARD_DIS
 	stb	r0,PACAIRQHAPPENED(r13)
 
@@ -988,8 +989,8 @@ start_here_common:
 	/* Mark interrupts soft and hard disabled (they might be enabled
 	 * in the PACA when doing hotplug)
 	 */
-	li	r0,0
-	stb	r0,PACASOFTIRQEN(r13)
+	li	r0,IRQS_DISABLED
+	stb	r0,PACAIRQSOFTMASK(r13)
 	li	r0,PACA_IRQ_HARD_DIS
 	stb	r0,PACAIRQHAPPENED(r13)
 
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 4fee00d414e8..d8670a37d70c 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -33,23 +33,6 @@
 #include <asm/fixmap.h>
 #include <asm/export.h>
 
-/* Macro to make the code more readable. */
-#ifdef CONFIG_8xx_CPU6
-#define SPRN_MI_TWC_ADDR	0x2b80
-#define SPRN_MI_RPN_ADDR	0x2d80
-#define SPRN_MD_TWC_ADDR	0x3b80
-#define SPRN_MD_RPN_ADDR	0x3d80
-
-#define MTSPR_CPU6(spr, reg, treg)	\
-	li	treg, spr##_ADDR;	\
-	stw	treg, 12(r0);		\
-	lwz	treg, 12(r0);		\
-	mtspr	spr, reg
-#else
-#define MTSPR_CPU6(spr, reg, treg)	\
-	mtspr	spr, reg
-#endif
-
 #if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000
 /* By simply checking Address >= 0x80000000, we know if its a kernel address */
 #define SIMPLE_KERNEL_ADDRESS		1
@@ -69,11 +52,7 @@
  * Value for the bits that have fixed value in RPN entries.
  * Also used for tagging DAR for DTLBerror.
  */
-#ifdef CONFIG_PPC_16K_PAGES
-#define RPN_PATTERN	(0x00f0 | MD_SPS16K)
-#else
 #define RPN_PATTERN	0x00f0
-#endif
 
 #define PAGE_SHIFT_512K		19
 #define PAGE_SHIFT_8M		23
@@ -134,15 +113,12 @@ turn_on_mmu:
  * task's thread_struct.
  */
 #define EXCEPTION_PROLOG	\
-	EXCEPTION_PROLOG_0;	\
+	mtspr	SPRN_SPRG_SCRATCH0, r10;	\
+	mtspr	SPRN_SPRG_SCRATCH1, r11;	\
 	mfcr	r10;		\
 	EXCEPTION_PROLOG_1;	\
 	EXCEPTION_PROLOG_2
 
-#define EXCEPTION_PROLOG_0	\
-	mtspr	SPRN_SPRG_SCRATCH0,r10;	\
-	mtspr	SPRN_SPRG_SCRATCH1,r11
-
 #define EXCEPTION_PROLOG_1	\
 	mfspr	r11,SPRN_SRR1;		/* check whether user or kernel */ \
 	andi.	r11,r11,MSR_PR;	\
@@ -177,13 +153,6 @@ turn_on_mmu:
 	SAVE_2GPRS(7, r11)
 
 /*
- * Exception exit code.
- */
-#define EXCEPTION_EPILOG_0	\
-	mfspr	r10,SPRN_SPRG_SCRATCH0;	\
-	mfspr	r11,SPRN_SPRG_SCRATCH1
-
-/*
  * Note: code which follows this uses cr0.eq (set if from kernel),
  * r11, r12 (SRR0), and r9 (SRR1).
  *
@@ -326,15 +295,10 @@ SystemCall:
 #endif
 
 InstructionTLBMiss:
-#if defined(CONFIG_8xx_CPU6) || defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
-	mtspr	SPRN_SPRG_SCRATCH2, r3
-#endif
-	EXCEPTION_PROLOG_0
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
-	lis	r10, (itlb_miss_counter - PAGE_OFFSET)@ha
-	lwz	r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10)
-	addi	r11, r11, 1
-	stw	r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10)
+	mtspr	SPRN_SPRG_SCRATCH0, r10
+	mtspr	SPRN_SPRG_SCRATCH1, r11
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
+	mtspr	SPRN_SPRG_SCRATCH2, r12
 #endif
 
 	/* If we are faulting a kernel address, we have to use the
@@ -345,7 +309,7 @@ InstructionTLBMiss:
 	/* Only modules will cause ITLB Misses as we always
 	 * pin the first 8MB of kernel memory */
 #if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
-	mfcr	r3
+	mfcr	r12
 #endif
 #ifdef ITLB_MISS_KERNEL
 #if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT)
@@ -388,40 +352,46 @@ _ENTRY(ITLBMiss_cmp)
 	lwz	r10, 0(r10)	/* Get the pte */
 4:
 #if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
-	mtcr	r3
+	mtcr	r12
 #endif
-	/* Insert the APG into the TWC from the Linux PTE. */
-	rlwimi	r11, r10, 0, 25, 26
-	/* Load the MI_TWC with the attributes for this "segment." */
-	MTSPR_CPU6(SPRN_MI_TWC, r11, r3)	/* Set segment attributes */
 
-#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES)
-	rlwimi	r10, r11, 1, MI_SPS16K
-#endif
 #ifdef CONFIG_SWAP
-	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
-	and	r11, r11, r10
-	rlwimi	r10, r11, 0, _PAGE_PRESENT
+	rlwinm	r11, r10, 31, _PAGE_ACCESSED >> 1
 #endif
-	li	r11, RPN_PATTERN
+	/* Load the MI_TWC with the attributes for this "segment." */
+	mtspr	SPRN_MI_TWC, r11	/* Set segment attributes */
+
+	li	r11, RPN_PATTERN | 0x200
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 20-23 and 28 must be clear.
-	 * Software indicator bits 24, 25, 26, and 27 must be
+	 * Software indicator bits 20 and 23 must be clear.
+	 * Software indicator bits 22, 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES)
-	rlwimi	r10, r11, 0, 0x0ff0	/* Set 24-27, clear 20-23 */
-#else
-	rlwimi	r10, r11, 0, 0x0ff8	/* Set 24-27, clear 20-23,28 */
-#endif
-	MTSPR_CPU6(SPRN_MI_RPN, r10, r3)	/* Update TLB entry */
+	rlwimi	r11, r10, 4, 0x0400	/* Copy _PAGE_EXEC into bit 21 */
+	rlwimi	r10, r11, 0, 0x0ff0	/* Set 22, 24-27, clear 20,23 */
+	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
 
 	/* Restore registers */
-#if defined(CONFIG_8xx_CPU6) || defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
-	mfspr	r3, SPRN_SPRG_SCRATCH2
+_ENTRY(itlb_miss_exit_1)
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
+	mfspr	r12, SPRN_SPRG_SCRATCH2
+#endif
+	rfi
+#ifdef CONFIG_PERF_EVENTS
+_ENTRY(itlb_miss_perf)
+	lis	r10, (itlb_miss_counter - PAGE_OFFSET)@ha
+	lwz	r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10)
+	addi	r11, r11, 1
+	stw	r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10)
+#endif
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
+	mfspr	r12, SPRN_SPRG_SCRATCH2
 #endif
-	EXCEPTION_EPILOG_0
 	rfi
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -436,7 +406,6 @@ _ENTRY(ITLBMiss_cmp)
 	rlwinm	r10, r11, 0, ~HUGEPD_SHIFT_MASK
 #endif
 	lwz	r10, 0(r10)	/* Get the pte */
-	rlwinm	r11, r11, 0, 0xf
 	b	4b
 
 20:	/* 512k pages */
@@ -445,21 +414,15 @@ _ENTRY(ITLBMiss_cmp)
 	/* Add level 2 base */
 	rlwimi	r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1
 	lwz	r10, 0(r10)	/* Get the pte */
-	rlwinm	r11, r11, 0, 0xf
 	b	4b
 #endif
 
 	. = 0x1200
 DataStoreTLBMiss:
-	mtspr	SPRN_SPRG_SCRATCH2, r3
-	EXCEPTION_PROLOG_0
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
-	lis	r10, (dtlb_miss_counter - PAGE_OFFSET)@ha
-	lwz	r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
-	addi	r11, r11, 1
-	stw	r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
-#endif
-	mfcr	r3
+	mtspr	SPRN_SPRG_SCRATCH0, r10
+	mtspr	SPRN_SPRG_SCRATCH1, r11
+	mtspr	SPRN_SPRG_SCRATCH2, r12
+	mfcr	r12
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
@@ -499,59 +462,49 @@ _ENTRY(DTLBMiss_jmp)
 	rlwimi	r10, r11, 0, 0, 32 - PAGE_SHIFT - 1	/* Add level 2 base */
 	lwz	r10, 0(r10)	/* Get the pte */
 4:
-	mtcr	r3
+	mtcr	r12
 
-	/* Insert the Guarded flag and APG into the TWC from the Linux PTE.
-	 * It is bit 26-27 of both the Linux PTE and the TWC (at least
+	/* Insert the Guarded flag into the TWC from the Linux PTE.
+	 * It is bit 27 of both the Linux PTE and the TWC (at least
 	 * I got that right :-).  It will be better when we can put
 	 * this into the Linux pgd/pmd and load it in the operation
 	 * above.
 	 */
-	rlwimi	r11, r10, 0, 26, 27
-	/* Insert the WriteThru flag into the TWC from the Linux PTE.
-	 * It is bit 25 in the Linux PTE and bit 30 in the TWC
-	 */
-	rlwimi	r11, r10, 32-5, 30, 30
-	MTSPR_CPU6(SPRN_MD_TWC, r11, r3)
-
-	/* In 4k pages mode, SPS (bit 28) in RPN must match PS[1] (bit 29)
-	 * In 16k pages mode, SPS is always 1 */
-#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES)
-	rlwimi	r10, r11, 1, MD_SPS16K
-#endif
-	/* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
-	 * We also need to know if the insn is a load/store, so:
-	 * Clear _PAGE_PRESENT and load that which will
-	 * trap into DTLB Error with store bit set accordinly.
-	 */
-	/* PRESENT=0x1, ACCESSED=0x20
-	 * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
-	 * r10 = (r10 & ~PRESENT) | r11;
-	 */
+	rlwimi	r11, r10, 0, _PAGE_GUARDED
 #ifdef CONFIG_SWAP
-	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
-	and	r11, r11, r10
-	rlwimi	r10, r11, 0, _PAGE_PRESENT
+	/* _PAGE_ACCESSED has to be set. We use second APG bit for that, 0
+	 * on that bit will represent a Non Access group
+	 */
+	rlwinm	r11, r10, 31, _PAGE_ACCESSED >> 1
 #endif
+	mtspr	SPRN_MD_TWC, r11
+
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 22 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
 	li	r11, RPN_PATTERN
-#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES)
 	rlwimi	r10, r11, 0, 24, 27	/* Set 24-27 */
-#else
-	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
-#endif
-	rlwimi	r10, r11, 0, 20, 20	/* clear 20 */
-	MTSPR_CPU6(SPRN_MD_RPN, r10, r3)	/* Update TLB entry */
+	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
 
 	/* Restore registers */
-	mfspr	r3, SPRN_SPRG_SCRATCH2
 	mtspr	SPRN_DAR, r11	/* Tag DAR */
-	EXCEPTION_EPILOG_0
+_ENTRY(dtlb_miss_exit_1)
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	mfspr	r12, SPRN_SPRG_SCRATCH2
+	rfi
+#ifdef CONFIG_PERF_EVENTS
+_ENTRY(dtlb_miss_perf)
+	lis	r10, (dtlb_miss_counter - PAGE_OFFSET)@ha
+	lwz	r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
+	addi	r11, r11, 1
+	stw	r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
+#endif
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	mfspr	r12, SPRN_SPRG_SCRATCH2
 	rfi
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -566,7 +519,6 @@ _ENTRY(DTLBMiss_jmp)
 	rlwinm	r10, r11, 0, ~HUGEPD_SHIFT_MASK
 #endif
 	lwz	r10, 0(r10)	/* Get the pte */
-	rlwinm	r11, r11, 0, 0xf
 	b	4b
 
 20:	/* 512k pages */
@@ -575,7 +527,6 @@ _ENTRY(DTLBMiss_jmp)
 	/* Add level 2 base */
 	rlwimi	r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1
 	lwz	r10, 0(r10)	/* Get the pte */
-	rlwinm	r11, r11, 0, 0xf
 	b	4b
 #endif
 
@@ -601,7 +552,8 @@ itlbie:
  */
 	. = 0x1400
 DataTLBError:
-	EXCEPTION_PROLOG_0
+	mtspr	SPRN_SPRG_SCRATCH0, r10
+	mtspr	SPRN_SPRG_SCRATCH1, r11
 	mfcr	r10
 
 	mfspr	r11, SPRN_DAR
@@ -636,7 +588,8 @@ dtlbie:
  */
 	. = 0x1c00
 DataBreakpoint:
-	EXCEPTION_PROLOG_0
+	mtspr	SPRN_SPRG_SCRATCH0, r10
+	mtspr	SPRN_SPRG_SCRATCH1, r11
 	mfcr	r10
 	mfspr	r11, SPRN_SRR0
 	cmplwi	cr0, r11, (dtlbie - PAGE_OFFSET)@l
@@ -652,13 +605,15 @@ DataBreakpoint:
 	EXC_XFER_EE(0x1c00, do_break)
 11:
 	mtcr	r10
-	EXCEPTION_EPILOG_0
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
 	rfi
 
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#ifdef CONFIG_PERF_EVENTS
 	. = 0x1d00
 InstructionBreakpoint:
-	EXCEPTION_PROLOG_0
+	mtspr	SPRN_SPRG_SCRATCH0, r10
+	mtspr	SPRN_SPRG_SCRATCH1, r11
 	lis	r10, (instruction_counter - PAGE_OFFSET)@ha
 	lwz	r11, (instruction_counter - PAGE_OFFSET)@l(r10)
 	addi	r11, r11, -1
@@ -666,7 +621,8 @@ InstructionBreakpoint:
 	lis	r10, 0xffff
 	ori	r10, r10, 0x01
 	mtspr	SPRN_COUNTA, r10
-	EXCEPTION_EPILOG_0
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
 	rfi
 #else
 	EXCEPTION(0x1d00, Trap_1d, unknown_exception, EXC_XFER_EE)
@@ -681,51 +637,57 @@ InstructionBreakpoint:
  * not enough space in the DataStoreTLBMiss area.
  */
 DTLBMissIMMR:
-	mtcr	r3
-	/* Set 512k byte guarded page and mark it valid */
-	li	r10, MD_PS512K | MD_GUARDED | MD_SVALID
-	MTSPR_CPU6(SPRN_MD_TWC, r10, r11)
+	mtcr	r12
+	/* Set 512k byte guarded page and mark it valid and accessed */
+	li	r10, MD_PS512K | MD_GUARDED | MD_SVALID | M_APG2
+	mtspr	SPRN_MD_TWC, r10
 	mfspr	r10, SPRN_IMMR			/* Get current IMMR */
 	rlwinm	r10, r10, 0, 0xfff80000		/* Get 512 kbytes boundary */
-	ori	r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY	| \
+	ori	r10, r10, 0xf0 | MD_SPS16K | _PAGE_PRIVILEGED | _PAGE_DIRTY | \
 			  _PAGE_PRESENT | _PAGE_NO_CACHE
-	MTSPR_CPU6(SPRN_MD_RPN, r10, r11)	/* Update TLB entry */
+	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
 
 	li	r11, RPN_PATTERN
 	mtspr	SPRN_DAR, r11	/* Tag DAR */
-	mfspr	r3, SPRN_SPRG_SCRATCH2
-	EXCEPTION_EPILOG_0
+_ENTRY(dtlb_miss_exit_2)
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	mfspr	r12, SPRN_SPRG_SCRATCH2
 	rfi
 
 DTLBMissLinear:
-	mtcr	r3
-	/* Set 8M byte page and mark it valid */
-	li	r11, MD_PS8MEG | MD_SVALID
-	MTSPR_CPU6(SPRN_MD_TWC, r11, r3)
+	mtcr	r12
+	/* Set 8M byte page and mark it valid and accessed */
+	li	r11, MD_PS8MEG | MD_SVALID | M_APG2
+	mtspr	SPRN_MD_TWC, r11
 	rlwinm	r10, r10, 0, 0x0f800000	/* 8xx supports max 256Mb RAM */
-	ori	r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY	| \
+	ori	r10, r10, 0xf0 | MD_SPS16K | _PAGE_PRIVILEGED | _PAGE_DIRTY | \
 			  _PAGE_PRESENT
-	MTSPR_CPU6(SPRN_MD_RPN, r10, r11)	/* Update TLB entry */
+	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
 
 	li	r11, RPN_PATTERN
 	mtspr	SPRN_DAR, r11	/* Tag DAR */
-	mfspr	r3, SPRN_SPRG_SCRATCH2
-	EXCEPTION_EPILOG_0
+_ENTRY(dtlb_miss_exit_3)
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	mfspr	r12, SPRN_SPRG_SCRATCH2
 	rfi
 
 #ifndef CONFIG_PIN_TLB_TEXT
 ITLBMissLinear:
-	mtcr	r3
-	/* Set 8M byte page and mark it valid */
-	li	r11, MI_PS8MEG | MI_SVALID | _PAGE_EXEC
-	MTSPR_CPU6(SPRN_MI_TWC, r11, r3)
+	mtcr	r12
+	/* Set 8M byte page and mark it valid,accessed */
+	li	r11, MI_PS8MEG | MI_SVALID | M_APG2
+	mtspr	SPRN_MI_TWC, r11
 	rlwinm	r10, r10, 0, 0x0f800000	/* 8xx supports max 256Mb RAM */
-	ori	r10, r10, 0xf0 | MI_SPS16K | _PAGE_SHARED | _PAGE_DIRTY	| \
+	ori	r10, r10, 0xf0 | MI_SPS16K | _PAGE_PRIVILEGED | _PAGE_DIRTY | \
 			  _PAGE_PRESENT
-	MTSPR_CPU6(SPRN_MI_RPN, r10, r11)	/* Update TLB entry */
+	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
 
-	mfspr	r3, SPRN_SPRG_SCRATCH2
-	EXCEPTION_EPILOG_0
+_ENTRY(itlb_miss_exit_2)
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	mfspr	r12, SPRN_SPRG_SCRATCH2
 	rfi
 #endif
 
@@ -933,13 +895,6 @@ start_here:
 	 */
 	lis	r6, swapper_pg_dir@ha
 	tophys(r6,r6)
-#ifdef CONFIG_8xx_CPU6
-	lis	r4, cpu6_errata_word@h
-	ori	r4, r4, cpu6_errata_word@l
-	li	r3, 0x3f80
-	stw	r3, 12(r4)
-	lwz	r3, 12(r4)
-#endif
 	mtspr	SPRN_M_TW, r6
 	lis	r4,2f@h
 	ori	r4,r4,2f@l
@@ -1004,8 +959,8 @@ initial_mmu:
 	lis	r8, KERNELBASE@h	/* Create vaddr for TLB */
 	ori	r8, r8, MI_EVALID	/* Mark it valid */
 	mtspr	SPRN_MI_EPN, r8
-	li	r8, MI_PS8MEG | (2 << 5)	/* Set 8M byte page, APG 2 */
-	ori	r8, r8, MI_SVALID	/* Make it valid */
+	li	r8, MI_PS8MEG /* Set 8M byte page */
+	ori	r8, r8, MI_SVALID | M_APG2	/* Make it valid, APG 2 */
 	mtspr	SPRN_MI_TWC, r8
 	li	r8, MI_BOOTINIT		/* Create RPN for address 0 */
 	mtspr	SPRN_MI_RPN, r8		/* Store TLB entry */
@@ -1032,7 +987,7 @@ initial_mmu:
 	ori	r8, r8, MD_EVALID	/* Mark it valid */
 	mtspr	SPRN_MD_EPN, r8
 	li	r8, MD_PS512K | MD_GUARDED	/* Set 512k byte page */
-	ori	r8, r8, MD_SVALID	/* Make it valid */
+	ori	r8, r8, MD_SVALID | M_APG2	/* Make it valid and accessed */
 	mtspr	SPRN_MD_TWC, r8
 	mr	r8, r9			/* Create paddr for TLB */
 	ori	r8, r8, MI_BOOTINIT|0x2 /* Inhibit cache -- Cort */
@@ -1061,7 +1016,7 @@ initial_mmu:
 #endif
 	/* Disable debug mode entry on breakpoints */
 	mfspr	r8, SPRN_DER
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#ifdef CONFIG_PERF_EVENTS
 	rlwinm	r8, r8, 0, ~0xc
 #else
 	rlwinm	r8, r8, 0, ~0x8
@@ -1094,13 +1049,7 @@ swapper_pg_dir:
 abatron_pteptrs:
 	.space	8
 
-#ifdef CONFIG_8xx_CPU6
-	.globl	cpu6_errata_word
-cpu6_errata_word:
-	.space	16
-#endif
-
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#ifdef CONFIG_PERF_EVENTS
 	.globl	itlb_miss_counter
 itlb_miss_counter:
 	.space	4
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S
index 48c21acef915..2b269315d377 100644
--- a/arch/powerpc/kernel/idle_book3e.S
+++ b/arch/powerpc/kernel/idle_book3e.S
@@ -17,6 +17,7 @@
 #include <asm/processor.h>
 #include <asm/thread_info.h>
 #include <asm/epapr_hcalls.h>
+#include <asm/hw_irq.h>
 
 /* 64-bit version only for now */
 #ifdef CONFIG_PPC64
@@ -46,8 +47,8 @@ _GLOBAL(\name)
 	bl	trace_hardirqs_on
 	addi    r1,r1,128
 #endif
-	li	r0,1
-	stb	r0,PACASOFTIRQEN(r13)
+	li	r0,IRQS_ENABLED
+	stb	r0,PACAIRQSOFTMASK(r13)
 	
 	/* Interrupts will make use return to LR, so get something we want
 	 * in there
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index f57a19348bdd..08faa93755f9 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -15,6 +15,7 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/irqflags.h>
+#include <asm/hw_irq.h>
 
 #undef DEBUG
 
@@ -53,8 +54,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
 	mfmsr	r7
 #endif /* CONFIG_TRACE_IRQFLAGS */
 
-	li	r0,1
-	stb	r0,PACASOFTIRQEN(r13)	/* we'll hard-enable shortly */
+	li	r0,IRQS_ENABLED
+	stb	r0,PACAIRQSOFTMASK(r13)	/* we'll hard-enable shortly */
 BEGIN_FTR_SECTION
 	DSSALL
 	sync
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index b7a84522e652..f88038847790 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -67,6 +67,7 @@
 #include <asm/smp.h>
 #include <asm/livepatch.h>
 #include <asm/asm-prototypes.h>
+#include <asm/hw_irq.h>
 
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
@@ -106,12 +107,6 @@ static inline notrace unsigned long get_irq_happened(void)
 	return happened;
 }
 
-static inline notrace void set_soft_enabled(unsigned long enable)
-{
-	__asm__ __volatile__("stb %0,%1(13)"
-	: : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled)));
-}
-
 static inline notrace int decrementer_check_overflow(void)
 {
  	u64 now = get_tb_or_rtc();
@@ -191,6 +186,11 @@ notrace unsigned int __check_irq_replay(void)
 		return 0x900;
 	}
 
+	if (happened & PACA_IRQ_PMI) {
+		local_paca->irq_happened &= ~PACA_IRQ_PMI;
+		return 0xf00;
+	}
+
 	if (happened & PACA_IRQ_EE) {
 		local_paca->irq_happened &= ~PACA_IRQ_EE;
 		return 0x500;
@@ -224,15 +224,16 @@ notrace unsigned int __check_irq_replay(void)
 	return 0;
 }
 
-notrace void arch_local_irq_restore(unsigned long en)
+notrace void arch_local_irq_restore(unsigned long mask)
 {
 	unsigned char irq_happened;
 	unsigned int replay;
 
 	/* Write the new soft-enabled value */
-	set_soft_enabled(en);
-	if (!en)
+	irq_soft_mask_set(mask);
+	if (mask)
 		return;
+
 	/*
 	 * From this point onward, we can take interrupts, preempt,
 	 * etc... unless we got hard-disabled. We check if an event
@@ -263,7 +264,7 @@ notrace void arch_local_irq_restore(unsigned long en)
 	 */
 	if (unlikely(irq_happened != PACA_IRQ_HARD_DIS))
 		__hard_irq_disable();
-#ifdef CONFIG_TRACE_IRQFLAGS
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
 	else {
 		/*
 		 * We should already be hard disabled here. We had bugs
@@ -274,9 +275,9 @@ notrace void arch_local_irq_restore(unsigned long en)
 		if (WARN_ON(mfmsr() & MSR_EE))
 			__hard_irq_disable();
 	}
-#endif /* CONFIG_TRACE_IRQFLAGS */
+#endif
 
-	set_soft_enabled(0);
+	irq_soft_mask_set(IRQS_ALL_DISABLED);
 	trace_hardirqs_off();
 
 	/*
@@ -288,7 +289,7 @@ notrace void arch_local_irq_restore(unsigned long en)
 
 	/* We can soft-enable now */
 	trace_hardirqs_on();
-	set_soft_enabled(1);
+	irq_soft_mask_set(IRQS_ENABLED);
 
 	/*
 	 * And replay if we have to. This will return with interrupts
@@ -363,7 +364,7 @@ bool prep_irq_for_idle(void)
 	 * of entering the low power state.
 	 */
 	local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
-	local_paca->soft_enabled = 1;
+	irq_soft_mask_set(IRQS_ENABLED);
 
 	/* Tell the caller to enter the low power state */
 	return true;
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 742e4658c5dc..efdd16a79075 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -273,7 +273,7 @@ static void machine_process_ue_event(struct work_struct *work)
 
 				pfn = evt->u.ue_error.physical_address >>
 					PAGE_SHIFT;
-				memory_failure(pfn, SIGBUS, 0);
+				memory_failure(pfn, 0);
 			} else
 				pr_warn("Failed to identify bad address from "
 					"where the uncorrectable error (UE) "
@@ -495,37 +495,123 @@ long machine_check_early(struct pt_regs *regs)
 	return handled;
 }
 
-long hmi_exception_realmode(struct pt_regs *regs)
-{
-	__this_cpu_inc(irq_stat.hmi_exceptions);
+/* Possible meanings for HMER_DEBUG_TRIG bit being set on POWER9 */
+static enum {
+	DTRIG_UNKNOWN,
+	DTRIG_VECTOR_CI,	/* need to emulate vector CI load instr */
+	DTRIG_SUSPEND_ESCAPE,	/* need to escape from TM suspend mode */
+} hmer_debug_trig_function;
 
-#ifdef CONFIG_PPC_BOOK3S_64
-	/* Workaround for P9 vector CI loads (see p9_hmi_special_emu) */
-	if (pvr_version_is(PVR_POWER9)) {
-		unsigned long hmer = mfspr(SPRN_HMER);
-
-		/* Do we have the debug bit set */
-		if (hmer & PPC_BIT(17)) {
-			hmer &= ~PPC_BIT(17);
-			mtspr(SPRN_HMER, hmer);
-
-			/*
-			 * Now to avoid problems with soft-disable we
-			 * only do the emulation if we are coming from
-			 * user space
-			 */
-			if (user_mode(regs))
-				local_paca->hmi_p9_special_emu = 1;
-
-			/*
-			 * Don't bother going to OPAL if that's the
-			 * only relevant bit.
-			 */
-			if (!(hmer & mfspr(SPRN_HMEER)))
-				return local_paca->hmi_p9_special_emu;
+static int init_debug_trig_function(void)
+{
+	int pvr;
+	struct device_node *cpun;
+	struct property *prop = NULL;
+	const char *str;
+
+	/* First look in the device tree */
+	preempt_disable();
+	cpun = of_get_cpu_node(smp_processor_id(), NULL);
+	if (cpun) {
+		of_property_for_each_string(cpun, "ibm,hmi-special-triggers",
+					    prop, str) {
+			if (strcmp(str, "bit17-vector-ci-load") == 0)
+				hmer_debug_trig_function = DTRIG_VECTOR_CI;
+			else if (strcmp(str, "bit17-tm-suspend-escape") == 0)
+				hmer_debug_trig_function = DTRIG_SUSPEND_ESCAPE;
 		}
+		of_node_put(cpun);
+	}
+	preempt_enable();
+
+	/* If we found the property, don't look at PVR */
+	if (prop)
+		goto out;
+
+	pvr = mfspr(SPRN_PVR);
+	/* Check for POWER9 Nimbus (scale-out) */
+	if ((PVR_VER(pvr) == PVR_POWER9) && (pvr & 0xe000) == 0) {
+		/* DD2.2 and later */
+		if ((pvr & 0xfff) >= 0x202)
+			hmer_debug_trig_function = DTRIG_SUSPEND_ESCAPE;
+		/* DD2.0 and DD2.1 - used for vector CI load emulation */
+		else if ((pvr & 0xfff) >= 0x200)
+			hmer_debug_trig_function = DTRIG_VECTOR_CI;
+	}
+
+ out:
+	switch (hmer_debug_trig_function) {
+	case DTRIG_VECTOR_CI:
+		pr_debug("HMI debug trigger used for vector CI load\n");
+		break;
+	case DTRIG_SUSPEND_ESCAPE:
+		pr_debug("HMI debug trigger used for TM suspend escape\n");
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+__initcall(init_debug_trig_function);
+
+/*
+ * Handle HMIs that occur as a result of a debug trigger.
+ * Return values:
+ * -1 means this is not a HMI cause that we know about
+ *  0 means no further handling is required
+ *  1 means further handling is required
+ */
+long hmi_handle_debugtrig(struct pt_regs *regs)
+{
+	unsigned long hmer = mfspr(SPRN_HMER);
+	long ret = 0;
+
+	/* HMER_DEBUG_TRIG bit is used for various workarounds on P9 */
+	if (!((hmer & HMER_DEBUG_TRIG)
+	      && hmer_debug_trig_function != DTRIG_UNKNOWN))
+		return -1;
+		
+	hmer &= ~HMER_DEBUG_TRIG;
+	/* HMER is a write-AND register */
+	mtspr(SPRN_HMER, ~HMER_DEBUG_TRIG);
+
+	switch (hmer_debug_trig_function) {
+	case DTRIG_VECTOR_CI:
+		/*
+		 * Now to avoid problems with soft-disable we
+		 * only do the emulation if we are coming from
+		 * host user space
+		 */
+		if (regs && user_mode(regs))
+			ret = local_paca->hmi_p9_special_emu = 1;
+
+		break;
+
+	default:
+		break;
 	}
-#endif /* CONFIG_PPC_BOOK3S_64 */
+
+	/*
+	 * See if any other HMI causes remain to be handled
+	 */
+	if (hmer & mfspr(SPRN_HMEER))
+		return -1;
+
+	return ret;
+}
+
+/*
+ * Return values:
+ */
+long hmi_exception_realmode(struct pt_regs *regs)
+{	
+	int ret;
+
+	__this_cpu_inc(irq_stat.hmi_exceptions);
+
+	ret = hmi_handle_debugtrig(regs);
+	if (ret >= 0)
+		return ret;
 
 	wait_for_subcore_guest_exit();
 
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 644f7040b91c..fe6fc63251fe 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -58,115 +58,6 @@ static unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
 	return pte_pfn(*ptep);
 }
 
-static void flush_tlb_206(unsigned int num_sets, unsigned int action)
-{
-	unsigned long rb;
-	unsigned int i;
-
-	switch (action) {
-	case TLB_INVAL_SCOPE_GLOBAL:
-		rb = TLBIEL_INVAL_SET;
-		break;
-	case TLB_INVAL_SCOPE_LPID:
-		rb = TLBIEL_INVAL_SET_LPID;
-		break;
-	default:
-		BUG();
-		break;
-	}
-
-	asm volatile("ptesync" : : : "memory");
-	for (i = 0; i < num_sets; i++) {
-		asm volatile("tlbiel %0" : : "r" (rb));
-		rb += 1 << TLBIEL_INVAL_SET_SHIFT;
-	}
-	asm volatile("ptesync" : : : "memory");
-}
-
-static void flush_tlb_300(unsigned int num_sets, unsigned int action)
-{
-	unsigned long rb;
-	unsigned int i;
-	unsigned int r;
-
-	switch (action) {
-	case TLB_INVAL_SCOPE_GLOBAL:
-		rb = TLBIEL_INVAL_SET;
-		break;
-	case TLB_INVAL_SCOPE_LPID:
-		rb = TLBIEL_INVAL_SET_LPID;
-		break;
-	default:
-		BUG();
-		break;
-	}
-
-	asm volatile("ptesync" : : : "memory");
-
-	if (early_radix_enabled())
-		r = 1;
-	else
-		r = 0;
-
-	/*
-	 * First flush table/PWC caches with set 0, then flush the
-	 * rest of the sets, partition scope. Radix must then do it
-	 * all again with process scope. Hash just has to flush
-	 * process table.
-	 */
-	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
-			"r"(rb), "r"(0), "i"(2), "i"(0), "r"(r));
-	for (i = 1; i < num_sets; i++) {
-		unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT);
-
-		asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
-				"r"(rb+set), "r"(0), "i"(2), "i"(0), "r"(r));
-	}
-
-	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
-			"r"(rb), "r"(0), "i"(2), "i"(1), "r"(r));
-	if (early_radix_enabled()) {
-		for (i = 1; i < num_sets; i++) {
-			unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT);
-
-			asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
-				"r"(rb+set), "r"(0), "i"(2), "i"(1), "r"(r));
-		}
-	}
-
-	asm volatile("ptesync" : : : "memory");
-}
-
-/*
- * Generic routines to flush TLB on POWER processors. These routines
- * are used as flush_tlb hook in the cpu_spec.
- *
- * action => TLB_INVAL_SCOPE_GLOBAL:  Invalidate all TLBs.
- *	     TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID.
- */
-void __flush_tlb_power7(unsigned int action)
-{
-	flush_tlb_206(POWER7_TLB_SETS, action);
-}
-
-void __flush_tlb_power8(unsigned int action)
-{
-	flush_tlb_206(POWER8_TLB_SETS, action);
-}
-
-void __flush_tlb_power9(unsigned int action)
-{
-	unsigned int num_sets;
-
-	if (early_radix_enabled())
-		num_sets = POWER9_TLB_SETS_RADIX;
-	else
-		num_sets = POWER9_TLB_SETS_HASH;
-
-	flush_tlb_300(num_sets, action);
-}
-
-
 /* flush SLBs and reload */
 #ifdef CONFIG_PPC_BOOK3S_64
 static void flush_and_reload_slb(void)
@@ -226,10 +117,8 @@ static int mce_flush(int what)
 		return 1;
 	}
 	if (what == MCE_FLUSH_TLB) {
-		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
-			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
-			return 1;
-		}
+		tlbiel_all();
+		return 1;
 	}
 
 	return 0;
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 8ac0bd2bddb0..3280953a82cf 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -623,7 +623,9 @@ BEGIN_FTR_SECTION
 	 * NOTE, we rely on r0 being 0 from above.
 	 */
 	mtspr	SPRN_IAMR,r0
+BEGIN_FTR_SECTION_NESTED(42)
 	mtspr	SPRN_AMOR,r0
+END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 	/* save regs for local vars on new stack.
diff --git a/arch/powerpc/kernel/module.lds b/arch/powerpc/kernel/module.lds
new file mode 100644
index 000000000000..cea5dc124be4
--- /dev/null
+++ b/arch/powerpc/kernel/module.lds
@@ -0,0 +1,8 @@
+/* Force alignment of .toc section.  */
+SECTIONS
+{
+	.toc 0 : ALIGN(256)
+	{
+		*(.got .toc)
+	}
+}
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 759104b99f9f..a2636c250b7b 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -93,6 +93,15 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym)
 {
 	return 0;
 }
+
+void *dereference_module_function_descriptor(struct module *mod, void *ptr)
+{
+	if (ptr < (void *)mod->arch.start_opd ||
+			ptr >= (void *)mod->arch.end_opd)
+		return ptr;
+
+	return dereference_function_descriptor(ptr);
+}
 #endif
 
 #define STUB_MAGIC 0x73747562 /* stub */
@@ -339,11 +348,19 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
 		char *p;
 		if (strcmp(secstrings + sechdrs[i].sh_name, ".stubs") == 0)
 			me->arch.stubs_section = i;
-		else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0)
+		else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0) {
 			me->arch.toc_section = i;
+			if (sechdrs[i].sh_addralign < 8)
+				sechdrs[i].sh_addralign = 8;
+		}
 		else if (strcmp(secstrings+sechdrs[i].sh_name,"__versions")==0)
 			dedotify_versions((void *)hdr + sechdrs[i].sh_offset,
 					  sechdrs[i].sh_size);
+		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".opd")) {
+			me->arch.start_opd = sechdrs[i].sh_addr;
+			me->arch.end_opd = sechdrs[i].sh_addr +
+					   sechdrs[i].sh_size;
+		}
 
 		/* We don't handle .init for the moment: rename to _init */
 		while ((p = strstr(secstrings + sechdrs[i].sh_name, ".init")))
@@ -373,12 +390,15 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
 	return 0;
 }
 
-/* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this
-   gives the value maximum span in an instruction which uses a signed
-   offset) */
+/*
+ * r2 is the TOC pointer: it actually points 0x8000 into the TOC (this gives the
+ * value maximum span in an instruction which uses a signed offset). Round down
+ * to a 256 byte boundary for the odd case where we are setting up r2 without a
+ * .toc section.
+ */
 static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me)
 {
-	return sechdrs[me->arch.toc_section].sh_addr + 0x8000;
+	return (sechdrs[me->arch.toc_section].sh_addr & ~0xfful) + 0x8000;
 }
 
 /* Both low and high 16 bits are added as SIGNED additions, so if low
@@ -487,12 +507,22 @@ static bool is_early_mcount_callsite(u32 *instruction)
    restore r2. */
 static int restore_r2(u32 *instruction, struct module *me)
 {
-	if (is_early_mcount_callsite(instruction - 1))
+	u32 *prev_insn = instruction - 1;
+
+	if (is_early_mcount_callsite(prev_insn))
+		return 1;
+
+	/*
+	 * Make sure the branch isn't a sibling call.  Sibling calls aren't
+	 * "link" branches and they don't return, so they don't need the r2
+	 * restore afterwards.
+	 */
+	if (!instr_is_relative_link_branch(*prev_insn))
 		return 1;
 
 	if (*instruction != PPC_INST_NOP) {
-		pr_err("%s: Expect noop after relocate, got %08x\n",
-		       me->name, *instruction);
+		pr_err("%s: Expected nop after call, got %08x at %pS\n",
+			me->name, *instruction, instruction);
 		return 0;
 	}
 	/* ld r2,R2_STACK_OFFSET(r1) */
@@ -614,7 +644,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 
 		case R_PPC_REL24:
 			/* FIXME: Handle weak symbols here --RR */
-			if (sym->st_shndx == SHN_UNDEF) {
+			if (sym->st_shndx == SHN_UNDEF ||
+			    sym->st_shndx == SHN_LIVEPATCH) {
 				/* External: go via stub */
 				value = stub_for_addr(sechdrs, value, me);
 				if (!value)
diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S
index 52fc864cdec4..98a3aeeb3c8c 100644
--- a/arch/powerpc/kernel/optprobes_head.S
+++ b/arch/powerpc/kernel/optprobes_head.S
@@ -58,7 +58,7 @@ optprobe_template_entry:
 	std	r5,_XER(r1)
 	mfcr	r5
 	std	r5,_CCR(r1)
-	lbz     r5,PACASOFTIRQEN(r13)
+	lbz     r5,PACAIRQSOFTMASK(r13)
 	std     r5,SOFTE(r1)
 
 	/*
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index d6597038931d..95ffedf14885 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -18,6 +18,8 @@
 #include <asm/pgtable.h>
 #include <asm/kexec.h>
 
+#include "setup.h"
+
 #ifdef CONFIG_PPC_BOOK3S
 
 /*
@@ -208,15 +210,14 @@ void __init allocate_pacas(void)
 	u64 limit;
 	int cpu;
 
-	limit = ppc64_rma_size;
-
 #ifdef CONFIG_PPC_BOOK3S_64
 	/*
-	 * We can't take SLB misses on the paca, and we want to access them
-	 * in real mode, so allocate them within the RMA and also within
-	 * the first segment.
+	 * We access pacas in real mode, and cannot take SLB faults
+	 * on them when in virtual mode, so allocate them accordingly.
 	 */
-	limit = min(0x10000000ULL, limit);
+	limit = min(ppc64_bolted_size(), ppc64_rma_size);
+#else
+	limit = ppc64_rma_size;
 #endif
 
 	paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 0ac7aa346c69..208e623b2557 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -60,7 +60,7 @@ resource_size_t isa_mem_base;
 EXPORT_SYMBOL(isa_mem_base);
 
 
-static const struct dma_map_ops *pci_dma_ops = &dma_direct_ops;
+static const struct dma_map_ops *pci_dma_ops = &dma_nommu_ops;
 
 void set_pci_dma_ops(const struct dma_map_ops *dma_ops)
 {
@@ -249,8 +249,31 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *pdev, int resno)
 
 	return pci_iov_resource_size(pdev, resno);
 }
+
+int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+{
+	if (ppc_md.pcibios_sriov_enable)
+		return ppc_md.pcibios_sriov_enable(pdev, num_vfs);
+
+	return 0;
+}
+
+int pcibios_sriov_disable(struct pci_dev *pdev)
+{
+	if (ppc_md.pcibios_sriov_disable)
+		return ppc_md.pcibios_sriov_disable(pdev);
+
+	return 0;
+}
+
 #endif /* CONFIG_PCI_IOV */
 
+void pcibios_bus_add_device(struct pci_dev *pdev)
+{
+	if (ppc_md.pcibios_bus_add_device)
+		ppc_md.pcibios_bus_add_device(pdev);
+}
+
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
 {
 #ifdef CONFIG_PPC64
@@ -1276,8 +1299,8 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 						i + PCI_BRIDGE_RESOURCES) == 0)
 				continue;
 		}
-		pr_warning("PCI: Cannot allocate resource region "
-			   "%d of PCI bridge %d, will remap\n", i, bus->number);
+		pr_warn("PCI: Cannot allocate resource region %d of PCI bridge %d, will remap\n",
+			i, bus->number);
 	clear_resource:
 		/* The resource might be figured out when doing
 		 * reassignment based on the resources required
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 0e395afbf0f4..ab147a1909c8 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -156,10 +156,8 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
 	pdn->parent = parent;
 	pdn->busno = busno;
 	pdn->devfn = devfn;
-#ifdef CONFIG_PPC_POWERNV
 	pdn->vf_index = vf_index;
 	pdn->pe_number = IODA_INVALID_PE;
-#endif
 	INIT_LIST_HEAD(&pdn->child_list);
 	INIT_LIST_HEAD(&pdn->list);
 	list_add_tail(&pdn->list, &parent->child_list);
@@ -226,9 +224,7 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 	 */
 	if (pdev->is_virtfn) {
 		pdn = pci_get_pdn(pdev);
-#ifdef CONFIG_PPC_POWERNV
 		pdn->pe_number = IODA_INVALID_PE;
-#endif
 		return;
 	}
 
@@ -294,9 +290,7 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
 		return NULL;
 	dn->data = pdn;
 	pdn->phb = hose;
-#ifdef CONFIG_PPC_POWERNV
 	pdn->pe_number = IODA_INVALID_PE;
-#endif
 	regs = of_get_property(dn, "reg", NULL);
 	if (regs) {
 		u32 addr = of_read_number(regs, 1);
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 0d790f8432d2..20ceec4a5f5e 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -38,7 +38,7 @@ static u32 get_int_prop(struct device_node *np, const char *name, u32 def)
  * @addr0: value of 1st cell of a device tree PCI address.
  * @bridge: Set this flag if the address is from a bridge 'ranges' property
  */
-static unsigned int pci_parse_of_flags(u32 addr0, int bridge)
+unsigned int pci_parse_of_flags(u32 addr0, int bridge)
 {
 	unsigned int flags = 0;
 
diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c
index 56548bf6231f..9bfbd800d32f 100644
--- a/arch/powerpc/kernel/proc_powerpc.c
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -63,7 +63,7 @@ static int __init proc_ppc64_init(void)
 {
 	struct proc_dir_entry *pde;
 
-	pde = proc_create_data("powerpc/systemcfg", S_IFREG|S_IRUGO, NULL,
+	pde = proc_create_data("powerpc/systemcfg", S_IFREG | 0444, NULL,
 			       &page_map_fops, vdso_data);
 	if (!pde)
 		return 1;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index bfdd783e3916..1738c4127b32 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -42,6 +42,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/uaccess.h>
 #include <linux/elf-randomize.h>
+#include <linux/pkeys.h>
 
 #include <asm/pgtable.h>
 #include <asm/io.h>
@@ -57,6 +58,7 @@
 #include <asm/debug.h>
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
+#include <asm/hw_irq.h>
 #endif
 #include <asm/code-patching.h>
 #include <asm/exec.h>
@@ -601,21 +603,16 @@ EXPORT_SYMBOL(flush_all_to_thread);
 
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 void do_send_trap(struct pt_regs *regs, unsigned long address,
-		  unsigned long error_code, int signal_code, int breakpt)
+		  unsigned long error_code, int breakpt)
 {
-	siginfo_t info;
-
-	current->thread.trap_nr = signal_code;
+	current->thread.trap_nr = TRAP_HWBKPT;
 	if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
 			11, SIGSEGV) == NOTIFY_STOP)
 		return;
 
 	/* Deliver the signal to userspace */
-	info.si_signo = SIGTRAP;
-	info.si_errno = breakpt;	/* breakpoint or watchpoint id */
-	info.si_code = signal_code;
-	info.si_addr = (void __user *)address;
-	force_sig_info(SIGTRAP, &info, current);
+	force_sig_ptrace_errno_trap(breakpt, /* breakpoint or watchpoint id */
+				    (void __user *)address);
 }
 #else	/* !CONFIG_PPC_ADV_DEBUG_REGS */
 void do_break (struct pt_regs *regs, unsigned long address,
@@ -1102,6 +1099,8 @@ static inline void save_sprs(struct thread_struct *t)
 		t->tar = mfspr(SPRN_TAR);
 	}
 #endif
+
+	thread_pkey_regs_save(t);
 }
 
 static inline void restore_sprs(struct thread_struct *old_thread,
@@ -1141,6 +1140,8 @@ static inline void restore_sprs(struct thread_struct *old_thread,
 	    old_thread->tidr != new_thread->tidr)
 		mtspr(SPRN_TIDR, new_thread->tidr);
 #endif
+
+	thread_pkey_regs_restore(new_thread, old_thread);
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -1403,13 +1404,13 @@ void show_regs(struct pt_regs * regs)
 
 	printk("NIP:  "REG" LR: "REG" CTR: "REG"\n",
 	       regs->nip, regs->link, regs->ctr);
-	printk("REGS: %p TRAP: %04lx   %s  (%s)\n",
+	printk("REGS: %px TRAP: %04lx   %s  (%s)\n",
 	       regs, regs->trap, print_tainted(), init_utsname()->release);
 	printk("MSR:  "REG" ", regs->msr);
 	print_msr_bits(regs->msr);
 	pr_cont("  CR: %08lx  XER: %08lx\n", regs->ccr, regs->xer);
 	trap = TRAP(regs);
-	if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
+	if ((TRAP(regs) != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
 		pr_cont("CFAR: "REG" ", regs->orig_gpr3);
 	if (trap == 0x200 || trap == 0x300 || trap == 0x600)
 #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
@@ -1509,14 +1510,15 @@ static int assign_thread_tidr(void)
 {
 	int index;
 	int err;
+	unsigned long flags;
 
 again:
 	if (!ida_pre_get(&vas_thread_ida, GFP_KERNEL))
 		return -ENOMEM;
 
-	spin_lock(&vas_thread_id_lock);
+	spin_lock_irqsave(&vas_thread_id_lock, flags);
 	err = ida_get_new_above(&vas_thread_ida, 1, &index);
-	spin_unlock(&vas_thread_id_lock);
+	spin_unlock_irqrestore(&vas_thread_id_lock, flags);
 
 	if (err == -EAGAIN)
 		goto again;
@@ -1524,9 +1526,9 @@ again:
 		return err;
 
 	if (index > MAX_THREAD_CONTEXT) {
-		spin_lock(&vas_thread_id_lock);
+		spin_lock_irqsave(&vas_thread_id_lock, flags);
 		ida_remove(&vas_thread_ida, index);
-		spin_unlock(&vas_thread_id_lock);
+		spin_unlock_irqrestore(&vas_thread_id_lock, flags);
 		return -ENOMEM;
 	}
 
@@ -1535,9 +1537,11 @@ again:
 
 static void free_thread_tidr(int id)
 {
-	spin_lock(&vas_thread_id_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vas_thread_id_lock, flags);
 	ida_remove(&vas_thread_ida, id);
-	spin_unlock(&vas_thread_id_lock);
+	spin_unlock_irqrestore(&vas_thread_id_lock, flags);
 }
 
 /*
@@ -1569,20 +1573,27 @@ void arch_release_task_struct(struct task_struct *t)
  */
 int set_thread_tidr(struct task_struct *t)
 {
+	int rc;
+
 	if (!cpu_has_feature(CPU_FTR_ARCH_300))
 		return -EINVAL;
 
 	if (t != current)
 		return -EINVAL;
 
-	t->thread.tidr = assign_thread_tidr();
-	if (t->thread.tidr < 0)
-		return t->thread.tidr;
+	if (t->thread.tidr)
+		return 0;
+
+	rc = assign_thread_tidr();
+	if (rc < 0)
+		return rc;
 
+	t->thread.tidr = rc;
 	mtspr(SPRN_TIDR, t->thread.tidr);
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(set_thread_tidr);
 
 #endif /* CONFIG_PPC64 */
 
@@ -1668,7 +1679,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 			childregs->gpr[14] = ppc_function_entry((void *)usp);
 #ifdef CONFIG_PPC64
 		clear_tsk_thread_flag(p, TIF_32BIT);
-		childregs->softe = 1;
+		childregs->softe = IRQS_ENABLED;
 #endif
 		childregs->gpr[15] = kthread_arg;
 		p->thread.regs = NULL;	/* no user register state */
@@ -1859,6 +1870,8 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.tm_tfiar = 0;
 	current->thread.load_tm = 0;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
+	thread_pkey_regs_init(&current->thread);
 }
 EXPORT_SYMBOL(start_thread);
 
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index b15bae265c90..4dffef947b8a 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -59,6 +59,7 @@
 #include <asm/epapr_hcalls.h>
 #include <asm/firmware.h>
 #include <asm/dt_cpu_ftrs.h>
+#include <asm/drmem.h>
 
 #include <mm/mmu_decl.h>
 
@@ -455,92 +456,74 @@ static int __init early_init_dt_scan_chosen_ppc(unsigned long node,
 
 #ifdef CONFIG_PPC_PSERIES
 /*
- * Interpret the ibm,dynamic-memory property in the
- * /ibm,dynamic-reconfiguration-memory node.
+ * Interpret the ibm dynamic reconfiguration memory LMBs.
  * This contains a list of memory blocks along with NUMA affinity
  * information.
  */
-static int __init early_init_dt_scan_drconf_memory(unsigned long node)
+static void __init early_init_drmem_lmb(struct drmem_lmb *lmb,
+					const __be32 **usm)
 {
-	const __be32 *dm, *ls, *usm;
-	int l;
-	unsigned long n, flags;
-	u64 base, size, memblock_size;
-	unsigned int is_kexec_kdump = 0, rngs;
-
-	ls = of_get_flat_dt_prop(node, "ibm,lmb-size", &l);
-	if (ls == NULL || l < dt_root_size_cells * sizeof(__be32))
-		return 0;
-	memblock_size = dt_mem_next_cell(dt_root_size_cells, &ls);
+	u64 base, size;
+	int is_kexec_kdump = 0, rngs;
 
-	dm = of_get_flat_dt_prop(node, "ibm,dynamic-memory", &l);
-	if (dm == NULL || l < sizeof(__be32))
-		return 0;
+	base = lmb->base_addr;
+	size = drmem_lmb_size();
+	rngs = 1;
 
-	n = of_read_number(dm++, 1);	/* number of entries */
-	if (l < (n * (dt_root_addr_cells + 4) + 1) * sizeof(__be32))
-		return 0;
+	/*
+	 * Skip this block if the reserved bit is set in flags
+	 * or if the block is not assigned to this partition.
+	 */
+	if ((lmb->flags & DRCONF_MEM_RESERVED) ||
+	    !(lmb->flags & DRCONF_MEM_ASSIGNED))
+		return;
 
-	/* check if this is a kexec/kdump kernel. */
-	usm = of_get_flat_dt_prop(node, "linux,drconf-usable-memory",
-						 &l);
-	if (usm != NULL)
+	if (*usm)
 		is_kexec_kdump = 1;
 
-	for (; n != 0; --n) {
-		base = dt_mem_next_cell(dt_root_addr_cells, &dm);
-		flags = of_read_number(&dm[3], 1);
-		/* skip DRC index, pad, assoc. list index, flags */
-		dm += 4;
-		/* skip this block if the reserved bit is set in flags
-		   or if the block is not assigned to this partition */
-		if ((flags & DRCONF_MEM_RESERVED) ||
-				!(flags & DRCONF_MEM_ASSIGNED))
-			continue;
-		size = memblock_size;
-		rngs = 1;
+	if (is_kexec_kdump) {
+		/*
+		 * For each memblock in ibm,dynamic-memory, a
+		 * corresponding entry in linux,drconf-usable-memory
+		 * property contains a counter 'p' followed by 'p'
+		 * (base, size) duple. Now read the counter from
+		 * linux,drconf-usable-memory property
+		 */
+		rngs = dt_mem_next_cell(dt_root_size_cells, usm);
+		if (!rngs) /* there are no (base, size) duple */
+			return;
+	}
+
+	do {
 		if (is_kexec_kdump) {
-			/*
-			 * For each memblock in ibm,dynamic-memory, a corresponding
-			 * entry in linux,drconf-usable-memory property contains
-			 * a counter 'p' followed by 'p' (base, size) duple.
-			 * Now read the counter from
-			 * linux,drconf-usable-memory property
-			 */
-			rngs = dt_mem_next_cell(dt_root_size_cells, &usm);
-			if (!rngs) /* there are no (base, size) duple */
+			base = dt_mem_next_cell(dt_root_addr_cells, usm);
+			size = dt_mem_next_cell(dt_root_size_cells, usm);
+		}
+
+		if (iommu_is_off) {
+			if (base >= 0x80000000ul)
 				continue;
+			if ((base + size) > 0x80000000ul)
+				size = 0x80000000ul - base;
 		}
-		do {
-			if (is_kexec_kdump) {
-				base = dt_mem_next_cell(dt_root_addr_cells,
-							 &usm);
-				size = dt_mem_next_cell(dt_root_size_cells,
-							 &usm);
-			}
-			if (iommu_is_off) {
-				if (base >= 0x80000000ul)
-					continue;
-				if ((base + size) > 0x80000000ul)
-					size = 0x80000000ul - base;
-			}
-			memblock_add(base, size);
-		} while (--rngs);
-	}
-	memblock_dump_all();
-	return 0;
+
+		DBG("Adding: %llx -> %llx\n", base, size);
+		memblock_add(base, size);
+	} while (--rngs);
 }
-#else
-#define early_init_dt_scan_drconf_memory(node)	0
 #endif /* CONFIG_PPC_PSERIES */
 
 static int __init early_init_dt_scan_memory_ppc(unsigned long node,
 						const char *uname,
 						int depth, void *data)
 {
+#ifdef CONFIG_PPC_PSERIES
 	if (depth == 1 &&
-	    strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0)
-		return early_init_dt_scan_drconf_memory(node);
+	    strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0) {
+		walk_drmem_lmbs_early(node, early_init_drmem_lmb);
+		return 0;
+	}
+#endif
 	
 	return early_init_dt_scan_memory(node, uname, depth, data);
 }
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 02190e90c7ae..adf044daafd7 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -869,10 +869,12 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
 		.reserved2 = 0,
 		.reserved3 = 0,
 		.subprocessors = 1,
+		.byte22 = OV5_FEAT(OV5_DRMEM_V2),
 		.intarch = 0,
 		.mmu = 0,
 		.hash_ext = 0,
 		.radix_ext = 0,
+		.byte22 = OV5_FEAT(OV5_DRC_INFO),
 	},
 
 	/* option vector 6: IBM PAPR hints */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index f52ad5bb7109..ca72d7391d40 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -35,6 +35,7 @@
 #include <linux/context_tracking.h>
 
 #include <linux/uaccess.h>
+#include <linux/pkeys.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/switch_to.h>
@@ -283,6 +284,18 @@ int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data)
 	if (regno == PT_DSCR)
 		return get_user_dscr(task, data);
 
+#ifdef CONFIG_PPC64
+	/*
+	 * softe copies paca->irq_soft_mask variable state. Since irq_soft_mask is
+	 * no more used as a flag, lets force usr to alway see the softe value as 1
+	 * which means interrupts are not soft disabled.
+	 */
+	if (regno == PT_SOFTE) {
+		*data = 1;
+		return  0;
+	}
+#endif
+
 	if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) {
 		*data = ((unsigned long *)task->thread.regs)[regno];
 		return 0;
@@ -1775,6 +1788,61 @@ static int pmu_set(struct task_struct *target,
 	return ret;
 }
 #endif
+
+#ifdef CONFIG_PPC_MEM_KEYS
+static int pkey_active(struct task_struct *target,
+		       const struct user_regset *regset)
+{
+	if (!arch_pkeys_enabled())
+		return -ENODEV;
+
+	return regset->n;
+}
+
+static int pkey_get(struct task_struct *target,
+		    const struct user_regset *regset,
+		    unsigned int pos, unsigned int count,
+		    void *kbuf, void __user *ubuf)
+{
+	BUILD_BUG_ON(TSO(amr) + sizeof(unsigned long) != TSO(iamr));
+	BUILD_BUG_ON(TSO(iamr) + sizeof(unsigned long) != TSO(uamor));
+
+	if (!arch_pkeys_enabled())
+		return -ENODEV;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &target->thread.amr, 0,
+				   ELF_NPKEY * sizeof(unsigned long));
+}
+
+static int pkey_set(struct task_struct *target,
+		      const struct user_regset *regset,
+		      unsigned int pos, unsigned int count,
+		      const void *kbuf, const void __user *ubuf)
+{
+	u64 new_amr;
+	int ret;
+
+	if (!arch_pkeys_enabled())
+		return -ENODEV;
+
+	/* Only the AMR can be set from userspace */
+	if (pos != 0 || count != sizeof(new_amr))
+		return -EINVAL;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &new_amr, 0, sizeof(new_amr));
+	if (ret)
+		return ret;
+
+	/* UAMOR determines which bits of the AMR can be set from userspace. */
+	target->thread.amr = (new_amr & target->thread.uamor) |
+		(target->thread.amr & ~target->thread.uamor);
+
+	return 0;
+}
+#endif /* CONFIG_PPC_MEM_KEYS */
+
 /*
  * These are our native regset flavors.
  */
@@ -1809,6 +1877,9 @@ enum powerpc_regset {
 	REGSET_EBB,		/* EBB registers */
 	REGSET_PMR,		/* Performance Monitor Registers */
 #endif
+#ifdef CONFIG_PPC_MEM_KEYS
+	REGSET_PKEY,		/* AMR register */
+#endif
 };
 
 static const struct user_regset native_regsets[] = {
@@ -1914,6 +1985,13 @@ static const struct user_regset native_regsets[] = {
 		.active = pmu_active, .get = pmu_get, .set = pmu_set
 	},
 #endif
+#ifdef CONFIG_PPC_MEM_KEYS
+	[REGSET_PKEY] = {
+		.core_note_type = NT_PPC_PKEY, .n = ELF_NPKEY,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = pkey_active, .get = pkey_get, .set = pkey_set
+	},
+#endif
 };
 
 static const struct user_regset_view user_ppc_native_view = {
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index c8c5f3a550c2..fb070d8cad07 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -261,19 +261,19 @@ static int __init proc_rtas_init(void)
 	if (rtas_node == NULL)
 		return -ENODEV;
 
-	proc_create("powerpc/rtas/progress", S_IRUGO|S_IWUSR, NULL,
+	proc_create("powerpc/rtas/progress", 0644, NULL,
 		    &ppc_rtas_progress_operations);
-	proc_create("powerpc/rtas/clock", S_IRUGO|S_IWUSR, NULL,
+	proc_create("powerpc/rtas/clock", 0644, NULL,
 		    &ppc_rtas_clock_operations);
-	proc_create("powerpc/rtas/poweron", S_IWUSR|S_IRUGO, NULL,
+	proc_create("powerpc/rtas/poweron", 0644, NULL,
 		    &ppc_rtas_poweron_operations);
-	proc_create("powerpc/rtas/sensors", S_IRUGO, NULL,
+	proc_create("powerpc/rtas/sensors", 0444, NULL,
 		    &ppc_rtas_sensors_operations);
-	proc_create("powerpc/rtas/frequency", S_IWUSR|S_IRUGO, NULL,
+	proc_create("powerpc/rtas/frequency", 0644, NULL,
 		    &ppc_rtas_tone_freq_operations);
-	proc_create("powerpc/rtas/volume", S_IWUSR|S_IRUGO, NULL,
+	proc_create("powerpc/rtas/volume", 0644, NULL,
 		    &ppc_rtas_tone_volume_operations);
-	proc_create("powerpc/rtas/rmo_buffer", S_IRUSR, NULL,
+	proc_create("powerpc/rtas/rmo_buffer", 0400, NULL,
 		    &ppc_rtas_rmo_buf_ops);
 	return 0;
 }
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index f6f6a8a5103a..10fabae2574d 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -727,7 +727,7 @@ static int __init rtas_flash_init(void)
 		const struct rtas_flash_file *f = &rtas_flash_files[i];
 		int token;
 
-		if (!proc_create(f->filename, S_IRUSR | S_IWUSR, NULL, &f->fops))
+		if (!proc_create(f->filename, 0600, NULL, &f->fops))
 			goto enomem;
 
 		/*
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 0f0b1b2f3b60..fc600a8b1e77 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -388,7 +388,7 @@ out:
 	return error;
 }
 
-static unsigned int rtas_log_poll(struct file *file, poll_table * wait)
+static __poll_t rtas_log_poll(struct file *file, poll_table * wait)
 {
 	poll_wait(file, &rtas_log_wait, wait);
 	if (rtas_log_size)
@@ -581,7 +581,7 @@ static int __init rtas_init(void)
 	if (!rtas_log_buf)
 		return -ENODEV;
 
-	entry = proc_create("powerpc/rtas/error_log", S_IRUSR, NULL,
+	entry = proc_create("powerpc/rtas/error_log", 0400, NULL,
 			    &proc_rtas_log_operations);
 	if (!entry)
 		printk(KERN_ERR "Failed to create error_log proc entry\n");
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 2075322cd225..d73ec518ef80 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -242,14 +242,6 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	unsigned short maj;
 	unsigned short min;
 
-	/* We only show online cpus: disable preempt (overzealous, I
-	 * knew) to prevent cpu going down. */
-	preempt_disable();
-	if (!cpu_online(cpu_id)) {
-		preempt_enable();
-		return 0;
-	}
-
 #ifdef CONFIG_SMP
 	pvr = per_cpu(cpu_pvr, cpu_id);
 #else
@@ -354,12 +346,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		   loops_per_jiffy / (500000/HZ),
 		   (loops_per_jiffy / (5000/HZ)) % 100);
 #endif
-
-#ifdef CONFIG_SMP
 	seq_printf(m, "\n");
-#endif
-
-	preempt_enable();
 
 	/* If this is the last cpu, print the summary */
 	if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids)
@@ -390,10 +377,10 @@ static void c_stop(struct seq_file *m, void *v)
 }
 
 const struct seq_operations cpuinfo_op = {
-	.start =c_start,
-	.next =	c_next,
-	.stop =	c_stop,
-	.show =	show_cpuinfo,
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= show_cpuinfo,
 };
 
 void __init check_for_initrd(void)
@@ -470,13 +457,13 @@ static void __init cpu_init_thread_core_maps(int tpc)
  */
 void __init smp_setup_cpu_maps(void)
 {
-	struct device_node *dn = NULL;
+	struct device_node *dn;
 	int cpu = 0;
 	int nthreads = 1;
 
 	DBG("smp_setup_cpu_maps()\n");
 
-	while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < nr_cpu_ids) {
+	for_each_node_by_type(dn, "cpu") {
 		const __be32 *intserv;
 		__be32 cpu_be;
 		int j, len;
@@ -516,6 +503,11 @@ void __init smp_setup_cpu_maps(void)
 			set_cpu_possible(cpu, true);
 			cpu++;
 		}
+
+		if (cpu >= nr_cpu_ids) {
+			of_node_put(dn);
+			break;
+		}
 	}
 
 	/* If no SMT supported, nthreads is forced to 1 */
@@ -704,6 +696,30 @@ int check_legacy_ioport(unsigned long base_port)
 }
 EXPORT_SYMBOL(check_legacy_ioport);
 
+static int ppc_panic_event(struct notifier_block *this,
+                             unsigned long event, void *ptr)
+{
+	/*
+	 * If firmware-assisted dump has been registered then trigger
+	 * firmware-assisted dump and let firmware handle everything else.
+	 */
+	crash_fadump(NULL, ptr);
+	ppc_md.panic(ptr);  /* May not return */
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block ppc_panic_block = {
+	.notifier_call = ppc_panic_event,
+	.priority = INT_MIN /* may not return; must be done last */
+};
+
+void __init setup_panic(void)
+{
+	if (!ppc_md.panic)
+		return;
+	atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block);
+}
+
 #ifdef CONFIG_CHECK_CACHE_COHERENCY
 /*
  * For platforms that have configurable cache-coherency.  This function
@@ -767,7 +783,7 @@ void arch_setup_pdev_archdata(struct platform_device *pdev)
 {
 	pdev->archdata.dma_mask = DMA_BIT_MASK(32);
 	pdev->dev.dma_mask = &pdev->archdata.dma_mask;
- 	set_dma_ops(&pdev->dev, &dma_direct_ops);
+ 	set_dma_ops(&pdev->dev, &dma_nommu_ops);
 }
 
 static __init void print_system_info(void)
@@ -848,6 +864,9 @@ void __init setup_arch(char **cmdline_p)
 	/* Probe the machine type, establish ppc_md. */
 	probe_machine();
 
+	/* Setup panic notifier if requested by the platform. */
+	setup_panic();
+
 	/*
 	 * Configure ppc_md.power_save (ppc32 only, 64-bit machines do
 	 * it from their respective probe() function.
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
index 21c18071d9d5..3fc11e30308f 100644
--- a/arch/powerpc/kernel/setup.h
+++ b/arch/powerpc/kernel/setup.h
@@ -51,6 +51,10 @@ void record_spr_defaults(void);
 static inline void record_spr_defaults(void) { };
 #endif
 
+#ifdef CONFIG_PPC64
+u64 ppc64_bolted_size(void);
+#endif
+
 /*
  * Having this in kvm_ppc.h makes include dependencies too
  * tricky to solve for setup-common.c so have it here.
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 8956a9856604..c388cc3357fa 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -10,8 +10,6 @@
  *      2 of the License, or (at your option) any later version.
  */
 
-#define DEBUG
-
 #include <linux/export.h>
 #include <linux/string.h>
 #include <linux/sched.h>
@@ -38,6 +36,7 @@
 #include <linux/memory.h>
 #include <linux/nmi.h>
 
+#include <asm/debugfs.h>
 #include <asm/io.h>
 #include <asm/kdump.h>
 #include <asm/prom.h>
@@ -68,6 +67,7 @@
 #include <asm/livepatch.h>
 #include <asm/opal.h>
 #include <asm/cputhreads.h>
+#include <asm/hw_irq.h>
 
 #include "setup.h"
 
@@ -189,6 +189,8 @@ static void __init fixup_boot_paca(void)
 	get_paca()->cpu_start = 1;
 	/* Allow percpu accesses to work until we setup percpu data */
 	get_paca()->data_offset = 0;
+	/* Mark interrupts disabled in PACA */
+	irq_soft_mask_set(IRQS_DISABLED);
 }
 
 static void __init configure_exceptions(void)
@@ -351,7 +353,7 @@ void __init early_setup(unsigned long dt_ptr)
 void early_setup_secondary(void)
 {
 	/* Mark interrupts disabled in PACA */
-	get_paca()->soft_enabled = 0;
+	irq_soft_mask_set(IRQS_DISABLED);
 
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu_secondary();
@@ -567,25 +569,31 @@ void __init initialize_cache_info(void)
 	DBG(" <- initialize_cache_info()\n");
 }
 
-/* This returns the limit below which memory accesses to the linear
- * mapping are guarnateed not to cause a TLB or SLB miss. This is
- * used to allocate interrupt or emergency stacks for which our
- * exception entry path doesn't deal with being interrupted.
+/*
+ * This returns the limit below which memory accesses to the linear
+ * mapping are guarnateed not to cause an architectural exception (e.g.,
+ * TLB or SLB miss fault).
+ *
+ * This is used to allocate PACAs and various interrupt stacks that
+ * that are accessed early in interrupt handlers that must not cause
+ * re-entrant interrupts.
  */
-static __init u64 safe_stack_limit(void)
+__init u64 ppc64_bolted_size(void)
 {
 #ifdef CONFIG_PPC_BOOK3E
 	/* Freescale BookE bolts the entire linear mapping */
-	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
+	/* XXX: BookE ppc64_rma_limit setup seems to disagree? */
+	if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E))
 		return linear_map_top;
 	/* Other BookE, we assume the first GB is bolted */
 	return 1ul << 30;
 #else
+	/* BookS radix, does not take faults on linear mapping */
 	if (early_radix_enabled())
 		return ULONG_MAX;
 
-	/* BookS, the first segment is bolted */
-	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
+	/* BookS hash, the first segment is bolted */
+	if (early_mmu_has_feature(MMU_FTR_1T_SEGMENT))
 		return 1UL << SID_SHIFT_1T;
 	return 1UL << SID_SHIFT;
 #endif
@@ -593,7 +601,7 @@ static __init u64 safe_stack_limit(void)
 
 void __init irqstack_early_init(void)
 {
-	u64 limit = safe_stack_limit();
+	u64 limit = ppc64_bolted_size();
 	unsigned int i;
 
 	/*
@@ -678,7 +686,7 @@ void __init emergency_stack_init(void)
 	 * initialized in kernel/irq.c. These are initialized here in order
 	 * to have emergency stacks available as early as possible.
 	 */
-	limit = min(safe_stack_limit(), ppc64_rma_size);
+	limit = min(ppc64_bolted_size(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
 		struct thread_info *ti;
@@ -801,3 +809,130 @@ static int __init disable_hardlockup_detector(void)
 	return 0;
 }
 early_initcall(disable_hardlockup_detector);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+static enum l1d_flush_type enabled_flush_types;
+static void *l1d_flush_fallback_area;
+static bool no_rfi_flush;
+bool rfi_flush;
+
+static int __init handle_no_rfi_flush(char *p)
+{
+	pr_info("rfi-flush: disabled on command line.");
+	no_rfi_flush = true;
+	return 0;
+}
+early_param("no_rfi_flush", handle_no_rfi_flush);
+
+/*
+ * The RFI flush is not KPTI, but because users will see doco that says to use
+ * nopti we hijack that option here to also disable the RFI flush.
+ */
+static int __init handle_no_pti(char *p)
+{
+	pr_info("rfi-flush: disabling due to 'nopti' on command line.\n");
+	handle_no_rfi_flush(NULL);
+	return 0;
+}
+early_param("nopti", handle_no_pti);
+
+static void do_nothing(void *unused)
+{
+	/*
+	 * We don't need to do the flush explicitly, just enter+exit kernel is
+	 * sufficient, the RFI exit handlers will do the right thing.
+	 */
+}
+
+void rfi_flush_enable(bool enable)
+{
+	if (rfi_flush == enable)
+		return;
+
+	if (enable) {
+		do_rfi_flush_fixups(enabled_flush_types);
+		on_each_cpu(do_nothing, NULL, 1);
+	} else
+		do_rfi_flush_fixups(L1D_FLUSH_NONE);
+
+	rfi_flush = enable;
+}
+
+static void init_fallback_flush(void)
+{
+	u64 l1d_size, limit;
+	int cpu;
+
+	l1d_size = ppc64_caches.l1d.size;
+	limit = min(ppc64_bolted_size(), ppc64_rma_size);
+
+	/*
+	 * Align to L1d size, and size it at 2x L1d size, to catch possible
+	 * hardware prefetch runoff. We don't have a recipe for load patterns to
+	 * reliably avoid the prefetcher.
+	 */
+	l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit));
+	memset(l1d_flush_fallback_area, 0, l1d_size * 2);
+
+	for_each_possible_cpu(cpu) {
+		paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area;
+		paca[cpu].l1d_flush_size = l1d_size;
+	}
+}
+
+void __init setup_rfi_flush(enum l1d_flush_type types, bool enable)
+{
+	if (types & L1D_FLUSH_FALLBACK) {
+		pr_info("rfi-flush: Using fallback displacement flush\n");
+		init_fallback_flush();
+	}
+
+	if (types & L1D_FLUSH_ORI)
+		pr_info("rfi-flush: Using ori type flush\n");
+
+	if (types & L1D_FLUSH_MTTRIG)
+		pr_info("rfi-flush: Using mttrig type flush\n");
+
+	enabled_flush_types = types;
+
+	if (!no_rfi_flush)
+		rfi_flush_enable(enable);
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int rfi_flush_set(void *data, u64 val)
+{
+	if (val == 1)
+		rfi_flush_enable(true);
+	else if (val == 0)
+		rfi_flush_enable(false);
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int rfi_flush_get(void *data, u64 *val)
+{
+	*val = rfi_flush ? 1 : 0;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n");
+
+static __init int rfi_flush_debugfs_init(void)
+{
+	debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
+	return 0;
+}
+device_initcall(rfi_flush_debugfs_init);
+#endif
+
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	if (rfi_flush)
+		return sprintf(buf, "Mitigation: RFI Flush\n");
+
+	return sprintf(buf, "Vulnerable\n");
+}
+#endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 3d7539b90010..61db86ecd318 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -153,6 +153,9 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 	if (thread_info_flags & _TIF_UPROBE)
 		uprobe_notify_resume(regs);
 
+	if (thread_info_flags & _TIF_PATCH_PENDING)
+		klp_update_patch_state(current);
+
 	if (thread_info_flags & _TIF_SIGPENDING) {
 		BUG_ON(regs != current->thread.regs);
 		do_signal(current);
@@ -163,9 +166,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 		tracehook_notify_resume(regs);
 	}
 
-	if (thread_info_flags & _TIF_PATCH_PENDING)
-		klp_update_patch_state(current);
-
 	user_enter();
 }
 
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 9ffd73296f64..a46de0035214 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -111,12 +111,20 @@ static inline int save_general_regs(struct pt_regs *regs,
 {
 	elf_greg_t64 *gregs = (elf_greg_t64 *)regs;
 	int i;
+	/* Force usr to alway see softe as 1 (interrupts enabled) */
+	elf_greg_t64 softe = 0x1;
 
 	WARN_ON(!FULL_REGS(regs));
 
 	for (i = 0; i <= PT_RESULT; i ++) {
 		if (i == 14 && !FULL_REGS(regs))
 			i = 32;
+		if ( i == PT_SOFTE) {
+			if(__put_user((unsigned int)softe, &frame->mc_gregs[i]))
+				return -EFAULT;
+			else
+				continue;
+		}
 		if (__put_user((unsigned int)gregs[i], &frame->mc_gregs[i]))
 			return -EFAULT;
 	}
@@ -873,75 +881,9 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 #endif
 
 #ifdef CONFIG_PPC64
-int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s)
-{
-	int err;
-
-	if (!access_ok (VERIFY_WRITE, d, sizeof(*d)))
-		return -EFAULT;
-
-	/* If you change siginfo_t structure, please be sure
-	 * this code is fixed accordingly.
-	 * It should never copy any pad contained in the structure
-	 * to avoid security leaks, but must copy the generic
-	 * 3 ints plus the relevant union member.
-	 * This routine must convert siginfo from 64bit to 32bit as well
-	 * at the same time.
-	 */
-	err = __put_user(s->si_signo, &d->si_signo);
-	err |= __put_user(s->si_errno, &d->si_errno);
-	err |= __put_user(s->si_code, &d->si_code);
-	if (s->si_code < 0)
-		err |= __copy_to_user(&d->_sifields._pad, &s->_sifields._pad,
-				      SI_PAD_SIZE32);
-	else switch(siginfo_layout(s->si_signo, s->si_code)) {
-	case SIL_CHLD:
-		err |= __put_user(s->si_pid, &d->si_pid);
-		err |= __put_user(s->si_uid, &d->si_uid);
-		err |= __put_user(s->si_utime, &d->si_utime);
-		err |= __put_user(s->si_stime, &d->si_stime);
-		err |= __put_user(s->si_status, &d->si_status);
-		break;
-	case SIL_FAULT:
-		err |= __put_user((unsigned int)(unsigned long)s->si_addr,
-				  &d->si_addr);
-		break;
-	case SIL_POLL:
-		err |= __put_user(s->si_band, &d->si_band);
-		err |= __put_user(s->si_fd, &d->si_fd);
-		break;
-	case SIL_TIMER:
-		err |= __put_user(s->si_tid, &d->si_tid);
-		err |= __put_user(s->si_overrun, &d->si_overrun);
-		err |= __put_user(s->si_int, &d->si_int);
-		break;
-	case SIL_SYS:
-		err |= __put_user(ptr_to_compat(s->si_call_addr), &d->si_call_addr);
-		err |= __put_user(s->si_syscall, &d->si_syscall);
-		err |= __put_user(s->si_arch, &d->si_arch);
-		break;
-	case SIL_RT:
-		err |= __put_user(s->si_int, &d->si_int);
-		/* fallthrough */
-	case SIL_KILL:
-		err |= __put_user(s->si_pid, &d->si_pid);
-		err |= __put_user(s->si_uid, &d->si_uid);
-		break;
-	}
-	return err;
-}
 
 #define copy_siginfo_to_user	copy_siginfo_to_user32
 
-int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
-{
-	if (copy_from_user(to, from, 3*sizeof(int)) ||
-	    copy_from_user(to->_sifields._pad,
-			   from->_sifields._pad, SI_PAD_SIZE32))
-		return -EFAULT;
-
-	return 0;
-}
 #endif /* CONFIG_PPC64 */
 
 /*
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 4b9ca3570344..720117690822 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -110,6 +110,8 @@ static long setup_sigcontext(struct sigcontext __user *sc,
 	struct pt_regs *regs = tsk->thread.regs;
 	unsigned long msr = regs->msr;
 	long err = 0;
+	/* Force usr to alway see softe as 1 (interrupts enabled) */
+	unsigned long softe = 0x1;
 
 	BUG_ON(tsk != current);
 
@@ -169,6 +171,7 @@ static long setup_sigcontext(struct sigcontext __user *sc,
 	WARN_ON(!FULL_REGS(regs));
 	err |= __copy_to_user(&sc->gp_regs, regs, GP_REGS_SIZE);
 	err |= __put_user(msr, &sc->gp_regs[PT_MSR]);
+	err |= __put_user(softe, &sc->gp_regs[PT_SOFTE]);
 	err |= __put_user(signr, &sc->signal);
 	err |= __put_user(handler, &sc->handler);
 	if (set != NULL)
@@ -207,7 +210,7 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 	elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc);
 #endif
 	struct pt_regs *regs = tsk->thread.regs;
-	unsigned long msr = tsk->thread.ckpt_regs.msr;
+	unsigned long msr = tsk->thread.regs->msr;
 	long err = 0;
 
 	BUG_ON(tsk != current);
@@ -216,6 +219,12 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 
 	WARN_ON(tm_suspend_disabled);
 
+	/* Restore checkpointed FP, VEC, and VSX bits from ckpt_regs as
+	 * it contains the correct FP, VEC, VSX state after we treclaimed
+	 * the transaction and giveup_all() was called on reclaiming.
+	 */
+	msr |= tsk->thread.ckpt_regs.msr & (MSR_FP | MSR_VEC | MSR_VSX);
+
 	/* Remove TM bits from thread's MSR.  The MSR in the sigcontext
 	 * just indicates to userland that we were doing a transaction, but we
 	 * don't want to return in transactional state.  This also ensures
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index e0a4c1f82e25..bbe7634b3a43 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -543,7 +543,25 @@ void smp_send_debugger_break(void)
 #ifdef CONFIG_KEXEC_CORE
 void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
 {
+	int cpu;
+
 	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, crash_ipi_callback, 1000000);
+	if (kdump_in_progress() && crash_wake_offline) {
+		for_each_present_cpu(cpu) {
+			if (cpu_online(cpu))
+				continue;
+			/*
+			 * crash_ipi_callback will wait for
+			 * all cpus, including offline CPUs.
+			 * We don't care about nmi_ipi_function.
+			 * Offline cpus will jump straight into
+			 * crash_ipi_callback, we can skip the
+			 * entire NMI dance and waiting for
+			 * cpus to clear pending mask, etc.
+			 */
+			do_smp_send_nmi_ipi(cpu);
+		}
+	}
 }
 #endif
 
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index b8d4a1dac39f..5a8bfee6e187 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -485,6 +485,7 @@ SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
 SYSFS_SPRSETUP(purr, SPRN_PURR);
 SYSFS_SPRSETUP(spurr, SPRN_SPURR);
 SYSFS_SPRSETUP(pir, SPRN_PIR);
+SYSFS_SPRSETUP(tscr, SPRN_TSCR);
 
 /*
   Lets only enable read for phyp resources and
@@ -495,6 +496,7 @@ static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
 static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
 static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
 static DEVICE_ATTR(pir, 0400, show_pir, NULL);
+static DEVICE_ATTR(tscr, 0600, show_tscr, store_tscr);
 
 /*
  * This is the system wide DSCR register default value. Any
@@ -785,6 +787,9 @@ static int register_cpu_online(unsigned int cpu)
 
 	if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2))
 		device_create_file(s, &dev_attr_pir);
+
+	if (cpu_has_feature(CPU_FTR_ARCH_206))
+		device_create_file(s, &dev_attr_tscr);
 #endif /* CONFIG_PPC64 */
 
 #ifdef CONFIG_PPC_FSL_BOOK3E
@@ -867,6 +872,9 @@ static int unregister_cpu_online(unsigned int cpu)
 
 	if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2))
 		device_remove_file(s, &dev_attr_pir);
+
+	if (cpu_has_feature(CPU_FTR_ARCH_206))
+		device_remove_file(s, &dev_attr_tscr);
 #endif /* CONFIG_PPC64 */
 
 #ifdef CONFIG_PPC_FSL_BOOK3E
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index fe6f3a285455..a32823dcd9a4 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -244,7 +244,7 @@ static u64 scan_dispatch_log(u64 stop_tb)
 void accumulate_stolen_time(void)
 {
 	u64 sst, ust;
-	u8 save_soft_enabled = local_paca->soft_enabled;
+	unsigned long save_irq_soft_mask = irq_soft_mask_return();
 	struct cpu_accounting_data *acct = &local_paca->accounting;
 
 	/* We are called early in the exception entry, before
@@ -253,7 +253,7 @@ void accumulate_stolen_time(void)
 	 * needs to reflect that so various debug stuff doesn't
 	 * complain
 	 */
-	local_paca->soft_enabled = 0;
+	irq_soft_mask_set(IRQS_DISABLED);
 
 	sst = scan_dispatch_log(acct->starttime_user);
 	ust = scan_dispatch_log(acct->starttime);
@@ -261,7 +261,7 @@ void accumulate_stolen_time(void)
 	acct->utime -= ust;
 	acct->steal_time += ust + sst;
 
-	local_paca->soft_enabled = save_soft_enabled;
+	irq_soft_mask_set(save_irq_soft_mask);
 }
 
 static inline u64 calculate_stolen_time(u64 stop_tb)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f3eb61be0d30..1e48d157196a 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -20,6 +20,7 @@
 #include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/pkeys.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
@@ -38,6 +39,8 @@
 #include <linux/ratelimit.h>
 #include <linux/context_tracking.h>
 #include <linux/smp.h>
+#include <linux/console.h>
+#include <linux/kmsg_dump.h>
 
 #include <asm/emulated_ops.h>
 #include <asm/pgtable.h>
@@ -142,6 +145,28 @@ static int die_owner = -1;
 static unsigned int die_nest_count;
 static int die_counter;
 
+extern void panic_flush_kmsg_start(void)
+{
+	/*
+	 * These are mostly taken from kernel/panic.c, but tries to do
+	 * relatively minimal work. Don't use delay functions (TB may
+	 * be broken), don't crash dump (need to set a firmware log),
+	 * don't run notifiers. We do want to get some information to
+	 * Linux console.
+	 */
+	console_verbose();
+	bust_spinlocks(1);
+}
+
+extern void panic_flush_kmsg_end(void)
+{
+	printk_safe_flush_on_panic();
+	kmsg_dump(KMSG_DUMP_PANIC);
+	bust_spinlocks(0);
+	debug_locks_off();
+	console_flush_on_panic();
+}
+
 static unsigned long oops_begin(struct pt_regs *regs)
 {
 	int cpu;
@@ -266,7 +291,9 @@ void user_single_step_siginfo(struct task_struct *tsk,
 	info->si_addr = (void __user *)regs->nip;
 }
 
-void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
+
+void _exception_pkey(int signr, struct pt_regs *regs, int code,
+		unsigned long addr, int key)
 {
 	siginfo_t info;
 	const char fmt32[] = KERN_INFO "%s[%d]: unhandled signal %d " \
@@ -289,13 +316,27 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
 		local_irq_enable();
 
 	current->thread.trap_nr = code;
+
+	/*
+	 * Save all the pkey registers AMR/IAMR/UAMOR. Eg: Core dumps need
+	 * to capture the content, if the task gets killed.
+	 */
+	thread_pkey_regs_save(&current->thread);
+
 	memset(&info, 0, sizeof(info));
 	info.si_signo = signr;
 	info.si_code = code;
 	info.si_addr = (void __user *) addr;
+	info.si_pkey = key;
+
 	force_sig_info(signr, &info, current);
 }
 
+void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
+{
+	_exception_pkey(signr, regs, code, addr, 0);
+}
+
 void system_reset_exception(struct pt_regs *regs)
 {
 	/*
@@ -337,7 +378,7 @@ void system_reset_exception(struct pt_regs *regs)
 	 * No debugger or crash dump registered, print logs then
 	 * panic.
 	 */
-	__die("System Reset", regs, SIGABRT);
+	die("System Reset", regs, SIGABRT);
 
 	mdelay(2*MSEC_PER_SEC); /* Wait a little while for others to print */
 	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
@@ -917,7 +958,7 @@ void unknown_exception(struct pt_regs *regs)
 	printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
 	       regs->nip, regs->msr, regs->trap);
 
-	_exception(SIGTRAP, regs, 0, 0);
+	_exception(SIGTRAP, regs, TRAP_FIXME, 0);
 
 	exception_exit(prev_state);
 }
@@ -939,7 +980,7 @@ bail:
 
 void RunModeException(struct pt_regs *regs)
 {
-	_exception(SIGTRAP, regs, 0, 0);
+	_exception(SIGTRAP, regs, TRAP_FIXME, 0);
 }
 
 void single_step_exception(struct pt_regs *regs)
@@ -978,7 +1019,7 @@ static void emulate_single_step(struct pt_regs *regs)
 
 static inline int __parse_fpscr(unsigned long fpscr)
 {
-	int ret = 0;
+	int ret = FPE_FIXME;
 
 	/* Invalid operation */
 	if ((fpscr & FPSCR_VE) && (fpscr & FPSCR_VX))
@@ -1564,7 +1605,7 @@ void facility_unavailable_exception(struct pt_regs *regs)
 	u8 status;
 	bool hv;
 
-	hv = (regs->trap == 0xf80);
+	hv = (TRAP(regs) == 0xf80);
 	if (hv)
 		value = mfspr(SPRN_HFSCR);
 	else
@@ -1750,34 +1791,34 @@ static void handle_debug(struct pt_regs *regs, unsigned long debug_status)
 #ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
 		current->thread.debug.dbcr2 &= ~DBCR2_DAC12MODE;
 #endif
-		do_send_trap(regs, mfspr(SPRN_DAC1), debug_status, TRAP_HWBKPT,
+		do_send_trap(regs, mfspr(SPRN_DAC1), debug_status,
 			     5);
 		changed |= 0x01;
 	}  else if (debug_status & (DBSR_DAC2R | DBSR_DAC2W)) {
 		dbcr_dac(current) &= ~(DBCR_DAC2R | DBCR_DAC2W);
-		do_send_trap(regs, mfspr(SPRN_DAC2), debug_status, TRAP_HWBKPT,
+		do_send_trap(regs, mfspr(SPRN_DAC2), debug_status,
 			     6);
 		changed |= 0x01;
 	}  else if (debug_status & DBSR_IAC1) {
 		current->thread.debug.dbcr0 &= ~DBCR0_IAC1;
 		dbcr_iac_range(current) &= ~DBCR_IAC12MODE;
-		do_send_trap(regs, mfspr(SPRN_IAC1), debug_status, TRAP_HWBKPT,
+		do_send_trap(regs, mfspr(SPRN_IAC1), debug_status,
 			     1);
 		changed |= 0x01;
 	}  else if (debug_status & DBSR_IAC2) {
 		current->thread.debug.dbcr0 &= ~DBCR0_IAC2;
-		do_send_trap(regs, mfspr(SPRN_IAC2), debug_status, TRAP_HWBKPT,
+		do_send_trap(regs, mfspr(SPRN_IAC2), debug_status,
 			     2);
 		changed |= 0x01;
 	}  else if (debug_status & DBSR_IAC3) {
 		current->thread.debug.dbcr0 &= ~DBCR0_IAC3;
 		dbcr_iac_range(current) &= ~DBCR_IAC34MODE;
-		do_send_trap(regs, mfspr(SPRN_IAC3), debug_status, TRAP_HWBKPT,
+		do_send_trap(regs, mfspr(SPRN_IAC3), debug_status,
 			     3);
 		changed |= 0x01;
 	}  else if (debug_status & DBSR_IAC4) {
 		current->thread.debug.dbcr0 &= ~DBCR0_IAC4;
-		do_send_trap(regs, mfspr(SPRN_IAC4), debug_status, TRAP_HWBKPT,
+		do_send_trap(regs, mfspr(SPRN_IAC4), debug_status,
 			     4);
 		changed |= 0x01;
 	}
@@ -1929,7 +1970,7 @@ void SPEFloatingPointException(struct pt_regs *regs)
 	extern int do_spe_mathemu(struct pt_regs *regs);
 	unsigned long spefscr;
 	int fpexc_mode;
-	int code = 0;
+	int code = FPE_FIXME;
 	int err;
 
 	flush_spe_to_thread(current);
@@ -1998,7 +2039,7 @@ void SPEFloatingPointRoundException(struct pt_regs *regs)
 		printk(KERN_ERR "unrecognized spe instruction "
 		       "in %s at %lx\n", current->comm, regs->nip);
 	} else {
-		_exception(SIGFPE, regs, 0, regs->nip);
+		_exception(SIGFPE, regs, FPE_FIXME, regs->nip);
 		return;
 	}
 }
@@ -2113,13 +2154,13 @@ static int __init ppc_warn_emulated_init(void)
 	if (!dir)
 		return -ENOMEM;
 
-	d = debugfs_create_u32("do_warn", S_IRUGO | S_IWUSR, dir,
+	d = debugfs_create_u32("do_warn", 0644, dir,
 			       &ppc_warn_emulated);
 	if (!d)
 		goto fail;
 
 	for (i = 0; i < sizeof(ppc_emulated)/sizeof(*entries); i++) {
-		d = debugfs_create_u32(entries[i].name, S_IRUGO | S_IWUSR, dir,
+		d = debugfs_create_u32(entries[i].name, 0644, dir,
 				       (u32 *)&entries[i].val.counter);
 		if (!d)
 			goto fail;
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index 382021324883..c002adcc694c 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -64,6 +64,12 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	cmpwi	cr0,r3,CLOCK_REALTIME
 	cmpwi	cr1,r3,CLOCK_MONOTONIC
 	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
+
+	cmpwi	cr5,r3,CLOCK_REALTIME_COARSE
+	cmpwi	cr6,r3,CLOCK_MONOTONIC_COARSE
+	cror	cr5*4+eq,cr5*4+eq,cr6*4+eq
+
+	cror	cr0*4+eq,cr0*4+eq,cr5*4+eq
 	bne	cr0,99f
 
 	mflr	r12			/* r12 saves lr */
@@ -72,6 +78,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
 	lis	r7,NSEC_PER_SEC@h	/* want nanoseconds */
 	ori	r7,r7,NSEC_PER_SEC@l
+	beq	cr5,70f
 50:	bl	V_LOCAL_FUNC(__do_get_tspec)	/* get time from tb & kernel */
 	bne	cr1,80f			/* if not monotonic, all done */
 
@@ -97,19 +104,57 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	ld	r0,CFG_TB_UPDATE_COUNT(r3)
         cmpld   cr0,r0,r8		/* check if updated */
 	bne-	50b
+	b	78f
 
-	/* Add wall->monotonic offset and check for overflow or underflow.
+	/*
+	 * For coarse clocks we get data directly from the vdso data page, so
+	 * we don't need to call __do_get_tspec, but we still need to do the
+	 * counter trick.
 	 */
-	add	r4,r4,r6
-	add	r5,r5,r9
-	cmpd	cr0,r5,r7
-	cmpdi	cr1,r5,0
-	blt	1f
-	subf	r5,r7,r5
-	addi	r4,r4,1
-1:	bge	cr1,80f
-	addi	r4,r4,-1
-	add	r5,r5,r7
+70:	ld      r8,CFG_TB_UPDATE_COUNT(r3)
+	andi.   r0,r8,1                 /* pending update ? loop */
+	bne-    70b
+	add     r3,r3,r0		/* r0 is already 0 */
+
+	/*
+	 * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
+	 * too
+	 */
+	ld      r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
+	ld      r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
+	bne     cr6,75f
+
+	/* CLOCK_MONOTONIC_COARSE */
+	lwa     r6,WTOM_CLOCK_SEC(r3)
+	lwa     r9,WTOM_CLOCK_NSEC(r3)
+
+	/* check if counter has updated */
+	or      r0,r6,r9
+75:	or	r0,r0,r4
+	or	r0,r0,r5
+	xor     r0,r0,r0
+	add     r3,r3,r0
+	ld      r0,CFG_TB_UPDATE_COUNT(r3)
+	cmpld   cr0,r0,r8               /* check if updated */
+	bne-    70b
+
+	/* Counter has not updated, so continue calculating proper values for
+	 * sec and nsec if monotonic coarse, or just return with the proper
+	 * values for realtime.
+	 */
+	bne     cr6,80f
+
+	/* Add wall->monotonic offset and check for overflow or underflow */
+78:	add     r4,r4,r6
+	add     r5,r5,r9
+	cmpd    cr0,r5,r7
+	cmpdi   cr1,r5,0
+	blt     79f
+	subf    r5,r7,r5
+	addi    r4,r4,1
+79:	bge     cr1,80f
+	addi    r4,r4,-1
+	add     r5,r5,r7
 
 80:	std	r4,TSPC64_TV_SEC(r11)
 	std	r5,TSPC64_TV_NSEC(r11)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 0494e1566ee2..c8af90ff49f0 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -132,6 +132,15 @@ SECTIONS
 	/* Read-only data */
 	RO_DATA(PAGE_SIZE)
 
+#ifdef CONFIG_PPC64
+	. = ALIGN(8);
+	__rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) {
+		__start___rfi_flush_fixup = .;
+		*(__rfi_flush_fixup)
+		__stop___rfi_flush_fixup = .;
+	}
+#endif
+
 	EXCEPTION_TABLE(0)
 
 	NOTES :kernel :notes
@@ -264,6 +273,7 @@ SECTIONS
 #ifdef CONFIG_PPC32
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
 		DATA_DATA
+		*(.data.rel*)
 		*(.sdata)
 		*(.sdata2)
 		*(.got.plt) *(.got)
@@ -278,7 +288,9 @@ SECTIONS
 	}
 
 	.opd : AT(ADDR(.opd) - LOAD_OFFSET) {
+		__start_opd = .;
 		*(.opd)
+		__end_opd = .;
 	}
 
 	. = ALIGN(256);
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 87da80ccced1..6256dc3b0087 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -6,6 +6,9 @@
  *
  * This uses code from arch/sparc/kernel/nmi.c and kernel/watchdog.c
  */
+
+#define pr_fmt(fmt) "watchdog: " fmt
+
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/init.h>
@@ -26,15 +29,45 @@
 #include <asm/paca.h>
 
 /*
- * The watchdog has a simple timer that runs on each CPU, once per timer
- * period. This is the heartbeat.
+ * The powerpc watchdog ensures that each CPU is able to service timers.
+ * The watchdog sets up a simple timer on each CPU to run once per timer
+ * period, and updates a per-cpu timestamp and a "pending" cpumask. This is
+ * the heartbeat.
+ *
+ * Then there are two systems to check that the heartbeat is still running.
+ * The local soft-NMI, and the SMP checker.
+ *
+ * The soft-NMI checker can detect lockups on the local CPU. When interrupts
+ * are disabled with local_irq_disable(), platforms that use soft-masking
+ * can leave hardware interrupts enabled and handle them with a masked
+ * interrupt handler. The masked handler can send the timer interrupt to the
+ * watchdog's soft_nmi_interrupt(), which appears to Linux as an NMI
+ * interrupt, and can be used to detect CPUs stuck with IRQs disabled.
+ *
+ * The soft-NMI checker will compare the heartbeat timestamp for this CPU
+ * with the current time, and take action if the difference exceeds the
+ * watchdog threshold.
+ *
+ * The limitation of the soft-NMI watchdog is that it does not work when
+ * interrupts are hard disabled or otherwise not being serviced. This is
+ * solved by also having a SMP watchdog where all CPUs check all other
+ * CPUs heartbeat.
  *
- * Then there are checks to see if the heartbeat has not triggered on a CPU
- * for the panic timeout period. Currently the watchdog only supports an
- * SMP check, so the heartbeat only turns on when we have 2 or more CPUs.
+ * The SMP checker can detect lockups on other CPUs. A gobal "pending"
+ * cpumask is kept, containing all CPUs which enable the watchdog. Each
+ * CPU clears their pending bit in their heartbeat timer. When the bitmask
+ * becomes empty, the last CPU to clear its pending bit updates a global
+ * timestamp and refills the pending bitmask.
  *
- * This is not an NMI watchdog, but Linux uses that name for a generic
- * watchdog in some cases, so NMI gets used in some places.
+ * In the heartbeat timer, if any CPU notices that the global timestamp has
+ * not been updated for a period exceeding the watchdog threshold, then it
+ * means the CPU(s) with their bit still set in the pending mask have had
+ * their heartbeat stop, and action is taken.
+ *
+ * Some platforms implement true NMI IPIs, which can by used by the SMP
+ * watchdog to detect an unresponsive CPU and pull it out of its stuck
+ * state with the NMI IPI, to get crash/debug data from it. This way the
+ * SMP watchdog can detect hardware interrupts off lockups.
  */
 
 static cpumask_t wd_cpus_enabled __read_mostly;
@@ -47,19 +80,7 @@ static u64 wd_timer_period_ms __read_mostly;  /* interval between heartbeat */
 static DEFINE_PER_CPU(struct timer_list, wd_timer);
 static DEFINE_PER_CPU(u64, wd_timer_tb);
 
-/*
- * These are for the SMP checker. CPUs clear their pending bit in their
- * heartbeat. If the bitmask becomes empty, the time is noted and the
- * bitmask is refilled.
- *
- * All CPUs clear their bit in the pending mask every timer period.
- * Once all have cleared, the time is noted and the bits are reset.
- * If the time since all clear was greater than the panic timeout,
- * we can panic with the list of stuck CPUs.
- *
- * This will work best with NMI IPIs for crash code so the stuck CPUs
- * can be pulled out to get their backtraces.
- */
+/* SMP checker bits */
 static unsigned long __wd_smp_lock;
 static cpumask_t wd_smp_cpus_pending;
 static cpumask_t wd_smp_cpus_stuck;
@@ -90,7 +111,7 @@ static inline void wd_smp_unlock(unsigned long *flags)
 
 static void wd_lockup_ipi(struct pt_regs *regs)
 {
-	pr_emerg("Watchdog CPU:%d Hard LOCKUP\n", raw_smp_processor_id());
+	pr_emerg("CPU %d Hard LOCKUP\n", raw_smp_processor_id());
 	print_modules();
 	print_irqtrace_events(current);
 	if (regs)
@@ -131,8 +152,8 @@ static void watchdog_smp_panic(int cpu, u64 tb)
 	if (cpumask_weight(&wd_smp_cpus_pending) == 0)
 		goto out;
 
-	pr_emerg("Watchdog CPU:%d detected Hard LOCKUP other CPUS:%*pbl\n",
-			cpu, cpumask_pr_args(&wd_smp_cpus_pending));
+	pr_emerg("CPU %d detected hard LOCKUP on other CPUs %*pbl\n",
+		 cpu, cpumask_pr_args(&wd_smp_cpus_pending));
 
 	if (!sysctl_hardlockup_all_cpu_backtrace) {
 		/*
@@ -175,7 +196,7 @@ static void wd_smp_clear_cpu_pending(int cpu, u64 tb)
 		if (unlikely(cpumask_test_cpu(cpu, &wd_smp_cpus_stuck))) {
 			unsigned long flags;
 
-			pr_emerg("Watchdog CPU:%d became unstuck\n", cpu);
+			pr_emerg("CPU %d became unstuck\n", cpu);
 			wd_smp_lock(&flags);
 			cpumask_clear_cpu(cpu, &wd_smp_cpus_stuck);
 			wd_smp_unlock(&flags);
@@ -233,13 +254,10 @@ void soft_nmi_interrupt(struct pt_regs *regs)
 		}
 		set_cpu_stuck(cpu, tb);
 
-		pr_emerg("Watchdog CPU:%d Hard LOCKUP\n", cpu);
+		pr_emerg("CPU %d self-detected hard LOCKUP @ %pS\n", cpu, (void *)regs->nip);
 		print_modules();
 		print_irqtrace_events(current);
-		if (regs)
-			show_regs(regs);
-		else
-			dump_stack();
+		show_regs(regs);
 
 		wd_smp_unlock(&flags);
 
@@ -388,30 +406,8 @@ int __init watchdog_nmi_probe(void)
 					"powerpc/watchdog:online",
 					start_wd_on_cpu, stop_wd_on_cpu);
 	if (err < 0) {
-		pr_warn("Watchdog could not be initialized");
+		pr_warn("could not be initialized");
 		return err;
 	}
 	return 0;
 }
-
-static void handle_backtrace_ipi(struct pt_regs *regs)
-{
-	nmi_cpu_backtrace(regs);
-}
-
-static void raise_backtrace_ipi(cpumask_t *mask)
-{
-	unsigned int cpu;
-
-	for_each_cpu(cpu, mask) {
-		if (cpu == smp_processor_id())
-			handle_backtrace_ipi(NULL);
-		else
-			smp_send_nmi_ipi(cpu, handle_backtrace_ipi, 1000000);
-	}
-}
-
-void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
-{
-	nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi);
-}
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 29ebe2fd5867..a93d719edc90 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -235,6 +235,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		gpte->may_read = true;
 		gpte->may_write = true;
 		gpte->page_size = MMU_PAGE_4K;
+		gpte->wimg = HPTE_R_M;
 
 		return 0;
 	}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 235319c2574e..b73dbc9e797d 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -65,11 +65,17 @@ struct kvm_resize_hpt {
 	u32 order;
 
 	/* These fields protected by kvm->lock */
+
+	/* Possible values and their usage:
+	 *  <0     an error occurred during allocation,
+	 *  -EBUSY allocation is in the progress,
+	 *  0      allocation made successfuly.
+	 */
 	int error;
-	bool prepare_done;
 
-	/* Private to the work thread, until prepare_done is true,
-	 * then protected by kvm->resize_hpt_sem */
+	/* Private to the work thread, until error != -EBUSY,
+	 * then protected by kvm->lock.
+	 */
 	struct kvm_hpt_info hpt;
 };
 
@@ -159,8 +165,6 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order)
 		 * Reset all the reverse-mapping chains for all memslots
 		 */
 		kvmppc_rmap_reset(kvm);
-		/* Ensure that each vcpu will flush its TLB on next entry. */
-		cpumask_setall(&kvm->arch.need_tlb_flush);
 		err = 0;
 		goto out;
 	}
@@ -176,6 +180,10 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order)
 	kvmppc_set_hpt(kvm, &info);
 
 out:
+	if (err == 0)
+		/* Ensure that each vcpu will flush its TLB on next entry. */
+		cpumask_setall(&kvm->arch.need_tlb_flush);
+
 	mutex_unlock(&kvm->lock);
 	return err;
 }
@@ -1238,8 +1246,9 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize,
 	unsigned long vpte, rpte, guest_rpte;
 	int ret;
 	struct revmap_entry *rev;
-	unsigned long apsize, psize, avpn, pteg, hash;
+	unsigned long apsize, avpn, pteg, hash;
 	unsigned long new_idx, new_pteg, replace_vpte;
+	int pshift;
 
 	hptep = (__be64 *)(old->virt + (idx << 4));
 
@@ -1298,8 +1307,8 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize,
 		goto out;
 
 	rpte = be64_to_cpu(hptep[1]);
-	psize = hpte_base_page_size(vpte, rpte);
-	avpn = HPTE_V_AVPN_VAL(vpte) & ~((psize - 1) >> 23);
+	pshift = kvmppc_hpte_base_page_shift(vpte, rpte);
+	avpn = HPTE_V_AVPN_VAL(vpte) & ~(((1ul << pshift) - 1) >> 23);
 	pteg = idx / HPTES_PER_GROUP;
 	if (vpte & HPTE_V_SECONDARY)
 		pteg = ~pteg;
@@ -1311,20 +1320,20 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize,
 		offset = (avpn & 0x1f) << 23;
 		vsid = avpn >> 5;
 		/* We can find more bits from the pteg value */
-		if (psize < (1ULL << 23))
-			offset |= ((vsid ^ pteg) & old_hash_mask) * psize;
+		if (pshift < 23)
+			offset |= ((vsid ^ pteg) & old_hash_mask) << pshift;
 
-		hash = vsid ^ (offset / psize);
+		hash = vsid ^ (offset >> pshift);
 	} else {
 		unsigned long offset, vsid;
 
 		/* We only have 40 - 23 bits of seg_off in avpn */
 		offset = (avpn & 0x1ffff) << 23;
 		vsid = avpn >> 17;
-		if (psize < (1ULL << 23))
-			offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) * psize;
+		if (pshift < 23)
+			offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) << pshift;
 
-		hash = vsid ^ (vsid << 25) ^ (offset / psize);
+		hash = vsid ^ (vsid << 25) ^ (offset >> pshift);
 	}
 
 	new_pteg = hash & new_hash_mask;
@@ -1412,16 +1421,20 @@ static void resize_hpt_pivot(struct kvm_resize_hpt *resize)
 
 static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize)
 {
-	BUG_ON(kvm->arch.resize_hpt != resize);
+	if (WARN_ON(!mutex_is_locked(&kvm->lock)))
+		return;
 
 	if (!resize)
 		return;
 
-	if (resize->hpt.virt)
-		kvmppc_free_hpt(&resize->hpt);
+	if (resize->error != -EBUSY) {
+		if (resize->hpt.virt)
+			kvmppc_free_hpt(&resize->hpt);
+		kfree(resize);
+	}
 
-	kvm->arch.resize_hpt = NULL;
-	kfree(resize);
+	if (kvm->arch.resize_hpt == resize)
+		kvm->arch.resize_hpt = NULL;
 }
 
 static void resize_hpt_prepare_work(struct work_struct *work)
@@ -1430,17 +1443,41 @@ static void resize_hpt_prepare_work(struct work_struct *work)
 						     struct kvm_resize_hpt,
 						     work);
 	struct kvm *kvm = resize->kvm;
-	int err;
+	int err = 0;
 
-	resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n",
-			 resize->order);
-
-	err = resize_hpt_allocate(resize);
+	if (WARN_ON(resize->error != -EBUSY))
+		return;
 
 	mutex_lock(&kvm->lock);
 
+	/* Request is still current? */
+	if (kvm->arch.resize_hpt == resize) {
+		/* We may request large allocations here:
+		 * do not sleep with kvm->lock held for a while.
+		 */
+		mutex_unlock(&kvm->lock);
+
+		resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n",
+				 resize->order);
+
+		err = resize_hpt_allocate(resize);
+
+		/* We have strict assumption about -EBUSY
+		 * when preparing for HPT resize.
+		 */
+		if (WARN_ON(err == -EBUSY))
+			err = -EINPROGRESS;
+
+		mutex_lock(&kvm->lock);
+		/* It is possible that kvm->arch.resize_hpt != resize
+		 * after we grab kvm->lock again.
+		 */
+	}
+
 	resize->error = err;
-	resize->prepare_done = true;
+
+	if (kvm->arch.resize_hpt != resize)
+		resize_hpt_release(kvm, resize);
 
 	mutex_unlock(&kvm->lock);
 }
@@ -1465,14 +1502,12 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
 
 	if (resize) {
 		if (resize->order == shift) {
-			/* Suitable resize in progress */
-			if (resize->prepare_done) {
-				ret = resize->error;
-				if (ret != 0)
-					resize_hpt_release(kvm, resize);
-			} else {
+			/* Suitable resize in progress? */
+			ret = resize->error;
+			if (ret == -EBUSY)
 				ret = 100; /* estimated time in ms */
-			}
+			else if (ret)
+				resize_hpt_release(kvm, resize);
 
 			goto out;
 		}
@@ -1492,6 +1527,8 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
 		ret = -ENOMEM;
 		goto out;
 	}
+
+	resize->error = -EBUSY;
 	resize->order = shift;
 	resize->kvm = kvm;
 	INIT_WORK(&resize->work, resize_hpt_prepare_work);
@@ -1546,16 +1583,12 @@ long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm,
 	if (!resize || (resize->order != shift))
 		goto out;
 
-	ret = -EBUSY;
-	if (!resize->prepare_done)
-		goto out;
-
 	ret = resize->error;
-	if (ret != 0)
+	if (ret)
 		goto out;
 
 	ret = resize_hpt_rehash(resize);
-	if (ret != 0)
+	if (ret)
 		goto out;
 
 	resize_hpt_pivot(resize);
@@ -1801,6 +1834,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 	ssize_t nb;
 	long int err, ret;
 	int mmu_ready;
+	int pshift;
 
 	if (!access_ok(VERIFY_READ, buf, count))
 		return -EFAULT;
@@ -1855,6 +1889,9 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 			err = -EINVAL;
 			if (!(v & HPTE_V_VALID))
 				goto out;
+			pshift = kvmppc_hpte_base_page_shift(v, r);
+			if (pshift <= 0)
+				goto out;
 			lbuf += 2;
 			nb += HPTE_SIZE;
 
@@ -1869,14 +1906,18 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 				goto out;
 			}
 			if (!mmu_ready && is_vrma_hpte(v)) {
-				unsigned long psize = hpte_base_page_size(v, r);
-				unsigned long senc = slb_pgsize_encoding(psize);
-				unsigned long lpcr;
+				unsigned long senc, lpcr;
 
+				senc = slb_pgsize_encoding(1ul << pshift);
 				kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
 					(VRMA_VSID << SLB_VSID_SHIFT_1T);
-				lpcr = senc << (LPCR_VRMASD_SH - 4);
-				kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
+				if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+					lpcr = senc << (LPCR_VRMASD_SH - 4);
+					kvmppc_update_lpcr(kvm, lpcr,
+							   LPCR_VRMASD);
+				} else {
+					kvmppc_setup_partition_table(kvm);
+				}
 				mmu_ready = 1;
 			}
 			++i;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 79ea3d9269db..e4f70c33fbc7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -93,10 +93,10 @@
 static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
 
 static int dynamic_mt_modes = 6;
-module_param(dynamic_mt_modes, int, S_IRUGO | S_IWUSR);
+module_param(dynamic_mt_modes, int, 0644);
 MODULE_PARM_DESC(dynamic_mt_modes, "Set of allowed dynamic micro-threading modes: 0 (= none), 2, 4, or 6 (= 2 or 4)");
 static int target_smt_mode;
-module_param(target_smt_mode, int, S_IRUGO | S_IWUSR);
+module_param(target_smt_mode, int, 0644);
 MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)");
 
 static bool indep_threads_mode = true;
@@ -109,18 +109,15 @@ static struct kernel_param_ops module_param_ops = {
 	.get = param_get_int,
 };
 
-module_param_cb(kvm_irq_bypass, &module_param_ops, &kvm_irq_bypass,
-							S_IRUGO | S_IWUSR);
+module_param_cb(kvm_irq_bypass, &module_param_ops, &kvm_irq_bypass, 0644);
 MODULE_PARM_DESC(kvm_irq_bypass, "Bypass passthrough interrupt optimization");
 
-module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect,
-							S_IRUGO | S_IWUSR);
+module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect, 0644);
 MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
 #endif
 
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
-static void kvmppc_setup_partition_table(struct kvm *kvm);
 
 static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
 		int *ip)
@@ -3574,7 +3571,7 @@ static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
 	return;
 }
 
-static void kvmppc_setup_partition_table(struct kvm *kvm)
+void kvmppc_setup_partition_table(struct kvm *kvm)
 {
 	unsigned long dw0, dw1;
 
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index c356f9a40b24..b11043b23c18 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -87,8 +87,7 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
 				   DSISR_MC_SLB_PARITY | DSISR_MC_DERAT_MULTI);
 		}
 		if (dsisr & DSISR_MC_TLB_MULTI) {
-			if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-				cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_LPID);
+			tlbiel_all_lpid(vcpu->kvm->arch.radix);
 			dsisr &= ~DSISR_MC_TLB_MULTI;
 		}
 		/* Any other errors we don't understand? */
@@ -105,8 +104,7 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
 		reload_slb(vcpu);
 		break;
 	case SRR1_MC_IFETCH_TLBMULTI:
-		if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_LPID);
+		tlbiel_all_lpid(vcpu->kvm->arch.radix);
 		break;
 	default:
 		handled = 0;
@@ -268,17 +266,19 @@ static void kvmppc_tb_resync_done(void)
  *   secondary threads to proceed.
  * - All secondary threads will eventually call opal hmi handler on
  *   their exit path.
+ *
+ * Returns 1 if the timebase offset should be applied, 0 if not.
  */
 
 long kvmppc_realmode_hmi_handler(void)
 {
-	int ptid = local_paca->kvm_hstate.ptid;
 	bool resync_req;
 
-	/* This is only called on primary thread. */
-	BUG_ON(ptid != 0);
 	__this_cpu_inc(irq_stat.hmi_exceptions);
 
+	if (hmi_handle_debugtrig(NULL) >= 0)
+		return 1;
+
 	/*
 	 * By now primary thread has already completed guest->host
 	 * partition switch but haven't signaled secondaries yet.
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 26c11f678fbf..8888e625a999 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -42,7 +42,7 @@ static void *real_vmalloc_addr(void *x)
 }
 
 /* Return 1 if we need to do a global tlbie, 0 if we can use tlbiel */
-static int global_invalidates(struct kvm *kvm, unsigned long flags)
+static int global_invalidates(struct kvm *kvm)
 {
 	int global;
 	int cpu;
@@ -522,7 +522,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 	if (v & HPTE_V_VALID) {
 		hpte[0] &= ~cpu_to_be64(HPTE_V_VALID);
 		rb = compute_tlbie_rb(v, pte_r, pte_index);
-		do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
+		do_tlbies(kvm, &rb, 1, global_invalidates(kvm), true);
 		/*
 		 * The reference (R) and change (C) bits in a HPT
 		 * entry can be set by hardware at any time up until
@@ -572,7 +572,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 
 	if (kvm_is_radix(kvm))
 		return H_FUNCTION;
-	global = global_invalidates(kvm, 0);
+	global = global_invalidates(kvm);
 	for (i = 0; i < 4 && ret == H_SUCCESS; ) {
 		n = 0;
 		for (; i < 4; ++i) {
@@ -732,8 +732,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 			rb = compute_tlbie_rb(v, r, pte_index);
 			hpte[0] = cpu_to_be64((pte_v & ~HPTE_V_VALID) |
 					      HPTE_V_ABSENT);
-			do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags),
-				  true);
+			do_tlbies(kvm, &rb, 1, global_invalidates(kvm), true);
 			/* Don't lose R/C bit updates done by hardware */
 			r |= be64_to_cpu(hpte[1]) & (HPTE_R_R | HPTE_R_C);
 			hpte[1] = cpu_to_be64(r);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 2659844784b8..7886b313d135 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -79,7 +79,7 @@ _GLOBAL_TOC(kvmppc_hv_entry_trampoline)
 	mtmsrd	r0,1		/* clear RI in MSR */
 	mtsrr0	r5
 	mtsrr1	r6
-	RFI
+	RFI_TO_KERNEL
 
 kvmppc_call_hv_entry:
 BEGIN_FTR_SECTION
@@ -199,7 +199,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtmsrd	r6, 1			/* Clear RI in MSR */
 	mtsrr0	r8
 	mtsrr1	r7
-	RFI
+	RFI_TO_KERNEL
 
 	/* Virtual-mode return */
 .Lvirt_return:
@@ -1167,8 +1167,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r4, VCPU_GPR(R4)(r4)
-
-	hrfid
+	HRFI_TO_GUEST
 	b	.
 
 secondary_too_late:
@@ -1909,16 +1908,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	bne	27f
 	bl	kvmppc_realmode_hmi_handler
 	nop
+	cmpdi	r3, 0
 	li	r12, BOOK3S_INTERRUPT_HMI
 	/*
-	 * At this point kvmppc_realmode_hmi_handler would have resync-ed
-	 * the TB. Hence it is not required to subtract guest timebase
-	 * offset from timebase. So, skip it.
+	 * At this point kvmppc_realmode_hmi_handler may have resync-ed
+	 * the TB, and if it has, we must not subtract the guest timebase
+	 * offset from the timebase. So, skip it.
 	 *
 	 * Also, do not call kvmppc_subcore_exit_guest() because it has
 	 * been invoked as part of kvmppc_realmode_hmi_handler().
 	 */
-	b	30f
+	beq	30f
 
 27:
 	/* Subtract timebase offset from timebase */
@@ -3249,7 +3249,7 @@ kvmppc_bad_host_intr:
 	mfctr	r4
 #endif
 	mfxer	r5
-	lbz	r6, PACASOFTIRQEN(r13)
+	lbz	r6, PACAIRQSOFTMASK(r13)
 	std	r3, _LINK(r1)
 	std	r4, _CTR(r1)
 	std	r5, _XER(r1)
@@ -3320,7 +3320,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	ld	r4, PACAKMSR(r13)
 	mtspr	SPRN_SRR0, r3
 	mtspr	SPRN_SRR1, r4
-	rfid
+	RFI_TO_KERNEL
 9:	addi	r3, r1, STACK_FRAME_OVERHEAD
 	bl	kvmppc_bad_interrupt
 	b	9b
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index d0dc8624198f..7deaeeb14b93 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -60,6 +60,7 @@ static void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
 #define MSR_USER32 MSR_USER
 #define MSR_USER64 MSR_USER
 #define HW_PAGE_SIZE PAGE_SIZE
+#define HPTE_R_M   _PAGE_COHERENT
 #endif
 
 static bool kvmppc_is_split_real(struct kvm_vcpu *vcpu)
@@ -557,6 +558,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		pte.eaddr = eaddr;
 		pte.vpage = eaddr >> 12;
 		pte.page_size = MMU_PAGE_64K;
+		pte.wimg = HPTE_R_M;
 	}
 
 	switch (kvmppc_get_msr(vcpu) & (MSR_DR|MSR_IR)) {
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 42a4b237df5f..34a5adeff084 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -46,6 +46,9 @@
 
 #define FUNC(name)		name
 
+#define RFI_TO_KERNEL	RFI
+#define RFI_TO_GUEST	RFI
+
 .macro INTERRUPT_TRAMPOLINE intno
 
 .global kvmppc_trampoline_\intno
@@ -141,7 +144,7 @@ kvmppc_handler_skip_ins:
 	GET_SCRATCH0(r13)
 
 	/* And get back into the code */
-	RFI
+	RFI_TO_KERNEL
 #endif
 
 /*
@@ -164,6 +167,6 @@ _GLOBAL_TOC(kvmppc_entry_trampoline)
 	ori	r5, r5, MSR_EE
 	mtsrr0	r7
 	mtsrr1	r6
-	RFI
+	RFI_TO_KERNEL
 
 #include "book3s_segment.S"
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 2a2b96d53999..93a180ceefad 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -156,7 +156,7 @@ no_dcbz32_on:
 	PPC_LL	r9, SVCPU_R9(r3)
 	PPC_LL	r3, (SVCPU_R3)(r3)
 
-	RFI
+	RFI_TO_GUEST
 kvmppc_handler_trampoline_enter_end:
 
 
@@ -407,5 +407,5 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	cmpwi	r12, BOOK3S_INTERRUPT_DOORBELL
 	beqa	BOOK3S_INTERRUPT_DOORBELL
 
-	RFI
+	RFI_TO_KERNEL
 kvmppc_handler_trampoline_exit_end:
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index d329b2add7e2..b8356cdc0c04 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -1039,7 +1039,7 @@ static void xics_debugfs_init(struct kvmppc_xics *xics)
 		return;
 	}
 
-	xics->dentry = debugfs_create_file(name, S_IRUGO, powerpc_debugfs_root,
+	xics->dentry = debugfs_create_file(name, 0444, powerpc_debugfs_root,
 					   xics, &xics_debug_fops);
 
 	pr_debug("%s: created %s\n", __func__, name);
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index bf457843e032..6882bc94eba8 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -16,7 +16,7 @@
 #include <linux/delay.h>
 #include <linux/percpu.h>
 #include <linux/cpumask.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/kvm_book3s.h>
 #include <asm/kvm_ppc.h>
 #include <asm/hvcall.h>
@@ -725,7 +725,8 @@ u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu)
 
 	/* Return the per-cpu state for state saving/migration */
 	return (u64)xc->cppr << KVM_REG_PPC_ICP_CPPR_SHIFT |
-	       (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT;
+	       (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT |
+	       (u64)0xff << KVM_REG_PPC_ICP_PPRI_SHIFT;
 }
 
 int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
@@ -1558,7 +1559,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 
 	/*
 	 * Restore P and Q. If the interrupt was pending, we
-	 * force both P and Q, which will trigger a resend.
+	 * force Q and !P, which will trigger a resend.
 	 *
 	 * That means that a guest that had both an interrupt
 	 * pending (queued) and Q set will restore with only
@@ -1566,7 +1567,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 	 * is perfectly fine as coalescing interrupts that haven't
 	 * been presented yet is always allowed.
 	 */
-	if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING)
+	if (val & KVM_XICS_PRESENTED && !(val & KVM_XICS_PENDING))
 		state->old_p = true;
 	if (val & KVM_XICS_QUEUED || val & KVM_XICS_PENDING)
 		state->old_q = true;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6b6c53c42ac9..0a7c88786ec0 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -39,6 +39,10 @@
 #include <asm/iommu.h>
 #include <asm/switch_to.h>
 #include <asm/xive.h>
+#ifdef CONFIG_PPC_PSERIES
+#include <asm/hvcall.h>
+#include <asm/plpar_wrappers.h>
+#endif
 
 #include "timing.h"
 #include "irq.h"
@@ -548,6 +552,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #ifdef CONFIG_KVM_XICS
 	case KVM_CAP_IRQ_XICS:
 #endif
+	case KVM_CAP_PPC_GET_CPU_CHAR:
 		r = 1;
 		break;
 
@@ -1407,7 +1412,6 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int r;
-	sigset_t sigsaved;
 
 	if (vcpu->mmio_needed) {
 		vcpu->mmio_needed = 0;
@@ -1448,16 +1452,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 #endif
 	}
 
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+	kvm_sigset_activate(vcpu);
 
 	if (run->immediate_exit)
 		r = -EINTR;
 	else
 		r = kvmppc_vcpu_run(run, vcpu);
 
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+	kvm_sigset_deactivate(vcpu);
 
 	return r;
 }
@@ -1762,6 +1764,124 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	return r;
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * These functions check whether the underlying hardware is safe
+ * against attacks based on observing the effects of speculatively
+ * executed instructions, and whether it supplies instructions for
+ * use in workarounds.  The information comes from firmware, either
+ * via the device tree on powernv platforms or from an hcall on
+ * pseries platforms.
+ */
+#ifdef CONFIG_PPC_PSERIES
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	struct h_cpu_char_result c;
+	unsigned long rc;
+
+	if (!machine_is(pseries))
+		return -ENOTTY;
+
+	rc = plpar_get_cpu_characteristics(&c);
+	if (rc == H_SUCCESS) {
+		cp->character = c.character;
+		cp->behaviour = c.behaviour;
+		cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+			KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+			KVM_PPC_CPU_CHAR_BR_HINT_HONOURED |
+			KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF |
+			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+	}
+	return 0;
+}
+#else
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	return -ENOTTY;
+}
+#endif
+
+static inline bool have_fw_feat(struct device_node *fw_features,
+				const char *state, const char *name)
+{
+	struct device_node *np;
+	bool r = false;
+
+	np = of_get_child_by_name(fw_features, name);
+	if (np) {
+		r = of_property_read_bool(np, state);
+		of_node_put(np);
+	}
+	return r;
+}
+
+static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	struct device_node *np, *fw_features;
+	int r;
+
+	memset(cp, 0, sizeof(*cp));
+	r = pseries_get_cpu_char(cp);
+	if (r != -ENOTTY)
+		return r;
+
+	np = of_find_node_by_name(NULL, "ibm,opal");
+	if (np) {
+		fw_features = of_get_child_by_name(np, "fw-features");
+		of_node_put(np);
+		if (!fw_features)
+			return 0;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-spec-barrier-ori31,31,0"))
+			cp->character |= KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-bcctrl-serialized"))
+			cp->character |= KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-l1d-flush-ori30,30,0"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-l1d-flush-trig2"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-l1d-thread-split"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-count-cache-disabled"))
+			cp->character |= KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+		cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+			KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+
+		if (have_fw_feat(fw_features, "enabled",
+				 "speculation-policy-favor-security"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY;
+		if (!have_fw_feat(fw_features, "disabled",
+				  "needs-l1d-flush-msr-pr-0-to-1"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR;
+		if (!have_fw_feat(fw_features, "disabled",
+				  "needs-spec-barrier-for-bound-checks"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+
+		of_node_put(fw_features);
+	}
+
+	return 0;
+}
+#endif
+
 long kvm_arch_vm_ioctl(struct file *filp,
                        unsigned int ioctl, unsigned long arg)
 {
@@ -1864,6 +1984,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = -EFAULT;
 		break;
 	}
+	case KVM_PPC_GET_CPU_CHAR: {
+		struct kvm_ppc_cpu_char cpuchar;
+
+		r = kvmppc_get_cpu_char(&cpuchar);
+		if (r >= 0 && copy_to_user(argp, &cpuchar, sizeof(cpuchar)))
+			r = -EFAULT;
+		break;
+	}
 	default: {
 		struct kvm *kvm = filp->private_data;
 		r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index d469224c4ada..e0d881ab304e 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -23,19 +23,26 @@
 #include <asm/code-patching.h>
 #include <asm/setup.h>
 
-static int __patch_instruction(unsigned int *addr, unsigned int instr)
+static int __patch_instruction(unsigned int *exec_addr, unsigned int instr,
+			       unsigned int *patch_addr)
 {
 	int err;
 
-	__put_user_size(instr, addr, 4, err);
+	__put_user_size(instr, patch_addr, 4, err);
 	if (err)
 		return err;
 
-	asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" :: "r" (addr));
+	asm ("dcbst 0, %0; sync; icbi 0,%1; sync; isync" :: "r" (patch_addr),
+							    "r" (exec_addr));
 
 	return 0;
 }
 
+int raw_patch_instruction(unsigned int *addr, unsigned int instr)
+{
+	return __patch_instruction(addr, instr, addr);
+}
+
 #ifdef CONFIG_STRICT_KERNEL_RWX
 static DEFINE_PER_CPU(struct vm_struct *, text_poke_area);
 
@@ -138,7 +145,7 @@ static inline int unmap_patch_area(unsigned long addr)
 int patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	int err;
-	unsigned int *dest = NULL;
+	unsigned int *patch_addr = NULL;
 	unsigned long flags;
 	unsigned long text_poke_addr;
 	unsigned long kaddr = (unsigned long)addr;
@@ -148,8 +155,8 @@ int patch_instruction(unsigned int *addr, unsigned int instr)
 	 * when text_poke_area is not ready, but we still need
 	 * to allow patching. We just do the plain old patching
 	 */
-	if (!this_cpu_read(*PTRRELOC(&text_poke_area)))
-		return __patch_instruction(addr, instr);
+	if (!this_cpu_read(text_poke_area))
+		return raw_patch_instruction(addr, instr);
 
 	local_irq_save(flags);
 
@@ -159,17 +166,10 @@ int patch_instruction(unsigned int *addr, unsigned int instr)
 		goto out;
 	}
 
-	dest = (unsigned int *)(text_poke_addr) +
+	patch_addr = (unsigned int *)(text_poke_addr) +
 			((kaddr & ~PAGE_MASK) / sizeof(unsigned int));
 
-	/*
-	 * We use __put_user_size so that we can handle faults while
-	 * writing to dest and return err to handle faults gracefully
-	 */
-	__put_user_size(instr, dest, 4, err);
-	if (!err)
-		asm ("dcbst 0, %0; sync; icbi 0,%0; icbi 0,%1; sync; isync"
-			::"r" (dest), "r"(addr));
+	__patch_instruction(addr, instr, patch_addr);
 
 	err = unmap_patch_area(text_poke_addr);
 	if (err)
@@ -184,7 +184,7 @@ out:
 
 int patch_instruction(unsigned int *addr, unsigned int instr)
 {
-	return __patch_instruction(addr, instr);
+	return raw_patch_instruction(addr, instr);
 }
 
 #endif /* CONFIG_STRICT_KERNEL_RWX */
@@ -302,6 +302,11 @@ int instr_is_relative_branch(unsigned int instr)
 	return instr_is_branch_iform(instr) || instr_is_branch_bform(instr);
 }
 
+int instr_is_relative_link_branch(unsigned int instr)
+{
+	return instr_is_relative_branch(instr) && (instr & BRANCH_SET_LINK);
+}
+
 static unsigned long branch_iform_target(const unsigned int *instr)
 {
 	signed long imm;
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 41cf5ae273cf..73697c4e3468 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -62,7 +62,7 @@ static int patch_alt_instruction(unsigned int *src, unsigned int *dest,
 		}
 	}
 
-	patch_instruction(dest, instr);
+	raw_patch_instruction(dest, instr);
 
 	return 0;
 }
@@ -91,7 +91,7 @@ static int patch_feature_section(unsigned long value, struct fixup_entry *fcur)
 	}
 
 	for (; dest < end; dest++)
-		patch_instruction(dest, PPC_INST_NOP);
+		raw_patch_instruction(dest, PPC_INST_NOP);
 
 	return 0;
 }
@@ -116,6 +116,47 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 	}
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+void do_rfi_flush_fixups(enum l1d_flush_type types)
+{
+	unsigned int instrs[3], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___rfi_flush_fixup),
+	end = PTRRELOC(&__stop___rfi_flush_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+
+	if (types & L1D_FLUSH_FALLBACK)
+		/* b .+16 to fallback flush */
+		instrs[0] = 0x48000010;
+
+	i = 0;
+	if (types & L1D_FLUSH_ORI) {
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+	}
+
+	if (types & L1D_FLUSH_MTTRIG)
+		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+		patch_instruction(dest + 1, instrs[1]);
+		patch_instruction(dest + 2, instrs[2]);
+	}
+
+	printk(KERN_DEBUG "rfi-flush: patched %d locations\n", i);
+}
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
 void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 {
 	long *start, *end;
@@ -129,7 +170,7 @@ void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 
 	for (; start < end; start++) {
 		dest = (void *)start + *start;
-		patch_instruction(dest, PPC_INST_LWSYNC);
+		raw_patch_instruction(dest, PPC_INST_LWSYNC);
 	}
 }
 
@@ -147,7 +188,7 @@ static void do_final_fixups(void)
 	length = (__end_interrupts - _stext) / sizeof(int);
 
 	while (length--) {
-		patch_instruction(dest, *src);
+		raw_patch_instruction(dest, *src);
 		src++;
 		dest++;
 	}
diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c
index f29212e40f40..849f50cd62f2 100644
--- a/arch/powerpc/mm/8xx_mmu.c
+++ b/arch/powerpc/mm/8xx_mmu.c
@@ -67,7 +67,7 @@ void __init MMU_init_hw(void)
 	/* PIN up to the 3 first 8Mb after IMMR in DTLB table */
 #ifdef CONFIG_PIN_TLB_DATA
 	unsigned long ctr = mfspr(SPRN_MD_CTR) & 0xfe000000;
-	unsigned long flags = 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY;
+	unsigned long flags = 0xf0 | MD_SPS16K | _PAGE_PRIVILEGED | _PAGE_DIRTY;
 #ifdef CONFIG_PIN_TLB_IMMR
 	int i = 29;
 #else
@@ -79,7 +79,7 @@ void __init MMU_init_hw(void)
 	for (; i < 32 && mem >= LARGE_PAGE_SIZE_8M; i++) {
 		mtspr(SPRN_MD_CTR, ctr | (i << 8));
 		mtspr(SPRN_MD_EPN, (unsigned long)__va(addr) | MD_EVALID);
-		mtspr(SPRN_MD_TWC, MD_PS8MEG | MD_SVALID);
+		mtspr(SPRN_MD_TWC, MD_PS8MEG | MD_SVALID | M_APG2);
 		mtspr(SPRN_MD_RPN, addr | flags | _PAGE_PRESENT);
 		addr += LARGE_PAGE_SIZE_8M;
 		mem -= LARGE_PAGE_SIZE_8M;
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 76a6b057d454..f06f3577d8d1 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -9,7 +9,7 @@ ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
 obj-y				:= fault.o mem.o pgtable.o mmap.o \
 				   init_$(BITS).o pgtable_$(BITS).o \
-				   init-common.o mmu_context.o
+				   init-common.o mmu_context.o drmem.o
 obj-$(CONFIG_PPC_MMU_NOHASH)	+= mmu_context_nohash.o tlb_nohash.o \
 				   tlb_nohash_low.o
 obj-$(CONFIG_PPC_BOOK3E)	+= tlb_low_$(BITS)e.o
@@ -44,3 +44,4 @@ obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
 obj-$(CONFIG_SPAPR_TCE_IOMMU)	+= mmu_context_iommu.o
 obj-$(CONFIG_PPC_PTDUMP)	+= dump_linuxpagetables.o
 obj-$(CONFIG_PPC_HTDUMP)	+= dump_hashpagetable.o
+obj-$(CONFIG_PPC_MEM_KEYS)	+= pkeys.o
diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c
new file mode 100644
index 000000000000..1604110c4238
--- /dev/null
+++ b/arch/powerpc/mm/drmem.c
@@ -0,0 +1,439 @@
+/*
+ * Dynamic reconfiguration memory support
+ *
+ * Copyright 2017 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "drmem: " fmt
+
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/memblock.h>
+#include <asm/prom.h>
+#include <asm/drmem.h>
+
+static struct drmem_lmb_info __drmem_info;
+struct drmem_lmb_info *drmem_info = &__drmem_info;
+
+u64 drmem_lmb_memory_max(void)
+{
+	struct drmem_lmb *last_lmb;
+
+	last_lmb = &drmem_info->lmbs[drmem_info->n_lmbs - 1];
+	return last_lmb->base_addr + drmem_lmb_size();
+}
+
+static u32 drmem_lmb_flags(struct drmem_lmb *lmb)
+{
+	/*
+	 * Return the value of the lmb flags field minus the reserved
+	 * bit used internally for hotplug processing.
+	 */
+	return lmb->flags & ~DRMEM_LMB_RESERVED;
+}
+
+static struct property *clone_property(struct property *prop, u32 prop_sz)
+{
+	struct property *new_prop;
+
+	new_prop = kzalloc(sizeof(*new_prop), GFP_KERNEL);
+	if (!new_prop)
+		return NULL;
+
+	new_prop->name = kstrdup(prop->name, GFP_KERNEL);
+	new_prop->value = kzalloc(prop_sz, GFP_KERNEL);
+	if (!new_prop->name || !new_prop->value) {
+		kfree(new_prop->name);
+		kfree(new_prop->value);
+		kfree(new_prop);
+		return NULL;
+	}
+
+	new_prop->length = prop_sz;
+#if defined(CONFIG_OF_DYNAMIC)
+	of_property_set_flag(new_prop, OF_DYNAMIC);
+#endif
+	return new_prop;
+}
+
+static int drmem_update_dt_v1(struct device_node *memory,
+			      struct property *prop)
+{
+	struct property *new_prop;
+	struct of_drconf_cell_v1 *dr_cell;
+	struct drmem_lmb *lmb;
+	u32 *p;
+
+	new_prop = clone_property(prop, prop->length);
+	if (!new_prop)
+		return -1;
+
+	p = new_prop->value;
+	*p++ = cpu_to_be32(drmem_info->n_lmbs);
+
+	dr_cell = (struct of_drconf_cell_v1 *)p;
+
+	for_each_drmem_lmb(lmb) {
+		dr_cell->base_addr = cpu_to_be64(lmb->base_addr);
+		dr_cell->drc_index = cpu_to_be32(lmb->drc_index);
+		dr_cell->aa_index = cpu_to_be32(lmb->aa_index);
+		dr_cell->flags = cpu_to_be32(drmem_lmb_flags(lmb));
+
+		dr_cell++;
+	}
+
+	of_update_property(memory, new_prop);
+	return 0;
+}
+
+static void init_drconf_v2_cell(struct of_drconf_cell_v2 *dr_cell,
+				struct drmem_lmb *lmb)
+{
+	dr_cell->base_addr = cpu_to_be64(lmb->base_addr);
+	dr_cell->drc_index = cpu_to_be32(lmb->drc_index);
+	dr_cell->aa_index = cpu_to_be32(lmb->aa_index);
+	dr_cell->flags = cpu_to_be32(lmb->flags);
+}
+
+static int drmem_update_dt_v2(struct device_node *memory,
+			      struct property *prop)
+{
+	struct property *new_prop;
+	struct of_drconf_cell_v2 *dr_cell;
+	struct drmem_lmb *lmb, *prev_lmb;
+	u32 lmb_sets, prop_sz, seq_lmbs;
+	u32 *p;
+
+	/* First pass, determine how many LMB sets are needed. */
+	lmb_sets = 0;
+	prev_lmb = NULL;
+	for_each_drmem_lmb(lmb) {
+		if (!prev_lmb) {
+			prev_lmb = lmb;
+			lmb_sets++;
+			continue;
+		}
+
+		if (prev_lmb->aa_index != lmb->aa_index ||
+		    prev_lmb->flags != lmb->flags)
+			lmb_sets++;
+
+		prev_lmb = lmb;
+	}
+
+	prop_sz = lmb_sets * sizeof(*dr_cell) + sizeof(__be32);
+	new_prop = clone_property(prop, prop_sz);
+	if (!new_prop)
+		return -1;
+
+	p = new_prop->value;
+	*p++ = cpu_to_be32(lmb_sets);
+
+	dr_cell = (struct of_drconf_cell_v2 *)p;
+
+	/* Second pass, populate the LMB set data */
+	prev_lmb = NULL;
+	seq_lmbs = 0;
+	for_each_drmem_lmb(lmb) {
+		if (prev_lmb == NULL) {
+			/* Start of first LMB set */
+			prev_lmb = lmb;
+			init_drconf_v2_cell(dr_cell, lmb);
+			seq_lmbs++;
+			continue;
+		}
+
+		if (prev_lmb->aa_index != lmb->aa_index ||
+		    prev_lmb->flags != lmb->flags) {
+			/* end of one set, start of another */
+			dr_cell->seq_lmbs = cpu_to_be32(seq_lmbs);
+			dr_cell++;
+
+			init_drconf_v2_cell(dr_cell, lmb);
+			seq_lmbs = 1;
+		} else {
+			seq_lmbs++;
+		}
+
+		prev_lmb = lmb;
+	}
+
+	/* close out last LMB set */
+	dr_cell->seq_lmbs = cpu_to_be32(seq_lmbs);
+	of_update_property(memory, new_prop);
+	return 0;
+}
+
+int drmem_update_dt(void)
+{
+	struct device_node *memory;
+	struct property *prop;
+	int rc = -1;
+
+	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
+	if (!memory)
+		return -1;
+
+	prop = of_find_property(memory, "ibm,dynamic-memory", NULL);
+	if (prop) {
+		rc = drmem_update_dt_v1(memory, prop);
+	} else {
+		prop = of_find_property(memory, "ibm,dynamic-memory-v2", NULL);
+		if (prop)
+			rc = drmem_update_dt_v2(memory, prop);
+	}
+
+	of_node_put(memory);
+	return rc;
+}
+
+static void __init read_drconf_v1_cell(struct drmem_lmb *lmb,
+				       const __be32 **prop)
+{
+	const __be32 *p = *prop;
+
+	lmb->base_addr = dt_mem_next_cell(dt_root_addr_cells, &p);
+	lmb->drc_index = of_read_number(p++, 1);
+
+	p++; /* skip reserved field */
+
+	lmb->aa_index = of_read_number(p++, 1);
+	lmb->flags = of_read_number(p++, 1);
+
+	*prop = p;
+}
+
+static void __init __walk_drmem_v1_lmbs(const __be32 *prop, const __be32 *usm,
+			void (*func)(struct drmem_lmb *, const __be32 **))
+{
+	struct drmem_lmb lmb;
+	u32 i, n_lmbs;
+
+	n_lmbs = of_read_number(prop++, 1);
+
+	for (i = 0; i < n_lmbs; i++) {
+		read_drconf_v1_cell(&lmb, &prop);
+		func(&lmb, &usm);
+	}
+}
+
+static void __init read_drconf_v2_cell(struct of_drconf_cell_v2 *dr_cell,
+				       const __be32 **prop)
+{
+	const __be32 *p = *prop;
+
+	dr_cell->seq_lmbs = of_read_number(p++, 1);
+	dr_cell->base_addr = dt_mem_next_cell(dt_root_addr_cells, &p);
+	dr_cell->drc_index = of_read_number(p++, 1);
+	dr_cell->aa_index = of_read_number(p++, 1);
+	dr_cell->flags = of_read_number(p++, 1);
+
+	*prop = p;
+}
+
+static void __init __walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm,
+			void (*func)(struct drmem_lmb *, const __be32 **))
+{
+	struct of_drconf_cell_v2 dr_cell;
+	struct drmem_lmb lmb;
+	u32 i, j, lmb_sets;
+
+	lmb_sets = of_read_number(prop++, 1);
+
+	for (i = 0; i < lmb_sets; i++) {
+		read_drconf_v2_cell(&dr_cell, &prop);
+
+		for (j = 0; j < dr_cell.seq_lmbs; j++) {
+			lmb.base_addr = dr_cell.base_addr;
+			dr_cell.base_addr += drmem_lmb_size();
+
+			lmb.drc_index = dr_cell.drc_index;
+			dr_cell.drc_index++;
+
+			lmb.aa_index = dr_cell.aa_index;
+			lmb.flags = dr_cell.flags;
+
+			func(&lmb, &usm);
+		}
+	}
+}
+
+#ifdef CONFIG_PPC_PSERIES
+void __init walk_drmem_lmbs_early(unsigned long node,
+			void (*func)(struct drmem_lmb *, const __be32 **))
+{
+	const __be32 *prop, *usm;
+	int len;
+
+	prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len);
+	if (!prop || len < dt_root_size_cells * sizeof(__be32))
+		return;
+
+	drmem_info->lmb_size = dt_mem_next_cell(dt_root_size_cells, &prop);
+
+	usm = of_get_flat_dt_prop(node, "linux,drconf-usable-memory", &len);
+
+	prop = of_get_flat_dt_prop(node, "ibm,dynamic-memory", &len);
+	if (prop) {
+		__walk_drmem_v1_lmbs(prop, usm, func);
+	} else {
+		prop = of_get_flat_dt_prop(node, "ibm,dynamic-memory-v2",
+					   &len);
+		if (prop)
+			__walk_drmem_v2_lmbs(prop, usm, func);
+	}
+
+	memblock_dump_all();
+}
+
+#endif
+
+static int __init init_drmem_lmb_size(struct device_node *dn)
+{
+	const __be32 *prop;
+	int len;
+
+	if (drmem_info->lmb_size)
+		return 0;
+
+	prop = of_get_property(dn, "ibm,lmb-size", &len);
+	if (!prop || len < dt_root_size_cells * sizeof(__be32)) {
+		pr_info("Could not determine LMB size\n");
+		return -1;
+	}
+
+	drmem_info->lmb_size = dt_mem_next_cell(dt_root_size_cells, &prop);
+	return 0;
+}
+
+/*
+ * Returns the property linux,drconf-usable-memory if
+ * it exists (the property exists only in kexec/kdump kernels,
+ * added by kexec-tools)
+ */
+static const __be32 *of_get_usable_memory(struct device_node *dn)
+{
+	const __be32 *prop;
+	u32 len;
+
+	prop = of_get_property(dn, "linux,drconf-usable-memory", &len);
+	if (!prop || len < sizeof(unsigned int))
+		return NULL;
+
+	return prop;
+}
+
+void __init walk_drmem_lmbs(struct device_node *dn,
+			    void (*func)(struct drmem_lmb *, const __be32 **))
+{
+	const __be32 *prop, *usm;
+
+	if (init_drmem_lmb_size(dn))
+		return;
+
+	usm = of_get_usable_memory(dn);
+
+	prop = of_get_property(dn, "ibm,dynamic-memory", NULL);
+	if (prop) {
+		__walk_drmem_v1_lmbs(prop, usm, func);
+	} else {
+		prop = of_get_property(dn, "ibm,dynamic-memory-v2", NULL);
+		if (prop)
+			__walk_drmem_v2_lmbs(prop, usm, func);
+	}
+}
+
+static void __init init_drmem_v1_lmbs(const __be32 *prop)
+{
+	struct drmem_lmb *lmb;
+
+	drmem_info->n_lmbs = of_read_number(prop++, 1);
+
+	drmem_info->lmbs = kcalloc(drmem_info->n_lmbs, sizeof(*lmb),
+				   GFP_KERNEL);
+	if (!drmem_info->lmbs)
+		return;
+
+	for_each_drmem_lmb(lmb)
+		read_drconf_v1_cell(lmb, &prop);
+}
+
+static void __init init_drmem_v2_lmbs(const __be32 *prop)
+{
+	struct drmem_lmb *lmb;
+	struct of_drconf_cell_v2 dr_cell;
+	const __be32 *p;
+	u32 i, j, lmb_sets;
+	int lmb_index;
+
+	lmb_sets = of_read_number(prop++, 1);
+
+	/* first pass, calculate the number of LMBs */
+	p = prop;
+	for (i = 0; i < lmb_sets; i++) {
+		read_drconf_v2_cell(&dr_cell, &p);
+		drmem_info->n_lmbs += dr_cell.seq_lmbs;
+	}
+
+	drmem_info->lmbs = kcalloc(drmem_info->n_lmbs, sizeof(*lmb),
+				   GFP_KERNEL);
+	if (!drmem_info->lmbs)
+		return;
+
+	/* second pass, read in the LMB information */
+	lmb_index = 0;
+	p = prop;
+
+	for (i = 0; i < lmb_sets; i++) {
+		read_drconf_v2_cell(&dr_cell, &p);
+
+		for (j = 0; j < dr_cell.seq_lmbs; j++) {
+			lmb = &drmem_info->lmbs[lmb_index++];
+
+			lmb->base_addr = dr_cell.base_addr;
+			dr_cell.base_addr += drmem_info->lmb_size;
+
+			lmb->drc_index = dr_cell.drc_index;
+			dr_cell.drc_index++;
+
+			lmb->aa_index = dr_cell.aa_index;
+			lmb->flags = dr_cell.flags;
+		}
+	}
+}
+
+static int __init drmem_init(void)
+{
+	struct device_node *dn;
+	const __be32 *prop;
+
+	dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
+	if (!dn) {
+		pr_info("No dynamic reconfiguration memory found\n");
+		return 0;
+	}
+
+	if (init_drmem_lmb_size(dn)) {
+		of_node_put(dn);
+		return 0;
+	}
+
+	prop = of_get_property(dn, "ibm,dynamic-memory", NULL);
+	if (prop) {
+		init_drmem_v1_lmbs(prop);
+	} else {
+		prop = of_get_property(dn, "ibm,dynamic-memory-v2", NULL);
+		if (prop)
+			init_drmem_v2_lmbs(prop);
+	}
+
+	of_node_put(dn);
+	return 0;
+}
+late_initcall(drmem_init);
diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c
index c2e7dea59490..876e2a3c79f2 100644
--- a/arch/powerpc/mm/dump_linuxpagetables.c
+++ b/arch/powerpc/mm/dump_linuxpagetables.c
@@ -112,26 +112,25 @@ struct flag_info {
 
 static const struct flag_info flag_array[] = {
 	{
-#ifdef CONFIG_PPC_BOOK3S_64
-		.mask	= _PAGE_PRIVILEGED,
-		.val	= 0,
-#else
-		.mask	= _PAGE_USER,
+		.mask	= _PAGE_USER | _PAGE_PRIVILEGED,
 		.val	= _PAGE_USER,
-#endif
 		.set	= "user",
 		.clear	= "    ",
 	}, {
-#if _PAGE_RO == 0
-		.mask	= _PAGE_RW,
+		.mask	= _PAGE_RW | _PAGE_RO | _PAGE_NA,
 		.val	= _PAGE_RW,
-#else
-		.mask	= _PAGE_RO,
-		.val	= 0,
-#endif
 		.set	= "rw",
-		.clear	= "ro",
 	}, {
+		.mask	= _PAGE_RW | _PAGE_RO | _PAGE_NA,
+		.val	= _PAGE_RO,
+		.set	= "ro",
+	}, {
+#if _PAGE_NA != 0
+		.mask	= _PAGE_RW | _PAGE_RO | _PAGE_NA,
+		.val	= _PAGE_RO,
+		.set	= "na",
+	}, {
+#endif
 		.mask	= _PAGE_EXEC,
 		.val	= _PAGE_EXEC,
 		.set	= " X ",
@@ -213,7 +212,7 @@ static const struct flag_info flag_array[] = {
 		.val	= H_PAGE_4K_PFN,
 		.set	= "4K_pfn",
 	}, {
-#endif
+#else /* CONFIG_PPC_64K_PAGES */
 		.mask	= H_PAGE_F_GIX,
 		.val	= H_PAGE_F_GIX,
 		.set	= "f_gix",
@@ -224,14 +223,11 @@ static const struct flag_info flag_array[] = {
 		.val	= H_PAGE_F_SECOND,
 		.set	= "f_second",
 	}, {
+#endif /* CONFIG_PPC_64K_PAGES */
 #endif
 		.mask	= _PAGE_SPECIAL,
 		.val	= _PAGE_SPECIAL,
 		.set	= "special",
-	}, {
-		.mask	= _PAGE_SHARED,
-		.val	= _PAGE_SHARED,
-		.set	= "shared",
 	}
 };
 
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 4797d08581ce..866446cf2d9a 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -107,7 +107,8 @@ static bool store_updates_sp(struct pt_regs *regs)
  */
 
 static int
-__bad_area_nosemaphore(struct pt_regs *regs, unsigned long address, int si_code)
+__bad_area_nosemaphore(struct pt_regs *regs, unsigned long address, int si_code,
+		int pkey)
 {
 	/*
 	 * If we are in kernel mode, bail out with a SEGV, this will
@@ -117,17 +118,18 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long address, int si_code)
 	if (!user_mode(regs))
 		return SIGSEGV;
 
-	_exception(SIGSEGV, regs, si_code, address);
+	_exception_pkey(SIGSEGV, regs, si_code, address, pkey);
 
 	return 0;
 }
 
 static noinline int bad_area_nosemaphore(struct pt_regs *regs, unsigned long address)
 {
-	return __bad_area_nosemaphore(regs, address, SEGV_MAPERR);
+	return __bad_area_nosemaphore(regs, address, SEGV_MAPERR, 0);
 }
 
-static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code)
+static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code,
+			int pkey)
 {
 	struct mm_struct *mm = current->mm;
 
@@ -137,12 +139,23 @@ static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code)
 	 */
 	up_read(&mm->mmap_sem);
 
-	return __bad_area_nosemaphore(regs, address, si_code);
+	return __bad_area_nosemaphore(regs, address, si_code, pkey);
 }
 
 static noinline int bad_area(struct pt_regs *regs, unsigned long address)
 {
-	return __bad_area(regs, address, SEGV_MAPERR);
+	return __bad_area(regs, address, SEGV_MAPERR, 0);
+}
+
+static int bad_key_fault_exception(struct pt_regs *regs, unsigned long address,
+				    int pkey)
+{
+	return __bad_area_nosemaphore(regs, address, SEGV_PKUERR, pkey);
+}
+
+static noinline int bad_access(struct pt_regs *regs, unsigned long address)
+{
+	return __bad_area(regs, address, SEGV_ACCERR, 0);
 }
 
 static int do_sigbus(struct pt_regs *regs, unsigned long address,
@@ -427,6 +440,10 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
+	if (error_code & DSISR_KEYFAULT)
+		return bad_key_fault_exception(regs, address,
+					       get_mm_addr_key(mm, address));
+
 	/*
 	 * We want to do this outside mmap_sem, because reading code around nip
 	 * can result in fault, which will cause a deadlock when called with
@@ -490,7 +507,7 @@ retry:
 
 good_area:
 	if (unlikely(access_error(is_write, is_exec, vma)))
-		return bad_area(regs, address);
+		return bad_access(regs, address);
 
 	/*
 	 * If for any reason at all we couldn't handle the fault,
@@ -498,6 +515,31 @@ good_area:
 	 * the fault.
 	 */
 	fault = handle_mm_fault(vma, address, flags);
+
+#ifdef CONFIG_PPC_MEM_KEYS
+	/*
+	 * if the HPTE is not hashed, hardware will not detect
+	 * a key fault. Lets check if we failed because of a
+	 * software detected key fault.
+	 */
+	if (unlikely(fault & VM_FAULT_SIGSEGV) &&
+		!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE,
+			is_exec, 0)) {
+		/*
+		 * The PGD-PDT...PMD-PTE tree may not have been fully setup.
+		 * Hence we cannot walk the tree to locate the PTE, to locate
+		 * the key. Hence let's use vma_pkey() to get the key; instead
+		 * of get_mm_addr_key().
+		 */
+		int pkey = vma_pkey(vma);
+
+		if (likely(pkey)) {
+			up_read(&mm->mmap_sem);
+			return bad_key_fault_exception(regs, address, pkey);
+		}
+	}
+#endif /* CONFIG_PPC_MEM_KEYS */
+
 	major |= fault & VM_FAULT_MAJOR;
 
 	/*
@@ -571,7 +613,7 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 
 	/* kernel has accessed a bad area */
 
-	switch (regs->trap) {
+	switch (TRAP(regs)) {
 	case 0x300:
 	case 0x380:
 		printk(KERN_ALERT "Unable to handle kernel paging request for "
diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c
index 6fa450c12d6d..5a69b51d08a3 100644
--- a/arch/powerpc/mm/hash64_4k.c
+++ b/arch/powerpc/mm/hash64_4k.c
@@ -20,6 +20,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		   pte_t *ptep, unsigned long trap, unsigned long flags,
 		   int ssize, int subpg_prot)
 {
+	real_pte_t rpte;
 	unsigned long hpte_group;
 	unsigned long rflags, pa;
 	unsigned long old_pte, new_pte;
@@ -54,6 +55,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	 * need to add in 0x1 if it's a read-only user page
 	 */
 	rflags = htab_convert_pte_flags(new_pte);
+	rpte = __real_pte(__pte(old_pte), ptep);
 
 	if (cpu_has_feature(CPU_FTR_NOEXECUTE) &&
 	    !cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
@@ -64,13 +66,10 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		/*
 		 * There MIGHT be an HPTE for this pte
 		 */
-		hash = hpt_hash(vpn, shift, ssize);
-		if (old_pte & H_PAGE_F_SECOND)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
+		unsigned long gslot = pte_get_hash_gslot(vpn, shift, ssize,
+							 rpte, 0);
 
-		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_4K,
+		if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, MMU_PAGE_4K,
 					       MMU_PAGE_4K, ssize, flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
@@ -118,8 +117,7 @@ repeat:
 			return -1;
 		}
 		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE;
-		new_pte |= (slot << H_PAGE_F_GIX_SHIFT) &
-			(H_PAGE_F_SECOND | H_PAGE_F_GIX);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
 	}
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;
diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c
index 1a68cb19b0e3..2253bbc6a599 100644
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/hash64_64k.c
@@ -15,34 +15,22 @@
 #include <linux/mm.h>
 #include <asm/machdep.h>
 #include <asm/mmu.h>
+
 /*
- * index from 0 - 15
+ * Return true, if the entry has a slot value which
+ * the software considers as invalid.
  */
-bool __rpte_sub_valid(real_pte_t rpte, unsigned long index)
+static inline bool hpte_soft_invalid(unsigned long hidx)
 {
-	unsigned long g_idx;
-	unsigned long ptev = pte_val(rpte.pte);
-
-	g_idx = (ptev & H_PAGE_COMBO_VALID) >> H_PAGE_F_GIX_SHIFT;
-	index = index >> 2;
-	if (g_idx & (0x1 << index))
-		return true;
-	else
-		return false;
+	return ((hidx & 0xfUL) == 0xfUL);
 }
+
 /*
  * index from 0 - 15
  */
-static unsigned long mark_subptegroup_valid(unsigned long ptev, unsigned long index)
+bool __rpte_sub_valid(real_pte_t rpte, unsigned long index)
 {
-	unsigned long g_idx;
-
-	if (!(ptev & H_PAGE_COMBO))
-		return ptev;
-	index = index >> 2;
-	g_idx = 0x1 << index;
-
-	return ptev | (g_idx << H_PAGE_F_GIX_SHIFT);
+	return !(hpte_soft_invalid(__rpte_to_hidx(rpte, index)));
 }
 
 int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
@@ -50,12 +38,11 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		   int ssize, int subpg_prot)
 {
 	real_pte_t rpte;
-	unsigned long *hidxp;
 	unsigned long hpte_group;
 	unsigned int subpg_index;
-	unsigned long rflags, pa, hidx;
+	unsigned long rflags, pa;
 	unsigned long old_pte, new_pte, subpg_pte;
-	unsigned long vpn, hash, slot;
+	unsigned long vpn, hash, slot, gslot;
 	unsigned long shift = mmu_psize_defs[MMU_PAGE_4K].shift;
 
 	/*
@@ -116,8 +103,8 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		 * On hash insert failure we use old pte value and we don't
 		 * want slot information there if we have a insert failure.
 		 */
-		old_pte &= ~(H_PAGE_HASHPTE | H_PAGE_F_GIX | H_PAGE_F_SECOND);
-		new_pte &= ~(H_PAGE_HASHPTE | H_PAGE_F_GIX | H_PAGE_F_SECOND);
+		old_pte &= ~H_PAGE_HASHPTE;
+		new_pte &= ~H_PAGE_HASHPTE;
 		goto htab_insert_hpte;
 	}
 	/*
@@ -126,18 +113,14 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	if (__rpte_sub_valid(rpte, subpg_index)) {
 		int ret;
 
-		hash = hpt_hash(vpn, shift, ssize);
-		hidx = __rpte_to_hidx(rpte, subpg_index);
-		if (hidx & _PTEIDX_SECONDARY)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += hidx & _PTEIDX_GROUP_IX;
-
-		ret = mmu_hash_ops.hpte_updatepp(slot, rflags, vpn,
+		gslot = pte_get_hash_gslot(vpn, shift, ssize, rpte,
+					   subpg_index);
+		ret = mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn,
 						 MMU_PAGE_4K, MMU_PAGE_4K,
 						 ssize, flags);
+
 		/*
-		 *if we failed because typically the HPTE wasn't really here
+		 * If we failed because typically the HPTE wasn't really here
 		 * we try an insertion.
 		 */
 		if (ret == -1)
@@ -148,6 +131,14 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	}
 
 htab_insert_hpte:
+
+	/*
+	 * Initialize all hidx entries to invalid value, the first time
+	 * the PTE is about to allocate a 4K HPTE.
+	 */
+	if (!(old_pte & H_PAGE_COMBO))
+		rpte.hidx = INVALID_RPTE_HIDX;
+
 	/*
 	 * handle H_PAGE_4K_PFN case
 	 */
@@ -172,15 +163,39 @@ repeat:
 	 * Primary is full, try the secondary
 	 */
 	if (unlikely(slot == -1)) {
+		bool soft_invalid;
+
 		hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
 						rflags, HPTE_V_SECONDARY,
 						MMU_PAGE_4K, MMU_PAGE_4K,
 						ssize);
-		if (slot == -1) {
-			if (mftb() & 0x1)
+
+		soft_invalid = hpte_soft_invalid(slot);
+		if (unlikely(soft_invalid)) {
+			/*
+			 * We got a valid slot from a hardware point of view.
+			 * but we cannot use it, because we use this special
+			 * value; as defined by hpte_soft_invalid(), to track
+			 * invalid slots. We cannot use it. So invalidate it.
+			 */
+			gslot = slot & _PTEIDX_GROUP_IX;
+			mmu_hash_ops.hpte_invalidate(hpte_group + gslot, vpn,
+						     MMU_PAGE_4K, MMU_PAGE_4K,
+						     ssize, 0);
+		}
+
+		if (unlikely(slot == -1 || soft_invalid)) {
+			/*
+			 * For soft invalid slot, let's ensure that we release a
+			 * slot from the primary, with the hope that we will
+			 * acquire that slot next time we try. This will ensure
+			 * that we do not get the same soft-invalid slot.
+			 */
+			if (soft_invalid || (mftb() & 0x1))
 				hpte_group = ((hash & htab_hash_mask) *
 					      HPTES_PER_GROUP) & ~0x7UL;
+
 			mmu_hash_ops.hpte_remove(hpte_group);
 			/*
 			 * FIXME!! Should be try the group from which we removed ?
@@ -198,21 +213,10 @@ repeat:
 				   MMU_PAGE_4K, MMU_PAGE_4K, old_pte);
 		return -1;
 	}
-	/*
-	 * Insert slot number & secondary bit in PTE second half,
-	 * clear H_PAGE_BUSY and set appropriate HPTE slot bit
-	 * Since we have H_PAGE_BUSY set on ptep, we can be sure
-	 * nobody is undating hidx.
-	 */
-	hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
-	rpte.hidx &= ~(0xfUL << (subpg_index << 2));
-	*hidxp = rpte.hidx  | (slot << (subpg_index << 2));
-	new_pte = mark_subptegroup_valid(new_pte, subpg_index);
-	new_pte |=  H_PAGE_HASHPTE;
-	/*
-	 * check __real_pte for details on matching smp_rmb()
-	 */
-	smp_wmb();
+
+	new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot);
+	new_pte |= H_PAGE_HASHPTE;
+
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;
 }
@@ -221,6 +225,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 		    unsigned long vsid, pte_t *ptep, unsigned long trap,
 		    unsigned long flags, int ssize)
 {
+	real_pte_t rpte;
 	unsigned long hpte_group;
 	unsigned long rflags, pa;
 	unsigned long old_pte, new_pte;
@@ -257,6 +262,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 	} while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
 
 	rflags = htab_convert_pte_flags(new_pte);
+	rpte = __real_pte(__pte(old_pte), ptep);
 
 	if (cpu_has_feature(CPU_FTR_NOEXECUTE) &&
 	    !cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
@@ -264,16 +270,13 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 
 	vpn  = hpt_vpn(ea, vsid, ssize);
 	if (unlikely(old_pte & H_PAGE_HASHPTE)) {
+		unsigned long gslot;
+
 		/*
 		 * There MIGHT be an HPTE for this pte
 		 */
-		hash = hpt_hash(vpn, shift, ssize);
-		if (old_pte & H_PAGE_F_SECOND)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
-
-		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_64K,
+		gslot = pte_get_hash_gslot(vpn, shift, ssize, rpte, 0);
+		if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, MMU_PAGE_64K,
 					       MMU_PAGE_64K, ssize,
 					       flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
@@ -322,9 +325,9 @@ repeat:
 					   MMU_PAGE_64K, MMU_PAGE_64K, old_pte);
 			return -1;
 		}
+
 		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE;
-		new_pte |= (slot << H_PAGE_F_GIX_SHIFT) &
-			(H_PAGE_F_SECOND | H_PAGE_F_GIX);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
 	}
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 3848af167df9..a0675e91ad7d 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -47,7 +47,105 @@
 
 DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
-static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+static inline void tlbiel_hash_set_isa206(unsigned int set, unsigned int is)
+{
+	unsigned long rb;
+
+	rb = (set << PPC_BITLSHIFT(51)) | (is << PPC_BITLSHIFT(53));
+
+	asm volatile("tlbiel %0" : : "r" (rb));
+}
+
+/*
+ * tlbiel instruction for hash, set invalidation
+ * i.e., r=1 and is=01 or is=10 or is=11
+ */
+static inline void tlbiel_hash_set_isa300(unsigned int set, unsigned int is,
+					unsigned int pid,
+					unsigned int ric, unsigned int prs)
+{
+	unsigned long rb;
+	unsigned long rs;
+	unsigned int r = 0; /* hash format */
+
+	rb = (set << PPC_BITLSHIFT(51)) | (is << PPC_BITLSHIFT(53));
+	rs = ((unsigned long)pid << PPC_BITLSHIFT(31));
+
+	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4)
+		     : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r)
+		     : "memory");
+}
+
+
+static void tlbiel_all_isa206(unsigned int num_sets, unsigned int is)
+{
+	unsigned int set;
+
+	asm volatile("ptesync": : :"memory");
+
+	for (set = 0; set < num_sets; set++)
+		tlbiel_hash_set_isa206(set, is);
+
+	asm volatile("ptesync": : :"memory");
+}
+
+static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
+{
+	unsigned int set;
+
+	asm volatile("ptesync": : :"memory");
+
+	/*
+	 * Flush the first set of the TLB, and any caching of partition table
+	 * entries. Then flush the remaining sets of the TLB. Hash mode uses
+	 * partition scoped TLB translations.
+	 */
+	tlbiel_hash_set_isa300(0, is, 0, 2, 0);
+	for (set = 1; set < num_sets; set++)
+		tlbiel_hash_set_isa300(set, is, 0, 0, 0);
+
+	/*
+	 * Now invalidate the process table cache.
+	 *
+	 * From ISA v3.0B p. 1078:
+	 *     The following forms are invalid.
+	 *      * PRS=1, R=0, and RIC!=2 (The only process-scoped
+	 *        HPT caching is of the Process Table.)
+	 */
+	tlbiel_hash_set_isa300(0, is, 0, 2, 1);
+
+	asm volatile("ptesync": : :"memory");
+}
+
+void hash__tlbiel_all(unsigned int action)
+{
+	unsigned int is;
+
+	switch (action) {
+	case TLB_INVAL_SCOPE_GLOBAL:
+		is = 3;
+		break;
+	case TLB_INVAL_SCOPE_LPID:
+		is = 2;
+		break;
+	default:
+		BUG();
+	}
+
+	if (early_cpu_has_feature(CPU_FTR_ARCH_300))
+		tlbiel_all_isa300(POWER9_TLB_SETS_HASH, is);
+	else if (early_cpu_has_feature(CPU_FTR_ARCH_207S))
+		tlbiel_all_isa206(POWER8_TLB_SETS, is);
+	else if (early_cpu_has_feature(CPU_FTR_ARCH_206))
+		tlbiel_all_isa206(POWER7_TLB_SETS, is);
+	else
+		WARN(1, "%s called on pre-POWER7 CPU\n", __func__);
+
+	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+}
+
+static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
+						int apsize, int ssize)
 {
 	unsigned long va;
 	unsigned int penc;
@@ -100,7 +198,15 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 			     : "memory");
 		break;
 	}
-	trace_tlbie(0, 0, va, 0, 0, 0, 0);
+	return va;
+}
+
+static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+{
+	unsigned long rb;
+
+	rb = ___tlbie(vpn, psize, apsize, ssize);
+	trace_tlbie(0, 0, rb, 0, 0, 0, 0);
 }
 
 static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
@@ -652,7 +758,7 @@ static void native_hpte_clear(void)
 		if (hpte_v & HPTE_V_VALID) {
 			hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn);
 			hptep->v = 0;
-			__tlbie(vpn, psize, apsize, ssize);
+			___tlbie(vpn, psize, apsize, ssize);
 		}
 	}
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 655a5a9a183d..7d07c7e17db6 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -36,6 +36,7 @@
 #include <linux/memblock.h>
 #include <linux/context_tracking.h>
 #include <linux/libfdt.h>
+#include <linux/pkeys.h>
 
 #include <asm/debugfs.h>
 #include <asm/processor.h>
@@ -232,6 +233,7 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
 		 */
 		rflags |= HPTE_R_M;
 
+	rflags |= pte_to_hpte_pkey_bits(pteflags);
 	return rflags;
 }
 
@@ -606,7 +608,7 @@ static void init_hpte_page_sizes(void)
 			continue;	/* not a supported page size */
 		for (ap = bp; ap < MMU_PAGE_COUNT; ++ap) {
 			penc = mmu_psize_defs[bp].penc[ap];
-			if (penc == -1)
+			if (penc == -1 || !mmu_psize_defs[ap].shift)
 				continue;
 			shift = mmu_psize_defs[ap].shift - LP_SHIFT;
 			if (shift <= 0)
@@ -772,7 +774,7 @@ void resize_hpt_for_hotplug(unsigned long new_mem_size)
 		int rc;
 
 		rc = mmu_hash_ops.resize_hpt(target_hpt_shift);
-		if (rc)
+		if (rc && (rc != -ENODEV))
 			printk(KERN_WARNING
 			       "Unable to resize hash page table to target order %d: %d\n",
 			       target_hpt_shift, rc);
@@ -979,8 +981,9 @@ void __init hash__early_init_devtree(void)
 
 void __init hash__early_init_mmu(void)
 {
+#ifndef CONFIG_PPC_64K_PAGES
 	/*
-	 * We have code in __hash_page_64K() and elsewhere, which assumes it can
+	 * We have code in __hash_page_4K() and elsewhere, which assumes it can
 	 * do the following:
 	 *   new_pte |= (slot << H_PAGE_F_GIX_SHIFT) & (H_PAGE_F_SECOND | H_PAGE_F_GIX);
 	 *
@@ -991,6 +994,7 @@ void __init hash__early_init_mmu(void)
 	 * with a BUILD_BUG_ON().
 	 */
 	BUILD_BUG_ON(H_PAGE_F_SECOND != (1ul  << (H_PAGE_F_GIX_SHIFT + 3)));
+#endif /* CONFIG_PPC_64K_PAGES */
 
 	htab_init_page_sizes();
 
@@ -1049,6 +1053,10 @@ void __init hash__early_init_mmu(void)
 	pr_info("Initializing hash mmu with SLB\n");
 	/* Initialize SLB management */
 	slb_initialize();
+
+	if (cpu_has_feature(CPU_FTR_ARCH_206)
+			&& cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 
 #ifdef CONFIG_SMP
@@ -1068,6 +1076,10 @@ void hash__early_init_mmu_secondary(void)
 	}
 	/* Initialize SLB */
 	slb_initialize();
+
+	if (cpu_has_feature(CPU_FTR_ARCH_206)
+			&& cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 #endif /* CONFIG_SMP */
 
@@ -1569,6 +1581,30 @@ out_exit:
 	local_irq_restore(flags);
 }
 
+#ifdef CONFIG_PPC_MEM_KEYS
+/*
+ * Return the protection key associated with the given address and the
+ * mm_struct.
+ */
+u16 get_mm_addr_key(struct mm_struct *mm, unsigned long address)
+{
+	pte_t *ptep;
+	u16 pkey = 0;
+	unsigned long flags;
+
+	if (!mm || !mm->pgd)
+		return 0;
+
+	local_irq_save(flags);
+	ptep = find_linux_pte(mm->pgd, address, NULL, NULL);
+	if (ptep)
+		pkey = pte_to_pkey_bits(pte_val(READ_ONCE(*ptep)));
+	local_irq_restore(flags);
+
+	return pkey;
+}
+#endif /* CONFIG_PPC_MEM_KEYS */
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 static inline void tm_flush_hash_page(int local)
 {
@@ -1592,29 +1628,42 @@ static inline void tm_flush_hash_page(int local)
 }
 #endif
 
+/*
+ * Return the global hash slot, corresponding to the given PTE, which contains
+ * the HPTE.
+ */
+unsigned long pte_get_hash_gslot(unsigned long vpn, unsigned long shift,
+		int ssize, real_pte_t rpte, unsigned int subpg_index)
+{
+	unsigned long hash, gslot, hidx;
+
+	hash = hpt_hash(vpn, shift, ssize);
+	hidx = __rpte_to_hidx(rpte, subpg_index);
+	if (hidx & _PTEIDX_SECONDARY)
+		hash = ~hash;
+	gslot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+	gslot += hidx & _PTEIDX_GROUP_IX;
+	return gslot;
+}
+
 /* WARNING: This is called from hash_low_64.S, if you change this prototype,
  *          do not forget to update the assembly call site !
  */
 void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
 		     unsigned long flags)
 {
-	unsigned long hash, index, shift, hidx, slot;
+	unsigned long index, shift, gslot;
 	int local = flags & HPTE_LOCAL_UPDATE;
 
 	DBG_LOW("flush_hash_page(vpn=%016lx)\n", vpn);
 	pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
-		hash = hpt_hash(vpn, shift, ssize);
-		hidx = __rpte_to_hidx(pte, index);
-		if (hidx & _PTEIDX_SECONDARY)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += hidx & _PTEIDX_GROUP_IX;
-		DBG_LOW(" sub %ld: hash=%lx, hidx=%lx\n", index, slot, hidx);
+		gslot = pte_get_hash_gslot(vpn, shift, ssize, pte, index);
+		DBG_LOW(" sub %ld: gslot=%lx\n", index, gslot);
 		/*
 		 * We use same base page size and actual psize, because we don't
 		 * use these functions for hugepage
 		 */
-		mmu_hash_ops.hpte_invalidate(slot, vpn, psize, psize,
+		mmu_hash_ops.hpte_invalidate(gslot, vpn, psize, psize,
 					     ssize, local);
 	} pte_iterate_hashed_end();
 
@@ -1825,16 +1874,24 @@ void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base,
 	 */
 	BUG_ON(first_memblock_base != 0);
 
-	/* On LPAR systems, the first entry is our RMA region,
-	 * non-LPAR 64-bit hash MMU systems don't have a limitation
-	 * on real mode access, but using the first entry works well
-	 * enough. We also clamp it to 1G to avoid some funky things
-	 * such as RTAS bugs etc...
+	/*
+	 * On virtualized systems the first entry is our RMA region aka VRMA,
+	 * non-virtualized 64-bit hash MMU systems don't have a limitation
+	 * on real mode access.
+	 *
+	 * For guests on platforms before POWER9, we clamp the it limit to 1G
+	 * to avoid some funky things such as RTAS bugs etc...
 	 */
-	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+	if (!early_cpu_has_feature(CPU_FTR_HVMODE)) {
+		ppc64_rma_size = first_memblock_size;
+		if (!early_cpu_has_feature(CPU_FTR_ARCH_300))
+			ppc64_rma_size = min_t(u64, ppc64_rma_size, 0x40000000);
 
-	/* Finally limit subsequent allocations */
-	memblock_set_current_limit(ppc64_rma_size);
+		/* Finally limit subsequent allocations */
+		memblock_set_current_limit(ppc64_rma_size);
+	} else {
+		ppc64_rma_size = ULONG_MAX;
+	}
 }
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index 0c2a91df3210..12511f5a015f 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -23,6 +23,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		     pte_t *ptep, unsigned long trap, unsigned long flags,
 		     int ssize, unsigned int shift, unsigned int mmu_psize)
 {
+	real_pte_t rpte;
 	unsigned long vpn;
 	unsigned long old_pte, new_pte;
 	unsigned long rflags, pa, sz;
@@ -62,6 +63,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	} while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
 
 	rflags = htab_convert_pte_flags(new_pte);
+	rpte = __real_pte(__pte(old_pte), ptep);
 
 	sz = ((1UL) << shift);
 	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
@@ -72,15 +74,10 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	/* Check if pte already has an hpte (case 2) */
 	if (unlikely(old_pte & H_PAGE_HASHPTE)) {
 		/* There MIGHT be an HPTE for this pte */
-		unsigned long hash, slot;
+		unsigned long gslot;
 
-		hash = hpt_hash(vpn, shift, ssize);
-		if (old_pte & H_PAGE_F_SECOND)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
-
-		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, mmu_psize,
+		gslot = pte_get_hash_gslot(vpn, shift, ssize, rpte, 0);
+		if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, mmu_psize,
 					       mmu_psize, ssize, flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
@@ -107,8 +104,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 			return -1;
 		}
 
-		new_pte |= (slot << H_PAGE_F_GIX_SHIFT) &
-			(H_PAGE_F_SECOND | H_PAGE_F_GIX);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
 	}
 
 	/*
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index a9b9083c5e49..876da2bc1796 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -96,7 +96,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 			*hpdp = __hugepd(__pa(new) |
 					 (shift_to_mmu_psize(pshift) << 2));
 #elif defined(CONFIG_PPC_8xx)
-			*hpdp = __hugepd(__pa(new) |
+			*hpdp = __hugepd(__pa(new) | _PMD_USER |
 					 (pshift == PAGE_SHIFT_8M ? _PMD_PAGE_8M :
 					  _PMD_PAGE_512K) | _PMD_PRESENT);
 #else
@@ -752,7 +752,7 @@ void flush_dcache_icache_hugepage(struct page *page)
  * So long as we atomically load page table pointers we are safe against teardown,
  * we can follow the address down to the the page and take a ref on it.
  * This function need to be called with interrupts disabled. We use this variant
- * when we have MSR[EE] = 0 but the paca->soft_enabled = 1
+ * when we have MSR[EE] = 0 but the paca->irq_soft_mask = IRQS_ENABLED
  */
 pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 			bool *is_thp, unsigned *hpage_shift)
@@ -855,9 +855,7 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 
 	pte = READ_ONCE(*ptep);
 
-	if (!pte_present(pte) || !pte_read(pte))
-		return 0;
-	if (write && !pte_write(pte))
+	if (!pte_access_permitted(pte, write))
 		return 0;
 
 	/* hugepages are never "special" */
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index a07722531b32..f6eb7e8f4c93 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -214,9 +214,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 
 		rc = vmemmap_create_mapping(start, page_size, __pa(p));
 		if (rc < 0) {
-			pr_warning(
-				"vmemmap_populate: Unable to create vmemmap mapping: %d\n",
-				rc);
+			pr_warn("%s: Unable to create vmemmap mapping: %d\n",
+				__func__, rc);
 			return -EFAULT;
 		}
 	}
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 4362b86ef84c..1281c6eb3a85 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -138,8 +138,7 @@ int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock)
 	start = (unsigned long)__va(start);
 	rc = create_section_mapping(start, start + size);
 	if (rc) {
-		pr_warning(
-			"Unable to create mapping for hot added memory 0x%llx..0x%llx: %d\n",
+		pr_warn("Unable to create mapping for hot added memory 0x%llx..0x%llx: %d\n",
 			start, start + size, rc);
 		return -EFAULT;
 	}
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 59c0766ae4e0..929d9ef7083f 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -16,6 +16,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/pkeys.h>
 #include <linux/spinlock.h>
 #include <linux/idr.h>
 #include <linux/export.h>
@@ -118,6 +119,7 @@ static int hash__init_new_context(struct mm_struct *mm)
 
 	subpage_prot_init_new_context(mm);
 
+	pkey_mm_init(mm);
 	return index;
 }
 
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index adb6364f4091..314d19ab9385 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -40,6 +40,7 @@
 #include <asm/hvcall.h>
 #include <asm/setup.h>
 #include <asm/vdso.h>
+#include <asm/drmem.h>
 
 static int numa_enabled = 1;
 
@@ -179,21 +180,6 @@ static const __be32 *of_get_associativity(struct device_node *dev)
 	return of_get_property(dev, "ibm,associativity", NULL);
 }
 
-/*
- * Returns the property linux,drconf-usable-memory if
- * it exists (the property exists only in kexec/kdump kernels,
- * added by kexec-tools)
- */
-static const __be32 *of_get_usable_memory(struct device_node *memory)
-{
-	const __be32 *prop;
-	u32 len;
-	prop = of_get_property(memory, "linux,drconf-usable-memory", &len);
-	if (!prop || len < sizeof(unsigned int))
-		return NULL;
-	return prop;
-}
-
 int __node_distance(int a, int b)
 {
 	int i;
@@ -387,69 +373,6 @@ static unsigned long read_n_cells(int n, const __be32 **buf)
 	return result;
 }
 
-/*
- * Read the next memblock list entry from the ibm,dynamic-memory property
- * and return the information in the provided of_drconf_cell structure.
- */
-static void read_drconf_cell(struct of_drconf_cell *drmem, const __be32 **cellp)
-{
-	const __be32 *cp;
-
-	drmem->base_addr = read_n_cells(n_mem_addr_cells, cellp);
-
-	cp = *cellp;
-	drmem->drc_index = of_read_number(cp, 1);
-	drmem->reserved = of_read_number(&cp[1], 1);
-	drmem->aa_index = of_read_number(&cp[2], 1);
-	drmem->flags = of_read_number(&cp[3], 1);
-
-	*cellp = cp + 4;
-}
-
-/*
- * Retrieve and validate the ibm,dynamic-memory property of the device tree.
- *
- * The layout of the ibm,dynamic-memory property is a number N of memblock
- * list entries followed by N memblock list entries.  Each memblock list entry
- * contains information as laid out in the of_drconf_cell struct above.
- */
-static int of_get_drconf_memory(struct device_node *memory, const __be32 **dm)
-{
-	const __be32 *prop;
-	u32 len, entries;
-
-	prop = of_get_property(memory, "ibm,dynamic-memory", &len);
-	if (!prop || len < sizeof(unsigned int))
-		return 0;
-
-	entries = of_read_number(prop++, 1);
-
-	/* Now that we know the number of entries, revalidate the size
-	 * of the property read in to ensure we have everything
-	 */
-	if (len < (entries * (n_mem_addr_cells + 4) + 1) * sizeof(unsigned int))
-		return 0;
-
-	*dm = prop;
-	return entries;
-}
-
-/*
- * Retrieve and validate the ibm,lmb-size property for drconf memory
- * from the device tree.
- */
-static u64 of_get_lmb_size(struct device_node *memory)
-{
-	const __be32 *prop;
-	u32 len;
-
-	prop = of_get_property(memory, "ibm,lmb-size", &len);
-	if (!prop || len < sizeof(unsigned int))
-		return 0;
-
-	return read_n_cells(n_mem_size_cells, &prop);
-}
-
 struct assoc_arrays {
 	u32	n_arrays;
 	u32	array_sz;
@@ -466,19 +389,27 @@ struct assoc_arrays {
  * indicating the size of each associativity array, followed by a list
  * of N associativity arrays.
  */
-static int of_get_assoc_arrays(struct device_node *memory,
-			       struct assoc_arrays *aa)
+static int of_get_assoc_arrays(struct assoc_arrays *aa)
 {
+	struct device_node *memory;
 	const __be32 *prop;
 	u32 len;
 
+	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
+	if (!memory)
+		return -1;
+
 	prop = of_get_property(memory, "ibm,associativity-lookup-arrays", &len);
-	if (!prop || len < 2 * sizeof(unsigned int))
+	if (!prop || len < 2 * sizeof(unsigned int)) {
+		of_node_put(memory);
 		return -1;
+	}
 
 	aa->n_arrays = of_read_number(prop++, 1);
 	aa->array_sz = of_read_number(prop++, 1);
 
+	of_node_put(memory);
+
 	/* Now that we know the number of arrays and size of each array,
 	 * revalidate the size of the property read in.
 	 */
@@ -493,26 +424,30 @@ static int of_get_assoc_arrays(struct device_node *memory,
  * This is like of_node_to_nid_single() for memory represented in the
  * ibm,dynamic-reconfiguration-memory node.
  */
-static int of_drconf_to_nid_single(struct of_drconf_cell *drmem,
-				   struct assoc_arrays *aa)
+static int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 {
+	struct assoc_arrays aa = { .arrays = NULL };
 	int default_nid = 0;
 	int nid = default_nid;
-	int index;
+	int rc, index;
+
+	rc = of_get_assoc_arrays(&aa);
+	if (rc)
+		return default_nid;
 
-	if (min_common_depth > 0 && min_common_depth <= aa->array_sz &&
-	    !(drmem->flags & DRCONF_MEM_AI_INVALID) &&
-	    drmem->aa_index < aa->n_arrays) {
-		index = drmem->aa_index * aa->array_sz + min_common_depth - 1;
-		nid = of_read_number(&aa->arrays[index], 1);
+	if (min_common_depth > 0 && min_common_depth <= aa.array_sz &&
+	    !(lmb->flags & DRCONF_MEM_AI_INVALID) &&
+	    lmb->aa_index < aa.n_arrays) {
+		index = lmb->aa_index * aa.array_sz + min_common_depth - 1;
+		nid = of_read_number(&aa.arrays[index], 1);
 
 		if (nid == 0xffff || nid >= MAX_NUMNODES)
 			nid = default_nid;
 
 		if (nid > 0) {
-			index = drmem->aa_index * aa->array_sz;
+			index = lmb->aa_index * aa.array_sz;
 			initialize_distance_lookup_table(nid,
-							&aa->arrays[index]);
+							&aa.arrays[index]);
 		}
 	}
 
@@ -551,7 +486,7 @@ static int numa_setup_cpu(unsigned long lcpu)
 	nid = of_node_to_nid_single(cpu);
 
 out_present:
-	if (nid < 0 || !node_online(nid))
+	if (nid < 0 || !node_possible(nid))
 		nid = first_online_node;
 
 	map_cpu_to_node(lcpu, nid);
@@ -645,67 +580,48 @@ static inline int __init read_usm_ranges(const __be32 **usm)
  * Extract NUMA information from the ibm,dynamic-reconfiguration-memory
  * node.  This assumes n_mem_{addr,size}_cells have been set.
  */
-static void __init parse_drconf_memory(struct device_node *memory)
+static void __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
+					const __be32 **usm)
 {
-	const __be32 *uninitialized_var(dm), *usm;
-	unsigned int n, rc, ranges, is_kexec_kdump = 0;
-	unsigned long lmb_size, base, size, sz;
+	unsigned int ranges, is_kexec_kdump = 0;
+	unsigned long base, size, sz;
 	int nid;
-	struct assoc_arrays aa = { .arrays = NULL };
-
-	n = of_get_drconf_memory(memory, &dm);
-	if (!n)
-		return;
-
-	lmb_size = of_get_lmb_size(memory);
-	if (!lmb_size)
-		return;
 
-	rc = of_get_assoc_arrays(memory, &aa);
-	if (rc)
+	/*
+	 * Skip this block if the reserved bit is set in flags (0x80)
+	 * or if the block is not assigned to this partition (0x8)
+	 */
+	if ((lmb->flags & DRCONF_MEM_RESERVED)
+	    || !(lmb->flags & DRCONF_MEM_ASSIGNED))
 		return;
 
-	/* check if this is a kexec/kdump kernel */
-	usm = of_get_usable_memory(memory);
-	if (usm != NULL)
+	if (*usm)
 		is_kexec_kdump = 1;
 
-	for (; n != 0; --n) {
-		struct of_drconf_cell drmem;
-
-		read_drconf_cell(&drmem, &dm);
+	base = lmb->base_addr;
+	size = drmem_lmb_size();
+	ranges = 1;
 
-		/* skip this block if the reserved bit is set in flags (0x80)
-		   or if the block is not assigned to this partition (0x8) */
-		if ((drmem.flags & DRCONF_MEM_RESERVED)
-		    || !(drmem.flags & DRCONF_MEM_ASSIGNED))
-			continue;
-
-		base = drmem.base_addr;
-		size = lmb_size;
-		ranges = 1;
+	if (is_kexec_kdump) {
+		ranges = read_usm_ranges(usm);
+		if (!ranges) /* there are no (base, size) duple */
+			return;
+	}
 
+	do {
 		if (is_kexec_kdump) {
-			ranges = read_usm_ranges(&usm);
-			if (!ranges) /* there are no (base, size) duple */
-				continue;
+			base = read_n_cells(n_mem_addr_cells, usm);
+			size = read_n_cells(n_mem_size_cells, usm);
 		}
-		do {
-			if (is_kexec_kdump) {
-				base = read_n_cells(n_mem_addr_cells, &usm);
-				size = read_n_cells(n_mem_size_cells, &usm);
-			}
-			nid = of_drconf_to_nid_single(&drmem, &aa);
-			fake_numa_create_new_node(
-				((base + size) >> PAGE_SHIFT),
-					   &nid);
-			node_set_online(nid);
-			sz = numa_enforce_memory_limit(base, size);
-			if (sz)
-				memblock_set_node(base, sz,
-						  &memblock.memory, nid);
-		} while (--ranges);
-	}
+
+		nid = of_drconf_to_nid_single(lmb);
+		fake_numa_create_new_node(((base + size) >> PAGE_SHIFT),
+					  &nid);
+		node_set_online(nid);
+		sz = numa_enforce_memory_limit(base, size);
+		if (sz)
+			memblock_set_node(base, sz, &memblock.memory, nid);
+	} while (--ranges);
 }
 
 static int __init parse_numa_properties(void)
@@ -800,8 +716,10 @@ new_range:
 	 * ibm,dynamic-reconfiguration-memory node.
 	 */
 	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
-	if (memory)
-		parse_drconf_memory(memory);
+	if (memory) {
+		walk_drmem_lmbs(memory, numa_setup_drmem_lmb);
+		of_node_put(memory);
+	}
 
 	return 0;
 }
@@ -892,6 +810,32 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 	NODE_DATA(nid)->node_spanned_pages = spanned_pages;
 }
 
+static void __init find_possible_nodes(void)
+{
+	struct device_node *rtas;
+	u32 numnodes, i;
+
+	if (min_common_depth <= 0)
+		return;
+
+	rtas = of_find_node_by_path("/rtas");
+	if (!rtas)
+		return;
+
+	if (of_property_read_u32_index(rtas,
+				"ibm,max-associativity-domains",
+				min_common_depth, &numnodes))
+		goto out;
+
+	for (i = 0; i < numnodes; i++) {
+		if (!node_possible(i))
+			node_set(i, node_possible_map);
+	}
+
+out:
+	of_node_put(rtas);
+}
+
 void __init initmem_init(void)
 {
 	int nid, cpu;
@@ -905,12 +849,15 @@ void __init initmem_init(void)
 	memblock_dump_all();
 
 	/*
-	 * Reduce the possible NUMA nodes to the online NUMA nodes,
-	 * since we do not support node hotplug. This ensures that  we
-	 * lower the maximum NUMA node ID to what is actually present.
+	 * Modify the set of possible NUMA nodes to reflect information
+	 * available about the set of online nodes, and the set of nodes
+	 * that we expect to make use of for this platform's affinity
+	 * calculations.
 	 */
 	nodes_and(node_possible_map, node_possible_map, node_online_map);
 
+	find_possible_nodes();
+
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;
 
@@ -979,43 +926,26 @@ early_param("topology_updates", early_topology_updates);
  * memory represented in the device tree by the property
  * ibm,dynamic-reconfiguration-memory/ibm,dynamic-memory.
  */
-static int hot_add_drconf_scn_to_nid(struct device_node *memory,
-				     unsigned long scn_addr)
+static int hot_add_drconf_scn_to_nid(unsigned long scn_addr)
 {
-	const __be32 *dm;
-	unsigned int drconf_cell_cnt, rc;
+	struct drmem_lmb *lmb;
 	unsigned long lmb_size;
-	struct assoc_arrays aa;
 	int nid = -1;
 
-	drconf_cell_cnt = of_get_drconf_memory(memory, &dm);
-	if (!drconf_cell_cnt)
-		return -1;
-
-	lmb_size = of_get_lmb_size(memory);
-	if (!lmb_size)
-		return -1;
-
-	rc = of_get_assoc_arrays(memory, &aa);
-	if (rc)
-		return -1;
-
-	for (; drconf_cell_cnt != 0; --drconf_cell_cnt) {
-		struct of_drconf_cell drmem;
-
-		read_drconf_cell(&drmem, &dm);
+	lmb_size = drmem_lmb_size();
 
+	for_each_drmem_lmb(lmb) {
 		/* skip this block if it is reserved or not assigned to
 		 * this partition */
-		if ((drmem.flags & DRCONF_MEM_RESERVED)
-		    || !(drmem.flags & DRCONF_MEM_ASSIGNED))
+		if ((lmb->flags & DRCONF_MEM_RESERVED)
+		    || !(lmb->flags & DRCONF_MEM_ASSIGNED))
 			continue;
 
-		if ((scn_addr < drmem.base_addr)
-		    || (scn_addr >= (drmem.base_addr + lmb_size)))
+		if ((scn_addr < lmb->base_addr)
+		    || (scn_addr >= (lmb->base_addr + lmb_size)))
 			continue;
 
-		nid = of_drconf_to_nid_single(&drmem, &aa);
+		nid = of_drconf_to_nid_single(lmb);
 		break;
 	}
 
@@ -1080,7 +1010,7 @@ int hot_add_scn_to_nid(unsigned long scn_addr)
 
 	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
 	if (memory) {
-		nid = hot_add_drconf_scn_to_nid(memory, scn_addr);
+		nid = hot_add_drconf_scn_to_nid(scn_addr);
 		of_node_put(memory);
 	} else {
 		nid = hot_add_node_scn_to_nid(scn_addr);
@@ -1096,11 +1026,7 @@ static u64 hot_add_drconf_memory_max(void)
 {
 	struct device_node *memory = NULL;
 	struct device_node *dn = NULL;
-	unsigned int drconf_cell_cnt = 0;
-	u64 lmb_size = 0;
-	const __be32 *dm = NULL;
 	const __be64 *lrdr = NULL;
-	struct of_drconf_cell drmem;
 
 	dn = of_find_node_by_path("/rtas");
 	if (dn) {
@@ -1112,14 +1038,8 @@ static u64 hot_add_drconf_memory_max(void)
 
 	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
 	if (memory) {
-		drconf_cell_cnt = of_get_drconf_memory(memory, &dm);
-		lmb_size = of_get_lmb_size(memory);
-
-		/* Advance to the last cell, each cell has 6 32 bit integers */
-		dm += (drconf_cell_cnt - 1) * 6;
-		read_drconf_cell(&drmem, &dm);
 		of_node_put(memory);
-		return drmem.base_addr + lmb_size;
+		return drmem_lmb_memory_max();
 	}
 	return 0;
 }
@@ -1278,6 +1198,42 @@ static long vphn_get_associativity(unsigned long cpu,
 	return rc;
 }
 
+int find_and_online_cpu_nid(int cpu)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	int new_nid;
+
+	/* Use associativity from first thread for all siblings */
+	vphn_get_associativity(cpu, associativity);
+	new_nid = associativity_to_nid(associativity);
+	if (new_nid < 0 || !node_possible(new_nid))
+		new_nid = first_online_node;
+
+	if (NODE_DATA(new_nid) == NULL) {
+#ifdef CONFIG_MEMORY_HOTPLUG
+		/*
+		 * Need to ensure that NODE_DATA is initialized for a node from
+		 * available memory (see memblock_alloc_try_nid). If unable to
+		 * init the node, then default to nearest node that has memory
+		 * installed.
+		 */
+		if (try_online_node(new_nid))
+			new_nid = first_online_node;
+#else
+		/*
+		 * Default to using the nearest node that has memory installed.
+		 * Otherwise, it would be necessary to patch the kernel MM code
+		 * to deal with more memoryless-node error conditions.
+		 */
+		new_nid = first_online_node;
+#endif
+	}
+
+	pr_debug("%s:%d cpu %d nid %d\n", __FUNCTION__, __LINE__,
+		cpu, new_nid);
+	return new_nid;
+}
+
 /*
  * Update the CPU maps and sysfs entries for a single CPU when its NUMA
  * characteristics change. This function doesn't perform any locking and is
@@ -1345,7 +1301,6 @@ int numa_update_cpu_topology(bool cpus_locked)
 {
 	unsigned int cpu, sibling, changed = 0;
 	struct topology_update_data *updates, *ud;
-	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	cpumask_t updated_cpus;
 	struct device *dev;
 	int weight, new_nid, i = 0;
@@ -1383,11 +1338,7 @@ int numa_update_cpu_topology(bool cpus_locked)
 			continue;
 		}
 
-		/* Use associativity from first thread for all siblings */
-		vphn_get_associativity(cpu, associativity);
-		new_nid = associativity_to_nid(associativity);
-		if (new_nid < 0 || !node_online(new_nid))
-			new_nid = first_online_node;
+		new_nid = find_and_online_cpu_nid(cpu);
 
 		if (new_nid == numa_cpu_lookup_table[cpu]) {
 			cpumask_andnot(&cpu_associativity_changes_mask,
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index 3b65917785a5..422e80253a33 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -90,16 +90,19 @@ void serialize_against_pte_lookup(struct mm_struct *mm)
  * We use this to invalidate a pmdp entry before switching from a
  * hugepte to regular pmd entry.
  */
-void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
-	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
+	unsigned long old_pmd;
+
+	old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
 	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	/*
 	 * This ensures that generic code that rely on IRQ disabling
 	 * to prevent a parallel THP split work as expected.
 	 */
 	serialize_against_pte_lookup(vma->vm_mm);
+	return __pmd(old_pmd);
 }
 
 static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)
diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c
index ec277913e01b..469808e77e58 100644
--- a/arch/powerpc/mm/pgtable-hash64.c
+++ b/arch/powerpc/mm/pgtable-hash64.c
@@ -296,28 +296,6 @@ pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 	return pgtable;
 }
 
-void hash__pmdp_huge_split_prepare(struct vm_area_struct *vma,
-			       unsigned long address, pmd_t *pmdp)
-{
-	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	VM_BUG_ON(REGION_ID(address) != USER_REGION_ID);
-	VM_BUG_ON(pmd_devmap(*pmdp));
-
-	/*
-	 * We can't mark the pmd none here, because that will cause a race
-	 * against exit_mmap. We need to continue mark pmd TRANS HUGE, while
-	 * we spilt, but at the same time we wan't rest of the ppc64 code
-	 * not to insert hash pte on this, because we will be modifying
-	 * the deposited pgtable in the caller of this function. Hence
-	 * clear the _PAGE_USER so that we move the fault handling to
-	 * higher level function and that will serialize against ptl.
-	 * We need to flush existing hash pte entries here even though,
-	 * the translation is still valid, because we will withdraw
-	 * pgtable_t after this.
-	 */
-	pmd_hugepage_update(vma->vm_mm, address, pmdp, 0, _PAGE_PRIVILEGED);
-}
-
 /*
  * A linux hugepage PMD was changed and the corresponding hash table entries
  * neesd to be flushed.
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index cfbbee941a76..573a9a2ee455 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -579,6 +579,9 @@ void __init radix__early_init_mmu(void)
 
 	radix_init_iamr();
 	radix_init_pgtable();
+
+	if (cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 
 void radix__early_init_mmu_secondary(void)
@@ -600,6 +603,9 @@ void radix__early_init_mmu_secondary(void)
 		radix_init_amor();
 	}
 	radix_init_iamr();
+
+	if (cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 
 void radix__mmu_cleanup_all(void)
@@ -622,22 +628,11 @@ void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
 	 * physical on those processors
 	 */
 	BUG_ON(first_memblock_base != 0);
+
 	/*
-	 * We limit the allocation that depend on ppc64_rma_size
-	 * to first_memblock_size. We also clamp it to 1GB to
-	 * avoid some funky things such as RTAS bugs.
-	 *
-	 * On radix config we really don't have a limitation
-	 * on real mode access. But keeping it as above works
-	 * well enough.
-	 */
-	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
-	/*
-	 * Finally limit subsequent allocations. We really don't want
-	 * to limit the memblock allocations to rma_size. FIXME!! should
-	 * we even limit at all ?
+	 * Radix mode is not limited by RMA / VRMA addressing.
 	 */
-	memblock_set_current_limit(first_memblock_base + first_memblock_size);
+	ppc64_rma_size = ULONG_MAX;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index a03ff3d99e0c..9f361ae571e9 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -54,7 +54,8 @@ static inline int pte_looks_normal(pte_t pte)
 	return 0;
 #else
 	return (pte_val(pte) &
-		(_PAGE_PRESENT | _PAGE_SPECIAL | _PAGE_NO_CACHE | _PAGE_USER)) ==
+		(_PAGE_PRESENT | _PAGE_SPECIAL | _PAGE_NO_CACHE | _PAGE_USER |
+		 _PAGE_PRIVILEGED)) ==
 		(_PAGE_PRESENT | _PAGE_USER);
 #endif
 }
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index f6c7f54c0515..d35d9ad3c1cd 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -98,14 +98,7 @@ ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
 
 	/* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
 	flags &= ~(_PAGE_USER | _PAGE_EXEC);
-
-#ifdef _PAGE_BAP_SR
-	/* _PAGE_USER contains _PAGE_BAP_SR on BookE using the new PTE format
-	 * which means that we just cleared supervisor access... oops ;-) This
-	 * restores it
-	 */
-	flags |= _PAGE_BAP_SR;
-#endif
+	flags |= _PAGE_PRIVILEGED;
 
 	return __ioremap_caller(addr, size, flags, __builtin_return_address(0));
 }
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 813ea22c3e00..c9a623c2d8a2 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -244,20 +244,8 @@ void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size,
 	/*
 	 * Force kernel mapping.
 	 */
-#if defined(CONFIG_PPC_BOOK3S_64)
-	flags |= _PAGE_PRIVILEGED;
-#else
 	flags &= ~_PAGE_USER;
-#endif
-
-
-#ifdef _PAGE_BAP_SR
-	/* _PAGE_USER contains _PAGE_BAP_SR on BookE using the new PTE format
-	 * which means that we just cleared supervisor access... oops ;-) This
-	 * restores it
-	 */
-	flags |= _PAGE_BAP_SR;
-#endif
+	flags |= _PAGE_PRIVILEGED;
 
 	if (ppc_md.ioremap)
 		return ppc_md.ioremap(addr, size, flags, caller);
diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c
new file mode 100644
index 000000000000..ba71c5481f42
--- /dev/null
+++ b/arch/powerpc/mm/pkeys.c
@@ -0,0 +1,468 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * PowerPC Memory Protection Keys management
+ *
+ * Copyright 2017, Ram Pai, IBM Corporation.
+ */
+
+#include <asm/mman.h>
+#include <asm/setup.h>
+#include <linux/pkeys.h>
+#include <linux/of_device.h>
+
+DEFINE_STATIC_KEY_TRUE(pkey_disabled);
+bool pkey_execute_disable_supported;
+int  pkeys_total;		/* Total pkeys as per device tree */
+bool pkeys_devtree_defined;	/* pkey property exported by device tree */
+u32  initial_allocation_mask;	/* Bits set for reserved keys */
+u64  pkey_amr_uamor_mask;	/* Bits in AMR/UMOR not to be touched */
+u64  pkey_iamr_mask;		/* Bits in AMR not to be touched */
+
+#define AMR_BITS_PER_PKEY 2
+#define AMR_RD_BIT 0x1UL
+#define AMR_WR_BIT 0x2UL
+#define IAMR_EX_BIT 0x1UL
+#define PKEY_REG_BITS (sizeof(u64)*8)
+#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey+1) * AMR_BITS_PER_PKEY))
+
+static void scan_pkey_feature(void)
+{
+	u32 vals[2];
+	struct device_node *cpu;
+
+	cpu = of_find_node_by_type(NULL, "cpu");
+	if (!cpu)
+		return;
+
+	if (of_property_read_u32_array(cpu,
+			"ibm,processor-storage-keys", vals, 2))
+		return;
+
+	/*
+	 * Since any pkey can be used for data or execute, we will just treat
+	 * all keys as equal and track them as one entity.
+	 */
+	pkeys_total = be32_to_cpu(vals[0]);
+	pkeys_devtree_defined = true;
+}
+
+static inline bool pkey_mmu_enabled(void)
+{
+	if (firmware_has_feature(FW_FEATURE_LPAR))
+		return pkeys_total;
+	else
+		return cpu_has_feature(CPU_FTR_PKEY);
+}
+
+int pkey_initialize(void)
+{
+	int os_reserved, i;
+
+	/*
+	 * We define PKEY_DISABLE_EXECUTE in addition to the arch-neutral
+	 * generic defines for PKEY_DISABLE_ACCESS and PKEY_DISABLE_WRITE.
+	 * Ensure that the bits a distinct.
+	 */
+	BUILD_BUG_ON(PKEY_DISABLE_EXECUTE &
+		     (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
+
+	/*
+	 * pkey_to_vmflag_bits() assumes that the pkey bits are contiguous
+	 * in the vmaflag. Make sure that is really the case.
+	 */
+	BUILD_BUG_ON(__builtin_clzl(ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT) +
+		     __builtin_popcountl(ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT)
+				!= (sizeof(u64) * BITS_PER_BYTE));
+
+	/* scan the device tree for pkey feature */
+	scan_pkey_feature();
+
+	/*
+	 * Let's assume 32 pkeys on P8 bare metal, if its not defined by device
+	 * tree. We make this exception since skiboot forgot to expose this
+	 * property on power8.
+	 */
+	if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR) &&
+			cpu_has_feature(CPU_FTRS_POWER8))
+		pkeys_total = 32;
+
+	/*
+	 * Adjust the upper limit, based on the number of bits supported by
+	 * arch-neutral code.
+	 */
+	pkeys_total = min_t(int, pkeys_total,
+			(ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT));
+
+	if (!pkey_mmu_enabled() || radix_enabled() || !pkeys_total)
+		static_branch_enable(&pkey_disabled);
+	else
+		static_branch_disable(&pkey_disabled);
+
+	if (static_branch_likely(&pkey_disabled))
+		return 0;
+
+	/*
+	 * The device tree cannot be relied to indicate support for
+	 * execute_disable support. Instead we use a PVR check.
+	 */
+	if (pvr_version_is(PVR_POWER7) || pvr_version_is(PVR_POWER7p))
+		pkey_execute_disable_supported = false;
+	else
+		pkey_execute_disable_supported = true;
+
+#ifdef CONFIG_PPC_4K_PAGES
+	/*
+	 * The OS can manage only 8 pkeys due to its inability to represent them
+	 * in the Linux 4K PTE.
+	 */
+	os_reserved = pkeys_total - 8;
+#else
+	os_reserved = 0;
+#endif
+	/*
+	 * Bits are in LE format. NOTE: 1, 0 are reserved.
+	 * key 0 is the default key, which allows read/write/execute.
+	 * key 1 is recommended not to be used. PowerISA(3.0) page 1015,
+	 * programming note.
+	 */
+	initial_allocation_mask = ~0x0;
+
+	/* register mask is in BE format */
+	pkey_amr_uamor_mask = ~0x0ul;
+	pkey_iamr_mask = ~0x0ul;
+
+	for (i = 2; i < (pkeys_total - os_reserved); i++) {
+		initial_allocation_mask &= ~(0x1 << i);
+		pkey_amr_uamor_mask &= ~(0x3ul << pkeyshift(i));
+		pkey_iamr_mask &= ~(0x1ul << pkeyshift(i));
+	}
+	return 0;
+}
+
+arch_initcall(pkey_initialize);
+
+void pkey_mm_init(struct mm_struct *mm)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return;
+	mm_pkey_allocation_map(mm) = initial_allocation_mask;
+	/* -1 means unallocated or invalid */
+	mm->context.execute_only_pkey = -1;
+}
+
+static inline u64 read_amr(void)
+{
+	return mfspr(SPRN_AMR);
+}
+
+static inline void write_amr(u64 value)
+{
+	mtspr(SPRN_AMR, value);
+}
+
+static inline u64 read_iamr(void)
+{
+	if (!likely(pkey_execute_disable_supported))
+		return 0x0UL;
+
+	return mfspr(SPRN_IAMR);
+}
+
+static inline void write_iamr(u64 value)
+{
+	if (!likely(pkey_execute_disable_supported))
+		return;
+
+	mtspr(SPRN_IAMR, value);
+}
+
+static inline u64 read_uamor(void)
+{
+	return mfspr(SPRN_UAMOR);
+}
+
+static inline void write_uamor(u64 value)
+{
+	mtspr(SPRN_UAMOR, value);
+}
+
+static bool is_pkey_enabled(int pkey)
+{
+	u64 uamor = read_uamor();
+	u64 pkey_bits = 0x3ul << pkeyshift(pkey);
+	u64 uamor_pkey_bits = (uamor & pkey_bits);
+
+	/*
+	 * Both the bits in UAMOR corresponding to the key should be set or
+	 * reset.
+	 */
+	WARN_ON(uamor_pkey_bits && (uamor_pkey_bits != pkey_bits));
+	return !!(uamor_pkey_bits);
+}
+
+static inline void init_amr(int pkey, u8 init_bits)
+{
+	u64 new_amr_bits = (((u64)init_bits & 0x3UL) << pkeyshift(pkey));
+	u64 old_amr = read_amr() & ~((u64)(0x3ul) << pkeyshift(pkey));
+
+	write_amr(old_amr | new_amr_bits);
+}
+
+static inline void init_iamr(int pkey, u8 init_bits)
+{
+	u64 new_iamr_bits = (((u64)init_bits & 0x1UL) << pkeyshift(pkey));
+	u64 old_iamr = read_iamr() & ~((u64)(0x1ul) << pkeyshift(pkey));
+
+	write_iamr(old_iamr | new_iamr_bits);
+}
+
+static void pkey_status_change(int pkey, bool enable)
+{
+	u64 old_uamor;
+
+	/* Reset the AMR and IAMR bits for this key */
+	init_amr(pkey, 0x0);
+	init_iamr(pkey, 0x0);
+
+	/* Enable/disable key */
+	old_uamor = read_uamor();
+	if (enable)
+		old_uamor |= (0x3ul << pkeyshift(pkey));
+	else
+		old_uamor &= ~(0x3ul << pkeyshift(pkey));
+	write_uamor(old_uamor);
+}
+
+void __arch_activate_pkey(int pkey)
+{
+	pkey_status_change(pkey, true);
+}
+
+void __arch_deactivate_pkey(int pkey)
+{
+	pkey_status_change(pkey, false);
+}
+
+/*
+ * Set the access rights in AMR IAMR and UAMOR registers for @pkey to that
+ * specified in @init_val.
+ */
+int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+				unsigned long init_val)
+{
+	u64 new_amr_bits = 0x0ul;
+	u64 new_iamr_bits = 0x0ul;
+
+	if (!is_pkey_enabled(pkey))
+		return -EINVAL;
+
+	if (init_val & PKEY_DISABLE_EXECUTE) {
+		if (!pkey_execute_disable_supported)
+			return -EINVAL;
+		new_iamr_bits |= IAMR_EX_BIT;
+	}
+	init_iamr(pkey, new_iamr_bits);
+
+	/* Set the bits we need in AMR: */
+	if (init_val & PKEY_DISABLE_ACCESS)
+		new_amr_bits |= AMR_RD_BIT | AMR_WR_BIT;
+	else if (init_val & PKEY_DISABLE_WRITE)
+		new_amr_bits |= AMR_WR_BIT;
+
+	init_amr(pkey, new_amr_bits);
+	return 0;
+}
+
+void thread_pkey_regs_save(struct thread_struct *thread)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return;
+
+	/*
+	 * TODO: Skip saving registers if @thread hasn't used any keys yet.
+	 */
+	thread->amr = read_amr();
+	thread->iamr = read_iamr();
+	thread->uamor = read_uamor();
+}
+
+void thread_pkey_regs_restore(struct thread_struct *new_thread,
+			      struct thread_struct *old_thread)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return;
+
+	/*
+	 * TODO: Just set UAMOR to zero if @new_thread hasn't used any keys yet.
+	 */
+	if (old_thread->amr != new_thread->amr)
+		write_amr(new_thread->amr);
+	if (old_thread->iamr != new_thread->iamr)
+		write_iamr(new_thread->iamr);
+	if (old_thread->uamor != new_thread->uamor)
+		write_uamor(new_thread->uamor);
+}
+
+void thread_pkey_regs_init(struct thread_struct *thread)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return;
+
+	write_amr(read_amr() & pkey_amr_uamor_mask);
+	write_iamr(read_iamr() & pkey_iamr_mask);
+	write_uamor(read_uamor() & pkey_amr_uamor_mask);
+}
+
+static inline bool pkey_allows_readwrite(int pkey)
+{
+	int pkey_shift = pkeyshift(pkey);
+
+	if (!is_pkey_enabled(pkey))
+		return true;
+
+	return !(read_amr() & ((AMR_RD_BIT|AMR_WR_BIT) << pkey_shift));
+}
+
+int __execute_only_pkey(struct mm_struct *mm)
+{
+	bool need_to_set_mm_pkey = false;
+	int execute_only_pkey = mm->context.execute_only_pkey;
+	int ret;
+
+	/* Do we need to assign a pkey for mm's execute-only maps? */
+	if (execute_only_pkey == -1) {
+		/* Go allocate one to use, which might fail */
+		execute_only_pkey = mm_pkey_alloc(mm);
+		if (execute_only_pkey < 0)
+			return -1;
+		need_to_set_mm_pkey = true;
+	}
+
+	/*
+	 * We do not want to go through the relatively costly dance to set AMR
+	 * if we do not need to. Check it first and assume that if the
+	 * execute-only pkey is readwrite-disabled than we do not have to set it
+	 * ourselves.
+	 */
+	if (!need_to_set_mm_pkey && !pkey_allows_readwrite(execute_only_pkey))
+		return execute_only_pkey;
+
+	/*
+	 * Set up AMR so that it denies access for everything other than
+	 * execution.
+	 */
+	ret = __arch_set_user_pkey_access(current, execute_only_pkey,
+					  PKEY_DISABLE_ACCESS |
+					  PKEY_DISABLE_WRITE);
+	/*
+	 * If the AMR-set operation failed somehow, just return 0 and
+	 * effectively disable execute-only support.
+	 */
+	if (ret) {
+		mm_pkey_free(mm, execute_only_pkey);
+		return -1;
+	}
+
+	/* We got one, store it and use it from here on out */
+	if (need_to_set_mm_pkey)
+		mm->context.execute_only_pkey = execute_only_pkey;
+	return execute_only_pkey;
+}
+
+static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma)
+{
+	/* Do this check first since the vm_flags should be hot */
+	if ((vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) != VM_EXEC)
+		return false;
+
+	return (vma_pkey(vma) == vma->vm_mm->context.execute_only_pkey);
+}
+
+/*
+ * This should only be called for *plain* mprotect calls.
+ */
+int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot,
+				  int pkey)
+{
+	/*
+	 * If the currently associated pkey is execute-only, but the requested
+	 * protection requires read or write, move it back to the default pkey.
+	 */
+	if (vma_is_pkey_exec_only(vma) && (prot & (PROT_READ | PROT_WRITE)))
+		return 0;
+
+	/*
+	 * The requested protection is execute-only. Hence let's use an
+	 * execute-only pkey.
+	 */
+	if (prot == PROT_EXEC) {
+		pkey = execute_only_pkey(vma->vm_mm);
+		if (pkey > 0)
+			return pkey;
+	}
+
+	/* Nothing to override. */
+	return vma_pkey(vma);
+}
+
+static bool pkey_access_permitted(int pkey, bool write, bool execute)
+{
+	int pkey_shift;
+	u64 amr;
+
+	if (!pkey)
+		return true;
+
+	if (!is_pkey_enabled(pkey))
+		return true;
+
+	pkey_shift = pkeyshift(pkey);
+	if (execute && !(read_iamr() & (IAMR_EX_BIT << pkey_shift)))
+		return true;
+
+	amr = read_amr(); /* Delay reading amr until absolutely needed */
+	return ((!write && !(amr & (AMR_RD_BIT << pkey_shift))) ||
+		(write &&  !(amr & (AMR_WR_BIT << pkey_shift))));
+}
+
+bool arch_pte_access_permitted(u64 pte, bool write, bool execute)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return true;
+
+	return pkey_access_permitted(pte_to_pkey_bits(pte), write, execute);
+}
+
+/*
+ * We only want to enforce protection keys on the current thread because we
+ * effectively have no access to AMR/IAMR for other threads or any way to tell
+ * which AMR/IAMR in a threaded process we could use.
+ *
+ * So do not enforce things if the VMA is not from the current mm, or if we are
+ * in a kernel thread.
+ */
+static inline bool vma_is_foreign(struct vm_area_struct *vma)
+{
+	if (!current->mm)
+		return true;
+
+	/* if it is not our ->mm, it has to be foreign */
+	if (current->mm != vma->vm_mm)
+		return true;
+
+	return false;
+}
+
+bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
+			       bool execute, bool foreign)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return true;
+	/*
+	 * Do not enforce our key-permissions on a foreign vma.
+	 */
+	if (foreign || vma_is_foreign(vma))
+		return true;
+
+	return pkey_access_permitted(vma_pkey(vma), write, execute);
+}
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index 781532d7bc4d..f14a07c2fb90 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -195,6 +195,9 @@ long sys_subpage_prot(unsigned long addr, unsigned long len, u32 __user *map)
 	unsigned long next, limit;
 	int err;
 
+	if (radix_enabled())
+		return -ENOENT;
+
 	/* Check parameters */
 	if ((addr & ~PAGE_MASK) || (len & ~PAGE_MASK) ||
 	    addr >= mm->task_size || len >= mm->task_size ||
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 884f4b705b57..71d1b19ad1c0 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -23,6 +23,72 @@
 #define RIC_FLUSH_PWC 1
 #define RIC_FLUSH_ALL 2
 
+/*
+ * tlbiel instruction for radix, set invalidation
+ * i.e., r=1 and is=01 or is=10 or is=11
+ */
+static inline void tlbiel_radix_set_isa300(unsigned int set, unsigned int is,
+					unsigned int pid,
+					unsigned int ric, unsigned int prs)
+{
+	unsigned long rb;
+	unsigned long rs;
+	unsigned int r = 1; /* radix format */
+
+	rb = (set << PPC_BITLSHIFT(51)) | (is << PPC_BITLSHIFT(53));
+	rs = ((unsigned long)pid << PPC_BITLSHIFT(31));
+
+	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4)
+		     : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r)
+		     : "memory");
+}
+
+static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
+{
+	unsigned int set;
+
+	asm volatile("ptesync": : :"memory");
+
+	/*
+	 * Flush the first set of the TLB, and the entire Page Walk Cache
+	 * and partition table entries. Then flush the remaining sets of the
+	 * TLB.
+	 */
+	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 0);
+	for (set = 1; set < num_sets; set++)
+		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 0);
+
+	/* Do the same for process scoped entries. */
+	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 1);
+	for (set = 1; set < num_sets; set++)
+		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1);
+
+	asm volatile("ptesync": : :"memory");
+}
+
+void radix__tlbiel_all(unsigned int action)
+{
+	unsigned int is;
+
+	switch (action) {
+	case TLB_INVAL_SCOPE_GLOBAL:
+		is = 3;
+		break;
+	case TLB_INVAL_SCOPE_LPID:
+		is = 2;
+		break;
+	default:
+		BUG();
+	}
+
+	if (early_cpu_has_feature(CPU_FTR_ARCH_300))
+		tlbiel_all_isa300(POWER9_TLB_SETS_RADIX, is);
+	else
+		WARN(1, "%s called on pre-POWER9 CPU\n", __func__);
+
+	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+}
+
 static inline void __tlbiel_pid(unsigned long pid, int set,
 				unsigned long ric)
 {
@@ -600,14 +666,12 @@ void radix__flush_tlb_all(void)
 	 */
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(1), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 	/*
 	 * now flush host entires by passing PRS = 0 and LPID == 0
 	 */
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(0) : "memory");
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
-	trace_tlbie(0, 0, rb, 0, ric, prs, r);
 }
 
 void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index bfc4a0869609..15fe5f0c8665 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -388,7 +388,10 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end)
 
 {
-	flush_tlb_mm(vma->vm_mm);
+	if (end - start == PAGE_SIZE && !(start & ~PAGE_MASK))
+		flush_tlb_page(vma, start);
+	else
+		flush_tlb_mm(vma->vm_mm);
 }
 EXPORT_SYMBOL(flush_tlb_range);
 
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index f9941b3b5770..872d1f6dd11e 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -18,8 +18,6 @@
 
 #include "bpf_jit32.h"
 
-int bpf_jit_enable __read_mostly;
-
 static inline void bpf_flush_icache(void *start, void *end)
 {
 	smp_wmb();
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 46d74e81aff1..0a34b0cec7b7 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -21,8 +21,6 @@
 
 #include "bpf_jit64.h"
 
-int bpf_jit_enable __read_mostly;
-
 static void bpf_jit_fill_ill_insns(void *area, unsigned int size)
 {
 	memset32(area, BREAKPOINT_INSTRUCTION, size/4);
@@ -383,10 +381,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
 		case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
-			PPC_CMPWI(src_reg, 0);
-			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
 			if (BPF_OP(code) == BPF_MOD) {
 				PPC_DIVWU(b2p[TMP_REG_1], dst_reg, src_reg);
 				PPC_MULW(b2p[TMP_REG_1], src_reg,
@@ -397,10 +391,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			goto bpf_alu32_trunc;
 		case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
 		case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
-			PPC_CMPDI(src_reg, 0);
-			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
 			if (BPF_OP(code) == BPF_MOD) {
 				PPC_DIVD(b2p[TMP_REG_1], dst_reg, src_reg);
 				PPC_MULD(b2p[TMP_REG_1], src_reg,
@@ -763,7 +753,8 @@ emit_clear:
 			func = (u8 *) __bpf_call_base + imm;
 
 			/* Save skb pointer if we need to re-cache skb data */
-			if (bpf_helper_changes_pkt_data(func))
+			if ((ctx->seen & SEEN_SKB) &&
+			    bpf_helper_changes_pkt_data(func))
 				PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx));
 
 			bpf_jit_emit_func_call(image, ctx, (u64)func);
@@ -772,7 +763,8 @@ emit_clear:
 			PPC_MR(b2p[BPF_REG_0], 3);
 
 			/* refresh skb cache */
-			if (bpf_helper_changes_pkt_data(func)) {
+			if ((ctx->seen & SEEN_SKB) &&
+			    bpf_helper_changes_pkt_data(func)) {
 				/* reload skb pointer to r3 */
 				PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx));
 				bpf_jit_emit_skb_loads(image, ctx);
@@ -993,7 +985,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	struct bpf_prog *tmp_fp;
 	bool bpf_blinded = false;
 
-	if (!bpf_jit_enable)
+	if (!fp->jit_requested)
 		return org_fp;
 
 	tmp_fp = bpf_jit_blind_constants(org_fp);
diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c
index 3c39f05f0af3..6c0020d1c561 100644
--- a/arch/powerpc/perf/8xx-pmu.c
+++ b/arch/powerpc/perf/8xx-pmu.c
@@ -18,6 +18,7 @@
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/ptrace.h>
+#include <asm/code-patching.h>
 
 #define PERF_8xx_ID_CPU_CYCLES		1
 #define PERF_8xx_ID_HW_INSTRUCTIONS	2
@@ -30,8 +31,13 @@
 
 extern unsigned long itlb_miss_counter, dtlb_miss_counter;
 extern atomic_t instruction_counter;
+extern unsigned int itlb_miss_perf, dtlb_miss_perf;
+extern unsigned int itlb_miss_exit_1, itlb_miss_exit_2;
+extern unsigned int dtlb_miss_exit_1, dtlb_miss_exit_2, dtlb_miss_exit_3;
 
 static atomic_t insn_ctr_ref;
+static atomic_t itlb_miss_ref;
+static atomic_t dtlb_miss_ref;
 
 static s64 get_insn_ctr(void)
 {
@@ -96,9 +102,24 @@ static int mpc8xx_pmu_add(struct perf_event *event, int flags)
 		val = get_insn_ctr();
 		break;
 	case PERF_8xx_ID_ITLB_LOAD_MISS:
+		if (atomic_inc_return(&itlb_miss_ref) == 1) {
+			unsigned long target = (unsigned long)&itlb_miss_perf;
+
+			patch_branch(&itlb_miss_exit_1, target, 0);
+#ifndef CONFIG_PIN_TLB_TEXT
+			patch_branch(&itlb_miss_exit_2, target, 0);
+#endif
+		}
 		val = itlb_miss_counter;
 		break;
 	case PERF_8xx_ID_DTLB_LOAD_MISS:
+		if (atomic_inc_return(&dtlb_miss_ref) == 1) {
+			unsigned long target = (unsigned long)&dtlb_miss_perf;
+
+			patch_branch(&dtlb_miss_exit_1, target, 0);
+			patch_branch(&dtlb_miss_exit_2, target, 0);
+			patch_branch(&dtlb_miss_exit_3, target, 0);
+		}
 		val = dtlb_miss_counter;
 		break;
 	}
@@ -143,13 +164,36 @@ static void mpc8xx_pmu_read(struct perf_event *event)
 
 static void mpc8xx_pmu_del(struct perf_event *event, int flags)
 {
+	/* mfspr r10, SPRN_SPRG_SCRATCH0 */
+	unsigned int insn = PPC_INST_MFSPR | __PPC_RS(R10) |
+			    __PPC_SPR(SPRN_SPRG_SCRATCH0);
+
 	mpc8xx_pmu_read(event);
-	if (event_type(event) != PERF_8xx_ID_HW_INSTRUCTIONS)
-		return;
 
 	/* If it was the last user, stop counting to avoid useles overhead */
-	if (atomic_dec_return(&insn_ctr_ref) == 0)
-		mtspr(SPRN_ICTRL, 7);
+	switch (event_type(event)) {
+	case PERF_8xx_ID_CPU_CYCLES:
+		break;
+	case PERF_8xx_ID_HW_INSTRUCTIONS:
+		if (atomic_dec_return(&insn_ctr_ref) == 0)
+			mtspr(SPRN_ICTRL, 7);
+		break;
+	case PERF_8xx_ID_ITLB_LOAD_MISS:
+		if (atomic_dec_return(&itlb_miss_ref) == 0) {
+			patch_instruction(&itlb_miss_exit_1, insn);
+#ifndef CONFIG_PIN_TLB_TEXT
+			patch_instruction(&itlb_miss_exit_2, insn);
+#endif
+		}
+		break;
+	case PERF_8xx_ID_DTLB_LOAD_MISS:
+		if (atomic_dec_return(&dtlb_miss_ref) == 0) {
+			patch_instruction(&dtlb_miss_exit_1, insn);
+			patch_instruction(&dtlb_miss_exit_2, insn);
+			patch_instruction(&dtlb_miss_exit_3, insn);
+		}
+		break;
+	}
 }
 
 static struct pmu mpc8xx_pmu = {
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 225c9c86d7c0..57ebc655d2ac 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -15,7 +15,7 @@ obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o e6500-pmu.o
 
 obj-$(CONFIG_HV_PERF_CTRS) += hv-24x7.o hv-gpci.o hv-common.o
 
-obj-$(CONFIG_PPC_8xx_PERF_EVENT) += 8xx-pmu.o
+obj-$(CONFIG_PPC_8xx) += 8xx-pmu.o
 
 obj-$(CONFIG_PPC64)		+= $(obj64-y)
 obj-$(CONFIG_PPC32)		+= $(obj32-y)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 9e3da168d54c..f89bbd54ecec 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -322,7 +322,7 @@ static inline void perf_read_regs(struct pt_regs *regs)
  */
 static inline int perf_intr_is_nmi(struct pt_regs *regs)
 {
-	return !regs->softe;
+	return (regs->softe & IRQS_DISABLED);
 }
 
 /*
@@ -410,8 +410,12 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 	int ret;
 	__u64 target;
 
-	if (is_kernel_addr(addr))
-		return branch_target((unsigned int *)addr);
+	if (is_kernel_addr(addr)) {
+		if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
+			return 0;
+
+		return branch_target(&instr);
+	}
 
 	/* Userspace: need copy instruction here then translate it */
 	pagefault_disable();
@@ -1415,7 +1419,7 @@ static int collect_events(struct perf_event *group, int max_count,
 	int n = 0;
 	struct perf_event *event;
 
-	if (!is_software_event(group)) {
+	if (group->pmu->task_ctx_nr == perf_hw_context) {
 		if (n >= max_count)
 			return -1;
 		ctrs[n] = group;
@@ -1423,7 +1427,7 @@ static int collect_events(struct perf_event *group, int max_count,
 		events[n++] = group->hw.config;
 	}
 	list_for_each_entry(event, &group->sibling_list, group_entry) {
-		if (!is_software_event(event) &&
+		if (event->pmu->task_ctx_nr == perf_hw_context &&
 		    event->state != PERF_EVENT_STATE_OFF) {
 			if (n >= max_count)
 				return -1;
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 0ead3cd73caa..d7532e7b9ab5 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -40,7 +40,6 @@ static struct imc_pmu *core_imc_pmu;
 /* Thread IMC data structures and variables */
 
 static DEFINE_PER_CPU(u64 *, thread_imc_mem);
-static struct imc_pmu *thread_imc_pmu;
 static int thread_imc_mem_size;
 
 struct imc_pmu *imc_event_to_pmu(struct perf_event *event)
@@ -117,17 +116,13 @@ static struct attribute *device_str_attr_create(const char *name, const char *st
 	return &attr->attr.attr;
 }
 
-struct imc_events *imc_parse_event(struct device_node *np, const char *scale,
-				  const char *unit, const char *prefix, u32 base)
+static int imc_parse_event(struct device_node *np, const char *scale,
+				  const char *unit, const char *prefix,
+				  u32 base, struct imc_events *event)
 {
-	struct imc_events *event;
 	const char *s;
 	u32 reg;
 
-	event = kzalloc(sizeof(struct imc_events), GFP_KERNEL);
-	if (!event)
-		return NULL;
-
 	if (of_property_read_u32(np, "reg", &reg))
 		goto error;
 	/* Add the base_reg value to the "reg" */
@@ -158,14 +153,32 @@ struct imc_events *imc_parse_event(struct device_node *np, const char *scale,
 			goto error;
 	}
 
-	return event;
+	return 0;
 error:
 	kfree(event->unit);
 	kfree(event->scale);
 	kfree(event->name);
-	kfree(event);
+	return -EINVAL;
+}
+
+/*
+ * imc_free_events: Function to cleanup the events list, having
+ * 		    "nr_entries".
+ */
+static void imc_free_events(struct imc_events *events, int nr_entries)
+{
+	int i;
+
+	/* Nothing to clean, return */
+	if (!events)
+		return;
+	for (i = 0; i < nr_entries; i++) {
+		kfree(events[i].unit);
+		kfree(events[i].scale);
+		kfree(events[i].name);
+	}
 
-	return NULL;
+	kfree(events);
 }
 
 /*
@@ -177,9 +190,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
 	struct attribute_group *attr_group;
 	struct attribute **attrs, *dev_str;
 	struct device_node *np, *pmu_events;
-	struct imc_events *ev;
 	u32 handle, base_reg;
-	int i=0, j=0, ct;
+	int i = 0, j = 0, ct, ret;
 	const char *prefix, *g_scale, *g_unit;
 	const char *ev_val_str, *ev_scale_str, *ev_unit_str;
 
@@ -217,15 +229,17 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
 	ct = 0;
 	/* Parse the events and update the struct */
 	for_each_child_of_node(pmu_events, np) {
-		ev = imc_parse_event(np, g_scale, g_unit, prefix, base_reg);
-		if (ev)
-			pmu->events[ct++] = ev;
+		ret = imc_parse_event(np, g_scale, g_unit, prefix, base_reg, &pmu->events[ct]);
+		if (!ret)
+			ct++;
 	}
 
 	/* Allocate memory for attribute group */
 	attr_group = kzalloc(sizeof(*attr_group), GFP_KERNEL);
-	if (!attr_group)
+	if (!attr_group) {
+		imc_free_events(pmu->events, ct);
 		return -ENOMEM;
+	}
 
 	/*
 	 * Allocate memory for attributes.
@@ -238,31 +252,31 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
 	attrs = kcalloc(((ct * 3) + 1), sizeof(struct attribute *), GFP_KERNEL);
 	if (!attrs) {
 		kfree(attr_group);
-		kfree(pmu->events);
+		imc_free_events(pmu->events, ct);
 		return -ENOMEM;
 	}
 
 	attr_group->name = "events";
 	attr_group->attrs = attrs;
 	do {
-		ev_val_str = kasprintf(GFP_KERNEL, "event=0x%x", pmu->events[i]->value);
-		dev_str = device_str_attr_create(pmu->events[i]->name, ev_val_str);
+		ev_val_str = kasprintf(GFP_KERNEL, "event=0x%x", pmu->events[i].value);
+		dev_str = device_str_attr_create(pmu->events[i].name, ev_val_str);
 		if (!dev_str)
 			continue;
 
 		attrs[j++] = dev_str;
-		if (pmu->events[i]->scale) {
-			ev_scale_str = kasprintf(GFP_KERNEL, "%s.scale",pmu->events[i]->name);
-			dev_str = device_str_attr_create(ev_scale_str, pmu->events[i]->scale);
+		if (pmu->events[i].scale) {
+			ev_scale_str = kasprintf(GFP_KERNEL, "%s.scale", pmu->events[i].name);
+			dev_str = device_str_attr_create(ev_scale_str, pmu->events[i].scale);
 			if (!dev_str)
 				continue;
 
 			attrs[j++] = dev_str;
 		}
 
-		if (pmu->events[i]->unit) {
-			ev_unit_str = kasprintf(GFP_KERNEL, "%s.unit",pmu->events[i]->name);
-			dev_str = device_str_attr_create(ev_unit_str, pmu->events[i]->unit);
+		if (pmu->events[i].unit) {
+			ev_unit_str = kasprintf(GFP_KERNEL, "%s.unit", pmu->events[i].name);
+			dev_str = device_str_attr_create(ev_unit_str, pmu->events[i].unit);
 			if (!dev_str)
 				continue;
 
@@ -273,7 +287,6 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
 	/* Save the event attribute */
 	pmu->attr_groups[IMC_EVENT_ATTR] = attr_group;
 
-	kfree(pmu->events);
 	return 0;
 }
 
@@ -310,6 +323,19 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu)
 		return 0;
 
 	/*
+	 * Check whether nest_imc is registered. We could end up here if the
+	 * cpuhotplug callback registration fails. i.e, callback invokes the
+	 * offline path for all successfully registered nodes. At this stage,
+	 * nest_imc pmu will not be registered and we should return here.
+	 *
+	 * We return with a zero since this is not an offline failure. And
+	 * cpuhp_setup_state() returns the actual failure reason to the caller,
+	 * which in turn will call the cleanup routine.
+	 */
+	if (!nest_pmus)
+		return 0;
+
+	/*
 	 * Now that this cpu is one of the designated,
 	 * find a next cpu a) which is online and b) in same chip.
 	 */
@@ -598,7 +624,8 @@ static int ppc_core_imc_cpu_online(unsigned int cpu)
 
 static int ppc_core_imc_cpu_offline(unsigned int cpu)
 {
-	unsigned int ncpu, core_id;
+	unsigned int core_id;
+	int ncpu;
 	struct imc_pmu_ref *ref;
 
 	/*
@@ -1158,6 +1185,15 @@ static void cleanup_all_thread_imc_memory(void)
 	}
 }
 
+/* Function to free the attr_groups which are dynamically allocated */
+static void imc_common_mem_free(struct imc_pmu *pmu_ptr)
+{
+	if (pmu_ptr->attr_groups[IMC_EVENT_ATTR])
+		kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
+	kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
+	kfree(pmu_ptr);
+}
+
 /*
  * Common function to unregister cpu hotplug callback and
  * free the memory.
@@ -1171,6 +1207,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 		if (nest_pmus == 1) {
 			cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE);
 			kfree(nest_imc_refc);
+			kfree(per_nest_pmu_arr);
 		}
 
 		if (nest_pmus > 0)
@@ -1189,14 +1226,6 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 		cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE);
 		cleanup_all_thread_imc_memory();
 	}
-
-	/* Only free the attr_groups which are dynamically allocated  */
-	if (pmu_ptr->attr_groups[IMC_EVENT_ATTR])
-		kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
-	kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
-	kfree(pmu_ptr);
-	kfree(per_nest_pmu_arr);
-	return;
 }
 
 
@@ -1245,8 +1274,10 @@ static int imc_mem_init(struct imc_pmu *pmu_ptr, struct device_node *parent,
 		core_imc_refc = kcalloc(nr_cores, sizeof(struct imc_pmu_ref),
 								GFP_KERNEL);
 
-		if (!core_imc_refc)
+		if (!core_imc_refc) {
+			kfree(pmu_ptr->mem_info);
 			return -ENOMEM;
+		}
 
 		core_imc_pmu = pmu_ptr;
 		break;
@@ -1259,11 +1290,12 @@ static int imc_mem_init(struct imc_pmu *pmu_ptr, struct device_node *parent,
 		thread_imc_mem_size = pmu_ptr->counter_mem_size;
 		for_each_online_cpu(cpu) {
 			res = thread_imc_mem_alloc(cpu, pmu_ptr->counter_mem_size);
-			if (res)
+			if (res) {
+				cleanup_all_thread_imc_memory();
 				return res;
+			}
 		}
 
-		thread_imc_pmu = pmu_ptr;
 		break;
 	default:
 		return -EINVAL;
@@ -1287,8 +1319,10 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 	int ret;
 
 	ret = imc_mem_init(pmu_ptr, parent, pmu_idx);
-	if (ret)
-		goto err_free;
+	if (ret) {
+		imc_common_mem_free(pmu_ptr);
+		return ret;
+	}
 
 	switch (pmu_ptr->domain) {
 	case IMC_DOMAIN_NEST:
@@ -1309,6 +1343,8 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 			ret = nest_pmu_cpumask_init();
 			if (ret) {
 				mutex_unlock(&nest_init_lock);
+				kfree(nest_imc_refc);
+				kfree(per_nest_pmu_arr);
 				goto err_free;
 			}
 		}
@@ -1353,6 +1389,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 	return 0;
 
 err_free:
+	imc_common_mem_free(pmu_ptr);
 	imc_common_cpuhp_mem_free(pmu_ptr);
 	return ret;
 }
diff --git a/arch/powerpc/platforms/44x/fsp2.c b/arch/powerpc/platforms/44x/fsp2.c
index 92e98048404f..04f0c73a9b4f 100644
--- a/arch/powerpc/platforms/44x/fsp2.c
+++ b/arch/powerpc/platforms/44x/fsp2.c
@@ -27,6 +27,17 @@
 #include <asm/time.h>
 #include <asm/uic.h>
 #include <asm/ppc4xx.h>
+#include <asm/dcr.h>
+#include <linux/interrupt.h>
+#include <linux/of_irq.h>
+#include "fsp2.h"
+
+#define FSP2_BUS_ERR	"ibm,bus-error-irq"
+#define FSP2_CMU_ERR	"ibm,cmu-error-irq"
+#define FSP2_CONF_ERR	"ibm,conf-error-irq"
+#define FSP2_OPBD_ERR	"ibm,opbd-error-irq"
+#define FSP2_MCUE	"ibm,mc-ue-irq"
+#define FSP2_RST_WRN	"ibm,reset-warning-irq"
 
 static __initdata struct of_device_id fsp2_of_bus[] = {
 	{ .compatible = "ibm,plb4", },
@@ -35,6 +46,194 @@ static __initdata struct of_device_id fsp2_of_bus[] = {
 	{},
 };
 
+static void l2regs(void)
+{
+	pr_err("L2 Controller:\n");
+	pr_err("MCK:      0x%08x\n", mfl2(L2MCK));
+	pr_err("INT:      0x%08x\n", mfl2(L2INT));
+	pr_err("PLBSTAT0: 0x%08x\n", mfl2(L2PLBSTAT0));
+	pr_err("PLBSTAT1: 0x%08x\n", mfl2(L2PLBSTAT1));
+	pr_err("ARRSTAT0: 0x%08x\n", mfl2(L2ARRSTAT0));
+	pr_err("ARRSTAT1: 0x%08x\n", mfl2(L2ARRSTAT1));
+	pr_err("ARRSTAT2: 0x%08x\n", mfl2(L2ARRSTAT2));
+	pr_err("CPUSTAT:  0x%08x\n", mfl2(L2CPUSTAT));
+	pr_err("RACSTAT0: 0x%08x\n", mfl2(L2RACSTAT0));
+	pr_err("WACSTAT0: 0x%08x\n", mfl2(L2WACSTAT0));
+	pr_err("WACSTAT1: 0x%08x\n", mfl2(L2WACSTAT1));
+	pr_err("WACSTAT2: 0x%08x\n", mfl2(L2WACSTAT2));
+	pr_err("WDFSTAT:  0x%08x\n", mfl2(L2WDFSTAT));
+	pr_err("LOG0:     0x%08x\n", mfl2(L2LOG0));
+	pr_err("LOG1:     0x%08x\n", mfl2(L2LOG1));
+	pr_err("LOG2:     0x%08x\n", mfl2(L2LOG2));
+	pr_err("LOG3:     0x%08x\n", mfl2(L2LOG3));
+	pr_err("LOG4:     0x%08x\n", mfl2(L2LOG4));
+	pr_err("LOG5:     0x%08x\n", mfl2(L2LOG5));
+}
+
+static void show_plbopb_regs(u32 base, int num)
+{
+	pr_err("\nPLBOPB Bridge %d:\n", num);
+	pr_err("GESR0: 0x%08x\n", mfdcr(base + PLB4OPB_GESR0));
+	pr_err("GESR1: 0x%08x\n", mfdcr(base + PLB4OPB_GESR1));
+	pr_err("GESR2: 0x%08x\n", mfdcr(base + PLB4OPB_GESR2));
+	pr_err("GEARU: 0x%08x\n", mfdcr(base + PLB4OPB_GEARU));
+	pr_err("GEAR:  0x%08x\n", mfdcr(base + PLB4OPB_GEAR));
+}
+
+static irqreturn_t bus_err_handler(int irq, void *data)
+{
+	pr_err("Bus Error\n");
+
+	l2regs();
+
+	pr_err("\nPLB6 Controller:\n");
+	pr_err("BC_SHD: 0x%08x\n", mfdcr(DCRN_PLB6_SHD));
+	pr_err("BC_ERR: 0x%08x\n", mfdcr(DCRN_PLB6_ERR));
+
+	pr_err("\nPLB6-to-PLB4 Bridge:\n");
+	pr_err("ESR:  0x%08x\n", mfdcr(DCRN_PLB6PLB4_ESR));
+	pr_err("EARH: 0x%08x\n", mfdcr(DCRN_PLB6PLB4_EARH));
+	pr_err("EARL: 0x%08x\n", mfdcr(DCRN_PLB6PLB4_EARL));
+
+	pr_err("\nPLB4-to-PLB6 Bridge:\n");
+	pr_err("ESR:  0x%08x\n", mfdcr(DCRN_PLB4PLB6_ESR));
+	pr_err("EARH: 0x%08x\n", mfdcr(DCRN_PLB4PLB6_EARH));
+	pr_err("EARL: 0x%08x\n", mfdcr(DCRN_PLB4PLB6_EARL));
+
+	pr_err("\nPLB6-to-MCIF Bridge:\n");
+	pr_err("BESR0: 0x%08x\n", mfdcr(DCRN_PLB6MCIF_BESR0));
+	pr_err("BESR1: 0x%08x\n", mfdcr(DCRN_PLB6MCIF_BESR1));
+	pr_err("BEARH: 0x%08x\n", mfdcr(DCRN_PLB6MCIF_BEARH));
+	pr_err("BEARL: 0x%08x\n", mfdcr(DCRN_PLB6MCIF_BEARL));
+
+	pr_err("\nPLB4 Arbiter:\n");
+	pr_err("P0ESRH 0x%08x\n", mfdcr(DCRN_PLB4_P0ESRH));
+	pr_err("P0ESRL 0x%08x\n", mfdcr(DCRN_PLB4_P0ESRL));
+	pr_err("P0EARH 0x%08x\n", mfdcr(DCRN_PLB4_P0EARH));
+	pr_err("P0EARH 0x%08x\n", mfdcr(DCRN_PLB4_P0EARH));
+	pr_err("P1ESRH 0x%08x\n", mfdcr(DCRN_PLB4_P1ESRH));
+	pr_err("P1ESRL 0x%08x\n", mfdcr(DCRN_PLB4_P1ESRL));
+	pr_err("P1EARH 0x%08x\n", mfdcr(DCRN_PLB4_P1EARH));
+	pr_err("P1EARH 0x%08x\n", mfdcr(DCRN_PLB4_P1EARH));
+
+	show_plbopb_regs(DCRN_PLB4OPB0_BASE, 0);
+	show_plbopb_regs(DCRN_PLB4OPB1_BASE, 1);
+	show_plbopb_regs(DCRN_PLB4OPB2_BASE, 2);
+	show_plbopb_regs(DCRN_PLB4OPB3_BASE, 3);
+
+	pr_err("\nPLB4-to-AHB Bridge:\n");
+	pr_err("ESR:   0x%08x\n", mfdcr(DCRN_PLB4AHB_ESR));
+	pr_err("SEUAR: 0x%08x\n", mfdcr(DCRN_PLB4AHB_SEUAR));
+	pr_err("SELAR: 0x%08x\n", mfdcr(DCRN_PLB4AHB_SELAR));
+
+	pr_err("\nAHB-to-PLB4 Bridge:\n");
+	pr_err("\nESR: 0x%08x\n", mfdcr(DCRN_AHBPLB4_ESR));
+	pr_err("\nEAR: 0x%08x\n", mfdcr(DCRN_AHBPLB4_EAR));
+	panic("Bus Error\n");
+}
+
+static irqreturn_t cmu_err_handler(int irq, void *data) {
+	pr_err("CMU Error\n");
+	pr_err("FIR0: 0x%08x\n", mfcmu(CMUN_FIR0));
+	panic("CMU Error\n");
+}
+
+static irqreturn_t conf_err_handler(int irq, void *data) {
+	pr_err("Configuration Logic Error\n");
+	pr_err("CONF_FIR: 0x%08x\n", mfdcr(DCRN_CONF_FIR_RWC));
+	pr_err("RPERR0:   0x%08x\n", mfdcr(DCRN_CONF_RPERR0));
+	pr_err("RPERR1:   0x%08x\n", mfdcr(DCRN_CONF_RPERR1));
+	panic("Configuration Logic Error\n");
+}
+
+static irqreturn_t opbd_err_handler(int irq, void *data) {
+	panic("OPBD Error\n");
+}
+
+static irqreturn_t mcue_handler(int irq, void *data) {
+	pr_err("DDR: Uncorrectable Error\n");
+	pr_err("MCSTAT:            0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_MCSTAT));
+	pr_err("MCOPT1:            0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_MCOPT1));
+	pr_err("MCOPT2:            0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_MCOPT2));
+	pr_err("PHYSTAT:           0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_PHYSTAT));
+	pr_err("CFGR0:             0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_CFGR0));
+	pr_err("CFGR1:             0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_CFGR1));
+	pr_err("CFGR2:             0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_CFGR2));
+	pr_err("CFGR3:             0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_CFGR3));
+	pr_err("SCRUB_CNTL:        0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_SCRUB_CNTL));
+	pr_err("ECCERR_PORT0:      0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_ECCERR_PORT0));
+	pr_err("ECCERR_ADDR_PORT0: 0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_ECCERR_ADDR_PORT0));
+	pr_err("ECCERR_CNT_PORT0:  0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_ECCERR_COUNT_PORT0));
+	pr_err("ECC_CHECK_PORT0:   0x%08x\n",
+		mfdcr(DCRN_DDR34_BASE + DCRN_DDR34_ECC_CHECK_PORT0));
+	pr_err("MCER0:            0x%08x\n",
+		mfdcr(DCRN_CW_BASE + DCRN_CW_MCER0));
+	pr_err("MCER1:            0x%08x\n",
+		mfdcr(DCRN_CW_BASE + DCRN_CW_MCER1));
+	pr_err("BESR:             0x%08x\n",
+		mfdcr(DCRN_PLB6MCIF_BESR0));
+	pr_err("BEARL:            0x%08x\n",
+		mfdcr(DCRN_PLB6MCIF_BEARL));
+	pr_err("BEARH:            0x%08x\n",
+		mfdcr(DCRN_PLB6MCIF_BEARH));
+	panic("DDR: Uncorrectable Error\n");
+}
+
+static irqreturn_t rst_wrn_handler(int irq, void *data) {
+	u32 crcs = mfcmu(CMUN_CRCS);
+	switch (crcs & CRCS_STAT_MASK) {
+	case CRCS_STAT_CHIP_RST_B:
+		panic("Received chassis-initiated reset request");
+	default:
+		panic("Unknown external reset: CRCS=0x%x", crcs);
+	}
+}
+
+static void node_irq_request(const char *compat, irq_handler_t errirq_handler)
+{
+	struct device_node *np;
+	unsigned int irq;
+	int32_t rc;
+
+	for_each_compatible_node(np, NULL, compat) {
+		irq = irq_of_parse_and_map(np, 0);
+		if (irq == NO_IRQ) {
+			pr_err("device tree node %s is missing a interrupt",
+			      np->name);
+			return;
+		}
+
+		rc = request_irq(irq, errirq_handler, 0, np->name, np);
+		if (rc) {
+			pr_err("fsp_of_probe: request_irq failed: np=%s rc=%d",
+			      np->full_name, rc);
+			return;
+		}
+	}
+}
+
+static void critical_irq_setup(void)
+{
+	node_irq_request(FSP2_CMU_ERR, cmu_err_handler);
+	node_irq_request(FSP2_BUS_ERR, bus_err_handler);
+	node_irq_request(FSP2_CONF_ERR, conf_err_handler);
+	node_irq_request(FSP2_OPBD_ERR, opbd_err_handler);
+	node_irq_request(FSP2_MCUE, mcue_handler);
+	node_irq_request(FSP2_RST_WRN, rst_wrn_handler);
+}
+
 static int __init fsp2_device_probe(void)
 {
 	of_platform_bus_probe(NULL, fsp2_of_bus, NULL);
@@ -44,18 +243,76 @@ machine_device_initcall(fsp2, fsp2_device_probe);
 
 static int __init fsp2_probe(void)
 {
+	u32 val;
 	unsigned long root = of_get_flat_dt_root();
 
 	if (!of_flat_dt_is_compatible(root, "ibm,fsp2"))
 		return 0;
+
+	/* Clear BC_ERR and mask snoopable request plb errors. */
+	val = mfdcr(DCRN_PLB6_CR0);
+	val |= 0x20000000;
+	mtdcr(DCRN_PLB6_BASE, val);
+	mtdcr(DCRN_PLB6_HD, 0xffff0000);
+	mtdcr(DCRN_PLB6_SHD, 0xffff0000);
+
+	/* TVSENSE reset is blocked (clock gated) by the POR default of the TVS
+	 * sleep config bit. As a consequence, TVSENSE will provide erratic
+	 * sensor values, which may result in spurious (parity) errors
+	 * recorded in the CMU FIR and leading to erroneous interrupt requests
+	 * once the CMU interrupt is unmasked.
+	 */
+
+	/* 1. set TVS1[UNDOZE] */
+	val = mfcmu(CMUN_TVS1);
+	val |= 0x4;
+	mtcmu(CMUN_TVS1, val);
+
+	/* 2. clear FIR[TVS] and FIR[TVSPAR] */
+	val = mfcmu(CMUN_FIR0);
+	val |= 0x30000000;
+	mtcmu(CMUN_FIR0, val);
+
+	/* L2 machine checks */
+	mtl2(L2PLBMCKEN0, 0xffffffff);
+	mtl2(L2PLBMCKEN1, 0x0000ffff);
+	mtl2(L2ARRMCKEN0, 0xffffffff);
+	mtl2(L2ARRMCKEN1, 0xffffffff);
+	mtl2(L2ARRMCKEN2, 0xfffff000);
+	mtl2(L2CPUMCKEN,  0xffffffff);
+	mtl2(L2RACMCKEN0, 0xffffffff);
+	mtl2(L2WACMCKEN0, 0xffffffff);
+	mtl2(L2WACMCKEN1, 0xffffffff);
+	mtl2(L2WACMCKEN2, 0xffffffff);
+	mtl2(L2WDFMCKEN,  0xffffffff);
+
+	/* L2 interrupts */
+	mtl2(L2PLBINTEN1, 0xffff0000);
+
+	/*
+	 * At a global level, enable all L2 machine checks and interrupts
+	 * reported by the L2 subsystems, except for the external machine check
+	 * input (UIC0.1).
+	 */
+	mtl2(L2MCKEN, 0x000007ff);
+	mtl2(L2INTEN, 0x000004ff);
+
+	/* Enable FSP-2 configuration logic parity errors */
+	mtdcr(DCRN_CONF_EIR_RS, 0x80000000);
 	return 1;
 }
 
+static void __init fsp2_irq_init(void)
+{
+	uic_init_tree();
+	critical_irq_setup();
+}
+
 define_machine(fsp2) {
 	.name			= "FSP-2",
 	.probe			= fsp2_probe,
 	.progress		= udbg_progress,
-	.init_IRQ		= uic_init_tree,
+	.init_IRQ		= fsp2_irq_init,
 	.get_irq		= uic_get_irq,
 	.restart		= ppc4xx_reset_system,
 	.calibrate_decr		= generic_calibrate_decr,
diff --git a/arch/powerpc/platforms/44x/fsp2.h b/arch/powerpc/platforms/44x/fsp2.h
new file mode 100644
index 000000000000..9e1d52754c8b
--- /dev/null
+++ b/arch/powerpc/platforms/44x/fsp2.h
@@ -0,0 +1,272 @@
+#ifndef _ASM_POWERPC_FSP_DCR_H_
+#define _ASM_POWERPC_FSP_DCR_H_
+#ifdef __KERNEL__
+#include <asm/dcr.h>
+
+#define DCRN_CMU_ADDR		0x00C	/* Chip management unic addr */
+#define DCRN_CMU_DATA		0x00D	/* Chip management unic data */
+
+/* PLB4 Arbiter */
+#define DCRN_PLB4_PCBI		0x010	/* PLB Crossbar ID/Rev Register */
+#define DCRN_PLB4_P0ACR		0x011	/* PLB0 Arbiter Control Register */
+#define DCRN_PLB4_P0ESRL	0x012	/* PLB0 Error Status Register Low */
+#define DCRN_PLB4_P0ESRH	0x013	/* PLB0 Error Status Register High */
+#define DCRN_PLB4_P0EARL	0x014	/* PLB0 Error Address Register Low */
+#define DCRN_PLB4_P0EARH	0x015	/* PLB0 Error Address Register High */
+#define DCRN_PLB4_P0ESRLS	0x016	/* PLB0 Error Status Register Low Set*/
+#define DCRN_PLB4_P0ESRHS	0x017	/* PLB0 Error Status Register High */
+#define DCRN_PLB4_PCBC		0x018	/* PLB Crossbar Control Register */
+#define DCRN_PLB4_P1ACR		0x019	/* PLB1 Arbiter Control Register */
+#define DCRN_PLB4_P1ESRL	0x01A	/* PLB1 Error Status Register Low */
+#define DCRN_PLB4_P1ESRH	0x01B	/* PLB1 Error Status Register High */
+#define DCRN_PLB4_P1EARL	0x01C	/* PLB1 Error Address Register Low */
+#define DCRN_PLB4_P1EARH	0x01D	/* PLB1 Error Address Register High */
+#define DCRN_PLB4_P1ESRLS	0x01E	/* PLB1 Error Status Register Low Set*/
+#define DCRN_PLB4_P1ESRHS	0x01F	/*PLB1 Error Status Register High Set*/
+
+/* PLB4/OPB bridge 0, 1, 2, 3 */
+#define DCRN_PLB4OPB0_BASE	0x020
+#define DCRN_PLB4OPB1_BASE	0x030
+#define DCRN_PLB4OPB2_BASE	0x040
+#define DCRN_PLB4OPB3_BASE	0x050
+
+#define PLB4OPB_GESR0		0x0	/* Error status 0: Master Dev 0-3 */
+#define PLB4OPB_GEAR		0x2	/* Error Address Register */
+#define PLB4OPB_GEARU		0x3	/* Error Upper Address Register */
+#define PLB4OPB_GESR1		0x4	/* Error Status 1: Master Dev 4-7 */
+#define PLB4OPB_GESR2		0xC	/* Error Status 2: Master Dev 8-11 */
+
+/* PLB4-to-AHB Bridge */
+#define DCRN_PLB4AHB_BASE	0x400
+#define DCRN_PLB4AHB_SEUAR	(DCRN_PLB4AHB_BASE + 1)
+#define DCRN_PLB4AHB_SELAR	(DCRN_PLB4AHB_BASE + 2)
+#define DCRN_PLB4AHB_ESR	(DCRN_PLB4AHB_BASE + 3)
+#define DCRN_AHBPLB4_ESR	(DCRN_PLB4AHB_BASE + 8)
+#define DCRN_AHBPLB4_EAR	(DCRN_PLB4AHB_BASE + 9)
+
+/* PLB6 Controller */
+#define DCRN_PLB6_BASE		0x11111300
+#define DCRN_PLB6_CR0		(DCRN_PLB6_BASE)
+#define DCRN_PLB6_ERR		(DCRN_PLB6_BASE + 0x0B)
+#define DCRN_PLB6_HD		(DCRN_PLB6_BASE + 0x0E)
+#define DCRN_PLB6_SHD		(DCRN_PLB6_BASE + 0x10)
+
+/* PLB4-to-PLB6 Bridge */
+#define DCRN_PLB4PLB6_BASE	0x11111320
+#define DCRN_PLB4PLB6_ESR	(DCRN_PLB4PLB6_BASE + 1)
+#define DCRN_PLB4PLB6_EARH	(DCRN_PLB4PLB6_BASE + 3)
+#define DCRN_PLB4PLB6_EARL	(DCRN_PLB4PLB6_BASE + 4)
+
+/* PLB6-to-PLB4 Bridge */
+#define DCRN_PLB6PLB4_BASE	0x11111350
+#define DCRN_PLB6PLB4_ESR	(DCRN_PLB6PLB4_BASE + 1)
+#define DCRN_PLB6PLB4_EARH	(DCRN_PLB6PLB4_BASE + 3)
+#define DCRN_PLB6PLB4_EARL	(DCRN_PLB6PLB4_BASE + 4)
+
+/* PLB6-to-MCIF Bridge */
+#define DCRN_PLB6MCIF_BASE	0x11111380
+#define DCRN_PLB6MCIF_BESR0	(DCRN_PLB6MCIF_BASE + 0)
+#define DCRN_PLB6MCIF_BESR1	(DCRN_PLB6MCIF_BASE + 1)
+#define DCRN_PLB6MCIF_BEARL	(DCRN_PLB6MCIF_BASE + 2)
+#define DCRN_PLB6MCIF_BEARH	(DCRN_PLB6MCIF_BASE + 3)
+
+/* Configuration Logic Registers */
+#define DCRN_CONF_BASE		0x11111400
+#define DCRN_CONF_FIR_RWC	(DCRN_CONF_BASE + 0x3A)
+#define DCRN_CONF_EIR_RS	(DCRN_CONF_BASE + 0x3E)
+#define DCRN_CONF_RPERR0	(DCRN_CONF_BASE + 0x4D)
+#define DCRN_CONF_RPERR1	(DCRN_CONF_BASE + 0x4E)
+
+#define DCRN_L2CDCRAI		0x11111100
+#define DCRN_L2CDCRDI		0x11111104
+/* L2 indirect addresses */
+#define L2MCK		0x120
+#define L2MCKEN		0x130
+#define L2INT		0x150
+#define L2INTEN		0x160
+#define L2LOG0		0x180
+#define L2LOG1		0x184
+#define L2LOG2		0x188
+#define L2LOG3		0x18C
+#define L2LOG4		0x190
+#define L2LOG5		0x194
+#define L2PLBSTAT0	0x300
+#define L2PLBSTAT1	0x304
+#define L2PLBMCKEN0	0x330
+#define L2PLBMCKEN1	0x334
+#define L2PLBINTEN0	0x360
+#define L2PLBINTEN1	0x364
+#define L2ARRSTAT0	0x500
+#define L2ARRSTAT1	0x504
+#define L2ARRSTAT2	0x508
+#define L2ARRMCKEN0	0x530
+#define L2ARRMCKEN1	0x534
+#define L2ARRMCKEN2	0x538
+#define L2ARRINTEN0	0x560
+#define L2ARRINTEN1	0x564
+#define L2ARRINTEN2	0x568
+#define L2CPUSTAT	0x700
+#define L2CPUMCKEN	0x730
+#define L2CPUINTEN	0x760
+#define L2RACSTAT0	0x900
+#define L2RACMCKEN0	0x930
+#define L2RACINTEN0	0x960
+#define L2WACSTAT0	0xD00
+#define L2WACSTAT1	0xD04
+#define L2WACSTAT2	0xD08
+#define L2WACMCKEN0	0xD30
+#define L2WACMCKEN1	0xD34
+#define L2WACMCKEN2	0xD38
+#define L2WACINTEN0	0xD60
+#define L2WACINTEN1	0xD64
+#define L2WACINTEN2	0xD68
+#define L2WDFSTAT	0xF00
+#define L2WDFMCKEN	0xF30
+#define L2WDFINTEN	0xF60
+
+/* DDR3/4 Memory Controller */
+#define DCRN_DDR34_BASE			0x11120000
+#define DCRN_DDR34_MCSTAT		0x10
+#define DCRN_DDR34_MCOPT1		0x20
+#define DCRN_DDR34_MCOPT2		0x21
+#define DCRN_DDR34_PHYSTAT		0x32
+#define DCRN_DDR34_CFGR0		0x40
+#define DCRN_DDR34_CFGR1		0x41
+#define DCRN_DDR34_CFGR2		0x42
+#define DCRN_DDR34_CFGR3		0x43
+#define DCRN_DDR34_SCRUB_CNTL		0xAA
+#define DCRN_DDR34_SCRUB_INT		0xAB
+#define DCRN_DDR34_SCRUB_START_ADDR	0xB0
+#define DCRN_DDR34_SCRUB_END_ADDR	0xD0
+#define DCRN_DDR34_ECCERR_ADDR_PORT0	0xE0
+#define DCRN_DDR34_ECCERR_ADDR_PORT1	0xE1
+#define DCRN_DDR34_ECCERR_ADDR_PORT2	0xE2
+#define DCRN_DDR34_ECCERR_ADDR_PORT3	0xE3
+#define DCRN_DDR34_ECCERR_COUNT_PORT0	0xE4
+#define DCRN_DDR34_ECCERR_COUNT_PORT1	0xE5
+#define DCRN_DDR34_ECCERR_COUNT_PORT2	0xE6
+#define DCRN_DDR34_ECCERR_COUNT_PORT3	0xE7
+#define DCRN_DDR34_ECCERR_PORT0		0xF0
+#define DCRN_DDR34_ECCERR_PORT1		0xF2
+#define DCRN_DDR34_ECCERR_PORT2		0xF4
+#define DCRN_DDR34_ECCERR_PORT3		0xF6
+#define DCRN_DDR34_ECC_CHECK_PORT0	0xF8
+#define DCRN_DDR34_ECC_CHECK_PORT1	0xF9
+#define DCRN_DDR34_ECC_CHECK_PORT2	0xF9
+#define DCRN_DDR34_ECC_CHECK_PORT3	0xFB
+
+#define DDR34_SCRUB_CNTL_STOP		0x00000000
+#define DDR34_SCRUB_CNTL_SCRUB		0x80000000
+#define DDR34_SCRUB_CNTL_UE_STOP	0x20000000
+#define DDR34_SCRUB_CNTL_CE_STOP	0x10000000
+#define DDR34_SCRUB_CNTL_RANK_EN	0x00008000
+
+/* PLB-Attached DDR3/4 Core Wrapper */
+#define DCRN_CW_BASE			0x11111800
+#define DCRN_CW_MCER0			0x00
+#define DCRN_CW_MCER1			0x01
+#define DCRN_CW_MCER_AND0		0x02
+#define DCRN_CW_MCER_AND1		0x03
+#define DCRN_CW_MCER_OR0		0x04
+#define DCRN_CW_MCER_OR1		0x05
+#define DCRN_CW_MCER_MASK0		0x06
+#define DCRN_CW_MCER_MASK1		0x07
+#define DCRN_CW_MCER_MASK_AND0		0x08
+#define DCRN_CW_MCER_MASK_AND1		0x09
+#define DCRN_CW_MCER_MASK_OR0		0x0A
+#define DCRN_CW_MCER_MASK_OR1		0x0B
+#define DCRN_CW_MCER_ACTION0		0x0C
+#define DCRN_CW_MCER_ACTION1		0x0D
+#define DCRN_CW_MCER_WOF0		0x0E
+#define DCRN_CW_MCER_WOF1		0x0F
+#define DCRN_CW_LFIR			0x10
+#define DCRN_CW_LFIR_AND		0x11
+#define DCRN_CW_LFIR_OR			0x12
+#define DCRN_CW_LFIR_MASK		0x13
+#define DCRN_CW_LFIR_MASK_AND		0x14
+#define DCRN_CW_LFIR_MASK_OR		0x15
+
+#define CW_MCER0_MEM_CE			0x00020000
+/* CMU addresses */
+#define CMUN_CRCS		0x00 /* Chip Reset Control/Status */
+#define CMUN_CONFFIR0		0x20 /* Config Reg Parity FIR 0 */
+#define CMUN_CONFFIR1		0x21 /* Config Reg Parity FIR 1 */
+#define CMUN_CONFFIR2		0x22 /* Config Reg Parity FIR 2 */
+#define CMUN_CONFFIR3		0x23 /* Config Reg Parity FIR 3 */
+#define CMUN_URCR3_RS		0x24 /* Unit Reset Control Reg 3 Set */
+#define CMUN_URCR3_C		0x25 /* Unit Reset Control Reg 3 Clear */
+#define CMUN_URCR3_P		0x26 /* Unit Reset Control Reg 3 Pulse */
+#define CMUN_PW0		0x2C /* Pulse Width Register */
+#define CMUN_URCR0_P		0x2D /* Unit Reset Control Reg 0 Pulse */
+#define CMUN_URCR1_P		0x2E /* Unit Reset Control Reg 1 Pulse */
+#define CMUN_URCR2_P		0x2F /* Unit Reset Control Reg 2 Pulse */
+#define CMUN_CLS_RW		0x30 /* Code Load Status (Read/Write) */
+#define CMUN_CLS_S		0x31 /* Code Load Status (Set) */
+#define CMUN_CLS_C		0x32 /* Code Load Status (Clear */
+#define CMUN_URCR2_RS		0x33 /* Unit Reset Control Reg 2 Set */
+#define CMUN_URCR2_C		0x34 /* Unit Reset Control Reg 2 Clear */
+#define CMUN_CLKEN0		0x35 /* Clock Enable 0 */
+#define CMUN_CLKEN1		0x36 /* Clock Enable 1 */
+#define CMUN_PCD0		0x37 /* PSI clock divider 0 */
+#define CMUN_PCD1		0x38 /* PSI clock divider 1 */
+#define CMUN_TMR0		0x39 /* Reset Timer */
+#define CMUN_TVS0		0x3A /* TV Sense Reg 0 */
+#define CMUN_TVS1		0x3B /* TV Sense Reg 1 */
+#define CMUN_MCCR		0x3C /* DRAM Configuration Reg */
+#define CMUN_FIR0		0x3D /* Fault Isolation Reg 0 */
+#define CMUN_FMR0		0x3E /* FIR Mask Reg 0 */
+#define CMUN_ETDRB		0x3F /* ETDR Backdoor */
+
+/* CRCS bit fields */
+#define CRCS_STAT_MASK		0xF0000000
+#define CRCS_STAT_POR		0x10000000
+#define CRCS_STAT_PHR		0x20000000
+#define CRCS_STAT_PCIE		0x30000000
+#define CRCS_STAT_CRCS_SYS	0x40000000
+#define CRCS_STAT_DBCR_SYS	0x50000000
+#define CRCS_STAT_HOST_SYS	0x60000000
+#define CRCS_STAT_CHIP_RST_B	0x70000000
+#define CRCS_STAT_CRCS_CHIP	0x80000000
+#define CRCS_STAT_DBCR_CHIP	0x90000000
+#define CRCS_STAT_HOST_CHIP	0xA0000000
+#define CRCS_STAT_PSI_CHIP	0xB0000000
+#define CRCS_STAT_CRCS_CORE	0xC0000000
+#define CRCS_STAT_DBCR_CORE	0xD0000000
+#define CRCS_STAT_HOST_CORE	0xE0000000
+#define CRCS_STAT_PCIE_HOT	0xF0000000
+#define CRCS_STAT_SELF_CORE	0x40000000
+#define CRCS_STAT_SELF_CHIP	0x50000000
+#define CRCS_WATCHE		0x08000000
+#define CRCS_CORE		0x04000000 /* Reset PPC440 core */
+#define CRCS_CHIP		0x02000000 /* Chip Reset */
+#define CRCS_SYS		0x01000000 /* System Reset */
+#define CRCS_WRCR		0x00800000 /* Watchdog reset on core reset */
+#define CRCS_EXTCR		0x00080000 /* CHIP_RST_B triggers chip reset */
+#define CRCS_PLOCK		0x00000002 /* PLL Locked */
+
+#define mtcmu(reg, data)		\
+do {					\
+	mtdcr(DCRN_CMU_ADDR, reg);	\
+	mtdcr(DCRN_CMU_DATA, data);	\
+} while (0)
+
+#define mfcmu(reg)\
+	({u32 data;			\
+	mtdcr(DCRN_CMU_ADDR, reg);	\
+	data = mfdcr(DCRN_CMU_DATA);	\
+	data; })
+
+#define mtl2(reg, data)			\
+do {					\
+	mtdcr(DCRN_L2CDCRAI, reg);	\
+	mtdcr(DCRN_L2CDCRDI, data);	\
+} while (0)
+
+#define mfl2(reg)			\
+	({u32 data;			\
+	mtdcr(DCRN_L2CDCRAI, reg);	\
+	data = mfdcr(DCRN_L2CDCRDI);	\
+	data; })
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_FSP2_DCR_H_ */
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index f99e79ee060e..48abb4cb304c 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -387,8 +387,8 @@ static unsigned int __init get_fifo_size(struct device_node *np,
 	if (fp)
 		return *fp;
 
-	pr_warning("no %s property in %pOF node, defaulting to %d\n",
-		   prop_name, np, DEFAULT_FIFO_SIZE);
+	pr_warn("no %s property in %pOF node, defaulting to %d\n",
+		prop_name, np, DEFAULT_FIFO_SIZE);
 
 	return DEFAULT_FIFO_SIZE;
 }
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 9e974b1e1697..17cf249b18ee 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -90,7 +90,7 @@ struct mpc52xx_gpt_priv {
 	struct list_head list;		/* List of all GPT devices */
 	struct device *dev;
 	struct mpc52xx_gpt __iomem *regs;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct irq_domain *irqhost;
 	u32 ipb_freq;
 	u8 wdt_mode;
@@ -141,9 +141,9 @@ static void mpc52xx_gpt_irq_unmask(struct irq_data *d)
 	struct mpc52xx_gpt_priv *gpt = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 
-	spin_lock_irqsave(&gpt->lock, flags);
+	raw_spin_lock_irqsave(&gpt->lock, flags);
 	setbits32(&gpt->regs->mode, MPC52xx_GPT_MODE_IRQ_EN);
-	spin_unlock_irqrestore(&gpt->lock, flags);
+	raw_spin_unlock_irqrestore(&gpt->lock, flags);
 }
 
 static void mpc52xx_gpt_irq_mask(struct irq_data *d)
@@ -151,9 +151,9 @@ static void mpc52xx_gpt_irq_mask(struct irq_data *d)
 	struct mpc52xx_gpt_priv *gpt = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 
-	spin_lock_irqsave(&gpt->lock, flags);
+	raw_spin_lock_irqsave(&gpt->lock, flags);
 	clrbits32(&gpt->regs->mode, MPC52xx_GPT_MODE_IRQ_EN);
-	spin_unlock_irqrestore(&gpt->lock, flags);
+	raw_spin_unlock_irqrestore(&gpt->lock, flags);
 }
 
 static void mpc52xx_gpt_irq_ack(struct irq_data *d)
@@ -171,14 +171,14 @@ static int mpc52xx_gpt_irq_set_type(struct irq_data *d, unsigned int flow_type)
 
 	dev_dbg(gpt->dev, "%s: virq=%i type=%x\n", __func__, d->irq, flow_type);
 
-	spin_lock_irqsave(&gpt->lock, flags);
+	raw_spin_lock_irqsave(&gpt->lock, flags);
 	reg = in_be32(&gpt->regs->mode) & ~MPC52xx_GPT_MODE_ICT_MASK;
 	if (flow_type & IRQF_TRIGGER_RISING)
 		reg |= MPC52xx_GPT_MODE_ICT_RISING;
 	if (flow_type & IRQF_TRIGGER_FALLING)
 		reg |= MPC52xx_GPT_MODE_ICT_FALLING;
 	out_be32(&gpt->regs->mode, reg);
-	spin_unlock_irqrestore(&gpt->lock, flags);
+	raw_spin_unlock_irqrestore(&gpt->lock, flags);
 
 	return 0;
 }
@@ -264,11 +264,11 @@ mpc52xx_gpt_irq_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node)
 	/* If the GPT is currently disabled, then change it to be in Input
 	 * Capture mode.  If the mode is non-zero, then the pin could be
 	 * already in use for something. */
-	spin_lock_irqsave(&gpt->lock, flags);
+	raw_spin_lock_irqsave(&gpt->lock, flags);
 	mode = in_be32(&gpt->regs->mode);
 	if ((mode & MPC52xx_GPT_MODE_MS_MASK) == 0)
 		out_be32(&gpt->regs->mode, mode | MPC52xx_GPT_MODE_MS_IC);
-	spin_unlock_irqrestore(&gpt->lock, flags);
+	raw_spin_unlock_irqrestore(&gpt->lock, flags);
 
 	dev_dbg(gpt->dev, "%s() complete. virq=%i\n", __func__, cascade_virq);
 }
@@ -295,9 +295,9 @@ mpc52xx_gpt_gpio_set(struct gpio_chip *gc, unsigned int gpio, int v)
 	dev_dbg(gpt->dev, "%s: gpio:%d v:%d\n", __func__, gpio, v);
 	r = v ? MPC52xx_GPT_MODE_GPIO_OUT_HIGH : MPC52xx_GPT_MODE_GPIO_OUT_LOW;
 
-	spin_lock_irqsave(&gpt->lock, flags);
+	raw_spin_lock_irqsave(&gpt->lock, flags);
 	clrsetbits_be32(&gpt->regs->mode, MPC52xx_GPT_MODE_GPIO_MASK, r);
-	spin_unlock_irqrestore(&gpt->lock, flags);
+	raw_spin_unlock_irqrestore(&gpt->lock, flags);
 }
 
 static int mpc52xx_gpt_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
@@ -307,9 +307,9 @@ static int mpc52xx_gpt_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
 
 	dev_dbg(gpt->dev, "%s: gpio:%d\n", __func__, gpio);
 
-	spin_lock_irqsave(&gpt->lock, flags);
+	raw_spin_lock_irqsave(&gpt->lock, flags);
 	clrbits32(&gpt->regs->mode, MPC52xx_GPT_MODE_GPIO_MASK);
-	spin_unlock_irqrestore(&gpt->lock, flags);
+	raw_spin_unlock_irqrestore(&gpt->lock, flags);
 
 	return 0;
 }
@@ -436,16 +436,16 @@ static int mpc52xx_gpt_do_start(struct mpc52xx_gpt_priv *gpt, u64 period,
 	}
 
 	/* Set and enable the timer, reject an attempt to use a wdt as gpt */
-	spin_lock_irqsave(&gpt->lock, flags);
+	raw_spin_lock_irqsave(&gpt->lock, flags);
 	if (as_wdt)
 		gpt->wdt_mode |= MPC52xx_GPT_IS_WDT;
 	else if ((gpt->wdt_mode & MPC52xx_GPT_IS_WDT) != 0) {
-		spin_unlock_irqrestore(&gpt->lock, flags);
+		raw_spin_unlock_irqrestore(&gpt->lock, flags);
 		return -EBUSY;
 	}
 	out_be32(&gpt->regs->count, prescale << 16 | clocks);
 	clrsetbits_be32(&gpt->regs->mode, clear, set);
-	spin_unlock_irqrestore(&gpt->lock, flags);
+	raw_spin_unlock_irqrestore(&gpt->lock, flags);
 
 	return 0;
 }
@@ -476,14 +476,14 @@ int mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt)
 	unsigned long flags;
 
 	/* reject the operation if the timer is used as watchdog (gpt 0 only) */
-	spin_lock_irqsave(&gpt->lock, flags);
+	raw_spin_lock_irqsave(&gpt->lock, flags);
 	if ((gpt->wdt_mode & MPC52xx_GPT_IS_WDT) != 0) {
-		spin_unlock_irqrestore(&gpt->lock, flags);
+		raw_spin_unlock_irqrestore(&gpt->lock, flags);
 		return -EBUSY;
 	}
 
 	clrbits32(&gpt->regs->mode, MPC52xx_GPT_MODE_COUNTER_ENABLE);
-	spin_unlock_irqrestore(&gpt->lock, flags);
+	raw_spin_unlock_irqrestore(&gpt->lock, flags);
 	return 0;
 }
 EXPORT_SYMBOL(mpc52xx_gpt_stop_timer);
@@ -500,9 +500,9 @@ u64 mpc52xx_gpt_timer_period(struct mpc52xx_gpt_priv *gpt)
 	u64 prescale;
 	unsigned long flags;
 
-	spin_lock_irqsave(&gpt->lock, flags);
+	raw_spin_lock_irqsave(&gpt->lock, flags);
 	period = in_be32(&gpt->regs->count);
-	spin_unlock_irqrestore(&gpt->lock, flags);
+	raw_spin_unlock_irqrestore(&gpt->lock, flags);
 
 	prescale = period >> 16;
 	period &= 0xffff;
@@ -532,9 +532,9 @@ static inline void mpc52xx_gpt_wdt_ping(struct mpc52xx_gpt_priv *gpt_wdt)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&gpt_wdt->lock, flags);
+	raw_spin_lock_irqsave(&gpt_wdt->lock, flags);
 	out_8((u8 *) &gpt_wdt->regs->mode, MPC52xx_GPT_MODE_WDT_PING);
-	spin_unlock_irqrestore(&gpt_wdt->lock, flags);
+	raw_spin_unlock_irqrestore(&gpt_wdt->lock, flags);
 }
 
 /* wdt misc device api */
@@ -638,11 +638,11 @@ static int mpc52xx_wdt_release(struct inode *inode, struct file *file)
 	struct mpc52xx_gpt_priv *gpt_wdt = file->private_data;
 	unsigned long flags;
 
-	spin_lock_irqsave(&gpt_wdt->lock, flags);
+	raw_spin_lock_irqsave(&gpt_wdt->lock, flags);
 	clrbits32(&gpt_wdt->regs->mode,
 		  MPC52xx_GPT_MODE_COUNTER_ENABLE | MPC52xx_GPT_MODE_WDT_EN);
 	gpt_wdt->wdt_mode &= ~MPC52xx_GPT_IS_WDT;
-	spin_unlock_irqrestore(&gpt_wdt->lock, flags);
+	raw_spin_unlock_irqrestore(&gpt_wdt->lock, flags);
 #endif
 	clear_bit(0, &wdt_is_active);
 	return 0;
@@ -723,7 +723,7 @@ static int mpc52xx_gpt_probe(struct platform_device *ofdev)
 	if (!gpt)
 		return -ENOMEM;
 
-	spin_lock_init(&gpt->lock);
+	raw_spin_lock_init(&gpt->lock);
 	gpt->dev = &ofdev->dev;
 	gpt->ipb_freq = mpc5xxx_get_bus_frequency(ofdev->dev.of_node);
 	gpt->regs = of_iomap(ofdev->dev.of_node, 0);
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index 96bb55ca61d3..d2ef39f0edc8 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -84,7 +84,7 @@ static ssize_t show_status(struct device *d,
 
 	return sprintf(buf, "%02x\n", ret);
 }
-static DEVICE_ATTR(status, S_IRUGO, show_status, NULL);
+static DEVICE_ATTR(status, 0444, show_status, NULL);
 
 static void mcu_power_off(void)
 {
diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c
index bb7b25acf26f..74c154e67c8b 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c
@@ -75,7 +75,7 @@ static void __init mpc832x_sys_setup_arch(void)
 		par_io_init(np);
 		of_node_put(np);
 
-		for (np = NULL; (np = of_find_node_by_name(np, "ucc")) != NULL;)
+		for_each_node_by_name(np, "ucc")
 			par_io_of_config(np);
 	}
 
diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
index a4539c5accb0..438986593873 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
@@ -204,7 +204,7 @@ static void __init mpc832x_rdb_setup_arch(void)
 		par_io_init(np);
 		of_node_put(np);
 
-		for (np = NULL; (np = of_find_node_by_name(np, "ucc")) != NULL;)
+		for_each_node_by_name(np, "ucc")
 			par_io_of_config(np);
 	}
 #endif				/* CONFIG_QUICC_ENGINE */
diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c
index 4fc3051c2b2e..fd44dd03e1f3 100644
--- a/arch/powerpc/platforms/83xx/mpc836x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c
@@ -83,7 +83,7 @@ static void __init mpc836x_mds_setup_arch(void)
 		par_io_init(np);
 		of_node_put(np);
 
-		for (np = NULL; (np = of_find_node_by_name(np, "ucc")) != NULL;)
+		for_each_node_by_name(np, "ucc")
 			par_io_of_config(np);
 #ifdef CONFIG_QE_USB
 		/* Must fixup Par IO before QE GPIO chips are registered. */
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index 82f8490b5aa7..38d4ba9f37b5 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -252,8 +252,7 @@ static int socrates_fpga_pic_host_xlate(struct irq_domain *h,
 		/* type is configurable */
 		if (intspec[1] != IRQ_TYPE_LEVEL_LOW &&
 		    intspec[1] != IRQ_TYPE_LEVEL_HIGH) {
-			pr_warning("FPGA PIC: invalid irq type, "
-				   "setting default active low\n");
+			pr_warn("FPGA PIC: invalid irq type, setting default active low\n");
 			*out_flags = IRQ_TYPE_LEVEL_LOW;
 		} else {
 			*out_flags = intspec[1];
@@ -267,7 +266,7 @@ static int socrates_fpga_pic_host_xlate(struct irq_domain *h,
 	if (intspec[2] <= 2)
 		fpga_irq->irq_line = intspec[2];
 	else
-		pr_warning("FPGA PIC: invalid irq routing\n");
+		pr_warn("FPGA PIC: invalid irq routing\n");
 
 	return 0;
 }
@@ -293,7 +292,7 @@ void socrates_fpga_pic_init(struct device_node *pic)
 	for (i = 0; i < 3; i++) {
 		socrates_fpga_irqs[i] = irq_of_parse_and_map(pic, i);
 		if (!socrates_fpga_irqs[i]) {
-			pr_warning("FPGA PIC: can't get irq%d.\n", i);
+			pr_warn("FPGA PIC: can't get irq%d\n", i);
 			continue;
 		}
 		irq_set_chained_handler(socrates_fpga_irqs[i],
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index a0e989ed4b6f..17c6cd3d02e6 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -101,7 +101,7 @@ static int __init mpc86xx_hpcn_probe(void)
 
 	/* Be nice and don't give silent boot death.  Delete this in 2.6.27 */
 	if (of_machine_is_compatible("mpc86xx")) {
-		pr_warning("WARNING: your dts/dtb is old. You must update before the next kernel release\n");
+		pr_warn("WARNING: your dts/dtb is old. You must update before the next kernel release.\n");
 		return 1;
 	}
 
diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig
index e2089d3de00c..d408162d5af4 100644
--- a/arch/powerpc/platforms/8xx/Kconfig
+++ b/arch/powerpc/platforms/8xx/Kconfig
@@ -116,18 +116,6 @@ config 8xx_GPIO
 
 	  If in doubt, say Y here.
 
-config 8xx_CPU6
-	bool "CPU6 Silicon Errata (860 Pre Rev. C)"
-	help
-	  MPC860 CPUs, prior to Rev C have some bugs in the silicon, which
-	  require workarounds for Linux (and most other OSes to work).  If you
-	  get a BUG() very early in boot, this might fix the problem.  For
-	  more details read the document entitled "MPC860 Family Device Errata
-	  Reference" on Freescale's website.  This option also incurs a
-	  performance hit.
-
-	  If in doubt, say N here.
-
 config 8xx_CPU15
 	bool "CPU15 Silicon Errata"
 	depends on !HUGETLB_PAGE
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 5a96a2763e4a..14ef17e10ec9 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -293,17 +293,6 @@ config CPM2
 	  you wish to build a kernel for a machine with a CPM2 coprocessor
 	  on it (826x, 827x, 8560).
 
-config AXON_RAM
-	tristate "Axon DDR2 memory device driver"
-	depends on PPC_IBM_CELL_BLADE && BLOCK
-	select DAX
-	default m
-	help
-	  It registers one block device per Axon's DDR2 memory bank found
-	  on a system. Block devices are called axonram?, their major and
-	  minor numbers are available in /proc/devices, /proc/partitions or
-	  in /sys/block/axonram?/dev.
-
 config FSL_ULI1575
 	bool
 	default n
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index ae07470fde3c..a429d859f15d 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -33,7 +33,6 @@ config PPC_85xx
 config PPC_8xx
 	bool "Freescale 8xx"
 	select FSL_SOC
-	select PPC_LIB_RHEAP
 	select SYS_SUPPORTS_HUGETLBFS
 
 config 40x
@@ -168,13 +167,6 @@ config PPC_FPU
 	bool
 	default y if PPC64
 
-config PPC_8xx_PERF_EVENT
-	bool "PPC 8xx perf events"
-	depends on PPC_8xx && PERF_EVENTS
-	help
-	  This is Performance Events support for PPC 8xx. The 8xx doesn't
-	  have a PMU but some events are emulated using 8xx features.
-
 config FSL_EMB_PERFMON
 	bool "Freescale Embedded Perfmon"
 	depends on E500 || PPC_83xx
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 6fc85e29dc08..5d4bf9aed51a 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -315,8 +315,7 @@ static int __init setup_iic(void)
 	struct cbe_iic_regs __iomem *node_iic;
 	const u32 *np;
 
-	for (dn = NULL;
-	     (dn = of_find_node_by_name(dn,"interrupt-controller")) != NULL;) {
+	for_each_node_by_name(dn, "interrupt-controller") {
 		if (!of_device_is_compatible(dn,
 				     "IBM,CBEA-Internal-Interrupt-Controller"))
 			continue;
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 4b91ad08eefd..12352a58072a 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -541,7 +541,7 @@ static struct cbe_iommu *cell_iommu_for_node(int nid)
 	return NULL;
 }
 
-static unsigned long cell_dma_direct_offset;
+static unsigned long cell_dma_nommu_offset;
 
 static unsigned long dma_iommu_fixed_base;
 
@@ -580,7 +580,7 @@ static void *dma_fixed_alloc_coherent(struct device *dev, size_t size,
 					    device_to_mask(dev), flag,
 					    dev_to_node(dev));
 	else
-		return dma_direct_ops.alloc(dev, size, dma_handle, flag,
+		return dma_nommu_ops.alloc(dev, size, dma_handle, flag,
 					    attrs);
 }
 
@@ -592,7 +592,7 @@ static void dma_fixed_free_coherent(struct device *dev, size_t size,
 		iommu_free_coherent(cell_get_iommu_table(dev), size, vaddr,
 				    dma_handle);
 	else
-		dma_direct_ops.free(dev, size, vaddr, dma_handle, attrs);
+		dma_nommu_ops.free(dev, size, vaddr, dma_handle, attrs);
 }
 
 static dma_addr_t dma_fixed_map_page(struct device *dev, struct page *page,
@@ -601,7 +601,7 @@ static dma_addr_t dma_fixed_map_page(struct device *dev, struct page *page,
 				     unsigned long attrs)
 {
 	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		return dma_direct_ops.map_page(dev, page, offset, size,
+		return dma_nommu_ops.map_page(dev, page, offset, size,
 					       direction, attrs);
 	else
 		return iommu_map_page(dev, cell_get_iommu_table(dev), page,
@@ -614,7 +614,7 @@ static void dma_fixed_unmap_page(struct device *dev, dma_addr_t dma_addr,
 				 unsigned long attrs)
 {
 	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		dma_direct_ops.unmap_page(dev, dma_addr, size, direction,
+		dma_nommu_ops.unmap_page(dev, dma_addr, size, direction,
 					  attrs);
 	else
 		iommu_unmap_page(cell_get_iommu_table(dev), dma_addr, size,
@@ -626,7 +626,7 @@ static int dma_fixed_map_sg(struct device *dev, struct scatterlist *sg,
 			   unsigned long attrs)
 {
 	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		return dma_direct_ops.map_sg(dev, sg, nents, direction, attrs);
+		return dma_nommu_ops.map_sg(dev, sg, nents, direction, attrs);
 	else
 		return ppc_iommu_map_sg(dev, cell_get_iommu_table(dev), sg,
 					nents, device_to_mask(dev),
@@ -638,7 +638,7 @@ static void dma_fixed_unmap_sg(struct device *dev, struct scatterlist *sg,
 			       unsigned long attrs)
 {
 	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		dma_direct_ops.unmap_sg(dev, sg, nents, direction, attrs);
+		dma_nommu_ops.unmap_sg(dev, sg, nents, direction, attrs);
 	else
 		ppc_iommu_unmap_sg(cell_get_iommu_table(dev), sg, nents,
 				   direction, attrs);
@@ -661,8 +661,8 @@ static void cell_dma_dev_setup(struct device *dev)
 {
 	if (get_pci_dma_ops() == &dma_iommu_ops)
 		set_iommu_table_base(dev, cell_get_iommu_table(dev));
-	else if (get_pci_dma_ops() == &dma_direct_ops)
-		set_dma_offset(dev, cell_dma_direct_offset);
+	else if (get_pci_dma_ops() == &dma_nommu_ops)
+		set_dma_offset(dev, cell_dma_nommu_offset);
 	else
 		BUG();
 }
@@ -810,14 +810,14 @@ static int __init cell_iommu_init_disabled(void)
 	unsigned long base = 0, size;
 
 	/* When no iommu is present, we use direct DMA ops */
-	set_pci_dma_ops(&dma_direct_ops);
+	set_pci_dma_ops(&dma_nommu_ops);
 
 	/* First make sure all IOC translation is turned off */
 	cell_disable_iommus();
 
 	/* If we have no Axon, we set up the spider DMA magic offset */
 	if (of_find_node_by_name(NULL, "axon") == NULL)
-		cell_dma_direct_offset = SPIDER_DMA_OFFSET;
+		cell_dma_nommu_offset = SPIDER_DMA_OFFSET;
 
 	/* Now we need to check to see where the memory is mapped
 	 * in PCI space. We assume that all busses use the same dma
@@ -851,13 +851,13 @@ static int __init cell_iommu_init_disabled(void)
 		return -ENODEV;
 	}
 
-	cell_dma_direct_offset += base;
+	cell_dma_nommu_offset += base;
 
-	if (cell_dma_direct_offset != 0)
+	if (cell_dma_nommu_offset != 0)
 		cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup;
 
 	printk("iommu: disabled, direct DMA offset is 0x%lx\n",
-	       cell_dma_direct_offset);
+	       cell_dma_nommu_offset);
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index d3543e68efe8..7d31b8d14661 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -192,8 +192,7 @@ static void __init mpic_init_IRQ(void)
 	struct device_node *dn;
 	struct mpic *mpic;
 
-	for (dn = NULL;
-	     (dn = of_find_node_by_name(dn, "interrupt-controller"));) {
+	for_each_node_by_name(dn, "interrupt-controller") {
 		if (!of_device_is_compatible(dn, "CBEA,platform-open-pic"))
 			continue;
 
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index aa44bfc46467..c137f0cb4151 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -343,8 +343,7 @@ void __init spider_init_IRQ(void)
 	 * device-tree is bogus anyway) so all we can do is pray or maybe test
 	 * the address and deduce the node-id
 	 */
-	for (dn = NULL;
-	     (dn = of_find_node_by_name(dn, "interrupt-controller"));) {
+	for_each_node_by_name(dn, "interrupt-controller") {
 		if (of_device_is_compatible(dn, "CBEA,platform-spider-pic")) {
 			if (of_address_to_resource(dn, 0, &r)) {
 				printk(KERN_WARNING "spider-pic: Failed\n");
diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c
index f636ee22b203..5c409c98cca8 100644
--- a/arch/powerpc/platforms/cell/spu_manage.c
+++ b/arch/powerpc/platforms/cell/spu_manage.c
@@ -292,12 +292,12 @@ static int __init of_enumerate_spus(int (*fn)(void *data))
 	unsigned int n = 0;
 
 	ret = -ENODEV;
-	for (node = of_find_node_by_type(NULL, "spe");
-			node; node = of_find_node_by_type(node, "spe")) {
+	for_each_node_by_type(node, "spe") {
 		ret = fn(node);
 		if (ret) {
 			printk(KERN_WARNING "%s: Error initializing %s\n",
 				__func__, node->name);
+			of_node_put(node);
 			break;
 		}
 		n++;
diff --git a/arch/powerpc/platforms/cell/spufs/backing_ops.c b/arch/powerpc/platforms/cell/spufs/backing_ops.c
index 6e8a9ef8590e..1a9a756b0b2f 100644
--- a/arch/powerpc/platforms/cell/spufs/backing_ops.c
+++ b/arch/powerpc/platforms/cell/spufs/backing_ops.c
@@ -86,10 +86,10 @@ static u32 spu_backing_mbox_stat_read(struct spu_context *ctx)
 	return ctx->csa.prob.mb_stat_R;
 }
 
-static unsigned int spu_backing_mbox_stat_poll(struct spu_context *ctx,
-					  unsigned int events)
+static __poll_t spu_backing_mbox_stat_poll(struct spu_context *ctx,
+					  __poll_t events)
 {
-	int ret;
+	__poll_t ret;
 	u32 stat;
 
 	ret = 0;
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 5ffcdeb1eb17..c1be486da899 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -762,10 +762,10 @@ out:
 	return count;
 }
 
-static unsigned int spufs_ibox_poll(struct file *file, poll_table *wait)
+static __poll_t spufs_ibox_poll(struct file *file, poll_table *wait)
 {
 	struct spu_context *ctx = file->private_data;
-	unsigned int mask;
+	__poll_t mask;
 
 	poll_wait(file, &ctx->ibox_wq, wait);
 
@@ -898,10 +898,10 @@ out:
 	return count;
 }
 
-static unsigned int spufs_wbox_poll(struct file *file, poll_table *wait)
+static __poll_t spufs_wbox_poll(struct file *file, poll_table *wait)
 {
 	struct spu_context *ctx = file->private_data;
-	unsigned int mask;
+	__poll_t mask;
 
 	poll_wait(file, &ctx->wbox_wq, wait);
 
@@ -1690,11 +1690,11 @@ out:
 	return ret;
 }
 
-static unsigned int spufs_mfc_poll(struct file *file,poll_table *wait)
+static __poll_t spufs_mfc_poll(struct file *file,poll_table *wait)
 {
 	struct spu_context *ctx = file->private_data;
 	u32 free_elements, tagstatus;
-	unsigned int mask;
+	__poll_t mask;
 
 	poll_wait(file, &ctx->mfc_wq, wait);
 
@@ -2375,8 +2375,8 @@ static int switch_log_sprint(struct spu_context *ctx, char *tbuf, int n)
 
 	p = ctx->switch_log->log + ctx->switch_log->tail % SWITCH_LOG_BUFSIZE;
 
-	return snprintf(tbuf, n, "%u.%09u %d %u %u %llu\n",
-			(unsigned int) p->tstamp.tv_sec,
+	return snprintf(tbuf, n, "%llu.%09u %d %u %u %llu\n",
+			(unsigned long long) p->tstamp.tv_sec,
 			(unsigned int) p->tstamp.tv_nsec,
 			p->spu_id,
 			(unsigned int) p->type,
@@ -2455,11 +2455,11 @@ static ssize_t spufs_switch_log_read(struct file *file, char __user *buf,
 	return cnt == 0 ? error : cnt;
 }
 
-static unsigned int spufs_switch_log_poll(struct file *file, poll_table *wait)
+static __poll_t spufs_switch_log_poll(struct file *file, poll_table *wait)
 {
 	struct inode *inode = file_inode(file);
 	struct spu_context *ctx = SPUFS_I(inode)->i_ctx;
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 	int rc;
 
 	poll_wait(file, &ctx->switch_log->wait, wait);
@@ -2499,7 +2499,7 @@ void spu_switch_log_notify(struct spu *spu, struct spu_context *ctx,
 		struct switch_log_entry *p;
 
 		p = ctx->switch_log->log + ctx->switch_log->head;
-		ktime_get_ts(&p->tstamp);
+		ktime_get_ts64(&p->tstamp);
 		p->timebase = get_tb();
 		p->spu_id = spu ? spu->number : -1;
 		p->type = type;
diff --git a/arch/powerpc/platforms/cell/spufs/hw_ops.c b/arch/powerpc/platforms/cell/spufs/hw_ops.c
index 8655c4cbefc2..fff58198b5b6 100644
--- a/arch/powerpc/platforms/cell/spufs/hw_ops.c
+++ b/arch/powerpc/platforms/cell/spufs/hw_ops.c
@@ -56,11 +56,10 @@ static u32 spu_hw_mbox_stat_read(struct spu_context *ctx)
 	return in_be32(&ctx->spu->problem->mb_stat_R);
 }
 
-static unsigned int spu_hw_mbox_stat_poll(struct spu_context *ctx,
-					  unsigned int events)
+static __poll_t spu_hw_mbox_stat_poll(struct spu_context *ctx, __poll_t events)
 {
 	struct spu *spu = ctx->spu;
-	int ret = 0;
+	__poll_t ret = 0;
 	u32 stat;
 
 	spin_lock_irq(&spu->register_lock);
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 9558d725a99b..db329d4bf1c3 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -455,7 +455,7 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 		}
 	}
 
-	ret = spufs_mkdir(inode, dentry, flags, mode & S_IRWXUGO);
+	ret = spufs_mkdir(inode, dentry, flags, mode & 0777);
 	if (ret)
 		goto out_aff_unlock;
 
@@ -546,7 +546,7 @@ static int spufs_create_gang(struct inode *inode,
 	struct path path = {.mnt = mnt, .dentry = dentry};
 	int ret;
 
-	ret = spufs_mkgang(inode, dentry, mode & S_IRWXUGO);
+	ret = spufs_mkgang(inode, dentry, mode & 0777);
 	if (!ret) {
 		ret = spufs_gang_open(&path);
 		if (ret < 0) {
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index 5e59f80e95db..b5fc1b3fe538 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -69,7 +69,7 @@ struct switch_log {
 	unsigned long		head;
 	unsigned long		tail;
 	struct switch_log_entry {
-		struct timespec	tstamp;
+		struct timespec64 tstamp;
 		s32		spu_id;
 		u32		type;
 		u32		val;
@@ -185,8 +185,7 @@ struct mfc_dma_command {
 struct spu_context_ops {
 	int (*mbox_read) (struct spu_context * ctx, u32 * data);
 	 u32(*mbox_stat_read) (struct spu_context * ctx);
-	unsigned int (*mbox_stat_poll)(struct spu_context *ctx,
-					unsigned int events);
+	__poll_t (*mbox_stat_poll)(struct spu_context *ctx, __poll_t events);
 	int (*ibox_read) (struct spu_context * ctx, u32 * data);
 	int (*wbox_write) (struct spu_context * ctx, u32 data);
 	 u32(*signal1_read) (struct spu_context * ctx);
diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c
index aafa01ba062f..2c72263ad6ab 100644
--- a/arch/powerpc/platforms/pasemi/dma_lib.c
+++ b/arch/powerpc/platforms/pasemi/dma_lib.c
@@ -589,7 +589,7 @@ int pasemi_dma_init(void)
 	pasemi_write_dma_reg(PAS_DMA_COM_RXCMD, 0);
 	while (pasemi_read_dma_reg(PAS_DMA_COM_RXSTA) & 1) {
 		if (time_after(jiffies, timeout)) {
-			pr_warning("Warning: Could not disable RX section\n");
+			pr_warn("Warning: Could not disable RX section\n");
 			break;
 		}
 	}
@@ -598,7 +598,7 @@ int pasemi_dma_init(void)
 	pasemi_write_dma_reg(PAS_DMA_COM_TXCMD, 0);
 	while (pasemi_read_dma_reg(PAS_DMA_COM_TXSTA) & 1) {
 		if (time_after(jiffies, timeout)) {
-			pr_warning("Warning: Could not disable TX section\n");
+			pr_warn("Warning: Could not disable TX section\n");
 			break;
 		}
 	}
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index 7fec04de27fc..78b80cbd9768 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -186,7 +186,7 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev)
 	 */
 	if (dev->vendor == 0x1959 && dev->device == 0xa007 &&
 	    !firmware_has_feature(FW_FEATURE_LPAR)) {
-		dev->dev.dma_ops = &dma_direct_ops;
+		dev->dev.dma_ops = &dma_nommu_ops;
 		/*
 		 * Set the coherent DMA mask to prevent the iommu
 		 * being used unnecessarily
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index c4a3e93dc324..d0b8ae53660d 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -363,7 +363,7 @@ static int pcmcia_notify(struct notifier_block *nb, unsigned long action,
 		return 0;
 
 	/* We use the direct ops for localbus */
-	dev->dma_ops = &dma_direct_ops;
+	dev->dma_ops = &dma_nommu_ops;
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/powermac/backlight.c b/arch/powerpc/platforms/powermac/backlight.c
index a00096b1c713..6b5dcccae1d3 100644
--- a/arch/powerpc/platforms/powermac/backlight.c
+++ b/arch/powerpc/platforms/powermac/backlight.c
@@ -186,7 +186,7 @@ int pmac_backlight_set_legacy_brightness(int brightness)
 	return __pmac_backlight_set_legacy_brightness(brightness);
 }
 
-int pmac_backlight_get_legacy_brightness()
+int pmac_backlight_get_legacy_brightness(void)
 {
 	int result = -ENXIO;
 
@@ -205,12 +205,12 @@ int pmac_backlight_get_legacy_brightness()
 	return result;
 }
 
-void pmac_backlight_disable()
+void pmac_backlight_disable(void)
 {
 	atomic_inc(&kernel_backlight_disabled);
 }
 
-void pmac_backlight_enable()
+void pmac_backlight_enable(void)
 {
 	atomic_dec(&kernel_backlight_disabled);
 }
diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c
index 9e3f39d36e88..466b84234683 100644
--- a/arch/powerpc/platforms/powermac/feature.c
+++ b/arch/powerpc/platforms/powermac/feature.c
@@ -2641,7 +2641,7 @@ static void __init probe_one_macio(const char *name, const char *compat, int typ
 	phys_addr_t		addr;
 	u64			size;
 
-	for (node = NULL; (node = of_find_node_by_name(node, name)) != NULL;) {
+	for_each_node_by_name(node, name) {
 		if (!compat)
 			break;
 		if (of_device_is_compatible(node, compat))
@@ -2853,7 +2853,6 @@ set_initial_features(void)
 		}
 
 		/* Enable ATA-100 before PCI probe. */
-		np = of_find_node_by_name(NULL, "ata-6");
 		for_each_node_by_name(np, "ata-6") {
 			if (np->parent
 			    && of_device_is_compatible(np->parent, "uni-north")
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 5e0719b27294..57bbff465964 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -486,15 +486,16 @@ static int __init pmac_pic_probe_mpic(void)
 	struct device_node *np, *master = NULL, *slave = NULL;
 
 	/* We can have up to 2 MPICs cascaded */
-	for (np = NULL; (np = of_find_node_by_type(np, "open-pic"))
-		     != NULL;) {
+	for_each_node_by_type(np, "open-pic") {
 		if (master == NULL &&
 		    of_get_property(np, "interrupts", NULL) == NULL)
 			master = of_node_get(np);
 		else if (slave == NULL)
 			slave = of_node_get(np);
-		if (master && slave)
+		if (master && slave) {
+			of_node_put(np);
 			break;
+		}
 	}
 
 	/* Check for bogus setups */
@@ -604,6 +605,7 @@ static int pmacpic_find_viaint(void)
 	if (np == NULL)
 		goto not_found;
 	viaint = irq_of_parse_and_map(np, 0);
+	of_node_put(np);
 
 not_found:
 #endif /* CONFIG_ADB_PMU */
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 2cd99eb30762..95275e0e2efa 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -774,8 +774,8 @@ static void __init smp_core99_probe(void)
 	if (ppc_md.progress) ppc_md.progress("smp_core99_probe", 0x345);
 
 	/* Count CPUs in the device-tree */
-       	for (cpus = NULL; (cpus = of_find_node_by_type(cpus, "cpu")) != NULL;)
-	       	++ncpus;
+	for_each_node_by_type(cpus, "cpu")
+		++ncpus;
 
 	printk(KERN_INFO "PowerMac SMP probe found %d cpus\n", ncpus);
 
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 3732118a0482..6c9d5199a7e2 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -17,3 +17,4 @@ obj-$(CONFIG_PERF_EVENTS) += opal-imc.o
 obj-$(CONFIG_PPC_MEMTRACE)	+= memtrace.o
 obj-$(CONFIG_PPC_VAS)	+= vas.o vas-window.o vas-debug.o
 obj-$(CONFIG_PPC_FTW)	+= nx-ftw.o
+obj-$(CONFIG_OCXL_BASE)	+= ocxl.o
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 4650fb294e7a..33c86c1a1720 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -43,6 +43,22 @@
 
 static int eeh_event_irq = -EINVAL;
 
+void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+
+	if (!pdev->is_virtfn)
+		return;
+
+	/*
+	 * The following operations will fail if VF's sysfs files
+	 * aren't created or its resources aren't finalized.
+	 */
+	eeh_add_device_early(pdn);
+	eeh_add_device_late(pdev);
+	eeh_sysfs_add_device(pdev);
+}
+
 static int pnv_eeh_init(void)
 {
 	struct pci_controller *hose;
@@ -86,6 +102,7 @@ static int pnv_eeh_init(void)
 	}
 
 	eeh_set_pe_aux_size(max_diag_size);
+	ppc_md.pcibios_bus_add_device = pnv_pcibios_bus_add_device;
 
 	return 0;
 }
@@ -1638,70 +1655,11 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
 	return ret;
 }
 
-static int pnv_eeh_restore_vf_config(struct pci_dn *pdn)
-{
-	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
-	u32 devctl, cmd, cap2, aer_capctl;
-	int old_mps;
-
-	if (edev->pcie_cap) {
-		/* Restore MPS */
-		old_mps = (ffs(pdn->mps) - 8) << 5;
-		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
-				     2, &devctl);
-		devctl &= ~PCI_EXP_DEVCTL_PAYLOAD;
-		devctl |= old_mps;
-		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
-				      2, devctl);
-
-		/* Disable Completion Timeout */
-		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP2,
-				     4, &cap2);
-		if (cap2 & 0x10) {
-			eeh_ops->read_config(pdn,
-					     edev->pcie_cap + PCI_EXP_DEVCTL2,
-					     4, &cap2);
-			cap2 |= 0x10;
-			eeh_ops->write_config(pdn,
-					      edev->pcie_cap + PCI_EXP_DEVCTL2,
-					      4, cap2);
-		}
-	}
-
-	/* Enable SERR and parity checking */
-	eeh_ops->read_config(pdn, PCI_COMMAND, 2, &cmd);
-	cmd |= (PCI_COMMAND_PARITY | PCI_COMMAND_SERR);
-	eeh_ops->write_config(pdn, PCI_COMMAND, 2, cmd);
-
-	/* Enable report various errors */
-	if (edev->pcie_cap) {
-		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
-				     2, &devctl);
-		devctl &= ~PCI_EXP_DEVCTL_CERE;
-		devctl |= (PCI_EXP_DEVCTL_NFERE |
-			   PCI_EXP_DEVCTL_FERE |
-			   PCI_EXP_DEVCTL_URRE);
-		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
-				      2, devctl);
-	}
-
-	/* Enable ECRC generation and check */
-	if (edev->pcie_cap && edev->aer_cap) {
-		eeh_ops->read_config(pdn, edev->aer_cap + PCI_ERR_CAP,
-				     4, &aer_capctl);
-		aer_capctl |= (PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE);
-		eeh_ops->write_config(pdn, edev->aer_cap + PCI_ERR_CAP,
-				      4, aer_capctl);
-	}
-
-	return 0;
-}
-
 static int pnv_eeh_restore_config(struct pci_dn *pdn)
 {
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 	struct pnv_phb *phb;
-	s64 ret;
+	s64 ret = 0;
 	int config_addr = (pdn->busno << 8) | (pdn->devfn);
 
 	if (!edev)
@@ -1715,7 +1673,7 @@ static int pnv_eeh_restore_config(struct pci_dn *pdn)
 	 * to be exported by firmware in extendible way.
 	 */
 	if (edev->physfn) {
-		ret = pnv_eeh_restore_vf_config(pdn);
+		ret = eeh_restore_vf_config(pdn);
 	} else {
 		phb = pdn->phb->private_data;
 		ret = opal_pci_reinit(phb->opal_id,
@@ -1728,7 +1686,7 @@ static int pnv_eeh_restore_config(struct pci_dn *pdn)
 		return -EIO;
 	}
 
-	return 0;
+	return ret;
 }
 
 static struct eeh_ops pnv_eeh_ops = {
@@ -1746,25 +1704,10 @@ static struct eeh_ops pnv_eeh_ops = {
 	.read_config            = pnv_eeh_read_config,
 	.write_config           = pnv_eeh_write_config,
 	.next_error		= pnv_eeh_next_error,
-	.restore_config		= pnv_eeh_restore_config
+	.restore_config		= pnv_eeh_restore_config,
+	.notify_resume		= NULL
 };
 
-void pcibios_bus_add_device(struct pci_dev *pdev)
-{
-	struct pci_dn *pdn = pci_get_pdn(pdev);
-
-	if (!pdev->is_virtfn)
-		return;
-
-	/*
-	 * The following operations will fail if VF's sysfs files
-	 * aren't created or its resources aren't finalized.
-	 */
-	eeh_add_device_early(pdn);
-	eeh_add_device_late(pdev);
-	eeh_sysfs_add_device(pdev);
-}
-
 #ifdef CONFIG_PCI_IOV
 static void pnv_pci_fixup_vf_mps(struct pci_dev *pdev)
 {
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index f6cbc1a71472..0a253b64ac5f 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -39,7 +39,10 @@
  */
 static struct pci_dev *get_pci_dev(struct device_node *dn)
 {
-	return PCI_DN(dn)->pcidev;
+	struct pci_dn *pdn = PCI_DN(dn);
+
+	return pci_get_domain_bus_and_slot(pci_domain_nr(pdn->phb->bus),
+					   pdn->busno, pdn->devfn);
 }
 
 /* Given a NPU device get the associated PCI device. */
@@ -277,7 +280,7 @@ static int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe)
 	int64_t rc = 0;
 	phys_addr_t top = memblock_end_of_DRAM();
 
-	if (phb->type != PNV_PHB_NPU || !npe->pdev)
+	if (phb->type != PNV_PHB_NPU_NVLINK || !npe->pdev)
 		return -EINVAL;
 
 	rc = pnv_npu_unset_window(npe, 0);
diff --git a/arch/powerpc/platforms/powernv/ocxl.c b/arch/powerpc/platforms/powernv/ocxl.c
new file mode 100644
index 000000000000..fa9b53af3c7b
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/ocxl.c
@@ -0,0 +1,515 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2017 IBM Corp.
+#include <asm/pnv-ocxl.h>
+#include <asm/opal.h>
+#include <asm/xive.h>
+#include <misc/ocxl-config.h>
+#include "pci.h"
+
+#define PNV_OCXL_TL_P9_RECV_CAP		0x000000000000000Full
+#define PNV_OCXL_ACTAG_MAX		64
+/* PASIDs are 20-bit, but on P9, NPU can only handle 15 bits */
+#define PNV_OCXL_PASID_BITS		15
+#define PNV_OCXL_PASID_MAX		((1 << PNV_OCXL_PASID_BITS) - 1)
+
+#define AFU_PRESENT (1 << 31)
+#define AFU_INDEX_MASK 0x3F000000
+#define AFU_INDEX_SHIFT 24
+#define ACTAG_MASK 0xFFF
+
+
+struct actag_range {
+	u16 start;
+	u16 count;
+};
+
+struct npu_link {
+	struct list_head list;
+	int domain;
+	int bus;
+	int dev;
+	u16 fn_desired_actags[8];
+	struct actag_range fn_actags[8];
+	bool assignment_done;
+};
+static struct list_head links_list = LIST_HEAD_INIT(links_list);
+static DEFINE_MUTEX(links_list_lock);
+
+
+/*
+ * opencapi actags handling:
+ *
+ * When sending commands, the opencapi device references the memory
+ * context it's targeting with an 'actag', which is really an alias
+ * for a (BDF, pasid) combination. When it receives a command, the NPU
+ * must do a lookup of the actag to identify the memory context. The
+ * hardware supports a finite number of actags per link (64 for
+ * POWER9).
+ *
+ * The device can carry multiple functions, and each function can have
+ * multiple AFUs. Each AFU advertises in its config space the number
+ * of desired actags. The host must configure in the config space of
+ * the AFU how many actags the AFU is really allowed to use (which can
+ * be less than what the AFU desires).
+ *
+ * When a PCI function is probed by the driver, it has no visibility
+ * about the other PCI functions and how many actags they'd like,
+ * which makes it impossible to distribute actags fairly among AFUs.
+ *
+ * Unfortunately, the only way to know how many actags a function
+ * desires is by looking at the data for each AFU in the config space
+ * and add them up. Similarly, the only way to know how many actags
+ * all the functions of the physical device desire is by adding the
+ * previously computed function counts. Then we can match that against
+ * what the hardware supports.
+ *
+ * To get a comprehensive view, we use a 'pci fixup': at the end of
+ * PCI enumeration, each function counts how many actags its AFUs
+ * desire and we save it in a 'npu_link' structure, shared between all
+ * the PCI functions of a same device. Therefore, when the first
+ * function is probed by the driver, we can get an idea of the total
+ * count of desired actags for the device, and assign the actags to
+ * the AFUs, by pro-rating if needed.
+ */
+
+static int find_dvsec_from_pos(struct pci_dev *dev, int dvsec_id, int pos)
+{
+	int vsec = pos;
+	u16 vendor, id;
+
+	while ((vsec = pci_find_next_ext_capability(dev, vsec,
+						    OCXL_EXT_CAP_ID_DVSEC))) {
+		pci_read_config_word(dev, vsec + OCXL_DVSEC_VENDOR_OFFSET,
+				&vendor);
+		pci_read_config_word(dev, vsec + OCXL_DVSEC_ID_OFFSET, &id);
+		if (vendor == PCI_VENDOR_ID_IBM && id == dvsec_id)
+			return vsec;
+	}
+	return 0;
+}
+
+static int find_dvsec_afu_ctrl(struct pci_dev *dev, u8 afu_idx)
+{
+	int vsec = 0;
+	u8 idx;
+
+	while ((vsec = find_dvsec_from_pos(dev, OCXL_DVSEC_AFU_CTRL_ID,
+					   vsec))) {
+		pci_read_config_byte(dev, vsec + OCXL_DVSEC_AFU_CTRL_AFU_IDX,
+				&idx);
+		if (idx == afu_idx)
+			return vsec;
+	}
+	return 0;
+}
+
+static int get_max_afu_index(struct pci_dev *dev, int *afu_idx)
+{
+	int pos;
+	u32 val;
+
+	pos = find_dvsec_from_pos(dev, OCXL_DVSEC_FUNC_ID, 0);
+	if (!pos)
+		return -ESRCH;
+
+	pci_read_config_dword(dev, pos + OCXL_DVSEC_FUNC_OFF_INDEX, &val);
+	if (val & AFU_PRESENT)
+		*afu_idx = (val & AFU_INDEX_MASK) >> AFU_INDEX_SHIFT;
+	else
+		*afu_idx = -1;
+	return 0;
+}
+
+static int get_actag_count(struct pci_dev *dev, int afu_idx, int *actag)
+{
+	int pos;
+	u16 actag_sup;
+
+	pos = find_dvsec_afu_ctrl(dev, afu_idx);
+	if (!pos)
+		return -ESRCH;
+
+	pci_read_config_word(dev, pos + OCXL_DVSEC_AFU_CTRL_ACTAG_SUP,
+			&actag_sup);
+	*actag = actag_sup & ACTAG_MASK;
+	return 0;
+}
+
+static struct npu_link *find_link(struct pci_dev *dev)
+{
+	struct npu_link *link;
+
+	list_for_each_entry(link, &links_list, list) {
+		/* The functions of a device all share the same link */
+		if (link->domain == pci_domain_nr(dev->bus) &&
+			link->bus == dev->bus->number &&
+			link->dev == PCI_SLOT(dev->devfn)) {
+			return link;
+		}
+	}
+
+	/* link doesn't exist yet. Allocate one */
+	link = kzalloc(sizeof(struct npu_link), GFP_KERNEL);
+	if (!link)
+		return NULL;
+	link->domain = pci_domain_nr(dev->bus);
+	link->bus = dev->bus->number;
+	link->dev = PCI_SLOT(dev->devfn);
+	list_add(&link->list, &links_list);
+	return link;
+}
+
+static void pnv_ocxl_fixup_actag(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct npu_link *link;
+	int rc, afu_idx = -1, i, actag;
+
+	if (!machine_is(powernv))
+		return;
+
+	if (phb->type != PNV_PHB_NPU_OCAPI)
+		return;
+
+	mutex_lock(&links_list_lock);
+
+	link = find_link(dev);
+	if (!link) {
+		dev_warn(&dev->dev, "couldn't update actag information\n");
+		mutex_unlock(&links_list_lock);
+		return;
+	}
+
+	/*
+	 * Check how many actags are desired for the AFUs under that
+	 * function and add it to the count for the link
+	 */
+	rc = get_max_afu_index(dev, &afu_idx);
+	if (rc) {
+		/* Most likely an invalid config space */
+		dev_dbg(&dev->dev, "couldn't find AFU information\n");
+		afu_idx = -1;
+	}
+
+	link->fn_desired_actags[PCI_FUNC(dev->devfn)] = 0;
+	for (i = 0; i <= afu_idx; i++) {
+		/*
+		 * AFU index 'holes' are allowed. So don't fail if we
+		 * can't read the actag info for an index
+		 */
+		rc = get_actag_count(dev, i, &actag);
+		if (rc)
+			continue;
+		link->fn_desired_actags[PCI_FUNC(dev->devfn)] += actag;
+	}
+	dev_dbg(&dev->dev, "total actags for function: %d\n",
+		link->fn_desired_actags[PCI_FUNC(dev->devfn)]);
+
+	mutex_unlock(&links_list_lock);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pnv_ocxl_fixup_actag);
+
+static u16 assign_fn_actags(u16 desired, u16 total)
+{
+	u16 count;
+
+	if (total <= PNV_OCXL_ACTAG_MAX)
+		count = desired;
+	else
+		count = PNV_OCXL_ACTAG_MAX * desired / total;
+
+	return count;
+}
+
+static void assign_actags(struct npu_link *link)
+{
+	u16 actag_count, range_start = 0, total_desired = 0;
+	int i;
+
+	for (i = 0; i < 8; i++)
+		total_desired += link->fn_desired_actags[i];
+
+	for (i = 0; i < 8; i++) {
+		if (link->fn_desired_actags[i]) {
+			actag_count = assign_fn_actags(
+				link->fn_desired_actags[i],
+				total_desired);
+			link->fn_actags[i].start = range_start;
+			link->fn_actags[i].count = actag_count;
+			range_start += actag_count;
+			WARN_ON(range_start >= PNV_OCXL_ACTAG_MAX);
+		}
+		pr_debug("link %x:%x:%x fct %d actags: start=%d count=%d (desired=%d)\n",
+			link->domain, link->bus, link->dev, i,
+			link->fn_actags[i].start, link->fn_actags[i].count,
+			link->fn_desired_actags[i]);
+	}
+	link->assignment_done = true;
+}
+
+int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled,
+		u16 *supported)
+{
+	struct npu_link *link;
+
+	mutex_lock(&links_list_lock);
+
+	link = find_link(dev);
+	if (!link) {
+		dev_err(&dev->dev, "actag information not found\n");
+		mutex_unlock(&links_list_lock);
+		return -ENODEV;
+	}
+	/*
+	 * On p9, we only have 64 actags per link, so they must be
+	 * shared by all the functions of the same adapter. We counted
+	 * the desired actag counts during PCI enumeration, so that we
+	 * can allocate a pro-rated number of actags to each function.
+	 */
+	if (!link->assignment_done)
+		assign_actags(link);
+
+	*base      = link->fn_actags[PCI_FUNC(dev->devfn)].start;
+	*enabled   = link->fn_actags[PCI_FUNC(dev->devfn)].count;
+	*supported = link->fn_desired_actags[PCI_FUNC(dev->devfn)];
+
+	mutex_unlock(&links_list_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_get_actag);
+
+int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count)
+{
+	struct npu_link *link;
+	int i, rc = -EINVAL;
+
+	/*
+	 * The number of PASIDs (process address space ID) which can
+	 * be used by a function depends on how many functions exist
+	 * on the device. The NPU needs to be configured to know how
+	 * many bits are available to PASIDs and how many are to be
+	 * used by the function BDF indentifier.
+	 *
+	 * We only support one AFU-carrying function for now.
+	 */
+	mutex_lock(&links_list_lock);
+
+	link = find_link(dev);
+	if (!link) {
+		dev_err(&dev->dev, "actag information not found\n");
+		mutex_unlock(&links_list_lock);
+		return -ENODEV;
+	}
+
+	for (i = 0; i < 8; i++)
+		if (link->fn_desired_actags[i] && (i == PCI_FUNC(dev->devfn))) {
+			*count = PNV_OCXL_PASID_MAX;
+			rc = 0;
+			break;
+		}
+
+	mutex_unlock(&links_list_lock);
+	dev_dbg(&dev->dev, "%d PASIDs available for function\n",
+		rc ? 0 : *count);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_get_pasid_count);
+
+static void set_templ_rate(unsigned int templ, unsigned int rate, char *buf)
+{
+	int shift, idx;
+
+	WARN_ON(templ > PNV_OCXL_TL_MAX_TEMPLATE);
+	idx = (PNV_OCXL_TL_MAX_TEMPLATE - templ) / 2;
+	shift = 4 * (1 - ((PNV_OCXL_TL_MAX_TEMPLATE - templ) % 2));
+	buf[idx] |= rate << shift;
+}
+
+int pnv_ocxl_get_tl_cap(struct pci_dev *dev, long *cap,
+			char *rate_buf, int rate_buf_size)
+{
+	if (rate_buf_size != PNV_OCXL_TL_RATE_BUF_SIZE)
+		return -EINVAL;
+	/*
+	 * The TL capabilities are a characteristic of the NPU, so
+	 * we go with hard-coded values.
+	 *
+	 * The receiving rate of each template is encoded on 4 bits.
+	 *
+	 * On P9:
+	 * - templates 0 -> 3 are supported
+	 * - templates 0, 1 and 3 have a 0 receiving rate
+	 * - template 2 has receiving rate of 1 (extra cycle)
+	 */
+	memset(rate_buf, 0, rate_buf_size);
+	set_templ_rate(2, 1, rate_buf);
+	*cap = PNV_OCXL_TL_P9_RECV_CAP;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_get_tl_cap);
+
+int pnv_ocxl_set_tl_conf(struct pci_dev *dev, long cap,
+			uint64_t rate_buf_phys, int rate_buf_size)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int rc;
+
+	if (rate_buf_size != PNV_OCXL_TL_RATE_BUF_SIZE)
+		return -EINVAL;
+
+	rc = opal_npu_tl_set(phb->opal_id, dev->devfn, cap,
+			rate_buf_phys, rate_buf_size);
+	if (rc) {
+		dev_err(&dev->dev, "Can't configure host TL: %d\n", rc);
+		return -EINVAL;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_set_tl_conf);
+
+int pnv_ocxl_get_xsl_irq(struct pci_dev *dev, int *hwirq)
+{
+	int rc;
+
+	rc = of_property_read_u32(dev->dev.of_node, "ibm,opal-xsl-irq", hwirq);
+	if (rc) {
+		dev_err(&dev->dev,
+			"Can't get translation interrupt for device\n");
+		return rc;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_get_xsl_irq);
+
+void pnv_ocxl_unmap_xsl_regs(void __iomem *dsisr, void __iomem *dar,
+			void __iomem *tfc, void __iomem *pe_handle)
+{
+	iounmap(dsisr);
+	iounmap(dar);
+	iounmap(tfc);
+	iounmap(pe_handle);
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_unmap_xsl_regs);
+
+int pnv_ocxl_map_xsl_regs(struct pci_dev *dev, void __iomem **dsisr,
+			void __iomem **dar, void __iomem **tfc,
+			void __iomem **pe_handle)
+{
+	u64 reg;
+	int i, j, rc = 0;
+	void __iomem *regs[4];
+
+	/*
+	 * opal stores the mmio addresses of the DSISR, DAR, TFC and
+	 * PE_HANDLE registers in a device tree property, in that
+	 * order
+	 */
+	for (i = 0; i < 4; i++) {
+		rc = of_property_read_u64_index(dev->dev.of_node,
+						"ibm,opal-xsl-mmio", i, &reg);
+		if (rc)
+			break;
+		regs[i] = ioremap(reg, 8);
+		if (!regs[i]) {
+			rc = -EINVAL;
+			break;
+		}
+	}
+	if (rc) {
+		dev_err(&dev->dev, "Can't map translation mmio registers\n");
+		for (j = i - 1; j >= 0; j--)
+			iounmap(regs[j]);
+	} else {
+		*dsisr = regs[0];
+		*dar = regs[1];
+		*tfc = regs[2];
+		*pe_handle = regs[3];
+	}
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_map_xsl_regs);
+
+struct spa_data {
+	u64 phb_opal_id;
+	u32 bdfn;
+};
+
+int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask,
+		void **platform_data)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct spa_data *data;
+	u32 bdfn;
+	int rc;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	bdfn = (dev->bus->number << 8) | dev->devfn;
+	rc = opal_npu_spa_setup(phb->opal_id, bdfn, virt_to_phys(spa_mem),
+				PE_mask);
+	if (rc) {
+		dev_err(&dev->dev, "Can't setup Shared Process Area: %d\n", rc);
+		kfree(data);
+		return rc;
+	}
+	data->phb_opal_id = phb->opal_id;
+	data->bdfn = bdfn;
+	*platform_data = (void *) data;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_spa_setup);
+
+void pnv_ocxl_spa_release(void *platform_data)
+{
+	struct spa_data *data = (struct spa_data *) platform_data;
+	int rc;
+
+	rc = opal_npu_spa_setup(data->phb_opal_id, data->bdfn, 0, 0);
+	WARN_ON(rc);
+	kfree(data);
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_spa_release);
+
+int pnv_ocxl_spa_remove_pe(void *platform_data, int pe_handle)
+{
+	struct spa_data *data = (struct spa_data *) platform_data;
+	int rc;
+
+	rc = opal_npu_spa_clear_cache(data->phb_opal_id, data->bdfn, pe_handle);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_spa_remove_pe);
+
+int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr)
+{
+	__be64 flags, trigger_page;
+	s64 rc;
+	u32 hwirq;
+
+	hwirq = xive_native_alloc_irq();
+	if (!hwirq)
+		return -ENOENT;
+
+	rc = opal_xive_get_irq_info(hwirq, &flags, NULL, &trigger_page, NULL,
+				NULL);
+	if (rc || !trigger_page) {
+		xive_native_free_irq(hwirq);
+		return -ENOENT;
+	}
+	*irq = hwirq;
+	*trigger_addr = be64_to_cpu(trigger_page);
+	return 0;
+
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_alloc_xive_irq);
+
+void pnv_ocxl_free_xive_irq(u32 irq)
+{
+	xive_native_free_irq(irq);
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_free_xive_irq);
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 4c827826c05e..0dc8fa4e0af2 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -103,9 +103,9 @@ static ssize_t dump_ack_store(struct dump_obj *dump_obj,
  * due to the dynamic size of the dump
  */
 static struct dump_attribute id_attribute =
-	__ATTR(id, S_IRUGO, dump_id_show, NULL);
+	__ATTR(id, 0444, dump_id_show, NULL);
 static struct dump_attribute type_attribute =
-	__ATTR(type, S_IRUGO, dump_type_show, NULL);
+	__ATTR(type, 0444, dump_type_show, NULL);
 static struct dump_attribute ack_attribute =
 	__ATTR(acknowledge, 0660, dump_ack_show, dump_ack_store);
 
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index ecd6d9177d13..ba6e437abb4b 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -83,9 +83,9 @@ static ssize_t elog_ack_store(struct elog_obj *elog_obj,
 }
 
 static struct elog_attribute id_attribute =
-	__ATTR(id, S_IRUGO, elog_id_show, NULL);
+	__ATTR(id, 0444, elog_id_show, NULL);
 static struct elog_attribute type_attribute =
-	__ATTR(type, S_IRUGO, elog_type_show, NULL);
+	__ATTR(type, 0444, elog_type_show, NULL);
 static struct elog_attribute ack_attribute =
 	__ATTR(acknowledge, 0660, elog_ack_show, elog_ack_store);
 
diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c
index 465ea105b771..dd4c9b8b8a81 100644
--- a/arch/powerpc/platforms/powernv/opal-imc.c
+++ b/arch/powerpc/platforms/powernv/opal-imc.c
@@ -21,6 +21,78 @@
 #include <asm/io.h>
 #include <asm/imc-pmu.h>
 #include <asm/cputhreads.h>
+#include <asm/debugfs.h>
+
+static struct dentry *imc_debugfs_parent;
+
+/* Helpers to export imc command and mode via debugfs */
+static int imc_mem_get(void *data, u64 *val)
+{
+	*val = cpu_to_be64(*(u64 *)data);
+	return 0;
+}
+
+static int imc_mem_set(void *data, u64 val)
+{
+	*(u64 *)data = cpu_to_be64(val);
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_imc_x64, imc_mem_get, imc_mem_set, "0x%016llx\n");
+
+static struct dentry *imc_debugfs_create_x64(const char *name, umode_t mode,
+					     struct dentry *parent, u64  *value)
+{
+	return debugfs_create_file_unsafe(name, mode, parent,
+					  value, &fops_imc_x64);
+}
+
+/*
+ * export_imc_mode_and_cmd: Create a debugfs interface
+ *                     for imc_cmd and imc_mode
+ *                     for each node in the system.
+ *  imc_mode and imc_cmd can be changed by echo into
+ *  this interface.
+ */
+static void export_imc_mode_and_cmd(struct device_node *node,
+				    struct imc_pmu *pmu_ptr)
+{
+	static u64 loc, *imc_mode_addr, *imc_cmd_addr;
+	int chip = 0, nid;
+	char mode[16], cmd[16];
+	u32 cb_offset;
+
+	imc_debugfs_parent = debugfs_create_dir("imc", powerpc_debugfs_root);
+
+	/*
+	 * Return here, either because 'imc' directory already exists,
+	 * Or failed to create a new one.
+	 */
+	if (!imc_debugfs_parent)
+		return;
+
+	if (of_property_read_u32(node, "cb_offset", &cb_offset))
+		cb_offset = IMC_CNTL_BLK_OFFSET;
+
+	for_each_node(nid) {
+		loc = (u64)(pmu_ptr->mem_info[chip].vbase) + cb_offset;
+		imc_mode_addr = (u64 *)(loc + IMC_CNTL_BLK_MODE_OFFSET);
+		sprintf(mode, "imc_mode_%d", nid);
+		if (!imc_debugfs_create_x64(mode, 0600, imc_debugfs_parent,
+					    imc_mode_addr))
+			goto err;
+
+		imc_cmd_addr = (u64 *)(loc + IMC_CNTL_BLK_CMD_OFFSET);
+		sprintf(cmd, "imc_cmd_%d", nid);
+		if (!imc_debugfs_create_x64(cmd, 0600, imc_debugfs_parent,
+					    imc_cmd_addr))
+			goto err;
+		chip++;
+	}
+	return;
+
+err:
+	debugfs_remove_recursive(imc_debugfs_parent);
+}
 
 /*
  * imc_get_mem_addr_nest: Function to get nest counter memory region
@@ -65,6 +137,7 @@ static int imc_get_mem_addr_nest(struct device_node *node,
 	}
 
 	pmu_ptr->imc_counter_mmaped = true;
+	export_imc_mode_and_cmd(node, pmu_ptr);
 	kfree(base_addr_arr);
 	kfree(chipid_arr);
 	return 0;
@@ -213,6 +286,10 @@ static int opal_imc_counters_probe(struct platform_device *pdev)
 		}
 	}
 
+	/* If none of the nest units are registered, remove debugfs interface */
+	if (pmu_count == 0)
+		debugfs_remove_recursive(imc_debugfs_parent);
+
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c
index d9916ea62305..8ddc1accf199 100644
--- a/arch/powerpc/platforms/powernv/opal-memory-errors.c
+++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c
@@ -60,7 +60,7 @@ static void handle_memory_error_event(struct OpalMemoryErrorData *merr_evt)
 	}
 
 	for (; paddr_start < paddr_end; paddr_start += PAGE_SIZE) {
-		memory_failure(paddr_start >> PAGE_SHIFT, 0, 0);
+		memory_failure(paddr_start >> PAGE_SHIFT, 0);
 	}
 }
 
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
index de4dd09f4a15..c18de0a9b1bd 100644
--- a/arch/powerpc/platforms/powernv/opal-prd.c
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -147,7 +147,7 @@ static bool opal_msg_queue_empty(void)
 	return ret;
 }
 
-static unsigned int opal_prd_poll(struct file *file,
+static __poll_t opal_prd_poll(struct file *file,
 		struct poll_table_struct *wait)
 {
 	poll_wait(file, &opal_prd_msg_wait, wait);
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
index 23fb6647dced..6fd4092798d5 100644
--- a/arch/powerpc/platforms/powernv/opal-sysparam.c
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -260,13 +260,13 @@ void __init opal_sys_param_init(void)
 		/* If the parameter is read-only or read-write */
 		switch (perm[i] & 3) {
 		case OPAL_SYSPARAM_READ:
-			attr[i].kobj_attr.attr.mode = S_IRUGO;
+			attr[i].kobj_attr.attr.mode = 0444;
 			break;
 		case OPAL_SYSPARAM_WRITE:
-			attr[i].kobj_attr.attr.mode = S_IWUSR;
+			attr[i].kobj_attr.attr.mode = 0200;
 			break;
 		case OPAL_SYSPARAM_RW:
-			attr[i].kobj_attr.attr.mode = S_IRUGO | S_IWUSR;
+			attr[i].kobj_attr.attr.mode = 0644;
 			break;
 		default:
 			break;
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 6f4b00a2ac46..1b2936ba6040 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -320,3 +320,6 @@ OPAL_CALL(opal_set_powercap,			OPAL_SET_POWERCAP);
 OPAL_CALL(opal_get_power_shift_ratio,		OPAL_GET_POWER_SHIFT_RATIO);
 OPAL_CALL(opal_set_power_shift_ratio,		OPAL_SET_POWER_SHIFT_RATIO);
 OPAL_CALL(opal_sensor_group_clear,		OPAL_SENSOR_GROUP_CLEAR);
+OPAL_CALL(opal_npu_spa_setup,			OPAL_NPU_SPA_SETUP);
+OPAL_CALL(opal_npu_spa_clear_cache,		OPAL_NPU_SPA_CLEAR_CACHE);
+OPAL_CALL(opal_npu_tl_set,			OPAL_NPU_TL_SET);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 041ddbd1fc57..c15182765ff5 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -127,7 +127,7 @@ int __init early_init_dt_scan_opal(unsigned long node,
 
 	if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
 		powerpc_firmware_features |= FW_FEATURE_OPAL;
-		pr_info("OPAL detected !\n");
+		pr_debug("OPAL detected !\n");
 	} else {
 		panic("OPAL != V3 detected, no longer supported.\n");
 	}
@@ -239,8 +239,8 @@ int opal_message_notifier_register(enum opal_msg_type msg_type,
 					struct notifier_block *nb)
 {
 	if (!nb || msg_type >= OPAL_MSG_TYPE_MAX) {
-		pr_warning("%s: Invalid arguments, msg_type:%d\n",
-			   __func__, msg_type);
+		pr_warn("%s: Invalid arguments, msg_type:%d\n",
+			__func__, msg_type);
 		return -EINVAL;
 	}
 
@@ -281,8 +281,8 @@ static void opal_handle_message(void)
 
 	/* check for errors. */
 	if (ret) {
-		pr_warning("%s: Failed to retrieve opal message, err=%lld\n",
-				__func__, ret);
+		pr_warn("%s: Failed to retrieve opal message, err=%lld\n",
+			__func__, ret);
 		return;
 	}
 
@@ -461,24 +461,14 @@ static int opal_recover_mce(struct pt_regs *regs,
 
 void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg)
 {
-	/*
-	 * This is mostly taken from kernel/panic.c, but tries to do
-	 * relatively minimal work. Don't use delay functions (TB may
-	 * be broken), don't crash dump (need to set a firmware log),
-	 * don't run notifiers. We do want to get some information to
-	 * Linux console.
-	 */
-	console_verbose();
-	bust_spinlocks(1);
+	panic_flush_kmsg_start();
+
 	pr_emerg("Hardware platform error: %s\n", msg);
 	if (regs)
 		show_regs(regs);
 	smp_send_stop();
-	printk_safe_flush_on_panic();
-	kmsg_dump(KMSG_DUMP_PANIC);
-	bust_spinlocks(0);
-	debug_locks_off();
-	console_flush_on_panic();
+
+	panic_flush_kmsg_end();
 
 	/*
 	 * Don't bother to shut things down because this will
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 749055553064..496e47696ed0 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -54,7 +54,8 @@
 #define POWERNV_IOMMU_DEFAULT_LEVELS	1
 #define POWERNV_IOMMU_MAX_LEVELS	5
 
-static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU" };
+static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK",
+					      "NPU_OCAPI" };
 static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl);
 
 void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
@@ -89,6 +90,7 @@ void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 }
 
 static bool pnv_iommu_bypass_disabled __read_mostly;
+static bool pci_reset_phbs __read_mostly;
 
 static int __init iommu_setup(char *str)
 {
@@ -110,6 +112,14 @@ static int __init iommu_setup(char *str)
 }
 early_param("iommu", iommu_setup);
 
+static int __init pci_reset_phbs_setup(char *str)
+{
+	pci_reset_phbs = true;
+	return 0;
+}
+
+early_param("ppc_pci_reset_phbs", pci_reset_phbs_setup);
+
 static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r)
 {
 	/*
@@ -924,7 +934,7 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 	 * Configure PELTV. NPUs don't have a PELTV table so skip
 	 * configuration on them.
 	 */
-	if (phb->type != PNV_PHB_NPU)
+	if (phb->type != PNV_PHB_NPU_NVLINK && phb->type != PNV_PHB_NPU_OCAPI)
 		pnv_ioda_set_peltv(phb, pe, true);
 
 	/* Setup reverse map */
@@ -1059,8 +1069,8 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 
 	pe = pnv_ioda_alloc_pe(phb);
 	if (!pe) {
-		pr_warning("%s: Not enough PE# available, disabling device\n",
-			   pci_name(dev));
+		pr_warn("%s: Not enough PE# available, disabling device\n",
+			pci_name(dev));
 		return NULL;
 	}
 
@@ -1072,7 +1082,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 	 * At some point we want to remove the PDN completely anyways
 	 */
 	pci_dev_get(dev);
-	pdn->pcidev = dev;
 	pdn->pe_number = pe->pe_number;
 	pe->flags = PNV_IODA_PE_DEV;
 	pe->pdev = dev;
@@ -1119,7 +1128,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
 			continue;
 
 		pe->device_count++;
-		pdn->pcidev = dev;
 		pdn->pe_number = pe->pe_number;
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
 			pnv_ioda_setup_same_PE(dev->subordinate, pe);
@@ -1164,7 +1172,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 		pe = pnv_ioda_alloc_pe(phb);
 
 	if (!pe) {
-		pr_warning("%s: Not enough PE# available for PCI bus %04x:%02x\n",
+		pr_warn("%s: Not enough PE# available for PCI bus %04x:%02x\n",
 			__func__, pci_domain_nr(bus), bus->number);
 		return NULL;
 	}
@@ -1234,7 +1242,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
 			pci_dev_get(npu_pdev);
 			npu_pdn = pci_get_pdn(npu_pdev);
 			rid = npu_pdev->bus->number << 8 | npu_pdn->devfn;
-			npu_pdn->pcidev = npu_pdev;
 			npu_pdn->pe_number = pe_num;
 			phb->ioda.pe_rmap[rid] = pe->pe_number;
 
@@ -1272,16 +1279,23 @@ static void pnv_pci_ioda_setup_PEs(void)
 {
 	struct pci_controller *hose, *tmp;
 	struct pnv_phb *phb;
+	struct pci_bus *bus;
+	struct pci_dev *pdev;
 
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
 		phb = hose->private_data;
-		if (phb->type == PNV_PHB_NPU) {
+		if (phb->type == PNV_PHB_NPU_NVLINK) {
 			/* PE#0 is needed for error reporting */
 			pnv_ioda_reserve_pe(phb, 0);
 			pnv_ioda_setup_npu_PEs(hose->bus);
 			if (phb->model == PNV_PHB_MODEL_NPU2)
 				pnv_npu2_init(phb);
 		}
+		if (phb->type == PNV_PHB_NPU_OCAPI) {
+			bus = hose->bus;
+			list_for_each_entry(pdev, &bus->devices, bus_list)
+				pnv_ioda_setup_dev_PE(pdev);
+		}
 	}
 }
 
@@ -1692,7 +1706,7 @@ m64_failed:
 	return ret;
 }
 
-int pcibios_sriov_disable(struct pci_dev *pdev)
+int pnv_pcibios_sriov_disable(struct pci_dev *pdev)
 {
 	pnv_pci_sriov_disable(pdev);
 
@@ -1701,7 +1715,7 @@ int pcibios_sriov_disable(struct pci_dev *pdev)
 	return 0;
 }
 
-int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
 {
 	/* Allocate PCI data */
 	add_dev_pci_data(pdev);
@@ -1850,7 +1864,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 
 	if (bypass) {
 		dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n");
-		set_dma_ops(&pdev->dev, &dma_direct_ops);
+		set_dma_ops(&pdev->dev, &dma_nommu_ops);
 	} else {
 		/*
 		 * If the device can't set the TCE bypass bit but still wants
@@ -1868,7 +1882,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 				return rc;
 			/* 4GB offset bypasses 32-bit space */
 			set_dma_offset(&pdev->dev, (1ULL << 32));
-			set_dma_ops(&pdev->dev, &dma_direct_ops);
+			set_dma_ops(&pdev->dev, &dma_nommu_ops);
 		} else if (dma_mask >> 32 && dma_mask != DMA_BIT_MASK(64)) {
 			/*
 			 * Fail the request if a DMA mask between 32 and 64 bits
@@ -2572,7 +2586,6 @@ static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
 	unsigned long direct_table_size;
 
 	if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS) ||
-			(window_size > memory_hotplug_max()) ||
 			!is_power_of_2(window_size))
 		return 0;
 
@@ -2640,7 +2653,7 @@ static int gpe_table_group_to_npe_cb(struct device *dev, void *opaque)
 
 	hose = pci_bus_to_host(pdev->bus);
 	phb = hose->private_data;
-	if (phb->type != PNV_PHB_NPU)
+	if (phb->type != PNV_PHB_NPU_NVLINK)
 		return 0;
 
 	*ptmppe = &phb->ioda.pe_array[pdn->pe_number];
@@ -2724,7 +2737,7 @@ static void pnv_pci_ioda_setup_iommu_api(void)
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
 		phb = hose->private_data;
 
-		if (phb->type != PNV_PHB_NPU)
+		if (phb->type != PNV_PHB_NPU_NVLINK)
 			continue;
 
 		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
@@ -3293,7 +3306,7 @@ static void pnv_pci_ioda_create_dbgfs(void)
 		sprintf(name, "PCI%04x", hose->global_number);
 		phb->dbgfs = debugfs_create_dir(name, powerpc_debugfs_root);
 		if (!phb->dbgfs) {
-			pr_warning("%s: Error on creating debugfs on PHB#%x\n",
+			pr_warn("%s: Error on creating debugfs on PHB#%x\n",
 				__func__, hose->global_number);
 			continue;
 		}
@@ -3774,6 +3787,13 @@ static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
 	.shutdown		= pnv_pci_ioda_shutdown,
 };
 
+static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {
+	.enable_device_hook	= pnv_pci_enable_device_hook,
+	.window_alignment	= pnv_pci_window_alignment,
+	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
+	.shutdown		= pnv_pci_ioda_shutdown,
+};
+
 #ifdef CONFIG_CXL_BASE
 const struct pci_controller_ops pnv_cxl_cx4_ioda_controller_ops = {
 	.dma_dev_setup		= pnv_pci_dma_dev_setup,
@@ -4007,9 +4027,14 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	 */
 	ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
 
-	if (phb->type == PNV_PHB_NPU) {
+	switch (phb->type) {
+	case PNV_PHB_NPU_NVLINK:
 		hose->controller_ops = pnv_npu_ioda_controller_ops;
-	} else {
+		break;
+	case PNV_PHB_NPU_OCAPI:
+		hose->controller_ops = pnv_npu_ocapi_ioda_controller_ops;
+		break;
+	default:
 		phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
 		hose->controller_ops = pnv_pci_ioda_controller_ops;
 	}
@@ -4019,6 +4044,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 #ifdef CONFIG_PCI_IOV
 	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
 	ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment;
+	ppc_md.pcibios_sriov_enable = pnv_pcibios_sriov_enable;
+	ppc_md.pcibios_sriov_disable = pnv_pcibios_sriov_disable;
 #endif
 
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
@@ -4026,15 +4053,16 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	/* Reset IODA tables to a clean state */
 	rc = opal_pci_reset(phb_id, OPAL_RESET_PCI_IODA_TABLE, OPAL_ASSERT_RESET);
 	if (rc)
-		pr_warning("  OPAL Error %ld performing IODA table reset !\n", rc);
+		pr_warn("  OPAL Error %ld performing IODA table reset !\n", rc);
 
 	/*
 	 * If we're running in kdump kernel, the previous kernel never
 	 * shutdown PCI devices correctly. We already got IODA table
 	 * cleaned out. So we have to issue PHB reset to stop all PCI
-	 * transactions from previous kernel.
+	 * transactions from previous kernel. The ppc_pci_reset_phbs
+	 * kernel parameter will force this reset too.
 	 */
-	if (is_kdump_kernel()) {
+	if (is_kdump_kernel() || pci_reset_phbs) {
 		pr_info("  Issue PHB reset ...\n");
 		pnv_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL);
 		pnv_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE);
@@ -4052,8 +4080,26 @@ void __init pnv_pci_init_ioda2_phb(struct device_node *np)
 
 void __init pnv_pci_init_npu_phb(struct device_node *np)
 {
-	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU);
+	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU_NVLINK);
+}
+
+void __init pnv_pci_init_npu2_opencapi_phb(struct device_node *np)
+{
+	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU_OCAPI);
+}
+
+static void pnv_npu2_opencapi_cfg_size_fixup(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	if (!machine_is(powernv))
+		return;
+
+	if (phb->type == PNV_PHB_NPU_OCAPI)
+		dev->cfg_size = PCI_CFG_SPACE_EXP_SIZE;
 }
+DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, pnv_npu2_opencapi_cfg_size_fixup);
 
 void __init pnv_pci_init_ioda_hub(struct device_node *np)
 {
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 5422f4a6317c..69d102cbf48f 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -1142,6 +1142,10 @@ void __init pnv_pci_init(void)
 	for_each_compatible_node(np, NULL, "ibm,ioda2-npu2-phb")
 		pnv_pci_init_npu_phb(np);
 
+	/* Look for NPU2 OpenCAPI PHBs */
+	for_each_compatible_node(np, NULL, "ibm,ioda2-npu2-opencapi-phb")
+		pnv_pci_init_npu2_opencapi_phb(np);
+
 	/* Configure IOMMU DMA hooks */
 	set_pci_dma_ops(&dma_iommu_ops);
 }
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index b772d7473896..eada4b6068cb 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -12,9 +12,10 @@ struct pci_dn;
 #define NV_NMMU_ATSD_REGS 8
 
 enum pnv_phb_type {
-	PNV_PHB_IODA1	= 0,
-	PNV_PHB_IODA2	= 1,
-	PNV_PHB_NPU	= 2,
+	PNV_PHB_IODA1		= 0,
+	PNV_PHB_IODA2		= 1,
+	PNV_PHB_NPU_NVLINK	= 2,
+	PNV_PHB_NPU_OCAPI	= 3,
 };
 
 /* Precise PHB model for error management */
@@ -227,6 +228,7 @@ extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 extern void pnv_pci_init_ioda_hub(struct device_node *np);
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_init_npu_phb(struct device_node *np);
+extern void pnv_pci_init_npu2_opencapi_phb(struct device_node *np);
 extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 1edfbc1e40f4..4fb21e17504a 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -37,13 +37,62 @@
 #include <asm/kexec.h>
 #include <asm/smp.h>
 #include <asm/tm.h>
+#include <asm/setup.h>
 
 #include "powernv.h"
 
+static void pnv_setup_rfi_flush(void)
+{
+	struct device_node *np, *fw_features;
+	enum l1d_flush_type type;
+	int enable;
+
+	/* Default to fallback in case fw-features are not available */
+	type = L1D_FLUSH_FALLBACK;
+	enable = 1;
+
+	np = of_find_node_by_name(NULL, "ibm,opal");
+	fw_features = of_get_child_by_name(np, "fw-features");
+	of_node_put(np);
+
+	if (fw_features) {
+		np = of_get_child_by_name(fw_features, "inst-l1d-flush-trig2");
+		if (np && of_property_read_bool(np, "enabled"))
+			type = L1D_FLUSH_MTTRIG;
+
+		of_node_put(np);
+
+		np = of_get_child_by_name(fw_features, "inst-l1d-flush-ori30,30,0");
+		if (np && of_property_read_bool(np, "enabled"))
+			type = L1D_FLUSH_ORI;
+
+		of_node_put(np);
+
+		/* Enable unless firmware says NOT to */
+		enable = 2;
+		np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-hv-1-to-0");
+		if (np && of_property_read_bool(np, "disabled"))
+			enable--;
+
+		of_node_put(np);
+
+		np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-pr-0-to-1");
+		if (np && of_property_read_bool(np, "disabled"))
+			enable--;
+
+		of_node_put(np);
+		of_node_put(fw_features);
+	}
+
+	setup_rfi_flush(type, enable > 0);
+}
+
 static void __init pnv_setup_arch(void)
 {
 	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
 
+	pnv_setup_rfi_flush();
+
 	/* Initialize SMP */
 	pnv_smp_init();
 
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index ba030669eca1..9664c8461f03 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -37,6 +37,8 @@
 #include <asm/kvm_ppc.h>
 #include <asm/ppc-opcode.h>
 #include <asm/cpuidle.h>
+#include <asm/kexec.h>
+#include <asm/reg.h>
 
 #include "powernv.h"
 
@@ -209,9 +211,32 @@ static void pnv_smp_cpu_kill_self(void)
 		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
 			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
+		} else if ((srr1 & wmask) == SRR1_WAKERESET) {
+			irq_set_pending_from_srr1(srr1);
+			/* Does not return */
 		}
+
 		smp_mb();
 
+		/*
+		 * For kdump kernels, we process the ipi and jump to
+		 * crash_ipi_callback
+		 */
+		if (kdump_in_progress()) {
+			/*
+			 * If we got to this point, we've not used
+			 * NMI's, otherwise we would have gone
+			 * via the SRR1_WAKERESET path. We are
+			 * using regular IPI's for waking up offline
+			 * threads.
+			 */
+			struct pt_regs regs;
+
+			ppc_save_regs(&regs);
+			crash_ipi_callback(&regs);
+			/* Does not return */
+		}
+
 		if (cpu_core_split_required())
 			continue;
 
@@ -371,5 +396,8 @@ void __init pnv_smp_init(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 	ppc_md.cpu_die	= pnv_smp_cpu_kill_self;
+#ifdef CONFIG_KEXEC_CORE
+	crash_wake_offline = 1;
+#endif
 #endif
 }
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index e48462447ff0..e7075aaff1bb 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -663,8 +663,8 @@ static void ps3_find_and_add_device(u64 bus_id, u64 dev_id)
 		if (rem)
 			break;
 	}
-	pr_warning("%s:%u: device %llu:%llu not found\n", __func__, __LINE__,
-		   bus_id, dev_id);
+	pr_warn("%s:%u: device %llu:%llu not found\n",
+		__func__, __LINE__, bus_id, dev_id);
 	return;
 
 found:
@@ -859,11 +859,9 @@ static int ps3_probe_thread(void *data)
 
 		if (notify_event->event_type != notify_region_probe ||
 		    notify_event->bus_id != dev.sbd.bus_id) {
-			pr_warning("%s:%u: bad notify_event: event %llu, "
-				   "dev_id %llu, dev_type %llu\n",
-				   __func__, __LINE__, notify_event->event_type,
-				   notify_event->dev_id,
-				   notify_event->dev_type);
+			pr_warn("%s:%u: bad notify_event: event %llu, dev_id %llu, dev_type %llu\n",
+				__func__, __LINE__, notify_event->event_type,
+				notify_event->dev_id, notify_event->dev_type);
 			continue;
 		}
 
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index b0f34663b1ae..7f870ec29daf 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -607,8 +607,8 @@ static int dma_ioc0_map_pages(struct ps3_dma_region *r, unsigned long phys_addr,
 				       r->ioid,
 				       iopte_flag);
 		if (result) {
-			pr_warning("%s:%d: lv1_put_iopte failed: %s\n",
-				   __func__, __LINE__, ps3_result(result));
+			pr_warn("%s:%d: lv1_put_iopte failed: %s\n",
+				__func__, __LINE__, ps3_result(result));
 			goto fail_map;
 		}
 		DBG("%s: pg=%d bus=%#lx, lpar=%#lx, ioid=%#x\n", __func__,
diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c
index 3db53e8aff92..cdbfc5cfd6f3 100644
--- a/arch/powerpc/platforms/ps3/os-area.c
+++ b/arch/powerpc/platforms/ps3/os-area.c
@@ -699,7 +699,7 @@ static void os_area_queue_work_handler(struct work_struct *work)
 
 	error = update_flash_db();
 	if (error)
-		pr_warning("%s: Could not update FLASH ROM\n", __func__);
+		pr_warn("%s: Could not update FLASH ROM\n", __func__);
 
 	pr_debug(" <- %s:%d\n", __func__, __LINE__);
 }
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 9dabea6e1443..77a37520068d 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -104,6 +104,21 @@ static void __noreturn ps3_halt(void)
 	ps3_sys_manager_halt(); /* never returns */
 }
 
+static void ps3_panic(char *str)
+{
+	DBG("%s:%d %s\n", __func__, __LINE__, str);
+
+	smp_send_stop();
+	printk("\n");
+	printk("   System does not reboot automatically.\n");
+	printk("   Please press POWER button.\n");
+	printk("\n");
+	panic_flush_kmsg_end();
+
+	while(1)
+		lv1_pause(1);
+}
+
 #if defined(CONFIG_FB_PS3) || defined(CONFIG_FB_PS3_MODULE) || \
     defined(CONFIG_PS3_FLASH) || defined(CONFIG_PS3_FLASH_MODULE)
 static void __init prealloc(struct ps3_prealloc *p)
@@ -255,6 +270,7 @@ define_machine(ps3) {
 	.probe				= ps3_probe,
 	.setup_arch			= ps3_setup_arch,
 	.init_IRQ			= ps3_init_IRQ,
+	.panic				= ps3_panic,
 	.get_boot_time			= ps3_get_boot_time,
 	.set_dabr			= ps3_set_dabr,
 	.calibrate_decr			= ps3_calibrate_decr,
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index 560aefde06c0..25427a48feae 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -72,20 +72,20 @@ MODULE_DESCRIPTION("IBM System p Collaborative Memory Manager");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(CMM_DRIVER_VERSION);
 
-module_param_named(delay, delay, uint, S_IRUGO | S_IWUSR);
+module_param_named(delay, delay, uint, 0644);
 MODULE_PARM_DESC(delay, "Delay (in seconds) between polls to query hypervisor paging requests. "
 		 "[Default=" __stringify(CMM_DEFAULT_DELAY) "]");
-module_param_named(hotplug_delay, hotplug_delay, uint, S_IRUGO | S_IWUSR);
+module_param_named(hotplug_delay, hotplug_delay, uint, 0644);
 MODULE_PARM_DESC(hotplug_delay, "Delay (in seconds) after memory hotplug remove "
 		 "before loaning resumes. "
 		 "[Default=" __stringify(CMM_HOTPLUG_DELAY) "]");
-module_param_named(oom_kb, oom_kb, uint, S_IRUGO | S_IWUSR);
+module_param_named(oom_kb, oom_kb, uint, 0644);
 MODULE_PARM_DESC(oom_kb, "Amount of memory in kb to free on OOM. "
 		 "[Default=" __stringify(CMM_OOM_KB) "]");
-module_param_named(min_mem_mb, min_mem_mb, ulong, S_IRUGO | S_IWUSR);
+module_param_named(min_mem_mb, min_mem_mb, ulong, 0644);
 MODULE_PARM_DESC(min_mem_mb, "Minimum amount of memory (in MB) to not balloon. "
 		 "[Default=" __stringify(CMM_MIN_MEM_MB) "]");
-module_param_named(debug, cmm_debug, uint, S_IRUGO | S_IWUSR);
+module_param_named(debug, cmm_debug, uint, 0644);
 MODULE_PARM_DESC(debug, "Enable module debugging logging. Set to 1 to enable. "
 		 "[Default=" __stringify(CMM_DEBUG) "]");
 
@@ -385,7 +385,7 @@ static int cmm_thread(void *dummy)
 	{							\
 		return sprintf(buf, format, ##args);		\
 	}							\
-	static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
+	static DEVICE_ATTR(name, 0444, show_##name, NULL)
 
 CMM_SHOW(loaned_kb, "%lu\n", PAGES2KB(loaned_pages));
 CMM_SHOW(loaned_target_kb, "%lu\n", PAGES2KB(loaned_pages_target));
@@ -411,7 +411,7 @@ static ssize_t store_oom_pages(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(oom_freed_kb, S_IWUSR | S_IRUGO,
+static DEVICE_ATTR(oom_freed_kb, 0644,
 		   show_oom_pages, store_oom_pages);
 
 static struct device_attribute *cmm_attrs[] = {
@@ -765,7 +765,7 @@ static int cmm_set_disable(const char *val, const struct kernel_param *kp)
 }
 
 module_param_call(disable, cmm_set_disable, param_get_uint,
-		  &cmm_disabled, S_IRUGO | S_IWUSR);
+		  &cmm_disabled, 0644);
 MODULE_PARM_DESC(disable, "Disable CMM. Set to 1 to disable. "
 		 "[Default=" __stringify(CMM_DISABLE) "]");
 
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 6e35780c5962..a0b20c03f078 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -574,11 +574,26 @@ static ssize_t dlpar_show(struct class *class, struct class_attribute *attr,
 
 static CLASS_ATTR_RW(dlpar);
 
-static int __init pseries_dlpar_init(void)
+int __init dlpar_workqueue_init(void)
 {
+	if (pseries_hp_wq)
+		return 0;
+
 	pseries_hp_wq = alloc_workqueue("pseries hotplug workqueue",
-					WQ_UNBOUND, 1);
+			WQ_UNBOUND, 1);
+
+	return pseries_hp_wq ? 0 : -ENOMEM;
+}
+
+static int __init dlpar_sysfs_init(void)
+{
+	int rc;
+
+	rc = dlpar_workqueue_init();
+	if (rc)
+		return rc;
+
 	return sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr);
 }
-machine_device_initcall(pseries, pseries_dlpar_init);
+machine_device_initcall(pseries, dlpar_sysfs_init);
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 6b812ad990e4..823cb27efa8b 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -55,6 +55,43 @@ static int ibm_get_config_addr_info;
 static int ibm_get_config_addr_info2;
 static int ibm_configure_pe;
 
+#ifdef CONFIG_PCI_IOV
+void pseries_pcibios_bus_add_device(struct pci_dev *pdev)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	struct pci_dn *physfn_pdn;
+	struct eeh_dev *edev;
+
+	if (!pdev->is_virtfn)
+		return;
+
+	pdn->device_id  =  pdev->device;
+	pdn->vendor_id  =  pdev->vendor;
+	pdn->class_code =  pdev->class;
+	/*
+	 * Last allow unfreeze return code used for retrieval
+	 * by user space in eeh-sysfs to show the last command
+	 * completion from platform.
+	 */
+	pdn->last_allow_rc =  0;
+	physfn_pdn      =  pci_get_pdn(pdev->physfn);
+	pdn->pe_number  =  physfn_pdn->pe_num_map[pdn->vf_index];
+	edev = pdn_to_eeh_dev(pdn);
+
+	/*
+	 * The following operations will fail if VF's sysfs files
+	 * aren't created or its resources aren't finalized.
+	 */
+	eeh_add_device_early(pdn);
+	eeh_add_device_late(pdev);
+	edev->pe_config_addr =  (pdn->busno << 16) | (pdn->devfn << 8);
+	eeh_rmv_from_parent_pe(edev); /* Remove as it is adding to bus pe */
+	eeh_add_to_parent_pe(edev);   /* Add as VF PE type */
+	eeh_sysfs_add_device(pdev);
+
+}
+#endif
+
 /*
  * Buffer for reporting slot-error-detail rtas calls. Its here
  * in BSS, and not dynamically alloced, so that it ends up in
@@ -120,6 +157,11 @@ static int pseries_eeh_init(void)
 	/* Set EEH probe mode */
 	eeh_add_flag(EEH_PROBE_MODE_DEVTREE | EEH_ENABLE_IO_FOR_LOG);
 
+#ifdef CONFIG_PCI_IOV
+	/* Set EEH machine dependent code */
+	ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device;
+#endif
+
 	return 0;
 }
 
@@ -684,6 +726,121 @@ static int pseries_eeh_write_config(struct pci_dn *pdn, int where, int size, u32
 	return rtas_write_config(pdn, where, size, val);
 }
 
+static int pseries_eeh_restore_config(struct pci_dn *pdn)
+{
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+	s64 ret = 0;
+
+	if (!edev)
+		return -EEXIST;
+
+	/*
+	 * FIXME: The MPS, error routing rules, timeout setting are worthy
+	 * to be exported by firmware in extendible way.
+	 */
+	if (edev->physfn)
+		ret = eeh_restore_vf_config(pdn);
+
+	if (ret) {
+		pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n",
+			__func__, edev->pe_config_addr, ret);
+		return -EIO;
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_PCI_IOV
+int pseries_send_allow_unfreeze(struct pci_dn *pdn,
+				u16 *vf_pe_array, int cur_vfs)
+{
+	int rc;
+	int ibm_allow_unfreeze = rtas_token("ibm,open-sriov-allow-unfreeze");
+	unsigned long buid, addr;
+
+	addr = rtas_config_addr(pdn->busno, pdn->devfn, 0);
+	buid = pdn->phb->buid;
+	spin_lock(&rtas_data_buf_lock);
+	memcpy(rtas_data_buf, vf_pe_array, RTAS_DATA_BUF_SIZE);
+	rc = rtas_call(ibm_allow_unfreeze, 5, 1, NULL,
+		       addr,
+		       BUID_HI(buid),
+		       BUID_LO(buid),
+		       rtas_data_buf, cur_vfs * sizeof(u16));
+	spin_unlock(&rtas_data_buf_lock);
+	if (rc)
+		pr_warn("%s: Failed to allow unfreeze for PHB#%x-PE#%lx, rc=%x\n",
+			__func__,
+			pdn->phb->global_number, addr, rc);
+	return rc;
+}
+
+static int pseries_call_allow_unfreeze(struct eeh_dev *edev)
+{
+	struct pci_dn *pdn, *tmp, *parent, *physfn_pdn;
+	int cur_vfs = 0, rc = 0, vf_index, bus, devfn;
+	u16 *vf_pe_array;
+
+	vf_pe_array = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL);
+	if (!vf_pe_array)
+		return -ENOMEM;
+	if (pci_num_vf(edev->physfn ? edev->physfn : edev->pdev)) {
+		if (edev->pdev->is_physfn) {
+			cur_vfs = pci_num_vf(edev->pdev);
+			pdn = eeh_dev_to_pdn(edev);
+			parent = pdn->parent;
+			for (vf_index = 0; vf_index < cur_vfs; vf_index++)
+				vf_pe_array[vf_index] =
+					cpu_to_be16(pdn->pe_num_map[vf_index]);
+			rc = pseries_send_allow_unfreeze(pdn, vf_pe_array,
+							 cur_vfs);
+			pdn->last_allow_rc = rc;
+			for (vf_index = 0; vf_index < cur_vfs; vf_index++) {
+				list_for_each_entry_safe(pdn, tmp,
+							 &parent->child_list,
+							 list) {
+					bus = pci_iov_virtfn_bus(edev->pdev,
+								 vf_index);
+					devfn = pci_iov_virtfn_devfn(edev->pdev,
+								     vf_index);
+					if (pdn->busno != bus ||
+					    pdn->devfn != devfn)
+						continue;
+					pdn->last_allow_rc = rc;
+				}
+			}
+		} else {
+			pdn = pci_get_pdn(edev->pdev);
+			vf_pe_array[0] = cpu_to_be16(pdn->pe_number);
+			physfn_pdn = pci_get_pdn(edev->physfn);
+			rc = pseries_send_allow_unfreeze(physfn_pdn,
+							 vf_pe_array, 1);
+			pdn->last_allow_rc = rc;
+		}
+	}
+
+	kfree(vf_pe_array);
+	return rc;
+}
+
+static int pseries_notify_resume(struct pci_dn *pdn)
+{
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+
+	if (!edev)
+		return -EEXIST;
+
+	if (rtas_token("ibm,open-sriov-allow-unfreeze")
+	    == RTAS_UNKNOWN_SERVICE)
+		return -EINVAL;
+
+	if (edev->pdev->is_physfn || edev->pdev->is_virtfn)
+		return pseries_call_allow_unfreeze(edev);
+
+	return 0;
+}
+#endif
+
 static struct eeh_ops pseries_eeh_ops = {
 	.name			= "pseries",
 	.init			= pseries_eeh_init,
@@ -699,7 +856,10 @@ static struct eeh_ops pseries_eeh_ops = {
 	.read_config		= pseries_eeh_read_config,
 	.write_config		= pseries_eeh_write_config,
 	.next_error		= NULL,
-	.restore_config		= NULL
+	.restore_config		= pseries_eeh_restore_config,
+#ifdef CONFIG_PCI_IOV
+	.notify_resume		= pseries_notify_resume
+#endif
 };
 
 /**
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index 63cc82ad58ac..a3bbeb43689e 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -114,6 +114,8 @@ static __initdata struct vec5_fw_feature
 vec5_fw_features_table[] = {
 	{FW_FEATURE_TYPE1_AFFINITY,	OV5_TYPE1_AFFINITY},
 	{FW_FEATURE_PRRN,		OV5_PRRN},
+	{FW_FEATURE_DRMEM_V2,		OV5_DRMEM_V2},
+	{FW_FEATURE_DRC_INFO,		OV5_DRC_INFO},
 };
 
 static void __init fw_vec5_feature_init(const char *vec5, unsigned long len)
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index a7d14aa7bb7c..dceb51454d8d 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -340,6 +340,8 @@ static void pseries_remove_processor(struct device_node *np)
 	cpu_maps_update_done();
 }
 
+extern int find_and_online_cpu_nid(int cpu);
+
 static int dlpar_online_cpu(struct device_node *dn)
 {
 	int rc = 0;
@@ -364,6 +366,7 @@ static int dlpar_online_cpu(struct device_node *dn)
 					!= CPU_STATE_OFFLINE);
 			cpu_maps_update_done();
 			timed_topology_update(1);
+			find_and_online_cpu_nid(cpu);
 			rc = device_online(get_cpu_device(cpu));
 			if (rc)
 				goto out;
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 1d48ab424bd9..c1578f54c626 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -23,6 +23,7 @@
 #include <asm/prom.h>
 #include <asm/sparsemem.h>
 #include <asm/fadump.h>
+#include <asm/drmem.h>
 #include "pseries.h"
 
 static bool rtas_hp_event;
@@ -100,100 +101,6 @@ static struct property *dlpar_clone_property(struct property *prop,
 	return new_prop;
 }
 
-static struct property *dlpar_clone_drconf_property(struct device_node *dn)
-{
-	struct property *prop, *new_prop;
-	struct of_drconf_cell *lmbs;
-	u32 num_lmbs, *p;
-	int i;
-
-	prop = of_find_property(dn, "ibm,dynamic-memory", NULL);
-	if (!prop)
-		return NULL;
-
-	new_prop = dlpar_clone_property(prop, prop->length);
-	if (!new_prop)
-		return NULL;
-
-	/* Convert the property to cpu endian-ness */
-	p = new_prop->value;
-	*p = be32_to_cpu(*p);
-
-	num_lmbs = *p++;
-	lmbs = (struct of_drconf_cell *)p;
-
-	for (i = 0; i < num_lmbs; i++) {
-		lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr);
-		lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index);
-		lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index);
-		lmbs[i].flags = be32_to_cpu(lmbs[i].flags);
-	}
-
-	return new_prop;
-}
-
-static void dlpar_update_drconf_property(struct device_node *dn,
-					 struct property *prop)
-{
-	struct of_drconf_cell *lmbs;
-	u32 num_lmbs, *p;
-	int i;
-
-	/* Convert the property back to BE */
-	p = prop->value;
-	num_lmbs = *p;
-	*p = cpu_to_be32(*p);
-	p++;
-
-	lmbs = (struct of_drconf_cell *)p;
-	for (i = 0; i < num_lmbs; i++) {
-		lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr);
-		lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index);
-		lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index);
-		lmbs[i].flags = cpu_to_be32(lmbs[i].flags);
-	}
-
-	rtas_hp_event = true;
-	of_update_property(dn, prop);
-	rtas_hp_event = false;
-}
-
-static int dlpar_update_device_tree_lmb(struct of_drconf_cell *lmb)
-{
-	struct device_node *dn;
-	struct property *prop;
-	struct of_drconf_cell *lmbs;
-	u32 *p, num_lmbs;
-	int i;
-
-	dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
-	if (!dn)
-		return -ENODEV;
-
-	prop = dlpar_clone_drconf_property(dn);
-	if (!prop) {
-		of_node_put(dn);
-		return -ENODEV;
-	}
-
-	p = prop->value;
-	num_lmbs = *p++;
-	lmbs = (struct of_drconf_cell *)p;
-
-	for (i = 0; i < num_lmbs; i++) {
-		if (lmbs[i].drc_index == lmb->drc_index) {
-			lmbs[i].flags = lmb->flags;
-			lmbs[i].aa_index = lmb->aa_index;
-
-			dlpar_update_drconf_property(dn, prop);
-			break;
-		}
-	}
-
-	of_node_put(dn);
-	return 0;
-}
-
 static u32 find_aa_index(struct device_node *dr_node,
 			 struct property *ala_prop, const u32 *lmb_assoc)
 {
@@ -256,7 +163,7 @@ static u32 find_aa_index(struct device_node *dr_node,
 	return aa_index;
 }
 
-static u32 lookup_lmb_associativity_index(struct of_drconf_cell *lmb)
+static u32 lookup_lmb_associativity_index(struct drmem_lmb *lmb)
 {
 	struct device_node *parent, *lmb_node, *dr_node;
 	struct property *ala_prop;
@@ -299,9 +206,9 @@ static u32 lookup_lmb_associativity_index(struct of_drconf_cell *lmb)
 	return aa_index;
 }
 
-static int dlpar_add_device_tree_lmb(struct of_drconf_cell *lmb)
+static int dlpar_add_device_tree_lmb(struct drmem_lmb *lmb)
 {
-	int aa_index;
+	int rc, aa_index;
 
 	lmb->flags |= DRCONF_MEM_ASSIGNED;
 
@@ -313,17 +220,29 @@ static int dlpar_add_device_tree_lmb(struct of_drconf_cell *lmb)
 	}
 
 	lmb->aa_index = aa_index;
-	return dlpar_update_device_tree_lmb(lmb);
+
+	rtas_hp_event = true;
+	rc = drmem_update_dt();
+	rtas_hp_event = false;
+
+	return rc;
 }
 
-static int dlpar_remove_device_tree_lmb(struct of_drconf_cell *lmb)
+static int dlpar_remove_device_tree_lmb(struct drmem_lmb *lmb)
 {
+	int rc;
+
 	lmb->flags &= ~DRCONF_MEM_ASSIGNED;
 	lmb->aa_index = 0xffffffff;
-	return dlpar_update_device_tree_lmb(lmb);
+
+	rtas_hp_event = true;
+	rc = drmem_update_dt();
+	rtas_hp_event = false;
+
+	return rc;
 }
 
-static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb)
+static struct memory_block *lmb_to_memblock(struct drmem_lmb *lmb)
 {
 	unsigned long section_nr;
 	struct mem_section *mem_sect;
@@ -336,7 +255,36 @@ static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb)
 	return mem_block;
 }
 
-static int dlpar_change_lmb_state(struct of_drconf_cell *lmb, bool online)
+static int get_lmb_range(u32 drc_index, int n_lmbs,
+			 struct drmem_lmb **start_lmb,
+			 struct drmem_lmb **end_lmb)
+{
+	struct drmem_lmb *lmb, *start, *end;
+	struct drmem_lmb *last_lmb;
+
+	start = NULL;
+	for_each_drmem_lmb(lmb) {
+		if (lmb->drc_index == drc_index) {
+			start = lmb;
+			break;
+		}
+	}
+
+	if (!start)
+		return -EINVAL;
+
+	end = &start[n_lmbs - 1];
+
+	last_lmb = &drmem_info->lmbs[drmem_info->n_lmbs - 1];
+	if (end > last_lmb)
+		return -EINVAL;
+
+	*start_lmb = start;
+	*end_lmb = end;
+	return 0;
+}
+
+static int dlpar_change_lmb_state(struct drmem_lmb *lmb, bool online)
 {
 	struct memory_block *mem_block;
 	int rc;
@@ -357,13 +305,13 @@ static int dlpar_change_lmb_state(struct of_drconf_cell *lmb, bool online)
 	return rc;
 }
 
-static int dlpar_online_lmb(struct of_drconf_cell *lmb)
+static int dlpar_online_lmb(struct drmem_lmb *lmb)
 {
 	return dlpar_change_lmb_state(lmb, true);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static int dlpar_offline_lmb(struct of_drconf_cell *lmb)
+static int dlpar_offline_lmb(struct drmem_lmb *lmb)
 {
 	return dlpar_change_lmb_state(lmb, false);
 }
@@ -426,7 +374,7 @@ static int pseries_remove_mem_node(struct device_node *np)
 	return 0;
 }
 
-static bool lmb_is_removable(struct of_drconf_cell *lmb)
+static bool lmb_is_removable(struct drmem_lmb *lmb)
 {
 	int i, scns_per_block;
 	int rc = 1;
@@ -458,9 +406,9 @@ static bool lmb_is_removable(struct of_drconf_cell *lmb)
 	return rc ? true : false;
 }
 
-static int dlpar_add_lmb(struct of_drconf_cell *);
+static int dlpar_add_lmb(struct drmem_lmb *);
 
-static int dlpar_remove_lmb(struct of_drconf_cell *lmb)
+static int dlpar_remove_lmb(struct drmem_lmb *lmb)
 {
 	unsigned long block_sz;
 	int nid, rc;
@@ -484,28 +432,25 @@ static int dlpar_remove_lmb(struct of_drconf_cell *lmb)
 	return 0;
 }
 
-static int dlpar_memory_remove_by_count(u32 lmbs_to_remove,
-					struct property *prop)
+static int dlpar_memory_remove_by_count(u32 lmbs_to_remove)
 {
-	struct of_drconf_cell *lmbs;
+	struct drmem_lmb *lmb;
 	int lmbs_removed = 0;
 	int lmbs_available = 0;
-	u32 num_lmbs, *p;
-	int i, rc;
+	int rc;
 
 	pr_info("Attempting to hot-remove %d LMB(s)\n", lmbs_to_remove);
 
 	if (lmbs_to_remove == 0)
 		return -EINVAL;
 
-	p = prop->value;
-	num_lmbs = *p++;
-	lmbs = (struct of_drconf_cell *)p;
-
 	/* Validate that there are enough LMBs to satisfy the request */
-	for (i = 0; i < num_lmbs; i++) {
-		if (lmb_is_removable(&lmbs[i]))
+	for_each_drmem_lmb(lmb) {
+		if (lmb_is_removable(lmb))
 			lmbs_available++;
+
+		if (lmbs_available == lmbs_to_remove)
+			break;
 	}
 
 	if (lmbs_available < lmbs_to_remove) {
@@ -514,45 +459,47 @@ static int dlpar_memory_remove_by_count(u32 lmbs_to_remove,
 		return -EINVAL;
 	}
 
-	for (i = 0; i < num_lmbs && lmbs_removed < lmbs_to_remove; i++) {
-		rc = dlpar_remove_lmb(&lmbs[i]);
+	for_each_drmem_lmb(lmb) {
+		rc = dlpar_remove_lmb(lmb);
 		if (rc)
 			continue;
 
-		lmbs_removed++;
-
 		/* Mark this lmb so we can add it later if all of the
 		 * requested LMBs cannot be removed.
 		 */
-		lmbs[i].reserved = 1;
+		drmem_mark_lmb_reserved(lmb);
+
+		lmbs_removed++;
+		if (lmbs_removed == lmbs_to_remove)
+			break;
 	}
 
 	if (lmbs_removed != lmbs_to_remove) {
 		pr_err("Memory hot-remove failed, adding LMB's back\n");
 
-		for (i = 0; i < num_lmbs; i++) {
-			if (!lmbs[i].reserved)
+		for_each_drmem_lmb(lmb) {
+			if (!drmem_lmb_reserved(lmb))
 				continue;
 
-			rc = dlpar_add_lmb(&lmbs[i]);
+			rc = dlpar_add_lmb(lmb);
 			if (rc)
 				pr_err("Failed to add LMB back, drc index %x\n",
-				       lmbs[i].drc_index);
+				       lmb->drc_index);
 
-			lmbs[i].reserved = 0;
+			drmem_remove_lmb_reservation(lmb);
 		}
 
 		rc = -EINVAL;
 	} else {
-		for (i = 0; i < num_lmbs; i++) {
-			if (!lmbs[i].reserved)
+		for_each_drmem_lmb(lmb) {
+			if (!drmem_lmb_reserved(lmb))
 				continue;
 
-			dlpar_release_drc(lmbs[i].drc_index);
+			dlpar_release_drc(lmb->drc_index);
 			pr_info("Memory at %llx was hot-removed\n",
-				lmbs[i].base_addr);
+				lmb->base_addr);
 
-			lmbs[i].reserved = 0;
+			drmem_remove_lmb_reservation(lmb);
 		}
 		rc = 0;
 	}
@@ -560,26 +507,21 @@ static int dlpar_memory_remove_by_count(u32 lmbs_to_remove,
 	return rc;
 }
 
-static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop)
+static int dlpar_memory_remove_by_index(u32 drc_index)
 {
-	struct of_drconf_cell *lmbs;
-	u32 num_lmbs, *p;
+	struct drmem_lmb *lmb;
 	int lmb_found;
-	int i, rc;
+	int rc;
 
 	pr_info("Attempting to hot-remove LMB, drc index %x\n", drc_index);
 
-	p = prop->value;
-	num_lmbs = *p++;
-	lmbs = (struct of_drconf_cell *)p;
-
 	lmb_found = 0;
-	for (i = 0; i < num_lmbs; i++) {
-		if (lmbs[i].drc_index == drc_index) {
+	for_each_drmem_lmb(lmb) {
+		if (lmb->drc_index == drc_index) {
 			lmb_found = 1;
-			rc = dlpar_remove_lmb(&lmbs[i]);
+			rc = dlpar_remove_lmb(lmb);
 			if (!rc)
-				dlpar_release_drc(lmbs[i].drc_index);
+				dlpar_release_drc(lmb->drc_index);
 
 			break;
 		}
@@ -590,35 +532,30 @@ static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop)
 
 	if (rc)
 		pr_info("Failed to hot-remove memory at %llx\n",
-			lmbs[i].base_addr);
+			lmb->base_addr);
 	else
-		pr_info("Memory at %llx was hot-removed\n", lmbs[i].base_addr);
+		pr_info("Memory at %llx was hot-removed\n", lmb->base_addr);
 
 	return rc;
 }
 
-static int dlpar_memory_readd_by_index(u32 drc_index, struct property *prop)
+static int dlpar_memory_readd_by_index(u32 drc_index)
 {
-	struct of_drconf_cell *lmbs;
-	u32 num_lmbs, *p;
+	struct drmem_lmb *lmb;
 	int lmb_found;
-	int i, rc;
+	int rc;
 
 	pr_info("Attempting to update LMB, drc index %x\n", drc_index);
 
-	p = prop->value;
-	num_lmbs = *p++;
-	lmbs = (struct of_drconf_cell *)p;
-
 	lmb_found = 0;
-	for (i = 0; i < num_lmbs; i++) {
-		if (lmbs[i].drc_index == drc_index) {
+	for_each_drmem_lmb(lmb) {
+		if (lmb->drc_index == drc_index) {
 			lmb_found = 1;
-			rc = dlpar_remove_lmb(&lmbs[i]);
+			rc = dlpar_remove_lmb(lmb);
 			if (!rc) {
-				rc = dlpar_add_lmb(&lmbs[i]);
+				rc = dlpar_add_lmb(lmb);
 				if (rc)
-					dlpar_release_drc(lmbs[i].drc_index);
+					dlpar_release_drc(lmb->drc_index);
 			}
 			break;
 		}
@@ -629,20 +566,18 @@ static int dlpar_memory_readd_by_index(u32 drc_index, struct property *prop)
 
 	if (rc)
 		pr_info("Failed to update memory at %llx\n",
-			lmbs[i].base_addr);
+			lmb->base_addr);
 	else
-		pr_info("Memory at %llx was updated\n", lmbs[i].base_addr);
+		pr_info("Memory at %llx was updated\n", lmb->base_addr);
 
 	return rc;
 }
 
-static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index,
-				     struct property *prop)
+static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
 {
-	struct of_drconf_cell *lmbs;
-	u32 num_lmbs, *p;
-	int i, rc, start_lmb_found;
-	int lmbs_available = 0, start_index = 0, end_index;
+	struct drmem_lmb *lmb, *start_lmb, *end_lmb;
+	int lmbs_available = 0;
+	int rc;
 
 	pr_info("Attempting to hot-remove %u LMB(s) at %x\n",
 		lmbs_to_remove, drc_index);
@@ -650,29 +585,13 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index,
 	if (lmbs_to_remove == 0)
 		return -EINVAL;
 
-	p = prop->value;
-	num_lmbs = *p++;
-	lmbs = (struct of_drconf_cell *)p;
-	start_lmb_found = 0;
-
-	/* Navigate to drc_index */
-	while (start_index < num_lmbs) {
-		if (lmbs[start_index].drc_index == drc_index) {
-			start_lmb_found = 1;
-			break;
-		}
-
-		start_index++;
-	}
-
-	if (!start_lmb_found)
+	rc = get_lmb_range(drc_index, lmbs_to_remove, &start_lmb, &end_lmb);
+	if (rc)
 		return -EINVAL;
 
-	end_index = start_index + lmbs_to_remove;
-
 	/* Validate that there are enough LMBs to satisfy the request */
-	for (i = start_index; i < end_index; i++) {
-		if (lmbs[i].flags & DRCONF_MEM_RESERVED)
+	for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
+		if (lmb->flags & DRCONF_MEM_RESERVED)
 			break;
 
 		lmbs_available++;
@@ -681,42 +600,43 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index,
 	if (lmbs_available < lmbs_to_remove)
 		return -EINVAL;
 
-	for (i = start_index; i < end_index; i++) {
-		if (!(lmbs[i].flags & DRCONF_MEM_ASSIGNED))
+	for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
+		if (!(lmb->flags & DRCONF_MEM_ASSIGNED))
 			continue;
 
-		rc = dlpar_remove_lmb(&lmbs[i]);
+		rc = dlpar_remove_lmb(lmb);
 		if (rc)
 			break;
 
-		lmbs[i].reserved = 1;
+		drmem_mark_lmb_reserved(lmb);
 	}
 
 	if (rc) {
 		pr_err("Memory indexed-count-remove failed, adding any removed LMBs\n");
 
-		for (i = start_index; i < end_index; i++) {
-			if (!lmbs[i].reserved)
+
+		for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
+			if (!drmem_lmb_reserved(lmb))
 				continue;
 
-			rc = dlpar_add_lmb(&lmbs[i]);
+			rc = dlpar_add_lmb(lmb);
 			if (rc)
 				pr_err("Failed to add LMB, drc index %x\n",
-				       be32_to_cpu(lmbs[i].drc_index));
+				       lmb->drc_index);
 
-			lmbs[i].reserved = 0;
+			drmem_remove_lmb_reservation(lmb);
 		}
 		rc = -EINVAL;
 	} else {
-		for (i = start_index; i < end_index; i++) {
-			if (!lmbs[i].reserved)
+		for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
+			if (!drmem_lmb_reserved(lmb))
 				continue;
 
-			dlpar_release_drc(lmbs[i].drc_index);
+			dlpar_release_drc(lmb->drc_index);
 			pr_info("Memory at %llx (drc index %x) was hot-removed\n",
-				lmbs[i].base_addr, lmbs[i].drc_index);
+				lmb->base_addr, lmb->drc_index);
 
-			lmbs[i].reserved = 0;
+			drmem_remove_lmb_reservation(lmb);
 		}
 	}
 
@@ -737,32 +657,30 @@ static inline int dlpar_memory_remove(struct pseries_hp_errorlog *hp_elog)
 {
 	return -EOPNOTSUPP;
 }
-static int dlpar_remove_lmb(struct of_drconf_cell *lmb)
+static int dlpar_remove_lmb(struct drmem_lmb *lmb)
 {
 	return -EOPNOTSUPP;
 }
-static int dlpar_memory_remove_by_count(u32 lmbs_to_remove,
-					struct property *prop)
+static int dlpar_memory_remove_by_count(u32 lmbs_to_remove)
 {
 	return -EOPNOTSUPP;
 }
-static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop)
+static int dlpar_memory_remove_by_index(u32 drc_index)
 {
 	return -EOPNOTSUPP;
 }
-static int dlpar_memory_readd_by_index(u32 drc_index, struct property *prop)
+static int dlpar_memory_readd_by_index(u32 drc_index)
 {
 	return -EOPNOTSUPP;
 }
 
-static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index,
-				     struct property *prop)
+static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
 {
 	return -EOPNOTSUPP;
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
-static int dlpar_add_lmb(struct of_drconf_cell *lmb)
+static int dlpar_add_lmb(struct drmem_lmb *lmb)
 {
 	unsigned long block_sz;
 	int nid, rc;
@@ -801,77 +719,79 @@ static int dlpar_add_lmb(struct of_drconf_cell *lmb)
 	return rc;
 }
 
-static int dlpar_memory_add_by_count(u32 lmbs_to_add, struct property *prop)
+static int dlpar_memory_add_by_count(u32 lmbs_to_add)
 {
-	struct of_drconf_cell *lmbs;
-	u32 num_lmbs, *p;
+	struct drmem_lmb *lmb;
 	int lmbs_available = 0;
 	int lmbs_added = 0;
-	int i, rc;
+	int rc;
 
 	pr_info("Attempting to hot-add %d LMB(s)\n", lmbs_to_add);
 
 	if (lmbs_to_add == 0)
 		return -EINVAL;
 
-	p = prop->value;
-	num_lmbs = *p++;
-	lmbs = (struct of_drconf_cell *)p;
-
 	/* Validate that there are enough LMBs to satisfy the request */
-	for (i = 0; i < num_lmbs; i++) {
-		if (!(lmbs[i].flags & DRCONF_MEM_ASSIGNED))
+	for_each_drmem_lmb(lmb) {
+		if (!(lmb->flags & DRCONF_MEM_ASSIGNED))
 			lmbs_available++;
+
+		if (lmbs_available == lmbs_to_add)
+			break;
 	}
 
 	if (lmbs_available < lmbs_to_add)
 		return -EINVAL;
 
-	for (i = 0; i < num_lmbs && lmbs_to_add != lmbs_added; i++) {
-		if (lmbs[i].flags & DRCONF_MEM_ASSIGNED)
+	for_each_drmem_lmb(lmb) {
+		if (lmb->flags & DRCONF_MEM_ASSIGNED)
 			continue;
 
-		rc = dlpar_acquire_drc(lmbs[i].drc_index);
+		rc = dlpar_acquire_drc(lmb->drc_index);
 		if (rc)
 			continue;
 
-		rc = dlpar_add_lmb(&lmbs[i]);
+		rc = dlpar_add_lmb(lmb);
 		if (rc) {
-			dlpar_release_drc(lmbs[i].drc_index);
+			dlpar_release_drc(lmb->drc_index);
 			continue;
 		}
 
-		lmbs_added++;
-
 		/* Mark this lmb so we can remove it later if all of the
 		 * requested LMBs cannot be added.
 		 */
-		lmbs[i].reserved = 1;
+		drmem_mark_lmb_reserved(lmb);
+
+		lmbs_added++;
+		if (lmbs_added == lmbs_to_add)
+			break;
 	}
 
 	if (lmbs_added != lmbs_to_add) {
 		pr_err("Memory hot-add failed, removing any added LMBs\n");
 
-		for (i = 0; i < num_lmbs; i++) {
-			if (!lmbs[i].reserved)
+		for_each_drmem_lmb(lmb) {
+			if (!drmem_lmb_reserved(lmb))
 				continue;
 
-			rc = dlpar_remove_lmb(&lmbs[i]);
+			rc = dlpar_remove_lmb(lmb);
 			if (rc)
 				pr_err("Failed to remove LMB, drc index %x\n",
-				       be32_to_cpu(lmbs[i].drc_index));
+				       lmb->drc_index);
 			else
-				dlpar_release_drc(lmbs[i].drc_index);
+				dlpar_release_drc(lmb->drc_index);
+
+			drmem_remove_lmb_reservation(lmb);
 		}
 		rc = -EINVAL;
 	} else {
-		for (i = 0; i < num_lmbs; i++) {
-			if (!lmbs[i].reserved)
+		for_each_drmem_lmb(lmb) {
+			if (!drmem_lmb_reserved(lmb))
 				continue;
 
 			pr_info("Memory at %llx (drc index %x) was hot-added\n",
-				lmbs[i].base_addr, lmbs[i].drc_index);
-			lmbs[i].reserved = 0;
+				lmb->base_addr, lmb->drc_index);
+			drmem_remove_lmb_reservation(lmb);
 		}
 		rc = 0;
 	}
@@ -879,28 +799,22 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add, struct property *prop)
 	return rc;
 }
 
-static int dlpar_memory_add_by_index(u32 drc_index, struct property *prop)
+static int dlpar_memory_add_by_index(u32 drc_index)
 {
-	struct of_drconf_cell *lmbs;
-	u32 num_lmbs, *p;
-	int i, lmb_found;
-	int rc;
+	struct drmem_lmb *lmb;
+	int rc, lmb_found;
 
 	pr_info("Attempting to hot-add LMB, drc index %x\n", drc_index);
 
-	p = prop->value;
-	num_lmbs = *p++;
-	lmbs = (struct of_drconf_cell *)p;
-
 	lmb_found = 0;
-	for (i = 0; i < num_lmbs; i++) {
-		if (lmbs[i].drc_index == drc_index) {
+	for_each_drmem_lmb(lmb) {
+		if (lmb->drc_index == drc_index) {
 			lmb_found = 1;
-			rc = dlpar_acquire_drc(lmbs[i].drc_index);
+			rc = dlpar_acquire_drc(lmb->drc_index);
 			if (!rc) {
-				rc = dlpar_add_lmb(&lmbs[i]);
+				rc = dlpar_add_lmb(lmb);
 				if (rc)
-					dlpar_release_drc(lmbs[i].drc_index);
+					dlpar_release_drc(lmb->drc_index);
 			}
 
 			break;
@@ -914,18 +828,16 @@ static int dlpar_memory_add_by_index(u32 drc_index, struct property *prop)
 		pr_info("Failed to hot-add memory, drc index %x\n", drc_index);
 	else
 		pr_info("Memory at %llx (drc index %x) was hot-added\n",
-			lmbs[i].base_addr, drc_index);
+			lmb->base_addr, drc_index);
 
 	return rc;
 }
 
-static int dlpar_memory_add_by_ic(u32 lmbs_to_add, u32 drc_index,
-				  struct property *prop)
+static int dlpar_memory_add_by_ic(u32 lmbs_to_add, u32 drc_index)
 {
-	struct of_drconf_cell *lmbs;
-	u32 num_lmbs, *p;
-	int i, rc, start_lmb_found;
-	int lmbs_available = 0, start_index = 0, end_index;
+	struct drmem_lmb *lmb, *start_lmb, *end_lmb;
+	int lmbs_available = 0;
+	int rc;
 
 	pr_info("Attempting to hot-add %u LMB(s) at index %x\n",
 		lmbs_to_add, drc_index);
@@ -933,29 +845,13 @@ static int dlpar_memory_add_by_ic(u32 lmbs_to_add, u32 drc_index,
 	if (lmbs_to_add == 0)
 		return -EINVAL;
 
-	p = prop->value;
-	num_lmbs = *p++;
-	lmbs = (struct of_drconf_cell *)p;
-	start_lmb_found = 0;
-
-	/* Navigate to drc_index */
-	while (start_index < num_lmbs) {
-		if (lmbs[start_index].drc_index == drc_index) {
-			start_lmb_found = 1;
-			break;
-		}
-
-		start_index++;
-	}
-
-	if (!start_lmb_found)
+	rc = get_lmb_range(drc_index, lmbs_to_add, &start_lmb, &end_lmb);
+	if (rc)
 		return -EINVAL;
 
-	end_index = start_index + lmbs_to_add;
-
 	/* Validate that the LMBs in this range are not reserved */
-	for (i = start_index; i < end_index; i++) {
-		if (lmbs[i].flags & DRCONF_MEM_RESERVED)
+	for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
+		if (lmb->flags & DRCONF_MEM_RESERVED)
 			break;
 
 		lmbs_available++;
@@ -964,46 +860,48 @@ static int dlpar_memory_add_by_ic(u32 lmbs_to_add, u32 drc_index,
 	if (lmbs_available < lmbs_to_add)
 		return -EINVAL;
 
-	for (i = start_index; i < end_index; i++) {
-		if (lmbs[i].flags & DRCONF_MEM_ASSIGNED)
+	for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
+		if (lmb->flags & DRCONF_MEM_ASSIGNED)
 			continue;
 
-		rc = dlpar_acquire_drc(lmbs[i].drc_index);
+		rc = dlpar_acquire_drc(lmb->drc_index);
 		if (rc)
 			break;
 
-		rc = dlpar_add_lmb(&lmbs[i]);
+		rc = dlpar_add_lmb(lmb);
 		if (rc) {
-			dlpar_release_drc(lmbs[i].drc_index);
+			dlpar_release_drc(lmb->drc_index);
 			break;
 		}
 
-		lmbs[i].reserved = 1;
+		drmem_mark_lmb_reserved(lmb);
 	}
 
 	if (rc) {
 		pr_err("Memory indexed-count-add failed, removing any added LMBs\n");
 
-		for (i = start_index; i < end_index; i++) {
-			if (!lmbs[i].reserved)
+		for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
+			if (!drmem_lmb_reserved(lmb))
 				continue;
 
-			rc = dlpar_remove_lmb(&lmbs[i]);
+			rc = dlpar_remove_lmb(lmb);
 			if (rc)
 				pr_err("Failed to remove LMB, drc index %x\n",
-				       be32_to_cpu(lmbs[i].drc_index));
+				       lmb->drc_index);
 			else
-				dlpar_release_drc(lmbs[i].drc_index);
+				dlpar_release_drc(lmb->drc_index);
+
+			drmem_remove_lmb_reservation(lmb);
 		}
 		rc = -EINVAL;
 	} else {
-		for (i = start_index; i < end_index; i++) {
-			if (!lmbs[i].reserved)
+		for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
+			if (!drmem_lmb_reserved(lmb))
 				continue;
 
 			pr_info("Memory at %llx (drc index %x) was hot-added\n",
-				lmbs[i].base_addr, lmbs[i].drc_index);
-			lmbs[i].reserved = 0;
+				lmb->base_addr, lmb->drc_index);
+			drmem_remove_lmb_reservation(lmb);
 		}
 	}
 
@@ -1012,37 +910,23 @@ static int dlpar_memory_add_by_ic(u32 lmbs_to_add, u32 drc_index,
 
 int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
 {
-	struct device_node *dn;
-	struct property *prop;
 	u32 count, drc_index;
 	int rc;
 
 	lock_device_hotplug();
 
-	dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
-	if (!dn) {
-		rc = -EINVAL;
-		goto dlpar_memory_out;
-	}
-
-	prop = dlpar_clone_drconf_property(dn);
-	if (!prop) {
-		rc = -EINVAL;
-		goto dlpar_memory_out;
-	}
-
 	switch (hp_elog->action) {
 	case PSERIES_HP_ELOG_ACTION_ADD:
 		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) {
 			count = hp_elog->_drc_u.drc_count;
-			rc = dlpar_memory_add_by_count(count, prop);
+			rc = dlpar_memory_add_by_count(count);
 		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) {
 			drc_index = hp_elog->_drc_u.drc_index;
-			rc = dlpar_memory_add_by_index(drc_index, prop);
+			rc = dlpar_memory_add_by_index(drc_index);
 		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_IC) {
 			count = hp_elog->_drc_u.ic.count;
 			drc_index = hp_elog->_drc_u.ic.index;
-			rc = dlpar_memory_add_by_ic(count, drc_index, prop);
+			rc = dlpar_memory_add_by_ic(count, drc_index);
 		} else {
 			rc = -EINVAL;
 		}
@@ -1051,14 +935,14 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
 	case PSERIES_HP_ELOG_ACTION_REMOVE:
 		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) {
 			count = hp_elog->_drc_u.drc_count;
-			rc = dlpar_memory_remove_by_count(count, prop);
+			rc = dlpar_memory_remove_by_count(count);
 		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) {
 			drc_index = hp_elog->_drc_u.drc_index;
-			rc = dlpar_memory_remove_by_index(drc_index, prop);
+			rc = dlpar_memory_remove_by_index(drc_index);
 		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_IC) {
 			count = hp_elog->_drc_u.ic.count;
 			drc_index = hp_elog->_drc_u.ic.index;
-			rc = dlpar_memory_remove_by_ic(count, drc_index, prop);
+			rc = dlpar_memory_remove_by_ic(count, drc_index);
 		} else {
 			rc = -EINVAL;
 		}
@@ -1066,7 +950,7 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
 		break;
 	case PSERIES_HP_ELOG_ACTION_READD:
 		drc_index = hp_elog->_drc_u.drc_index;
-		rc = dlpar_memory_readd_by_index(drc_index, prop);
+		rc = dlpar_memory_readd_by_index(drc_index);
 		break;
 	default:
 		pr_err("Invalid action (%d) specified\n", hp_elog->action);
@@ -1074,10 +958,6 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
 		break;
 	}
 
-	dlpar_free_property(prop);
-
-dlpar_memory_out:
-	of_node_put(dn);
 	unlock_device_hotplug();
 	return rc;
 }
@@ -1116,7 +996,7 @@ static int pseries_add_mem_node(struct device_node *np)
 
 static int pseries_update_drconf_memory(struct of_reconfig_data *pr)
 {
-	struct of_drconf_cell *new_drmem, *old_drmem;
+	struct of_drconf_cell_v1 *new_drmem, *old_drmem;
 	unsigned long memblock_size;
 	u32 entries;
 	__be32 *p;
@@ -1139,11 +1019,11 @@ static int pseries_update_drconf_memory(struct of_reconfig_data *pr)
 	 * of_drconf_cell's.
 	 */
 	entries = be32_to_cpu(*p++);
-	old_drmem = (struct of_drconf_cell *)p;
+	old_drmem = (struct of_drconf_cell_v1 *)p;
 
 	p = (__be32 *)pr->prop->value;
 	p++;
-	new_drmem = (struct of_drconf_cell *)p;
+	new_drmem = (struct of_drconf_cell_v1 *)p;
 
 	for (i = 0; i < entries; i++) {
 		if ((be32_to_cpu(old_drmem[i].flags) & DRCONF_MEM_ASSIGNED) &&
diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c
index 957ae347b0b3..89b7ce807e70 100644
--- a/arch/powerpc/platforms/pseries/hvCall_inst.c
+++ b/arch/powerpc/platforms/pseries/hvCall_inst.c
@@ -163,7 +163,7 @@ static int __init hcall_inst_init(void)
 
 	for_each_possible_cpu(cpu) {
 		snprintf(cpu_name_buf, CPU_NAME_BUF_SIZE, "cpu%d", cpu);
-		hcall_file = debugfs_create_file(cpu_name_buf, S_IRUGO,
+		hcall_file = debugfs_create_file(cpu_name_buf, 0444,
 						 hcall_root,
 						 per_cpu(hcall_stats, cpu),
 						 &hcall_inst_seq_fops);
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index 408a86044133..c7c1140c13b6 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -298,7 +298,7 @@ out:
 		return rc;
 	return count;
 }
-static BUS_ATTR(probe, S_IWUSR, NULL, ibmebus_store_probe);
+static BUS_ATTR(probe, 0200, NULL, ibmebus_store_probe);
 
 static ssize_t ibmebus_store_remove(struct bus_type *bus,
 				    const char *buf, size_t count)
@@ -325,7 +325,7 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus,
 		return -ENODEV;
 	}
 }
-static BUS_ATTR(remove, S_IWUSR, NULL, ibmebus_store_remove);
+static BUS_ATTR(remove, 0200, NULL, ibmebus_store_remove);
 
 static struct attribute *ibmbus_bus_attrs[] = {
 	&bus_attr_probe.attr,
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 69921f72e2da..06f02960b439 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -816,15 +816,15 @@ static void remove_ddw(struct device_node *np, bool remove_prop)
 	ret = tce_clearrange_multi_pSeriesLP(0,
 		1ULL << (be32_to_cpu(dwp->window_shift) - PAGE_SHIFT), dwp);
 	if (ret)
-		pr_warning("%pOF failed to clear tces in window.\n",
-			 np);
+		pr_warn("%pOF failed to clear tces in window.\n",
+			np);
 	else
 		pr_debug("%pOF successfully cleared tces in window.\n",
 			 np);
 
 	ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn);
 	if (ret)
-		pr_warning("%pOF: failed to remove direct window: rtas returned "
+		pr_warn("%pOF: failed to remove direct window: rtas returned "
 			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
 			np, ret, ddw_avail[2], liobn);
 	else
@@ -836,7 +836,7 @@ delprop:
 	if (remove_prop)
 		ret = of_remove_property(np, win64);
 	if (ret)
-		pr_warning("%pOF: failed to remove direct window property: %d\n",
+		pr_warn("%pOF: failed to remove direct window property: %d\n",
 			np, ret);
 }
 
@@ -1231,7 +1231,7 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
 			if (dma_offset != 0) {
 				dev_info(dev, "Using 64-bit direct DMA at offset %llx\n", dma_offset);
 				set_dma_offset(dev, dma_offset);
-				set_dma_ops(dev, &dma_direct_ops);
+				set_dma_ops(dev, &dma_nommu_ops);
 				ddw_enabled = true;
 			}
 		}
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index b2706c483067..c508c938dc71 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -370,10 +370,10 @@ static void parse_system_parameter_string(struct seq_file *m)
  */
 static int lparcfg_count_active_processors(void)
 {
-	struct device_node *cpus_dn = NULL;
+	struct device_node *cpus_dn;
 	int count = 0;
 
-	while ((cpus_dn = of_find_node_by_type(cpus_dn, "cpu"))) {
+	for_each_node_by_type(cpus_dn, "cpu") {
 #ifdef LPARCFG_DEBUG
 		printk(KERN_ERR "cpus_dn %p\n", cpus_dn);
 #endif
@@ -697,11 +697,11 @@ static const struct file_operations lparcfg_fops = {
 
 static int __init lparcfg_init(void)
 {
-	umode_t mode = S_IRUSR | S_IRGRP | S_IROTH;
+	umode_t mode = 0444;
 
 	/* Allow writing if we have FW_FEATURE_SPLPAR */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR))
-		mode |= S_IWUSR;
+		mode |= 0200;
 
 	if (!proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops)) {
 		printk(KERN_ERR "Failed to create powerpc/lparcfg\n");
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index f7042ad492ba..0f7fb7170b03 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -384,7 +384,7 @@ static ssize_t migration_store(struct class *class,
 #define MIGRATION_API_VERSION	1
 
 static CLASS_ATTR_WO(migration);
-static CLASS_ATTR_STRING(api_version, S_IRUGO, __stringify(MIGRATION_API_VERSION));
+static CLASS_ATTR_STRING(api_version, 0444, __stringify(MIGRATION_API_VERSION));
 
 static int __init mobility_sysfs_init(void)
 {
diff --git a/arch/powerpc/platforms/pseries/of_helpers.c b/arch/powerpc/platforms/pseries/of_helpers.c
index 7e75101fa522..6df192f38f80 100644
--- a/arch/powerpc/platforms/pseries/of_helpers.c
+++ b/arch/powerpc/platforms/pseries/of_helpers.c
@@ -3,6 +3,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/of.h>
+#include <asm/prom.h>
 
 #include "of_helpers.h"
 
@@ -37,3 +38,62 @@ struct device_node *pseries_of_derive_parent(const char *path)
 		kfree(parent_path);
 	return parent ? parent : ERR_PTR(-EINVAL);
 }
+
+
+/* Helper Routines to convert between drc_index to cpu numbers */
+
+int of_read_drc_info_cell(struct property **prop, const __be32 **curval,
+			struct of_drc_info *data)
+{
+	const char *p;
+	const __be32 *p2;
+
+	if (!data)
+		return -EINVAL;
+
+	/* Get drc-type:encode-string */
+	p = data->drc_type = (char*) (*curval);
+	p = of_prop_next_string(*prop, p);
+	if (!p)
+		return -EINVAL;
+
+	/* Get drc-name-prefix:encode-string */
+	data->drc_name_prefix = (char *)p;
+	p = of_prop_next_string(*prop, p);
+	if (!p)
+		return -EINVAL;
+
+	/* Get drc-index-start:encode-int */
+	p2 = (const __be32 *)p;
+	p2 = of_prop_next_u32(*prop, p2, &data->drc_index_start);
+	if (!p2)
+		return -EINVAL;
+
+	/* Get drc-name-suffix-start:encode-int */
+	p2 = of_prop_next_u32(*prop, p2, &data->drc_name_suffix_start);
+	if (!p2)
+		return -EINVAL;
+
+	/* Get number-sequential-elements:encode-int */
+	p2 = of_prop_next_u32(*prop, p2, &data->num_sequential_elems);
+	if (!p2)
+		return -EINVAL;
+
+	/* Get sequential-increment:encode-int */
+	p2 = of_prop_next_u32(*prop, p2, &data->sequential_inc);
+	if (!p2)
+		return -EINVAL;
+
+	/* Get drc-power-domain:encode-int */
+	p2 = of_prop_next_u32(*prop, p2, &data->drc_power_domain);
+	if (!p2)
+		return -EINVAL;
+
+	/* Should now know end of current entry */
+	(*curval) = (void *)p2;
+	data->last_drc_index = data->drc_index_start +
+		((data->num_sequential_elems - 1) * data->sequential_inc);
+
+	return 0;
+}
+EXPORT_SYMBOL(of_read_drc_info_cell);
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 09eba5a9929a..eab96637d6cf 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -3,17 +3,17 @@
  * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
  *
  * pSeries specific routines for PCI.
- * 
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
  * (at your option) any later version.
- *    
+ *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- * 
+ *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
@@ -54,10 +54,174 @@ void pcibios_name_device(struct pci_dev *dev)
 			}
 		}
 	}
-}   
+}
 DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_name_device);
 #endif
 
+#ifdef CONFIG_PCI_IOV
+#define MAX_VFS_FOR_MAP_PE 256
+struct pe_map_bar_entry {
+	__be64     bar;       /* Input:  Virtual Function BAR */
+	__be16     rid;       /* Input:  Virtual Function Router ID */
+	__be16     pe_num;    /* Output: Virtual Function PE Number */
+	__be32     reserved;  /* Reserved Space */
+};
+
+int pseries_send_map_pe(struct pci_dev *pdev,
+			u16 num_vfs,
+			struct pe_map_bar_entry *vf_pe_array)
+{
+	struct pci_dn *pdn;
+	int rc;
+	unsigned long buid, addr;
+	int ibm_map_pes = rtas_token("ibm,open-sriov-map-pe-number");
+
+	if (ibm_map_pes == RTAS_UNKNOWN_SERVICE)
+		return -EINVAL;
+
+	pdn = pci_get_pdn(pdev);
+	addr = rtas_config_addr(pdn->busno, pdn->devfn, 0);
+	buid = pdn->phb->buid;
+	spin_lock(&rtas_data_buf_lock);
+	memcpy(rtas_data_buf, vf_pe_array,
+	       RTAS_DATA_BUF_SIZE);
+	rc = rtas_call(ibm_map_pes, 5, 1, NULL, addr,
+		       BUID_HI(buid), BUID_LO(buid),
+		       rtas_data_buf,
+		       num_vfs * sizeof(struct pe_map_bar_entry));
+	memcpy(vf_pe_array, rtas_data_buf, RTAS_DATA_BUF_SIZE);
+	spin_unlock(&rtas_data_buf_lock);
+
+	if (rc)
+		dev_err(&pdev->dev,
+			"%s: Failed to associate pes PE#%lx, rc=%x\n",
+			__func__,  addr, rc);
+
+	return rc;
+}
+
+void pseries_set_pe_num(struct pci_dev *pdev, u16 vf_index, __be16 pe_num)
+{
+	struct pci_dn *pdn;
+
+	pdn = pci_get_pdn(pdev);
+	pdn->pe_num_map[vf_index] = be16_to_cpu(pe_num);
+	dev_dbg(&pdev->dev, "VF %04x:%02x:%02x.%x associated with PE#%x\n",
+		pci_domain_nr(pdev->bus),
+		pdev->bus->number,
+		PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)),
+		PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)),
+		pdn->pe_num_map[vf_index]);
+}
+
+int pseries_associate_pes(struct pci_dev *pdev, u16 num_vfs)
+{
+	struct pci_dn *pdn;
+	int i, rc, vf_index;
+	struct pe_map_bar_entry *vf_pe_array;
+	struct resource *res;
+	u64 size;
+
+	vf_pe_array = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL);
+	if (!vf_pe_array)
+		return -ENOMEM;
+
+	pdn = pci_get_pdn(pdev);
+	/* create firmware structure to associate pes */
+	for (vf_index = 0; vf_index < num_vfs; vf_index++) {
+		pdn->pe_num_map[vf_index] = IODA_INVALID_PE;
+		for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+			res = &pdev->resource[i + PCI_IOV_RESOURCES];
+			if (!res->parent)
+				continue;
+			size = pcibios_iov_resource_alignment(pdev, i +
+					PCI_IOV_RESOURCES);
+			vf_pe_array[vf_index].bar =
+				cpu_to_be64(res->start + size * vf_index);
+			vf_pe_array[vf_index].rid =
+				cpu_to_be16((pci_iov_virtfn_bus(pdev, vf_index)
+					    << 8) | pci_iov_virtfn_devfn(pdev,
+					    vf_index));
+			vf_pe_array[vf_index].pe_num =
+				cpu_to_be16(IODA_INVALID_PE);
+		}
+	}
+
+	rc = pseries_send_map_pe(pdev, num_vfs, vf_pe_array);
+	/* Only zero is success */
+	if (!rc)
+		for (vf_index = 0; vf_index < num_vfs; vf_index++)
+			pseries_set_pe_num(pdev, vf_index,
+					   vf_pe_array[vf_index].pe_num);
+
+	kfree(vf_pe_array);
+	return rc;
+}
+
+int pseries_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+{
+	struct pci_dn         *pdn;
+	int                    rc;
+	const int *max_vfs;
+	int max_config_vfs;
+	struct device_node *dn = pci_device_to_OF_node(pdev);
+
+	max_vfs = of_get_property(dn, "ibm,number-of-configurable-vfs", NULL);
+
+	if (!max_vfs)
+		return -EINVAL;
+
+	/* First integer stores max config */
+	max_config_vfs = of_read_number(&max_vfs[0], 1);
+	if (max_config_vfs < num_vfs && num_vfs > MAX_VFS_FOR_MAP_PE) {
+		dev_err(&pdev->dev,
+			"Num VFs %x > %x Configurable VFs\n",
+			num_vfs, (num_vfs > MAX_VFS_FOR_MAP_PE) ?
+			MAX_VFS_FOR_MAP_PE : max_config_vfs);
+		return -EINVAL;
+	}
+
+	pdn = pci_get_pdn(pdev);
+	pdn->pe_num_map = kmalloc_array(num_vfs,
+					sizeof(*pdn->pe_num_map),
+					GFP_KERNEL);
+	if (!pdn->pe_num_map)
+		return -ENOMEM;
+
+	rc = pseries_associate_pes(pdev, num_vfs);
+
+	/* Anything other than zero is failure */
+	if (rc) {
+		dev_err(&pdev->dev, "Failure to enable sriov: %x\n", rc);
+		kfree(pdn->pe_num_map);
+	} else {
+		pci_vf_drivers_autoprobe(pdev, false);
+	}
+
+	return rc;
+}
+
+int pseries_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+{
+	/* Allocate PCI data */
+	add_dev_pci_data(pdev);
+	return pseries_pci_sriov_enable(pdev, num_vfs);
+}
+
+int pseries_pcibios_sriov_disable(struct pci_dev *pdev)
+{
+	struct pci_dn         *pdn;
+
+	pdn = pci_get_pdn(pdev);
+	/* Releasing pe_num_map */
+	kfree(pdn->pe_num_map);
+	/* Release PCI data */
+	remove_dev_pci_data(pdev);
+	pci_vf_drivers_autoprobe(pdev, true);
+	return 0;
+}
+#endif
+
 static void __init pSeries_request_regions(void)
 {
 	if (!isa_io_base)
@@ -76,6 +240,11 @@ void __init pSeries_final_fixup(void)
 	pSeries_request_regions();
 
 	eeh_addr_cache_build();
+
+#ifdef CONFIG_PCI_IOV
+	ppc_md.pcibios_sriov_enable = pseries_pcibios_sriov_enable;
+	ppc_md.pcibios_sriov_disable = pseries_pcibios_sriov_disable;
+#endif
 }
 
 /*
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 4470a3194311..1ae1d9f4dbe9 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -98,4 +98,6 @@ static inline unsigned long cmo_get_page_size(void)
 	return CMO_PageSize;
 }
 
+int dlpar_workqueue_init(void);
+
 #endif /* _PSERIES_PSERIES_H */
diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c
index 35c891aabef0..6ed22127391b 100644
--- a/arch/powerpc/platforms/pseries/pseries_energy.c
+++ b/arch/powerpc/platforms/pseries/pseries_energy.c
@@ -22,6 +22,7 @@
 #include <asm/page.h>
 #include <asm/hvcall.h>
 #include <asm/firmware.h>
+#include <asm/prom.h>
 
 
 #define MODULE_VERS "1.0"
@@ -38,26 +39,58 @@ static int sysfs_entries;
 static u32 cpu_to_drc_index(int cpu)
 {
 	struct device_node *dn = NULL;
-	const int *indexes;
-	int i;
+	int thread_index;
 	int rc = 1;
 	u32 ret = 0;
 
 	dn = of_find_node_by_path("/cpus");
 	if (dn == NULL)
 		goto err;
-	indexes = of_get_property(dn, "ibm,drc-indexes", NULL);
-	if (indexes == NULL)
-		goto err_of_node_put;
+
 	/* Convert logical cpu number to core number */
-	i = cpu_core_index_of_thread(cpu);
-	/*
-	 * The first element indexes[0] is the number of drc_indexes
-	 * returned in the list.  Hence i+1 will get the drc_index
-	 * corresponding to core number i.
-	 */
-	WARN_ON(i > indexes[0]);
-	ret = indexes[i + 1];
+	thread_index = cpu_core_index_of_thread(cpu);
+
+	if (firmware_has_feature(FW_FEATURE_DRC_INFO)) {
+		struct property *info = NULL;
+		struct of_drc_info drc;
+		int j;
+		u32 num_set_entries;
+		const __be32 *value;
+
+		info = of_find_property(dn, "ibm,drc-info", NULL);
+		if (info == NULL)
+			goto err_of_node_put;
+
+		value = of_prop_next_u32(info, NULL, &num_set_entries);
+		if (!value)
+			goto err_of_node_put;
+
+		for (j = 0; j < num_set_entries; j++) {
+
+			of_read_drc_info_cell(&info, &value, &drc);
+			if (strncmp(drc.drc_type, "CPU", 3))
+				goto err;
+
+			if (thread_index < drc.last_drc_index)
+				break;
+		}
+
+		ret = drc.drc_index_start + (thread_index * drc.sequential_inc);
+	} else {
+		const __be32 *indexes;
+
+		indexes = of_get_property(dn, "ibm,drc-indexes", NULL);
+		if (indexes == NULL)
+			goto err_of_node_put;
+
+		/*
+		 * The first element indexes[0] is the number of drc_indexes
+		 * returned in the list.  Hence thread_index+1 will get the
+		 * drc_index corresponding to core number thread_index.
+		 */
+		ret = indexes[thread_index + 1];
+	}
+
 	rc = 0;
 
 err_of_node_put:
@@ -72,34 +105,71 @@ static int drc_index_to_cpu(u32 drc_index)
 {
 	struct device_node *dn = NULL;
 	const int *indexes;
-	int i, cpu = 0;
+	int thread_index = 0, cpu = 0;
 	int rc = 1;
 
 	dn = of_find_node_by_path("/cpus");
 	if (dn == NULL)
 		goto err;
-	indexes = of_get_property(dn, "ibm,drc-indexes", NULL);
-	if (indexes == NULL)
-		goto err_of_node_put;
-	/*
-	 * First element in the array is the number of drc_indexes
-	 * returned.  Search through the list to find the matching
-	 * drc_index and get the core number
-	 */
-	for (i = 0; i < indexes[0]; i++) {
-		if (indexes[i + 1] == drc_index)
+
+	if (firmware_has_feature(FW_FEATURE_DRC_INFO)) {
+		struct property *info = NULL;
+		struct of_drc_info drc;
+		int j;
+		u32 num_set_entries;
+		const __be32 *value;
+
+		info = of_find_property(dn, "ibm,drc-info", NULL);
+		if (info == NULL)
+			goto err_of_node_put;
+
+		value = of_prop_next_u32(info, NULL, &num_set_entries);
+		if (!value)
+			goto err_of_node_put;
+
+		for (j = 0; j < num_set_entries; j++) {
+
+			of_read_drc_info_cell(&info, &value, &drc);
+			if (strncmp(drc.drc_type, "CPU", 3))
+				goto err;
+
+			if (drc_index > drc.last_drc_index) {
+				cpu += drc.num_sequential_elems;
+				continue;
+			}
+			cpu += ((drc_index - drc.drc_index_start) /
+				drc.sequential_inc);
+
+			thread_index = cpu_first_thread_of_core(cpu);
+			rc = 0;
 			break;
+		}
+	} else {
+		unsigned long int i;
+
+		indexes = of_get_property(dn, "ibm,drc-indexes", NULL);
+		if (indexes == NULL)
+			goto err_of_node_put;
+		/*
+		 * First element in the array is the number of drc_indexes
+		 * returned.  Search through the list to find the matching
+		 * drc_index and get the core number
+		 */
+		for (i = 0; i < indexes[0]; i++) {
+			if (indexes[i + 1] == drc_index)
+				break;
+		}
+		/* Convert core number to logical cpu number */
+		thread_index = cpu_first_thread_of_core(i);
+		rc = 0;
 	}
-	/* Convert core number to logical cpu number */
-	cpu = cpu_first_thread_of_core(i);
-	rc = 0;
 
 err_of_node_put:
 	of_node_put(dn);
 err:
 	if (rc)
 		printk(KERN_WARNING "drc_index_to_cpu(%d) failed", drc_index);
-	return cpu;
+	return thread_index;
 }
 
 /*
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 4923ffe230cf..81d8614e7379 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -69,7 +69,8 @@ static int __init init_ras_IRQ(void)
 	/* Hotplug Events */
 	np = of_find_node_by_path("/event-sources/hot-plug-events");
 	if (np != NULL) {
-		request_event_sources_irqs(np, ras_hotplug_interrupt,
+		if (dlpar_workqueue_init() == 0)
+			request_event_sources_irqs(np, ras_hotplug_interrupt,
 					   "RAS_HOTPLUG");
 		of_node_put(np);
 	}
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index f24d8159c9e1..0e0208117e77 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -405,7 +405,7 @@ static int proc_ppc64_create_ofdt(void)
 {
 	struct proc_dir_entry *ent;
 
-	ent = proc_create("powerpc/ofdt", S_IWUSR, NULL, &ofdt_fops);
+	ent = proc_create("powerpc/ofdt", 0200, NULL, &ofdt_fops);
 	if (ent)
 		proc_set_size(ent, 0);
 
diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c
index c47585a78b69..054ce7a16fc3 100644
--- a/arch/powerpc/platforms/pseries/scanlog.c
+++ b/arch/powerpc/platforms/pseries/scanlog.c
@@ -179,7 +179,7 @@ static int __init scanlog_init(void)
 	if (!scanlog_buffer)
 		goto err;
 
-	ent = proc_create("powerpc/rtas/scan-log-dump", S_IRUSR, NULL,
+	ent = proc_create("powerpc/rtas/scan-log-dump", 0400, NULL,
 			  &scanlog_fops);
 	if (!ent)
 		goto err;
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 5f1beb8367ac..372d7ada1a0c 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -371,8 +371,8 @@ void pseries_disable_reloc_on_exc(void)
 		mdelay(get_longbusy_msecs(rc));
 	}
 	if (rc != H_SUCCESS)
-		pr_warning("Warning: Failed to disable relocation on "
-			   "exceptions: %ld\n", rc);
+		pr_warn("Warning: Failed to disable relocation on exceptions: %ld\n",
+			rc);
 }
 EXPORT_SYMBOL(pseries_disable_reloc_on_exc);
 
@@ -459,6 +459,195 @@ static void __init find_and_init_phbs(void)
 	of_pci_check_probe_only();
 }
 
+static void pseries_setup_rfi_flush(void)
+{
+	struct h_cpu_char_result result;
+	enum l1d_flush_type types;
+	bool enable;
+	long rc;
+
+	/* Enable by default */
+	enable = true;
+
+	rc = plpar_get_cpu_characteristics(&result);
+	if (rc == H_SUCCESS) {
+		types = L1D_FLUSH_NONE;
+
+		if (result.character & H_CPU_CHAR_L1D_FLUSH_TRIG2)
+			types |= L1D_FLUSH_MTTRIG;
+		if (result.character & H_CPU_CHAR_L1D_FLUSH_ORI30)
+			types |= L1D_FLUSH_ORI;
+
+		/* Use fallback if nothing set in hcall */
+		if (types == L1D_FLUSH_NONE)
+			types = L1D_FLUSH_FALLBACK;
+
+		if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR))
+			enable = false;
+	} else {
+		/* Default to fallback if case hcall is not available */
+		types = L1D_FLUSH_FALLBACK;
+	}
+
+	setup_rfi_flush(types, enable);
+}
+
+#ifdef CONFIG_PCI_IOV
+enum rtas_iov_fw_value_map {
+	NUM_RES_PROPERTY  = 0, /* Number of Resources */
+	LOW_INT           = 1, /* Lowest 32 bits of Address */
+	START_OF_ENTRIES  = 2, /* Always start of entry */
+	APERTURE_PROPERTY = 2, /* Start of entry+ to  Aperture Size */
+	WDW_SIZE_PROPERTY = 4, /* Start of entry+ to Window Size */
+	NEXT_ENTRY        = 7  /* Go to next entry on array */
+};
+
+enum get_iov_fw_value_index {
+	BAR_ADDRS     = 1,    /*  Get Bar Address */
+	APERTURE_SIZE = 2,    /*  Get Aperture Size */
+	WDW_SIZE      = 3     /*  Get Window Size */
+};
+
+resource_size_t pseries_get_iov_fw_value(struct pci_dev *dev, int resno,
+					 enum get_iov_fw_value_index value)
+{
+	const int *indexes;
+	struct device_node *dn = pci_device_to_OF_node(dev);
+	int i, num_res, ret = 0;
+
+	indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL);
+	if (!indexes)
+		return  0;
+
+	/*
+	 * First element in the array is the number of Bars
+	 * returned.  Search through the list to find the matching
+	 * bar
+	 */
+	num_res = of_read_number(&indexes[NUM_RES_PROPERTY], 1);
+	if (resno >= num_res)
+		return 0; /* or an errror */
+
+	i = START_OF_ENTRIES + NEXT_ENTRY * resno;
+	switch (value) {
+	case BAR_ADDRS:
+		ret = of_read_number(&indexes[i], 2);
+		break;
+	case APERTURE_SIZE:
+		ret = of_read_number(&indexes[i + APERTURE_PROPERTY], 2);
+		break;
+	case WDW_SIZE:
+		ret = of_read_number(&indexes[i + WDW_SIZE_PROPERTY], 2);
+		break;
+	}
+
+	return ret;
+}
+
+void of_pci_set_vf_bar_size(struct pci_dev *dev, const int *indexes)
+{
+	struct resource *res;
+	resource_size_t base, size;
+	int i, r, num_res;
+
+	num_res = of_read_number(&indexes[NUM_RES_PROPERTY], 1);
+	num_res = min_t(int, num_res, PCI_SRIOV_NUM_BARS);
+	for (i = START_OF_ENTRIES, r = 0; r < num_res && r < PCI_SRIOV_NUM_BARS;
+	     i += NEXT_ENTRY, r++) {
+		res = &dev->resource[r + PCI_IOV_RESOURCES];
+		base = of_read_number(&indexes[i], 2);
+		size = of_read_number(&indexes[i + APERTURE_PROPERTY], 2);
+		res->flags = pci_parse_of_flags(of_read_number
+						(&indexes[i + LOW_INT], 1), 0);
+		res->flags |= (IORESOURCE_MEM_64 | IORESOURCE_PCI_FIXED);
+		res->name = pci_name(dev);
+		res->start = base;
+		res->end = base + size - 1;
+	}
+}
+
+void of_pci_parse_iov_addrs(struct pci_dev *dev, const int *indexes)
+{
+	struct resource *res, *root, *conflict;
+	resource_size_t base, size;
+	int i, r, num_res;
+
+	/*
+	 * First element in the array is the number of Bars
+	 * returned.  Search through the list to find the matching
+	 * bars assign them from firmware into resources structure.
+	 */
+	num_res = of_read_number(&indexes[NUM_RES_PROPERTY], 1);
+	for (i = START_OF_ENTRIES, r = 0; r < num_res && r < PCI_SRIOV_NUM_BARS;
+	     i += NEXT_ENTRY, r++) {
+		res = &dev->resource[r + PCI_IOV_RESOURCES];
+		base = of_read_number(&indexes[i], 2);
+		size = of_read_number(&indexes[i + WDW_SIZE_PROPERTY], 2);
+		res->name = pci_name(dev);
+		res->start = base;
+		res->end = base + size - 1;
+		root = &iomem_resource;
+		dev_dbg(&dev->dev,
+			"pSeries IOV BAR %d: trying firmware assignment %pR\n",
+			 r + PCI_IOV_RESOURCES, res);
+		conflict = request_resource_conflict(root, res);
+		if (conflict) {
+			dev_info(&dev->dev,
+				 "BAR %d: %pR conflicts with %s %pR\n",
+				 r + PCI_IOV_RESOURCES, res,
+				 conflict->name, conflict);
+			res->flags |= IORESOURCE_UNSET;
+		}
+	}
+}
+
+static void pseries_pci_fixup_resources(struct pci_dev *pdev)
+{
+	const int *indexes;
+	struct device_node *dn = pci_device_to_OF_node(pdev);
+
+	/*Firmware must support open sriov otherwise dont configure*/
+	indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL);
+	if (!indexes)
+		return;
+	/* Assign the addresses from device tree*/
+	of_pci_set_vf_bar_size(pdev, indexes);
+}
+
+static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev)
+{
+	const int *indexes;
+	struct device_node *dn = pci_device_to_OF_node(pdev);
+
+	if (!pdev->is_physfn || pdev->is_added)
+		return;
+	/*Firmware must support open sriov otherwise dont configure*/
+	indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL);
+	if (!indexes)
+		return;
+	/* Assign the addresses from device tree*/
+	of_pci_parse_iov_addrs(pdev, indexes);
+}
+
+static resource_size_t pseries_pci_iov_resource_alignment(struct pci_dev *pdev,
+							  int resno)
+{
+	const __be32 *reg;
+	struct device_node *dn = pci_device_to_OF_node(pdev);
+
+	/*Firmware must support open sriov otherwise report regular alignment*/
+	reg = of_get_property(dn, "ibm,is-open-sriov-pf", NULL);
+	if (!reg)
+		return pci_iov_resource_size(pdev, resno);
+
+	if (!pdev->is_physfn)
+		return 0;
+	return pseries_get_iov_fw_value(pdev,
+					resno - PCI_IOV_RESOURCES,
+					APERTURE_SIZE);
+}
+#endif
+
 static void __init pSeries_setup_arch(void)
 {
 	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
@@ -476,6 +665,8 @@ static void __init pSeries_setup_arch(void)
 
 	fwnmi_init();
 
+	pseries_setup_rfi_flush();
+
 	/* By default, only probe PCI (can be overridden by rtas_pci) */
 	pci_add_flags(PCI_PROBE_ONLY);
 
@@ -490,6 +681,14 @@ static void __init pSeries_setup_arch(void)
 		vpa_init(boot_cpuid);
 		ppc_md.power_save = pseries_lpar_idle;
 		ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
+#ifdef CONFIG_PCI_IOV
+		ppc_md.pcibios_fixup_resources =
+			pseries_pci_fixup_resources;
+		ppc_md.pcibios_fixup_sriov =
+			pseries_pci_fixup_iov_resources;
+		ppc_md.pcibios_iov_resource_alignment =
+			pseries_pci_iov_resource_alignment;
+#endif
 	} else {
 		/* No special idle routine */
 		ppc_md.enable_pmcs = power4_enable_pmcs;
@@ -498,6 +697,12 @@ static void __init pSeries_setup_arch(void)
 	ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
 }
 
+static void pseries_panic(char *str)
+{
+	panic_flush_kmsg_end();
+	rtas_os_term(str);
+}
+
 static int __init pSeries_init_panel(void)
 {
 	/* Manually leave the kernel version on the panel. */
@@ -726,6 +931,7 @@ define_machine(pseries) {
 	.pcibios_fixup		= pSeries_final_fixup,
 	.restart		= rtas_restart,
 	.halt			= rtas_halt,
+	.panic			= pseries_panic,
 	.get_boot_time		= rtas_get_boot_time,
 	.get_rtc_time		= rtas_get_rtc_time,
 	.set_rtc_time		= rtas_set_rtc_time,
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 89726f07d249..52a021e1f86b 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -214,8 +214,7 @@ static ssize_t show_hibernate(struct device *dev,
 	return sprintf(buf, "%d\n", KERN_DT_UPDATE);
 }
 
-static DEVICE_ATTR(hibernate, S_IWUSR | S_IRUGO,
-		   show_hibernate, store_hibernate);
+static DEVICE_ATTR(hibernate, 0644, show_hibernate, store_hibernate);
 
 static struct bus_type suspend_subsys = {
 	.name = "power",
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index d86938260a86..49e04ec19238 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -618,7 +618,7 @@ static u64 vio_dma_get_required_mask(struct device *dev)
 static const struct dma_map_ops vio_dma_mapping_ops = {
 	.alloc             = vio_dma_iommu_alloc_coherent,
 	.free              = vio_dma_iommu_free_coherent,
-	.mmap		   = dma_direct_mmap_coherent,
+	.mmap		   = dma_nommu_mmap_coherent,
 	.map_sg            = vio_dma_iommu_map_sg,
 	.unmap_sg          = vio_dma_iommu_unmap_sg,
 	.map_page          = vio_dma_iommu_map_page,
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index 0baba21404dc..9861407d644a 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -32,7 +32,6 @@ mv64x60-$(CONFIG_PCI)		+= mv64x60_pci.o
 obj-$(CONFIG_MV64X60)		+= $(mv64x60-y) mv64x60_pic.o mv64x60_dev.o \
 				   mv64x60_udbg.o
 obj-$(CONFIG_RTC_DRV_CMOS)	+= rtc_cmos_setup.o
-obj-$(CONFIG_AXON_RAM)		+= axonram.o
 
 obj-$(CONFIG_PPC_INDIRECT_PCI)	+= indirect_pci.o
 obj-$(CONFIG_PPC_I8259)		+= i8259.o
@@ -43,7 +42,8 @@ obj-$(CONFIG_OF_RTC)		+= of_rtc.o
 
 obj-$(CONFIG_CPM)		+= cpm_common.o
 obj-$(CONFIG_CPM1)		+= cpm1.o
-obj-$(CONFIG_CPM2)		+= cpm2.o cpm2_pic.o
+obj-$(CONFIG_CPM2)		+= cpm2.o cpm2_pic.o cpm_gpio.o
+obj-$(CONFIG_8xx_GPIO)		+= cpm_gpio.o
 obj-$(CONFIG_QUICC_ENGINE)	+= cpm_common.o
 obj-$(CONFIG_PPC_DCR)		+= dcr.o
 obj-$(CONFIG_UCODE_PATCH)	+= micropatch.o
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
deleted file mode 100644
index 1b307c80b401..000000000000
--- a/arch/powerpc/sysdev/axonram.c
+++ /dev/null
@@ -1,383 +0,0 @@
-/*
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2006
- *
- * Author: Maxim Shchetynin <maxim@de.ibm.com>
- *
- * Axon DDR2 device driver.
- * It registers one block device per Axon's DDR2 memory bank found on a system.
- * Block devices are called axonram?, their major and minor numbers are
- * available in /proc/devices, /proc/partitions or in /sys/block/axonram?/dev.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/bio.h>
-#include <linux/blkdev.h>
-#include <linux/dax.h>
-#include <linux/device.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/genhd.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/ioport.h>
-#include <linux/irq.h>
-#include <linux/irqreturn.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/mod_devicetable.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/of_device.h>
-#include <linux/of_platform.h>
-#include <linux/pfn_t.h>
-#include <linux/uio.h>
-
-#include <asm/page.h>
-#include <asm/prom.h>
-
-#define AXON_RAM_MODULE_NAME		"axonram"
-#define AXON_RAM_DEVICE_NAME		"axonram"
-#define AXON_RAM_MINORS_PER_DISK	16
-#define AXON_RAM_BLOCK_SHIFT		PAGE_SHIFT
-#define AXON_RAM_BLOCK_SIZE		1 << AXON_RAM_BLOCK_SHIFT
-#define AXON_RAM_SECTOR_SHIFT		9
-#define AXON_RAM_SECTOR_SIZE		1 << AXON_RAM_SECTOR_SHIFT
-#define AXON_RAM_IRQ_FLAGS		IRQF_SHARED | IRQF_TRIGGER_RISING
-
-static int azfs_major, azfs_minor;
-
-struct axon_ram_bank {
-	struct platform_device	*device;
-	struct gendisk		*disk;
-	struct dax_device	*dax_dev;
-	unsigned int		irq_id;
-	unsigned long		ph_addr;
-	unsigned long		io_addr;
-	unsigned long		size;
-	unsigned long		ecc_counter;
-};
-
-static ssize_t
-axon_ram_sysfs_ecc(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct platform_device *device = to_platform_device(dev);
-	struct axon_ram_bank *bank = device->dev.platform_data;
-
-	BUG_ON(!bank);
-
-	return sprintf(buf, "%ld\n", bank->ecc_counter);
-}
-
-static DEVICE_ATTR(ecc, S_IRUGO, axon_ram_sysfs_ecc, NULL);
-
-/**
- * axon_ram_irq_handler - interrupt handler for Axon RAM ECC
- * @irq: interrupt ID
- * @dev: pointer to of_device
- */
-static irqreturn_t
-axon_ram_irq_handler(int irq, void *dev)
-{
-	struct platform_device *device = dev;
-	struct axon_ram_bank *bank = device->dev.platform_data;
-
-	BUG_ON(!bank);
-
-	dev_err(&device->dev, "Correctable memory error occurred\n");
-	bank->ecc_counter++;
-	return IRQ_HANDLED;
-}
-
-/**
- * axon_ram_make_request - make_request() method for block device
- * @queue, @bio: see blk_queue_make_request()
- */
-static blk_qc_t
-axon_ram_make_request(struct request_queue *queue, struct bio *bio)
-{
-	struct axon_ram_bank *bank = bio->bi_disk->private_data;
-	unsigned long phys_mem, phys_end;
-	void *user_mem;
-	struct bio_vec vec;
-	unsigned int transfered;
-	struct bvec_iter iter;
-
-	phys_mem = bank->io_addr + (bio->bi_iter.bi_sector <<
-				    AXON_RAM_SECTOR_SHIFT);
-	phys_end = bank->io_addr + bank->size;
-	transfered = 0;
-	bio_for_each_segment(vec, bio, iter) {
-		if (unlikely(phys_mem + vec.bv_len > phys_end)) {
-			bio_io_error(bio);
-			return BLK_QC_T_NONE;
-		}
-
-		user_mem = page_address(vec.bv_page) + vec.bv_offset;
-		if (bio_data_dir(bio) == READ)
-			memcpy(user_mem, (void *) phys_mem, vec.bv_len);
-		else
-			memcpy((void *) phys_mem, user_mem, vec.bv_len);
-
-		phys_mem += vec.bv_len;
-		transfered += vec.bv_len;
-	}
-	bio_endio(bio);
-	return BLK_QC_T_NONE;
-}
-
-static const struct block_device_operations axon_ram_devops = {
-	.owner		= THIS_MODULE,
-};
-
-static long
-__axon_ram_direct_access(struct axon_ram_bank *bank, pgoff_t pgoff, long nr_pages,
-		       void **kaddr, pfn_t *pfn)
-{
-	resource_size_t offset = pgoff * PAGE_SIZE;
-
-	*kaddr = (void *) bank->io_addr + offset;
-	*pfn = phys_to_pfn_t(bank->ph_addr + offset, PFN_DEV);
-	return (bank->size - offset) / PAGE_SIZE;
-}
-
-static long
-axon_ram_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		       void **kaddr, pfn_t *pfn)
-{
-	struct axon_ram_bank *bank = dax_get_private(dax_dev);
-
-	return __axon_ram_direct_access(bank, pgoff, nr_pages, kaddr, pfn);
-}
-
-static size_t axon_ram_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	return copy_from_iter(addr, bytes, i);
-}
-
-static const struct dax_operations axon_ram_dax_ops = {
-	.direct_access = axon_ram_dax_direct_access,
-	.copy_from_iter = axon_ram_copy_from_iter,
-};
-
-/**
- * axon_ram_probe - probe() method for platform driver
- * @device: see platform_driver method
- */
-static int axon_ram_probe(struct platform_device *device)
-{
-	static int axon_ram_bank_id = -1;
-	struct axon_ram_bank *bank;
-	struct resource resource;
-	int rc;
-
-	axon_ram_bank_id++;
-
-	dev_info(&device->dev, "Found memory controller on %pOF\n",
-			device->dev.of_node);
-
-	bank = kzalloc(sizeof(*bank), GFP_KERNEL);
-	if (!bank)
-		return -ENOMEM;
-
-	device->dev.platform_data = bank;
-
-	bank->device = device;
-
-	if (of_address_to_resource(device->dev.of_node, 0, &resource) != 0) {
-		dev_err(&device->dev, "Cannot access device tree\n");
-		rc = -EFAULT;
-		goto failed;
-	}
-
-	bank->size = resource_size(&resource);
-
-	if (bank->size == 0) {
-		dev_err(&device->dev, "No DDR2 memory found for %s%d\n",
-				AXON_RAM_DEVICE_NAME, axon_ram_bank_id);
-		rc = -ENODEV;
-		goto failed;
-	}
-
-	dev_info(&device->dev, "Register DDR2 memory device %s%d with %luMB\n",
-			AXON_RAM_DEVICE_NAME, axon_ram_bank_id, bank->size >> 20);
-
-	bank->ph_addr = resource.start;
-	bank->io_addr = (unsigned long) ioremap_prot(
-			bank->ph_addr, bank->size, _PAGE_NO_CACHE);
-	if (bank->io_addr == 0) {
-		dev_err(&device->dev, "ioremap() failed\n");
-		rc = -EFAULT;
-		goto failed;
-	}
-
-	bank->disk = alloc_disk(AXON_RAM_MINORS_PER_DISK);
-	if (bank->disk == NULL) {
-		dev_err(&device->dev, "Cannot register disk\n");
-		rc = -EFAULT;
-		goto failed;
-	}
-
-
-	bank->disk->major = azfs_major;
-	bank->disk->first_minor = azfs_minor;
-	bank->disk->fops = &axon_ram_devops;
-	bank->disk->private_data = bank;
-
-	sprintf(bank->disk->disk_name, "%s%d",
-			AXON_RAM_DEVICE_NAME, axon_ram_bank_id);
-
-	bank->dax_dev = alloc_dax(bank, bank->disk->disk_name,
-			&axon_ram_dax_ops);
-	if (!bank->dax_dev) {
-		rc = -ENOMEM;
-		goto failed;
-	}
-
-	bank->disk->queue = blk_alloc_queue(GFP_KERNEL);
-	if (bank->disk->queue == NULL) {
-		dev_err(&device->dev, "Cannot register disk queue\n");
-		rc = -EFAULT;
-		goto failed;
-	}
-
-	set_capacity(bank->disk, bank->size >> AXON_RAM_SECTOR_SHIFT);
-	blk_queue_make_request(bank->disk->queue, axon_ram_make_request);
-	blk_queue_logical_block_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE);
-	device_add_disk(&device->dev, bank->disk);
-
-	bank->irq_id = irq_of_parse_and_map(device->dev.of_node, 0);
-	if (!bank->irq_id) {
-		dev_err(&device->dev, "Cannot access ECC interrupt ID\n");
-		rc = -EFAULT;
-		goto failed;
-	}
-
-	rc = request_irq(bank->irq_id, axon_ram_irq_handler,
-			AXON_RAM_IRQ_FLAGS, bank->disk->disk_name, device);
-	if (rc != 0) {
-		dev_err(&device->dev, "Cannot register ECC interrupt handler\n");
-		bank->irq_id = 0;
-		rc = -EFAULT;
-		goto failed;
-	}
-
-	rc = device_create_file(&device->dev, &dev_attr_ecc);
-	if (rc != 0) {
-		dev_err(&device->dev, "Cannot create sysfs file\n");
-		rc = -EFAULT;
-		goto failed;
-	}
-
-	azfs_minor += bank->disk->minors;
-
-	return 0;
-
-failed:
-	if (bank->irq_id)
-		free_irq(bank->irq_id, device);
-	if (bank->disk != NULL) {
-		if (bank->disk->major > 0)
-			unregister_blkdev(bank->disk->major,
-					bank->disk->disk_name);
-		if (bank->disk->flags & GENHD_FL_UP)
-			del_gendisk(bank->disk);
-		put_disk(bank->disk);
-	}
-	kill_dax(bank->dax_dev);
-	put_dax(bank->dax_dev);
-	device->dev.platform_data = NULL;
-	if (bank->io_addr != 0)
-		iounmap((void __iomem *) bank->io_addr);
-	kfree(bank);
-	return rc;
-}
-
-/**
- * axon_ram_remove - remove() method for platform driver
- * @device: see of_platform_driver method
- */
-static int
-axon_ram_remove(struct platform_device *device)
-{
-	struct axon_ram_bank *bank = device->dev.platform_data;
-
-	BUG_ON(!bank || !bank->disk);
-
-	device_remove_file(&device->dev, &dev_attr_ecc);
-	free_irq(bank->irq_id, device);
-	kill_dax(bank->dax_dev);
-	put_dax(bank->dax_dev);
-	del_gendisk(bank->disk);
-	put_disk(bank->disk);
-	iounmap((void __iomem *) bank->io_addr);
-	kfree(bank);
-
-	return 0;
-}
-
-static const struct of_device_id axon_ram_device_id[] = {
-	{
-		.type	= "dma-memory"
-	},
-	{}
-};
-MODULE_DEVICE_TABLE(of, axon_ram_device_id);
-
-static struct platform_driver axon_ram_driver = {
-	.probe		= axon_ram_probe,
-	.remove		= axon_ram_remove,
-	.driver = {
-		.name = AXON_RAM_MODULE_NAME,
-		.of_match_table = axon_ram_device_id,
-	},
-};
-
-/**
- * axon_ram_init
- */
-static int __init
-axon_ram_init(void)
-{
-	azfs_major = register_blkdev(azfs_major, AXON_RAM_DEVICE_NAME);
-	if (azfs_major < 0) {
-		printk(KERN_ERR "%s cannot become block device major number\n",
-				AXON_RAM_MODULE_NAME);
-		return -EFAULT;
-	}
-	azfs_minor = 0;
-
-	return platform_driver_register(&axon_ram_driver);
-}
-
-/**
- * axon_ram_exit
- */
-static void __exit
-axon_ram_exit(void)
-{
-	platform_driver_unregister(&axon_ram_driver);
-	unregister_blkdev(azfs_major, AXON_RAM_DEVICE_NAME);
-}
-
-module_init(axon_ram_init);
-module_exit(axon_ram_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Maxim Shchetynin <maxim@de.ibm.com>");
-MODULE_DESCRIPTION("Axon DDR2 RAM device driver for IBM Cell BE");
diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c
index c6f154b602fb..5240d3a74a10 100644
--- a/arch/powerpc/sysdev/cpm1.c
+++ b/arch/powerpc/sysdev/cpm1.c
@@ -629,8 +629,9 @@ static int cpm1_gpio16_dir_in(struct gpio_chip *gc, unsigned int gpio)
 	return 0;
 }
 
-int cpm1_gpiochip_add16(struct device_node *np)
+int cpm1_gpiochip_add16(struct device *dev)
 {
+	struct device_node *np = dev->of_node;
 	struct cpm1_gpio16_chip *cpm1_gc;
 	struct of_mm_gpio_chip *mm_gc;
 	struct gpio_chip *gc;
@@ -660,6 +661,8 @@ int cpm1_gpiochip_add16(struct device_node *np)
 	gc->get = cpm1_gpio16_get;
 	gc->set = cpm1_gpio16_set;
 	gc->to_irq = cpm1_gpio16_to_irq;
+	gc->parent = dev;
+	gc->owner = THIS_MODULE;
 
 	return of_mm_gpiochip_add_data(np, mm_gc, cpm1_gc);
 }
@@ -755,8 +758,9 @@ static int cpm1_gpio32_dir_in(struct gpio_chip *gc, unsigned int gpio)
 	return 0;
 }
 
-int cpm1_gpiochip_add32(struct device_node *np)
+int cpm1_gpiochip_add32(struct device *dev)
 {
+	struct device_node *np = dev->of_node;
 	struct cpm1_gpio32_chip *cpm1_gc;
 	struct of_mm_gpio_chip *mm_gc;
 	struct gpio_chip *gc;
@@ -776,31 +780,10 @@ int cpm1_gpiochip_add32(struct device_node *np)
 	gc->direction_output = cpm1_gpio32_dir_out;
 	gc->get = cpm1_gpio32_get;
 	gc->set = cpm1_gpio32_set;
+	gc->parent = dev;
+	gc->owner = THIS_MODULE;
 
 	return of_mm_gpiochip_add_data(np, mm_gc, cpm1_gc);
 }
 
-static int cpm_init_par_io(void)
-{
-	struct device_node *np;
-
-	for_each_compatible_node(np, NULL, "fsl,cpm1-pario-bank-a")
-		cpm1_gpiochip_add16(np);
-
-	for_each_compatible_node(np, NULL, "fsl,cpm1-pario-bank-b")
-		cpm1_gpiochip_add32(np);
-
-	for_each_compatible_node(np, NULL, "fsl,cpm1-pario-bank-c")
-		cpm1_gpiochip_add16(np);
-
-	for_each_compatible_node(np, NULL, "fsl,cpm1-pario-bank-d")
-		cpm1_gpiochip_add16(np);
-
-	/* Port E uses CPM2 layout */
-	for_each_compatible_node(np, NULL, "fsl,cpm1-pario-bank-e")
-		cpm2_gpiochip_add32(np);
-	return 0;
-}
-arch_initcall(cpm_init_par_io);
-
 #endif /* CONFIG_8xx_GPIO */
diff --git a/arch/powerpc/sysdev/cpm2.c b/arch/powerpc/sysdev/cpm2.c
index f78ff841652c..07718b9a2c99 100644
--- a/arch/powerpc/sysdev/cpm2.c
+++ b/arch/powerpc/sysdev/cpm2.c
@@ -354,14 +354,3 @@ void cpm2_set_pin(int port, int pin, int flags)
 	else
 		clrbits32(&iop[port].odr, pin);
 }
-
-static int cpm_init_par_io(void)
-{
-	struct device_node *np;
-
-	for_each_compatible_node(np, NULL, "fsl,cpm2-pario-bank")
-		cpm2_gpiochip_add32(np);
-	return 0;
-}
-arch_initcall(cpm_init_par_io);
-
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index 51bf749a4f3a..b74508175b67 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -190,8 +190,9 @@ static int cpm2_gpio32_dir_in(struct gpio_chip *gc, unsigned int gpio)
 	return 0;
 }
 
-int cpm2_gpiochip_add32(struct device_node *np)
+int cpm2_gpiochip_add32(struct device *dev)
 {
+	struct device_node *np = dev->of_node;
 	struct cpm2_gpio32_chip *cpm2_gc;
 	struct of_mm_gpio_chip *mm_gc;
 	struct gpio_chip *gc;
@@ -211,6 +212,8 @@ int cpm2_gpiochip_add32(struct device_node *np)
 	gc->direction_output = cpm2_gpio32_dir_out;
 	gc->get = cpm2_gpio32_get;
 	gc->set = cpm2_gpio32_set;
+	gc->parent = dev;
+	gc->owner = THIS_MODULE;
 
 	return of_mm_gpiochip_add_data(np, mm_gc, cpm2_gc);
 }
diff --git a/arch/powerpc/sysdev/cpm_gpio.c b/arch/powerpc/sysdev/cpm_gpio.c
new file mode 100644
index 000000000000..0badc90be666
--- /dev/null
+++ b/arch/powerpc/sysdev/cpm_gpio.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common CPM GPIO wrapper for the CPM GPIO ports
+ *
+ * Author: Christophe Leroy <christophe.leroy@c-s.fr>
+ *
+ * Copyright 2017 CS Systemes d'Information.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/of_device.h>
+
+#include <asm/cpm.h>
+#ifdef CONFIG_8xx_GPIO
+#include <asm/cpm1.h>
+#endif
+
+static int cpm_gpio_probe(struct platform_device *ofdev)
+{
+	struct device *dev = &ofdev->dev;
+	int (*gp_add)(struct device *dev) = of_device_get_match_data(dev);
+
+	if (!gp_add)
+		return -ENODEV;
+
+	return gp_add(dev);
+}
+
+static const struct of_device_id cpm_gpio_match[] = {
+#ifdef CONFIG_8xx_GPIO
+	{
+		.compatible = "fsl,cpm1-pario-bank-a",
+		.data = cpm1_gpiochip_add16,
+	},
+	{
+		.compatible = "fsl,cpm1-pario-bank-b",
+		.data = cpm1_gpiochip_add32,
+	},
+	{
+		.compatible = "fsl,cpm1-pario-bank-c",
+		.data = cpm1_gpiochip_add16,
+	},
+	{
+		.compatible = "fsl,cpm1-pario-bank-d",
+		.data = cpm1_gpiochip_add16,
+	},
+	/* Port E uses CPM2 layout */
+	{
+		.compatible = "fsl,cpm1-pario-bank-e",
+		.data = cpm2_gpiochip_add32,
+	},
+#endif
+	{
+		.compatible = "fsl,cpm2-pario-bank",
+		.data = cpm2_gpiochip_add32,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, cpm_gpio_match);
+
+static struct platform_driver cpm_gpio_driver = {
+	.probe		= cpm_gpio_probe,
+	.driver		= {
+		.name	= "cpm-gpio",
+		.owner	= THIS_MODULE,
+		.of_match_table	= cpm_gpio_match,
+	},
+};
+
+static int __init cpm_gpio_init(void)
+{
+	return platform_driver_register(&cpm_gpio_driver);
+}
+arch_initcall(cpm_gpio_init);
+
+MODULE_AUTHOR("Christophe Leroy <christophe.leroy@c-s.fr>");
+MODULE_DESCRIPTION("Driver for CPM GPIO");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:cpm-gpio");
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 3573d54b2770..a6198d4f0f03 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -402,7 +402,7 @@ static int dart_dma_set_mask(struct device *dev, u64 dma_mask)
 	 */
 	if (dart_device_on_pcie(dev) && dma_mask >= DMA_BIT_MASK(40)) {
 		dev_info(dev, "Using 64-bit DMA iommu bypass\n");
-		set_dma_ops(dev, &dma_direct_ops);
+		set_dma_ops(dev, &dma_nommu_ops);
 	} else {
 		dev_info(dev, "Using 32-bit DMA via iommu\n");
 		set_dma_ops(dev, &dma_iommu_ops);
@@ -446,7 +446,7 @@ void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
 	controller_ops->dma_bus_setup = NULL;
 
 	/* Setup pci_dma ops */
-	set_pci_dma_ops(&dma_direct_ops);
+	set_pci_dma_ops(&dma_nommu_ops);
 }
 
 #ifdef CONFIG_PM
diff --git a/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c b/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
index 1707bf04dec6..94278e8af192 100644
--- a/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
+++ b/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
@@ -56,17 +56,16 @@ static ssize_t fsl_timer_wakeup_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
-	struct timeval interval;
-	int val = 0;
+	time64_t interval = 0;
 
 	mutex_lock(&sysfs_lock);
 	if (fsl_wakeup->timer) {
 		mpic_get_remain_time(fsl_wakeup->timer, &interval);
-		val = interval.tv_sec + 1;
+		interval++;
 	}
 	mutex_unlock(&sysfs_lock);
 
-	return sprintf(buf, "%d\n", val);
+	return sprintf(buf, "%lld\n", interval);
 }
 
 static ssize_t fsl_timer_wakeup_store(struct device *dev,
@@ -74,11 +73,10 @@ static ssize_t fsl_timer_wakeup_store(struct device *dev,
 				const char *buf,
 				size_t count)
 {
-	struct timeval interval;
+	time64_t interval;
 	int ret;
 
-	interval.tv_usec = 0;
-	if (kstrtol(buf, 0, &interval.tv_sec))
+	if (kstrtoll(buf, 0, &interval))
 		return -EINVAL;
 
 	mutex_lock(&sysfs_lock);
@@ -89,13 +87,13 @@ static ssize_t fsl_timer_wakeup_store(struct device *dev,
 		fsl_wakeup->timer = NULL;
 	}
 
-	if (!interval.tv_sec) {
+	if (!interval) {
 		mutex_unlock(&sysfs_lock);
 		return count;
 	}
 
 	fsl_wakeup->timer = mpic_request_timer(fsl_mpic_timer_irq,
-						fsl_wakeup, &interval);
+						fsl_wakeup, interval);
 	if (!fsl_wakeup->timer) {
 		mutex_unlock(&sysfs_lock);
 		return -EINVAL;
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 44cbf4c12ea1..df95102e732c 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -354,6 +354,7 @@ static int fsl_of_msi_remove(struct platform_device *ofdev)
 }
 
 static struct lock_class_key fsl_msi_irq_class;
+static struct lock_class_key fsl_msi_irq_request_class;
 
 static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 			       int offset, int irq_index)
@@ -373,7 +374,8 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 		dev_err(&dev->dev, "No memory for MSI cascade data\n");
 		return -ENOMEM;
 	}
-	irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class);
+	irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class,
+			      &fsl_msi_irq_request_class);
 	cascade_data->index = offset;
 	cascade_data->msi_data = msi;
 	cascade_data->virq = virt_msir;
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 22d98057f773..918be816b097 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -118,7 +118,7 @@ static void setup_swiotlb_ops(struct pci_controller *hose)
 {
 	if (ppc_swiotlb_enable) {
 		hose->controller_ops.dma_dev_setup = pci_dma_dev_setup_swiotlb;
-		set_pci_dma_ops(&swiotlb_dma_ops);
+		set_pci_dma_ops(&powerpc_swiotlb_dma_ops);
 	}
 }
 #else
@@ -135,7 +135,7 @@ static int fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask)
 	 * mapping that allows addressing any RAM address from across PCI.
 	 */
 	if (dev_is_pci(dev) && dma_mask >= pci64_dma_offset * 2 - 1) {
-		set_dma_ops(dev, &dma_direct_ops);
+		set_dma_ops(dev, &dma_nommu_ops);
 		set_dma_offset(dev, pci64_dma_offset);
 	}
 
@@ -448,7 +448,7 @@ static void setup_pci_atmu(struct pci_controller *hose)
 #endif
 		/* adjusting outbound windows could reclaim space in mem map */
 		if (paddr_hi < 0xffffffffull)
-			pr_warning("%pOF: WARNING: Outbound window cfg leaves "
+			pr_warn("%pOF: WARNING: Outbound window cfg leaves "
 				"gaps in memory map. Adjusting the memory map "
 				"could reduce unnecessary bounce buffering.\n",
 				hose->dn);
@@ -531,7 +531,7 @@ int fsl_add_bridge(struct platform_device *pdev, int is_primary)
 	dev = pdev->dev.of_node;
 
 	if (!of_device_is_available(dev)) {
-		pr_warning("%pOF: disabled\n", dev);
+		pr_warn("%pOF: disabled\n", dev);
 		return -ENODEV;
 	}
 
@@ -808,8 +808,8 @@ int __init mpc83xx_add_bridge(struct device_node *dev)
 	is_mpc83xx_pci = 1;
 
 	if (!of_device_is_available(dev)) {
-		pr_warning("%pOF: disabled by the firmware.\n",
-			   dev);
+		pr_warn("%pOF: disabled by the firmware.\n",
+			dev);
 		return -ENODEV;
 	}
 	pr_debug("Adding PCI host bridge %pOF\n", dev);
@@ -1070,7 +1070,7 @@ int fsl_pci_mcheck_exception(struct pt_regs *regs)
 	if (is_in_pci_mem_space(addr)) {
 		if (user_mode(regs)) {
 			pagefault_disable();
-			ret = get_user(regs->nip, &inst);
+			ret = get_user(inst, (__u32 __user *)regs->nip);
 			pagefault_enable();
 		} else {
 			ret = probe_kernel_address((void *)regs->nip, inst);
@@ -1304,10 +1304,8 @@ static int add_err_dev(struct platform_device *pdev)
 						   pdev->resource,
 						   pdev->num_resources,
 						   &pd, sizeof(pd));
-	if (IS_ERR(errdev))
-		return PTR_ERR(errdev);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(errdev);
 }
 
 static int fsl_pci_probe(struct platform_device *pdev)
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index ead3e2549ebf..73067805300a 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1008,9 +1008,8 @@ static int mpic_host_map(struct irq_domain *h, unsigned int virq,
 	if (hw == mpic->spurious_vec)
 		return -EINVAL;
 	if (mpic->protected && test_bit(hw, mpic->protected)) {
-		pr_warning("mpic: Mapping of source 0x%x failed, "
-			   "source protected by firmware !\n",\
-			   (unsigned int)hw);
+		pr_warn("mpic: Mapping of source 0x%x failed, source protected by firmware !\n",
+			(unsigned int)hw);
 		return -EPERM;
 	}
 
@@ -1040,9 +1039,8 @@ static int mpic_host_map(struct irq_domain *h, unsigned int virq,
 		return 0;
 
 	if (hw >= mpic->num_sources) {
-		pr_warning("mpic: Mapping of source 0x%x failed, "
-			   "source out of range !\n",\
-			   (unsigned int)hw);
+		pr_warn("mpic: Mapping of source 0x%x failed, source out of range !\n",
+			(unsigned int)hw);
 		return -EINVAL;
 	}
 
diff --git a/arch/powerpc/sysdev/mpic_timer.c b/arch/powerpc/sysdev/mpic_timer.c
index a418579591be..87e7c42777a8 100644
--- a/arch/powerpc/sysdev/mpic_timer.c
+++ b/arch/powerpc/sysdev/mpic_timer.c
@@ -47,9 +47,6 @@
 #define MAX_TICKS_CASCADE		(~0U)
 #define TIMER_OFFSET(num)		(1 << (TIMERS_PER_GROUP - 1 - num))
 
-/* tv_usec should be less than ONE_SECOND, otherwise use tv_sec */
-#define ONE_SECOND			1000000
-
 struct timer_regs {
 	u32	gtccr;
 	u32	res0[3];
@@ -90,51 +87,23 @@ static struct cascade_priv cascade_timer[] = {
 static LIST_HEAD(timer_group_list);
 
 static void convert_ticks_to_time(struct timer_group_priv *priv,
-		const u64 ticks, struct timeval *time)
+		const u64 ticks, time64_t *time)
 {
-	u64 tmp_sec;
-
-	time->tv_sec = (__kernel_time_t)div_u64(ticks, priv->timerfreq);
-	tmp_sec = (u64)time->tv_sec * (u64)priv->timerfreq;
-
-	time->tv_usec = 0;
-
-	if (tmp_sec <= ticks)
-		time->tv_usec = (__kernel_suseconds_t)
-			div_u64((ticks - tmp_sec) * 1000000, priv->timerfreq);
-
-	return;
+	*time = (u64)div_u64(ticks, priv->timerfreq);
 }
 
 /* the time set by the user is converted to "ticks" */
 static int convert_time_to_ticks(struct timer_group_priv *priv,
-		const struct timeval *time, u64 *ticks)
+		time64_t time, u64 *ticks)
 {
 	u64 max_value;		/* prevent u64 overflow */
-	u64 tmp = 0;
-
-	u64 tmp_sec;
-	u64 tmp_ms;
-	u64 tmp_us;
 
 	max_value = div_u64(ULLONG_MAX, priv->timerfreq);
 
-	if (time->tv_sec > max_value ||
-			(time->tv_sec == max_value && time->tv_usec > 0))
+	if (time > max_value)
 		return -EINVAL;
 
-	tmp_sec = (u64)time->tv_sec * (u64)priv->timerfreq;
-	tmp += tmp_sec;
-
-	tmp_ms = time->tv_usec / 1000;
-	tmp_ms = div_u64((u64)tmp_ms * (u64)priv->timerfreq, 1000);
-	tmp += tmp_ms;
-
-	tmp_us = time->tv_usec % 1000;
-	tmp_us = div_u64((u64)tmp_us * (u64)priv->timerfreq, 1000000);
-	tmp += tmp_us;
-
-	*ticks = tmp;
+	*ticks = (u64)time * (u64)priv->timerfreq;
 
 	return 0;
 }
@@ -223,7 +192,7 @@ static struct mpic_timer *get_cascade_timer(struct timer_group_priv *priv,
 	return allocated_timer;
 }
 
-static struct mpic_timer *get_timer(const struct timeval *time)
+static struct mpic_timer *get_timer(time64_t time)
 {
 	struct timer_group_priv *priv;
 	struct mpic_timer *timer;
@@ -277,7 +246,7 @@ static struct mpic_timer *get_timer(const struct timeval *time)
  * @handle: the timer to be started.
  *
  * It will do ->fn(->dev) callback from the hardware interrupt at
- * the ->timeval point in the future.
+ * the 'time64_t' point in the future.
  */
 void mpic_start_timer(struct mpic_timer *handle)
 {
@@ -319,7 +288,7 @@ EXPORT_SYMBOL(mpic_stop_timer);
  *
  * Query timer remaining time.
  */
-void mpic_get_remain_time(struct mpic_timer *handle, struct timeval *time)
+void mpic_get_remain_time(struct mpic_timer *handle, time64_t *time)
 {
 	struct timer_group_priv *priv = container_of(handle,
 			struct timer_group_priv, timer[handle->num]);
@@ -391,7 +360,7 @@ EXPORT_SYMBOL(mpic_free_timer);
  * else "handle" on success.
  */
 struct mpic_timer *mpic_request_timer(irq_handler_t fn, void *dev,
-					const struct timeval *time)
+				      time64_t time)
 {
 	struct mpic_timer *allocated_timer;
 	int ret;
@@ -399,11 +368,7 @@ struct mpic_timer *mpic_request_timer(irq_handler_t fn, void *dev,
 	if (list_empty(&timer_group_list))
 		return NULL;
 
-	if (!(time->tv_sec + time->tv_usec) ||
-			time->tv_sec < 0 || time->tv_usec < 0)
-		return NULL;
-
-	if (time->tv_usec > ONE_SECOND)
+	if (time < 0)
 		return NULL;
 
 	allocated_timer = get_timer(time);
diff --git a/arch/powerpc/sysdev/mv64x60_pci.c b/arch/powerpc/sysdev/mv64x60_pci.c
index d52b3b81e05f..50c411b1761e 100644
--- a/arch/powerpc/sysdev/mv64x60_pci.c
+++ b/arch/powerpc/sysdev/mv64x60_pci.c
@@ -73,7 +73,7 @@ static ssize_t mv64x60_hs_reg_write(struct file *filp, struct kobject *kobj,
 static const struct bin_attribute mv64x60_hs_reg_attr = { /* Hotswap register */
 	.attr = {
 		.name = "hs_reg",
-		.mode = S_IRUGO | S_IWUSR,
+		.mode = 0644,
 	},
 	.size  = MV64X60_VAL_LEN_MAX,
 	.read  = mv64x60_hs_reg_read,
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 2bfb9968d562..1459f4e8b698 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -241,18 +241,16 @@ static int __init icp_native_map_one_cpu(int hw_id, unsigned long addr,
 			  cpu, hw_id);
 
 	if (!request_mem_region(addr, size, rname)) {
-		pr_warning("icp_native: Could not reserve ICP MMIO"
-			   " for CPU %d, interrupt server #0x%x\n",
-			   cpu, hw_id);
+		pr_warn("icp_native: Could not reserve ICP MMIO for CPU %d, interrupt server #0x%x\n",
+			cpu, hw_id);
 		return -EBUSY;
 	}
 
 	icp_native_regs[cpu] = ioremap(addr, size);
 	kvmppc_set_xics_phys(cpu, addr);
 	if (!icp_native_regs[cpu]) {
-		pr_warning("icp_native: Failed ioremap for CPU %d, "
-			   "interrupt server #0x%x, addr %#lx\n",
-			   cpu, hw_id, addr);
+		pr_warn("icp_native: Failed ioremap for CPU %d, interrupt server #0x%x, addr %#lx\n",
+			cpu, hw_id, addr);
 		release_mem_region(addr, size);
 		return -ENOMEM;
 	}
diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c
index 1c6bf4b66f56..f85f916ba432 100644
--- a/arch/powerpc/sysdev/xics/ics-opal.c
+++ b/arch/powerpc/sysdev/xics/ics-opal.c
@@ -131,8 +131,8 @@ static int ics_opal_set_affinity(struct irq_data *d,
 
 	wanted_server = xics_get_irq_server(d->irq, cpumask, 1);
 	if (wanted_server < 0) {
-		pr_warning("%s: No online cpus in the mask %*pb for irq %d\n",
-			   __func__, cpumask_pr_args(cpumask), d->irq);
+		pr_warn("%s: No online cpus in the mask %*pb for irq %d\n",
+			__func__, cpumask_pr_args(cpumask), d->irq);
 		return -1;
 	}
 	server = ics_opal_mangle_server(wanted_server);
diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c
index 42e0c56ff81c..6aabc74688a6 100644
--- a/arch/powerpc/sysdev/xics/ics-rtas.c
+++ b/arch/powerpc/sysdev/xics/ics-rtas.c
@@ -141,8 +141,8 @@ static int ics_rtas_set_affinity(struct irq_data *d,
 
 	irq_server = xics_get_irq_server(d->irq, cpumask, 1);
 	if (irq_server == -1) {
-		pr_warning("%s: No online cpus in the mask %*pb for irq %d\n",
-			   __func__, cpumask_pr_args(cpumask), d->irq);
+		pr_warn("%s: No online cpus in the mask %*pb for irq %d\n",
+			__func__, cpumask_pr_args(cpumask), d->irq);
 		return -1;
 	}
 
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index ffe138b8b9dc..77e864d5506d 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -243,8 +243,8 @@ void xics_migrate_irqs_away(void)
 
 		/* This is expected during cpu offline. */
 		if (cpu_online(cpu))
-			pr_warning("IRQ %u affinity broken off cpu %u\n",
-			       virq, cpu);
+			pr_warn("IRQ %u affinity broken off cpu %u\n",
+				virq, cpu);
 
 		/* Reset affinity to all cpus */
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -466,7 +466,7 @@ void __init xics_init(void)
 		    rc = icp_opal_init();
 	}
 	if (rc < 0) {
-		pr_warning("XICS: Cannot find a Presentation Controller !\n");
+		pr_warn("XICS: Cannot find a Presentation Controller !\n");
 		return;
 	}
 
@@ -481,7 +481,7 @@ void __init xics_init(void)
 	if (rc < 0)
 		rc = ics_opal_init();
 	if (rc < 0)
-		pr_warning("XICS: Cannot find a Source Controller !\n");
+		pr_warn("XICS: Cannot find a Source Controller !\n");
 
 	/* Initialize common bits */
 	xics_get_server_size();
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index a3b8d7d1316e..40c06110821c 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -367,7 +367,8 @@ static void xive_irq_eoi(struct irq_data *d)
 	 * EOI the source if it hasn't been disabled and hasn't
 	 * been passed-through to a KVM guest
 	 */
-	if (!irqd_irq_disabled(d) && !irqd_is_forwarded_to_vcpu(d))
+	if (!irqd_irq_disabled(d) && !irqd_is_forwarded_to_vcpu(d) &&
+	    !(xd->flags & XIVE_IRQ_NO_EOI))
 		xive_do_source_eoi(irqd_to_hwirq(d), xd);
 
 	/*
@@ -1269,11 +1270,6 @@ static void xive_setup_cpu(void)
 {
 	struct xive_cpu *xc = __this_cpu_read(xive_cpu);
 
-	/* Debug: Dump the TM state */
-	pr_devel("CPU %d [HW 0x%02x] VT=%02x\n",
-	    smp_processor_id(), hard_smp_processor_id(),
-	    in_8(xive_tima + xive_tima_offset + TM_WORD2));
-
 	/* The backend might have additional things to do */
 	if (xive_ops->setup_cpu)
 		xive_ops->setup_cpu(smp_processor_id(), xc);
diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c
index 31db8c072acd..9deea5ee13f6 100644
--- a/arch/powerpc/xmon/ppc-dis.c
+++ b/arch/powerpc/xmon/ppc-dis.c
@@ -93,10 +93,6 @@ lookup_powerpc (unsigned long insn, ppc_cpu_t dialect)
 {
   const struct powerpc_opcode *opcode;
   const struct powerpc_opcode *opcode_end;
-  unsigned long op;
-
-  /* Get the major opcode of the instruction.  */
-  op = PPC_OP (insn);
 
   opcode_end = powerpc_opcodes + powerpc_num_opcodes;
   /* Find the first match in the opcode table for this major opcode.  */
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 1b2d8cb49abb..82e1a3ee6e0f 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1590,7 +1590,7 @@ static void print_bug_trap(struct pt_regs *regs)
 	printf("kernel BUG at %s:%u!\n",
 	       bug->file, bug->line);
 #else
-	printf("kernel BUG at %p!\n", (void *)bug->bug_addr);
+	printf("kernel BUG at %px!\n", (void *)bug->bug_addr);
 #endif
 #endif /* CONFIG_BUG */
 }
@@ -1623,7 +1623,7 @@ static void excprint(struct pt_regs *fp)
 	printf("  current = 0x%lx\n", current);
 #ifdef CONFIG_PPC64
 	printf("  paca    = 0x%lx\t softe: %d\t irq_happened: 0x%02x\n",
-	       local_paca, local_paca->soft_enabled, local_paca->irq_happened);
+	       local_paca, local_paca->irq_soft_mask, local_paca->irq_happened);
 #endif
 	if (current) {
 		printf("    pid   = %ld, comm = %s\n",
@@ -2329,7 +2329,7 @@ static void dump_one_paca(int cpu)
 
 	p = &paca[cpu];
 
-	printf("paca for cpu 0x%x @ %p:\n", cpu, p);
+	printf("paca for cpu 0x%x @ %px:\n", cpu, p);
 
 	printf(" %-*s = %s\n", 20, "possible", cpu_possible(cpu) ? "yes" : "no");
 	printf(" %-*s = %s\n", 20, "present", cpu_present(cpu) ? "yes" : "no");
@@ -2344,10 +2344,10 @@ static void dump_one_paca(int cpu)
 	DUMP(p, kernel_toc, "lx");
 	DUMP(p, kernelbase, "lx");
 	DUMP(p, kernel_msr, "lx");
-	DUMP(p, emergency_sp, "p");
+	DUMP(p, emergency_sp, "px");
 #ifdef CONFIG_PPC_BOOK3S_64
-	DUMP(p, nmi_emergency_sp, "p");
-	DUMP(p, mc_emergency_sp, "p");
+	DUMP(p, nmi_emergency_sp, "px");
+	DUMP(p, mc_emergency_sp, "px");
 	DUMP(p, in_nmi, "x");
 	DUMP(p, in_mce, "x");
 	DUMP(p, hmi_event_available, "x");
@@ -2375,23 +2375,25 @@ static void dump_one_paca(int cpu)
 	DUMP(p, slb_cache_ptr, "x");
 	for (i = 0; i < SLB_CACHE_ENTRIES; i++)
 		printf(" slb_cache[%d]:        = 0x%016lx\n", i, p->slb_cache[i]);
+
+	DUMP(p, rfi_flush_fallback_area, "px");
 #endif
 	DUMP(p, dscr_default, "llx");
 #ifdef CONFIG_PPC_BOOK3E
-	DUMP(p, pgd, "p");
-	DUMP(p, kernel_pgd, "p");
-	DUMP(p, tcd_ptr, "p");
-	DUMP(p, mc_kstack, "p");
-	DUMP(p, crit_kstack, "p");
-	DUMP(p, dbg_kstack, "p");
+	DUMP(p, pgd, "px");
+	DUMP(p, kernel_pgd, "px");
+	DUMP(p, tcd_ptr, "px");
+	DUMP(p, mc_kstack, "px");
+	DUMP(p, crit_kstack, "px");
+	DUMP(p, dbg_kstack, "px");
 #endif
-	DUMP(p, __current, "p");
+	DUMP(p, __current, "px");
 	DUMP(p, kstack, "lx");
 	printf(" kstack_base          = 0x%016lx\n", p->kstack & ~(THREAD_SIZE - 1));
 	DUMP(p, stab_rr, "lx");
 	DUMP(p, saved_r1, "lx");
 	DUMP(p, trap_save, "x");
-	DUMP(p, soft_enabled, "x");
+	DUMP(p, irq_soft_mask, "x");
 	DUMP(p, irq_happened, "x");
 	DUMP(p, io_sync, "x");
 	DUMP(p, irq_work_pending, "x");
@@ -2403,7 +2405,7 @@ static void dump_one_paca(int cpu)
 #endif
 
 #ifdef CONFIG_PPC_POWERNV
-	DUMP(p, core_idle_state_ptr, "p");
+	DUMP(p, core_idle_state_ptr, "px");
 	DUMP(p, thread_idle_state, "x");
 	DUMP(p, thread_mask, "x");
 	DUMP(p, subcore_sibling_mask, "x");
@@ -2945,7 +2947,7 @@ static void show_task(struct task_struct *tsk)
 		(tsk->exit_state & EXIT_DEAD) ? 'E' :
 		(tsk->state & TASK_INTERRUPTIBLE) ? 'S' : '?';
 
-	printf("%p %016lx %6d %6d %c %2d %s\n", tsk,
+	printf("%px %016lx %6d %6d %c %2d %s\n", tsk,
 		tsk->thread.ksp,
 		tsk->pid, tsk->parent->pid,
 		state, task_thread_info(tsk)->cpu,
@@ -2988,7 +2990,7 @@ static void show_pte(unsigned long addr)
 
 	if (setjmp(bus_error_jmp) != 0) {
 		catch_memory_errors = 0;
-		printf("*** Error dumping pte for task %p\n", tsk);
+		printf("*** Error dumping pte for task %px\n", tsk);
 		return;
 	}
 
@@ -3074,7 +3076,7 @@ static void show_tasks(void)
 
 	if (setjmp(bus_error_jmp) != 0) {
 		catch_memory_errors = 0;
-		printf("*** Error dumping task %p\n", tsk);
+		printf("*** Error dumping task %px\n", tsk);
 		return;
 	}
 
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 2c6adf12713a..865e14f50c14 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -83,7 +83,7 @@ config PGTABLE_LEVELS
 config HAVE_KPROBES
 	def_bool n
 
-config DMA_NOOP_OPS
+config DMA_DIRECT_OPS
 	def_bool y
 
 menu "Platform type"
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index e69de29bb2d1..47dacf06c679 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -0,0 +1,75 @@
+CONFIG_SMP=y
+CONFIG_PCI=y
+CONFIG_PCIE_XILINX=y
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_CHECKPOINT_RESTORE=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NETLINK_DIAG=y
+CONFIG_DEVTMPFS=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+CONFIG_MACB=y
+CONFIG_E1000E=y
+CONFIG_R8169=y
+CONFIG_MICROSEMI_PHY=y
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_DRM=y
+CONFIG_DRM_RADEON=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
+CONFIG_USB_XHCI_PLATFORM=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_UAS=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_RAS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
+# CONFIG_RCU_TRACE is not set
+CONFIG_CRYPTO_USER_API_HASH=y
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 18158be62a2b..681ac0d09314 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -1,12 +1,12 @@
 generic-y += bugs.h
 generic-y += cacheflush.h
 generic-y += checksum.h
-generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += dma.h
 generic-y += dma-contiguous.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
@@ -40,6 +40,7 @@ generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += sembuf.h
+generic-y += serial.h
 generic-y += setup.h
 generic-y += shmbuf.h
 generic-y += shmparam.h
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 6cbbb6a68d76..5ad4cb622bed 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -58,17 +58,17 @@
 #endif
 
 #if (__SIZEOF_INT__ == 4)
-#define INT		__ASM_STR(.word)
-#define SZINT		__ASM_STR(4)
-#define LGINT		__ASM_STR(2)
+#define RISCV_INT		__ASM_STR(.word)
+#define RISCV_SZINT		__ASM_STR(4)
+#define RISCV_LGINT		__ASM_STR(2)
 #else
 #error "Unexpected __SIZEOF_INT__"
 #endif
 
 #if (__SIZEOF_SHORT__ == 2)
-#define SHORT		__ASM_STR(.half)
-#define SZSHORT		__ASM_STR(2)
-#define LGSHORT		__ASM_STR(1)
+#define RISCV_SHORT		__ASM_STR(.half)
+#define RISCV_SZSHORT		__ASM_STR(2)
+#define RISCV_LGSHORT		__ASM_STR(1)
 #else
 #error "Unexpected __SIZEOF_SHORT__"
 #endif
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index e2e37c57cbeb..e65d1cd89e28 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -50,30 +50,30 @@ static __always_inline void atomic64_set(atomic64_t *v, long i)
  * have the AQ or RL bits set.  These don't return anything, so there's only
  * one version to worry about.
  */
-#define ATOMIC_OP(op, asm_op, c_op, I, asm_type, c_type, prefix)				\
-static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)		\
-{												\
-	__asm__ __volatile__ (									\
-		"amo" #asm_op "." #asm_type " zero, %1, %0"					\
-		: "+A" (v->counter)								\
-		: "r" (I)									\
-		: "memory");									\
+#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix)				\
+static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)	\
+{											\
+	__asm__ __volatile__ (								\
+		"amo" #asm_op "." #asm_type " zero, %1, %0"				\
+		: "+A" (v->counter)							\
+		: "r" (I)								\
+		: "memory");								\
 }
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I)			\
-        ATOMIC_OP (op, asm_op, c_op, I, w,  int,   )
+#define ATOMIC_OPS(op, asm_op, I)			\
+        ATOMIC_OP (op, asm_op, I, w,  int,   )
 #else
-#define ATOMIC_OPS(op, asm_op, c_op, I)			\
-        ATOMIC_OP (op, asm_op, c_op, I, w,  int,   )	\
-        ATOMIC_OP (op, asm_op, c_op, I, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, I)			\
+        ATOMIC_OP (op, asm_op, I, w,  int,   )	\
+        ATOMIC_OP (op, asm_op, I, d, long, 64)
 #endif
 
-ATOMIC_OPS(add, add, +,  i)
-ATOMIC_OPS(sub, add, +, -i)
-ATOMIC_OPS(and, and, &,  i)
-ATOMIC_OPS( or,  or, |,  i)
-ATOMIC_OPS(xor, xor, ^,  i)
+ATOMIC_OPS(add, add,  i)
+ATOMIC_OPS(sub, add, -i)
+ATOMIC_OPS(and, and,  i)
+ATOMIC_OPS( or,  or,  i)
+ATOMIC_OPS(xor, xor,  i)
 
 #undef ATOMIC_OP
 #undef ATOMIC_OPS
@@ -83,7 +83,7 @@ ATOMIC_OPS(xor, xor, ^,  i)
  * There's two flavors of these: the arithmatic ops have both fetch and return
  * versions, while the logical ops only have fetch versions.
  */
-#define ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix)			\
+#define ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, asm_type, c_type, prefix)				\
 static __always_inline c_type atomic##prefix##_fetch_##op##c_or(c_type i, atomic##prefix##_t *v)	\
 {													\
 	register c_type ret;										\
@@ -103,13 +103,13 @@ static __always_inline c_type atomic##prefix##_##op##_return##c_or(c_type i, ato
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
+        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, w,  int,   )	\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
+        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, w,  int,   )	\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, d, long, 64)	\
+        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, d, long, 64)	\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
 #endif
 
@@ -126,28 +126,28 @@ ATOMIC_OPS(sub, add, +, -i, .aqrl,         )
 #undef ATOMIC_OPS
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )
+#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or)				\
+        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w,  int,   )
 #else
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )		\
-        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or)				\
+        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w,  int,   )	\
+        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, d, long, 64)
 #endif
 
-ATOMIC_OPS(and, and, &,  i,      , _relaxed)
-ATOMIC_OPS(and, and, &,  i, .aq  , _acquire)
-ATOMIC_OPS(and, and, &,  i, .rl  , _release)
-ATOMIC_OPS(and, and, &,  i, .aqrl,         )
+ATOMIC_OPS(and, and, i,      , _relaxed)
+ATOMIC_OPS(and, and, i, .aq  , _acquire)
+ATOMIC_OPS(and, and, i, .rl  , _release)
+ATOMIC_OPS(and, and, i, .aqrl,         )
 
-ATOMIC_OPS( or,  or, |,  i,      , _relaxed)
-ATOMIC_OPS( or,  or, |,  i, .aq  , _acquire)
-ATOMIC_OPS( or,  or, |,  i, .rl  , _release)
-ATOMIC_OPS( or,  or, |,  i, .aqrl,         )
+ATOMIC_OPS( or,  or, i,      , _relaxed)
+ATOMIC_OPS( or,  or, i, .aq  , _acquire)
+ATOMIC_OPS( or,  or, i, .rl  , _release)
+ATOMIC_OPS( or,  or, i, .aqrl,         )
 
-ATOMIC_OPS(xor, xor, ^,  i,      , _relaxed)
-ATOMIC_OPS(xor, xor, ^,  i, .aq  , _acquire)
-ATOMIC_OPS(xor, xor, ^,  i, .rl  , _release)
-ATOMIC_OPS(xor, xor, ^,  i, .aqrl,         )
+ATOMIC_OPS(xor, xor, i,      , _relaxed)
+ATOMIC_OPS(xor, xor, i, .aq  , _acquire)
+ATOMIC_OPS(xor, xor, i, .rl  , _release)
+ATOMIC_OPS(xor, xor, i, .aqrl,         )
 
 #undef ATOMIC_OPS
 
@@ -182,13 +182,13 @@ ATOMIC_OPS(add_negative, add,  <, 0)
 #undef ATOMIC_OP
 #undef ATOMIC_OPS
 
-#define ATOMIC_OP(op, func_op, c_op, I, c_type, prefix)				\
+#define ATOMIC_OP(op, func_op, I, c_type, prefix)				\
 static __always_inline void atomic##prefix##_##op(atomic##prefix##_t *v)	\
 {										\
 	atomic##prefix##_##func_op(I, v);					\
 }
 
-#define ATOMIC_FETCH_OP(op, func_op, c_op, I, c_type, prefix)				\
+#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix)					\
 static __always_inline c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v)	\
 {											\
 	return atomic##prefix##_fetch_##func_op(I, v);					\
@@ -202,16 +202,16 @@ static __always_inline c_type atomic##prefix##_##op##_return(atomic##prefix##_t
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, c_op, I)						\
-        ATOMIC_OP       (op, asm_op, c_op, I,  int,   )				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I,  int,   )				\
+        ATOMIC_OP       (op, asm_op,       I,  int,   )				\
+        ATOMIC_FETCH_OP (op, asm_op,       I,  int,   )				\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, c_op, I)						\
-        ATOMIC_OP       (op, asm_op, c_op, I,  int,   )				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I,  int,   )				\
+        ATOMIC_OP       (op, asm_op,       I,  int,   )				\
+        ATOMIC_FETCH_OP (op, asm_op,       I,  int,   )				\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )				\
-        ATOMIC_OP       (op, asm_op, c_op, I, long, 64)				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, long, 64)				\
+        ATOMIC_OP       (op, asm_op,       I, long, 64)				\
+        ATOMIC_FETCH_OP (op, asm_op,       I, long, 64)				\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
 #endif
 
@@ -300,8 +300,13 @@ static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
 
 /*
  * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
- * {cmp,}xchg and the operations that return, so they need a barrier.  We just
- * use the other implementations directly.
+ * {cmp,}xchg and the operations that return, so they need a barrier.
+ */
+/*
+ * FIXME: atomic_cmpxchg_{acquire,release,relaxed} are all implemented by
+ * assigning the same barrier to both the LR and SC operations, but that might
+ * not make any sense.  We're waiting on a memory model specification to
+ * determine exactly what the right thing to do is here.
  */
 #define ATOMIC_OP(c_t, prefix, c_or, size, asm_or)						\
 static __always_inline c_t atomic##prefix##_cmpxchg##c_or(atomic##prefix##_t *v, c_t o, c_t n) 	\
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index 183534b7c39b..c0319cbf1eec 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -39,27 +39,23 @@
 #define smp_wmb()	RISCV_FENCE(w,w)
 
 /*
- * These fences exist to enforce ordering around the relaxed AMOs.  The
- * documentation defines that
- * "
- *     atomic_fetch_add();
- *   is equivalent to:
- *     smp_mb__before_atomic();
- *     atomic_fetch_add_relaxed();
- *     smp_mb__after_atomic();
- * "
- * So we emit full fences on both sides.
- */
-#define __smb_mb__before_atomic()	smp_mb()
-#define __smb_mb__after_atomic()	smp_mb()
-
-/*
- * These barriers prevent accesses performed outside a spinlock from being moved
- * inside a spinlock.  Since RISC-V sets the aq/rl bits on our spinlock only
- * enforce release consistency, we need full fences here.
+ * This is a very specific barrier: it's currently only used in two places in
+ * the kernel, both in the scheduler.  See include/linux/spinlock.h for the two
+ * orderings it guarantees, but the "critical section is RCsc" guarantee
+ * mandates a barrier on RISC-V.  The sequence looks like:
+ *
+ *    lr.aq lock
+ *    sc    lock <= LOCKED
+ *    smp_mb__after_spinlock()
+ *    // critical section
+ *    lr    lock
+ *    sc.rl lock <= UNLOCKED
+ *
+ * The AQ/RL pair provides a RCpc critical section, but there's not really any
+ * way we can take advantage of that here because the ordering is only enforced
+ * on that one lock.  Thus, we're just doing a full fence.
  */
-#define smb_mb__before_spinlock()	smp_mb()
-#define smb_mb__after_spinlock()	smp_mb()
+#define smp_mb__after_spinlock()	RISCV_FENCE(rw,rw)
 
 #include <asm-generic/barrier.h>
 
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 7c281ef1d583..f30daf26f08f 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -67,7 +67,7 @@
 		: "memory");
 
 #define __test_and_op_bit(op, mod, nr, addr) 			\
-	__test_and_op_bit_ord(op, mod, nr, addr, )
+	__test_and_op_bit_ord(op, mod, nr, addr, .aqrl)
 #define __op_bit(op, mod, nr, addr)				\
 	__op_bit_ord(op, mod, nr, addr, )
 
diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h
index c3e13764a943..bfc7f099ab1f 100644
--- a/arch/riscv/include/asm/bug.h
+++ b/arch/riscv/include/asm/bug.h
@@ -27,8 +27,8 @@
 typedef u32 bug_insn_t;
 
 #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
-#define __BUG_ENTRY_ADDR	INT " 1b - 2b"
-#define __BUG_ENTRY_FILE	INT " %0 - 2b"
+#define __BUG_ENTRY_ADDR	RISCV_INT " 1b - 2b"
+#define __BUG_ENTRY_FILE	RISCV_INT " %0 - 2b"
 #else
 #define __BUG_ENTRY_ADDR	RISCV_PTR " 1b"
 #define __BUG_ENTRY_FILE	RISCV_PTR " %0"
@@ -38,7 +38,7 @@ typedef u32 bug_insn_t;
 #define __BUG_ENTRY			\
 	__BUG_ENTRY_ADDR "\n\t"		\
 	__BUG_ENTRY_FILE "\n\t"		\
-	SHORT " %1"
+	RISCV_SHORT " %1"
 #else
 #define __BUG_ENTRY			\
 	__BUG_ENTRY_ADDR
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 0595585013b0..efd89a88d2d0 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -18,22 +18,44 @@
 
 #undef flush_icache_range
 #undef flush_icache_user_range
+#undef flush_dcache_page
 
 static inline void local_flush_icache_all(void)
 {
 	asm volatile ("fence.i" ::: "memory");
 }
 
+#define PG_dcache_clean PG_arch_1
+
+static inline void flush_dcache_page(struct page *page)
+{
+	if (test_bit(PG_dcache_clean, &page->flags))
+		clear_bit(PG_dcache_clean, &page->flags);
+}
+
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range(start, end) flush_icache_all()
+#define flush_icache_user_range(vma, pg, addr, len) flush_icache_all()
+
 #ifndef CONFIG_SMP
 
-#define flush_icache_range(start, end) local_flush_icache_all()
-#define flush_icache_user_range(vma, pg, addr, len) local_flush_icache_all()
+#define flush_icache_all() local_flush_icache_all()
+#define flush_icache_mm(mm, local) flush_icache_all()
 
 #else /* CONFIG_SMP */
 
-#define flush_icache_range(start, end) sbi_remote_fence_i(0)
-#define flush_icache_user_range(vma, pg, addr, len) sbi_remote_fence_i(0)
+#define flush_icache_all() sbi_remote_fence_i(0)
+void flush_icache_mm(struct mm_struct *mm, bool local);
 
 #endif /* CONFIG_SMP */
 
+/*
+ * Bits in sys_riscv_flush_icache()'s flags argument.
+ */
+#define SYS_RISCV_FLUSH_ICACHE_LOCAL 1UL
+#define SYS_RISCV_FLUSH_ICACHE_ALL   (SYS_RISCV_FLUSH_ICACHE_LOCAL)
+
 #endif /* _ASM_RISCV_CACHEFLUSH_H */
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 0d64bc9f4f91..3c7a2c97e377 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -17,10 +17,10 @@
 #include <linux/const.h>
 
 /* Status register flags */
-#define SR_IE   _AC(0x00000002, UL) /* Interrupt Enable */
-#define SR_PIE  _AC(0x00000020, UL) /* Previous IE */
-#define SR_PS   _AC(0x00000100, UL) /* Previously Supervisor */
-#define SR_SUM  _AC(0x00040000, UL) /* Supervisor may access User Memory */
+#define SR_SIE	_AC(0x00000002, UL) /* Supervisor Interrupt Enable */
+#define SR_SPIE	_AC(0x00000020, UL) /* Previous Supervisor IE */
+#define SR_SPP	_AC(0x00000100, UL) /* Previously Supervisor */
+#define SR_SUM	_AC(0x00040000, UL) /* Supervisor may access User Memory */
 
 #define SR_FS           _AC(0x00006000, UL) /* Floating-point Status */
 #define SR_FS_OFF       _AC(0x00000000, UL)
diff --git a/arch/riscv/include/asm/dma-mapping.h b/arch/riscv/include/asm/dma-mapping.h
deleted file mode 100644
index 3eec1000196d..000000000000
--- a/arch/riscv/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * Copyright (C) 2003-2004 Hewlett-Packard Co
- *	David Mosberger-Tang <davidm@hpl.hp.com>
- * Copyright (C) 2012 ARM Ltd.
- * Copyright (C) 2016 SiFive, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_RISCV_DMA_MAPPING_H
-#define __ASM_RISCV_DMA_MAPPING_H
-
-/* Use ops->dma_mapping_error (if it exists) or assume success */
-// #undef DMA_ERROR_CODE
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &dma_noop_ops;
-}
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-#endif	/* __ASM_RISCV_DMA_MAPPING_H */
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index c1f32cfcc79b..b269451e7e85 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -19,7 +19,7 @@
 #ifndef _ASM_RISCV_IO_H
 #define _ASM_RISCV_IO_H
 
-#ifdef CONFIG_MMU
+#include <linux/types.h>
 
 extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 
@@ -32,9 +32,7 @@ extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 #define ioremap_wc(addr, size) ioremap((addr), (size))
 #define ioremap_wt(addr, size) ioremap((addr), (size))
 
-extern void iounmap(void __iomem *addr);
-
-#endif /* CONFIG_MMU */
+extern void iounmap(volatile void __iomem *addr);
 
 /* Generic IO read/write.  These perform native-endian accesses. */
 #define __raw_writeb __raw_writeb
@@ -250,7 +248,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 			const ctype *buf = buffer;				\
 										\
 			do {							\
-				__raw_writeq(*buf++, addr);			\
+				__raw_write ## len(*buf++, addr);		\
 			} while (--count);					\
 		}								\
 		afence;								\
@@ -266,9 +264,9 @@ __io_reads_ins(reads, u32, l, __io_br(), __io_ar())
 __io_reads_ins(ins,  u8, b, __io_pbr(), __io_par())
 __io_reads_ins(ins, u16, w, __io_pbr(), __io_par())
 __io_reads_ins(ins, u32, l, __io_pbr(), __io_par())
-#define insb(addr, buffer, count) __insb((void __iomem *)addr, buffer, count)
-#define insw(addr, buffer, count) __insw((void __iomem *)addr, buffer, count)
-#define insl(addr, buffer, count) __insl((void __iomem *)addr, buffer, count)
+#define insb(addr, buffer, count) __insb((void __iomem *)(long)addr, buffer, count)
+#define insw(addr, buffer, count) __insw((void __iomem *)(long)addr, buffer, count)
+#define insl(addr, buffer, count) __insl((void __iomem *)(long)addr, buffer, count)
 
 __io_writes_outs(writes,  u8, b, __io_bw(), __io_aw())
 __io_writes_outs(writes, u16, w, __io_bw(), __io_aw())
@@ -280,9 +278,9 @@ __io_writes_outs(writes, u32, l, __io_bw(), __io_aw())
 __io_writes_outs(outs,  u8, b, __io_pbw(), __io_paw())
 __io_writes_outs(outs, u16, w, __io_pbw(), __io_paw())
 __io_writes_outs(outs, u32, l, __io_pbw(), __io_paw())
-#define outsb(addr, buffer, count) __outsb((void __iomem *)addr, buffer, count)
-#define outsw(addr, buffer, count) __outsw((void __iomem *)addr, buffer, count)
-#define outsl(addr, buffer, count) __outsl((void __iomem *)addr, buffer, count)
+#define outsb(addr, buffer, count) __outsb((void __iomem *)(long)addr, buffer, count)
+#define outsw(addr, buffer, count) __outsw((void __iomem *)(long)addr, buffer, count)
+#define outsl(addr, buffer, count) __outsl((void __iomem *)(long)addr, buffer, count)
 
 #ifdef CONFIG_64BIT
 __io_reads_ins(reads, u64, q, __io_br(), __io_ar())
diff --git a/arch/riscv/include/asm/irqflags.h b/arch/riscv/include/asm/irqflags.h
index 6fdc860d7f84..07a3c6d5706f 100644
--- a/arch/riscv/include/asm/irqflags.h
+++ b/arch/riscv/include/asm/irqflags.h
@@ -27,25 +27,25 @@ static inline unsigned long arch_local_save_flags(void)
 /* unconditionally enable interrupts */
 static inline void arch_local_irq_enable(void)
 {
-	csr_set(sstatus, SR_IE);
+	csr_set(sstatus, SR_SIE);
 }
 
 /* unconditionally disable interrupts */
 static inline void arch_local_irq_disable(void)
 {
-	csr_clear(sstatus, SR_IE);
+	csr_clear(sstatus, SR_SIE);
 }
 
 /* get status and disable interrupts */
 static inline unsigned long arch_local_irq_save(void)
 {
-	return csr_read_clear(sstatus, SR_IE);
+	return csr_read_clear(sstatus, SR_SIE);
 }
 
 /* test flags */
 static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
-	return !(flags & SR_IE);
+	return !(flags & SR_SIE);
 }
 
 /* test hardware interrupt enable bit */
@@ -57,7 +57,7 @@ static inline int arch_irqs_disabled(void)
 /* set interrupt enabled status */
 static inline void arch_local_irq_restore(unsigned long flags)
 {
-	csr_set(sstatus, flags & SR_IE);
+	csr_set(sstatus, flags & SR_SIE);
 }
 
 #endif /* _ASM_RISCV_IRQFLAGS_H */
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
index 66805cba9a27..5df2dccdba12 100644
--- a/arch/riscv/include/asm/mmu.h
+++ b/arch/riscv/include/asm/mmu.h
@@ -19,6 +19,10 @@
 
 typedef struct {
 	void *vdso;
+#ifdef CONFIG_SMP
+	/* A local icache flush is needed before user execution can resume. */
+	cpumask_t icache_stale_mask;
+#endif
 } mm_context_t;
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
index de1fc1631fc4..97424834dce2 100644
--- a/arch/riscv/include/asm/mmu_context.h
+++ b/arch/riscv/include/asm/mmu_context.h
@@ -1,5 +1,6 @@
 /*
  * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
  *
  *   This program is free software; you can redistribute it and/or
  *   modify it under the terms of the GNU General Public License
@@ -14,11 +15,13 @@
 #ifndef _ASM_RISCV_MMU_CONTEXT_H
 #define _ASM_RISCV_MMU_CONTEXT_H
 
+#include <linux/mm_types.h>
 #include <asm-generic/mm_hooks.h>
 
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
 
 static inline void enter_lazy_tlb(struct mm_struct *mm,
 	struct task_struct *task)
@@ -46,12 +49,54 @@ static inline void set_pgdir(pgd_t *pgd)
 	csr_write(sptbr, virt_to_pfn(pgd) | SPTBR_MODE);
 }
 
+/*
+ * When necessary, performs a deferred icache flush for the given MM context,
+ * on the local CPU.  RISC-V has no direct mechanism for instruction cache
+ * shoot downs, so instead we send an IPI that informs the remote harts they
+ * need to flush their local instruction caches.  To avoid pathologically slow
+ * behavior in a common case (a bunch of single-hart processes on a many-hart
+ * machine, ie 'make -j') we avoid the IPIs for harts that are not currently
+ * executing a MM context and instead schedule a deferred local instruction
+ * cache flush to be performed before execution resumes on each hart.  This
+ * actually performs that local instruction cache flush, which implicitly only
+ * refers to the current hart.
+ */
+static inline void flush_icache_deferred(struct mm_struct *mm)
+{
+#ifdef CONFIG_SMP
+	unsigned int cpu = smp_processor_id();
+	cpumask_t *mask = &mm->context.icache_stale_mask;
+
+	if (cpumask_test_cpu(cpu, mask)) {
+		cpumask_clear_cpu(cpu, mask);
+		/*
+		 * Ensure the remote hart's writes are visible to this hart.
+		 * This pairs with a barrier in flush_icache_mm.
+		 */
+		smp_mb();
+		local_flush_icache_all();
+	}
+#endif
+}
+
 static inline void switch_mm(struct mm_struct *prev,
 	struct mm_struct *next, struct task_struct *task)
 {
 	if (likely(prev != next)) {
+		/*
+		 * Mark the current MM context as inactive, and the next as
+		 * active.  This is at least used by the icache flushing
+		 * routines in order to determine who should
+		 */
+		unsigned int cpu = smp_processor_id();
+
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+		cpumask_set_cpu(cpu, mm_cpumask(next));
+
 		set_pgdir(next->pgd);
 		local_flush_tlb_all();
+
+		flush_icache_deferred(next);
 	}
 }
 
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 3399257780b2..16301966d65b 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -20,8 +20,6 @@
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_MMU
-
 /* Page Upper Directory not used in RISC-V */
 #include <asm-generic/pgtable-nopud.h>
 #include <asm/page.h>
@@ -178,28 +176,6 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr)
 #define pte_offset_map(dir, addr)	pte_offset_kernel((dir), (addr))
 #define pte_unmap(pte)			((void)(pte))
 
-/*
- * Certain architectures need to do special things when PTEs within
- * a page table are directly modified.  Thus, the following hook is
- * made available.
- */
-static inline void set_pte(pte_t *ptep, pte_t pteval)
-{
-	*ptep = pteval;
-}
-
-static inline void set_pte_at(struct mm_struct *mm,
-	unsigned long addr, pte_t *ptep, pte_t pteval)
-{
-	set_pte(ptep, pteval);
-}
-
-static inline void pte_clear(struct mm_struct *mm,
-	unsigned long addr, pte_t *ptep)
-{
-	set_pte_at(mm, addr, ptep, __pte(0));
-}
-
 static inline int pte_present(pte_t pte)
 {
 	return (pte_val(pte) & _PAGE_PRESENT);
@@ -210,21 +186,22 @@ static inline int pte_none(pte_t pte)
 	return (pte_val(pte) == 0);
 }
 
-/* static inline int pte_read(pte_t pte) */
-
 static inline int pte_write(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_WRITE;
 }
 
+static inline int pte_exec(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_EXEC;
+}
+
 static inline int pte_huge(pte_t pte)
 {
 	return pte_present(pte)
 		&& (pte_val(pte) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
 }
 
-/* static inline int pte_exec(pte_t pte) */
-
 static inline int pte_dirty(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_DIRTY;
@@ -311,6 +288,33 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
 	return pte_val(pte_a) == pte_val(pte_b);
 }
 
+/*
+ * Certain architectures need to do special things when PTEs within
+ * a page table are directly modified.  Thus, the following hook is
+ * made available.
+ */
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+	*ptep = pteval;
+}
+
+void flush_icache_pte(pte_t pte);
+
+static inline void set_pte_at(struct mm_struct *mm,
+	unsigned long addr, pte_t *ptep, pte_t pteval)
+{
+	if (pte_present(pteval) && pte_exec(pteval))
+		flush_icache_pte(pteval);
+
+	set_pte(ptep, pteval);
+}
+
+static inline void pte_clear(struct mm_struct *mm,
+	unsigned long addr, pte_t *ptep)
+{
+	set_pte_at(mm, addr, ptep, __pte(0));
+}
+
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 					unsigned long address, pte_t *ptep,
@@ -407,8 +411,6 @@ static inline void pgtable_cache_init(void)
 	/* No page table caches to initialize */
 }
 
-#endif /* CONFIG_MMU */
-
 #define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
 #define VMALLOC_END      (PAGE_OFFSET - 1)
 #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
index 93b8956e25e4..2c5df945d43c 100644
--- a/arch/riscv/include/asm/ptrace.h
+++ b/arch/riscv/include/asm/ptrace.h
@@ -66,7 +66,7 @@ struct pt_regs {
 #define REG_FMT "%08lx"
 #endif
 
-#define user_mode(regs) (((regs)->sstatus & SR_PS) == 0)
+#define user_mode(regs) (((regs)->sstatus & SR_SPP) == 0)
 
 
 /* Helpers for working with the instruction pointer */
diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
index 04c71d938afd..2fd27e8ef1fd 100644
--- a/arch/riscv/include/asm/spinlock.h
+++ b/arch/riscv/include/asm/spinlock.h
@@ -24,7 +24,7 @@
 
 /* FIXME: Replace this with a ticket lock, like MIPS. */
 
-#define arch_spin_is_locked(x)	((x)->lock != 0)
+#define arch_spin_is_locked(x)	(READ_ONCE((x)->lock) != 0)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
@@ -58,15 +58,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	}
 }
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_rmb();
-	do {
-		cpu_relax();
-	} while (arch_spin_is_locked(lock));
-	smp_acquire__after_ctrl_dep();
-}
-
 /***********************************************************/
 
 static inline void arch_read_lock(arch_rwlock_t *lock)
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 22c3536ed281..f8fa1cd2dad9 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -64,8 +64,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_stack		(init_thread_union.stack)
-
 #endif /* !__ASSEMBLY__ */
 
 /*
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
index 3df4932d8964..2f26989cb864 100644
--- a/arch/riscv/include/asm/timex.h
+++ b/arch/riscv/include/asm/timex.h
@@ -18,7 +18,7 @@
 
 typedef unsigned long cycles_t;
 
-static inline cycles_t get_cycles(void)
+static inline cycles_t get_cycles_inline(void)
 {
 	cycles_t n;
 
@@ -27,6 +27,7 @@ static inline cycles_t get_cycles(void)
 		: "=r" (n));
 	return n;
 }
+#define get_cycles get_cycles_inline
 
 #ifdef CONFIG_64BIT
 static inline uint64_t get_cycles64(void)
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 5ee4ae370b5e..7b9c24ebdf52 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -15,9 +15,12 @@
 #ifndef _ASM_RISCV_TLBFLUSH_H
 #define _ASM_RISCV_TLBFLUSH_H
 
-#ifdef CONFIG_MMU
+#include <linux/mm_types.h>
 
-/* Flush entire local TLB */
+/*
+ * Flush entire local TLB.  'sfence.vma' implicitly fences with the instruction
+ * cache as well, so a 'fence.i' is not necessary.
+ */
 static inline void local_flush_tlb_all(void)
 {
 	__asm__ __volatile__ ("sfence.vma" : : : "memory");
@@ -59,6 +62,4 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 	flush_tlb_all();
 }
 
-#endif /* CONFIG_MMU */
-
 #endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 27b90d64814b..14b0b22fb578 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -127,7 +127,6 @@ extern int fixup_exception(struct pt_regs *state);
  * call.
  */
 
-#ifdef CONFIG_MMU
 #define __get_user_asm(insn, x, ptr, err)			\
 do {								\
 	uintptr_t __tmp;					\
@@ -153,13 +152,11 @@ do {								\
 	__disable_user_access();				\
 	(x) = __x;						\
 } while (0)
-#endif /* CONFIG_MMU */
 
 #ifdef CONFIG_64BIT
 #define __get_user_8(x, ptr, err) \
 	__get_user_asm("ld", x, ptr, err)
 #else /* !CONFIG_64BIT */
-#ifdef CONFIG_MMU
 #define __get_user_8(x, ptr, err)				\
 do {								\
 	u32 __user *__ptr = (u32 __user *)(ptr);		\
@@ -193,7 +190,6 @@ do {								\
 	(x) = (__typeof__(x))((__typeof__((x)-(x)))(		\
 		(((u64)__hi << 32) | __lo)));			\
 } while (0)
-#endif /* CONFIG_MMU */
 #endif /* CONFIG_64BIT */
 
 
@@ -267,8 +263,6 @@ do {								\
 		((x) = 0, -EFAULT);				\
 })
 
-
-#ifdef CONFIG_MMU
 #define __put_user_asm(insn, x, ptr, err)			\
 do {								\
 	uintptr_t __tmp;					\
@@ -292,14 +286,11 @@ do {								\
 		: "rJ" (__x), "i" (-EFAULT));			\
 	__disable_user_access();				\
 } while (0)
-#endif /* CONFIG_MMU */
-
 
 #ifdef CONFIG_64BIT
 #define __put_user_8(x, ptr, err) \
 	__put_user_asm("sd", x, ptr, err)
 #else /* !CONFIG_64BIT */
-#ifdef CONFIG_MMU
 #define __put_user_8(x, ptr, err)				\
 do {								\
 	u32 __user *__ptr = (u32 __user *)(ptr);		\
@@ -329,7 +320,6 @@ do {								\
 		: "rJ" (__x), "rJ" (__x >> 32), "i" (-EFAULT));	\
 	__disable_user_access();				\
 } while (0)
-#endif /* CONFIG_MMU */
 #endif /* CONFIG_64BIT */
 
 
@@ -438,7 +428,6 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
  * will set "err" to -EFAULT, while successful accesses return the previous
  * value.
  */
-#ifdef CONFIG_MMU
 #define __cmpxchg_user(ptr, old, new, err, size, lrb, scb)	\
 ({								\
 	__typeof__(ptr) __ptr = (ptr);				\
@@ -508,6 +497,5 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
 	(err) = __err;						\
 	__ret;							\
 })
-#endif /* CONFIG_MMU */
 
 #endif /* _ASM_RISCV_UACCESS_H */
diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h
index 9f250ed007cd..2f704a5c4196 100644
--- a/arch/riscv/include/asm/unistd.h
+++ b/arch/riscv/include/asm/unistd.h
@@ -14,3 +14,4 @@
 #define __ARCH_HAVE_MMU
 #define __ARCH_WANT_SYS_CLONE
 #include <uapi/asm/unistd.h>
+#include <uapi/asm/syscalls.h>
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
index 602f61257553..541544d64c33 100644
--- a/arch/riscv/include/asm/vdso.h
+++ b/arch/riscv/include/asm/vdso.h
@@ -38,4 +38,8 @@ struct vdso_data {
 	(void __user *)((unsigned long)(base) + __vdso_##name);			\
 })
 
+#ifdef CONFIG_SMP
+asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
+#endif
+
 #endif /* _ASM_RISCV_VDSO_H */
diff --git a/arch/riscv/include/uapi/asm/Kbuild b/arch/riscv/include/uapi/asm/Kbuild
index 5ded96b06352..7e91f4850475 100644
--- a/arch/riscv/include/uapi/asm/Kbuild
+++ b/arch/riscv/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += setup.h
 generic-y += unistd.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/riscv/include/uapi/asm/syscalls.h b/arch/riscv/include/uapi/asm/syscalls.h
new file mode 100644
index 000000000000..818655b0d535
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/syscalls.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2017 SiFive
+ */
+
+#ifndef _ASM__UAPI__SYSCALLS_H
+#define _ASM__UAPI__SYSCALLS_H
+
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * __NR_riscv_flush_icache is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
+
+#endif
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 20ee86f782a9..7404ec222406 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -196,7 +196,7 @@ handle_syscall:
 	addi s2, s2, 0x4
 	REG_S s2, PT_SEPC(sp)
 	/* System calls run with interrupts enabled */
-	csrs sstatus, SR_IE
+	csrs sstatus, SR_SIE
 	/* Trace syscalls, but only if requested by the user. */
 	REG_L t0, TASK_TI_FLAGS(tp)
 	andi t0, t0, _TIF_SYSCALL_TRACE
@@ -224,8 +224,8 @@ ret_from_syscall:
 
 ret_from_exception:
 	REG_L s0, PT_SSTATUS(sp)
-	csrc sstatus, SR_IE
-	andi s0, s0, SR_PS
+	csrc sstatus, SR_SIE
+	andi s0, s0, SR_SPP
 	bnez s0, restore_all
 
 resume_userspace:
@@ -255,7 +255,7 @@ work_pending:
 	bnez s1, work_resched
 work_notifysig:
 	/* Handle pending signals and notify-resume requests */
-	csrs sstatus, SR_IE /* Enable interrupts for do_notify_resume() */
+	csrs sstatus, SR_SIE /* Enable interrupts for do_notify_resume() */
 	move a0, sp /* pt_regs */
 	move a1, s0 /* current_thread_info->flags */
 	tail do_notify_resume
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 76af908f87c1..78f670d70133 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -152,6 +152,3 @@ END(_start)
 __PAGE_ALIGNED_BSS
 	/* Empty zero page */
 	.balign PAGE_SIZE
-ENTRY(empty_zero_page)
-	.fill (empty_zero_page + PAGE_SIZE) - ., 1, 0x00
-END(empty_zero_page)
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 0d90dcc1fbd3..d7c6ca7c95ae 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -25,9 +25,9 @@
 #include <linux/sched/task_stack.h>
 #include <linux/tick.h>
 #include <linux/ptrace.h>
+#include <linux/uaccess.h>
 
 #include <asm/unistd.h>
-#include <asm/uaccess.h>
 #include <asm/processor.h>
 #include <asm/csr.h>
 #include <asm/string.h>
@@ -76,7 +76,7 @@ void show_regs(struct pt_regs *regs)
 void start_thread(struct pt_regs *regs, unsigned long pc,
 	unsigned long sp)
 {
-	regs->sstatus = SR_PIE /* User mode, irqs on */ | SR_FS_INITIAL;
+	regs->sstatus = SR_SPIE /* User mode, irqs on */ | SR_FS_INITIAL;
 	regs->sepc = pc;
 	regs->sp = sp;
 	set_fs(USER_DS);
@@ -110,7 +110,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 		const register unsigned long gp __asm__ ("gp");
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->gp = gp;
-		childregs->sstatus = SR_PS | SR_PIE; /* Supervisor, irqs on */
+		childregs->sstatus = SR_SPP | SR_SPIE; /* Supervisor, irqs on */
 
 		p->thread.ra = (unsigned long)ret_from_kernel_thread;
 		p->thread.s[0] = usp; /* fn */
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
index 23cc81ec9e94..551734248748 100644
--- a/arch/riscv/kernel/riscv_ksyms.c
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -12,4 +12,7 @@
 /*
  * Assembly functions that may be used (directly or indirectly) by modules
  */
+EXPORT_SYMBOL(__clear_user);
 EXPORT_SYMBOL(__copy_user);
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memcpy);
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index de7db114c315..cb7b0c63014e 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -38,10 +38,6 @@
 #include <asm/tlbflush.h>
 #include <asm/thread_info.h>
 
-#ifdef CONFIG_HVC_RISCV_SBI
-#include <asm/hvc_riscv_sbi.h>
-#endif
-
 #ifdef CONFIG_DUMMY_CONSOLE
 struct screen_info screen_info = {
 	.orig_video_lines	= 30,
@@ -58,7 +54,12 @@ static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
 #endif /* CONFIG_CMDLINE_BOOL */
 
 unsigned long va_pa_offset;
+EXPORT_SYMBOL(va_pa_offset);
 unsigned long pfn_base;
+EXPORT_SYMBOL(pfn_base);
+
+unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
+EXPORT_SYMBOL(empty_zero_page);
 
 /* The lucky hart to first increment this variable will boot the other cores */
 atomic_t hart_lottery;
@@ -207,13 +208,6 @@ static void __init setup_bootmem(void)
 
 void __init setup_arch(char **cmdline_p)
 {
-#if defined(CONFIG_HVC_RISCV_SBI)
-	if (likely(early_console == NULL)) {
-		early_console = &riscv_sbi_early_console_dev;
-		register_console(early_console);
-	}
-#endif
-
 #ifdef CONFIG_CMDLINE_BOOL
 #ifdef CONFIG_CMDLINE_OVERRIDE
 	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index b4a71ec5906f..6d3962435720 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -38,6 +38,13 @@ enum ipi_message_type {
 	IPI_MAX
 };
 
+
+/* Unsupported */
+int setup_profiling_timer(unsigned int multiplier)
+{
+	return -EINVAL;
+}
+
 irqreturn_t handle_ipi(void)
 {
 	unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
@@ -108,3 +115,51 @@ void smp_send_reschedule(int cpu)
 {
 	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
 }
+
+/*
+ * Performs an icache flush for the given MM context.  RISC-V has no direct
+ * mechanism for instruction cache shoot downs, so instead we send an IPI that
+ * informs the remote harts they need to flush their local instruction caches.
+ * To avoid pathologically slow behavior in a common case (a bunch of
+ * single-hart processes on a many-hart machine, ie 'make -j') we avoid the
+ * IPIs for harts that are not currently executing a MM context and instead
+ * schedule a deferred local instruction cache flush to be performed before
+ * execution resumes on each hart.
+ */
+void flush_icache_mm(struct mm_struct *mm, bool local)
+{
+	unsigned int cpu;
+	cpumask_t others, *mask;
+
+	preempt_disable();
+
+	/* Mark every hart's icache as needing a flush for this MM. */
+	mask = &mm->context.icache_stale_mask;
+	cpumask_setall(mask);
+	/* Flush this hart's I$ now, and mark it as flushed. */
+	cpu = smp_processor_id();
+	cpumask_clear_cpu(cpu, mask);
+	local_flush_icache_all();
+
+	/*
+	 * Flush the I$ of other harts concurrently executing, and mark them as
+	 * flushed.
+	 */
+	cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
+	local |= cpumask_empty(&others);
+	if (mm != current->active_mm || !local)
+		sbi_remote_fence_i(others.bits);
+	else {
+		/*
+		 * It's assumed that at least one strongly ordered operation is
+		 * performed on this hart between setting a hart's cpumask bit
+		 * and scheduling this MM context on that hart.  Sending an SBI
+		 * remote message will do this, but in the case where no
+		 * messages are sent we still need to order this hart's writes
+		 * with flush_icache_deferred().
+		 */
+		smp_mb();
+	}
+
+	preempt_enable();
+}
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 4351be7d0533..79c78668258e 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -14,8 +14,8 @@
  */
 
 #include <linux/syscalls.h>
-#include <asm/cmpxchg.h>
 #include <asm/unistd.h>
+#include <asm/cacheflush.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -47,3 +47,34 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
 	return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12);
 }
 #endif /* !CONFIG_64BIT */
+
+#ifdef CONFIG_SMP
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * sys_riscv_flush_icache() is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
+	uintptr_t, flags)
+{
+	struct mm_struct *mm = current->mm;
+	bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0;
+
+	/* Check the reserved flags. */
+	if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL))
+		return -EINVAL;
+
+	flush_icache_mm(mm, local);
+
+	return 0;
+}
+#endif
diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c
index 4e30dc5fb593..ade52b903a43 100644
--- a/arch/riscv/kernel/syscall_table.c
+++ b/arch/riscv/kernel/syscall_table.c
@@ -15,6 +15,7 @@
 #include <linux/linkage.h>
 #include <linux/syscalls.h>
 #include <asm-generic/syscalls.h>
+#include <asm/vdso.h>
 
 #undef __SYSCALL
 #define __SYSCALL(nr, call)	[nr] = (call),
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 523d0a8ac8db..324568d33921 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -1,7 +1,12 @@
 # Copied from arch/tile/kernel/vdso/Makefile
 
 # Symbols present in the vdso
-vdso-syms = rt_sigreturn
+vdso-syms  = rt_sigreturn
+vdso-syms += gettimeofday
+vdso-syms += clock_gettime
+vdso-syms += clock_getres
+vdso-syms += getcpu
+vdso-syms += flush_icache
 
 # Files to link into the vdso
 obj-vdso = $(patsubst %, %.o, $(vdso-syms))
diff --git a/arch/riscv/kernel/vdso/clock_getres.S b/arch/riscv/kernel/vdso/clock_getres.S
new file mode 100644
index 000000000000..edf7e2339648
--- /dev/null
+++ b/arch/riscv/kernel/vdso/clock_getres.S
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_clock_getres(clockid_t clock_id, struct timespec *res); */
+ENTRY(__vdso_clock_getres)
+	.cfi_startproc
+	/* For now, just do the syscall. */
+	li a7, __NR_clock_getres
+	ecall
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_clock_getres)
diff --git a/arch/riscv/kernel/vdso/clock_gettime.S b/arch/riscv/kernel/vdso/clock_gettime.S
new file mode 100644
index 000000000000..aac65676c6d5
--- /dev/null
+++ b/arch/riscv/kernel/vdso/clock_gettime.S
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_clock_gettime(clockid_t clock_id, struct timespec *tp); */
+ENTRY(__vdso_clock_gettime)
+	.cfi_startproc
+	/* For now, just do the syscall. */
+	li a7, __NR_clock_gettime
+	ecall
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_clock_gettime)
diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S
new file mode 100644
index 000000000000..023e4d4aef58
--- /dev/null
+++ b/arch/riscv/kernel/vdso/flush_icache.S
@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */
+ENTRY(__vdso_flush_icache)
+	.cfi_startproc
+#ifdef CONFIG_SMP
+	li a7, __NR_riscv_flush_icache
+	ecall
+#else
+	fence.i
+	li a0, 0
+#endif
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_flush_icache)
diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S
new file mode 100644
index 000000000000..cc7e98924484
--- /dev/null
+++ b/arch/riscv/kernel/vdso/getcpu.S
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */
+ENTRY(__vdso_getcpu)
+	.cfi_startproc
+	/* For now, just do the syscall. */
+	li a7, __NR_getcpu
+	ecall
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_getcpu)
diff --git a/arch/riscv/kernel/vdso/gettimeofday.S b/arch/riscv/kernel/vdso/gettimeofday.S
new file mode 100644
index 000000000000..da85d33e8990
--- /dev/null
+++ b/arch/riscv/kernel/vdso/gettimeofday.S
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); */
+ENTRY(__vdso_gettimeofday)
+	.cfi_startproc
+	/* For now, just do the syscall. */
+	li a7, __NR_gettimeofday
+	ecall
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_gettimeofday)
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index 8c9dce95c11d..cd1d47e0724b 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -70,8 +70,11 @@ VERSION
 	LINUX_4.15 {
 	global:
 		__vdso_rt_sigreturn;
-		__vdso_cmpxchg32;
-		__vdso_cmpxchg64;
+		__vdso_gettimeofday;
+		__vdso_clock_gettime;
+		__vdso_clock_getres;
+		__vdso_getcpu;
+		__vdso_flush_icache;
 	local: *;
 	};
 }
diff --git a/arch/riscv/lib/delay.c b/arch/riscv/lib/delay.c
index 1cc4ac3964b4..dce8ae24c6d3 100644
--- a/arch/riscv/lib/delay.c
+++ b/arch/riscv/lib/delay.c
@@ -84,6 +84,7 @@ void __delay(unsigned long cycles)
 	while ((unsigned long)(get_cycles() - t0) < cycles)
 		cpu_relax();
 }
+EXPORT_SYMBOL(__delay);
 
 void udelay(unsigned long usecs)
 {
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index 81f7d9ce6d88..eb22ab49b3e0 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -2,3 +2,4 @@ obj-y += init.o
 obj-y += fault.o
 obj-y += extable.o
 obj-y += ioremap.o
+obj-y += cacheflush.o
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
new file mode 100644
index 000000000000..498c0a0814fe
--- /dev/null
+++ b/arch/riscv/mm/cacheflush.c
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+
+void flush_icache_pte(pte_t pte)
+{
+	struct page *page = pte_page(pte);
+
+	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+		flush_icache_all();
+}
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index df2ca3c65048..ceebfc29305b 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -29,7 +29,6 @@
 
 #include <asm/pgalloc.h>
 #include <asm/ptrace.h>
-#include <asm/uaccess.h>
 
 /*
  * This routine handles page faults.  It determines the address and the
@@ -63,7 +62,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 		goto vmalloc_fault;
 
 	/* Enable interrupts if they were enabled in the parent context. */
-	if (likely(regs->sstatus & SR_PIE))
+	if (likely(regs->sstatus & SR_SPIE))
 		local_irq_enable();
 
 	/*
diff --git a/arch/riscv/mm/ioremap.c b/arch/riscv/mm/ioremap.c
index e99194a4077e..70ef2724cdf6 100644
--- a/arch/riscv/mm/ioremap.c
+++ b/arch/riscv/mm/ioremap.c
@@ -85,7 +85,7 @@ EXPORT_SYMBOL(ioremap);
  *
  * Caller must ensure there is only one unmapping for the same pointer.
  */
-void iounmap(void __iomem *addr)
+void iounmap(volatile void __iomem *addr)
 {
 	vunmap((void *)((unsigned long)addr & PAGE_MASK));
 }
diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild
index eae2c64cf69d..9fdff3fe1a42 100644
--- a/arch/s390/Kbuild
+++ b/arch/s390/Kbuild
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 obj-y				+= kernel/
 obj-y				+= mm/
 obj-$(CONFIG_KVM)		+= kvm/
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 829c67986db7..0105ce28e246 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -108,7 +108,6 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
@@ -140,7 +139,7 @@ config S390
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
-	select DMA_NOOP_OPS
+	select DMA_DIRECT_OPS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 6b3f41985f28..fd691c4ff89e 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # s390/Makefile
 #
@@ -6,10 +7,6 @@
 # for "archclean" and "archdep" for cleaning up and making dependencies for
 # this architecture
 #
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
 # Copyright (C) 1994 by Linus Torvalds
 #
 
@@ -91,9 +88,13 @@ KBUILD_CFLAGS	+= -DCC_USING_HOTPATCH
 endif
 endif
 
+# Test CFI features of binutils
+cfi := $(call as-instr,.cfi_startproc\n.cfi_val_offset 15$(comma)-160\n.cfi_endproc,-DCONFIG_AS_CFI_VAL_OFFSET=1)
+
 KBUILD_CFLAGS	+= -mbackchain -msoft-float $(cflags-y)
 KBUILD_CFLAGS	+= -pipe -fno-strength-reduce -Wno-sign-compare
-KBUILD_AFLAGS	+= $(aflags-y)
+KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables $(cfi)
+KBUILD_AFLAGS	+= $(aflags-y) $(cfi)
 
 OBJCOPYFLAGS	:= -O binary
 
@@ -110,6 +111,7 @@ drivers-y	+= drivers/s390/
 drivers-$(CONFIG_OPROFILE)	+= arch/s390/oprofile/
 
 boot		:= arch/s390/boot
+syscalls	:= arch/s390/kernel/syscalls
 tools		:= arch/s390/tools
 
 all: image bzImage
@@ -131,9 +133,12 @@ archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 	$(Q)$(MAKE) $(clean)=$(tools)
 
+archheaders:
+	$(Q)$(MAKE) $(build)=$(syscalls) uapi
+
 archprepare:
-	$(Q)$(MAKE) $(build)=$(tools) include/generated/facilities.h
-	$(Q)$(MAKE) $(build)=$(tools) include/generated/dis.h
+	$(Q)$(MAKE) $(build)=$(syscalls) kapi
+	$(Q)$(MAKE) $(build)=$(tools) kapi
 
 # Don't use tabs in echo arguments
 define archhelp
diff --git a/arch/s390/appldata/Makefile b/arch/s390/appldata/Makefile
index 99f1cf071304..b06def4a4f2f 100644
--- a/arch/s390/appldata/Makefile
+++ b/arch/s390/appldata/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Makefile for the Linux - z/VM Monitor Stream.
 #
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index ef3fb1b9201f..cb6e8066b1ad 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Base infrastructure for Linux-z/VM Monitor Stream, Stage 1.
  * Exports appldata_register_ops() and appldata_unregister_ops() for the
diff --git a/arch/s390/appldata/appldata_mem.c b/arch/s390/appldata/appldata_mem.c
index 598df5708501..e68136c3c23a 100644
--- a/arch/s390/appldata/appldata_mem.c
+++ b/arch/s390/appldata/appldata_mem.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Data gathering module for Linux-VM Monitor Stream, Stage 1.
  * Collects data related to memory management.
diff --git a/arch/s390/appldata/appldata_net_sum.c b/arch/s390/appldata/appldata_net_sum.c
index 66037d2622b4..8bc14b0d1def 100644
--- a/arch/s390/appldata/appldata_net_sum.c
+++ b/arch/s390/appldata/appldata_net_sum.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Data gathering module for Linux-VM Monitor Stream, Stage 1.
  * Collects accumulated network statistics (Packets received/transmitted,
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 45b3178200ab..433a994b1a89 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Data gathering module for Linux-VM Monitor Stream, Stage 1.
  * Collects misc. OS related data (CPU utilization, running processes).
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 29e3dc99b916..26d6a94f40f6 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -14,6 +14,7 @@ targets += misc.o piggy.o sizes.h head.o
 KBUILD_CFLAGS := -m64 -D__KERNEL__ -O2
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
 KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -msoft-float
+KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS += $(call cc-option,-mpacked-stack)
 KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 
diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
index 88e46d4a7784..8150132b144f 100644
--- a/arch/s390/boot/compressed/vmlinux.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -17,15 +17,15 @@ SECTIONS
 		HEAD_TEXT
 		_ehead = . ;
 	}
-	.rodata.compressed : {
-		*(.rodata.compressed)
-	}
 	.text :	{
 		_text = .;	/* Text */
 		*(.text)
 		*(.text.*)
 		_etext = . ;
 	}
+	.rodata.compressed : {
+		*(.rodata.compressed)
+	}
 	.rodata : {
 		_rodata = . ;
 		*(.rodata)	 /* read-only data */
@@ -48,4 +48,10 @@ SECTIONS
 		_ebss = .;
 	}
 	_end = .;
+
+	/* Sections to be discarded */
+	/DISCARD/ : {
+		*(.eh_frame)
+		*(*__ksymtab*)
+	}
 }
diff --git a/arch/s390/boot/compressed/vmlinux.scr b/arch/s390/boot/compressed/vmlinux.scr
index f02382ae5c48..42a242597f34 100644
--- a/arch/s390/boot/compressed/vmlinux.scr
+++ b/arch/s390/boot/compressed/vmlinux.scr
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 SECTIONS
 {
   .rodata.compressed : {
diff --git a/arch/s390/boot/install.sh b/arch/s390/boot/install.sh
index aed3069699bd..bed227f267ae 100644
--- a/arch/s390/boot/install.sh
+++ b/arch/s390/boot/install.sh
@@ -1,11 +1,8 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 #
 # arch/s390x/boot/install.sh
 #
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
 # Copyright (C) 1995 by Linus Torvalds
 #
 # Adapted from code in arch/i386/boot/Makefile by H. Peter Anvin
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 04e042edbab7..7dc7f58c4287 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -26,7 +26,6 @@ CONFIG_NET=y
 # CONFIG_IUCV is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_BLK_DEV_RAM=y
 # CONFIG_BLK_DEV_XPRAM is not set
 # CONFIG_DCSSBLK is not set
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index b48e20dd94e9..d60798737d86 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Cryptographic API.
  *
@@ -11,12 +12,6 @@
  *		Harald Freudenberger <freude@de.ibm.com>
  *
  * Derived from "crypto/aes_generic.c"
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #define KMSG_COMPONENT "aes_s390"
diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c
index 36aefc07d10c..8720e9203ecf 100644
--- a/arch/s390/crypto/arch_random.c
+++ b/arch/s390/crypto/arch_random.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * s390 arch random implementation.
  *
  * Copyright IBM Corp. 2017
  * Author(s): Harald Freudenberger <freude@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c
index 992e630c227b..423ee05887e6 100644
--- a/arch/s390/crypto/crc32-vx.c
+++ b/arch/s390/crypto/crc32-vx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Crypto-API module for CRC-32 algorithms implemented with the
  * z/Architecture Vector Extension Facility.
@@ -238,6 +239,7 @@ static struct shash_alg crc32_vx_algs[] = {
 			.cra_name	 = "crc32",
 			.cra_driver_name = "crc32-vx",
 			.cra_priority	 = 200,
+			.cra_flags	 = CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize	 = CRC32_BLOCK_SIZE,
 			.cra_ctxsize	 = sizeof(struct crc_ctx),
 			.cra_module	 = THIS_MODULE,
@@ -258,6 +260,7 @@ static struct shash_alg crc32_vx_algs[] = {
 			.cra_name	 = "crc32be",
 			.cra_driver_name = "crc32be-vx",
 			.cra_priority	 = 200,
+			.cra_flags	 = CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize	 = CRC32_BLOCK_SIZE,
 			.cra_ctxsize	 = sizeof(struct crc_ctx),
 			.cra_module	 = THIS_MODULE,
@@ -278,6 +281,7 @@ static struct shash_alg crc32_vx_algs[] = {
 			.cra_name	 = "crc32c",
 			.cra_driver_name = "crc32c-vx",
 			.cra_priority	 = 200,
+			.cra_flags	 = CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize	 = CRC32_BLOCK_SIZE,
 			.cra_ctxsize	 = sizeof(struct crc_ctx),
 			.cra_module	 = THIS_MODULE,
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 0d296662bbf0..5346b5a80bb6 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Cryptographic API.
  *
@@ -6,12 +7,6 @@
  * Copyright IBM Corp. 2003, 2011
  * Author(s): Thomas Spatzier
  *	      Jan Glauber (jan.glauber@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  */
 
 #include <linux/init.h>
diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c
index 564616d48d8b..3b7f96c9eead 100644
--- a/arch/s390/crypto/ghash_s390.c
+++ b/arch/s390/crypto/ghash_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Cryptographic API.
  *
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index a4e903ed7e21..003932db8d12 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Cryptographic API.
  *
@@ -7,11 +8,6 @@
  *   Copyright IBM Corp. 2017
  *   Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  *		Harald Freudenberger <freude@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  */
 
 #define KMSG_COMPONENT "paes_s390"
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 3e47c4a0f18b..a97a1802cfb4 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright IBM Corp. 2006, 2015
  * Author(s): Jan Glauber <jan.glauber@de.ibm.com>
diff --git a/arch/s390/crypto/sha.h b/arch/s390/crypto/sha.h
index 10f200790079..d6f8258b44df 100644
--- a/arch/s390/crypto/sha.h
+++ b/arch/s390/crypto/sha.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Cryptographic API.
  *
@@ -5,12 +6,6 @@
  *
  * Copyright IBM Corp. 2007
  * Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 #ifndef _CRYPTO_ARCH_S390_SHA_H
 #define _CRYPTO_ARCH_S390_SHA_H
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index c7de53d8da75..a00c17f761c1 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Cryptographic API.
  *
@@ -16,12 +17,6 @@
  *   Copyright (c) Alan Smithee.
  *   Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
  *   Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c
index 53c277999a28..944aa6b237cd 100644
--- a/arch/s390/crypto/sha256_s390.c
+++ b/arch/s390/crypto/sha256_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Cryptographic API.
  *
@@ -6,12 +7,6 @@
  * s390 Version:
  *   Copyright IBM Corp. 2005, 2011
  *   Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index 2f4caa1ef123..b17eded532b1 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Cryptographic API.
  *
@@ -5,12 +6,6 @@
  *
  * Copyright IBM Corp. 2007
  * Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 #include <crypto/internal/hash.h>
 #include <crypto/sha.h>
diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c
index c740f77285b2..cf0718d121bc 100644
--- a/arch/s390/crypto/sha_common.c
+++ b/arch/s390/crypto/sha_common.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Cryptographic API.
  *
@@ -5,12 +6,6 @@
  *
  * Copyright IBM Corp. 2007
  * Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #include <crypto/internal/hash.h>
diff --git a/arch/s390/hypfs/Makefile b/arch/s390/hypfs/Makefile
index 2ee25ba252d6..06f601509ce9 100644
--- a/arch/s390/hypfs/Makefile
+++ b/arch/s390/hypfs/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Makefile for the linux hypfs filesystem routines.
 #
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index cf8a2d92467f..43bbe63e2992 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -1,9 +1,9 @@
+// SPDX-License-Identifier: GPL-1.0+
 /*
  *    Hypervisor filesystem for Linux on s390.
  *
  *    Copyright IBM Corp. 2006, 2008
  *    Author(s): Michael Holzheu <holzheu@de.ibm.com>
- *    License: GPL
  */
 
 #define KMSG_COMPONENT "hypfs"
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 41c211a4d8b1..e3239772887a 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,8 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+generated-y += dis-defs.h
+generated-y += facility-defs.h
+generated-y += syscall_table.h
+generated-y += unistd_nr.h
+
 generic-y += asm-offsets.h
 generic-y += cacheflush.h
-generic-y += clkdev.h
 generic-y += device.h
 generic-y += dma-contiguous.h
+generic-y += dma-mapping.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += export.h
diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h
index a72002056b54..c2cf7bcdef9b 100644
--- a/arch/s390/include/asm/alternative.h
+++ b/arch/s390/include/asm/alternative.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_S390_ALTERNATIVE_H
 #define _ASM_S390_ALTERNATIVE_H
 
diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index c02f4aba88a6..cfce6835b109 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Adjunct processor (AP) interfaces
  *
  * Copyright IBM Corp. 2017
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  * Author(s): Tony Krowiak <akrowia@linux.vnet.ibm.com>
  *	      Martin Schwidefsky <schwidefsky@de.ibm.com>
  *	      Harald Freudenberger <freude@de.ibm.com>
diff --git a/arch/s390/include/asm/bugs.h b/arch/s390/include/asm/bugs.h
index 0f5bd894f4dc..aa42a179be33 100644
--- a/arch/s390/include/asm/bugs.h
+++ b/arch/s390/include/asm/bugs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  S390 version
  *    Copyright IBM Corp. 1999
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 5e6a63641a5f..9830fb6b076e 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -189,79 +189,6 @@ typedef u32		compat_old_sigset_t;	/* at least 32 bits */
 
 typedef u32		compat_sigset_word;
 
-typedef union compat_sigval {
-	compat_int_t	sival_int;
-	compat_uptr_t	sival_ptr;
-} compat_sigval_t;
-
-typedef struct compat_siginfo {
-	int	si_signo;
-	int	si_errno;
-	int	si_code;
-
-	union {
-		int _pad[128/sizeof(int) - 3];
-
-		/* kill() */
-		struct {
-			pid_t	_pid;	/* sender's pid */
-			uid_t	_uid;	/* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			compat_timer_t _tid;		/* timer id */
-			int _overrun;			/* overrun count */
-			compat_sigval_t _sigval;	/* same as below */
-			int _sys_private;	/* not to be passed to user */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			pid_t			_pid;	/* sender's pid */
-			uid_t			_uid;	/* sender's uid */
-			compat_sigval_t		_sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			pid_t			_pid;	/* which child */
-			uid_t			_uid;	/* sender's uid */
-			int			_status;/* exit code */
-			compat_clock_t		_utime;
-			compat_clock_t		_stime;
-		} _sigchld;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
-		struct {
-			__u32	_addr;	/* faulting insn/memory ref. - pointer */
-		} _sigfault;
-
-		/* SIGPOLL */
-		struct {
-			int	_band;	/* POLL_IN, POLL_OUT, POLL_MSG */
-			int	_fd;
-		} _sigpoll;
-	} _sifields;
-} compat_siginfo_t;
-
-/*
- * How these fields are to be accessed.
- */
-#define si_pid		_sifields._kill._pid
-#define si_uid		_sifields._kill._uid
-#define si_status	_sifields._sigchld._status
-#define si_utime	_sifields._sigchld._utime
-#define si_stime	_sifields._sigchld._stime
-#define si_value	_sifields._rt._sigval
-#define si_int		_sifields._rt._sigval.sival_int
-#define si_ptr		_sifields._rt._sigval.sival_ptr
-#define si_addr		_sifields._sigfault._addr
-#define si_band		_sifields._sigpoll._band
-#define si_fd		_sifields._sigpoll._fd
-#define si_tid		_sifields._timer._tid
-#define si_overrun	_sifields._timer._overrun
-
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
 /*
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index 792cda339af1..dd08db491b89 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * CPU-measurement facilities
  *
  *  Copyright IBM Corp. 2012
  *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  *	       Jan Glauber <jang@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 #ifndef _ASM_S390_CPU_MF_H
 #define _ASM_S390_CPU_MF_H
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index 6db78567294c..cdbaad50c7c7 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -229,13 +229,55 @@ struct diag204_x_phys_block {
 } __packed;
 
 enum diag26c_sc {
+	DIAG26C_PORT_VNIC    = 0x00000024,
 	DIAG26C_MAC_SERVICES = 0x00000030
 };
 
 enum diag26c_version {
-	DIAG26C_VERSION2 = 0x00000002	/* z/VM 5.4.0 */
+	DIAG26C_VERSION2	 = 0x00000002,	/* z/VM 5.4.0 */
+	DIAG26C_VERSION6_VM65918 = 0x00020006	/* z/VM 6.4.0 + VM65918 */
 };
 
+#define DIAG26C_VNIC_INFO	0x0002
+struct diag26c_vnic_req {
+	u32	resp_buf_len;
+	u32	resp_version;
+	u16	req_format;
+	u16	vlan_id;
+	u64	sys_name;
+	u8	res[2];
+	u16	devno;
+} __packed __aligned(8);
+
+#define VNIC_INFO_PROT_L3	1
+#define VNIC_INFO_PROT_L2	2
+/* Note: this is the bare minimum, use it for uninitialized VNICs only. */
+struct diag26c_vnic_resp {
+	u32	version;
+	u32	entry_cnt;
+	/* VNIC info: */
+	u32	next_entry;
+	u64	owner;
+	u16	devno;
+	u8	status;
+	u8	type;
+	u64	lan_owner;
+	u64	lan_name;
+	u64	port_name;
+	u8	port_type;
+	u8	ext_status:6;
+	u8	protocol:2;
+	u16	base_devno;
+	u32	port_num;
+	u32	ifindex;
+	u32	maxinfo;
+	u32	dev_count;
+	/* 3x device info: */
+	u8	dev_info1[28];
+	u8	dev_info2[28];
+	u8	dev_info3[28];
+} __packed __aligned(8);
+
 #define DIAG26C_GET_MAC	0x0000
 struct diag26c_mac_req {
 	u32	resp_buf_len;
diff --git a/arch/s390/include/asm/dis.h b/arch/s390/include/asm/dis.h
index b0480c60a8e1..c18ed6091914 100644
--- a/arch/s390/include/asm/dis.h
+++ b/arch/s390/include/asm/dis.h
@@ -9,7 +9,7 @@
 #ifndef __ASM_S390_DIS_H__
 #define __ASM_S390_DIS_H__
 
-#include <generated/dis.h>
+#include <asm/dis-defs.h>
 
 static inline int insn_length(unsigned char code)
 {
diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h
deleted file mode 100644
index eaf490f9c5bc..000000000000
--- a/arch/s390/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_S390_DMA_MAPPING_H
-#define _ASM_S390_DMA_MAPPING_H
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
-#include <linux/io.h>
-
-extern const struct dma_map_ops s390_pci_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &dma_noop_ops;
-}
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-#endif /* _ASM_S390_DMA_MAPPING_H */
diff --git a/arch/s390/include/asm/dwarf.h b/arch/s390/include/asm/dwarf.h
new file mode 100644
index 000000000000..4f21ae561e4d
--- /dev/null
+++ b/arch/s390/include/asm/dwarf.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_DWARF_H
+#define _ASM_S390_DWARF_H
+
+#ifdef __ASSEMBLY__
+
+#define CFI_STARTPROC		.cfi_startproc
+#define CFI_ENDPROC		.cfi_endproc
+#define CFI_DEF_CFA_OFFSET	.cfi_def_cfa_offset
+#define CFI_ADJUST_CFA_OFFSET	.cfi_adjust_cfa_offset
+#define CFI_RESTORE		.cfi_restore
+
+#ifdef CONFIG_AS_CFI_VAL_OFFSET
+#define CFI_VAL_OFFSET		.cfi_val_offset
+#else
+#define CFI_VAL_OFFSET		#
+#endif
+
+#ifndef BUILD_VDSO
+	/*
+	 * Emit CFI data in .debug_frame sections and not in .eh_frame
+	 * sections.  The .eh_frame CFI is used for runtime unwind
+	 * information that is not being used.  Hence, vmlinux.lds.S
+	 * can discard the .eh_frame sections.
+	 */
+	.cfi_sections .debug_frame
+#else
+	/*
+	 * For vDSO, emit CFI data in both, .eh_frame and .debug_frame
+	 * sections.
+	 */
+	.cfi_sections .eh_frame, .debug_frame
+#endif
+
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* _ASM_S390_DWARF_H */
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 9a3cb3983c01..1a61b1b997f2 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -194,13 +194,14 @@ struct arch_elf_state {
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	PAGE_SIZE
 
-/*
- * This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
- * space open for things that want to use the area for 32-bit pointers.
- */
-#define ELF_ET_DYN_BASE		(is_compat_task() ? 0x000400000UL : \
-						    0x100000000UL)
+/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
+   use of this is to invoke "./ld.so someprog" to test out a new version of
+   the loader.  We need to make sure that it is out of the way of the program
+   that it will "exec", and that there is sufficient room for the brk. 64-bit
+   tasks are aligned to 4GB. */
+#define ELF_ET_DYN_BASE (is_compat_task() ? \
+				(STACK_TOP / 3 * 2) : \
+				(STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports. */
diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index f040644575b7..fbe0c4be3cd8 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -8,7 +8,7 @@
 #ifndef __ASM_FACILITY_H
 #define __ASM_FACILITY_H
 
-#include <generated/facilities.h>
+#include <asm/facility-defs.h>
 #include <linux/string.h>
 #include <linux/preempt.h>
 #include <asm/lowcore.h>
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 921391f2341e..13de80cf741c 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -1,22 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 #ifndef _ASM_S390_KPROBES_H
 #define _ASM_S390_KPROBES_H
 /*
  *  Kernel Probes (KProbes)
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright IBM Corp. 2002, 2006
  *
  * 2002-Oct	Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index f3a9b5a445b6..c1b0a9ac1dc8 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * definition for kernel virtual machines on s390
  *
  * Copyright IBM Corp. 2008, 2009
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  */
 
@@ -210,7 +207,8 @@ struct kvm_s390_sie_block {
 	__u16	ipa;			/* 0x0056 */
 	__u32	ipb;			/* 0x0058 */
 	__u32	scaoh;			/* 0x005c */
-	__u8	reserved60;		/* 0x0060 */
+#define FPF_BPBC 	0x20
+	__u8	fpf;			/* 0x0060 */
 #define ECB_GS		0x40
 #define ECB_TE		0x10
 #define ECB_SRSI	0x04
diff --git a/arch/s390/include/asm/kvm_para.h b/arch/s390/include/asm/kvm_para.h
index 41393052ac57..74eeec9c0a80 100644
--- a/arch/s390/include/asm/kvm_para.h
+++ b/arch/s390/include/asm/kvm_para.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * definition for paravirtual devices on s390
  *
  * Copyright IBM Corp. 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
  */
 /*
@@ -20,8 +17,6 @@
  *
  * Copyright IBM Corp. 2007,2008
  * Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
  */
 #ifndef __S390_KVM_PARA_H
 #define __S390_KVM_PARA_H
diff --git a/arch/s390/include/asm/livepatch.h b/arch/s390/include/asm/livepatch.h
index 6de5c6cb0061..672f95b12d40 100644
--- a/arch/s390/include/asm/livepatch.h
+++ b/arch/s390/include/asm/livepatch.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * livepatch.h - s390-specific Kernel Live Patching Core
  *
@@ -7,13 +8,6 @@
  *	      Jiri Slaby
  */
 
-/*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- */
-
 #ifndef ASM_LIVEPATCH_H
 #define ASM_LIVEPATCH_H
 
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index f4a07f788f78..65154eaa3714 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -28,7 +28,7 @@ static inline int init_new_context(struct task_struct *tsk,
 #ifdef CONFIG_PGSTE
 	mm->context.alloc_pgste = page_table_allocate_pgste ||
 		test_thread_flag(TIF_PGSTE) ||
-		current->mm->context.alloc_pgste;
+		(current->mm && current->mm->context.alloc_pgste);
 	mm->context.has_pgste = 0;
 	mm->context.use_skey = 0;
 	mm->context.use_cmma = 0;
diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
index e8d9161fa17a..419fac7a62c0 100644
--- a/arch/s390/include/asm/pci_dma.h
+++ b/arch/s390/include/asm/pci_dma.h
@@ -201,4 +201,7 @@ void dma_cleanup_tables(unsigned long *);
 unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr);
 void dma_update_cpu_trans(unsigned long *entry, void *page_addr, int flags);
 
+extern const struct dma_map_ops s390_pci_dma_ops;
+
+
 #endif
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index d6c9d1e0dc2d..b9c0e361748b 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -40,6 +40,7 @@ struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs) perf_misc_flags(regs)
+#define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
 
 /* Perf pt_regs extension for sample-data-entry indicators */
 struct perf_sf_sde_regs {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index d7fe9838084d..2d24d33bf188 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -709,7 +709,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
 }
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0;
@@ -1505,12 +1505,12 @@ static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
 }
 
 #define __HAVE_ARCH_PMDP_INVALIDATE
-static inline void pmdp_invalidate(struct vm_area_struct *vma,
+static inline pmd_t pmdp_invalidate(struct vm_area_struct *vma,
 				   unsigned long addr, pmd_t *pmdp)
 {
 	pmd_t pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID);
 
-	pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd);
+	return pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd);
 }
 
 #define __HAVE_ARCH_PMDP_SET_WRPROTECT
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index a3788dafc0e1..6f70d81c40f2 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -74,9 +74,14 @@ enum {
  */
 struct pt_regs 
 {
-	unsigned long args[1];
-	psw_t psw;
-	unsigned long gprs[NUM_GPRS];
+	union {
+		user_pt_regs user_regs;
+		struct {
+			unsigned long args[1];
+			psw_t psw;
+			unsigned long gprs[NUM_GPRS];
+		};
+	};
 	unsigned long orig_gpr2;
 	unsigned int int_code;
 	unsigned int int_parm;
diff --git a/arch/s390/include/asm/segment.h b/arch/s390/include/asm/segment.h
index 8bfce3475b1c..97a0582b8d0f 100644
--- a/arch/s390/include/asm/segment.h
+++ b/arch/s390/include/asm/segment.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_SEGMENT_H
 #define _ASM_SEGMENT_H
 
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index ec7b476c1ac5..c61b2cc1a8a8 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -30,21 +30,20 @@ static inline void restore_access_regs(unsigned int *acrs)
 	asm volatile("lam 0,15,%0" : : "Q" (*(acrstype *)acrs));
 }
 
-#define switch_to(prev,next,last) do {					\
-	if (prev->mm) {							\
-		save_fpu_regs();					\
-		save_access_regs(&prev->thread.acrs[0]);		\
-		save_ri_cb(prev->thread.ri_cb);				\
-		save_gs_cb(prev->thread.gs_cb);				\
-	}								\
+#define switch_to(prev, next, last) do {				\
+	/* save_fpu_regs() sets the CIF_FPU flag, which enforces	\
+	 * a restore of the floating point / vector registers as	\
+	 * soon as the next task returns to user space			\
+	 */								\
+	save_fpu_regs();						\
+	save_access_regs(&prev->thread.acrs[0]);			\
+	save_ri_cb(prev->thread.ri_cb);					\
+	save_gs_cb(prev->thread.gs_cb);					\
 	update_cr_regs(next);						\
-	if (next->mm) {							\
-		set_cpu_flag(CIF_FPU);					\
-		restore_access_regs(&next->thread.acrs[0]);		\
-		restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);	\
-		restore_gs_cb(next->thread.gs_cb);			\
-	}								\
-	prev = __switch_to(prev,next);					\
+	restore_access_regs(&next->thread.acrs[0]);			\
+	restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);		\
+	restore_gs_cb(next->thread.gs_cb);				\
+	prev = __switch_to(prev, next);					\
 } while (0)
 
 #endif /* __ASM_SWITCH_TO_H */
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 6bc941be6921..96f9a9151fde 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Access to user system call parameters and results
  *
  *  Copyright IBM Corp. 2008
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 
 #ifndef _ASM_SYSCALL_H
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index a702cb9d4269..25057c118d56 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * definition for store system information stsi
  *
  * Copyright IBM Corp. 2001, 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Ulrich Weigand <weigand@de.ibm.com>
  *		 Christian Borntraeger <borntraeger@de.ibm.com>
  */
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 0880a37b6d3b..25d6ec3aaddd 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -42,8 +42,6 @@ struct thread_info {
 	.flags		= 0,			\
 }
 
-#define init_stack		(init_thread_union.stack)
-
 void arch_release_task_struct(struct task_struct *tsk);
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 1807229b292f..cca406fdbe51 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -53,6 +53,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu);
 static inline void topology_init_early(void) { }
 static inline void topology_schedule_update(void) { }
 static inline int topology_cpu_init(struct cpu *cpu) { return 0; }
+static inline int topology_cpu_dedicated(int cpu_nr) { return 0; }
 static inline void topology_expect_change(void) { }
 
 #endif /* CONFIG_SCHED_TOPOLOGY */
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 7807093b73be..fd79c0d35dc4 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -8,6 +8,7 @@
 #define _ASM_S390_UNISTD_H_
 
 #include <uapi/asm/unistd.h>
+#include <asm/unistd_nr.h>
 
 #define __IGNORE_time
 #define __IGNORE_pkey_mprotect
diff --git a/arch/s390/include/asm/vga.h b/arch/s390/include/asm/vga.h
index d375526c261f..605dc46bac5e 100644
--- a/arch/s390/include/asm/vga.h
+++ b/arch/s390/include/asm/vga.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_S390_VGA_H
 #define _ASM_S390_VGA_H
 
diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild
index 098f28778a13..faef3f7e8353 100644
--- a/arch/s390/include/uapi/asm/Kbuild
+++ b/arch/s390/include/uapi/asm/Kbuild
@@ -1,6 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generated-y += unistd_32.h
+generated-y += unistd_64.h
+
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/s390/include/uapi/asm/bpf_perf_event.h b/arch/s390/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 000000000000..cefe7c7cd4f6
--- /dev/null
+++ b/arch/s390/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 9ad172dcd912..4cdaa55fabfe 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -6,10 +6,6 @@
  *
  * Copyright IBM Corp. 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */
@@ -228,6 +224,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_RICCB  (1UL << 7)
 #define KVM_SYNC_FPRS   (1UL << 8)
 #define KVM_SYNC_GSCB   (1UL << 9)
+#define KVM_SYNC_BPBC   (1UL << 10)
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
@@ -251,7 +248,9 @@ struct kvm_sync_regs {
 	};
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;		/* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
-	__u8 padding1[52];	/* riccb needs to be 64byte aligned */
+	__u8 bpbc : 1;		/* bp mode */
+	__u8 reserved2 : 7;
+	__u8 padding1[51];	/* riccb needs to be 64byte aligned */
 	__u8 riccb[64];		/* runtime instrumentation controls block */
 	__u8 padding2[192];	/* sdnx needs to be 256byte aligned */
 	union {
diff --git a/arch/s390/include/uapi/asm/kvm_para.h b/arch/s390/include/uapi/asm/kvm_para.h
index 0dc86b3a7cb0..b9ab584adf43 100644
--- a/arch/s390/include/uapi/asm/kvm_para.h
+++ b/arch/s390/include/uapi/asm/kvm_para.h
@@ -4,9 +4,5 @@
  *
  * Copyright IBM Corp. 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
  */
diff --git a/arch/s390/include/uapi/asm/kvm_perf.h b/arch/s390/include/uapi/asm/kvm_perf.h
index c36c97ffdc6f..84606b8cc49e 100644
--- a/arch/s390/include/uapi/asm/kvm_perf.h
+++ b/arch/s390/include/uapi/asm/kvm_perf.h
@@ -4,10 +4,6 @@
  *
  * Copyright 2014 IBM Corp.
  * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_KVM_PERF_S390_H
diff --git a/arch/s390/include/uapi/asm/perf_regs.h b/arch/s390/include/uapi/asm/perf_regs.h
index 7c8564f98205..d17dd9e5d516 100644
--- a/arch/s390/include/uapi/asm/perf_regs.h
+++ b/arch/s390/include/uapi/asm/perf_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_S390_PERF_REGS_H
 #define _ASM_S390_PERF_REGS_H
 
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index 0d23c8ff2900..543dd70e12c8 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -162,7 +162,7 @@
 #define GPR_SIZE	8
 #define CR_SIZE		8
 
-#define STACK_FRAME_OVERHEAD    160      /* size of minimum stack frame */
+#define STACK_FRAME_OVERHEAD	160	 /* size of minimum stack frame */
 
 #endif /* __s390x__ */
 
@@ -179,17 +179,16 @@
 #define ACR_SIZE	4
 
 
-#define PTRACE_OLDSETOPTIONS         21
+#define PTRACE_OLDSETOPTIONS	     21
 
 #ifndef __ASSEMBLY__
 #include <linux/stddef.h>
 #include <linux/types.h>
 
-typedef union
-{
-	float   f;
-	double  d;
-        __u64   ui;
+typedef union {
+	float	f;
+	double	d;
+	__u64	ui;
 	struct
 	{
 		__u32 hi;
@@ -197,23 +196,21 @@ typedef union
 	} fp;
 } freg_t;
 
-typedef struct
-{
-	__u32   fpc;
+typedef struct {
+	__u32	fpc;
 	__u32	pad;
-	freg_t  fprs[NUM_FPRS];              
+	freg_t	fprs[NUM_FPRS];
 } s390_fp_regs;
 
-#define FPC_EXCEPTION_MASK      0xF8000000
-#define FPC_FLAGS_MASK          0x00F80000
-#define FPC_DXC_MASK            0x0000FF00
-#define FPC_RM_MASK             0x00000003
+#define FPC_EXCEPTION_MASK	0xF8000000
+#define FPC_FLAGS_MASK		0x00F80000
+#define FPC_DXC_MASK		0x0000FF00
+#define FPC_RM_MASK		0x00000003
 
 /* this typedef defines how a Program Status Word looks like */
-typedef struct 
-{
-        unsigned long mask;
-        unsigned long addr;
+typedef struct {
+	unsigned long mask;
+	unsigned long addr;
 } __attribute__ ((aligned(8))) psw_t;
 
 #ifndef __s390x__
@@ -282,8 +279,7 @@ typedef struct
 /*
  * The s390_regs structure is used to define the elf_gregset_t.
  */
-typedef struct
-{
+typedef struct {
 	psw_t psw;
 	unsigned long gprs[NUM_GPRS];
 	unsigned int  acrs[NUM_ACRS];
@@ -291,24 +287,32 @@ typedef struct
 } s390_regs;
 
 /*
+ * The user_pt_regs structure exports the beginning of
+ * the in-kernel pt_regs structure to user space.
+ */
+typedef struct {
+	unsigned long args[1];
+	psw_t psw;
+	unsigned long gprs[NUM_GPRS];
+} user_pt_regs;
+
+/*
  * Now for the user space program event recording (trace) definitions.
  * The following structures are used only for the ptrace interface, don't
  * touch or even look at it if you don't want to modify the user-space
  * ptrace interface. In particular stay away from it for in-kernel PER.
  */
-typedef struct
-{
+typedef struct {
 	unsigned long cr[NUM_CR_WORDS];
 } per_cr_words;
 
 #define PER_EM_MASK 0xE8000000UL
 
-typedef	struct
-{
+typedef struct {
 #ifdef __s390x__
-	unsigned                       : 32;
+	unsigned		       : 32;
 #endif /* __s390x__ */
-	unsigned em_branching          : 1;
+	unsigned em_branching	       : 1;
 	unsigned em_instruction_fetch  : 1;
 	/*
 	 * Switching on storage alteration automatically fixes
@@ -317,44 +321,41 @@ typedef	struct
 	unsigned em_storage_alteration : 1;
 	unsigned em_gpr_alt_unused     : 1;
 	unsigned em_store_real_address : 1;
-	unsigned                       : 3;
+	unsigned		       : 3;
 	unsigned branch_addr_ctl       : 1;
-	unsigned                       : 1;
+	unsigned		       : 1;
 	unsigned storage_alt_space_ctl : 1;
-	unsigned                       : 21;
+	unsigned		       : 21;
 	unsigned long starting_addr;
 	unsigned long ending_addr;
 } per_cr_bits;
 
-typedef struct
-{
+typedef struct {
 	unsigned short perc_atmid;
 	unsigned long address;
 	unsigned char access_id;
 } per_lowcore_words;
 
-typedef struct
-{
-	unsigned perc_branching          : 1;
+typedef struct {
+	unsigned perc_branching		 : 1;
 	unsigned perc_instruction_fetch  : 1;
 	unsigned perc_storage_alteration : 1;
-	unsigned perc_gpr_alt_unused     : 1;
+	unsigned perc_gpr_alt_unused	 : 1;
 	unsigned perc_store_real_address : 1;
-	unsigned                         : 3;
-	unsigned atmid_psw_bit_31        : 1;
-	unsigned atmid_validity_bit      : 1;
-	unsigned atmid_psw_bit_32        : 1;
-	unsigned atmid_psw_bit_5         : 1;
-	unsigned atmid_psw_bit_16        : 1;
-	unsigned atmid_psw_bit_17        : 1;
-	unsigned si                      : 2;
+	unsigned			 : 3;
+	unsigned atmid_psw_bit_31	 : 1;
+	unsigned atmid_validity_bit	 : 1;
+	unsigned atmid_psw_bit_32	 : 1;
+	unsigned atmid_psw_bit_5	 : 1;
+	unsigned atmid_psw_bit_16	 : 1;
+	unsigned atmid_psw_bit_17	 : 1;
+	unsigned si			 : 2;
 	unsigned long address;
-	unsigned                         : 4;
-	unsigned access_id               : 4;
+	unsigned			 : 4;
+	unsigned access_id		 : 4;
 } per_lowcore_bits;
 
-typedef struct
-{
+typedef struct {
 	union {
 		per_cr_words   words;
 		per_cr_bits    bits;
@@ -364,9 +365,9 @@ typedef struct
 	 * the kernel always sets them to zero. To enable single
 	 * stepping use ptrace(PTRACE_SINGLESTEP) instead.
 	 */
-	unsigned  single_step       : 1;
+	unsigned  single_step	    : 1;
 	unsigned  instruction_fetch : 1;
-	unsigned                    : 30;
+	unsigned		    : 30;
 	/*
 	 * These addresses are copied into cr10 & cr11 if single
 	 * stepping is switched off
@@ -376,11 +377,10 @@ typedef struct
 	union {
 		per_lowcore_words words;
 		per_lowcore_bits  bits;
-	} lowcore; 
+	} lowcore;
 } per_struct;
 
-typedef struct
-{
+typedef struct {
 	unsigned int  len;
 	unsigned long kernel_addr;
 	unsigned long process_addr;
@@ -390,12 +390,12 @@ typedef struct
  * S/390 specific non posix ptrace requests. I chose unusual values so
  * they are unlikely to clash with future ptrace definitions.
  */
-#define PTRACE_PEEKUSR_AREA           0x5000
-#define PTRACE_POKEUSR_AREA           0x5001
+#define PTRACE_PEEKUSR_AREA	      0x5000
+#define PTRACE_POKEUSR_AREA	      0x5001
 #define PTRACE_PEEKTEXT_AREA	      0x5002
 #define PTRACE_PEEKDATA_AREA	      0x5003
 #define PTRACE_POKETEXT_AREA	      0x5004
-#define PTRACE_POKEDATA_AREA 	      0x5005
+#define PTRACE_POKEDATA_AREA	      0x5005
 #define PTRACE_GET_LAST_BREAK	      0x5006
 #define PTRACE_PEEK_SYSTEM_CALL       0x5007
 #define PTRACE_POKE_SYSTEM_CALL	      0x5008
@@ -413,21 +413,19 @@ typedef struct
  * PT_PROT definition is loosely based on hppa bsd definition in
  * gdb/hppab-nat.c
  */
-#define PTRACE_PROT                       21
+#define PTRACE_PROT			  21
 
-typedef enum
-{
+typedef enum {
 	ptprot_set_access_watchpoint,
 	ptprot_set_write_watchpoint,
 	ptprot_disable_watchpoint
 } ptprot_flags;
 
-typedef struct
-{
+typedef struct {
 	unsigned long lowaddr;
 	unsigned long hiaddr;
 	ptprot_flags prot;
-} ptprot_area;                     
+} ptprot_area;
 
 /* Sequence of bytes for breakpoint illegal instruction.  */
 #define S390_BREAKPOINT     {0x0,0x1}
@@ -439,8 +437,7 @@ typedef struct
  * The user_regs_struct defines the way the user registers are
  * store on the stack for signal handling.
  */
-struct user_regs_struct
-{
+struct user_regs_struct {
 	psw_t psw;
 	unsigned long gprs[NUM_GPRS];
 	unsigned int  acrs[NUM_ACRS];
diff --git a/arch/s390/include/uapi/asm/sthyi.h b/arch/s390/include/uapi/asm/sthyi.h
index ec113db4eb7e..b1b022316983 100644
--- a/arch/s390/include/uapi/asm/sthyi.h
+++ b/arch/s390/include/uapi/asm/sthyi.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_ASM_STHYI_H
 #define _UAPI_ASM_STHYI_H
 
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 725120939051..01b5fe8b9db6 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -8,405 +8,10 @@
 #ifndef _UAPI_ASM_S390_UNISTD_H_
 #define _UAPI_ASM_S390_UNISTD_H_
 
-/*
- * This file contains the system call numbers.
- */
-
-#define __NR_exit                 1
-#define __NR_fork                 2
-#define __NR_read                 3
-#define __NR_write                4
-#define __NR_open                 5
-#define __NR_close                6
-#define __NR_restart_syscall	  7
-#define __NR_creat                8
-#define __NR_link                 9
-#define __NR_unlink              10
-#define __NR_execve              11
-#define __NR_chdir               12
-#define __NR_mknod               14
-#define __NR_chmod               15
-#define __NR_lseek               19
-#define __NR_getpid              20
-#define __NR_mount               21
-#define __NR_umount              22
-#define __NR_ptrace              26
-#define __NR_alarm               27
-#define __NR_pause               29
-#define __NR_utime               30
-#define __NR_access              33
-#define __NR_nice                34
-#define __NR_sync                36
-#define __NR_kill                37
-#define __NR_rename              38
-#define __NR_mkdir               39
-#define __NR_rmdir               40
-#define __NR_dup                 41
-#define __NR_pipe                42
-#define __NR_times               43
-#define __NR_brk                 45
-#define __NR_signal              48
-#define __NR_acct                51
-#define __NR_umount2             52
-#define __NR_ioctl               54
-#define __NR_fcntl               55
-#define __NR_setpgid             57
-#define __NR_umask               60
-#define __NR_chroot              61
-#define __NR_ustat               62
-#define __NR_dup2                63
-#define __NR_getppid             64
-#define __NR_getpgrp             65
-#define __NR_setsid              66
-#define __NR_sigaction           67
-#define __NR_sigsuspend          72
-#define __NR_sigpending          73
-#define __NR_sethostname         74
-#define __NR_setrlimit           75
-#define __NR_getrusage           77
-#define __NR_gettimeofday        78
-#define __NR_settimeofday        79
-#define __NR_symlink             83
-#define __NR_readlink            85
-#define __NR_uselib              86
-#define __NR_swapon              87
-#define __NR_reboot              88
-#define __NR_readdir             89
-#define __NR_mmap                90
-#define __NR_munmap              91
-#define __NR_truncate            92
-#define __NR_ftruncate           93
-#define __NR_fchmod              94
-#define __NR_getpriority         96
-#define __NR_setpriority         97
-#define __NR_statfs              99
-#define __NR_fstatfs            100
-#define __NR_socketcall         102
-#define __NR_syslog             103
-#define __NR_setitimer          104
-#define __NR_getitimer          105
-#define __NR_stat               106
-#define __NR_lstat              107
-#define __NR_fstat              108
-#define __NR_lookup_dcookie     110
-#define __NR_vhangup            111
-#define __NR_idle               112
-#define __NR_wait4              114
-#define __NR_swapoff            115
-#define __NR_sysinfo            116
-#define __NR_ipc                117
-#define __NR_fsync              118
-#define __NR_sigreturn          119
-#define __NR_clone              120
-#define __NR_setdomainname      121
-#define __NR_uname              122
-#define __NR_adjtimex           124
-#define __NR_mprotect           125
-#define __NR_sigprocmask        126
-#define __NR_create_module      127
-#define __NR_init_module        128
-#define __NR_delete_module      129
-#define __NR_get_kernel_syms    130
-#define __NR_quotactl           131
-#define __NR_getpgid            132
-#define __NR_fchdir             133
-#define __NR_bdflush            134
-#define __NR_sysfs              135
-#define __NR_personality        136
-#define __NR_afs_syscall        137 /* Syscall for Andrew File System */
-#define __NR_getdents           141
-#define __NR_flock              143
-#define __NR_msync              144
-#define __NR_readv              145
-#define __NR_writev             146
-#define __NR_getsid             147
-#define __NR_fdatasync          148
-#define __NR__sysctl            149
-#define __NR_mlock              150
-#define __NR_munlock            151
-#define __NR_mlockall           152
-#define __NR_munlockall         153
-#define __NR_sched_setparam             154
-#define __NR_sched_getparam             155
-#define __NR_sched_setscheduler         156
-#define __NR_sched_getscheduler         157
-#define __NR_sched_yield                158
-#define __NR_sched_get_priority_max     159
-#define __NR_sched_get_priority_min     160
-#define __NR_sched_rr_get_interval      161
-#define __NR_nanosleep          162
-#define __NR_mremap             163
-#define __NR_query_module       167
-#define __NR_poll               168
-#define __NR_nfsservctl         169
-#define __NR_prctl              172
-#define __NR_rt_sigreturn       173
-#define __NR_rt_sigaction       174
-#define __NR_rt_sigprocmask     175
-#define __NR_rt_sigpending      176
-#define __NR_rt_sigtimedwait    177
-#define __NR_rt_sigqueueinfo    178
-#define __NR_rt_sigsuspend      179
-#define __NR_pread64            180
-#define __NR_pwrite64           181
-#define __NR_getcwd             183
-#define __NR_capget             184
-#define __NR_capset             185
-#define __NR_sigaltstack        186
-#define __NR_sendfile           187
-#define __NR_getpmsg		188
-#define __NR_putpmsg		189
-#define __NR_vfork		190
-#define __NR_pivot_root         217
-#define __NR_mincore            218
-#define __NR_madvise            219
-#define __NR_getdents64		220
-#define __NR_readahead		222
-#define __NR_setxattr		224
-#define __NR_lsetxattr		225
-#define __NR_fsetxattr		226
-#define __NR_getxattr		227
-#define __NR_lgetxattr		228
-#define __NR_fgetxattr		229
-#define __NR_listxattr		230
-#define __NR_llistxattr		231
-#define __NR_flistxattr		232
-#define __NR_removexattr	233
-#define __NR_lremovexattr	234
-#define __NR_fremovexattr	235
-#define __NR_gettid		236
-#define __NR_tkill		237
-#define __NR_futex		238
-#define __NR_sched_setaffinity	239
-#define __NR_sched_getaffinity	240
-#define __NR_tgkill		241
-/* Number 242 is reserved for tux */
-#define __NR_io_setup		243
-#define __NR_io_destroy		244
-#define __NR_io_getevents	245
-#define __NR_io_submit		246
-#define __NR_io_cancel		247
-#define __NR_exit_group		248
-#define __NR_epoll_create	249
-#define __NR_epoll_ctl		250
-#define __NR_epoll_wait		251
-#define __NR_set_tid_address	252
-#define __NR_fadvise64		253
-#define __NR_timer_create	254
-#define __NR_timer_settime	255
-#define __NR_timer_gettime	256
-#define __NR_timer_getoverrun	257
-#define __NR_timer_delete	258
-#define __NR_clock_settime	259
-#define __NR_clock_gettime	260
-#define __NR_clock_getres	261
-#define __NR_clock_nanosleep	262
-/* Number 263 is reserved for vserver */
-#define __NR_statfs64		265
-#define __NR_fstatfs64		266
-#define __NR_remap_file_pages	267
-#define __NR_mbind		268
-#define __NR_get_mempolicy	269
-#define __NR_set_mempolicy	270
-#define __NR_mq_open		271
-#define __NR_mq_unlink		272
-#define __NR_mq_timedsend	273
-#define __NR_mq_timedreceive	274
-#define __NR_mq_notify		275
-#define __NR_mq_getsetattr	276
-#define __NR_kexec_load		277
-#define __NR_add_key		278
-#define __NR_request_key	279
-#define __NR_keyctl		280
-#define __NR_waitid		281
-#define __NR_ioprio_set		282
-#define __NR_ioprio_get		283
-#define __NR_inotify_init	284
-#define __NR_inotify_add_watch	285
-#define __NR_inotify_rm_watch	286
-#define __NR_migrate_pages	287
-#define __NR_openat		288
-#define __NR_mkdirat		289
-#define __NR_mknodat		290
-#define __NR_fchownat		291
-#define __NR_futimesat		292
-#define __NR_unlinkat		294
-#define __NR_renameat		295
-#define __NR_linkat		296
-#define __NR_symlinkat		297
-#define __NR_readlinkat		298
-#define __NR_fchmodat		299
-#define __NR_faccessat		300
-#define __NR_pselect6		301
-#define __NR_ppoll		302
-#define __NR_unshare		303
-#define __NR_set_robust_list	304
-#define __NR_get_robust_list	305
-#define __NR_splice		306
-#define __NR_sync_file_range	307
-#define __NR_tee		308
-#define __NR_vmsplice		309
-#define __NR_move_pages		310
-#define __NR_getcpu		311
-#define __NR_epoll_pwait	312
-#define __NR_utimes		313
-#define __NR_fallocate		314
-#define __NR_utimensat		315
-#define __NR_signalfd		316
-#define __NR_timerfd		317
-#define __NR_eventfd		318
-#define __NR_timerfd_create	319
-#define __NR_timerfd_settime	320
-#define __NR_timerfd_gettime	321
-#define __NR_signalfd4		322
-#define __NR_eventfd2		323
-#define __NR_inotify_init1	324
-#define __NR_pipe2		325
-#define __NR_dup3		326
-#define __NR_epoll_create1	327
-#define	__NR_preadv		328
-#define	__NR_pwritev		329
-#define __NR_rt_tgsigqueueinfo	330
-#define __NR_perf_event_open	331
-#define __NR_fanotify_init	332
-#define __NR_fanotify_mark	333
-#define __NR_prlimit64		334
-#define __NR_name_to_handle_at	335
-#define __NR_open_by_handle_at	336
-#define __NR_clock_adjtime	337
-#define __NR_syncfs		338
-#define __NR_setns		339
-#define __NR_process_vm_readv	340
-#define __NR_process_vm_writev	341
-#define __NR_s390_runtime_instr 342
-#define __NR_kcmp		343
-#define __NR_finit_module	344
-#define __NR_sched_setattr	345
-#define __NR_sched_getattr	346
-#define __NR_renameat2		347
-#define __NR_seccomp		348
-#define __NR_getrandom		349
-#define __NR_memfd_create	350
-#define __NR_bpf		351
-#define __NR_s390_pci_mmio_write	352
-#define __NR_s390_pci_mmio_read		353
-#define __NR_execveat		354
-#define __NR_userfaultfd	355
-#define __NR_membarrier		356
-#define __NR_recvmmsg		357
-#define __NR_sendmmsg		358
-#define __NR_socket		359
-#define __NR_socketpair		360
-#define __NR_bind		361
-#define __NR_connect		362
-#define __NR_listen		363
-#define __NR_accept4		364
-#define __NR_getsockopt		365
-#define __NR_setsockopt		366
-#define __NR_getsockname	367
-#define __NR_getpeername	368
-#define __NR_sendto		369
-#define __NR_sendmsg		370
-#define __NR_recvfrom		371
-#define __NR_recvmsg		372
-#define __NR_shutdown		373
-#define __NR_mlock2		374
-#define __NR_copy_file_range	375
-#define __NR_preadv2		376
-#define __NR_pwritev2		377
-#define __NR_s390_guarded_storage	378
-#define __NR_statx		379
-#define __NR_s390_sthyi		380
-#define NR_syscalls 381
-
-/* 
- * There are some system calls that are not present on 64 bit, some
- * have a different name although they do the same (e.g. __NR_chown32
- * is __NR_chown on 64 bit).
- */
-#ifndef __s390x__
-
-#define __NR_time		 13
-#define __NR_lchown		 16
-#define __NR_setuid		 23
-#define __NR_getuid		 24
-#define __NR_stime		 25
-#define __NR_setgid		 46
-#define __NR_getgid		 47
-#define __NR_geteuid		 49
-#define __NR_getegid		 50
-#define __NR_setreuid		 70
-#define __NR_setregid		 71
-#define __NR_getrlimit		 76
-#define __NR_getgroups		 80
-#define __NR_setgroups		 81
-#define __NR_fchown		 95
-#define __NR_ioperm		101
-#define __NR_setfsuid		138
-#define __NR_setfsgid		139
-#define __NR__llseek		140
-#define __NR__newselect 	142
-#define __NR_setresuid		164
-#define __NR_getresuid		165
-#define __NR_setresgid		170
-#define __NR_getresgid		171
-#define __NR_chown		182
-#define __NR_ugetrlimit		191	/* SuS compliant getrlimit */
-#define __NR_mmap2		192
-#define __NR_truncate64		193
-#define __NR_ftruncate64	194
-#define __NR_stat64		195
-#define __NR_lstat64		196
-#define __NR_fstat64		197
-#define __NR_lchown32		198
-#define __NR_getuid32		199
-#define __NR_getgid32		200
-#define __NR_geteuid32		201
-#define __NR_getegid32		202
-#define __NR_setreuid32		203
-#define __NR_setregid32		204
-#define __NR_getgroups32	205
-#define __NR_setgroups32	206
-#define __NR_fchown32		207
-#define __NR_setresuid32	208
-#define __NR_getresuid32	209
-#define __NR_setresgid32	210
-#define __NR_getresgid32	211
-#define __NR_chown32		212
-#define __NR_setuid32		213
-#define __NR_setgid32		214
-#define __NR_setfsuid32		215
-#define __NR_setfsgid32		216
-#define __NR_fcntl64		221
-#define __NR_sendfile64		223
-#define __NR_fadvise64_64	264
-#define __NR_fstatat64		293
-
+#ifdef __s390x__
+#include <asm/unistd_64.h>
 #else
-
-#define __NR_select		142
-#define __NR_getrlimit		191	/* SuS compliant getrlimit */
-#define __NR_lchown  		198
-#define __NR_getuid  		199
-#define __NR_getgid  		200
-#define __NR_geteuid  		201
-#define __NR_getegid  		202
-#define __NR_setreuid  		203
-#define __NR_setregid  		204
-#define __NR_getgroups  	205
-#define __NR_setgroups  	206
-#define __NR_fchown  		207
-#define __NR_setresuid  	208
-#define __NR_getresuid  	209
-#define __NR_setresgid  	210
-#define __NR_getresgid  	211
-#define __NR_chown  		212
-#define __NR_setuid  		213
-#define __NR_setgid  		214
-#define __NR_setfsuid  		215
-#define __NR_setfsgid  		216
-#define __NR_newfstatat		293
-
+#include <asm/unistd_32.h>
 #endif
 
 #endif /* _UAPI_ASM_S390_UNISTD_H_ */
diff --git a/arch/s390/include/uapi/asm/virtio-ccw.h b/arch/s390/include/uapi/asm/virtio-ccw.h
index 967aad390105..2b605f7e8483 100644
--- a/arch/s390/include/uapi/asm/virtio-ccw.h
+++ b/arch/s390/include/uapi/asm/virtio-ccw.h
@@ -1,13 +1,9 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
 /*
  * Definitions for virtio-ccw devices.
  *
  * Copyright IBM Corp. 2013
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *  Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
  */
 #ifndef __KVM_VIRTIO_CCW_H
diff --git a/arch/s390/include/uapi/asm/vmcp.h b/arch/s390/include/uapi/asm/vmcp.h
index 4caf71714a55..aeaaa030030e 100644
--- a/arch/s390/include/uapi/asm/vmcp.h
+++ b/arch/s390/include/uapi/asm/vmcp.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Copyright IBM Corp. 2004, 2005
  * Interface implementation for communication with the z/VM control program
diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h
index 137ef473584e..d568307321fc 100644
--- a/arch/s390/include/uapi/asm/zcrypt.h
+++ b/arch/s390/include/uapi/asm/zcrypt.h
@@ -9,20 +9,6 @@
  *	       Eric Rossman (edrossma@us.ibm.com)
  *
  *  Hotplug & misc device support: Jochen Roehrig (roehrig@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __ASM_S390_ZCRYPT_H
diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c
index 315986a06cf5..574e77622c04 100644
--- a/arch/s390/kernel/alternative.c
+++ b/arch/s390/kernel/alternative.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/module.h>
 #include <asm/alternative.h>
 #include <asm/facility.h>
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index f04db3779b34..79b7a3438d54 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -110,7 +110,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setregid16, u16, rgid, u16, egid)
 
 COMPAT_SYSCALL_DEFINE1(s390_setgid16, u16, gid)
 {
-	return sys_setgid((gid_t)gid);
+	return sys_setgid(low2highgid(gid));
 }
 
 COMPAT_SYSCALL_DEFINE2(s390_setreuid16, u16, ruid, u16, euid)
@@ -120,7 +120,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setreuid16, u16, ruid, u16, euid)
 
 COMPAT_SYSCALL_DEFINE1(s390_setuid16, u16, uid)
 {
-	return sys_setuid((uid_t)uid);
+	return sys_setuid(low2highuid(uid));
 }
 
 COMPAT_SYSCALL_DEFINE3(s390_setresuid16, u16, ruid, u16, euid, u16, suid)
@@ -173,12 +173,12 @@ COMPAT_SYSCALL_DEFINE3(s390_getresgid16, u16 __user *, rgidp,
 
 COMPAT_SYSCALL_DEFINE1(s390_setfsuid16, u16, uid)
 {
-	return sys_setfsuid((uid_t)uid);
+	return sys_setfsuid(low2highuid(uid));
 }
 
 COMPAT_SYSCALL_DEFINE1(s390_setfsgid16, u16, gid)
 {
-	return sys_setfsgid((gid_t)gid);
+	return sys_setfsgid(low2highgid(gid));
 }
 
 static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info)
@@ -263,6 +263,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplis
 		return retval;
 	}
 
+	groups_sort(group_info);
 	retval = set_current_groups(group_info);
 	put_group_info(group_info);
 
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index ef246940b44c..18c1eeb847b2 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -50,106 +50,6 @@ typedef struct
 	struct ucontext32 uc;
 } rt_sigframe32;
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
-{
-	int err;
-
-	/* If you change siginfo_t structure, please be sure
-	   this code is fixed accordingly.
-	   It should never copy any pad contained in the structure
-	   to avoid security leaks, but must copy the generic
-	   3 ints plus the relevant union member.  
-	   This routine must convert siginfo from 64bit to 32bit as well
-	   at the same time.  */
-	err = __put_user(from->si_signo, &to->si_signo);
-	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user(from->si_code, &to->si_code);
-	if (from->si_code < 0)
-		err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
-	else {
-		switch (siginfo_layout(from->si_signo, from->si_code)) {
-		case SIL_RT:
-			err |= __put_user(from->si_int, &to->si_int);
-			/* fallthrough */
-		case SIL_KILL:
-			err |= __put_user(from->si_pid, &to->si_pid);
-			err |= __put_user(from->si_uid, &to->si_uid);
-			break;
-		case SIL_CHLD:
-			err |= __put_user(from->si_pid, &to->si_pid);
-			err |= __put_user(from->si_uid, &to->si_uid);
-			err |= __put_user(from->si_utime, &to->si_utime);
-			err |= __put_user(from->si_stime, &to->si_stime);
-			err |= __put_user(from->si_status, &to->si_status);
-			break;
-		case SIL_FAULT:
-			err |= __put_user((unsigned long) from->si_addr,
-					  &to->si_addr);
-			break;
-		case SIL_POLL:
-			err |= __put_user(from->si_band, &to->si_band);
-			err |= __put_user(from->si_fd, &to->si_fd);
-			break;
-		case SIL_TIMER:
-			err |= __put_user(from->si_tid, &to->si_tid);
-			err |= __put_user(from->si_overrun, &to->si_overrun);
-			err |= __put_user(from->si_int, &to->si_int);
-			break;
-		default:
-			break;
-		}
-	}
-	return err ? -EFAULT : 0;
-}
-
-int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
-{
-	int err;
-	u32 tmp;
-
-	err = __get_user(to->si_signo, &from->si_signo);
-	err |= __get_user(to->si_errno, &from->si_errno);
-	err |= __get_user(to->si_code, &from->si_code);
-
-	if (to->si_code < 0)
-		err |= __copy_from_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
-	else {
-		switch (siginfo_layout(to->si_signo, to->si_code)) {
-		case SIL_RT:
-			err |= __get_user(to->si_int, &from->si_int);
-			/* fallthrough */
-		case SIL_KILL:
-			err |= __get_user(to->si_pid, &from->si_pid);
-			err |= __get_user(to->si_uid, &from->si_uid);
-			break;
-		case SIL_CHLD:
-			err |= __get_user(to->si_pid, &from->si_pid);
-			err |= __get_user(to->si_uid, &from->si_uid);
-			err |= __get_user(to->si_utime, &from->si_utime);
-			err |= __get_user(to->si_stime, &from->si_stime);
-			err |= __get_user(to->si_status, &from->si_status);
-			break;
-		case SIL_FAULT:
-			err |= __get_user(tmp, &from->si_addr);
-			to->si_addr = (void __force __user *)
-				(u64) (tmp & PSW32_ADDR_INSN);
-			break;
-		case SIL_POLL:
-			err |= __get_user(to->si_band, &from->si_band);
-			err |= __get_user(to->si_fd, &from->si_fd);
-			break;
-		case SIL_TIMER:
-			err |= __get_user(to->si_tid, &from->si_tid);
-			err |= __get_user(to->si_overrun, &from->si_overrun);
-			err |= __get_user(to->si_int, &from->si_int);
-			break;
-		default:
-			break;
-		}
-	}
-	return err ? -EFAULT : 0;
-}
-
 /* Store registers needed to create the signal frame */
 static void store_sigregs(void)
 {
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 58b9e127b615..80e974adb9e8 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -1392,7 +1392,7 @@ int debug_dflt_header_fn(debug_info_t *id, struct debug_view *view,
 	else
 		except_str = "-";
 	caller = (unsigned long) entry->caller;
-	rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %02i %p  ",
+	rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %02i %pK  ",
 		      area, sec, usec, level, except_str,
 		      entry->id.fields.cpuid, (void *)caller);
 	return rc;
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 3be829721cf9..b2c68fbf2634 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Disassemble s390 instructions.
  *
@@ -396,9 +397,14 @@ struct s390_insn *find_insn(unsigned char *code)
 	unsigned char opfrag;
 	int i;
 
+	/* Search the opcode offset table to find an entry which
+	 * matches the beginning of the opcode. If there is no match
+	 * the last entry will be used, which is the default entry for
+	 * unknown instructions as well as 1-byte opcode instructions.
+	 */
 	for (i = 0; i < ARRAY_SIZE(opcode_offset); i++) {
 		entry = &opcode_offset[i];
-		if (entry->opcode == code[0] || entry->opcode == 0)
+		if (entry->opcode == code[0])
 			break;
 	}
 
@@ -543,7 +549,7 @@ void show_code(struct pt_regs *regs)
 		start += opsize;
 		pr_cont("%s", buffer);
 		ptr = buffer;
-		ptr += sprintf(ptr, "\n\t  ");
+		ptr += sprintf(ptr, "\n          ");
 		hops++;
 	}
 	pr_cont("\n");
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 2aa545dca4d5..5b23c4f6e50c 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Stack dumping functions
  *
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index a316cd6999ad..6cd444d25545 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -180,18 +180,17 @@ _PIF_WORK	= (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
  */
 ENTRY(__switch_to)
 	stmg	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
-	lgr	%r1,%r2
-	aghi	%r1,__TASK_thread		# thread_struct of prev task
-	lg	%r5,__TASK_stack(%r3)		# start of kernel stack of next
-	stg	%r15,__THREAD_ksp(%r1)		# store kernel stack of prev
-	lgr	%r1,%r3
-	aghi	%r1,__TASK_thread		# thread_struct of next task
+	lghi	%r4,__TASK_stack
+	lghi	%r1,__TASK_thread
+	lg	%r5,0(%r4,%r3)			# start of kernel stack of next
+	stg	%r15,__THREAD_ksp(%r1,%r2)	# store kernel stack of prev
 	lgr	%r15,%r5
 	aghi	%r15,STACK_INIT			# end of kernel stack of next
 	stg	%r3,__LC_CURRENT		# store task struct of next
 	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
-	lg	%r15,__THREAD_ksp(%r1)		# load kernel stack of next
-	mvc	__LC_CURRENT_PID(4,%r0),__TASK_pid(%r3) # store pid of next
+	lg	%r15,__THREAD_ksp(%r1,%r3)	# load kernel stack of next
+	aghi	%r3,__TASK_pid
+	mvc	__LC_CURRENT_PID(4,%r0),0(%r3)	# store pid of next
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_LPP
 	bzr	%r14
@@ -1393,7 +1392,7 @@ cleanup_critical:
 #define SYSCALL(esame,emu)	.long esame
 	.globl	sys_call_table
 sys_call_table:
-#include "syscalls.S"
+#include "asm/syscall_table.h"
 #undef SYSCALL
 
 #ifdef CONFIG_COMPAT
@@ -1401,6 +1400,6 @@ sys_call_table:
 #define SYSCALL(esame,emu)	.long emu
 	.globl	sys_call_table_emu
 sys_call_table_emu:
-#include "syscalls.S"
+#include "asm/syscall_table.h"
 #undef SYSCALL
 #endif
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index b86fa3ee4927..5c42f16a54c4 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -66,7 +66,7 @@ __HEAD
 # subroutine to wait for end I/O
 #
 .Lirqwait:
-	mvc	0x1f0(16),.Lnewpsw	# set up IO interrupt psw
+	mvc	__LC_IO_NEW_PSW(16),.Lnewpsw	# set up IO interrupt psw
 	lpsw	.Lwaitpsw
 .Lioint:
 	br	%r14
@@ -98,7 +98,7 @@ __HEAD
 	bnz	.Llderr
 .Lwait4irq:
 	bas	%r14,.Lirqwait
-	c	%r1,0xb8		# compare subchannel number
+	c	%r1,__LC_SUBCHANNEL_ID	# compare subchannel number
 	bne	.Lwait4irq
 	tsch	0(%r5)
 
@@ -156,9 +156,9 @@ iplstart:
 	.fill	16,4,0x0
 0:	lmh	%r0,%r15,0(%r13)	# clear high-order half of gprs
 	sam31				# switch to 31 bit addressing mode
-	lh	%r1,0xb8		# test if subchannel number
+	lh	%r1,__LC_SUBCHANNEL_ID	# test if subchannel number
 	bct	%r1,.Lnoload		#  is valid
-	l	%r1,0xb8		# load ipl subchannel number
+	l	%r1,__LC_SUBCHANNEL_ID	# load ipl subchannel number
 	la	%r2,IPL_BS		# load start address
 	bas	%r14,.Lloader		# load rest of ipl image
 	l	%r12,.Lparm		# pointer to parameter area
@@ -239,7 +239,7 @@ iplstart:
 	bz	.Lnoreset
 .Lwaitforirq:
 	bas	%r14,.Lirqwait		# wait for IO interrupt
-	c	%r1,0xb8		# compare subchannel number
+	c	%r1,__LC_SUBCHANNEL_ID	# compare subchannel number
 	bne	.Lwaitforirq
 	la	%r5,.Lirb
 	tsch	0(%r5)
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 310e59e6eb4b..da5cc3b469aa 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *    ipl/reipl/dump support for Linux on s390.
  *
@@ -118,13 +119,9 @@ static char *dump_type_str(enum dump_type type)
 	}
 }
 
-/*
- * Must be in data section since the bss section
- * is not cleared when these are accessed.
- */
-static u8 ipl_ssid __section(.data) = 0;
-static u16 ipl_devno __section(.data) = 0;
-u32 ipl_flags __section(.data) = 0;
+static u8 ipl_ssid;
+static u16 ipl_devno;
+u32 ipl_flags;
 
 enum ipl_method {
 	REIPL_METHOD_CCW_CIO,
@@ -147,7 +144,7 @@ enum dump_method {
 	DUMP_METHOD_FCP_DIAG,
 };
 
-static int diag308_set_works = 0;
+static int diag308_set_works;
 
 static struct ipl_parameter_block ipl_block;
 
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 1a6521af1751..943d13e90c98 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  *  Kernel Probes (KProbes)
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright IBM Corp. 2002, 2006
  *
  * s390 port, used ppc64 as template. Mike Grundy <grundym@us.ibm.com>
@@ -33,7 +20,6 @@
 #include <linux/ftrace.h>
 #include <asm/set_memory.h>
 #include <asm/sections.h>
-#include <linux/uaccess.h>
 #include <asm/dis.h>
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe);
diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c
index bf9622f0e6b1..452502f9a0d9 100644
--- a/arch/s390/kernel/lgr.c
+++ b/arch/s390/kernel/lgr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Linux Guest Relocation (LGR) detection
  *
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 7b87991416fd..b7abfad4fd7d 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  *  Kernel module help for s390.
  *
@@ -8,20 +9,6 @@
  *
  *  based on i386 version
  *    Copyright (C) 2001 Rusty Russell.
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 #include <linux/module.h>
 #include <linux/elf.h>
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 6ff169253cae..c7a627620e5e 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *   Machine check handler
  *
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 746d03423333..cc085e2d2ce9 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Performance event support for s390x - CPU-measurement Counter Facility
  *
  *  Copyright IBM Corp. 2012, 2017
  *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 #define KMSG_COMPONENT	"cpum_cf"
 #define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 227b38bd82c9..1c9ddd7aa5ec 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Performance event support for the System z CPU-measurement Sampling Facility
  *
  * Copyright IBM Corp. 2013
  * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 #define KMSG_COMPONENT	"cpum_sf"
 #define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 93a386f4a3b5..0d770e513abf 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Performance event support for s390x
  *
  *  Copyright IBM Corp. 2012, 2013
  *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 #define KMSG_COMPONENT	"perf"
 #define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c
index f8603ebed669..54e2d634b849 100644
--- a/arch/s390/kernel/perf_regs.c
+++ b/arch/s390/kernel/perf_regs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/perf_event.h>
 #include <linux/perf_regs.h>
 #include <linux/kernel.h>
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 26c0523c1488..cd3df5514552 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -1651,6 +1651,14 @@ static const struct user_regset s390_compat_regsets[] = {
 		.set = s390_gs_cb_set,
 	},
 	{
+		.core_note_type = NT_S390_GS_BC,
+		.n = sizeof(struct gs_cb) / sizeof(__u64),
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.get = s390_gs_bc_get,
+		.set = s390_gs_bc_set,
+	},
+	{
 		.core_note_type = NT_S390_RI_CB,
 		.n = sizeof(struct runtime_instr_cb) / sizeof(__u64),
 		.size = sizeof(__u64),
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 090053cf279b..793da97f9a6e 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  S390 version
  *    Copyright IBM Corp. 1999, 2012
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index cd4334e80b64..a919b2f0141d 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -55,6 +55,7 @@
 #include <asm/sigp.h>
 #include <asm/idle.h>
 #include <asm/nmi.h>
+#include <asm/topology.h>
 #include "entry.h"
 
 enum {
@@ -1150,7 +1151,7 @@ static ssize_t __ref rescan_store(struct device *dev,
 	rc = smp_rescan_cpus();
 	return rc ? rc : count;
 }
-static DEVICE_ATTR(rescan, 0200, NULL, rescan_store);
+static DEVICE_ATTR_WO(rescan);
 #endif /* CONFIG_HOTPLUG_CPU */
 
 static int __init s390_smp_init(void)
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index e66687dc6144..460dcfba7d4e 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Stack trace management functions
  *
diff --git a/arch/s390/kernel/sthyi.c b/arch/s390/kernel/sthyi.c
index 12981e197f01..80b862e9c53c 100644
--- a/arch/s390/kernel/sthyi.c
+++ b/arch/s390/kernel/sthyi.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * store hypervisor information instruction emulation functions.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  * Copyright IBM Corp. 2016
  * Author(s): Janosch Frank <frankja@linux.vnet.ibm.com>
  */
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
deleted file mode 100644
index 308a7b63348b..000000000000
--- a/arch/s390/kernel/syscalls.S
+++ /dev/null
@@ -1,392 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * definitions for sys_call_table, each line represents an
- * entry in the table in the form
- * SYSCALL(64 bit syscall, 31 bit emulated syscall)
- *
- * this file is meant to be included from entry.S
- */
-
-#define NI_SYSCALL SYSCALL(sys_ni_syscall,sys_ni_syscall)
-
-NI_SYSCALL						/* 0 */
-SYSCALL(sys_exit,sys_exit)
-SYSCALL(sys_fork,sys_fork)
-SYSCALL(sys_read,compat_sys_s390_read)
-SYSCALL(sys_write,compat_sys_s390_write)
-SYSCALL(sys_open,compat_sys_open)			/* 5 */
-SYSCALL(sys_close,sys_close)
-SYSCALL(sys_restart_syscall,sys_restart_syscall)
-SYSCALL(sys_creat,compat_sys_creat)
-SYSCALL(sys_link,compat_sys_link)
-SYSCALL(sys_unlink,compat_sys_unlink)			/* 10 */
-SYSCALL(sys_execve,compat_sys_execve)
-SYSCALL(sys_chdir,compat_sys_chdir)
-SYSCALL(sys_ni_syscall,compat_sys_time)			/* old time syscall */
-SYSCALL(sys_mknod,compat_sys_mknod)
-SYSCALL(sys_chmod,compat_sys_chmod)			/* 15 */
-SYSCALL(sys_ni_syscall,compat_sys_s390_lchown16)	/* old lchown16 syscall*/
-NI_SYSCALL						/* old break syscall holder */
-NI_SYSCALL						/* old stat syscall holder */
-SYSCALL(sys_lseek,compat_sys_lseek)
-SYSCALL(sys_getpid,sys_getpid)				/* 20 */
-SYSCALL(sys_mount,compat_sys_mount)
-SYSCALL(sys_oldumount,compat_sys_oldumount)
-SYSCALL(sys_ni_syscall,compat_sys_s390_setuid16)	/* old setuid16 syscall*/
-SYSCALL(sys_ni_syscall,compat_sys_s390_getuid16)	/* old getuid16 syscall*/
-SYSCALL(sys_ni_syscall,compat_sys_stime)		/* 25 old stime syscall */
-SYSCALL(sys_ptrace,compat_sys_ptrace)
-SYSCALL(sys_alarm,sys_alarm)
-NI_SYSCALL						/* old fstat syscall */
-SYSCALL(sys_pause,sys_pause)
-SYSCALL(sys_utime,compat_sys_utime)			/* 30 */
-NI_SYSCALL						/* old stty syscall */
-NI_SYSCALL						/* old gtty syscall */
-SYSCALL(sys_access,compat_sys_access)
-SYSCALL(sys_nice,sys_nice)
-NI_SYSCALL						/* 35 old ftime syscall */
-SYSCALL(sys_sync,sys_sync)
-SYSCALL(sys_kill,sys_kill)
-SYSCALL(sys_rename,compat_sys_rename)
-SYSCALL(sys_mkdir,compat_sys_mkdir)
-SYSCALL(sys_rmdir,compat_sys_rmdir)			/* 40 */
-SYSCALL(sys_dup,sys_dup)
-SYSCALL(sys_pipe,compat_sys_pipe)
-SYSCALL(sys_times,compat_sys_times)
-NI_SYSCALL						/* old prof syscall */
-SYSCALL(sys_brk,compat_sys_brk)				/* 45 */
-SYSCALL(sys_ni_syscall,compat_sys_s390_setgid16)	/* old setgid16 syscall*/
-SYSCALL(sys_ni_syscall,compat_sys_s390_getgid16)	/* old getgid16 syscall*/
-SYSCALL(sys_signal,compat_sys_signal)
-SYSCALL(sys_ni_syscall,compat_sys_s390_geteuid16)	/* old geteuid16 syscall */
-SYSCALL(sys_ni_syscall,compat_sys_s390_getegid16)	/* 50 old getegid16 syscall */
-SYSCALL(sys_acct,compat_sys_acct)
-SYSCALL(sys_umount,compat_sys_umount)
-NI_SYSCALL						/* old lock syscall */
-SYSCALL(sys_ioctl,compat_sys_ioctl)
-SYSCALL(sys_fcntl,compat_sys_fcntl)			/* 55 */
-NI_SYSCALL						/* intel mpx syscall */
-SYSCALL(sys_setpgid,sys_setpgid)
-NI_SYSCALL						/* old ulimit syscall */
-NI_SYSCALL						/* old uname syscall */
-SYSCALL(sys_umask,sys_umask)				/* 60 */
-SYSCALL(sys_chroot,compat_sys_chroot)
-SYSCALL(sys_ustat,compat_sys_ustat)
-SYSCALL(sys_dup2,sys_dup2)
-SYSCALL(sys_getppid,sys_getppid)
-SYSCALL(sys_getpgrp,sys_getpgrp)			/* 65 */
-SYSCALL(sys_setsid,sys_setsid)
-SYSCALL(sys_sigaction,compat_sys_sigaction)
-NI_SYSCALL						/* old sgetmask syscall*/
-NI_SYSCALL						/* old ssetmask syscall*/
-SYSCALL(sys_ni_syscall,compat_sys_s390_setreuid16)	/* old setreuid16 syscall */
-SYSCALL(sys_ni_syscall,compat_sys_s390_setregid16)	/* old setregid16 syscall */
-SYSCALL(sys_sigsuspend,compat_sys_sigsuspend)
-SYSCALL(sys_sigpending,compat_sys_sigpending)
-SYSCALL(sys_sethostname,compat_sys_sethostname)
-SYSCALL(sys_setrlimit,compat_sys_setrlimit)		/* 75 */
-SYSCALL(sys_getrlimit,compat_sys_old_getrlimit)
-SYSCALL(sys_getrusage,compat_sys_getrusage)
-SYSCALL(sys_gettimeofday,compat_sys_gettimeofday)
-SYSCALL(sys_settimeofday,compat_sys_settimeofday)
-SYSCALL(sys_ni_syscall,compat_sys_s390_getgroups16)	/* 80 old getgroups16 syscall */
-SYSCALL(sys_ni_syscall,compat_sys_s390_setgroups16)	/* old setgroups16 syscall */
-NI_SYSCALL						/* old select syscall */
-SYSCALL(sys_symlink,compat_sys_symlink)
-NI_SYSCALL						/* old lstat syscall */
-SYSCALL(sys_readlink,compat_sys_readlink)		/* 85 */
-SYSCALL(sys_uselib,compat_sys_uselib)
-SYSCALL(sys_swapon,compat_sys_swapon)
-SYSCALL(sys_reboot,compat_sys_reboot)
-SYSCALL(sys_ni_syscall,compat_sys_old_readdir)		/* old readdir syscall */
-SYSCALL(sys_old_mmap,compat_sys_s390_old_mmap)		/* 90 */
-SYSCALL(sys_munmap,compat_sys_munmap)
-SYSCALL(sys_truncate,compat_sys_truncate)
-SYSCALL(sys_ftruncate,compat_sys_ftruncate)
-SYSCALL(sys_fchmod,sys_fchmod)
-SYSCALL(sys_ni_syscall,compat_sys_s390_fchown16)	/* 95 old fchown16 syscall*/
-SYSCALL(sys_getpriority,sys_getpriority)
-SYSCALL(sys_setpriority,sys_setpriority)
-NI_SYSCALL						/* old profil syscall */
-SYSCALL(sys_statfs,compat_sys_statfs)
-SYSCALL(sys_fstatfs,compat_sys_fstatfs)			/* 100 */
-NI_SYSCALL						/* ioperm for i386 */
-SYSCALL(sys_socketcall,compat_sys_socketcall)
-SYSCALL(sys_syslog,compat_sys_syslog)
-SYSCALL(sys_setitimer,compat_sys_setitimer)
-SYSCALL(sys_getitimer,compat_sys_getitimer)		/* 105 */
-SYSCALL(sys_newstat,compat_sys_newstat)
-SYSCALL(sys_newlstat,compat_sys_newlstat)
-SYSCALL(sys_newfstat,compat_sys_newfstat)
-NI_SYSCALL						/* old uname syscall */
-SYSCALL(sys_lookup_dcookie,compat_sys_lookup_dcookie)	/* 110 */
-SYSCALL(sys_vhangup,sys_vhangup)
-NI_SYSCALL						/* old "idle" system call */
-NI_SYSCALL						/* vm86old for i386 */
-SYSCALL(sys_wait4,compat_sys_wait4)
-SYSCALL(sys_swapoff,compat_sys_swapoff)			/* 115 */
-SYSCALL(sys_sysinfo,compat_sys_sysinfo)
-SYSCALL(sys_s390_ipc,compat_sys_s390_ipc)
-SYSCALL(sys_fsync,sys_fsync)
-SYSCALL(sys_sigreturn,compat_sys_sigreturn)
-SYSCALL(sys_clone,compat_sys_clone)			/* 120 */
-SYSCALL(sys_setdomainname,compat_sys_setdomainname)
-SYSCALL(sys_newuname,compat_sys_newuname)
-NI_SYSCALL						/* modify_ldt for i386 */
-SYSCALL(sys_adjtimex,compat_sys_adjtimex)
-SYSCALL(sys_mprotect,compat_sys_mprotect)		/* 125 */
-SYSCALL(sys_sigprocmask,compat_sys_sigprocmask)
-NI_SYSCALL						/* old "create module" */
-SYSCALL(sys_init_module,compat_sys_init_module)
-SYSCALL(sys_delete_module,compat_sys_delete_module)
-NI_SYSCALL						/* 130: old get_kernel_syms */
-SYSCALL(sys_quotactl,compat_sys_quotactl)
-SYSCALL(sys_getpgid,sys_getpgid)
-SYSCALL(sys_fchdir,sys_fchdir)
-SYSCALL(sys_bdflush,compat_sys_bdflush)
-SYSCALL(sys_sysfs,compat_sys_sysfs)			/* 135 */
-SYSCALL(sys_s390_personality,sys_s390_personality)
-NI_SYSCALL						/* for afs_syscall */
-SYSCALL(sys_ni_syscall,compat_sys_s390_setfsuid16)	/* old setfsuid16 syscall */
-SYSCALL(sys_ni_syscall,compat_sys_s390_setfsgid16)	/* old setfsgid16 syscall */
-SYSCALL(sys_llseek,compat_sys_llseek)			/* 140 */
-SYSCALL(sys_getdents,compat_sys_getdents)
-SYSCALL(sys_select,compat_sys_select)
-SYSCALL(sys_flock,sys_flock)
-SYSCALL(sys_msync,compat_sys_msync)
-SYSCALL(sys_readv,compat_sys_readv)			/* 145 */
-SYSCALL(sys_writev,compat_sys_writev)
-SYSCALL(sys_getsid,sys_getsid)
-SYSCALL(sys_fdatasync,sys_fdatasync)
-SYSCALL(sys_sysctl,compat_sys_sysctl)
-SYSCALL(sys_mlock,compat_sys_mlock)			/* 150 */
-SYSCALL(sys_munlock,compat_sys_munlock)
-SYSCALL(sys_mlockall,sys_mlockall)
-SYSCALL(sys_munlockall,sys_munlockall)
-SYSCALL(sys_sched_setparam,compat_sys_sched_setparam)
-SYSCALL(sys_sched_getparam,compat_sys_sched_getparam)	/* 155 */
-SYSCALL(sys_sched_setscheduler,compat_sys_sched_setscheduler)
-SYSCALL(sys_sched_getscheduler,sys_sched_getscheduler)
-SYSCALL(sys_sched_yield,sys_sched_yield)
-SYSCALL(sys_sched_get_priority_max,sys_sched_get_priority_max)
-SYSCALL(sys_sched_get_priority_min,sys_sched_get_priority_min)	/* 160 */
-SYSCALL(sys_sched_rr_get_interval,compat_sys_sched_rr_get_interval)
-SYSCALL(sys_nanosleep,compat_sys_nanosleep)
-SYSCALL(sys_mremap,compat_sys_mremap)
-SYSCALL(sys_ni_syscall,compat_sys_s390_setresuid16)	/* old setresuid16 syscall */
-SYSCALL(sys_ni_syscall,compat_sys_s390_getresuid16)	/* 165 old getresuid16 syscall */
-NI_SYSCALL						/* for vm86 */
-NI_SYSCALL						/* old sys_query_module */
-SYSCALL(sys_poll,compat_sys_poll)
-NI_SYSCALL						/* old nfsservctl */
-SYSCALL(sys_ni_syscall,compat_sys_s390_setresgid16)	/* 170 old setresgid16 syscall */
-SYSCALL(sys_ni_syscall,compat_sys_s390_getresgid16)	/* old getresgid16 syscall */
-SYSCALL(sys_prctl,compat_sys_prctl)
-SYSCALL(sys_rt_sigreturn,compat_sys_rt_sigreturn)
-SYSCALL(sys_rt_sigaction,compat_sys_rt_sigaction)
-SYSCALL(sys_rt_sigprocmask,compat_sys_rt_sigprocmask)	/* 175 */
-SYSCALL(sys_rt_sigpending,compat_sys_rt_sigpending)
-SYSCALL(sys_rt_sigtimedwait,compat_sys_rt_sigtimedwait)
-SYSCALL(sys_rt_sigqueueinfo,compat_sys_rt_sigqueueinfo)
-SYSCALL(sys_rt_sigsuspend,compat_sys_rt_sigsuspend)
-SYSCALL(sys_pread64,compat_sys_s390_pread64)		/* 180 */
-SYSCALL(sys_pwrite64,compat_sys_s390_pwrite64)
-SYSCALL(sys_ni_syscall,compat_sys_s390_chown16)		/* old chown16 syscall */
-SYSCALL(sys_getcwd,compat_sys_getcwd)
-SYSCALL(sys_capget,compat_sys_capget)
-SYSCALL(sys_capset,compat_sys_capset)			/* 185 */
-SYSCALL(sys_sigaltstack,compat_sys_sigaltstack)
-SYSCALL(sys_sendfile64,compat_sys_sendfile)
-NI_SYSCALL						/* streams1 */
-NI_SYSCALL						/* streams2 */
-SYSCALL(sys_vfork,sys_vfork)				/* 190 */
-SYSCALL(sys_getrlimit,compat_sys_getrlimit)
-SYSCALL(sys_mmap2,compat_sys_s390_mmap2)
-SYSCALL(sys_ni_syscall,compat_sys_s390_truncate64)
-SYSCALL(sys_ni_syscall,compat_sys_s390_ftruncate64)
-SYSCALL(sys_ni_syscall,compat_sys_s390_stat64)		/* 195 */
-SYSCALL(sys_ni_syscall,compat_sys_s390_lstat64)
-SYSCALL(sys_ni_syscall,compat_sys_s390_fstat64)
-SYSCALL(sys_lchown,compat_sys_lchown)
-SYSCALL(sys_getuid,sys_getuid)
-SYSCALL(sys_getgid,sys_getgid)				/* 200 */
-SYSCALL(sys_geteuid,sys_geteuid)
-SYSCALL(sys_getegid,sys_getegid)
-SYSCALL(sys_setreuid,sys_setreuid)
-SYSCALL(sys_setregid,sys_setregid)
-SYSCALL(sys_getgroups,compat_sys_getgroups)		/* 205 */
-SYSCALL(sys_setgroups,compat_sys_setgroups)
-SYSCALL(sys_fchown,sys_fchown)
-SYSCALL(sys_setresuid,sys_setresuid)
-SYSCALL(sys_getresuid,compat_sys_getresuid)
-SYSCALL(sys_setresgid,sys_setresgid)			/* 210 */
-SYSCALL(sys_getresgid,compat_sys_getresgid)
-SYSCALL(sys_chown,compat_sys_chown)
-SYSCALL(sys_setuid,sys_setuid)
-SYSCALL(sys_setgid,sys_setgid)
-SYSCALL(sys_setfsuid,sys_setfsuid)			/* 215 */
-SYSCALL(sys_setfsgid,sys_setfsgid)
-SYSCALL(sys_pivot_root,compat_sys_pivot_root)
-SYSCALL(sys_mincore,compat_sys_mincore)
-SYSCALL(sys_madvise,compat_sys_madvise)
-SYSCALL(sys_getdents64,compat_sys_getdents64)		/* 220 */
-SYSCALL(sys_ni_syscall,compat_sys_fcntl64)
-SYSCALL(sys_readahead,compat_sys_s390_readahead)
-SYSCALL(sys_ni_syscall,compat_sys_sendfile64)
-SYSCALL(sys_setxattr,compat_sys_setxattr)
-SYSCALL(sys_lsetxattr,compat_sys_lsetxattr)		/* 225 */
-SYSCALL(sys_fsetxattr,compat_sys_fsetxattr)
-SYSCALL(sys_getxattr,compat_sys_getxattr)
-SYSCALL(sys_lgetxattr,compat_sys_lgetxattr)
-SYSCALL(sys_fgetxattr,compat_sys_fgetxattr)
-SYSCALL(sys_listxattr,compat_sys_listxattr)		/* 230 */
-SYSCALL(sys_llistxattr,compat_sys_llistxattr)
-SYSCALL(sys_flistxattr,compat_sys_flistxattr)
-SYSCALL(sys_removexattr,compat_sys_removexattr)
-SYSCALL(sys_lremovexattr,compat_sys_lremovexattr)
-SYSCALL(sys_fremovexattr,compat_sys_fremovexattr)	/* 235 */
-SYSCALL(sys_gettid,sys_gettid)
-SYSCALL(sys_tkill,sys_tkill)
-SYSCALL(sys_futex,compat_sys_futex)
-SYSCALL(sys_sched_setaffinity,compat_sys_sched_setaffinity)
-SYSCALL(sys_sched_getaffinity,compat_sys_sched_getaffinity)	/* 240 */
-SYSCALL(sys_tgkill,sys_tgkill)
-NI_SYSCALL						/* reserved for TUX */
-SYSCALL(sys_io_setup,compat_sys_io_setup)
-SYSCALL(sys_io_destroy,compat_sys_io_destroy)
-SYSCALL(sys_io_getevents,compat_sys_io_getevents)	/* 245 */
-SYSCALL(sys_io_submit,compat_sys_io_submit)
-SYSCALL(sys_io_cancel,compat_sys_io_cancel)
-SYSCALL(sys_exit_group,sys_exit_group)
-SYSCALL(sys_epoll_create,sys_epoll_create)
-SYSCALL(sys_epoll_ctl,compat_sys_epoll_ctl)		/* 250 */
-SYSCALL(sys_epoll_wait,compat_sys_epoll_wait)
-SYSCALL(sys_set_tid_address,compat_sys_set_tid_address)
-SYSCALL(sys_fadvise64_64,compat_sys_s390_fadvise64)
-SYSCALL(sys_timer_create,compat_sys_timer_create)
-SYSCALL(sys_timer_settime,compat_sys_timer_settime)	/* 255 */
-SYSCALL(sys_timer_gettime,compat_sys_timer_gettime)
-SYSCALL(sys_timer_getoverrun,sys_timer_getoverrun)
-SYSCALL(sys_timer_delete,sys_timer_delete)
-SYSCALL(sys_clock_settime,compat_sys_clock_settime)
-SYSCALL(sys_clock_gettime,compat_sys_clock_gettime)	/* 260 */
-SYSCALL(sys_clock_getres,compat_sys_clock_getres)
-SYSCALL(sys_clock_nanosleep,compat_sys_clock_nanosleep)
-NI_SYSCALL						/* reserved for vserver */
-SYSCALL(sys_ni_syscall,compat_sys_s390_fadvise64_64)
-SYSCALL(sys_statfs64,compat_sys_statfs64)
-SYSCALL(sys_fstatfs64,compat_sys_fstatfs64)
-SYSCALL(sys_remap_file_pages,compat_sys_remap_file_pages)
-SYSCALL(sys_mbind,compat_sys_mbind)
-SYSCALL(sys_get_mempolicy,compat_sys_get_mempolicy)
-SYSCALL(sys_set_mempolicy,compat_sys_set_mempolicy)
-SYSCALL(sys_mq_open,compat_sys_mq_open)
-SYSCALL(sys_mq_unlink,compat_sys_mq_unlink)
-SYSCALL(sys_mq_timedsend,compat_sys_mq_timedsend)
-SYSCALL(sys_mq_timedreceive,compat_sys_mq_timedreceive)
-SYSCALL(sys_mq_notify,compat_sys_mq_notify)		/* 275 */
-SYSCALL(sys_mq_getsetattr,compat_sys_mq_getsetattr)
-SYSCALL(sys_kexec_load,compat_sys_kexec_load)
-SYSCALL(sys_add_key,compat_sys_add_key)
-SYSCALL(sys_request_key,compat_sys_request_key)
-SYSCALL(sys_keyctl,compat_sys_keyctl)			/* 280 */
-SYSCALL(sys_waitid,compat_sys_waitid)
-SYSCALL(sys_ioprio_set,sys_ioprio_set)
-SYSCALL(sys_ioprio_get,sys_ioprio_get)
-SYSCALL(sys_inotify_init,sys_inotify_init)
-SYSCALL(sys_inotify_add_watch,compat_sys_inotify_add_watch)	/* 285 */
-SYSCALL(sys_inotify_rm_watch,sys_inotify_rm_watch)
-SYSCALL(sys_migrate_pages,compat_sys_migrate_pages)
-SYSCALL(sys_openat,compat_sys_openat)
-SYSCALL(sys_mkdirat,compat_sys_mkdirat)
-SYSCALL(sys_mknodat,compat_sys_mknodat)			/* 290 */
-SYSCALL(sys_fchownat,compat_sys_fchownat)
-SYSCALL(sys_futimesat,compat_sys_futimesat)
-SYSCALL(sys_newfstatat,compat_sys_s390_fstatat64)
-SYSCALL(sys_unlinkat,compat_sys_unlinkat)
-SYSCALL(sys_renameat,compat_sys_renameat)		/* 295 */
-SYSCALL(sys_linkat,compat_sys_linkat)
-SYSCALL(sys_symlinkat,compat_sys_symlinkat)
-SYSCALL(sys_readlinkat,compat_sys_readlinkat)
-SYSCALL(sys_fchmodat,compat_sys_fchmodat)
-SYSCALL(sys_faccessat,compat_sys_faccessat)		/* 300 */
-SYSCALL(sys_pselect6,compat_sys_pselect6)
-SYSCALL(sys_ppoll,compat_sys_ppoll)
-SYSCALL(sys_unshare,compat_sys_unshare)
-SYSCALL(sys_set_robust_list,compat_sys_set_robust_list)
-SYSCALL(sys_get_robust_list,compat_sys_get_robust_list)
-SYSCALL(sys_splice,compat_sys_splice)
-SYSCALL(sys_sync_file_range,compat_sys_s390_sync_file_range)
-SYSCALL(sys_tee,compat_sys_tee)
-SYSCALL(sys_vmsplice,compat_sys_vmsplice)
-SYSCALL(sys_move_pages,compat_sys_move_pages)
-SYSCALL(sys_getcpu,compat_sys_getcpu)
-SYSCALL(sys_epoll_pwait,compat_sys_epoll_pwait)
-SYSCALL(sys_utimes,compat_sys_utimes)
-SYSCALL(sys_fallocate,compat_sys_s390_fallocate)
-SYSCALL(sys_utimensat,compat_sys_utimensat)		/* 315 */
-SYSCALL(sys_signalfd,compat_sys_signalfd)
-NI_SYSCALL						/* 317 old sys_timer_fd */
-SYSCALL(sys_eventfd,sys_eventfd)
-SYSCALL(sys_timerfd_create,sys_timerfd_create)
-SYSCALL(sys_timerfd_settime,compat_sys_timerfd_settime) /* 320 */
-SYSCALL(sys_timerfd_gettime,compat_sys_timerfd_gettime)
-SYSCALL(sys_signalfd4,compat_sys_signalfd4)
-SYSCALL(sys_eventfd2,sys_eventfd2)
-SYSCALL(sys_inotify_init1,sys_inotify_init1)
-SYSCALL(sys_pipe2,compat_sys_pipe2)			/* 325 */
-SYSCALL(sys_dup3,sys_dup3)
-SYSCALL(sys_epoll_create1,sys_epoll_create1)
-SYSCALL(sys_preadv,compat_sys_preadv)
-SYSCALL(sys_pwritev,compat_sys_pwritev)
-SYSCALL(sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo) /* 330 */
-SYSCALL(sys_perf_event_open,compat_sys_perf_event_open)
-SYSCALL(sys_fanotify_init,sys_fanotify_init)
-SYSCALL(sys_fanotify_mark,compat_sys_fanotify_mark)
-SYSCALL(sys_prlimit64,compat_sys_prlimit64)
-SYSCALL(sys_name_to_handle_at,compat_sys_name_to_handle_at) /* 335 */
-SYSCALL(sys_open_by_handle_at,compat_sys_open_by_handle_at)
-SYSCALL(sys_clock_adjtime,compat_sys_clock_adjtime)
-SYSCALL(sys_syncfs,sys_syncfs)
-SYSCALL(sys_setns,sys_setns)
-SYSCALL(sys_process_vm_readv,compat_sys_process_vm_readv) /* 340 */
-SYSCALL(sys_process_vm_writev,compat_sys_process_vm_writev)
-SYSCALL(sys_s390_runtime_instr,sys_s390_runtime_instr)
-SYSCALL(sys_kcmp,compat_sys_kcmp)
-SYSCALL(sys_finit_module,compat_sys_finit_module)
-SYSCALL(sys_sched_setattr,compat_sys_sched_setattr)	/* 345 */
-SYSCALL(sys_sched_getattr,compat_sys_sched_getattr)
-SYSCALL(sys_renameat2,compat_sys_renameat2)
-SYSCALL(sys_seccomp,compat_sys_seccomp)
-SYSCALL(sys_getrandom,compat_sys_getrandom)
-SYSCALL(sys_memfd_create,compat_sys_memfd_create)	/* 350 */
-SYSCALL(sys_bpf,compat_sys_bpf)
-SYSCALL(sys_s390_pci_mmio_write,compat_sys_s390_pci_mmio_write)
-SYSCALL(sys_s390_pci_mmio_read,compat_sys_s390_pci_mmio_read)
-SYSCALL(sys_execveat,compat_sys_execveat)
-SYSCALL(sys_userfaultfd,sys_userfaultfd)		/* 355 */
-SYSCALL(sys_membarrier,sys_membarrier)
-SYSCALL(sys_recvmmsg,compat_sys_recvmmsg)
-SYSCALL(sys_sendmmsg,compat_sys_sendmmsg)
-SYSCALL(sys_socket,sys_socket)
-SYSCALL(sys_socketpair,compat_sys_socketpair)		/* 360 */
-SYSCALL(sys_bind,sys_bind)
-SYSCALL(sys_connect,sys_connect)
-SYSCALL(sys_listen,sys_listen)
-SYSCALL(sys_accept4,sys_accept4)
-SYSCALL(sys_getsockopt,compat_sys_getsockopt)		/* 365 */
-SYSCALL(sys_setsockopt,compat_sys_setsockopt)
-SYSCALL(sys_getsockname,compat_sys_getsockname)
-SYSCALL(sys_getpeername,compat_sys_getpeername)
-SYSCALL(sys_sendto,compat_sys_sendto)
-SYSCALL(sys_sendmsg,compat_sys_sendmsg)			/* 370 */
-SYSCALL(sys_recvfrom,compat_sys_recvfrom)
-SYSCALL(sys_recvmsg,compat_sys_recvmsg)
-SYSCALL(sys_shutdown,sys_shutdown)
-SYSCALL(sys_mlock2,compat_sys_mlock2)
-SYSCALL(sys_copy_file_range,compat_sys_copy_file_range) /* 375 */
-SYSCALL(sys_preadv2,compat_sys_preadv2)
-SYSCALL(sys_pwritev2,compat_sys_pwritev2)
-SYSCALL(sys_s390_guarded_storage,compat_sys_s390_guarded_storage) /* 378 */
-SYSCALL(sys_statx,compat_sys_statx)
-SYSCALL(sys_s390_sthyi,compat_sys_s390_sthyi)
diff --git a/arch/s390/kernel/syscalls/Makefile b/arch/s390/kernel/syscalls/Makefile
new file mode 100644
index 000000000000..8ff96c08955f
--- /dev/null
+++ b/arch/s390/kernel/syscalls/Makefile
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0
+
+gen	:= arch/$(ARCH)/include/generated
+kapi	:= $(gen)/asm
+uapi	:= $(gen)/uapi/asm
+
+syscall	:= $(srctree)/$(src)/syscall.tbl
+systbl	:= $(srctree)/$(src)/syscalltbl
+
+gen-y := $(kapi)/syscall_table.h
+kapi-hdrs-y := $(kapi)/unistd_nr.h
+uapi-hdrs-y := $(uapi)/unistd_32.h
+uapi-hdrs-y += $(uapi)/unistd_64.h
+
+targets += $(addprefix ../../../,$(gen-y) $(kapi-hdrs-y) $(uapi-hdrs-y))
+
+PHONY += kapi uapi
+
+kapi:	$(gen-y) $(kapi-hdrs-y)
+uapi:	$(uapi-hdrs-y)
+
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \
+	  $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)')
+
+define filechk_syshdr
+	$(CONFIG_SHELL) '$(systbl)' -H -a $(syshdr_abi_$(basetarget)) -f "$2"
+endef
+
+define filechk_sysnr
+	$(CONFIG_SHELL) '$(systbl)' -N -a $(sysnr_abi_$(basetarget))
+endef
+
+define filechk_syscalls
+	$(CONFIG_SHELL) '$(systbl)' -S
+endef
+
+syshdr_abi_unistd_32 := common,32
+$(uapi)/unistd_32.h: $(syscall) FORCE
+	$(call filechk,syshdr,$@)
+
+syshdr_abi_unistd_64 := common,64
+$(uapi)/unistd_64.h: $(syscall) FORCE
+	$(call filechk,syshdr,$@)
+
+$(kapi)/syscall_table.h: $(syscall) FORCE
+	$(call filechk,syscalls)
+
+sysnr_abi_unistd_nr := common,32,64
+$(kapi)/unistd_nr.h: $(syscall) FORCE
+	$(call filechk,sysnr)
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
new file mode 100644
index 000000000000..b38d48464368
--- /dev/null
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -0,0 +1,390 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+#
+# System call table for s390
+#
+# Format:
+#
+# <nr> <abi> <syscall> <entry-64bit> <compat-entry>
+#
+# where <abi> can be common, 64, or 32
+
+1    common	exit			sys_exit			sys_exit
+2    common	fork			sys_fork			sys_fork
+3    common	read			sys_read			compat_sys_s390_read
+4    common	write			sys_write			compat_sys_s390_write
+5    common	open			sys_open			compat_sys_open
+6    common	close			sys_close			sys_close
+7    common	restart_syscall		sys_restart_syscall		sys_restart_syscall
+8    common	creat			sys_creat			compat_sys_creat
+9    common	link			sys_link			compat_sys_link
+10   common	unlink			sys_unlink			compat_sys_unlink
+11   common	execve			sys_execve			compat_sys_execve
+12   common	chdir			sys_chdir			compat_sys_chdir
+13   32		time			-				compat_sys_time
+14   common	mknod			sys_mknod			compat_sys_mknod
+15   common	chmod			sys_chmod			compat_sys_chmod
+16   32		lchown			-				compat_sys_s390_lchown16
+19   common	lseek			sys_lseek			compat_sys_lseek
+20   common	getpid			sys_getpid			sys_getpid
+21   common	mount			sys_mount			compat_sys_mount
+22   common	umount			sys_oldumount			compat_sys_oldumount
+23   32		setuid			-				compat_sys_s390_setuid16
+24   32		getuid			-				compat_sys_s390_getuid16
+25   32		stime			-				compat_sys_stime
+26   common	ptrace			sys_ptrace			compat_sys_ptrace
+27   common	alarm			sys_alarm			sys_alarm
+29   common	pause			sys_pause			sys_pause
+30   common	utime			sys_utime			compat_sys_utime
+33   common	access			sys_access			compat_sys_access
+34   common	nice			sys_nice			sys_nice
+36   common	sync			sys_sync			sys_sync
+37   common	kill			sys_kill			sys_kill
+38   common	rename			sys_rename			compat_sys_rename
+39   common	mkdir			sys_mkdir			compat_sys_mkdir
+40   common	rmdir			sys_rmdir			compat_sys_rmdir
+41   common	dup			sys_dup				sys_dup
+42   common	pipe			sys_pipe			compat_sys_pipe
+43   common	times			sys_times			compat_sys_times
+45   common	brk			sys_brk				compat_sys_brk
+46   32		setgid			-				compat_sys_s390_setgid16
+47   32		getgid			-				compat_sys_s390_getgid16
+48   common	signal			sys_signal			compat_sys_signal
+49   32		geteuid			-				compat_sys_s390_geteuid16
+50   32		getegid			-				compat_sys_s390_getegid16
+51   common	acct			sys_acct			compat_sys_acct
+52   common	umount2			sys_umount			compat_sys_umount
+54   common	ioctl			sys_ioctl			compat_sys_ioctl
+55   common	fcntl			sys_fcntl			compat_sys_fcntl
+57   common	setpgid			sys_setpgid			sys_setpgid
+60   common	umask			sys_umask			sys_umask
+61   common	chroot			sys_chroot			compat_sys_chroot
+62   common	ustat			sys_ustat			compat_sys_ustat
+63   common	dup2			sys_dup2			sys_dup2
+64   common	getppid			sys_getppid			sys_getppid
+65   common	getpgrp			sys_getpgrp			sys_getpgrp
+66   common	setsid			sys_setsid			sys_setsid
+67   common	sigaction		sys_sigaction			compat_sys_sigaction
+70   32		setreuid		-				compat_sys_s390_setreuid16
+71   32		setregid		-				compat_sys_s390_setregid16
+72   common	sigsuspend		sys_sigsuspend			compat_sys_sigsuspend
+73   common	sigpending		sys_sigpending			compat_sys_sigpending
+74   common	sethostname		sys_sethostname			compat_sys_sethostname
+75   common	setrlimit		sys_setrlimit			compat_sys_setrlimit
+76   32		getrlimit		-				compat_sys_old_getrlimit
+77   common	getrusage		sys_getrusage			compat_sys_getrusage
+78   common	gettimeofday		sys_gettimeofday		compat_sys_gettimeofday
+79   common	settimeofday		sys_settimeofday		compat_sys_settimeofday
+80   32		getgroups		-				compat_sys_s390_getgroups16
+81   32		setgroups		-				compat_sys_s390_setgroups16
+83   common	symlink			sys_symlink			compat_sys_symlink
+85   common	readlink		sys_readlink			compat_sys_readlink
+86   common	uselib			sys_uselib			compat_sys_uselib
+87   common	swapon			sys_swapon			compat_sys_swapon
+88   common	reboot			sys_reboot			compat_sys_reboot
+89   common	readdir			-				compat_sys_old_readdir
+90   common	mmap			sys_old_mmap			compat_sys_s390_old_mmap
+91   common	munmap			sys_munmap			compat_sys_munmap
+92   common	truncate		sys_truncate			compat_sys_truncate
+93   common	ftruncate		sys_ftruncate			compat_sys_ftruncate
+94   common	fchmod			sys_fchmod			sys_fchmod
+95   32		fchown			-				compat_sys_s390_fchown16
+96   common	getpriority		sys_getpriority			sys_getpriority
+97   common	setpriority		sys_setpriority			sys_setpriority
+99   common	statfs			sys_statfs			compat_sys_statfs
+100  common	fstatfs			sys_fstatfs			compat_sys_fstatfs
+101  32		ioperm			-				-
+102  common	socketcall		sys_socketcall			compat_sys_socketcall
+103  common	syslog			sys_syslog			compat_sys_syslog
+104  common	setitimer		sys_setitimer			compat_sys_setitimer
+105  common	getitimer		sys_getitimer			compat_sys_getitimer
+106  common	stat			sys_newstat			compat_sys_newstat
+107  common	lstat			sys_newlstat			compat_sys_newlstat
+108  common	fstat			sys_newfstat			compat_sys_newfstat
+110  common	lookup_dcookie		sys_lookup_dcookie		compat_sys_lookup_dcookie
+111  common	vhangup			sys_vhangup			sys_vhangup
+112  common	idle			-				-
+114  common	wait4			sys_wait4			compat_sys_wait4
+115  common	swapoff			sys_swapoff			compat_sys_swapoff
+116  common	sysinfo			sys_sysinfo			compat_sys_sysinfo
+117  common	ipc			sys_s390_ipc			compat_sys_s390_ipc
+118  common	fsync			sys_fsync			sys_fsync
+119  common	sigreturn		sys_sigreturn			compat_sys_sigreturn
+120  common	clone			sys_clone			compat_sys_clone
+121  common	setdomainname		sys_setdomainname		compat_sys_setdomainname
+122  common	uname			sys_newuname			compat_sys_newuname
+124  common	adjtimex		sys_adjtimex			compat_sys_adjtimex
+125  common	mprotect		sys_mprotect			compat_sys_mprotect
+126  common	sigprocmask		sys_sigprocmask			compat_sys_sigprocmask
+127  common	create_module		-				-
+128  common	init_module		sys_init_module			compat_sys_init_module
+129  common	delete_module		sys_delete_module		compat_sys_delete_module
+130  common	get_kernel_syms		-				-
+131  common	quotactl		sys_quotactl			compat_sys_quotactl
+132  common	getpgid			sys_getpgid			sys_getpgid
+133  common	fchdir			sys_fchdir			sys_fchdir
+134  common	bdflush			sys_bdflush			compat_sys_bdflush
+135  common	sysfs			sys_sysfs			compat_sys_sysfs
+136  common	personality		sys_s390_personality		sys_s390_personality
+137  common	afs_syscall		-				-
+138  32		setfsuid		-				compat_sys_s390_setfsuid16
+139  32		setfsgid		-				compat_sys_s390_setfsgid16
+140  32		_llseek			-				compat_sys_llseek
+141  common	getdents		sys_getdents			compat_sys_getdents
+142  32		_newselect		-				compat_sys_select
+142  64		select			sys_select			-
+143  common	flock			sys_flock			sys_flock
+144  common	msync			sys_msync			compat_sys_msync
+145  common	readv			sys_readv			compat_sys_readv
+146  common	writev			sys_writev			compat_sys_writev
+147  common	getsid			sys_getsid			sys_getsid
+148  common	fdatasync		sys_fdatasync			sys_fdatasync
+149  common	_sysctl			sys_sysctl			compat_sys_sysctl
+150  common	mlock			sys_mlock			compat_sys_mlock
+151  common	munlock			sys_munlock			compat_sys_munlock
+152  common	mlockall		sys_mlockall			sys_mlockall
+153  common	munlockall		sys_munlockall			sys_munlockall
+154  common	sched_setparam		sys_sched_setparam		compat_sys_sched_setparam
+155  common	sched_getparam		sys_sched_getparam		compat_sys_sched_getparam
+156  common	sched_setscheduler	sys_sched_setscheduler		compat_sys_sched_setscheduler
+157  common	sched_getscheduler	sys_sched_getscheduler		sys_sched_getscheduler
+158  common	sched_yield		sys_sched_yield			sys_sched_yield
+159  common	sched_get_priority_max	sys_sched_get_priority_max	sys_sched_get_priority_max
+160  common	sched_get_priority_min	sys_sched_get_priority_min	sys_sched_get_priority_min
+161  common	sched_rr_get_interval	sys_sched_rr_get_interval	compat_sys_sched_rr_get_interval
+162  common	nanosleep		sys_nanosleep			compat_sys_nanosleep
+163  common	mremap			sys_mremap			compat_sys_mremap
+164  32		setresuid		-				compat_sys_s390_setresuid16
+165  32		getresuid		-				compat_sys_s390_getresuid16
+167  common	query_module		-				-
+168  common	poll			sys_poll			compat_sys_poll
+169  common	nfsservctl		-				-
+170  32		setresgid		-				compat_sys_s390_setresgid16
+171  32		getresgid		-				compat_sys_s390_getresgid16
+172  common	prctl			sys_prctl			compat_sys_prctl
+173  common	rt_sigreturn		sys_rt_sigreturn		compat_sys_rt_sigreturn
+174  common	rt_sigaction		sys_rt_sigaction		compat_sys_rt_sigaction
+175  common	rt_sigprocmask		sys_rt_sigprocmask		compat_sys_rt_sigprocmask
+176  common	rt_sigpending		sys_rt_sigpending		compat_sys_rt_sigpending
+177  common	rt_sigtimedwait		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait
+178  common	rt_sigqueueinfo		sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
+179  common	rt_sigsuspend		sys_rt_sigsuspend		compat_sys_rt_sigsuspend
+180  common	pread64			sys_pread64			compat_sys_s390_pread64
+181  common	pwrite64		sys_pwrite64			compat_sys_s390_pwrite64
+182  32		chown			-				compat_sys_s390_chown16
+183  common	getcwd			sys_getcwd			compat_sys_getcwd
+184  common	capget			sys_capget			compat_sys_capget
+185  common	capset			sys_capset			compat_sys_capset
+186  common	sigaltstack		sys_sigaltstack			compat_sys_sigaltstack
+187  common	sendfile		sys_sendfile64			compat_sys_sendfile
+188  common	getpmsg			-				-
+189  common	putpmsg			-				-
+190  common	vfork			sys_vfork			sys_vfork
+191  32		ugetrlimit		-				compat_sys_getrlimit
+191  64		getrlimit		sys_getrlimit			-
+192  32		mmap2			-				compat_sys_s390_mmap2
+193  32		truncate64		-				compat_sys_s390_truncate64
+194  32		ftruncate64		-				compat_sys_s390_ftruncate64
+195  32		stat64			-				compat_sys_s390_stat64
+196  32		lstat64			-				compat_sys_s390_lstat64
+197  32		fstat64			-				compat_sys_s390_fstat64
+198  32		lchown32		-				compat_sys_lchown
+198  64		lchown			sys_lchown			-
+199  32		getuid32		-				sys_getuid
+199  64		getuid			sys_getuid			-
+200  32		getgid32		-				sys_getgid
+200  64		getgid			sys_getgid			-
+201  32		geteuid32		-				sys_geteuid
+201  64		geteuid			sys_geteuid			-
+202  32		getegid32		-				sys_getegid
+202  64		getegid			sys_getegid			-
+203  32		setreuid32		-				sys_setreuid
+203  64		setreuid		sys_setreuid			-
+204  32		setregid32		-				sys_setregid
+204  64		setregid		sys_setregid			-
+205  32		getgroups32		-				compat_sys_getgroups
+205  64		getgroups		sys_getgroups			-
+206  32		setgroups32		-				compat_sys_setgroups
+206  64		setgroups		sys_setgroups			-
+207  32		fchown32		-				sys_fchown
+207  64		fchown			sys_fchown			-
+208  32		setresuid32		-				sys_setresuid
+208  64		setresuid		sys_setresuid			-
+209  32		getresuid32		-				compat_sys_getresuid
+209  64		getresuid		sys_getresuid			-
+210  32		setresgid32		-				sys_setresgid
+210  64		setresgid		sys_setresgid			-
+211  32		getresgid32		-				compat_sys_getresgid
+211  64		getresgid		sys_getresgid			-
+212  32		chown32			-				compat_sys_chown
+212  64		chown			sys_chown			-
+213  32		setuid32		-				sys_setuid
+213  64		setuid			sys_setuid			-
+214  32		setgid32		-				sys_setgid
+214  64		setgid			sys_setgid			-
+215  32		setfsuid32		-				sys_setfsuid
+215  64		setfsuid		sys_setfsuid			-
+216  32		setfsgid32		-				sys_setfsgid
+216  64		setfsgid		sys_setfsgid			-
+217  common	pivot_root		sys_pivot_root			compat_sys_pivot_root
+218  common	mincore			sys_mincore			compat_sys_mincore
+219  common	madvise			sys_madvise			compat_sys_madvise
+220  common	getdents64		sys_getdents64			compat_sys_getdents64
+221  32		fcntl64			-				compat_sys_fcntl64
+222  common	readahead		sys_readahead			compat_sys_s390_readahead
+223  32		sendfile64		-				compat_sys_sendfile64
+224  common	setxattr		sys_setxattr			compat_sys_setxattr
+225  common	lsetxattr		sys_lsetxattr			compat_sys_lsetxattr
+226  common	fsetxattr		sys_fsetxattr			compat_sys_fsetxattr
+227  common	getxattr		sys_getxattr			compat_sys_getxattr
+228  common	lgetxattr		sys_lgetxattr			compat_sys_lgetxattr
+229  common	fgetxattr		sys_fgetxattr			compat_sys_fgetxattr
+230  common	listxattr		sys_listxattr			compat_sys_listxattr
+231  common	llistxattr		sys_llistxattr			compat_sys_llistxattr
+232  common	flistxattr		sys_flistxattr			compat_sys_flistxattr
+233  common	removexattr		sys_removexattr			compat_sys_removexattr
+234  common	lremovexattr		sys_lremovexattr		compat_sys_lremovexattr
+235  common	fremovexattr		sys_fremovexattr		compat_sys_fremovexattr
+236  common	gettid			sys_gettid			sys_gettid
+237  common	tkill			sys_tkill			sys_tkill
+238  common	futex			sys_futex			compat_sys_futex
+239  common	sched_setaffinity	sys_sched_setaffinity		compat_sys_sched_setaffinity
+240  common	sched_getaffinity	sys_sched_getaffinity		compat_sys_sched_getaffinity
+241  common	tgkill			sys_tgkill			sys_tgkill
+243  common	io_setup		sys_io_setup			compat_sys_io_setup
+244  common	io_destroy		sys_io_destroy			compat_sys_io_destroy
+245  common	io_getevents		sys_io_getevents		compat_sys_io_getevents
+246  common	io_submit		sys_io_submit			compat_sys_io_submit
+247  common	io_cancel		sys_io_cancel			compat_sys_io_cancel
+248  common	exit_group		sys_exit_group			sys_exit_group
+249  common	epoll_create		sys_epoll_create		sys_epoll_create
+250  common	epoll_ctl		sys_epoll_ctl			compat_sys_epoll_ctl
+251  common	epoll_wait		sys_epoll_wait			compat_sys_epoll_wait
+252  common	set_tid_address		sys_set_tid_address		compat_sys_set_tid_address
+253  common	fadvise64		sys_fadvise64_64		compat_sys_s390_fadvise64
+254  common	timer_create		sys_timer_create		compat_sys_timer_create
+255  common	timer_settime		sys_timer_settime		compat_sys_timer_settime
+256  common	timer_gettime		sys_timer_gettime		compat_sys_timer_gettime
+257  common	timer_getoverrun	sys_timer_getoverrun		sys_timer_getoverrun
+258  common	timer_delete		sys_timer_delete		sys_timer_delete
+259  common	clock_settime		sys_clock_settime		compat_sys_clock_settime
+260  common	clock_gettime		sys_clock_gettime		compat_sys_clock_gettime
+261  common	clock_getres		sys_clock_getres		compat_sys_clock_getres
+262  common	clock_nanosleep		sys_clock_nanosleep		compat_sys_clock_nanosleep
+264  32		fadvise64_64		-				compat_sys_s390_fadvise64_64
+265  common	statfs64		sys_statfs64			compat_sys_statfs64
+266  common	fstatfs64		sys_fstatfs64			compat_sys_fstatfs64
+267  common	remap_file_pages	sys_remap_file_pages		compat_sys_remap_file_pages
+268  common	mbind			sys_mbind			compat_sys_mbind
+269  common	get_mempolicy		sys_get_mempolicy		compat_sys_get_mempolicy
+270  common	set_mempolicy		sys_set_mempolicy		compat_sys_set_mempolicy
+271  common	mq_open			sys_mq_open			compat_sys_mq_open
+272  common	mq_unlink		sys_mq_unlink			compat_sys_mq_unlink
+273  common	mq_timedsend		sys_mq_timedsend		compat_sys_mq_timedsend
+274  common	mq_timedreceive		sys_mq_timedreceive		compat_sys_mq_timedreceive
+275  common	mq_notify		sys_mq_notify			compat_sys_mq_notify
+276  common	mq_getsetattr		sys_mq_getsetattr		compat_sys_mq_getsetattr
+277  common	kexec_load		sys_kexec_load			compat_sys_kexec_load
+278  common	add_key			sys_add_key			compat_sys_add_key
+279  common	request_key		sys_request_key			compat_sys_request_key
+280  common	keyctl			sys_keyctl			compat_sys_keyctl
+281  common	waitid			sys_waitid			compat_sys_waitid
+282  common	ioprio_set		sys_ioprio_set			sys_ioprio_set
+283  common	ioprio_get		sys_ioprio_get			sys_ioprio_get
+284  common	inotify_init		sys_inotify_init		sys_inotify_init
+285  common	inotify_add_watch	sys_inotify_add_watch		compat_sys_inotify_add_watch
+286  common	inotify_rm_watch	sys_inotify_rm_watch		sys_inotify_rm_watch
+287  common	migrate_pages		sys_migrate_pages		compat_sys_migrate_pages
+288  common	openat			sys_openat			compat_sys_openat
+289  common	mkdirat			sys_mkdirat			compat_sys_mkdirat
+290  common	mknodat			sys_mknodat			compat_sys_mknodat
+291  common	fchownat		sys_fchownat			compat_sys_fchownat
+292  common	futimesat		sys_futimesat			compat_sys_futimesat
+293  32		fstatat64		-				compat_sys_s390_fstatat64
+293  64		newfstatat		sys_newfstatat			-
+294  common	unlinkat		sys_unlinkat			compat_sys_unlinkat
+295  common	renameat		sys_renameat			compat_sys_renameat
+296  common	linkat			sys_linkat			compat_sys_linkat
+297  common	symlinkat		sys_symlinkat			compat_sys_symlinkat
+298  common	readlinkat		sys_readlinkat			compat_sys_readlinkat
+299  common	fchmodat		sys_fchmodat			compat_sys_fchmodat
+300  common	faccessat		sys_faccessat			compat_sys_faccessat
+301  common	pselect6		sys_pselect6			compat_sys_pselect6
+302  common	ppoll			sys_ppoll			compat_sys_ppoll
+303  common	unshare			sys_unshare			compat_sys_unshare
+304  common	set_robust_list		sys_set_robust_list		compat_sys_set_robust_list
+305  common	get_robust_list		sys_get_robust_list		compat_sys_get_robust_list
+306  common	splice			sys_splice			compat_sys_splice
+307  common	sync_file_range		sys_sync_file_range		compat_sys_s390_sync_file_range
+308  common	tee			sys_tee				compat_sys_tee
+309  common	vmsplice		sys_vmsplice			compat_sys_vmsplice
+310  common	move_pages		sys_move_pages			compat_sys_move_pages
+311  common	getcpu			sys_getcpu			compat_sys_getcpu
+312  common	epoll_pwait		sys_epoll_pwait			compat_sys_epoll_pwait
+313  common	utimes			sys_utimes			compat_sys_utimes
+314  common	fallocate		sys_fallocate			compat_sys_s390_fallocate
+315  common	utimensat		sys_utimensat			compat_sys_utimensat
+316  common	signalfd		sys_signalfd			compat_sys_signalfd
+317  common	timerfd			-				-
+318  common	eventfd			sys_eventfd			sys_eventfd
+319  common	timerfd_create		sys_timerfd_create		sys_timerfd_create
+320  common	timerfd_settime		sys_timerfd_settime		compat_sys_timerfd_settime
+321  common	timerfd_gettime		sys_timerfd_gettime		compat_sys_timerfd_gettime
+322  common	signalfd4		sys_signalfd4			compat_sys_signalfd4
+323  common	eventfd2		sys_eventfd2			sys_eventfd2
+324  common	inotify_init1		sys_inotify_init1		sys_inotify_init1
+325  common	pipe2			sys_pipe2			compat_sys_pipe2
+326  common	dup3			sys_dup3			sys_dup3
+327  common	epoll_create1		sys_epoll_create1		sys_epoll_create1
+328  common	preadv			sys_preadv			compat_sys_preadv
+329  common	pwritev			sys_pwritev			compat_sys_pwritev
+330  common	rt_tgsigqueueinfo	sys_rt_tgsigqueueinfo		compat_sys_rt_tgsigqueueinfo
+331  common	perf_event_open		sys_perf_event_open		compat_sys_perf_event_open
+332  common	fanotify_init		sys_fanotify_init		sys_fanotify_init
+333  common	fanotify_mark		sys_fanotify_mark		compat_sys_fanotify_mark
+334  common	prlimit64		sys_prlimit64			compat_sys_prlimit64
+335  common	name_to_handle_at	sys_name_to_handle_at		compat_sys_name_to_handle_at
+336  common	open_by_handle_at	sys_open_by_handle_at		compat_sys_open_by_handle_at
+337  common	clock_adjtime		sys_clock_adjtime		compat_sys_clock_adjtime
+338  common	syncfs			sys_syncfs			sys_syncfs
+339  common	setns			sys_setns			sys_setns
+340  common	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
+341  common	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+342  common	s390_runtime_instr	sys_s390_runtime_instr		sys_s390_runtime_instr
+343  common	kcmp			sys_kcmp			compat_sys_kcmp
+344  common	finit_module		sys_finit_module		compat_sys_finit_module
+345  common	sched_setattr		sys_sched_setattr		compat_sys_sched_setattr
+346  common	sched_getattr		sys_sched_getattr		compat_sys_sched_getattr
+347  common	renameat2		sys_renameat2			compat_sys_renameat2
+348  common	seccomp			sys_seccomp			compat_sys_seccomp
+349  common	getrandom		sys_getrandom			compat_sys_getrandom
+350  common	memfd_create		sys_memfd_create		compat_sys_memfd_create
+351  common	bpf			sys_bpf				compat_sys_bpf
+352  common	s390_pci_mmio_write	sys_s390_pci_mmio_write		compat_sys_s390_pci_mmio_write
+353  common	s390_pci_mmio_read	sys_s390_pci_mmio_read		compat_sys_s390_pci_mmio_read
+354  common	execveat		sys_execveat			compat_sys_execveat
+355  common	userfaultfd		sys_userfaultfd			sys_userfaultfd
+356  common	membarrier		sys_membarrier			sys_membarrier
+357  common	recvmmsg		sys_recvmmsg			compat_sys_recvmmsg
+358  common	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
+359  common	socket			sys_socket			sys_socket
+360  common	socketpair		sys_socketpair			compat_sys_socketpair
+361  common	bind			sys_bind			compat_sys_bind
+362  common	connect			sys_connect			compat_sys_connect
+363  common	listen			sys_listen			sys_listen
+364  common	accept4			sys_accept4			compat_sys_accept4
+365  common	getsockopt		sys_getsockopt			compat_sys_getsockopt
+366  common	setsockopt		sys_setsockopt			compat_sys_setsockopt
+367  common	getsockname		sys_getsockname			compat_sys_getsockname
+368  common	getpeername		sys_getpeername			compat_sys_getpeername
+369  common	sendto			sys_sendto			compat_sys_sendto
+370  common	sendmsg			sys_sendmsg			compat_sys_sendmsg
+371  common	recvfrom		sys_recvfrom			compat_sys_recvfrom
+372  common	recvmsg			sys_recvmsg			compat_sys_recvmsg
+373  common	shutdown		sys_shutdown			sys_shutdown
+374  common	mlock2			sys_mlock2			compat_sys_mlock2
+375  common	copy_file_range		sys_copy_file_range		compat_sys_copy_file_range
+376  common	preadv2			sys_preadv2			compat_sys_preadv2
+377  common	pwritev2		sys_pwritev2			compat_sys_pwritev2
+378  common	s390_guarded_storage	sys_s390_guarded_storage	compat_sys_s390_guarded_storage
+379  common	statx			sys_statx			compat_sys_statx
+380  common	s390_sthyi		sys_s390_sthyi			compat_sys_s390_sthyi
diff --git a/arch/s390/kernel/syscalls/syscalltbl b/arch/s390/kernel/syscalls/syscalltbl
new file mode 100755
index 000000000000..fbac1732f874
--- /dev/null
+++ b/arch/s390/kernel/syscalls/syscalltbl
@@ -0,0 +1,232 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table and header files
+#
+# Copyright IBM Corp. 2018
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+
+#
+# File path to the system call table definition.
+# You can set the path with the -i option.  If omitted,
+# system call table definitions are read from standard input.
+#
+SYSCALL_TBL=""
+
+
+create_syscall_table_entries()
+{
+	local nr abi name entry64 entry32 _ignore
+	local temp=$(mktemp ${TMPDIR:-/tmp}/syscalltbl-common.XXXXXXXXX)
+
+	(
+	#
+	# Initialize with 0 to create an NI_SYSCALL for 0
+	#
+	local prev_nr=0 prev_32=sys_ni_syscall prev_64=sys_ni_syscall
+	while read nr abi name entry64 entry32 _ignore; do
+		test x$entry32 = x- && entry32=sys_ni_syscall
+		test x$entry64 = x- && entry64=sys_ni_syscall
+
+		if test $prev_nr -eq $nr; then
+			#
+			# Same syscall but different ABI, just update
+			# the respective entry point
+			#
+			case $abi in
+			32)
+				prev_32=$entry32
+			;;
+			64)
+				prev_64=$entry64
+			;;
+			esac
+			continue;
+		else
+			printf "%d\t%s\t%s\n" $prev_nr $prev_64 $prev_32
+		fi
+
+		prev_nr=$nr
+		prev_64=$entry64
+		prev_32=$entry32
+	done
+	printf "%d\t%s\t%s\n" $prev_nr $prev_64 $prev_32
+	) >> $temp
+
+	#
+	# Check for duplicate syscall numbers
+	#
+	if ! cat $temp |cut -f1 |uniq -d 2>&1; then
+		echo "Error: generated system call table contains duplicate entries: $temp" >&2
+		exit 1
+	fi
+
+	#
+	# Generate syscall table
+	#
+	prev_nr=0
+	while read nr entry64 entry32; do
+		while test $prev_nr -lt $((nr - 1)); do
+			printf "NI_SYSCALL\n"
+			prev_nr=$((prev_nr + 1))
+		done
+		if test x$entry64 = xsys_ni_syscall &&
+		   test x$entry32 = xsys_ni_syscall; then
+			printf "NI_SYSCALL\n"
+		else
+			printf "SYSCALL(%s,%s)\n" $entry64 $entry32
+		fi
+		prev_nr=$nr
+	done < $temp
+	rm $temp
+}
+
+generate_syscall_table()
+{
+	cat <<-EoHEADER
+	/* SPDX-License-Identifier: GPL-2.0 */
+	/*
+	 * Definitions for sys_call_table, each line represents an
+	 * entry in the table in the form
+	 * SYSCALL(64 bit syscall, 31 bit emulated syscall)
+	 *
+	 * This file is meant to be included from entry.S.
+	 */
+
+	#define NI_SYSCALL SYSCALL(sys_ni_syscall,sys_ni_syscall)
+
+EoHEADER
+	grep -Ev '^(#|[[:blank:]]*$)' $SYSCALL_TBL	\
+		|sort -k1 -n				\
+		|create_syscall_table_entries
+}
+
+create_header_defines()
+{
+	local nr abi name _ignore
+
+	while read nr abi name _ignore; do
+		printf "#define __NR_%s %d\n" $name $nr
+	done
+}
+
+normalize_fileguard()
+{
+	local fileguard="$1"
+
+	echo "$1" |tr '[[:lower:]]' '[[:upper:]]' \
+		  |sed -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'
+}
+
+generate_syscall_header()
+{
+	local abis=$(echo "($1)" | tr ',' '|')
+	local filename="$2"
+	local fileguard suffix
+
+	if test "$filename"; then
+		fileguard=$(normalize_fileguard "__UAPI_ASM_S390_$2")
+	else
+		case "$abis" in
+		*64*) suffix=64 ;;
+		*32*) suffix=32 ;;
+		esac
+		fileguard=$(normalize_fileguard "__UAPI_ASM_S390_SYSCALLS_$suffix")
+	fi
+
+	cat <<-EoHEADER
+	/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+	#ifndef ${fileguard}
+	#define ${fileguard}
+
+EoHEADER
+
+	grep -E "^[[:digit:]]+[[:space:]]+${abis}" $SYSCALL_TBL	\
+		|sort -k1 -n					\
+		|create_header_defines
+
+	cat <<-EoFOOTER
+
+	#endif /* ${fileguard} */
+EoFOOTER
+}
+
+__max_syscall_nr()
+{
+	local abis=$(echo "($1)" | tr ',' '|')
+
+	grep -E "^[[:digit:]]+[[:space:]]+${abis}" $SYSCALL_TBL	 \
+		|sed -ne 's/^\([[:digit:]]*\)[[:space:]].*/\1/p' \
+		|sort -n					 \
+		|tail -1
+}
+
+
+generate_syscall_nr()
+{
+	local abis="$1"
+	local max_syscall_nr num_syscalls
+
+	max_syscall_nr=$(__max_syscall_nr "$abis")
+	num_syscalls=$((max_syscall_nr + 1))
+
+	cat <<-EoHEADER
+	/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+	#ifndef __ASM_S390_SYSCALLS_NR
+	#define __ASM_S390_SYSCALLS_NR
+
+	#define NR_syscalls ${num_syscalls}
+
+	#endif /* __ASM_S390_SYSCALLS_NR */
+EoHEADER
+}
+
+
+#
+# Parse command line arguments
+#
+do_syscall_header=""
+do_syscall_table=""
+do_syscall_nr=""
+output_file=""
+abi_list="common,64"
+filename=""
+while getopts ":HNSXi:a:f:" arg; do
+	case $arg in
+	a)
+		abi_list="$OPTARG"
+		;;
+	i)
+		SYSCALL_TBL="$OPTARG"
+		;;
+	f)
+		filename=${OPTARG##*/}
+		;;
+	H)
+		do_syscall_header=1
+		;;
+	N)
+		do_syscall_nr=1
+		;;
+	S)
+		do_syscall_table=1
+		;;
+	X)
+		set -x
+		;;
+	:)
+		echo "Missing argument for -$OPTARG" >&2
+		exit 1
+	;;
+	\?)
+		echo "Invalid option specified" >&2
+		exit 1
+	;;
+	esac
+done
+
+test "$do_syscall_header" && generate_syscall_header "$abi_list" "$filename"
+test "$do_syscall_table" && generate_syscall_table
+test "$do_syscall_nr" && generate_syscall_nr "$abi_list"
+
+exit 0
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index be6198193ec2..cf561160ea88 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *    Time of day based timer functions.
  *
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index f9b393d4a078..4b6e0397f66d 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *    Copyright IBM Corp. 2007, 2011
  *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
@@ -403,8 +404,7 @@ out:
 	put_online_cpus();
 	return rc ? rc : count;
 }
-static DEVICE_ATTR(dispatching, 0644, dispatching_show,
-			 dispatching_store);
+static DEVICE_ATTR_RW(dispatching);
 
 static ssize_t cpu_polarization_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 39a218703c50..f3a1c7c6824e 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * vdso setup for s390
  *
  *  Copyright IBM Corp. 2008
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 
 #include <linux/init.h>
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index 308564b9bf68..c5c856f320bc 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -10,6 +10,9 @@ obj-vdso32 = gettimeofday.o clock_getres.o clock_gettime.o note.o getcpu.o
 targets := $(obj-vdso32) vdso32.so vdso32.so.dbg
 obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
 
+KBUILD_AFLAGS += -DBUILD_VDSO
+KBUILD_CFLAGS += -DBUILD_VDSO
+
 KBUILD_AFLAGS_31 := $(filter-out -m64,$(KBUILD_AFLAGS))
 KBUILD_AFLAGS_31 += -m31 -s
 
diff --git a/arch/s390/kernel/vdso32/clock_getres.S b/arch/s390/kernel/vdso32/clock_getres.S
index eca3f001f081..eaf9cf1417f6 100644
--- a/arch/s390/kernel/vdso32/clock_getres.S
+++ b/arch/s390/kernel/vdso32/clock_getres.S
@@ -1,24 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Userland implementation of clock_getres() for 32 bits processes in a
  * s390 kernel for use in the vDSO
  *
  *  Copyright IBM Corp. 2008
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 #include <asm/vdso.h>
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
+#include <asm/dwarf.h>
 
 	.text
 	.align 4
 	.globl __kernel_clock_getres
 	.type  __kernel_clock_getres,@function
 __kernel_clock_getres:
-	.cfi_startproc
+	CFI_STARTPROC
 	basr	%r1,0
 	la	%r1,4f-.(%r1)
 	chi	%r2,__CLOCK_REALTIME
@@ -40,7 +38,7 @@ __kernel_clock_getres:
 3:	lhi	%r1,__NR_clock_getres		/* fallback to svc */
 	svc	0
 	br	%r14
+	CFI_ENDPROC
 4:	.long	__CLOCK_REALTIME_RES
 5:	.long	__CLOCK_COARSE_RES
-	.cfi_endproc
 	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S
index a5769b83d90e..a9418bf975db 100644
--- a/arch/s390/kernel/vdso32/clock_gettime.S
+++ b/arch/s390/kernel/vdso32/clock_gettime.S
@@ -1,25 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Userland implementation of clock_gettime() for 32 bits processes in a
  * s390 kernel for use in the vDSO
  *
  *  Copyright IBM Corp. 2008
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 #include <asm/vdso.h>
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
+#include <asm/dwarf.h>
 
 	.text
 	.align 4
 	.globl __kernel_clock_gettime
 	.type  __kernel_clock_gettime,@function
 __kernel_clock_gettime:
-	.cfi_startproc
+	CFI_STARTPROC
 	ahi	%r15,-16
+	CFI_DEF_CFA_OFFSET 176
+	CFI_VAL_OFFSET 15, -160
 	basr	%r5,0
 0:	al	%r5,21f-0b(%r5)			/* get &_vdso_data */
 	chi	%r2,__CLOCK_REALTIME_COARSE
@@ -72,9 +72,13 @@ __kernel_clock_gettime:
 	st	%r1,4(%r3)			/* store tp->tv_nsec */
 	lhi	%r2,0
 	ahi	%r15,16
+	CFI_DEF_CFA_OFFSET 160
+	CFI_RESTORE 15
 	br	%r14
 
 	/* CLOCK_MONOTONIC_COARSE */
+	CFI_DEF_CFA_OFFSET 176
+	CFI_VAL_OFFSET 15, -160
 9:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
 	tml	%r4,0x0001			/* pending update ? loop */
 	jnz	9b
@@ -154,15 +158,21 @@ __kernel_clock_gettime:
 	st	%r1,4(%r3)			/* store tp->tv_nsec */
 	lhi	%r2,0
 	ahi	%r15,16
+	CFI_DEF_CFA_OFFSET 160
+	CFI_RESTORE 15
 	br	%r14
 
 	/* Fallback to system call */
+	CFI_DEF_CFA_OFFSET 176
+	CFI_VAL_OFFSET 15, -160
 19:	lhi	%r1,__NR_clock_gettime
 	svc	0
 	ahi	%r15,16
+	CFI_DEF_CFA_OFFSET 160
+	CFI_RESTORE 15
 	br	%r14
+	CFI_ENDPROC
 
 20:	.long	1000000000
 21:	.long	_vdso_data - 0b
-	.cfi_endproc
 	.size	__kernel_clock_gettime,.-__kernel_clock_gettime
diff --git a/arch/s390/kernel/vdso32/getcpu.S b/arch/s390/kernel/vdso32/getcpu.S
index 5477a2c112fb..25515f3fbcea 100644
--- a/arch/s390/kernel/vdso32/getcpu.S
+++ b/arch/s390/kernel/vdso32/getcpu.S
@@ -8,13 +8,14 @@
  */
 #include <asm/vdso.h>
 #include <asm/asm-offsets.h>
+#include <asm/dwarf.h>
 
 	.text
 	.align 4
 	.globl __kernel_getcpu
 	.type  __kernel_getcpu,@function
 __kernel_getcpu:
-	.cfi_startproc
+	CFI_STARTPROC
 	la	%r4,0
 	sacf	256
 	l	%r5,__VDSO_CPU_NR(%r4)
@@ -28,5 +29,5 @@ __kernel_getcpu:
 	st	%r4,0(%r3)
 3:	lhi	%r2,0
 	br	%r14
-	.cfi_endproc
+	CFI_ENDPROC
 	.size	__kernel_getcpu,.-__kernel_getcpu
diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S
index 63b86dceb0bf..3c0db0fa6ad9 100644
--- a/arch/s390/kernel/vdso32/gettimeofday.S
+++ b/arch/s390/kernel/vdso32/gettimeofday.S
@@ -1,25 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Userland implementation of gettimeofday() for 32 bits processes in a
  * s390 kernel for use in the vDSO
  *
  *  Copyright IBM Corp. 2008
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 #include <asm/vdso.h>
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
+#include <asm/dwarf.h>
 
 	.text
 	.align 4
 	.globl __kernel_gettimeofday
 	.type  __kernel_gettimeofday,@function
 __kernel_gettimeofday:
-	.cfi_startproc
+	CFI_STARTPROC
 	ahi	%r15,-16
+	CFI_ADJUST_CFA_OFFSET 16
+	CFI_VAL_OFFSET 15, -160
 	basr	%r5,0
 0:	al	%r5,13f-0b(%r5)			/* get &_vdso_data */
 1:	ltr	%r3,%r3				/* check if tz is NULL */
@@ -92,9 +92,11 @@ __kernel_gettimeofday:
 	st	%r0,4(%r2)			/* store tv->tv_usec */
 10:	slr	%r2,%r2
 	ahi	%r15,16
+	CFI_ADJUST_CFA_OFFSET -16
+	CFI_RESTORE 15
 	br	%r14
+	CFI_ENDPROC
 11:	.long	1000000000
 12:	.long	274877907
 13:	.long	_vdso_data - 0b
-	.cfi_endproc
 	.size	__kernel_gettimeofday,.-__kernel_gettimeofday
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index f81ae7998883..15b1ceafc4c1 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -10,6 +10,9 @@ obj-vdso64 = gettimeofday.o clock_getres.o clock_gettime.o note.o getcpu.o
 targets := $(obj-vdso64) vdso64.so vdso64.so.dbg
 obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
 
+KBUILD_AFLAGS += -DBUILD_VDSO
+KBUILD_CFLAGS += -DBUILD_VDSO
+
 KBUILD_AFLAGS_64 := $(filter-out -m64,$(KBUILD_AFLAGS))
 KBUILD_AFLAGS_64 += -m64 -s
 
diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S
index c8513deb8c66..081435398e0a 100644
--- a/arch/s390/kernel/vdso64/clock_getres.S
+++ b/arch/s390/kernel/vdso64/clock_getres.S
@@ -1,24 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Userland implementation of clock_getres() for 64 bits processes in a
  * s390 kernel for use in the vDSO
  *
  *  Copyright IBM Corp. 2008
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 #include <asm/vdso.h>
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
+#include <asm/dwarf.h>
 
 	.text
 	.align 4
 	.globl __kernel_clock_getres
 	.type  __kernel_clock_getres,@function
 __kernel_clock_getres:
-	.cfi_startproc
+	CFI_STARTPROC
 	larl	%r1,4f
 	cghi	%r2,__CLOCK_REALTIME_COARSE
 	je	0f
@@ -46,7 +44,7 @@ __kernel_clock_getres:
 2:	lghi	%r1,__NR_clock_getres		/* fallback to svc */
 	svc	0
 	br	%r14
+	CFI_ENDPROC
 3:	.quad	__CLOCK_REALTIME_RES
 4:	.quad	__CLOCK_COARSE_RES
-	.cfi_endproc
 	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S
index 5d7b56b49458..fac3ab5ec83a 100644
--- a/arch/s390/kernel/vdso64/clock_gettime.S
+++ b/arch/s390/kernel/vdso64/clock_gettime.S
@@ -1,25 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Userland implementation of clock_gettime() for 64 bits processes in a
  * s390 kernel for use in the vDSO
  *
  *  Copyright IBM Corp. 2008
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 #include <asm/vdso.h>
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
+#include <asm/dwarf.h>
 
 	.text
 	.align 4
 	.globl __kernel_clock_gettime
 	.type  __kernel_clock_gettime,@function
 __kernel_clock_gettime:
-	.cfi_startproc
+	CFI_STARTPROC
 	aghi	%r15,-16
+	CFI_DEF_CFA_OFFSET 176
+	CFI_VAL_OFFSET 15, -160
 	larl	%r5,_vdso_data
 	cghi	%r2,__CLOCK_REALTIME_COARSE
 	je	4f
@@ -56,9 +56,13 @@ __kernel_clock_gettime:
 	stg	%r1,8(%r3)			/* store tp->tv_nsec */
 	lghi	%r2,0
 	aghi	%r15,16
+	CFI_DEF_CFA_OFFSET 160
+	CFI_RESTORE 15
 	br	%r14
 
 	/* CLOCK_MONOTONIC_COARSE */
+	CFI_DEF_CFA_OFFSET 176
+	CFI_VAL_OFFSET 15, -160
 3:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
 	tmll	%r4,0x0001			/* pending update ? loop */
 	jnz	3b
@@ -111,9 +115,13 @@ __kernel_clock_gettime:
 	stg	%r1,8(%r3)			/* store tp->tv_nsec */
 	lghi	%r2,0
 	aghi	%r15,16
+	CFI_DEF_CFA_OFFSET 160
+	CFI_RESTORE 15
 	br	%r14
 
 	/* CPUCLOCK_VIRT for this thread */
+	CFI_DEF_CFA_OFFSET 176
+	CFI_VAL_OFFSET 15, -160
 9:	lghi	%r4,0
 	icm	%r0,15,__VDSO_ECTG_OK(%r5)
 	jz	12f
@@ -134,15 +142,21 @@ __kernel_clock_gettime:
 	stg	%r4,8(%r3)
 	lghi	%r2,0
 	aghi	%r15,16
+	CFI_DEF_CFA_OFFSET 160
+	CFI_RESTORE 15
 	br	%r14
 
 	/* Fallback to system call */
+	CFI_DEF_CFA_OFFSET 176
+	CFI_VAL_OFFSET 15, -160
 12:	lghi	%r1,__NR_clock_gettime
 	svc	0
 	aghi	%r15,16
+	CFI_DEF_CFA_OFFSET 160
+	CFI_RESTORE 15
 	br	%r14
+	CFI_ENDPROC
 
 13:	.quad	1000000000
 14:	.quad	19342813113834067
-	.cfi_endproc
 	.size	__kernel_clock_gettime,.-__kernel_clock_gettime
diff --git a/arch/s390/kernel/vdso64/getcpu.S b/arch/s390/kernel/vdso64/getcpu.S
index e9c34364d97b..2446e9dac8ab 100644
--- a/arch/s390/kernel/vdso64/getcpu.S
+++ b/arch/s390/kernel/vdso64/getcpu.S
@@ -8,13 +8,14 @@
  */
 #include <asm/vdso.h>
 #include <asm/asm-offsets.h>
+#include <asm/dwarf.h>
 
 	.text
 	.align 4
 	.globl __kernel_getcpu
 	.type  __kernel_getcpu,@function
 __kernel_getcpu:
-	.cfi_startproc
+	CFI_STARTPROC
 	la	%r4,0
 	sacf	256
 	l	%r5,__VDSO_CPU_NR(%r4)
@@ -28,5 +29,5 @@ __kernel_getcpu:
 	st	%r4,0(%r3)
 3:	lghi	%r2,0
 	br	%r14
-	.cfi_endproc
+	CFI_ENDPROC
 	.size	__kernel_getcpu,.-__kernel_getcpu
diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S
index b02e62f3bc12..6e1f0b421695 100644
--- a/arch/s390/kernel/vdso64/gettimeofday.S
+++ b/arch/s390/kernel/vdso64/gettimeofday.S
@@ -1,25 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Userland implementation of gettimeofday() for 64 bits processes in a
  * s390 kernel for use in the vDSO
  *
  *  Copyright IBM Corp. 2008
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 #include <asm/vdso.h>
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
+#include <asm/dwarf.h>
 
 	.text
 	.align 4
 	.globl __kernel_gettimeofday
 	.type  __kernel_gettimeofday,@function
 __kernel_gettimeofday:
-	.cfi_startproc
+	CFI_STARTPROC
 	aghi	%r15,-16
+	CFI_ADJUST_CFA_OFFSET 16
+	CFI_VAL_OFFSET 15, -160
 	larl	%r5,_vdso_data
 0:	ltgr	%r3,%r3				/* check if tz is NULL */
 	je	1f
@@ -61,8 +61,10 @@ __kernel_gettimeofday:
 	stg	%r0,8(%r2)			/* store tv->tv_usec */
 4:	lghi	%r2,0
 	aghi	%r15,16
+	CFI_ADJUST_CFA_OFFSET -16
+	CFI_RESTORE 15
 	br	%r14
+	CFI_ENDPROC
 5:	.quad	1000000000
 	.long	274877907
-	.cfi_endproc
 	.size	__kernel_gettimeofday,.-__kernel_gettimeofday
diff --git a/arch/s390/kernel/vdso64/note.S b/arch/s390/kernel/vdso64/note.S
index 79a071e4357e..db19d0680a0a 100644
--- a/arch/s390/kernel/vdso64/note.S
+++ b/arch/s390/kernel/vdso64/note.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
  * Here we can supply some information useful to userland.
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index a049ff005f03..608cf2987d19 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -141,4 +141,7 @@ SECTIONS
 
 	/* Sections to be discarded */
 	DISCARDS
+	/DISCARD/ : {
+		*(.eh_frame)
+	}
 }
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index dd7178fbb4f3..f24395a01918 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *    Virtual cpu timer based timer functions.
  *
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 6048b1c6e580..05ee90a5ea08 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -1,10 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for kernel virtual machines on s390
 #
 # Copyright IBM Corp. 2008
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License (version 2 only)
-# as published by the Free Software Foundation.
 
 KVM := ../../../virt/kvm
 common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index d93a2c0474bf..89aa114a2cba 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * handling diagnose instructions
  *
  * Copyright IBM Corp. 2008, 2011
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index bec42b852246..f4c51756c462 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * access guest memory
  *
  * Copyright IBM Corp. 2008, 2014
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  */
 
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index bcbd86621d01..b5f3e82006d0 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kvm guest debug support
  *
  * Copyright IBM Corp. 2014
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): David Hildenbrand <dahi@linux.vnet.ibm.com>
  */
 #include <linux/kvm_host.h>
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 8fe034beb623..9c7d70715862 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * in-kernel handling for sie intercepts
  *
  * Copyright IBM Corp. 2008, 2014
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index fa557372d600..024ad8bcc516 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * handling kvm guest interrupts
  *
  * Copyright IBM Corp. 2008, 2015
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  */
 
diff --git a/arch/s390/kvm/irq.h b/arch/s390/kvm/irq.h
index d98e4159643d..484608c71dd0 100644
--- a/arch/s390/kvm/irq.h
+++ b/arch/s390/kvm/irq.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * s390 irqchip routines
  *
  * Copyright IBM Corp. 2014
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
  */
 #ifndef __KVM_IRQ_H
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 98ad8b9e0360..1371dff2b90d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * hosting zSeries kernel virtual machines
+ * hosting IBM Z kernel virtual machines (s390x)
  *
- * Copyright IBM Corp. 2008, 2009
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
+ * Copyright IBM Corp. 2008, 2017
  *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
@@ -424,6 +421,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_GS:
 		r = test_facility(133);
 		break;
+	case KVM_CAP_S390_BPB:
+		r = test_facility(82);
+		break;
 	default:
 		r = 0;
 	}
@@ -769,7 +769,7 @@ static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
 
 /*
  * Must be called with kvm->srcu held to avoid races on memslots, and with
- * kvm->lock to avoid races with ourselves and kvm_s390_vm_stop_migration.
+ * kvm->slots_lock to avoid races with ourselves and kvm_s390_vm_stop_migration.
  */
 static int kvm_s390_vm_start_migration(struct kvm *kvm)
 {
@@ -795,11 +795,12 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
 
 	if (kvm->arch.use_cmma) {
 		/*
-		 * Get the last slot. They should be sorted by base_gfn, so the
-		 * last slot is also the one at the end of the address space.
-		 * We have verified above that at least one slot is present.
+		 * Get the first slot. They are reverse sorted by base_gfn, so
+		 * the first slot is also the one at the end of the address
+		 * space. We have verified above that at least one slot is
+		 * present.
 		 */
-		ms = slots->memslots + slots->used_slots - 1;
+		ms = slots->memslots;
 		/* round up so we only use full longs */
 		ram_pages = roundup(ms->base_gfn + ms->npages, BITS_PER_LONG);
 		/* allocate enough bytes to store all the bits */
@@ -824,7 +825,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
 }
 
 /*
- * Must be called with kvm->lock to avoid races with ourselves and
+ * Must be called with kvm->slots_lock to avoid races with ourselves and
  * kvm_s390_vm_start_migration.
  */
 static int kvm_s390_vm_stop_migration(struct kvm *kvm)
@@ -839,6 +840,8 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm)
 
 	if (kvm->arch.use_cmma) {
 		kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION);
+		/* We have to wait for the essa emulation to finish */
+		synchronize_srcu(&kvm->srcu);
 		vfree(mgs->pgste_bitmap);
 	}
 	kfree(mgs);
@@ -848,14 +851,12 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm)
 static int kvm_s390_vm_set_migration(struct kvm *kvm,
 				     struct kvm_device_attr *attr)
 {
-	int idx, res = -ENXIO;
+	int res = -ENXIO;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->slots_lock);
 	switch (attr->attr) {
 	case KVM_S390_VM_MIGRATION_START:
-		idx = srcu_read_lock(&kvm->srcu);
 		res = kvm_s390_vm_start_migration(kvm);
-		srcu_read_unlock(&kvm->srcu, idx);
 		break;
 	case KVM_S390_VM_MIGRATION_STOP:
 		res = kvm_s390_vm_stop_migration(kvm);
@@ -863,7 +864,7 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm,
 	default:
 		break;
 	}
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->slots_lock);
 
 	return res;
 }
@@ -1753,7 +1754,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&args, argp, sizeof(args)))
 			break;
+		mutex_lock(&kvm->slots_lock);
 		r = kvm_s390_get_cmma_bits(kvm, &args);
+		mutex_unlock(&kvm->slots_lock);
 		if (!r) {
 			r = copy_to_user(argp, &args, sizeof(args));
 			if (r)
@@ -1767,7 +1770,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&args, argp, sizeof(args)))
 			break;
+		mutex_lock(&kvm->slots_lock);
 		r = kvm_s390_set_cmma_bits(kvm, &args);
+		mutex_unlock(&kvm->slots_lock);
 		break;
 	}
 	default:
@@ -2200,6 +2205,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	kvm_s390_set_prefix(vcpu, 0);
 	if (test_kvm_facility(vcpu->kvm, 64))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
+	if (test_kvm_facility(vcpu->kvm, 82))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
 	if (test_kvm_facility(vcpu->kvm, 133))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB;
 	/* fprs can be synchronized via vrs, even if the guest has no vx. With
@@ -2341,6 +2348,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
+	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
 	kvm_clear_async_pf_completion_queue(vcpu);
 	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
@@ -3300,6 +3308,11 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT;
 		vcpu->arch.gs_enabled = 1;
 	}
+	if ((kvm_run->kvm_dirty_regs & KVM_SYNC_BPBC) &&
+	    test_kvm_facility(vcpu->kvm, 82)) {
+		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+		vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
+	}
 	save_access_regs(vcpu->arch.host_acrs);
 	restore_access_regs(vcpu->run->s.regs.acrs);
 	/* save host (userspace) fprs/vrs */
@@ -3346,6 +3359,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->s.regs.pft = vcpu->arch.pfault_token;
 	kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
 	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
+	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
 	/* Save guest register state */
@@ -3372,7 +3386,6 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	int rc;
-	sigset_t sigsaved;
 
 	if (kvm_run->immediate_exit)
 		return -EINTR;
@@ -3382,8 +3395,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		return 0;
 	}
 
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+	kvm_sigset_activate(vcpu);
 
 	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
 		kvm_s390_vcpu_start(vcpu);
@@ -3417,8 +3429,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	disable_cpu_timer_accounting(vcpu);
 	store_regs(vcpu, kvm_run);
 
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+	kvm_sigset_deactivate(vcpu);
 
 	vcpu->stat.exit_userspace++;
 	return rc;
@@ -3811,6 +3822,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			r = -EINVAL;
 			break;
 		}
+		/* do not use irq_state.flags, it will break old QEMUs */
 		r = kvm_s390_set_irq_state(vcpu,
 					   (void __user *) irq_state.buf,
 					   irq_state.len);
@@ -3826,6 +3838,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			r = -EINVAL;
 			break;
 		}
+		/* do not use irq_state.flags, it will break old QEMUs */
 		r = kvm_s390_get_irq_state(vcpu,
 					   (__u8 __user *)  irq_state.buf,
 					   irq_state.len);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 10d65dfbc306..5e46ba429bcb 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * definition for kvm on s390
  *
  * Copyright IBM Corp. 2008, 2009
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  *               Christian Ehrhardt <ehrhardt@de.ibm.com>
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index c954ac49eee4..0714bfa56da0 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * handling privileged instructions
  *
  * Copyright IBM Corp. 2008, 2013
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */
@@ -235,8 +232,6 @@ static int try_handle_skey(struct kvm_vcpu *vcpu)
 		VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
 		return -EAGAIN;
 	}
-	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
-		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 	return 0;
 }
 
@@ -247,6 +242,9 @@ static int handle_iske(struct kvm_vcpu *vcpu)
 	int reg1, reg2;
 	int rc;
 
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
 	rc = try_handle_skey(vcpu);
 	if (rc)
 		return rc != -EAGAIN ? rc : 0;
@@ -276,6 +274,9 @@ static int handle_rrbe(struct kvm_vcpu *vcpu)
 	int reg1, reg2;
 	int rc;
 
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
 	rc = try_handle_skey(vcpu);
 	if (rc)
 		return rc != -EAGAIN ? rc : 0;
@@ -311,6 +312,9 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 	int reg1, reg2;
 	int rc;
 
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
 	rc = try_handle_skey(vcpu);
 	if (rc)
 		return rc != -EAGAIN ? rc : 0;
@@ -1002,7 +1006,7 @@ static inline int do_essa(struct kvm_vcpu *vcpu, const int orc)
 		cbrlo[entries] = gfn << PAGE_SHIFT;
 	}
 
-	if (orc) {
+	if (orc && gfn < ms->bitmap_size) {
 		/* increment only if we are really flipping the bit to 1 */
 		if (!test_and_set_bit(gfn, ms->pgste_bitmap))
 			atomic64_inc(&ms->dirty_pages);
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 9d592ef4104b..c1f5cde2c878 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * handling interprocessor communication
  *
  * Copyright IBM Corp. 2008, 2013
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  *               Christian Ehrhardt <ehrhardt@de.ibm.com>
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index a311938b63b3..751348348477 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kvm nested virtualization support for s390x
  *
  * Copyright IBM Corp. 2016
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): David Hildenbrand <dahi@linux.vnet.ibm.com>
  */
 #include <linux/vmalloc.h>
@@ -226,6 +223,12 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	memcpy(scb_o->gcr, scb_s->gcr, 128);
 	scb_o->pp = scb_s->pp;
 
+	/* branch prediction */
+	if (test_kvm_facility(vcpu->kvm, 82)) {
+		scb_o->fpf &= ~FPF_BPBC;
+		scb_o->fpf |= scb_s->fpf & FPF_BPBC;
+	}
+
 	/* interrupt intercept */
 	switch (scb_s->icptcode) {
 	case ICPT_PROGI:
@@ -268,6 +271,7 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	scb_s->ecb3 = 0;
 	scb_s->ecd = 0;
 	scb_s->fac = 0;
+	scb_s->fpf = 0;
 
 	rc = prepare_cpuflags(vcpu, vsie_page);
 	if (rc)
@@ -327,6 +331,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			prefix_unmapped(vsie_page);
 		scb_s->ecb |= scb_o->ecb & ECB_TE;
 	}
+	/* branch prediction */
+	if (test_kvm_facility(vcpu->kvm, 82))
+		scb_s->fpf |= scb_o->fpf & FPF_BPBC;
 	/* SIMD */
 	if (test_kvm_facility(vcpu->kvm, 129)) {
 		scb_s->eca |= scb_o->eca & ECA_VX;
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index cae5a1e16cbd..c4f8039a35e8 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -89,11 +89,11 @@ EXPORT_SYMBOL(enable_sacf_uaccess);
 
 void disable_sacf_uaccess(mm_segment_t old_fs)
 {
+	current->thread.mm_segment = old_fs;
 	if (old_fs == USER_DS && test_facility(27)) {
 		__ctl_load(S390_lowcore.user_asce, 1, 1);
 		clear_cpu_flag(CIF_ASCE_PRIMARY);
 	}
-	current->thread.mm_segment = old_fs;
 }
 EXPORT_SYMBOL(disable_sacf_uaccess);
 
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 3d017171ff8f..6cf024eb2085 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  Collaborative memory management interface.
  *
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index b2c140193b0a..05d459b638f5 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  KVM guest address space mapping code
  *
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 5bea139517a2..831bdcf407bb 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -1,24 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  *  flexible mmap layout support
  *
  * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
  * All Rights Reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- *
  * Started by Ingo Molnar <mingo@elte.hu>
  */
 
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 434a9564917b..cb364153c43c 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -83,8 +83,6 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
 
 	/* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */
 	VM_BUG_ON(mm->context.asce_limit < _REGION2_SIZE);
-	if (end >= TASK_SIZE_MAX)
-		return -ENOMEM;
 	rc = 0;
 	notify = 0;
 	while (mm->context.asce_limit < end) {
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index ae677f814bc0..4f2b65d01a70 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *    Copyright IBM Corp. 2007, 2011
  *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
diff --git a/arch/s390/net/Makefile b/arch/s390/net/Makefile
index 90568c33ddb0..e0d5f245e42b 100644
--- a/arch/s390/net/Makefile
+++ b/arch/s390/net/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Arch-specific network modules
 #
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index e81c16838b90..78a19c93b380 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -28,8 +28,6 @@
 #include <asm/set_memory.h>
 #include "bpf_jit.h"
 
-int bpf_jit_enable __read_mostly;
-
 struct bpf_jit {
 	u32 seen;		/* Flags to remember seen eBPF instructions */
 	u32 seen_reg[16];	/* Array to remember which registers are used */
@@ -55,8 +53,7 @@ struct bpf_jit {
 #define SEEN_LITERAL	8	/* code uses literals */
 #define SEEN_FUNC	16	/* calls C functions */
 #define SEEN_TAIL_CALL	32	/* code uses tail calls */
-#define SEEN_SKB_CHANGE	64	/* code changes skb data */
-#define SEEN_REG_AX	128	/* code uses constant blinding */
+#define SEEN_REG_AX	64	/* code uses constant blinding */
 #define SEEN_STACK	(SEEN_FUNC | SEEN_MEM | SEEN_SKB)
 
 /*
@@ -448,12 +445,12 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
 			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
 	}
-	if (jit->seen & SEEN_SKB)
+	if (jit->seen & SEEN_SKB) {
 		emit_load_skb_data_hlen(jit);
-	if (jit->seen & SEEN_SKB_CHANGE)
 		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
 		EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
 			      STK_OFF_SKBP);
+	}
 }
 
 /*
@@ -613,11 +610,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	{
 		int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
 
-		jit->seen |= SEEN_RET0;
-		/* ltr %src,%src (if src == 0 goto fail) */
-		EMIT2(0x1200, src_reg, src_reg);
-		/* jz <ret0> */
-		EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg);
 		/* lhi %w0,0 */
 		EMIT4_IMM(0xa7080000, REG_W0, 0);
 		/* lr %w1,%dst */
@@ -633,11 +625,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	{
 		int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
 
-		jit->seen |= SEEN_RET0;
-		/* ltgr %src,%src (if src == 0 goto fail) */
-		EMIT4(0xb9020000, src_reg, src_reg);
-		/* jz <ret0> */
-		EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg);
 		/* lghi %w0,0 */
 		EMIT4_IMM(0xa7090000, REG_W0, 0);
 		/* lgr %w1,%dst */
@@ -983,8 +970,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT2(0x0d00, REG_14, REG_W1);
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
-		if (bpf_helper_changes_pkt_data((void *)func)) {
-			jit->seen |= SEEN_SKB_CHANGE;
+		if ((jit->seen & SEEN_SKB) &&
+		    bpf_helper_changes_pkt_data((void *)func)) {
 			/* lg %b1,ST_OFF_SKBP(%r15) */
 			EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
 				      REG_15, STK_OFF_SKBP);
@@ -1300,7 +1287,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	struct bpf_jit jit;
 	int pass;
 
-	if (!bpf_jit_enable)
+	if (!fp->jit_requested)
 		return orig_fp;
 
 	tmp = bpf_jit_blind_constants(fp);
diff --git a/arch/s390/numa/Makefile b/arch/s390/numa/Makefile
index f94ecaffa71b..66c2dff74895 100644
--- a/arch/s390/numa/Makefile
+++ b/arch/s390/numa/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 obj-y			+= numa.o
 obj-y			+= toptree.o
 obj-$(CONFIG_NUMA_EMU)	+= mode_emu.o
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index 805d8b29193a..22d0871291ee 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Makefile for the s390 PCI subsystem.
 #
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 0fe649c0d542..4902fed221c0 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright IBM Corp. 2012
  *
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index c2f786f0ea06..b482e95b6249 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  Copyright IBM Corp. 2012,2015
  *
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 0d300ee00f4e..2d15d84c20ed 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright IBM Corp. 2012
  *
@@ -180,6 +181,9 @@ out_unlock:
 static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr,
 			   size_t size, int flags)
 {
+	unsigned long irqflags;
+	int ret;
+
 	/*
 	 * With zdev->tlb_refresh == 0, rpcit is not required to establish new
 	 * translations when previously invalid translation-table entries are
@@ -195,8 +199,22 @@ static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr,
 			return 0;
 	}
 
-	return zpci_refresh_trans((u64) zdev->fh << 32, dma_addr,
-				  PAGE_ALIGN(size));
+	ret = zpci_refresh_trans((u64) zdev->fh << 32, dma_addr,
+				 PAGE_ALIGN(size));
+	if (ret == -ENOMEM && !s390_iommu_strict) {
+		/* enable the hypervisor to free some resources */
+		if (zpci_refresh_global(zdev))
+			goto out;
+
+		spin_lock_irqsave(&zdev->iommu_bitmap_lock, irqflags);
+		bitmap_andnot(zdev->iommu_bitmap, zdev->iommu_bitmap,
+			      zdev->lazy_bitmap, zdev->iommu_pages);
+		bitmap_zero(zdev->lazy_bitmap, zdev->iommu_pages);
+		spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, irqflags);
+		ret = 0;
+	}
+out:
+	return ret;
 }
 
 static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index 81b840bc6e4e..f069929e8211 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * s390 specific pci instructions
  *
@@ -88,6 +89,9 @@ int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
 	if (cc)
 		zpci_err_insn(cc, status, addr, range);
 
+	if (cc == 1 && (status == 4 || status == 16))
+		return -ENOMEM;
+
 	return (cc) ? -EIO : 0;
 }
 
diff --git a/arch/s390/tools/.gitignore b/arch/s390/tools/.gitignore
index 72a4b2cf1365..71bd6f8eebaf 100644
--- a/arch/s390/tools/.gitignore
+++ b/arch/s390/tools/.gitignore
@@ -1 +1,2 @@
 gen_facilities
+gen_opcode_table
diff --git a/arch/s390/tools/Makefile b/arch/s390/tools/Makefile
index 2e70e25de07a..48cdac1143a9 100644
--- a/arch/s390/tools/Makefile
+++ b/arch/s390/tools/Makefile
@@ -3,22 +3,33 @@
 # Makefile for s390 specific build tools
 #
 
+kapi := arch/$(ARCH)/include/generated/asm
+kapi-hdrs-y := $(kapi)/facility-defs.h $(kapi)/dis-defs.h
+
+targets += $(addprefix ../../../,$(kapi-hdrs-y))
+PHONY += kapi
+
+kapi:	$(kapi-hdrs-y)
+
 hostprogs-y		    += gen_facilities
 hostprogs-y		    += gen_opcode_table
 
 HOSTCFLAGS_gen_facilities.o += -Wall $(LINUXINCLUDE)
 HOSTCFLAGS_gen_opcode_table.o += -Wall $(LINUXINCLUDE)
 
-define filechk_facilities.h
+# Ensure output directory exists
+_dummy := $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)')
+
+define filechk_facility-defs.h
 	$(obj)/gen_facilities
 endef
 
-define filechk_dis.h
+define filechk_dis-defs.h
 	( $(obj)/gen_opcode_table < $(srctree)/arch/$(ARCH)/tools/opcodes.txt )
 endef
 
-include/generated/facilities.h: $(obj)/gen_facilities FORCE
-	$(call filechk,facilities.h)
+$(kapi)/facility-defs.h: $(obj)/gen_facilities FORCE
+	$(call filechk,facility-defs.h)
 
-include/generated/dis.h: $(obj)/gen_opcode_table FORCE
-	$(call filechk,dis.h)
+$(kapi)/dis-defs.h: $(obj)/gen_opcode_table FORCE
+	$(call filechk,dis-defs.h)
diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c
index 0373801d9860..424a1ba4f874 100644
--- a/arch/s390/tools/gen_facilities.c
+++ b/arch/s390/tools/gen_facilities.c
@@ -128,8 +128,8 @@ static void print_facility_lists(void)
 
 int main(int argc, char **argv)
 {
-	printf("#ifndef __ASM_S390_FACILITIES__\n");
-	printf("#define __ASM_S390_FACILITIES__\n");
+	printf("#ifndef __ASM_S390_FACILITY_DEFS__\n");
+	printf("#define __ASM_S390_FACILITY_DEFS__\n");
 	printf("/*\n");
 	printf(" * DO NOT MODIFY.\n");
 	printf(" *\n");
diff --git a/arch/s390/tools/gen_opcode_table.c b/arch/s390/tools/gen_opcode_table.c
index 01d4c5a4bfe9..259aa0680d1a 100644
--- a/arch/s390/tools/gen_opcode_table.c
+++ b/arch/s390/tools/gen_opcode_table.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Generate opcode table initializers for the in-kernel disassembler.
  *
@@ -320,8 +321,8 @@ int main(int argc, char **argv)
 	struct gen_opcode *desc = &_desc;
 
 	read_instructions(desc);
-	printf("#ifndef __S390_GENERATED_DIS_H__\n");
-	printf("#define __S390_GENERATED_DIS_H__\n");
+	printf("#ifndef __S390_GENERATED_DIS_DEFS_H__\n");
+	printf("#define __S390_GENERATED_DIS_DEFS_H__\n");
 	printf("/*\n");
 	printf(" * DO NOT MODIFY.\n");
 	printf(" *\n");
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index 54b3b2039af1..1a0ee72f6a7c 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -1,5 +1,4 @@
 generic-y += barrier.h
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += extable.h
 generic-y += irq_work.h
diff --git a/arch/score/include/asm/thread_info.h b/arch/score/include/asm/thread_info.h
index ad51b56e51bd..bc4c7c90550f 100644
--- a/arch/score/include/asm/thread_info.h
+++ b/arch/score/include/asm/thread_info.h
@@ -58,9 +58,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* How to get the thread information struct from C. */
 register struct thread_info *__current_thread_info __asm__("r28");
 #define current_thread_info()	__current_thread_info
diff --git a/arch/score/include/uapi/asm/Kbuild b/arch/score/include/uapi/asm/Kbuild
index c94ee54210bc..b04fd1632051 100644
--- a/arch/score/include/uapi/asm/Kbuild
+++ b/arch/score/include/uapi/asm/Kbuild
@@ -1,4 +1,6 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y	+= bpf_perf_event.h
+generic-y	+= poll.h
 generic-y	+= siginfo.h
diff --git a/arch/score/include/uapi/asm/poll.h b/arch/score/include/uapi/asm/poll.h
deleted file mode 100644
index c636b85843cd..000000000000
--- a/arch/score/include/uapi/asm/poll.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_SCORE_POLL_H
-#define _ASM_SCORE_POLL_H
-
-#include <asm-generic/poll.h>
-
-#endif /* _ASM_SCORE_POLL_H */
diff --git a/arch/sh/boards/board-espt.c b/arch/sh/boards/board-espt.c
index 7291e2f11a47..4d6be53058d6 100644
--- a/arch/sh/boards/board-espt.c
+++ b/arch/sh/boards/board-espt.c
@@ -79,7 +79,6 @@ static struct resource sh_eth_resources[] = {
 
 static struct sh_eth_plat_data sh7763_eth_pdata = {
 	.phy = 0,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 
diff --git a/arch/sh/boards/board-sh7757lcr.c b/arch/sh/boards/board-sh7757lcr.c
index 0104c8199c48..1bde08dc067d 100644
--- a/arch/sh/boards/board-sh7757lcr.c
+++ b/arch/sh/boards/board-sh7757lcr.c
@@ -76,7 +76,6 @@ static struct resource sh_eth0_resources[] = {
 
 static struct sh_eth_plat_data sh7757_eth0_pdata = {
 	.phy = 1,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.set_mdio_gate = sh7757_eth_set_mdio_gate,
 };
 
@@ -104,7 +103,6 @@ static struct resource sh_eth1_resources[] = {
 
 static struct sh_eth_plat_data sh7757_eth1_pdata = {
 	.phy = 1,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.set_mdio_gate = sh7757_eth_set_mdio_gate,
 };
 
@@ -148,7 +146,6 @@ static struct resource sh_eth_giga0_resources[] = {
 
 static struct sh_eth_plat_data sh7757_eth_giga0_pdata = {
 	.phy = 18,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.set_mdio_gate = sh7757_eth_giga_set_mdio_gate,
 	.phy_interface = PHY_INTERFACE_MODE_RGMII_ID,
 };
@@ -182,7 +179,6 @@ static struct resource sh_eth_giga1_resources[] = {
 
 static struct sh_eth_plat_data sh7757_eth_giga1_pdata = {
 	.phy = 19,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.set_mdio_gate = sh7757_eth_giga_set_mdio_gate,
 	.phy_interface = PHY_INTERFACE_MODE_RGMII_ID,
 };
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index 1faf6cb93dcb..6f929abe0b50 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -159,7 +159,6 @@ static struct resource sh_eth_resources[] = {
 
 static struct sh_eth_plat_data sh_eth_plat = {
 	.phy = 0x1f, /* SMSC LAN8700 */
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 	.ether_link_active_low = 1
 };
diff --git a/arch/sh/boards/mach-se/770x/setup.c b/arch/sh/boards/mach-se/770x/setup.c
index 77c35350ee77..412326d59e6f 100644
--- a/arch/sh/boards/mach-se/770x/setup.c
+++ b/arch/sh/boards/mach-se/770x/setup.c
@@ -9,6 +9,7 @@
  */
 #include <linux/init.h>
 #include <linux/platform_device.h>
+#include <linux/sh_eth.h>
 #include <mach-se/mach/se.h>
 #include <mach-se/mach/mrshpc.h>
 #include <asm/machvec.h>
@@ -115,13 +116,23 @@ static struct platform_device heartbeat_device = {
 #if defined(CONFIG_CPU_SUBTYPE_SH7710) ||\
 	defined(CONFIG_CPU_SUBTYPE_SH7712)
 /* SH771X Ethernet driver */
+static struct sh_eth_plat_data sh_eth_plat = {
+	.phy = PHY_ID,
+	.phy_interface = PHY_INTERFACE_MODE_MII,
+};
+
 static struct resource sh_eth0_resources[] = {
 	[0] = {
 		.start = SH_ETH0_BASE,
-		.end = SH_ETH0_BASE + 0x1B8,
+		.end = SH_ETH0_BASE + 0x1B8 - 1,
 		.flags = IORESOURCE_MEM,
 	},
 	[1] = {
+		.start = SH_TSU_BASE,
+		.end = SH_TSU_BASE + 0x200 - 1,
+		.flags = IORESOURCE_MEM,
+	},
+	[2] = {
 		.start = SH_ETH0_IRQ,
 		.end = SH_ETH0_IRQ,
 		.flags = IORESOURCE_IRQ,
@@ -132,7 +143,7 @@ static struct platform_device sh_eth0_device = {
 	.name = "sh771x-ether",
 	.id = 0,
 	.dev = {
-		.platform_data = PHY_ID,
+		.platform_data = &sh_eth_plat,
 	},
 	.num_resources = ARRAY_SIZE(sh_eth0_resources),
 	.resource = sh_eth0_resources,
@@ -141,10 +152,15 @@ static struct platform_device sh_eth0_device = {
 static struct resource sh_eth1_resources[] = {
 	[0] = {
 		.start = SH_ETH1_BASE,
-		.end = SH_ETH1_BASE + 0x1B8,
+		.end = SH_ETH1_BASE + 0x1B8 - 1,
 		.flags = IORESOURCE_MEM,
 	},
 	[1] = {
+		.start = SH_TSU_BASE,
+		.end = SH_TSU_BASE + 0x200 - 1,
+		.flags = IORESOURCE_MEM,
+	},
+	[2] = {
 		.start = SH_ETH1_IRQ,
 		.end = SH_ETH1_IRQ,
 		.flags = IORESOURCE_IRQ,
@@ -155,7 +171,7 @@ static struct platform_device sh_eth1_device = {
 	.name = "sh771x-ether",
 	.id = 1,
 	.dev = {
-		.platform_data = PHY_ID,
+		.platform_data = &sh_eth_plat,
 	},
 	.num_resources = ARRAY_SIZE(sh_eth1_resources),
 	.resource = sh_eth1_resources,
diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index f1fecd395679..255952555656 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -374,7 +374,6 @@ static struct resource sh_eth_resources[] = {
 
 static struct sh_eth_plat_data sh_eth_plat = {
 	.phy = 0x1f, /* SMSC LAN8187 */
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 
diff --git a/arch/sh/boards/mach-sh7763rdp/setup.c b/arch/sh/boards/mach-sh7763rdp/setup.c
index 2c8fb04685d4..6e62686b81b1 100644
--- a/arch/sh/boards/mach-sh7763rdp/setup.c
+++ b/arch/sh/boards/mach-sh7763rdp/setup.c
@@ -87,7 +87,6 @@ static struct resource sh_eth_resources[] = {
 
 static struct sh_eth_plat_data sh7763_eth_pdata = {
 	.phy = 1,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 
diff --git a/arch/sh/configs/polaris_defconfig b/arch/sh/configs/polaris_defconfig
index 0a432b5f50e7..87641b7d6c4e 100644
--- a/arch/sh/configs/polaris_defconfig
+++ b/arch/sh/configs/polaris_defconfig
@@ -38,7 +38,6 @@ CONFIG_IP_MULTICAST=y
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/sh/drivers/push-switch.c b/arch/sh/drivers/push-switch.c
index a17181160233..762bc5619910 100644
--- a/arch/sh/drivers/push-switch.c
+++ b/arch/sh/drivers/push-switch.c
@@ -24,7 +24,7 @@ static ssize_t switch_show(struct device *dev,
 	struct push_switch_platform_info *psw_info = dev->platform_data;
 	return sprintf(buf, "%s\n", psw_info->name);
 }
-static DEVICE_ATTR(switch, S_IRUGO, switch_show, NULL);
+static DEVICE_ATTR_RO(switch);
 
 static void switch_timer(struct timer_list *t)
 {
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 1a6f9c39feef..1efcce74997b 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -1,4 +1,3 @@
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h
index becb798f1b04..cf5c792bf70b 100644
--- a/arch/sh/include/asm/thread_info.h
+++ b/arch/sh/include/asm/thread_info.h
@@ -63,9 +63,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* how to get the current stack pointer from C */
 register unsigned long current_stack_pointer asm("r15") __used;
 
diff --git a/arch/sh/include/mach-se/mach/se.h b/arch/sh/include/mach-se/mach/se.h
index 4246ef9b07a3..aa83fe1ff0b1 100644
--- a/arch/sh/include/mach-se/mach/se.h
+++ b/arch/sh/include/mach-se/mach/se.h
@@ -100,6 +100,7 @@
 /* Base address */
 #define SH_ETH0_BASE 0xA7000000
 #define SH_ETH1_BASE 0xA7000400
+#define SH_TSU_BASE  0xA7000800
 /* PHY ID */
 #if defined(CONFIG_CPU_SUBTYPE_SH7710)
 # define PHY_ID 0x00
diff --git a/arch/sh/include/uapi/asm/Kbuild b/arch/sh/include/uapi/asm/Kbuild
index e28531333efa..ba4d39cb321d 100644
--- a/arch/sh/include/uapi/asm/Kbuild
+++ b/arch/sh/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/sh/kernel/cpu/sh2/setup-sh7619.c b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
index 95796ad00fbe..d08db08dec38 100644
--- a/arch/sh/kernel/cpu/sh2/setup-sh7619.c
+++ b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
@@ -122,7 +122,6 @@ static struct platform_device scif2_device = {
 
 static struct sh_eth_plat_data eth_platform_data = {
 	.phy		= 1,
-	.edmac_endian	= EDMAC_LITTLE_ENDIAN,
 	.phy_interface	= PHY_INTERFACE_MODE_MII,
 };
 
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 2c7bdf8cb934..93522069cb15 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -20,7 +20,6 @@
 #include <linux/sched/task_stack.h>
 #include <linux/slab.h>
 #include <linux/elfcore.h>
-#include <linux/kallsyms.h>
 #include <linux/fs.h>
 #include <linux/ftrace.h>
 #include <linux/hw_breakpoint.h>
@@ -37,8 +36,8 @@ void show_regs(struct pt_regs * regs)
 	printk("\n");
 	show_regs_print_info(KERN_DEFAULT);
 
-	print_symbol("PC is at %s\n", instruction_pointer(regs));
-	print_symbol("PR is at %s\n", regs->pr);
+	printk("PC is at %pS\n", (void *)instruction_pointer(regs));
+	printk("PR is at %pS\n", (void *)regs->pr);
 
 	printk("PC  : %08lx SP  : %08lx SR  : %08lx ",
 	       regs->pc, regs->regs[15], regs->sr);
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index 57cff00cad17..b3770bb26211 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -609,7 +609,8 @@ asmlinkage void do_divide_error(unsigned long r4)
 		break;
 	}
 
-	force_sig_info(SIGFPE, &info, current);
+	info.si_signo = SIGFPE;
+	force_sig_info(info.si_signo, &info, current);
 }
 #endif
 
diff --git a/arch/sparc/crypto/Makefile b/arch/sparc/crypto/Makefile
index 818d3aa5172e..d257186c27d1 100644
--- a/arch/sparc/crypto/Makefile
+++ b/arch/sparc/crypto/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_CRYPTO_MD5_SPARC64) += md5-sparc64.o
 
 obj-$(CONFIG_CRYPTO_AES_SPARC64) += aes-sparc64.o
 obj-$(CONFIG_CRYPTO_DES_SPARC64) += des-sparc64.o
-obj-$(CONFIG_CRYPTO_DES_SPARC64) += camellia-sparc64.o
+obj-$(CONFIG_CRYPTO_CAMELLIA_SPARC64) += camellia-sparc64.o
 
 obj-$(CONFIG_CRYPTO_CRC32C_SPARC64) += crc32c-sparc64.o
 
diff --git a/arch/sparc/crypto/crc32c_glue.c b/arch/sparc/crypto/crc32c_glue.c
index d1064e46efe8..8aa664638c3c 100644
--- a/arch/sparc/crypto/crc32c_glue.c
+++ b/arch/sparc/crypto/crc32c_glue.c
@@ -133,6 +133,7 @@ static struct shash_alg alg = {
 		.cra_name		=	"crc32c",
 		.cra_driver_name	=	"crc32c-sparc64",
 		.cra_priority		=	SPARC_CR_OPCODE_PRIORITY,
+		.cra_flags		=	CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		=	CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		=	sizeof(u32),
 		.cra_alignmask		=	7,
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 80ddc01f57ac..ac67828da201 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -1,7 +1,6 @@
 # User exported sparc header files
 
 
-generic-y += clkdev.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += exec.h
diff --git a/arch/sparc/include/asm/asm-prototypes.h b/arch/sparc/include/asm/asm-prototypes.h
index 96e0972e8dbf..4987c735ff56 100644
--- a/arch/sparc/include/asm/asm-prototypes.h
+++ b/arch/sparc/include/asm/asm-prototypes.h
@@ -6,7 +6,7 @@
 #include <asm/xor.h>
 #include <asm/checksum.h>
 #include <asm/trap_block.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/atomic.h>
 #include <asm/ftrace.h>
 #include <asm/cacheflush.h>
diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h
index fa38c78de0f0..615283e16f22 100644
--- a/arch/sparc/include/asm/compat.h
+++ b/arch/sparc/include/asm/compat.h
@@ -149,65 +149,6 @@ typedef u32		compat_old_sigset_t;
 
 typedef u32		compat_sigset_word;
 
-typedef union compat_sigval {
-	compat_int_t	sival_int;
-	compat_uptr_t	sival_ptr;
-} compat_sigval_t;
-
-#define SI_PAD_SIZE32	(128/sizeof(int) - 3)
-
-typedef struct compat_siginfo {
-	int si_signo;
-	int si_errno;
-	int si_code;
-
-	union {
-		int _pad[SI_PAD_SIZE32];
-
-		/* kill() */
-		struct {
-			compat_pid_t _pid;		/* sender's pid */
-			unsigned int _uid;		/* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			compat_timer_t _tid;		/* timer id */
-			int _overrun;			/* overrun count */
-			compat_sigval_t _sigval;	/* same as below */
-			int _sys_private;	/* not to be passed to user */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			compat_pid_t _pid;		/* sender's pid */
-			unsigned int _uid;		/* sender's uid */
-			compat_sigval_t _sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			compat_pid_t _pid;		/* which child */
-			unsigned int _uid;		/* sender's uid */
-			int _status;			/* exit code */
-			compat_clock_t _utime;
-			compat_clock_t _stime;
-		} _sigchld;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */
-		struct {
-			u32 _addr; /* faulting insn/memory ref. */
-			int _trapno;
-		} _sigfault;
-
-		/* SIGPOLL */
-		struct {
-			int _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
-			int _fd;
-		} _sigpoll;
-	} _sifields;
-} compat_siginfo_t;
-
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
 /*
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index 89a0c57aed59..ab9c6b027b75 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -76,6 +76,10 @@
 #define HV_ETOOMANY			15 /* Too many items specified     */
 #define HV_ECHANNEL			16 /* Invalid LDC channel          */
 #define HV_EBUSY			17 /* Resource busy                */
+#define HV_EUNAVAILABLE			23 /* Resource or operation not
+					    * currently available, but may
+					    * become available in the future
+					    */
 
 /* mach_exit()
  * TRAP:	HV_FAST_TRAP
@@ -941,6 +945,139 @@ unsigned long sun4v_mmu_map_perm_addr(unsigned long vaddr,
  */
 #define HV_FAST_MEM_SYNC		0x32
 
+/* Coprocessor services
+ *
+ * M7 and later processors provide an on-chip coprocessor which
+ * accelerates database operations, and is known internally as
+ * DAX.
+ */
+
+/* ccb_submit()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_CCB_SUBMIT
+ * ARG0:	address of CCB array
+ * ARG1:	size (in bytes) of CCB array being submitted
+ * ARG2:	flags
+ * ARG3:	reserved
+ * RET0:	status (success or error code)
+ * RET1:	size (in bytes) of CCB array that was accepted (might be less
+ *		than arg1)
+ * RET2:	status data
+ *		if status == ENOMAP or ENOACCESS, identifies the VA in question
+ *		if status == EUNAVAILBLE, unavailable code
+ * RET3:	reserved
+ *
+ * ERRORS:	EOK		successful submission (check size)
+ *		EWOULDBLOCK	could not finish submissions, try again
+ *		EBADALIGN	array not 64B aligned or size not 64B multiple
+ *		ENORADDR	invalid RA for array or in CCB
+ *		ENOMAP		could not translate address (see status data)
+ *		EINVAL		invalid ccb or arguments
+ *		ETOOMANY	too many ccbs with all-or-nothing flag
+ *		ENOACCESS	guest has no access to submit ccbs or address
+ *				in CCB does not have correct permissions (check
+ *				status data)
+ *		EUNAVAILABLE	ccb operation could not be performed at this
+ *				time (check status data)
+ *				Status data codes:
+ *					0 - exact CCB could not be executed
+ *					1 - CCB opcode cannot be executed
+ *					2 - CCB version cannot be executed
+ *					3 - vcpu cannot execute CCBs
+ *					4 - no CCBs can be executed
+ */
+
+#define HV_CCB_SUBMIT               0x34
+#ifndef __ASSEMBLY__
+unsigned long sun4v_ccb_submit(unsigned long ccb_buf,
+			       unsigned long len,
+			       unsigned long flags,
+			       unsigned long reserved,
+			       void *submitted_len,
+			       void *status_data);
+#endif
+
+/* flags (ARG2) */
+#define HV_CCB_QUERY_CMD		BIT(1)
+#define HV_CCB_ARG0_TYPE_REAL		0UL
+#define HV_CCB_ARG0_TYPE_PRIMARY	BIT(4)
+#define HV_CCB_ARG0_TYPE_SECONDARY	BIT(5)
+#define HV_CCB_ARG0_TYPE_NUCLEUS	GENMASK(5, 4)
+#define HV_CCB_ARG0_PRIVILEGED		BIT(6)
+#define HV_CCB_ALL_OR_NOTHING		BIT(7)
+#define HV_CCB_QUEUE_INFO		BIT(8)
+#define HV_CCB_VA_REJECT		0UL
+#define HV_CCB_VA_SECONDARY		BIT(13)
+#define HV_CCB_VA_NUCLEUS		GENMASK(13, 12)
+#define HV_CCB_VA_PRIVILEGED		BIT(14)
+#define HV_CCB_VA_READ_ADI_DISABLE	BIT(15)	/* DAX2 only */
+
+/* ccb_info()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_CCB_INFO
+ * ARG0:	real address of CCB completion area
+ * RET0:	status (success or error code)
+ * RET1:	info array
+ *			- RET1[0]: CCB state
+ *			- RET1[1]: dax unit
+ *			- RET1[2]: queue number
+ *			- RET1[3]: queue position
+ *
+ * ERRORS:	EOK		operation successful
+ *		EBADALIGN	address not 64B aligned
+ *		ENORADDR	RA in address not valid
+ *		EINVAL		CA not valid
+ *		EWOULDBLOCK	info not available for this CCB currently, try
+ *				again
+ *		ENOACCESS	guest cannot use dax
+ */
+
+#define HV_CCB_INFO                 0x35
+#ifndef __ASSEMBLY__
+unsigned long sun4v_ccb_info(unsigned long ca,
+			     void *info_arr);
+#endif
+
+/* info array byte offsets (RET1) */
+#define CCB_INFO_OFFSET_CCB_STATE	0
+#define CCB_INFO_OFFSET_DAX_UNIT	2
+#define CCB_INFO_OFFSET_QUEUE_NUM	4
+#define CCB_INFO_OFFSET_QUEUE_POS	6
+
+/* CCB state (RET1[0]) */
+#define HV_CCB_STATE_COMPLETED      0
+#define HV_CCB_STATE_ENQUEUED       1
+#define HV_CCB_STATE_INPROGRESS     2
+#define HV_CCB_STATE_NOTFOUND       3
+
+/* ccb_kill()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_CCB_KILL
+ * ARG0:	real address of CCB completion area
+ * RET0:	status (success or error code)
+ * RET1:	CCB kill status
+ *
+ * ERRORS:	EOK		operation successful
+ *		EBADALIGN	address not 64B aligned
+ *		ENORADDR	RA in address not valid
+ *		EINVAL		CA not valid
+ *		EWOULDBLOCK	kill not available for this CCB currently, try
+ *				again
+ *		ENOACCESS	guest cannot use dax
+ */
+
+#define HV_CCB_KILL                 0x36
+#ifndef __ASSEMBLY__
+unsigned long sun4v_ccb_kill(unsigned long ca,
+			     void *kill_status);
+#endif
+
+/* CCB kill status (RET1) */
+#define HV_CCB_KILL_COMPLETED       0
+#define HV_CCB_KILL_DEQUEUED        1
+#define HV_CCB_KILL_KILLED          2
+#define HV_CCB_KILL_NOTFOUND        3
+
 /* Time of day services.
  *
  * The hypervisor maintains the time of day on a per-domain basis.
@@ -3355,6 +3492,7 @@ unsigned long sun4v_m7_set_perfreg(unsigned long reg_num,
 #define HV_GRP_SDIO_ERR			0x0109
 #define HV_GRP_REBOOT_DATA		0x0110
 #define HV_GRP_ATU			0x0111
+#define HV_GRP_DAX			0x0113
 #define HV_GRP_M7_PERF			0x0114
 #define HV_GRP_NIAG_PERF		0x0200
 #define HV_GRP_FIRE_PERF		0x0201
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 5a9e96be1665..339920fdf9ed 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -715,7 +715,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return pte_pfn(pte);
 }
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline unsigned long pmd_write(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
@@ -1010,7 +1010,7 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 			  pmd_t *pmd);
 
 #define __HAVE_ARCH_PMDP_INVALIDATE
-extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h
index febaaeb1a0fe..548b366165dd 100644
--- a/arch/sparc/include/asm/thread_info_32.h
+++ b/arch/sparc/include/asm/thread_info_32.h
@@ -63,9 +63,6 @@ struct thread_info {
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* how to get the thread information struct from C */
 register struct thread_info *current_thread_info_reg asm("g6");
 #define current_thread_info()   (current_thread_info_reg)
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index caf915321ba9..f7e7b0baec9f 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -120,9 +120,6 @@ struct thread_info {
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* how to get the thread information struct from C */
 register struct thread_info *current_thread_info_reg asm("g6");
 #define current_thread_info()	(current_thread_info_reg)
diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild
index 2178c78c7c1a..4680ba246b55 100644
--- a/arch/sparc/include/uapi/asm/Kbuild
+++ b/arch/sparc/include/uapi/asm/Kbuild
@@ -1,4 +1,5 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += types.h
diff --git a/arch/sparc/include/uapi/asm/oradax.h b/arch/sparc/include/uapi/asm/oradax.h
new file mode 100644
index 000000000000..722951908b0a
--- /dev/null
+++ b/arch/sparc/include/uapi/asm/oradax.h
@@ -0,0 +1,91 @@
+/*
+ * Copyright (c) 2017, Oracle and/or its affiliates. All rights reserved.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * Oracle DAX driver API definitions
+ */
+
+#ifndef _ORADAX_H
+#define	_ORADAX_H
+
+#include <linux/types.h>
+
+#define	CCB_KILL 0
+#define	CCB_INFO 1
+#define	CCB_DEQUEUE 2
+
+struct dax_command {
+	__u16 command;		/* CCB_KILL/INFO/DEQUEUE */
+	__u16 ca_offset;	/* offset into mmapped completion area */
+};
+
+struct ccb_kill_result {
+	__u16 action;		/* action taken to kill ccb */
+};
+
+struct ccb_info_result {
+	__u16 state;		/* state of enqueued ccb */
+	__u16 inst_num;		/* dax instance number of enqueued ccb */
+	__u16 q_num;		/* queue number of enqueued ccb */
+	__u16 q_pos;		/* ccb position in queue */
+};
+
+struct ccb_exec_result {
+	__u64	status_data;	/* additional status data (e.g. bad VA) */
+	__u32	status;		/* one of DAX_SUBMIT_* */
+};
+
+union ccb_result {
+	struct ccb_exec_result exec;
+	struct ccb_info_result info;
+	struct ccb_kill_result kill;
+};
+
+#define	DAX_MMAP_LEN		(16 * 1024)
+#define	DAX_MAX_CCBS		15
+#define	DAX_CCB_BUF_MAXLEN	(DAX_MAX_CCBS * 64)
+#define	DAX_NAME		"oradax"
+
+/* CCB_EXEC status */
+#define	DAX_SUBMIT_OK			0
+#define	DAX_SUBMIT_ERR_RETRY		1
+#define	DAX_SUBMIT_ERR_WOULDBLOCK	2
+#define	DAX_SUBMIT_ERR_BUSY		3
+#define	DAX_SUBMIT_ERR_THR_INIT		4
+#define	DAX_SUBMIT_ERR_ARG_INVAL	5
+#define	DAX_SUBMIT_ERR_CCB_INVAL	6
+#define	DAX_SUBMIT_ERR_NO_CA_AVAIL	7
+#define	DAX_SUBMIT_ERR_CCB_ARR_MMU_MISS	8
+#define	DAX_SUBMIT_ERR_NOMAP		9
+#define	DAX_SUBMIT_ERR_NOACCESS		10
+#define	DAX_SUBMIT_ERR_TOOMANY		11
+#define	DAX_SUBMIT_ERR_UNAVAIL		12
+#define	DAX_SUBMIT_ERR_INTERNAL		13
+
+/* CCB_INFO states - must match HV_CCB_STATE_* definitions */
+#define	DAX_CCB_COMPLETED	0
+#define	DAX_CCB_ENQUEUED	1
+#define	DAX_CCB_INPROGRESS	2
+#define	DAX_CCB_NOTFOUND	3
+
+/* CCB_KILL actions - must match HV_CCB_KILL_* definitions */
+#define	DAX_KILL_COMPLETED	0
+#define	DAX_KILL_DEQUEUED	1
+#define	DAX_KILL_KILLED		2
+#define	DAX_KILL_NOTFOUND	3
+
+#endif /* _ORADAX_H */
diff --git a/arch/sparc/include/uapi/asm/poll.h b/arch/sparc/include/uapi/asm/poll.h
index 72356c999125..2a81e79aa3ea 100644
--- a/arch/sparc/include/uapi/asm/poll.h
+++ b/arch/sparc/include/uapi/asm/poll.h
@@ -2,11 +2,31 @@
 #ifndef __SPARC_POLL_H
 #define __SPARC_POLL_H
 
+#ifndef __KERNEL__
 #define POLLWRNORM	POLLOUT
-#define POLLWRBAND	256
-#define POLLMSG		512
-#define POLLREMOVE	1024
-#define POLLRDHUP       2048
+#define POLLWRBAND	(__force __poll_t)256
+#define POLLMSG		(__force __poll_t)512
+#define POLLREMOVE	(__force __poll_t)1024
+#define POLLRDHUP       (__force __poll_t)2048
+#else
+#define __ARCH_HAS_MANGLED_POLL
+static inline __u16 mangle_poll(__poll_t val)
+{
+	__u16 v = (__force __u16)val;
+        /* bit 9 -> bit 8, bit 8 -> bit 2, bit 13 -> bit 11 */
+	return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6) |
+				((v & 0x2000) >> 2);
+
+
+}
+
+static inline __poll_t demangle_poll(__u16 v)
+{
+        /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
+	return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
+				((v & 4) << 6) | ((v & 0x800) << 2));
+}
+#endif
 
 #include <asm-generic/poll.h>
 
diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index a2bc1b2955b4..717ec7ef07f9 100644
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@@ -41,6 +41,7 @@ static struct api_info api_table[] = {
 	{ .group = HV_GRP_SDIO_ERR,				},
 	{ .group = HV_GRP_REBOOT_DATA,				},
 	{ .group = HV_GRP_ATU,		.flags = FLAG_PRE_API	},
+	{ .group = HV_GRP_DAX,					},
 	{ .group = HV_GRP_NIAG_PERF,	.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_FIRE_PERF,				},
 	{ .group = HV_GRP_N2_CPU,				},
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index bdfd3d8c6707..2f865a464576 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -871,3 +871,60 @@ ENTRY(sun4v_m7_set_perfreg)
 	retl
 	nop
 ENDPROC(sun4v_m7_set_perfreg)
+
+	/* %o0: address of CCB array
+	 * %o1: size (in bytes) of CCB array
+	 * %o2: flags
+	 * %o3: reserved
+	 *
+	 * returns:
+	 * %o0: status
+	 * %o1: size (in bytes) of the CCB array that was accepted
+	 * %o2: status data
+	 * %o3: reserved
+	 */
+ENTRY(sun4v_ccb_submit)
+	mov	%o5, %g1
+	mov	HV_CCB_SUBMIT, %o5
+	ta	HV_FAST_TRAP
+	stx	%o1, [%o4]
+	retl
+	 stx	%o2, [%g1]
+ENDPROC(sun4v_ccb_submit)
+EXPORT_SYMBOL(sun4v_ccb_submit)
+
+	/* %o0: completion area ra for the ccb to get info
+	 *
+	 * returns:
+	 * %o0: status
+	 * %o1: CCB state
+	 * %o2: position
+	 * %o3: dax unit
+	 * %o4: queue
+	 */
+ENTRY(sun4v_ccb_info)
+	mov	%o1, %g1
+	mov	HV_CCB_INFO, %o5
+	ta	HV_FAST_TRAP
+	sth	%o1, [%g1 + CCB_INFO_OFFSET_CCB_STATE]
+	sth	%o2, [%g1 + CCB_INFO_OFFSET_QUEUE_POS]
+	sth	%o3, [%g1 + CCB_INFO_OFFSET_DAX_UNIT]
+	retl
+	 sth	%o4, [%g1 + CCB_INFO_OFFSET_QUEUE_NUM]
+ENDPROC(sun4v_ccb_info)
+EXPORT_SYMBOL(sun4v_ccb_info)
+
+	/* %o0: completion area ra for the ccb to kill
+	 *
+	 * returns:
+	 * %o0: status
+	 * %o1: result of the kill
+	 */
+ENTRY(sun4v_ccb_kill)
+	mov	%o1, %g1
+	mov	HV_CCB_KILL, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 sth	%o1, [%g1]
+ENDPROC(sun4v_ccb_kill)
+EXPORT_SYMBOL(sun4v_ccb_kill)
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 54a6159b9cd8..44d379db3f64 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -70,75 +70,6 @@ struct rt_signal_frame32 {
 	/* __siginfo_rwin_t * */u32 rwin_save;
 } __attribute__((aligned(8)));
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
-{
-	int err;
-
-	if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
-		return -EFAULT;
-
-	/* If you change siginfo_t structure, please be sure
-	   this code is fixed accordingly.
-	   It should never copy any pad contained in the structure
-	   to avoid security leaks, but must copy the generic
-	   3 ints plus the relevant union member.
-	   This routine must convert siginfo from 64bit to 32bit as well
-	   at the same time.  */
-	err = __put_user(from->si_signo, &to->si_signo);
-	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user(from->si_code, &to->si_code);
-	if (from->si_code < 0)
-		err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
-	else {
-		switch (siginfo_layout(from->si_signo, from->si_code)) {
-		case SIL_TIMER:
-			err |= __put_user(from->si_tid, &to->si_tid);
-			err |= __put_user(from->si_overrun, &to->si_overrun);
-			err |= __put_user(from->si_int, &to->si_int);
-			break;
-		case SIL_CHLD:
-			err |= __put_user(from->si_utime, &to->si_utime);
-			err |= __put_user(from->si_stime, &to->si_stime);
-			err |= __put_user(from->si_status, &to->si_status);
-		default:
-		case SIL_KILL:
-			err |= __put_user(from->si_pid, &to->si_pid);
-			err |= __put_user(from->si_uid, &to->si_uid);
-			break;
-		case SIL_FAULT:
-			err |= __put_user(from->si_trapno, &to->si_trapno);
-			err |= __put_user((unsigned long)from->si_addr, &to->si_addr);
-			break;
-		case SIL_POLL:
-			err |= __put_user(from->si_band, &to->si_band);
-			err |= __put_user(from->si_fd, &to->si_fd);
-			break;
-		case SIL_RT:
-			err |= __put_user(from->si_pid, &to->si_pid);
-			err |= __put_user(from->si_uid, &to->si_uid);
-			err |= __put_user(from->si_int, &to->si_int);
-			break;
-		}
-	}
-	return err;
-}
-
-/* CAUTION: This is just a very minimalist implementation for the
- *          sake of compat_sys_rt_sigqueueinfo()
- */
-int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
-{
-	if (!access_ok(VERIFY_WRITE, from, sizeof(compat_siginfo_t)))
-		return -EFAULT;
-
-	if (copy_from_user(to, from, 3*sizeof(int)) ||
-	    copy_from_user(to->_sifields._pad, from->_sifields._pad,
-			   SI_PAD_SIZE))
-		return -EFAULT;
-
-	return 0;
-}
-
 /* Checks if the fp is valid.  We always build signal frames which are
  * 16-byte aligned, therefore we can always enforce that the restore
  * frame has that property as well.
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 20426a1c28f2..48366e5eb5b2 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -9,9 +9,6 @@
  *  Copyright (C) 1997,1998 Jakub Jelinek   (jj@sunsite.mff.cuni.cz)
  */
 
-#ifdef CONFIG_COMPAT
-#include <linux/compat.h>	/* for compat_old_sigset_t */
-#endif
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 0f0f76b4f6cd..063556fe2cb1 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -19,7 +19,7 @@ lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
 lib-$(CONFIG_SPARC64) += multi3.o
 lib-$(CONFIG_SPARC64) += fls.o
 lib-$(CONFIG_SPARC64) += fls64.o
-obj-$(CONFIG_SPARC64) += NG4fls.o
+lib-$(CONFIG_SPARC64) += NG4fls.o
 
 lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o
 lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o
diff --git a/arch/sparc/lib/hweight.S b/arch/sparc/lib/hweight.S
index e5547b22cd18..0ddbbb031822 100644
--- a/arch/sparc/lib/hweight.S
+++ b/arch/sparc/lib/hweight.S
@@ -44,8 +44,8 @@ EXPORT_SYMBOL(__arch_hweight32)
 	.previous
 
 ENTRY(__arch_hweight64)
-	sethi	%hi(__sw_hweight16), %g1
-	jmpl	%g1 + %lo(__sw_hweight16), %g0
+	sethi	%hi(__sw_hweight64), %g1
+	jmpl	%g1 + %lo(__sw_hweight64), %g0
 	 nop
 ENDPROC(__arch_hweight64)
 EXPORT_SYMBOL(__arch_hweight64)
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index be3136f142a9..a8103a84b4ac 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -113,7 +113,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
 	if (!printk_ratelimit())
 		return;
 
-	printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x",
+	printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x",
 	       task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 	       tsk->comm, task_pid_nr(tsk), address,
 	       (void *)regs->pc, (void *)regs->u_regs[UREG_I7],
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 815c03d7a765..41363f46797b 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -154,7 +154,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
 	if (!printk_ratelimit())
 		return;
 
-	printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x",
+	printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x",
 	       task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 	       tsk->comm, task_pid_nr(tsk), address,
 	       (void *)regs->tpc, (void *)regs->u_regs[UREG_I7],
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 4ae86bc0d35c..847ddffbf38a 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -219,17 +219,28 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	}
 }
 
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	pmd_t old;
+
+	do {
+		old = *pmdp;
+	} while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd);
+
+	return old;
+}
+
 /*
  * This routine is only called when splitting a THP
  */
-void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
-	pmd_t entry = *pmdp;
-
-	pmd_val(entry) &= ~_PAGE_VALID;
+	pmd_t old, entry;
 
-	set_pmd_at(vma->vm_mm, address, pmdp, entry);
+	entry = __pmd(pmd_val(*pmdp) & ~_PAGE_VALID);
+	old = pmdp_establish(vma, address, pmdp, entry);
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 
 	/*
@@ -240,6 +251,8 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 	if ((pmd_val(entry) & _PAGE_PMD_HUGE) &&
 	    !is_huge_zero_page(pmd_page(entry)))
 		(vma->vm_mm)->context.thp_pte_count--;
+
+	return old;
 }
 
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c
index 09e318eb34ee..3bd8ca95e521 100644
--- a/arch/sparc/net/bpf_jit_comp_32.c
+++ b/arch/sparc/net/bpf_jit_comp_32.c
@@ -11,8 +11,6 @@
 
 #include "bpf_jit_32.h"
 
-int bpf_jit_enable __read_mostly;
-
 static inline bool is_simm13(unsigned int value)
 {
 	return value + 0x1000 < 0x2000;
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 5765e7e711f7..48a25869349b 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -12,8 +12,6 @@
 
 #include "bpf_jit_64.h"
 
-int bpf_jit_enable __read_mostly;
-
 static inline bool is_simm13(unsigned int value)
 {
 	return value + 0x1000 < 0x2000;
@@ -969,31 +967,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		emit_alu(MULX, src, dst, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_write_y(G0, ctx);
 		emit_alu(DIV, src, dst, ctx);
 		break;
-
 	case BPF_ALU64 | BPF_DIV | BPF_X:
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_alu(UDIVX, src, dst, ctx);
 		break;
-
 	case BPF_ALU | BPF_MOD | BPF_X: {
 		const u8 tmp = bpf2sparc[TMP_REG_1];
 
 		ctx->tmp_1_used = true;
 
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_write_y(G0, ctx);
 		emit_alu3(DIV, dst, src, tmp, ctx);
 		emit_alu3(MULX, tmp, src, tmp, ctx);
@@ -1005,10 +989,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 
 		ctx->tmp_1_used = true;
 
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_alu3(UDIVX, dst, src, tmp, ctx);
 		emit_alu3(MULX, tmp, src, tmp, ctx);
 		emit_alu3(SUB, dst, tmp, dst, ctx);
@@ -1245,14 +1225,16 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		u8 *func = ((u8 *)__bpf_call_base) + imm;
 
 		ctx->saw_call = true;
+		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
+			emit_reg_move(bpf2sparc[BPF_REG_1], L7, ctx);
 
 		emit_call((u32 *)func, ctx);
 		emit_nop(ctx);
 
 		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
 
-		if (bpf_helper_changes_pkt_data(func) && ctx->saw_ld_abs_ind)
-			load_skb_regs(ctx, bpf2sparc[BPF_REG_6]);
+		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
+			load_skb_regs(ctx, L7);
 		break;
 	}
 
@@ -1507,17 +1489,25 @@ static void jit_fill_hole(void *area, unsigned int size)
 		*ptr++ = 0x91d02005; /* ta 5 */
 }
 
+struct sparc64_jit_data {
+	struct bpf_binary_header *header;
+	u8 *image;
+	struct jit_ctx ctx;
+};
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_prog *tmp, *orig_prog = prog;
+	struct sparc64_jit_data *jit_data;
 	struct bpf_binary_header *header;
 	bool tmp_blinded = false;
+	bool extra_pass = false;
 	struct jit_ctx ctx;
 	u32 image_size;
 	u8 *image_ptr;
 	int pass;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
@@ -1531,13 +1521,31 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = tmp;
 	}
 
+	jit_data = prog->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			prog = orig_prog;
+			goto out;
+		}
+		prog->aux->jit_data = jit_data;
+	}
+	if (jit_data->ctx.offset) {
+		ctx = jit_data->ctx;
+		image_ptr = jit_data->image;
+		header = jit_data->header;
+		extra_pass = true;
+		image_size = sizeof(u32) * ctx.idx;
+		goto skip_init_ctx;
+	}
+
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
 
 	ctx.offset = kcalloc(prog->len, sizeof(unsigned int), GFP_KERNEL);
 	if (ctx.offset == NULL) {
 		prog = orig_prog;
-		goto out;
+		goto out_off;
 	}
 
 	/* Fake pass to detect features used, and get an accurate assessment
@@ -1560,7 +1568,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 
 	ctx.image = (u32 *)image_ptr;
-
+skip_init_ctx:
 	for (pass = 1; pass < 3; pass++) {
 		ctx.idx = 0;
 
@@ -1591,14 +1599,24 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	bpf_flush_icache(header, (u8 *)header + (header->pages * PAGE_SIZE));
 
-	bpf_jit_binary_lock_ro(header);
+	if (!prog->is_func || extra_pass) {
+		bpf_jit_binary_lock_ro(header);
+	} else {
+		jit_data->ctx = ctx;
+		jit_data->image = image_ptr;
+		jit_data->header = header;
+	}
 
 	prog->bpf_func = (void *)ctx.image;
 	prog->jited = 1;
 	prog->jited_len = image_size;
 
+	if (!prog->is_func || extra_pass) {
 out_off:
-	kfree(ctx.offset);
+		kfree(ctx.offset);
+		kfree(jit_data);
+		prog->aux->jit_data = NULL;
+	}
 out:
 	if (tmp_blinded)
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?
diff --git a/arch/sparc/vdso/vma.c b/arch/sparc/vdso/vma.c
index 0a6f50098e23..f51595f861b8 100644
--- a/arch/sparc/vdso/vma.c
+++ b/arch/sparc/vdso/vma.c
@@ -251,7 +251,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	else
 		return map_vdso(&vdso_image_32_builtin, &vdso_mapping32);
 #else
-		return map_vdso(&vdso_image_64_builtin, &vdso_mapping64);
+	return map_vdso(&vdso_image_64_builtin, &vdso_mapping64);
 #endif
 
 }
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 02f269cfa538..ef9d403cbbe4 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -249,7 +249,7 @@ config HIGHMEM
 
 	  If unsure, say "true".
 
-config ZONE_DMA
+config ZONE_DMA32
 	def_bool y
 
 config IOMMU_HELPER
@@ -261,6 +261,7 @@ config NEED_SG_DMA_LENGTH
 config SWIOTLB
 	bool
 	default TILEGX
+	select DMA_DIRECT_OPS
 	select IOMMU_HELPER
 	select NEED_SG_DMA_LENGTH
 	select ARCH_HAS_DMA_SET_COHERENT_MASK
diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig
index 9f94435cc44f..357a4c271ad4 100644
--- a/arch/tile/configs/tilegx_defconfig
+++ b/arch/tile/configs/tilegx_defconfig
@@ -159,7 +159,6 @@ CONFIG_DNS_RESOLVER=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_CONNECTOR=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_CRYPTOLOOP=m
diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig
index 1c5bd4f8ffca..da2858755fa1 100644
--- a/arch/tile/configs/tilepro_defconfig
+++ b/arch/tile/configs/tilepro_defconfig
@@ -289,7 +289,6 @@ CONFIG_DNS_RESOLVER=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_CONNECTOR=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_CRYPTOLOOP=m
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index d28d2b8932c7..414dfc3a1808 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -1,6 +1,5 @@
 generic-y += bug.h
 generic-y += bugs.h
-generic-y += clkdev.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h
index 62a7b83025dd..769ff6ac0bf5 100644
--- a/arch/tile/include/asm/compat.h
+++ b/arch/tile/include/asm/compat.h
@@ -110,68 +110,6 @@ struct compat_flock64 {
 
 typedef u32               compat_sigset_word;
 
-typedef union compat_sigval {
-	compat_int_t	sival_int;
-	compat_uptr_t	sival_ptr;
-} compat_sigval_t;
-
-#define COMPAT_SI_PAD_SIZE	(128/sizeof(int) - 3)
-
-typedef struct compat_siginfo {
-	int si_signo;
-	int si_errno;
-	int si_code;
-
-	union {
-		int _pad[COMPAT_SI_PAD_SIZE];
-
-		/* kill() */
-		struct {
-			unsigned int _pid;	/* sender's pid */
-			unsigned int _uid;	/* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			compat_timer_t _tid;	/* timer id */
-			int _overrun;		/* overrun count */
-			compat_sigval_t _sigval;	/* same as below */
-			int _sys_private;	/* not to be passed to user */
-			int _overrun_incr;	/* amount to add to overrun */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			unsigned int _pid;	/* sender's pid */
-			unsigned int _uid;	/* sender's uid */
-			compat_sigval_t _sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			unsigned int _pid;	/* which child */
-			unsigned int _uid;	/* sender's uid */
-			int _status;		/* exit code */
-			compat_clock_t _utime;
-			compat_clock_t _stime;
-		} _sigchld;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
-		struct {
-			unsigned int _addr;	/* faulting insn/memory ref. */
-#ifdef __ARCH_SI_TRAPNO
-			int _trapno;	/* TRAP # which caused the signal */
-#endif
-		} _sigfault;
-
-		/* SIGPOLL */
-		struct {
-			int _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
-			int _fd;
-		} _sigpoll;
-	} _sifields;
-} compat_siginfo_t;
-
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
 struct compat_ipc64_perm {
diff --git a/arch/tile/include/asm/dma-mapping.h b/arch/tile/include/asm/dma-mapping.h
index 97ad62878290..d25fce101fc0 100644
--- a/arch/tile/include/asm/dma-mapping.h
+++ b/arch/tile/include/asm/dma-mapping.h
@@ -44,26 +44,6 @@ static inline void set_dma_offset(struct device *dev, dma_addr_t off)
 	dev->archdata.dma_offset = off;
 }
 
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return paddr;
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return daddr;
-}
-
-static inline void dma_mark_clean(void *addr, size_t size) {}
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return 0;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
 #define HAVE_ARCH_DMA_SET_MASK 1
 int dma_set_mask(struct device *dev, u64 mask);
 
diff --git a/arch/tile/include/asm/pgtable.h b/arch/tile/include/asm/pgtable.h
index 2a26cc4fefc2..adfa21b18488 100644
--- a/arch/tile/include/asm/pgtable.h
+++ b/arch/tile/include/asm/pgtable.h
@@ -475,7 +475,6 @@ static inline void pmd_clear(pmd_t *pmdp)
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_huge_page(pmd)	pte_huge(pmd_pte(pmd))
 #define pmd_mkhuge(pmd)		pte_pmd(pte_mkhuge(pmd_pte(pmd)))
-#define __HAVE_ARCH_PMD_WRITE
 
 #define pfn_pmd(pfn, pgprot)	pte_pmd(pfn_pte((pfn), (pgprot)))
 #define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index b7659b8f1117..2adcacd85749 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -59,9 +59,6 @@ struct thread_info {
 	.align_ctl	= 0,			\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 #endif /* !__ASSEMBLY__ */
 
 #if PAGE_SIZE < 8192
diff --git a/arch/tile/include/uapi/asm/Kbuild b/arch/tile/include/uapi/asm/Kbuild
index 5711de0a1b5e..cc439612bcd5 100644
--- a/arch/tile/include/uapi/asm/Kbuild
+++ b/arch/tile/include/uapi/asm/Kbuild
@@ -1,6 +1,7 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/tile/include/uapi/asm/siginfo.h b/arch/tile/include/uapi/asm/siginfo.h
index f234d24fff55..a812fcbf4267 100644
--- a/arch/tile/include/uapi/asm/siginfo.h
+++ b/arch/tile/include/uapi/asm/siginfo.h
@@ -24,12 +24,4 @@
 
 #include <asm-generic/siginfo.h>
 
-/*
- * Additional Tile-specific SIGILL si_codes
- */
-#define ILL_DBLFLT	9	/* double fault */
-#define ILL_HARDWALL	10	/* user networks hardwall violation */
-#undef NSIGILL
-#define NSIGILL		10
-
 #endif /* _ASM_TILE_SIGINFO_H */
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index 971d87a1d8cf..a703bd0e0488 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -50,79 +50,6 @@ struct compat_rt_sigframe {
 	struct compat_ucontext uc;
 };
 
-int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *from)
-{
-	int err;
-
-	if (!access_ok(VERIFY_WRITE, to, sizeof(struct compat_siginfo)))
-		return -EFAULT;
-
-	/* If you change siginfo_t structure, please make sure that
-	   this code is fixed accordingly.
-	   It should never copy any pad contained in the structure
-	   to avoid security leaks, but must copy the generic
-	   3 ints plus the relevant union member.  */
-	err = __put_user(from->si_signo, &to->si_signo);
-	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user(from->si_code, &to->si_code);
-
-	if (from->si_code < 0) {
-		err |= __put_user(from->si_pid, &to->si_pid);
-		err |= __put_user(from->si_uid, &to->si_uid);
-		err |= __put_user(from->si_int, &to->si_int);
-	} else {
-		/*
-		 * First 32bits of unions are always present:
-		 * si_pid === si_band === si_tid === si_addr(LS half)
-		 */
-		err |= __put_user(from->_sifields._pad[0],
-				  &to->_sifields._pad[0]);
-		switch (siginfo_layout(from->si_signo, from->si_code)) {
-		case SIL_FAULT:
-			break;
-		case SIL_CHLD:
-			err |= __put_user(from->si_utime, &to->si_utime);
-			err |= __put_user(from->si_stime, &to->si_stime);
-			err |= __put_user(from->si_status, &to->si_status);
-			/* FALL THROUGH */
-		default:
-		case SIL_KILL:
-			err |= __put_user(from->si_uid, &to->si_uid);
-			break;
-		case SIL_POLL:
-			err |= __put_user(from->si_fd, &to->si_fd);
-			break;
-		case SIL_TIMER:
-			err |= __put_user(from->si_overrun, &to->si_overrun);
-			err |= __put_user(from->si_int, &to->si_int);
-			break;
-		case SIL_RT:
-			err |= __put_user(from->si_uid, &to->si_uid);
-			err |= __put_user(from->si_int, &to->si_int);
-			break;
-		}
-	}
-	return err;
-}
-
-int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
-{
-	int err;
-
-	if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo)))
-		return -EFAULT;
-
-	err = __get_user(to->si_signo, &from->si_signo);
-	err |= __get_user(to->si_errno, &from->si_errno);
-	err |= __get_user(to->si_code, &from->si_code);
-
-	err |= __get_user(to->si_pid, &from->si_pid);
-	err |= __get_user(to->si_uid, &from->si_uid);
-	err |= __get_user(to->si_int, &from->si_int);
-
-	return err;
-}
-
 /* The assembly shim for this function arranges to ignore the return value. */
 long compat_sys_rt_sigreturn(void)
 {
diff --git a/arch/tile/kernel/pci-dma.c b/arch/tile/kernel/pci-dma.c
index f2abedc8a080..6a1efe5543fa 100644
--- a/arch/tile/kernel/pci-dma.c
+++ b/arch/tile/kernel/pci-dma.c
@@ -54,7 +54,7 @@ static void *tile_dma_alloc_coherent(struct device *dev, size_t size,
 	 * which case we will return NULL.  But such devices are uncommon.
 	 */
 	if (dma_mask <= DMA_BIT_MASK(32)) {
-		gfp |= GFP_DMA;
+		gfp |= GFP_DMA32;
 		node = 0;
 	}
 
@@ -509,39 +509,9 @@ EXPORT_SYMBOL(gx_pci_dma_map_ops);
 /* PCI DMA mapping functions for legacy PCI devices */
 
 #ifdef CONFIG_SWIOTLB
-static void *tile_swiotlb_alloc_coherent(struct device *dev, size_t size,
-					 dma_addr_t *dma_handle, gfp_t gfp,
-					 unsigned long attrs)
-{
-	gfp |= GFP_DMA;
-	return swiotlb_alloc_coherent(dev, size, dma_handle, gfp);
-}
-
-static void tile_swiotlb_free_coherent(struct device *dev, size_t size,
-				       void *vaddr, dma_addr_t dma_addr,
-				       unsigned long attrs)
-{
-	swiotlb_free_coherent(dev, size, vaddr, dma_addr);
-}
-
-static const struct dma_map_ops pci_swiotlb_dma_ops = {
-	.alloc = tile_swiotlb_alloc_coherent,
-	.free = tile_swiotlb_free_coherent,
-	.map_page = swiotlb_map_page,
-	.unmap_page = swiotlb_unmap_page,
-	.map_sg = swiotlb_map_sg_attrs,
-	.unmap_sg = swiotlb_unmap_sg_attrs,
-	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = swiotlb_sync_sg_for_device,
-	.dma_supported = swiotlb_dma_supported,
-	.mapping_error = swiotlb_dma_mapping_error,
-};
-
 static const struct dma_map_ops pci_hybrid_dma_ops = {
-	.alloc = tile_swiotlb_alloc_coherent,
-	.free = tile_swiotlb_free_coherent,
+	.alloc = swiotlb_alloc,
+	.free = swiotlb_free,
 	.map_page = tile_pci_dma_map_page,
 	.unmap_page = tile_pci_dma_unmap_page,
 	.map_sg = tile_pci_dma_map_sg,
@@ -552,7 +522,7 @@ static const struct dma_map_ops pci_hybrid_dma_ops = {
 	.sync_sg_for_device = tile_pci_dma_sync_sg_for_device,
 };
 
-const struct dma_map_ops *gx_legacy_pci_dma_map_ops = &pci_swiotlb_dma_ops;
+const struct dma_map_ops *gx_legacy_pci_dma_map_ops = &swiotlb_dma_ops;
 const struct dma_map_ops *gx_hybrid_pci_dma_map_ops = &pci_hybrid_dma_ops;
 #else
 const struct dma_map_ops *gx_legacy_pci_dma_map_ops;
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index ad83c1e66dbd..eb4e198f6f93 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -814,11 +814,11 @@ static void __init zone_sizes_init(void)
 #endif
 
 		if (start < dma_end) {
-			zones_size[ZONE_DMA] = min(zones_size[ZONE_NORMAL],
+			zones_size[ZONE_DMA32] = min(zones_size[ZONE_NORMAL],
 						   dma_end - start);
-			zones_size[ZONE_NORMAL] -= zones_size[ZONE_DMA];
+			zones_size[ZONE_NORMAL] -= zones_size[ZONE_DMA32];
 		} else {
-			zones_size[ZONE_DMA] = 0;
+			zones_size[ZONE_DMA32] = 0;
 		}
 
 		/* Take zone metadata from controller 0 if we're isolnode. */
@@ -830,7 +830,7 @@ static void __init zone_sizes_init(void)
 		       PFN_UP(node_percpu[i]));
 
 		/* Track the type of memory on each node */
-		if (zones_size[ZONE_NORMAL] || zones_size[ZONE_DMA])
+		if (zones_size[ZONE_NORMAL] || zones_size[ZONE_DMA32])
 			node_set_state(i, N_NORMAL_MEMORY);
 #ifdef CONFIG_HIGHMEM
 		if (end != start)
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index de3eae813e52..479d8033a801 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -163,11 +163,13 @@ static tilepro_bundle_bits rewrite_load_store_unaligned(
 	 * actual bad address in an SPR, which it doesn't.
 	 */
 	if (align_ctl == 0) {
-		siginfo_t info = {
-			.si_signo = SIGBUS,
-			.si_code = BUS_ADRALN,
-			.si_addr = addr
-		};
+		siginfo_t info;
+
+		clear_siginfo(&info);
+		info.si_signo = SIGBUS;
+		info.si_code = BUS_ADRALN;
+		info.si_addr = addr;
+
 		trace_unhandled_signal("unaligned trap", regs,
 				       (unsigned long)addr, SIGBUS);
 		force_sig_info(info.si_signo, &info, current);
@@ -210,11 +212,13 @@ static tilepro_bundle_bits rewrite_load_store_unaligned(
 	}
 
 	if (err) {
-		siginfo_t info = {
-			.si_signo = SIGBUS,
-			.si_code = BUS_ADRALN,
-			.si_addr = addr
-		};
+		siginfo_t info;
+
+		clear_siginfo(&info);
+		info.si_signo = SIGBUS;
+		info.si_code = BUS_ADRALN;
+		info.si_addr = addr;
+
 		trace_unhandled_signal("bad address for unaligned fixup", regs,
 				       (unsigned long)addr, SIGBUS);
 		force_sig_info(info.si_signo, &info, current);
diff --git a/arch/tile/kernel/sysfs.c b/arch/tile/kernel/sysfs.c
index 825867c53853..b09456a3d77a 100644
--- a/arch/tile/kernel/sysfs.c
+++ b/arch/tile/kernel/sysfs.c
@@ -38,7 +38,7 @@ static ssize_t chip_width_show(struct device *dev,
 {
 	return sprintf(page, "%u\n", smp_width);
 }
-static DEVICE_ATTR(chip_width, 0444, chip_width_show, NULL);
+static DEVICE_ATTR_RO(chip_width);
 
 static ssize_t chip_height_show(struct device *dev,
 				struct device_attribute *attr,
@@ -46,7 +46,7 @@ static ssize_t chip_height_show(struct device *dev,
 {
 	return sprintf(page, "%u\n", smp_height);
 }
-static DEVICE_ATTR(chip_height, 0444, chip_height_show, NULL);
+static DEVICE_ATTR_RO(chip_height);
 
 static ssize_t chip_serial_show(struct device *dev,
 				struct device_attribute *attr,
@@ -54,7 +54,7 @@ static ssize_t chip_serial_show(struct device *dev,
 {
 	return get_hv_confstr(page, HV_CONFSTR_CHIP_SERIAL_NUM);
 }
-static DEVICE_ATTR(chip_serial, 0444, chip_serial_show, NULL);
+static DEVICE_ATTR_RO(chip_serial);
 
 static ssize_t chip_revision_show(struct device *dev,
 				  struct device_attribute *attr,
@@ -62,7 +62,7 @@ static ssize_t chip_revision_show(struct device *dev,
 {
 	return get_hv_confstr(page, HV_CONFSTR_CHIP_REV);
 }
-static DEVICE_ATTR(chip_revision, 0444, chip_revision_show, NULL);
+static DEVICE_ATTR_RO(chip_revision);
 
 
 static ssize_t type_show(struct device *dev,
@@ -71,7 +71,7 @@ static ssize_t type_show(struct device *dev,
 {
 	return sprintf(page, "tilera\n");
 }
-static DEVICE_ATTR(type, 0444, type_show, NULL);
+static DEVICE_ATTR_RO(type);
 
 #define HV_CONF_ATTR(name, conf)					\
 	static ssize_t name ## _show(struct device *dev,		\
@@ -184,7 +184,7 @@ static ssize_t hv_stats_store(struct device *dev,
 	return n < 0 ? n : count;
 }
 
-static DEVICE_ATTR(hv_stats, 0644, hv_stats_show, hv_stats_store);
+static DEVICE_ATTR_RW(hv_stats);
 
 static int hv_stats_device_add(struct device *dev, struct subsys_interface *sif)
 {
diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c
index 9b08c6055f15..83a7186198d7 100644
--- a/arch/tile/kernel/traps.c
+++ b/arch/tile/kernel/traps.c
@@ -256,12 +256,14 @@ static int do_bpt(struct pt_regs *regs)
 void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 		       unsigned long reason)
 {
-	siginfo_t info = { 0 };
+	siginfo_t info;
 	int signo, code;
 	unsigned long address = 0;
 	tile_bundle_bits instr;
 	int is_kernel = !user_mode(regs);
 
+	clear_siginfo(&info);
+
 	/* Handle breakpoints, etc. */
 	if (is_kernel && fault_num == INT_ILL && do_bpt(regs))
 		return;
diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c
index 8149c38f67b6..77a0b6b6a2a1 100644
--- a/arch/tile/kernel/unaligned.c
+++ b/arch/tile/kernel/unaligned.c
@@ -980,11 +980,13 @@ void jit_bundle_gen(struct pt_regs *regs, tilegx_bundle_bits bundle,
 	}
 
 	if ((align_ctl == 0) || unexpected) {
-		siginfo_t info = {
-			.si_signo = SIGBUS,
-			.si_code = BUS_ADRALN,
-			.si_addr = (unsigned char __user *)0
-		};
+		siginfo_t info;
+
+		clear_siginfo(&info);
+		info.si_signo = SIGBUS;
+		info.si_code = BUS_ADRALN;
+		info.si_addr = (unsigned char __user *)0;
+
 		if (unaligned_printk)
 			pr_info("Unalign bundle: unexp @%llx, %llx\n",
 				(unsigned long long)regs->pc,
@@ -1396,11 +1398,12 @@ void jit_bundle_gen(struct pt_regs *regs, tilegx_bundle_bits bundle,
 				      &frag, sizeof(frag));
 		if (status) {
 			/* Fail to copy JIT into user land. send SIGSEGV. */
-			siginfo_t info = {
-				.si_signo = SIGSEGV,
-				.si_code = SEGV_MAPERR,
-				.si_addr = (void __user *)&jit_code_area[idx]
-			};
+			siginfo_t info;
+
+			clear_siginfo(&info);
+			info.si_signo = SIGSEGV;
+			info.si_code = SEGV_MAPERR;
+			info.si_addr = (void __user *)&jit_code_area[idx];
 
 			pr_warn("Unalign fixup: pid=%d %s jit_code_area=%llx\n",
 				current->pid, current->comm,
@@ -1511,11 +1514,12 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
 	 * If so, we will trigger SIGBUS.
 	 */
 	if ((regs->sp & 0x7) || (regs->ex1) || (align_ctl < 0)) {
-		siginfo_t info = {
-			.si_signo = SIGBUS,
-			.si_code = BUS_ADRALN,
-			.si_addr = (unsigned char __user *)0
-		};
+		siginfo_t info;
+
+		clear_siginfo(&info);
+		info.si_signo = SIGBUS;
+		info.si_code = BUS_ADRALN;
+		info.si_addr = (unsigned char __user *)0;
 
 		if (unaligned_printk)
 			pr_info("Unalign fixup: %d %llx @%llx\n",
@@ -1535,11 +1539,13 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
 	pc = (tilegx_bundle_bits __user *)(regs->pc);
 	if (get_user(bundle, pc) != 0) {
 		/* Probably never be here since pc is valid user address.*/
-		siginfo_t info = {
-			.si_signo = SIGSEGV,
-			.si_code = SEGV_MAPERR,
-			.si_addr = (void __user *)pc
-		};
+		siginfo_t info;
+
+		clear_siginfo(&info);
+		info.si_signo = SIGSEGV;
+		info.si_code = SEGV_MAPERR;
+		info.si_addr = (void __user *)pc;
+
 		pr_err("Couldn't read instruction at %p trying to step\n", pc);
 		trace_unhandled_signal("segfault in unalign fixup", regs,
 				       (unsigned long)info.si_addr, SIGSEGV);
diff --git a/arch/um/Makefile b/arch/um/Makefile
index b76fcce397a1..e54dda8a0363 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -116,8 +116,15 @@ endef
 KBUILD_KCONFIG := $(HOST_DIR)/um/Kconfig
 
 archheaders:
+	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-generic \
+	            kbuild-file=$(HOST_DIR)/include/asm/Kbuild \
+		    obj=$(HOST_DIR)/include/generated/asm
+	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-generic \
+	            kbuild-file=$(HOST_DIR)/include/uapi/asm/Kbuild \
+		    obj=$(HOST_DIR)/include/generated/uapi/asm
 	$(Q)$(MAKE) KBUILD_SRC= ARCH=$(HEADER_ARCH) archheaders
 
+
 archprepare: include/generated/user_constants.h
 
 LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static
diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c
index 12bdb5996bf5..7f9dbdbc4eb7 100644
--- a/arch/um/drivers/hostaudio_kern.c
+++ b/arch/um/drivers/hostaudio_kern.c
@@ -119,10 +119,10 @@ static ssize_t hostaudio_write(struct file *file, const char __user *buffer,
 	return err;
 }
 
-static unsigned int hostaudio_poll(struct file *file,
-				   struct poll_table_struct *wait)
+static __poll_t hostaudio_poll(struct file *file,
+				struct poll_table_struct *wait)
 {
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 
 #ifdef DEBUG
 	printk(KERN_DEBUG "hostaudio: poll called (unimplemented)\n");
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 50a32c33d729..bb5a196c3061 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,6 +1,6 @@
 generic-y += barrier.h
+generic-y += bpf_perf_event.h
 generic-y += bug.h
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += device.h
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index b668e351fd6c..fca34b2177e2 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -15,9 +15,10 @@ extern void uml_setup_stubs(struct mm_struct *mm);
 /*
  * Needed since we do not use the asm-generic/mm_hooks.h:
  */
-static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	uml_setup_stubs(mm);
+	return 0;
 }
 extern void arch_exit_mmap(struct mm_struct *mm);
 static inline void arch_unmap(struct mm_struct *mm,
diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
index 86942a492454..b58b746d3f2c 100644
--- a/arch/um/include/asm/processor-generic.h
+++ b/arch/um/include/asm/processor-generic.h
@@ -58,7 +58,10 @@ static inline void release_thread(struct task_struct *task)
 {
 }
 
-#define init_stack	(init_thread_union.stack)
+static inline void mm_copy_segments(struct mm_struct *from_mm,
+				    struct mm_struct *new_mm)
+{
+}
 
 /*
  * User space process size: 3GB (default).
diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h
index 9300f7630d2a..4eecd960ee8c 100644
--- a/arch/um/include/asm/thread_info.h
+++ b/arch/um/include/asm/thread_info.h
@@ -6,6 +6,9 @@
 #ifndef __UM_THREAD_INFO_H
 #define __UM_THREAD_INFO_H
 
+#define THREAD_SIZE_ORDER CONFIG_KERNEL_STACK_ORDER
+#define THREAD_SIZE ((1 << CONFIG_KERNEL_STACK_ORDER) * PAGE_SIZE)
+
 #ifndef __ASSEMBLY__
 
 #include <asm/types.h>
@@ -37,10 +40,6 @@ struct thread_info {
 	.real_thread = NULL,			\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
-#define THREAD_SIZE ((1 << CONFIG_KERNEL_STACK_ORDER) * PAGE_SIZE)
 /* how to get the thread information struct from C */
 static inline struct thread_info *current_thread_info(void)
 {
@@ -53,8 +52,6 @@ static inline struct thread_info *current_thread_info(void)
 	return ti;
 }
 
-#define THREAD_SIZE_ORDER CONFIG_KERNEL_STACK_ORDER
-
 #endif
 
 #define TIF_SYSCALL_TRACE	0	/* syscall trace active */
diff --git a/arch/um/include/asm/vmlinux.lds.h b/arch/um/include/asm/vmlinux.lds.h
new file mode 100644
index 000000000000..149494ae78ea
--- /dev/null
+++ b/arch/um/include/asm/vmlinux.lds.h
@@ -0,0 +1,2 @@
+#include <asm/thread_info.h>
+#include <asm-generic/vmlinux.lds.h>
diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S
index d417e3899700..5568cf882371 100644
--- a/arch/um/kernel/dyn.lds.S
+++ b/arch/um/kernel/dyn.lds.S
@@ -1,5 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <asm-generic/vmlinux.lds.h>
+#include <asm/vmlinux.lds.h>
 #include <asm/page.h>
 
 OUTPUT_FORMAT(ELF_FORMAT)
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 4e6fcb32620f..b2b02df9896e 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -150,7 +150,7 @@ static void show_segv_info(struct uml_pt_regs *regs)
 	if (!printk_ratelimit())
 		return;
 
-	printk("%s%s[%d]: segfault at %lx ip %p sp %p error %x",
+	printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x",
 		task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 		tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi),
 		(void *)UPT_IP(regs), (void *)UPT_SP(regs),
@@ -306,7 +306,7 @@ void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
 
 	arch_examine_signal(sig, regs);
 
-	memset(&clean_si, 0, sizeof(clean_si));
+	clear_siginfo(&clean_si);
 	clean_si.si_signo = si->si_signo;
 	clean_si.si_errno = si->si_errno;
 	clean_si.si_code = si->si_code;
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index f433690b9b37..a818ccef30ca 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -54,7 +54,7 @@ struct cpuinfo_um boot_cpu_data = {
 
 union thread_union cpu0_irqstack
 	__attribute__((__section__(".data..init_irqstack"))) =
-		{ INIT_THREAD_INFO(init_task) };
+		{ .thread_info = INIT_THREAD_INFO(init_task) };
 
 /* Changed in setup_arch, which is called in early boot */
 static char host_info[(__NEW_UTS_LEN + 1) * 5];
diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S
index 3d6ed6ba5b78..36b07ec09742 100644
--- a/arch/um/kernel/uml.lds.S
+++ b/arch/um/kernel/uml.lds.S
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#include <asm-generic/vmlinux.lds.h>
+#include <asm/vmlinux.lds.h>
 #include <asm/page.h>
 
 OUTPUT_FORMAT(ELF_FORMAT)
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index fda7e2153086..6f70c76c81fc 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -1,6 +1,5 @@
 generic-y += atomic.h
 generic-y += bugs.h
-generic-y += clkdev.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/unicore32/include/asm/dma-mapping.h b/arch/unicore32/include/asm/dma-mapping.h
index ac608c2f6af6..790bc2ef4af2 100644
--- a/arch/unicore32/include/asm/dma-mapping.h
+++ b/arch/unicore32/include/asm/dma-mapping.h
@@ -12,38 +12,11 @@
 #ifndef __UNICORE_DMA_MAPPING_H__
 #define __UNICORE_DMA_MAPPING_H__
 
-#ifdef __KERNEL__
-
-#include <linux/mm_types.h>
-#include <linux/scatterlist.h>
 #include <linux/swiotlb.h>
 
-extern const struct dma_map_ops swiotlb_dma_map_ops;
-
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return &swiotlb_dma_map_ops;
+	return &swiotlb_dma_ops;
 }
 
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (dev && dev->dma_mask)
-		return addr + size - 1 <= *dev->dma_mask;
-
-	return 1;
-}
-
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return paddr;
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return daddr;
-}
-
-static inline void dma_mark_clean(void *addr, size_t size) {}
-
-#endif /* __KERNEL__ */
 #endif
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index 59b06b48f27d..5c205a9cb5a6 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -81,9 +81,10 @@ do { \
 	} \
 } while (0)
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+				struct mm_struct *mm)
 {
+	return 0;
 }
 
 static inline void arch_unmap(struct mm_struct *mm,
diff --git a/arch/unicore32/include/asm/thread_info.h b/arch/unicore32/include/asm/thread_info.h
index e79ad6d5b5b2..5fb728f3b49a 100644
--- a/arch/unicore32/include/asm/thread_info.h
+++ b/arch/unicore32/include/asm/thread_info.h
@@ -87,9 +87,6 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,					\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /*
  * how to get the thread information struct from C
  */
diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild
index 759a71411169..8611ef980554 100644
--- a/arch/unicore32/include/uapi/asm/Kbuild
+++ b/arch/unicore32/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index ddaf78ae6854..2bc10b8e9cf4 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -23,7 +23,6 @@
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/interrupt.h>
-#include <linux/kallsyms.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/elfcore.h>
@@ -139,8 +138,8 @@ void __show_regs(struct pt_regs *regs)
 	char buf[64];
 
 	show_regs_print_info(KERN_DEFAULT);
-	print_symbol("PC is at %s\n", instruction_pointer(regs));
-	print_symbol("LR is at %s\n", regs->UCreg_lr);
+	printk("PC is at %pS\n", (void *)instruction_pointer(regs));
+	printk("LR is at %pS\n", (void *)regs->UCreg_lr);
 	printk(KERN_DEFAULT "pc : [<%08lx>]    lr : [<%08lx>]    psr: %08lx\n"
 	       "sp : %08lx  ip : %08lx  fp : %08lx\n",
 		regs->UCreg_pc, regs->UCreg_lr, regs->UCreg_asr,
diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c
index 5f25b39f04d4..c4ac6043ebb0 100644
--- a/arch/unicore32/kernel/traps.c
+++ b/arch/unicore32/kernel/traps.c
@@ -298,7 +298,6 @@ void abort(void)
 	/* if that doesn't kill us, halt */
 	panic("Oops failed to kill thread");
 }
-EXPORT_SYMBOL(abort);
 
 void __init trap_init(void)
 {
diff --git a/arch/unicore32/mm/Kconfig b/arch/unicore32/mm/Kconfig
index c256460cd363..e9154a59d561 100644
--- a/arch/unicore32/mm/Kconfig
+++ b/arch/unicore32/mm/Kconfig
@@ -42,6 +42,7 @@ config CPU_TLB_SINGLE_ENTRY_DISABLE
 
 config SWIOTLB
 	def_bool y
+	select DMA_DIRECT_OPS
 
 config IOMMU_HELPER
 	def_bool SWIOTLB
diff --git a/arch/unicore32/mm/Makefile b/arch/unicore32/mm/Makefile
index 681c0ef5ec9e..8106260583ab 100644
--- a/arch/unicore32/mm/Makefile
+++ b/arch/unicore32/mm/Makefile
@@ -6,8 +6,6 @@
 obj-y				:= extable.o fault.o init.o pgd.o mmu.o
 obj-y				+= flush.o ioremap.o
 
-obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
-
 obj-$(CONFIG_MODULES)		+= proc-syms.o
 
 obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
diff --git a/arch/unicore32/mm/dma-swiotlb.c b/arch/unicore32/mm/dma-swiotlb.c
deleted file mode 100644
index 525413d6690e..000000000000
--- a/arch/unicore32/mm/dma-swiotlb.c
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
- * Contains routines needed to support swiotlb for UniCore32.
- *
- * Copyright (C) 2010 Guan Xuetao
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-#include <linux/pci.h>
-#include <linux/cache.h>
-#include <linux/module.h>
-#include <linux/dma-mapping.h>
-#include <linux/swiotlb.h>
-#include <linux/bootmem.h>
-
-#include <asm/dma.h>
-
-static void *unicore_swiotlb_alloc_coherent(struct device *dev, size_t size,
-					    dma_addr_t *dma_handle, gfp_t flags,
-					    unsigned long attrs)
-{
-	return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
-}
-
-static void unicore_swiotlb_free_coherent(struct device *dev, size_t size,
-					  void *vaddr, dma_addr_t dma_addr,
-					  unsigned long attrs)
-{
-	swiotlb_free_coherent(dev, size, vaddr, dma_addr);
-}
-
-const struct dma_map_ops swiotlb_dma_map_ops = {
-	.alloc = unicore_swiotlb_alloc_coherent,
-	.free = unicore_swiotlb_free_coherent,
-	.map_sg = swiotlb_map_sg_attrs,
-	.unmap_sg = swiotlb_unmap_sg_attrs,
-	.dma_supported = swiotlb_dma_supported,
-	.map_page = swiotlb_map_page,
-	.unmap_page = swiotlb_unmap_page,
-	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = swiotlb_sync_sg_for_device,
-	.mapping_error = swiotlb_dma_mapping_error,
-};
-EXPORT_SYMBOL(swiotlb_dma_map_ops);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8eed3f94bfc7..72d5149bcaa1 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -54,8 +54,8 @@ config X86
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV			if X86_64
+	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API		if X86_64
-	# Causing hangs/crashes, see the commit that added this change for details.
 	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_SET_MEMORY
@@ -69,7 +69,6 @@ config X86
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_QUEUED_RWLOCKS
@@ -89,6 +88,7 @@ config X86
 	select GENERIC_CLOCKEVENTS_MIN_ADJUST
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_FIND_FIRST_BIT
 	select GENERIC_IOMAP
@@ -154,6 +154,7 @@ config X86
 	select HAVE_KERNEL_XZ
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
+	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_KRETPROBES
 	select HAVE_KVM
 	select HAVE_LIVEPATCH			if X86_64
@@ -429,6 +430,19 @@ config GOLDFISH
        def_bool y
        depends on X86_GOLDFISH
 
+config RETPOLINE
+	bool "Avoid speculative indirect branches in kernel"
+	default y
+	help
+	  Compile kernel with the retpoline compiler options to guard against
+	  kernel-to-user data leaks by avoiding speculative indirect
+	  branches. Requires a compiler with -mindirect-branch=thunk-extern
+	  support for full protection. The kernel may run slower.
+
+	  Without compiler support, at least indirect branches in assembler
+	  code are eliminated. Since this includes the syscall entry path,
+	  it is not entirely pointless.
+
 config INTEL_RDT
 	bool "Intel Resource Director Technology support"
 	default n
@@ -797,6 +811,15 @@ config PARAVIRT_TIME_ACCOUNTING
 config PARAVIRT_CLOCK
 	bool
 
+config JAILHOUSE_GUEST
+	bool "Jailhouse non-root cell support"
+	depends on X86_64 && PCI
+	select X86_PM_TIMER
+	---help---
+	  This option allows to run Linux as guest in a Jailhouse non-root
+	  cell. You can leave this option disabled if you only want to start
+	  Jailhouse and run Linux afterwards in the root cell.
+
 endif #HYPERVISOR_GUEST
 
 config NO_BOOTMEM
@@ -926,7 +949,8 @@ config MAXSMP
 config NR_CPUS
 	int "Maximum number of CPUs" if SMP && !MAXSMP
 	range 2 8 if SMP && X86_32 && !X86_BIGSMP
-	range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK
+	range 2 64 if SMP && X86_32 && X86_BIGSMP
+	range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64
 	range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64
 	default "1" if !SMP
 	default "8192" if MAXSMP
@@ -1241,9 +1265,9 @@ config MICROCODE
 	  CONFIG_BLK_DEV_INITRD in order for the loader to be able to scan the
 	  initrd for microcode blobs.
 
-	  In addition, you can build-in the microcode into the kernel. For that you
-	  need to enable FIRMWARE_IN_KERNEL and add the vendor-supplied microcode
-	  to the CONFIG_EXTRA_FIRMWARE config option.
+	  In addition, you can build the microcode into the kernel. For that you
+	  need to add the vendor-supplied microcode to the CONFIG_EXTRA_FIRMWARE
+	  config option.
 
 config MICROCODE_INTEL
 	bool "Intel microcode loading support"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 6293a8768a91..192e4d2f9efc 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -169,14 +169,6 @@ config IOMMU_DEBUG
 	  options. See Documentation/x86/x86_64/boot-options.txt for more
 	  details.
 
-config IOMMU_STRESS
-	bool "Enable IOMMU stress-test mode"
-	---help---
-	  This option disables various optimizations in IOMMU related
-	  code to do real stress testing of the IOMMU code. This option
-	  will cause a performance drop and should only be enabled for
-	  testing.
-
 config IOMMU_LEAK
 	bool "IOMMU leak tracing"
 	depends on IOMMU_DEBUG && DMA_API_DEBUG
@@ -400,6 +392,7 @@ config UNWINDER_FRAME_POINTER
 config UNWINDER_GUESS
 	bool "Guess unwinder"
 	depends on EXPERT
+	depends on !STACKDEPOT
 	---help---
 	  This option enables the "guess" unwinder for unwinding kernel stack
 	  traces.  It scans the stack and reports every kernel text address it
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 3e73bc255e4e..fad55160dcb9 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -230,6 +230,14 @@ KBUILD_CFLAGS += -Wno-sign-compare
 #
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 
+# Avoid indirect branches in kernel to deal with Spectre
+ifdef CONFIG_RETPOLINE
+    RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
+    ifneq ($(RETPOLINE_CFLAGS),)
+        KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE
+    endif
+endif
+
 archscripts: scripts_basic
 	$(Q)$(MAKE) $(build)=arch/x86/tools relocs
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 1e9c322e973a..f25e1530e064 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -80,6 +80,7 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o
 ifdef CONFIG_X86_64
 	vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o
 	vmlinux-objs-y += $(obj)/mem_encrypt.o
+	vmlinux-objs-y += $(obj)/pgtable_64.o
 endif
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index e56dbc67e837..353e20c3f114 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -999,6 +999,7 @@ struct boot_params *efi_main(struct efi_config *c,
 
 	/* Ask the firmware to clear memory on unclean shutdown */
 	efi_enable_reset_attack_mitigation(sys_table);
+	efi_retrieve_tpm2_eventlog(sys_table);
 
 	setup_graphics(boot_params);
 
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 20919b4f3133..fc313e29fe2c 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -305,10 +305,18 @@ ENTRY(startup_64)
 	leaq	boot_stack_end(%rbx), %rsp
 
 #ifdef CONFIG_X86_5LEVEL
-	/* Check if 5-level paging has already enabled */
-	movq	%cr4, %rax
-	testl	$X86_CR4_LA57, %eax
-	jnz	lvl5
+	/*
+	 * Check if we need to enable 5-level paging.
+	 * RSI holds real mode data and need to be preserved across
+	 * a function call.
+	 */
+	pushq	%rsi
+	call	l5_paging_required
+	popq	%rsi
+
+	/* If l5_paging_required() returned zero, we're done here. */
+	cmpq	$0, %rax
+	je	lvl5
 
 	/*
 	 * At this point we are in long mode with 4-level paging enabled,
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index b50c42455e25..98761a1576ce 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -169,6 +169,16 @@ void __puthex(unsigned long value)
 	}
 }
 
+static bool l5_supported(void)
+{
+	/* Check if leaf 7 is supported. */
+	if (native_cpuid_eax(0) < 7)
+		return 0;
+
+	/* Check if la57 is supported. */
+	return native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31));
+}
+
 #if CONFIG_X86_NEED_RELOCS
 static void handle_relocations(void *output, unsigned long output_len,
 			       unsigned long virt_addr)
@@ -362,6 +372,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	console_init();
 	debug_putstr("early console in extract_kernel\n");
 
+	if (IS_ENABLED(CONFIG_X86_5LEVEL) && !l5_supported()) {
+		error("This linux kernel as configured requires 5-level paging\n"
+			"This CPU does not support the required 'cr4.la57' feature\n"
+			"Unable to boot - please use a kernel appropriate for your CPU\n");
+	}
+
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c
index d5364ca2e3f9..b5e5e02f8cde 100644
--- a/arch/x86/boot/compressed/pagetable.c
+++ b/arch/x86/boot/compressed/pagetable.c
@@ -23,6 +23,9 @@
  */
 #undef CONFIG_AMD_MEM_ENCRYPT
 
+/* No PAGE_TABLE_ISOLATION support needed either: */
+#undef CONFIG_PAGE_TABLE_ISOLATION
+
 #include "misc.h"
 
 /* These actually do the work of building the kernel identity maps. */
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
new file mode 100644
index 000000000000..b4469a37e9a1
--- /dev/null
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -0,0 +1,28 @@
+#include <asm/processor.h>
+
+/*
+ * __force_order is used by special_insns.h asm code to force instruction
+ * serialization.
+ *
+ * It is not referenced from the code, but GCC < 5 with -fPIE would fail
+ * due to an undefined symbol. Define it to make these ancient GCCs work.
+ */
+unsigned long __force_order;
+
+int l5_paging_required(void)
+{
+	/* Check if leaf 7 is supported. */
+
+	if (native_cpuid_eax(0) < 7)
+		return 0;
+
+	/* Check if la57 is supported. */
+	if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
+		return 0;
+
+	/* Check if 5-level paging has already been enabled. */
+	if (native_read_cr4() & X86_CR4_LA57)
+		return 0;
+
+	return 1;
+}
diff --git a/arch/x86/boot/genimage.sh b/arch/x86/boot/genimage.sh
index 49f4970f693b..6a10d52a4145 100644
--- a/arch/x86/boot/genimage.sh
+++ b/arch/x86/boot/genimage.sh
@@ -44,9 +44,9 @@ FDINITRD=$6
 
 # Make sure the files actually exist
 verify "$FBZIMAGE"
-verify "$MTOOLSRC"
 
 genbzdisk() {
+	verify "$MTOOLSRC"
 	mformat a:
 	syslinux $FIMAGE
 	echo "$KCMDLINE" | mcopy - a:syslinux.cfg
@@ -57,6 +57,7 @@ genbzdisk() {
 }
 
 genfdimage144() {
+	verify "$MTOOLSRC"
 	dd if=/dev/zero of=$FIMAGE bs=1024 count=1440 2> /dev/null
 	mformat v:
 	syslinux $FIMAGE
@@ -68,6 +69,7 @@ genfdimage144() {
 }
 
 genfdimage288() {
+	verify "$MTOOLSRC"
 	dd if=/dev/zero of=$FIMAGE bs=1024 count=2880 2> /dev/null
 	mformat w:
 	syslinux $FIMAGE
@@ -78,39 +80,43 @@ genfdimage288() {
 	mcopy $FBZIMAGE w:linux
 }
 
-genisoimage() {
+geniso() {
 	tmp_dir=`dirname $FIMAGE`/isoimage
 	rm -rf $tmp_dir
 	mkdir $tmp_dir
-	for i in lib lib64 share end ; do
+	for i in lib lib64 share ; do
 		for j in syslinux ISOLINUX ; do
 			if [ -f /usr/$i/$j/isolinux.bin ] ; then
 				isolinux=/usr/$i/$j/isolinux.bin
-				cp $isolinux $tmp_dir
 			fi
 		done
 		for j in syslinux syslinux/modules/bios ; do
 			if [ -f /usr/$i/$j/ldlinux.c32 ]; then
 				ldlinux=/usr/$i/$j/ldlinux.c32
-				cp $ldlinux $tmp_dir
 			fi
 		done
 		if [ -n "$isolinux" -a -n "$ldlinux" ] ; then
 			break
 		fi
-		if [ $i = end -a -z "$isolinux" ] ; then
-			echo 'Need an isolinux.bin file, please install syslinux/isolinux.'
-			exit 1
-		fi
 	done
+	if [ -z "$isolinux" ] ; then
+		echo 'Need an isolinux.bin file, please install syslinux/isolinux.'
+		exit 1
+	fi
+	if [ -z "$ldlinux" ] ; then
+		echo 'Need an ldlinux.c32 file, please install syslinux/isolinux.'
+		exit 1
+	fi
+	cp $isolinux $tmp_dir
+	cp $ldlinux $tmp_dir
 	cp $FBZIMAGE $tmp_dir/linux
 	echo "$KCMDLINE" > $tmp_dir/isolinux.cfg
 	if [ -f "$FDINITRD" ] ; then
 		cp "$FDINITRD" $tmp_dir/initrd.img
 	fi
-	mkisofs -J -r -input-charset=utf-8 -quiet -o $FIMAGE -b isolinux.bin \
-		-c boot.cat -no-emul-boot -boot-load-size 4 -boot-info-table \
-		$tmp_dir
+	genisoimage -J -r -input-charset=utf-8 -quiet -o $FIMAGE \
+		-b isolinux.bin -c boot.cat -no-emul-boot -boot-load-size 4 \
+		-boot-info-table $tmp_dir
 	isohybrid $FIMAGE 2>/dev/null || true
 	rm -rf $tmp_dir
 }
@@ -119,6 +125,6 @@ case $1 in
 	bzdisk)     genbzdisk;;
 	fdimage144) genfdimage144;;
 	fdimage288) genfdimage288;;
-	isoimage)   genisoimage;;
+	isoimage)   geniso;;
 	*)          echo 'Unknown image format'; exit 1;
 esac
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 16627fec80b2..12e8484a8ee7 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -32,6 +32,7 @@
 #include <linux/linkage.h>
 #include <asm/inst.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 /*
  * The following macros are used to move an (un)aligned 16 byte value to/from
@@ -89,30 +90,6 @@ SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100
 ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
             .octa 0x00000000000000000000000000000000
 
-.section .rodata
-.align 16
-.type aad_shift_arr, @object
-.size aad_shift_arr, 272
-aad_shift_arr:
-        .octa     0xffffffffffffffffffffffffffffffff
-        .octa     0xffffffffffffffffffffffffffffff0C
-        .octa     0xffffffffffffffffffffffffffff0D0C
-        .octa     0xffffffffffffffffffffffffff0E0D0C
-        .octa     0xffffffffffffffffffffffff0F0E0D0C
-        .octa     0xffffffffffffffffffffff0C0B0A0908
-        .octa     0xffffffffffffffffffff0D0C0B0A0908
-        .octa     0xffffffffffffffffff0E0D0C0B0A0908
-        .octa     0xffffffffffffffff0F0E0D0C0B0A0908
-        .octa     0xffffffffffffff0C0B0A090807060504
-        .octa     0xffffffffffff0D0C0B0A090807060504
-        .octa     0xffffffffff0E0D0C0B0A090807060504
-        .octa     0xffffffff0F0E0D0C0B0A090807060504
-        .octa     0xffffff0C0B0A09080706050403020100
-        .octa     0xffff0D0C0B0A09080706050403020100
-        .octa     0xff0E0D0C0B0A09080706050403020100
-        .octa     0x0F0E0D0C0B0A09080706050403020100
-
-
 .text
 
 
@@ -256,6 +233,37 @@ aad_shift_arr:
 	pxor      \TMP1, \GH            # result is in TMP1
 .endm
 
+# Reads DLEN bytes starting at DPTR and stores in XMMDst
+# where 0 < DLEN < 16
+# Clobbers %rax, DLEN and XMM1
+.macro READ_PARTIAL_BLOCK DPTR DLEN XMM1 XMMDst
+        cmp $8, \DLEN
+        jl _read_lt8_\@
+        mov (\DPTR), %rax
+        MOVQ_R64_XMM %rax, \XMMDst
+        sub $8, \DLEN
+        jz _done_read_partial_block_\@
+	xor %eax, %eax
+_read_next_byte_\@:
+        shl $8, %rax
+        mov 7(\DPTR, \DLEN, 1), %al
+        dec \DLEN
+        jnz _read_next_byte_\@
+        MOVQ_R64_XMM %rax, \XMM1
+	pslldq $8, \XMM1
+        por \XMM1, \XMMDst
+	jmp _done_read_partial_block_\@
+_read_lt8_\@:
+	xor %eax, %eax
+_read_next_byte_lt8_\@:
+        shl $8, %rax
+        mov -1(\DPTR, \DLEN, 1), %al
+        dec \DLEN
+        jnz _read_next_byte_lt8_\@
+        MOVQ_R64_XMM %rax, \XMMDst
+_done_read_partial_block_\@:
+.endm
+
 /*
 * if a = number of total plaintext bytes
 * b = floor(a/16)
@@ -272,62 +280,30 @@ aad_shift_arr:
 XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation
         MOVADQ     SHUF_MASK(%rip), %xmm14
 	mov	   arg7, %r10           # %r10 = AAD
-	mov	   arg8, %r12           # %r12 = aadLen
-	mov	   %r12, %r11
+	mov	   arg8, %r11           # %r11 = aadLen
 	pxor	   %xmm\i, %xmm\i
 	pxor       \XMM2, \XMM2
 
 	cmp	   $16, %r11
-	jl	   _get_AAD_rest8\num_initial_blocks\operation
+	jl	   _get_AAD_rest\num_initial_blocks\operation
 _get_AAD_blocks\num_initial_blocks\operation:
 	movdqu	   (%r10), %xmm\i
 	PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data
 	pxor	   %xmm\i, \XMM2
 	GHASH_MUL  \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
 	add	   $16, %r10
-	sub	   $16, %r12
 	sub	   $16, %r11
 	cmp	   $16, %r11
 	jge	   _get_AAD_blocks\num_initial_blocks\operation
 
 	movdqu	   \XMM2, %xmm\i
+
+	/* read the last <16B of AAD */
+_get_AAD_rest\num_initial_blocks\operation:
 	cmp	   $0, %r11
 	je	   _get_AAD_done\num_initial_blocks\operation
 
-	pxor	   %xmm\i,%xmm\i
-
-	/* read the last <16B of AAD. since we have at least 4B of
-	data right after the AAD (the ICV, and maybe some CT), we can
-	read 4B/8B blocks safely, and then get rid of the extra stuff */
-_get_AAD_rest8\num_initial_blocks\operation:
-	cmp	   $4, %r11
-	jle	   _get_AAD_rest4\num_initial_blocks\operation
-	movq	   (%r10), \TMP1
-	add	   $8, %r10
-	sub	   $8, %r11
-	pslldq	   $8, \TMP1
-	psrldq	   $8, %xmm\i
-	pxor	   \TMP1, %xmm\i
-	jmp	   _get_AAD_rest8\num_initial_blocks\operation
-_get_AAD_rest4\num_initial_blocks\operation:
-	cmp	   $0, %r11
-	jle	   _get_AAD_rest0\num_initial_blocks\operation
-	mov	   (%r10), %eax
-	movq	   %rax, \TMP1
-	add	   $4, %r10
-	sub	   $4, %r10
-	pslldq	   $12, \TMP1
-	psrldq	   $4, %xmm\i
-	pxor	   \TMP1, %xmm\i
-_get_AAD_rest0\num_initial_blocks\operation:
-	/* finalize: shift out the extra bytes we read, and align
-	left. since pslldq can only shift by an immediate, we use
-	vpshufb and an array of shuffle masks */
-	movq	   %r12, %r11
-	salq	   $4, %r11
-	movdqu	   aad_shift_arr(%r11), \TMP1
-	PSHUFB_XMM \TMP1, %xmm\i
-_get_AAD_rest_final\num_initial_blocks\operation:
+	READ_PARTIAL_BLOCK %r10, %r11, \TMP1, %xmm\i
 	PSHUFB_XMM   %xmm14, %xmm\i # byte-reflect the AAD data
 	pxor	   \XMM2, %xmm\i
 	GHASH_MUL  %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
@@ -531,62 +507,30 @@ _initial_blocks_done\num_initial_blocks\operation:
 XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation
         MOVADQ     SHUF_MASK(%rip), %xmm14
 	mov	   arg7, %r10           # %r10 = AAD
-	mov	   arg8, %r12           # %r12 = aadLen
-	mov	   %r12, %r11
+	mov	   arg8, %r11           # %r11 = aadLen
 	pxor	   %xmm\i, %xmm\i
 	pxor	   \XMM2, \XMM2
 
 	cmp	   $16, %r11
-	jl	   _get_AAD_rest8\num_initial_blocks\operation
+	jl	   _get_AAD_rest\num_initial_blocks\operation
 _get_AAD_blocks\num_initial_blocks\operation:
 	movdqu	   (%r10), %xmm\i
 	PSHUFB_XMM   %xmm14, %xmm\i # byte-reflect the AAD data
 	pxor	   %xmm\i, \XMM2
 	GHASH_MUL  \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
 	add	   $16, %r10
-	sub	   $16, %r12
 	sub	   $16, %r11
 	cmp	   $16, %r11
 	jge	   _get_AAD_blocks\num_initial_blocks\operation
 
 	movdqu	   \XMM2, %xmm\i
+
+	/* read the last <16B of AAD */
+_get_AAD_rest\num_initial_blocks\operation:
 	cmp	   $0, %r11
 	je	   _get_AAD_done\num_initial_blocks\operation
 
-	pxor	   %xmm\i,%xmm\i
-
-	/* read the last <16B of AAD. since we have at least 4B of
-	data right after the AAD (the ICV, and maybe some PT), we can
-	read 4B/8B blocks safely, and then get rid of the extra stuff */
-_get_AAD_rest8\num_initial_blocks\operation:
-	cmp	   $4, %r11
-	jle	   _get_AAD_rest4\num_initial_blocks\operation
-	movq	   (%r10), \TMP1
-	add	   $8, %r10
-	sub	   $8, %r11
-	pslldq	   $8, \TMP1
-	psrldq	   $8, %xmm\i
-	pxor	   \TMP1, %xmm\i
-	jmp	   _get_AAD_rest8\num_initial_blocks\operation
-_get_AAD_rest4\num_initial_blocks\operation:
-	cmp	   $0, %r11
-	jle	   _get_AAD_rest0\num_initial_blocks\operation
-	mov	   (%r10), %eax
-	movq	   %rax, \TMP1
-	add	   $4, %r10
-	sub	   $4, %r10
-	pslldq	   $12, \TMP1
-	psrldq	   $4, %xmm\i
-	pxor	   \TMP1, %xmm\i
-_get_AAD_rest0\num_initial_blocks\operation:
-	/* finalize: shift out the extra bytes we read, and align
-	left. since pslldq can only shift by an immediate, we use
-	vpshufb and an array of shuffle masks */
-	movq	   %r12, %r11
-	salq	   $4, %r11
-	movdqu	   aad_shift_arr(%r11), \TMP1
-	PSHUFB_XMM \TMP1, %xmm\i
-_get_AAD_rest_final\num_initial_blocks\operation:
+	READ_PARTIAL_BLOCK %r10, %r11, \TMP1, %xmm\i
 	PSHUFB_XMM   %xmm14, %xmm\i # byte-reflect the AAD data
 	pxor	   \XMM2, %xmm\i
 	GHASH_MUL  %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
@@ -1385,14 +1329,6 @@ _esb_loop_\@:
 *
 *                        AAD Format with 64-bit Extended Sequence Number
 *
-* aadLen:
-*       from the definition of the spec, aadLen can only be 8 or 12 bytes.
-*       The code supports 16 too but for other sizes, the code will fail.
-*
-* TLen:
-*       from the definition of the spec, TLen can only be 8, 12 or 16 bytes.
-*       For other sizes, the code will fail.
-*
 * poly = x^128 + x^127 + x^126 + x^121 + 1
 *
 *****************************************************************************/
@@ -1486,19 +1422,16 @@ _zero_cipher_left_decrypt:
 	PSHUFB_XMM %xmm10, %xmm0
 
 	ENCRYPT_SINGLE_BLOCK  %xmm0, %xmm1    # E(K, Yn)
-	sub $16, %r11
-	add %r13, %r11
-	movdqu (%arg3,%r11,1), %xmm1   # receive the last <16 byte block
-	lea SHIFT_MASK+16(%rip), %r12
-	sub %r13, %r12
-# adjust the shuffle mask pointer to be able to shift 16-%r13 bytes
-# (%r13 is the number of bytes in plaintext mod 16)
-	movdqu (%r12), %xmm2           # get the appropriate shuffle mask
-	PSHUFB_XMM %xmm2, %xmm1            # right shift 16-%r13 butes
 
+	lea (%arg3,%r11,1), %r10
+	mov %r13, %r12
+	READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1
+
+	lea ALL_F+16(%rip), %r12
+	sub %r13, %r12
 	movdqa  %xmm1, %xmm2
 	pxor %xmm1, %xmm0            # Ciphertext XOR E(K, Yn)
-	movdqu ALL_F-SHIFT_MASK(%r12), %xmm1
+	movdqu (%r12), %xmm1
 	# get the appropriate mask to mask out top 16-%r13 bytes of %xmm0
 	pand %xmm1, %xmm0            # mask out top 16-%r13 bytes of %xmm0
 	pand    %xmm1, %xmm2
@@ -1507,9 +1440,6 @@ _zero_cipher_left_decrypt:
 
 	pxor %xmm2, %xmm8
 	GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
-	          # GHASH computation for the last <16 byte block
-	sub %r13, %r11
-	add $16, %r11
 
         # output %r13 bytes
 	MOVQ_R64_XMM	%xmm0, %rax
@@ -1663,14 +1593,6 @@ ENDPROC(aesni_gcm_dec)
 *
 *                         AAD Format with 64-bit Extended Sequence Number
 *
-* aadLen:
-*       from the definition of the spec, aadLen can only be 8 or 12 bytes.
-*       The code supports 16 too but for other sizes, the code will fail.
-*
-* TLen:
-*       from the definition of the spec, TLen can only be 8, 12 or 16 bytes.
-*       For other sizes, the code will fail.
-*
 * poly = x^128 + x^127 + x^126 + x^121 + 1
 ***************************************************************************/
 ENTRY(aesni_gcm_enc)
@@ -1763,19 +1685,16 @@ _zero_cipher_left_encrypt:
         movdqa SHUF_MASK(%rip), %xmm10
 	PSHUFB_XMM %xmm10, %xmm0
 
-
 	ENCRYPT_SINGLE_BLOCK	%xmm0, %xmm1        # Encrypt(K, Yn)
-	sub $16, %r11
-	add %r13, %r11
-	movdqu (%arg3,%r11,1), %xmm1     # receive the last <16 byte blocks
-	lea SHIFT_MASK+16(%rip), %r12
+
+	lea (%arg3,%r11,1), %r10
+	mov %r13, %r12
+	READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1
+
+	lea ALL_F+16(%rip), %r12
 	sub %r13, %r12
-	# adjust the shuffle mask pointer to be able to shift 16-r13 bytes
-	# (%r13 is the number of bytes in plaintext mod 16)
-	movdqu	(%r12), %xmm2           # get the appropriate shuffle mask
-	PSHUFB_XMM	%xmm2, %xmm1            # shift right 16-r13 byte
 	pxor	%xmm1, %xmm0            # Plaintext XOR Encrypt(K, Yn)
-	movdqu	ALL_F-SHIFT_MASK(%r12), %xmm1
+	movdqu	(%r12), %xmm1
 	# get the appropriate mask to mask out top 16-r13 bytes of xmm0
 	pand	%xmm1, %xmm0            # mask out top 16-r13 bytes of xmm0
         movdqa SHUF_MASK(%rip), %xmm10
@@ -1784,9 +1703,6 @@ _zero_cipher_left_encrypt:
 	pxor	%xmm0, %xmm8
 	GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
 	# GHASH computation for the last <16 byte block
-	sub	%r13, %r11
-	add	$16, %r11
-
 	movdqa SHUF_MASK(%rip), %xmm10
 	PSHUFB_XMM %xmm10, %xmm0
 
@@ -2884,7 +2800,7 @@ ENTRY(aesni_xts_crypt8)
 	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)
 
-	call *%r11
+	CALL_NOSPEC %r11
 
 	movdqu 0x00(OUTP), INC
 	pxor INC, STATE1
@@ -2929,7 +2845,7 @@ ENTRY(aesni_xts_crypt8)
 	_aesni_gf128mul_x_ble()
 	movups IV, (IVP)
 
-	call *%r11
+	CALL_NOSPEC %r11
 
 	movdqu 0x40(OUTP), INC
 	pxor INC, STATE1
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 3bf3dcf29825..34cf1c1f8c98 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -690,8 +690,8 @@ static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key,
 	       rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
 }
 
-static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key,
-			   unsigned int key_len)
+static int gcmaes_wrapper_set_key(struct crypto_aead *parent, const u8 *key,
+				  unsigned int key_len)
 {
 	struct cryptd_aead **ctx = crypto_aead_ctx(parent);
 	struct cryptd_aead *cryptd_tfm = *ctx;
@@ -716,8 +716,8 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead,
 
 /* This is the Integrity Check Value (aka the authentication tag length and can
  * be 8, 12 or 16 bytes long. */
-static int rfc4106_set_authsize(struct crypto_aead *parent,
-				unsigned int authsize)
+static int gcmaes_wrapper_set_authsize(struct crypto_aead *parent,
+				       unsigned int authsize)
 {
 	struct cryptd_aead **ctx = crypto_aead_ctx(parent);
 	struct cryptd_aead *cryptd_tfm = *ctx;
@@ -824,7 +824,7 @@ static int gcmaes_decrypt(struct aead_request *req, unsigned int assoclen,
 	if (sg_is_last(req->src) &&
 	    (!PageHighMem(sg_page(req->src)) ||
 	    req->src->offset + req->src->length <= PAGE_SIZE) &&
-	    sg_is_last(req->dst) &&
+	    sg_is_last(req->dst) && req->dst->length &&
 	    (!PageHighMem(sg_page(req->dst)) ||
 	    req->dst->offset + req->dst->length <= PAGE_SIZE)) {
 		one_entry_in_sg = 1;
@@ -929,7 +929,7 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 			      aes_ctx);
 }
 
-static int rfc4106_encrypt(struct aead_request *req)
+static int gcmaes_wrapper_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
@@ -945,7 +945,7 @@ static int rfc4106_encrypt(struct aead_request *req)
 	return crypto_aead_encrypt(req);
 }
 
-static int rfc4106_decrypt(struct aead_request *req)
+static int gcmaes_wrapper_decrypt(struct aead_request *req)
 {
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
@@ -1117,7 +1117,7 @@ static int generic_gcmaes_decrypt(struct aead_request *req)
 {
 	__be32 counter = cpu_to_be32(1);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+	struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm);
 	void *aes_ctx = &(ctx->aes_key_expanded);
 	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
 
@@ -1128,6 +1128,30 @@ static int generic_gcmaes_decrypt(struct aead_request *req)
 			      aes_ctx);
 }
 
+static int generic_gcmaes_init(struct crypto_aead *aead)
+{
+	struct cryptd_aead *cryptd_tfm;
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_tfm = cryptd_alloc_aead("__driver-generic-gcm-aes-aesni",
+				       CRYPTO_ALG_INTERNAL,
+				       CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+
+	*ctx = cryptd_tfm;
+	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
+
+	return 0;
+}
+
+static void generic_gcmaes_exit(struct crypto_aead *aead)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_free_aead(*ctx);
+}
+
 static struct aead_alg aesni_aead_algs[] = { {
 	.setkey			= common_rfc4106_set_key,
 	.setauthsize		= common_rfc4106_set_authsize,
@@ -1147,10 +1171,10 @@ static struct aead_alg aesni_aead_algs[] = { {
 }, {
 	.init			= rfc4106_init,
 	.exit			= rfc4106_exit,
-	.setkey			= rfc4106_set_key,
-	.setauthsize		= rfc4106_set_authsize,
-	.encrypt		= rfc4106_encrypt,
-	.decrypt		= rfc4106_decrypt,
+	.setkey			= gcmaes_wrapper_set_key,
+	.setauthsize		= gcmaes_wrapper_set_authsize,
+	.encrypt		= gcmaes_wrapper_encrypt,
+	.decrypt		= gcmaes_wrapper_decrypt,
 	.ivsize			= GCM_RFC4106_IV_SIZE,
 	.maxauthsize		= 16,
 	.base = {
@@ -1170,13 +1194,31 @@ static struct aead_alg aesni_aead_algs[] = { {
 	.ivsize			= GCM_AES_IV_SIZE,
 	.maxauthsize		= 16,
 	.base = {
+		.cra_name		= "__generic-gcm-aes-aesni",
+		.cra_driver_name	= "__driver-generic-gcm-aes-aesni",
+		.cra_priority		= 0,
+		.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct generic_gcmaes_ctx),
+		.cra_alignmask		= AESNI_ALIGN - 1,
+		.cra_module		= THIS_MODULE,
+	},
+}, {
+	.init			= generic_gcmaes_init,
+	.exit			= generic_gcmaes_exit,
+	.setkey			= gcmaes_wrapper_set_key,
+	.setauthsize		= gcmaes_wrapper_set_authsize,
+	.encrypt		= gcmaes_wrapper_encrypt,
+	.decrypt		= gcmaes_wrapper_decrypt,
+	.ivsize			= GCM_AES_IV_SIZE,
+	.maxauthsize		= 16,
+	.base = {
 		.cra_name		= "gcm(aes)",
 		.cra_driver_name	= "generic-gcm-aesni",
 		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_ASYNC,
 		.cra_blocksize		= 1,
-		.cra_ctxsize		= sizeof(struct generic_gcmaes_ctx),
-		.cra_alignmask		= AESNI_ALIGN - 1,
+		.cra_ctxsize		= sizeof(struct cryptd_aead *),
 		.cra_module		= THIS_MODULE,
 	},
 } };
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index f7c495e2863c..a14af6eb09cb 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -17,6 +17,7 @@
 
 #include <linux/linkage.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -1227,7 +1228,7 @@ camellia_xts_crypt_16way:
 	vpxor 14 * 16(%rax), %xmm15, %xmm14;
 	vpxor 15 * 16(%rax), %xmm15, %xmm15;
 
-	call *%r9;
+	CALL_NOSPEC %r9;
 
 	addq $(16 * 16), %rsp;
 
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index eee5b3982cfd..b66bbfa62f50 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -12,6 +12,7 @@
 
 #include <linux/linkage.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -1343,7 +1344,7 @@ camellia_xts_crypt_32way:
 	vpxor 14 * 32(%rax), %ymm15, %ymm14;
 	vpxor 15 * 32(%rax), %ymm15, %ymm15;
 
-	call *%r9;
+	CALL_NOSPEC %r9;
 
 	addq $(16 * 32), %rsp;
 
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 1e6af1b35f7b..dce7c5d39c2f 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -107,7 +107,6 @@ static struct skcipher_alg alg = {
 	.base.cra_priority	= 300,
 	.base.cra_blocksize	= 1,
 	.base.cra_ctxsize	= sizeof(struct chacha20_ctx),
-	.base.cra_alignmask	= sizeof(u32) - 1,
 	.base.cra_module	= THIS_MODULE,
 
 	.min_keysize		= CHACHA20_KEY_SIZE,
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 27226df3f7d8..c8d9cdacbf10 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -162,6 +162,7 @@ static struct shash_alg alg = {
 			.cra_name		= "crc32",
 			.cra_driver_name	= "crc32-pclmul",
 			.cra_priority		= 200,
+			.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize		= CHKSUM_BLOCK_SIZE,
 			.cra_ctxsize		= sizeof(u32),
 			.cra_module		= THIS_MODULE,
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index c194d5717ae5..5773e1161072 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -226,6 +226,7 @@ static struct shash_alg alg = {
 		.cra_name		=	"crc32c",
 		.cra_driver_name	=	"crc32c-intel",
 		.cra_priority		=	200,
+		.cra_flags		=	CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		=	CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		=	sizeof(u32),
 		.cra_module		=	THIS_MODULE,
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 7a7de27c6f41..d9b734d0c8cc 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -45,6 +45,7 @@
 
 #include <asm/inst.h>
 #include <linux/linkage.h>
+#include <asm/nospec-branch.h>
 
 ## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction
 
@@ -172,7 +173,7 @@ continue_block:
 	movzxw  (bufp, %rax, 2), len
 	lea	crc_array(%rip), bufp
 	lea     (bufp, len, 1), bufp
-	jmp     *bufp
+	JMP_NOSPEC bufp
 
 	################################################################
 	## 2a) PROCESS FULL BLOCKS:
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index e32142bc071d..790377797544 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -164,14 +164,12 @@ static struct shash_alg alg = {
 	.init		= poly1305_simd_init,
 	.update		= poly1305_simd_update,
 	.final		= crypto_poly1305_final,
-	.setkey		= crypto_poly1305_setkey,
 	.descsize	= sizeof(struct poly1305_simd_desc_ctx),
 	.base		= {
 		.cra_name		= "poly1305",
 		.cra_driver_name	= "poly1305-simd",
 		.cra_priority		= 300,
 		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
-		.cra_alignmask		= sizeof(u32) - 1,
 		.cra_blocksize		= POLY1305_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	},
diff --git a/arch/x86/crypto/salsa20-i586-asm_32.S b/arch/x86/crypto/salsa20-i586-asm_32.S
index 329452b8f794..6014b7b9e52a 100644
--- a/arch/x86/crypto/salsa20-i586-asm_32.S
+++ b/arch/x86/crypto/salsa20-i586-asm_32.S
@@ -1,6 +1,7 @@
-# salsa20_pm.s version 20051229
-# D. J. Bernstein
-# Public domain.
+# Derived from:
+#	salsa20_pm.s version 20051229
+#	D. J. Bernstein
+#	Public domain.
 
 #include <linux/linkage.h>
 
@@ -935,180 +936,3 @@ ENTRY(salsa20_encrypt_bytes)
 	# goto bytesatleast1
 	jmp	._bytesatleast1
 ENDPROC(salsa20_encrypt_bytes)
-
-# enter salsa20_keysetup
-ENTRY(salsa20_keysetup)
-	mov	%esp,%eax
-	and	$31,%eax
-	add	$256,%eax
-	sub	%eax,%esp
-	#   eax_stack = eax
-	movl	%eax,64(%esp)
-	#   ebx_stack = ebx
-	movl	%ebx,68(%esp)
-	#   esi_stack = esi
-	movl	%esi,72(%esp)
-	#   edi_stack = edi
-	movl	%edi,76(%esp)
-	#   ebp_stack = ebp
-	movl	%ebp,80(%esp)
-	#   k = arg2
-	movl	8(%esp,%eax),%ecx
-	#   kbits = arg3
-	movl	12(%esp,%eax),%edx
-	#   x = arg1
-	movl	4(%esp,%eax),%eax
-	#   in1 = *(uint32 *) (k + 0)
-	movl	0(%ecx),%ebx
-	#   in2 = *(uint32 *) (k + 4)
-	movl	4(%ecx),%esi
-	#   in3 = *(uint32 *) (k + 8)
-	movl	8(%ecx),%edi
-	#   in4 = *(uint32 *) (k + 12)
-	movl	12(%ecx),%ebp
-	#   *(uint32 *) (x + 4) = in1
-	movl	%ebx,4(%eax)
-	#   *(uint32 *) (x + 8) = in2
-	movl	%esi,8(%eax)
-	#   *(uint32 *) (x + 12) = in3
-	movl	%edi,12(%eax)
-	#   *(uint32 *) (x + 16) = in4
-	movl	%ebp,16(%eax)
-	#   kbits - 256
-	cmp	$256,%edx
-	#   goto kbits128 if unsigned<
-	jb	._kbits128
-._kbits256:
-	#     in11 = *(uint32 *) (k + 16)
-	movl	16(%ecx),%edx
-	#     in12 = *(uint32 *) (k + 20)
-	movl	20(%ecx),%ebx
-	#     in13 = *(uint32 *) (k + 24)
-	movl	24(%ecx),%esi
-	#     in14 = *(uint32 *) (k + 28)
-	movl	28(%ecx),%ecx
-	#     *(uint32 *) (x + 44) = in11
-	movl	%edx,44(%eax)
-	#     *(uint32 *) (x + 48) = in12
-	movl	%ebx,48(%eax)
-	#     *(uint32 *) (x + 52) = in13
-	movl	%esi,52(%eax)
-	#     *(uint32 *) (x + 56) = in14
-	movl	%ecx,56(%eax)
-	#     in0 = 1634760805
-	mov	$1634760805,%ecx
-	#     in5 = 857760878
-	mov	$857760878,%edx
-	#     in10 = 2036477234
-	mov	$2036477234,%ebx
-	#     in15 = 1797285236
-	mov	$1797285236,%esi
-	#     *(uint32 *) (x + 0) = in0
-	movl	%ecx,0(%eax)
-	#     *(uint32 *) (x + 20) = in5
-	movl	%edx,20(%eax)
-	#     *(uint32 *) (x + 40) = in10
-	movl	%ebx,40(%eax)
-	#     *(uint32 *) (x + 60) = in15
-	movl	%esi,60(%eax)
-	#   goto keysetupdone
-	jmp	._keysetupdone
-._kbits128:
-	#     in11 = *(uint32 *) (k + 0)
-	movl	0(%ecx),%edx
-	#     in12 = *(uint32 *) (k + 4)
-	movl	4(%ecx),%ebx
-	#     in13 = *(uint32 *) (k + 8)
-	movl	8(%ecx),%esi
-	#     in14 = *(uint32 *) (k + 12)
-	movl	12(%ecx),%ecx
-	#     *(uint32 *) (x + 44) = in11
-	movl	%edx,44(%eax)
-	#     *(uint32 *) (x + 48) = in12
-	movl	%ebx,48(%eax)
-	#     *(uint32 *) (x + 52) = in13
-	movl	%esi,52(%eax)
-	#     *(uint32 *) (x + 56) = in14
-	movl	%ecx,56(%eax)
-	#     in0 = 1634760805
-	mov	$1634760805,%ecx
-	#     in5 = 824206446
-	mov	$824206446,%edx
-	#     in10 = 2036477238
-	mov	$2036477238,%ebx
-	#     in15 = 1797285236
-	mov	$1797285236,%esi
-	#     *(uint32 *) (x + 0) = in0
-	movl	%ecx,0(%eax)
-	#     *(uint32 *) (x + 20) = in5
-	movl	%edx,20(%eax)
-	#     *(uint32 *) (x + 40) = in10
-	movl	%ebx,40(%eax)
-	#     *(uint32 *) (x + 60) = in15
-	movl	%esi,60(%eax)
-._keysetupdone:
-	#   eax = eax_stack
-	movl	64(%esp),%eax
-	#   ebx = ebx_stack
-	movl	68(%esp),%ebx
-	#   esi = esi_stack
-	movl	72(%esp),%esi
-	#   edi = edi_stack
-	movl	76(%esp),%edi
-	#   ebp = ebp_stack
-	movl	80(%esp),%ebp
-	# leave
-	add	%eax,%esp
-	ret
-ENDPROC(salsa20_keysetup)
-
-# enter salsa20_ivsetup
-ENTRY(salsa20_ivsetup)
-	mov	%esp,%eax
-	and	$31,%eax
-	add	$256,%eax
-	sub	%eax,%esp
-	#   eax_stack = eax
-	movl	%eax,64(%esp)
-	#   ebx_stack = ebx
-	movl	%ebx,68(%esp)
-	#   esi_stack = esi
-	movl	%esi,72(%esp)
-	#   edi_stack = edi
-	movl	%edi,76(%esp)
-	#   ebp_stack = ebp
-	movl	%ebp,80(%esp)
-	#   iv = arg2
-	movl	8(%esp,%eax),%ecx
-	#   x = arg1
-	movl	4(%esp,%eax),%eax
-	#   in6 = *(uint32 *) (iv + 0)
-	movl	0(%ecx),%edx
-	#   in7 = *(uint32 *) (iv + 4)
-	movl	4(%ecx),%ecx
-	#   in8 = 0
-	mov	$0,%ebx
-	#   in9 = 0
-	mov	$0,%esi
-	#   *(uint32 *) (x + 24) = in6
-	movl	%edx,24(%eax)
-	#   *(uint32 *) (x + 28) = in7
-	movl	%ecx,28(%eax)
-	#   *(uint32 *) (x + 32) = in8
-	movl	%ebx,32(%eax)
-	#   *(uint32 *) (x + 36) = in9
-	movl	%esi,36(%eax)
-	#   eax = eax_stack
-	movl	64(%esp),%eax
-	#   ebx = ebx_stack
-	movl	68(%esp),%ebx
-	#   esi = esi_stack
-	movl	72(%esp),%esi
-	#   edi = edi_stack
-	movl	76(%esp),%edi
-	#   ebp = ebp_stack
-	movl	80(%esp),%ebp
-	# leave
-	add	%eax,%esp
-	ret
-ENDPROC(salsa20_ivsetup)
diff --git a/arch/x86/crypto/salsa20-x86_64-asm_64.S b/arch/x86/crypto/salsa20-x86_64-asm_64.S
index 10db30d58006..03a4918f41ee 100644
--- a/arch/x86/crypto/salsa20-x86_64-asm_64.S
+++ b/arch/x86/crypto/salsa20-x86_64-asm_64.S
@@ -803,117 +803,3 @@ ENTRY(salsa20_encrypt_bytes)
 	# goto bytesatleast1
 	jmp	._bytesatleast1
 ENDPROC(salsa20_encrypt_bytes)
-
-# enter salsa20_keysetup
-ENTRY(salsa20_keysetup)
-	mov	%rsp,%r11
-	and	$31,%r11
-	add	$256,%r11
-	sub	%r11,%rsp
-	#   k = arg2
-	mov	%rsi,%rsi
-	#   kbits = arg3
-	mov	%rdx,%rdx
-	#   x = arg1
-	mov	%rdi,%rdi
-	#   in0 = *(uint64 *) (k + 0)
-	movq	0(%rsi),%r8
-	#   in2 = *(uint64 *) (k + 8)
-	movq	8(%rsi),%r9
-	#   *(uint64 *) (x + 4) = in0
-	movq	%r8,4(%rdi)
-	#   *(uint64 *) (x + 12) = in2
-	movq	%r9,12(%rdi)
-	#                    unsigned<? kbits - 256
-	cmp	$256,%rdx
-	# comment:fp stack unchanged by jump
-	#   goto kbits128 if unsigned<
-	jb	._kbits128
-#   kbits256:
-._kbits256:
-	#     in10 = *(uint64 *) (k + 16)
-	movq	16(%rsi),%rdx
-	#     in12 = *(uint64 *) (k + 24)
-	movq	24(%rsi),%rsi
-	#     *(uint64 *) (x + 44) = in10
-	movq	%rdx,44(%rdi)
-	#     *(uint64 *) (x + 52) = in12
-	movq	%rsi,52(%rdi)
-	#     in0 = 1634760805
-	mov	$1634760805,%rsi
-	#     in4 = 857760878
-	mov	$857760878,%rdx
-	#     in10 = 2036477234
-	mov	$2036477234,%rcx
-	#     in14 = 1797285236
-	mov	$1797285236,%r8
-	#     *(uint32 *) (x + 0) = in0
-	movl	%esi,0(%rdi)
-	#     *(uint32 *) (x + 20) = in4
-	movl	%edx,20(%rdi)
-	#     *(uint32 *) (x + 40) = in10
-	movl	%ecx,40(%rdi)
-	#     *(uint32 *) (x + 60) = in14
-	movl	%r8d,60(%rdi)
-	# comment:fp stack unchanged by jump
-	#   goto keysetupdone
-	jmp	._keysetupdone
-#   kbits128:
-._kbits128:
-	#     in10 = *(uint64 *) (k + 0)
-	movq	0(%rsi),%rdx
-	#     in12 = *(uint64 *) (k + 8)
-	movq	8(%rsi),%rsi
-	#     *(uint64 *) (x + 44) = in10
-	movq	%rdx,44(%rdi)
-	#     *(uint64 *) (x + 52) = in12
-	movq	%rsi,52(%rdi)
-	#     in0 = 1634760805
-	mov	$1634760805,%rsi
-	#     in4 = 824206446
-	mov	$824206446,%rdx
-	#     in10 = 2036477238
-	mov	$2036477238,%rcx
-	#     in14 = 1797285236
-	mov	$1797285236,%r8
-	#     *(uint32 *) (x + 0) = in0
-	movl	%esi,0(%rdi)
-	#     *(uint32 *) (x + 20) = in4
-	movl	%edx,20(%rdi)
-	#     *(uint32 *) (x + 40) = in10
-	movl	%ecx,40(%rdi)
-	#     *(uint32 *) (x + 60) = in14
-	movl	%r8d,60(%rdi)
-#   keysetupdone:
-._keysetupdone:
-	# leave
-	add	%r11,%rsp
-	mov	%rdi,%rax
-	mov	%rsi,%rdx
-	ret
-ENDPROC(salsa20_keysetup)
-
-# enter salsa20_ivsetup
-ENTRY(salsa20_ivsetup)
-	mov	%rsp,%r11
-	and	$31,%r11
-	add	$256,%r11
-	sub	%r11,%rsp
-	#   iv = arg2
-	mov	%rsi,%rsi
-	#   x = arg1
-	mov	%rdi,%rdi
-	#   in6 = *(uint64 *) (iv + 0)
-	movq	0(%rsi),%rsi
-	#   in8 = 0
-	mov	$0,%r8
-	#   *(uint64 *) (x + 24) = in6
-	movq	%rsi,24(%rdi)
-	#   *(uint64 *) (x + 32) = in8
-	movq	%r8,32(%rdi)
-	# leave
-	add	%r11,%rsp
-	mov	%rdi,%rax
-	mov	%rsi,%rdx
-	ret
-ENDPROC(salsa20_ivsetup)
diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
index 399a29d067d6..b07d7d959806 100644
--- a/arch/x86/crypto/salsa20_glue.c
+++ b/arch/x86/crypto/salsa20_glue.c
@@ -11,6 +11,9 @@
  * - x86-64 version, renamed as salsa20-x86_64-asm_64.S
  *   available from <http://cr.yp.to/snuffle/salsa20/amd64-3/salsa20.s>
  *
+ * Also modified to set up the initial state using the generic C code rather
+ * than in assembly.
+ *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
  * Software Foundation; either version 2 of the License, or (at your option)
@@ -18,100 +21,65 @@
  *
  */
 
-#include <crypto/algapi.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/salsa20.h>
 #include <linux/module.h>
-#include <linux/crypto.h>
 
-#define SALSA20_IV_SIZE        8U
-#define SALSA20_MIN_KEY_SIZE  16U
-#define SALSA20_MAX_KEY_SIZE  32U
+asmlinkage void salsa20_encrypt_bytes(u32 state[16], const u8 *src, u8 *dst,
+				      u32 bytes);
 
-struct salsa20_ctx
+static int salsa20_asm_crypt(struct skcipher_request *req)
 {
-	u32 input[16];
-};
-
-asmlinkage void salsa20_keysetup(struct salsa20_ctx *ctx, const u8 *k,
-				 u32 keysize, u32 ivsize);
-asmlinkage void salsa20_ivsetup(struct salsa20_ctx *ctx, const u8 *iv);
-asmlinkage void salsa20_encrypt_bytes(struct salsa20_ctx *ctx,
-				      const u8 *src, u8 *dst, u32 bytes);
-
-static int setkey(struct crypto_tfm *tfm, const u8 *key,
-		  unsigned int keysize)
-{
-	struct salsa20_ctx *ctx = crypto_tfm_ctx(tfm);
-	salsa20_keysetup(ctx, key, keysize*8, SALSA20_IV_SIZE*8);
-	return 0;
-}
-
-static int encrypt(struct blkcipher_desc *desc,
-		   struct scatterlist *dst, struct scatterlist *src,
-		   unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
-	struct crypto_blkcipher *tfm = desc->tfm;
-	struct salsa20_ctx *ctx = crypto_blkcipher_ctx(tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct salsa20_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	u32 state[16];
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, 64);
+	err = skcipher_walk_virt(&walk, req, true);
 
-	salsa20_ivsetup(ctx, walk.iv);
+	crypto_salsa20_init(state, ctx, walk.iv);
 
-	if (likely(walk.nbytes == nbytes))
-	{
-		salsa20_encrypt_bytes(ctx, walk.src.virt.addr,
-				      walk.dst.virt.addr, nbytes);
-		return blkcipher_walk_done(desc, &walk, 0);
-	}
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
 
-	while (walk.nbytes >= 64) {
-		salsa20_encrypt_bytes(ctx, walk.src.virt.addr,
-				      walk.dst.virt.addr,
-				      walk.nbytes - (walk.nbytes % 64));
-		err = blkcipher_walk_done(desc, &walk, walk.nbytes % 64);
-	}
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
 
-	if (walk.nbytes) {
-		salsa20_encrypt_bytes(ctx, walk.src.virt.addr,
-				      walk.dst.virt.addr, walk.nbytes);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		salsa20_encrypt_bytes(state, walk.src.virt.addr,
+				      walk.dst.virt.addr, nbytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
 }
 
-static struct crypto_alg alg = {
-	.cra_name           =   "salsa20",
-	.cra_driver_name    =   "salsa20-asm",
-	.cra_priority       =   200,
-	.cra_flags          =   CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_type           =   &crypto_blkcipher_type,
-	.cra_blocksize      =   1,
-	.cra_ctxsize        =   sizeof(struct salsa20_ctx),
-	.cra_alignmask      =	3,
-	.cra_module         =   THIS_MODULE,
-	.cra_u              =   {
-		.blkcipher = {
-			.setkey         =   setkey,
-			.encrypt        =   encrypt,
-			.decrypt        =   encrypt,
-			.min_keysize    =   SALSA20_MIN_KEY_SIZE,
-			.max_keysize    =   SALSA20_MAX_KEY_SIZE,
-			.ivsize         =   SALSA20_IV_SIZE,
-		}
-	}
+static struct skcipher_alg alg = {
+	.base.cra_name		= "salsa20",
+	.base.cra_driver_name	= "salsa20-asm",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct salsa20_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= SALSA20_MIN_KEY_SIZE,
+	.max_keysize		= SALSA20_MAX_KEY_SIZE,
+	.ivsize			= SALSA20_IV_SIZE,
+	.chunksize		= SALSA20_BLOCK_SIZE,
+	.setkey			= crypto_salsa20_setkey,
+	.encrypt		= salsa20_asm_crypt,
+	.decrypt		= salsa20_asm_crypt,
 };
 
 static int __init init(void)
 {
-	return crypto_register_alg(&alg);
+	return crypto_register_skcipher(&alg);
 }
 
 static void __exit fini(void)
 {
-	crypto_unregister_alg(&alg);
+	crypto_unregister_skcipher(&alg);
 }
 
 module_init(init);
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index 1c3b7ceb36d2..e7273a606a07 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -55,29 +55,31 @@
 #define RAB1bl %bl
 #define RAB2bl %cl
 
+#define CD0 0x0(%rsp)
+#define CD1 0x8(%rsp)
+#define CD2 0x10(%rsp)
+
+# used only before/after all rounds
 #define RCD0 %r8
 #define RCD1 %r9
 #define RCD2 %r10
 
-#define RCD0d %r8d
-#define RCD1d %r9d
-#define RCD2d %r10d
-
-#define RX0 %rbp
-#define RX1 %r11
-#define RX2 %r12
+# used only during rounds
+#define RX0 %r8
+#define RX1 %r9
+#define RX2 %r10
 
-#define RX0d %ebp
-#define RX1d %r11d
-#define RX2d %r12d
+#define RX0d %r8d
+#define RX1d %r9d
+#define RX2d %r10d
 
-#define RY0 %r13
-#define RY1 %r14
-#define RY2 %r15
+#define RY0 %r11
+#define RY1 %r12
+#define RY2 %r13
 
-#define RY0d %r13d
-#define RY1d %r14d
-#define RY2d %r15d
+#define RY0d %r11d
+#define RY1d %r12d
+#define RY2d %r13d
 
 #define RT0 %rdx
 #define RT1 %rsi
@@ -85,6 +87,8 @@
 #define RT0d %edx
 #define RT1d %esi
 
+#define RT1bl %sil
+
 #define do16bit_ror(rot, op1, op2, T0, T1, tmp1, tmp2, ab, dst) \
 	movzbl ab ## bl,		tmp2 ## d; \
 	movzbl ab ## bh,		tmp1 ## d; \
@@ -92,6 +96,11 @@
 	op1##l T0(CTX, tmp2, 4),	dst ## d; \
 	op2##l T1(CTX, tmp1, 4),	dst ## d;
 
+#define swap_ab_with_cd(ab, cd, tmp)	\
+	movq cd, tmp;			\
+	movq ab, cd;			\
+	movq tmp, ab;
+
 /*
  * Combined G1 & G2 function. Reordered with help of rotates to have moves
  * at begining.
@@ -110,15 +119,15 @@
 	/* G1,2 && G2,2 */ \
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 0, x ## 0); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 0, y ## 0); \
-	xchgq cd ## 0, ab ## 0; \
+	swap_ab_with_cd(ab ## 0, cd ## 0, RT0); \
 	\
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 1, x ## 1); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 1, y ## 1); \
-	xchgq cd ## 1, ab ## 1; \
+	swap_ab_with_cd(ab ## 1, cd ## 1, RT0); \
 	\
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 2, x ## 2); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 2, y ## 2); \
-	xchgq cd ## 2, ab ## 2;
+	swap_ab_with_cd(ab ## 2, cd ## 2, RT0);
 
 #define enc_round_end(ab, x, y, n) \
 	addl y ## d,			x ## d; \
@@ -168,6 +177,16 @@
 	decrypt_round3(ba, dc, (n*2)+1); \
 	decrypt_round3(ba, dc, (n*2));
 
+#define push_cd()	\
+	pushq RCD2;	\
+	pushq RCD1;	\
+	pushq RCD0;
+
+#define pop_cd()	\
+	popq RCD0;	\
+	popq RCD1;	\
+	popq RCD2;
+
 #define inpack3(in, n, xy, m) \
 	movq 4*(n)(in),			xy ## 0; \
 	xorq w+4*m(CTX),		xy ## 0; \
@@ -223,11 +242,8 @@ ENTRY(__twofish_enc_blk_3way)
 	 *	%rdx: src, RIO
 	 *	%rcx: bool, if true: xor output
 	 */
-	pushq %r15;
-	pushq %r14;
 	pushq %r13;
 	pushq %r12;
-	pushq %rbp;
 	pushq %rbx;
 
 	pushq %rcx; /* bool xor */
@@ -235,40 +251,36 @@ ENTRY(__twofish_enc_blk_3way)
 
 	inpack_enc3();
 
-	encrypt_cycle3(RAB, RCD, 0);
-	encrypt_cycle3(RAB, RCD, 1);
-	encrypt_cycle3(RAB, RCD, 2);
-	encrypt_cycle3(RAB, RCD, 3);
-	encrypt_cycle3(RAB, RCD, 4);
-	encrypt_cycle3(RAB, RCD, 5);
-	encrypt_cycle3(RAB, RCD, 6);
-	encrypt_cycle3(RAB, RCD, 7);
+	push_cd();
+	encrypt_cycle3(RAB, CD, 0);
+	encrypt_cycle3(RAB, CD, 1);
+	encrypt_cycle3(RAB, CD, 2);
+	encrypt_cycle3(RAB, CD, 3);
+	encrypt_cycle3(RAB, CD, 4);
+	encrypt_cycle3(RAB, CD, 5);
+	encrypt_cycle3(RAB, CD, 6);
+	encrypt_cycle3(RAB, CD, 7);
+	pop_cd();
 
 	popq RIO; /* dst */
-	popq %rbp; /* bool xor */
+	popq RT1; /* bool xor */
 
-	testb %bpl, %bpl;
+	testb RT1bl, RT1bl;
 	jnz .L__enc_xor3;
 
 	outunpack_enc3(mov);
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 
 .L__enc_xor3:
 	outunpack_enc3(xor);
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 ENDPROC(__twofish_enc_blk_3way)
 
@@ -278,35 +290,31 @@ ENTRY(twofish_dec_blk_3way)
 	 *	%rsi: dst
 	 *	%rdx: src, RIO
 	 */
-	pushq %r15;
-	pushq %r14;
 	pushq %r13;
 	pushq %r12;
-	pushq %rbp;
 	pushq %rbx;
 
 	pushq %rsi; /* dst */
 
 	inpack_dec3();
 
-	decrypt_cycle3(RAB, RCD, 7);
-	decrypt_cycle3(RAB, RCD, 6);
-	decrypt_cycle3(RAB, RCD, 5);
-	decrypt_cycle3(RAB, RCD, 4);
-	decrypt_cycle3(RAB, RCD, 3);
-	decrypt_cycle3(RAB, RCD, 2);
-	decrypt_cycle3(RAB, RCD, 1);
-	decrypt_cycle3(RAB, RCD, 0);
+	push_cd();
+	decrypt_cycle3(RAB, CD, 7);
+	decrypt_cycle3(RAB, CD, 6);
+	decrypt_cycle3(RAB, CD, 5);
+	decrypt_cycle3(RAB, CD, 4);
+	decrypt_cycle3(RAB, CD, 3);
+	decrypt_cycle3(RAB, CD, 2);
+	decrypt_cycle3(RAB, CD, 1);
+	decrypt_cycle3(RAB, CD, 0);
+	pop_cd();
 
 	popq RIO; /* dst */
 
 	outunpack_dec3();
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 ENDPROC(twofish_dec_blk_3way)
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 3fd8bc560fae..3f48f695d5e6 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -1,6 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/jump_label.h>
 #include <asm/unwind_hints.h>
+#include <asm/cpufeatures.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/asm-offsets.h>
+#include <asm/processor-flags.h>
 
 /*
 
@@ -187,6 +192,148 @@ For 32-bit we have the following conventions - kernel is built with
 #endif
 .endm
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+/*
+ * PAGE_TABLE_ISOLATION PGDs are 8k.  Flip bit 12 to switch between the two
+ * halves:
+ */
+#define PTI_USER_PGTABLE_BIT		PAGE_SHIFT
+#define PTI_USER_PGTABLE_MASK		(1 << PTI_USER_PGTABLE_BIT)
+#define PTI_USER_PCID_BIT		X86_CR3_PTI_PCID_USER_BIT
+#define PTI_USER_PCID_MASK		(1 << PTI_USER_PCID_BIT)
+#define PTI_USER_PGTABLE_AND_PCID_MASK  (PTI_USER_PCID_MASK | PTI_USER_PGTABLE_MASK)
+
+.macro SET_NOFLUSH_BIT	reg:req
+	bts	$X86_CR3_PCID_NOFLUSH_BIT, \reg
+.endm
+
+.macro ADJUST_KERNEL_CR3 reg:req
+	ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
+	/* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
+	andq    $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
+.endm
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	mov	%cr3, \scratch_reg
+	ADJUST_KERNEL_CR3 \scratch_reg
+	mov	\scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+#define THIS_CPU_user_pcid_flush_mask   \
+	PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
+
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	mov	%cr3, \scratch_reg
+
+	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+	/*
+	 * Test if the ASID needs a flush.
+	 */
+	movq	\scratch_reg, \scratch_reg2
+	andq	$(0x7FF), \scratch_reg		/* mask ASID */
+	bt	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	jnc	.Lnoflush_\@
+
+	/* Flush needed, clear the bit */
+	btr	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	movq	\scratch_reg2, \scratch_reg
+	jmp	.Lwrcr3_pcid_\@
+
+.Lnoflush_\@:
+	movq	\scratch_reg2, \scratch_reg
+	SET_NOFLUSH_BIT \scratch_reg
+
+.Lwrcr3_pcid_\@:
+	/* Flip the ASID to the user version */
+	orq	$(PTI_USER_PCID_MASK), \scratch_reg
+
+.Lwrcr3_\@:
+	/* Flip the PGD to the user version */
+	orq     $(PTI_USER_PGTABLE_MASK), \scratch_reg
+	mov	\scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+.macro SWITCH_TO_USER_CR3_STACK	scratch_reg:req
+	pushq	%rax
+	SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
+	popq	%rax
+.endm
+
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+	ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI
+	movq	%cr3, \scratch_reg
+	movq	\scratch_reg, \save_reg
+	/*
+	 * Test the user pagetable bit. If set, then the user page tables
+	 * are active. If clear CR3 already has the kernel page table
+	 * active.
+	 */
+	bt	$PTI_USER_PGTABLE_BIT, \scratch_reg
+	jnc	.Ldone_\@
+
+	ADJUST_KERNEL_CR3 \scratch_reg
+	movq	\scratch_reg, %cr3
+
+.Ldone_\@:
+.endm
+
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+	/*
+	 * KERNEL pages can always resume with NOFLUSH as we do
+	 * explicit flushes.
+	 */
+	bt	$PTI_USER_PGTABLE_BIT, \save_reg
+	jnc	.Lnoflush_\@
+
+	/*
+	 * Check if there's a pending flush for the user ASID we're
+	 * about to set.
+	 */
+	movq	\save_reg, \scratch_reg
+	andq	$(0x7FF), \scratch_reg
+	bt	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	jnc	.Lnoflush_\@
+
+	btr	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	jmp	.Lwrcr3_\@
+
+.Lnoflush_\@:
+	SET_NOFLUSH_BIT \save_reg
+
+.Lwrcr3_\@:
+	/*
+	 * The CR3 write could be avoided when not changing its value,
+	 * but would require a CR3 read *and* a scratch register.
+	 */
+	movq	\save_reg, %cr3
+.Lend_\@:
+.endm
+
+#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+.endm
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+.endm
+.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+.endm
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+.endm
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+.endm
+
+#endif
+
 #endif /* CONFIG_X86_64 */
 
 /*
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index d7d3cc24baf4..1e3883e45687 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -153,6 +153,9 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 		if (cached_flags & _TIF_UPROBE)
 			uprobe_notify_resume(regs);
 
+		if (cached_flags & _TIF_PATCH_PENDING)
+			klp_update_patch_state(current);
+
 		/* deal with pending signal delivery */
 		if (cached_flags & _TIF_SIGPENDING)
 			do_signal(regs);
@@ -165,9 +168,6 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 		if (cached_flags & _TIF_USER_RETURN_NOTIFY)
 			fire_user_return_notifiers();
 
-		if (cached_flags & _TIF_PATCH_PENDING)
-			klp_update_patch_state(current);
-
 		/* Disable IRQs and retry */
 		local_irq_disable();
 
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 4838037f97f6..2a35b1e0fb90 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -44,6 +44,7 @@
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 	.section .entry.text, "ax"
 
@@ -243,6 +244,18 @@ ENTRY(__switch_to_asm)
 	movl	%ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
 #endif
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * When switching from a shallower to a deeper call stack
+	 * the RSB may either underflow or use entries populated
+	 * with userspace addresses. On CPUs where those concerns
+	 * exist, overwrite the RSB with entries which capture
+	 * speculative execution to prevent attack.
+	 */
+	/* Clobbers %ebx */
+	FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
 	/* restore callee-saved registers */
 	popl	%esi
 	popl	%edi
@@ -290,7 +303,7 @@ ENTRY(ret_from_fork)
 
 	/* kernel thread */
 1:	movl	%edi, %eax
-	call	*%ebx
+	CALL_NOSPEC %ebx
 	/*
 	 * A kernel thread is allowed to return here after successfully
 	 * calling do_execve().  Exit to userspace to complete the execve()
@@ -919,7 +932,7 @@ common_exception:
 	movl	%ecx, %es
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
-	call	*%edi
+	CALL_NOSPEC %edi
 	jmp	ret_from_exception
 END(common_exception)
 
@@ -941,9 +954,10 @@ ENTRY(debug)
 	movl	%esp, %eax			# pt_regs pointer
 
 	/* Are we currently on the SYSENTER stack? */
-	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
-	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
-	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
 	jb	.Ldebug_from_sysenter_stack
 
 	TRACE_IRQS_OFF
@@ -984,9 +998,10 @@ ENTRY(nmi)
 	movl	%esp, %eax			# pt_regs pointer
 
 	/* Are we currently on the SYSENTER stack? */
-	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
-	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
-	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
 	jb	.Lnmi_from_sysenter_stack
 
 	/* Not on SYSENTER stack. */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f81d50d7ceac..a83570495162 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -23,7 +23,6 @@
 #include <asm/segment.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
-#include "calling.h"
 #include <asm/asm-offsets.h>
 #include <asm/msr.h>
 #include <asm/unistd.h>
@@ -38,8 +37,11 @@
 #include <asm/pgtable_types.h>
 #include <asm/export.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 #include <linux/err.h>
 
+#include "calling.h"
+
 .code64
 .section .entry.text, "ax"
 
@@ -140,6 +142,67 @@ END(native_usergs_sysret64)
  * with them due to bugs in both AMD and Intel CPUs.
  */
 
+	.pushsection .entry_trampoline, "ax"
+
+/*
+ * The code in here gets remapped into cpu_entry_area's trampoline.  This means
+ * that the assembler and linker have the wrong idea as to where this code
+ * lives (and, in fact, it's mapped more than once, so it's not even at a
+ * fixed address).  So we can't reference any symbols outside the entry
+ * trampoline and expect it to work.
+ *
+ * Instead, we carefully abuse %rip-relative addressing.
+ * _entry_trampoline(%rip) refers to the start of the remapped) entry
+ * trampoline.  We can thus find cpu_entry_area with this macro:
+ */
+
+#define CPU_ENTRY_AREA \
+	_entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip)
+
+/* The top word of the SYSENTER stack is hot and is usable as scratch space. */
+#define RSP_SCRATCH	CPU_ENTRY_AREA_entry_stack + \
+			SIZEOF_entry_stack - 8 + CPU_ENTRY_AREA
+
+ENTRY(entry_SYSCALL_64_trampoline)
+	UNWIND_HINT_EMPTY
+	swapgs
+
+	/* Stash the user RSP. */
+	movq	%rsp, RSP_SCRATCH
+
+	/* Note: using %rsp as a scratch reg. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
+	/* Load the top of the task stack into RSP */
+	movq	CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp
+
+	/* Start building the simulated IRET frame. */
+	pushq	$__USER_DS			/* pt_regs->ss */
+	pushq	RSP_SCRATCH			/* pt_regs->sp */
+	pushq	%r11				/* pt_regs->flags */
+	pushq	$__USER_CS			/* pt_regs->cs */
+	pushq	%rcx				/* pt_regs->ip */
+
+	/*
+	 * x86 lacks a near absolute jump, and we can't jump to the real
+	 * entry text with a relative jump.  We could push the target
+	 * address and then use retq, but this destroys the pipeline on
+	 * many CPUs (wasting over 20 cycles on Sandy Bridge).  Instead,
+	 * spill RDI and restore it in a second-stage trampoline.
+	 */
+	pushq	%rdi
+	movq	$entry_SYSCALL_64_stage2, %rdi
+	JMP_NOSPEC %rdi
+END(entry_SYSCALL_64_trampoline)
+
+	.popsection
+
+ENTRY(entry_SYSCALL_64_stage2)
+	UNWIND_HINT_EMPTY
+	popq	%rdi
+	jmp	entry_SYSCALL_64_after_hwframe
+END(entry_SYSCALL_64_stage2)
+
 ENTRY(entry_SYSCALL_64)
 	UNWIND_HINT_EMPTY
 	/*
@@ -149,6 +212,10 @@ ENTRY(entry_SYSCALL_64)
 	 */
 
 	swapgs
+	/*
+	 * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it
+	 * is not required to switch CR3.
+	 */
 	movq	%rsp, PER_CPU_VAR(rsp_scratch)
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
@@ -204,7 +271,12 @@ entry_SYSCALL_64_fastpath:
 	 * It might end up jumping to the slow path.  If it jumps, RAX
 	 * and all argument registers are clobbered.
 	 */
+#ifdef CONFIG_RETPOLINE
+	movq	sys_call_table(, %rax, 8), %rax
+	call	__x86_indirect_thunk_rax
+#else
 	call	*sys_call_table(, %rax, 8)
+#endif
 .Lentry_SYSCALL_64_after_fastpath_call:
 
 	movq	%rax, RAX(%rsp)
@@ -330,8 +402,25 @@ syscall_return_via_sysret:
 	popq	%rsi	/* skip rcx */
 	popq	%rdx
 	popq	%rsi
+
+	/*
+	 * Now all regs are restored except RSP and RDI.
+	 * Save old stack pointer and switch to trampoline stack.
+	 */
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+	pushq	RSP-RDI(%rdi)	/* RSP */
+	pushq	(%rdi)		/* RDI */
+
+	/*
+	 * We are on the trampoline stack.  All regs except RDI are live.
+	 * We can do future final exit work right here.
+	 */
+	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
 	popq	%rdi
-	movq	RSP-ORIG_RAX(%rsp), %rsp
+	popq	%rsp
 	USERGS_SYSRET64
 END(entry_SYSCALL_64)
 
@@ -359,7 +448,7 @@ ENTRY(stub_ptregs_64)
 	jmp	entry_SYSCALL64_slow_path
 
 1:
-	jmp	*%rax				/* Called from C */
+	JMP_NOSPEC %rax				/* Called from C */
 END(stub_ptregs_64)
 
 .macro ptregs_stub func
@@ -402,6 +491,18 @@ ENTRY(__switch_to_asm)
 	movq	%rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
 #endif
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * When switching from a shallower to a deeper call stack
+	 * the RSB may either underflow or use entries populated
+	 * with userspace addresses. On CPUs where those concerns
+	 * exist, overwrite the RSB with entries which capture
+	 * speculative execution to prevent attack.
+	 */
+	/* Clobbers %rbx */
+	FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
 	/* restore callee-saved registers */
 	popq	%r15
 	popq	%r14
@@ -438,7 +539,7 @@ ENTRY(ret_from_fork)
 1:
 	/* kernel thread */
 	movq	%r12, %rdi
-	call	*%rbx
+	CALL_NOSPEC %rbx
 	/*
 	 * A kernel thread is allowed to return here after successfully
 	 * calling do_execve().  Exit to userspace to complete the execve()
@@ -466,12 +567,13 @@ END(irq_entries_start)
 
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF
 #ifdef CONFIG_DEBUG_ENTRY
-	pushfq
-	testl $X86_EFLAGS_IF, (%rsp)
+	pushq %rax
+	SAVE_FLAGS(CLBR_RAX)
+	testl $X86_EFLAGS_IF, %eax
 	jz .Lokay_\@
 	ud2
 .Lokay_\@:
-	addq $8, %rsp
+	popq %rax
 #endif
 .endm
 
@@ -563,6 +665,13 @@ END(irq_entries_start)
 /* 0(%rsp): ~(interrupt number) */
 	.macro interrupt func
 	cld
+
+	testb	$3, CS-ORIG_RAX(%rsp)
+	jz	1f
+	SWAPGS
+	call	switch_to_thread_stack
+1:
+
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
@@ -572,12 +681,8 @@ END(irq_entries_start)
 	jz	1f
 
 	/*
-	 * IRQ from user mode.  Switch to kernel gsbase and inform context
-	 * tracking that we're in kernel mode.
-	 */
-	SWAPGS
-
-	/*
+	 * IRQ from user mode.
+	 *
 	 * We need to tell lockdep that IRQs are off.  We can't do this until
 	 * we fix gsbase, and we should do it before enter_from_user_mode
 	 * (which can take locks).  Since TRACE_IRQS_OFF idempotent,
@@ -630,10 +735,43 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
 	ud2
 1:
 #endif
-	SWAPGS
 	POP_EXTRA_REGS
-	POP_C_REGS
-	addq	$8, %rsp	/* skip regs->orig_ax */
+	popq	%r11
+	popq	%r10
+	popq	%r9
+	popq	%r8
+	popq	%rax
+	popq	%rcx
+	popq	%rdx
+	popq	%rsi
+
+	/*
+	 * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
+	 * Save old stack pointer and switch to trampoline stack.
+	 */
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+	/* Copy the IRET frame to the trampoline stack. */
+	pushq	6*8(%rdi)	/* SS */
+	pushq	5*8(%rdi)	/* RSP */
+	pushq	4*8(%rdi)	/* EFLAGS */
+	pushq	3*8(%rdi)	/* CS */
+	pushq	2*8(%rdi)	/* RIP */
+
+	/* Push user RDI on the trampoline stack. */
+	pushq	(%rdi)
+
+	/*
+	 * We are on the trampoline stack.  All regs except RDI are live.
+	 * We can do future final exit work right here.
+	 */
+
+	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
+	/* Restore RDI. */
+	popq	%rdi
+	SWAPGS
 	INTERRUPT_RETURN
 
 
@@ -713,7 +851,9 @@ native_irq_return_ldt:
 	 */
 
 	pushq	%rdi				/* Stash user RDI */
-	SWAPGS
+	SWAPGS					/* to kernel GS */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi	/* to kernel CR3 */
+
 	movq	PER_CPU_VAR(espfix_waddr), %rdi
 	movq	%rax, (0*8)(%rdi)		/* user RAX */
 	movq	(1*8)(%rsp), %rax		/* user RIP */
@@ -729,7 +869,6 @@ native_irq_return_ldt:
 	/* Now RAX == RSP. */
 
 	andl	$0xffff0000, %eax		/* RAX = (RSP & 0xffff0000) */
-	popq	%rdi				/* Restore user RDI */
 
 	/*
 	 * espfix_stack[31:16] == 0.  The page tables are set up such that
@@ -740,7 +879,11 @@ native_irq_return_ldt:
 	 * still points to an RO alias of the ESPFIX stack.
 	 */
 	orq	PER_CPU_VAR(espfix_stack), %rax
-	SWAPGS
+
+	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+	SWAPGS					/* to user GS */
+	popq	%rdi				/* Restore user RDI */
+
 	movq	%rax, %rsp
 	UNWIND_HINT_IRET_REGS offset=8
 
@@ -829,7 +972,35 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 /*
  * Exception entry points.
  */
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+
+/*
+ * Switch to the thread stack.  This is called with the IRET frame and
+ * orig_ax on the stack.  (That is, RDI..R12 are not on the stack and
+ * space has not been allocated for them.)
+ */
+ENTRY(switch_to_thread_stack)
+	UNWIND_HINT_FUNC
+
+	pushq	%rdi
+	/* Need to switch before accessing the thread stack. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
+
+	pushq	7*8(%rdi)		/* regs->ss */
+	pushq	6*8(%rdi)		/* regs->rsp */
+	pushq	5*8(%rdi)		/* regs->eflags */
+	pushq	4*8(%rdi)		/* regs->cs */
+	pushq	3*8(%rdi)		/* regs->ip */
+	pushq	2*8(%rdi)		/* regs->orig_ax */
+	pushq	8(%rdi)			/* return address */
+	UNWIND_HINT_FUNC
+
+	movq	(%rdi), %rdi
+	ret
+END(switch_to_thread_stack)
 
 .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
 ENTRY(\sym)
@@ -848,11 +1019,12 @@ ENTRY(\sym)
 
 	ALLOC_PT_GPREGS_ON_STACK
 
-	.if \paranoid
-	.if \paranoid == 1
+	.if \paranoid < 2
 	testb	$3, CS(%rsp)			/* If coming from userspace, switch stacks */
-	jnz	1f
+	jnz	.Lfrom_usermode_switch_stack_\@
 	.endif
+
+	.if \paranoid
 	call	paranoid_entry
 	.else
 	call	error_entry
@@ -894,20 +1066,15 @@ ENTRY(\sym)
 	jmp	error_exit
 	.endif
 
-	.if \paranoid == 1
+	.if \paranoid < 2
 	/*
-	 * Paranoid entry from userspace.  Switch stacks and treat it
+	 * Entry from userspace.  Switch stacks and treat it
 	 * as a normal entry.  This means that paranoid handlers
 	 * run in real process context if user_mode(regs).
 	 */
-1:
+.Lfrom_usermode_switch_stack_\@:
 	call	error_entry
 
-
-	movq	%rsp, %rdi			/* pt_regs pointer */
-	call	sync_regs
-	movq	%rax, %rsp			/* switch stack */
-
 	movq	%rsp, %rdi			/* pt_regs pointer */
 
 	.if \has_error_code
@@ -1098,7 +1265,7 @@ idtentry async_page_fault	do_async_page_fault	has_error_code=1
 #endif
 
 #ifdef CONFIG_X86_MCE
-idtentry machine_check					has_error_code=0	paranoid=1 do_sym=*machine_check_vector(%rip)
+idtentry machine_check		do_mce			has_error_code=0	paranoid=1
 #endif
 
 /*
@@ -1119,7 +1286,11 @@ ENTRY(paranoid_entry)
 	js	1f				/* negative -> in kernel */
 	SWAPGS
 	xorl	%ebx, %ebx
-1:	ret
+
+1:
+	SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
+
+	ret
 END(paranoid_entry)
 
 /*
@@ -1141,6 +1312,7 @@ ENTRY(paranoid_exit)
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	.Lparanoid_exit_no_swapgs
 	TRACE_IRQS_IRETQ
+	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
 	SWAPGS_UNSAFE_STACK
 	jmp	.Lparanoid_exit_restore
 .Lparanoid_exit_no_swapgs:
@@ -1168,8 +1340,18 @@ ENTRY(error_entry)
 	 * from user mode due to an IRET fault.
 	 */
 	SWAPGS
+	/* We have user CR3.  Change to kernel CR3. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
 .Lerror_entry_from_usermode_after_swapgs:
+	/* Put us onto the real thread stack. */
+	popq	%r12				/* save return addr in %12 */
+	movq	%rsp, %rdi			/* arg0 = pt_regs pointer */
+	call	sync_regs
+	movq	%rax, %rsp			/* switch stack */
+	ENCODE_FRAME_POINTER
+	pushq	%r12
+
 	/*
 	 * We need to tell lockdep that IRQs are off.  We can't do this until
 	 * we fix gsbase, and we should do it before enter_from_user_mode
@@ -1206,6 +1388,7 @@ ENTRY(error_entry)
 	 * .Lgs_change's error handler with kernel gsbase.
 	 */
 	SWAPGS
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 	jmp .Lerror_entry_done
 
 .Lbstep_iret:
@@ -1215,10 +1398,11 @@ ENTRY(error_entry)
 
 .Lerror_bad_iret:
 	/*
-	 * We came from an IRET to user mode, so we have user gsbase.
-	 * Switch to kernel gsbase:
+	 * We came from an IRET to user mode, so we have user
+	 * gsbase and CR3.  Switch to kernel gsbase and CR3:
 	 */
 	SWAPGS
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
 	/*
 	 * Pretend that the exception came from user mode: set up pt_regs
@@ -1250,6 +1434,10 @@ END(error_exit)
 /*
  * Runs on exception stack.  Xen PV does not go through this path at all,
  * so we can use real assembly here.
+ *
+ * Registers:
+ *	%r14: Used to save/restore the CR3 of the interrupted context
+ *	      when PAGE_TABLE_ISOLATION is in use.  Do not clobber.
  */
 ENTRY(nmi)
 	UNWIND_HINT_IRET_REGS
@@ -1313,6 +1501,7 @@ ENTRY(nmi)
 
 	swapgs
 	cld
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 	UNWIND_HINT_IRET_REGS base=%rdx offset=8
@@ -1565,6 +1754,8 @@ end_repeat_nmi:
 	movq	$-1, %rsi
 	call	do_nmi
 
+	RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
+
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	nmi_restore
 nmi_swapgs:
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 568e130d932c..98d5358e4041 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -48,7 +48,11 @@
  */
 ENTRY(entry_SYSENTER_compat)
 	/* Interrupts are off on entry. */
-	SWAPGS_UNSAFE_STACK
+	SWAPGS
+
+	/* We are about to clobber %rsp anyway, clobbering here is OK */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/*
@@ -186,8 +190,13 @@ ENTRY(entry_SYSCALL_compat)
 	/* Interrupts are off on entry. */
 	swapgs
 
-	/* Stash user ESP and switch to the kernel stack. */
+	/* Stash user ESP */
 	movl	%esp, %r8d
+
+	/* Use %rsp as scratch reg. User ESP is stashed in r8 */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
+	/* Switch to the kernel stack */
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/* Construct struct pt_regs on stack */
@@ -256,10 +265,22 @@ sysret32_from_system_call:
 	 * when the system call started, which is already known to user
 	 * code.  We zero R8-R10 to avoid info leaks.
          */
+	movq	RSP-ORIG_RAX(%rsp), %rsp
+
+	/*
+	 * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored
+	 * on the process stack which is not mapped to userspace and
+	 * not readable after we SWITCH_TO_USER_CR3.  Delay the CR3
+	 * switch until after after the last reference to the process
+	 * stack.
+	 *
+	 * %r8/%r9 are zeroed before the sysret, thus safe to clobber.
+	 */
+	SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9
+
 	xorq	%r8, %r8
 	xorq	%r9, %r9
 	xorq	%r10, %r10
-	movq	RSP-ORIG_RAX(%rsp), %rsp
 	swapgs
 	sysretl
 END(entry_SYSCALL_compat)
@@ -306,8 +327,11 @@ ENTRY(entry_INT80_compat)
 	 */
 	movl	%eax, %eax
 
-	/* Construct struct pt_regs on stack (iret frame is already on stack) */
 	pushq	%rax			/* pt_regs->orig_ax */
+
+	/* switch to thread stack expects orig_ax to be pushed */
+	call	switch_to_thread_stack
+
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 11b13c4b43d5..f19856d95c60 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -324,5 +324,5 @@ notrace time_t __vdso_time(time_t *t)
 		*t = result;
 	return result;
 }
-int time(time_t *t)
+time_t time(time_t *t)
 	__attribute__((weak, alias("__vdso_time")));
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index f279ba2643dc..577fa8adb785 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -37,6 +37,7 @@
 #include <asm/unistd.h>
 #include <asm/fixmap.h>
 #include <asm/traps.h>
+#include <asm/paravirt.h>
 
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
@@ -138,6 +139,10 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 	WARN_ON_ONCE(address != regs->ip);
 
+	/* This should be unreachable in NATIVE mode. */
+	if (WARN_ON(vsyscall_mode == NATIVE))
+		return false;
+
 	if (vsyscall_mode == NONE) {
 		warn_bad_vsyscall(KERN_INFO, regs,
 				  "vsyscall attempted with vsyscall=none");
@@ -329,16 +334,47 @@ int in_gate_area_no_mm(unsigned long addr)
 	return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
 }
 
+/*
+ * The VSYSCALL page is the only user-accessible page in the kernel address
+ * range.  Normally, the kernel page tables can have _PAGE_USER clear, but
+ * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls
+ * are enabled.
+ *
+ * Some day we may create a "minimal" vsyscall mode in which we emulate
+ * vsyscalls but leave the page not present.  If so, we skip calling
+ * this.
+ */
+void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
+	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
+	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
+#if CONFIG_PGTABLE_LEVELS >= 5
+	p4d->p4d |= _PAGE_USER;
+#endif
+	pud = pud_offset(p4d, VSYSCALL_ADDR);
+	set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
+	pmd = pmd_offset(pud, VSYSCALL_ADDR);
+	set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER));
+}
+
 void __init map_vsyscall(void)
 {
 	extern char __vsyscall_page;
 	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
 
-	if (vsyscall_mode != NONE)
+	if (vsyscall_mode != NONE) {
 		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
 			     vsyscall_mode == NATIVE
 			     ? PAGE_KERNEL_VSYSCALL
 			     : PAGE_KERNEL_VVAR);
+		set_vsyscall_pgtable_user_bits(swapper_pg_dir);
+	}
 
 	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
 		     (unsigned long)VSYSCALL_ADDR);
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index a6eee5ac4f58..2aefacf5c5b2 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -277,7 +277,7 @@ static int __init amd_power_pmu_init(void)
 	int ret;
 
 	if (!x86_match_cpu(cpu_match))
-		return 0;
+		return -ENODEV;
 
 	if (!boot_cpu_has(X86_FEATURE_ACC_POWER))
 		return -ENODEV;
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 141e07b06216..24ffa1e88cf9 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -582,6 +582,24 @@ static __init int bts_init(void)
 	if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts)
 		return -ENODEV;
 
+	if (boot_cpu_has(X86_FEATURE_PTI)) {
+		/*
+		 * BTS hardware writes through a virtual memory map we must
+		 * either use the kernel physical map, or the user mapping of
+		 * the AUX buffer.
+		 *
+		 * However, since this driver supports per-CPU and per-task inherit
+		 * we cannot use the user mapping since it will not be availble
+		 * if we're not running the owning process.
+		 *
+		 * With PTI we can't use the kernal map either, because its not
+		 * there when we run userspace.
+		 *
+		 * For now, disable this driver when using PTI.
+		 */
+		return -ENODEV;
+	}
+
 	bts_pmu.capabilities	= PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE |
 				  PERF_PMU_CAP_EXCLUSIVE;
 	bts_pmu.task_ctx_nr	= perf_sw_context;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 09c26a4f139c..731153a4681e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3847,6 +3847,8 @@ static struct attribute *intel_pmu_attrs[] = {
 
 __init int intel_pmu_init(void)
 {
+	struct attribute **extra_attr = NULL;
+	struct attribute **to_free = NULL;
 	union cpuid10_edx edx;
 	union cpuid10_eax eax;
 	union cpuid10_ebx ebx;
@@ -3854,7 +3856,6 @@ __init int intel_pmu_init(void)
 	unsigned int unused;
 	struct extra_reg *er;
 	int version, i;
-	struct attribute **extra_attr = NULL;
 	char *name;
 
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
@@ -4294,6 +4295,7 @@ __init int intel_pmu_init(void)
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
 		extra_attr = merge_attr(extra_attr, skl_format_attr);
+		to_free = extra_attr;
 		x86_pmu.cpu_events = get_hsw_events_attrs();
 		intel_pmu_pebs_data_source_skl(
 			boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
@@ -4401,6 +4403,7 @@ __init int intel_pmu_init(void)
 		pr_cont("full-width counters, ");
 	}
 
+	kfree(to_free);
 	return 0;
 }
 
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 3674a4b6f8bd..18c25ab28557 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -3,16 +3,19 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/perf_event.h>
+#include <asm/tlbflush.h>
 #include <asm/insn.h>
 
 #include "../perf_event.h"
 
+/* Waste a full page so it can be mapped into the cpu_entry_area */
+DEFINE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
 /* The size of a BTS record in bytes: */
 #define BTS_RECORD_SIZE		24
 
-#define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
 #define PEBS_FIXUP_SIZE		PAGE_SIZE
 
 /*
@@ -279,17 +282,67 @@ void fini_debug_store_on_cpu(int cpu)
 
 static DEFINE_PER_CPU(void *, insn_buffer);
 
-static int alloc_pebs_buffer(int cpu)
+static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	unsigned long start = (unsigned long)cea;
+	phys_addr_t pa;
+	size_t msz = 0;
+
+	pa = virt_to_phys(addr);
+
+	preempt_disable();
+	for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE)
+		cea_set_pte(cea, pa, prot);
+
+	/*
+	 * This is a cross-CPU update of the cpu_entry_area, we must shoot down
+	 * all TLB entries for it.
+	 */
+	flush_tlb_kernel_range(start, start + size);
+	preempt_enable();
+}
+
+static void ds_clear_cea(void *cea, size_t size)
+{
+	unsigned long start = (unsigned long)cea;
+	size_t msz = 0;
+
+	preempt_disable();
+	for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE)
+		cea_set_pte(cea, 0, PAGE_NONE);
+
+	flush_tlb_kernel_range(start, start + size);
+	preempt_enable();
+}
+
+static void *dsalloc_pages(size_t size, gfp_t flags, int cpu)
+{
+	unsigned int order = get_order(size);
 	int node = cpu_to_node(cpu);
-	int max;
-	void *buffer, *ibuffer;
+	struct page *page;
+
+	page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
+	return page ? page_address(page) : NULL;
+}
+
+static void dsfree_pages(const void *buffer, size_t size)
+{
+	if (buffer)
+		free_pages((unsigned long)buffer, get_order(size));
+}
+
+static int alloc_pebs_buffer(int cpu)
+{
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	struct debug_store *ds = hwev->ds;
+	size_t bsiz = x86_pmu.pebs_buffer_size;
+	int max, node = cpu_to_node(cpu);
+	void *buffer, *ibuffer, *cea;
 
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
+	buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -300,99 +353,94 @@ static int alloc_pebs_buffer(int cpu)
 	if (x86_pmu.intel_cap.pebs_format < 2) {
 		ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
 		if (!ibuffer) {
-			kfree(buffer);
+			dsfree_pages(buffer, bsiz);
 			return -ENOMEM;
 		}
 		per_cpu(insn_buffer, cpu) = ibuffer;
 	}
-
-	max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
-
-	ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+	hwev->ds_pebs_vaddr = buffer;
+	/* Update the cpu entry area mapping */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+	ds->pebs_buffer_base = (unsigned long) cea;
+	ds_update_cea(cea, buffer, bsiz, PAGE_KERNEL);
 	ds->pebs_index = ds->pebs_buffer_base;
-	ds->pebs_absolute_maximum = ds->pebs_buffer_base +
-		max * x86_pmu.pebs_record_size;
-
+	max = x86_pmu.pebs_record_size * (bsiz / x86_pmu.pebs_record_size);
+	ds->pebs_absolute_maximum = ds->pebs_buffer_base + max;
 	return 0;
 }
 
 static void release_pebs_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	void *cea;
 
-	if (!ds || !x86_pmu.pebs)
+	if (!x86_pmu.pebs)
 		return;
 
 	kfree(per_cpu(insn_buffer, cpu));
 	per_cpu(insn_buffer, cpu) = NULL;
 
-	kfree((void *)(unsigned long)ds->pebs_buffer_base);
-	ds->pebs_buffer_base = 0;
+	/* Clear the fixmap */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+	ds_clear_cea(cea, x86_pmu.pebs_buffer_size);
+	dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size);
+	hwev->ds_pebs_vaddr = NULL;
 }
 
 static int alloc_bts_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-	int node = cpu_to_node(cpu);
-	int max, thresh;
-	void *buffer;
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	struct debug_store *ds = hwev->ds;
+	void *buffer, *cea;
+	int max;
 
 	if (!x86_pmu.bts)
 		return 0;
 
-	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+	buffer = dsalloc_pages(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, cpu);
 	if (unlikely(!buffer)) {
 		WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
 		return -ENOMEM;
 	}
-
-	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
-	thresh = max / 16;
-
-	ds->bts_buffer_base = (u64)(unsigned long)buffer;
+	hwev->ds_bts_vaddr = buffer;
+	/* Update the fixmap */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+	ds->bts_buffer_base = (unsigned long) cea;
+	ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
 	ds->bts_index = ds->bts_buffer_base;
-	ds->bts_absolute_maximum = ds->bts_buffer_base +
-		max * BTS_RECORD_SIZE;
-	ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
-		thresh * BTS_RECORD_SIZE;
-
+	max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
+	ds->bts_absolute_maximum = ds->bts_buffer_base + max;
+	ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
 	return 0;
 }
 
 static void release_bts_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	void *cea;
 
-	if (!ds || !x86_pmu.bts)
+	if (!x86_pmu.bts)
 		return;
 
-	kfree((void *)(unsigned long)ds->bts_buffer_base);
-	ds->bts_buffer_base = 0;
+	/* Clear the fixmap */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+	ds_clear_cea(cea, BTS_BUFFER_SIZE);
+	dsfree_pages(hwev->ds_bts_vaddr, BTS_BUFFER_SIZE);
+	hwev->ds_bts_vaddr = NULL;
 }
 
 static int alloc_ds_buffer(int cpu)
 {
-	int node = cpu_to_node(cpu);
-	struct debug_store *ds;
-
-	ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
-	if (unlikely(!ds))
-		return -ENOMEM;
+	struct debug_store *ds = &get_cpu_entry_area(cpu)->cpu_debug_store;
 
+	memset(ds, 0, sizeof(*ds));
 	per_cpu(cpu_hw_events, cpu).ds = ds;
-
 	return 0;
 }
 
 static void release_ds_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
-	if (!ds)
-		return;
-
 	per_cpu(cpu_hw_events, cpu).ds = NULL;
-	kfree(ds);
 }
 
 void release_ds_buffers(void)
@@ -402,16 +450,22 @@ void release_ds_buffers(void)
 	if (!x86_pmu.bts && !x86_pmu.pebs)
 		return;
 
-	get_online_cpus();
-	for_each_online_cpu(cpu)
+	for_each_possible_cpu(cpu)
+		release_ds_buffer(cpu);
+
+	for_each_possible_cpu(cpu) {
+		/*
+		 * Again, ignore errors from offline CPUs, they will no longer
+		 * observe cpu_hw_events.ds and not program the DS_AREA when
+		 * they come up.
+		 */
 		fini_debug_store_on_cpu(cpu);
+	}
 
 	for_each_possible_cpu(cpu) {
 		release_pebs_buffer(cpu);
 		release_bts_buffer(cpu);
-		release_ds_buffer(cpu);
 	}
-	put_online_cpus();
 }
 
 void reserve_ds_buffers(void)
@@ -431,8 +485,6 @@ void reserve_ds_buffers(void)
 	if (!x86_pmu.pebs)
 		pebs_err = 1;
 
-	get_online_cpus();
-
 	for_each_possible_cpu(cpu) {
 		if (alloc_ds_buffer(cpu)) {
 			bts_err = 1;
@@ -469,11 +521,14 @@ void reserve_ds_buffers(void)
 		if (x86_pmu.pebs && !pebs_err)
 			x86_pmu.pebs_active = 1;
 
-		for_each_online_cpu(cpu)
+		for_each_possible_cpu(cpu) {
+			/*
+			 * Ignores wrmsr_on_cpu() errors for offline CPUs they
+			 * will get this call through intel_pmu_cpu_starting().
+			 */
 			init_debug_store_on_cpu(cpu);
+		}
 	}
-
-	put_online_cpus();
 }
 
 /*
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 005908ee9333..a2efb490f743 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -755,14 +755,14 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X,    hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X,    hsx_rapl_init),
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT,  hsw_rapl_init),
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE,   hsw_rapl_init),
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E,   hsw_rapl_init),
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X,	  hsx_rapl_init),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsx_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init),
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init),
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 14efaa0e8684..18e2628e2d8f 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -10,7 +10,9 @@ enum perf_msr_id {
 	PERF_MSR_SMI			= 4,
 	PERF_MSR_PTSC			= 5,
 	PERF_MSR_IRPERF			= 6,
-
+	PERF_MSR_THERM			= 7,
+	PERF_MSR_THERM_SNAP		= 8,
+	PERF_MSR_THERM_UNIT		= 9,
 	PERF_MSR_EVENT_MAX,
 };
 
@@ -29,6 +31,11 @@ static bool test_irperf(int idx)
 	return boot_cpu_has(X86_FEATURE_IRPERF);
 }
 
+static bool test_therm_status(int idx)
+{
+	return boot_cpu_has(X86_FEATURE_DTHERM);
+}
+
 static bool test_intel(int idx)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
@@ -95,22 +102,28 @@ struct perf_msr {
 	bool	(*test)(int idx);
 };
 
-PMU_EVENT_ATTR_STRING(tsc,    evattr_tsc,    "event=0x00");
-PMU_EVENT_ATTR_STRING(aperf,  evattr_aperf,  "event=0x01");
-PMU_EVENT_ATTR_STRING(mperf,  evattr_mperf,  "event=0x02");
-PMU_EVENT_ATTR_STRING(pperf,  evattr_pperf,  "event=0x03");
-PMU_EVENT_ATTR_STRING(smi,    evattr_smi,    "event=0x04");
-PMU_EVENT_ATTR_STRING(ptsc,   evattr_ptsc,   "event=0x05");
-PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06");
+PMU_EVENT_ATTR_STRING(tsc,				evattr_tsc,		"event=0x00"	);
+PMU_EVENT_ATTR_STRING(aperf,				evattr_aperf,		"event=0x01"	);
+PMU_EVENT_ATTR_STRING(mperf,				evattr_mperf,		"event=0x02"	);
+PMU_EVENT_ATTR_STRING(pperf,				evattr_pperf,		"event=0x03"	);
+PMU_EVENT_ATTR_STRING(smi,				evattr_smi,		"event=0x04"	);
+PMU_EVENT_ATTR_STRING(ptsc,				evattr_ptsc,		"event=0x05"	);
+PMU_EVENT_ATTR_STRING(irperf,				evattr_irperf,		"event=0x06"	);
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin,		evattr_therm,		"event=0x07"	);
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot,	evattr_therm_snap,	"1"		);
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit,		evattr_therm_unit,	"C"		);
 
 static struct perf_msr msr[] = {
-	[PERF_MSR_TSC]    = { 0,		&evattr_tsc,	NULL,		 },
-	[PERF_MSR_APERF]  = { MSR_IA32_APERF,	&evattr_aperf,	test_aperfmperf, },
-	[PERF_MSR_MPERF]  = { MSR_IA32_MPERF,	&evattr_mperf,	test_aperfmperf, },
-	[PERF_MSR_PPERF]  = { MSR_PPERF,	&evattr_pperf,	test_intel,	 },
-	[PERF_MSR_SMI]    = { MSR_SMI_COUNT,	&evattr_smi,	test_intel,	 },
-	[PERF_MSR_PTSC]   = { MSR_F15H_PTSC,	&evattr_ptsc,	test_ptsc,	 },
-	[PERF_MSR_IRPERF] = { MSR_F17H_IRPERF,	&evattr_irperf,	test_irperf,	 },
+	[PERF_MSR_TSC]		= { 0,				&evattr_tsc,		NULL,			},
+	[PERF_MSR_APERF]	= { MSR_IA32_APERF,		&evattr_aperf,		test_aperfmperf,	},
+	[PERF_MSR_MPERF]	= { MSR_IA32_MPERF,		&evattr_mperf,		test_aperfmperf,	},
+	[PERF_MSR_PPERF]	= { MSR_PPERF,			&evattr_pperf,		test_intel,		},
+	[PERF_MSR_SMI]		= { MSR_SMI_COUNT,		&evattr_smi,		test_intel,		},
+	[PERF_MSR_PTSC]		= { MSR_F15H_PTSC,		&evattr_ptsc,		test_ptsc,		},
+	[PERF_MSR_IRPERF]	= { MSR_F17H_IRPERF,		&evattr_irperf,		test_irperf,		},
+	[PERF_MSR_THERM]	= { MSR_IA32_THERM_STATUS,	&evattr_therm,		test_therm_status,	},
+	[PERF_MSR_THERM_SNAP]	= { MSR_IA32_THERM_STATUS,	&evattr_therm_snap,	test_therm_status,	},
+	[PERF_MSR_THERM_UNIT]	= { MSR_IA32_THERM_STATUS,	&evattr_therm_unit,	test_therm_status,	},
 };
 
 static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = {
@@ -161,9 +174,9 @@ static int msr_event_init(struct perf_event *event)
 	if (!msr[cfg].attr)
 		return -EINVAL;
 
-	event->hw.idx = -1;
-	event->hw.event_base = msr[cfg].msr;
-	event->hw.config = cfg;
+	event->hw.idx		= -1;
+	event->hw.event_base	= msr[cfg].msr;
+	event->hw.config	= cfg;
 
 	return 0;
 }
@@ -184,7 +197,7 @@ static void msr_event_update(struct perf_event *event)
 	u64 prev, now;
 	s64 delta;
 
-	/* Careful, an NMI might modify the previous event value. */
+	/* Careful, an NMI might modify the previous event value: */
 again:
 	prev = local64_read(&event->hw.prev_count);
 	now = msr_read_counter(event);
@@ -193,17 +206,22 @@ again:
 		goto again;
 
 	delta = now - prev;
-	if (unlikely(event->hw.event_base == MSR_SMI_COUNT))
+	if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) {
 		delta = sign_extend64(delta, 31);
-
-	local64_add(delta, &event->count);
+		local64_add(delta, &event->count);
+	} else if (unlikely(event->hw.event_base == MSR_IA32_THERM_STATUS)) {
+		/* If valid, extract digital readout, otherwise set to -1: */
+		now = now & (1ULL << 31) ? (now >> 16) & 0x3f :  -1;
+		local64_set(&event->count, now);
+	} else {
+		local64_add(delta, &event->count);
+	}
 }
 
 static void msr_event_start(struct perf_event *event, int flags)
 {
-	u64 now;
+	u64 now = msr_read_counter(event);
 
-	now = msr_read_counter(event);
 	local64_set(&event->hw.prev_count, now);
 }
 
@@ -250,9 +268,7 @@ static int __init msr_init(void)
 	for (i = PERF_MSR_TSC + 1; i < PERF_MSR_EVENT_MAX; i++) {
 		u64 val;
 
-		/*
-		 * Virt sucks arse; you cannot tell if a R/O MSR is present :/
-		 */
+		/* Virt sucks; you cannot tell if a R/O MSR is present :/ */
 		if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val))
 			msr[i].attr = NULL;
 	}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index f7aaadf9331f..8e4ea143ed96 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -14,6 +14,8 @@
 
 #include <linux/perf_event.h>
 
+#include <asm/intel_ds.h>
+
 /* To enable MSR tracing please use the generic trace points. */
 
 /*
@@ -77,8 +79,6 @@ struct amd_nb {
 	struct event_constraint event_constraints[X86_PMC_IDX_MAX];
 };
 
-/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS		8
 #define PEBS_COUNTER_MASK	((1ULL << MAX_PEBS_EVENTS) - 1)
 
 /*
@@ -95,23 +95,6 @@ struct amd_nb {
 	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
 	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)
 
-/*
- * A debug store configuration.
- *
- * We only support architectures that use 64bit fields.
- */
-struct debug_store {
-	u64	bts_buffer_base;
-	u64	bts_index;
-	u64	bts_absolute_maximum;
-	u64	bts_interrupt_threshold;
-	u64	pebs_buffer_base;
-	u64	pebs_index;
-	u64	pebs_absolute_maximum;
-	u64	pebs_interrupt_threshold;
-	u64	pebs_event_reset[MAX_PEBS_EVENTS];
-};
-
 #define PEBS_REGS \
 	(PERF_REG_X86_AX | \
 	 PERF_REG_X86_BX | \
@@ -216,6 +199,8 @@ struct cpu_hw_events {
 	 * Intel DebugStore bits
 	 */
 	struct debug_store	*ds;
+	void			*ds_pebs_vaddr;
+	void			*ds_bts_vaddr;
 	u64			pebs_enabled;
 	int			n_pebs;
 	int			n_large_pebs;
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 189a398290db..a0a206556919 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -239,17 +239,24 @@ void hyperv_report_panic(struct pt_regs *regs, long err)
 }
 EXPORT_SYMBOL_GPL(hyperv_report_panic);
 
-bool hv_is_hypercall_page_setup(void)
+bool hv_is_hyperv_initialized(void)
 {
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 
-	/* Check if the hypercall page is setup */
+	/*
+	 * Ensure that we're really on Hyper-V, and not a KVM or Xen
+	 * emulation of Hyper-V
+	 */
+	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
+		return false;
+
+	/*
+	 * Verify that earlier initialization succeeded by checking
+	 * that the hypercall page is setup
+	 */
 	hypercall_msr.as_uint64 = 0;
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
-	if (!hypercall_msr.enable)
-		return false;
-
-	return true;
+	return hypercall_msr.enable;
 }
-EXPORT_SYMBOL_GPL(hv_is_hypercall_page_setup);
+EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 9cc9e1c1e2db..56c9ebac946f 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -137,7 +137,12 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	}
 
 	if (info->mm) {
+		/*
+		 * AddressSpace argument must match the CR3 with PCID bits
+		 * stripped out.
+		 */
 		flush->address_space = virt_to_phys(info->mm->pgd);
+		flush->address_space &= CR3_ADDR_MASK;
 		flush->flags = 0;
 	} else {
 		flush->address_space = 0;
@@ -219,7 +224,12 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 	}
 
 	if (info->mm) {
+		/*
+		 * AddressSpace argument must match the CR3 with PCID bits
+		 * stripped out.
+		 */
 		flush->address_space = virt_to_phys(info->mm->pgd);
+		flush->address_space &= CR3_ADDR_MASK;
 		flush->flags = 0;
 	} else {
 		flush->address_space = 0;
@@ -278,8 +288,6 @@ void hyperv_setup_mmu_ops(void)
 	if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
 		return;
 
-	setup_clear_cpu_cap(X86_FEATURE_PCID);
-
 	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) {
 		pr_info("Using hypercall for remote TLB flush\n");
 		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 5d6a53fd7521..de690c2d2e33 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -6,7 +6,6 @@ generated-y += unistd_32_ia32.h
 generated-y += unistd_64_x32.h
 generated-y += xen-hypercalls.h
 
-generic-y += clkdev.h
 generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 8d0ec9df1cbe..44f5d79d5105 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -49,7 +49,7 @@ extern int acpi_fix_pin2_polarity;
 extern int acpi_disable_cmcff;
 
 extern u8 acpi_sci_flags;
-extern int acpi_sci_override_gsi;
+extern u32 acpi_sci_override_gsi;
 void acpi_pic_sci_set_trigger(unsigned int, u16);
 
 struct device;
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index dbfd0854651f..cf5961ca8677 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -140,7 +140,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	".popsection\n"							\
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr, feature, 1)			\
-	".popsection"
+	".popsection\n"
 
 #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
 	OLDINSTR_2(oldinstr, 1, 2)					\
@@ -151,7 +151,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr1, feature1, 1)			\
 	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
-	".popsection"
+	".popsection\n"
 
 /*
  * Alternative instructions for different CPU types or capabilities.
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a9e57f08bfa6..98722773391d 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -136,6 +136,7 @@ extern void disconnect_bsp_APIC(int virt_wire_setup);
 extern void disable_local_APIC(void);
 extern void lapic_shutdown(void);
 extern void sync_Arb_IDs(void);
+extern void init_bsp_APIC(void);
 extern void apic_intr_mode_init(void);
 extern void setup_local_APIC(void);
 extern void init_apic_mappings(void);
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index ff700d81e91e..4d111616524b 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -11,7 +11,34 @@
 #include <asm/pgtable.h>
 #include <asm/special_insns.h>
 #include <asm/preempt.h>
+#include <asm/asm.h>
 
 #ifndef CONFIG_X86_CMPXCHG64
 extern void cmpxchg8b_emu(void);
 #endif
+
+#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_X86_32
+#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void);
+#else
+#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void);
+INDIRECT_THUNK(8)
+INDIRECT_THUNK(9)
+INDIRECT_THUNK(10)
+INDIRECT_THUNK(11)
+INDIRECT_THUNK(12)
+INDIRECT_THUNK(13)
+INDIRECT_THUNK(14)
+INDIRECT_THUNK(15)
+#endif
+INDIRECT_THUNK(ax)
+INDIRECT_THUNK(bx)
+INDIRECT_THUNK(cx)
+INDIRECT_THUNK(dx)
+INDIRECT_THUNK(si)
+INDIRECT_THUNK(di)
+INDIRECT_THUNK(bp)
+asmlinkage void __fill_rsb(void);
+asmlinkage void __clear_rsb(void);
+
+#endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 219faaec51df..386a6900e206 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -136,6 +136,7 @@
 #endif
 
 #ifndef __ASSEMBLY__
+#ifndef __BPF__
 /*
  * This output constraint should be used for any inline asm which has a "call"
  * instruction.  Otherwise the asm may be inserted before the frame pointer
@@ -145,5 +146,6 @@
 register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
 #endif
+#endif
 
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 2cbd75dd2fd3..e1c8dab86670 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -127,88 +127,6 @@ typedef u32		compat_old_sigset_t;	/* at least 32 bits */
 
 typedef u32               compat_sigset_word;
 
-typedef union compat_sigval {
-	compat_int_t	sival_int;
-	compat_uptr_t	sival_ptr;
-} compat_sigval_t;
-
-typedef struct compat_siginfo {
-	int si_signo;
-	int si_errno;
-	int si_code;
-
-	union {
-		int _pad[128/sizeof(int) - 3];
-
-		/* kill() */
-		struct {
-			unsigned int _pid;	/* sender's pid */
-			unsigned int _uid;	/* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			compat_timer_t _tid;	/* timer id */
-			int _overrun;		/* overrun count */
-			compat_sigval_t _sigval;	/* same as below */
-			int _sys_private;	/* not to be passed to user */
-			int _overrun_incr;	/* amount to add to overrun */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			unsigned int _pid;	/* sender's pid */
-			unsigned int _uid;	/* sender's uid */
-			compat_sigval_t _sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			unsigned int _pid;	/* which child */
-			unsigned int _uid;	/* sender's uid */
-			int _status;		/* exit code */
-			compat_clock_t _utime;
-			compat_clock_t _stime;
-		} _sigchld;
-
-		/* SIGCHLD (x32 version) */
-		struct {
-			unsigned int _pid;	/* which child */
-			unsigned int _uid;	/* sender's uid */
-			int _status;		/* exit code */
-			compat_s64 _utime;
-			compat_s64 _stime;
-		} _sigchld_x32;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
-		struct {
-			unsigned int _addr;	/* faulting insn/memory ref. */
-			short int _addr_lsb;	/* Valid LSB of the reported address. */
-			union {
-				/* used when si_code=SEGV_BNDERR */
-				struct {
-					compat_uptr_t _lower;
-					compat_uptr_t _upper;
-				} _addr_bnd;
-				/* used when si_code=SEGV_PKUERR */
-				compat_u32 _pkey;
-			};
-		} _sigfault;
-
-		/* SIGPOLL */
-		struct {
-			int _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
-			int _fd;
-		} _sigpoll;
-
-		struct {
-			unsigned int _call_addr; /* calling insn */
-			int _syscall;	/* triggering system call number */
-			unsigned int _arch;	/* AUDIT_ARCH_* of syscall */
-		} _sigsys;
-	} _sifields;
-} compat_siginfo_t;
-
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
 struct compat_ipc64_perm {
@@ -331,4 +249,8 @@ static inline bool in_compat_syscall(void)
 }
 #define in_compat_syscall in_compat_syscall	/* override the generic impl */
 
+struct compat_siginfo;
+int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
+		const siginfo_t *from, bool x32_ABI);
+
 #endif /* _ASM_X86_COMPAT_H */
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
new file mode 100644
index 000000000000..4a7884b8dca5
--- /dev/null
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _ASM_X86_CPU_ENTRY_AREA_H
+#define _ASM_X86_CPU_ENTRY_AREA_H
+
+#include <linux/percpu-defs.h>
+#include <asm/processor.h>
+#include <asm/intel_ds.h>
+
+/*
+ * cpu_entry_area is a percpu region that contains things needed by the CPU
+ * and early entry/exit code.  Real types aren't used for all fields here
+ * to avoid circular header dependencies.
+ *
+ * Every field is a virtual alias of some other allocated backing store.
+ * There is no direct allocation of a struct cpu_entry_area.
+ */
+struct cpu_entry_area {
+	char gdt[PAGE_SIZE];
+
+	/*
+	 * The GDT is just below entry_stack and thus serves (on x86_64) as
+	 * a a read-only guard page.
+	 */
+	struct entry_stack_page entry_stack_page;
+
+	/*
+	 * On x86_64, the TSS is mapped RO.  On x86_32, it's mapped RW because
+	 * we need task switches to work, and task switches write to the TSS.
+	 */
+	struct tss_struct tss;
+
+	char entry_trampoline[PAGE_SIZE];
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Exception stacks used for IST entries.
+	 *
+	 * In the future, this should have a separate slot for each stack
+	 * with guard pages between them.
+	 */
+	char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+#endif
+#ifdef CONFIG_CPU_SUP_INTEL
+	/*
+	 * Per CPU debug store for Intel performance monitoring. Wastes a
+	 * full page at the moment.
+	 */
+	struct debug_store cpu_debug_store;
+	/*
+	 * The actual PEBS/BTS buffers must be mapped to user space
+	 * Reserve enough fixmap PTEs.
+	 */
+	struct debug_store_buffers cpu_debug_buffers;
+#endif
+};
+
+#define CPU_ENTRY_AREA_SIZE	(sizeof(struct cpu_entry_area))
+#define CPU_ENTRY_AREA_TOT_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
+
+DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+
+extern void setup_cpu_entry_areas(void);
+extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
+
+#define	CPU_ENTRY_AREA_RO_IDT		CPU_ENTRY_AREA_BASE
+#define CPU_ENTRY_AREA_PER_CPU		(CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
+
+#define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
+
+#define CPU_ENTRY_AREA_MAP_SIZE			\
+	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE)
+
+extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
+
+static inline struct entry_stack *cpu_entry_stack(int cpu)
+{
+	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
+}
+
+#endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index bf6a76202a77..70eddb3922ff 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -29,6 +29,7 @@ enum cpuid_leafs
 	CPUID_8000_000A_EDX,
 	CPUID_7_ECX,
 	CPUID_8000_0007_EBX,
+	CPUID_7_EDX,
 };
 
 #ifdef CONFIG_X86_FEATURE_NAMES
@@ -79,8 +80,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
 	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 19))
 
 #define DISABLED_MASK_BIT_SET(feature_bit)				\
 	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
@@ -101,8 +103,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
 	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 19))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
@@ -135,6 +138,8 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 	set_bit(bit, (unsigned long *)cpu_caps_set);	\
 } while (0)
 
+#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
+
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index c0b0e9e8aa66..1d9199e1c2ad 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS			18	   /* N 32-bit words worth of info */
+#define NCAPINTS			19	   /* N 32-bit words worth of info */
 #define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
@@ -197,17 +197,21 @@
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
 
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
-
+#define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
+#define X86_FEATURE_RETPOLINE		( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_INTEL_PT		( 7*32+15) /* Intel Processor Trace */
-#define X86_FEATURE_AVX512_4VNNIW	( 7*32+16) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS	( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_CDP_L2		( 7*32+15) /* Code and Data Prioritization L2 */
 
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
+
+#define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -242,6 +246,7 @@
 #define X86_FEATURE_AVX512IFMA		( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
 #define X86_FEATURE_CLFLUSHOPT		( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB		( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_INTEL_PT		( 9*32+25) /* Intel Processor Trace */
 #define X86_FEATURE_AVX512PF		( 9*32+26) /* AVX-512 Prefetch */
 #define X86_FEATURE_AVX512ER		( 9*32+27) /* AVX-512 Exponential and Reciprocal */
 #define X86_FEATURE_AVX512CD		( 9*32+28) /* AVX-512 Conflict Detection */
@@ -266,6 +271,10 @@
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
+#define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_IBRS		(13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_STIBP		(13*32+15) /* Single Thread Indirect Branch Predictors */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -314,6 +323,13 @@
 #define X86_FEATURE_SUCCOR		(17*32+ 1) /* Uncorrectable error containment and recovery */
 #define X86_FEATURE_SMCA		(17*32+ 3) /* Scalable MCA */
 
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
+#define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
+#define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+
 /*
  * BUG word(s)
  */
@@ -339,5 +355,8 @@
 #define X86_BUG_SWAPGS_FENCE		X86_BUG(11) /* SWAPGS without input dep on GS */
 #define X86_BUG_MONITOR			X86_BUG(12) /* IPI required to wake up remote CPU */
 #define X86_BUG_AMD_E400		X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_CPU_MELTDOWN		X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
+#define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
+#define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 4011cb03ef08..13c5ee878a47 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -7,6 +7,7 @@
 #include <asm/mmu.h>
 #include <asm/fixmap.h>
 #include <asm/irq_vectors.h>
+#include <asm/cpu_entry_area.h>
 
 #include <linux/smp.h>
 #include <linux/percpu.h>
@@ -20,6 +21,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
 
 	desc->type		= (info->read_exec_only ^ 1) << 1;
 	desc->type	       |= info->contents << 2;
+	/* Set the ACCESS bit so it can be mapped RO */
+	desc->type	       |= 1;
 
 	desc->s			= 1;
 	desc->dpl		= 0x3;
@@ -60,17 +63,10 @@ static inline struct desc_struct *get_current_gdt_rw(void)
 	return this_cpu_ptr(&gdt_page)->gdt;
 }
 
-/* Get the fixmap index for a specific processor */
-static inline unsigned int get_cpu_gdt_ro_index(int cpu)
-{
-	return FIX_GDT_REMAP_BEGIN + cpu;
-}
-
 /* Provide the fixmap address of the remapped GDT */
 static inline struct desc_struct *get_cpu_gdt_ro(int cpu)
 {
-	unsigned int idx = get_cpu_gdt_ro_index(cpu);
-	return (struct desc_struct *)__fix_to_virt(idx);
+	return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt;
 }
 
 /* Provide the current read-only GDT */
@@ -185,7 +181,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr,
 #endif
 }
 
-static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr)
+static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr)
 {
 	struct desc_struct *d = get_cpu_gdt_rw(cpu);
 	tss_desc tss;
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 14d6d5007314..33833d1909af 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -50,6 +50,12 @@
 # define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
 #endif
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define DISABLE_PTI		0
+#else
+# define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -60,7 +66,7 @@
 #define DISABLED_MASK4	(DISABLE_PCID)
 #define DISABLED_MASK5	0
 #define DISABLED_MASK6	0
-#define DISABLED_MASK7	0
+#define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
 #define DISABLED_MASK9	(DISABLE_MPX)
 #define DISABLED_MASK10	0
@@ -71,6 +77,7 @@
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
 #define DISABLED_MASK17	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define DISABLED_MASK18	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/dma-direct.h b/arch/x86/include/asm/dma-direct.h
new file mode 100644
index 000000000000..1295bc622ebe
--- /dev/null
+++ b/arch/x86/include/asm/dma-direct.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ASM_X86_DMA_DIRECT_H
+#define ASM_X86_DMA_DIRECT_H 1
+
+#include <linux/mem_encrypt.h>
+
+#ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */
+bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
+#else
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	if (!dev->dma_mask)
+		return 0;
+
+	return addr + size - 1 <= *dev->dma_mask;
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return __sme_set(paddr);
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+	return __sme_clr(daddr);
+}
+#endif /* CONFIG_X86_DMA_REMAP */
+#endif /* ASM_X86_DMA_DIRECT_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 0350d99bb8fd..6277c83c0eb1 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -12,7 +12,6 @@
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 #include <linux/dma-contiguous.h>
-#include <linux/mem_encrypt.h>
 
 #ifdef CONFIG_ISA
 # define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
@@ -31,6 +30,9 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return dma_ops;
 }
 
+int arch_dma_supported(struct device *dev, u64 mask);
+#define arch_dma_supported arch_dma_supported
+
 bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp);
 #define arch_dma_alloc_attrs arch_dma_alloc_attrs
 
@@ -42,31 +44,6 @@ extern void dma_generic_free_coherent(struct device *dev, size_t size,
 				      void *vaddr, dma_addr_t dma_addr,
 				      unsigned long attrs);
 
-#ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */
-extern bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);
-extern dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
-extern phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
-#else
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return 0;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return __sme_set(paddr);
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return __sme_clr(daddr);
-}
-#endif /* CONFIG_X86_DMA_REMAP */
-
 static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
 						    gfp_t gfp)
 {
diff --git a/arch/x86/include/asm/error-injection.h b/arch/x86/include/asm/error-injection.h
new file mode 100644
index 000000000000..47b7a1296245
--- /dev/null
+++ b/arch/x86/include/asm/error-injection.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ERROR_INJECTION_H
+#define _ASM_ERROR_INJECTION_H
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <asm/ptrace.h>
+#include <asm-generic/error-injection.h>
+
+asmlinkage void just_return_func(void);
+void override_function_with_return(struct pt_regs *regs);
+
+#endif /* _ASM_ERROR_INJECTION_H */
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
index 0211029076ea..6777480d8a42 100644
--- a/arch/x86/include/asm/espfix.h
+++ b/arch/x86/include/asm/espfix.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_ESPFIX_H
 #define _ASM_X86_ESPFIX_H
 
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_ESPFIX64
 
 #include <asm/percpu.h>
 
@@ -11,7 +11,8 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
 
 extern void init_espfix_bsp(void);
 extern void init_espfix_ap(int cpu);
-
-#endif /* CONFIG_X86_64 */
+#else
+static inline void init_espfix_ap(int cpu) { }
+#endif
 
 #endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index b0c505fe9a95..64c4a30e0d39 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -44,7 +44,6 @@ extern unsigned long __FIXADDR_TOP;
 			 PAGE_SIZE)
 #endif
 
-
 /*
  * Here we define all the compile-time 'special' virtual
  * addresses. The point is to have a constant address at
@@ -84,7 +83,6 @@ enum fixed_addresses {
 	FIX_IO_APIC_BASE_0,
 	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
 #endif
-	FIX_RO_IDT,	/* Virtual mapping for read-only IDT */
 #ifdef CONFIG_X86_32
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
@@ -100,9 +98,6 @@ enum fixed_addresses {
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif
-	/* Fixmap entries to remap the GDTs, one per processor. */
-	FIX_GDT_REMAP_BEGIN,
-	FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1,
 
 #ifdef CONFIG_ACPI_APEI_GHES
 	/* Used for GHES mapping from assorted contexts */
@@ -143,7 +138,7 @@ enum fixed_addresses {
 extern void reserve_top_address(unsigned long reserve);
 
 #define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
 
 extern int fixmaps_set;
 
diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h
index 4df2754ef380..44bbc39a57b3 100644
--- a/arch/x86/include/asm/fpu/signal.h
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -20,12 +20,6 @@ int ia32_setup_frame(int sig, struct ksignal *ksig,
 # define ia32_setup_rt_frame	__setup_rt_frame
 #endif
 
-#ifdef CONFIG_COMPAT
-int __copy_siginfo_to_user32(compat_siginfo_t __user *to,
-		const siginfo_t *from, bool x32_ABI);
-#endif
-
-
 extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
 			      struct task_struct *tsk);
 extern void convert_to_fxsr(struct task_struct *tsk,
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 1b0a5abcd8ae..8c5aaba6633f 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -20,16 +20,7 @@
 #ifndef _ASM_X86_HYPERVISOR_H
 #define _ASM_X86_HYPERVISOR_H
 
-#ifdef CONFIG_HYPERVISOR_GUEST
-
-#include <asm/kvm_para.h>
-#include <asm/x86_init.h>
-#include <asm/xen/hypervisor.h>
-
-/*
- * x86 hypervisor information
- */
-
+/* x86 hypervisor types  */
 enum x86_hypervisor_type {
 	X86_HYPER_NATIVE = 0,
 	X86_HYPER_VMWARE,
@@ -37,8 +28,15 @@ enum x86_hypervisor_type {
 	X86_HYPER_XEN_PV,
 	X86_HYPER_XEN_HVM,
 	X86_HYPER_KVM,
+	X86_HYPER_JAILHOUSE,
 };
 
+#ifdef CONFIG_HYPERVISOR_GUEST
+
+#include <asm/kvm_para.h>
+#include <asm/x86_init.h>
+#include <asm/xen/hypervisor.h>
+
 struct hypervisor_x86 {
 	/* Hypervisor name */
 	const char	*name;
@@ -58,7 +56,15 @@ struct hypervisor_x86 {
 
 extern enum x86_hypervisor_type x86_hyper_type;
 extern void init_hypervisor_platform(void);
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+	return x86_hyper_type == type;
+}
 #else
 static inline void init_hypervisor_platform(void) { }
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+	return type == X86_HYPER_NATIVE;
+}
 #endif /* CONFIG_HYPERVISOR_GUEST */
 #endif /* _ASM_X86_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index c8376b40e882..5cdcdbd4d892 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -69,6 +69,11 @@ struct legacy_pic {
 extern struct legacy_pic *legacy_pic;
 extern struct legacy_pic null_legacy_pic;
 
+static inline bool has_legacy_pic(void)
+{
+	return legacy_pic != &null_legacy_pic;
+}
+
 static inline int nr_legacy_irqs(void)
 {
 	return legacy_pic->nr_legacy_irqs;
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
new file mode 100644
index 000000000000..62a9f4966b42
--- /dev/null
+++ b/arch/x86/include/asm/intel_ds.h
@@ -0,0 +1,36 @@
+#ifndef _ASM_INTEL_DS_H
+#define _ASM_INTEL_DS_H
+
+#include <linux/percpu-defs.h>
+
+#define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS		8
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+	u64	bts_buffer_base;
+	u64	bts_index;
+	u64	bts_absolute_maximum;
+	u64	bts_interrupt_threshold;
+	u64	pebs_buffer_base;
+	u64	pebs_index;
+	u64	pebs_absolute_maximum;
+	u64	pebs_interrupt_threshold;
+	u64	pebs_event_reset[MAX_PEBS_EVENTS];
+} __aligned(PAGE_SIZE);
+
+DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
+struct debug_store_buffers {
+	char	bts_buffer[BTS_BUFFER_SIZE];
+	char	pebs_buffer[PEBS_BUFFER_SIZE];
+};
+
+#endif
diff --git a/arch/x86/include/asm/invpcid.h b/arch/x86/include/asm/invpcid.h
new file mode 100644
index 000000000000..989cfa86de85
--- /dev/null
+++ b/arch/x86/include/asm/invpcid.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_INVPCID
+#define _ASM_X86_INVPCID
+
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+			     unsigned long type)
+{
+	struct { u64 d[2]; } desc = { { pcid, addr } };
+
+	/*
+	 * The memory clobber is because the whole point is to invalidate
+	 * stale TLB entries and, especially if we're flushing global
+	 * mappings, we don't want the compiler to reorder any subsequent
+	 * memory accesses before the TLB flush.
+	 *
+	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+	 * invpcid (%rcx), %rax in long mode.
+	 */
+	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR		0
+#define INVPCID_TYPE_SINGLE_CTXT	1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
+#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+				     unsigned long addr)
+{
+	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
+
+#endif /* _ASM_X86_INVPCID */
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index 7d87437bd030..3de0489deade 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -147,6 +147,18 @@ int iosf_mbi_register_pmic_bus_access_notifier(struct notifier_block *nb);
 int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb);
 
 /**
+ * iosf_mbi_unregister_pmic_bus_access_notifier_unlocked - Unregister PMIC bus
+ *                                                         notifier, unlocked
+ *
+ * Like iosf_mbi_unregister_pmic_bus_access_notifier(), but for use when the
+ * caller has already called iosf_mbi_punit_acquire() itself.
+ *
+ * @nb: notifier_block to unregister
+ */
+int iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(
+	struct notifier_block *nb);
+
+/**
  * iosf_mbi_call_pmic_bus_access_notifier_chain - Call PMIC bus notifier chain
  *
  * @val: action to pass into listener's notifier_call function
@@ -154,6 +166,11 @@ int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb);
  */
 int iosf_mbi_call_pmic_bus_access_notifier_chain(unsigned long val, void *v);
 
+/**
+ * iosf_mbi_assert_punit_acquired - Assert that the P-Unit has been acquired.
+ */
+void iosf_mbi_assert_punit_acquired(void);
+
 #else /* CONFIG_IOSF_MBI is not enabled */
 static inline
 bool iosf_mbi_available(void)
@@ -197,12 +214,20 @@ int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb)
 	return 0;
 }
 
+static inline int
+iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(struct notifier_block *nb)
+{
+	return 0;
+}
+
 static inline
 int iosf_mbi_call_pmic_bus_access_notifier_chain(unsigned long val, void *v)
 {
 	return 0;
 }
 
+static inline void iosf_mbi_assert_punit_acquired(void) {}
+
 #endif /* CONFIG_IOSF_MBI */
 
 #endif /* IOSF_MBI_SYMS_H */
diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h
index 139feef467f7..c066ffae222b 100644
--- a/arch/x86/include/asm/irqdomain.h
+++ b/arch/x86/include/asm/irqdomain.h
@@ -44,7 +44,7 @@ extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
 			      unsigned int nr_irqs);
 extern int mp_irqdomain_activate(struct irq_domain *domain,
-				 struct irq_data *irq_data, bool early);
+				 struct irq_data *irq_data, bool reserve);
 extern void mp_irqdomain_deactivate(struct irq_domain *domain,
 				    struct irq_data *irq_data);
 extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index c8ef23f2c28f..89f08955fff7 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -142,6 +142,9 @@ static inline notrace unsigned long arch_local_irq_save(void)
 	swapgs;					\
 	sysretl
 
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(x)		pushfq; popq %rax
+#endif
 #else
 #define INTERRUPT_RETURN		iret
 #define ENABLE_INTERRUPTS_SYSEXIT	sti; sysexit
diff --git a/arch/x86/include/asm/jailhouse_para.h b/arch/x86/include/asm/jailhouse_para.h
new file mode 100644
index 000000000000..875b54376689
--- /dev/null
+++ b/arch/x86/include/asm/jailhouse_para.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL2.0 */
+
+/*
+ * Jailhouse paravirt_ops implementation
+ *
+ * Copyright (c) Siemens AG, 2015-2017
+ *
+ * Authors:
+ *  Jan Kiszka <jan.kiszka@siemens.com>
+ */
+
+#ifndef _ASM_X86_JAILHOUSE_PARA_H
+#define _ASM_X86_JAILHOUSE_PARA_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_JAILHOUSE_GUEST
+bool jailhouse_paravirt(void);
+#else
+static inline bool jailhouse_paravirt(void)
+{
+	return false;
+}
+#endif
+
+#endif /* _ASM_X86_JAILHOUSE_PARA_H */
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index f86a8caa561e..395c9631e000 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_stack_regs(struct pt_regs *regs);
 extern void __show_regs(struct pt_regs *regs, int all);
+extern void show_iret_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);
 
diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/include/asm/kmemcheck.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 9f2e3102e0bb..367d99cff426 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -67,6 +67,8 @@ extern const int kretprobe_blacklist_size;
 void arch_remove_kprobe(struct kprobe *p);
 asmlinkage void kretprobe_trampoline(void);
 
+extern void arch_kprobe_override_function(struct pt_regs *regs);
+
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
 	/* copy of the original instruction */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 034caa1a084e..b24b1c8b3979 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -214,8 +214,6 @@ struct x86_emulate_ops {
 	void (*halt)(struct x86_emulate_ctxt *ctxt);
 	void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
 	int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt);
-	void (*get_fpu)(struct x86_emulate_ctxt *ctxt); /* disables preempt */
-	void (*put_fpu)(struct x86_emulate_ctxt *ctxt); /* reenables preempt */
 	int (*intercept)(struct x86_emulate_ctxt *ctxt,
 			 struct x86_instruction_info *info,
 			 enum x86_intercept_stage stage);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1bfb99770c34..516798431328 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -536,7 +536,20 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu_memory_cache mmu_page_cache;
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
+	/*
+	 * QEMU userspace and the guest each have their own FPU state.
+	 * In vcpu_run, we switch between the user and guest FPU contexts.
+	 * While running a VCPU, the VCPU thread will have the guest FPU
+	 * context.
+	 *
+	 * Note that while the PKRU state lives inside the fpu registers,
+	 * it is switched out separately at VMENTER and VMEXIT time. The
+	 * "guest_fpu" state here contains the guest FPU context, with the
+	 * host PRKU bits.
+	 */
+	struct fpu user_fpu;
 	struct fpu guest_fpu;
+
 	u64 xcr0;
 	u64 guest_supported_xcr0;
 	u32 guest_xstate_size;
@@ -1161,7 +1174,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
 static inline int emulate_instruction(struct kvm_vcpu *vcpu,
 			int emulation_type)
 {
-	return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+	return x86_emulate_instruction(vcpu, 0,
+			emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0);
 }
 
 void kvm_enable_efer_bits(u64);
@@ -1434,4 +1448,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define put_smstate(type, buf, offset, val)                      \
 	*(type *)((buf) + (offset) - 0x7e00) = val
 
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+		unsigned long start, unsigned long end);
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index b1e8d8db921f..96ea4b5ba658 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -376,6 +376,7 @@ struct smca_bank {
 extern struct smca_bank smca_banks[MAX_NR_BANKS];
 
 extern const char *smca_get_long_name(enum smca_bank_types t);
+extern bool amd_mce_is_memory_error(struct mce *m);
 
 extern int mce_threshold_create_device(unsigned int cpu);
 extern int mce_threshold_remove_device(unsigned int cpu);
@@ -384,6 +385,7 @@ extern int mce_threshold_remove_device(unsigned int cpu);
 
 static inline int mce_threshold_create_device(unsigned int cpu) { return 0; };
 static inline int mce_threshold_remove_device(unsigned int cpu) { return 0; };
+static inline bool amd_mce_is_memory_error(struct mce *m) { return false; };
 
 #endif
 
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index c9459a4c3c68..22c5f3e6f820 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -39,7 +39,7 @@ void __init sme_unmap_bootdata(char *real_mode_data);
 
 void __init sme_early_init(void);
 
-void __init sme_encrypt_kernel(void);
+void __init sme_encrypt_kernel(struct boot_params *bp);
 void __init sme_enable(struct boot_params *bp);
 
 int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size);
@@ -67,7 +67,7 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { }
 
 static inline void __init sme_early_init(void) { }
 
-static inline void __init sme_encrypt_kernel(void) { }
+static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
 static inline void __init sme_enable(struct boot_params *bp) { }
 
 static inline bool sme_active(void) { return false; }
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 9ea26f167497..5ff3e8af2c20 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -3,6 +3,7 @@
 #define _ASM_X86_MMU_H
 
 #include <linux/spinlock.h>
+#include <linux/rwsem.h>
 #include <linux/mutex.h>
 #include <linux/atomic.h>
 
@@ -27,7 +28,8 @@ typedef struct {
 	atomic64_t tlb_gen;
 
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
-	struct ldt_struct *ldt;
+	struct rw_semaphore	ldt_usr_sem;
+	struct ldt_struct	*ldt;
 #endif
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 6d16d15d09a0..c931b88982a0 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -50,22 +50,53 @@ struct ldt_struct {
 	 * call gates.  On native, we could merge the ldt_struct and LDT
 	 * allocations, but it's not worth trying to optimize.
 	 */
-	struct desc_struct *entries;
-	unsigned int nr_entries;
+	struct desc_struct	*entries;
+	unsigned int		nr_entries;
+
+	/*
+	 * If PTI is in use, then the entries array is not mapped while we're
+	 * in user mode.  The whole array will be aliased at the addressed
+	 * given by ldt_slot_va(slot).  We use two slots so that we can allocate
+	 * and map, and enable a new LDT without invalidating the mapping
+	 * of an older, still-in-use LDT.
+	 *
+	 * slot will be -1 if this LDT doesn't have an alias mapping.
+	 */
+	int			slot;
 };
 
+/* This is a multiple of PAGE_SIZE. */
+#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
+
+static inline void *ldt_slot_va(int slot)
+{
+#ifdef CONFIG_X86_64
+	return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
+#else
+	BUG();
+#endif
+}
+
 /*
  * Used for LDT copy/destruction.
  */
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
+static inline void init_new_context_ldt(struct mm_struct *mm)
+{
+	mm->context.ldt = NULL;
+	init_rwsem(&mm->context.ldt_usr_sem);
+}
+int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm);
 void destroy_context_ldt(struct mm_struct *mm);
+void ldt_arch_exit_mmap(struct mm_struct *mm);
 #else	/* CONFIG_MODIFY_LDT_SYSCALL */
-static inline int init_new_context_ldt(struct task_struct *tsk,
-				       struct mm_struct *mm)
+static inline void init_new_context_ldt(struct mm_struct *mm) { }
+static inline int ldt_dup_context(struct mm_struct *oldmm,
+				  struct mm_struct *mm)
 {
 	return 0;
 }
-static inline void destroy_context_ldt(struct mm_struct *mm) {}
+static inline void destroy_context_ldt(struct mm_struct *mm) { }
+static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { }
 #endif
 
 static inline void load_mm_ldt(struct mm_struct *mm)
@@ -90,10 +121,31 @@ static inline void load_mm_ldt(struct mm_struct *mm)
 	 * that we can see.
 	 */
 
-	if (unlikely(ldt))
-		set_ldt(ldt->entries, ldt->nr_entries);
-	else
+	if (unlikely(ldt)) {
+		if (static_cpu_has(X86_FEATURE_PTI)) {
+			if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) {
+				/*
+				 * Whoops -- either the new LDT isn't mapped
+				 * (if slot == -1) or is mapped into a bogus
+				 * slot (if slot > 1).
+				 */
+				clear_LDT();
+				return;
+			}
+
+			/*
+			 * If page table isolation is enabled, ldt->entries
+			 * will not be mapped in the userspace pagetables.
+			 * Tell the CPU to access the LDT through the alias
+			 * at ldt_slot_va(ldt->slot).
+			 */
+			set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries);
+		} else {
+			set_ldt(ldt->entries, ldt->nr_entries);
+		}
+	} else {
 		clear_LDT();
+	}
 #else
 	clear_LDT();
 #endif
@@ -132,18 +184,21 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	mutex_init(&mm->context.lock);
+
 	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
 	atomic64_set(&mm->context.tlb_gen, 0);
 
-	#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
 		/* pkey 0 is the default and always allocated */
 		mm->context.pkey_allocation_map = 0x1;
 		/* -1 means unallocated or invalid */
 		mm->context.execute_only_pkey = -1;
 	}
-	#endif
-	return init_new_context_ldt(tsk, mm);
+#endif
+	init_new_context_ldt(mm);
+	return 0;
 }
 static inline void destroy_context(struct mm_struct *mm)
 {
@@ -176,15 +231,16 @@ do {						\
 } while (0)
 #endif
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	paravirt_arch_dup_mmap(oldmm, mm);
+	return ldt_dup_context(oldmm, mm);
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)
 {
 	paravirt_arch_exit_mmap(mm);
+	ldt_arch_exit_mmap(mm);
 }
 
 #ifdef CONFIG_X86_64
@@ -282,33 +338,6 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 }
 
 /*
- * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID
- * bits.  This serves two purposes.  It prevents a nasty situation in
- * which PCID-unaware code saves CR3, loads some other value (with PCID
- * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if
- * the saved ASID was nonzero.  It also means that any bugs involving
- * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger
- * deterministically.
- */
-
-static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid)
-{
-	if (static_cpu_has(X86_FEATURE_PCID)) {
-		VM_WARN_ON_ONCE(asid > 4094);
-		return __sme_pa(mm->pgd) | (asid + 1);
-	} else {
-		VM_WARN_ON_ONCE(asid != 0);
-		return __sme_pa(mm->pgd);
-	}
-}
-
-static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
-{
-	VM_WARN_ON_ONCE(asid > 4094);
-	return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH;
-}
-
-/*
  * This can be used from process context to figure out what the value of
  * CR3 is without needing to do a (slow) __read_cr3().
  *
@@ -317,7 +346,7 @@ static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
  */
 static inline unsigned long __get_current_cr3_fast(void)
 {
-	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm),
+	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
 		this_cpu_read(cpu_tlbstate.loaded_mm_asid));
 
 	/* For now, be very restrictive about when this can be called. */
diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h
index a6bec8028480..6fb923a34309 100644
--- a/arch/x86/include/asm/mpspec_def.h
+++ b/arch/x86/include/asm/mpspec_def.h
@@ -128,9 +128,17 @@ enum mp_irq_source_types {
 	mp_ExtINT = 3
 };
 
-#define MP_IRQDIR_DEFAULT	0
-#define MP_IRQDIR_HIGH		1
-#define MP_IRQDIR_LOW		3
+#define MP_IRQPOL_DEFAULT	0x0
+#define MP_IRQPOL_ACTIVE_HIGH	0x1
+#define MP_IRQPOL_RESERVED	0x2
+#define MP_IRQPOL_ACTIVE_LOW	0x3
+#define MP_IRQPOL_MASK		0x3
+
+#define MP_IRQTRIG_DEFAULT	0x0
+#define MP_IRQTRIG_EDGE		0x4
+#define MP_IRQTRIG_RESERVED	0x8
+#define MP_IRQTRIG_LEVEL	0xc
+#define MP_IRQTRIG_MASK		0xc
 
 #define MP_APIC_ALL	0xFF
 
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 5400add2885b..b52af150cbd8 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -7,6 +7,7 @@
 #include <linux/nmi.h>
 #include <asm/io.h>
 #include <asm/hyperv.h>
+#include <asm/nospec-branch.h>
 
 /*
  * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
@@ -186,10 +187,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 		return U64_MAX;
 
 	__asm__ __volatile__("mov %4, %%r8\n"
-			     "call *%5"
+			     CALL_NOSPEC
 			     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 			       "+c" (control), "+d" (input_address)
-			     :  "r" (output_address), "m" (hv_hypercall_pg)
+			     :  "r" (output_address),
+				THUNK_TARGET(hv_hypercall_pg)
 			     : "cc", "memory", "r8", "r9", "r10", "r11");
 #else
 	u32 input_address_hi = upper_32_bits(input_address);
@@ -200,13 +202,13 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	if (!hv_hypercall_pg)
 		return U64_MAX;
 
-	__asm__ __volatile__("call *%7"
+	__asm__ __volatile__(CALL_NOSPEC
 			     : "=A" (hv_status),
 			       "+c" (input_address_lo), ASM_CALL_CONSTRAINT
 			     : "A" (control),
 			       "b" (input_address_hi),
 			       "D"(output_address_hi), "S"(output_address_lo),
-			       "m" (hv_hypercall_pg)
+			       THUNK_TARGET(hv_hypercall_pg)
 			     : "cc", "memory");
 #endif /* !x86_64 */
 	return hv_status;
@@ -227,10 +229,10 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 
 #ifdef CONFIG_X86_64
 	{
-		__asm__ __volatile__("call *%4"
+		__asm__ __volatile__(CALL_NOSPEC
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
-				     : "m" (hv_hypercall_pg)
+				     : THUNK_TARGET(hv_hypercall_pg)
 				     : "cc", "r8", "r9", "r10", "r11");
 	}
 #else
@@ -238,13 +240,13 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 		u32 input1_hi = upper_32_bits(input1);
 		u32 input1_lo = lower_32_bits(input1);
 
-		__asm__ __volatile__ ("call *%5"
+		__asm__ __volatile__ (CALL_NOSPEC
 				      : "=A"(hv_status),
 					"+c"(input1_lo),
 					ASM_CALL_CONSTRAINT
 				      :	"A" (control),
 					"b" (input1_hi),
-					"m" (hv_hypercall_pg)
+					THUNK_TARGET(hv_hypercall_pg)
 				      : "cc", "edi", "esi");
 	}
 #endif
@@ -312,11 +314,11 @@ void hyperv_init(void);
 void hyperv_setup_mmu_ops(void);
 void hyper_alloc_mmu(void);
 void hyperv_report_panic(struct pt_regs *regs, long err);
-bool hv_is_hypercall_page_setup(void);
+bool hv_is_hyperv_initialized(void);
 void hyperv_cleanup(void);
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
-static inline bool hv_is_hypercall_page_setup(void) { return false; }
+static inline bool hv_is_hyperv_initialized(void) { return false; }
 static inline void hyperv_cleanup(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}
 #endif /* CONFIG_HYPERV */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 34c4922bbc3f..e520a1e6fc11 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -39,6 +39,13 @@
 
 /* Intel MSRs. Some also available on other CPUs */
 
+#define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
+#define SPEC_CTRL_IBRS			(1 << 0)   /* Indirect Branch Restricted Speculation */
+#define SPEC_CTRL_STIBP			(1 << 1)   /* Single Thread Indirect Branch Predictors */
+
+#define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
+#define PRED_CMD_IBPB			(1 << 0)   /* Indirect Branch Prediction Barrier */
+
 #define MSR_PPIN_CTL			0x0000004e
 #define MSR_PPIN			0x0000004f
 
@@ -57,6 +64,11 @@
 #define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
 
 #define MSR_MTRRcap			0x000000fe
+
+#define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
+#define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
+#define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
+
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
 
@@ -355,6 +367,9 @@
 #define FAM10H_MMIO_CONF_BASE_MASK	0xfffffffULL
 #define FAM10H_MMIO_CONF_BASE_SHIFT	20
 #define MSR_FAM10H_NODE_ID		0xc001100c
+#define MSR_F10H_DECFG			0xc0011029
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT	1
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE		BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
 
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1			0xc001001a
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
new file mode 100644
index 000000000000..d15d471348b8
--- /dev/null
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_X86_NOSPEC_BRANCH_H_
+#define _ASM_X86_NOSPEC_BRANCH_H_
+
+#include <asm/alternative.h>
+#include <asm/alternative-asm.h>
+#include <asm/cpufeatures.h>
+
+#ifdef __ASSEMBLY__
+
+/*
+ * This should be used immediately before a retpoline alternative.  It tells
+ * objtool where the retpolines are so that it can make sense of the control
+ * flow by just reading the original instruction(s) and ignoring the
+ * alternatives.
+ */
+.macro ANNOTATE_NOSPEC_ALTERNATIVE
+	.Lannotate_\@:
+	.pushsection .discard.nospec
+	.long .Lannotate_\@ - .
+	.popsection
+.endm
+
+/*
+ * These are the bare retpoline primitives for indirect jmp and call.
+ * Do not use these directly; they only exist to make the ALTERNATIVE
+ * invocation below less ugly.
+ */
+.macro RETPOLINE_JMP reg:req
+	call	.Ldo_rop_\@
+.Lspec_trap_\@:
+	pause
+	lfence
+	jmp	.Lspec_trap_\@
+.Ldo_rop_\@:
+	mov	\reg, (%_ASM_SP)
+	ret
+.endm
+
+/*
+ * This is a wrapper around RETPOLINE_JMP so the called function in reg
+ * returns to the instruction after the macro.
+ */
+.macro RETPOLINE_CALL reg:req
+	jmp	.Ldo_call_\@
+.Ldo_retpoline_jmp_\@:
+	RETPOLINE_JMP \reg
+.Ldo_call_\@:
+	call	.Ldo_retpoline_jmp_\@
+.endm
+
+/*
+ * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
+ * indirect jmp/call which may be susceptible to the Spectre variant 2
+ * attack.
+ */
+.macro JMP_NOSPEC reg:req
+#ifdef CONFIG_RETPOLINE
+	ANNOTATE_NOSPEC_ALTERNATIVE
+	ALTERNATIVE_2 __stringify(jmp *\reg),				\
+		__stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE,	\
+		__stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
+#else
+	jmp	*\reg
+#endif
+.endm
+
+.macro CALL_NOSPEC reg:req
+#ifdef CONFIG_RETPOLINE
+	ANNOTATE_NOSPEC_ALTERNATIVE
+	ALTERNATIVE_2 __stringify(call *\reg),				\
+		__stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
+		__stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD
+#else
+	call	*\reg
+#endif
+.endm
+
+/* This clobbers the BX register */
+.macro FILL_RETURN_BUFFER nr:req ftr:req
+#ifdef CONFIG_RETPOLINE
+	ALTERNATIVE "", "call __clear_rsb", \ftr
+#endif
+.endm
+
+#else /* __ASSEMBLY__ */
+
+#define ANNOTATE_NOSPEC_ALTERNATIVE				\
+	"999:\n\t"						\
+	".pushsection .discard.nospec\n\t"			\
+	".long 999b - .\n\t"					\
+	".popsection\n\t"
+
+#if defined(CONFIG_X86_64) && defined(RETPOLINE)
+
+/*
+ * Since the inline asm uses the %V modifier which is only in newer GCC,
+ * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE.
+ */
+# define CALL_NOSPEC						\
+	ANNOTATE_NOSPEC_ALTERNATIVE				\
+	ALTERNATIVE(						\
+	"call *%[thunk_target]\n",				\
+	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
+	X86_FEATURE_RETPOLINE)
+# define THUNK_TARGET(addr) [thunk_target] "r" (addr)
+
+#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE)
+/*
+ * For i386 we use the original ret-equivalent retpoline, because
+ * otherwise we'll run out of registers. We don't care about CET
+ * here, anyway.
+ */
+# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n",	\
+	"       jmp    904f;\n"					\
+	"       .align 16\n"					\
+	"901:	call   903f;\n"					\
+	"902:	pause;\n"					\
+	"    	lfence;\n"					\
+	"       jmp    902b;\n"					\
+	"       .align 16\n"					\
+	"903:	addl   $4, %%esp;\n"				\
+	"       pushl  %[thunk_target];\n"			\
+	"       ret;\n"						\
+	"       .align 16\n"					\
+	"904:	call   901b;\n",				\
+	X86_FEATURE_RETPOLINE)
+
+# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#else /* No retpoline for C / inline asm */
+# define CALL_NOSPEC "call *%[thunk_target]\n"
+# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#endif
+
+/* The Spectre V2 mitigation variants */
+enum spectre_v2_mitigation {
+	SPECTRE_V2_NONE,
+	SPECTRE_V2_RETPOLINE_MINIMAL,
+	SPECTRE_V2_RETPOLINE_MINIMAL_AMD,
+	SPECTRE_V2_RETPOLINE_GENERIC,
+	SPECTRE_V2_RETPOLINE_AMD,
+	SPECTRE_V2_IBRS,
+};
+
+extern char __indirect_thunk_start[];
+extern char __indirect_thunk_end[];
+
+/*
+ * On VMEXIT we must ensure that no RSB predictions learned in the guest
+ * can be followed in the host, by overwriting the RSB completely. Both
+ * retpoline and IBRS mitigations for Spectre v2 need this; only on future
+ * CPUs with IBRS_ATT *might* it be avoided.
+ */
+static inline void vmexit_fill_RSB(void)
+{
+#ifdef CONFIG_RETPOLINE
+	alternative_input("",
+			  "call __fill_rsb",
+			  X86_FEATURE_RETPOLINE,
+			  ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory"));
+#endif
+}
+
+static inline void indirect_branch_prediction_barrier(void)
+{
+	alternative_input("",
+			  "call __ibp_barrier",
+			  X86_FEATURE_USE_IBPB,
+			  ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory"));
+}
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 283efcaac8af..892df375b615 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -927,6 +927,15 @@ extern void default_banner(void);
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),	\
 		  CLBR_NONE,						\
 		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(clobbers)                                        \
+	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
+		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);        \
+		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl);    \
+		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+#endif
+
 #endif	/* CONFIG_X86_32 */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 7a5d6695abd3..eb66fa9cd0fc 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -38,6 +38,7 @@ do {						\
 #define PCI_NOASSIGN_ROMS	0x80000
 #define PCI_ROOT_NO_CRS		0x100000
 #define PCI_NOASSIGN_BARS	0x200000
+#define PCI_BIG_ROOT_WINDOW	0x400000
 
 extern unsigned int pci_probe;
 extern unsigned long pirq_table_addr;
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 4b5e1eafada7..aff42e1da6ee 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -30,6 +30,17 @@ static inline void paravirt_release_p4d(unsigned long pfn) {}
  */
 extern gfp_t __userpte_alloc_gfp;
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
+ * both 8k in size and 8k-aligned.  That lets us just flip bit 12
+ * in a pointer to swap between the two 4k halves.
+ */
+#define PGD_ALLOCATION_ORDER 1
+#else
+#define PGD_ALLOCATION_ORDER 0
+#endif
+
 /*
  * Allocate and free page tables.
  */
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index bc4af5453802..f24df59c40b2 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -158,7 +158,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #endif
 
-#ifdef CONFIG_SMP
 union split_pmd {
 	struct {
 		u32 pmd_low;
@@ -166,6 +165,8 @@ union split_pmd {
 	};
 	pmd_t pmd;
 };
+
+#ifdef CONFIG_SMP
 static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 {
 	union split_pmd res, *orig = (union split_pmd *)pmdp;
@@ -181,6 +182,40 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
 #endif
 
+#ifndef pmdp_establish
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	pmd_t old;
+
+	/*
+	 * If pmd has present bit cleared we can get away without expensive
+	 * cmpxchg64: we can update pmdp half-by-half without racing with
+	 * anybody.
+	 */
+	if (!(pmd_val(pmd) & _PAGE_PRESENT)) {
+		union split_pmd old, new, *ptr;
+
+		ptr = (union split_pmd *)pmdp;
+
+		new.pmd = pmd;
+
+		/* xchg acts as a barrier before setting of the high bits */
+		old.pmd_low = xchg(&ptr->pmd_low, new.pmd_low);
+		old.pmd_high = ptr->pmd_high;
+		ptr->pmd_high = new.pmd_high;
+		return old.pmd;
+	}
+
+	do {
+		old = *pmdp;
+	} while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd);
+
+	return old;
+}
+#endif
+
 #ifdef CONFIG_SMP
 union split_pud {
 	struct {
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 09f9e1e00e3b..63c2552b6b65 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -28,6 +28,7 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD];
 int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
 
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
 void ptdump_walk_pgd_level_checkwx(void);
 
 #ifdef CONFIG_DEBUG_WX
@@ -841,7 +842,12 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
 
 static inline int p4d_bad(p4d_t p4d)
 {
-	return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+	unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;
+
+	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+		ignore_flags |= _PAGE_NX;
+
+	return (p4d_flags(p4d) & ~ignore_flags) != 0;
 }
 #endif  /* CONFIG_PGTABLE_LEVELS > 3 */
 
@@ -875,7 +881,12 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 
 static inline int pgd_bad(pgd_t pgd)
 {
-	return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+	unsigned long ignore_flags = _PAGE_USER;
+
+	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+		ignore_flags |= _PAGE_NX;
+
+	return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
 }
 
 static inline int pgd_none(pgd_t pgd)
@@ -904,7 +915,11 @@ static inline int pgd_none(pgd_t pgd)
  * pgd_offset() returns a (pgd_t *)
  * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
  */
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address)))
+/*
+ * a shortcut to get a pgd_t in a given mm
+ */
+#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
 /*
  * a shortcut which implies the use of the kernel's pgd, instead
  * of a process's
@@ -1061,7 +1076,7 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
 				  unsigned long address, pmd_t *pmdp);
 
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
 	return pmd_flags(pmd) & _PAGE_RW;
@@ -1088,6 +1103,27 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 	clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
 }
 
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+	return pud_flags(pud) & _PAGE_RW;
+}
+
+#ifndef pmdp_establish
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	if (IS_ENABLED(CONFIG_SMP)) {
+		return xchg(pmdp, pmd);
+	} else {
+		pmd_t old = *pmdp;
+		*pmdp = pmd;
+		return old;
+	}
+}
+#endif
+
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
  *
@@ -1100,7 +1136,14 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
  */
 static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
 {
-       memcpy(dst, src, count * sizeof(pgd_t));
+	memcpy(dst, src, count * sizeof(pgd_t));
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+	/* Clone the user space pgd as well */
+	memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src),
+	       count * sizeof(pgd_t));
+#endif
 }
 
 #define PTE_SHIFT ilog2(PTRS_PER_PTE)
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index f2ca9b28fd68..ce245b0cdfca 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -38,13 +38,22 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 #define LAST_PKMAP 1024
 #endif
 
-#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1))	\
-		    & PMD_MASK)
+/*
+ * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
+ * to avoid include recursion hell
+ */
+#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 40)
+
+#define CPU_ENTRY_AREA_BASE				\
+	((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK)
+
+#define PKMAP_BASE		\
+	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
 
 #ifdef CONFIG_HIGHMEM
 # define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
 #else
-# define VMALLOC_END	(FIXADDR_START - 2 * PAGE_SIZE)
+# define VMALLOC_END	(CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
 #endif
 
 #define MODULES_VADDR	VMALLOC_START
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index e9f05331e732..81462e9a34f6 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -131,9 +131,97 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 #endif
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
+ * the user one is in the last 4k.  To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr |= BIT(bit);
+	return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr &= ~BIT(bit);
+	return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+/*
+ * Page table pages are page-aligned.  The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+	unsigned long ptr = (unsigned long)__ptr;
+
+	return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
+}
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return pgd;
+	return __pti_set_user_pgd(pgdp, pgd);
+}
+#else
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	return pgd;
+}
+#endif
+
 static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
+#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL)
+	p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd);
+#else
 	*p4dp = p4d;
+#endif
 }
 
 static inline void native_p4d_clear(p4d_t *p4d)
@@ -147,7 +235,11 @@ static inline void native_p4d_clear(p4d_t *p4d)
 
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	*pgdp = pti_set_user_pgd(pgdp, pgd);
+#else
 	*pgdp = pgd;
+#endif
 }
 
 static inline void native_pgd_clear(pgd_t *pgd)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 6d5f45dcd4a1..6b8f73dcbc2c 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -75,33 +75,52 @@ typedef struct { pteval_t pte; } pte_t;
 #define PGDIR_SIZE	(_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
-/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
-#define MAXMEM		_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+/*
+ * See Documentation/x86/x86_64/mm.txt for a description of the memory map.
+ *
+ * Be very careful vs. KASLR when changing anything here. The KASLR address
+ * range must not overlap with anything except the KASAN shadow area, which
+ * is correct as KASAN disables KASLR.
+ */
+#define MAXMEM			_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+
 #ifdef CONFIG_X86_5LEVEL
-#define VMALLOC_SIZE_TB _AC(16384, UL)
-#define __VMALLOC_BASE	_AC(0xff92000000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffd4000000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(12800, UL)
+# define __VMALLOC_BASE		_AC(0xffa0000000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffd4000000000000, UL)
+# define LDT_PGD_ENTRY		_AC(-112, UL)
+# define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 #else
-#define VMALLOC_SIZE_TB	_AC(32, UL)
-#define __VMALLOC_BASE	_AC(0xffffc90000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffffea0000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(32, UL)
+# define __VMALLOC_BASE		_AC(0xffffc90000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffffea0000000000, UL)
+# define LDT_PGD_ENTRY		_AC(-3, UL)
+# define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 #endif
+
 #ifdef CONFIG_RANDOMIZE_MEMORY
-#define VMALLOC_START	vmalloc_base
-#define VMEMMAP_START	vmemmap_base
+# define VMALLOC_START		vmalloc_base
+# define VMEMMAP_START		vmemmap_base
 #else
-#define VMALLOC_START	__VMALLOC_BASE
-#define VMEMMAP_START	__VMEMMAP_BASE
+# define VMALLOC_START		__VMALLOC_BASE
+# define VMEMMAP_START		__VMEMMAP_BASE
 #endif /* CONFIG_RANDOMIZE_MEMORY */
-#define VMALLOC_END	(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
-#define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
+
+#define VMALLOC_END		(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
+
+#define MODULES_VADDR		(__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 /* The module sections ends with the start of the fixmap */
-#define MODULES_END   __fix_to_virt(__end_of_fixed_addresses + 1)
-#define MODULES_LEN   (MODULES_END - MODULES_VADDR)
-#define ESPFIX_PGD_ENTRY _AC(-2, UL)
-#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
-#define EFI_VA_START	 ( -4 * (_AC(1, UL) << 30))
-#define EFI_VA_END	 (-68 * (_AC(1, UL) << 30))
+#define MODULES_END		_AC(0xffffffffff000000, UL)
+#define MODULES_LEN		(MODULES_END - MODULES_VADDR)
+
+#define ESPFIX_PGD_ENTRY	_AC(-2, UL)
+#define ESPFIX_BASE_ADDR	(ESPFIX_PGD_ENTRY << P4D_SHIFT)
+
+#define CPU_ENTRY_AREA_PGD	_AC(-4, UL)
+#define CPU_ENTRY_AREA_BASE	(CPU_ENTRY_AREA_PGD << P4D_SHIFT)
+
+#define EFI_VA_START		( -4 * (_AC(1, UL) << 30))
+#define EFI_VA_END		(-68 * (_AC(1, UL) << 30))
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 43212a43ee69..625a52a5594f 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -38,6 +38,11 @@
 #define CR3_ADDR_MASK	__sme_clr(0x7FFFFFFFFFFFF000ull)
 #define CR3_PCID_MASK	0xFFFull
 #define CR3_NOFLUSH	BIT_ULL(63)
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define X86_CR3_PTI_PCID_USER_BIT	11
+#endif
+
 #else
 /*
  * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index cc16fa882e3e..efbde088a718 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -163,9 +163,9 @@ enum cpuid_regs_idx {
 extern struct cpuinfo_x86	boot_cpu_data;
 extern struct cpuinfo_x86	new_cpu_data;
 
-extern struct tss_struct	doublefault_tss;
-extern __u32			cpu_caps_cleared[NCAPINTS];
-extern __u32			cpu_caps_set[NCAPINTS];
+extern struct x86_hw_tss	doublefault_tss;
+extern __u32			cpu_caps_cleared[NCAPINTS + NBUGINTS];
+extern __u32			cpu_caps_set[NCAPINTS + NBUGINTS];
 
 #ifdef CONFIG_SMP
 DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
@@ -253,6 +253,11 @@ static inline void load_cr3(pgd_t *pgdir)
 	write_cr3(__sme_pa(pgdir));
 }
 
+/*
+ * Note that while the legacy 'TSS' name comes from 'Task State Segment',
+ * on modern x86 CPUs the TSS also holds information important to 64-bit mode,
+ * unrelated to the task-switch mechanism:
+ */
 #ifdef CONFIG_X86_32
 /* This is the TSS defined by the hardware. */
 struct x86_hw_tss {
@@ -305,7 +310,13 @@ struct x86_hw_tss {
 struct x86_hw_tss {
 	u32			reserved1;
 	u64			sp0;
+
+	/*
+	 * We store cpu_current_top_of_stack in sp1 so it's always accessible.
+	 * Linux does not use ring 1, so sp1 is not otherwise needed.
+	 */
 	u64			sp1;
+
 	u64			sp2;
 	u64			reserved2;
 	u64			ist[7];
@@ -323,12 +334,22 @@ struct x86_hw_tss {
 #define IO_BITMAP_BITS			65536
 #define IO_BITMAP_BYTES			(IO_BITMAP_BITS/8)
 #define IO_BITMAP_LONGS			(IO_BITMAP_BYTES/sizeof(long))
-#define IO_BITMAP_OFFSET		offsetof(struct tss_struct, io_bitmap)
+#define IO_BITMAP_OFFSET		(offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss))
 #define INVALID_IO_BITMAP_OFFSET	0x8000
 
+struct entry_stack {
+	unsigned long		words[64];
+};
+
+struct entry_stack_page {
+	struct entry_stack stack;
+} __aligned(PAGE_SIZE);
+
 struct tss_struct {
 	/*
-	 * The hardware state:
+	 * The fixed hardware portion.  This must not cross a page boundary
+	 * at risk of violating the SDM's advice and potentially triggering
+	 * errata.
 	 */
 	struct x86_hw_tss	x86_tss;
 
@@ -339,18 +360,9 @@ struct tss_struct {
 	 * be within the limit.
 	 */
 	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
+} __aligned(PAGE_SIZE);
 
-#ifdef CONFIG_X86_32
-	/*
-	 * Space for the temporary SYSENTER stack.
-	 */
-	unsigned long		SYSENTER_stack_canary;
-	unsigned long		SYSENTER_stack[64];
-#endif
-
-} ____cacheline_aligned;
-
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
+DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
 
 /*
  * sizeof(unsigned long) coming from an extra "long" at the end
@@ -364,6 +376,9 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
 
 #ifdef CONFIG_X86_32
 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
+#else
+/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */
+#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
 #endif
 
 /*
@@ -523,7 +538,7 @@ static inline void native_set_iopl_mask(unsigned mask)
 static inline void
 native_load_sp0(unsigned long sp0)
 {
-	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
+	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
 static inline void native_swapgs(void)
@@ -535,12 +550,12 @@ static inline void native_swapgs(void)
 
 static inline unsigned long current_top_of_stack(void)
 {
-#ifdef CONFIG_X86_64
-	return this_cpu_read_stable(cpu_tss.x86_tss.sp0);
-#else
-	/* sp0 on x86_32 is special in and around vm86 mode. */
+	/*
+	 *  We can't read directly from tss.sp0: sp0 on x86_32 is special in
+	 *  and around vm86 mode and sp0 on x86_64 is special because of the
+	 *  entry trampoline.
+	 */
 	return this_cpu_read_stable(cpu_current_top_of_stack);
-#endif
 }
 
 static inline bool on_thread_stack(void)
@@ -837,13 +852,22 @@ static inline void spin_lock_prefetch(const void *x)
 
 #else
 /*
- * User space process size. 47bits minus one guard page.  The guard
- * page is necessary on Intel CPUs: if a SYSCALL instruction is at
- * the highest possible canonical userspace address, then that
- * syscall will enter the kernel with a non-canonical return
- * address, and SYSRET will explode dangerously.  We avoid this
- * particular problem by preventing anything from being mapped
- * at the maximum canonical address.
+ * User space process size.  This is the first address outside the user range.
+ * There are a few constraints that determine this:
+ *
+ * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
+ * address, then that syscall will enter the kernel with a
+ * non-canonical return address, and SYSRET will explode dangerously.
+ * We avoid this particular problem by preventing anything executable
+ * from being mapped at the maximum canonical address.
+ *
+ * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
+ * CPUs malfunction if they execute code from the highest canonical page.
+ * They'll speculate right off the end of the canonical space, and
+ * bad things happen.  This is worked around in the same way as the
+ * Intel problem.
+ *
+ * With page table isolation enabled, we map the LDT in ... [stay tuned]
  */
 #define TASK_SIZE_MAX	((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
 
@@ -947,4 +971,7 @@ bool xen_set_default_idle(void);
 
 void stop_this_cpu(void *dummy);
 void df_debug(struct pt_regs *regs, long error_code);
+
+void __ibp_barrier(void);
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
new file mode 100644
index 000000000000..0b5ef05b2d2d
--- /dev/null
+++ b/arch/x86/include/asm/pti.h
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _ASM_X86_PTI_H
+#define _ASM_X86_PTI_H
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern void pti_init(void);
+extern void pti_check_boottime_disable(void);
+#else
+static inline void pti_check_boottime_disable(void) { }
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PTI_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 14131dd06b29..6de1fd3d0097 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -109,6 +109,11 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->ax;
 }
 
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->ax = rc;
+}
+
 /*
  * user_mode(regs) determines whether a register set came from user
  * mode.  On x86_32, this is true if V8086 mode was enabled OR if the
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index d91ba04dd007..fb3a6de7440b 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -106,6 +106,7 @@
 #define REQUIRED_MASK15	0
 #define REQUIRED_MASK16	(NEED_LA57)
 #define REQUIRED_MASK17	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define REQUIRED_MASK18	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index b20f9d623f9c..8f09012b92e7 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -236,11 +236,23 @@
  */
 #define EARLY_IDT_HANDLER_SIZE 9
 
+/*
+ * xen_early_idt_handler_array is for Xen pv guests: for each entry in
+ * early_idt_handler_array it contains a prequel in the form of
+ * pop %rcx; pop %r11; jmp early_idt_handler_array[i]; summing up to
+ * max 8 bytes.
+ */
+#define XEN_EARLY_IDT_HANDLER_SIZE 8
+
 #ifndef __ASSEMBLY__
 
 extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
 extern void early_ignore_irq(void);
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV)
+extern const char xen_early_idt_handler_array[NUM_EXCEPTION_VECTORS][XEN_EARLY_IDT_HANDLER_SIZE];
+#endif
+
 /*
  * Load a segment. Fall back on loading the zero segment if something goes
  * wrong.  This variant assumes that loading zero fully clears the segment.
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 8da111b3c342..f73706878772 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -16,6 +16,7 @@ enum stack_type {
 	STACK_TYPE_TASK,
 	STACK_TYPE_IRQ,
 	STACK_TYPE_SOFTIRQ,
+	STACK_TYPE_ENTRY,
 	STACK_TYPE_EXCEPTION,
 	STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
 };
@@ -28,6 +29,8 @@ struct stack_info {
 bool in_task_stack(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info);
 
+bool in_entry_stack(unsigned long *stack, struct stack_info *info);
+
 int get_stack_info(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info, unsigned long *visit_mask);
 
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 982c325dad33..8be6afb58471 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -12,7 +12,13 @@
 
 /* image of the saved processor state */
 struct saved_context {
-	u16 es, fs, gs, ss;
+	/*
+	 * On x86_32, all segment registers, with the possible exception of
+	 * gs, are saved at kernel entry in pt_regs.
+	 */
+#ifdef CONFIG_X86_32_LAZY_GS
+	u16 gs;
+#endif
 	unsigned long cr0, cr2, cr3, cr4;
 	u64 misc_enable;
 	bool misc_enable_saved;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 7306e911faee..a7af9f53c0cb 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -20,8 +20,20 @@
  */
 struct saved_context {
 	struct pt_regs regs;
-	u16 ds, es, fs, gs, ss;
-	unsigned long gs_base, gs_kernel_base, fs_base;
+
+	/*
+	 * User CS and SS are saved in current_pt_regs().  The rest of the
+	 * segment selectors need to be saved and restored here.
+	 */
+	u16 ds, es, fs, gs;
+
+	/*
+	 * Usermode FSBASE and GSBASE may not match the fs and gs selectors,
+	 * so we save them separately.  We save the kernelmode GSBASE to
+	 * restore percpu access after resume.
+	 */
+	unsigned long kernelmode_gs_base, usermode_gs_base, fs_base;
+
 	unsigned long cr0, cr2, cr3, cr4, cr8;
 	u64 misc_enable;
 	bool misc_enable_saved;
@@ -30,8 +42,7 @@ struct saved_context {
 	u16 gdt_pad; /* Unused */
 	struct desc_ptr gdt_desc;
 	u16 idt_pad;
-	u16 idt_limit;
-	unsigned long idt_base;
+	struct desc_ptr idt;
 	u16 ldt;
 	u16 tss;
 	unsigned long tr;
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
index bdf9aed40403..1c6a6cb230ff 100644
--- a/arch/x86/include/asm/swiotlb.h
+++ b/arch/x86/include/asm/swiotlb.h
@@ -28,8 +28,6 @@ static inline void pci_swiotlb_late_init(void)
 }
 #endif
 
-static inline void dma_mark_clean(void *addr, size_t size) {}
-
 extern void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 					dma_addr_t *dma_handle, gfp_t flags,
 					unsigned long attrs);
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 8c6bd6863db9..eb5f7999a893 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -16,8 +16,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		      struct tss_struct *tss);
 
 /* This runs runs on the previous thread's stack. */
-static inline void prepare_switch_to(struct task_struct *prev,
-				     struct task_struct *next)
+static inline void prepare_switch_to(struct task_struct *next)
 {
 #ifdef CONFIG_VMAP_STACK
 	/*
@@ -70,7 +69,7 @@ struct fork_frame {
 
 #define switch_to(prev, next, last)					\
 do {									\
-	prepare_switch_to(prev, next);					\
+	prepare_switch_to(next);					\
 									\
 	((last) = __switch_to_asm((prev), (next)));			\
 } while (0)
@@ -79,10 +78,10 @@ do {									\
 static inline void refresh_sysenter_cs(struct thread_struct *thread)
 {
 	/* Only happens when SEP is enabled, no need to test "SEP"arately: */
-	if (unlikely(this_cpu_read(cpu_tss.x86_tss.ss1) == thread->sysenter_cs))
+	if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs))
 		return;
 
-	this_cpu_write(cpu_tss.x86_tss.ss1, thread->sysenter_cs);
+	this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs);
 	wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
 }
 #endif
@@ -90,10 +89,12 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
 /* This is used when switching tasks or entering/exiting vm86 mode. */
 static inline void update_sp0(struct task_struct *task)
 {
+	/* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */
 #ifdef CONFIG_X86_32
 	load_sp0(task->thread.sp0);
 #else
-	load_sp0(task_top_of_stack(task));
+	if (static_cpu_has(X86_FEATURE_XENPV))
+		load_sp0(task_top_of_stack(task));
 #endif
 }
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 70f425947dc5..d25a638a2720 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -62,8 +62,6 @@ struct thread_info {
 	.flags		= 0,			\
 }
 
-#define init_stack		(init_thread_union.stack)
-
 #else /* !__ASSEMBLY__ */
 
 #include <asm/asm-offsets.h>
@@ -207,7 +205,7 @@ static inline int arch_within_stack_frames(const void * const stack,
 #else /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_64
-# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
+# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1)
 #endif
 
 #endif
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 509046cfa5ce..d33e4a26dc7e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -9,70 +9,130 @@
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
 #include <asm/smp.h>
+#include <asm/invpcid.h>
+#include <asm/pti.h>
+#include <asm/processor-flags.h>
 
-static inline void __invpcid(unsigned long pcid, unsigned long addr,
-			     unsigned long type)
-{
-	struct { u64 d[2]; } desc = { { pcid, addr } };
+/*
+ * The x86 feature is called PCID (Process Context IDentifier). It is similar
+ * to what is traditionally called ASID on the RISC processors.
+ *
+ * We don't use the traditional ASID implementation, where each process/mm gets
+ * its own ASID and flush/restart when we run out of ASID space.
+ *
+ * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
+ * that came by on this CPU, allowing cheaper switch_mm between processes on
+ * this CPU.
+ *
+ * We end up with different spaces for different things. To avoid confusion we
+ * use different names for each of them:
+ *
+ * ASID  - [0, TLB_NR_DYN_ASIDS-1]
+ *         the canonical identifier for an mm
+ *
+ * kPCID - [1, TLB_NR_DYN_ASIDS]
+ *         the value we write into the PCID part of CR3; corresponds to the
+ *         ASID+1, because PCID 0 is special.
+ *
+ * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
+ *         for KPTI each mm has two address spaces and thus needs two
+ *         PCID values, but we can still do with a single ASID denomination
+ *         for each mm. Corresponds to kPCID + 2048.
+ *
+ */
 
-	/*
-	 * The memory clobber is because the whole point is to invalidate
-	 * stale TLB entries and, especially if we're flushing global
-	 * mappings, we don't want the compiler to reorder any subsequent
-	 * memory accesses before the TLB flush.
-	 *
-	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
-	 * invpcid (%rcx), %rax in long mode.
-	 */
-	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
-		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
-}
+/* There are 12 bits of space for ASIDS in CR3 */
+#define CR3_HW_ASID_BITS		12
 
-#define INVPCID_TYPE_INDIV_ADDR		0
-#define INVPCID_TYPE_SINGLE_CTXT	1
-#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
-#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+/*
+ * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
+ * user/kernel switches
+ */
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define PTI_CONSUMED_PCID_BITS	1
+#else
+# define PTI_CONSUMED_PCID_BITS	0
+#endif
 
-/* Flush all mappings for a given pcid and addr, not including globals. */
-static inline void invpcid_flush_one(unsigned long pcid,
-				     unsigned long addr)
-{
-	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
-}
+#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)
+
+/*
+ * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid.  -1 below to account
+ * for them being zero-based.  Another -1 is because PCID 0 is reserved for
+ * use by non-PCID-aware users.
+ */
+#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)
 
-/* Flush all mappings for a given PCID, not including globals. */
-static inline void invpcid_flush_single_context(unsigned long pcid)
+/*
+ * 6 because 6 should be plenty and struct tlb_state will fit in two cache
+ * lines.
+ */
+#define TLB_NR_DYN_ASIDS	6
+
+/*
+ * Given @asid, compute kPCID
+ */
+static inline u16 kern_pcid(u16 asid)
 {
-	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	/*
+	 * Make sure that the dynamic ASID space does not confict with the
+	 * bit we are using to switch between user and kernel ASIDs.
+	 */
+	BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT));
+
+	/*
+	 * The ASID being passed in here should have respected the
+	 * MAX_ASID_AVAILABLE and thus never have the switch bit set.
+	 */
+	VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT));
+#endif
+	/*
+	 * The dynamically-assigned ASIDs that get passed in are small
+	 * (<TLB_NR_DYN_ASIDS).  They never have the high switch bit set,
+	 * so do not bother to clear it.
+	 *
+	 * If PCID is on, ASID-aware code paths put the ASID+1 into the
+	 * PCID bits.  This serves two purposes.  It prevents a nasty
+	 * situation in which PCID-unaware code saves CR3, loads some other
+	 * value (with PCID == 0), and then restores CR3, thus corrupting
+	 * the TLB for ASID 0 if the saved ASID was nonzero.  It also means
+	 * that any bugs involving loading a PCID-enabled CR3 with
+	 * CR4.PCIDE off will trigger deterministically.
+	 */
+	return asid + 1;
 }
 
-/* Flush all mappings, including globals, for all PCIDs. */
-static inline void invpcid_flush_all(void)
+/*
+ * Given @asid, compute uPCID
+ */
+static inline u16 user_pcid(u16 asid)
 {
-	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+	u16 ret = kern_pcid(asid);
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
+#endif
+	return ret;
 }
 
-/* Flush all mappings for all PCIDs except globals. */
-static inline void invpcid_flush_all_nonglobals(void)
+struct pgd_t;
+static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
 {
-	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+	if (static_cpu_has(X86_FEATURE_PCID)) {
+		return __sme_pa(pgd) | kern_pcid(asid);
+	} else {
+		VM_WARN_ON_ONCE(asid != 0);
+		return __sme_pa(pgd);
+	}
 }
 
-static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
 {
-	u64 new_tlb_gen;
-
-	/*
-	 * Bump the generation count.  This also serves as a full barrier
-	 * that synchronizes with switch_mm(): callers are required to order
-	 * their read of mm_cpumask after their writes to the paging
-	 * structures.
-	 */
-	smp_mb__before_atomic();
-	new_tlb_gen = atomic64_inc_return(&mm->context.tlb_gen);
-	smp_mb__after_atomic();
-
-	return new_tlb_gen;
+	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+	VM_WARN_ON_ONCE(!this_cpu_has(X86_FEATURE_PCID));
+	return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
 }
 
 #ifdef CONFIG_PARAVIRT
@@ -99,12 +159,6 @@ static inline bool tlb_defer_switch_to_init_mm(void)
 	return !static_cpu_has(X86_FEATURE_PCID);
 }
 
-/*
- * 6 because 6 should be plenty and struct tlb_state will fit in
- * two cache lines.
- */
-#define TLB_NR_DYN_ASIDS 6
-
 struct tlb_context {
 	u64 ctx_id;
 	u64 tlb_gen;
@@ -139,6 +193,24 @@ struct tlb_state {
 	bool is_lazy;
 
 	/*
+	 * If set we changed the page tables in such a way that we
+	 * needed an invalidation of all contexts (aka. PCIDs / ASIDs).
+	 * This tells us to go invalidate all the non-loaded ctxs[]
+	 * on the next context switch.
+	 *
+	 * The current ctx was kept up-to-date as it ran and does not
+	 * need to be invalidated.
+	 */
+	bool invalidate_other;
+
+	/*
+	 * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate
+	 * the corresponding user PCID needs a flush next time we
+	 * switch to it; see SWITCH_TO_USER_CR3.
+	 */
+	unsigned short user_pcid_flush_mask;
+
+	/*
 	 * Access to this CR4 shadow and to H/W CR4 is protected by
 	 * disabling interrupts when modifying either one.
 	 */
@@ -173,40 +245,43 @@ static inline void cr4_init_shadow(void)
 	this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
 }
 
+static inline void __cr4_set(unsigned long cr4)
+{
+	lockdep_assert_irqs_disabled();
+	this_cpu_write(cpu_tlbstate.cr4, cr4);
+	__write_cr4(cr4);
+}
+
 /* Set in this cpu's CR4. */
 static inline void cr4_set_bits(unsigned long mask)
 {
-	unsigned long cr4;
+	unsigned long cr4, flags;
 
+	local_irq_save(flags);
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	if ((cr4 | mask) != cr4) {
-		cr4 |= mask;
-		this_cpu_write(cpu_tlbstate.cr4, cr4);
-		__write_cr4(cr4);
-	}
+	if ((cr4 | mask) != cr4)
+		__cr4_set(cr4 | mask);
+	local_irq_restore(flags);
 }
 
 /* Clear in this cpu's CR4. */
 static inline void cr4_clear_bits(unsigned long mask)
 {
-	unsigned long cr4;
+	unsigned long cr4, flags;
 
+	local_irq_save(flags);
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	if ((cr4 & ~mask) != cr4) {
-		cr4 &= ~mask;
-		this_cpu_write(cpu_tlbstate.cr4, cr4);
-		__write_cr4(cr4);
-	}
+	if ((cr4 & ~mask) != cr4)
+		__cr4_set(cr4 & ~mask);
+	local_irq_restore(flags);
 }
 
-static inline void cr4_toggle_bits(unsigned long mask)
+static inline void cr4_toggle_bits_irqsoff(unsigned long mask)
 {
 	unsigned long cr4;
 
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	cr4 ^= mask;
-	this_cpu_write(cpu_tlbstate.cr4, cr4);
-	__write_cr4(cr4);
+	__cr4_set(cr4 ^ mask);
 }
 
 /* Read the CR4 shadow. */
@@ -216,6 +291,14 @@ static inline unsigned long cr4_read_shadow(void)
 }
 
 /*
+ * Mark all other ASIDs as invalid, preserves the current.
+ */
+static inline void invalidate_other_asid(void)
+{
+	this_cpu_write(cpu_tlbstate.invalidate_other, true);
+}
+
+/*
  * Save some of cr4 feature set we're using (e.g.  Pentium 4MB
  * enable and PPro Global page enable), so that any CPU's that boot
  * up after us can get the correct flags.  This should only be used
@@ -234,37 +317,63 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
 
 extern void initialize_tlbstate_and_flush(void);
 
-static inline void __native_flush_tlb(void)
+/*
+ * Given an ASID, flush the corresponding user ASID.  We can delay this
+ * until the next time we switch to it.
+ *
+ * See SWITCH_TO_USER_CR3.
+ */
+static inline void invalidate_user_asid(u16 asid)
 {
+	/* There is no user ASID if address space separation is off */
+	if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+		return;
+
 	/*
-	 * If current->mm == NULL then we borrow a mm which may change during a
-	 * task switch and therefore we must not be preempted while we write CR3
-	 * back:
+	 * We only have a single ASID if PCID is off and the CR3
+	 * write will have flushed it.
 	 */
-	preempt_disable();
-	native_write_cr3(__native_read_cr3());
-	preempt_enable();
+	if (!cpu_feature_enabled(X86_FEATURE_PCID))
+		return;
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	__set_bit(kern_pcid(asid),
+		  (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
 }
 
-static inline void __native_flush_tlb_global_irq_disabled(void)
+/*
+ * flush the entire current user mapping
+ */
+static inline void __native_flush_tlb(void)
 {
-	unsigned long cr4;
+	/*
+	 * Preemption or interrupts must be disabled to protect the access
+	 * to the per CPU variable and to prevent being preempted between
+	 * read_cr3() and write_cr3().
+	 */
+	WARN_ON_ONCE(preemptible());
 
-	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	/* clear PGE */
-	native_write_cr4(cr4 & ~X86_CR4_PGE);
-	/* write old PGE again and flush TLBs */
-	native_write_cr4(cr4);
+	invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid));
+
+	/* If current->mm == NULL then the read_cr3() "borrows" an mm */
+	native_write_cr3(__native_read_cr3());
 }
 
+/*
+ * flush everything
+ */
 static inline void __native_flush_tlb_global(void)
 {
-	unsigned long flags;
+	unsigned long cr4, flags;
 
 	if (static_cpu_has(X86_FEATURE_INVPCID)) {
 		/*
 		 * Using INVPCID is considerably faster than a pair of writes
 		 * to CR4 sandwiched inside an IRQ flag save/restore.
+		 *
+		 * Note, this works with CR4.PCIDE=0 or 1.
 		 */
 		invpcid_flush_all();
 		return;
@@ -277,36 +386,69 @@ static inline void __native_flush_tlb_global(void)
 	 */
 	raw_local_irq_save(flags);
 
-	__native_flush_tlb_global_irq_disabled();
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	/* toggle PGE */
+	native_write_cr4(cr4 ^ X86_CR4_PGE);
+	/* write old PGE again and flush TLBs */
+	native_write_cr4(cr4);
 
 	raw_local_irq_restore(flags);
 }
 
+/*
+ * flush one page in the user mapping
+ */
 static inline void __native_flush_tlb_single(unsigned long addr)
 {
+	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+
 	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	/*
+	 * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1.
+	 * Just use invalidate_user_asid() in case we are called early.
+	 */
+	if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE))
+		invalidate_user_asid(loaded_mm_asid);
+	else
+		invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
 }
 
+/*
+ * flush everything
+ */
 static inline void __flush_tlb_all(void)
 {
-	if (boot_cpu_has(X86_FEATURE_PGE))
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		__flush_tlb_global();
-	else
+	} else {
+		/*
+		 * !PGE -> !PCID (setup_pcid()), thus every flush is total.
+		 */
 		__flush_tlb();
-
-	/*
-	 * Note: if we somehow had PCID but not PGE, then this wouldn't work --
-	 * we'd end up flushing kernel translations for the current ASID but
-	 * we might fail to flush kernel translations for other cached ASIDs.
-	 *
-	 * To avoid this issue, we force PCID off if PGE is off.
-	 */
+	}
 }
 
+/*
+ * flush one page in the kernel mapping
+ */
 static inline void __flush_tlb_one(unsigned long addr)
 {
 	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 	__flush_tlb_single(addr);
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	/*
+	 * __flush_tlb_single() will have cleared the TLB entry for this ASID,
+	 * but since kernel space is replicated across all, we must also
+	 * invalidate all others.
+	 */
+	invalidate_other_asid();
 }
 
 #define TLB_FLUSH_ALL	-1UL
@@ -367,6 +509,17 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
 void native_flush_tlb_others(const struct cpumask *cpumask,
 			     const struct flush_tlb_info *info);
 
+static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+{
+	/*
+	 * Bump the generation count.  This also serves as a full barrier
+	 * that synchronizes with switch_mm(): callers are required to order
+	 * their read of mm_cpumask after their writes to the paging
+	 * structures.
+	 */
+	return atomic64_inc_return(&mm->context.tlb_gen);
+}
+
 static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
 					struct mm_struct *mm)
 {
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 84b9ec0c1bc0..22647a642e98 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -283,34 +283,34 @@ TRACE_EVENT(vector_alloc_managed,
 DECLARE_EVENT_CLASS(vector_activate,
 
 	TP_PROTO(unsigned int irq, bool is_managed, bool can_reserve,
-		 bool early),
+		 bool reserve),
 
-	TP_ARGS(irq, is_managed, can_reserve, early),
+	TP_ARGS(irq, is_managed, can_reserve, reserve),
 
 	TP_STRUCT__entry(
 		__field(	unsigned int,	irq		)
 		__field(	bool,		is_managed	)
 		__field(	bool,		can_reserve	)
-		__field(	bool,		early		)
+		__field(	bool,		reserve		)
 	),
 
 	TP_fast_assign(
 		__entry->irq		= irq;
 		__entry->is_managed	= is_managed;
 		__entry->can_reserve	= can_reserve;
-		__entry->early		= early;
+		__entry->reserve	= reserve;
 	),
 
-	TP_printk("irq=%u is_managed=%d can_reserve=%d early=%d",
+	TP_printk("irq=%u is_managed=%d can_reserve=%d reserve=%d",
 		  __entry->irq, __entry->is_managed, __entry->can_reserve,
-		  __entry->early)
+		  __entry->reserve)
 );
 
 #define DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(name)				\
 DEFINE_EVENT_FN(vector_activate, name,					\
 	TP_PROTO(unsigned int irq, bool is_managed,			\
-		 bool can_reserve, bool early),				\
-	TP_ARGS(irq, is_managed, can_reserve, early), NULL, NULL);	\
+		 bool can_reserve, bool reserve),			\
+	TP_ARGS(irq, is_managed, can_reserve, reserve), NULL, NULL);	\
 
 DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_activate);
 DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_deactivate);
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 1fadd310ff68..3de69330e6c5 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -75,7 +75,6 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long);
 dotraplinkage void do_stack_segment(struct pt_regs *, long);
 #ifdef CONFIG_X86_64
 dotraplinkage void do_double_fault(struct pt_regs *, long);
-asmlinkage struct pt_regs *sync_regs(struct pt_regs *);
 #endif
 dotraplinkage void do_general_protection(struct pt_regs *, long);
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
@@ -89,6 +88,7 @@ dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *, long);
 #endif
+dotraplinkage void do_mce(struct pt_regs *, long);
 
 static inline int get_si_code(unsigned long condition)
 {
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index e9cc6fe1fc6f..1f86e1b0a5cd 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -7,6 +7,9 @@
 #include <asm/ptrace.h>
 #include <asm/stacktrace.h>
 
+#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip))
+#define IRET_FRAME_SIZE   (sizeof(struct pt_regs) - IRET_FRAME_OFFSET)
+
 struct unwind_state {
 	struct stack_info stack_info;
 	unsigned long stack_mask;
@@ -52,15 +55,28 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
 }
 
 #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER)
-static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+/*
+ * If 'partial' returns true, only the iret frame registers are valid.
+ */
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state,
+						    bool *partial)
 {
 	if (unwind_done(state))
 		return NULL;
 
+	if (partial) {
+#ifdef CONFIG_UNWINDER_ORC
+		*partial = !state->full_regs;
+#else
+		*partial = false;
+#endif
+	}
+
 	return state->regs;
 }
 #else
-static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state,
+						    bool *partial)
 {
 	return NULL;
 }
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 74f4c2ff6427..d8bfa98fca98 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -53,6 +53,10 @@ struct arch_uprobe {
 			u8	fixups;
 			u8	ilen;
 		} 			defparam;
+		struct {
+			u8	reg_offset;	/* to the start of pt_regs */
+			u8	ilen;
+		}			push;
 	};
 };
 
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 7cac79802ad2..7803114aa140 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -48,7 +48,6 @@
 #define UV2_NET_ENDPOINT_INTD		0x28
 #define UV_NET_ENDPOINT_INTD		(is_uv1_hub() ?			\
 			UV1_NET_ENDPOINT_INTD : UV2_NET_ENDPOINT_INTD)
-#define UV_DESC_PSHIFT			49
 #define UV_PAYLOADQ_GNODE_SHIFT		49
 #define UV_PTC_BASENAME			"sgi_uv/ptc_statistics"
 #define UV_BAU_BASENAME			"sgi_uv/bau_tunables"
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 036e26d63d9a..44cf6d6deb7a 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -241,6 +241,7 @@ static inline int uv_hub_info_check(int version)
 #define UV2_HUB_REVISION_BASE		3
 #define UV3_HUB_REVISION_BASE		5
 #define UV4_HUB_REVISION_BASE		7
+#define UV4A_HUB_REVISION_BASE		8	/* UV4 (fixed) rev 2 */
 
 #ifdef	UV1_HUB_IS_SUPPORTED
 static inline int is_uv1_hub(void)
@@ -280,6 +281,19 @@ static inline int is_uv3_hub(void)
 }
 #endif
 
+/* First test "is UV4A", then "is UV4" */
+#ifdef	UV4A_HUB_IS_SUPPORTED
+static inline int is_uv4a_hub(void)
+{
+	return (uv_hub_info->hub_revision >= UV4A_HUB_REVISION_BASE);
+}
+#else
+static inline int is_uv4a_hub(void)
+{
+	return 0;
+}
+#endif
+
 #ifdef	UV4_HUB_IS_SUPPORTED
 static inline int is_uv4_hub(void)
 {
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index 548d684a7960..ecb9ddef128f 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -39,9 +39,11 @@
  *	#define UV2Hxxx	b
  *	#define UV3Hxxx	c
  *	#define UV4Hxxx	d
+ *	#define UV4AHxxx e
  *	#define UVHxxx	(is_uv1_hub() ? UV1Hxxx :
  *			(is_uv2_hub() ? UV2Hxxx :
  *			(is_uv3_hub() ? UV3Hxxx :
+ *			(is_uv4a_hub() ? UV4AHxxx :
  *					UV4Hxxx))
  *
  * If the MMR exists on all hub types > 1 but have different addresses, the
@@ -49,8 +51,10 @@
  *	#define UV2Hxxx	b
  *	#define UV3Hxxx	c
  *	#define UV4Hxxx	d
+ *	#define UV4AHxxx e
  *	#define UVHxxx	(is_uv2_hub() ? UV2Hxxx :
  *			(is_uv3_hub() ? UV3Hxxx :
+ *			(is_uv4a_hub() ? UV4AHxxx :
  *					UV4Hxxx))
  *
  *	union uvh_xxx {
@@ -63,6 +67,7 @@
  *		} s2;
  *		struct uv3h_xxx_s {	 # Full UV3 definition (*)
  *		} s3;
+ *		(NOTE: No struct uv4ah_xxx_s members exist)
  *		struct uv4h_xxx_s {	 # Full UV4 definition (*)
  *		} s4;
  *	};
@@ -99,6 +104,7 @@
 #define UV2_HUB_IS_SUPPORTED	1
 #define UV3_HUB_IS_SUPPORTED	1
 #define UV4_HUB_IS_SUPPORTED	1
+#define UV4A_HUB_IS_SUPPORTED	1
 
 /* Error function to catch undefined references */
 extern unsigned long uv_undefined(char *str);
@@ -2779,35 +2785,47 @@ union uvh_lb_bau_sb_activation_status_1_u {
 	/*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_BASE_32)
 
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT	12
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	49
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0x7ffe000000000000UL
 
+#define UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	49
 #define UV1H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+#define UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0x7ffe000000000000UL
 
-
+#define UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	49
 #define UV2H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+#define UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0x7ffe000000000000UL
 
+#define UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	49
 #define UV3H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+#define UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0x7ffe000000000000UL
 
+#define UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	49
 #define UV4H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x00003ffffffff000UL
-
-
-union uvh_lb_bau_sb_descriptor_base_u {
-	unsigned long	v;
-	struct uvh_lb_bau_sb_descriptor_base_s {
-		unsigned long	rsvd_0_11:12;
-		unsigned long	rsvd_12_48:37;
-		unsigned long	node_id:14;			/* RW */
-		unsigned long	rsvd_63:1;
-	} s;
-	struct uv4h_lb_bau_sb_descriptor_base_s {
-		unsigned long	rsvd_0_11:12;
-		unsigned long	page_address:34;		/* RW */
-		unsigned long	rsvd_46_48:3;
-		unsigned long	node_id:14;			/* RW */
-		unsigned long	rsvd_63:1;
-	} s4;
-};
+#define UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0x7ffe000000000000UL
+
+#define UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	53
+#define UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000ffffffffff000UL
+#define UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0xffe0000000000000UL
+
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT (			\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT :	\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT :	\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT :	\
+	is_uv4a_hub() ? UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT :	\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT)
+
+#define UVH_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK (			\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK :	\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK :	\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK :	\
+	is_uv4a_hub() ? UV4AH_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK :	\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK)
+
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK (			\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK :	\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK :	\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK :	\
+	is_uv4a_hub() ? UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK :	\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK)
 
 /* ========================================================================= */
 /*                               UVH_NODE_ID                                 */
@@ -3031,6 +3049,41 @@ union uvh_node_present_table_u {
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
 
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
 
 union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
 	unsigned long	v;
@@ -3042,6 +3095,46 @@ union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
 		unsigned long	rsvd_53_62:10;
 		unsigned long	enable:1;			/* RW */
 	} s;
+	struct uv1h_rh_gam_alias210_overlay_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s1;
+	struct uvxh_rh_gam_alias210_overlay_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} sx;
+	struct uv2h_rh_gam_alias210_overlay_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s2;
+	struct uv3h_rh_gam_alias210_overlay_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s3;
+	struct uv4h_rh_gam_alias210_overlay_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3064,6 +3157,41 @@ union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
 
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
 
 union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
 	unsigned long	v;
@@ -3075,6 +3203,46 @@ union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
 		unsigned long	rsvd_53_62:10;
 		unsigned long	enable:1;			/* RW */
 	} s;
+	struct uv1h_rh_gam_alias210_overlay_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s1;
+	struct uvxh_rh_gam_alias210_overlay_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} sx;
+	struct uv2h_rh_gam_alias210_overlay_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s2;
+	struct uv3h_rh_gam_alias210_overlay_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s3;
+	struct uv4h_rh_gam_alias210_overlay_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3097,6 +3265,41 @@ union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
 
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
 
 union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
 	unsigned long	v;
@@ -3108,6 +3311,46 @@ union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
 		unsigned long	rsvd_53_62:10;
 		unsigned long	enable:1;			/* RW */
 	} s;
+	struct uv1h_rh_gam_alias210_overlay_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s1;
+	struct uvxh_rh_gam_alias210_overlay_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} sx;
+	struct uv2h_rh_gam_alias210_overlay_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s2;
+	struct uv3h_rh_gam_alias210_overlay_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s3;
+	struct uv4h_rh_gam_alias210_overlay_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3126,6 +3369,21 @@ union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
 
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
 
 union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
 	unsigned long	v;
@@ -3134,6 +3392,31 @@ union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
 		unsigned long	dest_base:22;			/* RW */
 		unsigned long	rsvd_46_63:18;
 	} s;
+	struct uv1h_rh_gam_alias210_redirect_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s1;
+	struct uvxh_rh_gam_alias210_redirect_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} sx;
+	struct uv2h_rh_gam_alias210_redirect_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s2;
+	struct uv3h_rh_gam_alias210_redirect_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s3;
+	struct uv4h_rh_gam_alias210_redirect_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3152,6 +3435,21 @@ union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
 
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
 
 union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
 	unsigned long	v;
@@ -3160,6 +3458,31 @@ union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
 		unsigned long	dest_base:22;			/* RW */
 		unsigned long	rsvd_46_63:18;
 	} s;
+	struct uv1h_rh_gam_alias210_redirect_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s1;
+	struct uvxh_rh_gam_alias210_redirect_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} sx;
+	struct uv2h_rh_gam_alias210_redirect_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s2;
+	struct uv3h_rh_gam_alias210_redirect_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s3;
+	struct uv4h_rh_gam_alias210_redirect_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3178,6 +3501,21 @@ union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
 
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
 
 union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 	unsigned long	v;
@@ -3186,6 +3524,31 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 		unsigned long	dest_base:22;			/* RW */
 		unsigned long	rsvd_46_63:18;
 	} s;
+	struct uv1h_rh_gam_alias210_redirect_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s1;
+	struct uvxh_rh_gam_alias210_redirect_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} sx;
+	struct uv2h_rh_gam_alias210_redirect_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s2;
+	struct uv3h_rh_gam_alias210_redirect_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s3;
+	struct uv4h_rh_gam_alias210_redirect_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3384,6 +3747,162 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 };
 
 /* ========================================================================= */
+/*                   UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR                    */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR uv_undefined("UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR")
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR uv_undefined("UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR")
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR 0x1603000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR 0x483000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR (				\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR :		\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR :		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR :		\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR)
+
+
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT	26
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT	46
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK	0x00003ffffc000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK	0x000fc00000000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT	26
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT	46
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK	0x00003ffffc000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK	0x000fc00000000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT 52
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK 0x000ffffffc000000UL
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK 0x03f0000000000000UL
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK)
+
+union uvh_rh_gam_mmioh_overlay_config0_mmr_u {
+	unsigned long	v;
+	struct uv3h_rh_gam_mmioh_overlay_config0_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:20;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	rsvd_56_62:7;
+		unsigned long	enable:1;			/* RW */
+	} s3;
+	struct uv4h_rh_gam_mmioh_overlay_config0_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:20;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	rsvd_56_62:7;
+		unsigned long	enable:1;			/* RW */
+	} s4;
+	struct uv4ah_rh_gam_mmioh_overlay_config0_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:26;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	undef_62:1;			/* Undefined */
+		unsigned long	enable:1;			/* RW */
+	} s4a;
+};
+
+/* ========================================================================= */
+/*                   UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR                    */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR uv_undefined("UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR")
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR uv_undefined("UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR")
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x1603000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x483000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR (				\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR :		\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR :		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR :		\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR)
+
+
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_SHFT	26
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT	46
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK	0x00003ffffc000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK	0x000fc00000000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_SHFT	26
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT	46
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK	0x00003ffffc000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK	0x000fc00000000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT 52
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK 0x000ffffffc000000UL
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK 0x03f0000000000000UL
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK)
+
+union uvh_rh_gam_mmioh_overlay_config1_mmr_u {
+	unsigned long	v;
+	struct uv3h_rh_gam_mmioh_overlay_config1_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:20;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	rsvd_56_62:7;
+		unsigned long	enable:1;			/* RW */
+	} s3;
+	struct uv4h_rh_gam_mmioh_overlay_config1_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:20;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	rsvd_56_62:7;
+		unsigned long	enable:1;			/* RW */
+	} s4;
+	struct uv4ah_rh_gam_mmioh_overlay_config1_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:26;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	undef_62:1;			/* Undefined */
+		unsigned long	enable:1;			/* RW */
+	} s4a;
+};
+
+/* ========================================================================= */
 /*                   UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR                     */
 /* ========================================================================= */
 #define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
@@ -3438,6 +3957,112 @@ union uvh_rh_gam_mmioh_overlay_config_mmr_u {
 };
 
 /* ========================================================================= */
+/*                  UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR                    */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR 0x1603800UL
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR 0x483800UL
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR (				\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR :		\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR :		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR :		\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR)
+
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH 128
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH 128
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH (			\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH :	\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH :	\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH)
+
+
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_SHFT 0
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_SHFT 0
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000000fffUL
+
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK)
+
+union uvh_rh_gam_mmioh_redirect_config0_mmr_u {
+	unsigned long	v;
+	struct uv3h_rh_gam_mmioh_redirect_config0_mmr_s {
+		unsigned long	nasid:15;			/* RW */
+		unsigned long	rsvd_15_63:49;
+	} s3;
+	struct uv4h_rh_gam_mmioh_redirect_config0_mmr_s {
+		unsigned long	nasid:15;			/* RW */
+		unsigned long	rsvd_15_63:49;
+	} s4;
+	struct uv4ah_rh_gam_mmioh_redirect_config0_mmr_s {
+		unsigned long	nasid:12;			/* RW */
+		unsigned long	rsvd_12_63:52;
+	} s4a;
+};
+
+/* ========================================================================= */
+/*                  UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR                    */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR 0x1604800UL
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR 0x484800UL
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR (				\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR :		\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR :		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR :		\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR)
+
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH 128
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH 128
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH (			\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH :	\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH :	\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH)
+
+
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_SHFT 0
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_SHFT 0
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000000fffUL
+
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK)
+
+union uvh_rh_gam_mmioh_redirect_config1_mmr_u {
+	unsigned long	v;
+	struct uv3h_rh_gam_mmioh_redirect_config1_mmr_s {
+		unsigned long	nasid:15;			/* RW */
+		unsigned long	rsvd_15_63:49;
+	} s3;
+	struct uv4h_rh_gam_mmioh_redirect_config1_mmr_s {
+		unsigned long	nasid:15;			/* RW */
+		unsigned long	rsvd_15_63:49;
+	} s4;
+	struct uv4ah_rh_gam_mmioh_redirect_config1_mmr_s {
+		unsigned long	nasid:12;			/* RW */
+		unsigned long	rsvd_12_63:52;
+	} s4a;
+};
+
+/* ========================================================================= */
 /*                    UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR                      */
 /* ========================================================================= */
 #define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL
@@ -4138,88 +4763,6 @@ union uv3h_gr0_gam_gr_config_u {
 };
 
 /* ========================================================================= */
-/*                   UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR                   */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR		0x1603000UL
-
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT	26
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT	46
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_SHFT 63
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK	0x00003ffffc000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK	0x000fc00000000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
-
-union uv3h_rh_gam_mmioh_overlay_config0_mmr_u {
-	unsigned long	v;
-	struct uv3h_rh_gam_mmioh_overlay_config0_mmr_s {
-		unsigned long	rsvd_0_25:26;
-		unsigned long	base:20;			/* RW */
-		unsigned long	m_io:6;				/* RW */
-		unsigned long	n_io:4;
-		unsigned long	rsvd_56_62:7;
-		unsigned long	enable:1;			/* RW */
-	} s3;
-};
-
-/* ========================================================================= */
-/*                   UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR                   */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR		0x1604000UL
-
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_SHFT	26
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT	46
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_SHFT 63
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK	0x00003ffffc000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK	0x000fc00000000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_MASK 0x8000000000000000UL
-
-union uv3h_rh_gam_mmioh_overlay_config1_mmr_u {
-	unsigned long	v;
-	struct uv3h_rh_gam_mmioh_overlay_config1_mmr_s {
-		unsigned long	rsvd_0_25:26;
-		unsigned long	base:20;			/* RW */
-		unsigned long	m_io:6;				/* RW */
-		unsigned long	n_io:4;
-		unsigned long	rsvd_56_62:7;
-		unsigned long	enable:1;			/* RW */
-	} s3;
-};
-
-/* ========================================================================= */
-/*                  UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR                   */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR		0x1603800UL
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH	128
-
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_SHFT 0
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000007fffUL
-
-union uv3h_rh_gam_mmioh_redirect_config0_mmr_u {
-	unsigned long	v;
-	struct uv3h_rh_gam_mmioh_redirect_config0_mmr_s {
-		unsigned long	nasid:15;			/* RW */
-		unsigned long	rsvd_15_63:49;
-	} s3;
-};
-
-/* ========================================================================= */
-/*                  UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR                   */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR		0x1604800UL
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH	128
-
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_SHFT 0
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000007fffUL
-
-union uv3h_rh_gam_mmioh_redirect_config1_mmr_u {
-	unsigned long	v;
-	struct uv3h_rh_gam_mmioh_redirect_config1_mmr_s {
-		unsigned long	nasid:15;			/* RW */
-		unsigned long	rsvd_15_63:49;
-	} s3;
-};
-
-/* ========================================================================= */
 /*                       UV4H_LB_PROC_INTD_QUEUE_FIRST                       */
 /* ========================================================================= */
 #define UV4H_LB_PROC_INTD_QUEUE_FIRST			0xa4100UL
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index d9a7c659009c..b986b2ca688a 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -7,6 +7,7 @@
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
 extern void map_vsyscall(void);
+extern void set_vsyscall_pgtable_user_bits(pgd_t *root);
 
 /*
  * Called on instruction fetch fault in vsyscall page.
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index aa4747569e23..fc2f082ac635 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -212,6 +212,7 @@ enum x86_legacy_i8042_state {
 struct x86_legacy_features {
 	enum x86_legacy_i8042_state i8042;
 	int rtc;
+	int warm_reset;
 	int no_vga;
 	int reserve_bios_regions;
 	struct x86_legacy_devices devices;
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 7cb282e9e587..bfd882617613 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -44,6 +44,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/smap.h>
+#include <asm/nospec-branch.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
@@ -217,9 +218,9 @@ privcmd_call(unsigned call,
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
 
 	stac();
-	asm volatile("call *%[call]"
+	asm volatile(CALL_NOSPEC
 		     : __HYPERCALL_5PARAM
-		     : [call] "a" (&hypercall_page[call])
+		     : [thunk_target] "a" (&hypercall_page[call])
 		     : __HYPERCALL_CLOBBER5);
 	clac();
 
diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
index da1489cb64dc..322681622d1e 100644
--- a/arch/x86/include/uapi/asm/Kbuild
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -1,6 +1,8 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generated-y += unistd_32.h
 generated-y += unistd_64.h
 generated-y += unistd_x32.h
+generic-y += poll.h
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index afdd5ae0fcc4..aebf60357758 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -9,6 +9,7 @@
 #define SETUP_PCI			3
 #define SETUP_EFI			4
 #define SETUP_APPLE_PROPERTIES		5
+#define SETUP_JAILHOUSE			6
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
@@ -126,6 +127,27 @@ struct boot_e820_entry {
 	__u32 type;
 } __attribute__((packed));
 
+/*
+ * Smallest compatible version of jailhouse_setup_data required by this kernel.
+ */
+#define JAILHOUSE_SETUP_REQUIRED_VERSION	1
+
+/*
+ * The boot loader is passing platform information via this Jailhouse-specific
+ * setup data structure.
+ */
+struct jailhouse_setup_data {
+	u16	version;
+	u16	compatible_version;
+	u16	pm_timer_address;
+	u16	num_cpus;
+	u64	pci_mmconfig_base;
+	u32	tsc_khz;
+	u32	apic_khz;
+	u8	standard_ioapic;
+	u8	cpu_ids[255];
+} __attribute__((packed));
+
 /* The so-called "zeropage" */
 struct boot_params {
 	struct screen_info screen_info;			/* 0x000 */
diff --git a/arch/x86/include/uapi/asm/poll.h b/arch/x86/include/uapi/asm/poll.h
deleted file mode 100644
index c98509d3149e..000000000000
--- a/arch/x86/include/uapi/asm/poll.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/poll.h>
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 7e1e730396ae..bcba3c643e63 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -78,7 +78,12 @@
 #define X86_CR3_PWT		_BITUL(X86_CR3_PWT_BIT)
 #define X86_CR3_PCD_BIT		4 /* Page Cache Disable */
 #define X86_CR3_PCD		_BITUL(X86_CR3_PCD_BIT)
-#define X86_CR3_PCID_MASK	_AC(0x00000fff,UL) /* PCID Mask */
+
+#define X86_CR3_PCID_BITS	12
+#define X86_CR3_PCID_MASK	(_AC((1UL << X86_CR3_PCID_BITS) - 1, UL))
+
+#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */
+#define X86_CR3_PCID_NOFLUSH    _BITULL(X86_CR3_PCID_NOFLUSH_BIT)
 
 /*
  * Intel CPU features in CR4
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 81bb565f4497..29786c87e864 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -29,10 +29,13 @@ KASAN_SANITIZE_stacktrace.o				:= n
 KASAN_SANITIZE_paravirt.o				:= n
 
 OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o	:= y
-OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o		:= y
 OBJECT_FILES_NON_STANDARD_test_nx.o			:= y
 OBJECT_FILES_NON_STANDARD_paravirt_patch_$(BITS).o	:= y
 
+ifdef CONFIG_FRAME_POINTER
+OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o		:= y
+endif
+
 # If instrumentation of this dir is enabled, boot hangs during first second.
 # Probably could be more selective here, but note that files related to irqs,
 # boot, dumpstack/stacktrace, etc are either non-interesting or can lead to
@@ -112,6 +115,8 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
 obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
 obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
 
+obj-$(CONFIG_JAILHOUSE_GUEST)	+= jailhouse.o
+
 obj-$(CONFIG_EISA)		+= eisa.o
 obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index f4c463df8b08..ec3a286163c3 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -68,8 +68,9 @@ int acpi_ioapic;
 int acpi_strict;
 int acpi_disable_cmcff;
 
+/* ACPI SCI override configuration */
 u8 acpi_sci_flags __initdata;
-int acpi_sci_override_gsi __initdata;
+u32 acpi_sci_override_gsi __initdata = INVALID_ACPI_IRQ;
 int acpi_skip_timer_override __initdata;
 int acpi_use_timer_override __initdata;
 int acpi_fix_pin2_polarity __initdata;
@@ -112,8 +113,6 @@ static u32 isa_irq_to_gsi[NR_IRQS_LEGACY] __read_mostly = {
 	0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
 };
 
-#define	ACPI_INVALID_GSI		INT_MIN
-
 /*
  * This is just a simple wrapper around early_memremap(),
  * with sanity checks for phys == 0 and size == 0.
@@ -372,7 +371,7 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 	 * and acpi_isa_irq_to_gsi() may give wrong result.
 	 */
 	if (gsi < nr_legacy_irqs() && isa_irq_to_gsi[gsi] == gsi)
-		isa_irq_to_gsi[gsi] = ACPI_INVALID_GSI;
+		isa_irq_to_gsi[gsi] = INVALID_ACPI_IRQ;
 	isa_irq_to_gsi[bus_irq] = gsi;
 }
 
@@ -620,24 +619,24 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
 	}
 
 	rc = acpi_get_override_irq(gsi, &trigger, &polarity);
-	if (rc == 0) {
-		trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
-		polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
-		irq = acpi_register_gsi(NULL, gsi, trigger, polarity);
-		if (irq >= 0) {
-			*irqp = irq;
-			return 0;
-		}
-	}
+	if (rc)
+		return rc;
 
-	return -1;
+	trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
+	polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
+	irq = acpi_register_gsi(NULL, gsi, trigger, polarity);
+	if (irq < 0)
+		return irq;
+
+	*irqp = irq;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
 
 int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi)
 {
 	if (isa_irq < nr_legacy_irqs() &&
-	    isa_irq_to_gsi[isa_irq] != ACPI_INVALID_GSI) {
+	    isa_irq_to_gsi[isa_irq] != INVALID_ACPI_IRQ) {
 		*gsi = isa_irq_to_gsi[isa_irq];
 		return 0;
 	}
@@ -676,8 +675,7 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
 	mutex_lock(&acpi_ioapic_lock);
 	irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info);
 	/* Don't set up the ACPI SCI because it's already set up */
-	if (irq >= 0 && enable_update_mptable &&
-	    acpi_gbl_FADT.sci_interrupt != gsi)
+	if (irq >= 0 && enable_update_mptable && gsi != acpi_gbl_FADT.sci_interrupt)
 		mp_config_acpi_gsi(dev, gsi, trigger, polarity);
 	mutex_unlock(&acpi_ioapic_lock);
 #endif
@@ -1211,8 +1209,9 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 	/*
 	 * If BIOS did not supply an INT_SRC_OVR for the SCI
 	 * pretend we got one so we can set the SCI flags.
+	 * But ignore setting up SCI on hardware reduced platforms.
 	 */
-	if (!acpi_sci_override_gsi)
+	if (acpi_sci_override_gsi == INVALID_ACPI_IRQ && !acpi_gbl_reduced_hardware)
 		acpi_sci_ioapic_setup(acpi_gbl_FADT.sci_interrupt, 0, 0,
 				      acpi_gbl_FADT.sci_interrupt);
 
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 7188aea91549..f1915b744052 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -138,6 +138,8 @@ static int __init acpi_sleep_setup(char *str)
 			acpi_nvs_nosave_s3();
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
+		if (strncmp(str, "nobl", 4) == 0)
+			acpi_sleep_no_blacklist();
 		str = strchr(str, ',');
 		if (str != NULL)
 			str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index dbaf14d69ebd..30571fdaaf6f 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -298,7 +298,7 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf)
 	tgt_rip  = next_rip + o_dspl;
 	n_dspl = tgt_rip - orig_insn;
 
-	DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl);
+	DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl);
 
 	if (tgt_rip - orig_insn >= 0) {
 		if (n_dspl - 2 <= 127)
@@ -344,15 +344,18 @@ done:
 static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
 {
 	unsigned long flags;
+	int i;
 
-	if (instr[0] != 0x90)
-		return;
+	for (i = 0; i < a->padlen; i++) {
+		if (instr[i] != 0x90)
+			return;
+	}
 
 	local_irq_save(flags);
 	add_nops(instr + (a->instrlen - a->padlen), a->padlen);
 	local_irq_restore(flags);
 
-	DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ",
+	DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ",
 		   instr, a->instrlen - a->padlen, a->padlen);
 }
 
@@ -373,7 +376,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	u8 *instr, *replacement;
 	u8 insnbuf[MAX_PATCH_LEN];
 
-	DPRINTK("alt table %p -> %p", start, end);
+	DPRINTK("alt table %px, -> %px", start, end);
 	/*
 	 * The scan order should be from start to end. A later scanned
 	 * alternative code can overwrite previously scanned alternative code.
@@ -397,14 +400,14 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 			continue;
 		}
 
-		DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d",
+		DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d",
 			a->cpuid >> 5,
 			a->cpuid & 0x1f,
 			instr, a->instrlen,
 			replacement, a->replacementlen, a->padlen);
 
-		DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr);
-		DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement);
+		DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr);
+		DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement);
 
 		memcpy(insnbuf, replacement, a->replacementlen);
 		insnbuf_sz = a->replacementlen;
@@ -430,7 +433,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 				 a->instrlen - a->replacementlen);
 			insnbuf_sz += a->instrlen - a->replacementlen;
 		}
-		DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr);
+		DUMP_BYTES(insnbuf, insnbuf_sz, "%px: final_insn: ", instr);
 
 		text_poke_early(instr, insnbuf, insnbuf_sz);
 	}
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index cc0e8bc0ea3f..ecd486cb06ab 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -31,6 +31,7 @@
 #include <linux/io.h>
 #include <linux/gfp.h>
 #include <linux/atomic.h>
+#include <linux/dma-direct.h>
 #include <asm/mtrr.h>
 #include <asm/pgtable.h>
 #include <asm/proto.h>
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index f5d92bc3b884..2c4d5ece7456 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -30,6 +30,7 @@
 #include <asm/dma.h>
 #include <asm/amd_nb.h>
 #include <asm/x86_init.h>
+#include <linux/crash_dump.h>
 
 /*
  * Using 512M as goal, in case kexec will load kernel_big
@@ -56,6 +57,33 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
+#ifdef CONFIG_PROC_VMCORE
+/*
+ * If the first kernel maps the aperture over e820 RAM, the kdump kernel will
+ * use the same range because it will remain configured in the northbridge.
+ * Trying to dump this area via /proc/vmcore may crash the machine, so exclude
+ * it from vmcore.
+ */
+static unsigned long aperture_pfn_start, aperture_page_count;
+
+static int gart_oldmem_pfn_is_ram(unsigned long pfn)
+{
+	return likely((pfn < aperture_pfn_start) ||
+		      (pfn >= aperture_pfn_start + aperture_page_count));
+}
+
+static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+{
+	aperture_pfn_start = aper_base >> PAGE_SHIFT;
+	aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT;
+	WARN_ON(register_oldmem_pfn_is_ram(&gart_oldmem_pfn_is_ram));
+}
+#else
+static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+{
+}
+#endif
+
 /* This code runs before the PCI subsystem is initialized, so just
    access the northbridge directly. */
 
@@ -435,8 +463,16 @@ int __init gart_iommu_hole_init(void)
 
 out:
 	if (!fix && !fallback_aper_force) {
-		if (last_aper_base)
+		if (last_aper_base) {
+			/*
+			 * If this is the kdump kernel, the first kernel
+			 * may have allocated the range over its e820 RAM
+			 * and fixed up the northbridge
+			 */
+			exclude_from_vmcore(last_aper_base, last_aper_order);
+
 			return 1;
+		}
 		return 0;
 	}
 
@@ -473,6 +509,14 @@ out:
 		return 0;
 	}
 
+	/*
+	 * If this is the kdump kernel _and_ the first kernel did not
+	 * configure the aperture in the northbridge, this range may
+	 * overlap with the first kernel's memory. We can't access the
+	 * range through vmcore even though it should be part of the dump.
+	 */
+	exclude_from_vmcore(aper_alloc, aper_order);
+
 	/* Fix up the north bridges */
 	for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
 		int bus, dev_base, dev_limit;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 6e272f3ea984..25ddf02598d2 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1286,6 +1286,55 @@ static int __init apic_intr_mode_select(void)
 	return APIC_SYMMETRIC_IO;
 }
 
+/*
+ * An initial setup of the virtual wire mode.
+ */
+void __init init_bsp_APIC(void)
+{
+	unsigned int value;
+
+	/*
+	 * Don't do the setup now if we have a SMP BIOS as the
+	 * through-I/O-APIC virtual wire mode might be active.
+	 */
+	if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC))
+		return;
+
+	/*
+	 * Do not trust the local APIC being empty at bootup.
+	 */
+	clear_local_APIC();
+
+	/*
+	 * Enable APIC.
+	 */
+	value = apic_read(APIC_SPIV);
+	value &= ~APIC_VECTOR_MASK;
+	value |= APIC_SPIV_APIC_ENABLED;
+
+#ifdef CONFIG_X86_32
+	/* This bit is reserved on P4/Xeon and should be cleared */
+	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
+	    (boot_cpu_data.x86 == 15))
+		value &= ~APIC_SPIV_FOCUS_DISABLED;
+	else
+#endif
+		value |= APIC_SPIV_FOCUS_DISABLED;
+	value |= SPURIOUS_APIC_VECTOR;
+	apic_write(APIC_SPIV, value);
+
+	/*
+	 * Set up the virtual wire mode.
+	 */
+	apic_write(APIC_LVT0, APIC_DM_EXTINT);
+	value = APIC_DM_NMI;
+	if (!lapic_is_integrated())		/* 82489DX */
+		value |= APIC_LVT_LEVEL_TRIGGER;
+	if (apic_extnmi == APIC_EXTNMI_NONE)
+		value |= APIC_LVT_MASKED;
+	apic_write(APIC_LVT1, value);
+}
+
 /* Init the interrupt delivery mode for the BSP */
 void __init apic_intr_mode_init(void)
 {
@@ -2626,11 +2675,13 @@ static int __init apic_set_verbosity(char *arg)
 		apic_verbosity = APIC_DEBUG;
 	else if (strcmp("verbose", arg) == 0)
 		apic_verbosity = APIC_VERBOSE;
+#ifdef CONFIG_X86_64
 	else {
 		pr_warning("APIC Verbosity level %s not recognised"
 			" use apic=verbose or apic=debug\n", arg);
 		return -EINVAL;
 	}
+#endif
 
 	return 0;
 }
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index aa85690e9b64..e84c9eb4e5b4 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -19,6 +19,7 @@
 #include <asm/smp.h>
 #include <asm/apic.h>
 #include <asm/ipi.h>
+#include <asm/jailhouse_para.h>
 
 #include <linux/acpi.h>
 
@@ -84,12 +85,8 @@ flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector)
 static void flat_send_IPI_allbutself(int vector)
 {
 	int cpu = smp_processor_id();
-#ifdef	CONFIG_HOTPLUG_CPU
-	int hotplug = 1;
-#else
-	int hotplug = 0;
-#endif
-	if (hotplug || vector == NMI_VECTOR) {
+
+	if (IS_ENABLED(CONFIG_HOTPLUG_CPU) || vector == NMI_VECTOR) {
 		if (!cpumask_equal(cpu_online_mask, cpumask_of(cpu))) {
 			unsigned long mask = cpumask_bits(cpu_online_mask)[0];
 
@@ -151,7 +148,7 @@ static struct apic apic_flat __ro_after_init = {
 	.apic_id_valid			= default_apic_id_valid,
 	.apic_id_registered		= flat_apic_id_registered,
 
-	.irq_delivery_mode		= dest_LowestPrio,
+	.irq_delivery_mode		= dest_Fixed,
 	.irq_dest_mode			= 1, /* logical */
 
 	.disable_esr			= 0,
@@ -218,6 +215,15 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	return 0;
 }
 
+static void physflat_init_apic_ldr(void)
+{
+	/*
+	 * LDR and DFR are not involved in physflat mode, rather:
+	 * "In physical destination mode, the destination processor is
+	 * specified by its local APIC ID [...]." (Intel SDM, 10.6.2.1)
+	 */
+}
+
 static void physflat_send_IPI_allbutself(int vector)
 {
 	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
@@ -230,7 +236,8 @@ static void physflat_send_IPI_all(int vector)
 
 static int physflat_probe(void)
 {
-	if (apic == &apic_physflat || num_possible_cpus() > 8)
+	if (apic == &apic_physflat || num_possible_cpus() > 8 ||
+	    jailhouse_paravirt())
 		return 1;
 
 	return 0;
@@ -251,8 +258,7 @@ static struct apic apic_physflat __ro_after_init = {
 	.dest_logical			= 0,
 	.check_apicid_used		= NULL,
 
-	/* not needed, but shouldn't hurt: */
-	.init_apic_ldr			= flat_init_apic_ldr,
+	.init_apic_ldr			= physflat_init_apic_ldr,
 
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 7b659c4480c9..5078b5ce63a7 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -110,7 +110,7 @@ struct apic apic_noop __ro_after_init = {
 	.apic_id_valid			= default_apic_id_valid,
 	.apic_id_registered		= noop_apic_id_registered,
 
-	.irq_delivery_mode		= dest_LowestPrio,
+	.irq_delivery_mode		= dest_Fixed,
 	/* logical delivery broadcast to all CPUs: */
 	.irq_dest_mode			= 1,
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 201579dc5242..8ad2e410974f 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -800,18 +800,18 @@ static int irq_polarity(int idx)
 	/*
 	 * Determine IRQ line polarity (high active or low active):
 	 */
-	switch (mp_irqs[idx].irqflag & 0x03) {
-	case 0:
+	switch (mp_irqs[idx].irqflag & MP_IRQPOL_MASK) {
+	case MP_IRQPOL_DEFAULT:
 		/* conforms to spec, ie. bus-type dependent polarity */
 		if (test_bit(bus, mp_bus_not_pci))
 			return default_ISA_polarity(idx);
 		else
 			return default_PCI_polarity(idx);
-	case 1:
+	case MP_IRQPOL_ACTIVE_HIGH:
 		return IOAPIC_POL_HIGH;
-	case 2:
+	case MP_IRQPOL_RESERVED:
 		pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n");
-	case 3:
+	case MP_IRQPOL_ACTIVE_LOW:
 	default: /* Pointless default required due to do gcc stupidity */
 		return IOAPIC_POL_LOW;
 	}
@@ -845,8 +845,8 @@ static int irq_trigger(int idx)
 	/*
 	 * Determine IRQ trigger mode (edge or level sensitive):
 	 */
-	switch ((mp_irqs[idx].irqflag >> 2) & 0x03) {
-	case 0:
+	switch (mp_irqs[idx].irqflag & MP_IRQTRIG_MASK) {
+	case MP_IRQTRIG_DEFAULT:
 		/* conforms to spec, ie. bus-type dependent trigger mode */
 		if (test_bit(bus, mp_bus_not_pci))
 			trigger = default_ISA_trigger(idx);
@@ -854,11 +854,11 @@ static int irq_trigger(int idx)
 			trigger = default_PCI_trigger(idx);
 		/* Take EISA into account */
 		return eisa_irq_trigger(idx, bus, trigger);
-	case 1:
+	case MP_IRQTRIG_EDGE:
 		return IOAPIC_EDGE;
-	case 2:
+	case MP_IRQTRIG_RESERVED:
 		pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n");
-	case 3:
+	case MP_IRQTRIG_LEVEL:
 	default: /* Pointless default required due to do gcc stupidity */
 		return IOAPIC_LEVEL;
 	}
@@ -2988,7 +2988,7 @@ void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
 }
 
 int mp_irqdomain_activate(struct irq_domain *domain,
-			  struct irq_data *irq_data, bool early)
+			  struct irq_data *irq_data, bool reserve)
 {
 	unsigned long flags;
 
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 9b18be764422..ce503c99f5c4 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -39,17 +39,13 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
 		((apic->irq_dest_mode == 0) ?
 			MSI_ADDR_DEST_MODE_PHYSICAL :
 			MSI_ADDR_DEST_MODE_LOGICAL) |
-		((apic->irq_delivery_mode != dest_LowestPrio) ?
-			MSI_ADDR_REDIRECTION_CPU :
-			MSI_ADDR_REDIRECTION_LOWPRI) |
+		MSI_ADDR_REDIRECTION_CPU |
 		MSI_ADDR_DEST_ID(cfg->dest_apicid);
 
 	msg->data =
 		MSI_DATA_TRIGGER_EDGE |
 		MSI_DATA_LEVEL_ASSERT |
-		((apic->irq_delivery_mode != dest_LowestPrio) ?
-			MSI_DATA_DELIVERY_FIXED :
-			MSI_DATA_DELIVERY_LOWPRI) |
+		MSI_DATA_DELIVERY_FIXED |
 		MSI_DATA_VECTOR(cfg->vector);
 }
 
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index fa22017de806..02e8acb134f8 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -105,7 +105,7 @@ static struct apic apic_default __ro_after_init = {
 	.apic_id_valid			= default_apic_id_valid,
 	.apic_id_registered		= default_apic_id_registered,
 
-	.irq_delivery_mode		= dest_LowestPrio,
+	.irq_delivery_mode		= dest_Fixed,
 	/* logical delivery broadcast to all CPUs: */
 	.irq_dest_mode			= 1,
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 6a823a25eaff..3cc471beb50b 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -184,6 +184,7 @@ static void reserve_irq_vector_locked(struct irq_data *irqd)
 	irq_matrix_reserve(vector_matrix);
 	apicd->can_reserve = true;
 	apicd->has_reserved = true;
+	irqd_set_can_reserve(irqd);
 	trace_vector_reserve(irqd->irq, 0);
 	vector_assign_managed_shutdown(irqd);
 }
@@ -368,8 +369,18 @@ static int activate_reserved(struct irq_data *irqd)
 	int ret;
 
 	ret = assign_irq_vector_any_locked(irqd);
-	if (!ret)
+	if (!ret) {
 		apicd->has_reserved = false;
+		/*
+		 * Core might have disabled reservation mode after
+		 * allocating the irq descriptor. Ideally this should
+		 * happen before allocation time, but that would require
+		 * completely convoluted ways of transporting that
+		 * information.
+		 */
+		if (!irqd_can_reserve(irqd))
+			apicd->can_reserve = false;
+	}
 	return ret;
 }
 
@@ -398,21 +409,21 @@ static int activate_managed(struct irq_data *irqd)
 }
 
 static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
-			       bool early)
+			       bool reserve)
 {
 	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	unsigned long flags;
 	int ret = 0;
 
 	trace_vector_activate(irqd->irq, apicd->is_managed,
-			      apicd->can_reserve, early);
+			      apicd->can_reserve, reserve);
 
 	/* Nothing to do for fixed assigned vectors */
 	if (!apicd->can_reserve && !apicd->is_managed)
 		return 0;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	if (early || irqd_is_managed_and_shutdown(irqd))
+	if (reserve || irqd_is_managed_and_shutdown(irqd))
 		vector_assign_managed_shutdown(irqd);
 	else if (apicd->is_managed)
 		ret = activate_managed(irqd);
@@ -478,6 +489,7 @@ static bool vector_configure_legacy(unsigned int virq, struct irq_data *irqd,
 	} else {
 		/* Release the vector */
 		apicd->can_reserve = true;
+		irqd_set_can_reserve(irqd);
 		clear_irq_vector(irqd);
 		realloc = true;
 	}
@@ -530,20 +542,23 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 
 		err = assign_irq_vector_policy(irqd, info);
 		trace_vector_setup(virq + i, false, err);
-		if (err)
+		if (err) {
+			irqd->chip_data = NULL;
+			free_apic_chip_data(apicd);
 			goto error;
+		}
 	}
 
 	return 0;
 
 error:
-	x86_vector_free_irqs(domain, virq, i + 1);
+	x86_vector_free_irqs(domain, virq, i);
 	return err;
 }
 
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
-void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d,
-			   struct irq_data *irqd, int ind)
+static void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d,
+				  struct irq_data *irqd, int ind)
 {
 	unsigned int cpu, vector, prev_cpu, prev_vector;
 	struct apic_chip_data *apicd;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 622f13ca8a94..8b04234e010b 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -184,7 +184,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = {
 	.apic_id_valid			= x2apic_apic_id_valid,
 	.apic_id_registered		= x2apic_apic_id_registered,
 
-	.irq_delivery_mode		= dest_LowestPrio,
+	.irq_delivery_mode		= dest_Fixed,
 	.irq_dest_mode			= 1, /* logical */
 
 	.disable_esr			= 0,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index e1b8e8bf6b3c..46b675aaf20b 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -137,6 +137,8 @@ static int __init early_get_pnodeid(void)
 	case UV3_HUB_PART_NUMBER_X:
 		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE;
 		break;
+
+	/* Update: UV4A has only a modified revision to indicate HUB fixes */
 	case UV4_HUB_PART_NUMBER:
 		uv_min_hub_revision_id += UV4_HUB_REVISION_BASE - 1;
 		uv_cpuid.gnode_shift = 2; /* min partition is 4 sockets */
@@ -316,6 +318,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	} else if (!strcmp(oem_table_id, "UVH")) {
 		/* Only UV1 systems: */
 		uv_system_type = UV_NON_UNIQUE_APIC;
+		x86_platform.legacy.warm_reset = 0;
 		__this_cpu_write(x2apic_extra_bits, pnodeid << uvh_apicid.s.pnode_shift);
 		uv_set_apicid_hibit();
 		uv_apic = 1;
@@ -767,6 +770,7 @@ static __init void map_gru_high(int max_pnode)
 		return;
 	}
 
+	/* Only UV3 has distributed GRU mode */
 	if (is_uv3_hub() && gru.s3.mode) {
 		map_gru_distributed(gru.v);
 		return;
@@ -790,63 +794,61 @@ static __init void map_mmr_high(int max_pnode)
 		pr_info("UV: MMR disabled\n");
 }
 
-/*
- * This commonality works because both 0 & 1 versions of the MMIOH OVERLAY
- * and REDIRECT MMR regs are exactly the same on UV3.
- */
-struct mmioh_config {
-	unsigned long overlay;
-	unsigned long redirect;
-	char *id;
-};
-
-static __initdata struct mmioh_config mmiohs[] = {
-	{
-		UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR,
-		UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR,
-		"MMIOH0"
-	},
-	{
-		UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR,
-		UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR,
-		"MMIOH1"
-	},
-};
-
-/* UV3 & UV4 have identical MMIOH overlay configs */
-static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
+/* UV3/4 have identical MMIOH overlay configs, UV4A is slightly different */
+static __init void map_mmioh_high_uv34(int index, int min_pnode, int max_pnode)
 {
-	union uv3h_rh_gam_mmioh_overlay_config0_mmr_u overlay;
+	unsigned long overlay;
 	unsigned long mmr;
 	unsigned long base;
+	unsigned long nasid_mask;
+	unsigned long m_overlay;
 	int i, n, shift, m_io, max_io;
 	int nasid, lnasid, fi, li;
 	char *id;
 
-	id = mmiohs[index].id;
-	overlay.v = uv_read_local_mmr(mmiohs[index].overlay);
-
-	pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n", id, overlay.v, overlay.s3.base, overlay.s3.m_io);
-	if (!overlay.s3.enable) {
+	if (index == 0) {
+		id = "MMIOH0";
+		m_overlay = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR;
+		overlay = uv_read_local_mmr(m_overlay);
+		base = overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK;
+		mmr = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR;
+		m_io = (overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK)
+			>> UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT;
+		shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT;
+		n = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH;
+		nasid_mask = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK;
+	} else {
+		id = "MMIOH1";
+		m_overlay = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR;
+		overlay = uv_read_local_mmr(m_overlay);
+		base = overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK;
+		mmr = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR;
+		m_io = (overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK)
+			>> UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT;
+		shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT;
+		n = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH;
+		nasid_mask = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK;
+	}
+	pr_info("UV: %s overlay 0x%lx base:0x%lx m_io:%d\n", id, overlay, base, m_io);
+	if (!(overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK)) {
 		pr_info("UV: %s disabled\n", id);
 		return;
 	}
 
-	shift = UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT;
-	base = (unsigned long)overlay.s3.base;
-	m_io = overlay.s3.m_io;
-	mmr = mmiohs[index].redirect;
-	n = UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH;
 	/* Convert to NASID: */
 	min_pnode *= 2;
 	max_pnode *= 2;
 	max_io = lnasid = fi = li = -1;
 
 	for (i = 0; i < n; i++) {
-		union uv3h_rh_gam_mmioh_redirect_config0_mmr_u redirect;
+		unsigned long m_redirect = mmr + i * 8;
+		unsigned long redirect = uv_read_local_mmr(m_redirect);
+
+		nasid = redirect & nasid_mask;
+		if (i == 0)
+			pr_info("UV: %s redirect base 0x%lx(@0x%lx) 0x%04x\n",
+				id, redirect, m_redirect, nasid);
 
-		redirect.v = uv_read_local_mmr(mmr + i * 8);
-		nasid = redirect.s3.nasid;
 		/* Invalid NASID: */
 		if (nasid < min_pnode || max_pnode < nasid)
 			nasid = -1;
@@ -894,8 +896,8 @@ static __init void map_mmioh_high(int min_pnode, int max_pnode)
 
 	if (is_uv3_hub() || is_uv4_hub()) {
 		/* Map both MMIOH regions: */
-		map_mmioh_high_uv3(0, min_pnode, max_pnode);
-		map_mmioh_high_uv3(1, min_pnode, max_pnode);
+		map_mmioh_high_uv34(0, min_pnode, max_pnode);
+		map_mmioh_high_uv34(1, min_pnode, max_pnode);
 		return;
 	}
 
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index e4b0d92b3ae0..ab1865342002 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1506,7 +1506,7 @@ static ssize_t do_read(struct file *fp, char __user *buf, size_t count, loff_t *
 	return 0;
 }
 
-static unsigned int do_poll(struct file *fp, poll_table *wait)
+static __poll_t do_poll(struct file *fp, poll_table *wait)
 {
 	struct apm_user *as;
 
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 8ea78275480d..76417a9aab73 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -17,6 +17,7 @@
 #include <asm/sigframe.h>
 #include <asm/bootparam.h>
 #include <asm/suspend.h>
+#include <asm/tlbflush.h>
 
 #ifdef CONFIG_XEN
 #include <xen/interface/xen.h>
@@ -93,4 +94,13 @@ void common(void) {
 
 	BLANK();
 	DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+
+	/* TLB state for the entry code */
+	OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask);
+
+	/* Layout info for cpu_entry_area */
+	OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
+	OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
+	OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
+	DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
 }
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index dedf428b20b6..fa1261eefa16 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -47,13 +47,8 @@ void foo(void)
 	BLANK();
 
 	/* Offset from the sysenter stack to tss.sp0 */
-	DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
-	       offsetofend(struct tss_struct, SYSENTER_stack));
-
-	/* Offset from cpu_tss to SYSENTER_stack */
-	OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack);
-	/* Size of SYSENTER_stack */
-	DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
+	DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
+	       offsetofend(struct cpu_entry_area, entry_stack_page.stack));
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 	BLANK();
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 630212fa9b9d..bf51e51d808d 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -23,6 +23,9 @@ int main(void)
 #ifdef CONFIG_PARAVIRT
 	OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
 	OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
+#ifdef CONFIG_DEBUG_ENTRY
+	OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl);
+#endif
 	BLANK();
 #endif
 
@@ -63,6 +66,7 @@ int main(void)
 
 	OFFSET(TSS_ist, tss_struct, x86_tss.ist);
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
+	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	BLANK();
 
 #ifdef CONFIG_CC_STACKPROTECTOR
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d58184b7cd44..ea831c858195 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -804,8 +804,11 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x17: init_amd_zn(c); break;
 	}
 
-	/* Enable workaround for FXSAVE leak */
-	if (c->x86 >= 6)
+	/*
+	 * Enable workaround for FXSAVE leak on CPUs
+	 * without a XSaveErPtr feature
+	 */
+	if ((c->x86 >= 6) && (!cpu_has(c, X86_FEATURE_XSAVEERPTR)))
 		set_cpu_bug(c, X86_BUG_FXSAVE_LEAK);
 
 	cpu_detect_cache_sizes(c);
@@ -826,8 +829,32 @@ static void init_amd(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_K8);
 
 	if (cpu_has(c, X86_FEATURE_XMM2)) {
-		/* MFENCE stops RDTSC speculation */
-		set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+		unsigned long long val;
+		int ret;
+
+		/*
+		 * A serializing LFENCE has less overhead than MFENCE, so
+		 * use it for execution serialization.  On families which
+		 * don't have that MSR, LFENCE is already serializing.
+		 * msr_set_bit() uses the safe accessors, too, even if the MSR
+		 * is not present.
+		 */
+		msr_set_bit(MSR_F10H_DECFG,
+			    MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+
+		/*
+		 * Verify that the MSR write was successful (could be running
+		 * under a hypervisor) and only then assume that LFENCE is
+		 * serializing.
+		 */
+		ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
+		if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
+			/* A serializing LFENCE stops RDTSC speculation */
+			set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+		} else {
+			/* MFENCE stops RDTSC speculation */
+			set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+		}
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ba0b2424c9b0..3bfb2b23d79c 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -10,6 +10,11 @@
  */
 #include <linux/init.h>
 #include <linux/utsname.h>
+#include <linux/cpu.h>
+#include <linux/module.h>
+
+#include <asm/nospec-branch.h>
+#include <asm/cmdline.h>
 #include <asm/bugs.h>
 #include <asm/processor.h>
 #include <asm/processor-flags.h>
@@ -19,6 +24,9 @@
 #include <asm/alternative.h>
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
+#include <asm/intel-family.h>
+
+static void __init spectre_v2_select_mitigation(void);
 
 void __init check_bugs(void)
 {
@@ -29,6 +37,9 @@ void __init check_bugs(void)
 		print_cpu_info(&boot_cpu_data);
 	}
 
+	/* Select the proper spectre mitigation before patching alternatives */
+	spectre_v2_select_mitigation();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -60,3 +71,249 @@ void __init check_bugs(void)
 		set_memory_4k((unsigned long)__va(0), 1);
 #endif
 }
+
+/* The kernel command line selection */
+enum spectre_v2_mitigation_cmd {
+	SPECTRE_V2_CMD_NONE,
+	SPECTRE_V2_CMD_AUTO,
+	SPECTRE_V2_CMD_FORCE,
+	SPECTRE_V2_CMD_RETPOLINE,
+	SPECTRE_V2_CMD_RETPOLINE_GENERIC,
+	SPECTRE_V2_CMD_RETPOLINE_AMD,
+};
+
+static const char *spectre_v2_strings[] = {
+	[SPECTRE_V2_NONE]			= "Vulnerable",
+	[SPECTRE_V2_RETPOLINE_MINIMAL]		= "Vulnerable: Minimal generic ASM retpoline",
+	[SPECTRE_V2_RETPOLINE_MINIMAL_AMD]	= "Vulnerable: Minimal AMD ASM retpoline",
+	[SPECTRE_V2_RETPOLINE_GENERIC]		= "Mitigation: Full generic retpoline",
+	[SPECTRE_V2_RETPOLINE_AMD]		= "Mitigation: Full AMD retpoline",
+};
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "Spectre V2 : " fmt
+
+static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
+
+#ifdef RETPOLINE
+static bool spectre_v2_bad_module;
+
+bool retpoline_module_ok(bool has_retpoline)
+{
+	if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline)
+		return true;
+
+	pr_err("System may be vunerable to spectre v2\n");
+	spectre_v2_bad_module = true;
+	return false;
+}
+
+static inline const char *spectre_v2_module_string(void)
+{
+	return spectre_v2_bad_module ? " - vulnerable module loaded" : "";
+}
+#else
+static inline const char *spectre_v2_module_string(void) { return ""; }
+#endif
+
+static void __init spec2_print_if_insecure(const char *reason)
+{
+	if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		pr_info("%s\n", reason);
+}
+
+static void __init spec2_print_if_secure(const char *reason)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		pr_info("%s\n", reason);
+}
+
+static inline bool retp_compiler(void)
+{
+	return __is_defined(RETPOLINE);
+}
+
+static inline bool match_option(const char *arg, int arglen, const char *opt)
+{
+	int len = strlen(opt);
+
+	return len == arglen && !strncmp(arg, opt, len);
+}
+
+static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
+{
+	char arg[20];
+	int ret;
+
+	ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
+				  sizeof(arg));
+	if (ret > 0)  {
+		if (match_option(arg, ret, "off")) {
+			goto disable;
+		} else if (match_option(arg, ret, "on")) {
+			spec2_print_if_secure("force enabled on command line.");
+			return SPECTRE_V2_CMD_FORCE;
+		} else if (match_option(arg, ret, "retpoline")) {
+			spec2_print_if_insecure("retpoline selected on command line.");
+			return SPECTRE_V2_CMD_RETPOLINE;
+		} else if (match_option(arg, ret, "retpoline,amd")) {
+			if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
+				pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
+				return SPECTRE_V2_CMD_AUTO;
+			}
+			spec2_print_if_insecure("AMD retpoline selected on command line.");
+			return SPECTRE_V2_CMD_RETPOLINE_AMD;
+		} else if (match_option(arg, ret, "retpoline,generic")) {
+			spec2_print_if_insecure("generic retpoline selected on command line.");
+			return SPECTRE_V2_CMD_RETPOLINE_GENERIC;
+		} else if (match_option(arg, ret, "auto")) {
+			return SPECTRE_V2_CMD_AUTO;
+		}
+	}
+
+	if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+		return SPECTRE_V2_CMD_AUTO;
+disable:
+	spec2_print_if_insecure("disabled on command line.");
+	return SPECTRE_V2_CMD_NONE;
+}
+
+/* Check for Skylake-like CPUs (for RSB handling) */
+static bool __init is_skylake_era(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86 == 6) {
+		switch (boot_cpu_data.x86_model) {
+		case INTEL_FAM6_SKYLAKE_MOBILE:
+		case INTEL_FAM6_SKYLAKE_DESKTOP:
+		case INTEL_FAM6_SKYLAKE_X:
+		case INTEL_FAM6_KABYLAKE_MOBILE:
+		case INTEL_FAM6_KABYLAKE_DESKTOP:
+			return true;
+		}
+	}
+	return false;
+}
+
+static void __init spectre_v2_select_mitigation(void)
+{
+	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
+	enum spectre_v2_mitigation mode = SPECTRE_V2_NONE;
+
+	/*
+	 * If the CPU is not affected and the command line mode is NONE or AUTO
+	 * then nothing to do.
+	 */
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) &&
+	    (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO))
+		return;
+
+	switch (cmd) {
+	case SPECTRE_V2_CMD_NONE:
+		return;
+
+	case SPECTRE_V2_CMD_FORCE:
+		/* FALLTRHU */
+	case SPECTRE_V2_CMD_AUTO:
+		goto retpoline_auto;
+
+	case SPECTRE_V2_CMD_RETPOLINE_AMD:
+		if (IS_ENABLED(CONFIG_RETPOLINE))
+			goto retpoline_amd;
+		break;
+	case SPECTRE_V2_CMD_RETPOLINE_GENERIC:
+		if (IS_ENABLED(CONFIG_RETPOLINE))
+			goto retpoline_generic;
+		break;
+	case SPECTRE_V2_CMD_RETPOLINE:
+		if (IS_ENABLED(CONFIG_RETPOLINE))
+			goto retpoline_auto;
+		break;
+	}
+	pr_err("kernel not compiled with retpoline; no mitigation available!");
+	return;
+
+retpoline_auto:
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+	retpoline_amd:
+		if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
+			pr_err("LFENCE not serializing. Switching to generic retpoline\n");
+			goto retpoline_generic;
+		}
+		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :
+					 SPECTRE_V2_RETPOLINE_MINIMAL_AMD;
+		setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD);
+		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
+	} else {
+	retpoline_generic:
+		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC :
+					 SPECTRE_V2_RETPOLINE_MINIMAL;
+		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
+	}
+
+	spectre_v2_enabled = mode;
+	pr_info("%s\n", spectre_v2_strings[mode]);
+
+	/*
+	 * If neither SMEP or KPTI are available, there is a risk of
+	 * hitting userspace addresses in the RSB after a context switch
+	 * from a shallow call stack to a deeper one. To prevent this fill
+	 * the entire RSB, even when using IBRS.
+	 *
+	 * Skylake era CPUs have a separate issue with *underflow* of the
+	 * RSB, when they will predict 'ret' targets from the generic BTB.
+	 * The proper mitigation for this is IBRS. If IBRS is not supported
+	 * or deactivated in favour of retpolines the RSB fill on context
+	 * switch is required.
+	 */
+	if ((!boot_cpu_has(X86_FEATURE_PTI) &&
+	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
+		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+		pr_info("Filling RSB on context switch\n");
+	}
+
+	/* Initialize Indirect Branch Prediction Barrier if supported */
+	if (boot_cpu_has(X86_FEATURE_IBPB)) {
+		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
+		pr_info("Enabling Indirect Branch Prediction Barrier\n");
+	}
+}
+
+#undef pr_fmt
+
+#ifdef CONFIG_SYSFS
+ssize_t cpu_show_meltdown(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+		return sprintf(buf, "Not affected\n");
+	if (boot_cpu_has(X86_FEATURE_PTI))
+		return sprintf(buf, "Mitigation: PTI\n");
+	return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spectre_v1(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
+		return sprintf(buf, "Not affected\n");
+	return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		return sprintf(buf, "Not affected\n");
+
+	return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+		       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+		       spectre_v2_module_string());
+}
+#endif
+
+void __ibp_barrier(void)
+{
+	__wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0);
+}
+EXPORT_SYMBOL_GPL(__ibp_barrier);
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 68bc6d9b3132..c578cd29c2d2 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -106,6 +106,10 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_64
 	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
 #endif
+	if (c->x86_power & (1 << 8)) {
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+	}
 }
 
 static void init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index fa998ca8aa5a..c7c996a692fd 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -47,6 +47,8 @@
 #include <asm/pat.h>
 #include <asm/microcode.h>
 #include <asm/microcode_intel.h>
+#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
 
 #ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/uv/uv.h>
@@ -476,8 +478,8 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c)
 	return NULL;		/* Not found */
 }
 
-__u32 cpu_caps_cleared[NCAPINTS];
-__u32 cpu_caps_set[NCAPINTS];
+__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS];
+__u32 cpu_caps_set[NCAPINTS + NBUGINTS];
 
 void load_percpu_segment(int cpu)
 {
@@ -490,28 +492,23 @@ void load_percpu_segment(int cpu)
 	load_stack_canary_segment();
 }
 
-/* Setup the fixmap mapping only once per-processor */
-static inline void setup_fixmap_gdt(int cpu)
-{
-#ifdef CONFIG_X86_64
-	/* On 64-bit systems, we use a read-only fixmap GDT. */
-	pgprot_t prot = PAGE_KERNEL_RO;
-#else
-	/*
-	 * On native 32-bit systems, the GDT cannot be read-only because
-	 * our double fault handler uses a task gate, and entering through
-	 * a task gate needs to change an available TSS to busy.  If the GDT
-	 * is read-only, that will triple fault.
-	 *
-	 * On Xen PV, the GDT must be read-only because the hypervisor requires
-	 * it.
-	 */
-	pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ?
-		PAGE_KERNEL_RO : PAGE_KERNEL;
+#ifdef CONFIG_X86_32
+/* The 32-bit entry code needs to find cpu_entry_area. */
+DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 #endif
 
-	__set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot);
-}
+#ifdef CONFIG_X86_64
+/*
+ * Special IST stacks which the CPU switches to when it calls
+ * an IST-marked descriptor entry. Up to 7 stacks (hardware
+ * limit), all of them are 4K, except the debug stack which
+ * is 8K.
+ */
+static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
+	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
+	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
+};
+#endif
 
 /* Load the original GDT from the per-cpu structure */
 void load_direct_gdt(int cpu)
@@ -747,7 +744,7 @@ static void apply_forced_caps(struct cpuinfo_x86 *c)
 {
 	int i;
 
-	for (i = 0; i < NCAPINTS; i++) {
+	for (i = 0; i < NCAPINTS + NBUGINTS; i++) {
 		c->x86_capability[i] &= ~cpu_caps_cleared[i];
 		c->x86_capability[i] |= cpu_caps_set[i];
 	}
@@ -774,6 +771,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
 		c->x86_capability[CPUID_7_ECX] = ecx;
+		c->x86_capability[CPUID_7_EDX] = edx;
 	}
 
 	/* Extended state features: level 0x0000000d */
@@ -881,6 +879,41 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #endif
 }
 
+static const __initdata struct x86_cpu_id cpu_no_speculation[] = {
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CEDARVIEW,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CLOVERVIEW,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_LINCROFT,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_PENWELL,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_PINEVIEW,	X86_FEATURE_ANY },
+	{ X86_VENDOR_CENTAUR,	5 },
+	{ X86_VENDOR_INTEL,	5 },
+	{ X86_VENDOR_NSC,	5 },
+	{ X86_VENDOR_ANY,	4 },
+	{}
+};
+
+static const __initdata struct x86_cpu_id cpu_no_meltdown[] = {
+	{ X86_VENDOR_AMD },
+	{}
+};
+
+static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c)
+{
+	u64 ia32_cap = 0;
+
+	if (x86_match_cpu(cpu_no_meltdown))
+		return false;
+
+	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+
+	/* Rogue Data Cache Load? No! */
+	if (ia32_cap & ARCH_CAP_RDCL_NO)
+		return false;
+
+	return true;
+}
+
 /*
  * Do minimum CPU detection early.
  * Fields really needed: vendor, cpuid_level, family, model, mask,
@@ -927,6 +960,14 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	}
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
+
+	if (!x86_match_cpu(cpu_no_speculation)) {
+		if (cpu_vulnerable_to_meltdown(c))
+			setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+		setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+		setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+	}
+
 	fpu__init_system(c);
 
 #ifdef CONFIG_X86_32
@@ -1250,7 +1291,7 @@ void enable_sep_cpu(void)
 		return;
 
 	cpu = get_cpu();
-	tss = &per_cpu(cpu_tss, cpu);
+	tss = &per_cpu(cpu_tss_rw, cpu);
 
 	/*
 	 * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field --
@@ -1259,11 +1300,7 @@ void enable_sep_cpu(void)
 
 	tss->x86_tss.ss1 = __KERNEL_CS;
 	wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
-
-	wrmsr(MSR_IA32_SYSENTER_ESP,
-	      (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
-	      0);
-
+	wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0);
 	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
 
 	put_cpu();
@@ -1357,25 +1394,22 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
-/*
- * Special IST stacks which the CPU switches to when it calls
- * an IST-marked descriptor entry. Up to 7 stacks (hardware
- * limit), all of them are 4K, except the debug stack which
- * is 8K.
- */
-static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
-	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
-	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
-};
-
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
-	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
-
 /* May not be marked __init: used by software suspend */
 void syscall_init(void)
 {
+	extern char _entry_trampoline[];
+	extern char entry_SYSCALL_64_trampoline[];
+
+	int cpu = smp_processor_id();
+	unsigned long SYSCALL64_entry_trampoline =
+		(unsigned long)get_cpu_entry_area(cpu)->entry_trampoline +
+		(entry_SYSCALL_64_trampoline - _entry_trampoline);
+
 	wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
-	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
+	if (static_cpu_has(X86_FEATURE_PTI))
+		wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
+	else
+		wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
 
 #ifdef CONFIG_IA32_EMULATION
 	wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
@@ -1386,7 +1420,7 @@ void syscall_init(void)
 	 * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
 	 */
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
-	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1));
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
 	wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
@@ -1530,7 +1564,7 @@ void cpu_init(void)
 	if (cpu)
 		load_ucode_ap();
 
-	t = &per_cpu(cpu_tss, cpu);
+	t = &per_cpu(cpu_tss_rw, cpu);
 	oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
@@ -1569,7 +1603,7 @@ void cpu_init(void)
 	 * set up and load the per-CPU TSS
 	 */
 	if (!oist->ist[0]) {
-		char *estacks = per_cpu(exception_stacks, cpu);
+		char *estacks = get_cpu_entry_area(cpu)->exception_stacks;
 
 		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
 			estacks += exception_stack_sizes[v];
@@ -1580,7 +1614,7 @@ void cpu_init(void)
 		}
 	}
 
-	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+	t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
 
 	/*
 	 * <= is required because the CPU will access up to
@@ -1596,11 +1630,12 @@ void cpu_init(void)
 	enter_lazy_tlb(&init_mm, me);
 
 	/*
-	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
-	 * task never enters user mode.
+	 * Initialize the TSS.  sp0 points to the entry trampoline stack
+	 * regardless of what task is running.
 	 */
-	set_tss_desc(cpu, t);
+	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
+	load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
 
 	load_mm_ldt(&init_mm);
 
@@ -1612,7 +1647,6 @@ void cpu_init(void)
 	if (is_uv_system())
 		uv_cpu_init();
 
-	setup_fixmap_gdt(cpu);
 	load_fixmap_gdt(cpu);
 }
 
@@ -1622,7 +1656,7 @@ void cpu_init(void)
 {
 	int cpu = smp_processor_id();
 	struct task_struct *curr = current;
-	struct tss_struct *t = &per_cpu(cpu_tss, cpu);
+	struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu);
 
 	wait_for_master_cpu(cpu);
 
@@ -1657,12 +1691,12 @@ void cpu_init(void)
 	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
 	 * task never enters user mode.
 	 */
-	set_tss_desc(cpu, t);
+	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
 
 	load_mm_ldt(&init_mm);
 
-	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+	t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
 
 #ifdef CONFIG_DOUBLEFAULT
 	/* Set up doublefault TSS pointer in the GDT */
@@ -1674,7 +1708,6 @@ void cpu_init(void)
 
 	fpu__init_cpu();
 
-	setup_fixmap_gdt(cpu);
 	load_fixmap_gdt(cpu);
 }
 #endif
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index bea8d3e24f50..479ca4728de0 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -31,6 +31,7 @@ extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
 extern const struct hypervisor_x86 x86_hyper_xen_pv;
 extern const struct hypervisor_x86 x86_hyper_xen_hvm;
 extern const struct hypervisor_x86 x86_hyper_kvm;
+extern const struct hypervisor_x86 x86_hyper_jailhouse;
 
 static const __initconst struct hypervisor_x86 * const hypervisors[] =
 {
@@ -45,6 +46,9 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] =
 #ifdef CONFIG_KVM_GUEST
 	&x86_hyper_kvm,
 #endif
+#ifdef CONFIG_JAILHOUSE_GUEST
+	&x86_hyper_jailhouse,
+#endif
 };
 
 enum x86_hypervisor_type x86_hyper_type;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b1af22073e28..6936d14d4c77 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -102,6 +102,59 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
 		ELF_HWCAP2 |= HWCAP2_RING3MWAIT;
 }
 
+/*
+ * Early microcode releases for the Spectre v2 mitigation were broken.
+ * Information taken from;
+ * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf
+ * - https://kb.vmware.com/s/article/52345
+ * - Microcode revisions observed in the wild
+ * - Release note from 20180108 microcode release
+ */
+struct sku_microcode {
+	u8 model;
+	u8 stepping;
+	u32 microcode;
+};
+static const struct sku_microcode spectre_bad_microcodes[] = {
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0B,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0A,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x09,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x0A,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x84 },
+	{ INTEL_FAM6_SKYLAKE_X,		0x03,	0x0100013e },
+	{ INTEL_FAM6_SKYLAKE_X,		0x04,	0x0200003c },
+	{ INTEL_FAM6_SKYLAKE_MOBILE,	0x03,	0xc2 },
+	{ INTEL_FAM6_SKYLAKE_DESKTOP,	0x03,	0xc2 },
+	{ INTEL_FAM6_BROADWELL_CORE,	0x04,	0x28 },
+	{ INTEL_FAM6_BROADWELL_GT3E,	0x01,	0x1b },
+	{ INTEL_FAM6_BROADWELL_XEON_D,	0x02,	0x14 },
+	{ INTEL_FAM6_BROADWELL_XEON_D,	0x03,	0x07000011 },
+	{ INTEL_FAM6_BROADWELL_X,	0x01,	0x0b000025 },
+	{ INTEL_FAM6_HASWELL_ULT,	0x01,	0x21 },
+	{ INTEL_FAM6_HASWELL_GT3E,	0x01,	0x18 },
+	{ INTEL_FAM6_HASWELL_CORE,	0x03,	0x23 },
+	{ INTEL_FAM6_HASWELL_X,		0x02,	0x3b },
+	{ INTEL_FAM6_HASWELL_X,		0x04,	0x10 },
+	{ INTEL_FAM6_IVYBRIDGE_X,	0x04,	0x42a },
+	/* Updated in the 20180108 release; blacklist until we know otherwise */
+	{ INTEL_FAM6_ATOM_GEMINI_LAKE,	0x01,	0x22 },
+	/* Observed in the wild */
+	{ INTEL_FAM6_SANDYBRIDGE_X,	0x06,	0x61b },
+	{ INTEL_FAM6_SANDYBRIDGE_X,	0x07,	0x712 },
+};
+
+static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
+		if (c->x86_model == spectre_bad_microcodes[i].model &&
+		    c->x86_mask == spectre_bad_microcodes[i].stepping)
+			return (c->microcode <= spectre_bad_microcodes[i].microcode);
+	}
+	return false;
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
@@ -123,6 +176,30 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		c->microcode = intel_get_microcode_revision();
 
 	/*
+	 * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support,
+	 * and they also have a different bit for STIBP support. Also,
+	 * a hypervisor might have set the individual AMD bits even on
+	 * Intel CPUs, for finer-grained selection of what's available.
+	 */
+	if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
+		set_cpu_cap(c, X86_FEATURE_IBRS);
+		set_cpu_cap(c, X86_FEATURE_IBPB);
+	}
+	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
+		set_cpu_cap(c, X86_FEATURE_STIBP);
+
+	/* Now if any of them are set, check the blacklist and clear the lot */
+	if ((cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) ||
+	     cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) {
+		pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n");
+		clear_cpu_cap(c, X86_FEATURE_IBRS);
+		clear_cpu_cap(c, X86_FEATURE_IBPB);
+		clear_cpu_cap(c, X86_FEATURE_STIBP);
+		clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL);
+		clear_cpu_cap(c, X86_FEATURE_INTEL_STIBP);
+	}
+
+	/*
 	 * Atom erratum AAE44/AAF40/AAG38/AAH41:
 	 *
 	 * A race condition between speculative fetches and invalidating
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 88dcf8479013..410629f10ad3 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -135,6 +135,40 @@ struct rdt_resource rdt_resources_all[] = {
 		.format_str		= "%d=%0*x",
 		.fflags			= RFTYPE_RES_CACHE,
 	},
+	[RDT_RESOURCE_L2DATA] =
+	{
+		.rid			= RDT_RESOURCE_L2DATA,
+		.name			= "L2DATA",
+		.domains		= domain_init(RDT_RESOURCE_L2DATA),
+		.msr_base		= IA32_L2_CBM_BASE,
+		.msr_update		= cat_wrmsr,
+		.cache_level		= 2,
+		.cache = {
+			.min_cbm_bits	= 1,
+			.cbm_idx_mult	= 2,
+			.cbm_idx_offset	= 0,
+		},
+		.parse_ctrlval		= parse_cbm,
+		.format_str		= "%d=%0*x",
+		.fflags			= RFTYPE_RES_CACHE,
+	},
+	[RDT_RESOURCE_L2CODE] =
+	{
+		.rid			= RDT_RESOURCE_L2CODE,
+		.name			= "L2CODE",
+		.domains		= domain_init(RDT_RESOURCE_L2CODE),
+		.msr_base		= IA32_L2_CBM_BASE,
+		.msr_update		= cat_wrmsr,
+		.cache_level		= 2,
+		.cache = {
+			.min_cbm_bits	= 1,
+			.cbm_idx_mult	= 2,
+			.cbm_idx_offset	= 1,
+		},
+		.parse_ctrlval		= parse_cbm,
+		.format_str		= "%d=%0*x",
+		.fflags			= RFTYPE_RES_CACHE,
+	},
 	[RDT_RESOURCE_MBA] =
 	{
 		.rid			= RDT_RESOURCE_MBA,
@@ -259,15 +293,15 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
 	r->alloc_enabled = true;
 }
 
-static void rdt_get_cdp_l3_config(int type)
+static void rdt_get_cdp_config(int level, int type)
 {
-	struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+	struct rdt_resource *r_l = &rdt_resources_all[level];
 	struct rdt_resource *r = &rdt_resources_all[type];
 
-	r->num_closid = r_l3->num_closid / 2;
-	r->cache.cbm_len = r_l3->cache.cbm_len;
-	r->default_ctrl = r_l3->default_ctrl;
-	r->cache.shareable_bits = r_l3->cache.shareable_bits;
+	r->num_closid = r_l->num_closid / 2;
+	r->cache.cbm_len = r_l->cache.cbm_len;
+	r->default_ctrl = r_l->default_ctrl;
+	r->cache.shareable_bits = r_l->cache.shareable_bits;
 	r->data_width = (r->cache.cbm_len + 3) / 4;
 	r->alloc_capable = true;
 	/*
@@ -277,6 +311,18 @@ static void rdt_get_cdp_l3_config(int type)
 	r->alloc_enabled = false;
 }
 
+static void rdt_get_cdp_l3_config(void)
+{
+	rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA);
+	rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3CODE);
+}
+
+static void rdt_get_cdp_l2_config(void)
+{
+	rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA);
+	rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE);
+}
+
 static int get_cache_id(int cpu, int level)
 {
 	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
@@ -525,10 +571,6 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 		 */
 		if (static_branch_unlikely(&rdt_mon_enable_key))
 			rmdir_mondata_subdir_allrdtgrp(r, d->id);
-		kfree(d->ctrl_val);
-		kfree(d->rmid_busy_llc);
-		kfree(d->mbm_total);
-		kfree(d->mbm_local);
 		list_del(&d->list);
 		if (is_mbm_enabled())
 			cancel_delayed_work(&d->mbm_over);
@@ -545,6 +587,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 			cancel_delayed_work(&d->cqm_limbo);
 		}
 
+		kfree(d->ctrl_val);
+		kfree(d->rmid_busy_llc);
+		kfree(d->mbm_total);
+		kfree(d->mbm_local);
 		kfree(d);
 		return;
 	}
@@ -645,6 +691,7 @@ enum {
 	RDT_FLAG_L3_CAT,
 	RDT_FLAG_L3_CDP,
 	RDT_FLAG_L2_CAT,
+	RDT_FLAG_L2_CDP,
 	RDT_FLAG_MBA,
 };
 
@@ -667,6 +714,7 @@ static struct rdt_options rdt_options[]  __initdata = {
 	RDT_OPT(RDT_FLAG_L3_CAT,    "l3cat",	X86_FEATURE_CAT_L3),
 	RDT_OPT(RDT_FLAG_L3_CDP,    "l3cdp",	X86_FEATURE_CDP_L3),
 	RDT_OPT(RDT_FLAG_L2_CAT,    "l2cat",	X86_FEATURE_CAT_L2),
+	RDT_OPT(RDT_FLAG_L2_CDP,    "l2cdp",	X86_FEATURE_CDP_L2),
 	RDT_OPT(RDT_FLAG_MBA,	    "mba",	X86_FEATURE_MBA),
 };
 #define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options)
@@ -729,15 +777,15 @@ static __init bool get_rdt_alloc_resources(void)
 
 	if (rdt_cpu_has(X86_FEATURE_CAT_L3)) {
 		rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]);
-		if (rdt_cpu_has(X86_FEATURE_CDP_L3)) {
-			rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA);
-			rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE);
-		}
+		if (rdt_cpu_has(X86_FEATURE_CDP_L3))
+			rdt_get_cdp_l3_config();
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CAT_L2)) {
 		/* CPUID 0x10.2 fields are same format at 0x10.1 */
 		rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]);
+		if (rdt_cpu_has(X86_FEATURE_CDP_L2))
+			rdt_get_cdp_l2_config();
 		ret = true;
 	}
 
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 3397244984f5..3fd7a70ee04a 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -7,12 +7,15 @@
 #include <linux/jump_label.h>
 
 #define IA32_L3_QOS_CFG		0xc81
+#define IA32_L2_QOS_CFG		0xc82
 #define IA32_L3_CBM_BASE	0xc90
 #define IA32_L2_CBM_BASE	0xd10
 #define IA32_MBA_THRTL_BASE	0xd50
 
 #define L3_QOS_CDP_ENABLE	0x01ULL
 
+#define L2_QOS_CDP_ENABLE	0x01ULL
+
 /*
  * Event IDs are used to program IA32_QM_EVTSEL before reading event
  * counter from IA32_QM_CTR
@@ -357,6 +360,8 @@ enum {
 	RDT_RESOURCE_L3DATA,
 	RDT_RESOURCE_L3CODE,
 	RDT_RESOURCE_L2,
+	RDT_RESOURCE_L2DATA,
+	RDT_RESOURCE_L2CODE,
 	RDT_RESOURCE_MBA,
 
 	/* Must be the last */
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 64c5ff97ee0d..bdab7d2f51af 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -990,6 +990,7 @@ out_destroy:
 	kernfs_remove(kn);
 	return ret;
 }
+
 static void l3_qos_cfg_update(void *arg)
 {
 	bool *enable = arg;
@@ -997,8 +998,17 @@ static void l3_qos_cfg_update(void *arg)
 	wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
 }
 
-static int set_l3_qos_cfg(struct rdt_resource *r, bool enable)
+static void l2_qos_cfg_update(void *arg)
 {
+	bool *enable = arg;
+
+	wrmsrl(IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
+}
+
+static int set_cache_qos_cfg(int level, bool enable)
+{
+	void (*update)(void *arg);
+	struct rdt_resource *r_l;
 	cpumask_var_t cpu_mask;
 	struct rdt_domain *d;
 	int cpu;
@@ -1006,16 +1016,24 @@ static int set_l3_qos_cfg(struct rdt_resource *r, bool enable)
 	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
 
-	list_for_each_entry(d, &r->domains, list) {
+	if (level == RDT_RESOURCE_L3)
+		update = l3_qos_cfg_update;
+	else if (level == RDT_RESOURCE_L2)
+		update = l2_qos_cfg_update;
+	else
+		return -EINVAL;
+
+	r_l = &rdt_resources_all[level];
+	list_for_each_entry(d, &r_l->domains, list) {
 		/* Pick one CPU from each domain instance to update MSR */
 		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
 	}
 	cpu = get_cpu();
 	/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
 	if (cpumask_test_cpu(cpu, cpu_mask))
-		l3_qos_cfg_update(&enable);
+		update(&enable);
 	/* Update QOS_CFG MSR on all other cpus in cpu_mask. */
-	smp_call_function_many(cpu_mask, l3_qos_cfg_update, &enable, 1);
+	smp_call_function_many(cpu_mask, update, &enable, 1);
 	put_cpu();
 
 	free_cpumask_var(cpu_mask);
@@ -1023,52 +1041,99 @@ static int set_l3_qos_cfg(struct rdt_resource *r, bool enable)
 	return 0;
 }
 
-static int cdp_enable(void)
+static int cdp_enable(int level, int data_type, int code_type)
 {
-	struct rdt_resource *r_l3data = &rdt_resources_all[RDT_RESOURCE_L3DATA];
-	struct rdt_resource *r_l3code = &rdt_resources_all[RDT_RESOURCE_L3CODE];
-	struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+	struct rdt_resource *r_ldata = &rdt_resources_all[data_type];
+	struct rdt_resource *r_lcode = &rdt_resources_all[code_type];
+	struct rdt_resource *r_l = &rdt_resources_all[level];
 	int ret;
 
-	if (!r_l3->alloc_capable || !r_l3data->alloc_capable ||
-	    !r_l3code->alloc_capable)
+	if (!r_l->alloc_capable || !r_ldata->alloc_capable ||
+	    !r_lcode->alloc_capable)
 		return -EINVAL;
 
-	ret = set_l3_qos_cfg(r_l3, true);
+	ret = set_cache_qos_cfg(level, true);
 	if (!ret) {
-		r_l3->alloc_enabled = false;
-		r_l3data->alloc_enabled = true;
-		r_l3code->alloc_enabled = true;
+		r_l->alloc_enabled = false;
+		r_ldata->alloc_enabled = true;
+		r_lcode->alloc_enabled = true;
 	}
 	return ret;
 }
 
-static void cdp_disable(void)
+static int cdpl3_enable(void)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+	return cdp_enable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA,
+			  RDT_RESOURCE_L3CODE);
+}
+
+static int cdpl2_enable(void)
+{
+	return cdp_enable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA,
+			  RDT_RESOURCE_L2CODE);
+}
+
+static void cdp_disable(int level, int data_type, int code_type)
+{
+	struct rdt_resource *r = &rdt_resources_all[level];
 
 	r->alloc_enabled = r->alloc_capable;
 
-	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) {
-		rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled = false;
-		rdt_resources_all[RDT_RESOURCE_L3CODE].alloc_enabled = false;
-		set_l3_qos_cfg(r, false);
+	if (rdt_resources_all[data_type].alloc_enabled) {
+		rdt_resources_all[data_type].alloc_enabled = false;
+		rdt_resources_all[code_type].alloc_enabled = false;
+		set_cache_qos_cfg(level, false);
 	}
 }
 
+static void cdpl3_disable(void)
+{
+	cdp_disable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, RDT_RESOURCE_L3CODE);
+}
+
+static void cdpl2_disable(void)
+{
+	cdp_disable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, RDT_RESOURCE_L2CODE);
+}
+
+static void cdp_disable_all(void)
+{
+	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled)
+		cdpl3_disable();
+	if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled)
+		cdpl2_disable();
+}
+
 static int parse_rdtgroupfs_options(char *data)
 {
 	char *token, *o = data;
 	int ret = 0;
 
 	while ((token = strsep(&o, ",")) != NULL) {
-		if (!*token)
-			return -EINVAL;
+		if (!*token) {
+			ret = -EINVAL;
+			goto out;
+		}
 
-		if (!strcmp(token, "cdp"))
-			ret = cdp_enable();
+		if (!strcmp(token, "cdp")) {
+			ret = cdpl3_enable();
+			if (ret)
+				goto out;
+		} else if (!strcmp(token, "cdpl2")) {
+			ret = cdpl2_enable();
+			if (ret)
+				goto out;
+		} else {
+			ret = -EINVAL;
+			goto out;
+		}
 	}
 
+	return 0;
+
+out:
+	pr_err("Invalid mount option \"%s\"\n", token);
+
 	return ret;
 }
 
@@ -1223,7 +1288,7 @@ out_mongrp:
 out_info:
 	kernfs_remove(kn_info);
 out_cdp:
-	cdp_disable();
+	cdp_disable_all();
 out:
 	rdt_last_cmd_clear();
 	mutex_unlock(&rdtgroup_mutex);
@@ -1383,7 +1448,7 @@ static void rdt_kill_sb(struct super_block *sb)
 	/*Put everything back to default values. */
 	for_each_alloc_enabled_rdt_resource(r)
 		reset_all_ctrls(r);
-	cdp_disable();
+	cdp_disable_all();
 	rmdir_all_sub();
 	static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
 	static_branch_disable_cpuslocked(&rdt_mon_enable_key);
diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
index 7f85b76f43bc..213e8c2ca702 100644
--- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
@@ -243,7 +243,7 @@ out:
 	return err ? err : buf - ubuf;
 }
 
-static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
+static __poll_t mce_chrdev_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &mce_chrdev_wait, wait);
 	if (READ_ONCE(mcelog.next))
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 4ca632a06e0b..5bbd06f38ff6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -59,6 +59,7 @@ static struct severity {
 #define  MCGMASK(x, y)	.mcgmask = x, .mcgres = y
 #define  MASK(x, y)	.mask = x, .result = y
 #define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S)
+#define MCI_UC_AR (MCI_STATUS_UC|MCI_STATUS_AR)
 #define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR)
 #define	MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV)
 
@@ -101,6 +102,22 @@ static struct severity {
 		NOSER, BITCLR(MCI_STATUS_UC)
 		),
 
+	/*
+	 * known AO MCACODs reported via MCE or CMC:
+	 *
+	 * SRAO could be signaled either via a machine check exception or
+	 * CMCI with the corresponding bit S 1 or 0. So we don't need to
+	 * check bit S for SRAO.
+	 */
+	MCESEV(
+		AO, "Action optional: memory scrubbing error",
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB)
+		),
+	MCESEV(
+		AO, "Action optional: last level cache writeback error",
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB)
+		),
+
 	/* ignore OVER for UCNA */
 	MCESEV(
 		UCNA, "Uncorrected no action required",
@@ -149,15 +166,6 @@ static struct severity {
 		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_SAR)
 		),
 
-	/* known AO MCACODs: */
-	MCESEV(
-		AO, "Action optional: memory scrubbing error",
-		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD_SCRUBMSK, MCI_UC_S|MCACOD_SCRUB)
-		),
-	MCESEV(
-		AO, "Action optional: last level cache writeback error",
-		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_S|MCACOD_L3WB)
-		),
 	MCESEV(
 		SOME, "Action optional: unknown MCACOD",
 		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_S)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index b1d616d08eee..3a8e88a611eb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -14,7 +14,6 @@
 #include <linux/capability.h>
 #include <linux/miscdevice.h>
 #include <linux/ratelimit.h>
-#include <linux/kallsyms.h>
 #include <linux/rcupdate.h>
 #include <linux/kobject.h>
 #include <linux/uaccess.h>
@@ -235,7 +234,7 @@ static void __print_mce(struct mce *m)
 			m->cs, m->ip);
 
 		if (m->cs == __KERNEL_CS)
-			print_symbol("{%s}", m->ip);
+			pr_cont("{%pS}", (void *)m->ip);
 		pr_cont("\n");
 	}
 
@@ -503,10 +502,8 @@ static int mce_usable_address(struct mce *m)
 bool mce_is_memory_error(struct mce *m)
 {
 	if (m->cpuvendor == X86_VENDOR_AMD) {
-		/* ErrCodeExt[20:16] */
-		u8 xec = (m->status >> 16) & 0x1f;
+		return amd_mce_is_memory_error(m);
 
-		return (xec == 0x0 || xec == 0x8);
 	} else if (m->cpuvendor == X86_VENDOR_INTEL) {
 		/*
 		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
@@ -530,6 +527,17 @@ bool mce_is_memory_error(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
+static bool mce_is_correctable(struct mce *m)
+{
+	if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
+		return false;
+
+	if (m->status & MCI_STATUS_UC)
+		return false;
+
+	return true;
+}
+
 static bool cec_add_mce(struct mce *m)
 {
 	if (!m)
@@ -537,7 +545,7 @@ static bool cec_add_mce(struct mce *m)
 
 	/* We eat only correctable DRAM errors with usable addresses. */
 	if (mce_is_memory_error(m) &&
-	    !(m->status & MCI_STATUS_UC) &&
+	    mce_is_correctable(m)  &&
 	    mce_usable_address(m))
 		if (!cec_add_elem(m->addr >> PAGE_SHIFT))
 			return true;
@@ -582,7 +590,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
 
 	if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) {
 		pfn = mce->addr >> PAGE_SHIFT;
-		memory_failure(pfn, MCE_VECTOR, 0);
+		memory_failure(pfn, 0);
 	}
 
 	return NOTIFY_OK;
@@ -1046,7 +1054,7 @@ static int do_memory_failure(struct mce *m)
 	pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
 	if (!(m->mcgstatus & MCG_STATUS_RIPV))
 		flags |= MF_MUST_KILL;
-	ret = memory_failure(m->addr >> PAGE_SHIFT, MCE_VECTOR, flags);
+	ret = memory_failure(m->addr >> PAGE_SHIFT, flags);
 	if (ret)
 		pr_err("Memory error not recovered");
 	return ret;
@@ -1325,7 +1333,7 @@ out_ist:
 EXPORT_SYMBOL_GPL(do_machine_check);
 
 #ifndef CONFIG_MEMORY_FAILURE
-int memory_failure(unsigned long pfn, int vector, int flags)
+int memory_failure(unsigned long pfn, int flags)
 {
 	/* mce_severity() should not hand us an ACTION_REQUIRED error */
 	BUG_ON(flags & MF_ACTION_REQUIRED);
@@ -1785,6 +1793,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code)
 void (*machine_check_vector)(struct pt_regs *, long error_code) =
 						unexpected_machine_check;
 
+dotraplinkage void do_mce(struct pt_regs *regs, long error_code)
+{
+	machine_check_vector(regs, error_code);
+}
+
 /*
  * Called for each booted CPU to set up machine checks.
  * Must be called with preempt off:
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 486f640b02ef..0f32ad242324 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -110,6 +110,20 @@ const char *smca_get_long_name(enum smca_bank_types t)
 }
 EXPORT_SYMBOL_GPL(smca_get_long_name);
 
+static enum smca_bank_types smca_get_bank_type(struct mce *m)
+{
+	struct smca_bank *b;
+
+	if (m->bank >= N_SMCA_BANK_TYPES)
+		return N_SMCA_BANK_TYPES;
+
+	b = &smca_banks[m->bank];
+	if (!b->hwid)
+		return N_SMCA_BANK_TYPES;
+
+	return b->hwid->bank_type;
+}
+
 static struct smca_hwid smca_hwid_mcatypes[] = {
 	/* { bank_type, hwid_mcatype, xec_bitmap } */
 
@@ -407,7 +421,9 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
 	    (deferred_error_int_vector != amd_deferred_error_interrupt))
 		deferred_error_int_vector = amd_deferred_error_interrupt;
 
-	low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+	if (!mce_flags.smca)
+		low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+
 	wrmsr(MSR_CU_DEF_ERR, low, high);
 }
 
@@ -738,6 +754,17 @@ out_err:
 }
 EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr);
 
+bool amd_mce_is_memory_error(struct mce *m)
+{
+	/* ErrCodeExt[20:16] */
+	u8 xec = (m->status >> 16) & 0x1f;
+
+	if (mce_flags.smca)
+		return smca_get_bank_type(m) == SMCA_UMC && xec == 0x0;
+
+	return m->bank == 4 && xec == 0x8;
+}
+
 static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
 {
 	struct mce m;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index c6daec4bdba5..330b8462d426 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -470,6 +470,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
 #define F14H_MPB_MAX_SIZE 1824
 #define F15H_MPB_MAX_SIZE 4096
 #define F16H_MPB_MAX_SIZE 3458
+#define F17H_MPB_MAX_SIZE 3200
 
 	switch (family) {
 	case 0x14:
@@ -481,6 +482,9 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
 	case 0x16:
 		max_size = F16H_MPB_MAX_SIZE;
 		break;
+	case 0x17:
+		max_size = F17H_MPB_MAX_SIZE;
+		break;
 	default:
 		max_size = F1XH_MPB_MAX_SIZE;
 		break;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index c4fa4a85d4cb..319dd65f98a2 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -239,7 +239,7 @@ static int __init save_microcode_in_initrd(void)
 		break;
 	case X86_VENDOR_AMD:
 		if (c->x86 >= 0x10)
-			return save_microcode_in_initrd_amd(cpuid_eax(1));
+			ret = save_microcode_in_initrd_amd(cpuid_eax(1));
 		break;
 	default:
 		break;
@@ -560,7 +560,7 @@ static ssize_t pf_show(struct device *dev,
 	return sprintf(buf, "0x%x\n", uci->cpu_sig.pf);
 }
 
-static DEVICE_ATTR(reload, 0200, NULL, reload_store);
+static DEVICE_ATTR_WO(reload);
 static DEVICE_ATTR(version, 0400, version_show, NULL);
 static DEVICE_ATTR(processor_flags, 0400, pf_show, NULL);
 
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 7dbcb7adf797..f7c55b0e753a 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -45,6 +45,9 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin";
 /* Current microcode patch used in early patching on the APs. */
 static struct microcode_intel *intel_ucode_patch;
 
+/* last level cache size per core */
+static int llc_size_per_core;
+
 static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
 					unsigned int s2, unsigned int p2)
 {
@@ -565,15 +568,6 @@ static void print_ucode(struct ucode_cpu_info *uci)
 }
 #else
 
-/*
- * Flush global tlb. We only do this in x86_64 where paging has been enabled
- * already and PGE should be enabled as well.
- */
-static inline void flush_tlb_early(void)
-{
-	__native_flush_tlb_global_irq_disabled();
-}
-
 static inline void print_ucode(struct ucode_cpu_info *uci)
 {
 	struct microcode_intel *mc;
@@ -602,10 +596,6 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 	if (rev != mc->hdr.rev)
 		return -1;
 
-#ifdef CONFIG_X86_64
-	/* Flush global tlb. This is precaution. */
-	flush_tlb_early();
-#endif
 	uci->cpu_sig.rev = rev;
 
 	if (early)
@@ -923,8 +913,19 @@ static bool is_blacklisted(unsigned int cpu)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) {
-		pr_err_once("late loading on model 79 is disabled.\n");
+	/*
+	 * Late loading on model 79 with microcode revision less than 0x0b000021
+	 * and LLC size per core bigger than 2.5MB may result in a system hang.
+	 * This behavior is documented in item BDF90, #334165 (Intel Xeon
+	 * Processor E7-8800/4800 v4 Product Family).
+	 */
+	if (c->x86 == 6 &&
+	    c->x86_model == INTEL_FAM6_BROADWELL_X &&
+	    c->x86_mask == 0x01 &&
+	    llc_size_per_core > 2621440 &&
+	    c->microcode < 0x0b000021) {
+		pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode);
+		pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
 		return true;
 	}
 
@@ -979,6 +980,15 @@ static struct microcode_ops microcode_intel_ops = {
 	.apply_microcode                  = apply_microcode_intel,
 };
 
+static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c)
+{
+	u64 llc_size = c->x86_cache_size * 1024;
+
+	do_div(llc_size, c->x86_max_cores);
+
+	return (int)llc_size;
+}
+
 struct microcode_ops * __init init_intel_microcode(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
@@ -989,5 +999,7 @@ struct microcode_ops * __init init_intel_microcode(void)
 		return NULL;
 	}
 
+	llc_size_per_core = calc_llc_size_per_core(c);
+
 	return &microcode_intel_ops;
 }
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 05459ad3db46..4075d2be5357 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -21,12 +21,10 @@ struct cpuid_bit {
 static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
-	{ X86_FEATURE_INTEL_PT,		CPUID_EBX, 25, 0x00000007, 0 },
-	{ X86_FEATURE_AVX512_4VNNIW,    CPUID_EDX,  2, 0x00000007, 0 },
-	{ X86_FEATURE_AVX512_4FMAPS,    CPUID_EDX,  3, 0x00000007, 0 },
 	{ X86_FEATURE_CAT_L3,		CPUID_EBX,  1, 0x00000010, 0 },
 	{ X86_FEATURE_CAT_L2,		CPUID_EBX,  2, 0x00000010, 0 },
 	{ X86_FEATURE_CDP_L3,		CPUID_ECX,  2, 0x00000010, 1 },
+	{ X86_FEATURE_CDP_L2,		CPUID_ECX,  2, 0x00000010, 2 },
 	{ X86_FEATURE_MBA,		CPUID_EBX,  3, 0x00000010, 0 },
 	{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
 	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 76e07698e6d1..25de5f6ca997 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -2,7 +2,6 @@
 /*
  * Architecture specific OF callbacks.
  */
-#include <linux/bootmem.h>
 #include <linux/export.h>
 #include <linux/io.h>
 #include <linux/interrupt.h>
@@ -39,11 +38,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	BUG();
 }
 
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
-}
-
 void __init add_dtb(u64 data)
 {
 	initial_dtb = data + offsetof(struct setup_data, data);
diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c
index 0e662c55ae90..0b8cedb20d6d 100644
--- a/arch/x86/kernel/doublefault.c
+++ b/arch/x86/kernel/doublefault.c
@@ -50,25 +50,23 @@ static void doublefault_fn(void)
 		cpu_relax();
 }
 
-struct tss_struct doublefault_tss __cacheline_aligned = {
-	.x86_tss = {
-		.sp0		= STACK_START,
-		.ss0		= __KERNEL_DS,
-		.ldt		= 0,
-		.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,
-
-		.ip		= (unsigned long) doublefault_fn,
-		/* 0x2 bit is always set */
-		.flags		= X86_EFLAGS_SF | 0x2,
-		.sp		= STACK_START,
-		.es		= __USER_DS,
-		.cs		= __KERNEL_CS,
-		.ss		= __KERNEL_DS,
-		.ds		= __USER_DS,
-		.fs		= __KERNEL_PERCPU,
-
-		.__cr3		= __pa_nodebug(swapper_pg_dir),
-	}
+struct x86_hw_tss doublefault_tss __cacheline_aligned = {
+	.sp0		= STACK_START,
+	.ss0		= __KERNEL_DS,
+	.ldt		= 0,
+	.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,
+
+	.ip		= (unsigned long) doublefault_fn,
+	/* 0x2 bit is always set */
+	.flags		= X86_EFLAGS_SF | 0x2,
+	.sp		= STACK_START,
+	.es		= __USER_DS,
+	.cs		= __KERNEL_CS,
+	.ss		= __KERNEL_DS,
+	.ds		= __USER_DS,
+	.fs		= __KERNEL_PERCPU,
+
+	.__cr3		= __pa_nodebug(swapper_pg_dir),
 };
 
 /* dummy for do_double_fault() call */
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index f13b4c00a5de..afbecff161d1 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -18,6 +18,7 @@
 #include <linux/nmi.h>
 #include <linux/sysfs.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 
@@ -43,6 +44,24 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task,
 	return true;
 }
 
+bool in_entry_stack(unsigned long *stack, struct stack_info *info)
+{
+	struct entry_stack *ss = cpu_entry_stack(smp_processor_id());
+
+	void *begin = ss;
+	void *end = ss + 1;
+
+	if ((void *)stack < begin || (void *)stack >= end)
+		return false;
+
+	info->type	= STACK_TYPE_ENTRY;
+	info->begin	= begin;
+	info->end	= end;
+	info->next_sp	= NULL;
+
+	return true;
+}
+
 static void printk_stack_address(unsigned long address, int reliable,
 				 char *log_lvl)
 {
@@ -50,6 +69,39 @@ static void printk_stack_address(unsigned long address, int reliable,
 	printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
 }
 
+void show_iret_regs(struct pt_regs *regs)
+{
+	printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip);
+	printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss,
+		regs->sp, regs->flags);
+}
+
+static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs,
+				  bool partial)
+{
+	/*
+	 * These on_stack() checks aren't strictly necessary: the unwind code
+	 * has already validated the 'regs' pointer.  The checks are done for
+	 * ordering reasons: if the registers are on the next stack, we don't
+	 * want to print them out yet.  Otherwise they'll be shown as part of
+	 * the wrong stack.  Later, when show_trace_log_lvl() switches to the
+	 * next stack, this function will be called again with the same regs so
+	 * they can be printed in the right context.
+	 */
+	if (!partial && on_stack(info, regs, sizeof(*regs))) {
+		__show_regs(regs, 0);
+
+	} else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET,
+				       IRET_FRAME_SIZE)) {
+		/*
+		 * When an interrupt or exception occurs in entry code, the
+		 * full pt_regs might not have been saved yet.  In that case
+		 * just print the iret frame.
+		 */
+		show_iret_regs(regs);
+	}
+}
+
 void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			unsigned long *stack, char *log_lvl)
 {
@@ -57,11 +109,13 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	struct stack_info stack_info = {0};
 	unsigned long visit_mask = 0;
 	int graph_idx = 0;
+	bool partial;
 
 	printk("%sCall Trace:\n", log_lvl);
 
 	unwind_start(&state, task, regs, stack);
 	stack = stack ? : get_stack_pointer(task, regs);
+	regs = unwind_get_entry_regs(&state, &partial);
 
 	/*
 	 * Iterate through the stacks, starting with the current stack pointer.
@@ -71,31 +125,35 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	 * - task stack
 	 * - interrupt stack
 	 * - HW exception stacks (double fault, nmi, debug, mce)
+	 * - entry stack
 	 *
-	 * x86-32 can have up to three stacks:
+	 * x86-32 can have up to four stacks:
 	 * - task stack
 	 * - softirq stack
 	 * - hardirq stack
+	 * - entry stack
 	 */
-	for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
+	for ( ; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
 		const char *stack_name;
 
-		/*
-		 * If we overflowed the task stack into a guard page, jump back
-		 * to the bottom of the usable stack.
-		 */
-		if (task_stack_page(task) - (void *)stack < PAGE_SIZE)
-			stack = task_stack_page(task);
-
-		if (get_stack_info(stack, task, &stack_info, &visit_mask))
-			break;
+		if (get_stack_info(stack, task, &stack_info, &visit_mask)) {
+			/*
+			 * We weren't on a valid stack.  It's possible that
+			 * we overflowed a valid stack into a guard page.
+			 * See if the next page up is valid so that we can
+			 * generate some kind of backtrace if this happens.
+			 */
+			stack = (unsigned long *)PAGE_ALIGN((unsigned long)stack);
+			if (get_stack_info(stack, task, &stack_info, &visit_mask))
+				break;
+		}
 
 		stack_name = stack_type_name(stack_info.type);
 		if (stack_name)
 			printk("%s <%s>\n", log_lvl, stack_name);
 
-		if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
-			__show_regs(regs, 0);
+		if (regs)
+			show_regs_if_on_stack(&stack_info, regs, partial);
 
 		/*
 		 * Scan the stack, printing any text addresses we find.  At the
@@ -119,7 +177,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 
 			/*
 			 * Don't print regs->ip again if it was already printed
-			 * by __show_regs() below.
+			 * by show_regs_if_on_stack().
 			 */
 			if (regs && stack == &regs->ip)
 				goto next;
@@ -154,9 +212,9 @@ next:
 			unwind_next_frame(&state);
 
 			/* if the frame has entry regs, print them */
-			regs = unwind_get_entry_regs(&state);
-			if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
-				__show_regs(regs, 0);
+			regs = unwind_get_entry_regs(&state, &partial);
+			if (regs)
+				show_regs_if_on_stack(&stack_info, regs, partial);
 		}
 
 		if (stack_name)
@@ -252,11 +310,13 @@ int __die(const char *str, struct pt_regs *regs, long err)
 	unsigned long sp;
 #endif
 	printk(KERN_DEFAULT
-	       "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter,
+	       "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
 	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT"         : "",
 	       IS_ENABLED(CONFIG_SMP)     ? " SMP"             : "",
 	       debug_pagealloc_enabled()  ? " DEBUG_PAGEALLOC" : "",
-	       IS_ENABLED(CONFIG_KASAN)   ? " KASAN"           : "");
+	       IS_ENABLED(CONFIG_KASAN)   ? " KASAN"           : "",
+	       IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ?
+	       (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : "");
 
 	if (notify_die(DIE_OOPS, str, regs, err,
 			current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index daefae83a3aa..04170f63e3a1 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -26,6 +26,9 @@ const char *stack_type_name(enum stack_type type)
 	if (type == STACK_TYPE_SOFTIRQ)
 		return "SOFTIRQ";
 
+	if (type == STACK_TYPE_ENTRY)
+		return "ENTRY_TRAMPOLINE";
+
 	return NULL;
 }
 
@@ -93,6 +96,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	if (task != current)
 		goto unknown;
 
+	if (in_entry_stack(stack, info))
+		goto recursion_check;
+
 	if (in_hardirq_stack(stack, info))
 		goto recursion_check;
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 88ce2ffdb110..563e28d14f2c 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -37,6 +37,15 @@ const char *stack_type_name(enum stack_type type)
 	if (type == STACK_TYPE_IRQ)
 		return "IRQ";
 
+	if (type == STACK_TYPE_ENTRY) {
+		/*
+		 * On 64-bit, we have a generic entry stack that we
+		 * use for all the kernel entry points, including
+		 * SYSENTER.
+		 */
+		return "ENTRY_TRAMPOLINE";
+	}
+
 	if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST)
 		return exception_stack_names[type - STACK_TYPE_EXCEPTION];
 
@@ -115,6 +124,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	if (in_irq_stack(stack, info))
 		goto recursion_check;
 
+	if (in_entry_stack(stack, info))
+		goto recursion_check;
+
 	goto unknown;
 
 recursion_check:
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 1e82f787c160..bae0d32e327b 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -243,7 +243,7 @@ static void __init intel_remapping_check(int num, int slot, int func)
 #define KB(x)	((x) * 1024UL)
 #define MB(x)	(KB (KB (x)))
 
-static size_t __init i830_tseg_size(void)
+static resource_size_t __init i830_tseg_size(void)
 {
 	u8 esmramc = read_pci_config_byte(0, 0, 0, I830_ESMRAMC);
 
@@ -256,7 +256,7 @@ static size_t __init i830_tseg_size(void)
 		return KB(512);
 }
 
-static size_t __init i845_tseg_size(void)
+static resource_size_t __init i845_tseg_size(void)
 {
 	u8 esmramc = read_pci_config_byte(0, 0, 0, I845_ESMRAMC);
 	u8 tseg_size = esmramc & I845_TSEG_SIZE_MASK;
@@ -273,7 +273,7 @@ static size_t __init i845_tseg_size(void)
 	return 0;
 }
 
-static size_t __init i85x_tseg_size(void)
+static resource_size_t __init i85x_tseg_size(void)
 {
 	u8 esmramc = read_pci_config_byte(0, 0, 0, I85X_ESMRAMC);
 
@@ -283,12 +283,12 @@ static size_t __init i85x_tseg_size(void)
 	return MB(1);
 }
 
-static size_t __init i830_mem_size(void)
+static resource_size_t __init i830_mem_size(void)
 {
 	return read_pci_config_byte(0, 0, 0, I830_DRB3) * MB(32);
 }
 
-static size_t __init i85x_mem_size(void)
+static resource_size_t __init i85x_mem_size(void)
 {
 	return read_pci_config_byte(0, 0, 1, I85X_DRB3) * MB(32);
 }
@@ -297,36 +297,36 @@ static size_t __init i85x_mem_size(void)
  * On 830/845/85x the stolen memory base isn't available in any
  * register. We need to calculate it as TOM-TSEG_SIZE-stolen_size.
  */
-static phys_addr_t __init i830_stolen_base(int num, int slot, int func,
-					   size_t stolen_size)
+static resource_size_t __init i830_stolen_base(int num, int slot, int func,
+					       resource_size_t stolen_size)
 {
-	return (phys_addr_t)i830_mem_size() - i830_tseg_size() - stolen_size;
+	return i830_mem_size() - i830_tseg_size() - stolen_size;
 }
 
-static phys_addr_t __init i845_stolen_base(int num, int slot, int func,
-					   size_t stolen_size)
+static resource_size_t __init i845_stolen_base(int num, int slot, int func,
+					       resource_size_t stolen_size)
 {
-	return (phys_addr_t)i830_mem_size() - i845_tseg_size() - stolen_size;
+	return i830_mem_size() - i845_tseg_size() - stolen_size;
 }
 
-static phys_addr_t __init i85x_stolen_base(int num, int slot, int func,
-					   size_t stolen_size)
+static resource_size_t __init i85x_stolen_base(int num, int slot, int func,
+					       resource_size_t stolen_size)
 {
-	return (phys_addr_t)i85x_mem_size() - i85x_tseg_size() - stolen_size;
+	return i85x_mem_size() - i85x_tseg_size() - stolen_size;
 }
 
-static phys_addr_t __init i865_stolen_base(int num, int slot, int func,
-					   size_t stolen_size)
+static resource_size_t __init i865_stolen_base(int num, int slot, int func,
+					       resource_size_t stolen_size)
 {
 	u16 toud = 0;
 
 	toud = read_pci_config_16(0, 0, 0, I865_TOUD);
 
-	return (phys_addr_t)(toud << 16) + i845_tseg_size();
+	return toud * KB(64) + i845_tseg_size();
 }
 
-static phys_addr_t __init gen3_stolen_base(int num, int slot, int func,
-					   size_t stolen_size)
+static resource_size_t __init gen3_stolen_base(int num, int slot, int func,
+					       resource_size_t stolen_size)
 {
 	u32 bsm;
 
@@ -337,10 +337,10 @@ static phys_addr_t __init gen3_stolen_base(int num, int slot, int func,
 	 */
 	bsm = read_pci_config(num, slot, func, INTEL_BSM);
 
-	return (phys_addr_t)bsm & INTEL_BSM_MASK;
+	return bsm & INTEL_BSM_MASK;
 }
 
-static size_t __init i830_stolen_size(int num, int slot, int func)
+static resource_size_t __init i830_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
 	u16 gms;
@@ -361,7 +361,7 @@ static size_t __init i830_stolen_size(int num, int slot, int func)
 	return 0;
 }
 
-static size_t __init gen3_stolen_size(int num, int slot, int func)
+static resource_size_t __init gen3_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
 	u16 gms;
@@ -390,7 +390,7 @@ static size_t __init gen3_stolen_size(int num, int slot, int func)
 	return 0;
 }
 
-static size_t __init gen6_stolen_size(int num, int slot, int func)
+static resource_size_t __init gen6_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
 	u16 gms;
@@ -398,10 +398,10 @@ static size_t __init gen6_stolen_size(int num, int slot, int func)
 	gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
 	gms = (gmch_ctrl >> SNB_GMCH_GMS_SHIFT) & SNB_GMCH_GMS_MASK;
 
-	return (size_t)gms * MB(32);
+	return gms * MB(32);
 }
 
-static size_t __init gen8_stolen_size(int num, int slot, int func)
+static resource_size_t __init gen8_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
 	u16 gms;
@@ -409,10 +409,10 @@ static size_t __init gen8_stolen_size(int num, int slot, int func)
 	gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
 	gms = (gmch_ctrl >> BDW_GMCH_GMS_SHIFT) & BDW_GMCH_GMS_MASK;
 
-	return (size_t)gms * MB(32);
+	return gms * MB(32);
 }
 
-static size_t __init chv_stolen_size(int num, int slot, int func)
+static resource_size_t __init chv_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
 	u16 gms;
@@ -426,14 +426,14 @@ static size_t __init chv_stolen_size(int num, int slot, int func)
 	 * 0x17 to 0x1d: 4MB increments start at 36MB
 	 */
 	if (gms < 0x11)
-		return (size_t)gms * MB(32);
+		return gms * MB(32);
 	else if (gms < 0x17)
-		return (size_t)(gms - 0x11 + 2) * MB(4);
+		return (gms - 0x11) * MB(4) + MB(8);
 	else
-		return (size_t)(gms - 0x17 + 9) * MB(4);
+		return (gms - 0x17) * MB(4) + MB(36);
 }
 
-static size_t __init gen9_stolen_size(int num, int slot, int func)
+static resource_size_t __init gen9_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
 	u16 gms;
@@ -444,14 +444,15 @@ static size_t __init gen9_stolen_size(int num, int slot, int func)
 	/* 0x0  to 0xef: 32MB increments starting at 0MB */
 	/* 0xf0 to 0xfe: 4MB increments starting at 4MB */
 	if (gms < 0xf0)
-		return (size_t)gms * MB(32);
+		return gms * MB(32);
 	else
-		return (size_t)(gms - 0xf0 + 1) * MB(4);
+		return (gms - 0xf0) * MB(4) + MB(4);
 }
 
 struct intel_early_ops {
-	size_t (*stolen_size)(int num, int slot, int func);
-	phys_addr_t (*stolen_base)(int num, int slot, int func, size_t size);
+	resource_size_t (*stolen_size)(int num, int slot, int func);
+	resource_size_t (*stolen_base)(int num, int slot, int func,
+				       resource_size_t size);
 };
 
 static const struct intel_early_ops i830_early_ops __initconst = {
@@ -527,16 +528,20 @@ static const struct pci_device_id intel_early_ids[] __initconst = {
 	INTEL_SKL_IDS(&gen9_early_ops),
 	INTEL_BXT_IDS(&gen9_early_ops),
 	INTEL_KBL_IDS(&gen9_early_ops),
+	INTEL_CFL_IDS(&gen9_early_ops),
 	INTEL_GLK_IDS(&gen9_early_ops),
 	INTEL_CNL_IDS(&gen9_early_ops),
 };
 
+struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0);
+EXPORT_SYMBOL(intel_graphics_stolen_res);
+
 static void __init
 intel_graphics_stolen(int num, int slot, int func,
 		      const struct intel_early_ops *early_ops)
 {
-	phys_addr_t base, end;
-	size_t size;
+	resource_size_t base, size;
+	resource_size_t end;
 
 	size = early_ops->stolen_size(num, slot, func);
 	base = early_ops->stolen_base(num, slot, func, size);
@@ -545,8 +550,12 @@ intel_graphics_stolen(int num, int slot, int func,
 		return;
 
 	end = base + size - 1;
-	printk(KERN_INFO "Reserving Intel graphics memory at %pa-%pa\n",
-	       &base, &end);
+
+	intel_graphics_stolen_res.start = base;
+	intel_graphics_stolen_res.end = end;
+
+	printk(KERN_INFO "Reserving Intel graphics memory at %pR\n",
+	       &intel_graphics_stolen_res);
 
 	/* Mark this space as reserved */
 	e820__range_add(base, size, E820_TYPE_RESERVED);
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index b6c6468e10bc..4c8440de3355 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -8,6 +8,7 @@
 #include <asm/segment.h>
 #include <asm/export.h>
 #include <asm/ftrace.h>
+#include <asm/nospec-branch.h>
 
 #ifdef CC_USING_FENTRY
 # define function_hook	__fentry__
@@ -197,7 +198,8 @@ ftrace_stub:
 	movl	0x4(%ebp), %edx
 	subl	$MCOUNT_INSN_SIZE, %eax
 
-	call	*ftrace_trace_function
+	movl	ftrace_trace_function, %ecx
+	CALL_NOSPEC %ecx
 
 	popl	%edx
 	popl	%ecx
@@ -241,5 +243,5 @@ return_to_handler:
 	movl	%eax, %ecx
 	popl	%edx
 	popl	%eax
-	jmp	*%ecx
+	JMP_NOSPEC %ecx
 #endif
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index c832291d948a..91b2cff4b79a 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -7,7 +7,8 @@
 #include <asm/ptrace.h>
 #include <asm/ftrace.h>
 #include <asm/export.h>
-
+#include <asm/nospec-branch.h>
+#include <asm/unwind_hints.h>
 
 	.code64
 	.section .entry.text, "ax"
@@ -20,7 +21,6 @@ EXPORT_SYMBOL(__fentry__)
 EXPORT_SYMBOL(mcount)
 #endif
 
-/* All cases save the original rbp (8 bytes) */
 #ifdef CONFIG_FRAME_POINTER
 # ifdef CC_USING_FENTRY
 /* Save parent and function stack frames (rip and rbp) */
@@ -31,7 +31,7 @@ EXPORT_SYMBOL(mcount)
 # endif
 #else
 /* No need to save a stack frame */
-# define MCOUNT_FRAME_SIZE	8
+# define MCOUNT_FRAME_SIZE	0
 #endif /* CONFIG_FRAME_POINTER */
 
 /* Size of stack used to save mcount regs in save_mcount_regs */
@@ -64,10 +64,10 @@ EXPORT_SYMBOL(mcount)
  */
 .macro save_mcount_regs added=0
 
-	/* Always save the original rbp */
+#ifdef CONFIG_FRAME_POINTER
+	/* Save the original rbp */
 	pushq %rbp
 
-#ifdef CONFIG_FRAME_POINTER
 	/*
 	 * Stack traces will stop at the ftrace trampoline if the frame pointer
 	 * is not set up properly. If fentry is used, we need to save a frame
@@ -105,7 +105,11 @@ EXPORT_SYMBOL(mcount)
 	 * Save the original RBP. Even though the mcount ABI does not
 	 * require this, it helps out callers.
 	 */
+#ifdef CONFIG_FRAME_POINTER
 	movq MCOUNT_REG_SIZE-8(%rsp), %rdx
+#else
+	movq %rbp, %rdx
+#endif
 	movq %rdx, RBP(%rsp)
 
 	/* Copy the parent address into %rsi (second parameter) */
@@ -148,7 +152,7 @@ EXPORT_SYMBOL(mcount)
 
 ENTRY(function_hook)
 	retq
-END(function_hook)
+ENDPROC(function_hook)
 
 ENTRY(ftrace_caller)
 	/* save_mcount_regs fills in first two parameters */
@@ -184,7 +188,7 @@ GLOBAL(ftrace_graph_call)
 /* This is weak to keep gas from relaxing the jumps */
 WEAK(ftrace_stub)
 	retq
-END(ftrace_caller)
+ENDPROC(ftrace_caller)
 
 ENTRY(ftrace_regs_caller)
 	/* Save the current flags before any operations that can change them */
@@ -255,7 +259,7 @@ GLOBAL(ftrace_regs_caller_end)
 
 	jmp ftrace_epilogue
 
-END(ftrace_regs_caller)
+ENDPROC(ftrace_regs_caller)
 
 
 #else /* ! CONFIG_DYNAMIC_FTRACE */
@@ -286,12 +290,12 @@ trace:
 	 * ip and parent ip are used and the list function is called when
 	 * function tracing is enabled.
 	 */
-	call   *ftrace_trace_function
-
+	movq ftrace_trace_function, %r8
+	CALL_NOSPEC %r8
 	restore_mcount_regs
 
 	jmp fgraph_trace
-END(function_hook)
+ENDPROC(function_hook)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -313,9 +317,10 @@ ENTRY(ftrace_graph_caller)
 	restore_mcount_regs
 
 	retq
-END(ftrace_graph_caller)
+ENDPROC(ftrace_graph_caller)
 
-GLOBAL(return_to_handler)
+ENTRY(return_to_handler)
+	UNWIND_HINT_EMPTY
 	subq  $24, %rsp
 
 	/* Save the return values */
@@ -329,5 +334,6 @@ GLOBAL(return_to_handler)
 	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
 	addq $24, %rsp
-	jmp *%rdi
+	JMP_NOSPEC %rdi
+END(return_to_handler)
 #endif
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 6a5d757b9cfd..7ba5d819ebe3 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -157,8 +157,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	p = fixup_pointer(&phys_base, physaddr);
 	*p += load_delta - sme_get_me_mask();
 
-	/* Encrypt the kernel (if SME is active) */
-	sme_encrypt_kernel();
+	/* Encrypt the kernel and related (if SME is active) */
+	sme_encrypt_kernel(bp);
 
 	/*
 	 * Return the SME encryption mask (if SME is active) to be used as a
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7dca675fe78d..04a625f0fcda 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -341,6 +341,27 @@ GLOBAL(early_recursion_flag)
 	.balign	PAGE_SIZE; \
 GLOBAL(name)
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Each PGD needs to be 8k long and 8k aligned.  We do not
+ * ever go out to userspace with these, so we do not
+ * strictly *need* the second page, but this allows us to
+ * have a single set_pgd() implementation that does not
+ * need to worry about whether it has 4k or 8k to work
+ * with.
+ *
+ * This ensures PGDs are 8k long:
+ */
+#define PTI_USER_PGD_FILL	512
+/* This ensures they are 8k-aligned: */
+#define NEXT_PGD_PAGE(name) \
+	.balign 2 * PAGE_SIZE; \
+GLOBAL(name)
+#else
+#define NEXT_PGD_PAGE(name) NEXT_PAGE(name)
+#define PTI_USER_PGD_FILL	0
+#endif
+
 /* Automate the creation of 1 to 1 mapping pmd entries */
 #define PMDS(START, PERM, COUNT)			\
 	i = 0 ;						\
@@ -350,13 +371,14 @@ GLOBAL(name)
 	.endr
 
 	__INITDATA
-NEXT_PAGE(early_top_pgt)
+NEXT_PGD_PAGE(early_top_pgt)
 	.fill	511,8,0
 #ifdef CONFIG_X86_5LEVEL
 	.quad	level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 #else
 	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 #endif
+	.fill	PTI_USER_PGD_FILL,8,0
 
 NEXT_PAGE(early_dynamic_pgts)
 	.fill	512*EARLY_DYNAMIC_PAGE_TABLES,8,0
@@ -364,13 +386,14 @@ NEXT_PAGE(early_dynamic_pgts)
 	.data
 
 #if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.org    init_top_pgt + PGD_PAGE_OFFSET*8, 0
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.org    init_top_pgt + PGD_START_KERNEL*8, 0
 	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
 	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+	.fill	PTI_USER_PGD_FILL,8,0
 
 NEXT_PAGE(level3_ident_pgt)
 	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
@@ -381,8 +404,9 @@ NEXT_PAGE(level2_ident_pgt)
 	 */
 	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
 #else
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
 	.fill	512,8,0
+	.fill	PTI_USER_PGD_FILL,8,0
 #endif
 
 #ifdef CONFIG_X86_5LEVEL
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index d985cef3984f..56d99be3706a 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -56,7 +56,7 @@ struct idt_data {
  * Early traps running on the DEFAULT_STACK because the other interrupt
  * stacks work only after cpu_init().
  */
-static const __initdata struct idt_data early_idts[] = {
+static const __initconst struct idt_data early_idts[] = {
 	INTG(X86_TRAP_DB,		debug),
 	SYSG(X86_TRAP_BP,		int3),
 #ifdef CONFIG_X86_32
@@ -70,7 +70,7 @@ static const __initdata struct idt_data early_idts[] = {
  * the traps which use them are reinitialized with IST after cpu_init() has
  * set up TSS.
  */
-static const __initdata struct idt_data def_idts[] = {
+static const __initconst struct idt_data def_idts[] = {
 	INTG(X86_TRAP_DE,		divide_error),
 	INTG(X86_TRAP_NMI,		nmi),
 	INTG(X86_TRAP_BR,		bounds),
@@ -108,7 +108,7 @@ static const __initdata struct idt_data def_idts[] = {
 /*
  * The APIC and SMP idt entries
  */
-static const __initdata struct idt_data apic_idts[] = {
+static const __initconst struct idt_data apic_idts[] = {
 #ifdef CONFIG_SMP
 	INTG(RESCHEDULE_VECTOR,		reschedule_interrupt),
 	INTG(CALL_FUNCTION_VECTOR,	call_function_interrupt),
@@ -150,7 +150,7 @@ static const __initdata struct idt_data apic_idts[] = {
  * Early traps running on the DEFAULT_STACK because the other interrupt
  * stacks work only after cpu_init().
  */
-static const __initdata struct idt_data early_pf_idts[] = {
+static const __initconst struct idt_data early_pf_idts[] = {
 	INTG(X86_TRAP_PF,		page_fault),
 };
 
@@ -158,7 +158,7 @@ static const __initdata struct idt_data early_pf_idts[] = {
  * Override for the debug_idt. Same as the default, but with interrupt
  * stack set to DEFAULT_STACK (0). Required for NMI trap handling.
  */
-static const __initdata struct idt_data dbg_idts[] = {
+static const __initconst struct idt_data dbg_idts[] = {
 	INTG(X86_TRAP_DB,	debug),
 	INTG(X86_TRAP_BP,	int3),
 };
@@ -180,7 +180,7 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;
  * The exceptions which use Interrupt stacks. They are setup after
  * cpu_init() when the TSS has been initialized.
  */
-static const __initdata struct idt_data ist_idts[] = {
+static const __initconst struct idt_data ist_idts[] = {
 	ISTG(X86_TRAP_DB,	debug,		DEBUG_STACK),
 	ISTG(X86_TRAP_NMI,	nmi,		NMI_STACK),
 	SISTG(X86_TRAP_BP,	int3,		DEBUG_STACK),
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 3feb648781c4..2f723301eb58 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -67,7 +67,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 	 * because the ->io_bitmap_max value must match the bitmap
 	 * contents:
 	 */
-	tss = &per_cpu(cpu_tss, get_cpu());
+	tss = &per_cpu(cpu_tss_rw, get_cpu());
 
 	if (turn_on)
 		bitmap_clear(t->io_bitmap_ptr, from, num);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 49cfd9fe7589..68e1867cca80 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -219,18 +219,6 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	/* high bit used in ret_from_ code  */
 	unsigned vector = ~regs->orig_ax;
 
-	/*
-	 * NB: Unlike exception entries, IRQ entries do not reliably
-	 * handle context tracking in the low-level entry code.  This is
-	 * because syscall entries execute briefly with IRQs on before
-	 * updating context tracking state, so we can take an IRQ from
-	 * kernel mode with CONTEXT_USER.  The low-level entry code only
-	 * updates the context if we came from user mode, so we won't
-	 * switch to CONTEXT_KERNEL.  We'll fix that once the syscall
-	 * code is cleaned up enough that we can cleanly defer enabling
-	 * IRQs.
-	 */
-
 	entering_irq();
 
 	/* entering_irq() tells RCU that we're not quiescent.  Check it. */
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index a83b3346a0e1..c1bdbd3d3232 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -20,6 +20,7 @@
 #include <linux/mm.h>
 
 #include <asm/apic.h>
+#include <asm/nospec-branch.h>
 
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
 
@@ -55,11 +56,11 @@ DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
 static void call_on_stack(void *func, void *stack)
 {
 	asm volatile("xchgl	%%ebx,%%esp	\n"
-		     "call	*%%edi		\n"
+		     CALL_NOSPEC
 		     "movl	%%ebx,%%esp	\n"
 		     : "=b" (stack)
 		     : "0" (stack),
-		       "D"(func)
+		       [thunk_target] "D"(func)
 		     : "memory", "cc", "edx", "ecx", "eax");
 }
 
@@ -95,11 +96,11 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 		call_on_stack(print_stack_overflow, isp);
 
 	asm volatile("xchgl	%%ebx,%%esp	\n"
-		     "call	*%%edi		\n"
+		     CALL_NOSPEC
 		     "movl	%%ebx,%%esp	\n"
 		     : "=a" (arg1), "=b" (isp)
 		     :  "0" (desc),   "1" (isp),
-			"D" (desc->handle_irq)
+			[thunk_target] "D" (desc->handle_irq)
 		     : "memory", "cc", "ecx");
 	return 1;
 }
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 020efbf5786b..d86e344f5b3d 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -57,10 +57,10 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 	if (regs->sp >= estack_top && regs->sp <= estack_bottom)
 		return;
 
-	WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n",
+	WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n",
 		current->comm, curbase, regs->sp,
 		irq_stack_top, irq_stack_bottom,
-		estack_top, estack_bottom);
+		estack_top, estack_bottom, (void *)regs->ip);
 
 	if (sysctl_panic_on_stackoverflow)
 		panic("low stack detected by irq handler - check messages\n");
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 8da3e909e967..a539410c4ea9 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -61,6 +61,9 @@ void __init init_ISA_irqs(void)
 	struct irq_chip *chip = legacy_pic->chip;
 	int i;
 
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+	init_bsp_APIC();
+#endif
 	legacy_pic->init(0);
 
 	for (i = 0; i < nr_legacy_irqs(); i++)
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index f73f475d0573..d177940aa090 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -24,7 +24,6 @@
 #include <linux/cpumask.h>
 #include <linux/cpuset.h>
 #include <linux/mutex.h>
-#include <linux/sched.h>
 #include <linux/sysctl.h>
 #include <linux/nodemask.h>
 
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
new file mode 100644
index 000000000000..b68fd895235a
--- /dev/null
+++ b/arch/x86/kernel/jailhouse.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL2.0
+/*
+ * Jailhouse paravirt_ops implementation
+ *
+ * Copyright (c) Siemens AG, 2015-2017
+ *
+ * Authors:
+ *  Jan Kiszka <jan.kiszka@siemens.com>
+ */
+
+#include <linux/acpi_pmtmr.h>
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <asm/apic.h>
+#include <asm/cpu.h>
+#include <asm/hypervisor.h>
+#include <asm/i8259.h>
+#include <asm/irqdomain.h>
+#include <asm/pci_x86.h>
+#include <asm/reboot.h>
+#include <asm/setup.h>
+
+static __initdata struct jailhouse_setup_data setup_data;
+static unsigned int precalibrated_tsc_khz;
+
+static uint32_t jailhouse_cpuid_base(void)
+{
+	if (boot_cpu_data.cpuid_level < 0 ||
+	    !boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return 0;
+
+	return hypervisor_cpuid_base("Jailhouse\0\0\0", 0);
+}
+
+static uint32_t __init jailhouse_detect(void)
+{
+	return jailhouse_cpuid_base();
+}
+
+static void jailhouse_get_wallclock(struct timespec *now)
+{
+	memset(now, 0, sizeof(*now));
+}
+
+static void __init jailhouse_timer_init(void)
+{
+	lapic_timer_frequency = setup_data.apic_khz * (1000 / HZ);
+}
+
+static unsigned long jailhouse_get_tsc(void)
+{
+	return precalibrated_tsc_khz;
+}
+
+static void __init jailhouse_x2apic_init(void)
+{
+#ifdef CONFIG_X86_X2APIC
+	if (!x2apic_enabled())
+		return;
+	/*
+	 * We do not have access to IR inside Jailhouse non-root cells.  So
+	 * we have to run in physical mode.
+	 */
+	x2apic_phys = 1;
+	/*
+	 * This will trigger the switch to apic_x2apic_phys.  Empty OEM IDs
+	 * ensure that only this APIC driver picks up the call.
+	 */
+	default_acpi_madt_oem_check("", "");
+#endif
+}
+
+static void __init jailhouse_get_smp_config(unsigned int early)
+{
+	struct ioapic_domain_cfg ioapic_cfg = {
+		.type = IOAPIC_DOMAIN_STRICT,
+		.ops = &mp_ioapic_irqdomain_ops,
+	};
+	struct mpc_intsrc mp_irq = {
+		.type = MP_INTSRC,
+		.irqtype = mp_INT,
+		.irqflag = MP_IRQPOL_ACTIVE_HIGH | MP_IRQTRIG_EDGE,
+	};
+	unsigned int cpu;
+
+	jailhouse_x2apic_init();
+
+	register_lapic_address(0xfee00000);
+
+	for (cpu = 0; cpu < setup_data.num_cpus; cpu++) {
+		generic_processor_info(setup_data.cpu_ids[cpu],
+				       boot_cpu_apic_version);
+	}
+
+	smp_found_config = 1;
+
+	if (setup_data.standard_ioapic) {
+		mp_register_ioapic(0, 0xfec00000, gsi_top, &ioapic_cfg);
+
+		/* Register 1:1 mapping for legacy UART IRQs 3 and 4 */
+		mp_irq.srcbusirq = mp_irq.dstirq = 3;
+		mp_save_irq(&mp_irq);
+
+		mp_irq.srcbusirq = mp_irq.dstirq = 4;
+		mp_save_irq(&mp_irq);
+	}
+}
+
+static void jailhouse_no_restart(void)
+{
+	pr_notice("Jailhouse: Restart not supported, halting\n");
+	machine_halt();
+}
+
+static int __init jailhouse_pci_arch_init(void)
+{
+	pci_direct_init(1);
+
+	/*
+	 * There are no bridges on the virtual PCI root bus under Jailhouse,
+	 * thus no other way to discover all devices than a full scan.
+	 * Respect any overrides via the command line, though.
+	 */
+	if (pcibios_last_bus < 0)
+		pcibios_last_bus = 0xff;
+
+	return 0;
+}
+
+static void __init jailhouse_init_platform(void)
+{
+	u64 pa_data = boot_params.hdr.setup_data;
+	struct setup_data header;
+	void *mapping;
+
+	x86_init.irqs.pre_vector_init	= x86_init_noop;
+	x86_init.timers.timer_init	= jailhouse_timer_init;
+	x86_init.mpparse.get_smp_config	= jailhouse_get_smp_config;
+	x86_init.pci.arch_init		= jailhouse_pci_arch_init;
+
+	x86_platform.calibrate_cpu	= jailhouse_get_tsc;
+	x86_platform.calibrate_tsc	= jailhouse_get_tsc;
+	x86_platform.get_wallclock	= jailhouse_get_wallclock;
+	x86_platform.legacy.rtc		= 0;
+	x86_platform.legacy.warm_reset	= 0;
+	x86_platform.legacy.i8042	= X86_LEGACY_I8042_PLATFORM_ABSENT;
+
+	legacy_pic			= &null_legacy_pic;
+
+	machine_ops.emergency_restart	= jailhouse_no_restart;
+
+	while (pa_data) {
+		mapping = early_memremap(pa_data, sizeof(header));
+		memcpy(&header, mapping, sizeof(header));
+		early_memunmap(mapping, sizeof(header));
+
+		if (header.type == SETUP_JAILHOUSE &&
+		    header.len >= sizeof(setup_data)) {
+			pa_data += offsetof(struct setup_data, data);
+
+			mapping = early_memremap(pa_data, sizeof(setup_data));
+			memcpy(&setup_data, mapping, sizeof(setup_data));
+			early_memunmap(mapping, sizeof(setup_data));
+
+			break;
+		}
+
+		pa_data = header.next;
+	}
+
+	if (!pa_data)
+		panic("Jailhouse: No valid setup data found");
+
+	if (setup_data.compatible_version > JAILHOUSE_SETUP_REQUIRED_VERSION)
+		panic("Jailhouse: Unsupported setup data structure");
+
+	pmtmr_ioport = setup_data.pm_timer_address;
+	pr_debug("Jailhouse: PM-Timer IO Port: %#x\n", pmtmr_ioport);
+
+	precalibrated_tsc_khz = setup_data.tsc_khz;
+	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+
+	pci_probe = 0;
+
+	/*
+	 * Avoid that the kernel complains about missing ACPI tables - there
+	 * are none in a non-root cell.
+	 */
+	disable_acpi();
+}
+
+bool jailhouse_paravirt(void)
+{
+	return jailhouse_cpuid_base() != 0;
+}
+
+static bool jailhouse_x2apic_available(void)
+{
+	/*
+	 * The x2APIC is only available if the root cell enabled it. Jailhouse
+	 * does not support switching between xAPIC and x2APIC.
+	 */
+	return x2apic_enabled();
+}
+
+const struct hypervisor_x86 x86_hyper_jailhouse __refconst = {
+	.name			= "Jailhouse",
+	.detect			= jailhouse_detect,
+	.init.init_platform	= jailhouse_init_platform,
+	.init.x2apic_available	= jailhouse_x2apic_available,
+};
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index e941136e24d8..203d398802a3 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -40,6 +40,7 @@
 #include <asm/debugreg.h>
 #include <asm/set_memory.h>
 #include <asm/sections.h>
+#include <asm/nospec-branch.h>
 
 #include "common.h"
 
@@ -203,7 +204,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real)
 }
 
 /* Check whether insn is indirect jump */
-static int insn_is_indirect_jump(struct insn *insn)
+static int __insn_is_indirect_jump(struct insn *insn)
 {
 	return ((insn->opcode.bytes[0] == 0xff &&
 		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
@@ -237,6 +238,26 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
 	return (start <= target && target <= start + len);
 }
 
+static int insn_is_indirect_jump(struct insn *insn)
+{
+	int ret = __insn_is_indirect_jump(insn);
+
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * Jump to x86_indirect_thunk_* is treated as an indirect jump.
+	 * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with
+	 * older gcc may use indirect jump. So we add this check instead of
+	 * replace indirect-jump check.
+	 */
+	if (!ret)
+		ret = insn_jump_into_range(insn,
+				(unsigned long)__indirect_thunk_start,
+				(unsigned long)__indirect_thunk_end -
+				(unsigned long)__indirect_thunk_start);
+#endif
+	return ret;
+}
+
 /* Decode whole function to ensure any instructions don't jump into target */
 static int can_optimize(unsigned long paddr)
 {
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 1c1eae961340..26d713ecad34 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -5,6 +5,11 @@
  * Copyright (C) 2002 Andi Kleen
  *
  * This handles calls from both 32bit and 64bit mode.
+ *
+ * Lock order:
+ *	contex.ldt_usr_sem
+ *	  mmap_sem
+ *	    context.lock
  */
 
 #include <linux/errno.h>
@@ -19,6 +24,7 @@
 #include <linux/uaccess.h>
 
 #include <asm/ldt.h>
+#include <asm/tlb.h>
 #include <asm/desc.h>
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
@@ -42,17 +48,15 @@ static void refresh_ldt_segments(void)
 #endif
 }
 
-/* context.lock is held for us, so we don't need any locking. */
+/* context.lock is held by the task which issued the smp function call */
 static void flush_ldt(void *__mm)
 {
 	struct mm_struct *mm = __mm;
-	mm_context_t *pc;
 
 	if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm)
 		return;
 
-	pc = &mm->context;
-	set_ldt(pc->ldt->entries, pc->ldt->nr_entries);
+	load_mm_ldt(mm);
 
 	refresh_ldt_segments();
 }
@@ -89,25 +93,143 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 		return NULL;
 	}
 
+	/* The new LDT isn't aliased for PTI yet. */
+	new_ldt->slot = -1;
+
 	new_ldt->nr_entries = num_entries;
 	return new_ldt;
 }
 
+/*
+ * If PTI is enabled, this maps the LDT into the kernelmode and
+ * usermode tables for the given mm.
+ *
+ * There is no corresponding unmap function.  Even if the LDT is freed, we
+ * leave the PTEs around until the slot is reused or the mm is destroyed.
+ * This is harmless: the LDT is always in ordinary memory, and no one will
+ * access the freed slot.
+ *
+ * If we wanted to unmap freed LDTs, we'd also need to do a flush to make
+ * it useful, and the flush would slow down modify_ldt().
+ */
+static int
+map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	bool is_vmalloc, had_top_level_entry;
+	unsigned long va;
+	spinlock_t *ptl;
+	pgd_t *pgd;
+	int i;
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return 0;
+
+	/*
+	 * Any given ldt_struct should have map_ldt_struct() called at most
+	 * once.
+	 */
+	WARN_ON(ldt->slot != -1);
+
+	/*
+	 * Did we already have the top level entry allocated?  We can't
+	 * use pgd_none() for this because it doens't do anything on
+	 * 4-level page table kernels.
+	 */
+	pgd = pgd_offset(mm, LDT_BASE_ADDR);
+	had_top_level_entry = (pgd->pgd != 0);
+
+	is_vmalloc = is_vmalloc_addr(ldt->entries);
+
+	for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) {
+		unsigned long offset = i << PAGE_SHIFT;
+		const void *src = (char *)ldt->entries + offset;
+		unsigned long pfn;
+		pte_t pte, *ptep;
+
+		va = (unsigned long)ldt_slot_va(slot) + offset;
+		pfn = is_vmalloc ? vmalloc_to_pfn(src) :
+			page_to_pfn(virt_to_page(src));
+		/*
+		 * Treat the PTI LDT range as a *userspace* range.
+		 * get_locked_pte() will allocate all needed pagetables
+		 * and account for them in this mm.
+		 */
+		ptep = get_locked_pte(mm, va, &ptl);
+		if (!ptep)
+			return -ENOMEM;
+		/*
+		 * Map it RO so the easy to find address is not a primary
+		 * target via some kernel interface which misses a
+		 * permission check.
+		 */
+		pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL));
+		set_pte_at(mm, va, ptep, pte);
+		pte_unmap_unlock(ptep, ptl);
+	}
+
+	if (mm->context.ldt) {
+		/*
+		 * We already had an LDT.  The top-level entry should already
+		 * have been allocated and synchronized with the usermode
+		 * tables.
+		 */
+		WARN_ON(!had_top_level_entry);
+		if (static_cpu_has(X86_FEATURE_PTI))
+			WARN_ON(!kernel_to_user_pgdp(pgd)->pgd);
+	} else {
+		/*
+		 * This is the first time we're mapping an LDT for this process.
+		 * Sync the pgd to the usermode tables.
+		 */
+		WARN_ON(had_top_level_entry);
+		if (static_cpu_has(X86_FEATURE_PTI)) {
+			WARN_ON(kernel_to_user_pgdp(pgd)->pgd);
+			set_pgd(kernel_to_user_pgdp(pgd), *pgd);
+		}
+	}
+
+	va = (unsigned long)ldt_slot_va(slot);
+	flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
+
+	ldt->slot = slot;
+#endif
+	return 0;
+}
+
+static void free_ldt_pgtables(struct mm_struct *mm)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	struct mmu_gather tlb;
+	unsigned long start = LDT_BASE_ADDR;
+	unsigned long end = start + (1UL << PGDIR_SHIFT);
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	tlb_gather_mmu(&tlb, mm, start, end);
+	free_pgd_range(&tlb, start, end, start, end);
+	tlb_finish_mmu(&tlb, start, end);
+#endif
+}
+
 /* After calling this, the LDT is immutable. */
 static void finalize_ldt_struct(struct ldt_struct *ldt)
 {
 	paravirt_alloc_ldt(ldt->entries, ldt->nr_entries);
 }
 
-/* context.lock is held */
-static void install_ldt(struct mm_struct *current_mm,
-			struct ldt_struct *ldt)
+static void install_ldt(struct mm_struct *mm, struct ldt_struct *ldt)
 {
+	mutex_lock(&mm->context.lock);
+
 	/* Synchronizes with READ_ONCE in load_mm_ldt. */
-	smp_store_release(&current_mm->context.ldt, ldt);
+	smp_store_release(&mm->context.ldt, ldt);
 
-	/* Activate the LDT for all CPUs using current_mm. */
-	on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+	/* Activate the LDT for all CPUs using currents mm. */
+	on_each_cpu_mask(mm_cpumask(mm), flush_ldt, mm, true);
+
+	mutex_unlock(&mm->context.lock);
 }
 
 static void free_ldt_struct(struct ldt_struct *ldt)
@@ -124,27 +246,20 @@ static void free_ldt_struct(struct ldt_struct *ldt)
 }
 
 /*
- * we do not have to muck with descriptors here, that is
- * done in switch_mm() as needed.
+ * Called on fork from arch_dup_mmap(). Just copy the current LDT state,
+ * the new task is not running, so nothing can be installed.
  */
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
+int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm)
 {
 	struct ldt_struct *new_ldt;
-	struct mm_struct *old_mm;
 	int retval = 0;
 
-	mutex_init(&mm->context.lock);
-	old_mm = current->mm;
-	if (!old_mm) {
-		mm->context.ldt = NULL;
+	if (!old_mm)
 		return 0;
-	}
 
 	mutex_lock(&old_mm->context.lock);
-	if (!old_mm->context.ldt) {
-		mm->context.ldt = NULL;
+	if (!old_mm->context.ldt)
 		goto out_unlock;
-	}
 
 	new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries);
 	if (!new_ldt) {
@@ -156,6 +271,12 @@ int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
 	       new_ldt->nr_entries * LDT_ENTRY_SIZE);
 	finalize_ldt_struct(new_ldt);
 
+	retval = map_ldt_struct(mm, new_ldt, 0);
+	if (retval) {
+		free_ldt_pgtables(mm);
+		free_ldt_struct(new_ldt);
+		goto out_unlock;
+	}
 	mm->context.ldt = new_ldt;
 
 out_unlock:
@@ -174,13 +295,18 @@ void destroy_context_ldt(struct mm_struct *mm)
 	mm->context.ldt = NULL;
 }
 
+void ldt_arch_exit_mmap(struct mm_struct *mm)
+{
+	free_ldt_pgtables(mm);
+}
+
 static int read_ldt(void __user *ptr, unsigned long bytecount)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long entries_size;
 	int retval;
 
-	mutex_lock(&mm->context.lock);
+	down_read(&mm->context.ldt_usr_sem);
 
 	if (!mm->context.ldt) {
 		retval = 0;
@@ -209,7 +335,7 @@ static int read_ldt(void __user *ptr, unsigned long bytecount)
 	retval = bytecount;
 
 out_unlock:
-	mutex_unlock(&mm->context.lock);
+	up_read(&mm->context.ldt_usr_sem);
 	return retval;
 }
 
@@ -269,7 +395,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 			ldt.avl = 0;
 	}
 
-	mutex_lock(&mm->context.lock);
+	if (down_write_killable(&mm->context.ldt_usr_sem))
+		return -EINTR;
 
 	old_ldt       = mm->context.ldt;
 	old_nr_entries = old_ldt ? old_ldt->nr_entries : 0;
@@ -286,12 +413,31 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 	new_ldt->entries[ldt_info.entry_number] = ldt;
 	finalize_ldt_struct(new_ldt);
 
+	/*
+	 * If we are using PTI, map the new LDT into the userspace pagetables.
+	 * If there is already an LDT, use the other slot so that other CPUs
+	 * will continue to use the old LDT until install_ldt() switches
+	 * them over to the new LDT.
+	 */
+	error = map_ldt_struct(mm, new_ldt, old_ldt ? !old_ldt->slot : 0);
+	if (error) {
+		/*
+		 * This only can fail for the first LDT setup. If an LDT is
+		 * already installed then the PTE page is already
+		 * populated. Mop up a half populated page table.
+		 */
+		if (!WARN_ON_ONCE(old_ldt))
+			free_ldt_pgtables(mm);
+		free_ldt_struct(new_ldt);
+		goto out_unlock;
+	}
+
 	install_ldt(mm, new_ldt);
 	free_ldt_struct(old_ldt);
 	error = 0;
 
 out_unlock:
-	mutex_unlock(&mm->context.lock);
+	up_write(&mm->context.ldt_usr_sem);
 out:
 	return error;
 }
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 00bc751c861c..edfede768688 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -48,8 +48,6 @@ static void load_segments(void)
 		"\tmovl $"STR(__KERNEL_DS)",%%eax\n"
 		"\tmovl %%eax,%%ds\n"
 		"\tmovl %%eax,%%es\n"
-		"\tmovl %%eax,%%fs\n"
-		"\tmovl %%eax,%%gs\n"
 		"\tmovl %%eax,%%ss\n"
 		: : : "eax", "memory");
 #undef STR
@@ -232,8 +230,8 @@ void machine_kexec(struct kimage *image)
 	 * The gdt & idt are now invalid.
 	 * If you want to load them you must set up your own idt & gdt.
 	 */
-	set_gdt(phys_to_virt(0), 0);
 	idt_invalidate(phys_to_virt(0));
+	set_gdt(phys_to_virt(0), 0);
 
 	/* now call it */
 	image->start = relocate_kernel_ptr((unsigned long)image->head,
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 3a4b12809ab5..27d0a1712663 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -281,7 +281,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
 	int ELCR_fallback = 0;
 
 	intsrc.type = MP_INTSRC;
-	intsrc.irqflag = 0;	/* conforming */
+	intsrc.irqflag = MP_IRQTRIG_DEFAULT | MP_IRQPOL_DEFAULT;
 	intsrc.srcbus = 0;
 	intsrc.dstapic = mpc_ioapic_id(0);
 
@@ -324,10 +324,13 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
 			 *  copy that information over to the MP table in the
 			 *  irqflag field (level sensitive, active high polarity).
 			 */
-			if (ELCR_trigger(i))
-				intsrc.irqflag = 13;
-			else
-				intsrc.irqflag = 0;
+			if (ELCR_trigger(i)) {
+				intsrc.irqflag = MP_IRQTRIG_LEVEL |
+						 MP_IRQPOL_ACTIVE_HIGH;
+			} else {
+				intsrc.irqflag = MP_IRQTRIG_DEFAULT |
+						 MP_IRQPOL_DEFAULT;
+			}
 		}
 
 		intsrc.srcbusirq = i;
@@ -419,7 +422,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
 	construct_ioapic_table(mpc_default_type);
 
 	lintsrc.type = MP_LINTSRC;
-	lintsrc.irqflag = 0;		/* conforming */
+	lintsrc.irqflag = MP_IRQTRIG_DEFAULT | MP_IRQPOL_DEFAULT;
 	lintsrc.srcbusid = 0;
 	lintsrc.srcbusirq = 0;
 	lintsrc.destapic = MP_APIC_ALL;
@@ -664,7 +667,7 @@ static int  __init get_MP_intsrc_index(struct mpc_intsrc *m)
 	if (m->irqtype != mp_INT)
 		return 0;
 
-	if (m->irqflag != 0x0f)
+	if (m->irqflag != (MP_IRQTRIG_LEVEL | MP_IRQPOL_ACTIVE_LOW))
 		return 0;
 
 	/* not legacy */
@@ -673,7 +676,8 @@ static int  __init get_MP_intsrc_index(struct mpc_intsrc *m)
 		if (mp_irqs[i].irqtype != mp_INT)
 			continue;
 
-		if (mp_irqs[i].irqflag != 0x0f)
+		if (mp_irqs[i].irqflag != (MP_IRQTRIG_LEVEL |
+					   MP_IRQPOL_ACTIVE_LOW))
 			continue;
 
 		if (mp_irqs[i].srcbus != m->srcbus)
@@ -784,7 +788,8 @@ static int  __init replace_intsrc_all(struct mpc_table *mpc,
 		if (mp_irqs[i].irqtype != mp_INT)
 			continue;
 
-		if (mp_irqs[i].irqflag != 0x0f)
+		if (mp_irqs[i].irqflag != (MP_IRQTRIG_LEVEL |
+					   MP_IRQPOL_ACTIVE_LOW))
 			continue;
 
 		if (nr_m_spare > 0) {
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index ac0be8283325..9edadabf04f6 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -10,7 +10,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
-DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)");
 DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
 
 DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq");
@@ -60,7 +59,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, read_cr2);
 		PATCH_SITE(pv_mmu_ops, read_cr3);
 		PATCH_SITE(pv_mmu_ops, write_cr3);
-		PATCH_SITE(pv_mmu_ops, flush_tlb_single);
 		PATCH_SITE(pv_cpu_ops, wbinvd);
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
 		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 599d7462eccc..df7ab02f959f 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-debug.h>
 #include <linux/dmar.h>
 #include <linux/export.h>
@@ -87,7 +87,6 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 
 	dma_mask = dma_alloc_coherent_mask(dev, flag);
 
-	flag &= ~__GFP_ZERO;
 again:
 	page = NULL;
 	/* CMA can be used only in the context which permits sleeping */
@@ -139,7 +138,6 @@ bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp)
 	if (!*dev)
 		*dev = &x86_dma_fallback_dev;
 
-	*gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
 	*gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp);
 
 	if (!is_device_dma_capable(*dev))
@@ -217,7 +215,7 @@ static __init int iommu_setup(char *p)
 }
 early_param("iommu", iommu_setup);
 
-int x86_dma_supported(struct device *dev, u64 mask)
+int arch_dma_supported(struct device *dev, u64 mask)
 {
 #ifdef CONFIG_PCI
 	if (mask > 0xffffffff && forbid_dac > 0) {
@@ -226,12 +224,6 @@ int x86_dma_supported(struct device *dev, u64 mask)
 	}
 #endif
 
-	/* Copied from i386. Doesn't make much sense, because it will
-	   only work for pci_alloc_coherent.
-	   The caller just has to use GFP_DMA in this case. */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
 	/* Tell the device to use SAC when IOMMU force is on.  This
 	   allows the driver to use cheaper accesses in some cases.
 
@@ -251,6 +243,17 @@ int x86_dma_supported(struct device *dev, u64 mask)
 
 	return 1;
 }
+EXPORT_SYMBOL(arch_dma_supported);
+
+int x86_dma_supported(struct device *dev, u64 mask)
+{
+	/* Copied from i386. Doesn't make much sense, because it will
+	   only work for pci_alloc_coherent.
+	   The caller just has to use GFP_DMA in this case. */
+	if (mask < DMA_BIT_MASK(24))
+		return 0;
+	return 1;
+}
 
 static int __init pci_iommu_init(void)
 {
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index b0caae27e1b7..618285e475c6 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Fallback functions when the main IOMMU code is not compiled in. This
    code is roughly equivalent to i386. */
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/scatterlist.h>
 #include <linux/string.h>
 #include <linux/gfp.h>
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 53bd05ea90d8..0ee0f8f34251 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -6,7 +6,7 @@
 #include <linux/init.h>
 #include <linux/swiotlb.h>
 #include <linux/bootmem.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/mem_encrypt.h>
 
 #include <asm/iommu.h>
@@ -48,7 +48,7 @@ void x86_swiotlb_free_coherent(struct device *dev, size_t size,
 		dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs);
 }
 
-static const struct dma_map_ops swiotlb_dma_ops = {
+static const struct dma_map_ops x86_swiotlb_dma_ops = {
 	.mapping_error = swiotlb_dma_mapping_error,
 	.alloc = x86_swiotlb_alloc_coherent,
 	.free = x86_swiotlb_free_coherent,
@@ -112,7 +112,7 @@ void __init pci_swiotlb_init(void)
 {
 	if (swiotlb) {
 		swiotlb_init(0);
-		dma_ops = &swiotlb_dma_ops;
+		dma_ops = &x86_swiotlb_dma_ops;
 	}
 }
 
@@ -120,7 +120,7 @@ void __init pci_swiotlb_late_init(void)
 {
 	/* An IOMMU turned us off. */
 	if (!swiotlb)
-		swiotlb_free();
+		swiotlb_exit();
 	else {
 		printk(KERN_INFO "PCI-DMA: "
 		       "Using software bounce buffering for IO (SWIOTLB)\n");
diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c
index 39a59299bfa0..235fe6008ac8 100644
--- a/arch/x86/kernel/platform-quirks.c
+++ b/arch/x86/kernel/platform-quirks.c
@@ -9,6 +9,7 @@ void __init x86_early_init_platform_quirks(void)
 {
 	x86_platform.legacy.i8042 = X86_LEGACY_I8042_EXPECTED_PRESENT;
 	x86_platform.legacy.rtc = 1;
+	x86_platform.legacy.warm_reset = 1;
 	x86_platform.legacy.reserve_bios_regions = 0;
 	x86_platform.legacy.devices.pnpbios = 1;
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 97fb3e5737f5..03408b942adb 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -21,7 +21,6 @@
 #include <linux/dmi.h>
 #include <linux/utsname.h>
 #include <linux/stackprotector.h>
-#include <linux/tick.h>
 #include <linux/cpuidle.h>
 #include <trace/events/power.h>
 #include <linux/hw_breakpoint.h>
@@ -47,7 +46,7 @@
  * section. Since TSS's are completely CPU-local, we want them
  * on exact cacheline boundaries, to eliminate cacheline ping-pong.
  */
-__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
+__visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = {
 	.x86_tss = {
 		/*
 		 * .sp0 is only used when entering ring 0 from a lower
@@ -56,6 +55,16 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 		 * Poison it.
 		 */
 		.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,
+
+#ifdef CONFIG_X86_64
+		/*
+		 * .sp1 is cpu_current_top_of_stack.  The init task never
+		 * runs user code, but cpu_current_top_of_stack should still
+		 * be well defined before the first context switch.
+		 */
+		.sp1 = TOP_OF_INIT_STACK,
+#endif
+
 #ifdef CONFIG_X86_32
 		.ss0 = __KERNEL_DS,
 		.ss1 = __KERNEL_CS,
@@ -71,11 +80,8 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 	  */
 	.io_bitmap		= { [0 ... IO_BITMAP_LONGS] = ~0 },
 #endif
-#ifdef CONFIG_X86_32
-	.SYSENTER_stack_canary	= STACK_END_MAGIC,
-#endif
 };
-EXPORT_PER_CPU_SYMBOL(cpu_tss);
+EXPORT_PER_CPU_SYMBOL(cpu_tss_rw);
 
 DEFINE_PER_CPU(bool, __tss_limit_invalid);
 EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
@@ -104,7 +110,7 @@ void exit_thread(struct task_struct *tsk)
 	struct fpu *fpu = &t->fpu;
 
 	if (bp) {
-		struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu());
+		struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu());
 
 		t->io_bitmap_ptr = NULL;
 		clear_thread_flag(TIF_IO_BITMAP);
@@ -299,7 +305,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 	}
 
 	if ((tifp ^ tifn) & _TIF_NOTSC)
-		cr4_toggle_bits(X86_CR4_TSD);
+		cr4_toggle_bits_irqsoff(X86_CR4_TSD);
 
 	if ((tifp ^ tifn) & _TIF_NOCPUID)
 		set_cpuid_faulting(!!(tifn & _TIF_NOCPUID));
@@ -373,19 +379,24 @@ void stop_this_cpu(void *dummy)
 	disable_local_APIC();
 	mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
 
+	/*
+	 * Use wbinvd on processors that support SME. This provides support
+	 * for performing a successful kexec when going from SME inactive
+	 * to SME active (or vice-versa). The cache must be cleared so that
+	 * if there are entries with the same physical address, both with and
+	 * without the encryption bit, they don't race each other when flushed
+	 * and potentially end up with the wrong entry being committed to
+	 * memory.
+	 */
+	if (boot_cpu_has(X86_FEATURE_SME))
+		native_wbinvd();
 	for (;;) {
 		/*
-		 * Use wbinvd followed by hlt to stop the processor. This
-		 * provides support for kexec on a processor that supports
-		 * SME. With kexec, going from SME inactive to SME active
-		 * requires clearing cache entries so that addresses without
-		 * the encryption bit set don't corrupt the same physical
-		 * address that has the encryption bit set when caches are
-		 * flushed. To achieve this a wbinvd is performed followed by
-		 * a hlt. Even if the processor is not in the kexec/SME
-		 * scenario this only adds a wbinvd to a halting processor.
+		 * Use native_halt() so that memory contents don't change
+		 * (stack usage and variables) after possibly issuing the
+		 * native_wbinvd() above.
 		 */
-		asm volatile("wbinvd; hlt" : : : "memory");
+		native_halt();
 	}
 }
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 45bf0c5f93e1..5224c6099184 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -234,7 +234,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	struct fpu *prev_fpu = &prev->fpu;
 	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
-	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
+	struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu);
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index eeeb34f85c25..c75466232016 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -69,9 +69,8 @@ void __show_regs(struct pt_regs *regs, int all)
 	unsigned int fsindex, gsindex;
 	unsigned int ds, cs, es;
 
-	printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip);
-	printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss,
-		regs->sp, regs->flags);
+	show_iret_regs(regs);
+
 	if (regs->orig_ax != -1)
 		pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax);
 	else
@@ -88,6 +87,9 @@ void __show_regs(struct pt_regs *regs, int all)
 	printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
 	       regs->r13, regs->r14, regs->r15);
 
+	if (!all)
+		return;
+
 	asm("movl %%ds,%0" : "=r" (ds));
 	asm("movl %%cs,%0" : "=r" (cs));
 	asm("movl %%es,%0" : "=r" (es));
@@ -98,9 +100,6 @@ void __show_regs(struct pt_regs *regs, int all)
 	rdmsrl(MSR_GS_BASE, gs);
 	rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
 
-	if (!all)
-		return;
-
 	cr0 = read_cr0();
 	cr2 = read_cr2();
 	cr3 = __read_cr3();
@@ -400,7 +399,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	struct fpu *prev_fpu = &prev->fpu;
 	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
-	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
+	struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu);
 
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
 		     this_cpu_read(irq_count) != -1);
@@ -462,6 +461,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * Switch the PDA and FPU contexts.
 	 */
 	this_cpu_write(current_task, next_p);
+	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
 	/* Reload sp0. */
 	update_sp0(next_p);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 8af2e8d0c0a1..1ae67e982af7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -114,7 +114,6 @@
 #include <asm/alternative.h>
 #include <asm/prom.h>
 #include <asm/microcode.h>
-#include <asm/mmu_context.h>
 #include <asm/kaslr.h>
 #include <asm/unwind.h>
 
@@ -364,16 +363,6 @@ static void __init reserve_initrd(void)
 	    !ramdisk_image || !ramdisk_size)
 		return;		/* No initrd provided by bootloader */
 
-	/*
-	 * If SME is active, this memory will be marked encrypted by the
-	 * kernel when it is accessed (including relocation). However, the
-	 * ramdisk image was loaded decrypted by the bootloader, so make
-	 * sure that it is encrypted before accessing it. For SEV the
-	 * ramdisk will already be encrypted, so only do this for SME.
-	 */
-	if (sme_active())
-		sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image);
-
 	initrd_start = 0;
 
 	mapped_size = memblock_mem_size(max_pfn_mapped);
@@ -906,9 +895,6 @@ void __init setup_arch(char **cmdline_p)
 		set_bit(EFI_BOOT, &efi.flags);
 		set_bit(EFI_64BIT, &efi.flags);
 	}
-
-	if (efi_enabled(EFI_BOOT))
-		efi_memblock_x86_reserve_range();
 #endif
 
 	x86_init.oem.arch_setup();
@@ -962,6 +948,8 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
+	if (efi_enabled(EFI_BOOT))
+		efi_memblock_x86_reserve_range();
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/*
 	 * Memory used by the kernel cannot be hot-removed because Linux
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index 8c6da1a643da..ac057f9b0763 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -25,8 +25,8 @@ static inline void signal_compat_build_tests(void)
 	 * limits also have to look at this code.  Make sure any
 	 * new fields are handled in copy_siginfo_to_user32()!
 	 */
-	BUILD_BUG_ON(NSIGILL  != 8);
-	BUILD_BUG_ON(NSIGFPE  != 8);
+	BUILD_BUG_ON(NSIGILL  != 11);
+	BUILD_BUG_ON(NSIGFPE  != 13);
 	BUILD_BUG_ON(NSIGSEGV != 4);
 	BUILD_BUG_ON(NSIGBUS  != 5);
 	BUILD_BUG_ON(NSIGTRAP != 4);
@@ -64,7 +64,7 @@ static inline void signal_compat_build_tests(void)
 	CHECK_SI_SIZE   (_kill, 2*sizeof(int));
 
 	CHECK_CSI_OFFSET(_timer);
-	CHECK_CSI_SIZE  (_timer, 5*sizeof(int));
+	CHECK_CSI_SIZE  (_timer, 3*sizeof(int));
 	CHECK_SI_SIZE   (_timer, 6*sizeof(int));
 
 	CHECK_CSI_OFFSET(_rt);
@@ -75,9 +75,11 @@ static inline void signal_compat_build_tests(void)
 	CHECK_CSI_SIZE  (_sigchld, 5*sizeof(int));
 	CHECK_SI_SIZE   (_sigchld, 8*sizeof(int));
 
+#ifdef CONFIG_X86_X32_ABI
 	CHECK_CSI_OFFSET(_sigchld_x32);
 	CHECK_CSI_SIZE  (_sigchld_x32, 7*sizeof(int));
 	/* no _sigchld_x32 in the generic siginfo_t */
+#endif
 
 	CHECK_CSI_OFFSET(_sigfault);
 	CHECK_CSI_SIZE  (_sigfault, 4*sizeof(int));
@@ -96,6 +98,8 @@ static inline void signal_compat_build_tests(void)
 
 void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact)
 {
+	signal_compat_build_tests();
+
 	/* Don't leak in-kernel non-uapi flags to user-space */
 	if (oact)
 		oact->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI);
@@ -111,116 +115,3 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact)
 	if (in_x32_syscall())
 		act->sa.sa_flags |= SA_X32_ABI;
 }
-
-int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from,
-		bool x32_ABI)
-{
-	int err = 0;
-
-	signal_compat_build_tests();
-
-	if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
-		return -EFAULT;
-
-	put_user_try {
-		/* If you change siginfo_t structure, please make sure that
-		   this code is fixed accordingly.
-		   It should never copy any pad contained in the structure
-		   to avoid security leaks, but must copy the generic
-		   3 ints plus the relevant union member.  */
-		put_user_ex(from->si_signo, &to->si_signo);
-		put_user_ex(from->si_errno, &to->si_errno);
-		put_user_ex(from->si_code, &to->si_code);
-
-		if (from->si_code < 0) {
-			put_user_ex(from->si_pid, &to->si_pid);
-			put_user_ex(from->si_uid, &to->si_uid);
-			put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr);
-		} else {
-			/*
-			 * First 32bits of unions are always present:
-			 * si_pid === si_band === si_tid === si_addr(LS half)
-			 */
-			put_user_ex(from->_sifields._pad[0],
-					  &to->_sifields._pad[0]);
-			switch (siginfo_layout(from->si_signo, from->si_code)) {
-			case SIL_FAULT:
-				if (from->si_signo == SIGBUS &&
-				    (from->si_code == BUS_MCEERR_AR ||
-				     from->si_code == BUS_MCEERR_AO))
-					put_user_ex(from->si_addr_lsb, &to->si_addr_lsb);
-
-				if (from->si_signo == SIGSEGV) {
-					if (from->si_code == SEGV_BNDERR) {
-						compat_uptr_t lower = (unsigned long)from->si_lower;
-						compat_uptr_t upper = (unsigned long)from->si_upper;
-						put_user_ex(lower, &to->si_lower);
-						put_user_ex(upper, &to->si_upper);
-					}
-					if (from->si_code == SEGV_PKUERR)
-						put_user_ex(from->si_pkey, &to->si_pkey);
-				}
-				break;
-			case SIL_SYS:
-				put_user_ex(from->si_syscall, &to->si_syscall);
-				put_user_ex(from->si_arch, &to->si_arch);
-				break;
-			case SIL_CHLD:
-				if (!x32_ABI) {
-					put_user_ex(from->si_utime, &to->si_utime);
-					put_user_ex(from->si_stime, &to->si_stime);
-				} else {
-					put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime);
-					put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime);
-				}
-				put_user_ex(from->si_status, &to->si_status);
-				/* FALL THROUGH */
-			case SIL_KILL:
-				put_user_ex(from->si_uid, &to->si_uid);
-				break;
-			case SIL_POLL:
-				put_user_ex(from->si_fd, &to->si_fd);
-				break;
-			case SIL_TIMER:
-				put_user_ex(from->si_overrun, &to->si_overrun);
-				put_user_ex(ptr_to_compat(from->si_ptr),
-					    &to->si_ptr);
-				break;
-			case SIL_RT:
-				put_user_ex(from->si_uid, &to->si_uid);
-				put_user_ex(from->si_int, &to->si_int);
-				break;
-			}
-		}
-	} put_user_catch(err);
-
-	return err;
-}
-
-/* from syscall's path, where we know the ABI */
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
-{
-	return __copy_siginfo_to_user32(to, from, in_x32_syscall());
-}
-
-int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
-{
-	int err = 0;
-	u32 ptr32;
-
-	if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t)))
-		return -EFAULT;
-
-	get_user_try {
-		get_user_ex(to->si_signo, &from->si_signo);
-		get_user_ex(to->si_errno, &from->si_errno);
-		get_user_ex(to->si_code, &from->si_code);
-
-		get_user_ex(to->si_pid, &from->si_pid);
-		get_user_ex(to->si_uid, &from->si_uid);
-		get_user_ex(ptr32, &from->si_ptr);
-		to->si_ptr = compat_ptr(ptr32);
-	} get_user_catch(err);
-
-	return err;
-}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3d01df7d7cf6..6f27facbaa9b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -75,7 +75,6 @@
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
 #include <asm/i8259.h>
-#include <asm/realmode.h>
 #include <asm/misc.h>
 #include <asm/qspinlock.h>
 
@@ -106,7 +105,7 @@ EXPORT_SYMBOL(__max_logical_packages);
 static unsigned int logical_packages __read_mostly;
 
 /* Maximum number of SMT threads on any online core */
-int __max_smt_threads __read_mostly;
+int __read_mostly __max_smt_threads = 1;
 
 /* Flag to indicate if a complete sched domain rebuild is required */
 bool x86_topology_update;
@@ -126,14 +125,10 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 	spin_lock_irqsave(&rtc_lock, flags);
 	CMOS_WRITE(0xa, 0xf);
 	spin_unlock_irqrestore(&rtc_lock, flags);
-	local_flush_tlb();
-	pr_debug("1.\n");
 	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
 							start_eip >> 4;
-	pr_debug("2.\n");
 	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
 							start_eip & 0xf;
-	pr_debug("3.\n");
 }
 
 static inline void smpboot_restore_warm_reset_vector(void)
@@ -141,11 +136,6 @@ static inline void smpboot_restore_warm_reset_vector(void)
 	unsigned long flags;
 
 	/*
-	 * Install writable page 0 entry to set BIOS data area.
-	 */
-	local_flush_tlb();
-
-	/*
 	 * Paranoid:  Set warm reset code and vector here back
 	 * to default values.
 	 */
@@ -237,7 +227,7 @@ static void notrace start_secondary(void *unused)
 	load_cr3(swapper_pg_dir);
 	__flush_tlb_all();
 #endif
-
+	load_current_idt();
 	cpu_init();
 	x86_cpuinit.early_percpu_clock_init();
 	preempt_disable();
@@ -932,12 +922,8 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
 	initial_code = (unsigned long)start_secondary;
 	initial_stack  = idle->thread.sp;
 
-	/*
-	 * Enable the espfix hack for this CPU
-	*/
-#ifdef CONFIG_X86_ESPFIX64
+	/* Enable the espfix hack for this CPU */
 	init_espfix_ap(cpu);
-#endif
 
 	/* So we see what's up */
 	announce_cpu(cpu, apicid);
@@ -947,7 +933,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
 	 * the targeted processor.
 	 */
 
-	if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+	if (x86_platform.legacy.warm_reset) {
 
 		pr_debug("Setting warm reset code and vector.\n");
 
@@ -1019,7 +1005,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
 	/* mark "stuck" area as not stuck */
 	*trampoline_status = 0;
 
-	if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+	if (x86_platform.legacy.warm_reset) {
 		/*
 		 * Cleanup possible dangling ends...
 		 */
@@ -1304,7 +1290,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 	 * Today neither Intel nor AMD support heterogenous systems so
 	 * extrapolate the boot cpu's data to all packages.
 	 */
-	ncpus = cpu_data(0).booted_cores * smp_num_siblings;
+	ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
 	__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
 	pr_info("Max logical packages: %u\n", __max_logical_packages);
 
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 77835bc021c7..093f2ea5dd56 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -102,7 +102,7 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 	for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
 	     unwind_next_frame(&state)) {
 
-		regs = unwind_get_entry_regs(&state);
+		regs = unwind_get_entry_regs(&state, NULL);
 		if (regs) {
 			/*
 			 * Kernel mode registers on the stack indicate an
@@ -164,8 +164,12 @@ int save_stack_trace_tsk_reliable(struct task_struct *tsk,
 {
 	int ret;
 
+	/*
+	 * If the task doesn't have a stack (e.g., a zombie), the stack is
+	 * "reliably" empty.
+	 */
 	if (!try_get_task_stack(tsk))
-		return -EINVAL;
+		return 0;
 
 	ret = __save_stack_trace_reliable(trace, tsk);
 
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index a4eb27918ceb..a2486f444073 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -138,6 +138,17 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn,
 		return -1;
 	set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot));
 	pte_unmap(pte);
+
+	/*
+	 * PTI poisons low addresses in the kernel page tables in the
+	 * name of making them unusable for userspace.  To execute
+	 * code at such a low address, the poison must be cleared.
+	 *
+	 * Note: 'pgd' actually gets set in p4d_alloc() _or_
+	 * pud_alloc() depending on 4/5-level paging.
+	 */
+	pgd->pgd &= ~_PAGE_NX;
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 749d189f8cd4..774ebafa97c4 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -69,9 +69,12 @@ static struct irqaction irq0  = {
 
 static void __init setup_default_timer_irq(void)
 {
-	if (!nr_legacy_irqs())
-		return;
-	setup_irq(0, &irq0);
+	/*
+	 * Unconditionally register the legacy timer; even without legacy
+	 * PIC/PIT we need this for the HPET0 in legacy replacement mode.
+	 */
+	if (setup_irq(0, &irq0))
+		pr_info("Failed to register legacy timer interrupt\n");
 }
 
 /* Default timer init function */
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 9a9c9b076955..a5b802a12212 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -93,17 +93,10 @@ static void set_tls_desc(struct task_struct *p, int idx,
 	cpu = get_cpu();
 
 	while (n-- > 0) {
-		if (LDT_empty(info) || LDT_zero(info)) {
+		if (LDT_empty(info) || LDT_zero(info))
 			memset(desc, 0, sizeof(*desc));
-		} else {
+		else
 			fill_ldt(desc, info);
-
-			/*
-			 * Always set the accessed bit so that the CPU
-			 * doesn't try to write to the (read-only) GDT.
-			 */
-			desc->type |= 1;
-		}
 		++info;
 		++desc;
 	}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 989514c94a55..446c9ef8cfc3 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -51,6 +51,7 @@
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/fpu/internal.h>
+#include <asm/cpu_entry_area.h>
 #include <asm/mce.h>
 #include <asm/fixmap.h>
 #include <asm/mach_traps.h>
@@ -348,23 +349,42 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 
 	/*
 	 * If IRET takes a non-IST fault on the espfix64 stack, then we
-	 * end up promoting it to a doublefault.  In that case, modify
-	 * the stack to make it look like we just entered the #GP
-	 * handler from user space, similar to bad_iret.
+	 * end up promoting it to a doublefault.  In that case, take
+	 * advantage of the fact that we're not using the normal (TSS.sp0)
+	 * stack right now.  We can write a fake #GP(0) frame at TSS.sp0
+	 * and then modify our own IRET frame so that, when we return,
+	 * we land directly at the #GP(0) vector with the stack already
+	 * set up according to its expectations.
+	 *
+	 * The net result is that our #GP handler will think that we
+	 * entered from usermode with the bad user context.
 	 *
 	 * No need for ist_enter here because we don't use RCU.
 	 */
-	if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+	if (((long)regs->sp >> P4D_SHIFT) == ESPFIX_PGD_ENTRY &&
 		regs->cs == __KERNEL_CS &&
 		regs->ip == (unsigned long)native_irq_return_iret)
 	{
-		struct pt_regs *normal_regs = task_pt_regs(current);
+		struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
 
-		/* Fake a #GP(0) from userspace. */
-		memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
-		normal_regs->orig_ax = 0;  /* Missing (lost) #GP error code */
+		/*
+		 * regs->sp points to the failing IRET frame on the
+		 * ESPFIX64 stack.  Copy it to the entry stack.  This fills
+		 * in gpregs->ss through gpregs->ip.
+		 *
+		 */
+		memmove(&gpregs->ip, (void *)regs->sp, 5*8);
+		gpregs->orig_ax = 0;  /* Missing (lost) #GP error code */
+
+		/*
+		 * Adjust our frame so that we return straight to the #GP
+		 * vector with the expected RSP value.  This is safe because
+		 * we won't enable interupts or schedule before we invoke
+		 * general_protection, so nothing will clobber the stack
+		 * frame we just set up.
+		 */
 		regs->ip = (unsigned long)general_protection;
-		regs->sp = (unsigned long)&normal_regs->orig_ax;
+		regs->sp = (unsigned long)&gpregs->orig_ax;
 
 		return;
 	}
@@ -389,7 +409,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 	 *
 	 *   Processors update CR2 whenever a page fault is detected. If a
 	 *   second page fault occurs while an earlier page fault is being
-	 *   deliv- ered, the faulting linear address of the second fault will
+	 *   delivered, the faulting linear address of the second fault will
 	 *   overwrite the contents of CR2 (replacing the previous
 	 *   address). These updates to CR2 occur even if the page fault
 	 *   results in a double fault or occurs during the delivery of a
@@ -605,14 +625,15 @@ NOKPROBE_SYMBOL(do_int3);
 
 #ifdef CONFIG_X86_64
 /*
- * Help handler running on IST stack to switch off the IST stack if the
- * interrupted code was in user mode. The actual stack switch is done in
- * entry_64.S
+ * Help handler running on a per-cpu (IST or entry trampoline) stack
+ * to switch to the normal thread stack if the interrupted code was in
+ * user mode. The actual stack switch is done in entry_64.S
  */
 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs)
 {
-	struct pt_regs *regs = task_pt_regs(current);
-	*regs = *eregs;
+	struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1;
+	if (regs != eregs)
+		*regs = *eregs;
 	return regs;
 }
 NOKPROBE_SYMBOL(sync_regs);
@@ -628,13 +649,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 	/*
 	 * This is called from entry_64.S early in handling a fault
 	 * caused by a bad iret to user mode.  To handle the fault
-	 * correctly, we want move our stack frame to task_pt_regs
-	 * and we want to pretend that the exception came from the
-	 * iret target.
+	 * correctly, we want to move our stack frame to where it would
+	 * be had we entered directly on the entry stack (rather than
+	 * just below the IRET frame) and we want to pretend that the
+	 * exception came from the IRET target.
 	 */
 	struct bad_iret_stack *new_stack =
-		container_of(task_pt_regs(current),
-			     struct bad_iret_stack, regs);
+		(struct bad_iret_stack *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
 
 	/* Copy the IRET target to the new stack. */
 	memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
@@ -795,14 +816,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	debug_stack_usage_dec();
 
 exit:
-#if defined(CONFIG_X86_32)
-	/*
-	 * This is the most likely code path that involves non-trivial use
-	 * of the SYSENTER stack.  Check that we haven't overrun it.
-	 */
-	WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC,
-	     "Overran or corrupted SYSENTER stack\n");
-#endif
 	ist_exit(regs);
 }
 NOKPROBE_SYMBOL(do_debug);
@@ -929,6 +942,9 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 
 void __init trap_init(void)
 {
+	/* Init cpu_entry_area before IST entries are set up */
+	setup_cpu_entry_areas();
+
 	idt_setup_traps();
 
 	/*
@@ -936,8 +952,9 @@ void __init trap_init(void)
 	 * "sidt" instruction will not leak the location of the kernel, and
 	 * to defend the IDT against arbitrary memory write vulnerabilities.
 	 * It will be reloaded in cpu_init() */
-	__set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO);
-	idt_descr.address = fix_to_virt(FIX_RO_IDT);
+	cea_set_pte(CPU_ENTRY_AREA_RO_IDT_VADDR, __pa_symbol(idt_table),
+		    PAGE_KERNEL_RO);
+	idt_descr.address = CPU_ENTRY_AREA_RO_IDT;
 
 	/*
 	 * Should be a barrier for any external CPU state:
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 8ea117f8142e..fb4302738410 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -25,6 +25,7 @@
 #include <asm/geode.h>
 #include <asm/apic.h>
 #include <asm/intel-family.h>
+#include <asm/i8259.h>
 
 unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -363,6 +364,20 @@ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin)
 	unsigned long tscmin, tscmax;
 	int pitcnt;
 
+	if (!has_legacy_pic()) {
+		/*
+		 * Relies on tsc_early_delay_calibrate() to have given us semi
+		 * usable udelay(), wait for the same 50ms we would have with
+		 * the PIT loop below.
+		 */
+		udelay(10 * USEC_PER_MSEC);
+		udelay(10 * USEC_PER_MSEC);
+		udelay(10 * USEC_PER_MSEC);
+		udelay(10 * USEC_PER_MSEC);
+		udelay(10 * USEC_PER_MSEC);
+		return ULONG_MAX;
+	}
+
 	/* Set the Gate high, disable speaker */
 	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
 
@@ -487,6 +502,9 @@ static unsigned long quick_pit_calibrate(void)
 	u64 tsc, delta;
 	unsigned long d1, d2;
 
+	if (!has_legacy_pic())
+		return 0;
+
 	/* Set the Gate high, disable speaker */
 	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
 
@@ -602,7 +620,6 @@ unsigned long native_calibrate_tsc(void)
 		case INTEL_FAM6_KABYLAKE_DESKTOP:
 			crystal_khz = 24000;	/* 24.0 MHz */
 			break;
-		case INTEL_FAM6_SKYLAKE_X:
 		case INTEL_FAM6_ATOM_DENVERTON:
 			crystal_khz = 25000;	/* 25.0 MHz */
 			break;
@@ -612,6 +629,8 @@ unsigned long native_calibrate_tsc(void)
 		}
 	}
 
+	if (crystal_khz == 0)
+		return 0;
 	/*
 	 * TSC frequency determined by CPUID is a "hardware reported"
 	 * frequency and is the most accurate one so far we have. This
@@ -987,8 +1006,6 @@ static void __init detect_art(void)
 
 /* clocksource code */
 
-static struct clocksource clocksource_tsc;
-
 static void tsc_resume(struct clocksource *cs)
 {
 	tsc_verify_tsc_adjust(true);
@@ -1039,12 +1056,31 @@ static void tsc_cs_tick_stable(struct clocksource *cs)
 /*
  * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
  */
+static struct clocksource clocksource_tsc_early = {
+	.name                   = "tsc-early",
+	.rating                 = 299,
+	.read                   = read_tsc,
+	.mask                   = CLOCKSOURCE_MASK(64),
+	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS |
+				  CLOCK_SOURCE_MUST_VERIFY,
+	.archdata               = { .vclock_mode = VCLOCK_TSC },
+	.resume			= tsc_resume,
+	.mark_unstable		= tsc_cs_mark_unstable,
+	.tick_stable		= tsc_cs_tick_stable,
+};
+
+/*
+ * Must mark VALID_FOR_HRES early such that when we unregister tsc_early
+ * this one will immediately take over. We will only register if TSC has
+ * been found good.
+ */
 static struct clocksource clocksource_tsc = {
 	.name                   = "tsc",
 	.rating                 = 300,
 	.read                   = read_tsc,
 	.mask                   = CLOCKSOURCE_MASK(64),
 	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS |
+				  CLOCK_SOURCE_VALID_FOR_HRES |
 				  CLOCK_SOURCE_MUST_VERIFY,
 	.archdata               = { .vclock_mode = VCLOCK_TSC },
 	.resume			= tsc_resume,
@@ -1168,8 +1204,8 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	int cpu;
 
 	/* Don't bother refining TSC on unstable systems */
-	if (check_tsc_unstable())
-		goto out;
+	if (tsc_unstable)
+		return;
 
 	/*
 	 * Since the work is started early in boot, we may be
@@ -1221,9 +1257,13 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 		set_cyc2ns_scale(tsc_khz, cpu, tsc_stop);
 
 out:
+	if (tsc_unstable)
+		return;
+
 	if (boot_cpu_has(X86_FEATURE_ART))
 		art_related_clocksource = &clocksource_tsc;
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
+	clocksource_unregister(&clocksource_tsc_early);
 }
 
 
@@ -1232,13 +1272,11 @@ static int __init init_tsc_clocksource(void)
 	if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
 		return 0;
 
+	if (check_tsc_unstable())
+		return 0;
+
 	if (tsc_clocksource_reliable)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
-	/* lower the rating if we already know its unstable: */
-	if (check_tsc_unstable()) {
-		clocksource_tsc.rating = 0;
-		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
-	}
 
 	if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
 		clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
@@ -1251,6 +1289,7 @@ static int __init init_tsc_clocksource(void)
 		if (boot_cpu_has(X86_FEATURE_ART))
 			art_related_clocksource = &clocksource_tsc;
 		clocksource_register_khz(&clocksource_tsc, tsc_khz);
+		clocksource_unregister(&clocksource_tsc_early);
 		return 0;
 	}
 
@@ -1315,6 +1354,12 @@ void __init tsc_init(void)
 		(unsigned long)cpu_khz / 1000,
 		(unsigned long)cpu_khz % 1000);
 
+	if (cpu_khz != tsc_khz) {
+		pr_info("Detected %lu.%03lu MHz TSC",
+			(unsigned long)tsc_khz / 1000,
+			(unsigned long)tsc_khz % 1000);
+	}
+
 	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
 	tsc_store_and_check_tsc_adjust(true);
 
@@ -1349,9 +1394,12 @@ void __init tsc_init(void)
 
 	check_system_tsc_reliable();
 
-	if (unsynchronized_tsc())
+	if (unsynchronized_tsc()) {
 		mark_tsc_unstable("TSCs unsynchronized");
+		return;
+	}
 
+	clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
 	detect_art();
 }
 
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index a3f973b2c97a..1f9188f5357c 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -74,8 +74,50 @@ static struct orc_entry *orc_module_find(unsigned long ip)
 }
 #endif
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+static struct orc_entry *orc_find(unsigned long ip);
+
+/*
+ * Ftrace dynamic trampolines do not have orc entries of their own.
+ * But they are copies of the ftrace entries that are static and
+ * defined in ftrace_*.S, which do have orc entries.
+ *
+ * If the undwinder comes across a ftrace trampoline, then find the
+ * ftrace function that was used to create it, and use that ftrace
+ * function's orc entrie, as the placement of the return code in
+ * the stack will be identical.
+ */
+static struct orc_entry *orc_ftrace_find(unsigned long ip)
+{
+	struct ftrace_ops *ops;
+	unsigned long caller;
+
+	ops = ftrace_ops_trampoline(ip);
+	if (!ops)
+		return NULL;
+
+	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+		caller = (unsigned long)ftrace_regs_call;
+	else
+		caller = (unsigned long)ftrace_call;
+
+	/* Prevent unlikely recursion */
+	if (ip == caller)
+		return NULL;
+
+	return orc_find(caller);
+}
+#else
+static struct orc_entry *orc_ftrace_find(unsigned long ip)
+{
+	return NULL;
+}
+#endif
+
 static struct orc_entry *orc_find(unsigned long ip)
 {
+	static struct orc_entry *orc;
+
 	if (!orc_init)
 		return NULL;
 
@@ -111,7 +153,11 @@ static struct orc_entry *orc_find(unsigned long ip)
 				  __stop_orc_unwind_ip - __start_orc_unwind_ip, ip);
 
 	/* Module lookup: */
-	return orc_module_find(ip);
+	orc = orc_module_find(ip);
+	if (orc)
+		return orc;
+
+	return orc_ftrace_find(ip);
 }
 
 static void orc_sort_swap(void *_a, void *_b, int size)
@@ -253,22 +299,15 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
 	return NULL;
 }
 
-static bool stack_access_ok(struct unwind_state *state, unsigned long addr,
+static bool stack_access_ok(struct unwind_state *state, unsigned long _addr,
 			    size_t len)
 {
 	struct stack_info *info = &state->stack_info;
+	void *addr = (void *)_addr;
 
-	/*
-	 * If the address isn't on the current stack, switch to the next one.
-	 *
-	 * We may have to traverse multiple stacks to deal with the possibility
-	 * that info->next_sp could point to an empty stack and the address
-	 * could be on a subsequent stack.
-	 */
-	while (!on_stack(info, (void *)addr, len))
-		if (get_stack_info(info->next_sp, state->task, info,
-				   &state->stack_mask))
-			return false;
+	if (!on_stack(info, addr, len) &&
+	    (get_stack_info(addr, state->task, info, &state->stack_mask)))
+		return false;
 
 	return true;
 }
@@ -283,42 +322,32 @@ static bool deref_stack_reg(struct unwind_state *state, unsigned long addr,
 	return true;
 }
 
-#define REGS_SIZE (sizeof(struct pt_regs))
-#define SP_OFFSET (offsetof(struct pt_regs, sp))
-#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip))
-#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip))
-
 static bool deref_stack_regs(struct unwind_state *state, unsigned long addr,
-			     unsigned long *ip, unsigned long *sp, bool full)
+			     unsigned long *ip, unsigned long *sp)
 {
-	size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE;
-	size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET;
-	struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE);
-
-	if (IS_ENABLED(CONFIG_X86_64)) {
-		if (!stack_access_ok(state, addr, regs_size))
-			return false;
+	struct pt_regs *regs = (struct pt_regs *)addr;
 
-		*ip = regs->ip;
-		*sp = regs->sp;
+	/* x86-32 support will be more complicated due to the &regs->sp hack */
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_32));
 
-		return true;
-	}
-
-	if (!stack_access_ok(state, addr, sp_offset))
+	if (!stack_access_ok(state, addr, sizeof(struct pt_regs)))
 		return false;
 
 	*ip = regs->ip;
+	*sp = regs->sp;
+	return true;
+}
 
-	if (user_mode(regs)) {
-		if (!stack_access_ok(state, addr + sp_offset,
-				     REGS_SIZE - SP_OFFSET))
-			return false;
+static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr,
+				  unsigned long *ip, unsigned long *sp)
+{
+	struct pt_regs *regs = (void *)addr - IRET_FRAME_OFFSET;
 
-		*sp = regs->sp;
-	} else
-		*sp = (unsigned long)&regs->sp;
+	if (!stack_access_ok(state, addr, IRET_FRAME_SIZE))
+		return false;
 
+	*ip = regs->ip;
+	*sp = regs->sp;
 	return true;
 }
 
@@ -327,7 +356,6 @@ bool unwind_next_frame(struct unwind_state *state)
 	unsigned long ip_p, sp, orig_ip, prev_sp = state->sp;
 	enum stack_type prev_type = state->stack_info.type;
 	struct orc_entry *orc;
-	struct pt_regs *ptregs;
 	bool indirect = false;
 
 	if (unwind_done(state))
@@ -435,7 +463,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_TYPE_REGS:
-		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) {
+		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
 			goto done;
@@ -447,20 +475,14 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_TYPE_REGS_IRET:
-		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) {
+		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference iret registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
 			goto done;
 		}
 
-		ptregs = container_of((void *)sp, struct pt_regs, ip);
-		if ((unsigned long)ptregs >= prev_sp &&
-		    on_stack(&state->stack_info, ptregs, REGS_SIZE)) {
-			state->regs = ptregs;
-			state->full_regs = false;
-		} else
-			state->regs = NULL;
-
+		state->regs = (void *)sp - IRET_FRAME_OFFSET;
+		state->full_regs = false;
 		state->signal = true;
 		break;
 
@@ -553,8 +575,18 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	}
 
 	if (get_stack_info((unsigned long *)state->sp, state->task,
-			   &state->stack_info, &state->stack_mask))
-		return;
+			   &state->stack_info, &state->stack_mask)) {
+		/*
+		 * We weren't on a valid stack.  It's possible that
+		 * we overflowed a valid stack into a guard page.
+		 * See if the next page up is valid so that we can
+		 * generate some kind of backtrace if this happens.
+		 */
+		void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp);
+		if (get_stack_info(next_page, state->task, &state->stack_info,
+				   &state->stack_mask))
+			return;
+	}
 
 	/*
 	 * The caller can provide the address of the first frame directly
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index a3755d293a48..85c7ef23d99f 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -528,11 +528,11 @@ static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	return 0;
 }
 
-static int push_ret_address(struct pt_regs *regs, unsigned long ip)
+static int emulate_push_stack(struct pt_regs *regs, unsigned long val)
 {
 	unsigned long new_sp = regs->sp - sizeof_long();
 
-	if (copy_to_user((void __user *)new_sp, &ip, sizeof_long()))
+	if (copy_to_user((void __user *)new_sp, &val, sizeof_long()))
 		return -EFAULT;
 
 	regs->sp = new_sp;
@@ -566,7 +566,7 @@ static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs
 		regs->ip += correction;
 	} else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) {
 		regs->sp += sizeof_long(); /* Pop incorrect return address */
-		if (push_ret_address(regs, utask->vaddr + auprobe->defparam.ilen))
+		if (emulate_push_stack(regs, utask->vaddr + auprobe->defparam.ilen))
 			return -ERESTART;
 	}
 	/* popf; tell the caller to not touch TF */
@@ -655,7 +655,7 @@ static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 		 *
 		 * But there is corner case, see the comment in ->post_xol().
 		 */
-		if (push_ret_address(regs, new_ip))
+		if (emulate_push_stack(regs, new_ip))
 			return false;
 	} else if (!check_jmp_cond(auprobe, regs)) {
 		offs = 0;
@@ -665,6 +665,16 @@ static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	return true;
 }
 
+static bool push_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	unsigned long *src_ptr = (void *)regs + auprobe->push.reg_offset;
+
+	if (emulate_push_stack(regs, *src_ptr))
+		return false;
+	regs->ip += auprobe->push.ilen;
+	return true;
+}
+
 static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 	BUG_ON(!branch_is_call(auprobe));
@@ -703,6 +713,10 @@ static const struct uprobe_xol_ops branch_xol_ops = {
 	.post_xol = branch_post_xol_op,
 };
 
+static const struct uprobe_xol_ops push_xol_ops = {
+	.emulate  = push_emulate_op,
+};
+
 /* Returns -ENOSYS if branch_xol_ops doesn't handle this insn */
 static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 {
@@ -750,6 +764,87 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 	return 0;
 }
 
+/* Returns -ENOSYS if push_xol_ops doesn't handle this insn */
+static int push_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
+{
+	u8 opc1 = OPCODE1(insn), reg_offset = 0;
+
+	if (opc1 < 0x50 || opc1 > 0x57)
+		return -ENOSYS;
+
+	if (insn->length > 2)
+		return -ENOSYS;
+	if (insn->length == 2) {
+		/* only support rex_prefix 0x41 (x64 only) */
+#ifdef CONFIG_X86_64
+		if (insn->rex_prefix.nbytes != 1 ||
+		    insn->rex_prefix.bytes[0] != 0x41)
+			return -ENOSYS;
+
+		switch (opc1) {
+		case 0x50:
+			reg_offset = offsetof(struct pt_regs, r8);
+			break;
+		case 0x51:
+			reg_offset = offsetof(struct pt_regs, r9);
+			break;
+		case 0x52:
+			reg_offset = offsetof(struct pt_regs, r10);
+			break;
+		case 0x53:
+			reg_offset = offsetof(struct pt_regs, r11);
+			break;
+		case 0x54:
+			reg_offset = offsetof(struct pt_regs, r12);
+			break;
+		case 0x55:
+			reg_offset = offsetof(struct pt_regs, r13);
+			break;
+		case 0x56:
+			reg_offset = offsetof(struct pt_regs, r14);
+			break;
+		case 0x57:
+			reg_offset = offsetof(struct pt_regs, r15);
+			break;
+		}
+#else
+		return -ENOSYS;
+#endif
+	} else {
+		switch (opc1) {
+		case 0x50:
+			reg_offset = offsetof(struct pt_regs, ax);
+			break;
+		case 0x51:
+			reg_offset = offsetof(struct pt_regs, cx);
+			break;
+		case 0x52:
+			reg_offset = offsetof(struct pt_regs, dx);
+			break;
+		case 0x53:
+			reg_offset = offsetof(struct pt_regs, bx);
+			break;
+		case 0x54:
+			reg_offset = offsetof(struct pt_regs, sp);
+			break;
+		case 0x55:
+			reg_offset = offsetof(struct pt_regs, bp);
+			break;
+		case 0x56:
+			reg_offset = offsetof(struct pt_regs, si);
+			break;
+		case 0x57:
+			reg_offset = offsetof(struct pt_regs, di);
+			break;
+		}
+	}
+
+	auprobe->push.reg_offset = reg_offset;
+	auprobe->push.ilen = insn->length;
+	auprobe->ops = &push_xol_ops;
+	return 0;
+}
+
 /**
  * arch_uprobe_analyze_insn - instruction analysis including validity and fixups.
  * @mm: the probed address space.
@@ -771,6 +866,10 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	if (ret != -ENOSYS)
 		return ret;
 
+	ret = push_setup_xol_ops(auprobe, &insn);
+	if (ret != -ENOSYS)
+		return ret;
+
 	/*
 	 * Figure out which fixups default_post_xol_op() will need to perform,
 	 * and annotate defparam->fixups accordingly.
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index a4009fb9be87..9b138a06c1a4 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -61,11 +61,17 @@ jiffies_64 = jiffies;
 		. = ALIGN(HPAGE_SIZE);				\
 		__end_rodata_hpage_align = .;
 
+#define ALIGN_ENTRY_TEXT_BEGIN	. = ALIGN(PMD_SIZE);
+#define ALIGN_ENTRY_TEXT_END	. = ALIGN(PMD_SIZE);
+
 #else
 
 #define X64_ALIGN_RODATA_BEGIN
 #define X64_ALIGN_RODATA_END
 
+#define ALIGN_ENTRY_TEXT_BEGIN
+#define ALIGN_ENTRY_TEXT_END
+
 #endif
 
 PHDRS {
@@ -102,11 +108,28 @@ SECTIONS
 		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
+		ALIGN_ENTRY_TEXT_BEGIN
 		ENTRY_TEXT
 		IRQENTRY_TEXT
+		ALIGN_ENTRY_TEXT_END
 		SOFTIRQENTRY_TEXT
 		*(.fixup)
 		*(.gnu.warning)
+
+#ifdef CONFIG_X86_64
+		. = ALIGN(PAGE_SIZE);
+		_entry_trampoline = .;
+		*(.entry_trampoline)
+		. = ALIGN(PAGE_SIZE);
+		ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
+#endif
+
+#ifdef CONFIG_RETPOLINE
+		__indirect_thunk_start = .;
+		*(.text.__x86.indirect_thunk)
+		__indirect_thunk_end = .;
+#endif
+
 		/* End of text section */
 		_etext = .;
 	} :text = 0x9090
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index cdc70a3a6583..c2cea6651279 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -44,7 +44,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_8086_0001_EDX] = {0x80860001, 0, CPUID_EDX},
 	[CPUID_1_ECX]         = {         1, 0, CPUID_ECX},
 	[CPUID_C000_0001_EDX] = {0xc0000001, 0, CPUID_EDX},
-	[CPUID_8000_0001_ECX] = {0xc0000001, 0, CPUID_ECX},
+	[CPUID_8000_0001_ECX] = {0x80000001, 0, CPUID_ECX},
 	[CPUID_7_0_EBX]       = {         7, 0, CPUID_EBX},
 	[CPUID_D_1_EAX]       = {       0xd, 1, CPUID_EAX},
 	[CPUID_F_0_EDX]       = {       0xf, 0, CPUID_EDX},
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8079d141792a..290ecf711aec 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -25,6 +25,7 @@
 #include <asm/kvm_emulate.h>
 #include <linux/stringify.h>
 #include <asm/debugreg.h>
+#include <asm/nospec-branch.h>
 
 #include "x86.h"
 #include "tss.h"
@@ -1021,8 +1022,8 @@ static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
 	void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf);
 
 	flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
-	asm("push %[flags]; popf; call *%[fastop]"
-	    : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags));
+	asm("push %[flags]; popf; " CALL_NOSPEC
+	    : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags));
 	return rc;
 }
 
@@ -1046,7 +1047,6 @@ static void fetch_register_operand(struct operand *op)
 
 static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break;
 	case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break;
@@ -1068,13 +1068,11 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 #endif
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 			  int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break;
 	case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break;
@@ -1096,12 +1094,10 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 #endif
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movq %%mm0, %0" : "=m"(*data)); break;
 	case 1: asm("movq %%mm1, %0" : "=m"(*data)); break;
@@ -1113,12 +1109,10 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %%mm7, %0" : "=m"(*data)); break;
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movq %0, %%mm0" : : "m"(*data)); break;
 	case 1: asm("movq %0, %%mm1" : : "m"(*data)); break;
@@ -1130,7 +1124,6 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %0, %%mm7" : : "m"(*data)); break;
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static int em_fninit(struct x86_emulate_ctxt *ctxt)
@@ -1138,9 +1131,7 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fninit");
-	ctxt->ops->put_fpu(ctxt);
 	return X86EMUL_CONTINUE;
 }
 
@@ -1151,9 +1142,7 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fnstcw %0": "+m"(fcw));
-	ctxt->ops->put_fpu(ctxt);
 
 	ctxt->dst.val = fcw;
 
@@ -1167,9 +1156,7 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fnstsw %0": "+m"(fsw));
-	ctxt->ops->put_fpu(ctxt);
 
 	ctxt->dst.val = fsw;
 
@@ -2404,9 +2391,21 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
 }
 
 static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
-				     u64 cr0, u64 cr4)
+				    u64 cr0, u64 cr3, u64 cr4)
 {
 	int bad;
+	u64 pcid;
+
+	/* In order to later set CR4.PCIDE, CR3[11:0] must be zero.  */
+	pcid = 0;
+	if (cr4 & X86_CR4_PCIDE) {
+		pcid = cr3 & 0xfff;
+		cr3 &= ~0xfff;
+	}
+
+	bad = ctxt->ops->set_cr(ctxt, 3, cr3);
+	if (bad)
+		return X86EMUL_UNHANDLEABLE;
 
 	/*
 	 * First enable PAE, long mode needs it before CR0.PG = 1 is set.
@@ -2425,6 +2424,12 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
 		bad = ctxt->ops->set_cr(ctxt, 4, cr4);
 		if (bad)
 			return X86EMUL_UNHANDLEABLE;
+		if (pcid) {
+			bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid);
+			if (bad)
+				return X86EMUL_UNHANDLEABLE;
+		}
+
 	}
 
 	return X86EMUL_CONTINUE;
@@ -2435,11 +2440,11 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	struct desc_struct desc;
 	struct desc_ptr dt;
 	u16 selector;
-	u32 val, cr0, cr4;
+	u32 val, cr0, cr3, cr4;
 	int i;
 
 	cr0 =                      GET_SMSTATE(u32, smbase, 0x7ffc);
-	ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8));
+	cr3 =                      GET_SMSTATE(u32, smbase, 0x7ff8);
 	ctxt->eflags =             GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
 	ctxt->_eip =               GET_SMSTATE(u32, smbase, 0x7ff0);
 
@@ -2481,14 +2486,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
 
 	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
 
-	return rsm_enter_protected_mode(ctxt, cr0, cr4);
+	return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
 }
 
 static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 {
 	struct desc_struct desc;
 	struct desc_ptr dt;
-	u64 val, cr0, cr4;
+	u64 val, cr0, cr3, cr4;
 	u32 base3;
 	u16 selector;
 	int i, r;
@@ -2505,7 +2510,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
 
 	cr0 =                       GET_SMSTATE(u64, smbase, 0x7f58);
-	ctxt->ops->set_cr(ctxt, 3,  GET_SMSTATE(u64, smbase, 0x7f50));
+	cr3 =                       GET_SMSTATE(u64, smbase, 0x7f50);
 	cr4 =                       GET_SMSTATE(u64, smbase, 0x7f48);
 	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
 	val =                       GET_SMSTATE(u64, smbase, 0x7ed0);
@@ -2533,7 +2538,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	dt.address =                GET_SMSTATE(u64, smbase, 0x7e68);
 	ctxt->ops->set_gdt(ctxt, &dt);
 
-	r = rsm_enter_protected_mode(ctxt, cr0, cr4);
+	r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
 	if (r != X86EMUL_CONTINUE)
 		return r;
 
@@ -4001,12 +4006,8 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	ctxt->ops->get_fpu(ctxt);
-
 	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
 
-	ctxt->ops->put_fpu(ctxt);
-
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
@@ -4014,6 +4015,26 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 		                   fxstate_size(ctxt));
 }
 
+/*
+ * FXRSTOR might restore XMM registers not provided by the guest. Fill
+ * in the host registers (via FXSAVE) instead, so they won't be modified.
+ * (preemption has to stay disabled until FXRSTOR).
+ *
+ * Use noinline to keep the stack for other functions called by callers small.
+ */
+static noinline int fxregs_fixup(struct fxregs_state *fx_state,
+				 const size_t used_size)
+{
+	struct fxregs_state fx_tmp;
+	int rc;
+
+	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_tmp));
+	memcpy((void *)fx_state + used_size, (void *)&fx_tmp + used_size,
+	       __fxstate_size(16) - used_size);
+
+	return rc;
+}
+
 static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 {
 	struct fxregs_state fx_state;
@@ -4024,19 +4045,17 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	ctxt->ops->get_fpu(ctxt);
-
 	size = fxstate_size(ctxt);
+	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
 	if (size < __fxstate_size(16)) {
-		rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
+		rc = fxregs_fixup(&fx_state, size);
 		if (rc != X86EMUL_CONTINUE)
 			goto out;
 	}
 
-	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
-	if (rc != X86EMUL_CONTINUE)
-		goto out;
-
 	if (fx_state.mxcsr >> 16) {
 		rc = emulate_gp(ctxt, 0);
 		goto out;
@@ -4046,8 +4065,6 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
 
 out:
-	ctxt->ops->put_fpu(ctxt);
-
 	return rc;
 }
 
@@ -5000,6 +5017,8 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	bool op_prefix = false;
 	bool has_seg_override = false;
 	struct opcode opcode;
+	u16 dummy;
+	struct desc_struct desc;
 
 	ctxt->memop.type = OP_NONE;
 	ctxt->memopp = NULL;
@@ -5018,6 +5037,11 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	switch (mode) {
 	case X86EMUL_MODE_REAL:
 	case X86EMUL_MODE_VM86:
+		def_op_bytes = def_ad_bytes = 2;
+		ctxt->ops->get_segment(ctxt, &dummy, &desc, NULL, VCPU_SREG_CS);
+		if (desc.d)
+			def_op_bytes = def_ad_bytes = 4;
+		break;
 	case X86EMUL_MODE_PROT16:
 		def_op_bytes = def_ad_bytes = 2;
 		break;
@@ -5290,9 +5314,7 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 
-	ctxt->ops->get_fpu(ctxt);
 	rc = asm_safe("fwait");
-	ctxt->ops->put_fpu(ctxt);
 
 	if (unlikely(rc != X86EMUL_CONTINUE))
 		return emulate_exception(ctxt, MF_VECTOR, 0, false);
@@ -5314,9 +5336,9 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
 	if (!(ctxt->d & ByteOp))
 		fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE;
 
-	asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n"
+	asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n"
 	    : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags),
-	      [fastop]"+S"(fop), ASM_CALL_CONSTRAINT
+	      [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT
 	    : "c"(ctxt->src2.val));
 
 	ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index bdff437acbcb..4e822ad363f3 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -209,12 +209,12 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
 
 	old_irr = ioapic->irr;
 	ioapic->irr |= mask;
-	if (edge)
+	if (edge) {
 		ioapic->irr_delivered &= ~mask;
-	if ((edge && old_irr == ioapic->irr) ||
-	    (!edge && entry.fields.remote_irr)) {
-		ret = 0;
-		goto out;
+		if (old_irr == ioapic->irr) {
+			ret = 0;
+			goto out;
+		}
 	}
 
 	ret = ioapic_service(ioapic, irq, line_status);
@@ -257,8 +257,7 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors)
 		    index == RTC_GSI) {
 			if (kvm_apic_match_dest(vcpu, NULL, 0,
 			             e->fields.dest_id, e->fields.dest_mode) ||
-			    (e->fields.trig_mode == IOAPIC_EDGE_TRIG &&
-			     kvm_apic_pending_eoi(vcpu, e->fields.vector)))
+			    kvm_apic_pending_eoi(vcpu, e->fields.vector))
 				__set_bit(e->fields.vector,
 					  ioapic_handled_vectors);
 		}
@@ -277,6 +276,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 {
 	unsigned index;
 	bool mask_before, mask_after;
+	int old_remote_irr, old_delivery_status;
 	union kvm_ioapic_redirect_entry *e;
 
 	switch (ioapic->ioregsel) {
@@ -299,14 +299,28 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 			return;
 		e = &ioapic->redirtbl[index];
 		mask_before = e->fields.mask;
+		/* Preserve read-only fields */
+		old_remote_irr = e->fields.remote_irr;
+		old_delivery_status = e->fields.delivery_status;
 		if (ioapic->ioregsel & 1) {
 			e->bits &= 0xffffffff;
 			e->bits |= (u64) val << 32;
 		} else {
 			e->bits &= ~0xffffffffULL;
 			e->bits |= (u32) val;
-			e->fields.remote_irr = 0;
 		}
+		e->fields.remote_irr = old_remote_irr;
+		e->fields.delivery_status = old_delivery_status;
+
+		/*
+		 * Some OSes (Linux, Xen) assume that Remote IRR bit will
+		 * be cleared by IOAPIC hardware when the entry is configured
+		 * as edge-triggered. This behavior is used to simulate an
+		 * explicit EOI on IOAPICs that don't have the EOI register.
+		 */
+		if (e->fields.trig_mode == IOAPIC_EDGE_TRIG)
+			e->fields.remote_irr = 0;
+
 		mask_after = e->fields.mask;
 		if (mask_before != mask_after)
 			kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
@@ -324,7 +338,9 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
 	struct kvm_lapic_irq irqe;
 	int ret;
 
-	if (entry->fields.mask)
+	if (entry->fields.mask ||
+	    (entry->fields.trig_mode == IOAPIC_LEVEL_TRIG &&
+	    entry->fields.remote_irr))
 		return -1;
 
 	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 943acbf00c69..e2c1fb8d35ce 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -266,9 +266,14 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
 	recalculate_apic_map(apic->vcpu->kvm);
 }
 
+static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
+{
+	return ((id >> 4) << 16) | (1 << (id & 0xf));
+}
+
 static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id)
 {
-	u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
+	u32 ldr = kvm_apic_calc_x2apic_ldr(id);
 
 	WARN_ON_ONCE(id != apic->vcpu->vcpu_id);
 
@@ -2245,6 +2250,7 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
 {
 	if (apic_x2apic_mode(vcpu->arch.apic)) {
 		u32 *id = (u32 *)(s->regs + APIC_ID);
+		u32 *ldr = (u32 *)(s->regs + APIC_LDR);
 
 		if (vcpu->kvm->arch.x2apic_format) {
 			if (*id != vcpu->vcpu_id)
@@ -2255,6 +2261,10 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
 			else
 				*id <<= 24;
 		}
+
+		/* In x2APIC mode, the LDR is fixed and based on the id */
+		if (set)
+			*ldr = kvm_apic_calc_x2apic_ldr(*id);
 	}
 
 	return 0;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e5e66e5c6640..2b8eb4da4d08 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3395,7 +3395,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 		spin_lock(&vcpu->kvm->mmu_lock);
 		if(make_mmu_pages_available(vcpu) < 0) {
 			spin_unlock(&vcpu->kvm->mmu_lock);
-			return 1;
+			return -ENOSPC;
 		}
 		sp = kvm_mmu_get_page(vcpu, 0, 0,
 				vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
@@ -3410,7 +3410,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 			spin_lock(&vcpu->kvm->mmu_lock);
 			if (make_mmu_pages_available(vcpu) < 0) {
 				spin_unlock(&vcpu->kvm->mmu_lock);
-				return 1;
+				return -ENOSPC;
 			}
 			sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
 					i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL);
@@ -3450,7 +3450,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 		spin_lock(&vcpu->kvm->mmu_lock);
 		if (make_mmu_pages_available(vcpu) < 0) {
 			spin_unlock(&vcpu->kvm->mmu_lock);
-			return 1;
+			return -ENOSPC;
 		}
 		sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
 				vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL);
@@ -3487,7 +3487,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 		spin_lock(&vcpu->kvm->mmu_lock);
 		if (make_mmu_pages_available(vcpu) < 0) {
 			spin_unlock(&vcpu->kvm->mmu_lock);
-			return 1;
+			return -ENOSPC;
 		}
 		sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL,
 				      0, ACC_ALL);
@@ -3781,7 +3781,8 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(!lapic_in_kernel(vcpu) ||
-		     kvm_event_needs_reinjection(vcpu)))
+		     kvm_event_needs_reinjection(vcpu) ||
+		     vcpu->arch.exception.pending))
 		return false;
 
 	if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu))
@@ -5465,30 +5466,34 @@ static void mmu_destroy_caches(void)
 
 int kvm_mmu_module_init(void)
 {
+	int ret = -ENOMEM;
+
 	kvm_mmu_clear_all_pte_masks();
 
 	pte_list_desc_cache = kmem_cache_create("pte_list_desc",
 					    sizeof(struct pte_list_desc),
 					    0, SLAB_ACCOUNT, NULL);
 	if (!pte_list_desc_cache)
-		goto nomem;
+		goto out;
 
 	mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header",
 						  sizeof(struct kvm_mmu_page),
 						  0, SLAB_ACCOUNT, NULL);
 	if (!mmu_page_header_cache)
-		goto nomem;
+		goto out;
 
 	if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL))
-		goto nomem;
+		goto out;
 
-	register_shrinker(&mmu_shrinker);
+	ret = register_shrinker(&mmu_shrinker);
+	if (ret)
+		goto out;
 
 	return 0;
 
-nomem:
+out:
 	mmu_destroy_caches();
-	return -ENOMEM;
+	return ret;
 }
 
 /*
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 59e13a79c2e3..f40d0da1f1d3 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -45,6 +45,7 @@
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
 #include <asm/irq_remapping.h>
+#include <asm/nospec-branch.h>
 
 #include <asm/virtext.h>
 #include "trace.h"
@@ -2197,6 +2198,8 @@ static int ud_interception(struct vcpu_svm *svm)
 	int er;
 
 	er = emulate_instruction(&svm->vcpu, EMULTYPE_TRAP_UD);
+	if (er == EMULATE_USER_EXIT)
+		return 0;
 	if (er != EMULATE_DONE)
 		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 	return 1;
@@ -4977,6 +4980,25 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 		"mov %%r14, %c[r14](%[svm]) \n\t"
 		"mov %%r15, %c[r15](%[svm]) \n\t"
 #endif
+		/*
+		* Clear host registers marked as clobbered to prevent
+		* speculative use.
+		*/
+		"xor %%" _ASM_BX ", %%" _ASM_BX " \n\t"
+		"xor %%" _ASM_CX ", %%" _ASM_CX " \n\t"
+		"xor %%" _ASM_DX ", %%" _ASM_DX " \n\t"
+		"xor %%" _ASM_SI ", %%" _ASM_SI " \n\t"
+		"xor %%" _ASM_DI ", %%" _ASM_DI " \n\t"
+#ifdef CONFIG_X86_64
+		"xor %%r8, %%r8 \n\t"
+		"xor %%r9, %%r9 \n\t"
+		"xor %%r10, %%r10 \n\t"
+		"xor %%r11, %%r11 \n\t"
+		"xor %%r12, %%r12 \n\t"
+		"xor %%r13, %%r13 \n\t"
+		"xor %%r14, %%r14 \n\t"
+		"xor %%r15, %%r15 \n\t"
+#endif
 		"pop %%" _ASM_BP
 		:
 		: [svm]"a"(svm),
@@ -5006,6 +5028,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 		);
 
+	/* Eliminate branch target predictions from guest mode */
+	vmexit_fill_RSB();
+
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_GS_BASE, svm->host.gs_base);
 #else
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 714a0673ec3c..a8b96dc4cd83 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -50,6 +50,7 @@
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
 #include <asm/mmu_context.h>
+#include <asm/nospec-branch.h>
 
 #include "trace.h"
 #include "pmu.h"
@@ -899,8 +900,16 @@ static inline short vmcs_field_to_offset(unsigned long field)
 {
 	BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX);
 
-	if (field >= ARRAY_SIZE(vmcs_field_to_offset_table) ||
-	    vmcs_field_to_offset_table[field] == 0)
+	if (field >= ARRAY_SIZE(vmcs_field_to_offset_table))
+		return -ENOENT;
+
+	/*
+	 * FIXME: Mitigation for CVE-2017-5753.  To be replaced with a
+	 * generic mechanism.
+	 */
+	asm("lfence");
+
+	if (vmcs_field_to_offset_table[field] == 0)
 		return -ENOENT;
 
 	return vmcs_field_to_offset_table[field];
@@ -2300,7 +2309,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		 * processors.  See 22.2.4.
 		 */
 		vmcs_writel(HOST_TR_BASE,
-			    (unsigned long)this_cpu_ptr(&cpu_tss));
+			    (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss);
 		vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt);   /* 22.2.4 */
 
 		/*
@@ -5600,7 +5609,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
 	}
 
-	vmcs_writel(GUEST_RFLAGS, 0x02);
+	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
 	kvm_rip_write(vcpu, 0xfff0);
 
 	vmcs_writel(GUEST_GDTR_BASE, 0);
@@ -5915,11 +5924,9 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 		return 1;  /* already handled by vmx_vcpu_run() */
 
 	if (is_invalid_opcode(intr_info)) {
-		if (is_guest_mode(vcpu)) {
-			kvm_queue_exception(vcpu, UD_VECTOR);
-			return 1;
-		}
 		er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD);
+		if (er == EMULATE_USER_EXIT)
+			return 0;
 		if (er != EMULATE_DONE)
 			kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
@@ -6602,7 +6609,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		if (kvm_test_request(KVM_REQ_EVENT, vcpu))
 			return 1;
 
-		err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);
+		err = emulate_instruction(vcpu, 0);
 
 		if (err == EMULATE_USER_EXIT) {
 			++vcpu->stat.mmio_exits;
@@ -6750,16 +6757,10 @@ static __init int hardware_setup(void)
 			goto out;
 	}
 
-	vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
 	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
 	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
 
-	/*
-	 * Allow direct access to the PC debug port (it is often used for I/O
-	 * delays, but the vmexits simply slow things down).
-	 */
 	memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
-	clear_bit(0x80, vmx_io_bitmap_a);
 
 	memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
 
@@ -7414,10 +7415,11 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
  */
 static void free_nested(struct vcpu_vmx *vmx)
 {
-	if (!vmx->nested.vmxon)
+	if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
 		return;
 
 	vmx->nested.vmxon = false;
+	vmx->nested.smm.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
@@ -9127,14 +9129,14 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 #endif
 			"pushf\n\t"
 			__ASM_SIZE(push) " $%c[cs]\n\t"
-			"call *%[entry]\n\t"
+			CALL_NOSPEC
 			:
 #ifdef CONFIG_X86_64
 			[sp]"=&r"(tmp),
 #endif
 			ASM_CALL_CONSTRAINT
 			:
-			[entry]"r"(entry),
+			THUNK_TARGET(entry),
 			[ss]"i"(__KERNEL_DS),
 			[cs]"i"(__KERNEL_CS)
 			);
@@ -9419,6 +9421,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		/* Save guest registers, load host registers, keep flags */
 		"mov %0, %c[wordsize](%%" _ASM_SP ") \n\t"
 		"pop %0 \n\t"
+		"setbe %c[fail](%0)\n\t"
 		"mov %%" _ASM_AX ", %c[rax](%0) \n\t"
 		"mov %%" _ASM_BX ", %c[rbx](%0) \n\t"
 		__ASM_SIZE(pop) " %c[rcx](%0) \n\t"
@@ -9435,12 +9438,23 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		"mov %%r13, %c[r13](%0) \n\t"
 		"mov %%r14, %c[r14](%0) \n\t"
 		"mov %%r15, %c[r15](%0) \n\t"
+		"xor %%r8d,  %%r8d \n\t"
+		"xor %%r9d,  %%r9d \n\t"
+		"xor %%r10d, %%r10d \n\t"
+		"xor %%r11d, %%r11d \n\t"
+		"xor %%r12d, %%r12d \n\t"
+		"xor %%r13d, %%r13d \n\t"
+		"xor %%r14d, %%r14d \n\t"
+		"xor %%r15d, %%r15d \n\t"
 #endif
 		"mov %%cr2, %%" _ASM_AX "   \n\t"
 		"mov %%" _ASM_AX ", %c[cr2](%0) \n\t"
 
+		"xor %%eax, %%eax \n\t"
+		"xor %%ebx, %%ebx \n\t"
+		"xor %%esi, %%esi \n\t"
+		"xor %%edi, %%edi \n\t"
 		"pop  %%" _ASM_BP "; pop  %%" _ASM_DX " \n\t"
-		"setbe %c[fail](%0) \n\t"
 		".pushsection .rodata \n\t"
 		".global vmx_return \n\t"
 		"vmx_return: " _ASM_PTR " 2b \n\t"
@@ -9477,6 +9491,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 	      );
 
+	/* Eliminate branch target predictions from guest mode */
+	vmexit_fill_RSB();
+
 	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
 	if (debugctlmsr)
 		update_debugctlmsr(debugctlmsr);
@@ -9800,8 +9817,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 	cr4_fixed1_update(X86_CR4_SMEP,       ebx, bit(X86_FEATURE_SMEP));
 	cr4_fixed1_update(X86_CR4_SMAP,       ebx, bit(X86_FEATURE_SMAP));
 	cr4_fixed1_update(X86_CR4_PKE,        ecx, bit(X86_FEATURE_PKU));
-	/* TODO: Use X86_CR4_UMIP and X86_FEATURE_UMIP macros */
-	cr4_fixed1_update(bit(11),            ecx, bit(2));
+	cr4_fixed1_update(X86_CR4_UMIP,       ecx, bit(X86_FEATURE_UMIP));
 
 #undef cr4_fixed1_update
 }
@@ -10875,6 +10891,11 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			return 1;
 	}
 
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
+		(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu) ||
+		(vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))
+			return 1;
+
 	return 0;
 }
 
@@ -11099,13 +11120,12 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long exit_qual;
-
-	if (kvm_event_needs_reinjection(vcpu))
-		return -EBUSY;
+	bool block_nested_events =
+	    vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
 
 	if (vcpu->arch.exception.pending &&
 		nested_vmx_check_exception(vcpu, &exit_qual)) {
-		if (vmx->nested.nested_run_pending)
+		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
 		vcpu->arch.exception.pending = false;
@@ -11114,14 +11134,14 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 
 	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
 	    vmx->nested.preemption_timer_expired) {
-		if (vmx->nested.nested_run_pending)
+		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
 		return 0;
 	}
 
 	if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
-		if (vmx->nested.nested_run_pending)
+		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 				  NMI_VECTOR | INTR_TYPE_NMI_INTR |
@@ -11137,7 +11157,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 
 	if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
 	    nested_exit_on_intr(vcpu)) {
-		if (vmx->nested.nested_run_pending)
+		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
 		return 0;
@@ -11324,6 +11344,24 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	kvm_clear_interrupt_queue(vcpu);
 }
 
+static void load_vmcs12_mmu_host_state(struct kvm_vcpu *vcpu,
+			struct vmcs12 *vmcs12)
+{
+	u32 entry_failure_code;
+
+	nested_ept_uninit_mmu_context(vcpu);
+
+	/*
+	 * Only PDPTE load can fail as the value of cr3 was checked on entry and
+	 * couldn't have changed.
+	 */
+	if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
+		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
+
+	if (!enable_ept)
+		vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+}
+
 /*
  * A part of what we need to when the nested L2 guest exits and we want to
  * run its L1 parent, is to reset L1's guest state to the host state specified
@@ -11337,7 +11375,6 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 				   struct vmcs12 *vmcs12)
 {
 	struct kvm_segment seg;
-	u32 entry_failure_code;
 
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
 		vcpu->arch.efer = vmcs12->host_ia32_efer;
@@ -11364,17 +11401,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
 	vmx_set_cr4(vcpu, vmcs12->host_cr4);
 
-	nested_ept_uninit_mmu_context(vcpu);
-
-	/*
-	 * Only PDPTE load can fail as the value of cr3 was checked on entry and
-	 * couldn't have changed.
-	 */
-	if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
-		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
-
-	if (!enable_ept)
-		vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+	load_vmcs12_mmu_host_state(vcpu, vmcs12);
 
 	if (enable_vpid) {
 		/*
@@ -11604,6 +11631,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	 * accordingly.
 	 */
 	nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+
+	load_vmcs12_mmu_host_state(vcpu, vmcs12);
+
 	/*
 	 * The emulated instruction was already skipped in
 	 * nested_vmx_run, but the updated RIP was never
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 34c85aa2e2d1..c53298dfbf50 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -107,6 +107,9 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops);
 static bool __read_mostly ignore_msrs = 0;
 module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
 
+static bool __read_mostly report_ignored_msrs = true;
+module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
+
 unsigned int min_timer_period_us = 500;
 module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
 
@@ -1795,10 +1798,13 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 	/* both __this_cpu_read() and rdtsc() should be on the same cpu */
 	get_cpu();
 
-	kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
-			   &hv_clock.tsc_shift,
-			   &hv_clock.tsc_to_system_mul);
-	ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+	if (__this_cpu_read(cpu_tsc_khz)) {
+		kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
+				   &hv_clock.tsc_shift,
+				   &hv_clock.tsc_to_system_mul);
+		ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+	} else
+		ret = ktime_get_boot_ns() + ka->kvmclock_offset;
 
 	put_cpu();
 
@@ -1830,6 +1836,9 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
 	 */
 	BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
 
+	if (guest_hv_clock.version & 1)
+		++guest_hv_clock.version;  /* first time write, random junk */
+
 	vcpu->hv_clock.version = guest_hv_clock.version + 1;
 	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
 				&vcpu->hv_clock,
@@ -2322,7 +2331,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		/* Drop writes to this legacy MSR -- see rdmsr
 		 * counterpart for further detail.
 		 */
-		vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", msr, data);
+		if (report_ignored_msrs)
+			vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
+				msr, data);
 		break;
 	case MSR_AMD64_OSVW_ID_LENGTH:
 		if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
@@ -2359,8 +2370,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 				    msr, data);
 			return 1;
 		} else {
-			vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
-				    msr, data);
+			if (report_ignored_msrs)
+				vcpu_unimpl(vcpu,
+					"ignored wrmsr: 0x%x data 0x%llx\n",
+					msr, data);
 			break;
 		}
 	}
@@ -2578,7 +2591,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 					       msr_info->index);
 			return 1;
 		} else {
-			vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index);
+			if (report_ignored_msrs)
+				vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n",
+					msr_info->index);
 			msr_info->data = 0;
 		}
 		break;
@@ -2922,7 +2937,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	pagefault_enable();
 	kvm_x86_ops->vcpu_put(vcpu);
-	kvm_put_guest_fpu(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
 }
 
@@ -4370,7 +4384,7 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
 					 addr, n, v))
 		    && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v))
 			break;
-		trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v);
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, v);
 		handled += n;
 		addr += n;
 		len -= n;
@@ -4629,7 +4643,7 @@ static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes)
 {
 	if (vcpu->mmio_read_completed) {
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes,
-			       vcpu->mmio_fragments[0].gpa, *(u64 *)val);
+			       vcpu->mmio_fragments[0].gpa, val);
 		vcpu->mmio_read_completed = 0;
 		return 1;
 	}
@@ -4651,14 +4665,14 @@ static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa,
 
 static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val)
 {
-	trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val);
+	trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, val);
 	return vcpu_mmio_write(vcpu, gpa, bytes, val);
 }
 
 static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  void *val, int bytes)
 {
-	trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0);
+	trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, NULL);
 	return X86EMUL_IO_NEEDED;
 }
 
@@ -5237,17 +5251,6 @@ static void emulator_halt(struct x86_emulate_ctxt *ctxt)
 	emul_to_vcpu(ctxt)->arch.halt_request = 1;
 }
 
-static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt)
-{
-	preempt_disable();
-	kvm_load_guest_fpu(emul_to_vcpu(ctxt));
-}
-
-static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt)
-{
-	preempt_enable();
-}
-
 static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
 			      struct x86_instruction_info *info,
 			      enum x86_intercept_stage stage)
@@ -5325,8 +5328,6 @@ static const struct x86_emulate_ops emulate_ops = {
 	.halt                = emulator_halt,
 	.wbinvd              = emulator_wbinvd,
 	.fix_hypercall       = emulator_fix_hypercall,
-	.get_fpu             = emulator_get_fpu,
-	.put_fpu             = emulator_put_fpu,
 	.intercept           = emulator_intercept,
 	.get_cpuid           = emulator_get_cpuid,
 	.set_nmi_mask        = emulator_set_nmi_mask,
@@ -5430,7 +5431,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
 		vcpu->run->internal.ndata = 0;
-		r = EMULATE_FAIL;
+		r = EMULATE_USER_EXIT;
 	}
 	kvm_queue_exception(vcpu, UD_VECTOR);
 
@@ -5722,6 +5723,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
 						emulation_type))
 				return EMULATE_DONE;
+			if (ctxt->have_exception && inject_emulated_exception(vcpu))
+				return EMULATE_DONE;
 			if (emulation_type & EMULTYPE_SKIP)
 				return EMULATE_FAIL;
 			return handle_emulation_failure(vcpu);
@@ -6761,6 +6764,20 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->tlb_flush(vcpu);
 }
 
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+		unsigned long start, unsigned long end)
+{
+	unsigned long apic_address;
+
+	/*
+	 * The physical address of apic access page is stored in the VMCS.
+	 * Update it when it becomes invalid.
+	 */
+	apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	if (start <= apic_address && apic_address < end)
+		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
+}
+
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 {
 	struct page *page = NULL;
@@ -6935,7 +6952,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);
-	kvm_load_guest_fpu(vcpu);
 
 	/*
 	 * Disable IRQs before setting IN_GUEST_MODE.  Posted interrupt
@@ -7248,14 +7264,11 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
-	struct fpu *fpu = &current->thread.fpu;
 	int r;
-	sigset_t sigsaved;
 
-	fpu__initialize(fpu);
+	kvm_sigset_activate(vcpu);
 
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+	kvm_load_guest_fpu(vcpu);
 
 	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
 		if (kvm_run->immediate_exit) {
@@ -7297,9 +7310,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		r = vcpu_run(vcpu);
 
 out:
+	kvm_put_guest_fpu(vcpu);
 	post_kvm_run_save(vcpu);
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+	kvm_sigset_deactivate(vcpu);
 
 	return r;
 }
@@ -7367,7 +7380,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 #endif
 
 	kvm_rip_write(vcpu, regs->rip);
-	kvm_set_rflags(vcpu, regs->rflags);
+	kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED);
 
 	vcpu->arch.exception.pending = false;
 
@@ -7481,6 +7494,29 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
 }
 EXPORT_SYMBOL_GPL(kvm_task_switch);
 
+int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
+		/*
+		 * When EFER.LME and CR0.PG are set, the processor is in
+		 * 64-bit mode (though maybe in a 32-bit code segment).
+		 * CR4.PAE and EFER.LMA must be set.
+		 */
+		if (!(sregs->cr4 & X86_CR4_PAE)
+		    || !(sregs->efer & EFER_LMA))
+			return -EINVAL;
+	} else {
+		/*
+		 * Not in 64-bit mode: EFER.LMA is clear and the code
+		 * segment cannot be 64-bit.
+		 */
+		if (sregs->efer & EFER_LMA || sregs->cs.l)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
@@ -7493,6 +7529,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 			(sregs->cr4 & X86_CR4_OSXSAVE))
 		return -EINVAL;
 
+	if (kvm_valid_sregs(vcpu, sregs))
+		return -EINVAL;
+
 	apic_base_msr.data = sregs->apic_base;
 	apic_base_msr.host_initiated = true;
 	if (kvm_set_apic_base(vcpu, &apic_base_msr))
@@ -7690,32 +7729,25 @@ static void fx_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr0 |= X86_CR0_ET;
 }
 
+/* Swap (qemu) user FPU context for the guest FPU context. */
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->guest_fpu_loaded)
-		return;
-
-	/*
-	 * Restore all possible states in the guest,
-	 * and assume host would use all available bits.
-	 * Guest xcr0 would be loaded later.
-	 */
-	vcpu->guest_fpu_loaded = 1;
-	__kernel_fpu_begin();
+	preempt_disable();
+	copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
 				~XFEATURE_MASK_PKRU);
+	preempt_enable();
 	trace_kvm_fpu(1);
 }
 
+/* When vcpu_run ends, restore user space FPU context. */
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->guest_fpu_loaded)
-		return;
-
-	vcpu->guest_fpu_loaded = 0;
+	preempt_disable();
 	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
-	__kernel_fpu_end();
+	copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
+	preempt_enable();
 	++vcpu->stat.fpu_reload;
 	trace_kvm_fpu(0);
 }
@@ -7832,7 +7864,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		 * To avoid have the INIT path from kvm_apic_has_events() that be
 		 * called with loaded FPU and does not let userspace fix the state.
 		 */
-		kvm_put_guest_fpu(vcpu);
+		if (init_event)
+			kvm_put_guest_fpu(vcpu);
 		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu.state.xsave,
 					XFEATURE_MASK_BNDREGS);
 		if (mpx_state_buffer)
@@ -7841,6 +7874,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 					XFEATURE_MASK_BNDCSR);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
+		if (init_event)
+			kvm_load_guest_fpu(vcpu);
 	}
 
 	if (!init_event) {
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 7b181b61170e..91e9700cc6dc 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -26,6 +26,9 @@ lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
+lib-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
+lib-$(CONFIG_RETPOLINE) += retpoline.o
+OBJECT_FILES_NON_STANDARD_retpoline.o :=y
 
 obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
 
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 4d34bb548b41..46e71a74e612 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -29,7 +29,8 @@
 #include <asm/errno.h>
 #include <asm/asm.h>
 #include <asm/export.h>
-				
+#include <asm/nospec-branch.h>
+
 /*
  * computes a partial checksum, e.g. for TCP/UDP fragments
  */
@@ -156,7 +157,7 @@ ENTRY(csum_partial)
 	negl %ebx
 	lea 45f(%ebx,%ebx,2), %ebx
 	testl %esi, %esi
-	jmp *%ebx
+	JMP_NOSPEC %ebx
 
 	# Handle 2-byte-aligned regions
 20:	addw (%esi), %ax
@@ -439,7 +440,7 @@ ENTRY(csum_partial_copy_generic)
 	andl $-32,%edx
 	lea 3f(%ebx,%ebx), %ebx
 	testl %esi, %esi 
-	jmp *%ebx
+	JMP_NOSPEC %ebx
 1:	addl $64,%esi
 	addl $64,%edi 
 	SRC(movb -32(%edx),%bl)	; SRC(movb (%edx),%bl)
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 553f8fd23cc4..f5b7f1b3b6d7 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -107,10 +107,10 @@ static void delay_mwaitx(unsigned long __loops)
 		delay = min_t(u64, MWAITX_MAX_LOOPS, loops);
 
 		/*
-		 * Use cpu_tss as a cacheline-aligned, seldomly
+		 * Use cpu_tss_rw as a cacheline-aligned, seldomly
 		 * accessed per-cpu variable as the monitor target.
 		 */
-		__monitorx(raw_cpu_ptr(&cpu_tss), 0, 0);
+		__monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
 
 		/*
 		 * AMD, like Intel, supports the EAX hint and EAX=0xf
@@ -162,7 +162,7 @@ void __delay(unsigned long loops)
 }
 EXPORT_SYMBOL(__delay);
 
-inline void __const_udelay(unsigned long xloops)
+void __const_udelay(unsigned long xloops)
 {
 	unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy;
 	int d0;
diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c
new file mode 100644
index 000000000000..7b881d03d0dd
--- /dev/null
+++ b/arch/x86/lib/error-inject.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+
+asmlinkage void just_return_func(void);
+
+asm(
+	".type just_return_func, @function\n"
+	"just_return_func:\n"
+	"	ret\n"
+	".size just_return_func, .-just_return_func\n"
+);
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	regs->ip = (unsigned long)&just_return_func;
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
new file mode 100644
index 000000000000..480edc3a5e03
--- /dev/null
+++ b/arch/x86/lib/retpoline.S
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/stringify.h>
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative-asm.h>
+#include <asm/export.h>
+#include <asm/nospec-branch.h>
+#include <asm/bitsperlong.h>
+
+.macro THUNK reg
+	.section .text.__x86.indirect_thunk
+
+ENTRY(__x86_indirect_thunk_\reg)
+	CFI_STARTPROC
+	JMP_NOSPEC %\reg
+	CFI_ENDPROC
+ENDPROC(__x86_indirect_thunk_\reg)
+.endm
+
+/*
+ * Despite being an assembler file we can't just use .irp here
+ * because __KSYM_DEPS__ only uses the C preprocessor and would
+ * only see one instance of "__x86_indirect_thunk_\reg" rather
+ * than one per register with the correct names. So we do it
+ * the simple and nasty way...
+ */
+#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
+#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
+#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg)
+
+GENERATE_THUNK(_ASM_AX)
+GENERATE_THUNK(_ASM_BX)
+GENERATE_THUNK(_ASM_CX)
+GENERATE_THUNK(_ASM_DX)
+GENERATE_THUNK(_ASM_SI)
+GENERATE_THUNK(_ASM_DI)
+GENERATE_THUNK(_ASM_BP)
+#ifdef CONFIG_64BIT
+GENERATE_THUNK(r8)
+GENERATE_THUNK(r9)
+GENERATE_THUNK(r10)
+GENERATE_THUNK(r11)
+GENERATE_THUNK(r12)
+GENERATE_THUNK(r13)
+GENERATE_THUNK(r14)
+GENERATE_THUNK(r15)
+#endif
+
+/*
+ * Fill the CPU return stack buffer.
+ *
+ * Each entry in the RSB, if used for a speculative 'ret', contains an
+ * infinite 'pause; lfence; jmp' loop to capture speculative execution.
+ *
+ * This is required in various cases for retpoline and IBRS-based
+ * mitigations for the Spectre variant 2 vulnerability. Sometimes to
+ * eliminate potentially bogus entries from the RSB, and sometimes
+ * purely to ensure that it doesn't get empty, which on some CPUs would
+ * allow predictions from other (unwanted!) sources to be used.
+ *
+ * Google experimented with loop-unrolling and this turned out to be
+ * the optimal version - two calls, each with their own speculation
+ * trap should their return address end up getting used, in a loop.
+ */
+.macro STUFF_RSB nr:req sp:req
+	mov	$(\nr / 2), %_ASM_BX
+	.align 16
+771:
+	call	772f
+773:						/* speculation trap */
+	pause
+	lfence
+	jmp	773b
+	.align 16
+772:
+	call	774f
+775:						/* speculation trap */
+	pause
+	lfence
+	jmp	775b
+	.align 16
+774:
+	dec	%_ASM_BX
+	jnz	771b
+	add	$((BITS_PER_LONG/8) * \nr), \sp
+.endm
+
+#define RSB_FILL_LOOPS		16	/* To avoid underflow */
+
+ENTRY(__fill_rsb)
+	STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP
+	ret
+END(__fill_rsb)
+EXPORT_SYMBOL_GPL(__fill_rsb)
+
+#define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
+
+ENTRY(__clear_rsb)
+	STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP
+	ret
+END(__clear_rsb)
+EXPORT_SYMBOL_GPL(__clear_rsb)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index c4d55919fac1..e0b85930dd77 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
 fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
 fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
 fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
-ff:
+ff: UD0
 EndTable
 
 Table: 3-byte opcode 1 (0x0f 0x38)
@@ -717,7 +717,7 @@ AVXcode: 2
 7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
-81: INVPID Gy,Mdq (66)
+81: INVVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
 83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
 88: vexpandps/d Vpd,Wpd (66),(ev)
@@ -970,6 +970,15 @@ GrpTable: Grp9
 EndTable
 
 GrpTable: Grp10
+# all are UD1
+0: UD1
+1: UD1
+2: UD1
+3: UD1
+4: UD1
+5: UD1
+6: UD1
+7: UD1
 EndTable
 
 # Grp11A and Grp11B are expressed as Grp11 in Intel SDM
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 8e13b8cc6bed..27e9e90a8d35 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -10,7 +10,7 @@ CFLAGS_REMOVE_mem_encrypt.o	= -pg
 endif
 
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o
+	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o
 
 # Make sure __phys_addr has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
@@ -41,9 +41,10 @@ obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat.o
 obj-$(CONFIG_NUMA_EMU)		+= numa_emulation.o
 
-obj-$(CONFIG_X86_INTEL_MPX)	+= mpx.o
-obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o
-obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
+obj-$(CONFIG_X86_INTEL_MPX)			+= mpx.o
+obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS)	+= pkeys.o
+obj-$(CONFIG_RANDOMIZE_MEMORY)			+= kaslr.o
+obj-$(CONFIG_PAGE_TABLE_ISOLATION)		+= pti.o
 
 obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt.o
 obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt_boot.o
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
new file mode 100644
index 000000000000..b9283cc27622
--- /dev/null
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/spinlock.h>
+#include <linux/percpu.h>
+
+#include <asm/cpu_entry_area.h>
+#include <asm/pgtable.h>
+#include <asm/fixmap.h>
+#include <asm/desc.h>
+
+static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);
+
+#ifdef CONFIG_X86_64
+static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+#endif
+
+struct cpu_entry_area *get_cpu_entry_area(int cpu)
+{
+	unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE;
+	BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0);
+
+	return (struct cpu_entry_area *) va;
+}
+EXPORT_SYMBOL(get_cpu_entry_area);
+
+void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags)
+{
+	unsigned long va = (unsigned long) cea_vaddr;
+
+	set_pte_vaddr(va, pfn_pte(pa >> PAGE_SHIFT, flags));
+}
+
+static void __init
+cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
+{
+	for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE)
+		cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
+}
+
+static void percpu_setup_debug_store(int cpu)
+{
+#ifdef CONFIG_CPU_SUP_INTEL
+	int npages;
+	void *cea;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return;
+
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_store;
+	npages = sizeof(struct debug_store) / PAGE_SIZE;
+	BUILD_BUG_ON(sizeof(struct debug_store) % PAGE_SIZE != 0);
+	cea_map_percpu_pages(cea, &per_cpu(cpu_debug_store, cpu), npages,
+			     PAGE_KERNEL);
+
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers;
+	/*
+	 * Force the population of PMDs for not yet allocated per cpu
+	 * memory like debug store buffers.
+	 */
+	npages = sizeof(struct debug_store_buffers) / PAGE_SIZE;
+	for (; npages; npages--, cea += PAGE_SIZE)
+		cea_set_pte(cea, 0, PAGE_NONE);
+#endif
+}
+
+/* Setup the fixmap mappings only once per-processor */
+static void __init setup_cpu_entry_area(int cpu)
+{
+#ifdef CONFIG_X86_64
+	extern char _entry_trampoline[];
+
+	/* On 64-bit systems, we use a read-only fixmap GDT and TSS. */
+	pgprot_t gdt_prot = PAGE_KERNEL_RO;
+	pgprot_t tss_prot = PAGE_KERNEL_RO;
+#else
+	/*
+	 * On native 32-bit systems, the GDT cannot be read-only because
+	 * our double fault handler uses a task gate, and entering through
+	 * a task gate needs to change an available TSS to busy.  If the
+	 * GDT is read-only, that will triple fault.  The TSS cannot be
+	 * read-only because the CPU writes to it on task switches.
+	 *
+	 * On Xen PV, the GDT must be read-only because the hypervisor
+	 * requires it.
+	 */
+	pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ?
+		PAGE_KERNEL_RO : PAGE_KERNEL;
+	pgprot_t tss_prot = PAGE_KERNEL;
+#endif
+
+	cea_set_pte(&get_cpu_entry_area(cpu)->gdt, get_cpu_gdt_paddr(cpu),
+		    gdt_prot);
+
+	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->entry_stack_page,
+			     per_cpu_ptr(&entry_stack_storage, cpu), 1,
+			     PAGE_KERNEL);
+
+	/*
+	 * The Intel SDM says (Volume 3, 7.2.1):
+	 *
+	 *  Avoid placing a page boundary in the part of the TSS that the
+	 *  processor reads during a task switch (the first 104 bytes). The
+	 *  processor may not correctly perform address translations if a
+	 *  boundary occurs in this area. During a task switch, the processor
+	 *  reads and writes into the first 104 bytes of each TSS (using
+	 *  contiguous physical addresses beginning with the physical address
+	 *  of the first byte of the TSS). So, after TSS access begins, if
+	 *  part of the 104 bytes is not physically contiguous, the processor
+	 *  will access incorrect information without generating a page-fault
+	 *  exception.
+	 *
+	 * There are also a lot of errata involving the TSS spanning a page
+	 * boundary.  Assert that we're not doing that.
+	 */
+	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
+		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
+	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
+	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->tss,
+			     &per_cpu(cpu_tss_rw, cpu),
+			     sizeof(struct tss_struct) / PAGE_SIZE, tss_prot);
+
+#ifdef CONFIG_X86_32
+	per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu);
+#endif
+
+#ifdef CONFIG_X86_64
+	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
+	BUILD_BUG_ON(sizeof(exception_stacks) !=
+		     sizeof(((struct cpu_entry_area *)0)->exception_stacks));
+	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->exception_stacks,
+			     &per_cpu(exception_stacks, cpu),
+			     sizeof(exception_stacks) / PAGE_SIZE, PAGE_KERNEL);
+
+	cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline,
+		     __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
+#endif
+	percpu_setup_debug_store(cpu);
+}
+
+static __init void setup_cpu_entry_area_ptes(void)
+{
+#ifdef CONFIG_X86_32
+	unsigned long start, end;
+
+	BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE);
+	BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK);
+
+	start = CPU_ENTRY_AREA_BASE;
+	end = start + CPU_ENTRY_AREA_MAP_SIZE;
+
+	/* Careful here: start + PMD_SIZE might wrap around */
+	for (; start < end && start >= CPU_ENTRY_AREA_BASE; start += PMD_SIZE)
+		populate_extra_pte(start);
+#endif
+}
+
+void __init setup_cpu_entry_areas(void)
+{
+	unsigned int cpu;
+
+	setup_cpu_entry_area_ptes();
+
+	for_each_possible_cpu(cpu)
+		setup_cpu_entry_area(cpu);
+}
diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c
index bfcffdf6c577..421f2664ffa0 100644
--- a/arch/x86/mm/debug_pagetables.c
+++ b/arch/x86/mm/debug_pagetables.c
@@ -5,7 +5,7 @@
 
 static int ptdump_show(struct seq_file *m, void *v)
 {
-	ptdump_walk_pgd_level(m, NULL);
+	ptdump_walk_pgd_level_debugfs(m, NULL, false);
 	return 0;
 }
 
@@ -22,21 +22,89 @@ static const struct file_operations ptdump_fops = {
 	.release	= single_release,
 };
 
-static struct dentry *pe;
+static int ptdump_show_curknl(struct seq_file *m, void *v)
+{
+	if (current->mm->pgd) {
+		down_read(&current->mm->mmap_sem);
+		ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, false);
+		up_read(&current->mm->mmap_sem);
+	}
+	return 0;
+}
+
+static int ptdump_open_curknl(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, ptdump_show_curknl, NULL);
+}
+
+static const struct file_operations ptdump_curknl_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ptdump_open_curknl,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+static struct dentry *pe_curusr;
+
+static int ptdump_show_curusr(struct seq_file *m, void *v)
+{
+	if (current->mm->pgd) {
+		down_read(&current->mm->mmap_sem);
+		ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, true);
+		up_read(&current->mm->mmap_sem);
+	}
+	return 0;
+}
+
+static int ptdump_open_curusr(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, ptdump_show_curusr, NULL);
+}
+
+static const struct file_operations ptdump_curusr_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ptdump_open_curusr,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+#endif
+
+static struct dentry *dir, *pe_knl, *pe_curknl;
 
 static int __init pt_dump_debug_init(void)
 {
-	pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL,
-				 &ptdump_fops);
-	if (!pe)
+	dir = debugfs_create_dir("page_tables", NULL);
+	if (!dir)
 		return -ENOMEM;
 
+	pe_knl = debugfs_create_file("kernel", 0400, dir, NULL,
+				     &ptdump_fops);
+	if (!pe_knl)
+		goto err;
+
+	pe_curknl = debugfs_create_file("current_kernel", 0400,
+					dir, NULL, &ptdump_curknl_fops);
+	if (!pe_curknl)
+		goto err;
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pe_curusr = debugfs_create_file("current_user", 0400,
+					dir, NULL, &ptdump_curusr_fops);
+	if (!pe_curusr)
+		goto err;
+#endif
 	return 0;
+err:
+	debugfs_remove_recursive(dir);
+	return -ENOMEM;
 }
 
 static void __exit pt_dump_debug_exit(void)
 {
-	debugfs_remove_recursive(pe);
+	debugfs_remove_recursive(dir);
 }
 
 module_init(pt_dump_debug_init);
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 5e3ac6fe6c9e..2a4849e92831 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -44,68 +44,97 @@ struct addr_marker {
 	unsigned long max_lines;
 };
 
-/* indices for address_markers; keep sync'd w/ address_markers below */
+/* Address space markers hints */
+
+#ifdef CONFIG_X86_64
+
 enum address_markers_idx {
 	USER_SPACE_NR = 0,
-#ifdef CONFIG_X86_64
 	KERNEL_SPACE_NR,
 	LOW_KERNEL_NR,
+#if defined(CONFIG_MODIFY_LDT_SYSCALL) && defined(CONFIG_X86_5LEVEL)
+	LDT_NR,
+#endif
 	VMALLOC_START_NR,
 	VMEMMAP_START_NR,
 #ifdef CONFIG_KASAN
 	KASAN_SHADOW_START_NR,
 	KASAN_SHADOW_END_NR,
 #endif
-# ifdef CONFIG_X86_ESPFIX64
+	CPU_ENTRY_AREA_NR,
+#if defined(CONFIG_MODIFY_LDT_SYSCALL) && !defined(CONFIG_X86_5LEVEL)
+	LDT_NR,
+#endif
+#ifdef CONFIG_X86_ESPFIX64
 	ESPFIX_START_NR,
-# endif
+#endif
+#ifdef CONFIG_EFI
+	EFI_END_NR,
+#endif
 	HIGH_KERNEL_NR,
 	MODULES_VADDR_NR,
 	MODULES_END_NR,
-#else
+	FIXADDR_START_NR,
+	END_OF_SPACE_NR,
+};
+
+static struct addr_marker address_markers[] = {
+	[USER_SPACE_NR]		= { 0,			"User Space" },
+	[KERNEL_SPACE_NR]	= { (1UL << 63),	"Kernel Space" },
+	[LOW_KERNEL_NR]		= { 0UL,		"Low Kernel Mapping" },
+	[VMALLOC_START_NR]	= { 0UL,		"vmalloc() Area" },
+	[VMEMMAP_START_NR]	= { 0UL,		"Vmemmap" },
+#ifdef CONFIG_KASAN
+	[KASAN_SHADOW_START_NR]	= { KASAN_SHADOW_START,	"KASAN shadow" },
+	[KASAN_SHADOW_END_NR]	= { KASAN_SHADOW_END,	"KASAN shadow end" },
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	[LDT_NR]		= { LDT_BASE_ADDR,	"LDT remap" },
+#endif
+	[CPU_ENTRY_AREA_NR]	= { CPU_ENTRY_AREA_BASE,"CPU entry Area" },
+#ifdef CONFIG_X86_ESPFIX64
+	[ESPFIX_START_NR]	= { ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
+#endif
+#ifdef CONFIG_EFI
+	[EFI_END_NR]		= { EFI_VA_END,		"EFI Runtime Services" },
+#endif
+	[HIGH_KERNEL_NR]	= { __START_KERNEL_map,	"High Kernel Mapping" },
+	[MODULES_VADDR_NR]	= { MODULES_VADDR,	"Modules" },
+	[MODULES_END_NR]	= { MODULES_END,	"End Modules" },
+	[FIXADDR_START_NR]	= { FIXADDR_START,	"Fixmap Area" },
+	[END_OF_SPACE_NR]	= { -1,			NULL }
+};
+
+#else /* CONFIG_X86_64 */
+
+enum address_markers_idx {
+	USER_SPACE_NR = 0,
 	KERNEL_SPACE_NR,
 	VMALLOC_START_NR,
 	VMALLOC_END_NR,
-# ifdef CONFIG_HIGHMEM
+#ifdef CONFIG_HIGHMEM
 	PKMAP_BASE_NR,
-# endif
-	FIXADDR_START_NR,
 #endif
+	CPU_ENTRY_AREA_NR,
+	FIXADDR_START_NR,
+	END_OF_SPACE_NR,
 };
 
-/* Address space markers hints */
 static struct addr_marker address_markers[] = {
-	{ 0, "User Space" },
-#ifdef CONFIG_X86_64
-	{ 0x8000000000000000UL, "Kernel Space" },
-	{ 0/* PAGE_OFFSET */,   "Low Kernel Mapping" },
-	{ 0/* VMALLOC_START */, "vmalloc() Area" },
-	{ 0/* VMEMMAP_START */, "Vmemmap" },
-#ifdef CONFIG_KASAN
-	{ KASAN_SHADOW_START,	"KASAN shadow" },
-	{ KASAN_SHADOW_END,	"KASAN shadow end" },
+	[USER_SPACE_NR]		= { 0,			"User Space" },
+	[KERNEL_SPACE_NR]	= { PAGE_OFFSET,	"Kernel Mapping" },
+	[VMALLOC_START_NR]	= { 0UL,		"vmalloc() Area" },
+	[VMALLOC_END_NR]	= { 0UL,		"vmalloc() End" },
+#ifdef CONFIG_HIGHMEM
+	[PKMAP_BASE_NR]		= { 0UL,		"Persistent kmap() Area" },
 #endif
-# ifdef CONFIG_X86_ESPFIX64
-	{ ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
-# endif
-# ifdef CONFIG_EFI
-	{ EFI_VA_END,		"EFI Runtime Services" },
-# endif
-	{ __START_KERNEL_map,   "High Kernel Mapping" },
-	{ MODULES_VADDR,        "Modules" },
-	{ MODULES_END,          "End Modules" },
-#else
-	{ PAGE_OFFSET,          "Kernel Mapping" },
-	{ 0/* VMALLOC_START */, "vmalloc() Area" },
-	{ 0/*VMALLOC_END*/,     "vmalloc() End" },
-# ifdef CONFIG_HIGHMEM
-	{ 0/*PKMAP_BASE*/,      "Persistent kmap() Area" },
-# endif
-	{ 0/*FIXADDR_START*/,   "Fixmap Area" },
-#endif
-	{ -1, NULL }		/* End of list */
+	[CPU_ENTRY_AREA_NR]	= { 0UL,		"CPU entry area" },
+	[FIXADDR_START_NR]	= { 0UL,		"Fixmap area" },
+	[END_OF_SPACE_NR]	= { -1,			NULL }
 };
 
+#endif /* !CONFIG_X86_64 */
+
 /* Multipliers for offsets within the PTEs */
 #define PTE_LEVEL_MULT (PAGE_SIZE)
 #define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT)
@@ -140,7 +169,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
 	static const char * const level_name[] =
 		{ "cr3", "pgd", "p4d", "pud", "pmd", "pte" };
 
-	if (!pgprot_val(prot)) {
+	if (!(pr & _PAGE_PRESENT)) {
 		/* Not present */
 		pt_dump_cont_printf(m, dmsg, "                              ");
 	} else {
@@ -447,7 +476,7 @@ static inline bool is_hypervisor_range(int idx)
 }
 
 static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
-				       bool checkwx)
+				       bool checkwx, bool dmesg)
 {
 #ifdef CONFIG_X86_64
 	pgd_t *start = (pgd_t *) &init_top_pgt;
@@ -460,7 +489,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 
 	if (pgd) {
 		start = pgd;
-		st.to_dmesg = true;
+		st.to_dmesg = dmesg;
 	}
 
 	st.check_wx = checkwx;
@@ -498,13 +527,37 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
 {
-	ptdump_walk_pgd_level_core(m, pgd, false);
+	ptdump_walk_pgd_level_core(m, pgd, false, true);
+}
+
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	if (user && static_cpu_has(X86_FEATURE_PTI))
+		pgd = kernel_to_user_pgdp(pgd);
+#endif
+	ptdump_walk_pgd_level_core(m, pgd, false, false);
+}
+EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
+
+static void ptdump_walk_user_pgd_level_checkwx(void)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pgd_t *pgd = (pgd_t *) &init_top_pgt;
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	pr_info("x86/mm: Checking user space page tables\n");
+	pgd = kernel_to_user_pgdp(pgd);
+	ptdump_walk_pgd_level_core(NULL, pgd, true, false);
+#endif
 }
-EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level);
 
 void ptdump_walk_pgd_level_checkwx(void)
 {
-	ptdump_walk_pgd_level_core(NULL, NULL, true);
+	ptdump_walk_pgd_level_core(NULL, NULL, true, false);
+	ptdump_walk_user_pgd_level_checkwx();
 }
 
 static int __init pt_dump_init(void)
@@ -525,8 +578,8 @@ static int __init pt_dump_init(void)
 	address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE;
 # endif
 	address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
+	address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE;
 #endif
-
 	return 0;
 }
 __initcall(pt_dump_init);
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 3321b446b66c..45f5d6cf65ae 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -1,6 +1,7 @@
 #include <linux/extable.h>
 #include <linux/uaccess.h>
 #include <linux/sched/debug.h>
+#include <xen/xen.h>
 
 #include <asm/fpu/internal.h>
 #include <asm/traps.h>
@@ -20,16 +21,16 @@ ex_fixup_handler(const struct exception_table_entry *x)
 	return (ex_handler_t)((unsigned long)&x->handler + x->handler);
 }
 
-bool ex_handler_default(const struct exception_table_entry *fixup,
-		       struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_default(const struct exception_table_entry *fixup,
+				  struct pt_regs *regs, int trapnr)
 {
 	regs->ip = ex_fixup_addr(fixup);
 	return true;
 }
 EXPORT_SYMBOL(ex_handler_default);
 
-bool ex_handler_fault(const struct exception_table_entry *fixup,
-		     struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_fault(const struct exception_table_entry *fixup,
+				struct pt_regs *regs, int trapnr)
 {
 	regs->ip = ex_fixup_addr(fixup);
 	regs->ax = trapnr;
@@ -41,8 +42,8 @@ EXPORT_SYMBOL_GPL(ex_handler_fault);
  * Handler for UD0 exception following a failed test against the
  * result of a refcount inc/dec/add/sub.
  */
-bool ex_handler_refcount(const struct exception_table_entry *fixup,
-			 struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_refcount(const struct exception_table_entry *fixup,
+				   struct pt_regs *regs, int trapnr)
 {
 	/* First unconditionally saturate the refcount. */
 	*(int *)regs->cx = INT_MIN / 2;
@@ -82,7 +83,7 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup,
 
 	return true;
 }
-EXPORT_SYMBOL_GPL(ex_handler_refcount);
+EXPORT_SYMBOL(ex_handler_refcount);
 
 /*
  * Handler for when we fail to restore a task's FPU state.  We should never get
@@ -94,8 +95,8 @@ EXPORT_SYMBOL_GPL(ex_handler_refcount);
  * of vulnerability by restoring from the initial state (essentially, zeroing
  * out all the FPU registers) if we can't restore from the task's FPU state.
  */
-bool ex_handler_fprestore(const struct exception_table_entry *fixup,
-			  struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
+				    struct pt_regs *regs, int trapnr)
 {
 	regs->ip = ex_fixup_addr(fixup);
 
@@ -107,8 +108,8 @@ bool ex_handler_fprestore(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL_GPL(ex_handler_fprestore);
 
-bool ex_handler_ext(const struct exception_table_entry *fixup,
-		   struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_ext(const struct exception_table_entry *fixup,
+			      struct pt_regs *regs, int trapnr)
 {
 	/* Special hack for uaccess_err */
 	current->thread.uaccess_err = 1;
@@ -117,8 +118,8 @@ bool ex_handler_ext(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL(ex_handler_ext);
 
-bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
-			     struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
+				       struct pt_regs *regs, int trapnr)
 {
 	if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pF)\n",
 			 (unsigned int)regs->cx, regs->ip, (void *)regs->ip))
@@ -132,8 +133,8 @@ bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL(ex_handler_rdmsr_unsafe);
 
-bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
-			     struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
+				       struct pt_regs *regs, int trapnr)
 {
 	if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pF)\n",
 			 (unsigned int)regs->cx, (unsigned int)regs->dx,
@@ -146,8 +147,8 @@ bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL(ex_handler_wrmsr_unsafe);
 
-bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
-			 struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
+				   struct pt_regs *regs, int trapnr)
 {
 	if (static_cpu_has(X86_BUG_NULL_SEG))
 		asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS));
@@ -156,7 +157,7 @@ bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL(ex_handler_clear_fs);
 
-bool ex_has_fault_handler(unsigned long ip)
+__visible bool ex_has_fault_handler(unsigned long ip)
 {
 	const struct exception_table_entry *e;
 	ex_handler_t handler;
@@ -212,8 +213,9 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
 	 * Old CPUs leave the high bits of CS on the stack
 	 * undefined.  I'm not sure which CPUs do this, but at least
 	 * the 486 DX works this way.
+	 * Xen pv domains are not using the default __KERNEL_CS.
 	 */
-	if (regs->cs != __KERNEL_CS)
+	if (!xen_pv_domain() && regs->cs != __KERNEL_CS)
 		goto fail;
 
 	/*
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 78ca9a8ee454..800de815519c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -172,14 +172,15 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
  * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
  *	     faulted on a pte with its pkey=4.
  */
-static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
+static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info,
+		u32 *pkey)
 {
 	/* This is effectively an #ifdef */
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))
 		return;
 
 	/* Fault not from Protection Keys: nothing to do */
-	if (si_code != SEGV_PKUERR)
+	if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV))
 		return;
 	/*
 	 * force_sig_info_fault() is called from a number of
@@ -218,7 +219,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
 		lsb = PAGE_SHIFT;
 	info.si_addr_lsb = lsb;
 
-	fill_sig_info_pkey(si_code, &info, pkey);
+	fill_sig_info_pkey(si_signo, si_code, &info, pkey);
 
 	force_sig_info(si_signo, &info, tsk);
 }
@@ -438,18 +439,13 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pgd_none(*pgd_ref))
 		return -1;
 
-	if (pgd_none(*pgd)) {
-		set_pgd(pgd, *pgd_ref);
-		arch_flush_lazy_mmu_mode();
-	} else if (CONFIG_PGTABLE_LEVELS > 4) {
-		/*
-		 * With folded p4d, pgd_none() is always false, so the pgd may
-		 * point to an empty page table entry and pgd_page_vaddr()
-		 * will return garbage.
-		 *
-		 * We will do the correct sanity check on the p4d level.
-		 */
-		BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+	if (CONFIG_PGTABLE_LEVELS > 4) {
+		if (pgd_none(*pgd)) {
+			set_pgd(pgd, *pgd_ref);
+			arch_flush_lazy_mmu_mode();
+		} else {
+			BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+		}
 	}
 
 	/* With 4-level paging, copying happens on the p4d level. */
@@ -458,7 +454,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (p4d_none(*p4d_ref))
 		return -1;
 
-	if (p4d_none(*p4d)) {
+	if (p4d_none(*p4d) && CONFIG_PGTABLE_LEVELS == 4) {
 		set_p4d(p4d, *p4d_ref);
 		arch_flush_lazy_mmu_mode();
 	} else {
@@ -469,6 +465,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	 * Below here mismatches are bugs because these lower tables
 	 * are shared:
 	 */
+	BUILD_BUG_ON(CONFIG_PGTABLE_LEVELS < 4);
 
 	pud = pud_offset(p4d, address);
 	pud_ref = pud_offset(p4d_ref, address);
@@ -701,7 +698,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 	else
 		printk(KERN_CONT "paging request");
 
-	printk(KERN_CONT " at %p\n", (void *) address);
+	printk(KERN_CONT " at %px\n", (void *) address);
 	printk(KERN_ALERT "IP: %pS\n", (void *)regs->ip);
 
 	dump_pagetable(address);
@@ -860,7 +857,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 	if (!printk_ratelimit())
 		return;
 
-	printk("%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
+	printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx",
 		task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 		tsk->comm, task_pid_nr(tsk), address,
 		(void *)regs->ip, (void *)regs->sp, error_code);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 6fdf91ef130a..82f5252c723a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -20,6 +20,7 @@
 #include <asm/kaslr.h>
 #include <asm/hypervisor.h>
 #include <asm/cpufeature.h>
+#include <asm/pti.h>
 
 /*
  * We need to define the tracepoints somewhere, and tlb.c
@@ -160,6 +161,12 @@ struct map_range {
 
 static int page_size_mask;
 
+static void enable_global_pages(void)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		__supported_pte_mask |= _PAGE_GLOBAL;
+}
+
 static void __init probe_page_size_mask(void)
 {
 	/*
@@ -177,11 +184,11 @@ static void __init probe_page_size_mask(void)
 		cr4_set_bits_and_update_boot(X86_CR4_PSE);
 
 	/* Enable PGE if available */
+	__supported_pte_mask &= ~_PAGE_GLOBAL;
 	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		cr4_set_bits_and_update_boot(X86_CR4_PGE);
-		__supported_pte_mask |= _PAGE_GLOBAL;
-	} else
-		__supported_pte_mask &= ~_PAGE_GLOBAL;
+		enable_global_pages();
+	}
 
 	/* Enable 1 GB linear kernel mappings if available: */
 	if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) {
@@ -194,34 +201,44 @@ static void __init probe_page_size_mask(void)
 
 static void setup_pcid(void)
 {
-#ifdef CONFIG_X86_64
-	if (boot_cpu_has(X86_FEATURE_PCID)) {
-		if (boot_cpu_has(X86_FEATURE_PGE)) {
-			/*
-			 * This can't be cr4_set_bits_and_update_boot() --
-			 * the trampoline code can't handle CR4.PCIDE and
-			 * it wouldn't do any good anyway.  Despite the name,
-			 * cr4_set_bits_and_update_boot() doesn't actually
-			 * cause the bits in question to remain set all the
-			 * way through the secondary boot asm.
-			 *
-			 * Instead, we brute-force it and set CR4.PCIDE
-			 * manually in start_secondary().
-			 */
-			cr4_set_bits(X86_CR4_PCIDE);
-		} else {
-			/*
-			 * flush_tlb_all(), as currently implemented, won't
-			 * work if PCID is on but PGE is not.  Since that
-			 * combination doesn't exist on real hardware, there's
-			 * no reason to try to fully support it, but it's
-			 * polite to avoid corrupting data if we're on
-			 * an improperly configured VM.
-			 */
-			setup_clear_cpu_cap(X86_FEATURE_PCID);
-		}
+	if (!IS_ENABLED(CONFIG_X86_64))
+		return;
+
+	if (!boot_cpu_has(X86_FEATURE_PCID))
+		return;
+
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
+		/*
+		 * This can't be cr4_set_bits_and_update_boot() -- the
+		 * trampoline code can't handle CR4.PCIDE and it wouldn't
+		 * do any good anyway.  Despite the name,
+		 * cr4_set_bits_and_update_boot() doesn't actually cause
+		 * the bits in question to remain set all the way through
+		 * the secondary boot asm.
+		 *
+		 * Instead, we brute-force it and set CR4.PCIDE manually in
+		 * start_secondary().
+		 */
+		cr4_set_bits(X86_CR4_PCIDE);
+
+		/*
+		 * INVPCID's single-context modes (2/3) only work if we set
+		 * X86_CR4_PCIDE, *and* we INVPCID support.  It's unusable
+		 * on systems that have X86_CR4_PCIDE clear, or that have
+		 * no INVPCID support at all.
+		 */
+		if (boot_cpu_has(X86_FEATURE_INVPCID))
+			setup_force_cpu_cap(X86_FEATURE_INVPCID_SINGLE);
+	} else {
+		/*
+		 * flush_tlb_all(), as currently implemented, won't work if
+		 * PCID is on but PGE is not.  Since that combination
+		 * doesn't exist on real hardware, there's no reason to try
+		 * to fully support it, but it's polite to avoid corrupting
+		 * data if we're on an improperly configured VM.
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_PCID);
 	}
-#endif
 }
 
 #ifdef CONFIG_X86_32
@@ -622,6 +639,7 @@ void __init init_mem_mapping(void)
 {
 	unsigned long end;
 
+	pti_check_boottime_disable();
 	probe_page_size_mask();
 	setup_pcid();
 
@@ -845,12 +863,12 @@ void __init zone_sizes_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
-DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
+__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
 	.loaded_mm = &init_mm,
 	.next_asid = 1,
 	.cr4 = ~0UL,	/* fail hard if we screw up cr4 shadow initialization */
 };
-EXPORT_SYMBOL_GPL(cpu_tlbstate);
+EXPORT_PER_CPU_SYMBOL(cpu_tlbstate);
 
 void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
 {
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8a64a6f2848d..135c9a7898c7 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -50,6 +50,7 @@
 #include <asm/setup.h>
 #include <asm/set_memory.h>
 #include <asm/page_types.h>
+#include <asm/cpu_entry_area.h>
 #include <asm/init.h>
 
 #include "mm_internal.h"
@@ -766,6 +767,7 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 	printk(KERN_INFO "virtual kernel memory layout:\n"
 		"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
+		"  cpu_entry : 0x%08lx - 0x%08lx   (%4ld kB)\n"
 #ifdef CONFIG_HIGHMEM
 		"    pkmap   : 0x%08lx - 0x%08lx   (%4ld kB)\n"
 #endif
@@ -777,6 +779,10 @@ void __init mem_init(void)
 		FIXADDR_START, FIXADDR_TOP,
 		(FIXADDR_TOP - FIXADDR_START) >> 10,
 
+		CPU_ENTRY_AREA_BASE,
+		CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE,
+		CPU_ENTRY_AREA_MAP_SIZE >> 10,
+
 #ifdef CONFIG_HIGHMEM
 		PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
 		(LAST_PKMAP*PAGE_SIZE) >> 10,
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 6e4573b1da34..c45b6ec5357b 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -404,11 +404,11 @@ void iounmap(volatile void __iomem *addr)
 		return;
 	}
 
+	mmiotrace_iounmap(addr);
+
 	addr = (volatile void __iomem *)
 		(PAGE_MASK & (unsigned long __force)addr);
 
-	mmiotrace_iounmap(addr);
-
 	/* Use the vm area unlocked, assuming the caller
 	   ensures there isn't another iounmap for the same address
 	   in parallel. Reuse of the virtual address is prevented by
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 99dfed6dfef8..af6f2f9c6a26 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -15,15 +15,20 @@
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
+#include <asm/cpu_entry_area.h>
 
 extern struct range pfn_mapped[E820_MAX_ENTRIES];
 
 static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
 
-static __init void *early_alloc(size_t size, int nid)
+static __init void *early_alloc(size_t size, int nid, bool panic)
 {
-	return memblock_virt_alloc_try_nid_nopanic(size, size,
-		__pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
+	if (panic)
+		return memblock_virt_alloc_try_nid(size, size,
+			__pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
+	else
+		return memblock_virt_alloc_try_nid_nopanic(size, size,
+			__pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
 }
 
 static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
@@ -37,14 +42,14 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
 		if (boot_cpu_has(X86_FEATURE_PSE) &&
 		    ((end - addr) == PMD_SIZE) &&
 		    IS_ALIGNED(addr, PMD_SIZE)) {
-			p = early_alloc(PMD_SIZE, nid);
+			p = early_alloc(PMD_SIZE, nid, false);
 			if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
 				return;
 			else if (p)
 				memblock_free(__pa(p), PMD_SIZE);
 		}
 
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		pmd_populate_kernel(&init_mm, pmd, p);
 	}
 
@@ -56,7 +61,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
 		if (!pte_none(*pte))
 			continue;
 
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL);
 		set_pte_at(&init_mm, addr, pte, entry);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
@@ -74,14 +79,14 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
 		if (boot_cpu_has(X86_FEATURE_GBPAGES) &&
 		    ((end - addr) == PUD_SIZE) &&
 		    IS_ALIGNED(addr, PUD_SIZE)) {
-			p = early_alloc(PUD_SIZE, nid);
+			p = early_alloc(PUD_SIZE, nid, false);
 			if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL))
 				return;
 			else if (p)
 				memblock_free(__pa(p), PUD_SIZE);
 		}
 
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		pud_populate(&init_mm, pud, p);
 	}
 
@@ -100,7 +105,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr,
 	unsigned long next;
 
 	if (p4d_none(*p4d)) {
-		void *p = early_alloc(PAGE_SIZE, nid);
+		void *p = early_alloc(PAGE_SIZE, nid, true);
 
 		p4d_populate(&init_mm, p4d, p);
 	}
@@ -121,7 +126,7 @@ static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr,
 	unsigned long next;
 
 	if (pgd_none(*pgd)) {
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		pgd_populate(&init_mm, pgd, p);
 	}
 
@@ -277,6 +282,7 @@ void __init kasan_early_init(void)
 void __init kasan_init(void)
 {
 	int i;
+	void *shadow_cpu_entry_begin, *shadow_cpu_entry_end;
 
 #ifdef CONFIG_KASAN_INLINE
 	register_die_notifier(&kasan_die_notifier);
@@ -321,16 +327,33 @@ void __init kasan_init(void)
 		map_range(&pfn_mapped[i]);
 	}
 
+	shadow_cpu_entry_begin = (void *)CPU_ENTRY_AREA_BASE;
+	shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin);
+	shadow_cpu_entry_begin = (void *)round_down((unsigned long)shadow_cpu_entry_begin,
+						PAGE_SIZE);
+
+	shadow_cpu_entry_end = (void *)(CPU_ENTRY_AREA_BASE +
+					CPU_ENTRY_AREA_MAP_SIZE);
+	shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end);
+	shadow_cpu_entry_end = (void *)round_up((unsigned long)shadow_cpu_entry_end,
+					PAGE_SIZE);
+
 	kasan_populate_zero_shadow(
 		kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
-		kasan_mem_to_shadow((void *)__START_KERNEL_map));
+		shadow_cpu_entry_begin);
+
+	kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin,
+			      (unsigned long)shadow_cpu_entry_end, 0);
+
+	kasan_populate_zero_shadow(shadow_cpu_entry_end,
+				kasan_mem_to_shadow((void *)__START_KERNEL_map));
 
 	kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext),
 			      (unsigned long)kasan_mem_to_shadow(_end),
 			      early_pfn_to_nid(__pa(_stext)));
 
 	kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
-			(void *)KASAN_SHADOW_END);
+				(void *)KASAN_SHADOW_END);
 
 	load_cr3(init_top_pgt);
 	__flush_tlb_all();
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 879ef930e2c2..aedebd2ebf1e 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -34,25 +34,14 @@
 #define TB_SHIFT 40
 
 /*
- * Virtual address start and end range for randomization. The end changes base
- * on configuration to have the highest amount of space for randomization.
- * It increases the possible random position for each randomized region.
+ * Virtual address start and end range for randomization.
  *
- * You need to add an if/def entry if you introduce a new memory region
- * compatible with KASLR. Your entry must be in logical order with memory
- * layout. For example, ESPFIX is before EFI because its virtual address is
- * before. You also need to add a BUILD_BUG_ON() in kernel_randomize_memory() to
- * ensure that this order is correct and won't be changed.
+ * The end address could depend on more configuration options to make the
+ * highest amount of space for randomization available, but that's too hard
+ * to keep straight and caused issues already.
  */
 static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
-
-#if defined(CONFIG_X86_ESPFIX64)
-static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
-#elif defined(CONFIG_EFI)
-static const unsigned long vaddr_end = EFI_VA_END;
-#else
-static const unsigned long vaddr_end = __START_KERNEL_map;
-#endif
+static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE;
 
 /* Default values */
 unsigned long page_offset_base = __PAGE_OFFSET_BASE;
@@ -101,15 +90,12 @@ void __init kernel_randomize_memory(void)
 	unsigned long remain_entropy;
 
 	/*
-	 * All these BUILD_BUG_ON checks ensures the memory layout is
-	 * consistent with the vaddr_start/vaddr_end variables.
+	 * These BUILD_BUG_ON checks ensure the memory layout is consistent
+	 * with the vaddr_start/vaddr_end variables. These checks are very
+	 * limited....
 	 */
 	BUILD_BUG_ON(vaddr_start >= vaddr_end);
-	BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) &&
-		     vaddr_end >= EFI_VA_END);
-	BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) ||
-		      IS_ENABLED(CONFIG_EFI)) &&
-		     vaddr_end >= __START_KERNEL_map);
+	BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE);
 	BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
 
 	if (!kaslr_memory_enabled())
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/error.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/error.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/opcode.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/opcode.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/pte.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/pte.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/selftest.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/selftest.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/shadow.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index c21c2ed04612..58477ec3d66d 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -435,17 +435,18 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	unsigned long flags;
 	int ret = 0;
 	unsigned long size = 0;
+	unsigned long addr = p->addr & PAGE_MASK;
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
 	unsigned int l;
 	pte_t *pte;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
-	if (get_kmmio_probe(p->addr)) {
+	if (get_kmmio_probe(addr)) {
 		ret = -EEXIST;
 		goto out;
 	}
 
-	pte = lookup_address(p->addr, &l);
+	pte = lookup_address(addr, &l);
 	if (!pte) {
 		ret = -EINVAL;
 		goto out;
@@ -454,7 +455,7 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	kmmio_count++;
 	list_add_rcu(&p->list, &kmmio_probes);
 	while (size < size_lim) {
-		if (add_kmmio_fault_page(p->addr + size))
+		if (add_kmmio_fault_page(addr + size))
 			pr_err("Unable to set page fault.\n");
 		size += page_level_size(l);
 	}
@@ -528,19 +529,20 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 {
 	unsigned long flags;
 	unsigned long size = 0;
+	unsigned long addr = p->addr & PAGE_MASK;
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
 	struct kmmio_fault_page *release_list = NULL;
 	struct kmmio_delayed_release *drelease;
 	unsigned int l;
 	pte_t *pte;
 
-	pte = lookup_address(p->addr, &l);
+	pte = lookup_address(addr, &l);
 	if (!pte)
 		return;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
 	while (size < size_lim) {
-		release_kmmio_fault_page(p->addr + size, &release_list);
+		release_kmmio_fault_page(addr + size, &release_list);
 		size += page_level_size(l);
 	}
 	list_del_rcu(&p->list);
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index d9a9e9fc75dd..1a53071e2e17 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -15,7 +15,7 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <linux/mm.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/swiotlb.h>
 #include <linux/mem_encrypt.h>
 
@@ -405,13 +405,13 @@ bool sme_active(void)
 {
 	return sme_me_mask && !sev_enabled;
 }
-EXPORT_SYMBOL_GPL(sme_active);
+EXPORT_SYMBOL(sme_active);
 
 bool sev_active(void)
 {
 	return sme_me_mask && sev_enabled;
 }
-EXPORT_SYMBOL_GPL(sev_active);
+EXPORT_SYMBOL(sev_active);
 
 static const struct dma_map_ops sev_dma_ops = {
 	.alloc                  = sev_alloc,
@@ -464,37 +464,62 @@ void swiotlb_set_mem_attributes(void *vaddr, unsigned long size)
 	set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT);
 }
 
-static void __init sme_clear_pgd(pgd_t *pgd_base, unsigned long start,
-				 unsigned long end)
+struct sme_populate_pgd_data {
+	void	*pgtable_area;
+	pgd_t	*pgd;
+
+	pmdval_t pmd_flags;
+	pteval_t pte_flags;
+	unsigned long paddr;
+
+	unsigned long vaddr;
+	unsigned long vaddr_end;
+};
+
+static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
 {
 	unsigned long pgd_start, pgd_end, pgd_size;
 	pgd_t *pgd_p;
 
-	pgd_start = start & PGDIR_MASK;
-	pgd_end = end & PGDIR_MASK;
+	pgd_start = ppd->vaddr & PGDIR_MASK;
+	pgd_end = ppd->vaddr_end & PGDIR_MASK;
 
-	pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1);
-	pgd_size *= sizeof(pgd_t);
+	pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t);
 
-	pgd_p = pgd_base + pgd_index(start);
+	pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
 
 	memset(pgd_p, 0, pgd_size);
 }
 
-#define PGD_FLAGS	_KERNPG_TABLE_NOENC
-#define P4D_FLAGS	_KERNPG_TABLE_NOENC
-#define PUD_FLAGS	_KERNPG_TABLE_NOENC
-#define PMD_FLAGS	(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
+#define PGD_FLAGS		_KERNPG_TABLE_NOENC
+#define P4D_FLAGS		_KERNPG_TABLE_NOENC
+#define PUD_FLAGS		_KERNPG_TABLE_NOENC
+#define PMD_FLAGS		_KERNPG_TABLE_NOENC
+
+#define PMD_FLAGS_LARGE		(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
+
+#define PMD_FLAGS_DEC		PMD_FLAGS_LARGE
+#define PMD_FLAGS_DEC_WP	((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
+				 (_PAGE_PAT | _PAGE_PWT))
+
+#define PMD_FLAGS_ENC		(PMD_FLAGS_LARGE | _PAGE_ENC)
+
+#define PTE_FLAGS		(__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL)
+
+#define PTE_FLAGS_DEC		PTE_FLAGS
+#define PTE_FLAGS_DEC_WP	((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
+				 (_PAGE_PAT | _PAGE_PWT))
+
+#define PTE_FLAGS_ENC		(PTE_FLAGS | _PAGE_ENC)
 
-static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
-				     unsigned long vaddr, pmdval_t pmd_val)
+static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
 {
 	pgd_t *pgd_p;
 	p4d_t *p4d_p;
 	pud_t *pud_p;
 	pmd_t *pmd_p;
 
-	pgd_p = pgd_base + pgd_index(vaddr);
+	pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
 	if (native_pgd_val(*pgd_p)) {
 		if (IS_ENABLED(CONFIG_X86_5LEVEL))
 			p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK);
@@ -504,15 +529,15 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
 		pgd_t pgd;
 
 		if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
-			p4d_p = pgtable_area;
+			p4d_p = ppd->pgtable_area;
 			memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D);
-			pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D;
+			ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D;
 
 			pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS);
 		} else {
-			pud_p = pgtable_area;
+			pud_p = ppd->pgtable_area;
 			memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
-			pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
+			ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
 
 			pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS);
 		}
@@ -520,58 +545,160 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
 	}
 
 	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
-		p4d_p += p4d_index(vaddr);
+		p4d_p += p4d_index(ppd->vaddr);
 		if (native_p4d_val(*p4d_p)) {
 			pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK);
 		} else {
 			p4d_t p4d;
 
-			pud_p = pgtable_area;
+			pud_p = ppd->pgtable_area;
 			memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
-			pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
+			ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
 
 			p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS);
 			native_set_p4d(p4d_p, p4d);
 		}
 	}
 
-	pud_p += pud_index(vaddr);
+	pud_p += pud_index(ppd->vaddr);
 	if (native_pud_val(*pud_p)) {
 		if (native_pud_val(*pud_p) & _PAGE_PSE)
-			goto out;
+			return NULL;
 
 		pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK);
 	} else {
 		pud_t pud;
 
-		pmd_p = pgtable_area;
+		pmd_p = ppd->pgtable_area;
 		memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD);
-		pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD;
+		ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD;
 
 		pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS);
 		native_set_pud(pud_p, pud);
 	}
 
-	pmd_p += pmd_index(vaddr);
+	return pmd_p;
+}
+
+static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
+{
+	pmd_t *pmd_p;
+
+	pmd_p = sme_prepare_pgd(ppd);
+	if (!pmd_p)
+		return;
+
+	pmd_p += pmd_index(ppd->vaddr);
 	if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE))
-		native_set_pmd(pmd_p, native_make_pmd(pmd_val));
+		native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags));
+}
 
-out:
-	return pgtable_area;
+static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
+{
+	pmd_t *pmd_p;
+	pte_t *pte_p;
+
+	pmd_p = sme_prepare_pgd(ppd);
+	if (!pmd_p)
+		return;
+
+	pmd_p += pmd_index(ppd->vaddr);
+	if (native_pmd_val(*pmd_p)) {
+		if (native_pmd_val(*pmd_p) & _PAGE_PSE)
+			return;
+
+		pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK);
+	} else {
+		pmd_t pmd;
+
+		pte_p = ppd->pgtable_area;
+		memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE);
+		ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE;
+
+		pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS);
+		native_set_pmd(pmd_p, pmd);
+	}
+
+	pte_p += pte_index(ppd->vaddr);
+	if (!native_pte_val(*pte_p))
+		native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags));
+}
+
+static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
+{
+	while (ppd->vaddr < ppd->vaddr_end) {
+		sme_populate_pgd_large(ppd);
+
+		ppd->vaddr += PMD_PAGE_SIZE;
+		ppd->paddr += PMD_PAGE_SIZE;
+	}
+}
+
+static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
+{
+	while (ppd->vaddr < ppd->vaddr_end) {
+		sme_populate_pgd(ppd);
+
+		ppd->vaddr += PAGE_SIZE;
+		ppd->paddr += PAGE_SIZE;
+	}
+}
+
+static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
+				   pmdval_t pmd_flags, pteval_t pte_flags)
+{
+	unsigned long vaddr_end;
+
+	ppd->pmd_flags = pmd_flags;
+	ppd->pte_flags = pte_flags;
+
+	/* Save original end value since we modify the struct value */
+	vaddr_end = ppd->vaddr_end;
+
+	/* If start is not 2MB aligned, create PTE entries */
+	ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE);
+	__sme_map_range_pte(ppd);
+
+	/* Create PMD entries */
+	ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK;
+	__sme_map_range_pmd(ppd);
+
+	/* If end is not 2MB aligned, create PTE entries */
+	ppd->vaddr_end = vaddr_end;
+	__sme_map_range_pte(ppd);
+}
+
+static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
+{
+	__sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC);
+}
+
+static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
+{
+	__sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC);
+}
+
+static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
+{
+	__sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP);
 }
 
 static unsigned long __init sme_pgtable_calc(unsigned long len)
 {
-	unsigned long p4d_size, pud_size, pmd_size;
+	unsigned long p4d_size, pud_size, pmd_size, pte_size;
 	unsigned long total;
 
 	/*
 	 * Perform a relatively simplistic calculation of the pagetable
-	 * entries that are needed. That mappings will be covered by 2MB
-	 * PMD entries so we can conservatively calculate the required
+	 * entries that are needed. Those mappings will be covered mostly
+	 * by 2MB PMD entries so we can conservatively calculate the required
 	 * number of P4D, PUD and PMD structures needed to perform the
-	 * mappings. Incrementing the count for each covers the case where
-	 * the addresses cross entries.
+	 * mappings.  For mappings that are not 2MB aligned, PTE mappings
+	 * would be needed for the start and end portion of the address range
+	 * that fall outside of the 2MB alignment.  This results in, at most,
+	 * two extra pages to hold PTE entries for each range that is mapped.
+	 * Incrementing the count for each covers the case where the addresses
+	 * cross entries.
 	 */
 	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
 		p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1;
@@ -585,8 +712,9 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
 	}
 	pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1;
 	pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD;
+	pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE;
 
-	total = p4d_size + pud_size + pmd_size;
+	total = p4d_size + pud_size + pmd_size + pte_size;
 
 	/*
 	 * Now calculate the added pagetable structures needed to populate
@@ -610,29 +738,29 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
 	return total;
 }
 
-void __init sme_encrypt_kernel(void)
+void __init __nostackprotector sme_encrypt_kernel(struct boot_params *bp)
 {
 	unsigned long workarea_start, workarea_end, workarea_len;
 	unsigned long execute_start, execute_end, execute_len;
 	unsigned long kernel_start, kernel_end, kernel_len;
+	unsigned long initrd_start, initrd_end, initrd_len;
+	struct sme_populate_pgd_data ppd;
 	unsigned long pgtable_area_len;
-	unsigned long paddr, pmd_flags;
 	unsigned long decrypted_base;
-	void *pgtable_area;
-	pgd_t *pgd;
 
 	if (!sme_active())
 		return;
 
 	/*
-	 * Prepare for encrypting the kernel by building new pagetables with
-	 * the necessary attributes needed to encrypt the kernel in place.
+	 * Prepare for encrypting the kernel and initrd by building new
+	 * pagetables with the necessary attributes needed to encrypt the
+	 * kernel in place.
 	 *
 	 *   One range of virtual addresses will map the memory occupied
-	 *   by the kernel as encrypted.
+	 *   by the kernel and initrd as encrypted.
 	 *
 	 *   Another range of virtual addresses will map the memory occupied
-	 *   by the kernel as decrypted and write-protected.
+	 *   by the kernel and initrd as decrypted and write-protected.
 	 *
 	 *     The use of write-protect attribute will prevent any of the
 	 *     memory from being cached.
@@ -643,6 +771,20 @@ void __init sme_encrypt_kernel(void)
 	kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE);
 	kernel_len = kernel_end - kernel_start;
 
+	initrd_start = 0;
+	initrd_end = 0;
+	initrd_len = 0;
+#ifdef CONFIG_BLK_DEV_INITRD
+	initrd_len = (unsigned long)bp->hdr.ramdisk_size |
+		     ((unsigned long)bp->ext_ramdisk_size << 32);
+	if (initrd_len) {
+		initrd_start = (unsigned long)bp->hdr.ramdisk_image |
+			       ((unsigned long)bp->ext_ramdisk_image << 32);
+		initrd_end = PAGE_ALIGN(initrd_start + initrd_len);
+		initrd_len = initrd_end - initrd_start;
+	}
+#endif
+
 	/* Set the encryption workarea to be immediately after the kernel */
 	workarea_start = kernel_end;
 
@@ -665,16 +807,21 @@ void __init sme_encrypt_kernel(void)
 	 */
 	pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD;
 	pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2;
+	if (initrd_len)
+		pgtable_area_len += sme_pgtable_calc(initrd_len) * 2;
 
 	/* PUDs and PMDs needed in the current pagetables for the workarea */
 	pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len);
 
 	/*
 	 * The total workarea includes the executable encryption area and
-	 * the pagetable area.
+	 * the pagetable area. The start of the workarea is already 2MB
+	 * aligned, align the end of the workarea on a 2MB boundary so that
+	 * we don't try to create/allocate PTE entries from the workarea
+	 * before it is mapped.
 	 */
 	workarea_len = execute_len + pgtable_area_len;
-	workarea_end = workarea_start + workarea_len;
+	workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE);
 
 	/*
 	 * Set the address to the start of where newly created pagetable
@@ -683,45 +830,30 @@ void __init sme_encrypt_kernel(void)
 	 * pagetables and when the new encrypted and decrypted kernel
 	 * mappings are populated.
 	 */
-	pgtable_area = (void *)execute_end;
+	ppd.pgtable_area = (void *)execute_end;
 
 	/*
 	 * Make sure the current pagetable structure has entries for
 	 * addressing the workarea.
 	 */
-	pgd = (pgd_t *)native_read_cr3_pa();
-	paddr = workarea_start;
-	while (paddr < workarea_end) {
-		pgtable_area = sme_populate_pgd(pgd, pgtable_area,
-						paddr,
-						paddr + PMD_FLAGS);
-
-		paddr += PMD_PAGE_SIZE;
-	}
+	ppd.pgd = (pgd_t *)native_read_cr3_pa();
+	ppd.paddr = workarea_start;
+	ppd.vaddr = workarea_start;
+	ppd.vaddr_end = workarea_end;
+	sme_map_range_decrypted(&ppd);
 
 	/* Flush the TLB - no globals so cr3 is enough */
 	native_write_cr3(__native_read_cr3());
 
 	/*
 	 * A new pagetable structure is being built to allow for the kernel
-	 * to be encrypted. It starts with an empty PGD that will then be
-	 * populated with new PUDs and PMDs as the encrypted and decrypted
-	 * kernel mappings are created.
+	 * and initrd to be encrypted. It starts with an empty PGD that will
+	 * then be populated with new PUDs and PMDs as the encrypted and
+	 * decrypted kernel mappings are created.
 	 */
-	pgd = pgtable_area;
-	memset(pgd, 0, sizeof(*pgd) * PTRS_PER_PGD);
-	pgtable_area += sizeof(*pgd) * PTRS_PER_PGD;
-
-	/* Add encrypted kernel (identity) mappings */
-	pmd_flags = PMD_FLAGS | _PAGE_ENC;
-	paddr = kernel_start;
-	while (paddr < kernel_end) {
-		pgtable_area = sme_populate_pgd(pgd, pgtable_area,
-						paddr,
-						paddr + pmd_flags);
-
-		paddr += PMD_PAGE_SIZE;
-	}
+	ppd.pgd = ppd.pgtable_area;
+	memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD);
+	ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD;
 
 	/*
 	 * A different PGD index/entry must be used to get different
@@ -730,47 +862,79 @@ void __init sme_encrypt_kernel(void)
 	 * the base of the mapping.
 	 */
 	decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1);
+	if (initrd_len) {
+		unsigned long check_base;
+
+		check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1);
+		decrypted_base = max(decrypted_base, check_base);
+	}
 	decrypted_base <<= PGDIR_SHIFT;
 
+	/* Add encrypted kernel (identity) mappings */
+	ppd.paddr = kernel_start;
+	ppd.vaddr = kernel_start;
+	ppd.vaddr_end = kernel_end;
+	sme_map_range_encrypted(&ppd);
+
 	/* Add decrypted, write-protected kernel (non-identity) mappings */
-	pmd_flags = (PMD_FLAGS & ~_PAGE_CACHE_MASK) | (_PAGE_PAT | _PAGE_PWT);
-	paddr = kernel_start;
-	while (paddr < kernel_end) {
-		pgtable_area = sme_populate_pgd(pgd, pgtable_area,
-						paddr + decrypted_base,
-						paddr + pmd_flags);
-
-		paddr += PMD_PAGE_SIZE;
+	ppd.paddr = kernel_start;
+	ppd.vaddr = kernel_start + decrypted_base;
+	ppd.vaddr_end = kernel_end + decrypted_base;
+	sme_map_range_decrypted_wp(&ppd);
+
+	if (initrd_len) {
+		/* Add encrypted initrd (identity) mappings */
+		ppd.paddr = initrd_start;
+		ppd.vaddr = initrd_start;
+		ppd.vaddr_end = initrd_end;
+		sme_map_range_encrypted(&ppd);
+		/*
+		 * Add decrypted, write-protected initrd (non-identity) mappings
+		 */
+		ppd.paddr = initrd_start;
+		ppd.vaddr = initrd_start + decrypted_base;
+		ppd.vaddr_end = initrd_end + decrypted_base;
+		sme_map_range_decrypted_wp(&ppd);
 	}
 
 	/* Add decrypted workarea mappings to both kernel mappings */
-	paddr = workarea_start;
-	while (paddr < workarea_end) {
-		pgtable_area = sme_populate_pgd(pgd, pgtable_area,
-						paddr,
-						paddr + PMD_FLAGS);
+	ppd.paddr = workarea_start;
+	ppd.vaddr = workarea_start;
+	ppd.vaddr_end = workarea_end;
+	sme_map_range_decrypted(&ppd);
 
-		pgtable_area = sme_populate_pgd(pgd, pgtable_area,
-						paddr + decrypted_base,
-						paddr + PMD_FLAGS);
-
-		paddr += PMD_PAGE_SIZE;
-	}
+	ppd.paddr = workarea_start;
+	ppd.vaddr = workarea_start + decrypted_base;
+	ppd.vaddr_end = workarea_end + decrypted_base;
+	sme_map_range_decrypted(&ppd);
 
 	/* Perform the encryption */
 	sme_encrypt_execute(kernel_start, kernel_start + decrypted_base,
-			    kernel_len, workarea_start, (unsigned long)pgd);
+			    kernel_len, workarea_start, (unsigned long)ppd.pgd);
+
+	if (initrd_len)
+		sme_encrypt_execute(initrd_start, initrd_start + decrypted_base,
+				    initrd_len, workarea_start,
+				    (unsigned long)ppd.pgd);
 
 	/*
 	 * At this point we are running encrypted.  Remove the mappings for
 	 * the decrypted areas - all that is needed for this is to remove
 	 * the PGD entry/entries.
 	 */
-	sme_clear_pgd(pgd, kernel_start + decrypted_base,
-		      kernel_end + decrypted_base);
+	ppd.vaddr = kernel_start + decrypted_base;
+	ppd.vaddr_end = kernel_end + decrypted_base;
+	sme_clear_pgd(&ppd);
+
+	if (initrd_len) {
+		ppd.vaddr = initrd_start + decrypted_base;
+		ppd.vaddr_end = initrd_end + decrypted_base;
+		sme_clear_pgd(&ppd);
+	}
 
-	sme_clear_pgd(pgd, workarea_start + decrypted_base,
-		      workarea_end + decrypted_base);
+	ppd.vaddr = workarea_start + decrypted_base;
+	ppd.vaddr_end = workarea_end + decrypted_base;
+	sme_clear_pgd(&ppd);
 
 	/* Flush the TLB - no globals so cr3 is enough */
 	native_write_cr3(__native_read_cr3());
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index 730e6d541df1..01f682cf77a8 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -22,9 +22,9 @@ ENTRY(sme_encrypt_execute)
 
 	/*
 	 * Entry parameters:
-	 *   RDI - virtual address for the encrypted kernel mapping
-	 *   RSI - virtual address for the decrypted kernel mapping
-	 *   RDX - length of kernel
+	 *   RDI - virtual address for the encrypted mapping
+	 *   RSI - virtual address for the decrypted mapping
+	 *   RDX - length to encrypt
 	 *   RCX - virtual address of the encryption workarea, including:
 	 *     - stack page (PAGE_SIZE)
 	 *     - encryption routine page (PAGE_SIZE)
@@ -41,9 +41,9 @@ ENTRY(sme_encrypt_execute)
 	addq	$PAGE_SIZE, %rax	/* Workarea encryption routine */
 
 	push	%r12
-	movq	%rdi, %r10		/* Encrypted kernel */
-	movq	%rsi, %r11		/* Decrypted kernel */
-	movq	%rdx, %r12		/* Kernel length */
+	movq	%rdi, %r10		/* Encrypted area */
+	movq	%rsi, %r11		/* Decrypted area */
+	movq	%rdx, %r12		/* Area length */
 
 	/* Copy encryption routine into the workarea */
 	movq	%rax, %rdi				/* Workarea encryption routine */
@@ -52,10 +52,10 @@ ENTRY(sme_encrypt_execute)
 	rep	movsb
 
 	/* Setup registers for call */
-	movq	%r10, %rdi		/* Encrypted kernel */
-	movq	%r11, %rsi		/* Decrypted kernel */
+	movq	%r10, %rdi		/* Encrypted area */
+	movq	%r11, %rsi		/* Decrypted area */
 	movq	%r8, %rdx		/* Pagetables used for encryption */
-	movq	%r12, %rcx		/* Kernel length */
+	movq	%r12, %rcx		/* Area length */
 	movq	%rax, %r8		/* Workarea encryption routine */
 	addq	$PAGE_SIZE, %r8		/* Workarea intermediate copy buffer */
 
@@ -71,7 +71,7 @@ ENDPROC(sme_encrypt_execute)
 
 ENTRY(__enc_copy)
 /*
- * Routine used to encrypt kernel.
+ * Routine used to encrypt memory in place.
  *   This routine must be run outside of the kernel proper since
  *   the kernel will be encrypted during the process. So this
  *   routine is defined here and then copied to an area outside
@@ -79,19 +79,19 @@ ENTRY(__enc_copy)
  *   during execution.
  *
  *   On entry the registers must be:
- *     RDI - virtual address for the encrypted kernel mapping
- *     RSI - virtual address for the decrypted kernel mapping
+ *     RDI - virtual address for the encrypted mapping
+ *     RSI - virtual address for the decrypted mapping
  *     RDX - address of the pagetables to use for encryption
- *     RCX - length of kernel
+ *     RCX - length of area
  *      R8 - intermediate copy buffer
  *
  *     RAX - points to this routine
  *
- * The kernel will be encrypted by copying from the non-encrypted
- * kernel space to an intermediate buffer and then copying from the
- * intermediate buffer back to the encrypted kernel space. The physical
- * addresses of the two kernel space mappings are the same which
- * results in the kernel being encrypted "in place".
+ * The area will be encrypted by copying from the non-encrypted
+ * memory space to an intermediate buffer and then copying from the
+ * intermediate buffer back to the encrypted memory space. The physical
+ * addresses of the two mappings are the same which results in the area
+ * being encrypted "in place".
  */
 	/* Enable the new page tables */
 	mov	%rdx, %cr3
@@ -103,47 +103,55 @@ ENTRY(__enc_copy)
 	orq	$X86_CR4_PGE, %rdx
 	mov	%rdx, %cr4
 
+	push	%r15
+	push	%r12
+
+	movq	%rcx, %r9		/* Save area length */
+	movq	%rdi, %r10		/* Save encrypted area address */
+	movq	%rsi, %r11		/* Save decrypted area address */
+
 	/* Set the PAT register PA5 entry to write-protect */
-	push	%rcx
 	movl	$MSR_IA32_CR_PAT, %ecx
 	rdmsr
-	push	%rdx			/* Save original PAT value */
+	mov	%rdx, %r15		/* Save original PAT value */
 	andl	$0xffff00ff, %edx	/* Clear PA5 */
 	orl	$0x00000500, %edx	/* Set PA5 to WP */
 	wrmsr
-	pop	%rdx			/* RDX contains original PAT value */
-	pop	%rcx
-
-	movq	%rcx, %r9		/* Save kernel length */
-	movq	%rdi, %r10		/* Save encrypted kernel address */
-	movq	%rsi, %r11		/* Save decrypted kernel address */
 
 	wbinvd				/* Invalidate any cache entries */
 
-	/* Copy/encrypt 2MB at a time */
+	/* Copy/encrypt up to 2MB at a time */
+	movq	$PMD_PAGE_SIZE, %r12
 1:
-	movq	%r11, %rsi		/* Source - decrypted kernel */
+	cmpq	%r12, %r9
+	jnb	2f
+	movq	%r9, %r12
+
+2:
+	movq	%r11, %rsi		/* Source - decrypted area */
 	movq	%r8, %rdi		/* Dest   - intermediate copy buffer */
-	movq	$PMD_PAGE_SIZE, %rcx	/* 2MB length */
+	movq	%r12, %rcx
 	rep	movsb
 
 	movq	%r8, %rsi		/* Source - intermediate copy buffer */
-	movq	%r10, %rdi		/* Dest   - encrypted kernel */
-	movq	$PMD_PAGE_SIZE, %rcx	/* 2MB length */
+	movq	%r10, %rdi		/* Dest   - encrypted area */
+	movq	%r12, %rcx
 	rep	movsb
 
-	addq	$PMD_PAGE_SIZE, %r11
-	addq	$PMD_PAGE_SIZE, %r10
-	subq	$PMD_PAGE_SIZE, %r9	/* Kernel length decrement */
+	addq	%r12, %r11
+	addq	%r12, %r10
+	subq	%r12, %r9		/* Kernel length decrement */
 	jnz	1b			/* Kernel length not zero? */
 
 	/* Restore PAT register */
-	push	%rdx			/* Save original PAT value */
 	movl	$MSR_IA32_CR_PAT, %ecx
 	rdmsr
-	pop	%rdx			/* Restore original PAT value */
+	mov	%r15, %rdx		/* Restore original PAT value */
 	wrmsr
 
+	pop	%r12
+	pop	%r15
+
 	ret
 .L__enc_copy_end:
 ENDPROC(__enc_copy)
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 4d434ddb75db..2c1ecf4763c4 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -29,7 +29,6 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
-#include <linux/kallsyms.h>
 #include <asm/pgtable.h>
 #include <linux/mmiotrace.h>
 #include <asm/e820/api.h> /* for ISA_START_ADDRESS */
@@ -123,8 +122,8 @@ static void die_kmmio_nesting_error(struct pt_regs *regs, unsigned long addr)
 	pr_emerg("unexpected fault for address: 0x%08lx, last fault for address: 0x%08lx\n",
 		 addr, my_reason->addr);
 	print_pte(addr);
-	print_symbol(KERN_EMERG "faulting IP is at %s\n", regs->ip);
-	print_symbol(KERN_EMERG "last faulting IP was at %s\n", my_reason->ip);
+	pr_emerg("faulting IP is at %pS\n", (void *)regs->ip);
+	pr_emerg("last faulting IP was at %pS\n", (void *)my_reason->ip);
 #ifdef __i386__
 	pr_emerg("eax: %08lx   ebx: %08lx   ecx: %08lx   edx: %08lx\n",
 		 regs->ax, regs->bx, regs->cx, regs->dx);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 96d456a94b03..004abf9ebf12 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -355,14 +355,15 @@ static inline void _pgd_free(pgd_t *pgd)
 		kmem_cache_free(pgd_cache, pgd);
 }
 #else
+
 static inline pgd_t *_pgd_alloc(void)
 {
-	return (pgd_t *)__get_free_page(PGALLOC_GFP);
+	return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER);
 }
 
 static inline void _pgd_free(pgd_t *pgd)
 {
-	free_page((unsigned long)pgd);
+	free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
 }
 #endif /* CONFIG_X86_PAE */
 
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 6b9bf023a700..c3c5274410a9 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -10,6 +10,7 @@
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/fixmap.h>
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
new file mode 100644
index 000000000000..ce38f165489b
--- /dev/null
+++ b/arch/x86/mm/pti.c
@@ -0,0 +1,368 @@
+/*
+ * Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * This code is based in part on work published here:
+ *
+ *	https://github.com/IAIK/KAISER
+ *
+ * The original work was written by and and signed off by for the Linux
+ * kernel by:
+ *
+ *   Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at>
+ *   Signed-off-by: Moritz Lipp <moritz.lipp@iaik.tugraz.at>
+ *   Signed-off-by: Daniel Gruss <daniel.gruss@iaik.tugraz.at>
+ *   Signed-off-by: Michael Schwarz <michael.schwarz@iaik.tugraz.at>
+ *
+ * Major changes to the original code by: Dave Hansen <dave.hansen@intel.com>
+ * Mostly rewritten by Thomas Gleixner <tglx@linutronix.de> and
+ *		       Andy Lutomirsky <luto@amacapital.net>
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/bug.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+
+#include <asm/cpufeature.h>
+#include <asm/hypervisor.h>
+#include <asm/vsyscall.h>
+#include <asm/cmdline.h>
+#include <asm/pti.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/desc.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "Kernel/User page tables isolation: " fmt
+
+/* Backporting helper */
+#ifndef __GFP_NOTRACK
+#define __GFP_NOTRACK	0
+#endif
+
+static void __init pti_print_if_insecure(const char *reason)
+{
+	if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+		pr_info("%s\n", reason);
+}
+
+static void __init pti_print_if_secure(const char *reason)
+{
+	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+		pr_info("%s\n", reason);
+}
+
+void __init pti_check_boottime_disable(void)
+{
+	char arg[5];
+	int ret;
+
+	if (hypervisor_is_type(X86_HYPER_XEN_PV)) {
+		pti_print_if_insecure("disabled on XEN PV.");
+		return;
+	}
+
+	ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
+	if (ret > 0)  {
+		if (ret == 3 && !strncmp(arg, "off", 3)) {
+			pti_print_if_insecure("disabled on command line.");
+			return;
+		}
+		if (ret == 2 && !strncmp(arg, "on", 2)) {
+			pti_print_if_secure("force enabled on command line.");
+			goto enable;
+		}
+		if (ret == 4 && !strncmp(arg, "auto", 4))
+			goto autosel;
+	}
+
+	if (cmdline_find_option_bool(boot_command_line, "nopti")) {
+		pti_print_if_insecure("disabled on command line.");
+		return;
+	}
+
+autosel:
+	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+		return;
+enable:
+	setup_force_cpu_cap(X86_FEATURE_PTI);
+}
+
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	/*
+	 * Changes to the high (kernel) portion of the kernelmode page
+	 * tables are not automatically propagated to the usermode tables.
+	 *
+	 * Users should keep in mind that, unlike the kernelmode tables,
+	 * there is no vmalloc_fault equivalent for the usermode tables.
+	 * Top-level entries added to init_mm's usermode pgd after boot
+	 * will not be automatically propagated to other mms.
+	 */
+	if (!pgdp_maps_userspace(pgdp))
+		return pgd;
+
+	/*
+	 * The user page tables get the full PGD, accessible from
+	 * userspace:
+	 */
+	kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd;
+
+	/*
+	 * If this is normal user memory, make it NX in the kernel
+	 * pagetables so that, if we somehow screw up and return to
+	 * usermode with the kernel CR3 loaded, we'll get a page fault
+	 * instead of allowing user code to execute with the wrong CR3.
+	 *
+	 * As exceptions, we don't set NX if:
+	 *  - _PAGE_USER is not set.  This could be an executable
+	 *     EFI runtime mapping or something similar, and the kernel
+	 *     may execute from it
+	 *  - we don't have NX support
+	 *  - we're clearing the PGD (i.e. the new pgd is not present).
+	 */
+	if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) &&
+	    (__supported_pte_mask & _PAGE_NX))
+		pgd.pgd |= _PAGE_NX;
+
+	/* return the copy of the PGD we want the kernel to use: */
+	return pgd;
+}
+
+/*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a P4D on success, or NULL on failure.
+ */
+static __init p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
+{
+	pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address));
+	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+
+	if (address < PAGE_OFFSET) {
+		WARN_ONCE(1, "attempt to walk user address\n");
+		return NULL;
+	}
+
+	if (pgd_none(*pgd)) {
+		unsigned long new_p4d_page = __get_free_page(gfp);
+		if (!new_p4d_page)
+			return NULL;
+
+		set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
+	}
+	BUILD_BUG_ON(pgd_large(*pgd) != 0);
+
+	return p4d_offset(pgd, address);
+}
+
+/*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a PMD on success, or NULL on failure.
+ */
+static __init pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
+{
+	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+	p4d_t *p4d = pti_user_pagetable_walk_p4d(address);
+	pud_t *pud;
+
+	BUILD_BUG_ON(p4d_large(*p4d) != 0);
+	if (p4d_none(*p4d)) {
+		unsigned long new_pud_page = __get_free_page(gfp);
+		if (!new_pud_page)
+			return NULL;
+
+		set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
+	}
+
+	pud = pud_offset(p4d, address);
+	/* The user page tables do not use large mappings: */
+	if (pud_large(*pud)) {
+		WARN_ON(1);
+		return NULL;
+	}
+	if (pud_none(*pud)) {
+		unsigned long new_pmd_page = __get_free_page(gfp);
+		if (!new_pmd_page)
+			return NULL;
+
+		set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
+	}
+
+	return pmd_offset(pud, address);
+}
+
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+/*
+ * Walk the shadow copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.  Does not support large pages.
+ *
+ * Note: this is only used when mapping *new* kernel data into the
+ * user/shadow page tables.  It is never used for userspace data.
+ *
+ * Returns a pointer to a PTE on success, or NULL on failure.
+ */
+static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
+{
+	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+	pmd_t *pmd = pti_user_pagetable_walk_pmd(address);
+	pte_t *pte;
+
+	/* We can't do anything sensible if we hit a large mapping. */
+	if (pmd_large(*pmd)) {
+		WARN_ON(1);
+		return NULL;
+	}
+
+	if (pmd_none(*pmd)) {
+		unsigned long new_pte_page = __get_free_page(gfp);
+		if (!new_pte_page)
+			return NULL;
+
+		set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
+	}
+
+	pte = pte_offset_kernel(pmd, address);
+	if (pte_flags(*pte) & _PAGE_USER) {
+		WARN_ONCE(1, "attempt to walk to user pte\n");
+		return NULL;
+	}
+	return pte;
+}
+
+static void __init pti_setup_vsyscall(void)
+{
+	pte_t *pte, *target_pte;
+	unsigned int level;
+
+	pte = lookup_address(VSYSCALL_ADDR, &level);
+	if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte))
+		return;
+
+	target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR);
+	if (WARN_ON(!target_pte))
+		return;
+
+	*target_pte = *pte;
+	set_vsyscall_pgtable_user_bits(kernel_to_user_pgdp(swapper_pg_dir));
+}
+#else
+static void __init pti_setup_vsyscall(void) { }
+#endif
+
+static void __init
+pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
+{
+	unsigned long addr;
+
+	/*
+	 * Clone the populated PMDs which cover start to end. These PMD areas
+	 * can have holes.
+	 */
+	for (addr = start; addr < end; addr += PMD_SIZE) {
+		pmd_t *pmd, *target_pmd;
+		pgd_t *pgd;
+		p4d_t *p4d;
+		pud_t *pud;
+
+		pgd = pgd_offset_k(addr);
+		if (WARN_ON(pgd_none(*pgd)))
+			return;
+		p4d = p4d_offset(pgd, addr);
+		if (WARN_ON(p4d_none(*p4d)))
+			return;
+		pud = pud_offset(p4d, addr);
+		if (pud_none(*pud))
+			continue;
+		pmd = pmd_offset(pud, addr);
+		if (pmd_none(*pmd))
+			continue;
+
+		target_pmd = pti_user_pagetable_walk_pmd(addr);
+		if (WARN_ON(!target_pmd))
+			return;
+
+		/*
+		 * Copy the PMD.  That is, the kernelmode and usermode
+		 * tables will share the last-level page tables of this
+		 * address range
+		 */
+		*target_pmd = pmd_clear_flags(*pmd, clear);
+	}
+}
+
+/*
+ * Clone a single p4d (i.e. a top-level entry on 4-level systems and a
+ * next-level entry on 5-level systems.
+ */
+static void __init pti_clone_p4d(unsigned long addr)
+{
+	p4d_t *kernel_p4d, *user_p4d;
+	pgd_t *kernel_pgd;
+
+	user_p4d = pti_user_pagetable_walk_p4d(addr);
+	kernel_pgd = pgd_offset_k(addr);
+	kernel_p4d = p4d_offset(kernel_pgd, addr);
+	*user_p4d = *kernel_p4d;
+}
+
+/*
+ * Clone the CPU_ENTRY_AREA into the user space visible page table.
+ */
+static void __init pti_clone_user_shared(void)
+{
+	pti_clone_p4d(CPU_ENTRY_AREA_BASE);
+}
+
+/*
+ * Clone the ESPFIX P4D into the user space visinble page table
+ */
+static void __init pti_setup_espfix64(void)
+{
+#ifdef CONFIG_X86_ESPFIX64
+	pti_clone_p4d(ESPFIX_BASE_ADDR);
+#endif
+}
+
+/*
+ * Clone the populated PMDs of the entry and irqentry text and force it RO.
+ */
+static void __init pti_clone_entry_text(void)
+{
+	pti_clone_pmds((unsigned long) __entry_text_start,
+			(unsigned long) __irqentry_text_end,
+		       _PAGE_RW | _PAGE_GLOBAL);
+}
+
+/*
+ * Initialize kernel page table isolation
+ */
+void __init pti_init(void)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	pr_info("enabled\n");
+
+	pti_clone_user_shared();
+	pti_clone_entry_text();
+	pti_setup_espfix64();
+	pti_setup_vsyscall();
+}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 3118392cdf75..5bfe61a5e8e3 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -28,6 +28,38 @@
  *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
  */
 
+/*
+ * We get here when we do something requiring a TLB invalidation
+ * but could not go invalidate all of the contexts.  We do the
+ * necessary invalidation by clearing out the 'ctx_id' which
+ * forces a TLB flush when the context is loaded.
+ */
+void clear_asid_other(void)
+{
+	u16 asid;
+
+	/*
+	 * This is only expected to be set if we have disabled
+	 * kernel _PAGE_GLOBAL pages.
+	 */
+	if (!static_cpu_has(X86_FEATURE_PTI)) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
+		/* Do not need to flush the current asid */
+		if (asid == this_cpu_read(cpu_tlbstate.loaded_mm_asid))
+			continue;
+		/*
+		 * Make sure the next time we go to switch to
+		 * this asid, we do a flush:
+		 */
+		this_cpu_write(cpu_tlbstate.ctxs[asid].ctx_id, 0);
+	}
+	this_cpu_write(cpu_tlbstate.invalidate_other, false);
+}
+
 atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
 
 
@@ -42,6 +74,9 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 		return;
 	}
 
+	if (this_cpu_read(cpu_tlbstate.invalidate_other))
+		clear_asid_other();
+
 	for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
 		if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) !=
 		    next->context.ctx_id)
@@ -65,6 +100,25 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 	*need_flush = true;
 }
 
+static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush)
+{
+	unsigned long new_mm_cr3;
+
+	if (need_flush) {
+		invalidate_user_asid(new_asid);
+		new_mm_cr3 = build_cr3(pgdir, new_asid);
+	} else {
+		new_mm_cr3 = build_cr3_noflush(pgdir, new_asid);
+	}
+
+	/*
+	 * Caution: many callers of this function expect
+	 * that load_cr3() is serializing and orders TLB
+	 * fills with respect to the mm_cpumask writes.
+	 */
+	write_cr3(new_mm_cr3);
+}
+
 void leave_mm(int cpu)
 {
 	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
@@ -97,6 +151,34 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	local_irq_restore(flags);
 }
 
+static void sync_current_stack_to_mm(struct mm_struct *mm)
+{
+	unsigned long sp = current_stack_pointer;
+	pgd_t *pgd = pgd_offset(mm, sp);
+
+	if (CONFIG_PGTABLE_LEVELS > 4) {
+		if (unlikely(pgd_none(*pgd))) {
+			pgd_t *pgd_ref = pgd_offset_k(sp);
+
+			set_pgd(pgd, *pgd_ref);
+		}
+	} else {
+		/*
+		 * "pgd" is faked.  The top level entries are "p4d"s, so sync
+		 * the p4d.  This compiles to approximately the same code as
+		 * the 5-level case.
+		 */
+		p4d_t *p4d = p4d_offset(pgd, sp);
+
+		if (unlikely(p4d_none(*p4d))) {
+			pgd_t *pgd_ref = pgd_offset_k(sp);
+			p4d_t *p4d_ref = p4d_offset(pgd_ref, sp);
+
+			set_p4d(p4d, *p4d_ref);
+		}
+	}
+}
+
 void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			struct task_struct *tsk)
 {
@@ -128,7 +210,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	 * isn't free.
 	 */
 #ifdef CONFIG_DEBUG_VM
-	if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) {
+	if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid))) {
 		/*
 		 * If we were to BUG here, we'd be very likely to kill
 		 * the system so hard that we don't see the call trace.
@@ -172,11 +254,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			 * mapped in the new pgd, we'll double-fault.  Forcibly
 			 * map it.
 			 */
-			unsigned int index = pgd_index(current_stack_pointer);
-			pgd_t *pgd = next->pgd + index;
-
-			if (unlikely(pgd_none(*pgd)))
-				set_pgd(pgd, init_mm.pgd[index]);
+			sync_current_stack_to_mm(next);
 		}
 
 		/* Stop remote flushes for the previous mm */
@@ -195,7 +273,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		if (need_flush) {
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
-			write_cr3(build_cr3(next, new_asid));
+			load_new_mm_cr3(next->pgd, new_asid, true);
 
 			/*
 			 * NB: This gets called via leave_mm() in the idle path
@@ -208,7 +286,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 		} else {
 			/* The new ASID is already up to date. */
-			write_cr3(build_cr3_noflush(next, new_asid));
+			load_new_mm_cr3(next->pgd, new_asid, false);
 
 			/* See above wrt _rcuidle. */
 			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
@@ -288,7 +366,7 @@ void initialize_tlbstate_and_flush(void)
 		!(cr4_read_shadow() & X86_CR4_PCIDE));
 
 	/* Force ASID 0 and force a TLB flush. */
-	write_cr3(build_cr3(mm, 0));
+	write_cr3(build_cr3(mm->pgd, 0));
 
 	/* Reinitialize tlbstate. */
 	this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
@@ -551,7 +629,7 @@ static void do_kernel_range_flush(void *info)
 
 	/* flush range by one by one 'invlpg' */
 	for (addr = f->start; addr < f->end; addr += PAGE_SIZE)
-		__flush_tlb_single(addr);
+		__flush_tlb_one(addr);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 0554e8aef4d5..4923d92f918d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -15,8 +15,6 @@
 #include <asm/set_memory.h>
 #include <linux/bpf.h>
 
-int bpf_jit_enable __read_mostly;
-
 /*
  * assembly code in arch/x86/net/bpf_jit.S
  */
@@ -154,6 +152,11 @@ static bool is_ereg(u32 reg)
 			     BIT(BPF_REG_AX));
 }
 
+static bool is_axreg(u32 reg)
+{
+	return reg == BPF_REG_0;
+}
+
 /* add modifiers if 'reg' maps to x64 registers r8..r15 */
 static u8 add_1mod(u8 byte, u32 reg)
 {
@@ -447,16 +450,36 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			else if (is_ereg(dst_reg))
 				EMIT1(add_1mod(0x40, dst_reg));
 
+			/* b3 holds 'normal' opcode, b2 short form only valid
+			 * in case dst is eax/rax.
+			 */
 			switch (BPF_OP(insn->code)) {
-			case BPF_ADD: b3 = 0xC0; break;
-			case BPF_SUB: b3 = 0xE8; break;
-			case BPF_AND: b3 = 0xE0; break;
-			case BPF_OR: b3 = 0xC8; break;
-			case BPF_XOR: b3 = 0xF0; break;
+			case BPF_ADD:
+				b3 = 0xC0;
+				b2 = 0x05;
+				break;
+			case BPF_SUB:
+				b3 = 0xE8;
+				b2 = 0x2D;
+				break;
+			case BPF_AND:
+				b3 = 0xE0;
+				b2 = 0x25;
+				break;
+			case BPF_OR:
+				b3 = 0xC8;
+				b2 = 0x0D;
+				break;
+			case BPF_XOR:
+				b3 = 0xF0;
+				b2 = 0x35;
+				break;
 			}
 
 			if (is_imm8(imm32))
 				EMIT3(0x83, add_1reg(b3, dst_reg), imm32);
+			else if (is_axreg(dst_reg))
+				EMIT1_off32(b2, imm32);
 			else
 				EMIT2_off32(0x81, add_1reg(b3, dst_reg), imm32);
 			break;
@@ -545,26 +568,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			 */
 			EMIT2(0x31, 0xd2);
 
-			if (BPF_SRC(insn->code) == BPF_X) {
-				/* if (src_reg == 0) return 0 */
-
-				/* cmp r11, 0 */
-				EMIT4(0x49, 0x83, 0xFB, 0x00);
-
-				/* jne .+9 (skip over pop, pop, xor and jmp) */
-				EMIT2(X86_JNE, 1 + 1 + 2 + 5);
-				EMIT1(0x5A); /* pop rdx */
-				EMIT1(0x58); /* pop rax */
-				EMIT2(0x31, 0xc0); /* xor eax, eax */
-
-				/* jmp cleanup_addr
-				 * addrs[i] - 11, because there are 11 bytes
-				 * after this insn: div, mov, pop, pop, mov
-				 */
-				jmp_offset = ctx->cleanup_addr - (addrs[i] - 11);
-				EMIT1_off32(0xE9, jmp_offset);
-			}
-
 			if (BPF_CLASS(insn->code) == BPF_ALU64)
 				/* div r11 */
 				EMIT3(0x49, 0xF7, 0xF3);
@@ -1109,19 +1112,29 @@ common_load:
 	return proglen;
 }
 
+struct x64_jit_data {
+	struct bpf_binary_header *header;
+	int *addrs;
+	u8 *image;
+	int proglen;
+	struct jit_context ctx;
+};
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_binary_header *header = NULL;
 	struct bpf_prog *tmp, *orig_prog = prog;
+	struct x64_jit_data *jit_data;
 	int proglen, oldproglen = 0;
 	struct jit_context ctx = {};
 	bool tmp_blinded = false;
+	bool extra_pass = false;
 	u8 *image = NULL;
 	int *addrs;
 	int pass;
 	int i;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
@@ -1135,10 +1148,28 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = tmp;
 	}
 
+	jit_data = prog->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			prog = orig_prog;
+			goto out;
+		}
+		prog->aux->jit_data = jit_data;
+	}
+	addrs = jit_data->addrs;
+	if (addrs) {
+		ctx = jit_data->ctx;
+		oldproglen = jit_data->proglen;
+		image = jit_data->image;
+		header = jit_data->header;
+		extra_pass = true;
+		goto skip_init_addrs;
+	}
 	addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL);
 	if (!addrs) {
 		prog = orig_prog;
-		goto out;
+		goto out_addrs;
 	}
 
 	/* Before first pass, make a rough estimation of addrs[]
@@ -1149,6 +1180,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		addrs[i] = proglen;
 	}
 	ctx.cleanup_addr = proglen;
+skip_init_addrs:
 
 	/* JITed image shrinks with every pass and the loop iterates
 	 * until the image stops shrinking. Very large bpf programs
@@ -1189,7 +1221,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (image) {
 		bpf_flush_icache(header, image + proglen);
-		bpf_jit_binary_lock_ro(header);
+		if (!prog->is_func || extra_pass) {
+			bpf_jit_binary_lock_ro(header);
+		} else {
+			jit_data->addrs = addrs;
+			jit_data->ctx = ctx;
+			jit_data->proglen = proglen;
+			jit_data->image = image;
+			jit_data->header = header;
+		}
 		prog->bpf_func = (void *)image;
 		prog->jited = 1;
 		prog->jited_len = proglen;
@@ -1197,8 +1237,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = orig_prog;
 	}
 
+	if (!prog->is_func || extra_pass) {
 out_addrs:
-	kfree(addrs);
+		kfree(addrs);
+		kfree(jit_data);
+		prog->aux->jit_data = NULL;
+	}
 out:
 	if (tmp_blinded)
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?
diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c
index bb461cfd01ab..526536c81ddc 100644
--- a/arch/x86/pci/broadcom_bus.c
+++ b/arch/x86/pci/broadcom_bus.c
@@ -97,7 +97,7 @@ static int __init broadcom_postcore_init(void)
 	 * We should get host bridge information from ACPI unless the BIOS
 	 * doesn't support it.
 	 */
-	if (acpi_os_get_root_pointer())
+	if (!acpi_disabled && acpi_os_get_root_pointer())
 		return 0;
 #endif
 
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 7a5350d08cef..563049c483a1 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -594,6 +594,11 @@ char *__init pcibios_setup(char *str)
 	} else if (!strcmp(str, "nocrs")) {
 		pci_probe |= PCI_ROOT_NO_CRS;
 		return NULL;
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+	} else if (!strcmp(str, "big_root_window")) {
+		pci_probe |= PCI_BIG_ROOT_WINDOW;
+		return NULL;
+#endif
 	} else if (!strcmp(str, "earlydump")) {
 		pci_early_dump_regs = 1;
 		return NULL;
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 1e996df687a3..54ef19e90705 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -662,9 +662,23 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid);
  */
 static void pci_amd_enable_64bit_bar(struct pci_dev *dev)
 {
-	unsigned i;
-	u32 base, limit, high;
+	static const char *name = "PCI Bus 0000:00";
 	struct resource *res, *conflict;
+	u32 base, limit, high;
+	struct pci_dev *other;
+	unsigned i;
+
+	if (!(pci_probe & PCI_BIG_ROOT_WINDOW))
+		return;
+
+	/* Check that we are the only device of that type */
+	other = pci_get_device(dev->vendor, dev->device, NULL);
+	if (other != dev ||
+	    (other = pci_get_device(dev->vendor, dev->device, other))) {
+		/* This is a multi-socket system, don't touch it for now */
+		pci_dev_put(other);
+		return;
+	}
 
 	for (i = 0; i < 8; i++) {
 		pci_read_config_dword(dev, AMD_141b_MMIO_BASE(i), &base);
@@ -689,17 +703,30 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev)
 	if (!res)
 		return;
 
-	res->name = "PCI Bus 0000:00";
+	/*
+	 * Allocate a 256GB window directly below the 0xfd00000000 hardware
+	 * limit (see AMD Family 15h Models 30h-3Fh BKDG, sec 2.4.6).
+	 */
+	res->name = name;
 	res->flags = IORESOURCE_PREFETCH | IORESOURCE_MEM |
 		IORESOURCE_MEM_64 | IORESOURCE_WINDOW;
-	res->start = 0x100000000ull;
+	res->start = 0xbd00000000ull;
 	res->end = 0xfd00000000ull - 1;
 
-	/* Just grab the free area behind system memory for this */
-	while ((conflict = request_resource_conflict(&iomem_resource, res)))
-		res->start = conflict->end + 1;
+	conflict = request_resource_conflict(&iomem_resource, res);
+	if (conflict) {
+		kfree(res);
+		if (conflict->name != name)
+			return;
 
-	dev_info(&dev->dev, "adding root bus resource %pR\n", res);
+		/* We are resuming from suspend; just reenable the window */
+		res = conflict;
+	} else {
+		dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n",
+			 res);
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+		pci_bus_add_resource(dev->bus, res, 0);
+	}
 
 	base = ((res->start >> 8) & AMD_141b_MMIO_BASE_MMIOBASE_MASK) |
 		AMD_141b_MMIO_BASE_RE_MASK | AMD_141b_MMIO_BASE_WE_MASK;
@@ -711,13 +738,16 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev)
 	pci_write_config_dword(dev, AMD_141b_MMIO_HIGH(i), high);
 	pci_write_config_dword(dev, AMD_141b_MMIO_LIMIT(i), limit);
 	pci_write_config_dword(dev, AMD_141b_MMIO_BASE(i), base);
-
-	pci_bus_add_resource(dev->bus, res, 0);
 }
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar);
 
 #endif
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 511921045312..43867bc85368 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -300,6 +300,7 @@ int __init intel_mid_pci_init(void)
 	pci_root_ops = intel_mid_pci_ops;
 	pci_soc_mode = 1;
 	/* Continue with standard init */
+	acpi_noirq_set();
 	return 1;
 }
 
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 53d600217973..75577c1490c4 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -26,6 +26,7 @@
 #include <linux/pci_ids.h>
 #include <linux/export.h>
 #include <linux/list.h>
+#include <linux/dma-direct.h>
 #include <asm/iommu.h>
 
 #define STA2X11_SWIOTLB_SIZE (4*1024*1024)
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 6a151ce70e86..c310a8284358 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -25,7 +25,6 @@
 #include <linux/spinlock.h>
 #include <linux/bootmem.h>
 #include <linux/ioport.h>
-#include <linux/init.h>
 #include <linux/mc146818rtc.h>
 #include <linux/efi.h>
 #include <linux/uaccess.h>
@@ -135,7 +134,9 @@ pgd_t * __init efi_call_phys_prolog(void)
 				pud[j] = *pud_offset(p4d_k, vaddr);
 			}
 		}
+		pgd_offset_k(pgd * PGDIR_SIZE)->pgd &= ~_PAGE_NX;
 	}
+
 out:
 	__flush_tlb_all();
 
@@ -196,6 +197,9 @@ static pgd_t *efi_pgd;
  * because we want to avoid inserting EFI region mappings (EFI_VA_END
  * to EFI_VA_START) into the standard kernel page tables. Everything
  * else can be shared, see efi_sync_low_kernel_mappings().
+ *
+ * We don't want the pgd on the pgd_list and cannot use pgd_alloc() for the
+ * allocation.
  */
 int __init efi_alloc_page_tables(void)
 {
@@ -208,7 +212,7 @@ int __init efi_alloc_page_tables(void)
 		return 0;
 
 	gfp_mask = GFP_KERNEL | __GFP_ZERO;
-	efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
+	efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
 	if (!efi_pgd)
 		return -ENOMEM;
 
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 8a99a2e96537..5b513ccffde4 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -592,7 +592,18 @@ static int qrk_capsule_setup_info(struct capsule_info *cap_info, void **pkbuff,
 	/*
 	 * Update the first page pointer to skip over the CSH header.
 	 */
-	cap_info->pages[0] += csh->headersize;
+	cap_info->phys[0] += csh->headersize;
+
+	/*
+	 * cap_info->capsule should point at a virtual mapping of the entire
+	 * capsule, starting at the capsule header. Our image has the Quark
+	 * security header prepended, so we cannot rely on the default vmap()
+	 * mapping created by the generic capsule code.
+	 * Given that the Quark firmware does not appear to care about the
+	 * virtual mapping, let's just point cap_info->capsule at our copy
+	 * of the capsule header.
+	 */
+	cap_info->capsule = &cap_info->header;
 
 	return 1;
 }
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
index dc036e511f48..5a0483e7bf66 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
@@ -60,7 +60,7 @@ static int __init tng_bt_sfi_setup(struct bt_sfi_data *ddata)
 	return 0;
 }
 
-static const struct bt_sfi_data tng_bt_sfi_data __initdata = {
+static struct bt_sfi_data tng_bt_sfi_data __initdata = {
 	.setup	= tng_bt_sfi_setup,
 };
 
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 86676cec99a1..2c67bae6bb53 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -194,7 +194,7 @@ void __init x86_intel_mid_early_setup(void)
 	x86_platform.calibrate_tsc = intel_mid_calibrate_tsc;
 	x86_platform.get_nmi_reason = intel_mid_get_nmi_reason;
 
-	x86_init.pci.init = intel_mid_pci_init;
+	x86_init.pci.arch_init = intel_mid_pci_init;
 	x86_init.pci.fixup_irqs = x86_init_noop;
 
 	legacy_pic = &null_legacy_pic;
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index 19b43e3a9f0f..7be1e1fe9ae3 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -96,8 +96,7 @@ int __init sfi_parse_mtmr(struct sfi_table_header *table)
 			pentry->freq_hz, pentry->irq);
 		mp_irq.type = MP_INTSRC;
 		mp_irq.irqtype = mp_INT;
-		/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
-		mp_irq.irqflag = 5;
+		mp_irq.irqflag = MP_IRQTRIG_EDGE | MP_IRQPOL_ACTIVE_HIGH;
 		mp_irq.srcbus = MP_BUS_ISA;
 		mp_irq.srcbusirq = pentry->irq;	/* IRQ */
 		mp_irq.dstapic = MP_APIC_ALL;
@@ -168,7 +167,7 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
 			totallen, (u32)pentry->phys_addr, pentry->irq);
 		mp_irq.type = MP_INTSRC;
 		mp_irq.irqtype = mp_INT;
-		mp_irq.irqflag = 0xf;	/* level trigger and active low */
+		mp_irq.irqflag = MP_IRQTRIG_LEVEL | MP_IRQPOL_ACTIVE_LOW;
 		mp_irq.srcbus = MP_BUS_ISA;
 		mp_irq.srcbusirq = pentry->irq;	/* IRQ */
 		mp_irq.dstapic = MP_APIC_ALL;
diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c
index a952ac199741..6f37a2137a79 100644
--- a/arch/x86/platform/intel/iosf_mbi.c
+++ b/arch/x86/platform/intel/iosf_mbi.c
@@ -218,14 +218,23 @@ int iosf_mbi_register_pmic_bus_access_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(iosf_mbi_register_pmic_bus_access_notifier);
 
+int iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(
+	struct notifier_block *nb)
+{
+	iosf_mbi_assert_punit_acquired();
+
+	return blocking_notifier_chain_unregister(
+				&iosf_mbi_pmic_bus_access_notifier, nb);
+}
+EXPORT_SYMBOL(iosf_mbi_unregister_pmic_bus_access_notifier_unlocked);
+
 int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb)
 {
 	int ret;
 
 	/* Wait for the bus to go inactive before unregistering */
 	mutex_lock(&iosf_mbi_punit_mutex);
-	ret = blocking_notifier_chain_unregister(
-				&iosf_mbi_pmic_bus_access_notifier, nb);
+	ret = iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(nb);
 	mutex_unlock(&iosf_mbi_punit_mutex);
 
 	return ret;
@@ -239,6 +248,12 @@ int iosf_mbi_call_pmic_bus_access_notifier_chain(unsigned long val, void *v)
 }
 EXPORT_SYMBOL(iosf_mbi_call_pmic_bus_access_notifier_chain);
 
+void iosf_mbi_assert_punit_acquired(void)
+{
+	WARN_ON(!mutex_is_locked(&iosf_mbi_punit_mutex));
+}
+EXPORT_SYMBOL(iosf_mbi_assert_punit_acquired);
+
 #ifdef CONFIG_IOSF_MBI_DEBUG
 static u32	dbg_mdr;
 static u32	dbg_mcr;
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index f44c0bc95aa2..c2e9285d1bf1 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -299,7 +299,7 @@ static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp,
 		local_flush_tlb();
 		stat->d_alltlb++;
 	} else {
-		__flush_tlb_one(msg->address);
+		__flush_tlb_single(msg->address);
 		stat->d_onetlb++;
 	}
 	stat->d_requestee++;
@@ -1751,7 +1751,8 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 		uv1 = 1;
 
 	/* the 14-bit pnode */
-	write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m));
+	write_mmr_descriptor_base(pnode,
+		(n << UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT | m));
 	/*
 	 * Initializing all 8 (ITEMS_PER_DESC) descriptors for each
 	 * cpu even though we only use the first one; one descriptor can
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 5f6fd860820a..e4cb9f4cde8a 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -128,7 +128,7 @@ static void uv_domain_free(struct irq_domain *domain, unsigned int virq,
  * on the specified blade to allow the sending of MSIs to the specified CPU.
  */
 static int uv_domain_activate(struct irq_domain *domain,
-			      struct irq_data *irq_data, bool early)
+			      struct irq_data *irq_data, bool reserve)
 {
 	uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
 	return 0;
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index c34bd8233f7c..5f64f30873e2 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -905,7 +905,7 @@ static inline void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master)
 /*
  * UV NMI handler
  */
-int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
+static int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 {
 	struct uv_hub_nmi_s *hub_nmi = uv_hub_nmi;
 	int cpu = smp_processor_id();
@@ -1013,7 +1013,7 @@ void uv_nmi_init(void)
 }
 
 /* Setup HUB NMI info */
-void __init uv_nmi_setup_common(bool hubbed)
+static void __init uv_nmi_setup_common(bool hubbed)
 {
 	int size = sizeof(void *) * (1 << NODES_SHIFT);
 	int cpu;
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 84fcfde53f8f..a7d966964c6f 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -82,12 +82,8 @@ static void __save_processor_state(struct saved_context *ctxt)
 	/*
 	 * descriptor tables
 	 */
-#ifdef CONFIG_X86_32
 	store_idt(&ctxt->idt);
-#else
-/* CONFIG_X86_64 */
-	store_idt((struct desc_ptr *)&ctxt->idt_limit);
-#endif
+
 	/*
 	 * We save it here, but restore it only in the hibernate case.
 	 * For ACPI S3 resume, this is loaded via 'early_gdt_desc' in 64-bit
@@ -103,22 +99,18 @@ static void __save_processor_state(struct saved_context *ctxt)
 	/*
 	 * segment registers
 	 */
-#ifdef CONFIG_X86_32
-	savesegment(es, ctxt->es);
-	savesegment(fs, ctxt->fs);
+#ifdef CONFIG_X86_32_LAZY_GS
 	savesegment(gs, ctxt->gs);
-	savesegment(ss, ctxt->ss);
-#else
-/* CONFIG_X86_64 */
-	asm volatile ("movw %%ds, %0" : "=m" (ctxt->ds));
-	asm volatile ("movw %%es, %0" : "=m" (ctxt->es));
-	asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs));
-	asm volatile ("movw %%gs, %0" : "=m" (ctxt->gs));
-	asm volatile ("movw %%ss, %0" : "=m" (ctxt->ss));
+#endif
+#ifdef CONFIG_X86_64
+	savesegment(gs, ctxt->gs);
+	savesegment(fs, ctxt->fs);
+	savesegment(ds, ctxt->ds);
+	savesegment(es, ctxt->es);
 
 	rdmsrl(MSR_FS_BASE, ctxt->fs_base);
-	rdmsrl(MSR_GS_BASE, ctxt->gs_base);
-	rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+	rdmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+	rdmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
 	mtrr_save_fixed_ranges(NULL);
 
 	rdmsrl(MSR_EFER, ctxt->efer);
@@ -160,17 +152,19 @@ static void do_fpu_end(void)
 static void fix_processor_context(void)
 {
 	int cpu = smp_processor_id();
-	struct tss_struct *t = &per_cpu(cpu_tss, cpu);
 #ifdef CONFIG_X86_64
 	struct desc_struct *desc = get_cpu_gdt_rw(cpu);
 	tss_desc tss;
 #endif
-	set_tss_desc(cpu, t);	/*
-				 * This just modifies memory; should not be
-				 * necessary. But... This is necessary, because
-				 * 386 hardware has concept of busy TSS or some
-				 * similar stupidity.
-				 */
+
+	/*
+	 * We need to reload TR, which requires that we change the
+	 * GDT entry to indicate "available" first.
+	 *
+	 * XXX: This could probably all be replaced by a call to
+	 * force_reload_TR().
+	 */
+	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 
 #ifdef CONFIG_X86_64
 	memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc));
@@ -178,6 +172,9 @@ static void fix_processor_context(void)
 	write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS);
 
 	syscall_init();				/* This sets MSR_*STAR and related */
+#else
+	if (boot_cpu_has(X86_FEATURE_SEP))
+		enable_sep_cpu();
 #endif
 	load_TR_desc();				/* This does ltr */
 	load_mm_ldt(current->active_mm);	/* This does lldt */
@@ -190,9 +187,12 @@ static void fix_processor_context(void)
 }
 
 /**
- *	__restore_processor_state - restore the contents of CPU registers saved
- *		by __save_processor_state()
- *	@ctxt - structure to load the registers contents from
+ * __restore_processor_state - restore the contents of CPU registers saved
+ *                             by __save_processor_state()
+ * @ctxt - structure to load the registers contents from
+ *
+ * The asm code that gets us here will have restored a usable GDT, although
+ * it will be pointing to the wrong alias.
  */
 static void notrace __restore_processor_state(struct saved_context *ctxt)
 {
@@ -215,46 +215,52 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	write_cr2(ctxt->cr2);
 	write_cr0(ctxt->cr0);
 
+	/* Restore the IDT. */
+	load_idt(&ctxt->idt);
+
 	/*
-	 * now restore the descriptor tables to their proper values
-	 * ltr is done i fix_processor_context().
+	 * Just in case the asm code got us here with the SS, DS, or ES
+	 * out of sync with the GDT, update them.
 	 */
-#ifdef CONFIG_X86_32
-	load_idt(&ctxt->idt);
+	loadsegment(ss, __KERNEL_DS);
+	loadsegment(ds, __USER_DS);
+	loadsegment(es, __USER_DS);
+
+	/*
+	 * Restore percpu access.  Percpu access can happen in exception
+	 * handlers or in complicated helpers like load_gs_index().
+	 */
+#ifdef CONFIG_X86_64
+	wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
 #else
-/* CONFIG_X86_64 */
-	load_idt((const struct desc_ptr *)&ctxt->idt_limit);
+	loadsegment(fs, __KERNEL_PERCPU);
+	loadsegment(gs, __KERNEL_STACK_CANARY);
 #endif
 
+	/* Restore the TSS, RO GDT, LDT, and usermode-relevant MSRs. */
+	fix_processor_context();
+
 	/*
-	 * segment registers
+	 * Now that we have descriptor tables fully restored and working
+	 * exception handling, restore the usermode segments.
 	 */
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_64
+	loadsegment(ds, ctxt->es);
 	loadsegment(es, ctxt->es);
 	loadsegment(fs, ctxt->fs);
-	loadsegment(gs, ctxt->gs);
-	loadsegment(ss, ctxt->ss);
+	load_gs_index(ctxt->gs);
 
 	/*
-	 * sysenter MSRs
+	 * Restore FSBASE and GSBASE after restoring the selectors, since
+	 * restoring the selectors clobbers the bases.  Keep in mind
+	 * that MSR_KERNEL_GS_BASE is horribly misnamed.
 	 */
-	if (boot_cpu_has(X86_FEATURE_SEP))
-		enable_sep_cpu();
-#else
-/* CONFIG_X86_64 */
-	asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds));
-	asm volatile ("movw %0, %%es" :: "r" (ctxt->es));
-	asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs));
-	load_gs_index(ctxt->gs);
-	asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss));
-
 	wrmsrl(MSR_FS_BASE, ctxt->fs_base);
-	wrmsrl(MSR_GS_BASE, ctxt->gs_base);
-	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
+#elif defined(CONFIG_X86_32_LAZY_GS)
+	loadsegment(gs, ctxt->gs);
 #endif
 
-	fix_processor_context();
-
 	do_fpu_end();
 	tsc_verify_tsc_adjust(true);
 	x86_platform.restore_sched_clock_state();
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index 972b8e8d939c..09af7ff53044 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -13,28 +13,28 @@ else
   posttest_64bit = -n
 endif
 
-distill_awk = $(srctree)/arch/x86/tools/distill.awk
+reformatter = $(srctree)/arch/x86/tools/objdump_reformat.awk
 chkobjdump = $(srctree)/arch/x86/tools/chkobjdump.awk
 
 quiet_cmd_posttest = TEST    $@
-      cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(distill_awk) | $(obj)/test_get_len $(posttest_64bit) $(posttest_verbose)
+      cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(reformatter) | $(obj)/insn_decoder_test $(posttest_64bit) $(posttest_verbose)
 
 quiet_cmd_sanitytest = TEST    $@
       cmd_sanitytest = $(obj)/insn_sanity $(posttest_64bit) -m 1000000
 
-posttest: $(obj)/test_get_len vmlinux $(obj)/insn_sanity
+posttest: $(obj)/insn_decoder_test vmlinux $(obj)/insn_sanity
 	$(call cmd,posttest)
 	$(call cmd,sanitytest)
 
-hostprogs-y	+= test_get_len insn_sanity
+hostprogs-y	+= insn_decoder_test insn_sanity
 
 # -I needed for generated C source and C source which in the kernel tree.
-HOSTCFLAGS_test_get_len.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/
+HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/
 
 HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
 
 # Dependencies are also needed.
-$(obj)/test_get_len.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+$(obj)/insn_decoder_test.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
 
 $(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
 
diff --git a/arch/x86/tools/test_get_len.c b/arch/x86/tools/insn_decoder_test.c
index ecf31e0358c8..a3b4fd954931 100644
--- a/arch/x86/tools/test_get_len.c
+++ b/arch/x86/tools/insn_decoder_test.c
@@ -9,10 +9,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright (C) IBM Corporation, 2009
  */
 
@@ -21,6 +17,7 @@
 #include <string.h>
 #include <assert.h>
 #include <unistd.h>
+#include <stdarg.h>
 
 #define unlikely(cond) (cond)
 
@@ -33,7 +30,7 @@
  * particular.  See if insn_get_length() and the disassembler agree
  * on the length of each instruction in an elf disassembly.
  *
- * Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len
+ * Usage: objdump -d a.out | awk -f objdump_reformat.awk | ./insn_decoder_test
  */
 
 const char *prog;
@@ -42,8 +39,8 @@ static int x86_64;
 
 static void usage(void)
 {
-	fprintf(stderr, "Usage: objdump -d a.out | awk -f distill.awk |"
-		" %s [-y|-n] [-v]\n", prog);
+	fprintf(stderr, "Usage: objdump -d a.out | awk -f objdump_reformat.awk"
+		" | %s [-y|-n] [-v]\n", prog);
 	fprintf(stderr, "\t-y	64bit mode\n");
 	fprintf(stderr, "\t-n	32bit mode\n");
 	fprintf(stderr, "\t-v	verbose mode\n");
@@ -52,10 +49,21 @@ static void usage(void)
 
 static void malformed_line(const char *line, int line_nr)
 {
-	fprintf(stderr, "%s: malformed line %d:\n%s", prog, line_nr, line);
+	fprintf(stderr, "%s: error: malformed line %d:\n%s",
+		prog, line_nr, line);
 	exit(3);
 }
 
+static void pr_warn(const char *fmt, ...)
+{
+	va_list ap;
+
+	fprintf(stderr, "%s: warning: ", prog);
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+}
+
 static void dump_field(FILE *fp, const char *name, const char *indent,
 		       struct insn_field *field)
 {
@@ -153,21 +161,20 @@ int main(int argc, char **argv)
 		insn_get_length(&insn);
 		if (insn.length != nb) {
 			warnings++;
-			fprintf(stderr, "Warning: %s found difference at %s\n",
-				prog, sym);
-			fprintf(stderr, "Warning: %s", line);
-			fprintf(stderr, "Warning: objdump says %d bytes, but "
-				"insn_get_length() says %d\n", nb,
-				insn.length);
+			pr_warn("Found an x86 instruction decoder bug, "
+				"please report this.\n", sym);
+			pr_warn("%s", line);
+			pr_warn("objdump says %d bytes, but insn_get_length() "
+				"says %d\n", nb, insn.length);
 			if (verbose)
 				dump_insn(stderr, &insn);
 		}
 	}
 	if (warnings)
-		fprintf(stderr, "Warning: decoded and checked %d"
-			" instructions with %d warnings\n", insns, warnings);
+		pr_warn("Decoded and checked %d instructions with %d "
+			"failures\n", insns, warnings);
 	else
-		fprintf(stdout, "Success: decoded and checked %d"
-			" instructions\n", insns);
+		fprintf(stdout, "%s: success: Decoded and checked %d"
+			" instructions\n", prog, insns);
 	return 0;
 }
diff --git a/arch/x86/tools/distill.awk b/arch/x86/tools/objdump_reformat.awk
index e0edeccc1429..f418c91b71f0 100644
--- a/arch/x86/tools/distill.awk
+++ b/arch/x86/tools/objdump_reformat.awk
@@ -1,7 +1,7 @@
 #!/bin/awk -f
 # SPDX-License-Identifier: GPL-2.0
-# Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len
-# Distills the disassembly as follows:
+# Usage: objdump -d a.out | awk -f objdump_reformat.awk | ./insn_decoder_test
+# Reformats the disassembly as follows:
 # - Removes all lines except the disassembled instructions.
 # - For instructions that exceed 1 line (7 bytes), crams all the hex bytes
 # into a single line.
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 6b830d4cb4c8..de58533d3664 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -57,7 +57,7 @@ static u32 xen_apic_read(u32 reg)
 		return 0;
 
 	if (reg == APIC_LVR)
-		return 0x10;
+		return 0x14;
 #ifdef CONFIG_X86_32
 	if (reg == APIC_LDR)
 		return SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d669e9d89001..c9081c6671f0 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1,8 +1,12 @@
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+#include <linux/bootmem.h>
+#endif
 #include <linux/cpu.h>
 #include <linux/kexec.h>
 
 #include <xen/features.h>
 #include <xen/page.h>
+#include <xen/interface/memory.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -331,3 +335,80 @@ void xen_arch_unregister_cpu(int num)
 }
 EXPORT_SYMBOL(xen_arch_unregister_cpu);
 #endif
+
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+void __init arch_xen_balloon_init(struct resource *hostmem_resource)
+{
+	struct xen_memory_map memmap;
+	int rc;
+	unsigned int i, last_guest_ram;
+	phys_addr_t max_addr = PFN_PHYS(max_pfn);
+	struct e820_table *xen_e820_table;
+	const struct e820_entry *entry;
+	struct resource *res;
+
+	if (!xen_initial_domain())
+		return;
+
+	xen_e820_table = kmalloc(sizeof(*xen_e820_table), GFP_KERNEL);
+	if (!xen_e820_table)
+		return;
+
+	memmap.nr_entries = ARRAY_SIZE(xen_e820_table->entries);
+	set_xen_guest_handle(memmap.buffer, xen_e820_table->entries);
+	rc = HYPERVISOR_memory_op(XENMEM_machine_memory_map, &memmap);
+	if (rc) {
+		pr_warn("%s: Can't read host e820 (%d)\n", __func__, rc);
+		goto out;
+	}
+
+	last_guest_ram = 0;
+	for (i = 0; i < memmap.nr_entries; i++) {
+		if (xen_e820_table->entries[i].addr >= max_addr)
+			break;
+		if (xen_e820_table->entries[i].type == E820_TYPE_RAM)
+			last_guest_ram = i;
+	}
+
+	entry = &xen_e820_table->entries[last_guest_ram];
+	if (max_addr >= entry->addr + entry->size)
+		goto out; /* No unallocated host RAM. */
+
+	hostmem_resource->start = max_addr;
+	hostmem_resource->end = entry->addr + entry->size;
+
+	/*
+	 * Mark non-RAM regions between the end of dom0 RAM and end of host RAM
+	 * as unavailable. The rest of that region can be used for hotplug-based
+	 * ballooning.
+	 */
+	for (; i < memmap.nr_entries; i++) {
+		entry = &xen_e820_table->entries[i];
+
+		if (entry->type == E820_TYPE_RAM)
+			continue;
+
+		if (entry->addr >= hostmem_resource->end)
+			break;
+
+		res = kzalloc(sizeof(*res), GFP_KERNEL);
+		if (!res)
+			goto out;
+
+		res->name = "Unavailable host RAM";
+		res->start = entry->addr;
+		res->end = (entry->addr + entry->size < hostmem_resource->end) ?
+			    entry->addr + entry->size : hostmem_resource->end;
+		rc = insert_resource(hostmem_resource, res);
+		if (rc) {
+			pr_warn("%s: Can't insert [%llx - %llx) (%d)\n",
+				__func__, res->start, res->end, rc);
+			kfree(res);
+			goto  out;
+		}
+	}
+
+ out:
+	kfree(xen_e820_table);
+}
+#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 5b2b3f3f6531..c047f42552e1 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -88,6 +88,8 @@
 #include "multicalls.h"
 #include "pmu.h"
 
+#include "../kernel/cpu/cpu.h" /* get_cpu_cap() */
+
 void *xen_initial_gdt;
 
 static int xen_cpu_up_prepare_pv(unsigned int cpu);
@@ -622,7 +624,7 @@ static struct trap_array_entry trap_array[] = {
 	{ simd_coprocessor_error,      xen_simd_coprocessor_error,      false },
 };
 
-static bool get_trap_addr(void **addr, unsigned int ist)
+static bool __ref get_trap_addr(void **addr, unsigned int ist)
 {
 	unsigned int nr;
 	bool ist_okay = false;
@@ -644,6 +646,14 @@ static bool get_trap_addr(void **addr, unsigned int ist)
 		}
 	}
 
+	if (nr == ARRAY_SIZE(trap_array) &&
+	    *addr >= (void *)early_idt_handler_array[0] &&
+	    *addr < (void *)early_idt_handler_array[NUM_EXCEPTION_VECTORS]) {
+		nr = (*addr - (void *)early_idt_handler_array[0]) /
+		     EARLY_IDT_HANDLER_SIZE;
+		*addr = (void *)xen_early_idt_handler_array[nr];
+	}
+
 	if (WARN_ON(ist != 0 && !ist_okay))
 		return false;
 
@@ -818,7 +828,7 @@ static void xen_load_sp0(unsigned long sp0)
 	mcs = xen_mc_entry(0);
 	MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
-	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
+	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
 void xen_set_iopl_mask(unsigned mask)
@@ -1250,6 +1260,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
 
 	/* Work out if we support NX */
+	get_cpu_cap(&boot_cpu_data);
 	x86_configure_nx();
 
 	/* Get mfn list */
@@ -1262,6 +1273,21 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	xen_setup_gdt(0);
 
 	xen_init_irq_ops();
+
+	/* Let's presume PV guests always boot on vCPU with id 0. */
+	per_cpu(xen_vcpu_id, 0) = 0;
+
+	/*
+	 * Setup xen_vcpu early because idt_setup_early_handler needs it for
+	 * local_irq_disable(), irqs_disabled().
+	 *
+	 * Don't do the full vcpu_info placement stuff until we have
+	 * the cpu_possible_mask and a non-dummy shared_info.
+	 */
+	xen_vcpu_info_reset(0);
+
+	idt_setup_early_handler();
+
 	xen_init_capabilities();
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -1295,18 +1321,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	 */
 	acpi_numa = -1;
 #endif
-	/* Let's presume PV guests always boot on vCPU with id 0. */
-	per_cpu(xen_vcpu_id, 0) = 0;
-
-	/*
-	 * Setup xen_vcpu early because start_kernel needs it for
-	 * local_irq_disable(), irqs_disabled().
-	 *
-	 * Don't do the full vcpu_info placement stuff until we have
-	 * the cpu_possible_mask and a non-dummy shared_info.
-	 */
-	xen_vcpu_info_reset(0);
-
 	WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv));
 
 	local_irq_disable();
diff --git a/arch/x86/xen/mmu_hvm.c b/arch/x86/xen/mmu_hvm.c
index 2cfcfe4f6b2a..dd2ad82eee80 100644
--- a/arch/x86/xen/mmu_hvm.c
+++ b/arch/x86/xen/mmu_hvm.c
@@ -75,6 +75,6 @@ void __init xen_hvm_init_mmu_ops(void)
 	if (is_pagetable_dying_supported())
 		pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
 #ifdef CONFIG_PROC_VMCORE
-	register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram);
+	WARN_ON(register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram));
 #endif
 }
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index fc048ec686e7..d85076223a69 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1325,20 +1325,18 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 {
 	struct {
 		struct mmuext_op op;
-#ifdef CONFIG_SMP
-		DECLARE_BITMAP(mask, num_processors);
-#else
 		DECLARE_BITMAP(mask, NR_CPUS);
-#endif
 	} *args;
 	struct multicall_space mcs;
+	const size_t mc_entry_size = sizeof(args->op) +
+		sizeof(args->mask[0]) * BITS_TO_LONGS(num_possible_cpus());
 
 	trace_xen_mmu_flush_tlb_others(cpus, info->mm, info->start, info->end);
 
 	if (cpumask_empty(cpus))
 		return;		/* nothing to do */
 
-	mcs = xen_mc_entry(sizeof(*args));
+	mcs = xen_mc_entry(mc_entry_size);
 	args = mcs.args;
 	args->op.arg2.vcpumask = to_cpumask(args->mask);
 
@@ -1902,6 +1900,18 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* Graft it onto L4[511][510] */
 	copy_page(level2_kernel_pgt, l2);
 
+	/*
+	 * Zap execute permission from the ident map. Due to the sharing of
+	 * L1 entries we need to do this in the L2.
+	 */
+	if (__supported_pte_mask & _PAGE_NX) {
+		for (i = 0; i < PTRS_PER_PMD; ++i) {
+			if (pmd_none(level2_ident_pgt[i]))
+				continue;
+			level2_ident_pgt[i] = pmd_set_flags(level2_ident_pgt[i], _PAGE_NX);
+		}
+	}
+
 	/* Copy the initial P->M table mappings if necessary. */
 	i = pgd_index(xen_start_info->mfn_list);
 	if (i && i < pgd_index(__START_KERNEL_map))
@@ -2261,7 +2271,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 
 	switch (idx) {
 	case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
-	case FIX_RO_IDT:
 #ifdef CONFIG_X86_32
 	case FIX_WP_TEST:
 # ifdef CONFIG_HIGHMEM
@@ -2272,7 +2281,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:
-	case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END:
 		/* All local page mappings */
 		pte = pfn_pte(phys, prot);
 		break;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index c114ca767b3b..6e0d2086eacb 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -808,7 +808,6 @@ char * __init xen_memory_setup(void)
 	addr = xen_e820_table.entries[0].addr;
 	size = xen_e820_table.entries[0].size;
 	while (i < xen_e820_table.nr_entries) {
-		bool discard = false;
 
 		chunk_size = size;
 		type = xen_e820_table.entries[i].type;
@@ -824,11 +823,10 @@ char * __init xen_memory_setup(void)
 				xen_add_extra_mem(pfn_s, n_pfns);
 				xen_max_p2m_pfn = pfn_s + n_pfns;
 			} else
-				discard = true;
+				type = E820_TYPE_UNUSABLE;
 		}
 
-		if (!discard)
-			xen_align_and_add_e820_region(addr, chunk_size, type);
+		xen_align_and_add_e820_region(addr, chunk_size, type);
 
 		addr += chunk_size;
 		size -= chunk_size;
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 02f3445a2b5f..cd97a62394e7 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -23,8 +23,6 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
 static DEFINE_PER_CPU(char *, irq_name);
 static bool xen_pvspin = true;
 
-#include <asm/qspinlock.h>
-
 static void xen_qlock_kick(int cpu)
 {
 	int irq = per_cpu(lock_kicker_irq, cpu);
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 8a10c9a9e2b5..417b339e5c8e 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -15,6 +15,7 @@
 
 #include <xen/interface/xen.h>
 
+#include <linux/init.h>
 #include <linux/linkage.h>
 
 .macro xen_pv_trap name
@@ -54,6 +55,19 @@ xen_pv_trap entry_INT80_compat
 #endif
 xen_pv_trap hypervisor_callback
 
+	__INIT
+ENTRY(xen_early_idt_handler_array)
+	i = 0
+	.rept NUM_EXCEPTION_VECTORS
+	pop %rcx
+	pop %r11
+	jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE
+	i = i + 1
+	.fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
+	.endr
+END(xen_early_idt_handler_array)
+	__FINIT
+
 hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
 /*
  * Xen64 iret frame:
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 75011b80660f..3b34745d0a52 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -72,7 +72,7 @@ u64 xen_clocksource_read(void);
 void xen_setup_cpu_clockevents(void);
 void xen_save_time_memory_area(void);
 void xen_restore_time_memory_area(void);
-void __init xen_init_time_ops(void);
+void __ref xen_init_time_ops(void);
 void __init xen_hvm_init_time_ops(void);
 
 irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 8bc52f749f20..c921e8bccdc8 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -15,6 +15,9 @@ config XTENSA
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
+	select GENERIC_STRNCPY_FROM_USER if KASAN
+	select HAVE_ARCH_KASAN if MMU
+	select HAVE_CC_STACKPROTECTOR
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
@@ -79,6 +82,10 @@ config VARIANT_IRQ_SWITCH
 config HAVE_XTENSA_GPIO32
 	def_bool n
 
+config KASAN_SHADOW_OFFSET
+	hex
+	default 0x6e400000
+
 menu "Processor type and features"
 
 choice
diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index 7ee02fe4a63d..3a934b72a272 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -42,10 +42,11 @@ export PLATFORM
 
 # temporarily until string.h is fixed
 KBUILD_CFLAGS += -ffreestanding -D__linux__
-
-KBUILD_CFLAGS += -pipe -mlongcalls
-
+KBUILD_CFLAGS += -pipe -mlongcalls -mtext-section-literals
 KBUILD_CFLAGS += $(call cc-option,-mforce-no-pic,)
+KBUILD_CFLAGS += $(call cc-option,-mno-serialize-volatile,)
+
+KBUILD_AFLAGS += -mlongcalls -mtext-section-literals
 
 ifneq ($(CONFIG_LD_NO_RELAX),)
 LDFLAGS := --no-relax
diff --git a/arch/xtensa/boot/boot-redboot/bootstrap.S b/arch/xtensa/boot/boot-redboot/bootstrap.S
index bf7fabe6310d..bbf3b4b080cd 100644
--- a/arch/xtensa/boot/boot-redboot/bootstrap.S
+++ b/arch/xtensa/boot/boot-redboot/bootstrap.S
@@ -42,6 +42,7 @@ __start_a0:
 	.align 4
 
 	.section .text, "ax"
+	.literal_position
 	.begin literal_prefix .text
 
 	/* put literals in here! */
diff --git a/arch/xtensa/boot/lib/Makefile b/arch/xtensa/boot/lib/Makefile
index d2a7f48564a4..355127faade1 100644
--- a/arch/xtensa/boot/lib/Makefile
+++ b/arch/xtensa/boot/lib/Makefile
@@ -15,6 +15,12 @@ CFLAGS_REMOVE_inftrees.o = -pg
 CFLAGS_REMOVE_inffast.o = -pg
 endif
 
+KASAN_SANITIZE := n
+
+CFLAGS_REMOVE_inflate.o += -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_zmem.o += -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_inftrees.o += -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_inffast.o += -fstack-protector -fstack-protector-strong
 
 quiet_cmd_copy_zlib = COPY    $@
       cmd_copy_zlib = cat $< > $@
diff --git a/arch/xtensa/configs/audio_kc705_defconfig b/arch/xtensa/configs/audio_kc705_defconfig
index 8d16925765cb..2bf964df37ba 100644
--- a/arch/xtensa/configs/audio_kc705_defconfig
+++ b/arch/xtensa/configs/audio_kc705_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IRQ_TIME_ACCOUNTING=y
diff --git a/arch/xtensa/configs/cadence_csp_defconfig b/arch/xtensa/configs/cadence_csp_defconfig
index f2d3094aa1d1..3221b7053fa3 100644
--- a/arch/xtensa/configs/cadence_csp_defconfig
+++ b/arch/xtensa/configs/cadence_csp_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_USELIB=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IRQ_TIME_ACCOUNTING=y
diff --git a/arch/xtensa/configs/generic_kc705_defconfig b/arch/xtensa/configs/generic_kc705_defconfig
index 744adeaf2945..985fa8546e4e 100644
--- a/arch/xtensa/configs/generic_kc705_defconfig
+++ b/arch/xtensa/configs/generic_kc705_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IRQ_TIME_ACCOUNTING=y
diff --git a/arch/xtensa/configs/nommu_kc705_defconfig b/arch/xtensa/configs/nommu_kc705_defconfig
index 78c2529d0459..624f9b3a3878 100644
--- a/arch/xtensa/configs/nommu_kc705_defconfig
+++ b/arch/xtensa/configs/nommu_kc705_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IRQ_TIME_ACCOUNTING=y
diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig
index 14e3ca353ac8..11fed6c06a7c 100644
--- a/arch/xtensa/configs/smp_lx200_defconfig
+++ b/arch/xtensa/configs/smp_lx200_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IRQ_TIME_ACCOUNTING=y
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index dff7cc39437c..436b20337168 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -1,5 +1,4 @@
 generic-y += bug.h
-generic-y += clkdev.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += dma-contiguous.h
diff --git a/arch/xtensa/include/asm/asmmacro.h b/arch/xtensa/include/asm/asmmacro.h
index 746dcc8b5abc..7f2ae5872151 100644
--- a/arch/xtensa/include/asm/asmmacro.h
+++ b/arch/xtensa/include/asm/asmmacro.h
@@ -150,5 +150,45 @@
 		__endl	\ar \as
 	.endm
 
+/* Load or store instructions that may cause exceptions use the EX macro. */
+
+#define EX(handler)				\
+	.section __ex_table, "a";		\
+	.word	97f, handler;			\
+	.previous				\
+97:
+
+
+/*
+ * Extract unaligned word that is split between two registers w0 and w1
+ * into r regardless of machine endianness. SAR must be loaded with the
+ * starting bit of the word (see __ssa8).
+ */
+
+	.macro __src_b	r, w0, w1
+#ifdef __XTENSA_EB__
+		src	\r, \w0, \w1
+#else
+		src	\r, \w1, \w0
+#endif
+	.endm
+
+/*
+ * Load 2 lowest address bits of r into SAR for __src_b to extract unaligned
+ * word starting at r from two registers loaded from consecutive aligned
+ * addresses covering r regardless of machine endianness.
+ *
+ *      r   0   1   2   3
+ * LE SAR   0   8  16  24
+ * BE SAR  32  24  16   8
+ */
+
+	.macro __ssa8	r
+#ifdef __XTENSA_EB__
+		ssa8b	\r
+#else
+		ssa8l	\r
+#endif
+	.endm
 
 #endif /* _XTENSA_ASMMACRO_H */
diff --git a/arch/xtensa/include/asm/current.h b/arch/xtensa/include/asm/current.h
index 47e46dcf5d49..5d98a7ad4251 100644
--- a/arch/xtensa/include/asm/current.h
+++ b/arch/xtensa/include/asm/current.h
@@ -11,6 +11,8 @@
 #ifndef _XTENSA_CURRENT_H
 #define _XTENSA_CURRENT_H
 
+#include <asm/thread_info.h>
+
 #ifndef __ASSEMBLY__
 
 #include <linux/thread_info.h>
@@ -26,8 +28,6 @@ static inline struct task_struct *get_current(void)
 
 #else
 
-#define CURRENT_SHIFT 13
-
 #define GET_CURRENT(reg,sp)		\
 	GET_THREAD_INFO(reg,sp);	\
 	l32i reg, reg, TI_TASK		\
diff --git a/arch/xtensa/include/asm/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h
index 153bf2370988..44098800dad7 100644
--- a/arch/xtensa/include/asm/dma-mapping.h
+++ b/arch/xtensa/include/asm/dma-mapping.h
@@ -23,14 +23,4 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return &xtensa_dma_map_ops;
 }
 
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return (dma_addr_t)paddr;
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return (phys_addr_t)daddr;
-}
-
 #endif	/* _XTENSA_DMA_MAPPING_H */
diff --git a/arch/xtensa/include/asm/fixmap.h b/arch/xtensa/include/asm/fixmap.h
index 0d30403b6c95..7e25c1b50ac0 100644
--- a/arch/xtensa/include/asm/fixmap.h
+++ b/arch/xtensa/include/asm/fixmap.h
@@ -44,7 +44,7 @@ enum fixed_addresses {
 	__end_of_fixed_addresses
 };
 
-#define FIXADDR_TOP     (VMALLOC_START - PAGE_SIZE)
+#define FIXADDR_TOP     (XCHAL_KSEG_CACHED_VADDR - PAGE_SIZE)
 #define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
 #define FIXADDR_START	((FIXADDR_TOP - FIXADDR_SIZE) & PMD_MASK)
 
@@ -63,7 +63,7 @@ static __always_inline unsigned long fix_to_virt(const unsigned int idx)
 	 * table.
 	 */
 	BUILD_BUG_ON(FIXADDR_START <
-		     XCHAL_PAGE_TABLE_VADDR + XCHAL_PAGE_TABLE_SIZE);
+		     TLBTEMP_BASE_1 + TLBTEMP_SIZE);
 	BUILD_BUG_ON(idx >= __end_of_fixed_addresses);
 	return __fix_to_virt(idx);
 }
diff --git a/arch/xtensa/include/asm/futex.h b/arch/xtensa/include/asm/futex.h
index eaaf1ebcc7a4..5bfbc1c401d4 100644
--- a/arch/xtensa/include/asm/futex.h
+++ b/arch/xtensa/include/asm/futex.h
@@ -92,7 +92,6 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
 	int ret = 0;
-	u32 prev;
 
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
@@ -103,26 +102,24 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 
 	__asm__ __volatile__ (
 	"	# futex_atomic_cmpxchg_inatomic\n"
-	"1:	l32i	%1, %3, 0\n"
-	"	mov	%0, %5\n"
-	"	wsr	%1, scompare1\n"
-	"2:	s32c1i	%0, %3, 0\n"
-	"3:\n"
+	"	wsr	%5, scompare1\n"
+	"1:	s32c1i	%1, %4, 0\n"
+	"	s32i	%1, %6, 0\n"
+	"2:\n"
 	"	.section .fixup,\"ax\"\n"
 	"	.align 4\n"
-	"4:	.long	3b\n"
-	"5:	l32r	%1, 4b\n"
-	"	movi	%0, %6\n"
+	"3:	.long	2b\n"
+	"4:	l32r	%1, 3b\n"
+	"	movi	%0, %7\n"
 	"	jx	%1\n"
 	"	.previous\n"
 	"	.section __ex_table,\"a\"\n"
-	"	.long 1b,5b,2b,5b\n"
+	"	.long 1b,4b\n"
 	"	.previous\n"
-	: "+r" (ret), "=&r" (prev), "+m" (*uaddr)
-	: "r" (uaddr), "r" (oldval), "r" (newval), "I" (-EFAULT)
+	: "+r" (ret), "+r" (newval), "+m" (*uaddr), "+m" (*uval)
+	: "r" (uaddr), "r" (oldval), "r" (uval), "I" (-EFAULT)
 	: "memory");
 
-	*uval = prev;
 	return ret;
 }
 
diff --git a/arch/xtensa/include/asm/highmem.h b/arch/xtensa/include/asm/highmem.h
index 6e070db1022e..04e9340eac4b 100644
--- a/arch/xtensa/include/asm/highmem.h
+++ b/arch/xtensa/include/asm/highmem.h
@@ -72,7 +72,7 @@ static inline void *kmap(struct page *page)
 	 * page table.
 	 */
 	BUILD_BUG_ON(PKMAP_BASE <
-		     XCHAL_PAGE_TABLE_VADDR + XCHAL_PAGE_TABLE_SIZE);
+		     TLBTEMP_BASE_1 + TLBTEMP_SIZE);
 	BUG_ON(in_interrupt());
 	if (!PageHighMem(page))
 		return page_address(page);
diff --git a/arch/xtensa/include/asm/kasan.h b/arch/xtensa/include/asm/kasan.h
new file mode 100644
index 000000000000..54be80876e57
--- /dev/null
+++ b/arch/xtensa/include/asm/kasan.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_KASAN
+
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <asm/kmem_layout.h>
+
+/* Start of area covered by KASAN */
+#define KASAN_START_VADDR __XTENSA_UL_CONST(0x90000000)
+/* Start of the shadow map */
+#define KASAN_SHADOW_START (XCHAL_PAGE_TABLE_VADDR + XCHAL_PAGE_TABLE_SIZE)
+/* Size of the shadow map */
+#define KASAN_SHADOW_SIZE (-KASAN_START_VADDR >> KASAN_SHADOW_SCALE_SHIFT)
+/* Offset for mem to shadow address transformation */
+#define KASAN_SHADOW_OFFSET __XTENSA_UL_CONST(CONFIG_KASAN_SHADOW_OFFSET)
+
+void __init kasan_early_init(void);
+void __init kasan_init(void);
+
+#else
+
+static inline void kasan_early_init(void)
+{
+}
+
+static inline void kasan_init(void)
+{
+}
+
+#endif
+#endif
+#endif
diff --git a/arch/xtensa/include/asm/kmem_layout.h b/arch/xtensa/include/asm/kmem_layout.h
index 561f8729bcde..2317c835a4db 100644
--- a/arch/xtensa/include/asm/kmem_layout.h
+++ b/arch/xtensa/include/asm/kmem_layout.h
@@ -71,4 +71,11 @@
 
 #endif
 
+#ifndef CONFIG_KASAN
+#define KERNEL_STACK_SHIFT	13
+#else
+#define KERNEL_STACK_SHIFT	15
+#endif
+#define KERNEL_STACK_SIZE	(1 << KERNEL_STACK_SHIFT)
+
 #endif
diff --git a/arch/xtensa/include/asm/linkage.h b/arch/xtensa/include/asm/linkage.h
new file mode 100644
index 000000000000..0ba9973235d9
--- /dev/null
+++ b/arch/xtensa/include/asm/linkage.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+#define __ALIGN		.align 4
+#define __ALIGN_STR	".align 4"
+
+#endif
diff --git a/arch/xtensa/include/asm/mmu_context.h b/arch/xtensa/include/asm/mmu_context.h
index f7e186dfc4e4..de5e6cbbafe4 100644
--- a/arch/xtensa/include/asm/mmu_context.h
+++ b/arch/xtensa/include/asm/mmu_context.h
@@ -52,6 +52,7 @@ DECLARE_PER_CPU(unsigned long, asid_cache);
 #define ASID_INSERT(x)	(0x03020001 | (((x) & ASID_MASK) << 8))
 
 void init_mmu(void);
+void init_kio(void);
 
 static inline void set_rasid_register (unsigned long val)
 {
diff --git a/arch/xtensa/include/asm/nommu_context.h b/arch/xtensa/include/asm/nommu_context.h
index 2cebdbbdb633..37251b2ef871 100644
--- a/arch/xtensa/include/asm/nommu_context.h
+++ b/arch/xtensa/include/asm/nommu_context.h
@@ -3,6 +3,10 @@ static inline void init_mmu(void)
 {
 }
 
+static inline void init_kio(void)
+{
+}
+
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 }
diff --git a/arch/xtensa/include/asm/page.h b/arch/xtensa/include/asm/page.h
index 4ddbfd57a7c8..5d69c11c01b8 100644
--- a/arch/xtensa/include/asm/page.h
+++ b/arch/xtensa/include/asm/page.h
@@ -36,8 +36,6 @@
 #define MAX_LOW_PFN	PHYS_PFN(0xfffffffful)
 #endif
 
-#define PGTABLE_START	0x80000000
-
 /*
  * Cache aliasing:
  *
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 30dd5b2e4ad5..38802259978f 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -12,9 +12,9 @@
 #define _XTENSA_PGTABLE_H
 
 #define __ARCH_USE_5LEVEL_HACK
-#include <asm-generic/pgtable-nopmd.h>
 #include <asm/page.h>
 #include <asm/kmem_layout.h>
+#include <asm-generic/pgtable-nopmd.h>
 
 /*
  * We only use two ring levels, user and kernel space.
@@ -170,6 +170,7 @@
 #define PAGE_SHARED_EXEC \
 	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_WRITABLE | _PAGE_HW_EXEC)
 #define PAGE_KERNEL	   __pgprot(_PAGE_PRESENT | _PAGE_HW_WRITE)
+#define PAGE_KERNEL_RO	   __pgprot(_PAGE_PRESENT)
 #define PAGE_KERNEL_EXEC   __pgprot(_PAGE_PRESENT|_PAGE_HW_WRITE|_PAGE_HW_EXEC)
 
 #if (DCACHE_WAY_SIZE > PAGE_SIZE)
diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h
index e2d9c5eb10bd..3a5c5918aea3 100644
--- a/arch/xtensa/include/asm/ptrace.h
+++ b/arch/xtensa/include/asm/ptrace.h
@@ -10,6 +10,7 @@
 #ifndef _XTENSA_PTRACE_H
 #define _XTENSA_PTRACE_H
 
+#include <asm/kmem_layout.h>
 #include <uapi/asm/ptrace.h>
 
 /*
@@ -38,20 +39,6 @@
  *		+-----------------------+ --------
  */
 
-#define KERNEL_STACK_SIZE (2 * PAGE_SIZE)
-
-/*  Offsets for exception_handlers[] (3 x 64-entries x 4-byte tables). */
-
-#define EXC_TABLE_KSTK		0x004	/* Kernel Stack */
-#define EXC_TABLE_DOUBLE_SAVE	0x008	/* Double exception save area for a0 */
-#define EXC_TABLE_FIXUP		0x00c	/* Fixup handler */
-#define EXC_TABLE_PARAM		0x010	/* For passing a parameter to fixup */
-#define EXC_TABLE_SYSCALL_SAVE	0x014	/* For fast syscall handler */
-#define EXC_TABLE_FAST_USER	0x100	/* Fast user exception handler */
-#define EXC_TABLE_FAST_KERNEL	0x200	/* Fast kernel exception handler */
-#define EXC_TABLE_DEFAULT	0x300	/* Default C-Handler */
-#define EXC_TABLE_SIZE		0x400
-
 #ifndef __ASSEMBLY__
 
 #include <asm/coprocessor.h>
diff --git a/arch/xtensa/include/asm/regs.h b/arch/xtensa/include/asm/regs.h
index 881a1134a4b4..477594e5817f 100644
--- a/arch/xtensa/include/asm/regs.h
+++ b/arch/xtensa/include/asm/regs.h
@@ -76,6 +76,7 @@
 #define EXCCAUSE_COPROCESSOR5_DISABLED		37
 #define EXCCAUSE_COPROCESSOR6_DISABLED		38
 #define EXCCAUSE_COPROCESSOR7_DISABLED		39
+#define EXCCAUSE_N				64
 
 /*  PS register fields.  */
 
diff --git a/arch/xtensa/include/asm/stackprotector.h b/arch/xtensa/include/asm/stackprotector.h
new file mode 100644
index 000000000000..e368f94fd2af
--- /dev/null
+++ b/arch/xtensa/include/asm/stackprotector.h
@@ -0,0 +1,40 @@
+/*
+ * GCC stack protector support.
+ *
+ * (This is directly adopted from the ARM implementation)
+ *
+ * Stack protector works by putting predefined pattern at the start of
+ * the stack frame and verifying that it hasn't been overwritten when
+ * returning from the function.  The pattern is called stack canary
+ * and gcc expects it to be defined by a global variable called
+ * "__stack_chk_guard" on Xtensa.  This unfortunately means that on SMP
+ * we cannot have a different canary value per task.
+ */
+
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+#include <linux/random.h>
+#include <linux/version.h>
+
+extern unsigned long __stack_chk_guard;
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+	unsigned long canary;
+
+	/* Try to get a semi random initial value. */
+	get_random_bytes(&canary, sizeof(canary));
+	canary ^= LINUX_VERSION_CODE;
+
+	current->stack_canary = canary;
+	__stack_chk_guard = current->stack_canary;
+}
+
+#endif	/* _ASM_STACKPROTECTOR_H */
diff --git a/arch/xtensa/include/asm/string.h b/arch/xtensa/include/asm/string.h
index 8d5d9dfadb09..89b51a0c752f 100644
--- a/arch/xtensa/include/asm/string.h
+++ b/arch/xtensa/include/asm/string.h
@@ -53,7 +53,7 @@ static inline char *strncpy(char *__dest, const char *__src, size_t __n)
 		"bne	%1, %5, 1b\n"
 		"2:"
 		: "=r" (__dest), "=r" (__src), "=&r" (__dummy)
-		: "0" (__dest), "1" (__src), "r" (__src+__n)
+		: "0" (__dest), "1" (__src), "r" ((uintptr_t)__src+__n)
 		: "memory");
 
 	return __xdest;
@@ -101,21 +101,40 @@ static inline int strncmp(const char *__cs, const char *__ct, size_t __n)
 		"2:\n\t"
 		"sub	%2, %2, %3"
 		: "=r" (__cs), "=r" (__ct), "=&r" (__res), "=&r" (__dummy)
-		: "0" (__cs), "1" (__ct), "r" (__cs+__n));
+		: "0" (__cs), "1" (__ct), "r" ((uintptr_t)__cs+__n));
 
 	return __res;
 }
 
 #define __HAVE_ARCH_MEMSET
 extern void *memset(void *__s, int __c, size_t __count);
+extern void *__memset(void *__s, int __c, size_t __count);
 
 #define __HAVE_ARCH_MEMCPY
 extern void *memcpy(void *__to, __const__ void *__from, size_t __n);
+extern void *__memcpy(void *__to, __const__ void *__from, size_t __n);
 
 #define __HAVE_ARCH_MEMMOVE
 extern void *memmove(void *__dest, __const__ void *__src, size_t __n);
+extern void *__memmove(void *__dest, __const__ void *__src, size_t __n);
 
 /* Don't build bcopy at all ...  */
 #define __HAVE_ARCH_BCOPY
 
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+
+/*
+ * For files that are not instrumented (e.g. mm/slub.c) we
+ * should use not instrumented version of mem* functions.
+ */
+
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memmove(dst, src, len) __memmove(dst, src, len)
+#define memset(s, c, n) __memset(s, c, n)
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+#endif
+
 #endif	/* _XTENSA_STRING_H */
diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h
index 7be2400f745a..2bd19ae61e47 100644
--- a/arch/xtensa/include/asm/thread_info.h
+++ b/arch/xtensa/include/asm/thread_info.h
@@ -11,7 +11,9 @@
 #ifndef _XTENSA_THREAD_INFO_H
 #define _XTENSA_THREAD_INFO_H
 
-#ifdef __KERNEL__
+#include <asm/kmem_layout.h>
+
+#define CURRENT_SHIFT KERNEL_STACK_SHIFT
 
 #ifndef __ASSEMBLY__
 # include <asm/processor.h>
@@ -77,14 +79,11 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
 /* how to get the thread information struct from C */
 static inline struct thread_info *current_thread_info(void)
 {
 	struct thread_info *ti;
-	 __asm__("extui %0,a1,0,13\n\t"
+	 __asm__("extui %0, a1, 0, "__stringify(CURRENT_SHIFT)"\n\t"
 	         "xor %0, a1, %0" : "=&r" (ti) : );
 	return ti;
 }
@@ -93,7 +92,7 @@ static inline struct thread_info *current_thread_info(void)
 
 /* how to get the thread information struct from ASM */
 #define GET_THREAD_INFO(reg,sp) \
-	extui reg, sp, 0, 13; \
+	extui reg, sp, 0, CURRENT_SHIFT; \
 	xor   reg, sp, reg
 #endif
 
@@ -130,8 +129,7 @@ static inline struct thread_info *current_thread_info(void)
  */
 #define TS_USEDFPU		0x0001	/* FPU was used by this task this quantum (SMP) */
 
-#define THREAD_SIZE 8192	//(2*PAGE_SIZE)
-#define THREAD_SIZE_ORDER 1
+#define THREAD_SIZE KERNEL_STACK_SIZE
+#define THREAD_SIZE_ORDER (KERNEL_STACK_SHIFT - PAGE_SHIFT)
 
-#endif	/* __KERNEL__ */
 #endif	/* _XTENSA_THREAD_INFO */
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 2e69aa4b843f..f5cd7a7e65e0 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -13,12 +13,47 @@
 #include <asm/ptrace.h>
 
 /*
+ * Per-CPU exception handling data structure.
+ * EXCSAVE1 points to it.
+ */
+struct exc_table {
+	/* Kernel Stack */
+	void *kstk;
+	/* Double exception save area for a0 */
+	unsigned long double_save;
+	/* Fixup handler */
+	void *fixup;
+	/* For passing a parameter to fixup */
+	void *fixup_param;
+	/* For fast syscall handler */
+	unsigned long syscall_save;
+	/* Fast user exception handlers */
+	void *fast_user_handler[EXCCAUSE_N];
+	/* Fast kernel exception handlers */
+	void *fast_kernel_handler[EXCCAUSE_N];
+	/* Default C-Handlers */
+	void *default_handler[EXCCAUSE_N];
+};
+
+/*
  * handler must be either of the following:
  *  void (*)(struct pt_regs *regs);
  *  void (*)(struct pt_regs *regs, unsigned long exccause);
  */
 extern void * __init trap_set_handler(int cause, void *handler);
 extern void do_unhandled(struct pt_regs *regs, unsigned long exccause);
+void fast_second_level_miss(void);
+
+/* Initialize minimal exc_table structure sufficient for basic paging */
+static inline void __init early_trap_init(void)
+{
+	static struct exc_table exc_table __initdata = {
+		.fast_kernel_handler[EXCCAUSE_DTLB_MISS] =
+			fast_second_level_miss,
+	};
+	__asm__ __volatile__("wsr  %0, excsave1\n" : : "a" (&exc_table));
+}
+
 void secondary_trap_init(void);
 
 static inline void spill_registers(void)
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index b8f152b6aaa5..f1158b4c629c 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -44,6 +44,8 @@
 #define __access_ok(addr, size) (__kernel_ok || __user_ok((addr), (size)))
 #define access_ok(type, addr, size) __access_ok((unsigned long)(addr), (size))
 
+#define user_addr_max() (uaccess_kernel() ? ~0UL : TASK_SIZE)
+
 /*
  * These are the main single-value transfer routines.  They
  * automatically use the right size if we just have the right pointer
@@ -261,7 +263,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 static inline unsigned long
 __xtensa_clear_user(void *addr, unsigned long size)
 {
-	if ( ! memset(addr, 0, size) )
+	if (!__memset(addr, 0, size))
 		return size;
 	return 0;
 }
@@ -277,6 +279,8 @@ clear_user(void *addr, unsigned long size)
 #define __clear_user  __xtensa_clear_user
 
 
+#ifndef CONFIG_GENERIC_STRNCPY_FROM_USER
+
 extern long __strncpy_user(char *, const char *, long);
 
 static inline long
@@ -286,6 +290,9 @@ strncpy_from_user(char *dst, const char *src, long count)
 		return __strncpy_user(dst, src, count);
 	return -EFAULT;
 }
+#else
+long strncpy_from_user(char *dst, const char *src, long count);
+#endif
 
 /*
  * Return the size of a string (including the ending 0!)
diff --git a/arch/xtensa/include/uapi/asm/Kbuild b/arch/xtensa/include/uapi/asm/Kbuild
index a5bcdfb890f1..837d4dd76785 100644
--- a/arch/xtensa/include/uapi/asm/Kbuild
+++ b/arch/xtensa/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
diff --git a/arch/xtensa/include/uapi/asm/poll.h b/arch/xtensa/include/uapi/asm/poll.h
index 4d249040b33d..e3246d41182c 100644
--- a/arch/xtensa/include/uapi/asm/poll.h
+++ b/arch/xtensa/include/uapi/asm/poll.h
@@ -12,9 +12,26 @@
 #ifndef _XTENSA_POLL_H
 #define _XTENSA_POLL_H
 
+#ifndef __KERNEL__
 #define POLLWRNORM	POLLOUT
-#define POLLWRBAND	0x0100
-#define POLLREMOVE	0x0800
+#define POLLWRBAND	(__force __poll_t)0x0100
+#define POLLREMOVE	(__force __poll_t)0x0800
+#else
+#define __ARCH_HAS_MANGLED_POLL
+static inline __u16 mangle_poll(__poll_t val)
+{
+	__u16 v = (__force __u16)val;
+	/* bit 9 -> bit 8, bit 8 -> bit 2 */
+	return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6);
+}
+
+static inline __poll_t demangle_poll(__u16 v)
+{
+        /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
+	return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
+				((v & 4) << 6));
+}
+#endif
 
 #include <asm-generic/poll.h>
 
diff --git a/arch/xtensa/kernel/Makefile b/arch/xtensa/kernel/Makefile
index bb8d55775a97..91907590d183 100644
--- a/arch/xtensa/kernel/Makefile
+++ b/arch/xtensa/kernel/Makefile
@@ -17,9 +17,6 @@ obj-$(CONFIG_XTENSA_VARIANT_HAVE_PERF_EVENTS) += perf_event.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
 obj-$(CONFIG_S32C1I_SELFTEST) += s32c1i_selftest.o
 
-AFLAGS_head.o += -mtext-section-literals
-AFLAGS_mxhead.o += -mtext-section-literals
-
 # In the Xtensa architecture, assembly generates literals which must always
 # precede the L32R instruction with a relative offset less than 256 kB.
 # Therefore, the .text and .literal section must be combined in parenthesis
diff --git a/arch/xtensa/kernel/align.S b/arch/xtensa/kernel/align.S
index 890004af03a9..9301452e521e 100644
--- a/arch/xtensa/kernel/align.S
+++ b/arch/xtensa/kernel/align.S
@@ -19,6 +19,7 @@
 #include <linux/linkage.h>
 #include <asm/current.h>
 #include <asm/asm-offsets.h>
+#include <asm/asmmacro.h>
 #include <asm/processor.h>
 
 #if XCHAL_UNALIGNED_LOAD_EXCEPTION || XCHAL_UNALIGNED_STORE_EXCEPTION
@@ -66,8 +67,6 @@
 #define	INSN_T		24
 #define	INSN_OP1	16
 
-.macro __src_b	r, w0, w1;	src	\r, \w0, \w1;	.endm
-.macro __ssa8	r;		ssa8b	\r;		.endm
 .macro __ssa8r	r;		ssa8l	\r;		.endm
 .macro __sh	r, s;		srl	\r, \s;		.endm
 .macro __sl	r, s;		sll	\r, \s;		.endm
@@ -81,8 +80,6 @@
 #define	INSN_T		4
 #define	INSN_OP1	12
 
-.macro __src_b	r, w0, w1;	src	\r, \w1, \w0;	.endm
-.macro __ssa8	r;		ssa8l	\r;		.endm
 .macro __ssa8r	r;		ssa8b	\r;		.endm
 .macro __sh	r, s;		sll	\r, \s;		.endm
 .macro __sl	r, s;		srl	\r, \s;		.endm
@@ -155,7 +152,7 @@
  *	     <  VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
  */
 
-
+	.literal_position
 ENTRY(fast_unaligned)
 
 	/* Note: We don't expect the address to be aligned on a word
diff --git a/arch/xtensa/kernel/asm-offsets.c b/arch/xtensa/kernel/asm-offsets.c
index bcb5beb81177..022cf918ec20 100644
--- a/arch/xtensa/kernel/asm-offsets.c
+++ b/arch/xtensa/kernel/asm-offsets.c
@@ -76,6 +76,9 @@ int main(void)
 	DEFINE(TASK_PID, offsetof (struct task_struct, pid));
 	DEFINE(TASK_THREAD, offsetof (struct task_struct, thread));
 	DEFINE(TASK_THREAD_INFO, offsetof (struct task_struct, stack));
+#ifdef CONFIG_CC_STACKPROTECTOR
+	DEFINE(TASK_STACK_CANARY, offsetof(struct task_struct, stack_canary));
+#endif
 	DEFINE(TASK_STRUCT_SIZE, sizeof (struct task_struct));
 
 	/* offsets in thread_info struct */
@@ -129,5 +132,18 @@ int main(void)
 	       offsetof(struct debug_table, icount_level_save));
 #endif
 
+	/* struct exc_table */
+	DEFINE(EXC_TABLE_KSTK, offsetof(struct exc_table, kstk));
+	DEFINE(EXC_TABLE_DOUBLE_SAVE, offsetof(struct exc_table, double_save));
+	DEFINE(EXC_TABLE_FIXUP, offsetof(struct exc_table, fixup));
+	DEFINE(EXC_TABLE_PARAM, offsetof(struct exc_table, fixup_param));
+	DEFINE(EXC_TABLE_SYSCALL_SAVE,
+	       offsetof(struct exc_table, syscall_save));
+	DEFINE(EXC_TABLE_FAST_USER,
+	       offsetof(struct exc_table, fast_user_handler));
+	DEFINE(EXC_TABLE_FAST_KERNEL,
+	       offsetof(struct exc_table, fast_kernel_handler));
+	DEFINE(EXC_TABLE_DEFAULT, offsetof(struct exc_table, default_handler));
+
 	return 0;
 }
diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S
index 3a98503ad11a..4f8b52d575a2 100644
--- a/arch/xtensa/kernel/coprocessor.S
+++ b/arch/xtensa/kernel/coprocessor.S
@@ -212,8 +212,7 @@ ENDPROC(coprocessor_restore)
 ENTRY(fast_coprocessor_double)
 
 	wsr	a0, excsave1
-	movi	a0, unrecoverable_exception
-	callx0	a0
+	call0	unrecoverable_exception
 
 ENDPROC(fast_coprocessor_double)
 
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 37a239556889..5caff0744f3c 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -14,6 +14,7 @@
 
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
+#include <asm/asmmacro.h>
 #include <asm/processor.h>
 #include <asm/coprocessor.h>
 #include <asm/thread_info.h>
@@ -125,6 +126,7 @@
  *
  * Note: _user_exception might be at an odd address. Don't use call0..call12
  */
+	.literal_position
 
 ENTRY(user_exception)
 
@@ -475,8 +477,7 @@ common_exception_return:
 1:
 	irq_save a2, a3
 #ifdef CONFIG_TRACE_IRQFLAGS
-	movi	a4, trace_hardirqs_off
-	callx4	a4
+	call4	trace_hardirqs_off
 #endif
 
 	/* Jump if we are returning from kernel exceptions. */
@@ -503,24 +504,20 @@ common_exception_return:
 	/* Call do_signal() */
 
 #ifdef CONFIG_TRACE_IRQFLAGS
-	movi	a4, trace_hardirqs_on
-	callx4	a4
+	call4	trace_hardirqs_on
 #endif
 	rsil	a2, 0
-	movi	a4, do_notify_resume	# int do_notify_resume(struct pt_regs*)
 	mov	a6, a1
-	callx4	a4
+	call4	do_notify_resume	# int do_notify_resume(struct pt_regs*)
 	j	1b
 
 3:	/* Reschedule */
 
 #ifdef CONFIG_TRACE_IRQFLAGS
-	movi	a4, trace_hardirqs_on
-	callx4	a4
+	call4	trace_hardirqs_on
 #endif
 	rsil	a2, 0
-	movi	a4, schedule	# void schedule (void)
-	callx4	a4
+	call4	schedule	# void schedule (void)
 	j	1b
 
 #ifdef CONFIG_PREEMPT
@@ -531,8 +528,7 @@ common_exception_return:
 
 	l32i	a4, a2, TI_PRE_COUNT
 	bnez	a4, 4f
-	movi	a4, preempt_schedule_irq
-	callx4	a4
+	call4	preempt_schedule_irq
 	j	1b
 #endif
 
@@ -545,23 +541,20 @@ common_exception_return:
 5:
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	_bbci.l	a4, TIF_DB_DISABLED, 7f
-	movi	a4, restore_dbreak
-	callx4	a4
+	call4	restore_dbreak
 7:
 #endif
 #ifdef CONFIG_DEBUG_TLB_SANITY
 	l32i	a4, a1, PT_DEPC
 	bgeui	a4, VALID_DOUBLE_EXCEPTION_ADDRESS, 4f
-	movi	a4, check_tlb_sanity
-	callx4	a4
+	call4	check_tlb_sanity
 #endif
 6:
 4:
 #ifdef CONFIG_TRACE_IRQFLAGS
 	extui	a4, a3, PS_INTLEVEL_SHIFT, PS_INTLEVEL_WIDTH
 	bgei	a4, LOCKLEVEL, 1f
-	movi	a4, trace_hardirqs_on
-	callx4	a4
+	call4	trace_hardirqs_on
 1:
 #endif
 	/* Restore optional registers. */
@@ -777,6 +770,8 @@ ENDPROC(kernel_exception)
  * When we get here,  a0 is trashed and saved to excsave[debuglevel]
  */
 
+	.literal_position
+
 ENTRY(debug_exception)
 
 	rsr	a0, SREG_EPS + XCHAL_DEBUGLEVEL
@@ -916,6 +911,8 @@ ENDPROC(debug_exception)
 unrecoverable_text:
 	.ascii "Unrecoverable error in exception handler\0"
 
+	.literal_position
+
 ENTRY(unrecoverable_exception)
 
 	movi	a0, 1
@@ -933,10 +930,8 @@ ENTRY(unrecoverable_exception)
 	movi	a0, 0
 	addi	a1, a1, PT_REGS_OFFSET
 
-	movi	a4, panic
 	movi	a6, unrecoverable_text
-
-	callx4	a4
+	call4	panic
 
 1:	j	1b
 
@@ -1073,8 +1068,7 @@ ENTRY(fast_syscall_unrecoverable)
 	xsr     a2, depc                # restore a2, depc
 
 	wsr     a0, excsave1
-	movi    a0, unrecoverable_exception
-	callx0  a0
+	call0	unrecoverable_exception
 
 ENDPROC(fast_syscall_unrecoverable)
 
@@ -1101,32 +1095,11 @@ ENDPROC(fast_syscall_unrecoverable)
  *	     <  VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
  *
  * Note: we don't have to save a2; a2 holds the return value
- *
- * We use the two macros TRY and CATCH:
- *
- * TRY	 adds an entry to the __ex_table fixup table for the immediately
- *	 following instruction.
- *
- * CATCH catches any exception that occurred at one of the preceding TRY
- *       statements and continues from there
- *
- * Usage TRY	l32i	a0, a1, 0
- *		<other code>
- *	 done:	rfe
- *	 CATCH	<set return code>
- *		j done
  */
 
-#ifdef CONFIG_FAST_SYSCALL_XTENSA
-
-#define TRY								\
-	.section __ex_table, "a";					\
-	.word	66f, 67f;						\
-	.text;								\
-66:
+	.literal_position
 
-#define CATCH								\
-67:
+#ifdef CONFIG_FAST_SYSCALL_XTENSA
 
 ENTRY(fast_syscall_xtensa)
 
@@ -1141,9 +1114,9 @@ ENTRY(fast_syscall_xtensa)
 
 .Lswp:	/* Atomic compare and swap */
 
-TRY	l32i	a0, a3, 0		# read old value
+EX(.Leac) l32i	a0, a3, 0		# read old value
 	bne	a0, a4, 1f		# same as old value? jump
-TRY	s32i	a5, a3, 0		# different, modify value
+EX(.Leac) s32i	a5, a3, 0		# different, modify value
 	l32i	a7, a2, PT_AREG7	# restore a7
 	l32i	a0, a2, PT_AREG0	# restore a0
 	movi	a2, 1			# and return 1
@@ -1156,12 +1129,12 @@ TRY	s32i	a5, a3, 0		# different, modify value
 
 .Lnswp:	/* Atomic set, add, and exg_add. */
 
-TRY	l32i	a7, a3, 0		# orig
+EX(.Leac) l32i	a7, a3, 0		# orig
 	addi	a6, a6, -SYS_XTENSA_ATOMIC_SET
 	add	a0, a4, a7		# + arg
 	moveqz	a0, a4, a6		# set
 	addi	a6, a6, SYS_XTENSA_ATOMIC_SET
-TRY	s32i	a0, a3, 0		# write new value
+EX(.Leac) s32i	a0, a3, 0		# write new value
 
 	mov	a0, a2
 	mov	a2, a7
@@ -1169,7 +1142,6 @@ TRY	s32i	a0, a3, 0		# write new value
 	l32i	a0, a0, PT_AREG0	# restore a0
 	rfe
 
-CATCH
 .Leac:	l32i	a7, a2, PT_AREG7	# restore a7
 	l32i	a0, a2, PT_AREG0	# restore a0
 	movi	a2, -EFAULT
@@ -1411,14 +1383,12 @@ ENTRY(fast_syscall_spill_registers)
 	rsync
 
 	movi	a6, SIGSEGV
-	movi	a4, do_exit
-	callx4	a4
+	call4	do_exit
 
 	/* shouldn't return, so panic */
 
 	wsr	a0, excsave1
-	movi	a0, unrecoverable_exception
-	callx0	a0		# should not return
+	call0	unrecoverable_exception		# should not return
 1:	j	1b
 
 
@@ -1564,8 +1534,8 @@ ENDPROC(fast_syscall_spill_registers)
 
 ENTRY(fast_second_level_miss_double_kernel)
 
-1:	movi	a0, unrecoverable_exception
-	callx0	a0		# should not return
+1:
+	call0	unrecoverable_exception		# should not return
 1:	j	1b
 
 ENDPROC(fast_second_level_miss_double_kernel)
@@ -1887,6 +1857,7 @@ ENDPROC(fast_store_prohibited)
  * void system_call (struct pt_regs* regs, int exccause)
  *                            a2                 a3
  */
+	.literal_position
 
 ENTRY(system_call)
 
@@ -1896,9 +1867,8 @@ ENTRY(system_call)
 
 	l32i	a3, a2, PT_AREG2
 	mov	a6, a2
-	movi	a4, do_syscall_trace_enter
 	s32i	a3, a2, PT_SYSCALL
-	callx4	a4
+	call4	do_syscall_trace_enter
 	mov	a3, a6
 
 	/* syscall = sys_call_table[syscall_nr] */
@@ -1930,9 +1900,8 @@ ENTRY(system_call)
 1:	/* regs->areg[2] = return_value */
 
 	s32i	a6, a2, PT_AREG2
-	movi	a4, do_syscall_trace_leave
 	mov	a6, a2
-	callx4	a4
+	call4	do_syscall_trace_leave
 	retw
 
 ENDPROC(system_call)
@@ -2002,6 +1971,12 @@ ENTRY(_switch_to)
 	s32i	a1, a2, THREAD_SP	# save stack pointer
 #endif
 
+#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
+	movi	a6, __stack_chk_guard
+	l32i	a8, a3, TASK_STACK_CANARY
+	s32i	a8, a6, 0
+#endif
+
 	/* Disable ints while we manipulate the stack pointer. */
 
 	irq_save a14, a3
@@ -2048,12 +2023,10 @@ ENTRY(ret_from_fork)
 	/* void schedule_tail (struct task_struct *prev)
 	 * Note: prev is still in a6 (return value from fake call4 frame)
 	 */
-	movi	a4, schedule_tail
-	callx4	a4
+	call4	schedule_tail
 
-	movi	a4, do_syscall_trace_leave
 	mov	a6, a1
-	callx4	a4
+	call4	do_syscall_trace_leave
 
 	j	common_exception_return
 
diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S
index 23ce62e60435..9c4e9433e536 100644
--- a/arch/xtensa/kernel/head.S
+++ b/arch/xtensa/kernel/head.S
@@ -264,11 +264,8 @@ ENTRY(_startup)
 
 	/* init_arch kick-starts the linux kernel */
 
-	movi	a4, init_arch
-	callx4	a4
-
-	movi	a4, start_kernel
-	callx4	a4
+	call4	init_arch
+	call4	start_kernel
 
 should_never_return:
 	j	should_never_return
@@ -294,8 +291,7 @@ should_never_return:
 	movi	a6, 0
 	wsr	a6, excsave1
 
-	movi	a4, secondary_start_kernel
-	callx4	a4
+	call4	secondary_start_kernel
 	j	should_never_return
 
 #endif  /* CONFIG_SMP */
diff --git a/arch/xtensa/kernel/module.c b/arch/xtensa/kernel/module.c
index b715237bae61..902845ddacb7 100644
--- a/arch/xtensa/kernel/module.c
+++ b/arch/xtensa/kernel/module.c
@@ -22,8 +22,6 @@
 #include <linux/kernel.h>
 #include <linux/cache.h>
 
-#undef DEBUG_RELOCATE
-
 static int
 decode_calln_opcode (unsigned char *location)
 {
@@ -58,10 +56,9 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 	unsigned char *location;
 	uint32_t value;
 
-#ifdef DEBUG_RELOCATE
-	printk("Applying relocate section %u to %u\n", relsec,
-	       sechdrs[relsec].sh_info);
-#endif
+	pr_debug("Applying relocate section %u to %u\n", relsec,
+		 sechdrs[relsec].sh_info);
+
 	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
 		location = (char *)sechdrs[sechdrs[relsec].sh_info].sh_addr
 			+ rela[i].r_offset;
@@ -87,7 +84,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 				value -= ((unsigned long)location & -4) + 4;
 				if ((value & 3) != 0 ||
 				    ((value + (1 << 19)) >> 20) != 0) {
-					printk("%s: relocation out of range, "
+					pr_err("%s: relocation out of range, "
 					       "section %d reloc %d "
 					       "sym '%s'\n",
 					       mod->name, relsec, i,
@@ -111,7 +108,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 				value -= (((unsigned long)location + 3) & -4);
 				if ((value & 3) != 0 ||
 				    (signed int)value >> 18 != -1) {
-					printk("%s: relocation out of range, "
+					pr_err("%s: relocation out of range, "
 					       "section %d reloc %d "
 					       "sym '%s'\n",
 					       mod->name, relsec, i,
@@ -156,7 +153,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 		case R_XTENSA_SLOT12_OP:
 		case R_XTENSA_SLOT13_OP:
 		case R_XTENSA_SLOT14_OP:
-			printk("%s: unexpected FLIX relocation: %u\n",
+			pr_err("%s: unexpected FLIX relocation: %u\n",
 			       mod->name,
 			       ELF32_R_TYPE(rela[i].r_info));
 			return -ENOEXEC;
@@ -176,13 +173,13 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 		case R_XTENSA_SLOT12_ALT:
 		case R_XTENSA_SLOT13_ALT:
 		case R_XTENSA_SLOT14_ALT:
-			printk("%s: unexpected ALT relocation: %u\n",
+			pr_err("%s: unexpected ALT relocation: %u\n",
 			       mod->name,
 			       ELF32_R_TYPE(rela[i].r_info));
 			return -ENOEXEC;
 
 		default:
-			printk("%s: unexpected relocation: %u\n",
+			pr_err("%s: unexpected relocation: %u\n",
 			       mod->name,
 			       ELF32_R_TYPE(rela[i].r_info));
 			return -ENOEXEC;
diff --git a/arch/xtensa/kernel/pci.c b/arch/xtensa/kernel/pci.c
index 903963ee495d..d981f01c8d89 100644
--- a/arch/xtensa/kernel/pci.c
+++ b/arch/xtensa/kernel/pci.c
@@ -29,14 +29,6 @@
 #include <asm/pci-bridge.h>
 #include <asm/platform.h>
 
-#undef DEBUG
-
-#ifdef DEBUG
-#define DBG(x...) printk(x)
-#else
-#define DBG(x...)
-#endif
-
 /* PCI Controller */
 
 
@@ -101,8 +93,8 @@ pcibios_enable_resources(struct pci_dev *dev, int mask)
 	for(idx=0; idx<6; idx++) {
 		r = &dev->resource[idx];
 		if (!r->start && r->end) {
-			printk (KERN_ERR "PCI: Device %s not available because "
-				"of resource collisions\n", pci_name(dev));
+			pr_err("PCI: Device %s not available because "
+			       "of resource collisions\n", pci_name(dev));
 			return -EINVAL;
 		}
 		if (r->flags & IORESOURCE_IO)
@@ -113,7 +105,7 @@ pcibios_enable_resources(struct pci_dev *dev, int mask)
 	if (dev->resource[PCI_ROM_RESOURCE].start)
 		cmd |= PCI_COMMAND_MEMORY;
 	if (cmd != old_cmd) {
-		printk("PCI: Enabling device %s (%04x -> %04x)\n",
+		pr_info("PCI: Enabling device %s (%04x -> %04x)\n",
 			pci_name(dev), old_cmd, cmd);
 		pci_write_config_word(dev, PCI_COMMAND, cmd);
 	}
@@ -144,8 +136,8 @@ static void __init pci_controller_apertures(struct pci_controller *pci_ctrl,
 	res = &pci_ctrl->io_resource;
 	if (!res->flags) {
 		if (io_offset)
-			printk (KERN_ERR "I/O resource not set for host"
-				" bridge %d\n", pci_ctrl->index);
+			pr_err("I/O resource not set for host bridge %d\n",
+			       pci_ctrl->index);
 		res->start = 0;
 		res->end = IO_SPACE_LIMIT;
 		res->flags = IORESOURCE_IO;
@@ -159,8 +151,8 @@ static void __init pci_controller_apertures(struct pci_controller *pci_ctrl,
 		if (!res->flags) {
 			if (i > 0)
 				continue;
-			printk(KERN_ERR "Memory resource not set for "
-			       "host bridge %d\n", pci_ctrl->index);
+			pr_err("Memory resource not set for host bridge %d\n",
+			       pci_ctrl->index);
 			res->start = 0;
 			res->end = ~0U;
 			res->flags = IORESOURCE_MEM;
@@ -176,7 +168,7 @@ static int __init pcibios_init(void)
 	struct pci_bus *bus;
 	int next_busno = 0, ret;
 
-	printk("PCI: Probing PCI hardware\n");
+	pr_info("PCI: Probing PCI hardware\n");
 
 	/* Scan all of the recorded PCI controllers.  */
 	for (pci_ctrl = pci_ctrl_head; pci_ctrl; pci_ctrl = pci_ctrl->next) {
@@ -232,7 +224,7 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 	for (idx=0; idx<6; idx++) {
 		r = &dev->resource[idx];
 		if (!r->start && r->end) {
-			printk(KERN_ERR "PCI: Device %s not available because "
+			pr_err("PCI: Device %s not available because "
 			       "of resource collisions\n", pci_name(dev));
 			return -EINVAL;
 		}
@@ -242,8 +234,8 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 			cmd |= PCI_COMMAND_MEMORY;
 	}
 	if (cmd != old_cmd) {
-		printk("PCI: Enabling device %s (%04x -> %04x)\n",
-		       pci_name(dev), old_cmd, cmd);
+		pr_info("PCI: Enabling device %s (%04x -> %04x)\n",
+			pci_name(dev), old_cmd, cmd);
 		pci_write_config_word(dev, PCI_COMMAND, cmd);
 	}
 
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index ff4f0ecb03dd..8dd0593fb2c4 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -58,6 +58,12 @@ void (*pm_power_off)(void) = NULL;
 EXPORT_SYMBOL(pm_power_off);
 
 
+#ifdef CONFIG_CC_STACKPROTECTOR
+#include <linux/stackprotector.h>
+unsigned long __stack_chk_guard __read_mostly;
+EXPORT_SYMBOL(__stack_chk_guard);
+#endif
+
 #if XTENSA_HAVE_COPROCESSORS
 
 void coprocessor_release_all(struct thread_info *ti)
diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index e2461968efb2..c0845cb1cbb9 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -278,7 +278,6 @@ static void ptrace_hbptriggered(struct perf_event *bp,
 				struct pt_regs *regs)
 {
 	int i;
-	siginfo_t info;
 	struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
 
 	if (bp->attr.bp_type & HW_BREAKPOINT_X) {
@@ -293,12 +292,7 @@ static void ptrace_hbptriggered(struct perf_event *bp,
 		i = (i << 1) | 1;
 	}
 
-	info.si_signo = SIGTRAP;
-	info.si_errno = i;
-	info.si_code = TRAP_HWBKPT;
-	info.si_addr = (void __user *)bkpt->address;
-
-	force_sig_info(SIGTRAP, &info, current);
+	force_sig_ptrace_errno_trap(i, (void __user *)bkpt->address);
 }
 
 static struct perf_event *ptrace_hbp_create(struct task_struct *tsk, int type)
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 08175df7a69e..686a27444bba 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -20,7 +20,6 @@
 #include <linux/mm.h>
 #include <linux/proc_fs.h>
 #include <linux/screen_info.h>
-#include <linux/bootmem.h>
 #include <linux/kernel.h>
 #include <linux/percpu.h>
 #include <linux/cpu.h>
@@ -36,6 +35,7 @@
 #endif
 
 #include <asm/bootparam.h>
+#include <asm/kasan.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -156,7 +156,7 @@ static int __init parse_bootparam(const bp_tag_t* tag)
 	/* Boot parameters must start with a BP_TAG_FIRST tag. */
 
 	if (tag->id != BP_TAG_FIRST) {
-		printk(KERN_WARNING "Invalid boot parameters!\n");
+		pr_warn("Invalid boot parameters!\n");
 		return 0;
 	}
 
@@ -165,15 +165,14 @@ static int __init parse_bootparam(const bp_tag_t* tag)
 	/* Parse all tags. */
 
 	while (tag != NULL && tag->id != BP_TAG_LAST) {
-	 	for (t = &__tagtable_begin; t < &__tagtable_end; t++) {
+		for (t = &__tagtable_begin; t < &__tagtable_end; t++) {
 			if (tag->id == t->tag) {
 				t->parse(tag);
 				break;
 			}
 		}
 		if (t == &__tagtable_end)
-			printk(KERN_WARNING "Ignoring tag "
-			       "0x%08x\n", tag->id);
+			pr_warn("Ignoring tag 0x%08x\n", tag->id);
 		tag = (bp_tag_t*)((unsigned long)(tag + 1) + tag->size);
 	}
 
@@ -208,6 +207,8 @@ static int __init xtensa_dt_io_area(unsigned long node, const char *uname,
 	/* round down to nearest 256MB boundary */
 	xtensa_kio_paddr &= 0xf0000000;
 
+	init_kio();
+
 	return 1;
 }
 #else
@@ -218,17 +219,6 @@ static int __init xtensa_dt_io_area(unsigned long node, const char *uname,
 }
 #endif
 
-void __init early_init_dt_add_memory_arch(u64 base, u64 size)
-{
-	size &= PAGE_MASK;
-	memblock_add(base, size);
-}
-
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return __alloc_bootmem(size, align, 0);
-}
-
 void __init early_init_devtree(void *params)
 {
 	early_init_dt_scan(params);
@@ -246,6 +236,14 @@ void __init early_init_devtree(void *params)
 
 void __init init_arch(bp_tag_t *bp_start)
 {
+	/* Initialize MMU. */
+
+	init_mmu();
+
+	/* Initialize initial KASAN shadow map */
+
+	kasan_early_init();
+
 	/* Parse boot parameters */
 
 	if (bp_start)
@@ -263,10 +261,6 @@ void __init init_arch(bp_tag_t *bp_start)
 	/* Early hook for platforms */
 
 	platform_init(bp_start);
-
-	/* Initialize MMU. */
-
-	init_mmu();
 }
 
 /*
@@ -277,13 +271,13 @@ extern char _end[];
 extern char _stext[];
 extern char _WindowVectors_text_start;
 extern char _WindowVectors_text_end;
-extern char _DebugInterruptVector_literal_start;
+extern char _DebugInterruptVector_text_start;
 extern char _DebugInterruptVector_text_end;
-extern char _KernelExceptionVector_literal_start;
+extern char _KernelExceptionVector_text_start;
 extern char _KernelExceptionVector_text_end;
-extern char _UserExceptionVector_literal_start;
+extern char _UserExceptionVector_text_start;
 extern char _UserExceptionVector_text_end;
-extern char _DoubleExceptionVector_literal_start;
+extern char _DoubleExceptionVector_text_start;
 extern char _DoubleExceptionVector_text_end;
 #if XCHAL_EXCM_LEVEL >= 2
 extern char _Level2InterruptVector_text_start;
@@ -317,6 +311,13 @@ static inline int mem_reserve(unsigned long start, unsigned long end)
 
 void __init setup_arch(char **cmdline_p)
 {
+	pr_info("config ID: %08x:%08x\n",
+		get_sr(SREG_EPC), get_sr(SREG_EXCSAVE));
+	if (get_sr(SREG_EPC) != XCHAL_HW_CONFIGID0 ||
+	    get_sr(SREG_EXCSAVE) != XCHAL_HW_CONFIGID1)
+		pr_info("built for config ID: %08x:%08x\n",
+			XCHAL_HW_CONFIGID0, XCHAL_HW_CONFIGID1);
+
 	*cmdline_p = command_line;
 	platform_setup(cmdline_p);
 	strlcpy(boot_command_line, *cmdline_p, COMMAND_LINE_SIZE);
@@ -339,16 +340,16 @@ void __init setup_arch(char **cmdline_p)
 	mem_reserve(__pa(&_WindowVectors_text_start),
 		    __pa(&_WindowVectors_text_end));
 
-	mem_reserve(__pa(&_DebugInterruptVector_literal_start),
+	mem_reserve(__pa(&_DebugInterruptVector_text_start),
 		    __pa(&_DebugInterruptVector_text_end));
 
-	mem_reserve(__pa(&_KernelExceptionVector_literal_start),
+	mem_reserve(__pa(&_KernelExceptionVector_text_start),
 		    __pa(&_KernelExceptionVector_text_end));
 
-	mem_reserve(__pa(&_UserExceptionVector_literal_start),
+	mem_reserve(__pa(&_UserExceptionVector_text_start),
 		    __pa(&_UserExceptionVector_text_end));
 
-	mem_reserve(__pa(&_DoubleExceptionVector_literal_start),
+	mem_reserve(__pa(&_DoubleExceptionVector_text_start),
 		    __pa(&_DoubleExceptionVector_text_end));
 
 #if XCHAL_EXCM_LEVEL >= 2
@@ -380,7 +381,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	parse_early_param();
 	bootmem_init();
-
+	kasan_init();
 	unflatten_and_copy_device_tree();
 
 #ifdef CONFIG_SMP
@@ -582,12 +583,14 @@ c_show(struct seq_file *f, void *slot)
 		      "model\t\t: Xtensa " XCHAL_HW_VERSION_NAME "\n"
 		      "core ID\t\t: " XCHAL_CORE_ID "\n"
 		      "build ID\t: 0x%x\n"
+		      "config ID\t: %08x:%08x\n"
 		      "byte order\t: %s\n"
 		      "cpu MHz\t\t: %lu.%02lu\n"
 		      "bogomips\t: %lu.%02lu\n",
 		      num_online_cpus(),
 		      cpumask_pr_args(cpu_online_mask),
 		      XCHAL_BUILD_UNIQUE_ID,
+		      get_sr(SREG_EPC), get_sr(SREG_EXCSAVE),
 		      XCHAL_HAVE_BE ?  "big" : "little",
 		      ccount_freq/1000000,
 		      (ccount_freq/10000) % 100,
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index d427e784ab44..f88e7a0b232c 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -28,8 +28,6 @@
 #include <asm/coprocessor.h>
 #include <asm/unistd.h>
 
-#define DEBUG_SIG  0
-
 extern struct task_struct *coproc_owners[];
 
 struct rt_sigframe
@@ -399,10 +397,8 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 	regs->areg[8] = (unsigned long) &frame->uc;
 	regs->threadptr = tp;
 
-#if DEBUG_SIG
-	printk("SIG rt deliver (%s:%d): signal=%d sp=%p pc=%08x\n",
-		current->comm, current->pid, sig, frame, regs->pc);
-#endif
+	pr_debug("SIG rt deliver (%s:%d): signal=%d sp=%p pc=%08lx\n",
+		 current->comm, current->pid, sig, frame, regs->pc);
 
 	return 0;
 }
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index bae697a06a98..32c5207f1226 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -33,6 +33,7 @@
 #include <linux/kallsyms.h>
 #include <linux/delay.h>
 #include <linux/hardirq.h>
+#include <linux/ratelimit.h>
 
 #include <asm/stacktrace.h>
 #include <asm/ptrace.h>
@@ -158,8 +159,7 @@ COPROCESSOR(7),
  * 2. it is a temporary memory buffer for the exception handlers.
  */
 
-DEFINE_PER_CPU(unsigned long, exc_table[EXC_TABLE_SIZE/4]);
-
+DEFINE_PER_CPU(struct exc_table, exc_table);
 DEFINE_PER_CPU(struct debug_table, debug_table);
 
 void die(const char*, struct pt_regs*, long);
@@ -178,13 +178,14 @@ __die_if_kernel(const char *str, struct pt_regs *regs, long err)
 void do_unhandled(struct pt_regs *regs, unsigned long exccause)
 {
 	__die_if_kernel("Caught unhandled exception - should not happen",
-	    		regs, SIGKILL);
+			regs, SIGKILL);
 
 	/* If in user mode, send SIGILL signal to current process */
-	printk("Caught unhandled exception in '%s' "
-	       "(pid = %d, pc = %#010lx) - should not happen\n"
-	       "\tEXCCAUSE is %ld\n",
-	       current->comm, task_pid_nr(current), regs->pc, exccause);
+	pr_info_ratelimited("Caught unhandled exception in '%s' "
+			    "(pid = %d, pc = %#010lx) - should not happen\n"
+			    "\tEXCCAUSE is %ld\n",
+			    current->comm, task_pid_nr(current), regs->pc,
+			    exccause);
 	force_sig(SIGILL, current);
 }
 
@@ -305,8 +306,8 @@ do_illegal_instruction(struct pt_regs *regs)
 
 	/* If in user mode, send SIGILL signal to current process. */
 
-	printk("Illegal Instruction in '%s' (pid = %d, pc = %#010lx)\n",
-	    current->comm, task_pid_nr(current), regs->pc);
+	pr_info_ratelimited("Illegal Instruction in '%s' (pid = %d, pc = %#010lx)\n",
+			    current->comm, task_pid_nr(current), regs->pc);
 	force_sig(SIGILL, current);
 }
 
@@ -325,13 +326,14 @@ do_unaligned_user (struct pt_regs *regs)
 	siginfo_t info;
 
 	__die_if_kernel("Unhandled unaligned exception in kernel",
-	    		regs, SIGKILL);
+			regs, SIGKILL);
 
 	current->thread.bad_vaddr = regs->excvaddr;
 	current->thread.error_code = -3;
-	printk("Unaligned memory access to %08lx in '%s' "
-	       "(pid = %d, pc = %#010lx)\n",
-	       regs->excvaddr, current->comm, task_pid_nr(current), regs->pc);
+	pr_info_ratelimited("Unaligned memory access to %08lx in '%s' "
+			    "(pid = %d, pc = %#010lx)\n",
+			    regs->excvaddr, current->comm,
+			    task_pid_nr(current), regs->pc);
 	info.si_signo = SIGBUS;
 	info.si_errno = 0;
 	info.si_code = BUS_ADRALN;
@@ -365,28 +367,28 @@ do_debug(struct pt_regs *regs)
 }
 
 
-static void set_handler(int idx, void *handler)
-{
-	unsigned int cpu;
-
-	for_each_possible_cpu(cpu)
-		per_cpu(exc_table, cpu)[idx] = (unsigned long)handler;
-}
+#define set_handler(type, cause, handler)				\
+	do {								\
+		unsigned int cpu;					\
+									\
+		for_each_possible_cpu(cpu)				\
+			per_cpu(exc_table, cpu).type[cause] = (handler);\
+	} while (0)
 
 /* Set exception C handler - for temporary use when probing exceptions */
 
 void * __init trap_set_handler(int cause, void *handler)
 {
-	void *previous = (void *)per_cpu(exc_table, 0)[
-		EXC_TABLE_DEFAULT / 4 + cause];
-	set_handler(EXC_TABLE_DEFAULT / 4 + cause, handler);
+	void *previous = per_cpu(exc_table, 0).default_handler[cause];
+
+	set_handler(default_handler, cause, handler);
 	return previous;
 }
 
 
 static void trap_init_excsave(void)
 {
-	unsigned long excsave1 = (unsigned long)this_cpu_ptr(exc_table);
+	unsigned long excsave1 = (unsigned long)this_cpu_ptr(&exc_table);
 	__asm__ __volatile__("wsr  %0, excsave1\n" : : "a" (excsave1));
 }
 
@@ -418,10 +420,10 @@ void __init trap_init(void)
 
 	/* Setup default vectors. */
 
-	for(i = 0; i < 64; i++) {
-		set_handler(EXC_TABLE_FAST_USER/4   + i, user_exception);
-		set_handler(EXC_TABLE_FAST_KERNEL/4 + i, kernel_exception);
-		set_handler(EXC_TABLE_DEFAULT/4 + i, do_unhandled);
+	for (i = 0; i < EXCCAUSE_N; i++) {
+		set_handler(fast_user_handler, i, user_exception);
+		set_handler(fast_kernel_handler, i, kernel_exception);
+		set_handler(default_handler, i, do_unhandled);
 	}
 
 	/* Setup specific handlers. */
@@ -433,11 +435,11 @@ void __init trap_init(void)
 		void *handler = dispatch_init_table[i].handler;
 
 		if (fast == 0)
-			set_handler (EXC_TABLE_DEFAULT/4 + cause, handler);
+			set_handler(default_handler, cause, handler);
 		if (fast && fast & USER)
-			set_handler (EXC_TABLE_FAST_USER/4 + cause, handler);
+			set_handler(fast_user_handler, cause, handler);
 		if (fast && fast & KRNL)
-			set_handler (EXC_TABLE_FAST_KERNEL/4 + cause, handler);
+			set_handler(fast_kernel_handler, cause, handler);
 	}
 
 	/* Initialize EXCSAVE_1 to hold the address of the exception table. */
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index 332e9d635fb6..841503d3307c 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -205,9 +205,6 @@ ENDPROC(_KernelExceptionVector)
  */
 
 	.section .DoubleExceptionVector.text, "ax"
-	.begin literal_prefix .DoubleExceptionVector
-	.globl _DoubleExceptionVector_WindowUnderflow
-	.globl _DoubleExceptionVector_WindowOverflow
 
 ENTRY(_DoubleExceptionVector)
 
@@ -217,8 +214,12 @@ ENTRY(_DoubleExceptionVector)
 	/* Check for kernel double exception (usually fatal). */
 
 	rsr	a2, ps
-	_bbci.l	a2, PS_UM_BIT, .Lksp
+	_bbsi.l	a2, PS_UM_BIT, 1f
+	j	.Lksp
 
+	.align	4
+	.literal_position
+1:
 	/* Check if we are currently handling a window exception. */
 	/* Note: We don't need to indicate that we enter a critical section. */
 
@@ -304,8 +305,7 @@ _DoubleExceptionVector_WindowUnderflow:
 .Lunrecoverable:
 	rsr	a3, excsave1
 	wsr	a0, excsave1
-	movi	a0, unrecoverable_exception
-	callx0	a0
+	call0	unrecoverable_exception
 
 .Lfixup:/* Check for a fixup handler or if we were in a critical section. */
 
@@ -475,11 +475,8 @@ _DoubleExceptionVector_handle_exception:
 	rotw	-3
 	j	1b
 
-
 ENDPROC(_DoubleExceptionVector)
 
-	.end literal_prefix
-
 	.text
 /*
  * Fixup handler for TLB miss in double exception handler for window owerflow.
@@ -508,6 +505,8 @@ ENDPROC(_DoubleExceptionVector)
  * a3: exctable, original value in excsave1
  */
 
+	.literal_position
+
 ENTRY(window_overflow_restore_a0_fixup)
 
 	rsr	a0, ps
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index 162c77e53ca8..70b731edc7b8 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -45,24 +45,16 @@ jiffies = jiffies_64;
 	LONG(sym ## _end);			\
 	LONG(LOADADDR(section))
 
-/* Macro to define a section for a vector.
- *
- * Use of the MIN function catches the types of errors illustrated in
- * the following example:
- *
- * Assume the section .DoubleExceptionVector.literal is completely
- * full.  Then a programmer adds code to .DoubleExceptionVector.text
- * that produces another literal.  The final literal position will
- * overlay onto the first word of the adjacent code section
- * .DoubleExceptionVector.text.  (In practice, the literals will
- * overwrite the code, and the first few instructions will be
- * garbage.)
+/*
+ * Macro to define a section for a vector. When CONFIG_VECTORS_OFFSET is
+ * defined code for every vector is located with other init data. At startup
+ * time head.S copies code for every vector to its final position according
+ * to description recorded in the corresponding RELOCATE_ENTRY.
  */
 
 #ifdef CONFIG_VECTORS_OFFSET
-#define SECTION_VECTOR(sym, section, addr, max_prevsec_size, prevsec)       \
-  section addr : AT((MIN(LOADADDR(prevsec) + max_prevsec_size,		    \
-		         LOADADDR(prevsec) + SIZEOF(prevsec)) + 3) & ~ 3)   \
+#define SECTION_VECTOR(sym, section, addr, prevsec)                         \
+  section addr : AT(((LOADADDR(prevsec) + SIZEOF(prevsec)) + 3) & ~ 3)      \
   {									    \
     . = ALIGN(4);							    \
     sym ## _start = ABSOLUTE(.);		 			    \
@@ -112,26 +104,19 @@ SECTIONS
 #if XCHAL_EXCM_LEVEL >= 6
   SECTION_VECTOR (.Level6InterruptVector.text, INTLEVEL6_VECTOR_VADDR)
 #endif
-  SECTION_VECTOR (.DebugInterruptVector.literal, DEBUG_VECTOR_VADDR - 4)
   SECTION_VECTOR (.DebugInterruptVector.text, DEBUG_VECTOR_VADDR)
-  SECTION_VECTOR (.KernelExceptionVector.literal, KERNEL_VECTOR_VADDR - 4)
   SECTION_VECTOR (.KernelExceptionVector.text, KERNEL_VECTOR_VADDR)
-  SECTION_VECTOR (.UserExceptionVector.literal, USER_VECTOR_VADDR - 4)
   SECTION_VECTOR (.UserExceptionVector.text, USER_VECTOR_VADDR)
-  SECTION_VECTOR (.DoubleExceptionVector.literal, DOUBLEEXC_VECTOR_VADDR - 20)
   SECTION_VECTOR (.DoubleExceptionVector.text, DOUBLEEXC_VECTOR_VADDR)
 #endif
 
+    IRQENTRY_TEXT
+    SOFTIRQENTRY_TEXT
+    ENTRY_TEXT
     TEXT_TEXT
-    VMLINUX_SYMBOL(__sched_text_start) = .;
-    *(.sched.literal .sched.text)
-    VMLINUX_SYMBOL(__sched_text_end) = .;
-    VMLINUX_SYMBOL(__cpuidle_text_start) = .;
-    *(.cpuidle.literal .cpuidle.text)
-    VMLINUX_SYMBOL(__cpuidle_text_end) = .;
-    VMLINUX_SYMBOL(__lock_text_start) = .;
-    *(.spinlock.literal .spinlock.text)
-    VMLINUX_SYMBOL(__lock_text_end) = .;
+    SCHED_TEXT
+    CPUIDLE_TEXT
+    LOCK_TEXT
 
   }
   _etext = .;
@@ -196,8 +181,6 @@ SECTIONS
 		   .KernelExceptionVector.text);
     RELOCATE_ENTRY(_UserExceptionVector_text,
 		   .UserExceptionVector.text);
-    RELOCATE_ENTRY(_DoubleExceptionVector_literal,
-		   .DoubleExceptionVector.literal);
     RELOCATE_ENTRY(_DoubleExceptionVector_text,
 		   .DoubleExceptionVector.text);
     RELOCATE_ENTRY(_DebugInterruptVector_text,
@@ -230,25 +213,19 @@ SECTIONS
 
   SECTION_VECTOR (_WindowVectors_text,
 		  .WindowVectors.text,
-		  WINDOW_VECTORS_VADDR, 4,
+		  WINDOW_VECTORS_VADDR,
 		  .dummy)
-  SECTION_VECTOR (_DebugInterruptVector_literal,
-		  .DebugInterruptVector.literal,
-		  DEBUG_VECTOR_VADDR - 4,
-		  SIZEOF(.WindowVectors.text),
-		  .WindowVectors.text)
   SECTION_VECTOR (_DebugInterruptVector_text,
 		  .DebugInterruptVector.text,
 		  DEBUG_VECTOR_VADDR,
-		  4,
-		  .DebugInterruptVector.literal)
+		  .WindowVectors.text)
 #undef LAST
 #define LAST	.DebugInterruptVector.text
 #if XCHAL_EXCM_LEVEL >= 2
   SECTION_VECTOR (_Level2InterruptVector_text,
 		  .Level2InterruptVector.text,
 		  INTLEVEL2_VECTOR_VADDR,
-		  SIZEOF(LAST), LAST)
+		  LAST)
 # undef LAST
 # define LAST	.Level2InterruptVector.text
 #endif
@@ -256,7 +233,7 @@ SECTIONS
   SECTION_VECTOR (_Level3InterruptVector_text,
 		  .Level3InterruptVector.text,
 		  INTLEVEL3_VECTOR_VADDR,
-		  SIZEOF(LAST), LAST)
+		  LAST)
 # undef LAST
 # define LAST	.Level3InterruptVector.text
 #endif
@@ -264,7 +241,7 @@ SECTIONS
   SECTION_VECTOR (_Level4InterruptVector_text,
 		  .Level4InterruptVector.text,
 		  INTLEVEL4_VECTOR_VADDR,
-		  SIZEOF(LAST), LAST)
+		  LAST)
 # undef LAST
 # define LAST	.Level4InterruptVector.text
 #endif
@@ -272,7 +249,7 @@ SECTIONS
   SECTION_VECTOR (_Level5InterruptVector_text,
 		  .Level5InterruptVector.text,
 		  INTLEVEL5_VECTOR_VADDR,
-		  SIZEOF(LAST), LAST)
+		  LAST)
 # undef LAST
 # define LAST	.Level5InterruptVector.text
 #endif
@@ -280,40 +257,23 @@ SECTIONS
   SECTION_VECTOR (_Level6InterruptVector_text,
 		  .Level6InterruptVector.text,
 		  INTLEVEL6_VECTOR_VADDR,
-		  SIZEOF(LAST), LAST)
+		  LAST)
 # undef LAST
 # define LAST	.Level6InterruptVector.text
 #endif
-  SECTION_VECTOR (_KernelExceptionVector_literal,
-		  .KernelExceptionVector.literal,
-		  KERNEL_VECTOR_VADDR - 4,
-		  SIZEOF(LAST), LAST)
-#undef LAST
   SECTION_VECTOR (_KernelExceptionVector_text,
 		  .KernelExceptionVector.text,
 		  KERNEL_VECTOR_VADDR,
-		  4,
-		  .KernelExceptionVector.literal)
-  SECTION_VECTOR (_UserExceptionVector_literal,
-		  .UserExceptionVector.literal,
-		  USER_VECTOR_VADDR - 4,
-		  SIZEOF(.KernelExceptionVector.text),
-		  .KernelExceptionVector.text)
+		  LAST)
+#undef LAST
   SECTION_VECTOR (_UserExceptionVector_text,
 		  .UserExceptionVector.text,
 		  USER_VECTOR_VADDR,
-		  4,
-		  .UserExceptionVector.literal)
-  SECTION_VECTOR (_DoubleExceptionVector_literal,
-		  .DoubleExceptionVector.literal,
-		  DOUBLEEXC_VECTOR_VADDR - 20,
-		  SIZEOF(.UserExceptionVector.text),
-		  .UserExceptionVector.text)
+		  .KernelExceptionVector.text)
   SECTION_VECTOR (_DoubleExceptionVector_text,
 		  .DoubleExceptionVector.text,
 		  DOUBLEEXC_VECTOR_VADDR,
-		  20,
-		  .DoubleExceptionVector.literal)
+		  .UserExceptionVector.text)
 
   . = (LOADADDR( .DoubleExceptionVector.text ) + SIZEOF( .DoubleExceptionVector.text ) + 3) & ~ 3;
 
@@ -323,7 +283,6 @@ SECTIONS
   SECTION_VECTOR (_SecondaryResetVector_text,
 		  .SecondaryResetVector.text,
 		  RESET_VECTOR1_VADDR,
-		  SIZEOF(.DoubleExceptionVector.text),
 		  .DoubleExceptionVector.text)
 
   . = LOADADDR(.SecondaryResetVector.text)+SIZEOF(.SecondaryResetVector.text);
@@ -373,5 +332,4 @@ SECTIONS
 
   /* Sections to be discarded */
   DISCARDS
-  /DISCARD/ : { *(.exit.literal) }
 }
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 672391003e40..04f19de46700 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -41,7 +41,12 @@
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memmove);
+EXPORT_SYMBOL(__memset);
+EXPORT_SYMBOL(__memcpy);
+EXPORT_SYMBOL(__memmove);
+#ifndef CONFIG_GENERIC_STRNCPY_FROM_USER
 EXPORT_SYMBOL(__strncpy_user);
+#endif
 EXPORT_SYMBOL(clear_page);
 EXPORT_SYMBOL(copy_page);
 
diff --git a/arch/xtensa/lib/checksum.S b/arch/xtensa/lib/checksum.S
index 4eb573d2720e..528fe0dd9339 100644
--- a/arch/xtensa/lib/checksum.S
+++ b/arch/xtensa/lib/checksum.S
@@ -14,9 +14,10 @@
  *		2 of the License, or (at your option) any later version.
  */
 
-#include <asm/errno.h>
+#include <linux/errno.h>
 #include <linux/linkage.h>
 #include <variant/core.h>
+#include <asm/asmmacro.h>
 
 /*
  * computes a partial checksum, e.g. for TCP/UDP fragments
@@ -175,23 +176,8 @@ ENDPROC(csum_partial)
 
 /*
  * Copy from ds while checksumming, otherwise like csum_partial
- *
- * The macros SRC and DST specify the type of access for the instruction.
- * thus we can call a custom exception handler for each access type.
  */
 
-#define SRC(y...)			\
-	9999: y;			\
-	.section __ex_table, "a";	\
-	.long 9999b, 6001f	;	\
-	.previous
-
-#define DST(y...)			\
-	9999: y;			\
-	.section __ex_table, "a";	\
-	.long 9999b, 6002f	;	\
-	.previous
-
 /*
 unsigned int csum_partial_copy_generic (const char *src, char *dst, int len,
 					int sum, int *src_err_ptr, int *dst_err_ptr)
@@ -244,28 +230,28 @@ ENTRY(csum_partial_copy_generic)
 	add	a10, a10, a2	/* a10 = end of last 32-byte src chunk */
 .Loop5:
 #endif
-SRC(	l32i	a9, a2, 0	)
-SRC(	l32i	a8, a2, 4	)
-DST(	s32i	a9, a3, 0	)
-DST(	s32i	a8, a3, 4	)
+EX(10f)	l32i	a9, a2, 0
+EX(10f)	l32i	a8, a2, 4
+EX(11f)	s32i	a9, a3, 0
+EX(11f)	s32i	a8, a3, 4
 	ONES_ADD(a5, a9)
 	ONES_ADD(a5, a8)
-SRC(	l32i	a9, a2, 8	)
-SRC(	l32i	a8, a2, 12	)
-DST(	s32i	a9, a3, 8	)
-DST(	s32i	a8, a3, 12	)
+EX(10f)	l32i	a9, a2, 8
+EX(10f)	l32i	a8, a2, 12
+EX(11f)	s32i	a9, a3, 8
+EX(11f)	s32i	a8, a3, 12
 	ONES_ADD(a5, a9)
 	ONES_ADD(a5, a8)
-SRC(	l32i	a9, a2, 16	)
-SRC(	l32i	a8, a2, 20	)
-DST(	s32i	a9, a3, 16	)
-DST(	s32i	a8, a3, 20	)
+EX(10f)	l32i	a9, a2, 16
+EX(10f)	l32i	a8, a2, 20
+EX(11f)	s32i	a9, a3, 16
+EX(11f)	s32i	a8, a3, 20
 	ONES_ADD(a5, a9)
 	ONES_ADD(a5, a8)
-SRC(	l32i	a9, a2, 24	)
-SRC(	l32i	a8, a2, 28	)
-DST(	s32i	a9, a3, 24	)
-DST(	s32i	a8, a3, 28	)
+EX(10f)	l32i	a9, a2, 24
+EX(10f)	l32i	a8, a2, 28
+EX(11f)	s32i	a9, a3, 24
+EX(11f)	s32i	a8, a3, 28
 	ONES_ADD(a5, a9)
 	ONES_ADD(a5, a8)
 	addi	a2, a2, 32
@@ -284,8 +270,8 @@ DST(	s32i	a8, a3, 28	)
 	add	a10, a10, a2	/* a10 = end of last 4-byte src chunk */
 .Loop6:
 #endif
-SRC(	l32i	a9, a2, 0	)
-DST(	s32i	a9, a3, 0	)
+EX(10f)	l32i	a9, a2, 0
+EX(11f)	s32i	a9, a3, 0
 	ONES_ADD(a5, a9)
 	addi	a2, a2, 4
 	addi	a3, a3, 4
@@ -315,8 +301,8 @@ DST(	s32i	a9, a3, 0	)
 	add	a10, a10, a2	/* a10 = end of last 2-byte src chunk */
 .Loop7:
 #endif
-SRC(	l16ui	a9, a2, 0	)
-DST(	s16i	a9, a3, 0	)
+EX(10f)	l16ui	a9, a2, 0
+EX(11f)	s16i	a9, a3, 0
 	ONES_ADD(a5, a9)
 	addi	a2, a2, 2
 	addi	a3, a3, 2
@@ -326,8 +312,8 @@ DST(	s16i	a9, a3, 0	)
 4:
 	/* This section processes a possible trailing odd byte. */
 	_bbci.l	a4, 0, 8f	/* 1-byte chunk */
-SRC(	l8ui	a9, a2, 0	)
-DST(	s8i	a9, a3, 0	)
+EX(10f)	l8ui	a9, a2, 0
+EX(11f)	s8i	a9, a3, 0
 #ifdef __XTENSA_EB__
 	slli	a9, a9, 8	/* shift byte to bits 8..15 */
 #endif
@@ -350,10 +336,10 @@ DST(	s8i	a9, a3, 0	)
 	add	a10, a10, a2	/* a10 = end of last odd-aligned, 2-byte src chunk */
 .Loop8:
 #endif
-SRC(	l8ui	a9, a2, 0	)
-SRC(	l8ui	a8, a2, 1	)
-DST(	s8i	a9, a3, 0	)
-DST(	s8i	a8, a3, 1	)
+EX(10f)	l8ui	a9, a2, 0
+EX(10f)	l8ui	a8, a2, 1
+EX(11f)	s8i	a9, a3, 0
+EX(11f)	s8i	a8, a3, 1
 #ifdef __XTENSA_EB__
 	slli	a9, a9, 8	/* combine into a single 16-bit value */
 #else				/* for checksum computation */
@@ -381,7 +367,7 @@ ENDPROC(csum_partial_copy_generic)
 	a12 = original dst for exception handling
 */
 
-6001:
+10:
 	_movi	a2, -EFAULT
 	s32i	a2, a6, 0	/* src_err_ptr */
 
@@ -403,7 +389,7 @@ ENDPROC(csum_partial_copy_generic)
 2:
 	retw
 
-6002:
+11:
 	movi	a2, -EFAULT
 	s32i	a2, a7, 0	/* dst_err_ptr */
 	movi	a2, 0
diff --git a/arch/xtensa/lib/memcopy.S b/arch/xtensa/lib/memcopy.S
index b1c219acabe7..c0f6981719d6 100644
--- a/arch/xtensa/lib/memcopy.S
+++ b/arch/xtensa/lib/memcopy.S
@@ -9,23 +9,9 @@
  * Copyright (C) 2002 - 2012 Tensilica Inc.
  */
 
+#include <linux/linkage.h>
 #include <variant/core.h>
-
-	.macro	src_b	r, w0, w1
-#ifdef __XTENSA_EB__
-	src	\r, \w0, \w1
-#else
-	src	\r, \w1, \w0
-#endif
-	.endm
-
-	.macro	ssa8	r
-#ifdef __XTENSA_EB__
-	ssa8b	\r
-#else
-	ssa8l	\r
-#endif
-	.endm
+#include <asm/asmmacro.h>
 
 /*
  * void *memcpy(void *dst, const void *src, size_t len);
@@ -123,10 +109,8 @@
 	addi	a5, a5,  2
 	j	.Ldstaligned	# dst is now aligned, return to main algorithm
 
-	.align	4
-	.global	memcpy
-	.type   memcpy,@function
-memcpy:
+ENTRY(__memcpy)
+WEAK(memcpy)
 
 	entry	sp, 16		# minimal stack frame
 	# a2/ dst, a3/ src, a4/ len
@@ -209,7 +193,7 @@ memcpy:
 .Lsrcunaligned:
 	_beqz	a4, .Ldone	# avoid loading anything for zero-length copies
 	# copy 16 bytes per iteration for word-aligned dst and unaligned src
-	ssa8	a3		# set shift amount from byte offset
+	__ssa8	a3		# set shift amount from byte offset
 
 /* set to 1 when running on ISS (simulator) with the
    lint or ferret client, or 0 to save a few cycles */
@@ -229,16 +213,16 @@ memcpy:
 .Loop2:
 	l32i	a7, a3,  4
 	l32i	a8, a3,  8
-	src_b	a6, a6, a7
+	__src_b	a6, a6, a7
 	s32i	a6, a5,  0
 	l32i	a9, a3, 12
-	src_b	a7, a7, a8
+	__src_b	a7, a7, a8
 	s32i	a7, a5,  4
 	l32i	a6, a3, 16
-	src_b	a8, a8, a9
+	__src_b	a8, a8, a9
 	s32i	a8, a5,  8
 	addi	a3, a3, 16
-	src_b	a9, a9, a6
+	__src_b	a9, a9, a6
 	s32i	a9, a5, 12
 	addi	a5, a5, 16
 #if !XCHAL_HAVE_LOOPS
@@ -249,10 +233,10 @@ memcpy:
 	# copy 8 bytes
 	l32i	a7, a3,  4
 	l32i	a8, a3,  8
-	src_b	a6, a6, a7
+	__src_b	a6, a6, a7
 	s32i	a6, a5,  0
 	addi	a3, a3,  8
-	src_b	a7, a7, a8
+	__src_b	a7, a7, a8
 	s32i	a7, a5,  4
 	addi	a5, a5,  8
 	mov	a6, a8
@@ -261,7 +245,7 @@ memcpy:
 	# copy 4 bytes
 	l32i	a7, a3,  4
 	addi	a3, a3,  4
-	src_b	a6, a6, a7
+	__src_b	a6, a6, a7
 	s32i	a6, a5,  0
 	addi	a5, a5,  4
 	mov	a6, a7
@@ -288,14 +272,14 @@ memcpy:
 	s8i	a6, a5,  0
 	retw
 
+ENDPROC(__memcpy)
 
 /*
  * void bcopy(const void *src, void *dest, size_t n);
  */
-	.align	4
-	.global	bcopy
-	.type   bcopy,@function
-bcopy:
+
+ENTRY(bcopy)
+
 	entry	sp, 16		# minimal stack frame
 	# a2=src, a3=dst, a4=len
 	mov	a5, a3
@@ -303,6 +287,8 @@ bcopy:
 	mov	a2, a5
 	j	.Lmovecommon	# go to common code for memmove+bcopy
 
+ENDPROC(bcopy)
+
 /*
  * void *memmove(void *dst, const void *src, size_t len);
  *
@@ -391,10 +377,8 @@ bcopy:
 	j	.Lbackdstaligned	# dst is now aligned,
 					# return to main algorithm
 
-	.align	4
-	.global	memmove
-	.type   memmove,@function
-memmove:
+ENTRY(__memmove)
+WEAK(memmove)
 
 	entry	sp, 16		# minimal stack frame
 	# a2/ dst, a3/ src, a4/ len
@@ -485,7 +469,7 @@ memmove:
 .Lbacksrcunaligned:
 	_beqz	a4, .Lbackdone	# avoid loading anything for zero-length copies
 	# copy 16 bytes per iteration for word-aligned dst and unaligned src
-	ssa8	a3		# set shift amount from byte offset
+	__ssa8	a3		# set shift amount from byte offset
 #define SIM_CHECKS_ALIGNMENT	1	/* set to 1 when running on ISS with
 					 * the lint or ferret client, or 0
 					 * to save a few cycles */
@@ -506,15 +490,15 @@ memmove:
 	l32i	a7, a3, 12
 	l32i	a8, a3,  8
 	addi	a5, a5, -16
-	src_b	a6, a7, a6
+	__src_b	a6, a7, a6
 	s32i	a6, a5, 12
 	l32i	a9, a3,  4
-	src_b	a7, a8, a7
+	__src_b	a7, a8, a7
 	s32i	a7, a5,  8
 	l32i	a6, a3,  0
-	src_b	a8, a9, a8
+	__src_b	a8, a9, a8
 	s32i	a8, a5,  4
-	src_b	a9, a6, a9
+	__src_b	a9, a6, a9
 	s32i	a9, a5,  0
 #if !XCHAL_HAVE_LOOPS
 	bne	a3, a10, .backLoop2 # continue loop if a3:src != a10:src_start
@@ -526,9 +510,9 @@ memmove:
 	l32i	a7, a3,  4
 	l32i	a8, a3,  0
 	addi	a5, a5, -8
-	src_b	a6, a7, a6
+	__src_b	a6, a7, a6
 	s32i	a6, a5,  4
-	src_b	a7, a8, a7
+	__src_b	a7, a8, a7
 	s32i	a7, a5,  0
 	mov	a6, a8
 .Lback12:
@@ -537,7 +521,7 @@ memmove:
 	addi	a3, a3, -4
 	l32i	a7, a3,  0
 	addi	a5, a5, -4
-	src_b	a6, a7, a6
+	__src_b	a6, a7, a6
 	s32i	a6, a5,  0
 	mov	a6, a7
 .Lback13:
@@ -566,11 +550,4 @@ memmove:
 	s8i	a6, a5,  0
 	retw
 
-
-/*
- * Local Variables:
- * mode:fundamental
- * comment-start: "# "
- * comment-start-skip: "# *"
- * End:
- */
+ENDPROC(__memmove)
diff --git a/arch/xtensa/lib/memset.S b/arch/xtensa/lib/memset.S
index 10b8c400f175..276747dec300 100644
--- a/arch/xtensa/lib/memset.S
+++ b/arch/xtensa/lib/memset.S
@@ -11,7 +11,9 @@
  *  Copyright (C) 2002 Tensilica Inc.
  */
 
+#include <linux/linkage.h>
 #include <variant/core.h>
+#include <asm/asmmacro.h>
 
 /*
  * void *memset(void *dst, int c, size_t length)
@@ -28,20 +30,10 @@
  *     the alignment labels).
  */
 
-/* Load or store instructions that may cause exceptions use the EX macro. */
-
-#define EX(insn,reg1,reg2,offset,handler)	\
-9:	insn	reg1, reg2, offset;		\
-	.section __ex_table, "a";		\
-	.word	9b, handler;			\
-	.previous
-
-
 .text
-.align	4
-.global	memset
-.type	memset,@function
-memset:
+ENTRY(__memset)
+WEAK(memset)
+
 	entry	sp, 16		# minimal stack frame
 	# a2/ dst, a3/ c, a4/ length
 	extui	a3, a3, 0, 8	# mask to just 8 bits
@@ -73,10 +65,10 @@ memset:
 	add	a6, a6, a5	# a6 = end of last 16B chunk
 #endif /* !XCHAL_HAVE_LOOPS */
 .Loop1:
-	EX(s32i, a3, a5,  0, memset_fixup)
-	EX(s32i, a3, a5,  4, memset_fixup)
-	EX(s32i, a3, a5,  8, memset_fixup)
-	EX(s32i, a3, a5, 12, memset_fixup)
+EX(10f) s32i	a3, a5,  0
+EX(10f) s32i	a3, a5,  4
+EX(10f) s32i	a3, a5,  8
+EX(10f) s32i	a3, a5, 12
 	addi	a5, a5, 16
 #if !XCHAL_HAVE_LOOPS
 	blt	a5, a6, .Loop1
@@ -84,23 +76,23 @@ memset:
 .Loop1done:
 	bbci.l	a4, 3, .L2
 	# set 8 bytes
-	EX(s32i, a3, a5,  0, memset_fixup)
-	EX(s32i, a3, a5,  4, memset_fixup)
+EX(10f) s32i	a3, a5,  0
+EX(10f) s32i	a3, a5,  4
 	addi	a5, a5,  8
 .L2:
 	bbci.l	a4, 2, .L3
 	# set 4 bytes
-	EX(s32i, a3, a5,  0, memset_fixup)
+EX(10f) s32i	a3, a5,  0
 	addi	a5, a5,  4
 .L3:
 	bbci.l	a4, 1, .L4
 	# set 2 bytes
-	EX(s16i, a3, a5,  0, memset_fixup)
+EX(10f) s16i	a3, a5,  0
 	addi	a5, a5,  2
 .L4:
 	bbci.l	a4, 0, .L5
 	# set 1 byte
-	EX(s8i, a3, a5,  0, memset_fixup)
+EX(10f) s8i	a3, a5,  0
 .L5:
 .Lret1:
 	retw
@@ -114,7 +106,7 @@ memset:
 	bbci.l	a5, 0, .L20		# branch if dst alignment half-aligned
 	# dst is only byte aligned
 	# set 1 byte
-	EX(s8i, a3, a5,  0, memset_fixup)
+EX(10f) s8i	a3, a5,  0
 	addi	a5, a5,  1
 	addi	a4, a4, -1
 	# now retest if dst aligned
@@ -122,7 +114,7 @@ memset:
 .L20:
 	# dst half-aligned
 	# set 2 bytes
-	EX(s16i, a3, a5,  0, memset_fixup)
+EX(10f) s16i	a3, a5,  0
 	addi	a5, a5,  2
 	addi	a4, a4, -2
 	j	.L0		# dst is now aligned, return to main algorithm
@@ -141,7 +133,7 @@ memset:
 	add	a6, a5, a4	# a6 = ending address
 #endif /* !XCHAL_HAVE_LOOPS */
 .Lbyteloop:
-	EX(s8i, a3, a5, 0, memset_fixup)
+EX(10f) s8i	a3, a5, 0
 	addi	a5, a5, 1
 #if !XCHAL_HAVE_LOOPS
 	blt	a5, a6, .Lbyteloop
@@ -149,12 +141,13 @@ memset:
 .Lbytesetdone:
 	retw
 
+ENDPROC(__memset)
 
 	.section .fixup, "ax"
 	.align	4
 
 /* We return zero if a failure occurred. */
 
-memset_fixup:
+10:
 	movi	a2, 0
 	retw
diff --git a/arch/xtensa/lib/pci-auto.c b/arch/xtensa/lib/pci-auto.c
index 34d05abbd921..a2b558161d6d 100644
--- a/arch/xtensa/lib/pci-auto.c
+++ b/arch/xtensa/lib/pci-auto.c
@@ -49,17 +49,6 @@
  *
  */
 
-
-/* define DEBUG to print some debugging messages. */
-
-#undef DEBUG
-
-#ifdef DEBUG
-# define DBG(x...) printk(x)
-#else
-# define DBG(x...)
-#endif
-
 static int pciauto_upper_iospc;
 static int pciauto_upper_memspc;
 
@@ -97,7 +86,7 @@ pciauto_setup_bars(struct pci_dev *dev, int bar_limit)
 		{
 			bar_size &= PCI_BASE_ADDRESS_IO_MASK;
 			upper_limit = &pciauto_upper_iospc;
-			DBG("PCI Autoconfig: BAR %d, I/O, ", bar_nr);
+			pr_debug("PCI Autoconfig: BAR %d, I/O, ", bar_nr);
 		}
 		else
 		{
@@ -107,7 +96,7 @@ pciauto_setup_bars(struct pci_dev *dev, int bar_limit)
 
 			bar_size &= PCI_BASE_ADDRESS_MEM_MASK;
 			upper_limit = &pciauto_upper_memspc;
-			DBG("PCI Autoconfig: BAR %d, Mem, ", bar_nr);
+			pr_debug("PCI Autoconfig: BAR %d, Mem, ", bar_nr);
 		}
 
 		/* Allocate a base address (bar_size is negative!) */
@@ -125,7 +114,8 @@ pciauto_setup_bars(struct pci_dev *dev, int bar_limit)
 		if (found_mem64)
 			pci_write_config_dword(dev, (bar+=4), 0x00000000);
 
-		DBG("size=0x%x, address=0x%x\n", ~bar_size + 1, *upper_limit);
+		pr_debug("size=0x%x, address=0x%x\n",
+			 ~bar_size + 1, *upper_limit);
 	}
 }
 
@@ -150,7 +140,7 @@ pciauto_setup_irq(struct pci_controller* pci_ctrl,struct pci_dev *dev,int devfn)
 	if (irq == -1)
 		irq = 0;
 
-	DBG("PCI Autoconfig: Interrupt %d, pin %d\n", irq, pin);
+	pr_debug("PCI Autoconfig: Interrupt %d, pin %d\n", irq, pin);
 
 	pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq);
 }
@@ -289,8 +279,8 @@ int __init pciauto_bus_scan(struct pci_controller *pci_ctrl, int current_bus)
 
 			int iosave, memsave;
 
-			DBG("PCI Autoconfig: Found P2P bridge, device %d\n",
-			    PCI_SLOT(pci_devfn));
+			pr_debug("PCI Autoconfig: Found P2P bridge, device %d\n",
+				 PCI_SLOT(pci_devfn));
 
 			/* Allocate PCI I/O and/or memory space */
 			pciauto_setup_bars(dev, PCI_BASE_ADDRESS_1);
@@ -306,23 +296,6 @@ int __init pciauto_bus_scan(struct pci_controller *pci_ctrl, int current_bus)
 
 		}
 
-
-#if 0
-		/* Skip legacy mode IDE controller */
-
-		if ((pci_class >> 16) == PCI_CLASS_STORAGE_IDE) {
-
-			unsigned char prg_iface;
-			pci_read_config_byte(dev, PCI_CLASS_PROG, &prg_iface);
-
-			if (!(prg_iface & PCIAUTO_IDE_MODE_MASK)) {
-				DBG("PCI Autoconfig: Skipping legacy mode "
-				    "IDE controller\n");
-				continue;
-			}
-		}
-#endif
-
 		/*
 		 * Found a peripheral, enable some standard
 		 * settings
@@ -337,8 +310,8 @@ int __init pciauto_bus_scan(struct pci_controller *pci_ctrl, int current_bus)
 		pci_write_config_byte(dev, PCI_LATENCY_TIMER, 0x80);
 
 		/* Allocate PCI I/O and/or memory space */
-		DBG("PCI Autoconfig: Found Bus %d, Device %d, Function %d\n",
-		    current_bus, PCI_SLOT(pci_devfn), PCI_FUNC(pci_devfn) );
+		pr_debug("PCI Autoconfig: Found Bus %d, Device %d, Function %d\n",
+			 current_bus, PCI_SLOT(pci_devfn), PCI_FUNC(pci_devfn));
 
 		pciauto_setup_bars(dev, PCI_BASE_ADDRESS_5);
 		pciauto_setup_irq(pci_ctrl, dev, pci_devfn);
diff --git a/arch/xtensa/lib/strncpy_user.S b/arch/xtensa/lib/strncpy_user.S
index 1ad0ecf45368..5fce16b67dca 100644
--- a/arch/xtensa/lib/strncpy_user.S
+++ b/arch/xtensa/lib/strncpy_user.S
@@ -11,16 +11,10 @@
  *  Copyright (C) 2002 Tensilica Inc.
  */
 
-#include <variant/core.h>
 #include <linux/errno.h>
-
-/* Load or store instructions that may cause exceptions use the EX macro. */
-
-#define EX(insn,reg1,reg2,offset,handler)	\
-9:	insn	reg1, reg2, offset;		\
-	.section __ex_table, "a";		\
-	.word	9b, handler;			\
-	.previous
+#include <linux/linkage.h>
+#include <variant/core.h>
+#include <asm/asmmacro.h>
 
 /*
  * char *__strncpy_user(char *dst, const char *src, size_t len)
@@ -54,10 +48,8 @@
 #   a12/ tmp
 
 .text
-.align	4
-.global	__strncpy_user
-.type	__strncpy_user,@function
-__strncpy_user:
+ENTRY(__strncpy_user)
+
 	entry	sp, 16		# minimal stack frame
 	# a2/ dst, a3/ src, a4/ len
 	mov	a11, a2		# leave dst in return value register
@@ -75,9 +67,9 @@ __strncpy_user:
 	j	.Ldstunaligned
 
 .Lsrc1mod2:	# src address is odd
-	EX(l8ui, a9, a3, 0, fixup_l)	# get byte 0
+EX(11f)	l8ui	a9, a3, 0		# get byte 0
 	addi	a3, a3, 1		# advance src pointer
-	EX(s8i, a9, a11, 0, fixup_s)	# store byte 0
+EX(10f)	s8i	a9, a11, 0		# store byte 0
 	beqz	a9, .Lret		# if byte 0 is zero
 	addi	a11, a11, 1		# advance dst pointer
 	addi	a4, a4, -1		# decrement len
@@ -85,16 +77,16 @@ __strncpy_user:
 	bbci.l	a3, 1, .Lsrcaligned	# if src is now word-aligned
 
 .Lsrc2mod4:	# src address is 2 mod 4
-	EX(l8ui, a9, a3, 0, fixup_l)	# get byte 0
+EX(11f)	l8ui	a9, a3, 0		# get byte 0
 	/* 1-cycle interlock */
-	EX(s8i, a9, a11, 0, fixup_s)	# store byte 0
+EX(10f)	s8i	a9, a11, 0		# store byte 0
 	beqz	a9, .Lret		# if byte 0 is zero
 	addi	a11, a11, 1		# advance dst pointer
 	addi	a4, a4, -1		# decrement len
 	beqz	a4, .Lret		# if len is zero
-	EX(l8ui, a9, a3, 1, fixup_l)	# get byte 0
+EX(11f)	l8ui	a9, a3, 1		# get byte 0
 	addi	a3, a3, 2		# advance src pointer
-	EX(s8i, a9, a11, 0, fixup_s)	# store byte 0
+EX(10f)	s8i	a9, a11, 0		# store byte 0
 	beqz	a9, .Lret		# if byte 0 is zero
 	addi	a11, a11, 1		# advance dst pointer
 	addi	a4, a4, -1		# decrement len
@@ -117,12 +109,12 @@ __strncpy_user:
 	add	a12, a12, a11	# a12 = end of last 4B chunck
 #endif
 .Loop1:
-	EX(l32i, a9, a3, 0, fixup_l)	# get word from src
+EX(11f)	l32i	a9, a3, 0		# get word from src
 	addi	a3, a3, 4		# advance src pointer
 	bnone	a9, a5, .Lz0		# if byte 0 is zero
 	bnone	a9, a6, .Lz1		# if byte 1 is zero
 	bnone	a9, a7, .Lz2		# if byte 2 is zero
-	EX(s32i, a9, a11, 0, fixup_s)	# store word to dst
+EX(10f)	s32i	a9, a11, 0		# store word to dst
 	bnone	a9, a8, .Lz3		# if byte 3 is zero
 	addi	a11, a11, 4		# advance dst pointer
 #if !XCHAL_HAVE_LOOPS
@@ -132,7 +124,7 @@ __strncpy_user:
 .Loop1done:
 	bbci.l	a4, 1, .L100
 	# copy 2 bytes
-	EX(l16ui, a9, a3, 0, fixup_l)
+EX(11f)	l16ui	a9, a3, 0
 	addi	a3, a3, 2		# advance src pointer
 #ifdef __XTENSA_EB__
 	bnone	a9, a7, .Lz0		# if byte 2 is zero
@@ -141,13 +133,13 @@ __strncpy_user:
 	bnone	a9, a5, .Lz0		# if byte 0 is zero
 	bnone	a9, a6, .Lz1		# if byte 1 is zero
 #endif
-	EX(s16i, a9, a11, 0, fixup_s)
+EX(10f)	s16i	a9, a11, 0
 	addi	a11, a11, 2		# advance dst pointer
 .L100:
 	bbci.l	a4, 0, .Lret
-	EX(l8ui, a9, a3, 0, fixup_l)
+EX(11f)	l8ui	a9, a3, 0
 	/* slot */
-	EX(s8i, a9, a11, 0, fixup_s)
+EX(10f)	s8i	a9, a11, 0
 	beqz	a9, .Lret		# if byte is zero
 	addi	a11, a11, 1-3		# advance dst ptr 1, but also cancel
 					# the effect of adding 3 in .Lz3 code
@@ -161,14 +153,14 @@ __strncpy_user:
 #ifdef __XTENSA_EB__
 	movi	a9, 0
 #endif /* __XTENSA_EB__ */
-	EX(s8i, a9, a11, 0, fixup_s)
+EX(10f)	s8i	a9, a11, 0
 	sub	a2, a11, a2		# compute strlen
 	retw
 .Lz1:	# byte 1 is zero
 #ifdef __XTENSA_EB__
 	extui   a9, a9, 16, 16
 #endif /* __XTENSA_EB__ */
-	EX(s16i, a9, a11, 0, fixup_s)
+EX(10f)	s16i	a9, a11, 0
 	addi	a11, a11, 1		# advance dst pointer
 	sub	a2, a11, a2		# compute strlen
 	retw
@@ -176,9 +168,9 @@ __strncpy_user:
 #ifdef __XTENSA_EB__
 	extui   a9, a9, 16, 16
 #endif /* __XTENSA_EB__ */
-	EX(s16i, a9, a11, 0, fixup_s)
+EX(10f)	s16i	a9, a11, 0
 	movi	a9, 0
-	EX(s8i, a9, a11, 2, fixup_s)
+EX(10f)	s8i	a9, a11, 2
 	addi	a11, a11, 2		# advance dst pointer
 	sub	a2, a11, a2		# compute strlen
 	retw
@@ -196,9 +188,9 @@ __strncpy_user:
 	add	a12, a11, a4		# a12 = ending address
 #endif /* XCHAL_HAVE_LOOPS */
 .Lnextbyte:
-	EX(l8ui, a9, a3, 0, fixup_l)
+EX(11f)	l8ui	a9, a3, 0
 	addi	a3, a3, 1
-	EX(s8i, a9, a11, 0, fixup_s)
+EX(10f)	s8i	a9, a11, 0
 	beqz	a9, .Lunalignedend
 	addi	a11, a11, 1
 #if !XCHAL_HAVE_LOOPS
@@ -209,6 +201,7 @@ __strncpy_user:
 	sub	a2, a11, a2		# compute strlen
 	retw
 
+ENDPROC(__strncpy_user)
 
 	.section .fixup, "ax"
 	.align	4
@@ -218,8 +211,7 @@ __strncpy_user:
 	 * implementation in memset().  Thus, we differentiate between
 	 * load/store fixups. */
 
-fixup_s:
-fixup_l:
+10:
+11:
 	movi	a2, -EFAULT
 	retw
-
diff --git a/arch/xtensa/lib/strnlen_user.S b/arch/xtensa/lib/strnlen_user.S
index 4c03b1e581e9..0b956ce7f386 100644
--- a/arch/xtensa/lib/strnlen_user.S
+++ b/arch/xtensa/lib/strnlen_user.S
@@ -11,15 +11,9 @@
  *  Copyright (C) 2002 Tensilica Inc.
  */
 
+#include <linux/linkage.h>
 #include <variant/core.h>
-
-/* Load or store instructions that may cause exceptions use the EX macro. */
-
-#define EX(insn,reg1,reg2,offset,handler)	\
-9:	insn	reg1, reg2, offset;		\
-	.section __ex_table, "a";		\
-	.word	9b, handler;			\
-	.previous
+#include <asm/asmmacro.h>
 
 /*
  * size_t __strnlen_user(const char *s, size_t len)
@@ -49,10 +43,8 @@
 #   a10/ tmp
 
 .text
-.align	4
-.global	__strnlen_user
-.type	__strnlen_user,@function
-__strnlen_user:
+ENTRY(__strnlen_user)
+
 	entry	sp, 16		# minimal stack frame
 	# a2/ s, a3/ len
 	addi	a4, a2, -4	# because we overincrement at the end;
@@ -77,7 +69,7 @@ __strnlen_user:
 	add	a10, a10, a4	# a10 = end of last 4B chunk
 #endif /* XCHAL_HAVE_LOOPS */
 .Loop:
-	EX(l32i, a9, a4, 4, lenfixup)	# get next word of string
+EX(10f)	l32i	a9, a4, 4		# get next word of string
 	addi	a4, a4, 4		# advance string pointer
 	bnone	a9, a5, .Lz0		# if byte 0 is zero
 	bnone	a9, a6, .Lz1		# if byte 1 is zero
@@ -88,7 +80,7 @@ __strnlen_user:
 #endif
 
 .Ldone:
-	EX(l32i, a9, a4, 4, lenfixup)	# load 4 bytes for remaining checks
+EX(10f)	l32i	a9, a4, 4	# load 4 bytes for remaining checks
 
 	bbci.l	a3, 1, .L100
 	# check two more bytes (bytes 0, 1 of word)
@@ -125,14 +117,14 @@ __strnlen_user:
 	retw
 
 .L1mod2:	# address is odd
-	EX(l8ui, a9, a4, 4, lenfixup)	# get byte 0
+EX(10f)	l8ui	a9, a4, 4		# get byte 0
 	addi	a4, a4, 1		# advance string pointer
 	beqz	a9, .Lz3		# if byte 0 is zero
 	bbci.l	a4, 1, .Laligned	# if string pointer is now word-aligned
 
 .L2mod4:	# address is 2 mod 4
 	addi	a4, a4, 2	# advance ptr for aligned access
-	EX(l32i, a9, a4, 0, lenfixup)	# get word with first two bytes of string
+EX(10f)	l32i	a9, a4, 0	# get word with first two bytes of string
 	bnone	a9, a7, .Lz2	# if byte 2 (of word, not string) is zero
 	bany	a9, a8, .Laligned # if byte 3 (of word, not string) is nonzero
 	# byte 3 is zero
@@ -140,8 +132,10 @@ __strnlen_user:
 	sub	a2, a4, a2	# subtract to get length
 	retw
 
+ENDPROC(__strnlen_user)
+
 	.section .fixup, "ax"
 	.align	4
-lenfixup:
+10:
 	movi	a2, 0
 	retw
diff --git a/arch/xtensa/lib/usercopy.S b/arch/xtensa/lib/usercopy.S
index d9cd766bde3e..64ab1971324f 100644
--- a/arch/xtensa/lib/usercopy.S
+++ b/arch/xtensa/lib/usercopy.S
@@ -53,30 +53,13 @@
  *	a11/ original length
  */
 
+#include <linux/linkage.h>
 #include <variant/core.h>
-
-#ifdef __XTENSA_EB__
-#define ALIGN(R, W0, W1) src	R, W0, W1
-#define SSA8(R)	ssa8b R
-#else
-#define ALIGN(R, W0, W1) src	R, W1, W0
-#define SSA8(R)	ssa8l R
-#endif
-
-/* Load or store instructions that may cause exceptions use the EX macro. */
-
-#define EX(insn,reg1,reg2,offset,handler)	\
-9:	insn	reg1, reg2, offset;		\
-	.section __ex_table, "a";		\
-	.word	9b, handler;			\
-	.previous
-
+#include <asm/asmmacro.h>
 
 	.text
-	.align	4
-	.global	__xtensa_copy_user
-	.type	__xtensa_copy_user,@function
-__xtensa_copy_user:
+ENTRY(__xtensa_copy_user)
+
 	entry	sp, 16		# minimal stack frame
 	# a2/ dst, a3/ src, a4/ len
 	mov	a5, a2		# copy dst so that a2 is return value
@@ -89,7 +72,7 @@ __xtensa_copy_user:
 				# per iteration
 	movi	a8, 3		  # if source is also aligned,
 	bnone	a3, a8, .Laligned # then use word copy
-	SSA8(	a3)		# set shift amount from byte offset
+	__ssa8	a3		# set shift amount from byte offset
 	bnez	a4, .Lsrcunaligned
 	movi	a2, 0		# return success for len==0
 	retw
@@ -102,9 +85,9 @@ __xtensa_copy_user:
 	bltui	a4, 7, .Lbytecopy	# do short copies byte by byte
 
 	# copy 1 byte
-	EX(l8ui, a6, a3, 0, fixup)
+EX(10f)	l8ui	a6, a3, 0
 	addi	a3, a3,  1
-	EX(s8i, a6, a5,  0, fixup)
+EX(10f)	s8i	a6, a5,  0
 	addi	a5, a5,  1
 	addi	a4, a4, -1
 	bbci.l	a5, 1, .Ldstaligned	# if dst is now aligned, then
@@ -112,11 +95,11 @@ __xtensa_copy_user:
 .Ldst2mod4:	# dst 16-bit aligned
 	# copy 2 bytes
 	bltui	a4, 6, .Lbytecopy	# do short copies byte by byte
-	EX(l8ui, a6, a3, 0, fixup)
-	EX(l8ui, a7, a3, 1, fixup)
+EX(10f)	l8ui	a6, a3, 0
+EX(10f)	l8ui	a7, a3, 1
 	addi	a3, a3,  2
-	EX(s8i, a6, a5,  0, fixup)
-	EX(s8i, a7, a5,  1, fixup)
+EX(10f)	s8i	a6, a5,  0
+EX(10f)	s8i	a7, a5,  1
 	addi	a5, a5,  2
 	addi	a4, a4, -2
 	j	.Ldstaligned	# dst is now aligned, return to main algorithm
@@ -135,9 +118,9 @@ __xtensa_copy_user:
 	add	a7, a3, a4	# a7 = end address for source
 #endif /* !XCHAL_HAVE_LOOPS */
 .Lnextbyte:
-	EX(l8ui, a6, a3, 0, fixup)
+EX(10f)	l8ui	a6, a3, 0
 	addi	a3, a3, 1
-	EX(s8i, a6, a5, 0, fixup)
+EX(10f)	s8i	a6, a5, 0
 	addi	a5, a5, 1
 #if !XCHAL_HAVE_LOOPS
 	blt	a3, a7, .Lnextbyte
@@ -161,15 +144,15 @@ __xtensa_copy_user:
 	add	a8, a8, a3	# a8 = end of last 16B source chunk
 #endif /* !XCHAL_HAVE_LOOPS */
 .Loop1:
-	EX(l32i, a6, a3,  0, fixup)
-	EX(l32i, a7, a3,  4, fixup)
-	EX(s32i, a6, a5,  0, fixup)
-	EX(l32i, a6, a3,  8, fixup)
-	EX(s32i, a7, a5,  4, fixup)
-	EX(l32i, a7, a3, 12, fixup)
-	EX(s32i, a6, a5,  8, fixup)
+EX(10f)	l32i	a6, a3,  0
+EX(10f)	l32i	a7, a3,  4
+EX(10f)	s32i	a6, a5,  0
+EX(10f)	l32i	a6, a3,  8
+EX(10f)	s32i	a7, a5,  4
+EX(10f)	l32i	a7, a3, 12
+EX(10f)	s32i	a6, a5,  8
 	addi	a3, a3, 16
-	EX(s32i, a7, a5, 12, fixup)
+EX(10f)	s32i	a7, a5, 12
 	addi	a5, a5, 16
 #if !XCHAL_HAVE_LOOPS
 	blt	a3, a8, .Loop1
@@ -177,31 +160,31 @@ __xtensa_copy_user:
 .Loop1done:
 	bbci.l	a4, 3, .L2
 	# copy 8 bytes
-	EX(l32i, a6, a3,  0, fixup)
-	EX(l32i, a7, a3,  4, fixup)
+EX(10f)	l32i	a6, a3,  0
+EX(10f)	l32i	a7, a3,  4
 	addi	a3, a3,  8
-	EX(s32i, a6, a5,  0, fixup)
-	EX(s32i, a7, a5,  4, fixup)
+EX(10f)	s32i	a6, a5,  0
+EX(10f)	s32i	a7, a5,  4
 	addi	a5, a5,  8
 .L2:
 	bbci.l	a4, 2, .L3
 	# copy 4 bytes
-	EX(l32i, a6, a3,  0, fixup)
+EX(10f)	l32i	a6, a3,  0
 	addi	a3, a3,  4
-	EX(s32i, a6, a5,  0, fixup)
+EX(10f)	s32i	a6, a5,  0
 	addi	a5, a5,  4
 .L3:
 	bbci.l	a4, 1, .L4
 	# copy 2 bytes
-	EX(l16ui, a6, a3,  0, fixup)
+EX(10f)	l16ui	a6, a3,  0
 	addi	a3, a3,  2
-	EX(s16i,  a6, a5,  0, fixup)
+EX(10f)	s16i	a6, a5,  0
 	addi	a5, a5,  2
 .L4:
 	bbci.l	a4, 0, .L5
 	# copy 1 byte
-	EX(l8ui, a6, a3,  0, fixup)
-	EX(s8i,  a6, a5,  0, fixup)
+EX(10f)	l8ui	a6, a3,  0
+EX(10f)	s8i	a6, a5,  0
 .L5:
 	movi	a2, 0		# return success for len bytes copied
 	retw
@@ -217,7 +200,7 @@ __xtensa_copy_user:
 	# copy 16 bytes per iteration for word-aligned dst and unaligned src
 	and	a10, a3, a8	# save unalignment offset for below
 	sub	a3, a3, a10	# align a3 (to avoid sim warnings only; not needed for hardware)
-	EX(l32i, a6, a3, 0, fixup)	# load first word
+EX(10f)	l32i	a6, a3, 0	# load first word
 #if XCHAL_HAVE_LOOPS
 	loopnez	a7, .Loop2done
 #else /* !XCHAL_HAVE_LOOPS */
@@ -226,19 +209,19 @@ __xtensa_copy_user:
 	add	a12, a12, a3	# a12 = end of last 16B source chunk
 #endif /* !XCHAL_HAVE_LOOPS */
 .Loop2:
-	EX(l32i, a7, a3,  4, fixup)
-	EX(l32i, a8, a3,  8, fixup)
-	ALIGN(	a6, a6, a7)
-	EX(s32i, a6, a5,  0, fixup)
-	EX(l32i, a9, a3, 12, fixup)
-	ALIGN(	a7, a7, a8)
-	EX(s32i, a7, a5,  4, fixup)
-	EX(l32i, a6, a3, 16, fixup)
-	ALIGN(	a8, a8, a9)
-	EX(s32i, a8, a5,  8, fixup)
+EX(10f)	l32i	a7, a3,  4
+EX(10f)	l32i	a8, a3,  8
+	__src_b	a6, a6, a7
+EX(10f)	s32i	a6, a5,  0
+EX(10f)	l32i	a9, a3, 12
+	__src_b	a7, a7, a8
+EX(10f)	s32i	a7, a5,  4
+EX(10f)	l32i	a6, a3, 16
+	__src_b	a8, a8, a9
+EX(10f)	s32i	a8, a5,  8
 	addi	a3, a3, 16
-	ALIGN(	a9, a9, a6)
-	EX(s32i, a9, a5, 12, fixup)
+	__src_b	a9, a9, a6
+EX(10f)	s32i	a9, a5, 12
 	addi	a5, a5, 16
 #if !XCHAL_HAVE_LOOPS
 	blt	a3, a12, .Loop2
@@ -246,43 +229,44 @@ __xtensa_copy_user:
 .Loop2done:
 	bbci.l	a4, 3, .L12
 	# copy 8 bytes
-	EX(l32i, a7, a3,  4, fixup)
-	EX(l32i, a8, a3,  8, fixup)
-	ALIGN(	a6, a6, a7)
-	EX(s32i, a6, a5,  0, fixup)
+EX(10f)	l32i	a7, a3,  4
+EX(10f)	l32i	a8, a3,  8
+	__src_b	a6, a6, a7
+EX(10f)	s32i	a6, a5,  0
 	addi	a3, a3,  8
-	ALIGN(	a7, a7, a8)
-	EX(s32i, a7, a5,  4, fixup)
+	__src_b	a7, a7, a8
+EX(10f)	s32i	a7, a5,  4
 	addi	a5, a5,  8
 	mov	a6, a8
 .L12:
 	bbci.l	a4, 2, .L13
 	# copy 4 bytes
-	EX(l32i, a7, a3,  4, fixup)
+EX(10f)	l32i	a7, a3,  4
 	addi	a3, a3,  4
-	ALIGN(	a6, a6, a7)
-	EX(s32i, a6, a5,  0, fixup)
+	__src_b	a6, a6, a7
+EX(10f)	s32i	a6, a5,  0
 	addi	a5, a5,  4
 	mov	a6, a7
 .L13:
 	add	a3, a3, a10	# readjust a3 with correct misalignment
 	bbci.l	a4, 1, .L14
 	# copy 2 bytes
-	EX(l8ui, a6, a3,  0, fixup)
-	EX(l8ui, a7, a3,  1, fixup)
+EX(10f)	l8ui	a6, a3,  0
+EX(10f)	l8ui	a7, a3,  1
 	addi	a3, a3,  2
-	EX(s8i, a6, a5,  0, fixup)
-	EX(s8i, a7, a5,  1, fixup)
+EX(10f)	s8i	a6, a5,  0
+EX(10f)	s8i	a7, a5,  1
 	addi	a5, a5,  2
 .L14:
 	bbci.l	a4, 0, .L15
 	# copy 1 byte
-	EX(l8ui, a6, a3,  0, fixup)
-	EX(s8i,  a6, a5,  0, fixup)
+EX(10f)	l8ui	a6, a3,  0
+EX(10f)	s8i	a6, a5,  0
 .L15:
 	movi	a2, 0		# return success for len bytes copied
 	retw
 
+ENDPROC(__xtensa_copy_user)
 
 	.section .fixup, "ax"
 	.align	4
@@ -294,7 +278,7 @@ __xtensa_copy_user:
  */
 
 
-fixup:
+10:
 	sub	a2, a5, a2	/* a2 <-- bytes copied */
 	sub	a2, a11, a2	/* a2 <-- bytes not copied */
 	retw
diff --git a/arch/xtensa/mm/Makefile b/arch/xtensa/mm/Makefile
index 0b3d296a016a..734888a00dc8 100644
--- a/arch/xtensa/mm/Makefile
+++ b/arch/xtensa/mm/Makefile
@@ -5,3 +5,8 @@
 obj-y			:= init.o misc.o
 obj-$(CONFIG_MMU)	+= cache.o fault.o ioremap.o mmu.o tlb.o
 obj-$(CONFIG_HIGHMEM)	+= highmem.o
+obj-$(CONFIG_KASAN)	+= kasan_init.o
+
+KASAN_SANITIZE_fault.o := n
+KASAN_SANITIZE_kasan_init.o := n
+KASAN_SANITIZE_mmu.o := n
diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c
index 3c75c4e597da..57dc231a0709 100644
--- a/arch/xtensa/mm/cache.c
+++ b/arch/xtensa/mm/cache.c
@@ -33,9 +33,6 @@
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 
-//#define printd(x...) printk(x)
-#define printd(x...) do { } while(0)
-
 /* 
  * Note:
  * The kernel provides one architecture bit PG_arch_1 in the page flags that 
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index a14df5aa98c8..8b9b6f44bb06 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -25,8 +25,6 @@
 DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST;
 void bad_page_fault(struct pt_regs*, unsigned long, int);
 
-#undef DEBUG_PAGE_FAULT
-
 /*
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate
@@ -68,10 +66,10 @@ void do_page_fault(struct pt_regs *regs)
 		    exccause == EXCCAUSE_ITLB_MISS ||
 		    exccause == EXCCAUSE_FETCH_CACHE_ATTRIBUTE) ? 1 : 0;
 
-#ifdef DEBUG_PAGE_FAULT
-	printk("[%s:%d:%08x:%d:%08x:%s%s]\n", current->comm, current->pid,
-	       address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
-#endif
+	pr_debug("[%s:%d:%08x:%d:%08lx:%s%s]\n",
+		 current->comm, current->pid,
+		 address, exccause, regs->pc,
+		 is_write ? "w" : "", is_exec ? "x" : "");
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
@@ -247,10 +245,8 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 
 	/* Are we prepared to handle this kernel fault?  */
 	if ((entry = search_exception_tables(regs->pc)) != NULL) {
-#ifdef DEBUG_PAGE_FAULT
-		printk(KERN_DEBUG "%s: Exception at pc=%#010lx (%lx)\n",
-				current->comm, regs->pc, entry->fixup);
-#endif
+		pr_debug("%s: Exception at pc=%#010lx (%lx)\n",
+			 current->comm, regs->pc, entry->fixup);
 		current->thread.bad_uaddr = address;
 		regs->pc = entry->fixup;
 		return;
@@ -259,9 +255,9 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 	/* Oops. The kernel tried to access some bad page. We'll have to
 	 * terminate things with extreme prejudice.
 	 */
-	printk(KERN_ALERT "Unable to handle kernel paging request at virtual "
-	       "address %08lx\n pc = %08lx, ra = %08lx\n",
-	       address, regs->pc, regs->areg[0]);
+	pr_alert("Unable to handle kernel paging request at virtual "
+		 "address %08lx\n pc = %08lx, ra = %08lx\n",
+		 address, regs->pc, regs->areg[0]);
 	die("Oops", regs, sig);
 	do_exit(sig);
 }
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 720fe4e8b497..d776ec0d7b22 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -100,29 +100,51 @@ void __init mem_init(void)
 
 	mem_init_print_info(NULL);
 	pr_info("virtual kernel memory layout:\n"
+#ifdef CONFIG_KASAN
+		"    kasan   : 0x%08lx - 0x%08lx  (%5lu MB)\n"
+#endif
+#ifdef CONFIG_MMU
+		"    vmalloc : 0x%08lx - 0x%08lx  (%5lu MB)\n"
+#endif
 #ifdef CONFIG_HIGHMEM
 		"    pkmap   : 0x%08lx - 0x%08lx  (%5lu kB)\n"
 		"    fixmap  : 0x%08lx - 0x%08lx  (%5lu kB)\n"
 #endif
-#ifdef CONFIG_MMU
-		"    vmalloc : 0x%08lx - 0x%08lx  (%5lu MB)\n"
+		"    lowmem  : 0x%08lx - 0x%08lx  (%5lu MB)\n"
+		"    .text   : 0x%08lx - 0x%08lx  (%5lu kB)\n"
+		"    .rodata : 0x%08lx - 0x%08lx  (%5lu kB)\n"
+		"    .data   : 0x%08lx - 0x%08lx  (%5lu kB)\n"
+		"    .init   : 0x%08lx - 0x%08lx  (%5lu kB)\n"
+		"    .bss    : 0x%08lx - 0x%08lx  (%5lu kB)\n",
+#ifdef CONFIG_KASAN
+		KASAN_SHADOW_START, KASAN_SHADOW_START + KASAN_SHADOW_SIZE,
+		KASAN_SHADOW_SIZE >> 20,
 #endif
-		"    lowmem  : 0x%08lx - 0x%08lx  (%5lu MB)\n",
+#ifdef CONFIG_MMU
+		VMALLOC_START, VMALLOC_END,
+		(VMALLOC_END - VMALLOC_START) >> 20,
 #ifdef CONFIG_HIGHMEM
 		PKMAP_BASE, PKMAP_BASE + LAST_PKMAP * PAGE_SIZE,
 		(LAST_PKMAP*PAGE_SIZE) >> 10,
 		FIXADDR_START, FIXADDR_TOP,
 		(FIXADDR_TOP - FIXADDR_START) >> 10,
 #endif
-#ifdef CONFIG_MMU
-		VMALLOC_START, VMALLOC_END,
-		(VMALLOC_END - VMALLOC_START) >> 20,
 		PAGE_OFFSET, PAGE_OFFSET +
 		(max_low_pfn - min_low_pfn) * PAGE_SIZE,
 #else
 		min_low_pfn * PAGE_SIZE, max_low_pfn * PAGE_SIZE,
 #endif
-		((max_low_pfn - min_low_pfn) * PAGE_SIZE) >> 20);
+		((max_low_pfn - min_low_pfn) * PAGE_SIZE) >> 20,
+		(unsigned long)_text, (unsigned long)_etext,
+		(unsigned long)(_etext - _text) >> 10,
+		(unsigned long)__start_rodata, (unsigned long)_sdata,
+		(unsigned long)(_sdata - __start_rodata) >> 10,
+		(unsigned long)_sdata, (unsigned long)_edata,
+		(unsigned long)(_edata - _sdata) >> 10,
+		(unsigned long)__init_begin, (unsigned long)__init_end,
+		(unsigned long)(__init_end - __init_begin) >> 10,
+		(unsigned long)__bss_start, (unsigned long)__bss_stop,
+		(unsigned long)(__bss_stop - __bss_start) >> 10);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/xtensa/mm/kasan_init.c b/arch/xtensa/mm/kasan_init.c
new file mode 100644
index 000000000000..6b532b6bd785
--- /dev/null
+++ b/arch/xtensa/mm/kasan_init.c
@@ -0,0 +1,95 @@
+/*
+ * Xtensa KASAN shadow map initialization
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2017 Cadence Design Systems Inc.
+ */
+
+#include <linux/bootmem.h>
+#include <linux/init_task.h>
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memblock.h>
+#include <asm/initialize_mmu.h>
+#include <asm/tlbflush.h>
+#include <asm/traps.h>
+
+void __init kasan_early_init(void)
+{
+	unsigned long vaddr = KASAN_SHADOW_START;
+	pgd_t *pgd = pgd_offset_k(vaddr);
+	pmd_t *pmd = pmd_offset(pgd, vaddr);
+	int i;
+
+	for (i = 0; i < PTRS_PER_PTE; ++i)
+		set_pte(kasan_zero_pte + i,
+			mk_pte(virt_to_page(kasan_zero_page), PAGE_KERNEL));
+
+	for (vaddr = 0; vaddr < KASAN_SHADOW_SIZE; vaddr += PMD_SIZE, ++pmd) {
+		BUG_ON(!pmd_none(*pmd));
+		set_pmd(pmd, __pmd((unsigned long)kasan_zero_pte));
+	}
+	early_trap_init();
+}
+
+static void __init populate(void *start, void *end)
+{
+	unsigned long n_pages = (end - start) / PAGE_SIZE;
+	unsigned long n_pmds = n_pages / PTRS_PER_PTE;
+	unsigned long i, j;
+	unsigned long vaddr = (unsigned long)start;
+	pgd_t *pgd = pgd_offset_k(vaddr);
+	pmd_t *pmd = pmd_offset(pgd, vaddr);
+	pte_t *pte = memblock_virt_alloc(n_pages * sizeof(pte_t), PAGE_SIZE);
+
+	pr_debug("%s: %p - %p\n", __func__, start, end);
+
+	for (i = j = 0; i < n_pmds; ++i) {
+		int k;
+
+		for (k = 0; k < PTRS_PER_PTE; ++k, ++j) {
+			phys_addr_t phys =
+				memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
+						    MEMBLOCK_ALLOC_ANYWHERE);
+
+			set_pte(pte + j, pfn_pte(PHYS_PFN(phys), PAGE_KERNEL));
+		}
+	}
+
+	for (i = 0; i < n_pmds ; ++i, pte += PTRS_PER_PTE)
+		set_pmd(pmd + i, __pmd((unsigned long)pte));
+
+	local_flush_tlb_all();
+	memset(start, 0, end - start);
+}
+
+void __init kasan_init(void)
+{
+	int i;
+
+	BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_START -
+		     (KASAN_START_VADDR >> KASAN_SHADOW_SCALE_SHIFT));
+	BUILD_BUG_ON(VMALLOC_START < KASAN_START_VADDR);
+
+	/*
+	 * Replace shadow map pages that cover addresses from VMALLOC area
+	 * start to the end of KSEG with clean writable pages.
+	 */
+	populate(kasan_mem_to_shadow((void *)VMALLOC_START),
+		 kasan_mem_to_shadow((void *)XCHAL_KSEG_BYPASS_VADDR));
+
+	/* Write protect kasan_zero_page and zero-initialize it again. */
+	for (i = 0; i < PTRS_PER_PTE; ++i)
+		set_pte(kasan_zero_pte + i,
+			mk_pte(virt_to_page(kasan_zero_page), PAGE_KERNEL_RO));
+
+	local_flush_tlb_all();
+	memset(kasan_zero_page, 0, PAGE_SIZE);
+
+	/* At this point kasan is fully initialized. Enable error messages. */
+	current->kasan_depth = 0;
+	pr_info("KernelAddressSanitizer initialized\n");
+}
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index 358d748d9083..9d1ecfc53670 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -56,7 +56,6 @@ static void __init fixedrange_init(void)
 
 void __init paging_init(void)
 {
-	memset(swapper_pg_dir, 0, PAGE_SIZE);
 #ifdef CONFIG_HIGHMEM
 	fixedrange_init();
 	pkmap_page_table = init_pmd(PKMAP_BASE, LAST_PKMAP);
@@ -82,6 +81,23 @@ void init_mmu(void)
 	set_itlbcfg_register(0);
 	set_dtlbcfg_register(0);
 #endif
+	init_kio();
+	local_flush_tlb_all();
+
+	/* Set rasid register to a known value. */
+
+	set_rasid_register(ASID_INSERT(ASID_USER_FIRST));
+
+	/* Set PTEVADDR special register to the start of the page
+	 * table, which is in kernel mappable space (ie. not
+	 * statically mapped).  This register's value is undefined on
+	 * reset.
+	 */
+	set_ptevaddr_register(XCHAL_PAGE_TABLE_VADDR);
+}
+
+void init_kio(void)
+{
 #if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 	/*
 	 * Update the IO area mapping in case xtensa_kio_paddr has changed
@@ -95,17 +111,4 @@ void init_mmu(void)
 	write_itlb_entry(__pte(xtensa_kio_paddr + CA_BYPASS),
 			XCHAL_KIO_BYPASS_VADDR + 6);
 #endif
-
-	local_flush_tlb_all();
-
-	/* Set rasid register to a known value. */
-
-	set_rasid_register(ASID_INSERT(ASID_USER_FIRST));
-
-	/* Set PTEVADDR special register to the start of the page
-	 * table, which is in kernel mappable space (ie. not
-	 * statically mapped).  This register's value is undefined on
-	 * reset.
-	 */
-	set_ptevaddr_register(PGTABLE_START);
 }
diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c
index 35c822286bbe..59153d0aa890 100644
--- a/arch/xtensa/mm/tlb.c
+++ b/arch/xtensa/mm/tlb.c
@@ -95,10 +95,8 @@ void local_flush_tlb_range(struct vm_area_struct *vma,
 	if (mm->context.asid[cpu] == NO_CONTEXT)
 		return;
 
-#if 0
-	printk("[tlbrange<%02lx,%08lx,%08lx>]\n",
-			(unsigned long)mm->context.asid[cpu], start, end);
-#endif
+	pr_debug("[tlbrange<%02lx,%08lx,%08lx>]\n",
+		 (unsigned long)mm->context.asid[cpu], start, end);
 	local_irq_save(flags);
 
 	if (end-start + (PAGE_SIZE-1) <= _TLB_ENTRIES << PAGE_SHIFT) {
diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c
index 464c2684c4f1..92f567f9a21e 100644
--- a/arch/xtensa/platforms/iss/console.c
+++ b/arch/xtensa/platforms/iss/console.c
@@ -185,7 +185,7 @@ int __init rs_init(void)
 
 	serial_driver = alloc_tty_driver(SERIAL_MAX_NUM_LINES);
 
-	printk ("%s %s\n", serial_name, serial_version);
+	pr_info("%s %s\n", serial_name, serial_version);
 
 	/* Initialize the tty_driver structure */
 
@@ -214,7 +214,7 @@ static __exit void rs_exit(void)
 	int error;
 
 	if ((error = tty_unregister_driver(serial_driver)))
-		printk("ISS_SERIAL: failed to unregister serial driver (%d)\n",
+		pr_err("ISS_SERIAL: failed to unregister serial driver (%d)\n",
 		       error);
 	put_tty_driver(serial_driver);
 	tty_port_destroy(&serial_port);
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index 6363b18e5b8c..d027dddc41ca 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -16,6 +16,8 @@
  *
  */
 
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
 #include <linux/list.h>
 #include <linux/irq.h>
 #include <linux/spinlock.h>
@@ -606,8 +608,6 @@ struct iss_net_init {
  * those fields. They will be later initialized in iss_net_init.
  */
 
-#define ERR KERN_ERR "iss_net_setup: "
-
 static int __init iss_net_setup(char *str)
 {
 	struct iss_net_private *device = NULL;
@@ -619,14 +619,14 @@ static int __init iss_net_setup(char *str)
 
 	end = strchr(str, '=');
 	if (!end) {
-		printk(ERR "Expected '=' after device number\n");
+		pr_err("Expected '=' after device number\n");
 		return 1;
 	}
 	*end = 0;
 	rc = kstrtouint(str, 0, &n);
 	*end = '=';
 	if (rc < 0) {
-		printk(ERR "Failed to parse '%s'\n", str);
+		pr_err("Failed to parse '%s'\n", str);
 		return 1;
 	}
 	str = end;
@@ -642,13 +642,13 @@ static int __init iss_net_setup(char *str)
 	spin_unlock(&devices_lock);
 
 	if (device && device->index == n) {
-		printk(ERR "Device %u already configured\n", n);
+		pr_err("Device %u already configured\n", n);
 		return 1;
 	}
 
 	new = alloc_bootmem(sizeof(*new));
 	if (new == NULL) {
-		printk(ERR "Alloc_bootmem failed\n");
+		pr_err("Alloc_bootmem failed\n");
 		return 1;
 	}
 
@@ -660,8 +660,6 @@ static int __init iss_net_setup(char *str)
 	return 1;
 }
 
-#undef ERR
-
 __setup("eth", iss_net_setup);
 
 /*
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index da1525ec4c87..d819dc77fe65 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -775,10 +775,11 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 	unsigned long flags;
 	int i;
 
+	spin_lock_irqsave(&bfqd->lock, flags);
+
 	if (!entity) /* root group */
-		return;
+		goto put_async_queues;
 
-	spin_lock_irqsave(&bfqd->lock, flags);
 	/*
 	 * Empty all service_trees belonging to this group before
 	 * deactivating the group itself.
@@ -809,6 +810,8 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 	}
 
 	__bfq_deactivate_entity(entity, false);
+
+put_async_queues:
 	bfq_put_async_queues(bfqd, bfqg);
 
 	spin_unlock_irqrestore(&bfqd->lock, flags);
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index bcb6d21baf12..47e6ec7427c4 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -166,6 +166,20 @@ static const int bfq_async_charge_factor = 10;
 /* Default timeout values, in jiffies, approximating CFQ defaults. */
 const int bfq_timeout = HZ / 8;
 
+/*
+ * Time limit for merging (see comments in bfq_setup_cooperator). Set
+ * to the slowest value that, in our tests, proved to be effective in
+ * removing false positives, while not causing true positives to miss
+ * queue merging.
+ *
+ * As can be deduced from the low time limit below, queue merging, if
+ * successful, happens at the very beggining of the I/O of the involved
+ * cooperating processes, as a consequence of the arrival of the very
+ * first requests from each cooperator.  After that, there is very
+ * little chance to find cooperators.
+ */
+static const unsigned long bfq_merge_time_limit = HZ/10;
+
 static struct kmem_cache *bfq_pool;
 
 /* Below this threshold (in ns), we consider thinktime immediate. */
@@ -178,7 +192,7 @@ static struct kmem_cache *bfq_pool;
 #define BFQQ_SEEK_THR		(sector_t)(8 * 100)
 #define BFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
 #define BFQQ_CLOSE_THR		(sector_t)(8 * 1024)
-#define BFQQ_SEEKY(bfqq)	(hweight32(bfqq->seek_history) > 32/8)
+#define BFQQ_SEEKY(bfqq)	(hweight32(bfqq->seek_history) > 19)
 
 /* Min number of samples required to perform peak-rate update */
 #define BFQ_RATE_MIN_SAMPLES	32
@@ -195,15 +209,17 @@ static struct kmem_cache *bfq_pool;
  * interactive applications automatically, using the following formula:
  * duration = (R / r) * T, where r is the peak rate of the device, and
  * R and T are two reference parameters.
- * In particular, R is the peak rate of the reference device (see below),
- * and T is a reference time: given the systems that are likely to be
- * installed on the reference device according to its speed class, T is
- * about the maximum time needed, under BFQ and while reading two files in
- * parallel, to load typical large applications on these systems.
- * In practice, the slower/faster the device at hand is, the more/less it
- * takes to load applications with respect to the reference device.
- * Accordingly, the longer/shorter BFQ grants weight raising to interactive
- * applications.
+ * In particular, R is the peak rate of the reference device (see
+ * below), and T is a reference time: given the systems that are
+ * likely to be installed on the reference device according to its
+ * speed class, T is about the maximum time needed, under BFQ and
+ * while reading two files in parallel, to load typical large
+ * applications on these systems (see the comments on
+ * max_service_from_wr below, for more details on how T is obtained).
+ * In practice, the slower/faster the device at hand is, the more/less
+ * it takes to load applications with respect to the reference device.
+ * Accordingly, the longer/shorter BFQ grants weight raising to
+ * interactive applications.
  *
  * BFQ uses four different reference pairs (R, T), depending on:
  * . whether the device is rotational or non-rotational;
@@ -240,6 +256,60 @@ static int T_slow[2];
 static int T_fast[2];
 static int device_speed_thresh[2];
 
+/*
+ * BFQ uses the above-detailed, time-based weight-raising mechanism to
+ * privilege interactive tasks. This mechanism is vulnerable to the
+ * following false positives: I/O-bound applications that will go on
+ * doing I/O for much longer than the duration of weight
+ * raising. These applications have basically no benefit from being
+ * weight-raised at the beginning of their I/O. On the opposite end,
+ * while being weight-raised, these applications
+ * a) unjustly steal throughput to applications that may actually need
+ * low latency;
+ * b) make BFQ uselessly perform device idling; device idling results
+ * in loss of device throughput with most flash-based storage, and may
+ * increase latencies when used purposelessly.
+ *
+ * BFQ tries to reduce these problems, by adopting the following
+ * countermeasure. To introduce this countermeasure, we need first to
+ * finish explaining how the duration of weight-raising for
+ * interactive tasks is computed.
+ *
+ * For a bfq_queue deemed as interactive, the duration of weight
+ * raising is dynamically adjusted, as a function of the estimated
+ * peak rate of the device, so as to be equal to the time needed to
+ * execute the 'largest' interactive task we benchmarked so far. By
+ * largest task, we mean the task for which each involved process has
+ * to do more I/O than for any of the other tasks we benchmarked. This
+ * reference interactive task is the start-up of LibreOffice Writer,
+ * and in this task each process/bfq_queue needs to have at most ~110K
+ * sectors transferred.
+ *
+ * This last piece of information enables BFQ to reduce the actual
+ * duration of weight-raising for at least one class of I/O-bound
+ * applications: those doing sequential or quasi-sequential I/O. An
+ * example is file copy. In fact, once started, the main I/O-bound
+ * processes of these applications usually consume the above 110K
+ * sectors in much less time than the processes of an application that
+ * is starting, because these I/O-bound processes will greedily devote
+ * almost all their CPU cycles only to their target,
+ * throughput-friendly I/O operations. This is even more true if BFQ
+ * happens to be underestimating the device peak rate, and thus
+ * overestimating the duration of weight raising. But, according to
+ * our measurements, once transferred 110K sectors, these processes
+ * have no right to be weight-raised any longer.
+ *
+ * Basing on the last consideration, BFQ ends weight-raising for a
+ * bfq_queue if the latter happens to have received an amount of
+ * service at least equal to the following constant. The constant is
+ * set to slightly more than 110K, to have a minimum safety margin.
+ *
+ * This early ending of weight-raising reduces the amount of time
+ * during which interactive false positives cause the two problems
+ * described at the beginning of these comments.
+ */
+static const unsigned long max_service_from_wr = 120000;
+
 #define RQ_BIC(rq)		icq_to_bic((rq)->elv.priv[0])
 #define RQ_BFQQ(rq)		((rq)->elv.priv[1])
 
@@ -403,6 +473,82 @@ static struct request *bfq_choose_req(struct bfq_data *bfqd,
 	}
 }
 
+/*
+ * See the comments on bfq_limit_depth for the purpose of
+ * the depths set in the function.
+ */
+static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
+{
+	bfqd->sb_shift = bt->sb.shift;
+
+	/*
+	 * In-word depths if no bfq_queue is being weight-raised:
+	 * leaving 25% of tags only for sync reads.
+	 *
+	 * In next formulas, right-shift the value
+	 * (1U<<bfqd->sb_shift), instead of computing directly
+	 * (1U<<(bfqd->sb_shift - something)), to be robust against
+	 * any possible value of bfqd->sb_shift, without having to
+	 * limit 'something'.
+	 */
+	/* no more than 50% of tags for async I/O */
+	bfqd->word_depths[0][0] = max((1U<<bfqd->sb_shift)>>1, 1U);
+	/*
+	 * no more than 75% of tags for sync writes (25% extra tags
+	 * w.r.t. async I/O, to prevent async I/O from starving sync
+	 * writes)
+	 */
+	bfqd->word_depths[0][1] = max(((1U<<bfqd->sb_shift) * 3)>>2, 1U);
+
+	/*
+	 * In-word depths in case some bfq_queue is being weight-
+	 * raised: leaving ~63% of tags for sync reads. This is the
+	 * highest percentage for which, in our tests, application
+	 * start-up times didn't suffer from any regression due to tag
+	 * shortage.
+	 */
+	/* no more than ~18% of tags for async I/O */
+	bfqd->word_depths[1][0] = max(((1U<<bfqd->sb_shift) * 3)>>4, 1U);
+	/* no more than ~37% of tags for sync writes (~20% extra tags) */
+	bfqd->word_depths[1][1] = max(((1U<<bfqd->sb_shift) * 6)>>4, 1U);
+}
+
+/*
+ * Async I/O can easily starve sync I/O (both sync reads and sync
+ * writes), by consuming all tags. Similarly, storms of sync writes,
+ * such as those that sync(2) may trigger, can starve sync reads.
+ * Limit depths of async I/O and sync writes so as to counter both
+ * problems.
+ */
+static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
+{
+	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+	struct bfq_data *bfqd = data->q->elevator->elevator_data;
+	struct sbitmap_queue *bt;
+
+	if (op_is_sync(op) && !op_is_write(op))
+		return;
+
+	if (data->flags & BLK_MQ_REQ_RESERVED) {
+		if (unlikely(!tags->nr_reserved_tags)) {
+			WARN_ON_ONCE(1);
+			return;
+		}
+		bt = &tags->breserved_tags;
+	} else
+		bt = &tags->bitmap_tags;
+
+	if (unlikely(bfqd->sb_shift != bt->sb.shift))
+		bfq_update_depths(bfqd, bt);
+
+	data->shallow_depth =
+		bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)];
+
+	bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u",
+			__func__, bfqd->wr_busy_queues, op_is_sync(op),
+			data->shallow_depth);
+}
+
 static struct bfq_queue *
 bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
 		     sector_t sector, struct rb_node **ret_parent,
@@ -444,6 +590,13 @@ bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
 	return bfqq;
 }
 
+static bool bfq_too_late_for_merging(struct bfq_queue *bfqq)
+{
+	return bfqq->service_from_backlogged > 0 &&
+		time_is_before_jiffies(bfqq->first_IO_time +
+				       bfq_merge_time_limit);
+}
+
 void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
 	struct rb_node **p, *parent;
@@ -454,6 +607,14 @@ void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 		bfqq->pos_root = NULL;
 	}
 
+	/*
+	 * bfqq cannot be merged any longer (see comments in
+	 * bfq_setup_cooperator): no point in adding bfqq into the
+	 * position tree.
+	 */
+	if (bfq_too_late_for_merging(bfqq))
+		return;
+
 	if (bfq_class_idle(bfqq))
 		return;
 	if (!bfqq->next_rq)
@@ -1247,6 +1408,7 @@ static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
 	if (old_wr_coeff == 1 && wr_or_deserves_wr) {
 		/* start a weight-raising period */
 		if (interactive) {
+			bfqq->service_from_wr = 0;
 			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
 			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
 		} else {
@@ -1627,6 +1789,8 @@ static void bfq_remove_request(struct request_queue *q,
 			rb_erase(&bfqq->pos_node, bfqq->pos_root);
 			bfqq->pos_root = NULL;
 		}
+	} else {
+		bfq_pos_tree_add_move(bfqd, bfqq);
 	}
 
 	if (rq->cmd_flags & REQ_META)
@@ -1933,6 +2097,9 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
 static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
 					struct bfq_queue *new_bfqq)
 {
+	if (bfq_too_late_for_merging(new_bfqq))
+		return false;
+
 	if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) ||
 	    (bfqq->ioprio_class != new_bfqq->ioprio_class))
 		return false;
@@ -1957,20 +2124,6 @@ static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
 }
 
 /*
- * If this function returns true, then bfqq cannot be merged. The idea
- * is that true cooperation happens very early after processes start
- * to do I/O. Usually, late cooperations are just accidental false
- * positives. In case bfqq is weight-raised, such false positives
- * would evidently degrade latency guarantees for bfqq.
- */
-static bool wr_from_too_long(struct bfq_queue *bfqq)
-{
-	return bfqq->wr_coeff > 1 &&
-		time_is_before_jiffies(bfqq->last_wr_start_finish +
-				       msecs_to_jiffies(100));
-}
-
-/*
  * Attempt to schedule a merge of bfqq with the currently in-service
  * queue or with a close queue among the scheduled queues.  Return
  * NULL if no merge was scheduled, a pointer to the shared bfq_queue
@@ -1983,11 +2136,6 @@ static bool wr_from_too_long(struct bfq_queue *bfqq)
  * to maintain. Besides, in such a critical condition as an out of memory,
  * the benefits of queue merging may be little relevant, or even negligible.
  *
- * Weight-raised queues can be merged only if their weight-raising
- * period has just started. In fact cooperating processes are usually
- * started together. Thus, with this filter we avoid false positives
- * that would jeopardize low-latency guarantees.
- *
  * WARNING: queue merging may impair fairness among non-weight raised
  * queues, for at least two reasons: 1) the original weight of a
  * merged queue may change during the merged state, 2) even being the
@@ -2001,12 +2149,24 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 {
 	struct bfq_queue *in_service_bfqq, *new_bfqq;
 
+	/*
+	 * Prevent bfqq from being merged if it has been created too
+	 * long ago. The idea is that true cooperating processes, and
+	 * thus their associated bfq_queues, are supposed to be
+	 * created shortly after each other. This is the case, e.g.,
+	 * for KVM/QEMU and dump I/O threads. Basing on this
+	 * assumption, the following filtering greatly reduces the
+	 * probability that two non-cooperating processes, which just
+	 * happen to do close I/O for some short time interval, have
+	 * their queues merged by mistake.
+	 */
+	if (bfq_too_late_for_merging(bfqq))
+		return NULL;
+
 	if (bfqq->new_bfqq)
 		return bfqq->new_bfqq;
 
-	if (!io_struct ||
-	    wr_from_too_long(bfqq) ||
-	    unlikely(bfqq == &bfqd->oom_bfqq))
+	if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq))
 		return NULL;
 
 	/* If there is only one backlogged queue, don't search. */
@@ -2015,12 +2175,9 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 
 	in_service_bfqq = bfqd->in_service_queue;
 
-	if (!in_service_bfqq || in_service_bfqq == bfqq
-	    || wr_from_too_long(in_service_bfqq) ||
-	    unlikely(in_service_bfqq == &bfqd->oom_bfqq))
-		goto check_scheduled;
-
-	if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
+	if (in_service_bfqq && in_service_bfqq != bfqq &&
+	    likely(in_service_bfqq != &bfqd->oom_bfqq) &&
+	    bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
 	    bfqq->entity.parent == in_service_bfqq->entity.parent &&
 	    bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) {
 		new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
@@ -2032,12 +2189,10 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	 * queues. The only thing we need is that the bio/request is not
 	 * NULL, as we need it to establish whether a cooperator exists.
 	 */
-check_scheduled:
 	new_bfqq = bfq_find_close_cooperator(bfqd, bfqq,
 			bfq_io_struct_pos(io_struct, request));
 
-	if (new_bfqq && !wr_from_too_long(new_bfqq) &&
-	    likely(new_bfqq != &bfqd->oom_bfqq) &&
+	if (new_bfqq && likely(new_bfqq != &bfqd->oom_bfqq) &&
 	    bfq_may_be_close_cooperator(bfqq, new_bfqq))
 		return bfq_setup_merge(bfqq, new_bfqq);
 
@@ -2062,7 +2217,8 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
 	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
 	if (unlikely(bfq_bfqq_just_created(bfqq) &&
-		     !bfq_bfqq_in_large_burst(bfqq))) {
+		     !bfq_bfqq_in_large_burst(bfqq) &&
+		     bfqq->bfqd->low_latency)) {
 		/*
 		 * bfqq being merged right after being created: bfqq
 		 * would have deserved interactive weight raising, but
@@ -2917,45 +3073,87 @@ static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
  * whereas soft_rt_next_start is set to infinity for applications that do
  * not.
  *
- * Unfortunately, even a greedy application may happen to behave in an
- * isochronous way if the CPU load is high. In fact, the application may
- * stop issuing requests while the CPUs are busy serving other processes,
- * then restart, then stop again for a while, and so on. In addition, if
- * the disk achieves a low enough throughput with the request pattern
- * issued by the application (e.g., because the request pattern is random
- * and/or the device is slow), then the application may meet the above
- * bandwidth requirement too. To prevent such a greedy application to be
- * deemed as soft real-time, a further rule is used in the computation of
- * soft_rt_next_start: soft_rt_next_start must be higher than the current
- * time plus the maximum time for which the arrival of a request is waited
- * for when a sync queue becomes idle, namely bfqd->bfq_slice_idle.
- * This filters out greedy applications, as the latter issue instead their
- * next request as soon as possible after the last one has been completed
- * (in contrast, when a batch of requests is completed, a soft real-time
- * application spends some time processing data).
+ * Unfortunately, even a greedy (i.e., I/O-bound) application may
+ * happen to meet, occasionally or systematically, both the above
+ * bandwidth and isochrony requirements. This may happen at least in
+ * the following circumstances. First, if the CPU load is high. The
+ * application may stop issuing requests while the CPUs are busy
+ * serving other processes, then restart, then stop again for a while,
+ * and so on. The other circumstances are related to the storage
+ * device: the storage device is highly loaded or reaches a low-enough
+ * throughput with the I/O of the application (e.g., because the I/O
+ * is random and/or the device is slow). In all these cases, the
+ * I/O of the application may be simply slowed down enough to meet
+ * the bandwidth and isochrony requirements. To reduce the probability
+ * that greedy applications are deemed as soft real-time in these
+ * corner cases, a further rule is used in the computation of
+ * soft_rt_next_start: the return value of this function is forced to
+ * be higher than the maximum between the following two quantities.
+ *
+ * (a) Current time plus: (1) the maximum time for which the arrival
+ *     of a request is waited for when a sync queue becomes idle,
+ *     namely bfqd->bfq_slice_idle, and (2) a few extra jiffies. We
+ *     postpone for a moment the reason for adding a few extra
+ *     jiffies; we get back to it after next item (b).  Lower-bounding
+ *     the return value of this function with the current time plus
+ *     bfqd->bfq_slice_idle tends to filter out greedy applications,
+ *     because the latter issue their next request as soon as possible
+ *     after the last one has been completed. In contrast, a soft
+ *     real-time application spends some time processing data, after a
+ *     batch of its requests has been completed.
  *
- * Unfortunately, the last filter may easily generate false positives if
- * only bfqd->bfq_slice_idle is used as a reference time interval and one
- * or both the following cases occur:
- * 1) HZ is so low that the duration of a jiffy is comparable to or higher
- *    than bfqd->bfq_slice_idle. This happens, e.g., on slow devices with
- *    HZ=100.
+ * (b) Current value of bfqq->soft_rt_next_start. As pointed out
+ *     above, greedy applications may happen to meet both the
+ *     bandwidth and isochrony requirements under heavy CPU or
+ *     storage-device load. In more detail, in these scenarios, these
+ *     applications happen, only for limited time periods, to do I/O
+ *     slowly enough to meet all the requirements described so far,
+ *     including the filtering in above item (a). These slow-speed
+ *     time intervals are usually interspersed between other time
+ *     intervals during which these applications do I/O at a very high
+ *     speed. Fortunately, exactly because of the high speed of the
+ *     I/O in the high-speed intervals, the values returned by this
+ *     function happen to be so high, near the end of any such
+ *     high-speed interval, to be likely to fall *after* the end of
+ *     the low-speed time interval that follows. These high values are
+ *     stored in bfqq->soft_rt_next_start after each invocation of
+ *     this function. As a consequence, if the last value of
+ *     bfqq->soft_rt_next_start is constantly used to lower-bound the
+ *     next value that this function may return, then, from the very
+ *     beginning of a low-speed interval, bfqq->soft_rt_next_start is
+ *     likely to be constantly kept so high that any I/O request
+ *     issued during the low-speed interval is considered as arriving
+ *     to soon for the application to be deemed as soft
+ *     real-time. Then, in the high-speed interval that follows, the
+ *     application will not be deemed as soft real-time, just because
+ *     it will do I/O at a high speed. And so on.
+ *
+ * Getting back to the filtering in item (a), in the following two
+ * cases this filtering might be easily passed by a greedy
+ * application, if the reference quantity was just
+ * bfqd->bfq_slice_idle:
+ * 1) HZ is so low that the duration of a jiffy is comparable to or
+ *    higher than bfqd->bfq_slice_idle. This happens, e.g., on slow
+ *    devices with HZ=100. The time granularity may be so coarse
+ *    that the approximation, in jiffies, of bfqd->bfq_slice_idle
+ *    is rather lower than the exact value.
  * 2) jiffies, instead of increasing at a constant rate, may stop increasing
  *    for a while, then suddenly 'jump' by several units to recover the lost
  *    increments. This seems to happen, e.g., inside virtual machines.
- * To address this issue, we do not use as a reference time interval just
- * bfqd->bfq_slice_idle, but bfqd->bfq_slice_idle plus a few jiffies. In
- * particular we add the minimum number of jiffies for which the filter
- * seems to be quite precise also in embedded systems and KVM/QEMU virtual
- * machines.
+ * To address this issue, in the filtering in (a) we do not use as a
+ * reference time interval just bfqd->bfq_slice_idle, but
+ * bfqd->bfq_slice_idle plus a few jiffies. In particular, we add the
+ * minimum number of jiffies for which the filter seems to be quite
+ * precise also in embedded systems and KVM/QEMU virtual machines.
  */
 static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
 						struct bfq_queue *bfqq)
 {
-	return max(bfqq->last_idle_bklogged +
-		   HZ * bfqq->service_from_backlogged /
-		   bfqd->bfq_wr_max_softrt_rate,
-		   jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
+	return max3(bfqq->soft_rt_next_start,
+		    bfqq->last_idle_bklogged +
+		    HZ * bfqq->service_from_backlogged /
+		    bfqd->bfq_wr_max_softrt_rate,
+		    jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
 }
 
 /**
@@ -3000,17 +3198,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta);
 
 	/*
-	 * Increase service_from_backlogged before next statement,
-	 * because the possible next invocation of
-	 * bfq_bfqq_charge_time would likely inflate
-	 * entity->service. In contrast, service_from_backlogged must
-	 * contain real service, to enable the soft real-time
-	 * heuristic to correctly compute the bandwidth consumed by
-	 * bfqq.
-	 */
-	bfqq->service_from_backlogged += entity->service;
-
-	/*
 	 * As above explained, charge slow (typically seeky) and
 	 * timed-out queues with the time and not the service
 	 * received, to favor sequential workloads.
@@ -3535,6 +3722,12 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 				bfqq->entity.prio_changed = 1;
 			}
 		}
+		if (bfqq->wr_coeff > 1 &&
+		    bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time &&
+		    bfqq->service_from_wr > max_service_from_wr) {
+			/* see comments on max_service_from_wr */
+			bfq_bfqq_end_wr(bfqq);
+		}
 	}
 	/*
 	 * To improve latency (for this or other queues), immediately
@@ -3630,8 +3823,8 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 		}
 
 		/*
-		 * We exploit the put_rq_private hook to decrement
-		 * rq_in_driver, but put_rq_private will not be
+		 * We exploit the bfq_finish_request hook to decrement
+		 * rq_in_driver, but bfq_finish_request will not be
 		 * invoked on this request. So, to avoid unbalance,
 		 * just start this request, without incrementing
 		 * rq_in_driver. As a negative consequence,
@@ -3640,14 +3833,14 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 		 * bfq_schedule_dispatch to be invoked uselessly.
 		 *
 		 * As for implementing an exact solution, the
-		 * put_request hook, if defined, is probably invoked
-		 * also on this request. So, by exploiting this hook,
-		 * we could 1) increment rq_in_driver here, and 2)
-		 * decrement it in put_request. Such a solution would
-		 * let the value of the counter be always accurate,
-		 * but it would entail using an extra interface
-		 * function. This cost seems higher than the benefit,
-		 * being the frequency of non-elevator-private
+		 * bfq_finish_request hook, if defined, is probably
+		 * invoked also on this request. So, by exploiting
+		 * this hook, we could 1) increment rq_in_driver here,
+		 * and 2) decrement it in bfq_finish_request. Such a
+		 * solution would let the value of the counter be
+		 * always accurate, but it would entail using an extra
+		 * interface function. This cost seems higher than the
+		 * benefit, being the frequency of non-elevator-private
 		 * requests very low.
 		 */
 		goto start_rq;
@@ -3689,35 +3882,16 @@ exit:
 	return rq;
 }
 
-static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
-{
-	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
-	struct request *rq;
 #if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
-	struct bfq_queue *in_serv_queue, *bfqq;
-	bool waiting_rq, idle_timer_disabled;
-#endif
-
-	spin_lock_irq(&bfqd->lock);
-
-#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
-	in_serv_queue = bfqd->in_service_queue;
-	waiting_rq = in_serv_queue && bfq_bfqq_wait_request(in_serv_queue);
-
-	rq = __bfq_dispatch_request(hctx);
-
-	idle_timer_disabled =
-		waiting_rq && !bfq_bfqq_wait_request(in_serv_queue);
-
-#else
-	rq = __bfq_dispatch_request(hctx);
-#endif
-	spin_unlock_irq(&bfqd->lock);
+static void bfq_update_dispatch_stats(struct request_queue *q,
+				      struct request *rq,
+				      struct bfq_queue *in_serv_queue,
+				      bool idle_timer_disabled)
+{
+	struct bfq_queue *bfqq = rq ? RQ_BFQQ(rq) : NULL;
 
-#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
-	bfqq = rq ? RQ_BFQQ(rq) : NULL;
 	if (!idle_timer_disabled && !bfqq)
-		return rq;
+		return;
 
 	/*
 	 * rq and bfqq are guaranteed to exist until this function
@@ -3732,7 +3906,7 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	 * In addition, the following queue lock guarantees that
 	 * bfqq_group(bfqq) exists as well.
 	 */
-	spin_lock_irq(hctx->queue->queue_lock);
+	spin_lock_irq(q->queue_lock);
 	if (idle_timer_disabled)
 		/*
 		 * Since the idle timer has been disabled,
@@ -3751,9 +3925,37 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 		bfqg_stats_set_start_empty_time(bfqg);
 		bfqg_stats_update_io_remove(bfqg, rq->cmd_flags);
 	}
-	spin_unlock_irq(hctx->queue->queue_lock);
+	spin_unlock_irq(q->queue_lock);
+}
+#else
+static inline void bfq_update_dispatch_stats(struct request_queue *q,
+					     struct request *rq,
+					     struct bfq_queue *in_serv_queue,
+					     bool idle_timer_disabled) {}
 #endif
 
+static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+	struct request *rq;
+	struct bfq_queue *in_serv_queue;
+	bool waiting_rq, idle_timer_disabled;
+
+	spin_lock_irq(&bfqd->lock);
+
+	in_serv_queue = bfqd->in_service_queue;
+	waiting_rq = in_serv_queue && bfq_bfqq_wait_request(in_serv_queue);
+
+	rq = __bfq_dispatch_request(hctx);
+
+	idle_timer_disabled =
+		waiting_rq && !bfq_bfqq_wait_request(in_serv_queue);
+
+	spin_unlock_irq(&bfqd->lock);
+
+	bfq_update_dispatch_stats(hctx->queue, rq, in_serv_queue,
+				  idle_timer_disabled);
+
 	return rq;
 }
 
@@ -4002,10 +4204,15 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	bfqq->split_time = bfq_smallest_from_now();
 
 	/*
-	 * Set to the value for which bfqq will not be deemed as
-	 * soft rt when it becomes backlogged.
+	 * To not forget the possibly high bandwidth consumed by a
+	 * process/queue in the recent past,
+	 * bfq_bfqq_softrt_next_start() returns a value at least equal
+	 * to the current value of bfqq->soft_rt_next_start (see
+	 * comments on bfq_bfqq_softrt_next_start).  Set
+	 * soft_rt_next_start to now, to mean that bfqq has consumed
+	 * no bandwidth so far.
 	 */
-	bfqq->soft_rt_next_start = bfq_greatest_from_now();
+	bfqq->soft_rt_next_start = jiffies;
 
 	/* first request is almost certainly seeky */
 	bfqq->seek_history = 1;
@@ -4276,16 +4483,46 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 	return idle_timer_disabled;
 }
 
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
+static void bfq_update_insert_stats(struct request_queue *q,
+				    struct bfq_queue *bfqq,
+				    bool idle_timer_disabled,
+				    unsigned int cmd_flags)
+{
+	if (!bfqq)
+		return;
+
+	/*
+	 * bfqq still exists, because it can disappear only after
+	 * either it is merged with another queue, or the process it
+	 * is associated with exits. But both actions must be taken by
+	 * the same process currently executing this flow of
+	 * instructions.
+	 *
+	 * In addition, the following queue lock guarantees that
+	 * bfqq_group(bfqq) exists as well.
+	 */
+	spin_lock_irq(q->queue_lock);
+	bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, cmd_flags);
+	if (idle_timer_disabled)
+		bfqg_stats_update_idle_time(bfqq_group(bfqq));
+	spin_unlock_irq(q->queue_lock);
+}
+#else
+static inline void bfq_update_insert_stats(struct request_queue *q,
+					   struct bfq_queue *bfqq,
+					   bool idle_timer_disabled,
+					   unsigned int cmd_flags) {}
+#endif
+
 static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 			       bool at_head)
 {
 	struct request_queue *q = hctx->queue;
 	struct bfq_data *bfqd = q->elevator->elevator_data;
-#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
 	struct bfq_queue *bfqq = RQ_BFQQ(rq);
 	bool idle_timer_disabled = false;
 	unsigned int cmd_flags;
-#endif
 
 	spin_lock_irq(&bfqd->lock);
 	if (blk_mq_sched_try_insert_merge(q, rq)) {
@@ -4304,7 +4541,6 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		else
 			list_add_tail(&rq->queuelist, &bfqd->dispatch);
 	} else {
-#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
 		idle_timer_disabled = __bfq_insert_request(bfqd, rq);
 		/*
 		 * Update bfqq, because, if a queue merge has occurred
@@ -4312,9 +4548,6 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		 * redirected into a new queue.
 		 */
 		bfqq = RQ_BFQQ(rq);
-#else
-		__bfq_insert_request(bfqd, rq);
-#endif
 
 		if (rq_mergeable(rq)) {
 			elv_rqhash_add(q, rq);
@@ -4323,35 +4556,17 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		}
 	}
 
-#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
 	/*
 	 * Cache cmd_flags before releasing scheduler lock, because rq
 	 * may disappear afterwards (for example, because of a request
 	 * merge).
 	 */
 	cmd_flags = rq->cmd_flags;
-#endif
+
 	spin_unlock_irq(&bfqd->lock);
 
-#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
-	if (!bfqq)
-		return;
-	/*
-	 * bfqq still exists, because it can disappear only after
-	 * either it is merged with another queue, or the process it
-	 * is associated with exits. But both actions must be taken by
-	 * the same process currently executing this flow of
-	 * instruction.
-	 *
-	 * In addition, the following queue lock guarantees that
-	 * bfqq_group(bfqq) exists as well.
-	 */
-	spin_lock_irq(q->queue_lock);
-	bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, cmd_flags);
-	if (idle_timer_disabled)
-		bfqg_stats_update_idle_time(bfqq_group(bfqq));
-	spin_unlock_irq(q->queue_lock);
-#endif
+	bfq_update_insert_stats(q, bfqq, idle_timer_disabled,
+				cmd_flags);
 }
 
 static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
@@ -4482,7 +4697,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 		bfq_schedule_dispatch(bfqd);
 }
 
-static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
+static void bfq_finish_request_body(struct bfq_queue *bfqq)
 {
 	bfqq->allocated--;
 
@@ -4512,7 +4727,7 @@ static void bfq_finish_request(struct request *rq)
 		spin_lock_irqsave(&bfqd->lock, flags);
 
 		bfq_completed_request(bfqq, bfqd);
-		bfq_put_rq_priv_body(bfqq);
+		bfq_finish_request_body(bfqq);
 
 		spin_unlock_irqrestore(&bfqd->lock, flags);
 	} else {
@@ -4533,7 +4748,7 @@ static void bfq_finish_request(struct request *rq)
 			bfqg_stats_update_io_remove(bfqq_group(bfqq),
 						    rq->cmd_flags);
 		}
-		bfq_put_rq_priv_body(bfqq);
+		bfq_finish_request_body(bfqq);
 	}
 
 	rq->elv.priv[0] = NULL;
@@ -4818,6 +5033,9 @@ static void bfq_exit_queue(struct elevator_queue *e)
 	hrtimer_cancel(&bfqd->idle_slice_timer);
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
+	/* release oom-queue reference to root group */
+	bfqg_and_blkg_put(bfqd->root_group);
+
 	blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq);
 #else
 	spin_lock_irq(&bfqd->lock);
@@ -5206,6 +5424,7 @@ static struct elv_fs_entry bfq_attrs[] = {
 
 static struct elevator_type iosched_bfq_mq = {
 	.ops.mq = {
+		.limit_depth		= bfq_limit_depth,
 		.prepare_request	= bfq_prepare_request,
 		.finish_request		= bfq_finish_request,
 		.exit_icq		= bfq_exit_icq,
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 91c4390903a1..350c39ae2896 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -337,6 +337,11 @@ struct bfq_queue {
 	 * last transition from idle to backlogged.
 	 */
 	unsigned long service_from_backlogged;
+	/*
+	 * Cumulative service received from the @bfq_queue since its
+	 * last transition to weight-raised state.
+	 */
+	unsigned long service_from_wr;
 
 	/*
 	 * Value of wr start time when switching to soft rt
@@ -344,6 +349,8 @@ struct bfq_queue {
 	unsigned long wr_start_at_switch_to_srt;
 
 	unsigned long split_time; /* time of last split */
+
+	unsigned long first_IO_time; /* time of first I/O for this queue */
 };
 
 /**
@@ -627,6 +634,18 @@ struct bfq_data {
 	struct bfq_io_cq *bio_bic;
 	/* bfqq associated with the task issuing current bio for merging */
 	struct bfq_queue *bio_bfqq;
+
+	/*
+	 * Cached sbitmap shift, used to compute depth limits in
+	 * bfq_update_depths.
+	 */
+	unsigned int sb_shift;
+
+	/*
+	 * Depth limits used in bfq_limit_depth (see comments on the
+	 * function)
+	 */
+	unsigned int word_depths[2][2];
 };
 
 enum bfqq_state_flags {
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index e495d3f9b4b0..4498c43245e2 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -835,6 +835,13 @@ void bfq_bfqq_served(struct bfq_queue *bfqq, int served)
 	struct bfq_entity *entity = &bfqq->entity;
 	struct bfq_service_tree *st;
 
+	if (!bfqq->service_from_backlogged)
+		bfqq->first_IO_time = jiffies;
+
+	if (bfqq->wr_coeff > 1)
+		bfqq->service_from_wr += served;
+
+	bfqq->service_from_backlogged += served;
 	for_each_entity(entity) {
 		st = bfq_entity_service_tree(entity);
 
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 23b42e8aa03e..9cfdd6c83b5b 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -374,7 +374,6 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 /**
  * __bio_integrity_endio - Integrity I/O completion function
  * @bio:	Protected bio
- * @error:	Pointer to errno
  *
  * Description: Completion for integrity I/O
  *
diff --git a/block/bio.c b/block/bio.c
index 228229f3bb76..e1708db48258 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -599,6 +599,8 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	bio->bi_disk = bio_src->bi_disk;
 	bio->bi_partno = bio_src->bi_partno;
 	bio_set_flag(bio, BIO_CLONED);
+	if (bio_flagged(bio_src, BIO_THROTTLED))
+		bio_set_flag(bio, BIO_THROTTLED);
 	bio->bi_opf = bio_src->bi_opf;
 	bio->bi_write_hint = bio_src->bi_write_hint;
 	bio->bi_iter = bio_src->bi_iter;
@@ -969,34 +971,6 @@ void bio_advance(struct bio *bio, unsigned bytes)
 EXPORT_SYMBOL(bio_advance);
 
 /**
- * bio_alloc_pages - allocates a single page for each bvec in a bio
- * @bio: bio to allocate pages for
- * @gfp_mask: flags for allocation
- *
- * Allocates pages up to @bio->bi_vcnt.
- *
- * Returns 0 on success, -ENOMEM on failure. On failure, any allocated pages are
- * freed.
- */
-int bio_alloc_pages(struct bio *bio, gfp_t gfp_mask)
-{
-	int i;
-	struct bio_vec *bv;
-
-	bio_for_each_segment_all(bv, bio, i) {
-		bv->bv_page = alloc_page(gfp_mask);
-		if (!bv->bv_page) {
-			while (--bv >= bio->bi_io_vec)
-				__free_page(bv->bv_page);
-			return -ENOMEM;
-		}
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(bio_alloc_pages);
-
-/**
  * bio_copy_data - copy contents of data buffers from one chain of bios to
  * another
  * @src: source bio list
@@ -1819,7 +1793,7 @@ EXPORT_SYMBOL(bio_endio);
 struct bio *bio_split(struct bio *bio, int sectors,
 		      gfp_t gfp, struct bio_set *bs)
 {
-	struct bio *split = NULL;
+	struct bio *split;
 
 	BUG_ON(sectors <= 0);
 	BUG_ON(sectors >= bio_sectors(bio));
@@ -1836,7 +1810,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	bio_advance(bio, split->bi_iter.bi_size);
 
 	if (bio_flagged(bio, BIO_TRACE_COMPLETION))
-		bio_set_flag(bio, BIO_TRACE_COMPLETION);
+		bio_set_flag(split, BIO_TRACE_COMPLETION);
 
 	return split;
 }
diff --git a/block/blk-core.c b/block/blk-core.c
index b8881750a3ac..a2005a485335 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -126,6 +126,8 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->start_time = jiffies;
 	set_start_time_ns(rq);
 	rq->part = NULL;
+	seqcount_init(&rq->gstate_seq);
+	u64_stats_init(&rq->aborted_gstate_sync);
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -562,6 +564,13 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all)
 	}
 }
 
+void blk_drain_queue(struct request_queue *q)
+{
+	spin_lock_irq(q->queue_lock);
+	__blk_drain_queue(q, true);
+	spin_unlock_irq(q->queue_lock);
+}
+
 /**
  * blk_queue_bypass_start - enter queue bypass mode
  * @q: queue of interest
@@ -689,11 +698,18 @@ void blk_cleanup_queue(struct request_queue *q)
 	 */
 	blk_freeze_queue(q);
 	spin_lock_irq(lock);
-	if (!q->mq_ops)
-		__blk_drain_queue(q, true);
 	queue_flag_set(QUEUE_FLAG_DEAD, q);
 	spin_unlock_irq(lock);
 
+	/*
+	 * make sure all in-progress dispatch are completed because
+	 * blk_freeze_queue() can only complete all requests, and
+	 * dispatch may still be in-progress since we dispatch requests
+	 * from more than one contexts
+	 */
+	if (q->mq_ops)
+		blk_mq_quiesce_queue(q);
+
 	/* for synchronous bio-based driver finish in-flight integrity i/o */
 	blk_flush_integrity();
 
@@ -1641,6 +1657,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 
 	lockdep_assert_held(q->queue_lock);
 
+	blk_req_zone_write_unlock(req);
 	blk_pm_put_request(req);
 
 	elv_completed_request(q, req);
@@ -2050,6 +2067,21 @@ static inline bool should_fail_request(struct hd_struct *part,
 
 #endif /* CONFIG_FAIL_MAKE_REQUEST */
 
+static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
+{
+	if (part->policy && op_is_write(bio_op(bio))) {
+		char b[BDEVNAME_SIZE];
+
+		printk(KERN_ERR
+		       "generic_make_request: Trying to write "
+			"to read-only block-device %s (partno %d)\n",
+			bio_devname(bio, b), part->partno);
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Remap block n of partition p to block n+start(p) of the disk.
  */
@@ -2058,27 +2090,28 @@ static inline int blk_partition_remap(struct bio *bio)
 	struct hd_struct *p;
 	int ret = 0;
 
+	rcu_read_lock();
+	p = __disk_get_part(bio->bi_disk, bio->bi_partno);
+	if (unlikely(!p || should_fail_request(p, bio->bi_iter.bi_size) ||
+		     bio_check_ro(bio, p))) {
+		ret = -EIO;
+		goto out;
+	}
+
 	/*
 	 * Zone reset does not include bi_size so bio_sectors() is always 0.
 	 * Include a test for the reset op code and perform the remap if needed.
 	 */
-	if (!bio->bi_partno ||
-	    (!bio_sectors(bio) && bio_op(bio) != REQ_OP_ZONE_RESET))
-		return 0;
+	if (!bio_sectors(bio) && bio_op(bio) != REQ_OP_ZONE_RESET)
+		goto out;
 
-	rcu_read_lock();
-	p = __disk_get_part(bio->bi_disk, bio->bi_partno);
-	if (likely(p && !should_fail_request(p, bio->bi_iter.bi_size))) {
-		bio->bi_iter.bi_sector += p->start_sect;
-		bio->bi_partno = 0;
-		trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
-				bio->bi_iter.bi_sector - p->start_sect);
-	} else {
-		printk("%s: fail for partition %d\n", __func__, bio->bi_partno);
-		ret = -EIO;
-	}
-	rcu_read_unlock();
+	bio->bi_iter.bi_sector += p->start_sect;
+	bio->bi_partno = 0;
+	trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
+			      bio->bi_iter.bi_sector - p->start_sect);
 
+out:
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -2137,15 +2170,19 @@ generic_make_request_checks(struct bio *bio)
 	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
 	 * if queue is not a request based queue.
 	 */
-
 	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q))
 		goto not_supported;
 
 	if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size))
 		goto end_io;
 
-	if (blk_partition_remap(bio))
-		goto end_io;
+	if (!bio->bi_partno) {
+		if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0)))
+			goto end_io;
+	} else {
+		if (blk_partition_remap(bio))
+			goto end_io;
+	}
 
 	if (bio_check_eod(bio, nr_sectors))
 		goto end_io;
@@ -2488,8 +2525,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 		 * bypass a potential scheduler on the bottom device for
 		 * insert.
 		 */
-		blk_mq_request_bypass_insert(rq, true);
-		return BLK_STS_OK;
+		return blk_mq_request_issue_directly(rq);
 	}
 
 	spin_lock_irqsave(q->queue_lock, flags);
@@ -2841,7 +2877,7 @@ void blk_start_request(struct request *req)
 		wbt_issue(req->q->rq_wb, &req->issue_stat);
 	}
 
-	BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
+	BUG_ON(blk_rq_is_complete(req));
 	blk_add_timer(req);
 }
 EXPORT_SYMBOL(blk_start_request);
@@ -3410,20 +3446,6 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork,
 }
 EXPORT_SYMBOL(kblockd_mod_delayed_work_on);
 
-int kblockd_schedule_delayed_work(struct delayed_work *dwork,
-				  unsigned long delay)
-{
-	return queue_delayed_work(kblockd_workqueue, dwork, delay);
-}
-EXPORT_SYMBOL(kblockd_schedule_delayed_work);
-
-int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
-				     unsigned long delay)
-{
-	return queue_delayed_work_on(cpu, kblockd_workqueue, dwork, delay);
-}
-EXPORT_SYMBOL(kblockd_schedule_delayed_work_on);
-
 /**
  * blk_start_plug - initialize blk_plug and track it inside the task_struct
  * @plug:	The &struct blk_plug that needs to be initialized
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 5c0f3dc446dc..f7b292f12449 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -61,7 +61,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * be reused after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_sched_insert_request(rq, at_head, true, false, false);
+		blk_mq_sched_insert_request(rq, at_head, true, false);
 		return;
 	}
 
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 2bc544ce3d2e..a676084d4740 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -37,6 +37,9 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	if (!q)
 		return -ENXIO;
 
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
 	if (flags & BLKDEV_DISCARD_SECURE) {
 		if (!blk_queue_secure_erase(q))
 			return -EOPNOTSUPP;
@@ -156,6 +159,9 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	if (!q)
 		return -ENXIO;
 
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
 	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
 	if ((sector | nr_sects) & bs_mask)
 		return -EINVAL;
@@ -233,6 +239,9 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 	if (!q)
 		return -ENXIO;
 
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
 	/* Ensure that max_write_zeroes_sectors doesn't overflow bi_size */
 	max_write_zeroes_sectors = bdev_write_zeroes_sectors(bdev);
 
@@ -287,6 +296,9 @@ static int __blkdev_issue_zero_pages(struct block_device *bdev,
 	if (!q)
 		return -ENXIO;
 
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
 	while (nr_sects != 0) {
 		bio = next_bio(bio, __blkdev_sectors_to_bio_pages(nr_sects),
 			       gfp_mask);
diff --git a/block/blk-map.c b/block/blk-map.c
index b21f8e86f120..db9373bd31ac 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -12,22 +12,29 @@
 #include "blk.h"
 
 /*
- * Append a bio to a passthrough request.  Only works can be merged into
- * the request based on the driver constraints.
+ * Append a bio to a passthrough request.  Only works if the bio can be merged
+ * into the request based on the driver constraints.
  */
-int blk_rq_append_bio(struct request *rq, struct bio *bio)
+int blk_rq_append_bio(struct request *rq, struct bio **bio)
 {
-	blk_queue_bounce(rq->q, &bio);
+	struct bio *orig_bio = *bio;
+
+	blk_queue_bounce(rq->q, bio);
 
 	if (!rq->bio) {
-		blk_rq_bio_prep(rq->q, rq, bio);
+		blk_rq_bio_prep(rq->q, rq, *bio);
 	} else {
-		if (!ll_back_merge_fn(rq->q, rq, bio))
+		if (!ll_back_merge_fn(rq->q, rq, *bio)) {
+			if (orig_bio != *bio) {
+				bio_put(*bio);
+				*bio = orig_bio;
+			}
 			return -EINVAL;
+		}
 
-		rq->biotail->bi_next = bio;
-		rq->biotail = bio;
-		rq->__data_len += bio->bi_iter.bi_size;
+		rq->biotail->bi_next = *bio;
+		rq->biotail = *bio;
+		rq->__data_len += (*bio)->bi_iter.bi_size;
 	}
 
 	return 0;
@@ -73,14 +80,12 @@ static int __blk_rq_map_user_iov(struct request *rq,
 	 * We link the bounce buffer in and could have to traverse it
 	 * later so we have to get a ref to prevent it from being freed
 	 */
-	ret = blk_rq_append_bio(rq, bio);
-	bio_get(bio);
+	ret = blk_rq_append_bio(rq, &bio);
 	if (ret) {
-		bio_endio(bio);
 		__blk_rq_unmap_user(orig_bio);
-		bio_put(bio);
 		return ret;
 	}
+	bio_get(bio);
 
 	return 0;
 }
@@ -114,7 +119,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	unsigned long align = q->dma_pad_mask | queue_dma_alignment(q);
 	struct bio *bio = NULL;
 	struct iov_iter i;
-	int ret;
+	int ret = -EINVAL;
 
 	if (!iter_is_iovec(iter))
 		goto fail;
@@ -143,7 +148,7 @@ unmap_rq:
 	__blk_rq_unmap_user(bio);
 fail:
 	rq->bio = NULL;
-	return -EINVAL;
+	return ret;
 }
 EXPORT_SYMBOL(blk_rq_map_user_iov);
 
@@ -213,7 +218,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	int reading = rq_data_dir(rq) == READ;
 	unsigned long addr = (unsigned long) kbuf;
 	int do_copy = 0;
-	struct bio *bio;
+	struct bio *bio, *orig_bio;
 	int ret;
 
 	if (len > (queue_max_hw_sectors(q) << 9))
@@ -236,10 +241,11 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (do_copy)
 		rq->rq_flags |= RQF_COPY_USER;
 
-	ret = blk_rq_append_bio(rq, bio);
+	orig_bio = bio;
+	ret = blk_rq_append_bio(rq, &bio);
 	if (unlikely(ret)) {
 		/* request is too big */
-		bio_put(bio);
+		bio_put(orig_bio);
 		return ret;
 	}
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index f5dedd57dff6..8452fc7164cc 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -128,9 +128,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 				nsegs++;
 				sectors = max_sectors;
 			}
-			if (sectors)
-				goto split;
-			/* Make this single bvec as the 1st segment */
+			goto split;
 		}
 
 		if (bvprvp && blk_queue_cluster(q)) {
@@ -146,22 +144,21 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			bvprvp = &bvprv;
 			sectors += bv.bv_len >> 9;
 
-			if (nsegs == 1 && seg_size > front_seg_size)
-				front_seg_size = seg_size;
 			continue;
 		}
 new_segment:
 		if (nsegs == queue_max_segments(q))
 			goto split;
 
+		if (nsegs == 1 && seg_size > front_seg_size)
+			front_seg_size = seg_size;
+
 		nsegs++;
 		bvprv = bv;
 		bvprvp = &bvprv;
 		seg_size = bv.bv_len;
 		sectors += bv.bv_len >> 9;
 
-		if (nsegs == 1 && seg_size > front_seg_size)
-			front_seg_size = seg_size;
 	}
 
 	do_split = false;
@@ -174,6 +171,8 @@ split:
 			bio = new;
 	}
 
+	if (nsegs == 1 && seg_size > front_seg_size)
+		front_seg_size = seg_size;
 	bio->bi_seg_front_size = front_seg_size;
 	if (seg_size > bio->bi_seg_back_size)
 		bio->bi_seg_back_size = seg_size;
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index b56a4f35720d..21cbc1f071c6 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -289,17 +289,12 @@ static const char *const rqf_name[] = {
 	RQF_NAME(HASHED),
 	RQF_NAME(STATS),
 	RQF_NAME(SPECIAL_PAYLOAD),
+	RQF_NAME(ZONE_WRITE_LOCKED),
+	RQF_NAME(MQ_TIMEOUT_EXPIRED),
+	RQF_NAME(MQ_POLL_SLEPT),
 };
 #undef RQF_NAME
 
-#define RQAF_NAME(name) [REQ_ATOM_##name] = #name
-static const char *const rqaf_name[] = {
-	RQAF_NAME(COMPLETE),
-	RQAF_NAME(STARTED),
-	RQAF_NAME(POLL_SLEPT),
-};
-#undef RQAF_NAME
-
 int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 {
 	const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
@@ -316,8 +311,7 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 	seq_puts(m, ", .rq_flags=");
 	blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
 		       ARRAY_SIZE(rqf_name));
-	seq_puts(m, ", .atomic_flags=");
-	blk_flags_show(m, rq->atomic_flags, rqaf_name, ARRAY_SIZE(rqaf_name));
+	seq_printf(m, ", complete=%d", blk_rq_is_complete(rq));
 	seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag,
 		   rq->internal_tag);
 	if (mq_ops->show_rq)
@@ -409,7 +403,7 @@ static void hctx_show_busy_rq(struct request *rq, void *data, bool reserved)
 	const struct show_busy_params *params = data;
 
 	if (blk_mq_map_queue(rq->q, rq->mq_ctx->cpu) == params->hctx &&
-	    test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+	    blk_mq_rq_state(rq) != MQ_RQ_IDLE)
 		__blk_mq_debugfs_rq_show(params->m,
 					 list_entry_rq(&rq->queuelist));
 }
@@ -703,7 +697,11 @@ static ssize_t blk_mq_debugfs_write(struct file *file, const char __user *buf,
 	const struct blk_mq_debugfs_attr *attr = m->private;
 	void *data = d_inode(file->f_path.dentry->d_parent)->i_private;
 
-	if (!attr->write)
+	/*
+	 * Attributes that only implement .seq_ops are read-only and 'attr' is
+	 * the same with 'data' in this case.
+	 */
+	if (attr == data || !attr->write)
 		return -EPERM;
 
 	return attr->write(data, buf, count, ppos);
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index c117bd8fd1f6..55c0a745b427 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -172,7 +172,6 @@ static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
 	WRITE_ONCE(hctx->dispatch_from, ctx);
 }
 
-/* return true if hw queue need to be run again */
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 {
 	struct request_queue *q = hctx->queue;
@@ -428,7 +427,7 @@ done:
 }
 
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
-				 bool run_queue, bool async, bool can_block)
+				 bool run_queue, bool async)
 {
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index ba1d1418a96d..1e9c9018ace1 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -18,7 +18,7 @@ bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
 void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
 
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
-				 bool run_queue, bool async, bool can_block);
+				 bool run_queue, bool async);
 void blk_mq_sched_insert_requests(struct request_queue *q,
 				  struct blk_mq_ctx *ctx,
 				  struct list_head *list, bool run_queue_async);
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 79969c3c234f..a54b4b070f1c 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -248,7 +248,7 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
 	return ret;
 }
 
-static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
+void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int i;
@@ -265,13 +265,6 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 	q->mq_sysfs_init_done = false;
 }
 
-void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
-{
-	mutex_lock(&q->sysfs_lock);
-	__blk_mq_unregister_dev(dev, q);
-	mutex_unlock(&q->sysfs_lock);
-}
-
 void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
 {
 	kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index c81b40ecd3f1..336dde07b230 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -134,12 +134,6 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 	ws = bt_wait_ptr(bt, data->hctx);
 	drop_ctx = data->ctx == NULL;
 	do {
-		prepare_to_wait(&ws->wait, &wait, TASK_UNINTERRUPTIBLE);
-
-		tag = __blk_mq_get_tag(data, bt);
-		if (tag != -1)
-			break;
-
 		/*
 		 * We're out of tags on this hardware queue, kick any
 		 * pending IO submits before going to sleep waiting for
@@ -155,6 +149,13 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 		if (tag != -1)
 			break;
 
+		prepare_to_wait_exclusive(&ws->wait, &wait,
+						TASK_UNINTERRUPTIBLE);
+
+		tag = __blk_mq_get_tag(data, bt);
+		if (tag != -1)
+			break;
+
 		if (data->ctx)
 			blk_mq_put_ctx(data->ctx);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 11097477eeab..01f271d40825 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -95,8 +95,7 @@ static void blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
 {
 	struct mq_inflight *mi = priv;
 
-	if (test_bit(REQ_ATOM_STARTED, &rq->atomic_flags) &&
-	    !test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags)) {
+	if (blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) {
 		/*
 		 * index[0] counts the specific partition that was asked
 		 * for. index[1] counts the ones that are active on the
@@ -161,6 +160,8 @@ void blk_freeze_queue(struct request_queue *q)
 	 * exported to drivers as the only user for unfreeze is blk_mq.
 	 */
 	blk_freeze_queue_start(q);
+	if (!q->mq_ops)
+		blk_drain_queue(q);
 	blk_mq_freeze_queue_wait(q);
 }
 
@@ -220,7 +221,7 @@ void blk_mq_quiesce_queue(struct request_queue *q)
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (hctx->flags & BLK_MQ_F_BLOCKING)
-			synchronize_srcu(hctx->queue_rq_srcu);
+			synchronize_srcu(hctx->srcu);
 		else
 			rcu = true;
 	}
@@ -270,15 +271,14 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 {
 	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
 	struct request *rq = tags->static_rqs[tag];
-
-	rq->rq_flags = 0;
+	req_flags_t rq_flags = 0;
 
 	if (data->flags & BLK_MQ_REQ_INTERNAL) {
 		rq->tag = -1;
 		rq->internal_tag = tag;
 	} else {
 		if (blk_mq_tag_busy(data->hctx)) {
-			rq->rq_flags = RQF_MQ_INFLIGHT;
+			rq_flags = RQF_MQ_INFLIGHT;
 			atomic_inc(&data->hctx->nr_active);
 		}
 		rq->tag = tag;
@@ -286,27 +286,22 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 		data->hctx->tags->rqs[rq->tag] = rq;
 	}
 
-	INIT_LIST_HEAD(&rq->queuelist);
 	/* csd/requeue_work/fifo_time is initialized before use */
 	rq->q = data->q;
 	rq->mq_ctx = data->ctx;
+	rq->rq_flags = rq_flags;
+	rq->cpu = -1;
 	rq->cmd_flags = op;
 	if (data->flags & BLK_MQ_REQ_PREEMPT)
 		rq->rq_flags |= RQF_PREEMPT;
 	if (blk_queue_io_stat(data->q))
 		rq->rq_flags |= RQF_IO_STAT;
-	/* do not touch atomic flags, it needs atomic ops against the timer */
-	rq->cpu = -1;
+	INIT_LIST_HEAD(&rq->queuelist);
 	INIT_HLIST_NODE(&rq->hash);
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->rq_disk = NULL;
 	rq->part = NULL;
 	rq->start_time = jiffies;
-#ifdef CONFIG_BLK_CGROUP
-	rq->rl = NULL;
-	set_start_time_ns(rq);
-	rq->io_start_time_ns = 0;
-#endif
 	rq->nr_phys_segments = 0;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	rq->nr_integrity_segments = 0;
@@ -314,6 +309,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	rq->special = NULL;
 	/* tag was already set */
 	rq->extra_len = 0;
+	rq->__deadline = 0;
 
 	INIT_LIST_HEAD(&rq->timeout_list);
 	rq->timeout = 0;
@@ -322,6 +318,12 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	rq->end_io_data = NULL;
 	rq->next_rq = NULL;
 
+#ifdef CONFIG_BLK_CGROUP
+	rq->rl = NULL;
+	set_start_time_ns(rq);
+	rq->io_start_time_ns = 0;
+#endif
+
 	data->ctx->rq_dispatched[op_is_sync(op)]++;
 	return rq;
 }
@@ -441,7 +443,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 		blk_queue_exit(q);
 		return ERR_PTR(-EXDEV);
 	}
-	cpu = cpumask_first(alloc_data.hctx->cpumask);
+	cpu = cpumask_first_and(alloc_data.hctx->cpumask, cpu_online_mask);
 	alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
 
 	rq = blk_mq_get_request(q, NULL, op, &alloc_data);
@@ -483,8 +485,7 @@ void blk_mq_free_request(struct request *rq)
 	if (blk_rq_rl(rq))
 		blk_put_rl(blk_rq_rl(rq));
 
-	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
-	clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
+	blk_mq_rq_update_state(rq, MQ_RQ_IDLE);
 	if (rq->tag != -1)
 		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
 	if (sched_tag != -1)
@@ -530,6 +531,9 @@ static void __blk_mq_complete_request(struct request *rq)
 	bool shared = false;
 	int cpu;
 
+	WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT);
+	blk_mq_rq_update_state(rq, MQ_RQ_COMPLETE);
+
 	if (rq->internal_tag != -1)
 		blk_mq_sched_completed_request(rq);
 	if (rq->rq_flags & RQF_STATS) {
@@ -557,6 +561,56 @@ static void __blk_mq_complete_request(struct request *rq)
 	put_cpu();
 }
 
+static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
+	__releases(hctx->srcu)
+{
+	if (!(hctx->flags & BLK_MQ_F_BLOCKING))
+		rcu_read_unlock();
+	else
+		srcu_read_unlock(hctx->srcu, srcu_idx);
+}
+
+static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx)
+	__acquires(hctx->srcu)
+{
+	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
+		/* shut up gcc false positive */
+		*srcu_idx = 0;
+		rcu_read_lock();
+	} else
+		*srcu_idx = srcu_read_lock(hctx->srcu);
+}
+
+static void blk_mq_rq_update_aborted_gstate(struct request *rq, u64 gstate)
+{
+	unsigned long flags;
+
+	/*
+	 * blk_mq_rq_aborted_gstate() is used from the completion path and
+	 * can thus be called from irq context.  u64_stats_fetch in the
+	 * middle of update on the same CPU leads to lockup.  Disable irq
+	 * while updating.
+	 */
+	local_irq_save(flags);
+	u64_stats_update_begin(&rq->aborted_gstate_sync);
+	rq->aborted_gstate = gstate;
+	u64_stats_update_end(&rq->aborted_gstate_sync);
+	local_irq_restore(flags);
+}
+
+static u64 blk_mq_rq_aborted_gstate(struct request *rq)
+{
+	unsigned int start;
+	u64 aborted_gstate;
+
+	do {
+		start = u64_stats_fetch_begin(&rq->aborted_gstate_sync);
+		aborted_gstate = rq->aborted_gstate;
+	} while (u64_stats_fetch_retry(&rq->aborted_gstate_sync, start));
+
+	return aborted_gstate;
+}
+
 /**
  * blk_mq_complete_request - end I/O on a request
  * @rq:		the request being processed
@@ -568,17 +622,33 @@ static void __blk_mq_complete_request(struct request *rq)
 void blk_mq_complete_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
+	int srcu_idx;
 
 	if (unlikely(blk_should_fake_timeout(q)))
 		return;
-	if (!blk_mark_rq_complete(rq))
+
+	/*
+	 * If @rq->aborted_gstate equals the current instance, timeout is
+	 * claiming @rq and we lost.  This is synchronized through
+	 * hctx_lock().  See blk_mq_timeout_work() for details.
+	 *
+	 * Completion path never blocks and we can directly use RCU here
+	 * instead of hctx_lock() which can be either RCU or SRCU.
+	 * However, that would complicate paths which want to synchronize
+	 * against us.  Let stay in sync with the issue path so that
+	 * hctx_lock() covers both issue and completion paths.
+	 */
+	hctx_lock(hctx, &srcu_idx);
+	if (blk_mq_rq_aborted_gstate(rq) != rq->gstate)
 		__blk_mq_complete_request(rq);
+	hctx_unlock(hctx, srcu_idx);
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
 int blk_mq_request_started(struct request *rq)
 {
-	return test_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
 }
 EXPORT_SYMBOL_GPL(blk_mq_request_started);
 
@@ -596,34 +666,27 @@ void blk_mq_start_request(struct request *rq)
 		wbt_issue(q->rq_wb, &rq->issue_stat);
 	}
 
-	blk_add_timer(rq);
-
-	WARN_ON_ONCE(test_bit(REQ_ATOM_STARTED, &rq->atomic_flags));
+	WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);
 
 	/*
-	 * Mark us as started and clear complete. Complete might have been
-	 * set if requeue raced with timeout, which then marked it as
-	 * complete. So be sure to clear complete again when we start
-	 * the request, otherwise we'll ignore the completion event.
+	 * Mark @rq in-flight which also advances the generation number,
+	 * and register for timeout.  Protect with a seqcount to allow the
+	 * timeout path to read both @rq->gstate and @rq->deadline
+	 * coherently.
 	 *
-	 * Ensure that ->deadline is visible before we set STARTED, such that
-	 * blk_mq_check_expired() is guaranteed to observe our ->deadline when
-	 * it observes STARTED.
+	 * This is the only place where a request is marked in-flight.  If
+	 * the timeout path reads an in-flight @rq->gstate, the
+	 * @rq->deadline it reads together under @rq->gstate_seq is
+	 * guaranteed to be the matching one.
 	 */
-	smp_wmb();
-	set_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
-	if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags)) {
-		/*
-		 * Coherence order guarantees these consecutive stores to a
-		 * single variable propagate in the specified order. Thus the
-		 * clear_bit() is ordered _after_ the set bit. See
-		 * blk_mq_check_expired().
-		 *
-		 * (the bits must be part of the same byte for this to be
-		 * true).
-		 */
-		clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
-	}
+	preempt_disable();
+	write_seqcount_begin(&rq->gstate_seq);
+
+	blk_mq_rq_update_state(rq, MQ_RQ_IN_FLIGHT);
+	blk_add_timer(rq);
+
+	write_seqcount_end(&rq->gstate_seq);
+	preempt_enable();
 
 	if (q->dma_drain_size && blk_rq_bytes(rq)) {
 		/*
@@ -637,13 +700,9 @@ void blk_mq_start_request(struct request *rq)
 EXPORT_SYMBOL(blk_mq_start_request);
 
 /*
- * When we reach here because queue is busy, REQ_ATOM_COMPLETE
- * flag isn't set yet, so there may be race with timeout handler,
- * but given rq->deadline is just set in .queue_rq() under
- * this situation, the race won't be possible in reality because
- * rq->timeout should be set as big enough to cover the window
- * between blk_mq_start_request() called from .queue_rq() and
- * clearing REQ_ATOM_STARTED here.
+ * When we reach here because queue is busy, it's safe to change the state
+ * to IDLE without checking @rq->aborted_gstate because we should still be
+ * holding the RCU read lock and thus protected against timeout.
  */
 static void __blk_mq_requeue_request(struct request *rq)
 {
@@ -655,7 +714,8 @@ static void __blk_mq_requeue_request(struct request *rq)
 	wbt_requeue(q->rq_wb, &rq->issue_stat);
 	blk_mq_sched_requeue_request(rq);
 
-	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
+	if (blk_mq_rq_state(rq) != MQ_RQ_IDLE) {
+		blk_mq_rq_update_state(rq, MQ_RQ_IDLE);
 		if (q->dma_drain_size && blk_rq_bytes(rq))
 			rq->nr_phys_segments--;
 	}
@@ -687,13 +747,13 @@ static void blk_mq_requeue_work(struct work_struct *work)
 
 		rq->rq_flags &= ~RQF_SOFTBARRIER;
 		list_del_init(&rq->queuelist);
-		blk_mq_sched_insert_request(rq, true, false, false, true);
+		blk_mq_sched_insert_request(rq, true, false, false);
 	}
 
 	while (!list_empty(&rq_list)) {
 		rq = list_entry(rq_list.next, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		blk_mq_sched_insert_request(rq, false, false, false, true);
+		blk_mq_sched_insert_request(rq, false, false, false);
 	}
 
 	blk_mq_run_hw_queues(q, false);
@@ -727,7 +787,7 @@ EXPORT_SYMBOL(blk_mq_add_to_requeue_list);
 
 void blk_mq_kick_requeue_list(struct request_queue *q)
 {
-	kblockd_schedule_delayed_work(&q->requeue_work, 0);
+	kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0);
 }
 EXPORT_SYMBOL(blk_mq_kick_requeue_list);
 
@@ -753,24 +813,15 @@ EXPORT_SYMBOL(blk_mq_tag_to_rq);
 struct blk_mq_timeout_data {
 	unsigned long next;
 	unsigned int next_set;
+	unsigned int nr_expired;
 };
 
-void blk_mq_rq_timed_out(struct request *req, bool reserved)
+static void blk_mq_rq_timed_out(struct request *req, bool reserved)
 {
 	const struct blk_mq_ops *ops = req->q->mq_ops;
 	enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
 
-	/*
-	 * We know that complete is set at this point. If STARTED isn't set
-	 * anymore, then the request isn't active and the "timeout" should
-	 * just be ignored. This can happen due to the bitflag ordering.
-	 * Timeout first checks if STARTED is set, and if it is, assumes
-	 * the request is active. But if we race with completion, then
-	 * both flags will get cleared. So check here again, and ignore
-	 * a timeout event with a request that isn't active.
-	 */
-	if (!test_bit(REQ_ATOM_STARTED, &req->atomic_flags))
-		return;
+	req->rq_flags |= RQF_MQ_TIMEOUT_EXPIRED;
 
 	if (ops->timeout)
 		ret = ops->timeout(req, reserved);
@@ -780,8 +831,13 @@ void blk_mq_rq_timed_out(struct request *req, bool reserved)
 		__blk_mq_complete_request(req);
 		break;
 	case BLK_EH_RESET_TIMER:
+		/*
+		 * As nothing prevents from completion happening while
+		 * ->aborted_gstate is set, this may lead to ignored
+		 * completions and further spurious timeouts.
+		 */
+		blk_mq_rq_update_aborted_gstate(req, 0);
 		blk_add_timer(req);
-		blk_clear_rq_complete(req);
 		break;
 	case BLK_EH_NOT_HANDLED:
 		break;
@@ -795,50 +851,51 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		struct request *rq, void *priv, bool reserved)
 {
 	struct blk_mq_timeout_data *data = priv;
-	unsigned long deadline;
+	unsigned long gstate, deadline;
+	int start;
 
-	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
-		return;
+	might_sleep();
 
-	/*
-	 * Ensures that if we see STARTED we must also see our
-	 * up-to-date deadline, see blk_mq_start_request().
-	 */
-	smp_rmb();
+	if (rq->rq_flags & RQF_MQ_TIMEOUT_EXPIRED)
+		return;
 
-	deadline = READ_ONCE(rq->deadline);
+	/* read coherent snapshots of @rq->state_gen and @rq->deadline */
+	while (true) {
+		start = read_seqcount_begin(&rq->gstate_seq);
+		gstate = READ_ONCE(rq->gstate);
+		deadline = blk_rq_deadline(rq);
+		if (!read_seqcount_retry(&rq->gstate_seq, start))
+			break;
+		cond_resched();
+	}
 
-	/*
-	 * The rq being checked may have been freed and reallocated
-	 * out already here, we avoid this race by checking rq->deadline
-	 * and REQ_ATOM_COMPLETE flag together:
-	 *
-	 * - if rq->deadline is observed as new value because of
-	 *   reusing, the rq won't be timed out because of timing.
-	 * - if rq->deadline is observed as previous value,
-	 *   REQ_ATOM_COMPLETE flag won't be cleared in reuse path
-	 *   because we put a barrier between setting rq->deadline
-	 *   and clearing the flag in blk_mq_start_request(), so
-	 *   this rq won't be timed out too.
-	 */
-	if (time_after_eq(jiffies, deadline)) {
-		if (!blk_mark_rq_complete(rq)) {
-			/*
-			 * Again coherence order ensures that consecutive reads
-			 * from the same variable must be in that order. This
-			 * ensures that if we see COMPLETE clear, we must then
-			 * see STARTED set and we'll ignore this timeout.
-			 *
-			 * (There's also the MB implied by the test_and_clear())
-			 */
-			blk_mq_rq_timed_out(rq, reserved);
-		}
+	/* if in-flight && overdue, mark for abortion */
+	if ((gstate & MQ_RQ_STATE_MASK) == MQ_RQ_IN_FLIGHT &&
+	    time_after_eq(jiffies, deadline)) {
+		blk_mq_rq_update_aborted_gstate(rq, gstate);
+		data->nr_expired++;
+		hctx->nr_expired++;
 	} else if (!data->next_set || time_after(data->next, deadline)) {
 		data->next = deadline;
 		data->next_set = 1;
 	}
 }
 
+static void blk_mq_terminate_expired(struct blk_mq_hw_ctx *hctx,
+		struct request *rq, void *priv, bool reserved)
+{
+	/*
+	 * We marked @rq->aborted_gstate and waited for RCU.  If there were
+	 * completions that we lost to, they would have finished and
+	 * updated @rq->gstate by now; otherwise, the completion path is
+	 * now guaranteed to see @rq->aborted_gstate and yield.  If
+	 * @rq->aborted_gstate still matches @rq->gstate, @rq is ours.
+	 */
+	if (!(rq->rq_flags & RQF_MQ_TIMEOUT_EXPIRED) &&
+	    READ_ONCE(rq->gstate) == rq->aborted_gstate)
+		blk_mq_rq_timed_out(rq, reserved);
+}
+
 static void blk_mq_timeout_work(struct work_struct *work)
 {
 	struct request_queue *q =
@@ -846,7 +903,9 @@ static void blk_mq_timeout_work(struct work_struct *work)
 	struct blk_mq_timeout_data data = {
 		.next		= 0,
 		.next_set	= 0,
+		.nr_expired	= 0,
 	};
+	struct blk_mq_hw_ctx *hctx;
 	int i;
 
 	/* A deadlock might occur if a request is stuck requiring a
@@ -865,14 +924,46 @@ static void blk_mq_timeout_work(struct work_struct *work)
 	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return;
 
+	/* scan for the expired ones and set their ->aborted_gstate */
 	blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data);
 
+	if (data.nr_expired) {
+		bool has_rcu = false;
+
+		/*
+		 * Wait till everyone sees ->aborted_gstate.  The
+		 * sequential waits for SRCUs aren't ideal.  If this ever
+		 * becomes a problem, we can add per-hw_ctx rcu_head and
+		 * wait in parallel.
+		 */
+		queue_for_each_hw_ctx(q, hctx, i) {
+			if (!hctx->nr_expired)
+				continue;
+
+			if (!(hctx->flags & BLK_MQ_F_BLOCKING))
+				has_rcu = true;
+			else
+				synchronize_srcu(hctx->srcu);
+
+			hctx->nr_expired = 0;
+		}
+		if (has_rcu)
+			synchronize_rcu();
+
+		/* terminate the ones we won */
+		blk_mq_queue_tag_busy_iter(q, blk_mq_terminate_expired, NULL);
+	}
+
 	if (data.next_set) {
 		data.next = blk_rq_timeout(round_jiffies_up(data.next));
 		mod_timer(&q->timeout, data.next);
 	} else {
-		struct blk_mq_hw_ctx *hctx;
-
+		/*
+		 * Request timeouts are handled as a forward rolling timer. If
+		 * we end up here it means that no requests are pending and
+		 * also that no request has been pending for a while. Mark
+		 * each hctx as idle.
+		 */
 		queue_for_each_hw_ctx(q, hctx, i) {
 			/* the hctx may be unmapped, so check it here */
 			if (blk_mq_hw_queue_mapped(hctx))
@@ -1008,66 +1099,67 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 
 /*
  * Mark us waiting for a tag. For shared tags, this involves hooking us into
- * the tag wakeups. For non-shared tags, we can simply mark us nedeing a
- * restart. For both caes, take care to check the condition again after
+ * the tag wakeups. For non-shared tags, we can simply mark us needing a
+ * restart. For both cases, take care to check the condition again after
  * marking us as waiting.
  */
 static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
 				 struct request *rq)
 {
 	struct blk_mq_hw_ctx *this_hctx = *hctx;
-	bool shared_tags = (this_hctx->flags & BLK_MQ_F_TAG_SHARED) != 0;
 	struct sbq_wait_state *ws;
 	wait_queue_entry_t *wait;
 	bool ret;
 
-	if (!shared_tags) {
+	if (!(this_hctx->flags & BLK_MQ_F_TAG_SHARED)) {
 		if (!test_bit(BLK_MQ_S_SCHED_RESTART, &this_hctx->state))
 			set_bit(BLK_MQ_S_SCHED_RESTART, &this_hctx->state);
-	} else {
-		wait = &this_hctx->dispatch_wait;
-		if (!list_empty_careful(&wait->entry))
-			return false;
 
-		spin_lock(&this_hctx->lock);
-		if (!list_empty(&wait->entry)) {
-			spin_unlock(&this_hctx->lock);
-			return false;
-		}
+		/*
+		 * It's possible that a tag was freed in the window between the
+		 * allocation failure and adding the hardware queue to the wait
+		 * queue.
+		 *
+		 * Don't clear RESTART here, someone else could have set it.
+		 * At most this will cost an extra queue run.
+		 */
+		return blk_mq_get_driver_tag(rq, hctx, false);
+	}
 
-		ws = bt_wait_ptr(&this_hctx->tags->bitmap_tags, this_hctx);
-		add_wait_queue(&ws->wait, wait);
+	wait = &this_hctx->dispatch_wait;
+	if (!list_empty_careful(&wait->entry))
+		return false;
+
+	spin_lock(&this_hctx->lock);
+	if (!list_empty(&wait->entry)) {
+		spin_unlock(&this_hctx->lock);
+		return false;
 	}
 
+	ws = bt_wait_ptr(&this_hctx->tags->bitmap_tags, this_hctx);
+	add_wait_queue(&ws->wait, wait);
+
 	/*
 	 * It's possible that a tag was freed in the window between the
 	 * allocation failure and adding the hardware queue to the wait
 	 * queue.
 	 */
 	ret = blk_mq_get_driver_tag(rq, hctx, false);
-
-	if (!shared_tags) {
-		/*
-		 * Don't clear RESTART here, someone else could have set it.
-		 * At most this will cost an extra queue run.
-		 */
-		return ret;
-	} else {
-		if (!ret) {
-			spin_unlock(&this_hctx->lock);
-			return false;
-		}
-
-		/*
-		 * We got a tag, remove ourselves from the wait queue to ensure
-		 * someone else gets the wakeup.
-		 */
-		spin_lock_irq(&ws->wait.lock);
-		list_del_init(&wait->entry);
-		spin_unlock_irq(&ws->wait.lock);
+	if (!ret) {
 		spin_unlock(&this_hctx->lock);
-		return true;
+		return false;
 	}
+
+	/*
+	 * We got a tag, remove ourselves from the wait queue to ensure
+	 * someone else gets the wakeup.
+	 */
+	spin_lock_irq(&ws->wait.lock);
+	list_del_init(&wait->entry);
+	spin_unlock_irq(&ws->wait.lock);
+	spin_unlock(&this_hctx->lock);
+
+	return true;
 }
 
 bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
@@ -1204,9 +1296,27 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	/*
 	 * We should be running this queue from one of the CPUs that
 	 * are mapped to it.
+	 *
+	 * There are at least two related races now between setting
+	 * hctx->next_cpu from blk_mq_hctx_next_cpu() and running
+	 * __blk_mq_run_hw_queue():
+	 *
+	 * - hctx->next_cpu is found offline in blk_mq_hctx_next_cpu(),
+	 *   but later it becomes online, then this warning is harmless
+	 *   at all
+	 *
+	 * - hctx->next_cpu is found online in blk_mq_hctx_next_cpu(),
+	 *   but later it becomes offline, then the warning can't be
+	 *   triggered, and we depend on blk-mq timeout handler to
+	 *   handle dispatched requests to this hctx
 	 */
-	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
-		cpu_online(hctx->next_cpu));
+	if (!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
+		cpu_online(hctx->next_cpu)) {
+		printk(KERN_WARNING "run queue from wrong CPU %d, hctx %s\n",
+			raw_smp_processor_id(),
+			cpumask_empty(hctx->cpumask) ? "inactive": "active");
+		dump_stack();
+	}
 
 	/*
 	 * We can't run the queue inline with ints disabled. Ensure that
@@ -1214,17 +1324,11 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	 */
 	WARN_ON_ONCE(in_interrupt());
 
-	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
-		rcu_read_lock();
-		blk_mq_sched_dispatch_requests(hctx);
-		rcu_read_unlock();
-	} else {
-		might_sleep();
+	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
 
-		srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);
-		blk_mq_sched_dispatch_requests(hctx);
-		srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);
-	}
+	hctx_lock(hctx, &srcu_idx);
+	blk_mq_sched_dispatch_requests(hctx);
+	hctx_unlock(hctx, srcu_idx);
 }
 
 /*
@@ -1235,20 +1339,47 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
  */
 static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 {
+	bool tried = false;
+
 	if (hctx->queue->nr_hw_queues == 1)
 		return WORK_CPU_UNBOUND;
 
 	if (--hctx->next_cpu_batch <= 0) {
 		int next_cpu;
-
-		next_cpu = cpumask_next(hctx->next_cpu, hctx->cpumask);
+select_cpu:
+		next_cpu = cpumask_next_and(hctx->next_cpu, hctx->cpumask,
+				cpu_online_mask);
 		if (next_cpu >= nr_cpu_ids)
-			next_cpu = cpumask_first(hctx->cpumask);
+			next_cpu = cpumask_first_and(hctx->cpumask,cpu_online_mask);
 
-		hctx->next_cpu = next_cpu;
+		/*
+		 * No online CPU is found, so have to make sure hctx->next_cpu
+		 * is set correctly for not breaking workqueue.
+		 */
+		if (next_cpu >= nr_cpu_ids)
+			hctx->next_cpu = cpumask_first(hctx->cpumask);
+		else
+			hctx->next_cpu = next_cpu;
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
 	}
 
+	/*
+	 * Do unbound schedule if we can't find a online CPU for this hctx,
+	 * and it should only happen in the path of handling CPU DEAD.
+	 */
+	if (!cpu_online(hctx->next_cpu)) {
+		if (!tried) {
+			tried = true;
+			goto select_cpu;
+		}
+
+		/*
+		 * Make sure to re-select CPU next time once after CPUs
+		 * in hctx->cpumask become online again.
+		 */
+		hctx->next_cpu_batch = 1;
+		return WORK_CPU_UNBOUND;
+	}
 	return hctx->next_cpu;
 }
 
@@ -1272,9 +1403,8 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
 		put_cpu();
 	}
 
-	kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
-					 &hctx->run_work,
-					 msecs_to_jiffies(msecs));
+	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
+				    msecs_to_jiffies(msecs));
 }
 
 void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
@@ -1285,7 +1415,23 @@ EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
 
 bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
-	if (blk_mq_hctx_has_pending(hctx)) {
+	int srcu_idx;
+	bool need_run;
+
+	/*
+	 * When queue is quiesced, we may be switching io scheduler, or
+	 * updating nr_hw_queues, or other things, and we can't run queue
+	 * any more, even __blk_mq_hctx_has_pending() can't be called safely.
+	 *
+	 * And queue will be rerun in blk_mq_unquiesce_queue() if it is
+	 * quiesced.
+	 */
+	hctx_lock(hctx, &srcu_idx);
+	need_run = !blk_queue_quiesced(hctx->queue) &&
+		blk_mq_hctx_has_pending(hctx);
+	hctx_unlock(hctx, srcu_idx);
+
+	if (need_run) {
 		__blk_mq_delay_run_hw_queue(hctx, async, 0);
 		return true;
 	}
@@ -1593,9 +1739,9 @@ static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
 	return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
 }
 
-static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
-					struct request *rq,
-					blk_qc_t *cookie, bool may_sleep)
+static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
+					    struct request *rq,
+					    blk_qc_t *cookie)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_queue_data bd = {
@@ -1604,15 +1750,52 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	};
 	blk_qc_t new_cookie;
 	blk_status_t ret;
+
+	new_cookie = request_to_qc_t(hctx, rq);
+
+	/*
+	 * For OK queue, we are done. For error, caller may kill it.
+	 * Any other error (busy), just add it to our list as we
+	 * previously would have done.
+	 */
+	ret = q->mq_ops->queue_rq(hctx, &bd);
+	switch (ret) {
+	case BLK_STS_OK:
+		*cookie = new_cookie;
+		break;
+	case BLK_STS_RESOURCE:
+		__blk_mq_requeue_request(rq);
+		break;
+	default:
+		*cookie = BLK_QC_T_NONE;
+		break;
+	}
+
+	return ret;
+}
+
+static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+						struct request *rq,
+						blk_qc_t *cookie,
+						bool bypass_insert)
+{
+	struct request_queue *q = rq->q;
 	bool run_queue = true;
 
-	/* RCU or SRCU read lock is needed before checking quiesced flag */
+	/*
+	 * RCU or SRCU read lock is needed before checking quiesced flag.
+	 *
+	 * When queue is stopped or quiesced, ignore 'bypass_insert' from
+	 * blk_mq_request_issue_directly(), and return BLK_STS_OK to caller,
+	 * and avoid driver to try to dispatch again.
+	 */
 	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) {
 		run_queue = false;
+		bypass_insert = false;
 		goto insert;
 	}
 
-	if (q->elevator)
+	if (q->elevator && !bypass_insert)
 		goto insert;
 
 	if (!blk_mq_get_driver_tag(rq, NULL, false))
@@ -1623,47 +1806,47 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		goto insert;
 	}
 
-	new_cookie = request_to_qc_t(hctx, rq);
-
-	/*
-	 * For OK queue, we are done. For error, kill it. Any other
-	 * error (busy), just add it to our list as we previously
-	 * would have done
-	 */
-	ret = q->mq_ops->queue_rq(hctx, &bd);
-	switch (ret) {
-	case BLK_STS_OK:
-		*cookie = new_cookie;
-		return;
-	case BLK_STS_RESOURCE:
-		__blk_mq_requeue_request(rq);
-		goto insert;
-	default:
-		*cookie = BLK_QC_T_NONE;
-		blk_mq_end_request(rq, ret);
-		return;
-	}
-
+	return __blk_mq_issue_directly(hctx, rq, cookie);
 insert:
-	blk_mq_sched_insert_request(rq, false, run_queue, false, may_sleep);
+	if (bypass_insert)
+		return BLK_STS_RESOURCE;
+
+	blk_mq_sched_insert_request(rq, false, run_queue, false);
+	return BLK_STS_OK;
 }
 
 static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		struct request *rq, blk_qc_t *cookie)
 {
-	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
-		rcu_read_lock();
-		__blk_mq_try_issue_directly(hctx, rq, cookie, false);
-		rcu_read_unlock();
-	} else {
-		unsigned int srcu_idx;
+	blk_status_t ret;
+	int srcu_idx;
 
-		might_sleep();
+	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
 
-		srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);
-		__blk_mq_try_issue_directly(hctx, rq, cookie, true);
-		srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);
-	}
+	hctx_lock(hctx, &srcu_idx);
+
+	ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false);
+	if (ret == BLK_STS_RESOURCE)
+		blk_mq_sched_insert_request(rq, false, true, false);
+	else if (ret != BLK_STS_OK)
+		blk_mq_end_request(rq, ret);
+
+	hctx_unlock(hctx, srcu_idx);
+}
+
+blk_status_t blk_mq_request_issue_directly(struct request *rq)
+{
+	blk_status_t ret;
+	int srcu_idx;
+	blk_qc_t unused_cookie;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu);
+
+	hctx_lock(hctx, &srcu_idx);
+	ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true);
+	hctx_unlock(hctx, srcu_idx);
+
+	return ret;
 }
 
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
@@ -1774,7 +1957,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	} else if (q->elevator) {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_sched_insert_request(rq, false, true, true, true);
+		blk_mq_sched_insert_request(rq, false, true, true);
 	} else {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
@@ -1867,6 +2050,22 @@ static size_t order_to_size(unsigned int order)
 	return (size_t)PAGE_SIZE << order;
 }
 
+static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
+			       unsigned int hctx_idx, int node)
+{
+	int ret;
+
+	if (set->ops->init_request) {
+		ret = set->ops->init_request(set, rq, hctx_idx, node);
+		if (ret)
+			return ret;
+	}
+
+	seqcount_init(&rq->gstate_seq);
+	u64_stats_init(&rq->aborted_gstate_sync);
+	return 0;
+}
+
 int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		     unsigned int hctx_idx, unsigned int depth)
 {
@@ -1928,12 +2127,9 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 			struct request *rq = p;
 
 			tags->static_rqs[i] = rq;
-			if (set->ops->init_request) {
-				if (set->ops->init_request(set, rq, hctx_idx,
-						node)) {
-					tags->static_rqs[i] = NULL;
-					goto fail;
-				}
+			if (blk_mq_init_request(set, rq, hctx_idx, node)) {
+				tags->static_rqs[i] = NULL;
+				goto fail;
 			}
 
 			p += rq_size;
@@ -1992,7 +2188,8 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 {
 	blk_mq_debugfs_unregister_hctx(hctx);
 
-	blk_mq_tag_idle(hctx);
+	if (blk_mq_hw_queue_mapped(hctx))
+		blk_mq_tag_idle(hctx);
 
 	if (set->ops->exit_request)
 		set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
@@ -2003,7 +2200,7 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 		set->ops->exit_hctx(hctx, hctx_idx);
 
 	if (hctx->flags & BLK_MQ_F_BLOCKING)
-		cleanup_srcu_struct(hctx->queue_rq_srcu);
+		cleanup_srcu_struct(hctx->srcu);
 
 	blk_mq_remove_cpuhp(hctx);
 	blk_free_flush_queue(hctx->fq);
@@ -2072,13 +2269,11 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	if (!hctx->fq)
 		goto sched_exit_hctx;
 
-	if (set->ops->init_request &&
-	    set->ops->init_request(set, hctx->fq->flush_rq, hctx_idx,
-				   node))
+	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, node))
 		goto free_fq;
 
 	if (hctx->flags & BLK_MQ_F_BLOCKING)
-		init_srcu_struct(hctx->queue_rq_srcu);
+		init_srcu_struct(hctx->srcu);
 
 	blk_mq_debugfs_register_hctx(q, hctx);
 
@@ -2114,16 +2309,11 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 		INIT_LIST_HEAD(&__ctx->rq_list);
 		__ctx->queue = q;
 
-		/* If the cpu isn't present, the cpu is mapped to first hctx */
-		if (!cpu_present(i))
-			continue;
-
-		hctx = blk_mq_map_queue(q, i);
-
 		/*
 		 * Set local node, IFF we have more than one hw queue. If
 		 * not, we remain on the home node of the device
 		 */
+		hctx = blk_mq_map_queue(q, i);
 		if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE)
 			hctx->numa_node = local_memory_node(cpu_to_node(i));
 	}
@@ -2180,7 +2370,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	 *
 	 * If the cpu isn't present, the cpu is mapped to first hctx.
 	 */
-	for_each_present_cpu(i) {
+	for_each_possible_cpu(i) {
 		hctx_idx = q->mq_map[i];
 		/* unmapped hw queue can be remapped after CPU topo changed */
 		if (!set->tags[hctx_idx] &&
@@ -2234,7 +2424,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		/*
 		 * Initialize batch roundrobin counts
 		 */
-		hctx->next_cpu = cpumask_first(hctx->cpumask);
+		hctx->next_cpu = cpumask_first_and(hctx->cpumask,
+				cpu_online_mask);
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
 	}
 }
@@ -2367,7 +2558,7 @@ static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
 {
 	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
 
-	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, queue_rq_srcu),
+	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
 			   __alignof__(struct blk_mq_hw_ctx)) !=
 		     sizeof(struct blk_mq_hw_ctx));
 
@@ -2384,6 +2575,9 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
 
 	blk_mq_sysfs_unregister(q);
+
+	/* protect against switching io scheduler  */
+	mutex_lock(&q->sysfs_lock);
 	for (i = 0; i < set->nr_hw_queues; i++) {
 		int node;
 
@@ -2428,6 +2622,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 		}
 	}
 	q->nr_hw_queues = i;
+	mutex_unlock(&q->sysfs_lock);
 	blk_mq_sysfs_register(q);
 }
 
@@ -2599,9 +2794,27 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 
 static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 {
-	if (set->ops->map_queues)
+	if (set->ops->map_queues) {
+		int cpu;
+		/*
+		 * transport .map_queues is usually done in the following
+		 * way:
+		 *
+		 * for (queue = 0; queue < set->nr_hw_queues; queue++) {
+		 * 	mask = get_cpu_mask(queue)
+		 * 	for_each_cpu(cpu, mask)
+		 * 		set->mq_map[cpu] = queue;
+		 * }
+		 *
+		 * When we need to remap, the table has to be cleared for
+		 * killing stale mapping since one CPU may not be mapped
+		 * to any hw queue.
+		 */
+		for_each_possible_cpu(cpu)
+			set->mq_map[cpu] = 0;
+
 		return set->ops->map_queues(set);
-	else
+	} else
 		return blk_mq_map_queues(set);
 }
 
@@ -2710,6 +2923,7 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 		return -EINVAL;
 
 	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue(q);
 
 	ret = 0;
 	queue_for_each_hw_ctx(q, hctx, i) {
@@ -2733,6 +2947,7 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	if (!ret)
 		q->nr_requests = nr;
 
+	blk_mq_unquiesce_queue(q);
 	blk_mq_unfreeze_queue(q);
 
 	return ret;
@@ -2848,7 +3063,7 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
 	unsigned int nsecs;
 	ktime_t kt;
 
-	if (test_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags))
+	if (rq->rq_flags & RQF_MQ_POLL_SLEPT)
 		return false;
 
 	/*
@@ -2868,7 +3083,7 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
 	if (!nsecs)
 		return false;
 
-	set_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
+	rq->rq_flags |= RQF_MQ_POLL_SLEPT;
 
 	/*
 	 * This will be replaced with the stats tracking code, using
@@ -2882,7 +3097,7 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
 
 	hrtimer_init_sleeper(&hs, current);
 	do {
-		if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags))
+		if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE)
 			break;
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		hrtimer_start_expires(&hs.timer, mode);
@@ -2968,12 +3183,6 @@ static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
 
 static int __init blk_mq_init(void)
 {
-	/*
-	 * See comment in block/blk.h rq_atomic_flags enum
-	 */
-	BUILD_BUG_ON((REQ_ATOM_STARTED / BITS_PER_BYTE) !=
-			(REQ_ATOM_COMPLETE / BITS_PER_BYTE));
-
 	cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
 				blk_mq_hctx_notify_dead);
 	return 0;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 6c7c3ff5bf62..88c558f71819 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -27,6 +27,20 @@ struct blk_mq_ctx {
 	struct kobject		kobj;
 } ____cacheline_aligned_in_smp;
 
+/*
+ * Bits for request->gstate.  The lower two bits carry MQ_RQ_* state value
+ * and the upper bits the generation number.
+ */
+enum mq_rq_state {
+	MQ_RQ_IDLE		= 0,
+	MQ_RQ_IN_FLIGHT		= 1,
+	MQ_RQ_COMPLETE		= 2,
+
+	MQ_RQ_STATE_BITS	= 2,
+	MQ_RQ_STATE_MASK	= (1 << MQ_RQ_STATE_BITS) - 1,
+	MQ_RQ_GEN_INC		= 1 << MQ_RQ_STATE_BITS,
+};
+
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
@@ -60,6 +74,9 @@ void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);
 
+/* Used by blk_insert_cloned_request() to issue request directly */
+blk_status_t blk_mq_request_issue_directly(struct request *rq);
+
 /*
  * CPU -> queue mappings
  */
@@ -81,10 +98,41 @@ extern int blk_mq_sysfs_register(struct request_queue *q);
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
 extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 
-extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
-
 void blk_mq_release(struct request_queue *q);
 
+/**
+ * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
+ * @rq: target request.
+ */
+static inline int blk_mq_rq_state(struct request *rq)
+{
+	return READ_ONCE(rq->gstate) & MQ_RQ_STATE_MASK;
+}
+
+/**
+ * blk_mq_rq_update_state() - set the current MQ_RQ_* state of a request
+ * @rq: target request.
+ * @state: new state to set.
+ *
+ * Set @rq's state to @state.  The caller is responsible for ensuring that
+ * there are no other updaters.  A request can transition into IN_FLIGHT
+ * only from IDLE and doing so increments the generation number.
+ */
+static inline void blk_mq_rq_update_state(struct request *rq,
+					  enum mq_rq_state state)
+{
+	u64 old_val = READ_ONCE(rq->gstate);
+	u64 new_val = (old_val & ~MQ_RQ_STATE_MASK) | state;
+
+	if (state == MQ_RQ_IN_FLIGHT) {
+		WARN_ON_ONCE((old_val & MQ_RQ_STATE_MASK) != MQ_RQ_IDLE);
+		new_val += MQ_RQ_GEN_INC;
+	}
+
+	/* avoid exposing interim values */
+	WRITE_ONCE(rq->gstate, new_val);
+}
+
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
 					   unsigned int cpu)
 {
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index e54be402899d..cbea895a5547 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -450,12 +450,9 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 		ret = wbt_init(q);
 		if (ret)
 			return ret;
-
-		rwb = q->rq_wb;
-		if (!rwb)
-			return -EINVAL;
 	}
 
+	rwb = q->rq_wb;
 	if (val == -1)
 		rwb->min_lat_nsec = wbt_default_latency_nsec(q);
 	else if (val >= 0)
@@ -856,6 +853,10 @@ struct kobj_type blk_queue_ktype = {
 	.release	= blk_release_queue,
 };
 
+/**
+ * blk_register_queue - register a block layer queue with sysfs
+ * @disk: Disk of which the request queue should be registered with sysfs.
+ */
 int blk_register_queue(struct gendisk *disk)
 {
 	int ret;
@@ -912,11 +913,12 @@ int blk_register_queue(struct gendisk *disk)
 	if (q->request_fn || (q->mq_ops && q->elevator)) {
 		ret = elv_register_queue(q);
 		if (ret) {
+			mutex_unlock(&q->sysfs_lock);
 			kobject_uevent(&q->kobj, KOBJ_REMOVE);
 			kobject_del(&q->kobj);
 			blk_trace_remove_sysfs(dev);
 			kobject_put(&dev->kobj);
-			goto unlock;
+			return ret;
 		}
 	}
 	ret = 0;
@@ -924,7 +926,15 @@ unlock:
 	mutex_unlock(&q->sysfs_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(blk_register_queue);
 
+/**
+ * blk_unregister_queue - counterpart of blk_register_queue()
+ * @disk: Disk of which the request queue should be unregistered from sysfs.
+ *
+ * Note: the caller is responsible for guaranteeing that this function is called
+ * after blk_register_queue() has finished.
+ */
 void blk_unregister_queue(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
@@ -932,21 +942,39 @@ void blk_unregister_queue(struct gendisk *disk)
 	if (WARN_ON(!q))
 		return;
 
-	mutex_lock(&q->sysfs_lock);
-	queue_flag_clear_unlocked(QUEUE_FLAG_REGISTERED, q);
-	mutex_unlock(&q->sysfs_lock);
+	/* Return early if disk->queue was never registered. */
+	if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+		return;
 
-	wbt_exit(q);
+	/*
+	 * Since sysfs_remove_dir() prevents adding new directory entries
+	 * before removal of existing entries starts, protect against
+	 * concurrent elv_iosched_store() calls.
+	 */
+	mutex_lock(&q->sysfs_lock);
 
+	spin_lock_irq(q->queue_lock);
+	queue_flag_clear(QUEUE_FLAG_REGISTERED, q);
+	spin_unlock_irq(q->queue_lock);
 
+	/*
+	 * Remove the sysfs attributes before unregistering the queue data
+	 * structures that can be modified through sysfs.
+	 */
 	if (q->mq_ops)
 		blk_mq_unregister_dev(disk_to_dev(disk), q);
-
-	if (q->request_fn || (q->mq_ops && q->elevator))
-		elv_unregister_queue(q);
+	mutex_unlock(&q->sysfs_lock);
 
 	kobject_uevent(&q->kobj, KOBJ_REMOVE);
 	kobject_del(&q->kobj);
 	blk_trace_remove_sysfs(disk_to_dev(disk));
+
+	wbt_exit(q);
+
+	mutex_lock(&q->sysfs_lock);
+	if (q->request_fn || (q->mq_ops && q->elevator))
+		elv_unregister_queue(q);
+	mutex_unlock(&q->sysfs_lock);
+
 	kobject_put(&disk_to_dev(disk)->kobj);
 }
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 825bc29767e6..c5a131673733 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -216,9 +216,9 @@ struct throtl_data
 
 	unsigned int scale;
 
-	struct latency_bucket tmp_buckets[LATENCY_BUCKET_SIZE];
-	struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE];
-	struct latency_bucket __percpu *latency_buckets;
+	struct latency_bucket tmp_buckets[2][LATENCY_BUCKET_SIZE];
+	struct avg_latency_bucket avg_buckets[2][LATENCY_BUCKET_SIZE];
+	struct latency_bucket __percpu *latency_buckets[2];
 	unsigned long last_calculate_time;
 	unsigned long filtered_latency;
 
@@ -1511,10 +1511,20 @@ static struct cftype throtl_legacy_files[] = {
 		.seq_show = blkg_print_stat_bytes,
 	},
 	{
+		.name = "throttle.io_service_bytes_recursive",
+		.private = (unsigned long)&blkcg_policy_throtl,
+		.seq_show = blkg_print_stat_bytes_recursive,
+	},
+	{
 		.name = "throttle.io_serviced",
 		.private = (unsigned long)&blkcg_policy_throtl,
 		.seq_show = blkg_print_stat_ios,
 	},
+	{
+		.name = "throttle.io_serviced_recursive",
+		.private = (unsigned long)&blkcg_policy_throtl,
+		.seq_show = blkg_print_stat_ios_recursive,
+	},
 	{ }	/* terminate */
 };
 
@@ -2040,10 +2050,10 @@ static void blk_throtl_update_idletime(struct throtl_grp *tg)
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 static void throtl_update_latency_buckets(struct throtl_data *td)
 {
-	struct avg_latency_bucket avg_latency[LATENCY_BUCKET_SIZE];
-	int i, cpu;
-	unsigned long last_latency = 0;
-	unsigned long latency;
+	struct avg_latency_bucket avg_latency[2][LATENCY_BUCKET_SIZE];
+	int i, cpu, rw;
+	unsigned long last_latency[2] = { 0 };
+	unsigned long latency[2];
 
 	if (!blk_queue_nonrot(td->queue))
 		return;
@@ -2052,56 +2062,67 @@ static void throtl_update_latency_buckets(struct throtl_data *td)
 	td->last_calculate_time = jiffies;
 
 	memset(avg_latency, 0, sizeof(avg_latency));
-	for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
-		struct latency_bucket *tmp = &td->tmp_buckets[i];
-
-		for_each_possible_cpu(cpu) {
-			struct latency_bucket *bucket;
-
-			/* this isn't race free, but ok in practice */
-			bucket = per_cpu_ptr(td->latency_buckets, cpu);
-			tmp->total_latency += bucket[i].total_latency;
-			tmp->samples += bucket[i].samples;
-			bucket[i].total_latency = 0;
-			bucket[i].samples = 0;
-		}
+	for (rw = READ; rw <= WRITE; rw++) {
+		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+			struct latency_bucket *tmp = &td->tmp_buckets[rw][i];
+
+			for_each_possible_cpu(cpu) {
+				struct latency_bucket *bucket;
+
+				/* this isn't race free, but ok in practice */
+				bucket = per_cpu_ptr(td->latency_buckets[rw],
+					cpu);
+				tmp->total_latency += bucket[i].total_latency;
+				tmp->samples += bucket[i].samples;
+				bucket[i].total_latency = 0;
+				bucket[i].samples = 0;
+			}
 
-		if (tmp->samples >= 32) {
-			int samples = tmp->samples;
+			if (tmp->samples >= 32) {
+				int samples = tmp->samples;
 
-			latency = tmp->total_latency;
+				latency[rw] = tmp->total_latency;
 
-			tmp->total_latency = 0;
-			tmp->samples = 0;
-			latency /= samples;
-			if (latency == 0)
-				continue;
-			avg_latency[i].latency = latency;
+				tmp->total_latency = 0;
+				tmp->samples = 0;
+				latency[rw] /= samples;
+				if (latency[rw] == 0)
+					continue;
+				avg_latency[rw][i].latency = latency[rw];
+			}
 		}
 	}
 
-	for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
-		if (!avg_latency[i].latency) {
-			if (td->avg_buckets[i].latency < last_latency)
-				td->avg_buckets[i].latency = last_latency;
-			continue;
-		}
+	for (rw = READ; rw <= WRITE; rw++) {
+		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+			if (!avg_latency[rw][i].latency) {
+				if (td->avg_buckets[rw][i].latency < last_latency[rw])
+					td->avg_buckets[rw][i].latency =
+						last_latency[rw];
+				continue;
+			}
 
-		if (!td->avg_buckets[i].valid)
-			latency = avg_latency[i].latency;
-		else
-			latency = (td->avg_buckets[i].latency * 7 +
-				avg_latency[i].latency) >> 3;
+			if (!td->avg_buckets[rw][i].valid)
+				latency[rw] = avg_latency[rw][i].latency;
+			else
+				latency[rw] = (td->avg_buckets[rw][i].latency * 7 +
+					avg_latency[rw][i].latency) >> 3;
 
-		td->avg_buckets[i].latency = max(latency, last_latency);
-		td->avg_buckets[i].valid = true;
-		last_latency = td->avg_buckets[i].latency;
+			td->avg_buckets[rw][i].latency = max(latency[rw],
+				last_latency[rw]);
+			td->avg_buckets[rw][i].valid = true;
+			last_latency[rw] = td->avg_buckets[rw][i].latency;
+		}
 	}
 
 	for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
 		throtl_log(&td->service_queue,
-			"Latency bucket %d: latency=%ld, valid=%d", i,
-			td->avg_buckets[i].latency, td->avg_buckets[i].valid);
+			"Latency bucket %d: read latency=%ld, read valid=%d, "
+			"write latency=%ld, write valid=%d", i,
+			td->avg_buckets[READ][i].latency,
+			td->avg_buckets[READ][i].valid,
+			td->avg_buckets[WRITE][i].latency,
+			td->avg_buckets[WRITE][i].valid);
 }
 #else
 static inline void throtl_update_latency_buckets(struct throtl_data *td)
@@ -2226,13 +2247,7 @@ again:
 out_unlock:
 	spin_unlock_irq(q->queue_lock);
 out:
-	/*
-	 * As multiple blk-throtls may stack in the same issue path, we
-	 * don't want bios to leave with the flag set.  Clear the flag if
-	 * being issued.
-	 */
-	if (!throttled)
-		bio_clear_flag(bio, BIO_THROTTLED);
+	bio_set_flag(bio, BIO_THROTTLED);
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 	if (throttled || !td->track_bio_latency)
@@ -2248,16 +2263,17 @@ static void throtl_track_latency(struct throtl_data *td, sector_t size,
 	struct latency_bucket *latency;
 	int index;
 
-	if (!td || td->limit_index != LIMIT_LOW || op != REQ_OP_READ ||
+	if (!td || td->limit_index != LIMIT_LOW ||
+	    !(op == REQ_OP_READ || op == REQ_OP_WRITE) ||
 	    !blk_queue_nonrot(td->queue))
 		return;
 
 	index = request_bucket_index(size);
 
-	latency = get_cpu_ptr(td->latency_buckets);
+	latency = get_cpu_ptr(td->latency_buckets[op]);
 	latency[index].total_latency += time;
 	latency[index].samples++;
-	put_cpu_ptr(td->latency_buckets);
+	put_cpu_ptr(td->latency_buckets[op]);
 }
 
 void blk_throtl_stat_add(struct request *rq, u64 time_ns)
@@ -2276,6 +2292,7 @@ void blk_throtl_bio_endio(struct bio *bio)
 	unsigned long finish_time;
 	unsigned long start_time;
 	unsigned long lat;
+	int rw = bio_data_dir(bio);
 
 	tg = bio->bi_cg_private;
 	if (!tg)
@@ -2304,7 +2321,7 @@ void blk_throtl_bio_endio(struct bio *bio)
 
 		bucket = request_bucket_index(
 			blk_stat_size(&bio->bi_issue_stat));
-		threshold = tg->td->avg_buckets[bucket].latency +
+		threshold = tg->td->avg_buckets[rw][bucket].latency +
 			tg->latency_target;
 		if (lat > threshold)
 			tg->bad_bio_cnt++;
@@ -2397,9 +2414,16 @@ int blk_throtl_init(struct request_queue *q)
 	td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
 	if (!td)
 		return -ENOMEM;
-	td->latency_buckets = __alloc_percpu(sizeof(struct latency_bucket) *
+	td->latency_buckets[READ] = __alloc_percpu(sizeof(struct latency_bucket) *
+		LATENCY_BUCKET_SIZE, __alignof__(u64));
+	if (!td->latency_buckets[READ]) {
+		kfree(td);
+		return -ENOMEM;
+	}
+	td->latency_buckets[WRITE] = __alloc_percpu(sizeof(struct latency_bucket) *
 		LATENCY_BUCKET_SIZE, __alignof__(u64));
-	if (!td->latency_buckets) {
+	if (!td->latency_buckets[WRITE]) {
+		free_percpu(td->latency_buckets[READ]);
 		kfree(td);
 		return -ENOMEM;
 	}
@@ -2418,7 +2442,8 @@ int blk_throtl_init(struct request_queue *q)
 	/* activate policy */
 	ret = blkcg_activate_policy(q, &blkcg_policy_throtl);
 	if (ret) {
-		free_percpu(td->latency_buckets);
+		free_percpu(td->latency_buckets[READ]);
+		free_percpu(td->latency_buckets[WRITE]);
 		kfree(td);
 	}
 	return ret;
@@ -2429,7 +2454,8 @@ void blk_throtl_exit(struct request_queue *q)
 	BUG_ON(!q->td);
 	throtl_shutdown_wq(q);
 	blkcg_deactivate_policy(q, &blkcg_policy_throtl);
-	free_percpu(q->td->latency_buckets);
+	free_percpu(q->td->latency_buckets[READ]);
+	free_percpu(q->td->latency_buckets[WRITE]);
 	kfree(q->td);
 }
 
@@ -2447,15 +2473,17 @@ void blk_throtl_register_queue(struct request_queue *q)
 	} else {
 		td->throtl_slice = DFL_THROTL_SLICE_HD;
 		td->filtered_latency = LATENCY_FILTERED_HD;
-		for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
-			td->avg_buckets[i].latency = DFL_HD_BASELINE_LATENCY;
+		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+			td->avg_buckets[READ][i].latency = DFL_HD_BASELINE_LATENCY;
+			td->avg_buckets[WRITE][i].latency = DFL_HD_BASELINE_LATENCY;
+		}
 	}
 #ifndef CONFIG_BLK_DEV_THROTTLING_LOW
 	/* if no low limit, use previous default */
 	td->throtl_slice = DFL_THROTL_SLICE_HD;
 #endif
 
-	td->track_bio_latency = !q->mq_ops && !q->request_fn;
+	td->track_bio_latency = !queue_is_rq_based(q);
 	if (!td->track_bio_latency)
 		blk_stat_enable_accounting(q);
 }
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 764ecf9aeb30..a05e3676d24a 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -112,7 +112,9 @@ static void blk_rq_timed_out(struct request *req)
 static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
 			  unsigned int *next_set)
 {
-	if (time_after_eq(jiffies, rq->deadline)) {
+	const unsigned long deadline = blk_rq_deadline(rq);
+
+	if (time_after_eq(jiffies, deadline)) {
 		list_del_init(&rq->timeout_list);
 
 		/*
@@ -120,8 +122,8 @@ static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout
 		 */
 		if (!blk_mark_rq_complete(rq))
 			blk_rq_timed_out(rq);
-	} else if (!*next_set || time_after(*next_timeout, rq->deadline)) {
-		*next_timeout = rq->deadline;
+	} else if (!*next_set || time_after(*next_timeout, deadline)) {
+		*next_timeout = deadline;
 		*next_set = 1;
 	}
 }
@@ -156,12 +158,17 @@ void blk_timeout_work(struct work_struct *work)
  */
 void blk_abort_request(struct request *req)
 {
-	if (blk_mark_rq_complete(req))
-		return;
-
 	if (req->q->mq_ops) {
-		blk_mq_rq_timed_out(req, false);
+		/*
+		 * All we need to ensure is that timeout scan takes place
+		 * immediately and that scan sees the new timeout value.
+		 * No need for fancy synchronizations.
+		 */
+		blk_rq_set_deadline(req, jiffies);
+		mod_timer(&req->q->timeout, 0);
 	} else {
+		if (blk_mark_rq_complete(req))
+			return;
 		blk_delete_timer(req);
 		blk_rq_timed_out(req);
 	}
@@ -208,7 +215,8 @@ void blk_add_timer(struct request *req)
 	if (!req->timeout)
 		req->timeout = q->rq_timeout;
 
-	WRITE_ONCE(req->deadline, jiffies + req->timeout);
+	blk_rq_set_deadline(req, jiffies + req->timeout);
+	req->rq_flags &= ~RQF_MQ_TIMEOUT_EXPIRED;
 
 	/*
 	 * Only the non-mq case needs to add the request to a protected list.
@@ -222,7 +230,7 @@ void blk_add_timer(struct request *req)
 	 * than an existing one, modify the timer. Round up to next nearest
 	 * second.
 	 */
-	expiry = blk_rq_timeout(round_jiffies_up(req->deadline));
+	expiry = blk_rq_timeout(round_jiffies_up(blk_rq_deadline(req)));
 
 	if (!timer_pending(&q->timeout) ||
 	    time_before(expiry, q->timeout.expires)) {
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index b252da0e4c11..ae8de9780085 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -178,12 +178,11 @@ void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat)
 
 		if (wbt_is_read(stat))
 			wb_timestamp(rwb, &rwb->last_comp);
-		wbt_clear_state(stat);
 	} else {
 		WARN_ON_ONCE(stat == rwb->sync_cookie);
 		__wbt_done(rwb, wbt_stat_to_mask(stat));
-		wbt_clear_state(stat);
 	}
+	wbt_clear_state(stat);
 }
 
 /*
@@ -482,7 +481,7 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 
 	/*
 	 * At this point we know it's a buffered write. If this is
-	 * kswapd trying to free memory, or REQ_SYNC is set, set, then
+	 * kswapd trying to free memory, or REQ_SYNC is set, then
 	 * it's WB_SYNC_ALL writeback, and we'll use the max limit for
 	 * that. If the write is marked as a background write, then use
 	 * the idle limit, or go to normal if we haven't had competing
@@ -723,8 +722,6 @@ int wbt_init(struct request_queue *q)
 		init_waitqueue_head(&rwb->rq_wait[i].wait);
 	}
 
-	rwb->wc = 1;
-	rwb->queue_depth = RWB_DEF_DEPTH;
 	rwb->last_comp = rwb->last_issue = jiffies;
 	rwb->queue = q;
 	rwb->win_nsec = RWB_WINDOW_NSEC;
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index ff57fb51b338..acb7252c7e81 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -22,6 +22,48 @@ static inline sector_t blk_zone_start(struct request_queue *q,
 }
 
 /*
+ * Return true if a request is a write requests that needs zone write locking.
+ */
+bool blk_req_needs_zone_write_lock(struct request *rq)
+{
+	if (!rq->q->seq_zones_wlock)
+		return false;
+
+	if (blk_rq_is_passthrough(rq))
+		return false;
+
+	switch (req_op(rq)) {
+	case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_WRITE_SAME:
+	case REQ_OP_WRITE:
+		return blk_rq_zone_is_seq(rq);
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock);
+
+void __blk_req_zone_write_lock(struct request *rq)
+{
+	if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq),
+					  rq->q->seq_zones_wlock)))
+		return;
+
+	WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
+	rq->rq_flags |= RQF_ZONE_WRITE_LOCKED;
+}
+EXPORT_SYMBOL_GPL(__blk_req_zone_write_lock);
+
+void __blk_req_zone_write_unlock(struct request *rq)
+{
+	rq->rq_flags &= ~RQF_ZONE_WRITE_LOCKED;
+	if (rq->q->seq_zones_wlock)
+		WARN_ON_ONCE(!test_and_clear_bit(blk_rq_zone_no(rq),
+						 rq->q->seq_zones_wlock));
+}
+EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);
+
+/*
  * Check that a zone report belongs to the partition.
  * If yes, fix its start sector and write pointer, copy it in the
  * zone information array and return true. Return false otherwise.
diff --git a/block/blk.h b/block/blk.h
index 3f1446937aec..46db5dc83dcb 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -120,33 +120,23 @@ void blk_account_io_completion(struct request *req, unsigned int bytes);
 void blk_account_io_done(struct request *req);
 
 /*
- * Internal atomic flags for request handling
- */
-enum rq_atomic_flags {
-	/*
-	 * Keep these two bits first - not because we depend on the
-	 * value of them, but we do depend on them being in the same
-	 * byte of storage to ensure ordering on writes. Keeping them
-	 * first will achieve that nicely.
-	 */
-	REQ_ATOM_COMPLETE = 0,
-	REQ_ATOM_STARTED,
-
-	REQ_ATOM_POLL_SLEPT,
-};
-
-/*
  * EH timer and IO completion will both attempt to 'grab' the request, make
- * sure that only one of them succeeds
+ * sure that only one of them succeeds. Steal the bottom bit of the
+ * __deadline field for this.
  */
 static inline int blk_mark_rq_complete(struct request *rq)
 {
-	return test_and_set_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
+	return test_and_set_bit(0, &rq->__deadline);
 }
 
 static inline void blk_clear_rq_complete(struct request *rq)
 {
-	clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
+	clear_bit(0, &rq->__deadline);
+}
+
+static inline bool blk_rq_is_complete(struct request *rq)
+{
+	return test_bit(0, &rq->__deadline);
 }
 
 /*
@@ -172,6 +162,9 @@ static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq
 		e->type->ops.sq.elevator_deactivate_req_fn(q, rq);
 }
 
+int elv_register_queue(struct request_queue *q);
+void elv_unregister_queue(struct request_queue *q);
+
 struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);
 
 #ifdef CONFIG_FAIL_IO_TIMEOUT
@@ -246,6 +239,21 @@ static inline void req_set_nomerge(struct request_queue *q, struct request *req)
 }
 
 /*
+ * Steal a bit from this field for legacy IO path atomic IO marking. Note that
+ * setting the deadline clears the bottom bit, potentially clearing the
+ * completed bit. The user has to be OK with this (current ones are fine).
+ */
+static inline void blk_rq_set_deadline(struct request *rq, unsigned long time)
+{
+	rq->__deadline = time & ~0x1UL;
+}
+
+static inline unsigned long blk_rq_deadline(struct request *rq)
+{
+	return rq->__deadline & ~0x1UL;
+}
+
+/*
  * Internal io_context interface
  */
 void get_io_context(struct io_context *ioc);
@@ -330,4 +338,6 @@ static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
 }
 #endif /* CONFIG_BOUNCE */
 
+extern void blk_drain_queue(struct request_queue *q);
+
 #endif /* BLK_INTERNAL_H */
diff --git a/block/bounce.c b/block/bounce.c
index fceb1a96480b..6a3e68292273 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -113,45 +113,50 @@ int init_emergency_isa_pool(void)
 static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
 {
 	unsigned char *vfrom;
-	struct bio_vec tovec, *fromvec = from->bi_io_vec;
+	struct bio_vec tovec, fromvec;
 	struct bvec_iter iter;
+	/*
+	 * The bio of @from is created by bounce, so we can iterate
+	 * its bvec from start to end, but the @from->bi_iter can't be
+	 * trusted because it might be changed by splitting.
+	 */
+	struct bvec_iter from_iter = BVEC_ITER_ALL_INIT;
 
 	bio_for_each_segment(tovec, to, iter) {
-		if (tovec.bv_page != fromvec->bv_page) {
+		fromvec = bio_iter_iovec(from, from_iter);
+		if (tovec.bv_page != fromvec.bv_page) {
 			/*
 			 * fromvec->bv_offset and fromvec->bv_len might have
 			 * been modified by the block layer, so use the original
 			 * copy, bounce_copy_vec already uses tovec->bv_len
 			 */
-			vfrom = page_address(fromvec->bv_page) +
+			vfrom = page_address(fromvec.bv_page) +
 				tovec.bv_offset;
 
 			bounce_copy_vec(&tovec, vfrom);
 			flush_dcache_page(tovec.bv_page);
 		}
-
-		fromvec++;
+		bio_advance_iter(from, &from_iter, tovec.bv_len);
 	}
 }
 
 static void bounce_end_io(struct bio *bio, mempool_t *pool)
 {
 	struct bio *bio_orig = bio->bi_private;
-	struct bio_vec *bvec, *org_vec;
+	struct bio_vec *bvec, orig_vec;
 	int i;
-	int start = bio_orig->bi_iter.bi_idx;
+	struct bvec_iter orig_iter = bio_orig->bi_iter;
 
 	/*
 	 * free up bounce indirect pages used
 	 */
 	bio_for_each_segment_all(bvec, bio, i) {
-		org_vec = bio_orig->bi_io_vec + i + start;
-
-		if (bvec->bv_page == org_vec->bv_page)
-			continue;
-
-		dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
-		mempool_free(bvec->bv_page, pool);
+		orig_vec = bio_iter_iovec(bio_orig, orig_iter);
+		if (bvec->bv_page != orig_vec.bv_page) {
+			dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
+			mempool_free(bvec->bv_page, pool);
+		}
+		bio_advance_iter(bio_orig, &orig_iter, orig_vec.bv_len);
 	}
 
 	bio_orig->bi_status = bio->bi_status;
@@ -200,6 +205,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	unsigned i = 0;
 	bool bounce = false;
 	int sectors = 0;
+	bool passthrough = bio_is_passthrough(*bio_orig);
 
 	bio_for_each_segment(from, *bio_orig, iter) {
 		if (i++ < BIO_MAX_PAGES)
@@ -210,13 +216,14 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	if (!bounce)
 		return;
 
-	if (sectors < bio_sectors(*bio_orig)) {
+	if (!passthrough && sectors < bio_sectors(*bio_orig)) {
 		bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split);
 		bio_chain(bio, *bio_orig);
 		generic_make_request(*bio_orig);
 		*bio_orig = bio;
 	}
-	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, bounce_bio_set);
+	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL :
+			bounce_bio_set);
 
 	bio_for_each_segment_all(to, bio, i) {
 		struct page *page = to->bv_page;
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 15d25ccd51a5..1474153f73e3 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -30,7 +30,7 @@
 
 /**
  * bsg_teardown_job - routine to teardown a bsg job
- * @job: bsg_job that is to be torn down
+ * @kref: kref inside bsg_job that is to be torn down
  */
 static void bsg_teardown_job(struct kref *kref)
 {
@@ -251,6 +251,7 @@ static void bsg_exit_rq(struct request_queue *q, struct request *req)
  * @name: device to give bsg device
  * @job_fn: bsg job handler
  * @dd_job_size: size of LLD data needed for each job
+ * @release: @dev release function
  */
 struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 		bsg_job_fn *job_fn, int dd_job_size,
diff --git a/block/bsg.c b/block/bsg.c
index 452f94f1c5d4..2e2c1e222209 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -32,6 +32,9 @@
 #define BSG_DESCRIPTION	"Block layer SCSI generic (bsg) driver"
 #define BSG_VERSION	"0.4"
 
+#define bsg_dbg(bd, fmt, ...) \
+	pr_debug("%s: " fmt, (bd)->name, ##__VA_ARGS__)
+
 struct bsg_device {
 	struct request_queue *queue;
 	spinlock_t lock;
@@ -55,14 +58,6 @@ enum {
 #define BSG_DEFAULT_CMDS	64
 #define BSG_MAX_DEVS		32768
 
-#undef BSG_DEBUG
-
-#ifdef BSG_DEBUG
-#define dprintk(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ##args)
-#else
-#define dprintk(fmt, args...)
-#endif
-
 static DEFINE_MUTEX(bsg_mutex);
 static DEFINE_IDR(bsg_minor_idr);
 
@@ -123,7 +118,7 @@ static struct bsg_command *bsg_alloc_command(struct bsg_device *bd)
 
 	bc->bd = bd;
 	INIT_LIST_HEAD(&bc->list);
-	dprintk("%s: returning free cmd %p\n", bd->name, bc);
+	bsg_dbg(bd, "returning free cmd %p\n", bc);
 	return bc;
 out:
 	spin_unlock_irq(&bd->lock);
@@ -222,7 +217,8 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t mode)
 	if (!bcd->class_dev)
 		return ERR_PTR(-ENXIO);
 
-	dprintk("map hdr %llx/%u %llx/%u\n", (unsigned long long) hdr->dout_xferp,
+	bsg_dbg(bd, "map hdr %llx/%u %llx/%u\n",
+		(unsigned long long) hdr->dout_xferp,
 		hdr->dout_xfer_len, (unsigned long long) hdr->din_xferp,
 		hdr->din_xfer_len);
 
@@ -299,8 +295,8 @@ static void bsg_rq_end_io(struct request *rq, blk_status_t status)
 	struct bsg_device *bd = bc->bd;
 	unsigned long flags;
 
-	dprintk("%s: finished rq %p bc %p, bio %p\n",
-		bd->name, rq, bc, bc->bio);
+	bsg_dbg(bd, "finished rq %p bc %p, bio %p\n",
+		rq, bc, bc->bio);
 
 	bc->hdr.duration = jiffies_to_msecs(jiffies - bc->hdr.duration);
 
@@ -333,7 +329,7 @@ static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
 	list_add_tail(&bc->list, &bd->busy_list);
 	spin_unlock_irq(&bd->lock);
 
-	dprintk("%s: queueing rq %p, bc %p\n", bd->name, rq, bc);
+	bsg_dbg(bd, "queueing rq %p, bc %p\n", rq, bc);
 
 	rq->end_io_data = bc;
 	blk_execute_rq_nowait(q, NULL, rq, at_head, bsg_rq_end_io);
@@ -379,7 +375,7 @@ static struct bsg_command *bsg_get_done_cmd(struct bsg_device *bd)
 		}
 	} while (1);
 
-	dprintk("%s: returning done %p\n", bd->name, bc);
+	bsg_dbg(bd, "returning done %p\n", bc);
 
 	return bc;
 }
@@ -390,7 +386,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	struct scsi_request *req = scsi_req(rq);
 	int ret = 0;
 
-	dprintk("rq %p bio %p 0x%x\n", rq, bio, req->result);
+	pr_debug("rq %p bio %p 0x%x\n", rq, bio, req->result);
 	/*
 	 * fill in all the output members
 	 */
@@ -469,7 +465,7 @@ static int bsg_complete_all_commands(struct bsg_device *bd)
 	struct bsg_command *bc;
 	int ret, tret;
 
-	dprintk("%s: entered\n", bd->name);
+	bsg_dbg(bd, "entered\n");
 
 	/*
 	 * wait for all commands to complete
@@ -572,7 +568,7 @@ bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	int ret;
 	ssize_t bytes_read;
 
-	dprintk("%s: read %zd bytes\n", bd->name, count);
+	bsg_dbg(bd, "read %zd bytes\n", count);
 
 	bsg_set_block(bd, file);
 
@@ -646,7 +642,7 @@ bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 	ssize_t bytes_written;
 	int ret;
 
-	dprintk("%s: write %zd bytes\n", bd->name, count);
+	bsg_dbg(bd, "write %zd bytes\n", count);
 
 	if (unlikely(uaccess_kernel()))
 		return -EINVAL;
@@ -664,7 +660,7 @@ bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 	if (!bytes_written || err_block_err(ret))
 		bytes_written = ret;
 
-	dprintk("%s: returning %zd\n", bd->name, bytes_written);
+	bsg_dbg(bd, "returning %zd\n", bytes_written);
 	return bytes_written;
 }
 
@@ -717,7 +713,7 @@ static int bsg_put_device(struct bsg_device *bd)
 	hlist_del(&bd->dev_list);
 	mutex_unlock(&bsg_mutex);
 
-	dprintk("%s: tearing down\n", bd->name);
+	bsg_dbg(bd, "tearing down\n");
 
 	/*
 	 * close can always block
@@ -744,9 +740,7 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 					 struct file *file)
 {
 	struct bsg_device *bd;
-#ifdef BSG_DEBUG
 	unsigned char buf[32];
-#endif
 
 	if (!blk_queue_scsi_passthrough(rq)) {
 		WARN_ONCE(true, "Attempt to register a non-SCSI queue\n");
@@ -771,7 +765,7 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 	hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
 
 	strncpy(bd->name, dev_name(rq->bsg_dev.class_dev), sizeof(bd->name) - 1);
-	dprintk("bound to <%s>, max queue %d\n",
+	bsg_dbg(bd, "bound to <%s>, max queue %d\n",
 		format_dev_t(buf, inode->i_rdev), bd->max_queue);
 
 	mutex_unlock(&bsg_mutex);
@@ -845,10 +839,10 @@ static int bsg_release(struct inode *inode, struct file *file)
 	return bsg_put_device(bd);
 }
 
-static unsigned int bsg_poll(struct file *file, poll_table *wait)
+static __poll_t bsg_poll(struct file *file, poll_table *wait)
 {
 	struct bsg_device *bd = file->private_data;
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 
 	poll_wait(file, &bd->wq_done, wait);
 	poll_wait(file, &bd->wq_free, wait);
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index b83f77460d28..9de9f156e203 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -50,8 +50,6 @@ struct deadline_data {
 	int front_merges;
 };
 
-static void deadline_move_request(struct deadline_data *, struct request *);
-
 static inline struct rb_root *
 deadline_rb_root(struct deadline_data *dd, struct request *rq)
 {
@@ -100,6 +98,12 @@ deadline_add_request(struct request_queue *q, struct request *rq)
 	struct deadline_data *dd = q->elevator->elevator_data;
 	const int data_dir = rq_data_dir(rq);
 
+	/*
+	 * This may be a requeue of a write request that has locked its
+	 * target zone. If it is the case, this releases the zone lock.
+	 */
+	blk_req_zone_write_unlock(rq);
+
 	deadline_add_rq_rb(dd, rq);
 
 	/*
@@ -190,6 +194,12 @@ deadline_move_to_dispatch(struct deadline_data *dd, struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
+	/*
+	 * For a zoned block device, write requests must write lock their
+	 * target zone.
+	 */
+	blk_req_zone_write_lock(rq);
+
 	deadline_remove_request(q, rq);
 	elv_dispatch_add_tail(q, rq);
 }
@@ -231,6 +241,69 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
 }
 
 /*
+ * For the specified data direction, return the next request to dispatch using
+ * arrival ordered lists.
+ */
+static struct request *
+deadline_fifo_request(struct deadline_data *dd, int data_dir)
+{
+	struct request *rq;
+
+	if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE))
+		return NULL;
+
+	if (list_empty(&dd->fifo_list[data_dir]))
+		return NULL;
+
+	rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+	if (data_dir == READ || !blk_queue_is_zoned(rq->q))
+		return rq;
+
+	/*
+	 * Look for a write request that can be dispatched, that is one with
+	 * an unlocked target zone.
+	 */
+	list_for_each_entry(rq, &dd->fifo_list[WRITE], queuelist) {
+		if (blk_req_can_dispatch_to_zone(rq))
+			return rq;
+	}
+
+	return NULL;
+}
+
+/*
+ * For the specified data direction, return the next request to dispatch using
+ * sector position sorted lists.
+ */
+static struct request *
+deadline_next_request(struct deadline_data *dd, int data_dir)
+{
+	struct request *rq;
+
+	if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE))
+		return NULL;
+
+	rq = dd->next_rq[data_dir];
+	if (!rq)
+		return NULL;
+
+	if (data_dir == READ || !blk_queue_is_zoned(rq->q))
+		return rq;
+
+	/*
+	 * Look for a write request that can be dispatched, that is one with
+	 * an unlocked target zone.
+	 */
+	while (rq) {
+		if (blk_req_can_dispatch_to_zone(rq))
+			return rq;
+		rq = deadline_latter_request(rq);
+	}
+
+	return NULL;
+}
+
+/*
  * deadline_dispatch_requests selects the best request according to
  * read/write expire, fifo_batch, etc
  */
@@ -239,16 +312,15 @@ static int deadline_dispatch_requests(struct request_queue *q, int force)
 	struct deadline_data *dd = q->elevator->elevator_data;
 	const int reads = !list_empty(&dd->fifo_list[READ]);
 	const int writes = !list_empty(&dd->fifo_list[WRITE]);
-	struct request *rq;
+	struct request *rq, *next_rq;
 	int data_dir;
 
 	/*
 	 * batches are currently reads XOR writes
 	 */
-	if (dd->next_rq[WRITE])
-		rq = dd->next_rq[WRITE];
-	else
-		rq = dd->next_rq[READ];
+	rq = deadline_next_request(dd, WRITE);
+	if (!rq)
+		rq = deadline_next_request(dd, READ);
 
 	if (rq && dd->batching < dd->fifo_batch)
 		/* we have a next request are still entitled to batch */
@@ -262,7 +334,8 @@ static int deadline_dispatch_requests(struct request_queue *q, int force)
 	if (reads) {
 		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ]));
 
-		if (writes && (dd->starved++ >= dd->writes_starved))
+		if (deadline_fifo_request(dd, WRITE) &&
+		    (dd->starved++ >= dd->writes_starved))
 			goto dispatch_writes;
 
 		data_dir = READ;
@@ -291,21 +364,29 @@ dispatch_find_request:
 	/*
 	 * we are not running a batch, find best request for selected data_dir
 	 */
-	if (deadline_check_fifo(dd, data_dir) || !dd->next_rq[data_dir]) {
+	next_rq = deadline_next_request(dd, data_dir);
+	if (deadline_check_fifo(dd, data_dir) || !next_rq) {
 		/*
 		 * A deadline has expired, the last request was in the other
 		 * direction, or we have run out of higher-sectored requests.
 		 * Start again from the request with the earliest expiry time.
 		 */
-		rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+		rq = deadline_fifo_request(dd, data_dir);
 	} else {
 		/*
 		 * The last req was the same dir and we have a next request in
 		 * sort order. No expired requests so continue on from here.
 		 */
-		rq = dd->next_rq[data_dir];
+		rq = next_rq;
 	}
 
+	/*
+	 * For a zoned block device, if we only have writes queued and none of
+	 * them can be dispatched, rq will be NULL.
+	 */
+	if (!rq)
+		return 0;
+
 	dd->batching = 0;
 
 dispatch_request:
@@ -318,6 +399,16 @@ dispatch_request:
 	return 1;
 }
 
+/*
+ * For zoned block devices, write unlock the target zone of completed
+ * write requests.
+ */
+static void
+deadline_completed_request(struct request_queue *q, struct request *rq)
+{
+	blk_req_zone_write_unlock(rq);
+}
+
 static void deadline_exit_queue(struct elevator_queue *e)
 {
 	struct deadline_data *dd = e->elevator_data;
@@ -439,6 +530,7 @@ static struct elevator_type iosched_deadline = {
 		.elevator_merged_fn =		deadline_merged_request,
 		.elevator_merge_req_fn =	deadline_merged_requests,
 		.elevator_dispatch_fn =		deadline_dispatch_requests,
+		.elevator_completed_req_fn =	deadline_completed_request,
 		.elevator_add_req_fn =		deadline_add_request,
 		.elevator_former_req_fn =	elv_rb_former_request,
 		.elevator_latter_req_fn =	elv_rb_latter_request,
diff --git a/block/elevator.c b/block/elevator.c
index 7bda083d5968..e87e9b43aba0 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -869,6 +869,8 @@ int elv_register_queue(struct request_queue *q)
 	struct elevator_queue *e = q->elevator;
 	int error;
 
+	lockdep_assert_held(&q->sysfs_lock);
+
 	error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
 	if (!error) {
 		struct elv_fs_entry *attr = e->type->elevator_attrs;
@@ -886,10 +888,11 @@ int elv_register_queue(struct request_queue *q)
 	}
 	return error;
 }
-EXPORT_SYMBOL(elv_register_queue);
 
 void elv_unregister_queue(struct request_queue *q)
 {
+	lockdep_assert_held(&q->sysfs_lock);
+
 	if (q) {
 		struct elevator_queue *e = q->elevator;
 
@@ -900,7 +903,6 @@ void elv_unregister_queue(struct request_queue *q)
 		wbt_enable_default(q);
 	}
 }
-EXPORT_SYMBOL(elv_unregister_queue);
 
 int elv_register(struct elevator_type *e)
 {
@@ -967,7 +969,10 @@ static int elevator_switch_mq(struct request_queue *q,
 {
 	int ret;
 
+	lockdep_assert_held(&q->sysfs_lock);
+
 	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue(q);
 
 	if (q->elevator) {
 		if (q->elevator->registered)
@@ -994,6 +999,7 @@ static int elevator_switch_mq(struct request_queue *q,
 		blk_add_trace_msg(q, "elv switch: none");
 
 out:
+	blk_mq_unquiesce_queue(q);
 	blk_mq_unfreeze_queue(q);
 	return ret;
 }
@@ -1010,6 +1016,8 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	bool old_registered = false;
 	int err;
 
+	lockdep_assert_held(&q->sysfs_lock);
+
 	if (q->mq_ops)
 		return elevator_switch_mq(q, new_e);
 
diff --git a/block/genhd.c b/block/genhd.c
index c2223f12a805..88a53c188cb7 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -629,16 +629,18 @@ exit:
 }
 
 /**
- * device_add_disk - add partitioning information to kernel list
+ * __device_add_disk - add disk information to kernel list
  * @parent: parent device for the disk
  * @disk: per-device partitioning information
+ * @register_queue: register the queue if set to true
  *
  * This function registers the partitioning information in @disk
  * with the kernel.
  *
  * FIXME: error handling
  */
-void device_add_disk(struct device *parent, struct gendisk *disk)
+static void __device_add_disk(struct device *parent, struct gendisk *disk,
+			      bool register_queue)
 {
 	dev_t devt;
 	int retval;
@@ -671,15 +673,19 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
 		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
 		disk->flags |= GENHD_FL_NO_PART_SCAN;
 	} else {
+		int ret;
+
 		/* Register BDI before referencing it from bdev */
 		disk_to_dev(disk)->devt = devt;
-		bdi_register_owner(disk->queue->backing_dev_info,
-				disk_to_dev(disk));
+		ret = bdi_register_owner(disk->queue->backing_dev_info,
+						disk_to_dev(disk));
+		WARN_ON(ret);
 		blk_register_region(disk_devt(disk), disk->minors, NULL,
 				    exact_match, exact_lock, disk);
 	}
 	register_disk(parent, disk);
-	blk_register_queue(disk);
+	if (register_queue)
+		blk_register_queue(disk);
 
 	/*
 	 * Take an extra ref on queue which will be put on disk_release()
@@ -690,8 +696,19 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
 	disk_add_events(disk);
 	blk_integrity_add(disk);
 }
+
+void device_add_disk(struct device *parent, struct gendisk *disk)
+{
+	__device_add_disk(parent, disk, true);
+}
 EXPORT_SYMBOL(device_add_disk);
 
+void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk)
+{
+	__device_add_disk(parent, disk, false);
+}
+EXPORT_SYMBOL(device_add_disk_no_queue_reg);
+
 void del_gendisk(struct gendisk *disk)
 {
 	struct disk_part_iter piter;
@@ -722,7 +739,8 @@ void del_gendisk(struct gendisk *disk)
 		 * Unregister bdi before releasing device numbers (as they can
 		 * get reused and we'd get clashes in sysfs).
 		 */
-		bdi_unregister(disk->queue->backing_dev_info);
+		if (!(disk->flags & GENHD_FL_HIDDEN))
+			bdi_unregister(disk->queue->backing_dev_info);
 		blk_unregister_queue(disk);
 	} else {
 		WARN_ON(1);
@@ -1389,7 +1407,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 
 	if (minors > DISK_MAX_PARTS) {
 		printk(KERN_ERR
-			"block: can't allocated more than %d partitions\n",
+			"block: can't allocate more than %d partitions\n",
 			DISK_MAX_PARTS);
 		minors = DISK_MAX_PARTS;
 	}
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index b4df317c2916..f95c60774ce8 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -100,9 +100,13 @@ struct kyber_hctx_data {
 	unsigned int cur_domain;
 	unsigned int batching;
 	wait_queue_entry_t domain_wait[KYBER_NUM_DOMAINS];
+	struct sbq_wait_state *domain_ws[KYBER_NUM_DOMAINS];
 	atomic_t wait_index[KYBER_NUM_DOMAINS];
 };
 
+static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
+			     void *key);
+
 static int rq_sched_domain(const struct request *rq)
 {
 	unsigned int op = rq->cmd_flags;
@@ -385,6 +389,9 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 
 	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
 		INIT_LIST_HEAD(&khd->rqs[i]);
+		init_waitqueue_func_entry(&khd->domain_wait[i],
+					  kyber_domain_wake);
+		khd->domain_wait[i].private = hctx;
 		INIT_LIST_HEAD(&khd->domain_wait[i].entry);
 		atomic_set(&khd->wait_index[i], 0);
 	}
@@ -524,35 +531,39 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd,
 	int nr;
 
 	nr = __sbitmap_queue_get(domain_tokens);
-	if (nr >= 0)
-		return nr;
 
 	/*
 	 * If we failed to get a domain token, make sure the hardware queue is
 	 * run when one becomes available. Note that this is serialized on
 	 * khd->lock, but we still need to be careful about the waker.
 	 */
-	if (list_empty_careful(&wait->entry)) {
-		init_waitqueue_func_entry(wait, kyber_domain_wake);
-		wait->private = hctx;
+	if (nr < 0 && list_empty_careful(&wait->entry)) {
 		ws = sbq_wait_ptr(domain_tokens,
 				  &khd->wait_index[sched_domain]);
+		khd->domain_ws[sched_domain] = ws;
 		add_wait_queue(&ws->wait, wait);
 
 		/*
 		 * Try again in case a token was freed before we got on the wait
-		 * queue. The waker may have already removed the entry from the
-		 * wait queue, but list_del_init() is okay with that.
+		 * queue.
 		 */
 		nr = __sbitmap_queue_get(domain_tokens);
-		if (nr >= 0) {
-			unsigned long flags;
+	}
 
-			spin_lock_irqsave(&ws->wait.lock, flags);
-			list_del_init(&wait->entry);
-			spin_unlock_irqrestore(&ws->wait.lock, flags);
-		}
+	/*
+	 * If we got a token while we were on the wait queue, remove ourselves
+	 * from the wait queue to ensure that all wake ups make forward
+	 * progress. It's possible that the waker already deleted the entry
+	 * between the !list_empty_careful() check and us grabbing the lock, but
+	 * list_del_init() is okay with that.
+	 */
+	if (nr >= 0 && !list_empty_careful(&wait->entry)) {
+		ws = khd->domain_ws[sched_domain];
+		spin_lock_irq(&ws->wait.lock);
+		list_del_init(&wait->entry);
+		spin_unlock_irq(&ws->wait.lock);
 	}
+
 	return nr;
 }
 
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 0179e484ec98..c56f211c8440 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -59,6 +59,7 @@ struct deadline_data {
 	int front_merges;
 
 	spinlock_t lock;
+	spinlock_t zone_lock;
 	struct list_head dispatch;
 };
 
@@ -192,13 +193,83 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
 }
 
 /*
+ * For the specified data direction, return the next request to
+ * dispatch using arrival ordered lists.
+ */
+static struct request *
+deadline_fifo_request(struct deadline_data *dd, int data_dir)
+{
+	struct request *rq;
+	unsigned long flags;
+
+	if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE))
+		return NULL;
+
+	if (list_empty(&dd->fifo_list[data_dir]))
+		return NULL;
+
+	rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+	if (data_dir == READ || !blk_queue_is_zoned(rq->q))
+		return rq;
+
+	/*
+	 * Look for a write request that can be dispatched, that is one with
+	 * an unlocked target zone.
+	 */
+	spin_lock_irqsave(&dd->zone_lock, flags);
+	list_for_each_entry(rq, &dd->fifo_list[WRITE], queuelist) {
+		if (blk_req_can_dispatch_to_zone(rq))
+			goto out;
+	}
+	rq = NULL;
+out:
+	spin_unlock_irqrestore(&dd->zone_lock, flags);
+
+	return rq;
+}
+
+/*
+ * For the specified data direction, return the next request to
+ * dispatch using sector position sorted lists.
+ */
+static struct request *
+deadline_next_request(struct deadline_data *dd, int data_dir)
+{
+	struct request *rq;
+	unsigned long flags;
+
+	if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE))
+		return NULL;
+
+	rq = dd->next_rq[data_dir];
+	if (!rq)
+		return NULL;
+
+	if (data_dir == READ || !blk_queue_is_zoned(rq->q))
+		return rq;
+
+	/*
+	 * Look for a write request that can be dispatched, that is one with
+	 * an unlocked target zone.
+	 */
+	spin_lock_irqsave(&dd->zone_lock, flags);
+	while (rq) {
+		if (blk_req_can_dispatch_to_zone(rq))
+			break;
+		rq = deadline_latter_request(rq);
+	}
+	spin_unlock_irqrestore(&dd->zone_lock, flags);
+
+	return rq;
+}
+
+/*
  * deadline_dispatch_requests selects the best request according to
  * read/write expire, fifo_batch, etc
  */
-static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
+static struct request *__dd_dispatch_request(struct deadline_data *dd)
 {
-	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
-	struct request *rq;
+	struct request *rq, *next_rq;
 	bool reads, writes;
 	int data_dir;
 
@@ -214,10 +285,9 @@ static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	/*
 	 * batches are currently reads XOR writes
 	 */
-	if (dd->next_rq[WRITE])
-		rq = dd->next_rq[WRITE];
-	else
-		rq = dd->next_rq[READ];
+	rq = deadline_next_request(dd, WRITE);
+	if (!rq)
+		rq = deadline_next_request(dd, READ);
 
 	if (rq && dd->batching < dd->fifo_batch)
 		/* we have a next request are still entitled to batch */
@@ -231,7 +301,8 @@ static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	if (reads) {
 		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ]));
 
-		if (writes && (dd->starved++ >= dd->writes_starved))
+		if (deadline_fifo_request(dd, WRITE) &&
+		    (dd->starved++ >= dd->writes_starved))
 			goto dispatch_writes;
 
 		data_dir = READ;
@@ -260,21 +331,29 @@ dispatch_find_request:
 	/*
 	 * we are not running a batch, find best request for selected data_dir
 	 */
-	if (deadline_check_fifo(dd, data_dir) || !dd->next_rq[data_dir]) {
+	next_rq = deadline_next_request(dd, data_dir);
+	if (deadline_check_fifo(dd, data_dir) || !next_rq) {
 		/*
 		 * A deadline has expired, the last request was in the other
 		 * direction, or we have run out of higher-sectored requests.
 		 * Start again from the request with the earliest expiry time.
 		 */
-		rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+		rq = deadline_fifo_request(dd, data_dir);
 	} else {
 		/*
 		 * The last req was the same dir and we have a next request in
 		 * sort order. No expired requests so continue on from here.
 		 */
-		rq = dd->next_rq[data_dir];
+		rq = next_rq;
 	}
 
+	/*
+	 * For a zoned block device, if we only have writes queued and none of
+	 * them can be dispatched, rq will be NULL.
+	 */
+	if (!rq)
+		return NULL;
+
 	dd->batching = 0;
 
 dispatch_request:
@@ -284,17 +363,27 @@ dispatch_request:
 	dd->batching++;
 	deadline_move_request(dd, rq);
 done:
+	/*
+	 * If the request needs its target zone locked, do it.
+	 */
+	blk_req_zone_write_lock(rq);
 	rq->rq_flags |= RQF_STARTED;
 	return rq;
 }
 
+/*
+ * One confusing aspect here is that we get called for a specific
+ * hardware queue, but we return a request that may not be for a
+ * different hardware queue. This is because mq-deadline has shared
+ * state for all hardware queues, in terms of sorting, FIFOs, etc.
+ */
 static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 {
 	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
 	struct request *rq;
 
 	spin_lock(&dd->lock);
-	rq = __dd_dispatch_request(hctx);
+	rq = __dd_dispatch_request(dd);
 	spin_unlock(&dd->lock);
 
 	return rq;
@@ -339,6 +428,7 @@ static int dd_init_queue(struct request_queue *q, struct elevator_type *e)
 	dd->front_merges = 1;
 	dd->fifo_batch = fifo_batch;
 	spin_lock_init(&dd->lock);
+	spin_lock_init(&dd->zone_lock);
 	INIT_LIST_HEAD(&dd->dispatch);
 
 	q->elevator = eq;
@@ -395,6 +485,12 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	struct deadline_data *dd = q->elevator->elevator_data;
 	const int data_dir = rq_data_dir(rq);
 
+	/*
+	 * This may be a requeue of a write request that has locked its
+	 * target zone. If it is the case, this releases the zone lock.
+	 */
+	blk_req_zone_write_unlock(rq);
+
 	if (blk_mq_sched_try_insert_merge(q, rq))
 		return;
 
@@ -439,6 +535,26 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 	spin_unlock(&dd->lock);
 }
 
+/*
+ * For zoned block devices, write unlock the target zone of
+ * completed write requests. Do this while holding the zone lock
+ * spinlock so that the zone is never unlocked while deadline_fifo_request()
+ * while deadline_next_request() are executing.
+ */
+static void dd_completed_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+
+	if (blk_queue_is_zoned(q)) {
+		struct deadline_data *dd = q->elevator->elevator_data;
+		unsigned long flags;
+
+		spin_lock_irqsave(&dd->zone_lock, flags);
+		blk_req_zone_write_unlock(rq);
+		spin_unlock_irqrestore(&dd->zone_lock, flags);
+	}
+}
+
 static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
@@ -640,6 +756,7 @@ static struct elevator_type mq_deadline = {
 	.ops.mq = {
 		.insert_requests	= dd_insert_requests,
 		.dispatch_request	= dd_dispatch_request,
+		.completed_request	= dd_completed_request,
 		.next_request		= elv_rb_latter_request,
 		.former_request		= elv_rb_former_request,
 		.bio_merge		= dd_bio_merge,
diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c
index 0af3a3db6fb0..82c44f7df911 100644
--- a/block/partitions/msdos.c
+++ b/block/partitions/msdos.c
@@ -301,7 +301,9 @@ static void parse_bsd(struct parsed_partitions *state,
 			continue;
 		bsd_start = le32_to_cpu(p->p_offset);
 		bsd_size = le32_to_cpu(p->p_size);
-		if (memcmp(flavour, "bsd\0", 4) == 0)
+		/* FreeBSD has relative offset if C partition offset is zero */
+		if (memcmp(flavour, "bsd\0", 4) == 0 &&
+		    le32_to_cpu(l->d_partitions[2].p_offset) == 0)
 			bsd_start += offset;
 		if (offset == bsd_start && size == bsd_size)
 			/* full parent partition, we have it already */
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index edcfff974527..60b471f8621b 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -384,9 +384,10 @@ out_put_request:
 
 /**
  * sg_scsi_ioctl  --  handle deprecated SCSI_IOCTL_SEND_COMMAND ioctl
- * @file:	file this ioctl operates on (optional)
  * @q:		request queue to send scsi commands down
  * @disk:	gendisk to operate on (option)
+ * @mode:	mode used to open the file through which the ioctl has been
+ *		submitted
  * @sic:	userspace structure describing the command to perform
  *
  * Send down the scsi command described by @sic to the device below
@@ -415,10 +416,10 @@ out_put_request:
  *      Positive numbers returned are the compacted SCSI error codes (4
  *      bytes in one int) where the lowest byte is the SCSI status.
  */
-#define OMAX_SB_LEN 16          /* For backward compatibility */
 int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		struct scsi_ioctl_command __user *sic)
 {
+	enum { OMAX_SB_LEN = 16 };	/* For backward compatibility */
 	struct request *rq;
 	struct scsi_request *req;
 	int err;
@@ -692,38 +693,9 @@ int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd)
 	if (bd && bd == bd->bd_contains)
 		return 0;
 
-	/* Actually none of these is particularly useful on a partition,
-	 * but they are safe.
-	 */
-	switch (cmd) {
-	case SCSI_IOCTL_GET_IDLUN:
-	case SCSI_IOCTL_GET_BUS_NUMBER:
-	case SCSI_IOCTL_GET_PCI:
-	case SCSI_IOCTL_PROBE_HOST:
-	case SG_GET_VERSION_NUM:
-	case SG_SET_TIMEOUT:
-	case SG_GET_TIMEOUT:
-	case SG_GET_RESERVED_SIZE:
-	case SG_SET_RESERVED_SIZE:
-	case SG_EMULATED_HOST:
-		return 0;
-	case CDROM_GET_CAPABILITY:
-		/* Keep this until we remove the printk below.  udev sends it
-		 * and we do not want to spam dmesg about it.   CD-ROMs do
-		 * not have partitions, so we get here only for disks.
-		 */
-		return -ENOIOCTLCMD;
-	default:
-		break;
-	}
-
 	if (capable(CAP_SYS_RAWIO))
 		return 0;
 
-	/* In particular, rule out all resets and host-specific ioctls.  */
-	printk_ratelimited(KERN_WARNING
-			   "%s: sending ioctl %x to a partition!\n", current->comm, cmd);
-
 	return -ENOIOCTLCMD;
 }
 EXPORT_SYMBOL(scsi_verify_blk_ioctl);
diff --git a/crypto/Kconfig b/crypto/Kconfig
index f7911963bb79..b75264b09a46 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -106,6 +106,7 @@ config CRYPTO_KPP
 config CRYPTO_ACOMP2
 	tristate
 	select CRYPTO_ALGAPI2
+	select SGL_ALLOC
 
 config CRYPTO_ACOMP
 	tristate
@@ -130,7 +131,7 @@ config CRYPTO_DH
 
 config CRYPTO_ECDH
 	tristate "ECDH algorithm"
-	select CRYTPO_KPP
+	select CRYPTO_KPP
 	select CRYPTO_RNG_DEFAULT
 	help
 	  Generic implementation of the ECDH algorithm
@@ -1339,6 +1340,7 @@ config CRYPTO_SALSA20_586
 	tristate "Salsa20 stream cipher algorithm (i586)"
 	depends on (X86 || UML_X86) && !64BIT
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_SALSA20
 	help
 	  Salsa20 stream cipher algorithm.
 
@@ -1352,6 +1354,7 @@ config CRYPTO_SALSA20_X86_64
 	tristate "Salsa20 stream cipher algorithm (x86_64)"
 	depends on (X86 || UML_X86) && 64BIT
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_SALSA20
 	help
 	  Salsa20 stream cipher algorithm.
 
diff --git a/crypto/Makefile b/crypto/Makefile
index d674884b2d51..cdbc03b35510 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -99,6 +99,7 @@ obj-$(CONFIG_CRYPTO_TWOFISH_COMMON) += twofish_common.o
 obj-$(CONFIG_CRYPTO_SERPENT) += serpent_generic.o
 CFLAGS_serpent_generic.o := $(call cc-option,-fsched-pressure)  # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149
 obj-$(CONFIG_CRYPTO_AES) += aes_generic.o
+CFLAGS_aes_generic.o := $(call cc-option,-fno-code-hoisting) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83356
 obj-$(CONFIG_CRYPTO_AES_TI) += aes_ti.o
 obj-$(CONFIG_CRYPTO_CAMELLIA) += camellia_generic.o
 obj-$(CONFIG_CRYPTO_CAST_COMMON) += cast_common.o
diff --git a/crypto/ablk_helper.c b/crypto/ablk_helper.c
index 1441f07d0a19..09776bb1360e 100644
--- a/crypto/ablk_helper.c
+++ b/crypto/ablk_helper.c
@@ -18,9 +18,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
- * USA
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  *
  */
 
@@ -28,7 +26,6 @@
 #include <linux/crypto.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/hardirq.h>
 #include <crypto/algapi.h>
 #include <crypto/cryptd.h>
 #include <crypto/ablk_helper.h>
diff --git a/crypto/aead.c b/crypto/aead.c
index f794b30a9407..60b3bbe973e7 100644
--- a/crypto/aead.c
+++ b/crypto/aead.c
@@ -54,11 +54,18 @@ int crypto_aead_setkey(struct crypto_aead *tfm,
 		       const u8 *key, unsigned int keylen)
 {
 	unsigned long alignmask = crypto_aead_alignmask(tfm);
+	int err;
 
 	if ((unsigned long)key & alignmask)
-		return setkey_unaligned(tfm, key, keylen);
+		err = setkey_unaligned(tfm, key, keylen);
+	else
+		err = crypto_aead_alg(tfm)->setkey(tfm, key, keylen);
+
+	if (err)
+		return err;
 
-	return crypto_aead_alg(tfm)->setkey(tfm, key, keylen);
+	crypto_aead_clear_flags(tfm, CRYPTO_TFM_NEED_KEY);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(crypto_aead_setkey);
 
@@ -93,6 +100,8 @@ static int crypto_aead_init_tfm(struct crypto_tfm *tfm)
 	struct crypto_aead *aead = __crypto_aead_cast(tfm);
 	struct aead_alg *alg = crypto_aead_alg(aead);
 
+	crypto_aead_set_flags(aead, CRYPTO_TFM_NEED_KEY);
+
 	aead->authsize = alg->maxauthsize;
 
 	if (alg->exit)
@@ -295,7 +304,7 @@ int aead_init_geniv(struct crypto_aead *aead)
 	if (err)
 		goto out;
 
-	ctx->sknull = crypto_get_default_null_skcipher2();
+	ctx->sknull = crypto_get_default_null_skcipher();
 	err = PTR_ERR(ctx->sknull);
 	if (IS_ERR(ctx->sknull))
 		goto out;
@@ -315,7 +324,7 @@ out:
 	return err;
 
 drop_null:
-	crypto_put_default_null_skcipher2();
+	crypto_put_default_null_skcipher();
 	goto out;
 }
 EXPORT_SYMBOL_GPL(aead_init_geniv);
@@ -325,7 +334,7 @@ void aead_exit_geniv(struct crypto_aead *tfm)
 	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
-	crypto_put_default_null_skcipher2();
+	crypto_put_default_null_skcipher();
 }
 EXPORT_SYMBOL_GPL(aead_exit_geniv);
 
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 85cea9de324a..0f8d8d5523c3 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -150,7 +150,7 @@ EXPORT_SYMBOL_GPL(af_alg_release_parent);
 
 static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
-	const u32 forbidden = CRYPTO_ALG_INTERNAL;
+	const u32 allowed = CRYPTO_ALG_KERN_DRIVER_ONLY;
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct sockaddr_alg *sa = (void *)uaddr;
@@ -158,6 +158,10 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	void *private;
 	int err;
 
+	/* If caller uses non-allowed flag, return error. */
+	if ((sa->salg_feat & ~allowed) || (sa->salg_mask & ~allowed))
+		return -EINVAL;
+
 	if (sock->state == SS_CONNECTED)
 		return -EINVAL;
 
@@ -176,9 +180,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (IS_ERR(type))
 		return PTR_ERR(type);
 
-	private = type->bind(sa->salg_name,
-			     sa->salg_feat & ~forbidden,
-			     sa->salg_mask & ~forbidden);
+	private = type->bind(sa->salg_name, sa->salg_feat, sa->salg_mask);
 	if (IS_ERR(private)) {
 		module_put(type->owner);
 		return PTR_ERR(private);
@@ -664,7 +666,7 @@ void af_alg_free_areq_sgls(struct af_alg_async_req *areq)
 	unsigned int i;
 
 	list_for_each_entry_safe(rsgl, tmp, &areq->rsgl_list, list) {
-		ctx->rcvused -= rsgl->sg_num_bytes;
+		atomic_sub(rsgl->sg_num_bytes, &ctx->rcvused);
 		af_alg_free_sg(&rsgl->sgl);
 		list_del(&rsgl->list);
 		if (rsgl != &areq->first_rsgl)
@@ -672,14 +674,15 @@ void af_alg_free_areq_sgls(struct af_alg_async_req *areq)
 	}
 
 	tsgl = areq->tsgl;
-	for_each_sg(tsgl, sg, areq->tsgl_entries, i) {
-		if (!sg_page(sg))
-			continue;
-		put_page(sg_page(sg));
-	}
+	if (tsgl) {
+		for_each_sg(tsgl, sg, areq->tsgl_entries, i) {
+			if (!sg_page(sg))
+				continue;
+			put_page(sg_page(sg));
+		}
 
-	if (areq->tsgl && areq->tsgl_entries)
 		sock_kfree_s(sk, tsgl, areq->tsgl_entries * sizeof(*tsgl));
+	}
 }
 EXPORT_SYMBOL_GPL(af_alg_free_areq_sgls);
 
@@ -1021,6 +1024,18 @@ unlock:
 EXPORT_SYMBOL_GPL(af_alg_sendpage);
 
 /**
+ * af_alg_free_resources - release resources required for crypto request
+ */
+void af_alg_free_resources(struct af_alg_async_req *areq)
+{
+	struct sock *sk = areq->sk;
+
+	af_alg_free_areq_sgls(areq);
+	sock_kfree_s(sk, areq, areq->areqlen);
+}
+EXPORT_SYMBOL_GPL(af_alg_free_resources);
+
+/**
  * af_alg_async_cb - AIO callback handler
  *
  * This handler cleans up the struct af_alg_async_req upon completion of the
@@ -1036,31 +1051,26 @@ void af_alg_async_cb(struct crypto_async_request *_req, int err)
 	struct kiocb *iocb = areq->iocb;
 	unsigned int resultlen;
 
-	lock_sock(sk);
-
 	/* Buffer size written by crypto operation. */
 	resultlen = areq->outlen;
 
-	af_alg_free_areq_sgls(areq);
-	sock_kfree_s(sk, areq, areq->areqlen);
-	__sock_put(sk);
+	af_alg_free_resources(areq);
+	sock_put(sk);
 
 	iocb->ki_complete(iocb, err ? err : resultlen, 0);
-
-	release_sock(sk);
 }
 EXPORT_SYMBOL_GPL(af_alg_async_cb);
 
 /**
  * af_alg_poll - poll system call handler
  */
-unsigned int af_alg_poll(struct file *file, struct socket *sock,
+__poll_t af_alg_poll(struct file *file, struct socket *sock,
 			 poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct af_alg_ctx *ctx = ask->private;
-	unsigned int mask;
+	__poll_t mask;
 
 	sock_poll_wait(file, sk_sleep(sk), wait);
 	mask = 0;
@@ -1130,12 +1140,6 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
 		if (!af_alg_readable(sk))
 			break;
 
-		if (!ctx->used) {
-			err = af_alg_wait_for_data(sk, flags);
-			if (err)
-				return err;
-		}
-
 		seglen = min_t(size_t, (maxsize - len),
 			       msg_data_left(msg));
 
@@ -1161,7 +1165,7 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
 
 		areq->last_rsgl = rsgl;
 		len += err;
-		ctx->rcvused += err;
+		atomic_add(err, &ctx->rcvused);
 		rsgl->sg_num_bytes = err;
 		iov_iter_advance(&msg->msg_iter, err);
 	}
diff --git a/crypto/ahash.c b/crypto/ahash.c
index 3a35d67de7d9..266fc1d64f61 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -193,11 +193,18 @@ int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key,
 			unsigned int keylen)
 {
 	unsigned long alignmask = crypto_ahash_alignmask(tfm);
+	int err;
 
 	if ((unsigned long)key & alignmask)
-		return ahash_setkey_unaligned(tfm, key, keylen);
+		err = ahash_setkey_unaligned(tfm, key, keylen);
+	else
+		err = tfm->setkey(tfm, key, keylen);
+
+	if (err)
+		return err;
 
-	return tfm->setkey(tfm, key, keylen);
+	crypto_ahash_clear_flags(tfm, CRYPTO_TFM_NEED_KEY);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(crypto_ahash_setkey);
 
@@ -368,7 +375,12 @@ EXPORT_SYMBOL_GPL(crypto_ahash_finup);
 
 int crypto_ahash_digest(struct ahash_request *req)
 {
-	return crypto_ahash_op(req, crypto_ahash_reqtfm(req)->digest);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+
+	if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
+		return -ENOKEY;
+
+	return crypto_ahash_op(req, tfm->digest);
 }
 EXPORT_SYMBOL_GPL(crypto_ahash_digest);
 
@@ -450,7 +462,6 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm)
 	struct ahash_alg *alg = crypto_ahash_alg(hash);
 
 	hash->setkey = ahash_nosetkey;
-	hash->has_setkey = false;
 	hash->export = ahash_no_export;
 	hash->import = ahash_no_import;
 
@@ -465,7 +476,8 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm)
 
 	if (alg->setkey) {
 		hash->setkey = alg->setkey;
-		hash->has_setkey = true;
+		if (!(alg->halg.base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY))
+			crypto_ahash_set_flags(hash, CRYPTO_TFM_NEED_KEY);
 	}
 	if (alg->export)
 		hash->export = alg->export;
@@ -649,5 +661,16 @@ struct hash_alg_common *ahash_attr_alg(struct rtattr *rta, u32 type, u32 mask)
 }
 EXPORT_SYMBOL_GPL(ahash_attr_alg);
 
+bool crypto_hash_alg_has_setkey(struct hash_alg_common *halg)
+{
+	struct crypto_alg *alg = &halg->base;
+
+	if (alg->cra_type != &crypto_ahash_type)
+		return crypto_shash_alg_has_setkey(__crypto_shash_alg(alg));
+
+	return __crypto_ahash_alg(alg)->setkey != NULL;
+}
+EXPORT_SYMBOL_GPL(crypto_hash_alg_has_setkey);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Asynchronous cryptographic hash type");
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 60d7366ed343..395b082d03a9 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -62,7 +62,7 @@ static int crypto_check_alg(struct crypto_alg *alg)
 	if (alg->cra_priority < 0)
 		return -EINVAL;
 
-	atomic_set(&alg->cra_refcnt, 1);
+	refcount_set(&alg->cra_refcnt, 1);
 
 	return crypto_set_driver_name(alg);
 }
@@ -123,7 +123,6 @@ static void crypto_remove_instance(struct crypto_instance *inst,
 	if (!tmpl || !crypto_tmpl_get(tmpl))
 		return;
 
-	crypto_notify(CRYPTO_MSG_ALG_UNREGISTER, &inst->alg);
 	list_move(&inst->alg.cra_list, list);
 	hlist_del(&inst->list);
 	inst->alg.cra_destroy = crypto_destroy_instance;
@@ -167,6 +166,18 @@ void crypto_remove_spawns(struct crypto_alg *alg, struct list_head *list,
 
 			spawn->alg = NULL;
 			spawns = &inst->alg.cra_users;
+
+			/*
+			 * We may encounter an unregistered instance here, since
+			 * an instance's spawns are set up prior to the instance
+			 * being registered.  An unregistered instance will have
+			 * NULL ->cra_users.next, since ->cra_users isn't
+			 * properly initialized until registration.  But an
+			 * unregistered instance cannot have any users, so treat
+			 * it the same as ->cra_users being empty.
+			 */
+			if (spawns->next == NULL)
+				break;
 		}
 	} while ((spawns = crypto_more_spawns(alg, &stack, &top,
 					      &secondary_spawns)));
@@ -224,7 +235,7 @@ static struct crypto_larval *__crypto_register_alg(struct crypto_alg *alg)
 	if (!larval->adult)
 		goto free_larval;
 
-	atomic_set(&larval->alg.cra_refcnt, 1);
+	refcount_set(&larval->alg.cra_refcnt, 1);
 	memcpy(larval->alg.cra_driver_name, alg->cra_driver_name,
 	       CRYPTO_MAX_ALG_NAME);
 	larval->alg.cra_priority = alg->cra_priority;
@@ -380,7 +391,6 @@ static int crypto_remove_alg(struct crypto_alg *alg, struct list_head *list)
 
 	alg->cra_flags |= CRYPTO_ALG_DEAD;
 
-	crypto_notify(CRYPTO_MSG_ALG_UNREGISTER, alg);
 	list_del_init(&alg->cra_list);
 	crypto_remove_spawns(alg, list, NULL);
 
@@ -399,7 +409,7 @@ int crypto_unregister_alg(struct crypto_alg *alg)
 	if (ret)
 		return ret;
 
-	BUG_ON(atomic_read(&alg->cra_refcnt) != 1);
+	BUG_ON(refcount_read(&alg->cra_refcnt) != 1);
 	if (alg->cra_destroy)
 		alg->cra_destroy(alg);
 
@@ -458,7 +468,6 @@ int crypto_register_template(struct crypto_template *tmpl)
 	}
 
 	list_add(&tmpl->list, &crypto_template_list);
-	crypto_notify(CRYPTO_MSG_TMPL_REGISTER, tmpl);
 	err = 0;
 out:
 	up_write(&crypto_alg_sem);
@@ -485,12 +494,10 @@ void crypto_unregister_template(struct crypto_template *tmpl)
 		BUG_ON(err);
 	}
 
-	crypto_notify(CRYPTO_MSG_TMPL_UNREGISTER, tmpl);
-
 	up_write(&crypto_alg_sem);
 
 	hlist_for_each_entry_safe(inst, n, list, list) {
-		BUG_ON(atomic_read(&inst->alg.cra_refcnt) != 1);
+		BUG_ON(refcount_read(&inst->alg.cra_refcnt) != 1);
 		crypto_free_instance(inst);
 	}
 	crypto_remove_final(&users);
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index aacae0837aff..4b07edd5a9ff 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -42,7 +42,6 @@
 
 struct aead_tfm {
 	struct crypto_aead *aead;
-	bool has_key;
 	struct crypto_skcipher *null_tfm;
 };
 
@@ -101,16 +100,22 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 	struct aead_tfm *aeadc = pask->private;
 	struct crypto_aead *tfm = aeadc->aead;
 	struct crypto_skcipher *null_tfm = aeadc->null_tfm;
-	unsigned int as = crypto_aead_authsize(tfm);
+	unsigned int i, as = crypto_aead_authsize(tfm);
 	struct af_alg_async_req *areq;
-	struct af_alg_tsgl *tsgl;
-	struct scatterlist *src;
+	struct af_alg_tsgl *tsgl, *tmp;
+	struct scatterlist *rsgl_src, *tsgl_src = NULL;
 	int err = 0;
 	size_t used = 0;		/* [in]  TX bufs to be en/decrypted */
 	size_t outlen = 0;		/* [out] RX bufs produced by kernel */
 	size_t usedpages = 0;		/* [in]  RX bufs to be used from user */
 	size_t processed = 0;		/* [in]  TX bufs to be consumed */
 
+	if (!ctx->used) {
+		err = af_alg_wait_for_data(sk, flags);
+		if (err)
+			return err;
+	}
+
 	/*
 	 * Data length provided by caller via sendmsg/sendpage that has not
 	 * yet been processed.
@@ -178,7 +183,22 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 	}
 
 	processed = used + ctx->aead_assoclen;
-	tsgl = list_first_entry(&ctx->tsgl_list, struct af_alg_tsgl, list);
+	list_for_each_entry_safe(tsgl, tmp, &ctx->tsgl_list, list) {
+		for (i = 0; i < tsgl->cur; i++) {
+			struct scatterlist *process_sg = tsgl->sg + i;
+
+			if (!(process_sg->length) || !sg_page(process_sg))
+				continue;
+			tsgl_src = process_sg;
+			break;
+		}
+		if (tsgl_src)
+			break;
+	}
+	if (processed && !tsgl_src) {
+		err = -EFAULT;
+		goto free;
+	}
 
 	/*
 	 * Copy of AAD from source to destination
@@ -194,7 +214,7 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 	 */
 
 	/* Use the RX SGL as source (and destination) for crypto op. */
-	src = areq->first_rsgl.sgl.sg;
+	rsgl_src = areq->first_rsgl.sgl.sg;
 
 	if (ctx->enc) {
 		/*
@@ -207,7 +227,7 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 		 *	    v	   v
 		 * RX SGL: AAD || PT || Tag
 		 */
-		err = crypto_aead_copy_sgl(null_tfm, tsgl->sg,
+		err = crypto_aead_copy_sgl(null_tfm, tsgl_src,
 					   areq->first_rsgl.sgl.sg, processed);
 		if (err)
 			goto free;
@@ -225,7 +245,7 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 		 */
 
 		 /* Copy AAD || CT to RX SGL buffer for in-place operation. */
-		err = crypto_aead_copy_sgl(null_tfm, tsgl->sg,
+		err = crypto_aead_copy_sgl(null_tfm, tsgl_src,
 					   areq->first_rsgl.sgl.sg, outlen);
 		if (err)
 			goto free;
@@ -257,23 +277,34 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 				 areq->tsgl);
 		} else
 			/* no RX SGL present (e.g. authentication only) */
-			src = areq->tsgl;
+			rsgl_src = areq->tsgl;
 	}
 
 	/* Initialize the crypto operation */
-	aead_request_set_crypt(&areq->cra_u.aead_req, src,
+	aead_request_set_crypt(&areq->cra_u.aead_req, rsgl_src,
 			       areq->first_rsgl.sgl.sg, used, ctx->iv);
 	aead_request_set_ad(&areq->cra_u.aead_req, ctx->aead_assoclen);
 	aead_request_set_tfm(&areq->cra_u.aead_req, tfm);
 
 	if (msg->msg_iocb && !is_sync_kiocb(msg->msg_iocb)) {
 		/* AIO operation */
+		sock_hold(sk);
 		areq->iocb = msg->msg_iocb;
+
+		/* Remember output size that will be generated. */
+		areq->outlen = outlen;
+
 		aead_request_set_callback(&areq->cra_u.aead_req,
 					  CRYPTO_TFM_REQ_MAY_BACKLOG,
 					  af_alg_async_cb, areq);
 		err = ctx->enc ? crypto_aead_encrypt(&areq->cra_u.aead_req) :
 				 crypto_aead_decrypt(&areq->cra_u.aead_req);
+
+		/* AIO operation in progress */
+		if (err == -EINPROGRESS || err == -EBUSY)
+			return -EIOCBQUEUED;
+
+		sock_put(sk);
 	} else {
 		/* Synchronous operation */
 		aead_request_set_callback(&areq->cra_u.aead_req,
@@ -285,19 +316,9 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 				&ctx->wait);
 	}
 
-	/* AIO operation in progress */
-	if (err == -EINPROGRESS) {
-		sock_hold(sk);
-
-		/* Remember output size that will be generated. */
-		areq->outlen = outlen;
-
-		return -EIOCBQUEUED;
-	}
 
 free:
-	af_alg_free_areq_sgls(areq);
-	sock_kfree_s(sk, areq, areq->areqlen);
+	af_alg_free_resources(areq);
 
 	return err ? err : outlen;
 }
@@ -376,7 +397,7 @@ static int aead_check_key(struct socket *sock)
 
 	err = -ENOKEY;
 	lock_sock_nested(psk, SINGLE_DEPTH_NESTING);
-	if (!tfm->has_key)
+	if (crypto_aead_get_flags(tfm->aead) & CRYPTO_TFM_NEED_KEY)
 		goto unlock;
 
 	if (!pask->refcnt++)
@@ -469,7 +490,7 @@ static void *aead_bind(const char *name, u32 type, u32 mask)
 		return ERR_CAST(aead);
 	}
 
-	null_tfm = crypto_get_default_null_skcipher2();
+	null_tfm = crypto_get_default_null_skcipher();
 	if (IS_ERR(null_tfm)) {
 		crypto_free_aead(aead);
 		kfree(tfm);
@@ -487,6 +508,7 @@ static void aead_release(void *private)
 	struct aead_tfm *tfm = private;
 
 	crypto_free_aead(tfm->aead);
+	crypto_put_default_null_skcipher();
 	kfree(tfm);
 }
 
@@ -500,12 +522,8 @@ static int aead_setauthsize(void *private, unsigned int authsize)
 static int aead_setkey(void *private, const u8 *key, unsigned int keylen)
 {
 	struct aead_tfm *tfm = private;
-	int err;
-
-	err = crypto_aead_setkey(tfm->aead, key, keylen);
-	tfm->has_key = !err;
 
-	return err;
+	return crypto_aead_setkey(tfm->aead, key, keylen);
 }
 
 static void aead_sock_destruct(struct sock *sk)
@@ -519,7 +537,6 @@ static void aead_sock_destruct(struct sock *sk)
 	unsigned int ivlen = crypto_aead_ivsize(tfm);
 
 	af_alg_pull_tsgl(sk, ctx->used, NULL, 0);
-	crypto_put_default_null_skcipher2();
 	sock_kzfree_s(sk, ctx->iv, ivlen);
 	sock_kfree_s(sk, ctx, ctx->len);
 	af_alg_release_parent(sk);
@@ -549,7 +566,7 @@ static int aead_accept_parent_nokey(void *private, struct sock *sk)
 	INIT_LIST_HEAD(&ctx->tsgl_list);
 	ctx->len = len;
 	ctx->used = 0;
-	ctx->rcvused = 0;
+	atomic_set(&ctx->rcvused, 0);
 	ctx->more = 0;
 	ctx->merge = 0;
 	ctx->enc = 0;
@@ -567,7 +584,7 @@ static int aead_accept_parent(void *private, struct sock *sk)
 {
 	struct aead_tfm *tfm = private;
 
-	if (!tfm->has_key)
+	if (crypto_aead_get_flags(tfm->aead) & CRYPTO_TFM_NEED_KEY)
 		return -ENOKEY;
 
 	return aead_accept_parent_nokey(private, sk);
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 76d2e716c792..6c9b1927a520 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -34,11 +34,6 @@ struct hash_ctx {
 	struct ahash_request req;
 };
 
-struct algif_hash_tfm {
-	struct crypto_ahash *hash;
-	bool has_key;
-};
-
 static int hash_alloc_result(struct sock *sk, struct hash_ctx *ctx)
 {
 	unsigned ds;
@@ -307,7 +302,7 @@ static int hash_check_key(struct socket *sock)
 	int err = 0;
 	struct sock *psk;
 	struct alg_sock *pask;
-	struct algif_hash_tfm *tfm;
+	struct crypto_ahash *tfm;
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 
@@ -321,7 +316,7 @@ static int hash_check_key(struct socket *sock)
 
 	err = -ENOKEY;
 	lock_sock_nested(psk, SINGLE_DEPTH_NESTING);
-	if (!tfm->has_key)
+	if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
 		goto unlock;
 
 	if (!pask->refcnt++)
@@ -412,41 +407,17 @@ static struct proto_ops algif_hash_ops_nokey = {
 
 static void *hash_bind(const char *name, u32 type, u32 mask)
 {
-	struct algif_hash_tfm *tfm;
-	struct crypto_ahash *hash;
-
-	tfm = kzalloc(sizeof(*tfm), GFP_KERNEL);
-	if (!tfm)
-		return ERR_PTR(-ENOMEM);
-
-	hash = crypto_alloc_ahash(name, type, mask);
-	if (IS_ERR(hash)) {
-		kfree(tfm);
-		return ERR_CAST(hash);
-	}
-
-	tfm->hash = hash;
-
-	return tfm;
+	return crypto_alloc_ahash(name, type, mask);
 }
 
 static void hash_release(void *private)
 {
-	struct algif_hash_tfm *tfm = private;
-
-	crypto_free_ahash(tfm->hash);
-	kfree(tfm);
+	crypto_free_ahash(private);
 }
 
 static int hash_setkey(void *private, const u8 *key, unsigned int keylen)
 {
-	struct algif_hash_tfm *tfm = private;
-	int err;
-
-	err = crypto_ahash_setkey(tfm->hash, key, keylen);
-	tfm->has_key = !err;
-
-	return err;
+	return crypto_ahash_setkey(private, key, keylen);
 }
 
 static void hash_sock_destruct(struct sock *sk)
@@ -461,11 +432,10 @@ static void hash_sock_destruct(struct sock *sk)
 
 static int hash_accept_parent_nokey(void *private, struct sock *sk)
 {
-	struct hash_ctx *ctx;
+	struct crypto_ahash *tfm = private;
 	struct alg_sock *ask = alg_sk(sk);
-	struct algif_hash_tfm *tfm = private;
-	struct crypto_ahash *hash = tfm->hash;
-	unsigned len = sizeof(*ctx) + crypto_ahash_reqsize(hash);
+	struct hash_ctx *ctx;
+	unsigned int len = sizeof(*ctx) + crypto_ahash_reqsize(tfm);
 
 	ctx = sock_kmalloc(sk, len, GFP_KERNEL);
 	if (!ctx)
@@ -478,7 +448,7 @@ static int hash_accept_parent_nokey(void *private, struct sock *sk)
 
 	ask->private = ctx;
 
-	ahash_request_set_tfm(&ctx->req, hash);
+	ahash_request_set_tfm(&ctx->req, tfm);
 	ahash_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				   crypto_req_done, &ctx->wait);
 
@@ -489,9 +459,9 @@ static int hash_accept_parent_nokey(void *private, struct sock *sk)
 
 static int hash_accept_parent(void *private, struct sock *sk)
 {
-	struct algif_hash_tfm *tfm = private;
+	struct crypto_ahash *tfm = private;
 
-	if (!tfm->has_key && crypto_ahash_has_setkey(tfm->hash))
+	if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
 		return -ENOKEY;
 
 	return hash_accept_parent_nokey(private, sk);
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 9954b078f0b9..c4e885df4564 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -38,11 +38,6 @@
 #include <linux/net.h>
 #include <net/sock.h>
 
-struct skcipher_tfm {
-	struct crypto_skcipher *skcipher;
-	bool has_key;
-};
-
 static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg,
 			    size_t size)
 {
@@ -50,8 +45,7 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg,
 	struct alg_sock *ask = alg_sk(sk);
 	struct sock *psk = ask->parent;
 	struct alg_sock *pask = alg_sk(psk);
-	struct skcipher_tfm *skc = pask->private;
-	struct crypto_skcipher *tfm = skc->skcipher;
+	struct crypto_skcipher *tfm = pask->private;
 	unsigned ivsize = crypto_skcipher_ivsize(tfm);
 
 	return af_alg_sendmsg(sock, msg, size, ivsize);
@@ -65,13 +59,18 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	struct sock *psk = ask->parent;
 	struct alg_sock *pask = alg_sk(psk);
 	struct af_alg_ctx *ctx = ask->private;
-	struct skcipher_tfm *skc = pask->private;
-	struct crypto_skcipher *tfm = skc->skcipher;
+	struct crypto_skcipher *tfm = pask->private;
 	unsigned int bs = crypto_skcipher_blocksize(tfm);
 	struct af_alg_async_req *areq;
 	int err = 0;
 	size_t len = 0;
 
+	if (!ctx->used) {
+		err = af_alg_wait_for_data(sk, flags);
+		if (err)
+			return err;
+	}
+
 	/* Allocate cipher request for current operation. */
 	areq = af_alg_alloc_areq(sk, sizeof(struct af_alg_async_req) +
 				     crypto_skcipher_reqsize(tfm));
@@ -117,13 +116,24 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 
 	if (msg->msg_iocb && !is_sync_kiocb(msg->msg_iocb)) {
 		/* AIO operation */
+		sock_hold(sk);
 		areq->iocb = msg->msg_iocb;
+
+		/* Remember output size that will be generated. */
+		areq->outlen = len;
+
 		skcipher_request_set_callback(&areq->cra_u.skcipher_req,
 					      CRYPTO_TFM_REQ_MAY_SLEEP,
 					      af_alg_async_cb, areq);
 		err = ctx->enc ?
 			crypto_skcipher_encrypt(&areq->cra_u.skcipher_req) :
 			crypto_skcipher_decrypt(&areq->cra_u.skcipher_req);
+
+		/* AIO operation in progress */
+		if (err == -EINPROGRESS || err == -EBUSY)
+			return -EIOCBQUEUED;
+
+		sock_put(sk);
 	} else {
 		/* Synchronous operation */
 		skcipher_request_set_callback(&areq->cra_u.skcipher_req,
@@ -136,19 +146,9 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 						 &ctx->wait);
 	}
 
-	/* AIO operation in progress */
-	if (err == -EINPROGRESS) {
-		sock_hold(sk);
-
-		/* Remember output size that will be generated. */
-		areq->outlen = len;
-
-		return -EIOCBQUEUED;
-	}
 
 free:
-	af_alg_free_areq_sgls(areq);
-	sock_kfree_s(sk, areq, areq->areqlen);
+	af_alg_free_resources(areq);
 
 	return err ? err : len;
 }
@@ -186,7 +186,6 @@ out:
 	return ret;
 }
 
-
 static struct proto_ops algif_skcipher_ops = {
 	.family		=	PF_ALG,
 
@@ -214,7 +213,7 @@ static int skcipher_check_key(struct socket *sock)
 	int err = 0;
 	struct sock *psk;
 	struct alg_sock *pask;
-	struct skcipher_tfm *tfm;
+	struct crypto_skcipher *tfm;
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 
@@ -228,7 +227,7 @@ static int skcipher_check_key(struct socket *sock)
 
 	err = -ENOKEY;
 	lock_sock_nested(psk, SINGLE_DEPTH_NESTING);
-	if (!tfm->has_key)
+	if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
 		goto unlock;
 
 	if (!pask->refcnt++)
@@ -307,41 +306,17 @@ static struct proto_ops algif_skcipher_ops_nokey = {
 
 static void *skcipher_bind(const char *name, u32 type, u32 mask)
 {
-	struct skcipher_tfm *tfm;
-	struct crypto_skcipher *skcipher;
-
-	tfm = kzalloc(sizeof(*tfm), GFP_KERNEL);
-	if (!tfm)
-		return ERR_PTR(-ENOMEM);
-
-	skcipher = crypto_alloc_skcipher(name, type, mask);
-	if (IS_ERR(skcipher)) {
-		kfree(tfm);
-		return ERR_CAST(skcipher);
-	}
-
-	tfm->skcipher = skcipher;
-
-	return tfm;
+	return crypto_alloc_skcipher(name, type, mask);
 }
 
 static void skcipher_release(void *private)
 {
-	struct skcipher_tfm *tfm = private;
-
-	crypto_free_skcipher(tfm->skcipher);
-	kfree(tfm);
+	crypto_free_skcipher(private);
 }
 
 static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen)
 {
-	struct skcipher_tfm *tfm = private;
-	int err;
-
-	err = crypto_skcipher_setkey(tfm->skcipher, key, keylen);
-	tfm->has_key = !err;
-
-	return err;
+	return crypto_skcipher_setkey(private, key, keylen);
 }
 
 static void skcipher_sock_destruct(struct sock *sk)
@@ -350,8 +325,7 @@ static void skcipher_sock_destruct(struct sock *sk)
 	struct af_alg_ctx *ctx = ask->private;
 	struct sock *psk = ask->parent;
 	struct alg_sock *pask = alg_sk(psk);
-	struct skcipher_tfm *skc = pask->private;
-	struct crypto_skcipher *tfm = skc->skcipher;
+	struct crypto_skcipher *tfm = pask->private;
 
 	af_alg_pull_tsgl(sk, ctx->used, NULL, 0);
 	sock_kzfree_s(sk, ctx->iv, crypto_skcipher_ivsize(tfm));
@@ -363,27 +337,26 @@ static int skcipher_accept_parent_nokey(void *private, struct sock *sk)
 {
 	struct af_alg_ctx *ctx;
 	struct alg_sock *ask = alg_sk(sk);
-	struct skcipher_tfm *tfm = private;
-	struct crypto_skcipher *skcipher = tfm->skcipher;
+	struct crypto_skcipher *tfm = private;
 	unsigned int len = sizeof(*ctx);
 
 	ctx = sock_kmalloc(sk, len, GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
-	ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(skcipher),
+	ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(tfm),
 			       GFP_KERNEL);
 	if (!ctx->iv) {
 		sock_kfree_s(sk, ctx, len);
 		return -ENOMEM;
 	}
 
-	memset(ctx->iv, 0, crypto_skcipher_ivsize(skcipher));
+	memset(ctx->iv, 0, crypto_skcipher_ivsize(tfm));
 
 	INIT_LIST_HEAD(&ctx->tsgl_list);
 	ctx->len = len;
 	ctx->used = 0;
-	ctx->rcvused = 0;
+	atomic_set(&ctx->rcvused, 0);
 	ctx->more = 0;
 	ctx->merge = 0;
 	ctx->enc = 0;
@@ -398,9 +371,9 @@ static int skcipher_accept_parent_nokey(void *private, struct sock *sk)
 
 static int skcipher_accept_parent(void *private, struct sock *sk)
 {
-	struct skcipher_tfm *tfm = private;
+	struct crypto_skcipher *tfm = private;
 
-	if (!tfm->has_key && crypto_skcipher_has_setkey(tfm->skcipher))
+	if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
 		return -ENOKEY;
 
 	return skcipher_accept_parent_nokey(private, sk);
diff --git a/crypto/api.c b/crypto/api.c
index 2a2479d168aa..70a894e52ff3 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -137,7 +137,7 @@ static struct crypto_alg *crypto_larval_add(const char *name, u32 type,
 	if (IS_ERR(larval))
 		return ERR_CAST(larval);
 
-	atomic_set(&larval->alg.cra_refcnt, 2);
+	refcount_set(&larval->alg.cra_refcnt, 2);
 
 	down_write(&crypto_alg_sem);
 	alg = __crypto_alg_lookup(name, type, mask);
@@ -205,7 +205,8 @@ struct crypto_alg *crypto_alg_lookup(const char *name, u32 type, u32 mask)
 }
 EXPORT_SYMBOL_GPL(crypto_alg_lookup);
 
-struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask)
+static struct crypto_alg *crypto_larval_lookup(const char *name, u32 type,
+					       u32 mask)
 {
 	struct crypto_alg *alg;
 
@@ -231,7 +232,6 @@ struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask)
 
 	return crypto_larval_add(name, type, mask);
 }
-EXPORT_SYMBOL_GPL(crypto_larval_lookup);
 
 int crypto_probing_notify(unsigned long val, void *v)
 {
diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c
index c1ca1e86f5c4..a6dcaa659aa8 100644
--- a/crypto/asymmetric_keys/pkcs7_parser.c
+++ b/crypto/asymmetric_keys/pkcs7_parser.c
@@ -148,8 +148,10 @@ struct pkcs7_message *pkcs7_parse_message(const void *data, size_t datalen)
 	}
 
 	ret = pkcs7_check_authattrs(ctx->msg);
-	if (ret < 0)
+	if (ret < 0) {
+		msg = ERR_PTR(ret);
 		goto out;
+	}
 
 	msg = ctx->msg;
 	ctx->msg = NULL;
diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c
index f6a009d88a33..1f4e25f10049 100644
--- a/crypto/asymmetric_keys/pkcs7_trust.c
+++ b/crypto/asymmetric_keys/pkcs7_trust.c
@@ -69,7 +69,7 @@ static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 		 /* Self-signed certificates form roots of their own, and if we
 		  * don't know them, then we can't accept them.
 		  */
-		if (x509->next == x509) {
+		if (x509->signer == x509) {
 			kleave(" = -ENOKEY [unknown self-signed]");
 			return -ENOKEY;
 		}
diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c
index 2d93d9eccb4d..39e6de0c2761 100644
--- a/crypto/asymmetric_keys/pkcs7_verify.c
+++ b/crypto/asymmetric_keys/pkcs7_verify.c
@@ -59,11 +59,8 @@ static int pkcs7_digest(struct pkcs7_message *pkcs7,
 	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	/* Digest the message [RFC2315 9.3] */
-	ret = crypto_shash_init(desc);
-	if (ret < 0)
-		goto error;
-	ret = crypto_shash_finup(desc, pkcs7->data, pkcs7->data_len,
-				 sig->digest);
+	ret = crypto_shash_digest(desc, pkcs7->data, pkcs7->data_len,
+				  sig->digest);
 	if (ret < 0)
 		goto error;
 	pr_devel("MsgDigest = [%*ph]\n", 8, sig->digest);
@@ -150,7 +147,7 @@ static int pkcs7_find_key(struct pkcs7_message *pkcs7,
 		pr_devel("Sig %u: Found cert serial match X.509[%u]\n",
 			 sinfo->index, certix);
 
-		if (x509->pub->pkey_algo != sinfo->sig->pkey_algo) {
+		if (strcmp(x509->pub->pkey_algo, sinfo->sig->pkey_algo) != 0) {
 			pr_warn("Sig %u: X.509 algo and PKCS#7 sig algo don't match\n",
 				sinfo->index);
 			continue;
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index bc3035ef27a2..de996586762a 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -73,7 +73,7 @@ int public_key_verify_signature(const struct public_key *pkey,
 	char alg_name_buf[CRYPTO_MAX_ALG_NAME];
 	void *output;
 	unsigned int outlen;
-	int ret = -ENOMEM;
+	int ret;
 
 	pr_devel("==>%s()\n", __func__);
 
@@ -99,6 +99,7 @@ int public_key_verify_signature(const struct public_key *pkey,
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
+	ret = -ENOMEM;
 	req = akcipher_request_alloc(tfm, GFP_KERNEL);
 	if (!req)
 		goto error_free_tfm;
@@ -127,7 +128,7 @@ int public_key_verify_signature(const struct public_key *pkey,
 	 * signature and returns that to us.
 	 */
 	ret = crypto_wait_req(crypto_akcipher_verify(req), &cwait);
-	if (ret < 0)
+	if (ret)
 		goto out_free_output;
 
 	/* Do the actual verification step. */
@@ -142,6 +143,8 @@ error_free_req:
 error_free_tfm:
 	crypto_free_akcipher(tfm);
 	pr_devel("<==%s() = %d\n", __func__, ret);
+	if (WARN_ON_ONCE(ret > 0))
+		ret = -EINVAL;
 	return ret;
 }
 EXPORT_SYMBOL_GPL(public_key_verify_signature);
diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index dd03fead1ca3..ce2df8c9c583 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -409,6 +409,8 @@ int x509_extract_key_data(void *context, size_t hdrlen,
 	ctx->cert->pub->pkey_algo = "rsa";
 
 	/* Discard the BIT STRING metadata */
+	if (vlen < 1 || *(const u8 *)value != 0)
+		return -EBADMSG;
 	ctx->key = value + 1;
 	ctx->key_size = vlen - 1;
 	return 0;
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index c9013582c026..9338b4558cdc 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -79,11 +79,7 @@ int x509_get_sig_params(struct x509_certificate *cert)
 	desc->tfm = tfm;
 	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
-	ret = crypto_shash_init(desc);
-	if (ret < 0)
-		goto error_2;
-	might_sleep();
-	ret = crypto_shash_finup(desc, cert->tbs, cert->tbs_size, sig->digest);
+	ret = crypto_shash_digest(desc, cert->tbs, cert->tbs_size, sig->digest);
 	if (ret < 0)
 		goto error_2;
 
@@ -135,7 +131,7 @@ int x509_check_for_self_signed(struct x509_certificate *cert)
 	}
 
 	ret = -EKEYREJECTED;
-	if (cert->pub->pkey_algo != cert->sig->pkey_algo)
+	if (strcmp(cert->pub->pkey_algo, cert->sig->pkey_algo) != 0)
 		goto out;
 
 	ret = public_key_verify_signature(cert->pub, cert->sig);
diff --git a/crypto/authenc.c b/crypto/authenc.c
index 875470b0e026..d3d6d72fe649 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -329,7 +329,7 @@ static int crypto_authenc_init_tfm(struct crypto_aead *tfm)
 	if (IS_ERR(enc))
 		goto err_free_ahash;
 
-	null = crypto_get_default_null_skcipher2();
+	null = crypto_get_default_null_skcipher();
 	err = PTR_ERR(null);
 	if (IS_ERR(null))
 		goto err_free_skcipher;
@@ -363,7 +363,7 @@ static void crypto_authenc_exit_tfm(struct crypto_aead *tfm)
 
 	crypto_free_ahash(ctx->auth);
 	crypto_free_skcipher(ctx->enc);
-	crypto_put_default_null_skcipher2();
+	crypto_put_default_null_skcipher();
 }
 
 static void crypto_authenc_free(struct aead_instance *inst)
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 0cf5fefdb859..15f91ddd7f0e 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -352,7 +352,7 @@ static int crypto_authenc_esn_init_tfm(struct crypto_aead *tfm)
 	if (IS_ERR(enc))
 		goto err_free_ahash;
 
-	null = crypto_get_default_null_skcipher2();
+	null = crypto_get_default_null_skcipher();
 	err = PTR_ERR(null);
 	if (IS_ERR(null))
 		goto err_free_skcipher;
@@ -389,7 +389,7 @@ static void crypto_authenc_esn_exit_tfm(struct crypto_aead *tfm)
 
 	crypto_free_ahash(ctx->auth);
 	crypto_free_skcipher(ctx->enc);
-	crypto_put_default_null_skcipher2();
+	crypto_put_default_null_skcipher();
 }
 
 static void crypto_authenc_esn_free(struct aead_instance *inst)
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index 6c43a0a17a55..01c0d4aa2563 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -18,7 +18,6 @@
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/errno.h>
-#include <linux/hardirq.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/seq_file.h>
diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c
index a02286bf319e..32ddd4836ff5 100644
--- a/crypto/camellia_generic.c
+++ b/crypto/camellia_generic.c
@@ -13,8 +13,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 /*
diff --git a/crypto/cast5_generic.c b/crypto/cast5_generic.c
index df5c72629383..66169c178314 100644
--- a/crypto/cast5_generic.c
+++ b/crypto/cast5_generic.c
@@ -16,8 +16,7 @@
 * any later version.
 *
 * You should have received a copy of the GNU General Public License
-* along with this program; if not, write to the Free Software
-* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+* along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
 
 
diff --git a/crypto/cast6_generic.c b/crypto/cast6_generic.c
index 058c8d755d03..c8e5ec69790e 100644
--- a/crypto/cast6_generic.c
+++ b/crypto/cast6_generic.c
@@ -13,8 +13,7 @@
  * any later version.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 
diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
index 4a45fa4890c0..e451c3cb6a56 100644
--- a/crypto/chacha20_generic.c
+++ b/crypto/chacha20_generic.c
@@ -9,44 +9,38 @@
  * (at your option) any later version.
  */
 
+#include <asm/unaligned.h>
 #include <crypto/algapi.h>
 #include <crypto/chacha20.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/module.h>
 
-static inline u32 le32_to_cpuvp(const void *p)
-{
-	return le32_to_cpup(p);
-}
-
 static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src,
 			     unsigned int bytes)
 {
-	u8 stream[CHACHA20_BLOCK_SIZE];
+	u32 stream[CHACHA20_BLOCK_WORDS];
 
 	if (dst != src)
 		memcpy(dst, src, bytes);
 
 	while (bytes >= CHACHA20_BLOCK_SIZE) {
 		chacha20_block(state, stream);
-		crypto_xor(dst, stream, CHACHA20_BLOCK_SIZE);
+		crypto_xor(dst, (const u8 *)stream, CHACHA20_BLOCK_SIZE);
 		bytes -= CHACHA20_BLOCK_SIZE;
 		dst += CHACHA20_BLOCK_SIZE;
 	}
 	if (bytes) {
 		chacha20_block(state, stream);
-		crypto_xor(dst, stream, bytes);
+		crypto_xor(dst, (const u8 *)stream, bytes);
 	}
 }
 
 void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv)
 {
-	static const char constant[16] = "expand 32-byte k";
-
-	state[0]  = le32_to_cpuvp(constant +  0);
-	state[1]  = le32_to_cpuvp(constant +  4);
-	state[2]  = le32_to_cpuvp(constant +  8);
-	state[3]  = le32_to_cpuvp(constant + 12);
+	state[0]  = 0x61707865; /* "expa" */
+	state[1]  = 0x3320646e; /* "nd 3" */
+	state[2]  = 0x79622d32; /* "2-by" */
+	state[3]  = 0x6b206574; /* "te k" */
 	state[4]  = ctx->key[0];
 	state[5]  = ctx->key[1];
 	state[6]  = ctx->key[2];
@@ -55,10 +49,10 @@ void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv)
 	state[9]  = ctx->key[5];
 	state[10] = ctx->key[6];
 	state[11] = ctx->key[7];
-	state[12] = le32_to_cpuvp(iv +  0);
-	state[13] = le32_to_cpuvp(iv +  4);
-	state[14] = le32_to_cpuvp(iv +  8);
-	state[15] = le32_to_cpuvp(iv + 12);
+	state[12] = get_unaligned_le32(iv +  0);
+	state[13] = get_unaligned_le32(iv +  4);
+	state[14] = get_unaligned_le32(iv +  8);
+	state[15] = get_unaligned_le32(iv + 12);
 }
 EXPORT_SYMBOL_GPL(crypto_chacha20_init);
 
@@ -72,7 +66,7 @@ int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
 		return -EINVAL;
 
 	for (i = 0; i < ARRAY_SIZE(ctx->key); i++)
-		ctx->key[i] = le32_to_cpuvp(key + i * sizeof(u32));
+		ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32));
 
 	return 0;
 }
@@ -111,7 +105,6 @@ static struct skcipher_alg alg = {
 	.base.cra_priority	= 100,
 	.base.cra_blocksize	= 1,
 	.base.cra_ctxsize	= sizeof(struct chacha20_ctx),
-	.base.cra_alignmask	= sizeof(u32) - 1,
 	.base.cra_module	= THIS_MODULE,
 
 	.min_keysize		= CHACHA20_KEY_SIZE,
diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c
index db1bc3147bc4..600afa99941f 100644
--- a/crypto/chacha20poly1305.c
+++ b/crypto/chacha20poly1305.c
@@ -610,6 +610,11 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 						    algt->mask));
 	if (IS_ERR(poly))
 		return PTR_ERR(poly);
+	poly_hash = __crypto_hash_alg_common(poly);
+
+	err = -EINVAL;
+	if (poly_hash->digestsize != POLY1305_DIGEST_SIZE)
+		goto out_put_poly;
 
 	err = -ENOMEM;
 	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
@@ -618,7 +623,6 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 
 	ctx = aead_instance_ctx(inst);
 	ctx->saltlen = CHACHAPOLY_IV_SIZE - ivsize;
-	poly_hash = __crypto_hash_alg_common(poly);
 	err = crypto_init_ahash_spawn(&ctx->poly, poly_hash,
 				      aead_crypto_instance(inst));
 	if (err)
diff --git a/crypto/crc32_generic.c b/crypto/crc32_generic.c
index aa2a25fc7482..718cbce8d169 100644
--- a/crypto/crc32_generic.c
+++ b/crypto/crc32_generic.c
@@ -133,6 +133,7 @@ static struct shash_alg alg = {
 		.cra_name		= "crc32",
 		.cra_driver_name	= "crc32-generic",
 		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(u32),
 		.cra_module		= THIS_MODULE,
diff --git a/crypto/crc32c_generic.c b/crypto/crc32c_generic.c
index 4c0a0e271876..372320399622 100644
--- a/crypto/crc32c_generic.c
+++ b/crypto/crc32c_generic.c
@@ -146,6 +146,7 @@ static struct shash_alg alg = {
 		.cra_name		=	"crc32c",
 		.cra_driver_name	=	"crc32c-generic",
 		.cra_priority		=	100,
+		.cra_flags		=	CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		=	CHKSUM_BLOCK_SIZE,
 		.cra_alignmask		=	3,
 		.cra_ctxsize		=	sizeof(struct chksum_ctx),
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index bd43cf5be14c..addca7bae33f 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -32,7 +32,9 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 
-#define CRYPTD_MAX_CPU_QLEN 1000
+static unsigned int cryptd_max_cpu_qlen = 1000;
+module_param(cryptd_max_cpu_qlen, uint, 0);
+MODULE_PARM_DESC(cryptd_max_cpu_qlen, "Set cryptd Max queue depth");
 
 struct cryptd_cpu_queue {
 	struct crypto_queue queue;
@@ -116,6 +118,7 @@ static int cryptd_init_queue(struct cryptd_queue *queue,
 		crypto_init_queue(&cpu_queue->queue, max_cpu_qlen);
 		INIT_WORK(&cpu_queue->work, cryptd_queue_worker);
 	}
+	pr_info("cryptd: max_cpu_qlen set to %d\n", max_cpu_qlen);
 	return 0;
 }
 
@@ -893,10 +896,9 @@ static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	if (err)
 		goto out_free_inst;
 
-	type = CRYPTO_ALG_ASYNC;
-	if (alg->cra_flags & CRYPTO_ALG_INTERNAL)
-		type |= CRYPTO_ALG_INTERNAL;
-	inst->alg.halg.base.cra_flags = type;
+	inst->alg.halg.base.cra_flags = CRYPTO_ALG_ASYNC |
+		(alg->cra_flags & (CRYPTO_ALG_INTERNAL |
+				   CRYPTO_ALG_OPTIONAL_KEY));
 
 	inst->alg.halg.digestsize = salg->digestsize;
 	inst->alg.halg.statesize = salg->statesize;
@@ -911,7 +913,8 @@ static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	inst->alg.finup  = cryptd_hash_finup_enqueue;
 	inst->alg.export = cryptd_hash_export;
 	inst->alg.import = cryptd_hash_import;
-	inst->alg.setkey = cryptd_hash_setkey;
+	if (crypto_shash_alg_has_setkey(salg))
+		inst->alg.setkey = cryptd_hash_setkey;
 	inst->alg.digest = cryptd_hash_digest_enqueue;
 
 	err = ahash_register_instance(tmpl, inst);
@@ -1372,7 +1375,7 @@ static int __init cryptd_init(void)
 {
 	int err;
 
-	err = cryptd_init_queue(&queue, CRYPTD_MAX_CPU_QLEN);
+	err = cryptd_init_queue(&queue, cryptd_max_cpu_qlen);
 	if (err)
 		return err;
 
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 0dbe2be7f783..5c291eedaa70 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -169,7 +169,7 @@ static int crypto_report_one(struct crypto_alg *alg,
 	ualg->cru_type = 0;
 	ualg->cru_mask = 0;
 	ualg->cru_flags = alg->cra_flags;
-	ualg->cru_refcnt = atomic_read(&alg->cra_refcnt);
+	ualg->cru_refcnt = refcount_read(&alg->cra_refcnt);
 
 	if (nla_put_u32(skb, CRYPTOCFGA_PRIORITY_VAL, alg->cra_priority))
 		goto nla_put_failure;
@@ -387,7 +387,7 @@ static int crypto_del_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto drop_alg;
 
 	err = -EBUSY;
-	if (atomic_read(&alg->cra_refcnt) > 2)
+	if (refcount_read(&alg->cra_refcnt) > 2)
 		goto drop_alg;
 
 	err = crypto_unregister_instance((struct crypto_instance *)alg);
diff --git a/crypto/ecc.c b/crypto/ecc.c
index 633a9bcdc574..18f32f2a5e1c 100644
--- a/crypto/ecc.c
+++ b/crypto/ecc.c
@@ -964,7 +964,7 @@ int ecc_gen_privkey(unsigned int curve_id, unsigned int ndigits, u64 *privkey)
 	 * DRBG with a security strength of 256.
 	 */
 	if (crypto_get_default_rng())
-		err = -EFAULT;
+		return -EFAULT;
 
 	err = crypto_rng_get_bytes(crypto_default_rng, (u8 *)priv, nbytes);
 	crypto_put_default_rng();
diff --git a/crypto/echainiv.c b/crypto/echainiv.c
index e3d889b122e0..45819e6015bf 100644
--- a/crypto/echainiv.c
+++ b/crypto/echainiv.c
@@ -118,8 +118,6 @@ static int echainiv_aead_create(struct crypto_template *tmpl,
 				struct rtattr **tb)
 {
 	struct aead_instance *inst;
-	struct crypto_aead_spawn *spawn;
-	struct aead_alg *alg;
 	int err;
 
 	inst = aead_geniv_alloc(tmpl, tb, 0, 0);
@@ -127,9 +125,6 @@ static int echainiv_aead_create(struct crypto_template *tmpl,
 	if (IS_ERR(inst))
 		return PTR_ERR(inst);
 
-	spawn = aead_instance_ctx(inst);
-	alg = crypto_spawn_aead_alg(spawn);
-
 	err = -EINVAL;
 	if (inst->alg.ivsize & (sizeof(u64) - 1) || !inst->alg.ivsize)
 		goto free_inst;
diff --git a/crypto/gcm.c b/crypto/gcm.c
index 8589681fb9f6..0ad879e1f9b2 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -1101,7 +1101,7 @@ static int crypto_rfc4543_init_tfm(struct crypto_aead *tfm)
 	if (IS_ERR(aead))
 		return PTR_ERR(aead);
 
-	null = crypto_get_default_null_skcipher2();
+	null = crypto_get_default_null_skcipher();
 	err = PTR_ERR(null);
 	if (IS_ERR(null))
 		goto err_free_aead;
@@ -1129,7 +1129,7 @@ static void crypto_rfc4543_exit_tfm(struct crypto_aead *tfm)
 	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
-	crypto_put_default_null_skcipher2();
+	crypto_put_default_null_skcipher();
 }
 
 static void crypto_rfc4543_free(struct aead_instance *inst)
diff --git a/crypto/gf128mul.c b/crypto/gf128mul.c
index 24e601954c7a..a4b1c026aaee 100644
--- a/crypto/gf128mul.c
+++ b/crypto/gf128mul.c
@@ -160,8 +160,6 @@ void gf128mul_x8_ble(le128 *r, const le128 *x)
 {
 	u64 a = le64_to_cpu(x->a);
 	u64 b = le64_to_cpu(x->b);
-
-	/* equivalent to gf128mul_table_be[b >> 63] (see crypto/gf128mul.c): */
 	u64 _tt = gf128mul_table_be[a >> 56];
 
 	r->a = cpu_to_le64((a << 8) | (b >> 56));
diff --git a/crypto/ghash-generic.c b/crypto/ghash-generic.c
index 12ad3e3a84e3..1bffb3f712dd 100644
--- a/crypto/ghash-generic.c
+++ b/crypto/ghash-generic.c
@@ -56,9 +56,6 @@ static int ghash_update(struct shash_desc *desc,
 	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	u8 *dst = dctx->buffer;
 
-	if (!ctx->gf128)
-		return -ENOKEY;
-
 	if (dctx->bytes) {
 		int n = min(srclen, dctx->bytes);
 		u8 *pos = dst + (GHASH_BLOCK_SIZE - dctx->bytes);
@@ -111,9 +108,6 @@ static int ghash_final(struct shash_desc *desc, u8 *dst)
 	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	u8 *buf = dctx->buffer;
 
-	if (!ctx->gf128)
-		return -ENOKEY;
-
 	ghash_flush(ctx, dctx);
 	memcpy(dst, buf, GHASH_BLOCK_SIZE);
 
diff --git a/crypto/hmac.c b/crypto/hmac.c
index 92871dc2a63e..e74730224f0a 100644
--- a/crypto/hmac.c
+++ b/crypto/hmac.c
@@ -195,11 +195,15 @@ static int hmac_create(struct crypto_template *tmpl, struct rtattr **tb)
 	salg = shash_attr_alg(tb[1], 0, 0);
 	if (IS_ERR(salg))
 		return PTR_ERR(salg);
+	alg = &salg->base;
 
+	/* The underlying hash algorithm must be unkeyed */
 	err = -EINVAL;
+	if (crypto_shash_alg_has_setkey(salg))
+		goto out_put_alg;
+
 	ds = salg->digestsize;
 	ss = salg->statesize;
-	alg = &salg->base;
 	if (ds > alg->cra_blocksize ||
 	    ss < alg->cra_blocksize)
 		goto out_put_alg;
diff --git a/crypto/internal.h b/crypto/internal.h
index f07320423191..5ac27fba10e8 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -30,9 +30,6 @@
 enum {
 	CRYPTO_MSG_ALG_REQUEST,
 	CRYPTO_MSG_ALG_REGISTER,
-	CRYPTO_MSG_ALG_UNREGISTER,
-	CRYPTO_MSG_TMPL_REGISTER,
-	CRYPTO_MSG_TMPL_UNREGISTER,
 };
 
 struct crypto_instance;
@@ -78,7 +75,6 @@ int crypto_init_compress_ops(struct crypto_tfm *tfm);
 
 struct crypto_larval *crypto_larval_alloc(const char *name, u32 type, u32 mask);
 void crypto_larval_kill(struct crypto_alg *alg);
-struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask);
 void crypto_alg_tested(const char *name, int err);
 
 void crypto_remove_spawns(struct crypto_alg *alg, struct list_head *list,
@@ -106,13 +102,13 @@ int crypto_type_has_alg(const char *name, const struct crypto_type *frontend,
 
 static inline struct crypto_alg *crypto_alg_get(struct crypto_alg *alg)
 {
-	atomic_inc(&alg->cra_refcnt);
+	refcount_inc(&alg->cra_refcnt);
 	return alg;
 }
 
 static inline void crypto_alg_put(struct crypto_alg *alg)
 {
-	if (atomic_dec_and_test(&alg->cra_refcnt) && alg->cra_destroy)
+	if (refcount_dec_and_test(&alg->cra_refcnt) && alg->cra_destroy)
 		alg->cra_destroy(alg);
 }
 
diff --git a/crypto/keywrap.c b/crypto/keywrap.c
index 744e35134c45..ec5c6a087c90 100644
--- a/crypto/keywrap.c
+++ b/crypto/keywrap.c
@@ -188,7 +188,7 @@ static int crypto_kw_decrypt(struct blkcipher_desc *desc,
 	}
 
 	/* Perform authentication check */
-	if (block.A != cpu_to_be64(0xa6a6a6a6a6a6a6a6))
+	if (block.A != cpu_to_be64(0xa6a6a6a6a6a6a6a6ULL))
 		ret = -EBADMSG;
 
 	memzero_explicit(&block, sizeof(struct crypto_kw_block));
@@ -221,7 +221,7 @@ static int crypto_kw_encrypt(struct blkcipher_desc *desc,
 	 * Place the predefined IV into block A -- for encrypt, the caller
 	 * does not need to provide an IV, but he needs to fetch the final IV.
 	 */
-	block.A = cpu_to_be64(0xa6a6a6a6a6a6a6a6);
+	block.A = cpu_to_be64(0xa6a6a6a6a6a6a6a6ULL);
 
 	/*
 	 * src scatterlist is read-only. dst scatterlist is r/w. During the
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index 4e6472658852..fe5129d6ff4e 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -26,7 +26,6 @@
 #include <linux/sched.h>
 #include <linux/sched/stat.h>
 #include <linux/slab.h>
-#include <linux/hardirq.h>
 
 #define MCRYPTD_MAX_CPU_QLEN 100
 #define MCRYPTD_BATCH 9
@@ -81,6 +80,7 @@ static int mcryptd_init_queue(struct mcryptd_queue *queue,
 		pr_debug("cpu_queue #%d %p\n", cpu, queue->cpu_queue);
 		crypto_init_queue(&cpu_queue->queue, max_cpu_qlen);
 		INIT_WORK(&cpu_queue->work, mcryptd_queue_worker);
+		spin_lock_init(&cpu_queue->q_lock);
 	}
 	return 0;
 }
@@ -104,15 +104,16 @@ static int mcryptd_enqueue_request(struct mcryptd_queue *queue,
 	int cpu, err;
 	struct mcryptd_cpu_queue *cpu_queue;
 
-	cpu = get_cpu();
-	cpu_queue = this_cpu_ptr(queue->cpu_queue);
-	rctx->tag.cpu = cpu;
+	cpu_queue = raw_cpu_ptr(queue->cpu_queue);
+	spin_lock(&cpu_queue->q_lock);
+	cpu = smp_processor_id();
+	rctx->tag.cpu = smp_processor_id();
 
 	err = crypto_enqueue_request(&cpu_queue->queue, request);
 	pr_debug("enqueue request: cpu %d cpu_queue %p request %p\n",
 		 cpu, cpu_queue, request);
+	spin_unlock(&cpu_queue->q_lock);
 	queue_work_on(cpu, kcrypto_wq, &cpu_queue->work);
-	put_cpu();
 
 	return err;
 }
@@ -161,16 +162,11 @@ static void mcryptd_queue_worker(struct work_struct *work)
 	cpu_queue = container_of(work, struct mcryptd_cpu_queue, work);
 	i = 0;
 	while (i < MCRYPTD_BATCH || single_task_running()) {
-		/*
-		 * preempt_disable/enable is used to prevent
-		 * being preempted by mcryptd_enqueue_request()
-		 */
-		local_bh_disable();
-		preempt_disable();
+
+		spin_lock_bh(&cpu_queue->q_lock);
 		backlog = crypto_get_backlog(&cpu_queue->queue);
 		req = crypto_dequeue_request(&cpu_queue->queue);
-		preempt_enable();
-		local_bh_enable();
+		spin_unlock_bh(&cpu_queue->q_lock);
 
 		if (!req) {
 			mcryptd_opportunistic_flush();
@@ -185,7 +181,7 @@ static void mcryptd_queue_worker(struct work_struct *work)
 		++i;
 	}
 	if (cpu_queue->queue.qlen)
-		queue_work(kcrypto_wq, &cpu_queue->work);
+		queue_work_on(smp_processor_id(), kcrypto_wq, &cpu_queue->work);
 }
 
 void mcryptd_flusher(struct work_struct *__work)
@@ -520,10 +516,9 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	if (err)
 		goto out_free_inst;
 
-	type = CRYPTO_ALG_ASYNC;
-	if (alg->cra_flags & CRYPTO_ALG_INTERNAL)
-		type |= CRYPTO_ALG_INTERNAL;
-	inst->alg.halg.base.cra_flags = type;
+	inst->alg.halg.base.cra_flags = CRYPTO_ALG_ASYNC |
+		(alg->cra_flags & (CRYPTO_ALG_INTERNAL |
+				   CRYPTO_ALG_OPTIONAL_KEY));
 
 	inst->alg.halg.digestsize = halg->digestsize;
 	inst->alg.halg.statesize = halg->statesize;
@@ -538,7 +533,8 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	inst->alg.finup  = mcryptd_hash_finup_enqueue;
 	inst->alg.export = mcryptd_hash_export;
 	inst->alg.import = mcryptd_hash_import;
-	inst->alg.setkey = mcryptd_hash_setkey;
+	if (crypto_hash_alg_has_setkey(halg))
+		inst->alg.setkey = mcryptd_hash_setkey;
 	inst->alg.digest = mcryptd_hash_digest_enqueue;
 
 	err = ahash_register_instance(tmpl, inst);
diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index ee9cfb99fe25..f8ec3d4ba4a8 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -254,6 +254,14 @@ static void pcrypt_aead_exit_tfm(struct crypto_aead *tfm)
 	crypto_free_aead(ctx->child);
 }
 
+static void pcrypt_free(struct aead_instance *inst)
+{
+	struct pcrypt_instance_ctx *ctx = aead_instance_ctx(inst);
+
+	crypto_drop_aead(&ctx->spawn);
+	kfree(inst);
+}
+
 static int pcrypt_init_instance(struct crypto_instance *inst,
 				struct crypto_alg *alg)
 {
@@ -319,6 +327,8 @@ static int pcrypt_create_aead(struct crypto_template *tmpl, struct rtattr **tb,
 	inst->alg.encrypt = pcrypt_aead_encrypt;
 	inst->alg.decrypt = pcrypt_aead_decrypt;
 
+	inst->free = pcrypt_free;
+
 	err = aead_register_instance(tmpl, inst);
 	if (err)
 		goto out_drop_aead;
@@ -349,14 +359,6 @@ static int pcrypt_create(struct crypto_template *tmpl, struct rtattr **tb)
 	return -EINVAL;
 }
 
-static void pcrypt_free(struct crypto_instance *inst)
-{
-	struct pcrypt_instance_ctx *ctx = crypto_instance_ctx(inst);
-
-	crypto_drop_aead(&ctx->spawn);
-	kfree(inst);
-}
-
 static int pcrypt_cpumask_change_notify(struct notifier_block *self,
 					unsigned long val, void *data)
 {
@@ -469,7 +471,6 @@ static void pcrypt_fini_padata(struct padata_pcrypt *pcrypt)
 static struct crypto_template pcrypt_tmpl = {
 	.name = "pcrypt",
 	.create = pcrypt_create,
-	.free = pcrypt_free,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
index b1c2d57dc734..b7a3a0613a30 100644
--- a/crypto/poly1305_generic.c
+++ b/crypto/poly1305_generic.c
@@ -47,17 +47,6 @@ int crypto_poly1305_init(struct shash_desc *desc)
 }
 EXPORT_SYMBOL_GPL(crypto_poly1305_init);
 
-int crypto_poly1305_setkey(struct crypto_shash *tfm,
-			   const u8 *key, unsigned int keylen)
-{
-	/* Poly1305 requires a unique key for each tag, which implies that
-	 * we can't set it on the tfm that gets accessed by multiple users
-	 * simultaneously. Instead we expect the key as the first 32 bytes in
-	 * the update() call. */
-	return -ENOTSUPP;
-}
-EXPORT_SYMBOL_GPL(crypto_poly1305_setkey);
-
 static void poly1305_setrkey(struct poly1305_desc_ctx *dctx, const u8 *key)
 {
 	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
@@ -76,6 +65,11 @@ static void poly1305_setskey(struct poly1305_desc_ctx *dctx, const u8 *key)
 	dctx->s[3] = get_unaligned_le32(key + 12);
 }
 
+/*
+ * Poly1305 requires a unique key for each tag, which implies that we can't set
+ * it on the tfm that gets accessed by multiple users simultaneously. Instead we
+ * expect the key as the first 32 bytes in the update() call.
+ */
 unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
 					const u8 *src, unsigned int srclen)
 {
@@ -210,7 +204,6 @@ EXPORT_SYMBOL_GPL(crypto_poly1305_update);
 int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
 {
 	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-	__le32 *mac = (__le32 *)dst;
 	u32 h0, h1, h2, h3, h4;
 	u32 g0, g1, g2, g3, g4;
 	u32 mask;
@@ -267,10 +260,10 @@ int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
 	h3 = (h3 >> 18) | (h4 <<  8);
 
 	/* mac = (h + s) % (2^128) */
-	f = (f >> 32) + h0 + dctx->s[0]; mac[0] = cpu_to_le32(f);
-	f = (f >> 32) + h1 + dctx->s[1]; mac[1] = cpu_to_le32(f);
-	f = (f >> 32) + h2 + dctx->s[2]; mac[2] = cpu_to_le32(f);
-	f = (f >> 32) + h3 + dctx->s[3]; mac[3] = cpu_to_le32(f);
+	f = (f >> 32) + h0 + dctx->s[0]; put_unaligned_le32(f, dst +  0);
+	f = (f >> 32) + h1 + dctx->s[1]; put_unaligned_le32(f, dst +  4);
+	f = (f >> 32) + h2 + dctx->s[2]; put_unaligned_le32(f, dst +  8);
+	f = (f >> 32) + h3 + dctx->s[3]; put_unaligned_le32(f, dst + 12);
 
 	return 0;
 }
@@ -281,14 +274,12 @@ static struct shash_alg poly1305_alg = {
 	.init		= crypto_poly1305_init,
 	.update		= crypto_poly1305_update,
 	.final		= crypto_poly1305_final,
-	.setkey		= crypto_poly1305_setkey,
 	.descsize	= sizeof(struct poly1305_desc_ctx),
 	.base		= {
 		.cra_name		= "poly1305",
 		.cra_driver_name	= "poly1305-generic",
 		.cra_priority		= 100,
 		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
-		.cra_alignmask		= sizeof(u32) - 1,
 		.cra_blocksize		= POLY1305_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	},
diff --git a/crypto/proc.c b/crypto/proc.c
index 2cc10c96d753..822fcef6d91c 100644
--- a/crypto/proc.c
+++ b/crypto/proc.c
@@ -46,7 +46,7 @@ static int c_show(struct seq_file *m, void *p)
 	seq_printf(m, "driver       : %s\n", alg->cra_driver_name);
 	seq_printf(m, "module       : %s\n", module_name(alg->cra_module));
 	seq_printf(m, "priority     : %d\n", alg->cra_priority);
-	seq_printf(m, "refcnt       : %d\n", atomic_read(&alg->cra_refcnt));
+	seq_printf(m, "refcnt       : %u\n", refcount_read(&alg->cra_refcnt));
 	seq_printf(m, "selftest     : %s\n",
 		   (alg->cra_flags & CRYPTO_ALG_TESTED) ?
 		   "passed" : "unknown");
diff --git a/crypto/rsa_helper.c b/crypto/rsa_helper.c
index 0b66dc824606..cad395d70d78 100644
--- a/crypto/rsa_helper.c
+++ b/crypto/rsa_helper.c
@@ -30,7 +30,7 @@ int rsa_get_n(void *context, size_t hdrlen, unsigned char tag,
 		return -EINVAL;
 
 	if (fips_enabled) {
-		while (!*ptr && n_sz) {
+		while (n_sz && !*ptr) {
 			ptr++;
 			n_sz--;
 		}
diff --git a/crypto/salsa20_generic.c b/crypto/salsa20_generic.c
index f550b5d94630..5074006a56c3 100644
--- a/crypto/salsa20_generic.c
+++ b/crypto/salsa20_generic.c
@@ -19,49 +19,19 @@
  *
  */
 
-#include <linux/init.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/salsa20.h>
 #include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/crypto.h>
-#include <linux/types.h>
-#include <linux/bitops.h>
-#include <crypto/algapi.h>
-#include <asm/byteorder.h>
 
-#define SALSA20_IV_SIZE        8U
-#define SALSA20_MIN_KEY_SIZE  16U
-#define SALSA20_MAX_KEY_SIZE  32U
-
-/*
- * Start of code taken from D. J. Bernstein's reference implementation.
- * With some modifications and optimizations made to suit our needs.
- */
-
-/*
-salsa20-ref.c version 20051118
-D. J. Bernstein
-Public domain.
-*/
-
-#define U32TO8_LITTLE(p, v) \
-	{ (p)[0] = (v >>  0) & 0xff; (p)[1] = (v >>  8) & 0xff; \
-	  (p)[2] = (v >> 16) & 0xff; (p)[3] = (v >> 24) & 0xff; }
-#define U8TO32_LITTLE(p)   \
-	(((u32)((p)[0])      ) | ((u32)((p)[1]) <<  8) | \
-	 ((u32)((p)[2]) << 16) | ((u32)((p)[3]) << 24)   )
-
-struct salsa20_ctx
-{
-	u32 input[16];
-};
-
-static void salsa20_wordtobyte(u8 output[64], const u32 input[16])
+static void salsa20_block(u32 *state, __le32 *stream)
 {
 	u32 x[16];
 	int i;
 
-	memcpy(x, input, sizeof(x));
-	for (i = 20; i > 0; i -= 2) {
+	memcpy(x, state, sizeof(x));
+
+	for (i = 0; i < 20; i += 2) {
 		x[ 4] ^= rol32((x[ 0] + x[12]),  7);
 		x[ 8] ^= rol32((x[ 4] + x[ 0]),  9);
 		x[12] ^= rol32((x[ 8] + x[ 4]), 13);
@@ -95,152 +65,137 @@ static void salsa20_wordtobyte(u8 output[64], const u32 input[16])
 		x[14] ^= rol32((x[13] + x[12]), 13);
 		x[15] ^= rol32((x[14] + x[13]), 18);
 	}
-	for (i = 0; i < 16; ++i)
-		x[i] += input[i];
-	for (i = 0; i < 16; ++i)
-		U32TO8_LITTLE(output + 4 * i,x[i]);
-}
 
-static const char sigma[16] = "expand 32-byte k";
-static const char tau[16] = "expand 16-byte k";
+	for (i = 0; i < 16; i++)
+		stream[i] = cpu_to_le32(x[i] + state[i]);
+
+	if (++state[8] == 0)
+		state[9]++;
+}
 
-static void salsa20_keysetup(struct salsa20_ctx *ctx, const u8 *k, u32 kbytes)
+static void salsa20_docrypt(u32 *state, u8 *dst, const u8 *src,
+			    unsigned int bytes)
 {
-	const char *constants;
+	__le32 stream[SALSA20_BLOCK_SIZE / sizeof(__le32)];
 
-	ctx->input[1] = U8TO32_LITTLE(k + 0);
-	ctx->input[2] = U8TO32_LITTLE(k + 4);
-	ctx->input[3] = U8TO32_LITTLE(k + 8);
-	ctx->input[4] = U8TO32_LITTLE(k + 12);
-	if (kbytes == 32) { /* recommended */
-		k += 16;
-		constants = sigma;
-	} else { /* kbytes == 16 */
-		constants = tau;
+	if (dst != src)
+		memcpy(dst, src, bytes);
+
+	while (bytes >= SALSA20_BLOCK_SIZE) {
+		salsa20_block(state, stream);
+		crypto_xor(dst, (const u8 *)stream, SALSA20_BLOCK_SIZE);
+		bytes -= SALSA20_BLOCK_SIZE;
+		dst += SALSA20_BLOCK_SIZE;
+	}
+	if (bytes) {
+		salsa20_block(state, stream);
+		crypto_xor(dst, (const u8 *)stream, bytes);
 	}
-	ctx->input[11] = U8TO32_LITTLE(k + 0);
-	ctx->input[12] = U8TO32_LITTLE(k + 4);
-	ctx->input[13] = U8TO32_LITTLE(k + 8);
-	ctx->input[14] = U8TO32_LITTLE(k + 12);
-	ctx->input[0] = U8TO32_LITTLE(constants + 0);
-	ctx->input[5] = U8TO32_LITTLE(constants + 4);
-	ctx->input[10] = U8TO32_LITTLE(constants + 8);
-	ctx->input[15] = U8TO32_LITTLE(constants + 12);
 }
 
-static void salsa20_ivsetup(struct salsa20_ctx *ctx, const u8 *iv)
+void crypto_salsa20_init(u32 *state, const struct salsa20_ctx *ctx,
+			 const u8 *iv)
 {
-	ctx->input[6] = U8TO32_LITTLE(iv + 0);
-	ctx->input[7] = U8TO32_LITTLE(iv + 4);
-	ctx->input[8] = 0;
-	ctx->input[9] = 0;
+	memcpy(state, ctx->initial_state, sizeof(ctx->initial_state));
+	state[6] = get_unaligned_le32(iv + 0);
+	state[7] = get_unaligned_le32(iv + 4);
 }
+EXPORT_SYMBOL_GPL(crypto_salsa20_init);
 
-static void salsa20_encrypt_bytes(struct salsa20_ctx *ctx, u8 *dst,
-				  const u8 *src, unsigned int bytes)
+int crypto_salsa20_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			  unsigned int keysize)
 {
-	u8 buf[64];
-
-	if (dst != src)
-		memcpy(dst, src, bytes);
-
-	while (bytes) {
-		salsa20_wordtobyte(buf, ctx->input);
-
-		ctx->input[8]++;
-		if (!ctx->input[8])
-			ctx->input[9]++;
+	static const char sigma[16] = "expand 32-byte k";
+	static const char tau[16] = "expand 16-byte k";
+	struct salsa20_ctx *ctx = crypto_skcipher_ctx(tfm);
+	const char *constants;
 
-		if (bytes <= 64) {
-			crypto_xor(dst, buf, bytes);
-			return;
-		}
+	if (keysize != SALSA20_MIN_KEY_SIZE &&
+	    keysize != SALSA20_MAX_KEY_SIZE)
+		return -EINVAL;
 
-		crypto_xor(dst, buf, 64);
-		bytes -= 64;
-		dst += 64;
+	ctx->initial_state[1] = get_unaligned_le32(key + 0);
+	ctx->initial_state[2] = get_unaligned_le32(key + 4);
+	ctx->initial_state[3] = get_unaligned_le32(key + 8);
+	ctx->initial_state[4] = get_unaligned_le32(key + 12);
+	if (keysize == 32) { /* recommended */
+		key += 16;
+		constants = sigma;
+	} else { /* keysize == 16 */
+		constants = tau;
 	}
-}
-
-/*
- * End of code taken from D. J. Bernstein's reference implementation.
- */
+	ctx->initial_state[11] = get_unaligned_le32(key + 0);
+	ctx->initial_state[12] = get_unaligned_le32(key + 4);
+	ctx->initial_state[13] = get_unaligned_le32(key + 8);
+	ctx->initial_state[14] = get_unaligned_le32(key + 12);
+	ctx->initial_state[0]  = get_unaligned_le32(constants + 0);
+	ctx->initial_state[5]  = get_unaligned_le32(constants + 4);
+	ctx->initial_state[10] = get_unaligned_le32(constants + 8);
+	ctx->initial_state[15] = get_unaligned_le32(constants + 12);
+
+	/* space for the nonce; it will be overridden for each request */
+	ctx->initial_state[6] = 0;
+	ctx->initial_state[7] = 0;
+
+	/* initial block number */
+	ctx->initial_state[8] = 0;
+	ctx->initial_state[9] = 0;
 
-static int setkey(struct crypto_tfm *tfm, const u8 *key,
-		  unsigned int keysize)
-{
-	struct salsa20_ctx *ctx = crypto_tfm_ctx(tfm);
-	salsa20_keysetup(ctx, key, keysize);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(crypto_salsa20_setkey);
 
-static int encrypt(struct blkcipher_desc *desc,
-		   struct scatterlist *dst, struct scatterlist *src,
-		   unsigned int nbytes)
+static int salsa20_crypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-	struct crypto_blkcipher *tfm = desc->tfm;
-	struct salsa20_ctx *ctx = crypto_blkcipher_ctx(tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct salsa20_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	u32 state[16];
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, 64);
+	err = skcipher_walk_virt(&walk, req, true);
 
-	salsa20_ivsetup(ctx, walk.iv);
+	crypto_salsa20_init(state, ctx, walk.iv);
 
-	if (likely(walk.nbytes == nbytes))
-	{
-		salsa20_encrypt_bytes(ctx, walk.dst.virt.addr,
-				      walk.src.virt.addr, nbytes);
-		return blkcipher_walk_done(desc, &walk, 0);
-	}
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
 
-	while (walk.nbytes >= 64) {
-		salsa20_encrypt_bytes(ctx, walk.dst.virt.addr,
-				      walk.src.virt.addr,
-				      walk.nbytes - (walk.nbytes % 64));
-		err = blkcipher_walk_done(desc, &walk, walk.nbytes % 64);
-	}
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
 
-	if (walk.nbytes) {
-		salsa20_encrypt_bytes(ctx, walk.dst.virt.addr,
-				      walk.src.virt.addr, walk.nbytes);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		salsa20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
+				nbytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
 }
 
-static struct crypto_alg alg = {
-	.cra_name           =   "salsa20",
-	.cra_driver_name    =   "salsa20-generic",
-	.cra_priority       =   100,
-	.cra_flags          =   CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_type           =   &crypto_blkcipher_type,
-	.cra_blocksize      =   1,
-	.cra_ctxsize        =   sizeof(struct salsa20_ctx),
-	.cra_alignmask      =	3,
-	.cra_module         =   THIS_MODULE,
-	.cra_u              =   {
-		.blkcipher = {
-			.setkey         =   setkey,
-			.encrypt        =   encrypt,
-			.decrypt        =   encrypt,
-			.min_keysize    =   SALSA20_MIN_KEY_SIZE,
-			.max_keysize    =   SALSA20_MAX_KEY_SIZE,
-			.ivsize         =   SALSA20_IV_SIZE,
-		}
-	}
+static struct skcipher_alg alg = {
+	.base.cra_name		= "salsa20",
+	.base.cra_driver_name	= "salsa20-generic",
+	.base.cra_priority	= 100,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct salsa20_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= SALSA20_MIN_KEY_SIZE,
+	.max_keysize		= SALSA20_MAX_KEY_SIZE,
+	.ivsize			= SALSA20_IV_SIZE,
+	.chunksize		= SALSA20_BLOCK_SIZE,
+	.setkey			= crypto_salsa20_setkey,
+	.encrypt		= salsa20_crypt,
+	.decrypt		= salsa20_crypt,
 };
 
 static int __init salsa20_generic_mod_init(void)
 {
-	return crypto_register_alg(&alg);
+	return crypto_register_skcipher(&alg);
 }
 
 static void __exit salsa20_generic_mod_fini(void)
 {
-	crypto_unregister_alg(&alg);
+	crypto_unregister_skcipher(&alg);
 }
 
 module_init(salsa20_generic_mod_init);
diff --git a/crypto/scompress.c b/crypto/scompress.c
index 2075e2c4e7df..968bbcf65c94 100644
--- a/crypto/scompress.c
+++ b/crypto/scompress.c
@@ -140,53 +140,6 @@ static int crypto_scomp_init_tfm(struct crypto_tfm *tfm)
 	return ret;
 }
 
-static void crypto_scomp_sg_free(struct scatterlist *sgl)
-{
-	int i, n;
-	struct page *page;
-
-	if (!sgl)
-		return;
-
-	n = sg_nents(sgl);
-	for_each_sg(sgl, sgl, n, i) {
-		page = sg_page(sgl);
-		if (page)
-			__free_page(page);
-	}
-
-	kfree(sgl);
-}
-
-static struct scatterlist *crypto_scomp_sg_alloc(size_t size, gfp_t gfp)
-{
-	struct scatterlist *sgl;
-	struct page *page;
-	int i, n;
-
-	n = ((size - 1) >> PAGE_SHIFT) + 1;
-
-	sgl = kmalloc_array(n, sizeof(struct scatterlist), gfp);
-	if (!sgl)
-		return NULL;
-
-	sg_init_table(sgl, n);
-
-	for (i = 0; i < n; i++) {
-		page = alloc_page(gfp);
-		if (!page)
-			goto err;
-		sg_set_page(sgl + i, page, PAGE_SIZE, 0);
-	}
-
-	return sgl;
-
-err:
-	sg_mark_end(sgl + i);
-	crypto_scomp_sg_free(sgl);
-	return NULL;
-}
-
 static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
 {
 	struct crypto_acomp *tfm = crypto_acomp_reqtfm(req);
@@ -220,7 +173,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
 					      scratch_dst, &req->dlen, *ctx);
 	if (!ret) {
 		if (!req->dst) {
-			req->dst = crypto_scomp_sg_alloc(req->dlen, GFP_ATOMIC);
+			req->dst = sgl_alloc(req->dlen, GFP_ATOMIC, NULL);
 			if (!req->dst)
 				goto out;
 		}
@@ -274,7 +227,7 @@ int crypto_init_scomp_ops_async(struct crypto_tfm *tfm)
 
 	crt->compress = scomp_acomp_compress;
 	crt->decompress = scomp_acomp_decompress;
-	crt->dst_free = crypto_scomp_sg_free;
+	crt->dst_free = sgl_free;
 	crt->reqsize = sizeof(void *);
 
 	return 0;
diff --git a/crypto/seqiv.c b/crypto/seqiv.c
index 570b7d1aa0ca..39dbf2f7e5f5 100644
--- a/crypto/seqiv.c
+++ b/crypto/seqiv.c
@@ -144,8 +144,6 @@ static int seqiv_aead_decrypt(struct aead_request *req)
 static int seqiv_aead_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct aead_instance *inst;
-	struct crypto_aead_spawn *spawn;
-	struct aead_alg *alg;
 	int err;
 
 	inst = aead_geniv_alloc(tmpl, tb, 0, 0);
@@ -153,9 +151,6 @@ static int seqiv_aead_create(struct crypto_template *tmpl, struct rtattr **tb)
 	if (IS_ERR(inst))
 		return PTR_ERR(inst);
 
-	spawn = aead_instance_ctx(inst);
-	alg = crypto_spawn_aead_alg(spawn);
-
 	err = -EINVAL;
 	if (inst->alg.ivsize != sizeof(u64))
 		goto free_inst;
diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c
index 7e8ed96236ce..a965b9d80559 100644
--- a/crypto/sha3_generic.c
+++ b/crypto/sha3_generic.c
@@ -5,6 +5,7 @@
  * http://nvlpubs.nist.gov/nistpubs/FIPS/NIST.FIPS.202.pdf
  *
  * SHA-3 code by Jeff Garzik <jeff@garzik.org>
+ *               Ard Biesheuvel <ard.biesheuvel@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -17,12 +18,10 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <crypto/sha3.h>
-#include <asm/byteorder.h>
+#include <asm/unaligned.h>
 
 #define KECCAK_ROUNDS 24
 
-#define ROTL64(x, y) (((x) << (y)) | ((x) >> (64 - (y))))
-
 static const u64 keccakf_rndc[24] = {
 	0x0000000000000001ULL, 0x0000000000008082ULL, 0x800000000000808aULL,
 	0x8000000080008000ULL, 0x000000000000808bULL, 0x0000000080000001ULL,
@@ -34,100 +33,133 @@ static const u64 keccakf_rndc[24] = {
 	0x8000000000008080ULL, 0x0000000080000001ULL, 0x8000000080008008ULL
 };
 
-static const int keccakf_rotc[24] = {
-	1,  3,  6,  10, 15, 21, 28, 36, 45, 55, 2,  14,
-	27, 41, 56, 8,  25, 43, 62, 18, 39, 61, 20, 44
-};
-
-static const int keccakf_piln[24] = {
-	10, 7,  11, 17, 18, 3, 5,  16, 8,  21, 24, 4,
-	15, 23, 19, 13, 12, 2, 20, 14, 22, 9,  6,  1
-};
-
 /* update the state with given number of rounds */
 
-static void keccakf(u64 st[25])
+static void __attribute__((__optimize__("O3"))) keccakf(u64 st[25])
 {
-	int i, j, round;
-	u64 t, bc[5];
+	u64 t[5], tt, bc[5];
+	int round;
 
 	for (round = 0; round < KECCAK_ROUNDS; round++) {
 
 		/* Theta */
-		for (i = 0; i < 5; i++)
-			bc[i] = st[i] ^ st[i + 5] ^ st[i + 10] ^ st[i + 15]
-				^ st[i + 20];
-
-		for (i = 0; i < 5; i++) {
-			t = bc[(i + 4) % 5] ^ ROTL64(bc[(i + 1) % 5], 1);
-			for (j = 0; j < 25; j += 5)
-				st[j + i] ^= t;
-		}
+		bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20];
+		bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21];
+		bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22];
+		bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23];
+		bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24];
+
+		t[0] = bc[4] ^ rol64(bc[1], 1);
+		t[1] = bc[0] ^ rol64(bc[2], 1);
+		t[2] = bc[1] ^ rol64(bc[3], 1);
+		t[3] = bc[2] ^ rol64(bc[4], 1);
+		t[4] = bc[3] ^ rol64(bc[0], 1);
+
+		st[0] ^= t[0];
 
 		/* Rho Pi */
-		t = st[1];
-		for (i = 0; i < 24; i++) {
-			j = keccakf_piln[i];
-			bc[0] = st[j];
-			st[j] = ROTL64(t, keccakf_rotc[i]);
-			t = bc[0];
-		}
+		tt = st[1];
+		st[ 1] = rol64(st[ 6] ^ t[1], 44);
+		st[ 6] = rol64(st[ 9] ^ t[4], 20);
+		st[ 9] = rol64(st[22] ^ t[2], 61);
+		st[22] = rol64(st[14] ^ t[4], 39);
+		st[14] = rol64(st[20] ^ t[0], 18);
+		st[20] = rol64(st[ 2] ^ t[2], 62);
+		st[ 2] = rol64(st[12] ^ t[2], 43);
+		st[12] = rol64(st[13] ^ t[3], 25);
+		st[13] = rol64(st[19] ^ t[4],  8);
+		st[19] = rol64(st[23] ^ t[3], 56);
+		st[23] = rol64(st[15] ^ t[0], 41);
+		st[15] = rol64(st[ 4] ^ t[4], 27);
+		st[ 4] = rol64(st[24] ^ t[4], 14);
+		st[24] = rol64(st[21] ^ t[1],  2);
+		st[21] = rol64(st[ 8] ^ t[3], 55);
+		st[ 8] = rol64(st[16] ^ t[1], 45);
+		st[16] = rol64(st[ 5] ^ t[0], 36);
+		st[ 5] = rol64(st[ 3] ^ t[3], 28);
+		st[ 3] = rol64(st[18] ^ t[3], 21);
+		st[18] = rol64(st[17] ^ t[2], 15);
+		st[17] = rol64(st[11] ^ t[1], 10);
+		st[11] = rol64(st[ 7] ^ t[2],  6);
+		st[ 7] = rol64(st[10] ^ t[0],  3);
+		st[10] = rol64(    tt ^ t[1],  1);
 
 		/* Chi */
-		for (j = 0; j < 25; j += 5) {
-			for (i = 0; i < 5; i++)
-				bc[i] = st[j + i];
-			for (i = 0; i < 5; i++)
-				st[j + i] ^= (~bc[(i + 1) % 5]) &
-					     bc[(i + 2) % 5];
-		}
+		bc[ 0] = ~st[ 1] & st[ 2];
+		bc[ 1] = ~st[ 2] & st[ 3];
+		bc[ 2] = ~st[ 3] & st[ 4];
+		bc[ 3] = ~st[ 4] & st[ 0];
+		bc[ 4] = ~st[ 0] & st[ 1];
+		st[ 0] ^= bc[ 0];
+		st[ 1] ^= bc[ 1];
+		st[ 2] ^= bc[ 2];
+		st[ 3] ^= bc[ 3];
+		st[ 4] ^= bc[ 4];
+
+		bc[ 0] = ~st[ 6] & st[ 7];
+		bc[ 1] = ~st[ 7] & st[ 8];
+		bc[ 2] = ~st[ 8] & st[ 9];
+		bc[ 3] = ~st[ 9] & st[ 5];
+		bc[ 4] = ~st[ 5] & st[ 6];
+		st[ 5] ^= bc[ 0];
+		st[ 6] ^= bc[ 1];
+		st[ 7] ^= bc[ 2];
+		st[ 8] ^= bc[ 3];
+		st[ 9] ^= bc[ 4];
+
+		bc[ 0] = ~st[11] & st[12];
+		bc[ 1] = ~st[12] & st[13];
+		bc[ 2] = ~st[13] & st[14];
+		bc[ 3] = ~st[14] & st[10];
+		bc[ 4] = ~st[10] & st[11];
+		st[10] ^= bc[ 0];
+		st[11] ^= bc[ 1];
+		st[12] ^= bc[ 2];
+		st[13] ^= bc[ 3];
+		st[14] ^= bc[ 4];
+
+		bc[ 0] = ~st[16] & st[17];
+		bc[ 1] = ~st[17] & st[18];
+		bc[ 2] = ~st[18] & st[19];
+		bc[ 3] = ~st[19] & st[15];
+		bc[ 4] = ~st[15] & st[16];
+		st[15] ^= bc[ 0];
+		st[16] ^= bc[ 1];
+		st[17] ^= bc[ 2];
+		st[18] ^= bc[ 3];
+		st[19] ^= bc[ 4];
+
+		bc[ 0] = ~st[21] & st[22];
+		bc[ 1] = ~st[22] & st[23];
+		bc[ 2] = ~st[23] & st[24];
+		bc[ 3] = ~st[24] & st[20];
+		bc[ 4] = ~st[20] & st[21];
+		st[20] ^= bc[ 0];
+		st[21] ^= bc[ 1];
+		st[22] ^= bc[ 2];
+		st[23] ^= bc[ 3];
+		st[24] ^= bc[ 4];
 
 		/* Iota */
 		st[0] ^= keccakf_rndc[round];
 	}
 }
 
-static void sha3_init(struct sha3_state *sctx, unsigned int digest_sz)
-{
-	memset(sctx, 0, sizeof(*sctx));
-	sctx->md_len = digest_sz;
-	sctx->rsiz = 200 - 2 * digest_sz;
-	sctx->rsizw = sctx->rsiz / 8;
-}
-
-static int sha3_224_init(struct shash_desc *desc)
-{
-	struct sha3_state *sctx = shash_desc_ctx(desc);
-
-	sha3_init(sctx, SHA3_224_DIGEST_SIZE);
-	return 0;
-}
-
-static int sha3_256_init(struct shash_desc *desc)
+int crypto_sha3_init(struct shash_desc *desc)
 {
 	struct sha3_state *sctx = shash_desc_ctx(desc);
+	unsigned int digest_size = crypto_shash_digestsize(desc->tfm);
 
-	sha3_init(sctx, SHA3_256_DIGEST_SIZE);
-	return 0;
-}
-
-static int sha3_384_init(struct shash_desc *desc)
-{
-	struct sha3_state *sctx = shash_desc_ctx(desc);
-
-	sha3_init(sctx, SHA3_384_DIGEST_SIZE);
-	return 0;
-}
-
-static int sha3_512_init(struct shash_desc *desc)
-{
-	struct sha3_state *sctx = shash_desc_ctx(desc);
+	sctx->rsiz = 200 - 2 * digest_size;
+	sctx->rsizw = sctx->rsiz / 8;
+	sctx->partial = 0;
 
-	sha3_init(sctx, SHA3_512_DIGEST_SIZE);
+	memset(sctx->st, 0, sizeof(sctx->st));
 	return 0;
 }
+EXPORT_SYMBOL(crypto_sha3_init);
 
-static int sha3_update(struct shash_desc *desc, const u8 *data,
+int crypto_sha3_update(struct shash_desc *desc, const u8 *data,
 		       unsigned int len)
 {
 	struct sha3_state *sctx = shash_desc_ctx(desc);
@@ -149,7 +181,7 @@ static int sha3_update(struct shash_desc *desc, const u8 *data,
 			unsigned int i;
 
 			for (i = 0; i < sctx->rsizw; i++)
-				sctx->st[i] ^= ((u64 *) src)[i];
+				sctx->st[i] ^= get_unaligned_le64(src + 8 * i);
 			keccakf(sctx->st);
 
 			done += sctx->rsiz;
@@ -163,125 +195,89 @@ static int sha3_update(struct shash_desc *desc, const u8 *data,
 
 	return 0;
 }
+EXPORT_SYMBOL(crypto_sha3_update);
 
-static int sha3_final(struct shash_desc *desc, u8 *out)
+int crypto_sha3_final(struct shash_desc *desc, u8 *out)
 {
 	struct sha3_state *sctx = shash_desc_ctx(desc);
 	unsigned int i, inlen = sctx->partial;
+	unsigned int digest_size = crypto_shash_digestsize(desc->tfm);
+	__le64 *digest = (__le64 *)out;
 
 	sctx->buf[inlen++] = 0x06;
 	memset(sctx->buf + inlen, 0, sctx->rsiz - inlen);
 	sctx->buf[sctx->rsiz - 1] |= 0x80;
 
 	for (i = 0; i < sctx->rsizw; i++)
-		sctx->st[i] ^= ((u64 *) sctx->buf)[i];
+		sctx->st[i] ^= get_unaligned_le64(sctx->buf + 8 * i);
 
 	keccakf(sctx->st);
 
-	for (i = 0; i < sctx->rsizw; i++)
-		sctx->st[i] = cpu_to_le64(sctx->st[i]);
+	for (i = 0; i < digest_size / 8; i++)
+		put_unaligned_le64(sctx->st[i], digest++);
 
-	memcpy(out, sctx->st, sctx->md_len);
+	if (digest_size & 4)
+		put_unaligned_le32(sctx->st[i], (__le32 *)digest);
 
 	memset(sctx, 0, sizeof(*sctx));
 	return 0;
 }
-
-static struct shash_alg sha3_224 = {
-	.digestsize	=	SHA3_224_DIGEST_SIZE,
-	.init		=	sha3_224_init,
-	.update		=	sha3_update,
-	.final		=	sha3_final,
-	.descsize	=	sizeof(struct sha3_state),
-	.base		=	{
-		.cra_name	=	"sha3-224",
-		.cra_driver_name =	"sha3-224-generic",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
-		.cra_blocksize	=	SHA3_224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-};
-
-static struct shash_alg sha3_256 = {
-	.digestsize	=	SHA3_256_DIGEST_SIZE,
-	.init		=	sha3_256_init,
-	.update		=	sha3_update,
-	.final		=	sha3_final,
-	.descsize	=	sizeof(struct sha3_state),
-	.base		=	{
-		.cra_name	=	"sha3-256",
-		.cra_driver_name =	"sha3-256-generic",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
-		.cra_blocksize	=	SHA3_256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-};
-
-static struct shash_alg sha3_384 = {
-	.digestsize	=	SHA3_384_DIGEST_SIZE,
-	.init		=	sha3_384_init,
-	.update		=	sha3_update,
-	.final		=	sha3_final,
-	.descsize	=	sizeof(struct sha3_state),
-	.base		=	{
-		.cra_name	=	"sha3-384",
-		.cra_driver_name =	"sha3-384-generic",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
-		.cra_blocksize	=	SHA3_384_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-};
-
-static struct shash_alg sha3_512 = {
-	.digestsize	=	SHA3_512_DIGEST_SIZE,
-	.init		=	sha3_512_init,
-	.update		=	sha3_update,
-	.final		=	sha3_final,
-	.descsize	=	sizeof(struct sha3_state),
-	.base		=	{
-		.cra_name	=	"sha3-512",
-		.cra_driver_name =	"sha3-512-generic",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
-		.cra_blocksize	=	SHA3_512_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-};
+EXPORT_SYMBOL(crypto_sha3_final);
+
+static struct shash_alg algs[] = { {
+	.digestsize		= SHA3_224_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= crypto_sha3_update,
+	.final			= crypto_sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-224",
+	.base.cra_driver_name	= "sha3-224-generic",
+	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+	.base.cra_blocksize	= SHA3_224_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.digestsize		= SHA3_256_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= crypto_sha3_update,
+	.final			= crypto_sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-256",
+	.base.cra_driver_name	= "sha3-256-generic",
+	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+	.base.cra_blocksize	= SHA3_256_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.digestsize		= SHA3_384_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= crypto_sha3_update,
+	.final			= crypto_sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-384",
+	.base.cra_driver_name	= "sha3-384-generic",
+	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+	.base.cra_blocksize	= SHA3_384_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.digestsize		= SHA3_512_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= crypto_sha3_update,
+	.final			= crypto_sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-512",
+	.base.cra_driver_name	= "sha3-512-generic",
+	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+	.base.cra_blocksize	= SHA3_512_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+} };
 
 static int __init sha3_generic_mod_init(void)
 {
-	int ret;
-
-	ret = crypto_register_shash(&sha3_224);
-	if (ret < 0)
-		goto err_out;
-	ret = crypto_register_shash(&sha3_256);
-	if (ret < 0)
-		goto err_out_224;
-	ret = crypto_register_shash(&sha3_384);
-	if (ret < 0)
-		goto err_out_256;
-	ret = crypto_register_shash(&sha3_512);
-	if (ret < 0)
-		goto err_out_384;
-
-	return 0;
-
-err_out_384:
-	crypto_unregister_shash(&sha3_384);
-err_out_256:
-	crypto_unregister_shash(&sha3_256);
-err_out_224:
-	crypto_unregister_shash(&sha3_224);
-err_out:
-	return ret;
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
 }
 
 static void __exit sha3_generic_mod_fini(void)
 {
-	crypto_unregister_shash(&sha3_224);
-	crypto_unregister_shash(&sha3_256);
-	crypto_unregister_shash(&sha3_384);
-	crypto_unregister_shash(&sha3_512);
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
 }
 
 module_init(sha3_generic_mod_init);
diff --git a/crypto/shash.c b/crypto/shash.c
index 325a14da5827..5d732c6bb4b2 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -25,11 +25,12 @@
 
 static const struct crypto_type crypto_shash_type;
 
-static int shash_no_setkey(struct crypto_shash *tfm, const u8 *key,
-			   unsigned int keylen)
+int shash_no_setkey(struct crypto_shash *tfm, const u8 *key,
+		    unsigned int keylen)
 {
 	return -ENOSYS;
 }
+EXPORT_SYMBOL_GPL(shash_no_setkey);
 
 static int shash_setkey_unaligned(struct crypto_shash *tfm, const u8 *key,
 				  unsigned int keylen)
@@ -57,11 +58,18 @@ int crypto_shash_setkey(struct crypto_shash *tfm, const u8 *key,
 {
 	struct shash_alg *shash = crypto_shash_alg(tfm);
 	unsigned long alignmask = crypto_shash_alignmask(tfm);
+	int err;
 
 	if ((unsigned long)key & alignmask)
-		return shash_setkey_unaligned(tfm, key, keylen);
+		err = shash_setkey_unaligned(tfm, key, keylen);
+	else
+		err = shash->setkey(tfm, key, keylen);
+
+	if (err)
+		return err;
 
-	return shash->setkey(tfm, key, keylen);
+	crypto_shash_clear_flags(tfm, CRYPTO_TFM_NEED_KEY);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(crypto_shash_setkey);
 
@@ -180,6 +188,9 @@ int crypto_shash_digest(struct shash_desc *desc, const u8 *data,
 	struct shash_alg *shash = crypto_shash_alg(tfm);
 	unsigned long alignmask = crypto_shash_alignmask(tfm);
 
+	if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
+		return -ENOKEY;
+
 	if (((unsigned long)data | (unsigned long)out) & alignmask)
 		return shash_digest_unaligned(desc, data, len, out);
 
@@ -359,7 +370,8 @@ int crypto_init_shash_ops_async(struct crypto_tfm *tfm)
 	crt->digest = shash_async_digest;
 	crt->setkey = shash_async_setkey;
 
-	crt->has_setkey = alg->setkey != shash_no_setkey;
+	crypto_ahash_set_flags(crt, crypto_shash_get_flags(shash) &
+				    CRYPTO_TFM_NEED_KEY);
 
 	if (alg->export)
 		crt->export = shash_async_export;
@@ -374,8 +386,14 @@ int crypto_init_shash_ops_async(struct crypto_tfm *tfm)
 static int crypto_shash_init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_shash *hash = __crypto_shash_cast(tfm);
+	struct shash_alg *alg = crypto_shash_alg(hash);
+
+	hash->descsize = alg->descsize;
+
+	if (crypto_shash_alg_has_setkey(alg) &&
+	    !(alg->base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY))
+		crypto_shash_set_flags(hash, CRYPTO_TFM_NEED_KEY);
 
-	hash->descsize = crypto_shash_alg(hash)->descsize;
 	return 0;
 }
 
diff --git a/crypto/simd.c b/crypto/simd.c
index 88203370a62f..208226d7f908 100644
--- a/crypto/simd.c
+++ b/crypto/simd.c
@@ -19,9 +19,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
- * USA
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  *
  */
 
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index d5692e35fab1..0fe2a2923ad0 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -449,6 +449,8 @@ static int skcipher_walk_skcipher(struct skcipher_walk *walk,
 
 	walk->total = req->cryptlen;
 	walk->nbytes = 0;
+	walk->iv = req->iv;
+	walk->oiv = req->iv;
 
 	if (unlikely(!walk->total))
 		return 0;
@@ -456,9 +458,6 @@ static int skcipher_walk_skcipher(struct skcipher_walk *walk,
 	scatterwalk_start(&walk->in, req->src);
 	scatterwalk_start(&walk->out, req->dst);
 
-	walk->iv = req->iv;
-	walk->oiv = req->iv;
-
 	walk->flags &= ~SKCIPHER_WALK_SLEEP;
 	walk->flags |= req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ?
 		       SKCIPHER_WALK_SLEEP : 0;
@@ -510,6 +509,8 @@ static int skcipher_walk_aead_common(struct skcipher_walk *walk,
 	int err;
 
 	walk->nbytes = 0;
+	walk->iv = req->iv;
+	walk->oiv = req->iv;
 
 	if (unlikely(!walk->total))
 		return 0;
@@ -522,8 +523,8 @@ static int skcipher_walk_aead_common(struct skcipher_walk *walk,
 	scatterwalk_copychunks(NULL, &walk->in, req->assoclen, 2);
 	scatterwalk_copychunks(NULL, &walk->out, req->assoclen, 2);
 
-	walk->iv = req->iv;
-	walk->oiv = req->iv;
+	scatterwalk_done(&walk->in, 0, walk->total);
+	scatterwalk_done(&walk->out, 0, walk->total);
 
 	if (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP)
 		walk->flags |= SKCIPHER_WALK_SLEEP;
@@ -597,8 +598,11 @@ static int skcipher_setkey_blkcipher(struct crypto_skcipher *tfm,
 	err = crypto_blkcipher_setkey(blkcipher, key, keylen);
 	crypto_skcipher_set_flags(tfm, crypto_blkcipher_get_flags(blkcipher) &
 				       CRYPTO_TFM_RES_MASK);
+	if (err)
+		return err;
 
-	return err;
+	crypto_skcipher_clear_flags(tfm, CRYPTO_TFM_NEED_KEY);
+	return 0;
 }
 
 static int skcipher_crypt_blkcipher(struct skcipher_request *req,
@@ -673,6 +677,9 @@ static int crypto_init_skcipher_ops_blkcipher(struct crypto_tfm *tfm)
 	skcipher->ivsize = crypto_blkcipher_ivsize(blkcipher);
 	skcipher->keysize = calg->cra_blkcipher.max_keysize;
 
+	if (skcipher->keysize)
+		crypto_skcipher_set_flags(skcipher, CRYPTO_TFM_NEED_KEY);
+
 	return 0;
 }
 
@@ -691,8 +698,11 @@ static int skcipher_setkey_ablkcipher(struct crypto_skcipher *tfm,
 	crypto_skcipher_set_flags(tfm,
 				  crypto_ablkcipher_get_flags(ablkcipher) &
 				  CRYPTO_TFM_RES_MASK);
+	if (err)
+		return err;
 
-	return err;
+	crypto_skcipher_clear_flags(tfm, CRYPTO_TFM_NEED_KEY);
+	return 0;
 }
 
 static int skcipher_crypt_ablkcipher(struct skcipher_request *req,
@@ -766,6 +776,9 @@ static int crypto_init_skcipher_ops_ablkcipher(struct crypto_tfm *tfm)
 			    sizeof(struct ablkcipher_request);
 	skcipher->keysize = calg->cra_ablkcipher.max_keysize;
 
+	if (skcipher->keysize)
+		crypto_skcipher_set_flags(skcipher, CRYPTO_TFM_NEED_KEY);
+
 	return 0;
 }
 
@@ -795,6 +808,7 @@ static int skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
 {
 	struct skcipher_alg *cipher = crypto_skcipher_alg(tfm);
 	unsigned long alignmask = crypto_skcipher_alignmask(tfm);
+	int err;
 
 	if (keylen < cipher->min_keysize || keylen > cipher->max_keysize) {
 		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
@@ -802,9 +816,15 @@ static int skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
 	}
 
 	if ((unsigned long)key & alignmask)
-		return skcipher_setkey_unaligned(tfm, key, keylen);
+		err = skcipher_setkey_unaligned(tfm, key, keylen);
+	else
+		err = cipher->setkey(tfm, key, keylen);
+
+	if (err)
+		return err;
 
-	return cipher->setkey(tfm, key, keylen);
+	crypto_skcipher_clear_flags(tfm, CRYPTO_TFM_NEED_KEY);
+	return 0;
 }
 
 static void crypto_skcipher_exit_tfm(struct crypto_tfm *tfm)
@@ -833,6 +853,9 @@ static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm)
 	skcipher->ivsize = alg->ivsize;
 	skcipher->keysize = alg->max_keysize;
 
+	if (skcipher->keysize)
+		crypto_skcipher_set_flags(skcipher, CRYPTO_TFM_NEED_KEY);
+
 	if (alg->exit)
 		skcipher->base.exit = crypto_skcipher_exit_tfm;
 
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 9267cbdb14d2..14213a096fd2 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -67,6 +67,7 @@ static char *alg = NULL;
 static u32 type;
 static u32 mask;
 static int mode;
+static u32 num_mb = 8;
 static char *tvmem[TVMEMSIZE];
 
 static char *check[] = {
@@ -79,6 +80,66 @@ static char *check[] = {
 	NULL
 };
 
+static u32 block_sizes[] = { 16, 64, 256, 1024, 8192, 0 };
+static u32 aead_sizes[] = { 16, 64, 256, 512, 1024, 2048, 4096, 8192, 0 };
+
+#define XBUFSIZE 8
+#define MAX_IVLEN 32
+
+static int testmgr_alloc_buf(char *buf[XBUFSIZE])
+{
+	int i;
+
+	for (i = 0; i < XBUFSIZE; i++) {
+		buf[i] = (void *)__get_free_page(GFP_KERNEL);
+		if (!buf[i])
+			goto err_free_buf;
+	}
+
+	return 0;
+
+err_free_buf:
+	while (i-- > 0)
+		free_page((unsigned long)buf[i]);
+
+	return -ENOMEM;
+}
+
+static void testmgr_free_buf(char *buf[XBUFSIZE])
+{
+	int i;
+
+	for (i = 0; i < XBUFSIZE; i++)
+		free_page((unsigned long)buf[i]);
+}
+
+static void sg_init_aead(struct scatterlist *sg, char *xbuf[XBUFSIZE],
+			 unsigned int buflen, const void *assoc,
+			 unsigned int aad_size)
+{
+	int np = (buflen + PAGE_SIZE - 1)/PAGE_SIZE;
+	int k, rem;
+
+	if (np > XBUFSIZE) {
+		rem = PAGE_SIZE;
+		np = XBUFSIZE;
+	} else {
+		rem = buflen % PAGE_SIZE;
+	}
+
+	sg_init_table(sg, np + 1);
+
+	sg_set_buf(&sg[0], assoc, aad_size);
+
+	if (rem)
+		np--;
+	for (k = 0; k < np; k++)
+		sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE);
+
+	if (rem)
+		sg_set_buf(&sg[k + 1], xbuf[k], rem);
+}
+
 static inline int do_one_aead_op(struct aead_request *req, int ret)
 {
 	struct crypto_wait *wait = req->base.data;
@@ -86,6 +147,298 @@ static inline int do_one_aead_op(struct aead_request *req, int ret)
 	return crypto_wait_req(ret, wait);
 }
 
+struct test_mb_aead_data {
+	struct scatterlist sg[XBUFSIZE];
+	struct scatterlist sgout[XBUFSIZE];
+	struct aead_request *req;
+	struct crypto_wait wait;
+	char *xbuf[XBUFSIZE];
+	char *xoutbuf[XBUFSIZE];
+	char *axbuf[XBUFSIZE];
+};
+
+static int do_mult_aead_op(struct test_mb_aead_data *data, int enc,
+				u32 num_mb)
+{
+	int i, rc[num_mb], err = 0;
+
+	/* Fire up a bunch of concurrent requests */
+	for (i = 0; i < num_mb; i++) {
+		if (enc == ENCRYPT)
+			rc[i] = crypto_aead_encrypt(data[i].req);
+		else
+			rc[i] = crypto_aead_decrypt(data[i].req);
+	}
+
+	/* Wait for all requests to finish */
+	for (i = 0; i < num_mb; i++) {
+		rc[i] = crypto_wait_req(rc[i], &data[i].wait);
+
+		if (rc[i]) {
+			pr_info("concurrent request %d error %d\n", i, rc[i]);
+			err = rc[i];
+		}
+	}
+
+	return err;
+}
+
+static int test_mb_aead_jiffies(struct test_mb_aead_data *data, int enc,
+				int blen, int secs, u32 num_mb)
+{
+	unsigned long start, end;
+	int bcount;
+	int ret;
+
+	for (start = jiffies, end = start + secs * HZ, bcount = 0;
+	     time_before(jiffies, end); bcount++) {
+		ret = do_mult_aead_op(data, enc, num_mb);
+		if (ret)
+			return ret;
+	}
+
+	pr_cont("%d operations in %d seconds (%ld bytes)\n",
+		bcount * num_mb, secs, (long)bcount * blen * num_mb);
+	return 0;
+}
+
+static int test_mb_aead_cycles(struct test_mb_aead_data *data, int enc,
+			       int blen, u32 num_mb)
+{
+	unsigned long cycles = 0;
+	int ret = 0;
+	int i;
+
+	/* Warm-up run. */
+	for (i = 0; i < 4; i++) {
+		ret = do_mult_aead_op(data, enc, num_mb);
+		if (ret)
+			goto out;
+	}
+
+	/* The real thing. */
+	for (i = 0; i < 8; i++) {
+		cycles_t start, end;
+
+		start = get_cycles();
+		ret = do_mult_aead_op(data, enc, num_mb);
+		end = get_cycles();
+
+		if (ret)
+			goto out;
+
+		cycles += end - start;
+	}
+
+out:
+	if (ret == 0)
+		pr_cont("1 operation in %lu cycles (%d bytes)\n",
+			(cycles + 4) / (8 * num_mb), blen);
+
+	return ret;
+}
+
+static void test_mb_aead_speed(const char *algo, int enc, int secs,
+			       struct aead_speed_template *template,
+			       unsigned int tcount, u8 authsize,
+			       unsigned int aad_size, u8 *keysize, u32 num_mb)
+{
+	struct test_mb_aead_data *data;
+	struct crypto_aead *tfm;
+	unsigned int i, j, iv_len;
+	const char *key;
+	const char *e;
+	void *assoc;
+	u32 *b_size;
+	char *iv;
+	int ret;
+
+
+	if (aad_size >= PAGE_SIZE) {
+		pr_err("associate data length (%u) too big\n", aad_size);
+		return;
+	}
+
+	iv = kzalloc(MAX_IVLEN, GFP_KERNEL);
+	if (!iv)
+		return;
+
+	if (enc == ENCRYPT)
+		e = "encryption";
+	else
+		e = "decryption";
+
+	data = kcalloc(num_mb, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out_free_iv;
+
+	tfm = crypto_alloc_aead(algo, 0, 0);
+	if (IS_ERR(tfm)) {
+		pr_err("failed to load transform for %s: %ld\n",
+			algo, PTR_ERR(tfm));
+		goto out_free_data;
+	}
+
+	ret = crypto_aead_setauthsize(tfm, authsize);
+
+	for (i = 0; i < num_mb; ++i)
+		if (testmgr_alloc_buf(data[i].xbuf)) {
+			while (i--)
+				testmgr_free_buf(data[i].xbuf);
+			goto out_free_tfm;
+		}
+
+	for (i = 0; i < num_mb; ++i)
+		if (testmgr_alloc_buf(data[i].axbuf)) {
+			while (i--)
+				testmgr_free_buf(data[i].axbuf);
+			goto out_free_xbuf;
+		}
+
+	for (i = 0; i < num_mb; ++i)
+		if (testmgr_alloc_buf(data[i].xoutbuf)) {
+			while (i--)
+				testmgr_free_buf(data[i].xoutbuf);
+			goto out_free_axbuf;
+		}
+
+	for (i = 0; i < num_mb; ++i) {
+		data[i].req = aead_request_alloc(tfm, GFP_KERNEL);
+		if (!data[i].req) {
+			pr_err("alg: skcipher: Failed to allocate request for %s\n",
+			       algo);
+			while (i--)
+				aead_request_free(data[i].req);
+			goto out_free_xoutbuf;
+		}
+	}
+
+	for (i = 0; i < num_mb; ++i) {
+		crypto_init_wait(&data[i].wait);
+		aead_request_set_callback(data[i].req,
+					  CRYPTO_TFM_REQ_MAY_BACKLOG,
+					  crypto_req_done, &data[i].wait);
+	}
+
+	pr_info("\ntesting speed of multibuffer %s (%s) %s\n", algo,
+		get_driver_name(crypto_aead, tfm), e);
+
+	i = 0;
+	do {
+		b_size = aead_sizes;
+		do {
+			if (*b_size + authsize > XBUFSIZE * PAGE_SIZE) {
+				pr_err("template (%u) too big for buffer (%lu)\n",
+				       authsize + *b_size,
+				       XBUFSIZE * PAGE_SIZE);
+				goto out;
+			}
+
+			pr_info("test %u (%d bit key, %d byte blocks): ", i,
+				*keysize * 8, *b_size);
+
+			/* Set up tfm global state, i.e. the key */
+
+			memset(tvmem[0], 0xff, PAGE_SIZE);
+			key = tvmem[0];
+			for (j = 0; j < tcount; j++) {
+				if (template[j].klen == *keysize) {
+					key = template[j].key;
+					break;
+				}
+			}
+
+			crypto_aead_clear_flags(tfm, ~0);
+
+			ret = crypto_aead_setkey(tfm, key, *keysize);
+			if (ret) {
+				pr_err("setkey() failed flags=%x\n",
+				       crypto_aead_get_flags(tfm));
+				goto out;
+			}
+
+			iv_len = crypto_aead_ivsize(tfm);
+			if (iv_len)
+				memset(iv, 0xff, iv_len);
+
+			/* Now setup per request stuff, i.e. buffers */
+
+			for (j = 0; j < num_mb; ++j) {
+				struct test_mb_aead_data *cur = &data[j];
+
+				assoc = cur->axbuf[0];
+				memset(assoc, 0xff, aad_size);
+
+				sg_init_aead(cur->sg, cur->xbuf,
+					     *b_size + (enc ? 0 : authsize),
+					     assoc, aad_size);
+
+				sg_init_aead(cur->sgout, cur->xoutbuf,
+					     *b_size + (enc ? authsize : 0),
+					     assoc, aad_size);
+
+				aead_request_set_ad(cur->req, aad_size);
+
+				if (!enc) {
+
+					aead_request_set_crypt(cur->req,
+							       cur->sgout,
+							       cur->sg,
+							       *b_size, iv);
+					ret = crypto_aead_encrypt(cur->req);
+					ret = do_one_aead_op(cur->req, ret);
+
+					if (ret) {
+						pr_err("calculating auth failed failed (%d)\n",
+						       ret);
+						break;
+					}
+				}
+
+				aead_request_set_crypt(cur->req, cur->sg,
+						       cur->sgout, *b_size +
+						       (enc ? 0 : authsize),
+						       iv);
+
+			}
+
+			if (secs)
+				ret = test_mb_aead_jiffies(data, enc, *b_size,
+							   secs, num_mb);
+			else
+				ret = test_mb_aead_cycles(data, enc, *b_size,
+							  num_mb);
+
+			if (ret) {
+				pr_err("%s() failed return code=%d\n", e, ret);
+				break;
+			}
+			b_size++;
+			i++;
+		} while (*b_size);
+		keysize++;
+	} while (*keysize);
+
+out:
+	for (i = 0; i < num_mb; ++i)
+		aead_request_free(data[i].req);
+out_free_xoutbuf:
+	for (i = 0; i < num_mb; ++i)
+		testmgr_free_buf(data[i].xoutbuf);
+out_free_axbuf:
+	for (i = 0; i < num_mb; ++i)
+		testmgr_free_buf(data[i].axbuf);
+out_free_xbuf:
+	for (i = 0; i < num_mb; ++i)
+		testmgr_free_buf(data[i].xbuf);
+out_free_tfm:
+	crypto_free_aead(tfm);
+out_free_data:
+	kfree(data);
+out_free_iv:
+	kfree(iv);
+}
+
 static int test_aead_jiffies(struct aead_request *req, int enc,
 				int blen, int secs)
 {
@@ -151,60 +504,6 @@ out:
 	return ret;
 }
 
-static u32 block_sizes[] = { 16, 64, 256, 1024, 8192, 0 };
-static u32 aead_sizes[] = { 16, 64, 256, 512, 1024, 2048, 4096, 8192, 0 };
-
-#define XBUFSIZE 8
-#define MAX_IVLEN 32
-
-static int testmgr_alloc_buf(char *buf[XBUFSIZE])
-{
-	int i;
-
-	for (i = 0; i < XBUFSIZE; i++) {
-		buf[i] = (void *)__get_free_page(GFP_KERNEL);
-		if (!buf[i])
-			goto err_free_buf;
-	}
-
-	return 0;
-
-err_free_buf:
-	while (i-- > 0)
-		free_page((unsigned long)buf[i]);
-
-	return -ENOMEM;
-}
-
-static void testmgr_free_buf(char *buf[XBUFSIZE])
-{
-	int i;
-
-	for (i = 0; i < XBUFSIZE; i++)
-		free_page((unsigned long)buf[i]);
-}
-
-static void sg_init_aead(struct scatterlist *sg, char *xbuf[XBUFSIZE],
-			unsigned int buflen)
-{
-	int np = (buflen + PAGE_SIZE - 1)/PAGE_SIZE;
-	int k, rem;
-
-	if (np > XBUFSIZE) {
-		rem = PAGE_SIZE;
-		np = XBUFSIZE;
-	} else {
-		rem = buflen % PAGE_SIZE;
-	}
-
-	sg_init_table(sg, np + 1);
-	np--;
-	for (k = 0; k < np; k++)
-		sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE);
-
-	sg_set_buf(&sg[k + 1], xbuf[k], rem);
-}
-
 static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 			    struct aead_speed_template *template,
 			    unsigned int tcount, u8 authsize,
@@ -316,19 +615,37 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 				goto out;
 			}
 
-			sg_init_aead(sg, xbuf,
-				    *b_size + (enc ? 0 : authsize));
+			sg_init_aead(sg, xbuf, *b_size + (enc ? 0 : authsize),
+				     assoc, aad_size);
 
 			sg_init_aead(sgout, xoutbuf,
-				    *b_size + (enc ? authsize : 0));
+				     *b_size + (enc ? authsize : 0), assoc,
+				     aad_size);
 
-			sg_set_buf(&sg[0], assoc, aad_size);
-			sg_set_buf(&sgout[0], assoc, aad_size);
+			aead_request_set_ad(req, aad_size);
+
+			if (!enc) {
+
+				/*
+				 * For decryption we need a proper auth so
+				 * we do the encryption path once with buffers
+				 * reversed (input <-> output) to calculate it
+				 */
+				aead_request_set_crypt(req, sgout, sg,
+						       *b_size, iv);
+				ret = do_one_aead_op(req,
+						     crypto_aead_encrypt(req));
+
+				if (ret) {
+					pr_err("calculating auth failed failed (%d)\n",
+					       ret);
+					break;
+				}
+			}
 
 			aead_request_set_crypt(req, sg, sgout,
 					       *b_size + (enc ? 0 : authsize),
 					       iv);
-			aead_request_set_ad(req, aad_size);
 
 			if (secs)
 				ret = test_aead_jiffies(req, enc, *b_size,
@@ -381,24 +698,98 @@ static inline int do_one_ahash_op(struct ahash_request *req, int ret)
 }
 
 struct test_mb_ahash_data {
-	struct scatterlist sg[TVMEMSIZE];
+	struct scatterlist sg[XBUFSIZE];
 	char result[64];
 	struct ahash_request *req;
 	struct crypto_wait wait;
 	char *xbuf[XBUFSIZE];
 };
 
-static void test_mb_ahash_speed(const char *algo, unsigned int sec,
-				struct hash_speed *speed)
+static inline int do_mult_ahash_op(struct test_mb_ahash_data *data, u32 num_mb)
+{
+	int i, rc[num_mb], err = 0;
+
+	/* Fire up a bunch of concurrent requests */
+	for (i = 0; i < num_mb; i++)
+		rc[i] = crypto_ahash_digest(data[i].req);
+
+	/* Wait for all requests to finish */
+	for (i = 0; i < num_mb; i++) {
+		rc[i] = crypto_wait_req(rc[i], &data[i].wait);
+
+		if (rc[i]) {
+			pr_info("concurrent request %d error %d\n", i, rc[i]);
+			err = rc[i];
+		}
+	}
+
+	return err;
+}
+
+static int test_mb_ahash_jiffies(struct test_mb_ahash_data *data, int blen,
+				 int secs, u32 num_mb)
+{
+	unsigned long start, end;
+	int bcount;
+	int ret;
+
+	for (start = jiffies, end = start + secs * HZ, bcount = 0;
+	     time_before(jiffies, end); bcount++) {
+		ret = do_mult_ahash_op(data, num_mb);
+		if (ret)
+			return ret;
+	}
+
+	pr_cont("%d operations in %d seconds (%ld bytes)\n",
+		bcount * num_mb, secs, (long)bcount * blen * num_mb);
+	return 0;
+}
+
+static int test_mb_ahash_cycles(struct test_mb_ahash_data *data, int blen,
+				u32 num_mb)
+{
+	unsigned long cycles = 0;
+	int ret = 0;
+	int i;
+
+	/* Warm-up run. */
+	for (i = 0; i < 4; i++) {
+		ret = do_mult_ahash_op(data, num_mb);
+		if (ret)
+			goto out;
+	}
+
+	/* The real thing. */
+	for (i = 0; i < 8; i++) {
+		cycles_t start, end;
+
+		start = get_cycles();
+		ret = do_mult_ahash_op(data, num_mb);
+		end = get_cycles();
+
+		if (ret)
+			goto out;
+
+		cycles += end - start;
+	}
+
+out:
+	if (ret == 0)
+		pr_cont("1 operation in %lu cycles (%d bytes)\n",
+			(cycles + 4) / (8 * num_mb), blen);
+
+	return ret;
+}
+
+static void test_mb_ahash_speed(const char *algo, unsigned int secs,
+				struct hash_speed *speed, u32 num_mb)
 {
 	struct test_mb_ahash_data *data;
 	struct crypto_ahash *tfm;
-	unsigned long start, end;
-	unsigned long cycles;
 	unsigned int i, j, k;
 	int ret;
 
-	data = kzalloc(sizeof(*data) * 8, GFP_KERNEL);
+	data = kcalloc(num_mb, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return;
 
@@ -409,7 +800,7 @@ static void test_mb_ahash_speed(const char *algo, unsigned int sec,
 		goto free_data;
 	}
 
-	for (i = 0; i < 8; ++i) {
+	for (i = 0; i < num_mb; ++i) {
 		if (testmgr_alloc_buf(data[i].xbuf))
 			goto out;
 
@@ -424,7 +815,12 @@ static void test_mb_ahash_speed(const char *algo, unsigned int sec,
 
 		ahash_request_set_callback(data[i].req, 0, crypto_req_done,
 					   &data[i].wait);
-		test_hash_sg_init(data[i].sg);
+
+		sg_init_table(data[i].sg, XBUFSIZE);
+		for (j = 0; j < XBUFSIZE; j++) {
+			sg_set_buf(data[i].sg + j, data[i].xbuf[j], PAGE_SIZE);
+			memset(data[i].xbuf[j], 0xff, PAGE_SIZE);
+		}
 	}
 
 	pr_info("\ntesting speed of multibuffer %s (%s)\n", algo,
@@ -435,16 +831,16 @@ static void test_mb_ahash_speed(const char *algo, unsigned int sec,
 		if (speed[i].blen != speed[i].plen)
 			continue;
 
-		if (speed[i].blen > TVMEMSIZE * PAGE_SIZE) {
+		if (speed[i].blen > XBUFSIZE * PAGE_SIZE) {
 			pr_err("template (%u) too big for tvmem (%lu)\n",
-			       speed[i].blen, TVMEMSIZE * PAGE_SIZE);
+			       speed[i].blen, XBUFSIZE * PAGE_SIZE);
 			goto out;
 		}
 
 		if (speed[i].klen)
 			crypto_ahash_setkey(tfm, tvmem[0], speed[i].klen);
 
-		for (k = 0; k < 8; k++)
+		for (k = 0; k < num_mb; k++)
 			ahash_request_set_crypt(data[k].req, data[k].sg,
 						data[k].result, speed[i].blen);
 
@@ -453,34 +849,12 @@ static void test_mb_ahash_speed(const char *algo, unsigned int sec,
 			i, speed[i].blen, speed[i].plen,
 			speed[i].blen / speed[i].plen);
 
-		start = get_cycles();
-
-		for (k = 0; k < 8; k++) {
-			ret = crypto_ahash_digest(data[k].req);
-			if (ret == -EINPROGRESS) {
-				ret = 0;
-				continue;
-			}
-
-			if (ret)
-				break;
-
-			crypto_req_done(&data[k].req->base, 0);
-		}
-
-		for (j = 0; j < k; j++) {
-			struct crypto_wait *wait = &data[j].wait;
-			int wait_ret;
-
-			wait_ret = crypto_wait_req(-EINPROGRESS, wait);
-			if (wait_ret)
-				ret = wait_ret;
-		}
+		if (secs)
+			ret = test_mb_ahash_jiffies(data, speed[i].blen, secs,
+						    num_mb);
+		else
+			ret = test_mb_ahash_cycles(data, speed[i].blen, num_mb);
 
-		end = get_cycles();
-		cycles = end - start;
-		pr_cont("%6lu cycles/operation, %4lu cycles/byte\n",
-			cycles, cycles / (8 * speed[i].blen));
 
 		if (ret) {
 			pr_err("At least one hashing failed ret=%d\n", ret);
@@ -489,10 +863,10 @@ static void test_mb_ahash_speed(const char *algo, unsigned int sec,
 	}
 
 out:
-	for (k = 0; k < 8; ++k)
+	for (k = 0; k < num_mb; ++k)
 		ahash_request_free(data[k].req);
 
-	for (k = 0; k < 8; ++k)
+	for (k = 0; k < num_mb; ++k)
 		testmgr_free_buf(data[k].xbuf);
 
 	crypto_free_ahash(tfm);
@@ -736,6 +1110,254 @@ static void test_hash_speed(const char *algo, unsigned int secs,
 	return test_ahash_speed_common(algo, secs, speed, CRYPTO_ALG_ASYNC);
 }
 
+struct test_mb_skcipher_data {
+	struct scatterlist sg[XBUFSIZE];
+	struct skcipher_request *req;
+	struct crypto_wait wait;
+	char *xbuf[XBUFSIZE];
+};
+
+static int do_mult_acipher_op(struct test_mb_skcipher_data *data, int enc,
+				u32 num_mb)
+{
+	int i, rc[num_mb], err = 0;
+
+	/* Fire up a bunch of concurrent requests */
+	for (i = 0; i < num_mb; i++) {
+		if (enc == ENCRYPT)
+			rc[i] = crypto_skcipher_encrypt(data[i].req);
+		else
+			rc[i] = crypto_skcipher_decrypt(data[i].req);
+	}
+
+	/* Wait for all requests to finish */
+	for (i = 0; i < num_mb; i++) {
+		rc[i] = crypto_wait_req(rc[i], &data[i].wait);
+
+		if (rc[i]) {
+			pr_info("concurrent request %d error %d\n", i, rc[i]);
+			err = rc[i];
+		}
+	}
+
+	return err;
+}
+
+static int test_mb_acipher_jiffies(struct test_mb_skcipher_data *data, int enc,
+				int blen, int secs, u32 num_mb)
+{
+	unsigned long start, end;
+	int bcount;
+	int ret;
+
+	for (start = jiffies, end = start + secs * HZ, bcount = 0;
+	     time_before(jiffies, end); bcount++) {
+		ret = do_mult_acipher_op(data, enc, num_mb);
+		if (ret)
+			return ret;
+	}
+
+	pr_cont("%d operations in %d seconds (%ld bytes)\n",
+		bcount * num_mb, secs, (long)bcount * blen * num_mb);
+	return 0;
+}
+
+static int test_mb_acipher_cycles(struct test_mb_skcipher_data *data, int enc,
+			       int blen, u32 num_mb)
+{
+	unsigned long cycles = 0;
+	int ret = 0;
+	int i;
+
+	/* Warm-up run. */
+	for (i = 0; i < 4; i++) {
+		ret = do_mult_acipher_op(data, enc, num_mb);
+		if (ret)
+			goto out;
+	}
+
+	/* The real thing. */
+	for (i = 0; i < 8; i++) {
+		cycles_t start, end;
+
+		start = get_cycles();
+		ret = do_mult_acipher_op(data, enc, num_mb);
+		end = get_cycles();
+
+		if (ret)
+			goto out;
+
+		cycles += end - start;
+	}
+
+out:
+	if (ret == 0)
+		pr_cont("1 operation in %lu cycles (%d bytes)\n",
+			(cycles + 4) / (8 * num_mb), blen);
+
+	return ret;
+}
+
+static void test_mb_skcipher_speed(const char *algo, int enc, int secs,
+				   struct cipher_speed_template *template,
+				   unsigned int tcount, u8 *keysize, u32 num_mb)
+{
+	struct test_mb_skcipher_data *data;
+	struct crypto_skcipher *tfm;
+	unsigned int i, j, iv_len;
+	const char *key;
+	const char *e;
+	u32 *b_size;
+	char iv[128];
+	int ret;
+
+	if (enc == ENCRYPT)
+		e = "encryption";
+	else
+		e = "decryption";
+
+	data = kcalloc(num_mb, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return;
+
+	tfm = crypto_alloc_skcipher(algo, 0, 0);
+	if (IS_ERR(tfm)) {
+		pr_err("failed to load transform for %s: %ld\n",
+			algo, PTR_ERR(tfm));
+		goto out_free_data;
+	}
+
+	for (i = 0; i < num_mb; ++i)
+		if (testmgr_alloc_buf(data[i].xbuf)) {
+			while (i--)
+				testmgr_free_buf(data[i].xbuf);
+			goto out_free_tfm;
+		}
+
+
+	for (i = 0; i < num_mb; ++i)
+		if (testmgr_alloc_buf(data[i].xbuf)) {
+			while (i--)
+				testmgr_free_buf(data[i].xbuf);
+			goto out_free_tfm;
+		}
+
+
+	for (i = 0; i < num_mb; ++i) {
+		data[i].req = skcipher_request_alloc(tfm, GFP_KERNEL);
+		if (!data[i].req) {
+			pr_err("alg: skcipher: Failed to allocate request for %s\n",
+			       algo);
+			while (i--)
+				skcipher_request_free(data[i].req);
+			goto out_free_xbuf;
+		}
+	}
+
+	for (i = 0; i < num_mb; ++i) {
+		skcipher_request_set_callback(data[i].req,
+					      CRYPTO_TFM_REQ_MAY_BACKLOG,
+					      crypto_req_done, &data[i].wait);
+		crypto_init_wait(&data[i].wait);
+	}
+
+	pr_info("\ntesting speed of multibuffer %s (%s) %s\n", algo,
+		get_driver_name(crypto_skcipher, tfm), e);
+
+	i = 0;
+	do {
+		b_size = block_sizes;
+		do {
+			if (*b_size > XBUFSIZE * PAGE_SIZE) {
+				pr_err("template (%u) too big for buffer (%lu)\n",
+				       *b_size, XBUFSIZE * PAGE_SIZE);
+				goto out;
+			}
+
+			pr_info("test %u (%d bit key, %d byte blocks): ", i,
+				*keysize * 8, *b_size);
+
+			/* Set up tfm global state, i.e. the key */
+
+			memset(tvmem[0], 0xff, PAGE_SIZE);
+			key = tvmem[0];
+			for (j = 0; j < tcount; j++) {
+				if (template[j].klen == *keysize) {
+					key = template[j].key;
+					break;
+				}
+			}
+
+			crypto_skcipher_clear_flags(tfm, ~0);
+
+			ret = crypto_skcipher_setkey(tfm, key, *keysize);
+			if (ret) {
+				pr_err("setkey() failed flags=%x\n",
+				       crypto_skcipher_get_flags(tfm));
+				goto out;
+			}
+
+			iv_len = crypto_skcipher_ivsize(tfm);
+			if (iv_len)
+				memset(&iv, 0xff, iv_len);
+
+			/* Now setup per request stuff, i.e. buffers */
+
+			for (j = 0; j < num_mb; ++j) {
+				struct test_mb_skcipher_data *cur = &data[j];
+				unsigned int k = *b_size;
+				unsigned int pages = DIV_ROUND_UP(k, PAGE_SIZE);
+				unsigned int p = 0;
+
+				sg_init_table(cur->sg, pages);
+
+				while (k > PAGE_SIZE) {
+					sg_set_buf(cur->sg + p, cur->xbuf[p],
+						   PAGE_SIZE);
+					memset(cur->xbuf[p], 0xff, PAGE_SIZE);
+					p++;
+					k -= PAGE_SIZE;
+				}
+
+				sg_set_buf(cur->sg + p, cur->xbuf[p], k);
+				memset(cur->xbuf[p], 0xff, k);
+
+				skcipher_request_set_crypt(cur->req, cur->sg,
+							   cur->sg, *b_size,
+							   iv);
+			}
+
+			if (secs)
+				ret = test_mb_acipher_jiffies(data, enc,
+							      *b_size, secs,
+							      num_mb);
+			else
+				ret = test_mb_acipher_cycles(data, enc,
+							     *b_size, num_mb);
+
+			if (ret) {
+				pr_err("%s() failed flags=%x\n", e,
+				       crypto_skcipher_get_flags(tfm));
+				break;
+			}
+			b_size++;
+			i++;
+		} while (*b_size);
+		keysize++;
+	} while (*keysize);
+
+out:
+	for (i = 0; i < num_mb; ++i)
+		skcipher_request_free(data[i].req);
+out_free_xbuf:
+	for (i = 0; i < num_mb; ++i)
+		testmgr_free_buf(data[i].xbuf);
+out_free_tfm:
+	crypto_free_skcipher(tfm);
+out_free_data:
+	kfree(data);
+}
+
 static inline int do_one_acipher_op(struct skcipher_request *req, int ret)
 {
 	struct crypto_wait *wait = req->base.data;
@@ -1557,16 +2179,24 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 				NULL, 0, 16, 16, aead_speed_template_20);
 		test_aead_speed("gcm(aes)", ENCRYPT, sec,
 				NULL, 0, 16, 8, speed_template_16_24_32);
+		test_aead_speed("rfc4106(gcm(aes))", DECRYPT, sec,
+				NULL, 0, 16, 16, aead_speed_template_20);
+		test_aead_speed("gcm(aes)", DECRYPT, sec,
+				NULL, 0, 16, 8, speed_template_16_24_32);
 		break;
 
 	case 212:
 		test_aead_speed("rfc4309(ccm(aes))", ENCRYPT, sec,
 				NULL, 0, 16, 16, aead_speed_template_19);
+		test_aead_speed("rfc4309(ccm(aes))", DECRYPT, sec,
+				NULL, 0, 16, 16, aead_speed_template_19);
 		break;
 
 	case 213:
 		test_aead_speed("rfc7539esp(chacha20,poly1305)", ENCRYPT, sec,
 				NULL, 0, 16, 8, aead_speed_template_36);
+		test_aead_speed("rfc7539esp(chacha20,poly1305)", DECRYPT, sec,
+				NULL, 0, 16, 8, aead_speed_template_36);
 		break;
 
 	case 214:
@@ -1574,6 +2204,33 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 				  speed_template_32);
 		break;
 
+	case 215:
+		test_mb_aead_speed("rfc4106(gcm(aes))", ENCRYPT, sec, NULL,
+				   0, 16, 16, aead_speed_template_20, num_mb);
+		test_mb_aead_speed("gcm(aes)", ENCRYPT, sec, NULL, 0, 16, 8,
+				   speed_template_16_24_32, num_mb);
+		test_mb_aead_speed("rfc4106(gcm(aes))", DECRYPT, sec, NULL,
+				   0, 16, 16, aead_speed_template_20, num_mb);
+		test_mb_aead_speed("gcm(aes)", DECRYPT, sec, NULL, 0, 16, 8,
+				   speed_template_16_24_32, num_mb);
+		break;
+
+	case 216:
+		test_mb_aead_speed("rfc4309(ccm(aes))", ENCRYPT, sec, NULL, 0,
+				   16, 16, aead_speed_template_19, num_mb);
+		test_mb_aead_speed("rfc4309(ccm(aes))", DECRYPT, sec, NULL, 0,
+				   16, 16, aead_speed_template_19, num_mb);
+		break;
+
+	case 217:
+		test_mb_aead_speed("rfc7539esp(chacha20,poly1305)", ENCRYPT,
+				   sec, NULL, 0, 16, 8, aead_speed_template_36,
+				   num_mb);
+		test_mb_aead_speed("rfc7539esp(chacha20,poly1305)", DECRYPT,
+				   sec, NULL, 0, 16, 8, aead_speed_template_36,
+				   num_mb);
+		break;
+
 	case 300:
 		if (alg) {
 			test_hash_speed(alg, sec, generic_hash_speed_template);
@@ -1778,19 +2435,23 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 		if (mode > 400 && mode < 500) break;
 		/* fall through */
 	case 422:
-		test_mb_ahash_speed("sha1", sec, generic_hash_speed_template);
+		test_mb_ahash_speed("sha1", sec, generic_hash_speed_template,
+				    num_mb);
 		if (mode > 400 && mode < 500) break;
 		/* fall through */
 	case 423:
-		test_mb_ahash_speed("sha256", sec, generic_hash_speed_template);
+		test_mb_ahash_speed("sha256", sec, generic_hash_speed_template,
+				    num_mb);
 		if (mode > 400 && mode < 500) break;
 		/* fall through */
 	case 424:
-		test_mb_ahash_speed("sha512", sec, generic_hash_speed_template);
+		test_mb_ahash_speed("sha512", sec, generic_hash_speed_template,
+				    num_mb);
 		if (mode > 400 && mode < 500) break;
 		/* fall through */
 	case 425:
-		test_mb_ahash_speed("sm3", sec, generic_hash_speed_template);
+		test_mb_ahash_speed("sm3", sec, generic_hash_speed_template,
+				    num_mb);
 		if (mode > 400 && mode < 500) break;
 		/* fall through */
 	case 499:
@@ -2008,6 +2669,218 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 				   speed_template_8_32);
 		break;
 
+	case 600:
+		test_mb_skcipher_speed("ecb(aes)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("ecb(aes)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("cbc(aes)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("cbc(aes)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("lrw(aes)", ENCRYPT, sec, NULL, 0,
+				       speed_template_32_40_48, num_mb);
+		test_mb_skcipher_speed("lrw(aes)", DECRYPT, sec, NULL, 0,
+				       speed_template_32_40_48, num_mb);
+		test_mb_skcipher_speed("xts(aes)", ENCRYPT, sec, NULL, 0,
+				       speed_template_32_64, num_mb);
+		test_mb_skcipher_speed("xts(aes)", DECRYPT, sec, NULL, 0,
+				       speed_template_32_64, num_mb);
+		test_mb_skcipher_speed("cts(cbc(aes))", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("cts(cbc(aes))", DECRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("ctr(aes)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("ctr(aes)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("cfb(aes)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("cfb(aes)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("ofb(aes)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("ofb(aes)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("rfc3686(ctr(aes))", ENCRYPT, sec, NULL,
+				       0, speed_template_20_28_36, num_mb);
+		test_mb_skcipher_speed("rfc3686(ctr(aes))", DECRYPT, sec, NULL,
+				       0, speed_template_20_28_36, num_mb);
+		break;
+
+	case 601:
+		test_mb_skcipher_speed("ecb(des3_ede)", ENCRYPT, sec,
+				       des3_speed_template, DES3_SPEED_VECTORS,
+				       speed_template_24, num_mb);
+		test_mb_skcipher_speed("ecb(des3_ede)", DECRYPT, sec,
+				       des3_speed_template, DES3_SPEED_VECTORS,
+				       speed_template_24, num_mb);
+		test_mb_skcipher_speed("cbc(des3_ede)", ENCRYPT, sec,
+				       des3_speed_template, DES3_SPEED_VECTORS,
+				       speed_template_24, num_mb);
+		test_mb_skcipher_speed("cbc(des3_ede)", DECRYPT, sec,
+				       des3_speed_template, DES3_SPEED_VECTORS,
+				       speed_template_24, num_mb);
+		test_mb_skcipher_speed("cfb(des3_ede)", ENCRYPT, sec,
+				       des3_speed_template, DES3_SPEED_VECTORS,
+				       speed_template_24, num_mb);
+		test_mb_skcipher_speed("cfb(des3_ede)", DECRYPT, sec,
+				       des3_speed_template, DES3_SPEED_VECTORS,
+				       speed_template_24, num_mb);
+		test_mb_skcipher_speed("ofb(des3_ede)", ENCRYPT, sec,
+				       des3_speed_template, DES3_SPEED_VECTORS,
+				       speed_template_24, num_mb);
+		test_mb_skcipher_speed("ofb(des3_ede)", DECRYPT, sec,
+				       des3_speed_template, DES3_SPEED_VECTORS,
+				       speed_template_24, num_mb);
+		break;
+
+	case 602:
+		test_mb_skcipher_speed("ecb(des)", ENCRYPT, sec, NULL, 0,
+				       speed_template_8, num_mb);
+		test_mb_skcipher_speed("ecb(des)", DECRYPT, sec, NULL, 0,
+				       speed_template_8, num_mb);
+		test_mb_skcipher_speed("cbc(des)", ENCRYPT, sec, NULL, 0,
+				       speed_template_8, num_mb);
+		test_mb_skcipher_speed("cbc(des)", DECRYPT, sec, NULL, 0,
+				       speed_template_8, num_mb);
+		test_mb_skcipher_speed("cfb(des)", ENCRYPT, sec, NULL, 0,
+				       speed_template_8, num_mb);
+		test_mb_skcipher_speed("cfb(des)", DECRYPT, sec, NULL, 0,
+				       speed_template_8, num_mb);
+		test_mb_skcipher_speed("ofb(des)", ENCRYPT, sec, NULL, 0,
+				       speed_template_8, num_mb);
+		test_mb_skcipher_speed("ofb(des)", DECRYPT, sec, NULL, 0,
+				       speed_template_8, num_mb);
+		break;
+
+	case 603:
+		test_mb_skcipher_speed("ecb(serpent)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("ecb(serpent)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("cbc(serpent)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("cbc(serpent)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("ctr(serpent)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("ctr(serpent)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("lrw(serpent)", ENCRYPT, sec, NULL, 0,
+				       speed_template_32_48, num_mb);
+		test_mb_skcipher_speed("lrw(serpent)", DECRYPT, sec, NULL, 0,
+				       speed_template_32_48, num_mb);
+		test_mb_skcipher_speed("xts(serpent)", ENCRYPT, sec, NULL, 0,
+				       speed_template_32_64, num_mb);
+		test_mb_skcipher_speed("xts(serpent)", DECRYPT, sec, NULL, 0,
+				       speed_template_32_64, num_mb);
+		break;
+
+	case 604:
+		test_mb_skcipher_speed("ecb(twofish)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("ecb(twofish)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("cbc(twofish)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("cbc(twofish)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("ctr(twofish)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("ctr(twofish)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_24_32, num_mb);
+		test_mb_skcipher_speed("lrw(twofish)", ENCRYPT, sec, NULL, 0,
+				       speed_template_32_40_48, num_mb);
+		test_mb_skcipher_speed("lrw(twofish)", DECRYPT, sec, NULL, 0,
+				       speed_template_32_40_48, num_mb);
+		test_mb_skcipher_speed("xts(twofish)", ENCRYPT, sec, NULL, 0,
+				       speed_template_32_48_64, num_mb);
+		test_mb_skcipher_speed("xts(twofish)", DECRYPT, sec, NULL, 0,
+				       speed_template_32_48_64, num_mb);
+		break;
+
+	case 605:
+		test_mb_skcipher_speed("ecb(arc4)", ENCRYPT, sec, NULL, 0,
+				       speed_template_8, num_mb);
+		break;
+
+	case 606:
+		test_mb_skcipher_speed("ecb(cast5)", ENCRYPT, sec, NULL, 0,
+				       speed_template_8_16, num_mb);
+		test_mb_skcipher_speed("ecb(cast5)", DECRYPT, sec, NULL, 0,
+				       speed_template_8_16, num_mb);
+		test_mb_skcipher_speed("cbc(cast5)", ENCRYPT, sec, NULL, 0,
+				       speed_template_8_16, num_mb);
+		test_mb_skcipher_speed("cbc(cast5)", DECRYPT, sec, NULL, 0,
+				       speed_template_8_16, num_mb);
+		test_mb_skcipher_speed("ctr(cast5)", ENCRYPT, sec, NULL, 0,
+				       speed_template_8_16, num_mb);
+		test_mb_skcipher_speed("ctr(cast5)", DECRYPT, sec, NULL, 0,
+				       speed_template_8_16, num_mb);
+		break;
+
+	case 607:
+		test_mb_skcipher_speed("ecb(cast6)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("ecb(cast6)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("cbc(cast6)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("cbc(cast6)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("ctr(cast6)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("ctr(cast6)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("lrw(cast6)", ENCRYPT, sec, NULL, 0,
+				       speed_template_32_48, num_mb);
+		test_mb_skcipher_speed("lrw(cast6)", DECRYPT, sec, NULL, 0,
+				       speed_template_32_48, num_mb);
+		test_mb_skcipher_speed("xts(cast6)", ENCRYPT, sec, NULL, 0,
+				       speed_template_32_64, num_mb);
+		test_mb_skcipher_speed("xts(cast6)", DECRYPT, sec, NULL, 0,
+				       speed_template_32_64, num_mb);
+		break;
+
+	case 608:
+		test_mb_skcipher_speed("ecb(camellia)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("ecb(camellia)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("cbc(camellia)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("cbc(camellia)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("ctr(camellia)", ENCRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("ctr(camellia)", DECRYPT, sec, NULL, 0,
+				       speed_template_16_32, num_mb);
+		test_mb_skcipher_speed("lrw(camellia)", ENCRYPT, sec, NULL, 0,
+				       speed_template_32_48, num_mb);
+		test_mb_skcipher_speed("lrw(camellia)", DECRYPT, sec, NULL, 0,
+				       speed_template_32_48, num_mb);
+		test_mb_skcipher_speed("xts(camellia)", ENCRYPT, sec, NULL, 0,
+				       speed_template_32_64, num_mb);
+		test_mb_skcipher_speed("xts(camellia)", DECRYPT, sec, NULL, 0,
+				       speed_template_32_64, num_mb);
+		break;
+
+	case 609:
+		test_mb_skcipher_speed("ecb(blowfish)", ENCRYPT, sec, NULL, 0,
+				       speed_template_8_32, num_mb);
+		test_mb_skcipher_speed("ecb(blowfish)", DECRYPT, sec, NULL, 0,
+				       speed_template_8_32, num_mb);
+		test_mb_skcipher_speed("cbc(blowfish)", ENCRYPT, sec, NULL, 0,
+				       speed_template_8_32, num_mb);
+		test_mb_skcipher_speed("cbc(blowfish)", DECRYPT, sec, NULL, 0,
+				       speed_template_8_32, num_mb);
+		test_mb_skcipher_speed("ctr(blowfish)", ENCRYPT, sec, NULL, 0,
+				       speed_template_8_32, num_mb);
+		test_mb_skcipher_speed("ctr(blowfish)", DECRYPT, sec, NULL, 0,
+				       speed_template_8_32, num_mb);
+		break;
+
 	case 1000:
 		test_available();
 		break;
@@ -2069,6 +2942,8 @@ module_param(mode, int, 0);
 module_param(sec, uint, 0);
 MODULE_PARM_DESC(sec, "Length in seconds of speed tests "
 		      "(defaults to zero which uses CPU cycles instead)");
+module_param(num_mb, uint, 0000);
+MODULE_PARM_DESC(num_mb, "Number of concurrent requests to be used in mb speed tests (defaults to 8)");
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Quick & dirty crypto testing module");
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 29d7020b8826..d5e23a142a04 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -177,6 +177,18 @@ static void testmgr_free_buf(char *buf[XBUFSIZE])
 		free_page((unsigned long)buf[i]);
 }
 
+static int ahash_guard_result(char *result, char c, int size)
+{
+	int i;
+
+	for (i = 0; i < size; i++) {
+		if (result[i] != c)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int ahash_partial_update(struct ahash_request **preq,
 	struct crypto_ahash *tfm, const struct hash_testvec *template,
 	void *hash_buff, int k, int temp, struct scatterlist *sg,
@@ -185,7 +197,8 @@ static int ahash_partial_update(struct ahash_request **preq,
 	char *state;
 	struct ahash_request *req;
 	int statesize, ret = -EINVAL;
-	const char guard[] = { 0x00, 0xba, 0xad, 0x00 };
+	static const unsigned char guard[] = { 0x00, 0xba, 0xad, 0x00 };
+	int digestsize = crypto_ahash_digestsize(tfm);
 
 	req = *preq;
 	statesize = crypto_ahash_statesize(
@@ -196,12 +209,19 @@ static int ahash_partial_update(struct ahash_request **preq,
 		goto out_nostate;
 	}
 	memcpy(state + statesize, guard, sizeof(guard));
+	memset(result, 1, digestsize);
 	ret = crypto_ahash_export(req, state);
 	WARN_ON(memcmp(state + statesize, guard, sizeof(guard)));
 	if (ret) {
 		pr_err("alg: hash: Failed to export() for %s\n", algo);
 		goto out;
 	}
+	ret = ahash_guard_result(result, 1, digestsize);
+	if (ret) {
+		pr_err("alg: hash: Failed, export used req->result for %s\n",
+		       algo);
+		goto out;
+	}
 	ahash_request_free(req);
 	req = ahash_request_alloc(tfm, GFP_KERNEL);
 	if (!req) {
@@ -221,6 +241,12 @@ static int ahash_partial_update(struct ahash_request **preq,
 		pr_err("alg: hash: Failed to import() for %s\n", algo);
 		goto out;
 	}
+	ret = ahash_guard_result(result, 1, digestsize);
+	if (ret) {
+		pr_err("alg: hash: Failed, import used req->result for %s\n",
+		       algo);
+		goto out;
+	}
 	ret = crypto_wait_req(crypto_ahash_update(req), wait);
 	if (ret)
 		goto out;
@@ -316,18 +342,31 @@ static int __test_hash(struct crypto_ahash *tfm,
 				goto out;
 			}
 		} else {
+			memset(result, 1, digest_size);
 			ret = crypto_wait_req(crypto_ahash_init(req), &wait);
 			if (ret) {
 				pr_err("alg: hash: init failed on test %d "
 				       "for %s: ret=%d\n", j, algo, -ret);
 				goto out;
 			}
+			ret = ahash_guard_result(result, 1, digest_size);
+			if (ret) {
+				pr_err("alg: hash: init failed on test %d "
+				       "for %s: used req->result\n", j, algo);
+				goto out;
+			}
 			ret = crypto_wait_req(crypto_ahash_update(req), &wait);
 			if (ret) {
 				pr_err("alg: hash: update failed on test %d "
 				       "for %s: ret=%d\n", j, algo, -ret);
 				goto out;
 			}
+			ret = ahash_guard_result(result, 1, digest_size);
+			if (ret) {
+				pr_err("alg: hash: update failed on test %d "
+				       "for %s: used req->result\n", j, algo);
+				goto out;
+			}
 			ret = crypto_wait_req(crypto_ahash_final(req), &wait);
 			if (ret) {
 				pr_err("alg: hash: final failed on test %d "
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index a714b6293959..6044f6906bd6 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -1052,6 +1052,142 @@ static const struct hash_testvec sha3_224_tv_template[] = {
 				"\xc9\xfd\x55\x74\x49\x44\x79\xba"
 				"\x5c\x7e\x7a\xb7\x6e\xf2\x64\xea"
 				"\xd0\xfc\xce\x33",
+		.np	= 2,
+		.tap	= { 28, 28 },
+	}, {
+		.plaintext = "\x08\x9f\x13\xaa\x41\xd8\x4c\xe3"
+			     "\x7a\x11\x85\x1c\xb3\x27\xbe\x55"
+			     "\xec\x60\xf7\x8e\x02\x99\x30\xc7"
+			     "\x3b\xd2\x69\x00\x74\x0b\xa2\x16"
+			     "\xad\x44\xdb\x4f\xe6\x7d\x14\x88"
+			     "\x1f\xb6\x2a\xc1\x58\xef\x63\xfa"
+			     "\x91\x05\x9c\x33\xca\x3e\xd5\x6c"
+			     "\x03\x77\x0e\xa5\x19\xb0\x47\xde"
+			     "\x52\xe9\x80\x17\x8b\x22\xb9\x2d"
+			     "\xc4\x5b\xf2\x66\xfd\x94\x08\x9f"
+			     "\x36\xcd\x41\xd8\x6f\x06\x7a\x11"
+			     "\xa8\x1c\xb3\x4a\xe1\x55\xec\x83"
+			     "\x1a\x8e\x25\xbc\x30\xc7\x5e\xf5"
+			     "\x69\x00\x97\x0b\xa2\x39\xd0\x44"
+			     "\xdb\x72\x09\x7d\x14\xab\x1f\xb6"
+			     "\x4d\xe4\x58\xef\x86\x1d\x91\x28"
+			     "\xbf\x33\xca\x61\xf8\x6c\x03\x9a"
+			     "\x0e\xa5\x3c\xd3\x47\xde\x75\x0c"
+			     "\x80\x17\xae\x22\xb9\x50\xe7\x5b"
+			     "\xf2\x89\x20\x94\x2b\xc2\x36\xcd"
+			     "\x64\xfb\x6f\x06\x9d\x11\xa8\x3f"
+			     "\xd6\x4a\xe1\x78\x0f\x83\x1a\xb1"
+			     "\x25\xbc\x53\xea\x5e\xf5\x8c\x00"
+			     "\x97\x2e\xc5\x39\xd0\x67\xfe\x72"
+			     "\x09\xa0\x14\xab\x42\xd9\x4d\xe4"
+			     "\x7b\x12\x86\x1d\xb4\x28\xbf\x56"
+			     "\xed\x61\xf8\x8f\x03\x9a\x31\xc8"
+			     "\x3c\xd3\x6a\x01\x75\x0c\xa3\x17"
+			     "\xae\x45\xdc\x50\xe7\x7e\x15\x89"
+			     "\x20\xb7\x2b\xc2\x59\xf0\x64\xfb"
+			     "\x92\x06\x9d\x34\xcb\x3f\xd6\x6d"
+			     "\x04\x78\x0f\xa6\x1a\xb1\x48\xdf"
+			     "\x53\xea\x81\x18\x8c\x23\xba\x2e"
+			     "\xc5\x5c\xf3\x67\xfe\x95\x09\xa0"
+			     "\x37\xce\x42\xd9\x70\x07\x7b\x12"
+			     "\xa9\x1d\xb4\x4b\xe2\x56\xed\x84"
+			     "\x1b\x8f\x26\xbd\x31\xc8\x5f\xf6"
+			     "\x6a\x01\x98\x0c\xa3\x3a\xd1\x45"
+			     "\xdc\x73\x0a\x7e\x15\xac\x20\xb7"
+			     "\x4e\xe5\x59\xf0\x87\x1e\x92\x29"
+			     "\xc0\x34\xcb\x62\xf9\x6d\x04\x9b"
+			     "\x0f\xa6\x3d\xd4\x48\xdf\x76\x0d"
+			     "\x81\x18\xaf\x23\xba\x51\xe8\x5c"
+			     "\xf3\x8a\x21\x95\x2c\xc3\x37\xce"
+			     "\x65\xfc\x70\x07\x9e\x12\xa9\x40"
+			     "\xd7\x4b\xe2\x79\x10\x84\x1b\xb2"
+			     "\x26\xbd\x54\xeb\x5f\xf6\x8d\x01"
+			     "\x98\x2f\xc6\x3a\xd1\x68\xff\x73"
+			     "\x0a\xa1\x15\xac\x43\xda\x4e\xe5"
+			     "\x7c\x13\x87\x1e\xb5\x29\xc0\x57"
+			     "\xee\x62\xf9\x90\x04\x9b\x32\xc9"
+			     "\x3d\xd4\x6b\x02\x76\x0d\xa4\x18"
+			     "\xaf\x46\xdd\x51\xe8\x7f\x16\x8a"
+			     "\x21\xb8\x2c\xc3\x5a\xf1\x65\xfc"
+			     "\x93\x07\x9e\x35\xcc\x40\xd7\x6e"
+			     "\x05\x79\x10\xa7\x1b\xb2\x49\xe0"
+			     "\x54\xeb\x82\x19\x8d\x24\xbb\x2f"
+			     "\xc6\x5d\xf4\x68\xff\x96\x0a\xa1"
+			     "\x38\xcf\x43\xda\x71\x08\x7c\x13"
+			     "\xaa\x1e\xb5\x4c\xe3\x57\xee\x85"
+			     "\x1c\x90\x27\xbe\x32\xc9\x60\xf7"
+			     "\x6b\x02\x99\x0d\xa4\x3b\xd2\x46"
+			     "\xdd\x74\x0b\x7f\x16\xad\x21\xb8"
+			     "\x4f\xe6\x5a\xf1\x88\x1f\x93\x2a"
+			     "\xc1\x35\xcc\x63\xfa\x6e\x05\x9c"
+			     "\x10\xa7\x3e\xd5\x49\xe0\x77\x0e"
+			     "\x82\x19\xb0\x24\xbb\x52\xe9\x5d"
+			     "\xf4\x8b\x22\x96\x2d\xc4\x38\xcf"
+			     "\x66\xfd\x71\x08\x9f\x13\xaa\x41"
+			     "\xd8\x4c\xe3\x7a\x11\x85\x1c\xb3"
+			     "\x27\xbe\x55\xec\x60\xf7\x8e\x02"
+			     "\x99\x30\xc7\x3b\xd2\x69\x00\x74"
+			     "\x0b\xa2\x16\xad\x44\xdb\x4f\xe6"
+			     "\x7d\x14\x88\x1f\xb6\x2a\xc1\x58"
+			     "\xef\x63\xfa\x91\x05\x9c\x33\xca"
+			     "\x3e\xd5\x6c\x03\x77\x0e\xa5\x19"
+			     "\xb0\x47\xde\x52\xe9\x80\x17\x8b"
+			     "\x22\xb9\x2d\xc4\x5b\xf2\x66\xfd"
+			     "\x94\x08\x9f\x36\xcd\x41\xd8\x6f"
+			     "\x06\x7a\x11\xa8\x1c\xb3\x4a\xe1"
+			     "\x55\xec\x83\x1a\x8e\x25\xbc\x30"
+			     "\xc7\x5e\xf5\x69\x00\x97\x0b\xa2"
+			     "\x39\xd0\x44\xdb\x72\x09\x7d\x14"
+			     "\xab\x1f\xb6\x4d\xe4\x58\xef\x86"
+			     "\x1d\x91\x28\xbf\x33\xca\x61\xf8"
+			     "\x6c\x03\x9a\x0e\xa5\x3c\xd3\x47"
+			     "\xde\x75\x0c\x80\x17\xae\x22\xb9"
+			     "\x50\xe7\x5b\xf2\x89\x20\x94\x2b"
+			     "\xc2\x36\xcd\x64\xfb\x6f\x06\x9d"
+			     "\x11\xa8\x3f\xd6\x4a\xe1\x78\x0f"
+			     "\x83\x1a\xb1\x25\xbc\x53\xea\x5e"
+			     "\xf5\x8c\x00\x97\x2e\xc5\x39\xd0"
+			     "\x67\xfe\x72\x09\xa0\x14\xab\x42"
+			     "\xd9\x4d\xe4\x7b\x12\x86\x1d\xb4"
+			     "\x28\xbf\x56\xed\x61\xf8\x8f\x03"
+			     "\x9a\x31\xc8\x3c\xd3\x6a\x01\x75"
+			     "\x0c\xa3\x17\xae\x45\xdc\x50\xe7"
+			     "\x7e\x15\x89\x20\xb7\x2b\xc2\x59"
+			     "\xf0\x64\xfb\x92\x06\x9d\x34\xcb"
+			     "\x3f\xd6\x6d\x04\x78\x0f\xa6\x1a"
+			     "\xb1\x48\xdf\x53\xea\x81\x18\x8c"
+			     "\x23\xba\x2e\xc5\x5c\xf3\x67\xfe"
+			     "\x95\x09\xa0\x37\xce\x42\xd9\x70"
+			     "\x07\x7b\x12\xa9\x1d\xb4\x4b\xe2"
+			     "\x56\xed\x84\x1b\x8f\x26\xbd\x31"
+			     "\xc8\x5f\xf6\x6a\x01\x98\x0c\xa3"
+			     "\x3a\xd1\x45\xdc\x73\x0a\x7e\x15"
+			     "\xac\x20\xb7\x4e\xe5\x59\xf0\x87"
+			     "\x1e\x92\x29\xc0\x34\xcb\x62\xf9"
+			     "\x6d\x04\x9b\x0f\xa6\x3d\xd4\x48"
+			     "\xdf\x76\x0d\x81\x18\xaf\x23\xba"
+			     "\x51\xe8\x5c\xf3\x8a\x21\x95\x2c"
+			     "\xc3\x37\xce\x65\xfc\x70\x07\x9e"
+			     "\x12\xa9\x40\xd7\x4b\xe2\x79\x10"
+			     "\x84\x1b\xb2\x26\xbd\x54\xeb\x5f"
+			     "\xf6\x8d\x01\x98\x2f\xc6\x3a\xd1"
+			     "\x68\xff\x73\x0a\xa1\x15\xac\x43"
+			     "\xda\x4e\xe5\x7c\x13\x87\x1e\xb5"
+			     "\x29\xc0\x57\xee\x62\xf9\x90\x04"
+			     "\x9b\x32\xc9\x3d\xd4\x6b\x02\x76"
+			     "\x0d\xa4\x18\xaf\x46\xdd\x51\xe8"
+			     "\x7f\x16\x8a\x21\xb8\x2c\xc3\x5a"
+			     "\xf1\x65\xfc\x93\x07\x9e\x35\xcc"
+			     "\x40\xd7\x6e\x05\x79\x10\xa7\x1b"
+			     "\xb2\x49\xe0\x54\xeb\x82\x19\x8d"
+			     "\x24\xbb\x2f\xc6\x5d\xf4\x68\xff"
+			     "\x96\x0a\xa1\x38\xcf\x43\xda\x71"
+			     "\x08\x7c\x13\xaa\x1e\xb5\x4c",
+		.psize     = 1023,
+		.digest    = "\x7d\x0f\x2f\xb7\x65\x3b\xa7\x26"
+			     "\xc3\x88\x20\x71\x15\x06\xe8\x2d"
+			     "\xa3\x92\x44\xab\x3e\xe7\xff\x86"
+			     "\xb6\x79\x10\x72",
 	},
 };
 
@@ -1077,6 +1213,142 @@ static const struct hash_testvec sha3_256_tv_template[] = {
 				"\x49\x10\x03\x76\xa8\x23\x5e\x2c"
 				"\x82\xe1\xb9\x99\x8a\x99\x9e\x21"
 				"\xdb\x32\xdd\x97\x49\x6d\x33\x76",
+		.np	= 2,
+		.tap	= { 28, 28 },
+	}, {
+		.plaintext = "\x08\x9f\x13\xaa\x41\xd8\x4c\xe3"
+			     "\x7a\x11\x85\x1c\xb3\x27\xbe\x55"
+			     "\xec\x60\xf7\x8e\x02\x99\x30\xc7"
+			     "\x3b\xd2\x69\x00\x74\x0b\xa2\x16"
+			     "\xad\x44\xdb\x4f\xe6\x7d\x14\x88"
+			     "\x1f\xb6\x2a\xc1\x58\xef\x63\xfa"
+			     "\x91\x05\x9c\x33\xca\x3e\xd5\x6c"
+			     "\x03\x77\x0e\xa5\x19\xb0\x47\xde"
+			     "\x52\xe9\x80\x17\x8b\x22\xb9\x2d"
+			     "\xc4\x5b\xf2\x66\xfd\x94\x08\x9f"
+			     "\x36\xcd\x41\xd8\x6f\x06\x7a\x11"
+			     "\xa8\x1c\xb3\x4a\xe1\x55\xec\x83"
+			     "\x1a\x8e\x25\xbc\x30\xc7\x5e\xf5"
+			     "\x69\x00\x97\x0b\xa2\x39\xd0\x44"
+			     "\xdb\x72\x09\x7d\x14\xab\x1f\xb6"
+			     "\x4d\xe4\x58\xef\x86\x1d\x91\x28"
+			     "\xbf\x33\xca\x61\xf8\x6c\x03\x9a"
+			     "\x0e\xa5\x3c\xd3\x47\xde\x75\x0c"
+			     "\x80\x17\xae\x22\xb9\x50\xe7\x5b"
+			     "\xf2\x89\x20\x94\x2b\xc2\x36\xcd"
+			     "\x64\xfb\x6f\x06\x9d\x11\xa8\x3f"
+			     "\xd6\x4a\xe1\x78\x0f\x83\x1a\xb1"
+			     "\x25\xbc\x53\xea\x5e\xf5\x8c\x00"
+			     "\x97\x2e\xc5\x39\xd0\x67\xfe\x72"
+			     "\x09\xa0\x14\xab\x42\xd9\x4d\xe4"
+			     "\x7b\x12\x86\x1d\xb4\x28\xbf\x56"
+			     "\xed\x61\xf8\x8f\x03\x9a\x31\xc8"
+			     "\x3c\xd3\x6a\x01\x75\x0c\xa3\x17"
+			     "\xae\x45\xdc\x50\xe7\x7e\x15\x89"
+			     "\x20\xb7\x2b\xc2\x59\xf0\x64\xfb"
+			     "\x92\x06\x9d\x34\xcb\x3f\xd6\x6d"
+			     "\x04\x78\x0f\xa6\x1a\xb1\x48\xdf"
+			     "\x53\xea\x81\x18\x8c\x23\xba\x2e"
+			     "\xc5\x5c\xf3\x67\xfe\x95\x09\xa0"
+			     "\x37\xce\x42\xd9\x70\x07\x7b\x12"
+			     "\xa9\x1d\xb4\x4b\xe2\x56\xed\x84"
+			     "\x1b\x8f\x26\xbd\x31\xc8\x5f\xf6"
+			     "\x6a\x01\x98\x0c\xa3\x3a\xd1\x45"
+			     "\xdc\x73\x0a\x7e\x15\xac\x20\xb7"
+			     "\x4e\xe5\x59\xf0\x87\x1e\x92\x29"
+			     "\xc0\x34\xcb\x62\xf9\x6d\x04\x9b"
+			     "\x0f\xa6\x3d\xd4\x48\xdf\x76\x0d"
+			     "\x81\x18\xaf\x23\xba\x51\xe8\x5c"
+			     "\xf3\x8a\x21\x95\x2c\xc3\x37\xce"
+			     "\x65\xfc\x70\x07\x9e\x12\xa9\x40"
+			     "\xd7\x4b\xe2\x79\x10\x84\x1b\xb2"
+			     "\x26\xbd\x54\xeb\x5f\xf6\x8d\x01"
+			     "\x98\x2f\xc6\x3a\xd1\x68\xff\x73"
+			     "\x0a\xa1\x15\xac\x43\xda\x4e\xe5"
+			     "\x7c\x13\x87\x1e\xb5\x29\xc0\x57"
+			     "\xee\x62\xf9\x90\x04\x9b\x32\xc9"
+			     "\x3d\xd4\x6b\x02\x76\x0d\xa4\x18"
+			     "\xaf\x46\xdd\x51\xe8\x7f\x16\x8a"
+			     "\x21\xb8\x2c\xc3\x5a\xf1\x65\xfc"
+			     "\x93\x07\x9e\x35\xcc\x40\xd7\x6e"
+			     "\x05\x79\x10\xa7\x1b\xb2\x49\xe0"
+			     "\x54\xeb\x82\x19\x8d\x24\xbb\x2f"
+			     "\xc6\x5d\xf4\x68\xff\x96\x0a\xa1"
+			     "\x38\xcf\x43\xda\x71\x08\x7c\x13"
+			     "\xaa\x1e\xb5\x4c\xe3\x57\xee\x85"
+			     "\x1c\x90\x27\xbe\x32\xc9\x60\xf7"
+			     "\x6b\x02\x99\x0d\xa4\x3b\xd2\x46"
+			     "\xdd\x74\x0b\x7f\x16\xad\x21\xb8"
+			     "\x4f\xe6\x5a\xf1\x88\x1f\x93\x2a"
+			     "\xc1\x35\xcc\x63\xfa\x6e\x05\x9c"
+			     "\x10\xa7\x3e\xd5\x49\xe0\x77\x0e"
+			     "\x82\x19\xb0\x24\xbb\x52\xe9\x5d"
+			     "\xf4\x8b\x22\x96\x2d\xc4\x38\xcf"
+			     "\x66\xfd\x71\x08\x9f\x13\xaa\x41"
+			     "\xd8\x4c\xe3\x7a\x11\x85\x1c\xb3"
+			     "\x27\xbe\x55\xec\x60\xf7\x8e\x02"
+			     "\x99\x30\xc7\x3b\xd2\x69\x00\x74"
+			     "\x0b\xa2\x16\xad\x44\xdb\x4f\xe6"
+			     "\x7d\x14\x88\x1f\xb6\x2a\xc1\x58"
+			     "\xef\x63\xfa\x91\x05\x9c\x33\xca"
+			     "\x3e\xd5\x6c\x03\x77\x0e\xa5\x19"
+			     "\xb0\x47\xde\x52\xe9\x80\x17\x8b"
+			     "\x22\xb9\x2d\xc4\x5b\xf2\x66\xfd"
+			     "\x94\x08\x9f\x36\xcd\x41\xd8\x6f"
+			     "\x06\x7a\x11\xa8\x1c\xb3\x4a\xe1"
+			     "\x55\xec\x83\x1a\x8e\x25\xbc\x30"
+			     "\xc7\x5e\xf5\x69\x00\x97\x0b\xa2"
+			     "\x39\xd0\x44\xdb\x72\x09\x7d\x14"
+			     "\xab\x1f\xb6\x4d\xe4\x58\xef\x86"
+			     "\x1d\x91\x28\xbf\x33\xca\x61\xf8"
+			     "\x6c\x03\x9a\x0e\xa5\x3c\xd3\x47"
+			     "\xde\x75\x0c\x80\x17\xae\x22\xb9"
+			     "\x50\xe7\x5b\xf2\x89\x20\x94\x2b"
+			     "\xc2\x36\xcd\x64\xfb\x6f\x06\x9d"
+			     "\x11\xa8\x3f\xd6\x4a\xe1\x78\x0f"
+			     "\x83\x1a\xb1\x25\xbc\x53\xea\x5e"
+			     "\xf5\x8c\x00\x97\x2e\xc5\x39\xd0"
+			     "\x67\xfe\x72\x09\xa0\x14\xab\x42"
+			     "\xd9\x4d\xe4\x7b\x12\x86\x1d\xb4"
+			     "\x28\xbf\x56\xed\x61\xf8\x8f\x03"
+			     "\x9a\x31\xc8\x3c\xd3\x6a\x01\x75"
+			     "\x0c\xa3\x17\xae\x45\xdc\x50\xe7"
+			     "\x7e\x15\x89\x20\xb7\x2b\xc2\x59"
+			     "\xf0\x64\xfb\x92\x06\x9d\x34\xcb"
+			     "\x3f\xd6\x6d\x04\x78\x0f\xa6\x1a"
+			     "\xb1\x48\xdf\x53\xea\x81\x18\x8c"
+			     "\x23\xba\x2e\xc5\x5c\xf3\x67\xfe"
+			     "\x95\x09\xa0\x37\xce\x42\xd9\x70"
+			     "\x07\x7b\x12\xa9\x1d\xb4\x4b\xe2"
+			     "\x56\xed\x84\x1b\x8f\x26\xbd\x31"
+			     "\xc8\x5f\xf6\x6a\x01\x98\x0c\xa3"
+			     "\x3a\xd1\x45\xdc\x73\x0a\x7e\x15"
+			     "\xac\x20\xb7\x4e\xe5\x59\xf0\x87"
+			     "\x1e\x92\x29\xc0\x34\xcb\x62\xf9"
+			     "\x6d\x04\x9b\x0f\xa6\x3d\xd4\x48"
+			     "\xdf\x76\x0d\x81\x18\xaf\x23\xba"
+			     "\x51\xe8\x5c\xf3\x8a\x21\x95\x2c"
+			     "\xc3\x37\xce\x65\xfc\x70\x07\x9e"
+			     "\x12\xa9\x40\xd7\x4b\xe2\x79\x10"
+			     "\x84\x1b\xb2\x26\xbd\x54\xeb\x5f"
+			     "\xf6\x8d\x01\x98\x2f\xc6\x3a\xd1"
+			     "\x68\xff\x73\x0a\xa1\x15\xac\x43"
+			     "\xda\x4e\xe5\x7c\x13\x87\x1e\xb5"
+			     "\x29\xc0\x57\xee\x62\xf9\x90\x04"
+			     "\x9b\x32\xc9\x3d\xd4\x6b\x02\x76"
+			     "\x0d\xa4\x18\xaf\x46\xdd\x51\xe8"
+			     "\x7f\x16\x8a\x21\xb8\x2c\xc3\x5a"
+			     "\xf1\x65\xfc\x93\x07\x9e\x35\xcc"
+			     "\x40\xd7\x6e\x05\x79\x10\xa7\x1b"
+			     "\xb2\x49\xe0\x54\xeb\x82\x19\x8d"
+			     "\x24\xbb\x2f\xc6\x5d\xf4\x68\xff"
+			     "\x96\x0a\xa1\x38\xcf\x43\xda\x71"
+			     "\x08\x7c\x13\xaa\x1e\xb5\x4c",
+		.psize     = 1023,
+		.digest    = "\xde\x41\x04\xbd\xda\xda\xd9\x71"
+			     "\xf7\xfa\x80\xf5\xea\x11\x03\xb1"
+			     "\x3b\x6a\xbc\x5f\xb9\x66\x26\xf7"
+			     "\x8a\x97\xbb\xf2\x07\x08\x38\x30",
 	},
 };
 
@@ -1109,6 +1381,144 @@ static const struct hash_testvec sha3_384_tv_template[] = {
 				"\x9b\xfd\xbc\x32\xb9\xd4\xad\x5a"
 				"\xa0\x4a\x1f\x07\x6e\x62\xfe\xa1"
 				"\x9e\xef\x51\xac\xd0\x65\x7c\x22",
+		.np	= 2,
+		.tap	= { 28, 28 },
+	}, {
+		.plaintext = "\x08\x9f\x13\xaa\x41\xd8\x4c\xe3"
+			     "\x7a\x11\x85\x1c\xb3\x27\xbe\x55"
+			     "\xec\x60\xf7\x8e\x02\x99\x30\xc7"
+			     "\x3b\xd2\x69\x00\x74\x0b\xa2\x16"
+			     "\xad\x44\xdb\x4f\xe6\x7d\x14\x88"
+			     "\x1f\xb6\x2a\xc1\x58\xef\x63\xfa"
+			     "\x91\x05\x9c\x33\xca\x3e\xd5\x6c"
+			     "\x03\x77\x0e\xa5\x19\xb0\x47\xde"
+			     "\x52\xe9\x80\x17\x8b\x22\xb9\x2d"
+			     "\xc4\x5b\xf2\x66\xfd\x94\x08\x9f"
+			     "\x36\xcd\x41\xd8\x6f\x06\x7a\x11"
+			     "\xa8\x1c\xb3\x4a\xe1\x55\xec\x83"
+			     "\x1a\x8e\x25\xbc\x30\xc7\x5e\xf5"
+			     "\x69\x00\x97\x0b\xa2\x39\xd0\x44"
+			     "\xdb\x72\x09\x7d\x14\xab\x1f\xb6"
+			     "\x4d\xe4\x58\xef\x86\x1d\x91\x28"
+			     "\xbf\x33\xca\x61\xf8\x6c\x03\x9a"
+			     "\x0e\xa5\x3c\xd3\x47\xde\x75\x0c"
+			     "\x80\x17\xae\x22\xb9\x50\xe7\x5b"
+			     "\xf2\x89\x20\x94\x2b\xc2\x36\xcd"
+			     "\x64\xfb\x6f\x06\x9d\x11\xa8\x3f"
+			     "\xd6\x4a\xe1\x78\x0f\x83\x1a\xb1"
+			     "\x25\xbc\x53\xea\x5e\xf5\x8c\x00"
+			     "\x97\x2e\xc5\x39\xd0\x67\xfe\x72"
+			     "\x09\xa0\x14\xab\x42\xd9\x4d\xe4"
+			     "\x7b\x12\x86\x1d\xb4\x28\xbf\x56"
+			     "\xed\x61\xf8\x8f\x03\x9a\x31\xc8"
+			     "\x3c\xd3\x6a\x01\x75\x0c\xa3\x17"
+			     "\xae\x45\xdc\x50\xe7\x7e\x15\x89"
+			     "\x20\xb7\x2b\xc2\x59\xf0\x64\xfb"
+			     "\x92\x06\x9d\x34\xcb\x3f\xd6\x6d"
+			     "\x04\x78\x0f\xa6\x1a\xb1\x48\xdf"
+			     "\x53\xea\x81\x18\x8c\x23\xba\x2e"
+			     "\xc5\x5c\xf3\x67\xfe\x95\x09\xa0"
+			     "\x37\xce\x42\xd9\x70\x07\x7b\x12"
+			     "\xa9\x1d\xb4\x4b\xe2\x56\xed\x84"
+			     "\x1b\x8f\x26\xbd\x31\xc8\x5f\xf6"
+			     "\x6a\x01\x98\x0c\xa3\x3a\xd1\x45"
+			     "\xdc\x73\x0a\x7e\x15\xac\x20\xb7"
+			     "\x4e\xe5\x59\xf0\x87\x1e\x92\x29"
+			     "\xc0\x34\xcb\x62\xf9\x6d\x04\x9b"
+			     "\x0f\xa6\x3d\xd4\x48\xdf\x76\x0d"
+			     "\x81\x18\xaf\x23\xba\x51\xe8\x5c"
+			     "\xf3\x8a\x21\x95\x2c\xc3\x37\xce"
+			     "\x65\xfc\x70\x07\x9e\x12\xa9\x40"
+			     "\xd7\x4b\xe2\x79\x10\x84\x1b\xb2"
+			     "\x26\xbd\x54\xeb\x5f\xf6\x8d\x01"
+			     "\x98\x2f\xc6\x3a\xd1\x68\xff\x73"
+			     "\x0a\xa1\x15\xac\x43\xda\x4e\xe5"
+			     "\x7c\x13\x87\x1e\xb5\x29\xc0\x57"
+			     "\xee\x62\xf9\x90\x04\x9b\x32\xc9"
+			     "\x3d\xd4\x6b\x02\x76\x0d\xa4\x18"
+			     "\xaf\x46\xdd\x51\xe8\x7f\x16\x8a"
+			     "\x21\xb8\x2c\xc3\x5a\xf1\x65\xfc"
+			     "\x93\x07\x9e\x35\xcc\x40\xd7\x6e"
+			     "\x05\x79\x10\xa7\x1b\xb2\x49\xe0"
+			     "\x54\xeb\x82\x19\x8d\x24\xbb\x2f"
+			     "\xc6\x5d\xf4\x68\xff\x96\x0a\xa1"
+			     "\x38\xcf\x43\xda\x71\x08\x7c\x13"
+			     "\xaa\x1e\xb5\x4c\xe3\x57\xee\x85"
+			     "\x1c\x90\x27\xbe\x32\xc9\x60\xf7"
+			     "\x6b\x02\x99\x0d\xa4\x3b\xd2\x46"
+			     "\xdd\x74\x0b\x7f\x16\xad\x21\xb8"
+			     "\x4f\xe6\x5a\xf1\x88\x1f\x93\x2a"
+			     "\xc1\x35\xcc\x63\xfa\x6e\x05\x9c"
+			     "\x10\xa7\x3e\xd5\x49\xe0\x77\x0e"
+			     "\x82\x19\xb0\x24\xbb\x52\xe9\x5d"
+			     "\xf4\x8b\x22\x96\x2d\xc4\x38\xcf"
+			     "\x66\xfd\x71\x08\x9f\x13\xaa\x41"
+			     "\xd8\x4c\xe3\x7a\x11\x85\x1c\xb3"
+			     "\x27\xbe\x55\xec\x60\xf7\x8e\x02"
+			     "\x99\x30\xc7\x3b\xd2\x69\x00\x74"
+			     "\x0b\xa2\x16\xad\x44\xdb\x4f\xe6"
+			     "\x7d\x14\x88\x1f\xb6\x2a\xc1\x58"
+			     "\xef\x63\xfa\x91\x05\x9c\x33\xca"
+			     "\x3e\xd5\x6c\x03\x77\x0e\xa5\x19"
+			     "\xb0\x47\xde\x52\xe9\x80\x17\x8b"
+			     "\x22\xb9\x2d\xc4\x5b\xf2\x66\xfd"
+			     "\x94\x08\x9f\x36\xcd\x41\xd8\x6f"
+			     "\x06\x7a\x11\xa8\x1c\xb3\x4a\xe1"
+			     "\x55\xec\x83\x1a\x8e\x25\xbc\x30"
+			     "\xc7\x5e\xf5\x69\x00\x97\x0b\xa2"
+			     "\x39\xd0\x44\xdb\x72\x09\x7d\x14"
+			     "\xab\x1f\xb6\x4d\xe4\x58\xef\x86"
+			     "\x1d\x91\x28\xbf\x33\xca\x61\xf8"
+			     "\x6c\x03\x9a\x0e\xa5\x3c\xd3\x47"
+			     "\xde\x75\x0c\x80\x17\xae\x22\xb9"
+			     "\x50\xe7\x5b\xf2\x89\x20\x94\x2b"
+			     "\xc2\x36\xcd\x64\xfb\x6f\x06\x9d"
+			     "\x11\xa8\x3f\xd6\x4a\xe1\x78\x0f"
+			     "\x83\x1a\xb1\x25\xbc\x53\xea\x5e"
+			     "\xf5\x8c\x00\x97\x2e\xc5\x39\xd0"
+			     "\x67\xfe\x72\x09\xa0\x14\xab\x42"
+			     "\xd9\x4d\xe4\x7b\x12\x86\x1d\xb4"
+			     "\x28\xbf\x56\xed\x61\xf8\x8f\x03"
+			     "\x9a\x31\xc8\x3c\xd3\x6a\x01\x75"
+			     "\x0c\xa3\x17\xae\x45\xdc\x50\xe7"
+			     "\x7e\x15\x89\x20\xb7\x2b\xc2\x59"
+			     "\xf0\x64\xfb\x92\x06\x9d\x34\xcb"
+			     "\x3f\xd6\x6d\x04\x78\x0f\xa6\x1a"
+			     "\xb1\x48\xdf\x53\xea\x81\x18\x8c"
+			     "\x23\xba\x2e\xc5\x5c\xf3\x67\xfe"
+			     "\x95\x09\xa0\x37\xce\x42\xd9\x70"
+			     "\x07\x7b\x12\xa9\x1d\xb4\x4b\xe2"
+			     "\x56\xed\x84\x1b\x8f\x26\xbd\x31"
+			     "\xc8\x5f\xf6\x6a\x01\x98\x0c\xa3"
+			     "\x3a\xd1\x45\xdc\x73\x0a\x7e\x15"
+			     "\xac\x20\xb7\x4e\xe5\x59\xf0\x87"
+			     "\x1e\x92\x29\xc0\x34\xcb\x62\xf9"
+			     "\x6d\x04\x9b\x0f\xa6\x3d\xd4\x48"
+			     "\xdf\x76\x0d\x81\x18\xaf\x23\xba"
+			     "\x51\xe8\x5c\xf3\x8a\x21\x95\x2c"
+			     "\xc3\x37\xce\x65\xfc\x70\x07\x9e"
+			     "\x12\xa9\x40\xd7\x4b\xe2\x79\x10"
+			     "\x84\x1b\xb2\x26\xbd\x54\xeb\x5f"
+			     "\xf6\x8d\x01\x98\x2f\xc6\x3a\xd1"
+			     "\x68\xff\x73\x0a\xa1\x15\xac\x43"
+			     "\xda\x4e\xe5\x7c\x13\x87\x1e\xb5"
+			     "\x29\xc0\x57\xee\x62\xf9\x90\x04"
+			     "\x9b\x32\xc9\x3d\xd4\x6b\x02\x76"
+			     "\x0d\xa4\x18\xaf\x46\xdd\x51\xe8"
+			     "\x7f\x16\x8a\x21\xb8\x2c\xc3\x5a"
+			     "\xf1\x65\xfc\x93\x07\x9e\x35\xcc"
+			     "\x40\xd7\x6e\x05\x79\x10\xa7\x1b"
+			     "\xb2\x49\xe0\x54\xeb\x82\x19\x8d"
+			     "\x24\xbb\x2f\xc6\x5d\xf4\x68\xff"
+			     "\x96\x0a\xa1\x38\xcf\x43\xda\x71"
+			     "\x08\x7c\x13\xaa\x1e\xb5\x4c",
+		.psize     = 1023,
+		.digest    = "\x1b\x19\x4d\x8f\xd5\x36\x87\x71"
+			     "\xcf\xca\x30\x85\x9b\xc1\x25\xc7"
+			     "\x00\xcb\x73\x8a\x8e\xd4\xfe\x2b"
+			     "\x1a\xa2\xdc\x2e\x41\xfd\x52\x51"
+			     "\xd2\x21\xae\x2d\xc7\xae\x8c\x40"
+			     "\xb9\xe6\x56\x48\x03\xcd\x88\x6b",
 	},
 };
 
@@ -1147,6 +1557,146 @@ static const struct hash_testvec sha3_512_tv_template[] = {
 				"\xba\x1b\x0d\x8d\xc7\x8c\x08\x63"
 				"\x46\xb5\x33\xb4\x9c\x03\x0d\x99"
 				"\xa2\x7d\xaf\x11\x39\xd6\xe7\x5e",
+		.np	= 2,
+		.tap	= { 28, 28 },
+	}, {
+		.plaintext = "\x08\x9f\x13\xaa\x41\xd8\x4c\xe3"
+			     "\x7a\x11\x85\x1c\xb3\x27\xbe\x55"
+			     "\xec\x60\xf7\x8e\x02\x99\x30\xc7"
+			     "\x3b\xd2\x69\x00\x74\x0b\xa2\x16"
+			     "\xad\x44\xdb\x4f\xe6\x7d\x14\x88"
+			     "\x1f\xb6\x2a\xc1\x58\xef\x63\xfa"
+			     "\x91\x05\x9c\x33\xca\x3e\xd5\x6c"
+			     "\x03\x77\x0e\xa5\x19\xb0\x47\xde"
+			     "\x52\xe9\x80\x17\x8b\x22\xb9\x2d"
+			     "\xc4\x5b\xf2\x66\xfd\x94\x08\x9f"
+			     "\x36\xcd\x41\xd8\x6f\x06\x7a\x11"
+			     "\xa8\x1c\xb3\x4a\xe1\x55\xec\x83"
+			     "\x1a\x8e\x25\xbc\x30\xc7\x5e\xf5"
+			     "\x69\x00\x97\x0b\xa2\x39\xd0\x44"
+			     "\xdb\x72\x09\x7d\x14\xab\x1f\xb6"
+			     "\x4d\xe4\x58\xef\x86\x1d\x91\x28"
+			     "\xbf\x33\xca\x61\xf8\x6c\x03\x9a"
+			     "\x0e\xa5\x3c\xd3\x47\xde\x75\x0c"
+			     "\x80\x17\xae\x22\xb9\x50\xe7\x5b"
+			     "\xf2\x89\x20\x94\x2b\xc2\x36\xcd"
+			     "\x64\xfb\x6f\x06\x9d\x11\xa8\x3f"
+			     "\xd6\x4a\xe1\x78\x0f\x83\x1a\xb1"
+			     "\x25\xbc\x53\xea\x5e\xf5\x8c\x00"
+			     "\x97\x2e\xc5\x39\xd0\x67\xfe\x72"
+			     "\x09\xa0\x14\xab\x42\xd9\x4d\xe4"
+			     "\x7b\x12\x86\x1d\xb4\x28\xbf\x56"
+			     "\xed\x61\xf8\x8f\x03\x9a\x31\xc8"
+			     "\x3c\xd3\x6a\x01\x75\x0c\xa3\x17"
+			     "\xae\x45\xdc\x50\xe7\x7e\x15\x89"
+			     "\x20\xb7\x2b\xc2\x59\xf0\x64\xfb"
+			     "\x92\x06\x9d\x34\xcb\x3f\xd6\x6d"
+			     "\x04\x78\x0f\xa6\x1a\xb1\x48\xdf"
+			     "\x53\xea\x81\x18\x8c\x23\xba\x2e"
+			     "\xc5\x5c\xf3\x67\xfe\x95\x09\xa0"
+			     "\x37\xce\x42\xd9\x70\x07\x7b\x12"
+			     "\xa9\x1d\xb4\x4b\xe2\x56\xed\x84"
+			     "\x1b\x8f\x26\xbd\x31\xc8\x5f\xf6"
+			     "\x6a\x01\x98\x0c\xa3\x3a\xd1\x45"
+			     "\xdc\x73\x0a\x7e\x15\xac\x20\xb7"
+			     "\x4e\xe5\x59\xf0\x87\x1e\x92\x29"
+			     "\xc0\x34\xcb\x62\xf9\x6d\x04\x9b"
+			     "\x0f\xa6\x3d\xd4\x48\xdf\x76\x0d"
+			     "\x81\x18\xaf\x23\xba\x51\xe8\x5c"
+			     "\xf3\x8a\x21\x95\x2c\xc3\x37\xce"
+			     "\x65\xfc\x70\x07\x9e\x12\xa9\x40"
+			     "\xd7\x4b\xe2\x79\x10\x84\x1b\xb2"
+			     "\x26\xbd\x54\xeb\x5f\xf6\x8d\x01"
+			     "\x98\x2f\xc6\x3a\xd1\x68\xff\x73"
+			     "\x0a\xa1\x15\xac\x43\xda\x4e\xe5"
+			     "\x7c\x13\x87\x1e\xb5\x29\xc0\x57"
+			     "\xee\x62\xf9\x90\x04\x9b\x32\xc9"
+			     "\x3d\xd4\x6b\x02\x76\x0d\xa4\x18"
+			     "\xaf\x46\xdd\x51\xe8\x7f\x16\x8a"
+			     "\x21\xb8\x2c\xc3\x5a\xf1\x65\xfc"
+			     "\x93\x07\x9e\x35\xcc\x40\xd7\x6e"
+			     "\x05\x79\x10\xa7\x1b\xb2\x49\xe0"
+			     "\x54\xeb\x82\x19\x8d\x24\xbb\x2f"
+			     "\xc6\x5d\xf4\x68\xff\x96\x0a\xa1"
+			     "\x38\xcf\x43\xda\x71\x08\x7c\x13"
+			     "\xaa\x1e\xb5\x4c\xe3\x57\xee\x85"
+			     "\x1c\x90\x27\xbe\x32\xc9\x60\xf7"
+			     "\x6b\x02\x99\x0d\xa4\x3b\xd2\x46"
+			     "\xdd\x74\x0b\x7f\x16\xad\x21\xb8"
+			     "\x4f\xe6\x5a\xf1\x88\x1f\x93\x2a"
+			     "\xc1\x35\xcc\x63\xfa\x6e\x05\x9c"
+			     "\x10\xa7\x3e\xd5\x49\xe0\x77\x0e"
+			     "\x82\x19\xb0\x24\xbb\x52\xe9\x5d"
+			     "\xf4\x8b\x22\x96\x2d\xc4\x38\xcf"
+			     "\x66\xfd\x71\x08\x9f\x13\xaa\x41"
+			     "\xd8\x4c\xe3\x7a\x11\x85\x1c\xb3"
+			     "\x27\xbe\x55\xec\x60\xf7\x8e\x02"
+			     "\x99\x30\xc7\x3b\xd2\x69\x00\x74"
+			     "\x0b\xa2\x16\xad\x44\xdb\x4f\xe6"
+			     "\x7d\x14\x88\x1f\xb6\x2a\xc1\x58"
+			     "\xef\x63\xfa\x91\x05\x9c\x33\xca"
+			     "\x3e\xd5\x6c\x03\x77\x0e\xa5\x19"
+			     "\xb0\x47\xde\x52\xe9\x80\x17\x8b"
+			     "\x22\xb9\x2d\xc4\x5b\xf2\x66\xfd"
+			     "\x94\x08\x9f\x36\xcd\x41\xd8\x6f"
+			     "\x06\x7a\x11\xa8\x1c\xb3\x4a\xe1"
+			     "\x55\xec\x83\x1a\x8e\x25\xbc\x30"
+			     "\xc7\x5e\xf5\x69\x00\x97\x0b\xa2"
+			     "\x39\xd0\x44\xdb\x72\x09\x7d\x14"
+			     "\xab\x1f\xb6\x4d\xe4\x58\xef\x86"
+			     "\x1d\x91\x28\xbf\x33\xca\x61\xf8"
+			     "\x6c\x03\x9a\x0e\xa5\x3c\xd3\x47"
+			     "\xde\x75\x0c\x80\x17\xae\x22\xb9"
+			     "\x50\xe7\x5b\xf2\x89\x20\x94\x2b"
+			     "\xc2\x36\xcd\x64\xfb\x6f\x06\x9d"
+			     "\x11\xa8\x3f\xd6\x4a\xe1\x78\x0f"
+			     "\x83\x1a\xb1\x25\xbc\x53\xea\x5e"
+			     "\xf5\x8c\x00\x97\x2e\xc5\x39\xd0"
+			     "\x67\xfe\x72\x09\xa0\x14\xab\x42"
+			     "\xd9\x4d\xe4\x7b\x12\x86\x1d\xb4"
+			     "\x28\xbf\x56\xed\x61\xf8\x8f\x03"
+			     "\x9a\x31\xc8\x3c\xd3\x6a\x01\x75"
+			     "\x0c\xa3\x17\xae\x45\xdc\x50\xe7"
+			     "\x7e\x15\x89\x20\xb7\x2b\xc2\x59"
+			     "\xf0\x64\xfb\x92\x06\x9d\x34\xcb"
+			     "\x3f\xd6\x6d\x04\x78\x0f\xa6\x1a"
+			     "\xb1\x48\xdf\x53\xea\x81\x18\x8c"
+			     "\x23\xba\x2e\xc5\x5c\xf3\x67\xfe"
+			     "\x95\x09\xa0\x37\xce\x42\xd9\x70"
+			     "\x07\x7b\x12\xa9\x1d\xb4\x4b\xe2"
+			     "\x56\xed\x84\x1b\x8f\x26\xbd\x31"
+			     "\xc8\x5f\xf6\x6a\x01\x98\x0c\xa3"
+			     "\x3a\xd1\x45\xdc\x73\x0a\x7e\x15"
+			     "\xac\x20\xb7\x4e\xe5\x59\xf0\x87"
+			     "\x1e\x92\x29\xc0\x34\xcb\x62\xf9"
+			     "\x6d\x04\x9b\x0f\xa6\x3d\xd4\x48"
+			     "\xdf\x76\x0d\x81\x18\xaf\x23\xba"
+			     "\x51\xe8\x5c\xf3\x8a\x21\x95\x2c"
+			     "\xc3\x37\xce\x65\xfc\x70\x07\x9e"
+			     "\x12\xa9\x40\xd7\x4b\xe2\x79\x10"
+			     "\x84\x1b\xb2\x26\xbd\x54\xeb\x5f"
+			     "\xf6\x8d\x01\x98\x2f\xc6\x3a\xd1"
+			     "\x68\xff\x73\x0a\xa1\x15\xac\x43"
+			     "\xda\x4e\xe5\x7c\x13\x87\x1e\xb5"
+			     "\x29\xc0\x57\xee\x62\xf9\x90\x04"
+			     "\x9b\x32\xc9\x3d\xd4\x6b\x02\x76"
+			     "\x0d\xa4\x18\xaf\x46\xdd\x51\xe8"
+			     "\x7f\x16\x8a\x21\xb8\x2c\xc3\x5a"
+			     "\xf1\x65\xfc\x93\x07\x9e\x35\xcc"
+			     "\x40\xd7\x6e\x05\x79\x10\xa7\x1b"
+			     "\xb2\x49\xe0\x54\xeb\x82\x19\x8d"
+			     "\x24\xbb\x2f\xc6\x5d\xf4\x68\xff"
+			     "\x96\x0a\xa1\x38\xcf\x43\xda\x71"
+			     "\x08\x7c\x13\xaa\x1e\xb5\x4c",
+		.psize     = 1023,
+		.digest    = "\x59\xda\x30\xe3\x90\xe4\x3d\xde"
+			     "\xf0\xc6\x42\x17\xd7\xb2\x26\x47"
+			     "\x90\x28\xa6\x84\xe8\x49\x7a\x86"
+			     "\xd6\xb8\x9e\xf8\x07\x59\x21\x03"
+			     "\xad\xd2\xed\x48\xa3\xb9\xa5\xf0"
+			     "\xb3\xae\x02\x2b\xb8\xaf\xc3\x3b"
+			     "\xd6\xb0\x8f\xcb\x76\x8b\xa7\x41"
+			     "\x32\xc2\x8e\x50\x91\x86\x90\xfb",
 	},
 };
 
diff --git a/crypto/twofish_common.c b/crypto/twofish_common.c
index 5f62c4f9f6e0..f3a0dd25f871 100644
--- a/crypto/twofish_common.c
+++ b/crypto/twofish_common.c
@@ -24,9 +24,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
- * USA
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  *
  * This code is a "clean room" implementation, written from the paper
  * _Twofish: A 128-Bit Block Cipher_ by Bruce Schneier, John Kelsey,
diff --git a/crypto/twofish_generic.c b/crypto/twofish_generic.c
index ebf7a3efb572..07e62433fbfb 100644
--- a/crypto/twofish_generic.c
+++ b/crypto/twofish_generic.c
@@ -23,9 +23,8 @@
  * GNU General Public License for more details.
  * 
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
- * USA
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  *
  * This code is a "clean room" implementation, written from the paper
  * _Twofish: A 128-Bit Block Cipher_ by Bruce Schneier, John Kelsey,
diff --git a/crypto/xcbc.c b/crypto/xcbc.c
index df90b332554c..25c75af50d3f 100644
--- a/crypto/xcbc.c
+++ b/crypto/xcbc.c
@@ -12,8 +12,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  *
  * Author:
  * 	Kazunori Miyazawa <miyazawa@linux-ipv6.org>
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 152744c5ef0f..879dc0604cba 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -153,6 +153,8 @@ source "drivers/remoteproc/Kconfig"
 
 source "drivers/rpmsg/Kconfig"
 
+source "drivers/soundwire/Kconfig"
+
 source "drivers/soc/Kconfig"
 
 source "drivers/devfreq/Kconfig"
@@ -211,4 +213,10 @@ source "drivers/mux/Kconfig"
 
 source "drivers/opp/Kconfig"
 
+source "drivers/visorbus/Kconfig"
+
+source "drivers/siox/Kconfig"
+
+source "drivers/slimbus/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index 1d034b680431..7a0438744053 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -87,6 +87,7 @@ obj-$(CONFIG_MTD)		+= mtd/
 obj-$(CONFIG_SPI)		+= spi/
 obj-$(CONFIG_SPMI)		+= spmi/
 obj-$(CONFIG_HSI)		+= hsi/
+obj-$(CONFIG_SLIMBUS)		+= slimbus/
 obj-y				+= net/
 obj-$(CONFIG_ATM)		+= atm/
 obj-$(CONFIG_FUSION)		+= message/
@@ -105,6 +106,7 @@ obj-$(CONFIG_TC)		+= tc/
 obj-$(CONFIG_UWB)		+= uwb/
 obj-$(CONFIG_USB_PHY)		+= usb/
 obj-$(CONFIG_USB)		+= usb/
+obj-$(CONFIG_USB_SUPPORT)	+= usb/
 obj-$(CONFIG_PCI)		+= usb/
 obj-$(CONFIG_USB_GADGET)	+= usb/
 obj-$(CONFIG_OF)		+= usb/
@@ -156,6 +158,7 @@ obj-$(CONFIG_MAILBOX)		+= mailbox/
 obj-$(CONFIG_HWSPINLOCK)	+= hwspinlock/
 obj-$(CONFIG_REMOTEPROC)	+= remoteproc/
 obj-$(CONFIG_RPMSG)		+= rpmsg/
+obj-$(CONFIG_SOUNDWIRE)		+= soundwire/
 
 # Virtualization drivers
 obj-$(CONFIG_VIRT_DRIVERS)	+= virt/
@@ -183,3 +186,5 @@ obj-$(CONFIG_FPGA)		+= fpga/
 obj-$(CONFIG_FSI)		+= fsi/
 obj-$(CONFIG_TEE)		+= tee/
 obj-$(CONFIG_MULTIPLEXER)	+= mux/
+obj-$(CONFIG_UNISYS_VISORBUS)	+= visorbus/
+obj-$(CONFIG_SIOX)		+= siox/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 46505396869e..d650c5b6ec90 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -361,22 +361,6 @@ config ACPI_PCI_SLOT
 	  i.e., segment/bus/device/function tuples, with physical slots in
 	  the system.  If you are unsure, say N.
 
-config X86_PM_TIMER
-	bool "Power Management Timer Support" if EXPERT
-	depends on X86
-	default y
-	help
-	  The Power Management Timer is available on all ACPI-capable,
-	  in most cases even if ACPI is unusable or blacklisted.
-
-	  This timing source is not affected by power management features
-	  like aggressive processor idling, throttling, frequency and/or
-	  voltage scaling, unlike the commonly used Time Stamp Counter
-	  (TSC) timing source.
-
-	  You should nearly always say Y here because many modern
-	  systems require this timer. 
-
 config ACPI_CONTAINER
 	bool "Container and Module Devices"
 	default (ACPI_HOTPLUG_MEMORY || ACPI_HOTPLUG_CPU)
@@ -564,3 +548,19 @@ config TPS68470_PMIC_OPREGION
 	  using this, are probed.
 
 endif	# ACPI
+
+config X86_PM_TIMER
+	bool "Power Management Timer Support" if EXPERT
+	depends on X86 && (ACPI || JAILHOUSE_GUEST)
+	default y
+	help
+	  The Power Management Timer is available on all ACPI-capable,
+	  in most cases even if ACPI is unusable or blacklisted.
+
+	  This timing source is not affected by power management features
+	  like aggressive processor idling, throttling, frequency and/or
+	  voltage scaling, unlike the commonly used Time Stamp Counter
+	  (TSC) timing source.
+
+	  You should nearly always say Y here because many modern
+	  systems require this timer.
diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c
index 3ec05aa1a903..2ff5c8c04e3b 100644
--- a/drivers/acpi/acpi_dbg.c
+++ b/drivers/acpi/acpi_dbg.c
@@ -718,9 +718,9 @@ again:
 	return size > 0 ? size : ret;
 }
 
-static unsigned int acpi_aml_poll(struct file *file, poll_table *wait)
+static __poll_t acpi_aml_poll(struct file *file, poll_table *wait)
 {
-	int masks = 0;
+	__poll_t masks = 0;
 
 	poll_wait(file, &acpi_aml_io.wait, wait);
 	if (acpi_aml_user_readable())
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 7f2b02cc8ea1..2bcffec8dbf0 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -427,6 +427,142 @@ out:
 	return 0;
 }
 
+struct lpss_device_links {
+	const char *supplier_hid;
+	const char *supplier_uid;
+	const char *consumer_hid;
+	const char *consumer_uid;
+	u32 flags;
+};
+
+/*
+ * The _DEP method is used to identify dependencies but instead of creating
+ * device links for every handle in _DEP, only links in the following list are
+ * created. That is necessary because, in the general case, _DEP can refer to
+ * devices that might not have drivers, or that are on different buses, or where
+ * the supplier is not enumerated until after the consumer is probed.
+ */
+static const struct lpss_device_links lpss_device_links[] = {
+	{"808622C1", "7", "80860F14", "3", DL_FLAG_PM_RUNTIME},
+};
+
+static bool hid_uid_match(const char *hid1, const char *uid1,
+			  const char *hid2, const char *uid2)
+{
+	return !strcmp(hid1, hid2) && uid1 && uid2 && !strcmp(uid1, uid2);
+}
+
+static bool acpi_lpss_is_supplier(struct acpi_device *adev,
+				  const struct lpss_device_links *link)
+{
+	return hid_uid_match(acpi_device_hid(adev), acpi_device_uid(adev),
+			     link->supplier_hid, link->supplier_uid);
+}
+
+static bool acpi_lpss_is_consumer(struct acpi_device *adev,
+				  const struct lpss_device_links *link)
+{
+	return hid_uid_match(acpi_device_hid(adev), acpi_device_uid(adev),
+			     link->consumer_hid, link->consumer_uid);
+}
+
+struct hid_uid {
+	const char *hid;
+	const char *uid;
+};
+
+static int match_hid_uid(struct device *dev, void *data)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	struct hid_uid *id = data;
+
+	if (!adev)
+		return 0;
+
+	return hid_uid_match(acpi_device_hid(adev), acpi_device_uid(adev),
+			     id->hid, id->uid);
+}
+
+static struct device *acpi_lpss_find_device(const char *hid, const char *uid)
+{
+	struct hid_uid data = {
+		.hid = hid,
+		.uid = uid,
+	};
+
+	return bus_find_device(&platform_bus_type, NULL, &data, match_hid_uid);
+}
+
+static bool acpi_lpss_dep(struct acpi_device *adev, acpi_handle handle)
+{
+	struct acpi_handle_list dep_devices;
+	acpi_status status;
+	int i;
+
+	if (!acpi_has_method(adev->handle, "_DEP"))
+		return false;
+
+	status = acpi_evaluate_reference(adev->handle, "_DEP", NULL,
+					 &dep_devices);
+	if (ACPI_FAILURE(status)) {
+		dev_dbg(&adev->dev, "Failed to evaluate _DEP.\n");
+		return false;
+	}
+
+	for (i = 0; i < dep_devices.count; i++) {
+		if (dep_devices.handles[i] == handle)
+			return true;
+	}
+
+	return false;
+}
+
+static void acpi_lpss_link_consumer(struct device *dev1,
+				    const struct lpss_device_links *link)
+{
+	struct device *dev2;
+
+	dev2 = acpi_lpss_find_device(link->consumer_hid, link->consumer_uid);
+	if (!dev2)
+		return;
+
+	if (acpi_lpss_dep(ACPI_COMPANION(dev2), ACPI_HANDLE(dev1)))
+		device_link_add(dev2, dev1, link->flags);
+
+	put_device(dev2);
+}
+
+static void acpi_lpss_link_supplier(struct device *dev1,
+				    const struct lpss_device_links *link)
+{
+	struct device *dev2;
+
+	dev2 = acpi_lpss_find_device(link->supplier_hid, link->supplier_uid);
+	if (!dev2)
+		return;
+
+	if (acpi_lpss_dep(ACPI_COMPANION(dev1), ACPI_HANDLE(dev2)))
+		device_link_add(dev1, dev2, link->flags);
+
+	put_device(dev2);
+}
+
+static void acpi_lpss_create_device_links(struct acpi_device *adev,
+					  struct platform_device *pdev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(lpss_device_links); i++) {
+		const struct lpss_device_links *link = &lpss_device_links[i];
+
+		if (acpi_lpss_is_supplier(adev, link))
+			acpi_lpss_link_consumer(&pdev->dev, link);
+
+		if (acpi_lpss_is_consumer(adev, link))
+			acpi_lpss_link_supplier(&pdev->dev, link);
+	}
+}
+
 static int acpi_lpss_create_device(struct acpi_device *adev,
 				   const struct acpi_device_id *id)
 {
@@ -465,6 +601,8 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 	acpi_dev_free_resource_list(&resource_list);
 
 	if (!pdata->mmio_base) {
+		/* Avoid acpi_bus_attach() instantiating a pdev for this dev. */
+		adev->pnp.type.platform_id = 0;
 		/* Skip the device, but continue the namespace scan. */
 		ret = 0;
 		goto err_out;
@@ -500,6 +638,7 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 	adev->driver_data = pdata;
 	pdev = acpi_create_platform_device(adev, dev_desc->properties);
 	if (!IS_ERR_OR_NULL(pdev)) {
+		acpi_lpss_create_device_links(adev, pdev);
 		return 1;
 	}
 
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 0972ec0e2eb8..f53ccc680238 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -80,8 +80,8 @@ MODULE_PARM_DESC(report_key_events,
 static bool device_id_scheme = false;
 module_param(device_id_scheme, bool, 0444);
 
-static bool only_lcd = false;
-module_param(only_lcd, bool, 0444);
+static int only_lcd = -1;
+module_param(only_lcd, int, 0444);
 
 static int register_count;
 static DEFINE_MUTEX(register_count_mutex);
@@ -2136,6 +2136,16 @@ int acpi_video_register(void)
 		goto leave;
 	}
 
+	/*
+	 * We're seeing a lot of bogus backlight interfaces on newer machines
+	 * without a LCD such as desktops, servers and HDMI sticks. Checking
+	 * the lcd flag fixes this, so enable this on any machines which are
+	 * win8 ready (where we also prefer the native backlight driver, so
+	 * normally the acpi_video code should not register there anyways).
+	 */
+	if (only_lcd == -1)
+		only_lcd = acpi_osi_is_win8();
+
 	dmi_check_system(video_dmi_table);
 
 	ret = acpi_bus_register_driver(&acpi_video_bus);
diff --git a/drivers/acpi/acpica/acapps.h b/drivers/acpi/acpica/acapps.h
index 7a1a68b5ac5c..2243c8164b34 100644
--- a/drivers/acpi/acpica/acapps.h
+++ b/drivers/acpi/acpica/acapps.h
@@ -80,6 +80,9 @@
 	prefix, ACPICA_COPYRIGHT, \
 	prefix
 
+#define ACPI_COMMON_BUILD_TIME \
+	"Build date/time: %s %s\n", __DATE__, __TIME__
+
 /* Macros for usage messages */
 
 #define ACPI_USAGE_HEADER(usage) \
diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h
index 71743e5252f5..54b8d9df9423 100644
--- a/drivers/acpi/acpica/acdebug.h
+++ b/drivers/acpi/acpica/acdebug.h
@@ -223,6 +223,10 @@ void
 acpi_db_execute(char *name, char **args, acpi_object_type *types, u32 flags);
 
 void
+acpi_db_create_execution_thread(char *method_name_arg,
+				char **arguments, acpi_object_type *types);
+
+void
 acpi_db_create_execution_threads(char *num_threads_arg,
 				 char *num_loops_arg, char *method_name_arg);
 
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 95eed442703f..45ef3f5dc9ad 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -46,7 +46,7 @@
 
 /*****************************************************************************
  *
- * Globals related to the ACPI tables
+ * Globals related to the incoming ACPI tables
  *
  ****************************************************************************/
 
@@ -87,7 +87,7 @@ ACPI_GLOBAL(u8, acpi_gbl_integer_nybble_width);
 
 /*****************************************************************************
  *
- * Mutual exclusion within ACPICA subsystem
+ * Mutual exclusion within the ACPICA subsystem
  *
  ****************************************************************************/
 
@@ -167,7 +167,7 @@ ACPI_GLOBAL(u8, acpi_gbl_next_owner_id_offset);
 
 ACPI_INIT_GLOBAL(u8, acpi_gbl_namespace_initialized, FALSE);
 
-/* Misc */
+/* Miscellaneous */
 
 ACPI_GLOBAL(u32, acpi_gbl_original_mode);
 ACPI_GLOBAL(u32, acpi_gbl_ns_lookup_count);
@@ -191,10 +191,9 @@ extern const char acpi_gbl_lower_hex_digits[];
 extern const char acpi_gbl_upper_hex_digits[];
 extern const struct acpi_opcode_info acpi_gbl_aml_op_info[AML_NUM_OPCODES];
 
-#ifdef ACPI_DBG_TRACK_ALLOCATIONS
-
 /* Lists for tracking memory allocations (debug only) */
 
+#ifdef ACPI_DBG_TRACK_ALLOCATIONS
 ACPI_GLOBAL(struct acpi_memory_list *, acpi_gbl_global_list);
 ACPI_GLOBAL(struct acpi_memory_list *, acpi_gbl_ns_node_list);
 ACPI_GLOBAL(u8, acpi_gbl_display_final_mem_stats);
@@ -203,7 +202,7 @@ ACPI_GLOBAL(u8, acpi_gbl_disable_mem_tracking);
 
 /*****************************************************************************
  *
- * Namespace globals
+ * ACPI Namespace
  *
  ****************************************************************************/
 
@@ -234,15 +233,20 @@ ACPI_INIT_GLOBAL(u32, acpi_gbl_nesting_level, 0);
 
 /*****************************************************************************
  *
- * Interpreter globals
+ * Interpreter/Parser globals
  *
  ****************************************************************************/
 
-ACPI_GLOBAL(struct acpi_thread_state *, acpi_gbl_current_walk_list);
-
 /* Control method single step flag */
 
 ACPI_GLOBAL(u8, acpi_gbl_cm_single_step);
+ACPI_GLOBAL(struct acpi_thread_state *, acpi_gbl_current_walk_list);
+ACPI_INIT_GLOBAL(union acpi_parse_object, *acpi_gbl_current_scope, NULL);
+
+/* ASL/ASL+ converter */
+
+ACPI_INIT_GLOBAL(u8, acpi_gbl_capture_comments, FALSE);
+ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_last_list_head, NULL);
 
 /*****************************************************************************
  *
@@ -252,7 +256,6 @@ ACPI_GLOBAL(u8, acpi_gbl_cm_single_step);
 
 extern struct acpi_bit_register_info
     acpi_gbl_bit_register_info[ACPI_NUM_BITREG];
-
 ACPI_GLOBAL(u8, acpi_gbl_sleep_type_a);
 ACPI_GLOBAL(u8, acpi_gbl_sleep_type_b);
 
@@ -263,7 +266,6 @@ ACPI_GLOBAL(u8, acpi_gbl_sleep_type_b);
  ****************************************************************************/
 
 #if (!ACPI_REDUCED_HARDWARE)
-
 ACPI_GLOBAL(u8, acpi_gbl_all_gpes_initialized);
 ACPI_GLOBAL(struct acpi_gpe_xrupt_info *, acpi_gbl_gpe_xrupt_list_head);
 ACPI_GLOBAL(struct acpi_gpe_block_info *,
@@ -272,10 +274,8 @@ ACPI_GLOBAL(acpi_gbl_event_handler, acpi_gbl_global_event_handler);
 ACPI_GLOBAL(void *, acpi_gbl_global_event_handler_context);
 ACPI_GLOBAL(struct acpi_fixed_event_handler,
 	    acpi_gbl_fixed_event_handlers[ACPI_NUM_FIXED_EVENTS]);
-
 extern struct acpi_fixed_event_info
     acpi_gbl_fixed_event_info[ACPI_NUM_FIXED_EVENTS];
-
 #endif				/* !ACPI_REDUCED_HARDWARE */
 
 /*****************************************************************************
@@ -291,14 +291,14 @@ ACPI_GLOBAL(u32, acpi_gpe_count);
 ACPI_GLOBAL(u32, acpi_sci_count);
 ACPI_GLOBAL(u32, acpi_fixed_event_count[ACPI_NUM_FIXED_EVENTS]);
 
-/* Support for dynamic control method tracing mechanism */
+/* Dynamic control method tracing mechanism */
 
 ACPI_GLOBAL(u32, acpi_gbl_original_dbg_level);
 ACPI_GLOBAL(u32, acpi_gbl_original_dbg_layer);
 
 /*****************************************************************************
  *
- * Debugger and Disassembler globals
+ * Debugger and Disassembler
  *
  ****************************************************************************/
 
@@ -326,7 +326,6 @@ ACPI_GLOBAL(struct acpi_external_file *, acpi_gbl_external_file_list);
 #endif
 
 #ifdef ACPI_DEBUGGER
-
 ACPI_INIT_GLOBAL(u8, acpi_gbl_abort_method, FALSE);
 ACPI_INIT_GLOBAL(acpi_thread_id, acpi_gbl_db_thread_id, ACPI_INVALID_THREAD_ID);
 
@@ -340,7 +339,6 @@ ACPI_GLOBAL(u32, acpi_gbl_db_console_debug_level);
 ACPI_GLOBAL(struct acpi_namespace_node *, acpi_gbl_db_scope_node);
 ACPI_GLOBAL(u8, acpi_gbl_db_terminate_loop);
 ACPI_GLOBAL(u8, acpi_gbl_db_threads_terminated);
-
 ACPI_GLOBAL(char *, acpi_gbl_db_args[ACPI_DEBUGGER_MAX_ARGS]);
 ACPI_GLOBAL(acpi_object_type, acpi_gbl_db_arg_types[ACPI_DEBUGGER_MAX_ARGS]);
 
@@ -350,32 +348,33 @@ ACPI_GLOBAL(char, acpi_gbl_db_parsed_buf[ACPI_DB_LINE_BUFFER_SIZE]);
 ACPI_GLOBAL(char, acpi_gbl_db_scope_buf[ACPI_DB_LINE_BUFFER_SIZE]);
 ACPI_GLOBAL(char, acpi_gbl_db_debug_filename[ACPI_DB_LINE_BUFFER_SIZE]);
 
-/*
- * Statistic globals
- */
+/* Statistics globals */
+
 ACPI_GLOBAL(u16, acpi_gbl_obj_type_count[ACPI_TOTAL_TYPES]);
 ACPI_GLOBAL(u16, acpi_gbl_node_type_count[ACPI_TOTAL_TYPES]);
 ACPI_GLOBAL(u16, acpi_gbl_obj_type_count_misc);
 ACPI_GLOBAL(u16, acpi_gbl_node_type_count_misc);
 ACPI_GLOBAL(u32, acpi_gbl_num_nodes);
 ACPI_GLOBAL(u32, acpi_gbl_num_objects);
-
 #endif				/* ACPI_DEBUGGER */
 
 #if defined (ACPI_DISASSEMBLER) || defined (ACPI_ASL_COMPILER)
-
 ACPI_GLOBAL(const char, *acpi_gbl_pld_panel_list[]);
 ACPI_GLOBAL(const char, *acpi_gbl_pld_vertical_position_list[]);
 ACPI_GLOBAL(const char, *acpi_gbl_pld_horizontal_position_list[]);
 ACPI_GLOBAL(const char, *acpi_gbl_pld_shape_list[]);
-
 ACPI_INIT_GLOBAL(u8, acpi_gbl_disasm_flag, FALSE);
-
 #endif
 
-/*
- * Meant for the -ca option.
- */
+/*****************************************************************************
+ *
+ * ACPICA application-specific globals
+ *
+ ****************************************************************************/
+
+/* ASL-to-ASL+ conversion utility (implemented within the iASL compiler) */
+
+#ifdef ACPI_ASL_COMPILER
 ACPI_INIT_GLOBAL(char *, acpi_gbl_current_inline_comment, NULL);
 ACPI_INIT_GLOBAL(char *, acpi_gbl_current_end_node_comment, NULL);
 ACPI_INIT_GLOBAL(char *, acpi_gbl_current_open_brace_comment, NULL);
@@ -386,23 +385,18 @@ ACPI_INIT_GLOBAL(char *, acpi_gbl_current_filename, NULL);
 ACPI_INIT_GLOBAL(char *, acpi_gbl_current_parent_filename, NULL);
 ACPI_INIT_GLOBAL(char *, acpi_gbl_current_include_filename, NULL);
 
-ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_last_list_head, NULL);
-
 ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_def_blk_comment_list_head,
 		 NULL);
 ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_def_blk_comment_list_tail,
 		 NULL);
-
 ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_reg_comment_list_head,
 		 NULL);
 ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_reg_comment_list_tail,
 		 NULL);
-
 ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_inc_comment_list_head,
 		 NULL);
 ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_inc_comment_list_tail,
 		 NULL);
-
 ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_end_blk_comment_list_head,
 		 NULL);
 ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_end_blk_comment_list_tail,
@@ -410,30 +404,18 @@ ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_end_blk_comment_list_tail,
 
 ACPI_INIT_GLOBAL(struct acpi_comment_addr_node,
 		 *acpi_gbl_comment_addr_list_head, NULL);
-
-ACPI_INIT_GLOBAL(union acpi_parse_object, *acpi_gbl_current_scope, NULL);
-
 ACPI_INIT_GLOBAL(struct acpi_file_node, *acpi_gbl_file_tree_root, NULL);
 
 ACPI_GLOBAL(acpi_cache_t *, acpi_gbl_reg_comment_cache);
 ACPI_GLOBAL(acpi_cache_t *, acpi_gbl_comment_addr_cache);
 ACPI_GLOBAL(acpi_cache_t *, acpi_gbl_file_cache);
 
-ACPI_INIT_GLOBAL(u8, gbl_capture_comments, FALSE);
-
 ACPI_INIT_GLOBAL(u8, acpi_gbl_debug_asl_conversion, FALSE);
 ACPI_INIT_GLOBAL(ACPI_FILE, acpi_gbl_conv_debug_file, NULL);
-
 ACPI_GLOBAL(char, acpi_gbl_table_sig[4]);
-
-/*****************************************************************************
- *
- * Application globals
- *
- ****************************************************************************/
+#endif
 
 #ifdef ACPI_APPLICATION
-
 ACPI_INIT_GLOBAL(ACPI_FILE, acpi_gbl_debug_file, NULL);
 ACPI_INIT_GLOBAL(ACPI_FILE, acpi_gbl_output_file, NULL);
 ACPI_INIT_GLOBAL(u8, acpi_gbl_debug_timeout, FALSE);
@@ -442,16 +424,6 @@ ACPI_INIT_GLOBAL(u8, acpi_gbl_debug_timeout, FALSE);
 
 ACPI_GLOBAL(acpi_spinlock, acpi_gbl_print_lock);	/* For print buffer */
 ACPI_GLOBAL(char, acpi_gbl_print_buffer[1024]);
-
 #endif				/* ACPI_APPLICATION */
 
-/*****************************************************************************
- *
- * Info/help support
- *
- ****************************************************************************/
-
-extern const struct ah_predefined_name asl_predefined_info[];
-extern const struct ah_device_id asl_device_ids[];
-
 #endif				/* __ACGLOBAL_H__ */
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 0d45b8bb1678..a56675f0661e 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -622,7 +622,7 @@ struct acpi_control_state {
 	union acpi_parse_object *predicate_op;
 	u8 *aml_predicate_start;	/* Start of if/while predicate */
 	u8 *package_end;	/* End of if/while block */
-	u32 loop_count;		/* While() loop counter */
+	u64 loop_timeout;	/* While() loop timeout */
 };
 
 /*
@@ -1218,16 +1218,17 @@ struct acpi_db_method_info {
 	acpi_object_type *types;
 
 	/*
-	 * Arguments to be passed to method for the command
-	 * Threads -
-	 *   the Number of threads, ID of current thread and
-	 *   Index of current thread inside all them created.
+	 * Arguments to be passed to method for the commands Threads and
+	 * Background. Note, ACPI specifies a maximum of 7 arguments (0 - 6).
+	 *
+	 * For the Threads command, the Number of threads, ID of current
+	 * thread and Index of current thread inside all them created.
 	 */
 	char init_args;
 #ifdef ACPI_DEBUGGER
-	acpi_object_type arg_types[4];
+	acpi_object_type arg_types[ACPI_METHOD_NUM_ARGS];
 #endif
-	char *arguments[4];
+	char *arguments[ACPI_METHOD_NUM_ARGS];
 	char num_threads_str[11];
 	char id_of_thread_str[11];
 	char index_of_thread_str[11];
diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h
index c7f0c96cc00f..128a3d71b598 100644
--- a/drivers/acpi/acpica/acmacros.h
+++ b/drivers/acpi/acpica/acmacros.h
@@ -455,7 +455,7 @@
  * the plist contains a set of parens to allow variable-length lists.
  * These macros are used for both the debug and non-debug versions of the code.
  */
-#define ACPI_ERROR_NAMESPACE(s, e)          acpi_ut_namespace_error (AE_INFO, s, e);
+#define ACPI_ERROR_NAMESPACE(s, p, e)       acpi_ut_prefixed_namespace_error (AE_INFO, s, p, e);
 #define ACPI_ERROR_METHOD(s, n, p, e)       acpi_ut_method_error (AE_INFO, s, n, p, e);
 #define ACPI_WARN_PREDEFINED(plist)         acpi_ut_predefined_warning plist
 #define ACPI_INFO_PREDEFINED(plist)         acpi_ut_predefined_info plist
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index 54a0c51b3e37..2fb1bb78d85c 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -289,6 +289,9 @@ acpi_ns_build_normalized_path(struct acpi_namespace_node *node,
 char *acpi_ns_get_normalized_pathname(struct acpi_namespace_node *node,
 				      u8 no_trailing);
 
+char *acpi_ns_build_prefixed_pathname(union acpi_generic_state *prefix_scope,
+				      const char *internal_path);
+
 char *acpi_ns_name_of_current_scope(struct acpi_walk_state *walk_state);
 
 acpi_status
diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index 83b75e9db7ef..b6b29d717824 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -118,9 +118,6 @@ extern const char *acpi_gbl_ptyp_decode[];
 #ifndef ACPI_MSG_ERROR
 #define ACPI_MSG_ERROR          "ACPI Error: "
 #endif
-#ifndef ACPI_MSG_EXCEPTION
-#define ACPI_MSG_EXCEPTION      "ACPI Exception: "
-#endif
 #ifndef ACPI_MSG_WARNING
 #define ACPI_MSG_WARNING        "ACPI Warning: "
 #endif
@@ -129,10 +126,10 @@ extern const char *acpi_gbl_ptyp_decode[];
 #endif
 
 #ifndef ACPI_MSG_BIOS_ERROR
-#define ACPI_MSG_BIOS_ERROR     "ACPI BIOS Error (bug): "
+#define ACPI_MSG_BIOS_ERROR     "Firmware Error (ACPI): "
 #endif
 #ifndef ACPI_MSG_BIOS_WARNING
-#define ACPI_MSG_BIOS_WARNING   "ACPI BIOS Warning (bug): "
+#define ACPI_MSG_BIOS_WARNING   "Firmware Warning (ACPI): "
 #endif
 
 /*
@@ -233,10 +230,10 @@ u64 acpi_ut_implicit_strtoul64(char *string);
  */
 acpi_status acpi_ut_init_globals(void);
 
-#if defined(ACPI_DEBUG_OUTPUT) || defined(ACPI_DEBUGGER)
-
 const char *acpi_ut_get_mutex_name(u32 mutex_id);
 
+#if defined(ACPI_DEBUG_OUTPUT) || defined(ACPI_DEBUGGER)
+
 const char *acpi_ut_get_notify_name(u32 notify_value, acpi_object_type type);
 #endif
 
@@ -641,9 +638,11 @@ void ut_convert_backslashes(char *pathname);
 
 void acpi_ut_repair_name(char *name);
 
-#if defined (ACPI_DEBUGGER) || defined (ACPI_APPLICATION)
+#if defined (ACPI_DEBUGGER) || defined (ACPI_APPLICATION) || defined (ACPI_DEBUG_OUTPUT)
 u8 acpi_ut_safe_strcpy(char *dest, acpi_size dest_size, char *source);
 
+void acpi_ut_safe_strncpy(char *dest, char *source, acpi_size dest_size);
+
 u8 acpi_ut_safe_strcat(char *dest, acpi_size dest_size, char *source);
 
 u8
@@ -737,9 +736,11 @@ acpi_ut_predefined_bios_error(const char *module_name,
 			      u8 node_flags, const char *format, ...);
 
 void
-acpi_ut_namespace_error(const char *module_name,
-			u32 line_number,
-			const char *internal_name, acpi_status lookup_status);
+acpi_ut_prefixed_namespace_error(const char *module_name,
+				 u32 line_number,
+				 union acpi_generic_state *prefix_scope,
+				 const char *internal_name,
+				 acpi_status lookup_status);
 
 void
 acpi_ut_method_error(const char *module_name,
diff --git a/drivers/acpi/acpica/dbexec.c b/drivers/acpi/acpica/dbexec.c
index 3b30319752f0..ed088fceb18d 100644
--- a/drivers/acpi/acpica/dbexec.c
+++ b/drivers/acpi/acpica/dbexec.c
@@ -67,6 +67,8 @@ static acpi_status
 acpi_db_execution_walk(acpi_handle obj_handle,
 		       u32 nesting_level, void *context, void **return_value);
 
+static void ACPI_SYSTEM_XFACE acpi_db_single_execution_thread(void *context);
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_db_delete_objects
@@ -229,7 +231,7 @@ static acpi_status acpi_db_execute_setup(struct acpi_db_method_info *info)
 
 	ACPI_FUNCTION_NAME(db_execute_setup);
 
-	/* Catenate the current scope to the supplied name */
+	/* Concatenate the current scope to the supplied name */
 
 	info->pathname[0] = 0;
 	if ((info->name[0] != '\\') && (info->name[0] != '/')) {
@@ -611,6 +613,112 @@ static void ACPI_SYSTEM_XFACE acpi_db_method_thread(void *context)
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_db_single_execution_thread
+ *
+ * PARAMETERS:  context                 - Method info struct
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Create one thread and execute a method
+ *
+ ******************************************************************************/
+
+static void ACPI_SYSTEM_XFACE acpi_db_single_execution_thread(void *context)
+{
+	struct acpi_db_method_info *info = context;
+	acpi_status status;
+	struct acpi_buffer return_obj;
+
+	acpi_os_printf("\n");
+
+	status = acpi_db_execute_method(info, &return_obj);
+	if (ACPI_FAILURE(status)) {
+		acpi_os_printf("%s During evaluation of %s\n",
+			       acpi_format_exception(status), info->pathname);
+		return;
+	}
+
+	/* Display a return object, if any */
+
+	if (return_obj.length) {
+		acpi_os_printf("Evaluation of %s returned object %p, "
+			       "external buffer length %X\n",
+			       acpi_gbl_db_method_info.pathname,
+			       return_obj.pointer, (u32)return_obj.length);
+
+		acpi_db_dump_external_object(return_obj.pointer, 1);
+	}
+
+	acpi_os_printf("\nBackground thread completed\n%c ",
+		       ACPI_DEBUGGER_COMMAND_PROMPT);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_db_create_execution_thread
+ *
+ * PARAMETERS:  method_name_arg         - Control method to execute
+ *              arguments               - Array of arguments to the method
+ *              types                   - Corresponding array of object types
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Create a single thread to evaluate a namespace object. Handles
+ *              arguments passed on command line for control methods.
+ *
+ ******************************************************************************/
+
+void
+acpi_db_create_execution_thread(char *method_name_arg,
+				char **arguments, acpi_object_type *types)
+{
+	acpi_status status;
+	u32 i;
+
+	memset(&acpi_gbl_db_method_info, 0, sizeof(struct acpi_db_method_info));
+	acpi_gbl_db_method_info.name = method_name_arg;
+	acpi_gbl_db_method_info.init_args = 1;
+	acpi_gbl_db_method_info.args = acpi_gbl_db_method_info.arguments;
+	acpi_gbl_db_method_info.types = acpi_gbl_db_method_info.arg_types;
+
+	/* Setup method arguments, up to 7 (0-6) */
+
+	for (i = 0; (i < ACPI_METHOD_NUM_ARGS) && *arguments; i++) {
+		acpi_gbl_db_method_info.arguments[i] = *arguments;
+		arguments++;
+
+		acpi_gbl_db_method_info.arg_types[i] = *types;
+		types++;
+	}
+
+	status = acpi_db_execute_setup(&acpi_gbl_db_method_info);
+	if (ACPI_FAILURE(status)) {
+		return;
+	}
+
+	/* Get the NS node, determines existence also */
+
+	status = acpi_get_handle(NULL, acpi_gbl_db_method_info.pathname,
+				 &acpi_gbl_db_method_info.method);
+	if (ACPI_FAILURE(status)) {
+		acpi_os_printf("%s Could not get handle for %s\n",
+			       acpi_format_exception(status),
+			       acpi_gbl_db_method_info.pathname);
+		return;
+	}
+
+	status = acpi_os_execute(OSL_DEBUGGER_EXEC_THREAD,
+				 acpi_db_single_execution_thread,
+				 &acpi_gbl_db_method_info);
+	if (ACPI_FAILURE(status)) {
+		return;
+	}
+
+	acpi_os_printf("\nBackground thread started\n");
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_db_create_execution_threads
  *
  * PARAMETERS:  num_threads_arg         - Number of threads to create
diff --git a/drivers/acpi/acpica/dbfileio.c b/drivers/acpi/acpica/dbfileio.c
index 4d81ea291d93..cf9607945704 100644
--- a/drivers/acpi/acpica/dbfileio.c
+++ b/drivers/acpi/acpica/dbfileio.c
@@ -99,8 +99,8 @@ void acpi_db_open_debug_file(char *name)
 	}
 
 	acpi_os_printf("Debug output file %s opened\n", name);
-	strncpy(acpi_gbl_db_debug_filename, name,
-		sizeof(acpi_gbl_db_debug_filename));
+	acpi_ut_safe_strncpy(acpi_gbl_db_debug_filename, name,
+			     sizeof(acpi_gbl_db_debug_filename));
 	acpi_gbl_db_output_to_file = TRUE;
 }
 #endif
diff --git a/drivers/acpi/acpica/dbinput.c b/drivers/acpi/acpica/dbinput.c
index 2626d79db064..954ca3b981a7 100644
--- a/drivers/acpi/acpica/dbinput.c
+++ b/drivers/acpi/acpica/dbinput.c
@@ -136,6 +136,7 @@ enum acpi_ex_debugger_commands {
 	CMD_UNLOAD,
 
 	CMD_TERMINATE,
+	CMD_BACKGROUND,
 	CMD_THREADS,
 
 	CMD_TEST,
@@ -212,6 +213,7 @@ static const struct acpi_db_command_info acpi_gbl_db_commands[] = {
 	{"UNLOAD", 1},
 
 	{"TERMINATE", 0},
+	{"BACKGROUND", 1},
 	{"THREADS", 3},
 
 	{"TEST", 1},
@@ -222,9 +224,56 @@ static const struct acpi_db_command_info acpi_gbl_db_commands[] = {
 /*
  * Help for all debugger commands. First argument is the number of lines
  * of help to output for the command.
+ *
+ * Note: Some commands are not supported by the kernel-level version of
+ * the debugger.
  */
 static const struct acpi_db_command_help acpi_gbl_db_command_help[] = {
-	{0, "\nGeneral-Purpose Commands:", "\n"},
+	{0, "\nNamespace Access:", "\n"},
+	{1, "  Businfo", "Display system bus info\n"},
+	{1, "  Disassemble <Method>", "Disassemble a control method\n"},
+	{1, "  Find <AcpiName> (? is wildcard)",
+	 "Find ACPI name(s) with wildcards\n"},
+	{1, "  Integrity", "Validate namespace integrity\n"},
+	{1, "  Methods", "Display list of loaded control methods\n"},
+	{1, "  Namespace [Object] [Depth]",
+	 "Display loaded namespace tree/subtree\n"},
+	{1, "  Notify <Object> <Value>", "Send a notification on Object\n"},
+	{1, "  Objects [ObjectType]",
+	 "Display summary of all objects or just given type\n"},
+	{1, "  Owner <OwnerId> [Depth]",
+	 "Display loaded namespace by object owner\n"},
+	{1, "  Paths", "Display full pathnames of namespace objects\n"},
+	{1, "  Predefined", "Check all predefined names\n"},
+	{1, "  Prefix [<Namepath>]", "Set or Get current execution prefix\n"},
+	{1, "  References <Addr>", "Find all references to object at addr\n"},
+	{1, "  Resources [DeviceName]",
+	 "Display Device resources (no arg = all devices)\n"},
+	{1, "  Set N <NamedObject> <Value>", "Set value for named integer\n"},
+	{1, "  Template <Object>", "Format/dump a Buffer/ResourceTemplate\n"},
+	{1, "  Type <Object>", "Display object type\n"},
+
+	{0, "\nControl Method Execution:", "\n"},
+	{1, "  Evaluate <Namepath> [Arguments]",
+	 "Evaluate object or control method\n"},
+	{1, "  Execute <Namepath> [Arguments]", "Synonym for Evaluate\n"},
+#ifdef ACPI_APPLICATION
+	{1, "  Background <Namepath> [Arguments]",
+	 "Evaluate object/method in a separate thread\n"},
+	{1, "  Thread <Threads><Loops><NamePath>",
+	 "Spawn threads to execute method(s)\n"},
+#endif
+	{1, "  Debug <Namepath> [Arguments]", "Single-Step a control method\n"},
+	{7, "  [Arguments] formats:", "Control method argument formats\n"},
+	{1, "     Hex Integer", "Integer\n"},
+	{1, "     \"Ascii String\"", "String\n"},
+	{1, "     (Hex Byte List)", "Buffer\n"},
+	{1, "         (01 42 7A BF)", "Buffer example (4 bytes)\n"},
+	{1, "     [Package Element List]", "Package\n"},
+	{1, "         [0x01 0x1234 \"string\"]",
+	 "Package example (3 elements)\n"},
+
+	{0, "\nMiscellaneous:", "\n"},
 	{1, "  Allocations", "Display list of current memory allocations\n"},
 	{2, "  Dump <Address>|<Namepath>", "\n"},
 	{0, "       [Byte|Word|Dword|Qword]",
@@ -248,46 +297,30 @@ static const struct acpi_db_command_help acpi_gbl_db_command_help[] = {
 	{1, "     Stack", "Display CPU stack usage\n"},
 	{1, "     Tables", "Info about current ACPI table(s)\n"},
 	{1, "  Tables", "Display info about loaded ACPI tables\n"},
+#ifdef ACPI_APPLICATION
+	{1, "  Terminate", "Delete namespace and all internal objects\n"},
+#endif
 	{1, "  ! <CommandNumber>", "Execute command from history buffer\n"},
 	{1, "  !!", "Execute last command again\n"},
 
-	{0, "\nNamespace Access Commands:", "\n"},
-	{1, "  Businfo", "Display system bus info\n"},
-	{1, "  Disassemble <Method>", "Disassemble a control method\n"},
-	{1, "  Find <AcpiName> (? is wildcard)",
-	 "Find ACPI name(s) with wildcards\n"},
-	{1, "  Integrity", "Validate namespace integrity\n"},
-	{1, "  Methods", "Display list of loaded control methods\n"},
-	{1, "  Namespace [Object] [Depth]",
-	 "Display loaded namespace tree/subtree\n"},
-	{1, "  Notify <Object> <Value>", "Send a notification on Object\n"},
-	{1, "  Objects [ObjectType]",
-	 "Display summary of all objects or just given type\n"},
-	{1, "  Owner <OwnerId> [Depth]",
-	 "Display loaded namespace by object owner\n"},
-	{1, "  Paths", "Display full pathnames of namespace objects\n"},
-	{1, "  Predefined", "Check all predefined names\n"},
-	{1, "  Prefix [<Namepath>]", "Set or Get current execution prefix\n"},
-	{1, "  References <Addr>", "Find all references to object at addr\n"},
-	{1, "  Resources [DeviceName]",
-	 "Display Device resources (no arg = all devices)\n"},
-	{1, "  Set N <NamedObject> <Value>", "Set value for named integer\n"},
-	{1, "  Template <Object>", "Format/dump a Buffer/ResourceTemplate\n"},
-	{1, "  Type <Object>", "Display object type\n"},
+	{0, "\nMethod and Namespace Debugging:", "\n"},
+	{5, "  Trace <State> [<Namepath>] [Once]",
+	 "Trace control method execution\n"},
+	{1, "     Enable", "Enable all messages\n"},
+	{1, "     Disable", "Disable tracing\n"},
+	{1, "     Method", "Enable method execution messages\n"},
+	{1, "     Opcode", "Enable opcode execution messages\n"},
+	{3, "  Test <TestName>", "Invoke a debug test\n"},
+	{1, "     Objects", "Read/write/compare all namespace data objects\n"},
+	{1, "     Predefined",
+	 "Validate all ACPI predefined names (_STA, etc.)\n"},
+	{1, "  Execute predefined",
+	 "Execute all predefined (public) methods\n"},
 
-	{0, "\nControl Method Execution Commands:", "\n"},
+	{0, "\nControl Method Single-Step Execution:", "\n"},
 	{1, "  Arguments (or Args)", "Display method arguments\n"},
 	{1, "  Breakpoint <AmlOffset>", "Set an AML execution breakpoint\n"},
 	{1, "  Call", "Run to next control method invocation\n"},
-	{1, "  Debug <Namepath> [Arguments]", "Single Step a control method\n"},
-	{6, "  Evaluate", "Synonym for Execute\n"},
-	{5, "  Execute <Namepath> [Arguments]", "Execute control method\n"},
-	{1, "     Hex Integer", "Integer method argument\n"},
-	{1, "     \"Ascii String\"", "String method argument\n"},
-	{1, "     (Hex Byte List)", "Buffer method argument\n"},
-	{1, "     [Package Element List]", "Package method argument\n"},
-	{5, "  Execute predefined",
-	 "Execute all predefined (public) methods\n"},
 	{1, "  Go", "Allow method to run to completion\n"},
 	{1, "  Information", "Display info about the current method\n"},
 	{1, "  Into", "Step into (not over) a method call\n"},
@@ -296,41 +329,24 @@ static const struct acpi_db_command_help acpi_gbl_db_command_help[] = {
 	{1, "  Results", "Display method result stack\n"},
 	{1, "  Set <A|L> <#> <Value>", "Set method data (Arguments/Locals)\n"},
 	{1, "  Stop", "Terminate control method\n"},
-	{5, "  Trace <State> [<Namepath>] [Once]",
-	 "Trace control method execution\n"},
-	{1, "     Enable", "Enable all messages\n"},
-	{1, "     Disable", "Disable tracing\n"},
-	{1, "     Method", "Enable method execution messages\n"},
-	{1, "     Opcode", "Enable opcode execution messages\n"},
 	{1, "  Tree", "Display control method calling tree\n"},
 	{1, "  <Enter>", "Single step next AML opcode (over calls)\n"},
 
 #ifdef ACPI_APPLICATION
-	{0, "\nHardware Simulation Commands:", "\n"},
-	{1, "  EnableAcpi", "Enable ACPI (hardware) mode\n"},
-	{1, "  Event <F|G> <Value>", "Generate AcpiEvent (Fixed/GPE)\n"},
-	{1, "  Gpe <GpeNum> [GpeBlockDevice]", "Simulate a GPE\n"},
-	{1, "  Gpes", "Display info on all GPE devices\n"},
-	{1, "  Sci", "Generate an SCI\n"},
-	{1, "  Sleep [SleepState]", "Simulate sleep/wake sequence(s) (0-5)\n"},
-
-	{0, "\nFile I/O Commands:", "\n"},
+	{0, "\nFile Operations:", "\n"},
 	{1, "  Close", "Close debug output file\n"},
 	{1, "  Load <Input Filename>", "Load ACPI table from a file\n"},
 	{1, "  Open <Output Filename>", "Open a file for debug output\n"},
 	{1, "  Unload <Namepath>",
 	 "Unload an ACPI table via namespace object\n"},
 
-	{0, "\nUser Space Commands:", "\n"},
-	{1, "  Terminate", "Delete namespace and all internal objects\n"},
-	{1, "  Thread <Threads><Loops><NamePath>",
-	 "Spawn threads to execute method(s)\n"},
-
-	{0, "\nDebug Test Commands:", "\n"},
-	{3, "  Test <TestName>", "Invoke a debug test\n"},
-	{1, "     Objects", "Read/write/compare all namespace data objects\n"},
-	{1, "     Predefined",
-	 "Execute all ACPI predefined names (_STA, etc.)\n"},
+	{0, "\nHardware Simulation:", "\n"},
+	{1, "  EnableAcpi", "Enable ACPI (hardware) mode\n"},
+	{1, "  Event <F|G> <Value>", "Generate AcpiEvent (Fixed/GPE)\n"},
+	{1, "  Gpe <GpeNum> [GpeBlockDevice]", "Simulate a GPE\n"},
+	{1, "  Gpes", "Display info on all GPE devices\n"},
+	{1, "  Sci", "Generate an SCI\n"},
+	{1, "  Sleep [SleepState]", "Simulate sleep/wake sequence(s) (0-5)\n"},
 #endif
 	{0, NULL, NULL}
 };
@@ -442,11 +458,15 @@ static void acpi_db_display_help(char *command)
 
 		/* No argument to help, display help for all commands */
 
+		acpi_os_printf("\nSummary of AML Debugger Commands\n\n");
+
 		while (next->invocation) {
 			acpi_os_printf("%-38s%s", next->invocation,
 				       next->description);
 			next++;
 		}
+		acpi_os_printf("\n");
+
 	} else {
 		/* Display help for all commands that match the subtring */
 
@@ -1087,6 +1107,13 @@ acpi_db_command_dispatch(char *input_buffer,
 		/*  acpi_initialize (NULL); */
 		break;
 
+	case CMD_BACKGROUND:
+
+		acpi_db_create_execution_thread(acpi_gbl_db_args[1],
+						&acpi_gbl_db_args[2],
+						&acpi_gbl_db_arg_types[2]);
+		break;
+
 	case CMD_THREADS:
 
 		acpi_db_create_execution_threads(acpi_gbl_db_args[1],
diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c
index f470e81b0499..4b6ebc2a2851 100644
--- a/drivers/acpi/acpica/dscontrol.c
+++ b/drivers/acpi/acpica/dscontrol.c
@@ -118,6 +118,8 @@ acpi_ds_exec_begin_control_op(struct acpi_walk_state *walk_state,
 		control_state->control.package_end =
 		    walk_state->parser_state.pkg_end;
 		control_state->control.opcode = op->common.aml_opcode;
+		control_state->control.loop_timeout = acpi_os_get_timer() +
+		    (u64)(acpi_gbl_max_loop_iterations * ACPI_100NSEC_PER_SEC);
 
 		/* Push the control state on this walk's control stack */
 
@@ -206,15 +208,15 @@ acpi_ds_exec_end_control_op(struct acpi_walk_state *walk_state,
 			/* Predicate was true, the body of the loop was just executed */
 
 			/*
-			 * This loop counter mechanism allows the interpreter to escape
-			 * possibly infinite loops. This can occur in poorly written AML
-			 * when the hardware does not respond within a while loop and the
-			 * loop does not implement a timeout.
+			 * This infinite loop detection mechanism allows the interpreter
+			 * to escape possibly infinite loops. This can occur in poorly
+			 * written AML when the hardware does not respond within a while
+			 * loop and the loop does not implement a timeout.
 			 */
-			control_state->control.loop_count++;
-			if (control_state->control.loop_count >
-			    acpi_gbl_max_loop_iterations) {
-				status = AE_AML_INFINITE_LOOP;
+			if (ACPI_TIME_AFTER(acpi_os_get_timer(),
+					    control_state->control.
+					    loop_timeout)) {
+				status = AE_AML_LOOP_TIMEOUT;
 				break;
 			}
 
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index 7bcf5f5ea029..0cab34a593d5 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -209,7 +209,8 @@ acpi_ds_create_buffer_field(union acpi_parse_object *op,
 					ACPI_IMODE_LOAD_PASS1, flags,
 					walk_state, &node);
 		if (ACPI_FAILURE(status)) {
-			ACPI_ERROR_NAMESPACE(arg->common.value.string, status);
+			ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+					     arg->common.value.string, status);
 			return_ACPI_STATUS(status);
 		}
 	}
@@ -383,7 +384,9 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info,
 							walk_state,
 							&info->connection_node);
 				if (ACPI_FAILURE(status)) {
-					ACPI_ERROR_NAMESPACE(child->common.
+					ACPI_ERROR_NAMESPACE(walk_state->
+							     scope_info,
+							     child->common.
 							     value.name,
 							     status);
 					return_ACPI_STATUS(status);
@@ -402,7 +405,8 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info,
 						ACPI_NS_DONT_OPEN_SCOPE,
 						walk_state, &info->field_node);
 			if (ACPI_FAILURE(status)) {
-				ACPI_ERROR_NAMESPACE((char *)&arg->named.name,
+				ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+						     (char *)&arg->named.name,
 						     status);
 				return_ACPI_STATUS(status);
 			} else {
@@ -498,7 +502,8 @@ acpi_ds_create_field(union acpi_parse_object *op,
 							&region_node);
 #endif
 		if (ACPI_FAILURE(status)) {
-			ACPI_ERROR_NAMESPACE(arg->common.value.name, status);
+			ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+					     arg->common.value.name, status);
 			return_ACPI_STATUS(status);
 		}
 	}
@@ -618,7 +623,8 @@ acpi_ds_init_field_objects(union acpi_parse_object *op,
 						ACPI_IMODE_LOAD_PASS1, flags,
 						walk_state, &node);
 			if (ACPI_FAILURE(status)) {
-				ACPI_ERROR_NAMESPACE((char *)&arg->named.name,
+				ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+						     (char *)&arg->named.name,
 						     status);
 				if (status != AE_ALREADY_EXISTS) {
 					return_ACPI_STATUS(status);
@@ -681,7 +687,8 @@ acpi_ds_create_bank_field(union acpi_parse_object *op,
 							&region_node);
 #endif
 		if (ACPI_FAILURE(status)) {
-			ACPI_ERROR_NAMESPACE(arg->common.value.name, status);
+			ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+					     arg->common.value.name, status);
 			return_ACPI_STATUS(status);
 		}
 	}
@@ -695,7 +702,8 @@ acpi_ds_create_bank_field(union acpi_parse_object *op,
 			   ACPI_NS_SEARCH_PARENT, walk_state,
 			   &info.register_node);
 	if (ACPI_FAILURE(status)) {
-		ACPI_ERROR_NAMESPACE(arg->common.value.string, status);
+		ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+				     arg->common.value.string, status);
 		return_ACPI_STATUS(status);
 	}
 
@@ -765,7 +773,8 @@ acpi_ds_create_index_field(union acpi_parse_object *op,
 			   ACPI_NS_SEARCH_PARENT, walk_state,
 			   &info.register_node);
 	if (ACPI_FAILURE(status)) {
-		ACPI_ERROR_NAMESPACE(arg->common.value.string, status);
+		ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+				     arg->common.value.string, status);
 		return_ACPI_STATUS(status);
 	}
 
@@ -778,7 +787,8 @@ acpi_ds_create_index_field(union acpi_parse_object *op,
 			   ACPI_NS_SEARCH_PARENT, walk_state,
 			   &info.data_register_node);
 	if (ACPI_FAILURE(status)) {
-		ACPI_ERROR_NAMESPACE(arg->common.value.string, status);
+		ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+				     arg->common.value.string, status);
 		return_ACPI_STATUS(status);
 	}
 
diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c
index 82448551781b..b21fe084ffc8 100644
--- a/drivers/acpi/acpica/dsobject.c
+++ b/drivers/acpi/acpica/dsobject.c
@@ -112,7 +112,9 @@ acpi_ds_build_internal_object(struct acpi_walk_state *walk_state,
 							 acpi_namespace_node,
 							 &(op->common.node)));
 				if (ACPI_FAILURE(status)) {
-					ACPI_ERROR_NAMESPACE(op->common.value.
+					ACPI_ERROR_NAMESPACE(walk_state->
+							     scope_info,
+							     op->common.value.
 							     string, status);
 					return_ACPI_STATUS(status);
 				}
diff --git a/drivers/acpi/acpica/dspkginit.c b/drivers/acpi/acpica/dspkginit.c
index 6d487edfe2de..5a602b75084e 100644
--- a/drivers/acpi/acpica/dspkginit.c
+++ b/drivers/acpi/acpica/dspkginit.c
@@ -297,8 +297,10 @@ acpi_ds_init_package_element(u8 object_type,
 {
 	union acpi_operand_object **element_ptr;
 
+	ACPI_FUNCTION_TRACE(ds_init_package_element);
+
 	if (!source_object) {
-		return (AE_OK);
+		return_ACPI_STATUS(AE_OK);
 	}
 
 	/*
@@ -329,7 +331,7 @@ acpi_ds_init_package_element(u8 object_type,
 		source_object->package.flags |= AOPOBJ_DATA_VALID;
 	}
 
-	return (AE_OK);
+	return_ACPI_STATUS(AE_OK);
 }
 
 /*******************************************************************************
@@ -352,6 +354,7 @@ acpi_ds_resolve_package_element(union acpi_operand_object **element_ptr)
 	union acpi_generic_state scope_info;
 	union acpi_operand_object *element = *element_ptr;
 	struct acpi_namespace_node *resolved_node;
+	struct acpi_namespace_node *original_node;
 	char *external_path = NULL;
 	acpi_object_type type;
 
@@ -441,6 +444,7 @@ acpi_ds_resolve_package_element(union acpi_operand_object **element_ptr)
 	 * will remain as named references. This behavior is not described
 	 * in the ACPI spec, but it appears to be an oversight.
 	 */
+	original_node = resolved_node;
 	status = acpi_ex_resolve_node_to_value(&resolved_node, NULL);
 	if (ACPI_FAILURE(status)) {
 		return_VOID;
@@ -468,26 +472,27 @@ acpi_ds_resolve_package_element(union acpi_operand_object **element_ptr)
 		 */
 	case ACPI_TYPE_DEVICE:
 	case ACPI_TYPE_THERMAL:
-
-		/* TBD: This may not be necesssary */
-
-		acpi_ut_add_reference(resolved_node->object);
+	case ACPI_TYPE_METHOD:
 		break;
 
 	case ACPI_TYPE_MUTEX:
-	case ACPI_TYPE_METHOD:
 	case ACPI_TYPE_POWER:
 	case ACPI_TYPE_PROCESSOR:
 	case ACPI_TYPE_EVENT:
 	case ACPI_TYPE_REGION:
 
+		/* acpi_ex_resolve_node_to_value gave these an extra reference */
+
+		acpi_ut_remove_reference(original_node->object);
 		break;
 
 	default:
 		/*
 		 * For all other types - the node was resolved to an actual
-		 * operand object with a value, return the object
+		 * operand object with a value, return the object. Remove
+		 * a reference on the existing object.
 		 */
+		acpi_ut_remove_reference(element);
 		*element_ptr = (union acpi_operand_object *)resolved_node;
 		break;
 	}
diff --git a/drivers/acpi/acpica/dsutils.c b/drivers/acpi/acpica/dsutils.c
index 0dabd9b95684..4c5faf629a83 100644
--- a/drivers/acpi/acpica/dsutils.c
+++ b/drivers/acpi/acpica/dsutils.c
@@ -583,7 +583,8 @@ acpi_ds_create_operand(struct acpi_walk_state *walk_state,
 			}
 
 			if (ACPI_FAILURE(status)) {
-				ACPI_ERROR_NAMESPACE(name_string, status);
+				ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+						     name_string, status);
 			}
 		}
 
diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c
index eaa859a89702..5771e4e4a99a 100644
--- a/drivers/acpi/acpica/dswload.c
+++ b/drivers/acpi/acpica/dswload.c
@@ -207,7 +207,8 @@ acpi_ds_load1_begin_op(struct acpi_walk_state *walk_state,
 		}
 #endif
 		if (ACPI_FAILURE(status)) {
-			ACPI_ERROR_NAMESPACE(path, status);
+			ACPI_ERROR_NAMESPACE(walk_state->scope_info, path,
+					     status);
 			return_ACPI_STATUS(status);
 		}
 
@@ -375,7 +376,8 @@ acpi_ds_load1_begin_op(struct acpi_walk_state *walk_state,
 			}
 
 			if (ACPI_FAILURE(status)) {
-				ACPI_ERROR_NAMESPACE(path, status);
+				ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+						     path, status);
 				return_ACPI_STATUS(status);
 			}
 		}
diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c
index aad83ef5a4ec..b3d0aaec8203 100644
--- a/drivers/acpi/acpica/dswload2.c
+++ b/drivers/acpi/acpica/dswload2.c
@@ -184,11 +184,14 @@ acpi_ds_load2_begin_op(struct acpi_walk_state *walk_state,
 				if (status == AE_NOT_FOUND) {
 					status = AE_OK;
 				} else {
-					ACPI_ERROR_NAMESPACE(buffer_ptr,
+					ACPI_ERROR_NAMESPACE(walk_state->
+							     scope_info,
+							     buffer_ptr,
 							     status);
 				}
 #else
-				ACPI_ERROR_NAMESPACE(buffer_ptr, status);
+				ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+						     buffer_ptr, status);
 #endif
 				return_ACPI_STATUS(status);
 			}
@@ -343,7 +346,8 @@ acpi_ds_load2_begin_op(struct acpi_walk_state *walk_state,
 	}
 
 	if (ACPI_FAILURE(status)) {
-		ACPI_ERROR_NAMESPACE(buffer_ptr, status);
+		ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+				     buffer_ptr, status);
 		return_ACPI_STATUS(status);
 	}
 
@@ -719,7 +723,8 @@ acpi_status acpi_ds_load2_end_op(struct acpi_walk_state *walk_state)
 			 */
 			op->common.node = new_node;
 		} else {
-			ACPI_ERROR_NAMESPACE(arg->common.value.string, status);
+			ACPI_ERROR_NAMESPACE(walk_state->scope_info,
+					     arg->common.value.string, status);
 		}
 		break;
 
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 28b447ff92df..bb58419f0d61 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -298,6 +298,16 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 		ACPI_EXCEPTION((AE_INFO, status, "Returned by Handler for [%s]",
 				acpi_ut_get_region_name(region_obj->region.
 							space_id)));
+
+		/*
+		 * Special case for an EC timeout. These are seen so frequently
+		 * that an additional error message is helpful
+		 */
+		if ((region_obj->region.space_id == ACPI_ADR_SPACE_EC) &&
+		    (status == AE_TIME)) {
+			ACPI_ERROR((AE_INFO,
+				    "Timeout from EC hardware or EC device driver"));
+		}
 	}
 
 	if (!(handler_desc->address_space.handler_flags &
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index 83398dc4b7c2..b2ff61bdb9a8 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -617,10 +617,11 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth)
 	u32 length;
 	u32 index;
 
-	ACPI_FUNCTION_NAME(ex_dump_operand)
+	ACPI_FUNCTION_NAME(ex_dump_operand);
 
-	    /* Check if debug output enabled */
-	    if (!ACPI_IS_DEBUG_ENABLED(ACPI_LV_EXEC, _COMPONENT)) {
+	/* Check if debug output enabled */
+
+	if (!ACPI_IS_DEBUG_ENABLED(ACPI_LV_EXEC, _COMPONENT)) {
 		return;
 	}
 
@@ -904,7 +905,7 @@ void
 acpi_ex_dump_operands(union acpi_operand_object **operands,
 		      const char *opcode_name, u32 num_operands)
 {
-	ACPI_FUNCTION_NAME(ex_dump_operands);
+	ACPI_FUNCTION_TRACE(ex_dump_operands);
 
 	if (!opcode_name) {
 		opcode_name = "UNKNOWN";
@@ -928,7 +929,7 @@ acpi_ex_dump_operands(union acpi_operand_object **operands,
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
 			  "**** End operand dump for [%s]\n", opcode_name));
-	return;
+	return_VOID;
 }
 
 /*******************************************************************************
diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c
index a2f4e25d45b1..5b4282902a83 100644
--- a/drivers/acpi/acpica/hwtimer.c
+++ b/drivers/acpi/acpica/hwtimer.c
@@ -150,10 +150,10 @@ ACPI_EXPORT_SYMBOL(acpi_get_timer)
  *
  ******************************************************************************/
 acpi_status
-acpi_get_timer_duration(u32 start_ticks, u32 end_ticks, u32 * time_elapsed)
+acpi_get_timer_duration(u32 start_ticks, u32 end_ticks, u32 *time_elapsed)
 {
 	acpi_status status;
-	u32 delta_ticks;
+	u64 delta_ticks;
 	u64 quotient;
 
 	ACPI_FUNCTION_TRACE(acpi_get_timer_duration);
@@ -168,30 +168,29 @@ acpi_get_timer_duration(u32 start_ticks, u32 end_ticks, u32 * time_elapsed)
 		return_ACPI_STATUS(AE_SUPPORT);
 	}
 
+	if (start_ticks == end_ticks) {
+		*time_elapsed = 0;
+		return_ACPI_STATUS(AE_OK);
+	}
+
 	/*
 	 * Compute Tick Delta:
 	 * Handle (max one) timer rollovers on 24-bit versus 32-bit timers.
 	 */
-	if (start_ticks < end_ticks) {
-		delta_ticks = end_ticks - start_ticks;
-	} else if (start_ticks > end_ticks) {
+	delta_ticks = end_ticks;
+	if (start_ticks > end_ticks) {
 		if ((acpi_gbl_FADT.flags & ACPI_FADT_32BIT_TIMER) == 0) {
 
 			/* 24-bit Timer */
 
-			delta_ticks =
-			    (((0x00FFFFFF - start_ticks) +
-			      end_ticks) & 0x00FFFFFF);
+			delta_ticks |= (u64)1 << 24;
 		} else {
 			/* 32-bit Timer */
 
-			delta_ticks = (0xFFFFFFFF - start_ticks) + end_ticks;
+			delta_ticks |= (u64)1 << 32;
 		}
-	} else {		/* start_ticks == end_ticks */
-
-		*time_elapsed = 0;
-		return_ACPI_STATUS(AE_OK);
 	}
+	delta_ticks -= start_ticks;
 
 	/*
 	 * Compute Duration (Requires a 64-bit multiply and divide):
@@ -199,10 +198,10 @@ acpi_get_timer_duration(u32 start_ticks, u32 end_ticks, u32 * time_elapsed)
 	 * time_elapsed (microseconds) =
 	 *  (delta_ticks * ACPI_USEC_PER_SEC) / ACPI_PM_TIMER_FREQUENCY;
 	 */
-	status = acpi_ut_short_divide(((u64)delta_ticks) * ACPI_USEC_PER_SEC,
+	status = acpi_ut_short_divide(delta_ticks * ACPI_USEC_PER_SEC,
 				      ACPI_PM_TIMER_FREQUENCY, &quotient, NULL);
 
-	*time_elapsed = (u32) quotient;
+	*time_elapsed = (u32)quotient;
 	return_ACPI_STATUS(status);
 }
 
diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c
index 3094cec4eab4..d1679035d5f3 100644
--- a/drivers/acpi/acpica/hwvalid.c
+++ b/drivers/acpi/acpica/hwvalid.c
@@ -128,14 +128,14 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width)
 	acpi_io_address last_address;
 	const struct acpi_port_info *port_info;
 
-	ACPI_FUNCTION_NAME(hw_validate_io_request);
+	ACPI_FUNCTION_TRACE(hw_validate_io_request);
 
 	/* Supported widths are 8/16/32 */
 
 	if ((bit_width != 8) && (bit_width != 16) && (bit_width != 32)) {
 		ACPI_ERROR((AE_INFO,
 			    "Bad BitWidth parameter: %8.8X", bit_width));
-		return (AE_BAD_PARAMETER);
+		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
 	port_info = acpi_protected_ports;
@@ -153,13 +153,13 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width)
 		ACPI_ERROR((AE_INFO,
 			    "Illegal I/O port address/length above 64K: %8.8X%8.8X/0x%X",
 			    ACPI_FORMAT_UINT64(address), byte_width));
-		return (AE_LIMIT);
+		return_ACPI_STATUS(AE_LIMIT);
 	}
 
 	/* Exit if requested address is not within the protected port table */
 
 	if (address > acpi_protected_ports[ACPI_PORT_INFO_ENTRIES - 1].end) {
-		return (AE_OK);
+		return_ACPI_STATUS(AE_OK);
 	}
 
 	/* Check request against the list of protected I/O ports */
@@ -180,8 +180,8 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width)
 			/* Port illegality may depend on the _OSI calls made by the BIOS */
 
 			if (acpi_gbl_osi_data >= port_info->osi_dependency) {
-				ACPI_DEBUG_PRINT((ACPI_DB_IO,
-						  "Denied AML access to port 0x%8.8X%8.8X/%X (%s 0x%.4X-0x%.4X)",
+				ACPI_DEBUG_PRINT((ACPI_DB_VALUES,
+						  "Denied AML access to port 0x%8.8X%8.8X/%X (%s 0x%.4X-0x%.4X)\n",
 						  ACPI_FORMAT_UINT64(address),
 						  byte_width, port_info->name,
 						  port_info->start,
@@ -198,7 +198,7 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width)
 		}
 	}
 
-	return (AE_OK);
+	return_ACPI_STATUS(AE_OK);
 }
 
 /******************************************************************************
diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index f2733f51ca8d..33e652a12fca 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -644,17 +644,18 @@ acpi_ns_lookup(union acpi_generic_state *scope_info,
 					    this_node->object;
 				}
 			}
-#ifdef ACPI_ASL_COMPILER
-			if (!acpi_gbl_disasm_flag &&
-			    (this_node->flags & ANOBJ_IS_EXTERNAL)) {
-				this_node->flags |= IMPLICIT_EXTERNAL;
-			}
-#endif
 		}
 
 		/* Special handling for the last segment (num_segments == 0) */
 
 		else {
+#ifdef ACPI_ASL_COMPILER
+			if (!acpi_gbl_disasm_flag
+			    && (this_node->flags & ANOBJ_IS_EXTERNAL)) {
+				this_node->flags &= ~IMPLICIT_EXTERNAL;
+			}
+#endif
+
 			/*
 			 * Sanity typecheck of the target object:
 			 *
diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c
index 539d775bbc92..d55dcc82f434 100644
--- a/drivers/acpi/acpica/nsconvert.c
+++ b/drivers/acpi/acpica/nsconvert.c
@@ -495,7 +495,8 @@ acpi_ns_convert_to_reference(struct acpi_namespace_node *scope,
 
 		/* Check if we are resolving a named reference within a package */
 
-		ACPI_ERROR_NAMESPACE(original_object->string.pointer, status);
+		ACPI_ERROR_NAMESPACE(&scope_info,
+				     original_object->string.pointer, status);
 		goto error_exit;
 	}
 
diff --git a/drivers/acpi/acpica/nsnames.c b/drivers/acpi/acpica/nsnames.c
index a410760a0308..22c92d1a24d8 100644
--- a/drivers/acpi/acpica/nsnames.c
+++ b/drivers/acpi/acpica/nsnames.c
@@ -49,6 +49,9 @@
 #define _COMPONENT          ACPI_NAMESPACE
 ACPI_MODULE_NAME("nsnames")
 
+/* Local Prototypes */
+static void acpi_ns_normalize_pathname(char *original_path);
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ns_get_external_pathname
@@ -63,6 +66,7 @@ ACPI_MODULE_NAME("nsnames")
  *              for error and debug statements.
  *
  ******************************************************************************/
+
 char *acpi_ns_get_external_pathname(struct acpi_namespace_node *node)
 {
 	char *name_buffer;
@@ -352,3 +356,148 @@ char *acpi_ns_get_normalized_pathname(struct acpi_namespace_node *node,
 
 	return_PTR(name_buffer);
 }
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_build_prefixed_pathname
+ *
+ * PARAMETERS:  prefix_scope        - Scope/Path that prefixes the internal path
+ *              internal_path       - Name or path of the namespace node
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Construct a fully qualified pathname from a concatenation of:
+ *              1) Path associated with the prefix_scope namespace node
+ *              2) External path representation of the Internal path
+ *
+ ******************************************************************************/
+
+char *acpi_ns_build_prefixed_pathname(union acpi_generic_state *prefix_scope,
+				      const char *internal_path)
+{
+	acpi_status status;
+	char *full_path = NULL;
+	char *external_path = NULL;
+	char *prefix_path = NULL;
+	u32 prefix_path_length = 0;
+
+	/* If there is a prefix, get the pathname to it */
+
+	if (prefix_scope && prefix_scope->scope.node) {
+		prefix_path =
+		    acpi_ns_get_normalized_pathname(prefix_scope->scope.node,
+						    TRUE);
+		if (prefix_path) {
+			prefix_path_length = strlen(prefix_path);
+		}
+	}
+
+	status = acpi_ns_externalize_name(ACPI_UINT32_MAX, internal_path,
+					  NULL, &external_path);
+	if (ACPI_FAILURE(status)) {
+		goto cleanup;
+	}
+
+	/* Merge the prefix path and the path. 2 is for one dot and trailing null */
+
+	full_path =
+	    ACPI_ALLOCATE_ZEROED(prefix_path_length + strlen(external_path) +
+				 2);
+	if (!full_path) {
+		goto cleanup;
+	}
+
+	/* Don't merge if the External path is already fully qualified */
+
+	if (prefix_path && (*external_path != '\\') && (*external_path != '^')) {
+		strcat(full_path, prefix_path);
+		if (prefix_path[1]) {
+			strcat(full_path, ".");
+		}
+	}
+
+	acpi_ns_normalize_pathname(external_path);
+	strcat(full_path, external_path);
+
+cleanup:
+	if (prefix_path) {
+		ACPI_FREE(prefix_path);
+	}
+	if (external_path) {
+		ACPI_FREE(external_path);
+	}
+
+	return (full_path);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_normalize_pathname
+ *
+ * PARAMETERS:  original_path       - Path to be normalized, in External format
+ *
+ * RETURN:      The original path is processed in-place
+ *
+ * DESCRIPTION: Remove trailing underscores from each element of a path.
+ *
+ *              For example:  \A___.B___.C___ becomes \A.B.C
+ *
+ ******************************************************************************/
+
+static void acpi_ns_normalize_pathname(char *original_path)
+{
+	char *input_path = original_path;
+	char *new_path_buffer;
+	char *new_path;
+	u32 i;
+
+	/* Allocate a temp buffer in which to construct the new path */
+
+	new_path_buffer = ACPI_ALLOCATE_ZEROED(strlen(input_path) + 1);
+	new_path = new_path_buffer;
+	if (!new_path_buffer) {
+		return;
+	}
+
+	/* Special characters may appear at the beginning of the path */
+
+	if (*input_path == '\\') {
+		*new_path = *input_path;
+		new_path++;
+		input_path++;
+	}
+
+	while (*input_path == '^') {
+		*new_path = *input_path;
+		new_path++;
+		input_path++;
+	}
+
+	/* Remainder of the path */
+
+	while (*input_path) {
+
+		/* Do one nameseg at a time */
+
+		for (i = 0; (i < ACPI_NAME_SIZE) && *input_path; i++) {
+			if ((i == 0) || (*input_path != '_')) {	/* First char is allowed to be underscore */
+				*new_path = *input_path;
+				new_path++;
+			}
+
+			input_path++;
+		}
+
+		/* Dot means that there are more namesegs to come */
+
+		if (*input_path == '.') {
+			*new_path = *input_path;
+			new_path++;
+			input_path++;
+		}
+	}
+
+	*new_path = 0;
+	strcpy(original_path, new_path_buffer);
+	ACPI_FREE(new_path_buffer);
+}
diff --git a/drivers/acpi/acpica/nssearch.c b/drivers/acpi/acpica/nssearch.c
index 5de8957f5ef0..e91dbee9235f 100644
--- a/drivers/acpi/acpica/nssearch.c
+++ b/drivers/acpi/acpica/nssearch.c
@@ -417,6 +417,7 @@ acpi_ns_search_and_enter(u32 target_name,
 	if (flags & ACPI_NS_EXTERNAL ||
 	    (walk_state && walk_state->opcode == AML_SCOPE_OP)) {
 		new_node->flags |= ANOBJ_IS_EXTERNAL;
+		new_node->flags |= IMPLICIT_EXTERNAL;
 	}
 #endif
 
diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c
index 783f4c838aee..9b51f65823b2 100644
--- a/drivers/acpi/acpica/nsxfeval.c
+++ b/drivers/acpi/acpica/nsxfeval.c
@@ -61,10 +61,10 @@ static void acpi_ns_resolve_references(struct acpi_evaluate_info *info);
  *
  * PARAMETERS:  handle              - Object handle (optional)
  *              pathname            - Object pathname (optional)
- *              external_params     - List of parameters to pass to method,
+ *              external_params     - List of parameters to pass to a method,
  *                                    terminated by NULL. May be NULL
  *                                    if no parameters are being passed.
- *              return_buffer       - Where to put method's return value (if
+ *              return_buffer       - Where to put the object's return value (if
  *                                    any). If NULL, no value is returned.
  *              return_type         - Expected type of return object
  *
@@ -100,13 +100,14 @@ acpi_evaluate_object_typed(acpi_handle handle,
 		free_buffer_on_error = TRUE;
 	}
 
+	/* Get a handle here, in order to build an error message if needed */
+
+	target_handle = handle;
 	if (pathname) {
 		status = acpi_get_handle(handle, pathname, &target_handle);
 		if (ACPI_FAILURE(status)) {
 			return_ACPI_STATUS(status);
 		}
-	} else {
-		target_handle = handle;
 	}
 
 	full_pathname = acpi_ns_get_external_pathname(target_handle);
diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c
index eb9dfaca555f..171e2faa7c50 100644
--- a/drivers/acpi/acpica/psargs.c
+++ b/drivers/acpi/acpica/psargs.c
@@ -361,7 +361,7 @@ acpi_ps_get_next_namepath(struct acpi_walk_state *walk_state,
 	/* Final exception check (may have been changed from code above) */
 
 	if (ACPI_FAILURE(status)) {
-		ACPI_ERROR_NAMESPACE(path, status);
+		ACPI_ERROR_NAMESPACE(walk_state->scope_info, path, status);
 
 		if ((walk_state->parse_flags & ACPI_PARSE_MODE_MASK) ==
 		    ACPI_PARSE_EXECUTE) {
diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c
index 0bef6df71bba..c0b179883ff2 100644
--- a/drivers/acpi/acpica/psobject.c
+++ b/drivers/acpi/acpica/psobject.c
@@ -372,16 +372,10 @@ acpi_ps_create_op(struct acpi_walk_state *walk_state,
 			 * external declaration opcode. Setting walk_state->Aml to
 			 * walk_state->parser_state.Aml + 2 moves increments the
 			 * walk_state->Aml past the object type and the paramcount of the
-			 * external opcode. For the error message, only print the AML
-			 * offset. We could attempt to print the name but this may cause
-			 * a segmentation fault when printing the namepath because the
-			 * AML may be incorrect.
+			 * external opcode.
 			 */
-			acpi_os_printf
-			    ("// Invalid external declaration at AML offset 0x%x.\n",
-			     walk_state->aml -
-			     walk_state->parser_state.aml_start);
 			walk_state->aml = walk_state->parser_state.aml + 2;
+			walk_state->parser_state.aml = walk_state->aml;
 			return_ACPI_STATUS(AE_CTRL_PARSE_CONTINUE);
 		}
 #endif
diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c
index 02642760cb93..cd59dfe6a47d 100644
--- a/drivers/acpi/acpica/psutils.c
+++ b/drivers/acpi/acpica/psutils.c
@@ -94,9 +94,11 @@ void acpi_ps_init_op(union acpi_parse_object *op, u16 opcode)
 	op->common.descriptor_type = ACPI_DESC_TYPE_PARSER;
 	op->common.aml_opcode = opcode;
 
-	ACPI_DISASM_ONLY_MEMBERS(strncpy(op->common.aml_op_name,
-					 (acpi_ps_get_opcode_info(opcode))->
-					 name, sizeof(op->common.aml_op_name)));
+	ACPI_DISASM_ONLY_MEMBERS(acpi_ut_safe_strncpy(op->common.aml_op_name,
+						      (acpi_ps_get_opcode_info
+						       (opcode))->name,
+						      sizeof(op->common.
+							     aml_op_name)));
 }
 
 /*******************************************************************************
@@ -158,10 +160,10 @@ union acpi_parse_object *acpi_ps_alloc_op(u16 opcode, u8 *aml)
 		if (opcode == AML_SCOPE_OP) {
 			acpi_gbl_current_scope = op;
 		}
-	}
 
-	if (gbl_capture_comments) {
-		ASL_CV_TRANSFER_COMMENTS(op);
+		if (acpi_gbl_capture_comments) {
+			ASL_CV_TRANSFER_COMMENTS(op);
+		}
 	}
 
 	return (op);
diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c
index 615a885e2ca3..cff7154b7fee 100644
--- a/drivers/acpi/acpica/utdebug.c
+++ b/drivers/acpi/acpica/utdebug.c
@@ -163,6 +163,9 @@ acpi_debug_print(u32 requested_debug_level,
 {
 	acpi_thread_id thread_id;
 	va_list args;
+#ifdef ACPI_APPLICATION
+	int fill_count;
+#endif
 
 	/* Check if debug output enabled */
 
@@ -202,10 +205,21 @@ acpi_debug_print(u32 requested_debug_level,
 		acpi_os_printf("[%u] ", (u32)thread_id);
 	}
 
-	acpi_os_printf("[%02ld] ", acpi_gbl_nesting_level);
-#endif
+	fill_count = 48 - acpi_gbl_nesting_level -
+	    strlen(acpi_ut_trim_function_name(function_name));
+	if (fill_count < 0) {
+		fill_count = 0;
+	}
+
+	acpi_os_printf("[%02ld] %*s",
+		       acpi_gbl_nesting_level, acpi_gbl_nesting_level + 1, " ");
+	acpi_os_printf("%s%*s: ",
+		       acpi_ut_trim_function_name(function_name), fill_count,
+		       " ");
 
+#else
 	acpi_os_printf("%-22.22s: ", acpi_ut_trim_function_name(function_name));
+#endif
 
 	va_start(args, format);
 	acpi_os_vprintf(format, args);
diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c
index 02cd2c2d961a..55debbad487d 100644
--- a/drivers/acpi/acpica/utdecode.c
+++ b/drivers/acpi/acpica/utdecode.c
@@ -395,11 +395,6 @@ const char *acpi_ut_get_reference_name(union acpi_operand_object *object)
 	return (acpi_gbl_ref_class_names[object->reference.class]);
 }
 
-#if defined(ACPI_DEBUG_OUTPUT) || defined(ACPI_DEBUGGER)
-/*
- * Strings and procedures used for debug only
- */
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ut_get_mutex_name
@@ -433,6 +428,12 @@ const char *acpi_ut_get_mutex_name(u32 mutex_id)
 	return (acpi_gbl_mutex_names[mutex_id]);
 }
 
+#if defined(ACPI_DEBUG_OUTPUT) || defined(ACPI_DEBUGGER)
+
+/*
+ * Strings and procedures used for debug only
+ */
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ut_get_notify_name
diff --git a/drivers/acpi/acpica/uterror.c b/drivers/acpi/acpica/uterror.c
index e3368186e1c1..42388dcb5ccc 100644
--- a/drivers/acpi/acpica/uterror.c
+++ b/drivers/acpi/acpica/uterror.c
@@ -182,6 +182,78 @@ acpi_ut_predefined_bios_error(const char *module_name,
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_ut_prefixed_namespace_error
+ *
+ * PARAMETERS:  module_name         - Caller's module name (for error output)
+ *              line_number         - Caller's line number (for error output)
+ *              prefix_scope        - Scope/Path that prefixes the internal path
+ *              internal_path       - Name or path of the namespace node
+ *              lookup_status       - Exception code from NS lookup
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Print error message with the full pathname constructed this way:
+ *
+ *                  prefix_scope_node_full_path.externalized_internal_path
+ *
+ * NOTE:        10/2017: Treat the major ns_lookup errors as firmware errors
+ *
+ ******************************************************************************/
+
+void
+acpi_ut_prefixed_namespace_error(const char *module_name,
+				 u32 line_number,
+				 union acpi_generic_state *prefix_scope,
+				 const char *internal_path,
+				 acpi_status lookup_status)
+{
+	char *full_path;
+	const char *message;
+
+	/*
+	 * Main cases:
+	 * 1) Object creation, object must not already exist
+	 * 2) Object lookup, object must exist
+	 */
+	switch (lookup_status) {
+	case AE_ALREADY_EXISTS:
+
+		acpi_os_printf(ACPI_MSG_BIOS_ERROR);
+		message = "Failure creating";
+		break;
+
+	case AE_NOT_FOUND:
+
+		acpi_os_printf(ACPI_MSG_BIOS_ERROR);
+		message = "Failure looking up";
+		break;
+
+	default:
+
+		acpi_os_printf(ACPI_MSG_ERROR);
+		message = "Failure looking up";
+		break;
+	}
+
+	/* Concatenate the prefix path and the internal path */
+
+	full_path =
+	    acpi_ns_build_prefixed_pathname(prefix_scope, internal_path);
+
+	acpi_os_printf("%s [%s], %s", message,
+		       full_path ? full_path : "Could not get pathname",
+		       acpi_format_exception(lookup_status));
+
+	if (full_path) {
+		ACPI_FREE(full_path);
+	}
+
+	ACPI_MSG_SUFFIX;
+}
+
+#ifdef __OBSOLETE_FUNCTION
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_ut_namespace_error
  *
  * PARAMETERS:  module_name         - Caller's module name (for error output)
@@ -240,6 +312,7 @@ acpi_ut_namespace_error(const char *module_name,
 	ACPI_MSG_SUFFIX;
 	ACPI_MSG_REDIRECT_END;
 }
+#endif
 
 /*******************************************************************************
  *
diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c
index 23e766d1691d..45eeb0dcf283 100644
--- a/drivers/acpi/acpica/utinit.c
+++ b/drivers/acpi/acpica/utinit.c
@@ -206,7 +206,6 @@ acpi_status acpi_ut_init_globals(void)
 	acpi_gbl_next_owner_id_offset = 0;
 	acpi_gbl_debugger_configuration = DEBUGGER_THREADING;
 	acpi_gbl_osi_mutex = NULL;
-	acpi_gbl_max_loop_iterations = ACPI_MAX_LOOP_COUNT;
 
 	/* Hardware oriented */
 
diff --git a/drivers/acpi/acpica/utmath.c b/drivers/acpi/acpica/utmath.c
index 5f9c680076c4..2055a858e5f5 100644
--- a/drivers/acpi/acpica/utmath.c
+++ b/drivers/acpi/acpica/utmath.c
@@ -134,7 +134,7 @@ acpi_status acpi_ut_short_shift_left(u64 operand, u32 count, u64 *out_result)
 
 	if ((count & 63) >= 32) {
 		operand_ovl.part.hi = operand_ovl.part.lo;
-		operand_ovl.part.lo ^= operand_ovl.part.lo;
+		operand_ovl.part.lo = 0;
 		count = (count & 63) - 32;
 	}
 	ACPI_SHIFT_LEFT_64_BY_32(operand_ovl.part.hi,
@@ -171,7 +171,7 @@ acpi_status acpi_ut_short_shift_right(u64 operand, u32 count, u64 *out_result)
 
 	if ((count & 63) >= 32) {
 		operand_ovl.part.lo = operand_ovl.part.hi;
-		operand_ovl.part.hi ^= operand_ovl.part.hi;
+		operand_ovl.part.hi = 0;
 		count = (count & 63) - 32;
 	}
 	ACPI_SHIFT_RIGHT_64_BY_32(operand_ovl.part.hi,
diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
index 586354788018..524ba931d5e8 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -286,8 +286,9 @@ acpi_status acpi_ut_acquire_mutex(acpi_mutex_handle mutex_id)
 		acpi_gbl_mutex_info[mutex_id].thread_id = this_thread_id;
 	} else {
 		ACPI_EXCEPTION((AE_INFO, status,
-				"Thread %u could not acquire Mutex [0x%X]",
-				(u32)this_thread_id, mutex_id));
+				"Thread %u could not acquire Mutex [%s] (0x%X)",
+				(u32)this_thread_id,
+				acpi_ut_get_mutex_name(mutex_id), mutex_id));
 	}
 
 	return (status);
@@ -322,8 +323,8 @@ acpi_status acpi_ut_release_mutex(acpi_mutex_handle mutex_id)
 	 */
 	if (acpi_gbl_mutex_info[mutex_id].thread_id == ACPI_MUTEX_NOT_ACQUIRED) {
 		ACPI_ERROR((AE_INFO,
-			    "Mutex [0x%X] is not acquired, cannot release",
-			    mutex_id));
+			    "Mutex [%s] (0x%X) is not acquired, cannot release",
+			    acpi_ut_get_mutex_name(mutex_id), mutex_id));
 
 		return (AE_NOT_ACQUIRED);
 	}
diff --git a/drivers/acpi/acpica/utnonansi.c b/drivers/acpi/acpica/utnonansi.c
index 792664982ea3..33a0970646df 100644
--- a/drivers/acpi/acpica/utnonansi.c
+++ b/drivers/acpi/acpica/utnonansi.c
@@ -140,7 +140,7 @@ int acpi_ut_stricmp(char *string1, char *string2)
 	return (c1 - c2);
 }
 
-#if defined (ACPI_DEBUGGER) || defined (ACPI_APPLICATION)
+#if defined (ACPI_DEBUGGER) || defined (ACPI_APPLICATION) || defined (ACPI_DEBUG_OUTPUT)
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ut_safe_strcpy, acpi_ut_safe_strcat, acpi_ut_safe_strncat
@@ -199,4 +199,13 @@ acpi_ut_safe_strncat(char *dest,
 	strncat(dest, source, max_transfer_length);
 	return (FALSE);
 }
+
+void acpi_ut_safe_strncpy(char *dest, char *source, acpi_size dest_size)
+{
+	/* Always terminate destination string */
+
+	strncpy(dest, source, dest_size);
+	dest[dest_size - 1] = 0;
+}
+
 #endif
diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c
index 3175b133c0e4..f6b8dd24b006 100644
--- a/drivers/acpi/acpica/utosi.c
+++ b/drivers/acpi/acpica/utosi.c
@@ -101,6 +101,8 @@ static struct acpi_interface_info acpi_default_supported_interfaces[] = {
 	{"Windows 2012", NULL, 0, ACPI_OSI_WIN_8},	/* Windows 8 and Server 2012 - Added 08/2012 */
 	{"Windows 2013", NULL, 0, ACPI_OSI_WIN_8},	/* Windows 8.1 and Server 2012 R2 - Added 01/2014 */
 	{"Windows 2015", NULL, 0, ACPI_OSI_WIN_10},	/* Windows 10 - Added 03/2015 */
+	{"Windows 2016", NULL, 0, ACPI_OSI_WIN_10_RS1},	/* Windows 10 version 1607 - Added 12/2017 */
+	{"Windows 2017", NULL, 0, ACPI_OSI_WIN_10_RS2},	/* Windows 10 version 1703 - Added 12/2017 */
 
 	/* Feature Group Strings */
 
diff --git a/drivers/acpi/acpica/utstrsuppt.c b/drivers/acpi/acpica/utstrsuppt.c
index 965fb5cec94f..97f48d71f9e6 100644
--- a/drivers/acpi/acpica/utstrsuppt.c
+++ b/drivers/acpi/acpica/utstrsuppt.c
@@ -52,10 +52,9 @@ static acpi_status
 acpi_ut_insert_digit(u64 *accumulated_value, u32 base, int ascii_digit);
 
 static acpi_status
-acpi_ut_strtoul_multiply64(u64 multiplicand, u64 multiplier, u64 *out_product);
+acpi_ut_strtoul_multiply64(u64 multiplicand, u32 base, u64 *out_product);
 
-static acpi_status
-acpi_ut_strtoul_add64(u64 addend1, u64 addend2, u64 *out_sum);
+static acpi_status acpi_ut_strtoul_add64(u64 addend1, u32 digit, u64 *out_sum);
 
 /*******************************************************************************
  *
@@ -357,7 +356,7 @@ acpi_ut_insert_digit(u64 *accumulated_value, u32 base, int ascii_digit)
  * FUNCTION:    acpi_ut_strtoul_multiply64
  *
  * PARAMETERS:  multiplicand            - Current accumulated converted integer
- *              multiplier              - Base/Radix
+ *              base                    - Base/Radix
  *              out_product             - Where the product is returned
  *
  * RETURN:      Status and 64-bit product
@@ -369,33 +368,40 @@ acpi_ut_insert_digit(u64 *accumulated_value, u32 base, int ascii_digit)
  ******************************************************************************/
 
 static acpi_status
-acpi_ut_strtoul_multiply64(u64 multiplicand, u64 multiplier, u64 *out_product)
+acpi_ut_strtoul_multiply64(u64 multiplicand, u32 base, u64 *out_product)
 {
-	u64 val;
+	u64 product;
+	u64 quotient;
 
 	/* Exit if either operand is zero */
 
 	*out_product = 0;
-	if (!multiplicand || !multiplier) {
+	if (!multiplicand || !base) {
 		return (AE_OK);
 	}
 
-	/* Check for 64-bit overflow before the actual multiplication */
-
-	acpi_ut_short_divide(ACPI_UINT64_MAX, (u32)multiplier, &val, NULL);
-	if (multiplicand > val) {
+	/*
+	 * Check for 64-bit overflow before the actual multiplication.
+	 *
+	 * Notes: 64-bit division is often not supported on 32-bit platforms
+	 * (it requires a library function), Therefore ACPICA has a local
+	 * 64-bit divide function. Also, Multiplier is currently only used
+	 * as the radix (8/10/16), to the 64/32 divide will always work.
+	 */
+	acpi_ut_short_divide(ACPI_UINT64_MAX, base, &quotient, NULL);
+	if (multiplicand > quotient) {
 		return (AE_NUMERIC_OVERFLOW);
 	}
 
-	val = multiplicand * multiplier;
+	product = multiplicand * base;
 
 	/* Check for 32-bit overflow if necessary */
 
-	if ((acpi_gbl_integer_bit_width == 32) && (val > ACPI_UINT32_MAX)) {
+	if ((acpi_gbl_integer_bit_width == 32) && (product > ACPI_UINT32_MAX)) {
 		return (AE_NUMERIC_OVERFLOW);
 	}
 
-	*out_product = val;
+	*out_product = product;
 	return (AE_OK);
 }
 
@@ -404,7 +410,7 @@ acpi_ut_strtoul_multiply64(u64 multiplicand, u64 multiplier, u64 *out_product)
  * FUNCTION:    acpi_ut_strtoul_add64
  *
  * PARAMETERS:  addend1                 - Current accumulated converted integer
- *              addend2                 - New hex value/char
+ *              digit                   - New hex value/char
  *              out_sum                 - Where sum is returned (Accumulator)
  *
  * RETURN:      Status and 64-bit sum
@@ -415,17 +421,17 @@ acpi_ut_strtoul_multiply64(u64 multiplicand, u64 multiplier, u64 *out_product)
  *
  ******************************************************************************/
 
-static acpi_status acpi_ut_strtoul_add64(u64 addend1, u64 addend2, u64 *out_sum)
+static acpi_status acpi_ut_strtoul_add64(u64 addend1, u32 digit, u64 *out_sum)
 {
 	u64 sum;
 
 	/* Check for 64-bit overflow before the actual addition */
 
-	if ((addend1 > 0) && (addend2 > (ACPI_UINT64_MAX - addend1))) {
+	if ((addend1 > 0) && (digit > (ACPI_UINT64_MAX - addend1))) {
 		return (AE_NUMERIC_OVERFLOW);
 	}
 
-	sum = addend1 + addend2;
+	sum = addend1 + digit;
 
 	/* Check for 32-bit overflow if necessary */
 
diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c
index 3c8de88ecbd5..633b4e2c669f 100644
--- a/drivers/acpi/acpica/uttrack.c
+++ b/drivers/acpi/acpica/uttrack.c
@@ -402,8 +402,8 @@ acpi_ut_track_allocation(struct acpi_debug_mem_block *allocation,
 	allocation->component = component;
 	allocation->line = line;
 
-	strncpy(allocation->module, module, ACPI_MAX_MODULE_NAME);
-	allocation->module[ACPI_MAX_MODULE_NAME - 1] = 0;
+	acpi_ut_safe_strncpy(allocation->module, (char *)module,
+			     ACPI_MAX_MODULE_NAME);
 
 	if (!element) {
 
@@ -717,7 +717,7 @@ exit:
 	if (!num_outstanding) {
 		ACPI_INFO(("No outstanding allocations"));
 	} else {
-		ACPI_ERROR((AE_INFO, "%u(0x%X) Outstanding allocations",
+		ACPI_ERROR((AE_INFO, "%u (0x%X) Outstanding cache allocations",
 			    num_outstanding, num_outstanding));
 	}
 
diff --git a/drivers/acpi/acpica/utxferror.c b/drivers/acpi/acpica/utxferror.c
index 950a1e500bfa..9da4f8ef2e77 100644
--- a/drivers/acpi/acpica/utxferror.c
+++ b/drivers/acpi/acpica/utxferror.c
@@ -96,8 +96,8 @@ ACPI_EXPORT_SYMBOL(acpi_error)
  *
  * RETURN:      None
  *
- * DESCRIPTION: Print "ACPI Exception" message with module/line/version info
- *              and decoded acpi_status.
+ * DESCRIPTION: Print an "ACPI Error" message with module/line/version
+ *              info as well as decoded acpi_status.
  *
  ******************************************************************************/
 void ACPI_INTERNAL_VAR_XFACE
@@ -111,10 +111,10 @@ acpi_exception(const char *module_name,
 	/* For AE_OK, just print the message */
 
 	if (ACPI_SUCCESS(status)) {
-		acpi_os_printf(ACPI_MSG_EXCEPTION);
+		acpi_os_printf(ACPI_MSG_ERROR);
 
 	} else {
-		acpi_os_printf(ACPI_MSG_EXCEPTION "%s, ",
+		acpi_os_printf(ACPI_MSG_ERROR "%s, ",
 			       acpi_format_exception(status));
 	}
 
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 6742f6c68034..9bff853e85f3 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -1007,7 +1007,7 @@ skip:
 	/* The record may be cleared by others, try read next record */
 	if (len == -ENOENT)
 		goto skip;
-	else if (len < sizeof(*rcd)) {
+	else if (len < 0 || len < sizeof(*rcd)) {
 		rc = -EIO;
 		goto out;
 	}
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 6402f7fad3bb..1efefe919555 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -410,7 +410,52 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int
 		flags = 0;
 
 	if (flags != -1)
-		memory_failure_queue(pfn, 0, flags);
+		memory_failure_queue(pfn, flags);
+#endif
+}
+
+/*
+ * PCIe AER errors need to be sent to the AER driver for reporting and
+ * recovery. The GHES severities map to the following AER severities and
+ * require the following handling:
+ *
+ * GHES_SEV_CORRECTABLE -> AER_CORRECTABLE
+ *     These need to be reported by the AER driver but no recovery is
+ *     necessary.
+ * GHES_SEV_RECOVERABLE -> AER_NONFATAL
+ * GHES_SEV_RECOVERABLE && CPER_SEC_RESET -> AER_FATAL
+ *     These both need to be reported and recovered from by the AER driver.
+ * GHES_SEV_PANIC does not make it to this handling since the kernel must
+ *     panic.
+ */
+static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
+{
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+	struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
+
+	if (pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
+	    pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) {
+		unsigned int devfn;
+		int aer_severity;
+
+		devfn = PCI_DEVFN(pcie_err->device_id.device,
+				  pcie_err->device_id.function);
+		aer_severity = cper_severity_to_aer(gdata->error_severity);
+
+		/*
+		 * If firmware reset the component to contain
+		 * the error, we must reinitialize it before
+		 * use, so treat it as a fatal AER error.
+		 */
+		if (gdata->flags & CPER_SEC_RESET)
+			aer_severity = AER_FATAL;
+
+		aer_recover_queue(pcie_err->device_id.segment,
+				  pcie_err->device_id.bus,
+				  devfn, aer_severity,
+				  (struct aer_capability_regs *)
+				  pcie_err->aer_info);
+	}
 #endif
 }
 
@@ -441,38 +486,9 @@ static void ghes_do_proc(struct ghes *ghes,
 			arch_apei_report_mem_error(sev, mem_err);
 			ghes_handle_memory_failure(gdata, sev);
 		}
-#ifdef CONFIG_ACPI_APEI_PCIEAER
 		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
-			struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
-
-			if (sev == GHES_SEV_RECOVERABLE &&
-			    sec_sev == GHES_SEV_RECOVERABLE &&
-			    pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
-			    pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) {
-				unsigned int devfn;
-				int aer_severity;
-
-				devfn = PCI_DEVFN(pcie_err->device_id.device,
-						  pcie_err->device_id.function);
-				aer_severity = cper_severity_to_aer(gdata->error_severity);
-
-				/*
-				 * If firmware reset the component to contain
-				 * the error, we must reinitialize it before
-				 * use, so treat it as a fatal AER error.
-				 */
-				if (gdata->flags & CPER_SEC_RESET)
-					aer_severity = AER_FATAL;
-
-				aer_recover_queue(pcie_err->device_id.segment,
-						  pcie_err->device_id.bus,
-						  devfn, aer_severity,
-						  (struct aer_capability_regs *)
-						  pcie_err->aer_info);
-			}
-
+			ghes_handle_aer(gdata);
 		}
-#endif
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 			struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
 
@@ -870,7 +886,6 @@ static void ghes_print_queued_estatus(void)
 	struct ghes_estatus_node *estatus_node;
 	struct acpi_hest_generic *generic;
 	struct acpi_hest_generic_status *estatus;
-	u32 len, node_len;
 
 	llnode = llist_del_all(&ghes_estatus_llist);
 	/*
@@ -882,8 +897,6 @@ static void ghes_print_queued_estatus(void)
 		estatus_node = llist_entry(llnode, struct ghes_estatus_node,
 					   llnode);
 		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-		len = cper_estatus_len(estatus);
-		node_len = GHES_ESTATUS_NODE_LEN(len);
 		generic = estatus_node->generic;
 		ghes_print_estatus(NULL, generic, estatus);
 		llnode = llnode->next;
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 13e7b56e33ae..19bc440820e6 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -70,6 +70,7 @@ static async_cookie_t async_cookie;
 static bool battery_driver_registered;
 static int battery_bix_broken_package;
 static int battery_notification_delay_ms;
+static int battery_full_discharging;
 static unsigned int cache_time = 1000;
 module_param(cache_time, uint, 0644);
 MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
@@ -214,9 +215,12 @@ static int acpi_battery_get_property(struct power_supply *psy,
 		return -ENODEV;
 	switch (psp) {
 	case POWER_SUPPLY_PROP_STATUS:
-		if (battery->state & ACPI_BATTERY_STATE_DISCHARGING)
-			val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
-		else if (battery->state & ACPI_BATTERY_STATE_CHARGING)
+		if (battery->state & ACPI_BATTERY_STATE_DISCHARGING) {
+			if (battery_full_discharging && battery->rate_now == 0)
+				val->intval = POWER_SUPPLY_STATUS_FULL;
+			else
+				val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
+		} else if (battery->state & ACPI_BATTERY_STATE_CHARGING)
 			val->intval = POWER_SUPPLY_STATUS_CHARGING;
 		else if (acpi_battery_is_charged(battery))
 			val->intval = POWER_SUPPLY_STATUS_FULL;
@@ -1166,6 +1170,12 @@ battery_notification_delay_quirk(const struct dmi_system_id *d)
 	return 0;
 }
 
+static int __init battery_full_discharging_quirk(const struct dmi_system_id *d)
+{
+	battery_full_discharging = 1;
+	return 0;
+}
+
 static const struct dmi_system_id bat_dmi_table[] __initconst = {
 	{
 		.callback = battery_bix_broken_package_quirk,
@@ -1183,6 +1193,22 @@ static const struct dmi_system_id bat_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire V5-573G"),
 		},
 	},
+	{
+		.callback = battery_full_discharging_quirk,
+		.ident = "ASUS GL502VSK",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GL502VSK"),
+		},
+	},
+	{
+		.callback = battery_full_discharging_quirk,
+		.ident = "ASUS UX305LA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "UX305LA"),
+		},
+	},
 	{},
 };
 
@@ -1237,13 +1263,11 @@ static int acpi_battery_add(struct acpi_device *device)
 
 #ifdef CONFIG_ACPI_PROCFS_POWER
 	result = acpi_battery_add_fs(device);
-#endif
 	if (result) {
-#ifdef CONFIG_ACPI_PROCFS_POWER
 		acpi_battery_remove_fs(device);
-#endif
 		goto fail;
 	}
+#endif
 
 	printk(KERN_INFO PREFIX "%s Slot [%s] (battery %s)\n",
 		ACPI_BATTERY_DEVICE_NAME, acpi_device_bid(device),
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 4d0979e02a28..f87ed3be779a 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -785,6 +785,24 @@ const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
 }
 EXPORT_SYMBOL_GPL(acpi_match_device);
 
+void *acpi_get_match_data(const struct device *dev)
+{
+	const struct acpi_device_id *match;
+
+	if (!dev->driver)
+		return NULL;
+
+	if (!dev->driver->acpi_match_table)
+		return NULL;
+
+	match = acpi_match_device(dev->driver->acpi_match_table, dev);
+	if (!match)
+		return NULL;
+
+	return (void *)match->driver_data;
+}
+EXPORT_SYMBOL_GPL(acpi_get_match_data);
+
 int acpi_match_device_ids(struct acpi_device *device,
 			  const struct acpi_device_id *ids)
 {
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index bf8e4d371fa7..e1eee7a60fad 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -30,6 +30,7 @@
 #include <linux/input.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
+#include <linux/dmi.h>
 #include <acpi/button.h>
 
 #define PREFIX "ACPI: "
@@ -76,6 +77,22 @@ static const struct acpi_device_id button_device_ids[] = {
 };
 MODULE_DEVICE_TABLE(acpi, button_device_ids);
 
+/*
+ * Some devices which don't even have a lid in anyway have a broken _LID
+ * method (e.g. pointing to a floating gpio pin) causing spurious LID events.
+ */
+static const struct dmi_system_id lid_blacklst[] = {
+	{
+		/* GP-electronic T701 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "T701"),
+			DMI_MATCH(DMI_BIOS_VERSION, "BYT70A.YNCHENG.WIN.007"),
+		},
+	},
+	{}
+};
+
 static int acpi_button_add(struct acpi_device *device);
 static int acpi_button_remove(struct acpi_device *device);
 static void acpi_button_notify(struct acpi_device *device, u32 event);
@@ -210,6 +227,8 @@ static int acpi_lid_notify_state(struct acpi_device *device, int state)
 	}
 	/* Send the platform triggered reliable event */
 	if (do_update) {
+		acpi_handle_debug(device->handle, "ACPI LID %s\n",
+				  state ? "open" : "closed");
 		input_report_switch(button->input, SW_LID, !state);
 		input_sync(button->input);
 		button->last_state = !!state;
@@ -473,6 +492,9 @@ static int acpi_button_add(struct acpi_device *device)
 	char *name, *class;
 	int error;
 
+	if (!strcmp(hid, ACPI_BUTTON_HID_LID) && dmi_check_system(lid_blacklst))
+		return -ENODEV;
+
 	button = kzalloc(sizeof(struct acpi_button), GFP_KERNEL);
 	if (!button)
 		return -ENOMEM;
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 21c28433c590..06ea4749ebd9 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -949,7 +949,7 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val)
 	}
 
 	*val = 0;
-	if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM)
+	if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0)
 		vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id);
 	else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
 		vaddr = reg_res->sys_mem_vaddr;
@@ -988,7 +988,7 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
 	struct cpc_reg *reg = &reg_res->cpc_entry.reg;
 
-	if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM)
+	if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0)
 		vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id);
 	else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
 		vaddr = reg_res->sys_mem_vaddr;
@@ -1035,14 +1035,15 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
 		*lowest_non_linear_reg, *nominal_reg;
 	u64 high, low, nom, min_nonlinear;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
-	struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
+	struct cppc_pcc_data *pcc_ss_data;
 	int ret = 0, regs_in_pcc = 0;
 
-	if (!cpc_desc) {
+	if (!cpc_desc || pcc_ss_id < 0) {
 		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
 		return -ENODEV;
 	}
 
+	pcc_ss_data = pcc_data[pcc_ss_id];
 	highest_reg = &cpc_desc->cpc_regs[HIGHEST_PERF];
 	lowest_reg = &cpc_desc->cpc_regs[LOWEST_PERF];
 	lowest_non_linear_reg = &cpc_desc->cpc_regs[LOW_NON_LINEAR_PERF];
@@ -1095,15 +1096,16 @@ int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 	struct cpc_register_resource *delivered_reg, *reference_reg,
 		*ref_perf_reg, *ctr_wrap_reg;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
-	struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
+	struct cppc_pcc_data *pcc_ss_data;
 	u64 delivered, reference, ref_perf, ctr_wrap_time;
 	int ret = 0, regs_in_pcc = 0;
 
-	if (!cpc_desc) {
+	if (!cpc_desc || pcc_ss_id < 0) {
 		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
 		return -ENODEV;
 	}
 
+	pcc_ss_data = pcc_data[pcc_ss_id];
 	delivered_reg = &cpc_desc->cpc_regs[DELIVERED_CTR];
 	reference_reg = &cpc_desc->cpc_regs[REFERENCE_CTR];
 	ref_perf_reg = &cpc_desc->cpc_regs[REFERENCE_PERF];
@@ -1169,14 +1171,15 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
 	struct cpc_register_resource *desired_reg;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
-	struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
+	struct cppc_pcc_data *pcc_ss_data;
 	int ret = 0;
 
-	if (!cpc_desc) {
+	if (!cpc_desc || pcc_ss_id < 0) {
 		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
 		return -ENODEV;
 	}
 
+	pcc_ss_data = pcc_data[pcc_ss_id];
 	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];
 
 	/*
@@ -1301,7 +1304,7 @@ unsigned int cppc_get_transition_latency(int cpu_num)
 	struct cpc_desc *cpc_desc;
 	struct cpc_register_resource *desired_reg;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu_num);
-	struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
+	struct cppc_pcc_data *pcc_ss_data;
 
 	cpc_desc = per_cpu(cpc_desc_ptr, cpu_num);
 	if (!cpc_desc)
@@ -1311,6 +1314,10 @@ unsigned int cppc_get_transition_latency(int cpu_num)
 	if (!CPC_IN_PCC(desired_reg))
 		return CPUFREQ_ETERNAL;
 
+	if (pcc_ss_id < 0)
+		return CPUFREQ_ETERNAL;
+
+	pcc_ss_data = pcc_data[pcc_ss_id];
 	if (pcc_ss_data->pcc_mpar)
 		latency_ns = 60 * (1000 * 1000 * 1000 / pcc_ss_data->pcc_mpar);
 
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index e4ffaeec9ec2..c4d0a1c912f0 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -990,7 +990,7 @@ void acpi_subsys_complete(struct device *dev)
 	 * the sleep state it is going out of and it has never been resumed till
 	 * now, resume it in case the firmware powered it up.
 	 */
-	if (dev->power.direct_complete && pm_resume_via_firmware())
+	if (pm_runtime_suspended(dev) && pm_resume_via_firmware())
 		pm_request_resume(dev);
 }
 EXPORT_SYMBOL_GPL(acpi_subsys_complete);
@@ -1039,10 +1039,28 @@ EXPORT_SYMBOL_GPL(acpi_subsys_suspend_late);
  */
 int acpi_subsys_suspend_noirq(struct device *dev)
 {
-	if (dev_pm_smart_suspend_and_suspended(dev))
+	int ret;
+
+	if (dev_pm_smart_suspend_and_suspended(dev)) {
+		dev->power.may_skip_resume = true;
 		return 0;
+	}
+
+	ret = pm_generic_suspend_noirq(dev);
+	if (ret)
+		return ret;
+
+	/*
+	 * If the target system sleep state is suspend-to-idle, it is sufficient
+	 * to check whether or not the device's wakeup settings are good for
+	 * runtime PM.  Otherwise, the pm_resume_via_firmware() check will cause
+	 * acpi_subsys_complete() to take care of fixing up the device's state
+	 * anyway, if need be.
+	 */
+	dev->power.may_skip_resume = device_may_wakeup(dev) ||
+					!device_can_wakeup(dev);
 
-	return pm_generic_suspend_noirq(dev);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(acpi_subsys_suspend_noirq);
 
@@ -1052,6 +1070,9 @@ EXPORT_SYMBOL_GPL(acpi_subsys_suspend_noirq);
  */
 int acpi_subsys_resume_noirq(struct device *dev)
 {
+	if (dev_pm_may_skip_resume(dev))
+		return 0;
+
 	/*
 	 * Devices with DPM_FLAG_SMART_SUSPEND may be left in runtime suspend
 	 * during system suspend, so update their runtime PM status to "active"
@@ -1138,7 +1159,7 @@ int acpi_subsys_thaw_noirq(struct device *dev)
 	 * skip all of the subsequent "thaw" callbacks for the device.
 	 */
 	if (dev_pm_smart_suspend_and_suspended(dev)) {
-		dev->power.direct_complete = true;
+		dev_pm_skip_next_resume_phases(dev);
 		return 0;
 	}
 
diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c
index 24418932612e..545e91420cde 100644
--- a/drivers/acpi/device_sysfs.c
+++ b/drivers/acpi/device_sysfs.c
@@ -146,6 +146,10 @@ static int create_pnp_modalias(struct acpi_device *acpi_dev, char *modalias,
 	int count;
 	struct acpi_hardware_id *id;
 
+	/* Avoid unnecessarily loading modules for non present devices. */
+	if (!acpi_device_is_present(acpi_dev))
+		return 0;
+
 	/*
 	 * Since we skip ACPI_DT_NAMESPACE_HID from the modalias below, 0 should
 	 * be returned if ACPI_DT_NAMESPACE_HID is the only ACPI/PNP ID in the
@@ -353,7 +357,7 @@ static ssize_t real_power_state_show(struct device *dev,
 	return sprintf(buf, "%s\n", acpi_power_state_string(state));
 }
 
-static DEVICE_ATTR(real_power_state, 0444, real_power_state_show, NULL);
+static DEVICE_ATTR_RO(real_power_state);
 
 static ssize_t power_state_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
@@ -363,7 +367,7 @@ static ssize_t power_state_show(struct device *dev,
 	return sprintf(buf, "%s\n", acpi_power_state_string(adev->power.state));
 }
 
-static DEVICE_ATTR(power_state, 0444, power_state_show, NULL);
+static DEVICE_ATTR_RO(power_state);
 
 static ssize_t
 acpi_eject_store(struct device *d, struct device_attribute *attr,
@@ -458,7 +462,7 @@ static ssize_t description_show(struct device *dev,
 
 	return result;
 }
-static DEVICE_ATTR(description, 0444, description_show, NULL);
+static DEVICE_ATTR_RO(description);
 
 static ssize_t
 acpi_device_sun_show(struct device *dev, struct device_attribute *attr,
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index da176c95aa2c..d9f38c645e4a 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1516,7 +1516,7 @@ static int acpi_ec_setup(struct acpi_ec *ec, bool handle_events)
 	}
 
 	acpi_handle_info(ec->handle,
-			 "GPE=0x%lx, EC_CMD/EC_SC=0x%lx, EC_DATA=0x%lx\n",
+			 "GPE=0x%x, EC_CMD/EC_SC=0x%lx, EC_DATA=0x%lx\n",
 			 ec->gpe, ec->command_addr, ec->data_addr);
 	return ret;
 }
@@ -1597,32 +1597,41 @@ static int acpi_ec_add(struct acpi_device *device)
 {
 	struct acpi_ec *ec = NULL;
 	int ret;
+	bool is_ecdt = false;
+	acpi_status status;
 
 	strcpy(acpi_device_name(device), ACPI_EC_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_EC_CLASS);
 
-	ec = acpi_ec_alloc();
-	if (!ec)
-		return -ENOMEM;
-	if (ec_parse_device(device->handle, 0, ec, NULL) !=
-		AE_CTRL_TERMINATE) {
+	if (!strcmp(acpi_device_hid(device), ACPI_ECDT_HID)) {
+		is_ecdt = true;
+		ec = boot_ec;
+	} else {
+		ec = acpi_ec_alloc();
+		if (!ec)
+			return -ENOMEM;
+		status = ec_parse_device(device->handle, 0, ec, NULL);
+		if (status != AE_CTRL_TERMINATE) {
 			ret = -EINVAL;
 			goto err_alloc;
+		}
 	}
 
 	if (acpi_is_boot_ec(ec)) {
-		boot_ec_is_ecdt = false;
-		/*
-		 * Trust PNP0C09 namespace location rather than ECDT ID.
-		 *
-		 * But trust ECDT GPE rather than _GPE because of ASUS quirks,
-		 * so do not change boot_ec->gpe to ec->gpe.
-		 */
-		boot_ec->handle = ec->handle;
-		acpi_handle_debug(ec->handle, "duplicated.\n");
-		acpi_ec_free(ec);
-		ec = boot_ec;
-		ret = acpi_config_boot_ec(ec, ec->handle, true, false);
+		boot_ec_is_ecdt = is_ecdt;
+		if (!is_ecdt) {
+			/*
+			 * Trust PNP0C09 namespace location rather than
+			 * ECDT ID. But trust ECDT GPE rather than _GPE
+			 * because of ASUS quirks, so do not change
+			 * boot_ec->gpe to ec->gpe.
+			 */
+			boot_ec->handle = ec->handle;
+			acpi_handle_debug(ec->handle, "duplicated.\n");
+			acpi_ec_free(ec);
+			ec = boot_ec;
+		}
+		ret = acpi_config_boot_ec(ec, ec->handle, true, is_ecdt);
 	} else
 		ret = acpi_ec_setup(ec, true);
 	if (ret)
@@ -1635,8 +1644,10 @@ static int acpi_ec_add(struct acpi_device *device)
 	ret = !!request_region(ec->command_addr, 1, "EC cmd");
 	WARN(!ret, "Could not request EC cmd io port 0x%lx", ec->command_addr);
 
-	/* Reprobe devices depending on the EC */
-	acpi_walk_dep_device_list(ec->handle);
+	if (!is_ecdt) {
+		/* Reprobe devices depending on the EC */
+		acpi_walk_dep_device_list(ec->handle);
+	}
 	acpi_handle_debug(ec->handle, "enumerated.\n");
 	return 0;
 
@@ -1692,6 +1703,7 @@ ec_parse_io_ports(struct acpi_resource *resource, void *context)
 
 static const struct acpi_device_id ec_device_ids[] = {
 	{"PNP0C09", 0},
+	{ACPI_ECDT_HID, 0},
 	{"", 0},
 };
 
@@ -1764,11 +1776,14 @@ static int __init acpi_ec_ecdt_start(void)
 	 * Note: ec->handle can be valid if this function is called after
 	 * acpi_ec_add(), hence the fast path.
 	 */
-	if (boot_ec->handle != ACPI_ROOT_OBJECT)
-		handle = boot_ec->handle;
-	else if (!acpi_ec_ecdt_get_handle(&handle))
-		return -ENODEV;
-	return acpi_config_boot_ec(boot_ec, handle, true, true);
+	if (boot_ec->handle == ACPI_ROOT_OBJECT) {
+		if (!acpi_ec_ecdt_get_handle(&handle))
+			return -ENODEV;
+		boot_ec->handle = handle;
+	}
+
+	/* Register to ACPI bus with PM ops attached */
+	return acpi_bus_register_early_device(ACPI_BUS_TYPE_ECDT_EC);
 }
 
 #if 0
@@ -2022,6 +2037,12 @@ int __init acpi_ec_init(void)
 
 	/* Drivers must be started after acpi_ec_query_init() */
 	dsdt_fail = acpi_bus_register_driver(&acpi_ec_driver);
+	/*
+	 * Register ECDT to ACPI bus only when PNP0C09 probe fails. This is
+	 * useful for platforms (confirmed on ASUS X550ZE) with valid ECDT
+	 * settings but invalid DSDT settings.
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=196847
+	 */
 	ecdt_fail = acpi_ec_ecdt_start();
 	return ecdt_fail && dsdt_fail ? -ENODEV : 0;
 }
diff --git a/drivers/acpi/ec_sys.c b/drivers/acpi/ec_sys.c
index 6c7dd7af789e..dd70d6c2bca0 100644
--- a/drivers/acpi/ec_sys.c
+++ b/drivers/acpi/ec_sys.c
@@ -128,7 +128,7 @@ static int acpi_ec_add_debugfs(struct acpi_ec *ec, unsigned int ec_device_count)
 		return -ENOMEM;
 	}
 
-	if (!debugfs_create_x32("gpe", 0444, dev_dir, (u32 *)&first_ec->gpe))
+	if (!debugfs_create_x32("gpe", 0444, dev_dir, &first_ec->gpe))
 		goto error;
 	if (!debugfs_create_bool("use_global_lock", 0444, dev_dir,
 				 &first_ec->global_lock))
diff --git a/drivers/acpi/evged.c b/drivers/acpi/evged.c
index 46f060356a22..f13ba2c07667 100644
--- a/drivers/acpi/evged.c
+++ b/drivers/acpi/evged.c
@@ -49,6 +49,11 @@
 
 #define MODULE_NAME	"acpi-ged"
 
+struct acpi_ged_device {
+	struct device *dev;
+	struct list_head event_list;
+};
+
 struct acpi_ged_event {
 	struct list_head node;
 	struct device *dev;
@@ -76,7 +81,8 @@ static acpi_status acpi_ged_request_interrupt(struct acpi_resource *ares,
 	unsigned int irq;
 	unsigned int gsi;
 	unsigned int irqflags = IRQF_ONESHOT;
-	struct device *dev = context;
+	struct acpi_ged_device *geddev = context;
+	struct device *dev = geddev->dev;
 	acpi_handle handle = ACPI_HANDLE(dev);
 	acpi_handle evt_handle;
 	struct resource r;
@@ -102,8 +108,6 @@ static acpi_status acpi_ged_request_interrupt(struct acpi_resource *ares,
 		return AE_ERROR;
 	}
 
-	dev_info(dev, "GED listening GSI %u @ IRQ %u\n", gsi, irq);
-
 	event = devm_kzalloc(dev, sizeof(*event), GFP_KERNEL);
 	if (!event)
 		return AE_ERROR;
@@ -116,29 +120,58 @@ static acpi_status acpi_ged_request_interrupt(struct acpi_resource *ares,
 	if (r.flags & IORESOURCE_IRQ_SHAREABLE)
 		irqflags |= IRQF_SHARED;
 
-	if (devm_request_threaded_irq(dev, irq, NULL, acpi_ged_irq_handler,
-				      irqflags, "ACPI:Ged", event)) {
+	if (request_threaded_irq(irq, NULL, acpi_ged_irq_handler,
+				 irqflags, "ACPI:Ged", event)) {
 		dev_err(dev, "failed to setup event handler for irq %u\n", irq);
 		return AE_ERROR;
 	}
 
+	dev_dbg(dev, "GED listening GSI %u @ IRQ %u\n", gsi, irq);
+	list_add_tail(&event->node, &geddev->event_list);
 	return AE_OK;
 }
 
 static int ged_probe(struct platform_device *pdev)
 {
+	struct acpi_ged_device *geddev;
 	acpi_status acpi_ret;
 
+	geddev = devm_kzalloc(&pdev->dev, sizeof(*geddev), GFP_KERNEL);
+	if (!geddev)
+		return -ENOMEM;
+
+	geddev->dev = &pdev->dev;
+	INIT_LIST_HEAD(&geddev->event_list);
 	acpi_ret = acpi_walk_resources(ACPI_HANDLE(&pdev->dev), "_CRS",
-				       acpi_ged_request_interrupt, &pdev->dev);
+				       acpi_ged_request_interrupt, geddev);
 	if (ACPI_FAILURE(acpi_ret)) {
 		dev_err(&pdev->dev, "unable to parse the _CRS record\n");
 		return -EINVAL;
 	}
+	platform_set_drvdata(pdev, geddev);
 
 	return 0;
 }
 
+static void ged_shutdown(struct platform_device *pdev)
+{
+	struct acpi_ged_device *geddev = platform_get_drvdata(pdev);
+	struct acpi_ged_event *event, *next;
+
+	list_for_each_entry_safe(event, next, &geddev->event_list, node) {
+		free_irq(event->irq, event);
+		list_del(&event->node);
+		dev_dbg(geddev->dev, "GED releasing GSI %u @ IRQ %u\n",
+			 event->gsi, event->irq);
+	}
+}
+
+static int ged_remove(struct platform_device *pdev)
+{
+	ged_shutdown(pdev);
+	return 0;
+}
+
 static const struct acpi_device_id ged_acpi_ids[] = {
 	{"ACPI0013"},
 	{},
@@ -146,6 +179,8 @@ static const struct acpi_device_id ged_acpi_ids[] = {
 
 static struct platform_driver ged_driver = {
 	.probe = ged_probe,
+	.remove = ged_remove,
+	.shutdown = ged_shutdown,
 	.driver = {
 		.name = MODULE_NAME,
 		.acpi_match_table = ACPI_PTR(ged_acpi_ids),
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index fc8c43e76707..1d0a501bc7f0 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -115,6 +115,7 @@ bool acpi_device_is_present(const struct acpi_device *adev);
 bool acpi_device_is_battery(struct acpi_device *adev);
 bool acpi_device_is_first_physical_node(struct acpi_device *adev,
 					const struct device *dev);
+int acpi_bus_register_early_device(int type);
 
 /* --------------------------------------------------------------------------
                      Device Matching and Notification
@@ -158,7 +159,7 @@ static inline void acpi_early_processor_osc(void) {}
    -------------------------------------------------------------------------- */
 struct acpi_ec {
 	acpi_handle handle;
-	unsigned long gpe;
+	u32 gpe;
 	unsigned long command_addr;
 	unsigned long data_addr;
 	bool global_lock;
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index ff2580e7611d..abeb4df4f22e 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1670,6 +1670,11 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 				dev_name(&adev_dimm->dev));
 		return -ENXIO;
 	}
+	/*
+	 * Record nfit_mem for the notification path to track back to
+	 * the nfit sysfs attributes for this dimm device object.
+	 */
+	dev_set_drvdata(&adev_dimm->dev, nfit_mem);
 
 	/*
 	 * Until standardization materializes we need to consider 4
@@ -1752,9 +1757,11 @@ static void shutdown_dimm_notify(void *data)
 			sysfs_put(nfit_mem->flags_attr);
 			nfit_mem->flags_attr = NULL;
 		}
-		if (adev_dimm)
+		if (adev_dimm) {
 			acpi_remove_notify_handler(adev_dimm->handle,
 					ACPI_DEVICE_NOTIFY, acpi_nvdimm_notify);
+			dev_set_drvdata(&adev_dimm->dev, NULL);
+		}
 	}
 	mutex_unlock(&acpi_desc->init_mutex);
 }
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 917f1cc0fda4..8ccaae3550d2 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -460,8 +460,7 @@ int __init acpi_numa_init(void)
 					srat_proc, ARRAY_SIZE(srat_proc), 0);
 
 		cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
-					    acpi_parse_memory_affinity,
-					    NR_NODE_MEMBLKS);
+					    acpi_parse_memory_affinity, 0);
 	}
 
 	/* SLIT: System Locality Information Table */
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index bc3d914dfc3e..85ad679390e3 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -612,7 +612,7 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link)
 			acpi_isa_irq_penalty[link->irq.active] +=
 				PIRQ_PENALTY_PCI_USING;
 
-		printk(KERN_WARNING PREFIX "%s [%s] enabled at IRQ %d\n",
+		pr_info("%s [%s] enabled at IRQ %d\n",
 		       acpi_device_name(link->device),
 		       acpi_device_bid(link->device), link->irq.active);
 	}
diff --git a/drivers/acpi/pmic/intel_pmic_bxtwc.c b/drivers/acpi/pmic/intel_pmic_bxtwc.c
index 90011aad4d20..886ac8b93cd0 100644
--- a/drivers/acpi/pmic/intel_pmic_bxtwc.c
+++ b/drivers/acpi/pmic/intel_pmic_bxtwc.c
@@ -400,7 +400,7 @@ static int intel_bxtwc_pmic_opregion_probe(struct platform_device *pdev)
 			&intel_bxtwc_pmic_opregion_data);
 }
 
-static struct platform_device_id bxt_wc_opregion_id_table[] = {
+static const struct platform_device_id bxt_wc_opregion_id_table[] = {
 	{ .name = "bxt_wcove_region" },
 	{},
 };
@@ -412,9 +412,4 @@ static struct platform_driver intel_bxtwc_pmic_opregion_driver = {
 	},
 	.id_table = bxt_wc_opregion_id_table,
 };
-
-static int __init intel_bxtwc_pmic_opregion_driver_init(void)
-{
-	return platform_driver_register(&intel_bxtwc_pmic_opregion_driver);
-}
-device_initcall(intel_bxtwc_pmic_opregion_driver_init);
+builtin_platform_driver(intel_bxtwc_pmic_opregion_driver);
diff --git a/drivers/acpi/pmic/intel_pmic_chtdc_ti.c b/drivers/acpi/pmic/intel_pmic_chtdc_ti.c
index 109c1e9c9c7a..f6d73a243d80 100644
--- a/drivers/acpi/pmic/intel_pmic_chtdc_ti.c
+++ b/drivers/acpi/pmic/intel_pmic_chtdc_ti.c
@@ -131,7 +131,4 @@ static struct platform_driver chtdc_ti_pmic_opregion_driver = {
 	},
 	.id_table = chtdc_ti_pmic_opregion_id_table,
 };
-module_platform_driver(chtdc_ti_pmic_opregion_driver);
-
-MODULE_DESCRIPTION("Dollar Cove TI PMIC opregion driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(chtdc_ti_pmic_opregion_driver);
diff --git a/drivers/acpi/pmic/intel_pmic_chtwc.c b/drivers/acpi/pmic/intel_pmic_chtwc.c
index 85636d7a9d39..9912422c8185 100644
--- a/drivers/acpi/pmic/intel_pmic_chtwc.c
+++ b/drivers/acpi/pmic/intel_pmic_chtwc.c
@@ -260,11 +260,10 @@ static int intel_cht_wc_pmic_opregion_probe(struct platform_device *pdev)
 			&intel_cht_wc_pmic_opregion_data);
 }
 
-static struct platform_device_id cht_wc_opregion_id_table[] = {
+static const struct platform_device_id cht_wc_opregion_id_table[] = {
 	{ .name = "cht_wcove_region" },
 	{},
 };
-MODULE_DEVICE_TABLE(platform, cht_wc_opregion_id_table);
 
 static struct platform_driver intel_cht_wc_pmic_opregion_driver = {
 	.probe = intel_cht_wc_pmic_opregion_probe,
@@ -273,8 +272,4 @@ static struct platform_driver intel_cht_wc_pmic_opregion_driver = {
 	},
 	.id_table = cht_wc_opregion_id_table,
 };
-module_platform_driver(intel_cht_wc_pmic_opregion_driver);
-
-MODULE_DESCRIPTION("Intel CHT Whiskey Cove PMIC operation region driver");
-MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(intel_cht_wc_pmic_opregion_driver);
diff --git a/drivers/acpi/pmic/intel_pmic_crc.c b/drivers/acpi/pmic/intel_pmic_crc.c
index d7f1761ab1bc..7ffa74048107 100644
--- a/drivers/acpi/pmic/intel_pmic_crc.c
+++ b/drivers/acpi/pmic/intel_pmic_crc.c
@@ -201,9 +201,4 @@ static struct platform_driver intel_crc_pmic_opregion_driver = {
 		.name = "crystal_cove_pmic",
 	},
 };
-
-static int __init intel_crc_pmic_opregion_driver_init(void)
-{
-	return platform_driver_register(&intel_crc_pmic_opregion_driver);
-}
-device_initcall(intel_crc_pmic_opregion_driver_init);
+builtin_platform_driver(intel_crc_pmic_opregion_driver);
diff --git a/drivers/acpi/pmic/intel_pmic_xpower.c b/drivers/acpi/pmic/intel_pmic_xpower.c
index 6c99d3f81095..316e55174aa9 100644
--- a/drivers/acpi/pmic/intel_pmic_xpower.c
+++ b/drivers/acpi/pmic/intel_pmic_xpower.c
@@ -278,9 +278,4 @@ static struct platform_driver intel_xpower_pmic_opregion_driver = {
 		.name = "axp288_pmic_acpi",
 	},
 };
-
-static int __init intel_xpower_pmic_opregion_driver_init(void)
-{
-	return platform_driver_register(&intel_xpower_pmic_opregion_driver);
-}
-device_initcall(intel_xpower_pmic_opregion_driver_init);
+builtin_platform_driver(intel_xpower_pmic_opregion_driver);
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index d50a7b6ccddd..5f0071c7e2e1 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -207,6 +207,7 @@ static void tsc_check_state(int state)
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_AMD:
 	case X86_VENDOR_INTEL:
+	case X86_VENDOR_CENTAUR:
 		/*
 		 * AMD Fam10h TSC will tick in all
 		 * C/P/S0/S1 states when this bit is set.
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index e26ea209b63e..466d1503aba0 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1271,9 +1271,17 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 	return 0;
 }
 
+static void *
+acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
+				  const struct device *dev)
+{
+	return acpi_get_match_data(dev);
+}
+
 #define DECLARE_ACPI_FWNODE_OPS(ops) \
 	const struct fwnode_operations ops = {				\
 		.device_is_available = acpi_fwnode_device_is_available, \
+		.device_get_match_data = acpi_fwnode_device_get_match_data, \
 		.property_present = acpi_fwnode_property_present,	\
 		.property_read_int_array =				\
 			acpi_fwnode_property_read_int_array,		\
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index e14e964bfe6d..b0fe5272c76a 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1024,6 +1024,9 @@ static void acpi_device_get_busid(struct acpi_device *device)
 	case ACPI_BUS_TYPE_SLEEP_BUTTON:
 		strcpy(device->pnp.bus_id, "SLPF");
 		break;
+	case ACPI_BUS_TYPE_ECDT_EC:
+		strcpy(device->pnp.bus_id, "ECDT");
+		break;
 	default:
 		acpi_get_name(device->handle, ACPI_SINGLE_NAME, &buffer);
 		/* Clean up trailing underscores (if any) */
@@ -1304,6 +1307,9 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp,
 	case ACPI_BUS_TYPE_SLEEP_BUTTON:
 		acpi_add_id(pnp, ACPI_BUTTON_HID_SLEEPF);
 		break;
+	case ACPI_BUS_TYPE_ECDT_EC:
+		acpi_add_id(pnp, ACPI_ECDT_HID);
+		break;
 	}
 }
 
@@ -2046,6 +2052,21 @@ void acpi_bus_trim(struct acpi_device *adev)
 }
 EXPORT_SYMBOL_GPL(acpi_bus_trim);
 
+int acpi_bus_register_early_device(int type)
+{
+	struct acpi_device *device = NULL;
+	int result;
+
+	result = acpi_add_single_object(&device, NULL,
+					type, ACPI_STA_DEFAULT);
+	if (result)
+		return result;
+
+	device->flags.match_driver = true;
+	return device_attach(&device->dev);
+}
+EXPORT_SYMBOL_GPL(acpi_bus_register_early_device);
+
 static int acpi_bus_scan_fixed(void)
 {
 	int result = 0;
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 8082871b409a..46cde0912762 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -367,10 +367,20 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 	{},
 };
 
+static bool ignore_blacklist;
+
+void __init acpi_sleep_no_blacklist(void)
+{
+	ignore_blacklist = true;
+}
+
 static void __init acpi_sleep_dmi_check(void)
 {
 	int year;
 
+	if (ignore_blacklist)
+		return;
+
 	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year >= 2012)
 		acpi_nvs_nosave_s3();
 
@@ -697,7 +707,8 @@ static const struct acpi_device_id lps0_device_ids[] = {
 #define ACPI_LPS0_ENTRY		5
 #define ACPI_LPS0_EXIT		6
 
-#define ACPI_S2IDLE_FUNC_MASK	((1 << ACPI_LPS0_ENTRY) | (1 << ACPI_LPS0_EXIT))
+#define ACPI_LPS0_SCREEN_MASK	((1 << ACPI_LPS0_SCREEN_OFF) | (1 << ACPI_LPS0_SCREEN_ON))
+#define ACPI_LPS0_PLATFORM_MASK	((1 << ACPI_LPS0_ENTRY) | (1 << ACPI_LPS0_EXIT))
 
 static acpi_handle lps0_device_handle;
 static guid_t lps0_dsm_guid;
@@ -900,7 +911,8 @@ static int lps0_device_attach(struct acpi_device *adev,
 	if (out_obj && out_obj->type == ACPI_TYPE_BUFFER) {
 		char bitmask = *(char *)out_obj->buffer.pointer;
 
-		if ((bitmask & ACPI_S2IDLE_FUNC_MASK) == ACPI_S2IDLE_FUNC_MASK) {
+		if ((bitmask & ACPI_LPS0_PLATFORM_MASK) == ACPI_LPS0_PLATFORM_MASK ||
+		    (bitmask & ACPI_LPS0_SCREEN_MASK) == ACPI_LPS0_SCREEN_MASK) {
 			lps0_dsm_func_mask = bitmask;
 			lps0_device_handle = adev->handle;
 			/*
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 06a150bb35bf..4fc59c3bc673 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -816,14 +816,8 @@ end:
  * interface:
  *   echo unmask > /sys/firmware/acpi/interrupts/gpe00
  */
-
-/*
- * Currently, the GPE flooding prevention only supports to mask the GPEs
- * numbered from 00 to 7f.
- */
-#define ACPI_MASKABLE_GPE_MAX	0x80
-
-static u64 __initdata acpi_masked_gpes;
+#define ACPI_MASKABLE_GPE_MAX	0xFF
+static DECLARE_BITMAP(acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX) __initdata;
 
 static int __init acpi_gpe_set_masked_gpes(char *val)
 {
@@ -831,7 +825,7 @@ static int __init acpi_gpe_set_masked_gpes(char *val)
 
 	if (kstrtou8(val, 0, &gpe) || gpe > ACPI_MASKABLE_GPE_MAX)
 		return -EINVAL;
-	acpi_masked_gpes |= ((u64)1<<gpe);
+	set_bit(gpe, acpi_masked_gpes_map);
 
 	return 1;
 }
@@ -843,15 +837,11 @@ void __init acpi_gpe_apply_masked_gpes(void)
 	acpi_status status;
 	u8 gpe;
 
-	for (gpe = 0;
-	     gpe < min_t(u8, ACPI_MASKABLE_GPE_MAX, acpi_current_gpe_count);
-	     gpe++) {
-		if (acpi_masked_gpes & ((u64)1<<gpe)) {
-			status = acpi_get_gpe_device(gpe, &handle);
-			if (ACPI_SUCCESS(status)) {
-				pr_info("Masking GPE 0x%x.\n", gpe);
-				(void)acpi_mask_gpe(handle, gpe, TRUE);
-			}
+	for_each_set_bit(gpe, acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX) {
+		status = acpi_get_gpe_device(gpe, &handle);
+		if (ACPI_SUCCESS(status)) {
+			pr_info("Masking GPE 0x%x.\n", gpe);
+			(void)acpi_mask_gpe(handle, gpe, TRUE);
 		}
 	}
 }
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 9d49a1acebe3..78db97687f26 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -737,16 +737,17 @@ bool acpi_dev_found(const char *hid)
 }
 EXPORT_SYMBOL(acpi_dev_found);
 
-struct acpi_dev_present_info {
+struct acpi_dev_match_info {
+	const char *dev_name;
 	struct acpi_device_id hid[2];
 	const char *uid;
 	s64 hrv;
 };
 
-static int acpi_dev_present_cb(struct device *dev, void *data)
+static int acpi_dev_match_cb(struct device *dev, void *data)
 {
 	struct acpi_device *adev = to_acpi_device(dev);
-	struct acpi_dev_present_info *match = data;
+	struct acpi_dev_match_info *match = data;
 	unsigned long long hrv;
 	acpi_status status;
 
@@ -757,6 +758,8 @@ static int acpi_dev_present_cb(struct device *dev, void *data)
 	    strcmp(adev->pnp.unique_id, match->uid)))
 		return 0;
 
+	match->dev_name = acpi_dev_name(adev);
+
 	if (match->hrv == -1)
 		return 1;
 
@@ -789,20 +792,44 @@ static int acpi_dev_present_cb(struct device *dev, void *data)
  */
 bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
 {
-	struct acpi_dev_present_info match = {};
+	struct acpi_dev_match_info match = {};
 	struct device *dev;
 
 	strlcpy(match.hid[0].id, hid, sizeof(match.hid[0].id));
 	match.uid = uid;
 	match.hrv = hrv;
 
-	dev = bus_find_device(&acpi_bus_type, NULL, &match,
-			      acpi_dev_present_cb);
-
+	dev = bus_find_device(&acpi_bus_type, NULL, &match, acpi_dev_match_cb);
 	return !!dev;
 }
 EXPORT_SYMBOL(acpi_dev_present);
 
+/**
+ * acpi_dev_get_first_match_name - Return name of first match of ACPI device
+ * @hid: Hardware ID of the device.
+ * @uid: Unique ID of the device, pass NULL to not check _UID
+ * @hrv: Hardware Revision of the device, pass -1 to not check _HRV
+ *
+ * Return device name if a matching device was present
+ * at the moment of invocation, or NULL otherwise.
+ *
+ * See additional information in acpi_dev_present() as well.
+ */
+const char *
+acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv)
+{
+	struct acpi_dev_match_info match = {};
+	struct device *dev;
+
+	strlcpy(match.hid[0].id, hid, sizeof(match.hid[0].id));
+	match.uid = uid;
+	match.hrv = hrv;
+
+	dev = bus_find_device(&acpi_bus_type, NULL, &match, acpi_dev_match_cb);
+	return dev ? match.dev_name : NULL;
+}
+EXPORT_SYMBOL(acpi_dev_get_first_match_name);
+
 /*
  * acpi_backlight= handling, this is done here rather then in video_detect.c
  * because __setup cannot be used in modules.
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index a73596a4f804..d21040c5d343 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -141,7 +141,7 @@ enum {
 };
 static uint32_t binder_debug_mask = BINDER_DEBUG_USER_ERROR |
 	BINDER_DEBUG_FAILED_TRANSACTION | BINDER_DEBUG_DEAD_TRANSACTION;
-module_param_named(debug_mask, binder_debug_mask, uint, S_IWUSR | S_IRUGO);
+module_param_named(debug_mask, binder_debug_mask, uint, 0644);
 
 static char *binder_devices_param = CONFIG_ANDROID_BINDER_DEVICES;
 module_param_named(devices, binder_devices_param, charp, 0444);
@@ -160,7 +160,7 @@ static int binder_set_stop_on_user_error(const char *val,
 	return ret;
 }
 module_param_call(stop_on_user_error, binder_set_stop_on_user_error,
-	param_get_int, &binder_stop_on_user_error, S_IWUSR | S_IRUGO);
+	param_get_int, &binder_stop_on_user_error, 0644);
 
 #define binder_debug(mask, x...) \
 	do { \
@@ -249,7 +249,7 @@ static struct binder_transaction_log_entry *binder_transaction_log_add(
 	unsigned int cur = atomic_inc_return(&log->cur);
 
 	if (cur >= ARRAY_SIZE(log->entry))
-		log->full = 1;
+		log->full = true;
 	e = &log->entry[cur % ARRAY_SIZE(log->entry)];
 	WRITE_ONCE(e->debug_id_done, 0);
 	/*
@@ -482,7 +482,8 @@ enum binder_deferred_state {
  * @tsk                   task_struct for group_leader of process
  *                        (invariant after initialized)
  * @files                 files_struct for process
- *                        (invariant after initialized)
+ *                        (protected by @files_lock)
+ * @files_lock            mutex to protect @files
  * @deferred_work_node:   element for binder_deferred_list
  *                        (protected by binder_deferred_lock)
  * @deferred_work:        bitmap of deferred work to perform
@@ -492,8 +493,6 @@ enum binder_deferred_state {
  *                        (protected by @inner_lock)
  * @todo:                 list of work for this process
  *                        (protected by @inner_lock)
- * @wait:                 wait queue head to wait for proc work
- *                        (invariant after initialized)
  * @stats:                per-process binder statistics
  *                        (atomics, no lock needed)
  * @delivered_death:      list of delivered death notification
@@ -530,12 +529,12 @@ struct binder_proc {
 	int pid;
 	struct task_struct *tsk;
 	struct files_struct *files;
+	struct mutex files_lock;
 	struct hlist_node deferred_work_node;
 	int deferred_work;
 	bool is_dead;
 
 	struct list_head todo;
-	wait_queue_head_t wait;
 	struct binder_stats stats;
 	struct list_head delivered_death;
 	int max_threads;
@@ -577,6 +576,8 @@ enum {
  *                        (protected by @proc->inner_lock)
  * @todo:                 list of work to do for this thread
  *                        (protected by @proc->inner_lock)
+ * @process_todo:         whether work in @todo should be processed
+ *                        (protected by @proc->inner_lock)
  * @return_error:         transaction errors reported by this thread
  *                        (only accessed by this thread)
  * @reply_error:          transaction errors reported by target thread
@@ -602,6 +603,7 @@ struct binder_thread {
 	bool looper_need_return; /* can be written by other thread */
 	struct binder_transaction *transaction_stack;
 	struct list_head todo;
+	bool process_todo;
 	struct binder_error return_error;
 	struct binder_error reply_error;
 	wait_queue_head_t wait;
@@ -787,6 +789,16 @@ static bool binder_worklist_empty(struct binder_proc *proc,
 	return ret;
 }
 
+/**
+ * binder_enqueue_work_ilocked() - Add an item to the work list
+ * @work:         struct binder_work to add to list
+ * @target_list:  list to add work to
+ *
+ * Adds the work to the specified list. Asserts that work
+ * is not already on a list.
+ *
+ * Requires the proc->inner_lock to be held.
+ */
 static void
 binder_enqueue_work_ilocked(struct binder_work *work,
 			   struct list_head *target_list)
@@ -797,22 +809,56 @@ binder_enqueue_work_ilocked(struct binder_work *work,
 }
 
 /**
- * binder_enqueue_work() - Add an item to the work list
- * @proc:         binder_proc associated with list
+ * binder_enqueue_deferred_thread_work_ilocked() - Add deferred thread work
+ * @thread:       thread to queue work to
  * @work:         struct binder_work to add to list
- * @target_list:  list to add work to
  *
- * Adds the work to the specified list. Asserts that work
- * is not already on a list.
+ * Adds the work to the todo list of the thread. Doesn't set the process_todo
+ * flag, which means that (if it wasn't already set) the thread will go to
+ * sleep without handling this work when it calls read.
+ *
+ * Requires the proc->inner_lock to be held.
  */
 static void
-binder_enqueue_work(struct binder_proc *proc,
-		    struct binder_work *work,
-		    struct list_head *target_list)
+binder_enqueue_deferred_thread_work_ilocked(struct binder_thread *thread,
+					    struct binder_work *work)
 {
-	binder_inner_proc_lock(proc);
-	binder_enqueue_work_ilocked(work, target_list);
-	binder_inner_proc_unlock(proc);
+	binder_enqueue_work_ilocked(work, &thread->todo);
+}
+
+/**
+ * binder_enqueue_thread_work_ilocked() - Add an item to the thread work list
+ * @thread:       thread to queue work to
+ * @work:         struct binder_work to add to list
+ *
+ * Adds the work to the todo list of the thread, and enables processing
+ * of the todo queue.
+ *
+ * Requires the proc->inner_lock to be held.
+ */
+static void
+binder_enqueue_thread_work_ilocked(struct binder_thread *thread,
+				   struct binder_work *work)
+{
+	binder_enqueue_work_ilocked(work, &thread->todo);
+	thread->process_todo = true;
+}
+
+/**
+ * binder_enqueue_thread_work() - Add an item to the thread work list
+ * @thread:       thread to queue work to
+ * @work:         struct binder_work to add to list
+ *
+ * Adds the work to the todo list of the thread, and enables processing
+ * of the todo queue.
+ */
+static void
+binder_enqueue_thread_work(struct binder_thread *thread,
+			   struct binder_work *work)
+{
+	binder_inner_proc_lock(thread->proc);
+	binder_enqueue_thread_work_ilocked(thread, work);
+	binder_inner_proc_unlock(thread->proc);
 }
 
 static void
@@ -877,20 +923,26 @@ static void binder_inc_node_tmpref_ilocked(struct binder_node *node);
 
 static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
 {
-	struct files_struct *files = proc->files;
 	unsigned long rlim_cur;
 	unsigned long irqs;
+	int ret;
 
-	if (files == NULL)
-		return -ESRCH;
-
-	if (!lock_task_sighand(proc->tsk, &irqs))
-		return -EMFILE;
-
+	mutex_lock(&proc->files_lock);
+	if (proc->files == NULL) {
+		ret = -ESRCH;
+		goto err;
+	}
+	if (!lock_task_sighand(proc->tsk, &irqs)) {
+		ret = -EMFILE;
+		goto err;
+	}
 	rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE);
 	unlock_task_sighand(proc->tsk, &irqs);
 
-	return __alloc_fd(files, 0, rlim_cur, flags);
+	ret = __alloc_fd(proc->files, 0, rlim_cur, flags);
+err:
+	mutex_unlock(&proc->files_lock);
+	return ret;
 }
 
 /*
@@ -899,8 +951,10 @@ static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
 static void task_fd_install(
 	struct binder_proc *proc, unsigned int fd, struct file *file)
 {
+	mutex_lock(&proc->files_lock);
 	if (proc->files)
 		__fd_install(proc->files, fd, file);
+	mutex_unlock(&proc->files_lock);
 }
 
 /*
@@ -910,9 +964,11 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd)
 {
 	int retval;
 
-	if (proc->files == NULL)
-		return -ESRCH;
-
+	mutex_lock(&proc->files_lock);
+	if (proc->files == NULL) {
+		retval = -ESRCH;
+		goto err;
+	}
 	retval = __close_fd(proc->files, fd);
 	/* can't restart close syscall because file table entry was cleared */
 	if (unlikely(retval == -ERESTARTSYS ||
@@ -920,14 +976,15 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd)
 		     retval == -ERESTARTNOHAND ||
 		     retval == -ERESTART_RESTARTBLOCK))
 		retval = -EINTR;
-
+err:
+	mutex_unlock(&proc->files_lock);
 	return retval;
 }
 
 static bool binder_has_work_ilocked(struct binder_thread *thread,
 				    bool do_proc_work)
 {
-	return !binder_worklist_empty_ilocked(&thread->todo) ||
+	return thread->process_todo ||
 		thread->looper_need_return ||
 		(do_proc_work &&
 		 !binder_worklist_empty_ilocked(&thread->proc->todo));
@@ -1215,6 +1272,17 @@ static int binder_inc_node_nilocked(struct binder_node *node, int strong,
 			node->local_strong_refs++;
 		if (!node->has_strong_ref && target_list) {
 			binder_dequeue_work_ilocked(&node->work);
+			/*
+			 * Note: this function is the only place where we queue
+			 * directly to a thread->todo without using the
+			 * corresponding binder_enqueue_thread_work() helper
+			 * functions; in this case it's ok to not set the
+			 * process_todo flag, since we know this node work will
+			 * always be followed by other work that starts queue
+			 * processing: in case of synchronous transactions, a
+			 * BR_REPLY or BR_ERROR; in case of oneway
+			 * transactions, a BR_TRANSACTION_COMPLETE.
+			 */
 			binder_enqueue_work_ilocked(&node->work, target_list);
 		}
 	} else {
@@ -1226,6 +1294,9 @@ static int binder_inc_node_nilocked(struct binder_node *node, int strong,
 					node->debug_id);
 				return -EINVAL;
 			}
+			/*
+			 * See comment above
+			 */
 			binder_enqueue_work_ilocked(&node->work, target_list);
 		}
 	}
@@ -1915,9 +1986,9 @@ static void binder_send_failed_reply(struct binder_transaction *t,
 			binder_pop_transaction_ilocked(target_thread, t);
 			if (target_thread->reply_error.cmd == BR_OK) {
 				target_thread->reply_error.cmd = error_code;
-				binder_enqueue_work_ilocked(
-					&target_thread->reply_error.work,
-					&target_thread->todo);
+				binder_enqueue_thread_work_ilocked(
+					target_thread,
+					&target_thread->reply_error.work);
 				wake_up_interruptible(&target_thread->wait);
 			} else {
 				WARN(1, "Unexpected reply error: %u\n",
@@ -1948,6 +2019,26 @@ static void binder_send_failed_reply(struct binder_transaction *t,
 }
 
 /**
+ * binder_cleanup_transaction() - cleans up undelivered transaction
+ * @t:		transaction that needs to be cleaned up
+ * @reason:	reason the transaction wasn't delivered
+ * @error_code:	error to return to caller (if synchronous call)
+ */
+static void binder_cleanup_transaction(struct binder_transaction *t,
+				       const char *reason,
+				       uint32_t error_code)
+{
+	if (t->buffer->target_node && !(t->flags & TF_ONE_WAY)) {
+		binder_send_failed_reply(t, error_code);
+	} else {
+		binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
+			"undelivered transaction %d, %s\n",
+			t->debug_id, reason);
+		binder_free_transaction(t);
+	}
+}
+
+/**
  * binder_validate_object() - checks for a valid metadata object in a buffer.
  * @buffer:	binder_buffer that we're parsing.
  * @offset:	offset in the buffer at which to validate an object.
@@ -2536,20 +2627,18 @@ static bool binder_proc_transaction(struct binder_transaction *t,
 				    struct binder_proc *proc,
 				    struct binder_thread *thread)
 {
-	struct list_head *target_list = NULL;
 	struct binder_node *node = t->buffer->target_node;
 	bool oneway = !!(t->flags & TF_ONE_WAY);
-	bool wakeup = true;
+	bool pending_async = false;
 
 	BUG_ON(!node);
 	binder_node_lock(node);
 	if (oneway) {
 		BUG_ON(thread);
 		if (node->has_async_transaction) {
-			target_list = &node->async_todo;
-			wakeup = false;
+			pending_async = true;
 		} else {
-			node->has_async_transaction = 1;
+			node->has_async_transaction = true;
 		}
 	}
 
@@ -2561,19 +2650,17 @@ static bool binder_proc_transaction(struct binder_transaction *t,
 		return false;
 	}
 
-	if (!thread && !target_list)
+	if (!thread && !pending_async)
 		thread = binder_select_thread_ilocked(proc);
 
 	if (thread)
-		target_list = &thread->todo;
-	else if (!target_list)
-		target_list = &proc->todo;
+		binder_enqueue_thread_work_ilocked(thread, &t->work);
+	else if (!pending_async)
+		binder_enqueue_work_ilocked(&t->work, &proc->todo);
 	else
-		BUG_ON(target_list != &node->async_todo);
-
-	binder_enqueue_work_ilocked(&t->work, target_list);
+		binder_enqueue_work_ilocked(&t->work, &node->async_todo);
 
-	if (wakeup)
+	if (!pending_async)
 		binder_wakeup_thread_ilocked(proc, thread, !oneway /* sync */);
 
 	binder_inner_proc_unlock(proc);
@@ -3068,10 +3155,10 @@ static void binder_transaction(struct binder_proc *proc,
 		}
 	}
 	tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE;
-	binder_enqueue_work(proc, tcomplete, &thread->todo);
 	t->work.type = BINDER_WORK_TRANSACTION;
 
 	if (reply) {
+		binder_enqueue_thread_work(thread, tcomplete);
 		binder_inner_proc_lock(target_proc);
 		if (target_thread->is_dead) {
 			binder_inner_proc_unlock(target_proc);
@@ -3079,13 +3166,21 @@ static void binder_transaction(struct binder_proc *proc,
 		}
 		BUG_ON(t->buffer->async_transaction != 0);
 		binder_pop_transaction_ilocked(target_thread, in_reply_to);
-		binder_enqueue_work_ilocked(&t->work, &target_thread->todo);
+		binder_enqueue_thread_work_ilocked(target_thread, &t->work);
 		binder_inner_proc_unlock(target_proc);
 		wake_up_interruptible_sync(&target_thread->wait);
 		binder_free_transaction(in_reply_to);
 	} else if (!(t->flags & TF_ONE_WAY)) {
 		BUG_ON(t->buffer->async_transaction != 0);
 		binder_inner_proc_lock(proc);
+		/*
+		 * Defer the TRANSACTION_COMPLETE, so we don't return to
+		 * userspace immediately; this allows the target process to
+		 * immediately start processing this transaction, reducing
+		 * latency. We will then return the TRANSACTION_COMPLETE when
+		 * the target replies (or there is an error).
+		 */
+		binder_enqueue_deferred_thread_work_ilocked(thread, tcomplete);
 		t->need_reply = 1;
 		t->from_parent = thread->transaction_stack;
 		thread->transaction_stack = t;
@@ -3099,6 +3194,7 @@ static void binder_transaction(struct binder_proc *proc,
 	} else {
 		BUG_ON(target_node == NULL);
 		BUG_ON(t->buffer->async_transaction != 1);
+		binder_enqueue_thread_work(thread, tcomplete);
 		if (!binder_proc_transaction(t, target_proc, NULL))
 			goto err_dead_proc_or_thread;
 	}
@@ -3177,15 +3273,11 @@ err_invalid_target_handle:
 	BUG_ON(thread->return_error.cmd != BR_OK);
 	if (in_reply_to) {
 		thread->return_error.cmd = BR_TRANSACTION_COMPLETE;
-		binder_enqueue_work(thread->proc,
-				    &thread->return_error.work,
-				    &thread->todo);
+		binder_enqueue_thread_work(thread, &thread->return_error.work);
 		binder_send_failed_reply(in_reply_to, return_error);
 	} else {
 		thread->return_error.cmd = return_error;
-		binder_enqueue_work(thread->proc,
-				    &thread->return_error.work,
-				    &thread->todo);
+		binder_enqueue_thread_work(thread, &thread->return_error.work);
 	}
 }
 
@@ -3391,7 +3483,7 @@ static int binder_thread_write(struct binder_proc *proc,
 				w = binder_dequeue_work_head_ilocked(
 						&buf_node->async_todo);
 				if (!w) {
-					buf_node->has_async_transaction = 0;
+					buf_node->has_async_transaction = false;
 				} else {
 					binder_enqueue_work_ilocked(
 							w, &proc->todo);
@@ -3489,10 +3581,9 @@ static int binder_thread_write(struct binder_proc *proc,
 					WARN_ON(thread->return_error.cmd !=
 						BR_OK);
 					thread->return_error.cmd = BR_ERROR;
-					binder_enqueue_work(
-						thread->proc,
-						&thread->return_error.work,
-						&thread->todo);
+					binder_enqueue_thread_work(
+						thread,
+						&thread->return_error.work);
 					binder_debug(
 						BINDER_DEBUG_FAILED_TRANSACTION,
 						"%d:%d BC_REQUEST_DEATH_NOTIFICATION failed\n",
@@ -3572,9 +3663,9 @@ static int binder_thread_write(struct binder_proc *proc,
 					if (thread->looper &
 					    (BINDER_LOOPER_STATE_REGISTERED |
 					     BINDER_LOOPER_STATE_ENTERED))
-						binder_enqueue_work_ilocked(
-								&death->work,
-								&thread->todo);
+						binder_enqueue_thread_work_ilocked(
+								thread,
+								&death->work);
 					else {
 						binder_enqueue_work_ilocked(
 								&death->work,
@@ -3629,8 +3720,8 @@ static int binder_thread_write(struct binder_proc *proc,
 				if (thread->looper &
 					(BINDER_LOOPER_STATE_REGISTERED |
 					 BINDER_LOOPER_STATE_ENTERED))
-					binder_enqueue_work_ilocked(
-						&death->work, &thread->todo);
+					binder_enqueue_thread_work_ilocked(
+						thread, &death->work);
 				else {
 					binder_enqueue_work_ilocked(
 							&death->work,
@@ -3804,6 +3895,8 @@ retry:
 			break;
 		}
 		w = binder_dequeue_work_head_ilocked(list);
+		if (binder_worklist_empty_ilocked(&thread->todo))
+			thread->process_todo = false;
 
 		switch (w->type) {
 		case BINDER_WORK_TRANSACTION: {
@@ -4015,12 +4108,20 @@ retry:
 		if (put_user(cmd, (uint32_t __user *)ptr)) {
 			if (t_from)
 				binder_thread_dec_tmpref(t_from);
+
+			binder_cleanup_transaction(t, "put_user failed",
+						   BR_FAILED_REPLY);
+
 			return -EFAULT;
 		}
 		ptr += sizeof(uint32_t);
 		if (copy_to_user(ptr, &tr, sizeof(tr))) {
 			if (t_from)
 				binder_thread_dec_tmpref(t_from);
+
+			binder_cleanup_transaction(t, "copy_to_user failed",
+						   BR_FAILED_REPLY);
+
 			return -EFAULT;
 		}
 		ptr += sizeof(tr);
@@ -4090,15 +4191,9 @@ static void binder_release_work(struct binder_proc *proc,
 			struct binder_transaction *t;
 
 			t = container_of(w, struct binder_transaction, work);
-			if (t->buffer->target_node &&
-			    !(t->flags & TF_ONE_WAY)) {
-				binder_send_failed_reply(t, BR_DEAD_REPLY);
-			} else {
-				binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
-					"undelivered transaction %d\n",
-					t->debug_id);
-				binder_free_transaction(t);
-			}
+
+			binder_cleanup_transaction(t, "process died.",
+						   BR_DEAD_REPLY);
 		} break;
 		case BINDER_WORK_RETURN_ERROR: {
 			struct binder_error *e = container_of(
@@ -4267,6 +4362,18 @@ static int binder_thread_release(struct binder_proc *proc,
 		if (t)
 			spin_lock(&t->lock);
 	}
+
+	/*
+	 * If this thread used poll, make sure we remove the waitqueue
+	 * from any epoll data structures holding it with POLLFREE.
+	 * waitqueue_active() is safe to use here because we're holding
+	 * the inner lock.
+	 */
+	if ((thread->looper & BINDER_LOOPER_STATE_POLL) &&
+	    waitqueue_active(&thread->wait)) {
+		wake_up_poll(&thread->wait, POLLHUP | POLLFREE);
+	}
+
 	binder_inner_proc_unlock(thread->proc);
 
 	if (send_reply)
@@ -4276,7 +4383,7 @@ static int binder_thread_release(struct binder_proc *proc,
 	return active_transactions;
 }
 
-static unsigned int binder_poll(struct file *filp,
+static __poll_t binder_poll(struct file *filp,
 				struct poll_table_struct *wait)
 {
 	struct binder_proc *proc = filp->private_data;
@@ -4605,11 +4712,13 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
 	ret = binder_alloc_mmap_handler(&proc->alloc, vma);
 	if (ret)
 		return ret;
+	mutex_lock(&proc->files_lock);
 	proc->files = get_files_struct(current);
+	mutex_unlock(&proc->files_lock);
 	return 0;
 
 err_bad_arg:
-	pr_err("binder_mmap: %d %lx-%lx %s failed %d\n",
+	pr_err("%s: %d %lx-%lx %s failed %d\n", __func__,
 	       proc->pid, vma->vm_start, vma->vm_end, failure_string, ret);
 	return ret;
 }
@@ -4619,7 +4728,7 @@ static int binder_open(struct inode *nodp, struct file *filp)
 	struct binder_proc *proc;
 	struct binder_device *binder_dev;
 
-	binder_debug(BINDER_DEBUG_OPEN_CLOSE, "binder_open: %d:%d\n",
+	binder_debug(BINDER_DEBUG_OPEN_CLOSE, "%s: %d:%d\n", __func__,
 		     current->group_leader->pid, current->pid);
 
 	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
@@ -4629,6 +4738,7 @@ static int binder_open(struct inode *nodp, struct file *filp)
 	spin_lock_init(&proc->outer_lock);
 	get_task_struct(current->group_leader);
 	proc->tsk = current->group_leader;
+	mutex_init(&proc->files_lock);
 	INIT_LIST_HEAD(&proc->todo);
 	proc->default_priority = task_nice(current);
 	binder_dev = container_of(filp->private_data, struct binder_device,
@@ -4657,7 +4767,7 @@ static int binder_open(struct inode *nodp, struct file *filp)
 		 * anyway print all contexts that a given PID has, so this
 		 * is not a problem.
 		 */
-		proc->debugfs_entry = debugfs_create_file(strbuf, S_IRUGO,
+		proc->debugfs_entry = debugfs_create_file(strbuf, 0444,
 			binder_debugfs_dir_entry_proc,
 			(void *)(unsigned long)proc->pid,
 			&binder_proc_fops);
@@ -4881,9 +4991,11 @@ static void binder_deferred_func(struct work_struct *work)
 
 		files = NULL;
 		if (defer & BINDER_DEFERRED_PUT_FILES) {
+			mutex_lock(&proc->files_lock);
 			files = proc->files;
 			if (files)
 				proc->files = NULL;
+			mutex_unlock(&proc->files_lock);
 		}
 
 		if (defer & BINDER_DEFERRED_FLUSH)
@@ -5484,7 +5596,9 @@ static int __init binder_init(void)
 	struct binder_device *device;
 	struct hlist_node *tmp;
 
-	binder_alloc_shrinker_init();
+	ret = binder_alloc_shrinker_init();
+	if (ret)
+		return ret;
 
 	atomic_set(&binder_transaction_log.cur, ~0U);
 	atomic_set(&binder_transaction_log_failed.cur, ~0U);
@@ -5496,27 +5610,27 @@ static int __init binder_init(void)
 
 	if (binder_debugfs_dir_entry_root) {
 		debugfs_create_file("state",
-				    S_IRUGO,
+				    0444,
 				    binder_debugfs_dir_entry_root,
 				    NULL,
 				    &binder_state_fops);
 		debugfs_create_file("stats",
-				    S_IRUGO,
+				    0444,
 				    binder_debugfs_dir_entry_root,
 				    NULL,
 				    &binder_stats_fops);
 		debugfs_create_file("transactions",
-				    S_IRUGO,
+				    0444,
 				    binder_debugfs_dir_entry_root,
 				    NULL,
 				    &binder_transactions_fops);
 		debugfs_create_file("transaction_log",
-				    S_IRUGO,
+				    0444,
 				    binder_debugfs_dir_entry_root,
 				    &binder_transaction_log,
 				    &binder_transaction_log_fops);
 		debugfs_create_file("failed_transaction_log",
-				    S_IRUGO,
+				    0444,
 				    binder_debugfs_dir_entry_root,
 				    &binder_transaction_log_failed,
 				    &binder_transaction_log_fops);
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 6f6f745605af..5a426c877dfb 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -281,6 +281,9 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 			goto err_vm_insert_page_failed;
 		}
 
+		if (index + 1 > alloc->pages_high)
+			alloc->pages_high = index + 1;
+
 		trace_binder_alloc_page_end(alloc, index);
 		/* vm_insert_page does not seem to increment the refcount */
 	}
@@ -324,11 +327,12 @@ err_no_vma:
 	return vma ? -ENOMEM : -ESRCH;
 }
 
-struct binder_buffer *binder_alloc_new_buf_locked(struct binder_alloc *alloc,
-						  size_t data_size,
-						  size_t offsets_size,
-						  size_t extra_buffers_size,
-						  int is_async)
+static struct binder_buffer *binder_alloc_new_buf_locked(
+				struct binder_alloc *alloc,
+				size_t data_size,
+				size_t offsets_size,
+				size_t extra_buffers_size,
+				int is_async)
 {
 	struct rb_node *n = alloc->free_buffers.rb_node;
 	struct binder_buffer *buffer;
@@ -666,7 +670,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 		goto err_already_mapped;
 	}
 
-	area = get_vm_area(vma->vm_end - vma->vm_start, VM_IOREMAP);
+	area = get_vm_area(vma->vm_end - vma->vm_start, VM_ALLOC);
 	if (area == NULL) {
 		ret = -ENOMEM;
 		failure_string = "get_vm_area";
@@ -853,6 +857,7 @@ void binder_alloc_print_pages(struct seq_file *m,
 	}
 	mutex_unlock(&alloc->mutex);
 	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
+	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);
 }
 
 /**
@@ -1002,8 +1007,14 @@ void binder_alloc_init(struct binder_alloc *alloc)
 	INIT_LIST_HEAD(&alloc->buffers);
 }
 
-void binder_alloc_shrinker_init(void)
+int binder_alloc_shrinker_init(void)
 {
-	list_lru_init(&binder_alloc_lru);
-	register_shrinker(&binder_shrinker);
+	int ret = list_lru_init(&binder_alloc_lru);
+
+	if (ret == 0) {
+		ret = register_shrinker(&binder_shrinker);
+		if (ret)
+			list_lru_destroy(&binder_alloc_lru);
+	}
+	return ret;
 }
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index 2dd33b6df104..9ef64e563856 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -92,6 +92,7 @@ struct binder_lru_page {
  * @pages:              array of binder_lru_page
  * @buffer_size:        size of address space specified via mmap
  * @pid:                pid for associated binder_proc (invariant after init)
+ * @pages_high:         high watermark of offset in @pages
  *
  * Bookkeeping structure for per-proc address space management for binder
  * buffers. It is normally initialized during binder_init() and binder_mmap()
@@ -112,6 +113,7 @@ struct binder_alloc {
 	size_t buffer_size;
 	uint32_t buffer_free;
 	int pid;
+	size_t pages_high;
 };
 
 #ifdef CONFIG_ANDROID_BINDER_IPC_SELFTEST
@@ -128,7 +130,7 @@ extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 						  size_t extra_buffers_size,
 						  int is_async);
 extern void binder_alloc_init(struct binder_alloc *alloc);
-void binder_alloc_shrinker_init(void);
+extern int binder_alloc_shrinker_init(void);
 extern void binder_alloc_vma_close(struct binder_alloc *alloc);
 extern struct binder_buffer *
 binder_alloc_prepare_to_free(struct binder_alloc *alloc,
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index cb5339166563..a7120d621154 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -92,6 +92,25 @@ config SATA_AHCI
 
 	  If unsure, say N.
 
+config SATA_MOBILE_LPM_POLICY
+	int "Default SATA Link Power Management policy for mobile chipsets"
+	range 0 4
+	default 0
+	depends on SATA_AHCI
+	help
+	  Select the Default SATA Link Power Management (LPM) policy to use
+	  for mobile / laptop variants of chipsets / "South Bridges".
+
+	  The value set has the following meanings:
+		0 => Keep firmware settings
+		1 => Maximum performance
+		2 => Medium power
+		3 => Medium power with Device Initiated PM enabled
+		4 => Minimum power
+
+	  Note "Minimum power" is known to cause issues, including disk
+	  corruption, with some disks and should not be used.
+
 config SATA_AHCI_PLATFORM
 	tristate "Platform AHCI SATA support"
 	help
@@ -925,15 +944,6 @@ endif # ATA_BMDMA
 
 comment "PIO-only SFF controllers"
 
-config PATA_AT32
-	tristate "Atmel AVR32 PATA support (Experimental)"
-	depends on AVR32 && PLATFORM_AT32AP
-	help
-	  This option enables support for the IDE devices on the
-	  Atmel AT32AP platform.
-
-	  If unsure, say N.
-
 config PATA_CMD640_PCI
 	tristate "CMD640 PCI PATA support (Experimental)"
 	depends on PCI
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index 8daec3e657f8..f1f5a3fbc777 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -96,7 +96,6 @@ obj-$(CONFIG_PATA_VIA)		+= pata_via.o
 obj-$(CONFIG_PATA_WINBOND)	+= pata_sl82c105.o
 
 # SFF PIO only
-obj-$(CONFIG_PATA_AT32)		+= pata_at32.o
 obj-$(CONFIG_PATA_CMD640_PCI)	+= pata_cmd640.o
 obj-$(CONFIG_PATA_FALCON)	+= pata_falcon.o
 obj-$(CONFIG_PATA_ISAPNP)	+= pata_isapnp.o
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 5443cb71d7ba..355a95a83a34 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -65,6 +65,7 @@ enum board_ids {
 	/* board IDs by feature in alphabetical order */
 	board_ahci,
 	board_ahci_ign_iferr,
+	board_ahci_mobile,
 	board_ahci_nomsi,
 	board_ahci_noncq,
 	board_ahci_nosntf,
@@ -140,6 +141,13 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
+	[board_ahci_mobile] = {
+		AHCI_HFLAGS	(AHCI_HFLAG_IS_MOBILE),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 	[board_ahci_nomsi] = {
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_MSI),
 		.flags		= AHCI_FLAG_COMMON,
@@ -252,13 +260,13 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x2924), board_ahci }, /* ICH9 */
 	{ PCI_VDEVICE(INTEL, 0x2925), board_ahci }, /* ICH9 */
 	{ PCI_VDEVICE(INTEL, 0x2927), board_ahci }, /* ICH9 */
-	{ PCI_VDEVICE(INTEL, 0x2929), board_ahci }, /* ICH9M */
-	{ PCI_VDEVICE(INTEL, 0x292a), board_ahci }, /* ICH9M */
-	{ PCI_VDEVICE(INTEL, 0x292b), board_ahci }, /* ICH9M */
-	{ PCI_VDEVICE(INTEL, 0x292c), board_ahci }, /* ICH9M */
-	{ PCI_VDEVICE(INTEL, 0x292f), board_ahci }, /* ICH9M */
+	{ PCI_VDEVICE(INTEL, 0x2929), board_ahci_mobile }, /* ICH9M */
+	{ PCI_VDEVICE(INTEL, 0x292a), board_ahci_mobile }, /* ICH9M */
+	{ PCI_VDEVICE(INTEL, 0x292b), board_ahci_mobile }, /* ICH9M */
+	{ PCI_VDEVICE(INTEL, 0x292c), board_ahci_mobile }, /* ICH9M */
+	{ PCI_VDEVICE(INTEL, 0x292f), board_ahci_mobile }, /* ICH9M */
 	{ PCI_VDEVICE(INTEL, 0x294d), board_ahci }, /* ICH9 */
-	{ PCI_VDEVICE(INTEL, 0x294e), board_ahci }, /* ICH9M */
+	{ PCI_VDEVICE(INTEL, 0x294e), board_ahci_mobile }, /* ICH9M */
 	{ PCI_VDEVICE(INTEL, 0x502a), board_ahci }, /* Tolapai */
 	{ PCI_VDEVICE(INTEL, 0x502b), board_ahci }, /* Tolapai */
 	{ PCI_VDEVICE(INTEL, 0x3a05), board_ahci }, /* ICH10 */
@@ -268,9 +276,9 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x3b23), board_ahci }, /* PCH AHCI */
 	{ PCI_VDEVICE(INTEL, 0x3b24), board_ahci }, /* PCH RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b25), board_ahci }, /* PCH RAID */
-	{ PCI_VDEVICE(INTEL, 0x3b29), board_ahci }, /* PCH AHCI */
+	{ PCI_VDEVICE(INTEL, 0x3b29), board_ahci_mobile }, /* PCH M AHCI */
 	{ PCI_VDEVICE(INTEL, 0x3b2b), board_ahci }, /* PCH RAID */
-	{ PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH RAID */
+	{ PCI_VDEVICE(INTEL, 0x3b2c), board_ahci_mobile }, /* PCH M RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b2f), board_ahci }, /* PCH AHCI */
 	{ PCI_VDEVICE(INTEL, 0x19b0), board_ahci }, /* DNV AHCI */
 	{ PCI_VDEVICE(INTEL, 0x19b1), board_ahci }, /* DNV AHCI */
@@ -293,9 +301,9 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x19cE), board_ahci }, /* DNV AHCI */
 	{ PCI_VDEVICE(INTEL, 0x19cF), board_ahci }, /* DNV AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c02), board_ahci }, /* CPT AHCI */
-	{ PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT AHCI */
+	{ PCI_VDEVICE(INTEL, 0x1c03), board_ahci_mobile }, /* CPT M AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c04), board_ahci }, /* CPT RAID */
-	{ PCI_VDEVICE(INTEL, 0x1c05), board_ahci }, /* CPT RAID */
+	{ PCI_VDEVICE(INTEL, 0x1c05), board_ahci_mobile }, /* CPT M RAID */
 	{ PCI_VDEVICE(INTEL, 0x1c06), board_ahci }, /* CPT RAID */
 	{ PCI_VDEVICE(INTEL, 0x1c07), board_ahci }, /* CPT RAID */
 	{ PCI_VDEVICE(INTEL, 0x1d02), board_ahci }, /* PBG AHCI */
@@ -304,28 +312,28 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* PBG RAID */
 	{ PCI_VDEVICE(INTEL, 0x2323), board_ahci }, /* DH89xxCC AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1e02), board_ahci }, /* Panther Point AHCI */
-	{ PCI_VDEVICE(INTEL, 0x1e03), board_ahci }, /* Panther Point AHCI */
+	{ PCI_VDEVICE(INTEL, 0x1e03), board_ahci_mobile }, /* Panther M AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1e04), board_ahci }, /* Panther Point RAID */
 	{ PCI_VDEVICE(INTEL, 0x1e05), board_ahci }, /* Panther Point RAID */
 	{ PCI_VDEVICE(INTEL, 0x1e06), board_ahci }, /* Panther Point RAID */
-	{ PCI_VDEVICE(INTEL, 0x1e07), board_ahci }, /* Panther Point RAID */
+	{ PCI_VDEVICE(INTEL, 0x1e07), board_ahci_mobile }, /* Panther M RAID */
 	{ PCI_VDEVICE(INTEL, 0x1e0e), board_ahci }, /* Panther Point RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c02), board_ahci }, /* Lynx Point AHCI */
-	{ PCI_VDEVICE(INTEL, 0x8c03), board_ahci }, /* Lynx Point AHCI */
+	{ PCI_VDEVICE(INTEL, 0x8c03), board_ahci_mobile }, /* Lynx M AHCI */
 	{ PCI_VDEVICE(INTEL, 0x8c04), board_ahci }, /* Lynx Point RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c05), board_ahci }, /* Lynx Point RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c05), board_ahci_mobile }, /* Lynx M RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c06), board_ahci }, /* Lynx Point RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c07), board_ahci }, /* Lynx Point RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c07), board_ahci_mobile }, /* Lynx M RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c0e), board_ahci }, /* Lynx Point RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c0f), board_ahci }, /* Lynx Point RAID */
-	{ PCI_VDEVICE(INTEL, 0x9c02), board_ahci }, /* Lynx Point-LP AHCI */
-	{ PCI_VDEVICE(INTEL, 0x9c03), board_ahci }, /* Lynx Point-LP AHCI */
-	{ PCI_VDEVICE(INTEL, 0x9c04), board_ahci }, /* Lynx Point-LP RAID */
-	{ PCI_VDEVICE(INTEL, 0x9c05), board_ahci }, /* Lynx Point-LP RAID */
-	{ PCI_VDEVICE(INTEL, 0x9c06), board_ahci }, /* Lynx Point-LP RAID */
-	{ PCI_VDEVICE(INTEL, 0x9c07), board_ahci }, /* Lynx Point-LP RAID */
-	{ PCI_VDEVICE(INTEL, 0x9c0e), board_ahci }, /* Lynx Point-LP RAID */
-	{ PCI_VDEVICE(INTEL, 0x9c0f), board_ahci }, /* Lynx Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c0f), board_ahci_mobile }, /* Lynx M RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c02), board_ahci_mobile }, /* Lynx LP AHCI */
+	{ PCI_VDEVICE(INTEL, 0x9c03), board_ahci_mobile }, /* Lynx LP AHCI */
+	{ PCI_VDEVICE(INTEL, 0x9c04), board_ahci_mobile }, /* Lynx LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c05), board_ahci_mobile }, /* Lynx LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c06), board_ahci_mobile }, /* Lynx LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c07), board_ahci_mobile }, /* Lynx LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c0e), board_ahci_mobile }, /* Lynx LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c0f), board_ahci_mobile }, /* Lynx LP RAID */
 	{ PCI_VDEVICE(INTEL, 0x1f22), board_ahci }, /* Avoton AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1f23), board_ahci }, /* Avoton AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1f24), board_ahci }, /* Avoton RAID */
@@ -353,26 +361,26 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x8d66), board_ahci }, /* Wellsburg RAID */
 	{ PCI_VDEVICE(INTEL, 0x8d6e), board_ahci }, /* Wellsburg RAID */
 	{ PCI_VDEVICE(INTEL, 0x23a3), board_ahci }, /* Coleto Creek AHCI */
-	{ PCI_VDEVICE(INTEL, 0x9c83), board_ahci }, /* Wildcat Point-LP AHCI */
-	{ PCI_VDEVICE(INTEL, 0x9c85), board_ahci }, /* Wildcat Point-LP RAID */
-	{ PCI_VDEVICE(INTEL, 0x9c87), board_ahci }, /* Wildcat Point-LP RAID */
-	{ PCI_VDEVICE(INTEL, 0x9c8f), board_ahci }, /* Wildcat Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c83), board_ahci_mobile }, /* Wildcat LP AHCI */
+	{ PCI_VDEVICE(INTEL, 0x9c85), board_ahci_mobile }, /* Wildcat LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c87), board_ahci_mobile }, /* Wildcat LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c8f), board_ahci_mobile }, /* Wildcat LP RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c82), board_ahci }, /* 9 Series AHCI */
-	{ PCI_VDEVICE(INTEL, 0x8c83), board_ahci }, /* 9 Series AHCI */
+	{ PCI_VDEVICE(INTEL, 0x8c83), board_ahci_mobile }, /* 9 Series M AHCI */
 	{ PCI_VDEVICE(INTEL, 0x8c84), board_ahci }, /* 9 Series RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c85), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c85), board_ahci_mobile }, /* 9 Series M RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c86), board_ahci }, /* 9 Series RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c87), board_ahci_mobile }, /* 9 Series M RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c8e), board_ahci }, /* 9 Series RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series RAID */
-	{ PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */
-	{ PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */
-	{ PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c8f), board_ahci_mobile }, /* 9 Series M RAID */
+	{ PCI_VDEVICE(INTEL, 0x9d03), board_ahci_mobile }, /* Sunrise LP AHCI */
+	{ PCI_VDEVICE(INTEL, 0x9d05), board_ahci_mobile }, /* Sunrise LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9d07), board_ahci_mobile }, /* Sunrise LP RAID */
 	{ PCI_VDEVICE(INTEL, 0xa102), board_ahci }, /* Sunrise Point-H AHCI */
-	{ PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */
+	{ PCI_VDEVICE(INTEL, 0xa103), board_ahci_mobile }, /* Sunrise M AHCI */
 	{ PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */
 	{ PCI_VDEVICE(INTEL, 0xa106), board_ahci }, /* Sunrise Point-H RAID */
-	{ PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */
+	{ PCI_VDEVICE(INTEL, 0xa107), board_ahci_mobile }, /* Sunrise M RAID */
 	{ PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */
 	{ PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Lewisburg AHCI*/
@@ -386,6 +394,11 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa252), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa256), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa356), board_ahci }, /* Cannon Lake PCH-H RAID */
+	{ PCI_VDEVICE(INTEL, 0x0f22), board_ahci_mobile }, /* Bay Trail AHCI */
+	{ PCI_VDEVICE(INTEL, 0x0f23), board_ahci_mobile }, /* Bay Trail AHCI */
+	{ PCI_VDEVICE(INTEL, 0x22a3), board_ahci_mobile }, /* Cherry Tr. AHCI */
+	{ PCI_VDEVICE(INTEL, 0x5ae3), board_ahci_mobile }, /* ApolloLake AHCI */
 
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
 	{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
@@ -593,6 +606,9 @@ static int marvell_enable = 1;
 module_param(marvell_enable, int, 0644);
 MODULE_PARM_DESC(marvell_enable, "Marvell SATA via AHCI (1 = enabled)");
 
+static int mobile_lpm_policy = CONFIG_SATA_MOBILE_LPM_POLICY;
+module_param(mobile_lpm_policy, int, 0644);
+MODULE_PARM_DESC(mobile_lpm_policy, "Default LPM policy for mobile chipsets");
 
 static void ahci_pci_save_initial_config(struct pci_dev *pdev,
 					 struct ahci_host_priv *hpriv)
@@ -1728,6 +1744,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		if (ap->flags & ATA_FLAG_EM)
 			ap->em_message_type = hpriv->em_msg_type;
 
+		if ((hpriv->flags & AHCI_HFLAG_IS_MOBILE) &&
+		    mobile_lpm_policy >= ATA_LPM_UNKNOWN &&
+		    mobile_lpm_policy <= ATA_LPM_MIN_POWER)
+			ap->target_lpm_policy = mobile_lpm_policy;
 
 		/* disabled/not-implemented port */
 		if (!(hpriv->port_map & (1 << i)))
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 749fd94441b0..a9d996e17d75 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -251,6 +251,9 @@ enum {
 	AHCI_HFLAG_YES_ALPM		= (1 << 23), /* force ALPM cap on */
 	AHCI_HFLAG_NO_WRITE_TO_RO	= (1 << 24), /* don't write to read
 							only registers */
+	AHCI_HFLAG_IS_MOBILE		= (1 << 25), /* mobile chipset, use
+							SATA_MOBILE_LPM_POLICY
+							as default lpm_policy */
 
 	/* ap->flags bits */
 
diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c
index 5936d1679bf3..ea430819c80b 100644
--- a/drivers/ata/ahci_brcm.c
+++ b/drivers/ata/ahci_brcm.c
@@ -70,6 +70,13 @@
 	(DATA_ENDIAN << DMADESC_ENDIAN_SHIFT) |		\
 	(MMIO_ENDIAN << MMIO_ENDIAN_SHIFT))
 
+#define BUS_CTRL_ENDIAN_NSP_CONF			\
+	(0x02 << DMADATA_ENDIAN_SHIFT | 0x02 << DMADESC_ENDIAN_SHIFT)
+
+#define BUS_CTRL_ENDIAN_CONF_MASK			\
+	(0x3 << MMIO_ENDIAN_SHIFT | 0x3 << DMADESC_ENDIAN_SHIFT |	\
+	 0x3 << DMADATA_ENDIAN_SHIFT | 0x3 << PIODATA_ENDIAN_SHIFT)
+
 enum brcm_ahci_version {
 	BRCM_SATA_BCM7425 = 1,
 	BRCM_SATA_BCM7445,
@@ -89,14 +96,6 @@ struct brcm_ahci_priv {
 	enum brcm_ahci_version version;
 };
 
-static const struct ata_port_info ahci_brcm_port_info = {
-	.flags		= AHCI_FLAG_COMMON | ATA_FLAG_NO_DIPM,
-	.link_flags	= ATA_LFLAG_NO_DB_DELAY,
-	.pio_mask	= ATA_PIO4,
-	.udma_mask	= ATA_UDMA6,
-	.port_ops	= &ahci_platform_ops,
-};
-
 static inline u32 brcm_sata_readreg(void __iomem *addr)
 {
 	/*
@@ -250,20 +249,105 @@ static u32 brcm_ahci_get_portmask(struct platform_device *pdev,
 static void brcm_sata_init(struct brcm_ahci_priv *priv)
 {
 	void __iomem *ctrl = priv->top_ctrl + SATA_TOP_CTRL_BUS_CTRL;
+	u32 data;
 
 	/* Configure endianness */
-	if (priv->version ==  BRCM_SATA_NSP) {
-		u32 data = brcm_sata_readreg(ctrl);
-
-		data &= ~((0x03 << DMADATA_ENDIAN_SHIFT) |
-			(0x03 << DMADESC_ENDIAN_SHIFT));
-		data |= (0x02 << DMADATA_ENDIAN_SHIFT) |
-			(0x02 << DMADESC_ENDIAN_SHIFT);
-		brcm_sata_writereg(data, ctrl);
-	} else
-		brcm_sata_writereg(BUS_CTRL_ENDIAN_CONF, ctrl);
+	data = brcm_sata_readreg(ctrl);
+	data &= ~BUS_CTRL_ENDIAN_CONF_MASK;
+	if (priv->version == BRCM_SATA_NSP)
+		data |= BUS_CTRL_ENDIAN_NSP_CONF;
+	else
+		data |= BUS_CTRL_ENDIAN_CONF;
+	brcm_sata_writereg(data, ctrl);
+}
+
+static unsigned int brcm_ahci_read_id(struct ata_device *dev,
+				      struct ata_taskfile *tf, u16 *id)
+{
+	struct ata_port *ap = dev->link->ap;
+	struct ata_host *host = ap->host;
+	struct ahci_host_priv *hpriv = host->private_data;
+	struct brcm_ahci_priv *priv = hpriv->plat_data;
+	void __iomem *mmio = hpriv->mmio;
+	unsigned int err_mask;
+	unsigned long flags;
+	int i, rc;
+	u32 ctl;
+
+	/* Try to read the device ID and, if this fails, proceed with the
+	 * recovery sequence below
+	 */
+	err_mask = ata_do_dev_read_id(dev, tf, id);
+	if (likely(!err_mask))
+		return err_mask;
+
+	/* Disable host interrupts */
+	spin_lock_irqsave(&host->lock, flags);
+	ctl = readl(mmio + HOST_CTL);
+	ctl &= ~HOST_IRQ_EN;
+	writel(ctl, mmio + HOST_CTL);
+	readl(mmio + HOST_CTL); /* flush */
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	/* Perform the SATA PHY reset sequence */
+	brcm_sata_phy_disable(priv, ap->port_no);
+
+	/* Bring the PHY back on */
+	brcm_sata_phy_enable(priv, ap->port_no);
+
+	/* Re-initialize and calibrate the PHY */
+	for (i = 0; i < hpriv->nports; i++) {
+		rc = phy_init(hpriv->phys[i]);
+		if (rc)
+			goto disable_phys;
+
+		rc = phy_calibrate(hpriv->phys[i]);
+		if (rc) {
+			phy_exit(hpriv->phys[i]);
+			goto disable_phys;
+		}
+	}
+
+	/* Re-enable host interrupts */
+	spin_lock_irqsave(&host->lock, flags);
+	ctl = readl(mmio + HOST_CTL);
+	ctl |= HOST_IRQ_EN;
+	writel(ctl, mmio + HOST_CTL);
+	readl(mmio + HOST_CTL); /* flush */
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	return ata_do_dev_read_id(dev, tf, id);
+
+disable_phys:
+	while (--i >= 0) {
+		phy_power_off(hpriv->phys[i]);
+		phy_exit(hpriv->phys[i]);
+	}
+
+	return AC_ERR_OTHER;
+}
+
+static void brcm_ahci_host_stop(struct ata_host *host)
+{
+	struct ahci_host_priv *hpriv = host->private_data;
+
+	ahci_platform_disable_resources(hpriv);
 }
 
+static struct ata_port_operations ahci_brcm_platform_ops = {
+	.inherits	= &ahci_ops,
+	.host_stop	= brcm_ahci_host_stop,
+	.read_id	= brcm_ahci_read_id,
+};
+
+static const struct ata_port_info ahci_brcm_port_info = {
+	.flags		= AHCI_FLAG_COMMON | ATA_FLAG_NO_DIPM,
+	.link_flags	= ATA_LFLAG_NO_DB_DELAY,
+	.pio_mask	= ATA_PIO4,
+	.udma_mask	= ATA_UDMA6,
+	.port_ops	= &ahci_brcm_platform_ops,
+};
+
 #ifdef CONFIG_PM_SLEEP
 static int brcm_ahci_suspend(struct device *dev)
 {
diff --git a/drivers/ata/ahci_mtk.c b/drivers/ata/ahci_mtk.c
index 80854f71559a..0ae6971c2a4c 100644
--- a/drivers/ata/ahci_mtk.c
+++ b/drivers/ata/ahci_mtk.c
@@ -1,5 +1,5 @@
 /*
- * MeidaTek AHCI SATA driver
+ * MediaTek AHCI SATA driver
  *
  * Copyright (c) 2017 MediaTek Inc.
  * Author: Ryder Lee <ryder.lee@mediatek.com>
@@ -25,7 +25,7 @@
 #include <linux/reset.h>
 #include "ahci.h"
 
-#define DRV_NAME		"ahci"
+#define DRV_NAME		"ahci-mtk"
 
 #define SYS_CFG			0x14
 #define SYS_CFG_SATA_MSK	GENMASK(31, 30)
@@ -192,5 +192,5 @@ static struct platform_driver mtk_ahci_driver = {
 };
 module_platform_driver(mtk_ahci_driver);
 
-MODULE_DESCRIPTION("MeidaTek SATA AHCI Driver");
+MODULE_DESCRIPTION("MediaTek SATA AHCI Driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c
index b6b0bf76dfc7..2685f28160f7 100644
--- a/drivers/ata/ahci_qoriq.c
+++ b/drivers/ata/ahci_qoriq.c
@@ -35,6 +35,8 @@
 
 /* port register default value */
 #define AHCI_PORT_PHY_1_CFG	0xa003fffe
+#define AHCI_PORT_PHY2_CFG	0x28184d1f
+#define AHCI_PORT_PHY3_CFG	0x0e081509
 #define AHCI_PORT_TRANS_CFG	0x08000029
 #define AHCI_PORT_AXICC_CFG	0x3fffffff
 
@@ -183,6 +185,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv)
 		writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2,
 				qpriv->ecc_addr);
 		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
+		writel(AHCI_PORT_PHY2_CFG, reg_base + PORT_PHY2);
+		writel(AHCI_PORT_PHY3_CFG, reg_base + PORT_PHY3);
 		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
 		if (qpriv->is_dmacoherent)
 			writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC);
@@ -190,6 +194,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv)
 
 	case AHCI_LS2080A:
 		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
+		writel(AHCI_PORT_PHY2_CFG, reg_base + PORT_PHY2);
+		writel(AHCI_PORT_PHY3_CFG, reg_base + PORT_PHY3);
 		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
 		if (qpriv->is_dmacoherent)
 			writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC);
@@ -201,6 +207,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv)
 		writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2,
 				qpriv->ecc_addr);
 		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
+		writel(AHCI_PORT_PHY2_CFG, reg_base + PORT_PHY2);
+		writel(AHCI_PORT_PHY3_CFG, reg_base + PORT_PHY3);
 		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
 		if (qpriv->is_dmacoherent)
 			writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC);
@@ -212,6 +220,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv)
 		writel(readl(qpriv->ecc_addr) | ECC_DIS_LS1088A,
 		       qpriv->ecc_addr);
 		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
+		writel(AHCI_PORT_PHY2_CFG, reg_base + PORT_PHY2);
+		writel(AHCI_PORT_PHY3_CFG, reg_base + PORT_PHY3);
 		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
 		if (qpriv->is_dmacoherent)
 			writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC);
@@ -219,6 +229,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv)
 
 	case AHCI_LS2088A:
 		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
+		writel(AHCI_PORT_PHY2_CFG, reg_base + PORT_PHY2);
+		writel(AHCI_PORT_PHY3_CFG, reg_base + PORT_PHY3);
 		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
 		if (qpriv->is_dmacoherent)
 			writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC);
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index b702c20fbc2b..7ecb1322a514 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -458,7 +458,7 @@ static const struct piix_map_db *piix_map_db_table[] = {
 	[ich8_2port_sata_byt]	= &ich8_2port_map_db,
 };
 
-static struct pci_bits piix_enable_bits[] = {
+static const struct pci_bits piix_enable_bits[] = {
 	{ 0x41U, 1U, 0x80UL, 0x80UL },	/* port 0 */
 	{ 0x43U, 1U, 0x80UL, 0x80UL },	/* port 1 */
 };
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 2a882929de4a..3c09122bf038 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -3082,13 +3082,19 @@ int sata_down_spd_limit(struct ata_link *link, u32 spd_limit)
 	bit = fls(mask) - 1;
 	mask &= ~(1 << bit);
 
-	/* Mask off all speeds higher than or equal to the current
-	 * one.  Force 1.5Gbps if current SPD is not available.
+	/*
+	 * Mask off all speeds higher than or equal to the current one.  At
+	 * this point, if current SPD is not available and we previously
+	 * recorded the link speed from SStatus, the driver has already
+	 * masked off the highest bit so mask should already be 1 or 0.
+	 * Otherwise, we should not force 1.5Gbps on a link where we have
+	 * not previously recorded speed from SStatus.  Just return in this
+	 * case.
 	 */
 	if (spd > 1)
 		mask &= (1 << (spd - 1)) - 1;
 	else
-		mask &= 1;
+		return -EINVAL;
 
 	/* were we already at the bottom? */
 	if (!mask)
@@ -4443,6 +4449,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=121671
 	 */
 	{ "LITEON CX1-JB*-HP",	NULL,		ATA_HORKAGE_MAX_SEC_1024 },
+	{ "LITEON EP1-*",	NULL,		ATA_HORKAGE_MAX_SEC_1024 },
 
 	/* Devices we expect to fail diagnostics */
 
diff --git a/drivers/ata/pata_at32.c b/drivers/ata/pata_at32.c
deleted file mode 100644
index 9aeb7a6dd4d4..000000000000
--- a/drivers/ata/pata_at32.c
+++ /dev/null
@@ -1,400 +0,0 @@
-/*
- * AVR32 SMC/CFC PATA Driver
- *
- * Copyright (C) 2007 Atmel Norway
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- */
-
-#define DEBUG
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/slab.h>
-#include <scsi/scsi_host.h>
-#include <linux/ata.h>
-#include <linux/libata.h>
-#include <linux/err.h>
-#include <linux/io.h>
-
-#include <mach/board.h>
-#include <mach/smc.h>
-
-#define DRV_NAME "pata_at32"
-#define DRV_VERSION "0.0.3"
-
-/*
- * CompactFlash controller memory layout relative to the base address:
- *
- *	Attribute memory:  0000 0000 -> 003f ffff
- *	Common memory:	   0040 0000 -> 007f ffff
- *	I/O memory:	   0080 0000 -> 00bf ffff
- *	True IDE Mode:	   00c0 0000 -> 00df ffff
- *	Alt IDE Mode:	   00e0 0000 -> 00ff ffff
- *
- * Only True IDE and Alt True IDE mode are needed for this driver.
- *
- *	True IDE mode	  => CS0 = 0, CS1 = 1 (cmd, error, stat, etc)
- *	Alt True IDE mode => CS0 = 1, CS1 = 0 (ctl, alt_stat)
- */
-#define CF_IDE_OFFSET	  0x00c00000
-#define CF_ALT_IDE_OFFSET 0x00e00000
-#define CF_RES_SIZE	  2048
-
-/*
- * Define DEBUG_BUS if you are doing debugging of your own EBI -> PATA
- * adaptor with a logic analyzer or similar.
- */
-#undef DEBUG_BUS
-
-/*
- * ATA PIO modes
- *
- *	Name	| Mb/s	| Min cycle time | Mask
- *	--------+-------+----------------+--------
- *	Mode 0	| 3.3	| 600 ns	 | 0x01
- *	Mode 1	| 5.2	| 383 ns	 | 0x03
- *	Mode 2	| 8.3	| 240 ns	 | 0x07
- *	Mode 3	| 11.1	| 180 ns	 | 0x0f
- *	Mode 4	| 16.7	| 120 ns	 | 0x1f
- *
- * Alter PIO_MASK below according to table to set maximal PIO mode.
- */
-enum {
-  PIO_MASK = ATA_PIO4,
-};
-
-/*
- * Struct containing private information about device.
- */
-struct at32_ide_info {
-	unsigned int		irq;
-	struct resource		res_ide;
-	struct resource		res_alt;
-	void __iomem		*ide_addr;
-	void __iomem		*alt_addr;
-	unsigned int		cs;
-	struct smc_config	smc;
-};
-
-/*
- * Setup SMC for the given ATA timing.
- */
-static int pata_at32_setup_timing(struct device *dev,
-				  struct at32_ide_info *info,
-				  const struct ata_timing *ata)
-{
-	struct smc_config *smc = &info->smc;
-	struct smc_timing timing;
-
-	int active;
-	int recover;
-
-	memset(&timing, 0, sizeof(struct smc_timing));
-
-	/* Total cycle time */
-	timing.read_cycle  = ata->cyc8b;
-
-	/* DIOR <= CFIOR timings */
-	timing.nrd_setup   = ata->setup;
-	timing.nrd_pulse   = ata->act8b;
-	timing.nrd_recover = ata->rec8b;
-
-	/* Convert nanosecond timing to clock cycles */
-	smc_set_timing(smc, &timing);
-
-	/* Add one extra cycle setup due to signal ring */
-	smc->nrd_setup = smc->nrd_setup + 1;
-
-	active  = smc->nrd_setup + smc->nrd_pulse;
-	recover = smc->read_cycle - active;
-
-	/* Need at least two cycles recovery */
-	if (recover < 2)
-	  smc->read_cycle = active + 2;
-
-	/* (CS0, CS1, DIR, OE) <= (CFCE1, CFCE2, CFRNW, NCSX) timings */
-	smc->ncs_read_setup = 1;
-	smc->ncs_read_pulse = smc->read_cycle - 2;
-
-	/* Write timings same as read timings */
-	smc->write_cycle = smc->read_cycle;
-	smc->nwe_setup = smc->nrd_setup;
-	smc->nwe_pulse = smc->nrd_pulse;
-	smc->ncs_write_setup = smc->ncs_read_setup;
-	smc->ncs_write_pulse = smc->ncs_read_pulse;
-
-	/* Do some debugging output of ATA and SMC timings */
-	dev_dbg(dev, "ATA: C=%d S=%d P=%d R=%d\n",
-		ata->cyc8b, ata->setup, ata->act8b, ata->rec8b);
-
-	dev_dbg(dev, "SMC: C=%d S=%d P=%d NS=%d NP=%d\n",
-		smc->read_cycle, smc->nrd_setup, smc->nrd_pulse,
-		smc->ncs_read_setup, smc->ncs_read_pulse);
-
-	/* Finally, configure the SMC */
-	return smc_set_configuration(info->cs, smc);
-}
-
-/*
- * Procedures for libATA.
- */
-static void pata_at32_set_piomode(struct ata_port *ap, struct ata_device *adev)
-{
-	struct ata_timing timing;
-	struct at32_ide_info *info = ap->host->private_data;
-
-	int ret;
-
-	/* Compute ATA timing */
-	ret = ata_timing_compute(adev, adev->pio_mode, &timing, 1000, 0);
-	if (ret) {
-		dev_warn(ap->dev, "Failed to compute ATA timing %d\n", ret);
-		return;
-	}
-
-	/* Setup SMC to ATA timing */
-	ret = pata_at32_setup_timing(ap->dev, info, &timing);
-	if (ret) {
-		dev_warn(ap->dev, "Failed to setup ATA timing %d\n", ret);
-		return;
-	}
-}
-
-static struct scsi_host_template at32_sht = {
-	ATA_PIO_SHT(DRV_NAME),
-};
-
-static struct ata_port_operations at32_port_ops = {
-	.inherits		= &ata_sff_port_ops,
-	.cable_detect		= ata_cable_40wire,
-	.set_piomode		= pata_at32_set_piomode,
-};
-
-static int __init pata_at32_init_one(struct device *dev,
-				     struct at32_ide_info *info)
-{
-	struct ata_host *host;
-	struct ata_port *ap;
-
-	host = ata_host_alloc(dev, 1);
-	if (!host)
-		return -ENOMEM;
-
-	ap = host->ports[0];
-
-	/* Setup ATA bindings */
-	ap->ops	     = &at32_port_ops;
-	ap->pio_mask = PIO_MASK;
-	ap->flags   |= ATA_FLAG_SLAVE_POSS;
-
-	/*
-	 * Since all 8-bit taskfile transfers has to go on the lower
-	 * byte of the data bus and there is a bug in the SMC that
-	 * makes it impossible to alter the bus width during runtime,
-	 * we need to hardwire the address signals as follows:
-	 *
-	 *	A_IDE(2:0) <= A_EBI(3:1)
-	 *
-	 * This makes all addresses on the EBI even, thus all data
-	 * will be on the lower byte of the data bus.  All addresses
-	 * used by libATA need to be altered according to this.
-	 */
-	ap->ioaddr.altstatus_addr = info->alt_addr + (0x06 << 1);
-	ap->ioaddr.ctl_addr	  = info->alt_addr + (0x06 << 1);
-
-	ap->ioaddr.data_addr	  = info->ide_addr + (ATA_REG_DATA << 1);
-	ap->ioaddr.error_addr	  = info->ide_addr + (ATA_REG_ERR << 1);
-	ap->ioaddr.feature_addr	  = info->ide_addr + (ATA_REG_FEATURE << 1);
-	ap->ioaddr.nsect_addr	  = info->ide_addr + (ATA_REG_NSECT << 1);
-	ap->ioaddr.lbal_addr	  = info->ide_addr + (ATA_REG_LBAL << 1);
-	ap->ioaddr.lbam_addr	  = info->ide_addr + (ATA_REG_LBAM << 1);
-	ap->ioaddr.lbah_addr	  = info->ide_addr + (ATA_REG_LBAH << 1);
-	ap->ioaddr.device_addr	  = info->ide_addr + (ATA_REG_DEVICE << 1);
-	ap->ioaddr.status_addr	  = info->ide_addr + (ATA_REG_STATUS << 1);
-	ap->ioaddr.command_addr	  = info->ide_addr + (ATA_REG_CMD << 1);
-
-	/* Set info as private data of ATA host */
-	host->private_data = info;
-
-	/* Register ATA device and return */
-	return ata_host_activate(host, info->irq, ata_sff_interrupt,
-				 IRQF_SHARED | IRQF_TRIGGER_RISING,
-				 &at32_sht);
-}
-
-/*
- * This function may come in handy for people analyzing their own
- * EBI -> PATA adaptors.
- */
-#ifdef DEBUG_BUS
-
-static void __init pata_at32_debug_bus(struct device *dev,
-				       struct at32_ide_info *info)
-{
-	const int d1 = 0xff;
-	const int d2 = 0x00;
-
-	int i;
-
-	/* Write 8-bit values (registers) */
-	iowrite8(d1, info->alt_addr + (0x06 << 1));
-	iowrite8(d2, info->alt_addr + (0x06 << 1));
-
-	for (i = 0; i < 8; i++) {
-		iowrite8(d1, info->ide_addr + (i << 1));
-		iowrite8(d2, info->ide_addr + (i << 1));
-	}
-
-	/* Write 16 bit values (data) */
-	iowrite16(d1,	   info->ide_addr);
-	iowrite16(d1 << 8, info->ide_addr);
-
-	iowrite16(d1,	   info->ide_addr);
-	iowrite16(d1 << 8, info->ide_addr);
-}
-
-#endif
-
-static int __init pata_at32_probe(struct platform_device *pdev)
-{
-	const struct ata_timing initial_timing =
-		{XFER_PIO_0, 70, 290, 240, 600, 165, 150, 600, 0};
-
-	struct device		 *dev = &pdev->dev;
-	struct at32_ide_info	 *info;
-	struct ide_platform_data *board = dev_get_platdata(&pdev->dev);
-	struct resource		 *res;
-
-	int irq;
-	int ret;
-
-	if (!board)
-		return -ENXIO;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENXIO;
-
-	/* Retrive IRQ */
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
-		return irq;
-
-	/* Setup struct containing private information */
-	info = kzalloc(sizeof(struct at32_ide_info), GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	info->irq = irq;
-	info->cs  = board->cs;
-
-	/* Request memory resources */
-	info->res_ide.start = res->start + CF_IDE_OFFSET;
-	info->res_ide.end   = info->res_ide.start + CF_RES_SIZE - 1;
-	info->res_ide.name  = "ide";
-	info->res_ide.flags = IORESOURCE_MEM;
-
-	ret = request_resource(res, &info->res_ide);
-	if (ret)
-		goto err_req_res_ide;
-
-	info->res_alt.start = res->start + CF_ALT_IDE_OFFSET;
-	info->res_alt.end   = info->res_alt.start + CF_RES_SIZE - 1;
-	info->res_alt.name  = "alt";
-	info->res_alt.flags = IORESOURCE_MEM;
-
-	ret = request_resource(res, &info->res_alt);
-	if (ret)
-		goto err_req_res_alt;
-
-	/* Setup non-timing elements of SMC */
-	info->smc.bus_width	 = 2; /* 16 bit data bus */
-	info->smc.nrd_controlled = 1; /* Sample data on rising edge of NRD */
-	info->smc.nwe_controlled = 0; /* Drive data on falling edge of NCS */
-	info->smc.nwait_mode	 = 3; /* NWAIT is in READY mode */
-	info->smc.byte_write	 = 0; /* Byte select access type */
-	info->smc.tdf_mode	 = 0; /* TDF optimization disabled */
-	info->smc.tdf_cycles	 = 0; /* No TDF wait cycles */
-
-	/* Setup SMC to ATA timing */
-	ret = pata_at32_setup_timing(dev, info, &initial_timing);
-	if (ret)
-		goto err_setup_timing;
-
-	/* Map ATA address space */
-	ret = -ENOMEM;
-	info->ide_addr = devm_ioremap(dev, info->res_ide.start, 16);
-	info->alt_addr = devm_ioremap(dev, info->res_alt.start, 16);
-	if (!info->ide_addr || !info->alt_addr)
-		goto err_ioremap;
-
-#ifdef DEBUG_BUS
-	pata_at32_debug_bus(dev, info);
-#endif
-
-	/* Setup and register ATA device */
-	ret = pata_at32_init_one(dev, info);
-	if (ret)
-		goto err_ata_device;
-
-	return 0;
-
- err_ata_device:
- err_ioremap:
- err_setup_timing:
-	release_resource(&info->res_alt);
- err_req_res_alt:
-	release_resource(&info->res_ide);
- err_req_res_ide:
-	kfree(info);
-
-	return ret;
-}
-
-static int __exit pata_at32_remove(struct platform_device *pdev)
-{
-	struct ata_host *host = platform_get_drvdata(pdev);
-	struct at32_ide_info *info;
-
-	if (!host)
-		return 0;
-
-	info = host->private_data;
-	ata_host_detach(host);
-
-	if (!info)
-		return 0;
-
-	release_resource(&info->res_ide);
-	release_resource(&info->res_alt);
-
-	kfree(info);
-
-	return 0;
-}
-
-/* work with hotplug and coldplug */
-MODULE_ALIAS("platform:at32_ide");
-
-static struct platform_driver pata_at32_driver = {
-	.remove	       = __exit_p(pata_at32_remove),
-	.driver	       = {
-		.name  = "at32_ide",
-	},
-};
-
-module_platform_driver_probe(pata_at32_driver, pata_at32_probe);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("AVR32 SMC/CFC PATA Driver");
-MODULE_AUTHOR("Kristoffer Nyborg Gregertsen <kngregertsen@norway.atmel.com>");
-MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/ata/pata_atiixp.c b/drivers/ata/pata_atiixp.c
index 49d705c9f0f7..4d49fd3c927b 100644
--- a/drivers/ata/pata_atiixp.c
+++ b/drivers/ata/pata_atiixp.c
@@ -278,6 +278,10 @@ static int atiixp_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	};
 	const struct ata_port_info *ppi[] = { &info, &info };
 
+	/* SB600 doesn't have secondary port wired */
+	if((pdev->device == PCI_DEVICE_ID_ATI_IXP600_IDE))
+		ppi[1] = &ata_dummy_port_info;
+
 	return ata_pci_bmdma_init_one(pdev, ppi, &atiixp_sht, NULL,
 				      ATA_HOST_PARALLEL_SCAN);
 }
diff --git a/drivers/ata/pata_it821x.c b/drivers/ata/pata_it821x.c
index 7a21edf89e72..8468b300193b 100644
--- a/drivers/ata/pata_it821x.c
+++ b/drivers/ata/pata_it821x.c
@@ -683,7 +683,7 @@ static u8 *it821x_firmware_command(struct ata_port *ap, u8 cmd, int len)
 			ioread16_rep(ap->ioaddr.data_addr, buf, len/2);
 			return (u8 *)buf;
 		}
-		mdelay(1);
+		usleep_range(500, 1000);
 	}
 	kfree(buf);
 	printk(KERN_ERR "it821x_firmware_command: timeout\n");
diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c
index ffd8d33c6e0f..1a18e675ba9f 100644
--- a/drivers/ata/pata_pdc2027x.c
+++ b/drivers/ata/pata_pdc2027x.c
@@ -82,7 +82,7 @@ static int pdc2027x_set_mode(struct ata_link *link, struct ata_device **r_failed
  * is issued to the device. However, if the controller clock is 133MHz,
  * the following tables must be used.
  */
-static struct pdc2027x_pio_timing {
+static const struct pdc2027x_pio_timing {
 	u8 value0, value1, value2;
 } pdc2027x_pio_timing_tbl[] = {
 	{ 0xfb, 0x2b, 0xac }, /* PIO mode 0 */
@@ -92,7 +92,7 @@ static struct pdc2027x_pio_timing {
 	{ 0x23, 0x09, 0x25 }, /* PIO mode 4, IORDY on, Prefetch off */
 };
 
-static struct pdc2027x_mdma_timing {
+static const struct pdc2027x_mdma_timing {
 	u8 value0, value1;
 } pdc2027x_mdma_timing_tbl[] = {
 	{ 0xdf, 0x5f }, /* MDMA mode 0 */
@@ -100,7 +100,7 @@ static struct pdc2027x_mdma_timing {
 	{ 0x69, 0x25 }, /* MDMA mode 2 */
 };
 
-static struct pdc2027x_udma_timing {
+static const struct pdc2027x_udma_timing {
 	u8 value0, value1, value2;
 } pdc2027x_udma_timing_tbl[] = {
 	{ 0x4a, 0x0f, 0xd5 }, /* UDMA mode 0 */
@@ -580,7 +580,7 @@ static void pdc_adjust_pll(struct ata_host *host, long pll_clock, unsigned int b
 	ioread16(mmio_base + PDC_PLL_CTL); /* flush */
 
 	/* Wait the PLL circuit to be stable */
-	mdelay(30);
+	msleep(30);
 
 #ifdef PDC_DEBUG
 	/*
@@ -620,7 +620,7 @@ static long pdc_detect_pll_input_clock(struct ata_host *host)
 	start_time = ktime_get();
 
 	/* Let the counter run for 100 ms. */
-	mdelay(100);
+	msleep(100);
 
 	/* Read the counter values again */
 	end_count = pdc_read_counter(host);
@@ -649,7 +649,7 @@ static long pdc_detect_pll_input_clock(struct ata_host *host)
  * @host: target ATA host
  * @board_idx: board identifier
  */
-static int pdc_hardware_init(struct ata_host *host, unsigned int board_idx)
+static void pdc_hardware_init(struct ata_host *host, unsigned int board_idx)
 {
 	long pll_clock;
 
@@ -665,8 +665,6 @@ static int pdc_hardware_init(struct ata_host *host, unsigned int board_idx)
 
 	/* Adjust PLL control register */
 	pdc_adjust_pll(host, pll_clock, board_idx);
-
-	return 0;
 }
 
 /**
@@ -753,8 +751,7 @@ static int pdc2027x_init_one(struct pci_dev *pdev,
 	//pci_enable_intx(pdev);
 
 	/* initialize adapter */
-	if (pdc_hardware_init(host, board_idx) != 0)
-		return -EIO;
+	pdc_hardware_init(host, board_idx);
 
 	pci_set_master(pdev);
 	return ata_host_activate(host, pdev->irq, ata_bmdma_interrupt,
@@ -778,8 +775,7 @@ static int pdc2027x_reinit_one(struct pci_dev *pdev)
 	else
 		board_idx = PDC_UDMA_133;
 
-	if (pdc_hardware_init(host, board_idx))
-		return -EIO;
+	pdc_hardware_init(host, board_idx);
 
 	ata_host_resume(host);
 	return 0;
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index cc208b72b199..42d4589b43d4 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -3596,7 +3596,7 @@ static void mv_reset_channel(struct mv_host_priv *hpriv, void __iomem *mmio,
 	hpriv->ops->phy_errata(hpriv, mmio, port_no);
 
 	if (IS_GEN_I(hpriv))
-		mdelay(1);
+		usleep_range(500, 1000);
 }
 
 static void mv_pmp_select(struct ata_port *ap, int pmp)
diff --git a/drivers/atm/ambassador.c b/drivers/atm/ambassador.c
index dd286ad404f8..9287ec958b70 100644
--- a/drivers/atm/ambassador.c
+++ b/drivers/atm/ambassador.c
@@ -2258,7 +2258,7 @@ static int amb_probe(struct pci_dev *pci_dev,
 
 	PRINTD (DBG_INFO, "registered Madge ATM adapter (no. %d) (%p) at %p",
 		dev->atm_dev->number, dev, dev->atm_dev);
-		dev->atm_dev->dev_data = (void *) dev;
+	dev->atm_dev->dev_data = (void *) dev;
 
 	// register our address
 	amb_esi (dev, dev->atm_dev->esi);
diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index ce47eb17901d..6470e3c4c990 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -473,7 +473,7 @@ static int do_rx_dma(struct atm_vcc *vcc,struct sk_buff *skb,
 		ENI_PRV_POS(skb) = eni_vcc->descr+size+1;
 		skb_queue_tail(&eni_dev->rx_queue,skb);
 		eni_vcc->last = skb;
-rx_enqueued++;
+		rx_enqueued++;
 	}
 	eni_vcc->descr = here;
 	eni_out(dma_wr,MID_DMA_WR_RX);
@@ -715,7 +715,7 @@ static void get_service(struct atm_dev *dev)
 			else eni_dev->slow = vcc;
 			eni_dev->last_slow = vcc;
 		}
-putting++;
+		putting++;
 		ENI_VCC(vcc)->servicing++;
 	}
 }
@@ -744,7 +744,7 @@ static void dequeue_rx(struct atm_dev *dev)
 		}
 		EVENT("dequeued (size=%ld,pos=0x%lx)\n",ENI_PRV_SIZE(skb),
 		    ENI_PRV_POS(skb));
-rx_dequeued++;
+		rx_dequeued++;
 		vcc = ATM_SKB(skb)->vcc;
 		eni_vcc = ENI_VCC(vcc);
 		first = 0;
@@ -1174,7 +1174,7 @@ DPRINTK("doing direct send\n"); /* @@@ well, this doesn't work anyway */
 	DPRINTK("dma_wr set to %d, tx_pos is now %ld\n",dma_wr,tx->tx_pos);
 	eni_out(dma_wr,MID_DMA_WR_TX);
 	skb_queue_tail(&eni_dev->tx_queue,skb);
-queued++;
+	queued++;
 	return enq_ok;
 }
 
@@ -1195,7 +1195,7 @@ static void poll_tx(struct atm_dev *dev)
 				if (res == enq_ok) continue;
 				DPRINTK("re-queuing TX PDU\n");
 				skb_queue_head(&tx->backlog,skb);
-requeued++;
+				requeued++;
 				if (res == enq_jam) return;
 				break;
 			}
@@ -1232,7 +1232,7 @@ static void dequeue_tx(struct atm_dev *dev)
 		else dev_kfree_skb_irq(skb);
 		atomic_inc(&vcc->stats->tx);
 		wake_up(&eni_dev->tx_wait);
-dma_complete++;
+		dma_complete++;
 	}
 }
 
@@ -1555,7 +1555,7 @@ static void eni_tasklet(unsigned long data)
 	}
 	if (events & MID_TX_COMPLETE) {
 		EVENT("INT: TX COMPLETE\n",0,0);
-tx_complete++;
+		tx_complete++;
 		wake_up(&eni_dev->tx_wait);
 		/* poll_rx ? */
 	}
@@ -2069,14 +2069,14 @@ static int eni_send(struct atm_vcc *vcc,struct sk_buff *skb)
 		}
 		*(u32 *) skb->data = htonl(*(u32 *) skb->data);
 	}
-submitted++;
+	submitted++;
 	ATM_SKB(skb)->vcc = vcc;
 	tasklet_disable(&ENI_DEV(vcc->dev)->task);
 	res = do_tx(skb);
 	tasklet_enable(&ENI_DEV(vcc->dev)->task);
 	if (res == enq_ok) return 0;
 	skb_queue_tail(&ENI_VCC(vcc)->tx->backlog,skb);
-backlogged++;
+	backlogged++;
 	tasklet_schedule(&ENI_DEV(vcc->dev)->task);
 	return 0;
 }
diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c
index 126855e6cb7d..6ebc4e4820fc 100644
--- a/drivers/atm/fore200e.c
+++ b/drivers/atm/fore200e.c
@@ -3083,8 +3083,8 @@ fore200e_proc_read(struct atm_dev *dev, loff_t* pos, char* page)
 	    ASSERT(fore200e_vcc);
 
 	    len = sprintf(page,
-			  "  %08x  %03d %05d %1d   %09lu %05d/%05d      %09lu %05d/%05d\n",
-			  (u32)(unsigned long)vcc,
+			  "  %pK  %03d %05d %1d   %09lu %05d/%05d      %09lu %05d/%05d\n",
+			  vcc,
 			  vcc->vpi, vcc->vci, fore200e_atm2fore_aal(vcc->qos.aal),
 			  fore200e_vcc->tx_pdu,
 			  fore200e_vcc->tx_min_pdu > 0xFFFF ? 0 : fore200e_vcc->tx_min_pdu,
diff --git a/drivers/atm/lanai.c b/drivers/atm/lanai.c
index 6664aa50789e..5f8e009b2da1 100644
--- a/drivers/atm/lanai.c
+++ b/drivers/atm/lanai.c
@@ -1586,8 +1586,8 @@ static int service_buffer_allocate(struct lanai_dev *lanai)
 	    lanai->pci);
 	if (unlikely(lanai->service.start == NULL))
 		return -ENOMEM;
-	DPRINTK("allocated service buffer at 0x%08lX, size %zu(%d)\n",
-	    (unsigned long) lanai->service.start,
+	DPRINTK("allocated service buffer at %p, size %zu(%d)\n",
+	    lanai->service.start,
 	    lanai_buf_size(&lanai->service),
 	    lanai_buf_size_cardorder(&lanai->service));
 	/* Clear ServWrite register to be safe */
@@ -2218,9 +2218,9 @@ static int lanai_dev_open(struct atm_dev *atmdev)
 #endif
 	memcpy(atmdev->esi, eeprom_mac(lanai), ESI_LEN);
 	lanai_timed_poll_start(lanai);
-	printk(KERN_NOTICE DEV_LABEL "(itf %d): rev.%d, base=0x%lx, irq=%u "
+	printk(KERN_NOTICE DEV_LABEL "(itf %d): rev.%d, base=%p, irq=%u "
 		"(%pMF)\n", lanai->number, (int) lanai->pci->revision,
-		(unsigned long) lanai->base, lanai->pci->irq, atmdev->esi);
+		lanai->base, lanai->pci->irq, atmdev->esi);
 	printk(KERN_NOTICE DEV_LABEL "(itf %d): LANAI%s, serialno=%u(0x%X), "
 	    "board_rev=%d\n", lanai->number,
 	    lanai->type==lanai2 ? "2" : "HB", (unsigned int) lanai->serialno,
diff --git a/drivers/atm/suni.c b/drivers/atm/suni.c
index b8825f2d79e0..4b044710a8cf 100644
--- a/drivers/atm/suni.c
+++ b/drivers/atm/suni.c
@@ -177,7 +177,7 @@ static int set_loopback(struct atm_dev *dev,int mode)
 		default:
 			return -EINVAL;
 	}
-	 dev->ops->phy_put(dev, control, reg);
+	dev->ops->phy_put(dev, control, reg);
 	PRIV(dev)->loop_mode = mode;
 	return 0;
 }
diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig
index d7d21118d3e0..2c2ed9cf8796 100644
--- a/drivers/auxdisplay/Kconfig
+++ b/drivers/auxdisplay/Kconfig
@@ -136,6 +136,7 @@ config CFAG12864B_RATE
 
 config IMG_ASCII_LCD
 	tristate "Imagination Technologies ASCII LCD Display"
+	depends on HAS_IOMEM
 	default y if MIPS_MALTA || MIPS_SEAD3
 	select SYSCON
 	help
diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c
index db040b378224..9180b9bd5821 100644
--- a/drivers/auxdisplay/img-ascii-lcd.c
+++ b/drivers/auxdisplay/img-ascii-lcd.c
@@ -441,3 +441,7 @@ static struct platform_driver img_ascii_lcd_driver = {
 	.remove	= img_ascii_lcd_remove,
 };
 module_platform_driver(img_ascii_lcd_driver);
+
+MODULE_DESCRIPTION("Imagination Technologies ASCII LCD Display");
+MODULE_AUTHOR("Paul Burton <paul.burton@mips.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 2f6614c9a229..29b0eb452b3a 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -86,35 +86,18 @@ config FW_LOADER
 	  require userspace firmware loading support, but a module built
 	  out-of-tree does.
 
-config FIRMWARE_IN_KERNEL
-	bool "Include in-kernel firmware blobs in kernel binary"
-	depends on FW_LOADER
-	default y
-	help
-	  The kernel source tree includes a number of firmware 'blobs'
-	  that are used by various drivers. The recommended way to
-	  use these is to run "make firmware_install", which, after
-	  converting ihex files to binary, copies all of the needed
-	  binary files in firmware/ to /lib/firmware/ on your system so
-	  that they can be loaded by userspace helpers on request.
-
-	  Enabling this option will build each required firmware blob
-	  into the kernel directly, where request_firmware() will find
-	  them without having to call out to userspace. This may be
-	  useful if your root file system requires a device that uses
-	  such firmware and do not wish to use an initrd.
-
-	  This single option controls the inclusion of firmware for
-	  every driver that uses request_firmware() and ships its
-	  firmware in the kernel source tree, which avoids a
-	  proliferation of 'Include firmware for xxx device' options.
-
-	  Say 'N' and let firmware be loaded from userspace.
-
 config EXTRA_FIRMWARE
 	string "External firmware blobs to build into the kernel binary"
 	depends on FW_LOADER
 	help
+	  Various drivers in the kernel source tree may require firmware,
+	  which is generally available in your distribution's linux-firmware
+	  package.
+
+	  The linux-firmware package should install firmware into
+	  /lib/firmware/ on your system, so they can be loaded by userspace
+	  helpers on request.
+
 	  This option allows firmware to be built into the kernel for the case
 	  where the user either cannot or doesn't want to provide it from
 	  userspace at runtime (for example, when the firmware in question is
@@ -125,11 +108,11 @@ config EXTRA_FIRMWARE
 	  firmware files -- the same names that appear in MODULE_FIRMWARE()
 	  and request_firmware() in the source. These files should exist under
 	  the directory specified by the EXTRA_FIRMWARE_DIR option, which is
-	  by default the firmware subdirectory of the kernel source tree.
+	  /lib/firmware by default.
 
 	  For example, you might set CONFIG_EXTRA_FIRMWARE="usb8388.bin", copy
-	  the usb8388.bin file into the firmware directory, and build the kernel.
-	  Then any request_firmware("usb8388.bin") will be satisfied internally
+	  the usb8388.bin file into /lib/firmware, and build the kernel. Then
+	  any request_firmware("usb8388.bin") will be satisfied internally
 	  without needing to call out to userspace.
 
 	  WARNING: If you include additional firmware files into your binary
@@ -235,6 +218,9 @@ config GENERIC_CPU_DEVICES
 config GENERIC_CPU_AUTOPROBE
 	bool
 
+config GENERIC_CPU_VULNERABILITIES
+	bool
+
 config SOC_BUS
 	bool
 	select GLOB
@@ -245,6 +231,7 @@ config DMA_SHARED_BUFFER
 	bool
 	default n
 	select ANON_INODES
+	select IRQ_WORK
 	help
 	  This option enables the framework for buffer-sharing between
 	  multiple drivers. A buffer is associated with a file using driver
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 4de87b0b53c8..52ec5174bcb1 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -1,15 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Arch specific cpu topology information
  *
  * Copyright (C) 2016, ARM Ltd.
  * Written by: Juri Lelli, ARM Ltd.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Released under the GPLv2 only.
- * SPDX-License-Identifier: GPL-2.0
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/base/attribute_container.c b/drivers/base/attribute_container.c
index 95e3ef82f3b7..20736aaa0e69 100644
--- a/drivers/base/attribute_container.c
+++ b/drivers/base/attribute_container.c
@@ -1,10 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * attribute_container.c - implementation of a simple container for classes
  *
  * Copyright (c) 2005 - James Bottomley <James.Bottomley@steeleye.com>
  *
- * This file is licensed under GPLv2
- *
  * The basic idea here is to enable a device to be attached to an
  * aritrary numer of classes without having to allocate storage for them.
  * Instead, the contained classes select the devices they need to attach
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 22a64fd3309b..ef6183306b40 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * bus.c - bus driver management
  *
@@ -5,9 +6,6 @@
  * Copyright (c) 2002-3 Open Source Development Labs
  * Copyright (c) 2007 Greg Kroah-Hartman <gregkh@suse.de>
  * Copyright (c) 2007 Novell Inc.
- *
- * This file is released under the GPLv2
- *
  */
 
 #include <linux/async.h>
@@ -309,7 +307,7 @@ int bus_for_each_dev(struct bus_type *bus, struct device *start,
 
 	klist_iter_init_node(&bus->p->klist_devices, &i,
 			     (start ? &start->p->knode_bus : NULL));
-	while ((dev = next_device(&i)) && !error)
+	while (!error && (dev = next_device(&i)))
 		error = fn(dev, data);
 	klist_iter_exit(&i);
 	return error;
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index eb3af2739537..edf726267282 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * cacheinfo support - processor cache information via sysfs
  *
  * Based on arch/x86/kernel/cpu/intel_cacheinfo.c
  * Author: Sudeep Holla <sudeep.holla@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
@@ -186,6 +175,11 @@ static void cache_associativity(struct cacheinfo *this_leaf)
 		this_leaf->ways_of_associativity = (size / nr_sets) / line_size;
 }
 
+static bool cache_node_is_unified(struct cacheinfo *this_leaf)
+{
+	return of_property_read_bool(this_leaf->of_node, "cache-unified");
+}
+
 static void cache_of_override_properties(unsigned int cpu)
 {
 	int index;
@@ -194,6 +188,14 @@ static void cache_of_override_properties(unsigned int cpu)
 
 	for (index = 0; index < cache_leaves(cpu); index++) {
 		this_leaf = this_cpu_ci->info_list + index;
+		/*
+		 * init_cache_level must setup the cache level correctly
+		 * overriding the architecturally specified levels, so
+		 * if type is NONE at this stage, it should be unified
+		 */
+		if (this_leaf->type == CACHE_TYPE_NOCACHE &&
+		    cache_node_is_unified(this_leaf))
+			this_leaf->type = CACHE_TYPE_UNIFIED;
 		cache_size(this_leaf);
 		cache_get_line_size(this_leaf);
 		cache_nr_sets(this_leaf);
diff --git a/drivers/base/class.c b/drivers/base/class.c
index 52eb8e644acd..54def4e02f00 100644
--- a/drivers/base/class.c
+++ b/drivers/base/class.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * class.c - basic device class management
  *
@@ -5,9 +6,6 @@
  * Copyright (c) 2002-3 Open Source Development Labs
  * Copyright (c) 2003-2004 Greg Kroah-Hartman
  * Copyright (c) 2003-2004 IBM Corp.
- *
- * This file is released under the GPLv2
- *
  */
 
 #include <linux/device.h>
diff --git a/drivers/base/component.c b/drivers/base/component.c
index 89b032f2ffd2..8946dfee4768 100644
--- a/drivers/base/component.c
+++ b/drivers/base/component.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Componentized device handling.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * This is work in progress.  We gather up the component devices into a list,
  * and bind them when instructed.  At the moment, we're specific to the DRM
  * subsystem, and only handles one master device, but this doesn't have to be
@@ -17,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/debugfs.h>
 
 struct component;
 
@@ -41,6 +39,7 @@ struct master {
 	const struct component_master_ops *ops;
 	struct device *dev;
 	struct component_match *match;
+	struct dentry *dentry;
 };
 
 struct component {
@@ -56,6 +55,80 @@ static DEFINE_MUTEX(component_mutex);
 static LIST_HEAD(component_list);
 static LIST_HEAD(masters);
 
+#ifdef CONFIG_DEBUG_FS
+
+static struct dentry *component_debugfs_dir;
+
+static int component_devices_show(struct seq_file *s, void *data)
+{
+	struct master *m = s->private;
+	struct component_match *match = m->match;
+	size_t i;
+
+	mutex_lock(&component_mutex);
+	seq_printf(s, "%-40s %20s\n", "master name", "status");
+	seq_puts(s, "-------------------------------------------------------------\n");
+	seq_printf(s, "%-40s %20s\n\n",
+		   dev_name(m->dev), m->bound ? "bound" : "not bound");
+
+	seq_printf(s, "%-40s %20s\n", "device name", "status");
+	seq_puts(s, "-------------------------------------------------------------\n");
+	for (i = 0; i < match->num; i++) {
+		struct device *d = (struct device *)match->compare[i].data;
+
+		seq_printf(s, "%-40s %20s\n", dev_name(d),
+			   match->compare[i].component ?
+			   "registered" : "not registered");
+	}
+	mutex_unlock(&component_mutex);
+
+	return 0;
+}
+
+static int component_devices_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, component_devices_show, inode->i_private);
+}
+
+static const struct file_operations component_devices_fops = {
+	.open = component_devices_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init component_debug_init(void)
+{
+	component_debugfs_dir = debugfs_create_dir("device_component", NULL);
+
+	return 0;
+}
+
+core_initcall(component_debug_init);
+
+static void component_master_debugfs_add(struct master *m)
+{
+	m->dentry = debugfs_create_file(dev_name(m->dev), 0444,
+					component_debugfs_dir,
+					m, &component_devices_fops);
+}
+
+static void component_master_debugfs_del(struct master *m)
+{
+	debugfs_remove(m->dentry);
+	m->dentry = NULL;
+}
+
+#else
+
+static void component_master_debugfs_add(struct master *m)
+{ }
+
+static void component_master_debugfs_del(struct master *m)
+{ }
+
+#endif
+
 static struct master *__master_find(struct device *dev,
 	const struct component_master_ops *ops)
 {
@@ -290,6 +363,7 @@ static void free_master(struct master *master)
 	struct component_match *match = master->match;
 	int i;
 
+	component_master_debugfs_del(master);
 	list_del(&master->node);
 
 	if (match) {
@@ -323,6 +397,7 @@ int component_master_add_with_match(struct device *dev,
 	master->ops = ops;
 	master->match = match;
 
+	component_master_debugfs_add(master);
 	/* Add to the list of available masters. */
 	mutex_lock(&component_mutex);
 	list_add(&master->node, &masters);
diff --git a/drivers/base/container.c b/drivers/base/container.c
index ecbfbe2e908f..1ba42d2d3532 100644
--- a/drivers/base/container.c
+++ b/drivers/base/container.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * System bus type for containers.
  *
  * Copyright (C) 2013, Intel Corporation
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/container.h>
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 110230d86527..b2261f92f2f1 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * drivers/base/core.c - core driver model code (device registration, etc)
  *
@@ -5,9 +6,6 @@
  * Copyright (c) 2002-3 Open Source Development Labs
  * Copyright (c) 2006 Greg Kroah-Hartman <gregkh@suse.de>
  * Copyright (c) 2006 Novell, Inc.
- *
- * This file is released under the GPLv2
- *
  */
 
 #include <linux/device.h>
@@ -22,7 +20,6 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/genhd.h>
-#include <linux/kallsyms.h>
 #include <linux/mutex.h>
 #include <linux/pm_runtime.h>
 #include <linux/netdevice.h>
@@ -687,8 +684,8 @@ static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr,
 	if (dev_attr->show)
 		ret = dev_attr->show(dev, dev_attr, buf);
 	if (ret >= (ssize_t)PAGE_SIZE) {
-		print_symbol("dev_attr_show: %s returned bad count\n",
-				(unsigned long)dev_attr->show);
+		printk("dev_attr_show: %pS returned bad count\n",
+				dev_attr->show);
 	}
 	return ret;
 }
@@ -2116,7 +2113,7 @@ int device_for_each_child(struct device *parent, void *data,
 		return 0;
 
 	klist_iter_init(&parent->p->klist_children, &i);
-	while ((child = next_device(&i)) && !error)
+	while (!error && (child = next_device(&i)))
 		error = fn(child, data);
 	klist_iter_exit(&i);
 	return error;
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 58a9b608d821..d21a2d913107 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * CPU subsystem support
  */
@@ -511,10 +512,58 @@ static void __init cpu_dev_register_generic(void)
 #endif
 }
 
+#ifdef CONFIG_GENERIC_CPU_VULNERABILITIES
+
+ssize_t __weak cpu_show_meltdown(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
+ssize_t __weak cpu_show_spectre_v1(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
+ssize_t __weak cpu_show_spectre_v2(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
+static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
+static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
+static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
+
+static struct attribute *cpu_root_vulnerabilities_attrs[] = {
+	&dev_attr_meltdown.attr,
+	&dev_attr_spectre_v1.attr,
+	&dev_attr_spectre_v2.attr,
+	NULL
+};
+
+static const struct attribute_group cpu_root_vulnerabilities_group = {
+	.name  = "vulnerabilities",
+	.attrs = cpu_root_vulnerabilities_attrs,
+};
+
+static void __init cpu_register_vulnerabilities(void)
+{
+	if (sysfs_create_group(&cpu_subsys.dev_root->kobj,
+			       &cpu_root_vulnerabilities_group))
+		pr_err("Unable to register CPU vulnerabilities\n");
+}
+
+#else
+static inline void cpu_register_vulnerabilities(void) { }
+#endif
+
 void __init cpu_dev_init(void)
 {
 	if (subsys_system_register(&cpu_subsys, cpu_root_attr_groups))
 		panic("Failed to register CPU subsystem");
 
 	cpu_dev_register_generic();
+	cpu_register_vulnerabilities();
 }
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 2c964f56dafe..de6fd092bf2f 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * drivers/base/dd.c - The core device/driver interactions.
  *
@@ -13,8 +14,6 @@
  * Copyright (c) 2002-3 Open Source Development Labs
  * Copyright (c) 2007-2009 Greg Kroah-Hartman <gregkh@suse.de>
  * Copyright (c) 2007-2009 Novell Inc.
- *
- * This file is released under the GPLv2
  */
 
 #include <linux/device.h>
@@ -289,6 +288,18 @@ static void driver_bound(struct device *dev)
 	kobject_uevent(&dev->kobj, KOBJ_BIND);
 }
 
+static ssize_t coredump_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	device_lock(dev);
+	if (dev->driver->coredump)
+		dev->driver->coredump(dev);
+	device_unlock(dev);
+
+	return count;
+}
+static DEVICE_ATTR_WO(coredump);
+
 static int driver_sysfs_add(struct device *dev)
 {
 	int ret;
@@ -298,14 +309,26 @@ static int driver_sysfs_add(struct device *dev)
 					     BUS_NOTIFY_BIND_DRIVER, dev);
 
 	ret = sysfs_create_link(&dev->driver->p->kobj, &dev->kobj,
+				kobject_name(&dev->kobj));
+	if (ret)
+		goto fail;
+
+	ret = sysfs_create_link(&dev->kobj, &dev->driver->p->kobj,
+				"driver");
+	if (ret)
+		goto rm_dev;
+
+	if (!IS_ENABLED(CONFIG_DEV_COREDUMP) || !dev->driver->coredump ||
+	    !device_create_file(dev, &dev_attr_coredump))
+		return 0;
+
+	sysfs_remove_link(&dev->kobj, "driver");
+
+rm_dev:
+	sysfs_remove_link(&dev->driver->p->kobj,
 			  kobject_name(&dev->kobj));
-	if (ret == 0) {
-		ret = sysfs_create_link(&dev->kobj, &dev->driver->p->kobj,
-					"driver");
-		if (ret)
-			sysfs_remove_link(&dev->driver->p->kobj,
-					kobject_name(&dev->kobj));
-	}
+
+fail:
 	return ret;
 }
 
@@ -314,6 +337,8 @@ static void driver_sysfs_remove(struct device *dev)
 	struct device_driver *drv = dev->driver;
 
 	if (drv) {
+		if (drv->coredump)
+			device_remove_file(dev, &dev_attr_coredump);
 		sysfs_remove_link(&drv->p->kobj, kobject_name(&dev->kobj));
 		sysfs_remove_link(&dev->kobj, "driver");
 	}
diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c
index 7be310f7db73..f1a3353f3494 100644
--- a/drivers/base/devcoredump.c
+++ b/drivers/base/devcoredump.c
@@ -1,23 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * This file is provided under the GPLv2 license.
- *
- * GPL LICENSE SUMMARY
- *
  * Copyright(c) 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 Intel Deutschland GmbH
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * The full GNU General Public License is included in this distribution
- * in the file called COPYING.
- *
  * Contact Information:
  *  Intel Linux Wireless <ilw@linux.intel.com>
  * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 71d577025285..95b67281cd2a 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -1,10 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * drivers/base/devres.c - device resource management
  *
  * Copyright (c) 2006  SUSE Linux Products GmbH
  * Copyright (c) 2006  Tejun Heo <teheo@suse.de>
- *
- * This file is released under the GPLv2.
  */
 
 #include <linux/device.h>
diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index ea9726e71468..d987dcd1bd56 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Contiguous Memory Allocator for DMA mapping framework
  * Copyright (c) 2010-2011 by Samsung Electronics.
  * Written by:
  *	Marek Szyprowski <m.szyprowski@samsung.com>
  *	Michal Nazarewicz <mina86@mina86.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License or (at your optional) any later version of the license.
  */
 
 #define pr_fmt(fmt) "cma: " fmt
diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c
index e584eddef0a7..3b118353ea17 100644
--- a/drivers/base/dma-mapping.c
+++ b/drivers/base/dma-mapping.c
@@ -1,10 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * drivers/base/dma-mapping.c - arch-independent dma-mapping routines
  *
  * Copyright (c) 2006  SUSE Linux Products GmbH
  * Copyright (c) 2006  Tejun Heo <teheo@suse.de>
- *
- * This file is released under the GPLv2.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/base/driver.c b/drivers/base/driver.c
index 4eabfe28d2b3..ba912558a510 100644
--- a/drivers/base/driver.c
+++ b/drivers/base/driver.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * driver.c - centralized device driver management
  *
@@ -5,9 +6,6 @@
  * Copyright (c) 2002-3 Open Source Development Labs
  * Copyright (c) 2007 Greg Kroah-Hartman <gregkh@suse.de>
  * Copyright (c) 2007 Novell Inc.
- *
- * This file is released under the GPLv2
- *
  */
 
 #include <linux/device.h>
@@ -52,7 +50,7 @@ int driver_for_each_device(struct device_driver *drv, struct device *start,
 
 	klist_iter_init_node(&drv->p->klist_devices, &i,
 			     start ? &start->p->knode_driver : NULL);
-	while ((dev = next_device(&i)) && !error)
+	while (!error && (dev = next_device(&i)))
 		error = fn(dev, data);
 	klist_iter_exit(&i);
 	return error;
diff --git a/drivers/base/firmware.c b/drivers/base/firmware.c
index 113815556809..8dff940e0db9 100644
--- a/drivers/base/firmware.c
+++ b/drivers/base/firmware.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * firmware.c - firmware subsystem hoohaw.
  *
@@ -5,8 +6,6 @@
  * Copyright (c) 2002-3 Open Source Development Labs
  * Copyright (c) 2007 Greg Kroah-Hartman <gregkh@suse.de>
  * Copyright (c) 2007 Novell Inc.
- *
- * This file is released under the GPLv2
  */
 #include <linux/kobject.h>
 #include <linux/module.h>
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 4b57cf5bc81d..7dd36ace6152 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * firmware_class.c - Multi purpose firmware loading support
  *
@@ -41,6 +42,96 @@ MODULE_AUTHOR("Manuel Estrada Sainz");
 MODULE_DESCRIPTION("Multi purpose firmware loading support");
 MODULE_LICENSE("GPL");
 
+enum fw_status {
+	FW_STATUS_UNKNOWN,
+	FW_STATUS_LOADING,
+	FW_STATUS_DONE,
+	FW_STATUS_ABORTED,
+};
+
+/*
+ * Concurrent request_firmware() for the same firmware need to be
+ * serialized.  struct fw_state is simple state machine which hold the
+ * state of the firmware loading.
+ */
+struct fw_state {
+	struct completion completion;
+	enum fw_status status;
+};
+
+/* firmware behavior options */
+#define FW_OPT_UEVENT	(1U << 0)
+#define FW_OPT_NOWAIT	(1U << 1)
+#define FW_OPT_USERHELPER	(1U << 2)
+#define FW_OPT_NO_WARN	(1U << 3)
+#define FW_OPT_NOCACHE	(1U << 4)
+#define FW_OPT_NOFALLBACK (1U << 5)
+
+struct firmware_cache {
+	/* firmware_buf instance will be added into the below list */
+	spinlock_t lock;
+	struct list_head head;
+	int state;
+
+#ifdef CONFIG_PM_SLEEP
+	/*
+	 * Names of firmware images which have been cached successfully
+	 * will be added into the below list so that device uncache
+	 * helper can trace which firmware images have been cached
+	 * before.
+	 */
+	spinlock_t name_lock;
+	struct list_head fw_names;
+
+	struct delayed_work work;
+
+	struct notifier_block   pm_notify;
+#endif
+};
+
+struct fw_priv {
+	struct kref ref;
+	struct list_head list;
+	struct firmware_cache *fwc;
+	struct fw_state fw_st;
+	void *data;
+	size_t size;
+	size_t allocated_size;
+#ifdef CONFIG_FW_LOADER_USER_HELPER
+	bool is_paged_buf;
+	bool need_uevent;
+	struct page **pages;
+	int nr_pages;
+	int page_array_size;
+	struct list_head pending_list;
+#endif
+	const char *fw_name;
+};
+
+struct fw_cache_entry {
+	struct list_head list;
+	const char *name;
+};
+
+struct fw_name_devm {
+	unsigned long magic;
+	const char *name;
+};
+
+static inline struct fw_priv *to_fw_priv(struct kref *ref)
+{
+	return container_of(ref, struct fw_priv, ref);
+}
+
+#define	FW_LOADER_NO_CACHE	0
+#define	FW_LOADER_START_CACHE	1
+
+/* fw_lock could be moved to 'struct fw_sysfs' but since it is just
+ * guarding for corner cases a global lock should be OK */
+static DEFINE_MUTEX(fw_lock);
+
+static struct firmware_cache fw_cache;
+
 /* Builtin firmware support */
 
 #ifdef CONFIG_FW_LOADER
@@ -48,6 +139,14 @@ MODULE_LICENSE("GPL");
 extern struct builtin_fw __start_builtin_fw[];
 extern struct builtin_fw __end_builtin_fw[];
 
+static void fw_copy_to_prealloc_buf(struct firmware *fw,
+				    void *buf, size_t size)
+{
+	if (!buf || size < fw->size)
+		return;
+	memcpy(buf, fw->data, fw->size);
+}
+
 static bool fw_get_builtin_firmware(struct firmware *fw, const char *name,
 				    void *buf, size_t size)
 {
@@ -57,9 +156,8 @@ static bool fw_get_builtin_firmware(struct firmware *fw, const char *name,
 		if (strcmp(name, b_fw->name) == 0) {
 			fw->size = b_fw->size;
 			fw->data = b_fw->data;
+			fw_copy_to_prealloc_buf(fw, buf, size);
 
-			if (buf && fw->size <= size)
-				memcpy(buf, fw->data, fw->size);
 			return true;
 		}
 	}
@@ -93,13 +191,6 @@ static inline bool fw_is_builtin_firmware(const struct firmware *fw)
 }
 #endif
 
-enum fw_status {
-	FW_STATUS_UNKNOWN,
-	FW_STATUS_LOADING,
-	FW_STATUS_DONE,
-	FW_STATUS_ABORTED,
-};
-
 static int loading_timeout = 60;	/* In seconds */
 
 static inline long firmware_loading_timeout(void)
@@ -107,29 +198,17 @@ static inline long firmware_loading_timeout(void)
 	return loading_timeout > 0 ? loading_timeout * HZ : MAX_JIFFY_OFFSET;
 }
 
-/*
- * Concurrent request_firmware() for the same firmware need to be
- * serialized.  struct fw_state is simple state machine which hold the
- * state of the firmware loading.
- */
-struct fw_state {
-	struct completion completion;
-	enum fw_status status;
-};
-
-static void fw_state_init(struct fw_state *fw_st)
+static void fw_state_init(struct fw_priv *fw_priv)
 {
+	struct fw_state *fw_st = &fw_priv->fw_st;
+
 	init_completion(&fw_st->completion);
 	fw_st->status = FW_STATUS_UNKNOWN;
 }
 
-static inline bool __fw_state_is_done(enum fw_status status)
-{
-	return status == FW_STATUS_DONE || status == FW_STATUS_ABORTED;
-}
-
-static int __fw_state_wait_common(struct fw_state *fw_st, long timeout)
+static int __fw_state_wait_common(struct fw_priv *fw_priv, long timeout)
 {
+	struct fw_state *fw_st = &fw_priv->fw_st;
 	long ret;
 
 	ret = wait_for_completion_killable_timeout(&fw_st->completion, timeout);
@@ -141,226 +220,172 @@ static int __fw_state_wait_common(struct fw_state *fw_st, long timeout)
 	return ret < 0 ? ret : 0;
 }
 
-static void __fw_state_set(struct fw_state *fw_st,
+static void __fw_state_set(struct fw_priv *fw_priv,
 			   enum fw_status status)
 {
+	struct fw_state *fw_st = &fw_priv->fw_st;
+
 	WRITE_ONCE(fw_st->status, status);
 
 	if (status == FW_STATUS_DONE || status == FW_STATUS_ABORTED)
 		complete_all(&fw_st->completion);
 }
 
-#define fw_state_start(fw_st)					\
-	__fw_state_set(fw_st, FW_STATUS_LOADING)
-#define fw_state_done(fw_st)					\
-	__fw_state_set(fw_st, FW_STATUS_DONE)
-#define fw_state_aborted(fw_st)					\
-	__fw_state_set(fw_st, FW_STATUS_ABORTED)
-#define fw_state_wait(fw_st)					\
-	__fw_state_wait_common(fw_st, MAX_SCHEDULE_TIMEOUT)
-
-static int __fw_state_check(struct fw_state *fw_st, enum fw_status status)
+static inline void fw_state_start(struct fw_priv *fw_priv)
 {
-	return fw_st->status == status;
+	__fw_state_set(fw_priv, FW_STATUS_LOADING);
 }
 
-#define fw_state_is_aborted(fw_st)				\
-	__fw_state_check(fw_st, FW_STATUS_ABORTED)
-
-#ifdef CONFIG_FW_LOADER_USER_HELPER
-
-#define fw_state_aborted(fw_st)					\
-	__fw_state_set(fw_st, FW_STATUS_ABORTED)
-#define fw_state_is_done(fw_st)					\
-	__fw_state_check(fw_st, FW_STATUS_DONE)
-#define fw_state_is_loading(fw_st)				\
-	__fw_state_check(fw_st, FW_STATUS_LOADING)
-#define fw_state_wait_timeout(fw_st, timeout)			\
-	__fw_state_wait_common(fw_st, timeout)
-
-#endif /* CONFIG_FW_LOADER_USER_HELPER */
+static inline void fw_state_done(struct fw_priv *fw_priv)
+{
+	__fw_state_set(fw_priv, FW_STATUS_DONE);
+}
 
-/* firmware behavior options */
-#define FW_OPT_UEVENT	(1U << 0)
-#define FW_OPT_NOWAIT	(1U << 1)
-#ifdef CONFIG_FW_LOADER_USER_HELPER
-#define FW_OPT_USERHELPER	(1U << 2)
-#else
-#define FW_OPT_USERHELPER	0
-#endif
-#ifdef CONFIG_FW_LOADER_USER_HELPER_FALLBACK
-#define FW_OPT_FALLBACK		FW_OPT_USERHELPER
-#else
-#define FW_OPT_FALLBACK		0
-#endif
-#define FW_OPT_NO_WARN	(1U << 3)
-#define FW_OPT_NOCACHE	(1U << 4)
+static inline void fw_state_aborted(struct fw_priv *fw_priv)
+{
+	__fw_state_set(fw_priv, FW_STATUS_ABORTED);
+}
 
-struct firmware_cache {
-	/* firmware_buf instance will be added into the below list */
-	spinlock_t lock;
-	struct list_head head;
-	int state;
+static inline int fw_state_wait(struct fw_priv *fw_priv)
+{
+	return __fw_state_wait_common(fw_priv, MAX_SCHEDULE_TIMEOUT);
+}
 
-#ifdef CONFIG_PM_SLEEP
-	/*
-	 * Names of firmware images which have been cached successfully
-	 * will be added into the below list so that device uncache
-	 * helper can trace which firmware images have been cached
-	 * before.
-	 */
-	spinlock_t name_lock;
-	struct list_head fw_names;
+static bool __fw_state_check(struct fw_priv *fw_priv,
+			     enum fw_status status)
+{
+	struct fw_state *fw_st = &fw_priv->fw_st;
 
-	struct delayed_work work;
+	return fw_st->status == status;
+}
 
-	struct notifier_block   pm_notify;
-#endif
-};
+static inline bool fw_state_is_aborted(struct fw_priv *fw_priv)
+{
+	return __fw_state_check(fw_priv, FW_STATUS_ABORTED);
+}
 
-struct firmware_buf {
-	struct kref ref;
-	struct list_head list;
-	struct firmware_cache *fwc;
-	struct fw_state fw_st;
-	void *data;
-	size_t size;
-	size_t allocated_size;
 #ifdef CONFIG_FW_LOADER_USER_HELPER
-	bool is_paged_buf;
-	bool need_uevent;
-	struct page **pages;
-	int nr_pages;
-	int page_array_size;
-	struct list_head pending_list;
-#endif
-	const char *fw_id;
-};
 
-struct fw_cache_entry {
-	struct list_head list;
-	const char *name;
-};
+static inline bool fw_sysfs_done(struct fw_priv *fw_priv)
+{
+	return __fw_state_check(fw_priv, FW_STATUS_DONE);
+}
 
-struct fw_name_devm {
-	unsigned long magic;
-	const char *name;
-};
+static inline bool fw_sysfs_loading(struct fw_priv *fw_priv)
+{
+	return __fw_state_check(fw_priv, FW_STATUS_LOADING);
+}
 
-#define to_fwbuf(d) container_of(d, struct firmware_buf, ref)
+static inline int fw_sysfs_wait_timeout(struct fw_priv *fw_priv,  long timeout)
+{
+	return __fw_state_wait_common(fw_priv, timeout);
+}
 
-#define	FW_LOADER_NO_CACHE	0
-#define	FW_LOADER_START_CACHE	1
+#endif /* CONFIG_FW_LOADER_USER_HELPER */
 
 static int fw_cache_piggyback_on_request(const char *name);
 
-/* fw_lock could be moved to 'struct firmware_priv' but since it is just
- * guarding for corner cases a global lock should be OK */
-static DEFINE_MUTEX(fw_lock);
-
-static struct firmware_cache fw_cache;
-
-static struct firmware_buf *__allocate_fw_buf(const char *fw_name,
-					      struct firmware_cache *fwc,
-					      void *dbuf, size_t size)
+static struct fw_priv *__allocate_fw_priv(const char *fw_name,
+					  struct firmware_cache *fwc,
+					  void *dbuf, size_t size)
 {
-	struct firmware_buf *buf;
+	struct fw_priv *fw_priv;
 
-	buf = kzalloc(sizeof(*buf), GFP_ATOMIC);
-	if (!buf)
+	fw_priv = kzalloc(sizeof(*fw_priv), GFP_ATOMIC);
+	if (!fw_priv)
 		return NULL;
 
-	buf->fw_id = kstrdup_const(fw_name, GFP_ATOMIC);
-	if (!buf->fw_id) {
-		kfree(buf);
+	fw_priv->fw_name = kstrdup_const(fw_name, GFP_ATOMIC);
+	if (!fw_priv->fw_name) {
+		kfree(fw_priv);
 		return NULL;
 	}
 
-	kref_init(&buf->ref);
-	buf->fwc = fwc;
-	buf->data = dbuf;
-	buf->allocated_size = size;
-	fw_state_init(&buf->fw_st);
+	kref_init(&fw_priv->ref);
+	fw_priv->fwc = fwc;
+	fw_priv->data = dbuf;
+	fw_priv->allocated_size = size;
+	fw_state_init(fw_priv);
 #ifdef CONFIG_FW_LOADER_USER_HELPER
-	INIT_LIST_HEAD(&buf->pending_list);
+	INIT_LIST_HEAD(&fw_priv->pending_list);
 #endif
 
-	pr_debug("%s: fw-%s buf=%p\n", __func__, fw_name, buf);
+	pr_debug("%s: fw-%s fw_priv=%p\n", __func__, fw_name, fw_priv);
 
-	return buf;
+	return fw_priv;
 }
 
-static struct firmware_buf *__fw_lookup_buf(const char *fw_name)
+static struct fw_priv *__lookup_fw_priv(const char *fw_name)
 {
-	struct firmware_buf *tmp;
+	struct fw_priv *tmp;
 	struct firmware_cache *fwc = &fw_cache;
 
 	list_for_each_entry(tmp, &fwc->head, list)
-		if (!strcmp(tmp->fw_id, fw_name))
+		if (!strcmp(tmp->fw_name, fw_name))
 			return tmp;
 	return NULL;
 }
 
 /* Returns 1 for batching firmware requests with the same name */
-static int fw_lookup_and_allocate_buf(const char *fw_name,
-				      struct firmware_cache *fwc,
-				      struct firmware_buf **buf, void *dbuf,
-				      size_t size)
+static int alloc_lookup_fw_priv(const char *fw_name,
+				struct firmware_cache *fwc,
+				struct fw_priv **fw_priv, void *dbuf,
+				size_t size)
 {
-	struct firmware_buf *tmp;
+	struct fw_priv *tmp;
 
 	spin_lock(&fwc->lock);
-	tmp = __fw_lookup_buf(fw_name);
+	tmp = __lookup_fw_priv(fw_name);
 	if (tmp) {
 		kref_get(&tmp->ref);
 		spin_unlock(&fwc->lock);
-		*buf = tmp;
-		pr_debug("batched request - sharing the same struct firmware_buf and lookup for multiple requests\n");
+		*fw_priv = tmp;
+		pr_debug("batched request - sharing the same struct fw_priv and lookup for multiple requests\n");
 		return 1;
 	}
-	tmp = __allocate_fw_buf(fw_name, fwc, dbuf, size);
+	tmp = __allocate_fw_priv(fw_name, fwc, dbuf, size);
 	if (tmp)
 		list_add(&tmp->list, &fwc->head);
 	spin_unlock(&fwc->lock);
 
-	*buf = tmp;
+	*fw_priv = tmp;
 
 	return tmp ? 0 : -ENOMEM;
 }
 
-static void __fw_free_buf(struct kref *ref)
+static void __free_fw_priv(struct kref *ref)
 	__releases(&fwc->lock)
 {
-	struct firmware_buf *buf = to_fwbuf(ref);
-	struct firmware_cache *fwc = buf->fwc;
+	struct fw_priv *fw_priv = to_fw_priv(ref);
+	struct firmware_cache *fwc = fw_priv->fwc;
 
-	pr_debug("%s: fw-%s buf=%p data=%p size=%u\n",
-		 __func__, buf->fw_id, buf, buf->data,
-		 (unsigned int)buf->size);
+	pr_debug("%s: fw-%s fw_priv=%p data=%p size=%u\n",
+		 __func__, fw_priv->fw_name, fw_priv, fw_priv->data,
+		 (unsigned int)fw_priv->size);
 
-	list_del(&buf->list);
+	list_del(&fw_priv->list);
 	spin_unlock(&fwc->lock);
 
 #ifdef CONFIG_FW_LOADER_USER_HELPER
-	if (buf->is_paged_buf) {
+	if (fw_priv->is_paged_buf) {
 		int i;
-		vunmap(buf->data);
-		for (i = 0; i < buf->nr_pages; i++)
-			__free_page(buf->pages[i]);
-		vfree(buf->pages);
+		vunmap(fw_priv->data);
+		for (i = 0; i < fw_priv->nr_pages; i++)
+			__free_page(fw_priv->pages[i]);
+		vfree(fw_priv->pages);
 	} else
 #endif
-	if (!buf->allocated_size)
-		vfree(buf->data);
-	kfree_const(buf->fw_id);
-	kfree(buf);
+	if (!fw_priv->allocated_size)
+		vfree(fw_priv->data);
+	kfree_const(fw_priv->fw_name);
+	kfree(fw_priv);
 }
 
-static void fw_free_buf(struct firmware_buf *buf)
+static void free_fw_priv(struct fw_priv *fw_priv)
 {
-	struct firmware_cache *fwc = buf->fwc;
+	struct firmware_cache *fwc = fw_priv->fwc;
 	spin_lock(&fwc->lock);
-	if (!kref_put(&buf->ref, __fw_free_buf))
+	if (!kref_put(&fw_priv->ref, __free_fw_priv))
 		spin_unlock(&fwc->lock);
 }
 
@@ -383,7 +408,7 @@ module_param_string(path, fw_path_para, sizeof(fw_path_para), 0644);
 MODULE_PARM_DESC(path, "customized firmware image search path with a higher priority than default path");
 
 static int
-fw_get_filesystem_firmware(struct device *device, struct firmware_buf *buf)
+fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv)
 {
 	loff_t size;
 	int i, len;
@@ -393,9 +418,9 @@ fw_get_filesystem_firmware(struct device *device, struct firmware_buf *buf)
 	size_t msize = INT_MAX;
 
 	/* Already populated data member means we're loading into a buffer */
-	if (buf->data) {
+	if (fw_priv->data) {
 		id = READING_FIRMWARE_PREALLOC_BUFFER;
-		msize = buf->allocated_size;
+		msize = fw_priv->allocated_size;
 	}
 
 	path = __getname();
@@ -408,15 +433,15 @@ fw_get_filesystem_firmware(struct device *device, struct firmware_buf *buf)
 			continue;
 
 		len = snprintf(path, PATH_MAX, "%s/%s",
-			       fw_path[i], buf->fw_id);
+			       fw_path[i], fw_priv->fw_name);
 		if (len >= PATH_MAX) {
 			rc = -ENAMETOOLONG;
 			break;
 		}
 
-		buf->size = 0;
-		rc = kernel_read_file_from_path(path, &buf->data, &size, msize,
-						id);
+		fw_priv->size = 0;
+		rc = kernel_read_file_from_path(path, &fw_priv->data, &size,
+						msize, id);
 		if (rc) {
 			if (rc == -ENOENT)
 				dev_dbg(device, "loading %s failed with error %d\n",
@@ -426,9 +451,9 @@ fw_get_filesystem_firmware(struct device *device, struct firmware_buf *buf)
 					 path, rc);
 			continue;
 		}
-		dev_dbg(device, "direct-loading %s\n", buf->fw_id);
-		buf->size = size;
-		fw_state_done(&buf->fw_st);
+		dev_dbg(device, "direct-loading %s\n", fw_priv->fw_name);
+		fw_priv->size = size;
+		fw_state_done(fw_priv);
 		break;
 	}
 	__putname(path);
@@ -444,22 +469,22 @@ static void firmware_free_data(const struct firmware *fw)
 		vfree(fw->data);
 		return;
 	}
-	fw_free_buf(fw->priv);
+	free_fw_priv(fw->priv);
 }
 
 /* store the pages buffer info firmware from buf */
-static void fw_set_page_data(struct firmware_buf *buf, struct firmware *fw)
+static void fw_set_page_data(struct fw_priv *fw_priv, struct firmware *fw)
 {
-	fw->priv = buf;
+	fw->priv = fw_priv;
 #ifdef CONFIG_FW_LOADER_USER_HELPER
-	fw->pages = buf->pages;
+	fw->pages = fw_priv->pages;
 #endif
-	fw->size = buf->size;
-	fw->data = buf->data;
+	fw->size = fw_priv->size;
+	fw->data = fw_priv->data;
 
-	pr_debug("%s: fw-%s buf=%p data=%p size=%u\n",
-		 __func__, buf->fw_id, buf, buf->data,
-		 (unsigned int)buf->size);
+	pr_debug("%s: fw-%s fw_priv=%p data=%p size=%u\n",
+		 __func__, fw_priv->fw_name, fw_priv, fw_priv->data,
+		 (unsigned int)fw_priv->size);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -523,13 +548,13 @@ static int fw_add_devm_name(struct device *dev, const char *name)
 }
 #endif
 
-static int assign_firmware_buf(struct firmware *fw, struct device *device,
-			       unsigned int opt_flags)
+static int assign_fw(struct firmware *fw, struct device *device,
+		     unsigned int opt_flags)
 {
-	struct firmware_buf *buf = fw->priv;
+	struct fw_priv *fw_priv = fw->priv;
 
 	mutex_lock(&fw_lock);
-	if (!buf->size || fw_state_is_aborted(&buf->fw_st)) {
+	if (!fw_priv->size || fw_state_is_aborted(fw_priv)) {
 		mutex_unlock(&fw_lock);
 		return -ENOENT;
 	}
@@ -544,20 +569,20 @@ static int assign_firmware_buf(struct firmware *fw, struct device *device,
 	/* don't cache firmware handled without uevent */
 	if (device && (opt_flags & FW_OPT_UEVENT) &&
 	    !(opt_flags & FW_OPT_NOCACHE))
-		fw_add_devm_name(device, buf->fw_id);
+		fw_add_devm_name(device, fw_priv->fw_name);
 
 	/*
 	 * After caching firmware image is started, let it piggyback
 	 * on request firmware.
 	 */
 	if (!(opt_flags & FW_OPT_NOCACHE) &&
-	    buf->fwc->state == FW_LOADER_START_CACHE) {
-		if (fw_cache_piggyback_on_request(buf->fw_id))
-			kref_get(&buf->ref);
+	    fw_priv->fwc->state == FW_LOADER_START_CACHE) {
+		if (fw_cache_piggyback_on_request(fw_priv->fw_name))
+			kref_get(&fw_priv->ref);
 	}
 
 	/* pass the pages buffer to driver at the last minute */
-	fw_set_page_data(buf, fw);
+	fw_set_page_data(fw_priv, fw);
 	mutex_unlock(&fw_lock);
 	return 0;
 }
@@ -566,49 +591,50 @@ static int assign_firmware_buf(struct firmware *fw, struct device *device,
  * user-mode helper code
  */
 #ifdef CONFIG_FW_LOADER_USER_HELPER
-struct firmware_priv {
+struct fw_sysfs {
 	bool nowait;
 	struct device dev;
-	struct firmware_buf *buf;
+	struct fw_priv *fw_priv;
 	struct firmware *fw;
 };
 
-static struct firmware_priv *to_firmware_priv(struct device *dev)
+static struct fw_sysfs *to_fw_sysfs(struct device *dev)
 {
-	return container_of(dev, struct firmware_priv, dev);
+	return container_of(dev, struct fw_sysfs, dev);
 }
 
-static void __fw_load_abort(struct firmware_buf *buf)
+static void __fw_load_abort(struct fw_priv *fw_priv)
 {
 	/*
 	 * There is a small window in which user can write to 'loading'
 	 * between loading done and disappearance of 'loading'
 	 */
-	if (fw_state_is_done(&buf->fw_st))
+	if (fw_sysfs_done(fw_priv))
 		return;
 
-	list_del_init(&buf->pending_list);
-	fw_state_aborted(&buf->fw_st);
+	list_del_init(&fw_priv->pending_list);
+	fw_state_aborted(fw_priv);
 }
 
-static void fw_load_abort(struct firmware_priv *fw_priv)
+static void fw_load_abort(struct fw_sysfs *fw_sysfs)
 {
-	struct firmware_buf *buf = fw_priv->buf;
+	struct fw_priv *fw_priv = fw_sysfs->fw_priv;
 
-	__fw_load_abort(buf);
+	__fw_load_abort(fw_priv);
 }
 
 static LIST_HEAD(pending_fw_head);
 
 static void kill_pending_fw_fallback_reqs(bool only_kill_custom)
 {
-	struct firmware_buf *buf;
-	struct firmware_buf *next;
+	struct fw_priv *fw_priv;
+	struct fw_priv *next;
 
 	mutex_lock(&fw_lock);
-	list_for_each_entry_safe(buf, next, &pending_fw_head, pending_list) {
-		if (!buf->need_uevent || !only_kill_custom)
-			 __fw_load_abort(buf);
+	list_for_each_entry_safe(fw_priv, next, &pending_fw_head,
+				 pending_list) {
+		if (!fw_priv->need_uevent || !only_kill_custom)
+			 __fw_load_abort(fw_priv);
 	}
 	mutex_unlock(&fw_lock);
 }
@@ -651,18 +677,18 @@ ATTRIBUTE_GROUPS(firmware_class);
 
 static void fw_dev_release(struct device *dev)
 {
-	struct firmware_priv *fw_priv = to_firmware_priv(dev);
+	struct fw_sysfs *fw_sysfs = to_fw_sysfs(dev);
 
-	kfree(fw_priv);
+	kfree(fw_sysfs);
 }
 
-static int do_firmware_uevent(struct firmware_priv *fw_priv, struct kobj_uevent_env *env)
+static int do_firmware_uevent(struct fw_sysfs *fw_sysfs, struct kobj_uevent_env *env)
 {
-	if (add_uevent_var(env, "FIRMWARE=%s", fw_priv->buf->fw_id))
+	if (add_uevent_var(env, "FIRMWARE=%s", fw_sysfs->fw_priv->fw_name))
 		return -ENOMEM;
 	if (add_uevent_var(env, "TIMEOUT=%i", loading_timeout))
 		return -ENOMEM;
-	if (add_uevent_var(env, "ASYNC=%d", fw_priv->nowait))
+	if (add_uevent_var(env, "ASYNC=%d", fw_sysfs->nowait))
 		return -ENOMEM;
 
 	return 0;
@@ -670,12 +696,12 @@ static int do_firmware_uevent(struct firmware_priv *fw_priv, struct kobj_uevent_
 
 static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
-	struct firmware_priv *fw_priv = to_firmware_priv(dev);
+	struct fw_sysfs *fw_sysfs = to_fw_sysfs(dev);
 	int err = 0;
 
 	mutex_lock(&fw_lock);
-	if (fw_priv->buf)
-		err = do_firmware_uevent(fw_priv, env);
+	if (fw_sysfs->fw_priv)
+		err = do_firmware_uevent(fw_sysfs, env);
 	mutex_unlock(&fw_lock);
 	return err;
 }
@@ -687,15 +713,25 @@ static struct class firmware_class = {
 	.dev_release	= fw_dev_release,
 };
 
+static inline int register_sysfs_loader(void)
+{
+	return class_register(&firmware_class);
+}
+
+static inline void unregister_sysfs_loader(void)
+{
+	class_unregister(&firmware_class);
+}
+
 static ssize_t firmware_loading_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
-	struct firmware_priv *fw_priv = to_firmware_priv(dev);
+	struct fw_sysfs *fw_sysfs = to_fw_sysfs(dev);
 	int loading = 0;
 
 	mutex_lock(&fw_lock);
-	if (fw_priv->buf)
-		loading = fw_state_is_loading(&fw_priv->buf->fw_st);
+	if (fw_sysfs->fw_priv)
+		loading = fw_sysfs_loading(fw_sysfs->fw_priv);
 	mutex_unlock(&fw_lock);
 
 	return sprintf(buf, "%d\n", loading);
@@ -707,14 +743,15 @@ static ssize_t firmware_loading_show(struct device *dev,
 #endif
 
 /* one pages buffer should be mapped/unmapped only once */
-static int fw_map_pages_buf(struct firmware_buf *buf)
+static int map_fw_priv_pages(struct fw_priv *fw_priv)
 {
-	if (!buf->is_paged_buf)
+	if (!fw_priv->is_paged_buf)
 		return 0;
 
-	vunmap(buf->data);
-	buf->data = vmap(buf->pages, buf->nr_pages, 0, PAGE_KERNEL_RO);
-	if (!buf->data)
+	vunmap(fw_priv->data);
+	fw_priv->data = vmap(fw_priv->pages, fw_priv->nr_pages, 0,
+			     PAGE_KERNEL_RO);
+	if (!fw_priv->data)
 		return -ENOMEM;
 	return 0;
 }
@@ -736,32 +773,32 @@ static ssize_t firmware_loading_store(struct device *dev,
 				      struct device_attribute *attr,
 				      const char *buf, size_t count)
 {
-	struct firmware_priv *fw_priv = to_firmware_priv(dev);
-	struct firmware_buf *fw_buf;
+	struct fw_sysfs *fw_sysfs = to_fw_sysfs(dev);
+	struct fw_priv *fw_priv;
 	ssize_t written = count;
 	int loading = simple_strtol(buf, NULL, 10);
 	int i;
 
 	mutex_lock(&fw_lock);
-	fw_buf = fw_priv->buf;
-	if (fw_state_is_aborted(&fw_buf->fw_st))
+	fw_priv = fw_sysfs->fw_priv;
+	if (fw_state_is_aborted(fw_priv))
 		goto out;
 
 	switch (loading) {
 	case 1:
 		/* discarding any previous partial load */
-		if (!fw_state_is_done(&fw_buf->fw_st)) {
-			for (i = 0; i < fw_buf->nr_pages; i++)
-				__free_page(fw_buf->pages[i]);
-			vfree(fw_buf->pages);
-			fw_buf->pages = NULL;
-			fw_buf->page_array_size = 0;
-			fw_buf->nr_pages = 0;
-			fw_state_start(&fw_buf->fw_st);
+		if (!fw_sysfs_done(fw_priv)) {
+			for (i = 0; i < fw_priv->nr_pages; i++)
+				__free_page(fw_priv->pages[i]);
+			vfree(fw_priv->pages);
+			fw_priv->pages = NULL;
+			fw_priv->page_array_size = 0;
+			fw_priv->nr_pages = 0;
+			fw_state_start(fw_priv);
 		}
 		break;
 	case 0:
-		if (fw_state_is_loading(&fw_buf->fw_st)) {
+		if (fw_sysfs_loading(fw_priv)) {
 			int rc;
 
 			/*
@@ -770,25 +807,25 @@ static ssize_t firmware_loading_store(struct device *dev,
 			 * see the mapped 'buf->data' once the loading
 			 * is completed.
 			 * */
-			rc = fw_map_pages_buf(fw_buf);
+			rc = map_fw_priv_pages(fw_priv);
 			if (rc)
 				dev_err(dev, "%s: map pages failed\n",
 					__func__);
 			else
 				rc = security_kernel_post_read_file(NULL,
-						fw_buf->data, fw_buf->size,
+						fw_priv->data, fw_priv->size,
 						READING_FIRMWARE);
 
 			/*
 			 * Same logic as fw_load_abort, only the DONE bit
 			 * is ignored and we set ABORT only on failure.
 			 */
-			list_del_init(&fw_buf->pending_list);
+			list_del_init(&fw_priv->pending_list);
 			if (rc) {
-				fw_state_aborted(&fw_buf->fw_st);
+				fw_state_aborted(fw_priv);
 				written = rc;
 			} else {
-				fw_state_done(&fw_buf->fw_st);
+				fw_state_done(fw_priv);
 			}
 			break;
 		}
@@ -797,7 +834,7 @@ static ssize_t firmware_loading_store(struct device *dev,
 		dev_err(dev, "%s: unexpected value (%d)\n", __func__, loading);
 		/* fallthrough */
 	case -1:
-		fw_load_abort(fw_priv);
+		fw_load_abort(fw_sysfs);
 		break;
 	}
 out:
@@ -807,16 +844,16 @@ out:
 
 static DEVICE_ATTR(loading, 0644, firmware_loading_show, firmware_loading_store);
 
-static void firmware_rw_buf(struct firmware_buf *buf, char *buffer,
+static void firmware_rw_data(struct fw_priv *fw_priv, char *buffer,
 			   loff_t offset, size_t count, bool read)
 {
 	if (read)
-		memcpy(buffer, buf->data + offset, count);
+		memcpy(buffer, fw_priv->data + offset, count);
 	else
-		memcpy(buf->data + offset, buffer, count);
+		memcpy(fw_priv->data + offset, buffer, count);
 }
 
-static void firmware_rw(struct firmware_buf *buf, char *buffer,
+static void firmware_rw(struct fw_priv *fw_priv, char *buffer,
 			loff_t offset, size_t count, bool read)
 {
 	while (count) {
@@ -825,14 +862,14 @@ static void firmware_rw(struct firmware_buf *buf, char *buffer,
 		int page_ofs = offset & (PAGE_SIZE-1);
 		int page_cnt = min_t(size_t, PAGE_SIZE - page_ofs, count);
 
-		page_data = kmap(buf->pages[page_nr]);
+		page_data = kmap(fw_priv->pages[page_nr]);
 
 		if (read)
 			memcpy(buffer, page_data + page_ofs, page_cnt);
 		else
 			memcpy(page_data + page_ofs, buffer, page_cnt);
 
-		kunmap(buf->pages[page_nr]);
+		kunmap(fw_priv->pages[page_nr]);
 		buffer += page_cnt;
 		offset += page_cnt;
 		count -= page_cnt;
@@ -844,69 +881,69 @@ static ssize_t firmware_data_read(struct file *filp, struct kobject *kobj,
 				  char *buffer, loff_t offset, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
-	struct firmware_priv *fw_priv = to_firmware_priv(dev);
-	struct firmware_buf *buf;
+	struct fw_sysfs *fw_sysfs = to_fw_sysfs(dev);
+	struct fw_priv *fw_priv;
 	ssize_t ret_count;
 
 	mutex_lock(&fw_lock);
-	buf = fw_priv->buf;
-	if (!buf || fw_state_is_done(&buf->fw_st)) {
+	fw_priv = fw_sysfs->fw_priv;
+	if (!fw_priv || fw_sysfs_done(fw_priv)) {
 		ret_count = -ENODEV;
 		goto out;
 	}
-	if (offset > buf->size) {
+	if (offset > fw_priv->size) {
 		ret_count = 0;
 		goto out;
 	}
-	if (count > buf->size - offset)
-		count = buf->size - offset;
+	if (count > fw_priv->size - offset)
+		count = fw_priv->size - offset;
 
 	ret_count = count;
 
-	if (buf->data)
-		firmware_rw_buf(buf, buffer, offset, count, true);
+	if (fw_priv->data)
+		firmware_rw_data(fw_priv, buffer, offset, count, true);
 	else
-		firmware_rw(buf, buffer, offset, count, true);
+		firmware_rw(fw_priv, buffer, offset, count, true);
 
 out:
 	mutex_unlock(&fw_lock);
 	return ret_count;
 }
 
-static int fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size)
+static int fw_realloc_pages(struct fw_sysfs *fw_sysfs, int min_size)
 {
-	struct firmware_buf *buf = fw_priv->buf;
+	struct fw_priv *fw_priv= fw_sysfs->fw_priv;
 	int pages_needed = PAGE_ALIGN(min_size) >> PAGE_SHIFT;
 
 	/* If the array of pages is too small, grow it... */
-	if (buf->page_array_size < pages_needed) {
+	if (fw_priv->page_array_size < pages_needed) {
 		int new_array_size = max(pages_needed,
-					 buf->page_array_size * 2);
+					 fw_priv->page_array_size * 2);
 		struct page **new_pages;
 
 		new_pages = vmalloc(new_array_size * sizeof(void *));
 		if (!new_pages) {
-			fw_load_abort(fw_priv);
+			fw_load_abort(fw_sysfs);
 			return -ENOMEM;
 		}
-		memcpy(new_pages, buf->pages,
-		       buf->page_array_size * sizeof(void *));
-		memset(&new_pages[buf->page_array_size], 0, sizeof(void *) *
-		       (new_array_size - buf->page_array_size));
-		vfree(buf->pages);
-		buf->pages = new_pages;
-		buf->page_array_size = new_array_size;
+		memcpy(new_pages, fw_priv->pages,
+		       fw_priv->page_array_size * sizeof(void *));
+		memset(&new_pages[fw_priv->page_array_size], 0, sizeof(void *) *
+		       (new_array_size - fw_priv->page_array_size));
+		vfree(fw_priv->pages);
+		fw_priv->pages = new_pages;
+		fw_priv->page_array_size = new_array_size;
 	}
 
-	while (buf->nr_pages < pages_needed) {
-		buf->pages[buf->nr_pages] =
+	while (fw_priv->nr_pages < pages_needed) {
+		fw_priv->pages[fw_priv->nr_pages] =
 			alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
 
-		if (!buf->pages[buf->nr_pages]) {
-			fw_load_abort(fw_priv);
+		if (!fw_priv->pages[fw_priv->nr_pages]) {
+			fw_load_abort(fw_sysfs);
 			return -ENOMEM;
 		}
-		buf->nr_pages++;
+		fw_priv->nr_pages++;
 	}
 	return 0;
 }
@@ -928,37 +965,37 @@ static ssize_t firmware_data_write(struct file *filp, struct kobject *kobj,
 				   char *buffer, loff_t offset, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
-	struct firmware_priv *fw_priv = to_firmware_priv(dev);
-	struct firmware_buf *buf;
+	struct fw_sysfs *fw_sysfs = to_fw_sysfs(dev);
+	struct fw_priv *fw_priv;
 	ssize_t retval;
 
 	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
 
 	mutex_lock(&fw_lock);
-	buf = fw_priv->buf;
-	if (!buf || fw_state_is_done(&buf->fw_st)) {
+	fw_priv = fw_sysfs->fw_priv;
+	if (!fw_priv || fw_sysfs_done(fw_priv)) {
 		retval = -ENODEV;
 		goto out;
 	}
 
-	if (buf->data) {
-		if (offset + count > buf->allocated_size) {
+	if (fw_priv->data) {
+		if (offset + count > fw_priv->allocated_size) {
 			retval = -ENOMEM;
 			goto out;
 		}
-		firmware_rw_buf(buf, buffer, offset, count, false);
+		firmware_rw_data(fw_priv, buffer, offset, count, false);
 		retval = count;
 	} else {
-		retval = fw_realloc_buffer(fw_priv, offset + count);
+		retval = fw_realloc_pages(fw_sysfs, offset + count);
 		if (retval)
 			goto out;
 
 		retval = count;
-		firmware_rw(buf, buffer, offset, count, false);
+		firmware_rw(fw_priv, buffer, offset, count, false);
 	}
 
-	buf->size = max_t(size_t, offset + count, buf->size);
+	fw_priv->size = max_t(size_t, offset + count, fw_priv->size);
 out:
 	mutex_unlock(&fw_lock);
 	return retval;
@@ -991,22 +1028,22 @@ static const struct attribute_group *fw_dev_attr_groups[] = {
 	NULL
 };
 
-static struct firmware_priv *
+static struct fw_sysfs *
 fw_create_instance(struct firmware *firmware, const char *fw_name,
 		   struct device *device, unsigned int opt_flags)
 {
-	struct firmware_priv *fw_priv;
+	struct fw_sysfs *fw_sysfs;
 	struct device *f_dev;
 
-	fw_priv = kzalloc(sizeof(*fw_priv), GFP_KERNEL);
-	if (!fw_priv) {
-		fw_priv = ERR_PTR(-ENOMEM);
+	fw_sysfs = kzalloc(sizeof(*fw_sysfs), GFP_KERNEL);
+	if (!fw_sysfs) {
+		fw_sysfs = ERR_PTR(-ENOMEM);
 		goto exit;
 	}
 
-	fw_priv->nowait = !!(opt_flags & FW_OPT_NOWAIT);
-	fw_priv->fw = firmware;
-	f_dev = &fw_priv->dev;
+	fw_sysfs->nowait = !!(opt_flags & FW_OPT_NOWAIT);
+	fw_sysfs->fw = firmware;
+	f_dev = &fw_sysfs->dev;
 
 	device_initialize(f_dev);
 	dev_set_name(f_dev, "%s", fw_name);
@@ -1014,20 +1051,20 @@ fw_create_instance(struct firmware *firmware, const char *fw_name,
 	f_dev->class = &firmware_class;
 	f_dev->groups = fw_dev_attr_groups;
 exit:
-	return fw_priv;
+	return fw_sysfs;
 }
 
 /* load a firmware via user helper */
-static int _request_firmware_load(struct firmware_priv *fw_priv,
+static int _request_firmware_load(struct fw_sysfs *fw_sysfs,
 				  unsigned int opt_flags, long timeout)
 {
 	int retval = 0;
-	struct device *f_dev = &fw_priv->dev;
-	struct firmware_buf *buf = fw_priv->buf;
+	struct device *f_dev = &fw_sysfs->dev;
+	struct fw_priv *fw_priv = fw_sysfs->fw_priv;
 
 	/* fall back on userspace loading */
-	if (!buf->data)
-		buf->is_paged_buf = true;
+	if (!fw_priv->data)
+		fw_priv->is_paged_buf = true;
 
 	dev_set_uevent_suppress(f_dev, true);
 
@@ -1038,31 +1075,31 @@ static int _request_firmware_load(struct firmware_priv *fw_priv,
 	}
 
 	mutex_lock(&fw_lock);
-	list_add(&buf->pending_list, &pending_fw_head);
+	list_add(&fw_priv->pending_list, &pending_fw_head);
 	mutex_unlock(&fw_lock);
 
 	if (opt_flags & FW_OPT_UEVENT) {
-		buf->need_uevent = true;
+		fw_priv->need_uevent = true;
 		dev_set_uevent_suppress(f_dev, false);
-		dev_dbg(f_dev, "firmware: requesting %s\n", buf->fw_id);
-		kobject_uevent(&fw_priv->dev.kobj, KOBJ_ADD);
+		dev_dbg(f_dev, "firmware: requesting %s\n", fw_priv->fw_name);
+		kobject_uevent(&fw_sysfs->dev.kobj, KOBJ_ADD);
 	} else {
 		timeout = MAX_JIFFY_OFFSET;
 	}
 
-	retval = fw_state_wait_timeout(&buf->fw_st, timeout);
+	retval = fw_sysfs_wait_timeout(fw_priv, timeout);
 	if (retval < 0) {
 		mutex_lock(&fw_lock);
-		fw_load_abort(fw_priv);
+		fw_load_abort(fw_sysfs);
 		mutex_unlock(&fw_lock);
 	}
 
-	if (fw_state_is_aborted(&buf->fw_st)) {
+	if (fw_state_is_aborted(fw_priv)) {
 		if (retval == -ERESTARTSYS)
 			retval = -EINTR;
 		else
 			retval = -EAGAIN;
-	} else if (buf->is_paged_buf && !buf->data)
+	} else if (fw_priv->is_paged_buf && !fw_priv->data)
 		retval = -ENOMEM;
 
 	device_del(f_dev);
@@ -1075,7 +1112,7 @@ static int fw_load_from_user_helper(struct firmware *firmware,
 				    const char *name, struct device *device,
 				    unsigned int opt_flags)
 {
-	struct firmware_priv *fw_priv;
+	struct fw_sysfs *fw_sysfs;
 	long timeout;
 	int ret;
 
@@ -1096,17 +1133,17 @@ static int fw_load_from_user_helper(struct firmware *firmware,
 		}
 	}
 
-	fw_priv = fw_create_instance(firmware, name, device, opt_flags);
-	if (IS_ERR(fw_priv)) {
-		ret = PTR_ERR(fw_priv);
+	fw_sysfs = fw_create_instance(firmware, name, device, opt_flags);
+	if (IS_ERR(fw_sysfs)) {
+		ret = PTR_ERR(fw_sysfs);
 		goto out_unlock;
 	}
 
-	fw_priv->buf = firmware->priv;
-	ret = _request_firmware_load(fw_priv, opt_flags, timeout);
+	fw_sysfs->fw_priv = firmware->priv;
+	ret = _request_firmware_load(fw_sysfs, opt_flags, timeout);
 
 	if (!ret)
-		ret = assign_firmware_buf(firmware, device, opt_flags);
+		ret = assign_fw(firmware, device, opt_flags);
 
 out_unlock:
 	usermodehelper_read_unlock();
@@ -1114,16 +1151,60 @@ out_unlock:
 	return ret;
 }
 
+#ifdef CONFIG_FW_LOADER_USER_HELPER_FALLBACK
+static bool fw_force_sysfs_fallback(unsigned int opt_flags)
+{
+	return true;
+}
+#else
+static bool fw_force_sysfs_fallback(unsigned int opt_flags)
+{
+	if (!(opt_flags & FW_OPT_USERHELPER))
+		return false;
+	return true;
+}
+#endif
+
+static bool fw_run_sysfs_fallback(unsigned int opt_flags)
+{
+	if ((opt_flags & FW_OPT_NOFALLBACK))
+		return false;
+
+	return fw_force_sysfs_fallback(opt_flags);
+}
+
+static int fw_sysfs_fallback(struct firmware *fw, const char *name,
+			    struct device *device,
+			    unsigned int opt_flags,
+			    int ret)
+{
+	if (!fw_run_sysfs_fallback(opt_flags))
+		return ret;
+
+	dev_warn(device, "Falling back to user helper\n");
+	return fw_load_from_user_helper(fw, name, device, opt_flags);
+}
 #else /* CONFIG_FW_LOADER_USER_HELPER */
-static inline int
-fw_load_from_user_helper(struct firmware *firmware, const char *name,
-			 struct device *device, unsigned int opt_flags)
+static int fw_sysfs_fallback(struct firmware *fw, const char *name,
+			     struct device *device,
+			     unsigned int opt_flags,
+			     int ret)
 {
-	return -ENOENT;
+	/* Keep carrying over the same error */
+	return ret;
 }
 
 static inline void kill_pending_fw_fallback_reqs(bool only_kill_custom) { }
 
+static inline int register_sysfs_loader(void)
+{
+	return 0;
+}
+
+static inline void unregister_sysfs_loader(void)
+{
+}
+
 #endif /* CONFIG_FW_LOADER_USER_HELPER */
 
 /* prepare firmware and firmware_buf structs;
@@ -1135,7 +1216,7 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name,
 			  struct device *device, void *dbuf, size_t size)
 {
 	struct firmware *firmware;
-	struct firmware_buf *buf;
+	struct fw_priv *fw_priv;
 	int ret;
 
 	*firmware_p = firmware = kzalloc(sizeof(*firmware), GFP_KERNEL);
@@ -1150,18 +1231,18 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name,
 		return 0; /* assigned */
 	}
 
-	ret = fw_lookup_and_allocate_buf(name, &fw_cache, &buf, dbuf, size);
+	ret = alloc_lookup_fw_priv(name, &fw_cache, &fw_priv, dbuf, size);
 
 	/*
-	 * bind with 'buf' now to avoid warning in failure path
+	 * bind with 'priv' now to avoid warning in failure path
 	 * of requesting firmware.
 	 */
-	firmware->priv = buf;
+	firmware->priv = fw_priv;
 
 	if (ret > 0) {
-		ret = fw_state_wait(&buf->fw_st);
+		ret = fw_state_wait(fw_priv);
 		if (!ret) {
-			fw_set_page_data(buf, firmware);
+			fw_set_page_data(fw_priv, firmware);
 			return 0; /* assigned */
 		}
 	}
@@ -1177,20 +1258,20 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name,
  * released until the last user calls release_firmware().
  *
  * Failed batched requests are possible as well, in such cases we just share
- * the struct firmware_buf and won't release it until all requests are woken
+ * the struct fw_priv and won't release it until all requests are woken
  * and have gone through this same path.
  */
 static void fw_abort_batch_reqs(struct firmware *fw)
 {
-	struct firmware_buf *buf;
+	struct fw_priv *fw_priv;
 
 	/* Loaded directly? */
 	if (!fw || !fw->priv)
 		return;
 
-	buf = fw->priv;
-	if (!fw_state_is_aborted(&buf->fw_st))
-		fw_state_aborted(&buf->fw_st);
+	fw_priv = fw->priv;
+	if (!fw_state_is_aborted(fw_priv))
+		fw_state_aborted(fw_priv);
 }
 
 /* called from request_firmware() and request_firmware_work_func() */
@@ -1220,13 +1301,9 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 			dev_warn(device,
 				 "Direct firmware load for %s failed with error %d\n",
 				 name, ret);
-		if (opt_flags & FW_OPT_USERHELPER) {
-			dev_warn(device, "Falling back to user helper\n");
-			ret = fw_load_from_user_helper(fw, name, device,
-						       opt_flags);
-		}
+		ret = fw_sysfs_fallback(fw, name, device, opt_flags, ret);
 	} else
-		ret = assign_firmware_buf(fw, device, opt_flags);
+		ret = assign_fw(fw, device, opt_flags);
 
  out:
 	if (ret < 0) {
@@ -1268,7 +1345,7 @@ request_firmware(const struct firmware **firmware_p, const char *name,
 	/* Need to pin this module until return */
 	__module_get(THIS_MODULE);
 	ret = _request_firmware(firmware_p, name, device, NULL, 0,
-				FW_OPT_UEVENT | FW_OPT_FALLBACK);
+				FW_OPT_UEVENT);
 	module_put(THIS_MODULE);
 	return ret;
 }
@@ -1292,7 +1369,8 @@ int request_firmware_direct(const struct firmware **firmware_p,
 
 	__module_get(THIS_MODULE);
 	ret = _request_firmware(firmware_p, name, device, NULL, 0,
-				FW_OPT_UEVENT | FW_OPT_NO_WARN);
+				FW_OPT_UEVENT | FW_OPT_NO_WARN |
+				FW_OPT_NOFALLBACK);
 	module_put(THIS_MODULE);
 	return ret;
 }
@@ -1321,8 +1399,7 @@ request_firmware_into_buf(const struct firmware **firmware_p, const char *name,
 
 	__module_get(THIS_MODULE);
 	ret = _request_firmware(firmware_p, name, device, buf, size,
-				FW_OPT_UEVENT | FW_OPT_FALLBACK |
-				FW_OPT_NOCACHE);
+				FW_OPT_UEVENT | FW_OPT_NOCACHE);
 	module_put(THIS_MODULE);
 	return ret;
 }
@@ -1414,7 +1491,7 @@ request_firmware_nowait(
 	fw_work->device = device;
 	fw_work->context = context;
 	fw_work->cont = cont;
-	fw_work->opt_flags = FW_OPT_NOWAIT | FW_OPT_FALLBACK |
+	fw_work->opt_flags = FW_OPT_NOWAIT |
 		(uevent ? FW_OPT_UEVENT : FW_OPT_USERHELPER);
 
 	if (!try_module_get(module)) {
@@ -1463,13 +1540,13 @@ static int cache_firmware(const char *fw_name)
 	return ret;
 }
 
-static struct firmware_buf *fw_lookup_buf(const char *fw_name)
+static struct fw_priv *lookup_fw_priv(const char *fw_name)
 {
-	struct firmware_buf *tmp;
+	struct fw_priv *tmp;
 	struct firmware_cache *fwc = &fw_cache;
 
 	spin_lock(&fwc->lock);
-	tmp = __fw_lookup_buf(fw_name);
+	tmp = __lookup_fw_priv(fw_name);
 	spin_unlock(&fwc->lock);
 
 	return tmp;
@@ -1488,7 +1565,7 @@ static struct firmware_buf *fw_lookup_buf(const char *fw_name)
  */
 static int uncache_firmware(const char *fw_name)
 {
-	struct firmware_buf *buf;
+	struct fw_priv *fw_priv;
 	struct firmware fw;
 
 	pr_debug("%s: %s\n", __func__, fw_name);
@@ -1496,9 +1573,9 @@ static int uncache_firmware(const char *fw_name)
 	if (fw_get_builtin_firmware(&fw, fw_name, NULL, 0))
 		return 0;
 
-	buf = fw_lookup_buf(fw_name);
-	if (buf) {
-		fw_free_buf(buf);
+	fw_priv = lookup_fw_priv(fw_name);
+	if (fw_priv) {
+		free_fw_priv(fw_priv);
 		return 0;
 	}
 
@@ -1767,20 +1844,11 @@ static int fw_suspend(void)
 static struct syscore_ops fw_syscore_ops = {
 	.suspend = fw_suspend,
 };
-#else
-static int fw_cache_piggyback_on_request(const char *name)
-{
-	return 0;
-}
-#endif
 
-static void __init fw_cache_init(void)
+static int __init register_fw_pm_ops(void)
 {
-	spin_lock_init(&fw_cache.lock);
-	INIT_LIST_HEAD(&fw_cache.head);
-	fw_cache.state = FW_LOADER_NO_CACHE;
+	int ret;
 
-#ifdef CONFIG_PM_SLEEP
 	spin_lock_init(&fw_cache.name_lock);
 	INIT_LIST_HEAD(&fw_cache.fw_names);
 
@@ -1788,10 +1856,39 @@ static void __init fw_cache_init(void)
 			  device_uncache_fw_images_work);
 
 	fw_cache.pm_notify.notifier_call = fw_pm_notify;
-	register_pm_notifier(&fw_cache.pm_notify);
+	ret = register_pm_notifier(&fw_cache.pm_notify);
+	if (ret)
+		return ret;
 
 	register_syscore_ops(&fw_syscore_ops);
+
+	return ret;
+}
+
+static inline void unregister_fw_pm_ops(void)
+{
+	unregister_syscore_ops(&fw_syscore_ops);
+	unregister_pm_notifier(&fw_cache.pm_notify);
+}
+#else
+static int fw_cache_piggyback_on_request(const char *name)
+{
+	return 0;
+}
+static inline int register_fw_pm_ops(void)
+{
+	return 0;
+}
+static inline void unregister_fw_pm_ops(void)
+{
+}
 #endif
+
+static void __init fw_cache_init(void)
+{
+	spin_lock_init(&fw_cache.lock);
+	INIT_LIST_HEAD(&fw_cache.head);
+	fw_cache.state = FW_LOADER_NO_CACHE;
 }
 
 static int fw_shutdown_notify(struct notifier_block *unused1,
@@ -1812,25 +1909,31 @@ static struct notifier_block fw_shutdown_nb = {
 
 static int __init firmware_class_init(void)
 {
+	int ret;
+
+	/* No need to unfold these on exit */
 	fw_cache_init();
-	register_reboot_notifier(&fw_shutdown_nb);
-#ifdef CONFIG_FW_LOADER_USER_HELPER
-	return class_register(&firmware_class);
-#else
-	return 0;
-#endif
+
+	ret = register_fw_pm_ops();
+	if (ret)
+		return ret;
+
+	ret = register_reboot_notifier(&fw_shutdown_nb);
+	if (ret)
+		goto out;
+
+	return register_sysfs_loader();
+
+out:
+	unregister_fw_pm_ops();
+	return ret;
 }
 
 static void __exit firmware_class_exit(void)
 {
-#ifdef CONFIG_PM_SLEEP
-	unregister_syscore_ops(&fw_syscore_ops);
-	unregister_pm_notifier(&fw_cache.pm_notify);
-#endif
+	unregister_fw_pm_ops();
 	unregister_reboot_notifier(&fw_shutdown_nb);
-#ifdef CONFIG_FW_LOADER_USER_HELPER
-	class_unregister(&firmware_class);
-#endif
+	unregister_sysfs_loader();
 }
 
 fs_initcall(firmware_class_init);
diff --git a/drivers/base/hypervisor.c b/drivers/base/hypervisor.c
index 4f8b741f4615..1ce59b4b53ce 100644
--- a/drivers/base/hypervisor.c
+++ b/drivers/base/hypervisor.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * hypervisor.c - /sys/hypervisor subsystem.
  *
  * Copyright (C) IBM Corp. 2006
  * Copyright (C) 2007 Greg Kroah-Hartman <gregkh@suse.de>
  * Copyright (C) 2007 Novell Inc.
- *
- * This file is released under the GPLv2
  */
 
 #include <linux/kobject.h>
diff --git a/drivers/base/init.c b/drivers/base/init.c
index 48c0e220acc0..dd85b05a6a16 100644
--- a/drivers/base/init.c
+++ b/drivers/base/init.c
@@ -1,8 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2002-3 Patrick Mochel
  * Copyright (c) 2002-3 Open Source Development Labs
- *
- * This file is released under the GPLv2
  */
 
 #include <linux/device.h>
diff --git a/drivers/base/isa.c b/drivers/base/isa.c
index cd6ccdcf9df0..2772f5d1948a 100644
--- a/drivers/base/isa.c
+++ b/drivers/base/isa.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * ISA bus.
  */
@@ -39,7 +40,7 @@ static int isa_bus_probe(struct device *dev)
 {
 	struct isa_driver *isa_driver = dev->platform_data;
 
-	if (isa_driver->probe)
+	if (isa_driver && isa_driver->probe)
 		return isa_driver->probe(dev, to_isa_dev(dev)->id);
 
 	return 0;
@@ -49,7 +50,7 @@ static int isa_bus_remove(struct device *dev)
 {
 	struct isa_driver *isa_driver = dev->platform_data;
 
-	if (isa_driver->remove)
+	if (isa_driver && isa_driver->remove)
 		return isa_driver->remove(dev, to_isa_dev(dev)->id);
 
 	return 0;
@@ -59,7 +60,7 @@ static void isa_bus_shutdown(struct device *dev)
 {
 	struct isa_driver *isa_driver = dev->platform_data;
 
-	if (isa_driver->shutdown)
+	if (isa_driver && isa_driver->shutdown)
 		isa_driver->shutdown(dev, to_isa_dev(dev)->id);
 }
 
@@ -67,7 +68,7 @@ static int isa_bus_suspend(struct device *dev, pm_message_t state)
 {
 	struct isa_driver *isa_driver = dev->platform_data;
 
-	if (isa_driver->suspend)
+	if (isa_driver && isa_driver->suspend)
 		return isa_driver->suspend(dev, to_isa_dev(dev)->id, state);
 
 	return 0;
@@ -77,7 +78,7 @@ static int isa_bus_resume(struct device *dev)
 {
 	struct isa_driver *isa_driver = dev->platform_data;
 
-	if (isa_driver->resume)
+	if (isa_driver && isa_driver->resume)
 		return isa_driver->resume(dev, to_isa_dev(dev)->id);
 
 	return 0;
diff --git a/drivers/base/map.c b/drivers/base/map.c
index c1d38234d725..5650ab2b247a 100644
--- a/drivers/base/map.c
+++ b/drivers/base/map.c
@@ -1,8 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  linux/drivers/base/map.c
  *
  * (C) Copyright Al Viro 2002,2003
- *	Released under GPL v2.
  *
  * NOTE: data structure needs to be changed.  It works, but for large dev_t
  * it will be too slow.  It is isolated, though, so these changes will be
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 1d60b58a8c19..fe4b24f05f6a 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -569,7 +569,7 @@ store_hard_offline_page(struct device *dev,
 	if (kstrtoull(buf, 0, &pfn) < 0)
 		return -EINVAL;
 	pfn >>= PAGE_SHIFT;
-	ret = memory_failure(pfn, 0, 0);
+	ret = memory_failure(pfn, 0);
 	return ret ? ret : count;
 }
 
diff --git a/drivers/base/module.c b/drivers/base/module.c
index 2a215780eda2..46ad4d636731 100644
--- a/drivers/base/module.c
+++ b/drivers/base/module.c
@@ -1,8 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * module.c - module sysfs fun for drivers
- *
- * This file is released under the GPLv2
- *
  */
 #include <linux/device.h>
 #include <linux/module.h>
diff --git a/drivers/base/pinctrl.c b/drivers/base/pinctrl.c
index eb929dd6ef1e..c22864458511 100644
--- a/drivers/base/pinctrl.c
+++ b/drivers/base/pinctrl.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Driver core interface to the pinctrl subsystem.
  *
@@ -6,8 +7,6 @@
  * Based on bits of regulator core, gpio core and clk core
  *
  * Author: Linus Walleij <linus.walleij@linaro.org>
- *
- * License terms: GNU General Public License (GPL) version 2
  */
 
 #include <linux/device.h>
diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
index e5473525e7b2..8e22073aeeed 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * MSI framework for platform devices
  *
  * Copyright (C) 2015 ARM Limited, All Rights Reserved.
  * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/device.h>
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index c203fb90c1a0..f1bf7b38d91c 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * platform.c - platform 'pseudo' bus for legacy devices
  *
  * Copyright (c) 2002-3 Patrick Mochel
  * Copyright (c) 2002-3 Open Source Development Labs
  *
- * This file is released under the GPLv2
- *
  * Please see Documentation/driver-model/platform.txt for more
  * information.
  */
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 0c80bea05bcb..528b24149bc7 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1032,15 +1032,12 @@ static int genpd_prepare(struct device *dev)
 static int genpd_finish_suspend(struct device *dev, bool poweroff)
 {
 	struct generic_pm_domain *genpd;
-	int ret;
+	int ret = 0;
 
 	genpd = dev_to_genpd(dev);
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	if (dev->power.wakeup_path && genpd_is_active_wakeup(genpd))
-		return 0;
-
 	if (poweroff)
 		ret = pm_generic_poweroff_noirq(dev);
 	else
@@ -1048,10 +1045,19 @@ static int genpd_finish_suspend(struct device *dev, bool poweroff)
 	if (ret)
 		return ret;
 
-	if (genpd->dev_ops.stop && genpd->dev_ops.start) {
-		ret = pm_runtime_force_suspend(dev);
-		if (ret)
+	if (dev->power.wakeup_path && genpd_is_active_wakeup(genpd))
+		return 0;
+
+	if (genpd->dev_ops.stop && genpd->dev_ops.start &&
+	    !pm_runtime_status_suspended(dev)) {
+		ret = genpd_stop_dev(genpd, dev);
+		if (ret) {
+			if (poweroff)
+				pm_generic_restore_noirq(dev);
+			else
+				pm_generic_resume_noirq(dev);
 			return ret;
+		}
 	}
 
 	genpd_lock(genpd);
@@ -1085,7 +1091,7 @@ static int genpd_suspend_noirq(struct device *dev)
 static int genpd_resume_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	int ret = 0;
+	int ret;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -1094,21 +1100,21 @@ static int genpd_resume_noirq(struct device *dev)
 		return -EINVAL;
 
 	if (dev->power.wakeup_path && genpd_is_active_wakeup(genpd))
-		return 0;
+		return pm_generic_resume_noirq(dev);
 
 	genpd_lock(genpd);
 	genpd_sync_power_on(genpd, true, 0);
 	genpd->suspended_count--;
 	genpd_unlock(genpd);
 
-	if (genpd->dev_ops.stop && genpd->dev_ops.start)
-		ret = pm_runtime_force_resume(dev);
-
-	ret = pm_generic_resume_noirq(dev);
-	if (ret)
-		return ret;
+	if (genpd->dev_ops.stop && genpd->dev_ops.start &&
+	    !pm_runtime_status_suspended(dev)) {
+		ret = genpd_start_dev(genpd, dev);
+		if (ret)
+			return ret;
+	}
 
-	return ret;
+	return pm_generic_resume_noirq(dev);
 }
 
 /**
@@ -1135,8 +1141,9 @@ static int genpd_freeze_noirq(struct device *dev)
 	if (ret)
 		return ret;
 
-	if (genpd->dev_ops.stop && genpd->dev_ops.start)
-		ret = pm_runtime_force_suspend(dev);
+	if (genpd->dev_ops.stop && genpd->dev_ops.start &&
+	    !pm_runtime_status_suspended(dev))
+		ret = genpd_stop_dev(genpd, dev);
 
 	return ret;
 }
@@ -1159,8 +1166,9 @@ static int genpd_thaw_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	if (genpd->dev_ops.stop && genpd->dev_ops.start) {
-		ret = pm_runtime_force_resume(dev);
+	if (genpd->dev_ops.stop && genpd->dev_ops.start &&
+	    !pm_runtime_status_suspended(dev)) {
+		ret = genpd_start_dev(genpd, dev);
 		if (ret)
 			return ret;
 	}
@@ -1217,8 +1225,9 @@ static int genpd_restore_noirq(struct device *dev)
 	genpd_sync_power_on(genpd, true, 0);
 	genpd_unlock(genpd);
 
-	if (genpd->dev_ops.stop && genpd->dev_ops.start) {
-		ret = pm_runtime_force_resume(dev);
+	if (genpd->dev_ops.stop && genpd->dev_ops.start &&
+	    !pm_runtime_status_suspended(dev)) {
+		ret = genpd_start_dev(genpd, dev);
 		if (ret)
 			return ret;
 	}
@@ -2199,20 +2208,8 @@ int genpd_dev_pm_attach(struct device *dev)
 
 	ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
 					"#power-domain-cells", 0, &pd_args);
-	if (ret < 0) {
-		if (ret != -ENOENT)
-			return ret;
-
-		/*
-		 * Try legacy Samsung-specific bindings
-		 * (for backwards compatibility of DT ABI)
-		 */
-		pd_args.args_count = 0;
-		pd_args.np = of_parse_phandle(dev->of_node,
-						"samsung,power-domain", 0);
-		if (!pd_args.np)
-			return -ENOENT;
-	}
+	if (ret < 0)
+		return ret;
 
 	mutex_lock(&gpd_list_lock);
 	pd = genpd_get_from_provider(&pd_args);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index db2f04415927..02a497e7c785 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -18,7 +18,6 @@
  */
 
 #include <linux/device.h>
-#include <linux/kallsyms.h>
 #include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/pm.h>
@@ -526,6 +525,88 @@ static void dpm_watchdog_clear(struct dpm_watchdog *wd)
 /*------------------------- Resume routines -------------------------*/
 
 /**
+ * dev_pm_skip_next_resume_phases - Skip next system resume phases for device.
+ * @dev: Target device.
+ *
+ * Make the core skip the "early resume" and "resume" phases for @dev.
+ *
+ * This function can be called by middle-layer code during the "noirq" phase of
+ * system resume if necessary, but not by device drivers.
+ */
+void dev_pm_skip_next_resume_phases(struct device *dev)
+{
+	dev->power.is_late_suspended = false;
+	dev->power.is_suspended = false;
+}
+
+/**
+ * suspend_event - Return a "suspend" message for given "resume" one.
+ * @resume_msg: PM message representing a system-wide resume transition.
+ */
+static pm_message_t suspend_event(pm_message_t resume_msg)
+{
+	switch (resume_msg.event) {
+	case PM_EVENT_RESUME:
+		return PMSG_SUSPEND;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RESTORE:
+		return PMSG_FREEZE;
+	case PM_EVENT_RECOVER:
+		return PMSG_HIBERNATE;
+	}
+	return PMSG_ON;
+}
+
+/**
+ * dev_pm_may_skip_resume - System-wide device resume optimization check.
+ * @dev: Target device.
+ *
+ * Checks whether or not the device may be left in suspend after a system-wide
+ * transition to the working state.
+ */
+bool dev_pm_may_skip_resume(struct device *dev)
+{
+	return !dev->power.must_resume && pm_transition.event != PM_EVENT_RESTORE;
+}
+
+static pm_callback_t dpm_subsys_resume_noirq_cb(struct device *dev,
+						pm_message_t state,
+						const char **info_p)
+{
+	pm_callback_t callback;
+	const char *info;
+
+	if (dev->pm_domain) {
+		info = "noirq power domain ";
+		callback = pm_noirq_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "noirq type ";
+		callback = pm_noirq_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "noirq class ";
+		callback = pm_noirq_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "noirq bus ";
+		callback = pm_noirq_op(dev->bus->pm, state);
+	} else {
+		return NULL;
+	}
+
+	if (info_p)
+		*info_p = info;
+
+	return callback;
+}
+
+static pm_callback_t dpm_subsys_suspend_noirq_cb(struct device *dev,
+						 pm_message_t state,
+						 const char **info_p);
+
+static pm_callback_t dpm_subsys_suspend_late_cb(struct device *dev,
+						pm_message_t state,
+						const char **info_p);
+
+/**
  * device_resume_noirq - Execute a "noirq resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
@@ -536,8 +617,9 @@ static void dpm_watchdog_clear(struct dpm_watchdog *wd)
  */
 static int device_resume_noirq(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback = NULL;
-	const char *info = NULL;
+	pm_callback_t callback;
+	const char *info;
+	bool skip_resume;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
@@ -551,29 +633,61 @@ static int device_resume_noirq(struct device *dev, pm_message_t state, bool asyn
 
 	dpm_wait_for_superior(dev, async);
 
-	if (dev->pm_domain) {
-		info = "noirq power domain ";
-		callback = pm_noirq_op(&dev->pm_domain->ops, state);
-	} else if (dev->type && dev->type->pm) {
-		info = "noirq type ";
-		callback = pm_noirq_op(dev->type->pm, state);
-	} else if (dev->class && dev->class->pm) {
-		info = "noirq class ";
-		callback = pm_noirq_op(dev->class->pm, state);
-	} else if (dev->bus && dev->bus->pm) {
-		info = "noirq bus ";
-		callback = pm_noirq_op(dev->bus->pm, state);
+	skip_resume = dev_pm_may_skip_resume(dev);
+
+	callback = dpm_subsys_resume_noirq_cb(dev, state, &info);
+	if (callback)
+		goto Run;
+
+	if (skip_resume)
+		goto Skip;
+
+	if (dev_pm_smart_suspend_and_suspended(dev)) {
+		pm_message_t suspend_msg = suspend_event(state);
+
+		/*
+		 * If "freeze" callbacks have been skipped during a transition
+		 * related to hibernation, the subsequent "thaw" callbacks must
+		 * be skipped too or bad things may happen.  Otherwise, resume
+		 * callbacks are going to be run for the device, so its runtime
+		 * PM status must be changed to reflect the new state after the
+		 * transition under way.
+		 */
+		if (!dpm_subsys_suspend_late_cb(dev, suspend_msg, NULL) &&
+		    !dpm_subsys_suspend_noirq_cb(dev, suspend_msg, NULL)) {
+			if (state.event == PM_EVENT_THAW) {
+				skip_resume = true;
+				goto Skip;
+			} else {
+				pm_runtime_set_active(dev);
+			}
+		}
 	}
 
-	if (!callback && dev->driver && dev->driver->pm) {
+	if (dev->driver && dev->driver->pm) {
 		info = "noirq driver ";
 		callback = pm_noirq_op(dev->driver->pm, state);
 	}
 
+Run:
 	error = dpm_run_callback(callback, dev, state, info);
+
+Skip:
 	dev->power.is_noirq_suspended = false;
 
- Out:
+	if (skip_resume) {
+		/*
+		 * The device is going to be left in suspend, but it might not
+		 * have been in runtime suspend before the system suspended, so
+		 * its runtime PM status needs to be updated to avoid confusing
+		 * the runtime PM framework when runtime PM is enabled for the
+		 * device again.
+		 */
+		pm_runtime_set_suspended(dev);
+		dev_pm_skip_next_resume_phases(dev);
+	}
+
+Out:
 	complete_all(&dev->power.completion);
 	TRACE_RESUME(error);
 	return error;
@@ -666,6 +780,35 @@ void dpm_resume_noirq(pm_message_t state)
 	dpm_noirq_end();
 }
 
+static pm_callback_t dpm_subsys_resume_early_cb(struct device *dev,
+						pm_message_t state,
+						const char **info_p)
+{
+	pm_callback_t callback;
+	const char *info;
+
+	if (dev->pm_domain) {
+		info = "early power domain ";
+		callback = pm_late_early_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "early type ";
+		callback = pm_late_early_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "early class ";
+		callback = pm_late_early_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "early bus ";
+		callback = pm_late_early_op(dev->bus->pm, state);
+	} else {
+		return NULL;
+	}
+
+	if (info_p)
+		*info_p = info;
+
+	return callback;
+}
+
 /**
  * device_resume_early - Execute an "early resume" callback for given device.
  * @dev: Device to handle.
@@ -676,8 +819,8 @@ void dpm_resume_noirq(pm_message_t state)
  */
 static int device_resume_early(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback = NULL;
-	const char *info = NULL;
+	pm_callback_t callback;
+	const char *info;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
@@ -691,19 +834,7 @@ static int device_resume_early(struct device *dev, pm_message_t state, bool asyn
 
 	dpm_wait_for_superior(dev, async);
 
-	if (dev->pm_domain) {
-		info = "early power domain ";
-		callback = pm_late_early_op(&dev->pm_domain->ops, state);
-	} else if (dev->type && dev->type->pm) {
-		info = "early type ";
-		callback = pm_late_early_op(dev->type->pm, state);
-	} else if (dev->class && dev->class->pm) {
-		info = "early class ";
-		callback = pm_late_early_op(dev->class->pm, state);
-	} else if (dev->bus && dev->bus->pm) {
-		info = "early bus ";
-		callback = pm_late_early_op(dev->bus->pm, state);
-	}
+	callback = dpm_subsys_resume_early_cb(dev, state, &info);
 
 	if (!callback && dev->driver && dev->driver->pm) {
 		info = "early driver ";
@@ -1074,6 +1205,77 @@ static pm_message_t resume_event(pm_message_t sleep_state)
 	return PMSG_ON;
 }
 
+static void dpm_superior_set_must_resume(struct device *dev)
+{
+	struct device_link *link;
+	int idx;
+
+	if (dev->parent)
+		dev->parent->power.must_resume = true;
+
+	idx = device_links_read_lock();
+
+	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+		link->supplier->power.must_resume = true;
+
+	device_links_read_unlock(idx);
+}
+
+static pm_callback_t dpm_subsys_suspend_noirq_cb(struct device *dev,
+						 pm_message_t state,
+						 const char **info_p)
+{
+	pm_callback_t callback;
+	const char *info;
+
+	if (dev->pm_domain) {
+		info = "noirq power domain ";
+		callback = pm_noirq_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "noirq type ";
+		callback = pm_noirq_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "noirq class ";
+		callback = pm_noirq_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "noirq bus ";
+		callback = pm_noirq_op(dev->bus->pm, state);
+	} else {
+		return NULL;
+	}
+
+	if (info_p)
+		*info_p = info;
+
+	return callback;
+}
+
+static bool device_must_resume(struct device *dev, pm_message_t state,
+			       bool no_subsys_suspend_noirq)
+{
+	pm_message_t resume_msg = resume_event(state);
+
+	/*
+	 * If all of the device driver's "noirq", "late" and "early" callbacks
+	 * are invoked directly by the core, the decision to allow the device to
+	 * stay in suspend can be based on its current runtime PM status and its
+	 * wakeup settings.
+	 */
+	if (no_subsys_suspend_noirq &&
+	    !dpm_subsys_suspend_late_cb(dev, state, NULL) &&
+	    !dpm_subsys_resume_early_cb(dev, resume_msg, NULL) &&
+	    !dpm_subsys_resume_noirq_cb(dev, resume_msg, NULL))
+		return !pm_runtime_status_suspended(dev) &&
+			(resume_msg.event != PM_EVENT_RESUME ||
+			 (device_can_wakeup(dev) && !device_may_wakeup(dev)));
+
+	/*
+	 * The only safe strategy here is to require that if the device may not
+	 * be left in suspend, resume callbacks must be invoked for it.
+	 */
+	return !dev->power.may_skip_resume;
+}
+
 /**
  * __device_suspend_noirq - Execute a "noirq suspend" callback for given device.
  * @dev: Device to handle.
@@ -1085,8 +1287,9 @@ static pm_message_t resume_event(pm_message_t sleep_state)
  */
 static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback = NULL;
-	const char *info = NULL;
+	pm_callback_t callback;
+	const char *info;
+	bool no_subsys_cb = false;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
@@ -1105,30 +1308,40 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a
 	if (dev->power.syscore || dev->power.direct_complete)
 		goto Complete;
 
-	if (dev->pm_domain) {
-		info = "noirq power domain ";
-		callback = pm_noirq_op(&dev->pm_domain->ops, state);
-	} else if (dev->type && dev->type->pm) {
-		info = "noirq type ";
-		callback = pm_noirq_op(dev->type->pm, state);
-	} else if (dev->class && dev->class->pm) {
-		info = "noirq class ";
-		callback = pm_noirq_op(dev->class->pm, state);
-	} else if (dev->bus && dev->bus->pm) {
-		info = "noirq bus ";
-		callback = pm_noirq_op(dev->bus->pm, state);
-	}
+	callback = dpm_subsys_suspend_noirq_cb(dev, state, &info);
+	if (callback)
+		goto Run;
 
-	if (!callback && dev->driver && dev->driver->pm) {
+	no_subsys_cb = !dpm_subsys_suspend_late_cb(dev, state, NULL);
+
+	if (dev_pm_smart_suspend_and_suspended(dev) && no_subsys_cb)
+		goto Skip;
+
+	if (dev->driver && dev->driver->pm) {
 		info = "noirq driver ";
 		callback = pm_noirq_op(dev->driver->pm, state);
 	}
 
+Run:
 	error = dpm_run_callback(callback, dev, state, info);
-	if (!error)
-		dev->power.is_noirq_suspended = true;
-	else
+	if (error) {
 		async_error = error;
+		goto Complete;
+	}
+
+Skip:
+	dev->power.is_noirq_suspended = true;
+
+	if (dev_pm_test_driver_flags(dev, DPM_FLAG_LEAVE_SUSPENDED)) {
+		dev->power.must_resume = dev->power.must_resume ||
+				atomic_read(&dev->power.usage_count) > 1 ||
+				device_must_resume(dev, state, no_subsys_cb);
+	} else {
+		dev->power.must_resume = true;
+	}
+
+	if (dev->power.must_resume)
+		dpm_superior_set_must_resume(dev);
 
 Complete:
 	complete_all(&dev->power.completion);
@@ -1234,6 +1447,50 @@ int dpm_suspend_noirq(pm_message_t state)
 	return ret;
 }
 
+static void dpm_propagate_wakeup_to_parent(struct device *dev)
+{
+	struct device *parent = dev->parent;
+
+	if (!parent)
+		return;
+
+	spin_lock_irq(&parent->power.lock);
+
+	if (dev->power.wakeup_path && !parent->power.ignore_children)
+		parent->power.wakeup_path = true;
+
+	spin_unlock_irq(&parent->power.lock);
+}
+
+static pm_callback_t dpm_subsys_suspend_late_cb(struct device *dev,
+						pm_message_t state,
+						const char **info_p)
+{
+	pm_callback_t callback;
+	const char *info;
+
+	if (dev->pm_domain) {
+		info = "late power domain ";
+		callback = pm_late_early_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "late type ";
+		callback = pm_late_early_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "late class ";
+		callback = pm_late_early_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "late bus ";
+		callback = pm_late_early_op(dev->bus->pm, state);
+	} else {
+		return NULL;
+	}
+
+	if (info_p)
+		*info_p = info;
+
+	return callback;
+}
+
 /**
  * __device_suspend_late - Execute a "late suspend" callback for given device.
  * @dev: Device to handle.
@@ -1244,8 +1501,8 @@ int dpm_suspend_noirq(pm_message_t state)
  */
 static int __device_suspend_late(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback = NULL;
-	const char *info = NULL;
+	pm_callback_t callback;
+	const char *info;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
@@ -1266,30 +1523,29 @@ static int __device_suspend_late(struct device *dev, pm_message_t state, bool as
 	if (dev->power.syscore || dev->power.direct_complete)
 		goto Complete;
 
-	if (dev->pm_domain) {
-		info = "late power domain ";
-		callback = pm_late_early_op(&dev->pm_domain->ops, state);
-	} else if (dev->type && dev->type->pm) {
-		info = "late type ";
-		callback = pm_late_early_op(dev->type->pm, state);
-	} else if (dev->class && dev->class->pm) {
-		info = "late class ";
-		callback = pm_late_early_op(dev->class->pm, state);
-	} else if (dev->bus && dev->bus->pm) {
-		info = "late bus ";
-		callback = pm_late_early_op(dev->bus->pm, state);
-	}
+	callback = dpm_subsys_suspend_late_cb(dev, state, &info);
+	if (callback)
+		goto Run;
 
-	if (!callback && dev->driver && dev->driver->pm) {
+	if (dev_pm_smart_suspend_and_suspended(dev) &&
+	    !dpm_subsys_suspend_noirq_cb(dev, state, NULL))
+		goto Skip;
+
+	if (dev->driver && dev->driver->pm) {
 		info = "late driver ";
 		callback = pm_late_early_op(dev->driver->pm, state);
 	}
 
+Run:
 	error = dpm_run_callback(callback, dev, state, info);
-	if (!error)
-		dev->power.is_late_suspended = true;
-	else
+	if (error) {
 		async_error = error;
+		goto Complete;
+	}
+	dpm_propagate_wakeup_to_parent(dev);
+
+Skip:
+	dev->power.is_late_suspended = true;
 
 Complete:
 	TRACE_SUSPEND(error);
@@ -1420,11 +1676,17 @@ static int legacy_suspend(struct device *dev, pm_message_t state,
 	return error;
 }
 
-static void dpm_clear_suppliers_direct_complete(struct device *dev)
+static void dpm_clear_superiors_direct_complete(struct device *dev)
 {
 	struct device_link *link;
 	int idx;
 
+	if (dev->parent) {
+		spin_lock_irq(&dev->parent->power.lock);
+		dev->parent->power.direct_complete = false;
+		spin_unlock_irq(&dev->parent->power.lock);
+	}
+
 	idx = device_links_read_lock();
 
 	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) {
@@ -1485,6 +1747,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 		dev->power.direct_complete = false;
 	}
 
+	dev->power.may_skip_resume = false;
+	dev->power.must_resume = false;
+
 	dpm_watchdog_set(&wd, dev);
 	device_lock(dev);
 
@@ -1528,20 +1793,12 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 
  End:
 	if (!error) {
-		struct device *parent = dev->parent;
-
 		dev->power.is_suspended = true;
-		if (parent) {
-			spin_lock_irq(&parent->power.lock);
-
-			dev->parent->power.direct_complete = false;
-			if (dev->power.wakeup_path
-			    && !dev->parent->power.ignore_children)
-				dev->parent->power.wakeup_path = true;
+		if (device_may_wakeup(dev))
+			dev->power.wakeup_path = true;
 
-			spin_unlock_irq(&parent->power.lock);
-		}
-		dpm_clear_suppliers_direct_complete(dev);
+		dpm_propagate_wakeup_to_parent(dev);
+		dpm_clear_superiors_direct_complete(dev);
 	}
 
 	device_unlock(dev);
@@ -1650,8 +1907,9 @@ static int device_prepare(struct device *dev, pm_message_t state)
 	if (dev->power.syscore)
 		return 0;
 
-	WARN_ON(dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) &&
-		!pm_runtime_enabled(dev));
+	WARN_ON(!pm_runtime_enabled(dev) &&
+		dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND |
+					      DPM_FLAG_LEAVE_SUSPENDED));
 
 	/*
 	 * If a device's parent goes into runtime suspend at the wrong time,
@@ -1663,7 +1921,7 @@ static int device_prepare(struct device *dev, pm_message_t state)
 
 	device_lock(dev);
 
-	dev->power.wakeup_path = device_may_wakeup(dev);
+	dev->power.wakeup_path = false;
 
 	if (dev->power.no_pm_callbacks) {
 		ret = 1;	/* Let device go direct_complete */
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 7beee75399d4..21244c53e377 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -41,20 +41,15 @@ extern void dev_pm_disable_wake_irq_check(struct device *dev);
 
 #ifdef CONFIG_PM_SLEEP
 
-extern int device_wakeup_attach_irq(struct device *dev,
-				    struct wake_irq *wakeirq);
+extern void device_wakeup_attach_irq(struct device *dev, struct wake_irq *wakeirq);
 extern void device_wakeup_detach_irq(struct device *dev);
 extern void device_wakeup_arm_wake_irqs(void);
 extern void device_wakeup_disarm_wake_irqs(void);
 
 #else
 
-static inline int
-device_wakeup_attach_irq(struct device *dev,
-			 struct wake_irq *wakeirq)
-{
-	return 0;
-}
+static inline void device_wakeup_attach_irq(struct device *dev,
+					    struct wake_irq *wakeirq) {}
 
 static inline void device_wakeup_detach_irq(struct device *dev)
 {
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 027d159ac381..8bef3cb2424d 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -276,7 +276,8 @@ static int rpm_get_suppliers(struct device *dev)
 			continue;
 
 		retval = pm_runtime_get_sync(link->supplier);
-		if (retval < 0) {
+		/* Ignore suppliers with disabled runtime PM. */
+		if (retval < 0 && retval != -EACCES) {
 			pm_runtime_put_noidle(link->supplier);
 			return retval;
 		}
@@ -1612,22 +1613,34 @@ void pm_runtime_drop_link(struct device *dev)
 	spin_unlock_irq(&dev->power.lock);
 }
 
+static bool pm_runtime_need_not_resume(struct device *dev)
+{
+	return atomic_read(&dev->power.usage_count) <= 1 &&
+		(atomic_read(&dev->power.child_count) == 0 ||
+		 dev->power.ignore_children);
+}
+
 /**
  * pm_runtime_force_suspend - Force a device into suspend state if needed.
  * @dev: Device to suspend.
  *
  * Disable runtime PM so we safely can check the device's runtime PM status and
- * if it is active, invoke it's .runtime_suspend callback to bring it into
- * suspend state. Keep runtime PM disabled to preserve the state unless we
- * encounter errors.
+ * if it is active, invoke its ->runtime_suspend callback to suspend it and
+ * change its runtime PM status field to RPM_SUSPENDED.  Also, if the device's
+ * usage and children counters don't indicate that the device was in use before
+ * the system-wide transition under way, decrement its parent's children counter
+ * (if there is a parent).  Keep runtime PM disabled to preserve the state
+ * unless we encounter errors.
  *
  * Typically this function may be invoked from a system suspend callback to make
- * sure the device is put into low power state.
+ * sure the device is put into low power state and it should only be used during
+ * system-wide PM transitions to sleep states.  It assumes that the analogous
+ * pm_runtime_force_resume() will be used to resume the device.
  */
 int pm_runtime_force_suspend(struct device *dev)
 {
 	int (*callback)(struct device *);
-	int ret = 0;
+	int ret;
 
 	pm_runtime_disable(dev);
 	if (pm_runtime_status_suspended(dev))
@@ -1635,27 +1648,23 @@ int pm_runtime_force_suspend(struct device *dev)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
 
-	if (!callback) {
-		ret = -ENOSYS;
-		goto err;
-	}
-
-	ret = callback(dev);
+	ret = callback ? callback(dev) : 0;
 	if (ret)
 		goto err;
 
 	/*
-	 * Increase the runtime PM usage count for the device's parent, in case
-	 * when we find the device being used when system suspend was invoked.
-	 * This informs pm_runtime_force_resume() to resume the parent
-	 * immediately, which is needed to be able to resume its children,
-	 * when not deferring the resume to be managed via runtime PM.
+	 * If the device can stay in suspend after the system-wide transition
+	 * to the working state that will follow, drop the children counter of
+	 * its parent, but set its status to RPM_SUSPENDED anyway in case this
+	 * function will be called again for it in the meantime.
 	 */
-	if (dev->parent && atomic_read(&dev->power.usage_count) > 1)
-		pm_runtime_get_noresume(dev->parent);
+	if (pm_runtime_need_not_resume(dev))
+		pm_runtime_set_suspended(dev);
+	else
+		__update_runtime_status(dev, RPM_SUSPENDED);
 
-	pm_runtime_set_suspended(dev);
 	return 0;
+
 err:
 	pm_runtime_enable(dev);
 	return ret;
@@ -1668,13 +1677,9 @@ EXPORT_SYMBOL_GPL(pm_runtime_force_suspend);
  *
  * Prior invoking this function we expect the user to have brought the device
  * into low power state by a call to pm_runtime_force_suspend(). Here we reverse
- * those actions and brings the device into full power, if it is expected to be
- * used on system resume. To distinguish that, we check whether the runtime PM
- * usage count is greater than 1 (the PM core increases the usage count in the
- * system PM prepare phase), as that indicates a real user (such as a subsystem,
- * driver, userspace, etc.) is using it. If that is the case, the device is
- * expected to be used on system resume as well, so then we resume it. In the
- * other case, we defer the resume to be managed via runtime PM.
+ * those actions and bring the device into full power, if it is expected to be
+ * used on system resume.  In the other case, we defer the resume to be managed
+ * via runtime PM.
  *
  * Typically this function may be invoked from a system resume callback.
  */
@@ -1683,32 +1688,18 @@ int pm_runtime_force_resume(struct device *dev)
 	int (*callback)(struct device *);
 	int ret = 0;
 
-	callback = RPM_GET_CALLBACK(dev, runtime_resume);
-
-	if (!callback) {
-		ret = -ENOSYS;
-		goto out;
-	}
-
-	if (!pm_runtime_status_suspended(dev))
+	if (!pm_runtime_status_suspended(dev) || pm_runtime_need_not_resume(dev))
 		goto out;
 
 	/*
-	 * Decrease the parent's runtime PM usage count, if we increased it
-	 * during system suspend in pm_runtime_force_suspend().
-	*/
-	if (atomic_read(&dev->power.usage_count) > 1) {
-		if (dev->parent)
-			pm_runtime_put_noidle(dev->parent);
-	} else {
-		goto out;
-	}
+	 * The value of the parent's children counter is correct already, so
+	 * just update the status of the device.
+	 */
+	__update_runtime_status(dev, RPM_ACTIVE);
 
-	ret = pm_runtime_set_active(dev);
-	if (ret)
-		goto out;
+	callback = RPM_GET_CALLBACK(dev, runtime_resume);
 
-	ret = callback(dev);
+	ret = callback ? callback(dev) : 0;
 	if (ret) {
 		pm_runtime_set_suspended(dev);
 		goto out;
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index e153e28b1857..0f651efc58a1 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -108,16 +108,10 @@ static ssize_t control_show(struct device *dev, struct device_attribute *attr,
 static ssize_t control_store(struct device * dev, struct device_attribute *attr,
 			     const char * buf, size_t n)
 {
-	char *cp;
-	int len = n;
-
-	cp = memchr(buf, '\n', n);
-	if (cp)
-		len = cp - buf;
 	device_lock(dev);
-	if (len == sizeof ctrl_auto - 1 && strncmp(buf, ctrl_auto, len) == 0)
+	if (sysfs_streq(buf, ctrl_auto))
 		pm_runtime_allow(dev);
-	else if (len == sizeof ctrl_on - 1 && strncmp(buf, ctrl_on, len) == 0)
+	else if (sysfs_streq(buf, ctrl_on))
 		pm_runtime_forbid(dev);
 	else
 		n = -EINVAL;
@@ -125,9 +119,9 @@ static ssize_t control_store(struct device * dev, struct device_attribute *attr,
 	return n;
 }
 
-static DEVICE_ATTR(control, 0644, control_show, control_store);
+static DEVICE_ATTR_RW(control);
 
-static ssize_t rtpm_active_time_show(struct device *dev,
+static ssize_t runtime_active_time_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	int ret;
@@ -138,9 +132,9 @@ static ssize_t rtpm_active_time_show(struct device *dev,
 	return ret;
 }
 
-static DEVICE_ATTR(runtime_active_time, 0444, rtpm_active_time_show, NULL);
+static DEVICE_ATTR_RO(runtime_active_time);
 
-static ssize_t rtpm_suspended_time_show(struct device *dev,
+static ssize_t runtime_suspended_time_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	int ret;
@@ -152,9 +146,9 @@ static ssize_t rtpm_suspended_time_show(struct device *dev,
 	return ret;
 }
 
-static DEVICE_ATTR(runtime_suspended_time, 0444, rtpm_suspended_time_show, NULL);
+static DEVICE_ATTR_RO(runtime_suspended_time);
 
-static ssize_t rtpm_status_show(struct device *dev,
+static ssize_t runtime_status_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	const char *p;
@@ -184,7 +178,7 @@ static ssize_t rtpm_status_show(struct device *dev,
 	return sprintf(buf, p);
 }
 
-static DEVICE_ATTR(runtime_status, 0444, rtpm_status_show, NULL);
+static DEVICE_ATTR_RO(runtime_status);
 
 static ssize_t autosuspend_delay_ms_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -211,26 +205,25 @@ static ssize_t autosuspend_delay_ms_store(struct device *dev,
 	return n;
 }
 
-static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
-		autosuspend_delay_ms_store);
+static DEVICE_ATTR_RW(autosuspend_delay_ms);
 
-static ssize_t pm_qos_resume_latency_show(struct device *dev,
-					  struct device_attribute *attr,
-					  char *buf)
+static ssize_t pm_qos_resume_latency_us_show(struct device *dev,
+					     struct device_attribute *attr,
+					     char *buf)
 {
 	s32 value = dev_pm_qos_requested_resume_latency(dev);
 
 	if (value == 0)
 		return sprintf(buf, "n/a\n");
-	else if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+	if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
 		value = 0;
 
 	return sprintf(buf, "%d\n", value);
 }
 
-static ssize_t pm_qos_resume_latency_store(struct device *dev,
-					   struct device_attribute *attr,
-					   const char *buf, size_t n)
+static ssize_t pm_qos_resume_latency_us_store(struct device *dev,
+					      struct device_attribute *attr,
+					      const char *buf, size_t n)
 {
 	s32 value;
 	int ret;
@@ -245,7 +238,7 @@ static ssize_t pm_qos_resume_latency_store(struct device *dev,
 
 		if (value == 0)
 			value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
-	} else if (!strcmp(buf, "n/a") || !strcmp(buf, "n/a\n")) {
+	} else if (sysfs_streq(buf, "n/a")) {
 		value = 0;
 	} else {
 		return -EINVAL;
@@ -256,26 +249,25 @@ static ssize_t pm_qos_resume_latency_store(struct device *dev,
 	return ret < 0 ? ret : n;
 }
 
-static DEVICE_ATTR(pm_qos_resume_latency_us, 0644,
-		   pm_qos_resume_latency_show, pm_qos_resume_latency_store);
+static DEVICE_ATTR_RW(pm_qos_resume_latency_us);
 
-static ssize_t pm_qos_latency_tolerance_show(struct device *dev,
-					     struct device_attribute *attr,
-					     char *buf)
+static ssize_t pm_qos_latency_tolerance_us_show(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
 {
 	s32 value = dev_pm_qos_get_user_latency_tolerance(dev);
 
 	if (value < 0)
 		return sprintf(buf, "auto\n");
-	else if (value == PM_QOS_LATENCY_ANY)
+	if (value == PM_QOS_LATENCY_ANY)
 		return sprintf(buf, "any\n");
 
 	return sprintf(buf, "%d\n", value);
 }
 
-static ssize_t pm_qos_latency_tolerance_store(struct device *dev,
-					      struct device_attribute *attr,
-					      const char *buf, size_t n)
+static ssize_t pm_qos_latency_tolerance_us_store(struct device *dev,
+						 struct device_attribute *attr,
+						 const char *buf, size_t n)
 {
 	s32 value;
 	int ret;
@@ -285,9 +277,9 @@ static ssize_t pm_qos_latency_tolerance_store(struct device *dev,
 		if (value < 0)
 			return -EINVAL;
 	} else {
-		if (!strcmp(buf, "auto") || !strcmp(buf, "auto\n"))
+		if (sysfs_streq(buf, "auto"))
 			value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
-		else if (!strcmp(buf, "any") || !strcmp(buf, "any\n"))
+		else if (sysfs_streq(buf, "any"))
 			value = PM_QOS_LATENCY_ANY;
 		else
 			return -EINVAL;
@@ -296,8 +288,7 @@ static ssize_t pm_qos_latency_tolerance_store(struct device *dev,
 	return ret < 0 ? ret : n;
 }
 
-static DEVICE_ATTR(pm_qos_latency_tolerance_us, 0644,
-		   pm_qos_latency_tolerance_show, pm_qos_latency_tolerance_store);
+static DEVICE_ATTR_RW(pm_qos_latency_tolerance_us);
 
 static ssize_t pm_qos_no_power_off_show(struct device *dev,
 					struct device_attribute *attr,
@@ -323,49 +314,39 @@ static ssize_t pm_qos_no_power_off_store(struct device *dev,
 	return ret < 0 ? ret : n;
 }
 
-static DEVICE_ATTR(pm_qos_no_power_off, 0644,
-		   pm_qos_no_power_off_show, pm_qos_no_power_off_store);
+static DEVICE_ATTR_RW(pm_qos_no_power_off);
 
 #ifdef CONFIG_PM_SLEEP
 static const char _enabled[] = "enabled";
 static const char _disabled[] = "disabled";
 
-static ssize_t
-wake_show(struct device * dev, struct device_attribute *attr, char * buf)
+static ssize_t wakeup_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	return sprintf(buf, "%s\n", device_can_wakeup(dev)
 		? (device_may_wakeup(dev) ? _enabled : _disabled)
 		: "");
 }
 
-static ssize_t
-wake_store(struct device * dev, struct device_attribute *attr,
-	const char * buf, size_t n)
+static ssize_t wakeup_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t n)
 {
-	char *cp;
-	int len = n;
-
 	if (!device_can_wakeup(dev))
 		return -EINVAL;
 
-	cp = memchr(buf, '\n', n);
-	if (cp)
-		len = cp - buf;
-	if (len == sizeof _enabled - 1
-			&& strncmp(buf, _enabled, sizeof _enabled - 1) == 0)
+	if (sysfs_streq(buf, _enabled))
 		device_set_wakeup_enable(dev, 1);
-	else if (len == sizeof _disabled - 1
-			&& strncmp(buf, _disabled, sizeof _disabled - 1) == 0)
+	else if (sysfs_streq(buf, _disabled))
 		device_set_wakeup_enable(dev, 0);
 	else
 		return -EINVAL;
 	return n;
 }
 
-static DEVICE_ATTR(wakeup, 0644, wake_show, wake_store);
+static DEVICE_ATTR_RW(wakeup);
 
 static ssize_t wakeup_count_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+				 struct device_attribute *attr, char *buf)
 {
 	unsigned long count = 0;
 	bool enabled = false;
@@ -379,10 +360,11 @@ static ssize_t wakeup_count_show(struct device *dev,
 	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
 }
 
-static DEVICE_ATTR(wakeup_count, 0444, wakeup_count_show, NULL);
+static DEVICE_ATTR_RO(wakeup_count);
 
 static ssize_t wakeup_active_count_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+					struct device_attribute *attr,
+					char *buf)
 {
 	unsigned long count = 0;
 	bool enabled = false;
@@ -396,11 +378,11 @@ static ssize_t wakeup_active_count_show(struct device *dev,
 	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
 }
 
-static DEVICE_ATTR(wakeup_active_count, 0444, wakeup_active_count_show, NULL);
+static DEVICE_ATTR_RO(wakeup_active_count);
 
 static ssize_t wakeup_abort_count_show(struct device *dev,
-					struct device_attribute *attr,
-					char *buf)
+				       struct device_attribute *attr,
+				       char *buf)
 {
 	unsigned long count = 0;
 	bool enabled = false;
@@ -414,7 +396,7 @@ static ssize_t wakeup_abort_count_show(struct device *dev,
 	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
 }
 
-static DEVICE_ATTR(wakeup_abort_count, 0444, wakeup_abort_count_show, NULL);
+static DEVICE_ATTR_RO(wakeup_abort_count);
 
 static ssize_t wakeup_expire_count_show(struct device *dev,
 					struct device_attribute *attr,
@@ -432,10 +414,10 @@ static ssize_t wakeup_expire_count_show(struct device *dev,
 	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
 }
 
-static DEVICE_ATTR(wakeup_expire_count, 0444, wakeup_expire_count_show, NULL);
+static DEVICE_ATTR_RO(wakeup_expire_count);
 
 static ssize_t wakeup_active_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+				  struct device_attribute *attr, char *buf)
 {
 	unsigned int active = 0;
 	bool enabled = false;
@@ -449,10 +431,11 @@ static ssize_t wakeup_active_show(struct device *dev,
 	return enabled ? sprintf(buf, "%u\n", active) : sprintf(buf, "\n");
 }
 
-static DEVICE_ATTR(wakeup_active, 0444, wakeup_active_show, NULL);
+static DEVICE_ATTR_RO(wakeup_active);
 
-static ssize_t wakeup_total_time_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+static ssize_t wakeup_total_time_ms_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
 {
 	s64 msec = 0;
 	bool enabled = false;
@@ -466,10 +449,10 @@ static ssize_t wakeup_total_time_show(struct device *dev,
 	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
 }
 
-static DEVICE_ATTR(wakeup_total_time_ms, 0444, wakeup_total_time_show, NULL);
+static DEVICE_ATTR_RO(wakeup_total_time_ms);
 
-static ssize_t wakeup_max_time_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+static ssize_t wakeup_max_time_ms_show(struct device *dev,
+				       struct device_attribute *attr, char *buf)
 {
 	s64 msec = 0;
 	bool enabled = false;
@@ -483,10 +466,11 @@ static ssize_t wakeup_max_time_show(struct device *dev,
 	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
 }
 
-static DEVICE_ATTR(wakeup_max_time_ms, 0444, wakeup_max_time_show, NULL);
+static DEVICE_ATTR_RO(wakeup_max_time_ms);
 
-static ssize_t wakeup_last_time_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+static ssize_t wakeup_last_time_ms_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
 {
 	s64 msec = 0;
 	bool enabled = false;
@@ -500,12 +484,12 @@ static ssize_t wakeup_last_time_show(struct device *dev,
 	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
 }
 
-static DEVICE_ATTR(wakeup_last_time_ms, 0444, wakeup_last_time_show, NULL);
+static DEVICE_ATTR_RO(wakeup_last_time_ms);
 
 #ifdef CONFIG_PM_AUTOSLEEP
-static ssize_t wakeup_prevent_sleep_time_show(struct device *dev,
-					      struct device_attribute *attr,
-					      char *buf)
+static ssize_t wakeup_prevent_sleep_time_ms_show(struct device *dev,
+						 struct device_attribute *attr,
+						 char *buf)
 {
 	s64 msec = 0;
 	bool enabled = false;
@@ -519,40 +503,39 @@ static ssize_t wakeup_prevent_sleep_time_show(struct device *dev,
 	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
 }
 
-static DEVICE_ATTR(wakeup_prevent_sleep_time_ms, 0444,
-		   wakeup_prevent_sleep_time_show, NULL);
+static DEVICE_ATTR_RO(wakeup_prevent_sleep_time_ms);
 #endif /* CONFIG_PM_AUTOSLEEP */
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM_ADVANCED_DEBUG
-static ssize_t rtpm_usagecount_show(struct device *dev,
-				    struct device_attribute *attr, char *buf)
+static ssize_t runtime_usage_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%d\n", atomic_read(&dev->power.usage_count));
 }
+static DEVICE_ATTR_RO(runtime_usage);
 
-static ssize_t rtpm_children_show(struct device *dev,
-				  struct device_attribute *attr, char *buf)
+static ssize_t runtime_active_kids_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
 {
 	return sprintf(buf, "%d\n", dev->power.ignore_children ?
 		0 : atomic_read(&dev->power.child_count));
 }
+static DEVICE_ATTR_RO(runtime_active_kids);
 
-static ssize_t rtpm_enabled_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
+static ssize_t runtime_enabled_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
 {
-	if ((dev->power.disable_depth) && (dev->power.runtime_auto == false))
+	if (dev->power.disable_depth && (dev->power.runtime_auto == false))
 		return sprintf(buf, "disabled & forbidden\n");
-	else if (dev->power.disable_depth)
+	if (dev->power.disable_depth)
 		return sprintf(buf, "disabled\n");
-	else if (dev->power.runtime_auto == false)
+	if (dev->power.runtime_auto == false)
 		return sprintf(buf, "forbidden\n");
 	return sprintf(buf, "enabled\n");
 }
-
-static DEVICE_ATTR(runtime_usage, 0444, rtpm_usagecount_show, NULL);
-static DEVICE_ATTR(runtime_active_kids, 0444, rtpm_children_show, NULL);
-static DEVICE_ATTR(runtime_enabled, 0444, rtpm_enabled_show, NULL);
+static DEVICE_ATTR_RO(runtime_enabled);
 
 #ifdef CONFIG_PM_SLEEP
 static ssize_t async_show(struct device *dev, struct device_attribute *attr,
@@ -566,23 +549,16 @@ static ssize_t async_show(struct device *dev, struct device_attribute *attr,
 static ssize_t async_store(struct device *dev, struct device_attribute *attr,
 			   const char *buf, size_t n)
 {
-	char *cp;
-	int len = n;
-
-	cp = memchr(buf, '\n', n);
-	if (cp)
-		len = cp - buf;
-	if (len == sizeof _enabled - 1 && strncmp(buf, _enabled, len) == 0)
+	if (sysfs_streq(buf, _enabled))
 		device_enable_async_suspend(dev);
-	else if (len == sizeof _disabled - 1 &&
-		 strncmp(buf, _disabled, len) == 0)
+	else if (sysfs_streq(buf, _disabled))
 		device_disable_async_suspend(dev);
 	else
 		return -EINVAL;
 	return n;
 }
 
-static DEVICE_ATTR(async, 0644, async_show, async_store);
+static DEVICE_ATTR_RW(async);
 
 #endif /* CONFIG_PM_SLEEP */
 #endif /* CONFIG_PM_ADVANCED_DEBUG */
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index ae0429827f31..a8ac86e4d79e 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -33,7 +33,6 @@ static int dev_pm_attach_wake_irq(struct device *dev, int irq,
 				  struct wake_irq *wirq)
 {
 	unsigned long flags;
-	int err;
 
 	if (!dev || !wirq)
 		return -EINVAL;
@@ -45,12 +44,11 @@ static int dev_pm_attach_wake_irq(struct device *dev, int irq,
 		return -EEXIST;
 	}
 
-	err = device_wakeup_attach_irq(dev, wirq);
-	if (!err)
-		dev->power.wakeirq = wirq;
+	dev->power.wakeirq = wirq;
+	device_wakeup_attach_irq(dev, wirq);
 
 	spin_unlock_irqrestore(&dev->power.lock, flags);
-	return err;
+	return 0;
 }
 
 /**
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 38559f04db2c..ea01621ed769 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -19,6 +19,11 @@
 
 #include "power.h"
 
+#ifndef CONFIG_SUSPEND
+suspend_state_t pm_suspend_target_state;
+#define pm_suspend_target_state	(PM_SUSPEND_ON)
+#endif
+
 /*
  * If set, the suspend/hibernate code will abort transitions to a sleep state
  * if wakeup events are registered during or immediately before the transition.
@@ -268,6 +273,9 @@ int device_wakeup_enable(struct device *dev)
 	if (!dev || !dev->power.can_wakeup)
 		return -EINVAL;
 
+	if (pm_suspend_target_state != PM_SUSPEND_ON)
+		dev_dbg(dev, "Suspicious %s() during system transition!\n", __func__);
+
 	ws = wakeup_source_register(dev_name(dev));
 	if (!ws)
 		return -ENOMEM;
@@ -291,22 +299,19 @@ EXPORT_SYMBOL_GPL(device_wakeup_enable);
  *
  * Call under the device's power.lock lock.
  */
-int device_wakeup_attach_irq(struct device *dev,
+void device_wakeup_attach_irq(struct device *dev,
 			     struct wake_irq *wakeirq)
 {
 	struct wakeup_source *ws;
 
 	ws = dev->power.wakeup;
-	if (!ws) {
-		dev_err(dev, "forgot to call call device_init_wakeup?\n");
-		return -EINVAL;
-	}
+	if (!ws)
+		return;
 
 	if (ws->wakeirq)
-		return -EEXIST;
+		dev_err(dev, "Leftover wakeup IRQ found, overriding\n");
 
 	ws->wakeirq = wakeirq;
-	return 0;
 }
 
 /**
@@ -448,9 +453,7 @@ int device_init_wakeup(struct device *dev, bool enable)
 		device_set_wakeup_capable(dev, true);
 		ret = device_wakeup_enable(dev);
 	} else {
-		if (dev->power.can_wakeup)
-			device_wakeup_disable(dev);
-
+		device_wakeup_disable(dev);
 		device_set_wakeup_capable(dev, false);
 	}
 
@@ -464,9 +467,6 @@ EXPORT_SYMBOL_GPL(device_init_wakeup);
  */
 int device_set_wakeup_enable(struct device *dev, bool enable)
 {
-	if (!dev || !dev->power.can_wakeup)
-		return -EINVAL;
-
 	return enable ? device_wakeup_enable(dev) : device_wakeup_disable(dev);
 }
 EXPORT_SYMBOL_GPL(device_set_wakeup_enable);
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 851b1b6596a4..302236281d83 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * property.c - Unified device property interface.
  *
  * Copyright (C) 2014, Intel Corporation
  * Authors: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
@@ -16,6 +13,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_graph.h>
+#include <linux/of_irq.h>
 #include <linux/property.h>
 #include <linux/etherdevice.h>
 #include <linux/phy.h>
@@ -698,6 +696,23 @@ int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode,
 }
 EXPORT_SYMBOL_GPL(fwnode_property_get_reference_args);
 
+static void property_entry_free_data(const struct property_entry *p)
+{
+	size_t i, nval;
+
+	if (p->is_array) {
+		if (p->is_string && p->pointer.str) {
+			nval = p->length / sizeof(const char *);
+			for (i = 0; i < nval; i++)
+				kfree(p->pointer.str[i]);
+		}
+		kfree(p->pointer.raw_data);
+	} else if (p->is_string) {
+		kfree(p->value.str);
+	}
+	kfree(p->name);
+}
+
 static int property_copy_string_array(struct property_entry *dst,
 				      const struct property_entry *src)
 {
@@ -728,34 +743,24 @@ static int property_entry_copy_data(struct property_entry *dst,
 {
 	int error;
 
-	dst->name = kstrdup(src->name, GFP_KERNEL);
-	if (!dst->name)
-		return -ENOMEM;
-
 	if (src->is_array) {
-		if (!src->length) {
-			error = -ENODATA;
-			goto out_free_name;
-		}
+		if (!src->length)
+			return -ENODATA;
 
 		if (src->is_string) {
 			error = property_copy_string_array(dst, src);
 			if (error)
-				goto out_free_name;
+				return error;
 		} else {
 			dst->pointer.raw_data = kmemdup(src->pointer.raw_data,
 							src->length, GFP_KERNEL);
-			if (!dst->pointer.raw_data) {
-				error = -ENOMEM;
-				goto out_free_name;
-			}
+			if (!dst->pointer.raw_data)
+				return -ENOMEM;
 		}
 	} else if (src->is_string) {
 		dst->value.str = kstrdup(src->value.str, GFP_KERNEL);
-		if (!dst->value.str && src->value.str) {
-			error = -ENOMEM;
-			goto out_free_name;
-		}
+		if (!dst->value.str && src->value.str)
+			return -ENOMEM;
 	} else {
 		dst->value.raw_data = src->value.raw_data;
 	}
@@ -764,28 +769,15 @@ static int property_entry_copy_data(struct property_entry *dst,
 	dst->is_array = src->is_array;
 	dst->is_string = src->is_string;
 
+	dst->name = kstrdup(src->name, GFP_KERNEL);
+	if (!dst->name)
+		goto out_free_data;
+
 	return 0;
 
-out_free_name:
-	kfree(dst->name);
-	return error;
-}
-
-static void property_entry_free_data(const struct property_entry *p)
-{
-	size_t i, nval;
-
-	if (p->is_array) {
-		if (p->is_string && p->pointer.str) {
-			nval = p->length / sizeof(const char *);
-			for (i = 0; i < nval; i++)
-				kfree(p->pointer.str[i]);
-		}
-		kfree(p->pointer.raw_data);
-	} else if (p->is_string) {
-		kfree(p->value.str);
-	}
-	kfree(p->name);
+out_free_data:
+	property_entry_free_data(dst);
+	return -ENOMEM;
 }
 
 /**
@@ -997,6 +989,32 @@ fwnode_get_next_child_node(const struct fwnode_handle *fwnode,
 EXPORT_SYMBOL_GPL(fwnode_get_next_child_node);
 
 /**
+ * fwnode_get_next_available_child_node - Return the next
+ * available child node handle for a node
+ * @fwnode: Firmware node to find the next child node for.
+ * @child: Handle to one of the node's child nodes or a %NULL handle.
+ */
+struct fwnode_handle *
+fwnode_get_next_available_child_node(const struct fwnode_handle *fwnode,
+				     struct fwnode_handle *child)
+{
+	struct fwnode_handle *next_child = child;
+
+	if (!fwnode)
+		return NULL;
+
+	do {
+		next_child = fwnode_get_next_child_node(fwnode, next_child);
+
+		if (!next_child || fwnode_device_is_available(next_child))
+			break;
+	} while (next_child);
+
+	return next_child;
+}
+EXPORT_SYMBOL_GPL(fwnode_get_next_available_child_node);
+
+/**
  * device_get_next_child_node - Return the next child node handle for a device
  * @dev: Device to find the next child node for.
  * @child: Handle to one of the device's child nodes or a null handle.
@@ -1126,21 +1144,21 @@ enum dev_dma_attr device_get_dma_attr(struct device *dev)
 EXPORT_SYMBOL_GPL(device_get_dma_attr);
 
 /**
- * device_get_phy_mode - Get phy mode for given device
- * @dev:	Pointer to the given device
+ * fwnode_get_phy_mode - Get phy mode for given firmware node
+ * @fwnode:	Pointer to the given node
  *
  * The function gets phy interface string from property 'phy-mode' or
  * 'phy-connection-type', and return its index in phy_modes table, or errno in
  * error case.
  */
-int device_get_phy_mode(struct device *dev)
+int fwnode_get_phy_mode(struct fwnode_handle *fwnode)
 {
 	const char *pm;
 	int err, i;
 
-	err = device_property_read_string(dev, "phy-mode", &pm);
+	err = fwnode_property_read_string(fwnode, "phy-mode", &pm);
 	if (err < 0)
-		err = device_property_read_string(dev,
+		err = fwnode_property_read_string(fwnode,
 						  "phy-connection-type", &pm);
 	if (err < 0)
 		return err;
@@ -1151,13 +1169,27 @@ int device_get_phy_mode(struct device *dev)
 
 	return -ENODEV;
 }
+EXPORT_SYMBOL_GPL(fwnode_get_phy_mode);
+
+/**
+ * device_get_phy_mode - Get phy mode for given device
+ * @dev:	Pointer to the given device
+ *
+ * The function gets phy interface string from property 'phy-mode' or
+ * 'phy-connection-type', and return its index in phy_modes table, or errno in
+ * error case.
+ */
+int device_get_phy_mode(struct device *dev)
+{
+	return fwnode_get_phy_mode(dev_fwnode(dev));
+}
 EXPORT_SYMBOL_GPL(device_get_phy_mode);
 
-static void *device_get_mac_addr(struct device *dev,
+static void *fwnode_get_mac_addr(struct fwnode_handle *fwnode,
 				 const char *name, char *addr,
 				 int alen)
 {
-	int ret = device_property_read_u8_array(dev, name, addr, alen);
+	int ret = fwnode_property_read_u8_array(fwnode, name, addr, alen);
 
 	if (ret == 0 && alen == ETH_ALEN && is_valid_ether_addr(addr))
 		return addr;
@@ -1165,8 +1197,8 @@ static void *device_get_mac_addr(struct device *dev,
 }
 
 /**
- * device_get_mac_address - Get the MAC for a given device
- * @dev:	Pointer to the device
+ * fwnode_get_mac_address - Get the MAC from the firmware node
+ * @fwnode:	Pointer to the firmware node
  * @addr:	Address of buffer to store the MAC in
  * @alen:	Length of the buffer pointed to by addr, should be ETH_ALEN
  *
@@ -1187,23 +1219,60 @@ static void *device_get_mac_addr(struct device *dev,
  * In this case, the real MAC is in 'local-mac-address', and 'mac-address'
  * exists but is all zeros.
 */
-void *device_get_mac_address(struct device *dev, char *addr, int alen)
+void *fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr, int alen)
 {
 	char *res;
 
-	res = device_get_mac_addr(dev, "mac-address", addr, alen);
+	res = fwnode_get_mac_addr(fwnode, "mac-address", addr, alen);
 	if (res)
 		return res;
 
-	res = device_get_mac_addr(dev, "local-mac-address", addr, alen);
+	res = fwnode_get_mac_addr(fwnode, "local-mac-address", addr, alen);
 	if (res)
 		return res;
 
-	return device_get_mac_addr(dev, "address", addr, alen);
+	return fwnode_get_mac_addr(fwnode, "address", addr, alen);
+}
+EXPORT_SYMBOL(fwnode_get_mac_address);
+
+/**
+ * device_get_mac_address - Get the MAC for a given device
+ * @dev:	Pointer to the device
+ * @addr:	Address of buffer to store the MAC in
+ * @alen:	Length of the buffer pointed to by addr, should be ETH_ALEN
+ */
+void *device_get_mac_address(struct device *dev, char *addr, int alen)
+{
+	return fwnode_get_mac_address(dev_fwnode(dev), addr, alen);
 }
 EXPORT_SYMBOL(device_get_mac_address);
 
 /**
+ * fwnode_irq_get - Get IRQ directly from a fwnode
+ * @fwnode:	Pointer to the firmware node
+ * @index:	Zero-based index of the IRQ
+ *
+ * Returns Linux IRQ number on success. Other values are determined
+ * accordingly to acpi_/of_ irq_get() operation.
+ */
+int fwnode_irq_get(struct fwnode_handle *fwnode, unsigned int index)
+{
+	struct device_node *of_node = to_of_node(fwnode);
+	struct resource res;
+	int ret;
+
+	if (IS_ENABLED(CONFIG_OF) && of_node)
+		return of_irq_get(of_node, index);
+
+	ret = acpi_irq_get(ACPI_HANDLE_FWNODE(fwnode), index, &res);
+	if (ret)
+		return ret;
+
+	return res.start;
+}
+EXPORT_SYMBOL(fwnode_irq_get);
+
+/**
  * device_graph_get_next_endpoint - Get next endpoint firmware node
  * @fwnode: Pointer to the parent firmware node
  * @prev: Previous endpoint node or %NULL to get the first
@@ -1340,3 +1409,10 @@ int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 	return fwnode_call_int_op(fwnode, graph_parse_endpoint, endpoint);
 }
 EXPORT_SYMBOL(fwnode_graph_parse_endpoint);
+
+void *device_get_match_data(struct device *dev)
+{
+	return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data,
+				  dev);
+}
+EXPORT_SYMBOL_GPL(device_get_match_data);
diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig
index 3a1535d812d8..aff34c0c2a3e 100644
--- a/drivers/base/regmap/Kconfig
+++ b/drivers/base/regmap/Kconfig
@@ -6,7 +6,6 @@
 config REGMAP
 	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_W1 || REGMAP_AC97 || REGMAP_MMIO || REGMAP_IRQ)
 	select IRQ_DOMAIN if REGMAP_IRQ
-	select REGMAP_HWSPINLOCK if HWSPINLOCK=y
 	bool
 
 config REGCACHE_COMPRESSED
@@ -21,6 +20,10 @@ config REGMAP_I2C
 	tristate
 	depends on I2C
 
+config REGMAP_SLIMBUS
+	tristate
+	depends on SLIMBUS
+
 config REGMAP_SPI
 	tristate
 	depends on SPI
@@ -39,5 +42,6 @@ config REGMAP_MMIO
 config REGMAP_IRQ
 	bool
 
-config REGMAP_HWSPINLOCK
-	bool
+config REGMAP_SOUNDWIRE
+	tristate
+	depends on SOUNDWIRE_BUS
diff --git a/drivers/base/regmap/Makefile b/drivers/base/regmap/Makefile
index 0d298c446108..5ed0023fabda 100644
--- a/drivers/base/regmap/Makefile
+++ b/drivers/base/regmap/Makefile
@@ -8,8 +8,10 @@ obj-$(CONFIG_REGCACHE_COMPRESSED) += regcache-lzo.o
 obj-$(CONFIG_DEBUG_FS) += regmap-debugfs.o
 obj-$(CONFIG_REGMAP_AC97) += regmap-ac97.o
 obj-$(CONFIG_REGMAP_I2C) += regmap-i2c.o
+obj-$(CONFIG_REGMAP_SLIMBUS) += regmap-slimbus.o
 obj-$(CONFIG_REGMAP_SPI) += regmap-spi.o
 obj-$(CONFIG_REGMAP_SPMI) += regmap-spmi.o
 obj-$(CONFIG_REGMAP_MMIO) += regmap-mmio.o
 obj-$(CONFIG_REGMAP_IRQ) += regmap-irq.o
 obj-$(CONFIG_REGMAP_W1) += regmap-w1.o
+obj-$(CONFIG_REGMAP_SOUNDWIRE) += regmap-sdw.o
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 8641183cac2f..53785e0e297a 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -77,6 +77,7 @@ struct regmap {
 	int async_ret;
 
 #ifdef CONFIG_DEBUG_FS
+	bool debugfs_disable;
 	struct dentry *debugfs;
 	const char *debugfs_name;
 
@@ -215,10 +216,17 @@ struct regmap_field {
 extern void regmap_debugfs_initcall(void);
 extern void regmap_debugfs_init(struct regmap *map, const char *name);
 extern void regmap_debugfs_exit(struct regmap *map);
+
+static inline void regmap_debugfs_disable(struct regmap *map)
+{
+	map->debugfs_disable = true;
+}
+
 #else
 static inline void regmap_debugfs_initcall(void) { }
 static inline void regmap_debugfs_init(struct regmap *map, const char *name) { }
 static inline void regmap_debugfs_exit(struct regmap *map) { }
+static inline void regmap_debugfs_disable(struct regmap *map) { }
 #endif
 
 /* regcache core declarations */
diff --git a/drivers/base/regmap/regcache-flat.c b/drivers/base/regmap/regcache-flat.c
index 4d2e50bfc726..bc6cd88b8cc6 100644
--- a/drivers/base/regmap/regcache-flat.c
+++ b/drivers/base/regmap/regcache-flat.c
@@ -37,9 +37,12 @@ static int regcache_flat_init(struct regmap *map)
 
 	cache = map->cache;
 
-	for (i = 0; i < map->num_reg_defaults; i++)
-		cache[regcache_flat_get_index(map, map->reg_defaults[i].reg)] =
-				map->reg_defaults[i].def;
+	for (i = 0; i < map->num_reg_defaults; i++) {
+		unsigned int reg = map->reg_defaults[i].reg;
+		unsigned int index = regcache_flat_get_index(map, reg);
+
+		cache[index] = map->reg_defaults[i].def;
+	}
 
 	return 0;
 }
@@ -56,8 +59,9 @@ static int regcache_flat_read(struct regmap *map,
 			      unsigned int reg, unsigned int *value)
 {
 	unsigned int *cache = map->cache;
+	unsigned int index = regcache_flat_get_index(map, reg);
 
-	*value = cache[regcache_flat_get_index(map, reg)];
+	*value = cache[index];
 
 	return 0;
 }
@@ -66,8 +70,9 @@ static int regcache_flat_write(struct regmap *map, unsigned int reg,
 			       unsigned int value)
 {
 	unsigned int *cache = map->cache;
+	unsigned int index = regcache_flat_get_index(map, reg);
 
-	cache[regcache_flat_get_index(map, reg)] = value;
+	cache[index] = value;
 
 	return 0;
 }
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 36ce3511c733..f3266334063e 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -529,6 +529,18 @@ void regmap_debugfs_init(struct regmap *map, const char *name)
 	struct regmap_range_node *range_node;
 	const char *devname = "dummy";
 
+	/*
+	 * Userspace can initiate reads from the hardware over debugfs.
+	 * Normally internal regmap structures and buffers are protected with
+	 * a mutex or a spinlock, but if the regmap owner decided to disable
+	 * all locking mechanisms, this is no longer the case. For safety:
+	 * don't create the debugfs entries if locking is disabled.
+	 */
+	if (map->debugfs_disable) {
+		dev_dbg(map->dev, "regmap locking disabled - not creating debugfs entries\n");
+		return;
+	}
+
 	/* If we don't have the debugfs root yet, postpone init */
 	if (!regmap_debugfs_root) {
 		struct regmap_debugfs_node *node;
diff --git a/drivers/base/regmap/regmap-sdw.c b/drivers/base/regmap/regmap-sdw.c
new file mode 100644
index 000000000000..50a66382d87d
--- /dev/null
+++ b/drivers/base/regmap/regmap-sdw.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright(c) 2015-17 Intel Corporation.
+
+#include <linux/device.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/soundwire/sdw.h>
+#include "internal.h"
+
+static int regmap_sdw_write(void *context, unsigned int reg, unsigned int val)
+{
+	struct device *dev = context;
+	struct sdw_slave *slave = dev_to_sdw_dev(dev);
+
+	return sdw_write(slave, reg, val);
+}
+
+static int regmap_sdw_read(void *context, unsigned int reg, unsigned int *val)
+{
+	struct device *dev = context;
+	struct sdw_slave *slave = dev_to_sdw_dev(dev);
+	int read;
+
+	read = sdw_read(slave, reg);
+	if (read < 0)
+		return read;
+
+	*val = read;
+	return 0;
+}
+
+static struct regmap_bus regmap_sdw = {
+	.reg_read = regmap_sdw_read,
+	.reg_write = regmap_sdw_write,
+	.reg_format_endian_default = REGMAP_ENDIAN_LITTLE,
+	.val_format_endian_default = REGMAP_ENDIAN_LITTLE,
+};
+
+static int regmap_sdw_config_check(const struct regmap_config *config)
+{
+	/* All register are 8-bits wide as per MIPI Soundwire 1.0 Spec */
+	if (config->val_bits != 8)
+		return -ENOTSUPP;
+
+	/* Registers are 32 bits wide */
+	if (config->reg_bits != 32)
+		return -ENOTSUPP;
+
+	if (config->pad_bits != 0)
+		return -ENOTSUPP;
+
+	return 0;
+}
+
+struct regmap *__regmap_init_sdw(struct sdw_slave *sdw,
+				 const struct regmap_config *config,
+				 struct lock_class_key *lock_key,
+				 const char *lock_name)
+{
+	int ret;
+
+	ret = regmap_sdw_config_check(config);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return __regmap_init(&sdw->dev, &regmap_sdw,
+			&sdw->dev, config, lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__regmap_init_sdw);
+
+struct regmap *__devm_regmap_init_sdw(struct sdw_slave *sdw,
+				      const struct regmap_config *config,
+				      struct lock_class_key *lock_key,
+				      const char *lock_name)
+{
+	int ret;
+
+	ret = regmap_sdw_config_check(config);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return __devm_regmap_init(&sdw->dev, &regmap_sdw,
+			&sdw->dev, config, lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__devm_regmap_init_sdw);
+
+MODULE_DESCRIPTION("Regmap SoundWire Module");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/base/regmap/regmap-slimbus.c b/drivers/base/regmap/regmap-slimbus.c
new file mode 100644
index 000000000000..c90bee81d954
--- /dev/null
+++ b/drivers/base/regmap/regmap-slimbus.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017, Linaro Ltd.
+
+#include <linux/regmap.h>
+#include <linux/slimbus.h>
+#include <linux/module.h>
+
+#include "internal.h"
+
+static int regmap_slimbus_byte_reg_read(void *context, unsigned int reg,
+					unsigned int *val)
+{
+	struct slim_device *sdev = context;
+	int v;
+
+	v = slim_readb(sdev, reg);
+
+	if (v < 0)
+		return v;
+
+	*val = v;
+
+	return 0;
+}
+
+static int regmap_slimbus_byte_reg_write(void *context, unsigned int reg,
+					 unsigned int val)
+{
+	struct slim_device *sdev = context;
+
+	return slim_writeb(sdev, reg, val);
+}
+
+static struct regmap_bus regmap_slimbus_bus = {
+	.reg_write = regmap_slimbus_byte_reg_write,
+	.reg_read = regmap_slimbus_byte_reg_read,
+	.reg_format_endian_default = REGMAP_ENDIAN_LITTLE,
+	.val_format_endian_default = REGMAP_ENDIAN_LITTLE,
+};
+
+static const struct regmap_bus *regmap_get_slimbus(struct slim_device *slim,
+					const struct regmap_config *config)
+{
+	if (config->val_bits == 8 && config->reg_bits == 8)
+		return &regmap_slimbus_bus;
+
+	return ERR_PTR(-ENOTSUPP);
+}
+
+struct regmap *__regmap_init_slimbus(struct slim_device *slimbus,
+				     const struct regmap_config *config,
+				     struct lock_class_key *lock_key,
+				     const char *lock_name)
+{
+	const struct regmap_bus *bus = regmap_get_slimbus(slimbus, config);
+
+	if (IS_ERR(bus))
+		return ERR_CAST(bus);
+
+	return __regmap_init(&slimbus->dev, bus, &slimbus->dev, config,
+			     lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__regmap_init_slimbus);
+
+struct regmap *__devm_regmap_init_slimbus(struct slim_device *slimbus,
+					  const struct regmap_config *config,
+					  struct lock_class_key *lock_key,
+					  const char *lock_name)
+{
+	const struct regmap_bus *bus = regmap_get_slimbus(slimbus, config);
+
+	if (IS_ERR(bus))
+		return ERR_CAST(bus);
+
+	return __devm_regmap_init(&slimbus->dev, bus, &slimbus, config,
+				  lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__devm_regmap_init_slimbus);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 8d516a9bfc01..ee302ccdfbc8 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -414,7 +414,6 @@ static unsigned int regmap_parse_64_native(const void *buf)
 }
 #endif
 
-#ifdef REGMAP_HWSPINLOCK
 static void regmap_lock_hwlock(void *__map)
 {
 	struct regmap *map = __map;
@@ -457,7 +456,11 @@ static void regmap_unlock_hwlock_irqrestore(void *__map)
 
 	hwspin_unlock_irqrestore(map->hwlock, &map->spinlock_flags);
 }
-#endif
+
+static void regmap_lock_unlock_none(void *__map)
+{
+
+}
 
 static void regmap_lock_mutex(void *__map)
 {
@@ -669,16 +672,26 @@ struct regmap *__regmap_init(struct device *dev,
 		goto err;
 	}
 
-	if (config->lock && config->unlock) {
+	if (config->name) {
+		map->name = kstrdup_const(config->name, GFP_KERNEL);
+		if (!map->name) {
+			ret = -ENOMEM;
+			goto err_map;
+		}
+	}
+
+	if (config->disable_locking) {
+		map->lock = map->unlock = regmap_lock_unlock_none;
+		regmap_debugfs_disable(map);
+	} else if (config->lock && config->unlock) {
 		map->lock = config->lock;
 		map->unlock = config->unlock;
 		map->lock_arg = config->lock_arg;
-	} else if (config->hwlock_id) {
-#ifdef REGMAP_HWSPINLOCK
+	} else if (config->use_hwlock) {
 		map->hwlock = hwspin_lock_request_specific(config->hwlock_id);
 		if (!map->hwlock) {
 			ret = -ENXIO;
-			goto err_map;
+			goto err_name;
 		}
 
 		switch (config->hwlock_mode) {
@@ -697,10 +710,6 @@ struct regmap *__regmap_init(struct device *dev,
 		}
 
 		map->lock_arg = map;
-#else
-		ret = -EINVAL;
-		goto err_map;
-#endif
 	} else {
 		if ((bus && bus->fast_io) ||
 		    config->fast_io) {
@@ -762,14 +771,15 @@ struct regmap *__regmap_init(struct device *dev,
 	map->volatile_reg = config->volatile_reg;
 	map->precious_reg = config->precious_reg;
 	map->cache_type = config->cache_type;
-	map->name = config->name;
 
 	spin_lock_init(&map->async_lock);
 	INIT_LIST_HEAD(&map->async_list);
 	INIT_LIST_HEAD(&map->async_free);
 	init_waitqueue_head(&map->async_waitq);
 
-	if (config->read_flag_mask || config->write_flag_mask) {
+	if (config->read_flag_mask ||
+	    config->write_flag_mask ||
+	    config->zero_flag_mask) {
 		map->read_flag_mask = config->read_flag_mask;
 		map->write_flag_mask = config->write_flag_mask;
 	} else if (bus) {
@@ -1116,8 +1126,10 @@ err_range:
 	regmap_range_exit(map);
 	kfree(map->work_buf);
 err_hwlock:
-	if (IS_ENABLED(REGMAP_HWSPINLOCK) && map->hwlock)
+	if (map->hwlock)
 		hwspin_lock_free(map->hwlock);
+err_name:
+	kfree_const(map->name);
 err_map:
 	kfree(map);
 err:
@@ -1305,8 +1317,9 @@ void regmap_exit(struct regmap *map)
 		kfree(async->work_buf);
 		kfree(async);
 	}
-	if (IS_ENABLED(REGMAP_HWSPINLOCK) && map->hwlock)
+	if (map->hwlock)
 		hwspin_lock_free(map->hwlock);
+	kfree_const(map->name);
 	kfree(map);
 }
 EXPORT_SYMBOL_GPL(regmap_exit);
@@ -2423,13 +2436,15 @@ static int _regmap_bus_read(void *context, unsigned int reg,
 {
 	int ret;
 	struct regmap *map = context;
+	void *work_val = map->work_buf + map->format.reg_bytes +
+		map->format.pad_bytes;
 
 	if (!map->format.parse_val)
 		return -EINVAL;
 
-	ret = _regmap_raw_read(map, reg, map->work_buf, map->format.val_bytes);
+	ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes);
 	if (ret == 0)
-		*val = map->format.parse_val(map->work_buf);
+		*val = map->format.parse_val(work_val);
 
 	return ret;
 }
diff --git a/drivers/base/soc.c b/drivers/base/soc.c
index 909dedae4c4e..4e80f48ad5d6 100644
--- a/drivers/base/soc.c
+++ b/drivers/base/soc.c
@@ -1,8 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) ST-Ericsson SA 2011
  *
  * Author: Lee Jones <lee.jones@linaro.org> for ST-Ericsson.
- * License terms:  GNU General Public License (GPL), version 2
  */
 
 #include <linux/sysfs.h>
diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c
index 8d98a329f6ea..6e076f359dcc 100644
--- a/drivers/base/syscore.c
+++ b/drivers/base/syscore.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  syscore.c - Execution of system core operations.
  *
  *  Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
- *
- *  This file is released under the GPLv2.
  */
 
 #include <linux/syscore_ops.h>
diff --git a/drivers/base/test/test_async_driver_probe.c b/drivers/base/test/test_async_driver_probe.c
index a3355d66bc12..e7f145d662f0 100644
--- a/drivers/base/test/test_async_driver_probe.c
+++ b/drivers/base/test/test_async_driver_probe.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2014 Google, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index d936fcf9f1fb..5fd9f167ecc1 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * driver/base/topology.c - Populate sysfs with cpu topology information
  *
@@ -6,22 +7,6 @@
  * Copyright (C) 2006, Intel Corp.
  *
  * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
  */
 #include <linux/mm.h>
 #include <linux/cpu.h>
diff --git a/drivers/base/transport_class.c b/drivers/base/transport_class.c
index f6c453c3816e..5ed86ded6e6b 100644
--- a/drivers/base/transport_class.c
+++ b/drivers/base/transport_class.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * transport_class.c - implementation of generic transport classes
  *                     using attribute_containers
  *
  * Copyright (c) 2005 - James Bottomley <James.Bottomley@steeleye.com>
  *
- * This file is licensed under GPLv2
- *
  * The basic idea here is to allow any "device controller" (which
  * would most often be a Host Bus Adapter to use the services of one
  * or more tranport classes for performing transport specific
diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig
index 02d78f6cecbb..ba8acca036df 100644
--- a/drivers/bcma/Kconfig
+++ b/drivers/bcma/Kconfig
@@ -55,7 +55,7 @@ config BCMA_DRIVER_PCI
 
 config BCMA_DRIVER_PCI_HOSTMODE
 	bool "Driver for PCI core working in hostmode"
-	depends on MIPS && BCMA_DRIVER_PCI
+	depends on MIPS && BCMA_DRIVER_PCI && PCI_DRIVERS_LEGACY
 	help
 	  PCI core hostmode operation (external PCI bus).
 
diff --git a/drivers/bcma/driver_pcie2.c b/drivers/bcma/driver_pcie2.c
index b1a6e327cb23..cf889fc62ac7 100644
--- a/drivers/bcma/driver_pcie2.c
+++ b/drivers/bcma/driver_pcie2.c
@@ -83,7 +83,8 @@ static void bcma_core_pcie2_hw_ltr_war(struct bcma_drv_pcie2 *pcie2)
 		bcma_core_pcie2_set_ltr_vals(pcie2);
 
 		/* TODO:
-		si_core_wrapperreg(pcie2, 3, 0x60, 0x8080, 0); */
+		 *si_core_wrapperreg(pcie2, 3, 0x60, 0x8080, 0);
+		 */
 
 		/* enable the LTR */
 		devstsctr2 |= PCIE2_CAP_DEVSTSCTRL2_LTRENAB;
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 442e777bdfb2..728075214959 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -6619,43 +6619,27 @@ static void DAC960_DestroyProcEntries(DAC960_Controller_T *Controller)
 
 #ifdef DAC960_GAM_MINOR
 
-/*
- * DAC960_gam_ioctl is the ioctl function for performing RAID operations.
-*/
-
-static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
-						unsigned long Argument)
+static long DAC960_gam_get_controller_info(DAC960_ControllerInfo_T __user *UserSpaceControllerInfo)
 {
-  long ErrorCode = 0;
-  if (!capable(CAP_SYS_ADMIN)) return -EACCES;
-
-  mutex_lock(&DAC960_mutex);
-  switch (Request)
-    {
-    case DAC960_IOCTL_GET_CONTROLLER_COUNT:
-      ErrorCode = DAC960_ControllerCount;
-      break;
-    case DAC960_IOCTL_GET_CONTROLLER_INFO:
-      {
-	DAC960_ControllerInfo_T __user *UserSpaceControllerInfo =
-	  (DAC960_ControllerInfo_T __user *) Argument;
 	DAC960_ControllerInfo_T ControllerInfo;
 	DAC960_Controller_T *Controller;
 	int ControllerNumber;
+	long ErrorCode;
+
 	if (UserSpaceControllerInfo == NULL)
 		ErrorCode = -EINVAL;
 	else ErrorCode = get_user(ControllerNumber,
 			     &UserSpaceControllerInfo->ControllerNumber);
 	if (ErrorCode != 0)
-		break;
+		goto out;
 	ErrorCode = -ENXIO;
 	if (ControllerNumber < 0 ||
 	    ControllerNumber > DAC960_ControllerCount - 1) {
-	  break;
+		goto out;
 	}
 	Controller = DAC960_Controllers[ControllerNumber];
 	if (Controller == NULL)
-		break;
+		goto out;
 	memset(&ControllerInfo, 0, sizeof(DAC960_ControllerInfo_T));
 	ControllerInfo.ControllerNumber = ControllerNumber;
 	ControllerInfo.FirmwareType = Controller->FirmwareType;
@@ -6670,12 +6654,12 @@ static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
 	strcpy(ControllerInfo.FirmwareVersion, Controller->FirmwareVersion);
 	ErrorCode = (copy_to_user(UserSpaceControllerInfo, &ControllerInfo,
 			     sizeof(DAC960_ControllerInfo_T)) ? -EFAULT : 0);
-	break;
-      }
-    case DAC960_IOCTL_V1_EXECUTE_COMMAND:
-      {
-	DAC960_V1_UserCommand_T __user *UserSpaceUserCommand =
-	  (DAC960_V1_UserCommand_T __user *) Argument;
+out:
+	return ErrorCode;
+}
+
+static long DAC960_gam_v1_execute_command(DAC960_V1_UserCommand_T __user *UserSpaceUserCommand)
+{
 	DAC960_V1_UserCommand_T UserCommand;
 	DAC960_Controller_T *Controller;
 	DAC960_Command_T *Command = NULL;
@@ -6688,39 +6672,41 @@ static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
 	int ControllerNumber, DataTransferLength;
 	unsigned char *DataTransferBuffer = NULL;
 	dma_addr_t DataTransferBufferDMA;
+        long ErrorCode;
+
 	if (UserSpaceUserCommand == NULL) {
 		ErrorCode = -EINVAL;
-		break;
+		goto out;
 	}
 	if (copy_from_user(&UserCommand, UserSpaceUserCommand,
 				   sizeof(DAC960_V1_UserCommand_T))) {
 		ErrorCode = -EFAULT;
-		break;
+		goto out;
 	}
 	ControllerNumber = UserCommand.ControllerNumber;
     	ErrorCode = -ENXIO;
 	if (ControllerNumber < 0 ||
 	    ControllerNumber > DAC960_ControllerCount - 1)
-	    	break;
+		goto out;
 	Controller = DAC960_Controllers[ControllerNumber];
 	if (Controller == NULL)
-		break;
+		goto out;
 	ErrorCode = -EINVAL;
 	if (Controller->FirmwareType != DAC960_V1_Controller)
-		break;
+		goto out;
 	CommandOpcode = UserCommand.CommandMailbox.Common.CommandOpcode;
 	DataTransferLength = UserCommand.DataTransferLength;
 	if (CommandOpcode & 0x80)
-		break;
+		goto out;
 	if (CommandOpcode == DAC960_V1_DCDB)
 	  {
 	    if (copy_from_user(&DCDB, UserCommand.DCDB,
 			       sizeof(DAC960_V1_DCDB_T))) {
 		ErrorCode = -EFAULT;
-		break;
+		goto out;
 	    }
 	    if (DCDB.Channel >= DAC960_V1_MaxChannels)
-	    		break;
+		goto out;
 	    if (!((DataTransferLength == 0 &&
 		   DCDB.Direction
 		   == DAC960_V1_DCDB_NoDataTransfer) ||
@@ -6730,15 +6716,15 @@ static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
 		  (DataTransferLength < 0 &&
 		   DCDB.Direction
 		   == DAC960_V1_DCDB_DataTransferSystemToDevice)))
-		   	break;
+			goto out;
 	    if (((DCDB.TransferLengthHigh4 << 16) | DCDB.TransferLength)
 		!= abs(DataTransferLength))
-			break;
+			goto out;
 	    DCDB_IOBUF = pci_alloc_consistent(Controller->PCIDevice,
 			sizeof(DAC960_V1_DCDB_T), &DCDB_IOBUFDMA);
 	    if (DCDB_IOBUF == NULL) {
 	    		ErrorCode = -ENOMEM;
-			break;
+			goto out;
 		}
 	  }
 	ErrorCode = -ENOMEM;
@@ -6748,19 +6734,19 @@ static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
                                                        DataTransferLength,
                                                        &DataTransferBufferDMA);
 	    if (DataTransferBuffer == NULL)
-	    	break;
+		goto out;
 	  }
 	else if (DataTransferLength < 0)
 	  {
 	    DataTransferBuffer = pci_alloc_consistent(Controller->PCIDevice,
 				-DataTransferLength, &DataTransferBufferDMA);
 	    if (DataTransferBuffer == NULL)
-	    	break;
+		goto out;
 	    if (copy_from_user(DataTransferBuffer,
 			       UserCommand.DataTransferBuffer,
 			       -DataTransferLength)) {
 		ErrorCode = -EFAULT;
-		break;
+		goto out;
 	    }
 	  }
 	if (CommandOpcode == DAC960_V1_DCDB)
@@ -6837,12 +6823,12 @@ static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
 	if (DCDB_IOBUF != NULL)
 	  pci_free_consistent(Controller->PCIDevice, sizeof(DAC960_V1_DCDB_T),
 			DCDB_IOBUF, DCDB_IOBUFDMA);
-      	break;
-      }
-    case DAC960_IOCTL_V2_EXECUTE_COMMAND:
-      {
-	DAC960_V2_UserCommand_T __user *UserSpaceUserCommand =
-	  (DAC960_V2_UserCommand_T __user *) Argument;
+	out:
+	return ErrorCode;
+}
+
+static long DAC960_gam_v2_execute_command(DAC960_V2_UserCommand_T __user *UserSpaceUserCommand)
+{
 	DAC960_V2_UserCommand_T UserCommand;
 	DAC960_Controller_T *Controller;
 	DAC960_Command_T *Command = NULL;
@@ -6855,26 +6841,26 @@ static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
 	dma_addr_t DataTransferBufferDMA;
 	unsigned char *RequestSenseBuffer = NULL;
 	dma_addr_t RequestSenseBufferDMA;
+	long ErrorCode = -EINVAL;
 
-	ErrorCode = -EINVAL;
 	if (UserSpaceUserCommand == NULL)
-		break;
+		goto out;
 	if (copy_from_user(&UserCommand, UserSpaceUserCommand,
 			   sizeof(DAC960_V2_UserCommand_T))) {
 		ErrorCode = -EFAULT;
-		break;
+		goto out;
 	}
 	ErrorCode = -ENXIO;
 	ControllerNumber = UserCommand.ControllerNumber;
 	if (ControllerNumber < 0 ||
 	    ControllerNumber > DAC960_ControllerCount - 1)
-	    	break;
+		goto out;
 	Controller = DAC960_Controllers[ControllerNumber];
 	if (Controller == NULL)
-		break;
+		goto out;
 	if (Controller->FirmwareType != DAC960_V2_Controller){
 		ErrorCode = -EINVAL;
-		break;
+		goto out;
 	}
 	DataTransferLength = UserCommand.DataTransferLength;
     	ErrorCode = -ENOMEM;
@@ -6884,14 +6870,14 @@ static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
                                                        DataTransferLength,
                                                        &DataTransferBufferDMA);
 	    if (DataTransferBuffer == NULL)
-	    	break;
+		goto out;
 	  }
 	else if (DataTransferLength < 0)
 	  {
 	    DataTransferBuffer = pci_alloc_consistent(Controller->PCIDevice,
 				-DataTransferLength, &DataTransferBufferDMA);
 	    if (DataTransferBuffer == NULL)
-	    	break;
+		goto out;
 	    if (copy_from_user(DataTransferBuffer,
 			       UserCommand.DataTransferBuffer,
 			       -DataTransferLength)) {
@@ -7001,42 +6987,44 @@ static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
 	if (RequestSenseBuffer != NULL)
 	  pci_free_consistent(Controller->PCIDevice, RequestSenseLength,
 		RequestSenseBuffer, RequestSenseBufferDMA);
-        break;
-      }
-    case DAC960_IOCTL_V2_GET_HEALTH_STATUS:
-      {
-	DAC960_V2_GetHealthStatus_T __user *UserSpaceGetHealthStatus =
-	  (DAC960_V2_GetHealthStatus_T __user *) Argument;
+out:
+        return ErrorCode;
+}
+
+static long DAC960_gam_v2_get_health_status(DAC960_V2_GetHealthStatus_T __user *UserSpaceGetHealthStatus)
+{
 	DAC960_V2_GetHealthStatus_T GetHealthStatus;
 	DAC960_V2_HealthStatusBuffer_T HealthStatusBuffer;
 	DAC960_Controller_T *Controller;
 	int ControllerNumber;
+	long ErrorCode;
+
 	if (UserSpaceGetHealthStatus == NULL) {
 		ErrorCode = -EINVAL;
-		break;
+		goto out;
 	}
 	if (copy_from_user(&GetHealthStatus, UserSpaceGetHealthStatus,
 			   sizeof(DAC960_V2_GetHealthStatus_T))) {
 		ErrorCode = -EFAULT;
-		break;
+		goto out;
 	}
 	ErrorCode = -ENXIO;
 	ControllerNumber = GetHealthStatus.ControllerNumber;
 	if (ControllerNumber < 0 ||
 	    ControllerNumber > DAC960_ControllerCount - 1)
-		    break;
+		goto out;
 	Controller = DAC960_Controllers[ControllerNumber];
 	if (Controller == NULL)
-		break;
+		goto out;
 	if (Controller->FirmwareType != DAC960_V2_Controller) {
 		ErrorCode = -EINVAL;
-		break;
+		goto out;
 	}
 	if (copy_from_user(&HealthStatusBuffer,
 			   GetHealthStatus.HealthStatusBuffer,
 			   sizeof(DAC960_V2_HealthStatusBuffer_T))) {
 		ErrorCode = -EFAULT;
-		break;
+		goto out;
 	}
 	ErrorCode = wait_event_interruptible_timeout(Controller->HealthStatusWaitQueue,
 			!(Controller->V2.HealthStatusBuffer->StatusChangeCounter
@@ -7046,7 +7034,7 @@ static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
 			DAC960_MonitoringTimerInterval);
 	if (ErrorCode == -ERESTARTSYS) {
 		ErrorCode = -EINTR;
-		break;
+		goto out;
 	}
 	if (copy_to_user(GetHealthStatus.HealthStatusBuffer,
 			 Controller->V2.HealthStatusBuffer,
@@ -7054,7 +7042,39 @@ static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
 		ErrorCode = -EFAULT;
 	else
 		ErrorCode =  0;
-      }
+
+out:
+	return ErrorCode;
+}
+
+/*
+ * DAC960_gam_ioctl is the ioctl function for performing RAID operations.
+*/
+
+static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
+						unsigned long Argument)
+{
+  long ErrorCode = 0;
+  void __user *argp = (void __user *)Argument;
+  if (!capable(CAP_SYS_ADMIN)) return -EACCES;
+
+  mutex_lock(&DAC960_mutex);
+  switch (Request)
+    {
+    case DAC960_IOCTL_GET_CONTROLLER_COUNT:
+      ErrorCode = DAC960_ControllerCount;
+      break;
+    case DAC960_IOCTL_GET_CONTROLLER_INFO:
+      ErrorCode = DAC960_gam_get_controller_info(argp);
+      break;
+    case DAC960_IOCTL_V1_EXECUTE_COMMAND:
+      ErrorCode = DAC960_gam_v1_execute_command(argp);
+      break;
+    case DAC960_IOCTL_V2_EXECUTE_COMMAND:
+      ErrorCode = DAC960_gam_v2_execute_command(argp);
+      break;
+    case DAC960_IOCTL_V2_GET_HEALTH_STATUS:
+      ErrorCode = DAC960_gam_v2_get_health_status(argp);
       break;
       default:
 	ErrorCode = -ENOTTY;
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 40579d0cb3d1..ad9b687a236a 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -20,6 +20,10 @@ config BLK_DEV_NULL_BLK
 	tristate "Null test block driver"
 	select CONFIGFS_FS
 
+config BLK_DEV_NULL_BLK_FAULT_INJECTION
+	bool "Support fault injection for Null test block driver"
+	depends on BLK_DEV_NULL_BLK && FAULT_INJECTION
+
 config BLK_DEV_FD
 	tristate "Normal floppy disk support"
 	depends on ARCH_MAY_HAVE_PC_FDC
diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h
index 9220f8e833d0..c0ebda1283cc 100644
--- a/drivers/block/aoe/aoe.h
+++ b/drivers/block/aoe/aoe.h
@@ -112,8 +112,7 @@ enum frame_flags {
 struct frame {
 	struct list_head head;
 	u32 tag;
-	struct timeval sent;	/* high-res time packet was sent */
-	u32 sent_jiffs;		/* low-res jiffies-based sent time */
+	ktime_t sent;			/* high-res time packet was sent */
 	ulong waited;
 	ulong waited_total;
 	struct aoetgt *t;		/* parent target I belong to */
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 812fed069708..540bb60cd071 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -398,8 +398,7 @@ aoecmd_ata_rw(struct aoedev *d)
 
 	skb = skb_clone(f->skb, GFP_ATOMIC);
 	if (skb) {
-		do_gettimeofday(&f->sent);
-		f->sent_jiffs = (u32) jiffies;
+		f->sent = ktime_get();
 		__skb_queue_head_init(&queue);
 		__skb_queue_tail(&queue, skb);
 		aoenet_xmit(&queue);
@@ -489,8 +488,7 @@ resend(struct aoedev *d, struct frame *f)
 	skb = skb_clone(skb, GFP_ATOMIC);
 	if (skb == NULL)
 		return;
-	do_gettimeofday(&f->sent);
-	f->sent_jiffs = (u32) jiffies;
+	f->sent = ktime_get();
 	__skb_queue_head_init(&queue);
 	__skb_queue_tail(&queue, skb);
 	aoenet_xmit(&queue);
@@ -499,33 +497,17 @@ resend(struct aoedev *d, struct frame *f)
 static int
 tsince_hr(struct frame *f)
 {
-	struct timeval now;
-	int n;
+	u64 delta = ktime_to_ns(ktime_sub(ktime_get(), f->sent));
 
-	do_gettimeofday(&now);
-	n = now.tv_usec - f->sent.tv_usec;
-	n += (now.tv_sec - f->sent.tv_sec) * USEC_PER_SEC;
+	/* delta is normally under 4.2 seconds, avoid 64-bit division */
+	if (likely(delta <= UINT_MAX))
+		return (u32)delta / NSEC_PER_USEC;
 
-	if (n < 0)
-		n = -n;
+	/* avoid overflow after 71 minutes */
+	if (delta > ((u64)INT_MAX * NSEC_PER_USEC))
+		return INT_MAX;
 
-	/* For relatively long periods, use jiffies to avoid
-	 * discrepancies caused by updates to the system time.
-	 *
-	 * On system with HZ of 1000, 32-bits is over 49 days
-	 * worth of jiffies, or over 71 minutes worth of usecs.
-	 *
-	 * Jiffies overflow is handled by subtraction of unsigned ints:
-	 * (gdb) print (unsigned) 2 - (unsigned) 0xfffffffe
-	 * $3 = 4
-	 * (gdb)
-	 */
-	if (n > USEC_PER_SEC / 4) {
-		n = ((u32) jiffies) - f->sent_jiffs;
-		n *= USEC_PER_SEC / HZ;
-	}
-
-	return n;
+	return div_u64(delta, NSEC_PER_USEC);
 }
 
 static int
@@ -589,7 +571,6 @@ reassign_frame(struct frame *f)
 	nf->waited = 0;
 	nf->waited_total = f->waited_total;
 	nf->sent = f->sent;
-	nf->sent_jiffs = f->sent_jiffs;
 	f->skb = skb;
 
 	return nf;
@@ -633,8 +614,7 @@ probe(struct aoetgt *t)
 
 	skb = skb_clone(f->skb, GFP_ATOMIC);
 	if (skb) {
-		do_gettimeofday(&f->sent);
-		f->sent_jiffs = (u32) jiffies;
+		f->sent = ktime_get();
 		__skb_queue_head_init(&queue);
 		__skb_queue_tail(&queue, skb);
 		aoenet_xmit(&queue);
@@ -1432,10 +1412,8 @@ aoecmd_ata_id(struct aoedev *d)
 	d->timer.function = rexmit_timer;
 
 	skb = skb_clone(skb, GFP_ATOMIC);
-	if (skb) {
-		do_gettimeofday(&f->sent);
-		f->sent_jiffs = (u32) jiffies;
-	}
+	if (skb)
+		f->sent = ktime_get();
 
 	return skb;
 }
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index bd97908c766f..9f4e6f502b84 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -953,7 +953,7 @@ static void drbd_bm_endio(struct bio *bio)
 	struct drbd_bm_aio_ctx *ctx = bio->bi_private;
 	struct drbd_device *device = ctx->device;
 	struct drbd_bitmap *b = device->bitmap;
-	unsigned int idx = bm_page_to_idx(bio->bi_io_vec[0].bv_page);
+	unsigned int idx = bm_page_to_idx(bio_first_page_all(bio));
 
 	if ((ctx->flags & BM_AIO_COPY_PAGES) == 0 &&
 	    !bm_test_page_unchanged(b->bm_pages[idx]))
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 4b4697a1f963..0a0394aa1b9c 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1847,7 +1847,7 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock,
 	      void *buf, size_t size, unsigned msg_flags)
 {
 	struct kvec iov = {.iov_base = buf, .iov_len = size};
-	struct msghdr msg;
+	struct msghdr msg = {.msg_flags = msg_flags | MSG_NOSIGNAL};
 	int rv, sent = 0;
 
 	if (!sock)
@@ -1855,12 +1855,6 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock,
 
 	/* THINK  if (signal_pending) return ... ? */
 
-	msg.msg_name       = NULL;
-	msg.msg_namelen    = 0;
-	msg.msg_control    = NULL;
-	msg.msg_controllen = 0;
-	msg.msg_flags      = msg_flags | MSG_NOSIGNAL;
-
 	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iov, 1, size);
 
 	if (sock == connection->data.socket) {
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index cb2fa63f6bc0..c72dee0ef083 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -516,7 +516,8 @@ static int drbd_recv_short(struct socket *sock, void *buf, size_t size, int flag
 	struct msghdr msg = {
 		.msg_flags = (flags ? flags : MSG_WAITALL | MSG_NOSIGNAL)
 	};
-	return kernel_recvmsg(sock, &msg, &iov, 1, size, msg.msg_flags);
+	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, size);
+	return sock_recvmsg(sock, &msg, msg.msg_flags);
 }
 
 static int drbd_recv(struct drbd_connection *connection, void *buf, size_t size)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index bc8e61506968..d5fe720cf149 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1581,9 +1581,8 @@ out:
 	return err;
 }
 
-static void lo_release(struct gendisk *disk, fmode_t mode)
+static void __lo_release(struct loop_device *lo)
 {
-	struct loop_device *lo = disk->private_data;
 	int err;
 
 	if (atomic_dec_return(&lo->lo_refcnt))
@@ -1610,6 +1609,13 @@ static void lo_release(struct gendisk *disk, fmode_t mode)
 	mutex_unlock(&lo->lo_ctl_mutex);
 }
 
+static void lo_release(struct gendisk *disk, fmode_t mode)
+{
+	mutex_lock(&loop_index_mutex);
+	__lo_release(disk->private_data);
+	mutex_unlock(&loop_index_mutex);
+}
+
 static const struct block_device_operations lo_fops = {
 	.owner =	THIS_MODULE,
 	.open =		lo_open,
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index c61960deb74a..6655893a3a7a 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -12,9 +12,9 @@
 #include <linux/slab.h>
 #include <linux/blk-mq.h>
 #include <linux/hrtimer.h>
-#include <linux/lightnvm.h>
 #include <linux/configfs.h>
 #include <linux/badblocks.h>
+#include <linux/fault-inject.h>
 
 #define SECTOR_SHIFT		9
 #define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
@@ -27,6 +27,10 @@
 #define TICKS_PER_SEC		50ULL
 #define TIMER_INTERVAL		(NSEC_PER_SEC / TICKS_PER_SEC)
 
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+static DECLARE_FAULT_ATTR(null_timeout_attr);
+#endif
+
 static inline u64 mb_per_tick(int mbps)
 {
 	return (1 << 20) / TICKS_PER_SEC * ((u64) mbps);
@@ -35,13 +39,13 @@ static inline u64 mb_per_tick(int mbps)
 struct nullb_cmd {
 	struct list_head list;
 	struct llist_node ll_list;
-	call_single_data_t csd;
+	struct __call_single_data csd;
 	struct request *rq;
 	struct bio *bio;
 	unsigned int tag;
+	blk_status_t error;
 	struct nullb_queue *nq;
 	struct hrtimer timer;
-	blk_status_t error;
 };
 
 struct nullb_queue {
@@ -107,7 +111,6 @@ struct nullb_device {
 	unsigned int hw_queue_depth; /* queue depth */
 	unsigned int index; /* index of the disk, only valid with a disk */
 	unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
-	bool use_lightnvm; /* register as a LightNVM device */
 	bool blocking; /* blocking blk-mq device */
 	bool use_per_node_hctx; /* use per-node allocation for hardware context */
 	bool power; /* power on/off the device */
@@ -121,7 +124,6 @@ struct nullb {
 	unsigned int index;
 	struct request_queue *q;
 	struct gendisk *disk;
-	struct nvm_dev *ndev;
 	struct blk_mq_tag_set *tag_set;
 	struct blk_mq_tag_set __tag_set;
 	unsigned int queue_depth;
@@ -139,7 +141,6 @@ static LIST_HEAD(nullb_list);
 static struct mutex lock;
 static int null_major;
 static DEFINE_IDA(nullb_indexes);
-static struct kmem_cache *ppa_cache;
 static struct blk_mq_tag_set tag_set;
 
 enum {
@@ -166,6 +167,11 @@ static int g_home_node = NUMA_NO_NODE;
 module_param_named(home_node, g_home_node, int, S_IRUGO);
 MODULE_PARM_DESC(home_node, "Home node for the device");
 
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+static char g_timeout_str[80];
+module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), S_IRUGO);
+#endif
+
 static int g_queue_mode = NULL_Q_MQ;
 
 static int null_param_store_val(const char *str, int *val, int min, int max)
@@ -208,10 +214,6 @@ static int nr_devices = 1;
 module_param(nr_devices, int, S_IRUGO);
 MODULE_PARM_DESC(nr_devices, "Number of devices to register");
 
-static bool g_use_lightnvm;
-module_param_named(use_lightnvm, g_use_lightnvm, bool, S_IRUGO);
-MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device");
-
 static bool g_blocking;
 module_param_named(blocking, g_blocking, bool, S_IRUGO);
 MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
@@ -345,7 +347,6 @@ NULLB_DEVICE_ATTR(blocksize, uint);
 NULLB_DEVICE_ATTR(irqmode, uint);
 NULLB_DEVICE_ATTR(hw_queue_depth, uint);
 NULLB_DEVICE_ATTR(index, uint);
-NULLB_DEVICE_ATTR(use_lightnvm, bool);
 NULLB_DEVICE_ATTR(blocking, bool);
 NULLB_DEVICE_ATTR(use_per_node_hctx, bool);
 NULLB_DEVICE_ATTR(memory_backed, bool);
@@ -455,7 +456,6 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_irqmode,
 	&nullb_device_attr_hw_queue_depth,
 	&nullb_device_attr_index,
-	&nullb_device_attr_use_lightnvm,
 	&nullb_device_attr_blocking,
 	&nullb_device_attr_use_per_node_hctx,
 	&nullb_device_attr_power,
@@ -471,7 +471,6 @@ static void nullb_device_release(struct config_item *item)
 {
 	struct nullb_device *dev = to_nullb_device(item);
 
-	badblocks_exit(&dev->badblocks);
 	null_free_device_storage(dev, false);
 	null_free_dev(dev);
 }
@@ -574,7 +573,6 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->blocksize = g_bs;
 	dev->irqmode = g_irqmode;
 	dev->hw_queue_depth = g_hw_queue_depth;
-	dev->use_lightnvm = g_use_lightnvm;
 	dev->blocking = g_blocking;
 	dev->use_per_node_hctx = g_use_per_node_hctx;
 	return dev;
@@ -582,6 +580,10 @@ static struct nullb_device *null_alloc_dev(void)
 
 static void null_free_dev(struct nullb_device *dev)
 {
+	if (!dev)
+		return;
+
+	badblocks_exit(&dev->badblocks);
 	kfree(dev);
 }
 
@@ -1349,6 +1351,12 @@ static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
 	return BLK_QC_T_NONE;
 }
 
+static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq)
+{
+	pr_info("null: rq %p timed out\n", rq);
+	return BLK_EH_HANDLED;
+}
+
 static int null_rq_prep_fn(struct request_queue *q, struct request *req)
 {
 	struct nullb *nullb = q->queuedata;
@@ -1366,6 +1374,16 @@ static int null_rq_prep_fn(struct request_queue *q, struct request *req)
 	return BLKPREP_DEFER;
 }
 
+static bool should_timeout_request(struct request *rq)
+{
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+	if (g_timeout_str[0])
+		return should_fail(&null_timeout_attr, 1);
+#endif
+
+	return false;
+}
+
 static void null_request_fn(struct request_queue *q)
 {
 	struct request *rq;
@@ -1373,12 +1391,20 @@ static void null_request_fn(struct request_queue *q)
 	while ((rq = blk_fetch_request(q)) != NULL) {
 		struct nullb_cmd *cmd = rq->special;
 
-		spin_unlock_irq(q->queue_lock);
-		null_handle_cmd(cmd);
-		spin_lock_irq(q->queue_lock);
+		if (!should_timeout_request(rq)) {
+			spin_unlock_irq(q->queue_lock);
+			null_handle_cmd(cmd);
+			spin_lock_irq(q->queue_lock);
+		}
 	}
 }
 
+static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
+{
+	pr_info("null: rq %p timed out\n", rq);
+	return BLK_EH_HANDLED;
+}
+
 static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 			 const struct blk_mq_queue_data *bd)
 {
@@ -1396,12 +1422,16 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	blk_mq_start_request(bd->rq);
 
-	return null_handle_cmd(cmd);
+	if (!should_timeout_request(bd->rq))
+		return null_handle_cmd(cmd);
+
+	return BLK_STS_OK;
 }
 
 static const struct blk_mq_ops null_mq_ops = {
 	.queue_rq       = null_queue_rq,
 	.complete	= null_softirq_done_fn,
+	.timeout	= null_timeout_rq,
 };
 
 static void cleanup_queue(struct nullb_queue *nq)
@@ -1420,170 +1450,6 @@ static void cleanup_queues(struct nullb *nullb)
 	kfree(nullb->queues);
 }
 
-#ifdef CONFIG_NVM
-
-static void null_lnvm_end_io(struct request *rq, blk_status_t status)
-{
-	struct nvm_rq *rqd = rq->end_io_data;
-
-	/* XXX: lighnvm core seems to expect NVM_RSP_* values here.. */
-	rqd->error = status ? -EIO : 0;
-	nvm_end_io(rqd);
-
-	blk_put_request(rq);
-}
-
-static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
-{
-	struct request_queue *q = dev->q;
-	struct request *rq;
-	struct bio *bio = rqd->bio;
-
-	rq = blk_mq_alloc_request(q,
-		op_is_write(bio_op(bio)) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
-	if (IS_ERR(rq))
-		return -ENOMEM;
-
-	blk_init_request_from_bio(rq, bio);
-
-	rq->end_io_data = rqd;
-
-	blk_execute_rq_nowait(q, NULL, rq, 0, null_lnvm_end_io);
-
-	return 0;
-}
-
-static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id)
-{
-	struct nullb *nullb = dev->q->queuedata;
-	sector_t size = (sector_t)nullb->dev->size * 1024 * 1024ULL;
-	sector_t blksize;
-	struct nvm_id_group *grp;
-
-	id->ver_id = 0x1;
-	id->vmnt = 0;
-	id->cap = 0x2;
-	id->dom = 0x1;
-
-	id->ppaf.blk_offset = 0;
-	id->ppaf.blk_len = 16;
-	id->ppaf.pg_offset = 16;
-	id->ppaf.pg_len = 16;
-	id->ppaf.sect_offset = 32;
-	id->ppaf.sect_len = 8;
-	id->ppaf.pln_offset = 40;
-	id->ppaf.pln_len = 8;
-	id->ppaf.lun_offset = 48;
-	id->ppaf.lun_len = 8;
-	id->ppaf.ch_offset = 56;
-	id->ppaf.ch_len = 8;
-
-	sector_div(size, nullb->dev->blocksize); /* convert size to pages */
-	size >>= 8; /* concert size to pgs pr blk */
-	grp = &id->grp;
-	grp->mtype = 0;
-	grp->fmtype = 0;
-	grp->num_ch = 1;
-	grp->num_pg = 256;
-	blksize = size;
-	size >>= 16;
-	grp->num_lun = size + 1;
-	sector_div(blksize, grp->num_lun);
-	grp->num_blk = blksize;
-	grp->num_pln = 1;
-
-	grp->fpg_sz = nullb->dev->blocksize;
-	grp->csecs = nullb->dev->blocksize;
-	grp->trdt = 25000;
-	grp->trdm = 25000;
-	grp->tprt = 500000;
-	grp->tprm = 500000;
-	grp->tbet = 1500000;
-	grp->tbem = 1500000;
-	grp->mpos = 0x010101; /* single plane rwe */
-	grp->cpar = nullb->dev->hw_queue_depth;
-
-	return 0;
-}
-
-static void *null_lnvm_create_dma_pool(struct nvm_dev *dev, char *name)
-{
-	mempool_t *virtmem_pool;
-
-	virtmem_pool = mempool_create_slab_pool(64, ppa_cache);
-	if (!virtmem_pool) {
-		pr_err("null_blk: Unable to create virtual memory pool\n");
-		return NULL;
-	}
-
-	return virtmem_pool;
-}
-
-static void null_lnvm_destroy_dma_pool(void *pool)
-{
-	mempool_destroy(pool);
-}
-
-static void *null_lnvm_dev_dma_alloc(struct nvm_dev *dev, void *pool,
-				gfp_t mem_flags, dma_addr_t *dma_handler)
-{
-	return mempool_alloc(pool, mem_flags);
-}
-
-static void null_lnvm_dev_dma_free(void *pool, void *entry,
-							dma_addr_t dma_handler)
-{
-	mempool_free(entry, pool);
-}
-
-static struct nvm_dev_ops null_lnvm_dev_ops = {
-	.identity		= null_lnvm_id,
-	.submit_io		= null_lnvm_submit_io,
-
-	.create_dma_pool	= null_lnvm_create_dma_pool,
-	.destroy_dma_pool	= null_lnvm_destroy_dma_pool,
-	.dev_dma_alloc		= null_lnvm_dev_dma_alloc,
-	.dev_dma_free		= null_lnvm_dev_dma_free,
-
-	/* Simulate nvme protocol restriction */
-	.max_phys_sect		= 64,
-};
-
-static int null_nvm_register(struct nullb *nullb)
-{
-	struct nvm_dev *dev;
-	int rv;
-
-	dev = nvm_alloc_dev(0);
-	if (!dev)
-		return -ENOMEM;
-
-	dev->q = nullb->q;
-	memcpy(dev->name, nullb->disk_name, DISK_NAME_LEN);
-	dev->ops = &null_lnvm_dev_ops;
-
-	rv = nvm_register(dev);
-	if (rv) {
-		kfree(dev);
-		return rv;
-	}
-	nullb->ndev = dev;
-	return 0;
-}
-
-static void null_nvm_unregister(struct nullb *nullb)
-{
-	nvm_unregister(nullb->ndev);
-}
-#else
-static int null_nvm_register(struct nullb *nullb)
-{
-	pr_err("null_blk: CONFIG_NVM needs to be enabled for LightNVM\n");
-	return -EINVAL;
-}
-static void null_nvm_unregister(struct nullb *nullb) {}
-#endif /* CONFIG_NVM */
-
 static void null_del_dev(struct nullb *nullb)
 {
 	struct nullb_device *dev = nullb->dev;
@@ -1592,10 +1458,7 @@ static void null_del_dev(struct nullb *nullb)
 
 	list_del_init(&nullb->list);
 
-	if (dev->use_lightnvm)
-		null_nvm_unregister(nullb);
-	else
-		del_gendisk(nullb->disk);
+	del_gendisk(nullb->disk);
 
 	if (test_bit(NULLB_DEV_FL_THROTTLED, &nullb->dev->flags)) {
 		hrtimer_cancel(&nullb->bw_timer);
@@ -1607,8 +1470,7 @@ static void null_del_dev(struct nullb *nullb)
 	if (dev->queue_mode == NULL_Q_MQ &&
 	    nullb->tag_set == &nullb->__tag_set)
 		blk_mq_free_tag_set(nullb->tag_set);
-	if (!dev->use_lightnvm)
-		put_disk(nullb->disk);
+	put_disk(nullb->disk);
 	cleanup_queues(nullb);
 	if (null_cache_active(nullb))
 		null_free_device_storage(nullb->dev, true);
@@ -1772,11 +1634,6 @@ static void null_validate_conf(struct nullb_device *dev)
 {
 	dev->blocksize = round_down(dev->blocksize, 512);
 	dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096);
-	if (dev->use_lightnvm && dev->blocksize != 4096)
-		dev->blocksize = 4096;
-
-	if (dev->use_lightnvm && dev->queue_mode != NULL_Q_MQ)
-		dev->queue_mode = NULL_Q_MQ;
 
 	if (dev->queue_mode == NULL_Q_MQ && dev->use_per_node_hctx) {
 		if (dev->submit_queues != nr_online_nodes)
@@ -1802,6 +1659,20 @@ static void null_validate_conf(struct nullb_device *dev)
 		dev->mbps = 0;
 }
 
+static bool null_setup_fault(void)
+{
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+	if (!g_timeout_str[0])
+		return true;
+
+	if (!setup_fault_attr(&null_timeout_attr, g_timeout_str))
+		return false;
+
+	null_timeout_attr.verbose = 0;
+#endif
+	return true;
+}
+
 static int null_add_dev(struct nullb_device *dev)
 {
 	struct nullb *nullb;
@@ -1835,6 +1706,10 @@ static int null_add_dev(struct nullb_device *dev)
 		if (rv)
 			goto out_cleanup_queues;
 
+		if (!null_setup_fault())
+			goto out_cleanup_queues;
+
+		nullb->tag_set->timeout = 5 * HZ;
 		nullb->q = blk_mq_init_queue(nullb->tag_set);
 		if (IS_ERR(nullb->q)) {
 			rv = -ENOMEM;
@@ -1858,8 +1733,14 @@ static int null_add_dev(struct nullb_device *dev)
 			rv = -ENOMEM;
 			goto out_cleanup_queues;
 		}
+
+		if (!null_setup_fault())
+			goto out_cleanup_blk_queue;
+
 		blk_queue_prep_rq(nullb->q, null_rq_prep_fn);
 		blk_queue_softirq_done(nullb->q, null_softirq_done_fn);
+		blk_queue_rq_timed_out(nullb->q, null_rq_timed_out_fn);
+		nullb->q->rq_timeout = 5 * HZ;
 		rv = init_driver_queues(nullb);
 		if (rv)
 			goto out_cleanup_blk_queue;
@@ -1892,11 +1773,7 @@ static int null_add_dev(struct nullb_device *dev)
 
 	sprintf(nullb->disk_name, "nullb%d", nullb->index);
 
-	if (dev->use_lightnvm)
-		rv = null_nvm_register(nullb);
-	else
-		rv = null_gendisk_register(nullb);
-
+	rv = null_gendisk_register(nullb);
 	if (rv)
 		goto out_cleanup_blk_queue;
 
@@ -1935,18 +1812,6 @@ static int __init null_init(void)
 		g_bs = PAGE_SIZE;
 	}
 
-	if (g_use_lightnvm && g_bs != 4096) {
-		pr_warn("null_blk: LightNVM only supports 4k block size\n");
-		pr_warn("null_blk: defaults block size to 4k\n");
-		g_bs = 4096;
-	}
-
-	if (g_use_lightnvm && g_queue_mode != NULL_Q_MQ) {
-		pr_warn("null_blk: LightNVM only supported for blk-mq\n");
-		pr_warn("null_blk: defaults queue mode to blk-mq\n");
-		g_queue_mode = NULL_Q_MQ;
-	}
-
 	if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
 		if (g_submit_queues != nr_online_nodes) {
 			pr_warn("null_blk: submit_queues param is set to %u.\n",
@@ -1979,16 +1844,6 @@ static int __init null_init(void)
 		goto err_conf;
 	}
 
-	if (g_use_lightnvm) {
-		ppa_cache = kmem_cache_create("ppa_cache", 64 * sizeof(u64),
-								0, 0, NULL);
-		if (!ppa_cache) {
-			pr_err("null_blk: unable to create ppa cache\n");
-			ret = -ENOMEM;
-			goto err_ppa;
-		}
-	}
-
 	for (i = 0; i < nr_devices; i++) {
 		dev = null_alloc_dev();
 		if (!dev) {
@@ -2012,8 +1867,6 @@ err_dev:
 		null_del_dev(nullb);
 		null_free_dev(dev);
 	}
-	kmem_cache_destroy(ppa_cache);
-err_ppa:
 	unregister_blkdev(null_major, "nullb");
 err_conf:
 	configfs_unregister_subsystem(&nullb_subsys);
@@ -2044,8 +1897,6 @@ static void __exit null_exit(void)
 
 	if (g_queue_mode == NULL_Q_MQ && shared_tags)
 		blk_mq_free_tag_set(&tag_set);
-
-	kmem_cache_destroy(ppa_cache);
 }
 
 module_init(null_init);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 67974796c350..531a0915066b 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2579,14 +2579,14 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	bdev = bdget(dev);
 	if (!bdev)
 		return -ENOMEM;
+	ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY, NULL);
+	if (ret)
+		return ret;
 	if (!blk_queue_scsi_passthrough(bdev_get_queue(bdev))) {
 		WARN_ONCE(true, "Attempt to register a non-SCSI queue\n");
-		bdput(bdev);
+		blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
 		return -EINVAL;
 	}
-	ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY, NULL);
-	if (ret)
-		return ret;
 
 	/* This is safe, since we have a reference from open(). */
 	__module_get(THIS_MODULE);
@@ -2745,7 +2745,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 	pd->pkt_dev = MKDEV(pktdev_major, idx);
 	ret = pkt_new_dev(pd, dev);
 	if (ret)
-		goto out_new_dev;
+		goto out_mem2;
 
 	/* inherit events of the host device */
 	disk->events = pd->bdev->bd_disk->events;
@@ -2763,8 +2763,6 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 	mutex_unlock(&ctl_mutex);
 	return 0;
 
-out_new_dev:
-	blk_cleanup_queue(disk->queue);
 out_mem2:
 	put_disk(disk);
 out_mem:
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 38fc5f397fde..cc93522a6d41 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3047,13 +3047,21 @@ static void format_lock_cookie(struct rbd_device *rbd_dev, char *buf)
 	mutex_unlock(&rbd_dev->watch_mutex);
 }
 
+static void __rbd_lock(struct rbd_device *rbd_dev, const char *cookie)
+{
+	struct rbd_client_id cid = rbd_get_cid(rbd_dev);
+
+	strcpy(rbd_dev->lock_cookie, cookie);
+	rbd_set_owner_cid(rbd_dev, &cid);
+	queue_work(rbd_dev->task_wq, &rbd_dev->acquired_lock_work);
+}
+
 /*
  * lock_rwsem must be held for write
  */
 static int rbd_lock(struct rbd_device *rbd_dev)
 {
 	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
-	struct rbd_client_id cid = rbd_get_cid(rbd_dev);
 	char cookie[32];
 	int ret;
 
@@ -3068,9 +3076,7 @@ static int rbd_lock(struct rbd_device *rbd_dev)
 		return ret;
 
 	rbd_dev->lock_state = RBD_LOCK_STATE_LOCKED;
-	strcpy(rbd_dev->lock_cookie, cookie);
-	rbd_set_owner_cid(rbd_dev, &cid);
-	queue_work(rbd_dev->task_wq, &rbd_dev->acquired_lock_work);
+	__rbd_lock(rbd_dev, cookie);
 	return 0;
 }
 
@@ -3856,7 +3862,7 @@ static void rbd_reacquire_lock(struct rbd_device *rbd_dev)
 			queue_delayed_work(rbd_dev->task_wq,
 					   &rbd_dev->lock_dwork, 0);
 	} else {
-		strcpy(rbd_dev->lock_cookie, cookie);
+		__rbd_lock(rbd_dev, cookie);
 	}
 }
 
@@ -4381,7 +4387,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	segment_size = rbd_obj_bytes(&rbd_dev->header);
 	blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE);
 	q->limits.max_sectors = queue_max_hw_sectors(q);
-	blk_queue_max_segments(q, segment_size / SECTOR_SIZE);
+	blk_queue_max_segments(q, USHRT_MAX);
 	blk_queue_max_segment_size(q, segment_size);
 	blk_queue_io_min(q, segment_size);
 	blk_queue_io_opt(q, segment_size);
diff --git a/drivers/block/smart1,2.h b/drivers/block/smart1,2.h
deleted file mode 100644
index e5565fbaeb30..000000000000
--- a/drivers/block/smart1,2.h
+++ /dev/null
@@ -1,278 +0,0 @@
-/*
- *    Disk Array driver for Compaq SMART2 Controllers
- *    Copyright 1998 Compaq Computer Corporation
- *
- *    This program is free software; you can redistribute it and/or modify
- *    it under the terms of the GNU General Public License as published by
- *    the Free Software Foundation; either version 2 of the License, or
- *    (at your option) any later version.
- *
- *    This program is distributed in the hope that it will be useful,
- *    but WITHOUT ANY WARRANTY; without even the implied warranty of
- *    MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- *    NON INFRINGEMENT.  See the GNU General Public License for more details.
- *
- *    You should have received a copy of the GNU General Public License
- *    along with this program; if not, write to the Free Software
- *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- *    Questions/Comments/Bugfixes to iss_storagedev@hp.com
- *
- *    If you want to make changes, improve or add functionality to this
- *    driver, you'll probably need the Compaq Array Controller Interface
- *    Specificiation (Document number ECG086/1198)
- */
-
-/*
- * This file contains the controller communication implementation for
- * Compaq SMART-1 and SMART-2 controllers.  To the best of my knowledge,
- * this should support:
- *
- *  PCI:
- *  SMART-2/P, SMART-2DH, SMART-2SL, SMART-221, SMART-3100ES, SMART-3200
- *  Integerated SMART Array Controller, SMART-4200, SMART-4250ES
- *
- *  EISA:
- *  SMART-2/E, SMART, IAES, IDA-2, IDA
- */
-
-/*
- * Memory mapped FIFO interface (SMART 42xx cards)
- */
-static void smart4_submit_command(ctlr_info_t *h, cmdlist_t *c)
-{
-        writel(c->busaddr, h->vaddr + S42XX_REQUEST_PORT_OFFSET);
-}
-
-/*  
- *  This card is the opposite of the other cards.  
- *   0 turns interrupts on... 
- *   0x08 turns them off... 
- */
-static void smart4_intr_mask(ctlr_info_t *h, unsigned long val)
-{
-	if (val) 
-	{ /* Turn interrupts on */
-		writel(0, h->vaddr + S42XX_REPLY_INTR_MASK_OFFSET);
-	} else /* Turn them off */
-	{
-        	writel( S42XX_INTR_OFF, 
-			h->vaddr + S42XX_REPLY_INTR_MASK_OFFSET);
-	}
-}
-
-/*
- *  For older cards FIFO Full = 0. 
- *  On this card 0 means there is room, anything else FIFO Full. 
- * 
- */ 
-static unsigned long smart4_fifo_full(ctlr_info_t *h)
-{
-	
-        return (!readl(h->vaddr + S42XX_REQUEST_PORT_OFFSET));
-}
-
-/* This type of controller returns -1 if the fifo is empty, 
- *    Not 0 like the others.
- *    And we need to let it know we read a value out 
- */ 
-static unsigned long smart4_completed(ctlr_info_t *h)
-{
-	long register_value 
-		= readl(h->vaddr + S42XX_REPLY_PORT_OFFSET);
-
-	/* Fifo is empty */
-	if( register_value == 0xffffffff)
-		return 0; 	
-
-	/* Need to let it know we got the reply */
-	/* We do this by writing a 0 to the port we just read from */
-	writel(0, h->vaddr + S42XX_REPLY_PORT_OFFSET);
-
-	return ((unsigned long) register_value); 
-}
-
- /*
- *  This hardware returns interrupt pending at a different place and 
- *  it does not tell us if the fifo is empty, we will have check  
- *  that by getting a 0 back from the command_completed call. 
- */
-static unsigned long smart4_intr_pending(ctlr_info_t *h)
-{
-	unsigned long register_value  = 
-		readl(h->vaddr + S42XX_INTR_STATUS);
-
-	if( register_value &  S42XX_INTR_PENDING) 
-		return  FIFO_NOT_EMPTY;	
-	return 0 ;
-}
-
-static struct access_method smart4_access = {
-	smart4_submit_command,
-	smart4_intr_mask,
-	smart4_fifo_full,
-	smart4_intr_pending,
-	smart4_completed,
-};
-
-/*
- * Memory mapped FIFO interface (PCI SMART2 and SMART 3xxx cards)
- */
-static void smart2_submit_command(ctlr_info_t *h, cmdlist_t *c)
-{
-	writel(c->busaddr, h->vaddr + COMMAND_FIFO);
-}
-
-static void smart2_intr_mask(ctlr_info_t *h, unsigned long val)
-{
-	writel(val, h->vaddr + INTR_MASK);
-}
-
-static unsigned long smart2_fifo_full(ctlr_info_t *h)
-{
-	return readl(h->vaddr + COMMAND_FIFO);
-}
-
-static unsigned long smart2_completed(ctlr_info_t *h)
-{
-	return readl(h->vaddr + COMMAND_COMPLETE_FIFO);
-}
-
-static unsigned long smart2_intr_pending(ctlr_info_t *h)
-{
-	return readl(h->vaddr + INTR_PENDING);
-}
-
-static struct access_method smart2_access = {
-	smart2_submit_command,
-	smart2_intr_mask,
-	smart2_fifo_full,
-	smart2_intr_pending,
-	smart2_completed,
-};
-
-/*
- *  IO access for SMART-2/E cards
- */
-static void smart2e_submit_command(ctlr_info_t *h, cmdlist_t *c)
-{
-	outl(c->busaddr, h->io_mem_addr + COMMAND_FIFO);
-}
-
-static void smart2e_intr_mask(ctlr_info_t *h, unsigned long val)
-{
-	outl(val, h->io_mem_addr + INTR_MASK);
-}
-
-static unsigned long smart2e_fifo_full(ctlr_info_t *h)
-{
-	return inl(h->io_mem_addr + COMMAND_FIFO);
-}
-
-static unsigned long smart2e_completed(ctlr_info_t *h)
-{
-	return inl(h->io_mem_addr + COMMAND_COMPLETE_FIFO);
-}
-
-static unsigned long smart2e_intr_pending(ctlr_info_t *h)
-{
-	return inl(h->io_mem_addr + INTR_PENDING);
-}
-
-static struct access_method smart2e_access = {
-	smart2e_submit_command,
-	smart2e_intr_mask,
-	smart2e_fifo_full,
-	smart2e_intr_pending,
-	smart2e_completed,
-};
-
-/*
- *  IO access for older SMART-1 type cards
- */
-#define SMART1_SYSTEM_MASK		0xC8E
-#define SMART1_SYSTEM_DOORBELL		0xC8F
-#define SMART1_LOCAL_MASK		0xC8C
-#define SMART1_LOCAL_DOORBELL		0xC8D
-#define SMART1_INTR_MASK		0xC89
-#define SMART1_LISTADDR			0xC90
-#define SMART1_LISTLEN			0xC94
-#define SMART1_TAG			0xC97
-#define SMART1_COMPLETE_ADDR		0xC98
-#define SMART1_LISTSTATUS		0xC9E
-
-#define CHANNEL_BUSY			0x01
-#define CHANNEL_CLEAR			0x02
-
-static void smart1_submit_command(ctlr_info_t *h, cmdlist_t *c)
-{
-	/*
-	 * This __u16 is actually a bunch of control flags on SMART
-	 * and below.  We want them all to be zero.
-	 */
-	c->hdr.size = 0;
-
-	outb(CHANNEL_CLEAR, h->io_mem_addr + SMART1_SYSTEM_DOORBELL);
-
-	outl(c->busaddr, h->io_mem_addr + SMART1_LISTADDR);
-	outw(c->size, h->io_mem_addr + SMART1_LISTLEN);
-
-	outb(CHANNEL_BUSY, h->io_mem_addr + SMART1_LOCAL_DOORBELL);
-}
-
-static void smart1_intr_mask(ctlr_info_t *h, unsigned long val)
-{
-	if (val == 1) {
-		outb(0xFD, h->io_mem_addr + SMART1_SYSTEM_DOORBELL);
-		outb(CHANNEL_BUSY, h->io_mem_addr + SMART1_LOCAL_DOORBELL);
-		outb(0x01, h->io_mem_addr + SMART1_INTR_MASK);
-		outb(0x01, h->io_mem_addr + SMART1_SYSTEM_MASK);
-	} else {
-		outb(0, h->io_mem_addr + 0xC8E);
-	}
-}
-
-static unsigned long smart1_fifo_full(ctlr_info_t *h)
-{
-	unsigned char chan;
-	chan = inb(h->io_mem_addr + SMART1_SYSTEM_DOORBELL) & CHANNEL_CLEAR;
-	return chan;
-}
-
-static unsigned long smart1_completed(ctlr_info_t *h)
-{
-	unsigned char status;
-	unsigned long cmd;
-
-	if (inb(h->io_mem_addr + SMART1_SYSTEM_DOORBELL) & CHANNEL_BUSY) {
-		outb(CHANNEL_BUSY, h->io_mem_addr + SMART1_SYSTEM_DOORBELL);
-
-		cmd = inl(h->io_mem_addr + SMART1_COMPLETE_ADDR);
-		status = inb(h->io_mem_addr + SMART1_LISTSTATUS);
-
-		outb(CHANNEL_CLEAR, h->io_mem_addr + SMART1_LOCAL_DOORBELL);
-
-		/*
-		 * this is x86 (actually compaq x86) only, so it's ok
-		 */
-		if (cmd) ((cmdlist_t*)bus_to_virt(cmd))->req.hdr.rcode = status;
-	} else {
-		cmd = 0;
-	}
-	return cmd;
-}
-
-static unsigned long smart1_intr_pending(ctlr_info_t *h)
-{
-	unsigned char chan;
-	chan = inb(h->io_mem_addr + SMART1_SYSTEM_DOORBELL) & CHANNEL_BUSY;
-	return chan;
-}
-
-static struct access_method smart1_access = {
-	smart1_submit_command,
-	smart1_intr_mask,
-	smart1_fifo_full,
-	smart1_intr_pending,
-	smart1_completed,
-};
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index d70eba30003a..0afa6c8c3857 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -430,7 +430,7 @@ static void put_entry_bdev(struct zram *zram, unsigned long entry)
 
 static void zram_page_end_io(struct bio *bio)
 {
-	struct page *page = bio->bi_io_vec[0].bv_page;
+	struct page *page = bio_first_page_all(bio);
 
 	page_endio(page, op_is_write(bio_op(bio)),
 			blk_status_to_errno(bio->bi_status));
diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 60e1c7d6986d..07e55cd8f8c8 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -31,6 +31,16 @@ config BT_HCIBTUSB
 	  Say Y here to compile support for Bluetooth USB devices into the
 	  kernel or say M to compile it as module (btusb).
 
+config BT_HCIBTUSB_AUTOSUSPEND
+	bool "Enable USB autosuspend for Bluetooth USB devices by default"
+	depends on BT_HCIBTUSB
+	help
+	  Say Y here to enable USB autosuspend for Bluetooth USB devices by
+	  default.
+
+	  This can be overridden by passing btusb.enable_autosuspend=[y|n]
+	  on the kernel commandline.
+
 config BT_HCIBTUSB_BCM
 	bool "Broadcom protocol support"
 	depends on BT_HCIBTUSB
@@ -67,6 +77,7 @@ config BT_HCIBTSDIO
 config BT_HCIUART
 	tristate "HCI UART driver"
 	depends on SERIAL_DEV_BUS || !SERIAL_DEV_BUS
+	depends on NVMEM || !NVMEM
 	depends on TTY
 	help
 	  Bluetooth HCI UART driver.
@@ -97,6 +108,7 @@ config BT_HCIUART_NOKIA
 	tristate "UART Nokia H4+ protocol support"
 	depends on BT_HCIUART
 	depends on BT_HCIUART_SERDEV
+	depends on GPIOLIB
 	depends on PM
 	select BT_HCIUART_H4
 	select BT_BCM
@@ -158,6 +170,7 @@ config BT_HCIUART_3WIRE
 config BT_HCIUART_INTEL
 	bool "Intel protocol support"
 	depends on BT_HCIUART
+	depends on GPIOLIB
 	select BT_HCIUART_H4
 	select BT_INTEL
 	help
@@ -171,6 +184,7 @@ config BT_HCIUART_BCM
 	depends on BT_HCIUART
 	depends on BT_HCIUART_SERDEV
 	depends on (!ACPI || SERIAL_DEV_CTRL_TTYPORT)
+	depends on GPIOLIB
 	select BT_HCIUART_H4
 	select BT_BCM
 	help
diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c
index d513ef4743dc..82437a69f99c 100644
--- a/drivers/bluetooth/bluecard_cs.c
+++ b/drivers/bluetooth/bluecard_cs.c
@@ -302,9 +302,7 @@ static void bluecard_write_wakeup(struct bluecard_info *info)
 			}
 
 			/* Wait until the command reaches the baseband */
-			prepare_to_wait(&wq, &wait, TASK_INTERRUPTIBLE);
-			schedule_timeout(HZ/10);
-			finish_wait(&wq, &wait);
+			mdelay(100);
 
 			/* Set baud on baseband */
 			info->ctrl_reg &= ~0x03;
@@ -316,9 +314,7 @@ static void bluecard_write_wakeup(struct bluecard_info *info)
 			outb(info->ctrl_reg, iobase + REG_CONTROL);
 
 			/* Wait before the next HCI packet can be send */
-			prepare_to_wait(&wq, &wait, TASK_INTERRUPTIBLE);
-			schedule_timeout(HZ);
-			finish_wait(&wq, &wait);
+			mdelay(1000);
 		}
 
 		if (len == skb->len) {
diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c
index 7971bfbd4321..801ea4ca65e4 100644
--- a/drivers/bluetooth/bpa10x.c
+++ b/drivers/bluetooth/bpa10x.c
@@ -259,7 +259,7 @@ static int bpa10x_flush(struct hci_dev *hdev)
 
 static int bpa10x_setup(struct hci_dev *hdev)
 {
-	const u8 req[] = { 0x07 };
+	static const u8 req[] = { 0x07 };
 	struct sk_buff *skb;
 
 	BT_DBG("%s", hdev->name);
diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index afa4cb3b16e3..6659f113042c 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -323,6 +323,7 @@ static const struct {
 	{ 0x410e, "BCM43341B0"	},	/* 002.001.014 */
 	{ 0x4406, "BCM4324B3"	},	/* 002.004.006 */
 	{ 0x610c, "BCM4354"	},	/* 003.001.012 */
+	{ 0x2122, "BCM4343A0"	},	/* 001.001.034 */
 	{ 0x2209, "BCM43430A1"  },	/* 001.002.009 */
 	{ 0x6119, "BCM4345C0"	},	/* 003.001.025 */
 	{ 0x230f, "BCM4356A2"	},	/* 001.003.015 */
diff --git a/drivers/bluetooth/btbcm.h b/drivers/bluetooth/btbcm.h
index d9e6b41658e5..cfe6ad4cc621 100644
--- a/drivers/bluetooth/btbcm.h
+++ b/drivers/bluetooth/btbcm.h
@@ -44,8 +44,8 @@ struct bcm_set_sleep_mode {
 	__u8 tristate_control;
 	__u8 usb_auto_sleep;
 	__u8 usb_resume_timeout;
-	__u8 pulsed_host_wake;
 	__u8 break_to_host;
+	__u8 pulsed_host_wake;
 } __packed;
 
 struct bcm_set_pcm_int_params {
diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 4459555c9d88..5270d5513201 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/regmap.h>
+#include <asm/unaligned.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -75,7 +76,7 @@ EXPORT_SYMBOL_GPL(btintel_check_bdaddr);
 
 int btintel_enter_mfg(struct hci_dev *hdev)
 {
-	const u8 param[] = { 0x01, 0x00 };
+	static const u8 param[] = { 0x01, 0x00 };
 	struct sk_buff *skb;
 
 	skb = __hci_cmd_sync(hdev, 0xfc11, 2, param, HCI_CMD_TIMEOUT);
@@ -569,6 +570,160 @@ struct regmap *btintel_regmap_init(struct hci_dev *hdev, u16 opcode_read,
 }
 EXPORT_SYMBOL_GPL(btintel_regmap_init);
 
+int btintel_send_intel_reset(struct hci_dev *hdev, u32 boot_param)
+{
+	struct intel_reset params = { 0x00, 0x01, 0x00, 0x01, 0x00000000 };
+	struct sk_buff *skb;
+
+	params.boot_param = cpu_to_le32(boot_param);
+
+	skb = __hci_cmd_sync(hdev, 0xfc01, sizeof(params), &params,
+			     HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		bt_dev_err(hdev, "Failed to send Intel Reset command");
+		return PTR_ERR(skb);
+	}
+
+	kfree_skb(skb);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btintel_send_intel_reset);
+
+int btintel_read_boot_params(struct hci_dev *hdev,
+			     struct intel_boot_params *params)
+{
+	struct sk_buff *skb;
+
+	skb = __hci_cmd_sync(hdev, 0xfc0d, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		bt_dev_err(hdev, "Reading Intel boot parameters failed (%ld)",
+			   PTR_ERR(skb));
+		return PTR_ERR(skb);
+	}
+
+	if (skb->len != sizeof(*params)) {
+		bt_dev_err(hdev, "Intel boot parameters size mismatch");
+		kfree_skb(skb);
+		return -EILSEQ;
+	}
+
+	memcpy(params, skb->data, sizeof(*params));
+
+	kfree_skb(skb);
+
+	if (params->status) {
+		bt_dev_err(hdev, "Intel boot parameters command failed (%02x)",
+			   params->status);
+		return -bt_to_errno(params->status);
+	}
+
+	bt_dev_info(hdev, "Device revision is %u",
+		    le16_to_cpu(params->dev_revid));
+
+	bt_dev_info(hdev, "Secure boot is %s",
+		    params->secure_boot ? "enabled" : "disabled");
+
+	bt_dev_info(hdev, "OTP lock is %s",
+		    params->otp_lock ? "enabled" : "disabled");
+
+	bt_dev_info(hdev, "API lock is %s",
+		    params->api_lock ? "enabled" : "disabled");
+
+	bt_dev_info(hdev, "Debug lock is %s",
+		    params->debug_lock ? "enabled" : "disabled");
+
+	bt_dev_info(hdev, "Minimum firmware build %u week %u %u",
+		    params->min_fw_build_nn, params->min_fw_build_cw,
+		    2000 + params->min_fw_build_yy);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btintel_read_boot_params);
+
+int btintel_download_firmware(struct hci_dev *hdev, const struct firmware *fw,
+			      u32 *boot_param)
+{
+	int err;
+	const u8 *fw_ptr;
+	u32 frag_len;
+
+	/* Start the firmware download transaction with the Init fragment
+	 * represented by the 128 bytes of CSS header.
+	 */
+	err = btintel_secure_send(hdev, 0x00, 128, fw->data);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send firmware header (%d)", err);
+		goto done;
+	}
+
+	/* Send the 256 bytes of public key information from the firmware
+	 * as the PKey fragment.
+	 */
+	err = btintel_secure_send(hdev, 0x03, 256, fw->data + 128);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send firmware pkey (%d)", err);
+		goto done;
+	}
+
+	/* Send the 256 bytes of signature information from the firmware
+	 * as the Sign fragment.
+	 */
+	err = btintel_secure_send(hdev, 0x02, 256, fw->data + 388);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send firmware signature (%d)", err);
+		goto done;
+	}
+
+	fw_ptr = fw->data + 644;
+	frag_len = 0;
+
+	while (fw_ptr - fw->data < fw->size) {
+		struct hci_command_hdr *cmd = (void *)(fw_ptr + frag_len);
+
+		/* Each SKU has a different reset parameter to use in the
+		 * HCI_Intel_Reset command and it is embedded in the firmware
+		 * data. So, instead of using static value per SKU, check
+		 * the firmware data and save it for later use.
+		 */
+		if (le16_to_cpu(cmd->opcode) == 0xfc0e) {
+			/* The boot parameter is the first 32-bit value
+			 * and rest of 3 octets are reserved.
+			 */
+			*boot_param = get_unaligned_le32(fw_ptr + sizeof(*cmd));
+
+			bt_dev_dbg(hdev, "boot_param=0x%x", *boot_param);
+		}
+
+		frag_len += sizeof(*cmd) + cmd->plen;
+
+		/* The parameter length of the secure send command requires
+		 * a 4 byte alignment. It happens so that the firmware file
+		 * contains proper Intel_NOP commands to align the fragments
+		 * as needed.
+		 *
+		 * Send set of commands with 4 byte alignment from the
+		 * firmware data buffer as a single Data fragement.
+		 */
+		if (!(frag_len % 4)) {
+			err = btintel_secure_send(hdev, 0x01, frag_len, fw_ptr);
+			if (err < 0) {
+				bt_dev_err(hdev,
+					   "Failed to send firmware data (%d)",
+					   err);
+				goto done;
+			}
+
+			fw_ptr += frag_len;
+			frag_len = 0;
+		}
+	}
+
+done:
+	return err;
+}
+EXPORT_SYMBOL_GPL(btintel_download_firmware);
+
 MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>");
 MODULE_DESCRIPTION("Bluetooth support for Intel devices ver " VERSION);
 MODULE_VERSION(VERSION);
diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index 1e8955aaafed..41c642cc523f 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -69,6 +69,14 @@ struct intel_secure_send_result {
 	__u8     status;
 } __packed;
 
+struct intel_reset {
+	__u8     reset_type;
+	__u8     patch_enable;
+	__u8     ddc_reload;
+	__u8     boot_option;
+	__le32   boot_param;
+} __packed;
+
 #if IS_ENABLED(CONFIG_BT_INTEL)
 
 int btintel_check_bdaddr(struct hci_dev *hdev);
@@ -89,7 +97,11 @@ int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver);
 
 struct regmap *btintel_regmap_init(struct hci_dev *hdev, u16 opcode_read,
 				   u16 opcode_write);
-
+int btintel_send_intel_reset(struct hci_dev *hdev, u32 boot_param);
+int btintel_read_boot_params(struct hci_dev *hdev,
+			     struct intel_boot_params *params);
+int btintel_download_firmware(struct hci_dev *dev, const struct firmware *fw,
+			      u32 *boot_param);
 #else
 
 static inline int btintel_check_bdaddr(struct hci_dev *hdev)
@@ -165,4 +177,23 @@ static inline struct regmap *btintel_regmap_init(struct hci_dev *hdev,
 {
 	return ERR_PTR(-EINVAL);
 }
+
+static inline int btintel_send_intel_reset(struct hci_dev *hdev,
+					   u32 reset_param)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int btintel_read_boot_params(struct hci_dev *hdev,
+					   struct intel_boot_params *params)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int btintel_download_firmware(struct hci_dev *dev,
+					    const struct firmware *fw,
+					    u32 *boot_param)
+{
+	return -EOPNOTSUPP;
+}
 #endif
diff --git a/drivers/bluetooth/btqcomsmd.c b/drivers/bluetooth/btqcomsmd.c
index 663bed63b871..2c9a5fc9137d 100644
--- a/drivers/bluetooth/btqcomsmd.c
+++ b/drivers/bluetooth/btqcomsmd.c
@@ -88,7 +88,8 @@ static int btqcomsmd_send(struct hci_dev *hdev, struct sk_buff *skb)
 		break;
 	}
 
-	kfree_skb(skb);
+	if (!ret)
+		kfree_skb(skb);
 
 	return ret;
 }
diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c
index c8e945d19ffe..20142bc77554 100644
--- a/drivers/bluetooth/btsdio.c
+++ b/drivers/bluetooth/btsdio.c
@@ -31,6 +31,7 @@
 #include <linux/errno.h>
 #include <linux/skbuff.h>
 
+#include <linux/mmc/host.h>
 #include <linux/mmc/sdio_ids.h>
 #include <linux/mmc/sdio_func.h>
 
@@ -292,6 +293,14 @@ static int btsdio_probe(struct sdio_func *func,
 		tuple = tuple->next;
 	}
 
+	/* BCM43341 devices soldered onto the PCB (non-removable) use an
+	 * uart connection for bluetooth, ignore the BT SDIO interface.
+	 */
+	if (func->vendor == SDIO_VENDOR_ID_BROADCOM &&
+	    func->device == SDIO_DEVICE_ID_BROADCOM_43341 &&
+	    !mmc_card_is_removable(func->card->host))
+		return -ENODEV;
+
 	data = devm_kzalloc(&func->dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index f7120c9eb9bd..2a55380ad730 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -23,6 +23,7 @@
 
 #include <linux/module.h>
 #include <linux/usb.h>
+#include <linux/usb/quirks.h>
 #include <linux/firmware.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
@@ -40,6 +41,7 @@
 
 static bool disable_scofix;
 static bool force_scofix;
+static bool enable_autosuspend = IS_ENABLED(CONFIG_BT_HCIBTUSB_AUTOSUSPEND);
 
 static bool reset = true;
 
@@ -263,6 +265,7 @@ static const struct usb_device_id blacklist_table[] = {
 	/* QCA ROME chipset */
 	{ USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe009), .driver_info = BTUSB_QCA_ROME },
+	{ USB_DEVICE(0x0cf3, 0xe010), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe300), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe301), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe360), .driver_info = BTUSB_QCA_ROME },
@@ -270,6 +273,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe09f), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0489, 0xe0a2), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x04ca, 0x3011), .driver_info = BTUSB_QCA_ROME },
+	{ USB_DEVICE(0x04ca, 0x3015), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x04ca, 0x3016), .driver_info = BTUSB_QCA_ROME },
 
 	/* Broadcom BCM2035 */
@@ -387,9 +391,8 @@ static const struct usb_device_id blacklist_table[] = {
 #define BTUSB_FIRMWARE_LOADED	7
 #define BTUSB_FIRMWARE_FAILED	8
 #define BTUSB_BOOTING		9
-#define BTUSB_RESET_RESUME	10
-#define BTUSB_DIAG_RUNNING	11
-#define BTUSB_OOB_WAKE_ENABLED	12
+#define BTUSB_DIAG_RUNNING	10
+#define BTUSB_OOB_WAKE_ENABLED	11
 
 struct btusb_data {
 	struct hci_dev       *hdev;
@@ -2006,15 +2009,11 @@ static int btusb_send_frame_intel(struct hci_dev *hdev, struct sk_buff *skb)
 
 static int btusb_setup_intel_new(struct hci_dev *hdev)
 {
-	static const u8 reset_param[] = { 0x00, 0x01, 0x00, 0x01,
-					  0x00, 0x08, 0x04, 0x00 };
 	struct btusb_data *data = hci_get_drvdata(hdev);
-	struct sk_buff *skb;
 	struct intel_version ver;
-	struct intel_boot_params *params;
+	struct intel_boot_params params;
 	const struct firmware *fw;
-	const u8 *fw_ptr;
-	u32 frag_len;
+	u32 boot_param;
 	char fwname[64];
 	ktime_t calltime, delta, rettime;
 	unsigned long long duration;
@@ -2022,6 +2021,12 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 
 	BT_DBG("%s", hdev->name);
 
+	/* Set the default boot parameter to 0x0 and it is updated to
+	 * SKU specific boot parameter after reading Intel_Write_Boot_Params
+	 * command while downloading the firmware.
+	 */
+	boot_param = 0x00000000;
+
 	calltime = ktime_get();
 
 	/* Read the Intel version information to determine if the device
@@ -2092,55 +2097,24 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	/* Read the secure boot parameters to identify the operating
 	 * details of the bootloader.
 	 */
-	skb = __hci_cmd_sync(hdev, 0xfc0d, 0, NULL, HCI_INIT_TIMEOUT);
-	if (IS_ERR(skb)) {
-		BT_ERR("%s: Reading Intel boot parameters failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
-		return PTR_ERR(skb);
-	}
-
-	if (skb->len != sizeof(*params)) {
-		BT_ERR("%s: Intel boot parameters size mismatch", hdev->name);
-		kfree_skb(skb);
-		return -EILSEQ;
-	}
-
-	params = (struct intel_boot_params *)skb->data;
-
-	bt_dev_info(hdev, "Device revision is %u",
-		    le16_to_cpu(params->dev_revid));
-
-	bt_dev_info(hdev, "Secure boot is %s",
-		    params->secure_boot ? "enabled" : "disabled");
-
-	bt_dev_info(hdev, "OTP lock is %s",
-		    params->otp_lock ? "enabled" : "disabled");
-
-	bt_dev_info(hdev, "API lock is %s",
-		    params->api_lock ? "enabled" : "disabled");
-
-	bt_dev_info(hdev, "Debug lock is %s",
-		    params->debug_lock ? "enabled" : "disabled");
-
-	bt_dev_info(hdev, "Minimum firmware build %u week %u %u",
-		    params->min_fw_build_nn, params->min_fw_build_cw,
-		    2000 + params->min_fw_build_yy);
+	err = btintel_read_boot_params(hdev, &params);
+	if (err)
+		return err;
 
 	/* It is required that every single firmware fragment is acknowledged
 	 * with a command complete event. If the boot parameters indicate
 	 * that this bootloader does not send them, then abort the setup.
 	 */
-	if (params->limited_cce != 0x00) {
+	if (params.limited_cce != 0x00) {
 		BT_ERR("%s: Unsupported Intel firmware loading method (%u)",
-		       hdev->name, params->limited_cce);
-		kfree_skb(skb);
+		       hdev->name, params.limited_cce);
 		return -EINVAL;
 	}
 
 	/* If the OTP has no valid Bluetooth device address, then there will
 	 * also be no valid address for the operational firmware.
 	 */
-	if (!bacmp(&params->otp_bdaddr, BDADDR_ANY)) {
+	if (!bacmp(&params.otp_bdaddr, BDADDR_ANY)) {
 		bt_dev_info(hdev, "No device address configured");
 		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
 	}
@@ -2171,7 +2145,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	case 0x0c:	/* WsP */
 		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi",
 			 le16_to_cpu(ver.hw_variant),
-			 le16_to_cpu(params->dev_revid));
+			 le16_to_cpu(params.dev_revid));
 		break;
 	case 0x11:	/* JfP */
 	case 0x12:	/* ThP */
@@ -2189,7 +2163,6 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	if (err < 0) {
 		BT_ERR("%s: Failed to load Intel firmware file (%d)",
 		       hdev->name, err);
-		kfree_skb(skb);
 		return err;
 	}
 
@@ -2203,7 +2176,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	case 0x0c:	/* WsP */
 		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.ddc",
 			 le16_to_cpu(ver.hw_variant),
-			 le16_to_cpu(params->dev_revid));
+			 le16_to_cpu(params.dev_revid));
 		break;
 	case 0x11:	/* JfP */
 	case 0x12:	/* ThP */
@@ -2217,8 +2190,6 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 		return -EINVAL;
 	}
 
-	kfree_skb(skb);
-
 	if (fw->size < 644) {
 		BT_ERR("%s: Invalid size of firmware file (%zu)",
 		       hdev->name, fw->size);
@@ -2228,64 +2199,10 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 
 	set_bit(BTUSB_DOWNLOADING, &data->flags);
 
-	/* Start the firmware download transaction with the Init fragment
-	 * represented by the 128 bytes of CSS header.
-	 */
-	err = btintel_secure_send(hdev, 0x00, 128, fw->data);
-	if (err < 0) {
-		BT_ERR("%s: Failed to send firmware header (%d)",
-		       hdev->name, err);
-		goto done;
-	}
-
-	/* Send the 256 bytes of public key information from the firmware
-	 * as the PKey fragment.
-	 */
-	err = btintel_secure_send(hdev, 0x03, 256, fw->data + 128);
-	if (err < 0) {
-		BT_ERR("%s: Failed to send firmware public key (%d)",
-		       hdev->name, err);
-		goto done;
-	}
-
-	/* Send the 256 bytes of signature information from the firmware
-	 * as the Sign fragment.
-	 */
-	err = btintel_secure_send(hdev, 0x02, 256, fw->data + 388);
-	if (err < 0) {
-		BT_ERR("%s: Failed to send firmware signature (%d)",
-		       hdev->name, err);
+	/* Start firmware downloading and get boot parameter */
+	err = btintel_download_firmware(hdev, fw, &boot_param);
+	if (err < 0)
 		goto done;
-	}
-
-	fw_ptr = fw->data + 644;
-	frag_len = 0;
-
-	while (fw_ptr - fw->data < fw->size) {
-		struct hci_command_hdr *cmd = (void *)(fw_ptr + frag_len);
-
-		frag_len += sizeof(*cmd) + cmd->plen;
-
-		/* The parameter length of the secure send command requires
-		 * a 4 byte alignment. It happens so that the firmware file
-		 * contains proper Intel_NOP commands to align the fragments
-		 * as needed.
-		 *
-		 * Send set of commands with 4 byte alignment from the
-		 * firmware data buffer as a single Data fragement.
-		 */
-		if (!(frag_len % 4)) {
-			err = btintel_secure_send(hdev, 0x01, frag_len, fw_ptr);
-			if (err < 0) {
-				BT_ERR("%s: Failed to send firmware data (%d)",
-				       hdev->name, err);
-				goto done;
-			}
-
-			fw_ptr += frag_len;
-			frag_len = 0;
-		}
-	}
 
 	set_bit(BTUSB_FIRMWARE_LOADED, &data->flags);
 
@@ -2338,12 +2255,9 @@ done:
 
 	set_bit(BTUSB_BOOTING, &data->flags);
 
-	skb = __hci_cmd_sync(hdev, 0xfc01, sizeof(reset_param), reset_param,
-			     HCI_INIT_TIMEOUT);
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
-
-	kfree_skb(skb);
+	err = btintel_send_intel_reset(hdev, boot_param);
+	if (err)
+		return err;
 
 	/* The bootloader will not indicate when the device is ready. This
 	 * is done by the operational firmware sending bootup notification.
@@ -3120,9 +3034,9 @@ static int btusb_probe(struct usb_interface *intf,
 
 		/* QCA Rome devices lose their updated firmware over suspend,
 		 * but the USB hub doesn't notice any status change.
-		 * Explicitly request a device reset on resume.
+		 * explicitly request a device reset on resume.
 		 */
-		set_bit(BTUSB_RESET_RESUME, &data->flags);
+		interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
 	}
 
 #ifdef CONFIG_BT_HCIBTUSB_RTL
@@ -3133,7 +3047,7 @@ static int btusb_probe(struct usb_interface *intf,
 		 * but the USB hub doesn't notice any status change.
 		 * Explicitly request a device reset on resume.
 		 */
-		set_bit(BTUSB_RESET_RESUME, &data->flags);
+		interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
 	}
 #endif
 
@@ -3213,6 +3127,9 @@ static int btusb_probe(struct usb_interface *intf,
 	}
 #endif
 
+	if (enable_autosuspend)
+		usb_enable_autosuspend(data->udev);
+
 	err = hci_register_dev(hdev);
 	if (err < 0)
 		goto out_free_dev;
@@ -3299,14 +3216,6 @@ static int btusb_suspend(struct usb_interface *intf, pm_message_t message)
 		enable_irq(data->oob_wake_irq);
 	}
 
-	/* Optionally request a device reset on resume, but only when
-	 * wakeups are disabled. If wakeups are enabled we assume the
-	 * device will stay powered up throughout suspend.
-	 */
-	if (test_bit(BTUSB_RESET_RESUME, &data->flags) &&
-	    !device_may_wakeup(&data->udev->dev))
-		data->udev->reset_resume = 1;
-
 	return 0;
 }
 
@@ -3425,6 +3334,9 @@ MODULE_PARM_DESC(disable_scofix, "Disable fixup of wrong SCO buffer size");
 module_param(force_scofix, bool, 0644);
 MODULE_PARM_DESC(force_scofix, "Force fixup of wrong SCO buffers size");
 
+module_param(enable_autosuspend, bool, 0644);
+MODULE_PARM_DESC(enable_autosuspend, "Enable USB autosuspend by default");
+
 module_param(reset, bool, 0644);
 MODULE_PARM_DESC(reset, "Send HCI reset command on initialization");
 
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 707c2d1b84c7..0438a64b8185 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -29,6 +29,7 @@
 #include <linux/acpi.h>
 #include <linux/of.h>
 #include <linux/property.h>
+#include <linux/platform_data/x86/apple.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/gpio/consumer.h>
@@ -52,7 +53,37 @@
 
 #define BCM_AUTOSUSPEND_DELAY	5000 /* default autosleep delay */
 
-/* device driver resources */
+/**
+ * struct bcm_device - device driver resources
+ * @serdev_hu: HCI UART controller struct
+ * @list: bcm_device_list node
+ * @dev: physical UART slave
+ * @name: device name logged by bt_dev_*() functions
+ * @device_wakeup: BT_WAKE pin,
+ *	assert = Bluetooth device must wake up or remain awake,
+ *	deassert = Bluetooth device may sleep when sleep criteria are met
+ * @shutdown: BT_REG_ON pin,
+ *	power up or power down Bluetooth device internal regulators
+ * @set_device_wakeup: callback to toggle BT_WAKE pin
+ *	either by accessing @device_wakeup or by calling @btlp
+ * @set_shutdown: callback to toggle BT_REG_ON pin
+ *	either by accessing @shutdown or by calling @btpu/@btpd
+ * @btlp: Apple ACPI method to toggle BT_WAKE pin ("Bluetooth Low Power")
+ * @btpu: Apple ACPI method to drive BT_REG_ON pin high ("Bluetooth Power Up")
+ * @btpd: Apple ACPI method to drive BT_REG_ON pin low ("Bluetooth Power Down")
+ * @clk: clock used by Bluetooth device
+ * @clk_enabled: whether @clk is prepared and enabled
+ * @init_speed: default baudrate of Bluetooth device;
+ *	the host UART is initially set to this baudrate so that
+ *	it can configure the Bluetooth device for @oper_speed
+ * @oper_speed: preferred baudrate of Bluetooth device;
+ *	set to 0 if @init_speed is already the preferred baudrate
+ * @irq: interrupt triggered by HOST_WAKE_BT pin
+ * @irq_active_low: whether @irq is active low
+ * @hu: pointer to HCI UART controller struct,
+ *	used to disable flow control during runtime suspend and system sleep
+ * @is_suspended: whether flow control is currently disabled
+ */
 struct bcm_device {
 	/* Must be the first member, hci_serdev.c expects this. */
 	struct hci_uart		serdev_hu;
@@ -63,6 +94,11 @@ struct bcm_device {
 	const char		*name;
 	struct gpio_desc	*device_wakeup;
 	struct gpio_desc	*shutdown;
+	int			(*set_device_wakeup)(struct bcm_device *, bool);
+	int			(*set_shutdown)(struct bcm_device *, bool);
+#ifdef CONFIG_ACPI
+	acpi_handle		btlp, btpu, btpd;
+#endif
 
 	struct clk		*clk;
 	bool			clk_enabled;
@@ -74,7 +110,7 @@ struct bcm_device {
 
 #ifdef CONFIG_PM
 	struct hci_uart		*hu;
-	bool			is_suspended; /* suspend/resume flag */
+	bool			is_suspended;
 #endif
 };
 
@@ -170,11 +206,21 @@ static bool bcm_device_exists(struct bcm_device *device)
 
 static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 {
-	if (powered && !IS_ERR(dev->clk) && !dev->clk_enabled)
-		clk_prepare_enable(dev->clk);
+	int err;
 
-	gpiod_set_value(dev->shutdown, powered);
-	gpiod_set_value(dev->device_wakeup, powered);
+	if (powered && !IS_ERR(dev->clk) && !dev->clk_enabled) {
+		err = clk_prepare_enable(dev->clk);
+		if (err)
+			return err;
+	}
+
+	err = dev->set_shutdown(dev, powered);
+	if (err)
+		goto err_clk_disable;
+
+	err = dev->set_device_wakeup(dev, powered);
+	if (err)
+		goto err_revert_shutdown;
 
 	if (!powered && !IS_ERR(dev->clk) && dev->clk_enabled)
 		clk_disable_unprepare(dev->clk);
@@ -182,6 +228,13 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 	dev->clk_enabled = powered;
 
 	return 0;
+
+err_revert_shutdown:
+	dev->set_shutdown(dev, !powered);
+err_clk_disable:
+	if (powered && !IS_ERR(dev->clk) && !dev->clk_enabled)
+		clk_disable_unprepare(dev->clk);
+	return err;
 }
 
 #ifdef CONFIG_PM
@@ -191,9 +244,7 @@ static irqreturn_t bcm_host_wake(int irq, void *data)
 
 	bt_dev_dbg(bdev, "Host wake IRQ");
 
-	pm_runtime_get(bdev->dev);
-	pm_runtime_mark_last_busy(bdev->dev);
-	pm_runtime_put_autosuspend(bdev->dev);
+	pm_request_resume(bdev->dev);
 
 	return IRQ_HANDLED;
 }
@@ -218,8 +269,10 @@ static int bcm_request_irq(struct bcm_data *bcm)
 			       bdev->irq_active_low ? IRQF_TRIGGER_FALLING :
 						      IRQF_TRIGGER_RISING,
 			       "host_wake", bdev);
-	if (err)
+	if (err) {
+		bdev->irq = err;
 		goto unlock;
+	}
 
 	device_init_wakeup(bdev->dev, true);
 
@@ -247,8 +300,8 @@ static const struct bcm_set_sleep_mode default_sleep_params = {
 	/* Irrelevant USB flags */
 	.usb_auto_sleep = 0,
 	.usb_resume_timeout = 0,
+	.break_to_host = 0,
 	.pulsed_host_wake = 0,
-	.break_to_host = 0
 };
 
 static int bcm_setup_sleep(struct hci_uart *hu)
@@ -304,6 +357,7 @@ static int bcm_open(struct hci_uart *hu)
 {
 	struct bcm_data *bcm;
 	struct list_head *p;
+	int err;
 
 	bt_dev_dbg(hu->hdev, "hu %p", hu);
 
@@ -318,7 +372,10 @@ static int bcm_open(struct hci_uart *hu)
 	mutex_lock(&bcm_device_lock);
 
 	if (hu->serdev) {
-		serdev_device_open(hu->serdev);
+		err = serdev_device_open(hu->serdev);
+		if (err)
+			goto err_free;
+
 		bcm->dev = serdev_device_get_drvdata(hu->serdev);
 		goto out;
 	}
@@ -346,17 +403,33 @@ out:
 	if (bcm->dev) {
 		hu->init_speed = bcm->dev->init_speed;
 		hu->oper_speed = bcm->dev->oper_speed;
-		bcm_gpio_set_power(bcm->dev, true);
+		err = bcm_gpio_set_power(bcm->dev, true);
+		if (err)
+			goto err_unset_hu;
 	}
 
 	mutex_unlock(&bcm_device_lock);
 	return 0;
+
+err_unset_hu:
+	if (hu->serdev)
+		serdev_device_close(hu->serdev);
+#ifdef CONFIG_PM
+	else
+		bcm->dev->hu = NULL;
+#endif
+err_free:
+	mutex_unlock(&bcm_device_lock);
+	hu->priv = NULL;
+	kfree(bcm);
+	return err;
 }
 
 static int bcm_close(struct hci_uart *hu)
 {
 	struct bcm_data *bcm = hu->priv;
 	struct bcm_device *bdev = NULL;
+	int err;
 
 	bt_dev_dbg(hu->hdev, "hu %p", hu);
 
@@ -374,16 +447,17 @@ static int bcm_close(struct hci_uart *hu)
 	}
 
 	if (bdev) {
-		bcm_gpio_set_power(bdev, false);
-#ifdef CONFIG_PM
-		pm_runtime_disable(bdev->dev);
-		pm_runtime_set_suspended(bdev->dev);
-
-		if (device_can_wakeup(bdev->dev)) {
+		if (IS_ENABLED(CONFIG_PM) && bdev->irq > 0) {
 			devm_free_irq(bdev->dev, bdev->irq, bdev);
 			device_init_wakeup(bdev->dev, false);
+			pm_runtime_disable(bdev->dev);
 		}
-#endif
+
+		err = bcm_gpio_set_power(bdev, false);
+		if (err)
+			bt_dev_err(hu->hdev, "Failed to power down");
+		else
+			pm_runtime_set_suspended(bdev->dev);
 	}
 	mutex_unlock(&bcm_device_lock);
 
@@ -512,11 +586,8 @@ static int bcm_recv(struct hci_uart *hu, const void *data, int count)
 	} else if (!bcm->rx_skb) {
 		/* Delay auto-suspend when receiving completed packet */
 		mutex_lock(&bcm_device_lock);
-		if (bcm->dev && bcm_device_exists(bcm->dev)) {
-			pm_runtime_get(bcm->dev->dev);
-			pm_runtime_mark_last_busy(bcm->dev->dev);
-			pm_runtime_put_autosuspend(bcm->dev->dev);
-		}
+		if (bcm->dev && bcm_device_exists(bcm->dev))
+			pm_request_resume(bcm->dev->dev);
 		mutex_unlock(&bcm_device_lock);
 	}
 
@@ -566,6 +637,7 @@ static struct sk_buff *bcm_dequeue(struct hci_uart *hu)
 static int bcm_suspend_device(struct device *dev)
 {
 	struct bcm_device *bdev = dev_get_drvdata(dev);
+	int err;
 
 	bt_dev_dbg(bdev, "");
 
@@ -577,27 +649,37 @@ static int bcm_suspend_device(struct device *dev)
 	}
 
 	/* Suspend the device */
-	if (bdev->device_wakeup) {
-		gpiod_set_value(bdev->device_wakeup, false);
-		bt_dev_dbg(bdev, "suspend, delaying 15 ms");
-		mdelay(15);
+	err = bdev->set_device_wakeup(bdev, false);
+	if (err) {
+		if (bdev->is_suspended && bdev->hu) {
+			bdev->is_suspended = false;
+			hci_uart_set_flow_control(bdev->hu, false);
+		}
+		return -EBUSY;
 	}
 
+	bt_dev_dbg(bdev, "suspend, delaying 15 ms");
+	msleep(15);
+
 	return 0;
 }
 
 static int bcm_resume_device(struct device *dev)
 {
 	struct bcm_device *bdev = dev_get_drvdata(dev);
+	int err;
 
 	bt_dev_dbg(bdev, "");
 
-	if (bdev->device_wakeup) {
-		gpiod_set_value(bdev->device_wakeup, true);
-		bt_dev_dbg(bdev, "resume, delaying 15 ms");
-		mdelay(15);
+	err = bdev->set_device_wakeup(bdev, true);
+	if (err) {
+		dev_err(dev, "Failed to power up\n");
+		return err;
 	}
 
+	bt_dev_dbg(bdev, "resume, delaying 15 ms");
+	msleep(15);
+
 	/* When this executes, the device has woken up already */
 	if (bdev->is_suspended && bdev->hu) {
 		bdev->is_suspended = false;
@@ -632,7 +714,7 @@ static int bcm_suspend(struct device *dev)
 	if (pm_runtime_active(dev))
 		bcm_suspend_device(dev);
 
-	if (device_may_wakeup(dev)) {
+	if (device_may_wakeup(dev) && bdev->irq > 0) {
 		error = enable_irq_wake(bdev->irq);
 		if (!error)
 			bt_dev_dbg(bdev, "BCM irq: enabled");
@@ -648,6 +730,7 @@ unlock:
 static int bcm_resume(struct device *dev)
 {
 	struct bcm_device *bdev = dev_get_drvdata(dev);
+	int err = 0;
 
 	bt_dev_dbg(bdev, "resume: is_suspended %d", bdev->is_suspended);
 
@@ -662,19 +745,21 @@ static int bcm_resume(struct device *dev)
 	if (!bdev->hu)
 		goto unlock;
 
-	if (device_may_wakeup(dev)) {
+	if (device_may_wakeup(dev) && bdev->irq > 0) {
 		disable_irq_wake(bdev->irq);
 		bt_dev_dbg(bdev, "BCM irq: disabled");
 	}
 
-	bcm_resume_device(dev);
+	err = bcm_resume_device(dev);
 
 unlock:
 	mutex_unlock(&bcm_device_lock);
 
-	pm_runtime_disable(dev);
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
+	if (!err) {
+		pm_runtime_disable(dev);
+		pm_runtime_set_active(dev);
+		pm_runtime_enable(dev);
+	}
 
 	return 0;
 }
@@ -771,25 +856,84 @@ static int bcm_resource(struct acpi_resource *ares, void *data)
 
 	return 0;
 }
+
+static int bcm_apple_set_device_wakeup(struct bcm_device *dev, bool awake)
+{
+	if (ACPI_FAILURE(acpi_execute_simple_method(dev->btlp, NULL, !awake)))
+		return -EIO;
+
+	return 0;
+}
+
+static int bcm_apple_set_shutdown(struct bcm_device *dev, bool powered)
+{
+	if (ACPI_FAILURE(acpi_evaluate_object(powered ? dev->btpu : dev->btpd,
+					      NULL, NULL, NULL)))
+		return -EIO;
+
+	return 0;
+}
+
+static int bcm_apple_get_resources(struct bcm_device *dev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev->dev);
+	const union acpi_object *obj;
+
+	if (!adev ||
+	    ACPI_FAILURE(acpi_get_handle(adev->handle, "BTLP", &dev->btlp)) ||
+	    ACPI_FAILURE(acpi_get_handle(adev->handle, "BTPU", &dev->btpu)) ||
+	    ACPI_FAILURE(acpi_get_handle(adev->handle, "BTPD", &dev->btpd)))
+		return -ENODEV;
+
+	if (!acpi_dev_get_property(adev, "baud", ACPI_TYPE_BUFFER, &obj) &&
+	    obj->buffer.length == 8)
+		dev->init_speed = *(u64 *)obj->buffer.pointer;
+
+	dev->set_device_wakeup = bcm_apple_set_device_wakeup;
+	dev->set_shutdown = bcm_apple_set_shutdown;
+
+	return 0;
+}
+#else
+static inline int bcm_apple_get_resources(struct bcm_device *dev)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_ACPI */
 
+static int bcm_gpio_set_device_wakeup(struct bcm_device *dev, bool awake)
+{
+	gpiod_set_value(dev->device_wakeup, awake);
+	return 0;
+}
+
+static int bcm_gpio_set_shutdown(struct bcm_device *dev, bool powered)
+{
+	gpiod_set_value(dev->shutdown, powered);
+	return 0;
+}
+
 static int bcm_get_resources(struct bcm_device *dev)
 {
 	dev->name = dev_name(dev->dev);
 
+	if (x86_apple_machine && !bcm_apple_get_resources(dev))
+		return 0;
+
 	dev->clk = devm_clk_get(dev->dev, NULL);
 
-	dev->device_wakeup = devm_gpiod_get_optional(dev->dev,
-						     "device-wakeup",
-						     GPIOD_OUT_LOW);
+	dev->device_wakeup = devm_gpiod_get(dev->dev, "device-wakeup",
+					    GPIOD_OUT_LOW);
 	if (IS_ERR(dev->device_wakeup))
 		return PTR_ERR(dev->device_wakeup);
 
-	dev->shutdown = devm_gpiod_get_optional(dev->dev, "shutdown",
-						GPIOD_OUT_LOW);
+	dev->shutdown = devm_gpiod_get(dev->dev, "shutdown", GPIOD_OUT_LOW);
 	if (IS_ERR(dev->shutdown))
 		return PTR_ERR(dev->shutdown);
 
+	dev->set_device_wakeup = bcm_gpio_set_device_wakeup;
+	dev->set_shutdown = bcm_gpio_set_shutdown;
+
 	/* IRQ can be declared in ACPI table as Interrupt or GpioInt */
 	if (dev->irq <= 0) {
 		struct gpio_desc *gpio;
@@ -802,7 +946,7 @@ static int bcm_get_resources(struct bcm_device *dev)
 		dev->irq = gpiod_to_irq(gpio);
 	}
 
-	dev_info(dev->dev, "BCM irq: %d\n", dev->irq);
+	dev_dbg(dev->dev, "BCM irq: %d\n", dev->irq);
 	return 0;
 }
 
@@ -892,7 +1036,9 @@ static int bcm_probe(struct platform_device *pdev)
 	list_add_tail(&dev->list, &bcm_device_list);
 	mutex_unlock(&bcm_device_lock);
 
-	bcm_gpio_set_power(dev, false);
+	ret = bcm_gpio_set_power(dev, false);
+	if (ret)
+		dev_err(&pdev->dev, "Failed to power down\n");
 
 	return 0;
 }
@@ -939,6 +1085,7 @@ static const struct acpi_device_id bcm_acpi_match[] = {
 	{ "BCM2E65", (kernel_ulong_t)&acpi_bcm_int_last_gpios },
 	{ "BCM2E67", (kernel_ulong_t)&acpi_bcm_int_last_gpios },
 	{ "BCM2E71", (kernel_ulong_t)&acpi_bcm_int_last_gpios },
+	{ "BCM2E72", (kernel_ulong_t)&acpi_bcm_int_last_gpios },
 	{ "BCM2E7B", (kernel_ulong_t)&acpi_bcm_int_last_gpios },
 	{ "BCM2E7C", (kernel_ulong_t)&acpi_bcm_int_last_gpios },
 	{ "BCM2E7E", (kernel_ulong_t)&acpi_bcm_int_first_gpios },
@@ -993,7 +1140,9 @@ static int bcm_serdev_probe(struct serdev_device *serdev)
 	if (err)
 		return err;
 
-	bcm_gpio_set_power(bcmdev, false);
+	err = bcm_gpio_set_power(bcmdev, false);
+	if (err)
+		dev_err(&serdev->dev, "Failed to power down\n");
 
 	return hci_uart_register_device(&bcmdev->serdev_hu, &bcm_proto);
 }
diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c
index aad07e40ea4f..7c166e3b308b 100644
--- a/drivers/bluetooth/hci_intel.c
+++ b/drivers/bluetooth/hci_intel.c
@@ -540,18 +540,15 @@ static int intel_set_baudrate(struct hci_uart *hu, unsigned int speed)
 
 static int intel_setup(struct hci_uart *hu)
 {
-	static const u8 reset_param[] = { 0x00, 0x01, 0x00, 0x01,
-					  0x00, 0x08, 0x04, 0x00 };
 	struct intel_data *intel = hu->priv;
 	struct hci_dev *hdev = hu->hdev;
 	struct sk_buff *skb;
 	struct intel_version ver;
-	struct intel_boot_params *params;
+	struct intel_boot_params params;
 	struct list_head *p;
 	const struct firmware *fw;
-	const u8 *fw_ptr;
 	char fwname[64];
-	u32 frag_len;
+	u32 boot_param;
 	ktime_t calltime, delta, rettime;
 	unsigned long long duration;
 	unsigned int init_speed, oper_speed;
@@ -563,6 +560,12 @@ static int intel_setup(struct hci_uart *hu)
 	hu->hdev->set_diag = btintel_set_diag;
 	hu->hdev->set_bdaddr = btintel_set_bdaddr;
 
+	/* Set the default boot parameter to 0x0 and it is updated to
+	 * SKU specific boot parameter after reading Intel_Write_Boot_Params
+	 * command while downloading the firmware.
+	 */
+	boot_param = 0x00000000;
+
 	calltime = ktime_get();
 
 	if (hu->init_speed)
@@ -656,85 +659,95 @@ static int intel_setup(struct hci_uart *hu)
 	/* Read the secure boot parameters to identify the operating
 	 * details of the bootloader.
 	 */
-	skb = __hci_cmd_sync(hdev, 0xfc0d, 0, NULL, HCI_CMD_TIMEOUT);
-	if (IS_ERR(skb)) {
-		bt_dev_err(hdev, "Reading Intel boot parameters failed (%ld)",
-			   PTR_ERR(skb));
-		return PTR_ERR(skb);
-	}
-
-	if (skb->len != sizeof(*params)) {
-		bt_dev_err(hdev, "Intel boot parameters size mismatch");
-		kfree_skb(skb);
-		return -EILSEQ;
-	}
-
-	params = (struct intel_boot_params *)skb->data;
-	if (params->status) {
-		bt_dev_err(hdev, "Intel boot parameters command failure (%02x)",
-			   params->status);
-		err = -bt_to_errno(params->status);
-		kfree_skb(skb);
+	err = btintel_read_boot_params(hdev, &params);
+	if (err)
 		return err;
-	}
-
-	bt_dev_info(hdev, "Device revision is %u",
-		    le16_to_cpu(params->dev_revid));
-
-	bt_dev_info(hdev, "Secure boot is %s",
-		    params->secure_boot ? "enabled" : "disabled");
-
-	bt_dev_info(hdev, "Minimum firmware build %u week %u %u",
-		params->min_fw_build_nn, params->min_fw_build_cw,
-		2000 + params->min_fw_build_yy);
 
 	/* It is required that every single firmware fragment is acknowledged
 	 * with a command complete event. If the boot parameters indicate
 	 * that this bootloader does not send them, then abort the setup.
 	 */
-	if (params->limited_cce != 0x00) {
+	if (params.limited_cce != 0x00) {
 		bt_dev_err(hdev, "Unsupported Intel firmware loading method (%u)",
-			   params->limited_cce);
-		kfree_skb(skb);
+			   params.limited_cce);
 		return -EINVAL;
 	}
 
 	/* If the OTP has no valid Bluetooth device address, then there will
 	 * also be no valid address for the operational firmware.
 	 */
-	if (!bacmp(&params->otp_bdaddr, BDADDR_ANY)) {
+	if (!bacmp(&params.otp_bdaddr, BDADDR_ANY)) {
 		bt_dev_info(hdev, "No device address configured");
 		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
 	}
 
 	/* With this Intel bootloader only the hardware variant and device
-	 * revision information are used to select the right firmware.
+	 * revision information are used to select the right firmware for SfP
+	 * and WsP.
 	 *
 	 * The firmware filename is ibt-<hw_variant>-<dev_revid>.sfi.
 	 *
 	 * Currently the supported hardware variants are:
 	 *   11 (0x0b) for iBT 3.0 (LnP/SfP)
+	 *   12 (0x0c) for iBT 3.5 (WsP)
+	 *
+	 * For ThP/JfP and for future SKU's, the FW name varies based on HW
+	 * variant, HW revision and FW revision, as these are dependent on CNVi
+	 * and RF Combination.
+	 *
+	 *   18 (0x12) for iBT3.5 (ThP/JfP)
+	 *
+	 * The firmware file name for these will be
+	 * ibt-<hw_variant>-<hw_revision>-<fw_revision>.sfi.
+	 *
 	 */
-	snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi",
-		le16_to_cpu(ver.hw_variant),
-		le16_to_cpu(params->dev_revid));
+	switch (ver.hw_variant) {
+	case 0x0b:      /* SfP */
+	case 0x0c:      /* WsP */
+		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi",
+			 le16_to_cpu(ver.hw_variant),
+			 le16_to_cpu(params.dev_revid));
+		break;
+	case 0x12:      /* ThP */
+		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.sfi",
+			 le16_to_cpu(ver.hw_variant),
+			 le16_to_cpu(ver.hw_revision),
+			 le16_to_cpu(ver.fw_revision));
+		break;
+	default:
+		bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)",
+			   ver.hw_variant);
+		return -EINVAL;
+	}
 
 	err = request_firmware(&fw, fwname, &hdev->dev);
 	if (err < 0) {
 		bt_dev_err(hdev, "Failed to load Intel firmware file (%d)",
 			   err);
-		kfree_skb(skb);
 		return err;
 	}
 
 	bt_dev_info(hdev, "Found device firmware: %s", fwname);
 
 	/* Save the DDC file name for later */
-	snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.ddc",
-		le16_to_cpu(ver.hw_variant),
-		le16_to_cpu(params->dev_revid));
-
-	kfree_skb(skb);
+	switch (ver.hw_variant) {
+	case 0x0b:      /* SfP */
+	case 0x0c:      /* WsP */
+		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.ddc",
+			 le16_to_cpu(ver.hw_variant),
+			 le16_to_cpu(params.dev_revid));
+		break;
+	case 0x12:      /* ThP */
+		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.ddc",
+			 le16_to_cpu(ver.hw_variant),
+			 le16_to_cpu(ver.hw_revision),
+			 le16_to_cpu(ver.fw_revision));
+		break;
+	default:
+		bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)",
+			   ver.hw_variant);
+		return -EINVAL;
+	}
 
 	if (fw->size < 644) {
 		bt_dev_err(hdev, "Invalid size of firmware file (%zu)",
@@ -745,70 +758,10 @@ static int intel_setup(struct hci_uart *hu)
 
 	set_bit(STATE_DOWNLOADING, &intel->flags);
 
-	/* Start the firmware download transaction with the Init fragment
-	 * represented by the 128 bytes of CSS header.
-	 */
-	err = btintel_secure_send(hdev, 0x00, 128, fw->data);
-	if (err < 0) {
-		bt_dev_err(hdev, "Failed to send firmware header (%d)", err);
-		goto done;
-	}
-
-	/* Send the 256 bytes of public key information from the firmware
-	 * as the PKey fragment.
-	 */
-	err = btintel_secure_send(hdev, 0x03, 256, fw->data + 128);
-	if (err < 0) {
-		bt_dev_err(hdev, "Failed to send firmware public key (%d)",
-			   err);
-		goto done;
-	}
-
-	/* Send the 256 bytes of signature information from the firmware
-	 * as the Sign fragment.
-	 */
-	err = btintel_secure_send(hdev, 0x02, 256, fw->data + 388);
-	if (err < 0) {
-		bt_dev_err(hdev, "Failed to send firmware signature (%d)",
-			   err);
+	/* Start firmware downloading and get boot parameter */
+	err = btintel_download_firmware(hdev, fw, &boot_param);
+	if (err < 0)
 		goto done;
-	}
-
-	fw_ptr = fw->data + 644;
-	frag_len = 0;
-
-	while (fw_ptr - fw->data < fw->size) {
-		struct hci_command_hdr *cmd = (void *)(fw_ptr + frag_len);
-
-		frag_len += sizeof(*cmd) + cmd->plen;
-
-		bt_dev_dbg(hdev, "Patching %td/%zu", (fw_ptr - fw->data),
-			   fw->size);
-
-		/* The parameter length of the secure send command requires
-		 * a 4 byte alignment. It happens so that the firmware file
-		 * contains proper Intel_NOP commands to align the fragments
-		 * as needed.
-		 *
-		 * Send set of commands with 4 byte alignment from the
-		 * firmware data buffer as a single Data fragement.
-		 */
-		if (frag_len % 4)
-			continue;
-
-		/* Send each command from the firmware data buffer as
-		 * a single Data fragment.
-		 */
-		err = btintel_secure_send(hdev, 0x01, frag_len, fw_ptr);
-		if (err < 0) {
-			bt_dev_err(hdev, "Failed to send firmware data (%d)",
-				   err);
-			goto done;
-		}
-
-		fw_ptr += frag_len;
-		frag_len = 0;
-	}
 
 	set_bit(STATE_FIRMWARE_LOADED, &intel->flags);
 
@@ -869,12 +822,9 @@ done:
 
 	set_bit(STATE_BOOTING, &intel->flags);
 
-	skb = __hci_cmd_sync(hdev, 0xfc01, sizeof(reset_param), reset_param,
-			     HCI_CMD_TIMEOUT);
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
-
-	kfree_skb(skb);
+	err = btintel_send_intel_reset(hdev, boot_param);
+	if (err)
+		return err;
 
 	/* The bootloader will not indicate when the device is ready. This
 	 * is done by the operational firmware sending bootup notification.
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index c823914b3a80..b6a71705b7d6 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -794,7 +794,7 @@ static ssize_t hci_uart_tty_write(struct tty_struct *tty, struct file *file,
 	return 0;
 }
 
-static unsigned int hci_uart_tty_poll(struct tty_struct *tty,
+static __poll_t hci_uart_tty_poll(struct tty_struct *tty,
 				      struct file *filp, poll_table *wait)
 {
 	return 0;
diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c
index e2c078d61730..1b4417a623a4 100644
--- a/drivers/bluetooth/hci_ll.c
+++ b/drivers/bluetooth/hci_ll.c
@@ -53,9 +53,14 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 #include <linux/gpio/consumer.h>
+#include <linux/nvmem-consumer.h>
 
 #include "hci_uart.h"
 
+/* Vendor-specific HCI commands */
+#define HCI_VS_WRITE_BD_ADDR			0xfc06
+#define HCI_VS_UPDATE_UART_HCI_BAUDRATE		0xff36
+
 /* HCILL commands */
 #define HCILL_GO_TO_SLEEP_IND	0x30
 #define HCILL_GO_TO_SLEEP_ACK	0x31
@@ -86,6 +91,7 @@ struct ll_device {
 	struct serdev_device *serdev;
 	struct gpio_desc *enable_gpio;
 	struct clk *ext_clk;
+	bdaddr_t bdaddr;
 };
 
 struct ll_struct {
@@ -620,7 +626,7 @@ static int download_firmware(struct ll_device *lldev)
 		case ACTION_SEND_COMMAND:	/* action send */
 			bt_dev_dbg(lldev->hu.hdev, "S");
 			cmd = (struct hci_command *)action_ptr;
-			if (cmd->opcode == 0xff36) {
+			if (cmd->opcode == HCI_VS_UPDATE_UART_HCI_BAUDRATE) {
 				/* ignore remote change
 				 * baud rate HCI VS command
 				 */
@@ -628,11 +634,11 @@ static int download_firmware(struct ll_device *lldev)
 				break;
 			}
 			if (cmd->prefix != 1)
-				bt_dev_dbg(lldev->hu.hdev, "command type %d\n", cmd->prefix);
+				bt_dev_dbg(lldev->hu.hdev, "command type %d", cmd->prefix);
 
 			skb = __hci_cmd_sync(lldev->hu.hdev, cmd->opcode, cmd->plen, &cmd->speed, HCI_INIT_TIMEOUT);
 			if (IS_ERR(skb)) {
-				bt_dev_err(lldev->hu.hdev, "send command failed\n");
+				bt_dev_err(lldev->hu.hdev, "send command failed");
 				err = PTR_ERR(skb);
 				goto out_rel_fw;
 			}
@@ -659,6 +665,24 @@ out_rel_fw:
 	return err;
 }
 
+static int ll_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
+{
+	bdaddr_t bdaddr_swapped;
+	struct sk_buff *skb;
+
+	/* HCI_VS_WRITE_BD_ADDR (at least on a CC2560A chip) expects the BD
+	 * address to be MSB first, but bdaddr_t has the convention of being
+	 * LSB first.
+	 */
+	baswap(&bdaddr_swapped, bdaddr);
+	skb = __hci_cmd_sync(hdev, HCI_VS_WRITE_BD_ADDR, sizeof(bdaddr_t),
+			     &bdaddr_swapped, HCI_INIT_TIMEOUT);
+	if (!IS_ERR(skb))
+		kfree_skb(skb);
+
+	return PTR_ERR_OR_ZERO(skb);
+}
+
 static int ll_setup(struct hci_uart *hu)
 {
 	int err, retry = 3;
@@ -671,14 +695,20 @@ static int ll_setup(struct hci_uart *hu)
 
 	lldev = serdev_device_get_drvdata(serdev);
 
+	hu->hdev->set_bdaddr = ll_set_bdaddr;
+
 	serdev_device_set_flow_control(serdev, true);
 
 	do {
-		/* Configure BT_EN to HIGH state */
+		/* Reset the Bluetooth device */
 		gpiod_set_value_cansleep(lldev->enable_gpio, 0);
 		msleep(5);
 		gpiod_set_value_cansleep(lldev->enable_gpio, 1);
-		msleep(100);
+		err = serdev_device_wait_for_cts(serdev, true, 200);
+		if (err) {
+			bt_dev_err(hu->hdev, "Failed to get CTS");
+			return err;
+		}
 
 		err = download_firmware(lldev);
 		if (!err)
@@ -691,6 +721,18 @@ static int ll_setup(struct hci_uart *hu)
 	if (err)
 		return err;
 
+	/* Set BD address if one was specified at probe */
+	if (!bacmp(&lldev->bdaddr, BDADDR_NONE)) {
+		/* This means that there was an error getting the BD address
+		 * during probe, so mark the device as having a bad address.
+		 */
+		set_bit(HCI_QUIRK_INVALID_BDADDR, &hu->hdev->quirks);
+	} else if (bacmp(&lldev->bdaddr, BDADDR_ANY)) {
+		err = ll_set_bdaddr(hu->hdev, &lldev->bdaddr);
+		if (err)
+			set_bit(HCI_QUIRK_INVALID_BDADDR, &hu->hdev->quirks);
+	}
+
 	/* Operational speed if any */
 	if (hu->oper_speed)
 		speed = hu->oper_speed;
@@ -700,7 +742,12 @@ static int ll_setup(struct hci_uart *hu)
 		speed = 0;
 
 	if (speed) {
-		struct sk_buff *skb = __hci_cmd_sync(hu->hdev, 0xff36, sizeof(speed), &speed, HCI_INIT_TIMEOUT);
+		__le32 speed_le = cpu_to_le32(speed);
+		struct sk_buff *skb;
+
+		skb = __hci_cmd_sync(hu->hdev, HCI_VS_UPDATE_UART_HCI_BAUDRATE,
+				     sizeof(speed_le), &speed_le,
+				     HCI_INIT_TIMEOUT);
 		if (!IS_ERR(skb)) {
 			kfree_skb(skb);
 			serdev_device_set_baudrate(serdev, speed);
@@ -716,6 +763,7 @@ static int hci_ti_probe(struct serdev_device *serdev)
 {
 	struct hci_uart *hu;
 	struct ll_device *lldev;
+	struct nvmem_cell *bdaddr_cell;
 	u32 max_speed = 3000000;
 
 	lldev = devm_kzalloc(&serdev->dev, sizeof(struct ll_device), GFP_KERNEL);
@@ -737,6 +785,52 @@ static int hci_ti_probe(struct serdev_device *serdev)
 	of_property_read_u32(serdev->dev.of_node, "max-speed", &max_speed);
 	hci_uart_set_speeds(hu, 115200, max_speed);
 
+	/* optional BD address from nvram */
+	bdaddr_cell = nvmem_cell_get(&serdev->dev, "bd-address");
+	if (IS_ERR(bdaddr_cell)) {
+		int err = PTR_ERR(bdaddr_cell);
+
+		if (err == -EPROBE_DEFER)
+			return err;
+
+		/* ENOENT means there is no matching nvmem cell and ENOSYS
+		 * means that nvmem is not enabled in the kernel configuration.
+		 */
+		if (err != -ENOENT && err != -ENOSYS) {
+			/* If there was some other error, give userspace a
+			 * chance to fix the problem instead of failing to load
+			 * the driver. Using BDADDR_NONE as a flag that is
+			 * tested later in the setup function.
+			 */
+			dev_warn(&serdev->dev,
+				 "Failed to get \"bd-address\" nvmem cell (%d)\n",
+				 err);
+			bacpy(&lldev->bdaddr, BDADDR_NONE);
+		}
+	} else {
+		bdaddr_t *bdaddr;
+		size_t len;
+
+		bdaddr = nvmem_cell_read(bdaddr_cell, &len);
+		nvmem_cell_put(bdaddr_cell);
+		if (IS_ERR(bdaddr)) {
+			dev_err(&serdev->dev, "Failed to read nvmem bd-address\n");
+			return PTR_ERR(bdaddr);
+		}
+		if (len != sizeof(bdaddr_t)) {
+			dev_err(&serdev->dev, "Invalid nvmem bd-address length\n");
+			kfree(bdaddr);
+			return -EINVAL;
+		}
+
+		/* As per the device tree bindings, the value from nvmem is
+		 * expected to be MSB first, but in the kernel it is expected
+		 * that bdaddr_t is LSB first.
+		 */
+		baswap(&lldev->bdaddr, bdaddr);
+		kfree(bdaddr);
+	}
+
 	return hci_uart_register_device(hu, &llp);
 }
 
@@ -748,6 +842,7 @@ static void hci_ti_remove(struct serdev_device *serdev)
 }
 
 static const struct of_device_id hci_ti_of_match[] = {
+	{ .compatible = "ti,cc2560" },
 	{ .compatible = "ti,wl1271-st" },
 	{ .compatible = "ti,wl1273-st" },
 	{ .compatible = "ti,wl1281-st" },
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index bbd7db7384e6..05ec530b8a3a 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -932,6 +932,9 @@ static int qca_setup(struct hci_uart *hu)
 	if (!ret) {
 		set_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags);
 		qca_debugfs_init(hdev);
+	} else if (ret == -ENOENT) {
+		/* No patch/nvm-config found, run with original fw/config */
+		ret = 0;
 	}
 
 	/* Setup bdaddr */
diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c
index 71664b22ec9d..e0e6461b9200 100644
--- a/drivers/bluetooth/hci_serdev.c
+++ b/drivers/bluetooth/hci_serdev.c
@@ -303,6 +303,7 @@ int hci_uart_register_device(struct hci_uart *hu,
 	hci_set_drvdata(hdev, hu);
 
 	INIT_WORK(&hu->write_work, hci_uart_write_work);
+	percpu_init_rwsem(&hu->proto_lock);
 
 	/* Only when vendor specific setup callback is provided, consider
 	 * the manufacturer information valid. This avoids filling in the
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index e6f6dbc04131..0521748a1972 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -299,7 +299,7 @@ static ssize_t vhci_write(struct kiocb *iocb, struct iov_iter *from)
 	return vhci_get_user(data, from);
 }
 
-static unsigned int vhci_poll(struct file *file, poll_table *wait)
+static __poll_t vhci_poll(struct file *file, poll_table *wait)
 {
 	struct vhci_data *data = file->private_data;
 
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index dc7b3c7b7d42..57e011d36a79 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -120,7 +120,7 @@ config QCOM_EBI2
 	  SRAM, ethernet adapters, FPGAs and LCD displays.
 
 config SIMPLE_PM_BUS
-	bool "Simple Power-Managed Bus Driver"
+	tristate "Simple Power-Managed Bus Driver"
 	depends on OF && PM
 	help
 	  Driver for transparent busses that don't need a real driver, but
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 3c29d36702a8..5426c04fe24b 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -1755,14 +1755,17 @@ static int cci_pmu_probe(struct platform_device *pdev)
 	raw_spin_lock_init(&cci_pmu->hw_events.pmu_lock);
 	mutex_init(&cci_pmu->reserve_mutex);
 	atomic_set(&cci_pmu->active_events, 0);
-	cpumask_set_cpu(smp_processor_id(), &cci_pmu->cpus);
+	cpumask_set_cpu(get_cpu(), &cci_pmu->cpus);
 
 	ret = cci_pmu_init(cci_pmu, pdev);
-	if (ret)
+	if (ret) {
+		put_cpu();
 		return ret;
+	}
 
 	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCI_ONLINE,
 					 &cci_pmu->node);
+	put_cpu();
 	pr_info("ARM %s PMU driver probed", cci_pmu->model->name);
 	return 0;
 }
diff --git a/drivers/bus/arm-ccn.c b/drivers/bus/arm-ccn.c
index 3063f5312397..b52332e52ca5 100644
--- a/drivers/bus/arm-ccn.c
+++ b/drivers/bus/arm-ccn.c
@@ -262,7 +262,7 @@ static struct attribute *arm_ccn_pmu_format_attrs[] = {
 	NULL
 };
 
-static struct attribute_group arm_ccn_pmu_format_attr_group = {
+static const struct attribute_group arm_ccn_pmu_format_attr_group = {
 	.name = "format",
 	.attrs = arm_ccn_pmu_format_attrs,
 };
@@ -451,7 +451,7 @@ static struct arm_ccn_pmu_event arm_ccn_pmu_events[] = {
 static struct attribute
 		*arm_ccn_pmu_events_attrs[ARRAY_SIZE(arm_ccn_pmu_events) + 1];
 
-static struct attribute_group arm_ccn_pmu_events_attr_group = {
+static const struct attribute_group arm_ccn_pmu_events_attr_group = {
 	.name = "events",
 	.is_visible = arm_ccn_pmu_events_is_visible,
 	.attrs = arm_ccn_pmu_events_attrs,
@@ -548,7 +548,7 @@ static struct attribute *arm_ccn_pmu_cmp_mask_attrs[] = {
 	NULL
 };
 
-static struct attribute_group arm_ccn_pmu_cmp_mask_attr_group = {
+static const struct attribute_group arm_ccn_pmu_cmp_mask_attr_group = {
 	.name = "cmp_mask",
 	.attrs = arm_ccn_pmu_cmp_mask_attrs,
 };
@@ -569,7 +569,7 @@ static struct attribute *arm_ccn_pmu_cpumask_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group arm_ccn_pmu_cpumask_attr_group = {
+static const struct attribute_group arm_ccn_pmu_cpumask_attr_group = {
 	.attrs = arm_ccn_pmu_cpumask_attrs,
 };
 
@@ -1268,10 +1268,12 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	if (ccn->dt.id == 0) {
 		name = "ccn";
 	} else {
-		int len = snprintf(NULL, 0, "ccn_%d", ccn->dt.id);
-
-		name = devm_kzalloc(ccn->dev, len + 1, GFP_KERNEL);
-		snprintf(name, len + 1, "ccn_%d", ccn->dt.id);
+		name = devm_kasprintf(ccn->dev, GFP_KERNEL, "ccn_%d",
+				      ccn->dt.id);
+		if (!name) {
+			err = -ENOMEM;
+			goto error_choose_name;
+		}
 	}
 
 	/* Perf driver registration */
@@ -1298,7 +1300,7 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	}
 
 	/* Pick one CPU which we will use to collect data from CCN... */
-	cpumask_set_cpu(smp_processor_id(), &ccn->dt.cpu);
+	cpumask_set_cpu(get_cpu(), &ccn->dt.cpu);
 
 	/* Also make sure that the overflow interrupt is handled by this CPU */
 	if (ccn->irq) {
@@ -1315,10 +1317,13 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 
 	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
 					 &ccn->dt.node);
+	put_cpu();
 	return 0;
 
 error_pmu_register:
 error_set_affinity:
+	put_cpu();
+error_choose_name:
 	ida_simple_remove(&arm_ccn_pmu_ida, ccn->dt.id);
 	for (i = 0; i < ccn->num_xps; i++)
 		writel(0, ccn->xp[i].base + CCN_XP_DT_CONTROL);
@@ -1581,8 +1586,8 @@ static int __init arm_ccn_init(void)
 
 static void __exit arm_ccn_exit(void)
 {
-	cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_CCN_ONLINE);
 	platform_driver_unregister(&arm_ccn_driver);
+	cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_CCN_ONLINE);
 }
 
 module_init(arm_ccn_init);
diff --git a/drivers/bus/omap_l3_noc.c b/drivers/bus/omap_l3_noc.c
index 5012e3ad1225..b040447575ad 100644
--- a/drivers/bus/omap_l3_noc.c
+++ b/drivers/bus/omap_l3_noc.c
@@ -375,3 +375,8 @@ static void __exit omap_l3_exit(void)
 	platform_driver_unregister(&omap_l3_driver);
 }
 module_exit(omap_l3_exit);
+
+MODULE_AUTHOR("Santosh Shilimkar");
+MODULE_AUTHOR("Sricharan R");
+MODULE_DESCRIPTION("OMAP L3 Interconnect error handling driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/bus/omap_l3_smx.c b/drivers/bus/omap_l3_smx.c
index 360a5c0a4ee0..b853a729537a 100644
--- a/drivers/bus/omap_l3_smx.c
+++ b/drivers/bus/omap_l3_smx.c
@@ -309,3 +309,9 @@ static void __exit omap3_l3_exit(void)
 	platform_driver_unregister(&omap3_l3_driver);
 }
 module_exit(omap3_l3_exit);
+
+MODULE_AUTHOR("Felipe Balbi");
+MODULE_AUTHOR("Santosh Shilimkar");
+MODULE_AUTHOR("Sricharan R");
+MODULE_DESCRIPTION("OMAP3XXX L3 Interconnect Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c
index 328ca93781cf..1b76d9585902 100644
--- a/drivers/bus/sunxi-rsb.c
+++ b/drivers/bus/sunxi-rsb.c
@@ -178,6 +178,7 @@ static struct bus_type sunxi_rsb_bus = {
 	.match		= sunxi_rsb_device_match,
 	.probe		= sunxi_rsb_device_probe,
 	.remove		= sunxi_rsb_device_remove,
+	.uevent		= of_device_uevent_modalias,
 };
 
 static void sunxi_rsb_dev_release(struct device *dev)
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index c3c76a1ea8a8..4d46003c46cf 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -18,6 +18,9 @@
 #include <linux/pm_runtime.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
+#include <linux/platform_data/ti-sysc.h>
+
+#include <dt-bindings/bus/ti-sysc.h>
 
 enum sysc_registers {
 	SYSC_REVISION,
@@ -36,6 +39,9 @@ enum sysc_clocks {
 
 static const char * const clock_names[] = { "fck", "ick", };
 
+#define SYSC_IDLEMODE_MASK		3
+#define SYSC_CLOCKACTIVITY_MASK		3
+
 /**
  * struct sysc - TI sysc interconnect target module registers and capabilities
  * @dev: struct device pointer
@@ -45,6 +51,10 @@ static const char * const clock_names[] = { "fck", "ick", };
  * @offsets: register offsets from module base
  * @clocks: clocks used by the interconnect target module
  * @legacy_mode: configured for legacy mode if set
+ * @cap: interconnect target module capabilities
+ * @cfg: interconnect target module configuration
+ * @name: name if available
+ * @revision: interconnect target module revision
  */
 struct sysc {
 	struct device *dev;
@@ -54,12 +64,34 @@ struct sysc {
 	int offsets[SYSC_MAX_REGS];
 	struct clk *clocks[SYSC_MAX_CLOCKS];
 	const char *legacy_mode;
+	const struct sysc_capabilities *cap;
+	struct sysc_config cfg;
+	const char *name;
+	u32 revision;
 };
 
+static u32 sysc_read(struct sysc *ddata, int offset)
+{
+	if (ddata->cfg.quirks & SYSC_QUIRK_16BIT) {
+		u32 val;
+
+		val = readw_relaxed(ddata->module_va + offset);
+		val |= (readw_relaxed(ddata->module_va + offset + 4) << 16);
+
+		return val;
+	}
+
+	return readl_relaxed(ddata->module_va + offset);
+}
+
 static u32 sysc_read_revision(struct sysc *ddata)
 {
-	return readl_relaxed(ddata->module_va +
-			     ddata->offsets[SYSC_REVISION]);
+	int offset = ddata->offsets[SYSC_REVISION];
+
+	if (offset < 0)
+		return 0;
+
+	return sysc_read(ddata, offset);
 }
 
 static int sysc_get_one_clock(struct sysc *ddata,
@@ -206,6 +238,21 @@ static int sysc_check_children(struct sysc *ddata)
 	return 0;
 }
 
+/*
+ * So far only I2C uses 16-bit read access with clockactivity with revision
+ * in two registers with stride of 4. We can detect this based on the rev
+ * register size to configure things far enough to be able to properly read
+ * the revision register.
+ */
+static void sysc_check_quirk_16bit(struct sysc *ddata, struct resource *res)
+{
+	if (resource_size(res) == 8) {
+		dev_dbg(ddata->dev,
+			"enabling 16-bit and clockactivity quirks\n");
+		ddata->cfg.quirks |= SYSC_QUIRK_16BIT | SYSC_QUIRK_USE_CLOCKACT;
+	}
+}
+
 /**
  * sysc_parse_one - parses the interconnect target module registers
  * @ddata: device driver data
@@ -236,6 +283,8 @@ static int sysc_parse_one(struct sysc *ddata, enum sysc_registers reg)
 	}
 
 	ddata->offsets[reg] = res->start - ddata->module_pa;
+	if (reg == SYSC_REVISION)
+		sysc_check_quirk_16bit(ddata, res);
 
 	return 0;
 }
@@ -369,22 +418,12 @@ static int sysc_map_and_check_registers(struct sysc *ddata)
  */
 static int sysc_show_rev(char *bufp, struct sysc *ddata)
 {
-	int error, len;
+	int len;
 
 	if (ddata->offsets[SYSC_REVISION] < 0)
 		return sprintf(bufp, ":NA");
 
-	error = pm_runtime_get_sync(ddata->dev);
-	if (error < 0) {
-		pm_runtime_put_noidle(ddata->dev);
-
-		return 0;
-	}
-
-	len = sprintf(bufp, ":%08x", sysc_read_revision(ddata));
-
-	pm_runtime_mark_last_busy(ddata->dev);
-	pm_runtime_put_autosuspend(ddata->dev);
+	len = sprintf(bufp, ":%08x", ddata->revision);
 
 	return len;
 }
@@ -464,6 +503,151 @@ static const struct dev_pm_ops sysc_pm_ops = {
 			   NULL)
 };
 
+/* At this point the module is configured enough to read the revision */
+static int sysc_init_module(struct sysc *ddata)
+{
+	int error;
+
+	error = pm_runtime_get_sync(ddata->dev);
+	if (error < 0) {
+		pm_runtime_put_noidle(ddata->dev);
+
+		return 0;
+	}
+	ddata->revision = sysc_read_revision(ddata);
+	pm_runtime_put_sync(ddata->dev);
+
+	return 0;
+}
+
+static int sysc_init_sysc_mask(struct sysc *ddata)
+{
+	struct device_node *np = ddata->dev->of_node;
+	int error;
+	u32 val;
+
+	error = of_property_read_u32(np, "ti,sysc-mask", &val);
+	if (error)
+		return 0;
+
+	if (val)
+		ddata->cfg.sysc_val = val & ddata->cap->sysc_mask;
+	else
+		ddata->cfg.sysc_val = ddata->cap->sysc_mask;
+
+	return 0;
+}
+
+static int sysc_init_idlemode(struct sysc *ddata, u8 *idlemodes,
+			      const char *name)
+{
+	struct device_node *np = ddata->dev->of_node;
+	struct property *prop;
+	const __be32 *p;
+	u32 val;
+
+	of_property_for_each_u32(np, name, prop, p, val) {
+		if (val >= SYSC_NR_IDLEMODES) {
+			dev_err(ddata->dev, "invalid idlemode: %i\n", val);
+			return -EINVAL;
+		}
+		*idlemodes |=  (1 << val);
+	}
+
+	return 0;
+}
+
+static int sysc_init_idlemodes(struct sysc *ddata)
+{
+	int error;
+
+	error = sysc_init_idlemode(ddata, &ddata->cfg.midlemodes,
+				   "ti,sysc-midle");
+	if (error)
+		return error;
+
+	error = sysc_init_idlemode(ddata, &ddata->cfg.sidlemodes,
+				   "ti,sysc-sidle");
+	if (error)
+		return error;
+
+	return 0;
+}
+
+/*
+ * Only some devices on omap4 and later have SYSCONFIG reset done
+ * bit. We can detect this if there is no SYSSTATUS at all, or the
+ * SYSTATUS bit 0 is not used. Note that some SYSSTATUS registers
+ * have multiple bits for the child devices like OHCI and EHCI.
+ * Depends on SYSC being parsed first.
+ */
+static int sysc_init_syss_mask(struct sysc *ddata)
+{
+	struct device_node *np = ddata->dev->of_node;
+	int error;
+	u32 val;
+
+	error = of_property_read_u32(np, "ti,syss-mask", &val);
+	if (error) {
+		if ((ddata->cap->type == TI_SYSC_OMAP4 ||
+		     ddata->cap->type == TI_SYSC_OMAP4_TIMER) &&
+		    (ddata->cfg.sysc_val & SYSC_OMAP4_SOFTRESET))
+			ddata->cfg.quirks |= SYSC_QUIRK_RESET_STATUS;
+
+		return 0;
+	}
+
+	if (!(val & 1) && (ddata->cfg.sysc_val & SYSC_OMAP4_SOFTRESET))
+		ddata->cfg.quirks |= SYSC_QUIRK_RESET_STATUS;
+
+	ddata->cfg.syss_mask = val;
+
+	return 0;
+}
+
+/* Device tree configured quirks */
+struct sysc_dts_quirk {
+	const char *name;
+	u32 mask;
+};
+
+static const struct sysc_dts_quirk sysc_dts_quirks[] = {
+	{ .name = "ti,no-idle-on-init",
+	  .mask = SYSC_QUIRK_NO_IDLE_ON_INIT, },
+	{ .name = "ti,no-reset-on-init",
+	  .mask = SYSC_QUIRK_NO_RESET_ON_INIT, },
+};
+
+static int sysc_init_dts_quirks(struct sysc *ddata)
+{
+	struct device_node *np = ddata->dev->of_node;
+	const struct property *prop;
+	int i, len, error;
+	u32 val;
+
+	ddata->legacy_mode = of_get_property(np, "ti,hwmods", NULL);
+
+	for (i = 0; i < ARRAY_SIZE(sysc_dts_quirks); i++) {
+		prop = of_get_property(np, sysc_dts_quirks[i].name, &len);
+		if (!prop)
+			break;
+
+		ddata->cfg.quirks |= sysc_dts_quirks[i].mask;
+	}
+
+	error = of_property_read_u32(np, "ti,sysc-delay-us", &val);
+	if (!error) {
+		if (val > 255) {
+			dev_warn(ddata->dev, "bad ti,sysc-delay-us: %i\n",
+				 val);
+		}
+
+		ddata->cfg.srst_udelay = (u8)val;
+	}
+
+	return 0;
+}
+
 static void sysc_unprepare(struct sysc *ddata)
 {
 	int i;
@@ -474,9 +658,230 @@ static void sysc_unprepare(struct sysc *ddata)
 	}
 }
 
+/*
+ * Common sysc register bits found on omap2, also known as type1
+ */
+static const struct sysc_regbits sysc_regbits_omap2 = {
+	.dmadisable_shift = -ENODEV,
+	.midle_shift = 12,
+	.sidle_shift = 3,
+	.clkact_shift = 8,
+	.emufree_shift = 5,
+	.enwkup_shift = 2,
+	.srst_shift = 1,
+	.autoidle_shift = 0,
+};
+
+static const struct sysc_capabilities sysc_omap2 = {
+	.type = TI_SYSC_OMAP2,
+	.sysc_mask = SYSC_OMAP2_CLOCKACTIVITY | SYSC_OMAP2_EMUFREE |
+		     SYSC_OMAP2_ENAWAKEUP | SYSC_OMAP2_SOFTRESET |
+		     SYSC_OMAP2_AUTOIDLE,
+	.regbits = &sysc_regbits_omap2,
+};
+
+/* All omap2 and 3 timers, and timers 1, 2 & 10 on omap 4 and 5 */
+static const struct sysc_capabilities sysc_omap2_timer = {
+	.type = TI_SYSC_OMAP2_TIMER,
+	.sysc_mask = SYSC_OMAP2_CLOCKACTIVITY | SYSC_OMAP2_EMUFREE |
+		     SYSC_OMAP2_ENAWAKEUP | SYSC_OMAP2_SOFTRESET |
+		     SYSC_OMAP2_AUTOIDLE,
+	.regbits = &sysc_regbits_omap2,
+	.mod_quirks = SYSC_QUIRK_USE_CLOCKACT,
+};
+
+/*
+ * SHAM2 (SHA1/MD5) sysc found on omap3, a variant of sysc_regbits_omap2
+ * with different sidle position
+ */
+static const struct sysc_regbits sysc_regbits_omap3_sham = {
+	.dmadisable_shift = -ENODEV,
+	.midle_shift = -ENODEV,
+	.sidle_shift = 4,
+	.clkact_shift = -ENODEV,
+	.enwkup_shift = -ENODEV,
+	.srst_shift = 1,
+	.autoidle_shift = 0,
+	.emufree_shift = -ENODEV,
+};
+
+static const struct sysc_capabilities sysc_omap3_sham = {
+	.type = TI_SYSC_OMAP3_SHAM,
+	.sysc_mask = SYSC_OMAP2_SOFTRESET | SYSC_OMAP2_AUTOIDLE,
+	.regbits = &sysc_regbits_omap3_sham,
+};
+
+/*
+ * AES register bits found on omap3 and later, a variant of
+ * sysc_regbits_omap2 with different sidle position
+ */
+static const struct sysc_regbits sysc_regbits_omap3_aes = {
+	.dmadisable_shift = -ENODEV,
+	.midle_shift = -ENODEV,
+	.sidle_shift = 6,
+	.clkact_shift = -ENODEV,
+	.enwkup_shift = -ENODEV,
+	.srst_shift = 1,
+	.autoidle_shift = 0,
+	.emufree_shift = -ENODEV,
+};
+
+static const struct sysc_capabilities sysc_omap3_aes = {
+	.type = TI_SYSC_OMAP3_AES,
+	.sysc_mask = SYSC_OMAP2_SOFTRESET | SYSC_OMAP2_AUTOIDLE,
+	.regbits = &sysc_regbits_omap3_aes,
+};
+
+/*
+ * Common sysc register bits found on omap4, also known as type2
+ */
+static const struct sysc_regbits sysc_regbits_omap4 = {
+	.dmadisable_shift = 16,
+	.midle_shift = 4,
+	.sidle_shift = 2,
+	.clkact_shift = -ENODEV,
+	.enwkup_shift = -ENODEV,
+	.emufree_shift = 1,
+	.srst_shift = 0,
+	.autoidle_shift = -ENODEV,
+};
+
+static const struct sysc_capabilities sysc_omap4 = {
+	.type = TI_SYSC_OMAP4,
+	.sysc_mask = SYSC_OMAP4_DMADISABLE | SYSC_OMAP4_FREEEMU |
+		     SYSC_OMAP4_SOFTRESET,
+	.regbits = &sysc_regbits_omap4,
+};
+
+static const struct sysc_capabilities sysc_omap4_timer = {
+	.type = TI_SYSC_OMAP4_TIMER,
+	.sysc_mask = SYSC_OMAP4_DMADISABLE | SYSC_OMAP4_FREEEMU |
+		     SYSC_OMAP4_SOFTRESET,
+	.regbits = &sysc_regbits_omap4,
+};
+
+/*
+ * Common sysc register bits found on omap4, also known as type3
+ */
+static const struct sysc_regbits sysc_regbits_omap4_simple = {
+	.dmadisable_shift = -ENODEV,
+	.midle_shift = 2,
+	.sidle_shift = 0,
+	.clkact_shift = -ENODEV,
+	.enwkup_shift = -ENODEV,
+	.srst_shift = -ENODEV,
+	.emufree_shift = -ENODEV,
+	.autoidle_shift = -ENODEV,
+};
+
+static const struct sysc_capabilities sysc_omap4_simple = {
+	.type = TI_SYSC_OMAP4_SIMPLE,
+	.regbits = &sysc_regbits_omap4_simple,
+};
+
+/*
+ * SmartReflex sysc found on omap34xx
+ */
+static const struct sysc_regbits sysc_regbits_omap34xx_sr = {
+	.dmadisable_shift = -ENODEV,
+	.midle_shift = -ENODEV,
+	.sidle_shift = -ENODEV,
+	.clkact_shift = 20,
+	.enwkup_shift = -ENODEV,
+	.srst_shift = -ENODEV,
+	.emufree_shift = -ENODEV,
+	.autoidle_shift = -ENODEV,
+};
+
+static const struct sysc_capabilities sysc_34xx_sr = {
+	.type = TI_SYSC_OMAP34XX_SR,
+	.sysc_mask = SYSC_OMAP2_CLOCKACTIVITY,
+	.regbits = &sysc_regbits_omap34xx_sr,
+	.mod_quirks = SYSC_QUIRK_USE_CLOCKACT | SYSC_QUIRK_UNCACHED,
+};
+
+/*
+ * SmartReflex sysc found on omap36xx and later
+ */
+static const struct sysc_regbits sysc_regbits_omap36xx_sr = {
+	.dmadisable_shift = -ENODEV,
+	.midle_shift = -ENODEV,
+	.sidle_shift = 24,
+	.clkact_shift = -ENODEV,
+	.enwkup_shift = 26,
+	.srst_shift = -ENODEV,
+	.emufree_shift = -ENODEV,
+	.autoidle_shift = -ENODEV,
+};
+
+static const struct sysc_capabilities sysc_36xx_sr = {
+	.type = TI_SYSC_OMAP36XX_SR,
+	.sysc_mask = SYSC_OMAP3_SR_ENAWAKEUP,
+	.regbits = &sysc_regbits_omap36xx_sr,
+	.mod_quirks = SYSC_QUIRK_UNCACHED,
+};
+
+static const struct sysc_capabilities sysc_omap4_sr = {
+	.type = TI_SYSC_OMAP4_SR,
+	.regbits = &sysc_regbits_omap36xx_sr,
+};
+
+/*
+ * McASP register bits found on omap4 and later
+ */
+static const struct sysc_regbits sysc_regbits_omap4_mcasp = {
+	.dmadisable_shift = -ENODEV,
+	.midle_shift = -ENODEV,
+	.sidle_shift = 0,
+	.clkact_shift = -ENODEV,
+	.enwkup_shift = -ENODEV,
+	.srst_shift = -ENODEV,
+	.emufree_shift = -ENODEV,
+	.autoidle_shift = -ENODEV,
+};
+
+static const struct sysc_capabilities sysc_omap4_mcasp = {
+	.type = TI_SYSC_OMAP4_MCASP,
+	.regbits = &sysc_regbits_omap4_mcasp,
+};
+
+/*
+ * FS USB host found on omap4 and later
+ */
+static const struct sysc_regbits sysc_regbits_omap4_usb_host_fs = {
+	.dmadisable_shift = -ENODEV,
+	.midle_shift = -ENODEV,
+	.sidle_shift = 24,
+	.clkact_shift = -ENODEV,
+	.enwkup_shift = 26,
+	.srst_shift = -ENODEV,
+	.emufree_shift = -ENODEV,
+	.autoidle_shift = -ENODEV,
+};
+
+static const struct sysc_capabilities sysc_omap4_usb_host_fs = {
+	.type = TI_SYSC_OMAP4_USB_HOST_FS,
+	.sysc_mask = SYSC_OMAP2_ENAWAKEUP,
+	.regbits = &sysc_regbits_omap4_usb_host_fs,
+};
+
+static int sysc_init_match(struct sysc *ddata)
+{
+	const struct sysc_capabilities *cap;
+
+	cap = of_device_get_match_data(ddata->dev);
+	if (!cap)
+		return -EINVAL;
+
+	ddata->cap = cap;
+	if (ddata->cap)
+		ddata->cfg.quirks |= ddata->cap->mod_quirks;
+
+	return 0;
+}
+
 static int sysc_probe(struct platform_device *pdev)
 {
-	struct device_node *np = pdev->dev.of_node;
 	struct sysc *ddata;
 	int error;
 
@@ -485,7 +890,15 @@ static int sysc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ddata->dev = &pdev->dev;
-	ddata->legacy_mode = of_get_property(np, "ti,hwmods", NULL);
+	platform_set_drvdata(pdev, ddata);
+
+	error = sysc_init_match(ddata);
+	if (error)
+		return error;
+
+	error = sysc_init_dts_quirks(ddata);
+	if (error)
+		goto unprepare;
 
 	error = sysc_get_clocks(ddata);
 	if (error)
@@ -495,9 +908,24 @@ static int sysc_probe(struct platform_device *pdev)
 	if (error)
 		goto unprepare;
 
-	platform_set_drvdata(pdev, ddata);
+	error = sysc_init_sysc_mask(ddata);
+	if (error)
+		goto unprepare;
+
+	error = sysc_init_idlemodes(ddata);
+	if (error)
+		goto unprepare;
+
+	error = sysc_init_syss_mask(ddata);
+	if (error)
+		goto unprepare;
 
 	pm_runtime_enable(ddata->dev);
+
+	error = sysc_init_module(ddata);
+	if (error)
+		goto unprepare;
+
 	error = pm_runtime_get_sync(ddata->dev);
 	if (error < 0) {
 		pm_runtime_put_noidle(ddata->dev);
@@ -554,16 +982,19 @@ unprepare:
 }
 
 static const struct of_device_id sysc_match[] = {
-	{ .compatible = "ti,sysc-omap2" },
-	{ .compatible = "ti,sysc-omap4" },
-	{ .compatible = "ti,sysc-omap4-simple" },
-	{ .compatible = "ti,sysc-omap3430-sr" },
-	{ .compatible = "ti,sysc-omap3630-sr" },
-	{ .compatible = "ti,sysc-omap4-sr" },
-	{ .compatible = "ti,sysc-omap3-sham" },
-	{ .compatible = "ti,sysc-omap-aes" },
-	{ .compatible = "ti,sysc-mcasp" },
-	{ .compatible = "ti,sysc-usb-host-fs" },
+	{ .compatible = "ti,sysc-omap2", .data = &sysc_omap2, },
+	{ .compatible = "ti,sysc-omap2-timer", .data = &sysc_omap2_timer, },
+	{ .compatible = "ti,sysc-omap4", .data = &sysc_omap4, },
+	{ .compatible = "ti,sysc-omap4-timer", .data = &sysc_omap4_timer, },
+	{ .compatible = "ti,sysc-omap4-simple", .data = &sysc_omap4_simple, },
+	{ .compatible = "ti,sysc-omap3430-sr", .data = &sysc_34xx_sr, },
+	{ .compatible = "ti,sysc-omap3630-sr", .data = &sysc_36xx_sr, },
+	{ .compatible = "ti,sysc-omap4-sr", .data = &sysc_omap4_sr, },
+	{ .compatible = "ti,sysc-omap3-sham", .data = &sysc_omap3_sham, },
+	{ .compatible = "ti,sysc-omap-aes", .data = &sysc_omap3_aes, },
+	{ .compatible = "ti,sysc-mcasp", .data = &sysc_omap4_mcasp, },
+	{ .compatible = "ti,sysc-usb-host-fs",
+	  .data = &sysc_omap4_usb_host_fs, },
 	{  },
 };
 MODULE_DEVICE_TABLE(of, sysc_match);
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 9b6b6023193b..c6271ce250b3 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -80,7 +80,7 @@ static struct _intel_private {
 	unsigned int needs_dmar : 1;
 	phys_addr_t gma_bus_addr;
 	/*  Size of memory reserved for graphics by the BIOS */
-	unsigned int stolen_size;
+	resource_size_t stolen_size;
 	/* Total number of gtt entries. */
 	unsigned int gtt_total_entries;
 	/* Part of the gtt that is mappable by the cpu, for those chips where
@@ -333,13 +333,13 @@ static void i810_write_entry(dma_addr_t addr, unsigned int entry,
 	writel_relaxed(addr | pte_flags, intel_private.gtt + entry);
 }
 
-static unsigned int intel_gtt_stolen_size(void)
+static resource_size_t intel_gtt_stolen_size(void)
 {
 	u16 gmch_ctrl;
 	u8 rdct;
 	int local = 0;
 	static const int ddt[4] = { 0, 16, 32, 64 };
-	unsigned int stolen_size = 0;
+	resource_size_t stolen_size = 0;
 
 	if (INTEL_GTT_GEN == 1)
 		return 0; /* no stolen mem on i81x */
@@ -417,8 +417,8 @@ static unsigned int intel_gtt_stolen_size(void)
 	}
 
 	if (stolen_size > 0) {
-		dev_info(&intel_private.bridge_dev->dev, "detected %dK %s memory\n",
-		       stolen_size / KB(1), local ? "local" : "stolen");
+		dev_info(&intel_private.bridge_dev->dev, "detected %lluK %s memory\n",
+		       (u64)stolen_size / KB(1), local ? "local" : "stolen");
 	} else {
 		dev_info(&intel_private.bridge_dev->dev,
 		       "no pre-allocated video memory detected\n");
@@ -872,6 +872,8 @@ void intel_gtt_insert_sg_entries(struct sg_table *st,
 		}
 	}
 	wmb();
+	if (intel_private.driver->chipset_flush)
+		intel_private.driver->chipset_flush();
 }
 EXPORT_SYMBOL(intel_gtt_insert_sg_entries);
 
@@ -1422,12 +1424,10 @@ int intel_gmch_probe(struct pci_dev *bridge_pdev, struct pci_dev *gpu_pdev,
 EXPORT_SYMBOL(intel_gmch_probe);
 
 void intel_gtt_get(u64 *gtt_total,
-		   u32 *stolen_size,
 		   phys_addr_t *mappable_base,
-		   u64 *mappable_end)
+		   resource_size_t *mappable_end)
 {
 	*gtt_total = intel_private.gtt_total_entries << PAGE_SHIFT;
-	*stolen_size = intel_private.stolen_size;
 	*mappable_base = intel_private.gma_bus_addr;
 	*mappable_end = intel_private.gtt_mappable_entries << PAGE_SHIFT;
 }
diff --git a/drivers/char/apm-emulation.c b/drivers/char/apm-emulation.c
index 1dfb9f8de171..a2a1c1478cd0 100644
--- a/drivers/char/apm-emulation.c
+++ b/drivers/char/apm-emulation.c
@@ -236,7 +236,7 @@ static ssize_t apm_read(struct file *fp, char __user *buf, size_t count, loff_t
 	return ret;
 }
 
-static unsigned int apm_poll(struct file *fp, poll_table * wait)
+static __poll_t apm_poll(struct file *fp, poll_table * wait)
 {
 	struct apm_user *as = fp->private_data;
 
diff --git a/drivers/char/dsp56k.c b/drivers/char/dsp56k.c
index 0d7b577e0ff0..2f92cc46698b 100644
--- a/drivers/char/dsp56k.c
+++ b/drivers/char/dsp56k.c
@@ -406,7 +406,7 @@ static long dsp56k_ioctl(struct file *file, unsigned int cmd,
  * Do I need this function at all???
  */
 #if 0
-static unsigned int dsp56k_poll(struct file *file, poll_table *wait)
+static __poll_t dsp56k_poll(struct file *file, poll_table *wait)
 {
 	int dev = iminor(file_inode(file)) & 0x0f;
 
diff --git a/drivers/char/dtlk.c b/drivers/char/dtlk.c
index 839ee61d352a..2697c22e3be2 100644
--- a/drivers/char/dtlk.c
+++ b/drivers/char/dtlk.c
@@ -91,7 +91,7 @@ static ssize_t dtlk_read(struct file *, char __user *,
 			 size_t nbytes, loff_t * ppos);
 static ssize_t dtlk_write(struct file *, const char __user *,
 			  size_t nbytes, loff_t * ppos);
-static unsigned int dtlk_poll(struct file *, poll_table *);
+static __poll_t dtlk_poll(struct file *, poll_table *);
 static int dtlk_open(struct inode *, struct file *);
 static int dtlk_release(struct inode *, struct file *);
 static long dtlk_ioctl(struct file *file,
@@ -228,9 +228,9 @@ static ssize_t dtlk_write(struct file *file, const char __user *buf,
 	return -EAGAIN;
 }
 
-static unsigned int dtlk_poll(struct file *file, poll_table * wait)
+static __poll_t dtlk_poll(struct file *file, poll_table * wait)
 {
-	int mask = 0;
+	__poll_t mask = 0;
 	unsigned long expires;
 
 	TRACE_TEXT(" dtlk_poll");
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index b941e6d59fd6..dbed4953f86c 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -342,7 +342,7 @@ out:
 	return retval;
 }
 
-static unsigned int hpet_poll(struct file *file, poll_table * wait)
+static __poll_t hpet_poll(struct file *file, poll_table * wait)
 {
 	unsigned long v;
 	struct hpet_dev *devp;
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index f6e3e5abc117..4d0f571c15f9 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -73,26 +73,14 @@ config HW_RANDOM_ATMEL
 
 	  If unsure, say Y.
 
-config HW_RANDOM_BCM63XX
-	tristate "Broadcom BCM63xx Random Number Generator support"
-	depends on BCM63XX || BMIPS_GENERIC
-	default HW_RANDOM
-	---help---
-	  This driver provides kernel-side support for the Random Number
-	  Generator hardware found on the Broadcom BCM63xx SoCs.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called bcm63xx-rng
-
-	  If unusure, say Y.
-
 config HW_RANDOM_BCM2835
-	tristate "Broadcom BCM2835 Random Number Generator support"
-	depends on ARCH_BCM2835 || ARCH_BCM_NSP || ARCH_BCM_5301X
+	tristate "Broadcom BCM2835/BCM63xx Random Number Generator support"
+	depends on ARCH_BCM2835 || ARCH_BCM_NSP || ARCH_BCM_5301X || \
+		   ARCH_BCM_63XX || BCM63XX || BMIPS_GENERIC
 	default HW_RANDOM
 	---help---
 	  This driver provides kernel-side support for the Random Number
-	  Generator hardware found on the Broadcom BCM2835 SoCs.
+	  Generator hardware found on the Broadcom BCM2835 and BCM63xx SoCs.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called bcm2835-rng
@@ -306,19 +294,6 @@ config HW_RANDOM_POWERNV
 
 	  If unsure, say Y.
 
-config HW_RANDOM_TPM
-	tristate "TPM HW Random Number Generator support"
-	depends on TCG_TPM
-	default HW_RANDOM
-	---help---
-	  This driver provides kernel-side support for the Random Number
-	  Generator in the Trusted Platform Module
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called tpm-rng.
-
-	  If unsure, say Y.
-
 config HW_RANDOM_HISI
 	tristate "Hisilicon Random Number Generator support"
 	depends on HW_RANDOM && ARCH_HISI
@@ -449,6 +424,18 @@ config HW_RANDOM_S390
 
 	  If unsure, say Y.
 
+config HW_RANDOM_EXYNOS
+	tristate "Samsung Exynos True Random Number Generator support"
+	depends on ARCH_EXYNOS || COMPILE_TEST
+	default HW_RANDOM
+	---help---
+	  This driver provides support for the True Random Number
+	  Generator available in Exynos SoCs.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called exynos-trng.
+
+	  If unsure, say Y.
 endif # HW_RANDOM
 
 config UML_RANDOM
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index f3728d008fff..b780370bd4eb 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -9,11 +9,11 @@ obj-$(CONFIG_HW_RANDOM_TIMERIOMEM) += timeriomem-rng.o
 obj-$(CONFIG_HW_RANDOM_INTEL) += intel-rng.o
 obj-$(CONFIG_HW_RANDOM_AMD) += amd-rng.o
 obj-$(CONFIG_HW_RANDOM_ATMEL) += atmel-rng.o
-obj-$(CONFIG_HW_RANDOM_BCM63XX)	+= bcm63xx-rng.o
 obj-$(CONFIG_HW_RANDOM_GEODE) += geode-rng.o
 obj-$(CONFIG_HW_RANDOM_N2RNG) += n2-rng.o
 n2-rng-y := n2-drv.o n2-asm.o
 obj-$(CONFIG_HW_RANDOM_VIA) += via-rng.o
+obj-$(CONFIG_HW_RANDOM_EXYNOS) += exynos-trng.o
 obj-$(CONFIG_HW_RANDOM_IXP4XX) += ixp4xx-rng.o
 obj-$(CONFIG_HW_RANDOM_OMAP) += omap-rng.o
 obj-$(CONFIG_HW_RANDOM_OMAP3_ROM) += omap3-rom-rng.o
@@ -27,7 +27,6 @@ obj-$(CONFIG_HW_RANDOM_NOMADIK) += nomadik-rng.o
 obj-$(CONFIG_HW_RANDOM_PSERIES) += pseries-rng.o
 obj-$(CONFIG_HW_RANDOM_POWERNV) += powernv-rng.o
 obj-$(CONFIG_HW_RANDOM_HISI)	+= hisi-rng.o
-obj-$(CONFIG_HW_RANDOM_TPM) += tpm-rng.o
 obj-$(CONFIG_HW_RANDOM_BCM2835) += bcm2835-rng.o
 obj-$(CONFIG_HW_RANDOM_IPROC_RNG200) += iproc-rng200.o
 obj-$(CONFIG_HW_RANDOM_MSM) += msm-rng.o
diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c
index 574211a49549..7a84cec30c3a 100644
--- a/drivers/char/hw_random/bcm2835-rng.c
+++ b/drivers/char/hw_random/bcm2835-rng.c
@@ -15,6 +15,7 @@
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/printk.h>
+#include <linux/clk.h>
 
 #define RNG_CTRL	0x0
 #define RNG_STATUS	0x4
@@ -29,116 +30,180 @@
 
 #define RNG_INT_OFF	0x1
 
-static void __init nsp_rng_init(void __iomem *base)
+struct bcm2835_rng_priv {
+	struct hwrng rng;
+	void __iomem *base;
+	bool mask_interrupts;
+	struct clk *clk;
+};
+
+static inline struct bcm2835_rng_priv *to_rng_priv(struct hwrng *rng)
 {
-	u32 val;
+	return container_of(rng, struct bcm2835_rng_priv, rng);
+}
+
+static inline u32 rng_readl(struct bcm2835_rng_priv *priv, u32 offset)
+{
+	/* MIPS chips strapped for BE will automagically configure the
+	 * peripheral registers for CPU-native byte order.
+	 */
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+		return __raw_readl(priv->base + offset);
+	else
+		return readl(priv->base + offset);
+}
 
-	/* mask the interrupt */
-	val = readl(base + RNG_INT_MASK);
-	val |= RNG_INT_OFF;
-	writel(val, base + RNG_INT_MASK);
+static inline void rng_writel(struct bcm2835_rng_priv *priv, u32 val,
+			      u32 offset)
+{
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+		__raw_writel(val, priv->base + offset);
+	else
+		writel(val, priv->base + offset);
 }
 
 static int bcm2835_rng_read(struct hwrng *rng, void *buf, size_t max,
 			       bool wait)
 {
-	void __iomem *rng_base = (void __iomem *)rng->priv;
+	struct bcm2835_rng_priv *priv = to_rng_priv(rng);
 	u32 max_words = max / sizeof(u32);
 	u32 num_words, count;
 
-	while ((__raw_readl(rng_base + RNG_STATUS) >> 24) == 0) {
+	while ((rng_readl(priv, RNG_STATUS) >> 24) == 0) {
 		if (!wait)
 			return 0;
 		cpu_relax();
 	}
 
-	num_words = readl(rng_base + RNG_STATUS) >> 24;
+	num_words = rng_readl(priv, RNG_STATUS) >> 24;
 	if (num_words > max_words)
 		num_words = max_words;
 
 	for (count = 0; count < num_words; count++)
-		((u32 *)buf)[count] = readl(rng_base + RNG_DATA);
+		((u32 *)buf)[count] = rng_readl(priv, RNG_DATA);
 
 	return num_words * sizeof(u32);
 }
 
-static struct hwrng bcm2835_rng_ops = {
-	.name	= "bcm2835",
-	.read	= bcm2835_rng_read,
+static int bcm2835_rng_init(struct hwrng *rng)
+{
+	struct bcm2835_rng_priv *priv = to_rng_priv(rng);
+	int ret = 0;
+	u32 val;
+
+	if (!IS_ERR(priv->clk)) {
+		ret = clk_prepare_enable(priv->clk);
+		if (ret)
+			return ret;
+	}
+
+	if (priv->mask_interrupts) {
+		/* mask the interrupt */
+		val = rng_readl(priv, RNG_INT_MASK);
+		val |= RNG_INT_OFF;
+		rng_writel(priv, val, RNG_INT_MASK);
+	}
+
+	/* set warm-up count & enable */
+	rng_writel(priv, RNG_WARMUP_COUNT, RNG_STATUS);
+	rng_writel(priv, RNG_RBGEN, RNG_CTRL);
+
+	return ret;
+}
+
+static void bcm2835_rng_cleanup(struct hwrng *rng)
+{
+	struct bcm2835_rng_priv *priv = to_rng_priv(rng);
+
+	/* disable rng hardware */
+	rng_writel(priv, 0, RNG_CTRL);
+
+	if (!IS_ERR(priv->clk))
+		clk_disable_unprepare(priv->clk);
+}
+
+struct bcm2835_rng_of_data {
+	bool mask_interrupts;
+};
+
+static const struct bcm2835_rng_of_data nsp_rng_of_data = {
+	.mask_interrupts = true,
 };
 
 static const struct of_device_id bcm2835_rng_of_match[] = {
 	{ .compatible = "brcm,bcm2835-rng"},
-	{ .compatible = "brcm,bcm-nsp-rng", .data = nsp_rng_init},
-	{ .compatible = "brcm,bcm5301x-rng", .data = nsp_rng_init},
+	{ .compatible = "brcm,bcm-nsp-rng", .data = &nsp_rng_of_data },
+	{ .compatible = "brcm,bcm5301x-rng", .data = &nsp_rng_of_data },
+	{ .compatible = "brcm,bcm6368-rng"},
 	{},
 };
 
 static int bcm2835_rng_probe(struct platform_device *pdev)
 {
+	const struct bcm2835_rng_of_data *of_data;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
-	void (*rng_setup)(void __iomem *base);
 	const struct of_device_id *rng_id;
-	void __iomem *rng_base;
+	struct bcm2835_rng_priv *priv;
+	struct resource *r;
 	int err;
 
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, priv);
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
 	/* map peripheral */
-	rng_base = of_iomap(np, 0);
-	if (!rng_base) {
-		dev_err(dev, "failed to remap rng regs");
-		return -ENODEV;
-	}
-	bcm2835_rng_ops.priv = (unsigned long)rng_base;
+	priv->base = devm_ioremap_resource(dev, r);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	/* Clock is optional on most platforms */
+	priv->clk = devm_clk_get(dev, NULL);
+
+	priv->rng.name = pdev->name;
+	priv->rng.init = bcm2835_rng_init;
+	priv->rng.read = bcm2835_rng_read;
+	priv->rng.cleanup = bcm2835_rng_cleanup;
 
 	rng_id = of_match_node(bcm2835_rng_of_match, np);
-	if (!rng_id) {
-		iounmap(rng_base);
+	if (!rng_id)
 		return -EINVAL;
-	}
-	/* Check for rng init function, execute it */
-	rng_setup = rng_id->data;
-	if (rng_setup)
-		rng_setup(rng_base);
 
-	/* set warm-up count & enable */
-	__raw_writel(RNG_WARMUP_COUNT, rng_base + RNG_STATUS);
-	__raw_writel(RNG_RBGEN, rng_base + RNG_CTRL);
+	/* Check for rng init function, execute it */
+	of_data = rng_id->data;
+	if (of_data)
+		priv->mask_interrupts = of_data->mask_interrupts;
 
 	/* register driver */
-	err = hwrng_register(&bcm2835_rng_ops);
-	if (err) {
+	err = devm_hwrng_register(dev, &priv->rng);
+	if (err)
 		dev_err(dev, "hwrng registration failed\n");
-		iounmap(rng_base);
-	} else
+	else
 		dev_info(dev, "hwrng registered\n");
 
 	return err;
 }
 
-static int bcm2835_rng_remove(struct platform_device *pdev)
-{
-	void __iomem *rng_base = (void __iomem *)bcm2835_rng_ops.priv;
-
-	/* disable rng hardware */
-	__raw_writel(0, rng_base + RNG_CTRL);
-
-	/* unregister driver */
-	hwrng_unregister(&bcm2835_rng_ops);
-	iounmap(rng_base);
-
-	return 0;
-}
-
 MODULE_DEVICE_TABLE(of, bcm2835_rng_of_match);
 
+static struct platform_device_id bcm2835_rng_devtype[] = {
+	{ .name = "bcm2835-rng" },
+	{ .name = "bcm63xx-rng" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(platform, bcm2835_rng_devtype);
+
 static struct platform_driver bcm2835_rng_driver = {
 	.driver = {
 		.name = "bcm2835-rng",
 		.of_match_table = bcm2835_rng_of_match,
 	},
 	.probe		= bcm2835_rng_probe,
-	.remove		= bcm2835_rng_remove,
+	.id_table	= bcm2835_rng_devtype,
 };
 module_platform_driver(bcm2835_rng_driver);
 
diff --git a/drivers/char/hw_random/bcm63xx-rng.c b/drivers/char/hw_random/bcm63xx-rng.c
deleted file mode 100644
index 5132c9cde50d..000000000000
--- a/drivers/char/hw_random/bcm63xx-rng.c
+++ /dev/null
@@ -1,154 +0,0 @@
-/*
- * Broadcom BCM63xx Random Number Generator support
- *
- * Copyright (C) 2011, Florian Fainelli <florian@openwrt.org>
- * Copyright (C) 2009, Broadcom Corporation
- *
- */
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/io.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/platform_device.h>
-#include <linux/hw_random.h>
-#include <linux/of.h>
-
-#define RNG_CTRL			0x00
-#define RNG_EN				(1 << 0)
-
-#define RNG_STAT			0x04
-#define RNG_AVAIL_MASK			(0xff000000)
-
-#define RNG_DATA			0x08
-#define RNG_THRES			0x0c
-#define RNG_MASK			0x10
-
-struct bcm63xx_rng_priv {
-	struct hwrng rng;
-	struct clk *clk;
-	void __iomem *regs;
-};
-
-#define to_rng_priv(rng)	container_of(rng, struct bcm63xx_rng_priv, rng)
-
-static int bcm63xx_rng_init(struct hwrng *rng)
-{
-	struct bcm63xx_rng_priv *priv = to_rng_priv(rng);
-	u32 val;
-	int error;
-
-	error = clk_prepare_enable(priv->clk);
-	if (error)
-		return error;
-
-	val = __raw_readl(priv->regs + RNG_CTRL);
-	val |= RNG_EN;
-	__raw_writel(val, priv->regs + RNG_CTRL);
-
-	return 0;
-}
-
-static void bcm63xx_rng_cleanup(struct hwrng *rng)
-{
-	struct bcm63xx_rng_priv *priv = to_rng_priv(rng);
-	u32 val;
-
-	val = __raw_readl(priv->regs + RNG_CTRL);
-	val &= ~RNG_EN;
-	__raw_writel(val, priv->regs + RNG_CTRL);
-
-	clk_disable_unprepare(priv->clk);
-}
-
-static int bcm63xx_rng_data_present(struct hwrng *rng, int wait)
-{
-	struct bcm63xx_rng_priv *priv = to_rng_priv(rng);
-
-	return __raw_readl(priv->regs + RNG_STAT) & RNG_AVAIL_MASK;
-}
-
-static int bcm63xx_rng_data_read(struct hwrng *rng, u32 *data)
-{
-	struct bcm63xx_rng_priv *priv = to_rng_priv(rng);
-
-	*data = __raw_readl(priv->regs + RNG_DATA);
-
-	return 4;
-}
-
-static int bcm63xx_rng_probe(struct platform_device *pdev)
-{
-	struct resource *r;
-	int ret;
-	struct bcm63xx_rng_priv *priv;
-
-	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!r) {
-		dev_err(&pdev->dev, "no iomem resource\n");
-		return -ENXIO;
-	}
-
-	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
-
-	priv->rng.name = pdev->name;
-	priv->rng.init = bcm63xx_rng_init;
-	priv->rng.cleanup = bcm63xx_rng_cleanup;
-	priv->rng.data_present = bcm63xx_rng_data_present;
-	priv->rng.data_read = bcm63xx_rng_data_read;
-
-	priv->clk = devm_clk_get(&pdev->dev, "ipsec");
-	if (IS_ERR(priv->clk)) {
-		ret = PTR_ERR(priv->clk);
-		dev_err(&pdev->dev, "no clock for device: %d\n", ret);
-		return ret;
-	}
-
-	if (!devm_request_mem_region(&pdev->dev, r->start,
-					resource_size(r), pdev->name)) {
-		dev_err(&pdev->dev, "request mem failed");
-		return -EBUSY;
-	}
-
-	priv->regs = devm_ioremap_nocache(&pdev->dev, r->start,
-					resource_size(r));
-	if (!priv->regs) {
-		dev_err(&pdev->dev, "ioremap failed");
-		return -ENOMEM;
-	}
-
-	ret = devm_hwrng_register(&pdev->dev, &priv->rng);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to register rng device: %d\n",
-			ret);
-		return ret;
-	}
-
-	dev_info(&pdev->dev, "registered RNG driver\n");
-
-	return 0;
-}
-
-#ifdef CONFIG_OF
-static const struct of_device_id bcm63xx_rng_of_match[] = {
-	{ .compatible = "brcm,bcm6368-rng", },
-	{},
-};
-MODULE_DEVICE_TABLE(of, bcm63xx_rng_of_match);
-#endif
-
-static struct platform_driver bcm63xx_rng_driver = {
-	.probe		= bcm63xx_rng_probe,
-	.driver		= {
-		.name	= "bcm63xx-rng",
-		.of_match_table = of_match_ptr(bcm63xx_rng_of_match),
-	},
-};
-
-module_platform_driver(bcm63xx_rng_driver);
-
-MODULE_AUTHOR("Florian Fainelli <florian@openwrt.org>");
-MODULE_DESCRIPTION("Broadcom BCM63xx RNG driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 657b8770b6b9..91bb98c42a1c 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -306,6 +306,10 @@ static int enable_best_rng(void)
 		ret = ((new_rng == current_rng) ? 0 : set_current_rng(new_rng));
 		if (!ret)
 			cur_rng_set_by_user = 0;
+	} else {
+		drop_current_rng();
+		cur_rng_set_by_user = 0;
+		ret = 0;
 	}
 
 	return ret;
diff --git a/drivers/char/hw_random/exynos-trng.c b/drivers/char/hw_random/exynos-trng.c
new file mode 100644
index 000000000000..1947aed7c044
--- /dev/null
+++ b/drivers/char/hw_random/exynos-trng.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RNG driver for Exynos TRNGs
+ *
+ * Author: Łukasz Stelmach <l.stelmach@samsung.com>
+ *
+ * Copyright 2017 (c) Samsung Electronics Software, Inc.
+ *
+ * Based on the Exynos PRNG driver drivers/crypto/exynos-rng by
+ * Krzysztof Kozłowski <krzk@kernel.org>
+ */
+
+#include <linux/clk.h>
+#include <linux/crypto.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/hw_random.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#define EXYNOS_TRNG_CLKDIV         (0x0)
+
+#define EXYNOS_TRNG_CTRL           (0x20)
+#define EXYNOS_TRNG_CTRL_RNGEN     BIT(31)
+
+#define EXYNOS_TRNG_POST_CTRL      (0x30)
+#define EXYNOS_TRNG_ONLINE_CTRL    (0x40)
+#define EXYNOS_TRNG_ONLINE_STAT    (0x44)
+#define EXYNOS_TRNG_ONLINE_MAXCHI2 (0x48)
+#define EXYNOS_TRNG_FIFO_CTRL      (0x50)
+#define EXYNOS_TRNG_FIFO_0         (0x80)
+#define EXYNOS_TRNG_FIFO_1         (0x84)
+#define EXYNOS_TRNG_FIFO_2         (0x88)
+#define EXYNOS_TRNG_FIFO_3         (0x8c)
+#define EXYNOS_TRNG_FIFO_4         (0x90)
+#define EXYNOS_TRNG_FIFO_5         (0x94)
+#define EXYNOS_TRNG_FIFO_6         (0x98)
+#define EXYNOS_TRNG_FIFO_7         (0x9c)
+#define EXYNOS_TRNG_FIFO_LEN       (8)
+#define EXYNOS_TRNG_CLOCK_RATE     (500000)
+
+
+struct exynos_trng_dev {
+	struct device    *dev;
+	void __iomem     *mem;
+	struct clk       *clk;
+	struct hwrng rng;
+};
+
+static int exynos_trng_do_read(struct hwrng *rng, void *data, size_t max,
+			       bool wait)
+{
+	struct exynos_trng_dev *trng;
+	int val;
+
+	max = min_t(size_t, max, (EXYNOS_TRNG_FIFO_LEN * 4));
+
+	trng = (struct exynos_trng_dev *)rng->priv;
+
+	writel_relaxed(max * 8, trng->mem + EXYNOS_TRNG_FIFO_CTRL);
+	val = readl_poll_timeout(trng->mem + EXYNOS_TRNG_FIFO_CTRL, val,
+				 val == 0, 200, 1000000);
+	if (val < 0)
+		return val;
+
+	memcpy_fromio(data, trng->mem + EXYNOS_TRNG_FIFO_0, max);
+
+	return max;
+}
+
+static int exynos_trng_init(struct hwrng *rng)
+{
+	struct exynos_trng_dev *trng = (struct exynos_trng_dev *)rng->priv;
+	unsigned long sss_rate;
+	u32 val;
+
+	sss_rate = clk_get_rate(trng->clk);
+
+	/*
+	 * For most TRNG circuits the clock frequency of under 500 kHz
+	 * is safe.
+	 */
+	val = sss_rate / (EXYNOS_TRNG_CLOCK_RATE * 2);
+	if (val > 0x7fff) {
+		dev_err(trng->dev, "clock divider too large: %d", val);
+		return -ERANGE;
+	}
+	val = val << 1;
+	writel_relaxed(val, trng->mem + EXYNOS_TRNG_CLKDIV);
+
+	/* Enable the generator. */
+	val = EXYNOS_TRNG_CTRL_RNGEN;
+	writel_relaxed(val, trng->mem + EXYNOS_TRNG_CTRL);
+
+	/*
+	 * Disable post-processing. /dev/hwrng is supposed to deliver
+	 * unprocessed data.
+	 */
+	writel_relaxed(0, trng->mem + EXYNOS_TRNG_POST_CTRL);
+
+	return 0;
+}
+
+static int exynos_trng_probe(struct platform_device *pdev)
+{
+	struct exynos_trng_dev *trng;
+	struct resource *res;
+	int ret = -ENOMEM;
+
+	trng = devm_kzalloc(&pdev->dev, sizeof(*trng), GFP_KERNEL);
+	if (!trng)
+		return ret;
+
+	trng->rng.name = devm_kstrdup(&pdev->dev, dev_name(&pdev->dev),
+				      GFP_KERNEL);
+	if (!trng->rng.name)
+		return ret;
+
+	trng->rng.init = exynos_trng_init;
+	trng->rng.read = exynos_trng_do_read;
+	trng->rng.priv = (unsigned long) trng;
+
+	platform_set_drvdata(pdev, trng);
+	trng->dev = &pdev->dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	trng->mem = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(trng->mem))
+		return PTR_ERR(trng->mem);
+
+	pm_runtime_enable(&pdev->dev);
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Could not get runtime PM.\n");
+		goto err_pm_get;
+	}
+
+	trng->clk = devm_clk_get(&pdev->dev, "secss");
+	if (IS_ERR(trng->clk)) {
+		ret = PTR_ERR(trng->clk);
+		dev_err(&pdev->dev, "Could not get clock.\n");
+		goto err_clock;
+	}
+
+	ret = clk_prepare_enable(trng->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "Could not enable the clk.\n");
+		goto err_clock;
+	}
+
+	ret = hwrng_register(&trng->rng);
+	if (ret) {
+		dev_err(&pdev->dev, "Could not register hwrng device.\n");
+		goto err_register;
+	}
+
+	dev_info(&pdev->dev, "Exynos True Random Number Generator.\n");
+
+	return 0;
+
+err_register:
+	clk_disable_unprepare(trng->clk);
+
+err_clock:
+	pm_runtime_put_sync(&pdev->dev);
+
+err_pm_get:
+	pm_runtime_disable(&pdev->dev);
+
+	return ret;
+}
+
+static int exynos_trng_remove(struct platform_device *pdev)
+{
+	struct exynos_trng_dev *trng =  platform_get_drvdata(pdev);
+
+	hwrng_unregister(&trng->rng);
+	clk_disable_unprepare(trng->clk);
+
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+static int __maybe_unused exynos_trng_suspend(struct device *dev)
+{
+	pm_runtime_put_sync(dev);
+
+	return 0;
+}
+
+static int __maybe_unused exynos_trng_resume(struct device *dev)
+{
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "Could not get runtime PM.\n");
+		pm_runtime_put_noidle(dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(exynos_trng_pm_ops, exynos_trng_suspend,
+			 exynos_trng_resume);
+
+static const struct of_device_id exynos_trng_dt_match[] = {
+	{
+		.compatible = "samsung,exynos5250-trng",
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, exynos_trng_dt_match);
+
+static struct platform_driver exynos_trng_driver = {
+	.driver = {
+		.name = "exynos-trng",
+		.pm = &exynos_trng_pm_ops,
+		.of_match_table = exynos_trng_dt_match,
+	},
+	.probe = exynos_trng_probe,
+	.remove = exynos_trng_remove,
+};
+
+module_platform_driver(exynos_trng_driver);
+MODULE_AUTHOR("Łukasz Stelmach");
+MODULE_DESCRIPTION("H/W TRNG driver for Exynos chips");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/char/hw_random/imx-rngc.c b/drivers/char/hw_random/imx-rngc.c
index 88db42d30760..eca87249bcff 100644
--- a/drivers/char/hw_random/imx-rngc.c
+++ b/drivers/char/hw_random/imx-rngc.c
@@ -282,8 +282,7 @@ static int __exit imx_rngc_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int imx_rngc_suspend(struct device *dev)
+static int __maybe_unused imx_rngc_suspend(struct device *dev)
 {
 	struct imx_rngc *rngc = dev_get_drvdata(dev);
 
@@ -292,7 +291,7 @@ static int imx_rngc_suspend(struct device *dev)
 	return 0;
 }
 
-static int imx_rngc_resume(struct device *dev)
+static int __maybe_unused imx_rngc_resume(struct device *dev)
 {
 	struct imx_rngc *rngc = dev_get_drvdata(dev);
 
@@ -301,11 +300,7 @@ static int imx_rngc_resume(struct device *dev)
 	return 0;
 }
 
-static const struct dev_pm_ops imx_rngc_pm_ops = {
-	.suspend	= imx_rngc_suspend,
-	.resume		= imx_rngc_resume,
-};
-#endif
+SIMPLE_DEV_PM_OPS(imx_rngc_pm_ops, imx_rngc_suspend, imx_rngc_resume);
 
 static const struct of_device_id imx_rngc_dt_ids[] = {
 	{ .compatible = "fsl,imx25-rngb", .data = NULL, },
@@ -316,9 +311,7 @@ MODULE_DEVICE_TABLE(of, imx_rngc_dt_ids);
 static struct platform_driver imx_rngc_driver = {
 	.driver = {
 		.name = "imx_rngc",
-#ifdef CONFIG_PM
 		.pm = &imx_rngc_pm_ops,
-#endif
 		.of_match_table = imx_rngc_dt_ids,
 	},
 	.remove = __exit_p(imx_rngc_remove),
diff --git a/drivers/char/hw_random/mtk-rng.c b/drivers/char/hw_random/mtk-rng.c
index 8da7bcf54105..7f99cd52b40e 100644
--- a/drivers/char/hw_random/mtk-rng.c
+++ b/drivers/char/hw_random/mtk-rng.c
@@ -135,6 +135,7 @@ static int mtk_rng_probe(struct platform_device *pdev)
 #endif
 	priv->rng.read = mtk_rng_read;
 	priv->rng.priv = (unsigned long)&pdev->dev;
+	priv->rng.quality = 900;
 
 	priv->clk = devm_clk_get(&pdev->dev, "rng");
 	if (IS_ERR(priv->clk)) {
diff --git a/drivers/char/hw_random/tpm-rng.c b/drivers/char/hw_random/tpm-rng.c
deleted file mode 100644
index d6d448266f07..000000000000
--- a/drivers/char/hw_random/tpm-rng.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Copyright (C) 2012 Kent Yoder IBM Corporation
- *
- * HWRNG interfaces to pull RNG data from a TPM
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#include <linux/module.h>
-#include <linux/hw_random.h>
-#include <linux/tpm.h>
-
-#define MODULE_NAME "tpm-rng"
-
-static int tpm_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
-{
-	return tpm_get_random(TPM_ANY_NUM, data, max);
-}
-
-static struct hwrng tpm_rng = {
-	.name = MODULE_NAME,
-	.read = tpm_rng_read,
-};
-
-static int __init rng_init(void)
-{
-	return hwrng_register(&tpm_rng);
-}
-module_init(rng_init);
-
-static void __exit rng_exit(void)
-{
-	hwrng_unregister(&tpm_rng);
-}
-module_exit(rng_exit);
-
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Kent Yoder <key@linux.vnet.ibm.com>");
-MODULE_DESCRIPTION("RNG driver for TPM devices");
diff --git a/drivers/char/ipmi/bt-bmc.c b/drivers/char/ipmi/bt-bmc.c
index 6edfaa72b98b..7992c870b0a2 100644
--- a/drivers/char/ipmi/bt-bmc.c
+++ b/drivers/char/ipmi/bt-bmc.c
@@ -338,10 +338,10 @@ static int bt_bmc_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static unsigned int bt_bmc_poll(struct file *file, poll_table *wait)
+static __poll_t bt_bmc_poll(struct file *file, poll_table *wait)
 {
 	struct bt_bmc *bt_bmc = file_bt_bmc(file);
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 	u8 ctrl;
 
 	poll_wait(file, &bt_bmc->queue, wait);
diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c
index 2ffca4232686..a011a7739f5e 100644
--- a/drivers/char/ipmi/ipmi_devintf.c
+++ b/drivers/char/ipmi/ipmi_devintf.c
@@ -78,10 +78,10 @@ static void file_receive_handler(struct ipmi_recv_msg *msg,
 	spin_unlock_irqrestore(&(priv->recv_msg_lock), flags);
 }
 
-static unsigned int ipmi_poll(struct file *file, poll_table *wait)
+static __poll_t ipmi_poll(struct file *file, poll_table *wait)
 {
 	struct ipmi_file_private *priv = file->private_data;
-	unsigned int             mask = 0;
+	__poll_t             mask = 0;
 	unsigned long            flags;
 
 	poll_wait(file, &priv->wait, wait);
diff --git a/drivers/char/ipmi/ipmi_dmi.c b/drivers/char/ipmi/ipmi_dmi.c
index ab78b3be7e33..c5112b17d7ea 100644
--- a/drivers/char/ipmi/ipmi_dmi.c
+++ b/drivers/char/ipmi/ipmi_dmi.c
@@ -106,7 +106,10 @@ static void __init dmi_add_platform_ipmi(unsigned long base_addr,
 		pr_err("ipmi:dmi: Error allocation IPMI platform device\n");
 		return;
 	}
-	pdev->driver_override = override;
+	pdev->driver_override = kasprintf(GFP_KERNEL, "%s",
+					  override);
+	if (!pdev->driver_override)
+		goto err;
 
 	if (type == IPMI_DMI_TYPE_SSIF) {
 		set_prop_entry(p[pidx++], "i2c-addr", u16, base_addr);
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index f45732a2cb3e..e0b0d7e2d976 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -84,7 +84,7 @@ static int panic_op_write_handler(const char *val,
 	char valcp[16];
 	char *s;
 
-	strncpy(valcp, val, 16);
+	strncpy(valcp, val, 15);
 	valcp[15] = '\0';
 
 	s = strstrip(valcp);
@@ -2588,7 +2588,7 @@ static ssize_t device_id_show(struct device *dev,
 
 	return snprintf(buf, 10, "%u\n", id.device_id);
 }
-static DEVICE_ATTR(device_id, S_IRUGO, device_id_show, NULL);
+static DEVICE_ATTR_RO(device_id);
 
 static ssize_t provides_device_sdrs_show(struct device *dev,
 					 struct device_attribute *attr,
@@ -2604,8 +2604,7 @@ static ssize_t provides_device_sdrs_show(struct device *dev,
 
 	return snprintf(buf, 10, "%u\n", (id.device_revision & 0x80) >> 7);
 }
-static DEVICE_ATTR(provides_device_sdrs, S_IRUGO, provides_device_sdrs_show,
-		   NULL);
+static DEVICE_ATTR_RO(provides_device_sdrs);
 
 static ssize_t revision_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
@@ -2620,7 +2619,7 @@ static ssize_t revision_show(struct device *dev, struct device_attribute *attr,
 
 	return snprintf(buf, 20, "%u\n", id.device_revision & 0x0F);
 }
-static DEVICE_ATTR(revision, S_IRUGO, revision_show, NULL);
+static DEVICE_ATTR_RO(revision);
 
 static ssize_t firmware_revision_show(struct device *dev,
 				      struct device_attribute *attr,
@@ -2637,7 +2636,7 @@ static ssize_t firmware_revision_show(struct device *dev,
 	return snprintf(buf, 20, "%u.%x\n", id.firmware_revision_1,
 			id.firmware_revision_2);
 }
-static DEVICE_ATTR(firmware_revision, S_IRUGO, firmware_revision_show, NULL);
+static DEVICE_ATTR_RO(firmware_revision);
 
 static ssize_t ipmi_version_show(struct device *dev,
 				 struct device_attribute *attr,
@@ -2655,7 +2654,7 @@ static ssize_t ipmi_version_show(struct device *dev,
 			ipmi_version_major(&id),
 			ipmi_version_minor(&id));
 }
-static DEVICE_ATTR(ipmi_version, S_IRUGO, ipmi_version_show, NULL);
+static DEVICE_ATTR_RO(ipmi_version);
 
 static ssize_t add_dev_support_show(struct device *dev,
 				    struct device_attribute *attr,
@@ -2688,7 +2687,7 @@ static ssize_t manufacturer_id_show(struct device *dev,
 
 	return snprintf(buf, 20, "0x%6.6x\n", id.manufacturer_id);
 }
-static DEVICE_ATTR(manufacturer_id, S_IRUGO, manufacturer_id_show, NULL);
+static DEVICE_ATTR_RO(manufacturer_id);
 
 static ssize_t product_id_show(struct device *dev,
 			       struct device_attribute *attr,
@@ -2704,7 +2703,7 @@ static ssize_t product_id_show(struct device *dev,
 
 	return snprintf(buf, 10, "0x%4.4x\n", id.product_id);
 }
-static DEVICE_ATTR(product_id, S_IRUGO, product_id_show, NULL);
+static DEVICE_ATTR_RO(product_id);
 
 static ssize_t aux_firmware_rev_show(struct device *dev,
 				     struct device_attribute *attr,
@@ -2742,7 +2741,7 @@ static ssize_t guid_show(struct device *dev, struct device_attribute *attr,
 
 	return snprintf(buf, 38, "%pUl\n", guid.b);
 }
-static DEVICE_ATTR(guid, S_IRUGO, guid_show, NULL);
+static DEVICE_ATTR_RO(guid);
 
 static struct attribute *bmc_dev_attrs[] = {
 	&dev_attr_device_id.attr,
diff --git a/drivers/char/ipmi/ipmi_powernv.c b/drivers/char/ipmi/ipmi_powernv.c
index 07fddbefefe4..bcf493d8e238 100644
--- a/drivers/char/ipmi/ipmi_powernv.c
+++ b/drivers/char/ipmi/ipmi_powernv.c
@@ -250,8 +250,9 @@ static int ipmi_powernv_probe(struct platform_device *pdev)
 		ipmi->irq = opal_event_request(prop);
 	}
 
-	if (request_irq(ipmi->irq, ipmi_opal_event, IRQ_TYPE_LEVEL_HIGH,
-				"opal-ipmi", ipmi)) {
+	rc = request_irq(ipmi->irq, ipmi_opal_event, IRQ_TYPE_LEVEL_HIGH,
+			 "opal-ipmi", ipmi);
+	if (rc) {
 		dev_warn(dev, "Unable to request irq\n");
 		goto err_dispose;
 	}
@@ -264,7 +265,6 @@ static int ipmi_powernv_probe(struct platform_device *pdev)
 		goto err_unregister;
 	}
 
-	/* todo: query actual ipmi_device_id */
 	rc = ipmi_register_smi(&ipmi_powernv_smi_handlers, ipmi, dev, 0);
 	if (rc) {
 		dev_warn(dev, "IPMI SMI registration failed (%d)\n", rc);
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 779869ed32b1..6768cb2dd740 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -199,6 +199,9 @@ struct smi_info {
 	/* The timer for this si. */
 	struct timer_list   si_timer;
 
+	/* This flag is set, if the timer can be set */
+	bool		    timer_can_start;
+
 	/* This flag is set, if the timer is running (timer_pending() isn't enough) */
 	bool		    timer_running;
 
@@ -355,6 +358,8 @@ out:
 
 static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
 {
+	if (!smi_info->timer_can_start)
+		return;
 	smi_info->last_timeout_jiffies = jiffies;
 	mod_timer(&smi_info->si_timer, new_val);
 	smi_info->timer_running = true;
@@ -374,21 +379,18 @@ static void start_new_msg(struct smi_info *smi_info, unsigned char *msg,
 	smi_info->handlers->start_transaction(smi_info->si_sm, msg, size);
 }
 
-static void start_check_enables(struct smi_info *smi_info, bool start_timer)
+static void start_check_enables(struct smi_info *smi_info)
 {
 	unsigned char msg[2];
 
 	msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
 	msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD;
 
-	if (start_timer)
-		start_new_msg(smi_info, msg, 2);
-	else
-		smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
+	start_new_msg(smi_info, msg, 2);
 	smi_info->si_state = SI_CHECKING_ENABLES;
 }
 
-static void start_clear_flags(struct smi_info *smi_info, bool start_timer)
+static void start_clear_flags(struct smi_info *smi_info)
 {
 	unsigned char msg[3];
 
@@ -397,10 +399,7 @@ static void start_clear_flags(struct smi_info *smi_info, bool start_timer)
 	msg[1] = IPMI_CLEAR_MSG_FLAGS_CMD;
 	msg[2] = WDT_PRE_TIMEOUT_INT;
 
-	if (start_timer)
-		start_new_msg(smi_info, msg, 3);
-	else
-		smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3);
+	start_new_msg(smi_info, msg, 3);
 	smi_info->si_state = SI_CLEARING_FLAGS;
 }
 
@@ -435,11 +434,11 @@ static void start_getting_events(struct smi_info *smi_info)
  * Note that we cannot just use disable_irq(), since the interrupt may
  * be shared.
  */
-static inline bool disable_si_irq(struct smi_info *smi_info, bool start_timer)
+static inline bool disable_si_irq(struct smi_info *smi_info)
 {
 	if ((smi_info->io.irq) && (!smi_info->interrupt_disabled)) {
 		smi_info->interrupt_disabled = true;
-		start_check_enables(smi_info, start_timer);
+		start_check_enables(smi_info);
 		return true;
 	}
 	return false;
@@ -449,7 +448,7 @@ static inline bool enable_si_irq(struct smi_info *smi_info)
 {
 	if ((smi_info->io.irq) && (smi_info->interrupt_disabled)) {
 		smi_info->interrupt_disabled = false;
-		start_check_enables(smi_info, true);
+		start_check_enables(smi_info);
 		return true;
 	}
 	return false;
@@ -467,7 +466,7 @@ static struct ipmi_smi_msg *alloc_msg_handle_irq(struct smi_info *smi_info)
 
 	msg = ipmi_alloc_smi_msg();
 	if (!msg) {
-		if (!disable_si_irq(smi_info, true))
+		if (!disable_si_irq(smi_info))
 			smi_info->si_state = SI_NORMAL;
 	} else if (enable_si_irq(smi_info)) {
 		ipmi_free_smi_msg(msg);
@@ -483,7 +482,7 @@ retry:
 		/* Watchdog pre-timeout */
 		smi_inc_stat(smi_info, watchdog_pretimeouts);
 
-		start_clear_flags(smi_info, true);
+		start_clear_flags(smi_info);
 		smi_info->msg_flags &= ~WDT_PRE_TIMEOUT_INT;
 		if (smi_info->intf)
 			ipmi_smi_watchdog_pretimeout(smi_info->intf);
@@ -866,7 +865,7 @@ restart:
 		 * disable and messages disabled.
 		 */
 		if (smi_info->supports_event_msg_buff || smi_info->io.irq) {
-			start_check_enables(smi_info, true);
+			start_check_enables(smi_info);
 		} else {
 			smi_info->curr_msg = alloc_msg_handle_irq(smi_info);
 			if (!smi_info->curr_msg)
@@ -1167,6 +1166,7 @@ static int smi_start_processing(void       *send_info,
 
 	/* Set up the timer that drives the interface. */
 	timer_setup(&new_smi->si_timer, smi_timeout, 0);
+	new_smi->timer_can_start = true;
 	smi_mod_timer(new_smi, jiffies + SI_TIMEOUT_JIFFIES);
 
 	/* Try to claim any interrupts. */
@@ -1936,10 +1936,14 @@ static void check_for_broken_irqs(struct smi_info *smi_info)
 	check_set_rcv_irq(smi_info);
 }
 
-static inline void wait_for_timer_and_thread(struct smi_info *smi_info)
+static inline void stop_timer_and_thread(struct smi_info *smi_info)
 {
-	if (smi_info->thread != NULL)
+	if (smi_info->thread != NULL) {
 		kthread_stop(smi_info->thread);
+		smi_info->thread = NULL;
+	}
+
+	smi_info->timer_can_start = false;
 	if (smi_info->timer_running)
 		del_timer_sync(&smi_info->si_timer);
 }
@@ -2043,6 +2047,7 @@ static int try_smi_init(struct smi_info *new_smi)
 	int rv = 0;
 	int i;
 	char *init_name = NULL;
+	bool platform_device_registered = false;
 
 	pr_info(PFX "Trying %s-specified %s state machine at %s address 0x%lx, slave address 0x%x, irq %d\n",
 		ipmi_addr_src_to_str(new_smi->io.addr_source),
@@ -2152,7 +2157,7 @@ static int try_smi_init(struct smi_info *new_smi)
 	 * Start clearing the flags before we enable interrupts or the
 	 * timer to avoid racing with the timer.
 	 */
-	start_clear_flags(new_smi, false);
+	start_clear_flags(new_smi);
 
 	/*
 	 * IRQ is defined to be set when non-zero.  req_events will
@@ -2171,6 +2176,7 @@ static int try_smi_init(struct smi_info *new_smi)
 				rv);
 			goto out_err;
 		}
+		platform_device_registered = true;
 	}
 
 	dev_set_drvdata(new_smi->io.dev, new_smi);
@@ -2238,7 +2244,7 @@ out_err_remove_attrs:
 	dev_set_drvdata(new_smi->io.dev, NULL);
 
 out_err_stop_timer:
-	wait_for_timer_and_thread(new_smi);
+	stop_timer_and_thread(new_smi);
 
 out_err:
 	new_smi->interrupt_disabled = true;
@@ -2277,10 +2283,11 @@ out_err:
 	}
 
 	if (new_smi->pdev) {
-		platform_device_unregister(new_smi->pdev);
+		if (platform_device_registered)
+			platform_device_unregister(new_smi->pdev);
+		else
+			platform_device_put(new_smi->pdev);
 		new_smi->pdev = NULL;
-	} else if (new_smi->pdev) {
-		platform_device_put(new_smi->pdev);
 	}
 
 	kfree(init_name);
@@ -2388,7 +2395,7 @@ static void cleanup_one_si(struct smi_info *to_clean)
 	 */
 	if (to_clean->io.irq_cleanup)
 		to_clean->io.irq_cleanup(&to_clean->io);
-	wait_for_timer_and_thread(to_clean);
+	stop_timer_and_thread(to_clean);
 
 	/*
 	 * Timeouts are stopped, now make sure the interrupts are off
@@ -2400,7 +2407,7 @@ static void cleanup_one_si(struct smi_info *to_clean)
 		schedule_timeout_uninterruptible(1);
 	}
 	if (to_clean->handlers)
-		disable_si_irq(to_clean, false);
+		disable_si_irq(to_clean);
 	while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) {
 		poll(to_clean);
 		schedule_timeout_uninterruptible(1);
diff --git a/drivers/char/ipmi/ipmi_si_parisc.c b/drivers/char/ipmi/ipmi_si_parisc.c
index 090b073ab441..6b10f0e18a95 100644
--- a/drivers/char/ipmi/ipmi_si_parisc.c
+++ b/drivers/char/ipmi/ipmi_si_parisc.c
@@ -10,6 +10,8 @@ static int __init ipmi_parisc_probe(struct parisc_device *dev)
 {
 	struct si_sm_io io;
 
+	memset(&io, 0, sizeof(io));
+
 	io.si_type	= SI_KCS;
 	io.addr_source	= SI_DEVICETREE;
 	io.addr_type	= IPMI_MEM_ADDR_SPACE;
diff --git a/drivers/char/ipmi/ipmi_si_pci.c b/drivers/char/ipmi/ipmi_si_pci.c
index 99771f5cad07..27dd11c49d21 100644
--- a/drivers/char/ipmi/ipmi_si_pci.c
+++ b/drivers/char/ipmi/ipmi_si_pci.c
@@ -103,10 +103,13 @@ static int ipmi_pci_probe(struct pci_dev *pdev,
 	io.addr_source_cleanup = ipmi_pci_cleanup;
 	io.addr_source_data = pdev;
 
-	if (pci_resource_flags(pdev, 0) & IORESOURCE_IO)
+	if (pci_resource_flags(pdev, 0) & IORESOURCE_IO) {
 		io.addr_type = IPMI_IO_ADDR_SPACE;
-	else
+		io.io_setup = ipmi_si_port_setup;
+	} else {
 		io.addr_type = IPMI_MEM_ADDR_SPACE;
+		io.io_setup = ipmi_si_mem_setup;
+	}
 	io.addr_data = pci_resource_start(pdev, 0);
 
 	io.regspacing = ipmi_pci_probe_regspacing(&io);
diff --git a/drivers/char/ipmi/ipmi_si_platform.c b/drivers/char/ipmi/ipmi_si_platform.c
index 9573f1116450..f4214870d726 100644
--- a/drivers/char/ipmi/ipmi_si_platform.c
+++ b/drivers/char/ipmi/ipmi_si_platform.c
@@ -40,7 +40,7 @@ MODULE_PARM_DESC(tryacpi, "Setting this to zero will disable the"
 #endif
 #ifdef CONFIG_OF
 module_param_named(tryopenfirmware, si_tryopenfirmware, bool, 0);
-MODULE_PARM_DESC(tryacpi, "Setting this to zero will disable the"
+MODULE_PARM_DESC(tryopenfirmware, "Setting this to zero will disable the"
 		 " default scan of the interfaces identified via OpenFirmware");
 #endif
 #ifdef CONFIG_DMI
diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c
index 3cfaec728604..f929e72bdac8 100644
--- a/drivers/char/ipmi/ipmi_ssif.c
+++ b/drivers/char/ipmi/ipmi_ssif.c
@@ -2071,8 +2071,7 @@ static int ssif_platform_remove(struct platform_device *dev)
 		return 0;
 
 	mutex_lock(&ssif_infos_mutex);
-	if (addr_info->client)
-		i2c_unregister_device(addr_info->client);
+	i2c_unregister_device(addr_info->client);
 
 	list_del(&addr_info->link);
 	kfree(addr_info);
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 76b270678b50..34bc1f3ca414 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -232,7 +232,7 @@ static int set_param_str(const char *val, const struct kernel_param *kp)
 	char       valcp[16];
 	char       *s;
 
-	strncpy(valcp, val, 16);
+	strncpy(valcp, val, 15);
 	valcp[15] = '\0';
 
 	s = strstrip(valcp);
@@ -298,7 +298,7 @@ module_param(pretimeout, timeout, 0644);
 MODULE_PARM_DESC(pretimeout, "Pretimeout value in seconds.");
 
 module_param(panic_wdt_timeout, timeout, 0644);
-MODULE_PARM_DESC(timeout, "Timeout value on kernel panic in seconds.");
+MODULE_PARM_DESC(panic_wdt_timeout, "Timeout value on kernel panic in seconds.");
 
 module_param_cb(action, &param_ops_str, action_op, 0644);
 MODULE_PARM_DESC(action, "Timeout action. One of: "
@@ -887,9 +887,9 @@ static int ipmi_open(struct inode *ino, struct file *filep)
 	}
 }
 
-static unsigned int ipmi_poll(struct file *file, poll_table *wait)
+static __poll_t ipmi_poll(struct file *file, poll_table *wait)
 {
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 
 	poll_wait(file, &read_q, wait);
 
diff --git a/drivers/char/lp.c b/drivers/char/lp.c
index 8249762192d5..8c4dd1a3bb6a 100644
--- a/drivers/char/lp.c
+++ b/drivers/char/lp.c
@@ -659,17 +659,31 @@ static int lp_do_ioctl(unsigned int minor, unsigned int cmd,
 	return retval;
 }
 
-static int lp_set_timeout(unsigned int minor, struct timeval *par_timeout)
+static int lp_set_timeout(unsigned int minor, s64 tv_sec, long tv_usec)
 {
 	long to_jiffies;
 
 	/* Convert to jiffies, place in lp_table */
-	if ((par_timeout->tv_sec < 0) ||
-	    (par_timeout->tv_usec < 0)) {
+	if (tv_sec < 0 || tv_usec < 0)
 		return -EINVAL;
+
+	/*
+	 * we used to not check, so let's not make this fatal,
+	 * but deal with user space passing a 32-bit tv_nsec in
+	 * a 64-bit field, capping the timeout to 1 second
+	 * worth of microseconds, and capping the total at
+	 * MAX_JIFFY_OFFSET.
+	 */
+	if (tv_usec > 999999)
+		tv_usec = 999999;
+
+	if (tv_sec >= MAX_SEC_IN_JIFFIES - 1) {
+		to_jiffies = MAX_JIFFY_OFFSET;
+	} else {
+		to_jiffies = DIV_ROUND_UP(tv_usec, 1000000/HZ);
+		to_jiffies += tv_sec * (long) HZ;
 	}
-	to_jiffies = DIV_ROUND_UP(par_timeout->tv_usec, 1000000/HZ);
-	to_jiffies += par_timeout->tv_sec * (long) HZ;
+
 	if (to_jiffies <= 0) {
 		return -EINVAL;
 	}
@@ -677,23 +691,43 @@ static int lp_set_timeout(unsigned int minor, struct timeval *par_timeout)
 	return 0;
 }
 
+static int lp_set_timeout32(unsigned int minor, void __user *arg)
+{
+	s32 karg[2];
+
+	if (copy_from_user(karg, arg, sizeof(karg)))
+		return -EFAULT;
+
+	return lp_set_timeout(minor, karg[0], karg[1]);
+}
+
+static int lp_set_timeout64(unsigned int minor, void __user *arg)
+{
+	s64 karg[2];
+
+	if (copy_from_user(karg, arg, sizeof(karg)))
+		return -EFAULT;
+
+	return lp_set_timeout(minor, karg[0], karg[1]);
+}
+
 static long lp_ioctl(struct file *file, unsigned int cmd,
 			unsigned long arg)
 {
 	unsigned int minor;
-	struct timeval par_timeout;
 	int ret;
 
 	minor = iminor(file_inode(file));
 	mutex_lock(&lp_mutex);
 	switch (cmd) {
-	case LPSETTIMEOUT:
-		if (copy_from_user(&par_timeout, (void __user *)arg,
-					sizeof (struct timeval))) {
-			ret = -EFAULT;
+	case LPSETTIMEOUT_OLD:
+		if (BITS_PER_LONG == 32) {
+			ret = lp_set_timeout32(minor, (void __user *)arg);
 			break;
 		}
-		ret = lp_set_timeout(minor, &par_timeout);
+		/* fallthrough for 64-bit */
+	case LPSETTIMEOUT_NEW:
+		ret = lp_set_timeout64(minor, (void __user *)arg);
 		break;
 	default:
 		ret = lp_do_ioctl(minor, cmd, arg, (void __user *)arg);
@@ -709,18 +743,19 @@ static long lp_compat_ioctl(struct file *file, unsigned int cmd,
 			unsigned long arg)
 {
 	unsigned int minor;
-	struct timeval par_timeout;
 	int ret;
 
 	minor = iminor(file_inode(file));
 	mutex_lock(&lp_mutex);
 	switch (cmd) {
-	case LPSETTIMEOUT:
-		if (compat_get_timeval(&par_timeout, compat_ptr(arg))) {
-			ret = -EFAULT;
+	case LPSETTIMEOUT_OLD:
+		if (!COMPAT_USE_64BIT_TIME) {
+			ret = lp_set_timeout32(minor, (void __user *)arg);
 			break;
 		}
-		ret = lp_set_timeout(minor, &par_timeout);
+		/* fallthrough for x32 mode */
+	case LPSETTIMEOUT_NEW:
+		ret = lp_set_timeout64(minor, (void __user *)arg);
 		break;
 #ifdef LP_STATS
 	case LPGETSTATS:
@@ -865,7 +900,7 @@ static int __init lp_setup (char *str)
 			printk(KERN_INFO "lp: too many ports, %s ignored.\n",
 			       str);
 	} else if (!strcmp(str, "reset")) {
-		reset = 1;
+		reset = true;
 	}
 	return 1;
 }
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 6aefe5370e5b..052011bcf100 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -107,6 +107,8 @@ static ssize_t read_mem(struct file *file, char __user *buf,
 	phys_addr_t p = *ppos;
 	ssize_t read, sz;
 	void *ptr;
+	char *bounce;
+	int err;
 
 	if (p != *ppos)
 		return 0;
@@ -129,15 +131,22 @@ static ssize_t read_mem(struct file *file, char __user *buf,
 	}
 #endif
 
+	bounce = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!bounce)
+		return -ENOMEM;
+
 	while (count > 0) {
 		unsigned long remaining;
 		int allowed;
 
 		sz = size_inside_page(p, count);
 
+		err = -EPERM;
 		allowed = page_is_allowed(p >> PAGE_SHIFT);
 		if (!allowed)
-			return -EPERM;
+			goto failed;
+
+		err = -EFAULT;
 		if (allowed == 2) {
 			/* Show zeros for restricted memory. */
 			remaining = clear_user(buf, sz);
@@ -149,24 +158,32 @@ static ssize_t read_mem(struct file *file, char __user *buf,
 			 */
 			ptr = xlate_dev_mem_ptr(p);
 			if (!ptr)
-				return -EFAULT;
-
-			remaining = copy_to_user(buf, ptr, sz);
+				goto failed;
 
+			err = probe_kernel_read(bounce, ptr, sz);
 			unxlate_dev_mem_ptr(p, ptr);
+			if (err)
+				goto failed;
+
+			remaining = copy_to_user(buf, bounce, sz);
 		}
 
 		if (remaining)
-			return -EFAULT;
+			goto failed;
 
 		buf += sz;
 		p += sz;
 		count -= sz;
 		read += sz;
 	}
+	kfree(bounce);
 
 	*ppos += read;
 	return read;
+
+failed:
+	kfree(bounce);
+	return err;
 }
 
 static ssize_t write_mem(struct file *file, const char __user *buf,
diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c
index 9a1aaf538758..819fe37a3683 100644
--- a/drivers/char/pcmcia/cm4040_cs.c
+++ b/drivers/char/pcmcia/cm4040_cs.c
@@ -415,10 +415,10 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf,
 	return count;
 }
 
-static unsigned int cm4040_poll(struct file *filp, poll_table *wait)
+static __poll_t cm4040_poll(struct file *filp, poll_table *wait)
 {
 	struct reader_dev *dev = filp->private_data;
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 
 	poll_wait(filp, &dev->poll_wait, wait);
 
diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c
index d256110ba672..7a56d1a13ec3 100644
--- a/drivers/char/ppdev.c
+++ b/drivers/char/ppdev.c
@@ -769,10 +769,10 @@ static int pp_release(struct inode *inode, struct file *file)
 }
 
 /* No kernel lock held - fine */
-static unsigned int pp_poll(struct file *file, poll_table *wait)
+static __poll_t pp_poll(struct file *file, poll_table *wait)
 {
 	struct pp_struct *pp = file->private_data;
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 
 	poll_wait(file, &pp->irq_wait, wait);
 	if (atomic_read(&pp->irqc))
diff --git a/drivers/char/random.c b/drivers/char/random.c
index ec42c8bb9b0d..80f2c326db47 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -431,9 +431,9 @@ static int crng_init = 0;
 static int crng_init_cnt = 0;
 #define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE)
 static void _extract_crng(struct crng_state *crng,
-			  __u8 out[CHACHA20_BLOCK_SIZE]);
+			  __u32 out[CHACHA20_BLOCK_WORDS]);
 static void _crng_backtrack_protect(struct crng_state *crng,
-				    __u8 tmp[CHACHA20_BLOCK_SIZE], int used);
+				    __u32 tmp[CHACHA20_BLOCK_WORDS], int used);
 static void process_random_ready_list(void);
 static void _get_random_bytes(void *buf, int nbytes);
 
@@ -817,7 +817,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 	unsigned long	flags;
 	int		i, num;
 	union {
-		__u8	block[CHACHA20_BLOCK_SIZE];
+		__u32	block[CHACHA20_BLOCK_WORDS];
 		__u32	key[8];
 	} buf;
 
@@ -851,7 +851,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 }
 
 static void _extract_crng(struct crng_state *crng,
-			  __u8 out[CHACHA20_BLOCK_SIZE])
+			  __u32 out[CHACHA20_BLOCK_WORDS])
 {
 	unsigned long v, flags;
 
@@ -867,7 +867,7 @@ static void _extract_crng(struct crng_state *crng,
 	spin_unlock_irqrestore(&crng->lock, flags);
 }
 
-static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
+static void extract_crng(__u32 out[CHACHA20_BLOCK_WORDS])
 {
 	struct crng_state *crng = NULL;
 
@@ -885,7 +885,7 @@ static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
  * enough) to mutate the CRNG key to provide backtracking protection.
  */
 static void _crng_backtrack_protect(struct crng_state *crng,
-				    __u8 tmp[CHACHA20_BLOCK_SIZE], int used)
+				    __u32 tmp[CHACHA20_BLOCK_WORDS], int used)
 {
 	unsigned long	flags;
 	__u32		*s, *d;
@@ -897,14 +897,14 @@ static void _crng_backtrack_protect(struct crng_state *crng,
 		used = 0;
 	}
 	spin_lock_irqsave(&crng->lock, flags);
-	s = (__u32 *) &tmp[used];
+	s = &tmp[used / sizeof(__u32)];
 	d = &crng->state[4];
 	for (i=0; i < 8; i++)
 		*d++ ^= *s++;
 	spin_unlock_irqrestore(&crng->lock, flags);
 }
 
-static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used)
+static void crng_backtrack_protect(__u32 tmp[CHACHA20_BLOCK_WORDS], int used)
 {
 	struct crng_state *crng = NULL;
 
@@ -920,7 +920,7 @@ static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used)
 static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
 {
 	ssize_t ret = 0, i = CHACHA20_BLOCK_SIZE;
-	__u8 tmp[CHACHA20_BLOCK_SIZE];
+	__u32 tmp[CHACHA20_BLOCK_WORDS];
 	int large_request = (nbytes > 256);
 
 	while (nbytes) {
@@ -1507,7 +1507,7 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
  */
 static void _get_random_bytes(void *buf, int nbytes)
 {
-	__u8 tmp[CHACHA20_BLOCK_SIZE];
+	__u32 tmp[CHACHA20_BLOCK_WORDS];
 
 	trace_get_random_bytes(nbytes, _RET_IP_);
 
@@ -1784,10 +1784,10 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 	return ret;
 }
 
-static unsigned int
+static __poll_t
 random_poll(struct file *file, poll_table * wait)
 {
-	unsigned int mask;
+	__poll_t mask;
 
 	poll_wait(file, &random_read_wait, wait);
 	poll_wait(file, &random_write_wait, wait);
@@ -2114,7 +2114,7 @@ u64 get_random_u64(void)
 	if (use_lock)
 		read_lock_irqsave(&batched_entropy_reset_lock, flags);
 	if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
-		extract_crng((u8 *)batch->entropy_u64);
+		extract_crng((__u32 *)batch->entropy_u64);
 		batch->position = 0;
 	}
 	ret = batch->entropy_u64[batch->position++];
@@ -2144,7 +2144,7 @@ u32 get_random_u32(void)
 	if (use_lock)
 		read_lock_irqsave(&batched_entropy_reset_lock, flags);
 	if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
-		extract_crng((u8 *)batch->entropy_u32);
+		extract_crng(batch->entropy_u32);
 		batch->position = 0;
 	}
 	ret = batch->entropy_u32[batch->position++];
diff --git a/drivers/char/rtc.c b/drivers/char/rtc.c
index 5542a438bbd0..c6a317120a55 100644
--- a/drivers/char/rtc.c
+++ b/drivers/char/rtc.c
@@ -147,7 +147,7 @@ static long rtc_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 static void rtc_get_rtc_time(struct rtc_time *rtc_tm);
 
 #ifdef RTC_IRQ
-static unsigned int rtc_poll(struct file *file, poll_table *wait);
+static __poll_t rtc_poll(struct file *file, poll_table *wait);
 #endif
 
 static void get_rtc_alm_time(struct rtc_time *alm_tm);
@@ -790,7 +790,7 @@ no_irq:
 }
 
 #ifdef RTC_IRQ
-static unsigned int rtc_poll(struct file *file, poll_table *wait)
+static __poll_t rtc_poll(struct file *file, poll_table *wait)
 {
 	unsigned long l;
 
diff --git a/drivers/char/snsc.c b/drivers/char/snsc.c
index 6aa32679fd58..7f49fa0f41d7 100644
--- a/drivers/char/snsc.c
+++ b/drivers/char/snsc.c
@@ -321,10 +321,10 @@ scdrv_write(struct file *file, const char __user *buf,
 	return status;
 }
 
-static unsigned int
+static __poll_t
 scdrv_poll(struct file *file, struct poll_table_struct *wait)
 {
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 	int status = 0;
 	struct subch_data_s *sd = (struct subch_data_s *) file->private_data;
 	unsigned long flags;
diff --git a/drivers/char/sonypi.c b/drivers/char/sonypi.c
index d3a979e25724..fc041c462aa4 100644
--- a/drivers/char/sonypi.c
+++ b/drivers/char/sonypi.c
@@ -940,7 +940,7 @@ static ssize_t sonypi_misc_read(struct file *file, char __user *buf,
 	return ret;
 }
 
-static unsigned int sonypi_misc_poll(struct file *file, poll_table *wait)
+static __poll_t sonypi_misc_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &sonypi_device.fifo_proc_list, wait);
 	if (kfifo_len(&sonypi_device.fifo))
diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index a30352202f1f..18c81cbe4704 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -26,6 +26,17 @@ menuconfig TCG_TPM
 
 if TCG_TPM
 
+config HW_RANDOM_TPM
+	bool "TPM HW Random Number Generator support"
+	depends on TCG_TPM && HW_RANDOM && !(TCG_TPM=y && HW_RANDOM=m)
+	default y
+	---help---
+	  This setting exposes the TPM's Random Number Generator as a hwrng
+	  device. This allows the kernel to collect randomness from the TPM at
+	  boot, and provides the TPM randomines in /dev/hwrng.
+
+	  If unsure, say Y.
+
 config TCG_TIS_CORE
 	tristate
 	---help---
diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile
index 34b4bcf46f43..acd758381c58 100644
--- a/drivers/char/tpm/Makefile
+++ b/drivers/char/tpm/Makefile
@@ -6,8 +6,9 @@ obj-$(CONFIG_TCG_TPM) += tpm.o
 tpm-y := tpm-interface.o tpm-dev.o tpm-sysfs.o tpm-chip.o tpm2-cmd.o \
 	 tpm-dev-common.o tpmrm-dev.o tpm1_eventlog.o tpm2_eventlog.o \
          tpm2-space.o
-tpm-$(CONFIG_ACPI) += tpm_ppi.o tpm_acpi.o
-tpm-$(CONFIG_OF) += tpm_of.o
+tpm-$(CONFIG_ACPI) += tpm_ppi.o tpm_eventlog_acpi.o
+tpm-$(CONFIG_EFI) += tpm_eventlog_efi.o
+tpm-$(CONFIG_OF) += tpm_eventlog_of.o
 obj-$(CONFIG_TCG_TIS_CORE) += tpm_tis_core.o
 obj-$(CONFIG_TCG_TIS) += tpm_tis.o
 obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi.o
diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 0eca20c5a80c..0a62c19937b6 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -26,8 +26,9 @@
 #include <linux/spinlock.h>
 #include <linux/freezer.h>
 #include <linux/major.h>
+#include <linux/tpm_eventlog.h>
+#include <linux/hw_random.h>
 #include "tpm.h"
-#include "tpm_eventlog.h"
 
 DEFINE_IDR(dev_nums_idr);
 static DEFINE_MUTEX(idr_lock);
@@ -80,21 +81,26 @@ void tpm_put_ops(struct tpm_chip *chip)
 EXPORT_SYMBOL_GPL(tpm_put_ops);
 
 /**
- * tpm_chip_find_get() - return tpm_chip for a given chip number
- * @chip_num: id to find
+ * tpm_chip_find_get() - find and reserve a TPM chip
+ * @chip:	a &struct tpm_chip instance, %NULL for the default chip
  *
- * The return'd chip has been tpm_try_get_ops'd and must be released via
- * tpm_put_ops
+ * Finds a TPM chip and reserves its class device and operations. The chip must
+ * be released with tpm_chip_put_ops() after use.
+ *
+ * Return:
+ * A reserved &struct tpm_chip instance.
+ * %NULL if a chip is not found.
+ * %NULL if the chip is not available.
  */
-struct tpm_chip *tpm_chip_find_get(int chip_num)
+struct tpm_chip *tpm_chip_find_get(struct tpm_chip *chip)
 {
-	struct tpm_chip *chip, *res = NULL;
+	struct tpm_chip *res = NULL;
+	int chip_num = 0;
 	int chip_prev;
 
 	mutex_lock(&idr_lock);
 
-	if (chip_num == TPM_ANY_NUM) {
-		chip_num = 0;
+	if (!chip) {
 		do {
 			chip_prev = chip_num;
 			chip = idr_get_next(&dev_nums_idr, &chip_num);
@@ -104,8 +110,7 @@ struct tpm_chip *tpm_chip_find_get(int chip_num)
 			}
 		} while (chip_prev != chip_num);
 	} else {
-		chip = idr_find(&dev_nums_idr, chip_num);
-		if (chip && !tpm_try_get_ops(chip))
+		if (!tpm_try_get_ops(chip))
 			res = chip;
 	}
 
@@ -387,6 +392,26 @@ static int tpm_add_legacy_sysfs(struct tpm_chip *chip)
 
 	return 0;
 }
+
+static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	struct tpm_chip *chip = container_of(rng, struct tpm_chip, hwrng);
+
+	return tpm_get_random(chip, data, max);
+}
+
+static int tpm_add_hwrng(struct tpm_chip *chip)
+{
+	if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM))
+		return 0;
+
+	snprintf(chip->hwrng_name, sizeof(chip->hwrng_name),
+		 "tpm-rng-%d", chip->dev_num);
+	chip->hwrng.name = chip->hwrng_name;
+	chip->hwrng.read = tpm_hwrng_read;
+	return hwrng_register(&chip->hwrng);
+}
+
 /*
  * tpm_chip_register() - create a character device for the TPM chip
  * @chip: TPM chip to use.
@@ -419,11 +444,13 @@ int tpm_chip_register(struct tpm_chip *chip)
 
 	tpm_add_ppi(chip);
 
+	rc = tpm_add_hwrng(chip);
+	if (rc)
+		goto out_ppi;
+
 	rc = tpm_add_char_device(chip);
-	if (rc) {
-		tpm_bios_log_teardown(chip);
-		return rc;
-	}
+	if (rc)
+		goto out_hwrng;
 
 	rc = tpm_add_legacy_sysfs(chip);
 	if (rc) {
@@ -432,6 +459,14 @@ int tpm_chip_register(struct tpm_chip *chip)
 	}
 
 	return 0;
+
+out_hwrng:
+	if (IS_ENABLED(CONFIG_HW_RANDOM_TPM))
+		hwrng_unregister(&chip->hwrng);
+out_ppi:
+	tpm_bios_log_teardown(chip);
+
+	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm_chip_register);
 
@@ -451,6 +486,8 @@ EXPORT_SYMBOL_GPL(tpm_chip_register);
 void tpm_chip_unregister(struct tpm_chip *chip)
 {
 	tpm_del_legacy_sysfs(chip);
+	if (IS_ENABLED(CONFIG_HW_RANDOM_TPM))
+		hwrng_unregister(&chip->hwrng);
 	tpm_bios_log_teardown(chip);
 	if (chip->flags & TPM_CHIP_FLAG_TPM2)
 		cdev_device_del(&chip->cdevs, &chip->devs);
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 1d6729be4cd6..76df4fbcf089 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -30,9 +30,9 @@
 #include <linux/spinlock.h>
 #include <linux/freezer.h>
 #include <linux/pm_runtime.h>
+#include <linux/tpm_eventlog.h>
 
 #include "tpm.h"
-#include "tpm_eventlog.h"
 
 #define TPM_MAX_ORDINAL 243
 #define TSC_MAX_ORDINAL 12
@@ -328,7 +328,7 @@ unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip,
 }
 EXPORT_SYMBOL_GPL(tpm_calc_ordinal_duration);
 
-static bool tpm_validate_command(struct tpm_chip *chip,
+static int tpm_validate_command(struct tpm_chip *chip,
 				 struct tpm_space *space,
 				 const u8 *cmd,
 				 size_t len)
@@ -340,10 +340,10 @@ static bool tpm_validate_command(struct tpm_chip *chip,
 	unsigned int nr_handles;
 
 	if (len < TPM_HEADER_SIZE)
-		return false;
+		return -EINVAL;
 
 	if (!space)
-		return true;
+		return 0;
 
 	if (chip->flags & TPM_CHIP_FLAG_TPM2 && chip->nr_commands) {
 		cc = be32_to_cpu(header->ordinal);
@@ -352,7 +352,7 @@ static bool tpm_validate_command(struct tpm_chip *chip,
 		if (i < 0) {
 			dev_dbg(&chip->dev, "0x%04X is an invalid command\n",
 				cc);
-			return false;
+			return -EOPNOTSUPP;
 		}
 
 		attrs = chip->cc_attrs_tbl[i];
@@ -362,11 +362,11 @@ static bool tpm_validate_command(struct tpm_chip *chip,
 			goto err_len;
 	}
 
-	return true;
+	return 0;
 err_len:
 	dev_dbg(&chip->dev,
 		"%s: insufficient command length %zu", __func__, len);
-	return false;
+	return -EINVAL;
 }
 
 /**
@@ -391,8 +391,20 @@ ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space,
 	unsigned long stop;
 	bool need_locality;
 
-	if (!tpm_validate_command(chip, space, buf, bufsiz))
-		return -EINVAL;
+	rc = tpm_validate_command(chip, space, buf, bufsiz);
+	if (rc == -EINVAL)
+		return rc;
+	/*
+	 * If the command is not implemented by the TPM, synthesize a
+	 * response with a TPM2_RC_COMMAND_CODE return for user-space.
+	 */
+	if (rc == -EOPNOTSUPP) {
+		header->length = cpu_to_be32(sizeof(*header));
+		header->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS);
+		header->return_code = cpu_to_be32(TPM2_RC_COMMAND_CODE |
+						  TSS2_RESMGR_TPM_RC_LAYER);
+		return bufsiz;
+	}
 
 	if (bufsiz > TPM_BUFSIZE)
 		bufsiz = TPM_BUFSIZE;
@@ -413,6 +425,9 @@ ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space,
 	if (chip->dev.parent)
 		pm_runtime_get_sync(chip->dev.parent);
 
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, true);
+
 	/* Store the decision as chip->locality will be changed. */
 	need_locality = chip->locality == -1;
 
@@ -489,6 +504,9 @@ out:
 		chip->locality = -1;
 	}
 out_no_locality:
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, false);
+
 	if (chip->dev.parent)
 		pm_runtime_put_sync(chip->dev.parent);
 
@@ -809,19 +827,20 @@ int tpm_pcr_read_dev(struct tpm_chip *chip, int pcr_idx, u8 *res_buf)
 }
 
 /**
- * tpm_is_tpm2 - is the chip a TPM2 chip?
- * @chip_num:	tpm idx # or ANY
+ * tpm_is_tpm2 - do we a have a TPM2 chip?
+ * @chip:	a &struct tpm_chip instance, %NULL for the default chip
  *
- * Returns < 0 on error, and 1 or 0 on success depending whether the chip
- * is a TPM2 chip.
+ * Return:
+ * 1 if we have a TPM2 chip.
+ * 0 if we don't have a TPM2 chip.
+ * A negative number for system errors (errno).
  */
-int tpm_is_tpm2(u32 chip_num)
+int tpm_is_tpm2(struct tpm_chip *chip)
 {
-	struct tpm_chip *chip;
 	int rc;
 
-	chip = tpm_chip_find_get(chip_num);
-	if (chip == NULL)
+	chip = tpm_chip_find_get(chip);
+	if (!chip)
 		return -ENODEV;
 
 	rc = (chip->flags & TPM_CHIP_FLAG_TPM2) != 0;
@@ -833,23 +852,19 @@ int tpm_is_tpm2(u32 chip_num)
 EXPORT_SYMBOL_GPL(tpm_is_tpm2);
 
 /**
- * tpm_pcr_read - read a pcr value
- * @chip_num:	tpm idx # or ANY
- * @pcr_idx:	pcr idx to retrieve
- * @res_buf:	TPM_PCR value
- *		size of res_buf is 20 bytes (or NULL if you don't care)
+ * tpm_pcr_read - read a PCR value from SHA1 bank
+ * @chip:	a &struct tpm_chip instance, %NULL for the default chip
+ * @pcr_idx:	the PCR to be retrieved
+ * @res_buf:	the value of the PCR
  *
- * The TPM driver should be built-in, but for whatever reason it
- * isn't, protect against the chip disappearing, by incrementing
- * the module usage count.
+ * Return: same as with tpm_transmit_cmd()
  */
-int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf)
+int tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf)
 {
-	struct tpm_chip *chip;
 	int rc;
 
-	chip = tpm_chip_find_get(chip_num);
-	if (chip == NULL)
+	chip = tpm_chip_find_get(chip);
+	if (!chip)
 		return -ENODEV;
 	if (chip->flags & TPM_CHIP_FLAG_TPM2)
 		rc = tpm2_pcr_read(chip, pcr_idx, res_buf);
@@ -889,25 +904,26 @@ static int tpm1_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash,
 }
 
 /**
- * tpm_pcr_extend - extend pcr value with hash
- * @chip_num:	tpm idx # or AN&
- * @pcr_idx:	pcr idx to extend
- * @hash:	hash value used to extend pcr value
+ * tpm_pcr_extend - extend a PCR value in SHA1 bank.
+ * @chip:	a &struct tpm_chip instance, %NULL for the default chip
+ * @pcr_idx:	the PCR to be retrieved
+ * @hash:	the hash value used to extend the PCR value
  *
- * The TPM driver should be built-in, but for whatever reason it
- * isn't, protect against the chip disappearing, by incrementing
- * the module usage count.
+ * Note: with TPM 2.0 extends also those banks with a known digest size to the
+ * cryto subsystem in order to prevent malicious use of those PCR banks. In the
+ * future we should dynamically determine digest sizes.
+ *
+ * Return: same as with tpm_transmit_cmd()
  */
-int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash)
+int tpm_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash)
 {
 	int rc;
-	struct tpm_chip *chip;
 	struct tpm2_digest digest_list[ARRAY_SIZE(chip->active_banks)];
 	u32 count = 0;
 	int i;
 
-	chip = tpm_chip_find_get(chip_num);
-	if (chip == NULL)
+	chip = tpm_chip_find_get(chip);
+	if (!chip)
 		return -ENODEV;
 
 	if (chip->flags & TPM_CHIP_FLAG_TPM2) {
@@ -1019,82 +1035,29 @@ out:
 	return rc;
 }
 
-int tpm_send(u32 chip_num, void *cmd, size_t buflen)
+/**
+ * tpm_send - send a TPM command
+ * @chip:	a &struct tpm_chip instance, %NULL for the default chip
+ * @cmd:	a TPM command buffer
+ * @buflen:	the length of the TPM command buffer
+ *
+ * Return: same as with tpm_transmit_cmd()
+ */
+int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen)
 {
-	struct tpm_chip *chip;
 	int rc;
 
-	chip = tpm_chip_find_get(chip_num);
-	if (chip == NULL)
+	chip = tpm_chip_find_get(chip);
+	if (!chip)
 		return -ENODEV;
 
 	rc = tpm_transmit_cmd(chip, NULL, cmd, buflen, 0, 0,
-			      "attempting tpm_cmd");
+			      "attempting to a send a command");
 	tpm_put_ops(chip);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm_send);
 
-static bool wait_for_tpm_stat_cond(struct tpm_chip *chip, u8 mask,
-					bool check_cancel, bool *canceled)
-{
-	u8 status = chip->ops->status(chip);
-
-	*canceled = false;
-	if ((status & mask) == mask)
-		return true;
-	if (check_cancel && chip->ops->req_canceled(chip, status)) {
-		*canceled = true;
-		return true;
-	}
-	return false;
-}
-
-int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout,
-		      wait_queue_head_t *queue, bool check_cancel)
-{
-	unsigned long stop;
-	long rc;
-	u8 status;
-	bool canceled = false;
-
-	/* check current status */
-	status = chip->ops->status(chip);
-	if ((status & mask) == mask)
-		return 0;
-
-	stop = jiffies + timeout;
-
-	if (chip->flags & TPM_CHIP_FLAG_IRQ) {
-again:
-		timeout = stop - jiffies;
-		if ((long)timeout <= 0)
-			return -ETIME;
-		rc = wait_event_interruptible_timeout(*queue,
-			wait_for_tpm_stat_cond(chip, mask, check_cancel,
-					       &canceled),
-			timeout);
-		if (rc > 0) {
-			if (canceled)
-				return -ECANCELED;
-			return 0;
-		}
-		if (rc == -ERESTARTSYS && freezing(current)) {
-			clear_thread_flag(TIF_SIGPENDING);
-			goto again;
-		}
-	} else {
-		do {
-			tpm_msleep(TPM_TIMEOUT);
-			status = chip->ops->status(chip);
-			if ((status & mask) == mask)
-				return 0;
-		} while (time_before(jiffies, stop));
-	}
-	return -ETIME;
-}
-EXPORT_SYMBOL_GPL(wait_for_tpm_stat);
-
 #define TPM_ORD_SAVESTATE 152
 #define SAVESTATE_RESULT_SIZE 10
 
@@ -1187,16 +1150,15 @@ static const struct tpm_input_header tpm_getrandom_header = {
 };
 
 /**
- * tpm_get_random() - Get random bytes from the tpm's RNG
- * @chip_num: A specific chip number for the request or TPM_ANY_NUM
- * @out: destination buffer for the random bytes
- * @max: the max number of bytes to write to @out
+ * tpm_get_random() - get random bytes from the TPM's RNG
+ * @chip:	a &struct tpm_chip instance, %NULL for the default chip
+ * @out:	destination buffer for the random bytes
+ * @max:	the max number of bytes to write to @out
  *
- * Returns < 0 on error and the number of bytes read on success
+ * Return: same as with tpm_transmit_cmd()
  */
-int tpm_get_random(u32 chip_num, u8 *out, size_t max)
+int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max)
 {
-	struct tpm_chip *chip;
 	struct tpm_cmd_t tpm_cmd;
 	u32 recd, num_bytes = min_t(u32, max, TPM_MAX_RNG_DATA), rlength;
 	int err, total = 0, retries = 5;
@@ -1205,8 +1167,8 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
 	if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
 		return -EINVAL;
 
-	chip = tpm_chip_find_get(chip_num);
-	if (chip == NULL)
+	chip = tpm_chip_find_get(chip);
+	if (!chip)
 		return -ENODEV;
 
 	if (chip->flags & TPM_CHIP_FLAG_TPM2) {
@@ -1248,22 +1210,23 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
 EXPORT_SYMBOL_GPL(tpm_get_random);
 
 /**
- * tpm_seal_trusted() - seal a trusted key
- * @chip_num: A specific chip number for the request or TPM_ANY_NUM
- * @options: authentication values and other options
- * @payload: the key data in clear and encrypted form
+ * tpm_seal_trusted() - seal a trusted key payload
+ * @chip:	a &struct tpm_chip instance, %NULL for the default chip
+ * @options:	authentication values and other options
+ * @payload:	the key data in clear and encrypted form
  *
- * Returns < 0 on error and 0 on success. At the moment, only TPM 2.0 chips
- * are supported.
+ * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in
+ * the keyring subsystem.
+ *
+ * Return: same as with tpm_transmit_cmd()
  */
-int tpm_seal_trusted(u32 chip_num, struct trusted_key_payload *payload,
+int tpm_seal_trusted(struct tpm_chip *chip, struct trusted_key_payload *payload,
 		     struct trusted_key_options *options)
 {
-	struct tpm_chip *chip;
 	int rc;
 
-	chip = tpm_chip_find_get(chip_num);
-	if (chip == NULL || !(chip->flags & TPM_CHIP_FLAG_TPM2))
+	chip = tpm_chip_find_get(chip);
+	if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2))
 		return -ENODEV;
 
 	rc = tpm2_seal_trusted(chip, payload, options);
@@ -1275,21 +1238,23 @@ EXPORT_SYMBOL_GPL(tpm_seal_trusted);
 
 /**
  * tpm_unseal_trusted() - unseal a trusted key
- * @chip_num: A specific chip number for the request or TPM_ANY_NUM
- * @options: authentication values and other options
- * @payload: the key data in clear and encrypted form
+ * @chip:	a &struct tpm_chip instance, %NULL for the default chip
+ * @options:	authentication values and other options
+ * @payload:	the key data in clear and encrypted form
+ *
+ * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in
+ * the keyring subsystem.
  *
- * Returns < 0 on error and 0 on success. At the moment, only TPM 2.0 chips
- * are supported.
+ * Return: same as with tpm_transmit_cmd()
  */
-int tpm_unseal_trusted(u32 chip_num, struct trusted_key_payload *payload,
+int tpm_unseal_trusted(struct tpm_chip *chip,
+		       struct trusted_key_payload *payload,
 		       struct trusted_key_options *options)
 {
-	struct tpm_chip *chip;
 	int rc;
 
-	chip = tpm_chip_find_get(chip_num);
-	if (chip == NULL || !(chip->flags & TPM_CHIP_FLAG_TPM2))
+	chip = tpm_chip_find_get(chip);
+	if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2))
 		return -ENODEV;
 
 	rc = tpm2_unseal_trusted(chip, payload, options);
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 528cffbd49d3..f895fba4e20d 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
+#include <linux/hw_random.h>
 #include <linux/mutex.h>
 #include <linux/sched.h>
 #include <linux/platform_device.h>
@@ -34,6 +35,7 @@
 #include <linux/acpi.h>
 #include <linux/cdev.h>
 #include <linux/highmem.h>
+#include <linux/tpm_eventlog.h>
 #include <crypto/hash_info.h>
 
 #ifdef CONFIG_X86
@@ -93,12 +95,17 @@ enum tpm2_structures {
 	TPM2_ST_SESSIONS	= 0x8002,
 };
 
+/* Indicates from what layer of the software stack the error comes from */
+#define TSS2_RC_LAYER_SHIFT	 16
+#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT)
+
 enum tpm2_return_codes {
 	TPM2_RC_SUCCESS		= 0x0000,
 	TPM2_RC_HASH		= 0x0083, /* RC_FMT1 */
 	TPM2_RC_HANDLE		= 0x008B,
 	TPM2_RC_INITIALIZE	= 0x0100, /* RC_VER1 */
 	TPM2_RC_DISABLED	= 0x0120,
+	TPM2_RC_COMMAND_CODE    = 0x0143,
 	TPM2_RC_TESTING		= 0x090A, /* RC_WARN */
 	TPM2_RC_REFERENCE_H0	= 0x0910,
 };
@@ -210,6 +217,9 @@ struct tpm_chip {
 	int dev_num;		/* /dev/tpm# */
 	unsigned long is_open;	/* only one allowed */
 
+	char hwrng_name[64];
+	struct hwrng hwrng;
+
 	struct mutex tpm_mutex;	/* tpm is processing */
 
 	unsigned long timeout_a; /* jiffies */
@@ -385,10 +395,6 @@ struct tpm_cmd_t {
 	tpm_cmd_params	params;
 } __packed;
 
-struct tpm2_digest {
-	u16 alg_id;
-	u8 digest[SHA512_DIGEST_SIZE];
-} __packed;
 
 /* A string buffer type for constructing TPM commands. This is based on the
  * ideas of string buffer code in security/keys/trusted.h but is heap based
@@ -512,16 +518,14 @@ int tpm_do_selftest(struct tpm_chip *chip);
 unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal);
 int tpm_pm_suspend(struct device *dev);
 int tpm_pm_resume(struct device *dev);
-int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout,
-		      wait_queue_head_t *queue, bool check_cancel);
 
 static inline void tpm_msleep(unsigned int delay_msec)
 {
-	usleep_range(delay_msec * 1000,
-		     (delay_msec * 1000) + TPM_TIMEOUT_RANGE_US);
+	usleep_range((delay_msec * 1000) - TPM_TIMEOUT_RANGE_US,
+		     delay_msec * 1000);
 };
 
-struct tpm_chip *tpm_chip_find_get(int chip_num);
+struct tpm_chip *tpm_chip_find_get(struct tpm_chip *chip);
 __must_check int tpm_try_get_ops(struct tpm_chip *chip);
 void tpm_put_ops(struct tpm_chip *chip);
 
@@ -575,4 +579,34 @@ int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u32 cc,
 		       u8 *cmd);
 int tpm2_commit_space(struct tpm_chip *chip, struct tpm_space *space,
 		      u32 cc, u8 *buf, size_t *bufsiz);
+
+extern const struct seq_operations tpm2_binary_b_measurements_seqops;
+
+#if defined(CONFIG_ACPI)
+int tpm_read_log_acpi(struct tpm_chip *chip);
+#else
+static inline int tpm_read_log_acpi(struct tpm_chip *chip)
+{
+	return -ENODEV;
+}
+#endif
+#if defined(CONFIG_OF)
+int tpm_read_log_of(struct tpm_chip *chip);
+#else
+static inline int tpm_read_log_of(struct tpm_chip *chip)
+{
+	return -ENODEV;
+}
+#endif
+#if defined(CONFIG_EFI)
+int tpm_read_log_efi(struct tpm_chip *chip);
+#else
+static inline int tpm_read_log_efi(struct tpm_chip *chip)
+{
+	return -ENODEV;
+}
+#endif
+
+int tpm_bios_log_setup(struct tpm_chip *chip);
+void tpm_bios_log_teardown(struct tpm_chip *chip);
 #endif
diff --git a/drivers/char/tpm/tpm1_eventlog.c b/drivers/char/tpm/tpm1_eventlog.c
index 9a8605e500b5..add798bd69d0 100644
--- a/drivers/char/tpm/tpm1_eventlog.c
+++ b/drivers/char/tpm/tpm1_eventlog.c
@@ -21,13 +21,14 @@
  */
 
 #include <linux/seq_file.h>
+#include <linux/efi.h>
 #include <linux/fs.h>
 #include <linux/security.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/tpm_eventlog.h>
 
 #include "tpm.h"
-#include "tpm_eventlog.h"
 
 
 static const char* tcpa_event_type_strings[] = {
@@ -371,6 +372,10 @@ static int tpm_read_log(struct tpm_chip *chip)
 	if (rc != -ENODEV)
 		return rc;
 
+	rc = tpm_read_log_efi(chip);
+	if (rc != -ENODEV)
+		return rc;
+
 	return tpm_read_log_of(chip);
 }
 
@@ -388,11 +393,13 @@ int tpm_bios_log_setup(struct tpm_chip *chip)
 {
 	const char *name = dev_name(&chip->dev);
 	unsigned int cnt;
+	int log_version;
 	int rc = 0;
 
 	rc = tpm_read_log(chip);
-	if (rc)
+	if (rc < 0)
 		return rc;
+	log_version = rc;
 
 	cnt = 0;
 	chip->bios_dir[cnt] = securityfs_create_dir(name, NULL);
@@ -404,7 +411,7 @@ int tpm_bios_log_setup(struct tpm_chip *chip)
 	cnt++;
 
 	chip->bin_log_seqops.chip = chip;
-	if (chip->flags & TPM_CHIP_FLAG_TPM2)
+	if (log_version == EFI_TCG2_EVENT_LOG_FORMAT_TCG_2)
 		chip->bin_log_seqops.seqops =
 			&tpm2_binary_b_measurements_seqops;
 	else
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index f40d20671a78..c17e75348a99 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -849,28 +849,26 @@ static const struct tpm_input_header tpm2_selftest_header = {
 static int tpm2_do_selftest(struct tpm_chip *chip)
 {
 	int rc;
-	unsigned int delay_msec = 20;
+	unsigned int delay_msec = 10;
 	long duration;
 	struct tpm2_cmd cmd;
 
 	duration = jiffies_to_msecs(
 		tpm2_calc_ordinal_duration(chip, TPM2_CC_SELF_TEST));
 
-	while (duration > 0) {
+	while (1) {
 		cmd.header.in = tpm2_selftest_header;
 		cmd.params.selftest_in.full_test = 0;
 
 		rc = tpm_transmit_cmd(chip, NULL, &cmd, TPM2_SELF_TEST_IN_SIZE,
 				      0, 0, "continue selftest");
 
-		if (rc != TPM2_RC_TESTING)
+		if (rc != TPM2_RC_TESTING || delay_msec >= duration)
 			break;
 
-		tpm_msleep(delay_msec);
-		duration -= delay_msec;
-
-		/* wait longer the next round */
+		/* wait longer than before */
 		delay_msec *= 2;
+		tpm_msleep(delay_msec);
 	}
 
 	return rc;
diff --git a/drivers/char/tpm/tpm2_eventlog.c b/drivers/char/tpm/tpm2_eventlog.c
index 34a8afa69138..1ce4411292ba 100644
--- a/drivers/char/tpm/tpm2_eventlog.c
+++ b/drivers/char/tpm/tpm2_eventlog.c
@@ -21,9 +21,9 @@
 #include <linux/security.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/tpm_eventlog.h>
 
 #include "tpm.h"
-#include "tpm_eventlog.h"
 
 /*
  * calc_tpm2_event_size() - calculate the event size, where event
diff --git a/drivers/char/tpm/tpm_acpi.c b/drivers/char/tpm/tpm_eventlog_acpi.c
index 169edf3ce86d..66f19e93c216 100644
--- a/drivers/char/tpm/tpm_acpi.c
+++ b/drivers/char/tpm/tpm_eventlog_acpi.c
@@ -25,9 +25,9 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
+#include <linux/tpm_eventlog.h>
 
 #include "tpm.h"
-#include "tpm_eventlog.h"
 
 struct acpi_tcpa {
 	struct acpi_table_header hdr;
@@ -102,7 +102,7 @@ int tpm_read_log_acpi(struct tpm_chip *chip)
 	memcpy_fromio(log->bios_event_log, virt, len);
 
 	acpi_os_unmap_iomem(virt, len);
-	return 0;
+	return EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2;
 
 err:
 	kfree(log->bios_event_log);
diff --git a/drivers/char/tpm/tpm_eventlog_efi.c b/drivers/char/tpm/tpm_eventlog_efi.c
new file mode 100644
index 000000000000..e3f9ffd341d2
--- /dev/null
+++ b/drivers/char/tpm/tpm_eventlog_efi.c
@@ -0,0 +1,66 @@
+/*
+ * Copyright (C) 2017 Google
+ *
+ * Authors:
+ *      Thiebaud Weksteen <tweek@google.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/efi.h>
+#include <linux/tpm_eventlog.h>
+
+#include "tpm.h"
+
+/* read binary bios log from EFI configuration table */
+int tpm_read_log_efi(struct tpm_chip *chip)
+{
+
+	struct linux_efi_tpm_eventlog *log_tbl;
+	struct tpm_bios_log *log;
+	u32 log_size;
+	u8 tpm_log_version;
+
+	if (!(chip->flags & TPM_CHIP_FLAG_TPM2))
+		return -ENODEV;
+
+	if (efi.tpm_log == EFI_INVALID_TABLE_ADDR)
+		return -ENODEV;
+
+	log = &chip->log;
+
+	log_tbl = memremap(efi.tpm_log, sizeof(*log_tbl), MEMREMAP_WB);
+	if (!log_tbl) {
+		pr_err("Could not map UEFI TPM log table !\n");
+		return -ENOMEM;
+	}
+
+	log_size = log_tbl->size;
+	memunmap(log_tbl);
+
+	log_tbl = memremap(efi.tpm_log, sizeof(*log_tbl) + log_size,
+			   MEMREMAP_WB);
+	if (!log_tbl) {
+		pr_err("Could not map UEFI TPM log table payload!\n");
+		return -ENOMEM;
+	}
+
+	/* malloc EventLog space */
+	log->bios_event_log = kmalloc(log_size, GFP_KERNEL);
+	if (!log->bios_event_log)
+		goto err_memunmap;
+	memcpy(log->bios_event_log, log_tbl->log, log_size);
+	log->bios_event_log_end = log->bios_event_log + log_size;
+
+	tpm_log_version = log_tbl->version;
+	memunmap(log_tbl);
+	return tpm_log_version;
+
+err_memunmap:
+	memunmap(log_tbl);
+	return -ENOMEM;
+}
diff --git a/drivers/char/tpm/tpm_of.c b/drivers/char/tpm/tpm_eventlog_of.c
index aadb7f464076..96fd5646f866 100644
--- a/drivers/char/tpm/tpm_of.c
+++ b/drivers/char/tpm/tpm_eventlog_of.c
@@ -17,9 +17,9 @@
 
 #include <linux/slab.h>
 #include <linux/of.h>
+#include <linux/tpm_eventlog.h>
 
 #include "tpm.h"
-#include "tpm_eventlog.h"
 
 int tpm_read_log_of(struct tpm_chip *chip)
 {
@@ -76,5 +76,7 @@ int tpm_read_log_of(struct tpm_chip *chip)
 
 	memcpy(log->bios_event_log, __va(base), size);
 
-	return 0;
+	if (chip->flags & TPM_CHIP_FLAG_TPM2)
+		return EFI_TCG2_EVENT_LOG_FORMAT_TCG_2;
+	return EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2;
 }
diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c
index 79d6bbb58e39..c1dd39eaaeeb 100644
--- a/drivers/char/tpm/tpm_i2c_infineon.c
+++ b/drivers/char/tpm/tpm_i2c_infineon.c
@@ -665,9 +665,9 @@ out_err:
 }
 
 static const struct i2c_device_id tpm_tis_i2c_table[] = {
-	{"tpm_i2c_infineon", 0},
-	{"slb9635tt", 0},
-	{"slb9645tt", 1},
+	{"tpm_i2c_infineon"},
+	{"slb9635tt"},
+	{"slb9645tt"},
 	{},
 };
 
@@ -675,24 +675,9 @@ MODULE_DEVICE_TABLE(i2c, tpm_tis_i2c_table);
 
 #ifdef CONFIG_OF
 static const struct of_device_id tpm_tis_i2c_of_match[] = {
-	{
-		.name = "tpm_i2c_infineon",
-		.type = "tpm",
-		.compatible = "infineon,tpm_i2c_infineon",
-		.data = (void *)0
-	},
-	{
-		.name = "slb9635tt",
-		.type = "tpm",
-		.compatible = "infineon,slb9635tt",
-		.data = (void *)0
-	},
-	{
-		.name = "slb9645tt",
-		.type = "tpm",
-		.compatible = "infineon,slb9645tt",
-		.data = (void *)1
-	},
+	{.compatible = "infineon,tpm_i2c_infineon"},
+	{.compatible = "infineon,slb9635tt"},
+	{.compatible = "infineon,slb9645tt"},
 	{},
 };
 MODULE_DEVICE_TABLE(of, tpm_tis_i2c_of_match);
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index e2d1055fb814..f08949a5f678 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -133,93 +133,14 @@ static int check_acpi_tpm2(struct device *dev)
 }
 #endif
 
-#ifdef CONFIG_X86
-#define INTEL_LEGACY_BLK_BASE_ADDR      0xFED08000
-#define ILB_REMAP_SIZE			0x100
-#define LPC_CNTRL_REG_OFFSET            0x84
-#define LPC_CLKRUN_EN                   (1 << 2)
-
-static void __iomem *ilb_base_addr;
-
-static inline bool is_bsw(void)
-{
-	return ((boot_cpu_data.x86_model == INTEL_FAM6_ATOM_AIRMONT) ? 1 : 0);
-}
-
-/**
- * tpm_platform_begin_xfer() - clear LPC CLKRUN_EN i.e. clocks will be running
- */
-static void tpm_platform_begin_xfer(void)
-{
-	u32 clkrun_val;
-
-	if (!is_bsw())
-		return;
-
-	clkrun_val = ioread32(ilb_base_addr + LPC_CNTRL_REG_OFFSET);
-
-	/* Disable LPC CLKRUN# */
-	clkrun_val &= ~LPC_CLKRUN_EN;
-	iowrite32(clkrun_val, ilb_base_addr + LPC_CNTRL_REG_OFFSET);
-
-	/*
-	 * Write any random value on port 0x80 which is on LPC, to make
-	 * sure LPC clock is running before sending any TPM command.
-	 */
-	outb(0xCC, 0x80);
-
-}
-
-/**
- * tpm_platform_end_xfer() - set LPC CLKRUN_EN i.e. clocks can be turned off
- */
-static void tpm_platform_end_xfer(void)
-{
-	u32 clkrun_val;
-
-	if (!is_bsw())
-		return;
-
-	clkrun_val = ioread32(ilb_base_addr + LPC_CNTRL_REG_OFFSET);
-
-	/* Enable LPC CLKRUN# */
-	clkrun_val |= LPC_CLKRUN_EN;
-	iowrite32(clkrun_val, ilb_base_addr + LPC_CNTRL_REG_OFFSET);
-
-	/*
-	 * Write any random value on port 0x80 which is on LPC, to make
-	 * sure LPC clock is running before sending any TPM command.
-	 */
-	outb(0xCC, 0x80);
-
-}
-#else
-static inline bool is_bsw(void)
-{
-	return false;
-}
-
-static void tpm_platform_begin_xfer(void)
-{
-}
-
-static void tpm_platform_end_xfer(void)
-{
-}
-#endif
-
 static int tpm_tcg_read_bytes(struct tpm_tis_data *data, u32 addr, u16 len,
 			      u8 *result)
 {
 	struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data);
 
-	tpm_platform_begin_xfer();
-
 	while (len--)
 		*result++ = ioread8(phy->iobase + addr);
 
-	tpm_platform_end_xfer();
-
 	return 0;
 }
 
@@ -228,13 +149,9 @@ static int tpm_tcg_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len,
 {
 	struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data);
 
-	tpm_platform_begin_xfer();
-
 	while (len--)
 		iowrite8(*value++, phy->iobase + addr);
 
-	tpm_platform_end_xfer();
-
 	return 0;
 }
 
@@ -242,12 +159,8 @@ static int tpm_tcg_read16(struct tpm_tis_data *data, u32 addr, u16 *result)
 {
 	struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data);
 
-	tpm_platform_begin_xfer();
-
 	*result = ioread16(phy->iobase + addr);
 
-	tpm_platform_end_xfer();
-
 	return 0;
 }
 
@@ -255,12 +168,8 @@ static int tpm_tcg_read32(struct tpm_tis_data *data, u32 addr, u32 *result)
 {
 	struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data);
 
-	tpm_platform_begin_xfer();
-
 	*result = ioread32(phy->iobase + addr);
 
-	tpm_platform_end_xfer();
-
 	return 0;
 }
 
@@ -268,12 +177,8 @@ static int tpm_tcg_write32(struct tpm_tis_data *data, u32 addr, u32 value)
 {
 	struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data);
 
-	tpm_platform_begin_xfer();
-
 	iowrite32(value, phy->iobase + addr);
 
-	tpm_platform_end_xfer();
-
 	return 0;
 }
 
@@ -461,11 +366,6 @@ static int __init init_tis(void)
 	if (rc)
 		goto err_force;
 
-#ifdef CONFIG_X86
-	if (is_bsw())
-		ilb_base_addr = ioremap(INTEL_LEGACY_BLK_BASE_ADDR,
-					ILB_REMAP_SIZE);
-#endif
 	rc = platform_driver_register(&tis_drv);
 	if (rc)
 		goto err_platform;
@@ -484,10 +384,6 @@ err_pnp:
 err_platform:
 	if (force_pdev)
 		platform_device_unregister(force_pdev);
-#ifdef CONFIG_X86
-	if (is_bsw())
-		iounmap(ilb_base_addr);
-#endif
 err_force:
 	return rc;
 }
@@ -497,10 +393,6 @@ static void __exit cleanup_tis(void)
 	pnp_unregister_driver(&tis_pnp_driver);
 	platform_driver_unregister(&tis_drv);
 
-#ifdef CONFIG_X86
-	if (is_bsw())
-		iounmap(ilb_base_addr);
-#endif
 	if (force_pdev)
 		platform_device_unregister(force_pdev);
 }
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index fdde971bc810..183a5f54d875 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -31,6 +31,74 @@
 #include "tpm.h"
 #include "tpm_tis_core.h"
 
+/* This is a polling delay to check for status and burstcount.
+ * As per ddwg input, expectation is that status check and burstcount
+ * check should return within few usecs.
+ */
+#define TPM_POLL_SLEEP	1  /* msec */
+
+static void tpm_tis_clkrun_enable(struct tpm_chip *chip, bool value);
+
+static bool wait_for_tpm_stat_cond(struct tpm_chip *chip, u8 mask,
+					bool check_cancel, bool *canceled)
+{
+	u8 status = chip->ops->status(chip);
+
+	*canceled = false;
+	if ((status & mask) == mask)
+		return true;
+	if (check_cancel && chip->ops->req_canceled(chip, status)) {
+		*canceled = true;
+		return true;
+	}
+	return false;
+}
+
+static int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask,
+		unsigned long timeout, wait_queue_head_t *queue,
+		bool check_cancel)
+{
+	unsigned long stop;
+	long rc;
+	u8 status;
+	bool canceled = false;
+
+	/* check current status */
+	status = chip->ops->status(chip);
+	if ((status & mask) == mask)
+		return 0;
+
+	stop = jiffies + timeout;
+
+	if (chip->flags & TPM_CHIP_FLAG_IRQ) {
+again:
+		timeout = stop - jiffies;
+		if ((long)timeout <= 0)
+			return -ETIME;
+		rc = wait_event_interruptible_timeout(*queue,
+			wait_for_tpm_stat_cond(chip, mask, check_cancel,
+					       &canceled),
+			timeout);
+		if (rc > 0) {
+			if (canceled)
+				return -ECANCELED;
+			return 0;
+		}
+		if (rc == -ERESTARTSYS && freezing(current)) {
+			clear_thread_flag(TIF_SIGPENDING);
+			goto again;
+		}
+	} else {
+		do {
+			tpm_msleep(TPM_POLL_SLEEP);
+			status = chip->ops->status(chip);
+			if ((status & mask) == mask)
+				return 0;
+		} while (time_before(jiffies, stop));
+	}
+	return -ETIME;
+}
+
 /* Before we attempt to access the TPM we must see that the valid bit is set.
  * The specification says that this bit is 0 at reset and remains 0 until the
  * 'TPM has gone through its self test and initialization and has established
@@ -164,7 +232,7 @@ static int get_burstcount(struct tpm_chip *chip)
 		burstcnt = (value >> 8) & 0xFFFF;
 		if (burstcnt)
 			return burstcnt;
-		tpm_msleep(TPM_TIMEOUT);
+		tpm_msleep(TPM_POLL_SLEEP);
 	} while (time_before(jiffies, stop));
 	return -EBUSY;
 }
@@ -421,19 +489,28 @@ static bool tpm_tis_update_timeouts(struct tpm_chip *chip,
 	int i, rc;
 	u32 did_vid;
 
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, true);
+
 	rc = tpm_tis_read32(priv, TPM_DID_VID(0), &did_vid);
 	if (rc < 0)
-		return rc;
+		goto out;
 
 	for (i = 0; i != ARRAY_SIZE(vendor_timeout_overrides); i++) {
 		if (vendor_timeout_overrides[i].did_vid != did_vid)
 			continue;
 		memcpy(timeout_cap, vendor_timeout_overrides[i].timeout_us,
 		       sizeof(vendor_timeout_overrides[i].timeout_us));
-		return true;
+		rc = true;
 	}
 
-	return false;
+	rc = false;
+
+out:
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, false);
+
+	return rc;
 }
 
 /*
@@ -653,14 +730,73 @@ void tpm_tis_remove(struct tpm_chip *chip)
 	u32 interrupt;
 	int rc;
 
+	tpm_tis_clkrun_enable(chip, true);
+
 	rc = tpm_tis_read32(priv, reg, &interrupt);
 	if (rc < 0)
 		interrupt = 0;
 
 	tpm_tis_write32(priv, reg, ~TPM_GLOBAL_INT_ENABLE & interrupt);
+
+	tpm_tis_clkrun_enable(chip, false);
+
+	if (priv->ilb_base_addr)
+		iounmap(priv->ilb_base_addr);
 }
 EXPORT_SYMBOL_GPL(tpm_tis_remove);
 
+/**
+ * tpm_tis_clkrun_enable() - Keep clkrun protocol disabled for entire duration
+ *                           of a single TPM command
+ * @chip:	TPM chip to use
+ * @value:	1 - Disable CLKRUN protocol, so that clocks are free running
+ *		0 - Enable CLKRUN protocol
+ * Call this function directly in tpm_tis_remove() in error or driver removal
+ * path, since the chip->ops is set to NULL in tpm_chip_unregister().
+ */
+static void tpm_tis_clkrun_enable(struct tpm_chip *chip, bool value)
+{
+	struct tpm_tis_data *data = dev_get_drvdata(&chip->dev);
+	u32 clkrun_val;
+
+	if (!IS_ENABLED(CONFIG_X86) || !is_bsw() ||
+	    !data->ilb_base_addr)
+		return;
+
+	if (value) {
+		data->clkrun_enabled++;
+		if (data->clkrun_enabled > 1)
+			return;
+		clkrun_val = ioread32(data->ilb_base_addr + LPC_CNTRL_OFFSET);
+
+		/* Disable LPC CLKRUN# */
+		clkrun_val &= ~LPC_CLKRUN_EN;
+		iowrite32(clkrun_val, data->ilb_base_addr + LPC_CNTRL_OFFSET);
+
+		/*
+		 * Write any random value on port 0x80 which is on LPC, to make
+		 * sure LPC clock is running before sending any TPM command.
+		 */
+		outb(0xCC, 0x80);
+	} else {
+		data->clkrun_enabled--;
+		if (data->clkrun_enabled)
+			return;
+
+		clkrun_val = ioread32(data->ilb_base_addr + LPC_CNTRL_OFFSET);
+
+		/* Enable LPC CLKRUN# */
+		clkrun_val |= LPC_CLKRUN_EN;
+		iowrite32(clkrun_val, data->ilb_base_addr + LPC_CNTRL_OFFSET);
+
+		/*
+		 * Write any random value on port 0x80 which is on LPC, to make
+		 * sure LPC clock is running before sending any TPM command.
+		 */
+		outb(0xCC, 0x80);
+	}
+}
+
 static const struct tpm_class_ops tpm_tis = {
 	.flags = TPM_OPS_AUTO_STARTUP,
 	.status = tpm_tis_status,
@@ -673,13 +809,17 @@ static const struct tpm_class_ops tpm_tis = {
 	.req_canceled = tpm_tis_req_canceled,
 	.request_locality = request_locality,
 	.relinquish_locality = release_locality,
+	.clk_enable = tpm_tis_clkrun_enable,
 };
 
 int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
 		      const struct tpm_tis_phy_ops *phy_ops,
 		      acpi_handle acpi_dev_handle)
 {
-	u32 vendor, intfcaps, intmask;
+	u32 vendor;
+	u32 intfcaps;
+	u32 intmask;
+	u32 clkrun_val;
 	u8 rid;
 	int rc, probe;
 	struct tpm_chip *chip;
@@ -700,6 +840,23 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
 	priv->phy_ops = phy_ops;
 	dev_set_drvdata(&chip->dev, priv);
 
+	if (is_bsw()) {
+		priv->ilb_base_addr = ioremap(INTEL_LEGACY_BLK_BASE_ADDR,
+					ILB_REMAP_SIZE);
+		if (!priv->ilb_base_addr)
+			return -ENOMEM;
+
+		clkrun_val = ioread32(priv->ilb_base_addr + LPC_CNTRL_OFFSET);
+		/* Check if CLKRUN# is already not enabled in the LPC bus */
+		if (!(clkrun_val & LPC_CLKRUN_EN)) {
+			iounmap(priv->ilb_base_addr);
+			priv->ilb_base_addr = NULL;
+		}
+	}
+
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, true);
+
 	if (wait_startup(chip, 0) != 0) {
 		rc = -ENODEV;
 		goto out_err;
@@ -790,9 +947,20 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
 		}
 	}
 
-	return tpm_chip_register(chip);
+	rc = tpm_chip_register(chip);
+	if (rc)
+		goto out_err;
+
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, false);
+
+	return 0;
 out_err:
+	if ((chip->ops != NULL) && (chip->ops->clk_enable != NULL))
+		chip->ops->clk_enable(chip, false);
+
 	tpm_tis_remove(chip);
+
 	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm_tis_core_init);
@@ -804,22 +972,31 @@ static void tpm_tis_reenable_interrupts(struct tpm_chip *chip)
 	u32 intmask;
 	int rc;
 
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, true);
+
 	/* reenable interrupts that device may have lost or
 	 * BIOS/firmware may have disabled
 	 */
 	rc = tpm_tis_write8(priv, TPM_INT_VECTOR(priv->locality), priv->irq);
 	if (rc < 0)
-		return;
+		goto out;
 
 	rc = tpm_tis_read32(priv, TPM_INT_ENABLE(priv->locality), &intmask);
 	if (rc < 0)
-		return;
+		goto out;
 
 	intmask |= TPM_INTF_CMD_READY_INT
 	    | TPM_INTF_LOCALITY_CHANGE_INT | TPM_INTF_DATA_AVAIL_INT
 	    | TPM_INTF_STS_VALID_INT | TPM_GLOBAL_INT_ENABLE;
 
 	tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask);
+
+out:
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, false);
+
+	return;
 }
 
 int tpm_tis_resume(struct device *dev)
diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h
index 6bbac319ff3b..d5c6a2e952b3 100644
--- a/drivers/char/tpm/tpm_tis_core.h
+++ b/drivers/char/tpm/tpm_tis_core.h
@@ -79,6 +79,11 @@ enum tis_defaults {
 #define	TPM_DID_VID(l)			(0x0F00 | ((l) << 12))
 #define	TPM_RID(l)			(0x0F04 | ((l) << 12))
 
+#define LPC_CNTRL_OFFSET		0x84
+#define LPC_CLKRUN_EN			(1 << 2)
+#define INTEL_LEGACY_BLK_BASE_ADDR	0xFED08000
+#define ILB_REMAP_SIZE			0x100
+
 enum tpm_tis_flags {
 	TPM_TIS_ITPM_WORKAROUND		= BIT(0),
 };
@@ -89,6 +94,8 @@ struct tpm_tis_data {
 	int irq;
 	bool irq_tested;
 	unsigned int flags;
+	void __iomem *ilb_base_addr;
+	u16 clkrun_enabled;
 	wait_queue_head_t int_queue;
 	wait_queue_head_t read_queue;
 	const struct tpm_tis_phy_ops *phy_ops;
@@ -144,6 +151,15 @@ static inline int tpm_tis_write32(struct tpm_tis_data *data, u32 addr,
 	return data->phy_ops->write32(data, addr, value);
 }
 
+static inline bool is_bsw(void)
+{
+#ifdef CONFIG_X86
+	return ((boot_cpu_data.x86_model == INTEL_FAM6_ATOM_AIRMONT) ? 1 : 0);
+#else
+	return false;
+#endif
+}
+
 void tpm_tis_remove(struct tpm_chip *chip);
 int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
 		      const struct tpm_tis_phy_ops *phy_ops,
diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c
index 1d877cc9af97..674218b50b13 100644
--- a/drivers/char/tpm/tpm_vtpm_proxy.c
+++ b/drivers/char/tpm/tpm_vtpm_proxy.c
@@ -173,10 +173,10 @@ static ssize_t vtpm_proxy_fops_write(struct file *filp, const char __user *buf,
  *
  * Return: Poll flags
  */
-static unsigned int vtpm_proxy_fops_poll(struct file *filp, poll_table *wait)
+static __poll_t vtpm_proxy_fops_poll(struct file *filp, poll_table *wait)
 {
 	struct proxy_dev *proxy_dev = filp->private_data;
-	unsigned ret;
+	__poll_t ret;
 
 	poll_wait(filp, &proxy_dev->wq, wait);
 
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
index 656e8af95d52..911475d36800 100644
--- a/drivers/char/tpm/xen-tpmfront.c
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -10,6 +10,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
+#include <linux/freezer.h>
 #include <xen/xen.h>
 #include <xen/events.h>
 #include <xen/interface/io/tpmif.h>
@@ -39,6 +40,66 @@ enum status_bits {
 	VTPM_STATUS_CANCELED = 0x8,
 };
 
+static bool wait_for_tpm_stat_cond(struct tpm_chip *chip, u8 mask,
+					bool check_cancel, bool *canceled)
+{
+	u8 status = chip->ops->status(chip);
+
+	*canceled = false;
+	if ((status & mask) == mask)
+		return true;
+	if (check_cancel && chip->ops->req_canceled(chip, status)) {
+		*canceled = true;
+		return true;
+	}
+	return false;
+}
+
+static int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask,
+		unsigned long timeout, wait_queue_head_t *queue,
+		bool check_cancel)
+{
+	unsigned long stop;
+	long rc;
+	u8 status;
+	bool canceled = false;
+
+	/* check current status */
+	status = chip->ops->status(chip);
+	if ((status & mask) == mask)
+		return 0;
+
+	stop = jiffies + timeout;
+
+	if (chip->flags & TPM_CHIP_FLAG_IRQ) {
+again:
+		timeout = stop - jiffies;
+		if ((long)timeout <= 0)
+			return -ETIME;
+		rc = wait_event_interruptible_timeout(*queue,
+			wait_for_tpm_stat_cond(chip, mask, check_cancel,
+					       &canceled),
+			timeout);
+		if (rc > 0) {
+			if (canceled)
+				return -ECANCELED;
+			return 0;
+		}
+		if (rc == -ERESTARTSYS && freezing(current)) {
+			clear_thread_flag(TIF_SIGPENDING);
+			goto again;
+		}
+	} else {
+		do {
+			tpm_msleep(TPM_TIMEOUT);
+			status = chip->ops->status(chip);
+			if ((status & mask) == mask)
+				return 0;
+		} while (time_before(jiffies, stop));
+	}
+	return -ETIME;
+}
+
 static u8 vtpm_status(struct tpm_chip *chip)
 {
 	struct tpm_private *priv = dev_get_drvdata(&chip->dev);
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index d1aed2513bd9..813a2e46824d 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -982,10 +982,10 @@ error_out:
 	return ret;
 }
 
-static unsigned int port_fops_poll(struct file *filp, poll_table *wait)
+static __poll_t port_fops_poll(struct file *filp, poll_table *wait)
 {
 	struct port *port;
-	unsigned int ret;
+	__poll_t ret;
 
 	port = filp->private_data;
 	poll_wait(filp, &port->waitqueue, wait);
diff --git a/drivers/char/xillybus/Kconfig b/drivers/char/xillybus/Kconfig
index b302684d86c1..a1f16df08d32 100644
--- a/drivers/char/xillybus/Kconfig
+++ b/drivers/char/xillybus/Kconfig
@@ -4,7 +4,7 @@
 
 config XILLYBUS
 	tristate "Xillybus generic FPGA interface"
-	depends on PCI || (OF_ADDRESS && OF_IRQ)
+	depends on PCI || OF
 	select CRC32
 	help
 	  Xillybus is a generic interface for peripherals designed on
@@ -24,7 +24,7 @@ config XILLYBUS_PCIE
 
 config XILLYBUS_OF
 	tristate "Xillybus over Device Tree"
-	depends on OF_ADDRESS && OF_IRQ && HAS_DMA
+	depends on OF && HAS_DMA
 	help
 	  Set to M if you want Xillybus to find its resources from the
 	  Open Firmware Flattened Device Tree. If the target is an embedded
diff --git a/drivers/char/xillybus/xillybus_core.c b/drivers/char/xillybus/xillybus_core.c
index b6c9cdead7f3..88e1cf475d3f 100644
--- a/drivers/char/xillybus/xillybus_core.c
+++ b/drivers/char/xillybus/xillybus_core.c
@@ -1736,10 +1736,10 @@ end:
 	return pos;
 }
 
-static unsigned int xillybus_poll(struct file *filp, poll_table *wait)
+static __poll_t xillybus_poll(struct file *filp, poll_table *wait)
 {
 	struct xilly_channel *channel = filp->private_data;
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 	unsigned long flags;
 
 	poll_wait(filp, &channel->endpoint->ep_wait, wait);
diff --git a/drivers/char/xillybus/xillybus_of.c b/drivers/char/xillybus/xillybus_of.c
index 78a492f5acfb..4d6625ccb48f 100644
--- a/drivers/char/xillybus/xillybus_of.c
+++ b/drivers/char/xillybus/xillybus_of.c
@@ -15,10 +15,6 @@
 #include <linux/slab.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
-#include <linux/of_irq.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
-#include <linux/of_platform.h>
 #include <linux/err.h>
 #include "xillybus.h"
 
@@ -123,7 +119,7 @@ static int xilly_drv_probe(struct platform_device *op)
 	struct xilly_endpoint *endpoint;
 	int rc;
 	int irq;
-	struct resource res;
+	struct resource *res;
 	struct xilly_endpoint_hardware *ephw = &of_hw;
 
 	if (of_property_read_bool(dev->of_node, "dma-coherent"))
@@ -136,13 +132,13 @@ static int xilly_drv_probe(struct platform_device *op)
 
 	dev_set_drvdata(dev, endpoint);
 
-	rc = of_address_to_resource(dev->of_node, 0, &res);
-	endpoint->registers = devm_ioremap_resource(dev, &res);
+	res = platform_get_resource(op, IORESOURCE_MEM, 0);
+	endpoint->registers = devm_ioremap_resource(dev, res);
 
 	if (IS_ERR(endpoint->registers))
 		return PTR_ERR(endpoint->registers);
 
-	irq = irq_of_parse_and_map(dev->of_node, 0);
+	irq = platform_get_irq(op, 0);
 
 	rc = devm_request_irq(dev, irq, xillybus_isr, 0, xillyname, endpoint);
 
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 1c4e1aa6767e..98ce9fc6e6c0 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -142,6 +142,18 @@ config COMMON_CLK_GEMINI
 	  This driver supports the SoC clocks on the Cortina Systems Gemini
 	  platform, also known as SL3516 or CS3516.
 
+config COMMON_CLK_ASPEED
+	bool "Clock driver for Aspeed BMC SoCs"
+	depends on ARCH_ASPEED || COMPILE_TEST
+	default ARCH_ASPEED
+	select MFD_SYSCON
+	select RESET_CONTROLLER
+	---help---
+	  This driver supports the SoC clocks on the Aspeed BMC platforms.
+
+	  The G4 and G5 series, including the ast2400 and ast2500, are supported
+	  by this driver.
+
 config COMMON_CLK_S2MPS11
 	tristate "Clock driver for S2MPS1X/S5M8767 MFD"
 	depends on MFD_SEC_CORE || COMPILE_TEST
@@ -236,6 +248,7 @@ source "drivers/clk/mvebu/Kconfig"
 source "drivers/clk/qcom/Kconfig"
 source "drivers/clk/renesas/Kconfig"
 source "drivers/clk/samsung/Kconfig"
+source "drivers/clk/sprd/Kconfig"
 source "drivers/clk/sunxi-ng/Kconfig"
 source "drivers/clk/tegra/Kconfig"
 source "drivers/clk/ti/Kconfig"
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index f7f761b02bed..71ec41e6364f 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_ARCH_CLPS711X)		+= clk-clps711x.o
 obj-$(CONFIG_COMMON_CLK_CS2000_CP)	+= clk-cs2000-cp.o
 obj-$(CONFIG_ARCH_EFM32)		+= clk-efm32gg.o
 obj-$(CONFIG_COMMON_CLK_GEMINI)		+= clk-gemini.o
+obj-$(CONFIG_COMMON_CLK_ASPEED)		+= clk-aspeed.o
 obj-$(CONFIG_ARCH_HIGHBANK)		+= clk-highbank.o
 obj-$(CONFIG_CLK_HSDK)			+= clk-hsdk-pll.o
 obj-$(CONFIG_COMMON_CLK_MAX77686)	+= clk-max77686.o
@@ -67,7 +68,7 @@ obj-$(CONFIG_ARCH_MXC)			+= imx/
 obj-$(CONFIG_MACH_INGENIC)		+= ingenic/
 obj-$(CONFIG_ARCH_KEYSTONE)		+= keystone/
 obj-$(CONFIG_MACH_LOONGSON32)		+= loongson1/
-obj-$(CONFIG_ARCH_MEDIATEK)		+= mediatek/
+obj-y					+= mediatek/
 obj-$(CONFIG_COMMON_CLK_AMLOGIC)	+= meson/
 obj-$(CONFIG_MACH_PIC32)		+= microchip/
 ifeq ($(CONFIG_COMMON_CLK), y)
@@ -85,6 +86,7 @@ obj-$(CONFIG_COMMON_CLK_SAMSUNG)	+= samsung/
 obj-$(CONFIG_ARCH_SIRF)			+= sirf/
 obj-$(CONFIG_ARCH_SOCFPGA)		+= socfpga/
 obj-$(CONFIG_PLAT_SPEAR)		+= spear/
+obj-$(CONFIG_ARCH_SPRD)			+= sprd/
 obj-$(CONFIG_ARCH_STI)			+= st/
 obj-$(CONFIG_ARCH_SUNXI)		+= sunxi/
 obj-$(CONFIG_ARCH_SUNXI)		+= sunxi-ng/
diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
index 85a449cf61e3..0e6aab1252fc 100644
--- a/drivers/clk/at91/clk-programmable.c
+++ b/drivers/clk/at91/clk-programmable.c
@@ -204,6 +204,8 @@ at91_clk_register_programmable(struct regmap *regmap,
 	if (ret) {
 		kfree(prog);
 		hw = ERR_PTR(ret);
+	} else {
+		pmc_register_pck(id);
 	}
 
 	return hw;
diff --git a/drivers/clk/at91/pmc.c b/drivers/clk/at91/pmc.c
index 775af473fe11..1fa27f4ea538 100644
--- a/drivers/clk/at91/pmc.c
+++ b/drivers/clk/at91/pmc.c
@@ -22,6 +22,7 @@
 #include "pmc.h"
 
 #define PMC_MAX_IDS 128
+#define PMC_MAX_PCKS 8
 
 int of_at91_get_clk_range(struct device_node *np, const char *propname,
 			  struct clk_range *range)
@@ -50,6 +51,7 @@ EXPORT_SYMBOL_GPL(of_at91_get_clk_range);
 static struct regmap *pmcreg;
 
 static u8 registered_ids[PMC_MAX_IDS];
+static u8 registered_pcks[PMC_MAX_PCKS];
 
 static struct
 {
@@ -66,8 +68,13 @@ static struct
 	u32 pcr[PMC_MAX_IDS];
 	u32 audio_pll0;
 	u32 audio_pll1;
+	u32 pckr[PMC_MAX_PCKS];
 } pmc_cache;
 
+/*
+ * As Peripheral ID 0 is invalid on AT91 chips, the identifier is stored
+ * without alteration in the table, and 0 is for unused clocks.
+ */
 void pmc_register_id(u8 id)
 {
 	int i;
@@ -82,11 +89,30 @@ void pmc_register_id(u8 id)
 	}
 }
 
+/*
+ * As Programmable Clock 0 is valid on AT91 chips, there is an offset
+ * of 1 between the stored value and the real clock ID.
+ */
+void pmc_register_pck(u8 pck)
+{
+	int i;
+
+	for (i = 0; i < PMC_MAX_PCKS; i++) {
+		if (registered_pcks[i] == 0) {
+			registered_pcks[i] = pck + 1;
+			break;
+		}
+		if (registered_pcks[i] == (pck + 1))
+			break;
+	}
+}
+
 static int pmc_suspend(void)
 {
 	int i;
+	u8 num;
 
-	regmap_read(pmcreg, AT91_PMC_IMR, &pmc_cache.scsr);
+	regmap_read(pmcreg, AT91_PMC_SCSR, &pmc_cache.scsr);
 	regmap_read(pmcreg, AT91_PMC_PCSR, &pmc_cache.pcsr0);
 	regmap_read(pmcreg, AT91_CKGR_UCKR, &pmc_cache.uckr);
 	regmap_read(pmcreg, AT91_CKGR_MOR, &pmc_cache.mor);
@@ -103,14 +129,29 @@ static int pmc_suspend(void)
 		regmap_read(pmcreg, AT91_PMC_PCR,
 			    &pmc_cache.pcr[registered_ids[i]]);
 	}
+	for (i = 0; registered_pcks[i]; i++) {
+		num = registered_pcks[i] - 1;
+		regmap_read(pmcreg, AT91_PMC_PCKR(num), &pmc_cache.pckr[num]);
+	}
 
 	return 0;
 }
 
+static bool pmc_ready(unsigned int mask)
+{
+	unsigned int status;
+
+	regmap_read(pmcreg, AT91_PMC_SR, &status);
+
+	return ((status & mask) == mask) ? 1 : 0;
+}
+
 static void pmc_resume(void)
 {
-	int i, ret = 0;
+	int i;
+	u8 num;
 	u32 tmp;
+	u32 mask = AT91_PMC_MCKRDY | AT91_PMC_LOCKA;
 
 	regmap_read(pmcreg, AT91_PMC_MCKR, &tmp);
 	if (pmc_cache.mckr != tmp)
@@ -119,7 +160,7 @@ static void pmc_resume(void)
 	if (pmc_cache.pllar != tmp)
 		pr_warn("PLLAR was not configured properly by the firmware\n");
 
-	regmap_write(pmcreg, AT91_PMC_IMR, pmc_cache.scsr);
+	regmap_write(pmcreg, AT91_PMC_SCER, pmc_cache.scsr);
 	regmap_write(pmcreg, AT91_PMC_PCER, pmc_cache.pcsr0);
 	regmap_write(pmcreg, AT91_CKGR_UCKR, pmc_cache.uckr);
 	regmap_write(pmcreg, AT91_CKGR_MOR, pmc_cache.mor);
@@ -133,14 +174,16 @@ static void pmc_resume(void)
 			     pmc_cache.pcr[registered_ids[i]] |
 			     AT91_PMC_PCR_CMD);
 	}
-
-	if (pmc_cache.uckr & AT91_PMC_UPLLEN) {
-		ret = regmap_read_poll_timeout(pmcreg, AT91_PMC_SR, tmp,
-					       !(tmp & AT91_PMC_LOCKU),
-					       10, 5000);
-		if (ret)
-			pr_crit("USB PLL didn't lock when resuming\n");
+	for (i = 0; registered_pcks[i]; i++) {
+		num = registered_pcks[i] - 1;
+		regmap_write(pmcreg, AT91_PMC_PCKR(num), pmc_cache.pckr[num]);
 	}
+
+	if (pmc_cache.uckr & AT91_PMC_UPLLEN)
+		mask |= AT91_PMC_LOCKU;
+
+	while (!pmc_ready(mask))
+		cpu_relax();
 }
 
 static struct syscore_ops pmc_syscore_ops = {
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 858e8ef7e8db..d22b1fa9ecdc 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -31,8 +31,10 @@ int of_at91_get_clk_range(struct device_node *np, const char *propname,
 
 #ifdef CONFIG_PM
 void pmc_register_id(u8 id);
+void pmc_register_pck(u8 pck);
 #else
 static inline void pmc_register_id(u8 id) {}
+static inline void pmc_register_pck(u8 pck) {}
 #endif
 
 #endif /* __PMC_H_ */
diff --git a/drivers/clk/bcm/clk-cygnus.c b/drivers/clk/bcm/clk-cygnus.c
index 464fdc4bc66b..b8d073e4855f 100644
--- a/drivers/clk/bcm/clk-cygnus.c
+++ b/drivers/clk/bcm/clk-cygnus.c
@@ -269,23 +269,10 @@ static void __init cygnus_asiu_init(struct device_node *node)
 }
 CLK_OF_DECLARE(cygnus_asiu_clk, "brcm,cygnus-asiu-clk", cygnus_asiu_init);
 
-/*
- * AUDIO PLL VCO frequency parameter table
- *
- * PLL output frequency = ((ndiv_int + ndiv_frac / 2^20) *
- * (parent clock rate / pdiv)
- *
- * On Cygnus, parent is the 25MHz oscillator
- */
-static const struct iproc_pll_vco_param audiopll_vco_params[] = {
-	/* rate (Hz) ndiv_int ndiv_frac pdiv */
-	{ 1354750204UL,  54,     199238,   1 },
-	{ 1769470191UL,  70,     816639,   1 },
-};
-
 static const struct iproc_pll_ctrl audiopll = {
 	.flags = IPROC_CLK_PLL_NEEDS_SW_CFG | IPROC_CLK_PLL_HAS_NDIV_FRAC |
-		IPROC_CLK_PLL_USER_MODE_ON | IPROC_CLK_PLL_RESET_ACTIVE_LOW,
+		IPROC_CLK_PLL_USER_MODE_ON | IPROC_CLK_PLL_RESET_ACTIVE_LOW |
+		IPROC_CLK_PLL_CALC_PARAM,
 	.reset = RESET_VAL(0x5c, 0, 1),
 	.dig_filter = DF_VAL(0x48, 0, 3, 6, 4, 3, 3),
 	.sw_ctrl = SW_CTRL_VAL(0x4, 0),
@@ -300,8 +287,7 @@ static const struct iproc_pll_ctrl audiopll = {
 static const struct iproc_clk_ctrl audiopll_clk[] = {
 	[BCM_CYGNUS_AUDIOPLL_CH0] = {
 		.channel = BCM_CYGNUS_AUDIOPLL_CH0,
-		.flags = IPROC_CLK_AON |
-				IPROC_CLK_MCLK_DIV_BY_2,
+		.flags = IPROC_CLK_AON | IPROC_CLK_MCLK_DIV_BY_2,
 		.enable = ENABLE_VAL(0x14, 8, 10, 9),
 		.mdiv = REG_VAL(0x14, 0, 8),
 	},
@@ -321,9 +307,8 @@ static const struct iproc_clk_ctrl audiopll_clk[] = {
 
 static void __init cygnus_audiopll_clk_init(struct device_node *node)
 {
-	iproc_pll_clk_setup(node, &audiopll, audiopll_vco_params,
-			    ARRAY_SIZE(audiopll_vco_params), audiopll_clk,
-			    ARRAY_SIZE(audiopll_clk));
+	iproc_pll_clk_setup(node, &audiopll, NULL, 0,
+			    audiopll_clk,  ARRAY_SIZE(audiopll_clk));
 }
 CLK_OF_DECLARE(cygnus_audiopll, "brcm,cygnus-audiopll",
 			cygnus_audiopll_clk_init);
diff --git a/drivers/clk/bcm/clk-iproc-pll.c b/drivers/clk/bcm/clk-iproc-pll.c
index 375d8dd80d45..43a58ae5a89d 100644
--- a/drivers/clk/bcm/clk-iproc-pll.c
+++ b/drivers/clk/bcm/clk-iproc-pll.c
@@ -69,16 +69,6 @@ enum vco_freq_range {
 	VCO_MAX       = 4000000000U,
 };
 
-struct iproc_pll;
-
-struct iproc_clk {
-	struct clk_hw hw;
-	const char *name;
-	struct iproc_pll *pll;
-	unsigned long rate;
-	const struct iproc_clk_ctrl *ctrl;
-};
-
 struct iproc_pll {
 	void __iomem *status_base;
 	void __iomem *control_base;
@@ -88,13 +78,49 @@ struct iproc_pll {
 	const struct iproc_pll_ctrl *ctrl;
 	const struct iproc_pll_vco_param *vco_param;
 	unsigned int num_vco_entries;
+};
 
-	struct clk_hw_onecell_data *clk_data;
-	struct iproc_clk *clks;
+struct iproc_clk {
+	struct clk_hw hw;
+	struct iproc_pll *pll;
+	const struct iproc_clk_ctrl *ctrl;
 };
 
 #define to_iproc_clk(hw) container_of(hw, struct iproc_clk, hw)
 
+static int pll_calc_param(unsigned long target_rate,
+			unsigned long parent_rate,
+			struct iproc_pll_vco_param *vco_out)
+{
+	u64 ndiv_int, ndiv_frac, residual;
+
+	ndiv_int = target_rate / parent_rate;
+
+	if (!ndiv_int || (ndiv_int > 255))
+		return -EINVAL;
+
+	residual = target_rate - (ndiv_int * parent_rate);
+	residual <<= 20;
+
+	/*
+	 * Add half of the divisor so the result will be rounded to closest
+	 * instead of rounded down.
+	 */
+	residual += (parent_rate / 2);
+	ndiv_frac = div64_u64((u64)residual, (u64)parent_rate);
+
+	vco_out->ndiv_int = ndiv_int;
+	vco_out->ndiv_frac = ndiv_frac;
+	vco_out->pdiv = 1;
+
+	vco_out->rate = vco_out->ndiv_int * parent_rate;
+	residual = (u64)vco_out->ndiv_frac * (u64)parent_rate;
+	residual >>= 20;
+	vco_out->rate += residual;
+
+	return 0;
+}
+
 /*
  * Based on the target frequency, find a match from the VCO frequency parameter
  * table and return its index
@@ -252,17 +278,51 @@ static void __pll_bring_out_reset(struct iproc_pll *pll, unsigned int kp,
 	iproc_pll_write(pll, pll->control_base, reset->offset, val);
 }
 
-static int pll_set_rate(struct iproc_clk *clk, unsigned int rate_index,
+/*
+ * Determines if the change to be applied to the PLL is minor (just an update
+ * or the fractional divider). If so, then we can avoid going through a
+ * disruptive reset and lock sequence.
+ */
+static bool pll_fractional_change_only(struct iproc_pll *pll,
+				       struct iproc_pll_vco_param *vco)
+{
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+	u32 val;
+	u32 ndiv_int;
+	unsigned int pdiv;
+
+	/* PLL needs to be locked */
+	val = readl(pll->status_base + ctrl->status.offset);
+	if ((val & (1 << ctrl->status.shift)) == 0)
+		return false;
+
+	val = readl(pll->control_base + ctrl->ndiv_int.offset);
+	ndiv_int = (val >> ctrl->ndiv_int.shift) &
+		bit_mask(ctrl->ndiv_int.width);
+
+	if (ndiv_int != vco->ndiv_int)
+		return false;
+
+	val = readl(pll->control_base + ctrl->pdiv.offset);
+	pdiv = (val >> ctrl->pdiv.shift) & bit_mask(ctrl->pdiv.width);
+
+	if (pdiv != vco->pdiv)
+		return false;
+
+	return true;
+}
+
+static int pll_set_rate(struct iproc_clk *clk, struct iproc_pll_vco_param *vco,
 			unsigned long parent_rate)
 {
 	struct iproc_pll *pll = clk->pll;
-	const struct iproc_pll_vco_param *vco = &pll->vco_param[rate_index];
 	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
 	int ka = 0, ki, kp, ret;
 	unsigned long rate = vco->rate;
 	u32 val;
 	enum kp_band kp_index;
 	unsigned long ref_freq;
+	const char *clk_name = clk_hw_get_name(&clk->hw);
 
 	/*
 	 * reference frequency = parent frequency / PDIV
@@ -285,22 +345,35 @@ static int pll_set_rate(struct iproc_clk *clk, unsigned int rate_index,
 		kp_index = KP_BAND_HIGH_HIGH;
 	} else {
 		pr_err("%s: pll: %s has invalid rate: %lu\n", __func__,
-				clk->name, rate);
+				clk_name, rate);
 		return -EINVAL;
 	}
 
 	kp = get_kp(ref_freq, kp_index);
 	if (kp < 0) {
-		pr_err("%s: pll: %s has invalid kp\n", __func__, clk->name);
+		pr_err("%s: pll: %s has invalid kp\n", __func__, clk_name);
 		return kp;
 	}
 
 	ret = __pll_enable(pll);
 	if (ret) {
-		pr_err("%s: pll: %s fails to enable\n", __func__, clk->name);
+		pr_err("%s: pll: %s fails to enable\n", __func__, clk_name);
 		return ret;
 	}
 
+	if (pll_fractional_change_only(clk->pll, vco)) {
+		/* program fractional part of NDIV */
+		if (ctrl->flags & IPROC_CLK_PLL_HAS_NDIV_FRAC) {
+			val = readl(pll->control_base + ctrl->ndiv_frac.offset);
+			val &= ~(bit_mask(ctrl->ndiv_frac.width) <<
+				 ctrl->ndiv_frac.shift);
+			val |= vco->ndiv_frac << ctrl->ndiv_frac.shift;
+			iproc_pll_write(pll, pll->control_base,
+					ctrl->ndiv_frac.offset, val);
+			return 0;
+		}
+	}
+
 	/* put PLL in reset */
 	__pll_put_in_reset(pll);
 
@@ -354,7 +427,7 @@ static int pll_set_rate(struct iproc_clk *clk, unsigned int rate_index,
 
 	ret = pll_wait_for_lock(pll);
 	if (ret < 0) {
-		pr_err("%s: pll: %s failed to lock\n", __func__, clk->name);
+		pr_err("%s: pll: %s failed to lock\n", __func__, clk_name);
 		return ret;
 	}
 
@@ -390,16 +463,15 @@ static unsigned long iproc_pll_recalc_rate(struct clk_hw *hw,
 	u32 val;
 	u64 ndiv, ndiv_int, ndiv_frac;
 	unsigned int pdiv;
+	unsigned long rate;
 
 	if (parent_rate == 0)
 		return 0;
 
 	/* PLL needs to be locked */
 	val = readl(pll->status_base + ctrl->status.offset);
-	if ((val & (1 << ctrl->status.shift)) == 0) {
-		clk->rate = 0;
+	if ((val & (1 << ctrl->status.shift)) == 0)
 		return 0;
-	}
 
 	/*
 	 * PLL output frequency =
@@ -421,35 +493,60 @@ static unsigned long iproc_pll_recalc_rate(struct clk_hw *hw,
 	val = readl(pll->control_base + ctrl->pdiv.offset);
 	pdiv = (val >> ctrl->pdiv.shift) & bit_mask(ctrl->pdiv.width);
 
-	clk->rate = (ndiv * parent_rate) >> 20;
+	rate = (ndiv * parent_rate) >> 20;
 
 	if (pdiv == 0)
-		clk->rate *= 2;
+		rate *= 2;
 	else
-		clk->rate /= pdiv;
+		rate /= pdiv;
 
-	return clk->rate;
+	return rate;
 }
 
-static long iproc_pll_round_rate(struct clk_hw *hw, unsigned long rate,
-				 unsigned long *parent_rate)
+static int iproc_pll_determine_rate(struct clk_hw *hw,
+		struct clk_rate_request *req)
 {
-	unsigned i;
+	unsigned int  i;
 	struct iproc_clk *clk = to_iproc_clk(hw);
 	struct iproc_pll *pll = clk->pll;
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+	unsigned long  diff, best_diff;
+	unsigned int  best_idx = 0;
+	int ret;
+
+	if (req->rate == 0 || req->best_parent_rate == 0)
+		return -EINVAL;
+
+	if (ctrl->flags & IPROC_CLK_PLL_CALC_PARAM) {
+		struct iproc_pll_vco_param vco_param;
 
-	if (rate == 0 || *parent_rate == 0 || !pll->vco_param)
+		ret = pll_calc_param(req->rate, req->best_parent_rate,
+					&vco_param);
+		if (ret)
+			return ret;
+
+		req->rate = vco_param.rate;
+		return 0;
+	}
+
+	if (!pll->vco_param)
 		return -EINVAL;
 
+	best_diff = ULONG_MAX;
 	for (i = 0; i < pll->num_vco_entries; i++) {
-		if (rate <= pll->vco_param[i].rate)
+		diff = abs(req->rate - pll->vco_param[i].rate);
+		if (diff <= best_diff) {
+			best_diff = diff;
+			best_idx = i;
+		}
+		/* break now if perfect match */
+		if (diff == 0)
 			break;
 	}
 
-	if (i == pll->num_vco_entries)
-		i--;
+	req->rate = pll->vco_param[best_idx].rate;
 
-	return pll->vco_param[i].rate;
+	return 0;
 }
 
 static int iproc_pll_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -457,13 +554,23 @@ static int iproc_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 {
 	struct iproc_clk *clk = to_iproc_clk(hw);
 	struct iproc_pll *pll = clk->pll;
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+	struct iproc_pll_vco_param vco_param;
 	int rate_index, ret;
 
-	rate_index = pll_get_rate_index(pll, rate);
-	if (rate_index < 0)
-		return rate_index;
+	if (ctrl->flags & IPROC_CLK_PLL_CALC_PARAM) {
+		ret = pll_calc_param(rate, parent_rate, &vco_param);
+		if (ret)
+			return ret;
+	} else {
+		rate_index = pll_get_rate_index(pll, rate);
+		if (rate_index < 0)
+			return rate_index;
 
-	ret = pll_set_rate(clk, rate_index, parent_rate);
+		vco_param = pll->vco_param[rate_index];
+	}
+
+	ret = pll_set_rate(clk, &vco_param, parent_rate);
 	return ret;
 }
 
@@ -471,7 +578,7 @@ static const struct clk_ops iproc_pll_ops = {
 	.enable = iproc_pll_enable,
 	.disable = iproc_pll_disable,
 	.recalc_rate = iproc_pll_recalc_rate,
-	.round_rate = iproc_pll_round_rate,
+	.determine_rate = iproc_pll_determine_rate,
 	.set_rate = iproc_pll_set_rate,
 };
 
@@ -518,6 +625,7 @@ static unsigned long iproc_clk_recalc_rate(struct clk_hw *hw,
 	struct iproc_pll *pll = clk->pll;
 	u32 val;
 	unsigned int mdiv;
+	unsigned long rate;
 
 	if (parent_rate == 0)
 		return 0;
@@ -528,32 +636,33 @@ static unsigned long iproc_clk_recalc_rate(struct clk_hw *hw,
 		mdiv = 256;
 
 	if (ctrl->flags & IPROC_CLK_MCLK_DIV_BY_2)
-		clk->rate = parent_rate / (mdiv * 2);
+		rate = parent_rate / (mdiv * 2);
 	else
-		clk->rate = parent_rate / mdiv;
+		rate = parent_rate / mdiv;
 
-	return clk->rate;
+	return rate;
 }
 
-static long iproc_clk_round_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long *parent_rate)
+static int iproc_clk_determine_rate(struct clk_hw *hw,
+		struct clk_rate_request *req)
 {
-	unsigned int div;
+	unsigned int bestdiv;
 
-	if (rate == 0 || *parent_rate == 0)
+	if (req->rate == 0)
 		return -EINVAL;
+	if (req->rate == req->best_parent_rate)
+		return 0;
 
-	if (rate == *parent_rate)
-		return *parent_rate;
+	bestdiv = DIV_ROUND_CLOSEST(req->best_parent_rate, req->rate);
+	if (bestdiv < 2)
+		req->rate = req->best_parent_rate;
 
-	div = DIV_ROUND_UP(*parent_rate, rate);
-	if (div < 2)
-		return *parent_rate;
+	if (bestdiv > 256)
+		bestdiv = 256;
 
-	if (div > 256)
-		div = 256;
+	req->rate = req->best_parent_rate / bestdiv;
 
-	return *parent_rate / div;
+	return 0;
 }
 
 static int iproc_clk_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -568,10 +677,10 @@ static int iproc_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (rate == 0 || parent_rate == 0)
 		return -EINVAL;
 
+	div = DIV_ROUND_CLOSEST(parent_rate, rate);
 	if (ctrl->flags & IPROC_CLK_MCLK_DIV_BY_2)
-		div = DIV_ROUND_UP(parent_rate, rate * 2);
-	else
-		div = DIV_ROUND_UP(parent_rate, rate);
+		div /=  2;
+
 	if (div > 256)
 		return -EINVAL;
 
@@ -583,10 +692,6 @@ static int iproc_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 		val |= div << ctrl->mdiv.shift;
 	}
 	iproc_pll_write(pll, pll->control_base, ctrl->mdiv.offset, val);
-	if (ctrl->flags & IPROC_CLK_MCLK_DIV_BY_2)
-		clk->rate = parent_rate / (div * 2);
-	else
-		clk->rate = parent_rate / div;
 
 	return 0;
 }
@@ -595,7 +700,7 @@ static const struct clk_ops iproc_clk_ops = {
 	.enable = iproc_clk_enable,
 	.disable = iproc_clk_disable,
 	.recalc_rate = iproc_clk_recalc_rate,
-	.round_rate = iproc_clk_round_rate,
+	.determine_rate = iproc_clk_determine_rate,
 	.set_rate = iproc_clk_set_rate,
 };
 
@@ -629,6 +734,8 @@ void iproc_pll_clk_setup(struct device_node *node,
 	struct iproc_clk *iclk;
 	struct clk_init_data init;
 	const char *parent_name;
+	struct iproc_clk *iclk_array;
+	struct clk_hw_onecell_data *clk_data;
 
 	if (WARN_ON(!pll_ctrl) || WARN_ON(!clk_ctrl))
 		return;
@@ -637,14 +744,14 @@ void iproc_pll_clk_setup(struct device_node *node,
 	if (WARN_ON(!pll))
 		return;
 
-	pll->clk_data = kzalloc(sizeof(*pll->clk_data->hws) * num_clks +
-				sizeof(*pll->clk_data), GFP_KERNEL);
-	if (WARN_ON(!pll->clk_data))
+	clk_data = kzalloc(sizeof(*clk_data->hws) * num_clks +
+				sizeof(*clk_data), GFP_KERNEL);
+	if (WARN_ON(!clk_data))
 		goto err_clk_data;
-	pll->clk_data->num = num_clks;
+	clk_data->num = num_clks;
 
-	pll->clks = kcalloc(num_clks, sizeof(*pll->clks), GFP_KERNEL);
-	if (WARN_ON(!pll->clks))
+	iclk_array = kcalloc(num_clks, sizeof(struct iproc_clk), GFP_KERNEL);
+	if (WARN_ON(!iclk_array))
 		goto err_clks;
 
 	pll->control_base = of_iomap(node, 0);
@@ -674,9 +781,8 @@ void iproc_pll_clk_setup(struct device_node *node,
 	/* initialize and register the PLL itself */
 	pll->ctrl = pll_ctrl;
 
-	iclk = &pll->clks[0];
+	iclk = &iclk_array[0];
 	iclk->pll = pll;
-	iclk->name = node->name;
 
 	init.name = node->name;
 	init.ops = &iproc_pll_ops;
@@ -697,7 +803,7 @@ void iproc_pll_clk_setup(struct device_node *node,
 	if (WARN_ON(ret))
 		goto err_pll_register;
 
-	pll->clk_data->hws[0] = &iclk->hw;
+	clk_data->hws[0] = &iclk->hw;
 
 	/* now initialize and register all leaf clocks */
 	for (i = 1; i < num_clks; i++) {
@@ -711,8 +817,7 @@ void iproc_pll_clk_setup(struct device_node *node,
 		if (WARN_ON(ret))
 			goto err_clk_register;
 
-		iclk = &pll->clks[i];
-		iclk->name = clk_name;
+		iclk = &iclk_array[i];
 		iclk->pll = pll;
 		iclk->ctrl = &clk_ctrl[i];
 
@@ -727,11 +832,10 @@ void iproc_pll_clk_setup(struct device_node *node,
 		if (WARN_ON(ret))
 			goto err_clk_register;
 
-		pll->clk_data->hws[i] = &iclk->hw;
+		clk_data->hws[i] = &iclk->hw;
 	}
 
-	ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get,
-				     pll->clk_data);
+	ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data);
 	if (WARN_ON(ret))
 		goto err_clk_register;
 
@@ -739,7 +843,7 @@ void iproc_pll_clk_setup(struct device_node *node,
 
 err_clk_register:
 	while (--i >= 0)
-		clk_hw_unregister(pll->clk_data->hws[i]);
+		clk_hw_unregister(clk_data->hws[i]);
 
 err_pll_register:
 	if (pll->status_base != pll->control_base)
@@ -756,10 +860,10 @@ err_asiu_iomap:
 	iounmap(pll->control_base);
 
 err_pll_iomap:
-	kfree(pll->clks);
+	kfree(iclk_array);
 
 err_clks:
-	kfree(pll->clk_data);
+	kfree(clk_data);
 
 err_clk_data:
 	kfree(pll);
diff --git a/drivers/clk/bcm/clk-iproc.h b/drivers/clk/bcm/clk-iproc.h
index 2148b4ea9f28..a48ddd3e0b28 100644
--- a/drivers/clk/bcm/clk-iproc.h
+++ b/drivers/clk/bcm/clk-iproc.h
@@ -81,6 +81,11 @@
 #define IPROC_CLK_PLL_RESET_ACTIVE_LOW BIT(9)
 
 /*
+ * Calculate the PLL parameters are runtime, instead of using table
+ */
+#define IPROC_CLK_PLL_CALC_PARAM BIT(10)
+
+/*
  * Parameters for VCO frequency configuration
  *
  * VCO frequency =
diff --git a/drivers/clk/clk-aspeed.c b/drivers/clk/clk-aspeed.c
new file mode 100644
index 000000000000..9f7f931d6b2f
--- /dev/null
+++ b/drivers/clk/clk-aspeed.c
@@ -0,0 +1,667 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#define pr_fmt(fmt) "clk-aspeed: " fmt
+
+#include <linux/clk-provider.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset-controller.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <dt-bindings/clock/aspeed-clock.h>
+
+#define ASPEED_NUM_CLKS		35
+
+#define ASPEED_RESET_CTRL	0x04
+#define ASPEED_CLK_SELECTION	0x08
+#define ASPEED_CLK_STOP_CTRL	0x0c
+#define ASPEED_MPLL_PARAM	0x20
+#define ASPEED_HPLL_PARAM	0x24
+#define  AST2500_HPLL_BYPASS_EN	BIT(20)
+#define  AST2400_HPLL_STRAPPED	BIT(18)
+#define  AST2400_HPLL_BYPASS_EN	BIT(17)
+#define ASPEED_MISC_CTRL	0x2c
+#define  UART_DIV13_EN		BIT(12)
+#define ASPEED_STRAP		0x70
+#define  CLKIN_25MHZ_EN		BIT(23)
+#define  AST2400_CLK_SOURCE_SEL	BIT(18)
+#define ASPEED_CLK_SELECTION_2	0xd8
+
+/* Globally visible clocks */
+static DEFINE_SPINLOCK(aspeed_clk_lock);
+
+/* Keeps track of all clocks */
+static struct clk_hw_onecell_data *aspeed_clk_data;
+
+static void __iomem *scu_base;
+
+/**
+ * struct aspeed_gate_data - Aspeed gated clocks
+ * @clock_idx: bit used to gate this clock in the clock register
+ * @reset_idx: bit used to reset this IP in the reset register. -1 if no
+ *             reset is required when enabling the clock
+ * @name: the clock name
+ * @parent_name: the name of the parent clock
+ * @flags: standard clock framework flags
+ */
+struct aspeed_gate_data {
+	u8		clock_idx;
+	s8		reset_idx;
+	const char	*name;
+	const char	*parent_name;
+	unsigned long	flags;
+};
+
+/**
+ * struct aspeed_clk_gate - Aspeed specific clk_gate structure
+ * @hw:		handle between common and hardware-specific interfaces
+ * @reg:	register controlling gate
+ * @clock_idx:	bit used to gate this clock in the clock register
+ * @reset_idx:	bit used to reset this IP in the reset register. -1 if no
+ *		reset is required when enabling the clock
+ * @flags:	hardware-specific flags
+ * @lock:	register lock
+ *
+ * Some of the clocks in the Aspeed SoC must be put in reset before enabling.
+ * This modified version of clk_gate allows an optional reset bit to be
+ * specified.
+ */
+struct aspeed_clk_gate {
+	struct clk_hw	hw;
+	struct regmap	*map;
+	u8		clock_idx;
+	s8		reset_idx;
+	u8		flags;
+	spinlock_t	*lock;
+};
+
+#define to_aspeed_clk_gate(_hw) container_of(_hw, struct aspeed_clk_gate, hw)
+
+/* TODO: ask Aspeed about the actual parent data */
+static const struct aspeed_gate_data aspeed_gates[] = {
+	/*				 clk rst   name			parent	flags */
+	[ASPEED_CLK_GATE_ECLK] =	{  0, -1, "eclk-gate",		"eclk",	0 }, /* Video Engine */
+	[ASPEED_CLK_GATE_GCLK] =	{  1,  7, "gclk-gate",		NULL,	0 }, /* 2D engine */
+	[ASPEED_CLK_GATE_MCLK] =	{  2, -1, "mclk-gate",		"mpll",	CLK_IS_CRITICAL }, /* SDRAM */
+	[ASPEED_CLK_GATE_VCLK] =	{  3,  6, "vclk-gate",		NULL,	0 }, /* Video Capture */
+	[ASPEED_CLK_GATE_BCLK] =	{  4, 10, "bclk-gate",		"bclk",	0 }, /* PCIe/PCI */
+	[ASPEED_CLK_GATE_DCLK] =	{  5, -1, "dclk-gate",		NULL,	0 }, /* DAC */
+	[ASPEED_CLK_GATE_REFCLK] =	{  6, -1, "refclk-gate",	"clkin", CLK_IS_CRITICAL },
+	[ASPEED_CLK_GATE_USBPORT2CLK] =	{  7,  3, "usb-port2-gate",	NULL,	0 }, /* USB2.0 Host port 2 */
+	[ASPEED_CLK_GATE_LCLK] =	{  8,  5, "lclk-gate",		NULL,	0 }, /* LPC */
+	[ASPEED_CLK_GATE_USBUHCICLK] =	{  9, 15, "usb-uhci-gate",	NULL,	0 }, /* USB1.1 (requires port 2 enabled) */
+	[ASPEED_CLK_GATE_D1CLK] =	{ 10, 13, "d1clk-gate",		NULL,	0 }, /* GFX CRT */
+	[ASPEED_CLK_GATE_YCLK] =	{ 13,  4, "yclk-gate",		NULL,	0 }, /* HAC */
+	[ASPEED_CLK_GATE_USBPORT1CLK] = { 14, 14, "usb-port1-gate",	NULL,	0 }, /* USB2 hub/USB2 host port 1/USB1.1 dev */
+	[ASPEED_CLK_GATE_UART1CLK] =	{ 15, -1, "uart1clk-gate",	"uart",	0 }, /* UART1 */
+	[ASPEED_CLK_GATE_UART2CLK] =	{ 16, -1, "uart2clk-gate",	"uart",	0 }, /* UART2 */
+	[ASPEED_CLK_GATE_UART5CLK] =	{ 17, -1, "uart5clk-gate",	"uart",	0 }, /* UART5 */
+	[ASPEED_CLK_GATE_ESPICLK] =	{ 19, -1, "espiclk-gate",	NULL,	0 }, /* eSPI */
+	[ASPEED_CLK_GATE_MAC1CLK] =	{ 20, 11, "mac1clk-gate",	"mac",	0 }, /* MAC1 */
+	[ASPEED_CLK_GATE_MAC2CLK] =	{ 21, 12, "mac2clk-gate",	"mac",	0 }, /* MAC2 */
+	[ASPEED_CLK_GATE_RSACLK] =	{ 24, -1, "rsaclk-gate",	NULL,	0 }, /* RSA */
+	[ASPEED_CLK_GATE_UART3CLK] =	{ 25, -1, "uart3clk-gate",	"uart",	0 }, /* UART3 */
+	[ASPEED_CLK_GATE_UART4CLK] =	{ 26, -1, "uart4clk-gate",	"uart",	0 }, /* UART4 */
+	[ASPEED_CLK_GATE_SDCLKCLK] =	{ 27, 16, "sdclk-gate",		NULL,	0 }, /* SDIO/SD */
+	[ASPEED_CLK_GATE_LHCCLK] =	{ 28, -1, "lhclk-gate",		"lhclk", 0 }, /* LPC master/LPC+ */
+};
+
+static const struct clk_div_table ast2500_mac_div_table[] = {
+	{ 0x0, 4 }, /* Yep, really. Aspeed confirmed this is correct */
+	{ 0x1, 4 },
+	{ 0x2, 6 },
+	{ 0x3, 8 },
+	{ 0x4, 10 },
+	{ 0x5, 12 },
+	{ 0x6, 14 },
+	{ 0x7, 16 },
+	{ 0 }
+};
+
+static const struct clk_div_table ast2400_div_table[] = {
+	{ 0x0, 2 },
+	{ 0x1, 4 },
+	{ 0x2, 6 },
+	{ 0x3, 8 },
+	{ 0x4, 10 },
+	{ 0x5, 12 },
+	{ 0x6, 14 },
+	{ 0x7, 16 },
+	{ 0 }
+};
+
+static const struct clk_div_table ast2500_div_table[] = {
+	{ 0x0, 4 },
+	{ 0x1, 8 },
+	{ 0x2, 12 },
+	{ 0x3, 16 },
+	{ 0x4, 20 },
+	{ 0x5, 24 },
+	{ 0x6, 28 },
+	{ 0x7, 32 },
+	{ 0 }
+};
+
+static struct clk_hw *aspeed_ast2400_calc_pll(const char *name, u32 val)
+{
+	unsigned int mult, div;
+
+	if (val & AST2400_HPLL_BYPASS_EN) {
+		/* Pass through mode */
+		mult = div = 1;
+	} else {
+		/* F = 24Mhz * (2-OD) * [(N + 2) / (D + 1)] */
+		u32 n = (val >> 5) & 0x3f;
+		u32 od = (val >> 4) & 0x1;
+		u32 d = val & 0xf;
+
+		mult = (2 - od) * (n + 2);
+		div = d + 1;
+	}
+	return clk_hw_register_fixed_factor(NULL, name, "clkin", 0,
+			mult, div);
+};
+
+static struct clk_hw *aspeed_ast2500_calc_pll(const char *name, u32 val)
+{
+	unsigned int mult, div;
+
+	if (val & AST2500_HPLL_BYPASS_EN) {
+		/* Pass through mode */
+		mult = div = 1;
+	} else {
+		/* F = clkin * [(M+1) / (N+1)] / (P + 1) */
+		u32 p = (val >> 13) & 0x3f;
+		u32 m = (val >> 5) & 0xff;
+		u32 n = val & 0x1f;
+
+		mult = (m + 1) / (n + 1);
+		div = p + 1;
+	}
+
+	return clk_hw_register_fixed_factor(NULL, name, "clkin", 0,
+			mult, div);
+}
+
+struct aspeed_clk_soc_data {
+	const struct clk_div_table *div_table;
+	const struct clk_div_table *mac_div_table;
+	struct clk_hw *(*calc_pll)(const char *name, u32 val);
+};
+
+static const struct aspeed_clk_soc_data ast2500_data = {
+	.div_table = ast2500_div_table,
+	.mac_div_table = ast2500_mac_div_table,
+	.calc_pll = aspeed_ast2500_calc_pll,
+};
+
+static const struct aspeed_clk_soc_data ast2400_data = {
+	.div_table = ast2400_div_table,
+	.mac_div_table = ast2400_div_table,
+	.calc_pll = aspeed_ast2400_calc_pll,
+};
+
+static int aspeed_clk_enable(struct clk_hw *hw)
+{
+	struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw);
+	unsigned long flags;
+	u32 clk = BIT(gate->clock_idx);
+	u32 rst = BIT(gate->reset_idx);
+	u32 enval;
+
+	spin_lock_irqsave(gate->lock, flags);
+
+	if (gate->reset_idx >= 0) {
+		/* Put IP in reset */
+		regmap_update_bits(gate->map, ASPEED_RESET_CTRL, rst, rst);
+
+		/* Delay 100us */
+		udelay(100);
+	}
+
+	/* Enable clock */
+	enval = (gate->flags & CLK_GATE_SET_TO_DISABLE) ? 0 : clk;
+	regmap_update_bits(gate->map, ASPEED_CLK_STOP_CTRL, clk, enval);
+
+	if (gate->reset_idx >= 0) {
+		/* A delay of 10ms is specified by the ASPEED docs */
+		mdelay(10);
+
+		/* Take IP out of reset */
+		regmap_update_bits(gate->map, ASPEED_RESET_CTRL, rst, 0);
+	}
+
+	spin_unlock_irqrestore(gate->lock, flags);
+
+	return 0;
+}
+
+static void aspeed_clk_disable(struct clk_hw *hw)
+{
+	struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw);
+	unsigned long flags;
+	u32 clk = BIT(gate->clock_idx);
+	u32 enval;
+
+	spin_lock_irqsave(gate->lock, flags);
+
+	enval = (gate->flags & CLK_GATE_SET_TO_DISABLE) ? clk : 0;
+	regmap_update_bits(gate->map, ASPEED_CLK_STOP_CTRL, clk, enval);
+
+	spin_unlock_irqrestore(gate->lock, flags);
+}
+
+static int aspeed_clk_is_enabled(struct clk_hw *hw)
+{
+	struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw);
+	u32 clk = BIT(gate->clock_idx);
+	u32 reg;
+
+	regmap_read(gate->map, ASPEED_CLK_STOP_CTRL, &reg);
+
+	return (reg & clk) ? 0 : 1;
+}
+
+static const struct clk_ops aspeed_clk_gate_ops = {
+	.enable = aspeed_clk_enable,
+	.disable = aspeed_clk_disable,
+	.is_enabled = aspeed_clk_is_enabled,
+};
+
+/**
+ * struct aspeed_reset - Aspeed reset controller
+ * @map: regmap to access the containing system controller
+ * @rcdev: reset controller device
+ */
+struct aspeed_reset {
+	struct regmap			*map;
+	struct reset_controller_dev	rcdev;
+};
+
+#define to_aspeed_reset(p) container_of((p), struct aspeed_reset, rcdev)
+
+static const u8 aspeed_resets[] = {
+	[ASPEED_RESET_XDMA]	= 25,
+	[ASPEED_RESET_MCTP]	= 24,
+	[ASPEED_RESET_ADC]	= 23,
+	[ASPEED_RESET_JTAG_MASTER] = 22,
+	[ASPEED_RESET_MIC]	= 18,
+	[ASPEED_RESET_PWM]	=  9,
+	[ASPEED_RESET_PCIVGA]	=  8,
+	[ASPEED_RESET_I2C]	=  2,
+	[ASPEED_RESET_AHB]	=  1,
+};
+
+static int aspeed_reset_deassert(struct reset_controller_dev *rcdev,
+				 unsigned long id)
+{
+	struct aspeed_reset *ar = to_aspeed_reset(rcdev);
+	u32 rst = BIT(aspeed_resets[id]);
+
+	return regmap_update_bits(ar->map, ASPEED_RESET_CTRL, rst, 0);
+}
+
+static int aspeed_reset_assert(struct reset_controller_dev *rcdev,
+			       unsigned long id)
+{
+	struct aspeed_reset *ar = to_aspeed_reset(rcdev);
+	u32 rst = BIT(aspeed_resets[id]);
+
+	return regmap_update_bits(ar->map, ASPEED_RESET_CTRL, rst, rst);
+}
+
+static int aspeed_reset_status(struct reset_controller_dev *rcdev,
+			       unsigned long id)
+{
+	struct aspeed_reset *ar = to_aspeed_reset(rcdev);
+	u32 val, rst = BIT(aspeed_resets[id]);
+	int ret;
+
+	ret = regmap_read(ar->map, ASPEED_RESET_CTRL, &val);
+	if (ret)
+		return ret;
+
+	return !!(val & rst);
+}
+
+static const struct reset_control_ops aspeed_reset_ops = {
+	.assert = aspeed_reset_assert,
+	.deassert = aspeed_reset_deassert,
+	.status = aspeed_reset_status,
+};
+
+static struct clk_hw *aspeed_clk_hw_register_gate(struct device *dev,
+		const char *name, const char *parent_name, unsigned long flags,
+		struct regmap *map, u8 clock_idx, u8 reset_idx,
+		u8 clk_gate_flags, spinlock_t *lock)
+{
+	struct aspeed_clk_gate *gate;
+	struct clk_init_data init;
+	struct clk_hw *hw;
+	int ret;
+
+	gate = kzalloc(sizeof(*gate), GFP_KERNEL);
+	if (!gate)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.ops = &aspeed_clk_gate_ops;
+	init.flags = flags;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+
+	gate->map = map;
+	gate->clock_idx = clock_idx;
+	gate->reset_idx = reset_idx;
+	gate->flags = clk_gate_flags;
+	gate->lock = lock;
+	gate->hw.init = &init;
+
+	hw = &gate->hw;
+	ret = clk_hw_register(dev, hw);
+	if (ret) {
+		kfree(gate);
+		hw = ERR_PTR(ret);
+	}
+
+	return hw;
+}
+
+static int aspeed_clk_probe(struct platform_device *pdev)
+{
+	const struct aspeed_clk_soc_data *soc_data;
+	struct device *dev = &pdev->dev;
+	struct aspeed_reset *ar;
+	struct regmap *map;
+	struct clk_hw *hw;
+	u32 val, rate;
+	int i, ret;
+
+	map = syscon_node_to_regmap(dev->of_node);
+	if (IS_ERR(map)) {
+		dev_err(dev, "no syscon regmap\n");
+		return PTR_ERR(map);
+	}
+
+	ar = devm_kzalloc(dev, sizeof(*ar), GFP_KERNEL);
+	if (!ar)
+		return -ENOMEM;
+
+	ar->map = map;
+	ar->rcdev.owner = THIS_MODULE;
+	ar->rcdev.nr_resets = ARRAY_SIZE(aspeed_resets);
+	ar->rcdev.ops = &aspeed_reset_ops;
+	ar->rcdev.of_node = dev->of_node;
+
+	ret = devm_reset_controller_register(dev, &ar->rcdev);
+	if (ret) {
+		dev_err(dev, "could not register reset controller\n");
+		return ret;
+	}
+
+	/* SoC generations share common layouts but have different divisors */
+	soc_data = of_device_get_match_data(dev);
+	if (!soc_data) {
+		dev_err(dev, "no match data for platform\n");
+		return -EINVAL;
+	}
+
+	/* UART clock div13 setting */
+	regmap_read(map, ASPEED_MISC_CTRL, &val);
+	if (val & UART_DIV13_EN)
+		rate = 24000000 / 13;
+	else
+		rate = 24000000;
+	/* TODO: Find the parent data for the uart clock */
+	hw = clk_hw_register_fixed_rate(dev, "uart", NULL, 0, rate);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+	aspeed_clk_data->hws[ASPEED_CLK_UART] = hw;
+
+	/*
+	 * Memory controller (M-PLL) PLL. This clock is configured by the
+	 * bootloader, and is exposed to Linux as a read-only clock rate.
+	 */
+	regmap_read(map, ASPEED_MPLL_PARAM, &val);
+	hw = soc_data->calc_pll("mpll", val);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+	aspeed_clk_data->hws[ASPEED_CLK_MPLL] =	hw;
+
+	/* SD/SDIO clock divider (TODO: There's a gate too) */
+	hw = clk_hw_register_divider_table(dev, "sdio", "hpll", 0,
+			scu_base + ASPEED_CLK_SELECTION, 12, 3, 0,
+			soc_data->div_table,
+			&aspeed_clk_lock);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+	aspeed_clk_data->hws[ASPEED_CLK_SDIO] = hw;
+
+	/* MAC AHB bus clock divider */
+	hw = clk_hw_register_divider_table(dev, "mac", "hpll", 0,
+			scu_base + ASPEED_CLK_SELECTION, 16, 3, 0,
+			soc_data->mac_div_table,
+			&aspeed_clk_lock);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+	aspeed_clk_data->hws[ASPEED_CLK_MAC] = hw;
+
+	/* LPC Host (LHCLK) clock divider */
+	hw = clk_hw_register_divider_table(dev, "lhclk", "hpll", 0,
+			scu_base + ASPEED_CLK_SELECTION, 20, 3, 0,
+			soc_data->div_table,
+			&aspeed_clk_lock);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+	aspeed_clk_data->hws[ASPEED_CLK_LHCLK] = hw;
+
+	/* P-Bus (BCLK) clock divider */
+	hw = clk_hw_register_divider_table(dev, "bclk", "hpll", 0,
+			scu_base + ASPEED_CLK_SELECTION_2, 0, 2, 0,
+			soc_data->div_table,
+			&aspeed_clk_lock);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+	aspeed_clk_data->hws[ASPEED_CLK_BCLK] = hw;
+
+	/*
+	 * TODO: There are a number of clocks that not included in this driver
+	 * as more information is required:
+	 *   D2-PLL
+	 *   D-PLL
+	 *   YCLK
+	 *   RGMII
+	 *   RMII
+	 *   UART[1..5] clock source mux
+	 *   Video Engine (ECLK) mux and clock divider
+	 */
+
+	for (i = 0; i < ARRAY_SIZE(aspeed_gates); i++) {
+		const struct aspeed_gate_data *gd = &aspeed_gates[i];
+		u32 gate_flags;
+
+		/* Special case: the USB port 1 clock (bit 14) is always
+		 * working the opposite way from the other ones.
+		 */
+		gate_flags = (gd->clock_idx == 14) ? 0 : CLK_GATE_SET_TO_DISABLE;
+		hw = aspeed_clk_hw_register_gate(dev,
+				gd->name,
+				gd->parent_name,
+				gd->flags,
+				map,
+				gd->clock_idx,
+				gd->reset_idx,
+				gate_flags,
+				&aspeed_clk_lock);
+		if (IS_ERR(hw))
+			return PTR_ERR(hw);
+		aspeed_clk_data->hws[i] = hw;
+	}
+
+	return 0;
+};
+
+static const struct of_device_id aspeed_clk_dt_ids[] = {
+	{ .compatible = "aspeed,ast2400-scu", .data = &ast2400_data },
+	{ .compatible = "aspeed,ast2500-scu", .data = &ast2500_data },
+	{ }
+};
+
+static struct platform_driver aspeed_clk_driver = {
+	.probe  = aspeed_clk_probe,
+	.driver = {
+		.name = "aspeed-clk",
+		.of_match_table = aspeed_clk_dt_ids,
+		.suppress_bind_attrs = true,
+	},
+};
+builtin_platform_driver(aspeed_clk_driver);
+
+static void __init aspeed_ast2400_cc(struct regmap *map)
+{
+	struct clk_hw *hw;
+	u32 val, freq, div;
+
+	/*
+	 * CLKIN is the crystal oscillator, 24, 48 or 25MHz selected by
+	 * strapping
+	 */
+	regmap_read(map, ASPEED_STRAP, &val);
+	if (val & CLKIN_25MHZ_EN)
+		freq = 25000000;
+	else if (val & AST2400_CLK_SOURCE_SEL)
+		freq = 48000000;
+	else
+		freq = 24000000;
+	hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, freq);
+	pr_debug("clkin @%u MHz\n", freq / 1000000);
+
+	/*
+	 * High-speed PLL clock derived from the crystal. This the CPU clock,
+	 * and we assume that it is enabled
+	 */
+	regmap_read(map, ASPEED_HPLL_PARAM, &val);
+	WARN(val & AST2400_HPLL_STRAPPED, "hpll is strapped not configured");
+	aspeed_clk_data->hws[ASPEED_CLK_HPLL] = aspeed_ast2400_calc_pll("hpll", val);
+
+	/*
+	 * Strap bits 11:10 define the CPU/AHB clock frequency ratio (aka HCLK)
+	 *   00: Select CPU:AHB = 1:1
+	 *   01: Select CPU:AHB = 2:1
+	 *   10: Select CPU:AHB = 4:1
+	 *   11: Select CPU:AHB = 3:1
+	 */
+	regmap_read(map, ASPEED_STRAP, &val);
+	val = (val >> 10) & 0x3;
+	div = val + 1;
+	if (div == 3)
+		div = 4;
+	else if (div == 4)
+		div = 3;
+	hw = clk_hw_register_fixed_factor(NULL, "ahb", "hpll", 0, 1, div);
+	aspeed_clk_data->hws[ASPEED_CLK_AHB] = hw;
+
+	/* APB clock clock selection register SCU08 (aka PCLK) */
+	hw = clk_hw_register_divider_table(NULL, "apb", "hpll", 0,
+			scu_base + ASPEED_CLK_SELECTION, 23, 3, 0,
+			ast2400_div_table,
+			&aspeed_clk_lock);
+	aspeed_clk_data->hws[ASPEED_CLK_APB] = hw;
+}
+
+static void __init aspeed_ast2500_cc(struct regmap *map)
+{
+	struct clk_hw *hw;
+	u32 val, freq, div;
+
+	/* CLKIN is the crystal oscillator, 24 or 25MHz selected by strapping */
+	regmap_read(map, ASPEED_STRAP, &val);
+	if (val & CLKIN_25MHZ_EN)
+		freq = 25000000;
+	else
+		freq = 24000000;
+	hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, freq);
+	pr_debug("clkin @%u MHz\n", freq / 1000000);
+
+	/*
+	 * High-speed PLL clock derived from the crystal. This the CPU clock,
+	 * and we assume that it is enabled
+	 */
+	regmap_read(map, ASPEED_HPLL_PARAM, &val);
+	aspeed_clk_data->hws[ASPEED_CLK_HPLL] = aspeed_ast2500_calc_pll("hpll", val);
+
+	/* Strap bits 11:9 define the AXI/AHB clock frequency ratio (aka HCLK)*/
+	regmap_read(map, ASPEED_STRAP, &val);
+	val = (val >> 9) & 0x7;
+	WARN(val == 0, "strapping is zero: cannot determine ahb clock");
+	div = 2 * (val + 1);
+	hw = clk_hw_register_fixed_factor(NULL, "ahb", "hpll", 0, 1, div);
+	aspeed_clk_data->hws[ASPEED_CLK_AHB] = hw;
+
+	/* APB clock clock selection register SCU08 (aka PCLK) */
+	regmap_read(map, ASPEED_CLK_SELECTION, &val);
+	val = (val >> 23) & 0x7;
+	div = 4 * (val + 1);
+	hw = clk_hw_register_fixed_factor(NULL, "apb", "hpll", 0, 1, div);
+	aspeed_clk_data->hws[ASPEED_CLK_APB] = hw;
+};
+
+static void __init aspeed_cc_init(struct device_node *np)
+{
+	struct regmap *map;
+	u32 val;
+	int ret;
+	int i;
+
+	scu_base = of_iomap(np, 0);
+	if (!scu_base)
+		return;
+
+	aspeed_clk_data = kzalloc(sizeof(*aspeed_clk_data) +
+			sizeof(*aspeed_clk_data->hws) * ASPEED_NUM_CLKS,
+			GFP_KERNEL);
+	if (!aspeed_clk_data)
+		return;
+
+	/*
+	 * This way all clocks fetched before the platform device probes,
+	 * except those we assign here for early use, will be deferred.
+	 */
+	for (i = 0; i < ASPEED_NUM_CLKS; i++)
+		aspeed_clk_data->hws[i] = ERR_PTR(-EPROBE_DEFER);
+
+	map = syscon_node_to_regmap(np);
+	if (IS_ERR(map)) {
+		pr_err("no syscon regmap\n");
+		return;
+	}
+	/*
+	 * We check that the regmap works on this very first access,
+	 * but as this is an MMIO-backed regmap, subsequent regmap
+	 * access is not going to fail and we skip error checks from
+	 * this point.
+	 */
+	ret = regmap_read(map, ASPEED_STRAP, &val);
+	if (ret) {
+		pr_err("failed to read strapping register\n");
+		return;
+	}
+
+	if (of_device_is_compatible(np, "aspeed,ast2400-scu"))
+		aspeed_ast2400_cc(map);
+	else if (of_device_is_compatible(np, "aspeed,ast2500-scu"))
+		aspeed_ast2500_cc(map);
+	else
+		pr_err("unknown platform, failed to add clocks\n");
+
+	aspeed_clk_data->num = ASPEED_NUM_CLKS;
+	ret = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, aspeed_clk_data);
+	if (ret)
+		pr_err("failed to add DT provider: %d\n", ret);
+};
+CLK_OF_DECLARE_DRIVER(aspeed_cc_g5, "aspeed,ast2500-scu", aspeed_cc_init);
+CLK_OF_DECLARE_DRIVER(aspeed_cc_g4, "aspeed,ast2400-scu", aspeed_cc_init);
diff --git a/drivers/clk/clk-axi-clkgen.c b/drivers/clk/clk-axi-clkgen.c
index 5e918e7afaba..48d11f2598e8 100644
--- a/drivers/clk/clk-axi-clkgen.c
+++ b/drivers/clk/clk-axi-clkgen.c
@@ -40,6 +40,10 @@
 #define MMCM_REG_FILTER1	0x4e
 #define MMCM_REG_FILTER2	0x4f
 
+#define MMCM_CLKOUT_NOCOUNT	BIT(6)
+
+#define MMCM_CLK_DIV_NOCOUNT	BIT(12)
+
 struct axi_clkgen {
 	void __iomem *base;
 	struct clk_hw clk_hw;
@@ -298,13 +302,17 @@ static long axi_clkgen_round_rate(struct clk_hw *hw, unsigned long rate,
 	unsigned long *parent_rate)
 {
 	unsigned int d, m, dout;
+	unsigned long long tmp;
 
 	axi_clkgen_calc_params(*parent_rate, rate, &d, &m, &dout);
 
 	if (d == 0 || dout == 0 || m == 0)
 		return -EINVAL;
 
-	return *parent_rate / d * m / dout;
+	tmp = (unsigned long long)*parent_rate * m;
+	tmp = DIV_ROUND_CLOSEST_ULL(tmp, dout * d);
+
+	return min_t(unsigned long long, tmp, LONG_MAX);
 }
 
 static unsigned long axi_clkgen_recalc_rate(struct clk_hw *clk_hw,
@@ -315,18 +323,33 @@ static unsigned long axi_clkgen_recalc_rate(struct clk_hw *clk_hw,
 	unsigned int reg;
 	unsigned long long tmp;
 
-	axi_clkgen_mmcm_read(axi_clkgen, MMCM_REG_CLKOUT0_1, &reg);
-	dout = (reg & 0x3f) + ((reg >> 6) & 0x3f);
+	axi_clkgen_mmcm_read(axi_clkgen, MMCM_REG_CLKOUT0_2, &reg);
+	if (reg & MMCM_CLKOUT_NOCOUNT) {
+		dout = 1;
+	} else {
+		axi_clkgen_mmcm_read(axi_clkgen, MMCM_REG_CLKOUT0_1, &reg);
+		dout = (reg & 0x3f) + ((reg >> 6) & 0x3f);
+	}
+
 	axi_clkgen_mmcm_read(axi_clkgen, MMCM_REG_CLK_DIV, &reg);
-	d = (reg & 0x3f) + ((reg >> 6) & 0x3f);
-	axi_clkgen_mmcm_read(axi_clkgen, MMCM_REG_CLK_FB1, &reg);
-	m = (reg & 0x3f) + ((reg >> 6) & 0x3f);
+	if (reg & MMCM_CLK_DIV_NOCOUNT)
+		d = 1;
+	else
+		d = (reg & 0x3f) + ((reg >> 6) & 0x3f);
+
+	axi_clkgen_mmcm_read(axi_clkgen, MMCM_REG_CLK_FB2, &reg);
+	if (reg & MMCM_CLKOUT_NOCOUNT) {
+		m = 1;
+	} else {
+		axi_clkgen_mmcm_read(axi_clkgen, MMCM_REG_CLK_FB1, &reg);
+		m = (reg & 0x3f) + ((reg >> 6) & 0x3f);
+	}
 
 	if (d == 0 || dout == 0)
 		return 0;
 
-	tmp = (unsigned long long)(parent_rate / d) * m;
-	do_div(tmp, dout);
+	tmp = (unsigned long long)parent_rate * m;
+	tmp = DIV_ROUND_CLOSEST_ULL(tmp, dout * d);
 
 	return min_t(unsigned long long, tmp, ULONG_MAX);
 }
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 4ed516cb7276..b49942b9fe50 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -118,12 +118,11 @@ static unsigned int _get_val(const struct clk_div_table *table,
 unsigned long divider_recalc_rate(struct clk_hw *hw, unsigned long parent_rate,
 				  unsigned int val,
 				  const struct clk_div_table *table,
-				  unsigned long flags)
+				  unsigned long flags, unsigned long width)
 {
-	struct clk_divider *divider = to_clk_divider(hw);
 	unsigned int div;
 
-	div = _get_div(table, val, flags, divider->width);
+	div = _get_div(table, val, flags, width);
 	if (!div) {
 		WARN(!(flags & CLK_DIVIDER_ALLOW_ZERO),
 			"%s: Zero divisor and CLK_DIVIDER_ALLOW_ZERO not set\n",
@@ -145,7 +144,7 @@ static unsigned long clk_divider_recalc_rate(struct clk_hw *hw,
 	val &= div_mask(divider->width);
 
 	return divider_recalc_rate(hw, parent_rate, val, divider->table,
-				   divider->flags);
+				   divider->flags, divider->width);
 }
 
 static bool _is_valid_table_div(const struct clk_div_table *table,
diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c
index b0ea753b8709..3a1812f65e5d 100644
--- a/drivers/clk/clk-qoriq.c
+++ b/drivers/clk/clk-qoriq.c
@@ -41,7 +41,7 @@ struct clockgen_pll_div {
 };
 
 struct clockgen_pll {
-	struct clockgen_pll_div div[4];
+	struct clockgen_pll_div div[8];
 };
 
 #define CLKSEL_VALID	1
@@ -1127,6 +1127,13 @@ static void __init create_one_pll(struct clockgen *cg, int idx)
 		struct clk *clk;
 		int ret;
 
+		/*
+		 * For platform PLL, there are 8 divider clocks.
+		 * For core PLL, there are 4 divider clocks at most.
+		 */
+		if (idx != PLATFORM_PLL && i >= 4)
+			break;
+
 		snprintf(pll->div[i].name, sizeof(pll->div[i].name),
 			 "cg-pll%d-div%d", idx, i + 1);
 
diff --git a/drivers/clk/clk-si5351.c b/drivers/clk/clk-si5351.c
index 20d90769cced..50e7c341e97e 100644
--- a/drivers/clk/clk-si5351.c
+++ b/drivers/clk/clk-si5351.c
@@ -72,7 +72,7 @@ static const char * const si5351_input_names[] = {
 	"xtal", "clkin"
 };
 static const char * const si5351_pll_names[] = {
-	"plla", "pllb", "vxco"
+	"si5351_plla", "si5351_pllb", "si5351_vxco"
 };
 static const char * const si5351_msynth_names[] = {
 	"ms0", "ms1", "ms2", "ms3", "ms4", "ms5", "ms6", "ms7"
@@ -903,13 +903,42 @@ static int _si5351_clkout_set_disable_state(
 	return 0;
 }
 
+static void _si5351_clkout_reset_pll(struct si5351_driver_data *drvdata, int num)
+{
+	u8 val = si5351_reg_read(drvdata, SI5351_CLK0_CTRL + num);
+
+	switch (val & SI5351_CLK_INPUT_MASK) {
+	case SI5351_CLK_INPUT_XTAL:
+	case SI5351_CLK_INPUT_CLKIN:
+		return;  /* pll not used, no need to reset */
+	}
+
+	si5351_reg_write(drvdata, SI5351_PLL_RESET,
+			 val & SI5351_CLK_PLL_SELECT ? SI5351_PLL_RESET_B :
+						       SI5351_PLL_RESET_A);
+
+	dev_dbg(&drvdata->client->dev, "%s - %s: pll = %d\n",
+		__func__, clk_hw_get_name(&drvdata->clkout[num].hw),
+		(val & SI5351_CLK_PLL_SELECT) ? 1 : 0);
+}
+
 static int si5351_clkout_prepare(struct clk_hw *hw)
 {
 	struct si5351_hw_data *hwdata =
 		container_of(hw, struct si5351_hw_data, hw);
+	struct si5351_platform_data *pdata =
+		hwdata->drvdata->client->dev.platform_data;
 
 	si5351_set_bits(hwdata->drvdata, SI5351_CLK0_CTRL + hwdata->num,
 			SI5351_CLK_POWERDOWN, 0);
+
+	/*
+	 * Do a pll soft reset on the parent pll -- needed to get a
+	 * deterministic phase relationship between the output clocks.
+	 */
+	if (pdata->clkout[hwdata->num].pll_reset)
+		_si5351_clkout_reset_pll(hwdata->drvdata, hwdata->num);
+
 	si5351_set_bits(hwdata->drvdata, SI5351_OUTPUT_ENABLE_CTRL,
 			(1 << hwdata->num), 0);
 	return 0;
@@ -1297,6 +1326,9 @@ static int si5351_dt_parse(struct i2c_client *client,
 
 		pdata->clkout[num].pll_master =
 			of_property_read_bool(child, "silabs,pll-master");
+
+		pdata->clkout[num].pll_reset =
+			of_property_read_bool(child, "silabs,pll-reset");
 	}
 	client->dev.platform_data = pdata;
 
@@ -1437,11 +1469,6 @@ static int si5351_i2c_probe(struct i2c_client *client,
 		}
 	}
 
-	if (!IS_ERR(drvdata->pxtal))
-		clk_prepare_enable(drvdata->pxtal);
-	if (!IS_ERR(drvdata->pclkin))
-		clk_prepare_enable(drvdata->pclkin);
-
 	/* register xtal input clock gate */
 	memset(&init, 0, sizeof(init));
 	init.name = si5351_input_names[0];
@@ -1456,7 +1483,7 @@ static int si5351_i2c_probe(struct i2c_client *client,
 	ret = devm_clk_hw_register(&client->dev, &drvdata->xtal);
 	if (ret) {
 		dev_err(&client->dev, "unable to register %s\n", init.name);
-		goto err_clk;
+		return ret;
 	}
 
 	/* register clkin input clock gate */
@@ -1474,7 +1501,7 @@ static int si5351_i2c_probe(struct i2c_client *client,
 		if (ret) {
 			dev_err(&client->dev, "unable to register %s\n",
 				init.name);
-			goto err_clk;
+			return ret;
 		}
 	}
 
@@ -1496,7 +1523,7 @@ static int si5351_i2c_probe(struct i2c_client *client,
 	ret = devm_clk_hw_register(&client->dev, &drvdata->pll[0].hw);
 	if (ret) {
 		dev_err(&client->dev, "unable to register %s\n", init.name);
-		goto err_clk;
+		return ret;
 	}
 
 	/* register PLLB or VXCO (Si5351B) */
@@ -1520,7 +1547,7 @@ static int si5351_i2c_probe(struct i2c_client *client,
 	ret = devm_clk_hw_register(&client->dev, &drvdata->pll[1].hw);
 	if (ret) {
 		dev_err(&client->dev, "unable to register %s\n", init.name);
-		goto err_clk;
+		return ret;
 	}
 
 	/* register clk multisync and clk out divider */
@@ -1539,7 +1566,7 @@ static int si5351_i2c_probe(struct i2c_client *client,
 
 	if (WARN_ON(!drvdata->msynth || !drvdata->clkout)) {
 		ret = -ENOMEM;
-		goto err_clk;
+		return ret;
 	}
 
 	for (n = 0; n < num_clocks; n++) {
@@ -1559,7 +1586,7 @@ static int si5351_i2c_probe(struct i2c_client *client,
 		if (ret) {
 			dev_err(&client->dev, "unable to register %s\n",
 				init.name);
-			goto err_clk;
+			return ret;
 		}
 	}
 
@@ -1587,7 +1614,7 @@ static int si5351_i2c_probe(struct i2c_client *client,
 		if (ret) {
 			dev_err(&client->dev, "unable to register %s\n",
 				init.name);
-			goto err_clk;
+			return ret;
 		}
 
 		/* set initial clkout rate */
@@ -1606,17 +1633,17 @@ static int si5351_i2c_probe(struct i2c_client *client,
 				     drvdata);
 	if (ret) {
 		dev_err(&client->dev, "unable to add clk provider\n");
-		goto err_clk;
+		return ret;
 	}
 
 	return 0;
+}
 
-err_clk:
-	if (!IS_ERR(drvdata->pxtal))
-		clk_disable_unprepare(drvdata->pxtal);
-	if (!IS_ERR(drvdata->pclkin))
-		clk_disable_unprepare(drvdata->pclkin);
-	return ret;
+static int si5351_i2c_remove(struct i2c_client *client)
+{
+	of_clk_del_provider(client->dev.of_node);
+
+	return 0;
 }
 
 static const struct i2c_device_id si5351_i2c_ids[] = {
@@ -1634,6 +1661,7 @@ static struct i2c_driver si5351_driver = {
 		.of_match_table = of_match_ptr(si5351_dt_ids),
 	},
 	.probe = si5351_i2c_probe,
+	.remove = si5351_i2c_remove,
 	.id_table = si5351_i2c_ids,
 };
 module_i2c_driver(si5351_driver);
diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c
index 96c6b6bc8f0e..da44f8dc1d29 100644
--- a/drivers/clk/clk-stm32f4.c
+++ b/drivers/clk/clk-stm32f4.c
@@ -1424,7 +1424,7 @@ static void __init stm32f4_rcc_init(struct device_node *np)
 
 	base = of_iomap(np, 0);
 	if (!base) {
-		pr_err("%s: unable to map resource", np->name);
+		pr_err("%s: unable to map resource\n", np->name);
 		return;
 	}
 
diff --git a/drivers/clk/clk-stm32h7.c b/drivers/clk/clk-stm32h7.c
index 61c3e40507d3..db2b162c0d4c 100644
--- a/drivers/clk/clk-stm32h7.c
+++ b/drivers/clk/clk-stm32h7.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) Gabriel Fernandez 2017
- * Author: Gabriel Fernandez <gabriel.fernandez@st.com>
- *
- * License terms: GPL V2.0.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) STMicroelectronics 2017
+ * Author: Gabriel Fernandez <gabriel.fernandez@st.com> for STMicroelectronics.
  */
 
 #include <linux/clk.h>
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 647d056df88c..0f686a9dac3e 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -24,6 +24,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/sched.h>
 #include <linux/clkdev.h>
+#include <linux/stringify.h>
 
 #include "clk.h"
 
@@ -62,6 +63,7 @@ struct clk_core {
 	bool			orphan;
 	unsigned int		enable_count;
 	unsigned int		prepare_count;
+	unsigned int		protect_count;
 	unsigned long		min_rate;
 	unsigned long		max_rate;
 	unsigned long		accuracy;
@@ -86,6 +88,7 @@ struct clk {
 	const char *con_id;
 	unsigned long min_rate;
 	unsigned long max_rate;
+	unsigned int exclusive_count;
 	struct hlist_node clks_node;
 };
 
@@ -141,10 +144,18 @@ static unsigned long clk_enable_lock(void)
 {
 	unsigned long flags;
 
-	if (!spin_trylock_irqsave(&enable_lock, flags)) {
+	/*
+	 * On UP systems, spin_trylock_irqsave() always returns true, even if
+	 * we already hold the lock. So, in that case, we rely only on
+	 * reference counting.
+	 */
+	if (!IS_ENABLED(CONFIG_SMP) ||
+	    !spin_trylock_irqsave(&enable_lock, flags)) {
 		if (enable_owner == current) {
 			enable_refcnt++;
 			__acquire(enable_lock);
+			if (!IS_ENABLED(CONFIG_SMP))
+				local_save_flags(flags);
 			return flags;
 		}
 		spin_lock_irqsave(&enable_lock, flags);
@@ -170,6 +181,11 @@ static void clk_enable_unlock(unsigned long flags)
 	spin_unlock_irqrestore(&enable_lock, flags);
 }
 
+static bool clk_core_rate_is_protected(struct clk_core *core)
+{
+	return core->protect_count;
+}
+
 static bool clk_core_is_prepared(struct clk_core *core)
 {
 	bool ret = false;
@@ -220,7 +236,8 @@ static bool clk_core_is_enabled(struct clk_core *core)
 
 	ret = core->ops->is_enabled(core->hw);
 done:
-	clk_pm_runtime_put(core);
+	if (core->dev)
+		pm_runtime_put(core->dev);
 
 	return ret;
 }
@@ -381,6 +398,11 @@ bool clk_hw_is_prepared(const struct clk_hw *hw)
 	return clk_core_is_prepared(hw->core);
 }
 
+bool clk_hw_rate_is_protected(const struct clk_hw *hw)
+{
+	return clk_core_rate_is_protected(hw->core);
+}
+
 bool clk_hw_is_enabled(const struct clk_hw *hw)
 {
 	return clk_core_is_enabled(hw->core);
@@ -519,6 +541,139 @@ EXPORT_SYMBOL_GPL(__clk_mux_determine_rate_closest);
 
 /***        clk api        ***/
 
+static void clk_core_rate_unprotect(struct clk_core *core)
+{
+	lockdep_assert_held(&prepare_lock);
+
+	if (!core)
+		return;
+
+	if (WARN_ON(core->protect_count == 0))
+		return;
+
+	if (--core->protect_count > 0)
+		return;
+
+	clk_core_rate_unprotect(core->parent);
+}
+
+static int clk_core_rate_nuke_protect(struct clk_core *core)
+{
+	int ret;
+
+	lockdep_assert_held(&prepare_lock);
+
+	if (!core)
+		return -EINVAL;
+
+	if (core->protect_count == 0)
+		return 0;
+
+	ret = core->protect_count;
+	core->protect_count = 1;
+	clk_core_rate_unprotect(core);
+
+	return ret;
+}
+
+/**
+ * clk_rate_exclusive_put - release exclusivity over clock rate control
+ * @clk: the clk over which the exclusivity is released
+ *
+ * clk_rate_exclusive_put() completes a critical section during which a clock
+ * consumer cannot tolerate any other consumer making any operation on the
+ * clock which could result in a rate change or rate glitch. Exclusive clocks
+ * cannot have their rate changed, either directly or indirectly due to changes
+ * further up the parent chain of clocks. As a result, clocks up parent chain
+ * also get under exclusive control of the calling consumer.
+ *
+ * If exlusivity is claimed more than once on clock, even by the same consumer,
+ * the rate effectively gets locked as exclusivity can't be preempted.
+ *
+ * Calls to clk_rate_exclusive_put() must be balanced with calls to
+ * clk_rate_exclusive_get(). Calls to this function may sleep, and do not return
+ * error status.
+ */
+void clk_rate_exclusive_put(struct clk *clk)
+{
+	if (!clk)
+		return;
+
+	clk_prepare_lock();
+
+	/*
+	 * if there is something wrong with this consumer protect count, stop
+	 * here before messing with the provider
+	 */
+	if (WARN_ON(clk->exclusive_count <= 0))
+		goto out;
+
+	clk_core_rate_unprotect(clk->core);
+	clk->exclusive_count--;
+out:
+	clk_prepare_unlock();
+}
+EXPORT_SYMBOL_GPL(clk_rate_exclusive_put);
+
+static void clk_core_rate_protect(struct clk_core *core)
+{
+	lockdep_assert_held(&prepare_lock);
+
+	if (!core)
+		return;
+
+	if (core->protect_count == 0)
+		clk_core_rate_protect(core->parent);
+
+	core->protect_count++;
+}
+
+static void clk_core_rate_restore_protect(struct clk_core *core, int count)
+{
+	lockdep_assert_held(&prepare_lock);
+
+	if (!core)
+		return;
+
+	if (count == 0)
+		return;
+
+	clk_core_rate_protect(core);
+	core->protect_count = count;
+}
+
+/**
+ * clk_rate_exclusive_get - get exclusivity over the clk rate control
+ * @clk: the clk over which the exclusity of rate control is requested
+ *
+ * clk_rate_exlusive_get() begins a critical section during which a clock
+ * consumer cannot tolerate any other consumer making any operation on the
+ * clock which could result in a rate change or rate glitch. Exclusive clocks
+ * cannot have their rate changed, either directly or indirectly due to changes
+ * further up the parent chain of clocks. As a result, clocks up parent chain
+ * also get under exclusive control of the calling consumer.
+ *
+ * If exlusivity is claimed more than once on clock, even by the same consumer,
+ * the rate effectively gets locked as exclusivity can't be preempted.
+ *
+ * Calls to clk_rate_exclusive_get() should be balanced with calls to
+ * clk_rate_exclusive_put(). Calls to this function may sleep.
+ * Returns 0 on success, -EERROR otherwise
+ */
+int clk_rate_exclusive_get(struct clk *clk)
+{
+	if (!clk)
+		return 0;
+
+	clk_prepare_lock();
+	clk_core_rate_protect(clk->core);
+	clk->exclusive_count++;
+	clk_prepare_unlock();
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(clk_rate_exclusive_get);
+
 static void clk_core_unprepare(struct clk_core *core)
 {
 	lockdep_assert_held(&prepare_lock);
@@ -905,10 +1060,9 @@ static int clk_disable_unused(void)
 }
 late_initcall_sync(clk_disable_unused);
 
-static int clk_core_round_rate_nolock(struct clk_core *core,
-				      struct clk_rate_request *req)
+static int clk_core_determine_round_nolock(struct clk_core *core,
+					   struct clk_rate_request *req)
 {
-	struct clk_core *parent;
 	long rate;
 
 	lockdep_assert_held(&prepare_lock);
@@ -916,16 +1070,15 @@ static int clk_core_round_rate_nolock(struct clk_core *core,
 	if (!core)
 		return 0;
 
-	parent = core->parent;
-	if (parent) {
-		req->best_parent_hw = parent->hw;
-		req->best_parent_rate = parent->rate;
-	} else {
-		req->best_parent_hw = NULL;
-		req->best_parent_rate = 0;
-	}
-
-	if (core->ops->determine_rate) {
+	/*
+	 * At this point, core protection will be disabled if
+	 * - if the provider is not protected at all
+	 * - if the calling consumer is the only one which has exclusivity
+	 *   over the provider
+	 */
+	if (clk_core_rate_is_protected(core)) {
+		req->rate = core->rate;
+	} else if (core->ops->determine_rate) {
 		return core->ops->determine_rate(core->hw, req);
 	} else if (core->ops->round_rate) {
 		rate = core->ops->round_rate(core->hw, req->rate,
@@ -934,12 +1087,55 @@ static int clk_core_round_rate_nolock(struct clk_core *core,
 			return rate;
 
 		req->rate = rate;
-	} else if (core->flags & CLK_SET_RATE_PARENT) {
-		return clk_core_round_rate_nolock(parent, req);
 	} else {
-		req->rate = core->rate;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void clk_core_init_rate_req(struct clk_core * const core,
+				   struct clk_rate_request *req)
+{
+	struct clk_core *parent;
+
+	if (WARN_ON(!core || !req))
+		return;
+
+	parent = core->parent;
+	if (parent) {
+		req->best_parent_hw = parent->hw;
+		req->best_parent_rate = parent->rate;
+	} else {
+		req->best_parent_hw = NULL;
+		req->best_parent_rate = 0;
 	}
+}
+
+static bool clk_core_can_round(struct clk_core * const core)
+{
+	if (core->ops->determine_rate || core->ops->round_rate)
+		return true;
+
+	return false;
+}
+
+static int clk_core_round_rate_nolock(struct clk_core *core,
+				      struct clk_rate_request *req)
+{
+	lockdep_assert_held(&prepare_lock);
+
+	if (!core)
+		return 0;
+
+	clk_core_init_rate_req(core, req);
 
+	if (clk_core_can_round(core))
+		return clk_core_determine_round_nolock(core, req);
+	else if (core->flags & CLK_SET_RATE_PARENT)
+		return clk_core_round_rate_nolock(core->parent, req);
+
+	req->rate = core->rate;
 	return 0;
 }
 
@@ -996,10 +1192,17 @@ long clk_round_rate(struct clk *clk, unsigned long rate)
 
 	clk_prepare_lock();
 
+	if (clk->exclusive_count)
+		clk_core_rate_unprotect(clk->core);
+
 	clk_core_get_boundaries(clk->core, &req.min_rate, &req.max_rate);
 	req.rate = rate;
 
 	ret = clk_core_round_rate_nolock(clk->core, &req);
+
+	if (clk->exclusive_count)
+		clk_core_rate_protect(clk->core);
+
 	clk_prepare_unlock();
 
 	if (ret)
@@ -1432,34 +1635,23 @@ static struct clk_core *clk_calc_new_rates(struct clk_core *core,
 	clk_core_get_boundaries(core, &min_rate, &max_rate);
 
 	/* find the closest rate and parent clk/rate */
-	if (core->ops->determine_rate) {
+	if (clk_core_can_round(core)) {
 		struct clk_rate_request req;
 
 		req.rate = rate;
 		req.min_rate = min_rate;
 		req.max_rate = max_rate;
-		if (parent) {
-			req.best_parent_hw = parent->hw;
-			req.best_parent_rate = parent->rate;
-		} else {
-			req.best_parent_hw = NULL;
-			req.best_parent_rate = 0;
-		}
 
-		ret = core->ops->determine_rate(core->hw, &req);
+		clk_core_init_rate_req(core, &req);
+
+		ret = clk_core_determine_round_nolock(core, &req);
 		if (ret < 0)
 			return NULL;
 
 		best_parent_rate = req.best_parent_rate;
 		new_rate = req.rate;
 		parent = req.best_parent_hw ? req.best_parent_hw->core : NULL;
-	} else if (core->ops->round_rate) {
-		ret = core->ops->round_rate(core->hw, rate,
-					    &best_parent_rate);
-		if (ret < 0)
-			return NULL;
 
-		new_rate = ret;
 		if (new_rate < min_rate || new_rate > max_rate)
 			return NULL;
 	} else if (!parent || !(core->flags & CLK_SET_RATE_PARENT)) {
@@ -1564,6 +1756,9 @@ static void clk_change_rate(struct clk_core *core)
 		best_parent_rate = core->parent->rate;
 	}
 
+	if (clk_pm_runtime_get(core))
+		return;
+
 	if (core->flags & CLK_SET_RATE_UNGATE) {
 		unsigned long flags;
 
@@ -1634,27 +1829,62 @@ static void clk_change_rate(struct clk_core *core)
 	/* handle the new child who might not be in core->children yet */
 	if (core->new_child)
 		clk_change_rate(core->new_child);
+
+	clk_pm_runtime_put(core);
+}
+
+static unsigned long clk_core_req_round_rate_nolock(struct clk_core *core,
+						     unsigned long req_rate)
+{
+	int ret, cnt;
+	struct clk_rate_request req;
+
+	lockdep_assert_held(&prepare_lock);
+
+	if (!core)
+		return 0;
+
+	/* simulate what the rate would be if it could be freely set */
+	cnt = clk_core_rate_nuke_protect(core);
+	if (cnt < 0)
+		return cnt;
+
+	clk_core_get_boundaries(core, &req.min_rate, &req.max_rate);
+	req.rate = req_rate;
+
+	ret = clk_core_round_rate_nolock(core, &req);
+
+	/* restore the protection */
+	clk_core_rate_restore_protect(core, cnt);
+
+	return ret ? 0 : req.rate;
 }
 
 static int clk_core_set_rate_nolock(struct clk_core *core,
 				    unsigned long req_rate)
 {
 	struct clk_core *top, *fail_clk;
-	unsigned long rate = req_rate;
+	unsigned long rate;
 	int ret = 0;
 
 	if (!core)
 		return 0;
 
+	rate = clk_core_req_round_rate_nolock(core, req_rate);
+
 	/* bail early if nothing to do */
 	if (rate == clk_core_get_rate_nolock(core))
 		return 0;
 
+	/* fail on a direct rate set of a protected provider */
+	if (clk_core_rate_is_protected(core))
+		return -EBUSY;
+
 	if ((core->flags & CLK_SET_RATE_GATE) && core->prepare_count)
 		return -EBUSY;
 
 	/* calculate new rates and get the topmost changed clock */
-	top = clk_calc_new_rates(core, rate);
+	top = clk_calc_new_rates(core, req_rate);
 	if (!top)
 		return -EINVAL;
 
@@ -1713,8 +1943,14 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 	/* prevent racing with updates to the clock topology */
 	clk_prepare_lock();
 
+	if (clk->exclusive_count)
+		clk_core_rate_unprotect(clk->core);
+
 	ret = clk_core_set_rate_nolock(clk->core, rate);
 
+	if (clk->exclusive_count)
+		clk_core_rate_protect(clk->core);
+
 	clk_prepare_unlock();
 
 	return ret;
@@ -1722,6 +1958,53 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 EXPORT_SYMBOL_GPL(clk_set_rate);
 
 /**
+ * clk_set_rate_exclusive - specify a new rate get exclusive control
+ * @clk: the clk whose rate is being changed
+ * @rate: the new rate for clk
+ *
+ * This is a combination of clk_set_rate() and clk_rate_exclusive_get()
+ * within a critical section
+ *
+ * This can be used initially to ensure that at least 1 consumer is
+ * statisfied when several consumers are competing for exclusivity over the
+ * same clock provider.
+ *
+ * The exclusivity is not applied if setting the rate failed.
+ *
+ * Calls to clk_rate_exclusive_get() should be balanced with calls to
+ * clk_rate_exclusive_put().
+ *
+ * Returns 0 on success, -EERROR otherwise.
+ */
+int clk_set_rate_exclusive(struct clk *clk, unsigned long rate)
+{
+	int ret;
+
+	if (!clk)
+		return 0;
+
+	/* prevent racing with updates to the clock topology */
+	clk_prepare_lock();
+
+	/*
+	 * The temporary protection removal is not here, on purpose
+	 * This function is meant to be used instead of clk_rate_protect,
+	 * so before the consumer code path protect the clock provider
+	 */
+
+	ret = clk_core_set_rate_nolock(clk->core, rate);
+	if (!ret) {
+		clk_core_rate_protect(clk->core);
+		clk->exclusive_count++;
+	}
+
+	clk_prepare_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_set_rate_exclusive);
+
+/**
  * clk_set_rate_range - set a rate range for a clock source
  * @clk: clock source
  * @min: desired minimum clock rate in Hz, inclusive
@@ -1732,6 +2015,7 @@ EXPORT_SYMBOL_GPL(clk_set_rate);
 int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max)
 {
 	int ret = 0;
+	unsigned long old_min, old_max, rate;
 
 	if (!clk)
 		return 0;
@@ -1745,12 +2029,46 @@ int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max)
 
 	clk_prepare_lock();
 
-	if (min != clk->min_rate || max != clk->max_rate) {
-		clk->min_rate = min;
-		clk->max_rate = max;
-		ret = clk_core_set_rate_nolock(clk->core, clk->core->req_rate);
+	if (clk->exclusive_count)
+		clk_core_rate_unprotect(clk->core);
+
+	/* Save the current values in case we need to rollback the change */
+	old_min = clk->min_rate;
+	old_max = clk->max_rate;
+	clk->min_rate = min;
+	clk->max_rate = max;
+
+	rate = clk_core_get_rate_nolock(clk->core);
+	if (rate < min || rate > max) {
+		/*
+		 * FIXME:
+		 * We are in bit of trouble here, current rate is outside the
+		 * the requested range. We are going try to request appropriate
+		 * range boundary but there is a catch. It may fail for the
+		 * usual reason (clock broken, clock protected, etc) but also
+		 * because:
+		 * - round_rate() was not favorable and fell on the wrong
+		 *   side of the boundary
+		 * - the determine_rate() callback does not really check for
+		 *   this corner case when determining the rate
+		 */
+
+		if (rate < min)
+			rate = min;
+		else
+			rate = max;
+
+		ret = clk_core_set_rate_nolock(clk->core, rate);
+		if (ret) {
+			/* rollback the changes */
+			clk->min_rate = old_min;
+			clk->max_rate = old_max;
+		}
 	}
 
+	if (clk->exclusive_count)
+		clk_core_rate_protect(clk->core);
+
 	clk_prepare_unlock();
 
 	return ret;
@@ -1871,32 +2189,31 @@ bool clk_has_parent(struct clk *clk, struct clk *parent)
 }
 EXPORT_SYMBOL_GPL(clk_has_parent);
 
-static int clk_core_set_parent(struct clk_core *core, struct clk_core *parent)
+static int clk_core_set_parent_nolock(struct clk_core *core,
+				      struct clk_core *parent)
 {
 	int ret = 0;
 	int p_index = 0;
 	unsigned long p_rate = 0;
 
+	lockdep_assert_held(&prepare_lock);
+
 	if (!core)
 		return 0;
 
-	/* prevent racing with updates to the clock topology */
-	clk_prepare_lock();
-
 	if (core->parent == parent)
-		goto out;
+		return 0;
 
 	/* verify ops for for multi-parent clks */
-	if ((core->num_parents > 1) && (!core->ops->set_parent)) {
-		ret = -ENOSYS;
-		goto out;
-	}
+	if (core->num_parents > 1 && !core->ops->set_parent)
+		return -EPERM;
 
 	/* check that we are allowed to re-parent if the clock is in use */
-	if ((core->flags & CLK_SET_PARENT_GATE) && core->prepare_count) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if ((core->flags & CLK_SET_PARENT_GATE) && core->prepare_count)
+		return -EBUSY;
+
+	if (clk_core_rate_is_protected(core))
+		return -EBUSY;
 
 	/* try finding the new parent index */
 	if (parent) {
@@ -1904,15 +2221,14 @@ static int clk_core_set_parent(struct clk_core *core, struct clk_core *parent)
 		if (p_index < 0) {
 			pr_debug("%s: clk %s can not be parent of clk %s\n",
 					__func__, parent->name, core->name);
-			ret = p_index;
-			goto out;
+			return p_index;
 		}
 		p_rate = parent->rate;
 	}
 
 	ret = clk_pm_runtime_get(core);
 	if (ret)
-		goto out;
+		return ret;
 
 	/* propagate PRE_RATE_CHANGE notifications */
 	ret = __clk_speculate_rates(core, p_rate);
@@ -1934,8 +2250,6 @@ static int clk_core_set_parent(struct clk_core *core, struct clk_core *parent)
 
 runtime_put:
 	clk_pm_runtime_put(core);
-out:
-	clk_prepare_unlock();
 
 	return ret;
 }
@@ -1959,13 +2273,50 @@ out:
  */
 int clk_set_parent(struct clk *clk, struct clk *parent)
 {
+	int ret;
+
 	if (!clk)
 		return 0;
 
-	return clk_core_set_parent(clk->core, parent ? parent->core : NULL);
+	clk_prepare_lock();
+
+	if (clk->exclusive_count)
+		clk_core_rate_unprotect(clk->core);
+
+	ret = clk_core_set_parent_nolock(clk->core,
+					 parent ? parent->core : NULL);
+
+	if (clk->exclusive_count)
+		clk_core_rate_protect(clk->core);
+
+	clk_prepare_unlock();
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(clk_set_parent);
 
+static int clk_core_set_phase_nolock(struct clk_core *core, int degrees)
+{
+	int ret = -EINVAL;
+
+	lockdep_assert_held(&prepare_lock);
+
+	if (!core)
+		return 0;
+
+	if (clk_core_rate_is_protected(core))
+		return -EBUSY;
+
+	trace_clk_set_phase(core, degrees);
+
+	if (core->ops->set_phase)
+		ret = core->ops->set_phase(core->hw, degrees);
+
+	trace_clk_set_phase_complete(core, degrees);
+
+	return ret;
+}
+
 /**
  * clk_set_phase - adjust the phase shift of a clock signal
  * @clk: clock signal source
@@ -1988,7 +2339,7 @@ EXPORT_SYMBOL_GPL(clk_set_parent);
  */
 int clk_set_phase(struct clk *clk, int degrees)
 {
-	int ret = -EINVAL;
+	int ret;
 
 	if (!clk)
 		return 0;
@@ -2000,15 +2351,13 @@ int clk_set_phase(struct clk *clk, int degrees)
 
 	clk_prepare_lock();
 
-	trace_clk_set_phase(clk->core, degrees);
+	if (clk->exclusive_count)
+		clk_core_rate_unprotect(clk->core);
 
-	if (clk->core->ops->set_phase)
-		ret = clk->core->ops->set_phase(clk->core->hw, degrees);
+	ret = clk_core_set_phase_nolock(clk->core, degrees);
 
-	trace_clk_set_phase_complete(clk->core, degrees);
-
-	if (!ret)
-		clk->core->phase = degrees;
+	if (clk->exclusive_count)
+		clk_core_rate_protect(clk->core);
 
 	clk_prepare_unlock();
 
@@ -2096,11 +2445,12 @@ static void clk_summary_show_one(struct seq_file *s, struct clk_core *c,
 	if (!c)
 		return;
 
-	seq_printf(s, "%*s%-*s %11d %12d %11lu %10lu %-3d\n",
+	seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu %-3d\n",
 		   level * 3 + 1, "",
 		   30 - level * 3, c->name,
-		   c->enable_count, c->prepare_count, clk_core_get_rate(c),
-		   clk_core_get_accuracy(c), clk_core_get_phase(c));
+		   c->enable_count, c->prepare_count, c->protect_count,
+		   clk_core_get_rate(c), clk_core_get_accuracy(c),
+		   clk_core_get_phase(c));
 }
 
 static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c,
@@ -2122,7 +2472,8 @@ static int clk_summary_show(struct seq_file *s, void *data)
 	struct clk_core *c;
 	struct hlist_head **lists = (struct hlist_head **)s->private;
 
-	seq_puts(s, "   clock                         enable_cnt  prepare_cnt        rate   accuracy   phase\n");
+	seq_puts(s, "                                 enable  prepare  protect                               \n");
+	seq_puts(s, "   clock                          count    count    count        rate   accuracy   phase\n");
 	seq_puts(s, "----------------------------------------------------------------------------------------\n");
 
 	clk_prepare_lock();
@@ -2158,6 +2509,7 @@ static void clk_dump_one(struct seq_file *s, struct clk_core *c, int level)
 	seq_printf(s, "\"%s\": { ", c->name);
 	seq_printf(s, "\"enable_count\": %d,", c->enable_count);
 	seq_printf(s, "\"prepare_count\": %d,", c->prepare_count);
+	seq_printf(s, "\"protect_count\": %d,", c->protect_count);
 	seq_printf(s, "\"rate\": %lu,", clk_core_get_rate(c));
 	seq_printf(s, "\"accuracy\": %lu,", clk_core_get_accuracy(c));
 	seq_printf(s, "\"phase\": %d", clk_core_get_phase(c));
@@ -2217,6 +2569,58 @@ static const struct file_operations clk_dump_fops = {
 	.release	= single_release,
 };
 
+static const struct {
+	unsigned long flag;
+	const char *name;
+} clk_flags[] = {
+#define ENTRY(f) { f, __stringify(f) }
+	ENTRY(CLK_SET_RATE_GATE),
+	ENTRY(CLK_SET_PARENT_GATE),
+	ENTRY(CLK_SET_RATE_PARENT),
+	ENTRY(CLK_IGNORE_UNUSED),
+	ENTRY(CLK_IS_BASIC),
+	ENTRY(CLK_GET_RATE_NOCACHE),
+	ENTRY(CLK_SET_RATE_NO_REPARENT),
+	ENTRY(CLK_GET_ACCURACY_NOCACHE),
+	ENTRY(CLK_RECALC_NEW_RATES),
+	ENTRY(CLK_SET_RATE_UNGATE),
+	ENTRY(CLK_IS_CRITICAL),
+	ENTRY(CLK_OPS_PARENT_ENABLE),
+#undef ENTRY
+};
+
+static int clk_flags_dump(struct seq_file *s, void *data)
+{
+	struct clk_core *core = s->private;
+	unsigned long flags = core->flags;
+	unsigned int i;
+
+	for (i = 0; flags && i < ARRAY_SIZE(clk_flags); i++) {
+		if (flags & clk_flags[i].flag) {
+			seq_printf(s, "%s\n", clk_flags[i].name);
+			flags &= ~clk_flags[i].flag;
+		}
+	}
+	if (flags) {
+		/* Unknown flags */
+		seq_printf(s, "0x%lx\n", flags);
+	}
+
+	return 0;
+}
+
+static int clk_flags_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, clk_flags_dump, inode->i_private);
+}
+
+static const struct file_operations clk_flags_fops = {
+	.open		= clk_flags_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static int possible_parents_dump(struct seq_file *s, void *data)
 {
 	struct clk_core *core = s->private;
@@ -2258,43 +2662,46 @@ static int clk_debug_create_one(struct clk_core *core, struct dentry *pdentry)
 
 	core->dentry = d;
 
-	d = debugfs_create_u32("clk_rate", S_IRUGO, core->dentry,
-			(u32 *)&core->rate);
+	d = debugfs_create_ulong("clk_rate", 0444, core->dentry, &core->rate);
 	if (!d)
 		goto err_out;
 
-	d = debugfs_create_u32("clk_accuracy", S_IRUGO, core->dentry,
-			(u32 *)&core->accuracy);
+	d = debugfs_create_ulong("clk_accuracy", 0444, core->dentry,
+				 &core->accuracy);
 	if (!d)
 		goto err_out;
 
-	d = debugfs_create_u32("clk_phase", S_IRUGO, core->dentry,
-			(u32 *)&core->phase);
+	d = debugfs_create_u32("clk_phase", 0444, core->dentry, &core->phase);
 	if (!d)
 		goto err_out;
 
-	d = debugfs_create_x32("clk_flags", S_IRUGO, core->dentry,
-			(u32 *)&core->flags);
+	d = debugfs_create_file("clk_flags", 0444, core->dentry, core,
+				&clk_flags_fops);
 	if (!d)
 		goto err_out;
 
-	d = debugfs_create_u32("clk_prepare_count", S_IRUGO, core->dentry,
-			(u32 *)&core->prepare_count);
+	d = debugfs_create_u32("clk_prepare_count", 0444, core->dentry,
+			       &core->prepare_count);
 	if (!d)
 		goto err_out;
 
-	d = debugfs_create_u32("clk_enable_count", S_IRUGO, core->dentry,
-			(u32 *)&core->enable_count);
+	d = debugfs_create_u32("clk_enable_count", 0444, core->dentry,
+			       &core->enable_count);
 	if (!d)
 		goto err_out;
 
-	d = debugfs_create_u32("clk_notifier_count", S_IRUGO, core->dentry,
-			(u32 *)&core->notifier_count);
+	d = debugfs_create_u32("clk_protect_count", 0444, core->dentry,
+			       &core->protect_count);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_u32("clk_notifier_count", 0444, core->dentry,
+			       &core->notifier_count);
 	if (!d)
 		goto err_out;
 
 	if (core->num_parents > 1) {
-		d = debugfs_create_file("clk_possible_parents", S_IRUGO,
+		d = debugfs_create_file("clk_possible_parents", 0444,
 				core->dentry, core, &possible_parents_fops);
 		if (!d)
 			goto err_out;
@@ -2330,12 +2737,8 @@ static int clk_debug_register(struct clk_core *core)
 
 	mutex_lock(&clk_debug_lock);
 	hlist_add_head(&core->debug_node, &clk_debug_list);
-
-	if (!inited)
-		goto unlock;
-
-	ret = clk_debug_create_one(core, rootdir);
-unlock:
+	if (inited)
+		ret = clk_debug_create_one(core, rootdir);
 	mutex_unlock(&clk_debug_lock);
 
 	return ret;
@@ -2390,22 +2793,22 @@ static int __init clk_debug_init(void)
 	if (!rootdir)
 		return -ENOMEM;
 
-	d = debugfs_create_file("clk_summary", S_IRUGO, rootdir, &all_lists,
+	d = debugfs_create_file("clk_summary", 0444, rootdir, &all_lists,
 				&clk_summary_fops);
 	if (!d)
 		return -ENOMEM;
 
-	d = debugfs_create_file("clk_dump", S_IRUGO, rootdir, &all_lists,
+	d = debugfs_create_file("clk_dump", 0444, rootdir, &all_lists,
 				&clk_dump_fops);
 	if (!d)
 		return -ENOMEM;
 
-	d = debugfs_create_file("clk_orphan_summary", S_IRUGO, rootdir,
+	d = debugfs_create_file("clk_orphan_summary", 0444, rootdir,
 				&orphan_list, &clk_summary_fops);
 	if (!d)
 		return -ENOMEM;
 
-	d = debugfs_create_file("clk_orphan_dump", S_IRUGO, rootdir,
+	d = debugfs_create_file("clk_orphan_dump", 0444, rootdir,
 				&orphan_list, &clk_dump_fops);
 	if (!d)
 		return -ENOMEM;
@@ -2570,14 +2973,17 @@ static int __clk_core_init(struct clk_core *core)
 	 */
 	hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) {
 		struct clk_core *parent = __clk_init_parent(orphan);
+		unsigned long flags;
 
 		/*
 		 * we could call __clk_set_parent, but that would result in a
 		 * redundant call to the .set_rate op, if it exists
 		 */
 		if (parent) {
-			__clk_set_parent_before(orphan, parent);
-			__clk_set_parent_after(orphan, parent, NULL);
+			/* update the clk tree topology */
+			flags = clk_enable_lock();
+			clk_reparent(orphan, parent);
+			clk_enable_unlock(flags);
 			__clk_recalc_accuracies(orphan);
 			__clk_recalc_rates(orphan, 0);
 		}
@@ -2678,7 +3084,13 @@ struct clk *clk_register(struct device *dev, struct clk_hw *hw)
 		ret = -ENOMEM;
 		goto fail_name;
 	}
+
+	if (WARN_ON(!hw->init->ops)) {
+		ret = -EINVAL;
+		goto fail_ops;
+	}
 	core->ops = hw->init->ops;
+
 	if (dev && pm_runtime_enabled(dev))
 		core->dev = dev;
 	if (dev && dev->driver)
@@ -2740,6 +3152,7 @@ fail_parent_names_copy:
 		kfree_const(core->parent_names[i]);
 	kfree(core->parent_names);
 fail_parent_names:
+fail_ops:
 	kfree_const(core->name);
 fail_name:
 	kfree(core);
@@ -2851,7 +3264,7 @@ void clk_unregister(struct clk *clk)
 		/* Reparent all children to the orphan list. */
 		hlist_for_each_entry_safe(child, t, &clk->core->children,
 					  child_node)
-			clk_core_set_parent(child, NULL);
+			clk_core_set_parent_nolock(child, NULL);
 	}
 
 	hlist_del_init(&clk->core->child_node);
@@ -2859,6 +3272,11 @@ void clk_unregister(struct clk *clk)
 	if (clk->core->prepare_count)
 		pr_warn("%s: unregistering prepared clock: %s\n",
 					__func__, clk->core->name);
+
+	if (clk->core->protect_count)
+		pr_warn("%s: unregistering protected clock: %s\n",
+					__func__, clk->core->name);
+
 	kref_put(&clk->core->ref, __clk_release);
 unlock:
 	clk_prepare_unlock();
@@ -3017,6 +3435,18 @@ void __clk_put(struct clk *clk)
 
 	clk_prepare_lock();
 
+	/*
+	 * Before calling clk_put, all calls to clk_rate_exclusive_get() from a
+	 * given user should be balanced with calls to clk_rate_exclusive_put()
+	 * and by that same consumer
+	 */
+	if (WARN_ON(clk->exclusive_count)) {
+		/* We voiced our concern, let's sanitize the situation */
+		clk->core->protect_count -= (clk->exclusive_count - 1);
+		clk_core_rate_unprotect(clk->core);
+		clk->exclusive_count = 0;
+	}
+
 	hlist_del(&clk->clks_node);
 	if (clk->min_rate > clk->core->req_rate ||
 	    clk->max_rate < clk->core->req_rate)
@@ -3553,7 +3983,7 @@ static int parent_ready(struct device_node *np)
  * of_clk_detect_critical() - set CLK_IS_CRITICAL flag from Device Tree
  * @np: Device node pointer associated with clock provider
  * @index: clock index
- * @flags: pointer to clk_core->flags
+ * @flags: pointer to top-level framework flags
  *
  * Detects if the clock-critical property exists and, if so, sets the
  * corresponding CLK_IS_CRITICAL flag.
diff --git a/drivers/clk/clk.h b/drivers/clk/clk.h
index 00b35a13cdf3..70c0ba6336c1 100644
--- a/drivers/clk/clk.h
+++ b/drivers/clk/clk.h
@@ -20,6 +20,8 @@ struct clk *__of_clk_get_from_provider(struct of_phandle_args *clkspec,
 struct clk *__clk_create_clk(struct clk_hw *hw, const char *dev_id,
 			     const char *con_id);
 void __clk_free_clk(struct clk *clk);
+int __clk_get(struct clk *clk);
+void __clk_put(struct clk *clk);
 #else
 /* All these casts to avoid ifdefs in clkdev... */
 static inline struct clk *
@@ -32,5 +34,7 @@ static struct clk_hw *__clk_get_hw(struct clk *clk)
 {
 	return (struct clk_hw *)clk;
 }
+static inline int __clk_get(struct clk *clk) { return 1; }
+static inline void __clk_put(struct clk *clk) { }
 
 #endif
diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index 6b2f29df3f70..7513411140b6 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -256,7 +256,7 @@ vclkdev_alloc(struct clk_hw *hw, const char *con_id, const char *dev_fmt,
 {
 	struct clk_lookup_alloc *cla;
 
-	cla = __clkdev_alloc(sizeof(*cla));
+	cla = kzalloc(sizeof(*cla), GFP_KERNEL);
 	if (!cla)
 		return NULL;
 
diff --git a/drivers/clk/h8300/clk-div.c b/drivers/clk/h8300/clk-div.c
index 4ae624425e9d..d413ade95c99 100644
--- a/drivers/clk/h8300/clk-div.c
+++ b/drivers/clk/h8300/clk-div.c
@@ -24,13 +24,13 @@ static void __init h8300_div_clk_setup(struct device_node *node)
 
 	num_parents = of_clk_get_parent_count(node);
 	if (!num_parents) {
-		pr_err("%s: no parent found", clk_name);
+		pr_err("%s: no parent found\n", clk_name);
 		return;
 	}
 
 	divcr = of_iomap(node, 0);
 	if (divcr == NULL) {
-		pr_err("%s: failed to map divide register", clk_name);
+		pr_err("%s: failed to map divide register\n", clk_name);
 		goto error;
 	}
 	offset = (unsigned long)divcr & 3;
diff --git a/drivers/clk/h8300/clk-h8s2678.c b/drivers/clk/h8300/clk-h8s2678.c
index fc24b0b55a3d..b68045d8b921 100644
--- a/drivers/clk/h8300/clk-h8s2678.c
+++ b/drivers/clk/h8300/clk-h8s2678.c
@@ -93,7 +93,7 @@ static void __init h8s2678_pll_clk_setup(struct device_node *node)
 
 	num_parents = of_clk_get_parent_count(node);
 	if (!num_parents) {
-		pr_err("%s: no parent found", clk_name);
+		pr_err("%s: no parent found\n", clk_name);
 		return;
 	}
 
@@ -104,13 +104,13 @@ static void __init h8s2678_pll_clk_setup(struct device_node *node)
 
 	pll_clock->sckcr = of_iomap(node, 0);
 	if (pll_clock->sckcr == NULL) {
-		pr_err("%s: failed to map divide register", clk_name);
+		pr_err("%s: failed to map divide register\n", clk_name);
 		goto free_clock;
 	}
 
 	pll_clock->pllcr = of_iomap(node, 1);
 	if (pll_clock->pllcr == NULL) {
-		pr_err("%s: failed to map multiply register", clk_name);
+		pr_err("%s: failed to map multiply register\n", clk_name);
 		goto unmap_sckcr;
 	}
 
diff --git a/drivers/clk/hisilicon/Kconfig b/drivers/clk/hisilicon/Kconfig
index 7098bfd32b1b..1bd43550e4c8 100644
--- a/drivers/clk/hisilicon/Kconfig
+++ b/drivers/clk/hisilicon/Kconfig
@@ -49,3 +49,9 @@ config STUB_CLK_HI6220
 	default ARCH_HISI
 	help
 	  Build the Hisilicon Hi6220 stub clock driver.
+
+config STUB_CLK_HI3660
+	bool "Hi3660 Stub Clock Driver"
+	depends on COMMON_CLK_HI3660 && MAILBOX
+	help
+	  Build the Hisilicon Hi3660 stub clock driver.
diff --git a/drivers/clk/hisilicon/Makefile b/drivers/clk/hisilicon/Makefile
index 0e55612112af..4806fc2cb4ac 100644
--- a/drivers/clk/hisilicon/Makefile
+++ b/drivers/clk/hisilicon/Makefile
@@ -15,3 +15,4 @@ obj-$(CONFIG_COMMON_CLK_HI3798CV200)	+= crg-hi3798cv200.o
 obj-$(CONFIG_COMMON_CLK_HI6220)	+= clk-hi6220.o
 obj-$(CONFIG_RESET_HISI)	+= reset.o
 obj-$(CONFIG_STUB_CLK_HI6220)	+= clk-hi6220-stub.o
+obj-$(CONFIG_STUB_CLK_HI3660)	+= clk-hi3660-stub.o
diff --git a/drivers/clk/hisilicon/clk-hi3660-stub.c b/drivers/clk/hisilicon/clk-hi3660-stub.c
new file mode 100644
index 000000000000..9b6c72bbddf9
--- /dev/null
+++ b/drivers/clk/hisilicon/clk-hi3660-stub.c
@@ -0,0 +1,185 @@
+/*
+ * Hisilicon clock driver
+ *
+ * Copyright (c) 2013-2017 Hisilicon Limited.
+ * Copyright (c) 2017 Linaro Limited.
+ *
+ * Author: Kai Zhao <zhaokai1@hisilicon.com>
+ *	    Tao Wang <kevin.wangtao@hisilicon.com>
+ *	    Leo Yan <leo.yan@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/mailbox_client.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <dt-bindings/clock/hi3660-clock.h>
+
+#define HI3660_STUB_CLOCK_DATA		(0x70)
+#define MHZ				(1000 * 1000)
+
+#define DEFINE_CLK_STUB(_id, _cmd, _name)			\
+	{							\
+		.id = (_id),					\
+		.cmd = (_cmd),					\
+		.hw.init = &(struct clk_init_data) {		\
+			.name = #_name,				\
+			.ops = &hi3660_stub_clk_ops,		\
+			.num_parents = 0,			\
+			.flags = CLK_GET_RATE_NOCACHE,		\
+		},						\
+	},
+
+#define to_stub_clk(_hw) container_of(_hw, struct hi3660_stub_clk, hw)
+
+struct hi3660_stub_clk_chan {
+	struct mbox_client cl;
+	struct mbox_chan *mbox;
+};
+
+struct hi3660_stub_clk {
+	unsigned int id;
+	struct clk_hw hw;
+	unsigned int cmd;
+	unsigned int msg[8];
+	unsigned int rate;
+};
+
+static void __iomem *freq_reg;
+static struct hi3660_stub_clk_chan stub_clk_chan;
+
+static unsigned long hi3660_stub_clk_recalc_rate(struct clk_hw *hw,
+						 unsigned long parent_rate)
+{
+	struct hi3660_stub_clk *stub_clk = to_stub_clk(hw);
+
+	/*
+	 * LPM3 writes back the CPU frequency in shared SRAM so read
+	 * back the frequency.
+	 */
+	stub_clk->rate = readl(freq_reg + (stub_clk->id << 2)) * MHZ;
+	return stub_clk->rate;
+}
+
+static long hi3660_stub_clk_round_rate(struct clk_hw *hw, unsigned long rate,
+				       unsigned long *prate)
+{
+	/*
+	 * LPM3 handles rate rounding so just return whatever
+	 * rate is requested.
+	 */
+	return rate;
+}
+
+static int hi3660_stub_clk_set_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long parent_rate)
+{
+	struct hi3660_stub_clk *stub_clk = to_stub_clk(hw);
+
+	stub_clk->msg[0] = stub_clk->cmd;
+	stub_clk->msg[1] = rate / MHZ;
+
+	dev_dbg(stub_clk_chan.cl.dev, "set rate msg[0]=0x%x msg[1]=0x%x\n",
+		stub_clk->msg[0], stub_clk->msg[1]);
+
+	mbox_send_message(stub_clk_chan.mbox, stub_clk->msg);
+	mbox_client_txdone(stub_clk_chan.mbox, 0);
+
+	stub_clk->rate = rate;
+	return 0;
+}
+
+static const struct clk_ops hi3660_stub_clk_ops = {
+	.recalc_rate    = hi3660_stub_clk_recalc_rate,
+	.round_rate     = hi3660_stub_clk_round_rate,
+	.set_rate       = hi3660_stub_clk_set_rate,
+};
+
+static struct hi3660_stub_clk hi3660_stub_clks[HI3660_CLK_STUB_NUM] = {
+	DEFINE_CLK_STUB(HI3660_CLK_STUB_CLUSTER0, 0x0001030A, "cpu-cluster.0")
+	DEFINE_CLK_STUB(HI3660_CLK_STUB_CLUSTER1, 0x0002030A, "cpu-cluster.1")
+	DEFINE_CLK_STUB(HI3660_CLK_STUB_GPU, 0x0003030A, "clk-g3d")
+	DEFINE_CLK_STUB(HI3660_CLK_STUB_DDR, 0x00040309, "clk-ddrc")
+};
+
+static struct clk_hw *hi3660_stub_clk_hw_get(struct of_phandle_args *clkspec,
+					     void *data)
+{
+	unsigned int idx = clkspec->args[0];
+
+	if (idx >= HI3660_CLK_STUB_NUM) {
+		pr_err("%s: invalid index %u\n", __func__, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return &hi3660_stub_clks[idx].hw;
+}
+
+static int hi3660_stub_clk_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	unsigned int i;
+	int ret;
+
+	/* Use mailbox client without blocking */
+	stub_clk_chan.cl.dev = dev;
+	stub_clk_chan.cl.tx_done = NULL;
+	stub_clk_chan.cl.tx_block = false;
+	stub_clk_chan.cl.knows_txdone = false;
+
+	/* Allocate mailbox channel */
+	stub_clk_chan.mbox = mbox_request_channel(&stub_clk_chan.cl, 0);
+	if (IS_ERR(stub_clk_chan.mbox))
+		return PTR_ERR(stub_clk_chan.mbox);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	freq_reg = devm_ioremap(dev, res->start, resource_size(res));
+	if (!freq_reg)
+		return -ENOMEM;
+
+	freq_reg += HI3660_STUB_CLOCK_DATA;
+
+	for (i = 0; i < HI3660_CLK_STUB_NUM; i++) {
+		ret = devm_clk_hw_register(&pdev->dev, &hi3660_stub_clks[i].hw);
+		if (ret)
+			return ret;
+	}
+
+	return devm_of_clk_add_hw_provider(&pdev->dev, hi3660_stub_clk_hw_get,
+					   hi3660_stub_clks);
+}
+
+static const struct of_device_id hi3660_stub_clk_of_match[] = {
+	{ .compatible = "hisilicon,hi3660-stub-clk", },
+	{}
+};
+
+static struct platform_driver hi3660_stub_clk_driver = {
+	.probe	= hi3660_stub_clk_probe,
+	.driver = {
+		.name = "hi3660-stub-clk",
+		.of_match_table = hi3660_stub_clk_of_match,
+	},
+};
+
+static int __init hi3660_stub_clk_init(void)
+{
+	return platform_driver_register(&hi3660_stub_clk_driver);
+}
+subsys_initcall(hi3660_stub_clk_init);
diff --git a/drivers/clk/hisilicon/clkdivider-hi6220.c b/drivers/clk/hisilicon/clkdivider-hi6220.c
index a1c1f684ad58..9f46cf9dcc65 100644
--- a/drivers/clk/hisilicon/clkdivider-hi6220.c
+++ b/drivers/clk/hisilicon/clkdivider-hi6220.c
@@ -56,7 +56,7 @@ static unsigned long hi6220_clkdiv_recalc_rate(struct clk_hw *hw,
 	val &= div_mask(dclk->width);
 
 	return divider_recalc_rate(hw, parent_rate, val, dclk->table,
-				   CLK_DIVIDER_ROUND_CLOSEST);
+				   CLK_DIVIDER_ROUND_CLOSEST, dclk->width);
 }
 
 static long hi6220_clkdiv_round_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/clk/imx/clk-imx51-imx53.c b/drivers/clk/imx/clk-imx51-imx53.c
index 7bcaf270db11..c864992e6983 100644
--- a/drivers/clk/imx/clk-imx51-imx53.c
+++ b/drivers/clk/imx/clk-imx51-imx53.c
@@ -257,10 +257,6 @@ static void __init mx5_clocks_common_init(void __iomem *ccm_base)
 	clk[IMX5_CLK_VPU_SEL]		= imx_clk_mux("vpu_sel", MXC_CCM_CBCMR, 14, 2, vpu_sel, ARRAY_SIZE(vpu_sel));
 	clk[IMX5_CLK_VPU_GATE]		= imx_clk_gate2("vpu_gate", "vpu_sel", MXC_CCM_CCGR5, 6);
 	clk[IMX5_CLK_VPU_REFERENCE_GATE] = imx_clk_gate2("vpu_reference_gate", "osc", MXC_CCM_CCGR5, 8);
-	clk[IMX5_CLK_UART4_IPG_GATE]	= imx_clk_gate2("uart4_ipg_gate", "ipg", MXC_CCM_CCGR7, 8);
-	clk[IMX5_CLK_UART4_PER_GATE]	= imx_clk_gate2("uart4_per_gate", "uart_root", MXC_CCM_CCGR7, 10);
-	clk[IMX5_CLK_UART5_IPG_GATE]	= imx_clk_gate2("uart5_ipg_gate", "ipg", MXC_CCM_CCGR7, 12);
-	clk[IMX5_CLK_UART5_PER_GATE]	= imx_clk_gate2("uart5_per_gate", "uart_root", MXC_CCM_CCGR7, 14);
 	clk[IMX5_CLK_GPC_DVFS]		= imx_clk_gate2("gpc_dvfs", "dummy", MXC_CCM_CCGR5, 24);
 
 	clk[IMX5_CLK_SSI_APM]		= imx_clk_mux("ssi_apm", MXC_CCM_CSCMR1, 8, 2, ssi_apm_sels, ARRAY_SIZE(ssi_apm_sels));
@@ -361,6 +357,10 @@ static void __init mx50_clocks_init(struct device_node *np)
 	clk[IMX5_CLK_USB_PHY1_GATE]	= imx_clk_gate2("usb_phy1_gate", "usb_phy_sel", MXC_CCM_CCGR4, 10);
 	clk[IMX5_CLK_USB_PHY2_GATE]	= imx_clk_gate2("usb_phy2_gate", "usb_phy_sel", MXC_CCM_CCGR4, 12);
 	clk[IMX5_CLK_I2C3_GATE]		= imx_clk_gate2("i2c3_gate", "per_root", MXC_CCM_CCGR1, 22);
+	clk[IMX5_CLK_UART4_IPG_GATE]	= imx_clk_gate2("uart4_ipg_gate", "ipg", MXC_CCM_CCGR7, 8);
+	clk[IMX5_CLK_UART4_PER_GATE]	= imx_clk_gate2("uart4_per_gate", "uart_root", MXC_CCM_CCGR7, 10);
+	clk[IMX5_CLK_UART5_IPG_GATE]	= imx_clk_gate2("uart5_ipg_gate", "ipg", MXC_CCM_CCGR7, 12);
+	clk[IMX5_CLK_UART5_PER_GATE]	= imx_clk_gate2("uart5_per_gate", "uart_root", MXC_CCM_CCGR7, 14);
 
 	clk[IMX5_CLK_CKO1_SEL]		= imx_clk_mux("cko1_sel", MXC_CCM_CCOSR, 0, 4,
 						mx53_cko1_sel, ARRAY_SIZE(mx53_cko1_sel));
@@ -562,6 +562,10 @@ static void __init mx53_clocks_init(struct device_node *np)
 	clk[IMX5_CLK_IEEE1588_PRED]	= imx_clk_divider("ieee1588_pred", "ieee1588_sel", MXC_CCM_CSCDR2, 6, 3);
 	clk[IMX5_CLK_IEEE1588_PODF]	= imx_clk_divider("ieee1588_podf", "ieee1588_pred", MXC_CCM_CSCDR2, 0, 6);
 	clk[IMX5_CLK_IEEE1588_GATE]	= imx_clk_gate2("ieee1588_serial_gate", "ieee1588_podf", MXC_CCM_CCGR7, 6);
+	clk[IMX5_CLK_UART4_IPG_GATE]	= imx_clk_gate2("uart4_ipg_gate", "ipg", MXC_CCM_CCGR7, 8);
+	clk[IMX5_CLK_UART4_PER_GATE]	= imx_clk_gate2("uart4_per_gate", "uart_root", MXC_CCM_CCGR7, 10);
+	clk[IMX5_CLK_UART5_IPG_GATE]	= imx_clk_gate2("uart5_ipg_gate", "ipg", MXC_CCM_CCGR7, 12);
+	clk[IMX5_CLK_UART5_PER_GATE]	= imx_clk_gate2("uart5_per_gate", "uart_root", MXC_CCM_CCGR7, 14);
 
 	clk[IMX5_CLK_CKO1_SEL]		= imx_clk_mux("cko1_sel", MXC_CCM_CCOSR, 0, 4,
 						mx53_cko1_sel, ARRAY_SIZE(mx53_cko1_sel));
diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig
index 59dc0aad553c..1f9ea0f21df1 100644
--- a/drivers/clk/mediatek/Kconfig
+++ b/drivers/clk/mediatek/Kconfig
@@ -1,136 +1,140 @@
 #
-# MediaTek SoC drivers
+# MediaTek Clock Drivers
 #
+menu "Clock driver for MediaTek SoC"
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+
 config COMMON_CLK_MEDIATEK
 	bool
+	select RESET_CONTROLLER
 	---help---
-	  Mediatek SoCs' clock support.
+	  MediaTek SoCs' clock support.
 
 config COMMON_CLK_MT2701
-	bool "Clock driver for Mediatek MT2701"
+	bool "Clock driver for MediaTek MT2701"
 	depends on (ARCH_MEDIATEK && ARM) || COMPILE_TEST
 	select COMMON_CLK_MEDIATEK
 	default ARCH_MEDIATEK && ARM
 	---help---
-	  This driver supports Mediatek MT2701 basic clocks.
+	  This driver supports MediaTek MT2701 basic clocks.
 
 config COMMON_CLK_MT2701_MMSYS
-	bool "Clock driver for Mediatek MT2701 mmsys"
+	bool "Clock driver for MediaTek MT2701 mmsys"
 	depends on COMMON_CLK_MT2701
 	---help---
-	  This driver supports Mediatek MT2701 mmsys clocks.
+	  This driver supports MediaTek MT2701 mmsys clocks.
 
 config COMMON_CLK_MT2701_IMGSYS
-	bool "Clock driver for Mediatek MT2701 imgsys"
+	bool "Clock driver for MediaTek MT2701 imgsys"
 	depends on COMMON_CLK_MT2701
 	---help---
-	  This driver supports Mediatek MT2701 imgsys clocks.
+	  This driver supports MediaTek MT2701 imgsys clocks.
 
 config COMMON_CLK_MT2701_VDECSYS
-	bool "Clock driver for Mediatek MT2701 vdecsys"
+	bool "Clock driver for MediaTek MT2701 vdecsys"
 	depends on COMMON_CLK_MT2701
 	---help---
-	  This driver supports Mediatek MT2701 vdecsys clocks.
+	  This driver supports MediaTek MT2701 vdecsys clocks.
 
 config COMMON_CLK_MT2701_HIFSYS
-	bool "Clock driver for Mediatek MT2701 hifsys"
+	bool "Clock driver for MediaTek MT2701 hifsys"
 	depends on COMMON_CLK_MT2701
 	---help---
-	  This driver supports Mediatek MT2701 hifsys clocks.
+	  This driver supports MediaTek MT2701 hifsys clocks.
 
 config COMMON_CLK_MT2701_ETHSYS
-	bool "Clock driver for Mediatek MT2701 ethsys"
+	bool "Clock driver for MediaTek MT2701 ethsys"
 	depends on COMMON_CLK_MT2701
 	---help---
-	  This driver supports Mediatek MT2701 ethsys clocks.
+	  This driver supports MediaTek MT2701 ethsys clocks.
 
 config COMMON_CLK_MT2701_BDPSYS
-	bool "Clock driver for Mediatek MT2701 bdpsys"
+	bool "Clock driver for MediaTek MT2701 bdpsys"
 	depends on COMMON_CLK_MT2701
 	---help---
-	  This driver supports Mediatek MT2701 bdpsys clocks.
+	  This driver supports MediaTek MT2701 bdpsys clocks.
 
 config COMMON_CLK_MT2712
-	bool "Clock driver for Mediatek MT2712"
+	bool "Clock driver for MediaTek MT2712"
 	depends on (ARCH_MEDIATEK && ARM64) || COMPILE_TEST
 	select COMMON_CLK_MEDIATEK
 	default ARCH_MEDIATEK && ARM64
 	---help---
-	  This driver supports Mediatek MT2712 basic clocks.
+	  This driver supports MediaTek MT2712 basic clocks.
 
 config COMMON_CLK_MT2712_BDPSYS
-	bool "Clock driver for Mediatek MT2712 bdpsys"
+	bool "Clock driver for MediaTek MT2712 bdpsys"
 	depends on COMMON_CLK_MT2712
 	---help---
-	  This driver supports Mediatek MT2712 bdpsys clocks.
+	  This driver supports MediaTek MT2712 bdpsys clocks.
 
 config COMMON_CLK_MT2712_IMGSYS
-	bool "Clock driver for Mediatek MT2712 imgsys"
+	bool "Clock driver for MediaTek MT2712 imgsys"
 	depends on COMMON_CLK_MT2712
 	---help---
-	  This driver supports Mediatek MT2712 imgsys clocks.
+	  This driver supports MediaTek MT2712 imgsys clocks.
 
 config COMMON_CLK_MT2712_JPGDECSYS
-	bool "Clock driver for Mediatek MT2712 jpgdecsys"
+	bool "Clock driver for MediaTek MT2712 jpgdecsys"
 	depends on COMMON_CLK_MT2712
 	---help---
-	  This driver supports Mediatek MT2712 jpgdecsys clocks.
+	  This driver supports MediaTek MT2712 jpgdecsys clocks.
 
 config COMMON_CLK_MT2712_MFGCFG
-	bool "Clock driver for Mediatek MT2712 mfgcfg"
+	bool "Clock driver for MediaTek MT2712 mfgcfg"
 	depends on COMMON_CLK_MT2712
 	---help---
-	  This driver supports Mediatek MT2712 mfgcfg clocks.
+	  This driver supports MediaTek MT2712 mfgcfg clocks.
 
 config COMMON_CLK_MT2712_MMSYS
-	bool "Clock driver for Mediatek MT2712 mmsys"
+	bool "Clock driver for MediaTek MT2712 mmsys"
 	depends on COMMON_CLK_MT2712
 	---help---
-	  This driver supports Mediatek MT2712 mmsys clocks.
+	  This driver supports MediaTek MT2712 mmsys clocks.
 
 config COMMON_CLK_MT2712_VDECSYS
-	bool "Clock driver for Mediatek MT2712 vdecsys"
+	bool "Clock driver for MediaTek MT2712 vdecsys"
 	depends on COMMON_CLK_MT2712
 	---help---
-	  This driver supports Mediatek MT2712 vdecsys clocks.
+	  This driver supports MediaTek MT2712 vdecsys clocks.
 
 config COMMON_CLK_MT2712_VENCSYS
-	bool "Clock driver for Mediatek MT2712 vencsys"
+	bool "Clock driver for MediaTek MT2712 vencsys"
 	depends on COMMON_CLK_MT2712
 	---help---
-	  This driver supports Mediatek MT2712 vencsys clocks.
+	  This driver supports MediaTek MT2712 vencsys clocks.
 
 config COMMON_CLK_MT6797
-       bool "Clock driver for Mediatek MT6797"
+       bool "Clock driver for MediaTek MT6797"
        depends on (ARCH_MEDIATEK && ARM64) || COMPILE_TEST
        select COMMON_CLK_MEDIATEK
        default ARCH_MEDIATEK && ARM64
        ---help---
-         This driver supports Mediatek MT6797 basic clocks.
+         This driver supports MediaTek MT6797 basic clocks.
 
 config COMMON_CLK_MT6797_MMSYS
-       bool "Clock driver for Mediatek MT6797 mmsys"
+       bool "Clock driver for MediaTek MT6797 mmsys"
        depends on COMMON_CLK_MT6797
        ---help---
-         This driver supports Mediatek MT6797 mmsys clocks.
+         This driver supports MediaTek MT6797 mmsys clocks.
 
 config COMMON_CLK_MT6797_IMGSYS
-       bool "Clock driver for Mediatek MT6797 imgsys"
+       bool "Clock driver for MediaTek MT6797 imgsys"
        depends on COMMON_CLK_MT6797
        ---help---
-         This driver supports Mediatek MT6797 imgsys clocks.
+         This driver supports MediaTek MT6797 imgsys clocks.
 
 config COMMON_CLK_MT6797_VDECSYS
-       bool "Clock driver for Mediatek MT6797 vdecsys"
+       bool "Clock driver for MediaTek MT6797 vdecsys"
        depends on COMMON_CLK_MT6797
        ---help---
-         This driver supports Mediatek MT6797 vdecsys clocks.
+         This driver supports MediaTek MT6797 vdecsys clocks.
 
 config COMMON_CLK_MT6797_VENCSYS
-       bool "Clock driver for Mediatek MT6797 vencsys"
+       bool "Clock driver for MediaTek MT6797 vencsys"
        depends on COMMON_CLK_MT6797
        ---help---
-         This driver supports Mediatek MT6797 vencsys clocks.
+         This driver supports MediaTek MT6797 vencsys clocks.
 
 config COMMON_CLK_MT7622
 	bool "Clock driver for MediaTek MT7622"
@@ -163,17 +167,18 @@ config COMMON_CLK_MT7622_AUDSYS
 	  to audio consumers such as I2S and TDM.
 
 config COMMON_CLK_MT8135
-	bool "Clock driver for Mediatek MT8135"
+	bool "Clock driver for MediaTek MT8135"
 	depends on (ARCH_MEDIATEK && ARM) || COMPILE_TEST
 	select COMMON_CLK_MEDIATEK
 	default ARCH_MEDIATEK && ARM
 	---help---
-	  This driver supports Mediatek MT8135 clocks.
+	  This driver supports MediaTek MT8135 clocks.
 
 config COMMON_CLK_MT8173
-	bool "Clock driver for Mediatek MT8173"
+	bool "Clock driver for MediaTek MT8173"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	select COMMON_CLK_MEDIATEK
 	default ARCH_MEDIATEK
 	---help---
-	  This driver supports Mediatek MT8173 clocks.
+	  This driver supports MediaTek MT8173 clocks.
+endmenu
diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile
index c421ffcd49ff..5160fdc4bbb8 100644
--- a/drivers/clk/mediatek/Makefile
+++ b/drivers/clk/mediatek/Makefile
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_COMMON_CLK_MEDIATEK) += clk-mtk.o clk-pll.o clk-gate.o clk-apmixed.o clk-cpumux.o
-obj-$(CONFIG_RESET_CONTROLLER) += reset.o
+obj-$(CONFIG_COMMON_CLK_MEDIATEK) += clk-mtk.o clk-pll.o clk-gate.o clk-apmixed.o clk-cpumux.o reset.o
 obj-$(CONFIG_COMMON_CLK_MT6797) += clk-mt6797.o
 obj-$(CONFIG_COMMON_CLK_MT6797_IMGSYS) += clk-mt6797-img.o
 obj-$(CONFIG_COMMON_CLK_MT6797_MMSYS) += clk-mt6797-mm.o
diff --git a/drivers/clk/mediatek/clk-mtk.h b/drivers/clk/mediatek/clk-mtk.h
index f10250dcece4..f83c2bbb677e 100644
--- a/drivers/clk/mediatek/clk-mtk.h
+++ b/drivers/clk/mediatek/clk-mtk.h
@@ -20,6 +20,7 @@
 #include <linux/clk-provider.h>
 
 struct clk;
+struct clk_onecell_data;
 
 #define MAX_MUX_GATE_BIT	31
 #define INVALID_MUX_GATE_BIT	(MAX_MUX_GATE_BIT + 1)
@@ -228,14 +229,7 @@ void mtk_clk_register_plls(struct device_node *node,
 struct clk *mtk_clk_register_ref2usb_tx(const char *name,
 			const char *parent_name, void __iomem *reg);
 
-#ifdef CONFIG_RESET_CONTROLLER
 void mtk_register_reset_controller(struct device_node *np,
 			unsigned int num_regs, int regofs);
-#else
-static inline void mtk_register_reset_controller(struct device_node *np,
-			unsigned int num_regs, int regofs)
-{
-}
-#endif
 
 #endif /* __DRV_CLK_MTK_H */
diff --git a/drivers/clk/meson/Kconfig b/drivers/clk/meson/Kconfig
index d2d0174a6eca..7694302c70a4 100644
--- a/drivers/clk/meson/Kconfig
+++ b/drivers/clk/meson/Kconfig
@@ -19,3 +19,11 @@ config COMMON_CLK_GXBB
 	help
 	  Support for the clock controller on AmLogic S905 devices, aka gxbb.
 	  Say Y if you want peripherals and CPU frequency scaling to work.
+
+config COMMON_CLK_AXG
+	bool
+	depends on COMMON_CLK_AMLOGIC
+	select RESET_CONTROLLER
+	help
+	  Support for the clock controller on AmLogic A113D devices, aka axg.
+	  Say Y if you want peripherals and CPU frequency scaling to work.
diff --git a/drivers/clk/meson/Makefile b/drivers/clk/meson/Makefile
index b139d41b25da..3c03ce583798 100644
--- a/drivers/clk/meson/Makefile
+++ b/drivers/clk/meson/Makefile
@@ -5,3 +5,4 @@
 obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-pll.o clk-cpu.o clk-mpll.o clk-audio-divider.o
 obj-$(CONFIG_COMMON_CLK_MESON8B) += meson8b.o
 obj-$(CONFIG_COMMON_CLK_GXBB)	 += gxbb.o gxbb-aoclk.o gxbb-aoclk-regmap.o gxbb-aoclk-32k.o
+obj-$(CONFIG_COMMON_CLK_AXG)	 += axg.o
diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c
new file mode 100644
index 000000000000..1294f3ad7cd5
--- /dev/null
+++ b/drivers/clk/meson/axg.c
@@ -0,0 +1,938 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * AmLogic Meson-AXG Clock Controller Driver
+ *
+ * Copyright (c) 2016 Baylibre SAS.
+ * Author: Michael Turquette <mturquette@baylibre.com>
+ *
+ * Copyright (c) 2017 Amlogic, inc.
+ * Author: Qiufang Dai <qiufang.dai@amlogic.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/init.h>
+
+#include "clkc.h"
+#include "axg.h"
+
+static DEFINE_SPINLOCK(meson_clk_lock);
+
+static const struct pll_rate_table sys_pll_rate_table[] = {
+	PLL_RATE(24000000, 56, 1, 2),
+	PLL_RATE(48000000, 64, 1, 2),
+	PLL_RATE(72000000, 72, 1, 2),
+	PLL_RATE(96000000, 64, 1, 2),
+	PLL_RATE(120000000, 80, 1, 2),
+	PLL_RATE(144000000, 96, 1, 2),
+	PLL_RATE(168000000, 56, 1, 1),
+	PLL_RATE(192000000, 64, 1, 1),
+	PLL_RATE(216000000, 72, 1, 1),
+	PLL_RATE(240000000, 80, 1, 1),
+	PLL_RATE(264000000, 88, 1, 1),
+	PLL_RATE(288000000, 96, 1, 1),
+	PLL_RATE(312000000, 52, 1, 2),
+	PLL_RATE(336000000, 56, 1, 2),
+	PLL_RATE(360000000, 60, 1, 2),
+	PLL_RATE(384000000, 64, 1, 2),
+	PLL_RATE(408000000, 68, 1, 2),
+	PLL_RATE(432000000, 72, 1, 2),
+	PLL_RATE(456000000, 76, 1, 2),
+	PLL_RATE(480000000, 80, 1, 2),
+	PLL_RATE(504000000, 84, 1, 2),
+	PLL_RATE(528000000, 88, 1, 2),
+	PLL_RATE(552000000, 92, 1, 2),
+	PLL_RATE(576000000, 96, 1, 2),
+	PLL_RATE(600000000, 50, 1, 1),
+	PLL_RATE(624000000, 52, 1, 1),
+	PLL_RATE(648000000, 54, 1, 1),
+	PLL_RATE(672000000, 56, 1, 1),
+	PLL_RATE(696000000, 58, 1, 1),
+	PLL_RATE(720000000, 60, 1, 1),
+	PLL_RATE(744000000, 62, 1, 1),
+	PLL_RATE(768000000, 64, 1, 1),
+	PLL_RATE(792000000, 66, 1, 1),
+	PLL_RATE(816000000, 68, 1, 1),
+	PLL_RATE(840000000, 70, 1, 1),
+	PLL_RATE(864000000, 72, 1, 1),
+	PLL_RATE(888000000, 74, 1, 1),
+	PLL_RATE(912000000, 76, 1, 1),
+	PLL_RATE(936000000, 78, 1, 1),
+	PLL_RATE(960000000, 80, 1, 1),
+	PLL_RATE(984000000, 82, 1, 1),
+	PLL_RATE(1008000000, 84, 1, 1),
+	PLL_RATE(1032000000, 86, 1, 1),
+	PLL_RATE(1056000000, 88, 1, 1),
+	PLL_RATE(1080000000, 90, 1, 1),
+	PLL_RATE(1104000000, 92, 1, 1),
+	PLL_RATE(1128000000, 94, 1, 1),
+	PLL_RATE(1152000000, 96, 1, 1),
+	PLL_RATE(1176000000, 98, 1, 1),
+	PLL_RATE(1200000000, 50, 1, 0),
+	PLL_RATE(1224000000, 51, 1, 0),
+	PLL_RATE(1248000000, 52, 1, 0),
+	PLL_RATE(1272000000, 53, 1, 0),
+	PLL_RATE(1296000000, 54, 1, 0),
+	PLL_RATE(1320000000, 55, 1, 0),
+	PLL_RATE(1344000000, 56, 1, 0),
+	PLL_RATE(1368000000, 57, 1, 0),
+	PLL_RATE(1392000000, 58, 1, 0),
+	PLL_RATE(1416000000, 59, 1, 0),
+	PLL_RATE(1440000000, 60, 1, 0),
+	PLL_RATE(1464000000, 61, 1, 0),
+	PLL_RATE(1488000000, 62, 1, 0),
+	PLL_RATE(1512000000, 63, 1, 0),
+	PLL_RATE(1536000000, 64, 1, 0),
+	PLL_RATE(1560000000, 65, 1, 0),
+	PLL_RATE(1584000000, 66, 1, 0),
+	PLL_RATE(1608000000, 67, 1, 0),
+	PLL_RATE(1632000000, 68, 1, 0),
+	PLL_RATE(1656000000, 68, 1, 0),
+	PLL_RATE(1680000000, 68, 1, 0),
+	PLL_RATE(1704000000, 68, 1, 0),
+	PLL_RATE(1728000000, 69, 1, 0),
+	PLL_RATE(1752000000, 69, 1, 0),
+	PLL_RATE(1776000000, 69, 1, 0),
+	PLL_RATE(1800000000, 69, 1, 0),
+	PLL_RATE(1824000000, 70, 1, 0),
+	PLL_RATE(1848000000, 70, 1, 0),
+	PLL_RATE(1872000000, 70, 1, 0),
+	PLL_RATE(1896000000, 70, 1, 0),
+	PLL_RATE(1920000000, 71, 1, 0),
+	PLL_RATE(1944000000, 71, 1, 0),
+	PLL_RATE(1968000000, 71, 1, 0),
+	PLL_RATE(1992000000, 71, 1, 0),
+	PLL_RATE(2016000000, 72, 1, 0),
+	PLL_RATE(2040000000, 72, 1, 0),
+	PLL_RATE(2064000000, 72, 1, 0),
+	PLL_RATE(2088000000, 72, 1, 0),
+	PLL_RATE(2112000000, 73, 1, 0),
+	{ /* sentinel */ },
+};
+
+static struct meson_clk_pll axg_fixed_pll = {
+	.m = {
+		.reg_off = HHI_MPLL_CNTL,
+		.shift   = 0,
+		.width   = 9,
+	},
+	.n = {
+		.reg_off = HHI_MPLL_CNTL,
+		.shift   = 9,
+		.width   = 5,
+	},
+	.od = {
+		.reg_off = HHI_MPLL_CNTL,
+		.shift   = 16,
+		.width   = 2,
+	},
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "fixed_pll",
+		.ops = &meson_clk_pll_ro_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+	},
+};
+
+static struct meson_clk_pll axg_sys_pll = {
+	.m = {
+		.reg_off = HHI_SYS_PLL_CNTL,
+		.shift   = 0,
+		.width   = 9,
+	},
+	.n = {
+		.reg_off = HHI_SYS_PLL_CNTL,
+		.shift   = 9,
+		.width   = 5,
+	},
+	.od = {
+		.reg_off = HHI_SYS_PLL_CNTL,
+		.shift   = 10,
+		.width   = 2,
+	},
+	.rate_table = sys_pll_rate_table,
+	.rate_count = ARRAY_SIZE(sys_pll_rate_table),
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "sys_pll",
+		.ops = &meson_clk_pll_ro_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+		.flags = CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static const struct pll_rate_table axg_gp0_pll_rate_table[] = {
+	PLL_RATE(240000000, 40, 1, 2),
+	PLL_RATE(246000000, 41, 1, 2),
+	PLL_RATE(252000000, 42, 1, 2),
+	PLL_RATE(258000000, 43, 1, 2),
+	PLL_RATE(264000000, 44, 1, 2),
+	PLL_RATE(270000000, 45, 1, 2),
+	PLL_RATE(276000000, 46, 1, 2),
+	PLL_RATE(282000000, 47, 1, 2),
+	PLL_RATE(288000000, 48, 1, 2),
+	PLL_RATE(294000000, 49, 1, 2),
+	PLL_RATE(300000000, 50, 1, 2),
+	PLL_RATE(306000000, 51, 1, 2),
+	PLL_RATE(312000000, 52, 1, 2),
+	PLL_RATE(318000000, 53, 1, 2),
+	PLL_RATE(324000000, 54, 1, 2),
+	PLL_RATE(330000000, 55, 1, 2),
+	PLL_RATE(336000000, 56, 1, 2),
+	PLL_RATE(342000000, 57, 1, 2),
+	PLL_RATE(348000000, 58, 1, 2),
+	PLL_RATE(354000000, 59, 1, 2),
+	PLL_RATE(360000000, 60, 1, 2),
+	PLL_RATE(366000000, 61, 1, 2),
+	PLL_RATE(372000000, 62, 1, 2),
+	PLL_RATE(378000000, 63, 1, 2),
+	PLL_RATE(384000000, 64, 1, 2),
+	PLL_RATE(390000000, 65, 1, 3),
+	PLL_RATE(396000000, 66, 1, 3),
+	PLL_RATE(402000000, 67, 1, 3),
+	PLL_RATE(408000000, 68, 1, 3),
+	PLL_RATE(480000000, 40, 1, 1),
+	PLL_RATE(492000000, 41, 1, 1),
+	PLL_RATE(504000000, 42, 1, 1),
+	PLL_RATE(516000000, 43, 1, 1),
+	PLL_RATE(528000000, 44, 1, 1),
+	PLL_RATE(540000000, 45, 1, 1),
+	PLL_RATE(552000000, 46, 1, 1),
+	PLL_RATE(564000000, 47, 1, 1),
+	PLL_RATE(576000000, 48, 1, 1),
+	PLL_RATE(588000000, 49, 1, 1),
+	PLL_RATE(600000000, 50, 1, 1),
+	PLL_RATE(612000000, 51, 1, 1),
+	PLL_RATE(624000000, 52, 1, 1),
+	PLL_RATE(636000000, 53, 1, 1),
+	PLL_RATE(648000000, 54, 1, 1),
+	PLL_RATE(660000000, 55, 1, 1),
+	PLL_RATE(672000000, 56, 1, 1),
+	PLL_RATE(684000000, 57, 1, 1),
+	PLL_RATE(696000000, 58, 1, 1),
+	PLL_RATE(708000000, 59, 1, 1),
+	PLL_RATE(720000000, 60, 1, 1),
+	PLL_RATE(732000000, 61, 1, 1),
+	PLL_RATE(744000000, 62, 1, 1),
+	PLL_RATE(756000000, 63, 1, 1),
+	PLL_RATE(768000000, 64, 1, 1),
+	PLL_RATE(780000000, 65, 1, 1),
+	PLL_RATE(792000000, 66, 1, 1),
+	PLL_RATE(804000000, 67, 1, 1),
+	PLL_RATE(816000000, 68, 1, 1),
+	PLL_RATE(960000000, 40, 1, 0),
+	PLL_RATE(984000000, 41, 1, 0),
+	PLL_RATE(1008000000, 42, 1, 0),
+	PLL_RATE(1032000000, 43, 1, 0),
+	PLL_RATE(1056000000, 44, 1, 0),
+	PLL_RATE(1080000000, 45, 1, 0),
+	PLL_RATE(1104000000, 46, 1, 0),
+	PLL_RATE(1128000000, 47, 1, 0),
+	PLL_RATE(1152000000, 48, 1, 0),
+	PLL_RATE(1176000000, 49, 1, 0),
+	PLL_RATE(1200000000, 50, 1, 0),
+	PLL_RATE(1224000000, 51, 1, 0),
+	PLL_RATE(1248000000, 52, 1, 0),
+	PLL_RATE(1272000000, 53, 1, 0),
+	PLL_RATE(1296000000, 54, 1, 0),
+	PLL_RATE(1320000000, 55, 1, 0),
+	PLL_RATE(1344000000, 56, 1, 0),
+	PLL_RATE(1368000000, 57, 1, 0),
+	PLL_RATE(1392000000, 58, 1, 0),
+	PLL_RATE(1416000000, 59, 1, 0),
+	PLL_RATE(1440000000, 60, 1, 0),
+	PLL_RATE(1464000000, 61, 1, 0),
+	PLL_RATE(1488000000, 62, 1, 0),
+	PLL_RATE(1512000000, 63, 1, 0),
+	PLL_RATE(1536000000, 64, 1, 0),
+	PLL_RATE(1560000000, 65, 1, 0),
+	PLL_RATE(1584000000, 66, 1, 0),
+	PLL_RATE(1608000000, 67, 1, 0),
+	PLL_RATE(1632000000, 68, 1, 0),
+	{ /* sentinel */ },
+};
+
+static struct pll_params_table axg_gp0_params_table[] = {
+	PLL_PARAM(HHI_GP0_PLL_CNTL, 0x40010250),
+	PLL_PARAM(HHI_GP0_PLL_CNTL1, 0xc084a000),
+	PLL_PARAM(HHI_GP0_PLL_CNTL2, 0xb75020be),
+	PLL_PARAM(HHI_GP0_PLL_CNTL3, 0x0a59a288),
+	PLL_PARAM(HHI_GP0_PLL_CNTL4, 0xc000004d),
+	PLL_PARAM(HHI_GP0_PLL_CNTL5, 0x00078000),
+};
+
+static struct meson_clk_pll axg_gp0_pll = {
+	.m = {
+		.reg_off = HHI_GP0_PLL_CNTL,
+		.shift   = 0,
+		.width   = 9,
+	},
+	.n = {
+		.reg_off = HHI_GP0_PLL_CNTL,
+		.shift   = 9,
+		.width   = 5,
+	},
+	.od = {
+		.reg_off = HHI_GP0_PLL_CNTL,
+		.shift   = 16,
+		.width   = 2,
+	},
+	.params = {
+		.params_table = axg_gp0_params_table,
+		.params_count =	ARRAY_SIZE(axg_gp0_params_table),
+		.no_init_reset = true,
+		.reset_lock_loop = true,
+	},
+	.rate_table = axg_gp0_pll_rate_table,
+	.rate_count = ARRAY_SIZE(axg_gp0_pll_rate_table),
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "gp0_pll",
+		.ops = &meson_clk_pll_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+	},
+};
+
+
+static struct clk_fixed_factor axg_fclk_div2 = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div2",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor axg_fclk_div3 = {
+	.mult = 1,
+	.div = 3,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div3",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor axg_fclk_div4 = {
+	.mult = 1,
+	.div = 4,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div4",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor axg_fclk_div5 = {
+	.mult = 1,
+	.div = 5,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div5",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor axg_fclk_div7 = {
+	.mult = 1,
+	.div = 7,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div7",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct meson_clk_mpll axg_mpll0 = {
+	.sdm = {
+		.reg_off = HHI_MPLL_CNTL7,
+		.shift   = 0,
+		.width   = 14,
+	},
+	.sdm_en = {
+		.reg_off = HHI_MPLL_CNTL7,
+		.shift   = 15,
+		.width	 = 1,
+	},
+	.n2 = {
+		.reg_off = HHI_MPLL_CNTL7,
+		.shift   = 16,
+		.width   = 9,
+	},
+	.en = {
+		.reg_off = HHI_MPLL_CNTL7,
+		.shift   = 14,
+		.width	 = 1,
+	},
+	.ssen = {
+		.reg_off = HHI_MPLL_CNTL,
+		.shift   = 25,
+		.width	 = 1,
+	},
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpll0",
+		.ops = &meson_clk_mpll_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct meson_clk_mpll axg_mpll1 = {
+	.sdm = {
+		.reg_off = HHI_MPLL_CNTL8,
+		.shift   = 0,
+		.width   = 14,
+	},
+	.sdm_en = {
+		.reg_off = HHI_MPLL_CNTL8,
+		.shift   = 15,
+		.width	 = 1,
+	},
+	.n2 = {
+		.reg_off = HHI_MPLL_CNTL8,
+		.shift   = 16,
+		.width   = 9,
+	},
+	.en = {
+		.reg_off = HHI_MPLL_CNTL8,
+		.shift   = 14,
+		.width	 = 1,
+	},
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpll1",
+		.ops = &meson_clk_mpll_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct meson_clk_mpll axg_mpll2 = {
+	.sdm = {
+		.reg_off = HHI_MPLL_CNTL9,
+		.shift   = 0,
+		.width   = 14,
+	},
+	.sdm_en = {
+		.reg_off = HHI_MPLL_CNTL9,
+		.shift   = 15,
+		.width	 = 1,
+	},
+	.n2 = {
+		.reg_off = HHI_MPLL_CNTL9,
+		.shift   = 16,
+		.width   = 9,
+	},
+	.en = {
+		.reg_off = HHI_MPLL_CNTL9,
+		.shift   = 14,
+		.width	 = 1,
+	},
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpll2",
+		.ops = &meson_clk_mpll_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct meson_clk_mpll axg_mpll3 = {
+	.sdm = {
+		.reg_off = HHI_MPLL3_CNTL0,
+		.shift   = 12,
+		.width   = 14,
+	},
+	.sdm_en = {
+		.reg_off = HHI_MPLL3_CNTL0,
+		.shift   = 11,
+		.width	 = 1,
+	},
+	.n2 = {
+		.reg_off = HHI_MPLL3_CNTL0,
+		.shift   = 2,
+		.width   = 9,
+	},
+	.en = {
+		.reg_off = HHI_MPLL3_CNTL0,
+		.shift   = 0,
+		.width	 = 1,
+	},
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpll3",
+		.ops = &meson_clk_mpll_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+/*
+ * FIXME The legacy composite clocks (e.g. clk81) are both PLL post-dividers
+ * and should be modeled with their respective PLLs via the forthcoming
+ * coordinated clock rates feature
+ */
+static u32 mux_table_clk81[]	= { 0, 2, 3, 4, 5, 6, 7 };
+static const char * const clk81_parent_names[] = {
+	"xtal", "fclk_div7", "mpll1", "mpll2", "fclk_div4",
+	"fclk_div3", "fclk_div5"
+};
+
+static struct clk_mux axg_mpeg_clk_sel = {
+	.reg = (void *)HHI_MPEG_CLK_CNTL,
+	.mask = 0x7,
+	.shift = 12,
+	.flags = CLK_MUX_READ_ONLY,
+	.table = mux_table_clk81,
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpeg_clk_sel",
+		.ops = &clk_mux_ro_ops,
+		.parent_names = clk81_parent_names,
+		.num_parents = ARRAY_SIZE(clk81_parent_names),
+	},
+};
+
+static struct clk_divider axg_mpeg_clk_div = {
+	.reg = (void *)HHI_MPEG_CLK_CNTL,
+	.shift = 0,
+	.width = 7,
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpeg_clk_div",
+		.ops = &clk_divider_ops,
+		.parent_names = (const char *[]){ "mpeg_clk_sel" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_gate axg_clk81 = {
+	.reg = (void *)HHI_MPEG_CLK_CNTL,
+	.bit_idx = 7,
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "clk81",
+		.ops = &clk_gate_ops,
+		.parent_names = (const char *[]){ "mpeg_clk_div" },
+		.num_parents = 1,
+		.flags = (CLK_SET_RATE_PARENT | CLK_IS_CRITICAL),
+	},
+};
+
+static const char * const axg_sd_emmc_clk0_parent_names[] = {
+	"xtal", "fclk_div2", "fclk_div3", "fclk_div5", "fclk_div7",
+
+	/*
+	 * Following these parent clocks, we should also have had mpll2, mpll3
+	 * and gp0_pll but these clocks are too precious to be used here. All
+	 * the necessary rates for MMC and NAND operation can be acheived using
+	 * xtal or fclk_div clocks
+	 */
+};
+
+/* SDcard clock */
+static struct clk_mux axg_sd_emmc_b_clk0_sel = {
+	.reg = (void *)HHI_SD_EMMC_CLK_CNTL,
+	.mask = 0x7,
+	.shift = 25,
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data) {
+		.name = "sd_emmc_b_clk0_sel",
+		.ops = &clk_mux_ops,
+		.parent_names = axg_sd_emmc_clk0_parent_names,
+		.num_parents = ARRAY_SIZE(axg_sd_emmc_clk0_parent_names),
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_divider axg_sd_emmc_b_clk0_div = {
+	.reg = (void *)HHI_SD_EMMC_CLK_CNTL,
+	.shift = 16,
+	.width = 7,
+	.lock = &meson_clk_lock,
+	.flags = CLK_DIVIDER_ROUND_CLOSEST,
+	.hw.init = &(struct clk_init_data) {
+		.name = "sd_emmc_b_clk0_div",
+		.ops = &clk_divider_ops,
+		.parent_names = (const char *[]){ "sd_emmc_b_clk0_sel" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_gate axg_sd_emmc_b_clk0 = {
+	.reg = (void *)HHI_SD_EMMC_CLK_CNTL,
+	.bit_idx = 23,
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "sd_emmc_b_clk0",
+		.ops = &clk_gate_ops,
+		.parent_names = (const char *[]){ "sd_emmc_b_clk0_div" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+/* EMMC/NAND clock */
+static struct clk_mux axg_sd_emmc_c_clk0_sel = {
+	.reg = (void *)HHI_NAND_CLK_CNTL,
+	.mask = 0x7,
+	.shift = 9,
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data) {
+		.name = "sd_emmc_c_clk0_sel",
+		.ops = &clk_mux_ops,
+		.parent_names = axg_sd_emmc_clk0_parent_names,
+		.num_parents = ARRAY_SIZE(axg_sd_emmc_clk0_parent_names),
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_divider axg_sd_emmc_c_clk0_div = {
+	.reg = (void *)HHI_NAND_CLK_CNTL,
+	.shift = 0,
+	.width = 7,
+	.lock = &meson_clk_lock,
+	.flags = CLK_DIVIDER_ROUND_CLOSEST,
+	.hw.init = &(struct clk_init_data) {
+		.name = "sd_emmc_c_clk0_div",
+		.ops = &clk_divider_ops,
+		.parent_names = (const char *[]){ "sd_emmc_c_clk0_sel" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_gate axg_sd_emmc_c_clk0 = {
+	.reg = (void *)HHI_NAND_CLK_CNTL,
+	.bit_idx = 7,
+	.lock = &meson_clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "sd_emmc_c_clk0",
+		.ops = &clk_gate_ops,
+		.parent_names = (const char *[]){ "sd_emmc_c_clk0_div" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+/* Everything Else (EE) domain gates */
+static MESON_GATE(axg_ddr, HHI_GCLK_MPEG0, 0);
+static MESON_GATE(axg_audio_locker, HHI_GCLK_MPEG0, 2);
+static MESON_GATE(axg_mipi_dsi_host, HHI_GCLK_MPEG0, 3);
+static MESON_GATE(axg_isa, HHI_GCLK_MPEG0, 5);
+static MESON_GATE(axg_pl301, HHI_GCLK_MPEG0, 6);
+static MESON_GATE(axg_periphs, HHI_GCLK_MPEG0, 7);
+static MESON_GATE(axg_spicc_0, HHI_GCLK_MPEG0, 8);
+static MESON_GATE(axg_i2c, HHI_GCLK_MPEG0, 9);
+static MESON_GATE(axg_rng0, HHI_GCLK_MPEG0, 12);
+static MESON_GATE(axg_uart0, HHI_GCLK_MPEG0, 13);
+static MESON_GATE(axg_mipi_dsi_phy, HHI_GCLK_MPEG0, 14);
+static MESON_GATE(axg_spicc_1, HHI_GCLK_MPEG0, 15);
+static MESON_GATE(axg_pcie_a, HHI_GCLK_MPEG0, 16);
+static MESON_GATE(axg_pcie_b, HHI_GCLK_MPEG0, 17);
+static MESON_GATE(axg_hiu_reg, HHI_GCLK_MPEG0, 19);
+static MESON_GATE(axg_assist_misc, HHI_GCLK_MPEG0, 23);
+static MESON_GATE(axg_emmc_b, HHI_GCLK_MPEG0, 25);
+static MESON_GATE(axg_emmc_c, HHI_GCLK_MPEG0, 26);
+static MESON_GATE(axg_dma, HHI_GCLK_MPEG0, 27);
+static MESON_GATE(axg_spi, HHI_GCLK_MPEG0, 30);
+
+static MESON_GATE(axg_audio, HHI_GCLK_MPEG1, 0);
+static MESON_GATE(axg_eth_core, HHI_GCLK_MPEG1, 3);
+static MESON_GATE(axg_uart1, HHI_GCLK_MPEG1, 16);
+static MESON_GATE(axg_g2d, HHI_GCLK_MPEG1, 20);
+static MESON_GATE(axg_usb0, HHI_GCLK_MPEG1, 21);
+static MESON_GATE(axg_usb1, HHI_GCLK_MPEG1, 22);
+static MESON_GATE(axg_reset, HHI_GCLK_MPEG1, 23);
+static MESON_GATE(axg_usb_general, HHI_GCLK_MPEG1, 26);
+static MESON_GATE(axg_ahb_arb0, HHI_GCLK_MPEG1, 29);
+static MESON_GATE(axg_efuse, HHI_GCLK_MPEG1, 30);
+static MESON_GATE(axg_boot_rom, HHI_GCLK_MPEG1, 31);
+
+static MESON_GATE(axg_ahb_data_bus, HHI_GCLK_MPEG2, 1);
+static MESON_GATE(axg_ahb_ctrl_bus, HHI_GCLK_MPEG2, 2);
+static MESON_GATE(axg_usb1_to_ddr, HHI_GCLK_MPEG2, 8);
+static MESON_GATE(axg_usb0_to_ddr, HHI_GCLK_MPEG2, 9);
+static MESON_GATE(axg_mmc_pclk, HHI_GCLK_MPEG2, 11);
+static MESON_GATE(axg_vpu_intr, HHI_GCLK_MPEG2, 25);
+static MESON_GATE(axg_sec_ahb_ahb3_bridge, HHI_GCLK_MPEG2, 26);
+static MESON_GATE(axg_gic, HHI_GCLK_MPEG2, 30);
+
+/* Always On (AO) domain gates */
+
+static MESON_GATE(axg_ao_media_cpu, HHI_GCLK_AO, 0);
+static MESON_GATE(axg_ao_ahb_sram, HHI_GCLK_AO, 1);
+static MESON_GATE(axg_ao_ahb_bus, HHI_GCLK_AO, 2);
+static MESON_GATE(axg_ao_iface, HHI_GCLK_AO, 3);
+static MESON_GATE(axg_ao_i2c, HHI_GCLK_AO, 4);
+
+/* Array of all clocks provided by this provider */
+
+static struct clk_hw_onecell_data axg_hw_onecell_data = {
+	.hws = {
+		[CLKID_SYS_PLL]			= &axg_sys_pll.hw,
+		[CLKID_FIXED_PLL]		= &axg_fixed_pll.hw,
+		[CLKID_FCLK_DIV2]		= &axg_fclk_div2.hw,
+		[CLKID_FCLK_DIV3]		= &axg_fclk_div3.hw,
+		[CLKID_FCLK_DIV4]		= &axg_fclk_div4.hw,
+		[CLKID_FCLK_DIV5]		= &axg_fclk_div5.hw,
+		[CLKID_FCLK_DIV7]		= &axg_fclk_div7.hw,
+		[CLKID_GP0_PLL]			= &axg_gp0_pll.hw,
+		[CLKID_MPEG_SEL]		= &axg_mpeg_clk_sel.hw,
+		[CLKID_MPEG_DIV]		= &axg_mpeg_clk_div.hw,
+		[CLKID_CLK81]			= &axg_clk81.hw,
+		[CLKID_MPLL0]			= &axg_mpll0.hw,
+		[CLKID_MPLL1]			= &axg_mpll1.hw,
+		[CLKID_MPLL2]			= &axg_mpll2.hw,
+		[CLKID_MPLL3]			= &axg_mpll3.hw,
+		[CLKID_DDR]			= &axg_ddr.hw,
+		[CLKID_AUDIO_LOCKER]		= &axg_audio_locker.hw,
+		[CLKID_MIPI_DSI_HOST]		= &axg_mipi_dsi_host.hw,
+		[CLKID_ISA]			= &axg_isa.hw,
+		[CLKID_PL301]			= &axg_pl301.hw,
+		[CLKID_PERIPHS]			= &axg_periphs.hw,
+		[CLKID_SPICC0]			= &axg_spicc_0.hw,
+		[CLKID_I2C]			= &axg_i2c.hw,
+		[CLKID_RNG0]			= &axg_rng0.hw,
+		[CLKID_UART0]			= &axg_uart0.hw,
+		[CLKID_MIPI_DSI_PHY]		= &axg_mipi_dsi_phy.hw,
+		[CLKID_SPICC1]			= &axg_spicc_1.hw,
+		[CLKID_PCIE_A]			= &axg_pcie_a.hw,
+		[CLKID_PCIE_B]			= &axg_pcie_b.hw,
+		[CLKID_HIU_IFACE]		= &axg_hiu_reg.hw,
+		[CLKID_ASSIST_MISC]		= &axg_assist_misc.hw,
+		[CLKID_SD_EMMC_B]		= &axg_emmc_b.hw,
+		[CLKID_SD_EMMC_C]		= &axg_emmc_c.hw,
+		[CLKID_DMA]			= &axg_dma.hw,
+		[CLKID_SPI]			= &axg_spi.hw,
+		[CLKID_AUDIO]			= &axg_audio.hw,
+		[CLKID_ETH]			= &axg_eth_core.hw,
+		[CLKID_UART1]			= &axg_uart1.hw,
+		[CLKID_G2D]			= &axg_g2d.hw,
+		[CLKID_USB0]			= &axg_usb0.hw,
+		[CLKID_USB1]			= &axg_usb1.hw,
+		[CLKID_RESET]			= &axg_reset.hw,
+		[CLKID_USB]			= &axg_usb_general.hw,
+		[CLKID_AHB_ARB0]		= &axg_ahb_arb0.hw,
+		[CLKID_EFUSE]			= &axg_efuse.hw,
+		[CLKID_BOOT_ROM]		= &axg_boot_rom.hw,
+		[CLKID_AHB_DATA_BUS]		= &axg_ahb_data_bus.hw,
+		[CLKID_AHB_CTRL_BUS]		= &axg_ahb_ctrl_bus.hw,
+		[CLKID_USB1_DDR_BRIDGE]		= &axg_usb1_to_ddr.hw,
+		[CLKID_USB0_DDR_BRIDGE]		= &axg_usb0_to_ddr.hw,
+		[CLKID_MMC_PCLK]		= &axg_mmc_pclk.hw,
+		[CLKID_VPU_INTR]		= &axg_vpu_intr.hw,
+		[CLKID_SEC_AHB_AHB3_BRIDGE]	= &axg_sec_ahb_ahb3_bridge.hw,
+		[CLKID_GIC]			= &axg_gic.hw,
+		[CLKID_AO_MEDIA_CPU]		= &axg_ao_media_cpu.hw,
+		[CLKID_AO_AHB_SRAM]		= &axg_ao_ahb_sram.hw,
+		[CLKID_AO_AHB_BUS]		= &axg_ao_ahb_bus.hw,
+		[CLKID_AO_IFACE]		= &axg_ao_iface.hw,
+		[CLKID_AO_I2C]			= &axg_ao_i2c.hw,
+		[CLKID_SD_EMMC_B_CLK0_SEL]	= &axg_sd_emmc_b_clk0_sel.hw,
+		[CLKID_SD_EMMC_B_CLK0_DIV]	= &axg_sd_emmc_b_clk0_div.hw,
+		[CLKID_SD_EMMC_B_CLK0]		= &axg_sd_emmc_b_clk0.hw,
+		[CLKID_SD_EMMC_C_CLK0_SEL]	= &axg_sd_emmc_c_clk0_sel.hw,
+		[CLKID_SD_EMMC_C_CLK0_DIV]	= &axg_sd_emmc_c_clk0_div.hw,
+		[CLKID_SD_EMMC_C_CLK0]		= &axg_sd_emmc_c_clk0.hw,
+		[NR_CLKS]			= NULL,
+	},
+	.num = NR_CLKS,
+};
+
+/* Convenience tables to populate base addresses in .probe */
+
+static struct meson_clk_pll *const axg_clk_plls[] = {
+	&axg_fixed_pll,
+	&axg_sys_pll,
+	&axg_gp0_pll,
+};
+
+static struct meson_clk_mpll *const axg_clk_mplls[] = {
+	&axg_mpll0,
+	&axg_mpll1,
+	&axg_mpll2,
+	&axg_mpll3,
+};
+
+static struct clk_gate *const axg_clk_gates[] = {
+	&axg_clk81,
+	&axg_ddr,
+	&axg_audio_locker,
+	&axg_mipi_dsi_host,
+	&axg_isa,
+	&axg_pl301,
+	&axg_periphs,
+	&axg_spicc_0,
+	&axg_i2c,
+	&axg_rng0,
+	&axg_uart0,
+	&axg_mipi_dsi_phy,
+	&axg_spicc_1,
+	&axg_pcie_a,
+	&axg_pcie_b,
+	&axg_hiu_reg,
+	&axg_assist_misc,
+	&axg_emmc_b,
+	&axg_emmc_c,
+	&axg_dma,
+	&axg_spi,
+	&axg_audio,
+	&axg_eth_core,
+	&axg_uart1,
+	&axg_g2d,
+	&axg_usb0,
+	&axg_usb1,
+	&axg_reset,
+	&axg_usb_general,
+	&axg_ahb_arb0,
+	&axg_efuse,
+	&axg_boot_rom,
+	&axg_ahb_data_bus,
+	&axg_ahb_ctrl_bus,
+	&axg_usb1_to_ddr,
+	&axg_usb0_to_ddr,
+	&axg_mmc_pclk,
+	&axg_vpu_intr,
+	&axg_sec_ahb_ahb3_bridge,
+	&axg_gic,
+	&axg_ao_media_cpu,
+	&axg_ao_ahb_sram,
+	&axg_ao_ahb_bus,
+	&axg_ao_iface,
+	&axg_ao_i2c,
+	&axg_sd_emmc_b_clk0,
+	&axg_sd_emmc_c_clk0,
+};
+
+static struct clk_mux *const axg_clk_muxes[] = {
+	&axg_mpeg_clk_sel,
+	&axg_sd_emmc_b_clk0_sel,
+	&axg_sd_emmc_c_clk0_sel,
+};
+
+static struct clk_divider *const axg_clk_dividers[] = {
+	&axg_mpeg_clk_div,
+	&axg_sd_emmc_b_clk0_div,
+	&axg_sd_emmc_c_clk0_div,
+};
+
+struct clkc_data {
+	struct clk_gate *const *clk_gates;
+	unsigned int clk_gates_count;
+	struct meson_clk_mpll *const *clk_mplls;
+	unsigned int clk_mplls_count;
+	struct meson_clk_pll *const *clk_plls;
+	unsigned int clk_plls_count;
+	struct clk_mux *const *clk_muxes;
+	unsigned int clk_muxes_count;
+	struct clk_divider *const *clk_dividers;
+	unsigned int clk_dividers_count;
+	struct clk_hw_onecell_data *hw_onecell_data;
+};
+
+static const struct clkc_data axg_clkc_data = {
+	.clk_gates = axg_clk_gates,
+	.clk_gates_count = ARRAY_SIZE(axg_clk_gates),
+	.clk_mplls = axg_clk_mplls,
+	.clk_mplls_count = ARRAY_SIZE(axg_clk_mplls),
+	.clk_plls = axg_clk_plls,
+	.clk_plls_count = ARRAY_SIZE(axg_clk_plls),
+	.clk_muxes = axg_clk_muxes,
+	.clk_muxes_count = ARRAY_SIZE(axg_clk_muxes),
+	.clk_dividers = axg_clk_dividers,
+	.clk_dividers_count = ARRAY_SIZE(axg_clk_dividers),
+	.hw_onecell_data = &axg_hw_onecell_data,
+};
+
+static const struct of_device_id clkc_match_table[] = {
+	{ .compatible = "amlogic,axg-clkc", .data = &axg_clkc_data },
+	{}
+};
+
+static int axg_clkc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct clkc_data *clkc_data;
+	struct resource *res;
+	void __iomem *clk_base;
+	int ret, clkid, i;
+
+	clkc_data = of_device_get_match_data(&pdev->dev);
+	if (!clkc_data)
+		return -EINVAL;
+
+	/*  Generic clocks and PLLs */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
+	clk_base = devm_ioremap(&pdev->dev, res->start, resource_size(res));
+	if (!clk_base) {
+		dev_err(&pdev->dev, "Unable to map clk base\n");
+		return -ENXIO;
+	}
+
+	/* Populate base address for PLLs */
+	for (i = 0; i < clkc_data->clk_plls_count; i++)
+		clkc_data->clk_plls[i]->base = clk_base;
+
+	/* Populate base address for MPLLs */
+	for (i = 0; i < clkc_data->clk_mplls_count; i++)
+		clkc_data->clk_mplls[i]->base = clk_base;
+
+	/* Populate base address for gates */
+	for (i = 0; i < clkc_data->clk_gates_count; i++)
+		clkc_data->clk_gates[i]->reg = clk_base +
+			(u64)clkc_data->clk_gates[i]->reg;
+
+	/* Populate base address for muxes */
+	for (i = 0; i < clkc_data->clk_muxes_count; i++)
+		clkc_data->clk_muxes[i]->reg = clk_base +
+			(u64)clkc_data->clk_muxes[i]->reg;
+
+	/* Populate base address for dividers */
+	for (i = 0; i < clkc_data->clk_dividers_count; i++)
+		clkc_data->clk_dividers[i]->reg = clk_base +
+			(u64)clkc_data->clk_dividers[i]->reg;
+
+	for (clkid = 0; clkid < clkc_data->hw_onecell_data->num; clkid++) {
+		/* array might be sparse */
+		if (!clkc_data->hw_onecell_data->hws[clkid])
+			continue;
+
+		ret = devm_clk_hw_register(dev,
+					clkc_data->hw_onecell_data->hws[clkid]);
+		if (ret) {
+			dev_err(&pdev->dev, "Clock registration failed\n");
+			return ret;
+		}
+	}
+
+	return of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get,
+			clkc_data->hw_onecell_data);
+}
+
+static struct platform_driver axg_driver = {
+	.probe		= axg_clkc_probe,
+	.driver		= {
+		.name	= "axg-clkc",
+		.of_match_table = clkc_match_table,
+	},
+};
+
+builtin_platform_driver(axg_driver);
diff --git a/drivers/clk/meson/axg.h b/drivers/clk/meson/axg.h
new file mode 100644
index 000000000000..ce0bafdb6b28
--- /dev/null
+++ b/drivers/clk/meson/axg.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */
+/*
+ * Copyright (c) 2016 AmLogic, Inc.
+ * Author: Michael Turquette <mturquette@baylibre.com>
+ *
+ * Copyright (c) 2017 Amlogic, inc.
+ * Author: Qiufang Dai <qiufang.dai@amlogic.com>
+ *
+ */
+#ifndef __AXG_H
+#define __AXG_H
+
+/*
+ * Clock controller register offsets
+ *
+ * Register offsets from the data sheet must be multiplied by 4 before
+ * adding them to the base address to get the right value.
+ */
+#define HHI_GP0_PLL_CNTL		0x40
+#define HHI_GP0_PLL_CNTL2		0x44
+#define HHI_GP0_PLL_CNTL3		0x48
+#define HHI_GP0_PLL_CNTL4		0x4c
+#define HHI_GP0_PLL_CNTL5		0x50
+#define HHI_GP0_PLL_STS			0x54
+#define HHI_GP0_PLL_CNTL1		0x58
+#define HHI_HIFI_PLL_CNTL		0x80
+#define HHI_HIFI_PLL_CNTL2		0x84
+#define HHI_HIFI_PLL_CNTL3		0x88
+#define HHI_HIFI_PLL_CNTL4		0x8C
+#define HHI_HIFI_PLL_CNTL5		0x90
+#define HHI_HIFI_PLL_STS		0x94
+#define HHI_HIFI_PLL_CNTL1		0x98
+
+#define HHI_XTAL_DIVN_CNTL		0xbc
+#define HHI_GCLK2_MPEG0			0xc0
+#define HHI_GCLK2_MPEG1			0xc4
+#define HHI_GCLK2_MPEG2			0xc8
+#define HHI_GCLK2_OTHER			0xd0
+#define HHI_GCLK2_AO			0xd4
+#define HHI_PCIE_PLL_CNTL		0xd8
+#define HHI_PCIE_PLL_CNTL1		0xdC
+#define HHI_PCIE_PLL_CNTL2		0xe0
+#define HHI_PCIE_PLL_CNTL3		0xe4
+#define HHI_PCIE_PLL_CNTL4		0xe8
+#define HHI_PCIE_PLL_CNTL5		0xec
+#define HHI_PCIE_PLL_CNTL6		0xf0
+#define HHI_PCIE_PLL_STS		0xf4
+
+#define HHI_MEM_PD_REG0			0x100
+#define HHI_VPU_MEM_PD_REG0		0x104
+#define HHI_VIID_CLK_DIV		0x128
+#define HHI_VIID_CLK_CNTL		0x12c
+
+#define HHI_GCLK_MPEG0			0x140
+#define HHI_GCLK_MPEG1			0x144
+#define HHI_GCLK_MPEG2			0x148
+#define HHI_GCLK_OTHER			0x150
+#define HHI_GCLK_AO			0x154
+#define HHI_SYS_CPU_CLK_CNTL1		0x15c
+#define HHI_SYS_CPU_RESET_CNTL		0x160
+#define HHI_VID_CLK_DIV			0x164
+#define HHI_SPICC_HCLK_CNTL		0x168
+
+#define HHI_MPEG_CLK_CNTL		0x174
+#define HHI_VID_CLK_CNTL		0x17c
+#define HHI_TS_CLK_CNTL			0x190
+#define HHI_VID_CLK_CNTL2		0x194
+#define HHI_SYS_CPU_CLK_CNTL0		0x19c
+#define HHI_VID_PLL_CLK_DIV		0x1a0
+#define HHI_VPU_CLK_CNTL		0x1bC
+
+#define HHI_VAPBCLK_CNTL		0x1F4
+
+#define HHI_GEN_CLK_CNTL		0x228
+
+#define HHI_VDIN_MEAS_CLK_CNTL		0x250
+#define HHI_NAND_CLK_CNTL		0x25C
+#define HHI_SD_EMMC_CLK_CNTL		0x264
+
+#define HHI_MPLL_CNTL			0x280
+#define HHI_MPLL_CNTL2			0x284
+#define HHI_MPLL_CNTL3			0x288
+#define HHI_MPLL_CNTL4			0x28C
+#define HHI_MPLL_CNTL5			0x290
+#define HHI_MPLL_CNTL6			0x294
+#define HHI_MPLL_CNTL7			0x298
+#define HHI_MPLL_CNTL8			0x29C
+#define HHI_MPLL_CNTL9			0x2A0
+#define HHI_MPLL_CNTL10			0x2A4
+
+#define HHI_MPLL3_CNTL0			0x2E0
+#define HHI_MPLL3_CNTL1			0x2E4
+#define HHI_PLL_TOP_MISC		0x2E8
+
+#define HHI_SYS_PLL_CNTL1		0x2FC
+#define HHI_SYS_PLL_CNTL		0x300
+#define HHI_SYS_PLL_CNTL2		0x304
+#define HHI_SYS_PLL_CNTL3		0x308
+#define HHI_SYS_PLL_CNTL4		0x30c
+#define HHI_SYS_PLL_CNTL5		0x310
+#define HHI_SYS_PLL_STS			0x314
+#define HHI_DPLL_TOP_I			0x318
+#define HHI_DPLL_TOP2_I			0x31C
+
+/*
+ * CLKID index values
+ *
+ * These indices are entirely contrived and do not map onto the hardware.
+ * It has now been decided to expose everything by default in the DT header:
+ * include/dt-bindings/clock/axg-clkc.h. Only the clocks ids we don't want
+ * to expose, such as the internal muxes and dividers of composite clocks,
+ * will remain defined here.
+ */
+#define CLKID_MPEG_SEL				8
+#define CLKID_MPEG_DIV				9
+#define CLKID_SD_EMMC_B_CLK0_SEL		61
+#define CLKID_SD_EMMC_B_CLK0_DIV		62
+#define CLKID_SD_EMMC_C_CLK0_SEL		63
+#define CLKID_SD_EMMC_C_CLK0_DIV		64
+
+#define NR_CLKS					65
+
+/* include the CLKIDs that have been made part of the DT binding */
+#include <dt-bindings/clock/axg-clkc.h>
+
+#endif /* __AXG_H */
diff --git a/drivers/clk/meson/clk-mpll.c b/drivers/clk/meson/clk-mpll.c
index 44a5a535ca63..5144360e2c80 100644
--- a/drivers/clk/meson/clk-mpll.c
+++ b/drivers/clk/meson/clk-mpll.c
@@ -98,7 +98,7 @@ static void params_from_rate(unsigned long requested_rate,
 		*sdm = SDM_DEN - 1;
 	} else {
 		*n2 = div;
-		*sdm = DIV_ROUND_UP(rem * SDM_DEN, requested_rate);
+		*sdm = DIV_ROUND_UP_ULL((u64)rem * SDM_DEN, requested_rate);
 	}
 }
 
diff --git a/drivers/clk/meson/clkc.h b/drivers/clk/meson/clkc.h
index 1629da9b4141..c2ff0520ce53 100644
--- a/drivers/clk/meson/clkc.h
+++ b/drivers/clk/meson/clkc.h
@@ -134,7 +134,7 @@ struct meson_clk_audio_divider {
 struct clk_gate _name = { 						\
 	.reg = (void __iomem *) _reg, 					\
 	.bit_idx = (_bit), 						\
-	.lock = &clk_lock,						\
+	.lock = &meson_clk_lock,					\
 	.hw.init = &(struct clk_init_data) { 				\
 		.name = #_name,					\
 		.ops = &clk_gate_ops,					\
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index ae385310e980..af24455af5b4 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -27,7 +27,7 @@
 #include "clkc.h"
 #include "gxbb.h"
 
-static DEFINE_SPINLOCK(clk_lock);
+static DEFINE_SPINLOCK(meson_clk_lock);
 
 static const struct pll_rate_table sys_pll_rate_table[] = {
 	PLL_RATE(24000000, 56, 1, 2),
@@ -294,7 +294,7 @@ static struct meson_clk_pll gxbb_fixed_pll = {
 		.shift   = 16,
 		.width   = 2,
 	},
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "fixed_pll",
 		.ops = &meson_clk_pll_ro_ops,
@@ -330,7 +330,7 @@ static struct meson_clk_pll gxbb_hdmi_pll = {
 		.shift   = 22,
 		.width   = 2,
 	},
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "hdmi_pll",
 		.ops = &meson_clk_pll_ro_ops,
@@ -358,7 +358,7 @@ static struct meson_clk_pll gxbb_sys_pll = {
 	},
 	.rate_table = sys_pll_rate_table,
 	.rate_count = ARRAY_SIZE(sys_pll_rate_table),
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "sys_pll",
 		.ops = &meson_clk_pll_ro_ops,
@@ -399,7 +399,7 @@ static struct meson_clk_pll gxbb_gp0_pll = {
 	},
 	.rate_table = gxbb_gp0_pll_rate_table,
 	.rate_count = ARRAY_SIZE(gxbb_gp0_pll_rate_table),
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "gp0_pll",
 		.ops = &meson_clk_pll_ops,
@@ -442,7 +442,7 @@ static struct meson_clk_pll gxl_gp0_pll = {
 	},
 	.rate_table = gxl_gp0_pll_rate_table,
 	.rate_count = ARRAY_SIZE(gxl_gp0_pll_rate_table),
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "gp0_pll",
 		.ops = &meson_clk_pll_ops,
@@ -533,7 +533,7 @@ static struct meson_clk_mpll gxbb_mpll0 = {
 		.shift   = 25,
 		.width	 = 1,
 	},
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mpll0",
 		.ops = &meson_clk_mpll_ops,
@@ -563,7 +563,7 @@ static struct meson_clk_mpll gxbb_mpll1 = {
 		.shift   = 14,
 		.width	 = 1,
 	},
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mpll1",
 		.ops = &meson_clk_mpll_ops,
@@ -593,7 +593,7 @@ static struct meson_clk_mpll gxbb_mpll2 = {
 		.shift   = 14,
 		.width	 = 1,
 	},
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mpll2",
 		.ops = &meson_clk_mpll_ops,
@@ -620,7 +620,7 @@ static struct clk_mux gxbb_mpeg_clk_sel = {
 	.shift = 12,
 	.flags = CLK_MUX_READ_ONLY,
 	.table = mux_table_clk81,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mpeg_clk_sel",
 		.ops = &clk_mux_ro_ops,
@@ -639,7 +639,7 @@ static struct clk_divider gxbb_mpeg_clk_div = {
 	.reg = (void *)HHI_MPEG_CLK_CNTL,
 	.shift = 0,
 	.width = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mpeg_clk_div",
 		.ops = &clk_divider_ops,
@@ -653,7 +653,7 @@ static struct clk_divider gxbb_mpeg_clk_div = {
 static struct clk_gate gxbb_clk81 = {
 	.reg = (void *)HHI_MPEG_CLK_CNTL,
 	.bit_idx = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "clk81",
 		.ops = &clk_gate_ops,
@@ -667,7 +667,7 @@ static struct clk_mux gxbb_sar_adc_clk_sel = {
 	.reg = (void *)HHI_SAR_CLK_CNTL,
 	.mask = 0x3,
 	.shift = 9,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "sar_adc_clk_sel",
 		.ops = &clk_mux_ops,
@@ -681,7 +681,7 @@ static struct clk_divider gxbb_sar_adc_clk_div = {
 	.reg = (void *)HHI_SAR_CLK_CNTL,
 	.shift = 0,
 	.width = 8,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "sar_adc_clk_div",
 		.ops = &clk_divider_ops,
@@ -693,7 +693,7 @@ static struct clk_divider gxbb_sar_adc_clk_div = {
 static struct clk_gate gxbb_sar_adc_clk = {
 	.reg = (void *)HHI_SAR_CLK_CNTL,
 	.bit_idx = 8,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "sar_adc_clk",
 		.ops = &clk_gate_ops,
@@ -719,7 +719,7 @@ static struct clk_mux gxbb_mali_0_sel = {
 	.mask = 0x7,
 	.shift = 9,
 	.table = mux_table_mali_0_1,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mali_0_sel",
 		.ops = &clk_mux_ops,
@@ -738,7 +738,7 @@ static struct clk_divider gxbb_mali_0_div = {
 	.reg = (void *)HHI_MALI_CLK_CNTL,
 	.shift = 0,
 	.width = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mali_0_div",
 		.ops = &clk_divider_ops,
@@ -751,7 +751,7 @@ static struct clk_divider gxbb_mali_0_div = {
 static struct clk_gate gxbb_mali_0 = {
 	.reg = (void *)HHI_MALI_CLK_CNTL,
 	.bit_idx = 8,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mali_0",
 		.ops = &clk_gate_ops,
@@ -766,7 +766,7 @@ static struct clk_mux gxbb_mali_1_sel = {
 	.mask = 0x7,
 	.shift = 25,
 	.table = mux_table_mali_0_1,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mali_1_sel",
 		.ops = &clk_mux_ops,
@@ -785,7 +785,7 @@ static struct clk_divider gxbb_mali_1_div = {
 	.reg = (void *)HHI_MALI_CLK_CNTL,
 	.shift = 16,
 	.width = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mali_1_div",
 		.ops = &clk_divider_ops,
@@ -798,7 +798,7 @@ static struct clk_divider gxbb_mali_1_div = {
 static struct clk_gate gxbb_mali_1 = {
 	.reg = (void *)HHI_MALI_CLK_CNTL,
 	.bit_idx = 24,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mali_1",
 		.ops = &clk_gate_ops,
@@ -818,7 +818,7 @@ static struct clk_mux gxbb_mali = {
 	.mask = 1,
 	.shift = 31,
 	.table = mux_table_mali,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mali",
 		.ops = &clk_mux_ops,
@@ -834,7 +834,7 @@ static struct clk_mux gxbb_cts_amclk_sel = {
 	.shift = 9,
 	/* Default parent unknown (register reset value: 0) */
 	.table = (u32[]){ 1, 2, 3 },
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 		.hw.init = &(struct clk_init_data){
 		.name = "cts_amclk_sel",
 		.ops = &clk_mux_ops,
@@ -851,7 +851,7 @@ static struct meson_clk_audio_divider gxbb_cts_amclk_div = {
 		.width   = 8,
 	},
 	.flags = CLK_DIVIDER_ROUND_CLOSEST,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "cts_amclk_div",
 		.ops = &meson_clk_audio_divider_ops,
@@ -864,7 +864,7 @@ static struct meson_clk_audio_divider gxbb_cts_amclk_div = {
 static struct clk_gate gxbb_cts_amclk = {
 	.reg = (void *) HHI_AUD_CLK_CNTL,
 	.bit_idx = 8,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "cts_amclk",
 		.ops = &clk_gate_ops,
@@ -880,7 +880,7 @@ static struct clk_mux gxbb_cts_mclk_i958_sel = {
 	.shift = 25,
 	/* Default parent unknown (register reset value: 0) */
 	.table = (u32[]){ 1, 2, 3 },
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data) {
 		.name = "cts_mclk_i958_sel",
 		.ops = &clk_mux_ops,
@@ -894,7 +894,7 @@ static struct clk_divider gxbb_cts_mclk_i958_div = {
 	.reg = (void *)HHI_AUD_CLK_CNTL2,
 	.shift = 16,
 	.width = 8,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.flags = CLK_DIVIDER_ROUND_CLOSEST,
 	.hw.init = &(struct clk_init_data) {
 		.name = "cts_mclk_i958_div",
@@ -908,7 +908,7 @@ static struct clk_divider gxbb_cts_mclk_i958_div = {
 static struct clk_gate gxbb_cts_mclk_i958 = {
 	.reg = (void *)HHI_AUD_CLK_CNTL2,
 	.bit_idx = 24,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "cts_mclk_i958",
 		.ops = &clk_gate_ops,
@@ -922,7 +922,7 @@ static struct clk_mux gxbb_cts_i958 = {
 	.reg = (void *)HHI_AUD_CLK_CNTL2,
 	.mask = 0x1,
 	.shift = 27,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 		.hw.init = &(struct clk_init_data){
 		.name = "cts_i958",
 		.ops = &clk_mux_ops,
@@ -940,7 +940,7 @@ static struct clk_divider gxbb_32k_clk_div = {
 	.reg = (void *)HHI_32K_CLK_CNTL,
 	.shift = 0,
 	.width = 14,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "32k_clk_div",
 		.ops = &clk_divider_ops,
@@ -953,7 +953,7 @@ static struct clk_divider gxbb_32k_clk_div = {
 static struct clk_gate gxbb_32k_clk = {
 	.reg = (void *)HHI_32K_CLK_CNTL,
 	.bit_idx = 15,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "32k_clk",
 		.ops = &clk_gate_ops,
@@ -971,7 +971,7 @@ static struct clk_mux gxbb_32k_clk_sel = {
 	.reg = (void *)HHI_32K_CLK_CNTL,
 	.mask = 0x3,
 	.shift = 16,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 		.hw.init = &(struct clk_init_data){
 		.name = "32k_clk_sel",
 		.ops = &clk_mux_ops,
@@ -997,7 +997,7 @@ static struct clk_mux gxbb_sd_emmc_a_clk0_sel = {
 	.reg = (void *)HHI_SD_EMMC_CLK_CNTL,
 	.mask = 0x7,
 	.shift = 9,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data) {
 		.name = "sd_emmc_a_clk0_sel",
 		.ops = &clk_mux_ops,
@@ -1011,7 +1011,7 @@ static struct clk_divider gxbb_sd_emmc_a_clk0_div = {
 	.reg = (void *)HHI_SD_EMMC_CLK_CNTL,
 	.shift = 0,
 	.width = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.flags = CLK_DIVIDER_ROUND_CLOSEST,
 	.hw.init = &(struct clk_init_data) {
 		.name = "sd_emmc_a_clk0_div",
@@ -1025,23 +1025,13 @@ static struct clk_divider gxbb_sd_emmc_a_clk0_div = {
 static struct clk_gate gxbb_sd_emmc_a_clk0 = {
 	.reg = (void *)HHI_SD_EMMC_CLK_CNTL,
 	.bit_idx = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "sd_emmc_a_clk0",
 		.ops = &clk_gate_ops,
 		.parent_names = (const char *[]){ "sd_emmc_a_clk0_div" },
 		.num_parents = 1,
-
-		/*
-		 * FIXME:
-		 * We need CLK_IGNORE_UNUSED because mmc DT node point to xtal
-		 * instead of this clock. CCF would gate this on boot, killing
-		 * the mmc controller. Please remove this flag once DT properly
-		 * point to this clock instead of xtal
-		 *
-		 * Same goes for emmc B and C clocks
-		 */
-		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -1050,7 +1040,7 @@ static struct clk_mux gxbb_sd_emmc_b_clk0_sel = {
 	.reg = (void *)HHI_SD_EMMC_CLK_CNTL,
 	.mask = 0x7,
 	.shift = 25,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data) {
 		.name = "sd_emmc_b_clk0_sel",
 		.ops = &clk_mux_ops,
@@ -1064,7 +1054,7 @@ static struct clk_divider gxbb_sd_emmc_b_clk0_div = {
 	.reg = (void *)HHI_SD_EMMC_CLK_CNTL,
 	.shift = 16,
 	.width = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.flags = CLK_DIVIDER_ROUND_CLOSEST,
 	.hw.init = &(struct clk_init_data) {
 		.name = "sd_emmc_b_clk0_div",
@@ -1078,13 +1068,13 @@ static struct clk_divider gxbb_sd_emmc_b_clk0_div = {
 static struct clk_gate gxbb_sd_emmc_b_clk0 = {
 	.reg = (void *)HHI_SD_EMMC_CLK_CNTL,
 	.bit_idx = 23,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "sd_emmc_b_clk0",
 		.ops = &clk_gate_ops,
 		.parent_names = (const char *[]){ "sd_emmc_b_clk0_div" },
 		.num_parents = 1,
-		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -1093,7 +1083,7 @@ static struct clk_mux gxbb_sd_emmc_c_clk0_sel = {
 	.reg = (void *)HHI_NAND_CLK_CNTL,
 	.mask = 0x7,
 	.shift = 9,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data) {
 		.name = "sd_emmc_c_clk0_sel",
 		.ops = &clk_mux_ops,
@@ -1107,7 +1097,7 @@ static struct clk_divider gxbb_sd_emmc_c_clk0_div = {
 	.reg = (void *)HHI_NAND_CLK_CNTL,
 	.shift = 0,
 	.width = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.flags = CLK_DIVIDER_ROUND_CLOSEST,
 	.hw.init = &(struct clk_init_data) {
 		.name = "sd_emmc_c_clk0_div",
@@ -1121,13 +1111,13 @@ static struct clk_divider gxbb_sd_emmc_c_clk0_div = {
 static struct clk_gate gxbb_sd_emmc_c_clk0 = {
 	.reg = (void *)HHI_NAND_CLK_CNTL,
 	.bit_idx = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "sd_emmc_c_clk0",
 		.ops = &clk_gate_ops,
 		.parent_names = (const char *[]){ "sd_emmc_c_clk0_div" },
 		.num_parents = 1,
-		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -1142,7 +1132,7 @@ static struct clk_mux gxbb_vpu_0_sel = {
 	.reg = (void *)HHI_VPU_CLK_CNTL,
 	.mask = 0x3,
 	.shift = 9,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.table = mux_table_vpu,
 	.hw.init = &(struct clk_init_data){
 		.name = "vpu_0_sel",
@@ -1161,7 +1151,7 @@ static struct clk_divider gxbb_vpu_0_div = {
 	.reg = (void *)HHI_VPU_CLK_CNTL,
 	.shift = 0,
 	.width = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "vpu_0_div",
 		.ops = &clk_divider_ops,
@@ -1174,7 +1164,7 @@ static struct clk_divider gxbb_vpu_0_div = {
 static struct clk_gate gxbb_vpu_0 = {
 	.reg = (void *)HHI_VPU_CLK_CNTL,
 	.bit_idx = 8,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data) {
 		.name = "vpu_0",
 		.ops = &clk_gate_ops,
@@ -1188,7 +1178,7 @@ static struct clk_mux gxbb_vpu_1_sel = {
 	.reg = (void *)HHI_VPU_CLK_CNTL,
 	.mask = 0x3,
 	.shift = 25,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.table = mux_table_vpu,
 	.hw.init = &(struct clk_init_data){
 		.name = "vpu_1_sel",
@@ -1207,7 +1197,7 @@ static struct clk_divider gxbb_vpu_1_div = {
 	.reg = (void *)HHI_VPU_CLK_CNTL,
 	.shift = 16,
 	.width = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "vpu_1_div",
 		.ops = &clk_divider_ops,
@@ -1220,7 +1210,7 @@ static struct clk_divider gxbb_vpu_1_div = {
 static struct clk_gate gxbb_vpu_1 = {
 	.reg = (void *)HHI_VPU_CLK_CNTL,
 	.bit_idx = 24,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data) {
 		.name = "vpu_1",
 		.ops = &clk_gate_ops,
@@ -1234,7 +1224,7 @@ static struct clk_mux gxbb_vpu = {
 	.reg = (void *)HHI_VPU_CLK_CNTL,
 	.mask = 1,
 	.shift = 31,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "vpu",
 		.ops = &clk_mux_ops,
@@ -1259,7 +1249,7 @@ static struct clk_mux gxbb_vapb_0_sel = {
 	.reg = (void *)HHI_VAPBCLK_CNTL,
 	.mask = 0x3,
 	.shift = 9,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.table = mux_table_vapb,
 	.hw.init = &(struct clk_init_data){
 		.name = "vapb_0_sel",
@@ -1278,7 +1268,7 @@ static struct clk_divider gxbb_vapb_0_div = {
 	.reg = (void *)HHI_VAPBCLK_CNTL,
 	.shift = 0,
 	.width = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "vapb_0_div",
 		.ops = &clk_divider_ops,
@@ -1291,7 +1281,7 @@ static struct clk_divider gxbb_vapb_0_div = {
 static struct clk_gate gxbb_vapb_0 = {
 	.reg = (void *)HHI_VAPBCLK_CNTL,
 	.bit_idx = 8,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data) {
 		.name = "vapb_0",
 		.ops = &clk_gate_ops,
@@ -1305,7 +1295,7 @@ static struct clk_mux gxbb_vapb_1_sel = {
 	.reg = (void *)HHI_VAPBCLK_CNTL,
 	.mask = 0x3,
 	.shift = 25,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.table = mux_table_vapb,
 	.hw.init = &(struct clk_init_data){
 		.name = "vapb_1_sel",
@@ -1324,7 +1314,7 @@ static struct clk_divider gxbb_vapb_1_div = {
 	.reg = (void *)HHI_VAPBCLK_CNTL,
 	.shift = 16,
 	.width = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "vapb_1_div",
 		.ops = &clk_divider_ops,
@@ -1337,7 +1327,7 @@ static struct clk_divider gxbb_vapb_1_div = {
 static struct clk_gate gxbb_vapb_1 = {
 	.reg = (void *)HHI_VAPBCLK_CNTL,
 	.bit_idx = 24,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data) {
 		.name = "vapb_1",
 		.ops = &clk_gate_ops,
@@ -1351,7 +1341,7 @@ static struct clk_mux gxbb_vapb_sel = {
 	.reg = (void *)HHI_VAPBCLK_CNTL,
 	.mask = 1,
 	.shift = 31,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "vapb_sel",
 		.ops = &clk_mux_ops,
@@ -1368,7 +1358,7 @@ static struct clk_mux gxbb_vapb_sel = {
 static struct clk_gate gxbb_vapb = {
 	.reg = (void *)HHI_VAPBCLK_CNTL,
 	.bit_idx = 30,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data) {
 		.name = "vapb",
 		.ops = &clk_gate_ops,
@@ -1386,7 +1376,7 @@ static MESON_GATE(gxbb_pl301, HHI_GCLK_MPEG0, 6);
 static MESON_GATE(gxbb_periphs, HHI_GCLK_MPEG0, 7);
 static MESON_GATE(gxbb_spicc, HHI_GCLK_MPEG0, 8);
 static MESON_GATE(gxbb_i2c, HHI_GCLK_MPEG0, 9);
-static MESON_GATE(gxbb_sar_adc, HHI_GCLK_MPEG0, 10);
+static MESON_GATE(gxbb_sana, HHI_GCLK_MPEG0, 10);
 static MESON_GATE(gxbb_smart_card, HHI_GCLK_MPEG0, 11);
 static MESON_GATE(gxbb_rng0, HHI_GCLK_MPEG0, 12);
 static MESON_GATE(gxbb_uart0, HHI_GCLK_MPEG0, 13);
@@ -1437,7 +1427,7 @@ static MESON_GATE(gxbb_usb0_ddr_bridge, HHI_GCLK_MPEG2, 9);
 static MESON_GATE(gxbb_mmc_pclk, HHI_GCLK_MPEG2, 11);
 static MESON_GATE(gxbb_dvin, HHI_GCLK_MPEG2, 12);
 static MESON_GATE(gxbb_uart2, HHI_GCLK_MPEG2, 15);
-static MESON_GATE(gxbb_sana, HHI_GCLK_MPEG2, 22);
+static MESON_GATE(gxbb_sar_adc, HHI_GCLK_MPEG2, 22);
 static MESON_GATE(gxbb_vpu_intr, HHI_GCLK_MPEG2, 25);
 static MESON_GATE(gxbb_sec_ahb_ahb3_bridge, HHI_GCLK_MPEG2, 26);
 static MESON_GATE(gxbb_clk81_a53, HHI_GCLK_MPEG2, 29);
diff --git a/drivers/clk/meson/meson8b.c b/drivers/clk/meson/meson8b.c
index 20ab7190d328..3ffea80c1308 100644
--- a/drivers/clk/meson/meson8b.c
+++ b/drivers/clk/meson/meson8b.c
@@ -32,7 +32,7 @@
 #include "clkc.h"
 #include "meson8b.h"
 
-static DEFINE_SPINLOCK(clk_lock);
+static DEFINE_SPINLOCK(meson_clk_lock);
 
 static void __iomem *clk_base;
 
@@ -136,7 +136,7 @@ static struct meson_clk_pll meson8b_fixed_pll = {
 		.shift   = 16,
 		.width   = 2,
 	},
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "fixed_pll",
 		.ops = &meson_clk_pll_ro_ops,
@@ -162,7 +162,7 @@ static struct meson_clk_pll meson8b_vid_pll = {
 		.shift   = 16,
 		.width   = 2,
 	},
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "vid_pll",
 		.ops = &meson_clk_pll_ro_ops,
@@ -190,7 +190,7 @@ static struct meson_clk_pll meson8b_sys_pll = {
 	},
 	.rate_table = sys_pll_rate_table,
 	.rate_count = ARRAY_SIZE(sys_pll_rate_table),
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "sys_pll",
 		.ops = &meson_clk_pll_ops,
@@ -281,7 +281,7 @@ static struct meson_clk_mpll meson8b_mpll0 = {
 		.shift   = 25,
 		.width   = 1,
 	},
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mpll0",
 		.ops = &meson_clk_mpll_ops,
@@ -311,7 +311,7 @@ static struct meson_clk_mpll meson8b_mpll1 = {
 		.shift   = 14,
 		.width   = 1,
 	},
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mpll1",
 		.ops = &meson_clk_mpll_ops,
@@ -341,7 +341,7 @@ static struct meson_clk_mpll meson8b_mpll2 = {
 		.shift   = 14,
 		.width   = 1,
 	},
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mpll2",
 		.ops = &meson_clk_mpll_ops,
@@ -375,7 +375,7 @@ struct clk_mux meson8b_mpeg_clk_sel = {
 	.shift = 12,
 	.flags = CLK_MUX_READ_ONLY,
 	.table = mux_table_clk81,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mpeg_clk_sel",
 		.ops = &clk_mux_ro_ops,
@@ -395,7 +395,7 @@ struct clk_divider meson8b_mpeg_clk_div = {
 	.reg = (void *)HHI_MPEG_CLK_CNTL,
 	.shift = 0,
 	.width = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "mpeg_clk_div",
 		.ops = &clk_divider_ops,
@@ -408,7 +408,7 @@ struct clk_divider meson8b_mpeg_clk_div = {
 struct clk_gate meson8b_clk81 = {
 	.reg = (void *)HHI_MPEG_CLK_CNTL,
 	.bit_idx = 7,
-	.lock = &clk_lock,
+	.lock = &meson_clk_lock,
 	.hw.init = &(struct clk_init_data){
 		.name = "clk81",
 		.ops = &clk_gate_ops,
@@ -773,7 +773,7 @@ static int meson8b_clk_reset_update(struct reset_controller_dev *rcdev,
 
 	reset = &meson8b_clk_reset_bits[id];
 
-	spin_lock_irqsave(&clk_lock, flags);
+	spin_lock_irqsave(&meson_clk_lock, flags);
 
 	val = readl(meson8b_clk_reset->base + reset->reg);
 	if (assert)
@@ -782,7 +782,7 @@ static int meson8b_clk_reset_update(struct reset_controller_dev *rcdev,
 		val &= ~BIT(reset->bit_idx);
 	writel(val, meson8b_clk_reset->base + reset->reg);
 
-	spin_unlock_irqrestore(&clk_lock, flags);
+	spin_unlock_irqrestore(&meson_clk_lock, flags);
 
 	return 0;
 }
diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c
index cecb0fdfaef6..87213ea7fc84 100644
--- a/drivers/clk/mvebu/armada-37xx-periph.c
+++ b/drivers/clk/mvebu/armada-37xx-periph.c
@@ -21,9 +21,11 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/mfd/syscon.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/regmap.h>
 #include <linux/slab.h>
 
 #define TBG_SEL		0x0
@@ -33,6 +35,26 @@
 #define CLK_SEL		0x10
 #define CLK_DIS		0x14
 
+#define LOAD_LEVEL_NR	4
+
+#define ARMADA_37XX_NB_L0L1	0x18
+#define ARMADA_37XX_NB_L2L3	0x1C
+#define		ARMADA_37XX_NB_TBG_DIV_OFF	13
+#define		ARMADA_37XX_NB_TBG_DIV_MASK	0x7
+#define		ARMADA_37XX_NB_CLK_SEL_OFF	11
+#define		ARMADA_37XX_NB_CLK_SEL_MASK	0x1
+#define		ARMADA_37XX_NB_TBG_SEL_OFF	9
+#define		ARMADA_37XX_NB_TBG_SEL_MASK	0x3
+#define		ARMADA_37XX_NB_CONFIG_SHIFT	16
+#define ARMADA_37XX_NB_DYN_MOD	0x24
+#define		ARMADA_37XX_NB_DFS_EN	31
+#define ARMADA_37XX_NB_CPU_LOAD	0x30
+#define		ARMADA_37XX_NB_CPU_LOAD_MASK	0x3
+#define		ARMADA_37XX_DVFS_LOAD_0		0
+#define		ARMADA_37XX_DVFS_LOAD_1		1
+#define		ARMADA_37XX_DVFS_LOAD_2		2
+#define		ARMADA_37XX_DVFS_LOAD_3		3
+
 struct clk_periph_driver_data {
 	struct clk_hw_onecell_data *hw_data;
 	spinlock_t lock;
@@ -46,7 +68,18 @@ struct clk_double_div {
 	u8 shift2;
 };
 
+struct clk_pm_cpu {
+	struct clk_hw hw;
+	void __iomem *reg_mux;
+	u8 shift_mux;
+	u32 mask_mux;
+	void __iomem *reg_div;
+	u8 shift_div;
+	struct regmap *nb_pm_base;
+};
+
 #define to_clk_double_div(_hw) container_of(_hw, struct clk_double_div, hw)
+#define to_clk_pm_cpu(_hw) container_of(_hw, struct clk_pm_cpu, hw)
 
 struct clk_periph_data {
 	const char *name;
@@ -55,6 +88,7 @@ struct clk_periph_data {
 	struct clk_hw *mux_hw;
 	struct clk_hw *rate_hw;
 	struct clk_hw *gate_hw;
+	struct clk_hw *muxrate_hw;
 	bool is_double_div;
 };
 
@@ -79,7 +113,9 @@ static const struct clk_div_table clk_table2[] = {
 	{ .val = 1, .div = 4, },
 	{ .val = 0, .div = 0, }, /* last entry */
 };
+
 static const struct clk_ops clk_double_div_ops;
+static const struct clk_ops clk_pm_cpu_ops;
 
 #define PERIPH_GATE(_name, _bit)		\
 struct clk_gate gate_##_name = {		\
@@ -121,6 +157,18 @@ struct clk_divider rate_##_name = {		\
 	}					\
 };
 
+#define PERIPH_PM_CPU(_name, _shift1, _reg, _shift2)	\
+struct clk_pm_cpu muxrate_##_name = {		\
+	.reg_mux = (void *)TBG_SEL,		\
+	.mask_mux = 3,				\
+	.shift_mux = _shift1,			\
+	.reg_div = (void *)_reg,		\
+	.shift_div = _shift2,			\
+	.hw.init = &(struct clk_init_data){	\
+		.ops =  &clk_pm_cpu_ops,	\
+	}					\
+};
+
 #define PERIPH_CLK_FULL_DD(_name, _bit, _shift, _reg1, _reg2, _shift1, _shift2)\
 static PERIPH_GATE(_name, _bit);			    \
 static PERIPH_MUX(_name, _shift);			    \
@@ -135,10 +183,6 @@ static PERIPH_DIV(_name, _reg, _shift1, _table);
 static PERIPH_GATE(_name, _bit);			\
 static PERIPH_DIV(_name, _reg, _shift, _table);
 
-#define PERIPH_CLK_MUX_DIV(_name, _shift,  _reg, _shift_div, _table)	\
-static PERIPH_MUX(_name, _shift);			    \
-static PERIPH_DIV(_name, _reg, _shift_div, _table);
-
 #define PERIPH_CLK_MUX_DD(_name, _shift, _reg1, _reg2, _shift1, _shift2)\
 static PERIPH_MUX(_name, _shift);			    \
 static PERIPH_DOUBLEDIV(_name, _reg1, _reg2, _shift1, _shift2);
@@ -179,13 +223,12 @@ static PERIPH_DOUBLEDIV(_name, _reg1, _reg2, _shift1, _shift2);
 	  .rate_hw = &rate_##_name.hw,				\
 	}
 
-#define REF_CLK_MUX_DIV(_name)				\
+#define REF_CLK_PM_CPU(_name)				\
 	{ .name = #_name,				\
 	  .parent_names = (const char *[]){ "TBG-A-P",	\
 	      "TBG-B-P", "TBG-A-S", "TBG-B-S"},		\
 	  .num_parents = 4,				\
-	  .mux_hw = &mux_##_name.hw,			\
-	  .rate_hw = &rate_##_name.hw,			\
+	  .muxrate_hw = &muxrate_##_name.hw,		\
 	}
 
 #define REF_CLK_MUX_DD(_name)				\
@@ -215,9 +258,9 @@ PERIPH_CLK_FULL_DD(ddr_fclk, 21, 16, DIV_SEL0, DIV_SEL0, 15, 12);
 PERIPH_CLK_FULL(trace, 22, 18, DIV_SEL0, 20, clk_table6);
 PERIPH_CLK_FULL(counter, 23, 20, DIV_SEL0, 23, clk_table6);
 PERIPH_CLK_FULL_DD(eip97, 24, 24, DIV_SEL2, DIV_SEL2, 22, 19);
-PERIPH_CLK_MUX_DIV(cpu, 22, DIV_SEL0, 28, clk_table6);
+static PERIPH_PM_CPU(cpu, 22, DIV_SEL0, 28);
 
-static struct clk_periph_data data_nb[] ={
+static struct clk_periph_data data_nb[] = {
 	REF_CLK_FULL_DD(mmc),
 	REF_CLK_FULL_DD(sata_host),
 	REF_CLK_FULL_DD(sec_at),
@@ -234,7 +277,7 @@ static struct clk_periph_data data_nb[] ={
 	REF_CLK_FULL(trace),
 	REF_CLK_FULL(counter),
 	REF_CLK_FULL_DD(eip97),
-	REF_CLK_MUX_DIV(cpu),
+	REF_CLK_PM_CPU(cpu),
 	{ },
 };
 
@@ -281,7 +324,7 @@ static unsigned int get_div(void __iomem *reg, int shift)
 }
 
 static unsigned long clk_double_div_recalc_rate(struct clk_hw *hw,
-		unsigned long parent_rate)
+						unsigned long parent_rate)
 {
 	struct clk_double_div *double_div = to_clk_double_div(hw);
 	unsigned int div;
@@ -296,6 +339,222 @@ static const struct clk_ops clk_double_div_ops = {
 	.recalc_rate = clk_double_div_recalc_rate,
 };
 
+static void armada_3700_pm_dvfs_update_regs(unsigned int load_level,
+					    unsigned int *reg,
+					    unsigned int *offset)
+{
+	if (load_level <= ARMADA_37XX_DVFS_LOAD_1)
+		*reg = ARMADA_37XX_NB_L0L1;
+	else
+		*reg = ARMADA_37XX_NB_L2L3;
+
+	if (load_level == ARMADA_37XX_DVFS_LOAD_0 ||
+	    load_level ==  ARMADA_37XX_DVFS_LOAD_2)
+		*offset += ARMADA_37XX_NB_CONFIG_SHIFT;
+}
+
+static bool armada_3700_pm_dvfs_is_enabled(struct regmap *base)
+{
+	unsigned int val, reg = ARMADA_37XX_NB_DYN_MOD;
+
+	if (IS_ERR(base))
+		return false;
+
+	regmap_read(base, reg, &val);
+
+	return !!(val & BIT(ARMADA_37XX_NB_DFS_EN));
+}
+
+static unsigned int armada_3700_pm_dvfs_get_cpu_div(struct regmap *base)
+{
+	unsigned int reg = ARMADA_37XX_NB_CPU_LOAD;
+	unsigned int offset = ARMADA_37XX_NB_TBG_DIV_OFF;
+	unsigned int load_level, div;
+
+	/*
+	 * This function is always called after the function
+	 * armada_3700_pm_dvfs_is_enabled, so no need to check again
+	 * if the base is valid.
+	 */
+	regmap_read(base, reg, &load_level);
+
+	/*
+	 * The register and the offset inside this register accessed to
+	 * read the current divider depend on the load level
+	 */
+	load_level &= ARMADA_37XX_NB_CPU_LOAD_MASK;
+	armada_3700_pm_dvfs_update_regs(load_level, &reg, &offset);
+
+	regmap_read(base, reg, &div);
+
+	return (div >> offset) & ARMADA_37XX_NB_TBG_DIV_MASK;
+}
+
+static unsigned int armada_3700_pm_dvfs_get_cpu_parent(struct regmap *base)
+{
+	unsigned int reg = ARMADA_37XX_NB_CPU_LOAD;
+	unsigned int offset = ARMADA_37XX_NB_TBG_SEL_OFF;
+	unsigned int load_level, sel;
+
+	/*
+	 * This function is always called after the function
+	 * armada_3700_pm_dvfs_is_enabled, so no need to check again
+	 * if the base is valid
+	 */
+	regmap_read(base, reg, &load_level);
+
+	/*
+	 * The register and the offset inside this register accessed to
+	 * read the current divider depend on the load level
+	 */
+	load_level &= ARMADA_37XX_NB_CPU_LOAD_MASK;
+	armada_3700_pm_dvfs_update_regs(load_level, &reg, &offset);
+
+	regmap_read(base, reg, &sel);
+
+	return (sel >> offset) & ARMADA_37XX_NB_TBG_SEL_MASK;
+}
+
+static u8 clk_pm_cpu_get_parent(struct clk_hw *hw)
+{
+	struct clk_pm_cpu *pm_cpu = to_clk_pm_cpu(hw);
+	int num_parents = clk_hw_get_num_parents(hw);
+	u32 val;
+
+	if (armada_3700_pm_dvfs_is_enabled(pm_cpu->nb_pm_base)) {
+		val = armada_3700_pm_dvfs_get_cpu_parent(pm_cpu->nb_pm_base);
+	} else {
+		val = readl(pm_cpu->reg_mux) >> pm_cpu->shift_mux;
+		val &= pm_cpu->mask_mux;
+	}
+
+	if (val >= num_parents)
+		return -EINVAL;
+
+	return val;
+}
+
+static int clk_pm_cpu_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_pm_cpu *pm_cpu = to_clk_pm_cpu(hw);
+	struct regmap *base = pm_cpu->nb_pm_base;
+	int load_level;
+
+	/*
+	 * We set the clock parent only if the DVFS is available but
+	 * not enabled.
+	 */
+	if (IS_ERR(base) || armada_3700_pm_dvfs_is_enabled(base))
+		return -EINVAL;
+
+	/* Set the parent clock for all the load level */
+	for (load_level = 0; load_level < LOAD_LEVEL_NR; load_level++) {
+		unsigned int reg, mask,  val,
+			offset = ARMADA_37XX_NB_TBG_SEL_OFF;
+
+		armada_3700_pm_dvfs_update_regs(load_level, &reg, &offset);
+
+		val = index << offset;
+		mask = ARMADA_37XX_NB_TBG_SEL_MASK << offset;
+		regmap_update_bits(base, reg, mask, val);
+	}
+	return 0;
+}
+
+static unsigned long clk_pm_cpu_recalc_rate(struct clk_hw *hw,
+					    unsigned long parent_rate)
+{
+	struct clk_pm_cpu *pm_cpu = to_clk_pm_cpu(hw);
+	unsigned int div;
+
+	if (armada_3700_pm_dvfs_is_enabled(pm_cpu->nb_pm_base))
+		div = armada_3700_pm_dvfs_get_cpu_div(pm_cpu->nb_pm_base);
+	else
+		div = get_div(pm_cpu->reg_div, pm_cpu->shift_div);
+	return DIV_ROUND_UP_ULL((u64)parent_rate, div);
+}
+
+static long clk_pm_cpu_round_rate(struct clk_hw *hw, unsigned long rate,
+				  unsigned long *parent_rate)
+{
+	struct clk_pm_cpu *pm_cpu = to_clk_pm_cpu(hw);
+	struct regmap *base = pm_cpu->nb_pm_base;
+	unsigned int div = *parent_rate / rate;
+	unsigned int load_level;
+	/* only available when DVFS is enabled */
+	if (!armada_3700_pm_dvfs_is_enabled(base))
+		return -EINVAL;
+
+	for (load_level = 0; load_level < LOAD_LEVEL_NR; load_level++) {
+		unsigned int reg, val, offset = ARMADA_37XX_NB_TBG_DIV_OFF;
+
+		armada_3700_pm_dvfs_update_regs(load_level, &reg, &offset);
+
+		regmap_read(base, reg, &val);
+
+		val >>= offset;
+		val &= ARMADA_37XX_NB_TBG_DIV_MASK;
+		if (val == div)
+			/*
+			 * We found a load level matching the target
+			 * divider, switch to this load level and
+			 * return.
+			 */
+			return *parent_rate / div;
+	}
+
+	/* We didn't find any valid divider */
+	return -EINVAL;
+}
+
+static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate,
+			       unsigned long parent_rate)
+{
+	struct clk_pm_cpu *pm_cpu = to_clk_pm_cpu(hw);
+	struct regmap *base = pm_cpu->nb_pm_base;
+	unsigned int div = parent_rate / rate;
+	unsigned int load_level;
+
+	/* only available when DVFS is enabled */
+	if (!armada_3700_pm_dvfs_is_enabled(base))
+		return -EINVAL;
+
+	for (load_level = 0; load_level < LOAD_LEVEL_NR; load_level++) {
+		unsigned int reg, mask, val,
+			offset = ARMADA_37XX_NB_TBG_DIV_OFF;
+
+		armada_3700_pm_dvfs_update_regs(load_level, &reg, &offset);
+
+		regmap_read(base, reg, &val);
+		val >>= offset;
+		val &= ARMADA_37XX_NB_TBG_DIV_MASK;
+
+		if (val == div) {
+			/*
+			 * We found a load level matching the target
+			 * divider, switch to this load level and
+			 * return.
+			 */
+			reg = ARMADA_37XX_NB_CPU_LOAD;
+			mask = ARMADA_37XX_NB_CPU_LOAD_MASK;
+			regmap_update_bits(base, reg, mask, load_level);
+
+			return rate;
+		}
+	}
+
+	/* We didn't find any valid divider */
+	return -EINVAL;
+}
+
+static const struct clk_ops clk_pm_cpu_ops = {
+	.get_parent = clk_pm_cpu_get_parent,
+	.set_parent = clk_pm_cpu_set_parent,
+	.round_rate = clk_pm_cpu_round_rate,
+	.set_rate = clk_pm_cpu_set_rate,
+	.recalc_rate = clk_pm_cpu_recalc_rate,
+};
+
 static const struct of_device_id armada_3700_periph_clock_of_match[] = {
 	{ .compatible = "marvell,armada-3700-periph-clock-nb",
 	  .data = data_nb, },
@@ -303,6 +562,7 @@ static const struct of_device_id armada_3700_periph_clock_of_match[] = {
 	.data = data_sb, },
 	{ }
 };
+
 static int armada_3700_add_composite_clk(const struct clk_periph_data *data,
 					 void __iomem *reg, spinlock_t *lock,
 					 struct device *dev, struct clk_hw **hw)
@@ -354,15 +614,31 @@ static int armada_3700_add_composite_clk(const struct clk_periph_data *data,
 		}
 	}
 
-	*hw = clk_hw_register_composite(dev, data->name, data->parent_names,
-				       data->num_parents, mux_hw,
-				       mux_ops, rate_hw, rate_ops,
-				       gate_hw, gate_ops, CLK_IGNORE_UNUSED);
+	if (data->muxrate_hw) {
+		struct clk_pm_cpu *pmcpu_clk;
+		struct clk_hw *muxrate_hw = data->muxrate_hw;
+		struct regmap *map;
 
-	if (IS_ERR(*hw))
-		return PTR_ERR(*hw);
+		pmcpu_clk =  to_clk_pm_cpu(muxrate_hw);
+		pmcpu_clk->reg_mux = reg + (u64)pmcpu_clk->reg_mux;
+		pmcpu_clk->reg_div = reg + (u64)pmcpu_clk->reg_div;
 
-	return 0;
+		mux_hw = muxrate_hw;
+		rate_hw = muxrate_hw;
+		mux_ops = muxrate_hw->init->ops;
+		rate_ops = muxrate_hw->init->ops;
+
+		map = syscon_regmap_lookup_by_compatible(
+				"marvell,armada-3700-nb-pm");
+		pmcpu_clk->nb_pm_base = map;
+	}
+
+	*hw = clk_hw_register_composite(dev, data->name, data->parent_names,
+					data->num_parents, mux_hw,
+					mux_ops, rate_hw, rate_ops,
+					gate_hw, gate_ops, CLK_IGNORE_UNUSED);
+
+	return PTR_ERR_OR_ZERO(*hw);
 }
 
 static int armada_3700_periph_clock_probe(struct platform_device *pdev)
@@ -406,12 +682,11 @@ static int armada_3700_periph_clock_probe(struct platform_device *pdev)
 		if (armada_3700_add_composite_clk(&data[i], reg,
 						  &driver_data->lock, dev, hw))
 			dev_err(dev, "Can't register periph clock %s\n",
-			       data[i].name);
-
+				data[i].name);
 	}
 
 	ret = of_clk_add_hw_provider(np, of_clk_hw_onecell_get,
-				  driver_data->hw_data);
+				     driver_data->hw_data);
 	if (ret) {
 		for (i = 0; i < num_periph; i++)
 			clk_hw_unregister(driver_data->hw_data->hws[i]);
diff --git a/drivers/clk/nxp/clk-lpc32xx.c b/drivers/clk/nxp/clk-lpc32xx.c
index 7b359afd620e..f5d815f577e0 100644
--- a/drivers/clk/nxp/clk-lpc32xx.c
+++ b/drivers/clk/nxp/clk-lpc32xx.c
@@ -526,7 +526,7 @@ static unsigned long clk_pll_recalc_rate(struct clk_hw *hw,
 	    !(pll_is_valid(parent_rate, 1, 1000000, 20000000)
 	      && pll_is_valid(cco_rate, 1, 156000000, 320000000)
 	      && pll_is_valid(ref_rate, 1, 1000000, 27000000)))
-		pr_err("%s: PLL clocks are not in valid ranges: %lu/%lu/%lu",
+		pr_err("%s: PLL clocks are not in valid ranges: %lu/%lu/%lu\n",
 		       clk_hw_get_name(hw),
 		       parent_rate, cco_rate, ref_rate);
 
@@ -956,7 +956,7 @@ static unsigned long clk_divider_recalc_rate(struct clk_hw *hw,
 	val &= div_mask(divider->width);
 
 	return divider_recalc_rate(hw, parent_rate, val, divider->table,
-				   divider->flags);
+				   divider->flags, divider->width);
 }
 
 static long clk_divider_round_rate(struct clk_hw *hw, unsigned long rate,
@@ -1505,7 +1505,7 @@ static void __init lpc32xx_clk_init(struct device_node *np)
 		return;
 	}
 	if (clk_get_rate(clk_32k) != 32768) {
-		pr_err("invalid clock rate of external 32KHz oscillator");
+		pr_err("invalid clock rate of external 32KHz oscillator\n");
 		return;
 	}
 
diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c
index 42bdaa772be0..2d126df2bccd 100644
--- a/drivers/clk/pxa/clk-pxa3xx.c
+++ b/drivers/clk/pxa/clk-pxa3xx.c
@@ -329,12 +329,16 @@ static void __init pxa3xx_dummy_clocks_init(void)
 
 static void __init pxa3xx_base_clocks_init(void)
 {
+	struct clk *clk;
+
 	pxa3xx_register_plls();
 	pxa3xx_register_core();
 	clk_register_clk_pxa3xx_system_bus();
 	clk_register_clk_pxa3xx_ac97();
 	clk_register_clk_pxa3xx_smemc();
-	clk_register_gate(NULL, "CLK_POUT", "osc_13mhz", 0, OSCC, 11, 0, NULL);
+	clk = clk_register_gate(NULL, "CLK_POUT",
+				"osc_13mhz", 0, OSCC, 11, 0, NULL);
+	clk_register_clkdev(clk, "CLK_POUT", NULL);
 	clkdev_pxa_register(CLK_OSTIMER, "OSTIMER0", NULL,
 			    clk_register_fixed_factor(NULL, "os-timer0",
 						      "osc_13mhz", 0, 1, 4));
diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index 9f6c278deead..fbf4532f94b8 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -12,6 +12,27 @@ config COMMON_CLK_QCOM
 	select REGMAP_MMIO
 	select RESET_CONTROLLER
 
+config QCOM_A53PLL
+	tristate "MSM8916 A53 PLL"
+	depends on COMMON_CLK_QCOM
+	default ARCH_QCOM
+	help
+	  Support for the A53 PLL on MSM8916 devices. It provides
+	  the CPU with frequencies above 1GHz.
+	  Say Y if you want to support higher CPU frequencies on MSM8916
+	  devices.
+
+config QCOM_CLK_APCS_MSM8916
+	tristate "MSM8916 APCS Clock Controller"
+	depends on COMMON_CLK_QCOM
+	depends on QCOM_APCS_IPC || COMPILE_TEST
+	default ARCH_QCOM
+	help
+	  Support for the APCS Clock Controller on msm8916 devices. The
+	  APCS is managing the mux and divider which feeds the CPUs.
+	  Say Y if you want to support CPU frequency scaling on devices
+	  such as msm8916.
+
 config QCOM_CLK_RPM
 	tristate "RPM based Clock Controller"
 	depends on COMMON_CLK_QCOM && MFD_QCOM_RPM
@@ -196,3 +217,12 @@ config MSM_MMCC_8996
 	  Support for the multimedia clock controller on msm8996 devices.
 	  Say Y if you want to support multimedia devices such as display,
 	  graphics, video encode/decode, camera, etc.
+
+config SPMI_PMIC_CLKDIV
+	tristate "SPMI PMIC clkdiv Support"
+	depends on (COMMON_CLK_QCOM && SPMI) || COMPILE_TEST
+	help
+	  This driver supports the clkdiv functionality on the Qualcomm
+	  Technologies, Inc. SPMI PMIC. It configures the frequency of
+	  clkdiv outputs of the PMIC. These clocks are typically wired
+	  through alternate functions on GPIO pins.
diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile
index 26410d31446b..230332cf317e 100644
--- a/drivers/clk/qcom/Makefile
+++ b/drivers/clk/qcom/Makefile
@@ -10,6 +10,7 @@ clk-qcom-y += clk-rcg2.o
 clk-qcom-y += clk-branch.o
 clk-qcom-y += clk-regmap-divider.o
 clk-qcom-y += clk-regmap-mux.o
+clk-qcom-y += clk-regmap-mux-div.o
 clk-qcom-y += reset.o
 clk-qcom-$(CONFIG_QCOM_GDSC) += gdsc.o
 
@@ -32,5 +33,8 @@ obj-$(CONFIG_MSM_LCC_8960) += lcc-msm8960.o
 obj-$(CONFIG_MSM_MMCC_8960) += mmcc-msm8960.o
 obj-$(CONFIG_MSM_MMCC_8974) += mmcc-msm8974.o
 obj-$(CONFIG_MSM_MMCC_8996) += mmcc-msm8996.o
+obj-$(CONFIG_QCOM_A53PLL) += a53-pll.o
+obj-$(CONFIG_QCOM_CLK_APCS_MSM8916) += apcs-msm8916.o
 obj-$(CONFIG_QCOM_CLK_RPM) += clk-rpm.o
 obj-$(CONFIG_QCOM_CLK_SMD_RPM) += clk-smd-rpm.o
+obj-$(CONFIG_SPMI_PMIC_CLKDIV) += clk-spmi-pmic-div.o
diff --git a/drivers/clk/qcom/a53-pll.c b/drivers/clk/qcom/a53-pll.c
new file mode 100644
index 000000000000..45cfc57bff92
--- /dev/null
+++ b/drivers/clk/qcom/a53-pll.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Qualcomm A53 PLL driver
+ *
+ * Copyright (c) 2017, Linaro Limited
+ * Author: Georgi Djakov <georgi.djakov@linaro.org>
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/module.h>
+
+#include "clk-pll.h"
+#include "clk-regmap.h"
+
+static const struct pll_freq_tbl a53pll_freq[] = {
+	{  998400000, 52, 0x0, 0x1, 0 },
+	{ 1094400000, 57, 0x0, 0x1, 0 },
+	{ 1152000000, 62, 0x0, 0x1, 0 },
+	{ 1209600000, 63, 0x0, 0x1, 0 },
+	{ 1248000000, 65, 0x0, 0x1, 0 },
+	{ 1363200000, 71, 0x0, 0x1, 0 },
+	{ 1401600000, 73, 0x0, 0x1, 0 },
+	{ }
+};
+
+static const struct regmap_config a53pll_regmap_config = {
+	.reg_bits		= 32,
+	.reg_stride		= 4,
+	.val_bits		= 32,
+	.max_register		= 0x40,
+	.fast_io		= true,
+};
+
+static int qcom_a53pll_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct regmap *regmap;
+	struct resource *res;
+	struct clk_pll *pll;
+	void __iomem *base;
+	struct clk_init_data init = { };
+	int ret;
+
+	pll = devm_kzalloc(dev, sizeof(*pll), GFP_KERNEL);
+	if (!pll)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	regmap = devm_regmap_init_mmio(dev, base, &a53pll_regmap_config);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	pll->l_reg = 0x04;
+	pll->m_reg = 0x08;
+	pll->n_reg = 0x0c;
+	pll->config_reg = 0x14;
+	pll->mode_reg = 0x00;
+	pll->status_reg = 0x1c;
+	pll->status_bit = 16;
+	pll->freq_tbl = a53pll_freq;
+
+	init.name = "a53pll";
+	init.parent_names = (const char *[]){ "xo" };
+	init.num_parents = 1;
+	init.ops = &clk_pll_sr2_ops;
+	init.flags = CLK_IS_CRITICAL;
+	pll->clkr.hw.init = &init;
+
+	ret = devm_clk_register_regmap(dev, &pll->clkr);
+	if (ret) {
+		dev_err(dev, "failed to register regmap clock: %d\n", ret);
+		return ret;
+	}
+
+	ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get,
+					  &pll->clkr.hw);
+	if (ret) {
+		dev_err(dev, "failed to add clock provider: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id qcom_a53pll_match_table[] = {
+	{ .compatible = "qcom,msm8916-a53pll" },
+	{ }
+};
+
+static struct platform_driver qcom_a53pll_driver = {
+	.probe = qcom_a53pll_probe,
+	.driver = {
+		.name = "qcom-a53pll",
+		.of_match_table = qcom_a53pll_match_table,
+	},
+};
+module_platform_driver(qcom_a53pll_driver);
+
+MODULE_DESCRIPTION("Qualcomm A53 PLL Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/apcs-msm8916.c b/drivers/clk/qcom/apcs-msm8916.c
new file mode 100644
index 000000000000..246957f1a413
--- /dev/null
+++ b/drivers/clk/qcom/apcs-msm8916.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Qualcomm APCS clock controller driver
+ *
+ * Copyright (c) 2017, Linaro Limited
+ * Author: Georgi Djakov <georgi.djakov@linaro.org>
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include "clk-regmap.h"
+#include "clk-regmap-mux-div.h"
+
+static const u32 gpll0_a53cc_map[] = { 4, 5 };
+
+static const char * const gpll0_a53cc[] = {
+	"gpll0_vote",
+	"a53pll",
+};
+
+/*
+ * We use the notifier function for switching to a temporary safe configuration
+ * (mux and divider), while the A53 PLL is reconfigured.
+ */
+static int a53cc_notifier_cb(struct notifier_block *nb, unsigned long event,
+			     void *data)
+{
+	int ret = 0;
+	struct clk_regmap_mux_div *md = container_of(nb,
+						     struct clk_regmap_mux_div,
+						     clk_nb);
+	if (event == PRE_RATE_CHANGE)
+		/* set the mux and divider to safe frequency (400mhz) */
+		ret = mux_div_set_src_div(md, 4, 3);
+
+	return notifier_from_errno(ret);
+}
+
+static int qcom_apcs_msm8916_clk_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device *parent = dev->parent;
+	struct clk_regmap_mux_div *a53cc;
+	struct regmap *regmap;
+	struct clk_init_data init = { };
+	int ret;
+
+	regmap = dev_get_regmap(parent, NULL);
+	if (IS_ERR(regmap)) {
+		ret = PTR_ERR(regmap);
+		dev_err(dev, "failed to get regmap: %d\n", ret);
+		return ret;
+	}
+
+	a53cc = devm_kzalloc(dev, sizeof(*a53cc), GFP_KERNEL);
+	if (!a53cc)
+		return -ENOMEM;
+
+	init.name = "a53mux";
+	init.parent_names = gpll0_a53cc;
+	init.num_parents = ARRAY_SIZE(gpll0_a53cc);
+	init.ops = &clk_regmap_mux_div_ops;
+	init.flags = CLK_SET_RATE_PARENT;
+
+	a53cc->clkr.hw.init = &init;
+	a53cc->clkr.regmap = regmap;
+	a53cc->reg_offset = 0x50;
+	a53cc->hid_width = 5;
+	a53cc->hid_shift = 0;
+	a53cc->src_width = 3;
+	a53cc->src_shift = 8;
+	a53cc->parent_map = gpll0_a53cc_map;
+
+	a53cc->pclk = devm_clk_get(parent, NULL);
+	if (IS_ERR(a53cc->pclk)) {
+		ret = PTR_ERR(a53cc->pclk);
+		dev_err(dev, "failed to get clk: %d\n", ret);
+		return ret;
+	}
+
+	a53cc->clk_nb.notifier_call = a53cc_notifier_cb;
+	ret = clk_notifier_register(a53cc->pclk, &a53cc->clk_nb);
+	if (ret) {
+		dev_err(dev, "failed to register clock notifier: %d\n", ret);
+		return ret;
+	}
+
+	ret = devm_clk_register_regmap(dev, &a53cc->clkr);
+	if (ret) {
+		dev_err(dev, "failed to register regmap clock: %d\n", ret);
+		goto err;
+	}
+
+	ret = of_clk_add_hw_provider(parent->of_node, of_clk_hw_simple_get,
+				     &a53cc->clkr.hw);
+	if (ret) {
+		dev_err(dev, "failed to add clock provider: %d\n", ret);
+		goto err;
+	}
+
+	platform_set_drvdata(pdev, a53cc);
+
+	return 0;
+
+err:
+	clk_notifier_unregister(a53cc->pclk, &a53cc->clk_nb);
+	return ret;
+}
+
+static int qcom_apcs_msm8916_clk_remove(struct platform_device *pdev)
+{
+	struct clk_regmap_mux_div *a53cc = platform_get_drvdata(pdev);
+	struct device *parent = pdev->dev.parent;
+
+	clk_notifier_unregister(a53cc->pclk, &a53cc->clk_nb);
+	of_clk_del_provider(parent->of_node);
+
+	return 0;
+}
+
+static struct platform_driver qcom_apcs_msm8916_clk_driver = {
+	.probe = qcom_apcs_msm8916_clk_probe,
+	.remove = qcom_apcs_msm8916_clk_remove,
+	.driver = {
+		.name = "qcom-apcs-msm8916-clk",
+	},
+};
+module_platform_driver(qcom_apcs_msm8916_clk_driver);
+
+MODULE_AUTHOR("Georgi Djakov <georgi.djakov@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Qualcomm MSM8916 APCS clock driver");
diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index 47a1da3739ce..6d04cd96482a 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -20,7 +20,7 @@
 #include "clk-alpha-pll.h"
 #include "common.h"
 
-#define PLL_MODE		0x00
+#define PLL_MODE(p)		((p)->offset + 0x0)
 # define PLL_OUTCTRL		BIT(0)
 # define PLL_BYPASSNL		BIT(1)
 # define PLL_RESET_N		BIT(2)
@@ -32,35 +32,87 @@
 # define PLL_VOTE_FSM_ENA	BIT(20)
 # define PLL_FSM_ENA		BIT(20)
 # define PLL_VOTE_FSM_RESET	BIT(21)
+# define PLL_UPDATE		BIT(22)
+# define PLL_UPDATE_BYPASS	BIT(23)
 # define PLL_OFFLINE_ACK	BIT(28)
+# define ALPHA_PLL_ACK_LATCH	BIT(29)
 # define PLL_ACTIVE_FLAG	BIT(30)
 # define PLL_LOCK_DET		BIT(31)
 
-#define PLL_L_VAL		0x04
-#define PLL_ALPHA_VAL		0x08
-#define PLL_ALPHA_VAL_U		0x0c
+#define PLL_L_VAL(p)		((p)->offset + (p)->regs[PLL_OFF_L_VAL])
+#define PLL_ALPHA_VAL(p)	((p)->offset + (p)->regs[PLL_OFF_ALPHA_VAL])
+#define PLL_ALPHA_VAL_U(p)	((p)->offset + (p)->regs[PLL_OFF_ALPHA_VAL_U])
 
-#define PLL_USER_CTL		0x10
+#define PLL_USER_CTL(p)		((p)->offset + (p)->regs[PLL_OFF_USER_CTL])
 # define PLL_POST_DIV_SHIFT	8
-# define PLL_POST_DIV_MASK	0xf
+# define PLL_POST_DIV_MASK(p)	GENMASK((p)->width, 0)
 # define PLL_ALPHA_EN		BIT(24)
+# define PLL_ALPHA_MODE		BIT(25)
 # define PLL_VCO_SHIFT		20
 # define PLL_VCO_MASK		0x3
 
-#define PLL_USER_CTL_U		0x14
-
-#define PLL_CONFIG_CTL		0x18
-#define PLL_CONFIG_CTL_U	0x20
-#define PLL_TEST_CTL		0x1c
-#define PLL_TEST_CTL_U		0x20
-#define PLL_STATUS		0x24
+#define PLL_USER_CTL_U(p)	((p)->offset + (p)->regs[PLL_OFF_USER_CTL_U])
+
+#define PLL_CONFIG_CTL(p)	((p)->offset + (p)->regs[PLL_OFF_CONFIG_CTL])
+#define PLL_CONFIG_CTL_U(p)	((p)->offset + (p)->regs[PLL_OFF_CONFIG_CTL_U])
+#define PLL_TEST_CTL(p)		((p)->offset + (p)->regs[PLL_OFF_TEST_CTL])
+#define PLL_TEST_CTL_U(p)	((p)->offset + (p)->regs[PLL_OFF_TEST_CTL_U])
+#define PLL_STATUS(p)		((p)->offset + (p)->regs[PLL_OFF_STATUS])
+
+const u8 clk_alpha_pll_regs[][PLL_OFF_MAX_REGS] = {
+	[CLK_ALPHA_PLL_TYPE_DEFAULT] =  {
+		[PLL_OFF_L_VAL] = 0x04,
+		[PLL_OFF_ALPHA_VAL] = 0x08,
+		[PLL_OFF_ALPHA_VAL_U] = 0x0c,
+		[PLL_OFF_USER_CTL] = 0x10,
+		[PLL_OFF_USER_CTL_U] = 0x14,
+		[PLL_OFF_CONFIG_CTL] = 0x18,
+		[PLL_OFF_TEST_CTL] = 0x1c,
+		[PLL_OFF_TEST_CTL_U] = 0x20,
+		[PLL_OFF_STATUS] = 0x24,
+	},
+	[CLK_ALPHA_PLL_TYPE_HUAYRA] =  {
+		[PLL_OFF_L_VAL] = 0x04,
+		[PLL_OFF_ALPHA_VAL] = 0x08,
+		[PLL_OFF_USER_CTL] = 0x10,
+		[PLL_OFF_CONFIG_CTL] = 0x14,
+		[PLL_OFF_CONFIG_CTL_U] = 0x18,
+		[PLL_OFF_TEST_CTL] = 0x1c,
+		[PLL_OFF_TEST_CTL_U] = 0x20,
+		[PLL_OFF_STATUS] = 0x24,
+	},
+	[CLK_ALPHA_PLL_TYPE_BRAMMO] =  {
+		[PLL_OFF_L_VAL] = 0x04,
+		[PLL_OFF_ALPHA_VAL] = 0x08,
+		[PLL_OFF_ALPHA_VAL_U] = 0x0c,
+		[PLL_OFF_USER_CTL] = 0x10,
+		[PLL_OFF_CONFIG_CTL] = 0x18,
+		[PLL_OFF_TEST_CTL] = 0x1c,
+		[PLL_OFF_STATUS] = 0x24,
+	},
+};
+EXPORT_SYMBOL_GPL(clk_alpha_pll_regs);
 
 /*
  * Even though 40 bits are present, use only 32 for ease of calculation.
  */
 #define ALPHA_REG_BITWIDTH	40
-#define ALPHA_BITWIDTH		32
-#define ALPHA_16BIT_MASK	0xffff
+#define ALPHA_REG_16BIT_WIDTH	16
+#define ALPHA_BITWIDTH		32U
+#define ALPHA_SHIFT(w)		min(w, ALPHA_BITWIDTH)
+
+#define PLL_HUAYRA_M_WIDTH		8
+#define PLL_HUAYRA_M_SHIFT		8
+#define PLL_HUAYRA_M_MASK		0xff
+#define PLL_HUAYRA_N_SHIFT		0
+#define PLL_HUAYRA_N_MASK		0xff
+#define PLL_HUAYRA_ALPHA_WIDTH		16
+
+#define pll_alpha_width(p)					\
+		((PLL_ALPHA_VAL_U(p) - PLL_ALPHA_VAL(p) == 4) ?	\
+				 ALPHA_REG_BITWIDTH : ALPHA_REG_16BIT_WIDTH)
+
+#define pll_has_64bit_config(p)	((PLL_CONFIG_CTL_U(p) - PLL_CONFIG_CTL(p)) == 4)
 
 #define to_clk_alpha_pll(_hw) container_of(to_clk_regmap(_hw), \
 					   struct clk_alpha_pll, clkr)
@@ -71,18 +123,17 @@
 static int wait_for_pll(struct clk_alpha_pll *pll, u32 mask, bool inverse,
 			const char *action)
 {
-	u32 val, off;
+	u32 val;
 	int count;
 	int ret;
 	const char *name = clk_hw_get_name(&pll->clkr.hw);
 
-	off = pll->offset;
-	ret = regmap_read(pll->clkr.regmap, off + PLL_MODE, &val);
+	ret = regmap_read(pll->clkr.regmap, PLL_MODE(pll), &val);
 	if (ret)
 		return ret;
 
 	for (count = 100; count > 0; count--) {
-		ret = regmap_read(pll->clkr.regmap, off + PLL_MODE, &val);
+		ret = regmap_read(pll->clkr.regmap, PLL_MODE(pll), &val);
 		if (ret)
 			return ret;
 		if (inverse && !(val & mask))
@@ -109,16 +160,30 @@ static int wait_for_pll(struct clk_alpha_pll *pll, u32 mask, bool inverse,
 #define wait_for_pll_offline(pll) \
 	wait_for_pll(pll, PLL_OFFLINE_ACK, 0, "offline")
 
+#define wait_for_pll_update(pll) \
+	wait_for_pll(pll, PLL_UPDATE, 1, "update")
+
+#define wait_for_pll_update_ack_set(pll) \
+	wait_for_pll(pll, ALPHA_PLL_ACK_LATCH, 0, "update_ack_set")
+
+#define wait_for_pll_update_ack_clear(pll) \
+	wait_for_pll(pll, ALPHA_PLL_ACK_LATCH, 1, "update_ack_clear")
+
 void clk_alpha_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 			     const struct alpha_pll_config *config)
 {
 	u32 val, mask;
-	u32 off = pll->offset;
 
-	regmap_write(regmap, off + PLL_L_VAL, config->l);
-	regmap_write(regmap, off + PLL_ALPHA_VAL, config->alpha);
-	regmap_write(regmap, off + PLL_CONFIG_CTL, config->config_ctl_val);
-	regmap_write(regmap, off + PLL_CONFIG_CTL_U, config->config_ctl_hi_val);
+	regmap_write(regmap, PLL_L_VAL(pll), config->l);
+	regmap_write(regmap, PLL_ALPHA_VAL(pll), config->alpha);
+	regmap_write(regmap, PLL_CONFIG_CTL(pll), config->config_ctl_val);
+
+	if (pll_has_64bit_config(pll))
+		regmap_write(regmap, PLL_CONFIG_CTL_U(pll),
+			     config->config_ctl_hi_val);
+
+	if (pll_alpha_width(pll) > 32)
+		regmap_write(regmap, PLL_ALPHA_VAL_U(pll), config->alpha_hi);
 
 	val = config->main_output_mask;
 	val |= config->aux_output_mask;
@@ -127,6 +192,8 @@ void clk_alpha_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 	val |= config->pre_div_val;
 	val |= config->post_div_val;
 	val |= config->vco_val;
+	val |= config->alpha_en_mask;
+	val |= config->alpha_mode_mask;
 
 	mask = config->main_output_mask;
 	mask |= config->aux_output_mask;
@@ -136,20 +203,19 @@ void clk_alpha_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 	mask |= config->post_div_mask;
 	mask |= config->vco_mask;
 
-	regmap_update_bits(regmap, off + PLL_USER_CTL, mask, val);
+	regmap_update_bits(regmap, PLL_USER_CTL(pll), mask, val);
 
 	if (pll->flags & SUPPORTS_FSM_MODE)
-		qcom_pll_set_fsm_mode(regmap, off + PLL_MODE, 6, 0);
+		qcom_pll_set_fsm_mode(regmap, PLL_MODE(pll), 6, 0);
 }
 
 static int clk_alpha_pll_hwfsm_enable(struct clk_hw *hw)
 {
 	int ret;
-	u32 val, off;
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
+	u32 val;
 
-	off = pll->offset;
-	ret = regmap_read(pll->clkr.regmap, off + PLL_MODE, &val);
+	ret = regmap_read(pll->clkr.regmap, PLL_MODE(pll), &val);
 	if (ret)
 		return ret;
 
@@ -158,7 +224,7 @@ static int clk_alpha_pll_hwfsm_enable(struct clk_hw *hw)
 	if (pll->flags & SUPPORTS_OFFLINE_REQ)
 		val &= ~PLL_OFFLINE_REQ;
 
-	ret = regmap_write(pll->clkr.regmap, off + PLL_MODE, val);
+	ret = regmap_write(pll->clkr.regmap, PLL_MODE(pll), val);
 	if (ret)
 		return ret;
 
@@ -171,16 +237,15 @@ static int clk_alpha_pll_hwfsm_enable(struct clk_hw *hw)
 static void clk_alpha_pll_hwfsm_disable(struct clk_hw *hw)
 {
 	int ret;
-	u32 val, off;
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
+	u32 val;
 
-	off = pll->offset;
-	ret = regmap_read(pll->clkr.regmap, off + PLL_MODE, &val);
+	ret = regmap_read(pll->clkr.regmap, PLL_MODE(pll), &val);
 	if (ret)
 		return;
 
 	if (pll->flags & SUPPORTS_OFFLINE_REQ) {
-		ret = regmap_update_bits(pll->clkr.regmap, off + PLL_MODE,
+		ret = regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll),
 					 PLL_OFFLINE_REQ, PLL_OFFLINE_REQ);
 		if (ret)
 			return;
@@ -191,7 +256,7 @@ static void clk_alpha_pll_hwfsm_disable(struct clk_hw *hw)
 	}
 
 	/* Disable hwfsm */
-	ret = regmap_update_bits(pll->clkr.regmap, off + PLL_MODE,
+	ret = regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll),
 				 PLL_FSM_ENA, 0);
 	if (ret)
 		return;
@@ -202,11 +267,10 @@ static void clk_alpha_pll_hwfsm_disable(struct clk_hw *hw)
 static int pll_is_enabled(struct clk_hw *hw, u32 mask)
 {
 	int ret;
-	u32 val, off;
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
+	u32 val;
 
-	off = pll->offset;
-	ret = regmap_read(pll->clkr.regmap, off + PLL_MODE, &val);
+	ret = regmap_read(pll->clkr.regmap, PLL_MODE(pll), &val);
 	if (ret)
 		return ret;
 
@@ -227,12 +291,10 @@ static int clk_alpha_pll_enable(struct clk_hw *hw)
 {
 	int ret;
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
-	u32 val, mask, off;
-
-	off = pll->offset;
+	u32 val, mask;
 
 	mask = PLL_OUTCTRL | PLL_RESET_N | PLL_BYPASSNL;
-	ret = regmap_read(pll->clkr.regmap, off + PLL_MODE, &val);
+	ret = regmap_read(pll->clkr.regmap, PLL_MODE(pll), &val);
 	if (ret)
 		return ret;
 
@@ -248,7 +310,7 @@ static int clk_alpha_pll_enable(struct clk_hw *hw)
 	if ((val & mask) == mask)
 		return 0;
 
-	ret = regmap_update_bits(pll->clkr.regmap, off + PLL_MODE,
+	ret = regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll),
 				 PLL_BYPASSNL, PLL_BYPASSNL);
 	if (ret)
 		return ret;
@@ -260,7 +322,7 @@ static int clk_alpha_pll_enable(struct clk_hw *hw)
 	mb();
 	udelay(5);
 
-	ret = regmap_update_bits(pll->clkr.regmap, off + PLL_MODE,
+	ret = regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll),
 				 PLL_RESET_N, PLL_RESET_N);
 	if (ret)
 		return ret;
@@ -269,7 +331,7 @@ static int clk_alpha_pll_enable(struct clk_hw *hw)
 	if (ret)
 		return ret;
 
-	ret = regmap_update_bits(pll->clkr.regmap, off + PLL_MODE,
+	ret = regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll),
 				 PLL_OUTCTRL, PLL_OUTCTRL);
 
 	/* Ensure that the write above goes through before returning. */
@@ -281,11 +343,9 @@ static void clk_alpha_pll_disable(struct clk_hw *hw)
 {
 	int ret;
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
-	u32 val, mask, off;
-
-	off = pll->offset;
+	u32 val, mask;
 
-	ret = regmap_read(pll->clkr.regmap, off + PLL_MODE, &val);
+	ret = regmap_read(pll->clkr.regmap, PLL_MODE(pll), &val);
 	if (ret)
 		return;
 
@@ -296,23 +356,25 @@ static void clk_alpha_pll_disable(struct clk_hw *hw)
 	}
 
 	mask = PLL_OUTCTRL;
-	regmap_update_bits(pll->clkr.regmap, off + PLL_MODE, mask, 0);
+	regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll), mask, 0);
 
 	/* Delay of 2 output clock ticks required until output is disabled */
 	mb();
 	udelay(1);
 
 	mask = PLL_RESET_N | PLL_BYPASSNL;
-	regmap_update_bits(pll->clkr.regmap, off + PLL_MODE, mask, 0);
+	regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll), mask, 0);
 }
 
-static unsigned long alpha_pll_calc_rate(u64 prate, u32 l, u32 a)
+static unsigned long
+alpha_pll_calc_rate(u64 prate, u32 l, u32 a, u32 alpha_width)
 {
-	return (prate * l) + ((prate * a) >> ALPHA_BITWIDTH);
+	return (prate * l) + ((prate * a) >> ALPHA_SHIFT(alpha_width));
 }
 
 static unsigned long
-alpha_pll_round_rate(unsigned long rate, unsigned long prate, u32 *l, u64 *a)
+alpha_pll_round_rate(unsigned long rate, unsigned long prate, u32 *l, u64 *a,
+		     u32 alpha_width)
 {
 	u64 remainder;
 	u64 quotient;
@@ -327,14 +389,15 @@ alpha_pll_round_rate(unsigned long rate, unsigned long prate, u32 *l, u64 *a)
 	}
 
 	/* Upper ALPHA_BITWIDTH bits of Alpha */
-	quotient = remainder << ALPHA_BITWIDTH;
+	quotient = remainder << ALPHA_SHIFT(alpha_width);
+
 	remainder = do_div(quotient, prate);
 
 	if (remainder)
 		quotient++;
 
 	*a = quotient;
-	return alpha_pll_calc_rate(prate, *l, *a);
+	return alpha_pll_calc_rate(prate, *l, *a, alpha_width);
 }
 
 static const struct pll_vco *
@@ -356,71 +419,138 @@ clk_alpha_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	u32 l, low, high, ctl;
 	u64 a = 0, prate = parent_rate;
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
-	u32 off = pll->offset;
+	u32 alpha_width = pll_alpha_width(pll);
 
-	regmap_read(pll->clkr.regmap, off + PLL_L_VAL, &l);
+	regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l);
 
-	regmap_read(pll->clkr.regmap, off + PLL_USER_CTL, &ctl);
+	regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl);
 	if (ctl & PLL_ALPHA_EN) {
-		regmap_read(pll->clkr.regmap, off + PLL_ALPHA_VAL, &low);
-		if (pll->flags & SUPPORTS_16BIT_ALPHA) {
-			a = low & ALPHA_16BIT_MASK;
-		} else {
-			regmap_read(pll->clkr.regmap, off + PLL_ALPHA_VAL_U,
+		regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &low);
+		if (alpha_width > 32) {
+			regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL_U(pll),
 				    &high);
 			a = (u64)high << 32 | low;
-			a >>= ALPHA_REG_BITWIDTH - ALPHA_BITWIDTH;
+		} else {
+			a = low & GENMASK(alpha_width - 1, 0);
 		}
+
+		if (alpha_width > ALPHA_BITWIDTH)
+			a >>= alpha_width - ALPHA_BITWIDTH;
 	}
 
-	return alpha_pll_calc_rate(prate, l, a);
+	return alpha_pll_calc_rate(prate, l, a, alpha_width);
 }
 
-static int clk_alpha_pll_set_rate(struct clk_hw *hw, unsigned long rate,
-				  unsigned long prate)
+static int clk_alpha_pll_update_latch(struct clk_alpha_pll *pll,
+				      int (*is_enabled)(struct clk_hw *))
+{
+	int ret;
+	u32 mode;
+
+	if (!is_enabled(&pll->clkr.hw) ||
+	    !(pll->flags & SUPPORTS_DYNAMIC_UPDATE))
+		return 0;
+
+	regmap_read(pll->clkr.regmap, PLL_MODE(pll), &mode);
+
+	/* Latch the input to the PLL */
+	regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll), PLL_UPDATE,
+			   PLL_UPDATE);
+
+	/* Wait for 2 reference cycle before checking ACK bit */
+	udelay(1);
+
+	/*
+	 * PLL will latch the new L, Alpha and freq control word.
+	 * PLL will respond by raising PLL_ACK_LATCH output when new programming
+	 * has been latched in and PLL is being updated. When
+	 * UPDATE_LOGIC_BYPASS bit is not set, PLL_UPDATE will be cleared
+	 * automatically by hardware when PLL_ACK_LATCH is asserted by PLL.
+	 */
+	if (mode & PLL_UPDATE_BYPASS) {
+		ret = wait_for_pll_update_ack_set(pll);
+		if (ret)
+			return ret;
+
+		regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll), PLL_UPDATE, 0);
+	} else {
+		ret = wait_for_pll_update(pll);
+		if (ret)
+			return ret;
+	}
+
+	ret = wait_for_pll_update_ack_clear(pll);
+	if (ret)
+		return ret;
+
+	/* Wait for PLL output to stabilize */
+	udelay(10);
+
+	return 0;
+}
+
+static int __clk_alpha_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long prate,
+				    int (*is_enabled)(struct clk_hw *))
 {
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
 	const struct pll_vco *vco;
-	u32 l, off = pll->offset;
+	u32 l, alpha_width = pll_alpha_width(pll);
 	u64 a;
 
-	rate = alpha_pll_round_rate(rate, prate, &l, &a);
+	rate = alpha_pll_round_rate(rate, prate, &l, &a, alpha_width);
 	vco = alpha_pll_find_vco(pll, rate);
-	if (!vco) {
+	if (pll->vco_table && !vco) {
 		pr_err("alpha pll not in a valid vco range\n");
 		return -EINVAL;
 	}
 
-	regmap_write(pll->clkr.regmap, off + PLL_L_VAL, l);
+	regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l);
 
-	if (pll->flags & SUPPORTS_16BIT_ALPHA) {
-		regmap_write(pll->clkr.regmap, off + PLL_ALPHA_VAL,
-			     a & ALPHA_16BIT_MASK);
-	} else {
-		a <<= (ALPHA_REG_BITWIDTH - ALPHA_BITWIDTH);
-		regmap_write(pll->clkr.regmap, off + PLL_ALPHA_VAL_U, a >> 32);
+	if (alpha_width > ALPHA_BITWIDTH)
+		a <<= alpha_width - ALPHA_BITWIDTH;
+
+	if (alpha_width > 32)
+		regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL_U(pll), a >> 32);
+
+	regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), a);
+
+	if (vco) {
+		regmap_update_bits(pll->clkr.regmap, PLL_USER_CTL(pll),
+				   PLL_VCO_MASK << PLL_VCO_SHIFT,
+				   vco->val << PLL_VCO_SHIFT);
 	}
 
-	regmap_update_bits(pll->clkr.regmap, off + PLL_USER_CTL,
-			   PLL_VCO_MASK << PLL_VCO_SHIFT,
-			   vco->val << PLL_VCO_SHIFT);
+	regmap_update_bits(pll->clkr.regmap, PLL_USER_CTL(pll),
+			   PLL_ALPHA_EN, PLL_ALPHA_EN);
 
-	regmap_update_bits(pll->clkr.regmap, off + PLL_USER_CTL, PLL_ALPHA_EN,
-			   PLL_ALPHA_EN);
+	return clk_alpha_pll_update_latch(pll, is_enabled);
+}
 
-	return 0;
+static int clk_alpha_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+				  unsigned long prate)
+{
+	return __clk_alpha_pll_set_rate(hw, rate, prate,
+					clk_alpha_pll_is_enabled);
+}
+
+static int clk_alpha_pll_hwfsm_set_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long prate)
+{
+	return __clk_alpha_pll_set_rate(hw, rate, prate,
+					clk_alpha_pll_hwfsm_is_enabled);
 }
 
 static long clk_alpha_pll_round_rate(struct clk_hw *hw, unsigned long rate,
 				     unsigned long *prate)
 {
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
-	u32 l;
+	u32 l, alpha_width = pll_alpha_width(pll);
 	u64 a;
 	unsigned long min_freq, max_freq;
 
-	rate = alpha_pll_round_rate(rate, *prate, &l, &a);
-	if (alpha_pll_find_vco(pll, rate))
+	rate = alpha_pll_round_rate(rate, *prate, &l, &a, alpha_width);
+	if (!pll->vco_table || alpha_pll_find_vco(pll, rate))
 		return rate;
 
 	min_freq = pll->vco_table[0].min_freq;
@@ -429,6 +559,158 @@ static long clk_alpha_pll_round_rate(struct clk_hw *hw, unsigned long rate,
 	return clamp(rate, min_freq, max_freq);
 }
 
+static unsigned long
+alpha_huayra_pll_calc_rate(u64 prate, u32 l, u32 a)
+{
+	/*
+	 * a contains 16 bit alpha_val in two’s compliment number in the range
+	 * of [-0.5, 0.5).
+	 */
+	if (a >= BIT(PLL_HUAYRA_ALPHA_WIDTH - 1))
+		l -= 1;
+
+	return (prate * l) + (prate * a >> PLL_HUAYRA_ALPHA_WIDTH);
+}
+
+static unsigned long
+alpha_huayra_pll_round_rate(unsigned long rate, unsigned long prate,
+			    u32 *l, u32 *a)
+{
+	u64 remainder;
+	u64 quotient;
+
+	quotient = rate;
+	remainder = do_div(quotient, prate);
+	*l = quotient;
+
+	if (!remainder) {
+		*a = 0;
+		return rate;
+	}
+
+	quotient = remainder << PLL_HUAYRA_ALPHA_WIDTH;
+	remainder = do_div(quotient, prate);
+
+	if (remainder)
+		quotient++;
+
+	/*
+	 * alpha_val should be in two’s compliment number in the range
+	 * of [-0.5, 0.5) so if quotient >= 0.5 then increment the l value
+	 * since alpha value will be subtracted in this case.
+	 */
+	if (quotient >= BIT(PLL_HUAYRA_ALPHA_WIDTH - 1))
+		*l += 1;
+
+	*a = quotient;
+	return alpha_huayra_pll_calc_rate(prate, *l, *a);
+}
+
+static unsigned long
+alpha_pll_huayra_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
+{
+	u64 rate = parent_rate, tmp;
+	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
+	u32 l, alpha = 0, ctl, alpha_m, alpha_n;
+
+	regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l);
+	regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl);
+
+	if (ctl & PLL_ALPHA_EN) {
+		regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &alpha);
+		/*
+		 * Depending upon alpha_mode, it can be treated as M/N value or
+		 * as a two’s compliment number. When alpha_mode=1,
+		 * pll_alpha_val<15:8>=M and pll_apla_val<7:0>=N
+		 *
+		 *		Fout=FIN*(L+(M/N))
+		 *
+		 * M is a signed number (-128 to 127) and N is unsigned
+		 * (0 to 255). M/N has to be within +/-0.5.
+		 *
+		 * When alpha_mode=0, it is a two’s compliment number in the
+		 * range [-0.5, 0.5).
+		 *
+		 *		Fout=FIN*(L+(alpha_val)/2^16)
+		 *
+		 * where alpha_val is two’s compliment number.
+		 */
+		if (!(ctl & PLL_ALPHA_MODE))
+			return alpha_huayra_pll_calc_rate(rate, l, alpha);
+
+		alpha_m = alpha >> PLL_HUAYRA_M_SHIFT & PLL_HUAYRA_M_MASK;
+		alpha_n = alpha >> PLL_HUAYRA_N_SHIFT & PLL_HUAYRA_N_MASK;
+
+		rate *= l;
+		tmp = parent_rate;
+		if (alpha_m >= BIT(PLL_HUAYRA_M_WIDTH - 1)) {
+			alpha_m = BIT(PLL_HUAYRA_M_WIDTH) - alpha_m;
+			tmp *= alpha_m;
+			do_div(tmp, alpha_n);
+			rate -= tmp;
+		} else {
+			tmp *= alpha_m;
+			do_div(tmp, alpha_n);
+			rate += tmp;
+		}
+
+		return rate;
+	}
+
+	return alpha_huayra_pll_calc_rate(rate, l, alpha);
+}
+
+static int alpha_pll_huayra_set_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long prate)
+{
+	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
+	u32 l, a, ctl, cur_alpha = 0;
+
+	rate = alpha_huayra_pll_round_rate(rate, prate, &l, &a);
+
+	regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl);
+
+	if (ctl & PLL_ALPHA_EN)
+		regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &cur_alpha);
+
+	/*
+	 * Huayra PLL supports PLL dynamic programming. User can change L_VAL,
+	 * without having to go through the power on sequence.
+	 */
+	if (clk_alpha_pll_is_enabled(hw)) {
+		if (cur_alpha != a) {
+			pr_err("clock needs to be gated %s\n",
+			       clk_hw_get_name(hw));
+			return -EBUSY;
+		}
+
+		regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l);
+		/* Ensure that the write above goes to detect L val change. */
+		mb();
+		return wait_for_pll_enable_lock(pll);
+	}
+
+	regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l);
+	regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), a);
+
+	if (a == 0)
+		regmap_update_bits(pll->clkr.regmap, PLL_USER_CTL(pll),
+				   PLL_ALPHA_EN, 0x0);
+	else
+		regmap_update_bits(pll->clkr.regmap, PLL_USER_CTL(pll),
+				   PLL_ALPHA_EN | PLL_ALPHA_MODE, PLL_ALPHA_EN);
+
+	return 0;
+}
+
+static long alpha_pll_huayra_round_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long *prate)
+{
+	u32 l, a;
+
+	return alpha_huayra_pll_round_rate(rate, *prate, &l, &a);
+}
+
 const struct clk_ops clk_alpha_pll_ops = {
 	.enable = clk_alpha_pll_enable,
 	.disable = clk_alpha_pll_disable,
@@ -439,13 +721,23 @@ const struct clk_ops clk_alpha_pll_ops = {
 };
 EXPORT_SYMBOL_GPL(clk_alpha_pll_ops);
 
+const struct clk_ops clk_alpha_pll_huayra_ops = {
+	.enable = clk_alpha_pll_enable,
+	.disable = clk_alpha_pll_disable,
+	.is_enabled = clk_alpha_pll_is_enabled,
+	.recalc_rate = alpha_pll_huayra_recalc_rate,
+	.round_rate = alpha_pll_huayra_round_rate,
+	.set_rate = alpha_pll_huayra_set_rate,
+};
+EXPORT_SYMBOL_GPL(clk_alpha_pll_huayra_ops);
+
 const struct clk_ops clk_alpha_pll_hwfsm_ops = {
 	.enable = clk_alpha_pll_hwfsm_enable,
 	.disable = clk_alpha_pll_hwfsm_disable,
 	.is_enabled = clk_alpha_pll_hwfsm_is_enabled,
 	.recalc_rate = clk_alpha_pll_recalc_rate,
 	.round_rate = clk_alpha_pll_round_rate,
-	.set_rate = clk_alpha_pll_set_rate,
+	.set_rate = clk_alpha_pll_hwfsm_set_rate,
 };
 EXPORT_SYMBOL_GPL(clk_alpha_pll_hwfsm_ops);
 
@@ -455,10 +747,10 @@ clk_alpha_pll_postdiv_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	struct clk_alpha_pll_postdiv *pll = to_clk_alpha_pll_postdiv(hw);
 	u32 ctl;
 
-	regmap_read(pll->clkr.regmap, pll->offset + PLL_USER_CTL, &ctl);
+	regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl);
 
 	ctl >>= PLL_POST_DIV_SHIFT;
-	ctl &= PLL_POST_DIV_MASK;
+	ctl &= PLL_POST_DIV_MASK(pll);
 
 	return parent_rate >> fls(ctl);
 }
@@ -472,16 +764,48 @@ static const struct clk_div_table clk_alpha_div_table[] = {
 	{ }
 };
 
+static const struct clk_div_table clk_alpha_2bit_div_table[] = {
+	{ 0x0, 1 },
+	{ 0x1, 2 },
+	{ 0x3, 4 },
+	{ }
+};
+
 static long
 clk_alpha_pll_postdiv_round_rate(struct clk_hw *hw, unsigned long rate,
 				 unsigned long *prate)
 {
 	struct clk_alpha_pll_postdiv *pll = to_clk_alpha_pll_postdiv(hw);
+	const struct clk_div_table *table;
 
-	return divider_round_rate(hw, rate, prate, clk_alpha_div_table,
+	if (pll->width == 2)
+		table = clk_alpha_2bit_div_table;
+	else
+		table = clk_alpha_div_table;
+
+	return divider_round_rate(hw, rate, prate, table,
 				  pll->width, CLK_DIVIDER_POWER_OF_TWO);
 }
 
+static long
+clk_alpha_pll_postdiv_round_ro_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long *prate)
+{
+	struct clk_alpha_pll_postdiv *pll = to_clk_alpha_pll_postdiv(hw);
+	u32 ctl, div;
+
+	regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl);
+
+	ctl >>= PLL_POST_DIV_SHIFT;
+	ctl &= BIT(pll->width) - 1;
+	div = 1 << fls(ctl);
+
+	if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)
+		*prate = clk_hw_round_rate(clk_hw_get_parent(hw), div * rate);
+
+	return DIV_ROUND_UP_ULL((u64)*prate, div);
+}
+
 static int clk_alpha_pll_postdiv_set_rate(struct clk_hw *hw, unsigned long rate,
 					  unsigned long parent_rate)
 {
@@ -491,8 +815,8 @@ static int clk_alpha_pll_postdiv_set_rate(struct clk_hw *hw, unsigned long rate,
 	/* 16 -> 0xf, 8 -> 0x7, 4 -> 0x3, 2 -> 0x1, 1 -> 0x0 */
 	div = DIV_ROUND_UP_ULL((u64)parent_rate, rate) - 1;
 
-	return regmap_update_bits(pll->clkr.regmap, pll->offset + PLL_USER_CTL,
-				  PLL_POST_DIV_MASK << PLL_POST_DIV_SHIFT,
+	return regmap_update_bits(pll->clkr.regmap, PLL_USER_CTL(pll),
+				  PLL_POST_DIV_MASK(pll) << PLL_POST_DIV_SHIFT,
 				  div << PLL_POST_DIV_SHIFT);
 }
 
@@ -502,3 +826,9 @@ const struct clk_ops clk_alpha_pll_postdiv_ops = {
 	.set_rate = clk_alpha_pll_postdiv_set_rate,
 };
 EXPORT_SYMBOL_GPL(clk_alpha_pll_postdiv_ops);
+
+const struct clk_ops clk_alpha_pll_postdiv_ro_ops = {
+	.round_rate = clk_alpha_pll_postdiv_round_ro_rate,
+	.recalc_rate = clk_alpha_pll_postdiv_recalc_rate,
+};
+EXPORT_SYMBOL_GPL(clk_alpha_pll_postdiv_ro_ops);
diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h
index d6e1ee2c7348..7593e8a56cf2 100644
--- a/drivers/clk/qcom/clk-alpha-pll.h
+++ b/drivers/clk/qcom/clk-alpha-pll.h
@@ -17,6 +17,30 @@
 #include <linux/clk-provider.h>
 #include "clk-regmap.h"
 
+/* Alpha PLL types */
+enum {
+	CLK_ALPHA_PLL_TYPE_DEFAULT,
+	CLK_ALPHA_PLL_TYPE_HUAYRA,
+	CLK_ALPHA_PLL_TYPE_BRAMMO,
+	CLK_ALPHA_PLL_TYPE_MAX,
+};
+
+enum {
+	PLL_OFF_L_VAL,
+	PLL_OFF_ALPHA_VAL,
+	PLL_OFF_ALPHA_VAL_U,
+	PLL_OFF_USER_CTL,
+	PLL_OFF_USER_CTL_U,
+	PLL_OFF_CONFIG_CTL,
+	PLL_OFF_CONFIG_CTL_U,
+	PLL_OFF_TEST_CTL,
+	PLL_OFF_TEST_CTL_U,
+	PLL_OFF_STATUS,
+	PLL_OFF_MAX_REGS
+};
+
+extern const u8 clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_MAX][PLL_OFF_MAX_REGS];
+
 struct pll_vco {
 	unsigned long min_freq;
 	unsigned long max_freq;
@@ -27,16 +51,18 @@ struct pll_vco {
  * struct clk_alpha_pll - phase locked loop (PLL)
  * @offset: base address of registers
  * @vco_table: array of VCO settings
+ * @regs: alpha pll register map (see @clk_alpha_pll_regs)
  * @clkr: regmap clock handle
  */
 struct clk_alpha_pll {
 	u32 offset;
+	const u8 *regs;
 
 	const struct pll_vco *vco_table;
 	size_t num_vco;
 #define SUPPORTS_OFFLINE_REQ	BIT(0)
-#define SUPPORTS_16BIT_ALPHA	BIT(1)
 #define SUPPORTS_FSM_MODE	BIT(2)
+#define SUPPORTS_DYNAMIC_UPDATE	BIT(3)
 	u8 flags;
 
 	struct clk_regmap clkr;
@@ -45,12 +71,14 @@ struct clk_alpha_pll {
 /**
  * struct clk_alpha_pll_postdiv - phase locked loop (PLL) post-divider
  * @offset: base address of registers
+ * @regs: alpha pll register map (see @clk_alpha_pll_regs)
  * @width: width of post-divider
  * @clkr: regmap clock handle
  */
 struct clk_alpha_pll_postdiv {
 	u32 offset;
 	u8 width;
+	const u8 *regs;
 
 	struct clk_regmap clkr;
 };
@@ -58,12 +86,15 @@ struct clk_alpha_pll_postdiv {
 struct alpha_pll_config {
 	u32 l;
 	u32 alpha;
+	u32 alpha_hi;
 	u32 config_ctl_val;
 	u32 config_ctl_hi_val;
 	u32 main_output_mask;
 	u32 aux_output_mask;
 	u32 aux2_output_mask;
 	u32 early_output_mask;
+	u32 alpha_en_mask;
+	u32 alpha_mode_mask;
 	u32 pre_div_val;
 	u32 pre_div_mask;
 	u32 post_div_val;
@@ -75,6 +106,8 @@ struct alpha_pll_config {
 extern const struct clk_ops clk_alpha_pll_ops;
 extern const struct clk_ops clk_alpha_pll_hwfsm_ops;
 extern const struct clk_ops clk_alpha_pll_postdiv_ops;
+extern const struct clk_ops clk_alpha_pll_huayra_ops;
+extern const struct clk_ops clk_alpha_pll_postdiv_ro_ops;
 
 void clk_alpha_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 			     const struct alpha_pll_config *config);
diff --git a/drivers/clk/qcom/clk-rcg.h b/drivers/clk/qcom/clk-rcg.h
index a2495457e564..2a7489a84e69 100644
--- a/drivers/clk/qcom/clk-rcg.h
+++ b/drivers/clk/qcom/clk-rcg.h
@@ -26,16 +26,6 @@ struct freq_tbl {
 };
 
 /**
- * struct parent_map - map table for PLL source select configuration values
- * @src: source PLL
- * @cfg: configuration value
- */
-struct parent_map {
-	u8 src;
-	u8 cfg;
-};
-
-/**
  * struct mn - M/N:D counter
  * @mnctr_en_bit: bit to enable mn counter
  * @mnctr_reset_bit: bit to assert mn counter reset
diff --git a/drivers/clk/qcom/clk-regmap-divider.c b/drivers/clk/qcom/clk-regmap-divider.c
index 53484912301e..4e9b8c2c8980 100644
--- a/drivers/clk/qcom/clk-regmap-divider.c
+++ b/drivers/clk/qcom/clk-regmap-divider.c
@@ -23,6 +23,29 @@ static inline struct clk_regmap_div *to_clk_regmap_div(struct clk_hw *hw)
 	return container_of(to_clk_regmap(hw), struct clk_regmap_div, clkr);
 }
 
+static long div_round_ro_rate(struct clk_hw *hw, unsigned long rate,
+			      unsigned long *prate)
+{
+	struct clk_regmap_div *divider = to_clk_regmap_div(hw);
+	struct clk_regmap *clkr = &divider->clkr;
+	u32 div;
+	struct clk_hw *hw_parent = clk_hw_get_parent(hw);
+
+	regmap_read(clkr->regmap, divider->reg, &div);
+	div >>= divider->shift;
+	div &= BIT(divider->width) - 1;
+	div += 1;
+
+	if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) {
+		if (!hw_parent)
+			return -EINVAL;
+
+		*prate = clk_hw_round_rate(hw_parent, rate * div);
+	}
+
+	return DIV_ROUND_UP_ULL((u64)*prate, div);
+}
+
 static long div_round_rate(struct clk_hw *hw, unsigned long rate,
 			   unsigned long *prate)
 {
@@ -59,7 +82,7 @@ static unsigned long div_recalc_rate(struct clk_hw *hw,
 	div &= BIT(divider->width) - 1;
 
 	return divider_recalc_rate(hw, parent_rate, div, NULL,
-				   CLK_DIVIDER_ROUND_CLOSEST);
+				   CLK_DIVIDER_ROUND_CLOSEST, divider->width);
 }
 
 const struct clk_ops clk_regmap_div_ops = {
@@ -68,3 +91,9 @@ const struct clk_ops clk_regmap_div_ops = {
 	.recalc_rate = div_recalc_rate,
 };
 EXPORT_SYMBOL_GPL(clk_regmap_div_ops);
+
+const struct clk_ops clk_regmap_div_ro_ops = {
+	.round_rate = div_round_ro_rate,
+	.recalc_rate = div_recalc_rate,
+};
+EXPORT_SYMBOL_GPL(clk_regmap_div_ro_ops);
diff --git a/drivers/clk/qcom/clk-regmap-divider.h b/drivers/clk/qcom/clk-regmap-divider.h
index fc4492e3a827..8c39c2703caf 100644
--- a/drivers/clk/qcom/clk-regmap-divider.h
+++ b/drivers/clk/qcom/clk-regmap-divider.h
@@ -25,5 +25,6 @@ struct clk_regmap_div {
 };
 
 extern const struct clk_ops clk_regmap_div_ops;
+extern const struct clk_ops clk_regmap_div_ro_ops;
 
 #endif
diff --git a/drivers/clk/qcom/clk-regmap-mux-div.c b/drivers/clk/qcom/clk-regmap-mux-div.c
new file mode 100644
index 000000000000..6044839da85a
--- /dev/null
+++ b/drivers/clk/qcom/clk-regmap-mux-div.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017, Linaro Limited
+ * Author: Georgi Djakov <georgi.djakov@linaro.org>
+ */
+
+#include <linux/bitops.h>
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/regmap.h>
+
+#include "clk-regmap-mux-div.h"
+
+#define CMD_RCGR			0x0
+#define CMD_RCGR_UPDATE			BIT(0)
+#define CMD_RCGR_DIRTY_CFG		BIT(4)
+#define CMD_RCGR_ROOT_OFF		BIT(31)
+#define CFG_RCGR			0x4
+
+#define to_clk_regmap_mux_div(_hw) \
+	container_of(to_clk_regmap(_hw), struct clk_regmap_mux_div, clkr)
+
+int mux_div_set_src_div(struct clk_regmap_mux_div *md, u32 src, u32 div)
+{
+	int ret, count;
+	u32 val, mask;
+	const char *name = clk_hw_get_name(&md->clkr.hw);
+
+	val = (div << md->hid_shift) | (src << md->src_shift);
+	mask = ((BIT(md->hid_width) - 1) << md->hid_shift) |
+	       ((BIT(md->src_width) - 1) << md->src_shift);
+
+	ret = regmap_update_bits(md->clkr.regmap, CFG_RCGR + md->reg_offset,
+				 mask, val);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(md->clkr.regmap, CMD_RCGR + md->reg_offset,
+				 CMD_RCGR_UPDATE, CMD_RCGR_UPDATE);
+	if (ret)
+		return ret;
+
+	/* Wait for update to take effect */
+	for (count = 500; count > 0; count--) {
+		ret = regmap_read(md->clkr.regmap, CMD_RCGR + md->reg_offset,
+				  &val);
+		if (ret)
+			return ret;
+		if (!(val & CMD_RCGR_UPDATE))
+			return 0;
+		udelay(1);
+	}
+
+	pr_err("%s: RCG did not update its configuration", name);
+	return -EBUSY;
+}
+EXPORT_SYMBOL_GPL(mux_div_set_src_div);
+
+static void mux_div_get_src_div(struct clk_regmap_mux_div *md, u32 *src,
+				u32 *div)
+{
+	u32 val, d, s;
+	const char *name = clk_hw_get_name(&md->clkr.hw);
+
+	regmap_read(md->clkr.regmap, CMD_RCGR + md->reg_offset, &val);
+
+	if (val & CMD_RCGR_DIRTY_CFG) {
+		pr_err("%s: RCG configuration is pending\n", name);
+		return;
+	}
+
+	regmap_read(md->clkr.regmap, CFG_RCGR + md->reg_offset, &val);
+	s = (val >> md->src_shift);
+	s &= BIT(md->src_width) - 1;
+	*src = s;
+
+	d = (val >> md->hid_shift);
+	d &= BIT(md->hid_width) - 1;
+	*div = d;
+}
+
+static inline bool is_better_rate(unsigned long req, unsigned long best,
+				  unsigned long new)
+{
+	return (req <= new && new < best) || (best < req && best < new);
+}
+
+static int mux_div_determine_rate(struct clk_hw *hw,
+				  struct clk_rate_request *req)
+{
+	struct clk_regmap_mux_div *md = to_clk_regmap_mux_div(hw);
+	unsigned int i, div, max_div;
+	unsigned long actual_rate, best_rate = 0;
+	unsigned long req_rate = req->rate;
+
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
+		struct clk_hw *parent = clk_hw_get_parent_by_index(hw, i);
+		unsigned long parent_rate = clk_hw_get_rate(parent);
+
+		max_div = BIT(md->hid_width) - 1;
+		for (div = 1; div < max_div; div++) {
+			parent_rate = mult_frac(req_rate, div, 2);
+			parent_rate = clk_hw_round_rate(parent, parent_rate);
+			actual_rate = mult_frac(parent_rate, 2, div);
+
+			if (is_better_rate(req_rate, best_rate, actual_rate)) {
+				best_rate = actual_rate;
+				req->rate = best_rate;
+				req->best_parent_rate = parent_rate;
+				req->best_parent_hw = parent;
+			}
+
+			if (actual_rate < req_rate || best_rate <= req_rate)
+				break;
+		}
+	}
+
+	if (!best_rate)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __mux_div_set_rate_and_parent(struct clk_hw *hw, unsigned long rate,
+					 unsigned long prate, u32 src)
+{
+	struct clk_regmap_mux_div *md = to_clk_regmap_mux_div(hw);
+	int ret;
+	u32 div, max_div, best_src = 0, best_div = 0;
+	unsigned int i;
+	unsigned long actual_rate, best_rate = 0;
+
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
+		struct clk_hw *parent = clk_hw_get_parent_by_index(hw, i);
+		unsigned long parent_rate = clk_hw_get_rate(parent);
+
+		max_div = BIT(md->hid_width) - 1;
+		for (div = 1; div < max_div; div++) {
+			parent_rate = mult_frac(rate, div, 2);
+			parent_rate = clk_hw_round_rate(parent, parent_rate);
+			actual_rate = mult_frac(parent_rate, 2, div);
+
+			if (is_better_rate(rate, best_rate, actual_rate)) {
+				best_rate = actual_rate;
+				best_src = md->parent_map[i];
+				best_div = div - 1;
+			}
+
+			if (actual_rate < rate || best_rate <= rate)
+				break;
+		}
+	}
+
+	ret = mux_div_set_src_div(md, best_src, best_div);
+	if (!ret) {
+		md->div = best_div;
+		md->src = best_src;
+	}
+
+	return ret;
+}
+
+static u8 mux_div_get_parent(struct clk_hw *hw)
+{
+	struct clk_regmap_mux_div *md = to_clk_regmap_mux_div(hw);
+	const char *name = clk_hw_get_name(hw);
+	u32 i, div, src = 0;
+
+	mux_div_get_src_div(md, &src, &div);
+
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++)
+		if (src == md->parent_map[i])
+			return i;
+
+	pr_err("%s: Can't find parent with src %d\n", name, src);
+	return 0;
+}
+
+static int mux_div_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_regmap_mux_div *md = to_clk_regmap_mux_div(hw);
+
+	return mux_div_set_src_div(md, md->parent_map[index], md->div);
+}
+
+static int mux_div_set_rate(struct clk_hw *hw,
+			    unsigned long rate, unsigned long prate)
+{
+	struct clk_regmap_mux_div *md = to_clk_regmap_mux_div(hw);
+
+	return __mux_div_set_rate_and_parent(hw, rate, prate, md->src);
+}
+
+static int mux_div_set_rate_and_parent(struct clk_hw *hw,  unsigned long rate,
+				       unsigned long prate, u8 index)
+{
+	struct clk_regmap_mux_div *md = to_clk_regmap_mux_div(hw);
+
+	return __mux_div_set_rate_and_parent(hw, rate, prate,
+					     md->parent_map[index]);
+}
+
+static unsigned long mux_div_recalc_rate(struct clk_hw *hw, unsigned long prate)
+{
+	struct clk_regmap_mux_div *md = to_clk_regmap_mux_div(hw);
+	u32 div, src;
+	int i, num_parents = clk_hw_get_num_parents(hw);
+	const char *name = clk_hw_get_name(hw);
+
+	mux_div_get_src_div(md, &src, &div);
+	for (i = 0; i < num_parents; i++)
+		if (src == md->parent_map[i]) {
+			struct clk_hw *p = clk_hw_get_parent_by_index(hw, i);
+			unsigned long parent_rate = clk_hw_get_rate(p);
+
+			return mult_frac(parent_rate, 2, div + 1);
+		}
+
+	pr_err("%s: Can't find parent %d\n", name, src);
+	return 0;
+}
+
+const struct clk_ops clk_regmap_mux_div_ops = {
+	.get_parent = mux_div_get_parent,
+	.set_parent = mux_div_set_parent,
+	.set_rate = mux_div_set_rate,
+	.set_rate_and_parent = mux_div_set_rate_and_parent,
+	.determine_rate = mux_div_determine_rate,
+	.recalc_rate = mux_div_recalc_rate,
+};
+EXPORT_SYMBOL_GPL(clk_regmap_mux_div_ops);
diff --git a/drivers/clk/qcom/clk-regmap-mux-div.h b/drivers/clk/qcom/clk-regmap-mux-div.h
new file mode 100644
index 000000000000..6cd6261be7ac
--- /dev/null
+++ b/drivers/clk/qcom/clk-regmap-mux-div.h
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017, Linaro Limited
+ * Author: Georgi Djakov <georgi.djakov@linaro.org>
+ */
+
+#ifndef __QCOM_CLK_REGMAP_MUX_DIV_H__
+#define __QCOM_CLK_REGMAP_MUX_DIV_H__
+
+#include <linux/clk-provider.h>
+#include "clk-regmap.h"
+
+/**
+ * struct mux_div_clk - combined mux/divider clock
+ * @reg_offset: offset of the mux/divider register
+ * @hid_width:	number of bits in half integer divider
+ * @hid_shift:	lowest bit of hid value field
+ * @src_width:	number of bits in source select
+ * @src_shift:	lowest bit of source select field
+ * @div:	the divider raw configuration value
+ * @src:	the mux index which will be used if the clock is enabled
+ * @parent_map: map from parent_names index to src_sel field
+ * @clkr:	handle between common and hardware-specific interfaces
+ * @pclk:	the input PLL clock
+ * @clk_nb:	clock notifier for rate changes of the input PLL
+ */
+struct clk_regmap_mux_div {
+	u32				reg_offset;
+	u32				hid_width;
+	u32				hid_shift;
+	u32				src_width;
+	u32				src_shift;
+	u32				div;
+	u32				src;
+	const u32			*parent_map;
+	struct clk_regmap		clkr;
+	struct clk			*pclk;
+	struct notifier_block		clk_nb;
+};
+
+extern const struct clk_ops clk_regmap_mux_div_ops;
+extern int mux_div_set_src_div(struct clk_regmap_mux_div *md, u32 src, u32 div);
+
+#endif
diff --git a/drivers/clk/qcom/clk-regmap-mux.c b/drivers/clk/qcom/clk-regmap-mux.c
index cae3071f384c..0f3a1bda3e91 100644
--- a/drivers/clk/qcom/clk-regmap-mux.c
+++ b/drivers/clk/qcom/clk-regmap-mux.c
@@ -35,6 +35,9 @@ static u8 mux_get_parent(struct clk_hw *hw)
 	val >>= mux->shift;
 	val &= mask;
 
+	if (mux->parent_map)
+		return qcom_find_src_index(hw, mux->parent_map, val);
+
 	return val;
 }
 
@@ -45,6 +48,9 @@ static int mux_set_parent(struct clk_hw *hw, u8 index)
 	unsigned int mask = GENMASK(mux->width + mux->shift - 1, mux->shift);
 	unsigned int val;
 
+	if (mux->parent_map)
+		index = mux->parent_map[index].cfg;
+
 	val = index;
 	val <<= mux->shift;
 
diff --git a/drivers/clk/qcom/clk-regmap-mux.h b/drivers/clk/qcom/clk-regmap-mux.h
index 5cec76154fda..7797cddabe6b 100644
--- a/drivers/clk/qcom/clk-regmap-mux.h
+++ b/drivers/clk/qcom/clk-regmap-mux.h
@@ -16,11 +16,13 @@
 
 #include <linux/clk-provider.h>
 #include "clk-regmap.h"
+#include "common.h"
 
 struct clk_regmap_mux {
 	u32			reg;
 	u32			shift;
 	u32			width;
+	const struct parent_map	*parent_map;
 	struct clk_regmap	clkr;
 };
 
diff --git a/drivers/clk/qcom/clk-spmi-pmic-div.c b/drivers/clk/qcom/clk-spmi-pmic-div.c
new file mode 100644
index 000000000000..8672ab84746f
--- /dev/null
+++ b/drivers/clk/qcom/clk-spmi-pmic-div.c
@@ -0,0 +1,302 @@
+/* Copyright (c) 2017, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/log2.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#define REG_DIV_CTL1			0x43
+#define DIV_CTL1_DIV_FACTOR_MASK	GENMASK(2, 0)
+
+#define REG_EN_CTL			0x46
+#define REG_EN_MASK			BIT(7)
+
+struct clkdiv {
+	struct regmap		*regmap;
+	u16			base;
+	spinlock_t		lock;
+
+	struct clk_hw		hw;
+	unsigned int		cxo_period_ns;
+};
+
+static inline struct clkdiv *to_clkdiv(struct clk_hw *hw)
+{
+	return container_of(hw, struct clkdiv, hw);
+}
+
+static inline unsigned int div_factor_to_div(unsigned int div_factor)
+{
+	if (!div_factor)
+		div_factor = 1;
+
+	return 1 << (div_factor - 1);
+}
+
+static inline unsigned int div_to_div_factor(unsigned int div)
+{
+	return min(ilog2(div) + 1, 7);
+}
+
+static bool is_spmi_pmic_clkdiv_enabled(struct clkdiv *clkdiv)
+{
+	unsigned int val = 0;
+
+	regmap_read(clkdiv->regmap, clkdiv->base + REG_EN_CTL, &val);
+
+	return val & REG_EN_MASK;
+}
+
+static int
+__spmi_pmic_clkdiv_set_enable_state(struct clkdiv *clkdiv, bool enable,
+				    unsigned int div_factor)
+{
+	int ret;
+	unsigned int ns = clkdiv->cxo_period_ns;
+	unsigned int div = div_factor_to_div(div_factor);
+
+	ret = regmap_update_bits(clkdiv->regmap, clkdiv->base + REG_EN_CTL,
+				 REG_EN_MASK, enable ? REG_EN_MASK : 0);
+	if (ret)
+		return ret;
+
+	if (enable)
+		ndelay((2 + 3 * div) * ns);
+	else
+		ndelay(3 * div * ns);
+
+	return 0;
+}
+
+static int spmi_pmic_clkdiv_set_enable_state(struct clkdiv *clkdiv, bool enable)
+{
+	unsigned int div_factor;
+
+	regmap_read(clkdiv->regmap, clkdiv->base + REG_DIV_CTL1, &div_factor);
+	div_factor &= DIV_CTL1_DIV_FACTOR_MASK;
+
+	return __spmi_pmic_clkdiv_set_enable_state(clkdiv, enable, div_factor);
+}
+
+static int clk_spmi_pmic_div_enable(struct clk_hw *hw)
+{
+	struct clkdiv *clkdiv = to_clkdiv(hw);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&clkdiv->lock, flags);
+	ret = spmi_pmic_clkdiv_set_enable_state(clkdiv, true);
+	spin_unlock_irqrestore(&clkdiv->lock, flags);
+
+	return ret;
+}
+
+static void clk_spmi_pmic_div_disable(struct clk_hw *hw)
+{
+	struct clkdiv *clkdiv = to_clkdiv(hw);
+	unsigned long flags;
+
+	spin_lock_irqsave(&clkdiv->lock, flags);
+	spmi_pmic_clkdiv_set_enable_state(clkdiv, false);
+	spin_unlock_irqrestore(&clkdiv->lock, flags);
+}
+
+static long clk_spmi_pmic_div_round_rate(struct clk_hw *hw, unsigned long rate,
+					 unsigned long *parent_rate)
+{
+	unsigned int div, div_factor;
+
+	div = DIV_ROUND_UP(*parent_rate, rate);
+	div_factor = div_to_div_factor(div);
+	div = div_factor_to_div(div_factor);
+
+	return *parent_rate / div;
+}
+
+static unsigned long
+clk_spmi_pmic_div_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
+{
+	struct clkdiv *clkdiv = to_clkdiv(hw);
+	unsigned int div_factor;
+
+	regmap_read(clkdiv->regmap, clkdiv->base + REG_DIV_CTL1, &div_factor);
+	div_factor &= DIV_CTL1_DIV_FACTOR_MASK;
+
+	return parent_rate / div_factor_to_div(div_factor);
+}
+
+static int clk_spmi_pmic_div_set_rate(struct clk_hw *hw, unsigned long rate,
+				      unsigned long parent_rate)
+{
+	struct clkdiv *clkdiv = to_clkdiv(hw);
+	unsigned int div_factor = div_to_div_factor(parent_rate / rate);
+	unsigned long flags;
+	bool enabled;
+	int ret;
+
+	spin_lock_irqsave(&clkdiv->lock, flags);
+	enabled = is_spmi_pmic_clkdiv_enabled(clkdiv);
+	if (enabled) {
+		ret = spmi_pmic_clkdiv_set_enable_state(clkdiv, false);
+		if (ret)
+			goto unlock;
+	}
+
+	ret = regmap_update_bits(clkdiv->regmap, clkdiv->base + REG_DIV_CTL1,
+				 DIV_CTL1_DIV_FACTOR_MASK, div_factor);
+	if (ret)
+		goto unlock;
+
+	if (enabled)
+		ret = __spmi_pmic_clkdiv_set_enable_state(clkdiv, true,
+							  div_factor);
+
+unlock:
+	spin_unlock_irqrestore(&clkdiv->lock, flags);
+
+	return ret;
+}
+
+static const struct clk_ops clk_spmi_pmic_div_ops = {
+	.enable = clk_spmi_pmic_div_enable,
+	.disable = clk_spmi_pmic_div_disable,
+	.set_rate = clk_spmi_pmic_div_set_rate,
+	.recalc_rate = clk_spmi_pmic_div_recalc_rate,
+	.round_rate = clk_spmi_pmic_div_round_rate,
+};
+
+struct spmi_pmic_div_clk_cc {
+	int		nclks;
+	struct clkdiv	clks[];
+};
+
+static struct clk_hw *
+spmi_pmic_div_clk_hw_get(struct of_phandle_args *clkspec, void *data)
+{
+	struct spmi_pmic_div_clk_cc *cc = data;
+	int idx = clkspec->args[0] - 1; /* Start at 1 instead of 0 */
+
+	if (idx < 0 || idx >= cc->nclks) {
+		pr_err("%s: index value %u is invalid; allowed range [1, %d]\n",
+		       __func__, clkspec->args[0], cc->nclks);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return &cc->clks[idx].hw;
+}
+
+static int spmi_pmic_clkdiv_probe(struct platform_device *pdev)
+{
+	struct spmi_pmic_div_clk_cc *cc;
+	struct clk_init_data init = {};
+	struct clkdiv *clkdiv;
+	struct clk *cxo;
+	struct regmap *regmap;
+	struct device *dev = &pdev->dev;
+	struct device_node *of_node = dev->of_node;
+	const char *parent_name;
+	int nclks, i, ret, cxo_hz;
+	char name[20];
+	u32 start;
+
+	ret = of_property_read_u32(of_node, "reg", &start);
+	if (ret < 0) {
+		dev_err(dev, "reg property reading failed\n");
+		return ret;
+	}
+
+	regmap = dev_get_regmap(dev->parent, NULL);
+	if (!regmap) {
+		dev_err(dev, "Couldn't get parent's regmap\n");
+		return -EINVAL;
+	}
+
+	ret = of_property_read_u32(of_node, "qcom,num-clkdivs", &nclks);
+	if (ret < 0) {
+		dev_err(dev, "qcom,num-clkdivs property reading failed, ret=%d\n",
+			ret);
+		return ret;
+	}
+
+	if (!nclks)
+		return -EINVAL;
+
+	cc = devm_kzalloc(dev, sizeof(*cc) + sizeof(*cc->clks) * nclks,
+			  GFP_KERNEL);
+	if (!cc)
+		return -ENOMEM;
+	cc->nclks = nclks;
+
+	cxo = clk_get(dev, "xo");
+	if (IS_ERR(cxo)) {
+		ret = PTR_ERR(cxo);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get xo clock\n");
+		return ret;
+	}
+	cxo_hz = clk_get_rate(cxo);
+	clk_put(cxo);
+
+	parent_name = of_clk_get_parent_name(of_node, 0);
+	if (!parent_name) {
+		dev_err(dev, "missing parent clock\n");
+		return -ENODEV;
+	}
+
+	init.name = name;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+	init.ops = &clk_spmi_pmic_div_ops;
+
+	for (i = 0, clkdiv = cc->clks; i < nclks; i++) {
+		snprintf(name, sizeof(name), "div_clk%d", i + 1);
+
+		spin_lock_init(&clkdiv[i].lock);
+		clkdiv[i].base = start + i * 0x100;
+		clkdiv[i].regmap = regmap;
+		clkdiv[i].cxo_period_ns = NSEC_PER_SEC / cxo_hz;
+		clkdiv[i].hw.init = &init;
+
+		ret = devm_clk_hw_register(dev, &clkdiv[i].hw);
+		if (ret)
+			return ret;
+	}
+
+	return devm_of_clk_add_hw_provider(dev, spmi_pmic_div_clk_hw_get, cc);
+}
+
+static const struct of_device_id spmi_pmic_clkdiv_match_table[] = {
+	{ .compatible = "qcom,spmi-clkdiv" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, spmi_pmic_clkdiv_match_table);
+
+static struct platform_driver spmi_pmic_clkdiv_driver = {
+	.driver		= {
+		.name	= "qcom,spmi-pmic-clkdiv",
+		.of_match_table = spmi_pmic_clkdiv_match_table,
+	},
+	.probe		= spmi_pmic_clkdiv_probe,
+};
+module_platform_driver(spmi_pmic_clkdiv_driver);
+
+MODULE_DESCRIPTION("QCOM SPMI PMIC clkdiv driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/common.h b/drivers/clk/qcom/common.h
index 23c1927669ba..00196ee15e73 100644
--- a/drivers/clk/qcom/common.h
+++ b/drivers/clk/qcom/common.h
@@ -20,7 +20,6 @@ struct qcom_reset_map;
 struct regmap;
 struct freq_tbl;
 struct clk_hw;
-struct parent_map;
 
 #define PLL_LOCK_COUNT_SHIFT	8
 #define PLL_LOCK_COUNT_MASK	0x3f
@@ -39,6 +38,16 @@ struct qcom_cc_desc {
 	size_t num_gdscs;
 };
 
+/**
+ * struct parent_map - map table for source select configuration values
+ * @src: source
+ * @cfg: configuration value
+ */
+struct parent_map {
+	u8 src;
+	u8 cfg;
+};
+
 extern const struct freq_tbl *qcom_find_freq(const struct freq_tbl *f,
 					     unsigned long rate);
 extern const struct freq_tbl *qcom_find_freq_floor(const struct freq_tbl *f,
diff --git a/drivers/clk/qcom/gcc-ipq8074.c b/drivers/clk/qcom/gcc-ipq8074.c
index 0f735d37690f..0462f4a8c932 100644
--- a/drivers/clk/qcom/gcc-ipq8074.c
+++ b/drivers/clk/qcom/gcc-ipq8074.c
@@ -28,6 +28,8 @@
 #include "clk-rcg.h"
 #include "clk-branch.h"
 #include "clk-alpha-pll.h"
+#include "clk-regmap-divider.h"
+#include "clk-regmap-mux.h"
 #include "reset.h"
 
 #define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
@@ -36,6 +38,24 @@ enum {
 	P_XO,
 	P_GPLL0,
 	P_GPLL0_DIV2,
+	P_GPLL2,
+	P_GPLL4,
+	P_GPLL6,
+	P_SLEEP_CLK,
+	P_PCIE20_PHY0_PIPE,
+	P_PCIE20_PHY1_PIPE,
+	P_USB3PHY_0_PIPE,
+	P_USB3PHY_1_PIPE,
+	P_UBI32_PLL,
+	P_NSS_CRYPTO_PLL,
+	P_BIAS_PLL,
+	P_BIAS_PLL_NSS_NOC,
+	P_UNIPHY0_RX,
+	P_UNIPHY0_TX,
+	P_UNIPHY1_RX,
+	P_UNIPHY1_TX,
+	P_UNIPHY2_RX,
+	P_UNIPHY2_TX,
 };
 
 static const char * const gcc_xo_gpll0_gpll0_out_main_div2[] = {
@@ -50,8 +70,345 @@ static const struct parent_map gcc_xo_gpll0_gpll0_out_main_div2_map[] = {
 	{ P_GPLL0_DIV2, 4 },
 };
 
+static const char * const gcc_xo_gpll0[] = {
+	"xo",
+	"gpll0",
+};
+
+static const struct parent_map gcc_xo_gpll0_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+};
+
+static const char * const gcc_xo_gpll0_gpll2_gpll0_out_main_div2[] = {
+	"xo",
+	"gpll0",
+	"gpll2",
+	"gpll0_out_main_div2",
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll2_gpll0_out_main_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL2, 2 },
+	{ P_GPLL0_DIV2, 4 },
+};
+
+static const char * const gcc_xo_gpll0_sleep_clk[] = {
+	"xo",
+	"gpll0",
+	"sleep_clk",
+};
+
+static const struct parent_map gcc_xo_gpll0_sleep_clk_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 2 },
+	{ P_SLEEP_CLK, 6 },
+};
+
+static const char * const gcc_xo_gpll6_gpll0_gpll0_out_main_div2[] = {
+	"xo",
+	"gpll6",
+	"gpll0",
+	"gpll0_out_main_div2",
+};
+
+static const struct parent_map gcc_xo_gpll6_gpll0_gpll0_out_main_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL6, 1 },
+	{ P_GPLL0, 3 },
+	{ P_GPLL0_DIV2, 4 },
+};
+
+static const char * const gcc_xo_gpll0_out_main_div2_gpll0[] = {
+	"xo",
+	"gpll0_out_main_div2",
+	"gpll0",
+};
+
+static const struct parent_map gcc_xo_gpll0_out_main_div2_gpll0_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0_DIV2, 2 },
+	{ P_GPLL0, 1 },
+};
+
+static const char * const gcc_usb3phy_0_cc_pipe_clk_xo[] = {
+	"usb3phy_0_cc_pipe_clk",
+	"xo",
+};
+
+static const struct parent_map gcc_usb3phy_0_cc_pipe_clk_xo_map[] = {
+	{ P_USB3PHY_0_PIPE, 0 },
+	{ P_XO, 2 },
+};
+
+static const char * const gcc_usb3phy_1_cc_pipe_clk_xo[] = {
+	"usb3phy_1_cc_pipe_clk",
+	"xo",
+};
+
+static const struct parent_map gcc_usb3phy_1_cc_pipe_clk_xo_map[] = {
+	{ P_USB3PHY_1_PIPE, 0 },
+	{ P_XO, 2 },
+};
+
+static const char * const gcc_pcie20_phy0_pipe_clk_xo[] = {
+	"pcie20_phy0_pipe_clk",
+	"xo",
+};
+
+static const struct parent_map gcc_pcie20_phy0_pipe_clk_xo_map[] = {
+	{ P_PCIE20_PHY0_PIPE, 0 },
+	{ P_XO, 2 },
+};
+
+static const char * const gcc_pcie20_phy1_pipe_clk_xo[] = {
+	"pcie20_phy1_pipe_clk",
+	"xo",
+};
+
+static const struct parent_map gcc_pcie20_phy1_pipe_clk_xo_map[] = {
+	{ P_PCIE20_PHY1_PIPE, 0 },
+	{ P_XO, 2 },
+};
+
+static const char * const gcc_xo_gpll0_gpll6_gpll0_div2[] = {
+	"xo",
+	"gpll0",
+	"gpll6",
+	"gpll0_out_main_div2",
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll6_gpll0_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL6, 2 },
+	{ P_GPLL0_DIV2, 4 },
+};
+
+static const char * const gcc_xo_gpll0_gpll6_gpll0_out_main_div2[] = {
+	"xo",
+	"gpll0",
+	"gpll6",
+	"gpll0_out_main_div2",
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll6_gpll0_out_main_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL6, 2 },
+	{ P_GPLL0_DIV2, 3 },
+};
+
+static const char * const gcc_xo_bias_pll_nss_noc_clk_gpll0_gpll2[] = {
+	"xo",
+	"bias_pll_nss_noc_clk",
+	"gpll0",
+	"gpll2",
+};
+
+static const struct parent_map gcc_xo_bias_pll_nss_noc_clk_gpll0_gpll2_map[] = {
+	{ P_XO, 0 },
+	{ P_BIAS_PLL_NSS_NOC, 1 },
+	{ P_GPLL0, 2 },
+	{ P_GPLL2, 3 },
+};
+
+static const char * const gcc_xo_nss_crypto_pll_gpll0[] = {
+	"xo",
+	"nss_crypto_pll",
+	"gpll0",
+};
+
+static const struct parent_map gcc_xo_nss_crypto_pll_gpll0_map[] = {
+	{ P_XO, 0 },
+	{ P_NSS_CRYPTO_PLL, 1 },
+	{ P_GPLL0, 2 },
+};
+
+static const char * const gcc_xo_ubi32_pll_gpll0_gpll2_gpll4_gpll6[] = {
+	"xo",
+	"ubi32_pll",
+	"gpll0",
+	"gpll2",
+	"gpll4",
+	"gpll6",
+};
+
+static const struct parent_map gcc_xo_ubi32_gpll0_gpll2_gpll4_gpll6_map[] = {
+	{ P_XO, 0 },
+	{ P_UBI32_PLL, 1 },
+	{ P_GPLL0, 2 },
+	{ P_GPLL2, 3 },
+	{ P_GPLL4, 4 },
+	{ P_GPLL6, 5 },
+};
+
+static const char * const gcc_xo_gpll0_out_main_div2[] = {
+	"xo",
+	"gpll0_out_main_div2",
+};
+
+static const struct parent_map gcc_xo_gpll0_out_main_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0_DIV2, 1 },
+};
+
+static const char * const gcc_xo_bias_gpll0_gpll4_nss_ubi32[] = {
+	"xo",
+	"bias_pll_cc_clk",
+	"gpll0",
+	"gpll4",
+	"nss_crypto_pll",
+	"ubi32_pll",
+};
+
+static const struct parent_map gcc_xo_bias_gpll0_gpll4_nss_ubi32_map[] = {
+	{ P_XO, 0 },
+	{ P_BIAS_PLL, 1 },
+	{ P_GPLL0, 2 },
+	{ P_GPLL4, 3 },
+	{ P_NSS_CRYPTO_PLL, 4 },
+	{ P_UBI32_PLL, 5 },
+};
+
+static const char * const gcc_xo_gpll0_gpll4[] = {
+	"xo",
+	"gpll0",
+	"gpll4",
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll4_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL4, 2 },
+};
+
+static const char * const gcc_xo_uniphy0_rx_tx_ubi32_bias[] = {
+	"xo",
+	"uniphy0_gcc_rx_clk",
+	"uniphy0_gcc_tx_clk",
+	"ubi32_pll",
+	"bias_pll_cc_clk",
+};
+
+static const struct parent_map gcc_xo_uniphy0_rx_tx_ubi32_bias_map[] = {
+	{ P_XO, 0 },
+	{ P_UNIPHY0_RX, 1 },
+	{ P_UNIPHY0_TX, 2 },
+	{ P_UBI32_PLL, 5 },
+	{ P_BIAS_PLL, 6 },
+};
+
+static const char * const gcc_xo_uniphy0_tx_rx_ubi32_bias[] = {
+	"xo",
+	"uniphy0_gcc_tx_clk",
+	"uniphy0_gcc_rx_clk",
+	"ubi32_pll",
+	"bias_pll_cc_clk",
+};
+
+static const struct parent_map gcc_xo_uniphy0_tx_rx_ubi32_bias_map[] = {
+	{ P_XO, 0 },
+	{ P_UNIPHY0_TX, 1 },
+	{ P_UNIPHY0_RX, 2 },
+	{ P_UBI32_PLL, 5 },
+	{ P_BIAS_PLL, 6 },
+};
+
+static const char * const gcc_xo_uniphy0_rx_tx_uniphy1_rx_tx_ubi32_bias[] = {
+	"xo",
+	"uniphy0_gcc_rx_clk",
+	"uniphy0_gcc_tx_clk",
+	"uniphy1_gcc_rx_clk",
+	"uniphy1_gcc_tx_clk",
+	"ubi32_pll",
+	"bias_pll_cc_clk",
+};
+
+static const struct parent_map
+gcc_xo_uniphy0_rx_tx_uniphy1_rx_tx_ubi32_bias_map[] = {
+	{ P_XO, 0 },
+	{ P_UNIPHY0_RX, 1 },
+	{ P_UNIPHY0_TX, 2 },
+	{ P_UNIPHY1_RX, 3 },
+	{ P_UNIPHY1_TX, 4 },
+	{ P_UBI32_PLL, 5 },
+	{ P_BIAS_PLL, 6 },
+};
+
+static const char * const gcc_xo_uniphy0_tx_rx_uniphy1_tx_rx_ubi32_bias[] = {
+	"xo",
+	"uniphy0_gcc_tx_clk",
+	"uniphy0_gcc_rx_clk",
+	"uniphy1_gcc_tx_clk",
+	"uniphy1_gcc_rx_clk",
+	"ubi32_pll",
+	"bias_pll_cc_clk",
+};
+
+static const struct parent_map
+gcc_xo_uniphy0_tx_rx_uniphy1_tx_rx_ubi32_bias_map[] = {
+	{ P_XO, 0 },
+	{ P_UNIPHY0_TX, 1 },
+	{ P_UNIPHY0_RX, 2 },
+	{ P_UNIPHY1_TX, 3 },
+	{ P_UNIPHY1_RX, 4 },
+	{ P_UBI32_PLL, 5 },
+	{ P_BIAS_PLL, 6 },
+};
+
+static const char * const gcc_xo_uniphy2_rx_tx_ubi32_bias[] = {
+	"xo",
+	"uniphy2_gcc_rx_clk",
+	"uniphy2_gcc_tx_clk",
+	"ubi32_pll",
+	"bias_pll_cc_clk",
+};
+
+static const struct parent_map gcc_xo_uniphy2_rx_tx_ubi32_bias_map[] = {
+	{ P_XO, 0 },
+	{ P_UNIPHY2_RX, 1 },
+	{ P_UNIPHY2_TX, 2 },
+	{ P_UBI32_PLL, 5 },
+	{ P_BIAS_PLL, 6 },
+};
+
+static const char * const gcc_xo_uniphy2_tx_rx_ubi32_bias[] = {
+	"xo",
+	"uniphy2_gcc_tx_clk",
+	"uniphy2_gcc_rx_clk",
+	"ubi32_pll",
+	"bias_pll_cc_clk",
+};
+
+static const struct parent_map gcc_xo_uniphy2_tx_rx_ubi32_bias_map[] = {
+	{ P_XO, 0 },
+	{ P_UNIPHY2_TX, 1 },
+	{ P_UNIPHY2_RX, 2 },
+	{ P_UBI32_PLL, 5 },
+	{ P_BIAS_PLL, 6 },
+};
+
+static const char * const gcc_xo_gpll0_gpll6_gpll0_sleep_clk[] = {
+	"xo",
+	"gpll0",
+	"gpll6",
+	"gpll0_out_main_div2",
+	"sleep_clk",
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll6_gpll0_sleep_clk_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL6, 2 },
+	{ P_GPLL0_DIV2, 4 },
+	{ P_SLEEP_CLK, 6 },
+};
+
 static struct clk_alpha_pll gpll0_main = {
 	.offset = 0x21000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.clkr = {
 		.enable_reg = 0x0b000,
 		.enable_mask = BIT(0),
@@ -82,13 +439,194 @@ static struct clk_fixed_factor gpll0_out_main_div2 = {
 
 static struct clk_alpha_pll_postdiv gpll0 = {
 	.offset = 0x21000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.width = 4,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "gpll0",
 		.parent_names = (const char *[]){
 			"gpll0_main"
 		},
 		.num_parents = 1,
-		.ops = &clk_alpha_pll_postdiv_ops,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+	},
+};
+
+static struct clk_alpha_pll gpll2_main = {
+	.offset = 0x4a000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.clkr = {
+		.enable_reg = 0x0b000,
+		.enable_mask = BIT(2),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpll2_main",
+			.parent_names = (const char *[]){
+				"xo"
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_ops,
+			.flags = CLK_IS_CRITICAL,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv gpll2 = {
+	.offset = 0x4a000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.width = 4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll2",
+		.parent_names = (const char *[]){
+			"gpll2_main"
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_alpha_pll gpll4_main = {
+	.offset = 0x24000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.clkr = {
+		.enable_reg = 0x0b000,
+		.enable_mask = BIT(5),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpll4_main",
+			.parent_names = (const char *[]){
+				"xo"
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_ops,
+			.flags = CLK_IS_CRITICAL,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv gpll4 = {
+	.offset = 0x24000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.width = 4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll4",
+		.parent_names = (const char *[]){
+			"gpll4_main"
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_alpha_pll gpll6_main = {
+	.offset = 0x37000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_BRAMMO],
+	.flags = SUPPORTS_DYNAMIC_UPDATE,
+	.clkr = {
+		.enable_reg = 0x0b000,
+		.enable_mask = BIT(7),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpll6_main",
+			.parent_names = (const char *[]){
+				"xo"
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_ops,
+			.flags = CLK_IS_CRITICAL,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv gpll6 = {
+	.offset = 0x37000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_BRAMMO],
+	.width = 2,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll6",
+		.parent_names = (const char *[]){
+			"gpll6_main"
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_fixed_factor gpll6_out_main_div2 = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "gpll6_out_main_div2",
+		.parent_names = (const char *[]){
+			"gpll6_main"
+		},
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_alpha_pll ubi32_pll_main = {
+	.offset = 0x25000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_HUAYRA],
+	.flags = SUPPORTS_DYNAMIC_UPDATE,
+	.clkr = {
+		.enable_reg = 0x0b000,
+		.enable_mask = BIT(6),
+		.hw.init = &(struct clk_init_data){
+			.name = "ubi32_pll_main",
+			.parent_names = (const char *[]){
+				"xo"
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_huayra_ops,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv ubi32_pll = {
+	.offset = 0x25000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_HUAYRA],
+	.width = 2,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "ubi32_pll",
+		.parent_names = (const char *[]){
+			"ubi32_pll_main"
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_alpha_pll nss_crypto_pll_main = {
+	.offset = 0x22000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.clkr = {
+		.enable_reg = 0x0b000,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_crypto_pll_main",
+			.parent_names = (const char *[]){
+				"xo"
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_ops,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv nss_crypto_pll = {
+	.offset = 0x22000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.width = 4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_crypto_pll",
+		.parent_names = (const char *[]){
+			"nss_crypto_pll_main"
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -428,6 +966,1063 @@ static struct clk_rcg2 blsp1_uart6_apps_clk_src = {
 	},
 };
 
+static const struct freq_tbl ftbl_pcie_axi_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(200000000, P_GPLL0, 4, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 pcie0_axi_clk_src = {
+	.cmd_rcgr = 0x75054,
+	.freq_tbl = ftbl_pcie_axi_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcie0_axi_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_pcie_aux_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+};
+
+static struct clk_rcg2 pcie0_aux_clk_src = {
+	.cmd_rcgr = 0x75024,
+	.freq_tbl = ftbl_pcie_aux_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcie0_aux_clk_src",
+		.parent_names = gcc_xo_gpll0_sleep_clk,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_mux pcie0_pipe_clk_src = {
+	.reg = 0x7501c,
+	.shift = 8,
+	.width = 2,
+	.parent_map = gcc_pcie20_phy0_pipe_clk_xo_map,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie0_pipe_clk_src",
+			.parent_names = gcc_pcie20_phy0_pipe_clk_xo,
+			.num_parents = 2,
+			.ops = &clk_regmap_mux_closest_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg2 pcie1_axi_clk_src = {
+	.cmd_rcgr = 0x76054,
+	.freq_tbl = ftbl_pcie_axi_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcie1_axi_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 pcie1_aux_clk_src = {
+	.cmd_rcgr = 0x76024,
+	.freq_tbl = ftbl_pcie_aux_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcie1_aux_clk_src",
+		.parent_names = gcc_xo_gpll0_sleep_clk,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_mux pcie1_pipe_clk_src = {
+	.reg = 0x7601c,
+	.shift = 8,
+	.width = 2,
+	.parent_map = gcc_pcie20_phy1_pipe_clk_xo_map,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie1_pipe_clk_src",
+			.parent_names = gcc_pcie20_phy1_pipe_clk_xo,
+			.num_parents = 2,
+			.ops = &clk_regmap_mux_closest_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_sdcc_apps_clk_src[] = {
+	F(144000, P_XO, 16, 3, 25),
+	F(400000, P_XO, 12, 1, 4),
+	F(24000000, P_GPLL2, 12, 1, 4),
+	F(48000000, P_GPLL2, 12, 1, 2),
+	F(96000000, P_GPLL2, 12, 0, 0),
+	F(177777778, P_GPLL0, 4.5, 0, 0),
+	F(192000000, P_GPLL2, 6, 0, 0),
+	F(384000000, P_GPLL2, 3, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 sdcc1_apps_clk_src = {
+	.cmd_rcgr = 0x42004,
+	.freq_tbl = ftbl_sdcc_apps_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll2_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sdcc1_apps_clk_src",
+		.parent_names = gcc_xo_gpll0_gpll2_gpll0_out_main_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(160000000, P_GPLL0, 5, 0, 0),
+	F(308570000, P_GPLL6, 3.5, 0, 0),
+};
+
+static struct clk_rcg2 sdcc1_ice_core_clk_src = {
+	.cmd_rcgr = 0x5d000,
+	.freq_tbl = ftbl_sdcc_ice_core_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_gpll0_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sdcc1_ice_core_clk_src",
+		.parent_names = gcc_xo_gpll0_gpll6_gpll0_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 sdcc2_apps_clk_src = {
+	.cmd_rcgr = 0x43004,
+	.freq_tbl = ftbl_sdcc_apps_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll2_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sdcc2_apps_clk_src",
+		.parent_names = gcc_xo_gpll0_gpll2_gpll0_out_main_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_usb_master_clk_src[] = {
+	F(80000000, P_GPLL0_DIV2, 5, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	F(133330000, P_GPLL0, 6, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 usb0_master_clk_src = {
+	.cmd_rcgr = 0x3e00c,
+	.freq_tbl = ftbl_usb_master_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_out_main_div2_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb0_master_clk_src",
+		.parent_names = gcc_xo_gpll0_out_main_div2_gpll0,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_usb_aux_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 usb0_aux_clk_src = {
+	.cmd_rcgr = 0x3e05c,
+	.freq_tbl = ftbl_usb_aux_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb0_aux_clk_src",
+		.parent_names = gcc_xo_gpll0_sleep_clk,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_usb_mock_utmi_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(20000000, P_GPLL6, 6, 1, 9),
+	F(60000000, P_GPLL6, 6, 1, 3),
+	{ }
+};
+
+static struct clk_rcg2 usb0_mock_utmi_clk_src = {
+	.cmd_rcgr = 0x3e020,
+	.freq_tbl = ftbl_usb_mock_utmi_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll6_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb0_mock_utmi_clk_src",
+		.parent_names = gcc_xo_gpll6_gpll0_gpll0_out_main_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_mux usb0_pipe_clk_src = {
+	.reg = 0x3e048,
+	.shift = 8,
+	.width = 2,
+	.parent_map = gcc_usb3phy_0_cc_pipe_clk_xo_map,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "usb0_pipe_clk_src",
+			.parent_names = gcc_usb3phy_0_cc_pipe_clk_xo,
+			.num_parents = 2,
+			.ops = &clk_regmap_mux_closest_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg2 usb1_master_clk_src = {
+	.cmd_rcgr = 0x3f00c,
+	.freq_tbl = ftbl_usb_master_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_out_main_div2_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb1_master_clk_src",
+		.parent_names = gcc_xo_gpll0_out_main_div2_gpll0,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 usb1_aux_clk_src = {
+	.cmd_rcgr = 0x3f05c,
+	.freq_tbl = ftbl_usb_aux_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb1_aux_clk_src",
+		.parent_names = gcc_xo_gpll0_sleep_clk,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 usb1_mock_utmi_clk_src = {
+	.cmd_rcgr = 0x3f020,
+	.freq_tbl = ftbl_usb_mock_utmi_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll6_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb1_mock_utmi_clk_src",
+		.parent_names = gcc_xo_gpll6_gpll0_gpll0_out_main_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_mux usb1_pipe_clk_src = {
+	.reg = 0x3f048,
+	.shift = 8,
+	.width = 2,
+	.parent_map = gcc_usb3phy_1_cc_pipe_clk_xo_map,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "usb1_pipe_clk_src",
+			.parent_names = gcc_usb3phy_1_cc_pipe_clk_xo,
+			.num_parents = 2,
+			.ops = &clk_regmap_mux_closest_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch gcc_xo_clk_src = {
+	.halt_reg = 0x30018,
+	.clkr = {
+		.enable_reg = 0x30018,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_xo_clk_src",
+			.parent_names = (const char *[]){
+				"xo"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_fixed_factor gcc_xo_div4_clk_src = {
+	.mult = 1,
+	.div = 4,
+	.hw.init = &(struct clk_init_data){
+		.name = "gcc_xo_div4_clk_src",
+		.parent_names = (const char *[]){
+			"gcc_xo_clk_src"
+		},
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct freq_tbl ftbl_system_noc_bfdcd_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(50000000, P_GPLL0_DIV2, 8, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	F(133333333, P_GPLL0, 6, 0, 0),
+	F(160000000, P_GPLL0, 5, 0, 0),
+	F(200000000, P_GPLL0, 4, 0, 0),
+	F(266666667, P_GPLL0, 3, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 system_noc_bfdcd_clk_src = {
+	.cmd_rcgr = 0x26004,
+	.freq_tbl = ftbl_system_noc_bfdcd_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "system_noc_bfdcd_clk_src",
+		.parent_names = gcc_xo_gpll0_gpll6_gpll0_out_main_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+		.flags = CLK_IS_CRITICAL,
+	},
+};
+
+static struct clk_fixed_factor system_noc_clk_src = {
+	.mult = 1,
+	.div = 1,
+	.hw.init = &(struct clk_init_data){
+		.name = "system_noc_clk_src",
+		.parent_names = (const char *[]){
+			"system_noc_bfdcd_clk_src"
+		},
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_ce_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(200000000, P_GPLL0, 4, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_ce_clk_src = {
+	.cmd_rcgr = 0x68098,
+	.freq_tbl = ftbl_nss_ce_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_ce_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_noc_bfdcd_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(461500000, P_BIAS_PLL_NSS_NOC, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_noc_bfdcd_clk_src = {
+	.cmd_rcgr = 0x68088,
+	.freq_tbl = ftbl_nss_noc_bfdcd_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_bias_pll_nss_noc_clk_gpll0_gpll2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_noc_bfdcd_clk_src",
+		.parent_names = gcc_xo_bias_pll_nss_noc_clk_gpll0_gpll2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_fixed_factor nss_noc_clk_src = {
+	.mult = 1,
+	.div = 1,
+	.hw.init = &(struct clk_init_data){
+		.name = "nss_noc_clk_src",
+		.parent_names = (const char *[]){
+			"nss_noc_bfdcd_clk_src"
+		},
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_crypto_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(600000000, P_NSS_CRYPTO_PLL, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_crypto_clk_src = {
+	.cmd_rcgr = 0x68144,
+	.freq_tbl = ftbl_nss_crypto_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_nss_crypto_pll_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_crypto_clk_src",
+		.parent_names = gcc_xo_nss_crypto_pll_gpll0,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_ubi_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(187200000, P_UBI32_PLL, 8, 0, 0),
+	F(748800000, P_UBI32_PLL, 2, 0, 0),
+	F(1497600000, P_UBI32_PLL, 1, 0, 0),
+	F(1689600000, P_UBI32_PLL, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_ubi0_clk_src = {
+	.cmd_rcgr = 0x68104,
+	.freq_tbl = ftbl_nss_ubi_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_ubi32_gpll0_gpll2_gpll4_gpll6_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_ubi0_clk_src",
+		.parent_names = gcc_xo_ubi32_pll_gpll0_gpll2_gpll4_gpll6,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap_div nss_ubi0_div_clk_src = {
+	.reg = 0x68118,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_ubi0_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_ubi0_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ro_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg2 nss_ubi1_clk_src = {
+	.cmd_rcgr = 0x68124,
+	.freq_tbl = ftbl_nss_ubi_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_ubi32_gpll0_gpll2_gpll4_gpll6_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_ubi1_clk_src",
+		.parent_names = gcc_xo_ubi32_pll_gpll0_gpll2_gpll4_gpll6,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap_div nss_ubi1_div_clk_src = {
+	.reg = 0x68138,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_ubi1_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_ubi1_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ro_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_ubi_mpt_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(25000000, P_GPLL0_DIV2, 16, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 ubi_mpt_clk_src = {
+	.cmd_rcgr = 0x68090,
+	.freq_tbl = ftbl_ubi_mpt_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "ubi_mpt_clk_src",
+		.parent_names = gcc_xo_gpll0_out_main_div2,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_imem_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(400000000, P_GPLL0, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_imem_clk_src = {
+	.cmd_rcgr = 0x68158,
+	.freq_tbl = ftbl_nss_imem_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll4_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_imem_clk_src",
+		.parent_names = gcc_xo_gpll0_gpll4,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_ppe_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(300000000, P_BIAS_PLL, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_ppe_clk_src = {
+	.cmd_rcgr = 0x68080,
+	.freq_tbl = ftbl_nss_ppe_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_bias_gpll0_gpll4_nss_ubi32_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_ppe_clk_src",
+		.parent_names = gcc_xo_bias_gpll0_gpll4_nss_ubi32,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_fixed_factor nss_ppe_cdiv_clk_src = {
+	.mult = 1,
+	.div = 4,
+	.hw.init = &(struct clk_init_data){
+		.name = "nss_ppe_cdiv_clk_src",
+		.parent_names = (const char *[]){
+			"nss_ppe_clk_src"
+		},
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_port1_rx_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY0_RX, 5, 0, 0),
+	F(125000000, P_UNIPHY0_RX, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_port1_rx_clk_src = {
+	.cmd_rcgr = 0x68020,
+	.freq_tbl = ftbl_nss_port1_rx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_rx_tx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port1_rx_clk_src",
+		.parent_names = gcc_xo_uniphy0_rx_tx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port1_rx_div_clk_src = {
+	.reg = 0x68400,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port1_rx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port1_rx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_nss_port1_tx_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY0_TX, 5, 0, 0),
+	F(125000000, P_UNIPHY0_TX, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_port1_tx_clk_src = {
+	.cmd_rcgr = 0x68028,
+	.freq_tbl = ftbl_nss_port1_tx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_tx_rx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port1_tx_clk_src",
+		.parent_names = gcc_xo_uniphy0_tx_rx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port1_tx_div_clk_src = {
+	.reg = 0x68404,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port1_tx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port1_tx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg2 nss_port2_rx_clk_src = {
+	.cmd_rcgr = 0x68030,
+	.freq_tbl = ftbl_nss_port1_rx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_rx_tx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port2_rx_clk_src",
+		.parent_names = gcc_xo_uniphy0_rx_tx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port2_rx_div_clk_src = {
+	.reg = 0x68410,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port2_rx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port2_rx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg2 nss_port2_tx_clk_src = {
+	.cmd_rcgr = 0x68038,
+	.freq_tbl = ftbl_nss_port1_tx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_tx_rx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port2_tx_clk_src",
+		.parent_names = gcc_xo_uniphy0_tx_rx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port2_tx_div_clk_src = {
+	.reg = 0x68414,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port2_tx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port2_tx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg2 nss_port3_rx_clk_src = {
+	.cmd_rcgr = 0x68040,
+	.freq_tbl = ftbl_nss_port1_rx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_rx_tx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port3_rx_clk_src",
+		.parent_names = gcc_xo_uniphy0_rx_tx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port3_rx_div_clk_src = {
+	.reg = 0x68420,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port3_rx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port3_rx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg2 nss_port3_tx_clk_src = {
+	.cmd_rcgr = 0x68048,
+	.freq_tbl = ftbl_nss_port1_tx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_tx_rx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port3_tx_clk_src",
+		.parent_names = gcc_xo_uniphy0_tx_rx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port3_tx_div_clk_src = {
+	.reg = 0x68424,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port3_tx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port3_tx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg2 nss_port4_rx_clk_src = {
+	.cmd_rcgr = 0x68050,
+	.freq_tbl = ftbl_nss_port1_rx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_rx_tx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port4_rx_clk_src",
+		.parent_names = gcc_xo_uniphy0_rx_tx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port4_rx_div_clk_src = {
+	.reg = 0x68430,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port4_rx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port4_rx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg2 nss_port4_tx_clk_src = {
+	.cmd_rcgr = 0x68058,
+	.freq_tbl = ftbl_nss_port1_tx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_tx_rx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port4_tx_clk_src",
+		.parent_names = gcc_xo_uniphy0_tx_rx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port4_tx_div_clk_src = {
+	.reg = 0x68434,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port4_tx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port4_tx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_nss_port5_rx_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY1_RX, 12.5, 0, 0),
+	F(78125000, P_UNIPHY1_RX, 4, 0, 0),
+	F(125000000, P_UNIPHY1_RX, 2.5, 0, 0),
+	F(156250000, P_UNIPHY1_RX, 2, 0, 0),
+	F(312500000, P_UNIPHY1_RX, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_port5_rx_clk_src = {
+	.cmd_rcgr = 0x68060,
+	.freq_tbl = ftbl_nss_port5_rx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_rx_tx_uniphy1_rx_tx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port5_rx_clk_src",
+		.parent_names = gcc_xo_uniphy0_rx_tx_uniphy1_rx_tx_ubi32_bias,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port5_rx_div_clk_src = {
+	.reg = 0x68440,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port5_rx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port5_rx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_nss_port5_tx_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY1_TX, 12.5, 0, 0),
+	F(78125000, P_UNIPHY1_TX, 4, 0, 0),
+	F(125000000, P_UNIPHY1_TX, 2.5, 0, 0),
+	F(156250000, P_UNIPHY1_TX, 2, 0, 0),
+	F(312500000, P_UNIPHY1_TX, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_port5_tx_clk_src = {
+	.cmd_rcgr = 0x68068,
+	.freq_tbl = ftbl_nss_port5_tx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_tx_rx_uniphy1_tx_rx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port5_tx_clk_src",
+		.parent_names = gcc_xo_uniphy0_tx_rx_uniphy1_tx_rx_ubi32_bias,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port5_tx_div_clk_src = {
+	.reg = 0x68444,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port5_tx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port5_tx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_nss_port6_rx_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY2_RX, 12.5, 0, 0),
+	F(78125000, P_UNIPHY2_RX, 4, 0, 0),
+	F(125000000, P_UNIPHY2_RX, 2.5, 0, 0),
+	F(156250000, P_UNIPHY2_RX, 2, 0, 0),
+	F(312500000, P_UNIPHY2_RX, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_port6_rx_clk_src = {
+	.cmd_rcgr = 0x68070,
+	.freq_tbl = ftbl_nss_port6_rx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy2_rx_tx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port6_rx_clk_src",
+		.parent_names = gcc_xo_uniphy2_rx_tx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port6_rx_div_clk_src = {
+	.reg = 0x68450,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port6_rx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port6_rx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_nss_port6_tx_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY2_TX, 12.5, 0, 0),
+	F(78125000, P_UNIPHY2_TX, 4, 0, 0),
+	F(125000000, P_UNIPHY2_TX, 2.5, 0, 0),
+	F(156250000, P_UNIPHY2_TX, 2, 0, 0),
+	F(312500000, P_UNIPHY2_TX, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 nss_port6_tx_clk_src = {
+	.cmd_rcgr = 0x68078,
+	.freq_tbl = ftbl_nss_port6_tx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy2_tx_rx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port6_tx_clk_src",
+		.parent_names = gcc_xo_uniphy2_tx_rx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port6_tx_div_clk_src = {
+	.reg = 0x68454,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port6_tx_div_clk_src",
+			.parent_names = (const char *[]){
+				"nss_port6_tx_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct freq_tbl ftbl_crypto_clk_src[] = {
+	F(40000000, P_GPLL0_DIV2, 10, 0, 0),
+	F(80000000, P_GPLL0, 10, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	F(160000000, P_GPLL0, 5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 crypto_clk_src = {
+	.cmd_rcgr = 0x16004,
+	.freq_tbl = ftbl_crypto_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "crypto_clk_src",
+		.parent_names = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_gp_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gp1_clk_src = {
+	.cmd_rcgr = 0x08004,
+	.freq_tbl = ftbl_gp_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_gpll0_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gp1_clk_src",
+		.parent_names = gcc_xo_gpll0_gpll6_gpll0_sleep_clk,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gp2_clk_src = {
+	.cmd_rcgr = 0x09004,
+	.freq_tbl = ftbl_gp_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_gpll0_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gp2_clk_src",
+		.parent_names = gcc_xo_gpll0_gpll6_gpll0_sleep_clk,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gp3_clk_src = {
+	.cmd_rcgr = 0x0a004,
+	.freq_tbl = ftbl_gp_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_gpll0_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gp3_clk_src",
+		.parent_names = gcc_xo_gpll0_gpll6_gpll0_sleep_clk,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
 static struct clk_branch gcc_blsp1_ahb_clk = {
 	.halt_reg = 0x01008,
 	.clkr = {
@@ -803,14 +2398,1957 @@ static struct clk_branch gcc_qpic_clk = {
 	},
 };
 
+static struct clk_branch gcc_pcie0_ahb_clk = {
+	.halt_reg = 0x75010,
+	.clkr = {
+		.enable_reg = 0x75010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie0_aux_clk = {
+	.halt_reg = 0x75014,
+	.clkr = {
+		.enable_reg = 0x75014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_aux_clk",
+			.parent_names = (const char *[]){
+				"pcie0_aux_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie0_axi_m_clk = {
+	.halt_reg = 0x75008,
+	.clkr = {
+		.enable_reg = 0x75008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_axi_m_clk",
+			.parent_names = (const char *[]){
+				"pcie0_axi_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie0_axi_s_clk = {
+	.halt_reg = 0x7500c,
+	.clkr = {
+		.enable_reg = 0x7500c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_axi_s_clk",
+			.parent_names = (const char *[]){
+				"pcie0_axi_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie0_pipe_clk = {
+	.halt_reg = 0x75018,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x75018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_pipe_clk",
+			.parent_names = (const char *[]){
+				"pcie0_pipe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sys_noc_pcie0_axi_clk = {
+	.halt_reg = 0x26048,
+	.clkr = {
+		.enable_reg = 0x26048,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sys_noc_pcie0_axi_clk",
+			.parent_names = (const char *[]){
+				"pcie0_axi_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie1_ahb_clk = {
+	.halt_reg = 0x76010,
+	.clkr = {
+		.enable_reg = 0x76010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie1_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie1_aux_clk = {
+	.halt_reg = 0x76014,
+	.clkr = {
+		.enable_reg = 0x76014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie1_aux_clk",
+			.parent_names = (const char *[]){
+				"pcie1_aux_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie1_axi_m_clk = {
+	.halt_reg = 0x76008,
+	.clkr = {
+		.enable_reg = 0x76008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie1_axi_m_clk",
+			.parent_names = (const char *[]){
+				"pcie1_axi_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie1_axi_s_clk = {
+	.halt_reg = 0x7600c,
+	.clkr = {
+		.enable_reg = 0x7600c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie1_axi_s_clk",
+			.parent_names = (const char *[]){
+				"pcie1_axi_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie1_pipe_clk = {
+	.halt_reg = 0x76018,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x76018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie1_pipe_clk",
+			.parent_names = (const char *[]){
+				"pcie1_pipe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sys_noc_pcie1_axi_clk = {
+	.halt_reg = 0x2604c,
+	.clkr = {
+		.enable_reg = 0x2604c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sys_noc_pcie1_axi_clk",
+			.parent_names = (const char *[]){
+				"pcie1_axi_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_aux_clk = {
+	.halt_reg = 0x3e044,
+	.clkr = {
+		.enable_reg = 0x3e044,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_aux_clk",
+			.parent_names = (const char *[]){
+				"usb0_aux_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sys_noc_usb0_axi_clk = {
+	.halt_reg = 0x26040,
+	.clkr = {
+		.enable_reg = 0x26040,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sys_noc_usb0_axi_clk",
+			.parent_names = (const char *[]){
+				"usb0_master_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_master_clk = {
+	.halt_reg = 0x3e000,
+	.clkr = {
+		.enable_reg = 0x3e000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_master_clk",
+			.parent_names = (const char *[]){
+				"usb0_master_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_mock_utmi_clk = {
+	.halt_reg = 0x3e008,
+	.clkr = {
+		.enable_reg = 0x3e008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_mock_utmi_clk",
+			.parent_names = (const char *[]){
+				"usb0_mock_utmi_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_phy_cfg_ahb_clk = {
+	.halt_reg = 0x3e080,
+	.clkr = {
+		.enable_reg = 0x3e080,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_phy_cfg_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_pipe_clk = {
+	.halt_reg = 0x3e040,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x3e040,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_pipe_clk",
+			.parent_names = (const char *[]){
+				"usb0_pipe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_sleep_clk = {
+	.halt_reg = 0x3e004,
+	.clkr = {
+		.enable_reg = 0x3e004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_sleep_clk",
+			.parent_names = (const char *[]){
+				"gcc_sleep_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb1_aux_clk = {
+	.halt_reg = 0x3f044,
+	.clkr = {
+		.enable_reg = 0x3f044,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb1_aux_clk",
+			.parent_names = (const char *[]){
+				"usb1_aux_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sys_noc_usb1_axi_clk = {
+	.halt_reg = 0x26044,
+	.clkr = {
+		.enable_reg = 0x26044,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sys_noc_usb1_axi_clk",
+			.parent_names = (const char *[]){
+				"usb1_master_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb1_master_clk = {
+	.halt_reg = 0x3f000,
+	.clkr = {
+		.enable_reg = 0x3f000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb1_master_clk",
+			.parent_names = (const char *[]){
+				"usb1_master_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb1_mock_utmi_clk = {
+	.halt_reg = 0x3f008,
+	.clkr = {
+		.enable_reg = 0x3f008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb1_mock_utmi_clk",
+			.parent_names = (const char *[]){
+				"usb1_mock_utmi_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb1_phy_cfg_ahb_clk = {
+	.halt_reg = 0x3f080,
+	.clkr = {
+		.enable_reg = 0x3f080,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb1_phy_cfg_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb1_pipe_clk = {
+	.halt_reg = 0x3f040,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x3f040,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb1_pipe_clk",
+			.parent_names = (const char *[]){
+				"usb1_pipe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb1_sleep_clk = {
+	.halt_reg = 0x3f004,
+	.clkr = {
+		.enable_reg = 0x3f004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb1_sleep_clk",
+			.parent_names = (const char *[]){
+				"gcc_sleep_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_ahb_clk = {
+	.halt_reg = 0x4201c,
+	.clkr = {
+		.enable_reg = 0x4201c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_apps_clk = {
+	.halt_reg = 0x42018,
+	.clkr = {
+		.enable_reg = 0x42018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_apps_clk",
+			.parent_names = (const char *[]){
+				"sdcc1_apps_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_ice_core_clk = {
+	.halt_reg = 0x5d014,
+	.clkr = {
+		.enable_reg = 0x5d014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_ice_core_clk",
+			.parent_names = (const char *[]){
+				"sdcc1_ice_core_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc2_ahb_clk = {
+	.halt_reg = 0x4301c,
+	.clkr = {
+		.enable_reg = 0x4301c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc2_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc2_apps_clk = {
+	.halt_reg = 0x43018,
+	.clkr = {
+		.enable_reg = 0x43018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc2_apps_clk",
+			.parent_names = (const char *[]){
+				"sdcc2_apps_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_mem_noc_nss_axi_clk = {
+	.halt_reg = 0x1d03c,
+	.clkr = {
+		.enable_reg = 0x1d03c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_mem_noc_nss_axi_clk",
+			.parent_names = (const char *[]){
+				"nss_noc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ce_apb_clk = {
+	.halt_reg = 0x68174,
+	.clkr = {
+		.enable_reg = 0x68174,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ce_apb_clk",
+			.parent_names = (const char *[]){
+				"nss_ce_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ce_axi_clk = {
+	.halt_reg = 0x68170,
+	.clkr = {
+		.enable_reg = 0x68170,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ce_axi_clk",
+			.parent_names = (const char *[]){
+				"nss_ce_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_cfg_clk = {
+	.halt_reg = 0x68160,
+	.clkr = {
+		.enable_reg = 0x68160,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_cfg_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_crypto_clk = {
+	.halt_reg = 0x68164,
+	.clkr = {
+		.enable_reg = 0x68164,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_crypto_clk",
+			.parent_names = (const char *[]){
+				"nss_crypto_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_csr_clk = {
+	.halt_reg = 0x68318,
+	.clkr = {
+		.enable_reg = 0x68318,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_csr_clk",
+			.parent_names = (const char *[]){
+				"nss_ce_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_edma_cfg_clk = {
+	.halt_reg = 0x6819c,
+	.clkr = {
+		.enable_reg = 0x6819c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_edma_cfg_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_edma_clk = {
+	.halt_reg = 0x68198,
+	.clkr = {
+		.enable_reg = 0x68198,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_edma_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_imem_clk = {
+	.halt_reg = 0x68178,
+	.clkr = {
+		.enable_reg = 0x68178,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_imem_clk",
+			.parent_names = (const char *[]){
+				"nss_imem_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_noc_clk = {
+	.halt_reg = 0x68168,
+	.clkr = {
+		.enable_reg = 0x68168,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_noc_clk",
+			.parent_names = (const char *[]){
+				"nss_noc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ppe_btq_clk = {
+	.halt_reg = 0x6833c,
+	.clkr = {
+		.enable_reg = 0x6833c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ppe_btq_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ppe_cfg_clk = {
+	.halt_reg = 0x68194,
+	.clkr = {
+		.enable_reg = 0x68194,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ppe_cfg_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ppe_clk = {
+	.halt_reg = 0x68190,
+	.clkr = {
+		.enable_reg = 0x68190,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ppe_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ppe_ipe_clk = {
+	.halt_reg = 0x68338,
+	.clkr = {
+		.enable_reg = 0x68338,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ppe_ipe_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ptp_ref_clk = {
+	.halt_reg = 0x6816c,
+	.clkr = {
+		.enable_reg = 0x6816c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ptp_ref_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_cdiv_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_ce_apb_clk = {
+	.halt_reg = 0x6830c,
+	.clkr = {
+		.enable_reg = 0x6830c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_ce_apb_clk",
+			.parent_names = (const char *[]){
+				"nss_ce_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_ce_axi_clk = {
+	.halt_reg = 0x68308,
+	.clkr = {
+		.enable_reg = 0x68308,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_ce_axi_clk",
+			.parent_names = (const char *[]){
+				"nss_ce_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_crypto_clk = {
+	.halt_reg = 0x68314,
+	.clkr = {
+		.enable_reg = 0x68314,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_crypto_clk",
+			.parent_names = (const char *[]){
+				"nss_crypto_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_ppe_cfg_clk = {
+	.halt_reg = 0x68304,
+	.clkr = {
+		.enable_reg = 0x68304,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_ppe_cfg_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_ppe_clk = {
+	.halt_reg = 0x68300,
+	.clkr = {
+		.enable_reg = 0x68300,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_ppe_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_qosgen_ref_clk = {
+	.halt_reg = 0x68180,
+	.clkr = {
+		.enable_reg = 0x68180,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_qosgen_ref_clk",
+			.parent_names = (const char *[]){
+				"gcc_xo_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_snoc_clk = {
+	.halt_reg = 0x68188,
+	.clkr = {
+		.enable_reg = 0x68188,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_snoc_clk",
+			.parent_names = (const char *[]){
+				"system_noc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_timeout_ref_clk = {
+	.halt_reg = 0x68184,
+	.clkr = {
+		.enable_reg = 0x68184,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_timeout_ref_clk",
+			.parent_names = (const char *[]){
+				"gcc_xo_div4_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_ubi0_ahb_clk = {
+	.halt_reg = 0x68270,
+	.clkr = {
+		.enable_reg = 0x68270,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_ubi0_ahb_clk",
+			.parent_names = (const char *[]){
+				"nss_ce_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_ubi1_ahb_clk = {
+	.halt_reg = 0x68274,
+	.clkr = {
+		.enable_reg = 0x68274,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_ubi1_ahb_clk",
+			.parent_names = (const char *[]){
+				"nss_ce_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi0_ahb_clk = {
+	.halt_reg = 0x6820c,
+	.clkr = {
+		.enable_reg = 0x6820c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi0_ahb_clk",
+			.parent_names = (const char *[]){
+				"nss_ce_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi0_axi_clk = {
+	.halt_reg = 0x68200,
+	.clkr = {
+		.enable_reg = 0x68200,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi0_axi_clk",
+			.parent_names = (const char *[]){
+				"nss_noc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi0_nc_axi_clk = {
+	.halt_reg = 0x68204,
+	.clkr = {
+		.enable_reg = 0x68204,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi0_nc_axi_clk",
+			.parent_names = (const char *[]){
+				"nss_noc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi0_core_clk = {
+	.halt_reg = 0x68210,
+	.clkr = {
+		.enable_reg = 0x68210,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi0_core_clk",
+			.parent_names = (const char *[]){
+				"nss_ubi0_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi0_mpt_clk = {
+	.halt_reg = 0x68208,
+	.clkr = {
+		.enable_reg = 0x68208,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi0_mpt_clk",
+			.parent_names = (const char *[]){
+				"ubi_mpt_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi1_ahb_clk = {
+	.halt_reg = 0x6822c,
+	.clkr = {
+		.enable_reg = 0x6822c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi1_ahb_clk",
+			.parent_names = (const char *[]){
+				"nss_ce_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi1_axi_clk = {
+	.halt_reg = 0x68220,
+	.clkr = {
+		.enable_reg = 0x68220,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi1_axi_clk",
+			.parent_names = (const char *[]){
+				"nss_noc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi1_nc_axi_clk = {
+	.halt_reg = 0x68224,
+	.clkr = {
+		.enable_reg = 0x68224,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi1_nc_axi_clk",
+			.parent_names = (const char *[]){
+				"nss_noc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi1_core_clk = {
+	.halt_reg = 0x68230,
+	.clkr = {
+		.enable_reg = 0x68230,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi1_core_clk",
+			.parent_names = (const char *[]){
+				"nss_ubi1_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi1_mpt_clk = {
+	.halt_reg = 0x68228,
+	.clkr = {
+		.enable_reg = 0x68228,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi1_mpt_clk",
+			.parent_names = (const char *[]){
+				"ubi_mpt_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_cmn_12gpll_ahb_clk = {
+	.halt_reg = 0x56308,
+	.clkr = {
+		.enable_reg = 0x56308,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_cmn_12gpll_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_cmn_12gpll_sys_clk = {
+	.halt_reg = 0x5630c,
+	.clkr = {
+		.enable_reg = 0x5630c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_cmn_12gpll_sys_clk",
+			.parent_names = (const char *[]){
+				"gcc_xo_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_mdio_ahb_clk = {
+	.halt_reg = 0x58004,
+	.clkr = {
+		.enable_reg = 0x58004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_mdio_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_ahb_clk = {
+	.halt_reg = 0x56008,
+	.clkr = {
+		.enable_reg = 0x56008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_sys_clk = {
+	.halt_reg = 0x5600c,
+	.clkr = {
+		.enable_reg = 0x5600c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_sys_clk",
+			.parent_names = (const char *[]){
+				"gcc_xo_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy1_ahb_clk = {
+	.halt_reg = 0x56108,
+	.clkr = {
+		.enable_reg = 0x56108,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy1_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy1_sys_clk = {
+	.halt_reg = 0x5610c,
+	.clkr = {
+		.enable_reg = 0x5610c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy1_sys_clk",
+			.parent_names = (const char *[]){
+				"gcc_xo_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy2_ahb_clk = {
+	.halt_reg = 0x56208,
+	.clkr = {
+		.enable_reg = 0x56208,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy2_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy2_sys_clk = {
+	.halt_reg = 0x5620c,
+	.clkr = {
+		.enable_reg = 0x5620c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy2_sys_clk",
+			.parent_names = (const char *[]){
+				"gcc_xo_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port1_rx_clk = {
+	.halt_reg = 0x68240,
+	.clkr = {
+		.enable_reg = 0x68240,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port1_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port1_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port1_tx_clk = {
+	.halt_reg = 0x68244,
+	.clkr = {
+		.enable_reg = 0x68244,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port1_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port1_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port2_rx_clk = {
+	.halt_reg = 0x68248,
+	.clkr = {
+		.enable_reg = 0x68248,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port2_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port2_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port2_tx_clk = {
+	.halt_reg = 0x6824c,
+	.clkr = {
+		.enable_reg = 0x6824c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port2_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port2_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port3_rx_clk = {
+	.halt_reg = 0x68250,
+	.clkr = {
+		.enable_reg = 0x68250,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port3_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port3_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port3_tx_clk = {
+	.halt_reg = 0x68254,
+	.clkr = {
+		.enable_reg = 0x68254,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port3_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port3_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port4_rx_clk = {
+	.halt_reg = 0x68258,
+	.clkr = {
+		.enable_reg = 0x68258,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port4_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port4_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port4_tx_clk = {
+	.halt_reg = 0x6825c,
+	.clkr = {
+		.enable_reg = 0x6825c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port4_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port4_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port5_rx_clk = {
+	.halt_reg = 0x68260,
+	.clkr = {
+		.enable_reg = 0x68260,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port5_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port5_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port5_tx_clk = {
+	.halt_reg = 0x68264,
+	.clkr = {
+		.enable_reg = 0x68264,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port5_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port5_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port6_rx_clk = {
+	.halt_reg = 0x68268,
+	.clkr = {
+		.enable_reg = 0x68268,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port6_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port6_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port6_tx_clk = {
+	.halt_reg = 0x6826c,
+	.clkr = {
+		.enable_reg = 0x6826c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port6_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port6_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_port1_mac_clk = {
+	.halt_reg = 0x68320,
+	.clkr = {
+		.enable_reg = 0x68320,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_port1_mac_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_port2_mac_clk = {
+	.halt_reg = 0x68324,
+	.clkr = {
+		.enable_reg = 0x68324,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_port2_mac_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_port3_mac_clk = {
+	.halt_reg = 0x68328,
+	.clkr = {
+		.enable_reg = 0x68328,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_port3_mac_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_port4_mac_clk = {
+	.halt_reg = 0x6832c,
+	.clkr = {
+		.enable_reg = 0x6832c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_port4_mac_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_port5_mac_clk = {
+	.halt_reg = 0x68330,
+	.clkr = {
+		.enable_reg = 0x68330,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_port5_mac_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_port6_mac_clk = {
+	.halt_reg = 0x68334,
+	.clkr = {
+		.enable_reg = 0x68334,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_port6_mac_clk",
+			.parent_names = (const char *[]){
+				"nss_ppe_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port1_rx_clk = {
+	.halt_reg = 0x56010,
+	.clkr = {
+		.enable_reg = 0x56010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port1_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port1_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port1_tx_clk = {
+	.halt_reg = 0x56014,
+	.clkr = {
+		.enable_reg = 0x56014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port1_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port1_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port2_rx_clk = {
+	.halt_reg = 0x56018,
+	.clkr = {
+		.enable_reg = 0x56018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port2_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port2_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port2_tx_clk = {
+	.halt_reg = 0x5601c,
+	.clkr = {
+		.enable_reg = 0x5601c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port2_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port2_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port3_rx_clk = {
+	.halt_reg = 0x56020,
+	.clkr = {
+		.enable_reg = 0x56020,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port3_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port3_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port3_tx_clk = {
+	.halt_reg = 0x56024,
+	.clkr = {
+		.enable_reg = 0x56024,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port3_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port3_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port4_rx_clk = {
+	.halt_reg = 0x56028,
+	.clkr = {
+		.enable_reg = 0x56028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port4_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port4_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port4_tx_clk = {
+	.halt_reg = 0x5602c,
+	.clkr = {
+		.enable_reg = 0x5602c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port4_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port4_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port5_rx_clk = {
+	.halt_reg = 0x56030,
+	.clkr = {
+		.enable_reg = 0x56030,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port5_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port5_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port5_tx_clk = {
+	.halt_reg = 0x56034,
+	.clkr = {
+		.enable_reg = 0x56034,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port5_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port5_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy1_port5_rx_clk = {
+	.halt_reg = 0x56110,
+	.clkr = {
+		.enable_reg = 0x56110,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy1_port5_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port5_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy1_port5_tx_clk = {
+	.halt_reg = 0x56114,
+	.clkr = {
+		.enable_reg = 0x56114,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy1_port5_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port5_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy2_port6_rx_clk = {
+	.halt_reg = 0x56210,
+	.clkr = {
+		.enable_reg = 0x56210,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy2_port6_rx_clk",
+			.parent_names = (const char *[]){
+				"nss_port6_rx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy2_port6_tx_clk = {
+	.halt_reg = 0x56214,
+	.clkr = {
+		.enable_reg = 0x56214,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy2_port6_tx_clk",
+			.parent_names = (const char *[]){
+				"nss_port6_tx_div_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_crypto_ahb_clk = {
+	.halt_reg = 0x16024,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x0b004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_crypto_ahb_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_crypto_axi_clk = {
+	.halt_reg = 0x16020,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x0b004,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_crypto_axi_clk",
+			.parent_names = (const char *[]){
+				"pcnoc_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_crypto_clk = {
+	.halt_reg = 0x1601c,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x0b004,
+		.enable_mask = BIT(2),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_crypto_clk",
+			.parent_names = (const char *[]){
+				"crypto_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp1_clk = {
+	.halt_reg = 0x08000,
+	.clkr = {
+		.enable_reg = 0x08000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp1_clk",
+			.parent_names = (const char *[]){
+				"gp1_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp2_clk = {
+	.halt_reg = 0x09000,
+	.clkr = {
+		.enable_reg = 0x09000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp2_clk",
+			.parent_names = (const char *[]){
+				"gp2_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp3_clk = {
+	.halt_reg = 0x0a000,
+	.clkr = {
+		.enable_reg = 0x0a000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp3_clk",
+			.parent_names = (const char *[]){
+				"gp3_clk_src"
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_hw *gcc_ipq8074_hws[] = {
 	&gpll0_out_main_div2.hw,
+	&gpll6_out_main_div2.hw,
 	&pcnoc_clk_src.hw,
+	&system_noc_clk_src.hw,
+	&gcc_xo_div4_clk_src.hw,
+	&nss_noc_clk_src.hw,
+	&nss_ppe_cdiv_clk_src.hw,
 };
 
 static struct clk_regmap *gcc_ipq8074_clks[] = {
 	[GPLL0_MAIN] = &gpll0_main.clkr,
 	[GPLL0] = &gpll0.clkr,
+	[GPLL2_MAIN] = &gpll2_main.clkr,
+	[GPLL2] = &gpll2.clkr,
+	[GPLL4_MAIN] = &gpll4_main.clkr,
+	[GPLL4] = &gpll4.clkr,
+	[GPLL6_MAIN] = &gpll6_main.clkr,
+	[GPLL6] = &gpll6.clkr,
+	[UBI32_PLL_MAIN] = &ubi32_pll_main.clkr,
+	[UBI32_PLL] = &ubi32_pll.clkr,
+	[NSS_CRYPTO_PLL_MAIN] = &nss_crypto_pll_main.clkr,
+	[NSS_CRYPTO_PLL] = &nss_crypto_pll.clkr,
 	[PCNOC_BFDCD_CLK_SRC] = &pcnoc_bfdcd_clk_src.clkr,
 	[GCC_SLEEP_CLK_SRC] = &gcc_sleep_clk_src.clkr,
 	[BLSP1_QUP1_I2C_APPS_CLK_SRC] = &blsp1_qup1_i2c_apps_clk_src.clkr,
@@ -831,6 +4369,63 @@ static struct clk_regmap *gcc_ipq8074_clks[] = {
 	[BLSP1_UART4_APPS_CLK_SRC] = &blsp1_uart4_apps_clk_src.clkr,
 	[BLSP1_UART5_APPS_CLK_SRC] = &blsp1_uart5_apps_clk_src.clkr,
 	[BLSP1_UART6_APPS_CLK_SRC] = &blsp1_uart6_apps_clk_src.clkr,
+	[PCIE0_AXI_CLK_SRC] = &pcie0_axi_clk_src.clkr,
+	[PCIE0_AUX_CLK_SRC] = &pcie0_aux_clk_src.clkr,
+	[PCIE0_PIPE_CLK_SRC] = &pcie0_pipe_clk_src.clkr,
+	[PCIE1_AXI_CLK_SRC] = &pcie1_axi_clk_src.clkr,
+	[PCIE1_AUX_CLK_SRC] = &pcie1_aux_clk_src.clkr,
+	[PCIE1_PIPE_CLK_SRC] = &pcie1_pipe_clk_src.clkr,
+	[SDCC1_APPS_CLK_SRC] = &sdcc1_apps_clk_src.clkr,
+	[SDCC1_ICE_CORE_CLK_SRC] = &sdcc1_ice_core_clk_src.clkr,
+	[SDCC2_APPS_CLK_SRC] = &sdcc2_apps_clk_src.clkr,
+	[USB0_MASTER_CLK_SRC] = &usb0_master_clk_src.clkr,
+	[USB0_AUX_CLK_SRC] = &usb0_aux_clk_src.clkr,
+	[USB0_MOCK_UTMI_CLK_SRC] = &usb0_mock_utmi_clk_src.clkr,
+	[USB0_PIPE_CLK_SRC] = &usb0_pipe_clk_src.clkr,
+	[USB1_MASTER_CLK_SRC] = &usb1_master_clk_src.clkr,
+	[USB1_AUX_CLK_SRC] = &usb1_aux_clk_src.clkr,
+	[USB1_MOCK_UTMI_CLK_SRC] = &usb1_mock_utmi_clk_src.clkr,
+	[USB1_PIPE_CLK_SRC] = &usb1_pipe_clk_src.clkr,
+	[GCC_XO_CLK_SRC] = &gcc_xo_clk_src.clkr,
+	[SYSTEM_NOC_BFDCD_CLK_SRC] = &system_noc_bfdcd_clk_src.clkr,
+	[NSS_CE_CLK_SRC] = &nss_ce_clk_src.clkr,
+	[NSS_NOC_BFDCD_CLK_SRC] = &nss_noc_bfdcd_clk_src.clkr,
+	[NSS_CRYPTO_CLK_SRC] = &nss_crypto_clk_src.clkr,
+	[NSS_UBI0_CLK_SRC] = &nss_ubi0_clk_src.clkr,
+	[NSS_UBI0_DIV_CLK_SRC] = &nss_ubi0_div_clk_src.clkr,
+	[NSS_UBI1_CLK_SRC] = &nss_ubi1_clk_src.clkr,
+	[NSS_UBI1_DIV_CLK_SRC] = &nss_ubi1_div_clk_src.clkr,
+	[UBI_MPT_CLK_SRC] = &ubi_mpt_clk_src.clkr,
+	[NSS_IMEM_CLK_SRC] = &nss_imem_clk_src.clkr,
+	[NSS_PPE_CLK_SRC] = &nss_ppe_clk_src.clkr,
+	[NSS_PORT1_RX_CLK_SRC] = &nss_port1_rx_clk_src.clkr,
+	[NSS_PORT1_RX_DIV_CLK_SRC] = &nss_port1_rx_div_clk_src.clkr,
+	[NSS_PORT1_TX_CLK_SRC] = &nss_port1_tx_clk_src.clkr,
+	[NSS_PORT1_TX_DIV_CLK_SRC] = &nss_port1_tx_div_clk_src.clkr,
+	[NSS_PORT2_RX_CLK_SRC] = &nss_port2_rx_clk_src.clkr,
+	[NSS_PORT2_RX_DIV_CLK_SRC] = &nss_port2_rx_div_clk_src.clkr,
+	[NSS_PORT2_TX_CLK_SRC] = &nss_port2_tx_clk_src.clkr,
+	[NSS_PORT2_TX_DIV_CLK_SRC] = &nss_port2_tx_div_clk_src.clkr,
+	[NSS_PORT3_RX_CLK_SRC] = &nss_port3_rx_clk_src.clkr,
+	[NSS_PORT3_RX_DIV_CLK_SRC] = &nss_port3_rx_div_clk_src.clkr,
+	[NSS_PORT3_TX_CLK_SRC] = &nss_port3_tx_clk_src.clkr,
+	[NSS_PORT3_TX_DIV_CLK_SRC] = &nss_port3_tx_div_clk_src.clkr,
+	[NSS_PORT4_RX_CLK_SRC] = &nss_port4_rx_clk_src.clkr,
+	[NSS_PORT4_RX_DIV_CLK_SRC] = &nss_port4_rx_div_clk_src.clkr,
+	[NSS_PORT4_TX_CLK_SRC] = &nss_port4_tx_clk_src.clkr,
+	[NSS_PORT4_TX_DIV_CLK_SRC] = &nss_port4_tx_div_clk_src.clkr,
+	[NSS_PORT5_RX_CLK_SRC] = &nss_port5_rx_clk_src.clkr,
+	[NSS_PORT5_RX_DIV_CLK_SRC] = &nss_port5_rx_div_clk_src.clkr,
+	[NSS_PORT5_TX_CLK_SRC] = &nss_port5_tx_clk_src.clkr,
+	[NSS_PORT5_TX_DIV_CLK_SRC] = &nss_port5_tx_div_clk_src.clkr,
+	[NSS_PORT6_RX_CLK_SRC] = &nss_port6_rx_clk_src.clkr,
+	[NSS_PORT6_RX_DIV_CLK_SRC] = &nss_port6_rx_div_clk_src.clkr,
+	[NSS_PORT6_TX_CLK_SRC] = &nss_port6_tx_clk_src.clkr,
+	[NSS_PORT6_TX_DIV_CLK_SRC] = &nss_port6_tx_div_clk_src.clkr,
+	[CRYPTO_CLK_SRC] = &crypto_clk_src.clkr,
+	[GP1_CLK_SRC] = &gp1_clk_src.clkr,
+	[GP2_CLK_SRC] = &gp2_clk_src.clkr,
+	[GP3_CLK_SRC] = &gp3_clk_src.clkr,
 	[GCC_BLSP1_AHB_CLK] = &gcc_blsp1_ahb_clk.clkr,
 	[GCC_BLSP1_QUP1_I2C_APPS_CLK] = &gcc_blsp1_qup1_i2c_apps_clk.clkr,
 	[GCC_BLSP1_QUP1_SPI_APPS_CLK] = &gcc_blsp1_qup1_spi_apps_clk.clkr,
@@ -853,6 +4448,119 @@ static struct clk_regmap *gcc_ipq8074_clks[] = {
 	[GCC_PRNG_AHB_CLK] = &gcc_prng_ahb_clk.clkr,
 	[GCC_QPIC_AHB_CLK] = &gcc_qpic_ahb_clk.clkr,
 	[GCC_QPIC_CLK] = &gcc_qpic_clk.clkr,
+	[GCC_PCIE0_AHB_CLK] = &gcc_pcie0_ahb_clk.clkr,
+	[GCC_PCIE0_AUX_CLK] = &gcc_pcie0_aux_clk.clkr,
+	[GCC_PCIE0_AXI_M_CLK] = &gcc_pcie0_axi_m_clk.clkr,
+	[GCC_PCIE0_AXI_S_CLK] = &gcc_pcie0_axi_s_clk.clkr,
+	[GCC_PCIE0_PIPE_CLK] = &gcc_pcie0_pipe_clk.clkr,
+	[GCC_SYS_NOC_PCIE0_AXI_CLK] = &gcc_sys_noc_pcie0_axi_clk.clkr,
+	[GCC_PCIE1_AHB_CLK] = &gcc_pcie1_ahb_clk.clkr,
+	[GCC_PCIE1_AUX_CLK] = &gcc_pcie1_aux_clk.clkr,
+	[GCC_PCIE1_AXI_M_CLK] = &gcc_pcie1_axi_m_clk.clkr,
+	[GCC_PCIE1_AXI_S_CLK] = &gcc_pcie1_axi_s_clk.clkr,
+	[GCC_PCIE1_PIPE_CLK] = &gcc_pcie1_pipe_clk.clkr,
+	[GCC_SYS_NOC_PCIE1_AXI_CLK] = &gcc_sys_noc_pcie1_axi_clk.clkr,
+	[GCC_USB0_AUX_CLK] = &gcc_usb0_aux_clk.clkr,
+	[GCC_SYS_NOC_USB0_AXI_CLK] = &gcc_sys_noc_usb0_axi_clk.clkr,
+	[GCC_USB0_MASTER_CLK] = &gcc_usb0_master_clk.clkr,
+	[GCC_USB0_MOCK_UTMI_CLK] = &gcc_usb0_mock_utmi_clk.clkr,
+	[GCC_USB0_PHY_CFG_AHB_CLK] = &gcc_usb0_phy_cfg_ahb_clk.clkr,
+	[GCC_USB0_PIPE_CLK] = &gcc_usb0_pipe_clk.clkr,
+	[GCC_USB0_SLEEP_CLK] = &gcc_usb0_sleep_clk.clkr,
+	[GCC_USB1_AUX_CLK] = &gcc_usb1_aux_clk.clkr,
+	[GCC_SYS_NOC_USB1_AXI_CLK] = &gcc_sys_noc_usb1_axi_clk.clkr,
+	[GCC_USB1_MASTER_CLK] = &gcc_usb1_master_clk.clkr,
+	[GCC_USB1_MOCK_UTMI_CLK] = &gcc_usb1_mock_utmi_clk.clkr,
+	[GCC_USB1_PHY_CFG_AHB_CLK] = &gcc_usb1_phy_cfg_ahb_clk.clkr,
+	[GCC_USB1_PIPE_CLK] = &gcc_usb1_pipe_clk.clkr,
+	[GCC_USB1_SLEEP_CLK] = &gcc_usb1_sleep_clk.clkr,
+	[GCC_SDCC1_AHB_CLK] = &gcc_sdcc1_ahb_clk.clkr,
+	[GCC_SDCC1_APPS_CLK] = &gcc_sdcc1_apps_clk.clkr,
+	[GCC_SDCC1_ICE_CORE_CLK] = &gcc_sdcc1_ice_core_clk.clkr,
+	[GCC_SDCC2_AHB_CLK] = &gcc_sdcc2_ahb_clk.clkr,
+	[GCC_SDCC2_APPS_CLK] = &gcc_sdcc2_apps_clk.clkr,
+	[GCC_MEM_NOC_NSS_AXI_CLK] = &gcc_mem_noc_nss_axi_clk.clkr,
+	[GCC_NSS_CE_APB_CLK] = &gcc_nss_ce_apb_clk.clkr,
+	[GCC_NSS_CE_AXI_CLK] = &gcc_nss_ce_axi_clk.clkr,
+	[GCC_NSS_CFG_CLK] = &gcc_nss_cfg_clk.clkr,
+	[GCC_NSS_CRYPTO_CLK] = &gcc_nss_crypto_clk.clkr,
+	[GCC_NSS_CSR_CLK] = &gcc_nss_csr_clk.clkr,
+	[GCC_NSS_EDMA_CFG_CLK] = &gcc_nss_edma_cfg_clk.clkr,
+	[GCC_NSS_EDMA_CLK] = &gcc_nss_edma_clk.clkr,
+	[GCC_NSS_IMEM_CLK] = &gcc_nss_imem_clk.clkr,
+	[GCC_NSS_NOC_CLK] = &gcc_nss_noc_clk.clkr,
+	[GCC_NSS_PPE_BTQ_CLK] = &gcc_nss_ppe_btq_clk.clkr,
+	[GCC_NSS_PPE_CFG_CLK] = &gcc_nss_ppe_cfg_clk.clkr,
+	[GCC_NSS_PPE_CLK] = &gcc_nss_ppe_clk.clkr,
+	[GCC_NSS_PPE_IPE_CLK] = &gcc_nss_ppe_ipe_clk.clkr,
+	[GCC_NSS_PTP_REF_CLK] = &gcc_nss_ptp_ref_clk.clkr,
+	[GCC_NSSNOC_CE_APB_CLK] = &gcc_nssnoc_ce_apb_clk.clkr,
+	[GCC_NSSNOC_CE_AXI_CLK] = &gcc_nssnoc_ce_axi_clk.clkr,
+	[GCC_NSSNOC_CRYPTO_CLK] = &gcc_nssnoc_crypto_clk.clkr,
+	[GCC_NSSNOC_PPE_CFG_CLK] = &gcc_nssnoc_ppe_cfg_clk.clkr,
+	[GCC_NSSNOC_PPE_CLK] = &gcc_nssnoc_ppe_clk.clkr,
+	[GCC_NSSNOC_QOSGEN_REF_CLK] = &gcc_nssnoc_qosgen_ref_clk.clkr,
+	[GCC_NSSNOC_SNOC_CLK] = &gcc_nssnoc_snoc_clk.clkr,
+	[GCC_NSSNOC_TIMEOUT_REF_CLK] = &gcc_nssnoc_timeout_ref_clk.clkr,
+	[GCC_NSSNOC_UBI0_AHB_CLK] = &gcc_nssnoc_ubi0_ahb_clk.clkr,
+	[GCC_NSSNOC_UBI1_AHB_CLK] = &gcc_nssnoc_ubi1_ahb_clk.clkr,
+	[GCC_UBI0_AHB_CLK] = &gcc_ubi0_ahb_clk.clkr,
+	[GCC_UBI0_AXI_CLK] = &gcc_ubi0_axi_clk.clkr,
+	[GCC_UBI0_NC_AXI_CLK] = &gcc_ubi0_nc_axi_clk.clkr,
+	[GCC_UBI0_CORE_CLK] = &gcc_ubi0_core_clk.clkr,
+	[GCC_UBI0_MPT_CLK] = &gcc_ubi0_mpt_clk.clkr,
+	[GCC_UBI1_AHB_CLK] = &gcc_ubi1_ahb_clk.clkr,
+	[GCC_UBI1_AXI_CLK] = &gcc_ubi1_axi_clk.clkr,
+	[GCC_UBI1_NC_AXI_CLK] = &gcc_ubi1_nc_axi_clk.clkr,
+	[GCC_UBI1_CORE_CLK] = &gcc_ubi1_core_clk.clkr,
+	[GCC_UBI1_MPT_CLK] = &gcc_ubi1_mpt_clk.clkr,
+	[GCC_CMN_12GPLL_AHB_CLK] = &gcc_cmn_12gpll_ahb_clk.clkr,
+	[GCC_CMN_12GPLL_SYS_CLK] = &gcc_cmn_12gpll_sys_clk.clkr,
+	[GCC_MDIO_AHB_CLK] = &gcc_mdio_ahb_clk.clkr,
+	[GCC_UNIPHY0_AHB_CLK] = &gcc_uniphy0_ahb_clk.clkr,
+	[GCC_UNIPHY0_SYS_CLK] = &gcc_uniphy0_sys_clk.clkr,
+	[GCC_UNIPHY1_AHB_CLK] = &gcc_uniphy1_ahb_clk.clkr,
+	[GCC_UNIPHY1_SYS_CLK] = &gcc_uniphy1_sys_clk.clkr,
+	[GCC_UNIPHY2_AHB_CLK] = &gcc_uniphy2_ahb_clk.clkr,
+	[GCC_UNIPHY2_SYS_CLK] = &gcc_uniphy2_sys_clk.clkr,
+	[GCC_NSS_PORT1_RX_CLK] = &gcc_nss_port1_rx_clk.clkr,
+	[GCC_NSS_PORT1_TX_CLK] = &gcc_nss_port1_tx_clk.clkr,
+	[GCC_NSS_PORT2_RX_CLK] = &gcc_nss_port2_rx_clk.clkr,
+	[GCC_NSS_PORT2_TX_CLK] = &gcc_nss_port2_tx_clk.clkr,
+	[GCC_NSS_PORT3_RX_CLK] = &gcc_nss_port3_rx_clk.clkr,
+	[GCC_NSS_PORT3_TX_CLK] = &gcc_nss_port3_tx_clk.clkr,
+	[GCC_NSS_PORT4_RX_CLK] = &gcc_nss_port4_rx_clk.clkr,
+	[GCC_NSS_PORT4_TX_CLK] = &gcc_nss_port4_tx_clk.clkr,
+	[GCC_NSS_PORT5_RX_CLK] = &gcc_nss_port5_rx_clk.clkr,
+	[GCC_NSS_PORT5_TX_CLK] = &gcc_nss_port5_tx_clk.clkr,
+	[GCC_NSS_PORT6_RX_CLK] = &gcc_nss_port6_rx_clk.clkr,
+	[GCC_NSS_PORT6_TX_CLK] = &gcc_nss_port6_tx_clk.clkr,
+	[GCC_PORT1_MAC_CLK] = &gcc_port1_mac_clk.clkr,
+	[GCC_PORT2_MAC_CLK] = &gcc_port2_mac_clk.clkr,
+	[GCC_PORT3_MAC_CLK] = &gcc_port3_mac_clk.clkr,
+	[GCC_PORT4_MAC_CLK] = &gcc_port4_mac_clk.clkr,
+	[GCC_PORT5_MAC_CLK] = &gcc_port5_mac_clk.clkr,
+	[GCC_PORT6_MAC_CLK] = &gcc_port6_mac_clk.clkr,
+	[GCC_UNIPHY0_PORT1_RX_CLK] = &gcc_uniphy0_port1_rx_clk.clkr,
+	[GCC_UNIPHY0_PORT1_TX_CLK] = &gcc_uniphy0_port1_tx_clk.clkr,
+	[GCC_UNIPHY0_PORT2_RX_CLK] = &gcc_uniphy0_port2_rx_clk.clkr,
+	[GCC_UNIPHY0_PORT2_TX_CLK] = &gcc_uniphy0_port2_tx_clk.clkr,
+	[GCC_UNIPHY0_PORT3_RX_CLK] = &gcc_uniphy0_port3_rx_clk.clkr,
+	[GCC_UNIPHY0_PORT3_TX_CLK] = &gcc_uniphy0_port3_tx_clk.clkr,
+	[GCC_UNIPHY0_PORT4_RX_CLK] = &gcc_uniphy0_port4_rx_clk.clkr,
+	[GCC_UNIPHY0_PORT4_TX_CLK] = &gcc_uniphy0_port4_tx_clk.clkr,
+	[GCC_UNIPHY0_PORT5_RX_CLK] = &gcc_uniphy0_port5_rx_clk.clkr,
+	[GCC_UNIPHY0_PORT5_TX_CLK] = &gcc_uniphy0_port5_tx_clk.clkr,
+	[GCC_UNIPHY1_PORT5_RX_CLK] = &gcc_uniphy1_port5_rx_clk.clkr,
+	[GCC_UNIPHY1_PORT5_TX_CLK] = &gcc_uniphy1_port5_tx_clk.clkr,
+	[GCC_UNIPHY2_PORT6_RX_CLK] = &gcc_uniphy2_port6_rx_clk.clkr,
+	[GCC_UNIPHY2_PORT6_TX_CLK] = &gcc_uniphy2_port6_tx_clk.clkr,
+	[GCC_CRYPTO_AHB_CLK] = &gcc_crypto_ahb_clk.clkr,
+	[GCC_CRYPTO_AXI_CLK] = &gcc_crypto_axi_clk.clkr,
+	[GCC_CRYPTO_CLK] = &gcc_crypto_clk.clkr,
+	[GCC_GP1_CLK] = &gcc_gp1_clk.clkr,
+	[GCC_GP2_CLK] = &gcc_gp2_clk.clkr,
+	[GCC_GP3_CLK] = &gcc_gp3_clk.clkr,
 };
 
 static const struct qcom_reset_map gcc_ipq8074_resets[] = {
@@ -945,6 +4653,48 @@ static const struct qcom_reset_map gcc_ipq8074_resets[] = {
 	[GCC_APC0_VOLTAGE_DROOP_DETECTOR_BCR] = { 0x78000, 0 },
 	[GCC_APC1_VOLTAGE_DROOP_DETECTOR_BCR] = { 0x79000, 0 },
 	[GCC_SMMU_CATS_BCR] = { 0x7c000, 0 },
+	[GCC_UBI0_AXI_ARES] = { 0x68010, 0 },
+	[GCC_UBI0_AHB_ARES] = { 0x68010, 1 },
+	[GCC_UBI0_NC_AXI_ARES] = { 0x68010, 2 },
+	[GCC_UBI0_DBG_ARES] = { 0x68010, 3 },
+	[GCC_UBI0_CORE_CLAMP_ENABLE] = { 0x68010, 4 },
+	[GCC_UBI0_CLKRST_CLAMP_ENABLE] = { 0x68010, 5 },
+	[GCC_UBI1_AXI_ARES] = { 0x68010, 8 },
+	[GCC_UBI1_AHB_ARES] = { 0x68010, 9 },
+	[GCC_UBI1_NC_AXI_ARES] = { 0x68010, 10 },
+	[GCC_UBI1_DBG_ARES] = { 0x68010, 11 },
+	[GCC_UBI1_CORE_CLAMP_ENABLE] = { 0x68010, 12 },
+	[GCC_UBI1_CLKRST_CLAMP_ENABLE] = { 0x68010, 13 },
+	[GCC_NSS_CFG_ARES] = { 0x68010, 16 },
+	[GCC_NSS_IMEM_ARES] = { 0x68010, 17 },
+	[GCC_NSS_NOC_ARES] = { 0x68010, 18 },
+	[GCC_NSS_CRYPTO_ARES] = { 0x68010, 19 },
+	[GCC_NSS_CSR_ARES] = { 0x68010, 20 },
+	[GCC_NSS_CE_APB_ARES] = { 0x68010, 21 },
+	[GCC_NSS_CE_AXI_ARES] = { 0x68010, 22 },
+	[GCC_NSSNOC_CE_APB_ARES] = { 0x68010, 23 },
+	[GCC_NSSNOC_CE_AXI_ARES] = { 0x68010, 24 },
+	[GCC_NSSNOC_UBI0_AHB_ARES] = { 0x68010, 25 },
+	[GCC_NSSNOC_UBI1_AHB_ARES] = { 0x68010, 26 },
+	[GCC_NSSNOC_SNOC_ARES] = { 0x68010, 27 },
+	[GCC_NSSNOC_CRYPTO_ARES] = { 0x68010, 28 },
+	[GCC_NSSNOC_ATB_ARES] = { 0x68010, 29 },
+	[GCC_NSSNOC_QOSGEN_REF_ARES] = { 0x68010, 30 },
+	[GCC_NSSNOC_TIMEOUT_REF_ARES] = { 0x68010, 31 },
+	[GCC_PCIE0_PIPE_ARES] = { 0x75040, 0 },
+	[GCC_PCIE0_SLEEP_ARES] = { 0x75040, 1 },
+	[GCC_PCIE0_CORE_STICKY_ARES] = { 0x75040, 2 },
+	[GCC_PCIE0_AXI_MASTER_ARES] = { 0x75040, 3 },
+	[GCC_PCIE0_AXI_SLAVE_ARES] = { 0x75040, 4 },
+	[GCC_PCIE0_AHB_ARES] = { 0x75040, 5 },
+	[GCC_PCIE0_AXI_MASTER_STICKY_ARES] = { 0x75040, 6 },
+	[GCC_PCIE1_PIPE_ARES] = { 0x76040, 0 },
+	[GCC_PCIE1_SLEEP_ARES] = { 0x76040, 1 },
+	[GCC_PCIE1_CORE_STICKY_ARES] = { 0x76040, 2 },
+	[GCC_PCIE1_AXI_MASTER_ARES] = { 0x76040, 3 },
+	[GCC_PCIE1_AXI_SLAVE_ARES] = { 0x76040, 4 },
+	[GCC_PCIE1_AHB_ARES] = { 0x76040, 5 },
+	[GCC_PCIE1_AXI_MASTER_STICKY_ARES] = { 0x76040, 6 },
 };
 
 static const struct of_device_id gcc_ipq8074_match_table[] = {
diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c
index 3410ee68d4bc..d6c7f50ba86a 100644
--- a/drivers/clk/qcom/gcc-msm8916.c
+++ b/drivers/clk/qcom/gcc-msm8916.c
@@ -1259,20 +1259,25 @@ static struct clk_branch gcc_ultaudio_ahbfabric_ixfabric_lpm_clk = {
 };
 
 static const struct freq_tbl ftbl_gcc_ultaudio_lpaif_i2s_clk[] = {
+	F(128000, P_XO, 10, 1, 15),
 	F(256000, P_XO, 5, 1, 15),
+	F(384000, P_XO, 5, 1, 10),
 	F(512000, P_XO, 5, 2, 15),
+	F(576000, P_XO, 5, 3, 20),
 	F(705600, P_GPLL1, 16, 1, 80),
 	F(768000, P_XO, 5, 1, 5),
 	F(800000, P_XO, 5, 5, 24),
-	F(1024000, P_GPLL1, 14, 1, 63),
+	F(1024000, P_XO, 5, 4, 15),
 	F(1152000, P_XO, 1, 3, 50),
 	F(1411200, P_GPLL1, 16, 1, 40),
 	F(1536000, P_XO, 1, 2, 25),
 	F(1600000, P_XO, 12, 0, 0),
-	F(2048000, P_GPLL1, 9, 1, 49),
+	F(1728000, P_XO, 5, 9, 20),
+	F(2048000, P_XO, 5, 8, 15),
+	F(2304000, P_XO, 5, 3, 5),
 	F(2400000, P_XO, 8, 0, 0),
 	F(2822400, P_GPLL1, 16, 1, 20),
-	F(3072000, P_GPLL1, 14, 1, 21),
+	F(3072000, P_XO, 5, 4, 5),
 	F(4096000, P_GPLL1, 9, 2, 49),
 	F(4800000, P_XO, 4, 0, 0),
 	F(5644800, P_GPLL1, 16, 1, 10),
@@ -1431,6 +1436,7 @@ static struct clk_branch gcc_ultaudio_stc_xo_clk = {
 
 static const struct freq_tbl ftbl_codec_clk[] = {
 	F(9600000, P_XO, 2, 0, 0),
+	F(12288000, P_XO, 1, 16, 25),
 	F(19200000, P_XO, 1, 0, 0),
 	F(11289600, P_EXT_MCLK, 1, 0, 0),
 	{ }
@@ -1438,6 +1444,7 @@ static const struct freq_tbl ftbl_codec_clk[] = {
 
 static struct clk_rcg2 codec_digcodec_clk_src = {
 	.cmd_rcgr = 0x1c09c,
+	.mnd_width = 8,
 	.hid_width = 5,
 	.parent_map = gcc_xo_gpll1_emclk_sleep_map,
 	.freq_tbl = ftbl_codec_clk,
diff --git a/drivers/clk/qcom/gcc-msm8994.c b/drivers/clk/qcom/gcc-msm8994.c
index 7983288d9141..1e38efc37180 100644
--- a/drivers/clk/qcom/gcc-msm8994.c
+++ b/drivers/clk/qcom/gcc-msm8994.c
@@ -73,6 +73,7 @@ static struct clk_fixed_factor xo = {
 
 static struct clk_alpha_pll gpll0_early = {
 	.offset = 0x00000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.clkr = {
 		.enable_reg = 0x1480,
 		.enable_mask = BIT(0),
@@ -88,6 +89,7 @@ static struct clk_alpha_pll gpll0_early = {
 
 static struct clk_alpha_pll_postdiv gpll0 = {
 	.offset = 0x00000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.clkr.hw.init = &(struct clk_init_data)
 	{
 		.name = "gpll0",
@@ -99,6 +101,7 @@ static struct clk_alpha_pll_postdiv gpll0 = {
 
 static struct clk_alpha_pll gpll4_early = {
 	.offset = 0x1dc0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.clkr = {
 		.enable_reg = 0x1480,
 		.enable_mask = BIT(4),
@@ -114,6 +117,7 @@ static struct clk_alpha_pll gpll4_early = {
 
 static struct clk_alpha_pll_postdiv gpll4 = {
 	.offset = 0x1dc0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.clkr.hw.init = &(struct clk_init_data)
 	{
 		.name = "gpll4",
diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c
index 7ddec886fcd3..5d7451209206 100644
--- a/drivers/clk/qcom/gcc-msm8996.c
+++ b/drivers/clk/qcom/gcc-msm8996.c
@@ -227,6 +227,7 @@ static struct clk_fixed_factor xo = {
 
 static struct clk_alpha_pll gpll0_early = {
 	.offset = 0x00000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.clkr = {
 		.enable_reg = 0x52000,
 		.enable_mask = BIT(0),
@@ -252,6 +253,7 @@ static struct clk_fixed_factor gpll0_early_div = {
 
 static struct clk_alpha_pll_postdiv gpll0 = {
 	.offset = 0x00000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "gpll0",
 		.parent_names = (const char *[]){ "gpll0_early" },
@@ -262,6 +264,7 @@ static struct clk_alpha_pll_postdiv gpll0 = {
 
 static struct clk_alpha_pll gpll4_early = {
 	.offset = 0x77000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.clkr = {
 		.enable_reg = 0x52000,
 		.enable_mask = BIT(4),
@@ -276,6 +279,7 @@ static struct clk_alpha_pll gpll4_early = {
 
 static struct clk_alpha_pll_postdiv gpll4 = {
 	.offset = 0x77000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "gpll4",
 		.parent_names = (const char *[]){ "gpll4_early" },
diff --git a/drivers/clk/qcom/mmcc-msm8996.c b/drivers/clk/qcom/mmcc-msm8996.c
index 352394d8fd8c..66a2fa4ec93c 100644
--- a/drivers/clk/qcom/mmcc-msm8996.c
+++ b/drivers/clk/qcom/mmcc-msm8996.c
@@ -267,6 +267,7 @@ static struct pll_vco mmpll_t_vco[] = {
 
 static struct clk_alpha_pll mmpll0_early = {
 	.offset = 0x0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.vco_table = mmpll_p_vco,
 	.num_vco = ARRAY_SIZE(mmpll_p_vco),
 	.clkr = {
@@ -283,6 +284,7 @@ static struct clk_alpha_pll mmpll0_early = {
 
 static struct clk_alpha_pll_postdiv mmpll0 = {
 	.offset = 0x0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.width = 4,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "mmpll0",
@@ -295,6 +297,7 @@ static struct clk_alpha_pll_postdiv mmpll0 = {
 
 static struct clk_alpha_pll mmpll1_early = {
 	.offset = 0x30,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.vco_table = mmpll_p_vco,
 	.num_vco = ARRAY_SIZE(mmpll_p_vco),
 	.clkr = {
@@ -311,6 +314,7 @@ static struct clk_alpha_pll mmpll1_early = {
 
 static struct clk_alpha_pll_postdiv mmpll1 = {
 	.offset = 0x30,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.width = 4,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "mmpll1",
@@ -323,6 +327,7 @@ static struct clk_alpha_pll_postdiv mmpll1 = {
 
 static struct clk_alpha_pll mmpll2_early = {
 	.offset = 0x4100,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.vco_table = mmpll_gfx_vco,
 	.num_vco = ARRAY_SIZE(mmpll_gfx_vco),
 	.clkr.hw.init = &(struct clk_init_data){
@@ -335,6 +340,7 @@ static struct clk_alpha_pll mmpll2_early = {
 
 static struct clk_alpha_pll_postdiv mmpll2 = {
 	.offset = 0x4100,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.width = 4,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "mmpll2",
@@ -347,6 +353,7 @@ static struct clk_alpha_pll_postdiv mmpll2 = {
 
 static struct clk_alpha_pll mmpll3_early = {
 	.offset = 0x60,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.vco_table = mmpll_p_vco,
 	.num_vco = ARRAY_SIZE(mmpll_p_vco),
 	.clkr.hw.init = &(struct clk_init_data){
@@ -359,6 +366,7 @@ static struct clk_alpha_pll mmpll3_early = {
 
 static struct clk_alpha_pll_postdiv mmpll3 = {
 	.offset = 0x60,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.width = 4,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "mmpll3",
@@ -371,6 +379,7 @@ static struct clk_alpha_pll_postdiv mmpll3 = {
 
 static struct clk_alpha_pll mmpll4_early = {
 	.offset = 0x90,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.vco_table = mmpll_t_vco,
 	.num_vco = ARRAY_SIZE(mmpll_t_vco),
 	.clkr.hw.init = &(struct clk_init_data){
@@ -383,6 +392,7 @@ static struct clk_alpha_pll mmpll4_early = {
 
 static struct clk_alpha_pll_postdiv mmpll4 = {
 	.offset = 0x90,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.width = 2,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "mmpll4",
@@ -395,6 +405,7 @@ static struct clk_alpha_pll_postdiv mmpll4 = {
 
 static struct clk_alpha_pll mmpll5_early = {
 	.offset = 0xc0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.vco_table = mmpll_p_vco,
 	.num_vco = ARRAY_SIZE(mmpll_p_vco),
 	.clkr.hw.init = &(struct clk_init_data){
@@ -407,6 +418,7 @@ static struct clk_alpha_pll mmpll5_early = {
 
 static struct clk_alpha_pll_postdiv mmpll5 = {
 	.offset = 0xc0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.width = 4,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "mmpll5",
@@ -419,6 +431,7 @@ static struct clk_alpha_pll_postdiv mmpll5 = {
 
 static struct clk_alpha_pll mmpll8_early = {
 	.offset = 0x4130,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.vco_table = mmpll_gfx_vco,
 	.num_vco = ARRAY_SIZE(mmpll_gfx_vco),
 	.clkr.hw.init = &(struct clk_init_data){
@@ -431,6 +444,7 @@ static struct clk_alpha_pll mmpll8_early = {
 
 static struct clk_alpha_pll_postdiv mmpll8 = {
 	.offset = 0x4130,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.width = 4,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "mmpll8",
@@ -443,6 +457,7 @@ static struct clk_alpha_pll_postdiv mmpll8 = {
 
 static struct clk_alpha_pll mmpll9_early = {
 	.offset = 0x4200,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.vco_table = mmpll_t_vco,
 	.num_vco = ARRAY_SIZE(mmpll_t_vco),
 	.clkr.hw.init = &(struct clk_init_data){
@@ -455,6 +470,7 @@ static struct clk_alpha_pll mmpll9_early = {
 
 static struct clk_alpha_pll_postdiv mmpll9 = {
 	.offset = 0x4200,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
 	.width = 2,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "mmpll9",
diff --git a/drivers/clk/renesas/clk-mstp.c b/drivers/clk/renesas/clk-mstp.c
index c944cc421e30..858c24d4da8f 100644
--- a/drivers/clk/renesas/clk-mstp.c
+++ b/drivers/clk/renesas/clk-mstp.c
@@ -341,7 +341,7 @@ void __init cpg_mstp_add_clk_domain(struct device_node *np)
 		return;
 
 	pd->name = np->name;
-	pd->flags = GENPD_FLAG_PM_CLK;
+	pd->flags = GENPD_FLAG_PM_CLK | GENPD_FLAG_ACTIVE_WAKEUP;
 	pd->attach_dev = cpg_mstp_attach_dev;
 	pd->detach_dev = cpg_mstp_detach_dev;
 	pm_genpd_init(pd, &pm_domain_always_on_gov, false);
diff --git a/drivers/clk/renesas/r8a7796-cpg-mssr.c b/drivers/clk/renesas/r8a7796-cpg-mssr.c
index b3767472088a..41e29734126b 100644
--- a/drivers/clk/renesas/r8a7796-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a7796-cpg-mssr.c
@@ -115,6 +115,7 @@ static const struct cpg_core_clk r8a7796_core_clks[] __initconst = {
 };
 
 static const struct mssr_mod_clk r8a7796_mod_clks[] __initconst = {
+	DEF_MOD("fdp1-0",		 119,	R8A7796_CLK_S0D1),
 	DEF_MOD("scif5",		 202,	R8A7796_CLK_S3D4),
 	DEF_MOD("scif4",		 203,	R8A7796_CLK_S3D4),
 	DEF_MOD("scif3",		 204,	R8A7796_CLK_S3D4),
diff --git a/drivers/clk/renesas/r8a77970-cpg-mssr.c b/drivers/clk/renesas/r8a77970-cpg-mssr.c
index 72f98527473a..f55842917e8d 100644
--- a/drivers/clk/renesas/r8a77970-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a77970-cpg-mssr.c
@@ -105,6 +105,7 @@ static const struct mssr_mod_clk r8a77970_mod_clks[] __initconst = {
 	DEF_MOD("vspd0",		 623,	R8A77970_CLK_S2D1),
 	DEF_MOD("csi40",		 716,	R8A77970_CLK_CSI0),
 	DEF_MOD("du0",			 724,	R8A77970_CLK_S2D1),
+	DEF_MOD("lvds",			 727,	R8A77970_CLK_S2D1),
 	DEF_MOD("vin3",			 808,	R8A77970_CLK_S2D1),
 	DEF_MOD("vin2",			 809,	R8A77970_CLK_S2D1),
 	DEF_MOD("vin1",			 810,	R8A77970_CLK_S2D1),
diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c
index e3d03ffea4bc..e3cc72c81311 100644
--- a/drivers/clk/renesas/renesas-cpg-mssr.c
+++ b/drivers/clk/renesas/renesas-cpg-mssr.c
@@ -513,7 +513,7 @@ static int __init cpg_mssr_add_clk_domain(struct device *dev,
 
 	genpd = &pd->genpd;
 	genpd->name = np->name;
-	genpd->flags = GENPD_FLAG_PM_CLK;
+	genpd->flags = GENPD_FLAG_PM_CLK | GENPD_FLAG_ACTIVE_WAKEUP;
 	genpd->attach_dev = cpg_mssr_attach_dev;
 	genpd->detach_dev = cpg_mssr_detach_dev;
 	pm_genpd_init(genpd, &pm_domain_always_on_gov, false);
diff --git a/drivers/clk/spear/clk-frac-synth.c b/drivers/clk/spear/clk-frac-synth.c
index 229c96daece6..f5be02205ac6 100644
--- a/drivers/clk/spear/clk-frac-synth.c
+++ b/drivers/clk/spear/clk-frac-synth.c
@@ -131,7 +131,7 @@ struct clk *clk_register_frac(const char *name, const char *parent_name,
 	struct clk *clk;
 
 	if (!name || !parent_name || !reg || !rtbl || !rtbl_cnt) {
-		pr_err("Invalid arguments passed");
+		pr_err("Invalid arguments passed\n");
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/drivers/clk/spear/clk-gpt-synth.c b/drivers/clk/spear/clk-gpt-synth.c
index 28262f422562..6ed406d943ba 100644
--- a/drivers/clk/spear/clk-gpt-synth.c
+++ b/drivers/clk/spear/clk-gpt-synth.c
@@ -120,7 +120,7 @@ struct clk *clk_register_gpt(const char *name, const char *parent_name, unsigned
 	struct clk *clk;
 
 	if (!name || !parent_name || !reg || !rtbl || !rtbl_cnt) {
-		pr_err("Invalid arguments passed");
+		pr_err("Invalid arguments passed\n");
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/drivers/clk/sprd/Kconfig b/drivers/clk/sprd/Kconfig
new file mode 100644
index 000000000000..87892471eb96
--- /dev/null
+++ b/drivers/clk/sprd/Kconfig
@@ -0,0 +1,14 @@
+config SPRD_COMMON_CLK
+	tristate "Clock support for Spreadtrum SoCs"
+	depends on ARCH_SPRD || COMPILE_TEST
+	default ARCH_SPRD
+
+if SPRD_COMMON_CLK
+
+# SoC Drivers
+
+config SPRD_SC9860_CLK
+	tristate "Support for the Spreadtrum SC9860 clocks"
+	depends on (ARM64 && ARCH_SPRD) || COMPILE_TEST
+	default ARM64 && ARCH_SPRD
+endif
diff --git a/drivers/clk/sprd/Makefile b/drivers/clk/sprd/Makefile
new file mode 100644
index 000000000000..b0d81e541ebd
--- /dev/null
+++ b/drivers/clk/sprd/Makefile
@@ -0,0 +1,11 @@
+obj-$(CONFIG_SPRD_COMMON_CLK)	+= clk-sprd.o
+
+clk-sprd-y	+= common.o
+clk-sprd-y	+= gate.o
+clk-sprd-y	+= mux.o
+clk-sprd-y	+= div.o
+clk-sprd-y	+= composite.o
+clk-sprd-y	+= pll.o
+
+## SoC support
+obj-$(CONFIG_SPRD_SC9860_CLK)	+= sc9860-clk.o
diff --git a/drivers/clk/sprd/common.c b/drivers/clk/sprd/common.c
new file mode 100644
index 000000000000..e038b0447206
--- /dev/null
+++ b/drivers/clk/sprd/common.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum clock infrastructure
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+
+#include "common.h"
+
+static const struct regmap_config sprdclk_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0xffff,
+	.fast_io	= true,
+};
+
+static void sprd_clk_set_regmap(const struct sprd_clk_desc *desc,
+			 struct regmap *regmap)
+{
+	int i;
+	struct sprd_clk_common *cclk;
+
+	for (i = 0; i < desc->num_clk_clks; i++) {
+		cclk = desc->clk_clks[i];
+		if (!cclk)
+			continue;
+
+		cclk->regmap = regmap;
+	}
+}
+
+int sprd_clk_regmap_init(struct platform_device *pdev,
+			 const struct sprd_clk_desc *desc)
+{
+	void __iomem *base;
+	struct device_node *node = pdev->dev.of_node;
+	struct regmap *regmap;
+
+	if (of_find_property(node, "sprd,syscon", NULL)) {
+		regmap = syscon_regmap_lookup_by_phandle(node, "sprd,syscon");
+		if (IS_ERR_OR_NULL(regmap)) {
+			pr_err("%s: failed to get syscon regmap\n", __func__);
+			return PTR_ERR(regmap);
+		}
+	} else {
+		base = of_iomap(node, 0);
+		regmap = devm_regmap_init_mmio(&pdev->dev, base,
+					       &sprdclk_regmap_config);
+		if (IS_ERR_OR_NULL(regmap)) {
+			pr_err("failed to init regmap\n");
+			return PTR_ERR(regmap);
+		}
+	}
+
+	sprd_clk_set_regmap(desc, regmap);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sprd_clk_regmap_init);
+
+int sprd_clk_probe(struct device *dev, struct clk_hw_onecell_data *clkhw)
+{
+	int i, ret;
+	struct clk_hw *hw;
+
+	for (i = 0; i < clkhw->num; i++) {
+
+		hw = clkhw->hws[i];
+
+		if (!hw)
+			continue;
+
+		ret = devm_clk_hw_register(dev, hw);
+		if (ret) {
+			dev_err(dev, "Couldn't register clock %d - %s\n",
+				i, hw->init->name);
+			return ret;
+		}
+	}
+
+	ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, clkhw);
+	if (ret)
+		dev_err(dev, "Failed to add clock provider\n");
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sprd_clk_probe);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/sprd/common.h b/drivers/clk/sprd/common.h
new file mode 100644
index 000000000000..abd9ff5ef448
--- /dev/null
+++ b/drivers/clk/sprd/common.h
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum clock infrastructure
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#ifndef _SPRD_CLK_COMMON_H_
+#define _SPRD_CLK_COMMON_H_
+
+#include <linux/clk-provider.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+
+struct device_node;
+
+struct sprd_clk_common {
+	struct regmap	*regmap;
+	u32		reg;
+	struct clk_hw	hw;
+};
+
+struct sprd_clk_desc {
+	struct sprd_clk_common		**clk_clks;
+	unsigned long			num_clk_clks;
+	struct clk_hw_onecell_data      *hw_clks;
+};
+
+static inline struct sprd_clk_common *
+	hw_to_sprd_clk_common(const struct clk_hw *hw)
+{
+	return container_of(hw, struct sprd_clk_common, hw);
+}
+int sprd_clk_regmap_init(struct platform_device *pdev,
+			 const struct sprd_clk_desc *desc);
+int sprd_clk_probe(struct device *dev, struct clk_hw_onecell_data *clkhw);
+
+#endif /* _SPRD_CLK_COMMON_H_ */
diff --git a/drivers/clk/sprd/composite.c b/drivers/clk/sprd/composite.c
new file mode 100644
index 000000000000..ebb644820b1e
--- /dev/null
+++ b/drivers/clk/sprd/composite.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum composite clock driver
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#include <linux/clk-provider.h>
+
+#include "composite.h"
+
+static long sprd_comp_round_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long *parent_rate)
+{
+	struct sprd_comp *cc = hw_to_sprd_comp(hw);
+
+	return sprd_div_helper_round_rate(&cc->common, &cc->div,
+					 rate, parent_rate);
+}
+
+static unsigned long sprd_comp_recalc_rate(struct clk_hw *hw,
+					  unsigned long parent_rate)
+{
+	struct sprd_comp *cc = hw_to_sprd_comp(hw);
+
+	return sprd_div_helper_recalc_rate(&cc->common, &cc->div, parent_rate);
+}
+
+static int sprd_comp_set_rate(struct clk_hw *hw, unsigned long rate,
+			     unsigned long parent_rate)
+{
+	struct sprd_comp *cc = hw_to_sprd_comp(hw);
+
+	return sprd_div_helper_set_rate(&cc->common, &cc->div,
+				       rate, parent_rate);
+}
+
+static u8 sprd_comp_get_parent(struct clk_hw *hw)
+{
+	struct sprd_comp *cc = hw_to_sprd_comp(hw);
+
+	return sprd_mux_helper_get_parent(&cc->common, &cc->mux);
+}
+
+static int sprd_comp_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct sprd_comp *cc = hw_to_sprd_comp(hw);
+
+	return sprd_mux_helper_set_parent(&cc->common, &cc->mux, index);
+}
+
+const struct clk_ops sprd_comp_ops = {
+	.get_parent	= sprd_comp_get_parent,
+	.set_parent	= sprd_comp_set_parent,
+
+	.round_rate	= sprd_comp_round_rate,
+	.recalc_rate	= sprd_comp_recalc_rate,
+	.set_rate	= sprd_comp_set_rate,
+};
+EXPORT_SYMBOL_GPL(sprd_comp_ops);
diff --git a/drivers/clk/sprd/composite.h b/drivers/clk/sprd/composite.h
new file mode 100644
index 000000000000..0984e9e252dc
--- /dev/null
+++ b/drivers/clk/sprd/composite.h
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum composite clock driver
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#ifndef _SPRD_COMPOSITE_H_
+#define _SPRD_COMPOSITE_H_
+
+#include "common.h"
+#include "mux.h"
+#include "div.h"
+
+struct sprd_comp {
+	struct sprd_mux_ssel	mux;
+	struct sprd_div_internal	div;
+	struct sprd_clk_common	common;
+};
+
+#define SPRD_COMP_CLK_TABLE(_struct, _name, _parent, _reg, _table,	\
+			_mshift, _mwidth, _dshift, _dwidth, _flags)	\
+	struct sprd_comp _struct = {					\
+		.mux	= _SPRD_MUX_CLK(_mshift, _mwidth, _table),	\
+		.div	= _SPRD_DIV_CLK(_dshift, _dwidth),		\
+		.common = {						\
+			.regmap		= NULL,				\
+			.reg		= _reg,				\
+			.hw.init = CLK_HW_INIT_PARENTS(_name,		\
+						       _parent,		\
+						       &sprd_comp_ops,	\
+						       _flags),		\
+			 }						\
+	}
+
+#define SPRD_COMP_CLK(_struct, _name, _parent, _reg, _mshift,	\
+			_mwidth, _dshift, _dwidth, _flags)	\
+	SPRD_COMP_CLK_TABLE(_struct, _name, _parent, _reg,	\
+			    NULL, _mshift, _mwidth,		\
+			    _dshift, _dwidth, _flags)
+
+static inline struct sprd_comp *hw_to_sprd_comp(const struct clk_hw *hw)
+{
+	struct sprd_clk_common *common = hw_to_sprd_clk_common(hw);
+
+	return container_of(common, struct sprd_comp, common);
+}
+
+extern const struct clk_ops sprd_comp_ops;
+
+#endif /* _SPRD_COMPOSITE_H_ */
diff --git a/drivers/clk/sprd/div.c b/drivers/clk/sprd/div.c
new file mode 100644
index 000000000000..7621a1d1ab9c
--- /dev/null
+++ b/drivers/clk/sprd/div.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum divider clock driver
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#include <linux/clk-provider.h>
+
+#include "div.h"
+
+long sprd_div_helper_round_rate(struct sprd_clk_common *common,
+				const struct sprd_div_internal *div,
+				unsigned long rate,
+				unsigned long *parent_rate)
+{
+	return divider_round_rate(&common->hw, rate, parent_rate,
+				  NULL, div->width, 0);
+}
+EXPORT_SYMBOL_GPL(sprd_div_helper_round_rate);
+
+static long sprd_div_round_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long *parent_rate)
+{
+	struct sprd_div *cd = hw_to_sprd_div(hw);
+
+	return sprd_div_helper_round_rate(&cd->common, &cd->div,
+					  rate, parent_rate);
+}
+
+unsigned long sprd_div_helper_recalc_rate(struct sprd_clk_common *common,
+					  const struct sprd_div_internal *div,
+					  unsigned long parent_rate)
+{
+	unsigned long val;
+	unsigned int reg;
+
+	regmap_read(common->regmap, common->reg, &reg);
+	val = reg >> div->shift;
+	val &= (1 << div->width) - 1;
+
+	return divider_recalc_rate(&common->hw, parent_rate, val, NULL, 0,
+				   div->width);
+}
+EXPORT_SYMBOL_GPL(sprd_div_helper_recalc_rate);
+
+static unsigned long sprd_div_recalc_rate(struct clk_hw *hw,
+					  unsigned long parent_rate)
+{
+	struct sprd_div *cd = hw_to_sprd_div(hw);
+
+	return sprd_div_helper_recalc_rate(&cd->common, &cd->div, parent_rate);
+}
+
+int sprd_div_helper_set_rate(const struct sprd_clk_common *common,
+			     const struct sprd_div_internal *div,
+			     unsigned long rate,
+			     unsigned long parent_rate)
+{
+	unsigned long val;
+	unsigned int reg;
+
+	val = divider_get_val(rate, parent_rate, NULL,
+			      div->width, 0);
+
+	regmap_read(common->regmap, common->reg, &reg);
+	reg &= ~GENMASK(div->width + div->shift - 1, div->shift);
+
+	regmap_write(common->regmap, common->reg,
+			  reg | (val << div->shift));
+
+	return 0;
+
+}
+EXPORT_SYMBOL_GPL(sprd_div_helper_set_rate);
+
+static int sprd_div_set_rate(struct clk_hw *hw, unsigned long rate,
+			     unsigned long parent_rate)
+{
+	struct sprd_div *cd = hw_to_sprd_div(hw);
+
+	return sprd_div_helper_set_rate(&cd->common, &cd->div,
+					rate, parent_rate);
+}
+
+const struct clk_ops sprd_div_ops = {
+	.recalc_rate = sprd_div_recalc_rate,
+	.round_rate = sprd_div_round_rate,
+	.set_rate = sprd_div_set_rate,
+};
+EXPORT_SYMBOL_GPL(sprd_div_ops);
diff --git a/drivers/clk/sprd/div.h b/drivers/clk/sprd/div.h
new file mode 100644
index 000000000000..b3033d24d431
--- /dev/null
+++ b/drivers/clk/sprd/div.h
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum divider clock driver
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#ifndef _SPRD_DIV_H_
+#define _SPRD_DIV_H_
+
+#include "common.h"
+
+/**
+ * struct sprd_div_internal - Internal divider description
+ * @shift: Bit offset of the divider in its register
+ * @width: Width of the divider field in its register
+ *
+ * That structure represents a single divider, and is meant to be
+ * embedded in other structures representing the various clock
+ * classes.
+ */
+struct sprd_div_internal {
+	u8	shift;
+	u8	width;
+};
+
+#define _SPRD_DIV_CLK(_shift, _width)	\
+	{				\
+		.shift	= _shift,	\
+		.width	= _width,	\
+	}
+
+struct sprd_div {
+	struct sprd_div_internal	div;
+	struct sprd_clk_common	common;
+};
+
+#define SPRD_DIV_CLK(_struct, _name, _parent, _reg,			\
+			_shift, _width, _flags)				\
+	struct sprd_div _struct = {					\
+		.div	= _SPRD_DIV_CLK(_shift, _width),		\
+		.common	= {						\
+			.regmap		= NULL,				\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      &sprd_div_ops,	\
+						      _flags),		\
+		}							\
+	}
+
+static inline struct sprd_div *hw_to_sprd_div(const struct clk_hw *hw)
+{
+	struct sprd_clk_common *common = hw_to_sprd_clk_common(hw);
+
+	return container_of(common, struct sprd_div, common);
+}
+
+long sprd_div_helper_round_rate(struct sprd_clk_common *common,
+				const struct sprd_div_internal *div,
+				unsigned long rate,
+				unsigned long *parent_rate);
+
+unsigned long sprd_div_helper_recalc_rate(struct sprd_clk_common *common,
+					  const struct sprd_div_internal *div,
+					  unsigned long parent_rate);
+
+int sprd_div_helper_set_rate(const struct sprd_clk_common *common,
+			     const struct sprd_div_internal *div,
+			     unsigned long rate,
+			     unsigned long parent_rate);
+
+extern const struct clk_ops sprd_div_ops;
+
+#endif /* _SPRD_DIV_H_ */
diff --git a/drivers/clk/sprd/gate.c b/drivers/clk/sprd/gate.c
new file mode 100644
index 000000000000..f59d1936b412
--- /dev/null
+++ b/drivers/clk/sprd/gate.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum gate clock driver
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#include <linux/clk-provider.h>
+#include <linux/regmap.h>
+
+#include "gate.h"
+
+static void clk_gate_toggle(const struct sprd_gate *sg, bool en)
+{
+	const struct sprd_clk_common *common = &sg->common;
+	unsigned int reg;
+	bool set = sg->flags & CLK_GATE_SET_TO_DISABLE ? true : false;
+
+	set ^= en;
+
+	regmap_read(common->regmap, common->reg, &reg);
+
+	if (set)
+		reg |= sg->enable_mask;
+	else
+		reg &= ~sg->enable_mask;
+
+	regmap_write(common->regmap, common->reg, reg);
+}
+
+static void clk_sc_gate_toggle(const struct sprd_gate *sg, bool en)
+{
+	const struct sprd_clk_common *common = &sg->common;
+	bool set = sg->flags & CLK_GATE_SET_TO_DISABLE ? 1 : 0;
+	unsigned int offset;
+
+	set ^= en;
+
+	/*
+	 * Each set/clear gate clock has three registers:
+	 * common->reg			- base register
+	 * common->reg + offset		- set register
+	 * common->reg + 2 * offset	- clear register
+	 */
+	offset = set ? sg->sc_offset : sg->sc_offset * 2;
+
+	regmap_write(common->regmap, common->reg + offset,
+			  sg->enable_mask);
+}
+
+static void sprd_gate_disable(struct clk_hw *hw)
+{
+	struct sprd_gate *sg = hw_to_sprd_gate(hw);
+
+	clk_gate_toggle(sg, false);
+}
+
+static int sprd_gate_enable(struct clk_hw *hw)
+{
+	struct sprd_gate *sg = hw_to_sprd_gate(hw);
+
+	clk_gate_toggle(sg, true);
+
+	return 0;
+}
+
+static void sprd_sc_gate_disable(struct clk_hw *hw)
+{
+	struct sprd_gate *sg = hw_to_sprd_gate(hw);
+
+	clk_sc_gate_toggle(sg, false);
+}
+
+static int sprd_sc_gate_enable(struct clk_hw *hw)
+{
+	struct sprd_gate *sg = hw_to_sprd_gate(hw);
+
+	clk_sc_gate_toggle(sg, true);
+
+	return 0;
+}
+static int sprd_gate_is_enabled(struct clk_hw *hw)
+{
+	struct sprd_gate *sg = hw_to_sprd_gate(hw);
+	struct sprd_clk_common *common = &sg->common;
+	unsigned int reg;
+
+	regmap_read(common->regmap, common->reg, &reg);
+
+	if (sg->flags & CLK_GATE_SET_TO_DISABLE)
+		reg ^= sg->enable_mask;
+
+	reg &= sg->enable_mask;
+
+	return reg ? 1 : 0;
+}
+
+const struct clk_ops sprd_gate_ops = {
+	.disable	= sprd_gate_disable,
+	.enable		= sprd_gate_enable,
+	.is_enabled	= sprd_gate_is_enabled,
+};
+EXPORT_SYMBOL_GPL(sprd_gate_ops);
+
+const struct clk_ops sprd_sc_gate_ops = {
+	.disable	= sprd_sc_gate_disable,
+	.enable		= sprd_sc_gate_enable,
+	.is_enabled	= sprd_gate_is_enabled,
+};
+EXPORT_SYMBOL_GPL(sprd_sc_gate_ops);
+
diff --git a/drivers/clk/sprd/gate.h b/drivers/clk/sprd/gate.h
new file mode 100644
index 000000000000..2e582c68a08b
--- /dev/null
+++ b/drivers/clk/sprd/gate.h
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum gate clock driver
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#ifndef _SPRD_GATE_H_
+#define _SPRD_GATE_H_
+
+#include "common.h"
+
+struct sprd_gate {
+	u32			enable_mask;
+	u16			flags;
+	u16			sc_offset;
+
+	struct sprd_clk_common	common;
+};
+
+#define SPRD_SC_GATE_CLK_OPS(_struct, _name, _parent, _reg, _sc_offset,	\
+			     _enable_mask, _flags, _gate_flags, _ops)	\
+	struct sprd_gate _struct = {					\
+		.enable_mask	= _enable_mask,				\
+		.sc_offset	= _sc_offset,				\
+		.flags		= _gate_flags,				\
+		.common	= {						\
+			.regmap		= NULL,				\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      _ops,		\
+						      _flags),		\
+		}							\
+	}
+
+#define SPRD_GATE_CLK(_struct, _name, _parent, _reg,			\
+		      _enable_mask, _flags, _gate_flags)		\
+	SPRD_SC_GATE_CLK_OPS(_struct, _name, _parent, _reg, 0,		\
+			     _enable_mask, _flags, _gate_flags,		\
+			     &sprd_gate_ops)
+
+#define SPRD_SC_GATE_CLK(_struct, _name, _parent, _reg, _sc_offset,	\
+			 _enable_mask, _flags, _gate_flags)		\
+	SPRD_SC_GATE_CLK_OPS(_struct, _name, _parent, _reg, _sc_offset,	\
+			     _enable_mask, _flags, _gate_flags,		\
+			     &sprd_sc_gate_ops)
+
+static inline struct sprd_gate *hw_to_sprd_gate(const struct clk_hw *hw)
+{
+	struct sprd_clk_common *common = hw_to_sprd_clk_common(hw);
+
+	return container_of(common, struct sprd_gate, common);
+}
+
+extern const struct clk_ops sprd_gate_ops;
+extern const struct clk_ops sprd_sc_gate_ops;
+
+#endif /* _SPRD_GATE_H_ */
diff --git a/drivers/clk/sprd/mux.c b/drivers/clk/sprd/mux.c
new file mode 100644
index 000000000000..624041b60358
--- /dev/null
+++ b/drivers/clk/sprd/mux.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum multiplexer clock driver
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/regmap.h>
+
+#include "mux.h"
+
+u8 sprd_mux_helper_get_parent(const struct sprd_clk_common *common,
+			      const struct sprd_mux_ssel *mux)
+{
+	unsigned int reg;
+	u8 parent;
+	int num_parents;
+	int i;
+
+	regmap_read(common->regmap, common->reg, &reg);
+	parent = reg >> mux->shift;
+	parent &= (1 << mux->width) - 1;
+
+	if (!mux->table)
+		return parent;
+
+	num_parents = clk_hw_get_num_parents(&common->hw);
+
+	for (i = 0; i < num_parents - 1; i++)
+		if (parent >= mux->table[i] && parent < mux->table[i + 1])
+			return i;
+
+	return num_parents - 1;
+}
+EXPORT_SYMBOL_GPL(sprd_mux_helper_get_parent);
+
+static u8 sprd_mux_get_parent(struct clk_hw *hw)
+{
+	struct sprd_mux *cm = hw_to_sprd_mux(hw);
+
+	return sprd_mux_helper_get_parent(&cm->common, &cm->mux);
+}
+
+int sprd_mux_helper_set_parent(const struct sprd_clk_common *common,
+			       const struct sprd_mux_ssel *mux,
+			       u8 index)
+{
+	unsigned int reg;
+
+	if (mux->table)
+		index = mux->table[index];
+
+	regmap_read(common->regmap, common->reg, &reg);
+	reg &= ~GENMASK(mux->width + mux->shift - 1, mux->shift);
+	regmap_write(common->regmap, common->reg,
+			  reg | (index << mux->shift));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sprd_mux_helper_set_parent);
+
+static int sprd_mux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct sprd_mux *cm = hw_to_sprd_mux(hw);
+
+	return sprd_mux_helper_set_parent(&cm->common, &cm->mux, index);
+}
+
+const struct clk_ops sprd_mux_ops = {
+	.get_parent = sprd_mux_get_parent,
+	.set_parent = sprd_mux_set_parent,
+	.determine_rate = __clk_mux_determine_rate,
+};
+EXPORT_SYMBOL_GPL(sprd_mux_ops);
diff --git a/drivers/clk/sprd/mux.h b/drivers/clk/sprd/mux.h
new file mode 100644
index 000000000000..548cfa0f145c
--- /dev/null
+++ b/drivers/clk/sprd/mux.h
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum multiplexer clock driver
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#ifndef _SPRD_MUX_H_
+#define _SPRD_MUX_H_
+
+#include "common.h"
+
+/**
+ * struct sprd_mux_ssel - Mux clock's source select bits in its register
+ * @shift: Bit offset of the divider in its register
+ * @width: Width of the divider field in its register
+ * @table: For some mux clocks, not all sources are used on some special
+ *	   chips, this matches the value of mux clock's register and the
+ *	   sources which are used for this mux clock
+ */
+struct sprd_mux_ssel {
+	u8		shift;
+	u8		width;
+	const u8	*table;
+};
+
+struct sprd_mux {
+	struct sprd_mux_ssel mux;
+	struct sprd_clk_common	common;
+};
+
+#define _SPRD_MUX_CLK(_shift, _width, _table)		\
+	{						\
+		.shift	= _shift,			\
+		.width	= _width,			\
+		.table	= _table,			\
+	}
+
+#define SPRD_MUX_CLK_TABLE(_struct, _name, _parents, _table,		\
+				     _reg, _shift, _width,		\
+				     _flags)				\
+	struct sprd_mux _struct = {					\
+		.mux	= _SPRD_MUX_CLK(_shift, _width, _table),	\
+		.common	= {						\
+			.regmap		= NULL,				\
+			.reg		= _reg,				\
+			.hw.init = CLK_HW_INIT_PARENTS(_name,		\
+						       _parents,	\
+						       &sprd_mux_ops,	\
+						       _flags),		\
+		}							\
+	}
+
+#define SPRD_MUX_CLK(_struct, _name, _parents, _reg,		\
+		     _shift, _width, _flags)			\
+	SPRD_MUX_CLK_TABLE(_struct, _name, _parents, NULL,	\
+			   _reg, _shift, _width, _flags)
+
+static inline struct sprd_mux *hw_to_sprd_mux(const struct clk_hw *hw)
+{
+	struct sprd_clk_common *common = hw_to_sprd_clk_common(hw);
+
+	return container_of(common, struct sprd_mux, common);
+}
+
+extern const struct clk_ops sprd_mux_ops;
+
+u8 sprd_mux_helper_get_parent(const struct sprd_clk_common *common,
+			      const struct sprd_mux_ssel *mux);
+int sprd_mux_helper_set_parent(const struct sprd_clk_common *common,
+			       const struct sprd_mux_ssel *mux,
+			       u8 index);
+
+#endif /* _SPRD_MUX_H_ */
diff --git a/drivers/clk/sprd/pll.c b/drivers/clk/sprd/pll.c
new file mode 100644
index 000000000000..36b4402bf09e
--- /dev/null
+++ b/drivers/clk/sprd/pll.c
@@ -0,0 +1,266 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum pll clock driver
+//
+// Copyright (C) 2015~2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include "pll.h"
+
+#define CLK_PLL_1M	1000000
+#define CLK_PLL_10M	(CLK_PLL_1M * 10)
+
+#define pindex(pll, member)		\
+	(pll->factors[member].shift / (8 * sizeof(pll->regs_num)))
+
+#define pshift(pll, member)		\
+	(pll->factors[member].shift % (8 * sizeof(pll->regs_num)))
+
+#define pwidth(pll, member)		\
+	pll->factors[member].width
+
+#define pmask(pll, member)					\
+	((pwidth(pll, member)) ?				\
+	GENMASK(pwidth(pll, member) + pshift(pll, member) - 1,	\
+	pshift(pll, member)) : 0)
+
+#define pinternal(pll, cfg, member)	\
+	(cfg[pindex(pll, member)] & pmask(pll, member))
+
+#define pinternal_val(pll, cfg, member)	\
+	(pinternal(pll, cfg, member) >> pshift(pll, member))
+
+static inline unsigned int
+sprd_pll_read(const struct sprd_pll *pll, u8 index)
+{
+	const struct sprd_clk_common *common = &pll->common;
+	unsigned int val = 0;
+
+	if (WARN_ON(index >= pll->regs_num))
+		return 0;
+
+	regmap_read(common->regmap, common->reg + index * 4, &val);
+
+	return val;
+}
+
+static inline void
+sprd_pll_write(const struct sprd_pll *pll, u8 index,
+				  u32 msk, u32 val)
+{
+	const struct sprd_clk_common *common = &pll->common;
+	unsigned int offset, reg;
+	int ret = 0;
+
+	if (WARN_ON(index >= pll->regs_num))
+		return;
+
+	offset = common->reg + index * 4;
+	ret = regmap_read(common->regmap, offset, &reg);
+	if (!ret)
+		regmap_write(common->regmap, offset, (reg & ~msk) | val);
+}
+
+static unsigned long pll_get_refin(const struct sprd_pll *pll)
+{
+	u32 shift, mask, index, refin_id = 3;
+	const unsigned long refin[4] = { 2, 4, 13, 26 };
+
+	if (pwidth(pll, PLL_REFIN)) {
+		index = pindex(pll, PLL_REFIN);
+		shift = pshift(pll, PLL_REFIN);
+		mask = pmask(pll, PLL_REFIN);
+		refin_id = (sprd_pll_read(pll, index) & mask) >> shift;
+		if (refin_id > 3)
+			refin_id = 3;
+	}
+
+	return refin[refin_id];
+}
+
+static u32 pll_get_ibias(u64 rate, const u64 *table)
+{
+	u32 i, num = table[0];
+
+	for (i = 1; i < num + 1; i++)
+		if (rate <= table[i])
+			break;
+
+	return (i == num + 1) ? num : i;
+}
+
+static unsigned long _sprd_pll_recalc_rate(const struct sprd_pll *pll,
+					   unsigned long parent_rate)
+{
+	u32 *cfg;
+	u32 i, mask, regs_num = pll->regs_num;
+	unsigned long rate, nint, kint = 0;
+	u64 refin;
+	u16 k1, k2;
+
+	cfg = kcalloc(regs_num, sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return -ENOMEM;
+
+	for (i = 0; i < regs_num; i++)
+		cfg[i] = sprd_pll_read(pll, i);
+
+	refin = pll_get_refin(pll);
+
+	if (pinternal(pll, cfg, PLL_PREDIV))
+		refin = refin * 2;
+
+	if (pwidth(pll, PLL_POSTDIV) &&
+	    ((pll->fflag == 1 && pinternal(pll, cfg, PLL_POSTDIV)) ||
+	     (!pll->fflag && !pinternal(pll, cfg, PLL_POSTDIV))))
+		refin = refin / 2;
+
+	if (!pinternal(pll, cfg, PLL_DIV_S)) {
+		rate = refin * pinternal_val(pll, cfg, PLL_N) * CLK_PLL_10M;
+	} else {
+		nint = pinternal_val(pll, cfg, PLL_NINT);
+		if (pinternal(pll, cfg, PLL_SDM_EN))
+			kint = pinternal_val(pll, cfg, PLL_KINT);
+
+		mask = pmask(pll, PLL_KINT);
+
+		k1 = pll->k1;
+		k2 = pll->k2;
+		rate = DIV_ROUND_CLOSEST_ULL(refin * kint * k1,
+					 ((mask >> __ffs(mask)) + 1)) *
+					 k2 + refin * nint * CLK_PLL_1M;
+	}
+
+	return rate;
+}
+
+#define SPRD_PLL_WRITE_CHECK(pll, i, mask, val)		\
+	(((sprd_pll_read(pll, i) & mask) == val) ? 0 : (-EFAULT))
+
+static int _sprd_pll_set_rate(const struct sprd_pll *pll,
+			      unsigned long rate,
+			      unsigned long parent_rate)
+{
+	struct reg_cfg *cfg;
+	int ret = 0;
+	u32 mask, shift, width, ibias_val, index;
+	u32 regs_num = pll->regs_num, i = 0;
+	unsigned long kint, nint;
+	u64 tmp, refin, fvco = rate;
+
+	cfg = kcalloc(regs_num, sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return -ENOMEM;
+
+	refin = pll_get_refin(pll);
+
+	mask = pmask(pll, PLL_PREDIV);
+	index = pindex(pll, PLL_PREDIV);
+	width = pwidth(pll, PLL_PREDIV);
+	if (width && (sprd_pll_read(pll, index) & mask))
+		refin = refin * 2;
+
+	mask = pmask(pll, PLL_POSTDIV);
+	index = pindex(pll, PLL_POSTDIV);
+	width = pwidth(pll, PLL_POSTDIV);
+	cfg[index].msk = mask;
+	if (width && ((pll->fflag == 1 && fvco <= pll->fvco) ||
+		      (pll->fflag == 0 && fvco > pll->fvco)))
+		cfg[index].val |= mask;
+
+	if (width && fvco <= pll->fvco)
+		fvco = fvco * 2;
+
+	mask = pmask(pll, PLL_DIV_S);
+	index = pindex(pll, PLL_DIV_S);
+	cfg[index].val |= mask;
+	cfg[index].msk |= mask;
+
+	mask = pmask(pll, PLL_SDM_EN);
+	index = pindex(pll, PLL_SDM_EN);
+	cfg[index].val |= mask;
+	cfg[index].msk |= mask;
+
+	nint = do_div(fvco, refin * CLK_PLL_1M);
+	mask = pmask(pll, PLL_NINT);
+	index = pindex(pll, PLL_NINT);
+	shift = pshift(pll, PLL_NINT);
+	cfg[index].val |= (nint << shift) & mask;
+	cfg[index].msk |= mask;
+
+	mask = pmask(pll, PLL_KINT);
+	index = pindex(pll, PLL_KINT);
+	width = pwidth(pll, PLL_KINT);
+	shift = pshift(pll, PLL_KINT);
+	tmp = fvco - refin * nint * CLK_PLL_1M;
+	tmp = do_div(tmp, 10000) * ((mask >> shift) + 1);
+	kint = DIV_ROUND_CLOSEST_ULL(tmp, refin * 100);
+	cfg[index].val |= (kint << shift) & mask;
+	cfg[index].msk |= mask;
+
+	ibias_val = pll_get_ibias(fvco, pll->itable);
+
+	mask = pmask(pll, PLL_IBIAS);
+	index = pindex(pll, PLL_IBIAS);
+	shift = pshift(pll, PLL_IBIAS);
+	cfg[index].val |= ibias_val << shift & mask;
+	cfg[index].msk |= mask;
+
+	for (i = 0; i < regs_num; i++) {
+		if (cfg[i].msk) {
+			sprd_pll_write(pll, i, cfg[i].msk, cfg[i].val);
+			ret |= SPRD_PLL_WRITE_CHECK(pll, i, cfg[i].msk,
+						   cfg[i].val);
+		}
+	}
+
+	if (!ret)
+		udelay(pll->udelay);
+
+	return ret;
+}
+
+static unsigned long sprd_pll_recalc_rate(struct clk_hw *hw,
+					  unsigned long parent_rate)
+{
+	struct sprd_pll *pll = hw_to_sprd_pll(hw);
+
+	return _sprd_pll_recalc_rate(pll, parent_rate);
+}
+
+static int sprd_pll_set_rate(struct clk_hw *hw,
+			     unsigned long rate,
+			     unsigned long parent_rate)
+{
+	struct sprd_pll *pll = hw_to_sprd_pll(hw);
+
+	return _sprd_pll_set_rate(pll, rate, parent_rate);
+}
+
+static int sprd_pll_clk_prepare(struct clk_hw *hw)
+{
+	struct sprd_pll *pll = hw_to_sprd_pll(hw);
+
+	udelay(pll->udelay);
+
+	return 0;
+}
+
+static long sprd_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long *prate)
+{
+	return rate;
+}
+
+const struct clk_ops sprd_pll_ops = {
+	.prepare = sprd_pll_clk_prepare,
+	.recalc_rate = sprd_pll_recalc_rate,
+	.round_rate = sprd_pll_round_rate,
+	.set_rate = sprd_pll_set_rate,
+};
+EXPORT_SYMBOL_GPL(sprd_pll_ops);
diff --git a/drivers/clk/sprd/pll.h b/drivers/clk/sprd/pll.h
new file mode 100644
index 000000000000..514175621099
--- /dev/null
+++ b/drivers/clk/sprd/pll.h
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum pll clock driver
+//
+// Copyright (C) 2015~2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#ifndef _SPRD_PLL_H_
+#define _SPRD_PLL_H_
+
+#include "common.h"
+
+struct reg_cfg {
+	u32 val;
+	u32 msk;
+};
+
+struct clk_bit_field {
+	u8 shift;
+	u8 width;
+};
+
+enum {
+	PLL_LOCK_DONE,
+	PLL_DIV_S,
+	PLL_MOD_EN,
+	PLL_SDM_EN,
+	PLL_REFIN,
+	PLL_IBIAS,
+	PLL_N,
+	PLL_NINT,
+	PLL_KINT,
+	PLL_PREDIV,
+	PLL_POSTDIV,
+
+	PLL_FACT_MAX
+};
+
+/*
+ * struct sprd_pll - definition of adjustable pll clock
+ *
+ * @reg:	registers used to set the configuration of pll clock,
+ *		reg[0] shows how many registers this pll clock uses.
+ * @itable:	pll ibias table, itable[0] means how many items this
+ *		table includes
+ * @udelay	delay time after setting rate
+ * @factors	used to calculate the pll clock rate
+ * @fvco:	fvco threshold rate
+ * @fflag:	fvco flag
+ */
+struct sprd_pll {
+	u32 regs_num;
+	const u64 *itable;
+	const struct clk_bit_field *factors;
+	u16 udelay;
+	u16 k1;
+	u16 k2;
+	u16 fflag;
+	u64 fvco;
+
+	struct sprd_clk_common	common;
+};
+
+#define SPRD_PLL_WITH_ITABLE_K_FVCO(_struct, _name, _parent, _reg,	\
+				    _regs_num, _itable, _factors,	\
+				    _udelay, _k1, _k2, _fflag, _fvco)	\
+	struct sprd_pll _struct = {					\
+		.regs_num	= _regs_num,				\
+		.itable		= _itable,				\
+		.factors	= _factors,				\
+		.udelay		= _udelay,				\
+		.k1		= _k1,					\
+		.k2		= _k2,					\
+		.fflag		= _fflag,				\
+		.fvco		= _fvco,				\
+		.common		= {					\
+			.regmap		= NULL,				\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      &sprd_pll_ops,	\
+						      0),		\
+		},							\
+	}
+
+#define SPRD_PLL_WITH_ITABLE_K(_struct, _name, _parent, _reg,		\
+			       _regs_num, _itable, _factors,		\
+			       _udelay, _k1, _k2)			\
+	SPRD_PLL_WITH_ITABLE_K_FVCO(_struct, _name, _parent, _reg,	\
+				    _regs_num, _itable, _factors,	\
+				    _udelay, _k1, _k2, 0, 0)
+
+#define SPRD_PLL_WITH_ITABLE_1K(_struct, _name, _parent, _reg,		\
+				_regs_num, _itable, _factors, _udelay)	\
+	SPRD_PLL_WITH_ITABLE_K_FVCO(_struct, _name, _parent, _reg,	\
+				    _regs_num, _itable, _factors,	\
+				    _udelay, 1000, 1000, 0, 0)
+
+static inline struct sprd_pll *hw_to_sprd_pll(struct clk_hw *hw)
+{
+	struct sprd_clk_common *common = hw_to_sprd_clk_common(hw);
+
+	return container_of(common, struct sprd_pll, common);
+}
+
+extern const struct clk_ops sprd_pll_ops;
+
+#endif /* _SPRD_PLL_H_ */
diff --git a/drivers/clk/sprd/sc9860-clk.c b/drivers/clk/sprd/sc9860-clk.c
new file mode 100644
index 000000000000..ed5c027df0f4
--- /dev/null
+++ b/drivers/clk/sprd/sc9860-clk.c
@@ -0,0 +1,1974 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreatrum SC9860 clock driver
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include <dt-bindings/clock/sprd,sc9860-clk.h>
+
+#include "common.h"
+#include "composite.h"
+#include "div.h"
+#include "gate.h"
+#include "mux.h"
+#include "pll.h"
+
+static CLK_FIXED_FACTOR(fac_4m,		"fac-4m",	"ext-26m",
+			6, 1, 0);
+static CLK_FIXED_FACTOR(fac_2m,		"fac-2m",	"ext-26m",
+			13, 1, 0);
+static CLK_FIXED_FACTOR(fac_1m,		"fac-1m",	"ext-26m",
+			26, 1, 0);
+static CLK_FIXED_FACTOR(fac_250k,	"fac-250k",	"ext-26m",
+			104, 1, 0);
+static CLK_FIXED_FACTOR(fac_rpll0_26m,	"rpll0-26m",	"ext-26m",
+			1, 1, 0);
+static CLK_FIXED_FACTOR(fac_rpll1_26m,	"rpll1-26m",	"ext-26m",
+			1, 1, 0);
+static CLK_FIXED_FACTOR(fac_rco_25m,	"rco-25m",	"ext-rc0-100m",
+			4, 1, 0);
+static CLK_FIXED_FACTOR(fac_rco_4m,	"rco-4m",	"ext-rc0-100m",
+			25, 1, 0);
+static CLK_FIXED_FACTOR(fac_rco_2m,	"rco-2m",	"ext-rc0-100m",
+			50, 1, 0);
+static CLK_FIXED_FACTOR(fac_3k2,	"fac-3k2",	"ext-32k",
+			10, 1, 0);
+static CLK_FIXED_FACTOR(fac_1k,		"fac-1k",	"ext-32k",
+			32, 1, 0);
+
+static SPRD_SC_GATE_CLK(mpll0_gate,	"mpll0-gate",	"ext-26m", 0xb0,
+		     0x1000, BIT(2), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(mpll1_gate,	"mpll1-gate",	"ext-26m", 0xb0,
+		     0x1000, BIT(18), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(dpll0_gate,	"dpll0-gate",	"ext-26m", 0xb4,
+		     0x1000, BIT(2), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(dpll1_gate,	"dpll1-gate",	"ext-26m", 0xb4,
+		     0x1000, BIT(18), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ltepll0_gate,	"ltepll0-gate",	"ext-26m", 0xb8,
+		     0x1000, BIT(2), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(twpll_gate,	"twpll-gate",	"ext-26m", 0xbc,
+		     0x1000, BIT(2), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ltepll1_gate,	"ltepll1-gate",	"ext-26m", 0x10c,
+		     0x1000, BIT(2), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(rpll0_gate,	"rpll0-gate",	"ext-26m", 0x16c,
+		     0x1000, BIT(2), 0, 0);
+static SPRD_SC_GATE_CLK(rpll1_gate,	"rpll1-gate",	"ext-26m", 0x16c,
+		     0x1000, BIT(18), 0, 0);
+static SPRD_SC_GATE_CLK(cppll_gate,	"cppll-gate",	"ext-26m", 0x2b4,
+		     0x1000, BIT(2), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(gpll_gate,	"gpll-gate",	"ext-26m", 0x32c,
+		0x1000, BIT(0), CLK_IGNORE_UNUSED, CLK_GATE_SET_TO_DISABLE);
+
+static struct sprd_clk_common *sc9860_pmu_gate_clks[] = {
+	/* address base is 0x402b0000 */
+	&mpll0_gate.common,
+	&mpll1_gate.common,
+	&dpll0_gate.common,
+	&dpll1_gate.common,
+	&ltepll0_gate.common,
+	&twpll_gate.common,
+	&ltepll1_gate.common,
+	&rpll0_gate.common,
+	&rpll1_gate.common,
+	&cppll_gate.common,
+	&gpll_gate.common,
+};
+
+static struct clk_hw_onecell_data sc9860_pmu_gate_hws = {
+	.hws	= {
+		[CLK_FAC_4M]		= &fac_4m.hw,
+		[CLK_FAC_2M]		= &fac_2m.hw,
+		[CLK_FAC_1M]		= &fac_1m.hw,
+		[CLK_FAC_250K]		= &fac_250k.hw,
+		[CLK_FAC_RPLL0_26M]	= &fac_rpll0_26m.hw,
+		[CLK_FAC_RPLL1_26M]	= &fac_rpll1_26m.hw,
+		[CLK_FAC_RCO25M]	= &fac_rco_25m.hw,
+		[CLK_FAC_RCO4M]		= &fac_rco_4m.hw,
+		[CLK_FAC_RCO2M]		= &fac_rco_2m.hw,
+		[CLK_FAC_3K2]		= &fac_3k2.hw,
+		[CLK_FAC_1K]		= &fac_1k.hw,
+		[CLK_MPLL0_GATE]	= &mpll0_gate.common.hw,
+		[CLK_MPLL1_GATE]	= &mpll1_gate.common.hw,
+		[CLK_DPLL0_GATE]	= &dpll0_gate.common.hw,
+		[CLK_DPLL1_GATE]	= &dpll1_gate.common.hw,
+		[CLK_LTEPLL0_GATE]	= &ltepll0_gate.common.hw,
+		[CLK_TWPLL_GATE]	= &twpll_gate.common.hw,
+		[CLK_LTEPLL1_GATE]	= &ltepll1_gate.common.hw,
+		[CLK_RPLL0_GATE]	= &rpll0_gate.common.hw,
+		[CLK_RPLL1_GATE]	= &rpll1_gate.common.hw,
+		[CLK_CPPLL_GATE]	= &cppll_gate.common.hw,
+		[CLK_GPLL_GATE]		= &gpll_gate.common.hw,
+	},
+	.num	= CLK_PMU_GATE_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_pmu_gate_desc = {
+	.clk_clks	= sc9860_pmu_gate_clks,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_pmu_gate_clks),
+	.hw_clks        = &sc9860_pmu_gate_hws,
+};
+
+/* GPLL/LPLL/DPLL/RPLL/CPLL */
+static const u64 itable1[4] = {3, 780000000, 988000000, 1196000000};
+
+/* TWPLL/MPLL0/MPLL1 */
+static const u64 itable2[4] = {3, 1638000000, 2080000000, 2600000000UL};
+
+static const struct clk_bit_field f_mpll0[PLL_FACT_MAX] = {
+	{ .shift = 20,	.width = 1 },	/* lock_done	*/
+	{ .shift = 19,	.width = 1 },	/* div_s	*/
+	{ .shift = 18,	.width = 1 },	/* mod_en	*/
+	{ .shift = 17,	.width = 1 },	/* sdm_en	*/
+	{ .shift = 0,	.width = 0 },	/* refin	*/
+	{ .shift = 11,	.width = 2 },	/* ibias	*/
+	{ .shift = 0,	.width = 7 },	/* n		*/
+	{ .shift = 57,	.width = 7 },	/* nint		*/
+	{ .shift = 32,	.width = 23},	/* kint		*/
+	{ .shift = 0,	.width = 0 },	/* prediv	*/
+	{ .shift = 56,	.width = 1 },	/* postdiv	*/
+};
+static SPRD_PLL_WITH_ITABLE_K_FVCO(mpll0_clk, "mpll0", "mpll0-gate", 0x24,
+				   2, itable2, f_mpll0, 200,
+				   1000, 1000, 1, 1300000000);
+
+static const struct clk_bit_field f_mpll1[PLL_FACT_MAX] = {
+	{ .shift = 20,	.width = 1 },	/* lock_done	*/
+	{ .shift = 19,	.width = 1 },	/* div_s	*/
+	{ .shift = 18,	.width = 1 },	/* mod_en	*/
+	{ .shift = 17,	.width = 1 },	/* sdm_en	*/
+	{ .shift = 0,	.width = 0 },	/* refin	*/
+	{ .shift = 11,	.width = 2 },	/* ibias	*/
+	{ .shift = 0,	.width = 7 },	/* n		*/
+	{ .shift = 57,	.width = 7 },	/* nint		*/
+	{ .shift = 32,	.width = 23},	/* kint		*/
+	{ .shift = 56,	.width = 1 },	/* prediv	*/
+	{ .shift = 0,	.width = 0 },	/* postdiv	*/
+};
+static SPRD_PLL_WITH_ITABLE_1K(mpll1_clk, "mpll1", "mpll1-gate", 0x2c,
+			       2, itable2, f_mpll1, 200);
+
+static const struct clk_bit_field f_dpll[PLL_FACT_MAX] = {
+	{ .shift = 16,	.width = 1 },	/* lock_done	*/
+	{ .shift = 15,	.width = 1 },	/* div_s	*/
+	{ .shift = 14,	.width = 1 },	/* mod_en	*/
+	{ .shift = 13,	.width = 1 },	/* sdm_en	*/
+	{ .shift = 0,	.width = 0 },	/* refin	*/
+	{ .shift = 8,	.width = 2 },	/* ibias	*/
+	{ .shift = 0,	.width = 7 },	/* n		*/
+	{ .shift = 57,	.width = 7 },	/* nint		*/
+	{ .shift = 32,	.width = 23},	/* kint		*/
+	{ .shift = 0,	.width = 0 },	/* prediv	*/
+	{ .shift = 0,	.width = 0 },	/* postdiv	*/
+};
+static SPRD_PLL_WITH_ITABLE_1K(dpll0_clk, "dpll0", "dpll0-gate", 0x34,
+			       2, itable1, f_dpll, 200);
+
+static SPRD_PLL_WITH_ITABLE_1K(dpll1_clk, "dpll1", "dpll1-gate", 0x3c,
+			       2, itable1, f_dpll, 200);
+
+static const struct clk_bit_field f_rpll[PLL_FACT_MAX] = {
+	{ .shift = 0,	.width = 1 },	/* lock_done	*/
+	{ .shift = 3,	.width = 1 },	/* div_s	*/
+	{ .shift = 80,	.width = 1 },	/* mod_en	*/
+	{ .shift = 81,	.width = 1 },	/* sdm_en	*/
+	{ .shift = 0,	.width = 0 },	/* refin	*/
+	{ .shift = 14,	.width = 2 },	/* ibias	*/
+	{ .shift = 16,	.width = 7 },	/* n		*/
+	{ .shift = 4,	.width = 7 },	/* nint		*/
+	{ .shift = 32,	.width = 23},	/* kint		*/
+	{ .shift = 0,	.width = 0 },	/* prediv	*/
+	{ .shift = 0,	.width = 0 },	/* postdiv	*/
+};
+static SPRD_PLL_WITH_ITABLE_1K(rpll0_clk, "rpll0", "rpll0-gate", 0x44,
+			       3, itable1, f_rpll, 200);
+
+static SPRD_PLL_WITH_ITABLE_1K(rpll1_clk, "rpll1", "rpll1-gate", 0x50,
+			       3, itable1, f_rpll, 200);
+
+static const struct clk_bit_field f_twpll[PLL_FACT_MAX] = {
+	{ .shift = 21,	.width = 1 },	/* lock_done	*/
+	{ .shift = 20,	.width = 1 },	/* div_s	*/
+	{ .shift = 19,	.width = 1 },	/* mod_en	*/
+	{ .shift = 18,	.width = 1 },	/* sdm_en	*/
+	{ .shift = 0,	.width = 0 },	/* refin	*/
+	{ .shift = 13,	.width = 2 },	/* ibias	*/
+	{ .shift = 0,	.width = 7 },	/* n		*/
+	{ .shift = 57,	.width = 7 },	/* nint		*/
+	{ .shift = 32,	.width = 23},	/* kint		*/
+	{ .shift = 0,	.width = 0 },	/* prediv	*/
+	{ .shift = 0,	.width = 0 },	/* postdiv	*/
+};
+static SPRD_PLL_WITH_ITABLE_1K(twpll_clk, "twpll", "twpll-gate", 0x5c,
+			       2, itable2, f_twpll, 200);
+
+static const struct clk_bit_field f_ltepll[PLL_FACT_MAX] = {
+	{ .shift = 31,	.width = 1 },	/* lock_done	*/
+	{ .shift = 27,	.width = 1 },	/* div_s	*/
+	{ .shift = 26,	.width = 1 },	/* mod_en	*/
+	{ .shift = 25,	.width = 1 },	/* sdm_en	*/
+	{ .shift = 0,	.width = 0 },	/* refin	*/
+	{ .shift = 20,	.width = 2 },	/* ibias	*/
+	{ .shift = 0,	.width = 7 },	/* n		*/
+	{ .shift = 57,	.width = 7 },	/* nint		*/
+	{ .shift = 32,	.width = 23},	/* kint		*/
+	{ .shift = 0,	.width = 0 },	/* prediv	*/
+	{ .shift = 0,	.width = 0 },	/* postdiv	*/
+};
+static SPRD_PLL_WITH_ITABLE_1K(ltepll0_clk, "ltepll0", "ltepll0-gate",
+			       0x64, 2, itable1,
+			       f_ltepll, 200);
+static SPRD_PLL_WITH_ITABLE_1K(ltepll1_clk, "ltepll1", "ltepll1-gate",
+			       0x6c, 2, itable1,
+			       f_ltepll, 200);
+
+static const struct clk_bit_field f_gpll[PLL_FACT_MAX] = {
+	{ .shift = 18,	.width = 1 },	/* lock_done	*/
+	{ .shift = 15,	.width = 1 },	/* div_s	*/
+	{ .shift = 14,	.width = 1 },	/* mod_en	*/
+	{ .shift = 13,	.width = 1 },	/* sdm_en	*/
+	{ .shift = 0,	.width = 0 },	/* refin	*/
+	{ .shift = 8,	.width = 2 },	/* ibias	*/
+	{ .shift = 0,	.width = 7 },	/* n		*/
+	{ .shift = 57,	.width = 7 },	/* nint		*/
+	{ .shift = 32,	.width = 23},	/* kint		*/
+	{ .shift = 0,	.width = 0 },	/* prediv	*/
+	{ .shift = 17,	.width = 1 },	/* postdiv	*/
+};
+static SPRD_PLL_WITH_ITABLE_K_FVCO(gpll_clk, "gpll", "gpll-gate", 0x9c,
+				   2, itable1, f_gpll, 200,
+				   1000, 1000, 1, 600000000);
+
+static const struct clk_bit_field f_cppll[PLL_FACT_MAX] = {
+	{ .shift = 17,	.width = 1 },	/* lock_done	*/
+	{ .shift = 15,	.width = 1 },	/* div_s	*/
+	{ .shift = 14,	.width = 1 },	/* mod_en	*/
+	{ .shift = 13,	.width = 1 },	/* sdm_en	*/
+	{ .shift = 0,	.width = 0 },	/* refin	*/
+	{ .shift = 8,	.width = 2 },	/* ibias	*/
+	{ .shift = 0,	.width = 7 },	/* n		*/
+	{ .shift = 57,	.width = 7 },	/* nint		*/
+	{ .shift = 32,	.width = 23},	/* kint		*/
+	{ .shift = 0,	.width = 0 },	/* prediv	*/
+	{ .shift = 0,	.width = 0 },	/* postdiv	*/
+};
+static SPRD_PLL_WITH_ITABLE_1K(cppll_clk, "cppll", "cppll-gate", 0xc4,
+			       2, itable1, f_cppll, 200);
+
+static CLK_FIXED_FACTOR(gpll_42m5, "gpll-42m5", "gpll", 20, 1, 0);
+static CLK_FIXED_FACTOR(twpll_768m, "twpll-768m", "twpll", 2, 1, 0);
+static CLK_FIXED_FACTOR(twpll_384m, "twpll-384m", "twpll", 4, 1, 0);
+static CLK_FIXED_FACTOR(twpll_192m, "twpll-192m", "twpll", 8, 1, 0);
+static CLK_FIXED_FACTOR(twpll_96m, "twpll-96m", "twpll", 16, 1, 0);
+static CLK_FIXED_FACTOR(twpll_48m, "twpll-48m", "twpll", 32, 1, 0);
+static CLK_FIXED_FACTOR(twpll_24m, "twpll-24m", "twpll", 64, 1, 0);
+static CLK_FIXED_FACTOR(twpll_12m, "twpll-12m", "twpll", 128, 1, 0);
+static CLK_FIXED_FACTOR(twpll_512m, "twpll-512m", "twpll", 3, 1, 0);
+static CLK_FIXED_FACTOR(twpll_256m, "twpll-256m", "twpll", 6, 1, 0);
+static CLK_FIXED_FACTOR(twpll_128m, "twpll-128m", "twpll", 12, 1, 0);
+static CLK_FIXED_FACTOR(twpll_64m, "twpll-64m", "twpll", 24, 1, 0);
+static CLK_FIXED_FACTOR(twpll_307m2, "twpll-307m2", "twpll", 5, 1, 0);
+static CLK_FIXED_FACTOR(twpll_153m6, "twpll-153m6", "twpll", 10, 1, 0);
+static CLK_FIXED_FACTOR(twpll_76m8, "twpll-76m8", "twpll", 20, 1, 0);
+static CLK_FIXED_FACTOR(twpll_51m2, "twpll-51m2", "twpll", 30, 1, 0);
+static CLK_FIXED_FACTOR(twpll_38m4, "twpll-38m4", "twpll", 40, 1, 0);
+static CLK_FIXED_FACTOR(twpll_19m2, "twpll-19m2", "twpll", 80, 1, 0);
+static CLK_FIXED_FACTOR(l0_614m4, "l0-614m4", "ltepll0", 2, 1, 0);
+static CLK_FIXED_FACTOR(l0_409m6, "l0-409m6", "ltepll0", 3, 1, 0);
+static CLK_FIXED_FACTOR(l0_38m, "l0-38m", "ltepll0", 32, 1, 0);
+static CLK_FIXED_FACTOR(l1_38m, "l1-38m", "ltepll1", 32, 1, 0);
+static CLK_FIXED_FACTOR(rpll0_192m, "rpll0-192m", "rpll0", 6, 1, 0);
+static CLK_FIXED_FACTOR(rpll0_96m, "rpll0-96m", "rpll0", 12, 1, 0);
+static CLK_FIXED_FACTOR(rpll0_48m, "rpll0-48m", "rpll0", 24, 1, 0);
+static CLK_FIXED_FACTOR(rpll1_468m, "rpll1-468m", "rpll1", 2, 1, 0);
+static CLK_FIXED_FACTOR(rpll1_192m, "rpll1-192m", "rpll1", 6, 1, 0);
+static CLK_FIXED_FACTOR(rpll1_96m, "rpll1-96m", "rpll1", 12, 1, 0);
+static CLK_FIXED_FACTOR(rpll1_64m, "rpll1-64m", "rpll1", 18, 1, 0);
+static CLK_FIXED_FACTOR(rpll1_48m, "rpll1-48m", "rpll1", 24, 1, 0);
+static CLK_FIXED_FACTOR(dpll0_50m, "dpll0-50m", "dpll0", 16, 1, 0);
+static CLK_FIXED_FACTOR(dpll1_50m, "dpll1-50m", "dpll1", 16, 1, 0);
+static CLK_FIXED_FACTOR(cppll_50m, "cppll-50m", "cppll", 18, 1, 0);
+static CLK_FIXED_FACTOR(m0_39m, "m0-39m", "mpll0", 32, 1, 0);
+static CLK_FIXED_FACTOR(m1_63m, "m1-63m", "mpll1", 32, 1, 0);
+
+static struct sprd_clk_common *sc9860_pll_clks[] = {
+	/* address base is 0x40400000 */
+	&mpll0_clk.common,
+	&mpll1_clk.common,
+	&dpll0_clk.common,
+	&dpll1_clk.common,
+	&rpll0_clk.common,
+	&rpll1_clk.common,
+	&twpll_clk.common,
+	&ltepll0_clk.common,
+	&ltepll1_clk.common,
+	&gpll_clk.common,
+	&cppll_clk.common,
+};
+
+static struct clk_hw_onecell_data sc9860_pll_hws = {
+	.hws	= {
+		[CLK_MPLL0]		= &mpll0_clk.common.hw,
+		[CLK_MPLL1]		= &mpll1_clk.common.hw,
+		[CLK_DPLL0]		= &dpll0_clk.common.hw,
+		[CLK_DPLL1]		= &dpll1_clk.common.hw,
+		[CLK_RPLL0]		= &rpll0_clk.common.hw,
+		[CLK_RPLL1]		= &rpll1_clk.common.hw,
+		[CLK_TWPLL]		= &twpll_clk.common.hw,
+		[CLK_LTEPLL0]		= &ltepll0_clk.common.hw,
+		[CLK_LTEPLL1]		= &ltepll1_clk.common.hw,
+		[CLK_GPLL]		= &gpll_clk.common.hw,
+		[CLK_CPPLL]		= &cppll_clk.common.hw,
+		[CLK_GPLL_42M5]		= &gpll_42m5.hw,
+		[CLK_TWPLL_768M]	= &twpll_768m.hw,
+		[CLK_TWPLL_384M]	= &twpll_384m.hw,
+		[CLK_TWPLL_192M]	= &twpll_192m.hw,
+		[CLK_TWPLL_96M]		= &twpll_96m.hw,
+		[CLK_TWPLL_48M]		= &twpll_48m.hw,
+		[CLK_TWPLL_24M]		= &twpll_24m.hw,
+		[CLK_TWPLL_12M]		= &twpll_12m.hw,
+		[CLK_TWPLL_512M]	= &twpll_512m.hw,
+		[CLK_TWPLL_256M]	= &twpll_256m.hw,
+		[CLK_TWPLL_128M]	= &twpll_128m.hw,
+		[CLK_TWPLL_64M]		= &twpll_64m.hw,
+		[CLK_TWPLL_307M2]	= &twpll_307m2.hw,
+		[CLK_TWPLL_153M6]	= &twpll_153m6.hw,
+		[CLK_TWPLL_76M8]	= &twpll_76m8.hw,
+		[CLK_TWPLL_51M2]	= &twpll_51m2.hw,
+		[CLK_TWPLL_38M4]	= &twpll_38m4.hw,
+		[CLK_TWPLL_19M2]	= &twpll_19m2.hw,
+		[CLK_L0_614M4]		= &l0_614m4.hw,
+		[CLK_L0_409M6]		= &l0_409m6.hw,
+		[CLK_L0_38M]		= &l0_38m.hw,
+		[CLK_L1_38M]		= &l1_38m.hw,
+		[CLK_RPLL0_192M]	= &rpll0_192m.hw,
+		[CLK_RPLL0_96M]		= &rpll0_96m.hw,
+		[CLK_RPLL0_48M]		= &rpll0_48m.hw,
+		[CLK_RPLL1_468M]	= &rpll1_468m.hw,
+		[CLK_RPLL1_192M]	= &rpll1_192m.hw,
+		[CLK_RPLL1_96M]		= &rpll1_96m.hw,
+		[CLK_RPLL1_64M]		= &rpll1_64m.hw,
+		[CLK_RPLL1_48M]		= &rpll1_48m.hw,
+		[CLK_DPLL0_50M]		= &dpll0_50m.hw,
+		[CLK_DPLL1_50M]		= &dpll1_50m.hw,
+		[CLK_CPPLL_50M]		= &cppll_50m.hw,
+		[CLK_M0_39M]		= &m0_39m.hw,
+		[CLK_M1_63M]		= &m1_63m.hw,
+	},
+	.num	= CLK_PLL_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_pll_desc = {
+	.clk_clks	= sc9860_pll_clks,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_pll_clks),
+	.hw_clks	= &sc9860_pll_hws,
+};
+
+#define SC9860_MUX_FLAG	\
+	(CLK_GET_RATE_NOCACHE | CLK_SET_RATE_NO_REPARENT)
+
+static const char * const ap_apb_parents[] = { "ext-26m", "twpll-64m",
+					       "twpll-96m", "twpll-128m" };
+static SPRD_MUX_CLK(ap_apb, "ap-apb", ap_apb_parents,
+		    0x20, 0, 1, SC9860_MUX_FLAG);
+
+static const char * const ap_apb_usb3[] = { "ext-32k", "twpll-24m" };
+static SPRD_MUX_CLK(ap_usb3, "ap-usb3", ap_apb_usb3,
+		    0x2c, 0, 1, SC9860_MUX_FLAG);
+
+static const char * const uart_parents[] = {	"ext-26m",	"twpll-48m",
+						"twpll-51m2",	"twpll-96m" };
+static SPRD_COMP_CLK(uart0_clk,	"uart0",	uart_parents, 0x30,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(uart1_clk,	"uart1",	uart_parents, 0x34,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(uart2_clk,	"uart2",	uart_parents, 0x38,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(uart3_clk,	"uart3",	uart_parents, 0x3c,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(uart4_clk,	"uart4",	uart_parents, 0x40,
+		     0, 2, 8, 3, 0);
+
+static const char * const i2c_parents[] = { "ext-26m", "twpll-48m",
+					    "twpll-51m2", "twpll-153m6" };
+static SPRD_COMP_CLK(i2c0_clk,	"i2c0", i2c_parents, 0x44,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(i2c1_clk,	"i2c1", i2c_parents, 0x48,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(i2c2_clk,	"i2c2", i2c_parents, 0x4c,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(i2c3_clk,	"i2c3", i2c_parents, 0x50,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(i2c4_clk,	"i2c4", i2c_parents, 0x54,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(i2c5_clk,	"i2c5", i2c_parents, 0x58,
+		     0, 2, 8, 3, 0);
+
+static const char * const spi_parents[] = {	"ext-26m",	"twpll-128m",
+						"twpll-153m6",	"twpll-192m" };
+static SPRD_COMP_CLK(spi0_clk,	"spi0",	spi_parents, 0x5c,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(spi1_clk,	"spi1",	spi_parents, 0x60,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(spi2_clk,	"spi2",	spi_parents, 0x64,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(spi3_clk,	"spi3",	spi_parents, 0x68,
+		     0, 2, 8, 3, 0);
+
+static const char * const iis_parents[] = { "ext-26m",
+					    "twpll-128m",
+					    "twpll-153m6" };
+static SPRD_COMP_CLK(iis0_clk,	"iis0",	iis_parents, 0x6c,
+		     0, 2, 8, 6, 0);
+static SPRD_COMP_CLK(iis1_clk,	"iis1",	iis_parents, 0x70,
+		     0, 2, 8, 6, 0);
+static SPRD_COMP_CLK(iis2_clk,	"iis2",	iis_parents, 0x74,
+		     0, 2, 8, 6, 0);
+static SPRD_COMP_CLK(iis3_clk,	"iis3",	iis_parents, 0x78,
+		     0, 2, 8, 6, 0);
+
+static struct sprd_clk_common *sc9860_ap_clks[] = {
+	/* address base is 0x20000000 */
+	&ap_apb.common,
+	&ap_usb3.common,
+	&uart0_clk.common,
+	&uart1_clk.common,
+	&uart2_clk.common,
+	&uart3_clk.common,
+	&uart4_clk.common,
+	&i2c0_clk.common,
+	&i2c1_clk.common,
+	&i2c2_clk.common,
+	&i2c3_clk.common,
+	&i2c4_clk.common,
+	&i2c5_clk.common,
+	&spi0_clk.common,
+	&spi1_clk.common,
+	&spi2_clk.common,
+	&spi3_clk.common,
+	&iis0_clk.common,
+	&iis1_clk.common,
+	&iis2_clk.common,
+	&iis3_clk.common,
+};
+
+static struct clk_hw_onecell_data sc9860_ap_clk_hws = {
+	.hws	= {
+		[CLK_AP_APB]	= &ap_apb.common.hw,
+		[CLK_AP_USB3]	= &ap_usb3.common.hw,
+		[CLK_UART0]	= &uart0_clk.common.hw,
+		[CLK_UART1]	= &uart1_clk.common.hw,
+		[CLK_UART2]	= &uart2_clk.common.hw,
+		[CLK_UART3]	= &uart3_clk.common.hw,
+		[CLK_UART4]	= &uart4_clk.common.hw,
+		[CLK_I2C0]	= &i2c0_clk.common.hw,
+		[CLK_I2C1]	= &i2c1_clk.common.hw,
+		[CLK_I2C2]	= &i2c2_clk.common.hw,
+		[CLK_I2C3]	= &i2c3_clk.common.hw,
+		[CLK_I2C4]	= &i2c4_clk.common.hw,
+		[CLK_I2C5]	= &i2c5_clk.common.hw,
+		[CLK_SPI0]	= &spi0_clk.common.hw,
+		[CLK_SPI1]	= &spi1_clk.common.hw,
+		[CLK_SPI2]	= &spi2_clk.common.hw,
+		[CLK_SPI3]	= &spi3_clk.common.hw,
+		[CLK_IIS0]	= &iis0_clk.common.hw,
+		[CLK_IIS1]	= &iis1_clk.common.hw,
+		[CLK_IIS2]	= &iis2_clk.common.hw,
+		[CLK_IIS3]	= &iis3_clk.common.hw,
+	},
+	.num	= CLK_AP_CLK_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_ap_clk_desc = {
+	.clk_clks	= sc9860_ap_clks,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_ap_clks),
+	.hw_clks	= &sc9860_ap_clk_hws,
+};
+
+static const char * const aon_apb_parents[] = { "rco-25m",	"ext-26m",
+						"ext-rco-100m",	"twpll-96m",
+						"twpll-128m",
+						"twpll-153m6" };
+static SPRD_COMP_CLK(aon_apb, "aon-apb", aon_apb_parents, 0x230,
+		     0, 3, 8, 2, 0);
+
+static const char * const aux_parents[] = { "ext-32k",		"rpll0-26m",
+					    "rpll1-26m",	"ext-26m",
+					    "cppll-50m",	"rco-25m",
+					    "dpll0-50m",	"dpll1-50m",
+					    "gpll-42m5",	"twpll-48m",
+					    "m0-39m",		"m1-63m",
+					    "l0-38m",		"l1-38m" };
+
+static SPRD_COMP_CLK(aux0_clk,	"aux0",		aux_parents, 0x238,
+		     0, 5, 8, 4, 0);
+static SPRD_COMP_CLK(aux1_clk,	"aux1",		aux_parents, 0x23c,
+		     0, 5, 8, 4, 0);
+static SPRD_COMP_CLK(aux2_clk,	"aux2",		aux_parents, 0x240,
+		     0, 5, 8, 4, 0);
+static SPRD_COMP_CLK(probe_clk,	"probe",	aux_parents, 0x244,
+		     0, 5, 8, 4, 0);
+
+static const char * const sp_ahb_parents[] = {	"rco-4m",	"ext-26m",
+						"ext-rco-100m",	"twpll-96m",
+						"twpll-128m",
+						"twpll-153m6" };
+static SPRD_COMP_CLK(sp_ahb,	"sp-ahb",	sp_ahb_parents, 0x2d0,
+		     0, 3, 8, 2, 0);
+
+static const char * const cci_parents[] = {	"ext-26m",	"twpll-384m",
+						"l0-614m4",	"twpll-768m" };
+static SPRD_COMP_CLK(cci_clk,	"cci",		cci_parents, 0x300,
+		     0, 2, 8, 2, 0);
+static SPRD_COMP_CLK(gic_clk,	"gic",		cci_parents, 0x304,
+		     0, 2, 8, 2, 0);
+static SPRD_COMP_CLK(cssys_clk,	"cssys",	cci_parents, 0x310,
+		     0, 2, 8, 2, 0);
+
+static const char * const sdio_2x_parents[] = {	"fac-1m",	"ext-26m",
+						"twpll-307m2",	"twpll-384m",
+						"l0-409m6" };
+static SPRD_COMP_CLK(sdio0_2x,	"sdio0-2x",	sdio_2x_parents, 0x328,
+		     0, 3, 8, 4, 0);
+static SPRD_COMP_CLK(sdio1_2x,	"sdio1-2x",	sdio_2x_parents, 0x330,
+		     0, 3, 8, 4, 0);
+static SPRD_COMP_CLK(sdio2_2x,	"sdio2-2x",	sdio_2x_parents, 0x338,
+		     0, 3, 8, 4, 0);
+static SPRD_COMP_CLK(emmc_2x,	"emmc-2x",	sdio_2x_parents, 0x340,
+		     0, 3, 8, 4, 0);
+
+static SPRD_DIV_CLK(sdio0_1x,	"sdio0-1x",	"sdio0-2x",	0x32c,
+		    8, 1, 0);
+static SPRD_DIV_CLK(sdio1_1x,	"sdio1-1x",	"sdio1-2x",	0x334,
+		    8, 1, 0);
+static SPRD_DIV_CLK(sdio2_1x,	"sdio2-1x",	"sdio2-2x",	0x33c,
+		    8, 1, 0);
+static SPRD_DIV_CLK(emmc_1x,	"emmc-1x",	"emmc-2x",	0x344,
+		    8, 1, 0);
+
+static const char * const adi_parents[] = {	"rco-4m",	"ext-26m",
+						"rco-25m",	"twpll-38m4",
+						"twpll-51m2" };
+static SPRD_MUX_CLK(adi_clk,	"adi",	adi_parents, 0x234,
+		    0, 3, SC9860_MUX_FLAG);
+
+static const char * const pwm_parents[] = {	"ext-32k",	"ext-26m",
+						"rco-4m",	"rco-25m",
+						"twpll-48m" };
+static SPRD_MUX_CLK(pwm0_clk,	"pwm0",	pwm_parents, 0x248,
+		    0, 3, SC9860_MUX_FLAG);
+static SPRD_MUX_CLK(pwm1_clk,	"pwm1",	pwm_parents, 0x24c,
+		    0, 3, SC9860_MUX_FLAG);
+static SPRD_MUX_CLK(pwm2_clk,	"pwm2",	pwm_parents, 0x250,
+		    0, 3, SC9860_MUX_FLAG);
+static SPRD_MUX_CLK(pwm3_clk,	"pwm3",	pwm_parents, 0x254,
+		    0, 3, SC9860_MUX_FLAG);
+
+static const char * const efuse_parents[] = { "rco-25m", "ext-26m" };
+static SPRD_MUX_CLK(efuse_clk, "efuse", efuse_parents, 0x258,
+		    0, 1, SC9860_MUX_FLAG);
+
+static const char * const cm3_uart_parents[] = { "rco-4m",	"ext-26m",
+						 "rco-100m",	"twpll-48m",
+						 "twpll-51m2",	"twpll-96m",
+						 "twpll-128m" };
+static SPRD_MUX_CLK(cm3_uart0, "cm3-uart0", cm3_uart_parents, 0x25c,
+		    0, 3, SC9860_MUX_FLAG);
+static SPRD_MUX_CLK(cm3_uart1, "cm3-uart1", cm3_uart_parents, 0x260,
+		    0, 3, SC9860_MUX_FLAG);
+
+static const char * const thm_parents[] = { "ext-32k", "fac-250k" };
+static SPRD_MUX_CLK(thm_clk,	"thm",	thm_parents, 0x270,
+		    0, 1, SC9860_MUX_FLAG);
+
+static const char * const cm3_i2c_parents[] = {	"rco-4m",
+						"ext-26m",
+						"rco-100m",
+						"twpll-48m",
+						"twpll-51m2",
+						"twpll-153m6" };
+static SPRD_MUX_CLK(cm3_i2c0, "cm3-i2c0", cm3_i2c_parents, 0x274,
+		    0, 3, SC9860_MUX_FLAG);
+static SPRD_MUX_CLK(cm3_i2c1, "cm3-i2c1", cm3_i2c_parents, 0x278,
+		    0, 3, SC9860_MUX_FLAG);
+static SPRD_MUX_CLK(aon_i2c, "aon-i2c",	cm3_i2c_parents, 0x280,
+		    0, 3, SC9860_MUX_FLAG);
+
+static const char * const cm4_spi_parents[] = {	"ext-26m",	"twpll-96m",
+						"rco-100m",	"twpll-128m",
+						"twpll-153m6",	"twpll-192m" };
+static SPRD_MUX_CLK(cm4_spi, "cm4-spi", cm4_spi_parents, 0x27c,
+		    0, 3, SC9860_MUX_FLAG);
+
+static SPRD_MUX_CLK(avs_clk, "avs", uart_parents, 0x284,
+		    0, 2, SC9860_MUX_FLAG);
+
+static const char * const ca53_dap_parents[] = { "ext-26m",	"rco-4m",
+						 "rco-100m",	"twpll-76m8",
+						 "twpll-128m",	"twpll-153m6" };
+static SPRD_MUX_CLK(ca53_dap, "ca53-dap", ca53_dap_parents, 0x288,
+		    0, 3, SC9860_MUX_FLAG);
+
+static const char * const ca53_ts_parents[] = {	"ext-32k", "ext-26m",
+						"clk-twpll-128m",
+						"clk-twpll-153m6" };
+static SPRD_MUX_CLK(ca53_ts, "ca53-ts", ca53_ts_parents, 0x290,
+		    0, 2, SC9860_MUX_FLAG);
+
+static const char * const djtag_tck_parents[] = { "rco-4m", "ext-26m" };
+static SPRD_MUX_CLK(djtag_tck, "djtag-tck", djtag_tck_parents, 0x2c8,
+		    0, 1, SC9860_MUX_FLAG);
+
+static const char * const pmu_parents[] = { "ext-32k", "rco-4m", "clk-4m" };
+static SPRD_MUX_CLK(pmu_clk, "pmu", pmu_parents, 0x2e0,
+		    0, 2, SC9860_MUX_FLAG);
+
+static const char * const pmu_26m_parents[] = { "rco-25m", "ext-26m" };
+static SPRD_MUX_CLK(pmu_26m, "pmu-26m", pmu_26m_parents, 0x2e4,
+		    0, 1, SC9860_MUX_FLAG);
+
+static const char * const debounce_parents[] = { "ext-32k", "rco-4m",
+						 "rco-25m", "ext-26m" };
+static SPRD_MUX_CLK(debounce_clk, "debounce", debounce_parents, 0x2e8,
+		    0, 2, SC9860_MUX_FLAG);
+
+static const char * const otg2_ref_parents[] = { "twpll-12m", "twpll-24m" };
+static SPRD_MUX_CLK(otg2_ref, "otg2-ref", otg2_ref_parents, 0x2f4,
+		    0, 1, SC9860_MUX_FLAG);
+
+static const char * const usb3_ref_parents[] = { "twpll-24m", "twpll-19m2",
+						 "twpll-48m" };
+static SPRD_MUX_CLK(usb3_ref, "usb3-ref", usb3_ref_parents, 0x2f8,
+		    0, 2, SC9860_MUX_FLAG);
+
+static const char * const ap_axi_parents[] = { "ext-26m", "twpll-76m8",
+					       "twpll-128m", "twpll-256m" };
+static SPRD_MUX_CLK(ap_axi, "ap-axi", ap_axi_parents, 0x324,
+		    0, 2, SC9860_MUX_FLAG);
+
+static struct sprd_clk_common *sc9860_aon_prediv[] = {
+	/* address base is 0x402d0000 */
+	&aon_apb.common,
+	&aux0_clk.common,
+	&aux1_clk.common,
+	&aux2_clk.common,
+	&probe_clk.common,
+	&sp_ahb.common,
+	&cci_clk.common,
+	&gic_clk.common,
+	&cssys_clk.common,
+	&sdio0_2x.common,
+	&sdio1_2x.common,
+	&sdio2_2x.common,
+	&emmc_2x.common,
+	&sdio0_1x.common,
+	&sdio1_1x.common,
+	&sdio2_1x.common,
+	&emmc_1x.common,
+	&adi_clk.common,
+	&pwm0_clk.common,
+	&pwm1_clk.common,
+	&pwm2_clk.common,
+	&pwm3_clk.common,
+	&efuse_clk.common,
+	&cm3_uart0.common,
+	&cm3_uart1.common,
+	&thm_clk.common,
+	&cm3_i2c0.common,
+	&cm3_i2c1.common,
+	&cm4_spi.common,
+	&aon_i2c.common,
+	&avs_clk.common,
+	&ca53_dap.common,
+	&ca53_ts.common,
+	&djtag_tck.common,
+	&pmu_clk.common,
+	&pmu_26m.common,
+	&debounce_clk.common,
+	&otg2_ref.common,
+	&usb3_ref.common,
+	&ap_axi.common,
+};
+
+static struct clk_hw_onecell_data sc9860_aon_prediv_hws = {
+	.hws	= {
+		[CLK_AON_APB]		= &aon_apb.common.hw,
+		[CLK_AUX0]		= &aux0_clk.common.hw,
+		[CLK_AUX1]		= &aux1_clk.common.hw,
+		[CLK_AUX2]		= &aux2_clk.common.hw,
+		[CLK_PROBE]		= &probe_clk.common.hw,
+		[CLK_SP_AHB]		= &sp_ahb.common.hw,
+		[CLK_CCI]		= &cci_clk.common.hw,
+		[CLK_GIC]		= &gic_clk.common.hw,
+		[CLK_CSSYS]		= &cssys_clk.common.hw,
+		[CLK_SDIO0_2X]		= &sdio0_2x.common.hw,
+		[CLK_SDIO1_2X]		= &sdio1_2x.common.hw,
+		[CLK_SDIO2_2X]		= &sdio2_2x.common.hw,
+		[CLK_EMMC_2X]		= &emmc_2x.common.hw,
+		[CLK_SDIO0_1X]		= &sdio0_1x.common.hw,
+		[CLK_SDIO1_1X]		= &sdio1_1x.common.hw,
+		[CLK_SDIO2_1X]		= &sdio2_1x.common.hw,
+		[CLK_EMMC_1X]		= &emmc_1x.common.hw,
+		[CLK_ADI]		= &adi_clk.common.hw,
+		[CLK_PWM0]		= &pwm0_clk.common.hw,
+		[CLK_PWM1]		= &pwm1_clk.common.hw,
+		[CLK_PWM2]		= &pwm2_clk.common.hw,
+		[CLK_PWM3]		= &pwm3_clk.common.hw,
+		[CLK_EFUSE]		= &efuse_clk.common.hw,
+		[CLK_CM3_UART0]		= &cm3_uart0.common.hw,
+		[CLK_CM3_UART1]		= &cm3_uart1.common.hw,
+		[CLK_THM]		= &thm_clk.common.hw,
+		[CLK_CM3_I2C0]		= &cm3_i2c0.common.hw,
+		[CLK_CM3_I2C1]		= &cm3_i2c1.common.hw,
+		[CLK_CM4_SPI]		= &cm4_spi.common.hw,
+		[CLK_AON_I2C]		= &aon_i2c.common.hw,
+		[CLK_AVS]		= &avs_clk.common.hw,
+		[CLK_CA53_DAP]		= &ca53_dap.common.hw,
+		[CLK_CA53_TS]		= &ca53_ts.common.hw,
+		[CLK_DJTAG_TCK]		= &djtag_tck.common.hw,
+		[CLK_PMU]		= &pmu_clk.common.hw,
+		[CLK_PMU_26M]		= &pmu_26m.common.hw,
+		[CLK_DEBOUNCE]		= &debounce_clk.common.hw,
+		[CLK_OTG2_REF]		= &otg2_ref.common.hw,
+		[CLK_USB3_REF]		= &usb3_ref.common.hw,
+		[CLK_AP_AXI]		= &ap_axi.common.hw,
+	},
+	.num	= CLK_AON_PREDIV_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_aon_prediv_desc = {
+	.clk_clks	= sc9860_aon_prediv,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_aon_prediv),
+	.hw_clks	= &sc9860_aon_prediv_hws,
+};
+
+static SPRD_SC_GATE_CLK(usb3_eb,		"usb3-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(2), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(usb3_suspend,	"usb3-suspend", "ap-axi", 0x0,
+		     0x1000, BIT(3), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(usb3_ref_eb,	"usb3-ref-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(4), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(dma_eb,		"dma-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(5), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(sdio0_eb,		"sdio0-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(7), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(sdio1_eb,		"sdio1-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(8), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(sdio2_eb,		"sdio2-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(9), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(emmc_eb,		"emmc-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(10), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(rom_eb,		"rom-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(12), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(busmon_eb,		"busmon-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(13), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(cc63s_eb,		"cc63s-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(22), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(cc63p_eb,		"cc63p-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(23), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ce0_eb,		"ce0-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(24), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ce1_eb,		"ce1-eb",	"ap-axi", 0x0,
+		     0x1000, BIT(25), CLK_IGNORE_UNUSED, 0);
+
+static struct sprd_clk_common *sc9860_apahb_gate[] = {
+	/* address base is 0x20210000 */
+	&usb3_eb.common,
+	&usb3_suspend.common,
+	&usb3_ref_eb.common,
+	&dma_eb.common,
+	&sdio0_eb.common,
+	&sdio1_eb.common,
+	&sdio2_eb.common,
+	&emmc_eb.common,
+	&rom_eb.common,
+	&busmon_eb.common,
+	&cc63s_eb.common,
+	&cc63p_eb.common,
+	&ce0_eb.common,
+	&ce1_eb.common,
+};
+
+static struct clk_hw_onecell_data sc9860_apahb_gate_hws = {
+	.hws	= {
+		[CLK_USB3_EB]		= &usb3_eb.common.hw,
+		[CLK_USB3_SUSPEND_EB]	= &usb3_suspend.common.hw,
+		[CLK_USB3_REF_EB]	= &usb3_ref_eb.common.hw,
+		[CLK_DMA_EB]		= &dma_eb.common.hw,
+		[CLK_SDIO0_EB]		= &sdio0_eb.common.hw,
+		[CLK_SDIO1_EB]		= &sdio1_eb.common.hw,
+		[CLK_SDIO2_EB]		= &sdio2_eb.common.hw,
+		[CLK_EMMC_EB]		= &emmc_eb.common.hw,
+		[CLK_ROM_EB]		= &rom_eb.common.hw,
+		[CLK_BUSMON_EB]		= &busmon_eb.common.hw,
+		[CLK_CC63S_EB]		= &cc63s_eb.common.hw,
+		[CLK_CC63P_EB]		= &cc63p_eb.common.hw,
+		[CLK_CE0_EB]		= &ce0_eb.common.hw,
+		[CLK_CE1_EB]		= &ce1_eb.common.hw,
+	},
+	.num	= CLK_APAHB_GATE_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_apahb_gate_desc = {
+	.clk_clks	= sc9860_apahb_gate,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_apahb_gate),
+	.hw_clks	= &sc9860_apahb_gate_hws,
+};
+
+static SPRD_SC_GATE_CLK(avs_lit_eb,	"avs-lit-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(0), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(avs_big_eb,	"avs-big-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(1), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ap_intc5_eb,	"ap-intc5-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(2), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(gpio_eb,		"gpio-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(3), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(pwm0_eb,		"pwm0-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(4), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(pwm1_eb,		"pwm1-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(5), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(pwm2_eb,		"pwm2-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(6), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(pwm3_eb,		"pwm3-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(7), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(kpd_eb,		"kpd-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(8), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(aon_sys_eb,	"aon-sys-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(9), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ap_sys_eb,	"ap-sys-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(10), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(aon_tmr_eb,	"aon-tmr-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(11), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ap_tmr0_eb,	"ap-tmr0-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(12), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(efuse_eb,	"efuse-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(13), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(eic_eb,		"eic-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(14), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(pub1_reg_eb,	"pub1-reg-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(15), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(adi_eb,		"adi-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(16), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ap_intc0_eb,	"ap-intc0-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(17), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ap_intc1_eb,	"ap-intc1-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(18), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ap_intc2_eb,	"ap-intc2-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(19), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ap_intc3_eb,	"ap-intc3-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(20), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ap_intc4_eb,	"ap-intc4-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(21), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(splk_eb,		"splk-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(22), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(mspi_eb,		"mspi-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(23), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(pub0_reg_eb,	"pub0-reg-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(24), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(pin_eb,		"pin-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(25), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(aon_ckg_eb,	"aon-ckg-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(26), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(gpu_eb,		"gpu-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(27), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(apcpu_ts0_eb,	"apcpu-ts0-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(28), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(apcpu_ts1_eb,	"apcpu-ts1-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(29), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(dap_eb,		"dap-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(30), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(i2c_eb,		"i2c-eb",	"aon-apb", 0x0,
+		     0x1000, BIT(31), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(pmu_eb,		"pmu-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(0), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(thm_eb,		"thm-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(1), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(aux0_eb,		"aux0-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(2), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(aux1_eb,		"aux1-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(3), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(aux2_eb,		"aux2-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(4), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(probe_eb,		"probe-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(5), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(gpu0_avs_eb,	"gpu0-avs-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(6), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(gpu1_avs_eb,	"gpu1-avs-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(7), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(apcpu_wdg_eb,	"apcpu-wdg-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(8), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ap_tmr1_eb,	"ap-tmr1-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(9), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ap_tmr2_eb,	"ap-tmr2-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(10), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(disp_emc_eb,	"disp-emc-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(11), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(zip_emc_eb,	"zip-emc-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(12), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(gsp_emc_eb,	"gsp-emc-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(13), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(osc_aon_eb,	"osc-aon-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(14), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(lvds_trx_eb,	"lvds-trx-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(15), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(lvds_tcxo_eb,	"lvds-tcxo-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(16), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(mdar_eb,		"mdar-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(17), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(rtc4m0_cal_eb, "rtc4m0-cal-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(18), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(rct100m_cal_eb, "rct100m-cal-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(19), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(djtag_eb,		"djtag-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(20), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(mbox_eb,		"mbox-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(21), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(aon_dma_eb,	"aon-dma-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(22), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(dbg_emc_eb,	"dbg-emc-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(23), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(lvds_pll_div_en, "lvds-pll-div-en", "aon-apb", 0x4,
+		     0x1000, BIT(24), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(def_eb,		"def-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(25), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(aon_apb_rsv0,	"aon-apb-rsv0",	"aon-apb", 0x4,
+		     0x1000, BIT(26), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(orp_jtag_eb,	"orp-jtag-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(27), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(vsp_eb,		"vsp-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(28), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(cam_eb,		"cam-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(29), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(disp_eb,		"disp-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(30), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(dbg_axi_if_eb, "dbg-axi-if-eb",	"aon-apb", 0x4,
+		     0x1000, BIT(31), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(sdio0_2x_en,	"sdio0-2x-en",	"aon-apb", 0x13c,
+			       0x1000, BIT(2), 0, 0);
+static SPRD_SC_GATE_CLK(sdio1_2x_en,	"sdio1-2x-en",	"aon-apb", 0x13c,
+			       0x1000, BIT(4), 0, 0);
+static SPRD_SC_GATE_CLK(sdio2_2x_en,	"sdio2-2x-en",	"aon-apb", 0x13c,
+			       0x1000, BIT(6), 0, 0);
+static SPRD_SC_GATE_CLK(emmc_2x_en,	"emmc-2x-en",	"aon-apb", 0x13c,
+			       0x1000, BIT(9), 0, 0);
+
+static struct sprd_clk_common *sc9860_aon_gate[] = {
+	/* address base is 0x402e0000 */
+	&avs_lit_eb.common,
+	&avs_big_eb.common,
+	&ap_intc5_eb.common,
+	&gpio_eb.common,
+	&pwm0_eb.common,
+	&pwm1_eb.common,
+	&pwm2_eb.common,
+	&pwm3_eb.common,
+	&kpd_eb.common,
+	&aon_sys_eb.common,
+	&ap_sys_eb.common,
+	&aon_tmr_eb.common,
+	&ap_tmr0_eb.common,
+	&efuse_eb.common,
+	&eic_eb.common,
+	&pub1_reg_eb.common,
+	&adi_eb.common,
+	&ap_intc0_eb.common,
+	&ap_intc1_eb.common,
+	&ap_intc2_eb.common,
+	&ap_intc3_eb.common,
+	&ap_intc4_eb.common,
+	&splk_eb.common,
+	&mspi_eb.common,
+	&pub0_reg_eb.common,
+	&pin_eb.common,
+	&aon_ckg_eb.common,
+	&gpu_eb.common,
+	&apcpu_ts0_eb.common,
+	&apcpu_ts1_eb.common,
+	&dap_eb.common,
+	&i2c_eb.common,
+	&pmu_eb.common,
+	&thm_eb.common,
+	&aux0_eb.common,
+	&aux1_eb.common,
+	&aux2_eb.common,
+	&probe_eb.common,
+	&gpu0_avs_eb.common,
+	&gpu1_avs_eb.common,
+	&apcpu_wdg_eb.common,
+	&ap_tmr1_eb.common,
+	&ap_tmr2_eb.common,
+	&disp_emc_eb.common,
+	&zip_emc_eb.common,
+	&gsp_emc_eb.common,
+	&osc_aon_eb.common,
+	&lvds_trx_eb.common,
+	&lvds_tcxo_eb.common,
+	&mdar_eb.common,
+	&rtc4m0_cal_eb.common,
+	&rct100m_cal_eb.common,
+	&djtag_eb.common,
+	&mbox_eb.common,
+	&aon_dma_eb.common,
+	&dbg_emc_eb.common,
+	&lvds_pll_div_en.common,
+	&def_eb.common,
+	&aon_apb_rsv0.common,
+	&orp_jtag_eb.common,
+	&vsp_eb.common,
+	&cam_eb.common,
+	&disp_eb.common,
+	&dbg_axi_if_eb.common,
+	&sdio0_2x_en.common,
+	&sdio1_2x_en.common,
+	&sdio2_2x_en.common,
+	&emmc_2x_en.common,
+};
+
+static struct clk_hw_onecell_data sc9860_aon_gate_hws = {
+	.hws	= {
+		[CLK_AVS_LIT_EB]	= &avs_lit_eb.common.hw,
+		[CLK_AVS_BIG_EB]	= &avs_big_eb.common.hw,
+		[CLK_AP_INTC5_EB]	= &ap_intc5_eb.common.hw,
+		[CLK_GPIO_EB]		= &gpio_eb.common.hw,
+		[CLK_PWM0_EB]		= &pwm0_eb.common.hw,
+		[CLK_PWM1_EB]		= &pwm1_eb.common.hw,
+		[CLK_PWM2_EB]		= &pwm2_eb.common.hw,
+		[CLK_PWM3_EB]		= &pwm3_eb.common.hw,
+		[CLK_KPD_EB]		= &kpd_eb.common.hw,
+		[CLK_AON_SYS_EB]	= &aon_sys_eb.common.hw,
+		[CLK_AP_SYS_EB]		= &ap_sys_eb.common.hw,
+		[CLK_AON_TMR_EB]	= &aon_tmr_eb.common.hw,
+		[CLK_AP_TMR0_EB]	= &ap_tmr0_eb.common.hw,
+		[CLK_EFUSE_EB]		= &efuse_eb.common.hw,
+		[CLK_EIC_EB]		= &eic_eb.common.hw,
+		[CLK_PUB1_REG_EB]	= &pub1_reg_eb.common.hw,
+		[CLK_ADI_EB]		= &adi_eb.common.hw,
+		[CLK_AP_INTC0_EB]	= &ap_intc0_eb.common.hw,
+		[CLK_AP_INTC1_EB]	= &ap_intc1_eb.common.hw,
+		[CLK_AP_INTC2_EB]	= &ap_intc2_eb.common.hw,
+		[CLK_AP_INTC3_EB]	= &ap_intc3_eb.common.hw,
+		[CLK_AP_INTC4_EB]	= &ap_intc4_eb.common.hw,
+		[CLK_SPLK_EB]		= &splk_eb.common.hw,
+		[CLK_MSPI_EB]		= &mspi_eb.common.hw,
+		[CLK_PUB0_REG_EB]	= &pub0_reg_eb.common.hw,
+		[CLK_PIN_EB]		= &pin_eb.common.hw,
+		[CLK_AON_CKG_EB]	= &aon_ckg_eb.common.hw,
+		[CLK_GPU_EB]		= &gpu_eb.common.hw,
+		[CLK_APCPU_TS0_EB]	= &apcpu_ts0_eb.common.hw,
+		[CLK_APCPU_TS1_EB]	= &apcpu_ts1_eb.common.hw,
+		[CLK_DAP_EB]		= &dap_eb.common.hw,
+		[CLK_I2C_EB]		= &i2c_eb.common.hw,
+		[CLK_PMU_EB]		= &pmu_eb.common.hw,
+		[CLK_THM_EB]		= &thm_eb.common.hw,
+		[CLK_AUX0_EB]		= &aux0_eb.common.hw,
+		[CLK_AUX1_EB]		= &aux1_eb.common.hw,
+		[CLK_AUX2_EB]		= &aux2_eb.common.hw,
+		[CLK_PROBE_EB]		= &probe_eb.common.hw,
+		[CLK_GPU0_AVS_EB]	= &gpu0_avs_eb.common.hw,
+		[CLK_GPU1_AVS_EB]	= &gpu1_avs_eb.common.hw,
+		[CLK_APCPU_WDG_EB]	= &apcpu_wdg_eb.common.hw,
+		[CLK_AP_TMR1_EB]	= &ap_tmr1_eb.common.hw,
+		[CLK_AP_TMR2_EB]	= &ap_tmr2_eb.common.hw,
+		[CLK_DISP_EMC_EB]	= &disp_emc_eb.common.hw,
+		[CLK_ZIP_EMC_EB]	= &zip_emc_eb.common.hw,
+		[CLK_GSP_EMC_EB]	= &gsp_emc_eb.common.hw,
+		[CLK_OSC_AON_EB]	= &osc_aon_eb.common.hw,
+		[CLK_LVDS_TRX_EB]	= &lvds_trx_eb.common.hw,
+		[CLK_LVDS_TCXO_EB]	= &lvds_tcxo_eb.common.hw,
+		[CLK_MDAR_EB]		= &mdar_eb.common.hw,
+		[CLK_RTC4M0_CAL_EB]	= &rtc4m0_cal_eb.common.hw,
+		[CLK_RCT100M_CAL_EB]	= &rct100m_cal_eb.common.hw,
+		[CLK_DJTAG_EB]		= &djtag_eb.common.hw,
+		[CLK_MBOX_EB]		= &mbox_eb.common.hw,
+		[CLK_AON_DMA_EB]	= &aon_dma_eb.common.hw,
+		[CLK_DBG_EMC_EB]	= &dbg_emc_eb.common.hw,
+		[CLK_LVDS_PLL_DIV_EN]	= &lvds_pll_div_en.common.hw,
+		[CLK_DEF_EB]		= &def_eb.common.hw,
+		[CLK_AON_APB_RSV0]	= &aon_apb_rsv0.common.hw,
+		[CLK_ORP_JTAG_EB]	= &orp_jtag_eb.common.hw,
+		[CLK_VSP_EB]		= &vsp_eb.common.hw,
+		[CLK_CAM_EB]		= &cam_eb.common.hw,
+		[CLK_DISP_EB]		= &disp_eb.common.hw,
+		[CLK_DBG_AXI_IF_EB]	= &dbg_axi_if_eb.common.hw,
+		[CLK_SDIO0_2X_EN]	= &sdio0_2x_en.common.hw,
+		[CLK_SDIO1_2X_EN]	= &sdio1_2x_en.common.hw,
+		[CLK_SDIO2_2X_EN]	= &sdio2_2x_en.common.hw,
+		[CLK_EMMC_2X_EN]	= &emmc_2x_en.common.hw,
+	},
+	.num	= CLK_AON_GATE_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_aon_gate_desc = {
+	.clk_clks	= sc9860_aon_gate,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_aon_gate),
+	.hw_clks	= &sc9860_aon_gate_hws,
+};
+
+static const u8 mcu_table[] = { 0, 1, 2, 3, 4, 8 };
+static const char * const lit_mcu_parents[] = {	"ext-26m",	"twpll-512m",
+						"twpll-768m",	"ltepll0",
+						"twpll",	"mpll0" };
+static SPRD_COMP_CLK_TABLE(lit_mcu, "lit-mcu", lit_mcu_parents, 0x20,
+			   mcu_table, 0, 4, 4, 3, 0);
+
+static const char * const big_mcu_parents[] = {	"ext-26m",	"twpll-512m",
+						"twpll-768m",	"ltepll0",
+						"twpll",	"mpll1" };
+static SPRD_COMP_CLK_TABLE(big_mcu, "big-mcu", big_mcu_parents, 0x24,
+			   mcu_table, 0, 4, 4, 3, 0);
+
+static struct sprd_clk_common *sc9860_aonsecure_clk[] = {
+	/* address base is 0x40880000 */
+	&lit_mcu.common,
+	&big_mcu.common,
+};
+
+static struct clk_hw_onecell_data sc9860_aonsecure_clk_hws = {
+	.hws	= {
+		[CLK_LIT_MCU]		= &lit_mcu.common.hw,
+		[CLK_BIG_MCU]		= &big_mcu.common.hw,
+	},
+	.num	= CLK_AONSECURE_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_aonsecure_clk_desc = {
+	.clk_clks	= sc9860_aonsecure_clk,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_aonsecure_clk),
+	.hw_clks	= &sc9860_aonsecure_clk_hws,
+};
+
+static SPRD_SC_GATE_CLK(agcp_iis0_eb,	"agcp-iis0-eb",		"aon-apb",
+		     0x0, 0x100, BIT(0), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_iis1_eb,	"agcp-iis1-eb",		"aon-apb",
+		     0x0, 0x100, BIT(1), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_iis2_eb,	"agcp-iis2-eb",		"aon-apb",
+		     0x0, 0x100, BIT(2), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_iis3_eb,	"agcp-iis3-eb",		"aon-apb",
+		     0x0, 0x100, BIT(3), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_uart_eb,	"agcp-uart-eb",		"aon-apb",
+		     0x0, 0x100, BIT(4), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_dmacp_eb,	"agcp-dmacp-eb",	"aon-apb",
+		     0x0, 0x100, BIT(5), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_dmaap_eb,	"agcp-dmaap-eb",	"aon-apb",
+		     0x0, 0x100, BIT(6), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_arc48k_eb,	"agcp-arc48k-eb",	"aon-apb",
+		     0x0, 0x100, BIT(10), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_src44p1k_eb, "agcp-src44p1k-eb",	"aon-apb",
+		     0x0, 0x100, BIT(11), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_mcdt_eb,	"agcp-mcdt-eb",		"aon-apb",
+		     0x0, 0x100, BIT(12), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_vbcifd_eb,	"agcp-vbcifd-eb",	"aon-apb",
+		     0x0, 0x100, BIT(13), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_vbc_eb,	"agcp-vbc-eb",		"aon-apb",
+		     0x0, 0x100, BIT(14), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_spinlock_eb, "agcp-spinlock-eb",	"aon-apb",
+		     0x0, 0x100, BIT(15), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_icu_eb,	"agcp-icu-eb",		"aon-apb",
+		     0x0, 0x100, BIT(16), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(agcp_ap_ashb_eb, "agcp-ap-ashb-eb",	"aon-apb",
+		     0x0, 0x100, BIT(17), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_cp_ashb_eb, "agcp-cp-ashb-eb",	"aon-apb",
+		     0x0, 0x100, BIT(18), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_aud_eb,	"agcp-aud-eb",		"aon-apb",
+		     0x0, 0x100, BIT(19), 0, 0);
+static SPRD_SC_GATE_CLK(agcp_audif_eb,	"agcp-audif-eb",	"aon-apb",
+		     0x0, 0x100, BIT(20), 0, 0);
+
+static struct sprd_clk_common *sc9860_agcp_gate[] = {
+	/* address base is 0x415e0000 */
+	&agcp_iis0_eb.common,
+	&agcp_iis1_eb.common,
+	&agcp_iis2_eb.common,
+	&agcp_iis3_eb.common,
+	&agcp_uart_eb.common,
+	&agcp_dmacp_eb.common,
+	&agcp_dmaap_eb.common,
+	&agcp_arc48k_eb.common,
+	&agcp_src44p1k_eb.common,
+	&agcp_mcdt_eb.common,
+	&agcp_vbcifd_eb.common,
+	&agcp_vbc_eb.common,
+	&agcp_spinlock_eb.common,
+	&agcp_icu_eb.common,
+	&agcp_ap_ashb_eb.common,
+	&agcp_cp_ashb_eb.common,
+	&agcp_aud_eb.common,
+	&agcp_audif_eb.common,
+};
+
+static struct clk_hw_onecell_data sc9860_agcp_gate_hws = {
+	.hws	= {
+		[CLK_AGCP_IIS0_EB]	= &agcp_iis0_eb.common.hw,
+		[CLK_AGCP_IIS1_EB]	= &agcp_iis1_eb.common.hw,
+		[CLK_AGCP_IIS2_EB]	= &agcp_iis2_eb.common.hw,
+		[CLK_AGCP_IIS3_EB]	= &agcp_iis3_eb.common.hw,
+		[CLK_AGCP_UART_EB]	= &agcp_uart_eb.common.hw,
+		[CLK_AGCP_DMACP_EB]	= &agcp_dmacp_eb.common.hw,
+		[CLK_AGCP_DMAAP_EB]	= &agcp_dmaap_eb.common.hw,
+		[CLK_AGCP_ARC48K_EB]	= &agcp_arc48k_eb.common.hw,
+		[CLK_AGCP_SRC44P1K_EB]	= &agcp_src44p1k_eb.common.hw,
+		[CLK_AGCP_MCDT_EB]	= &agcp_mcdt_eb.common.hw,
+		[CLK_AGCP_VBCIFD_EB]	= &agcp_vbcifd_eb.common.hw,
+		[CLK_AGCP_VBC_EB]	= &agcp_vbc_eb.common.hw,
+		[CLK_AGCP_SPINLOCK_EB]	= &agcp_spinlock_eb.common.hw,
+		[CLK_AGCP_ICU_EB]	= &agcp_icu_eb.common.hw,
+		[CLK_AGCP_AP_ASHB_EB]	= &agcp_ap_ashb_eb.common.hw,
+		[CLK_AGCP_CP_ASHB_EB]	= &agcp_cp_ashb_eb.common.hw,
+		[CLK_AGCP_AUD_EB]	= &agcp_aud_eb.common.hw,
+		[CLK_AGCP_AUDIF_EB]	= &agcp_audif_eb.common.hw,
+	},
+	.num	= CLK_AGCP_GATE_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_agcp_gate_desc = {
+	.clk_clks	= sc9860_agcp_gate,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_agcp_gate),
+	.hw_clks	= &sc9860_agcp_gate_hws,
+};
+
+static const char * const gpu_parents[] = { "twpll-512m",
+					    "twpll-768m",
+					    "gpll" };
+static SPRD_COMP_CLK(gpu_clk,	"gpu",	gpu_parents, 0x20,
+		     0, 2, 8, 4, 0);
+
+static struct sprd_clk_common *sc9860_gpu_clk[] = {
+	/* address base is 0x60200000 */
+	&gpu_clk.common,
+};
+
+static struct clk_hw_onecell_data sc9860_gpu_clk_hws = {
+	.hws	= {
+		[CLK_GPU]	= &gpu_clk.common.hw,
+	},
+	.num	= CLK_GPU_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_gpu_clk_desc = {
+	.clk_clks	= sc9860_gpu_clk,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_gpu_clk),
+	.hw_clks	= &sc9860_gpu_clk_hws,
+};
+
+static const char * const ahb_parents[] = { "ext-26m", "twpll-96m",
+					    "twpll-128m", "twpll-153m6" };
+static SPRD_MUX_CLK(ahb_vsp, "ahb-vsp", ahb_parents, 0x20,
+		    0, 2, SC9860_MUX_FLAG);
+
+static const char * const vsp_parents[] = {	"twpll-76m8",	"twpll-128m",
+						"twpll-256m",	"twpll-307m2",
+						"twpll-384m" };
+static SPRD_COMP_CLK(vsp_clk, "vsp", vsp_parents, 0x24, 0, 3, 8, 2, 0);
+
+static const char * const dispc_parents[] = {	"twpll-76m8",	"twpll-128m",
+						"twpll-256m",	"twpll-307m2" };
+static SPRD_COMP_CLK(vsp_enc, "vsp-enc", dispc_parents, 0x28, 0, 2, 8, 2, 0);
+
+static const char * const vpp_parents[] = { "twpll-96m", "twpll-153m6",
+					    "twpll-192m", "twpll-256m" };
+static SPRD_MUX_CLK(vpp_clk, "vpp", vpp_parents, 0x2c,
+		    0, 2, SC9860_MUX_FLAG);
+static const char * const vsp_26m_parents[] = { "ext-26m" };
+static SPRD_MUX_CLK(vsp_26m, "vsp-26m", vsp_26m_parents, 0x30,
+		    0, 1, SC9860_MUX_FLAG);
+
+static struct sprd_clk_common *sc9860_vsp_clk[] = {
+	/* address base is 0x61000000 */
+	&ahb_vsp.common,
+	&vsp_clk.common,
+	&vsp_enc.common,
+	&vpp_clk.common,
+	&vsp_26m.common,
+};
+
+static struct clk_hw_onecell_data sc9860_vsp_clk_hws = {
+	.hws	= {
+		[CLK_AHB_VSP]	= &ahb_vsp.common.hw,
+		[CLK_VSP]	= &vsp_clk.common.hw,
+		[CLK_VSP_ENC]	= &vsp_enc.common.hw,
+		[CLK_VPP]	= &vpp_clk.common.hw,
+		[CLK_VSP_26M]	= &vsp_26m.common.hw,
+	},
+	.num	= CLK_VSP_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_vsp_clk_desc = {
+	.clk_clks	= sc9860_vsp_clk,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_vsp_clk),
+	.hw_clks	= &sc9860_vsp_clk_hws,
+};
+
+static SPRD_SC_GATE_CLK(vsp_dec_eb,	"vsp-dec-eb",	"ahb-vsp", 0x0,
+		     0x1000, BIT(0), 0, 0);
+static SPRD_SC_GATE_CLK(vsp_ckg_eb,	"vsp-ckg-eb",	"ahb-vsp", 0x0,
+		     0x1000, BIT(1), 0, 0);
+static SPRD_SC_GATE_CLK(vsp_mmu_eb,	"vsp-mmu-eb",	"ahb-vsp", 0x0,
+		     0x1000, BIT(2), 0, 0);
+static SPRD_SC_GATE_CLK(vsp_enc_eb,	"vsp-enc-eb",	"ahb-vsp", 0x0,
+		     0x1000, BIT(3), 0, 0);
+static SPRD_SC_GATE_CLK(vpp_eb,		"vpp-eb",	"ahb-vsp", 0x0,
+		     0x1000, BIT(4), 0, 0);
+static SPRD_SC_GATE_CLK(vsp_26m_eb,	"vsp-26m-eb",	"ahb-vsp", 0x0,
+		     0x1000, BIT(5), 0, 0);
+static SPRD_GATE_CLK(vsp_axi_gate,	"vsp-axi-gate",	"ahb-vsp", 0x8,
+		     BIT(0), 0, 0);
+static SPRD_GATE_CLK(vsp_enc_gate,	"vsp-enc-gate",	"ahb-vsp", 0x8,
+		     BIT(1), 0, 0);
+static SPRD_GATE_CLK(vpp_axi_gate,	"vpp-axi-gate",	"ahb-vsp", 0x8,
+		     BIT(2), 0, 0);
+static SPRD_GATE_CLK(vsp_bm_gate,	"vsp-bm-gate",	"ahb-vsp", 0x8,
+		     BIT(8), 0, 0);
+static SPRD_GATE_CLK(vsp_enc_bm_gate, "vsp-enc-bm-gate", "ahb-vsp", 0x8,
+		     BIT(9), 0, 0);
+static SPRD_GATE_CLK(vpp_bm_gate,	"vpp-bm-gate",	"ahb-vsp", 0x8,
+		     BIT(10), 0, 0);
+
+static struct sprd_clk_common *sc9860_vsp_gate[] = {
+	/* address base is 0x61100000 */
+	&vsp_dec_eb.common,
+	&vsp_ckg_eb.common,
+	&vsp_mmu_eb.common,
+	&vsp_enc_eb.common,
+	&vpp_eb.common,
+	&vsp_26m_eb.common,
+	&vsp_axi_gate.common,
+	&vsp_enc_gate.common,
+	&vpp_axi_gate.common,
+	&vsp_bm_gate.common,
+	&vsp_enc_bm_gate.common,
+	&vpp_bm_gate.common,
+};
+
+static struct clk_hw_onecell_data sc9860_vsp_gate_hws = {
+	.hws	= {
+		[CLK_VSP_DEC_EB]	= &vsp_dec_eb.common.hw,
+		[CLK_VSP_CKG_EB]	= &vsp_ckg_eb.common.hw,
+		[CLK_VSP_MMU_EB]	= &vsp_mmu_eb.common.hw,
+		[CLK_VSP_ENC_EB]	= &vsp_enc_eb.common.hw,
+		[CLK_VPP_EB]		= &vpp_eb.common.hw,
+		[CLK_VSP_26M_EB]	= &vsp_26m_eb.common.hw,
+		[CLK_VSP_AXI_GATE]	= &vsp_axi_gate.common.hw,
+		[CLK_VSP_ENC_GATE]	= &vsp_enc_gate.common.hw,
+		[CLK_VPP_AXI_GATE]	= &vpp_axi_gate.common.hw,
+		[CLK_VSP_BM_GATE]	= &vsp_bm_gate.common.hw,
+		[CLK_VSP_ENC_BM_GATE]	= &vsp_enc_bm_gate.common.hw,
+		[CLK_VPP_BM_GATE]	= &vpp_bm_gate.common.hw,
+	},
+	.num	= CLK_VSP_GATE_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_vsp_gate_desc = {
+	.clk_clks	= sc9860_vsp_gate,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_vsp_gate),
+	.hw_clks	= &sc9860_vsp_gate_hws,
+};
+
+static SPRD_MUX_CLK(ahb_cam, "ahb-cam", ahb_parents, 0x20,
+		    0, 2, SC9860_MUX_FLAG);
+static const char * const sensor_parents[] = {	"ext-26m",	"twpll-48m",
+						"twpll-76m8",	"twpll-96m" };
+static SPRD_COMP_CLK(sensor0_clk, "sensor0", sensor_parents, 0x24,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(sensor1_clk, "sensor1", sensor_parents, 0x28,
+		     0, 2, 8, 3, 0);
+static SPRD_COMP_CLK(sensor2_clk, "sensor2", sensor_parents, 0x2c,
+		     0, 2, 8, 3, 0);
+static SPRD_GATE_CLK(mipi_csi0_eb, "mipi-csi0-eb", "ahb-cam", 0x4c,
+		     BIT(16), 0, 0);
+static SPRD_GATE_CLK(mipi_csi1_eb, "mipi-csi1-eb", "ahb-cam", 0x50,
+		     BIT(16), 0, 0);
+
+static struct sprd_clk_common *sc9860_cam_clk[] = {
+	/* address base is 0x62000000 */
+	&ahb_cam.common,
+	&sensor0_clk.common,
+	&sensor1_clk.common,
+	&sensor2_clk.common,
+	&mipi_csi0_eb.common,
+	&mipi_csi1_eb.common,
+};
+
+static struct clk_hw_onecell_data sc9860_cam_clk_hws = {
+	.hws	= {
+		[CLK_AHB_CAM]		= &ahb_cam.common.hw,
+		[CLK_SENSOR0]		= &sensor0_clk.common.hw,
+		[CLK_SENSOR1]		= &sensor1_clk.common.hw,
+		[CLK_SENSOR2]		= &sensor2_clk.common.hw,
+		[CLK_MIPI_CSI0_EB]	= &mipi_csi0_eb.common.hw,
+		[CLK_MIPI_CSI1_EB]	= &mipi_csi1_eb.common.hw,
+	},
+	.num	= CLK_CAM_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_cam_clk_desc = {
+	.clk_clks	= sc9860_cam_clk,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_cam_clk),
+	.hw_clks	= &sc9860_cam_clk_hws,
+};
+
+static SPRD_SC_GATE_CLK(dcam0_eb,		"dcam0-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(0), 0, 0);
+static SPRD_SC_GATE_CLK(dcam1_eb,		"dcam1-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(1), 0, 0);
+static SPRD_SC_GATE_CLK(isp0_eb,		"isp0-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(2), 0, 0);
+static SPRD_SC_GATE_CLK(csi0_eb,		"csi0-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(3), 0, 0);
+static SPRD_SC_GATE_CLK(csi1_eb,		"csi1-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(4), 0, 0);
+static SPRD_SC_GATE_CLK(jpg0_eb,		"jpg0-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(5), 0, 0);
+static SPRD_SC_GATE_CLK(jpg1_eb,		"jpg1-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(6), 0, 0);
+static SPRD_SC_GATE_CLK(cam_ckg_eb,	"cam-ckg-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(7), 0, 0);
+static SPRD_SC_GATE_CLK(cam_mmu_eb,	"cam-mmu-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(8), 0, 0);
+static SPRD_SC_GATE_CLK(isp1_eb,		"isp1-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(9), 0, 0);
+static SPRD_SC_GATE_CLK(cpp_eb,		"cpp-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(10), 0, 0);
+static SPRD_SC_GATE_CLK(mmu_pf_eb,		"mmu-pf-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(11), 0, 0);
+static SPRD_SC_GATE_CLK(isp2_eb,		"isp2-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(12), 0, 0);
+static SPRD_SC_GATE_CLK(dcam2isp_if_eb, "dcam2isp-if-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(13), 0, 0);
+static SPRD_SC_GATE_CLK(isp2dcam_if_eb, "isp2dcam-if-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(14), 0, 0);
+static SPRD_SC_GATE_CLK(isp_lclk_eb,	"isp-lclk-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(15), 0, 0);
+static SPRD_SC_GATE_CLK(isp_iclk_eb,	"isp-iclk-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(16), 0, 0);
+static SPRD_SC_GATE_CLK(isp_mclk_eb,	"isp-mclk-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(17), 0, 0);
+static SPRD_SC_GATE_CLK(isp_pclk_eb,	"isp-pclk-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(18), 0, 0);
+static SPRD_SC_GATE_CLK(isp_isp2dcam_eb, "isp-isp2dcam-eb", "ahb-cam", 0x0,
+		     0x1000, BIT(19), 0, 0);
+static SPRD_SC_GATE_CLK(dcam0_if_eb,	"dcam0-if-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(20), 0, 0);
+static SPRD_SC_GATE_CLK(clk26m_if_eb,	"clk26m-if-eb",	"ahb-cam", 0x0,
+		     0x1000, BIT(21), 0, 0);
+static SPRD_GATE_CLK(cphy0_gate, "cphy0-gate", "ahb-cam", 0x8,
+		     BIT(0), 0, 0);
+static SPRD_GATE_CLK(mipi_csi0_gate, "mipi-csi0-gate", "ahb-cam", 0x8,
+		     BIT(1), 0, 0);
+static SPRD_GATE_CLK(cphy1_gate,	"cphy1-gate",	"ahb-cam", 0x8,
+		     BIT(2), 0, 0);
+static SPRD_GATE_CLK(mipi_csi1,		"mipi-csi1",	"ahb-cam", 0x8,
+		     BIT(3), 0, 0);
+static SPRD_GATE_CLK(dcam0_axi_gate,	"dcam0-axi-gate", "ahb-cam", 0x8,
+		     BIT(4), 0, 0);
+static SPRD_GATE_CLK(dcam1_axi_gate,	"dcam1-axi-gate", "ahb-cam", 0x8,
+		     BIT(5), 0, 0);
+static SPRD_GATE_CLK(sensor0_gate,	"sensor0-gate",	"ahb-cam", 0x8,
+		     BIT(6), 0, 0);
+static SPRD_GATE_CLK(sensor1_gate,	"sensor1-gate",	"ahb-cam", 0x8,
+		     BIT(7), 0, 0);
+static SPRD_GATE_CLK(jpg0_axi_gate,	"jpg0-axi-gate", "ahb-cam", 0x8,
+		     BIT(8), 0, 0);
+static SPRD_GATE_CLK(gpg1_axi_gate,	"gpg1-axi-gate", "ahb-cam", 0x8,
+		     BIT(9), 0, 0);
+static SPRD_GATE_CLK(isp0_axi_gate,	"isp0-axi-gate", "ahb-cam", 0x8,
+		     BIT(10), 0, 0);
+static SPRD_GATE_CLK(isp1_axi_gate,	"isp1-axi-gate", "ahb-cam", 0x8,
+		     BIT(11), 0, 0);
+static SPRD_GATE_CLK(isp2_axi_gate,	"isp2-axi-gate", "ahb-cam", 0x8,
+		     BIT(12), 0, 0);
+static SPRD_GATE_CLK(cpp_axi_gate,	"cpp-axi-gate",	"ahb-cam", 0x8,
+		     BIT(13), 0, 0);
+static SPRD_GATE_CLK(d0_if_axi_gate,	"d0-if-axi-gate", "ahb-cam", 0x8,
+		     BIT(14), 0, 0);
+static SPRD_GATE_CLK(d2i_if_axi_gate, "d2i-if-axi-gate", "ahb-cam", 0x8,
+		     BIT(15), 0, 0);
+static SPRD_GATE_CLK(i2d_if_axi_gate, "i2d-if-axi-gate", "ahb-cam", 0x8,
+		     BIT(16), 0, 0);
+static SPRD_GATE_CLK(spare_axi_gate, "spare-axi-gate",	"ahb-cam", 0x8,
+		     BIT(17), 0, 0);
+static SPRD_GATE_CLK(sensor2_gate, "sensor2-gate",	"ahb-cam", 0x8,
+		     BIT(18), 0, 0);
+static SPRD_SC_GATE_CLK(d0if_in_d_en, "d0if-in-d-en", "ahb-cam", 0x28,
+		     0x1000, BIT(0), 0, 0);
+static SPRD_SC_GATE_CLK(d1if_in_d_en, "d1if-in-d-en", "ahb-cam", 0x28,
+		     0x1000, BIT(1), 0, 0);
+static SPRD_SC_GATE_CLK(d0if_in_d2i_en, "d0if-in-d2i-en", "ahb-cam", 0x28,
+		     0x1000, BIT(2), 0, 0);
+static SPRD_SC_GATE_CLK(d1if_in_d2i_en, "d1if-in-d2i-en",	"ahb-cam", 0x28,
+		     0x1000, BIT(3), 0, 0);
+static SPRD_SC_GATE_CLK(ia_in_d2i_en, "ia-in-d2i-en",	"ahb-cam", 0x28,
+		     0x1000, BIT(4), 0, 0);
+static SPRD_SC_GATE_CLK(ib_in_d2i_en,	"ib-in-d2i-en",	"ahb-cam", 0x28,
+		     0x1000, BIT(5), 0, 0);
+static SPRD_SC_GATE_CLK(ic_in_d2i_en,	"ic-in-d2i-en",	"ahb-cam", 0x28,
+		     0x1000, BIT(6), 0, 0);
+static SPRD_SC_GATE_CLK(ia_in_i_en,	"ia-in-i-en",	"ahb-cam", 0x28,
+		     0x1000, BIT(7), 0, 0);
+static SPRD_SC_GATE_CLK(ib_in_i_en,	"ib-in-i-en",	"ahb-cam", 0x28,
+		     0x1000, BIT(8), 0, 0);
+static SPRD_SC_GATE_CLK(ic_in_i_en,	"ic-in-i-en",	"ahb-cam", 0x28,
+		     0x1000, BIT(9), 0, 0);
+
+static struct sprd_clk_common *sc9860_cam_gate[] = {
+	/* address base is 0x62100000 */
+	&dcam0_eb.common,
+	&dcam1_eb.common,
+	&isp0_eb.common,
+	&csi0_eb.common,
+	&csi1_eb.common,
+	&jpg0_eb.common,
+	&jpg1_eb.common,
+	&cam_ckg_eb.common,
+	&cam_mmu_eb.common,
+	&isp1_eb.common,
+	&cpp_eb.common,
+	&mmu_pf_eb.common,
+	&isp2_eb.common,
+	&dcam2isp_if_eb.common,
+	&isp2dcam_if_eb.common,
+	&isp_lclk_eb.common,
+	&isp_iclk_eb.common,
+	&isp_mclk_eb.common,
+	&isp_pclk_eb.common,
+	&isp_isp2dcam_eb.common,
+	&dcam0_if_eb.common,
+	&clk26m_if_eb.common,
+	&cphy0_gate.common,
+	&mipi_csi0_gate.common,
+	&cphy1_gate.common,
+	&mipi_csi1.common,
+	&dcam0_axi_gate.common,
+	&dcam1_axi_gate.common,
+	&sensor0_gate.common,
+	&sensor1_gate.common,
+	&jpg0_axi_gate.common,
+	&gpg1_axi_gate.common,
+	&isp0_axi_gate.common,
+	&isp1_axi_gate.common,
+	&isp2_axi_gate.common,
+	&cpp_axi_gate.common,
+	&d0_if_axi_gate.common,
+	&d2i_if_axi_gate.common,
+	&i2d_if_axi_gate.common,
+	&spare_axi_gate.common,
+	&sensor2_gate.common,
+	&d0if_in_d_en.common,
+	&d1if_in_d_en.common,
+	&d0if_in_d2i_en.common,
+	&d1if_in_d2i_en.common,
+	&ia_in_d2i_en.common,
+	&ib_in_d2i_en.common,
+	&ic_in_d2i_en.common,
+	&ia_in_i_en.common,
+	&ib_in_i_en.common,
+	&ic_in_i_en.common,
+};
+
+static struct clk_hw_onecell_data sc9860_cam_gate_hws = {
+	.hws	= {
+		[CLK_DCAM0_EB]		= &dcam0_eb.common.hw,
+		[CLK_DCAM1_EB]		= &dcam1_eb.common.hw,
+		[CLK_ISP0_EB]		= &isp0_eb.common.hw,
+		[CLK_CSI0_EB]		= &csi0_eb.common.hw,
+		[CLK_CSI1_EB]		= &csi1_eb.common.hw,
+		[CLK_JPG0_EB]		= &jpg0_eb.common.hw,
+		[CLK_JPG1_EB]		= &jpg1_eb.common.hw,
+		[CLK_CAM_CKG_EB]	= &cam_ckg_eb.common.hw,
+		[CLK_CAM_MMU_EB]	= &cam_mmu_eb.common.hw,
+		[CLK_ISP1_EB]		= &isp1_eb.common.hw,
+		[CLK_CPP_EB]		= &cpp_eb.common.hw,
+		[CLK_MMU_PF_EB]		= &mmu_pf_eb.common.hw,
+		[CLK_ISP2_EB]		= &isp2_eb.common.hw,
+		[CLK_DCAM2ISP_IF_EB]	= &dcam2isp_if_eb.common.hw,
+		[CLK_ISP2DCAM_IF_EB]	= &isp2dcam_if_eb.common.hw,
+		[CLK_ISP_LCLK_EB]	= &isp_lclk_eb.common.hw,
+		[CLK_ISP_ICLK_EB]	= &isp_iclk_eb.common.hw,
+		[CLK_ISP_MCLK_EB]	= &isp_mclk_eb.common.hw,
+		[CLK_ISP_PCLK_EB]	= &isp_pclk_eb.common.hw,
+		[CLK_ISP_ISP2DCAM_EB]	= &isp_isp2dcam_eb.common.hw,
+		[CLK_DCAM0_IF_EB]	= &dcam0_if_eb.common.hw,
+		[CLK_CLK26M_IF_EB]	= &clk26m_if_eb.common.hw,
+		[CLK_CPHY0_GATE]	= &cphy0_gate.common.hw,
+		[CLK_MIPI_CSI0_GATE]	= &mipi_csi0_gate.common.hw,
+		[CLK_CPHY1_GATE]	= &cphy1_gate.common.hw,
+		[CLK_MIPI_CSI1]		= &mipi_csi1.common.hw,
+		[CLK_DCAM0_AXI_GATE]	= &dcam0_axi_gate.common.hw,
+		[CLK_DCAM1_AXI_GATE]	= &dcam1_axi_gate.common.hw,
+		[CLK_SENSOR0_GATE]	= &sensor0_gate.common.hw,
+		[CLK_SENSOR1_GATE]	= &sensor1_gate.common.hw,
+		[CLK_JPG0_AXI_GATE]	= &jpg0_axi_gate.common.hw,
+		[CLK_GPG1_AXI_GATE]	= &gpg1_axi_gate.common.hw,
+		[CLK_ISP0_AXI_GATE]	= &isp0_axi_gate.common.hw,
+		[CLK_ISP1_AXI_GATE]	= &isp1_axi_gate.common.hw,
+		[CLK_ISP2_AXI_GATE]	= &isp2_axi_gate.common.hw,
+		[CLK_CPP_AXI_GATE]	= &cpp_axi_gate.common.hw,
+		[CLK_D0_IF_AXI_GATE]	= &d0_if_axi_gate.common.hw,
+		[CLK_D2I_IF_AXI_GATE]	= &d2i_if_axi_gate.common.hw,
+		[CLK_I2D_IF_AXI_GATE]	= &i2d_if_axi_gate.common.hw,
+		[CLK_SPARE_AXI_GATE]	= &spare_axi_gate.common.hw,
+		[CLK_SENSOR2_GATE]	= &sensor2_gate.common.hw,
+		[CLK_D0IF_IN_D_EN]	= &d0if_in_d_en.common.hw,
+		[CLK_D1IF_IN_D_EN]	= &d1if_in_d_en.common.hw,
+		[CLK_D0IF_IN_D2I_EN]	= &d0if_in_d2i_en.common.hw,
+		[CLK_D1IF_IN_D2I_EN]	= &d1if_in_d2i_en.common.hw,
+		[CLK_IA_IN_D2I_EN]	= &ia_in_d2i_en.common.hw,
+		[CLK_IB_IN_D2I_EN]	= &ib_in_d2i_en.common.hw,
+		[CLK_IC_IN_D2I_EN]	= &ic_in_d2i_en.common.hw,
+		[CLK_IA_IN_I_EN]	= &ia_in_i_en.common.hw,
+		[CLK_IB_IN_I_EN]	= &ib_in_i_en.common.hw,
+		[CLK_IC_IN_I_EN]	= &ic_in_i_en.common.hw,
+	},
+	.num	= CLK_CAM_GATE_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_cam_gate_desc = {
+	.clk_clks	= sc9860_cam_gate,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_cam_gate),
+	.hw_clks	= &sc9860_cam_gate_hws,
+};
+
+static SPRD_MUX_CLK(ahb_disp, "ahb-disp", ahb_parents, 0x20,
+		    0, 2, SC9860_MUX_FLAG);
+static SPRD_COMP_CLK(dispc0_dpi, "dispc0-dpi", dispc_parents,	0x34,
+		     0, 2, 8, 2, 0);
+static SPRD_COMP_CLK(dispc1_dpi, "dispc1-dpi", dispc_parents,	0x40,
+		     0, 2, 8, 2, 0);
+
+static struct sprd_clk_common *sc9860_disp_clk[] = {
+	/* address base is 0x63000000 */
+	&ahb_disp.common,
+	&dispc0_dpi.common,
+	&dispc1_dpi.common,
+};
+
+static struct clk_hw_onecell_data sc9860_disp_clk_hws = {
+	.hws	= {
+		[CLK_AHB_DISP]		= &ahb_disp.common.hw,
+		[CLK_DISPC0_DPI]	= &dispc0_dpi.common.hw,
+		[CLK_DISPC1_DPI]	= &dispc1_dpi.common.hw,
+	},
+	.num	= CLK_DISP_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_disp_clk_desc = {
+	.clk_clks	= sc9860_disp_clk,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_disp_clk),
+	.hw_clks	= &sc9860_disp_clk_hws,
+};
+
+static SPRD_SC_GATE_CLK(dispc0_eb,	"dispc0-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(0), 0, 0);
+static SPRD_SC_GATE_CLK(dispc1_eb,	"dispc1-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(1), 0, 0);
+static SPRD_SC_GATE_CLK(dispc_mmu_eb,	"dispc-mmu-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(2), 0, 0);
+static SPRD_SC_GATE_CLK(gsp0_eb,		"gsp0-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(3), 0, 0);
+static SPRD_SC_GATE_CLK(gsp1_eb,		"gsp1-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(4), 0, 0);
+static SPRD_SC_GATE_CLK(gsp0_mmu_eb,	"gsp0-mmu-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(5), 0, 0);
+static SPRD_SC_GATE_CLK(gsp1_mmu_eb,	"gsp1-mmu-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(6), 0, 0);
+static SPRD_SC_GATE_CLK(dsi0_eb,		"dsi0-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(7), 0, 0);
+static SPRD_SC_GATE_CLK(dsi1_eb,		"dsi1-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(8), 0, 0);
+static SPRD_SC_GATE_CLK(disp_ckg_eb,	"disp-ckg-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(9), 0, 0);
+static SPRD_SC_GATE_CLK(disp_gpu_eb,	"disp-gpu-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(10), 0, 0);
+static SPRD_SC_GATE_CLK(gpu_mtx_eb,	"gpu-mtx-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(13), 0, 0);
+static SPRD_SC_GATE_CLK(gsp_mtx_eb,	"gsp-mtx-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(14), 0, 0);
+static SPRD_SC_GATE_CLK(tmc_mtx_eb,	"tmc-mtx-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(15), 0, 0);
+static SPRD_SC_GATE_CLK(dispc_mtx_eb,	"dispc-mtx-eb",	"ahb-disp", 0x0,
+		     0x1000, BIT(16), 0, 0);
+static SPRD_GATE_CLK(dphy0_gate,	"dphy0-gate",	"ahb-disp", 0x8,
+		     BIT(0), 0, 0);
+static SPRD_GATE_CLK(dphy1_gate,	"dphy1-gate",	"ahb-disp", 0x8,
+		     BIT(1), 0, 0);
+static SPRD_GATE_CLK(gsp0_a_gate,	"gsp0-a-gate",	"ahb-disp", 0x8,
+		     BIT(2), 0, 0);
+static SPRD_GATE_CLK(gsp1_a_gate,	"gsp1-a-gate",	"ahb-disp", 0x8,
+		     BIT(3), 0, 0);
+static SPRD_GATE_CLK(gsp0_f_gate,	"gsp0-f-gate",	"ahb-disp", 0x8,
+		     BIT(4), 0, 0);
+static SPRD_GATE_CLK(gsp1_f_gate,	"gsp1-f-gate",	"ahb-disp", 0x8,
+		     BIT(5), 0, 0);
+static SPRD_GATE_CLK(d_mtx_f_gate,	"d-mtx-f-gate",	"ahb-disp", 0x8,
+		     BIT(6), 0, 0);
+static SPRD_GATE_CLK(d_mtx_a_gate,	"d-mtx-a-gate",	"ahb-disp", 0x8,
+		     BIT(7), 0, 0);
+static SPRD_GATE_CLK(d_noc_f_gate,	"d-noc-f-gate",	"ahb-disp", 0x8,
+		     BIT(8), 0, 0);
+static SPRD_GATE_CLK(d_noc_a_gate,	"d-noc-a-gate",	"ahb-disp", 0x8,
+		     BIT(9), 0, 0);
+static SPRD_GATE_CLK(gsp_mtx_f_gate, "gsp-mtx-f-gate", "ahb-disp",  0x8,
+		     BIT(10), 0, 0);
+static SPRD_GATE_CLK(gsp_mtx_a_gate, "gsp-mtx-a-gate", "ahb-disp",  0x8,
+		     BIT(11), 0, 0);
+static SPRD_GATE_CLK(gsp_noc_f_gate, "gsp-noc-f-gate", "ahb-disp",  0x8,
+		     BIT(12), 0, 0);
+static SPRD_GATE_CLK(gsp_noc_a_gate, "gsp-noc-a-gate", "ahb-disp",  0x8,
+		     BIT(13), 0, 0);
+static SPRD_GATE_CLK(dispm0idle_gate, "dispm0idle-gate", "ahb-disp", 0x8,
+		     BIT(14), 0, 0);
+static SPRD_GATE_CLK(gspm0idle_gate, "gspm0idle-gate", "ahb-disp",  0x8,
+		     BIT(15), 0, 0);
+
+static struct sprd_clk_common *sc9860_disp_gate[] = {
+	/* address base is 0x63100000 */
+	&dispc0_eb.common,
+	&dispc1_eb.common,
+	&dispc_mmu_eb.common,
+	&gsp0_eb.common,
+	&gsp1_eb.common,
+	&gsp0_mmu_eb.common,
+	&gsp1_mmu_eb.common,
+	&dsi0_eb.common,
+	&dsi1_eb.common,
+	&disp_ckg_eb.common,
+	&disp_gpu_eb.common,
+	&gpu_mtx_eb.common,
+	&gsp_mtx_eb.common,
+	&tmc_mtx_eb.common,
+	&dispc_mtx_eb.common,
+	&dphy0_gate.common,
+	&dphy1_gate.common,
+	&gsp0_a_gate.common,
+	&gsp1_a_gate.common,
+	&gsp0_f_gate.common,
+	&gsp1_f_gate.common,
+	&d_mtx_f_gate.common,
+	&d_mtx_a_gate.common,
+	&d_noc_f_gate.common,
+	&d_noc_a_gate.common,
+	&gsp_mtx_f_gate.common,
+	&gsp_mtx_a_gate.common,
+	&gsp_noc_f_gate.common,
+	&gsp_noc_a_gate.common,
+	&dispm0idle_gate.common,
+	&gspm0idle_gate.common,
+};
+
+static struct clk_hw_onecell_data sc9860_disp_gate_hws = {
+	.hws	= {
+		[CLK_DISPC0_EB]		= &dispc0_eb.common.hw,
+		[CLK_DISPC1_EB]		= &dispc1_eb.common.hw,
+		[CLK_DISPC_MMU_EB]	= &dispc_mmu_eb.common.hw,
+		[CLK_GSP0_EB]		= &gsp0_eb.common.hw,
+		[CLK_GSP1_EB]		= &gsp1_eb.common.hw,
+		[CLK_GSP0_MMU_EB]	= &gsp0_mmu_eb.common.hw,
+		[CLK_GSP1_MMU_EB]	= &gsp1_mmu_eb.common.hw,
+		[CLK_DSI0_EB]		= &dsi0_eb.common.hw,
+		[CLK_DSI1_EB]		= &dsi1_eb.common.hw,
+		[CLK_DISP_CKG_EB]	= &disp_ckg_eb.common.hw,
+		[CLK_DISP_GPU_EB]	= &disp_gpu_eb.common.hw,
+		[CLK_GPU_MTX_EB]	= &gpu_mtx_eb.common.hw,
+		[CLK_GSP_MTX_EB]	= &gsp_mtx_eb.common.hw,
+		[CLK_TMC_MTX_EB]	= &tmc_mtx_eb.common.hw,
+		[CLK_DISPC_MTX_EB]	= &dispc_mtx_eb.common.hw,
+		[CLK_DPHY0_GATE]	= &dphy0_gate.common.hw,
+		[CLK_DPHY1_GATE]	= &dphy1_gate.common.hw,
+		[CLK_GSP0_A_GATE]	= &gsp0_a_gate.common.hw,
+		[CLK_GSP1_A_GATE]	= &gsp1_a_gate.common.hw,
+		[CLK_GSP0_F_GATE]	= &gsp0_f_gate.common.hw,
+		[CLK_GSP1_F_GATE]	= &gsp1_f_gate.common.hw,
+		[CLK_D_MTX_F_GATE]	= &d_mtx_f_gate.common.hw,
+		[CLK_D_MTX_A_GATE]	= &d_mtx_a_gate.common.hw,
+		[CLK_D_NOC_F_GATE]	= &d_noc_f_gate.common.hw,
+		[CLK_D_NOC_A_GATE]	= &d_noc_a_gate.common.hw,
+		[CLK_GSP_MTX_F_GATE]	= &gsp_mtx_f_gate.common.hw,
+		[CLK_GSP_MTX_A_GATE]	= &gsp_mtx_a_gate.common.hw,
+		[CLK_GSP_NOC_F_GATE]	= &gsp_noc_f_gate.common.hw,
+		[CLK_GSP_NOC_A_GATE]	= &gsp_noc_a_gate.common.hw,
+		[CLK_DISPM0IDLE_GATE]	= &dispm0idle_gate.common.hw,
+		[CLK_GSPM0IDLE_GATE]	= &gspm0idle_gate.common.hw,
+	},
+	.num	= CLK_DISP_GATE_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_disp_gate_desc = {
+	.clk_clks	= sc9860_disp_gate,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_disp_gate),
+	.hw_clks	= &sc9860_disp_gate_hws,
+};
+
+static SPRD_SC_GATE_CLK(sim0_eb,	"sim0-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(0), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(iis0_eb,	"iis0-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(1), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(iis1_eb,	"iis1-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(2), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(iis2_eb,	"iis2-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(3), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(iis3_eb,	"iis3-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(4), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(spi0_eb,	"spi0-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(5), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(spi1_eb,	"spi1-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(6), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(spi2_eb,	"spi2-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(7), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(i2c0_eb,	"i2c0-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(8), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(i2c1_eb,	"i2c1-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(9), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(i2c2_eb,	"i2c2-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(10), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(i2c3_eb,	"i2c3-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(11), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(i2c4_eb,	"i2c4-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(12), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(i2c5_eb,	"i2c5-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(13), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(uart0_eb,	"uart0-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(14), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(uart1_eb,	"uart1-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(15), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(uart2_eb,	"uart2-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(16), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(uart3_eb,	"uart3-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(17), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(uart4_eb,	"uart4-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(18), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(ap_ckg_eb,	"ap-ckg-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(19), CLK_IGNORE_UNUSED, 0);
+static SPRD_SC_GATE_CLK(spi3_eb,	"spi3-eb",	"ap-apb", 0x0,
+		     0x1000, BIT(20), CLK_IGNORE_UNUSED, 0);
+
+static struct sprd_clk_common *sc9860_apapb_gate[] = {
+	/* address base is 0x70b00000 */
+	&sim0_eb.common,
+	&iis0_eb.common,
+	&iis1_eb.common,
+	&iis2_eb.common,
+	&iis3_eb.common,
+	&spi0_eb.common,
+	&spi1_eb.common,
+	&spi2_eb.common,
+	&i2c0_eb.common,
+	&i2c1_eb.common,
+	&i2c2_eb.common,
+	&i2c3_eb.common,
+	&i2c4_eb.common,
+	&i2c5_eb.common,
+	&uart0_eb.common,
+	&uart1_eb.common,
+	&uart2_eb.common,
+	&uart3_eb.common,
+	&uart4_eb.common,
+	&ap_ckg_eb.common,
+	&spi3_eb.common,
+};
+
+static struct clk_hw_onecell_data sc9860_apapb_gate_hws = {
+	.hws	= {
+		[CLK_SIM0_EB]		= &sim0_eb.common.hw,
+		[CLK_IIS0_EB]		= &iis0_eb.common.hw,
+		[CLK_IIS1_EB]		= &iis1_eb.common.hw,
+		[CLK_IIS2_EB]		= &iis2_eb.common.hw,
+		[CLK_IIS3_EB]		= &iis3_eb.common.hw,
+		[CLK_SPI0_EB]		= &spi0_eb.common.hw,
+		[CLK_SPI1_EB]		= &spi1_eb.common.hw,
+		[CLK_SPI2_EB]		= &spi2_eb.common.hw,
+		[CLK_I2C0_EB]		= &i2c0_eb.common.hw,
+		[CLK_I2C1_EB]		= &i2c1_eb.common.hw,
+		[CLK_I2C2_EB]		= &i2c2_eb.common.hw,
+		[CLK_I2C3_EB]		= &i2c3_eb.common.hw,
+		[CLK_I2C4_EB]		= &i2c4_eb.common.hw,
+		[CLK_I2C5_EB]		= &i2c5_eb.common.hw,
+		[CLK_UART0_EB]		= &uart0_eb.common.hw,
+		[CLK_UART1_EB]		= &uart1_eb.common.hw,
+		[CLK_UART2_EB]		= &uart2_eb.common.hw,
+		[CLK_UART3_EB]		= &uart3_eb.common.hw,
+		[CLK_UART4_EB]		= &uart4_eb.common.hw,
+		[CLK_AP_CKG_EB]		= &ap_ckg_eb.common.hw,
+		[CLK_SPI3_EB]		= &spi3_eb.common.hw,
+	},
+	.num	= CLK_APAPB_GATE_NUM,
+};
+
+static const struct sprd_clk_desc sc9860_apapb_gate_desc = {
+	.clk_clks	= sc9860_apapb_gate,
+	.num_clk_clks	= ARRAY_SIZE(sc9860_apapb_gate),
+	.hw_clks	= &sc9860_apapb_gate_hws,
+};
+
+static const struct of_device_id sprd_sc9860_clk_ids[] = {
+	{ .compatible = "sprd,sc9860-pmu-gate",		/* 0x402b */
+	  .data = &sc9860_pmu_gate_desc },
+	{ .compatible = "sprd,sc9860-pll",		/* 0x4040 */
+	  .data = &sc9860_pll_desc },
+	{ .compatible = "sprd,sc9860-ap-clk",		/* 0x2000 */
+	  .data = &sc9860_ap_clk_desc },
+	{ .compatible = "sprd,sc9860-aon-prediv",	/* 0x402d */
+	  .data = &sc9860_aon_prediv_desc },
+	{ .compatible = "sprd,sc9860-apahb-gate",	/* 0x2021 */
+	  .data = &sc9860_apahb_gate_desc },
+	{ .compatible = "sprd,sc9860-aon-gate",		/* 0x402e */
+	  .data = &sc9860_aon_gate_desc },
+	{ .compatible = "sprd,sc9860-aonsecure-clk",	/* 0x4088 */
+	  .data = &sc9860_aonsecure_clk_desc },
+	{ .compatible = "sprd,sc9860-agcp-gate",	/* 0x415e */
+	  .data = &sc9860_agcp_gate_desc },
+	{ .compatible = "sprd,sc9860-gpu-clk",		/* 0x6020 */
+	  .data = &sc9860_gpu_clk_desc },
+	{ .compatible = "sprd,sc9860-vsp-clk",		/* 0x6100 */
+	  .data = &sc9860_vsp_clk_desc },
+	{ .compatible = "sprd,sc9860-vsp-gate",		/* 0x6110 */
+	  .data = &sc9860_vsp_gate_desc },
+	{ .compatible = "sprd,sc9860-cam-clk",		/* 0x6200 */
+	  .data = &sc9860_cam_clk_desc },
+	{ .compatible = "sprd,sc9860-cam-gate",		/* 0x6210 */
+	  .data = &sc9860_cam_gate_desc },
+	{ .compatible = "sprd,sc9860-disp-clk",		/* 0x6300 */
+	  .data = &sc9860_disp_clk_desc },
+	{ .compatible = "sprd,sc9860-disp-gate",	/* 0x6310 */
+	  .data = &sc9860_disp_gate_desc },
+	{ .compatible = "sprd,sc9860-apapb-gate",	/* 0x70b0 */
+	  .data = &sc9860_apapb_gate_desc },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, sprd_sc9860_clk_ids);
+
+static int sc9860_clk_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *match;
+	const struct sprd_clk_desc *desc;
+
+	match = of_match_node(sprd_sc9860_clk_ids, pdev->dev.of_node);
+	if (!match) {
+		pr_err("%s: of_match_node() failed", __func__);
+		return -ENODEV;
+	}
+
+	desc = match->data;
+	sprd_clk_regmap_init(pdev, desc);
+
+	return sprd_clk_probe(&pdev->dev, desc->hw_clks);
+}
+
+static struct platform_driver sc9860_clk_driver = {
+	.probe	= sc9860_clk_probe,
+	.driver	= {
+		.name	= "sc9860-clk",
+		.of_match_table	= sprd_sc9860_clk_ids,
+	},
+};
+module_platform_driver(sc9860_clk_driver);
+
+MODULE_DESCRIPTION("Spreadtrum SC9860 Clock Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:sc9860-clk");
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
index 2bb4cabf802f..ee9c12cf3f08 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
@@ -400,28 +400,45 @@ static SUNXI_CCU_MP_WITH_MUX_GATE(nand_clk, "nand", mod0_default_parents, 0x080,
 				  BIT(31),	/* gate */
 				  0);
 
+/*
+ * MMC clocks are the new timing mode (see A83T & H3) variety, but without
+ * the mode switch. This means they have a 2x post divider between the clock
+ * and the MMC module. This is not documented in the manual, but is taken
+ * into consideration when setting the mmc module clocks in the BSP kernel.
+ * Without it, MMC performance is degraded.
+ *
+ * We model it here to be consistent with other SoCs supporting this mode.
+ * The alternative would be to add the 2x multiplier when setting the MMC
+ * module clock in the MMC driver, just for the A64.
+ */
 static const char * const mmc_default_parents[] = { "osc24M", "pll-periph0-2x",
 						    "pll-periph1-2x" };
-static SUNXI_CCU_MP_WITH_MUX_GATE(mmc0_clk, "mmc0", mmc_default_parents, 0x088,
-				  0, 4,		/* M */
-				  16, 2,	/* P */
-				  24, 2,	/* mux */
-				  BIT(31),	/* gate */
-				  0);
-
-static SUNXI_CCU_MP_WITH_MUX_GATE(mmc1_clk, "mmc1", mmc_default_parents, 0x08c,
-				  0, 4,		/* M */
-				  16, 2,	/* P */
-				  24, 2,	/* mux */
-				  BIT(31),	/* gate */
-				  0);
-
-static SUNXI_CCU_MP_WITH_MUX_GATE(mmc2_clk, "mmc2", mmc_default_parents, 0x090,
-				  0, 4,		/* M */
-				  16, 2,	/* P */
-				  24, 2,	/* mux */
-				  BIT(31),	/* gate */
-				  0);
+static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc0_clk, "mmc0",
+					  mmc_default_parents, 0x088,
+					  0, 4,		/* M */
+					  16, 2,	/* P */
+					  24, 2,	/* mux */
+					  BIT(31),	/* gate */
+					  2,		/* post-div */
+					  0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1",
+					  mmc_default_parents, 0x08c,
+					  0, 4,		/* M */
+					  16, 2,	/* P */
+					  24, 2,	/* mux */
+					  BIT(31),	/* gate */
+					  2,		/* post-div */
+					  0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2",
+					  mmc_default_parents, 0x090,
+					  0, 4,		/* M */
+					  16, 2,	/* P */
+					  24, 2,	/* mux */
+					  BIT(31),	/* gate */
+					  2,		/* post-div */
+					  0);
 
 static const char * const ts_parents[] = { "osc24M", "pll-periph0", };
 static SUNXI_CCU_MP_WITH_MUX_GATE(ts_clk, "ts", ts_parents, 0x098,
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a83t.c b/drivers/clk/sunxi-ng/ccu-sun8i-a83t.c
index 5cedcd0d8be8..7d08015b980d 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-a83t.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-a83t.c
@@ -76,15 +76,26 @@ static struct ccu_mult pll_c1cpux_clk = {
  */
 #define SUN8I_A83T_PLL_AUDIO_REG	0x008
 
+/* clock rates doubled for post divider */
+static struct ccu_sdm_setting pll_audio_sdm_table[] = {
+	{ .rate = 45158400, .pattern = 0xc00121ff, .m = 29, .n = 54 },
+	{ .rate = 49152000, .pattern = 0xc000e147, .m = 30, .n = 61 },
+};
+
 static struct ccu_nm pll_audio_clk = {
 	.enable		= BIT(31),
 	.lock		= BIT(2),
 	.n		= _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0),
 	.m		= _SUNXI_CCU_DIV(0, 6),
+	.fixed_post_div	= 2,
+	.sdm		= _SUNXI_CCU_SDM(pll_audio_sdm_table, BIT(24),
+					 0x284, BIT(31)),
 	.common		= {
 		.reg		= SUN8I_A83T_PLL_AUDIO_REG,
 		.lock_reg	= CCU_SUN8I_A83T_LOCK_REG,
-		.features	= CCU_FEATURE_LOCK_REG,
+		.features	= CCU_FEATURE_LOCK_REG |
+				  CCU_FEATURE_FIXED_POSTDIV |
+				  CCU_FEATURE_SIGMA_DELTA_MOD,
 		.hw.init	= CLK_HW_INIT("pll-audio", "osc24M",
 					      &ccu_nm_ops, CLK_SET_RATE_UNGATE),
 	},
@@ -493,8 +504,8 @@ static SUNXI_CCU_MUX_WITH_GATE(tcon0_clk, "tcon0", tcon0_parents,
 				 0x118, 24, 3, BIT(31), CLK_SET_RATE_PARENT);
 
 static const char * const tcon1_parents[] = { "pll-video1" };
-static SUNXI_CCU_MUX_WITH_GATE(tcon1_clk, "tcon1", tcon1_parents,
-				 0x11c, 24, 3, BIT(31), CLK_SET_RATE_PARENT);
+static SUNXI_CCU_M_WITH_MUX_GATE(tcon1_clk, "tcon1", tcon1_parents,
+				 0x11c, 0, 4, 24, 2, BIT(31), CLK_SET_RATE_PARENT);
 
 static SUNXI_CCU_GATE(csi_misc_clk, "csi-misc", "osc24M", 0x130, BIT(16), 0);
 
@@ -889,9 +900,10 @@ static int sun8i_a83t_ccu_probe(struct platform_device *pdev)
 	if (IS_ERR(reg))
 		return PTR_ERR(reg);
 
-	/* Enforce d1 = 0, d2 = 0 for Audio PLL */
+	/* Enforce d1 = 0, d2 = 1 for Audio PLL */
 	val = readl(reg + SUN8I_A83T_PLL_AUDIO_REG);
-	val &= ~(BIT(16) | BIT(18));
+	val &= ~BIT(16);
+	val |= BIT(18);
 	writel(val, reg + SUN8I_A83T_PLL_AUDIO_REG);
 
 	/* Enforce P = 1 for both CPU cluster PLLs */
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-de2.c b/drivers/clk/sunxi-ng/ccu-sun8i-de2.c
index 5cc9d9952121..468d1abaf0ee 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-de2.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-de2.c
@@ -41,6 +41,8 @@ static SUNXI_CCU_GATE(wb_clk,		"wb",		"wb-div",
 
 static SUNXI_CCU_M(mixer0_div_clk, "mixer0-div", "de", 0x0c, 0, 4,
 		   CLK_SET_RATE_PARENT);
+static SUNXI_CCU_M(mixer1_div_clk, "mixer1-div", "de", 0x0c, 4, 4,
+		   CLK_SET_RATE_PARENT);
 static SUNXI_CCU_M(wb_div_clk, "wb-div", "de", 0x0c, 8, 4,
 		   CLK_SET_RATE_PARENT);
 
@@ -65,6 +67,20 @@ static struct ccu_common *sun8i_a83t_de2_clks[] = {
 	&wb_div_a83_clk.common,
 };
 
+static struct ccu_common *sun8i_h3_de2_clks[] = {
+	&mixer0_clk.common,
+	&mixer1_clk.common,
+	&wb_clk.common,
+
+	&bus_mixer0_clk.common,
+	&bus_mixer1_clk.common,
+	&bus_wb_clk.common,
+
+	&mixer0_div_clk.common,
+	&mixer1_div_clk.common,
+	&wb_div_clk.common,
+};
+
 static struct ccu_common *sun8i_v3s_de2_clks[] = {
 	&mixer0_clk.common,
 	&wb_clk.common,
@@ -93,6 +109,23 @@ static struct clk_hw_onecell_data sun8i_a83t_de2_hw_clks = {
 	.num	= CLK_NUMBER,
 };
 
+static struct clk_hw_onecell_data sun8i_h3_de2_hw_clks = {
+	.hws	= {
+		[CLK_MIXER0]		= &mixer0_clk.common.hw,
+		[CLK_MIXER1]		= &mixer1_clk.common.hw,
+		[CLK_WB]		= &wb_clk.common.hw,
+
+		[CLK_BUS_MIXER0]	= &bus_mixer0_clk.common.hw,
+		[CLK_BUS_MIXER1]	= &bus_mixer1_clk.common.hw,
+		[CLK_BUS_WB]		= &bus_wb_clk.common.hw,
+
+		[CLK_MIXER0_DIV]	= &mixer0_div_clk.common.hw,
+		[CLK_MIXER1_DIV]	= &mixer1_div_clk.common.hw,
+		[CLK_WB_DIV]		= &wb_div_clk.common.hw,
+	},
+	.num	= CLK_NUMBER,
+};
+
 static struct clk_hw_onecell_data sun8i_v3s_de2_hw_clks = {
 	.hws	= {
 		[CLK_MIXER0]		= &mixer0_clk.common.hw,
@@ -133,11 +166,21 @@ static const struct sunxi_ccu_desc sun8i_a83t_de2_clk_desc = {
 	.num_resets	= ARRAY_SIZE(sun8i_a83t_de2_resets),
 };
 
+static const struct sunxi_ccu_desc sun8i_h3_de2_clk_desc = {
+	.ccu_clks	= sun8i_h3_de2_clks,
+	.num_ccu_clks	= ARRAY_SIZE(sun8i_h3_de2_clks),
+
+	.hw_clks	= &sun8i_h3_de2_hw_clks,
+
+	.resets		= sun8i_a83t_de2_resets,
+	.num_resets	= ARRAY_SIZE(sun8i_a83t_de2_resets),
+};
+
 static const struct sunxi_ccu_desc sun50i_a64_de2_clk_desc = {
-	.ccu_clks	= sun8i_a83t_de2_clks,
-	.num_ccu_clks	= ARRAY_SIZE(sun8i_a83t_de2_clks),
+	.ccu_clks	= sun8i_h3_de2_clks,
+	.num_ccu_clks	= ARRAY_SIZE(sun8i_h3_de2_clks),
 
-	.hw_clks	= &sun8i_a83t_de2_hw_clks,
+	.hw_clks	= &sun8i_h3_de2_hw_clks,
 
 	.resets		= sun50i_a64_de2_resets,
 	.num_resets	= ARRAY_SIZE(sun50i_a64_de2_resets),
@@ -238,6 +281,10 @@ static const struct of_device_id sunxi_de2_clk_ids[] = {
 		.data = &sun8i_a83t_de2_clk_desc,
 	},
 	{
+		.compatible = "allwinner,sun8i-h3-de2-clk",
+		.data = &sun8i_h3_de2_clk_desc,
+	},
+	{
 		.compatible = "allwinner,sun8i-v3s-de2-clk",
 		.data = &sun8i_v3s_de2_clk_desc,
 	},
diff --git a/drivers/clk/sunxi-ng/ccu_common.h b/drivers/clk/sunxi-ng/ccu_common.h
index 5d684ce77c54..568cfaed0813 100644
--- a/drivers/clk/sunxi-ng/ccu_common.h
+++ b/drivers/clk/sunxi-ng/ccu_common.h
@@ -31,35 +31,6 @@
 
 struct device_node;
 
-#define CLK_HW_INIT(_name, _parent, _ops, _flags)			\
-	&(struct clk_init_data) {					\
-		.flags		= _flags,				\
-		.name		= _name,				\
-		.parent_names	= (const char *[]) { _parent },		\
-		.num_parents	= 1,					\
-		.ops 		= _ops,					\
-	}
-
-#define CLK_HW_INIT_PARENTS(_name, _parents, _ops, _flags)		\
-	&(struct clk_init_data) {					\
-		.flags		= _flags,				\
-		.name		= _name,				\
-		.parent_names	= _parents,				\
-		.num_parents	= ARRAY_SIZE(_parents),			\
-		.ops 		= _ops,					\
-	}
-
-#define CLK_FIXED_FACTOR(_struct, _name, _parent,			\
-			_div, _mult, _flags)				\
-	struct clk_fixed_factor _struct = {				\
-		.div		= _div,					\
-		.mult		= _mult,				\
-		.hw.init	= CLK_HW_INIT(_name,			\
-					      _parent,			\
-					      &clk_fixed_factor_ops,	\
-					      _flags),			\
-	}
-
 struct ccu_common {
 	void __iomem	*base;
 	u16		reg;
diff --git a/drivers/clk/sunxi-ng/ccu_div.c b/drivers/clk/sunxi-ng/ccu_div.c
index baa3cf96507b..302a18efd39f 100644
--- a/drivers/clk/sunxi-ng/ccu_div.c
+++ b/drivers/clk/sunxi-ng/ccu_div.c
@@ -71,7 +71,7 @@ static unsigned long ccu_div_recalc_rate(struct clk_hw *hw,
 						  parent_rate);
 
 	val = divider_recalc_rate(hw, parent_rate, val, cd->div.table,
-				  cd->div.flags);
+				  cd->div.flags, cd->div.width);
 
 	if (cd->common.features & CCU_FEATURE_FIXED_POSTDIV)
 		val /= cd->fixed_post_div;
diff --git a/drivers/clk/sunxi-ng/ccu_mp.c b/drivers/clk/sunxi-ng/ccu_mp.c
index 688855e7dc8c..5d0af4051737 100644
--- a/drivers/clk/sunxi-ng/ccu_mp.c
+++ b/drivers/clk/sunxi-ng/ccu_mp.c
@@ -50,12 +50,19 @@ static unsigned long ccu_mp_round_rate(struct ccu_mux_internal *mux,
 	unsigned int max_m, max_p;
 	unsigned int m, p;
 
+	if (cmp->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate *= cmp->fixed_post_div;
+
 	max_m = cmp->m.max ?: 1 << cmp->m.width;
 	max_p = cmp->p.max ?: 1 << ((1 << cmp->p.width) - 1);
 
 	ccu_mp_find_best(*parent_rate, rate, max_m, max_p, &m, &p);
+	rate = *parent_rate / p / m;
+
+	if (cmp->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate /= cmp->fixed_post_div;
 
-	return *parent_rate / p / m;
+	return rate;
 }
 
 static void ccu_mp_disable(struct clk_hw *hw)
@@ -83,6 +90,7 @@ static unsigned long ccu_mp_recalc_rate(struct clk_hw *hw,
 					unsigned long parent_rate)
 {
 	struct ccu_mp *cmp = hw_to_ccu_mp(hw);
+	unsigned long rate;
 	unsigned int m, p;
 	u32 reg;
 
@@ -101,7 +109,11 @@ static unsigned long ccu_mp_recalc_rate(struct clk_hw *hw,
 	p = reg >> cmp->p.shift;
 	p &= (1 << cmp->p.width) - 1;
 
-	return (parent_rate >> p) / m;
+	rate = (parent_rate >> p) / m;
+	if (cmp->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate /= cmp->fixed_post_div;
+
+	return rate;
 }
 
 static int ccu_mp_determine_rate(struct clk_hw *hw,
@@ -129,6 +141,10 @@ static int ccu_mp_set_rate(struct clk_hw *hw, unsigned long rate,
 	max_m = cmp->m.max ?: 1 << cmp->m.width;
 	max_p = cmp->p.max ?: 1 << ((1 << cmp->p.width) - 1);
 
+	/* Adjust target rate according to post-dividers */
+	if (cmp->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate = rate * cmp->fixed_post_div;
+
 	ccu_mp_find_best(parent_rate, rate, max_m, max_p, &m, &p);
 
 	spin_lock_irqsave(cmp->common.lock, flags);
diff --git a/drivers/clk/sunxi-ng/ccu_mp.h b/drivers/clk/sunxi-ng/ccu_mp.h
index aaef11d747ea..5107635e61de 100644
--- a/drivers/clk/sunxi-ng/ccu_mp.h
+++ b/drivers/clk/sunxi-ng/ccu_mp.h
@@ -33,9 +33,33 @@ struct ccu_mp {
 	struct ccu_div_internal		m;
 	struct ccu_div_internal		p;
 	struct ccu_mux_internal	mux;
+
+	unsigned int		fixed_post_div;
+
 	struct ccu_common	common;
 };
 
+#define SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(_struct, _name, _parents, _reg, \
+					   _mshift, _mwidth,		\
+					   _pshift, _pwidth,		\
+					   _muxshift, _muxwidth,	\
+					   _gate, _postdiv, _flags)	\
+	struct ccu_mp _struct = {					\
+		.enable	= _gate,					\
+		.m	= _SUNXI_CCU_DIV(_mshift, _mwidth),		\
+		.p	= _SUNXI_CCU_DIV(_pshift, _pwidth),		\
+		.mux	= _SUNXI_CCU_MUX(_muxshift, _muxwidth),		\
+		.fixed_post_div	= _postdiv,				\
+		.common	= {						\
+			.reg		= _reg,				\
+			.features	= CCU_FEATURE_FIXED_POSTDIV,	\
+			.hw.init	= CLK_HW_INIT_PARENTS(_name,	\
+							      _parents, \
+							      &ccu_mp_ops, \
+							      _flags),	\
+		}							\
+	}
+
 #define SUNXI_CCU_MP_WITH_MUX_GATE(_struct, _name, _parents, _reg,	\
 				   _mshift, _mwidth,			\
 				   _pshift, _pwidth,			\
diff --git a/drivers/clk/sunxi-ng/ccu_nm.c b/drivers/clk/sunxi-ng/ccu_nm.c
index 7620aa973a6e..a16de092bf94 100644
--- a/drivers/clk/sunxi-ng/ccu_nm.c
+++ b/drivers/clk/sunxi-ng/ccu_nm.c
@@ -70,11 +70,18 @@ static unsigned long ccu_nm_recalc_rate(struct clk_hw *hw,
 					unsigned long parent_rate)
 {
 	struct ccu_nm *nm = hw_to_ccu_nm(hw);
+	unsigned long rate;
 	unsigned long n, m;
 	u32 reg;
 
-	if (ccu_frac_helper_is_enabled(&nm->common, &nm->frac))
-		return ccu_frac_helper_read_rate(&nm->common, &nm->frac);
+	if (ccu_frac_helper_is_enabled(&nm->common, &nm->frac)) {
+		rate = ccu_frac_helper_read_rate(&nm->common, &nm->frac);
+
+		if (nm->common.features & CCU_FEATURE_FIXED_POSTDIV)
+			rate /= nm->fixed_post_div;
+
+		return rate;
+	}
 
 	reg = readl(nm->common.base + nm->common.reg);
 
@@ -90,15 +97,15 @@ static unsigned long ccu_nm_recalc_rate(struct clk_hw *hw,
 	if (!m)
 		m++;
 
-	if (ccu_sdm_helper_is_enabled(&nm->common, &nm->sdm)) {
-		unsigned long rate =
-			ccu_sdm_helper_read_rate(&nm->common, &nm->sdm,
-						 m, n);
-		if (rate)
-			return rate;
-	}
+	if (ccu_sdm_helper_is_enabled(&nm->common, &nm->sdm))
+		rate = ccu_sdm_helper_read_rate(&nm->common, &nm->sdm, m, n);
+	else
+		rate = parent_rate * n / m;
+
+	if (nm->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate /= nm->fixed_post_div;
 
-	return parent_rate * n / m;
+	return rate;
 }
 
 static long ccu_nm_round_rate(struct clk_hw *hw, unsigned long rate,
@@ -107,11 +114,20 @@ static long ccu_nm_round_rate(struct clk_hw *hw, unsigned long rate,
 	struct ccu_nm *nm = hw_to_ccu_nm(hw);
 	struct _ccu_nm _nm;
 
-	if (ccu_frac_helper_has_rate(&nm->common, &nm->frac, rate))
+	if (nm->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate *= nm->fixed_post_div;
+
+	if (ccu_frac_helper_has_rate(&nm->common, &nm->frac, rate)) {
+		if (nm->common.features & CCU_FEATURE_FIXED_POSTDIV)
+			rate /= nm->fixed_post_div;
 		return rate;
+	}
 
-	if (ccu_sdm_helper_has_rate(&nm->common, &nm->sdm, rate))
+	if (ccu_sdm_helper_has_rate(&nm->common, &nm->sdm, rate)) {
+		if (nm->common.features & CCU_FEATURE_FIXED_POSTDIV)
+			rate /= nm->fixed_post_div;
 		return rate;
+	}
 
 	_nm.min_n = nm->n.min ?: 1;
 	_nm.max_n = nm->n.max ?: 1 << nm->n.width;
@@ -119,8 +135,12 @@ static long ccu_nm_round_rate(struct clk_hw *hw, unsigned long rate,
 	_nm.max_m = nm->m.max ?: 1 << nm->m.width;
 
 	ccu_nm_find_best(*parent_rate, rate, &_nm);
+	rate = *parent_rate * _nm.n / _nm.m;
+
+	if (nm->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate /= nm->fixed_post_div;
 
-	return *parent_rate * _nm.n / _nm.m;
+	return rate;
 }
 
 static int ccu_nm_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -131,6 +151,10 @@ static int ccu_nm_set_rate(struct clk_hw *hw, unsigned long rate,
 	unsigned long flags;
 	u32 reg;
 
+	/* Adjust target rate according to post-dividers */
+	if (nm->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate = rate * nm->fixed_post_div;
+
 	if (ccu_frac_helper_has_rate(&nm->common, &nm->frac, rate)) {
 		spin_lock_irqsave(nm->common.lock, flags);
 
diff --git a/drivers/clk/sunxi-ng/ccu_nm.h b/drivers/clk/sunxi-ng/ccu_nm.h
index c623b0c7a23c..eba586b4c7d0 100644
--- a/drivers/clk/sunxi-ng/ccu_nm.h
+++ b/drivers/clk/sunxi-ng/ccu_nm.h
@@ -36,6 +36,8 @@ struct ccu_nm {
 	struct ccu_frac_internal	frac;
 	struct ccu_sdm_internal		sdm;
 
+	unsigned int		fixed_post_div;
+
 	struct ccu_common	common;
 };
 
diff --git a/drivers/clk/sunxi/clk-factors.c b/drivers/clk/sunxi/clk-factors.c
index 856fef65433b..661a73284e9f 100644
--- a/drivers/clk/sunxi/clk-factors.c
+++ b/drivers/clk/sunxi/clk-factors.c
@@ -176,10 +176,10 @@ static const struct clk_ops clk_factors_ops = {
 	.set_rate = clk_factors_set_rate,
 };
 
-struct clk *sunxi_factors_register(struct device_node *node,
-				   const struct factors_data *data,
-				   spinlock_t *lock,
-				   void __iomem *reg)
+static struct clk *__sunxi_factors_register(struct device_node *node,
+					    const struct factors_data *data,
+					    spinlock_t *lock, void __iomem *reg,
+					    unsigned long flags)
 {
 	struct clk *clk;
 	struct clk_factors *factors;
@@ -249,7 +249,7 @@ struct clk *sunxi_factors_register(struct device_node *node,
 			parents, i,
 			mux_hw, &clk_mux_ops,
 			&factors->hw, &clk_factors_ops,
-			gate_hw, &clk_gate_ops, 0);
+			gate_hw, &clk_gate_ops, CLK_IS_CRITICAL);
 	if (IS_ERR(clk))
 		goto err_register;
 
@@ -272,6 +272,22 @@ err_factors:
 	return NULL;
 }
 
+struct clk *sunxi_factors_register(struct device_node *node,
+				   const struct factors_data *data,
+				   spinlock_t *lock,
+				   void __iomem *reg)
+{
+	return __sunxi_factors_register(node, data, lock, reg, 0);
+}
+
+struct clk *sunxi_factors_register_critical(struct device_node *node,
+					    const struct factors_data *data,
+					    spinlock_t *lock,
+					    void __iomem *reg)
+{
+	return __sunxi_factors_register(node, data, lock, reg, CLK_IS_CRITICAL);
+}
+
 void sunxi_factors_unregister(struct device_node *node, struct clk *clk)
 {
 	struct clk_hw *hw = __clk_get_hw(clk);
diff --git a/drivers/clk/sunxi/clk-factors.h b/drivers/clk/sunxi/clk-factors.h
index 824f746b2567..7ad2ca924d0d 100644
--- a/drivers/clk/sunxi/clk-factors.h
+++ b/drivers/clk/sunxi/clk-factors.h
@@ -55,6 +55,10 @@ struct clk *sunxi_factors_register(struct device_node *node,
 				   const struct factors_data *data,
 				   spinlock_t *lock,
 				   void __iomem *reg);
+struct clk *sunxi_factors_register_critical(struct device_node *node,
+					    const struct factors_data *data,
+					    spinlock_t *lock,
+					    void __iomem *reg);
 
 void sunxi_factors_unregister(struct device_node *node, struct clk *clk);
 
diff --git a/drivers/clk/sunxi/clk-mod0.c b/drivers/clk/sunxi/clk-mod0.c
index 4417ae129ac7..a27c264cc9b4 100644
--- a/drivers/clk/sunxi/clk-mod0.c
+++ b/drivers/clk/sunxi/clk-mod0.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
@@ -155,7 +154,6 @@ static DEFINE_SPINLOCK(sun5i_a13_mbus_lock);
 
 static void __init sun5i_a13_mbus_setup(struct device_node *node)
 {
-	struct clk *mbus;
 	void __iomem *reg;
 
 	reg = of_iomap(node, 0);
@@ -164,12 +162,9 @@ static void __init sun5i_a13_mbus_setup(struct device_node *node)
 		return;
 	}
 
-	mbus = sunxi_factors_register(node, &sun4i_a10_mod0_data,
-				      &sun5i_a13_mbus_lock, reg);
-
 	/* The MBUS clocks needs to be always enabled */
-	__clk_get(mbus);
-	clk_prepare_enable(mbus);
+	sunxi_factors_register_critical(node, &sun4i_a10_mod0_data,
+					&sun5i_a13_mbus_lock, reg);
 }
 CLK_OF_DECLARE(sun5i_a13_mbus, "allwinner,sun5i-a13-mbus-clk", sun5i_a13_mbus_setup);
 
diff --git a/drivers/clk/sunxi/clk-sun8i-apb0.c b/drivers/clk/sunxi/clk-sun8i-apb0.c
index ea1eed24778c..d5c31804ee54 100644
--- a/drivers/clk/sunxi/clk-sun8i-apb0.c
+++ b/drivers/clk/sunxi/clk-sun8i-apb0.c
@@ -98,10 +98,7 @@ static int sun8i_a23_apb0_clk_probe(struct platform_device *pdev)
 		return PTR_ERR(reg);
 
 	clk = sun8i_a23_apb0_register(np, reg);
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
-
-	return 0;
+	return PTR_ERR_OR_ZERO(clk);
 }
 
 static const struct of_device_id sun8i_a23_apb0_clk_dt_ids[] = {
diff --git a/drivers/clk/sunxi/clk-sun8i-mbus.c b/drivers/clk/sunxi/clk-sun8i-mbus.c
index b200ebf159ee..56db89b6979f 100644
--- a/drivers/clk/sunxi/clk-sun8i-mbus.c
+++ b/drivers/clk/sunxi/clk-sun8i-mbus.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -82,11 +81,12 @@ static void __init sun8i_a23_mbus_setup(struct device_node *node)
 	mux->mask = SUN8I_MBUS_MUX_MASK;
 	mux->lock = &sun8i_a23_mbus_lock;
 
+	/* The MBUS clocks needs to be always enabled */
 	clk = clk_register_composite(NULL, clk_name, parents, num_parents,
 				     &mux->hw, &clk_mux_ops,
 				     &div->hw, &clk_divider_ops,
 				     &gate->hw, &clk_gate_ops,
-				     0);
+				     CLK_IS_CRITICAL);
 	if (IS_ERR(clk))
 		goto err_free_gate;
 
@@ -95,9 +95,6 @@ static void __init sun8i_a23_mbus_setup(struct device_node *node)
 		goto err_unregister_clk;
 
 	kfree(parents); /* parents is deep copied */
-	/* The MBUS clocks needs to be always enabled */
-	__clk_get(clk);
-	clk_prepare_enable(clk);
 
 	return;
 
diff --git a/drivers/clk/sunxi/clk-sun9i-core.c b/drivers/clk/sunxi/clk-sun9i-core.c
index 43f014f85803..e9295c286d5d 100644
--- a/drivers/clk/sunxi/clk-sun9i-core.c
+++ b/drivers/clk/sunxi/clk-sun9i-core.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/clk.h>
-#include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -140,7 +139,6 @@ static DEFINE_SPINLOCK(sun9i_a80_gt_lock);
 static void __init sun9i_a80_gt_setup(struct device_node *node)
 {
 	void __iomem *reg;
-	struct clk *gt;
 
 	reg = of_io_request_and_map(node, 0, of_node_full_name(node));
 	if (IS_ERR(reg)) {
@@ -149,12 +147,9 @@ static void __init sun9i_a80_gt_setup(struct device_node *node)
 		return;
 	}
 
-	gt = sunxi_factors_register(node, &sun9i_a80_gt_data,
-				    &sun9i_a80_gt_lock, reg);
-
 	/* The GT bus clock needs to be always enabled */
-	__clk_get(gt);
-	clk_prepare_enable(gt);
+	sunxi_factors_register_critical(node, &sun9i_a80_gt_data,
+					&sun9i_a80_gt_lock, reg);
 }
 CLK_OF_DECLARE(sun9i_a80_gt, "allwinner,sun9i-a80-gt-clk", sun9i_a80_gt_setup);
 
diff --git a/drivers/clk/sunxi/clk-sun9i-mmc.c b/drivers/clk/sunxi/clk-sun9i-mmc.c
index a1a634253d6f..f00d8758ba24 100644
--- a/drivers/clk/sunxi/clk-sun9i-mmc.c
+++ b/drivers/clk/sunxi/clk-sun9i-mmc.c
@@ -16,6 +16,7 @@
 
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -83,9 +84,20 @@ static int sun9i_mmc_reset_deassert(struct reset_controller_dev *rcdev,
 	return 0;
 }
 
+static int sun9i_mmc_reset_reset(struct reset_controller_dev *rcdev,
+				 unsigned long id)
+{
+	sun9i_mmc_reset_assert(rcdev, id);
+	udelay(10);
+	sun9i_mmc_reset_deassert(rcdev, id);
+
+	return 0;
+}
+
 static const struct reset_control_ops sun9i_mmc_reset_ops = {
 	.assert		= sun9i_mmc_reset_assert,
 	.deassert	= sun9i_mmc_reset_deassert,
+	.reset		= sun9i_mmc_reset_reset,
 };
 
 static int sun9i_a80_mmc_config_clk_probe(struct platform_device *pdev)
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index aa4add580516..012714d94b42 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -656,7 +656,8 @@ static const struct mux_data sun8i_h3_ahb2_mux_data __initconst = {
 };
 
 static struct clk * __init sunxi_mux_clk_setup(struct device_node *node,
-					       const struct mux_data *data)
+					       const struct mux_data *data,
+					       unsigned long flags)
 {
 	struct clk *clk;
 	const char *clk_name = node->name;
@@ -678,7 +679,7 @@ static struct clk * __init sunxi_mux_clk_setup(struct device_node *node,
 	}
 
 	clk = clk_register_mux(NULL, clk_name, parents, i,
-			       CLK_SET_RATE_PARENT, reg,
+			       CLK_SET_RATE_PARENT | flags, reg,
 			       data->shift, SUNXI_MUX_GATE_WIDTH,
 			       0, &clk_lock);
 
@@ -703,29 +704,22 @@ out_unmap:
 
 static void __init sun4i_cpu_clk_setup(struct device_node *node)
 {
-	struct clk *clk;
-
-	clk = sunxi_mux_clk_setup(node, &sun4i_cpu_mux_data);
-	if (!clk)
-		return;
-
 	/* Protect CPU clock */
-	__clk_get(clk);
-	clk_prepare_enable(clk);
+	sunxi_mux_clk_setup(node, &sun4i_cpu_mux_data, CLK_IS_CRITICAL);
 }
 CLK_OF_DECLARE(sun4i_cpu, "allwinner,sun4i-a10-cpu-clk",
 	       sun4i_cpu_clk_setup);
 
 static void __init sun6i_ahb1_mux_clk_setup(struct device_node *node)
 {
-	sunxi_mux_clk_setup(node, &sun6i_a31_ahb1_mux_data);
+	sunxi_mux_clk_setup(node, &sun6i_a31_ahb1_mux_data, 0);
 }
 CLK_OF_DECLARE(sun6i_ahb1_mux, "allwinner,sun6i-a31-ahb1-mux-clk",
 	       sun6i_ahb1_mux_clk_setup);
 
 static void __init sun8i_ahb2_clk_setup(struct device_node *node)
 {
-	sunxi_mux_clk_setup(node, &sun8i_h3_ahb2_mux_data);
+	sunxi_mux_clk_setup(node, &sun8i_h3_ahb2_mux_data, 0);
 }
 CLK_OF_DECLARE(sun8i_ahb2, "allwinner,sun8i-h3-ahb2-clk",
 	       sun8i_ahb2_clk_setup);
@@ -900,6 +894,7 @@ struct divs_data {
 		u8 shift; /* otherwise it's a normal divisor with this shift */
 		u8 pow;   /* is it power-of-two based? */
 		u8 gate;  /* is it independently gateable? */
+		bool critical;
 	} div[SUNXI_DIVS_MAX_QTY];
 };
 
@@ -915,7 +910,8 @@ static const struct divs_data pll5_divs_data __initconst = {
 	.factors = &sun4i_pll5_data,
 	.ndivs = 2,
 	.div = {
-		{ .shift = 0, .pow = 0, }, /* M, DDR */
+		/* Protect PLL5_DDR */
+		{ .shift = 0, .pow = 0, .critical = true }, /* M, DDR */
 		{ .shift = 16, .pow = 1, }, /* P, other */
 		/* No output for the base factor clock */
 	}
@@ -1089,7 +1085,9 @@ static struct clk ** __init sunxi_divs_clk_setup(struct device_node *node,
 						 NULL, NULL,
 						 rate_hw, rate_ops,
 						 gate_hw, &clk_gate_ops,
-						 clkflags);
+						 clkflags |
+						 data->div[i].critical ?
+							CLK_IS_CRITICAL : 0);
 
 		WARN_ON(IS_ERR(clk_data->clks[i]));
 	}
@@ -1117,15 +1115,7 @@ out_unmap:
 
 static void __init sun4i_pll5_clk_setup(struct device_node *node)
 {
-	struct clk **clks;
-
-	clks = sunxi_divs_clk_setup(node, &pll5_divs_data);
-	if (!clks)
-		return;
-
-	/* Protect PLL5_DDR */
-	__clk_get(clks[0]);
-	clk_prepare_enable(clks[0]);
+	sunxi_divs_clk_setup(node, &pll5_divs_data);
 }
 CLK_OF_DECLARE(sun4i_pll5, "allwinner,sun4i-a10-pll5-clk",
 	       sun4i_pll5_clk_setup);
diff --git a/drivers/clk/ti/Makefile b/drivers/clk/ti/Makefile
index a2293ee09440..5ab295d2a3cb 100644
--- a/drivers/clk/ti/Makefile
+++ b/drivers/clk/ti/Makefile
@@ -19,10 +19,6 @@ obj-$(CONFIG_SOC_DRA7XX)		+= $(clk-common) clk-7xx.o \
 					   clk-dra7-atl.o dpll3xxx.o dpll44xx.o
 obj-$(CONFIG_SOC_AM43XX)		+= $(clk-common) dpll3xxx.o clk-43xx.o
 
-ifdef CONFIG_ATAGS
-obj-$(CONFIG_ARCH_OMAP3)                += clk-3xxx-legacy.o
-endif
-
 endif	# CONFIG_ARCH_OMAP2PLUS
 
 obj-$(CONFIG_COMMON_CLK_TI_ADPLL)	+= adpll.o
diff --git a/drivers/clk/ti/apll.c b/drivers/clk/ti/apll.c
index 83b148f8037c..9498e9363b57 100644
--- a/drivers/clk/ti/apll.c
+++ b/drivers/clk/ti/apll.c
@@ -133,9 +133,10 @@ static const struct clk_ops apll_ck_ops = {
 	.get_parent	= &dra7_init_apll_parent,
 };
 
-static void __init omap_clk_register_apll(struct clk_hw *hw,
+static void __init omap_clk_register_apll(void *user,
 					  struct device_node *node)
 {
+	struct clk_hw *hw = user;
 	struct clk_hw_omap *clk_hw = to_clk_hw_omap(hw);
 	struct dpll_data *ad = clk_hw->dpll_data;
 	struct clk *clk;
diff --git a/drivers/clk/ti/clk-33xx.c b/drivers/clk/ti/clk-33xx.c
index 0e47d95faf49..612491a26070 100644
--- a/drivers/clk/ti/clk-33xx.c
+++ b/drivers/clk/ti/clk-33xx.c
@@ -19,98 +19,201 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clk/ti.h>
+#include <dt-bindings/clock/am3.h>
 
 #include "clock.h"
 
+static const char * const am3_gpio1_dbclk_parents[] __initconst = {
+	"l4_per_cm:clk:0138:0",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data am3_gpio2_bit_data[] __initconst = {
+	{ 18, TI_CLK_GATE, am3_gpio1_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data am3_gpio3_bit_data[] __initconst = {
+	{ 18, TI_CLK_GATE, am3_gpio1_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data am3_gpio4_bit_data[] __initconst = {
+	{ 18, TI_CLK_GATE, am3_gpio1_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data am3_l4_per_clkctrl_regs[] __initconst = {
+	{ AM3_CPGMAC0_CLKCTRL, NULL, CLKF_SW_SUP, "cpsw_125mhz_gclk", "cpsw_125mhz_clkdm" },
+	{ AM3_LCDC_CLKCTRL, NULL, CLKF_SW_SUP, "lcd_gclk", "lcdc_clkdm" },
+	{ AM3_USB_OTG_HS_CLKCTRL, NULL, CLKF_SW_SUP, "usbotg_fck", "l3s_clkdm" },
+	{ AM3_TPTC0_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM3_EMIF_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_ddr_m2_div2_ck", "l3_clkdm" },
+	{ AM3_OCMCRAM_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM3_GPMC_CLKCTRL, NULL, CLKF_SW_SUP, "l3s_gclk", "l3s_clkdm" },
+	{ AM3_MCASP0_CLKCTRL, NULL, CLKF_SW_SUP, "mcasp0_fck", "l3s_clkdm" },
+	{ AM3_UART6_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM3_MMC1_CLKCTRL, NULL, CLKF_SW_SUP, "mmc_clk" },
+	{ AM3_ELM_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM3_I2C3_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM3_I2C2_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM3_SPI0_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM3_SPI1_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM3_L4_LS_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM3_MCASP1_CLKCTRL, NULL, CLKF_SW_SUP, "mcasp1_fck", "l3s_clkdm" },
+	{ AM3_UART2_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM3_UART3_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM3_UART4_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM3_UART5_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM3_TIMER7_CLKCTRL, NULL, CLKF_SW_SUP, "timer7_fck" },
+	{ AM3_TIMER2_CLKCTRL, NULL, CLKF_SW_SUP, "timer2_fck" },
+	{ AM3_TIMER3_CLKCTRL, NULL, CLKF_SW_SUP, "timer3_fck" },
+	{ AM3_TIMER4_CLKCTRL, NULL, CLKF_SW_SUP, "timer4_fck" },
+	{ AM3_RNG_CLKCTRL, NULL, CLKF_SW_SUP, "rng_fck" },
+	{ AM3_AES_CLKCTRL, NULL, CLKF_SW_SUP, "aes0_fck", "l3_clkdm" },
+	{ AM3_SHAM_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM3_GPIO2_CLKCTRL, am3_gpio2_bit_data, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM3_GPIO3_CLKCTRL, am3_gpio3_bit_data, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM3_GPIO4_CLKCTRL, am3_gpio4_bit_data, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM3_TPCC_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM3_D_CAN0_CLKCTRL, NULL, CLKF_SW_SUP, "dcan0_fck" },
+	{ AM3_D_CAN1_CLKCTRL, NULL, CLKF_SW_SUP, "dcan1_fck" },
+	{ AM3_EPWMSS1_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM3_EPWMSS0_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM3_EPWMSS2_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM3_L3_INSTR_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM3_L3_MAIN_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM3_PRUSS_CLKCTRL, NULL, CLKF_SW_SUP, "pruss_ocp_gclk", "pruss_ocp_clkdm" },
+	{ AM3_TIMER5_CLKCTRL, NULL, CLKF_SW_SUP, "timer5_fck" },
+	{ AM3_TIMER6_CLKCTRL, NULL, CLKF_SW_SUP, "timer6_fck" },
+	{ AM3_MMC2_CLKCTRL, NULL, CLKF_SW_SUP, "mmc_clk" },
+	{ AM3_MMC3_CLKCTRL, NULL, CLKF_SW_SUP, "mmc_clk", "l3s_clkdm" },
+	{ AM3_TPTC1_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM3_TPTC2_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM3_SPINLOCK_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM3_MAILBOX_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM3_L4_HS_CLKCTRL, NULL, CLKF_SW_SUP, "l4hs_gclk", "l4hs_clkdm" },
+	{ AM3_OCPWP_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM3_CLKDIV32K_CLKCTRL, NULL, CLKF_SW_SUP, "clkdiv32k_ck", "clk_24mhz_clkdm" },
+	{ 0 },
+};
+
+static const char * const am3_gpio0_dbclk_parents[] __initconst = {
+	"gpio0_dbclk_mux_ck",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data am3_gpio1_bit_data[] __initconst = {
+	{ 18, TI_CLK_GATE, am3_gpio0_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const char * const am3_dbg_sysclk_ck_parents[] __initconst = {
+	"sys_clkin_ck",
+	NULL,
+};
+
+static const char * const am3_trace_pmd_clk_mux_ck_parents[] __initconst = {
+	"l4_wkup_cm:clk:0010:19",
+	"l4_wkup_cm:clk:0010:30",
+	NULL,
+};
+
+static const char * const am3_trace_clk_div_ck_parents[] __initconst = {
+	"l4_wkup_cm:clk:0010:20",
+	NULL,
+};
+
+static const struct omap_clkctrl_div_data am3_trace_clk_div_ck_data __initconst = {
+	.max_div = 64,
+	.flags = CLK_DIVIDER_POWER_OF_TWO,
+};
+
+static const char * const am3_stm_clk_div_ck_parents[] __initconst = {
+	"l4_wkup_cm:clk:0010:22",
+	NULL,
+};
+
+static const struct omap_clkctrl_div_data am3_stm_clk_div_ck_data __initconst = {
+	.max_div = 64,
+	.flags = CLK_DIVIDER_POWER_OF_TWO,
+};
+
+static const char * const am3_dbg_clka_ck_parents[] __initconst = {
+	"dpll_core_m4_ck",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data am3_debugss_bit_data[] __initconst = {
+	{ 19, TI_CLK_GATE, am3_dbg_sysclk_ck_parents, NULL },
+	{ 20, TI_CLK_MUX, am3_trace_pmd_clk_mux_ck_parents, NULL },
+	{ 22, TI_CLK_MUX, am3_trace_pmd_clk_mux_ck_parents, NULL },
+	{ 24, TI_CLK_DIVIDER, am3_trace_clk_div_ck_parents, &am3_trace_clk_div_ck_data },
+	{ 27, TI_CLK_DIVIDER, am3_stm_clk_div_ck_parents, &am3_stm_clk_div_ck_data },
+	{ 30, TI_CLK_GATE, am3_dbg_clka_ck_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data am3_l4_wkup_clkctrl_regs[] __initconst = {
+	{ AM3_CONTROL_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_core_m4_div2_ck" },
+	{ AM3_GPIO1_CLKCTRL, am3_gpio1_bit_data, CLKF_SW_SUP, "dpll_core_m4_div2_ck" },
+	{ AM3_L4_WKUP_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_core_m4_div2_ck" },
+	{ AM3_DEBUGSS_CLKCTRL, am3_debugss_bit_data, CLKF_SW_SUP, "l4_wkup_cm:clk:0010:24", "l3_aon_clkdm" },
+	{ AM3_WKUP_M3_CLKCTRL, NULL, CLKF_NO_IDLEST, "dpll_core_m4_div2_ck", "l4_wkup_aon_clkdm" },
+	{ AM3_UART1_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_wkupdm_ck" },
+	{ AM3_I2C1_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_wkupdm_ck" },
+	{ AM3_ADC_TSC_CLKCTRL, NULL, CLKF_SW_SUP, "adc_tsc_fck" },
+	{ AM3_SMARTREFLEX0_CLKCTRL, NULL, CLKF_SW_SUP, "smartreflex0_fck" },
+	{ AM3_TIMER1_CLKCTRL, NULL, CLKF_SW_SUP, "timer1_fck" },
+	{ AM3_SMARTREFLEX1_CLKCTRL, NULL, CLKF_SW_SUP, "smartreflex1_fck" },
+	{ AM3_WD_TIMER2_CLKCTRL, NULL, CLKF_SW_SUP, "wdt1_fck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data am3_mpu_clkctrl_regs[] __initconst = {
+	{ AM3_MPU_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_mpu_m2_ck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data am3_l4_rtc_clkctrl_regs[] __initconst = {
+	{ AM3_RTC_CLKCTRL, NULL, CLKF_SW_SUP, "clk_32768_ck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data am3_gfx_l3_clkctrl_regs[] __initconst = {
+	{ AM3_GFX_CLKCTRL, NULL, CLKF_SW_SUP, "gfx_fck_div_ck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data am3_l4_cefuse_clkctrl_regs[] __initconst = {
+	{ AM3_CEFUSE_CLKCTRL, NULL, CLKF_SW_SUP, "sys_clkin_ck" },
+	{ 0 },
+};
+
+const struct omap_clkctrl_data am3_clkctrl_data[] __initconst = {
+	{ 0x44e00014, am3_l4_per_clkctrl_regs },
+	{ 0x44e00404, am3_l4_wkup_clkctrl_regs },
+	{ 0x44e00604, am3_mpu_clkctrl_regs },
+	{ 0x44e00800, am3_l4_rtc_clkctrl_regs },
+	{ 0x44e00904, am3_gfx_l3_clkctrl_regs },
+	{ 0x44e00a20, am3_l4_cefuse_clkctrl_regs },
+	{ 0 },
+};
+
 static struct ti_dt_clk am33xx_clks[] = {
-	DT_CLK(NULL, "clk_32768_ck", "clk_32768_ck"),
-	DT_CLK(NULL, "clk_rc32k_ck", "clk_rc32k_ck"),
-	DT_CLK(NULL, "virt_19200000_ck", "virt_19200000_ck"),
-	DT_CLK(NULL, "virt_24000000_ck", "virt_24000000_ck"),
-	DT_CLK(NULL, "virt_25000000_ck", "virt_25000000_ck"),
-	DT_CLK(NULL, "virt_26000000_ck", "virt_26000000_ck"),
-	DT_CLK(NULL, "sys_clkin_ck", "sys_clkin_ck"),
-	DT_CLK(NULL, "tclkin_ck", "tclkin_ck"),
-	DT_CLK(NULL, "dpll_core_ck", "dpll_core_ck"),
-	DT_CLK(NULL, "dpll_core_x2_ck", "dpll_core_x2_ck"),
-	DT_CLK(NULL, "dpll_core_m4_ck", "dpll_core_m4_ck"),
-	DT_CLK(NULL, "dpll_core_m5_ck", "dpll_core_m5_ck"),
-	DT_CLK(NULL, "dpll_core_m6_ck", "dpll_core_m6_ck"),
-	DT_CLK(NULL, "dpll_mpu_ck", "dpll_mpu_ck"),
-	DT_CLK(NULL, "dpll_mpu_m2_ck", "dpll_mpu_m2_ck"),
-	DT_CLK(NULL, "dpll_ddr_ck", "dpll_ddr_ck"),
-	DT_CLK(NULL, "dpll_ddr_m2_ck", "dpll_ddr_m2_ck"),
-	DT_CLK(NULL, "dpll_ddr_m2_div2_ck", "dpll_ddr_m2_div2_ck"),
-	DT_CLK(NULL, "dpll_disp_ck", "dpll_disp_ck"),
-	DT_CLK(NULL, "dpll_disp_m2_ck", "dpll_disp_m2_ck"),
-	DT_CLK(NULL, "dpll_per_ck", "dpll_per_ck"),
-	DT_CLK(NULL, "dpll_per_m2_ck", "dpll_per_m2_ck"),
-	DT_CLK(NULL, "dpll_per_m2_div4_wkupdm_ck", "dpll_per_m2_div4_wkupdm_ck"),
-	DT_CLK(NULL, "dpll_per_m2_div4_ck", "dpll_per_m2_div4_ck"),
-	DT_CLK(NULL, "adc_tsc_fck", "adc_tsc_fck"),
-	DT_CLK(NULL, "cefuse_fck", "cefuse_fck"),
-	DT_CLK(NULL, "clkdiv32k_ck", "clkdiv32k_ck"),
-	DT_CLK(NULL, "clkdiv32k_ick", "clkdiv32k_ick"),
-	DT_CLK(NULL, "dcan0_fck", "dcan0_fck"),
-	DT_CLK("481cc000.d_can", NULL, "dcan0_fck"),
-	DT_CLK(NULL, "dcan1_fck", "dcan1_fck"),
-	DT_CLK("481d0000.d_can", NULL, "dcan1_fck"),
-	DT_CLK(NULL, "pruss_ocp_gclk", "pruss_ocp_gclk"),
-	DT_CLK(NULL, "mcasp0_fck", "mcasp0_fck"),
-	DT_CLK(NULL, "mcasp1_fck", "mcasp1_fck"),
-	DT_CLK(NULL, "mmu_fck", "mmu_fck"),
-	DT_CLK(NULL, "smartreflex0_fck", "smartreflex0_fck"),
-	DT_CLK(NULL, "smartreflex1_fck", "smartreflex1_fck"),
-	DT_CLK(NULL, "sha0_fck", "sha0_fck"),
-	DT_CLK(NULL, "aes0_fck", "aes0_fck"),
-	DT_CLK(NULL, "rng_fck", "rng_fck"),
-	DT_CLK(NULL, "timer1_fck", "timer1_fck"),
-	DT_CLK(NULL, "timer2_fck", "timer2_fck"),
-	DT_CLK(NULL, "timer3_fck", "timer3_fck"),
-	DT_CLK(NULL, "timer4_fck", "timer4_fck"),
-	DT_CLK(NULL, "timer5_fck", "timer5_fck"),
-	DT_CLK(NULL, "timer6_fck", "timer6_fck"),
-	DT_CLK(NULL, "timer7_fck", "timer7_fck"),
-	DT_CLK(NULL, "usbotg_fck", "usbotg_fck"),
-	DT_CLK(NULL, "ieee5000_fck", "ieee5000_fck"),
-	DT_CLK(NULL, "wdt1_fck", "wdt1_fck"),
-	DT_CLK(NULL, "l4_rtc_gclk", "l4_rtc_gclk"),
-	DT_CLK(NULL, "l3_gclk", "l3_gclk"),
-	DT_CLK(NULL, "dpll_core_m4_div2_ck", "dpll_core_m4_div2_ck"),
-	DT_CLK(NULL, "l4hs_gclk", "l4hs_gclk"),
-	DT_CLK(NULL, "l3s_gclk", "l3s_gclk"),
-	DT_CLK(NULL, "l4fw_gclk", "l4fw_gclk"),
-	DT_CLK(NULL, "l4ls_gclk", "l4ls_gclk"),
-	DT_CLK(NULL, "clk_24mhz", "clk_24mhz"),
-	DT_CLK(NULL, "sysclk_div_ck", "sysclk_div_ck"),
-	DT_CLK(NULL, "cpsw_125mhz_gclk", "cpsw_125mhz_gclk"),
-	DT_CLK(NULL, "cpsw_cpts_rft_clk", "cpsw_cpts_rft_clk"),
-	DT_CLK(NULL, "gpio0_dbclk_mux_ck", "gpio0_dbclk_mux_ck"),
-	DT_CLK(NULL, "gpio0_dbclk", "gpio0_dbclk"),
-	DT_CLK(NULL, "gpio1_dbclk", "gpio1_dbclk"),
-	DT_CLK(NULL, "gpio2_dbclk", "gpio2_dbclk"),
-	DT_CLK(NULL, "gpio3_dbclk", "gpio3_dbclk"),
-	DT_CLK(NULL, "lcd_gclk", "lcd_gclk"),
-	DT_CLK(NULL, "mmc_clk", "mmc_clk"),
-	DT_CLK(NULL, "gfx_fclk_clksel_ck", "gfx_fclk_clksel_ck"),
-	DT_CLK(NULL, "gfx_fck_div_ck", "gfx_fck_div_ck"),
-	DT_CLK(NULL, "sysclkout_pre_ck", "sysclkout_pre_ck"),
-	DT_CLK(NULL, "clkout2_div_ck", "clkout2_div_ck"),
-	DT_CLK(NULL, "timer_32k_ck", "clkdiv32k_ick"),
+	DT_CLK(NULL, "timer_32k_ck", "l4_per_cm:0138:0"),
 	DT_CLK(NULL, "timer_sys_ck", "sys_clkin_ck"),
-	DT_CLK(NULL, "dbg_sysclk_ck", "dbg_sysclk_ck"),
-	DT_CLK(NULL, "dbg_clka_ck", "dbg_clka_ck"),
-	DT_CLK(NULL, "stm_pmd_clock_mux_ck", "stm_pmd_clock_mux_ck"),
-	DT_CLK(NULL, "trace_pmd_clk_mux_ck", "trace_pmd_clk_mux_ck"),
-	DT_CLK(NULL, "stm_clk_div_ck", "stm_clk_div_ck"),
-	DT_CLK(NULL, "trace_clk_div_ck", "trace_clk_div_ck"),
-	DT_CLK(NULL, "clkout2_ck", "clkout2_ck"),
-	DT_CLK("48300200.ehrpwm", "tbclk", "ehrpwm0_tbclk"),
-	DT_CLK("48302200.ehrpwm", "tbclk", "ehrpwm1_tbclk"),
-	DT_CLK("48304200.ehrpwm", "tbclk", "ehrpwm2_tbclk"),
-	DT_CLK("48300200.pwm", "tbclk", "ehrpwm0_tbclk"),
-	DT_CLK("48302200.pwm", "tbclk", "ehrpwm1_tbclk"),
-	DT_CLK("48304200.pwm", "tbclk", "ehrpwm2_tbclk"),
+	DT_CLK(NULL, "clkdiv32k_ick", "l4_per_cm:0138:0"),
+	DT_CLK(NULL, "dbg_clka_ck", "l4_wkup_cm:0010:30"),
+	DT_CLK(NULL, "dbg_sysclk_ck", "l4_wkup_cm:0010:19"),
+	DT_CLK(NULL, "gpio0_dbclk", "l4_wkup_cm:0004:18"),
+	DT_CLK(NULL, "gpio1_dbclk", "l4_per_cm:0098:18"),
+	DT_CLK(NULL, "gpio2_dbclk", "l4_per_cm:009c:18"),
+	DT_CLK(NULL, "gpio3_dbclk", "l4_per_cm:00a0:18"),
+	DT_CLK(NULL, "stm_clk_div_ck", "l4_wkup_cm:0010:27"),
+	DT_CLK(NULL, "stm_pmd_clock_mux_ck", "l4_wkup_cm:0010:22"),
+	DT_CLK(NULL, "trace_clk_div_ck", "l4_wkup_cm:0010:24"),
+	DT_CLK(NULL, "trace_pmd_clk_mux_ck", "l4_wkup_cm:0010:20"),
 	{ .node_name = NULL },
 };
 
@@ -133,6 +236,8 @@ int __init am33xx_dt_clk_init(void)
 
 	omap2_clk_disable_autoidle_all();
 
+	ti_clk_add_aliases();
+
 	omap2_clk_enable_init_clocks(enable_init_clks,
 				     ARRAY_SIZE(enable_init_clks));
 
diff --git a/drivers/clk/ti/clk-3xxx-legacy.c b/drivers/clk/ti/clk-3xxx-legacy.c
deleted file mode 100644
index 0fbf8a917955..000000000000
--- a/drivers/clk/ti/clk-3xxx-legacy.c
+++ /dev/null
@@ -1,4656 +0,0 @@
-/*
- * OMAP3 Legacy clock data
- *
- * Copyright (C) 2014 Texas Instruments, Inc
- *     Tero Kristo (t-kristo@ti.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#include <linux/kernel.h>
-#include <linux/clk.h>
-#include <linux/clk-provider.h>
-#include <linux/clk/ti.h>
-
-#include "clock.h"
-
-static struct ti_clk_fixed virt_12m_ck_data = {
-	.frequency = 12000000,
-};
-
-static struct ti_clk virt_12m_ck = {
-	.name = "virt_12m_ck",
-	.type = TI_CLK_FIXED,
-	.data = &virt_12m_ck_data,
-};
-
-static struct ti_clk_fixed virt_13m_ck_data = {
-	.frequency = 13000000,
-};
-
-static struct ti_clk virt_13m_ck = {
-	.name = "virt_13m_ck",
-	.type = TI_CLK_FIXED,
-	.data = &virt_13m_ck_data,
-};
-
-static struct ti_clk_fixed virt_19200000_ck_data = {
-	.frequency = 19200000,
-};
-
-static struct ti_clk virt_19200000_ck = {
-	.name = "virt_19200000_ck",
-	.type = TI_CLK_FIXED,
-	.data = &virt_19200000_ck_data,
-};
-
-static struct ti_clk_fixed virt_26000000_ck_data = {
-	.frequency = 26000000,
-};
-
-static struct ti_clk virt_26000000_ck = {
-	.name = "virt_26000000_ck",
-	.type = TI_CLK_FIXED,
-	.data = &virt_26000000_ck_data,
-};
-
-static struct ti_clk_fixed virt_38_4m_ck_data = {
-	.frequency = 38400000,
-};
-
-static struct ti_clk virt_38_4m_ck = {
-	.name = "virt_38_4m_ck",
-	.type = TI_CLK_FIXED,
-	.data = &virt_38_4m_ck_data,
-};
-
-static struct ti_clk_fixed virt_16_8m_ck_data = {
-	.frequency = 16800000,
-};
-
-static struct ti_clk virt_16_8m_ck = {
-	.name = "virt_16_8m_ck",
-	.type = TI_CLK_FIXED,
-	.data = &virt_16_8m_ck_data,
-};
-
-static const char *osc_sys_ck_parents[] = {
-	"virt_12m_ck",
-	"virt_13m_ck",
-	"virt_19200000_ck",
-	"virt_26000000_ck",
-	"virt_38_4m_ck",
-	"virt_16_8m_ck",
-};
-
-static struct ti_clk_mux osc_sys_ck_data = {
-	.num_parents = ARRAY_SIZE(osc_sys_ck_parents),
-	.reg = 0xd40,
-	.module = TI_CLKM_PRM,
-	.parents = osc_sys_ck_parents,
-};
-
-static struct ti_clk osc_sys_ck = {
-	.name = "osc_sys_ck",
-	.type = TI_CLK_MUX,
-	.data = &osc_sys_ck_data,
-};
-
-static struct ti_clk_divider sys_ck_data = {
-	.parent = "osc_sys_ck",
-	.bit_shift = 6,
-	.max_div = 3,
-	.reg = 0x1270,
-	.module = TI_CLKM_PRM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk sys_ck = {
-	.name = "sys_ck",
-	.type = TI_CLK_DIVIDER,
-	.data = &sys_ck_data,
-};
-
-static const char *dpll3_ck_parents[] = {
-	"sys_ck",
-	"sys_ck",
-};
-
-static struct ti_clk_dpll dpll3_ck_data = {
-	.num_parents = ARRAY_SIZE(dpll3_ck_parents),
-	.control_reg = 0xd00,
-	.idlest_reg = 0xd20,
-	.mult_div1_reg = 0xd40,
-	.autoidle_reg = 0xd30,
-	.module = TI_CLKM_CM,
-	.parents = dpll3_ck_parents,
-	.flags = CLKF_CORE,
-	.freqsel_mask = 0xf0,
-	.div1_mask = 0x7f00,
-	.idlest_mask = 0x1,
-	.auto_recal_bit = 0x3,
-	.max_divider = 0x80,
-	.min_divider = 0x1,
-	.recal_en_bit = 0x5,
-	.max_multiplier = 0x7ff,
-	.enable_mask = 0x7,
-	.mult_mask = 0x7ff0000,
-	.recal_st_bit = 0x5,
-	.autoidle_mask = 0x7,
-};
-
-static struct ti_clk dpll3_ck = {
-	.name = "dpll3_ck",
-	.clkdm_name = "dpll3_clkdm",
-	.type = TI_CLK_DPLL,
-	.data = &dpll3_ck_data,
-};
-
-static struct ti_clk_divider dpll3_m2_ck_data = {
-	.parent = "dpll3_ck",
-	.bit_shift = 27,
-	.max_div = 31,
-	.reg = 0xd40,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll3_m2_ck = {
-	.name = "dpll3_m2_ck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll3_m2_ck_data,
-};
-
-static struct ti_clk_fixed_factor core_ck_data = {
-	.parent = "dpll3_m2_ck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk core_ck = {
-	.name = "core_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &core_ck_data,
-};
-
-static struct ti_clk_divider l3_ick_data = {
-	.parent = "core_ck",
-	.max_div = 3,
-	.reg = 0xa40,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk l3_ick = {
-	.name = "l3_ick",
-	.type = TI_CLK_DIVIDER,
-	.data = &l3_ick_data,
-};
-
-static struct ti_clk_fixed_factor security_l3_ick_data = {
-	.parent = "l3_ick",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk security_l3_ick = {
-	.name = "security_l3_ick",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &security_l3_ick_data,
-};
-
-static struct ti_clk_fixed_factor wkup_l4_ick_data = {
-	.parent = "sys_ck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk wkup_l4_ick = {
-	.name = "wkup_l4_ick",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &wkup_l4_ick_data,
-};
-
-static struct ti_clk_gate usim_ick_data = {
-	.parent = "wkup_l4_ick",
-	.bit_shift = 9,
-	.reg = 0xc10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk usim_ick = {
-	.name = "usim_ick",
-	.clkdm_name = "wkup_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &usim_ick_data,
-};
-
-static struct ti_clk_gate dss2_alwon_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 1,
-	.reg = 0xe00,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk dss2_alwon_fck = {
-	.name = "dss2_alwon_fck",
-	.clkdm_name = "dss_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &dss2_alwon_fck_data,
-};
-
-static struct ti_clk_divider l4_ick_data = {
-	.parent = "l3_ick",
-	.bit_shift = 2,
-	.max_div = 3,
-	.reg = 0xa40,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk l4_ick = {
-	.name = "l4_ick",
-	.type = TI_CLK_DIVIDER,
-	.data = &l4_ick_data,
-};
-
-static struct ti_clk_fixed_factor core_l4_ick_data = {
-	.parent = "l4_ick",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk core_l4_ick = {
-	.name = "core_l4_ick",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &core_l4_ick_data,
-};
-
-static struct ti_clk_gate mmchs2_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 25,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mmchs2_ick = {
-	.name = "mmchs2_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mmchs2_ick_data,
-};
-
-static const char *dpll4_ck_parents[] = {
-	"sys_ck",
-	"sys_ck",
-};
-
-static struct ti_clk_dpll dpll4_ck_data = {
-	.num_parents = ARRAY_SIZE(dpll4_ck_parents),
-	.control_reg = 0xd00,
-	.idlest_reg = 0xd20,
-	.mult_div1_reg = 0xd44,
-	.autoidle_reg = 0xd30,
-	.module = TI_CLKM_CM,
-	.parents = dpll4_ck_parents,
-	.flags = CLKF_PER,
-	.freqsel_mask = 0xf00000,
-	.modes = 0x82,
-	.div1_mask = 0x7f,
-	.idlest_mask = 0x2,
-	.auto_recal_bit = 0x13,
-	.max_divider = 0x80,
-	.min_divider = 0x1,
-	.recal_en_bit = 0x6,
-	.max_multiplier = 0x7ff,
-	.enable_mask = 0x70000,
-	.mult_mask = 0x7ff00,
-	.recal_st_bit = 0x6,
-	.autoidle_mask = 0x38,
-};
-
-static struct ti_clk dpll4_ck = {
-	.name = "dpll4_ck",
-	.clkdm_name = "dpll4_clkdm",
-	.type = TI_CLK_DPLL,
-	.data = &dpll4_ck_data,
-};
-
-static struct ti_clk_divider dpll4_m2_ck_data = {
-	.parent = "dpll4_ck",
-	.max_div = 63,
-	.reg = 0xd48,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll4_m2_ck = {
-	.name = "dpll4_m2_ck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll4_m2_ck_data,
-};
-
-static struct ti_clk_fixed_factor dpll4_m2x2_mul_ck_data = {
-	.parent = "dpll4_m2_ck",
-	.div = 1,
-	.mult = 2,
-};
-
-static struct ti_clk dpll4_m2x2_mul_ck = {
-	.name = "dpll4_m2x2_mul_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll4_m2x2_mul_ck_data,
-};
-
-static struct ti_clk_gate dpll4_m2x2_ck_data = {
-	.parent = "dpll4_m2x2_mul_ck",
-	.bit_shift = 0x1b,
-	.reg = 0xd00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_SET_BIT_TO_DISABLE,
-};
-
-static struct ti_clk dpll4_m2x2_ck = {
-	.name = "dpll4_m2x2_ck",
-	.type = TI_CLK_GATE,
-	.data = &dpll4_m2x2_ck_data,
-};
-
-static struct ti_clk_fixed_factor omap_96m_alwon_fck_data = {
-	.parent = "dpll4_m2x2_ck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk omap_96m_alwon_fck = {
-	.name = "omap_96m_alwon_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &omap_96m_alwon_fck_data,
-};
-
-static struct ti_clk_fixed_factor cm_96m_fck_data = {
-	.parent = "omap_96m_alwon_fck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk cm_96m_fck = {
-	.name = "cm_96m_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &cm_96m_fck_data,
-};
-
-static const char *omap_96m_fck_parents[] = {
-	"cm_96m_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux omap_96m_fck_data = {
-	.bit_shift = 6,
-	.num_parents = ARRAY_SIZE(omap_96m_fck_parents),
-	.reg = 0xd40,
-	.module = TI_CLKM_CM,
-	.parents = omap_96m_fck_parents,
-};
-
-static struct ti_clk omap_96m_fck = {
-	.name = "omap_96m_fck",
-	.type = TI_CLK_MUX,
-	.data = &omap_96m_fck_data,
-};
-
-static struct ti_clk_fixed_factor core_96m_fck_data = {
-	.parent = "omap_96m_fck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk core_96m_fck = {
-	.name = "core_96m_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &core_96m_fck_data,
-};
-
-static struct ti_clk_gate mspro_fck_data = {
-	.parent = "core_96m_fck",
-	.bit_shift = 23,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk mspro_fck = {
-	.name = "mspro_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mspro_fck_data,
-};
-
-static struct ti_clk_gate dss_ick_3430es2_data = {
-	.parent = "l4_ick",
-	.bit_shift = 0,
-	.reg = 0xe10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_DSS | CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk dss_ick_3430es2 = {
-	.name = "dss_ick",
-	.clkdm_name = "dss_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &dss_ick_3430es2_data,
-};
-
-static struct ti_clk_gate uart4_ick_am35xx_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 23,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk uart4_ick_am35xx = {
-	.name = "uart4_ick_am35xx",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &uart4_ick_am35xx_data,
-};
-
-static struct ti_clk_fixed_factor security_l4_ick2_data = {
-	.parent = "l4_ick",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk security_l4_ick2 = {
-	.name = "security_l4_ick2",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &security_l4_ick2_data,
-};
-
-static struct ti_clk_gate aes1_ick_data = {
-	.parent = "security_l4_ick2",
-	.bit_shift = 3,
-	.reg = 0xa14,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk aes1_ick = {
-	.name = "aes1_ick",
-	.type = TI_CLK_GATE,
-	.data = &aes1_ick_data,
-};
-
-static const char *dpll5_ck_parents[] = {
-	"sys_ck",
-	"sys_ck",
-};
-
-static struct ti_clk_dpll dpll5_ck_data = {
-	.num_parents = ARRAY_SIZE(dpll5_ck_parents),
-	.control_reg = 0xd04,
-	.idlest_reg = 0xd24,
-	.mult_div1_reg = 0xd4c,
-	.autoidle_reg = 0xd34,
-	.module = TI_CLKM_CM,
-	.parents = dpll5_ck_parents,
-	.freqsel_mask = 0xf0,
-	.modes = 0x82,
-	.div1_mask = 0x7f,
-	.idlest_mask = 0x1,
-	.auto_recal_bit = 0x3,
-	.max_divider = 0x80,
-	.min_divider = 0x1,
-	.recal_en_bit = 0x19,
-	.max_multiplier = 0x7ff,
-	.enable_mask = 0x7,
-	.mult_mask = 0x7ff00,
-	.recal_st_bit = 0x19,
-	.autoidle_mask = 0x7,
-};
-
-static struct ti_clk dpll5_ck = {
-	.name = "dpll5_ck",
-	.clkdm_name = "dpll5_clkdm",
-	.type = TI_CLK_DPLL,
-	.data = &dpll5_ck_data,
-};
-
-static struct ti_clk_divider dpll5_m2_ck_data = {
-	.parent = "dpll5_ck",
-	.max_div = 31,
-	.reg = 0xd50,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll5_m2_ck = {
-	.name = "dpll5_m2_ck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll5_m2_ck_data,
-};
-
-static struct ti_clk_gate usbhost_120m_fck_data = {
-	.parent = "dpll5_m2_ck",
-	.bit_shift = 1,
-	.reg = 0x1400,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk usbhost_120m_fck = {
-	.name = "usbhost_120m_fck",
-	.clkdm_name = "usbhost_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &usbhost_120m_fck_data,
-};
-
-static struct ti_clk_fixed_factor cm_96m_d2_fck_data = {
-	.parent = "cm_96m_fck",
-	.div = 2,
-	.mult = 1,
-};
-
-static struct ti_clk cm_96m_d2_fck = {
-	.name = "cm_96m_d2_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &cm_96m_d2_fck_data,
-};
-
-static struct ti_clk_fixed sys_altclk_data = {
-	.frequency = 0x0,
-};
-
-static struct ti_clk sys_altclk = {
-	.name = "sys_altclk",
-	.type = TI_CLK_FIXED,
-	.data = &sys_altclk_data,
-};
-
-static const char *omap_48m_fck_parents[] = {
-	"cm_96m_d2_fck",
-	"sys_altclk",
-};
-
-static struct ti_clk_mux omap_48m_fck_data = {
-	.bit_shift = 3,
-	.num_parents = ARRAY_SIZE(omap_48m_fck_parents),
-	.reg = 0xd40,
-	.module = TI_CLKM_CM,
-	.parents = omap_48m_fck_parents,
-};
-
-static struct ti_clk omap_48m_fck = {
-	.name = "omap_48m_fck",
-	.type = TI_CLK_MUX,
-	.data = &omap_48m_fck_data,
-};
-
-static struct ti_clk_fixed_factor core_48m_fck_data = {
-	.parent = "omap_48m_fck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk core_48m_fck = {
-	.name = "core_48m_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &core_48m_fck_data,
-};
-
-static struct ti_clk_fixed mcbsp_clks_data = {
-	.frequency = 0x0,
-};
-
-static struct ti_clk mcbsp_clks = {
-	.name = "mcbsp_clks",
-	.type = TI_CLK_FIXED,
-	.data = &mcbsp_clks_data,
-};
-
-static struct ti_clk_gate mcbsp2_gate_fck_data = {
-	.parent = "mcbsp_clks",
-	.bit_shift = 0,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_fixed_factor per_96m_fck_data = {
-	.parent = "omap_96m_alwon_fck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk per_96m_fck = {
-	.name = "per_96m_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &per_96m_fck_data,
-};
-
-static const char *mcbsp2_mux_fck_parents[] = {
-	"per_96m_fck",
-	"mcbsp_clks",
-};
-
-static struct ti_clk_mux mcbsp2_mux_fck_data = {
-	.bit_shift = 6,
-	.num_parents = ARRAY_SIZE(mcbsp2_mux_fck_parents),
-	.reg = 0x274,
-	.module = TI_CLKM_SCRM,
-	.parents = mcbsp2_mux_fck_parents,
-};
-
-static struct ti_clk_composite mcbsp2_fck_data = {
-	.mux = &mcbsp2_mux_fck_data,
-	.gate = &mcbsp2_gate_fck_data,
-};
-
-static struct ti_clk mcbsp2_fck = {
-	.name = "mcbsp2_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &mcbsp2_fck_data,
-};
-
-static struct ti_clk_fixed_factor dpll3_m2x2_ck_data = {
-	.parent = "dpll3_m2_ck",
-	.div = 1,
-	.mult = 2,
-};
-
-static struct ti_clk dpll3_m2x2_ck = {
-	.name = "dpll3_m2x2_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll3_m2x2_ck_data,
-};
-
-static struct ti_clk_fixed_factor corex2_fck_data = {
-	.parent = "dpll3_m2x2_ck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk corex2_fck = {
-	.name = "corex2_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &corex2_fck_data,
-};
-
-static struct ti_clk_gate ssi_ssr_gate_fck_3430es1_data = {
-	.parent = "corex2_fck",
-	.bit_shift = 0,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_NO_WAIT,
-};
-
-static int ssi_ssr_div_fck_3430es1_divs[] = {
-	0,
-	1,
-	2,
-	3,
-	4,
-	0,
-	6,
-	0,
-	8,
-};
-
-static struct ti_clk_divider ssi_ssr_div_fck_3430es1_data = {
-	.num_dividers = ARRAY_SIZE(ssi_ssr_div_fck_3430es1_divs),
-	.parent = "corex2_fck",
-	.bit_shift = 8,
-	.dividers = ssi_ssr_div_fck_3430es1_divs,
-	.reg = 0xa40,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_composite ssi_ssr_fck_3430es1_data = {
-	.gate = &ssi_ssr_gate_fck_3430es1_data,
-	.divider = &ssi_ssr_div_fck_3430es1_data,
-};
-
-static struct ti_clk ssi_ssr_fck_3430es1 = {
-	.name = "ssi_ssr_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &ssi_ssr_fck_3430es1_data,
-};
-
-static struct ti_clk_fixed_factor ssi_sst_fck_3430es1_data = {
-	.parent = "ssi_ssr_fck",
-	.div = 2,
-	.mult = 1,
-};
-
-static struct ti_clk ssi_sst_fck_3430es1 = {
-	.name = "ssi_sst_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &ssi_sst_fck_3430es1_data,
-};
-
-static struct ti_clk_fixed omap_32k_fck_data = {
-	.frequency = 32768,
-};
-
-static struct ti_clk omap_32k_fck = {
-	.name = "omap_32k_fck",
-	.type = TI_CLK_FIXED,
-	.data = &omap_32k_fck_data,
-};
-
-static struct ti_clk_fixed_factor per_32k_alwon_fck_data = {
-	.parent = "omap_32k_fck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk per_32k_alwon_fck = {
-	.name = "per_32k_alwon_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &per_32k_alwon_fck_data,
-};
-
-static struct ti_clk_gate gpio5_dbck_data = {
-	.parent = "per_32k_alwon_fck",
-	.bit_shift = 16,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk gpio5_dbck = {
-	.name = "gpio5_dbck",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio5_dbck_data,
-};
-
-static struct ti_clk_gate gpt1_ick_data = {
-	.parent = "wkup_l4_ick",
-	.bit_shift = 0,
-	.reg = 0xc10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt1_ick = {
-	.name = "gpt1_ick",
-	.clkdm_name = "wkup_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt1_ick_data,
-};
-
-static struct ti_clk_gate mcspi3_fck_data = {
-	.parent = "core_48m_fck",
-	.bit_shift = 20,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk mcspi3_fck = {
-	.name = "mcspi3_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcspi3_fck_data,
-};
-
-static struct ti_clk_gate gpt2_gate_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 3,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static const char *gpt2_mux_fck_parents[] = {
-	"omap_32k_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux gpt2_mux_fck_data = {
-	.num_parents = ARRAY_SIZE(gpt2_mux_fck_parents),
-	.reg = 0x1040,
-	.module = TI_CLKM_CM,
-	.parents = gpt2_mux_fck_parents,
-};
-
-static struct ti_clk_composite gpt2_fck_data = {
-	.mux = &gpt2_mux_fck_data,
-	.gate = &gpt2_gate_fck_data,
-};
-
-static struct ti_clk gpt2_fck = {
-	.name = "gpt2_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &gpt2_fck_data,
-};
-
-static struct ti_clk_gate gpt10_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 11,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt10_ick = {
-	.name = "gpt10_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt10_ick_data,
-};
-
-static struct ti_clk_gate uart2_fck_data = {
-	.parent = "core_48m_fck",
-	.bit_shift = 14,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk uart2_fck = {
-	.name = "uart2_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &uart2_fck_data,
-};
-
-static struct ti_clk_fixed_factor sr_l4_ick_data = {
-	.parent = "l4_ick",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk sr_l4_ick = {
-	.name = "sr_l4_ick",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &sr_l4_ick_data,
-};
-
-static struct ti_clk_fixed_factor omap_96m_d8_fck_data = {
-	.parent = "omap_96m_fck",
-	.div = 8,
-	.mult = 1,
-};
-
-static struct ti_clk omap_96m_d8_fck = {
-	.name = "omap_96m_d8_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &omap_96m_d8_fck_data,
-};
-
-static struct ti_clk_divider dpll4_m5_ck_data = {
-	.parent = "dpll4_ck",
-	.max_div = 63,
-	.reg = 0xf40,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll4_m5_ck = {
-	.name = "dpll4_m5_ck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll4_m5_ck_data,
-};
-
-static struct ti_clk_fixed_factor dpll4_m5x2_mul_ck_data = {
-	.parent = "dpll4_m5_ck",
-	.div = 1,
-	.mult = 2,
-	.flags = CLKF_SET_RATE_PARENT,
-};
-
-static struct ti_clk dpll4_m5x2_mul_ck = {
-	.name = "dpll4_m5x2_mul_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll4_m5x2_mul_ck_data,
-};
-
-static struct ti_clk_gate dpll4_m5x2_ck_data = {
-	.parent = "dpll4_m5x2_mul_ck",
-	.bit_shift = 0x1e,
-	.reg = 0xd00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_SET_BIT_TO_DISABLE,
-};
-
-static struct ti_clk dpll4_m5x2_ck = {
-	.name = "dpll4_m5x2_ck",
-	.type = TI_CLK_GATE,
-	.data = &dpll4_m5x2_ck_data,
-};
-
-static struct ti_clk_gate cam_mclk_data = {
-	.parent = "dpll4_m5x2_ck",
-	.bit_shift = 0,
-	.reg = 0xf00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_SET_RATE_PARENT,
-};
-
-static struct ti_clk cam_mclk = {
-	.name = "cam_mclk",
-	.type = TI_CLK_GATE,
-	.data = &cam_mclk_data,
-};
-
-static struct ti_clk_gate mcbsp3_gate_fck_data = {
-	.parent = "mcbsp_clks",
-	.bit_shift = 1,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static const char *mcbsp3_mux_fck_parents[] = {
-	"per_96m_fck",
-	"mcbsp_clks",
-};
-
-static struct ti_clk_mux mcbsp3_mux_fck_data = {
-	.num_parents = ARRAY_SIZE(mcbsp3_mux_fck_parents),
-	.reg = 0x2d8,
-	.module = TI_CLKM_SCRM,
-	.parents = mcbsp3_mux_fck_parents,
-};
-
-static struct ti_clk_composite mcbsp3_fck_data = {
-	.mux = &mcbsp3_mux_fck_data,
-	.gate = &mcbsp3_gate_fck_data,
-};
-
-static struct ti_clk mcbsp3_fck = {
-	.name = "mcbsp3_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &mcbsp3_fck_data,
-};
-
-static struct ti_clk_gate csi2_96m_fck_data = {
-	.parent = "core_96m_fck",
-	.bit_shift = 1,
-	.reg = 0xf00,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk csi2_96m_fck = {
-	.name = "csi2_96m_fck",
-	.clkdm_name = "cam_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &csi2_96m_fck_data,
-};
-
-static struct ti_clk_gate gpt9_gate_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 10,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static const char *gpt9_mux_fck_parents[] = {
-	"omap_32k_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux gpt9_mux_fck_data = {
-	.bit_shift = 7,
-	.num_parents = ARRAY_SIZE(gpt9_mux_fck_parents),
-	.reg = 0x1040,
-	.module = TI_CLKM_CM,
-	.parents = gpt9_mux_fck_parents,
-};
-
-static struct ti_clk_composite gpt9_fck_data = {
-	.mux = &gpt9_mux_fck_data,
-	.gate = &gpt9_gate_fck_data,
-};
-
-static struct ti_clk gpt9_fck = {
-	.name = "gpt9_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &gpt9_fck_data,
-};
-
-static struct ti_clk_divider dpll3_m3_ck_data = {
-	.parent = "dpll3_ck",
-	.bit_shift = 16,
-	.max_div = 31,
-	.reg = 0x1140,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll3_m3_ck = {
-	.name = "dpll3_m3_ck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll3_m3_ck_data,
-};
-
-static struct ti_clk_fixed_factor dpll3_m3x2_mul_ck_data = {
-	.parent = "dpll3_m3_ck",
-	.div = 1,
-	.mult = 2,
-};
-
-static struct ti_clk dpll3_m3x2_mul_ck = {
-	.name = "dpll3_m3x2_mul_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll3_m3x2_mul_ck_data,
-};
-
-static struct ti_clk_gate sr2_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 7,
-	.reg = 0xc00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk sr2_fck = {
-	.name = "sr2_fck",
-	.clkdm_name = "wkup_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &sr2_fck_data,
-};
-
-static struct ti_clk_fixed pclk_ck_data = {
-	.frequency = 27000000,
-};
-
-static struct ti_clk pclk_ck = {
-	.name = "pclk_ck",
-	.type = TI_CLK_FIXED,
-	.data = &pclk_ck_data,
-};
-
-static struct ti_clk_gate wdt2_ick_data = {
-	.parent = "wkup_l4_ick",
-	.bit_shift = 5,
-	.reg = 0xc10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk wdt2_ick = {
-	.name = "wdt2_ick",
-	.clkdm_name = "wkup_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &wdt2_ick_data,
-};
-
-static struct ti_clk_fixed_factor core_l3_ick_data = {
-	.parent = "l3_ick",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk core_l3_ick = {
-	.name = "core_l3_ick",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &core_l3_ick_data,
-};
-
-static struct ti_clk_gate mcspi4_fck_data = {
-	.parent = "core_48m_fck",
-	.bit_shift = 21,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk mcspi4_fck = {
-	.name = "mcspi4_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcspi4_fck_data,
-};
-
-static struct ti_clk_fixed_factor per_48m_fck_data = {
-	.parent = "omap_48m_fck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk per_48m_fck = {
-	.name = "per_48m_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &per_48m_fck_data,
-};
-
-static struct ti_clk_gate uart4_fck_data = {
-	.parent = "per_48m_fck",
-	.bit_shift = 18,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk uart4_fck = {
-	.name = "uart4_fck",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &uart4_fck_data,
-};
-
-static struct ti_clk_fixed_factor omap_96m_d10_fck_data = {
-	.parent = "omap_96m_fck",
-	.div = 10,
-	.mult = 1,
-};
-
-static struct ti_clk omap_96m_d10_fck = {
-	.name = "omap_96m_d10_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &omap_96m_d10_fck_data,
-};
-
-static struct ti_clk_gate usim_gate_fck_data = {
-	.parent = "omap_96m_fck",
-	.bit_shift = 9,
-	.reg = 0xc00,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_fixed_factor per_l4_ick_data = {
-	.parent = "l4_ick",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk per_l4_ick = {
-	.name = "per_l4_ick",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &per_l4_ick_data,
-};
-
-static struct ti_clk_gate gpt5_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 6,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt5_ick = {
-	.name = "gpt5_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt5_ick_data,
-};
-
-static struct ti_clk_gate mcspi2_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 19,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mcspi2_ick = {
-	.name = "mcspi2_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcspi2_ick_data,
-};
-
-static struct ti_clk_fixed_factor ssi_l4_ick_data = {
-	.parent = "l4_ick",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk ssi_l4_ick = {
-	.name = "ssi_l4_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &ssi_l4_ick_data,
-};
-
-static struct ti_clk_gate ssi_ick_3430es1_data = {
-	.parent = "ssi_l4_ick",
-	.bit_shift = 0,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_NO_WAIT | CLKF_INTERFACE,
-};
-
-static struct ti_clk ssi_ick_3430es1 = {
-	.name = "ssi_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &ssi_ick_3430es1_data,
-};
-
-static struct ti_clk_gate i2c2_fck_data = {
-	.parent = "core_96m_fck",
-	.bit_shift = 16,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk i2c2_fck = {
-	.name = "i2c2_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &i2c2_fck_data,
-};
-
-static struct ti_clk_divider dpll1_fck_data = {
-	.parent = "core_ck",
-	.bit_shift = 19,
-	.max_div = 7,
-	.reg = 0x940,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll1_fck = {
-	.name = "dpll1_fck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll1_fck_data,
-};
-
-static const char *dpll1_ck_parents[] = {
-	"sys_ck",
-	"dpll1_fck",
-};
-
-static struct ti_clk_dpll dpll1_ck_data = {
-	.num_parents = ARRAY_SIZE(dpll1_ck_parents),
-	.control_reg = 0x904,
-	.idlest_reg = 0x924,
-	.mult_div1_reg = 0x940,
-	.autoidle_reg = 0x934,
-	.module = TI_CLKM_CM,
-	.parents = dpll1_ck_parents,
-	.freqsel_mask = 0xf0,
-	.modes = 0xa0,
-	.div1_mask = 0x7f,
-	.idlest_mask = 0x1,
-	.auto_recal_bit = 0x3,
-	.max_divider = 0x80,
-	.min_divider = 0x1,
-	.recal_en_bit = 0x7,
-	.max_multiplier = 0x7ff,
-	.enable_mask = 0x7,
-	.mult_mask = 0x7ff00,
-	.recal_st_bit = 0x7,
-	.autoidle_mask = 0x7,
-};
-
-static struct ti_clk dpll1_ck = {
-	.name = "dpll1_ck",
-	.clkdm_name = "dpll1_clkdm",
-	.type = TI_CLK_DPLL,
-	.data = &dpll1_ck_data,
-};
-
-static struct ti_clk_fixed secure_32k_fck_data = {
-	.frequency = 32768,
-};
-
-static struct ti_clk secure_32k_fck = {
-	.name = "secure_32k_fck",
-	.type = TI_CLK_FIXED,
-	.data = &secure_32k_fck_data,
-};
-
-static struct ti_clk_gate gpio5_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 16,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpio5_ick = {
-	.name = "gpio5_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio5_ick_data,
-};
-
-static struct ti_clk_divider dpll4_m4_ck_data = {
-	.parent = "dpll4_ck",
-	.max_div = 32,
-	.reg = 0xe40,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll4_m4_ck = {
-	.name = "dpll4_m4_ck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll4_m4_ck_data,
-};
-
-static struct ti_clk_fixed_factor dpll4_m4x2_mul_ck_data = {
-	.parent = "dpll4_m4_ck",
-	.div = 1,
-	.mult = 2,
-	.flags = CLKF_SET_RATE_PARENT,
-};
-
-static struct ti_clk dpll4_m4x2_mul_ck = {
-	.name = "dpll4_m4x2_mul_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll4_m4x2_mul_ck_data,
-};
-
-static struct ti_clk_gate dpll4_m4x2_ck_data = {
-	.parent = "dpll4_m4x2_mul_ck",
-	.bit_shift = 0x1d,
-	.reg = 0xd00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_SET_RATE_PARENT | CLKF_SET_BIT_TO_DISABLE,
-};
-
-static struct ti_clk dpll4_m4x2_ck = {
-	.name = "dpll4_m4x2_ck",
-	.type = TI_CLK_GATE,
-	.data = &dpll4_m4x2_ck_data,
-};
-
-static struct ti_clk_gate dss1_alwon_fck_3430es2_data = {
-	.parent = "dpll4_m4x2_ck",
-	.bit_shift = 0,
-	.reg = 0xe00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_DSS | CLKF_SET_RATE_PARENT,
-};
-
-static struct ti_clk dss1_alwon_fck_3430es2 = {
-	.name = "dss1_alwon_fck",
-	.clkdm_name = "dss_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &dss1_alwon_fck_3430es2_data,
-};
-
-static struct ti_clk_gate uart3_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 11,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk uart3_ick = {
-	.name = "uart3_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &uart3_ick_data,
-};
-
-static struct ti_clk_divider dpll4_m3_ck_data = {
-	.parent = "dpll4_ck",
-	.bit_shift = 8,
-	.max_div = 32,
-	.reg = 0xe40,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll4_m3_ck = {
-	.name = "dpll4_m3_ck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll4_m3_ck_data,
-};
-
-static struct ti_clk_gate mcbsp3_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 1,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mcbsp3_ick = {
-	.name = "mcbsp3_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcbsp3_ick_data,
-};
-
-static struct ti_clk_gate gpio3_dbck_data = {
-	.parent = "per_32k_alwon_fck",
-	.bit_shift = 14,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk gpio3_dbck = {
-	.name = "gpio3_dbck",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio3_dbck_data,
-};
-
-static struct ti_clk_gate fac_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 8,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk fac_ick = {
-	.name = "fac_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &fac_ick_data,
-};
-
-static struct ti_clk_gate clkout2_src_gate_ck_data = {
-	.parent = "core_ck",
-	.bit_shift = 7,
-	.reg = 0xd70,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_NO_WAIT,
-};
-
-static struct ti_clk_fixed_factor dpll4_m3x2_mul_ck_data = {
-	.parent = "dpll4_m3_ck",
-	.div = 1,
-	.mult = 2,
-};
-
-static struct ti_clk dpll4_m3x2_mul_ck = {
-	.name = "dpll4_m3x2_mul_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll4_m3x2_mul_ck_data,
-};
-
-static struct ti_clk_gate dpll4_m3x2_ck_data = {
-	.parent = "dpll4_m3x2_mul_ck",
-	.bit_shift = 0x1c,
-	.reg = 0xd00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_SET_BIT_TO_DISABLE,
-};
-
-static struct ti_clk dpll4_m3x2_ck = {
-	.name = "dpll4_m3x2_ck",
-	.type = TI_CLK_GATE,
-	.data = &dpll4_m3x2_ck_data,
-};
-
-static const char *omap_54m_fck_parents[] = {
-	"dpll4_m3x2_ck",
-	"sys_altclk",
-};
-
-static struct ti_clk_mux omap_54m_fck_data = {
-	.bit_shift = 5,
-	.num_parents = ARRAY_SIZE(omap_54m_fck_parents),
-	.reg = 0xd40,
-	.module = TI_CLKM_CM,
-	.parents = omap_54m_fck_parents,
-};
-
-static struct ti_clk omap_54m_fck = {
-	.name = "omap_54m_fck",
-	.type = TI_CLK_MUX,
-	.data = &omap_54m_fck_data,
-};
-
-static const char *clkout2_src_mux_ck_parents[] = {
-	"core_ck",
-	"sys_ck",
-	"cm_96m_fck",
-	"omap_54m_fck",
-};
-
-static struct ti_clk_mux clkout2_src_mux_ck_data = {
-	.num_parents = ARRAY_SIZE(clkout2_src_mux_ck_parents),
-	.reg = 0xd70,
-	.module = TI_CLKM_CM,
-	.parents = clkout2_src_mux_ck_parents,
-};
-
-static struct ti_clk_composite clkout2_src_ck_data = {
-	.mux = &clkout2_src_mux_ck_data,
-	.gate = &clkout2_src_gate_ck_data,
-};
-
-static struct ti_clk clkout2_src_ck = {
-	.name = "clkout2_src_ck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &clkout2_src_ck_data,
-};
-
-static struct ti_clk_gate i2c1_fck_data = {
-	.parent = "core_96m_fck",
-	.bit_shift = 15,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk i2c1_fck = {
-	.name = "i2c1_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &i2c1_fck_data,
-};
-
-static struct ti_clk_gate wdt3_fck_data = {
-	.parent = "per_32k_alwon_fck",
-	.bit_shift = 12,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk wdt3_fck = {
-	.name = "wdt3_fck",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &wdt3_fck_data,
-};
-
-static struct ti_clk_gate gpt7_gate_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 8,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static const char *gpt7_mux_fck_parents[] = {
-	"omap_32k_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux gpt7_mux_fck_data = {
-	.bit_shift = 5,
-	.num_parents = ARRAY_SIZE(gpt7_mux_fck_parents),
-	.reg = 0x1040,
-	.module = TI_CLKM_CM,
-	.parents = gpt7_mux_fck_parents,
-};
-
-static struct ti_clk_composite gpt7_fck_data = {
-	.mux = &gpt7_mux_fck_data,
-	.gate = &gpt7_gate_fck_data,
-};
-
-static struct ti_clk gpt7_fck = {
-	.name = "gpt7_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &gpt7_fck_data,
-};
-
-static struct ti_clk_gate usb_l4_gate_ick_data = {
-	.parent = "l4_ick",
-	.bit_shift = 5,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INTERFACE,
-};
-
-static struct ti_clk_divider usb_l4_div_ick_data = {
-	.parent = "l4_ick",
-	.bit_shift = 4,
-	.max_div = 1,
-	.reg = 0xa40,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk_composite usb_l4_ick_data = {
-	.gate = &usb_l4_gate_ick_data,
-	.divider = &usb_l4_div_ick_data,
-};
-
-static struct ti_clk usb_l4_ick = {
-	.name = "usb_l4_ick",
-	.type = TI_CLK_COMPOSITE,
-	.data = &usb_l4_ick_data,
-};
-
-static struct ti_clk_gate uart4_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 18,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk uart4_ick = {
-	.name = "uart4_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &uart4_ick_data,
-};
-
-static struct ti_clk_fixed dummy_ck_data = {
-	.frequency = 0,
-};
-
-static struct ti_clk dummy_ck = {
-	.name = "dummy_ck",
-	.type = TI_CLK_FIXED,
-	.data = &dummy_ck_data,
-};
-
-static const char *gpt3_mux_fck_parents[] = {
-	"omap_32k_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux gpt3_mux_fck_data = {
-	.bit_shift = 1,
-	.num_parents = ARRAY_SIZE(gpt3_mux_fck_parents),
-	.reg = 0x1040,
-	.module = TI_CLKM_CM,
-	.parents = gpt3_mux_fck_parents,
-};
-
-static struct ti_clk_gate gpt9_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 10,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt9_ick = {
-	.name = "gpt9_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt9_ick_data,
-};
-
-static struct ti_clk_gate gpt10_gate_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 11,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_gate dss_ick_3430es1_data = {
-	.parent = "l4_ick",
-	.bit_shift = 0,
-	.reg = 0xe10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_NO_WAIT | CLKF_INTERFACE,
-};
-
-static struct ti_clk dss_ick_3430es1 = {
-	.name = "dss_ick",
-	.clkdm_name = "dss_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &dss_ick_3430es1_data,
-};
-
-static struct ti_clk_gate gpt11_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 12,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt11_ick = {
-	.name = "gpt11_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt11_ick_data,
-};
-
-static struct ti_clk_divider dpll2_fck_data = {
-	.parent = "core_ck",
-	.bit_shift = 19,
-	.max_div = 7,
-	.reg = 0x40,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll2_fck = {
-	.name = "dpll2_fck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll2_fck_data,
-};
-
-static struct ti_clk_gate uart1_fck_data = {
-	.parent = "core_48m_fck",
-	.bit_shift = 13,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk uart1_fck = {
-	.name = "uart1_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &uart1_fck_data,
-};
-
-static struct ti_clk_gate hsotgusb_ick_3430es1_data = {
-	.parent = "core_l3_ick",
-	.bit_shift = 4,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_NO_WAIT | CLKF_INTERFACE,
-};
-
-static struct ti_clk hsotgusb_ick_3430es1 = {
-	.name = "hsotgusb_ick_3430es1",
-	.clkdm_name = "core_l3_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &hsotgusb_ick_3430es1_data,
-};
-
-static struct ti_clk_gate gpio2_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 13,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpio2_ick = {
-	.name = "gpio2_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio2_ick_data,
-};
-
-static struct ti_clk_gate mmchs1_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 24,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mmchs1_ick = {
-	.name = "mmchs1_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mmchs1_ick_data,
-};
-
-static struct ti_clk_gate modem_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 31,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk modem_fck = {
-	.name = "modem_fck",
-	.clkdm_name = "d2d_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &modem_fck_data,
-};
-
-static struct ti_clk_gate mcbsp4_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 2,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mcbsp4_ick = {
-	.name = "mcbsp4_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcbsp4_ick_data,
-};
-
-static struct ti_clk_gate gpio1_ick_data = {
-	.parent = "wkup_l4_ick",
-	.bit_shift = 3,
-	.reg = 0xc10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpio1_ick = {
-	.name = "gpio1_ick",
-	.clkdm_name = "wkup_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio1_ick_data,
-};
-
-static const char *gpt6_mux_fck_parents[] = {
-	"omap_32k_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux gpt6_mux_fck_data = {
-	.bit_shift = 4,
-	.num_parents = ARRAY_SIZE(gpt6_mux_fck_parents),
-	.reg = 0x1040,
-	.module = TI_CLKM_CM,
-	.parents = gpt6_mux_fck_parents,
-};
-
-static struct ti_clk_fixed_factor dpll1_x2_ck_data = {
-	.parent = "dpll1_ck",
-	.div = 1,
-	.mult = 2,
-};
-
-static struct ti_clk dpll1_x2_ck = {
-	.name = "dpll1_x2_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll1_x2_ck_data,
-};
-
-static struct ti_clk_divider dpll1_x2m2_ck_data = {
-	.parent = "dpll1_x2_ck",
-	.max_div = 31,
-	.reg = 0x944,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll1_x2m2_ck = {
-	.name = "dpll1_x2m2_ck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll1_x2m2_ck_data,
-};
-
-static struct ti_clk_fixed_factor mpu_ck_data = {
-	.parent = "dpll1_x2m2_ck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk mpu_ck = {
-	.name = "mpu_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &mpu_ck_data,
-};
-
-static struct ti_clk_divider arm_fck_data = {
-	.parent = "mpu_ck",
-	.max_div = 2,
-	.reg = 0x924,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk arm_fck = {
-	.name = "arm_fck",
-	.type = TI_CLK_DIVIDER,
-	.data = &arm_fck_data,
-};
-
-static struct ti_clk_fixed_factor core_d3_ck_data = {
-	.parent = "core_ck",
-	.div = 3,
-	.mult = 1,
-};
-
-static struct ti_clk core_d3_ck = {
-	.name = "core_d3_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &core_d3_ck_data,
-};
-
-static struct ti_clk_gate gpt11_gate_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 12,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-};
-
-static const char *gpt11_mux_fck_parents[] = {
-	"omap_32k_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux gpt11_mux_fck_data = {
-	.bit_shift = 7,
-	.num_parents = ARRAY_SIZE(gpt11_mux_fck_parents),
-	.reg = 0xa40,
-	.module = TI_CLKM_CM,
-	.parents = gpt11_mux_fck_parents,
-};
-
-static struct ti_clk_composite gpt11_fck_data = {
-	.mux = &gpt11_mux_fck_data,
-	.gate = &gpt11_gate_fck_data,
-};
-
-static struct ti_clk gpt11_fck = {
-	.name = "gpt11_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &gpt11_fck_data,
-};
-
-static struct ti_clk_fixed_factor core_d6_ck_data = {
-	.parent = "core_ck",
-	.div = 6,
-	.mult = 1,
-};
-
-static struct ti_clk core_d6_ck = {
-	.name = "core_d6_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &core_d6_ck_data,
-};
-
-static struct ti_clk_gate uart4_fck_am35xx_data = {
-	.parent = "core_48m_fck",
-	.bit_shift = 23,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk uart4_fck_am35xx = {
-	.name = "uart4_fck_am35xx",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &uart4_fck_am35xx_data,
-};
-
-static struct ti_clk_gate dpll3_m3x2_ck_data = {
-	.parent = "dpll3_m3x2_mul_ck",
-	.bit_shift = 0xc,
-	.reg = 0xd00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_SET_BIT_TO_DISABLE,
-};
-
-static struct ti_clk dpll3_m3x2_ck = {
-	.name = "dpll3_m3x2_ck",
-	.type = TI_CLK_GATE,
-	.data = &dpll3_m3x2_ck_data,
-};
-
-static struct ti_clk_fixed_factor emu_core_alwon_ck_data = {
-	.parent = "dpll3_m3x2_ck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk emu_core_alwon_ck = {
-	.name = "emu_core_alwon_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &emu_core_alwon_ck_data,
-};
-
-static struct ti_clk_divider dpll4_m6_ck_data = {
-	.parent = "dpll4_ck",
-	.bit_shift = 24,
-	.max_div = 63,
-	.reg = 0x1140,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll4_m6_ck = {
-	.name = "dpll4_m6_ck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll4_m6_ck_data,
-};
-
-static struct ti_clk_fixed_factor dpll4_m6x2_mul_ck_data = {
-	.parent = "dpll4_m6_ck",
-	.div = 1,
-	.mult = 2,
-};
-
-static struct ti_clk dpll4_m6x2_mul_ck = {
-	.name = "dpll4_m6x2_mul_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll4_m6x2_mul_ck_data,
-};
-
-static struct ti_clk_gate dpll4_m6x2_ck_data = {
-	.parent = "dpll4_m6x2_mul_ck",
-	.bit_shift = 0x1f,
-	.reg = 0xd00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_SET_BIT_TO_DISABLE,
-};
-
-static struct ti_clk dpll4_m6x2_ck = {
-	.name = "dpll4_m6x2_ck",
-	.type = TI_CLK_GATE,
-	.data = &dpll4_m6x2_ck_data,
-};
-
-static struct ti_clk_fixed_factor emu_per_alwon_ck_data = {
-	.parent = "dpll4_m6x2_ck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk emu_per_alwon_ck = {
-	.name = "emu_per_alwon_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &emu_per_alwon_ck_data,
-};
-
-static struct ti_clk_fixed_factor emu_mpu_alwon_ck_data = {
-	.parent = "mpu_ck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk emu_mpu_alwon_ck = {
-	.name = "emu_mpu_alwon_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &emu_mpu_alwon_ck_data,
-};
-
-static const char *emu_src_mux_ck_parents[] = {
-	"sys_ck",
-	"emu_core_alwon_ck",
-	"emu_per_alwon_ck",
-	"emu_mpu_alwon_ck",
-};
-
-static struct ti_clk_mux emu_src_mux_ck_data = {
-	.num_parents = ARRAY_SIZE(emu_src_mux_ck_parents),
-	.reg = 0x1140,
-	.module = TI_CLKM_CM,
-	.parents = emu_src_mux_ck_parents,
-};
-
-static struct ti_clk emu_src_mux_ck = {
-	.name = "emu_src_mux_ck",
-	.type = TI_CLK_MUX,
-	.data = &emu_src_mux_ck_data,
-};
-
-static struct ti_clk_gate emu_src_ck_data = {
-	.parent = "emu_src_mux_ck",
-	.flags = CLKF_CLKDM,
-};
-
-static struct ti_clk emu_src_ck = {
-	.name = "emu_src_ck",
-	.clkdm_name = "emu_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &emu_src_ck_data,
-};
-
-static struct ti_clk_divider atclk_fck_data = {
-	.parent = "emu_src_ck",
-	.bit_shift = 4,
-	.max_div = 3,
-	.reg = 0x1140,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk atclk_fck = {
-	.name = "atclk_fck",
-	.type = TI_CLK_DIVIDER,
-	.data = &atclk_fck_data,
-};
-
-static struct ti_clk_gate ipss_ick_data = {
-	.parent = "core_l3_ick",
-	.bit_shift = 4,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_AM35XX | CLKF_INTERFACE,
-};
-
-static struct ti_clk ipss_ick = {
-	.name = "ipss_ick",
-	.clkdm_name = "core_l3_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &ipss_ick_data,
-};
-
-static struct ti_clk_gate emac_ick_data = {
-	.parent = "ipss_ick",
-	.bit_shift = 1,
-	.reg = 0x59c,
-	.module = TI_CLKM_SCRM,
-	.flags = CLKF_AM35XX,
-};
-
-static struct ti_clk emac_ick = {
-	.name = "emac_ick",
-	.clkdm_name = "core_l3_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &emac_ick_data,
-};
-
-static struct ti_clk_gate vpfe_ick_data = {
-	.parent = "ipss_ick",
-	.bit_shift = 2,
-	.reg = 0x59c,
-	.module = TI_CLKM_SCRM,
-	.flags = CLKF_AM35XX,
-};
-
-static struct ti_clk vpfe_ick = {
-	.name = "vpfe_ick",
-	.clkdm_name = "core_l3_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &vpfe_ick_data,
-};
-
-static const char *dpll2_ck_parents[] = {
-	"sys_ck",
-	"dpll2_fck",
-};
-
-static struct ti_clk_dpll dpll2_ck_data = {
-	.num_parents = ARRAY_SIZE(dpll2_ck_parents),
-	.control_reg = 0x4,
-	.idlest_reg = 0x24,
-	.mult_div1_reg = 0x40,
-	.autoidle_reg = 0x34,
-	.module = TI_CLKM_CM,
-	.parents = dpll2_ck_parents,
-	.freqsel_mask = 0xf0,
-	.modes = 0xa2,
-	.div1_mask = 0x7f,
-	.idlest_mask = 0x1,
-	.auto_recal_bit = 0x3,
-	.max_divider = 0x80,
-	.min_divider = 0x1,
-	.recal_en_bit = 0x8,
-	.max_multiplier = 0x7ff,
-	.enable_mask = 0x7,
-	.mult_mask = 0x7ff00,
-	.recal_st_bit = 0x8,
-	.autoidle_mask = 0x7,
-};
-
-static struct ti_clk dpll2_ck = {
-	.name = "dpll2_ck",
-	.clkdm_name = "dpll2_clkdm",
-	.type = TI_CLK_DPLL,
-	.data = &dpll2_ck_data,
-};
-
-static struct ti_clk_divider dpll2_m2_ck_data = {
-	.parent = "dpll2_ck",
-	.max_div = 31,
-	.reg = 0x44,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk dpll2_m2_ck = {
-	.name = "dpll2_m2_ck",
-	.type = TI_CLK_DIVIDER,
-	.data = &dpll2_m2_ck_data,
-};
-
-static const char *mcbsp4_mux_fck_parents[] = {
-	"per_96m_fck",
-	"mcbsp_clks",
-};
-
-static struct ti_clk_mux mcbsp4_mux_fck_data = {
-	.bit_shift = 2,
-	.num_parents = ARRAY_SIZE(mcbsp4_mux_fck_parents),
-	.reg = 0x2d8,
-	.module = TI_CLKM_SCRM,
-	.parents = mcbsp4_mux_fck_parents,
-};
-
-static const char *mcbsp1_mux_fck_parents[] = {
-	"core_96m_fck",
-	"mcbsp_clks",
-};
-
-static struct ti_clk_mux mcbsp1_mux_fck_data = {
-	.bit_shift = 2,
-	.num_parents = ARRAY_SIZE(mcbsp1_mux_fck_parents),
-	.reg = 0x274,
-	.module = TI_CLKM_SCRM,
-	.parents = mcbsp1_mux_fck_parents,
-};
-
-static struct ti_clk_gate gpt8_gate_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 9,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_gate gpt8_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 9,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt8_ick = {
-	.name = "gpt8_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt8_ick_data,
-};
-
-static const char *gpt10_mux_fck_parents[] = {
-	"omap_32k_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux gpt10_mux_fck_data = {
-	.bit_shift = 6,
-	.num_parents = ARRAY_SIZE(gpt10_mux_fck_parents),
-	.reg = 0xa40,
-	.module = TI_CLKM_CM,
-	.parents = gpt10_mux_fck_parents,
-};
-
-static struct ti_clk_gate mmchs3_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 30,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mmchs3_ick = {
-	.name = "mmchs3_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mmchs3_ick_data,
-};
-
-static struct ti_clk_gate gpio3_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 14,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpio3_ick = {
-	.name = "gpio3_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio3_ick_data,
-};
-
-static const char *traceclk_src_fck_parents[] = {
-	"sys_ck",
-	"emu_core_alwon_ck",
-	"emu_per_alwon_ck",
-	"emu_mpu_alwon_ck",
-};
-
-static struct ti_clk_mux traceclk_src_fck_data = {
-	.bit_shift = 2,
-	.num_parents = ARRAY_SIZE(traceclk_src_fck_parents),
-	.reg = 0x1140,
-	.module = TI_CLKM_CM,
-	.parents = traceclk_src_fck_parents,
-};
-
-static struct ti_clk traceclk_src_fck = {
-	.name = "traceclk_src_fck",
-	.type = TI_CLK_MUX,
-	.data = &traceclk_src_fck_data,
-};
-
-static struct ti_clk_divider traceclk_fck_data = {
-	.parent = "traceclk_src_fck",
-	.bit_shift = 11,
-	.max_div = 7,
-	.reg = 0x1140,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk traceclk_fck = {
-	.name = "traceclk_fck",
-	.type = TI_CLK_DIVIDER,
-	.data = &traceclk_fck_data,
-};
-
-static struct ti_clk_gate mcbsp5_gate_fck_data = {
-	.parent = "mcbsp_clks",
-	.bit_shift = 10,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_gate sad2d_ick_data = {
-	.parent = "l3_ick",
-	.bit_shift = 3,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk sad2d_ick = {
-	.name = "sad2d_ick",
-	.clkdm_name = "d2d_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &sad2d_ick_data,
-};
-
-static const char *gpt1_mux_fck_parents[] = {
-	"omap_32k_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux gpt1_mux_fck_data = {
-	.num_parents = ARRAY_SIZE(gpt1_mux_fck_parents),
-	.reg = 0xc40,
-	.module = TI_CLKM_CM,
-	.parents = gpt1_mux_fck_parents,
-};
-
-static struct ti_clk_gate hecc_ck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 3,
-	.reg = 0x59c,
-	.module = TI_CLKM_SCRM,
-	.flags = CLKF_AM35XX,
-};
-
-static struct ti_clk hecc_ck = {
-	.name = "hecc_ck",
-	.clkdm_name = "core_l3_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &hecc_ck_data,
-};
-
-static struct ti_clk_gate gpt1_gate_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 0,
-	.reg = 0xc00,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_composite gpt1_fck_data = {
-	.mux = &gpt1_mux_fck_data,
-	.gate = &gpt1_gate_fck_data,
-};
-
-static struct ti_clk gpt1_fck = {
-	.name = "gpt1_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &gpt1_fck_data,
-};
-
-static struct ti_clk_gate dpll4_m2x2_ck_omap36xx_data = {
-	.parent = "dpll4_m2x2_mul_ck",
-	.bit_shift = 0x1b,
-	.reg = 0xd00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_HSDIV | CLKF_SET_BIT_TO_DISABLE,
-};
-
-static struct ti_clk dpll4_m2x2_ck_omap36xx = {
-	.name = "dpll4_m2x2_ck",
-	.type = TI_CLK_GATE,
-	.data = &dpll4_m2x2_ck_omap36xx_data,
-	.patch = &dpll4_m2x2_ck,
-};
-
-static struct ti_clk_divider gfx_l3_fck_data = {
-	.parent = "l3_ick",
-	.max_div = 7,
-	.reg = 0xb40,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk gfx_l3_fck = {
-	.name = "gfx_l3_fck",
-	.type = TI_CLK_DIVIDER,
-	.data = &gfx_l3_fck_data,
-};
-
-static struct ti_clk_gate gfx_cg1_ck_data = {
-	.parent = "gfx_l3_fck",
-	.bit_shift = 1,
-	.reg = 0xb00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk gfx_cg1_ck = {
-	.name = "gfx_cg1_ck",
-	.clkdm_name = "gfx_3430es1_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gfx_cg1_ck_data,
-};
-
-static struct ti_clk_gate mailboxes_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 7,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mailboxes_ick = {
-	.name = "mailboxes_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mailboxes_ick_data,
-};
-
-static struct ti_clk_gate sha11_ick_data = {
-	.parent = "security_l4_ick2",
-	.bit_shift = 1,
-	.reg = 0xa14,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk sha11_ick = {
-	.name = "sha11_ick",
-	.type = TI_CLK_GATE,
-	.data = &sha11_ick_data,
-};
-
-static struct ti_clk_gate hsotgusb_ick_am35xx_data = {
-	.parent = "ipss_ick",
-	.bit_shift = 0,
-	.reg = 0x59c,
-	.module = TI_CLKM_SCRM,
-	.flags = CLKF_AM35XX,
-};
-
-static struct ti_clk hsotgusb_ick_am35xx = {
-	.name = "hsotgusb_ick_am35xx",
-	.clkdm_name = "core_l3_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &hsotgusb_ick_am35xx_data,
-};
-
-static struct ti_clk_gate mmchs3_fck_data = {
-	.parent = "core_96m_fck",
-	.bit_shift = 30,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk mmchs3_fck = {
-	.name = "mmchs3_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mmchs3_fck_data,
-};
-
-static struct ti_clk_divider pclk_fck_data = {
-	.parent = "emu_src_ck",
-	.bit_shift = 8,
-	.max_div = 7,
-	.reg = 0x1140,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk pclk_fck = {
-	.name = "pclk_fck",
-	.type = TI_CLK_DIVIDER,
-	.data = &pclk_fck_data,
-};
-
-static const char *dpll4_ck_omap36xx_parents[] = {
-	"sys_ck",
-	"sys_ck",
-};
-
-static struct ti_clk_dpll dpll4_ck_omap36xx_data = {
-	.num_parents = ARRAY_SIZE(dpll4_ck_omap36xx_parents),
-	.control_reg = 0xd00,
-	.idlest_reg = 0xd20,
-	.mult_div1_reg = 0xd44,
-	.autoidle_reg = 0xd30,
-	.module = TI_CLKM_CM,
-	.parents = dpll4_ck_omap36xx_parents,
-	.modes = 0x82,
-	.div1_mask = 0x7f,
-	.idlest_mask = 0x2,
-	.auto_recal_bit = 0x13,
-	.max_divider = 0x80,
-	.min_divider = 0x1,
-	.recal_en_bit = 0x6,
-	.max_multiplier = 0xfff,
-	.enable_mask = 0x70000,
-	.mult_mask = 0xfff00,
-	.recal_st_bit = 0x6,
-	.autoidle_mask = 0x38,
-	.sddiv_mask = 0xff000000,
-	.dco_mask = 0xe00000,
-	.flags = CLKF_PER | CLKF_J_TYPE,
-};
-
-static struct ti_clk dpll4_ck_omap36xx = {
-	.name = "dpll4_ck",
-	.type = TI_CLK_DPLL,
-	.data = &dpll4_ck_omap36xx_data,
-	.patch = &dpll4_ck,
-};
-
-static struct ti_clk_gate uart3_fck_data = {
-	.parent = "per_48m_fck",
-	.bit_shift = 11,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk uart3_fck = {
-	.name = "uart3_fck",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &uart3_fck_data,
-};
-
-static struct ti_clk_fixed_factor wkup_32k_fck_data = {
-	.parent = "omap_32k_fck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk wkup_32k_fck = {
-	.name = "wkup_32k_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &wkup_32k_fck_data,
-};
-
-static struct ti_clk_gate sys_clkout1_data = {
-	.parent = "osc_sys_ck",
-	.bit_shift = 7,
-	.reg = 0xd70,
-	.module = TI_CLKM_PRM,
-};
-
-static struct ti_clk sys_clkout1 = {
-	.name = "sys_clkout1",
-	.type = TI_CLK_GATE,
-	.data = &sys_clkout1_data,
-};
-
-static struct ti_clk_fixed_factor gpmc_fck_data = {
-	.parent = "core_l3_ick",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk gpmc_fck = {
-	.name = "gpmc_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &gpmc_fck_data,
-};
-
-static struct ti_clk_fixed_factor dpll5_m2_d20_ck_data = {
-	.parent = "dpll5_m2_ck",
-	.div = 20,
-	.mult = 1,
-};
-
-static struct ti_clk dpll5_m2_d20_ck = {
-	.name = "dpll5_m2_d20_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll5_m2_d20_ck_data,
-};
-
-static struct ti_clk_gate dpll4_m5x2_ck_omap36xx_data = {
-	.parent = "dpll4_m5x2_mul_ck",
-	.bit_shift = 0x1e,
-	.reg = 0xd00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_HSDIV | CLKF_SET_RATE_PARENT | CLKF_SET_BIT_TO_DISABLE,
-};
-
-static struct ti_clk dpll4_m5x2_ck_omap36xx = {
-	.name = "dpll4_m5x2_ck",
-	.type = TI_CLK_GATE,
-	.data = &dpll4_m5x2_ck_omap36xx_data,
-	.patch = &dpll4_m5x2_ck,
-};
-
-static struct ti_clk_gate ssi_ssr_gate_fck_3430es2_data = {
-	.parent = "corex2_fck",
-	.bit_shift = 0,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_NO_WAIT,
-};
-
-static struct ti_clk_gate uart1_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 13,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk uart1_ick = {
-	.name = "uart1_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &uart1_ick_data,
-};
-
-static struct ti_clk_gate iva2_ck_data = {
-	.parent = "dpll2_m2_ck",
-	.bit_shift = 0,
-	.reg = 0x0,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk iva2_ck = {
-	.name = "iva2_ck",
-	.clkdm_name = "iva2_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &iva2_ck_data,
-};
-
-static struct ti_clk_gate pka_ick_data = {
-	.parent = "security_l3_ick",
-	.bit_shift = 4,
-	.reg = 0xa14,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk pka_ick = {
-	.name = "pka_ick",
-	.type = TI_CLK_GATE,
-	.data = &pka_ick_data,
-};
-
-static struct ti_clk_gate gpt12_ick_data = {
-	.parent = "wkup_l4_ick",
-	.bit_shift = 1,
-	.reg = 0xc10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt12_ick = {
-	.name = "gpt12_ick",
-	.clkdm_name = "wkup_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt12_ick_data,
-};
-
-static const char *mcbsp5_mux_fck_parents[] = {
-	"core_96m_fck",
-	"mcbsp_clks",
-};
-
-static struct ti_clk_mux mcbsp5_mux_fck_data = {
-	.bit_shift = 4,
-	.num_parents = ARRAY_SIZE(mcbsp5_mux_fck_parents),
-	.reg = 0x2d8,
-	.module = TI_CLKM_SCRM,
-	.parents = mcbsp5_mux_fck_parents,
-};
-
-static struct ti_clk_composite mcbsp5_fck_data = {
-	.mux = &mcbsp5_mux_fck_data,
-	.gate = &mcbsp5_gate_fck_data,
-};
-
-static struct ti_clk mcbsp5_fck = {
-	.name = "mcbsp5_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &mcbsp5_fck_data,
-};
-
-static struct ti_clk_gate usbhost_48m_fck_data = {
-	.parent = "omap_48m_fck",
-	.bit_shift = 0,
-	.reg = 0x1400,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_DSS,
-};
-
-static struct ti_clk usbhost_48m_fck = {
-	.name = "usbhost_48m_fck",
-	.clkdm_name = "usbhost_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &usbhost_48m_fck_data,
-};
-
-static struct ti_clk_gate des1_ick_data = {
-	.parent = "security_l4_ick2",
-	.bit_shift = 0,
-	.reg = 0xa14,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk des1_ick = {
-	.name = "des1_ick",
-	.type = TI_CLK_GATE,
-	.data = &des1_ick_data,
-};
-
-static struct ti_clk_gate sgx_gate_fck_data = {
-	.parent = "core_ck",
-	.bit_shift = 1,
-	.reg = 0xb00,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_fixed_factor core_d4_ck_data = {
-	.parent = "core_ck",
-	.div = 4,
-	.mult = 1,
-};
-
-static struct ti_clk core_d4_ck = {
-	.name = "core_d4_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &core_d4_ck_data,
-};
-
-static struct ti_clk_fixed_factor omap_192m_alwon_fck_data = {
-	.parent = "dpll4_m2x2_ck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk omap_192m_alwon_fck = {
-	.name = "omap_192m_alwon_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &omap_192m_alwon_fck_data,
-};
-
-static struct ti_clk_fixed_factor core_d2_ck_data = {
-	.parent = "core_ck",
-	.div = 2,
-	.mult = 1,
-};
-
-static struct ti_clk core_d2_ck = {
-	.name = "core_d2_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &core_d2_ck_data,
-};
-
-static struct ti_clk_fixed_factor corex2_d3_fck_data = {
-	.parent = "corex2_fck",
-	.div = 3,
-	.mult = 1,
-};
-
-static struct ti_clk corex2_d3_fck = {
-	.name = "corex2_d3_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &corex2_d3_fck_data,
-};
-
-static struct ti_clk_fixed_factor corex2_d5_fck_data = {
-	.parent = "corex2_fck",
-	.div = 5,
-	.mult = 1,
-};
-
-static struct ti_clk corex2_d5_fck = {
-	.name = "corex2_d5_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &corex2_d5_fck_data,
-};
-
-static const char *sgx_mux_fck_parents[] = {
-	"core_d3_ck",
-	"core_d4_ck",
-	"core_d6_ck",
-	"cm_96m_fck",
-	"omap_192m_alwon_fck",
-	"core_d2_ck",
-	"corex2_d3_fck",
-	"corex2_d5_fck",
-};
-
-static struct ti_clk_mux sgx_mux_fck_data = {
-	.num_parents = ARRAY_SIZE(sgx_mux_fck_parents),
-	.reg = 0xb40,
-	.module = TI_CLKM_CM,
-	.parents = sgx_mux_fck_parents,
-};
-
-static struct ti_clk_composite sgx_fck_data = {
-	.mux = &sgx_mux_fck_data,
-	.gate = &sgx_gate_fck_data,
-};
-
-static struct ti_clk sgx_fck = {
-	.name = "sgx_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &sgx_fck_data,
-};
-
-static struct ti_clk_gate mcspi1_fck_data = {
-	.parent = "core_48m_fck",
-	.bit_shift = 18,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk mcspi1_fck = {
-	.name = "mcspi1_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcspi1_fck_data,
-};
-
-static struct ti_clk_gate mmchs2_fck_data = {
-	.parent = "core_96m_fck",
-	.bit_shift = 25,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk mmchs2_fck = {
-	.name = "mmchs2_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mmchs2_fck_data,
-};
-
-static struct ti_clk_gate mcspi2_fck_data = {
-	.parent = "core_48m_fck",
-	.bit_shift = 19,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk mcspi2_fck = {
-	.name = "mcspi2_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcspi2_fck_data,
-};
-
-static struct ti_clk_gate vpfe_fck_data = {
-	.parent = "pclk_ck",
-	.bit_shift = 10,
-	.reg = 0x59c,
-	.module = TI_CLKM_SCRM,
-};
-
-static struct ti_clk vpfe_fck = {
-	.name = "vpfe_fck",
-	.type = TI_CLK_GATE,
-	.data = &vpfe_fck_data,
-};
-
-static struct ti_clk_gate gpt4_gate_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 5,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_gate mcbsp1_gate_fck_data = {
-	.parent = "mcbsp_clks",
-	.bit_shift = 9,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_gate gpt5_gate_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 6,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static const char *gpt5_mux_fck_parents[] = {
-	"omap_32k_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux gpt5_mux_fck_data = {
-	.bit_shift = 3,
-	.num_parents = ARRAY_SIZE(gpt5_mux_fck_parents),
-	.reg = 0x1040,
-	.module = TI_CLKM_CM,
-	.parents = gpt5_mux_fck_parents,
-};
-
-static struct ti_clk_composite gpt5_fck_data = {
-	.mux = &gpt5_mux_fck_data,
-	.gate = &gpt5_gate_fck_data,
-};
-
-static struct ti_clk gpt5_fck = {
-	.name = "gpt5_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &gpt5_fck_data,
-};
-
-static struct ti_clk_gate ts_fck_data = {
-	.parent = "omap_32k_fck",
-	.bit_shift = 1,
-	.reg = 0xa08,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk ts_fck = {
-	.name = "ts_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &ts_fck_data,
-};
-
-static struct ti_clk_fixed_factor wdt1_fck_data = {
-	.parent = "secure_32k_fck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk wdt1_fck = {
-	.name = "wdt1_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &wdt1_fck_data,
-};
-
-static struct ti_clk_gate dpll4_m6x2_ck_omap36xx_data = {
-	.parent = "dpll4_m6x2_mul_ck",
-	.bit_shift = 0x1f,
-	.reg = 0xd00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_HSDIV | CLKF_SET_BIT_TO_DISABLE,
-};
-
-static struct ti_clk dpll4_m6x2_ck_omap36xx = {
-	.name = "dpll4_m6x2_ck",
-	.type = TI_CLK_GATE,
-	.data = &dpll4_m6x2_ck_omap36xx_data,
-	.patch = &dpll4_m6x2_ck,
-};
-
-static const char *gpt4_mux_fck_parents[] = {
-	"omap_32k_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux gpt4_mux_fck_data = {
-	.bit_shift = 2,
-	.num_parents = ARRAY_SIZE(gpt4_mux_fck_parents),
-	.reg = 0x1040,
-	.module = TI_CLKM_CM,
-	.parents = gpt4_mux_fck_parents,
-};
-
-static struct ti_clk_gate usbhost_ick_data = {
-	.parent = "l4_ick",
-	.bit_shift = 0,
-	.reg = 0x1410,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_DSS | CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk usbhost_ick = {
-	.name = "usbhost_ick",
-	.clkdm_name = "usbhost_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &usbhost_ick_data,
-};
-
-static struct ti_clk_gate mcbsp2_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 0,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mcbsp2_ick = {
-	.name = "mcbsp2_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcbsp2_ick_data,
-};
-
-static struct ti_clk_gate omapctrl_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 6,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk omapctrl_ick = {
-	.name = "omapctrl_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &omapctrl_ick_data,
-};
-
-static struct ti_clk_fixed_factor omap_96m_d4_fck_data = {
-	.parent = "omap_96m_fck",
-	.div = 4,
-	.mult = 1,
-};
-
-static struct ti_clk omap_96m_d4_fck = {
-	.name = "omap_96m_d4_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &omap_96m_d4_fck_data,
-};
-
-static struct ti_clk_gate gpt6_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 7,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt6_ick = {
-	.name = "gpt6_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt6_ick_data,
-};
-
-static struct ti_clk_gate dpll3_m3x2_ck_omap36xx_data = {
-	.parent = "dpll3_m3x2_mul_ck",
-	.bit_shift = 0xc,
-	.reg = 0xd00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_HSDIV | CLKF_SET_BIT_TO_DISABLE,
-};
-
-static struct ti_clk dpll3_m3x2_ck_omap36xx = {
-	.name = "dpll3_m3x2_ck",
-	.type = TI_CLK_GATE,
-	.data = &dpll3_m3x2_ck_omap36xx_data,
-	.patch = &dpll3_m3x2_ck,
-};
-
-static struct ti_clk_gate i2c3_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 17,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk i2c3_ick = {
-	.name = "i2c3_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &i2c3_ick_data,
-};
-
-static struct ti_clk_gate gpio6_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 17,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpio6_ick = {
-	.name = "gpio6_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio6_ick_data,
-};
-
-static struct ti_clk_gate mspro_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 23,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mspro_ick = {
-	.name = "mspro_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mspro_ick_data,
-};
-
-static struct ti_clk_composite mcbsp1_fck_data = {
-	.mux = &mcbsp1_mux_fck_data,
-	.gate = &mcbsp1_gate_fck_data,
-};
-
-static struct ti_clk mcbsp1_fck = {
-	.name = "mcbsp1_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &mcbsp1_fck_data,
-};
-
-static struct ti_clk_gate gpt3_gate_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 4,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_fixed rmii_ck_data = {
-	.frequency = 50000000,
-};
-
-static struct ti_clk rmii_ck = {
-	.name = "rmii_ck",
-	.type = TI_CLK_FIXED,
-	.data = &rmii_ck_data,
-};
-
-static struct ti_clk_gate gpt6_gate_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 7,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_composite gpt6_fck_data = {
-	.mux = &gpt6_mux_fck_data,
-	.gate = &gpt6_gate_fck_data,
-};
-
-static struct ti_clk gpt6_fck = {
-	.name = "gpt6_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &gpt6_fck_data,
-};
-
-static struct ti_clk_fixed_factor dpll5_m2_d4_ck_data = {
-	.parent = "dpll5_m2_ck",
-	.div = 4,
-	.mult = 1,
-};
-
-static struct ti_clk dpll5_m2_d4_ck = {
-	.name = "dpll5_m2_d4_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll5_m2_d4_ck_data,
-};
-
-static struct ti_clk_fixed_factor sys_d2_ck_data = {
-	.parent = "sys_ck",
-	.div = 2,
-	.mult = 1,
-};
-
-static struct ti_clk sys_d2_ck = {
-	.name = "sys_d2_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &sys_d2_ck_data,
-};
-
-static struct ti_clk_fixed_factor omap_96m_d2_fck_data = {
-	.parent = "omap_96m_fck",
-	.div = 2,
-	.mult = 1,
-};
-
-static struct ti_clk omap_96m_d2_fck = {
-	.name = "omap_96m_d2_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &omap_96m_d2_fck_data,
-};
-
-static struct ti_clk_fixed_factor dpll5_m2_d8_ck_data = {
-	.parent = "dpll5_m2_ck",
-	.div = 8,
-	.mult = 1,
-};
-
-static struct ti_clk dpll5_m2_d8_ck = {
-	.name = "dpll5_m2_d8_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll5_m2_d8_ck_data,
-};
-
-static struct ti_clk_fixed_factor dpll5_m2_d16_ck_data = {
-	.parent = "dpll5_m2_ck",
-	.div = 16,
-	.mult = 1,
-};
-
-static struct ti_clk dpll5_m2_d16_ck = {
-	.name = "dpll5_m2_d16_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll5_m2_d16_ck_data,
-};
-
-static const char *usim_mux_fck_parents[] = {
-	"sys_ck",
-	"sys_d2_ck",
-	"omap_96m_d2_fck",
-	"omap_96m_d4_fck",
-	"omap_96m_d8_fck",
-	"omap_96m_d10_fck",
-	"dpll5_m2_d4_ck",
-	"dpll5_m2_d8_ck",
-	"dpll5_m2_d16_ck",
-	"dpll5_m2_d20_ck",
-};
-
-static struct ti_clk_mux usim_mux_fck_data = {
-	.bit_shift = 3,
-	.num_parents = ARRAY_SIZE(usim_mux_fck_parents),
-	.reg = 0xc40,
-	.module = TI_CLKM_CM,
-	.parents = usim_mux_fck_parents,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk_composite usim_fck_data = {
-	.mux = &usim_mux_fck_data,
-	.gate = &usim_gate_fck_data,
-};
-
-static struct ti_clk usim_fck = {
-	.name = "usim_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &usim_fck_data,
-};
-
-static int ssi_ssr_div_fck_3430es2_divs[] = {
-	0,
-	1,
-	2,
-	3,
-	4,
-	0,
-	6,
-	0,
-	8,
-};
-
-static struct ti_clk_divider ssi_ssr_div_fck_3430es2_data = {
-	.num_dividers = ARRAY_SIZE(ssi_ssr_div_fck_3430es2_divs),
-	.parent = "corex2_fck",
-	.bit_shift = 8,
-	.dividers = ssi_ssr_div_fck_3430es2_divs,
-	.reg = 0xa40,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_composite ssi_ssr_fck_3430es2_data = {
-	.gate = &ssi_ssr_gate_fck_3430es2_data,
-	.divider = &ssi_ssr_div_fck_3430es2_data,
-};
-
-static struct ti_clk ssi_ssr_fck_3430es2 = {
-	.name = "ssi_ssr_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &ssi_ssr_fck_3430es2_data,
-};
-
-static struct ti_clk_gate dss1_alwon_fck_3430es1_data = {
-	.parent = "dpll4_m4x2_ck",
-	.bit_shift = 0,
-	.reg = 0xe00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_SET_RATE_PARENT,
-};
-
-static struct ti_clk dss1_alwon_fck_3430es1 = {
-	.name = "dss1_alwon_fck",
-	.clkdm_name = "dss_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &dss1_alwon_fck_3430es1_data,
-};
-
-static struct ti_clk_gate gpt3_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 4,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt3_ick = {
-	.name = "gpt3_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt3_ick_data,
-};
-
-static struct ti_clk_fixed_factor omap_12m_fck_data = {
-	.parent = "omap_48m_fck",
-	.div = 4,
-	.mult = 1,
-};
-
-static struct ti_clk omap_12m_fck = {
-	.name = "omap_12m_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &omap_12m_fck_data,
-};
-
-static struct ti_clk_fixed_factor core_12m_fck_data = {
-	.parent = "omap_12m_fck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk core_12m_fck = {
-	.name = "core_12m_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &core_12m_fck_data,
-};
-
-static struct ti_clk_gate hdq_fck_data = {
-	.parent = "core_12m_fck",
-	.bit_shift = 22,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk hdq_fck = {
-	.name = "hdq_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &hdq_fck_data,
-};
-
-static struct ti_clk_gate usbtll_fck_data = {
-	.parent = "dpll5_m2_ck",
-	.bit_shift = 2,
-	.reg = 0xa08,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk usbtll_fck = {
-	.name = "usbtll_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &usbtll_fck_data,
-};
-
-static struct ti_clk_gate hsotgusb_fck_am35xx_data = {
-	.parent = "sys_ck",
-	.bit_shift = 8,
-	.reg = 0x59c,
-	.module = TI_CLKM_SCRM,
-};
-
-static struct ti_clk hsotgusb_fck_am35xx = {
-	.name = "hsotgusb_fck_am35xx",
-	.clkdm_name = "core_l3_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &hsotgusb_fck_am35xx_data,
-};
-
-static struct ti_clk_gate hsotgusb_ick_3430es2_data = {
-	.parent = "core_l3_ick",
-	.bit_shift = 4,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_HSOTGUSB | CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk hsotgusb_ick_3430es2 = {
-	.name = "hsotgusb_ick_3430es2",
-	.clkdm_name = "core_l3_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &hsotgusb_ick_3430es2_data,
-};
-
-static struct ti_clk_gate gfx_l3_ck_data = {
-	.parent = "l3_ick",
-	.bit_shift = 0,
-	.reg = 0xb10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk gfx_l3_ck = {
-	.name = "gfx_l3_ck",
-	.clkdm_name = "gfx_3430es1_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gfx_l3_ck_data,
-};
-
-static struct ti_clk_fixed_factor gfx_l3_ick_data = {
-	.parent = "gfx_l3_ck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk gfx_l3_ick = {
-	.name = "gfx_l3_ick",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &gfx_l3_ick_data,
-};
-
-static struct ti_clk_gate mcbsp1_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 9,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mcbsp1_ick = {
-	.name = "mcbsp1_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcbsp1_ick_data,
-};
-
-static struct ti_clk_fixed_factor gpt12_fck_data = {
-	.parent = "secure_32k_fck",
-	.div = 1,
-	.mult = 1,
-};
-
-static struct ti_clk gpt12_fck = {
-	.name = "gpt12_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &gpt12_fck_data,
-};
-
-static struct ti_clk_gate gfx_cg2_ck_data = {
-	.parent = "gfx_l3_fck",
-	.bit_shift = 2,
-	.reg = 0xb00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk gfx_cg2_ck = {
-	.name = "gfx_cg2_ck",
-	.clkdm_name = "gfx_3430es1_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gfx_cg2_ck_data,
-};
-
-static struct ti_clk_gate i2c2_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 16,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk i2c2_ick = {
-	.name = "i2c2_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &i2c2_ick_data,
-};
-
-static struct ti_clk_gate gpio4_dbck_data = {
-	.parent = "per_32k_alwon_fck",
-	.bit_shift = 15,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk gpio4_dbck = {
-	.name = "gpio4_dbck",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio4_dbck_data,
-};
-
-static struct ti_clk_gate i2c3_fck_data = {
-	.parent = "core_96m_fck",
-	.bit_shift = 17,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk i2c3_fck = {
-	.name = "i2c3_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &i2c3_fck_data,
-};
-
-static struct ti_clk_composite gpt3_fck_data = {
-	.mux = &gpt3_mux_fck_data,
-	.gate = &gpt3_gate_fck_data,
-};
-
-static struct ti_clk gpt3_fck = {
-	.name = "gpt3_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &gpt3_fck_data,
-};
-
-static struct ti_clk_gate i2c1_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 15,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk i2c1_ick = {
-	.name = "i2c1_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &i2c1_ick_data,
-};
-
-static struct ti_clk_gate omap_32ksync_ick_data = {
-	.parent = "wkup_l4_ick",
-	.bit_shift = 2,
-	.reg = 0xc10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk omap_32ksync_ick = {
-	.name = "omap_32ksync_ick",
-	.clkdm_name = "wkup_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &omap_32ksync_ick_data,
-};
-
-static struct ti_clk_gate aes2_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 28,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk aes2_ick = {
-	.name = "aes2_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &aes2_ick_data,
-};
-
-static const char *gpt8_mux_fck_parents[] = {
-	"omap_32k_fck",
-	"sys_ck",
-};
-
-static struct ti_clk_mux gpt8_mux_fck_data = {
-	.bit_shift = 6,
-	.num_parents = ARRAY_SIZE(gpt8_mux_fck_parents),
-	.reg = 0x1040,
-	.module = TI_CLKM_CM,
-	.parents = gpt8_mux_fck_parents,
-};
-
-static struct ti_clk_composite gpt8_fck_data = {
-	.mux = &gpt8_mux_fck_data,
-	.gate = &gpt8_gate_fck_data,
-};
-
-static struct ti_clk gpt8_fck = {
-	.name = "gpt8_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &gpt8_fck_data,
-};
-
-static struct ti_clk_gate mcbsp4_gate_fck_data = {
-	.parent = "mcbsp_clks",
-	.bit_shift = 2,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk_composite mcbsp4_fck_data = {
-	.mux = &mcbsp4_mux_fck_data,
-	.gate = &mcbsp4_gate_fck_data,
-};
-
-static struct ti_clk mcbsp4_fck = {
-	.name = "mcbsp4_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &mcbsp4_fck_data,
-};
-
-static struct ti_clk_gate gpio2_dbck_data = {
-	.parent = "per_32k_alwon_fck",
-	.bit_shift = 13,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk gpio2_dbck = {
-	.name = "gpio2_dbck",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio2_dbck_data,
-};
-
-static struct ti_clk_gate usbtll_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 2,
-	.reg = 0xa18,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk usbtll_ick = {
-	.name = "usbtll_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &usbtll_ick_data,
-};
-
-static struct ti_clk_gate mcspi4_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 21,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mcspi4_ick = {
-	.name = "mcspi4_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcspi4_ick_data,
-};
-
-static struct ti_clk_gate dss_96m_fck_data = {
-	.parent = "omap_96m_fck",
-	.bit_shift = 2,
-	.reg = 0xe00,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk dss_96m_fck = {
-	.name = "dss_96m_fck",
-	.clkdm_name = "dss_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &dss_96m_fck_data,
-};
-
-static struct ti_clk_divider rm_ick_data = {
-	.parent = "l4_ick",
-	.bit_shift = 1,
-	.max_div = 3,
-	.reg = 0xc40,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk rm_ick = {
-	.name = "rm_ick",
-	.type = TI_CLK_DIVIDER,
-	.data = &rm_ick_data,
-};
-
-static struct ti_clk_gate hdq_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 22,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk hdq_ick = {
-	.name = "hdq_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &hdq_ick_data,
-};
-
-static struct ti_clk_fixed_factor dpll3_x2_ck_data = {
-	.parent = "dpll3_ck",
-	.div = 1,
-	.mult = 2,
-};
-
-static struct ti_clk dpll3_x2_ck = {
-	.name = "dpll3_x2_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll3_x2_ck_data,
-};
-
-static struct ti_clk_gate mad2d_ick_data = {
-	.parent = "l3_ick",
-	.bit_shift = 3,
-	.reg = 0xa18,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mad2d_ick = {
-	.name = "mad2d_ick",
-	.clkdm_name = "d2d_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mad2d_ick_data,
-};
-
-static struct ti_clk_gate fshostusb_fck_data = {
-	.parent = "core_48m_fck",
-	.bit_shift = 5,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk fshostusb_fck = {
-	.name = "fshostusb_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &fshostusb_fck_data,
-};
-
-static struct ti_clk_gate sr1_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 6,
-	.reg = 0xc00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk sr1_fck = {
-	.name = "sr1_fck",
-	.clkdm_name = "wkup_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &sr1_fck_data,
-};
-
-static struct ti_clk_gate des2_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 26,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk des2_ick = {
-	.name = "des2_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &des2_ick_data,
-};
-
-static struct ti_clk_gate sdrc_ick_data = {
-	.parent = "core_l3_ick",
-	.bit_shift = 1,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk sdrc_ick = {
-	.name = "sdrc_ick",
-	.clkdm_name = "core_l3_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &sdrc_ick_data,
-};
-
-static struct ti_clk_composite gpt4_fck_data = {
-	.mux = &gpt4_mux_fck_data,
-	.gate = &gpt4_gate_fck_data,
-};
-
-static struct ti_clk gpt4_fck = {
-	.name = "gpt4_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &gpt4_fck_data,
-};
-
-static struct ti_clk_gate dpll4_m3x2_ck_omap36xx_data = {
-	.parent = "dpll4_m3x2_mul_ck",
-	.bit_shift = 0x1c,
-	.reg = 0xd00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_HSDIV | CLKF_SET_BIT_TO_DISABLE,
-};
-
-static struct ti_clk dpll4_m3x2_ck_omap36xx = {
-	.name = "dpll4_m3x2_ck",
-	.type = TI_CLK_GATE,
-	.data = &dpll4_m3x2_ck_omap36xx_data,
-	.patch = &dpll4_m3x2_ck,
-};
-
-static struct ti_clk_gate cpefuse_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 0,
-	.reg = 0xa08,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk cpefuse_fck = {
-	.name = "cpefuse_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &cpefuse_fck_data,
-};
-
-static struct ti_clk_gate mcspi3_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 20,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mcspi3_ick = {
-	.name = "mcspi3_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcspi3_ick_data,
-};
-
-static struct ti_clk_fixed_factor ssi_sst_fck_3430es2_data = {
-	.parent = "ssi_ssr_fck",
-	.div = 2,
-	.mult = 1,
-};
-
-static struct ti_clk ssi_sst_fck_3430es2 = {
-	.name = "ssi_sst_fck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &ssi_sst_fck_3430es2_data,
-};
-
-static struct ti_clk_gate gpio1_dbck_data = {
-	.parent = "wkup_32k_fck",
-	.bit_shift = 3,
-	.reg = 0xc00,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk gpio1_dbck = {
-	.name = "gpio1_dbck",
-	.clkdm_name = "wkup_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio1_dbck_data,
-};
-
-static struct ti_clk_gate gpt4_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 5,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt4_ick = {
-	.name = "gpt4_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt4_ick_data,
-};
-
-static struct ti_clk_gate gpt2_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 3,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt2_ick = {
-	.name = "gpt2_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt2_ick_data,
-};
-
-static struct ti_clk_gate mmchs1_fck_data = {
-	.parent = "core_96m_fck",
-	.bit_shift = 24,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk mmchs1_fck = {
-	.name = "mmchs1_fck",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mmchs1_fck_data,
-};
-
-static struct ti_clk_fixed dummy_apb_pclk_data = {
-	.frequency = 0x0,
-};
-
-static struct ti_clk dummy_apb_pclk = {
-	.name = "dummy_apb_pclk",
-	.type = TI_CLK_FIXED,
-	.data = &dummy_apb_pclk_data,
-};
-
-static struct ti_clk_gate gpio6_dbck_data = {
-	.parent = "per_32k_alwon_fck",
-	.bit_shift = 17,
-	.reg = 0x1000,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk gpio6_dbck = {
-	.name = "gpio6_dbck",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio6_dbck_data,
-};
-
-static struct ti_clk_gate uart2_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 14,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk uart2_ick = {
-	.name = "uart2_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &uart2_ick_data,
-};
-
-static struct ti_clk_fixed_factor dpll4_x2_ck_data = {
-	.parent = "dpll4_ck",
-	.div = 1,
-	.mult = 2,
-};
-
-static struct ti_clk dpll4_x2_ck = {
-	.name = "dpll4_x2_ck",
-	.type = TI_CLK_FIXED_FACTOR,
-	.data = &dpll4_x2_ck_data,
-};
-
-static struct ti_clk_gate gpt7_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 8,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpt7_ick = {
-	.name = "gpt7_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpt7_ick_data,
-};
-
-static struct ti_clk_gate dss_tv_fck_data = {
-	.parent = "omap_54m_fck",
-	.bit_shift = 2,
-	.reg = 0xe00,
-	.module = TI_CLKM_CM,
-};
-
-static struct ti_clk dss_tv_fck = {
-	.name = "dss_tv_fck",
-	.clkdm_name = "dss_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &dss_tv_fck_data,
-};
-
-static struct ti_clk_gate mcbsp5_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 10,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mcbsp5_ick = {
-	.name = "mcbsp5_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcbsp5_ick_data,
-};
-
-static struct ti_clk_gate mcspi1_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 18,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk mcspi1_ick = {
-	.name = "mcspi1_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &mcspi1_ick_data,
-};
-
-static struct ti_clk_gate d2d_26m_fck_data = {
-	.parent = "sys_ck",
-	.bit_shift = 3,
-	.reg = 0xa00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk d2d_26m_fck = {
-	.name = "d2d_26m_fck",
-	.clkdm_name = "d2d_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &d2d_26m_fck_data,
-};
-
-static struct ti_clk_gate wdt3_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 12,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk wdt3_ick = {
-	.name = "wdt3_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &wdt3_ick_data,
-};
-
-static struct ti_clk_divider pclkx2_fck_data = {
-	.parent = "emu_src_ck",
-	.bit_shift = 6,
-	.max_div = 3,
-	.reg = 0x1140,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_STARTS_AT_ONE,
-};
-
-static struct ti_clk pclkx2_fck = {
-	.name = "pclkx2_fck",
-	.type = TI_CLK_DIVIDER,
-	.data = &pclkx2_fck_data,
-};
-
-static struct ti_clk_gate sha12_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 27,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk sha12_ick = {
-	.name = "sha12_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &sha12_ick_data,
-};
-
-static struct ti_clk_gate emac_fck_data = {
-	.parent = "rmii_ck",
-	.bit_shift = 9,
-	.reg = 0x59c,
-	.module = TI_CLKM_SCRM,
-};
-
-static struct ti_clk emac_fck = {
-	.name = "emac_fck",
-	.type = TI_CLK_GATE,
-	.data = &emac_fck_data,
-};
-
-static struct ti_clk_composite gpt10_fck_data = {
-	.mux = &gpt10_mux_fck_data,
-	.gate = &gpt10_gate_fck_data,
-};
-
-static struct ti_clk gpt10_fck = {
-	.name = "gpt10_fck",
-	.type = TI_CLK_COMPOSITE,
-	.data = &gpt10_fck_data,
-};
-
-static struct ti_clk_gate wdt2_fck_data = {
-	.parent = "wkup_32k_fck",
-	.bit_shift = 5,
-	.reg = 0xc00,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk wdt2_fck = {
-	.name = "wdt2_fck",
-	.clkdm_name = "wkup_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &wdt2_fck_data,
-};
-
-static struct ti_clk_gate cam_ick_data = {
-	.parent = "l4_ick",
-	.bit_shift = 0,
-	.reg = 0xf10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_NO_WAIT | CLKF_INTERFACE,
-};
-
-static struct ti_clk cam_ick = {
-	.name = "cam_ick",
-	.clkdm_name = "cam_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &cam_ick_data,
-};
-
-static struct ti_clk_gate ssi_ick_3430es2_data = {
-	.parent = "ssi_l4_ick",
-	.bit_shift = 0,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_SSI | CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk ssi_ick_3430es2 = {
-	.name = "ssi_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &ssi_ick_3430es2_data,
-};
-
-static struct ti_clk_gate gpio4_ick_data = {
-	.parent = "per_l4_ick",
-	.bit_shift = 15,
-	.reg = 0x1010,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk gpio4_ick = {
-	.name = "gpio4_ick",
-	.clkdm_name = "per_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &gpio4_ick_data,
-};
-
-static struct ti_clk_gate wdt1_ick_data = {
-	.parent = "wkup_l4_ick",
-	.bit_shift = 4,
-	.reg = 0xc10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk wdt1_ick = {
-	.name = "wdt1_ick",
-	.clkdm_name = "wkup_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &wdt1_ick_data,
-};
-
-static struct ti_clk_gate rng_ick_data = {
-	.parent = "security_l4_ick2",
-	.bit_shift = 2,
-	.reg = 0xa14,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk rng_ick = {
-	.name = "rng_ick",
-	.type = TI_CLK_GATE,
-	.data = &rng_ick_data,
-};
-
-static struct ti_clk_gate icr_ick_data = {
-	.parent = "core_l4_ick",
-	.bit_shift = 29,
-	.reg = 0xa10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_OMAP3 | CLKF_INTERFACE,
-};
-
-static struct ti_clk icr_ick = {
-	.name = "icr_ick",
-	.clkdm_name = "core_l4_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &icr_ick_data,
-};
-
-static struct ti_clk_gate sgx_ick_data = {
-	.parent = "l3_ick",
-	.bit_shift = 0,
-	.reg = 0xb10,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_WAIT,
-};
-
-static struct ti_clk sgx_ick = {
-	.name = "sgx_ick",
-	.clkdm_name = "sgx_clkdm",
-	.type = TI_CLK_GATE,
-	.data = &sgx_ick_data,
-};
-
-static struct ti_clk_divider sys_clkout2_data = {
-	.parent = "clkout2_src_ck",
-	.bit_shift = 3,
-	.max_div = 64,
-	.reg = 0xd70,
-	.module = TI_CLKM_CM,
-	.flags = CLKF_INDEX_POWER_OF_TWO,
-};
-
-static struct ti_clk sys_clkout2 = {
-	.name = "sys_clkout2",
-	.type = TI_CLK_DIVIDER,
-	.data = &sys_clkout2_data,
-};
-
-static struct ti_clk_alias omap34xx_omap36xx_clks[] = {
-	CLK(NULL, "security_l4_ick2", &security_l4_ick2),
-	CLK(NULL, "aes1_ick", &aes1_ick),
-	CLK("omap_rng", "ick", &rng_ick),
-	CLK("omap3-rom-rng", "ick", &rng_ick),
-	CLK(NULL, "sha11_ick", &sha11_ick),
-	CLK(NULL, "des1_ick", &des1_ick),
-	CLK(NULL, "cam_mclk", &cam_mclk),
-	CLK(NULL, "cam_ick", &cam_ick),
-	CLK(NULL, "csi2_96m_fck", &csi2_96m_fck),
-	CLK(NULL, "security_l3_ick", &security_l3_ick),
-	CLK(NULL, "pka_ick", &pka_ick),
-	CLK(NULL, "icr_ick", &icr_ick),
-	CLK(NULL, "des2_ick", &des2_ick),
-	CLK(NULL, "mspro_ick", &mspro_ick),
-	CLK(NULL, "mailboxes_ick", &mailboxes_ick),
-	CLK(NULL, "ssi_l4_ick", &ssi_l4_ick),
-	CLK(NULL, "sr1_fck", &sr1_fck),
-	CLK(NULL, "sr2_fck", &sr2_fck),
-	CLK(NULL, "sr_l4_ick", &sr_l4_ick),
-	CLK(NULL, "dpll2_fck", &dpll2_fck),
-	CLK(NULL, "dpll2_ck", &dpll2_ck),
-	CLK(NULL, "dpll2_m2_ck", &dpll2_m2_ck),
-	CLK(NULL, "iva2_ck", &iva2_ck),
-	CLK(NULL, "modem_fck", &modem_fck),
-	CLK(NULL, "sad2d_ick", &sad2d_ick),
-	CLK(NULL, "mad2d_ick", &mad2d_ick),
-	CLK(NULL, "mspro_fck", &mspro_fck),
-	{ NULL },
-};
-
-static struct ti_clk_alias omap36xx_omap3430es2plus_clks[] = {
-	CLK(NULL, "ssi_ssr_fck", &ssi_ssr_fck_3430es2),
-	CLK(NULL, "ssi_sst_fck", &ssi_sst_fck_3430es2),
-	CLK("musb-omap2430", "ick", &hsotgusb_ick_3430es2),
-	CLK(NULL, "hsotgusb_ick", &hsotgusb_ick_3430es2),
-	CLK(NULL, "ssi_ick", &ssi_ick_3430es2),
-	CLK(NULL, "sys_d2_ck", &sys_d2_ck),
-	CLK(NULL, "omap_96m_d2_fck", &omap_96m_d2_fck),
-	CLK(NULL, "omap_96m_d4_fck", &omap_96m_d4_fck),
-	CLK(NULL, "omap_96m_d8_fck", &omap_96m_d8_fck),
-	CLK(NULL, "omap_96m_d10_fck", &omap_96m_d10_fck),
-	CLK(NULL, "dpll5_m2_d4_ck", &dpll5_m2_d4_ck),
-	CLK(NULL, "dpll5_m2_d8_ck", &dpll5_m2_d8_ck),
-	CLK(NULL, "dpll5_m2_d16_ck", &dpll5_m2_d16_ck),
-	CLK(NULL, "dpll5_m2_d20_ck", &dpll5_m2_d20_ck),
-	CLK(NULL, "usim_fck", &usim_fck),
-	CLK(NULL, "usim_ick", &usim_ick),
-	{ NULL },
-};
-
-static struct ti_clk_alias omap3xxx_clks[] = {
-	CLK(NULL, "apb_pclk", &dummy_apb_pclk),
-	CLK(NULL, "omap_32k_fck", &omap_32k_fck),
-	CLK(NULL, "virt_12m_ck", &virt_12m_ck),
-	CLK(NULL, "virt_13m_ck", &virt_13m_ck),
-	CLK(NULL, "virt_19200000_ck", &virt_19200000_ck),
-	CLK(NULL, "virt_26000000_ck", &virt_26000000_ck),
-	CLK(NULL, "virt_38_4m_ck", &virt_38_4m_ck),
-	CLK(NULL, "virt_16_8m_ck", &virt_16_8m_ck),
-	CLK(NULL, "osc_sys_ck", &osc_sys_ck),
-	CLK("twl", "fck", &osc_sys_ck),
-	CLK(NULL, "sys_ck", &sys_ck),
-	CLK(NULL, "timer_sys_ck", &sys_ck),
-	CLK(NULL, "dpll4_ck", &dpll4_ck),
-	CLK(NULL, "dpll4_m2_ck", &dpll4_m2_ck),
-	CLK(NULL, "dpll4_m2x2_mul_ck", &dpll4_m2x2_mul_ck),
-	CLK(NULL, "dpll4_m2x2_ck", &dpll4_m2x2_ck),
-	CLK(NULL, "omap_96m_alwon_fck", &omap_96m_alwon_fck),
-	CLK(NULL, "dpll3_ck", &dpll3_ck),
-	CLK(NULL, "dpll3_m3_ck", &dpll3_m3_ck),
-	CLK(NULL, "dpll3_m3x2_mul_ck", &dpll3_m3x2_mul_ck),
-	CLK(NULL, "dpll3_m3x2_ck", &dpll3_m3x2_ck),
-	CLK("etb", "emu_core_alwon_ck", &emu_core_alwon_ck),
-	CLK(NULL, "sys_altclk", &sys_altclk),
-	CLK(NULL, "sys_clkout1", &sys_clkout1),
-	CLK(NULL, "dpll3_m2_ck", &dpll3_m2_ck),
-	CLK(NULL, "core_ck", &core_ck),
-	CLK(NULL, "dpll1_fck", &dpll1_fck),
-	CLK(NULL, "dpll1_ck", &dpll1_ck),
-	CLK(NULL, "cpufreq_ck", &dpll1_ck),
-	CLK(NULL, "dpll1_x2_ck", &dpll1_x2_ck),
-	CLK(NULL, "dpll1_x2m2_ck", &dpll1_x2m2_ck),
-	CLK(NULL, "dpll3_x2_ck", &dpll3_x2_ck),
-	CLK(NULL, "dpll3_m2x2_ck", &dpll3_m2x2_ck),
-	CLK(NULL, "dpll4_x2_ck", &dpll4_x2_ck),
-	CLK(NULL, "cm_96m_fck", &cm_96m_fck),
-	CLK(NULL, "omap_96m_fck", &omap_96m_fck),
-	CLK(NULL, "dpll4_m3_ck", &dpll4_m3_ck),
-	CLK(NULL, "dpll4_m3x2_mul_ck", &dpll4_m3x2_mul_ck),
-	CLK(NULL, "dpll4_m3x2_ck", &dpll4_m3x2_ck),
-	CLK(NULL, "omap_54m_fck", &omap_54m_fck),
-	CLK(NULL, "cm_96m_d2_fck", &cm_96m_d2_fck),
-	CLK(NULL, "omap_48m_fck", &omap_48m_fck),
-	CLK(NULL, "omap_12m_fck", &omap_12m_fck),
-	CLK(NULL, "dpll4_m4_ck", &dpll4_m4_ck),
-	CLK(NULL, "dpll4_m4x2_mul_ck", &dpll4_m4x2_mul_ck),
-	CLK(NULL, "dpll4_m4x2_ck", &dpll4_m4x2_ck),
-	CLK(NULL, "dpll4_m5_ck", &dpll4_m5_ck),
-	CLK(NULL, "dpll4_m5x2_mul_ck", &dpll4_m5x2_mul_ck),
-	CLK(NULL, "dpll4_m5x2_ck", &dpll4_m5x2_ck),
-	CLK(NULL, "dpll4_m6_ck", &dpll4_m6_ck),
-	CLK(NULL, "dpll4_m6x2_mul_ck", &dpll4_m6x2_mul_ck),
-	CLK(NULL, "dpll4_m6x2_ck", &dpll4_m6x2_ck),
-	CLK("etb", "emu_per_alwon_ck", &emu_per_alwon_ck),
-	CLK(NULL, "clkout2_src_ck", &clkout2_src_ck),
-	CLK(NULL, "sys_clkout2", &sys_clkout2),
-	CLK(NULL, "corex2_fck", &corex2_fck),
-	CLK(NULL, "mpu_ck", &mpu_ck),
-	CLK(NULL, "arm_fck", &arm_fck),
-	CLK("etb", "emu_mpu_alwon_ck", &emu_mpu_alwon_ck),
-	CLK(NULL, "l3_ick", &l3_ick),
-	CLK(NULL, "l4_ick", &l4_ick),
-	CLK(NULL, "rm_ick", &rm_ick),
-	CLK(NULL, "timer_32k_ck", &omap_32k_fck),
-	CLK(NULL, "gpt10_fck", &gpt10_fck),
-	CLK(NULL, "gpt11_fck", &gpt11_fck),
-	CLK(NULL, "core_96m_fck", &core_96m_fck),
-	CLK(NULL, "mmchs2_fck", &mmchs2_fck),
-	CLK(NULL, "mmchs1_fck", &mmchs1_fck),
-	CLK(NULL, "i2c3_fck", &i2c3_fck),
-	CLK(NULL, "i2c2_fck", &i2c2_fck),
-	CLK(NULL, "i2c1_fck", &i2c1_fck),
-	CLK(NULL, "core_48m_fck", &core_48m_fck),
-	CLK(NULL, "mcspi4_fck", &mcspi4_fck),
-	CLK(NULL, "mcspi3_fck", &mcspi3_fck),
-	CLK(NULL, "mcspi2_fck", &mcspi2_fck),
-	CLK(NULL, "mcspi1_fck", &mcspi1_fck),
-	CLK(NULL, "uart2_fck", &uart2_fck),
-	CLK(NULL, "uart1_fck", &uart1_fck),
-	CLK(NULL, "core_12m_fck", &core_12m_fck),
-	CLK("omap_hdq.0", "fck", &hdq_fck),
-	CLK(NULL, "hdq_fck", &hdq_fck),
-	CLK(NULL, "core_l3_ick", &core_l3_ick),
-	CLK(NULL, "sdrc_ick", &sdrc_ick),
-	CLK(NULL, "gpmc_fck", &gpmc_fck),
-	CLK(NULL, "core_l4_ick", &core_l4_ick),
-	CLK("omap_hsmmc.1", "ick", &mmchs2_ick),
-	CLK("omap_hsmmc.0", "ick", &mmchs1_ick),
-	CLK(NULL, "mmchs2_ick", &mmchs2_ick),
-	CLK(NULL, "mmchs1_ick", &mmchs1_ick),
-	CLK("omap_hdq.0", "ick", &hdq_ick),
-	CLK(NULL, "hdq_ick", &hdq_ick),
-	CLK("omap2_mcspi.4", "ick", &mcspi4_ick),
-	CLK("omap2_mcspi.3", "ick", &mcspi3_ick),
-	CLK("omap2_mcspi.2", "ick", &mcspi2_ick),
-	CLK("omap2_mcspi.1", "ick", &mcspi1_ick),
-	CLK(NULL, "mcspi4_ick", &mcspi4_ick),
-	CLK(NULL, "mcspi3_ick", &mcspi3_ick),
-	CLK(NULL, "mcspi2_ick", &mcspi2_ick),
-	CLK(NULL, "mcspi1_ick", &mcspi1_ick),
-	CLK("omap_i2c.3", "ick", &i2c3_ick),
-	CLK("omap_i2c.2", "ick", &i2c2_ick),
-	CLK("omap_i2c.1", "ick", &i2c1_ick),
-	CLK(NULL, "i2c3_ick", &i2c3_ick),
-	CLK(NULL, "i2c2_ick", &i2c2_ick),
-	CLK(NULL, "i2c1_ick", &i2c1_ick),
-	CLK(NULL, "uart2_ick", &uart2_ick),
-	CLK(NULL, "uart1_ick", &uart1_ick),
-	CLK(NULL, "gpt11_ick", &gpt11_ick),
-	CLK(NULL, "gpt10_ick", &gpt10_ick),
-	CLK(NULL, "mcbsp5_ick", &mcbsp5_ick),
-	CLK(NULL, "mcbsp1_ick", &mcbsp1_ick),
-	CLK(NULL, "omapctrl_ick", &omapctrl_ick),
-	CLK(NULL, "dss_tv_fck", &dss_tv_fck),
-	CLK(NULL, "dss_96m_fck", &dss_96m_fck),
-	CLK(NULL, "dss2_alwon_fck", &dss2_alwon_fck),
-	CLK(NULL, "init_60m_fclk", &dummy_ck),
-	CLK(NULL, "gpt1_fck", &gpt1_fck),
-	CLK(NULL, "aes2_ick", &aes2_ick),
-	CLK(NULL, "wkup_32k_fck", &wkup_32k_fck),
-	CLK(NULL, "gpio1_dbck", &gpio1_dbck),
-	CLK(NULL, "sha12_ick", &sha12_ick),
-	CLK(NULL, "wdt2_fck", &wdt2_fck),
-	CLK(NULL, "wkup_l4_ick", &wkup_l4_ick),
-	CLK("omap_wdt", "ick", &wdt2_ick),
-	CLK(NULL, "wdt2_ick", &wdt2_ick),
-	CLK(NULL, "wdt1_ick", &wdt1_ick),
-	CLK(NULL, "gpio1_ick", &gpio1_ick),
-	CLK(NULL, "omap_32ksync_ick", &omap_32ksync_ick),
-	CLK(NULL, "gpt12_ick", &gpt12_ick),
-	CLK(NULL, "gpt1_ick", &gpt1_ick),
-	CLK(NULL, "per_96m_fck", &per_96m_fck),
-	CLK(NULL, "per_48m_fck", &per_48m_fck),
-	CLK(NULL, "uart3_fck", &uart3_fck),
-	CLK(NULL, "gpt2_fck", &gpt2_fck),
-	CLK(NULL, "gpt3_fck", &gpt3_fck),
-	CLK(NULL, "gpt4_fck", &gpt4_fck),
-	CLK(NULL, "gpt5_fck", &gpt5_fck),
-	CLK(NULL, "gpt6_fck", &gpt6_fck),
-	CLK(NULL, "gpt7_fck", &gpt7_fck),
-	CLK(NULL, "gpt8_fck", &gpt8_fck),
-	CLK(NULL, "gpt9_fck", &gpt9_fck),
-	CLK(NULL, "per_32k_alwon_fck", &per_32k_alwon_fck),
-	CLK(NULL, "gpio6_dbck", &gpio6_dbck),
-	CLK(NULL, "gpio5_dbck", &gpio5_dbck),
-	CLK(NULL, "gpio4_dbck", &gpio4_dbck),
-	CLK(NULL, "gpio3_dbck", &gpio3_dbck),
-	CLK(NULL, "gpio2_dbck", &gpio2_dbck),
-	CLK(NULL, "wdt3_fck", &wdt3_fck),
-	CLK(NULL, "per_l4_ick", &per_l4_ick),
-	CLK(NULL, "gpio6_ick", &gpio6_ick),
-	CLK(NULL, "gpio5_ick", &gpio5_ick),
-	CLK(NULL, "gpio4_ick", &gpio4_ick),
-	CLK(NULL, "gpio3_ick", &gpio3_ick),
-	CLK(NULL, "gpio2_ick", &gpio2_ick),
-	CLK(NULL, "wdt3_ick", &wdt3_ick),
-	CLK(NULL, "uart3_ick", &uart3_ick),
-	CLK(NULL, "uart4_ick", &uart4_ick),
-	CLK(NULL, "gpt9_ick", &gpt9_ick),
-	CLK(NULL, "gpt8_ick", &gpt8_ick),
-	CLK(NULL, "gpt7_ick", &gpt7_ick),
-	CLK(NULL, "gpt6_ick", &gpt6_ick),
-	CLK(NULL, "gpt5_ick", &gpt5_ick),
-	CLK(NULL, "gpt4_ick", &gpt4_ick),
-	CLK(NULL, "gpt3_ick", &gpt3_ick),
-	CLK(NULL, "gpt2_ick", &gpt2_ick),
-	CLK(NULL, "mcbsp_clks", &mcbsp_clks),
-	CLK("omap-mcbsp.1", "ick", &mcbsp1_ick),
-	CLK("omap-mcbsp.2", "ick", &mcbsp2_ick),
-	CLK("omap-mcbsp.3", "ick", &mcbsp3_ick),
-	CLK("omap-mcbsp.4", "ick", &mcbsp4_ick),
-	CLK("omap-mcbsp.5", "ick", &mcbsp5_ick),
-	CLK(NULL, "mcbsp1_ick", &mcbsp1_ick),
-	CLK(NULL, "mcbsp2_ick", &mcbsp2_ick),
-	CLK(NULL, "mcbsp3_ick", &mcbsp3_ick),
-	CLK(NULL, "mcbsp4_ick", &mcbsp4_ick),
-	CLK(NULL, "mcbsp5_ick", &mcbsp5_ick),
-	CLK(NULL, "mcbsp1_fck", &mcbsp1_fck),
-	CLK(NULL, "mcbsp2_fck", &mcbsp2_fck),
-	CLK(NULL, "mcbsp3_fck", &mcbsp3_fck),
-	CLK(NULL, "mcbsp4_fck", &mcbsp4_fck),
-	CLK(NULL, "mcbsp5_fck", &mcbsp5_fck),
-	CLK(NULL, "emu_src_mux_ck", &emu_src_mux_ck),
-	CLK("etb", "emu_src_ck", &emu_src_ck),
-	CLK(NULL, "emu_src_mux_ck", &emu_src_mux_ck),
-	CLK(NULL, "emu_src_ck", &emu_src_ck),
-	CLK(NULL, "pclk_fck", &pclk_fck),
-	CLK(NULL, "pclkx2_fck", &pclkx2_fck),
-	CLK(NULL, "atclk_fck", &atclk_fck),
-	CLK(NULL, "traceclk_src_fck", &traceclk_src_fck),
-	CLK(NULL, "traceclk_fck", &traceclk_fck),
-	CLK(NULL, "secure_32k_fck", &secure_32k_fck),
-	CLK(NULL, "gpt12_fck", &gpt12_fck),
-	CLK(NULL, "wdt1_fck", &wdt1_fck),
-	{ NULL },
-};
-
-static struct ti_clk_alias omap36xx_am35xx_omap3430es2plus_clks[] = {
-	CLK(NULL, "dpll5_ck", &dpll5_ck),
-	CLK(NULL, "dpll5_m2_ck", &dpll5_m2_ck),
-	CLK(NULL, "core_d3_ck", &core_d3_ck),
-	CLK(NULL, "core_d4_ck", &core_d4_ck),
-	CLK(NULL, "core_d6_ck", &core_d6_ck),
-	CLK(NULL, "omap_192m_alwon_fck", &omap_192m_alwon_fck),
-	CLK(NULL, "core_d2_ck", &core_d2_ck),
-	CLK(NULL, "corex2_d3_fck", &corex2_d3_fck),
-	CLK(NULL, "corex2_d5_fck", &corex2_d5_fck),
-	CLK(NULL, "sgx_fck", &sgx_fck),
-	CLK(NULL, "sgx_ick", &sgx_ick),
-	CLK(NULL, "cpefuse_fck", &cpefuse_fck),
-	CLK(NULL, "ts_fck", &ts_fck),
-	CLK(NULL, "usbtll_fck", &usbtll_fck),
-	CLK(NULL, "usbtll_ick", &usbtll_ick),
-	CLK("omap_hsmmc.2", "ick", &mmchs3_ick),
-	CLK(NULL, "mmchs3_ick", &mmchs3_ick),
-	CLK(NULL, "mmchs3_fck", &mmchs3_fck),
-	CLK(NULL, "dss1_alwon_fck", &dss1_alwon_fck_3430es2),
-	CLK("omapdss_dss", "ick", &dss_ick_3430es2),
-	CLK(NULL, "dss_ick", &dss_ick_3430es2),
-	CLK(NULL, "usbhost_120m_fck", &usbhost_120m_fck),
-	CLK(NULL, "usbhost_48m_fck", &usbhost_48m_fck),
-	CLK(NULL, "usbhost_ick", &usbhost_ick),
-	{ NULL },
-};
-
-static struct ti_clk_alias omap3430es1_clks[] = {
-	CLK(NULL, "gfx_l3_ck", &gfx_l3_ck),
-	CLK(NULL, "gfx_l3_fck", &gfx_l3_fck),
-	CLK(NULL, "gfx_l3_ick", &gfx_l3_ick),
-	CLK(NULL, "gfx_cg1_ck", &gfx_cg1_ck),
-	CLK(NULL, "gfx_cg2_ck", &gfx_cg2_ck),
-	CLK(NULL, "d2d_26m_fck", &d2d_26m_fck),
-	CLK(NULL, "fshostusb_fck", &fshostusb_fck),
-	CLK(NULL, "ssi_ssr_fck", &ssi_ssr_fck_3430es1),
-	CLK(NULL, "ssi_sst_fck", &ssi_sst_fck_3430es1),
-	CLK("musb-omap2430", "ick", &hsotgusb_ick_3430es1),
-	CLK(NULL, "hsotgusb_ick", &hsotgusb_ick_3430es1),
-	CLK(NULL, "fac_ick", &fac_ick),
-	CLK(NULL, "ssi_ick", &ssi_ick_3430es1),
-	CLK(NULL, "usb_l4_ick", &usb_l4_ick),
-	CLK(NULL, "dss1_alwon_fck", &dss1_alwon_fck_3430es1),
-	CLK("omapdss_dss", "ick", &dss_ick_3430es1),
-	CLK(NULL, "dss_ick", &dss_ick_3430es1),
-	{ NULL },
-};
-
-static struct ti_clk_alias omap36xx_clks[] = {
-	CLK(NULL, "uart4_fck", &uart4_fck),
-	{ NULL },
-};
-
-static struct ti_clk_alias am35xx_clks[] = {
-	CLK(NULL, "ipss_ick", &ipss_ick),
-	CLK(NULL, "rmii_ck", &rmii_ck),
-	CLK(NULL, "pclk_ck", &pclk_ck),
-	CLK(NULL, "emac_ick", &emac_ick),
-	CLK(NULL, "emac_fck", &emac_fck),
-	CLK("davinci_emac.0", NULL, &emac_ick),
-	CLK("davinci_mdio.0", NULL, &emac_fck),
-	CLK("vpfe-capture", "master", &vpfe_ick),
-	CLK("vpfe-capture", "slave", &vpfe_fck),
-	CLK(NULL, "hsotgusb_ick", &hsotgusb_ick_am35xx),
-	CLK(NULL, "hsotgusb_fck", &hsotgusb_fck_am35xx),
-	CLK(NULL, "hecc_ck", &hecc_ck),
-	CLK(NULL, "uart4_ick", &uart4_ick_am35xx),
-	CLK(NULL, "uart4_fck", &uart4_fck_am35xx),
-	{ NULL },
-};
-
-static struct ti_clk *omap36xx_clk_patches[] = {
-	&dpll4_m3x2_ck_omap36xx,
-	&dpll3_m3x2_ck_omap36xx,
-	&dpll4_m6x2_ck_omap36xx,
-	&dpll4_m2x2_ck_omap36xx,
-	&dpll4_m5x2_ck_omap36xx,
-	&dpll4_ck_omap36xx,
-	NULL,
-};
-
-static const char *enable_init_clks[] = {
-	"sdrc_ick",
-	"gpmc_fck",
-	"omapctrl_ick",
-};
-
-static void __init omap3_clk_legacy_common_init(void)
-{
-	omap2_clk_disable_autoidle_all();
-
-	omap2_clk_enable_init_clocks(enable_init_clks,
-				     ARRAY_SIZE(enable_init_clks));
-
-	pr_info("Clocking rate (Crystal/Core/MPU): %ld.%01ld/%ld/%ld MHz\n",
-		(clk_get_rate(osc_sys_ck.clk) / 1000000),
-		(clk_get_rate(osc_sys_ck.clk) / 100000) % 10,
-		(clk_get_rate(core_ck.clk) / 1000000),
-		(clk_get_rate(arm_fck.clk) / 1000000));
-}
-
-int __init omap3430es1_clk_legacy_init(void)
-{
-	int r;
-
-	r = ti_clk_register_legacy_clks(omap3430es1_clks);
-	r |= ti_clk_register_legacy_clks(omap34xx_omap36xx_clks);
-	r |= ti_clk_register_legacy_clks(omap3xxx_clks);
-
-	omap3_clk_legacy_common_init();
-
-	return r;
-}
-
-int __init omap3430_clk_legacy_init(void)
-{
-	int r;
-
-	r = ti_clk_register_legacy_clks(omap34xx_omap36xx_clks);
-	r |= ti_clk_register_legacy_clks(omap36xx_omap3430es2plus_clks);
-	r |= ti_clk_register_legacy_clks(omap36xx_am35xx_omap3430es2plus_clks);
-	r |= ti_clk_register_legacy_clks(omap3xxx_clks);
-
-	omap3_clk_legacy_common_init();
-	omap3_clk_lock_dpll5();
-
-	return r;
-}
-
-int __init omap36xx_clk_legacy_init(void)
-{
-	int r;
-
-	ti_clk_patch_legacy_clks(omap36xx_clk_patches);
-	r = ti_clk_register_legacy_clks(omap36xx_clks);
-	r |= ti_clk_register_legacy_clks(omap36xx_omap3430es2plus_clks);
-	r |= ti_clk_register_legacy_clks(omap34xx_omap36xx_clks);
-	r |= ti_clk_register_legacy_clks(omap36xx_am35xx_omap3430es2plus_clks);
-	r |= ti_clk_register_legacy_clks(omap3xxx_clks);
-
-	omap3_clk_legacy_common_init();
-	omap3_clk_lock_dpll5();
-
-	return r;
-}
-
-int __init am35xx_clk_legacy_init(void)
-{
-	int r;
-
-	r = ti_clk_register_legacy_clks(am35xx_clks);
-	r |= ti_clk_register_legacy_clks(omap36xx_am35xx_omap3430es2plus_clks);
-	r |= ti_clk_register_legacy_clks(omap3xxx_clks);
-
-	omap3_clk_legacy_common_init();
-	omap3_clk_lock_dpll5();
-
-	return r;
-}
diff --git a/drivers/clk/ti/clk-3xxx.c b/drivers/clk/ti/clk-3xxx.c
index b1251cae98b8..8aa5f5793835 100644
--- a/drivers/clk/ti/clk-3xxx.c
+++ b/drivers/clk/ti/clk-3xxx.c
@@ -224,296 +224,43 @@ const struct clk_hw_omap_ops clkhwops_am35xx_ipss_wait = {
 };
 
 static struct ti_dt_clk omap3xxx_clks[] = {
-	DT_CLK(NULL, "apb_pclk", "dummy_apb_pclk"),
-	DT_CLK(NULL, "omap_32k_fck", "omap_32k_fck"),
-	DT_CLK(NULL, "virt_12m_ck", "virt_12m_ck"),
-	DT_CLK(NULL, "virt_13m_ck", "virt_13m_ck"),
-	DT_CLK(NULL, "virt_19200000_ck", "virt_19200000_ck"),
-	DT_CLK(NULL, "virt_26000000_ck", "virt_26000000_ck"),
-	DT_CLK(NULL, "virt_38_4m_ck", "virt_38_4m_ck"),
-	DT_CLK(NULL, "osc_sys_ck", "osc_sys_ck"),
-	DT_CLK("twl", "fck", "osc_sys_ck"),
-	DT_CLK(NULL, "sys_ck", "sys_ck"),
-	DT_CLK(NULL, "omap_96m_alwon_fck", "omap_96m_alwon_fck"),
-	DT_CLK("etb", "emu_core_alwon_ck", "emu_core_alwon_ck"),
-	DT_CLK(NULL, "sys_altclk", "sys_altclk"),
-	DT_CLK(NULL, "sys_clkout1", "sys_clkout1"),
-	DT_CLK(NULL, "dpll1_ck", "dpll1_ck"),
-	DT_CLK(NULL, "dpll1_x2_ck", "dpll1_x2_ck"),
-	DT_CLK(NULL, "dpll1_x2m2_ck", "dpll1_x2m2_ck"),
-	DT_CLK(NULL, "dpll3_ck", "dpll3_ck"),
-	DT_CLK(NULL, "core_ck", "core_ck"),
-	DT_CLK(NULL, "dpll3_x2_ck", "dpll3_x2_ck"),
-	DT_CLK(NULL, "dpll3_m2_ck", "dpll3_m2_ck"),
-	DT_CLK(NULL, "dpll3_m2x2_ck", "dpll3_m2x2_ck"),
-	DT_CLK(NULL, "dpll3_m3_ck", "dpll3_m3_ck"),
-	DT_CLK(NULL, "dpll3_m3x2_ck", "dpll3_m3x2_ck"),
-	DT_CLK(NULL, "dpll4_ck", "dpll4_ck"),
-	DT_CLK(NULL, "dpll4_x2_ck", "dpll4_x2_ck"),
-	DT_CLK(NULL, "omap_96m_fck", "omap_96m_fck"),
-	DT_CLK(NULL, "cm_96m_fck", "cm_96m_fck"),
-	DT_CLK(NULL, "omap_54m_fck", "omap_54m_fck"),
-	DT_CLK(NULL, "omap_48m_fck", "omap_48m_fck"),
-	DT_CLK(NULL, "omap_12m_fck", "omap_12m_fck"),
-	DT_CLK(NULL, "dpll4_m2_ck", "dpll4_m2_ck"),
-	DT_CLK(NULL, "dpll4_m2x2_ck", "dpll4_m2x2_ck"),
-	DT_CLK(NULL, "dpll4_m3_ck", "dpll4_m3_ck"),
-	DT_CLK(NULL, "dpll4_m3x2_ck", "dpll4_m3x2_ck"),
-	DT_CLK(NULL, "dpll4_m4_ck", "dpll4_m4_ck"),
-	DT_CLK(NULL, "dpll4_m4x2_ck", "dpll4_m4x2_ck"),
-	DT_CLK(NULL, "dpll4_m5_ck", "dpll4_m5_ck"),
-	DT_CLK(NULL, "dpll4_m5x2_ck", "dpll4_m5x2_ck"),
-	DT_CLK(NULL, "dpll4_m6_ck", "dpll4_m6_ck"),
-	DT_CLK(NULL, "dpll4_m6x2_ck", "dpll4_m6x2_ck"),
-	DT_CLK("etb", "emu_per_alwon_ck", "emu_per_alwon_ck"),
-	DT_CLK(NULL, "clkout2_src_ck", "clkout2_src_ck"),
-	DT_CLK(NULL, "sys_clkout2", "sys_clkout2"),
-	DT_CLK(NULL, "corex2_fck", "corex2_fck"),
-	DT_CLK(NULL, "dpll1_fck", "dpll1_fck"),
-	DT_CLK(NULL, "mpu_ck", "mpu_ck"),
-	DT_CLK(NULL, "arm_fck", "arm_fck"),
-	DT_CLK("etb", "emu_mpu_alwon_ck", "emu_mpu_alwon_ck"),
-	DT_CLK(NULL, "l3_ick", "l3_ick"),
-	DT_CLK(NULL, "l4_ick", "l4_ick"),
-	DT_CLK(NULL, "rm_ick", "rm_ick"),
-	DT_CLK(NULL, "gpt10_fck", "gpt10_fck"),
-	DT_CLK(NULL, "gpt11_fck", "gpt11_fck"),
-	DT_CLK(NULL, "core_96m_fck", "core_96m_fck"),
-	DT_CLK(NULL, "mmchs2_fck", "mmchs2_fck"),
-	DT_CLK(NULL, "mmchs1_fck", "mmchs1_fck"),
-	DT_CLK(NULL, "i2c3_fck", "i2c3_fck"),
-	DT_CLK(NULL, "i2c2_fck", "i2c2_fck"),
-	DT_CLK(NULL, "i2c1_fck", "i2c1_fck"),
-	DT_CLK(NULL, "core_48m_fck", "core_48m_fck"),
-	DT_CLK(NULL, "mcspi4_fck", "mcspi4_fck"),
-	DT_CLK(NULL, "mcspi3_fck", "mcspi3_fck"),
-	DT_CLK(NULL, "mcspi2_fck", "mcspi2_fck"),
-	DT_CLK(NULL, "mcspi1_fck", "mcspi1_fck"),
-	DT_CLK(NULL, "uart2_fck", "uart2_fck"),
-	DT_CLK(NULL, "uart1_fck", "uart1_fck"),
-	DT_CLK(NULL, "core_12m_fck", "core_12m_fck"),
-	DT_CLK("omap_hdq.0", "fck", "hdq_fck"),
-	DT_CLK(NULL, "hdq_fck", "hdq_fck"),
-	DT_CLK(NULL, "core_l3_ick", "core_l3_ick"),
-	DT_CLK(NULL, "sdrc_ick", "sdrc_ick"),
-	DT_CLK(NULL, "gpmc_fck", "gpmc_fck"),
-	DT_CLK(NULL, "core_l4_ick", "core_l4_ick"),
-	DT_CLK("omap_hsmmc.1", "ick", "mmchs2_ick"),
-	DT_CLK("omap_hsmmc.0", "ick", "mmchs1_ick"),
-	DT_CLK(NULL, "mmchs2_ick", "mmchs2_ick"),
-	DT_CLK(NULL, "mmchs1_ick", "mmchs1_ick"),
-	DT_CLK("omap_hdq.0", "ick", "hdq_ick"),
-	DT_CLK(NULL, "hdq_ick", "hdq_ick"),
-	DT_CLK("omap2_mcspi.4", "ick", "mcspi4_ick"),
-	DT_CLK("omap2_mcspi.3", "ick", "mcspi3_ick"),
-	DT_CLK("omap2_mcspi.2", "ick", "mcspi2_ick"),
-	DT_CLK("omap2_mcspi.1", "ick", "mcspi1_ick"),
-	DT_CLK(NULL, "mcspi4_ick", "mcspi4_ick"),
-	DT_CLK(NULL, "mcspi3_ick", "mcspi3_ick"),
-	DT_CLK(NULL, "mcspi2_ick", "mcspi2_ick"),
-	DT_CLK(NULL, "mcspi1_ick", "mcspi1_ick"),
-	DT_CLK("omap_i2c.3", "ick", "i2c3_ick"),
-	DT_CLK("omap_i2c.2", "ick", "i2c2_ick"),
-	DT_CLK("omap_i2c.1", "ick", "i2c1_ick"),
-	DT_CLK(NULL, "i2c3_ick", "i2c3_ick"),
-	DT_CLK(NULL, "i2c2_ick", "i2c2_ick"),
-	DT_CLK(NULL, "i2c1_ick", "i2c1_ick"),
-	DT_CLK(NULL, "uart2_ick", "uart2_ick"),
-	DT_CLK(NULL, "uart1_ick", "uart1_ick"),
-	DT_CLK(NULL, "gpt11_ick", "gpt11_ick"),
-	DT_CLK(NULL, "gpt10_ick", "gpt10_ick"),
-	DT_CLK(NULL, "omapctrl_ick", "omapctrl_ick"),
-	DT_CLK(NULL, "dss_tv_fck", "dss_tv_fck"),
-	DT_CLK(NULL, "dss_96m_fck", "dss_96m_fck"),
-	DT_CLK(NULL, "dss2_alwon_fck", "dss2_alwon_fck"),
-	DT_CLK(NULL, "init_60m_fclk", "dummy_ck"),
-	DT_CLK(NULL, "gpt1_fck", "gpt1_fck"),
-	DT_CLK(NULL, "aes2_ick", "aes2_ick"),
-	DT_CLK(NULL, "wkup_32k_fck", "wkup_32k_fck"),
-	DT_CLK(NULL, "gpio1_dbck", "gpio1_dbck"),
-	DT_CLK(NULL, "sha12_ick", "sha12_ick"),
-	DT_CLK(NULL, "wdt2_fck", "wdt2_fck"),
-	DT_CLK("omap_wdt", "ick", "wdt2_ick"),
-	DT_CLK(NULL, "wdt2_ick", "wdt2_ick"),
-	DT_CLK(NULL, "wdt1_ick", "wdt1_ick"),
-	DT_CLK(NULL, "gpio1_ick", "gpio1_ick"),
-	DT_CLK(NULL, "omap_32ksync_ick", "omap_32ksync_ick"),
-	DT_CLK(NULL, "gpt12_ick", "gpt12_ick"),
-	DT_CLK(NULL, "gpt1_ick", "gpt1_ick"),
-	DT_CLK(NULL, "per_96m_fck", "per_96m_fck"),
-	DT_CLK(NULL, "per_48m_fck", "per_48m_fck"),
-	DT_CLK(NULL, "uart3_fck", "uart3_fck"),
-	DT_CLK(NULL, "gpt2_fck", "gpt2_fck"),
-	DT_CLK(NULL, "gpt3_fck", "gpt3_fck"),
-	DT_CLK(NULL, "gpt4_fck", "gpt4_fck"),
-	DT_CLK(NULL, "gpt5_fck", "gpt5_fck"),
-	DT_CLK(NULL, "gpt6_fck", "gpt6_fck"),
-	DT_CLK(NULL, "gpt7_fck", "gpt7_fck"),
-	DT_CLK(NULL, "gpt8_fck", "gpt8_fck"),
-	DT_CLK(NULL, "gpt9_fck", "gpt9_fck"),
-	DT_CLK(NULL, "per_32k_alwon_fck", "per_32k_alwon_fck"),
-	DT_CLK(NULL, "gpio6_dbck", "gpio6_dbck"),
-	DT_CLK(NULL, "gpio5_dbck", "gpio5_dbck"),
-	DT_CLK(NULL, "gpio4_dbck", "gpio4_dbck"),
-	DT_CLK(NULL, "gpio3_dbck", "gpio3_dbck"),
-	DT_CLK(NULL, "gpio2_dbck", "gpio2_dbck"),
-	DT_CLK(NULL, "wdt3_fck", "wdt3_fck"),
-	DT_CLK(NULL, "per_l4_ick", "per_l4_ick"),
-	DT_CLK(NULL, "gpio6_ick", "gpio6_ick"),
-	DT_CLK(NULL, "gpio5_ick", "gpio5_ick"),
-	DT_CLK(NULL, "gpio4_ick", "gpio4_ick"),
-	DT_CLK(NULL, "gpio3_ick", "gpio3_ick"),
-	DT_CLK(NULL, "gpio2_ick", "gpio2_ick"),
-	DT_CLK(NULL, "wdt3_ick", "wdt3_ick"),
-	DT_CLK(NULL, "uart3_ick", "uart3_ick"),
-	DT_CLK(NULL, "gpt9_ick", "gpt9_ick"),
-	DT_CLK(NULL, "gpt8_ick", "gpt8_ick"),
-	DT_CLK(NULL, "gpt7_ick", "gpt7_ick"),
-	DT_CLK(NULL, "gpt6_ick", "gpt6_ick"),
-	DT_CLK(NULL, "gpt5_ick", "gpt5_ick"),
-	DT_CLK(NULL, "gpt4_ick", "gpt4_ick"),
-	DT_CLK(NULL, "gpt3_ick", "gpt3_ick"),
-	DT_CLK(NULL, "gpt2_ick", "gpt2_ick"),
-	DT_CLK(NULL, "mcbsp_clks", "mcbsp_clks"),
-	DT_CLK(NULL, "mcbsp1_ick", "mcbsp1_ick"),
-	DT_CLK(NULL, "mcbsp2_ick", "mcbsp2_ick"),
-	DT_CLK(NULL, "mcbsp3_ick", "mcbsp3_ick"),
-	DT_CLK(NULL, "mcbsp4_ick", "mcbsp4_ick"),
-	DT_CLK(NULL, "mcbsp5_ick", "mcbsp5_ick"),
-	DT_CLK(NULL, "mcbsp1_fck", "mcbsp1_fck"),
-	DT_CLK(NULL, "mcbsp2_fck", "mcbsp2_fck"),
-	DT_CLK(NULL, "mcbsp3_fck", "mcbsp3_fck"),
-	DT_CLK(NULL, "mcbsp4_fck", "mcbsp4_fck"),
-	DT_CLK(NULL, "mcbsp5_fck", "mcbsp5_fck"),
-	DT_CLK("etb", "emu_src_ck", "emu_src_ck"),
-	DT_CLK(NULL, "emu_src_ck", "emu_src_ck"),
-	DT_CLK(NULL, "pclk_fck", "pclk_fck"),
-	DT_CLK(NULL, "pclkx2_fck", "pclkx2_fck"),
-	DT_CLK(NULL, "atclk_fck", "atclk_fck"),
-	DT_CLK(NULL, "traceclk_src_fck", "traceclk_src_fck"),
-	DT_CLK(NULL, "traceclk_fck", "traceclk_fck"),
-	DT_CLK(NULL, "secure_32k_fck", "secure_32k_fck"),
-	DT_CLK(NULL, "gpt12_fck", "gpt12_fck"),
-	DT_CLK(NULL, "wdt1_fck", "wdt1_fck"),
 	DT_CLK(NULL, "timer_32k_ck", "omap_32k_fck"),
 	DT_CLK(NULL, "timer_sys_ck", "sys_ck"),
-	DT_CLK(NULL, "cpufreq_ck", "dpll1_ck"),
-	{ .node_name = NULL },
-};
-
-static struct ti_dt_clk omap34xx_omap36xx_clks[] = {
-	DT_CLK(NULL, "aes1_ick", "aes1_ick"),
-	DT_CLK("omap_rng", "ick", "rng_ick"),
-	DT_CLK("omap3-rom-rng", "ick", "rng_ick"),
-	DT_CLK(NULL, "sha11_ick", "sha11_ick"),
-	DT_CLK(NULL, "des1_ick", "des1_ick"),
-	DT_CLK(NULL, "cam_mclk", "cam_mclk"),
-	DT_CLK(NULL, "cam_ick", "cam_ick"),
-	DT_CLK(NULL, "csi2_96m_fck", "csi2_96m_fck"),
-	DT_CLK(NULL, "security_l3_ick", "security_l3_ick"),
-	DT_CLK(NULL, "pka_ick", "pka_ick"),
-	DT_CLK(NULL, "icr_ick", "icr_ick"),
-	DT_CLK("omap-aes", "ick", "aes2_ick"),
-	DT_CLK("omap-sham", "ick", "sha12_ick"),
-	DT_CLK(NULL, "des2_ick", "des2_ick"),
-	DT_CLK(NULL, "mspro_ick", "mspro_ick"),
-	DT_CLK(NULL, "mailboxes_ick", "mailboxes_ick"),
-	DT_CLK(NULL, "ssi_l4_ick", "ssi_l4_ick"),
-	DT_CLK(NULL, "sr1_fck", "sr1_fck"),
-	DT_CLK(NULL, "sr2_fck", "sr2_fck"),
-	DT_CLK(NULL, "sr_l4_ick", "sr_l4_ick"),
-	DT_CLK(NULL, "security_l4_ick2", "security_l4_ick2"),
-	DT_CLK(NULL, "wkup_l4_ick", "wkup_l4_ick"),
-	DT_CLK(NULL, "dpll2_fck", "dpll2_fck"),
-	DT_CLK(NULL, "iva2_ck", "iva2_ck"),
-	DT_CLK(NULL, "modem_fck", "modem_fck"),
-	DT_CLK(NULL, "sad2d_ick", "sad2d_ick"),
-	DT_CLK(NULL, "mad2d_ick", "mad2d_ick"),
-	DT_CLK(NULL, "mspro_fck", "mspro_fck"),
-	DT_CLK(NULL, "dpll2_ck", "dpll2_ck"),
-	DT_CLK(NULL, "dpll2_m2_ck", "dpll2_m2_ck"),
 	{ .node_name = NULL },
 };
 
 static struct ti_dt_clk omap36xx_omap3430es2plus_clks[] = {
 	DT_CLK(NULL, "ssi_ssr_fck", "ssi_ssr_fck_3430es2"),
 	DT_CLK(NULL, "ssi_sst_fck", "ssi_sst_fck_3430es2"),
-	DT_CLK("musb-omap2430", "ick", "hsotgusb_ick_3430es2"),
 	DT_CLK(NULL, "hsotgusb_ick", "hsotgusb_ick_3430es2"),
 	DT_CLK(NULL, "ssi_ick", "ssi_ick_3430es2"),
-	DT_CLK(NULL, "usim_fck", "usim_fck"),
-	DT_CLK(NULL, "usim_ick", "usim_ick"),
 	{ .node_name = NULL },
 };
 
 static struct ti_dt_clk omap3430es1_clks[] = {
-	DT_CLK(NULL, "gfx_l3_ck", "gfx_l3_ck"),
-	DT_CLK(NULL, "gfx_l3_fck", "gfx_l3_fck"),
-	DT_CLK(NULL, "gfx_l3_ick", "gfx_l3_ick"),
-	DT_CLK(NULL, "gfx_cg1_ck", "gfx_cg1_ck"),
-	DT_CLK(NULL, "gfx_cg2_ck", "gfx_cg2_ck"),
-	DT_CLK(NULL, "d2d_26m_fck", "d2d_26m_fck"),
-	DT_CLK(NULL, "fshostusb_fck", "fshostusb_fck"),
 	DT_CLK(NULL, "ssi_ssr_fck", "ssi_ssr_fck_3430es1"),
 	DT_CLK(NULL, "ssi_sst_fck", "ssi_sst_fck_3430es1"),
-	DT_CLK("musb-omap2430", "ick", "hsotgusb_ick_3430es1"),
 	DT_CLK(NULL, "hsotgusb_ick", "hsotgusb_ick_3430es1"),
-	DT_CLK(NULL, "fac_ick", "fac_ick"),
 	DT_CLK(NULL, "ssi_ick", "ssi_ick_3430es1"),
-	DT_CLK(NULL, "usb_l4_ick", "usb_l4_ick"),
 	DT_CLK(NULL, "dss1_alwon_fck", "dss1_alwon_fck_3430es1"),
-	DT_CLK("omapdss_dss", "ick", "dss_ick_3430es1"),
 	DT_CLK(NULL, "dss_ick", "dss_ick_3430es1"),
 	{ .node_name = NULL },
 };
 
 static struct ti_dt_clk omap36xx_am35xx_omap3430es2plus_clks[] = {
-	DT_CLK(NULL, "virt_16_8m_ck", "virt_16_8m_ck"),
-	DT_CLK(NULL, "dpll5_ck", "dpll5_ck"),
-	DT_CLK(NULL, "dpll5_m2_ck", "dpll5_m2_ck"),
-	DT_CLK(NULL, "sgx_fck", "sgx_fck"),
-	DT_CLK(NULL, "sgx_ick", "sgx_ick"),
-	DT_CLK(NULL, "cpefuse_fck", "cpefuse_fck"),
-	DT_CLK(NULL, "ts_fck", "ts_fck"),
-	DT_CLK(NULL, "usbtll_fck", "usbtll_fck"),
-	DT_CLK(NULL, "usbtll_ick", "usbtll_ick"),
-	DT_CLK("omap_hsmmc.2", "ick", "mmchs3_ick"),
-	DT_CLK(NULL, "mmchs3_ick", "mmchs3_ick"),
-	DT_CLK(NULL, "mmchs3_fck", "mmchs3_fck"),
 	DT_CLK(NULL, "dss1_alwon_fck", "dss1_alwon_fck_3430es2"),
-	DT_CLK("omapdss_dss", "ick", "dss_ick_3430es2"),
 	DT_CLK(NULL, "dss_ick", "dss_ick_3430es2"),
-	DT_CLK(NULL, "usbhost_120m_fck", "usbhost_120m_fck"),
-	DT_CLK(NULL, "usbhost_48m_fck", "usbhost_48m_fck"),
-	DT_CLK(NULL, "usbhost_ick", "usbhost_ick"),
 	{ .node_name = NULL },
 };
 
 static struct ti_dt_clk am35xx_clks[] = {
-	DT_CLK(NULL, "ipss_ick", "ipss_ick"),
-	DT_CLK(NULL, "rmii_ck", "rmii_ck"),
-	DT_CLK(NULL, "pclk_ck", "pclk_ck"),
-	DT_CLK(NULL, "emac_ick", "emac_ick"),
-	DT_CLK(NULL, "emac_fck", "emac_fck"),
-	DT_CLK("davinci_emac.0", NULL, "emac_ick"),
-	DT_CLK("davinci_mdio.0", NULL, "emac_fck"),
-	DT_CLK("vpfe-capture", "master", "vpfe_ick"),
-	DT_CLK("vpfe-capture", "slave", "vpfe_fck"),
 	DT_CLK(NULL, "hsotgusb_ick", "hsotgusb_ick_am35xx"),
 	DT_CLK(NULL, "hsotgusb_fck", "hsotgusb_fck_am35xx"),
-	DT_CLK(NULL, "hecc_ck", "hecc_ck"),
 	DT_CLK(NULL, "uart4_ick", "uart4_ick_am35xx"),
 	DT_CLK(NULL, "uart4_fck", "uart4_fck_am35xx"),
 	{ .node_name = NULL },
 };
 
-static struct ti_dt_clk omap36xx_clks[] = {
-	DT_CLK(NULL, "omap_192m_alwon_fck", "omap_192m_alwon_fck"),
-	DT_CLK(NULL, "uart4_fck", "uart4_fck"),
-	DT_CLK(NULL, "uart4_ick", "uart4_ick"),
-	{ .node_name = NULL },
-};
-
 static const char *enable_init_clks[] = {
 	"sdrc_ick",
 	"gpmc_fck",
@@ -579,16 +326,10 @@ static int __init omap3xxx_dt_clk_init(int soc_type)
 	    soc_type == OMAP3_SOC_OMAP3630)
 		ti_dt_clocks_register(omap36xx_omap3430es2plus_clks);
 
-	if (soc_type == OMAP3_SOC_OMAP3430_ES1 ||
-	    soc_type == OMAP3_SOC_OMAP3430_ES2_PLUS ||
-	    soc_type == OMAP3_SOC_OMAP3630)
-		ti_dt_clocks_register(omap34xx_omap36xx_clks);
-
-	if (soc_type == OMAP3_SOC_OMAP3630)
-		ti_dt_clocks_register(omap36xx_clks);
-
 	omap2_clk_disable_autoidle_all();
 
+	ti_clk_add_aliases();
+
 	omap2_clk_enable_init_clocks(enable_init_clks,
 				     ARRAY_SIZE(enable_init_clks));
 
diff --git a/drivers/clk/ti/clk-43xx.c b/drivers/clk/ti/clk-43xx.c
index e816a7500e43..2b7c2e017665 100644
--- a/drivers/clk/ti/clk-43xx.c
+++ b/drivers/clk/ti/clk-43xx.c
@@ -19,109 +19,208 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clk/ti.h>
+#include <dt-bindings/clock/am4.h>
 
 #include "clock.h"
 
+static const char * const am4_synctimer_32kclk_parents[] __initconst = {
+	"mux_synctimer32k_ck",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data am4_counter_32k_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, am4_synctimer_32kclk_parents, NULL },
+	{ 0 },
+};
+
+static const char * const am4_gpio0_dbclk_parents[] __initconst = {
+	"gpio0_dbclk_mux_ck",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data am4_gpio1_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, am4_gpio0_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data am4_l4_wkup_clkctrl_regs[] __initconst = {
+	{ AM4_ADC_TSC_CLKCTRL, NULL, CLKF_SW_SUP, "adc_tsc_fck", "l3s_tsc_clkdm" },
+	{ AM4_L4_WKUP_CLKCTRL, NULL, CLKF_SW_SUP, "sys_clkin_ck", "l4_wkup_clkdm" },
+	{ AM4_WKUP_M3_CLKCTRL, NULL, CLKF_NO_IDLEST, "sys_clkin_ck" },
+	{ AM4_COUNTER_32K_CLKCTRL, am4_counter_32k_bit_data, CLKF_SW_SUP, "l4_wkup_cm:clk:0210:8" },
+	{ AM4_TIMER1_CLKCTRL, NULL, CLKF_SW_SUP, "timer1_fck", "l4_wkup_clkdm" },
+	{ AM4_WD_TIMER2_CLKCTRL, NULL, CLKF_SW_SUP, "wdt1_fck", "l4_wkup_clkdm" },
+	{ AM4_I2C1_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_wkupdm_ck", "l4_wkup_clkdm" },
+	{ AM4_UART1_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_wkupdm_ck", "l4_wkup_clkdm" },
+	{ AM4_SMARTREFLEX0_CLKCTRL, NULL, CLKF_SW_SUP, "smartreflex0_fck", "l4_wkup_clkdm" },
+	{ AM4_SMARTREFLEX1_CLKCTRL, NULL, CLKF_SW_SUP, "smartreflex1_fck", "l4_wkup_clkdm" },
+	{ AM4_CONTROL_CLKCTRL, NULL, CLKF_SW_SUP, "sys_clkin_ck", "l4_wkup_clkdm" },
+	{ AM4_GPIO1_CLKCTRL, am4_gpio1_bit_data, CLKF_SW_SUP, "sys_clkin_ck", "l4_wkup_clkdm" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data am4_mpu_clkctrl_regs[] __initconst = {
+	{ AM4_MPU_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_mpu_m2_ck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data am4_gfx_l3_clkctrl_regs[] __initconst = {
+	{ AM4_GFX_CLKCTRL, NULL, CLKF_SW_SUP, "gfx_fck_div_ck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data am4_l4_rtc_clkctrl_regs[] __initconst = {
+	{ AM4_RTC_CLKCTRL, NULL, CLKF_SW_SUP, "clk_32768_ck" },
+	{ 0 },
+};
+
+static const char * const am4_usb_otg_ss0_refclk960m_parents[] __initconst = {
+	"dpll_per_clkdcoldo",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data am4_usb_otg_ss0_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, am4_usb_otg_ss0_refclk960m_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data am4_usb_otg_ss1_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, am4_usb_otg_ss0_refclk960m_parents, NULL },
+	{ 0 },
+};
+
+static const char * const am4_gpio1_dbclk_parents[] __initconst = {
+	"clkdiv32k_ick",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data am4_gpio2_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, am4_gpio1_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data am4_gpio3_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, am4_gpio1_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data am4_gpio4_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, am4_gpio1_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data am4_gpio5_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, am4_gpio1_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data am4_gpio6_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, am4_gpio1_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data am4_l4_per_clkctrl_regs[] __initconst = {
+	{ AM4_L3_MAIN_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM4_AES_CLKCTRL, NULL, CLKF_SW_SUP, "aes0_fck", "l3_clkdm" },
+	{ AM4_DES_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM4_L3_INSTR_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM4_OCMCRAM_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM4_SHAM_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM4_VPFE0_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3s_clkdm" },
+	{ AM4_VPFE1_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3s_clkdm" },
+	{ AM4_TPCC_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM4_TPTC0_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM4_TPTC1_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM4_TPTC2_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" },
+	{ AM4_L4_HS_CLKCTRL, NULL, CLKF_SW_SUP, "l4hs_gclk", "l3_clkdm" },
+	{ AM4_GPMC_CLKCTRL, NULL, CLKF_SW_SUP, "l3s_gclk", "l3s_clkdm" },
+	{ AM4_MCASP0_CLKCTRL, NULL, CLKF_SW_SUP, "mcasp0_fck", "l3s_clkdm" },
+	{ AM4_MCASP1_CLKCTRL, NULL, CLKF_SW_SUP, "mcasp1_fck", "l3s_clkdm" },
+	{ AM4_MMC3_CLKCTRL, NULL, CLKF_SW_SUP, "mmc_clk", "l3s_clkdm" },
+	{ AM4_QSPI_CLKCTRL, NULL, CLKF_SW_SUP, "l3s_gclk", "l3s_clkdm" },
+	{ AM4_USB_OTG_SS0_CLKCTRL, am4_usb_otg_ss0_bit_data, CLKF_SW_SUP, "l3s_gclk", "l3s_clkdm" },
+	{ AM4_USB_OTG_SS1_CLKCTRL, am4_usb_otg_ss1_bit_data, CLKF_SW_SUP, "l3s_gclk", "l3s_clkdm" },
+	{ AM4_PRUSS_CLKCTRL, NULL, CLKF_SW_SUP, "pruss_ocp_gclk", "pruss_ocp_clkdm" },
+	{ AM4_L4_LS_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_D_CAN0_CLKCTRL, NULL, CLKF_SW_SUP, "dcan0_fck" },
+	{ AM4_D_CAN1_CLKCTRL, NULL, CLKF_SW_SUP, "dcan1_fck" },
+	{ AM4_EPWMSS0_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_EPWMSS1_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_EPWMSS2_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_EPWMSS3_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_EPWMSS4_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_EPWMSS5_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_ELM_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_GPIO2_CLKCTRL, am4_gpio2_bit_data, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_GPIO3_CLKCTRL, am4_gpio3_bit_data, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_GPIO4_CLKCTRL, am4_gpio4_bit_data, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_GPIO5_CLKCTRL, am4_gpio5_bit_data, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_GPIO6_CLKCTRL, am4_gpio6_bit_data, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_HDQ1W_CLKCTRL, NULL, CLKF_SW_SUP, "func_12m_clk" },
+	{ AM4_I2C2_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_I2C3_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_MAILBOX_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_MMC1_CLKCTRL, NULL, CLKF_SW_SUP, "mmc_clk" },
+	{ AM4_MMC2_CLKCTRL, NULL, CLKF_SW_SUP, "mmc_clk" },
+	{ AM4_RNG_CLKCTRL, NULL, CLKF_SW_SUP, "rng_fck" },
+	{ AM4_SPI0_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_SPI1_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_SPI2_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_SPI3_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_SPI4_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_SPINLOCK_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_TIMER2_CLKCTRL, NULL, CLKF_SW_SUP, "timer2_fck" },
+	{ AM4_TIMER3_CLKCTRL, NULL, CLKF_SW_SUP, "timer3_fck" },
+	{ AM4_TIMER4_CLKCTRL, NULL, CLKF_SW_SUP, "timer4_fck" },
+	{ AM4_TIMER5_CLKCTRL, NULL, CLKF_SW_SUP, "timer5_fck" },
+	{ AM4_TIMER6_CLKCTRL, NULL, CLKF_SW_SUP, "timer6_fck" },
+	{ AM4_TIMER7_CLKCTRL, NULL, CLKF_SW_SUP, "timer7_fck" },
+	{ AM4_TIMER8_CLKCTRL, NULL, CLKF_SW_SUP, "timer8_fck" },
+	{ AM4_TIMER9_CLKCTRL, NULL, CLKF_SW_SUP, "timer9_fck" },
+	{ AM4_TIMER10_CLKCTRL, NULL, CLKF_SW_SUP, "timer10_fck" },
+	{ AM4_TIMER11_CLKCTRL, NULL, CLKF_SW_SUP, "timer11_fck" },
+	{ AM4_UART2_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_UART3_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_UART4_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_UART5_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_UART6_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_per_m2_div4_ck" },
+	{ AM4_OCP2SCP0_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_OCP2SCP1_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" },
+	{ AM4_EMIF_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_ddr_m2_ck", "emif_clkdm" },
+	{ AM4_DSS_CORE_CLKCTRL, NULL, CLKF_SW_SUP, "disp_clk", "dss_clkdm" },
+	{ AM4_CPGMAC0_CLKCTRL, NULL, CLKF_SW_SUP, "cpsw_125mhz_gclk", "cpsw_125mhz_clkdm" },
+	{ 0 },
+};
+
+const struct omap_clkctrl_data am4_clkctrl_data[] __initconst = {
+	{ 0x44df2820, am4_l4_wkup_clkctrl_regs },
+	{ 0x44df8320, am4_mpu_clkctrl_regs },
+	{ 0x44df8420, am4_gfx_l3_clkctrl_regs },
+	{ 0x44df8520, am4_l4_rtc_clkctrl_regs },
+	{ 0x44df8820, am4_l4_per_clkctrl_regs },
+	{ 0 },
+};
+
+const struct omap_clkctrl_data am438x_clkctrl_data[] __initconst = {
+	{ 0x44df2820, am4_l4_wkup_clkctrl_regs },
+	{ 0x44df8320, am4_mpu_clkctrl_regs },
+	{ 0x44df8420, am4_gfx_l3_clkctrl_regs },
+	{ 0x44df8820, am4_l4_per_clkctrl_regs },
+	{ 0 },
+};
+
 static struct ti_dt_clk am43xx_clks[] = {
-	DT_CLK(NULL, "clk_32768_ck", "clk_32768_ck"),
-	DT_CLK(NULL, "clk_rc32k_ck", "clk_rc32k_ck"),
-	DT_CLK(NULL, "virt_19200000_ck", "virt_19200000_ck"),
-	DT_CLK(NULL, "virt_24000000_ck", "virt_24000000_ck"),
-	DT_CLK(NULL, "virt_25000000_ck", "virt_25000000_ck"),
-	DT_CLK(NULL, "virt_26000000_ck", "virt_26000000_ck"),
-	DT_CLK(NULL, "sys_clkin_ck", "sys_clkin_ck"),
-	DT_CLK(NULL, "tclkin_ck", "tclkin_ck"),
-	DT_CLK(NULL, "dpll_core_ck", "dpll_core_ck"),
-	DT_CLK(NULL, "dpll_core_x2_ck", "dpll_core_x2_ck"),
-	DT_CLK(NULL, "dpll_core_m4_ck", "dpll_core_m4_ck"),
-	DT_CLK(NULL, "dpll_core_m5_ck", "dpll_core_m5_ck"),
-	DT_CLK(NULL, "dpll_core_m6_ck", "dpll_core_m6_ck"),
-	DT_CLK(NULL, "dpll_mpu_ck", "dpll_mpu_ck"),
-	DT_CLK(NULL, "dpll_mpu_m2_ck", "dpll_mpu_m2_ck"),
-	DT_CLK(NULL, "dpll_ddr_ck", "dpll_ddr_ck"),
-	DT_CLK(NULL, "dpll_ddr_m2_ck", "dpll_ddr_m2_ck"),
-	DT_CLK(NULL, "dpll_disp_ck", "dpll_disp_ck"),
-	DT_CLK(NULL, "dpll_disp_m2_ck", "dpll_disp_m2_ck"),
-	DT_CLK(NULL, "dpll_per_ck", "dpll_per_ck"),
-	DT_CLK(NULL, "dpll_per_m2_ck", "dpll_per_m2_ck"),
-	DT_CLK(NULL, "dpll_per_m2_div4_wkupdm_ck", "dpll_per_m2_div4_wkupdm_ck"),
-	DT_CLK(NULL, "dpll_per_m2_div4_ck", "dpll_per_m2_div4_ck"),
-	DT_CLK(NULL, "adc_tsc_fck", "adc_tsc_fck"),
-	DT_CLK(NULL, "clkdiv32k_ck", "clkdiv32k_ck"),
-	DT_CLK(NULL, "clkdiv32k_ick", "clkdiv32k_ick"),
-	DT_CLK(NULL, "dcan0_fck", "dcan0_fck"),
-	DT_CLK(NULL, "dcan1_fck", "dcan1_fck"),
-	DT_CLK(NULL, "pruss_ocp_gclk", "pruss_ocp_gclk"),
-	DT_CLK(NULL, "mcasp0_fck", "mcasp0_fck"),
-	DT_CLK(NULL, "mcasp1_fck", "mcasp1_fck"),
-	DT_CLK(NULL, "smartreflex0_fck", "smartreflex0_fck"),
-	DT_CLK(NULL, "smartreflex1_fck", "smartreflex1_fck"),
-	DT_CLK(NULL, "sha0_fck", "sha0_fck"),
-	DT_CLK(NULL, "aes0_fck", "aes0_fck"),
-	DT_CLK(NULL, "rng_fck", "rng_fck"),
-	DT_CLK(NULL, "timer1_fck", "timer1_fck"),
-	DT_CLK(NULL, "timer2_fck", "timer2_fck"),
-	DT_CLK(NULL, "timer3_fck", "timer3_fck"),
-	DT_CLK(NULL, "timer4_fck", "timer4_fck"),
-	DT_CLK(NULL, "timer5_fck", "timer5_fck"),
-	DT_CLK(NULL, "timer6_fck", "timer6_fck"),
-	DT_CLK(NULL, "timer7_fck", "timer7_fck"),
-	DT_CLK(NULL, "wdt1_fck", "wdt1_fck"),
-	DT_CLK(NULL, "l3_gclk", "l3_gclk"),
-	DT_CLK(NULL, "dpll_core_m4_div2_ck", "dpll_core_m4_div2_ck"),
-	DT_CLK(NULL, "l4hs_gclk", "l4hs_gclk"),
-	DT_CLK(NULL, "l3s_gclk", "l3s_gclk"),
-	DT_CLK(NULL, "l4ls_gclk", "l4ls_gclk"),
-	DT_CLK(NULL, "clk_24mhz", "clk_24mhz"),
-	DT_CLK(NULL, "cpsw_125mhz_gclk", "cpsw_125mhz_gclk"),
-	DT_CLK(NULL, "cpsw_cpts_rft_clk", "cpsw_cpts_rft_clk"),
-	DT_CLK(NULL, "dpll_clksel_mac_clk", "dpll_clksel_mac_clk"),
-	DT_CLK(NULL, "gpio0_dbclk_mux_ck", "gpio0_dbclk_mux_ck"),
-	DT_CLK(NULL, "gpio0_dbclk", "gpio0_dbclk"),
-	DT_CLK(NULL, "gpio1_dbclk", "gpio1_dbclk"),
-	DT_CLK(NULL, "gpio2_dbclk", "gpio2_dbclk"),
-	DT_CLK(NULL, "gpio3_dbclk", "gpio3_dbclk"),
-	DT_CLK(NULL, "gpio4_dbclk", "gpio4_dbclk"),
-	DT_CLK(NULL, "gpio5_dbclk", "gpio5_dbclk"),
-	DT_CLK(NULL, "mmc_clk", "mmc_clk"),
-	DT_CLK(NULL, "gfx_fclk_clksel_ck", "gfx_fclk_clksel_ck"),
-	DT_CLK(NULL, "gfx_fck_div_ck", "gfx_fck_div_ck"),
 	DT_CLK(NULL, "timer_32k_ck", "clkdiv32k_ick"),
 	DT_CLK(NULL, "timer_sys_ck", "sys_clkin_ck"),
-	DT_CLK(NULL, "sysclk_div", "sysclk_div"),
-	DT_CLK(NULL, "disp_clk", "disp_clk"),
-	DT_CLK(NULL, "clk_32k_mosc_ck", "clk_32k_mosc_ck"),
-	DT_CLK(NULL, "clk_32k_tpm_ck", "clk_32k_tpm_ck"),
-	DT_CLK(NULL, "dpll_extdev_ck", "dpll_extdev_ck"),
-	DT_CLK(NULL, "dpll_extdev_m2_ck", "dpll_extdev_m2_ck"),
-	DT_CLK(NULL, "mux_synctimer32k_ck", "mux_synctimer32k_ck"),
-	DT_CLK(NULL, "synctimer_32kclk", "synctimer_32kclk"),
-	DT_CLK(NULL, "timer8_fck", "timer8_fck"),
-	DT_CLK(NULL, "timer9_fck", "timer9_fck"),
-	DT_CLK(NULL, "timer10_fck", "timer10_fck"),
-	DT_CLK(NULL, "timer11_fck", "timer11_fck"),
-	DT_CLK(NULL, "cpsw_50m_clkdiv", "cpsw_50m_clkdiv"),
-	DT_CLK(NULL, "cpsw_5m_clkdiv", "cpsw_5m_clkdiv"),
-	DT_CLK(NULL, "dpll_ddr_x2_ck", "dpll_ddr_x2_ck"),
-	DT_CLK(NULL, "dpll_ddr_m4_ck", "dpll_ddr_m4_ck"),
-	DT_CLK(NULL, "dpll_per_clkdcoldo", "dpll_per_clkdcoldo"),
-	DT_CLK(NULL, "dll_aging_clk_div", "dll_aging_clk_div"),
-	DT_CLK(NULL, "div_core_25m_ck", "div_core_25m_ck"),
-	DT_CLK(NULL, "func_12m_clk", "func_12m_clk"),
-	DT_CLK(NULL, "vtp_clk_div", "vtp_clk_div"),
-	DT_CLK(NULL, "usbphy_32khz_clkmux", "usbphy_32khz_clkmux"),
-	DT_CLK("48300200.ehrpwm", "tbclk", "ehrpwm0_tbclk"),
-	DT_CLK("48302200.ehrpwm", "tbclk", "ehrpwm1_tbclk"),
-	DT_CLK("48304200.ehrpwm", "tbclk", "ehrpwm2_tbclk"),
-	DT_CLK("48306200.ehrpwm", "tbclk", "ehrpwm3_tbclk"),
-	DT_CLK("48308200.ehrpwm", "tbclk", "ehrpwm4_tbclk"),
-	DT_CLK("4830a200.ehrpwm", "tbclk", "ehrpwm5_tbclk"),
-	DT_CLK("48300200.pwm", "tbclk", "ehrpwm0_tbclk"),
-	DT_CLK("48302200.pwm", "tbclk", "ehrpwm1_tbclk"),
-	DT_CLK("48304200.pwm", "tbclk", "ehrpwm2_tbclk"),
-	DT_CLK("48306200.pwm", "tbclk", "ehrpwm3_tbclk"),
-	DT_CLK("48308200.pwm", "tbclk", "ehrpwm4_tbclk"),
-	DT_CLK("4830a200.pwm", "tbclk", "ehrpwm5_tbclk"),
+	DT_CLK(NULL, "gpio0_dbclk", "l4_wkup_cm:0348:8"),
+	DT_CLK(NULL, "gpio1_dbclk", "l4_per_cm:0458:8"),
+	DT_CLK(NULL, "gpio2_dbclk", "l4_per_cm:0460:8"),
+	DT_CLK(NULL, "gpio3_dbclk", "l4_per_cm:0468:8"),
+	DT_CLK(NULL, "gpio4_dbclk", "l4_per_cm:0470:8"),
+	DT_CLK(NULL, "gpio5_dbclk", "l4_per_cm:0478:8"),
+	DT_CLK(NULL, "synctimer_32kclk", "l4_wkup_cm:0210:8"),
+	DT_CLK(NULL, "usb_otg_ss0_refclk960m", "l4_per_cm:0240:8"),
+	DT_CLK(NULL, "usb_otg_ss1_refclk960m", "l4_per_cm:0248:8"),
 	{ .node_name = NULL },
 };
 
@@ -133,6 +232,8 @@ int __init am43xx_dt_clk_init(void)
 
 	omap2_clk_disable_autoidle_all();
 
+	ti_clk_add_aliases();
+
 	/*
 	 * cpsw_cpts_rft_clk  has got the choice of 3 clocksources
 	 * dpll_core_m4_ck, dpll_core_m5_ck and dpll_disp_m2_ck.
diff --git a/drivers/clk/ti/clk-44xx.c b/drivers/clk/ti/clk-44xx.c
index 2005f032c02f..339d30d64ebb 100644
--- a/drivers/clk/ti/clk-44xx.c
+++ b/drivers/clk/ti/clk-44xx.c
@@ -35,7 +35,7 @@
 #define OMAP4_DPLL_USB_DEFFREQ				960000000
 
 static const struct omap_clkctrl_reg_data omap4_mpuss_clkctrl_regs[] __initconst = {
-	{ OMAP4_MPU_CLKCTRL, NULL, CLKF_HW_SUP, "dpll_mpu_m2_ck" },
+	{ OMAP4_MPU_CLKCTRL, NULL, 0, "dpll_mpu_m2_ck" },
 	{ 0 },
 };
 
@@ -59,7 +59,7 @@ static const struct omap_clkctrl_bit_data omap4_aess_bit_data[] __initconst = {
 };
 
 static const char * const omap4_func_dmic_abe_gfclk_parents[] __initconst = {
-	"dmic_sync_mux_ck",
+	"abe_cm:clk:0018:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -79,7 +79,7 @@ static const struct omap_clkctrl_bit_data omap4_dmic_bit_data[] __initconst = {
 };
 
 static const char * const omap4_func_mcasp_abe_gfclk_parents[] __initconst = {
-	"mcasp_sync_mux_ck",
+	"abe_cm:clk:0020:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -92,7 +92,7 @@ static const struct omap_clkctrl_bit_data omap4_mcasp_bit_data[] __initconst = {
 };
 
 static const char * const omap4_func_mcbsp1_gfclk_parents[] __initconst = {
-	"mcbsp1_sync_mux_ck",
+	"abe_cm:clk:0028:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -105,7 +105,7 @@ static const struct omap_clkctrl_bit_data omap4_mcbsp1_bit_data[] __initconst =
 };
 
 static const char * const omap4_func_mcbsp2_gfclk_parents[] __initconst = {
-	"mcbsp2_sync_mux_ck",
+	"abe_cm:clk:0030:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -118,7 +118,7 @@ static const struct omap_clkctrl_bit_data omap4_mcbsp2_bit_data[] __initconst =
 };
 
 static const char * const omap4_func_mcbsp3_gfclk_parents[] __initconst = {
-	"mcbsp3_sync_mux_ck",
+	"abe_cm:clk:0038:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -186,18 +186,18 @@ static const struct omap_clkctrl_bit_data omap4_timer8_bit_data[] __initconst =
 
 static const struct omap_clkctrl_reg_data omap4_abe_clkctrl_regs[] __initconst = {
 	{ OMAP4_L4_ABE_CLKCTRL, NULL, 0, "ocp_abe_iclk" },
-	{ OMAP4_AESS_CLKCTRL, omap4_aess_bit_data, CLKF_SW_SUP, "aess_fclk" },
+	{ OMAP4_AESS_CLKCTRL, omap4_aess_bit_data, CLKF_SW_SUP, "abe_cm:clk:0008:24" },
 	{ OMAP4_MCPDM_CLKCTRL, NULL, CLKF_SW_SUP, "pad_clks_ck" },
-	{ OMAP4_DMIC_CLKCTRL, omap4_dmic_bit_data, CLKF_SW_SUP, "func_dmic_abe_gfclk" },
-	{ OMAP4_MCASP_CLKCTRL, omap4_mcasp_bit_data, CLKF_SW_SUP, "func_mcasp_abe_gfclk" },
-	{ OMAP4_MCBSP1_CLKCTRL, omap4_mcbsp1_bit_data, CLKF_SW_SUP, "func_mcbsp1_gfclk" },
-	{ OMAP4_MCBSP2_CLKCTRL, omap4_mcbsp2_bit_data, CLKF_SW_SUP, "func_mcbsp2_gfclk" },
-	{ OMAP4_MCBSP3_CLKCTRL, omap4_mcbsp3_bit_data, CLKF_SW_SUP, "func_mcbsp3_gfclk" },
-	{ OMAP4_SLIMBUS1_CLKCTRL, omap4_slimbus1_bit_data, CLKF_SW_SUP, "slimbus1_fclk_0" },
-	{ OMAP4_TIMER5_CLKCTRL, omap4_timer5_bit_data, CLKF_SW_SUP, "timer5_sync_mux" },
-	{ OMAP4_TIMER6_CLKCTRL, omap4_timer6_bit_data, CLKF_SW_SUP, "timer6_sync_mux" },
-	{ OMAP4_TIMER7_CLKCTRL, omap4_timer7_bit_data, CLKF_SW_SUP, "timer7_sync_mux" },
-	{ OMAP4_TIMER8_CLKCTRL, omap4_timer8_bit_data, CLKF_SW_SUP, "timer8_sync_mux" },
+	{ OMAP4_DMIC_CLKCTRL, omap4_dmic_bit_data, CLKF_SW_SUP, "abe_cm:clk:0018:24" },
+	{ OMAP4_MCASP_CLKCTRL, omap4_mcasp_bit_data, CLKF_SW_SUP, "abe_cm:clk:0020:24" },
+	{ OMAP4_MCBSP1_CLKCTRL, omap4_mcbsp1_bit_data, CLKF_SW_SUP, "abe_cm:clk:0028:24" },
+	{ OMAP4_MCBSP2_CLKCTRL, omap4_mcbsp2_bit_data, CLKF_SW_SUP, "abe_cm:clk:0030:24" },
+	{ OMAP4_MCBSP3_CLKCTRL, omap4_mcbsp3_bit_data, CLKF_SW_SUP, "abe_cm:clk:0038:24" },
+	{ OMAP4_SLIMBUS1_CLKCTRL, omap4_slimbus1_bit_data, CLKF_SW_SUP, "abe_cm:clk:0040:8" },
+	{ OMAP4_TIMER5_CLKCTRL, omap4_timer5_bit_data, CLKF_SW_SUP, "abe_cm:clk:0048:24" },
+	{ OMAP4_TIMER6_CLKCTRL, omap4_timer6_bit_data, CLKF_SW_SUP, "abe_cm:clk:0050:24" },
+	{ OMAP4_TIMER7_CLKCTRL, omap4_timer7_bit_data, CLKF_SW_SUP, "abe_cm:clk:0058:24" },
+	{ OMAP4_TIMER8_CLKCTRL, omap4_timer8_bit_data, CLKF_SW_SUP, "abe_cm:clk:0060:24" },
 	{ OMAP4_WD_TIMER3_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
 	{ 0 },
 };
@@ -280,6 +280,7 @@ static const char * const omap4_fdif_fck_parents[] __initconst = {
 
 static const struct omap_clkctrl_div_data omap4_fdif_fck_data __initconst = {
 	.max_div = 4,
+	.flags = CLK_DIVIDER_POWER_OF_TWO,
 };
 
 static const struct omap_clkctrl_bit_data omap4_fdif_bit_data[] __initconst = {
@@ -289,7 +290,7 @@ static const struct omap_clkctrl_bit_data omap4_fdif_bit_data[] __initconst = {
 
 static const struct omap_clkctrl_reg_data omap4_iss_clkctrl_regs[] __initconst = {
 	{ OMAP4_ISS_CLKCTRL, omap4_iss_bit_data, CLKF_SW_SUP, "ducati_clk_mux_ck" },
-	{ OMAP4_FDIF_CLKCTRL, omap4_fdif_bit_data, CLKF_SW_SUP, "fdif_fck" },
+	{ OMAP4_FDIF_CLKCTRL, omap4_fdif_bit_data, CLKF_SW_SUP, "iss_cm:clk:0008:24" },
 	{ 0 },
 };
 
@@ -322,7 +323,7 @@ static const struct omap_clkctrl_bit_data omap4_dss_core_bit_data[] __initconst
 };
 
 static const struct omap_clkctrl_reg_data omap4_l3_dss_clkctrl_regs[] __initconst = {
-	{ OMAP4_DSS_CORE_CLKCTRL, omap4_dss_core_bit_data, CLKF_SW_SUP, "dss_dss_clk" },
+	{ OMAP4_DSS_CORE_CLKCTRL, omap4_dss_core_bit_data, CLKF_SW_SUP, "l3_dss_cm:clk:0000:8" },
 	{ 0 },
 };
 
@@ -338,7 +339,7 @@ static const struct omap_clkctrl_bit_data omap4_gpu_bit_data[] __initconst = {
 };
 
 static const struct omap_clkctrl_reg_data omap4_l3_gfx_clkctrl_regs[] __initconst = {
-	{ OMAP4_GPU_CLKCTRL, omap4_gpu_bit_data, CLKF_SW_SUP, "sgx_clk_mux" },
+	{ OMAP4_GPU_CLKCTRL, omap4_gpu_bit_data, CLKF_SW_SUP, "l3_gfx_cm:clk:0000:24" },
 	{ 0 },
 };
 
@@ -365,6 +366,7 @@ static const char * const omap4_hsi_fck_parents[] __initconst = {
 
 static const struct omap_clkctrl_div_data omap4_hsi_fck_data __initconst = {
 	.max_div = 4,
+	.flags = CLK_DIVIDER_POWER_OF_TWO,
 };
 
 static const struct omap_clkctrl_bit_data omap4_hsi_bit_data[] __initconst = {
@@ -373,12 +375,12 @@ static const struct omap_clkctrl_bit_data omap4_hsi_bit_data[] __initconst = {
 };
 
 static const char * const omap4_usb_host_hs_utmi_p1_clk_parents[] __initconst = {
-	"utmi_p1_gfclk",
+	"l3_init_cm:clk:0038:24",
 	NULL,
 };
 
 static const char * const omap4_usb_host_hs_utmi_p2_clk_parents[] __initconst = {
-	"utmi_p2_gfclk",
+	"l3_init_cm:clk:0038:25",
 	NULL,
 };
 
@@ -419,7 +421,7 @@ static const struct omap_clkctrl_bit_data omap4_usb_host_hs_bit_data[] __initcon
 };
 
 static const char * const omap4_usb_otg_hs_xclk_parents[] __initconst = {
-	"otg_60m_gfclk",
+	"l3_init_cm:clk:0040:24",
 	NULL,
 };
 
@@ -453,14 +455,14 @@ static const struct omap_clkctrl_bit_data omap4_ocp2scp_usb_phy_bit_data[] __ini
 };
 
 static const struct omap_clkctrl_reg_data omap4_l3_init_clkctrl_regs[] __initconst = {
-	{ OMAP4_MMC1_CLKCTRL, omap4_mmc1_bit_data, CLKF_SW_SUP, "hsmmc1_fclk" },
-	{ OMAP4_MMC2_CLKCTRL, omap4_mmc2_bit_data, CLKF_SW_SUP, "hsmmc2_fclk" },
-	{ OMAP4_HSI_CLKCTRL, omap4_hsi_bit_data, CLKF_HW_SUP, "hsi_fck" },
+	{ OMAP4_MMC1_CLKCTRL, omap4_mmc1_bit_data, CLKF_SW_SUP, "l3_init_cm:clk:0008:24" },
+	{ OMAP4_MMC2_CLKCTRL, omap4_mmc2_bit_data, CLKF_SW_SUP, "l3_init_cm:clk:0010:24" },
+	{ OMAP4_HSI_CLKCTRL, omap4_hsi_bit_data, CLKF_HW_SUP, "l3_init_cm:clk:0018:24" },
 	{ OMAP4_USB_HOST_HS_CLKCTRL, omap4_usb_host_hs_bit_data, CLKF_SW_SUP, "init_60m_fclk" },
 	{ OMAP4_USB_OTG_HS_CLKCTRL, omap4_usb_otg_hs_bit_data, CLKF_HW_SUP, "l3_div_ck" },
 	{ OMAP4_USB_TLL_HS_CLKCTRL, omap4_usb_tll_hs_bit_data, CLKF_HW_SUP, "l4_div_ck" },
 	{ OMAP4_USB_HOST_FS_CLKCTRL, NULL, CLKF_SW_SUP, "func_48mc_fclk" },
-	{ OMAP4_OCP2SCP_USB_PHY_CLKCTRL, omap4_ocp2scp_usb_phy_bit_data, CLKF_HW_SUP, "ocp2scp_usb_phy_phy_48m" },
+	{ OMAP4_OCP2SCP_USB_PHY_CLKCTRL, omap4_ocp2scp_usb_phy_bit_data, CLKF_HW_SUP, "l3_init_cm:clk:00c0:8" },
 	{ 0 },
 };
 
@@ -531,7 +533,7 @@ static const struct omap_clkctrl_bit_data omap4_gpio6_bit_data[] __initconst = {
 };
 
 static const char * const omap4_per_mcbsp4_gfclk_parents[] __initconst = {
-	"mcbsp4_sync_mux_ck",
+	"l4_per_cm:clk:00c0:26",
 	"pad_clks_ck",
 	NULL,
 };
@@ -544,7 +546,7 @@ static const char * const omap4_mcbsp4_sync_mux_ck_parents[] __initconst = {
 
 static const struct omap_clkctrl_bit_data omap4_mcbsp4_bit_data[] __initconst = {
 	{ 24, TI_CLK_MUX, omap4_per_mcbsp4_gfclk_parents, NULL },
-	{ 25, TI_CLK_MUX, omap4_mcbsp4_sync_mux_ck_parents, NULL },
+	{ 26, TI_CLK_MUX, omap4_mcbsp4_sync_mux_ck_parents, NULL },
 	{ 0 },
 };
 
@@ -571,12 +573,12 @@ static const struct omap_clkctrl_bit_data omap4_slimbus2_bit_data[] __initconst
 };
 
 static const struct omap_clkctrl_reg_data omap4_l4_per_clkctrl_regs[] __initconst = {
-	{ OMAP4_TIMER10_CLKCTRL, omap4_timer10_bit_data, CLKF_SW_SUP, "cm2_dm10_mux" },
-	{ OMAP4_TIMER11_CLKCTRL, omap4_timer11_bit_data, CLKF_SW_SUP, "cm2_dm11_mux" },
-	{ OMAP4_TIMER2_CLKCTRL, omap4_timer2_bit_data, CLKF_SW_SUP, "cm2_dm2_mux" },
-	{ OMAP4_TIMER3_CLKCTRL, omap4_timer3_bit_data, CLKF_SW_SUP, "cm2_dm3_mux" },
-	{ OMAP4_TIMER4_CLKCTRL, omap4_timer4_bit_data, CLKF_SW_SUP, "cm2_dm4_mux" },
-	{ OMAP4_TIMER9_CLKCTRL, omap4_timer9_bit_data, CLKF_SW_SUP, "cm2_dm9_mux" },
+	{ OMAP4_TIMER10_CLKCTRL, omap4_timer10_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0008:24" },
+	{ OMAP4_TIMER11_CLKCTRL, omap4_timer11_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0010:24" },
+	{ OMAP4_TIMER2_CLKCTRL, omap4_timer2_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0018:24" },
+	{ OMAP4_TIMER3_CLKCTRL, omap4_timer3_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0020:24" },
+	{ OMAP4_TIMER4_CLKCTRL, omap4_timer4_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0028:24" },
+	{ OMAP4_TIMER9_CLKCTRL, omap4_timer9_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0030:24" },
 	{ OMAP4_ELM_CLKCTRL, NULL, 0, "l4_div_ck" },
 	{ OMAP4_GPIO2_CLKCTRL, omap4_gpio2_bit_data, CLKF_HW_SUP, "l4_div_ck" },
 	{ OMAP4_GPIO3_CLKCTRL, omap4_gpio3_bit_data, CLKF_HW_SUP, "l4_div_ck" },
@@ -589,14 +591,14 @@ static const struct omap_clkctrl_reg_data omap4_l4_per_clkctrl_regs[] __initcons
 	{ OMAP4_I2C3_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
 	{ OMAP4_I2C4_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
 	{ OMAP4_L4_PER_CLKCTRL, NULL, 0, "l4_div_ck" },
-	{ OMAP4_MCBSP4_CLKCTRL, omap4_mcbsp4_bit_data, CLKF_SW_SUP, "per_mcbsp4_gfclk" },
+	{ OMAP4_MCBSP4_CLKCTRL, omap4_mcbsp4_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:00c0:24" },
 	{ OMAP4_MCSPI1_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_MCSPI2_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_MCSPI3_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_MCSPI4_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_MMC3_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_MMC4_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
-	{ OMAP4_SLIMBUS2_CLKCTRL, omap4_slimbus2_bit_data, CLKF_SW_SUP, "slimbus2_fclk_0" },
+	{ OMAP4_SLIMBUS2_CLKCTRL, omap4_slimbus2_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0118:8" },
 	{ OMAP4_UART1_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_UART2_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_UART3_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
@@ -619,7 +621,7 @@ static const struct omap_clkctrl_reg_data omap4_l4_wkup_clkctrl_regs[] __initcon
 	{ OMAP4_L4_WKUP_CLKCTRL, NULL, 0, "l4_wkup_clk_mux_ck" },
 	{ OMAP4_WD_TIMER2_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
 	{ OMAP4_GPIO1_CLKCTRL, omap4_gpio1_bit_data, CLKF_HW_SUP, "l4_wkup_clk_mux_ck" },
-	{ OMAP4_TIMER1_CLKCTRL, omap4_timer1_bit_data, CLKF_SW_SUP, "dmt1_clk_mux" },
+	{ OMAP4_TIMER1_CLKCTRL, omap4_timer1_bit_data, CLKF_SW_SUP, "l4_wkup_cm:clk:0020:24" },
 	{ OMAP4_COUNTER_32K_CLKCTRL, NULL, 0, "sys_32k_ck" },
 	{ OMAP4_KBD_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
 	{ 0 },
@@ -633,7 +635,7 @@ static const char * const omap4_pmd_stm_clock_mux_ck_parents[] __initconst = {
 };
 
 static const char * const omap4_trace_clk_div_div_ck_parents[] __initconst = {
-	"pmd_trace_clk_mux_ck",
+	"emu_sys_cm:clk:0000:22",
 	NULL,
 };
 
@@ -651,12 +653,13 @@ static const struct omap_clkctrl_div_data omap4_trace_clk_div_div_ck_data __init
 };
 
 static const char * const omap4_stm_clk_div_ck_parents[] __initconst = {
-	"pmd_stm_clock_mux_ck",
+	"emu_sys_cm:clk:0000:20",
 	NULL,
 };
 
 static const struct omap_clkctrl_div_data omap4_stm_clk_div_ck_data __initconst = {
 	.max_div = 64,
+	.flags = CLK_DIVIDER_POWER_OF_TWO,
 };
 
 static const struct omap_clkctrl_bit_data omap4_debugss_bit_data[] __initconst = {
@@ -697,52 +700,79 @@ const struct omap_clkctrl_data omap4_clkctrl_data[] __initconst = {
 };
 
 static struct ti_dt_clk omap44xx_clks[] = {
-	DT_CLK("smp_twd", NULL, "mpu_periphclk"),
-	DT_CLK("omapdss_dss", "ick", "dss_fck"),
-	DT_CLK("usbhs_omap", "fs_fck", "usb_host_fs_fck"),
-	DT_CLK("usbhs_omap", "hs_fck", "usb_host_hs_fck"),
-	DT_CLK("musb-omap2430", "ick", "usb_otg_hs_ick"),
-	DT_CLK("usbhs_omap", "usbtll_ick", "usb_tll_hs_ick"),
-	DT_CLK("usbhs_tll", "usbtll_ick", "usb_tll_hs_ick"),
-	DT_CLK("omap_i2c.1", "ick", "dummy_ck"),
-	DT_CLK("omap_i2c.2", "ick", "dummy_ck"),
-	DT_CLK("omap_i2c.3", "ick", "dummy_ck"),
-	DT_CLK("omap_i2c.4", "ick", "dummy_ck"),
-	DT_CLK(NULL, "mailboxes_ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.0", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.1", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.2", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.3", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.4", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.1", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.2", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.3", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.4", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.1", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.2", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.3", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.4", "ick", "dummy_ck"),
-	DT_CLK(NULL, "uart1_ick", "dummy_ck"),
-	DT_CLK(NULL, "uart2_ick", "dummy_ck"),
-	DT_CLK(NULL, "uart3_ick", "dummy_ck"),
-	DT_CLK(NULL, "uart4_ick", "dummy_ck"),
-	DT_CLK("usbhs_omap", "usbhost_ick", "dummy_ck"),
-	DT_CLK("usbhs_omap", "usbtll_fck", "dummy_ck"),
-	DT_CLK("usbhs_tll", "usbtll_fck", "dummy_ck"),
-	DT_CLK("omap_wdt", "ick", "dummy_ck"),
 	DT_CLK(NULL, "timer_32k_ck", "sys_32k_ck"),
-	DT_CLK("4a318000.timer", "timer_sys_ck", "sys_clkin_ck"),
-	DT_CLK("48032000.timer", "timer_sys_ck", "sys_clkin_ck"),
-	DT_CLK("48034000.timer", "timer_sys_ck", "sys_clkin_ck"),
-	DT_CLK("48036000.timer", "timer_sys_ck", "sys_clkin_ck"),
-	DT_CLK("4803e000.timer", "timer_sys_ck", "sys_clkin_ck"),
-	DT_CLK("48086000.timer", "timer_sys_ck", "sys_clkin_ck"),
-	DT_CLK("48088000.timer", "timer_sys_ck", "sys_clkin_ck"),
-	DT_CLK("40138000.timer", "timer_sys_ck", "syc_clk_div_ck"),
-	DT_CLK("4013a000.timer", "timer_sys_ck", "syc_clk_div_ck"),
-	DT_CLK("4013c000.timer", "timer_sys_ck", "syc_clk_div_ck"),
-	DT_CLK("4013e000.timer", "timer_sys_ck", "syc_clk_div_ck"),
-	DT_CLK(NULL, "cpufreq_ck", "dpll_mpu_ck"),
+	/*
+	 * XXX: All the clock aliases below are only needed for legacy
+	 * hwmod support. Once hwmod is removed, these can be removed
+	 * also.
+	 */
+	DT_CLK(NULL, "aess_fclk", "abe_cm:0008:24"),
+	DT_CLK(NULL, "cm2_dm10_mux", "l4_per_cm:0008:24"),
+	DT_CLK(NULL, "cm2_dm11_mux", "l4_per_cm:0010:24"),
+	DT_CLK(NULL, "cm2_dm2_mux", "l4_per_cm:0018:24"),
+	DT_CLK(NULL, "cm2_dm3_mux", "l4_per_cm:0020:24"),
+	DT_CLK(NULL, "cm2_dm4_mux", "l4_per_cm:0028:24"),
+	DT_CLK(NULL, "cm2_dm9_mux", "l4_per_cm:0030:24"),
+	DT_CLK(NULL, "dmic_sync_mux_ck", "abe_cm:0018:26"),
+	DT_CLK(NULL, "dmt1_clk_mux", "l4_wkup_cm:0020:24"),
+	DT_CLK(NULL, "dss_48mhz_clk", "l3_dss_cm:0000:9"),
+	DT_CLK(NULL, "dss_dss_clk", "l3_dss_cm:0000:8"),
+	DT_CLK(NULL, "dss_sys_clk", "l3_dss_cm:0000:10"),
+	DT_CLK(NULL, "dss_tv_clk", "l3_dss_cm:0000:11"),
+	DT_CLK(NULL, "fdif_fck", "iss_cm:0008:24"),
+	DT_CLK(NULL, "func_dmic_abe_gfclk", "abe_cm:0018:24"),
+	DT_CLK(NULL, "func_mcasp_abe_gfclk", "abe_cm:0020:24"),
+	DT_CLK(NULL, "func_mcbsp1_gfclk", "abe_cm:0028:24"),
+	DT_CLK(NULL, "func_mcbsp2_gfclk", "abe_cm:0030:24"),
+	DT_CLK(NULL, "func_mcbsp3_gfclk", "abe_cm:0038:24"),
+	DT_CLK(NULL, "gpio1_dbclk", "l4_wkup_cm:0018:8"),
+	DT_CLK(NULL, "gpio2_dbclk", "l4_per_cm:0040:8"),
+	DT_CLK(NULL, "gpio3_dbclk", "l4_per_cm:0048:8"),
+	DT_CLK(NULL, "gpio4_dbclk", "l4_per_cm:0050:8"),
+	DT_CLK(NULL, "gpio5_dbclk", "l4_per_cm:0058:8"),
+	DT_CLK(NULL, "gpio6_dbclk", "l4_per_cm:0060:8"),
+	DT_CLK(NULL, "hsi_fck", "l3_init_cm:0018:24"),
+	DT_CLK(NULL, "hsmmc1_fclk", "l3_init_cm:0008:24"),
+	DT_CLK(NULL, "hsmmc2_fclk", "l3_init_cm:0010:24"),
+	DT_CLK(NULL, "iss_ctrlclk", "iss_cm:0000:8"),
+	DT_CLK(NULL, "mcasp_sync_mux_ck", "abe_cm:0020:26"),
+	DT_CLK(NULL, "mcbsp1_sync_mux_ck", "abe_cm:0028:26"),
+	DT_CLK(NULL, "mcbsp2_sync_mux_ck", "abe_cm:0030:26"),
+	DT_CLK(NULL, "mcbsp3_sync_mux_ck", "abe_cm:0038:26"),
+	DT_CLK(NULL, "mcbsp4_sync_mux_ck", "l4_per_cm:00c0:26"),
+	DT_CLK(NULL, "ocp2scp_usb_phy_phy_48m", "l3_init_cm:00c0:8"),
+	DT_CLK(NULL, "otg_60m_gfclk", "l3_init_cm:0040:24"),
+	DT_CLK(NULL, "per_mcbsp4_gfclk", "l4_per_cm:00c0:24"),
+	DT_CLK(NULL, "pmd_stm_clock_mux_ck", "emu_sys_cm:0000:20"),
+	DT_CLK(NULL, "pmd_trace_clk_mux_ck", "emu_sys_cm:0000:22"),
+	DT_CLK(NULL, "sgx_clk_mux", "l3_gfx_cm:0000:24"),
+	DT_CLK(NULL, "slimbus1_fclk_0", "abe_cm:0040:8"),
+	DT_CLK(NULL, "slimbus1_fclk_1", "abe_cm:0040:9"),
+	DT_CLK(NULL, "slimbus1_fclk_2", "abe_cm:0040:10"),
+	DT_CLK(NULL, "slimbus1_slimbus_clk", "abe_cm:0040:11"),
+	DT_CLK(NULL, "slimbus2_fclk_0", "l4_per_cm:0118:8"),
+	DT_CLK(NULL, "slimbus2_fclk_1", "l4_per_cm:0118:9"),
+	DT_CLK(NULL, "slimbus2_slimbus_clk", "l4_per_cm:0118:10"),
+	DT_CLK(NULL, "stm_clk_div_ck", "emu_sys_cm:0000:27"),
+	DT_CLK(NULL, "timer5_sync_mux", "abe_cm:0048:24"),
+	DT_CLK(NULL, "timer6_sync_mux", "abe_cm:0050:24"),
+	DT_CLK(NULL, "timer7_sync_mux", "abe_cm:0058:24"),
+	DT_CLK(NULL, "timer8_sync_mux", "abe_cm:0060:24"),
+	DT_CLK(NULL, "trace_clk_div_div_ck", "emu_sys_cm:0000:24"),
+	DT_CLK(NULL, "usb_host_hs_func48mclk", "l3_init_cm:0038:15"),
+	DT_CLK(NULL, "usb_host_hs_hsic480m_p1_clk", "l3_init_cm:0038:13"),
+	DT_CLK(NULL, "usb_host_hs_hsic480m_p2_clk", "l3_init_cm:0038:14"),
+	DT_CLK(NULL, "usb_host_hs_hsic60m_p1_clk", "l3_init_cm:0038:11"),
+	DT_CLK(NULL, "usb_host_hs_hsic60m_p2_clk", "l3_init_cm:0038:12"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p1_clk", "l3_init_cm:0038:8"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p2_clk", "l3_init_cm:0038:9"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p3_clk", "l3_init_cm:0038:10"),
+	DT_CLK(NULL, "usb_otg_hs_xclk", "l3_init_cm:0040:8"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch0_clk", "l3_init_cm:0048:8"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch1_clk", "l3_init_cm:0048:9"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch2_clk", "l3_init_cm:0048:10"),
+	DT_CLK(NULL, "utmi_p1_gfclk", "l3_init_cm:0038:24"),
+	DT_CLK(NULL, "utmi_p2_gfclk", "l3_init_cm:0038:25"),
 	{ .node_name = NULL },
 };
 
diff --git a/drivers/clk/ti/clk-54xx.c b/drivers/clk/ti/clk-54xx.c
index 294bc03ec067..a17b0c4646a1 100644
--- a/drivers/clk/ti/clk-54xx.c
+++ b/drivers/clk/ti/clk-54xx.c
@@ -16,6 +16,7 @@
 #include <linux/clkdev.h>
 #include <linux/io.h>
 #include <linux/clk/ti.h>
+#include <dt-bindings/clock/omap5.h>
 
 #include "clock.h"
 
@@ -27,201 +28,511 @@
  */
 #define OMAP5_DPLL_USB_DEFFREQ				960000000
 
+static const struct omap_clkctrl_reg_data omap5_mpu_clkctrl_regs[] __initconst = {
+	{ OMAP5_MPU_CLKCTRL, NULL, 0, "dpll_mpu_m2_ck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_dsp_clkctrl_regs[] __initconst = {
+	{ OMAP5_MMU_DSP_CLKCTRL, NULL, CLKF_HW_SUP, "dpll_iva_h11x2_ck" },
+	{ 0 },
+};
+
+static const char * const omap5_dmic_gfclk_parents[] __initconst = {
+	"abe_cm:clk:0018:26",
+	"pad_clks_ck",
+	"slimbus_clk",
+	NULL,
+};
+
+static const char * const omap5_dmic_sync_mux_ck_parents[] __initconst = {
+	"abe_24m_fclk",
+	"dss_syc_gfclk_div",
+	"func_24m_clk",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data omap5_dmic_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_dmic_gfclk_parents, NULL },
+	{ 26, TI_CLK_MUX, omap5_dmic_sync_mux_ck_parents, NULL },
+	{ 0 },
+};
+
+static const char * const omap5_mcbsp1_gfclk_parents[] __initconst = {
+	"abe_cm:clk:0028:26",
+	"pad_clks_ck",
+	"slimbus_clk",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data omap5_mcbsp1_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_mcbsp1_gfclk_parents, NULL },
+	{ 26, TI_CLK_MUX, omap5_dmic_sync_mux_ck_parents, NULL },
+	{ 0 },
+};
+
+static const char * const omap5_mcbsp2_gfclk_parents[] __initconst = {
+	"abe_cm:clk:0030:26",
+	"pad_clks_ck",
+	"slimbus_clk",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data omap5_mcbsp2_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_mcbsp2_gfclk_parents, NULL },
+	{ 26, TI_CLK_MUX, omap5_dmic_sync_mux_ck_parents, NULL },
+	{ 0 },
+};
+
+static const char * const omap5_mcbsp3_gfclk_parents[] __initconst = {
+	"abe_cm:clk:0038:26",
+	"pad_clks_ck",
+	"slimbus_clk",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data omap5_mcbsp3_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_mcbsp3_gfclk_parents, NULL },
+	{ 26, TI_CLK_MUX, omap5_dmic_sync_mux_ck_parents, NULL },
+	{ 0 },
+};
+
+static const char * const omap5_timer5_gfclk_mux_parents[] __initconst = {
+	"dss_syc_gfclk_div",
+	"sys_32k_ck",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data omap5_timer5_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_timer5_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_timer6_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_timer5_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_timer7_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_timer5_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_timer8_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_timer5_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_abe_clkctrl_regs[] __initconst = {
+	{ OMAP5_L4_ABE_CLKCTRL, NULL, 0, "abe_iclk" },
+	{ OMAP5_MCPDM_CLKCTRL, NULL, CLKF_SW_SUP, "pad_clks_ck" },
+	{ OMAP5_DMIC_CLKCTRL, omap5_dmic_bit_data, CLKF_SW_SUP, "abe_cm:clk:0018:24" },
+	{ OMAP5_MCBSP1_CLKCTRL, omap5_mcbsp1_bit_data, CLKF_SW_SUP, "abe_cm:clk:0028:24" },
+	{ OMAP5_MCBSP2_CLKCTRL, omap5_mcbsp2_bit_data, CLKF_SW_SUP, "abe_cm:clk:0030:24" },
+	{ OMAP5_MCBSP3_CLKCTRL, omap5_mcbsp3_bit_data, CLKF_SW_SUP, "abe_cm:clk:0038:24" },
+	{ OMAP5_TIMER5_CLKCTRL, omap5_timer5_bit_data, CLKF_SW_SUP, "abe_cm:clk:0048:24" },
+	{ OMAP5_TIMER6_CLKCTRL, omap5_timer6_bit_data, CLKF_SW_SUP, "abe_cm:clk:0050:24" },
+	{ OMAP5_TIMER7_CLKCTRL, omap5_timer7_bit_data, CLKF_SW_SUP, "abe_cm:clk:0058:24" },
+	{ OMAP5_TIMER8_CLKCTRL, omap5_timer8_bit_data, CLKF_SW_SUP, "abe_cm:clk:0060:24" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_l3main1_clkctrl_regs[] __initconst = {
+	{ OMAP5_L3_MAIN_1_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_l3main2_clkctrl_regs[] __initconst = {
+	{ OMAP5_L3_MAIN_2_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_ipu_clkctrl_regs[] __initconst = {
+	{ OMAP5_MMU_IPU_CLKCTRL, NULL, CLKF_HW_SUP, "dpll_core_h22x2_ck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_dma_clkctrl_regs[] __initconst = {
+	{ OMAP5_DMA_SYSTEM_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_emif_clkctrl_regs[] __initconst = {
+	{ OMAP5_DMM_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ OMAP5_EMIF1_CLKCTRL, NULL, CLKF_HW_SUP, "dpll_core_h11x2_ck" },
+	{ OMAP5_EMIF2_CLKCTRL, NULL, CLKF_HW_SUP, "dpll_core_h11x2_ck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_l4cfg_clkctrl_regs[] __initconst = {
+	{ OMAP5_L4_CFG_CLKCTRL, NULL, 0, "l4_root_clk_div" },
+	{ OMAP5_SPINLOCK_CLKCTRL, NULL, 0, "l4_root_clk_div" },
+	{ OMAP5_MAILBOX_CLKCTRL, NULL, 0, "l4_root_clk_div" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_l3instr_clkctrl_regs[] __initconst = {
+	{ OMAP5_L3_MAIN_3_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div" },
+	{ OMAP5_L3_INSTR_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div" },
+	{ 0 },
+};
+
+static const char * const omap5_timer10_gfclk_mux_parents[] __initconst = {
+	"sys_clkin",
+	"sys_32k_ck",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data omap5_timer10_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_timer11_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_timer2_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_timer3_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_timer4_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_timer9_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const char * const omap5_gpio2_dbclk_parents[] __initconst = {
+	"sys_32k_ck",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data omap5_gpio2_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_gpio2_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_gpio3_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_gpio2_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_gpio4_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_gpio2_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_gpio5_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_gpio2_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_gpio6_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_gpio2_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_gpio7_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_gpio2_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_gpio8_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_gpio2_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_l4per_clkctrl_regs[] __initconst = {
+	{ OMAP5_TIMER10_CLKCTRL, omap5_timer10_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0008:24" },
+	{ OMAP5_TIMER11_CLKCTRL, omap5_timer11_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0010:24" },
+	{ OMAP5_TIMER2_CLKCTRL, omap5_timer2_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0018:24" },
+	{ OMAP5_TIMER3_CLKCTRL, omap5_timer3_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0020:24" },
+	{ OMAP5_TIMER4_CLKCTRL, omap5_timer4_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0028:24" },
+	{ OMAP5_TIMER9_CLKCTRL, omap5_timer9_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0030:24" },
+	{ OMAP5_GPIO2_CLKCTRL, omap5_gpio2_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ OMAP5_GPIO3_CLKCTRL, omap5_gpio3_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ OMAP5_GPIO4_CLKCTRL, omap5_gpio4_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ OMAP5_GPIO5_CLKCTRL, omap5_gpio5_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ OMAP5_GPIO6_CLKCTRL, omap5_gpio6_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ OMAP5_I2C1_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
+	{ OMAP5_I2C2_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
+	{ OMAP5_I2C3_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
+	{ OMAP5_I2C4_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
+	{ OMAP5_L4_PER_CLKCTRL, NULL, 0, "l4_root_clk_div" },
+	{ OMAP5_MCSPI1_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_MCSPI2_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_MCSPI3_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_MCSPI4_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_GPIO7_CLKCTRL, omap5_gpio7_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ OMAP5_GPIO8_CLKCTRL, omap5_gpio8_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ OMAP5_MMC3_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_MMC4_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_UART1_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_UART2_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_UART3_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_UART4_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_MMC5_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
+	{ OMAP5_I2C5_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
+	{ OMAP5_UART5_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_UART6_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ 0 },
+};
+
+static const char * const omap5_dss_dss_clk_parents[] __initconst = {
+	"dpll_per_h12x2_ck",
+	NULL,
+};
+
+static const char * const omap5_dss_48mhz_clk_parents[] __initconst = {
+	"func_48m_fclk",
+	NULL,
+};
+
+static const char * const omap5_dss_sys_clk_parents[] __initconst = {
+	"dss_syc_gfclk_div",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data omap5_dss_core_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_dss_dss_clk_parents, NULL },
+	{ 9, TI_CLK_GATE, omap5_dss_48mhz_clk_parents, NULL },
+	{ 10, TI_CLK_GATE, omap5_dss_sys_clk_parents, NULL },
+	{ 11, TI_CLK_GATE, omap5_gpio2_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_dss_clkctrl_regs[] __initconst = {
+	{ OMAP5_DSS_CORE_CLKCTRL, omap5_dss_core_bit_data, CLKF_SW_SUP, "dss_cm:clk:0000:8" },
+	{ 0 },
+};
+
+static const char * const omap5_mmc1_fclk_mux_parents[] __initconst = {
+	"func_128m_clk",
+	"dpll_per_m2x2_ck",
+	NULL,
+};
+
+static const char * const omap5_mmc1_fclk_parents[] __initconst = {
+	"l3init_cm:clk:0008:24",
+	NULL,
+};
+
+static const struct omap_clkctrl_div_data omap5_mmc1_fclk_data __initconst = {
+	.max_div = 2,
+};
+
+static const struct omap_clkctrl_bit_data omap5_mmc1_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_gpio2_dbclk_parents, NULL },
+	{ 24, TI_CLK_MUX, omap5_mmc1_fclk_mux_parents, NULL },
+	{ 25, TI_CLK_DIVIDER, omap5_mmc1_fclk_parents, &omap5_mmc1_fclk_data },
+	{ 0 },
+};
+
+static const char * const omap5_mmc2_fclk_parents[] __initconst = {
+	"l3init_cm:clk:0010:24",
+	NULL,
+};
+
+static const struct omap_clkctrl_div_data omap5_mmc2_fclk_data __initconst = {
+	.max_div = 2,
+};
+
+static const struct omap_clkctrl_bit_data omap5_mmc2_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_mmc1_fclk_mux_parents, NULL },
+	{ 25, TI_CLK_DIVIDER, omap5_mmc2_fclk_parents, &omap5_mmc2_fclk_data },
+	{ 0 },
+};
+
+static const char * const omap5_usb_host_hs_hsic60m_p3_clk_parents[] __initconst = {
+	"l3init_60m_fclk",
+	NULL,
+};
+
+static const char * const omap5_usb_host_hs_hsic480m_p3_clk_parents[] __initconst = {
+	"dpll_usb_m2_ck",
+	NULL,
+};
+
+static const char * const omap5_usb_host_hs_utmi_p1_clk_parents[] __initconst = {
+	"l3init_cm:clk:0038:24",
+	NULL,
+};
+
+static const char * const omap5_usb_host_hs_utmi_p2_clk_parents[] __initconst = {
+	"l3init_cm:clk:0038:25",
+	NULL,
+};
+
+static const char * const omap5_utmi_p1_gfclk_parents[] __initconst = {
+	"l3init_60m_fclk",
+	"xclk60mhsp1_ck",
+	NULL,
+};
+
+static const char * const omap5_utmi_p2_gfclk_parents[] __initconst = {
+	"l3init_60m_fclk",
+	"xclk60mhsp2_ck",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data omap5_usb_host_hs_bit_data[] __initconst = {
+	{ 6, TI_CLK_GATE, omap5_usb_host_hs_hsic60m_p3_clk_parents, NULL },
+	{ 7, TI_CLK_GATE, omap5_usb_host_hs_hsic480m_p3_clk_parents, NULL },
+	{ 8, TI_CLK_GATE, omap5_usb_host_hs_utmi_p1_clk_parents, NULL },
+	{ 9, TI_CLK_GATE, omap5_usb_host_hs_utmi_p2_clk_parents, NULL },
+	{ 10, TI_CLK_GATE, omap5_usb_host_hs_hsic60m_p3_clk_parents, NULL },
+	{ 11, TI_CLK_GATE, omap5_usb_host_hs_hsic60m_p3_clk_parents, NULL },
+	{ 12, TI_CLK_GATE, omap5_usb_host_hs_hsic60m_p3_clk_parents, NULL },
+	{ 13, TI_CLK_GATE, omap5_usb_host_hs_hsic480m_p3_clk_parents, NULL },
+	{ 14, TI_CLK_GATE, omap5_usb_host_hs_hsic480m_p3_clk_parents, NULL },
+	{ 24, TI_CLK_MUX, omap5_utmi_p1_gfclk_parents, NULL },
+	{ 25, TI_CLK_MUX, omap5_utmi_p2_gfclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_usb_tll_hs_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_usb_host_hs_hsic60m_p3_clk_parents, NULL },
+	{ 9, TI_CLK_GATE, omap5_usb_host_hs_hsic60m_p3_clk_parents, NULL },
+	{ 10, TI_CLK_GATE, omap5_usb_host_hs_hsic60m_p3_clk_parents, NULL },
+	{ 0 },
+};
+
+static const char * const omap5_sata_ref_clk_parents[] __initconst = {
+	"sys_clkin",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data omap5_sata_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_sata_ref_clk_parents, NULL },
+	{ 0 },
+};
+
+static const char * const omap5_usb_otg_ss_refclk960m_parents[] __initconst = {
+	"dpll_usb_clkdcoldo",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data omap5_usb_otg_ss_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_usb_otg_ss_refclk960m_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_l3init_clkctrl_regs[] __initconst = {
+	{ OMAP5_MMC1_CLKCTRL, omap5_mmc1_bit_data, CLKF_SW_SUP, "l3init_cm:clk:0008:25" },
+	{ OMAP5_MMC2_CLKCTRL, omap5_mmc2_bit_data, CLKF_SW_SUP, "l3init_cm:clk:0010:25" },
+	{ OMAP5_USB_HOST_HS_CLKCTRL, omap5_usb_host_hs_bit_data, CLKF_SW_SUP, "l3init_60m_fclk" },
+	{ OMAP5_USB_TLL_HS_CLKCTRL, omap5_usb_tll_hs_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ OMAP5_SATA_CLKCTRL, omap5_sata_bit_data, CLKF_SW_SUP, "func_48m_fclk" },
+	{ OMAP5_OCP2SCP1_CLKCTRL, NULL, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ OMAP5_OCP2SCP3_CLKCTRL, NULL, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ OMAP5_USB_OTG_SS_CLKCTRL, omap5_usb_otg_ss_bit_data, CLKF_HW_SUP, "dpll_core_h13x2_ck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_gpio1_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, omap5_gpio2_dbclk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data omap5_timer1_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, omap5_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data omap5_wkupaon_clkctrl_regs[] __initconst = {
+	{ OMAP5_L4_WKUP_CLKCTRL, NULL, 0, "wkupaon_iclk_mux" },
+	{ OMAP5_WD_TIMER2_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
+	{ OMAP5_GPIO1_CLKCTRL, omap5_gpio1_bit_data, CLKF_HW_SUP, "wkupaon_iclk_mux" },
+	{ OMAP5_TIMER1_CLKCTRL, omap5_timer1_bit_data, CLKF_SW_SUP, "wkupaon_cm:clk:0020:24" },
+	{ OMAP5_COUNTER_32K_CLKCTRL, NULL, 0, "wkupaon_iclk_mux" },
+	{ OMAP5_KBD_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
+	{ 0 },
+};
+
+const struct omap_clkctrl_data omap5_clkctrl_data[] __initconst = {
+	{ 0x4a004320, omap5_mpu_clkctrl_regs },
+	{ 0x4a004420, omap5_dsp_clkctrl_regs },
+	{ 0x4a004520, omap5_abe_clkctrl_regs },
+	{ 0x4a008720, omap5_l3main1_clkctrl_regs },
+	{ 0x4a008820, omap5_l3main2_clkctrl_regs },
+	{ 0x4a008920, omap5_ipu_clkctrl_regs },
+	{ 0x4a008a20, omap5_dma_clkctrl_regs },
+	{ 0x4a008b20, omap5_emif_clkctrl_regs },
+	{ 0x4a008d20, omap5_l4cfg_clkctrl_regs },
+	{ 0x4a008e20, omap5_l3instr_clkctrl_regs },
+	{ 0x4a009020, omap5_l4per_clkctrl_regs },
+	{ 0x4a009420, omap5_dss_clkctrl_regs },
+	{ 0x4a009620, omap5_l3init_clkctrl_regs },
+	{ 0x4ae07920, omap5_wkupaon_clkctrl_regs },
+	{ 0 },
+};
+
 static struct ti_dt_clk omap54xx_clks[] = {
-	DT_CLK(NULL, "pad_clks_src_ck", "pad_clks_src_ck"),
-	DT_CLK(NULL, "pad_clks_ck", "pad_clks_ck"),
-	DT_CLK(NULL, "secure_32k_clk_src_ck", "secure_32k_clk_src_ck"),
-	DT_CLK(NULL, "slimbus_src_clk", "slimbus_src_clk"),
-	DT_CLK(NULL, "slimbus_clk", "slimbus_clk"),
-	DT_CLK(NULL, "sys_32k_ck", "sys_32k_ck"),
-	DT_CLK(NULL, "virt_12000000_ck", "virt_12000000_ck"),
-	DT_CLK(NULL, "virt_13000000_ck", "virt_13000000_ck"),
-	DT_CLK(NULL, "virt_16800000_ck", "virt_16800000_ck"),
-	DT_CLK(NULL, "virt_19200000_ck", "virt_19200000_ck"),
-	DT_CLK(NULL, "virt_26000000_ck", "virt_26000000_ck"),
-	DT_CLK(NULL, "virt_27000000_ck", "virt_27000000_ck"),
-	DT_CLK(NULL, "virt_38400000_ck", "virt_38400000_ck"),
-	DT_CLK(NULL, "sys_clkin", "sys_clkin"),
-	DT_CLK(NULL, "xclk60mhsp1_ck", "xclk60mhsp1_ck"),
-	DT_CLK(NULL, "xclk60mhsp2_ck", "xclk60mhsp2_ck"),
-	DT_CLK(NULL, "abe_dpll_bypass_clk_mux", "abe_dpll_bypass_clk_mux"),
-	DT_CLK(NULL, "abe_dpll_clk_mux", "abe_dpll_clk_mux"),
-	DT_CLK(NULL, "dpll_abe_ck", "dpll_abe_ck"),
-	DT_CLK(NULL, "dpll_abe_x2_ck", "dpll_abe_x2_ck"),
-	DT_CLK(NULL, "dpll_abe_m2x2_ck", "dpll_abe_m2x2_ck"),
-	DT_CLK(NULL, "abe_24m_fclk", "abe_24m_fclk"),
-	DT_CLK(NULL, "abe_clk", "abe_clk"),
-	DT_CLK(NULL, "abe_iclk", "abe_iclk"),
-	DT_CLK(NULL, "abe_lp_clk_div", "abe_lp_clk_div"),
-	DT_CLK(NULL, "dpll_abe_m3x2_ck", "dpll_abe_m3x2_ck"),
-	DT_CLK(NULL, "dpll_core_ck", "dpll_core_ck"),
-	DT_CLK(NULL, "dpll_core_x2_ck", "dpll_core_x2_ck"),
-	DT_CLK(NULL, "dpll_core_h21x2_ck", "dpll_core_h21x2_ck"),
-	DT_CLK(NULL, "c2c_fclk", "c2c_fclk"),
-	DT_CLK(NULL, "c2c_iclk", "c2c_iclk"),
-	DT_CLK(NULL, "custefuse_sys_gfclk_div", "custefuse_sys_gfclk_div"),
-	DT_CLK(NULL, "dpll_core_h11x2_ck", "dpll_core_h11x2_ck"),
-	DT_CLK(NULL, "dpll_core_h12x2_ck", "dpll_core_h12x2_ck"),
-	DT_CLK(NULL, "dpll_core_h13x2_ck", "dpll_core_h13x2_ck"),
-	DT_CLK(NULL, "dpll_core_h14x2_ck", "dpll_core_h14x2_ck"),
-	DT_CLK(NULL, "dpll_core_h22x2_ck", "dpll_core_h22x2_ck"),
-	DT_CLK(NULL, "dpll_core_h23x2_ck", "dpll_core_h23x2_ck"),
-	DT_CLK(NULL, "dpll_core_h24x2_ck", "dpll_core_h24x2_ck"),
-	DT_CLK(NULL, "dpll_core_m2_ck", "dpll_core_m2_ck"),
-	DT_CLK(NULL, "dpll_core_m3x2_ck", "dpll_core_m3x2_ck"),
-	DT_CLK(NULL, "iva_dpll_hs_clk_div", "iva_dpll_hs_clk_div"),
-	DT_CLK(NULL, "dpll_iva_ck", "dpll_iva_ck"),
-	DT_CLK(NULL, "dpll_iva_x2_ck", "dpll_iva_x2_ck"),
-	DT_CLK(NULL, "dpll_iva_h11x2_ck", "dpll_iva_h11x2_ck"),
-	DT_CLK(NULL, "dpll_iva_h12x2_ck", "dpll_iva_h12x2_ck"),
-	DT_CLK(NULL, "mpu_dpll_hs_clk_div", "mpu_dpll_hs_clk_div"),
-	DT_CLK(NULL, "dpll_mpu_ck", "dpll_mpu_ck"),
-	DT_CLK(NULL, "dpll_mpu_m2_ck", "dpll_mpu_m2_ck"),
-	DT_CLK(NULL, "per_dpll_hs_clk_div", "per_dpll_hs_clk_div"),
-	DT_CLK(NULL, "dpll_per_ck", "dpll_per_ck"),
-	DT_CLK(NULL, "dpll_per_x2_ck", "dpll_per_x2_ck"),
-	DT_CLK(NULL, "dpll_per_h11x2_ck", "dpll_per_h11x2_ck"),
-	DT_CLK(NULL, "dpll_per_h12x2_ck", "dpll_per_h12x2_ck"),
-	DT_CLK(NULL, "dpll_per_h14x2_ck", "dpll_per_h14x2_ck"),
-	DT_CLK(NULL, "dpll_per_m2_ck", "dpll_per_m2_ck"),
-	DT_CLK(NULL, "dpll_per_m2x2_ck", "dpll_per_m2x2_ck"),
-	DT_CLK(NULL, "dpll_per_m3x2_ck", "dpll_per_m3x2_ck"),
-	DT_CLK(NULL, "dpll_unipro1_ck", "dpll_unipro1_ck"),
-	DT_CLK(NULL, "dpll_unipro1_clkdcoldo", "dpll_unipro1_clkdcoldo"),
-	DT_CLK(NULL, "dpll_unipro1_m2_ck", "dpll_unipro1_m2_ck"),
-	DT_CLK(NULL, "dpll_unipro2_ck", "dpll_unipro2_ck"),
-	DT_CLK(NULL, "dpll_unipro2_clkdcoldo", "dpll_unipro2_clkdcoldo"),
-	DT_CLK(NULL, "dpll_unipro2_m2_ck", "dpll_unipro2_m2_ck"),
-	DT_CLK(NULL, "usb_dpll_hs_clk_div", "usb_dpll_hs_clk_div"),
-	DT_CLK(NULL, "dpll_usb_ck", "dpll_usb_ck"),
-	DT_CLK(NULL, "dpll_usb_clkdcoldo", "dpll_usb_clkdcoldo"),
-	DT_CLK(NULL, "dpll_usb_m2_ck", "dpll_usb_m2_ck"),
-	DT_CLK(NULL, "dss_syc_gfclk_div", "dss_syc_gfclk_div"),
-	DT_CLK(NULL, "func_128m_clk", "func_128m_clk"),
-	DT_CLK(NULL, "func_12m_fclk", "func_12m_fclk"),
-	DT_CLK(NULL, "func_24m_clk", "func_24m_clk"),
-	DT_CLK(NULL, "func_48m_fclk", "func_48m_fclk"),
-	DT_CLK(NULL, "func_96m_fclk", "func_96m_fclk"),
-	DT_CLK(NULL, "l3_iclk_div", "l3_iclk_div"),
-	DT_CLK(NULL, "gpu_l3_iclk", "gpu_l3_iclk"),
-	DT_CLK(NULL, "l3init_60m_fclk", "l3init_60m_fclk"),
-	DT_CLK(NULL, "wkupaon_iclk_mux", "wkupaon_iclk_mux"),
-	DT_CLK(NULL, "l3instr_ts_gclk_div", "l3instr_ts_gclk_div"),
-	DT_CLK(NULL, "l4_root_clk_div", "l4_root_clk_div"),
-	DT_CLK(NULL, "dss_32khz_clk", "dss_32khz_clk"),
-	DT_CLK(NULL, "dss_48mhz_clk", "dss_48mhz_clk"),
-	DT_CLK(NULL, "dss_dss_clk", "dss_dss_clk"),
-	DT_CLK(NULL, "dss_sys_clk", "dss_sys_clk"),
-	DT_CLK(NULL, "gpio1_dbclk", "gpio1_dbclk"),
-	DT_CLK(NULL, "gpio2_dbclk", "gpio2_dbclk"),
-	DT_CLK(NULL, "gpio3_dbclk", "gpio3_dbclk"),
-	DT_CLK(NULL, "gpio4_dbclk", "gpio4_dbclk"),
-	DT_CLK(NULL, "gpio5_dbclk", "gpio5_dbclk"),
-	DT_CLK(NULL, "gpio6_dbclk", "gpio6_dbclk"),
-	DT_CLK(NULL, "gpio7_dbclk", "gpio7_dbclk"),
-	DT_CLK(NULL, "gpio8_dbclk", "gpio8_dbclk"),
-	DT_CLK(NULL, "iss_ctrlclk", "iss_ctrlclk"),
-	DT_CLK(NULL, "lli_txphy_clk", "lli_txphy_clk"),
-	DT_CLK(NULL, "lli_txphy_ls_clk", "lli_txphy_ls_clk"),
-	DT_CLK(NULL, "mmc1_32khz_clk", "mmc1_32khz_clk"),
-	DT_CLK(NULL, "sata_ref_clk", "sata_ref_clk"),
-	DT_CLK(NULL, "slimbus1_slimbus_clk", "slimbus1_slimbus_clk"),
-	DT_CLK(NULL, "usb_host_hs_hsic480m_p1_clk", "usb_host_hs_hsic480m_p1_clk"),
-	DT_CLK(NULL, "usb_host_hs_hsic480m_p2_clk", "usb_host_hs_hsic480m_p2_clk"),
-	DT_CLK(NULL, "usb_host_hs_hsic480m_p3_clk", "usb_host_hs_hsic480m_p3_clk"),
-	DT_CLK(NULL, "usb_host_hs_hsic60m_p1_clk", "usb_host_hs_hsic60m_p1_clk"),
-	DT_CLK(NULL, "usb_host_hs_hsic60m_p2_clk", "usb_host_hs_hsic60m_p2_clk"),
-	DT_CLK(NULL, "usb_host_hs_hsic60m_p3_clk", "usb_host_hs_hsic60m_p3_clk"),
-	DT_CLK(NULL, "usb_host_hs_utmi_p1_clk", "usb_host_hs_utmi_p1_clk"),
-	DT_CLK(NULL, "usb_host_hs_utmi_p2_clk", "usb_host_hs_utmi_p2_clk"),
-	DT_CLK(NULL, "usb_host_hs_utmi_p3_clk", "usb_host_hs_utmi_p3_clk"),
-	DT_CLK(NULL, "usb_otg_ss_refclk960m", "usb_otg_ss_refclk960m"),
-	DT_CLK(NULL, "usb_phy_cm_clk32k", "usb_phy_cm_clk32k"),
-	DT_CLK(NULL, "usb_tll_hs_usb_ch0_clk", "usb_tll_hs_usb_ch0_clk"),
-	DT_CLK(NULL, "usb_tll_hs_usb_ch1_clk", "usb_tll_hs_usb_ch1_clk"),
-	DT_CLK(NULL, "usb_tll_hs_usb_ch2_clk", "usb_tll_hs_usb_ch2_clk"),
-	DT_CLK(NULL, "aess_fclk", "aess_fclk"),
-	DT_CLK(NULL, "dmic_sync_mux_ck", "dmic_sync_mux_ck"),
-	DT_CLK(NULL, "dmic_gfclk", "dmic_gfclk"),
-	DT_CLK(NULL, "fdif_fclk", "fdif_fclk"),
-	DT_CLK(NULL, "gpu_core_gclk_mux", "gpu_core_gclk_mux"),
-	DT_CLK(NULL, "gpu_hyd_gclk_mux", "gpu_hyd_gclk_mux"),
-	DT_CLK(NULL, "hsi_fclk", "hsi_fclk"),
-	DT_CLK(NULL, "mcasp_sync_mux_ck", "mcasp_sync_mux_ck"),
-	DT_CLK(NULL, "mcasp_gfclk", "mcasp_gfclk"),
-	DT_CLK(NULL, "mcbsp1_sync_mux_ck", "mcbsp1_sync_mux_ck"),
-	DT_CLK(NULL, "mcbsp1_gfclk", "mcbsp1_gfclk"),
-	DT_CLK(NULL, "mcbsp2_sync_mux_ck", "mcbsp2_sync_mux_ck"),
-	DT_CLK(NULL, "mcbsp2_gfclk", "mcbsp2_gfclk"),
-	DT_CLK(NULL, "mcbsp3_sync_mux_ck", "mcbsp3_sync_mux_ck"),
-	DT_CLK(NULL, "mcbsp3_gfclk", "mcbsp3_gfclk"),
-	DT_CLK(NULL, "mmc1_fclk_mux", "mmc1_fclk_mux"),
-	DT_CLK(NULL, "mmc1_fclk", "mmc1_fclk"),
-	DT_CLK(NULL, "mmc2_fclk_mux", "mmc2_fclk_mux"),
-	DT_CLK(NULL, "mmc2_fclk", "mmc2_fclk"),
-	DT_CLK(NULL, "timer10_gfclk_mux", "timer10_gfclk_mux"),
-	DT_CLK(NULL, "timer11_gfclk_mux", "timer11_gfclk_mux"),
-	DT_CLK(NULL, "timer1_gfclk_mux", "timer1_gfclk_mux"),
-	DT_CLK(NULL, "timer2_gfclk_mux", "timer2_gfclk_mux"),
-	DT_CLK(NULL, "timer3_gfclk_mux", "timer3_gfclk_mux"),
-	DT_CLK(NULL, "timer4_gfclk_mux", "timer4_gfclk_mux"),
-	DT_CLK(NULL, "timer5_gfclk_mux", "timer5_gfclk_mux"),
-	DT_CLK(NULL, "timer6_gfclk_mux", "timer6_gfclk_mux"),
-	DT_CLK(NULL, "timer7_gfclk_mux", "timer7_gfclk_mux"),
-	DT_CLK(NULL, "timer8_gfclk_mux", "timer8_gfclk_mux"),
-	DT_CLK(NULL, "timer9_gfclk_mux", "timer9_gfclk_mux"),
-	DT_CLK(NULL, "utmi_p1_gfclk", "utmi_p1_gfclk"),
-	DT_CLK(NULL, "utmi_p2_gfclk", "utmi_p2_gfclk"),
-	DT_CLK(NULL, "auxclk0_src_ck", "auxclk0_src_ck"),
-	DT_CLK(NULL, "auxclk0_ck", "auxclk0_ck"),
-	DT_CLK(NULL, "auxclkreq0_ck", "auxclkreq0_ck"),
-	DT_CLK(NULL, "auxclk1_src_ck", "auxclk1_src_ck"),
-	DT_CLK(NULL, "auxclk1_ck", "auxclk1_ck"),
-	DT_CLK(NULL, "auxclkreq1_ck", "auxclkreq1_ck"),
-	DT_CLK(NULL, "auxclk2_src_ck", "auxclk2_src_ck"),
-	DT_CLK(NULL, "auxclk2_ck", "auxclk2_ck"),
-	DT_CLK(NULL, "auxclkreq2_ck", "auxclkreq2_ck"),
-	DT_CLK(NULL, "auxclk3_src_ck", "auxclk3_src_ck"),
-	DT_CLK(NULL, "auxclk3_ck", "auxclk3_ck"),
-	DT_CLK(NULL, "auxclkreq3_ck", "auxclkreq3_ck"),
-	DT_CLK("omap_i2c.1", "ick", "dummy_ck"),
-	DT_CLK("omap_i2c.2", "ick", "dummy_ck"),
-	DT_CLK("omap_i2c.3", "ick", "dummy_ck"),
-	DT_CLK("omap_i2c.4", "ick", "dummy_ck"),
-	DT_CLK(NULL, "mailboxes_ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.0", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.1", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.2", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.3", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.4", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.1", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.2", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.3", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.4", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.1", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.2", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.3", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.4", "ick", "dummy_ck"),
-	DT_CLK(NULL, "uart1_ick", "dummy_ck"),
-	DT_CLK(NULL, "uart2_ick", "dummy_ck"),
-	DT_CLK(NULL, "uart3_ick", "dummy_ck"),
-	DT_CLK(NULL, "uart4_ick", "dummy_ck"),
-	DT_CLK("usbhs_omap", "usbhost_ick", "dummy_ck"),
-	DT_CLK("usbhs_omap", "usbtll_fck", "dummy_ck"),
-	DT_CLK("omap_wdt", "ick", "dummy_ck"),
 	DT_CLK(NULL, "timer_32k_ck", "sys_32k_ck"),
 	DT_CLK(NULL, "sys_clkin_ck", "sys_clkin"),
-	DT_CLK("4ae18000.timer", "timer_sys_ck", "sys_clkin"),
-	DT_CLK("48032000.timer", "timer_sys_ck", "sys_clkin"),
-	DT_CLK("48034000.timer", "timer_sys_ck", "sys_clkin"),
-	DT_CLK("48036000.timer", "timer_sys_ck", "sys_clkin"),
-	DT_CLK("4803e000.timer", "timer_sys_ck", "sys_clkin"),
-	DT_CLK("48086000.timer", "timer_sys_ck", "sys_clkin"),
-	DT_CLK("48088000.timer", "timer_sys_ck", "sys_clkin"),
-	DT_CLK("40138000.timer", "timer_sys_ck", "dss_syc_gfclk_div"),
-	DT_CLK("4013a000.timer", "timer_sys_ck", "dss_syc_gfclk_div"),
-	DT_CLK("4013c000.timer", "timer_sys_ck", "dss_syc_gfclk_div"),
-	DT_CLK("4013e000.timer", "timer_sys_ck", "dss_syc_gfclk_div"),
+	DT_CLK(NULL, "dmic_gfclk", "abe_cm:0018:24"),
+	DT_CLK(NULL, "dmic_sync_mux_ck", "abe_cm:0018:26"),
+	DT_CLK(NULL, "dss_32khz_clk", "dss_cm:0000:11"),
+	DT_CLK(NULL, "dss_48mhz_clk", "dss_cm:0000:9"),
+	DT_CLK(NULL, "dss_dss_clk", "dss_cm:0000:8"),
+	DT_CLK(NULL, "dss_sys_clk", "dss_cm:0000:10"),
+	DT_CLK(NULL, "gpio1_dbclk", "wkupaon_cm:0018:8"),
+	DT_CLK(NULL, "gpio2_dbclk", "l4per_cm:0040:8"),
+	DT_CLK(NULL, "gpio3_dbclk", "l4per_cm:0048:8"),
+	DT_CLK(NULL, "gpio4_dbclk", "l4per_cm:0050:8"),
+	DT_CLK(NULL, "gpio5_dbclk", "l4per_cm:0058:8"),
+	DT_CLK(NULL, "gpio6_dbclk", "l4per_cm:0060:8"),
+	DT_CLK(NULL, "gpio7_dbclk", "l4per_cm:00f0:8"),
+	DT_CLK(NULL, "gpio8_dbclk", "l4per_cm:00f8:8"),
+	DT_CLK(NULL, "mcbsp1_gfclk", "abe_cm:0028:24"),
+	DT_CLK(NULL, "mcbsp1_sync_mux_ck", "abe_cm:0028:26"),
+	DT_CLK(NULL, "mcbsp2_gfclk", "abe_cm:0030:24"),
+	DT_CLK(NULL, "mcbsp2_sync_mux_ck", "abe_cm:0030:26"),
+	DT_CLK(NULL, "mcbsp3_gfclk", "abe_cm:0038:24"),
+	DT_CLK(NULL, "mcbsp3_sync_mux_ck", "abe_cm:0038:26"),
+	DT_CLK(NULL, "mmc1_32khz_clk", "l3init_cm:0008:8"),
+	DT_CLK(NULL, "mmc1_fclk", "l3init_cm:0008:25"),
+	DT_CLK(NULL, "mmc1_fclk_mux", "l3init_cm:0008:24"),
+	DT_CLK(NULL, "mmc2_fclk", "l3init_cm:0010:25"),
+	DT_CLK(NULL, "mmc2_fclk_mux", "l3init_cm:0010:24"),
+	DT_CLK(NULL, "sata_ref_clk", "l3init_cm:0068:8"),
+	DT_CLK(NULL, "timer10_gfclk_mux", "l4per_cm:0008:24"),
+	DT_CLK(NULL, "timer11_gfclk_mux", "l4per_cm:0010:24"),
+	DT_CLK(NULL, "timer1_gfclk_mux", "wkupaon_cm:0020:24"),
+	DT_CLK(NULL, "timer2_gfclk_mux", "l4per_cm:0018:24"),
+	DT_CLK(NULL, "timer3_gfclk_mux", "l4per_cm:0020:24"),
+	DT_CLK(NULL, "timer4_gfclk_mux", "l4per_cm:0028:24"),
+	DT_CLK(NULL, "timer5_gfclk_mux", "abe_cm:0048:24"),
+	DT_CLK(NULL, "timer6_gfclk_mux", "abe_cm:0050:24"),
+	DT_CLK(NULL, "timer7_gfclk_mux", "abe_cm:0058:24"),
+	DT_CLK(NULL, "timer8_gfclk_mux", "abe_cm:0060:24"),
+	DT_CLK(NULL, "timer9_gfclk_mux", "l4per_cm:0030:24"),
+	DT_CLK(NULL, "usb_host_hs_hsic480m_p1_clk", "l3init_cm:0038:13"),
+	DT_CLK(NULL, "usb_host_hs_hsic480m_p2_clk", "l3init_cm:0038:14"),
+	DT_CLK(NULL, "usb_host_hs_hsic480m_p3_clk", "l3init_cm:0038:7"),
+	DT_CLK(NULL, "usb_host_hs_hsic60m_p1_clk", "l3init_cm:0038:11"),
+	DT_CLK(NULL, "usb_host_hs_hsic60m_p2_clk", "l3init_cm:0038:12"),
+	DT_CLK(NULL, "usb_host_hs_hsic60m_p3_clk", "l3init_cm:0038:6"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p1_clk", "l3init_cm:0038:8"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p2_clk", "l3init_cm:0038:9"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p3_clk", "l3init_cm:0038:10"),
+	DT_CLK(NULL, "usb_otg_ss_refclk960m", "l3init_cm:00d0:8"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch0_clk", "l3init_cm:0048:8"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch1_clk", "l3init_cm:0048:9"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch2_clk", "l3init_cm:0048:10"),
+	DT_CLK(NULL, "utmi_p1_gfclk", "l3init_cm:0038:24"),
+	DT_CLK(NULL, "utmi_p2_gfclk", "l3init_cm:0038:25"),
 	{ .node_name = NULL },
 };
 
@@ -234,6 +545,8 @@ int __init omap5xxx_dt_clk_init(void)
 
 	omap2_clk_disable_autoidle_all();
 
+	ti_clk_add_aliases();
+
 	abe_dpll_ref = clk_get_sys(NULL, "abe_dpll_clk_mux");
 	sys_32k_ck = clk_get_sys(NULL, "sys_32k_ck");
 	rc = clk_set_parent(abe_dpll_ref, sys_32k_ck);
diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c
index 9fd6043314eb..fb249a1637a5 100644
--- a/drivers/clk/ti/clk-7xx.c
+++ b/drivers/clk/ti/clk-7xx.c
@@ -15,297 +15,809 @@
 #include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/clk/ti.h>
+#include <dt-bindings/clock/dra7.h>
 
 #include "clock.h"
 
 #define DRA7_DPLL_GMAC_DEFFREQ				1000000000
 #define DRA7_DPLL_USB_DEFFREQ				960000000
 
+static const struct omap_clkctrl_reg_data dra7_mpu_clkctrl_regs[] __initconst = {
+	{ DRA7_MPU_CLKCTRL, NULL, 0, "dpll_mpu_m2_ck" },
+	{ 0 },
+};
+
+static const char * const dra7_mcasp1_aux_gfclk_mux_parents[] __initconst = {
+	"per_abe_x1_gfclk2_div",
+	"video1_clk2_div",
+	"video2_clk2_div",
+	"hdmi_clk2_div",
+	NULL,
+};
+
+static const char * const dra7_mcasp1_ahclkx_mux_parents[] __initconst = {
+	"abe_24m_fclk",
+	"abe_sys_clk_div",
+	"func_24m_clk",
+	"atl_clkin3_ck",
+	"atl_clkin2_ck",
+	"atl_clkin1_ck",
+	"atl_clkin0_ck",
+	"sys_clkin2",
+	"ref_clkin0_ck",
+	"ref_clkin1_ck",
+	"ref_clkin2_ck",
+	"ref_clkin3_ck",
+	"mlb_clk",
+	"mlbp_clk",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_mcasp1_bit_data[] __initconst = {
+	{ 22, TI_CLK_MUX, dra7_mcasp1_aux_gfclk_mux_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_mcasp1_ahclkx_mux_parents, NULL },
+	{ 28, TI_CLK_MUX, dra7_mcasp1_ahclkx_mux_parents, NULL },
+	{ 0 },
+};
+
+static const char * const dra7_timer5_gfclk_mux_parents[] __initconst = {
+	"timer_sys_clk_div",
+	"sys_32k_ck",
+	"sys_clkin2",
+	"ref_clkin0_ck",
+	"ref_clkin1_ck",
+	"ref_clkin2_ck",
+	"ref_clkin3_ck",
+	"abe_giclk_div",
+	"video1_div_clk",
+	"video2_div_clk",
+	"hdmi_div_clk",
+	"clkoutmux0_clk_mux",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer5_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer5_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer6_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer5_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer7_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer5_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer8_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer5_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const char * const dra7_uart6_gfclk_mux_parents[] __initconst = {
+	"func_48m_fclk",
+	"dpll_per_m2x2_ck",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_uart6_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_ipu_clkctrl_regs[] __initconst = {
+	{ DRA7_MCASP1_CLKCTRL, dra7_mcasp1_bit_data, CLKF_SW_SUP, "ipu_cm:clk:0010:22" },
+	{ DRA7_TIMER5_CLKCTRL, dra7_timer5_bit_data, CLKF_SW_SUP, "ipu_cm:clk:0018:24" },
+	{ DRA7_TIMER6_CLKCTRL, dra7_timer6_bit_data, CLKF_SW_SUP, "ipu_cm:clk:0020:24" },
+	{ DRA7_TIMER7_CLKCTRL, dra7_timer7_bit_data, CLKF_SW_SUP, "ipu_cm:clk:0028:24" },
+	{ DRA7_TIMER8_CLKCTRL, dra7_timer8_bit_data, CLKF_SW_SUP, "ipu_cm:clk:0030:24" },
+	{ DRA7_I2C5_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
+	{ DRA7_UART6_CLKCTRL, dra7_uart6_bit_data, CLKF_SW_SUP, "ipu_cm:clk:0040:24" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_rtc_clkctrl_regs[] __initconst = {
+	{ DRA7_RTCSS_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_coreaon_clkctrl_regs[] __initconst = {
+	{ DRA7_SMARTREFLEX_MPU_CLKCTRL, NULL, CLKF_SW_SUP, "wkupaon_iclk_mux" },
+	{ DRA7_SMARTREFLEX_CORE_CLKCTRL, NULL, CLKF_SW_SUP, "wkupaon_iclk_mux" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_l3main1_clkctrl_regs[] __initconst = {
+	{ DRA7_L3_MAIN_1_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_GPMC_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_TPCC_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_TPTC0_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_TPTC1_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_VCP1_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_VCP2_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_dma_clkctrl_regs[] __initconst = {
+	{ DRA7_DMA_SYSTEM_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_emif_clkctrl_regs[] __initconst = {
+	{ DRA7_DMM_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ 0 },
+};
+
+static const char * const dra7_atl_dpll_clk_mux_parents[] __initconst = {
+	"sys_32k_ck",
+	"video1_clkin_ck",
+	"video2_clkin_ck",
+	"hdmi_clkin_ck",
+	NULL,
+};
+
+static const char * const dra7_atl_gfclk_mux_parents[] __initconst = {
+	"l3_iclk_div",
+	"dpll_abe_m2_ck",
+	"atl_cm:clk:0000:24",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_atl_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_atl_dpll_clk_mux_parents, NULL },
+	{ 26, TI_CLK_MUX, dra7_atl_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_atl_clkctrl_regs[] __initconst = {
+	{ DRA7_ATL_CLKCTRL, dra7_atl_bit_data, CLKF_SW_SUP, "atl_cm:clk:0000:26" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_l4cfg_clkctrl_regs[] __initconst = {
+	{ DRA7_L4_CFG_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_SPINLOCK_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX1_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX2_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX3_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX4_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX5_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX6_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX7_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX8_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX9_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX10_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX11_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX12_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_MAILBOX13_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_l3instr_clkctrl_regs[] __initconst = {
+	{ DRA7_L3_MAIN_2_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_L3_INSTR_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div" },
+	{ 0 },
+};
+
+static const char * const dra7_dss_dss_clk_parents[] __initconst = {
+	"dpll_per_h12x2_ck",
+	NULL,
+};
+
+static const char * const dra7_dss_48mhz_clk_parents[] __initconst = {
+	"func_48m_fclk",
+	NULL,
+};
+
+static const char * const dra7_dss_hdmi_clk_parents[] __initconst = {
+	"hdmi_dpll_clk_mux",
+	NULL,
+};
+
+static const char * const dra7_dss_32khz_clk_parents[] __initconst = {
+	"sys_32k_ck",
+	NULL,
+};
+
+static const char * const dra7_dss_video1_clk_parents[] __initconst = {
+	"video1_dpll_clk_mux",
+	NULL,
+};
+
+static const char * const dra7_dss_video2_clk_parents[] __initconst = {
+	"video2_dpll_clk_mux",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_dss_core_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_dss_clk_parents, NULL },
+	{ 9, TI_CLK_GATE, dra7_dss_48mhz_clk_parents, NULL },
+	{ 10, TI_CLK_GATE, dra7_dss_hdmi_clk_parents, NULL },
+	{ 11, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 12, TI_CLK_GATE, dra7_dss_video1_clk_parents, NULL },
+	{ 13, TI_CLK_GATE, dra7_dss_video2_clk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_dss_clkctrl_regs[] __initconst = {
+	{ DRA7_DSS_CORE_CLKCTRL, dra7_dss_core_bit_data, CLKF_SW_SUP, "dss_cm:clk:0000:8" },
+	{ DRA7_BB2D_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_core_h24x2_ck" },
+	{ 0 },
+};
+
+static const char * const dra7_mmc1_fclk_mux_parents[] __initconst = {
+	"func_128m_clk",
+	"dpll_per_m2x2_ck",
+	NULL,
+};
+
+static const char * const dra7_mmc1_fclk_div_parents[] __initconst = {
+	"l3init_cm:clk:0008:24",
+	NULL,
+};
+
+static const struct omap_clkctrl_div_data dra7_mmc1_fclk_div_data __initconst = {
+	.max_div = 4,
+	.flags = CLK_DIVIDER_POWER_OF_TWO,
+};
+
+static const struct omap_clkctrl_bit_data dra7_mmc1_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_mmc1_fclk_mux_parents, NULL },
+	{ 25, TI_CLK_DIVIDER, dra7_mmc1_fclk_div_parents, &dra7_mmc1_fclk_div_data },
+	{ 0 },
+};
+
+static const char * const dra7_mmc2_fclk_div_parents[] __initconst = {
+	"l3init_cm:clk:0010:24",
+	NULL,
+};
+
+static const struct omap_clkctrl_div_data dra7_mmc2_fclk_div_data __initconst = {
+	.max_div = 4,
+	.flags = CLK_DIVIDER_POWER_OF_TWO,
+};
+
+static const struct omap_clkctrl_bit_data dra7_mmc2_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_mmc1_fclk_mux_parents, NULL },
+	{ 25, TI_CLK_DIVIDER, dra7_mmc2_fclk_div_parents, &dra7_mmc2_fclk_div_data },
+	{ 0 },
+};
+
+static const char * const dra7_usb_otg_ss2_refclk960m_parents[] __initconst = {
+	"l3init_960m_gfclk",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_usb_otg_ss2_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_usb_otg_ss2_refclk960m_parents, NULL },
+	{ 0 },
+};
+
+static const char * const dra7_sata_ref_clk_parents[] __initconst = {
+	"sys_clkin1",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_sata_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_sata_ref_clk_parents, NULL },
+	{ 0 },
+};
+
+static const char * const dra7_optfclk_pciephy1_clk_parents[] __initconst = {
+	"apll_pcie_ck",
+	NULL,
+};
+
+static const char * const dra7_optfclk_pciephy1_div_clk_parents[] __initconst = {
+	"optfclk_pciephy_div",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_pcie1_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 9, TI_CLK_GATE, dra7_optfclk_pciephy1_clk_parents, NULL },
+	{ 10, TI_CLK_GATE, dra7_optfclk_pciephy1_div_clk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_pcie2_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 9, TI_CLK_GATE, dra7_optfclk_pciephy1_clk_parents, NULL },
+	{ 10, TI_CLK_GATE, dra7_optfclk_pciephy1_div_clk_parents, NULL },
+	{ 0 },
+};
+
+static const char * const dra7_rmii_50mhz_clk_mux_parents[] __initconst = {
+	"dpll_gmac_h11x2_ck",
+	"rmii_clk_ck",
+	NULL,
+};
+
+static const char * const dra7_gmac_rft_clk_mux_parents[] __initconst = {
+	"video1_clkin_ck",
+	"video2_clkin_ck",
+	"dpll_abe_m2_ck",
+	"hdmi_clkin_ck",
+	"l3_iclk_div",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_gmac_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_rmii_50mhz_clk_mux_parents, NULL },
+	{ 25, TI_CLK_MUX, dra7_gmac_rft_clk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_usb_otg_ss1_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_usb_otg_ss2_refclk960m_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_l3init_clkctrl_regs[] __initconst = {
+	{ DRA7_MMC1_CLKCTRL, dra7_mmc1_bit_data, CLKF_SW_SUP, "l3init_cm:clk:0008:25" },
+	{ DRA7_MMC2_CLKCTRL, dra7_mmc2_bit_data, CLKF_SW_SUP, "l3init_cm:clk:0010:25" },
+	{ DRA7_USB_OTG_SS2_CLKCTRL, dra7_usb_otg_ss2_bit_data, CLKF_HW_SUP, "dpll_core_h13x2_ck" },
+	{ DRA7_USB_OTG_SS3_CLKCTRL, NULL, CLKF_HW_SUP, "dpll_core_h13x2_ck" },
+	{ DRA7_USB_OTG_SS4_CLKCTRL, NULL, CLKF_HW_SUP, "dpll_core_h13x2_ck" },
+	{ DRA7_SATA_CLKCTRL, dra7_sata_bit_data, CLKF_SW_SUP, "func_48m_fclk" },
+	{ DRA7_PCIE1_CLKCTRL, dra7_pcie1_bit_data, CLKF_SW_SUP, "l4_root_clk_div", "pcie_clkdm" },
+	{ DRA7_PCIE2_CLKCTRL, dra7_pcie2_bit_data, CLKF_SW_SUP, "l4_root_clk_div", "pcie_clkdm" },
+	{ DRA7_GMAC_CLKCTRL, dra7_gmac_bit_data, CLKF_SW_SUP, "dpll_gmac_ck", "gmac_clkdm" },
+	{ DRA7_OCP2SCP1_CLKCTRL, NULL, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ DRA7_OCP2SCP3_CLKCTRL, NULL, CLKF_HW_SUP, "l4_root_clk_div" },
+	{ DRA7_USB_OTG_SS1_CLKCTRL, dra7_usb_otg_ss1_bit_data, CLKF_HW_SUP, "dpll_core_h13x2_ck" },
+	{ 0 },
+};
+
+static const char * const dra7_timer10_gfclk_mux_parents[] __initconst = {
+	"timer_sys_clk_div",
+	"sys_32k_ck",
+	"sys_clkin2",
+	"ref_clkin0_ck",
+	"ref_clkin1_ck",
+	"ref_clkin2_ck",
+	"ref_clkin3_ck",
+	"abe_giclk_div",
+	"video1_div_clk",
+	"video2_div_clk",
+	"hdmi_div_clk",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer10_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer11_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer2_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer3_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer4_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer9_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_gpio2_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_gpio3_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_gpio4_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_gpio5_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_gpio6_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer13_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer14_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer15_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_gpio7_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_gpio8_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 0 },
+};
+
+static const char * const dra7_mmc3_gfclk_div_parents[] __initconst = {
+	"l4per_cm:clk:0120:24",
+	NULL,
+};
+
+static const struct omap_clkctrl_div_data dra7_mmc3_gfclk_div_data __initconst = {
+	.max_div = 4,
+	.flags = CLK_DIVIDER_POWER_OF_TWO,
+};
+
+static const struct omap_clkctrl_bit_data dra7_mmc3_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 25, TI_CLK_DIVIDER, dra7_mmc3_gfclk_div_parents, &dra7_mmc3_gfclk_div_data },
+	{ 0 },
+};
+
+static const char * const dra7_mmc4_gfclk_div_parents[] __initconst = {
+	"l4per_cm:clk:0128:24",
+	NULL,
+};
+
+static const struct omap_clkctrl_div_data dra7_mmc4_gfclk_div_data __initconst = {
+	.max_div = 4,
+	.flags = CLK_DIVIDER_POWER_OF_TWO,
+};
+
+static const struct omap_clkctrl_bit_data dra7_mmc4_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 25, TI_CLK_DIVIDER, dra7_mmc4_gfclk_div_parents, &dra7_mmc4_gfclk_div_data },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer16_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const char * const dra7_qspi_gfclk_mux_parents[] __initconst = {
+	"func_128m_clk",
+	"dpll_per_h13x2_ck",
+	NULL,
+};
+
+static const char * const dra7_qspi_gfclk_div_parents[] __initconst = {
+	"l4per_cm:clk:0138:24",
+	NULL,
+};
+
+static const struct omap_clkctrl_div_data dra7_qspi_gfclk_div_data __initconst = {
+	.max_div = 4,
+	.flags = CLK_DIVIDER_POWER_OF_TWO,
+};
+
+static const struct omap_clkctrl_bit_data dra7_qspi_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_qspi_gfclk_mux_parents, NULL },
+	{ 25, TI_CLK_DIVIDER, dra7_qspi_gfclk_div_parents, &dra7_qspi_gfclk_div_data },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_uart1_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_uart2_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_uart3_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_uart4_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_mcasp2_bit_data[] __initconst = {
+	{ 22, TI_CLK_MUX, dra7_mcasp1_aux_gfclk_mux_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_mcasp1_ahclkx_mux_parents, NULL },
+	{ 28, TI_CLK_MUX, dra7_mcasp1_ahclkx_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_mcasp3_bit_data[] __initconst = {
+	{ 22, TI_CLK_MUX, dra7_mcasp1_aux_gfclk_mux_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_mcasp1_ahclkx_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_uart5_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_mcasp5_bit_data[] __initconst = {
+	{ 22, TI_CLK_MUX, dra7_mcasp1_aux_gfclk_mux_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_mcasp1_ahclkx_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_mcasp8_bit_data[] __initconst = {
+	{ 22, TI_CLK_MUX, dra7_mcasp1_aux_gfclk_mux_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_mcasp1_ahclkx_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_mcasp4_bit_data[] __initconst = {
+	{ 22, TI_CLK_MUX, dra7_mcasp1_aux_gfclk_mux_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_mcasp1_ahclkx_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_uart7_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_uart8_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_uart9_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_mcasp6_bit_data[] __initconst = {
+	{ 22, TI_CLK_MUX, dra7_mcasp1_aux_gfclk_mux_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_mcasp1_ahclkx_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_mcasp7_bit_data[] __initconst = {
+	{ 22, TI_CLK_MUX, dra7_mcasp1_aux_gfclk_mux_parents, NULL },
+	{ 24, TI_CLK_MUX, dra7_mcasp1_ahclkx_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_l4per_clkctrl_regs[] __initconst = {
+	{ DRA7_L4_PER2_CLKCTRL, NULL, 0, "l3_iclk_div", "l4per2_clkdm" },
+	{ DRA7_L4_PER3_CLKCTRL, NULL, 0, "l3_iclk_div", "l4per3_clkdm" },
+	{ DRA7_TIMER10_CLKCTRL, dra7_timer10_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0028:24" },
+	{ DRA7_TIMER11_CLKCTRL, dra7_timer11_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0030:24" },
+	{ DRA7_TIMER2_CLKCTRL, dra7_timer2_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0038:24" },
+	{ DRA7_TIMER3_CLKCTRL, dra7_timer3_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0040:24" },
+	{ DRA7_TIMER4_CLKCTRL, dra7_timer4_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0048:24" },
+	{ DRA7_TIMER9_CLKCTRL, dra7_timer9_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0050:24" },
+	{ DRA7_ELM_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_GPIO2_CLKCTRL, dra7_gpio2_bit_data, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_GPIO3_CLKCTRL, dra7_gpio3_bit_data, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_GPIO4_CLKCTRL, dra7_gpio4_bit_data, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_GPIO5_CLKCTRL, dra7_gpio5_bit_data, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_GPIO6_CLKCTRL, dra7_gpio6_bit_data, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_HDQ1W_CLKCTRL, NULL, CLKF_SW_SUP, "func_12m_fclk" },
+	{ DRA7_EPWMSS1_CLKCTRL, NULL, CLKF_SW_SUP, "l4_root_clk_div", "l4per2_clkdm" },
+	{ DRA7_EPWMSS2_CLKCTRL, NULL, CLKF_SW_SUP, "l4_root_clk_div", "l4per2_clkdm" },
+	{ DRA7_I2C1_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
+	{ DRA7_I2C2_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
+	{ DRA7_I2C3_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
+	{ DRA7_I2C4_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
+	{ DRA7_L4_PER1_CLKCTRL, NULL, 0, "l3_iclk_div" },
+	{ DRA7_EPWMSS0_CLKCTRL, NULL, CLKF_SW_SUP, "l4_root_clk_div", "l4per2_clkdm" },
+	{ DRA7_TIMER13_CLKCTRL, dra7_timer13_bit_data, CLKF_SW_SUP, "l4per_cm:clk:00c8:24", "l4per3_clkdm" },
+	{ DRA7_TIMER14_CLKCTRL, dra7_timer14_bit_data, CLKF_SW_SUP, "l4per_cm:clk:00d0:24", "l4per3_clkdm" },
+	{ DRA7_TIMER15_CLKCTRL, dra7_timer15_bit_data, CLKF_SW_SUP, "l4per_cm:clk:00d8:24", "l4per3_clkdm" },
+	{ DRA7_MCSPI1_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ DRA7_MCSPI2_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ DRA7_MCSPI3_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ DRA7_MCSPI4_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
+	{ DRA7_GPIO7_CLKCTRL, dra7_gpio7_bit_data, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_GPIO8_CLKCTRL, dra7_gpio8_bit_data, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_MMC3_CLKCTRL, dra7_mmc3_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0120:25" },
+	{ DRA7_MMC4_CLKCTRL, dra7_mmc4_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0128:25" },
+	{ DRA7_TIMER16_CLKCTRL, dra7_timer16_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0130:24", "l4per3_clkdm" },
+	{ DRA7_QSPI_CLKCTRL, dra7_qspi_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0138:25", "l4per2_clkdm" },
+	{ DRA7_UART1_CLKCTRL, dra7_uart1_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0140:24" },
+	{ DRA7_UART2_CLKCTRL, dra7_uart2_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0148:24" },
+	{ DRA7_UART3_CLKCTRL, dra7_uart3_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0150:24" },
+	{ DRA7_UART4_CLKCTRL, dra7_uart4_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0158:24" },
+	{ DRA7_MCASP2_CLKCTRL, dra7_mcasp2_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0160:22", "l4per2_clkdm" },
+	{ DRA7_MCASP3_CLKCTRL, dra7_mcasp3_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0168:22", "l4per2_clkdm" },
+	{ DRA7_UART5_CLKCTRL, dra7_uart5_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0170:24" },
+	{ DRA7_MCASP5_CLKCTRL, dra7_mcasp5_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0178:22", "l4per2_clkdm" },
+	{ DRA7_MCASP8_CLKCTRL, dra7_mcasp8_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0190:24", "l4per2_clkdm" },
+	{ DRA7_MCASP4_CLKCTRL, dra7_mcasp4_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0198:22", "l4per2_clkdm" },
+	{ DRA7_AES1_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div", "l4sec_clkdm" },
+	{ DRA7_AES2_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div", "l4sec_clkdm" },
+	{ DRA7_DES_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div", "l4sec_clkdm" },
+	{ DRA7_RNG_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div", "l4sec_clkdm" },
+	{ DRA7_SHAM_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div", "l4sec_clkdm" },
+	{ DRA7_UART7_CLKCTRL, dra7_uart7_bit_data, CLKF_SW_SUP, "l4per_cm:clk:01d0:24", "l4per2_clkdm" },
+	{ DRA7_UART8_CLKCTRL, dra7_uart8_bit_data, CLKF_SW_SUP, "l4per_cm:clk:01e0:24", "l4per2_clkdm" },
+	{ DRA7_UART9_CLKCTRL, dra7_uart9_bit_data, CLKF_SW_SUP, "l4per_cm:clk:01e8:24", "l4per2_clkdm" },
+	{ DRA7_DCAN2_CLKCTRL, NULL, CLKF_SW_SUP, "sys_clkin1", "l4per2_clkdm" },
+	{ DRA7_MCASP6_CLKCTRL, dra7_mcasp6_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0204:22", "l4per2_clkdm" },
+	{ DRA7_MCASP7_CLKCTRL, dra7_mcasp7_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0208:22", "l4per2_clkdm" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_gpio1_bit_data[] __initconst = {
+	{ 8, TI_CLK_GATE, dra7_dss_32khz_clk_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_timer1_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_timer10_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_bit_data dra7_uart10_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_uart6_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const char * const dra7_dcan1_sys_clk_mux_parents[] __initconst = {
+	"sys_clkin1",
+	"sys_clkin2",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_dcan1_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_dcan1_sys_clk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_wkupaon_clkctrl_regs[] __initconst = {
+	{ DRA7_L4_WKUP_CLKCTRL, NULL, 0, "wkupaon_iclk_mux" },
+	{ DRA7_WD_TIMER2_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
+	{ DRA7_GPIO1_CLKCTRL, dra7_gpio1_bit_data, CLKF_HW_SUP, "wkupaon_iclk_mux" },
+	{ DRA7_TIMER1_CLKCTRL, dra7_timer1_bit_data, CLKF_SW_SUP, "wkupaon_cm:clk:0020:24" },
+	{ DRA7_TIMER12_CLKCTRL, NULL, 0, "secure_32k_clk_src_ck" },
+	{ DRA7_COUNTER_32K_CLKCTRL, NULL, 0, "wkupaon_iclk_mux" },
+	{ DRA7_UART10_CLKCTRL, dra7_uart10_bit_data, CLKF_SW_SUP, "wkupaon_cm:clk:0060:24" },
+	{ DRA7_DCAN1_CLKCTRL, dra7_dcan1_bit_data, CLKF_SW_SUP, "wkupaon_cm:clk:0068:24" },
+	{ 0 },
+};
+
+const struct omap_clkctrl_data dra7_clkctrl_data[] __initconst = {
+	{ 0x4a005320, dra7_mpu_clkctrl_regs },
+	{ 0x4a005540, dra7_ipu_clkctrl_regs },
+	{ 0x4a005740, dra7_rtc_clkctrl_regs },
+	{ 0x4a008620, dra7_coreaon_clkctrl_regs },
+	{ 0x4a008720, dra7_l3main1_clkctrl_regs },
+	{ 0x4a008a20, dra7_dma_clkctrl_regs },
+	{ 0x4a008b20, dra7_emif_clkctrl_regs },
+	{ 0x4a008c00, dra7_atl_clkctrl_regs },
+	{ 0x4a008d20, dra7_l4cfg_clkctrl_regs },
+	{ 0x4a008e20, dra7_l3instr_clkctrl_regs },
+	{ 0x4a009120, dra7_dss_clkctrl_regs },
+	{ 0x4a009320, dra7_l3init_clkctrl_regs },
+	{ 0x4a009700, dra7_l4per_clkctrl_regs },
+	{ 0x4ae07820, dra7_wkupaon_clkctrl_regs },
+	{ 0 },
+};
+
 static struct ti_dt_clk dra7xx_clks[] = {
-	DT_CLK(NULL, "atl_clkin0_ck", "atl_clkin0_ck"),
-	DT_CLK(NULL, "atl_clkin1_ck", "atl_clkin1_ck"),
-	DT_CLK(NULL, "atl_clkin2_ck", "atl_clkin2_ck"),
-	DT_CLK(NULL, "atl_clkin3_ck", "atl_clkin3_ck"),
-	DT_CLK(NULL, "hdmi_clkin_ck", "hdmi_clkin_ck"),
-	DT_CLK(NULL, "mlb_clkin_ck", "mlb_clkin_ck"),
-	DT_CLK(NULL, "mlbp_clkin_ck", "mlbp_clkin_ck"),
-	DT_CLK(NULL, "pciesref_acs_clk_ck", "pciesref_acs_clk_ck"),
-	DT_CLK(NULL, "ref_clkin0_ck", "ref_clkin0_ck"),
-	DT_CLK(NULL, "ref_clkin1_ck", "ref_clkin1_ck"),
-	DT_CLK(NULL, "ref_clkin2_ck", "ref_clkin2_ck"),
-	DT_CLK(NULL, "ref_clkin3_ck", "ref_clkin3_ck"),
-	DT_CLK(NULL, "rmii_clk_ck", "rmii_clk_ck"),
-	DT_CLK(NULL, "sdvenc_clkin_ck", "sdvenc_clkin_ck"),
-	DT_CLK(NULL, "secure_32k_clk_src_ck", "secure_32k_clk_src_ck"),
-	DT_CLK(NULL, "sys_32k_ck", "sys_32k_ck"),
-	DT_CLK(NULL, "virt_12000000_ck", "virt_12000000_ck"),
-	DT_CLK(NULL, "virt_13000000_ck", "virt_13000000_ck"),
-	DT_CLK(NULL, "virt_16800000_ck", "virt_16800000_ck"),
-	DT_CLK(NULL, "virt_19200000_ck", "virt_19200000_ck"),
-	DT_CLK(NULL, "virt_20000000_ck", "virt_20000000_ck"),
-	DT_CLK(NULL, "virt_26000000_ck", "virt_26000000_ck"),
-	DT_CLK(NULL, "virt_27000000_ck", "virt_27000000_ck"),
-	DT_CLK(NULL, "virt_38400000_ck", "virt_38400000_ck"),
-	DT_CLK(NULL, "sys_clkin1", "sys_clkin1"),
-	DT_CLK(NULL, "sys_clkin2", "sys_clkin2"),
-	DT_CLK(NULL, "usb_otg_clkin_ck", "usb_otg_clkin_ck"),
-	DT_CLK(NULL, "video1_clkin_ck", "video1_clkin_ck"),
-	DT_CLK(NULL, "video1_m2_clkin_ck", "video1_m2_clkin_ck"),
-	DT_CLK(NULL, "video2_clkin_ck", "video2_clkin_ck"),
-	DT_CLK(NULL, "video2_m2_clkin_ck", "video2_m2_clkin_ck"),
-	DT_CLK(NULL, "abe_dpll_sys_clk_mux", "abe_dpll_sys_clk_mux"),
-	DT_CLK(NULL, "abe_dpll_bypass_clk_mux", "abe_dpll_bypass_clk_mux"),
-	DT_CLK(NULL, "abe_dpll_clk_mux", "abe_dpll_clk_mux"),
-	DT_CLK(NULL, "dpll_abe_ck", "dpll_abe_ck"),
-	DT_CLK(NULL, "dpll_abe_x2_ck", "dpll_abe_x2_ck"),
-	DT_CLK(NULL, "dpll_abe_m2x2_ck", "dpll_abe_m2x2_ck"),
-	DT_CLK(NULL, "abe_24m_fclk", "abe_24m_fclk"),
-	DT_CLK(NULL, "abe_clk", "abe_clk"),
-	DT_CLK(NULL, "aess_fclk", "aess_fclk"),
-	DT_CLK(NULL, "abe_giclk_div", "abe_giclk_div"),
-	DT_CLK(NULL, "abe_lp_clk_div", "abe_lp_clk_div"),
-	DT_CLK(NULL, "abe_sys_clk_div", "abe_sys_clk_div"),
-	DT_CLK(NULL, "adc_gfclk_mux", "adc_gfclk_mux"),
-	DT_CLK(NULL, "dpll_pcie_ref_ck", "dpll_pcie_ref_ck"),
-	DT_CLK(NULL, "dpll_pcie_ref_m2ldo_ck", "dpll_pcie_ref_m2ldo_ck"),
-	DT_CLK(NULL, "apll_pcie_ck", "apll_pcie_ck"),
-	DT_CLK(NULL, "apll_pcie_clkvcoldo", "apll_pcie_clkvcoldo"),
-	DT_CLK(NULL, "apll_pcie_clkvcoldo_div", "apll_pcie_clkvcoldo_div"),
-	DT_CLK(NULL, "apll_pcie_m2_ck", "apll_pcie_m2_ck"),
-	DT_CLK(NULL, "sys_clk1_dclk_div", "sys_clk1_dclk_div"),
-	DT_CLK(NULL, "sys_clk2_dclk_div", "sys_clk2_dclk_div"),
-	DT_CLK(NULL, "dpll_abe_m2_ck", "dpll_abe_m2_ck"),
-	DT_CLK(NULL, "per_abe_x1_dclk_div", "per_abe_x1_dclk_div"),
-	DT_CLK(NULL, "dpll_abe_m3x2_ck", "dpll_abe_m3x2_ck"),
-	DT_CLK(NULL, "dpll_core_ck", "dpll_core_ck"),
-	DT_CLK(NULL, "dpll_core_x2_ck", "dpll_core_x2_ck"),
-	DT_CLK(NULL, "dpll_core_h12x2_ck", "dpll_core_h12x2_ck"),
-	DT_CLK(NULL, "mpu_dpll_hs_clk_div", "mpu_dpll_hs_clk_div"),
-	DT_CLK(NULL, "dpll_mpu_ck", "dpll_mpu_ck"),
-	DT_CLK(NULL, "dpll_mpu_m2_ck", "dpll_mpu_m2_ck"),
-	DT_CLK(NULL, "mpu_dclk_div", "mpu_dclk_div"),
-	DT_CLK(NULL, "dsp_dpll_hs_clk_div", "dsp_dpll_hs_clk_div"),
-	DT_CLK(NULL, "dpll_dsp_ck", "dpll_dsp_ck"),
-	DT_CLK(NULL, "dpll_dsp_m2_ck", "dpll_dsp_m2_ck"),
-	DT_CLK(NULL, "dsp_gclk_div", "dsp_gclk_div"),
-	DT_CLK(NULL, "iva_dpll_hs_clk_div", "iva_dpll_hs_clk_div"),
-	DT_CLK(NULL, "dpll_iva_ck", "dpll_iva_ck"),
-	DT_CLK(NULL, "dpll_iva_m2_ck", "dpll_iva_m2_ck"),
-	DT_CLK(NULL, "iva_dclk", "iva_dclk"),
-	DT_CLK(NULL, "dpll_gpu_ck", "dpll_gpu_ck"),
-	DT_CLK(NULL, "dpll_gpu_m2_ck", "dpll_gpu_m2_ck"),
-	DT_CLK(NULL, "gpu_dclk", "gpu_dclk"),
-	DT_CLK(NULL, "dpll_core_m2_ck", "dpll_core_m2_ck"),
-	DT_CLK(NULL, "core_dpll_out_dclk_div", "core_dpll_out_dclk_div"),
-	DT_CLK(NULL, "dpll_ddr_ck", "dpll_ddr_ck"),
-	DT_CLK(NULL, "dpll_ddr_m2_ck", "dpll_ddr_m2_ck"),
-	DT_CLK(NULL, "emif_phy_dclk_div", "emif_phy_dclk_div"),
-	DT_CLK(NULL, "dpll_gmac_ck", "dpll_gmac_ck"),
-	DT_CLK(NULL, "dpll_gmac_m2_ck", "dpll_gmac_m2_ck"),
-	DT_CLK(NULL, "gmac_250m_dclk_div", "gmac_250m_dclk_div"),
-	DT_CLK(NULL, "video2_dclk_div", "video2_dclk_div"),
-	DT_CLK(NULL, "video1_dclk_div", "video1_dclk_div"),
-	DT_CLK(NULL, "hdmi_dclk_div", "hdmi_dclk_div"),
-	DT_CLK(NULL, "per_dpll_hs_clk_div", "per_dpll_hs_clk_div"),
-	DT_CLK(NULL, "dpll_per_ck", "dpll_per_ck"),
-	DT_CLK(NULL, "dpll_per_m2_ck", "dpll_per_m2_ck"),
-	DT_CLK(NULL, "func_96m_aon_dclk_div", "func_96m_aon_dclk_div"),
-	DT_CLK(NULL, "usb_dpll_hs_clk_div", "usb_dpll_hs_clk_div"),
-	DT_CLK(NULL, "dpll_usb_ck", "dpll_usb_ck"),
-	DT_CLK(NULL, "dpll_usb_m2_ck", "dpll_usb_m2_ck"),
-	DT_CLK(NULL, "l3init_480m_dclk_div", "l3init_480m_dclk_div"),
-	DT_CLK(NULL, "usb_otg_dclk_div", "usb_otg_dclk_div"),
-	DT_CLK(NULL, "sata_dclk_div", "sata_dclk_div"),
-	DT_CLK(NULL, "dpll_pcie_ref_m2_ck", "dpll_pcie_ref_m2_ck"),
-	DT_CLK(NULL, "pcie2_dclk_div", "pcie2_dclk_div"),
-	DT_CLK(NULL, "pcie_dclk_div", "pcie_dclk_div"),
-	DT_CLK(NULL, "emu_dclk_div", "emu_dclk_div"),
-	DT_CLK(NULL, "secure_32k_dclk_div", "secure_32k_dclk_div"),
-	DT_CLK(NULL, "eve_dpll_hs_clk_div", "eve_dpll_hs_clk_div"),
-	DT_CLK(NULL, "dpll_eve_ck", "dpll_eve_ck"),
-	DT_CLK(NULL, "dpll_eve_m2_ck", "dpll_eve_m2_ck"),
-	DT_CLK(NULL, "eve_dclk_div", "eve_dclk_div"),
-	DT_CLK(NULL, "clkoutmux0_clk_mux", "clkoutmux0_clk_mux"),
-	DT_CLK(NULL, "clkoutmux1_clk_mux", "clkoutmux1_clk_mux"),
-	DT_CLK(NULL, "clkoutmux2_clk_mux", "clkoutmux2_clk_mux"),
-	DT_CLK(NULL, "custefuse_sys_gfclk_div", "custefuse_sys_gfclk_div"),
-	DT_CLK(NULL, "dpll_core_h13x2_ck", "dpll_core_h13x2_ck"),
-	DT_CLK(NULL, "dpll_core_h14x2_ck", "dpll_core_h14x2_ck"),
-	DT_CLK(NULL, "dpll_core_h22x2_ck", "dpll_core_h22x2_ck"),
-	DT_CLK(NULL, "dpll_core_h23x2_ck", "dpll_core_h23x2_ck"),
-	DT_CLK(NULL, "dpll_core_h24x2_ck", "dpll_core_h24x2_ck"),
-	DT_CLK(NULL, "dpll_ddr_x2_ck", "dpll_ddr_x2_ck"),
-	DT_CLK(NULL, "dpll_ddr_h11x2_ck", "dpll_ddr_h11x2_ck"),
-	DT_CLK(NULL, "dpll_dsp_x2_ck", "dpll_dsp_x2_ck"),
-	DT_CLK(NULL, "dpll_dsp_m3x2_ck", "dpll_dsp_m3x2_ck"),
-	DT_CLK(NULL, "dpll_gmac_x2_ck", "dpll_gmac_x2_ck"),
-	DT_CLK(NULL, "dpll_gmac_h11x2_ck", "dpll_gmac_h11x2_ck"),
-	DT_CLK(NULL, "dpll_gmac_h12x2_ck", "dpll_gmac_h12x2_ck"),
-	DT_CLK(NULL, "dpll_gmac_h13x2_ck", "dpll_gmac_h13x2_ck"),
-	DT_CLK(NULL, "dpll_gmac_m3x2_ck", "dpll_gmac_m3x2_ck"),
-	DT_CLK(NULL, "dpll_per_x2_ck", "dpll_per_x2_ck"),
-	DT_CLK(NULL, "dpll_per_h11x2_ck", "dpll_per_h11x2_ck"),
-	DT_CLK(NULL, "dpll_per_h12x2_ck", "dpll_per_h12x2_ck"),
-	DT_CLK(NULL, "dpll_per_h13x2_ck", "dpll_per_h13x2_ck"),
-	DT_CLK(NULL, "dpll_per_h14x2_ck", "dpll_per_h14x2_ck"),
-	DT_CLK(NULL, "dpll_per_m2x2_ck", "dpll_per_m2x2_ck"),
-	DT_CLK(NULL, "dpll_usb_clkdcoldo", "dpll_usb_clkdcoldo"),
-	DT_CLK(NULL, "eve_clk", "eve_clk"),
-	DT_CLK(NULL, "func_128m_clk", "func_128m_clk"),
-	DT_CLK(NULL, "func_12m_fclk", "func_12m_fclk"),
-	DT_CLK(NULL, "func_24m_clk", "func_24m_clk"),
-	DT_CLK(NULL, "func_48m_fclk", "func_48m_fclk"),
-	DT_CLK(NULL, "func_96m_fclk", "func_96m_fclk"),
-	DT_CLK(NULL, "gmii_m_clk_div", "gmii_m_clk_div"),
-	DT_CLK(NULL, "hdmi_clk2_div", "hdmi_clk2_div"),
-	DT_CLK(NULL, "hdmi_div_clk", "hdmi_div_clk"),
-	DT_CLK(NULL, "hdmi_dpll_clk_mux", "hdmi_dpll_clk_mux"),
-	DT_CLK(NULL, "l3_iclk_div", "l3_iclk_div"),
-	DT_CLK(NULL, "l3init_60m_fclk", "l3init_60m_fclk"),
-	DT_CLK(NULL, "l4_root_clk_div", "l4_root_clk_div"),
-	DT_CLK(NULL, "mlb_clk", "mlb_clk"),
-	DT_CLK(NULL, "mlbp_clk", "mlbp_clk"),
-	DT_CLK(NULL, "per_abe_x1_gfclk2_div", "per_abe_x1_gfclk2_div"),
-	DT_CLK(NULL, "timer_sys_clk_div", "timer_sys_clk_div"),
-	DT_CLK(NULL, "video1_clk2_div", "video1_clk2_div"),
-	DT_CLK(NULL, "video1_div_clk", "video1_div_clk"),
-	DT_CLK(NULL, "video1_dpll_clk_mux", "video1_dpll_clk_mux"),
-	DT_CLK(NULL, "video2_clk2_div", "video2_clk2_div"),
-	DT_CLK(NULL, "video2_div_clk", "video2_div_clk"),
-	DT_CLK(NULL, "video2_dpll_clk_mux", "video2_dpll_clk_mux"),
-	DT_CLK(NULL, "wkupaon_iclk_mux", "wkupaon_iclk_mux"),
-	DT_CLK(NULL, "dss_32khz_clk", "dss_32khz_clk"),
-	DT_CLK(NULL, "dss_48mhz_clk", "dss_48mhz_clk"),
-	DT_CLK(NULL, "dss_dss_clk", "dss_dss_clk"),
-	DT_CLK(NULL, "dss_hdmi_clk", "dss_hdmi_clk"),
-	DT_CLK(NULL, "dss_video1_clk", "dss_video1_clk"),
-	DT_CLK(NULL, "dss_video2_clk", "dss_video2_clk"),
-	DT_CLK(NULL, "gpio1_dbclk", "gpio1_dbclk"),
-	DT_CLK(NULL, "gpio2_dbclk", "gpio2_dbclk"),
-	DT_CLK(NULL, "gpio3_dbclk", "gpio3_dbclk"),
-	DT_CLK(NULL, "gpio4_dbclk", "gpio4_dbclk"),
-	DT_CLK(NULL, "gpio5_dbclk", "gpio5_dbclk"),
-	DT_CLK(NULL, "gpio6_dbclk", "gpio6_dbclk"),
-	DT_CLK(NULL, "gpio7_dbclk", "gpio7_dbclk"),
-	DT_CLK(NULL, "gpio8_dbclk", "gpio8_dbclk"),
-	DT_CLK(NULL, "mmc1_clk32k", "mmc1_clk32k"),
-	DT_CLK(NULL, "mmc2_clk32k", "mmc2_clk32k"),
-	DT_CLK(NULL, "mmc3_clk32k", "mmc3_clk32k"),
-	DT_CLK(NULL, "mmc4_clk32k", "mmc4_clk32k"),
-	DT_CLK(NULL, "sata_ref_clk", "sata_ref_clk"),
-	DT_CLK(NULL, "usb_otg_ss1_refclk960m", "usb_otg_ss1_refclk960m"),
-	DT_CLK(NULL, "usb_otg_ss2_refclk960m", "usb_otg_ss2_refclk960m"),
-	DT_CLK(NULL, "usb_phy1_always_on_clk32k", "usb_phy1_always_on_clk32k"),
-	DT_CLK(NULL, "usb_phy2_always_on_clk32k", "usb_phy2_always_on_clk32k"),
-	DT_CLK(NULL, "usb_phy3_always_on_clk32k", "usb_phy3_always_on_clk32k"),
-	DT_CLK(NULL, "atl_dpll_clk_mux", "atl_dpll_clk_mux"),
-	DT_CLK(NULL, "atl_gfclk_mux", "atl_gfclk_mux"),
-	DT_CLK(NULL, "dcan1_sys_clk_mux", "dcan1_sys_clk_mux"),
-	DT_CLK(NULL, "gmac_rft_clk_mux", "gmac_rft_clk_mux"),
-	DT_CLK(NULL, "gpu_core_gclk_mux", "gpu_core_gclk_mux"),
-	DT_CLK(NULL, "gpu_hyd_gclk_mux", "gpu_hyd_gclk_mux"),
-	DT_CLK(NULL, "ipu1_gfclk_mux", "ipu1_gfclk_mux"),
-	DT_CLK(NULL, "l3instr_ts_gclk_div", "l3instr_ts_gclk_div"),
-	DT_CLK(NULL, "mcasp1_ahclkr_mux", "mcasp1_ahclkr_mux"),
-	DT_CLK(NULL, "mcasp1_ahclkx_mux", "mcasp1_ahclkx_mux"),
-	DT_CLK(NULL, "mcasp1_aux_gfclk_mux", "mcasp1_aux_gfclk_mux"),
-	DT_CLK(NULL, "mcasp2_ahclkr_mux", "mcasp2_ahclkr_mux"),
-	DT_CLK(NULL, "mcasp2_ahclkx_mux", "mcasp2_ahclkx_mux"),
-	DT_CLK(NULL, "mcasp2_aux_gfclk_mux", "mcasp2_aux_gfclk_mux"),
-	DT_CLK(NULL, "mcasp3_ahclkx_mux", "mcasp3_ahclkx_mux"),
-	DT_CLK(NULL, "mcasp3_aux_gfclk_mux", "mcasp3_aux_gfclk_mux"),
-	DT_CLK(NULL, "mcasp4_ahclkx_mux", "mcasp4_ahclkx_mux"),
-	DT_CLK(NULL, "mcasp4_aux_gfclk_mux", "mcasp4_aux_gfclk_mux"),
-	DT_CLK(NULL, "mcasp5_ahclkx_mux", "mcasp5_ahclkx_mux"),
-	DT_CLK(NULL, "mcasp5_aux_gfclk_mux", "mcasp5_aux_gfclk_mux"),
-	DT_CLK(NULL, "mcasp6_ahclkx_mux", "mcasp6_ahclkx_mux"),
-	DT_CLK(NULL, "mcasp6_aux_gfclk_mux", "mcasp6_aux_gfclk_mux"),
-	DT_CLK(NULL, "mcasp7_ahclkx_mux", "mcasp7_ahclkx_mux"),
-	DT_CLK(NULL, "mcasp7_aux_gfclk_mux", "mcasp7_aux_gfclk_mux"),
-	DT_CLK(NULL, "mcasp8_ahclkx_mux", "mcasp8_ahclkx_mux"),
-	DT_CLK(NULL, "mcasp8_aux_gfclk_mux", "mcasp8_aux_gfclk_mux"),
-	DT_CLK(NULL, "mmc1_fclk_mux", "mmc1_fclk_mux"),
-	DT_CLK(NULL, "mmc1_fclk_div", "mmc1_fclk_div"),
-	DT_CLK(NULL, "mmc2_fclk_mux", "mmc2_fclk_mux"),
-	DT_CLK(NULL, "mmc2_fclk_div", "mmc2_fclk_div"),
-	DT_CLK(NULL, "mmc3_gfclk_mux", "mmc3_gfclk_mux"),
-	DT_CLK(NULL, "mmc3_gfclk_div", "mmc3_gfclk_div"),
-	DT_CLK(NULL, "mmc4_gfclk_mux", "mmc4_gfclk_mux"),
-	DT_CLK(NULL, "mmc4_gfclk_div", "mmc4_gfclk_div"),
-	DT_CLK(NULL, "qspi_gfclk_mux", "qspi_gfclk_mux"),
-	DT_CLK(NULL, "qspi_gfclk_div", "qspi_gfclk_div"),
-	DT_CLK(NULL, "timer10_gfclk_mux", "timer10_gfclk_mux"),
-	DT_CLK(NULL, "timer11_gfclk_mux", "timer11_gfclk_mux"),
-	DT_CLK(NULL, "timer13_gfclk_mux", "timer13_gfclk_mux"),
-	DT_CLK(NULL, "timer14_gfclk_mux", "timer14_gfclk_mux"),
-	DT_CLK(NULL, "timer15_gfclk_mux", "timer15_gfclk_mux"),
-	DT_CLK(NULL, "timer16_gfclk_mux", "timer16_gfclk_mux"),
-	DT_CLK(NULL, "timer1_gfclk_mux", "timer1_gfclk_mux"),
-	DT_CLK(NULL, "timer2_gfclk_mux", "timer2_gfclk_mux"),
-	DT_CLK(NULL, "timer3_gfclk_mux", "timer3_gfclk_mux"),
-	DT_CLK(NULL, "timer4_gfclk_mux", "timer4_gfclk_mux"),
-	DT_CLK(NULL, "timer5_gfclk_mux", "timer5_gfclk_mux"),
-	DT_CLK(NULL, "timer6_gfclk_mux", "timer6_gfclk_mux"),
-	DT_CLK(NULL, "timer7_gfclk_mux", "timer7_gfclk_mux"),
-	DT_CLK(NULL, "timer8_gfclk_mux", "timer8_gfclk_mux"),
-	DT_CLK(NULL, "timer9_gfclk_mux", "timer9_gfclk_mux"),
-	DT_CLK(NULL, "uart10_gfclk_mux", "uart10_gfclk_mux"),
-	DT_CLK(NULL, "uart1_gfclk_mux", "uart1_gfclk_mux"),
-	DT_CLK(NULL, "uart2_gfclk_mux", "uart2_gfclk_mux"),
-	DT_CLK(NULL, "uart3_gfclk_mux", "uart3_gfclk_mux"),
-	DT_CLK(NULL, "uart4_gfclk_mux", "uart4_gfclk_mux"),
-	DT_CLK(NULL, "uart5_gfclk_mux", "uart5_gfclk_mux"),
-	DT_CLK(NULL, "uart6_gfclk_mux", "uart6_gfclk_mux"),
-	DT_CLK(NULL, "uart7_gfclk_mux", "uart7_gfclk_mux"),
-	DT_CLK(NULL, "uart8_gfclk_mux", "uart8_gfclk_mux"),
-	DT_CLK(NULL, "uart9_gfclk_mux", "uart9_gfclk_mux"),
-	DT_CLK(NULL, "vip1_gclk_mux", "vip1_gclk_mux"),
-	DT_CLK(NULL, "vip2_gclk_mux", "vip2_gclk_mux"),
-	DT_CLK(NULL, "vip3_gclk_mux", "vip3_gclk_mux"),
-	DT_CLK("omap_i2c.1", "ick", "dummy_ck"),
-	DT_CLK("omap_i2c.2", "ick", "dummy_ck"),
-	DT_CLK("omap_i2c.3", "ick", "dummy_ck"),
-	DT_CLK("omap_i2c.4", "ick", "dummy_ck"),
-	DT_CLK(NULL, "mailboxes_ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.0", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.1", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.2", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.3", "ick", "dummy_ck"),
-	DT_CLK("omap_hsmmc.4", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.1", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.2", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.3", "ick", "dummy_ck"),
-	DT_CLK("omap-mcbsp.4", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.1", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.2", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.3", "ick", "dummy_ck"),
-	DT_CLK("omap2_mcspi.4", "ick", "dummy_ck"),
-	DT_CLK(NULL, "uart1_ick", "dummy_ck"),
-	DT_CLK(NULL, "uart2_ick", "dummy_ck"),
-	DT_CLK(NULL, "uart3_ick", "dummy_ck"),
-	DT_CLK(NULL, "uart4_ick", "dummy_ck"),
-	DT_CLK("usbhs_omap", "usbhost_ick", "dummy_ck"),
-	DT_CLK("usbhs_omap", "usbtll_fck", "dummy_ck"),
-	DT_CLK("omap_wdt", "ick", "dummy_ck"),
 	DT_CLK(NULL, "timer_32k_ck", "sys_32k_ck"),
 	DT_CLK(NULL, "sys_clkin_ck", "timer_sys_clk_div"),
-	DT_CLK("4ae18000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("48032000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("48034000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("48036000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("4803e000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("48086000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("48088000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("48820000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("48822000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("48824000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("48826000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("48828000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("4882a000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("4882c000.timer", "timer_sys_ck", "timer_sys_clk_div"),
-	DT_CLK("4882e000.timer", "timer_sys_ck", "timer_sys_clk_div"),
 	DT_CLK(NULL, "sys_clkin", "sys_clkin1"),
-	DT_CLK(NULL, "dss_deshdcp_clk", "dss_deshdcp_clk"),
+	DT_CLK(NULL, "atl_dpll_clk_mux", "atl_cm:0000:24"),
+	DT_CLK(NULL, "atl_gfclk_mux", "atl_cm:0000:26"),
+	DT_CLK(NULL, "dcan1_sys_clk_mux", "wkupaon_cm:0068:24"),
+	DT_CLK(NULL, "dss_32khz_clk", "dss_cm:0000:11"),
+	DT_CLK(NULL, "dss_48mhz_clk", "dss_cm:0000:9"),
+	DT_CLK(NULL, "dss_dss_clk", "dss_cm:0000:8"),
+	DT_CLK(NULL, "dss_hdmi_clk", "dss_cm:0000:10"),
+	DT_CLK(NULL, "dss_video1_clk", "dss_cm:0000:12"),
+	DT_CLK(NULL, "dss_video2_clk", "dss_cm:0000:13"),
+	DT_CLK(NULL, "gmac_rft_clk_mux", "l3init_cm:00b0:25"),
+	DT_CLK(NULL, "gpio1_dbclk", "wkupaon_cm:0018:8"),
+	DT_CLK(NULL, "gpio2_dbclk", "l4per_cm:0060:8"),
+	DT_CLK(NULL, "gpio3_dbclk", "l4per_cm:0068:8"),
+	DT_CLK(NULL, "gpio4_dbclk", "l4per_cm:0070:8"),
+	DT_CLK(NULL, "gpio5_dbclk", "l4per_cm:0078:8"),
+	DT_CLK(NULL, "gpio6_dbclk", "l4per_cm:0080:8"),
+	DT_CLK(NULL, "gpio7_dbclk", "l4per_cm:0110:8"),
+	DT_CLK(NULL, "gpio8_dbclk", "l4per_cm:0118:8"),
+	DT_CLK(NULL, "mcasp1_ahclkr_mux", "ipu_cm:0010:28"),
+	DT_CLK(NULL, "mcasp1_ahclkx_mux", "ipu_cm:0010:24"),
+	DT_CLK(NULL, "mcasp1_aux_gfclk_mux", "ipu_cm:0010:22"),
+	DT_CLK(NULL, "mcasp2_ahclkr_mux", "l4per_cm:0160:28"),
+	DT_CLK(NULL, "mcasp2_ahclkx_mux", "l4per_cm:0160:24"),
+	DT_CLK(NULL, "mcasp2_aux_gfclk_mux", "l4per_cm:0160:22"),
+	DT_CLK(NULL, "mcasp3_ahclkx_mux", "l4per_cm:0168:24"),
+	DT_CLK(NULL, "mcasp3_aux_gfclk_mux", "l4per_cm:0168:22"),
+	DT_CLK(NULL, "mcasp4_ahclkx_mux", "l4per_cm:0198:24"),
+	DT_CLK(NULL, "mcasp4_aux_gfclk_mux", "l4per_cm:0198:22"),
+	DT_CLK(NULL, "mcasp5_ahclkx_mux", "l4per_cm:0178:24"),
+	DT_CLK(NULL, "mcasp5_aux_gfclk_mux", "l4per_cm:0178:22"),
+	DT_CLK(NULL, "mcasp6_ahclkx_mux", "l4per_cm:0204:24"),
+	DT_CLK(NULL, "mcasp6_aux_gfclk_mux", "l4per_cm:0204:22"),
+	DT_CLK(NULL, "mcasp7_ahclkx_mux", "l4per_cm:0208:24"),
+	DT_CLK(NULL, "mcasp7_aux_gfclk_mux", "l4per_cm:0208:22"),
+	DT_CLK(NULL, "mcasp8_ahclkx_mux", "l4per_cm:0190:22"),
+	DT_CLK(NULL, "mcasp8_aux_gfclk_mux", "l4per_cm:0190:24"),
+	DT_CLK(NULL, "mmc1_clk32k", "l3init_cm:0008:8"),
+	DT_CLK(NULL, "mmc1_fclk_div", "l3init_cm:0008:25"),
+	DT_CLK(NULL, "mmc1_fclk_mux", "l3init_cm:0008:24"),
+	DT_CLK(NULL, "mmc2_clk32k", "l3init_cm:0010:8"),
+	DT_CLK(NULL, "mmc2_fclk_div", "l3init_cm:0010:25"),
+	DT_CLK(NULL, "mmc2_fclk_mux", "l3init_cm:0010:24"),
+	DT_CLK(NULL, "mmc3_clk32k", "l4per_cm:0120:8"),
+	DT_CLK(NULL, "mmc3_gfclk_div", "l4per_cm:0120:25"),
+	DT_CLK(NULL, "mmc3_gfclk_mux", "l4per_cm:0120:24"),
+	DT_CLK(NULL, "mmc4_clk32k", "l4per_cm:0128:8"),
+	DT_CLK(NULL, "mmc4_gfclk_div", "l4per_cm:0128:25"),
+	DT_CLK(NULL, "mmc4_gfclk_mux", "l4per_cm:0128:24"),
+	DT_CLK(NULL, "optfclk_pciephy1_32khz", "l3init_cm:0090:8"),
+	DT_CLK(NULL, "optfclk_pciephy1_clk", "l3init_cm:0090:9"),
+	DT_CLK(NULL, "optfclk_pciephy1_div_clk", "l3init_cm:0090:10"),
+	DT_CLK(NULL, "optfclk_pciephy2_32khz", "l3init_cm:0098:8"),
+	DT_CLK(NULL, "optfclk_pciephy2_clk", "l3init_cm:0098:9"),
+	DT_CLK(NULL, "optfclk_pciephy2_div_clk", "l3init_cm:0098:10"),
+	DT_CLK(NULL, "qspi_gfclk_div", "l4per_cm:0138:25"),
+	DT_CLK(NULL, "qspi_gfclk_mux", "l4per_cm:0138:24"),
+	DT_CLK(NULL, "rmii_50mhz_clk_mux", "l3init_cm:00b0:24"),
+	DT_CLK(NULL, "sata_ref_clk", "l3init_cm:0068:8"),
+	DT_CLK(NULL, "timer10_gfclk_mux", "l4per_cm:0028:24"),
+	DT_CLK(NULL, "timer11_gfclk_mux", "l4per_cm:0030:24"),
+	DT_CLK(NULL, "timer13_gfclk_mux", "l4per_cm:00c8:24"),
+	DT_CLK(NULL, "timer14_gfclk_mux", "l4per_cm:00d0:24"),
+	DT_CLK(NULL, "timer15_gfclk_mux", "l4per_cm:00d8:24"),
+	DT_CLK(NULL, "timer16_gfclk_mux", "l4per_cm:0130:24"),
+	DT_CLK(NULL, "timer1_gfclk_mux", "wkupaon_cm:0020:24"),
+	DT_CLK(NULL, "timer2_gfclk_mux", "l4per_cm:0038:24"),
+	DT_CLK(NULL, "timer3_gfclk_mux", "l4per_cm:0040:24"),
+	DT_CLK(NULL, "timer4_gfclk_mux", "l4per_cm:0048:24"),
+	DT_CLK(NULL, "timer5_gfclk_mux", "ipu_cm:0018:24"),
+	DT_CLK(NULL, "timer6_gfclk_mux", "ipu_cm:0020:24"),
+	DT_CLK(NULL, "timer7_gfclk_mux", "ipu_cm:0028:24"),
+	DT_CLK(NULL, "timer8_gfclk_mux", "ipu_cm:0030:24"),
+	DT_CLK(NULL, "timer9_gfclk_mux", "l4per_cm:0050:24"),
+	DT_CLK(NULL, "uart10_gfclk_mux", "wkupaon_cm:0060:24"),
+	DT_CLK(NULL, "uart1_gfclk_mux", "l4per_cm:0140:24"),
+	DT_CLK(NULL, "uart2_gfclk_mux", "l4per_cm:0148:24"),
+	DT_CLK(NULL, "uart3_gfclk_mux", "l4per_cm:0150:24"),
+	DT_CLK(NULL, "uart4_gfclk_mux", "l4per_cm:0158:24"),
+	DT_CLK(NULL, "uart5_gfclk_mux", "l4per_cm:0170:24"),
+	DT_CLK(NULL, "uart6_gfclk_mux", "ipu_cm:0040:24"),
+	DT_CLK(NULL, "uart7_gfclk_mux", "l4per_cm:01d0:24"),
+	DT_CLK(NULL, "uart8_gfclk_mux", "l4per_cm:01e0:24"),
+	DT_CLK(NULL, "uart9_gfclk_mux", "l4per_cm:01e8:24"),
+	DT_CLK(NULL, "usb_otg_ss1_refclk960m", "l3init_cm:00d0:8"),
+	DT_CLK(NULL, "usb_otg_ss2_refclk960m", "l3init_cm:0020:8"),
 	{ .node_name = NULL },
 };
 
@@ -318,6 +830,8 @@ int __init dra7xx_dt_clk_init(void)
 
 	omap2_clk_disable_autoidle_all();
 
+	ti_clk_add_aliases();
+
 	dpll_ck = clk_get_sys(NULL, "dpll_gmac_ck");
 	rc = clk_set_rate(dpll_ck, DRA7_DPLL_GMAC_DEFFREQ);
 	if (rc)
diff --git a/drivers/clk/ti/clk-814x.c b/drivers/clk/ti/clk-814x.c
index 52c6efc53731..f688fdd2cb59 100644
--- a/drivers/clk/ti/clk-814x.c
+++ b/drivers/clk/ti/clk-814x.c
@@ -9,23 +9,48 @@
 #include <linux/clk-provider.h>
 #include <linux/clk/ti.h>
 #include <linux/of_platform.h>
+#include <dt-bindings/clock/dm814.h>
 
 #include "clock.h"
 
+static const struct omap_clkctrl_reg_data dm814_default_clkctrl_regs[] __initconst = {
+	{ DM814_USB_OTG_HS_CLKCTRL, NULL, CLKF_SW_SUP, "pll260dcoclkldo" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dm814_alwon_clkctrl_regs[] __initconst = {
+	{ DM814_UART1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM814_UART2_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM814_UART3_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM814_GPIO1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk6_ck" },
+	{ DM814_GPIO2_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk6_ck" },
+	{ DM814_I2C1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM814_I2C2_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM814_WD_TIMER_CLKCTRL, NULL, CLKF_SW_SUP | CLKF_NO_IDLEST, "sysclk18_ck" },
+	{ DM814_MCSPI1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM814_GPMC_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk6_ck" },
+	{ DM814_CPGMAC0_CLKCTRL, NULL, CLKF_SW_SUP, "cpsw_125mhz_gclk" },
+	{ DM814_MPU_CLKCTRL, NULL, CLKF_SW_SUP, "mpu_ck" },
+	{ DM814_RTC_CLKCTRL, NULL, CLKF_SW_SUP | CLKF_NO_IDLEST, "sysclk18_ck" },
+	{ DM814_TPCC_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk4_ck" },
+	{ DM814_TPTC0_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk4_ck" },
+	{ DM814_TPTC1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk4_ck" },
+	{ DM814_TPTC2_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk4_ck" },
+	{ DM814_TPTC3_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk4_ck" },
+	{ DM814_MMC1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk8_ck" },
+	{ DM814_MMC2_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk8_ck" },
+	{ DM814_MMC3_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk8_ck" },
+	{ 0 },
+};
+
+const struct omap_clkctrl_data dm814_clkctrl_data[] __initconst = {
+	{ 0x48180500, dm814_default_clkctrl_regs },
+	{ 0x48181400, dm814_alwon_clkctrl_regs },
+	{ 0 },
+};
+
 static struct ti_dt_clk dm814_clks[] = {
-	DT_CLK(NULL, "devosc_ck", "devosc_ck"),
-	DT_CLK(NULL, "mpu_ck", "mpu_ck"),
-	DT_CLK(NULL, "sysclk4_ck", "sysclk4_ck"),
-	DT_CLK(NULL, "sysclk5_ck", "sysclk5_ck"),
-	DT_CLK(NULL, "sysclk6_ck", "sysclk6_ck"),
-	DT_CLK(NULL, "sysclk8_ck", "sysclk8_ck"),
-	DT_CLK(NULL, "sysclk10_ck", "sysclk10_ck"),
-	DT_CLK(NULL, "sysclk18_ck", "sysclk18_ck"),
 	DT_CLK(NULL, "timer_sys_ck", "devosc_ck"),
-	DT_CLK(NULL, "timer1_fck", "timer1_fck"),
-	DT_CLK(NULL, "timer2_fck", "timer2_fck"),
-	DT_CLK(NULL, "cpsw_125mhz_gclk", "cpsw_125mhz_gclk"),
-	DT_CLK(NULL, "cpsw_cpts_rft_clk", "cpsw_cpts_rft_clk"),
 	{ .node_name = NULL },
 };
 
@@ -83,6 +108,7 @@ int __init dm814x_dt_clk_init(void)
 {
 	ti_dt_clocks_register(dm814_clks);
 	omap2_clk_disable_autoidle_all();
+	ti_clk_add_aliases();
 	omap2_clk_enable_init_clocks(NULL, 0);
 	timer_clocks_initialized = true;
 
diff --git a/drivers/clk/ti/clk-816x.c b/drivers/clk/ti/clk-816x.c
index 2a5d84fdddc5..7d215cdf9dda 100644
--- a/drivers/clk/ti/clk-816x.c
+++ b/drivers/clk/ti/clk-816x.c
@@ -13,30 +13,59 @@
 #include <linux/list.h>
 #include <linux/clk-provider.h>
 #include <linux/clk/ti.h>
+#include <dt-bindings/clock/dm816.h>
 
 #include "clock.h"
 
+static const struct omap_clkctrl_reg_data dm816_default_clkctrl_regs[] __initconst = {
+	{ DM816_USB_OTG_HS_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk6_ck" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dm816_alwon_clkctrl_regs[] __initconst = {
+	{ DM816_UART1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM816_UART2_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM816_UART3_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM816_GPIO1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk6_ck" },
+	{ DM816_GPIO2_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk6_ck" },
+	{ DM816_I2C1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM816_I2C2_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM816_TIMER1_CLKCTRL, NULL, CLKF_SW_SUP, "timer1_fck" },
+	{ DM816_TIMER2_CLKCTRL, NULL, CLKF_SW_SUP, "timer2_fck" },
+	{ DM816_TIMER3_CLKCTRL, NULL, CLKF_SW_SUP, "timer3_fck" },
+	{ DM816_TIMER4_CLKCTRL, NULL, CLKF_SW_SUP, "timer4_fck" },
+	{ DM816_TIMER5_CLKCTRL, NULL, CLKF_SW_SUP, "timer5_fck" },
+	{ DM816_TIMER6_CLKCTRL, NULL, CLKF_SW_SUP, "timer6_fck" },
+	{ DM816_TIMER7_CLKCTRL, NULL, CLKF_SW_SUP, "timer7_fck" },
+	{ DM816_WD_TIMER_CLKCTRL, NULL, CLKF_SW_SUP | CLKF_NO_IDLEST, "sysclk18_ck" },
+	{ DM816_MCSPI1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM816_MAILBOX_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk6_ck" },
+	{ DM816_SPINBOX_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk6_ck" },
+	{ DM816_MMC1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk10_ck" },
+	{ DM816_GPMC_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk6_ck" },
+	{ DM816_DAVINCI_MDIO_CLKCTRL, NULL, CLKF_SW_SUP | CLKF_NO_IDLEST, "sysclk24_ck" },
+	{ DM816_EMAC1_CLKCTRL, NULL, CLKF_SW_SUP | CLKF_NO_IDLEST, "sysclk24_ck" },
+	{ DM816_MPU_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk2_ck" },
+	{ DM816_RTC_CLKCTRL, NULL, CLKF_SW_SUP | CLKF_NO_IDLEST, "sysclk18_ck" },
+	{ DM816_TPCC_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk4_ck" },
+	{ DM816_TPTC0_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk4_ck" },
+	{ DM816_TPTC1_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk4_ck" },
+	{ DM816_TPTC2_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk4_ck" },
+	{ DM816_TPTC3_CLKCTRL, NULL, CLKF_SW_SUP, "sysclk4_ck" },
+	{ 0 },
+};
+
+const struct omap_clkctrl_data dm816_clkctrl_data[] __initconst = {
+	{ 0x48180500, dm816_default_clkctrl_regs },
+	{ 0x48181400, dm816_alwon_clkctrl_regs },
+	{ 0 },
+};
+
 static struct ti_dt_clk dm816x_clks[] = {
 	DT_CLK(NULL, "sys_clkin", "sys_clkin_ck"),
 	DT_CLK(NULL, "timer_sys_ck", "sys_clkin_ck"),
-	DT_CLK(NULL, "sys_32k_ck", "sys_32k_ck"),
 	DT_CLK(NULL, "timer_32k_ck", "sysclk18_ck"),
 	DT_CLK(NULL, "timer_ext_ck", "tclkin_ck"),
-	DT_CLK(NULL, "mpu_ck", "mpu_ck"),
-	DT_CLK(NULL, "timer1_fck", "timer1_fck"),
-	DT_CLK(NULL, "timer2_fck", "timer2_fck"),
-	DT_CLK(NULL, "timer3_fck", "timer3_fck"),
-	DT_CLK(NULL, "timer4_fck", "timer4_fck"),
-	DT_CLK(NULL, "timer5_fck", "timer5_fck"),
-	DT_CLK(NULL, "timer6_fck", "timer6_fck"),
-	DT_CLK(NULL, "timer7_fck", "timer7_fck"),
-	DT_CLK(NULL, "sysclk4_ck", "sysclk4_ck"),
-	DT_CLK(NULL, "sysclk5_ck", "sysclk5_ck"),
-	DT_CLK(NULL, "sysclk6_ck", "sysclk6_ck"),
-	DT_CLK(NULL, "sysclk10_ck", "sysclk10_ck"),
-	DT_CLK(NULL, "sysclk18_ck", "sysclk18_ck"),
-	DT_CLK(NULL, "sysclk24_ck", "sysclk24_ck"),
-	DT_CLK("4a100000.ethernet", "sysclk24_ck", "sysclk24_ck"),
 	{ .node_name = NULL },
 };
 
@@ -50,6 +79,7 @@ int __init dm816x_dt_clk_init(void)
 {
 	ti_dt_clocks_register(dm816x_clks);
 	omap2_clk_disable_autoidle_all();
+	ti_clk_add_aliases();
 	omap2_clk_enable_init_clocks(enable_init_clks,
 				     ARRAY_SIZE(enable_init_clks));
 
diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c
index e5a1c8297a1d..f4d6802a8544 100644
--- a/drivers/clk/ti/clk.c
+++ b/drivers/clk/ti/clk.c
@@ -108,25 +108,77 @@ void __init ti_dt_clocks_register(struct ti_dt_clk oclks[])
 	struct device_node *node;
 	struct clk *clk;
 	struct of_phandle_args clkspec;
+	char buf[64];
+	char *ptr;
+	char *tags[2];
+	int i;
+	int num_args;
+	int ret;
+	static bool clkctrl_nodes_missing;
+	static bool has_clkctrl_data;
 
 	for (c = oclks; c->node_name != NULL; c++) {
-		node = of_find_node_by_name(NULL, c->node_name);
+		strcpy(buf, c->node_name);
+		ptr = buf;
+		for (i = 0; i < 2; i++)
+			tags[i] = NULL;
+		num_args = 0;
+		while (*ptr) {
+			if (*ptr == ':') {
+				if (num_args >= 2) {
+					pr_warn("Bad number of tags on %s\n",
+						c->node_name);
+					return;
+				}
+				tags[num_args++] = ptr + 1;
+				*ptr = 0;
+			}
+			ptr++;
+		}
+
+		if (num_args && clkctrl_nodes_missing)
+			continue;
+
+		node = of_find_node_by_name(NULL, buf);
+		if (num_args)
+			node = of_find_node_by_name(node, "clk");
 		clkspec.np = node;
+		clkspec.args_count = num_args;
+		for (i = 0; i < num_args; i++) {
+			ret = kstrtoint(tags[i], i ? 10 : 16, clkspec.args + i);
+			if (ret) {
+				pr_warn("Bad tag in %s at %d: %s\n",
+					c->node_name, i, tags[i]);
+				return;
+			}
+		}
 		clk = of_clk_get_from_provider(&clkspec);
 
 		if (!IS_ERR(clk)) {
 			c->lk.clk = clk;
 			clkdev_add(&c->lk);
 		} else {
-			pr_warn("failed to lookup clock node %s\n",
-				c->node_name);
+			if (num_args && !has_clkctrl_data) {
+				if (of_find_compatible_node(NULL, NULL,
+							    "ti,clkctrl")) {
+					has_clkctrl_data = true;
+				} else {
+					clkctrl_nodes_missing = true;
+
+					pr_warn("missing clkctrl nodes, please update your dts.\n");
+					continue;
+				}
+			}
+
+			pr_warn("failed to lookup clock node %s, ret=%ld\n",
+				c->node_name, PTR_ERR(clk));
 		}
 	}
 }
 
 struct clk_init_item {
 	struct device_node *node;
-	struct clk_hw *hw;
+	void *user;
 	ti_of_clk_init_cb_t func;
 	struct list_head link;
 };
@@ -136,14 +188,14 @@ static LIST_HEAD(retry_list);
 /**
  * ti_clk_retry_init - retries a failed clock init at later phase
  * @node: device not for the clock
- * @hw: partially initialized clk_hw struct for the clock
+ * @user: user data pointer
  * @func: init function to be called for the clock
  *
  * Adds a failed clock init to the retry list. The retry list is parsed
  * once all the other clocks have been initialized.
  */
-int __init ti_clk_retry_init(struct device_node *node, struct clk_hw *hw,
-			      ti_of_clk_init_cb_t func)
+int __init ti_clk_retry_init(struct device_node *node, void *user,
+			     ti_of_clk_init_cb_t func)
 {
 	struct clk_init_item *retry;
 
@@ -154,7 +206,7 @@ int __init ti_clk_retry_init(struct device_node *node, struct clk_hw *hw,
 
 	retry->node = node;
 	retry->func = func;
-	retry->hw = hw;
+	retry->user = user;
 	list_add(&retry->link, &retry_list);
 
 	return 0;
@@ -276,7 +328,7 @@ void ti_dt_clk_init_retry_clks(void)
 	while (!list_empty(&retry_list) && retries) {
 		list_for_each_entry_safe(retry, tmp, &retry_list, link) {
 			pr_debug("retry-init: %s\n", retry->node->name);
-			retry->func(retry->hw, retry->node);
+			retry->func(retry->user, retry->node);
 			list_del(&retry->link);
 			kfree(retry);
 		}
@@ -284,141 +336,6 @@ void ti_dt_clk_init_retry_clks(void)
 	}
 }
 
-#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_ATAGS)
-void __init ti_clk_patch_legacy_clks(struct ti_clk **patch)
-{
-	while (*patch) {
-		memcpy((*patch)->patch, *patch, sizeof(**patch));
-		patch++;
-	}
-}
-
-struct clk __init *ti_clk_register_clk(struct ti_clk *setup)
-{
-	struct clk *clk;
-	struct ti_clk_fixed *fixed;
-	struct ti_clk_fixed_factor *fixed_factor;
-	struct clk_hw *clk_hw;
-	int ret;
-
-	if (setup->clk)
-		return setup->clk;
-
-	switch (setup->type) {
-	case TI_CLK_FIXED:
-		fixed = setup->data;
-
-		clk = clk_register_fixed_rate(NULL, setup->name, NULL, 0,
-					      fixed->frequency);
-		if (!IS_ERR(clk)) {
-			ret = ti_clk_add_alias(NULL, clk, setup->name);
-			if (ret) {
-				clk_unregister(clk);
-				clk = ERR_PTR(ret);
-			}
-		}
-		break;
-	case TI_CLK_MUX:
-		clk = ti_clk_register_mux(setup);
-		break;
-	case TI_CLK_DIVIDER:
-		clk = ti_clk_register_divider(setup);
-		break;
-	case TI_CLK_COMPOSITE:
-		clk = ti_clk_register_composite(setup);
-		break;
-	case TI_CLK_FIXED_FACTOR:
-		fixed_factor = setup->data;
-
-		clk = clk_register_fixed_factor(NULL, setup->name,
-						fixed_factor->parent,
-						0, fixed_factor->mult,
-						fixed_factor->div);
-		if (!IS_ERR(clk)) {
-			ret = ti_clk_add_alias(NULL, clk, setup->name);
-			if (ret) {
-				clk_unregister(clk);
-				clk = ERR_PTR(ret);
-			}
-		}
-		break;
-	case TI_CLK_GATE:
-		clk = ti_clk_register_gate(setup);
-		break;
-	case TI_CLK_DPLL:
-		clk = ti_clk_register_dpll(setup);
-		break;
-	default:
-		pr_err("bad type for %s!\n", setup->name);
-		clk = ERR_PTR(-EINVAL);
-	}
-
-	if (!IS_ERR(clk)) {
-		setup->clk = clk;
-		if (setup->clkdm_name) {
-			clk_hw = __clk_get_hw(clk);
-			if (clk_hw_get_flags(clk_hw) & CLK_IS_BASIC) {
-				pr_warn("can't setup clkdm for basic clk %s\n",
-					setup->name);
-			} else {
-				to_clk_hw_omap(clk_hw)->clkdm_name =
-					setup->clkdm_name;
-				omap2_init_clk_clkdm(clk_hw);
-			}
-		}
-	}
-
-	return clk;
-}
-
-int __init ti_clk_register_legacy_clks(struct ti_clk_alias *clks)
-{
-	struct clk *clk;
-	bool retry;
-	struct ti_clk_alias *retry_clk;
-	struct ti_clk_alias *tmp;
-
-	while (clks->clk) {
-		clk = ti_clk_register_clk(clks->clk);
-		if (IS_ERR(clk)) {
-			if (PTR_ERR(clk) == -EAGAIN) {
-				list_add(&clks->link, &retry_list);
-			} else {
-				pr_err("register for %s failed: %ld\n",
-				       clks->clk->name, PTR_ERR(clk));
-				return PTR_ERR(clk);
-			}
-		}
-		clks++;
-	}
-
-	retry = true;
-
-	while (!list_empty(&retry_list) && retry) {
-		retry = false;
-		list_for_each_entry_safe(retry_clk, tmp, &retry_list, link) {
-			pr_debug("retry-init: %s\n", retry_clk->clk->name);
-			clk = ti_clk_register_clk(retry_clk->clk);
-			if (IS_ERR(clk)) {
-				if (PTR_ERR(clk) == -EAGAIN) {
-					continue;
-				} else {
-					pr_err("register for %s failed: %ld\n",
-					       retry_clk->clk->name,
-					       PTR_ERR(clk));
-					return PTR_ERR(clk);
-				}
-			} else {
-				retry = true;
-				list_del(&retry_clk->link);
-			}
-		}
-	}
-
-	return 0;
-}
-#endif
-
 static const struct of_device_id simple_clk_match_table[] __initconst = {
 	{ .compatible = "fixed-clock" },
 	{ .compatible = "fixed-factor-clock" },
diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c
index 53e71d0503ec..afa0d6bfc5c1 100644
--- a/drivers/clk/ti/clkctrl.c
+++ b/drivers/clk/ti/clkctrl.c
@@ -21,6 +21,7 @@
 #include <linux/of_address.h>
 #include <linux/clk/ti.h>
 #include <linux/delay.h>
+#include <linux/timekeeping.h>
 #include "clock.h"
 
 #define NO_IDLEST			0x1
@@ -46,6 +47,7 @@ static bool _early_timeout = true;
 struct omap_clkctrl_provider {
 	void __iomem *base;
 	struct list_head clocks;
+	char *clkdm_name;
 };
 
 struct omap_clkctrl_clk {
@@ -89,7 +91,18 @@ static bool _omap4_is_ready(u32 val)
 
 static bool _omap4_is_timeout(union omap4_timeout *time, u32 timeout)
 {
-	if (unlikely(_early_timeout)) {
+	/*
+	 * There are two special cases where ktime_to_ns() can't be
+	 * used to track the timeouts. First one is during early boot
+	 * when the timers haven't been initialized yet. The second
+	 * one is during suspend-resume cycle while timekeeping is
+	 * being suspended / resumed. Clocksource for the system
+	 * can be from a timer that requires pm_runtime access, which
+	 * will eventually bring us here with timekeeping_suspended,
+	 * during both suspend entry and resume paths. This happens
+	 * at least on am43xx platform.
+	 */
+	if (unlikely(_early_timeout || timekeeping_suspended)) {
 		if (time->cycles++ < timeout) {
 			udelay(1);
 			return false;
@@ -208,6 +221,7 @@ static const struct clk_ops omap4_clkctrl_clk_ops = {
 	.enable		= _omap4_clkctrl_clk_enable,
 	.disable	= _omap4_clkctrl_clk_disable,
 	.is_enabled	= _omap4_clkctrl_clk_is_enabled,
+	.init		= omap2_init_clk_clkdm,
 };
 
 static struct clk_hw *_ti_omap4_clkctrl_xlate(struct of_phandle_args *clkspec,
@@ -321,6 +335,9 @@ _ti_clkctrl_setup_mux(struct omap_clkctrl_provider *provider,
 	}
 
 	mux->mask = num_parents;
+	if (!(mux->flags & CLK_MUX_INDEX_ONE))
+		mux->mask--;
+
 	mux->mask = (1 << fls(mux->mask)) - 1;
 
 	mux->shift = data->bit;
@@ -340,6 +357,7 @@ _ti_clkctrl_setup_div(struct omap_clkctrl_provider *provider,
 {
 	struct clk_omap_divider *div;
 	const struct omap_clkctrl_div_data *div_data = data->data;
+	u8 div_flags = 0;
 
 	div = kzalloc(sizeof(*div), GFP_KERNEL);
 	if (!div)
@@ -347,12 +365,16 @@ _ti_clkctrl_setup_div(struct omap_clkctrl_provider *provider,
 
 	div->reg.ptr = reg;
 	div->shift = data->bit;
+	div->flags = div_data->flags;
+
+	if (div->flags & CLK_DIVIDER_POWER_OF_TWO)
+		div_flags |= CLKF_INDEX_POWER_OF_TWO;
 
-	if (ti_clk_parse_divider_data((int *)div_data->dividers,
-				      div_data->max_div, 0, 0,
+	if (ti_clk_parse_divider_data((int *)div_data->dividers, 0,
+				      div_data->max_div, div_flags,
 				      &div->width, &div->table)) {
-		pr_err("%s: Data parsing for %s:%04x:%d failed\n", __func__,
-		       node->name, offset, data->bit);
+		pr_err("%s: Data parsing for %pOF:%04x:%d failed\n", __func__,
+		       node, offset, data->bit);
 		kfree(div);
 		return;
 	}
@@ -400,6 +422,12 @@ _ti_clkctrl_setup_subclks(struct omap_clkctrl_provider *provider,
 	}
 }
 
+static void __init _clkctrl_add_provider(void *data,
+					 struct device_node *np)
+{
+	of_clk_add_hw_provider(np, _ti_omap4_clkctrl_xlate, data);
+}
+
 static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 {
 	struct omap_clkctrl_provider *provider;
@@ -411,6 +439,7 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 	struct omap_clkctrl_clk *clkctrl_clk;
 	const __be32 *addrp;
 	u32 addr;
+	int ret;
 
 	addrp = of_get_address(node, 0, NULL, NULL);
 	addr = (u32)of_translate_address(node, addrp);
@@ -419,6 +448,31 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 	if (of_machine_is_compatible("ti,omap4"))
 		data = omap4_clkctrl_data;
 #endif
+#ifdef CONFIG_SOC_OMAP5
+	if (of_machine_is_compatible("ti,omap5"))
+		data = omap5_clkctrl_data;
+#endif
+#ifdef CONFIG_SOC_DRA7XX
+	if (of_machine_is_compatible("ti,dra7"))
+		data = dra7_clkctrl_data;
+#endif
+#ifdef CONFIG_SOC_AM33XX
+	if (of_machine_is_compatible("ti,am33xx"))
+		data = am3_clkctrl_data;
+#endif
+#ifdef CONFIG_SOC_AM43XX
+	if (of_machine_is_compatible("ti,am4372"))
+		data = am4_clkctrl_data;
+	if (of_machine_is_compatible("ti,am438x"))
+		data = am438x_clkctrl_data;
+#endif
+#ifdef CONFIG_SOC_TI81XX
+	if (of_machine_is_compatible("ti,dm814"))
+		data = dm814_clkctrl_data;
+
+	if (of_machine_is_compatible("ti,dm816"))
+		data = dm816_clkctrl_data;
+#endif
 
 	while (data->addr) {
 		if (addr == data->addr)
@@ -428,7 +482,7 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 	}
 
 	if (!data->addr) {
-		pr_err("%s not found from clkctrl data.\n", node->name);
+		pr_err("%pOF not found from clkctrl data.\n", node);
 		return;
 	}
 
@@ -438,6 +492,21 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 
 	provider->base = of_iomap(node, 0);
 
+	provider->clkdm_name = kmalloc(strlen(node->parent->name) + 3,
+				       GFP_KERNEL);
+	if (!provider->clkdm_name) {
+		kfree(provider);
+		return;
+	}
+
+	/*
+	 * Create default clkdm name, replace _cm from end of parent node
+	 * name with _clkdm
+	 */
+	strcpy(provider->clkdm_name, node->parent->name);
+	provider->clkdm_name[strlen(provider->clkdm_name) - 2] = 0;
+	strcat(provider->clkdm_name, "clkdm");
+
 	INIT_LIST_HEAD(&provider->clocks);
 
 	/* Generate clocks */
@@ -460,6 +529,11 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 		if (reg_data->flags & CLKF_NO_IDLEST)
 			hw->flags |= NO_IDLEST;
 
+		if (reg_data->clkdm_name)
+			hw->clkdm_name = reg_data->clkdm_name;
+		else
+			hw->clkdm_name = provider->clkdm_name;
+
 		init.parent_names = &reg_data->parent;
 		init.num_parents = 1;
 		init.flags = 0;
@@ -485,7 +559,10 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 		reg_data++;
 	}
 
-	of_clk_add_hw_provider(node, _ti_omap4_clkctrl_xlate, provider);
+	ret = of_clk_add_hw_provider(node, _ti_omap4_clkctrl_xlate, provider);
+	if (ret == -EPROBE_DEFER)
+		ti_clk_retry_init(node, provider, _clkctrl_add_provider);
+
 	return;
 
 cleanup:
diff --git a/drivers/clk/ti/clock.h b/drivers/clk/ti/clock.h
index 561dbe99ced7..d9b43bfc2532 100644
--- a/drivers/clk/ti/clock.h
+++ b/drivers/clk/ti/clock.h
@@ -92,17 +92,6 @@ struct ti_clk {
 	struct clk *clk;
 };
 
-struct ti_clk_alias {
-	struct ti_clk *clk;
-	struct clk_lookup lk;
-	struct list_head link;
-};
-
-struct ti_clk_fixed {
-	u32 frequency;
-	u16 flags;
-};
-
 struct ti_clk_mux {
 	u8 bit_shift;
 	int num_parents;
@@ -123,13 +112,6 @@ struct ti_clk_divider {
 	u16 flags;
 };
 
-struct ti_clk_fixed_factor {
-	const char *parent;
-	u16 div;
-	u16 mult;
-	u16 flags;
-};
-
 struct ti_clk_gate {
 	const char *parent;
 	u8 bit_shift;
@@ -138,44 +120,6 @@ struct ti_clk_gate {
 	u16 flags;
 };
 
-struct ti_clk_composite {
-	struct ti_clk_divider *divider;
-	struct ti_clk_mux *mux;
-	struct ti_clk_gate *gate;
-	u16 flags;
-};
-
-struct ti_clk_clkdm_gate {
-	const char *parent;
-	u16 flags;
-};
-
-struct ti_clk_dpll {
-	int num_parents;
-	u16 control_reg;
-	u16 idlest_reg;
-	u16 autoidle_reg;
-	u16 mult_div1_reg;
-	u8 module;
-	const char **parents;
-	u16 flags;
-	u8 modes;
-	u32 mult_mask;
-	u32 div1_mask;
-	u32 enable_mask;
-	u32 autoidle_mask;
-	u32 freqsel_mask;
-	u32 idlest_mask;
-	u32 dco_mask;
-	u32 sddiv_mask;
-	u16 max_multiplier;
-	u16 max_divider;
-	u8 min_divider;
-	u8 auto_recal_bit;
-	u8 recal_en_bit;
-	u8 recal_st_bit;
-};
-
 /* Composite clock component types */
 enum {
 	CLK_COMPONENT_TYPE_GATE = 0,
@@ -207,6 +151,7 @@ struct ti_dt_clk {
 struct omap_clkctrl_div_data {
 	const int *dividers;
 	int max_div;
+	u32 flags;
 };
 
 struct omap_clkctrl_bit_data {
@@ -221,6 +166,7 @@ struct omap_clkctrl_reg_data {
 	const struct omap_clkctrl_bit_data *bit_data;
 	u16 flags;
 	const char *parent;
+	const char *clkdm_name;
 };
 
 struct omap_clkctrl_data {
@@ -229,40 +175,35 @@ struct omap_clkctrl_data {
 };
 
 extern const struct omap_clkctrl_data omap4_clkctrl_data[];
+extern const struct omap_clkctrl_data omap5_clkctrl_data[];
+extern const struct omap_clkctrl_data dra7_clkctrl_data[];
+extern const struct omap_clkctrl_data am3_clkctrl_data[];
+extern const struct omap_clkctrl_data am4_clkctrl_data[];
+extern const struct omap_clkctrl_data am438x_clkctrl_data[];
+extern const struct omap_clkctrl_data dm814_clkctrl_data[];
+extern const struct omap_clkctrl_data dm816_clkctrl_data[];
 
 #define CLKF_SW_SUP	BIT(0)
 #define CLKF_HW_SUP	BIT(1)
 #define CLKF_NO_IDLEST	BIT(2)
 
-typedef void (*ti_of_clk_init_cb_t)(struct clk_hw *, struct device_node *);
+typedef void (*ti_of_clk_init_cb_t)(void *, struct device_node *);
 
-struct clk *ti_clk_register_gate(struct ti_clk *setup);
-struct clk *ti_clk_register_interface(struct ti_clk *setup);
-struct clk *ti_clk_register_mux(struct ti_clk *setup);
-struct clk *ti_clk_register_divider(struct ti_clk *setup);
-struct clk *ti_clk_register_composite(struct ti_clk *setup);
-struct clk *ti_clk_register_dpll(struct ti_clk *setup);
 struct clk *ti_clk_register(struct device *dev, struct clk_hw *hw,
 			    const char *con);
 int ti_clk_add_alias(struct device *dev, struct clk *clk, const char *con);
 void ti_clk_add_aliases(void);
 
-struct clk_hw *ti_clk_build_component_div(struct ti_clk_divider *setup);
-struct clk_hw *ti_clk_build_component_gate(struct ti_clk_gate *setup);
 struct clk_hw *ti_clk_build_component_mux(struct ti_clk_mux *setup);
 
 int ti_clk_parse_divider_data(int *div_table, int num_dividers, int max_div,
 			      u8 flags, u8 *width,
 			      const struct clk_div_table **table);
 
-void ti_clk_patch_legacy_clks(struct ti_clk **patch);
-struct clk *ti_clk_register_clk(struct ti_clk *setup);
-int ti_clk_register_legacy_clks(struct ti_clk_alias *clks);
-
 int ti_clk_get_reg_addr(struct device_node *node, int index,
 			struct clk_omap_reg *reg);
 void ti_dt_clocks_register(struct ti_dt_clk *oclks);
-int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw,
+int ti_clk_retry_init(struct device_node *node, void *user,
 		      ti_of_clk_init_cb_t func);
 int ti_clk_add_component(struct device_node *node, struct clk_hw *hw, int type);
 
diff --git a/drivers/clk/ti/composite.c b/drivers/clk/ti/composite.c
index beea89463ca2..030e8b2c1050 100644
--- a/drivers/clk/ti/composite.c
+++ b/drivers/clk/ti/composite.c
@@ -116,54 +116,10 @@ static inline struct clk_hw *_get_hw(struct clk_hw_omap_comp *clk, int idx)
 
 #define to_clk_hw_comp(_hw) container_of(_hw, struct clk_hw_omap_comp, hw)
 
-#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_ATAGS)
-struct clk *ti_clk_register_composite(struct ti_clk *setup)
-{
-	struct ti_clk_composite *comp;
-	struct clk_hw *gate;
-	struct clk_hw *mux;
-	struct clk_hw *div;
-	int num_parents = 1;
-	const char * const *parent_names = NULL;
-	struct clk *clk;
-	int ret;
-
-	comp = setup->data;
-
-	div = ti_clk_build_component_div(comp->divider);
-	gate = ti_clk_build_component_gate(comp->gate);
-	mux = ti_clk_build_component_mux(comp->mux);
-
-	if (div)
-		parent_names = &comp->divider->parent;
-
-	if (gate)
-		parent_names = &comp->gate->parent;
-
-	if (mux) {
-		num_parents = comp->mux->num_parents;
-		parent_names = comp->mux->parents;
-	}
-
-	clk = clk_register_composite(NULL, setup->name,
-				     parent_names, num_parents, mux,
-				     &ti_clk_mux_ops, div,
-				     &ti_composite_divider_ops, gate,
-				     &ti_composite_gate_ops, 0);
-
-	ret = ti_clk_add_alias(NULL, clk, setup->name);
-	if (ret) {
-		clk_unregister(clk);
-		return ERR_PTR(ret);
-	}
-
-	return clk;
-}
-#endif
-
-static void __init _register_composite(struct clk_hw *hw,
+static void __init _register_composite(void *user,
 				       struct device_node *node)
 {
+	struct clk_hw *hw = user;
 	struct clk *clk;
 	struct clk_hw_omap_comp *cclk = to_clk_hw_comp(hw);
 	struct component_clk *comp;
diff --git a/drivers/clk/ti/dpll.c b/drivers/clk/ti/dpll.c
index d4e4444bc5ca..7d33ca9042cb 100644
--- a/drivers/clk/ti/dpll.c
+++ b/drivers/clk/ti/dpll.c
@@ -152,9 +152,10 @@ static const struct clk_ops dpll_x2_ck_ops = {
  * clk-bypass is missing), the clock is added to retry list and
  * the initialization is retried on later stage.
  */
-static void __init _register_dpll(struct clk_hw *hw,
+static void __init _register_dpll(void *user,
 				  struct device_node *node)
 {
+	struct clk_hw *hw = user;
 	struct clk_hw_omap *clk_hw = to_clk_hw_omap(hw);
 	struct dpll_data *dd = clk_hw->dpll_data;
 	struct clk *clk;
@@ -202,96 +203,6 @@ cleanup:
 	kfree(clk_hw);
 }
 
-#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_ATAGS)
-void _get_reg(u8 module, u16 offset, struct clk_omap_reg *reg)
-{
-	reg->index = module;
-	reg->offset = offset;
-}
-
-struct clk *ti_clk_register_dpll(struct ti_clk *setup)
-{
-	struct clk_hw_omap *clk_hw;
-	struct clk_init_data init = { NULL };
-	struct dpll_data *dd;
-	struct clk *clk;
-	struct ti_clk_dpll *dpll;
-	const struct clk_ops *ops = &omap3_dpll_ck_ops;
-	struct clk *clk_ref;
-	struct clk *clk_bypass;
-
-	dpll = setup->data;
-
-	if (dpll->num_parents < 2)
-		return ERR_PTR(-EINVAL);
-
-	clk_ref = clk_get_sys(NULL, dpll->parents[0]);
-	clk_bypass = clk_get_sys(NULL, dpll->parents[1]);
-
-	if (IS_ERR_OR_NULL(clk_ref) || IS_ERR_OR_NULL(clk_bypass))
-		return ERR_PTR(-EAGAIN);
-
-	dd = kzalloc(sizeof(*dd), GFP_KERNEL);
-	clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
-	if (!dd || !clk_hw) {
-		clk = ERR_PTR(-ENOMEM);
-		goto cleanup;
-	}
-
-	clk_hw->dpll_data = dd;
-	clk_hw->ops = &clkhwops_omap3_dpll;
-	clk_hw->hw.init = &init;
-
-	init.name = setup->name;
-	init.ops = ops;
-
-	init.num_parents = dpll->num_parents;
-	init.parent_names = dpll->parents;
-
-	_get_reg(dpll->module, dpll->control_reg, &dd->control_reg);
-	_get_reg(dpll->module, dpll->idlest_reg, &dd->idlest_reg);
-	_get_reg(dpll->module, dpll->mult_div1_reg, &dd->mult_div1_reg);
-	_get_reg(dpll->module, dpll->autoidle_reg, &dd->autoidle_reg);
-
-	dd->modes = dpll->modes;
-	dd->div1_mask = dpll->div1_mask;
-	dd->idlest_mask = dpll->idlest_mask;
-	dd->mult_mask = dpll->mult_mask;
-	dd->autoidle_mask = dpll->autoidle_mask;
-	dd->enable_mask = dpll->enable_mask;
-	dd->sddiv_mask = dpll->sddiv_mask;
-	dd->dco_mask = dpll->dco_mask;
-	dd->max_divider = dpll->max_divider;
-	dd->min_divider = dpll->min_divider;
-	dd->max_multiplier = dpll->max_multiplier;
-	dd->auto_recal_bit = dpll->auto_recal_bit;
-	dd->recal_en_bit = dpll->recal_en_bit;
-	dd->recal_st_bit = dpll->recal_st_bit;
-
-	dd->clk_ref = __clk_get_hw(clk_ref);
-	dd->clk_bypass = __clk_get_hw(clk_bypass);
-
-	if (dpll->flags & CLKF_CORE)
-		ops = &omap3_dpll_core_ck_ops;
-
-	if (dpll->flags & CLKF_PER)
-		ops = &omap3_dpll_per_ck_ops;
-
-	if (dpll->flags & CLKF_J_TYPE)
-		dd->flags |= DPLL_J_TYPE;
-
-	clk = ti_clk_register(NULL, &clk_hw->hw, setup->name);
-
-	if (!IS_ERR(clk))
-		return clk;
-
-cleanup:
-	kfree(dd);
-	kfree(clk_hw);
-	return clk;
-}
-#endif
-
 #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) || \
 	defined(CONFIG_SOC_DRA7XX) || defined(CONFIG_SOC_AM33XX) || \
 	defined(CONFIG_SOC_AM43XX)
diff --git a/drivers/clk/ti/gate.c b/drivers/clk/ti/gate.c
index 7151ec3a1b07..935b2de5fb88 100644
--- a/drivers/clk/ti/gate.c
+++ b/drivers/clk/ti/gate.c
@@ -128,53 +128,6 @@ static struct clk *_register_gate(struct device *dev, const char *name,
 	return clk;
 }
 
-#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_ATAGS)
-struct clk *ti_clk_register_gate(struct ti_clk *setup)
-{
-	const struct clk_ops *ops = &omap_gate_clk_ops;
-	const struct clk_hw_omap_ops *hw_ops = NULL;
-	struct clk_omap_reg reg;
-	u32 flags = 0;
-	u8 clk_gate_flags = 0;
-	struct ti_clk_gate *gate;
-
-	gate = setup->data;
-
-	if (gate->flags & CLKF_INTERFACE)
-		return ti_clk_register_interface(setup);
-
-	if (gate->flags & CLKF_SET_RATE_PARENT)
-		flags |= CLK_SET_RATE_PARENT;
-
-	if (gate->flags & CLKF_SET_BIT_TO_DISABLE)
-		clk_gate_flags |= INVERT_ENABLE;
-
-	if (gate->flags & CLKF_HSDIV) {
-		ops = &omap_gate_clk_hsdiv_restore_ops;
-		hw_ops = &clkhwops_wait;
-	}
-
-	if (gate->flags & CLKF_DSS)
-		hw_ops = &clkhwops_omap3430es2_dss_usbhost_wait;
-
-	if (gate->flags & CLKF_WAIT)
-		hw_ops = &clkhwops_wait;
-
-	if (gate->flags & CLKF_CLKDM)
-		ops = &omap_gate_clkdm_clk_ops;
-
-	if (gate->flags & CLKF_AM35XX)
-		hw_ops = &clkhwops_am35xx_ipss_module_wait;
-
-	reg.index = gate->module;
-	reg.offset = gate->reg;
-	reg.ptr = NULL;
-
-	return _register_gate(NULL, setup->name, gate->parent, flags,
-			      &reg, gate->bit_shift,
-			      clk_gate_flags, ops, hw_ops);
-}
-
 struct clk_hw *ti_clk_build_component_gate(struct ti_clk_gate *setup)
 {
 	struct clk_hw_omap *gate;
@@ -204,7 +157,6 @@ struct clk_hw *ti_clk_build_component_gate(struct ti_clk_gate *setup)
 
 	return &gate->hw;
 }
-#endif
 
 static void __init _of_ti_gate_clk_setup(struct device_node *node,
 					 const struct clk_ops *ops,
diff --git a/drivers/clk/ti/interface.c b/drivers/clk/ti/interface.c
index 62cf50c1e1e3..41ae7021670e 100644
--- a/drivers/clk/ti/interface.c
+++ b/drivers/clk/ti/interface.c
@@ -67,38 +67,6 @@ static struct clk *_register_interface(struct device *dev, const char *name,
 	return clk;
 }
 
-#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_ATAGS)
-struct clk *ti_clk_register_interface(struct ti_clk *setup)
-{
-	const struct clk_hw_omap_ops *ops = &clkhwops_iclk_wait;
-	struct clk_omap_reg reg;
-	struct ti_clk_gate *gate;
-
-	gate = setup->data;
-	reg.index = gate->module;
-	reg.offset = gate->reg;
-	reg.ptr = NULL;
-
-	if (gate->flags & CLKF_NO_WAIT)
-		ops = &clkhwops_iclk;
-
-	if (gate->flags & CLKF_HSOTGUSB)
-		ops = &clkhwops_omap3430es2_iclk_hsotgusb_wait;
-
-	if (gate->flags & CLKF_DSS)
-		ops = &clkhwops_omap3430es2_iclk_dss_usbhost_wait;
-
-	if (gate->flags & CLKF_SSI)
-		ops = &clkhwops_omap3430es2_iclk_ssi_wait;
-
-	if (gate->flags & CLKF_AM35XX)
-		ops = &clkhwops_am35xx_ipss_wait;
-
-	return _register_interface(NULL, setup->name, gate->parent,
-				   &reg, gate->bit_shift, ops);
-}
-#endif
-
 static void __init _of_ti_interface_clk_setup(struct device_node *node,
 					      const struct clk_hw_omap_ops *ops)
 {
diff --git a/drivers/clk/zte/clk.h b/drivers/clk/zte/clk.h
index 4df0f121b56d..f1041e36bcf1 100644
--- a/drivers/clk/zte/clk.h
+++ b/drivers/clk/zte/clk.h
@@ -14,24 +14,6 @@
 
 #define PNAME(x) static const char *x[]
 
-#define CLK_HW_INIT(_name, _parent, _ops, _flags)			\
-	&(struct clk_init_data) {					\
-		.flags		= _flags,				\
-		.name		= _name,				\
-		.parent_names	= (const char *[]) { _parent },		\
-		.num_parents	= 1,					\
-		.ops		= _ops,					\
-	}
-
-#define CLK_HW_INIT_PARENTS(_name, _parents, _ops, _flags)		\
-	&(struct clk_init_data) {					\
-		.flags		= _flags,				\
-		.name		= _name,				\
-		.parent_names	= _parents,				\
-		.num_parents	= ARRAY_SIZE(_parents),			\
-		.ops		= _ops,					\
-	}
-
 struct zx_pll_config {
 	unsigned long rate;
 	u32 cfg0;
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index c729a88007d0..b3b4ed9b6874 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -269,6 +269,7 @@ config CLKSRC_STM32
 	bool "Clocksource for STM32 SoCs" if !ARCH_STM32
 	depends on OF && ARM && (ARCH_STM32 || COMPILE_TEST)
 	select CLKSRC_MMIO
+	select TIMER_OF
 
 config CLKSRC_MPS2
 	bool "Clocksource for MPS2 SoCs" if COMPILE_TEST
@@ -441,6 +442,13 @@ config MTK_TIMER
 	help
 	  Support for Mediatek timer driver.
 
+config SPRD_TIMER
+	bool "Spreadtrum timer driver" if COMPILE_TEST
+	depends on HAS_IOMEM
+	select TIMER_OF
+	help
+	  Enables support for the Spreadtrum timer driver.
+
 config SYS_SUPPORTS_SH_MTU2
         bool
 
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 72711f1491e3..d6dec4489d66 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -54,6 +54,7 @@ obj-$(CONFIG_CLKSRC_TI_32K)	+= timer-ti-32k.o
 obj-$(CONFIG_CLKSRC_NPS)	+= timer-nps.o
 obj-$(CONFIG_OXNAS_RPS_TIMER)	+= timer-oxnas-rps.o
 obj-$(CONFIG_OWL_TIMER)		+= owl-timer.o
+obj-$(CONFIG_SPRD_TIMER)	+= timer-sprd.o
 
 obj-$(CONFIG_ARC_TIMERS)		+= arc_timer.o
 obj-$(CONFIG_ARM_ARCH_TIMER)		+= arm_arch_timer.o
diff --git a/drivers/clocksource/owl-timer.c b/drivers/clocksource/owl-timer.c
index c68630565079..ea00a5e8f95d 100644
--- a/drivers/clocksource/owl-timer.c
+++ b/drivers/clocksource/owl-timer.c
@@ -168,5 +168,6 @@ static int __init owl_timer_init(struct device_node *node)
 
 	return 0;
 }
-CLOCKSOURCE_OF_DECLARE(owl_s500, "actions,s500-timer", owl_timer_init);
-CLOCKSOURCE_OF_DECLARE(owl_s900, "actions,s900-timer", owl_timer_init);
+TIMER_OF_DECLARE(owl_s500, "actions,s500-timer", owl_timer_init);
+TIMER_OF_DECLARE(owl_s700, "actions,s700-timer", owl_timer_init);
+TIMER_OF_DECLARE(owl_s900, "actions,s900-timer", owl_timer_init);
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 9de47d4d2d9e..43f4d5c4d6fa 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -384,7 +384,7 @@ static int __init tcb_clksrc_init(void)
 
 	printk(bootinfo, clksrc.name, CONFIG_ATMEL_TCB_CLKSRC_BLOCK,
 			divided_rate / 1000000,
-			((divided_rate + 500000) % 1000000) / 1000);
+			((divided_rate % 1000000) + 500) / 1000);
 
 	if (tc->tcb_config && tc->tcb_config->counter_width == 32) {
 		/* use apropriate function to read 32 bit counter */
diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c
index a31990408153..06ed88a2a8a0 100644
--- a/drivers/clocksource/timer-of.c
+++ b/drivers/clocksource/timer-of.c
@@ -24,7 +24,13 @@
 
 #include "timer-of.h"
 
-static __init void timer_irq_exit(struct of_timer_irq *of_irq)
+/**
+ * timer_of_irq_exit - Release the interrupt
+ * @of_irq: an of_timer_irq structure pointer
+ *
+ * Free the irq resource
+ */
+static __init void timer_of_irq_exit(struct of_timer_irq *of_irq)
 {
 	struct timer_of *to = container_of(of_irq, struct timer_of, of_irq);
 
@@ -34,8 +40,24 @@ static __init void timer_irq_exit(struct of_timer_irq *of_irq)
 		free_irq(of_irq->irq, clkevt);
 }
 
-static __init int timer_irq_init(struct device_node *np,
-				 struct of_timer_irq *of_irq)
+/**
+ * timer_of_irq_init - Request the interrupt
+ * @np: a device tree node pointer
+ * @of_irq: an of_timer_irq structure pointer
+ *
+ * Get the interrupt number from the DT from its definition and
+ * request it. The interrupt is gotten by falling back the following way:
+ *
+ * - Get interrupt number by name
+ * - Get interrupt number by index
+ *
+ * When the interrupt is per CPU, 'request_percpu_irq()' is called,
+ * otherwise 'request_irq()' is used.
+ *
+ * Returns 0 on success, < 0 otherwise
+ */
+static __init int timer_of_irq_init(struct device_node *np,
+				    struct of_timer_irq *of_irq)
 {
 	int ret;
 	struct timer_of *to = container_of(of_irq, struct timer_of, of_irq);
@@ -72,15 +94,30 @@ static __init int timer_irq_init(struct device_node *np,
 	return 0;
 }
 
-static __init void timer_clk_exit(struct of_timer_clk *of_clk)
+/**
+ * timer_of_clk_exit - Release the clock resources
+ * @of_clk: a of_timer_clk structure pointer
+ *
+ * Disables and releases the refcount on the clk
+ */
+static __init void timer_of_clk_exit(struct of_timer_clk *of_clk)
 {
 	of_clk->rate = 0;
 	clk_disable_unprepare(of_clk->clk);
 	clk_put(of_clk->clk);
 }
 
-static __init int timer_clk_init(struct device_node *np,
-				 struct of_timer_clk *of_clk)
+/**
+ * timer_of_clk_init - Initialize the clock resources
+ * @np: a device tree node pointer
+ * @of_clk: a of_timer_clk structure pointer
+ *
+ * Get the clock by name or by index, enable it and get the rate
+ *
+ * Returns 0 on success, < 0 otherwise
+ */
+static __init int timer_of_clk_init(struct device_node *np,
+				    struct of_timer_clk *of_clk)
 {
 	int ret;
 
@@ -116,19 +153,19 @@ out_clk_put:
 	goto out;
 }
 
-static __init void timer_base_exit(struct of_timer_base *of_base)
+static __init void timer_of_base_exit(struct of_timer_base *of_base)
 {
 	iounmap(of_base->base);
 }
 
-static __init int timer_base_init(struct device_node *np,
-				  struct of_timer_base *of_base)
+static __init int timer_of_base_init(struct device_node *np,
+				     struct of_timer_base *of_base)
 {
-	const char *name = of_base->name ? of_base->name : np->full_name;
-
-	of_base->base = of_io_request_and_map(np, of_base->index, name);
+	of_base->base = of_base->name ?
+		of_io_request_and_map(np, of_base->index, of_base->name) :
+		of_iomap(np, of_base->index);
 	if (IS_ERR(of_base->base)) {
-		pr_err("Failed to iomap (%s)\n", name);
+		pr_err("Failed to iomap (%s)\n", of_base->name);
 		return PTR_ERR(of_base->base);
 	}
 
@@ -141,21 +178,21 @@ int __init timer_of_init(struct device_node *np, struct timer_of *to)
 	int flags = 0;
 
 	if (to->flags & TIMER_OF_BASE) {
-		ret = timer_base_init(np, &to->of_base);
+		ret = timer_of_base_init(np, &to->of_base);
 		if (ret)
 			goto out_fail;
 		flags |= TIMER_OF_BASE;
 	}
 
 	if (to->flags & TIMER_OF_CLOCK) {
-		ret = timer_clk_init(np, &to->of_clk);
+		ret = timer_of_clk_init(np, &to->of_clk);
 		if (ret)
 			goto out_fail;
 		flags |= TIMER_OF_CLOCK;
 	}
 
 	if (to->flags & TIMER_OF_IRQ) {
-		ret = timer_irq_init(np, &to->of_irq);
+		ret = timer_of_irq_init(np, &to->of_irq);
 		if (ret)
 			goto out_fail;
 		flags |= TIMER_OF_IRQ;
@@ -163,17 +200,20 @@ int __init timer_of_init(struct device_node *np, struct timer_of *to)
 
 	if (!to->clkevt.name)
 		to->clkevt.name = np->name;
+
+	to->np = np;
+
 	return ret;
 
 out_fail:
 	if (flags & TIMER_OF_IRQ)
-		timer_irq_exit(&to->of_irq);
+		timer_of_irq_exit(&to->of_irq);
 
 	if (flags & TIMER_OF_CLOCK)
-		timer_clk_exit(&to->of_clk);
+		timer_of_clk_exit(&to->of_clk);
 
 	if (flags & TIMER_OF_BASE)
-		timer_base_exit(&to->of_base);
+		timer_of_base_exit(&to->of_base);
 	return ret;
 }
 
@@ -187,11 +227,11 @@ out_fail:
 void __init timer_of_cleanup(struct timer_of *to)
 {
 	if (to->flags & TIMER_OF_IRQ)
-		timer_irq_exit(&to->of_irq);
+		timer_of_irq_exit(&to->of_irq);
 
 	if (to->flags & TIMER_OF_CLOCK)
-		timer_clk_exit(&to->of_clk);
+		timer_of_clk_exit(&to->of_clk);
 
 	if (to->flags & TIMER_OF_BASE)
-		timer_base_exit(&to->of_base);
+		timer_of_base_exit(&to->of_base);
 }
diff --git a/drivers/clocksource/timer-of.h b/drivers/clocksource/timer-of.h
index 3f708f1be43d..a5478f3e8589 100644
--- a/drivers/clocksource/timer-of.h
+++ b/drivers/clocksource/timer-of.h
@@ -33,6 +33,7 @@ struct of_timer_clk {
 
 struct timer_of {
 	unsigned int flags;
+	struct device_node *np;
 	struct clock_event_device clkevt;
 	struct of_timer_base of_base;
 	struct of_timer_irq  of_irq;
diff --git a/drivers/clocksource/timer-sprd.c b/drivers/clocksource/timer-sprd.c
new file mode 100644
index 000000000000..ef9ebeafb3ed
--- /dev/null
+++ b/drivers/clocksource/timer-sprd.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Spreadtrum Communications Inc.
+ */
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+
+#include "timer-of.h"
+
+#define TIMER_NAME		"sprd_timer"
+
+#define TIMER_LOAD_LO		0x0
+#define TIMER_LOAD_HI		0x4
+#define TIMER_VALUE_LO		0x8
+#define TIMER_VALUE_HI		0xc
+
+#define TIMER_CTL		0x10
+#define TIMER_CTL_PERIOD_MODE	BIT(0)
+#define TIMER_CTL_ENABLE	BIT(1)
+#define TIMER_CTL_64BIT_WIDTH	BIT(16)
+
+#define TIMER_INT		0x14
+#define TIMER_INT_EN		BIT(0)
+#define TIMER_INT_RAW_STS	BIT(1)
+#define TIMER_INT_MASK_STS	BIT(2)
+#define TIMER_INT_CLR		BIT(3)
+
+#define TIMER_VALUE_SHDW_LO	0x18
+#define TIMER_VALUE_SHDW_HI	0x1c
+
+#define TIMER_VALUE_LO_MASK	GENMASK(31, 0)
+
+static void sprd_timer_enable(void __iomem *base, u32 flag)
+{
+	u32 val = readl_relaxed(base + TIMER_CTL);
+
+	val |= TIMER_CTL_ENABLE;
+	if (flag & TIMER_CTL_64BIT_WIDTH)
+		val |= TIMER_CTL_64BIT_WIDTH;
+	else
+		val &= ~TIMER_CTL_64BIT_WIDTH;
+
+	if (flag & TIMER_CTL_PERIOD_MODE)
+		val |= TIMER_CTL_PERIOD_MODE;
+	else
+		val &= ~TIMER_CTL_PERIOD_MODE;
+
+	writel_relaxed(val, base + TIMER_CTL);
+}
+
+static void sprd_timer_disable(void __iomem *base)
+{
+	u32 val = readl_relaxed(base + TIMER_CTL);
+
+	val &= ~TIMER_CTL_ENABLE;
+	writel_relaxed(val, base + TIMER_CTL);
+}
+
+static void sprd_timer_update_counter(void __iomem *base, unsigned long cycles)
+{
+	writel_relaxed(cycles & TIMER_VALUE_LO_MASK, base + TIMER_LOAD_LO);
+	writel_relaxed(0, base + TIMER_LOAD_HI);
+}
+
+static void sprd_timer_enable_interrupt(void __iomem *base)
+{
+	writel_relaxed(TIMER_INT_EN, base + TIMER_INT);
+}
+
+static void sprd_timer_clear_interrupt(void __iomem *base)
+{
+	u32 val = readl_relaxed(base + TIMER_INT);
+
+	val |= TIMER_INT_CLR;
+	writel_relaxed(val, base + TIMER_INT);
+}
+
+static int sprd_timer_set_next_event(unsigned long cycles,
+				     struct clock_event_device *ce)
+{
+	struct timer_of *to = to_timer_of(ce);
+
+	sprd_timer_disable(timer_of_base(to));
+	sprd_timer_update_counter(timer_of_base(to), cycles);
+	sprd_timer_enable(timer_of_base(to), 0);
+
+	return 0;
+}
+
+static int sprd_timer_set_periodic(struct clock_event_device *ce)
+{
+	struct timer_of *to = to_timer_of(ce);
+
+	sprd_timer_disable(timer_of_base(to));
+	sprd_timer_update_counter(timer_of_base(to), timer_of_period(to));
+	sprd_timer_enable(timer_of_base(to), TIMER_CTL_PERIOD_MODE);
+
+	return 0;
+}
+
+static int sprd_timer_shutdown(struct clock_event_device *ce)
+{
+	struct timer_of *to = to_timer_of(ce);
+
+	sprd_timer_disable(timer_of_base(to));
+	return 0;
+}
+
+static irqreturn_t sprd_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *ce = (struct clock_event_device *)dev_id;
+	struct timer_of *to = to_timer_of(ce);
+
+	sprd_timer_clear_interrupt(timer_of_base(to));
+
+	if (clockevent_state_oneshot(ce))
+		sprd_timer_disable(timer_of_base(to));
+
+	ce->event_handler(ce);
+	return IRQ_HANDLED;
+}
+
+static struct timer_of to = {
+	.flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK,
+
+	.clkevt = {
+		.name = TIMER_NAME,
+		.rating = 300,
+		.features = CLOCK_EVT_FEAT_DYNIRQ | CLOCK_EVT_FEAT_PERIODIC |
+			CLOCK_EVT_FEAT_ONESHOT,
+		.set_state_shutdown = sprd_timer_shutdown,
+		.set_state_periodic = sprd_timer_set_periodic,
+		.set_next_event = sprd_timer_set_next_event,
+		.cpumask = cpu_possible_mask,
+	},
+
+	.of_irq = {
+		.handler = sprd_timer_interrupt,
+		.flags = IRQF_TIMER | IRQF_IRQPOLL,
+	},
+};
+
+static int __init sprd_timer_init(struct device_node *np)
+{
+	int ret;
+
+	ret = timer_of_init(np, &to);
+	if (ret)
+		return ret;
+
+	sprd_timer_enable_interrupt(timer_of_base(&to));
+	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+					1, UINT_MAX);
+
+	return 0;
+}
+
+TIMER_OF_DECLARE(sc9860_timer, "sprd,sc9860-timer", sprd_timer_init);
diff --git a/drivers/clocksource/timer-stm32.c b/drivers/clocksource/timer-stm32.c
index 8f2423789ba9..e5cdc3af684c 100644
--- a/drivers/clocksource/timer-stm32.c
+++ b/drivers/clocksource/timer-stm32.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
+#include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
@@ -16,175 +17,318 @@
 #include <linux/of_irq.h>
 #include <linux/clk.h>
 #include <linux/reset.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+
+#include "timer-of.h"
 
 #define TIM_CR1		0x00
 #define TIM_DIER	0x0c
 #define TIM_SR		0x10
 #define TIM_EGR		0x14
+#define TIM_CNT		0x24
 #define TIM_PSC		0x28
 #define TIM_ARR		0x2c
+#define TIM_CCR1	0x34
 
 #define TIM_CR1_CEN	BIT(0)
+#define TIM_CR1_UDIS	BIT(1)
 #define TIM_CR1_OPM	BIT(3)
 #define TIM_CR1_ARPE	BIT(7)
 
 #define TIM_DIER_UIE	BIT(0)
+#define TIM_DIER_CC1IE	BIT(1)
 
 #define TIM_SR_UIF	BIT(0)
 
 #define TIM_EGR_UG	BIT(0)
 
-struct stm32_clock_event_ddata {
-	struct clock_event_device evtdev;
-	unsigned periodic_top;
-	void __iomem *base;
+#define TIM_PSC_MAX	USHRT_MAX
+#define TIM_PSC_CLKRATE	10000
+
+struct stm32_timer_private {
+	int bits;
 };
 
-static int stm32_clock_event_shutdown(struct clock_event_device *evtdev)
+/**
+ * stm32_timer_of_bits_set - set accessor helper
+ * @to: a timer_of structure pointer
+ * @bits: the number of bits (16 or 32)
+ *
+ * Accessor helper to set the number of bits in the timer-of private
+ * structure.
+ *
+ */
+static void stm32_timer_of_bits_set(struct timer_of *to, int bits)
 {
-	struct stm32_clock_event_ddata *data =
-		container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
-	void *base = data->base;
+	struct stm32_timer_private *pd = to->private_data;
 
-	writel_relaxed(0, base + TIM_CR1);
-	return 0;
+	pd->bits = bits;
+}
+
+/**
+ * stm32_timer_of_bits_get - get accessor helper
+ * @to: a timer_of structure pointer
+ *
+ * Accessor helper to get the number of bits in the timer-of private
+ * structure.
+ *
+ * Returns an integer corresponding to the number of bits.
+ */
+static int stm32_timer_of_bits_get(struct timer_of *to)
+{
+	struct stm32_timer_private *pd = to->private_data;
+
+	return pd->bits;
+}
+
+static void __iomem *stm32_timer_cnt __read_mostly;
+
+static u64 notrace stm32_read_sched_clock(void)
+{
+	return readl_relaxed(stm32_timer_cnt);
+}
+
+static struct delay_timer stm32_timer_delay;
+
+static unsigned long stm32_read_delay(void)
+{
+	return readl_relaxed(stm32_timer_cnt);
 }
 
-static int stm32_clock_event_set_periodic(struct clock_event_device *evtdev)
+static void stm32_clock_event_disable(struct timer_of *to)
 {
-	struct stm32_clock_event_ddata *data =
-		container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
-	void *base = data->base;
+	writel_relaxed(0, timer_of_base(to) + TIM_DIER);
+}
+
+/**
+ * stm32_timer_start - Start the counter without event
+ * @to: a timer_of structure pointer
+ *
+ * Start the timer in order to have the counter reset and start
+ * incrementing but disable interrupt event when there is a counter
+ * overflow. By default, the counter direction is used as upcounter.
+ */
+static void stm32_timer_start(struct timer_of *to)
+{
+	writel_relaxed(TIM_CR1_UDIS | TIM_CR1_CEN, timer_of_base(to) + TIM_CR1);
+}
+
+static int stm32_clock_event_shutdown(struct clock_event_device *clkevt)
+{
+	struct timer_of *to = to_timer_of(clkevt);
+
+	stm32_clock_event_disable(to);
 
-	writel_relaxed(data->periodic_top, base + TIM_ARR);
-	writel_relaxed(TIM_CR1_ARPE | TIM_CR1_CEN, base + TIM_CR1);
 	return 0;
 }
 
 static int stm32_clock_event_set_next_event(unsigned long evt,
-					    struct clock_event_device *evtdev)
+					    struct clock_event_device *clkevt)
 {
-	struct stm32_clock_event_ddata *data =
-		container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
+	struct timer_of *to = to_timer_of(clkevt);
+	unsigned long now, next;
+
+	next = readl_relaxed(timer_of_base(to) + TIM_CNT) + evt;
+	writel_relaxed(next, timer_of_base(to) + TIM_CCR1);
+	now = readl_relaxed(timer_of_base(to) + TIM_CNT);
+
+	if ((next - now) > evt)
+		return -ETIME;
 
-	writel_relaxed(evt, data->base + TIM_ARR);
-	writel_relaxed(TIM_CR1_ARPE | TIM_CR1_OPM | TIM_CR1_CEN,
-		       data->base + TIM_CR1);
+	writel_relaxed(TIM_DIER_CC1IE, timer_of_base(to) + TIM_DIER);
+
+	return 0;
+}
+
+static int stm32_clock_event_set_periodic(struct clock_event_device *clkevt)
+{
+	struct timer_of *to = to_timer_of(clkevt);
+
+	stm32_timer_start(to);
+
+	return stm32_clock_event_set_next_event(timer_of_period(to), clkevt);
+}
+
+static int stm32_clock_event_set_oneshot(struct clock_event_device *clkevt)
+{
+	struct timer_of *to = to_timer_of(clkevt);
+
+	stm32_timer_start(to);
 
 	return 0;
 }
 
 static irqreturn_t stm32_clock_event_handler(int irq, void *dev_id)
 {
-	struct stm32_clock_event_ddata *data = dev_id;
+	struct clock_event_device *clkevt = (struct clock_event_device *)dev_id;
+	struct timer_of *to = to_timer_of(clkevt);
+
+	writel_relaxed(0, timer_of_base(to) + TIM_SR);
 
-	writel_relaxed(0, data->base + TIM_SR);
+	if (clockevent_state_periodic(clkevt))
+		stm32_clock_event_set_periodic(clkevt);
+	else
+		stm32_clock_event_shutdown(clkevt);
 
-	data->evtdev.event_handler(&data->evtdev);
+	clkevt->event_handler(clkevt);
 
 	return IRQ_HANDLED;
 }
 
-static struct stm32_clock_event_ddata clock_event_ddata = {
-	.evtdev = {
-		.name = "stm32 clockevent",
-		.features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-		.set_state_shutdown = stm32_clock_event_shutdown,
-		.set_state_periodic = stm32_clock_event_set_periodic,
-		.set_state_oneshot = stm32_clock_event_shutdown,
-		.tick_resume = stm32_clock_event_shutdown,
-		.set_next_event = stm32_clock_event_set_next_event,
-		.rating = 200,
-	},
-};
+/**
+ * stm32_timer_width - Sort out the timer width (32/16)
+ * @to: a pointer to a timer-of structure
+ *
+ * Write the 32-bit max value and read/return the result. If the timer
+ * is 32 bits wide, the result will be UINT_MAX, otherwise it will
+ * be truncated by the 16-bit register to USHRT_MAX.
+ *
+ */
+static void __init stm32_timer_set_width(struct timer_of *to)
+{
+	u32 width;
+
+	writel_relaxed(UINT_MAX, timer_of_base(to) + TIM_ARR);
+
+	width = readl_relaxed(timer_of_base(to) + TIM_ARR);
+
+	stm32_timer_of_bits_set(to, width == UINT_MAX ? 32 : 16);
+}
 
-static int __init stm32_clockevent_init(struct device_node *np)
+/**
+ * stm32_timer_set_prescaler - Compute and set the prescaler register
+ * @to: a pointer to a timer-of structure
+ *
+ * Depending on the timer width, compute the prescaler to always
+ * target a 10MHz timer rate for 16 bits. 32-bit timers are
+ * considered precise and long enough to not use the prescaler.
+ */
+static void __init stm32_timer_set_prescaler(struct timer_of *to)
 {
-	struct stm32_clock_event_ddata *data = &clock_event_ddata;
-	struct clk *clk;
-	struct reset_control *rstc;
-	unsigned long rate, max_delta;
-	int irq, ret, bits, prescaler = 1;
-
-	clk = of_clk_get(np, 0);
-	if (IS_ERR(clk)) {
-		ret = PTR_ERR(clk);
-		pr_err("failed to get clock for clockevent (%d)\n", ret);
-		goto err_clk_get;
+	int prescaler = 1;
+
+	if (stm32_timer_of_bits_get(to) != 32) {
+		prescaler = DIV_ROUND_CLOSEST(timer_of_rate(to),
+					      TIM_PSC_CLKRATE);
+		/*
+		 * The prescaler register is an u16, the variable
+		 * can't be greater than TIM_PSC_MAX, let's cap it in
+		 * this case.
+		 */
+		prescaler = prescaler < TIM_PSC_MAX ? prescaler : TIM_PSC_MAX;
 	}
 
-	ret = clk_prepare_enable(clk);
-	if (ret) {
-		pr_err("failed to enable timer clock for clockevent (%d)\n",
-		       ret);
-		goto err_clk_enable;
-	}
+	writel_relaxed(prescaler - 1, timer_of_base(to) + TIM_PSC);
+	writel_relaxed(TIM_EGR_UG, timer_of_base(to) + TIM_EGR);
+	writel_relaxed(0, timer_of_base(to) + TIM_SR);
 
-	rate = clk_get_rate(clk);
+	/* Adjust rate and period given the prescaler value */
+	to->of_clk.rate = DIV_ROUND_CLOSEST(to->of_clk.rate, prescaler);
+	to->of_clk.period = DIV_ROUND_UP(to->of_clk.rate, HZ);
+}
 
-	rstc = of_reset_control_get(np, NULL);
-	if (!IS_ERR(rstc)) {
-		reset_control_assert(rstc);
-		reset_control_deassert(rstc);
+static int __init stm32_clocksource_init(struct timer_of *to)
+{
+        u32 bits = stm32_timer_of_bits_get(to);
+	const char *name = to->np->full_name;
+
+	/*
+	 * This driver allows to register several timers and relies on
+	 * the generic time framework to select the right one.
+	 * However, nothing allows to do the same for the
+	 * sched_clock. We are not interested in a sched_clock for the
+	 * 16-bit timers but only for the 32-bit one, so if no 32-bit
+	 * timer is registered yet, we select this 32-bit timer as a
+	 * sched_clock.
+	 */
+	if (bits == 32 && !stm32_timer_cnt) {
+
+		/*
+		 * Start immediately the counter as we will be using
+		 * it right after.
+		 */
+		stm32_timer_start(to);
+
+		stm32_timer_cnt = timer_of_base(to) + TIM_CNT;
+		sched_clock_register(stm32_read_sched_clock, bits, timer_of_rate(to));
+		pr_info("%s: STM32 sched_clock registered\n", name);
+
+		stm32_timer_delay.read_current_timer = stm32_read_delay;
+		stm32_timer_delay.freq = timer_of_rate(to);
+		register_current_timer_delay(&stm32_timer_delay);
+		pr_info("%s: STM32 delay timer registered\n", name);
 	}
 
-	data->base = of_iomap(np, 0);
-	if (!data->base) {
-		ret = -ENXIO;
-		pr_err("failed to map registers for clockevent\n");
-		goto err_iomap;
-	}
+	return clocksource_mmio_init(timer_of_base(to) + TIM_CNT, name,
+				     timer_of_rate(to), bits == 32 ? 250 : 100,
+				     bits, clocksource_mmio_readl_up);
+}
 
-	irq = irq_of_parse_and_map(np, 0);
-	if (!irq) {
-		ret = -EINVAL;
-		pr_err("%pOF: failed to get irq.\n", np);
-		goto err_get_irq;
-	}
+static void __init stm32_clockevent_init(struct timer_of *to)
+{
+	u32 bits = stm32_timer_of_bits_get(to);
 
-	/* Detect whether the timer is 16 or 32 bits */
-	writel_relaxed(~0U, data->base + TIM_ARR);
-	max_delta = readl_relaxed(data->base + TIM_ARR);
-	if (max_delta == ~0U) {
-		prescaler = 1;
-		bits = 32;
-	} else {
-		prescaler = 1024;
-		bits = 16;
-	}
-	writel_relaxed(0, data->base + TIM_ARR);
+	to->clkevt.name = to->np->full_name;
+	to->clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+	to->clkevt.set_state_shutdown = stm32_clock_event_shutdown;
+	to->clkevt.set_state_periodic = stm32_clock_event_set_periodic;
+	to->clkevt.set_state_oneshot = stm32_clock_event_set_oneshot;
+	to->clkevt.tick_resume = stm32_clock_event_shutdown;
+	to->clkevt.set_next_event = stm32_clock_event_set_next_event;
+	to->clkevt.rating = bits == 32 ? 250 : 100;
+
+	clockevents_config_and_register(&to->clkevt, timer_of_rate(to), 0x1,
+					(1 <<  bits) - 1);
+
+	pr_info("%pOF: STM32 clockevent driver initialized (%d bits)\n",
+		to->np, bits);
+}
+
+static int __init stm32_timer_init(struct device_node *node)
+{
+	struct reset_control *rstc;
+	struct timer_of *to;
+	int ret;
+
+	to = kzalloc(sizeof(*to), GFP_KERNEL);
+	if (!to)
+		return -ENOMEM;
 
-	writel_relaxed(prescaler - 1, data->base + TIM_PSC);
-	writel_relaxed(TIM_EGR_UG, data->base + TIM_EGR);
-	writel_relaxed(TIM_DIER_UIE, data->base + TIM_DIER);
-	writel_relaxed(0, data->base + TIM_SR);
+	to->flags = TIMER_OF_IRQ | TIMER_OF_CLOCK | TIMER_OF_BASE;
+	to->of_irq.handler = stm32_clock_event_handler;
 
-	data->periodic_top = DIV_ROUND_CLOSEST(rate, prescaler * HZ);
+	ret = timer_of_init(node, to);
+	if (ret)
+		goto err;
 
-	clockevents_config_and_register(&data->evtdev,
-					DIV_ROUND_CLOSEST(rate, prescaler),
-					0x1, max_delta);
+	to->private_data = kzalloc(sizeof(struct stm32_timer_private),
+				   GFP_KERNEL);
+	if (!to->private_data)
+		goto deinit;
 
-	ret = request_irq(irq, stm32_clock_event_handler, IRQF_TIMER,
-			"stm32 clockevent", data);
-	if (ret) {
-		pr_err("%pOF: failed to request irq.\n", np);
-		goto err_get_irq;
+	rstc = of_reset_control_get(node, NULL);
+	if (!IS_ERR(rstc)) {
+		reset_control_assert(rstc);
+		reset_control_deassert(rstc);
 	}
 
-	pr_info("%pOF: STM32 clockevent driver initialized (%d bits)\n",
-			np, bits);
+	stm32_timer_set_width(to);
 
-	return ret;
+	stm32_timer_set_prescaler(to);
+
+	ret = stm32_clocksource_init(to);
+	if (ret)
+		goto deinit;
+
+	stm32_clockevent_init(to);
+	return 0;
 
-err_get_irq:
-	iounmap(data->base);
-err_iomap:
-	clk_disable_unprepare(clk);
-err_clk_enable:
-	clk_put(clk);
-err_clk_get:
+deinit:
+	timer_of_cleanup(to);
+err:
+	kfree(to);
 	return ret;
 }
 
-TIMER_OF_DECLARE(stm32, "st,stm32-timer", stm32_clockevent_init);
+TIMER_OF_DECLARE(stm32, "st,stm32-timer", stm32_timer_init);
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 4ebae43118ef..d8addbce40bc 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -275,6 +275,7 @@ config BMIPS_CPUFREQ
 
 config LOONGSON2_CPUFREQ
 	tristate "Loongson2 CPUFreq Driver"
+	depends on LEMOTE_MACH2F
 	help
 	  This option adds a CPUFreq driver for loongson processors which
 	  support software configurable cpu frequency.
@@ -287,6 +288,7 @@ config LOONGSON2_CPUFREQ
 
 config LOONGSON1_CPUFREQ
 	tristate "Loongson1 CPUFreq Driver"
+	depends on LOONGSON1_LS1B
 	help
 	  This option adds a CPUFreq driver for loongson1 processors which
 	  support software configurable cpu frequency.
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index bdce4488ded1..3a88e33b0cfe 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -2,6 +2,29 @@
 # ARM CPU Frequency scaling drivers
 #
 
+config ACPI_CPPC_CPUFREQ
+	tristate "CPUFreq driver based on the ACPI CPPC spec"
+	depends on ACPI_PROCESSOR
+	select ACPI_CPPC_LIB
+	help
+	  This adds a CPUFreq driver which uses CPPC methods
+	  as described in the ACPIv5.1 spec. CPPC stands for
+	  Collaborative Processor Performance Controls. It
+	  is based on an abstract continuous scale of CPU
+	  performance values which allows the remote power
+	  processor to flexibly optimize for power and
+	  performance. CPPC relies on power management firmware
+	  support for its operation.
+
+	  If in doubt, say N.
+
+config ARM_ARMADA_37XX_CPUFREQ
+	tristate "Armada 37xx CPUFreq support"
+	depends on ARCH_MVEBU
+	help
+	  This adds the CPUFreq driver support for Marvell Armada 37xx SoCs.
+	  The Armada 37xx PMU supports 4 frequency and VDD levels.
+
 # big LITTLE core layer and glue drivers
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
@@ -12,6 +35,30 @@ config ARM_BIG_LITTLE_CPUFREQ
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
 
+config ARM_DT_BL_CPUFREQ
+	tristate "Generic probing via DT for ARM big LITTLE CPUfreq driver"
+	depends on ARM_BIG_LITTLE_CPUFREQ && OF
+	help
+	  This enables probing via DT for Generic CPUfreq driver for ARM
+	  big.LITTLE platform. This gets frequency tables from DT.
+
+config ARM_SCPI_CPUFREQ
+	tristate "SCPI based CPUfreq driver"
+	depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
+	help
+	  This adds the CPUfreq driver support for ARM big.LITTLE platforms
+	  using SCPI protocol for CPU power management.
+
+	  This driver uses SCPI Message Protocol driver to interact with the
+	  firmware providing the CPU DVFS functionality.
+
+config ARM_VEXPRESS_SPC_CPUFREQ
+	tristate "Versatile Express SPC based CPUfreq driver"
+	depends on ARM_BIG_LITTLE_CPUFREQ && ARCH_VEXPRESS_SPC
+	help
+	  This add the CPUfreq driver support for Versatile Express
+	  big.LITTLE platforms using SPC for power management.
+
 config ARM_BRCMSTB_AVS_CPUFREQ
 	tristate "Broadcom STB AVS CPUfreq driver"
 	depends on ARCH_BRCMSTB || COMPILE_TEST
@@ -33,20 +80,6 @@ config ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
 
 	  If in doubt, say N.
 
-config ARM_DT_BL_CPUFREQ
-	tristate "Generic probing via DT for ARM big LITTLE CPUfreq driver"
-	depends on ARM_BIG_LITTLE_CPUFREQ && OF
-	help
-	  This enables probing via DT for Generic CPUfreq driver for ARM
-	  big.LITTLE platform. This gets frequency tables from DT.
-
-config ARM_VEXPRESS_SPC_CPUFREQ
-        tristate "Versatile Express SPC based CPUfreq driver"
-	depends on ARM_BIG_LITTLE_CPUFREQ && ARCH_VEXPRESS_SPC
-        help
-          This add the CPUfreq driver support for Versatile Express
-	  big.LITTLE platforms using SPC for power management.
-
 config ARM_EXYNOS5440_CPUFREQ
 	tristate "SAMSUNG EXYNOS5440"
 	depends on SOC_EXYNOS5440
@@ -205,16 +238,6 @@ config ARM_SA1100_CPUFREQ
 config ARM_SA1110_CPUFREQ
 	bool
 
-config ARM_SCPI_CPUFREQ
-        tristate "SCPI based CPUfreq driver"
-	depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
-        help
-	  This adds the CPUfreq driver support for ARM big.LITTLE platforms
-	  using SCPI protocol for CPU power management.
-
-	  This driver uses SCPI Message Protocol driver to interact with the
-	  firmware providing the CPU DVFS functionality.
-
 config ARM_SPEAR_CPUFREQ
 	bool "SPEAr CPUFreq support"
 	depends on PLAT_SPEAR
@@ -275,20 +298,3 @@ config ARM_PXA2xx_CPUFREQ
 	  This add the CPUFreq driver support for Intel PXA2xx SOCs.
 
 	  If in doubt, say N.
-
-config ACPI_CPPC_CPUFREQ
-	tristate "CPUFreq driver based on the ACPI CPPC spec"
-	depends on ACPI_PROCESSOR
-	select ACPI_CPPC_LIB
-	default n
-	help
-	  This adds a CPUFreq driver which uses CPPC methods
-	  as described in the ACPIv5.1 spec. CPPC stands for
-	  Collaborative Processor Performance Controls. It
-	  is based on an abstract continuous scale of CPU
-	  performance values which allows the remote power
-	  processor to flexibly optimize for power and
-	  performance. CPPC relies on power management firmware
-	  support for its operation.
-
-	  If in doubt, say N.
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 812f9e0d01a3..e07715ce8844 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -52,23 +52,26 @@ obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ)	+= arm_big_little.o
 # LITTLE drivers, so that it is probed last.
 obj-$(CONFIG_ARM_DT_BL_CPUFREQ)		+= arm_big_little_dt.o
 
+obj-$(CONFIG_ARM_ARMADA_37XX_CPUFREQ)	+= armada-37xx-cpufreq.o
 obj-$(CONFIG_ARM_BRCMSTB_AVS_CPUFREQ)	+= brcmstb-avs-cpufreq.o
+obj-$(CONFIG_ACPI_CPPC_CPUFREQ)		+= cppc_cpufreq.o
 obj-$(CONFIG_ARCH_DAVINCI)		+= davinci-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS5440_CPUFREQ)	+= exynos5440-cpufreq.o
 obj-$(CONFIG_ARM_HIGHBANK_CPUFREQ)	+= highbank-cpufreq.o
 obj-$(CONFIG_ARM_IMX6Q_CPUFREQ)		+= imx6q-cpufreq.o
 obj-$(CONFIG_ARM_KIRKWOOD_CPUFREQ)	+= kirkwood-cpufreq.o
 obj-$(CONFIG_ARM_MEDIATEK_CPUFREQ)	+= mediatek-cpufreq.o
+obj-$(CONFIG_MACH_MVEBU_V7)		+= mvebu-cpufreq.o
 obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ)	+= omap-cpufreq.o
 obj-$(CONFIG_ARM_PXA2xx_CPUFREQ)	+= pxa2xx-cpufreq.o
 obj-$(CONFIG_PXA3xx)			+= pxa3xx-cpufreq.o
-obj-$(CONFIG_ARM_S3C24XX_CPUFREQ)	+= s3c24xx-cpufreq.o
-obj-$(CONFIG_ARM_S3C24XX_CPUFREQ_DEBUGFS) += s3c24xx-cpufreq-debugfs.o
 obj-$(CONFIG_ARM_S3C2410_CPUFREQ)	+= s3c2410-cpufreq.o
 obj-$(CONFIG_ARM_S3C2412_CPUFREQ)	+= s3c2412-cpufreq.o
 obj-$(CONFIG_ARM_S3C2416_CPUFREQ)	+= s3c2416-cpufreq.o
 obj-$(CONFIG_ARM_S3C2440_CPUFREQ)	+= s3c2440-cpufreq.o
 obj-$(CONFIG_ARM_S3C64XX_CPUFREQ)	+= s3c64xx-cpufreq.o
+obj-$(CONFIG_ARM_S3C24XX_CPUFREQ)	+= s3c24xx-cpufreq.o
+obj-$(CONFIG_ARM_S3C24XX_CPUFREQ_DEBUGFS) += s3c24xx-cpufreq-debugfs.o
 obj-$(CONFIG_ARM_S5PV210_CPUFREQ)	+= s5pv210-cpufreq.o
 obj-$(CONFIG_ARM_SA1100_CPUFREQ)	+= sa1100-cpufreq.o
 obj-$(CONFIG_ARM_SA1110_CPUFREQ)	+= sa1110-cpufreq.o
@@ -81,8 +84,6 @@ obj-$(CONFIG_ARM_TEGRA124_CPUFREQ)	+= tegra124-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA186_CPUFREQ)	+= tegra186-cpufreq.o
 obj-$(CONFIG_ARM_TI_CPUFREQ)		+= ti-cpufreq.o
 obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ)	+= vexpress-spc-cpufreq.o
-obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o
-obj-$(CONFIG_MACH_MVEBU_V7)		+= mvebu-cpufreq.o
 
 
 ##################################################################################
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index 65ec5f01aa8d..c56b57dcfda5 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -526,34 +526,13 @@ static int bL_cpufreq_exit(struct cpufreq_policy *policy)
 
 static void bL_cpufreq_ready(struct cpufreq_policy *policy)
 {
-	struct device *cpu_dev = get_cpu_device(policy->cpu);
 	int cur_cluster = cpu_to_cluster(policy->cpu);
-	struct device_node *np;
 
 	/* Do not register a cpu_cooling device if we are in IKS mode */
 	if (cur_cluster >= MAX_CLUSTERS)
 		return;
 
-	np = of_node_get(cpu_dev->of_node);
-	if (WARN_ON(!np))
-		return;
-
-	if (of_find_property(np, "#cooling-cells", NULL)) {
-		u32 power_coefficient = 0;
-
-		of_property_read_u32(np, "dynamic-power-coefficient",
-				     &power_coefficient);
-
-		cdev[cur_cluster] = of_cpufreq_power_cooling_register(np,
-				policy, power_coefficient, NULL);
-		if (IS_ERR(cdev[cur_cluster])) {
-			dev_err(cpu_dev,
-				"running cpufreq without cooling device: %ld\n",
-				PTR_ERR(cdev[cur_cluster]));
-			cdev[cur_cluster] = NULL;
-		}
-	}
-	of_node_put(np);
+	cdev[cur_cluster] = of_cpufreq_cooling_register(policy);
 }
 
 static struct cpufreq_driver bL_cpufreq_driver = {
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
new file mode 100644
index 000000000000..c6ebc88a7d8d
--- /dev/null
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -0,0 +1,241 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * CPU frequency scaling support for Armada 37xx platform.
+ *
+ * Copyright (C) 2017 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+/* Power management in North Bridge register set */
+#define ARMADA_37XX_NB_L0L1	0x18
+#define ARMADA_37XX_NB_L2L3	0x1C
+#define  ARMADA_37XX_NB_TBG_DIV_OFF	13
+#define  ARMADA_37XX_NB_TBG_DIV_MASK	0x7
+#define  ARMADA_37XX_NB_CLK_SEL_OFF	11
+#define  ARMADA_37XX_NB_CLK_SEL_MASK	0x1
+#define  ARMADA_37XX_NB_CLK_SEL_TBG	0x1
+#define  ARMADA_37XX_NB_TBG_SEL_OFF	9
+#define  ARMADA_37XX_NB_TBG_SEL_MASK	0x3
+#define  ARMADA_37XX_NB_VDD_SEL_OFF	6
+#define  ARMADA_37XX_NB_VDD_SEL_MASK	0x3
+#define  ARMADA_37XX_NB_CONFIG_SHIFT	16
+#define ARMADA_37XX_NB_DYN_MOD	0x24
+#define  ARMADA_37XX_NB_CLK_SEL_EN	BIT(26)
+#define  ARMADA_37XX_NB_TBG_EN		BIT(28)
+#define  ARMADA_37XX_NB_DIV_EN		BIT(29)
+#define  ARMADA_37XX_NB_VDD_EN		BIT(30)
+#define  ARMADA_37XX_NB_DFS_EN		BIT(31)
+#define ARMADA_37XX_NB_CPU_LOAD 0x30
+#define  ARMADA_37XX_NB_CPU_LOAD_MASK	0x3
+#define  ARMADA_37XX_DVFS_LOAD_0	0
+#define  ARMADA_37XX_DVFS_LOAD_1	1
+#define  ARMADA_37XX_DVFS_LOAD_2	2
+#define  ARMADA_37XX_DVFS_LOAD_3	3
+
+/*
+ * On Armada 37xx the Power management manages 4 level of CPU load,
+ * each level can be associated with a CPU clock source, a CPU
+ * divider, a VDD level, etc...
+ */
+#define LOAD_LEVEL_NR	4
+
+struct armada_37xx_dvfs {
+	u32 cpu_freq_max;
+	u8 divider[LOAD_LEVEL_NR];
+};
+
+static struct armada_37xx_dvfs armada_37xx_dvfs[] = {
+	{.cpu_freq_max = 1200*1000*1000, .divider = {1, 2, 4, 6} },
+	{.cpu_freq_max = 1000*1000*1000, .divider = {1, 2, 4, 5} },
+	{.cpu_freq_max = 800*1000*1000,  .divider = {1, 2, 3, 4} },
+	{.cpu_freq_max = 600*1000*1000,  .divider = {2, 4, 5, 6} },
+};
+
+static struct armada_37xx_dvfs *armada_37xx_cpu_freq_info_get(u32 freq)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(armada_37xx_dvfs); i++) {
+		if (freq == armada_37xx_dvfs[i].cpu_freq_max)
+			return &armada_37xx_dvfs[i];
+	}
+
+	pr_err("Unsupported CPU frequency %d MHz\n", freq/1000000);
+	return NULL;
+}
+
+/*
+ * Setup the four level managed by the hardware. Once the four level
+ * will be configured then the DVFS will be enabled.
+ */
+static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
+						 struct clk *clk, u8 *divider)
+{
+	int load_lvl;
+	struct clk *parent;
+
+	for (load_lvl = 0; load_lvl < LOAD_LEVEL_NR; load_lvl++) {
+		unsigned int reg, mask, val, offset = 0;
+
+		if (load_lvl <= ARMADA_37XX_DVFS_LOAD_1)
+			reg = ARMADA_37XX_NB_L0L1;
+		else
+			reg = ARMADA_37XX_NB_L2L3;
+
+		if (load_lvl == ARMADA_37XX_DVFS_LOAD_0 ||
+		    load_lvl == ARMADA_37XX_DVFS_LOAD_2)
+			offset += ARMADA_37XX_NB_CONFIG_SHIFT;
+
+		/* Set cpu clock source, for all the level we use TBG */
+		val = ARMADA_37XX_NB_CLK_SEL_TBG << ARMADA_37XX_NB_CLK_SEL_OFF;
+		mask = (ARMADA_37XX_NB_CLK_SEL_MASK
+			<< ARMADA_37XX_NB_CLK_SEL_OFF);
+
+		/*
+		 * Set cpu divider based on the pre-computed array in
+		 * order to have balanced step.
+		 */
+		val |= divider[load_lvl] << ARMADA_37XX_NB_TBG_DIV_OFF;
+		mask |= (ARMADA_37XX_NB_TBG_DIV_MASK
+			<< ARMADA_37XX_NB_TBG_DIV_OFF);
+
+		/* Set VDD divider which is actually the load level. */
+		val |= load_lvl << ARMADA_37XX_NB_VDD_SEL_OFF;
+		mask |= (ARMADA_37XX_NB_VDD_SEL_MASK
+			<< ARMADA_37XX_NB_VDD_SEL_OFF);
+
+		val <<= offset;
+		mask <<= offset;
+
+		regmap_update_bits(base, reg, mask, val);
+	}
+
+	/*
+	 * Set cpu clock source, for all the level we keep the same
+	 * clock source that the one already configured. For this one
+	 * we need to use the clock framework
+	 */
+	parent = clk_get_parent(clk);
+	clk_set_parent(clk, parent);
+}
+
+static void __init armada37xx_cpufreq_disable_dvfs(struct regmap *base)
+{
+	unsigned int reg = ARMADA_37XX_NB_DYN_MOD,
+		mask = ARMADA_37XX_NB_DFS_EN;
+
+	regmap_update_bits(base, reg, mask, 0);
+}
+
+static void __init armada37xx_cpufreq_enable_dvfs(struct regmap *base)
+{
+	unsigned int val, reg = ARMADA_37XX_NB_CPU_LOAD,
+		mask = ARMADA_37XX_NB_CPU_LOAD_MASK;
+
+	/* Start with the highest load (0) */
+	val = ARMADA_37XX_DVFS_LOAD_0;
+	regmap_update_bits(base, reg, mask, val);
+
+	/* Now enable DVFS for the CPUs */
+	reg = ARMADA_37XX_NB_DYN_MOD;
+	mask =	ARMADA_37XX_NB_CLK_SEL_EN | ARMADA_37XX_NB_TBG_EN |
+		ARMADA_37XX_NB_DIV_EN | ARMADA_37XX_NB_VDD_EN |
+		ARMADA_37XX_NB_DFS_EN;
+
+	regmap_update_bits(base, reg, mask, mask);
+}
+
+static int __init armada37xx_cpufreq_driver_init(void)
+{
+	struct armada_37xx_dvfs *dvfs;
+	struct platform_device *pdev;
+	unsigned int cur_frequency;
+	struct regmap *nb_pm_base;
+	struct device *cpu_dev;
+	int load_lvl, ret;
+	struct clk *clk;
+
+	nb_pm_base =
+		syscon_regmap_lookup_by_compatible("marvell,armada-3700-nb-pm");
+
+	if (IS_ERR(nb_pm_base))
+		return -ENODEV;
+
+	/* Before doing any configuration on the DVFS first, disable it */
+	armada37xx_cpufreq_disable_dvfs(nb_pm_base);
+
+	/*
+	 * On CPU 0 register the operating points supported (which are
+	 * the nominal CPU frequency and full integer divisions of
+	 * it).
+	 */
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev) {
+		dev_err(cpu_dev, "Cannot get CPU\n");
+		return -ENODEV;
+	}
+
+	clk = clk_get(cpu_dev, 0);
+	if (IS_ERR(clk)) {
+		dev_err(cpu_dev, "Cannot get clock for CPU0\n");
+		return PTR_ERR(clk);
+	}
+
+	/* Get nominal (current) CPU frequency */
+	cur_frequency = clk_get_rate(clk);
+	if (!cur_frequency) {
+		dev_err(cpu_dev, "Failed to get clock rate for CPU\n");
+		return -EINVAL;
+	}
+
+	dvfs = armada_37xx_cpu_freq_info_get(cur_frequency);
+	if (!dvfs)
+		return -EINVAL;
+
+	armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider);
+
+	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
+	     load_lvl++) {
+		unsigned long freq = cur_frequency / dvfs->divider[load_lvl];
+
+		ret = dev_pm_opp_add(cpu_dev, freq, 0);
+		if (ret) {
+			/* clean-up the already added opp before leaving */
+			while (load_lvl-- > ARMADA_37XX_DVFS_LOAD_0) {
+				freq = cur_frequency / dvfs->divider[load_lvl];
+				dev_pm_opp_remove(cpu_dev, freq);
+			}
+			return ret;
+		}
+	}
+
+	/* Now that everything is setup, enable the DVFS at hardware level */
+	armada37xx_cpufreq_enable_dvfs(nb_pm_base);
+
+	pdev = platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
+
+	return PTR_ERR_OR_ZERO(pdev);
+}
+/* late_initcall, to guarantee the driver is loaded after A37xx clock driver */
+late_initcall(armada37xx_cpufreq_driver_init);
+
+MODULE_AUTHOR("Gregory CLEMENT <gregory.clement@free-electrons.com>");
+MODULE_DESCRIPTION("Armada 37xx cpufreq driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index ecc56e26f8f6..3b585e4bfac5 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -108,6 +108,14 @@ static const struct of_device_id blacklist[] __initconst = {
 
 	{ .compatible = "marvell,armadaxp", },
 
+	{ .compatible = "mediatek,mt2701", },
+	{ .compatible = "mediatek,mt2712", },
+	{ .compatible = "mediatek,mt7622", },
+	{ .compatible = "mediatek,mt7623", },
+	{ .compatible = "mediatek,mt817x", },
+	{ .compatible = "mediatek,mt8173", },
+	{ .compatible = "mediatek,mt8176", },
+
 	{ .compatible = "nvidia,tegra124", },
 
 	{ .compatible = "st,stih407", },
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 545946ad0752..de3d104c25d7 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -319,33 +319,8 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 static void cpufreq_ready(struct cpufreq_policy *policy)
 {
 	struct private_data *priv = policy->driver_data;
-	struct device_node *np = of_node_get(priv->cpu_dev->of_node);
 
-	if (WARN_ON(!np))
-		return;
-
-	/*
-	 * For now, just loading the cooling device;
-	 * thermal DT code takes care of matching them.
-	 */
-	if (of_find_property(np, "#cooling-cells", NULL)) {
-		u32 power_coefficient = 0;
-
-		of_property_read_u32(np, "dynamic-power-coefficient",
-				     &power_coefficient);
-
-		priv->cdev = of_cpufreq_power_cooling_register(np,
-				policy, power_coefficient, NULL);
-		if (IS_ERR(priv->cdev)) {
-			dev_err(priv->cpu_dev,
-				"running cpufreq without cooling device: %ld\n",
-				PTR_ERR(priv->cdev));
-
-			priv->cdev = NULL;
-		}
-	}
-
-	of_node_put(np);
+	priv->cdev = of_cpufreq_cooling_register(policy);
 }
 
 static struct cpufreq_driver dt_cpufreq_driver = {
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 41d148af7748..421f318c0e66 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -601,19 +601,18 @@ static struct cpufreq_governor *find_governor(const char *str_governor)
 /**
  * cpufreq_parse_governor - parse a governor string
  */
-static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
-				struct cpufreq_governor **governor)
+static int cpufreq_parse_governor(char *str_governor,
+				  struct cpufreq_policy *policy)
 {
-	int err = -EINVAL;
-
 	if (cpufreq_driver->setpolicy) {
 		if (!strncasecmp(str_governor, "performance", CPUFREQ_NAME_LEN)) {
-			*policy = CPUFREQ_POLICY_PERFORMANCE;
-			err = 0;
-		} else if (!strncasecmp(str_governor, "powersave",
-						CPUFREQ_NAME_LEN)) {
-			*policy = CPUFREQ_POLICY_POWERSAVE;
-			err = 0;
+			policy->policy = CPUFREQ_POLICY_PERFORMANCE;
+			return 0;
+		}
+
+		if (!strncasecmp(str_governor, "powersave", CPUFREQ_NAME_LEN)) {
+			policy->policy = CPUFREQ_POLICY_POWERSAVE;
+			return 0;
 		}
 	} else {
 		struct cpufreq_governor *t;
@@ -621,26 +620,31 @@ static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
 		mutex_lock(&cpufreq_governor_mutex);
 
 		t = find_governor(str_governor);
-
-		if (t == NULL) {
+		if (!t) {
 			int ret;
 
 			mutex_unlock(&cpufreq_governor_mutex);
+
 			ret = request_module("cpufreq_%s", str_governor);
-			mutex_lock(&cpufreq_governor_mutex);
+			if (ret)
+				return -EINVAL;
 
-			if (ret == 0)
-				t = find_governor(str_governor);
-		}
+			mutex_lock(&cpufreq_governor_mutex);
 
-		if (t != NULL) {
-			*governor = t;
-			err = 0;
+			t = find_governor(str_governor);
 		}
+		if (t && !try_module_get(t->owner))
+			t = NULL;
 
 		mutex_unlock(&cpufreq_governor_mutex);
+
+		if (t) {
+			policy->governor = t;
+			return 0;
+		}
 	}
-	return err;
+
+	return -EINVAL;
 }
 
 /**
@@ -760,11 +764,14 @@ static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
 	if (ret != 1)
 		return -EINVAL;
 
-	if (cpufreq_parse_governor(str_governor, &new_policy.policy,
-						&new_policy.governor))
+	if (cpufreq_parse_governor(str_governor, &new_policy))
 		return -EINVAL;
 
 	ret = cpufreq_set_policy(policy, &new_policy);
+
+	if (new_policy.governor)
+		module_put(new_policy.governor->owner);
+
 	return ret ? ret : count;
 }
 
@@ -1044,8 +1051,7 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy)
 		if (policy->last_policy)
 			new_policy.policy = policy->last_policy;
 		else
-			cpufreq_parse_governor(gov->name, &new_policy.policy,
-					       NULL);
+			cpufreq_parse_governor(gov->name, &new_policy);
 	}
 	/* set default policy */
 	return cpufreq_set_policy(policy, &new_policy);
@@ -2160,7 +2166,6 @@ void cpufreq_unregister_governor(struct cpufreq_governor *governor)
 	mutex_lock(&cpufreq_governor_mutex);
 	list_del(&governor->governor_list);
 	mutex_unlock(&cpufreq_governor_mutex);
-	return;
 }
 EXPORT_SYMBOL_GPL(cpufreq_unregister_governor);
 
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 58d4f4e1ad6a..ca38229b045a 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -22,6 +22,8 @@
 
 #include "cpufreq_governor.h"
 
+#define CPUFREQ_DBS_MIN_SAMPLING_INTERVAL	(2 * TICK_NSEC / NSEC_PER_USEC)
+
 static DEFINE_PER_CPU(struct cpu_dbs_info, cpu_dbs);
 
 static DEFINE_MUTEX(gov_dbs_data_mutex);
@@ -47,11 +49,15 @@ ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf,
 {
 	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct policy_dbs_info *policy_dbs;
+	unsigned int sampling_interval;
 	int ret;
-	ret = sscanf(buf, "%u", &dbs_data->sampling_rate);
-	if (ret != 1)
+
+	ret = sscanf(buf, "%u", &sampling_interval);
+	if (ret != 1 || sampling_interval < CPUFREQ_DBS_MIN_SAMPLING_INTERVAL)
 		return -EINVAL;
 
+	dbs_data->sampling_rate = sampling_interval;
+
 	/*
 	 * We are operating under dbs_data->mutex and so the list and its
 	 * entries can't be freed concurrently.
@@ -430,7 +436,14 @@ int cpufreq_dbs_governor_init(struct cpufreq_policy *policy)
 	if (ret)
 		goto free_policy_dbs_info;
 
-	dbs_data->sampling_rate = cpufreq_policy_transition_delay_us(policy);
+	/*
+	 * The sampling interval should not be less than the transition latency
+	 * of the CPU and it also cannot be too small for dbs_update() to work
+	 * correctly.
+	 */
+	dbs_data->sampling_rate = max_t(unsigned int,
+					CPUFREQ_DBS_MIN_SAMPLING_INTERVAL,
+					cpufreq_policy_transition_delay_us(policy));
 
 	if (!have_governor_per_policy())
 		gov->gdbs_data = dbs_data;
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 1e55b5790853..1572129844a5 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -27,7 +27,7 @@ struct cpufreq_stats {
 	unsigned int *trans_table;
 };
 
-static int cpufreq_stats_update(struct cpufreq_stats *stats)
+static void cpufreq_stats_update(struct cpufreq_stats *stats)
 {
 	unsigned long long cur_time = get_jiffies_64();
 
@@ -35,7 +35,6 @@ static int cpufreq_stats_update(struct cpufreq_stats *stats)
 	stats->time_in_state[stats->last_index] += cur_time - stats->last_time;
 	stats->last_time = cur_time;
 	spin_unlock(&cpufreq_stats_lock);
-	return 0;
 }
 
 static void cpufreq_stats_clear_table(struct cpufreq_stats *stats)
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 628fe899cb48..741f22e5cee3 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -25,15 +25,29 @@ static struct regulator *arm_reg;
 static struct regulator *pu_reg;
 static struct regulator *soc_reg;
 
-static struct clk *arm_clk;
-static struct clk *pll1_sys_clk;
-static struct clk *pll1_sw_clk;
-static struct clk *step_clk;
-static struct clk *pll2_pfd2_396m_clk;
-
-/* clk used by i.MX6UL */
-static struct clk *pll2_bus_clk;
-static struct clk *secondary_sel_clk;
+enum IMX6_CPUFREQ_CLKS {
+	ARM,
+	PLL1_SYS,
+	STEP,
+	PLL1_SW,
+	PLL2_PFD2_396M,
+	/* MX6UL requires two more clks */
+	PLL2_BUS,
+	SECONDARY_SEL,
+};
+#define IMX6Q_CPUFREQ_CLK_NUM		5
+#define IMX6UL_CPUFREQ_CLK_NUM		7
+
+static int num_clks;
+static struct clk_bulk_data clks[] = {
+	{ .id = "arm" },
+	{ .id = "pll1_sys" },
+	{ .id = "step" },
+	{ .id = "pll1_sw" },
+	{ .id = "pll2_pfd2_396m" },
+	{ .id = "pll2_bus" },
+	{ .id = "secondary_sel" },
+};
 
 static struct device *cpu_dev;
 static bool free_opp;
@@ -53,7 +67,7 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 
 	new_freq = freq_table[index].frequency;
 	freq_hz = new_freq * 1000;
-	old_freq = clk_get_rate(arm_clk) / 1000;
+	old_freq = clk_get_rate(clks[ARM].clk) / 1000;
 
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
 	if (IS_ERR(opp)) {
@@ -112,29 +126,35 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 		 * voltage of 528MHz, so lower the CPU frequency to one
 		 * half before changing CPU frequency.
 		 */
-		clk_set_rate(arm_clk, (old_freq >> 1) * 1000);
-		clk_set_parent(pll1_sw_clk, pll1_sys_clk);
-		if (freq_hz > clk_get_rate(pll2_pfd2_396m_clk))
-			clk_set_parent(secondary_sel_clk, pll2_bus_clk);
+		clk_set_rate(clks[ARM].clk, (old_freq >> 1) * 1000);
+		clk_set_parent(clks[PLL1_SW].clk, clks[PLL1_SYS].clk);
+		if (freq_hz > clk_get_rate(clks[PLL2_PFD2_396M].clk))
+			clk_set_parent(clks[SECONDARY_SEL].clk,
+				       clks[PLL2_BUS].clk);
 		else
-			clk_set_parent(secondary_sel_clk, pll2_pfd2_396m_clk);
-		clk_set_parent(step_clk, secondary_sel_clk);
-		clk_set_parent(pll1_sw_clk, step_clk);
+			clk_set_parent(clks[SECONDARY_SEL].clk,
+				       clks[PLL2_PFD2_396M].clk);
+		clk_set_parent(clks[STEP].clk, clks[SECONDARY_SEL].clk);
+		clk_set_parent(clks[PLL1_SW].clk, clks[STEP].clk);
+		if (freq_hz > clk_get_rate(clks[PLL2_BUS].clk)) {
+			clk_set_rate(clks[PLL1_SYS].clk, new_freq * 1000);
+			clk_set_parent(clks[PLL1_SW].clk, clks[PLL1_SYS].clk);
+		}
 	} else {
-		clk_set_parent(step_clk, pll2_pfd2_396m_clk);
-		clk_set_parent(pll1_sw_clk, step_clk);
-		if (freq_hz > clk_get_rate(pll2_pfd2_396m_clk)) {
-			clk_set_rate(pll1_sys_clk, new_freq * 1000);
-			clk_set_parent(pll1_sw_clk, pll1_sys_clk);
+		clk_set_parent(clks[STEP].clk, clks[PLL2_PFD2_396M].clk);
+		clk_set_parent(clks[PLL1_SW].clk, clks[STEP].clk);
+		if (freq_hz > clk_get_rate(clks[PLL2_PFD2_396M].clk)) {
+			clk_set_rate(clks[PLL1_SYS].clk, new_freq * 1000);
+			clk_set_parent(clks[PLL1_SW].clk, clks[PLL1_SYS].clk);
 		} else {
 			/* pll1_sys needs to be enabled for divider rate change to work. */
 			pll1_sys_temp_enabled = true;
-			clk_prepare_enable(pll1_sys_clk);
+			clk_prepare_enable(clks[PLL1_SYS].clk);
 		}
 	}
 
 	/* Ensure the arm clock divider is what we expect */
-	ret = clk_set_rate(arm_clk, new_freq * 1000);
+	ret = clk_set_rate(clks[ARM].clk, new_freq * 1000);
 	if (ret) {
 		dev_err(cpu_dev, "failed to set clock rate: %d\n", ret);
 		regulator_set_voltage_tol(arm_reg, volt_old, 0);
@@ -143,7 +163,7 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 
 	/* PLL1 is only needed until after ARM-PODF is set. */
 	if (pll1_sys_temp_enabled)
-		clk_disable_unprepare(pll1_sys_clk);
+		clk_disable_unprepare(clks[PLL1_SYS].clk);
 
 	/* scaling down?  scale voltage after frequency */
 	if (new_freq < old_freq) {
@@ -174,7 +194,7 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int ret;
 
-	policy->clk = arm_clk;
+	policy->clk = clks[ARM].clk;
 	ret = cpufreq_generic_init(policy, freq_table, transition_latency);
 	policy->suspend_freq = policy->max;
 
@@ -226,23 +246,61 @@ static void imx6q_opp_check_speed_grading(struct device *dev)
 	val >>= OCOTP_CFG3_SPEED_SHIFT;
 	val &= 0x3;
 
-	if ((val != OCOTP_CFG3_SPEED_1P2GHZ) &&
-	     of_machine_is_compatible("fsl,imx6q"))
-		if (dev_pm_opp_disable(dev, 1200000000))
-			dev_warn(dev, "failed to disable 1.2GHz OPP\n");
 	if (val < OCOTP_CFG3_SPEED_996MHZ)
 		if (dev_pm_opp_disable(dev, 996000000))
 			dev_warn(dev, "failed to disable 996MHz OPP\n");
-	if (of_machine_is_compatible("fsl,imx6q")) {
+
+	if (of_machine_is_compatible("fsl,imx6q") ||
+	    of_machine_is_compatible("fsl,imx6qp")) {
 		if (val != OCOTP_CFG3_SPEED_852MHZ)
 			if (dev_pm_opp_disable(dev, 852000000))
 				dev_warn(dev, "failed to disable 852MHz OPP\n");
+		if (val != OCOTP_CFG3_SPEED_1P2GHZ)
+			if (dev_pm_opp_disable(dev, 1200000000))
+				dev_warn(dev, "failed to disable 1.2GHz OPP\n");
 	}
 	iounmap(base);
 put_node:
 	of_node_put(np);
 }
 
+#define OCOTP_CFG3_6UL_SPEED_696MHZ	0x2
+
+static void imx6ul_opp_check_speed_grading(struct device *dev)
+{
+	struct device_node *np;
+	void __iomem *base;
+	u32 val;
+
+	np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-ocotp");
+	if (!np)
+		return;
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		dev_err(dev, "failed to map ocotp\n");
+		goto put_node;
+	}
+
+	/*
+	 * Speed GRADING[1:0] defines the max speed of ARM:
+	 * 2b'00: Reserved;
+	 * 2b'01: 528000000Hz;
+	 * 2b'10: 696000000Hz;
+	 * 2b'11: Reserved;
+	 * We need to set the max speed of ARM according to fuse map.
+	 */
+	val = readl_relaxed(base + OCOTP_CFG3);
+	val >>= OCOTP_CFG3_SPEED_SHIFT;
+	val &= 0x3;
+	if (val != OCOTP_CFG3_6UL_SPEED_696MHZ)
+		if (dev_pm_opp_disable(dev, 696000000))
+			dev_warn(dev, "failed to disable 696MHz OPP\n");
+	iounmap(base);
+put_node:
+	of_node_put(np);
+}
+
 static int imx6q_cpufreq_probe(struct platform_device *pdev)
 {
 	struct device_node *np;
@@ -265,28 +323,15 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
-	arm_clk = clk_get(cpu_dev, "arm");
-	pll1_sys_clk = clk_get(cpu_dev, "pll1_sys");
-	pll1_sw_clk = clk_get(cpu_dev, "pll1_sw");
-	step_clk = clk_get(cpu_dev, "step");
-	pll2_pfd2_396m_clk = clk_get(cpu_dev, "pll2_pfd2_396m");
-	if (IS_ERR(arm_clk) || IS_ERR(pll1_sys_clk) || IS_ERR(pll1_sw_clk) ||
-	    IS_ERR(step_clk) || IS_ERR(pll2_pfd2_396m_clk)) {
-		dev_err(cpu_dev, "failed to get clocks\n");
-		ret = -ENOENT;
-		goto put_clk;
-	}
-
 	if (of_machine_is_compatible("fsl,imx6ul") ||
-	    of_machine_is_compatible("fsl,imx6ull")) {
-		pll2_bus_clk = clk_get(cpu_dev, "pll2_bus");
-		secondary_sel_clk = clk_get(cpu_dev, "secondary_sel");
-		if (IS_ERR(pll2_bus_clk) || IS_ERR(secondary_sel_clk)) {
-			dev_err(cpu_dev, "failed to get clocks specific to imx6ul\n");
-			ret = -ENOENT;
-			goto put_clk;
-		}
-	}
+	    of_machine_is_compatible("fsl,imx6ull"))
+		num_clks = IMX6UL_CPUFREQ_CLK_NUM;
+	else
+		num_clks = IMX6Q_CPUFREQ_CLK_NUM;
+
+	ret = clk_bulk_get(cpu_dev, num_clks, clks);
+	if (ret)
+		goto put_node;
 
 	arm_reg = regulator_get(cpu_dev, "arm");
 	pu_reg = regulator_get_optional(cpu_dev, "pu");
@@ -310,7 +355,10 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 		goto put_reg;
 	}
 
-	imx6q_opp_check_speed_grading(cpu_dev);
+	if (of_machine_is_compatible("fsl,imx6ul"))
+		imx6ul_opp_check_speed_grading(cpu_dev);
+	else
+		imx6q_opp_check_speed_grading(cpu_dev);
 
 	/* Because we have added the OPPs here, we must free them */
 	free_opp = true;
@@ -423,22 +471,11 @@ put_reg:
 		regulator_put(pu_reg);
 	if (!IS_ERR(soc_reg))
 		regulator_put(soc_reg);
-put_clk:
-	if (!IS_ERR(arm_clk))
-		clk_put(arm_clk);
-	if (!IS_ERR(pll1_sys_clk))
-		clk_put(pll1_sys_clk);
-	if (!IS_ERR(pll1_sw_clk))
-		clk_put(pll1_sw_clk);
-	if (!IS_ERR(step_clk))
-		clk_put(step_clk);
-	if (!IS_ERR(pll2_pfd2_396m_clk))
-		clk_put(pll2_pfd2_396m_clk);
-	if (!IS_ERR(pll2_bus_clk))
-		clk_put(pll2_bus_clk);
-	if (!IS_ERR(secondary_sel_clk))
-		clk_put(secondary_sel_clk);
+
+	clk_bulk_put(num_clks, clks);
+put_node:
 	of_node_put(np);
+
 	return ret;
 }
 
@@ -452,13 +489,8 @@ static int imx6q_cpufreq_remove(struct platform_device *pdev)
 	if (!IS_ERR(pu_reg))
 		regulator_put(pu_reg);
 	regulator_put(soc_reg);
-	clk_put(arm_clk);
-	clk_put(pll1_sys_clk);
-	clk_put(pll1_sw_clk);
-	clk_put(step_clk);
-	clk_put(pll2_pfd2_396m_clk);
-	clk_put(pll2_bus_clk);
-	clk_put(secondary_sel_clk);
+
+	clk_bulk_put(num_clks, clks);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 93a0e88bef76..7edf7a0e5a96 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1595,15 +1595,6 @@ static const struct pstate_funcs knl_funcs = {
 	.get_val = core_get_val,
 };
 
-static const struct pstate_funcs bxt_funcs = {
-	.get_max = core_get_max_pstate,
-	.get_max_physical = core_get_max_pstate_physical,
-	.get_min = core_get_min_pstate,
-	.get_turbo = core_get_turbo_pstate,
-	.get_scaling = core_get_scaling,
-	.get_val = core_get_val,
-};
-
 #define ICPU(model, policy) \
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\
 			(unsigned long)&policy }
@@ -1627,8 +1618,9 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(INTEL_FAM6_BROADWELL_XEON_D,	core_funcs),
 	ICPU(INTEL_FAM6_XEON_PHI_KNL,		knl_funcs),
 	ICPU(INTEL_FAM6_XEON_PHI_KNM,		knl_funcs),
-	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		bxt_funcs),
-	ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE,       bxt_funcs),
+	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		core_funcs),
+	ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE,       core_funcs),
+	ICPU(INTEL_FAM6_SKYLAKE_X,		core_funcs),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index c46a12df40dd..5faa37c5b091 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -894,7 +894,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy)
 	if ((longhaul_version != TYPE_LONGHAUL_V1) && (scale_voltage != 0))
 		longhaul_setup_voltagescaling();
 
-	policy->cpuinfo.transition_latency = 200000;	/* nsec */
+	policy->transition_delay_us = 200000;	/* usec */
 
 	return cpufreq_table_validate_and_show(policy, longhaul_table);
 }
diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c
index 18c4bd9a5c65..8c04dddd3c28 100644
--- a/drivers/cpufreq/mediatek-cpufreq.c
+++ b/drivers/cpufreq/mediatek-cpufreq.c
@@ -310,28 +310,8 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
 static void mtk_cpufreq_ready(struct cpufreq_policy *policy)
 {
 	struct mtk_cpu_dvfs_info *info = policy->driver_data;
-	struct device_node *np = of_node_get(info->cpu_dev->of_node);
-	u32 capacitance = 0;
 
-	if (WARN_ON(!np))
-		return;
-
-	if (of_find_property(np, "#cooling-cells", NULL)) {
-		of_property_read_u32(np, DYNAMIC_POWER, &capacitance);
-
-		info->cdev = of_cpufreq_power_cooling_register(np,
-						policy, capacitance, NULL);
-
-		if (IS_ERR(info->cdev)) {
-			dev_err(info->cpu_dev,
-				"running cpufreq without cooling device: %ld\n",
-				PTR_ERR(info->cdev));
-
-			info->cdev = NULL;
-		}
-	}
-
-	of_node_put(np);
+	info->cdev = of_cpufreq_cooling_register(policy);
 }
 
 static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
@@ -574,6 +554,7 @@ static struct platform_driver mtk_cpufreq_platdrv = {
 /* List of machines supported by this driver */
 static const struct of_device_id mtk_cpufreq_machines[] __initconst = {
 	{ .compatible = "mediatek,mt2701", },
+	{ .compatible = "mediatek,mt2712", },
 	{ .compatible = "mediatek,mt7622", },
 	{ .compatible = "mediatek,mt7623", },
 	{ .compatible = "mediatek,mt817x", },
@@ -620,3 +601,7 @@ static int __init mtk_cpufreq_driver_init(void)
 	return 0;
 }
 device_initcall(mtk_cpufreq_driver_init);
+
+MODULE_DESCRIPTION("MediaTek CPUFreq driver");
+MODULE_AUTHOR("Pi-Cheng Chen <pi-cheng.chen@linaro.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpufreq/mvebu-cpufreq.c b/drivers/cpufreq/mvebu-cpufreq.c
index ed915ee85dd9..31513bd42705 100644
--- a/drivers/cpufreq/mvebu-cpufreq.c
+++ b/drivers/cpufreq/mvebu-cpufreq.c
@@ -76,12 +76,6 @@ static int __init armada_xp_pmsu_cpufreq_init(void)
 			return PTR_ERR(clk);
 		}
 
-		/*
-		 * In case of a failure of dev_pm_opp_add(), we don't
-		 * bother with cleaning up the registered OPP (there's
-		 * no function to do so), and simply cancel the
-		 * registration of the cpufreq device.
-		 */
 		ret = dev_pm_opp_add(cpu_dev, clk_get_rate(clk), 0);
 		if (ret) {
 			clk_put(clk);
@@ -91,7 +85,8 @@ static int __init armada_xp_pmsu_cpufreq_init(void)
 		ret = dev_pm_opp_add(cpu_dev, clk_get_rate(clk) / 2, 0);
 		if (ret) {
 			clk_put(clk);
-			return ret;
+			dev_err(cpu_dev, "Failed to register OPPs\n");
+			goto opp_register_failed;
 		}
 
 		ret = dev_pm_opp_set_sharing_cpus(cpu_dev,
@@ -99,9 +94,16 @@ static int __init armada_xp_pmsu_cpufreq_init(void)
 		if (ret)
 			dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
 				__func__, ret);
+		clk_put(clk);
 	}
 
 	platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
 	return 0;
+
+opp_register_failed:
+	/* As registering has failed remove all the opp for all cpus */
+	dev_pm_opp_cpumask_remove_table(cpu_possible_mask);
+
+	return ret;
 }
 device_initcall(armada_xp_pmsu_cpufreq_init);
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index b6d7c4c98d0a..29cdec198657 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -29,6 +29,7 @@
 #include <linux/reboot.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/hashtable.h>
 #include <trace/events/power.h>
 
 #include <asm/cputhreads.h>
@@ -38,14 +39,13 @@
 #include <asm/opal.h>
 #include <linux/timer.h>
 
-#define POWERNV_MAX_PSTATES	256
+#define POWERNV_MAX_PSTATES_ORDER  8
+#define POWERNV_MAX_PSTATES	(1UL << (POWERNV_MAX_PSTATES_ORDER))
 #define PMSR_PSAFE_ENABLE	(1UL << 30)
 #define PMSR_SPR_EM_DISABLE	(1UL << 31)
-#define PMSR_MAX(x)		((x >> 32) & 0xFF)
+#define MAX_PSTATE_SHIFT	32
 #define LPSTATE_SHIFT		48
 #define GPSTATE_SHIFT		56
-#define GET_LPSTATE(x)		(((x) >> LPSTATE_SHIFT) & 0xFF)
-#define GET_GPSTATE(x)		(((x) >> GPSTATE_SHIFT) & 0xFF)
 
 #define MAX_RAMP_DOWN_TIME				5120
 /*
@@ -94,6 +94,27 @@ struct global_pstate_info {
 };
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
+
+DEFINE_HASHTABLE(pstate_revmap, POWERNV_MAX_PSTATES_ORDER);
+/**
+ * struct pstate_idx_revmap_data: Entry in the hashmap pstate_revmap
+ *				  indexed by a function of pstate id.
+ *
+ * @pstate_id: pstate id for this entry.
+ *
+ * @cpufreq_table_idx: Index into the powernv_freqs
+ *		       cpufreq_frequency_table for frequency
+ *		       corresponding to pstate_id.
+ *
+ * @hentry: hlist_node that hooks this entry into the pstate_revmap
+ *	    hashtable
+ */
+struct pstate_idx_revmap_data {
+	u8 pstate_id;
+	unsigned int cpufreq_table_idx;
+	struct hlist_node hentry;
+};
+
 static bool rebooting, throttled, occ_reset;
 
 static const char * const throttle_reason[] = {
@@ -148,39 +169,56 @@ static struct powernv_pstate_info {
 	bool wof_enabled;
 } powernv_pstate_info;
 
-/* Use following macros for conversions between pstate_id and index */
-static inline int idx_to_pstate(unsigned int i)
+static inline u8 extract_pstate(u64 pmsr_val, unsigned int shift)
+{
+	return ((pmsr_val >> shift) & 0xFF);
+}
+
+#define extract_local_pstate(x) extract_pstate(x, LPSTATE_SHIFT)
+#define extract_global_pstate(x) extract_pstate(x, GPSTATE_SHIFT)
+#define extract_max_pstate(x)  extract_pstate(x, MAX_PSTATE_SHIFT)
+
+/* Use following functions for conversions between pstate_id and index */
+
+/**
+ * idx_to_pstate : Returns the pstate id corresponding to the
+ *		   frequency in the cpufreq frequency table
+ *		   powernv_freqs indexed by @i.
+ *
+ *		   If @i is out of bound, this will return the pstate
+ *		   corresponding to the nominal frequency.
+ */
+static inline u8 idx_to_pstate(unsigned int i)
 {
 	if (unlikely(i >= powernv_pstate_info.nr_pstates)) {
-		pr_warn_once("index %u is out of bound\n", i);
+		pr_warn_once("idx_to_pstate: index %u is out of bound\n", i);
 		return powernv_freqs[powernv_pstate_info.nominal].driver_data;
 	}
 
 	return powernv_freqs[i].driver_data;
 }
 
-static inline unsigned int pstate_to_idx(int pstate)
+/**
+ * pstate_to_idx : Returns the index in the cpufreq frequencytable
+ *		   powernv_freqs for the frequency whose corresponding
+ *		   pstate id is @pstate.
+ *
+ *		   If no frequency corresponding to @pstate is found,
+ *		   this will return the index of the nominal
+ *		   frequency.
+ */
+static unsigned int pstate_to_idx(u8 pstate)
 {
-	int min = powernv_freqs[powernv_pstate_info.min].driver_data;
-	int max = powernv_freqs[powernv_pstate_info.max].driver_data;
+	unsigned int key = pstate % POWERNV_MAX_PSTATES;
+	struct pstate_idx_revmap_data *revmap_data;
 
-	if (min > 0) {
-		if (unlikely((pstate < max) || (pstate > min))) {
-			pr_warn_once("pstate %d is out of bound\n", pstate);
-			return powernv_pstate_info.nominal;
-		}
-	} else {
-		if (unlikely((pstate > max) || (pstate < min))) {
-			pr_warn_once("pstate %d is out of bound\n", pstate);
-			return powernv_pstate_info.nominal;
-		}
+	hash_for_each_possible(pstate_revmap, revmap_data, hentry, key) {
+		if (revmap_data->pstate_id == pstate)
+			return revmap_data->cpufreq_table_idx;
 	}
-	/*
-	 * abs() is deliberately used so that is works with
-	 * both monotonically increasing and decreasing
-	 * pstate values
-	 */
-	return abs(pstate - idx_to_pstate(powernv_pstate_info.max));
+
+	pr_warn_once("pstate_to_idx: pstate 0x%x not found\n", pstate);
+	return powernv_pstate_info.nominal;
 }
 
 static inline void reset_gpstates(struct cpufreq_policy *policy)
@@ -247,7 +285,7 @@ static int init_powernv_pstates(void)
 		powernv_pstate_info.wof_enabled = true;
 
 next:
-	pr_info("cpufreq pstate min %d nominal %d max %d\n", pstate_min,
+	pr_info("cpufreq pstate min 0x%x nominal 0x%x max 0x%x\n", pstate_min,
 		pstate_nominal, pstate_max);
 	pr_info("Workload Optimized Frequency is %s in the platform\n",
 		(powernv_pstate_info.wof_enabled) ? "enabled" : "disabled");
@@ -278,19 +316,30 @@ next:
 
 	powernv_pstate_info.nr_pstates = nr_pstates;
 	pr_debug("NR PStates %d\n", nr_pstates);
+
 	for (i = 0; i < nr_pstates; i++) {
 		u32 id = be32_to_cpu(pstate_ids[i]);
 		u32 freq = be32_to_cpu(pstate_freqs[i]);
+		struct pstate_idx_revmap_data *revmap_data;
+		unsigned int key;
 
 		pr_debug("PState id %d freq %d MHz\n", id, freq);
 		powernv_freqs[i].frequency = freq * 1000; /* kHz */
-		powernv_freqs[i].driver_data = id;
+		powernv_freqs[i].driver_data = id & 0xFF;
+
+		revmap_data = (struct pstate_idx_revmap_data *)
+			      kmalloc(sizeof(*revmap_data), GFP_KERNEL);
+
+		revmap_data->pstate_id = id & 0xFF;
+		revmap_data->cpufreq_table_idx = i;
+		key = (revmap_data->pstate_id) % POWERNV_MAX_PSTATES;
+		hash_add(pstate_revmap, &revmap_data->hentry, key);
 
 		if (id == pstate_max)
 			powernv_pstate_info.max = i;
-		else if (id == pstate_nominal)
+		if (id == pstate_nominal)
 			powernv_pstate_info.nominal = i;
-		else if (id == pstate_min)
+		if (id == pstate_min)
 			powernv_pstate_info.min = i;
 
 		if (powernv_pstate_info.wof_enabled && id == pstate_turbo) {
@@ -307,14 +356,13 @@ next:
 }
 
 /* Returns the CPU frequency corresponding to the pstate_id. */
-static unsigned int pstate_id_to_freq(int pstate_id)
+static unsigned int pstate_id_to_freq(u8 pstate_id)
 {
 	int i;
 
 	i = pstate_to_idx(pstate_id);
 	if (i >= powernv_pstate_info.nr_pstates || i < 0) {
-		pr_warn("PState id %d outside of PState table, "
-			"reporting nominal id %d instead\n",
+		pr_warn("PState id 0x%x outside of PState table, reporting nominal id 0x%x instead\n",
 			pstate_id, idx_to_pstate(powernv_pstate_info.nominal));
 		i = powernv_pstate_info.nominal;
 	}
@@ -420,8 +468,8 @@ static inline void set_pmspr(unsigned long sprn, unsigned long val)
  */
 struct powernv_smp_call_data {
 	unsigned int freq;
-	int pstate_id;
-	int gpstate_id;
+	u8 pstate_id;
+	u8 gpstate_id;
 };
 
 /*
@@ -438,22 +486,15 @@ struct powernv_smp_call_data {
 static void powernv_read_cpu_freq(void *arg)
 {
 	unsigned long pmspr_val;
-	s8 local_pstate_id;
 	struct powernv_smp_call_data *freq_data = arg;
 
 	pmspr_val = get_pmspr(SPRN_PMSR);
-
-	/*
-	 * The local pstate id corresponds bits 48..55 in the PMSR.
-	 * Note: Watch out for the sign!
-	 */
-	local_pstate_id = (pmspr_val >> 48) & 0xFF;
-	freq_data->pstate_id = local_pstate_id;
+	freq_data->pstate_id = extract_local_pstate(pmspr_val);
 	freq_data->freq = pstate_id_to_freq(freq_data->pstate_id);
 
-	pr_debug("cpu %d pmsr %016lX pstate_id %d frequency %d kHz\n",
-		raw_smp_processor_id(), pmspr_val, freq_data->pstate_id,
-		freq_data->freq);
+	pr_debug("cpu %d pmsr %016lX pstate_id 0x%x frequency %d kHz\n",
+		 raw_smp_processor_id(), pmspr_val, freq_data->pstate_id,
+		 freq_data->freq);
 }
 
 /*
@@ -515,21 +556,21 @@ static void powernv_cpufreq_throttle_check(void *data)
 	struct chip *chip;
 	unsigned int cpu = smp_processor_id();
 	unsigned long pmsr;
-	int pmsr_pmax;
+	u8 pmsr_pmax;
 	unsigned int pmsr_pmax_idx;
 
 	pmsr = get_pmspr(SPRN_PMSR);
 	chip = this_cpu_read(chip_info);
 
 	/* Check for Pmax Capping */
-	pmsr_pmax = (s8)PMSR_MAX(pmsr);
+	pmsr_pmax = extract_max_pstate(pmsr);
 	pmsr_pmax_idx = pstate_to_idx(pmsr_pmax);
 	if (pmsr_pmax_idx != powernv_pstate_info.max) {
 		if (chip->throttled)
 			goto next;
 		chip->throttled = true;
 		if (pmsr_pmax_idx > powernv_pstate_info.nominal) {
-			pr_warn_once("CPU %d on Chip %u has Pmax(%d) reduced below nominal frequency(%d)\n",
+			pr_warn_once("CPU %d on Chip %u has Pmax(0x%x) reduced below that of nominal frequency(0x%x)\n",
 				     cpu, chip->id, pmsr_pmax,
 				     idx_to_pstate(powernv_pstate_info.nominal));
 			chip->throttle_sub_turbo++;
@@ -645,8 +686,8 @@ void gpstate_timer_handler(struct timer_list *t)
 	 * value. Hence, read from PMCR to get correct data.
 	 */
 	val = get_pmspr(SPRN_PMCR);
-	freq_data.gpstate_id = (s8)GET_GPSTATE(val);
-	freq_data.pstate_id = (s8)GET_LPSTATE(val);
+	freq_data.gpstate_id = extract_global_pstate(val);
+	freq_data.pstate_id = extract_local_pstate(val);
 	if (freq_data.gpstate_id  == freq_data.pstate_id) {
 		reset_gpstates(policy);
 		spin_unlock(&gpstates->gpstate_lock);
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index 4ada55b8856e..0562761a3dec 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -275,20 +275,8 @@ static int qoriq_cpufreq_target(struct cpufreq_policy *policy,
 static void qoriq_cpufreq_ready(struct cpufreq_policy *policy)
 {
 	struct cpu_data *cpud = policy->driver_data;
-	struct device_node *np = of_get_cpu_node(policy->cpu, NULL);
 
-	if (of_find_property(np, "#cooling-cells", NULL)) {
-		cpud->cdev = of_cpufreq_cooling_register(np, policy);
-
-		if (IS_ERR(cpud->cdev) && PTR_ERR(cpud->cdev) != -ENOSYS) {
-			pr_err("cpu%d is not running as cooling device: %ld\n",
-					policy->cpu, PTR_ERR(cpud->cdev));
-
-			cpud->cdev = NULL;
-		}
-	}
-
-	of_node_put(np);
+	cpud->cdev = of_cpufreq_cooling_register(policy);
 }
 
 static struct cpufreq_driver qoriq_cpufreq_driver = {
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index 05d299052c5c..247fcbfa4cb5 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -18,27 +18,89 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/clk.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/cpu_cooling.h>
+#include <linux/export.h>
 #include <linux/module.h>
-#include <linux/platform_device.h>
+#include <linux/of_platform.h>
 #include <linux/pm_opp.h>
 #include <linux/scpi_protocol.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 
-#include "arm_big_little.h"
+struct scpi_data {
+	struct clk *clk;
+	struct device *cpu_dev;
+	struct thermal_cooling_device *cdev;
+};
 
 static struct scpi_ops *scpi_ops;
 
-static int scpi_get_transition_latency(struct device *cpu_dev)
+static unsigned int scpi_cpufreq_get_rate(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
+	struct scpi_data *priv = policy->driver_data;
+	unsigned long rate = clk_get_rate(priv->clk);
+
+	return rate / 1000;
+}
+
+static int
+scpi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
+{
+	struct scpi_data *priv = policy->driver_data;
+	u64 rate = policy->freq_table[index].frequency * 1000;
+	int ret;
+
+	ret = clk_set_rate(priv->clk, rate);
+	if (!ret && (clk_get_rate(priv->clk) != rate))
+		ret = -EIO;
+
+	return ret;
+}
+
+static int
+scpi_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 {
-	return scpi_ops->get_transition_latency(cpu_dev);
+	int cpu, domain, tdomain;
+	struct device *tcpu_dev;
+
+	domain = scpi_ops->device_domain_id(cpu_dev);
+	if (domain < 0)
+		return domain;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == cpu_dev->id)
+			continue;
+
+		tcpu_dev = get_cpu_device(cpu);
+		if (!tcpu_dev)
+			continue;
+
+		tdomain = scpi_ops->device_domain_id(tcpu_dev);
+		if (tdomain == domain)
+			cpumask_set_cpu(cpu, cpumask);
+	}
+
+	return 0;
 }
 
-static int scpi_init_opp_table(const struct cpumask *cpumask)
+static int scpi_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int ret;
-	struct device *cpu_dev = get_cpu_device(cpumask_first(cpumask));
+	unsigned int latency;
+	struct device *cpu_dev;
+	struct scpi_data *priv;
+	struct cpufreq_frequency_table *freq_table;
+
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("failed to get cpu%d device\n", policy->cpu);
+		return -ENODEV;
+	}
 
 	ret = scpi_ops->add_opps_to_device(cpu_dev);
 	if (ret) {
@@ -46,32 +108,133 @@ static int scpi_init_opp_table(const struct cpumask *cpumask)
 		return ret;
 	}
 
-	ret = dev_pm_opp_set_sharing_cpus(cpu_dev, cpumask);
-	if (ret)
+	ret = scpi_get_sharing_cpus(cpu_dev, policy->cpus);
+	if (ret) {
+		dev_warn(cpu_dev, "failed to get sharing cpumask\n");
+		return ret;
+	}
+
+	ret = dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus);
+	if (ret) {
 		dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
 			__func__, ret);
+		return ret;
+	}
+
+	ret = dev_pm_opp_get_opp_count(cpu_dev);
+	if (ret <= 0) {
+		dev_dbg(cpu_dev, "OPP table is not ready, deferring probe\n");
+		ret = -EPROBE_DEFER;
+		goto out_free_opp;
+	}
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		ret = -ENOMEM;
+		goto out_free_opp;
+	}
+
+	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
+	if (ret) {
+		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
+		goto out_free_priv;
+	}
+
+	priv->cpu_dev = cpu_dev;
+	priv->clk = clk_get(cpu_dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		dev_err(cpu_dev, "%s: Failed to get clk for cpu: %d\n",
+			__func__, cpu_dev->id);
+		goto out_free_cpufreq_table;
+	}
+
+	policy->driver_data = priv;
+
+	ret = cpufreq_table_validate_and_show(policy, freq_table);
+	if (ret) {
+		dev_err(cpu_dev, "%s: invalid frequency table: %d\n", __func__,
+			ret);
+		goto out_put_clk;
+	}
+
+	/* scpi allows DVFS request for any domain from any CPU */
+	policy->dvfs_possible_from_any_cpu = true;
+
+	latency = scpi_ops->get_transition_latency(cpu_dev);
+	if (!latency)
+		latency = CPUFREQ_ETERNAL;
+
+	policy->cpuinfo.transition_latency = latency;
+
+	policy->fast_switch_possible = false;
+	return 0;
+
+out_put_clk:
+	clk_put(priv->clk);
+out_free_cpufreq_table:
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
+out_free_priv:
+	kfree(priv);
+out_free_opp:
+	dev_pm_opp_cpumask_remove_table(policy->cpus);
+
 	return ret;
 }
 
-static const struct cpufreq_arm_bL_ops scpi_cpufreq_ops = {
-	.name	= "scpi",
-	.get_transition_latency = scpi_get_transition_latency,
-	.init_opp_table = scpi_init_opp_table,
-	.free_opp_table = dev_pm_opp_cpumask_remove_table,
+static int scpi_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	struct scpi_data *priv = policy->driver_data;
+
+	cpufreq_cooling_unregister(priv->cdev);
+	clk_put(priv->clk);
+	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
+	kfree(priv);
+	dev_pm_opp_cpumask_remove_table(policy->related_cpus);
+
+	return 0;
+}
+
+static void scpi_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	struct scpi_data *priv = policy->driver_data;
+	struct thermal_cooling_device *cdev;
+
+	cdev = of_cpufreq_cooling_register(policy);
+	if (!IS_ERR(cdev))
+		priv->cdev = cdev;
+}
+
+static struct cpufreq_driver scpi_cpufreq_driver = {
+	.name	= "scpi-cpufreq",
+	.flags	= CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+		  CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.verify	= cpufreq_generic_frequency_table_verify,
+	.attr	= cpufreq_generic_attr,
+	.get	= scpi_cpufreq_get_rate,
+	.init	= scpi_cpufreq_init,
+	.exit	= scpi_cpufreq_exit,
+	.ready	= scpi_cpufreq_ready,
+	.target_index	= scpi_cpufreq_set_target,
 };
 
 static int scpi_cpufreq_probe(struct platform_device *pdev)
 {
+	int ret;
+
 	scpi_ops = get_scpi_ops();
 	if (!scpi_ops)
 		return -EIO;
 
-	return bL_cpufreq_register(&scpi_cpufreq_ops);
+	ret = cpufreq_register_driver(&scpi_cpufreq_driver);
+	if (ret)
+		dev_err(&pdev->dev, "%s: registering cpufreq failed, err: %d\n",
+			__func__, ret);
+	return ret;
 }
 
 static int scpi_cpufreq_remove(struct platform_device *pdev)
 {
-	bL_cpufreq_unregister(&scpi_cpufreq_ops);
+	cpufreq_unregister_driver(&scpi_cpufreq_driver);
 	scpi_ops = NULL;
 	return 0;
 }
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
index 923317f03b4b..a099b7bf74cd 100644
--- a/drivers/cpufreq/ti-cpufreq.c
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -17,6 +17,7 @@
 #include <linux/cpu.h>
 #include <linux/io.h>
 #include <linux/mfd/syscon.h>
+#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
@@ -50,6 +51,7 @@ struct ti_cpufreq_soc_data {
 	unsigned long efuse_mask;
 	unsigned long efuse_shift;
 	unsigned long rev_offset;
+	bool multi_regulator;
 };
 
 struct ti_cpufreq_data {
@@ -57,6 +59,7 @@ struct ti_cpufreq_data {
 	struct device_node *opp_node;
 	struct regmap *syscon;
 	const struct ti_cpufreq_soc_data *soc_data;
+	struct opp_table *opp_table;
 };
 
 static unsigned long amx3_efuse_xlate(struct ti_cpufreq_data *opp_data,
@@ -95,6 +98,7 @@ static struct ti_cpufreq_soc_data am3x_soc_data = {
 	.efuse_offset = 0x07fc,
 	.efuse_mask = 0x1fff,
 	.rev_offset = 0x600,
+	.multi_regulator = false,
 };
 
 static struct ti_cpufreq_soc_data am4x_soc_data = {
@@ -103,6 +107,7 @@ static struct ti_cpufreq_soc_data am4x_soc_data = {
 	.efuse_offset = 0x0610,
 	.efuse_mask = 0x3f,
 	.rev_offset = 0x600,
+	.multi_regulator = false,
 };
 
 static struct ti_cpufreq_soc_data dra7_soc_data = {
@@ -111,6 +116,7 @@ static struct ti_cpufreq_soc_data dra7_soc_data = {
 	.efuse_mask = 0xf80000,
 	.efuse_shift = 19,
 	.rev_offset = 0x204,
+	.multi_regulator = true,
 };
 
 /**
@@ -195,12 +201,14 @@ static const struct of_device_id ti_cpufreq_of_match[] = {
 	{},
 };
 
-static int ti_cpufreq_init(void)
+static int ti_cpufreq_probe(struct platform_device *pdev)
 {
 	u32 version[VERSION_COUNT];
 	struct device_node *np;
 	const struct of_device_id *match;
+	struct opp_table *ti_opp_table;
 	struct ti_cpufreq_data *opp_data;
+	const char * const reg_names[] = {"vdd", "vbb"};
 	int ret;
 
 	np = of_find_node_by_path("/");
@@ -247,16 +255,29 @@ static int ti_cpufreq_init(void)
 	if (ret)
 		goto fail_put_node;
 
-	ret = PTR_ERR_OR_ZERO(dev_pm_opp_set_supported_hw(opp_data->cpu_dev,
-							  version, VERSION_COUNT));
-	if (ret) {
+	ti_opp_table = dev_pm_opp_set_supported_hw(opp_data->cpu_dev,
+						   version, VERSION_COUNT);
+	if (IS_ERR(ti_opp_table)) {
 		dev_err(opp_data->cpu_dev,
 			"Failed to set supported hardware\n");
+		ret = PTR_ERR(ti_opp_table);
 		goto fail_put_node;
 	}
 
-	of_node_put(opp_data->opp_node);
+	opp_data->opp_table = ti_opp_table;
+
+	if (opp_data->soc_data->multi_regulator) {
+		ti_opp_table = dev_pm_opp_set_regulators(opp_data->cpu_dev,
+							 reg_names,
+							 ARRAY_SIZE(reg_names));
+		if (IS_ERR(ti_opp_table)) {
+			dev_pm_opp_put_supported_hw(opp_data->opp_table);
+			ret =  PTR_ERR(ti_opp_table);
+			goto fail_put_node;
+		}
+	}
 
+	of_node_put(opp_data->opp_node);
 register_cpufreq_dt:
 	platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
 
@@ -269,4 +290,22 @@ free_opp_data:
 
 	return ret;
 }
-device_initcall(ti_cpufreq_init);
+
+static int ti_cpufreq_init(void)
+{
+	platform_device_register_simple("ti-cpufreq", -1, NULL, 0);
+	return 0;
+}
+module_init(ti_cpufreq_init);
+
+static struct platform_driver ti_cpufreq_driver = {
+	.probe = ti_cpufreq_probe,
+	.driver = {
+		.name = "ti-cpufreq",
+	},
+};
+module_platform_driver(ti_cpufreq_driver);
+
+MODULE_DESCRIPTION("TI CPUFreq/OPP hw-supported driver");
+MODULE_AUTHOR("Dave Gerlach <d-gerlach@ti.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index e06605b21841..1a8234e706bc 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -76,6 +76,8 @@ static int snooze_loop(struct cpuidle_device *dev,
 	ppc64_runlatch_on();
 	clear_thread_flag(TIF_POLLING_NRFLAG);
 
+	local_irq_disable();
+
 	return index;
 }
 
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index a187a39fb866..9e56bc411061 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -51,8 +51,6 @@ static inline void idle_loop_epilog(unsigned long in_purr)
 	get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
 	get_lppaca()->idle = 0;
 
-	if (irqs_disabled())
-		local_irq_enable();
 	ppc64_runlatch_on();
 }
 
@@ -87,6 +85,8 @@ static int snooze_loop(struct cpuidle_device *dev,
 	HMT_medium();
 	clear_thread_flag(TIF_POLLING_NRFLAG);
 
+	local_irq_disable();
+
 	idle_loop_epilog(in_purr);
 
 	return index;
@@ -121,6 +121,7 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
 	HMT_medium();
 	check_and_cede_processor();
 
+	local_irq_disable();
 	get_lppaca()->donate_dedicated_cpu = 0;
 
 	idle_loop_epilog(in_purr);
@@ -145,6 +146,7 @@ static int shared_cede_loop(struct cpuidle_device *dev,
 	 */
 	check_and_cede_processor();
 
+	local_irq_disable();
 	idle_loop_epilog(in_purr);
 
 	return index;
@@ -172,11 +174,17 @@ static struct cpuidle_state dedicated_states[] = {
  * States for shared partition case.
  */
 static struct cpuidle_state shared_states[] = {
+	{ /* Snooze */
+		.name = "snooze",
+		.desc = "snooze",
+		.exit_latency = 0,
+		.target_residency = 0,
+		.enter = &snooze_loop },
 	{ /* Shared Cede */
 		.name = "Shared Cede",
 		.desc = "Shared Cede",
-		.exit_latency = 0,
-		.target_residency = 0,
+		.exit_latency = 10,
+		.target_residency = 100,
 		.enter = &shared_cede_loop },
 };
 
diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c
index 4e78263e34a4..5d359aff3cc5 100644
--- a/drivers/cpuidle/governor.c
+++ b/drivers/cpuidle/governor.c
@@ -36,14 +36,15 @@ static struct cpuidle_governor * __cpuidle_find_governor(const char *str)
 /**
  * cpuidle_switch_governor - changes the governor
  * @gov: the new target governor
- *
- * NOTE: "gov" can be NULL to specify disabled
  * Must be called with cpuidle_lock acquired.
  */
 int cpuidle_switch_governor(struct cpuidle_governor *gov)
 {
 	struct cpuidle_device *dev;
 
+	if (!gov)
+		return -EINVAL;
+
 	if (gov == cpuidle_curr_governor)
 		return 0;
 
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 47ec920d5b71..4b741b83e23f 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -723,7 +723,6 @@ config CRYPTO_DEV_ARTPEC6
 	select CRYPTO_HASH
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
-	select CRYPTO_SHA384
 	select CRYPTO_SHA512
 	help
 	  Enables the driver for the on-chip crypto accelerator
diff --git a/drivers/crypto/amcc/crypto4xx_alg.c b/drivers/crypto/amcc/crypto4xx_alg.c
index eeaf27859d80..ea83d0bff0e9 100644
--- a/drivers/crypto/amcc/crypto4xx_alg.c
+++ b/drivers/crypto/amcc/crypto4xx_alg.c
@@ -256,10 +256,6 @@ static inline bool crypto4xx_aead_need_fallback(struct aead_request *req,
 	if (is_ccm && !(req->iv[0] == 1 || req->iv[0] == 3))
 		return true;
 
-	/* CCM - fix CBC MAC mismatch in special case */
-	if (is_ccm && decrypt && !req->assoclen)
-		return true;
-
 	return false;
 }
 
@@ -330,7 +326,7 @@ int crypto4xx_setkey_aes_ccm(struct crypto_aead *cipher, const u8 *key,
 	sa = (struct dynamic_sa_ctl *) ctx->sa_in;
 	sa->sa_contents.w = SA_AES_CCM_CONTENTS | (keylen << 2);
 
-	set_dynamic_sa_command_0(sa, SA_NOT_SAVE_HASH, SA_NOT_SAVE_IV,
+	set_dynamic_sa_command_0(sa, SA_SAVE_HASH, SA_NOT_SAVE_IV,
 				 SA_LOAD_HASH_FROM_SA, SA_LOAD_IV_FROM_STATE,
 				 SA_NO_HEADER_PROC, SA_HASH_ALG_CBC_MAC,
 				 SA_CIPHER_ALG_AES,
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index c44954e274bc..76f459ad2821 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -128,7 +128,14 @@ static void crypto4xx_hw_init(struct crypto4xx_device *dev)
 	writel(PPC4XX_INT_DESCR_CNT, dev->ce_base + CRYPTO4XX_INT_DESCR_CNT);
 	writel(PPC4XX_INT_DESCR_CNT, dev->ce_base + CRYPTO4XX_INT_DESCR_CNT);
 	writel(PPC4XX_INT_CFG, dev->ce_base + CRYPTO4XX_INT_CFG);
-	writel(PPC4XX_PD_DONE_INT, dev->ce_base + CRYPTO4XX_INT_EN);
+	if (dev->is_revb) {
+		writel(PPC4XX_INT_TIMEOUT_CNT_REVB << 10,
+		       dev->ce_base + CRYPTO4XX_INT_TIMEOUT_CNT);
+		writel(PPC4XX_PD_DONE_INT | PPC4XX_TMO_ERR_INT,
+		       dev->ce_base + CRYPTO4XX_INT_EN);
+	} else {
+		writel(PPC4XX_PD_DONE_INT, dev->ce_base + CRYPTO4XX_INT_EN);
+	}
 }
 
 int crypto4xx_alloc_sa(struct crypto4xx_ctx *ctx, u32 size)
@@ -275,14 +282,12 @@ static u32 crypto4xx_put_pd_to_pdr(struct crypto4xx_device *dev, u32 idx)
  */
 static u32 crypto4xx_build_gdr(struct crypto4xx_device *dev)
 {
-	dev->gdr = dma_alloc_coherent(dev->core_dev->device,
-				      sizeof(struct ce_gd) * PPC4XX_NUM_GD,
-				      &dev->gdr_pa, GFP_ATOMIC);
+	dev->gdr = dma_zalloc_coherent(dev->core_dev->device,
+				       sizeof(struct ce_gd) * PPC4XX_NUM_GD,
+				       &dev->gdr_pa, GFP_ATOMIC);
 	if (!dev->gdr)
 		return -ENOMEM;
 
-	memset(dev->gdr, 0, sizeof(struct ce_gd) * PPC4XX_NUM_GD);
-
 	return 0;
 }
 
@@ -570,15 +575,14 @@ static void crypto4xx_aead_done(struct crypto4xx_device *dev,
 				struct pd_uinfo *pd_uinfo,
 				struct ce_pd *pd)
 {
-	struct aead_request *aead_req;
-	struct crypto4xx_ctx *ctx;
+	struct aead_request *aead_req = container_of(pd_uinfo->async_req,
+		struct aead_request, base);
 	struct scatterlist *dst = pd_uinfo->dest_va;
+	size_t cp_len = crypto_aead_authsize(
+		crypto_aead_reqtfm(aead_req));
+	u32 icv[cp_len];
 	int err = 0;
 
-	aead_req = container_of(pd_uinfo->async_req, struct aead_request,
-				base);
-	ctx  = crypto_tfm_ctx(aead_req->base.tfm);
-
 	if (pd_uinfo->using_sd) {
 		crypto4xx_copy_pkt_to_dst(dev, pd, pd_uinfo,
 					  pd->pd_ctl_len.bf.pkt_len,
@@ -590,38 +594,39 @@ static void crypto4xx_aead_done(struct crypto4xx_device *dev,
 
 	if (pd_uinfo->sa_va->sa_command_0.bf.dir == DIR_OUTBOUND) {
 		/* append icv at the end */
-		size_t cp_len = crypto_aead_authsize(
-			crypto_aead_reqtfm(aead_req));
-		u32 icv[cp_len];
-
 		crypto4xx_memcpy_from_le32(icv, pd_uinfo->sr_va->save_digest,
 					   cp_len);
 
 		scatterwalk_map_and_copy(icv, dst, aead_req->cryptlen,
 					 cp_len, 1);
+	} else {
+		/* check icv at the end */
+		scatterwalk_map_and_copy(icv, aead_req->src,
+			aead_req->assoclen + aead_req->cryptlen -
+			cp_len, cp_len, 0);
+
+		crypto4xx_memcpy_from_le32(icv, icv, cp_len);
+
+		if (crypto_memneq(icv, pd_uinfo->sr_va->save_digest, cp_len))
+			err = -EBADMSG;
 	}
 
 	crypto4xx_ret_sg_desc(dev, pd_uinfo);
 
 	if (pd->pd_ctl.bf.status & 0xff) {
-		if (pd->pd_ctl.bf.status & 0x1) {
-			/* authentication error */
-			err = -EBADMSG;
-		} else {
-			if (!__ratelimit(&dev->aead_ratelimit)) {
-				if (pd->pd_ctl.bf.status & 2)
-					pr_err("pad fail error\n");
-				if (pd->pd_ctl.bf.status & 4)
-					pr_err("seqnum fail\n");
-				if (pd->pd_ctl.bf.status & 8)
-					pr_err("error _notify\n");
-				pr_err("aead return err status = 0x%02x\n",
-					pd->pd_ctl.bf.status & 0xff);
-				pr_err("pd pad_ctl = 0x%08x\n",
-					pd->pd_ctl.bf.pd_pad_ctl);
-			}
-			err = -EINVAL;
+		if (!__ratelimit(&dev->aead_ratelimit)) {
+			if (pd->pd_ctl.bf.status & 2)
+				pr_err("pad fail error\n");
+			if (pd->pd_ctl.bf.status & 4)
+				pr_err("seqnum fail\n");
+			if (pd->pd_ctl.bf.status & 8)
+				pr_err("error _notify\n");
+			pr_err("aead return err status = 0x%02x\n",
+				pd->pd_ctl.bf.status & 0xff);
+			pr_err("pd pad_ctl = 0x%08x\n",
+				pd->pd_ctl.bf.pd_pad_ctl);
 		}
+		err = -EINVAL;
 	}
 
 	if (pd_uinfo->state & PD_ENTRY_BUSY)
@@ -1070,21 +1075,29 @@ static void crypto4xx_bh_tasklet_cb(unsigned long data)
 /**
  * Top Half of isr.
  */
-static irqreturn_t crypto4xx_ce_interrupt_handler(int irq, void *data)
+static inline irqreturn_t crypto4xx_interrupt_handler(int irq, void *data,
+						      u32 clr_val)
 {
 	struct device *dev = (struct device *)data;
 	struct crypto4xx_core_device *core_dev = dev_get_drvdata(dev);
 
-	if (!core_dev->dev->ce_base)
-		return 0;
-
-	writel(PPC4XX_INTERRUPT_CLR,
-	       core_dev->dev->ce_base + CRYPTO4XX_INT_CLR);
+	writel(clr_val, core_dev->dev->ce_base + CRYPTO4XX_INT_CLR);
 	tasklet_schedule(&core_dev->tasklet);
 
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t crypto4xx_ce_interrupt_handler(int irq, void *data)
+{
+	return crypto4xx_interrupt_handler(irq, data, PPC4XX_INTERRUPT_CLR);
+}
+
+static irqreturn_t crypto4xx_ce_interrupt_handler_revb(int irq, void *data)
+{
+	return crypto4xx_interrupt_handler(irq, data, PPC4XX_INTERRUPT_CLR |
+		PPC4XX_TMO_ERR_INT);
+}
+
 /**
  * Supported Crypto Algorithms
  */
@@ -1266,6 +1279,8 @@ static int crypto4xx_probe(struct platform_device *ofdev)
 	struct resource res;
 	struct device *dev = &ofdev->dev;
 	struct crypto4xx_core_device *core_dev;
+	u32 pvr;
+	bool is_revb = true;
 
 	rc = of_address_to_resource(ofdev->dev.of_node, 0, &res);
 	if (rc)
@@ -1282,6 +1297,7 @@ static int crypto4xx_probe(struct platform_device *ofdev)
 		       mfdcri(SDR0, PPC405EX_SDR0_SRST) | PPC405EX_CE_RESET);
 		mtdcri(SDR0, PPC405EX_SDR0_SRST,
 		       mfdcri(SDR0, PPC405EX_SDR0_SRST) & ~PPC405EX_CE_RESET);
+		is_revb = false;
 	} else if (of_find_compatible_node(NULL, NULL,
 			"amcc,ppc460sx-crypto")) {
 		mtdcri(SDR0, PPC460SX_SDR0_SRST,
@@ -1304,7 +1320,22 @@ static int crypto4xx_probe(struct platform_device *ofdev)
 	if (!core_dev->dev)
 		goto err_alloc_dev;
 
+	/*
+	 * Older version of 460EX/GT have a hardware bug.
+	 * Hence they do not support H/W based security intr coalescing
+	 */
+	pvr = mfspr(SPRN_PVR);
+	if (is_revb && ((pvr >> 4) == 0x130218A)) {
+		u32 min = PVR_MIN(pvr);
+
+		if (min < 4) {
+			dev_info(dev, "RevA detected - disable interrupt coalescing\n");
+			is_revb = false;
+		}
+	}
+
 	core_dev->dev->core_dev = core_dev;
+	core_dev->dev->is_revb = is_revb;
 	core_dev->device = dev;
 	spin_lock_init(&core_dev->lock);
 	INIT_LIST_HEAD(&core_dev->dev->alg_list);
@@ -1325,13 +1356,6 @@ static int crypto4xx_probe(struct platform_device *ofdev)
 	tasklet_init(&core_dev->tasklet, crypto4xx_bh_tasklet_cb,
 		     (unsigned long) dev);
 
-	/* Register for Crypto isr, Crypto Engine IRQ */
-	core_dev->irq = irq_of_parse_and_map(ofdev->dev.of_node, 0);
-	rc = request_irq(core_dev->irq, crypto4xx_ce_interrupt_handler, 0,
-			 core_dev->dev->name, dev);
-	if (rc)
-		goto err_request_irq;
-
 	core_dev->dev->ce_base = of_iomap(ofdev->dev.of_node, 0);
 	if (!core_dev->dev->ce_base) {
 		dev_err(dev, "failed to of_iomap\n");
@@ -1339,6 +1363,15 @@ static int crypto4xx_probe(struct platform_device *ofdev)
 		goto err_iomap;
 	}
 
+	/* Register for Crypto isr, Crypto Engine IRQ */
+	core_dev->irq = irq_of_parse_and_map(ofdev->dev.of_node, 0);
+	rc = request_irq(core_dev->irq, is_revb ?
+			 crypto4xx_ce_interrupt_handler_revb :
+			 crypto4xx_ce_interrupt_handler, 0,
+			 KBUILD_MODNAME, dev);
+	if (rc)
+		goto err_request_irq;
+
 	/* need to setup pdr, rdr, gdr and sdr before this */
 	crypto4xx_hw_init(core_dev->dev);
 
@@ -1352,11 +1385,11 @@ static int crypto4xx_probe(struct platform_device *ofdev)
 	return 0;
 
 err_start_dev:
-	iounmap(core_dev->dev->ce_base);
-err_iomap:
 	free_irq(core_dev->irq, dev);
 err_request_irq:
 	irq_dispose_mapping(core_dev->irq);
+	iounmap(core_dev->dev->ce_base);
+err_iomap:
 	tasklet_kill(&core_dev->tasklet);
 err_build_sdr:
 	crypto4xx_destroy_sdr(core_dev->dev);
@@ -1397,7 +1430,7 @@ MODULE_DEVICE_TABLE(of, crypto4xx_match);
 
 static struct platform_driver crypto4xx_driver = {
 	.driver = {
-		.name = MODULE_NAME,
+		.name = KBUILD_MODNAME,
 		.of_match_table = crypto4xx_match,
 	},
 	.probe		= crypto4xx_probe,
diff --git a/drivers/crypto/amcc/crypto4xx_core.h b/drivers/crypto/amcc/crypto4xx_core.h
index 8ac3bd37203b..23b726da6534 100644
--- a/drivers/crypto/amcc/crypto4xx_core.h
+++ b/drivers/crypto/amcc/crypto4xx_core.h
@@ -28,8 +28,6 @@
 #include "crypto4xx_reg_def.h"
 #include "crypto4xx_sa.h"
 
-#define MODULE_NAME "crypto4xx"
-
 #define PPC460SX_SDR0_SRST                      0x201
 #define PPC405EX_SDR0_SRST                      0x200
 #define PPC460EX_SDR0_SRST                      0x201
@@ -82,7 +80,6 @@ struct pd_uinfo {
 
 struct crypto4xx_device {
 	struct crypto4xx_core_device *core_dev;
-	char *name;
 	void __iomem *ce_base;
 	void __iomem *trng_base;
 
@@ -109,6 +106,7 @@ struct crypto4xx_device {
 	struct list_head alg_list;	/* List of algorithm supported
 					by this device */
 	struct ratelimit_state aead_ratelimit;
+	bool is_revb;
 };
 
 struct crypto4xx_core_device {
diff --git a/drivers/crypto/amcc/crypto4xx_reg_def.h b/drivers/crypto/amcc/crypto4xx_reg_def.h
index 0a22ec5d1a96..472331787e04 100644
--- a/drivers/crypto/amcc/crypto4xx_reg_def.h
+++ b/drivers/crypto/amcc/crypto4xx_reg_def.h
@@ -121,13 +121,15 @@
 #define PPC4XX_PD_SIZE				6
 #define PPC4XX_CTX_DONE_INT			0x2000
 #define PPC4XX_PD_DONE_INT			0x8000
+#define PPC4XX_TMO_ERR_INT			0x40000
 #define PPC4XX_BYTE_ORDER			0x22222
 #define PPC4XX_INTERRUPT_CLR			0x3ffff
 #define PPC4XX_PRNG_CTRL_AUTO_EN		0x3
 #define PPC4XX_DC_3DES_EN			1
 #define PPC4XX_TRNG_EN				0x00020000
-#define PPC4XX_INT_DESCR_CNT			4
+#define PPC4XX_INT_DESCR_CNT			7
 #define PPC4XX_INT_TIMEOUT_CNT			0
+#define PPC4XX_INT_TIMEOUT_CNT_REVB		0x3FF
 #define PPC4XX_INT_CFG				1
 /**
  * all follow define are ad hoc
diff --git a/drivers/crypto/amcc/crypto4xx_trng.c b/drivers/crypto/amcc/crypto4xx_trng.c
index 677ca17fd223..5e63742b0d22 100644
--- a/drivers/crypto/amcc/crypto4xx_trng.c
+++ b/drivers/crypto/amcc/crypto4xx_trng.c
@@ -92,7 +92,7 @@ void ppc4xx_trng_probe(struct crypto4xx_core_device *core_dev)
 	if (!rng)
 		goto err_out;
 
-	rng->name = MODULE_NAME;
+	rng->name = KBUILD_MODNAME;
 	rng->data_present = ppc4xx_trng_data_present;
 	rng->data_read = ppc4xx_trng_data_read;
 	rng->priv = (unsigned long) dev;
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index 456278440863..0fb8bbf41a8d 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -22,6 +22,7 @@
 #include <linux/slab.h>
 
 #include <crypto/aes.h>
+#include <crypto/gcm.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
@@ -1934,7 +1935,7 @@ static int artpec6_crypto_prepare_aead(struct aead_request *areq)
 
 	memcpy(req_ctx->hw_ctx.J0, areq->iv, crypto_aead_ivsize(cipher));
 	// The HW omits the initial increment of the counter field.
-	crypto_inc(req_ctx->hw_ctx.J0+12, 4);
+	memcpy(req_ctx->hw_ctx.J0 + GCM_AES_IV_SIZE, "\x00\x00\x00\x01", 4);
 
 	ret = artpec6_crypto_setup_out_descr(common, &req_ctx->hw_ctx,
 		sizeof(struct artpec6_crypto_aead_hw_ctx), false, false);
@@ -2956,7 +2957,7 @@ static struct aead_alg aead_algos[] = {
 		.setkey = artpec6_crypto_aead_set_key,
 		.encrypt = artpec6_crypto_aead_encrypt,
 		.decrypt = artpec6_crypto_aead_decrypt,
-		.ivsize = AES_BLOCK_SIZE,
+		.ivsize = GCM_AES_IV_SIZE,
 		.maxauthsize = AES_BLOCK_SIZE,
 
 		.base = {
@@ -3041,9 +3042,6 @@ static int artpec6_crypto_probe(struct platform_device *pdev)
 	variant = (enum artpec6_crypto_variant)match->data;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENODEV;
-
 	base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index ce70b44d0fb6..2b75f95bbe1b 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -42,7 +42,6 @@
 #include <crypto/authenc.h>
 #include <crypto/skcipher.h>
 #include <crypto/hash.h>
-#include <crypto/aes.h>
 #include <crypto/sha3.h>
 
 #include "util.h"
diff --git a/drivers/crypto/bfin_crc.c b/drivers/crypto/bfin_crc.c
index a118b9bed669..bfbf8bf77f03 100644
--- a/drivers/crypto/bfin_crc.c
+++ b/drivers/crypto/bfin_crc.c
@@ -494,7 +494,8 @@ static struct ahash_alg algs = {
 		.cra_driver_name	= DRIVER_NAME,
 		.cra_priority		= 100,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC,
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct bfin_crypto_crc_ctx),
 		.cra_alignmask		= 3,
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index baa8dd52472d..2188235be02d 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -108,6 +108,7 @@ struct caam_ctx {
 	dma_addr_t sh_desc_dec_dma;
 	dma_addr_t sh_desc_givenc_dma;
 	dma_addr_t key_dma;
+	enum dma_data_direction dir;
 	struct device *jrdev;
 	struct alginfo adata;
 	struct alginfo cdata;
@@ -118,6 +119,7 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 {
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
+	struct caam_drv_private *ctrlpriv = dev_get_drvdata(jrdev->parent);
 	u32 *desc;
 	int rem_bytes = CAAM_DESC_BYTES_MAX - AEAD_DESC_JOB_IO_LEN -
 			ctx->adata.keylen_pad;
@@ -136,9 +138,10 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 
 	/* aead_encrypt shared descriptor */
 	desc = ctx->sh_desc_enc;
-	cnstr_shdsc_aead_null_encap(desc, &ctx->adata, ctx->authsize);
+	cnstr_shdsc_aead_null_encap(desc, &ctx->adata, ctx->authsize,
+				    ctrlpriv->era);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	/*
 	 * Job Descriptor and Shared Descriptors
@@ -154,9 +157,10 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 
 	/* aead_decrypt shared descriptor */
 	desc = ctx->sh_desc_dec;
-	cnstr_shdsc_aead_null_decap(desc, &ctx->adata, ctx->authsize);
+	cnstr_shdsc_aead_null_decap(desc, &ctx->adata, ctx->authsize,
+				    ctrlpriv->era);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	return 0;
 }
@@ -168,6 +172,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	unsigned int ivsize = crypto_aead_ivsize(aead);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
+	struct caam_drv_private *ctrlpriv = dev_get_drvdata(jrdev->parent);
 	u32 ctx1_iv_off = 0;
 	u32 *desc, *nonce = NULL;
 	u32 inl_mask;
@@ -234,9 +239,9 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	desc = ctx->sh_desc_enc;
 	cnstr_shdsc_aead_encap(desc, &ctx->cdata, &ctx->adata, ivsize,
 			       ctx->authsize, is_rfc3686, nonce, ctx1_iv_off,
-			       false);
+			       false, ctrlpriv->era);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 skip_enc:
 	/*
@@ -266,9 +271,9 @@ skip_enc:
 	desc = ctx->sh_desc_dec;
 	cnstr_shdsc_aead_decap(desc, &ctx->cdata, &ctx->adata, ivsize,
 			       ctx->authsize, alg->caam.geniv, is_rfc3686,
-			       nonce, ctx1_iv_off, false);
+			       nonce, ctx1_iv_off, false, ctrlpriv->era);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	if (!alg->caam.geniv)
 		goto skip_givenc;
@@ -300,9 +305,9 @@ skip_enc:
 	desc = ctx->sh_desc_enc;
 	cnstr_shdsc_aead_givencap(desc, &ctx->cdata, &ctx->adata, ivsize,
 				  ctx->authsize, is_rfc3686, nonce,
-				  ctx1_iv_off, false);
+				  ctx1_iv_off, false, ctrlpriv->era);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 skip_givenc:
 	return 0;
@@ -346,7 +351,7 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	desc = ctx->sh_desc_enc;
 	cnstr_shdsc_gcm_encap(desc, &ctx->cdata, ctx->authsize);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	/*
 	 * Job Descriptor and Shared Descriptors
@@ -363,7 +368,7 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	desc = ctx->sh_desc_dec;
 	cnstr_shdsc_gcm_decap(desc, &ctx->cdata, ctx->authsize);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	return 0;
 }
@@ -405,7 +410,7 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	desc = ctx->sh_desc_enc;
 	cnstr_shdsc_rfc4106_encap(desc, &ctx->cdata, ctx->authsize);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	/*
 	 * Job Descriptor and Shared Descriptors
@@ -422,7 +427,7 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	desc = ctx->sh_desc_dec;
 	cnstr_shdsc_rfc4106_decap(desc, &ctx->cdata, ctx->authsize);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	return 0;
 }
@@ -465,7 +470,7 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	desc = ctx->sh_desc_enc;
 	cnstr_shdsc_rfc4543_encap(desc, &ctx->cdata, ctx->authsize);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	/*
 	 * Job Descriptor and Shared Descriptors
@@ -482,7 +487,7 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	desc = ctx->sh_desc_dec;
 	cnstr_shdsc_rfc4543_decap(desc, &ctx->cdata, ctx->authsize);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	return 0;
 }
@@ -503,6 +508,7 @@ static int aead_setkey(struct crypto_aead *aead,
 {
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
+	struct caam_drv_private *ctrlpriv = dev_get_drvdata(jrdev->parent);
 	struct crypto_authenc_keys keys;
 	int ret = 0;
 
@@ -517,6 +523,27 @@ static int aead_setkey(struct crypto_aead *aead,
 		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
 #endif
 
+	/*
+	 * If DKP is supported, use it in the shared descriptor to generate
+	 * the split key.
+	 */
+	if (ctrlpriv->era >= 6) {
+		ctx->adata.keylen = keys.authkeylen;
+		ctx->adata.keylen_pad = split_key_len(ctx->adata.algtype &
+						      OP_ALG_ALGSEL_MASK);
+
+		if (ctx->adata.keylen_pad + keys.enckeylen > CAAM_MAX_KEY_SIZE)
+			goto badkey;
+
+		memcpy(ctx->key, keys.authkey, keys.authkeylen);
+		memcpy(ctx->key + ctx->adata.keylen_pad, keys.enckey,
+		       keys.enckeylen);
+		dma_sync_single_for_device(jrdev, ctx->key_dma,
+					   ctx->adata.keylen_pad +
+					   keys.enckeylen, ctx->dir);
+		goto skip_split_key;
+	}
+
 	ret = gen_split_key(ctx->jrdev, ctx->key, &ctx->adata, keys.authkey,
 			    keys.authkeylen, CAAM_MAX_KEY_SIZE -
 			    keys.enckeylen);
@@ -527,12 +554,14 @@ static int aead_setkey(struct crypto_aead *aead,
 	/* postpend encryption key to auth split key */
 	memcpy(ctx->key + ctx->adata.keylen_pad, keys.enckey, keys.enckeylen);
 	dma_sync_single_for_device(jrdev, ctx->key_dma, ctx->adata.keylen_pad +
-				   keys.enckeylen, DMA_TO_DEVICE);
+				   keys.enckeylen, ctx->dir);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "ctx.key@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, ctx->key,
 		       ctx->adata.keylen_pad + keys.enckeylen, 1);
 #endif
+
+skip_split_key:
 	ctx->cdata.keylen = keys.enckeylen;
 	return aead_set_sh_desc(aead);
 badkey:
@@ -552,7 +581,7 @@ static int gcm_setkey(struct crypto_aead *aead,
 #endif
 
 	memcpy(ctx->key, key, keylen);
-	dma_sync_single_for_device(jrdev, ctx->key_dma, keylen, DMA_TO_DEVICE);
+	dma_sync_single_for_device(jrdev, ctx->key_dma, keylen, ctx->dir);
 	ctx->cdata.keylen = keylen;
 
 	return gcm_set_sh_desc(aead);
@@ -580,7 +609,7 @@ static int rfc4106_setkey(struct crypto_aead *aead,
 	 */
 	ctx->cdata.keylen = keylen - 4;
 	dma_sync_single_for_device(jrdev, ctx->key_dma, ctx->cdata.keylen,
-				   DMA_TO_DEVICE);
+				   ctx->dir);
 	return rfc4106_set_sh_desc(aead);
 }
 
@@ -606,7 +635,7 @@ static int rfc4543_setkey(struct crypto_aead *aead,
 	 */
 	ctx->cdata.keylen = keylen - 4;
 	dma_sync_single_for_device(jrdev, ctx->key_dma, ctx->cdata.keylen,
-				   DMA_TO_DEVICE);
+				   ctx->dir);
 	return rfc4543_set_sh_desc(aead);
 }
 
@@ -625,7 +654,6 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 	const bool is_rfc3686 = (ctr_mode &&
 				 (strstr(alg_name, "rfc3686") != NULL));
 
-	memcpy(ctx->key, key, keylen);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "key in @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
@@ -648,9 +676,8 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 		keylen -= CTR_RFC3686_NONCE_SIZE;
 	}
 
-	dma_sync_single_for_device(jrdev, ctx->key_dma, keylen, DMA_TO_DEVICE);
 	ctx->cdata.keylen = keylen;
-	ctx->cdata.key_virt = ctx->key;
+	ctx->cdata.key_virt = key;
 	ctx->cdata.key_inline = true;
 
 	/* ablkcipher_encrypt shared descriptor */
@@ -658,21 +685,21 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 	cnstr_shdsc_ablkcipher_encap(desc, &ctx->cdata, ivsize, is_rfc3686,
 				     ctx1_iv_off);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	/* ablkcipher_decrypt shared descriptor */
 	desc = ctx->sh_desc_dec;
 	cnstr_shdsc_ablkcipher_decap(desc, &ctx->cdata, ivsize, is_rfc3686,
 				     ctx1_iv_off);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	/* ablkcipher_givencrypt shared descriptor */
 	desc = ctx->sh_desc_givenc;
 	cnstr_shdsc_ablkcipher_givencap(desc, &ctx->cdata, ivsize, is_rfc3686,
 					ctx1_iv_off);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_givenc_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	return 0;
 }
@@ -691,23 +718,21 @@ static int xts_ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 		return -EINVAL;
 	}
 
-	memcpy(ctx->key, key, keylen);
-	dma_sync_single_for_device(jrdev, ctx->key_dma, keylen, DMA_TO_DEVICE);
 	ctx->cdata.keylen = keylen;
-	ctx->cdata.key_virt = ctx->key;
+	ctx->cdata.key_virt = key;
 	ctx->cdata.key_inline = true;
 
 	/* xts_ablkcipher_encrypt shared descriptor */
 	desc = ctx->sh_desc_enc;
 	cnstr_shdsc_xts_ablkcipher_encap(desc, &ctx->cdata);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	/* xts_ablkcipher_decrypt shared descriptor */
 	desc = ctx->sh_desc_dec;
 	cnstr_shdsc_xts_ablkcipher_decap(desc, &ctx->cdata);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 
 	return 0;
 }
@@ -979,9 +1004,6 @@ static void init_aead_job(struct aead_request *req,
 		append_seq_out_ptr(desc, dst_dma,
 				   req->assoclen + req->cryptlen - authsize,
 				   out_options);
-
-	/* REG3 = assoclen */
-	append_math_add_imm_u32(desc, REG3, ZERO, IMM, req->assoclen);
 }
 
 static void init_gcm_job(struct aead_request *req,
@@ -996,6 +1018,7 @@ static void init_gcm_job(struct aead_request *req,
 	unsigned int last;
 
 	init_aead_job(req, edesc, all_contig, encrypt);
+	append_math_add_imm_u32(desc, REG3, ZERO, IMM, req->assoclen);
 
 	/* BUG This should not be specific to generic GCM. */
 	last = 0;
@@ -1022,6 +1045,7 @@ static void init_authenc_job(struct aead_request *req,
 						 struct caam_aead_alg, aead);
 	unsigned int ivsize = crypto_aead_ivsize(aead);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct caam_drv_private *ctrlpriv = dev_get_drvdata(ctx->jrdev->parent);
 	const bool ctr_mode = ((ctx->cdata.algtype & OP_ALG_AAI_MASK) ==
 			       OP_ALG_AAI_CTR_MOD128);
 	const bool is_rfc3686 = alg->caam.rfc3686;
@@ -1045,6 +1069,15 @@ static void init_authenc_job(struct aead_request *req,
 
 	init_aead_job(req, edesc, all_contig, encrypt);
 
+	/*
+	 * {REG3, DPOVRD} = assoclen, depending on whether MATH command supports
+	 * having DPOVRD as destination.
+	 */
+	if (ctrlpriv->era < 3)
+		append_math_add_imm_u32(desc, REG3, ZERO, IMM, req->assoclen);
+	else
+		append_math_add_imm_u32(desc, DPOVRD, ZERO, IMM, req->assoclen);
+
 	if (ivsize && ((is_rfc3686 && encrypt) || !alg->caam.geniv))
 		append_load_as_imm(desc, req->iv, ivsize,
 				   LDST_CLASS_1_CCB |
@@ -3228,9 +3261,11 @@ struct caam_crypto_alg {
 	struct caam_alg_entry caam;
 };
 
-static int caam_init_common(struct caam_ctx *ctx, struct caam_alg_entry *caam)
+static int caam_init_common(struct caam_ctx *ctx, struct caam_alg_entry *caam,
+			    bool uses_dkp)
 {
 	dma_addr_t dma_addr;
+	struct caam_drv_private *priv;
 
 	ctx->jrdev = caam_jr_alloc();
 	if (IS_ERR(ctx->jrdev)) {
@@ -3238,10 +3273,16 @@ static int caam_init_common(struct caam_ctx *ctx, struct caam_alg_entry *caam)
 		return PTR_ERR(ctx->jrdev);
 	}
 
+	priv = dev_get_drvdata(ctx->jrdev->parent);
+	if (priv->era >= 6 && uses_dkp)
+		ctx->dir = DMA_BIDIRECTIONAL;
+	else
+		ctx->dir = DMA_TO_DEVICE;
+
 	dma_addr = dma_map_single_attrs(ctx->jrdev, ctx->sh_desc_enc,
 					offsetof(struct caam_ctx,
 						 sh_desc_enc_dma),
-					DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+					ctx->dir, DMA_ATTR_SKIP_CPU_SYNC);
 	if (dma_mapping_error(ctx->jrdev, dma_addr)) {
 		dev_err(ctx->jrdev, "unable to map key, shared descriptors\n");
 		caam_jr_free(ctx->jrdev);
@@ -3269,7 +3310,7 @@ static int caam_cra_init(struct crypto_tfm *tfm)
 		 container_of(alg, struct caam_crypto_alg, crypto_alg);
 	struct caam_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	return caam_init_common(ctx, &caam_alg->caam);
+	return caam_init_common(ctx, &caam_alg->caam, false);
 }
 
 static int caam_aead_init(struct crypto_aead *tfm)
@@ -3279,14 +3320,15 @@ static int caam_aead_init(struct crypto_aead *tfm)
 		 container_of(alg, struct caam_aead_alg, aead);
 	struct caam_ctx *ctx = crypto_aead_ctx(tfm);
 
-	return caam_init_common(ctx, &caam_alg->caam);
+	return caam_init_common(ctx, &caam_alg->caam,
+				alg->setkey == aead_setkey);
 }
 
 static void caam_exit_common(struct caam_ctx *ctx)
 {
 	dma_unmap_single_attrs(ctx->jrdev, ctx->sh_desc_enc_dma,
 			       offsetof(struct caam_ctx, sh_desc_enc_dma),
-			       DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+			       ctx->dir, DMA_ATTR_SKIP_CPU_SYNC);
 	caam_jr_free(ctx->jrdev);
 }
 
diff --git a/drivers/crypto/caam/caamalg_desc.c b/drivers/crypto/caam/caamalg_desc.c
index 530c14ee32de..ceb93fbb76e6 100644
--- a/drivers/crypto/caam/caamalg_desc.c
+++ b/drivers/crypto/caam/caamalg_desc.c
@@ -45,16 +45,16 @@ static inline void append_dec_op1(u32 *desc, u32 type)
  * cnstr_shdsc_aead_null_encap - IPSec ESP encapsulation shared descriptor
  *                               (non-protocol) with no (null) encryption.
  * @desc: pointer to buffer used for descriptor construction
- * @adata: pointer to authentication transform definitions. Note that since a
- *         split key is to be used, the size of the split key itself is
- *         specified. Valid algorithm values - one of OP_ALG_ALGSEL_{MD5, SHA1,
- *         SHA224, SHA256, SHA384, SHA512} ANDed with OP_ALG_AAI_HMAC_PRECOMP.
+ * @adata: pointer to authentication transform definitions.
+ *         A split key is required for SEC Era < 6; the size of the split key
+ *         is specified in this case. Valid algorithm values - one of
+ *         OP_ALG_ALGSEL_{MD5, SHA1, SHA224, SHA256, SHA384, SHA512} ANDed
+ *         with OP_ALG_AAI_HMAC_PRECOMP.
  * @icvsize: integrity check value (ICV) size (truncated or full)
- *
- * Note: Requires an MDHA split key.
+ * @era: SEC Era
  */
 void cnstr_shdsc_aead_null_encap(u32 * const desc, struct alginfo *adata,
-				 unsigned int icvsize)
+				 unsigned int icvsize, int era)
 {
 	u32 *key_jump_cmd, *read_move_cmd, *write_move_cmd;
 
@@ -63,13 +63,18 @@ void cnstr_shdsc_aead_null_encap(u32 * const desc, struct alginfo *adata,
 	/* Skip if already shared */
 	key_jump_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
 				   JUMP_COND_SHRD);
-	if (adata->key_inline)
-		append_key_as_imm(desc, adata->key_virt, adata->keylen_pad,
-				  adata->keylen, CLASS_2 | KEY_DEST_MDHA_SPLIT |
-				  KEY_ENC);
-	else
-		append_key(desc, adata->key_dma, adata->keylen, CLASS_2 |
-			   KEY_DEST_MDHA_SPLIT | KEY_ENC);
+	if (era < 6) {
+		if (adata->key_inline)
+			append_key_as_imm(desc, adata->key_virt,
+					  adata->keylen_pad, adata->keylen,
+					  CLASS_2 | KEY_DEST_MDHA_SPLIT |
+					  KEY_ENC);
+		else
+			append_key(desc, adata->key_dma, adata->keylen,
+				   CLASS_2 | KEY_DEST_MDHA_SPLIT | KEY_ENC);
+	} else {
+		append_proto_dkp(desc, adata);
+	}
 	set_jump_tgt_here(desc, key_jump_cmd);
 
 	/* assoclen + cryptlen = seqinlen */
@@ -121,16 +126,16 @@ EXPORT_SYMBOL(cnstr_shdsc_aead_null_encap);
  * cnstr_shdsc_aead_null_decap - IPSec ESP decapsulation shared descriptor
  *                               (non-protocol) with no (null) decryption.
  * @desc: pointer to buffer used for descriptor construction
- * @adata: pointer to authentication transform definitions. Note that since a
- *         split key is to be used, the size of the split key itself is
- *         specified. Valid algorithm values - one of OP_ALG_ALGSEL_{MD5, SHA1,
- *         SHA224, SHA256, SHA384, SHA512} ANDed with OP_ALG_AAI_HMAC_PRECOMP.
+ * @adata: pointer to authentication transform definitions.
+ *         A split key is required for SEC Era < 6; the size of the split key
+ *         is specified in this case. Valid algorithm values - one of
+ *         OP_ALG_ALGSEL_{MD5, SHA1, SHA224, SHA256, SHA384, SHA512} ANDed
+ *         with OP_ALG_AAI_HMAC_PRECOMP.
  * @icvsize: integrity check value (ICV) size (truncated or full)
- *
- * Note: Requires an MDHA split key.
+ * @era: SEC Era
  */
 void cnstr_shdsc_aead_null_decap(u32 * const desc, struct alginfo *adata,
-				 unsigned int icvsize)
+				 unsigned int icvsize, int era)
 {
 	u32 *key_jump_cmd, *read_move_cmd, *write_move_cmd, *jump_cmd;
 
@@ -139,13 +144,18 @@ void cnstr_shdsc_aead_null_decap(u32 * const desc, struct alginfo *adata,
 	/* Skip if already shared */
 	key_jump_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
 				   JUMP_COND_SHRD);
-	if (adata->key_inline)
-		append_key_as_imm(desc, adata->key_virt, adata->keylen_pad,
-				  adata->keylen, CLASS_2 |
-				  KEY_DEST_MDHA_SPLIT | KEY_ENC);
-	else
-		append_key(desc, adata->key_dma, adata->keylen, CLASS_2 |
-			   KEY_DEST_MDHA_SPLIT | KEY_ENC);
+	if (era < 6) {
+		if (adata->key_inline)
+			append_key_as_imm(desc, adata->key_virt,
+					  adata->keylen_pad, adata->keylen,
+					  CLASS_2 | KEY_DEST_MDHA_SPLIT |
+					  KEY_ENC);
+		else
+			append_key(desc, adata->key_dma, adata->keylen,
+				   CLASS_2 | KEY_DEST_MDHA_SPLIT | KEY_ENC);
+	} else {
+		append_proto_dkp(desc, adata);
+	}
 	set_jump_tgt_here(desc, key_jump_cmd);
 
 	/* Class 2 operation */
@@ -204,7 +214,7 @@ EXPORT_SYMBOL(cnstr_shdsc_aead_null_decap);
 static void init_sh_desc_key_aead(u32 * const desc,
 				  struct alginfo * const cdata,
 				  struct alginfo * const adata,
-				  const bool is_rfc3686, u32 *nonce)
+				  const bool is_rfc3686, u32 *nonce, int era)
 {
 	u32 *key_jump_cmd;
 	unsigned int enckeylen = cdata->keylen;
@@ -224,13 +234,18 @@ static void init_sh_desc_key_aead(u32 * const desc,
 	if (is_rfc3686)
 		enckeylen -= CTR_RFC3686_NONCE_SIZE;
 
-	if (adata->key_inline)
-		append_key_as_imm(desc, adata->key_virt, adata->keylen_pad,
-				  adata->keylen, CLASS_2 |
-				  KEY_DEST_MDHA_SPLIT | KEY_ENC);
-	else
-		append_key(desc, adata->key_dma, adata->keylen, CLASS_2 |
-			   KEY_DEST_MDHA_SPLIT | KEY_ENC);
+	if (era < 6) {
+		if (adata->key_inline)
+			append_key_as_imm(desc, adata->key_virt,
+					  adata->keylen_pad, adata->keylen,
+					  CLASS_2 | KEY_DEST_MDHA_SPLIT |
+					  KEY_ENC);
+		else
+			append_key(desc, adata->key_dma, adata->keylen,
+				   CLASS_2 | KEY_DEST_MDHA_SPLIT | KEY_ENC);
+	} else {
+		append_proto_dkp(desc, adata);
+	}
 
 	if (cdata->key_inline)
 		append_key_as_imm(desc, cdata->key_virt, enckeylen,
@@ -261,26 +276,27 @@ static void init_sh_desc_key_aead(u32 * const desc,
  * @cdata: pointer to block cipher transform definitions
  *         Valid algorithm values - one of OP_ALG_ALGSEL_{AES, DES, 3DES} ANDed
  *         with OP_ALG_AAI_CBC or OP_ALG_AAI_CTR_MOD128.
- * @adata: pointer to authentication transform definitions. Note that since a
- *         split key is to be used, the size of the split key itself is
- *         specified. Valid algorithm values - one of OP_ALG_ALGSEL_{MD5, SHA1,
- *         SHA224, SHA256, SHA384, SHA512} ANDed with OP_ALG_AAI_HMAC_PRECOMP.
+ * @adata: pointer to authentication transform definitions.
+ *         A split key is required for SEC Era < 6; the size of the split key
+ *         is specified in this case. Valid algorithm values - one of
+ *         OP_ALG_ALGSEL_{MD5, SHA1, SHA224, SHA256, SHA384, SHA512} ANDed
+ *         with OP_ALG_AAI_HMAC_PRECOMP.
  * @ivsize: initialization vector size
  * @icvsize: integrity check value (ICV) size (truncated or full)
  * @is_rfc3686: true when ctr(aes) is wrapped by rfc3686 template
  * @nonce: pointer to rfc3686 nonce
  * @ctx1_iv_off: IV offset in CONTEXT1 register
  * @is_qi: true when called from caam/qi
- *
- * Note: Requires an MDHA split key.
+ * @era: SEC Era
  */
 void cnstr_shdsc_aead_encap(u32 * const desc, struct alginfo *cdata,
 			    struct alginfo *adata, unsigned int ivsize,
 			    unsigned int icvsize, const bool is_rfc3686,
-			    u32 *nonce, const u32 ctx1_iv_off, const bool is_qi)
+			    u32 *nonce, const u32 ctx1_iv_off, const bool is_qi,
+			    int era)
 {
 	/* Note: Context registers are saved. */
-	init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce);
+	init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce, era);
 
 	/* Class 2 operation */
 	append_operation(desc, adata->algtype | OP_ALG_AS_INITFINAL |
@@ -306,8 +322,13 @@ void cnstr_shdsc_aead_encap(u32 * const desc, struct alginfo *cdata,
 	}
 
 	/* Read and write assoclen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+	if (is_qi || era < 3) {
+		append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+		append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+	} else {
+		append_math_add(desc, VARSEQINLEN, ZERO, DPOVRD, CAAM_CMD_SZ);
+		append_math_add(desc, VARSEQOUTLEN, ZERO, DPOVRD, CAAM_CMD_SZ);
+	}
 
 	/* Skip assoc data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
@@ -350,27 +371,27 @@ EXPORT_SYMBOL(cnstr_shdsc_aead_encap);
  * @cdata: pointer to block cipher transform definitions
  *         Valid algorithm values - one of OP_ALG_ALGSEL_{AES, DES, 3DES} ANDed
  *         with OP_ALG_AAI_CBC or OP_ALG_AAI_CTR_MOD128.
- * @adata: pointer to authentication transform definitions. Note that since a
- *         split key is to be used, the size of the split key itself is
- *         specified. Valid algorithm values - one of OP_ALG_ALGSEL_{MD5, SHA1,
- *         SHA224, SHA256, SHA384, SHA512} ANDed with OP_ALG_AAI_HMAC_PRECOMP.
+ * @adata: pointer to authentication transform definitions.
+ *         A split key is required for SEC Era < 6; the size of the split key
+ *         is specified in this case. Valid algorithm values - one of
+ *         OP_ALG_ALGSEL_{MD5, SHA1, SHA224, SHA256, SHA384, SHA512} ANDed
+ *         with OP_ALG_AAI_HMAC_PRECOMP.
  * @ivsize: initialization vector size
  * @icvsize: integrity check value (ICV) size (truncated or full)
  * @is_rfc3686: true when ctr(aes) is wrapped by rfc3686 template
  * @nonce: pointer to rfc3686 nonce
  * @ctx1_iv_off: IV offset in CONTEXT1 register
  * @is_qi: true when called from caam/qi
- *
- * Note: Requires an MDHA split key.
+ * @era: SEC Era
  */
 void cnstr_shdsc_aead_decap(u32 * const desc, struct alginfo *cdata,
 			    struct alginfo *adata, unsigned int ivsize,
 			    unsigned int icvsize, const bool geniv,
 			    const bool is_rfc3686, u32 *nonce,
-			    const u32 ctx1_iv_off, const bool is_qi)
+			    const u32 ctx1_iv_off, const bool is_qi, int era)
 {
 	/* Note: Context registers are saved. */
-	init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce);
+	init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce, era);
 
 	/* Class 2 operation */
 	append_operation(desc, adata->algtype | OP_ALG_AS_INITFINAL |
@@ -397,11 +418,23 @@ void cnstr_shdsc_aead_decap(u32 * const desc, struct alginfo *cdata,
 	}
 
 	/* Read and write assoclen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
-	if (geniv)
-		append_math_add_imm_u32(desc, VARSEQOUTLEN, REG3, IMM, ivsize);
-	else
-		append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+	if (is_qi || era < 3) {
+		append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+		if (geniv)
+			append_math_add_imm_u32(desc, VARSEQOUTLEN, REG3, IMM,
+						ivsize);
+		else
+			append_math_add(desc, VARSEQOUTLEN, ZERO, REG3,
+					CAAM_CMD_SZ);
+	} else {
+		append_math_add(desc, VARSEQINLEN, ZERO, DPOVRD, CAAM_CMD_SZ);
+		if (geniv)
+			append_math_add_imm_u32(desc, VARSEQOUTLEN, DPOVRD, IMM,
+						ivsize);
+		else
+			append_math_add(desc, VARSEQOUTLEN, ZERO, DPOVRD,
+					CAAM_CMD_SZ);
+	}
 
 	/* Skip assoc data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
@@ -456,29 +489,29 @@ EXPORT_SYMBOL(cnstr_shdsc_aead_decap);
  * @cdata: pointer to block cipher transform definitions
  *         Valid algorithm values - one of OP_ALG_ALGSEL_{AES, DES, 3DES} ANDed
  *         with OP_ALG_AAI_CBC or OP_ALG_AAI_CTR_MOD128.
- * @adata: pointer to authentication transform definitions. Note that since a
- *         split key is to be used, the size of the split key itself is
- *         specified. Valid algorithm values - one of OP_ALG_ALGSEL_{MD5, SHA1,
- *         SHA224, SHA256, SHA384, SHA512} ANDed with OP_ALG_AAI_HMAC_PRECOMP.
+ * @adata: pointer to authentication transform definitions.
+ *         A split key is required for SEC Era < 6; the size of the split key
+ *         is specified in this case. Valid algorithm values - one of
+ *         OP_ALG_ALGSEL_{MD5, SHA1, SHA224, SHA256, SHA384, SHA512} ANDed
+ *         with OP_ALG_AAI_HMAC_PRECOMP.
  * @ivsize: initialization vector size
  * @icvsize: integrity check value (ICV) size (truncated or full)
  * @is_rfc3686: true when ctr(aes) is wrapped by rfc3686 template
  * @nonce: pointer to rfc3686 nonce
  * @ctx1_iv_off: IV offset in CONTEXT1 register
  * @is_qi: true when called from caam/qi
- *
- * Note: Requires an MDHA split key.
+ * @era: SEC Era
  */
 void cnstr_shdsc_aead_givencap(u32 * const desc, struct alginfo *cdata,
 			       struct alginfo *adata, unsigned int ivsize,
 			       unsigned int icvsize, const bool is_rfc3686,
 			       u32 *nonce, const u32 ctx1_iv_off,
-			       const bool is_qi)
+			       const bool is_qi, int era)
 {
 	u32 geniv, moveiv;
 
 	/* Note: Context registers are saved. */
-	init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce);
+	init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce, era);
 
 	if (is_qi) {
 		u32 *wait_load_cmd;
@@ -528,8 +561,13 @@ copy_iv:
 			 OP_ALG_ENCRYPT);
 
 	/* Read and write assoclen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+	if (is_qi || era < 3) {
+		append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+		append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+	} else {
+		append_math_add(desc, VARSEQINLEN, ZERO, DPOVRD, CAAM_CMD_SZ);
+		append_math_add(desc, VARSEQOUTLEN, ZERO, DPOVRD, CAAM_CMD_SZ);
+	}
 
 	/* Skip assoc data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
@@ -1075,7 +1113,7 @@ void cnstr_shdsc_ablkcipher_encap(u32 * const desc, struct alginfo *cdata,
 
 	/* Load nonce into CONTEXT1 reg */
 	if (is_rfc3686) {
-		u8 *nonce = cdata->key_virt + cdata->keylen;
+		const u8 *nonce = cdata->key_virt + cdata->keylen;
 
 		append_load_as_imm(desc, nonce, CTR_RFC3686_NONCE_SIZE,
 				   LDST_CLASS_IND_CCB |
@@ -1140,7 +1178,7 @@ void cnstr_shdsc_ablkcipher_decap(u32 * const desc, struct alginfo *cdata,
 
 	/* Load nonce into CONTEXT1 reg */
 	if (is_rfc3686) {
-		u8 *nonce = cdata->key_virt + cdata->keylen;
+		const u8 *nonce = cdata->key_virt + cdata->keylen;
 
 		append_load_as_imm(desc, nonce, CTR_RFC3686_NONCE_SIZE,
 				   LDST_CLASS_IND_CCB |
@@ -1209,7 +1247,7 @@ void cnstr_shdsc_ablkcipher_givencap(u32 * const desc, struct alginfo *cdata,
 
 	/* Load Nonce into CONTEXT1 reg */
 	if (is_rfc3686) {
-		u8 *nonce = cdata->key_virt + cdata->keylen;
+		const u8 *nonce = cdata->key_virt + cdata->keylen;
 
 		append_load_as_imm(desc, nonce, CTR_RFC3686_NONCE_SIZE,
 				   LDST_CLASS_IND_CCB |
diff --git a/drivers/crypto/caam/caamalg_desc.h b/drivers/crypto/caam/caamalg_desc.h
index e412ec8f7005..5f9445ae2114 100644
--- a/drivers/crypto/caam/caamalg_desc.h
+++ b/drivers/crypto/caam/caamalg_desc.h
@@ -43,28 +43,28 @@
 					 15 * CAAM_CMD_SZ)
 
 void cnstr_shdsc_aead_null_encap(u32 * const desc, struct alginfo *adata,
-				 unsigned int icvsize);
+				 unsigned int icvsize, int era);
 
 void cnstr_shdsc_aead_null_decap(u32 * const desc, struct alginfo *adata,
-				 unsigned int icvsize);
+				 unsigned int icvsize, int era);
 
 void cnstr_shdsc_aead_encap(u32 * const desc, struct alginfo *cdata,
 			    struct alginfo *adata, unsigned int ivsize,
 			    unsigned int icvsize, const bool is_rfc3686,
 			    u32 *nonce, const u32 ctx1_iv_off,
-			    const bool is_qi);
+			    const bool is_qi, int era);
 
 void cnstr_shdsc_aead_decap(u32 * const desc, struct alginfo *cdata,
 			    struct alginfo *adata, unsigned int ivsize,
 			    unsigned int icvsize, const bool geniv,
 			    const bool is_rfc3686, u32 *nonce,
-			    const u32 ctx1_iv_off, const bool is_qi);
+			    const u32 ctx1_iv_off, const bool is_qi, int era);
 
 void cnstr_shdsc_aead_givencap(u32 * const desc, struct alginfo *cdata,
 			       struct alginfo *adata, unsigned int ivsize,
 			       unsigned int icvsize, const bool is_rfc3686,
 			       u32 *nonce, const u32 ctx1_iv_off,
-			       const bool is_qi);
+			       const bool is_qi, int era);
 
 void cnstr_shdsc_gcm_encap(u32 * const desc, struct alginfo *cdata,
 			   unsigned int icvsize);
diff --git a/drivers/crypto/caam/caamalg_qi.c b/drivers/crypto/caam/caamalg_qi.c
index f9f08fce4356..4aecc9435f69 100644
--- a/drivers/crypto/caam/caamalg_qi.c
+++ b/drivers/crypto/caam/caamalg_qi.c
@@ -53,6 +53,7 @@ struct caam_ctx {
 	u32 sh_desc_givenc[DESC_MAX_USED_LEN];
 	u8 key[CAAM_MAX_KEY_SIZE];
 	dma_addr_t key_dma;
+	enum dma_data_direction dir;
 	struct alginfo adata;
 	struct alginfo cdata;
 	unsigned int authsize;
@@ -74,6 +75,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	const bool ctr_mode = ((ctx->cdata.algtype & OP_ALG_AAI_MASK) ==
 			       OP_ALG_AAI_CTR_MOD128);
 	const bool is_rfc3686 = alg->caam.rfc3686;
+	struct caam_drv_private *ctrlpriv = dev_get_drvdata(ctx->jrdev->parent);
 
 	if (!ctx->cdata.keylen || !ctx->authsize)
 		return 0;
@@ -124,7 +126,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 
 	cnstr_shdsc_aead_encap(ctx->sh_desc_enc, &ctx->cdata, &ctx->adata,
 			       ivsize, ctx->authsize, is_rfc3686, nonce,
-			       ctx1_iv_off, true);
+			       ctx1_iv_off, true, ctrlpriv->era);
 
 skip_enc:
 	/* aead_decrypt shared descriptor */
@@ -149,7 +151,8 @@ skip_enc:
 
 	cnstr_shdsc_aead_decap(ctx->sh_desc_dec, &ctx->cdata, &ctx->adata,
 			       ivsize, ctx->authsize, alg->caam.geniv,
-			       is_rfc3686, nonce, ctx1_iv_off, true);
+			       is_rfc3686, nonce, ctx1_iv_off, true,
+			       ctrlpriv->era);
 
 	if (!alg->caam.geniv)
 		goto skip_givenc;
@@ -176,7 +179,7 @@ skip_enc:
 
 	cnstr_shdsc_aead_givencap(ctx->sh_desc_enc, &ctx->cdata, &ctx->adata,
 				  ivsize, ctx->authsize, is_rfc3686, nonce,
-				  ctx1_iv_off, true);
+				  ctx1_iv_off, true, ctrlpriv->era);
 
 skip_givenc:
 	return 0;
@@ -197,6 +200,7 @@ static int aead_setkey(struct crypto_aead *aead, const u8 *key,
 {
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
+	struct caam_drv_private *ctrlpriv = dev_get_drvdata(jrdev->parent);
 	struct crypto_authenc_keys keys;
 	int ret = 0;
 
@@ -211,6 +215,27 @@ static int aead_setkey(struct crypto_aead *aead, const u8 *key,
 		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
 #endif
 
+	/*
+	 * If DKP is supported, use it in the shared descriptor to generate
+	 * the split key.
+	 */
+	if (ctrlpriv->era >= 6) {
+		ctx->adata.keylen = keys.authkeylen;
+		ctx->adata.keylen_pad = split_key_len(ctx->adata.algtype &
+						      OP_ALG_ALGSEL_MASK);
+
+		if (ctx->adata.keylen_pad + keys.enckeylen > CAAM_MAX_KEY_SIZE)
+			goto badkey;
+
+		memcpy(ctx->key, keys.authkey, keys.authkeylen);
+		memcpy(ctx->key + ctx->adata.keylen_pad, keys.enckey,
+		       keys.enckeylen);
+		dma_sync_single_for_device(jrdev, ctx->key_dma,
+					   ctx->adata.keylen_pad +
+					   keys.enckeylen, ctx->dir);
+		goto skip_split_key;
+	}
+
 	ret = gen_split_key(jrdev, ctx->key, &ctx->adata, keys.authkey,
 			    keys.authkeylen, CAAM_MAX_KEY_SIZE -
 			    keys.enckeylen);
@@ -220,13 +245,14 @@ static int aead_setkey(struct crypto_aead *aead, const u8 *key,
 	/* postpend encryption key to auth split key */
 	memcpy(ctx->key + ctx->adata.keylen_pad, keys.enckey, keys.enckeylen);
 	dma_sync_single_for_device(jrdev, ctx->key_dma, ctx->adata.keylen_pad +
-				   keys.enckeylen, DMA_TO_DEVICE);
+				   keys.enckeylen, ctx->dir);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "ctx.key@" __stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, ctx->key,
 		       ctx->adata.keylen_pad + keys.enckeylen, 1);
 #endif
 
+skip_split_key:
 	ctx->cdata.keylen = keys.enckeylen;
 
 	ret = aead_set_sh_desc(aead);
@@ -272,7 +298,6 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 	const bool is_rfc3686 = (ctr_mode && strstr(alg_name, "rfc3686"));
 	int ret = 0;
 
-	memcpy(ctx->key, key, keylen);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "key in @" __stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
@@ -295,9 +320,8 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 		keylen -= CTR_RFC3686_NONCE_SIZE;
 	}
 
-	dma_sync_single_for_device(jrdev, ctx->key_dma, keylen, DMA_TO_DEVICE);
 	ctx->cdata.keylen = keylen;
-	ctx->cdata.key_virt = ctx->key;
+	ctx->cdata.key_virt = key;
 	ctx->cdata.key_inline = true;
 
 	/* ablkcipher encrypt, decrypt, givencrypt shared descriptors */
@@ -356,10 +380,8 @@ static int xts_ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 		return -EINVAL;
 	}
 
-	memcpy(ctx->key, key, keylen);
-	dma_sync_single_for_device(jrdev, ctx->key_dma, keylen, DMA_TO_DEVICE);
 	ctx->cdata.keylen = keylen;
-	ctx->cdata.key_virt = ctx->key;
+	ctx->cdata.key_virt = key;
 	ctx->cdata.key_inline = true;
 
 	/* xts ablkcipher encrypt, decrypt shared descriptors */
@@ -668,7 +690,7 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 	qm_sg_ents = 1 + !!ivsize + mapped_src_nents +
 		     (mapped_dst_nents > 1 ? mapped_dst_nents : 0);
 	if (unlikely(qm_sg_ents > CAAM_QI_MAX_AEAD_SG)) {
-		dev_err(qidev, "Insufficient S/G entries: %d > %lu\n",
+		dev_err(qidev, "Insufficient S/G entries: %d > %zu\n",
 			qm_sg_ents, CAAM_QI_MAX_AEAD_SG);
 		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
 			   iv_dma, ivsize, op_type, 0, 0);
@@ -905,7 +927,7 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 
 	qm_sg_ents += mapped_dst_nents > 1 ? mapped_dst_nents : 0;
 	if (unlikely(qm_sg_ents > CAAM_QI_MAX_ABLKCIPHER_SG)) {
-		dev_err(qidev, "Insufficient S/G entries: %d > %lu\n",
+		dev_err(qidev, "Insufficient S/G entries: %d > %zu\n",
 			qm_sg_ents, CAAM_QI_MAX_ABLKCIPHER_SG);
 		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
 			   iv_dma, ivsize, op_type, 0, 0);
@@ -1058,7 +1080,7 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 	}
 
 	if (unlikely(qm_sg_ents > CAAM_QI_MAX_ABLKCIPHER_SG)) {
-		dev_err(qidev, "Insufficient S/G entries: %d > %lu\n",
+		dev_err(qidev, "Insufficient S/G entries: %d > %zu\n",
 			qm_sg_ents, CAAM_QI_MAX_ABLKCIPHER_SG);
 		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
 			   iv_dma, ivsize, GIVENCRYPT, 0, 0);
@@ -2123,7 +2145,8 @@ struct caam_crypto_alg {
 	struct caam_alg_entry caam;
 };
 
-static int caam_init_common(struct caam_ctx *ctx, struct caam_alg_entry *caam)
+static int caam_init_common(struct caam_ctx *ctx, struct caam_alg_entry *caam,
+			    bool uses_dkp)
 {
 	struct caam_drv_private *priv;
 
@@ -2137,8 +2160,14 @@ static int caam_init_common(struct caam_ctx *ctx, struct caam_alg_entry *caam)
 		return PTR_ERR(ctx->jrdev);
 	}
 
+	priv = dev_get_drvdata(ctx->jrdev->parent);
+	if (priv->era >= 6 && uses_dkp)
+		ctx->dir = DMA_BIDIRECTIONAL;
+	else
+		ctx->dir = DMA_TO_DEVICE;
+
 	ctx->key_dma = dma_map_single(ctx->jrdev, ctx->key, sizeof(ctx->key),
-				      DMA_TO_DEVICE);
+				      ctx->dir);
 	if (dma_mapping_error(ctx->jrdev, ctx->key_dma)) {
 		dev_err(ctx->jrdev, "unable to map key\n");
 		caam_jr_free(ctx->jrdev);
@@ -2149,7 +2178,6 @@ static int caam_init_common(struct caam_ctx *ctx, struct caam_alg_entry *caam)
 	ctx->cdata.algtype = OP_TYPE_CLASS1_ALG | caam->class1_alg_type;
 	ctx->adata.algtype = OP_TYPE_CLASS2_ALG | caam->class2_alg_type;
 
-	priv = dev_get_drvdata(ctx->jrdev->parent);
 	ctx->qidev = priv->qidev;
 
 	spin_lock_init(&ctx->lock);
@@ -2167,7 +2195,7 @@ static int caam_cra_init(struct crypto_tfm *tfm)
 							crypto_alg);
 	struct caam_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	return caam_init_common(ctx, &caam_alg->caam);
+	return caam_init_common(ctx, &caam_alg->caam, false);
 }
 
 static int caam_aead_init(struct crypto_aead *tfm)
@@ -2177,7 +2205,8 @@ static int caam_aead_init(struct crypto_aead *tfm)
 						      aead);
 	struct caam_ctx *ctx = crypto_aead_ctx(tfm);
 
-	return caam_init_common(ctx, &caam_alg->caam);
+	return caam_init_common(ctx, &caam_alg->caam,
+				alg->setkey == aead_setkey);
 }
 
 static void caam_exit_common(struct caam_ctx *ctx)
@@ -2186,8 +2215,7 @@ static void caam_exit_common(struct caam_ctx *ctx)
 	caam_drv_ctx_rel(ctx->drv_ctx[DECRYPT]);
 	caam_drv_ctx_rel(ctx->drv_ctx[GIVENCRYPT]);
 
-	dma_unmap_single(ctx->jrdev, ctx->key_dma, sizeof(ctx->key),
-			 DMA_TO_DEVICE);
+	dma_unmap_single(ctx->jrdev, ctx->key_dma, sizeof(ctx->key), ctx->dir);
 
 	caam_jr_free(ctx->jrdev);
 }
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 616720a04e7a..0beb28196e20 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -107,6 +107,7 @@ struct caam_hash_ctx {
 	dma_addr_t sh_desc_update_first_dma;
 	dma_addr_t sh_desc_fin_dma;
 	dma_addr_t sh_desc_digest_dma;
+	enum dma_data_direction dir;
 	struct device *jrdev;
 	u8 key[CAAM_MAX_HASH_KEY_SIZE];
 	int ctx_len;
@@ -241,7 +242,8 @@ static inline int ctx_map_to_sec4_sg(struct device *jrdev,
  *     read and write to seqout
  */
 static inline void ahash_gen_sh_desc(u32 *desc, u32 state, int digestsize,
-				     struct caam_hash_ctx *ctx, bool import_ctx)
+				     struct caam_hash_ctx *ctx, bool import_ctx,
+				     int era)
 {
 	u32 op = ctx->adata.algtype;
 	u32 *skip_key_load;
@@ -254,9 +256,12 @@ static inline void ahash_gen_sh_desc(u32 *desc, u32 state, int digestsize,
 		skip_key_load = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
 					    JUMP_COND_SHRD);
 
-		append_key_as_imm(desc, ctx->key, ctx->adata.keylen_pad,
-				  ctx->adata.keylen, CLASS_2 |
-				  KEY_DEST_MDHA_SPLIT | KEY_ENC);
+		if (era < 6)
+			append_key_as_imm(desc, ctx->key, ctx->adata.keylen_pad,
+					  ctx->adata.keylen, CLASS_2 |
+					  KEY_DEST_MDHA_SPLIT | KEY_ENC);
+		else
+			append_proto_dkp(desc, &ctx->adata);
 
 		set_jump_tgt_here(desc, skip_key_load);
 
@@ -289,13 +294,17 @@ static int ahash_set_sh_desc(struct crypto_ahash *ahash)
 	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
 	int digestsize = crypto_ahash_digestsize(ahash);
 	struct device *jrdev = ctx->jrdev;
+	struct caam_drv_private *ctrlpriv = dev_get_drvdata(jrdev->parent);
 	u32 *desc;
 
+	ctx->adata.key_virt = ctx->key;
+
 	/* ahash_update shared descriptor */
 	desc = ctx->sh_desc_update;
-	ahash_gen_sh_desc(desc, OP_ALG_AS_UPDATE, ctx->ctx_len, ctx, true);
+	ahash_gen_sh_desc(desc, OP_ALG_AS_UPDATE, ctx->ctx_len, ctx, true,
+			  ctrlpriv->era);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_update_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR,
 		       "ahash update shdesc@"__stringify(__LINE__)": ",
@@ -304,9 +313,10 @@ static int ahash_set_sh_desc(struct crypto_ahash *ahash)
 
 	/* ahash_update_first shared descriptor */
 	desc = ctx->sh_desc_update_first;
-	ahash_gen_sh_desc(desc, OP_ALG_AS_INIT, ctx->ctx_len, ctx, false);
+	ahash_gen_sh_desc(desc, OP_ALG_AS_INIT, ctx->ctx_len, ctx, false,
+			  ctrlpriv->era);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_update_first_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR,
 		       "ahash update first shdesc@"__stringify(__LINE__)": ",
@@ -315,9 +325,10 @@ static int ahash_set_sh_desc(struct crypto_ahash *ahash)
 
 	/* ahash_final shared descriptor */
 	desc = ctx->sh_desc_fin;
-	ahash_gen_sh_desc(desc, OP_ALG_AS_FINALIZE, digestsize, ctx, true);
+	ahash_gen_sh_desc(desc, OP_ALG_AS_FINALIZE, digestsize, ctx, true,
+			  ctrlpriv->era);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_fin_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "ahash final shdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
@@ -326,9 +337,10 @@ static int ahash_set_sh_desc(struct crypto_ahash *ahash)
 
 	/* ahash_digest shared descriptor */
 	desc = ctx->sh_desc_digest;
-	ahash_gen_sh_desc(desc, OP_ALG_AS_INITFINAL, digestsize, ctx, false);
+	ahash_gen_sh_desc(desc, OP_ALG_AS_INITFINAL, digestsize, ctx, false,
+			  ctrlpriv->era);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_digest_dma,
-				   desc_bytes(desc), DMA_TO_DEVICE);
+				   desc_bytes(desc), ctx->dir);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR,
 		       "ahash digest shdesc@"__stringify(__LINE__)": ",
@@ -421,6 +433,7 @@ static int ahash_setkey(struct crypto_ahash *ahash,
 	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
 	int blocksize = crypto_tfm_alg_blocksize(&ahash->base);
 	int digestsize = crypto_ahash_digestsize(ahash);
+	struct caam_drv_private *ctrlpriv = dev_get_drvdata(ctx->jrdev->parent);
 	int ret;
 	u8 *hashed_key = NULL;
 
@@ -441,16 +454,26 @@ static int ahash_setkey(struct crypto_ahash *ahash,
 		key = hashed_key;
 	}
 
-	ret = gen_split_key(ctx->jrdev, ctx->key, &ctx->adata, key, keylen,
-			    CAAM_MAX_HASH_KEY_SIZE);
-	if (ret)
-		goto bad_free_key;
+	/*
+	 * If DKP is supported, use it in the shared descriptor to generate
+	 * the split key.
+	 */
+	if (ctrlpriv->era >= 6) {
+		ctx->adata.key_inline = true;
+		ctx->adata.keylen = keylen;
+		ctx->adata.keylen_pad = split_key_len(ctx->adata.algtype &
+						      OP_ALG_ALGSEL_MASK);
 
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ctx.key@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, ctx->key,
-		       ctx->adata.keylen_pad, 1);
-#endif
+		if (ctx->adata.keylen_pad > CAAM_MAX_HASH_KEY_SIZE)
+			goto bad_free_key;
+
+		memcpy(ctx->key, key, keylen);
+	} else {
+		ret = gen_split_key(ctx->jrdev, ctx->key, &ctx->adata, key,
+				    keylen, CAAM_MAX_HASH_KEY_SIZE);
+		if (ret)
+			goto bad_free_key;
+	}
 
 	kfree(hashed_key);
 	return ahash_set_sh_desc(ahash);
@@ -1715,6 +1738,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 					 HASH_MSG_LEN + 64,
 					 HASH_MSG_LEN + SHA512_DIGEST_SIZE };
 	dma_addr_t dma_addr;
+	struct caam_drv_private *priv;
 
 	/*
 	 * Get a Job ring from Job Ring driver to ensure in-order
@@ -1726,10 +1750,13 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 		return PTR_ERR(ctx->jrdev);
 	}
 
+	priv = dev_get_drvdata(ctx->jrdev->parent);
+	ctx->dir = priv->era >= 6 ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
+
 	dma_addr = dma_map_single_attrs(ctx->jrdev, ctx->sh_desc_update,
 					offsetof(struct caam_hash_ctx,
 						 sh_desc_update_dma),
-					DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+					ctx->dir, DMA_ATTR_SKIP_CPU_SYNC);
 	if (dma_mapping_error(ctx->jrdev, dma_addr)) {
 		dev_err(ctx->jrdev, "unable to map shared descriptors\n");
 		caam_jr_free(ctx->jrdev);
@@ -1764,7 +1791,7 @@ static void caam_hash_cra_exit(struct crypto_tfm *tfm)
 	dma_unmap_single_attrs(ctx->jrdev, ctx->sh_desc_update_dma,
 			       offsetof(struct caam_hash_ctx,
 					sh_desc_update_dma),
-			       DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+			       ctx->dir, DMA_ATTR_SKIP_CPU_SYNC);
 	caam_jr_free(ctx->jrdev);
 }
 
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 027e121c6f70..75d280cb2dc0 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -611,6 +611,8 @@ static int caam_probe(struct platform_device *pdev)
 		goto iounmap_ctrl;
 	}
 
+	ctrlpriv->era = caam_get_era();
+
 	ret = of_platform_populate(nprop, caam_match, NULL, dev);
 	if (ret) {
 		dev_err(dev, "JR platform devices creation error\n");
@@ -742,7 +744,7 @@ static int caam_probe(struct platform_device *pdev)
 
 	/* Report "alive" for developer to see */
 	dev_info(dev, "device ID = 0x%016llx (Era %d)\n", caam_id,
-		 caam_get_era());
+		 ctrlpriv->era);
 	dev_info(dev, "job rings = %d, qi = %d, dpaa2 = %s\n",
 		 ctrlpriv->total_jobrs, ctrlpriv->qi_present,
 		 caam_dpaa2 ? "yes" : "no");
diff --git a/drivers/crypto/caam/desc.h b/drivers/crypto/caam/desc.h
index 8142de7ba050..f76ff160a02c 100644
--- a/drivers/crypto/caam/desc.h
+++ b/drivers/crypto/caam/desc.h
@@ -444,6 +444,18 @@
 #define OP_PCLID_DSAVERIFY	(0x16 << OP_PCLID_SHIFT)
 #define OP_PCLID_RSAENC_PUBKEY  (0x18 << OP_PCLID_SHIFT)
 #define OP_PCLID_RSADEC_PRVKEY  (0x19 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_MD5	(0x20 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_SHA1	(0x21 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_SHA224	(0x22 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_SHA256	(0x23 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_SHA384	(0x24 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_SHA512	(0x25 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_RIF_MD5	(0x60 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_RIF_SHA1	(0x61 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_RIF_SHA224	(0x62 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_RIF_SHA256	(0x63 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_RIF_SHA384	(0x64 << OP_PCLID_SHIFT)
+#define OP_PCLID_DKP_RIF_SHA512	(0x65 << OP_PCLID_SHIFT)
 
 /* Assuming OP_TYPE = OP_TYPE_DECAP_PROTOCOL/ENCAP_PROTOCOL */
 #define OP_PCLID_IPSEC		(0x01 << OP_PCLID_SHIFT)
@@ -1093,6 +1105,22 @@
 /* MacSec protinfos */
 #define OP_PCL_MACSEC				 0x0001
 
+/* Derived Key Protocol (DKP) Protinfo */
+#define OP_PCL_DKP_SRC_SHIFT	14
+#define OP_PCL_DKP_SRC_MASK	(3 << OP_PCL_DKP_SRC_SHIFT)
+#define OP_PCL_DKP_SRC_IMM	(0 << OP_PCL_DKP_SRC_SHIFT)
+#define OP_PCL_DKP_SRC_SEQ	(1 << OP_PCL_DKP_SRC_SHIFT)
+#define OP_PCL_DKP_SRC_PTR	(2 << OP_PCL_DKP_SRC_SHIFT)
+#define OP_PCL_DKP_SRC_SGF	(3 << OP_PCL_DKP_SRC_SHIFT)
+#define OP_PCL_DKP_DST_SHIFT	12
+#define OP_PCL_DKP_DST_MASK	(3 << OP_PCL_DKP_DST_SHIFT)
+#define OP_PCL_DKP_DST_IMM	(0 << OP_PCL_DKP_DST_SHIFT)
+#define OP_PCL_DKP_DST_SEQ	(1 << OP_PCL_DKP_DST_SHIFT)
+#define OP_PCL_DKP_DST_PTR	(2 << OP_PCL_DKP_DST_SHIFT)
+#define OP_PCL_DKP_DST_SGF	(3 << OP_PCL_DKP_DST_SHIFT)
+#define OP_PCL_DKP_KEY_SHIFT	0
+#define OP_PCL_DKP_KEY_MASK	(0xfff << OP_PCL_DKP_KEY_SHIFT)
+
 /* PKI unidirectional protocol protinfo bits */
 #define OP_PCL_PKPROT_TEST			 0x0008
 #define OP_PCL_PKPROT_DECRYPT			 0x0004
@@ -1452,6 +1480,7 @@
 #define MATH_DEST_REG1		(0x01 << MATH_DEST_SHIFT)
 #define MATH_DEST_REG2		(0x02 << MATH_DEST_SHIFT)
 #define MATH_DEST_REG3		(0x03 << MATH_DEST_SHIFT)
+#define MATH_DEST_DPOVRD	(0x07 << MATH_DEST_SHIFT)
 #define MATH_DEST_SEQINLEN	(0x08 << MATH_DEST_SHIFT)
 #define MATH_DEST_SEQOUTLEN	(0x09 << MATH_DEST_SHIFT)
 #define MATH_DEST_VARSEQINLEN	(0x0a << MATH_DEST_SHIFT)
diff --git a/drivers/crypto/caam/desc_constr.h b/drivers/crypto/caam/desc_constr.h
index ba1ca0806f0a..d4256fa4a1d6 100644
--- a/drivers/crypto/caam/desc_constr.h
+++ b/drivers/crypto/caam/desc_constr.h
@@ -109,7 +109,7 @@ static inline void init_job_desc_shared(u32 * const desc, dma_addr_t ptr,
 	append_ptr(desc, ptr);
 }
 
-static inline void append_data(u32 * const desc, void *data, int len)
+static inline void append_data(u32 * const desc, const void *data, int len)
 {
 	u32 *offset = desc_end(desc);
 
@@ -172,7 +172,7 @@ static inline void append_cmd_ptr_extlen(u32 * const desc, dma_addr_t ptr,
 	append_cmd(desc, len);
 }
 
-static inline void append_cmd_data(u32 * const desc, void *data, int len,
+static inline void append_cmd_data(u32 * const desc, const void *data, int len,
 				   u32 command)
 {
 	append_cmd(desc, command | IMMEDIATE | len);
@@ -271,7 +271,7 @@ APPEND_SEQ_PTR_INTLEN(in, IN)
 APPEND_SEQ_PTR_INTLEN(out, OUT)
 
 #define APPEND_CMD_PTR_TO_IMM(cmd, op) \
-static inline void append_##cmd##_as_imm(u32 * const desc, void *data, \
+static inline void append_##cmd##_as_imm(u32 * const desc, const void *data, \
 					 unsigned int len, u32 options) \
 { \
 	PRINT_POS; \
@@ -312,7 +312,7 @@ APPEND_CMD_PTR_LEN(seq_out_ptr, SEQ_OUT_PTR, u32)
  * from length of immediate data provided, e.g., split keys
  */
 #define APPEND_CMD_PTR_TO_IMM2(cmd, op) \
-static inline void append_##cmd##_as_imm(u32 * const desc, void *data, \
+static inline void append_##cmd##_as_imm(u32 * const desc, const void *data, \
 					 unsigned int data_len, \
 					 unsigned int len, u32 options) \
 { \
@@ -452,7 +452,7 @@ struct alginfo {
 	unsigned int keylen_pad;
 	union {
 		dma_addr_t key_dma;
-		void *key_virt;
+		const void *key_virt;
 	};
 	bool key_inline;
 };
@@ -496,4 +496,45 @@ static inline int desc_inline_query(unsigned int sd_base_len,
 	return (rem_bytes >= 0) ? 0 : -1;
 }
 
+/**
+ * append_proto_dkp - Derived Key Protocol (DKP): key -> split key
+ * @desc: pointer to buffer used for descriptor construction
+ * @adata: pointer to authentication transform definitions.
+ *         keylen should be the length of initial key, while keylen_pad
+ *         the length of the derived (split) key.
+ *         Valid algorithm values - one of OP_ALG_ALGSEL_{MD5, SHA1, SHA224,
+ *         SHA256, SHA384, SHA512}.
+ */
+static inline void append_proto_dkp(u32 * const desc, struct alginfo *adata)
+{
+	u32 protid;
+
+	/*
+	 * Quick & dirty translation from OP_ALG_ALGSEL_{MD5, SHA*}
+	 * to OP_PCLID_DKP_{MD5, SHA*}
+	 */
+	protid = (adata->algtype & OP_ALG_ALGSEL_SUBMASK) |
+		 (0x20 << OP_ALG_ALGSEL_SHIFT);
+
+	if (adata->key_inline) {
+		int words;
+
+		append_operation(desc, OP_TYPE_UNI_PROTOCOL | protid |
+				 OP_PCL_DKP_SRC_IMM | OP_PCL_DKP_DST_IMM |
+				 adata->keylen);
+		append_data(desc, adata->key_virt, adata->keylen);
+
+		/* Reserve space in descriptor buffer for the derived key */
+		words = (ALIGN(adata->keylen_pad, CAAM_CMD_SZ) -
+			 ALIGN(adata->keylen, CAAM_CMD_SZ)) / CAAM_CMD_SZ;
+		if (words)
+			(*desc) = cpu_to_caam32(caam32_to_cpu(*desc) + words);
+	} else {
+		append_operation(desc, OP_TYPE_UNI_PROTOCOL | protid |
+				 OP_PCL_DKP_SRC_PTR | OP_PCL_DKP_DST_PTR |
+				 adata->keylen);
+		append_ptr(desc, adata->key_dma);
+	}
+}
+
 #endif /* DESC_CONSTR_H */
diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h
index 91f1107276e5..7696a774a362 100644
--- a/drivers/crypto/caam/intern.h
+++ b/drivers/crypto/caam/intern.h
@@ -84,6 +84,7 @@ struct caam_drv_private {
 	u8 qi_present;		/* Nonzero if QI present in device */
 	int secvio_irq;		/* Security violation interrupt number */
 	int virt_en;		/* Virtualization enabled in CAAM */
+	int era;		/* CAAM Era (internal HW revision) */
 
 #define	RNG4_MAX_HANDLES 2
 	/* RNG4 block */
diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c
index 8c79c3a153dc..312b5f042f31 100644
--- a/drivers/crypto/caam/key_gen.c
+++ b/drivers/crypto/caam/key_gen.c
@@ -11,36 +11,6 @@
 #include "desc_constr.h"
 #include "key_gen.h"
 
-/**
- * split_key_len - Compute MDHA split key length for a given algorithm
- * @hash: Hashing algorithm selection, one of OP_ALG_ALGSEL_* - MD5, SHA1,
- *        SHA224, SHA384, SHA512.
- *
- * Return: MDHA split key length
- */
-static inline u32 split_key_len(u32 hash)
-{
-	/* Sizes for MDHA pads (*not* keys): MD5, SHA1, 224, 256, 384, 512 */
-	static const u8 mdpadlen[] = { 16, 20, 32, 32, 64, 64 };
-	u32 idx;
-
-	idx = (hash & OP_ALG_ALGSEL_SUBMASK) >> OP_ALG_ALGSEL_SHIFT;
-
-	return (u32)(mdpadlen[idx] * 2);
-}
-
-/**
- * split_key_pad_len - Compute MDHA split key pad length for a given algorithm
- * @hash: Hashing algorithm selection, one of OP_ALG_ALGSEL_* - MD5, SHA1,
- *        SHA224, SHA384, SHA512.
- *
- * Return: MDHA split key pad length
- */
-static inline u32 split_key_pad_len(u32 hash)
-{
-	return ALIGN(split_key_len(hash), 16);
-}
-
 void split_key_done(struct device *dev, u32 *desc, u32 err,
 			   void *context)
 {
diff --git a/drivers/crypto/caam/key_gen.h b/drivers/crypto/caam/key_gen.h
index 5db055c25bd2..818f78f6fc1a 100644
--- a/drivers/crypto/caam/key_gen.h
+++ b/drivers/crypto/caam/key_gen.h
@@ -6,6 +6,36 @@
  *
  */
 
+/**
+ * split_key_len - Compute MDHA split key length for a given algorithm
+ * @hash: Hashing algorithm selection, one of OP_ALG_ALGSEL_* - MD5, SHA1,
+ *        SHA224, SHA384, SHA512.
+ *
+ * Return: MDHA split key length
+ */
+static inline u32 split_key_len(u32 hash)
+{
+	/* Sizes for MDHA pads (*not* keys): MD5, SHA1, 224, 256, 384, 512 */
+	static const u8 mdpadlen[] = { 16, 20, 32, 32, 64, 64 };
+	u32 idx;
+
+	idx = (hash & OP_ALG_ALGSEL_SUBMASK) >> OP_ALG_ALGSEL_SHIFT;
+
+	return (u32)(mdpadlen[idx] * 2);
+}
+
+/**
+ * split_key_pad_len - Compute MDHA split key pad length for a given algorithm
+ * @hash: Hashing algorithm selection, one of OP_ALG_ALGSEL_* - MD5, SHA1,
+ *        SHA224, SHA384, SHA512.
+ *
+ * Return: MDHA split key pad length
+ */
+static inline u32 split_key_pad_len(u32 hash)
+{
+	return ALIGN(split_key_len(hash), 16);
+}
+
 struct split_key_result {
 	struct completion completion;
 	int err;
diff --git a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
index 169e66231bcf..b0ba4331944b 100644
--- a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
+++ b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
@@ -459,7 +459,8 @@ int process_request(struct cpt_vf *cptvf, struct cpt_request_info *req)
 	info->completion_addr = kzalloc(sizeof(union cpt_res_s), GFP_KERNEL);
 	if (unlikely(!info->completion_addr)) {
 		dev_err(&pdev->dev, "Unable to allocate memory for completion_addr\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto request_cleanup;
 	}
 
 	result = (union cpt_res_s *)info->completion_addr;
diff --git a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c
index 4addc238a6ef..deaefd532aaa 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c
@@ -6,7 +6,6 @@
 #include "nitrox_dev.h"
 #include "nitrox_req.h"
 #include "nitrox_csr.h"
-#include "nitrox_req.h"
 
 /* SLC_STORE_INFO */
 #define MIN_UDD_LEN 16
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-galois.c b/drivers/crypto/ccp/ccp-crypto-aes-galois.c
index ff02b713c6f6..ca1f0d780b61 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-galois.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-galois.c
@@ -21,7 +21,6 @@
 #include <crypto/ctr.h>
 #include <crypto/gcm.h>
 #include <crypto/scatterwalk.h>
-#include <linux/delay.h>
 
 #include "ccp-crypto.h"
 
diff --git a/drivers/crypto/chelsio/Kconfig b/drivers/crypto/chelsio/Kconfig
index 3e104f5aa0c2..5ae9f8706f17 100644
--- a/drivers/crypto/chelsio/Kconfig
+++ b/drivers/crypto/chelsio/Kconfig
@@ -5,6 +5,7 @@ config CRYPTO_DEV_CHELSIO
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
 	select CRYPTO_AUTHENC
+	select CRYPTO_GF128MUL
 	---help---
 	  The Chelsio Crypto Co-processor driver for T6 adapters.
 
@@ -18,3 +19,13 @@ config CRYPTO_DEV_CHELSIO
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called chcr.
+
+config CHELSIO_IPSEC_INLINE
+        bool "Chelsio IPSec XFRM Tx crypto offload"
+        depends on CHELSIO_T4
+	depends on CRYPTO_DEV_CHELSIO
+        depends on XFRM_OFFLOAD
+        depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD
+        default n
+        ---help---
+          Enable support for IPSec Tx Inline.
diff --git a/drivers/crypto/chelsio/Makefile b/drivers/crypto/chelsio/Makefile
index bebdf06687ad..eaecaf1ebcf3 100644
--- a/drivers/crypto/chelsio/Makefile
+++ b/drivers/crypto/chelsio/Makefile
@@ -2,3 +2,4 @@ ccflags-y := -Idrivers/net/ethernet/chelsio/cxgb4
 
 obj-$(CONFIG_CRYPTO_DEV_CHELSIO) += chcr.o
 chcr-objs :=  chcr_core.o chcr_algo.o
+chcr-$(CONFIG_CHELSIO_IPSEC_INLINE) += chcr_ipsec.o
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 4eed7171e2ae..34a02d690548 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -73,6 +73,29 @@
 
 #define IV AES_BLOCK_SIZE
 
+static unsigned int sgl_ent_len[] = {
+	0, 0, 16, 24, 40, 48, 64, 72, 88,
+	96, 112, 120, 136, 144, 160, 168, 184,
+	192, 208, 216, 232, 240, 256, 264, 280,
+	288, 304, 312, 328, 336, 352, 360, 376
+};
+
+static unsigned int dsgl_ent_len[] = {
+	0, 32, 32, 48, 48, 64, 64, 80, 80,
+	112, 112, 128, 128, 144, 144, 160, 160,
+	192, 192, 208, 208, 224, 224, 240, 240,
+	272, 272, 288, 288, 304, 304, 320, 320
+};
+
+static u32 round_constant[11] = {
+	0x01000000, 0x02000000, 0x04000000, 0x08000000,
+	0x10000000, 0x20000000, 0x40000000, 0x80000000,
+	0x1B000000, 0x36000000, 0x6C000000
+};
+
+static int chcr_handle_cipher_resp(struct ablkcipher_request *req,
+				   unsigned char *input, int err);
+
 static inline  struct chcr_aead_ctx *AEAD_CTX(struct chcr_context *ctx)
 {
 	return ctx->crypto_ctx->aeadctx;
@@ -108,18 +131,6 @@ static inline int is_ofld_imm(const struct sk_buff *skb)
 	return (skb->len <= SGE_MAX_WR_LEN);
 }
 
-/*
- *	sgl_len - calculates the size of an SGL of the given capacity
- *	@n: the number of SGL entries
- *	Calculates the number of flits needed for a scatter/gather list that
- *	can hold the given number of entries.
- */
-static inline unsigned int sgl_len(unsigned int n)
-{
-	n--;
-	return (3 * n) / 2 + (n & 1) + 2;
-}
-
 static int sg_nents_xlen(struct scatterlist *sg, unsigned int reqlen,
 			 unsigned int entlen,
 			 unsigned int skip)
@@ -160,7 +171,6 @@ static inline void chcr_handle_ahash_resp(struct ahash_request *req,
 
 	if (input == NULL)
 		goto out;
-	reqctx = ahash_request_ctx(req);
 	digestsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req));
 	if (reqctx->is_sg_map)
 		chcr_hash_dma_unmap(&u_ctx->lldi.pdev->dev, req);
@@ -183,30 +193,17 @@ static inline void chcr_handle_ahash_resp(struct ahash_request *req,
 	}
 out:
 	req->base.complete(&req->base, err);
+}
 
-	}
-
-static inline void chcr_handle_aead_resp(struct aead_request *req,
-					 unsigned char *input,
-					 int err)
+static inline int get_aead_subtype(struct crypto_aead *aead)
 {
-	struct chcr_aead_reqctx *reqctx = aead_request_ctx(req);
-	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct uld_ctx *u_ctx = ULD_CTX(a_ctx(tfm));
-
-
-	chcr_aead_dma_unmap(&u_ctx->lldi.pdev->dev, req, reqctx->op);
-	if (reqctx->b0_dma)
-		dma_unmap_single(&u_ctx->lldi.pdev->dev, reqctx->b0_dma,
-				 reqctx->b0_len, DMA_BIDIRECTIONAL);
-	if (reqctx->verify == VERIFY_SW) {
-		chcr_verify_tag(req, input, &err);
-		reqctx->verify = VERIFY_HW;
+	struct aead_alg *alg = crypto_aead_alg(aead);
+	struct chcr_alg_template *chcr_crypto_alg =
+		container_of(alg, struct chcr_alg_template, alg.aead);
+	return chcr_crypto_alg->type & CRYPTO_ALG_SUB_TYPE_MASK;
 }
-	req->base.complete(&req->base, err);
 
-}
-static void chcr_verify_tag(struct aead_request *req, u8 *input, int *err)
+void chcr_verify_tag(struct aead_request *req, u8 *input, int *err)
 {
 	u8 temp[SHA512_DIGEST_SIZE];
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
@@ -231,6 +228,25 @@ static void chcr_verify_tag(struct aead_request *req, u8 *input, int *err)
 		*err = 0;
 }
 
+static inline void chcr_handle_aead_resp(struct aead_request *req,
+					 unsigned char *input,
+					 int err)
+{
+	struct chcr_aead_reqctx *reqctx = aead_request_ctx(req);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct uld_ctx *u_ctx = ULD_CTX(a_ctx(tfm));
+
+	chcr_aead_dma_unmap(&u_ctx->lldi.pdev->dev, req, reqctx->op);
+	if (reqctx->b0_dma)
+		dma_unmap_single(&u_ctx->lldi.pdev->dev, reqctx->b0_dma,
+				 reqctx->b0_len, DMA_BIDIRECTIONAL);
+	if (reqctx->verify == VERIFY_SW) {
+		chcr_verify_tag(req, input, &err);
+		reqctx->verify = VERIFY_HW;
+	}
+	req->base.complete(&req->base, err);
+}
+
 /*
  *	chcr_handle_resp - Unmap the DMA buffers associated with the request
  *	@req: crypto request
@@ -558,7 +574,8 @@ static void  ulptx_walk_add_sg(struct ulptx_walk *walk,
 			skip = 0;
 		}
 	}
-	if (walk->nents == 0) {
+	WARN(!sg, "SG should not be null here\n");
+	if (sg && (walk->nents == 0)) {
 		small = min_t(unsigned int, sg_dma_len(sg) - skip_len, len);
 		sgmin = min_t(unsigned int, small, CHCR_SRC_SG_SIZE);
 		walk->sgl->len0 = cpu_to_be32(sgmin);
@@ -595,14 +612,6 @@ static void  ulptx_walk_add_sg(struct ulptx_walk *walk,
 	}
 }
 
-static inline int get_aead_subtype(struct crypto_aead *aead)
-{
-	struct aead_alg *alg = crypto_aead_alg(aead);
-	struct chcr_alg_template *chcr_crypto_alg =
-		container_of(alg, struct chcr_alg_template, alg.aead);
-	return chcr_crypto_alg->type & CRYPTO_ALG_SUB_TYPE_MASK;
-}
-
 static inline int get_cryptoalg_subtype(struct crypto_tfm *tfm)
 {
 	struct crypto_alg *alg = tfm->__crt_alg;
@@ -675,7 +684,7 @@ static int chcr_sg_ent_in_wr(struct scatterlist *src,
 			if (srclen <= dstlen)
 				break;
 			less = min_t(unsigned int, sg_dma_len(dst) - offset -
-				dstskip, CHCR_DST_SG_SIZE);
+				     dstskip, CHCR_DST_SG_SIZE);
 			dstlen += less;
 			offset += less;
 			if (offset == sg_dma_len(dst)) {
@@ -686,7 +695,7 @@ static int chcr_sg_ent_in_wr(struct scatterlist *src,
 			dstskip = 0;
 		}
 		src = sg_next(src);
-		 srcskip = 0;
+		srcskip = 0;
 	}
 	return min(srclen, dstlen);
 }
@@ -1008,7 +1017,8 @@ static unsigned int adjust_ctr_overflow(u8 *iv, u32 bytes)
 	return bytes;
 }
 
-static int chcr_update_tweak(struct ablkcipher_request *req, u8 *iv)
+static int chcr_update_tweak(struct ablkcipher_request *req, u8 *iv,
+			     u32 isfinal)
 {
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct ablk_ctx *ablkctx = ABLK_CTX(c_ctx(tfm));
@@ -1035,7 +1045,8 @@ static int chcr_update_tweak(struct ablkcipher_request *req, u8 *iv)
 	for (i = 0; i < (round % 8); i++)
 		gf128mul_x_ble((le128 *)iv, (le128 *)iv);
 
-	crypto_cipher_decrypt_one(cipher, iv, iv);
+	if (!isfinal)
+		crypto_cipher_decrypt_one(cipher, iv, iv);
 out:
 	return ret;
 }
@@ -1056,7 +1067,7 @@ static int chcr_update_cipher_iv(struct ablkcipher_request *req,
 			CTR_RFC3686_IV_SIZE) = cpu_to_be32((reqctx->processed /
 						AES_BLOCK_SIZE) + 1);
 	else if (subtype == CRYPTO_ALG_SUB_TYPE_XTS)
-		ret = chcr_update_tweak(req, iv);
+		ret = chcr_update_tweak(req, iv, 0);
 	else if (subtype == CRYPTO_ALG_SUB_TYPE_CBC) {
 		if (reqctx->op)
 			sg_pcopy_to_buffer(req->src, sg_nents(req->src), iv,
@@ -1087,7 +1098,7 @@ static int chcr_final_cipher_iv(struct ablkcipher_request *req,
 		ctr_add_iv(iv, req->info, (reqctx->processed /
 			   AES_BLOCK_SIZE));
 	else if (subtype == CRYPTO_ALG_SUB_TYPE_XTS)
-		ret = chcr_update_tweak(req, iv);
+		ret = chcr_update_tweak(req, iv, 1);
 	else if (subtype == CRYPTO_ALG_SUB_TYPE_CBC) {
 		if (reqctx->op)
 			sg_pcopy_to_buffer(req->src, sg_nents(req->src), iv,
@@ -1101,7 +1112,6 @@ static int chcr_final_cipher_iv(struct ablkcipher_request *req,
 
 }
 
-
 static int chcr_handle_cipher_resp(struct ablkcipher_request *req,
 				   unsigned char *input, int err)
 {
@@ -1135,10 +1145,10 @@ static int chcr_handle_cipher_resp(struct ablkcipher_request *req,
 		bytes = chcr_sg_ent_in_wr(reqctx->srcsg, reqctx->dstsg, 1,
 					  SPACE_LEFT(ablkctx->enckey_len),
 					  reqctx->src_ofst, reqctx->dst_ofst);
-	if ((bytes + reqctx->processed) >= req->nbytes)
-		bytes  = req->nbytes - reqctx->processed;
-	else
-		bytes = ROUND_16(bytes);
+		if ((bytes + reqctx->processed) >= req->nbytes)
+			bytes  = req->nbytes - reqctx->processed;
+		else
+			bytes = ROUND_16(bytes);
 	} else {
 		/*CTR mode counter overfloa*/
 		bytes  = req->nbytes - reqctx->processed;
@@ -1239,15 +1249,15 @@ static int process_cipher(struct ablkcipher_request *req,
 					  MIN_CIPHER_SG,
 					  SPACE_LEFT(ablkctx->enckey_len),
 					  0, 0);
-	if ((bytes + reqctx->processed) >= req->nbytes)
-		bytes  = req->nbytes - reqctx->processed;
-	else
-		bytes = ROUND_16(bytes);
+		if ((bytes + reqctx->processed) >= req->nbytes)
+			bytes  = req->nbytes - reqctx->processed;
+		else
+			bytes = ROUND_16(bytes);
 	} else {
 		bytes = req->nbytes;
 	}
 	if (get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) ==
-				  CRYPTO_ALG_SUB_TYPE_CTR) {
+	    CRYPTO_ALG_SUB_TYPE_CTR) {
 		bytes = adjust_ctr_overflow(req->info, bytes);
 	}
 	if (get_cryptoalg_subtype(crypto_ablkcipher_tfm(tfm)) ==
@@ -2014,11 +2024,8 @@ static int chcr_aead_common_init(struct aead_request *req,
 	struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm));
 	struct chcr_aead_reqctx  *reqctx = aead_request_ctx(req);
 	int error = -EINVAL;
-	unsigned int dst_size;
 	unsigned int authsize = crypto_aead_authsize(tfm);
 
-	dst_size = req->assoclen + req->cryptlen + (op_type ?
-					-authsize : authsize);
 	/* validate key size */
 	if (aeadctx->enckey_len == 0)
 		goto err;
@@ -2083,7 +2090,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 	struct cpl_rx_phys_dsgl *phys_cpl;
 	struct ulptx_sgl *ulptx;
 	unsigned int transhdr_len;
-	unsigned int dst_size = 0, temp;
+	unsigned int dst_size = 0, temp, subtype = get_aead_subtype(tfm);
 	unsigned int   kctx_len = 0, dnents;
 	unsigned int  assoclen = req->assoclen;
 	unsigned int  authsize = crypto_aead_authsize(tfm);
@@ -2097,24 +2104,19 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 		return NULL;
 
 	reqctx->b0_dma = 0;
-	if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_NULL) {
+	if (subtype == CRYPTO_ALG_SUB_TYPE_CBC_NULL ||
+	subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) {
 		null = 1;
 		assoclen = 0;
 	}
-	dst_size = assoclen + req->cryptlen + (op_type ? -authsize :
-						    authsize);
 	error = chcr_aead_common_init(req, op_type);
 	if (error)
 		return ERR_PTR(error);
-	if (dst_size) {
-		dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0);
-		dnents += sg_nents_xlen(req->dst, req->cryptlen +
-			(op_type ? -authsize : authsize), CHCR_DST_SG_SIZE,
-			req->assoclen);
-		dnents += MIN_AUTH_SG; // For IV
-	} else {
-		dnents = 0;
-	}
+	dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0);
+	dnents += sg_nents_xlen(req->dst, req->cryptlen +
+		(op_type ? -authsize : authsize), CHCR_DST_SG_SIZE,
+		req->assoclen);
+	dnents += MIN_AUTH_SG; // For IV
 
 	dst_size = get_space_for_phys_dsgl(dnents);
 	kctx_len = (ntohl(KEY_CONTEXT_CTX_LEN_V(aeadctx->key_ctx_hdr)) << 4)
@@ -2162,16 +2164,23 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 					temp & 0xF,
 					null ? 0 : assoclen + IV + 1,
 					temp, temp);
+	if (subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL ||
+	    subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA)
+		temp = CHCR_SCMD_CIPHER_MODE_AES_CTR;
+	else
+		temp = CHCR_SCMD_CIPHER_MODE_AES_CBC;
 	chcr_req->sec_cpl.seqno_numivs = FILL_SEC_CPL_SCMD0_SEQNO(op_type,
 					(op_type == CHCR_ENCRYPT_OP) ? 1 : 0,
-					CHCR_SCMD_CIPHER_MODE_AES_CBC,
+					temp,
 					actx->auth_mode, aeadctx->hmac_ctrl,
 					IV >> 1);
 	chcr_req->sec_cpl.ivgen_hdrlen =  FILL_SEC_CPL_IVGEN_HDRLEN(0, 0, 1,
 					 0, 0, dst_size);
 
 	chcr_req->key_ctx.ctx_hdr = aeadctx->key_ctx_hdr;
-	if (op_type == CHCR_ENCRYPT_OP)
+	if (op_type == CHCR_ENCRYPT_OP ||
+		subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA ||
+		subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL)
 		memcpy(chcr_req->key_ctx.key, aeadctx->key,
 		       aeadctx->enckey_len);
 	else
@@ -2181,7 +2190,16 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 	memcpy(chcr_req->key_ctx.key + (DIV_ROUND_UP(aeadctx->enckey_len, 16) <<
 					4), actx->h_iopad, kctx_len -
 				(DIV_ROUND_UP(aeadctx->enckey_len, 16) << 4));
-	memcpy(reqctx->iv, req->iv, IV);
+	if (subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA ||
+	    subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) {
+		memcpy(reqctx->iv, aeadctx->nonce, CTR_RFC3686_NONCE_SIZE);
+		memcpy(reqctx->iv + CTR_RFC3686_NONCE_SIZE, req->iv,
+				CTR_RFC3686_IV_SIZE);
+		*(__be32 *)(reqctx->iv + CTR_RFC3686_NONCE_SIZE +
+			CTR_RFC3686_IV_SIZE) = cpu_to_be32(1);
+	} else {
+		memcpy(reqctx->iv, req->iv, IV);
+	}
 	phys_cpl = (struct cpl_rx_phys_dsgl *)((u8 *)(chcr_req + 1) + kctx_len);
 	ulptx = (struct ulptx_sgl *)((u8 *)(phys_cpl + 1) + dst_size);
 	chcr_add_aead_dst_ent(req, phys_cpl, assoclen, op_type, qid);
@@ -2202,9 +2220,9 @@ err:
 	return ERR_PTR(error);
 }
 
-static int chcr_aead_dma_map(struct device *dev,
-			     struct aead_request *req,
-			     unsigned short op_type)
+int chcr_aead_dma_map(struct device *dev,
+		      struct aead_request *req,
+		      unsigned short op_type)
 {
 	int error;
 	struct chcr_aead_reqctx  *reqctx = aead_request_ctx(req);
@@ -2246,9 +2264,9 @@ err:
 	return -ENOMEM;
 }
 
-static void chcr_aead_dma_unmap(struct device *dev,
-			     struct aead_request *req,
-			     unsigned short op_type)
+void chcr_aead_dma_unmap(struct device *dev,
+			 struct aead_request *req,
+			 unsigned short op_type)
 {
 	struct chcr_aead_reqctx  *reqctx = aead_request_ctx(req);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
@@ -2273,10 +2291,10 @@ static void chcr_aead_dma_unmap(struct device *dev,
 	}
 }
 
-static inline void chcr_add_aead_src_ent(struct aead_request *req,
-			       struct ulptx_sgl *ulptx,
-			       unsigned int assoclen,
-			       unsigned short op_type)
+void chcr_add_aead_src_ent(struct aead_request *req,
+			   struct ulptx_sgl *ulptx,
+			   unsigned int assoclen,
+			   unsigned short op_type)
 {
 	struct ulptx_walk ulp_walk;
 	struct chcr_aead_reqctx  *reqctx = aead_request_ctx(req);
@@ -2308,11 +2326,11 @@ static inline void chcr_add_aead_src_ent(struct aead_request *req,
 	}
 }
 
-static inline void chcr_add_aead_dst_ent(struct aead_request *req,
-			       struct cpl_rx_phys_dsgl *phys_cpl,
-			       unsigned int assoclen,
-			       unsigned short op_type,
-			       unsigned short qid)
+void chcr_add_aead_dst_ent(struct aead_request *req,
+			   struct cpl_rx_phys_dsgl *phys_cpl,
+			   unsigned int assoclen,
+			   unsigned short op_type,
+			   unsigned short qid)
 {
 	struct chcr_aead_reqctx  *reqctx = aead_request_ctx(req);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
@@ -2330,9 +2348,9 @@ static inline void chcr_add_aead_dst_ent(struct aead_request *req,
 	dsgl_walk_end(&dsgl_walk, qid);
 }
 
-static inline void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
-					   struct ulptx_sgl *ulptx,
-					   struct  cipher_wr_param *wrparam)
+void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
+			     struct ulptx_sgl *ulptx,
+			     struct  cipher_wr_param *wrparam)
 {
 	struct ulptx_walk ulp_walk;
 	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
@@ -2355,10 +2373,10 @@ static inline void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
 	}
 }
 
-static inline void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
-					   struct cpl_rx_phys_dsgl *phys_cpl,
-					   struct  cipher_wr_param *wrparam,
-					   unsigned short qid)
+void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
+			     struct cpl_rx_phys_dsgl *phys_cpl,
+			     struct  cipher_wr_param *wrparam,
+			     unsigned short qid)
 {
 	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
 	struct dsgl_walk dsgl_walk;
@@ -2373,9 +2391,9 @@ static inline void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
 	dsgl_walk_end(&dsgl_walk, qid);
 }
 
-static inline void chcr_add_hash_src_ent(struct ahash_request *req,
-					   struct ulptx_sgl *ulptx,
-					   struct hash_wr_param *param)
+void chcr_add_hash_src_ent(struct ahash_request *req,
+			   struct ulptx_sgl *ulptx,
+			   struct hash_wr_param *param)
 {
 	struct ulptx_walk ulp_walk;
 	struct chcr_ahash_req_ctx *reqctx = ahash_request_ctx(req);
@@ -2395,16 +2413,13 @@ static inline void chcr_add_hash_src_ent(struct ahash_request *req,
 			ulptx_walk_add_page(&ulp_walk, param->bfr_len,
 					    &reqctx->dma_addr);
 		ulptx_walk_add_sg(&ulp_walk, req->src, param->sg_len,
-					  0);
-//	       reqctx->srcsg = ulp_walk.last_sg;
-//	       reqctx->src_ofst = ulp_walk.last_sg_len;
-			ulptx_walk_end(&ulp_walk);
+				  0);
+		ulptx_walk_end(&ulp_walk);
 	}
 }
 
-
-static inline int chcr_hash_dma_map(struct device *dev,
-			     struct ahash_request *req)
+int chcr_hash_dma_map(struct device *dev,
+		      struct ahash_request *req)
 {
 	struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(req);
 	int error = 0;
@@ -2414,13 +2429,13 @@ static inline int chcr_hash_dma_map(struct device *dev,
 	error = dma_map_sg(dev, req->src, sg_nents(req->src),
 			   DMA_TO_DEVICE);
 	if (!error)
-		return error;
+		return -ENOMEM;
 	req_ctx->is_sg_map = 1;
 	return 0;
 }
 
-static inline void chcr_hash_dma_unmap(struct device *dev,
-			     struct ahash_request *req)
+void chcr_hash_dma_unmap(struct device *dev,
+			 struct ahash_request *req)
 {
 	struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(req);
 
@@ -2433,9 +2448,8 @@ static inline void chcr_hash_dma_unmap(struct device *dev,
 
 }
 
-
-static int chcr_cipher_dma_map(struct device *dev,
-			     struct ablkcipher_request *req)
+int chcr_cipher_dma_map(struct device *dev,
+			struct ablkcipher_request *req)
 {
 	int error;
 	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
@@ -2469,8 +2483,9 @@ err:
 	dma_unmap_single(dev, reqctx->iv_dma, IV, DMA_BIDIRECTIONAL);
 	return -ENOMEM;
 }
-static void chcr_cipher_dma_unmap(struct device *dev,
-				  struct ablkcipher_request *req)
+
+void chcr_cipher_dma_unmap(struct device *dev,
+			   struct ablkcipher_request *req)
 {
 	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
 
@@ -2666,8 +2681,6 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 	sub_type = get_aead_subtype(tfm);
 	if (sub_type == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309)
 		assoclen -= 8;
-	dst_size = assoclen + req->cryptlen + (op_type ? -authsize :
-						   authsize);
 	error = chcr_aead_common_init(req, op_type);
 	if (error)
 		return ERR_PTR(error);
@@ -2677,15 +2690,11 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 	error = aead_ccm_validate_input(op_type, req, aeadctx, sub_type);
 	if (error)
 		goto err;
-	if (dst_size) {
-		dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0);
-		dnents += sg_nents_xlen(req->dst, req->cryptlen
-				+ (op_type ? -authsize : authsize),
-				CHCR_DST_SG_SIZE, req->assoclen);
-		dnents += MIN_CCM_SG; // For IV and B0
-	} else {
-		dnents = 0;
-	}
+	dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0);
+	dnents += sg_nents_xlen(req->dst, req->cryptlen
+			+ (op_type ? -authsize : authsize),
+			CHCR_DST_SG_SIZE, req->assoclen);
+	dnents += MIN_CCM_SG; // For IV and B0
 	dst_size = get_space_for_phys_dsgl(dnents);
 	kctx_len = ((DIV_ROUND_UP(aeadctx->enckey_len, 16)) << 4) * 2;
 	transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size);
@@ -2780,19 +2789,14 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 		assoclen = req->assoclen - 8;
 
 	reqctx->b0_dma = 0;
-	dst_size = assoclen + req->cryptlen + (op_type ? -authsize :  authsize);
 	error = chcr_aead_common_init(req, op_type);
-		if (error)
-			return	ERR_PTR(error);
-	if (dst_size) {
-		dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0);
-		dnents += sg_nents_xlen(req->dst,
-			req->cryptlen + (op_type ? -authsize : authsize),
+	if (error)
+		return ERR_PTR(error);
+	dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0);
+	dnents += sg_nents_xlen(req->dst, req->cryptlen +
+				(op_type ? -authsize : authsize),
 				CHCR_DST_SG_SIZE, req->assoclen);
-		dnents += MIN_GCM_SG; // For IV
-	} else {
-		dnents = 0;
-	}
+	dnents += MIN_GCM_SG; // For IV
 	dst_size = get_space_for_phys_dsgl(dnents);
 	kctx_len = ((DIV_ROUND_UP(aeadctx->enckey_len, 16)) << 4) +
 		AEAD_H_SIZE;
@@ -2829,10 +2833,10 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	chcr_req->sec_cpl.aadstart_cipherstop_hi = FILL_SEC_CPL_CIPHERSTOP_HI(
 					assoclen ? 1 : 0, assoclen,
 					assoclen + IV + 1, 0);
-		chcr_req->sec_cpl.cipherstop_lo_authinsert =
+	chcr_req->sec_cpl.cipherstop_lo_authinsert =
 			FILL_SEC_CPL_AUTHINSERT(0, assoclen + IV + 1,
 						temp, temp);
-		chcr_req->sec_cpl.seqno_numivs =
+	chcr_req->sec_cpl.seqno_numivs =
 			FILL_SEC_CPL_SCMD0_SEQNO(op_type, (op_type ==
 					CHCR_ENCRYPT_OP) ? 1 : 0,
 					CHCR_SCMD_CIPHER_MODE_AES_GCM,
@@ -3212,7 +3216,7 @@ static int chcr_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 	struct chcr_authenc_ctx *actx = AUTHENC_CTX(aeadctx);
 	/* it contains auth and cipher key both*/
 	struct crypto_authenc_keys keys;
-	unsigned int bs;
+	unsigned int bs, subtype;
 	unsigned int max_authsize = crypto_aead_alg(authenc)->maxauthsize;
 	int err = 0, i, key_ctx_len = 0;
 	unsigned char ck_size = 0;
@@ -3241,6 +3245,15 @@ static int chcr_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 		pr_err("chcr : Unsupported digest size\n");
 		goto out;
 	}
+	subtype = get_aead_subtype(authenc);
+	if (subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA ||
+		subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) {
+		if (keys.enckeylen < CTR_RFC3686_NONCE_SIZE)
+			goto out;
+		memcpy(aeadctx->nonce, keys.enckey + (keys.enckeylen
+		- CTR_RFC3686_NONCE_SIZE), CTR_RFC3686_NONCE_SIZE);
+		keys.enckeylen -= CTR_RFC3686_NONCE_SIZE;
+	}
 	if (keys.enckeylen == AES_KEYSIZE_128) {
 		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128;
 	} else if (keys.enckeylen == AES_KEYSIZE_192) {
@@ -3258,9 +3271,12 @@ static int chcr_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 	 */
 	memcpy(aeadctx->key, keys.enckey, keys.enckeylen);
 	aeadctx->enckey_len = keys.enckeylen;
-	get_aes_decrypt_key(actx->dec_rrkey, aeadctx->key,
-			    aeadctx->enckey_len << 3);
+	if (subtype == CRYPTO_ALG_SUB_TYPE_CBC_SHA ||
+		subtype == CRYPTO_ALG_SUB_TYPE_CBC_NULL) {
 
+		get_aes_decrypt_key(actx->dec_rrkey, aeadctx->key,
+			    aeadctx->enckey_len << 3);
+	}
 	base_hash  = chcr_alloc_shash(max_authsize);
 	if (IS_ERR(base_hash)) {
 		pr_err("chcr : Base driver cannot be loaded\n");
@@ -3333,6 +3349,7 @@ static int chcr_aead_digest_null_setkey(struct crypto_aead *authenc,
 	struct crypto_authenc_keys keys;
 	int err;
 	/* it contains auth and cipher key both*/
+	unsigned int subtype;
 	int key_ctx_len = 0;
 	unsigned char ck_size = 0;
 
@@ -3350,6 +3367,15 @@ static int chcr_aead_digest_null_setkey(struct crypto_aead *authenc,
 		crypto_aead_set_flags(authenc, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		goto out;
 	}
+	subtype = get_aead_subtype(authenc);
+	if (subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA ||
+	    subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) {
+		if (keys.enckeylen < CTR_RFC3686_NONCE_SIZE)
+			goto out;
+		memcpy(aeadctx->nonce, keys.enckey + (keys.enckeylen
+			- CTR_RFC3686_NONCE_SIZE), CTR_RFC3686_NONCE_SIZE);
+		keys.enckeylen -= CTR_RFC3686_NONCE_SIZE;
+	}
 	if (keys.enckeylen == AES_KEYSIZE_128) {
 		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128;
 	} else if (keys.enckeylen == AES_KEYSIZE_192) {
@@ -3357,13 +3383,16 @@ static int chcr_aead_digest_null_setkey(struct crypto_aead *authenc,
 	} else if (keys.enckeylen == AES_KEYSIZE_256) {
 		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256;
 	} else {
-		pr_err("chcr : Unsupported cipher key\n");
+		pr_err("chcr : Unsupported cipher key %d\n", keys.enckeylen);
 		goto out;
 	}
 	memcpy(aeadctx->key, keys.enckey, keys.enckeylen);
 	aeadctx->enckey_len = keys.enckeylen;
-	get_aes_decrypt_key(actx->dec_rrkey, aeadctx->key,
-				    aeadctx->enckey_len << 3);
+	if (subtype == CRYPTO_ALG_SUB_TYPE_CBC_SHA ||
+	    subtype == CRYPTO_ALG_SUB_TYPE_CBC_NULL) {
+		get_aes_decrypt_key(actx->dec_rrkey, aeadctx->key,
+				aeadctx->enckey_len << 3);
+	}
 	key_ctx_len =  sizeof(struct _key_ctx)
 		+ ((DIV_ROUND_UP(keys.enckeylen, 16)) << 4);
 
@@ -3375,6 +3404,40 @@ out:
 	aeadctx->enckey_len = 0;
 	return -EINVAL;
 }
+
+static int chcr_aead_op(struct aead_request *req,
+			unsigned short op_type,
+			int size,
+			create_wr_t create_wr_fn)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct uld_ctx *u_ctx;
+	struct sk_buff *skb;
+
+	if (!a_ctx(tfm)->dev) {
+		pr_err("chcr : %s : No crypto device.\n", __func__);
+		return -ENXIO;
+	}
+	u_ctx = ULD_CTX(a_ctx(tfm));
+	if (cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
+				   a_ctx(tfm)->tx_qidx)) {
+		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
+			return -EBUSY;
+	}
+
+	/* Form a WR from req */
+	skb = create_wr_fn(req, u_ctx->lldi.rxq_ids[a_ctx(tfm)->rx_qidx], size,
+			   op_type);
+
+	if (IS_ERR(skb) || !skb)
+		return PTR_ERR(skb);
+
+	skb->dev = u_ctx->lldi.ports[0];
+	set_wr_txq(skb, CPL_PRIORITY_DATA, a_ctx(tfm)->tx_qidx);
+	chcr_send_wr(skb);
+	return -EINPROGRESS;
+}
+
 static int chcr_aead_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
@@ -3383,8 +3446,10 @@ static int chcr_aead_encrypt(struct aead_request *req)
 	reqctx->verify = VERIFY_HW;
 
 	switch (get_aead_subtype(tfm)) {
-	case CRYPTO_ALG_SUB_TYPE_AEAD_AUTHENC:
-	case CRYPTO_ALG_SUB_TYPE_AEAD_NULL:
+	case CRYPTO_ALG_SUB_TYPE_CTR_SHA:
+	case CRYPTO_ALG_SUB_TYPE_CBC_SHA:
+	case CRYPTO_ALG_SUB_TYPE_CBC_NULL:
+	case CRYPTO_ALG_SUB_TYPE_CTR_NULL:
 		return chcr_aead_op(req, CHCR_ENCRYPT_OP, 0,
 				    create_authenc_wr);
 	case CRYPTO_ALG_SUB_TYPE_AEAD_CCM:
@@ -3413,8 +3478,10 @@ static int chcr_aead_decrypt(struct aead_request *req)
 	}
 
 	switch (get_aead_subtype(tfm)) {
-	case CRYPTO_ALG_SUB_TYPE_AEAD_AUTHENC:
-	case CRYPTO_ALG_SUB_TYPE_AEAD_NULL:
+	case CRYPTO_ALG_SUB_TYPE_CBC_SHA:
+	case CRYPTO_ALG_SUB_TYPE_CTR_SHA:
+	case CRYPTO_ALG_SUB_TYPE_CBC_NULL:
+	case CRYPTO_ALG_SUB_TYPE_CTR_NULL:
 		return chcr_aead_op(req, CHCR_DECRYPT_OP, size,
 				    create_authenc_wr);
 	case CRYPTO_ALG_SUB_TYPE_AEAD_CCM:
@@ -3427,38 +3494,6 @@ static int chcr_aead_decrypt(struct aead_request *req)
 	}
 }
 
-static int chcr_aead_op(struct aead_request *req,
-			  unsigned short op_type,
-			  int size,
-			  create_wr_t create_wr_fn)
-{
-	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct uld_ctx *u_ctx;
-	struct sk_buff *skb;
-
-	if (!a_ctx(tfm)->dev) {
-		pr_err("chcr : %s : No crypto device.\n", __func__);
-		return -ENXIO;
-	}
-	u_ctx = ULD_CTX(a_ctx(tfm));
-	if (cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
-				   a_ctx(tfm)->tx_qidx)) {
-		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
-			return -EBUSY;
-	}
-
-	/* Form a WR from req */
-	skb = create_wr_fn(req, u_ctx->lldi.rxq_ids[a_ctx(tfm)->rx_qidx], size,
-			   op_type);
-
-	if (IS_ERR(skb) || !skb)
-		return PTR_ERR(skb);
-
-	skb->dev = u_ctx->lldi.ports[0];
-	set_wr_txq(skb, CPL_PRIORITY_DATA, a_ctx(tfm)->tx_qidx);
-	chcr_send_wr(skb);
-	return -EINPROGRESS;
-}
 static struct chcr_alg_template driver_algs[] = {
 	/* AES-CBC */
 	{
@@ -3742,7 +3777,7 @@ static struct chcr_alg_template driver_algs[] = {
 		}
 	},
 	{
-		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_AEAD_AUTHENC,
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_SHA,
 		.is_registered = 0,
 		.alg.aead = {
 			.base = {
@@ -3763,7 +3798,7 @@ static struct chcr_alg_template driver_algs[] = {
 		}
 	},
 	{
-		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_AEAD_AUTHENC,
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_SHA,
 		.is_registered = 0,
 		.alg.aead = {
 			.base = {
@@ -3785,7 +3820,7 @@ static struct chcr_alg_template driver_algs[] = {
 		}
 	},
 	{
-		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_AEAD_AUTHENC,
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_SHA,
 		.is_registered = 0,
 		.alg.aead = {
 			.base = {
@@ -3805,7 +3840,7 @@ static struct chcr_alg_template driver_algs[] = {
 		}
 	},
 	{
-		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_AEAD_AUTHENC,
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_SHA,
 		.is_registered = 0,
 		.alg.aead = {
 			.base = {
@@ -3826,7 +3861,7 @@ static struct chcr_alg_template driver_algs[] = {
 		}
 	},
 	{
-		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_AEAD_AUTHENC,
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_SHA,
 		.is_registered = 0,
 		.alg.aead = {
 			.base = {
@@ -3847,7 +3882,7 @@ static struct chcr_alg_template driver_algs[] = {
 		}
 	},
 	{
-		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_AEAD_NULL,
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CBC_NULL,
 		.is_registered = 0,
 		.alg.aead = {
 			.base = {
@@ -3867,6 +3902,133 @@ static struct chcr_alg_template driver_algs[] = {
 			.setauthsize = chcr_authenc_null_setauthsize,
 		}
 	},
+	{
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_SHA,
+		.is_registered = 0,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),rfc3686(ctr(aes)))",
+				.cra_driver_name =
+				"authenc-hmac-sha1-rfc3686-ctr-aes-chcr",
+				.cra_blocksize	 = 1,
+				.cra_priority = CHCR_AEAD_PRIORITY,
+				.cra_ctxsize =	sizeof(struct chcr_context) +
+						sizeof(struct chcr_aead_ctx) +
+						sizeof(struct chcr_authenc_ctx),
+
+			},
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+			.setkey = chcr_authenc_setkey,
+			.setauthsize = chcr_authenc_setauthsize,
+		}
+	},
+	{
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_SHA,
+		.is_registered = 0,
+		.alg.aead = {
+			.base = {
+
+				.cra_name = "authenc(hmac(sha256),rfc3686(ctr(aes)))",
+				.cra_driver_name =
+				"authenc-hmac-sha256-rfc3686-ctr-aes-chcr",
+				.cra_blocksize	 = 1,
+				.cra_priority = CHCR_AEAD_PRIORITY,
+				.cra_ctxsize =	sizeof(struct chcr_context) +
+						sizeof(struct chcr_aead_ctx) +
+						sizeof(struct chcr_authenc_ctx),
+
+			},
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize	= SHA256_DIGEST_SIZE,
+			.setkey = chcr_authenc_setkey,
+			.setauthsize = chcr_authenc_setauthsize,
+		}
+	},
+	{
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_SHA,
+		.is_registered = 0,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),rfc3686(ctr(aes)))",
+				.cra_driver_name =
+				"authenc-hmac-sha224-rfc3686-ctr-aes-chcr",
+				.cra_blocksize	 = 1,
+				.cra_priority = CHCR_AEAD_PRIORITY,
+				.cra_ctxsize =	sizeof(struct chcr_context) +
+						sizeof(struct chcr_aead_ctx) +
+						sizeof(struct chcr_authenc_ctx),
+			},
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+			.setkey = chcr_authenc_setkey,
+			.setauthsize = chcr_authenc_setauthsize,
+		}
+	},
+	{
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_SHA,
+		.is_registered = 0,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha384),rfc3686(ctr(aes)))",
+				.cra_driver_name =
+				"authenc-hmac-sha384-rfc3686-ctr-aes-chcr",
+				.cra_blocksize	 = 1,
+				.cra_priority = CHCR_AEAD_PRIORITY,
+				.cra_ctxsize =	sizeof(struct chcr_context) +
+						sizeof(struct chcr_aead_ctx) +
+						sizeof(struct chcr_authenc_ctx),
+
+			},
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA384_DIGEST_SIZE,
+			.setkey = chcr_authenc_setkey,
+			.setauthsize = chcr_authenc_setauthsize,
+		}
+	},
+	{
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_SHA,
+		.is_registered = 0,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha512),rfc3686(ctr(aes)))",
+				.cra_driver_name =
+				"authenc-hmac-sha512-rfc3686-ctr-aes-chcr",
+				.cra_blocksize	 = 1,
+				.cra_priority = CHCR_AEAD_PRIORITY,
+				.cra_ctxsize =	sizeof(struct chcr_context) +
+						sizeof(struct chcr_aead_ctx) +
+						sizeof(struct chcr_authenc_ctx),
+
+			},
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
+			.setkey = chcr_authenc_setkey,
+			.setauthsize = chcr_authenc_setauthsize,
+		}
+	},
+	{
+		.type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_SUB_TYPE_CTR_NULL,
+		.is_registered = 0,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(digest_null,rfc3686(ctr(aes)))",
+				.cra_driver_name =
+				"authenc-digest_null-rfc3686-ctr-aes-chcr",
+				.cra_blocksize	 = 1,
+				.cra_priority = CHCR_AEAD_PRIORITY,
+				.cra_ctxsize =	sizeof(struct chcr_context) +
+						sizeof(struct chcr_aead_ctx) +
+						sizeof(struct chcr_authenc_ctx),
+
+			},
+			.ivsize  = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = 0,
+			.setkey  = chcr_aead_digest_null_setkey,
+			.setauthsize = chcr_authenc_null_setauthsize,
+		}
+	},
+
 };
 
 /*
diff --git a/drivers/crypto/chelsio/chcr_algo.h b/drivers/crypto/chelsio/chcr_algo.h
index 96c9335ee728..d1673a5d4bf5 100644
--- a/drivers/crypto/chelsio/chcr_algo.h
+++ b/drivers/crypto/chelsio/chcr_algo.h
@@ -226,15 +226,6 @@
 #define SPACE_LEFT(len) \
 	((SGE_MAX_WR_LEN - WR_MIN_LEN - (len)))
 
-unsigned int sgl_ent_len[] = {0, 0, 16, 24, 40, 48, 64, 72, 88,
-				96, 112, 120, 136, 144, 160, 168, 184,
-				192, 208, 216, 232, 240, 256, 264, 280,
-				288, 304, 312, 328, 336, 352, 360, 376};
-unsigned int dsgl_ent_len[] = {0, 32, 32, 48, 48, 64, 64, 80, 80,
-				112, 112, 128, 128, 144, 144, 160, 160,
-				192, 192, 208, 208, 224, 224, 240, 240,
-				272, 272, 288, 288, 304, 304, 320, 320};
-
 struct algo_param {
 	unsigned int auth_mode;
 	unsigned int mk_size;
@@ -404,10 +395,4 @@ static inline u32 aes_ks_subword(const u32 w)
 	return *(u32 *)(&bytes[0]);
 }
 
-static u32 round_constant[11] = {
-	0x01000000, 0x02000000, 0x04000000, 0x08000000,
-	0x10000000, 0x20000000, 0x40000000, 0x80000000,
-	0x1B000000, 0x36000000, 0x6C000000
-};
-
 #endif /* __CHCR_ALGO_H__ */
diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c
index f5a2624081dc..04f277cade7c 100644
--- a/drivers/crypto/chelsio/chcr_core.c
+++ b/drivers/crypto/chelsio/chcr_core.c
@@ -48,6 +48,9 @@ static struct cxgb4_uld_info chcr_uld_info = {
 	.add = chcr_uld_add,
 	.state_change = chcr_uld_state_change,
 	.rx_handler = chcr_uld_rx_handler,
+#ifdef CONFIG_CHELSIO_IPSEC_INLINE
+	.tx_handler = chcr_uld_tx_handler,
+#endif /* CONFIG_CHELSIO_IPSEC_INLINE */
 };
 
 struct uld_ctx *assign_chcr_device(void)
@@ -164,6 +167,10 @@ static void *chcr_uld_add(const struct cxgb4_lld_info *lld)
 		goto out;
 	}
 	u_ctx->lldi = *lld;
+#ifdef CONFIG_CHELSIO_IPSEC_INLINE
+	if (lld->crypto & ULP_CRYPTO_IPSEC_INLINE)
+		chcr_add_xfrmops(lld);
+#endif /* CONFIG_CHELSIO_IPSEC_INLINE */
 out:
 	return u_ctx;
 }
@@ -187,6 +194,13 @@ int chcr_uld_rx_handler(void *handle, const __be64 *rsp,
 	return 0;
 }
 
+#ifdef CONFIG_CHELSIO_IPSEC_INLINE
+int chcr_uld_tx_handler(struct sk_buff *skb, struct net_device *dev)
+{
+	return chcr_ipsec_xmit(skb, dev);
+}
+#endif /* CONFIG_CHELSIO_IPSEC_INLINE */
+
 static int chcr_uld_state_change(void *handle, enum cxgb4_state state)
 {
 	struct uld_ctx *u_ctx = handle;
diff --git a/drivers/crypto/chelsio/chcr_core.h b/drivers/crypto/chelsio/chcr_core.h
index 94e7412f6164..3c29ee09b8b5 100644
--- a/drivers/crypto/chelsio/chcr_core.h
+++ b/drivers/crypto/chelsio/chcr_core.h
@@ -39,6 +39,7 @@
 #include <crypto/algapi.h>
 #include "t4_hw.h"
 #include "cxgb4.h"
+#include "t4_msg.h"
 #include "cxgb4_uld.h"
 
 #define DRV_MODULE_NAME "chcr"
@@ -89,12 +90,49 @@ struct uld_ctx {
 	struct chcr_dev *dev;
 };
 
+struct chcr_ipsec_req {
+	struct ulp_txpkt ulptx;
+	struct ulptx_idata sc_imm;
+	struct cpl_tx_sec_pdu sec_cpl;
+	struct _key_ctx key_ctx;
+};
+
+struct chcr_ipsec_wr {
+	struct fw_ulptx_wr wreq;
+	struct chcr_ipsec_req req;
+};
+
+struct ipsec_sa_entry {
+	int hmac_ctrl;
+	unsigned int enckey_len;
+	unsigned int kctx_len;
+	unsigned int authsize;
+	__be32 key_ctx_hdr;
+	char salt[MAX_SALT];
+	char key[2 * AES_MAX_KEY_SIZE];
+};
+
+/*
+ *      sgl_len - calculates the size of an SGL of the given capacity
+ *      @n: the number of SGL entries
+ *      Calculates the number of flits needed for a scatter/gather list that
+ *      can hold the given number of entries.
+ */
+static inline unsigned int sgl_len(unsigned int n)
+{
+	n--;
+	return (3 * n) / 2 + (n & 1) + 2;
+}
+
 struct uld_ctx *assign_chcr_device(void);
 int chcr_send_wr(struct sk_buff *skb);
 int start_crypto(void);
 int stop_crypto(void);
 int chcr_uld_rx_handler(void *handle, const __be64 *rsp,
 			const struct pkt_gl *pgl);
+int chcr_uld_tx_handler(struct sk_buff *skb, struct net_device *dev);
 int chcr_handle_resp(struct crypto_async_request *req, unsigned char *input,
 		     int err);
+int chcr_ipsec_xmit(struct sk_buff *skb, struct net_device *dev);
+void chcr_add_xfrmops(const struct cxgb4_lld_info *lld);
 #endif /* __CHCR_CORE_H__ */
diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h
index 94a87e3ad9bc..7daf0a17a7d2 100644
--- a/drivers/crypto/chelsio/chcr_crypto.h
+++ b/drivers/crypto/chelsio/chcr_crypto.h
@@ -134,14 +134,16 @@
 #define CRYPTO_ALG_SUB_TYPE_HASH_HMAC       0x01000000
 #define CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106    0x02000000
 #define CRYPTO_ALG_SUB_TYPE_AEAD_GCM	    0x03000000
-#define CRYPTO_ALG_SUB_TYPE_AEAD_AUTHENC    0x04000000
+#define CRYPTO_ALG_SUB_TYPE_CBC_SHA	    0x04000000
 #define CRYPTO_ALG_SUB_TYPE_AEAD_CCM        0x05000000
 #define CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309    0x06000000
-#define CRYPTO_ALG_SUB_TYPE_AEAD_NULL       0x07000000
+#define CRYPTO_ALG_SUB_TYPE_CBC_NULL	    0x07000000
 #define CRYPTO_ALG_SUB_TYPE_CTR             0x08000000
 #define CRYPTO_ALG_SUB_TYPE_CTR_RFC3686     0x09000000
 #define CRYPTO_ALG_SUB_TYPE_XTS		    0x0a000000
 #define CRYPTO_ALG_SUB_TYPE_CBC		    0x0b000000
+#define CRYPTO_ALG_SUB_TYPE_CTR_SHA	    0x0c000000
+#define CRYPTO_ALG_SUB_TYPE_CTR_NULL   0x0d000000
 #define CRYPTO_ALG_TYPE_HMAC (CRYPTO_ALG_TYPE_AHASH |\
 			      CRYPTO_ALG_SUB_TYPE_HASH_HMAC)
 
@@ -210,8 +212,6 @@ struct dsgl_walk {
 	struct phys_sge_pairs *to;
 };
 
-
-
 struct chcr_gcm_ctx {
 	u8 ghash_h[AEAD_H_SIZE];
 };
@@ -227,21 +227,18 @@ struct __aead_ctx {
 	struct chcr_authenc_ctx authenc[0];
 };
 
-
-
 struct chcr_aead_ctx {
 	__be32 key_ctx_hdr;
 	unsigned int enckey_len;
 	struct crypto_aead *sw_cipher;
 	u8 salt[MAX_SALT];
 	u8 key[CHCR_AES_MAX_KEY_LEN];
+	u8 nonce[4];
 	u16 hmac_ctrl;
 	u16 mayverify;
 	struct	__aead_ctx ctx[0];
 };
 
-
-
 struct hmac_ctx {
 	struct crypto_shash *base_hash;
 	u8 ipad[CHCR_HASH_MAX_BLOCK_SIZE_128];
@@ -307,44 +304,29 @@ typedef struct sk_buff *(*create_wr_t)(struct aead_request *req,
 				       int size,
 				       unsigned short op_type);
 
-static int chcr_aead_op(struct aead_request *req_base,
-			  unsigned short op_type,
-			  int size,
-			  create_wr_t create_wr_fn);
-static inline int get_aead_subtype(struct crypto_aead *aead);
-static int chcr_handle_cipher_resp(struct ablkcipher_request *req,
-				   unsigned char *input, int err);
-static void chcr_verify_tag(struct aead_request *req, u8 *input, int *err);
-static int chcr_aead_dma_map(struct device *dev, struct aead_request *req,
-			     unsigned short op_type);
-static void chcr_aead_dma_unmap(struct device *dev, struct aead_request
-				*req, unsigned short op_type);
-static inline void chcr_add_aead_dst_ent(struct aead_request *req,
-				    struct cpl_rx_phys_dsgl *phys_cpl,
-				    unsigned int assoclen,
-				    unsigned short op_type,
-				    unsigned short qid);
-static inline void chcr_add_aead_src_ent(struct aead_request *req,
-				    struct ulptx_sgl *ulptx,
-				    unsigned int assoclen,
-				    unsigned short op_type);
-static inline void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
-					   struct ulptx_sgl *ulptx,
-					   struct  cipher_wr_param *wrparam);
-static int chcr_cipher_dma_map(struct device *dev,
-			       struct ablkcipher_request *req);
-static void chcr_cipher_dma_unmap(struct device *dev,
-				  struct ablkcipher_request *req);
-static inline void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
-					   struct cpl_rx_phys_dsgl *phys_cpl,
-					   struct  cipher_wr_param *wrparam,
-					   unsigned short qid);
+void chcr_verify_tag(struct aead_request *req, u8 *input, int *err);
+int chcr_aead_dma_map(struct device *dev, struct aead_request *req,
+		      unsigned short op_type);
+void chcr_aead_dma_unmap(struct device *dev, struct aead_request *req,
+			 unsigned short op_type);
+void chcr_add_aead_dst_ent(struct aead_request *req,
+			   struct cpl_rx_phys_dsgl *phys_cpl,
+			   unsigned int assoclen, unsigned short op_type,
+			   unsigned short qid);
+void chcr_add_aead_src_ent(struct aead_request *req, struct ulptx_sgl *ulptx,
+			   unsigned int assoclen, unsigned short op_type);
+void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
+			     struct ulptx_sgl *ulptx,
+			     struct  cipher_wr_param *wrparam);
+int chcr_cipher_dma_map(struct device *dev, struct ablkcipher_request *req);
+void chcr_cipher_dma_unmap(struct device *dev, struct ablkcipher_request *req);
+void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
+			     struct cpl_rx_phys_dsgl *phys_cpl,
+			     struct  cipher_wr_param *wrparam,
+			     unsigned short qid);
 int sg_nents_len_skip(struct scatterlist *sg, u64 len, u64 skip);
-static inline void chcr_add_hash_src_ent(struct ahash_request *req,
-					 struct ulptx_sgl *ulptx,
-					 struct hash_wr_param *param);
-static inline int chcr_hash_dma_map(struct device *dev,
-				    struct ahash_request *req);
-static inline void chcr_hash_dma_unmap(struct device *dev,
-				       struct ahash_request *req);
+void chcr_add_hash_src_ent(struct ahash_request *req, struct ulptx_sgl *ulptx,
+			   struct hash_wr_param *param);
+int chcr_hash_dma_map(struct device *dev, struct ahash_request *req);
+void chcr_hash_dma_unmap(struct device *dev, struct ahash_request *req);
 #endif /* __CHCR_CRYPTO_H__ */
diff --git a/drivers/crypto/chelsio/chcr_ipsec.c b/drivers/crypto/chelsio/chcr_ipsec.c
new file mode 100644
index 000000000000..db1e241104ed
--- /dev/null
+++ b/drivers/crypto/chelsio/chcr_ipsec.c
@@ -0,0 +1,654 @@
+/*
+ * This file is part of the Chelsio T6 Crypto driver for Linux.
+ *
+ * Copyright (c) 2003-2017 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * Written and Maintained by:
+ *	Atul Gupta (atul.gupta@chelsio.com)
+ */
+
+#define pr_fmt(fmt) "chcr:" fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/cryptohash.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/highmem.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/netdevice.h>
+#include <net/esp.h>
+#include <net/xfrm.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include <crypto/authenc.h>
+#include <crypto/internal/aead.h>
+#include <crypto/null.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/aead.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/internal/hash.h>
+
+#include "chcr_core.h"
+#include "chcr_algo.h"
+#include "chcr_crypto.h"
+
+/*
+ * Max Tx descriptor space we allow for an Ethernet packet to be inlined
+ * into a WR.
+ */
+#define MAX_IMM_TX_PKT_LEN 256
+#define GCM_ESP_IV_SIZE     8
+
+static int chcr_xfrm_add_state(struct xfrm_state *x);
+static void chcr_xfrm_del_state(struct xfrm_state *x);
+static void chcr_xfrm_free_state(struct xfrm_state *x);
+static bool chcr_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x);
+
+static const struct xfrmdev_ops chcr_xfrmdev_ops = {
+	.xdo_dev_state_add      = chcr_xfrm_add_state,
+	.xdo_dev_state_delete   = chcr_xfrm_del_state,
+	.xdo_dev_state_free     = chcr_xfrm_free_state,
+	.xdo_dev_offload_ok     = chcr_ipsec_offload_ok,
+};
+
+/* Add offload xfrms to Chelsio Interface */
+void chcr_add_xfrmops(const struct cxgb4_lld_info *lld)
+{
+	struct net_device *netdev = NULL;
+	int i;
+
+	for (i = 0; i < lld->nports; i++) {
+		netdev = lld->ports[i];
+		if (!netdev)
+			continue;
+		netdev->xfrmdev_ops = &chcr_xfrmdev_ops;
+		netdev->hw_enc_features |= NETIF_F_HW_ESP;
+		netdev->features |= NETIF_F_HW_ESP;
+		rtnl_lock();
+		netdev_change_features(netdev);
+		rtnl_unlock();
+	}
+}
+
+static inline int chcr_ipsec_setauthsize(struct xfrm_state *x,
+					 struct ipsec_sa_entry *sa_entry)
+{
+	int hmac_ctrl;
+	int authsize = x->aead->alg_icv_len / 8;
+
+	sa_entry->authsize = authsize;
+
+	switch (authsize) {
+	case ICV_8:
+		hmac_ctrl = CHCR_SCMD_HMAC_CTRL_DIV2;
+		break;
+	case ICV_12:
+		hmac_ctrl = CHCR_SCMD_HMAC_CTRL_IPSEC_96BIT;
+		break;
+	case ICV_16:
+		hmac_ctrl = CHCR_SCMD_HMAC_CTRL_NO_TRUNC;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return hmac_ctrl;
+}
+
+static inline int chcr_ipsec_setkey(struct xfrm_state *x,
+				    struct ipsec_sa_entry *sa_entry)
+{
+	struct crypto_cipher *cipher;
+	int keylen = (x->aead->alg_key_len + 7) / 8;
+	unsigned char *key = x->aead->alg_key;
+	int ck_size, key_ctx_size = 0;
+	unsigned char ghash_h[AEAD_H_SIZE];
+	int ret = 0;
+
+	if (keylen > 3) {
+		keylen -= 4;  /* nonce/salt is present in the last 4 bytes */
+		memcpy(sa_entry->salt, key + keylen, 4);
+	}
+
+	if (keylen == AES_KEYSIZE_128) {
+		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128;
+	} else if (keylen == AES_KEYSIZE_192) {
+		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_192;
+	} else if (keylen == AES_KEYSIZE_256) {
+		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256;
+	} else {
+		pr_err("GCM: Invalid key length %d\n", keylen);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	memcpy(sa_entry->key, key, keylen);
+	sa_entry->enckey_len = keylen;
+	key_ctx_size = sizeof(struct _key_ctx) +
+			      ((DIV_ROUND_UP(keylen, 16)) << 4) +
+			      AEAD_H_SIZE;
+
+	sa_entry->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size,
+						 CHCR_KEYCTX_MAC_KEY_SIZE_128,
+						 0, 0,
+						 key_ctx_size >> 4);
+
+	/* Calculate the H = CIPH(K, 0 repeated 16 times).
+	 * It will go in key context
+	 */
+	cipher = crypto_alloc_cipher("aes-generic", 0, 0);
+	if (IS_ERR(cipher)) {
+		sa_entry->enckey_len = 0;
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = crypto_cipher_setkey(cipher, key, keylen);
+	if (ret) {
+		sa_entry->enckey_len = 0;
+		goto out1;
+	}
+	memset(ghash_h, 0, AEAD_H_SIZE);
+	crypto_cipher_encrypt_one(cipher, ghash_h, ghash_h);
+	memcpy(sa_entry->key + (DIV_ROUND_UP(sa_entry->enckey_len, 16) *
+	       16), ghash_h, AEAD_H_SIZE);
+	sa_entry->kctx_len = ((DIV_ROUND_UP(sa_entry->enckey_len, 16)) << 4) +
+			      AEAD_H_SIZE;
+out1:
+	crypto_free_cipher(cipher);
+out:
+	return ret;
+}
+
+/*
+ * chcr_xfrm_add_state
+ * returns 0 on success, negative error if failed to send message to FPGA
+ * positive error if FPGA returned a bad response
+ */
+static int chcr_xfrm_add_state(struct xfrm_state *x)
+{
+	struct ipsec_sa_entry *sa_entry;
+	int res = 0;
+
+	if (x->props.aalgo != SADB_AALG_NONE) {
+		pr_debug("CHCR: Cannot offload authenticated xfrm states\n");
+		return -EINVAL;
+	}
+	if (x->props.calgo != SADB_X_CALG_NONE) {
+		pr_debug("CHCR: Cannot offload compressed xfrm states\n");
+		return -EINVAL;
+	}
+	if (x->props.flags & XFRM_STATE_ESN) {
+		pr_debug("CHCR: Cannot offload ESN xfrm states\n");
+		return -EINVAL;
+	}
+	if (x->props.family != AF_INET &&
+	    x->props.family != AF_INET6) {
+		pr_debug("CHCR: Only IPv4/6 xfrm state offloaded\n");
+		return -EINVAL;
+	}
+	if (x->props.mode != XFRM_MODE_TRANSPORT &&
+	    x->props.mode != XFRM_MODE_TUNNEL) {
+		pr_debug("CHCR: Only transport and tunnel xfrm offload\n");
+		return -EINVAL;
+	}
+	if (x->id.proto != IPPROTO_ESP) {
+		pr_debug("CHCR: Only ESP xfrm state offloaded\n");
+		return -EINVAL;
+	}
+	if (x->encap) {
+		pr_debug("CHCR: Encapsulated xfrm state not offloaded\n");
+		return -EINVAL;
+	}
+	if (!x->aead) {
+		pr_debug("CHCR: Cannot offload xfrm states without aead\n");
+		return -EINVAL;
+	}
+	if (x->aead->alg_icv_len != 128 &&
+	    x->aead->alg_icv_len != 96) {
+		pr_debug("CHCR: Cannot offload xfrm states with AEAD ICV length other than 96b & 128b\n");
+	return -EINVAL;
+	}
+	if ((x->aead->alg_key_len != 128 + 32) &&
+	    (x->aead->alg_key_len != 256 + 32)) {
+		pr_debug("CHCR: Cannot offload xfrm states with AEAD key length other than 128/256 bit\n");
+		return -EINVAL;
+	}
+	if (x->tfcpad) {
+		pr_debug("CHCR: Cannot offload xfrm states with tfc padding\n");
+		return -EINVAL;
+	}
+	if (!x->geniv) {
+		pr_debug("CHCR: Cannot offload xfrm states without geniv\n");
+		return -EINVAL;
+	}
+	if (strcmp(x->geniv, "seqiv")) {
+		pr_debug("CHCR: Cannot offload xfrm states with geniv other than seqiv\n");
+		return -EINVAL;
+	}
+
+	sa_entry = kzalloc(sizeof(*sa_entry), GFP_KERNEL);
+	if (!sa_entry) {
+		res = -ENOMEM;
+		goto out;
+	}
+
+	sa_entry->hmac_ctrl = chcr_ipsec_setauthsize(x, sa_entry);
+	chcr_ipsec_setkey(x, sa_entry);
+	x->xso.offload_handle = (unsigned long)sa_entry;
+	try_module_get(THIS_MODULE);
+out:
+	return res;
+}
+
+static void chcr_xfrm_del_state(struct xfrm_state *x)
+{
+	/* do nothing */
+	if (!x->xso.offload_handle)
+		return;
+}
+
+static void chcr_xfrm_free_state(struct xfrm_state *x)
+{
+	struct ipsec_sa_entry *sa_entry;
+
+	if (!x->xso.offload_handle)
+		return;
+
+	sa_entry = (struct ipsec_sa_entry *)x->xso.offload_handle;
+	kfree(sa_entry);
+	module_put(THIS_MODULE);
+}
+
+static bool chcr_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
+{
+	/* Offload with IP options is not supported yet */
+	if (ip_hdr(skb)->ihl > 5)
+		return false;
+
+	return true;
+}
+
+static inline int is_eth_imm(const struct sk_buff *skb, unsigned int kctx_len)
+{
+	int hdrlen = sizeof(struct chcr_ipsec_req) + kctx_len;
+
+	hdrlen += sizeof(struct cpl_tx_pkt);
+	if (skb->len <= MAX_IMM_TX_PKT_LEN - hdrlen)
+		return hdrlen;
+	return 0;
+}
+
+static inline unsigned int calc_tx_sec_flits(const struct sk_buff *skb,
+					     unsigned int kctx_len)
+{
+	unsigned int flits;
+	int hdrlen = is_eth_imm(skb, kctx_len);
+
+	/* If the skb is small enough, we can pump it out as a work request
+	 * with only immediate data.  In that case we just have to have the
+	 * TX Packet header plus the skb data in the Work Request.
+	 */
+
+	if (hdrlen)
+		return DIV_ROUND_UP(skb->len + hdrlen, sizeof(__be64));
+
+	flits = sgl_len(skb_shinfo(skb)->nr_frags + 1);
+
+	/* Otherwise, we're going to have to construct a Scatter gather list
+	 * of the skb body and fragments.  We also include the flits necessary
+	 * for the TX Packet Work Request and CPL.  We always have a firmware
+	 * Write Header (incorporated as part of the cpl_tx_pkt_lso and
+	 * cpl_tx_pkt structures), followed by either a TX Packet Write CPL
+	 * message or, if we're doing a Large Send Offload, an LSO CPL message
+	 * with an embedded TX Packet Write CPL message.
+	 */
+	flits += (sizeof(struct fw_ulptx_wr) +
+		  sizeof(struct chcr_ipsec_req) +
+		  kctx_len +
+		  sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64);
+	return flits;
+}
+
+inline void *copy_cpltx_pktxt(struct sk_buff *skb,
+				struct net_device *dev,
+				void *pos)
+{
+	struct adapter *adap;
+	struct port_info *pi;
+	struct sge_eth_txq *q;
+	struct cpl_tx_pkt_core *cpl;
+	u64 cntrl = 0;
+	u32 ctrl0, qidx;
+
+	pi = netdev_priv(dev);
+	adap = pi->adapter;
+	qidx = skb->queue_mapping;
+	q = &adap->sge.ethtxq[qidx + pi->first_qset];
+
+	cpl = (struct cpl_tx_pkt_core *)pos;
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
+		cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
+	ctrl0 = TXPKT_OPCODE_V(CPL_TX_PKT_XT) | TXPKT_INTF_V(pi->tx_chan) |
+			       TXPKT_PF_V(adap->pf);
+	if (skb_vlan_tag_present(skb)) {
+		q->vlan_ins++;
+		cntrl |= TXPKT_VLAN_VLD_F | TXPKT_VLAN_V(skb_vlan_tag_get(skb));
+	}
+
+	cpl->ctrl0 = htonl(ctrl0);
+	cpl->pack = htons(0);
+	cpl->len = htons(skb->len);
+	cpl->ctrl1 = cpu_to_be64(cntrl);
+
+	pos += sizeof(struct cpl_tx_pkt_core);
+	return pos;
+}
+
+inline void *copy_key_cpltx_pktxt(struct sk_buff *skb,
+				struct net_device *dev,
+				void *pos,
+				struct ipsec_sa_entry *sa_entry)
+{
+	struct adapter *adap;
+	struct port_info *pi;
+	struct sge_eth_txq *q;
+	unsigned int len, qidx;
+	struct _key_ctx *key_ctx;
+	int left, eoq, key_len;
+
+	pi = netdev_priv(dev);
+	adap = pi->adapter;
+	qidx = skb->queue_mapping;
+	q = &adap->sge.ethtxq[qidx + pi->first_qset];
+	len = sa_entry->enckey_len + sizeof(struct cpl_tx_pkt_core);
+	key_len = sa_entry->kctx_len;
+
+	/* end of queue, reset pos to start of queue */
+	eoq = (void *)q->q.stat - pos;
+	left = eoq;
+	if (!eoq) {
+		pos = q->q.desc;
+		left = 64 * q->q.size;
+	}
+
+	/* Copy the Key context header */
+	key_ctx = (struct _key_ctx *)pos;
+	key_ctx->ctx_hdr = sa_entry->key_ctx_hdr;
+	memcpy(key_ctx->salt, sa_entry->salt, MAX_SALT);
+	pos += sizeof(struct _key_ctx);
+	left -= sizeof(struct _key_ctx);
+
+	if (likely(len <= left)) {
+		memcpy(key_ctx->key, sa_entry->key, key_len);
+		pos += key_len;
+	} else {
+		if (key_len <= left) {
+			memcpy(pos, sa_entry->key, key_len);
+			pos += key_len;
+		} else {
+			memcpy(pos, sa_entry->key, left);
+			memcpy(q->q.desc, sa_entry->key + left,
+			       key_len - left);
+			pos = (u8 *)q->q.desc + (key_len - left);
+		}
+	}
+	/* Copy CPL TX PKT XT */
+	pos = copy_cpltx_pktxt(skb, dev, pos);
+
+	return pos;
+}
+
+inline void *chcr_crypto_wreq(struct sk_buff *skb,
+			       struct net_device *dev,
+			       void *pos,
+			       int credits,
+			       struct ipsec_sa_entry *sa_entry)
+{
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+	unsigned int immdatalen = 0;
+	unsigned int ivsize = GCM_ESP_IV_SIZE;
+	struct chcr_ipsec_wr *wr;
+	unsigned int flits;
+	u32 wr_mid;
+	int qidx = skb_get_queue_mapping(skb);
+	struct sge_eth_txq *q = &adap->sge.ethtxq[qidx + pi->first_qset];
+	unsigned int kctx_len = sa_entry->kctx_len;
+	int qid = q->q.cntxt_id;
+
+	atomic_inc(&adap->chcr_stats.ipsec_cnt);
+
+	flits = calc_tx_sec_flits(skb, kctx_len);
+
+	if (is_eth_imm(skb, kctx_len))
+		immdatalen = skb->len;
+
+	/* WR Header */
+	wr = (struct chcr_ipsec_wr *)pos;
+	wr->wreq.op_to_compl = htonl(FW_WR_OP_V(FW_ULPTX_WR));
+	wr_mid = FW_CRYPTO_LOOKASIDE_WR_LEN16_V(DIV_ROUND_UP(flits, 2));
+
+	if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+		netif_tx_stop_queue(q->txq);
+		q->q.stops++;
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+	}
+	wr_mid |= FW_ULPTX_WR_DATA_F;
+	wr->wreq.flowid_len16 = htonl(wr_mid);
+
+	/* ULPTX */
+	wr->req.ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(pi->port_id, qid);
+	wr->req.ulptx.len = htonl(DIV_ROUND_UP(flits, 2)  - 1);
+
+	/* Sub-command */
+	wr->req.sc_imm.cmd_more = FILL_CMD_MORE(immdatalen);
+	wr->req.sc_imm.len = cpu_to_be32(sizeof(struct cpl_tx_sec_pdu) +
+					 sizeof(wr->req.key_ctx) +
+					 kctx_len +
+					 sizeof(struct cpl_tx_pkt_core) +
+					 immdatalen);
+
+	/* CPL_SEC_PDU */
+	wr->req.sec_cpl.op_ivinsrtofst = htonl(
+				CPL_TX_SEC_PDU_OPCODE_V(CPL_TX_SEC_PDU) |
+				CPL_TX_SEC_PDU_CPLLEN_V(2) |
+				CPL_TX_SEC_PDU_PLACEHOLDER_V(1) |
+				CPL_TX_SEC_PDU_IVINSRTOFST_V(
+				(skb_transport_offset(skb) +
+				sizeof(struct ip_esp_hdr) + 1)));
+
+	wr->req.sec_cpl.pldlen = htonl(skb->len);
+
+	wr->req.sec_cpl.aadstart_cipherstop_hi = FILL_SEC_CPL_CIPHERSTOP_HI(
+				(skb_transport_offset(skb) + 1),
+				(skb_transport_offset(skb) +
+				 sizeof(struct ip_esp_hdr)),
+				(skb_transport_offset(skb) +
+				 sizeof(struct ip_esp_hdr) +
+				 GCM_ESP_IV_SIZE + 1), 0);
+
+	wr->req.sec_cpl.cipherstop_lo_authinsert =
+		FILL_SEC_CPL_AUTHINSERT(0, skb_transport_offset(skb) +
+					   sizeof(struct ip_esp_hdr) +
+					   GCM_ESP_IV_SIZE + 1,
+					   sa_entry->authsize,
+					   sa_entry->authsize);
+	wr->req.sec_cpl.seqno_numivs =
+		FILL_SEC_CPL_SCMD0_SEQNO(CHCR_ENCRYPT_OP, 1,
+					 CHCR_SCMD_CIPHER_MODE_AES_GCM,
+					 CHCR_SCMD_AUTH_MODE_GHASH,
+					 sa_entry->hmac_ctrl,
+					 ivsize >> 1);
+	wr->req.sec_cpl.ivgen_hdrlen =  FILL_SEC_CPL_IVGEN_HDRLEN(0, 0, 1,
+								  0, 0, 0);
+
+	pos += sizeof(struct fw_ulptx_wr) +
+	       sizeof(struct ulp_txpkt) +
+	       sizeof(struct ulptx_idata) +
+	       sizeof(struct cpl_tx_sec_pdu);
+
+	pos = copy_key_cpltx_pktxt(skb, dev, pos, sa_entry);
+
+	return pos;
+}
+
+/**
+ *      flits_to_desc - returns the num of Tx descriptors for the given flits
+ *      @n: the number of flits
+ *
+ *      Returns the number of Tx descriptors needed for the supplied number
+ *      of flits.
+ */
+static inline unsigned int flits_to_desc(unsigned int n)
+{
+	WARN_ON(n > SGE_MAX_WR_LEN / 8);
+	return DIV_ROUND_UP(n, 8);
+}
+
+static inline unsigned int txq_avail(const struct sge_txq *q)
+{
+	return q->size - 1 - q->in_use;
+}
+
+static void eth_txq_stop(struct sge_eth_txq *q)
+{
+	netif_tx_stop_queue(q->txq);
+	q->q.stops++;
+}
+
+static inline void txq_advance(struct sge_txq *q, unsigned int n)
+{
+	q->in_use += n;
+	q->pidx += n;
+	if (q->pidx >= q->size)
+		q->pidx -= q->size;
+}
+
+/*
+ *      chcr_ipsec_xmit called from ULD Tx handler
+ */
+int chcr_ipsec_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct xfrm_state *x = xfrm_input_state(skb);
+	struct ipsec_sa_entry *sa_entry;
+	u64 *pos, *end, *before, *sgl;
+	int qidx, left, credits;
+	unsigned int flits = 0, ndesc, kctx_len;
+	struct adapter *adap;
+	struct sge_eth_txq *q;
+	struct port_info *pi;
+	dma_addr_t addr[MAX_SKB_FRAGS + 1];
+	bool immediate = false;
+
+	if (!x->xso.offload_handle)
+		return NETDEV_TX_BUSY;
+
+	sa_entry = (struct ipsec_sa_entry *)x->xso.offload_handle;
+	kctx_len = sa_entry->kctx_len;
+
+	if (skb->sp->len != 1) {
+out_free:       dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	pi = netdev_priv(dev);
+	adap = pi->adapter;
+	qidx = skb->queue_mapping;
+	q = &adap->sge.ethtxq[qidx + pi->first_qset];
+
+	cxgb4_reclaim_completed_tx(adap, &q->q, true);
+
+	flits = calc_tx_sec_flits(skb, sa_entry->kctx_len);
+	ndesc = flits_to_desc(flits);
+	credits = txq_avail(&q->q) - ndesc;
+
+	if (unlikely(credits < 0)) {
+		eth_txq_stop(q);
+		dev_err(adap->pdev_dev,
+			"%s: Tx ring %u full while queue awake! cred:%d %d %d flits:%d\n",
+			dev->name, qidx, credits, ndesc, txq_avail(&q->q),
+			flits);
+		return NETDEV_TX_BUSY;
+	}
+
+	if (is_eth_imm(skb, kctx_len))
+		immediate = true;
+
+	if (!immediate &&
+	    unlikely(cxgb4_map_skb(adap->pdev_dev, skb, addr) < 0)) {
+		q->mapping_err++;
+		goto out_free;
+	}
+
+	pos = (u64 *)&q->q.desc[q->q.pidx];
+	before = (u64 *)pos;
+	end = (u64 *)pos + flits;
+	/* Setup IPSec CPL */
+	pos = (void *)chcr_crypto_wreq(skb, dev, (void *)pos,
+				       credits, sa_entry);
+	if (before > (u64 *)pos) {
+		left = (u8 *)end - (u8 *)q->q.stat;
+		end = (void *)q->q.desc + left;
+	}
+	if (pos == (u64 *)q->q.stat) {
+		left = (u8 *)end - (u8 *)q->q.stat;
+		end = (void *)q->q.desc + left;
+		pos = (void *)q->q.desc;
+	}
+
+	sgl = (void *)pos;
+	if (immediate) {
+		cxgb4_inline_tx_skb(skb, &q->q, sgl);
+		dev_consume_skb_any(skb);
+	} else {
+		int last_desc;
+
+		cxgb4_write_sgl(skb, &q->q, (void *)sgl, end,
+				0, addr);
+		skb_orphan(skb);
+
+		last_desc = q->q.pidx + ndesc - 1;
+		if (last_desc >= q->q.size)
+			last_desc -= q->q.size;
+		q->q.sdesc[last_desc].skb = skb;
+		q->q.sdesc[last_desc].sgl = (struct ulptx_sgl *)sgl;
+	}
+	txq_advance(&q->q, ndesc);
+
+	cxgb4_ring_tx_db(adap, &q->q, ndesc);
+	return NETDEV_TX_OK;
+}
diff --git a/drivers/crypto/exynos-rng.c b/drivers/crypto/exynos-rng.c
index 451620b475a0..86f5f459762e 100644
--- a/drivers/crypto/exynos-rng.c
+++ b/drivers/crypto/exynos-rng.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * exynos-rng.c - Random Number Generator driver for the Exynos
  *
@@ -6,15 +7,6 @@
  * Loosely based on old driver from drivers/char/hw_random/exynos-rng.c:
  * Copyright (C) 2012 Samsung Electronics
  * Jonghwa Lee <jonghwa3.lee@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation;
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/clk.h>
@@ -22,12 +14,18 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 
 #include <crypto/internal/rng.h>
 
 #define EXYNOS_RNG_CONTROL		0x0
 #define EXYNOS_RNG_STATUS		0x10
+
+#define EXYNOS_RNG_SEED_CONF		0x14
+#define EXYNOS_RNG_GEN_PRNG	        BIT(1)
+
 #define EXYNOS_RNG_SEED_BASE		0x140
 #define EXYNOS_RNG_SEED(n)		(EXYNOS_RNG_SEED_BASE + (n * 0x4))
 #define EXYNOS_RNG_OUT_BASE		0x160
@@ -43,13 +41,21 @@
 #define EXYNOS_RNG_SEED_REGS		5
 #define EXYNOS_RNG_SEED_SIZE		(EXYNOS_RNG_SEED_REGS * 4)
 
+enum exynos_prng_type {
+	EXYNOS_PRNG_UNKNOWN = 0,
+	EXYNOS_PRNG_EXYNOS4,
+	EXYNOS_PRNG_EXYNOS5,
+};
+
 /*
- * Driver re-seeds itself with generated random numbers to increase
- * the randomness.
+ * Driver re-seeds itself with generated random numbers to hinder
+ * backtracking of the original seed.
  *
  * Time for next re-seed in ms.
  */
-#define EXYNOS_RNG_RESEED_TIME		100
+#define EXYNOS_RNG_RESEED_TIME		1000
+#define EXYNOS_RNG_RESEED_BYTES		65536
+
 /*
  * In polling mode, do not wait infinitely for the engine to finish the work.
  */
@@ -63,13 +69,17 @@ struct exynos_rng_ctx {
 /* Device associated memory */
 struct exynos_rng_dev {
 	struct device			*dev;
+	enum exynos_prng_type		type;
 	void __iomem			*mem;
 	struct clk			*clk;
+	struct mutex 			lock;
 	/* Generated numbers stored for seeding during resume */
 	u8				seed_save[EXYNOS_RNG_SEED_SIZE];
 	unsigned int			seed_save_len;
 	/* Time of last seeding in jiffies */
 	unsigned long			last_seeding;
+	/* Bytes generated since last seeding */
+	unsigned long			bytes_seeding;
 };
 
 static struct exynos_rng_dev *exynos_rng_dev;
@@ -114,39 +124,12 @@ static int exynos_rng_set_seed(struct exynos_rng_dev *rng,
 	}
 
 	rng->last_seeding = jiffies;
+	rng->bytes_seeding = 0;
 
 	return 0;
 }
 
 /*
- * Read from output registers and put the data under 'dst' array,
- * up to dlen bytes.
- *
- * Returns number of bytes actually stored in 'dst' (dlen
- * or EXYNOS_RNG_SEED_SIZE).
- */
-static unsigned int exynos_rng_copy_random(struct exynos_rng_dev *rng,
-					   u8 *dst, unsigned int dlen)
-{
-	unsigned int cnt = 0;
-	int i, j;
-	u32 val;
-
-	for (j = 0; j < EXYNOS_RNG_SEED_REGS; j++) {
-		val = exynos_rng_readl(rng, EXYNOS_RNG_OUT(j));
-
-		for (i = 0; i < 4; i++) {
-			dst[cnt] = val & 0xff;
-			val >>= 8;
-			if (++cnt >= dlen)
-				return cnt;
-		}
-	}
-
-	return cnt;
-}
-
-/*
  * Start the engine and poll for finish.  Then read from output registers
  * filling the 'dst' buffer up to 'dlen' bytes or up to size of generated
  * random data (EXYNOS_RNG_SEED_SIZE).
@@ -160,8 +143,13 @@ static int exynos_rng_get_random(struct exynos_rng_dev *rng,
 {
 	int retry = EXYNOS_RNG_WAIT_RETRIES;
 
-	exynos_rng_writel(rng, EXYNOS_RNG_CONTROL_START,
-			  EXYNOS_RNG_CONTROL);
+	if (rng->type == EXYNOS_PRNG_EXYNOS4) {
+		exynos_rng_writel(rng, EXYNOS_RNG_CONTROL_START,
+				  EXYNOS_RNG_CONTROL);
+	} else if (rng->type == EXYNOS_PRNG_EXYNOS5) {
+		exynos_rng_writel(rng, EXYNOS_RNG_GEN_PRNG,
+				  EXYNOS_RNG_SEED_CONF);
+	}
 
 	while (!(exynos_rng_readl(rng,
 			EXYNOS_RNG_STATUS) & EXYNOS_RNG_STATUS_RNG_DONE) && --retry)
@@ -173,7 +161,9 @@ static int exynos_rng_get_random(struct exynos_rng_dev *rng,
 	/* Clear status bit */
 	exynos_rng_writel(rng, EXYNOS_RNG_STATUS_RNG_DONE,
 			  EXYNOS_RNG_STATUS);
-	*read = exynos_rng_copy_random(rng, dst, dlen);
+	*read = min_t(size_t, dlen, EXYNOS_RNG_SEED_SIZE);
+	memcpy_fromio(dst, rng->mem + EXYNOS_RNG_OUT_BASE, *read);
+	rng->bytes_seeding += *read;
 
 	return 0;
 }
@@ -187,13 +177,18 @@ static void exynos_rng_reseed(struct exynos_rng_dev *rng)
 	unsigned int read = 0;
 	u8 seed[EXYNOS_RNG_SEED_SIZE];
 
-	if (time_before(now, next_seeding))
+	if (time_before(now, next_seeding) &&
+	    rng->bytes_seeding < EXYNOS_RNG_RESEED_BYTES)
 		return;
 
 	if (exynos_rng_get_random(rng, seed, sizeof(seed), &read))
 		return;
 
 	exynos_rng_set_seed(rng, seed, read);
+
+	/* Let others do some of their job. */
+	mutex_unlock(&rng->lock);
+	mutex_lock(&rng->lock);
 }
 
 static int exynos_rng_generate(struct crypto_rng *tfm,
@@ -209,6 +204,7 @@ static int exynos_rng_generate(struct crypto_rng *tfm,
 	if (ret)
 		return ret;
 
+	mutex_lock(&rng->lock);
 	do {
 		ret = exynos_rng_get_random(rng, dst, dlen, &read);
 		if (ret)
@@ -219,6 +215,7 @@ static int exynos_rng_generate(struct crypto_rng *tfm,
 
 		exynos_rng_reseed(rng);
 	} while (dlen > 0);
+	mutex_unlock(&rng->lock);
 
 	clk_disable_unprepare(rng->clk);
 
@@ -236,7 +233,9 @@ static int exynos_rng_seed(struct crypto_rng *tfm, const u8 *seed,
 	if (ret)
 		return ret;
 
+	mutex_lock(&rng->lock);
 	ret = exynos_rng_set_seed(ctx->rng, seed, slen);
+	mutex_unlock(&rng->lock);
 
 	clk_disable_unprepare(rng->clk);
 
@@ -259,7 +258,7 @@ static struct rng_alg exynos_rng_alg = {
 	.base			= {
 		.cra_name		= "stdrng",
 		.cra_driver_name	= "exynos_rng",
-		.cra_priority		= 100,
+		.cra_priority		= 300,
 		.cra_ctxsize		= sizeof(struct exynos_rng_ctx),
 		.cra_module		= THIS_MODULE,
 		.cra_init		= exynos_rng_kcapi_init,
@@ -279,6 +278,10 @@ static int exynos_rng_probe(struct platform_device *pdev)
 	if (!rng)
 		return -ENOMEM;
 
+	rng->type = (enum exynos_prng_type)of_device_get_match_data(&pdev->dev);
+
+	mutex_init(&rng->lock);
+
 	rng->dev = &pdev->dev;
 	rng->clk = devm_clk_get(&pdev->dev, "secss");
 	if (IS_ERR(rng->clk)) {
@@ -329,9 +332,14 @@ static int __maybe_unused exynos_rng_suspend(struct device *dev)
 	if (ret)
 		return ret;
 
+	mutex_lock(&rng->lock);
+
 	/* Get new random numbers and store them for seeding on resume. */
 	exynos_rng_get_random(rng, rng->seed_save, sizeof(rng->seed_save),
 			      &(rng->seed_save_len));
+
+	mutex_unlock(&rng->lock);
+
 	dev_dbg(rng->dev, "Stored %u bytes for seeding on system resume\n",
 		rng->seed_save_len);
 
@@ -354,8 +362,12 @@ static int __maybe_unused exynos_rng_resume(struct device *dev)
 	if (ret)
 		return ret;
 
+	mutex_lock(&rng->lock);
+
 	ret = exynos_rng_set_seed(rng, rng->seed_save, rng->seed_save_len);
 
+	mutex_unlock(&rng->lock);
+
 	clk_disable_unprepare(rng->clk);
 
 	return ret;
@@ -367,6 +379,10 @@ static SIMPLE_DEV_PM_OPS(exynos_rng_pm_ops, exynos_rng_suspend,
 static const struct of_device_id exynos_rng_dt_match[] = {
 	{
 		.compatible = "samsung,exynos4-rng",
+		.data = (const void *)EXYNOS_PRNG_EXYNOS4,
+	}, {
+		.compatible = "samsung,exynos5250-prng",
+		.data = (const void *)EXYNOS_PRNG_EXYNOS5,
 	},
 	{ },
 };
@@ -386,4 +402,4 @@ module_platform_driver(exynos_rng_driver);
 
 MODULE_DESCRIPTION("Exynos H/W Random Number Generator driver");
 MODULE_AUTHOR("Krzysztof Kozlowski <krzk@kernel.org>");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c
index e09d4055b19e..a5a36fe7bf2c 100644
--- a/drivers/crypto/hifn_795x.c
+++ b/drivers/crypto/hifn_795x.c
@@ -2579,6 +2579,7 @@ err_out_unmap_bars:
 	for (i = 0; i < 3; ++i)
 		if (dev->bar[i])
 			iounmap(dev->bar[i]);
+	kfree(dev);
 
 err_out_free_regions:
 	pci_release_regions(pdev);
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 89ba9e85c0f3..225e74a7f724 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -108,10 +108,10 @@ static void eip197_write_firmware(struct safexcel_crypto_priv *priv,
 	writel(EIP197_PE_ICE_x_CTRL_SW_RESET |
 	       EIP197_PE_ICE_x_CTRL_CLR_ECC_CORR |
 	       EIP197_PE_ICE_x_CTRL_CLR_ECC_NON_CORR,
-	       priv->base + ctrl);
+	       EIP197_PE(priv) + ctrl);
 
 	/* Enable access to the program memory */
-	writel(prog_en, priv->base + EIP197_PE_ICE_RAM_CTRL);
+	writel(prog_en, EIP197_PE(priv) + EIP197_PE_ICE_RAM_CTRL);
 
 	/* Write the firmware */
 	for (i = 0; i < fw->size / sizeof(u32); i++)
@@ -119,12 +119,12 @@ static void eip197_write_firmware(struct safexcel_crypto_priv *priv,
 		       priv->base + EIP197_CLASSIFICATION_RAMS + i * sizeof(u32));
 
 	/* Disable access to the program memory */
-	writel(0, priv->base + EIP197_PE_ICE_RAM_CTRL);
+	writel(0, EIP197_PE(priv) + EIP197_PE_ICE_RAM_CTRL);
 
 	/* Release engine from reset */
-	val = readl(priv->base + ctrl);
+	val = readl(EIP197_PE(priv) + ctrl);
 	val &= ~EIP197_PE_ICE_x_CTRL_SW_RESET;
-	writel(val, priv->base + ctrl);
+	writel(val, EIP197_PE(priv) + ctrl);
 }
 
 static int eip197_load_firmwares(struct safexcel_crypto_priv *priv)
@@ -145,14 +145,14 @@ static int eip197_load_firmwares(struct safexcel_crypto_priv *priv)
 	 }
 
 	/* Clear the scratchpad memory */
-	val = readl(priv->base + EIP197_PE_ICE_SCRATCH_CTRL);
+	val = readl(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL);
 	val |= EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_TIMER |
 	       EIP197_PE_ICE_SCRATCH_CTRL_TIMER_EN |
 	       EIP197_PE_ICE_SCRATCH_CTRL_SCRATCH_ACCESS |
 	       EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_ACCESS;
-	writel(val, priv->base + EIP197_PE_ICE_SCRATCH_CTRL);
+	writel(val, EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL);
 
-	memset(priv->base + EIP197_PE_ICE_SCRATCH_RAM, 0,
+	memset(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_RAM, 0,
 	       EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
 
 	eip197_write_firmware(priv, fw[FW_IFPP], EIP197_PE_ICE_FPP_CTRL,
@@ -173,7 +173,7 @@ static int safexcel_hw_setup_cdesc_rings(struct safexcel_crypto_priv *priv)
 	u32 hdw, cd_size_rnd, val;
 	int i;
 
-	hdw = readl(priv->base + EIP197_HIA_OPTIONS);
+	hdw = readl(EIP197_HIA_AIC_G(priv) + EIP197_HIA_OPTIONS);
 	hdw &= GENMASK(27, 25);
 	hdw >>= 25;
 
@@ -182,26 +182,25 @@ static int safexcel_hw_setup_cdesc_rings(struct safexcel_crypto_priv *priv)
 	for (i = 0; i < priv->config.rings; i++) {
 		/* ring base address */
 		writel(lower_32_bits(priv->ring[i].cdr.base_dma),
-		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_RING_BASE_ADDR_LO);
+		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_LO);
 		writel(upper_32_bits(priv->ring[i].cdr.base_dma),
-		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
+		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
 
 		writel(EIP197_xDR_DESC_MODE_64BIT | (priv->config.cd_offset << 16) |
 		       priv->config.cd_size,
-		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_DESC_SIZE);
+		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_DESC_SIZE);
 		writel(((EIP197_FETCH_COUNT * (cd_size_rnd << hdw)) << 16) |
 		       (EIP197_FETCH_COUNT * priv->config.cd_offset),
-		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_CFG);
+		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_CFG);
 
 		/* Configure DMA tx control */
 		val = EIP197_HIA_xDR_CFG_WR_CACHE(WR_CACHE_3BITS);
 		val |= EIP197_HIA_xDR_CFG_RD_CACHE(RD_CACHE_3BITS);
-		writel(val,
-		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_DMA_CFG);
+		writel(val, EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_DMA_CFG);
 
 		/* clear any pending interrupt */
 		writel(GENMASK(5, 0),
-		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_STAT);
+		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_STAT);
 	}
 
 	return 0;
@@ -212,7 +211,7 @@ static int safexcel_hw_setup_rdesc_rings(struct safexcel_crypto_priv *priv)
 	u32 hdw, rd_size_rnd, val;
 	int i;
 
-	hdw = readl(priv->base + EIP197_HIA_OPTIONS);
+	hdw = readl(EIP197_HIA_AIC_G(priv) + EIP197_HIA_OPTIONS);
 	hdw &= GENMASK(27, 25);
 	hdw >>= 25;
 
@@ -221,33 +220,33 @@ static int safexcel_hw_setup_rdesc_rings(struct safexcel_crypto_priv *priv)
 	for (i = 0; i < priv->config.rings; i++) {
 		/* ring base address */
 		writel(lower_32_bits(priv->ring[i].rdr.base_dma),
-		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_RING_BASE_ADDR_LO);
+		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_LO);
 		writel(upper_32_bits(priv->ring[i].rdr.base_dma),
-		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
+		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
 
 		writel(EIP197_xDR_DESC_MODE_64BIT | (priv->config.rd_offset << 16) |
 		       priv->config.rd_size,
-		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_DESC_SIZE);
+		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_DESC_SIZE);
 
 		writel(((EIP197_FETCH_COUNT * (rd_size_rnd << hdw)) << 16) |
 		       (EIP197_FETCH_COUNT * priv->config.rd_offset),
-		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_CFG);
+		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_CFG);
 
 		/* Configure DMA tx control */
 		val = EIP197_HIA_xDR_CFG_WR_CACHE(WR_CACHE_3BITS);
 		val |= EIP197_HIA_xDR_CFG_RD_CACHE(RD_CACHE_3BITS);
 		val |= EIP197_HIA_xDR_WR_RES_BUF | EIP197_HIA_xDR_WR_CTRL_BUG;
 		writel(val,
-		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_DMA_CFG);
+		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_DMA_CFG);
 
 		/* clear any pending interrupt */
 		writel(GENMASK(7, 0),
-		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_STAT);
+		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_STAT);
 
 		/* enable ring interrupt */
-		val = readl(priv->base + EIP197_HIA_AIC_R_ENABLE_CTRL(i));
+		val = readl(EIP197_HIA_AIC_R(priv) + EIP197_HIA_AIC_R_ENABLE_CTRL(i));
 		val |= EIP197_RDR_IRQ(i);
-		writel(val, priv->base + EIP197_HIA_AIC_R_ENABLE_CTRL(i));
+		writel(val, EIP197_HIA_AIC_R(priv) + EIP197_HIA_AIC_R_ENABLE_CTRL(i));
 	}
 
 	return 0;
@@ -259,39 +258,40 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	int i, ret;
 
 	/* Determine endianess and configure byte swap */
-	version = readl(priv->base + EIP197_HIA_VERSION);
-	val = readl(priv->base + EIP197_HIA_MST_CTRL);
+	version = readl(EIP197_HIA_AIC(priv) + EIP197_HIA_VERSION);
+	val = readl(EIP197_HIA_AIC(priv) + EIP197_HIA_MST_CTRL);
 
 	if ((version & 0xffff) == EIP197_HIA_VERSION_BE)
 		val |= EIP197_MST_CTRL_BYTE_SWAP;
 	else if (((version >> 16) & 0xffff) == EIP197_HIA_VERSION_LE)
 		val |= (EIP197_MST_CTRL_NO_BYTE_SWAP >> 24);
 
-	writel(val, priv->base + EIP197_HIA_MST_CTRL);
-
+	writel(val, EIP197_HIA_AIC(priv) + EIP197_HIA_MST_CTRL);
 
 	/* Configure wr/rd cache values */
 	writel(EIP197_MST_CTRL_RD_CACHE(RD_CACHE_4BITS) |
 	       EIP197_MST_CTRL_WD_CACHE(WR_CACHE_4BITS),
-	       priv->base + EIP197_MST_CTRL);
+	       EIP197_HIA_GEN_CFG(priv) + EIP197_MST_CTRL);
 
 	/* Interrupts reset */
 
 	/* Disable all global interrupts */
-	writel(0, priv->base + EIP197_HIA_AIC_G_ENABLE_CTRL);
+	writel(0, EIP197_HIA_AIC_G(priv) + EIP197_HIA_AIC_G_ENABLE_CTRL);
 
 	/* Clear any pending interrupt */
-	writel(GENMASK(31, 0), priv->base + EIP197_HIA_AIC_G_ACK);
+	writel(GENMASK(31, 0), EIP197_HIA_AIC_G(priv) + EIP197_HIA_AIC_G_ACK);
 
 	/* Data Fetch Engine configuration */
 
 	/* Reset all DFE threads */
 	writel(EIP197_DxE_THR_CTRL_RESET_PE,
-	       priv->base + EIP197_HIA_DFE_THR_CTRL);
+	       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL);
 
-	/* Reset HIA input interface arbiter */
-	writel(EIP197_HIA_RA_PE_CTRL_RESET,
-	       priv->base + EIP197_HIA_RA_PE_CTRL);
+	if (priv->version == EIP197) {
+		/* Reset HIA input interface arbiter */
+		writel(EIP197_HIA_RA_PE_CTRL_RESET,
+		       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL);
+	}
 
 	/* DMA transfer size to use */
 	val = EIP197_HIA_DFE_CFG_DIS_DEBUG;
@@ -299,29 +299,32 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	val |= EIP197_HIA_DxE_CFG_MIN_CTRL_SIZE(5) | EIP197_HIA_DxE_CFG_MAX_CTRL_SIZE(7);
 	val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(RD_CACHE_3BITS);
 	val |= EIP197_HIA_DxE_CFG_CTRL_CACHE_CTRL(RD_CACHE_3BITS);
-	writel(val, priv->base + EIP197_HIA_DFE_CFG);
+	writel(val, EIP197_HIA_DFE(priv) + EIP197_HIA_DFE_CFG);
 
 	/* Leave the DFE threads reset state */
-	writel(0, priv->base + EIP197_HIA_DFE_THR_CTRL);
+	writel(0, EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL);
 
 	/* Configure the procesing engine thresholds */
 	writel(EIP197_PE_IN_xBUF_THRES_MIN(5) | EIP197_PE_IN_xBUF_THRES_MAX(9),
-	      priv->base + EIP197_PE_IN_DBUF_THRES);
+	       EIP197_PE(priv) + EIP197_PE_IN_DBUF_THRES);
 	writel(EIP197_PE_IN_xBUF_THRES_MIN(5) | EIP197_PE_IN_xBUF_THRES_MAX(7),
-	      priv->base + EIP197_PE_IN_TBUF_THRES);
+	       EIP197_PE(priv) + EIP197_PE_IN_TBUF_THRES);
 
-	/* enable HIA input interface arbiter and rings */
-	writel(EIP197_HIA_RA_PE_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
-	       priv->base + EIP197_HIA_RA_PE_CTRL);
+	if (priv->version == EIP197) {
+		/* enable HIA input interface arbiter and rings */
+		writel(EIP197_HIA_RA_PE_CTRL_EN |
+		       GENMASK(priv->config.rings - 1, 0),
+		       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL);
+	}
 
 	/* Data Store Engine configuration */
 
 	/* Reset all DSE threads */
 	writel(EIP197_DxE_THR_CTRL_RESET_PE,
-	       priv->base + EIP197_HIA_DSE_THR_CTRL);
+	       EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL);
 
 	/* Wait for all DSE threads to complete */
-	while ((readl(priv->base + EIP197_HIA_DSE_THR_STAT) &
+	while ((readl(EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_STAT) &
 		GENMASK(15, 12)) != GENMASK(15, 12))
 		;
 
@@ -330,15 +333,19 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(7) | EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(8);
 	val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(WR_CACHE_3BITS);
 	val |= EIP197_HIA_DSE_CFG_ALLWAYS_BUFFERABLE;
-	val |= EIP197_HIA_DSE_CFG_EN_SINGLE_WR;
-	writel(val, priv->base + EIP197_HIA_DSE_CFG);
+	/* FIXME: instability issues can occur for EIP97 but disabling it impact
+	 * performances.
+	 */
+	if (priv->version == EIP197)
+		val |= EIP197_HIA_DSE_CFG_EN_SINGLE_WR;
+	writel(val, EIP197_HIA_DSE(priv) + EIP197_HIA_DSE_CFG);
 
 	/* Leave the DSE threads reset state */
-	writel(0, priv->base + EIP197_HIA_DSE_THR_CTRL);
+	writel(0, EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL);
 
 	/* Configure the procesing engine thresholds */
 	writel(EIP197_PE_OUT_DBUF_THRES_MIN(7) | EIP197_PE_OUT_DBUF_THRES_MAX(8),
-	       priv->base + EIP197_PE_OUT_DBUF_THRES);
+	       EIP197_PE(priv) + EIP197_PE_OUT_DBUF_THRES);
 
 	/* Processing Engine configuration */
 
@@ -348,73 +355,75 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
 	val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
 	val |= EIP197_ALG_SHA2;
-	writel(val, priv->base + EIP197_PE_EIP96_FUNCTION_EN);
+	writel(val, EIP197_PE(priv) + EIP197_PE_EIP96_FUNCTION_EN);
 
 	/* Command Descriptor Rings prepare */
 	for (i = 0; i < priv->config.rings; i++) {
 		/* Clear interrupts for this ring */
 		writel(GENMASK(31, 0),
-		       priv->base + EIP197_HIA_AIC_R_ENABLE_CLR(i));
+		       EIP197_HIA_AIC_R(priv) + EIP197_HIA_AIC_R_ENABLE_CLR(i));
 
 		/* Disable external triggering */
-		writel(0, priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_CFG);
+		writel(0, EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_CFG);
 
 		/* Clear the pending prepared counter */
 		writel(EIP197_xDR_PREP_CLR_COUNT,
-		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_PREP_COUNT);
+		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_PREP_COUNT);
 
 		/* Clear the pending processed counter */
 		writel(EIP197_xDR_PROC_CLR_COUNT,
-		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_PROC_COUNT);
+		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_PROC_COUNT);
 
 		writel(0,
-		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_PREP_PNTR);
+		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_PREP_PNTR);
 		writel(0,
-		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_PROC_PNTR);
+		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_PROC_PNTR);
 
 		writel((EIP197_DEFAULT_RING_SIZE * priv->config.cd_offset) << 2,
-		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_RING_SIZE);
+		       EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_RING_SIZE);
 	}
 
 	/* Result Descriptor Ring prepare */
 	for (i = 0; i < priv->config.rings; i++) {
 		/* Disable external triggering*/
-		writel(0, priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_CFG);
+		writel(0, EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_CFG);
 
 		/* Clear the pending prepared counter */
 		writel(EIP197_xDR_PREP_CLR_COUNT,
-		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_PREP_COUNT);
+		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_PREP_COUNT);
 
 		/* Clear the pending processed counter */
 		writel(EIP197_xDR_PROC_CLR_COUNT,
-		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_PROC_COUNT);
+		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_PROC_COUNT);
 
 		writel(0,
-		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_PREP_PNTR);
+		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_PREP_PNTR);
 		writel(0,
-		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_PROC_PNTR);
+		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_PROC_PNTR);
 
 		/* Ring size */
 		writel((EIP197_DEFAULT_RING_SIZE * priv->config.rd_offset) << 2,
-		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_RING_SIZE);
+		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_RING_SIZE);
 	}
 
 	/* Enable command descriptor rings */
 	writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
-	       priv->base + EIP197_HIA_DFE_THR_CTRL);
+	       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL);
 
 	/* Enable result descriptor rings */
 	writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
-	       priv->base + EIP197_HIA_DSE_THR_CTRL);
+	       EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL);
 
 	/* Clear any HIA interrupt */
-	writel(GENMASK(30, 20), priv->base + EIP197_HIA_AIC_G_ACK);
+	writel(GENMASK(30, 20), EIP197_HIA_AIC_G(priv) + EIP197_HIA_AIC_G_ACK);
 
-	eip197_trc_cache_init(priv);
+	if (priv->version == EIP197) {
+		eip197_trc_cache_init(priv);
 
-	ret = eip197_load_firmwares(priv);
-	if (ret)
-		return ret;
+		ret = eip197_load_firmwares(priv);
+		if (ret)
+			return ret;
+	}
 
 	safexcel_hw_setup_cdesc_rings(priv);
 	safexcel_hw_setup_rdesc_rings(priv);
@@ -422,6 +431,23 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	return 0;
 }
 
+/* Called with ring's lock taken */
+static int safexcel_try_push_requests(struct safexcel_crypto_priv *priv,
+				      int ring, int reqs)
+{
+	int coal = min_t(int, reqs, EIP197_MAX_BATCH_SZ);
+
+	if (!coal)
+		return 0;
+
+	/* Configure when we want an interrupt */
+	writel(EIP197_HIA_RDR_THRESH_PKT_MODE |
+	       EIP197_HIA_RDR_THRESH_PROC_PKT(coal),
+	       EIP197_HIA_RDR(priv, ring) + EIP197_HIA_xDR_THRESH);
+
+	return coal;
+}
+
 void safexcel_dequeue(struct safexcel_crypto_priv *priv, int ring)
 {
 	struct crypto_async_request *req, *backlog;
@@ -429,34 +455,36 @@ void safexcel_dequeue(struct safexcel_crypto_priv *priv, int ring)
 	struct safexcel_request *request;
 	int ret, nreq = 0, cdesc = 0, rdesc = 0, commands, results;
 
-	priv->ring[ring].need_dequeue = false;
+	/* If a request wasn't properly dequeued because of a lack of resources,
+	 * proceeded it first,
+	 */
+	req = priv->ring[ring].req;
+	backlog = priv->ring[ring].backlog;
+	if (req)
+		goto handle_req;
 
-	do {
+	while (true) {
 		spin_lock_bh(&priv->ring[ring].queue_lock);
 		backlog = crypto_get_backlog(&priv->ring[ring].queue);
 		req = crypto_dequeue_request(&priv->ring[ring].queue);
 		spin_unlock_bh(&priv->ring[ring].queue_lock);
 
-		if (!req)
+		if (!req) {
+			priv->ring[ring].req = NULL;
+			priv->ring[ring].backlog = NULL;
 			goto finalize;
+		}
 
+handle_req:
 		request = kzalloc(sizeof(*request), EIP197_GFP_FLAGS(*req));
-		if (!request) {
-			spin_lock_bh(&priv->ring[ring].queue_lock);
-			crypto_enqueue_request(&priv->ring[ring].queue, req);
-			spin_unlock_bh(&priv->ring[ring].queue_lock);
-
-			priv->ring[ring].need_dequeue = true;
-			goto finalize;
-		}
+		if (!request)
+			goto request_failed;
 
 		ctx = crypto_tfm_ctx(req->tfm);
 		ret = ctx->send(req, ring, request, &commands, &results);
 		if (ret) {
 			kfree(request);
-			req->complete(req, ret);
-			priv->ring[ring].need_dequeue = true;
-			goto finalize;
+			goto request_failed;
 		}
 
 		if (backlog)
@@ -468,30 +496,39 @@ void safexcel_dequeue(struct safexcel_crypto_priv *priv, int ring)
 
 		cdesc += commands;
 		rdesc += results;
-	} while (nreq++ < EIP197_MAX_BATCH_SZ);
+		nreq++;
+	}
+
+request_failed:
+	/* Not enough resources to handle all the requests. Bail out and save
+	 * the request and the backlog for the next dequeue call (per-ring).
+	 */
+	priv->ring[ring].req = req;
+	priv->ring[ring].backlog = backlog;
 
 finalize:
-	if (nreq == EIP197_MAX_BATCH_SZ)
-		priv->ring[ring].need_dequeue = true;
-	else if (!nreq)
+	if (!nreq)
 		return;
 
-	spin_lock_bh(&priv->ring[ring].lock);
+	spin_lock_bh(&priv->ring[ring].egress_lock);
 
-	/* Configure when we want an interrupt */
-	writel(EIP197_HIA_RDR_THRESH_PKT_MODE |
-	       EIP197_HIA_RDR_THRESH_PROC_PKT(nreq),
-	       priv->base + EIP197_HIA_RDR(ring) + EIP197_HIA_xDR_THRESH);
+	if (!priv->ring[ring].busy) {
+		nreq -= safexcel_try_push_requests(priv, ring, nreq);
+		if (nreq)
+			priv->ring[ring].busy = true;
+	}
+
+	priv->ring[ring].requests_left += nreq;
+
+	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	/* let the RDR know we have pending descriptors */
 	writel((rdesc * priv->config.rd_offset) << 2,
-	       priv->base + EIP197_HIA_RDR(ring) + EIP197_HIA_xDR_PREP_COUNT);
+	       EIP197_HIA_RDR(priv, ring) + EIP197_HIA_xDR_PREP_COUNT);
 
 	/* let the CDR know we have pending descriptors */
 	writel((cdesc * priv->config.cd_offset) << 2,
-	       priv->base + EIP197_HIA_CDR(ring) + EIP197_HIA_xDR_PREP_COUNT);
-
-	spin_unlock_bh(&priv->ring[ring].lock);
+	       EIP197_HIA_CDR(priv, ring) + EIP197_HIA_xDR_PREP_COUNT);
 }
 
 void safexcel_free_context(struct safexcel_crypto_priv *priv,
@@ -540,7 +577,6 @@ void safexcel_inv_complete(struct crypto_async_request *req, int error)
 }
 
 int safexcel_invalidate_cache(struct crypto_async_request *async,
-			      struct safexcel_context *ctx,
 			      struct safexcel_crypto_priv *priv,
 			      dma_addr_t ctxr_dma, int ring,
 			      struct safexcel_request *request)
@@ -587,14 +623,17 @@ static inline void safexcel_handle_result_descriptor(struct safexcel_crypto_priv
 {
 	struct safexcel_request *sreq;
 	struct safexcel_context *ctx;
-	int ret, i, nreq, ndesc = 0;
+	int ret, i, nreq, ndesc, tot_descs, done;
 	bool should_complete;
 
-	nreq = readl(priv->base + EIP197_HIA_RDR(ring) + EIP197_HIA_xDR_PROC_COUNT);
-	nreq >>= 24;
-	nreq &= GENMASK(6, 0);
+handle_results:
+	tot_descs = 0;
+
+	nreq = readl(EIP197_HIA_RDR(priv, ring) + EIP197_HIA_xDR_PROC_COUNT);
+	nreq >>= EIP197_xDR_PROC_xD_PKT_OFFSET;
+	nreq &= EIP197_xDR_PROC_xD_PKT_MASK;
 	if (!nreq)
-		return;
+		goto requests_left;
 
 	for (i = 0; i < nreq; i++) {
 		spin_lock_bh(&priv->ring[ring].egress_lock);
@@ -607,14 +646,11 @@ static inline void safexcel_handle_result_descriptor(struct safexcel_crypto_priv
 		ndesc = ctx->handle_result(priv, ring, sreq->req,
 					   &should_complete, &ret);
 		if (ndesc < 0) {
+			kfree(sreq);
 			dev_err(priv->dev, "failed to handle result (%d)", ndesc);
-			return;
+			goto acknowledge;
 		}
 
-		writel(EIP197_xDR_PROC_xD_PKT(1) |
-		       EIP197_xDR_PROC_xD_COUNT(ndesc * priv->config.rd_offset),
-		       priv->base + EIP197_HIA_RDR(ring) + EIP197_HIA_xDR_PROC_COUNT);
-
 		if (should_complete) {
 			local_bh_disable();
 			sreq->req->complete(sreq->req, ret);
@@ -622,19 +658,41 @@ static inline void safexcel_handle_result_descriptor(struct safexcel_crypto_priv
 		}
 
 		kfree(sreq);
+		tot_descs += ndesc;
 	}
+
+acknowledge:
+	if (i) {
+		writel(EIP197_xDR_PROC_xD_PKT(i) |
+		       EIP197_xDR_PROC_xD_COUNT(tot_descs * priv->config.rd_offset),
+		       EIP197_HIA_RDR(priv, ring) + EIP197_HIA_xDR_PROC_COUNT);
+	}
+
+	/* If the number of requests overflowed the counter, try to proceed more
+	 * requests.
+	 */
+	if (nreq == EIP197_xDR_PROC_xD_PKT_MASK)
+		goto handle_results;
+
+requests_left:
+	spin_lock_bh(&priv->ring[ring].egress_lock);
+
+	done = safexcel_try_push_requests(priv, ring,
+					  priv->ring[ring].requests_left);
+
+	priv->ring[ring].requests_left -= done;
+	if (!done && !priv->ring[ring].requests_left)
+		priv->ring[ring].busy = false;
+
+	spin_unlock_bh(&priv->ring[ring].egress_lock);
 }
 
-static void safexcel_handle_result_work(struct work_struct *work)
+static void safexcel_dequeue_work(struct work_struct *work)
 {
 	struct safexcel_work_data *data =
 			container_of(work, struct safexcel_work_data, work);
-	struct safexcel_crypto_priv *priv = data->priv;
-
-	safexcel_handle_result_descriptor(priv, data->ring);
 
-	if (priv->ring[data->ring].need_dequeue)
-		safexcel_dequeue(data->priv, data->ring);
+	safexcel_dequeue(data->priv, data->ring);
 }
 
 struct safexcel_ring_irq_data {
@@ -646,16 +704,16 @@ static irqreturn_t safexcel_irq_ring(int irq, void *data)
 {
 	struct safexcel_ring_irq_data *irq_data = data;
 	struct safexcel_crypto_priv *priv = irq_data->priv;
-	int ring = irq_data->ring;
+	int ring = irq_data->ring, rc = IRQ_NONE;
 	u32 status, stat;
 
-	status = readl(priv->base + EIP197_HIA_AIC_R_ENABLED_STAT(ring));
+	status = readl(EIP197_HIA_AIC_R(priv) + EIP197_HIA_AIC_R_ENABLED_STAT(ring));
 	if (!status)
-		return IRQ_NONE;
+		return rc;
 
 	/* RDR interrupts */
 	if (status & EIP197_RDR_IRQ(ring)) {
-		stat = readl(priv->base + EIP197_HIA_RDR(ring) + EIP197_HIA_xDR_STAT);
+		stat = readl(EIP197_HIA_RDR(priv, ring) + EIP197_HIA_xDR_STAT);
 
 		if (unlikely(stat & EIP197_xDR_ERR)) {
 			/*
@@ -665,22 +723,37 @@ static irqreturn_t safexcel_irq_ring(int irq, void *data)
 			 */
 			dev_err(priv->dev, "RDR: fatal error.");
 		} else if (likely(stat & EIP197_xDR_THRESH)) {
-			queue_work(priv->ring[ring].workqueue, &priv->ring[ring].work_data.work);
+			rc = IRQ_WAKE_THREAD;
 		}
 
 		/* ACK the interrupts */
 		writel(stat & 0xff,
-		       priv->base + EIP197_HIA_RDR(ring) + EIP197_HIA_xDR_STAT);
+		       EIP197_HIA_RDR(priv, ring) + EIP197_HIA_xDR_STAT);
 	}
 
 	/* ACK the interrupts */
-	writel(status, priv->base + EIP197_HIA_AIC_R_ACK(ring));
+	writel(status, EIP197_HIA_AIC_R(priv) + EIP197_HIA_AIC_R_ACK(ring));
+
+	return rc;
+}
+
+static irqreturn_t safexcel_irq_ring_thread(int irq, void *data)
+{
+	struct safexcel_ring_irq_data *irq_data = data;
+	struct safexcel_crypto_priv *priv = irq_data->priv;
+	int ring = irq_data->ring;
+
+	safexcel_handle_result_descriptor(priv, ring);
+
+	queue_work(priv->ring[ring].workqueue,
+		   &priv->ring[ring].work_data.work);
 
 	return IRQ_HANDLED;
 }
 
 static int safexcel_request_ring_irq(struct platform_device *pdev, const char *name,
 				     irq_handler_t handler,
+				     irq_handler_t threaded_handler,
 				     struct safexcel_ring_irq_data *ring_irq_priv)
 {
 	int ret, irq = platform_get_irq_byname(pdev, name);
@@ -690,8 +763,9 @@ static int safexcel_request_ring_irq(struct platform_device *pdev, const char *n
 		return irq;
 	}
 
-	ret = devm_request_irq(&pdev->dev, irq, handler, 0,
-			       dev_name(&pdev->dev), ring_irq_priv);
+	ret = devm_request_threaded_irq(&pdev->dev, irq, handler,
+					threaded_handler, IRQF_ONESHOT,
+					dev_name(&pdev->dev), ring_irq_priv);
 	if (ret) {
 		dev_err(&pdev->dev, "unable to request IRQ %d\n", irq);
 		return ret;
@@ -754,11 +828,11 @@ static void safexcel_configure(struct safexcel_crypto_priv *priv)
 {
 	u32 val, mask;
 
-	val = readl(priv->base + EIP197_HIA_OPTIONS);
+	val = readl(EIP197_HIA_AIC_G(priv) + EIP197_HIA_OPTIONS);
 	val = (val & GENMASK(27, 25)) >> 25;
 	mask = BIT(val) - 1;
 
-	val = readl(priv->base + EIP197_HIA_OPTIONS);
+	val = readl(EIP197_HIA_AIC_G(priv) + EIP197_HIA_OPTIONS);
 	priv->config.rings = min_t(u32, val & GENMASK(3, 0), max_rings);
 
 	priv->config.cd_size = (sizeof(struct safexcel_command_desc) / sizeof(u32));
@@ -768,6 +842,35 @@ static void safexcel_configure(struct safexcel_crypto_priv *priv)
 	priv->config.rd_offset = (priv->config.rd_size + mask) & ~mask;
 }
 
+static void safexcel_init_register_offsets(struct safexcel_crypto_priv *priv)
+{
+	struct safexcel_register_offsets *offsets = &priv->offsets;
+
+	if (priv->version == EIP197) {
+		offsets->hia_aic	= EIP197_HIA_AIC_BASE;
+		offsets->hia_aic_g	= EIP197_HIA_AIC_G_BASE;
+		offsets->hia_aic_r	= EIP197_HIA_AIC_R_BASE;
+		offsets->hia_aic_xdr	= EIP197_HIA_AIC_xDR_BASE;
+		offsets->hia_dfe	= EIP197_HIA_DFE_BASE;
+		offsets->hia_dfe_thr	= EIP197_HIA_DFE_THR_BASE;
+		offsets->hia_dse	= EIP197_HIA_DSE_BASE;
+		offsets->hia_dse_thr	= EIP197_HIA_DSE_THR_BASE;
+		offsets->hia_gen_cfg	= EIP197_HIA_GEN_CFG_BASE;
+		offsets->pe		= EIP197_PE_BASE;
+	} else {
+		offsets->hia_aic	= EIP97_HIA_AIC_BASE;
+		offsets->hia_aic_g	= EIP97_HIA_AIC_G_BASE;
+		offsets->hia_aic_r	= EIP97_HIA_AIC_R_BASE;
+		offsets->hia_aic_xdr	= EIP97_HIA_AIC_xDR_BASE;
+		offsets->hia_dfe	= EIP97_HIA_DFE_BASE;
+		offsets->hia_dfe_thr	= EIP97_HIA_DFE_THR_BASE;
+		offsets->hia_dse	= EIP97_HIA_DSE_BASE;
+		offsets->hia_dse_thr	= EIP97_HIA_DSE_THR_BASE;
+		offsets->hia_gen_cfg	= EIP97_HIA_GEN_CFG_BASE;
+		offsets->pe		= EIP97_PE_BASE;
+	}
+}
+
 static int safexcel_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -780,6 +883,9 @@ static int safexcel_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	priv->dev = dev;
+	priv->version = (enum safexcel_eip_version)of_device_get_match_data(dev);
+
+	safexcel_init_register_offsets(priv);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	priv->base = devm_ioremap_resource(dev, res);
@@ -838,6 +944,7 @@ static int safexcel_probe(struct platform_device *pdev)
 
 		snprintf(irq_name, 6, "ring%d", i);
 		irq = safexcel_request_ring_irq(pdev, irq_name, safexcel_irq_ring,
+						safexcel_irq_ring_thread,
 						ring_irq);
 		if (irq < 0) {
 			ret = irq;
@@ -846,7 +953,7 @@ static int safexcel_probe(struct platform_device *pdev)
 
 		priv->ring[i].work_data.priv = priv;
 		priv->ring[i].work_data.ring = i;
-		INIT_WORK(&priv->ring[i].work_data.work, safexcel_handle_result_work);
+		INIT_WORK(&priv->ring[i].work_data.work, safexcel_dequeue_work);
 
 		snprintf(wq_name, 9, "wq_ring%d", i);
 		priv->ring[i].workqueue = create_singlethread_workqueue(wq_name);
@@ -855,6 +962,9 @@ static int safexcel_probe(struct platform_device *pdev)
 			goto err_clk;
 		}
 
+		priv->ring[i].requests_left = 0;
+		priv->ring[i].busy = false;
+
 		crypto_init_queue(&priv->ring[i].queue,
 				  EIP197_DEFAULT_RING_SIZE);
 
@@ -902,7 +1012,14 @@ static int safexcel_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id safexcel_of_match_table[] = {
-	{ .compatible = "inside-secure,safexcel-eip197" },
+	{
+		.compatible = "inside-secure,safexcel-eip97",
+		.data = (void *)EIP97,
+	},
+	{
+		.compatible = "inside-secure,safexcel-eip197",
+		.data = (void *)EIP197,
+	},
 	{},
 };
 
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 304c5838c11a..4e219c21608b 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -19,64 +19,103 @@
 #define EIP197_HIA_VERSION_BE			0x35ca
 
 /* Static configuration */
-#define EIP197_DEFAULT_RING_SIZE		64
+#define EIP197_DEFAULT_RING_SIZE		400
 #define EIP197_MAX_TOKENS			5
 #define EIP197_MAX_RINGS			4
 #define EIP197_FETCH_COUNT			1
-#define EIP197_MAX_BATCH_SZ			EIP197_DEFAULT_RING_SIZE
+#define EIP197_MAX_BATCH_SZ			64
 
 #define EIP197_GFP_FLAGS(base)	((base).flags & CRYPTO_TFM_REQ_MAY_SLEEP ? \
 				 GFP_KERNEL : GFP_ATOMIC)
 
+/* Register base offsets */
+#define EIP197_HIA_AIC(priv)		((priv)->base + (priv)->offsets.hia_aic)
+#define EIP197_HIA_AIC_G(priv)		((priv)->base + (priv)->offsets.hia_aic_g)
+#define EIP197_HIA_AIC_R(priv)		((priv)->base + (priv)->offsets.hia_aic_r)
+#define EIP197_HIA_AIC_xDR(priv)	((priv)->base + (priv)->offsets.hia_aic_xdr)
+#define EIP197_HIA_DFE(priv)		((priv)->base + (priv)->offsets.hia_dfe)
+#define EIP197_HIA_DFE_THR(priv)	((priv)->base + (priv)->offsets.hia_dfe_thr)
+#define EIP197_HIA_DSE(priv)		((priv)->base + (priv)->offsets.hia_dse)
+#define EIP197_HIA_DSE_THR(priv)	((priv)->base + (priv)->offsets.hia_dse_thr)
+#define EIP197_HIA_GEN_CFG(priv)	((priv)->base + (priv)->offsets.hia_gen_cfg)
+#define EIP197_PE(priv)			((priv)->base + (priv)->offsets.pe)
+
+/* EIP197 base offsets */
+#define EIP197_HIA_AIC_BASE		0x90000
+#define EIP197_HIA_AIC_G_BASE		0x90000
+#define EIP197_HIA_AIC_R_BASE		0x90800
+#define EIP197_HIA_AIC_xDR_BASE		0x80000
+#define EIP197_HIA_DFE_BASE		0x8c000
+#define EIP197_HIA_DFE_THR_BASE		0x8c040
+#define EIP197_HIA_DSE_BASE		0x8d000
+#define EIP197_HIA_DSE_THR_BASE		0x8d040
+#define EIP197_HIA_GEN_CFG_BASE		0xf0000
+#define EIP197_PE_BASE			0xa0000
+
+/* EIP97 base offsets */
+#define EIP97_HIA_AIC_BASE		0x0
+#define EIP97_HIA_AIC_G_BASE		0x0
+#define EIP97_HIA_AIC_R_BASE		0x0
+#define EIP97_HIA_AIC_xDR_BASE		0x0
+#define EIP97_HIA_DFE_BASE		0xf000
+#define EIP97_HIA_DFE_THR_BASE		0xf200
+#define EIP97_HIA_DSE_BASE		0xf400
+#define EIP97_HIA_DSE_THR_BASE		0xf600
+#define EIP97_HIA_GEN_CFG_BASE		0x10000
+#define EIP97_PE_BASE			0x10000
+
 /* CDR/RDR register offsets */
-#define EIP197_HIA_xDR_OFF(r)			(0x80000 + (r) * 0x1000)
-#define EIP197_HIA_CDR(r)			(EIP197_HIA_xDR_OFF(r))
-#define EIP197_HIA_RDR(r)			(EIP197_HIA_xDR_OFF(r) + 0x800)
-#define EIP197_HIA_xDR_RING_BASE_ADDR_LO	0x0
-#define EIP197_HIA_xDR_RING_BASE_ADDR_HI	0x4
-#define EIP197_HIA_xDR_RING_SIZE		0x18
-#define EIP197_HIA_xDR_DESC_SIZE		0x1c
-#define EIP197_HIA_xDR_CFG			0x20
-#define EIP197_HIA_xDR_DMA_CFG			0x24
-#define EIP197_HIA_xDR_THRESH			0x28
-#define EIP197_HIA_xDR_PREP_COUNT		0x2c
-#define EIP197_HIA_xDR_PROC_COUNT		0x30
-#define EIP197_HIA_xDR_PREP_PNTR		0x34
-#define EIP197_HIA_xDR_PROC_PNTR		0x38
-#define EIP197_HIA_xDR_STAT			0x3c
+#define EIP197_HIA_xDR_OFF(priv, r)		(EIP197_HIA_AIC_xDR(priv) + (r) * 0x1000)
+#define EIP197_HIA_CDR(priv, r)			(EIP197_HIA_xDR_OFF(priv, r))
+#define EIP197_HIA_RDR(priv, r)			(EIP197_HIA_xDR_OFF(priv, r) + 0x800)
+#define EIP197_HIA_xDR_RING_BASE_ADDR_LO	0x0000
+#define EIP197_HIA_xDR_RING_BASE_ADDR_HI	0x0004
+#define EIP197_HIA_xDR_RING_SIZE		0x0018
+#define EIP197_HIA_xDR_DESC_SIZE		0x001c
+#define EIP197_HIA_xDR_CFG			0x0020
+#define EIP197_HIA_xDR_DMA_CFG			0x0024
+#define EIP197_HIA_xDR_THRESH			0x0028
+#define EIP197_HIA_xDR_PREP_COUNT		0x002c
+#define EIP197_HIA_xDR_PROC_COUNT		0x0030
+#define EIP197_HIA_xDR_PREP_PNTR		0x0034
+#define EIP197_HIA_xDR_PROC_PNTR		0x0038
+#define EIP197_HIA_xDR_STAT			0x003c
 
 /* register offsets */
-#define EIP197_HIA_DFE_CFG			0x8c000
-#define EIP197_HIA_DFE_THR_CTRL			0x8c040
-#define EIP197_HIA_DFE_THR_STAT			0x8c044
-#define EIP197_HIA_DSE_CFG			0x8d000
-#define EIP197_HIA_DSE_THR_CTRL			0x8d040
-#define EIP197_HIA_DSE_THR_STAT			0x8d044
-#define EIP197_HIA_RA_PE_CTRL			0x90010
-#define EIP197_HIA_RA_PE_STAT			0x90014
+#define EIP197_HIA_DFE_CFG			0x0000
+#define EIP197_HIA_DFE_THR_CTRL			0x0000
+#define EIP197_HIA_DFE_THR_STAT			0x0004
+#define EIP197_HIA_DSE_CFG			0x0000
+#define EIP197_HIA_DSE_THR_CTRL			0x0000
+#define EIP197_HIA_DSE_THR_STAT			0x0004
+#define EIP197_HIA_RA_PE_CTRL			0x0010
+#define EIP197_HIA_RA_PE_STAT			0x0014
 #define EIP197_HIA_AIC_R_OFF(r)			((r) * 0x1000)
-#define EIP197_HIA_AIC_R_ENABLE_CTRL(r)		(0x9e808 - EIP197_HIA_AIC_R_OFF(r))
-#define EIP197_HIA_AIC_R_ENABLED_STAT(r)	(0x9e810 - EIP197_HIA_AIC_R_OFF(r))
-#define EIP197_HIA_AIC_R_ACK(r)			(0x9e810 - EIP197_HIA_AIC_R_OFF(r))
-#define EIP197_HIA_AIC_R_ENABLE_CLR(r)		(0x9e814 - EIP197_HIA_AIC_R_OFF(r))
-#define EIP197_HIA_AIC_G_ENABLE_CTRL		0x9f808
-#define EIP197_HIA_AIC_G_ENABLED_STAT		0x9f810
-#define EIP197_HIA_AIC_G_ACK			0x9f810
-#define EIP197_HIA_MST_CTRL			0x9fff4
-#define EIP197_HIA_OPTIONS			0x9fff8
-#define EIP197_HIA_VERSION			0x9fffc
-#define EIP197_PE_IN_DBUF_THRES			0xa0000
-#define EIP197_PE_IN_TBUF_THRES			0xa0100
-#define EIP197_PE_ICE_SCRATCH_RAM		0xa0800
-#define EIP197_PE_ICE_PUE_CTRL			0xa0c80
-#define EIP197_PE_ICE_SCRATCH_CTRL		0xa0d04
-#define EIP197_PE_ICE_FPP_CTRL			0xa0d80
-#define EIP197_PE_ICE_RAM_CTRL			0xa0ff0
-#define EIP197_PE_EIP96_FUNCTION_EN		0xa1004
-#define EIP197_PE_EIP96_CONTEXT_CTRL		0xa1008
-#define EIP197_PE_EIP96_CONTEXT_STAT		0xa100c
-#define EIP197_PE_OUT_DBUF_THRES		0xa1c00
-#define EIP197_PE_OUT_TBUF_THRES		0xa1d00
+#define EIP197_HIA_AIC_R_ENABLE_CTRL(r)		(0xe008 - EIP197_HIA_AIC_R_OFF(r))
+#define EIP197_HIA_AIC_R_ENABLED_STAT(r)	(0xe010 - EIP197_HIA_AIC_R_OFF(r))
+#define EIP197_HIA_AIC_R_ACK(r)			(0xe010 - EIP197_HIA_AIC_R_OFF(r))
+#define EIP197_HIA_AIC_R_ENABLE_CLR(r)		(0xe014 - EIP197_HIA_AIC_R_OFF(r))
+#define EIP197_HIA_AIC_G_ENABLE_CTRL		0xf808
+#define EIP197_HIA_AIC_G_ENABLED_STAT		0xf810
+#define EIP197_HIA_AIC_G_ACK			0xf810
+#define EIP197_HIA_MST_CTRL			0xfff4
+#define EIP197_HIA_OPTIONS			0xfff8
+#define EIP197_HIA_VERSION			0xfffc
+#define EIP197_PE_IN_DBUF_THRES			0x0000
+#define EIP197_PE_IN_TBUF_THRES			0x0100
+#define EIP197_PE_ICE_SCRATCH_RAM		0x0800
+#define EIP197_PE_ICE_PUE_CTRL			0x0c80
+#define EIP197_PE_ICE_SCRATCH_CTRL		0x0d04
+#define EIP197_PE_ICE_FPP_CTRL			0x0d80
+#define EIP197_PE_ICE_RAM_CTRL			0x0ff0
+#define EIP197_PE_EIP96_FUNCTION_EN		0x1004
+#define EIP197_PE_EIP96_CONTEXT_CTRL		0x1008
+#define EIP197_PE_EIP96_CONTEXT_STAT		0x100c
+#define EIP197_PE_OUT_DBUF_THRES		0x1c00
+#define EIP197_PE_OUT_TBUF_THRES		0x1d00
+#define EIP197_MST_CTRL				0xfff4
+
+/* EIP197-specific registers, no indirection */
 #define EIP197_CLASSIFICATION_RAMS		0xe0000
 #define EIP197_TRC_CTRL				0xf0800
 #define EIP197_TRC_LASTRES			0xf0804
@@ -90,7 +129,6 @@
 #define EIP197_TRC_ECCDATASTAT			0xf083c
 #define EIP197_TRC_ECCDATA			0xf0840
 #define EIP197_CS_RAM_CTRL			0xf7ff0
-#define EIP197_MST_CTRL				0xffff4
 
 /* EIP197_HIA_xDR_DESC_SIZE */
 #define EIP197_xDR_DESC_MODE_64BIT		BIT(31)
@@ -117,6 +155,8 @@
 #define EIP197_xDR_PREP_CLR_COUNT		BIT(31)
 
 /* EIP197_HIA_xDR_PROC_COUNT */
+#define EIP197_xDR_PROC_xD_PKT_OFFSET		24
+#define EIP197_xDR_PROC_xD_PKT_MASK		GENMASK(6, 0)
 #define EIP197_xDR_PROC_xD_COUNT(n)		((n) << 2)
 #define EIP197_xDR_PROC_xD_PKT(n)		((n) << 24)
 #define EIP197_xDR_PROC_CLR_COUNT		BIT(31)
@@ -463,12 +503,33 @@ struct safexcel_work_data {
 	int ring;
 };
 
+enum safexcel_eip_version {
+	EIP97,
+	EIP197,
+};
+
+struct safexcel_register_offsets {
+	u32 hia_aic;
+	u32 hia_aic_g;
+	u32 hia_aic_r;
+	u32 hia_aic_xdr;
+	u32 hia_dfe;
+	u32 hia_dfe_thr;
+	u32 hia_dse;
+	u32 hia_dse_thr;
+	u32 hia_gen_cfg;
+	u32 pe;
+};
+
 struct safexcel_crypto_priv {
 	void __iomem *base;
 	struct device *dev;
 	struct clk *clk;
 	struct safexcel_config config;
 
+	enum safexcel_eip_version version;
+	struct safexcel_register_offsets offsets;
+
 	/* context DMA pool */
 	struct dma_pool *context_pool;
 
@@ -489,7 +550,20 @@ struct safexcel_crypto_priv {
 		/* queue */
 		struct crypto_queue queue;
 		spinlock_t queue_lock;
-		bool need_dequeue;
+
+		/* Number of requests in the engine that needs the threshold
+		 * interrupt to be set up.
+		 */
+		int requests_left;
+
+		/* The ring is currently handling at least one request */
+		bool busy;
+
+		/* Store for current requests when bailing out of the dequeueing
+		 * function when no enough resources are available.
+		 */
+		struct crypto_async_request *req;
+		struct crypto_async_request *backlog;
 	} ring[EIP197_MAX_RINGS];
 };
 
@@ -539,7 +613,6 @@ void safexcel_free_context(struct safexcel_crypto_priv *priv,
 				  struct crypto_async_request *req,
 				  int result_sz);
 int safexcel_invalidate_cache(struct crypto_async_request *async,
-			      struct safexcel_context *ctx,
 			      struct safexcel_crypto_priv *priv,
 			      dma_addr_t ctxr_dma, int ring,
 			      struct safexcel_request *request);
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 5438552bc6d7..63a8768ed2ae 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -14,6 +14,7 @@
 
 #include <crypto/aes.h>
 #include <crypto/skcipher.h>
+#include <crypto/internal/skcipher.h>
 
 #include "safexcel.h"
 
@@ -26,13 +27,17 @@ struct safexcel_cipher_ctx {
 	struct safexcel_context base;
 	struct safexcel_crypto_priv *priv;
 
-	enum safexcel_cipher_direction direction;
 	u32 mode;
 
 	__le32 key[8];
 	unsigned int key_len;
 };
 
+struct safexcel_cipher_req {
+	enum safexcel_cipher_direction direction;
+	bool needs_inv;
+};
+
 static void safexcel_cipher_token(struct safexcel_cipher_ctx *ctx,
 				  struct crypto_async_request *async,
 				  struct safexcel_command_desc *cdesc,
@@ -64,6 +69,7 @@ static int safexcel_aes_setkey(struct crypto_skcipher *ctfm, const u8 *key,
 {
 	struct crypto_tfm *tfm = crypto_skcipher_tfm(ctfm);
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_crypto_priv *priv = ctx->priv;
 	struct crypto_aes_ctx aes;
 	int ret, i;
 
@@ -73,10 +79,12 @@ static int safexcel_aes_setkey(struct crypto_skcipher *ctfm, const u8 *key,
 		return ret;
 	}
 
-	for (i = 0; i < len / sizeof(u32); i++) {
-		if (ctx->key[i] != cpu_to_le32(aes.key_enc[i])) {
-			ctx->base.needs_inv = true;
-			break;
+	if (priv->version == EIP197 && ctx->base.ctxr_dma) {
+		for (i = 0; i < len / sizeof(u32); i++) {
+			if (ctx->key[i] != cpu_to_le32(aes.key_enc[i])) {
+				ctx->base.needs_inv = true;
+				break;
+			}
 		}
 	}
 
@@ -90,12 +98,15 @@ static int safexcel_aes_setkey(struct crypto_skcipher *ctfm, const u8 *key,
 }
 
 static int safexcel_context_control(struct safexcel_cipher_ctx *ctx,
+				    struct crypto_async_request *async,
 				    struct safexcel_command_desc *cdesc)
 {
 	struct safexcel_crypto_priv *priv = ctx->priv;
+	struct skcipher_request *req = skcipher_request_cast(async);
+	struct safexcel_cipher_req *sreq = skcipher_request_ctx(req);
 	int ctrl_size;
 
-	if (ctx->direction == SAFEXCEL_ENCRYPT)
+	if (sreq->direction == SAFEXCEL_ENCRYPT)
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_CRYPTO_OUT;
 	else
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_CRYPTO_IN;
@@ -126,9 +137,9 @@ static int safexcel_context_control(struct safexcel_cipher_ctx *ctx,
 	return 0;
 }
 
-static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
-				  struct crypto_async_request *async,
-				  bool *should_complete, int *ret)
+static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int ring,
+				      struct crypto_async_request *async,
+				      bool *should_complete, int *ret)
 {
 	struct skcipher_request *req = skcipher_request_cast(async);
 	struct safexcel_result_desc *rdesc;
@@ -238,7 +249,7 @@ static int safexcel_aes_send(struct crypto_async_request *async,
 		n_cdesc++;
 
 		if (n_cdesc == 1) {
-			safexcel_context_control(ctx, cdesc);
+			safexcel_context_control(ctx, async, cdesc);
 			safexcel_cipher_token(ctx, async, cdesc, req->cryptlen);
 		}
 
@@ -265,7 +276,6 @@ static int safexcel_aes_send(struct crypto_async_request *async,
 	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	request->req = &req->base;
-	ctx->base.handle_result = safexcel_handle_result;
 
 	*commands = n_cdesc;
 	*results = n_rdesc;
@@ -341,8 +351,6 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 
 	ring = safexcel_select_ring(priv);
 	ctx->base.ring = ring;
-	ctx->base.needs_inv = false;
-	ctx->base.send = safexcel_aes_send;
 
 	spin_lock_bh(&priv->ring[ring].queue_lock);
 	enq_ret = crypto_enqueue_request(&priv->ring[ring].queue, async);
@@ -351,14 +359,34 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 	if (enq_ret != -EINPROGRESS)
 		*ret = enq_ret;
 
-	if (!priv->ring[ring].need_dequeue)
-		safexcel_dequeue(priv, ring);
+	queue_work(priv->ring[ring].workqueue,
+		   &priv->ring[ring].work_data.work);
 
 	*should_complete = false;
 
 	return ndesc;
 }
 
+static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
+				  struct crypto_async_request *async,
+				  bool *should_complete, int *ret)
+{
+	struct skcipher_request *req = skcipher_request_cast(async);
+	struct safexcel_cipher_req *sreq = skcipher_request_ctx(req);
+	int err;
+
+	if (sreq->needs_inv) {
+		sreq->needs_inv = false;
+		err = safexcel_handle_inv_result(priv, ring, async,
+						 should_complete, ret);
+	} else {
+		err = safexcel_handle_req_result(priv, ring, async,
+						 should_complete, ret);
+	}
+
+	return err;
+}
+
 static int safexcel_cipher_send_inv(struct crypto_async_request *async,
 				    int ring, struct safexcel_request *request,
 				    int *commands, int *results)
@@ -368,9 +396,7 @@ static int safexcel_cipher_send_inv(struct crypto_async_request *async,
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret;
 
-	ctx->base.handle_result = safexcel_handle_inv_result;
-
-	ret = safexcel_invalidate_cache(async, &ctx->base, priv,
+	ret = safexcel_invalidate_cache(async, priv,
 					ctx->base.ctxr_dma, ring, request);
 	if (unlikely(ret))
 		return ret;
@@ -381,32 +407,54 @@ static int safexcel_cipher_send_inv(struct crypto_async_request *async,
 	return 0;
 }
 
+static int safexcel_send(struct crypto_async_request *async,
+			 int ring, struct safexcel_request *request,
+			 int *commands, int *results)
+{
+	struct skcipher_request *req = skcipher_request_cast(async);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct safexcel_cipher_req *sreq = skcipher_request_ctx(req);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	int ret;
+
+	BUG_ON(priv->version == EIP97 && sreq->needs_inv);
+
+	if (sreq->needs_inv)
+		ret = safexcel_cipher_send_inv(async, ring, request,
+					       commands, results);
+	else
+		ret = safexcel_aes_send(async, ring, request,
+					commands, results);
+	return ret;
+}
+
 static int safexcel_cipher_exit_inv(struct crypto_tfm *tfm)
 {
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
-	struct skcipher_request req;
+	SKCIPHER_REQUEST_ON_STACK(req, __crypto_skcipher_cast(tfm));
+	struct safexcel_cipher_req *sreq = skcipher_request_ctx(req);
 	struct safexcel_inv_result result = {};
 	int ring = ctx->base.ring;
 
-	memset(&req, 0, sizeof(struct skcipher_request));
+	memset(req, 0, sizeof(struct skcipher_request));
 
 	/* create invalidation request */
 	init_completion(&result.completion);
-	skcipher_request_set_callback(&req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-					safexcel_inv_complete, &result);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      safexcel_inv_complete, &result);
 
-	skcipher_request_set_tfm(&req, __crypto_skcipher_cast(tfm));
-	ctx = crypto_tfm_ctx(req.base.tfm);
+	skcipher_request_set_tfm(req, __crypto_skcipher_cast(tfm));
+	ctx = crypto_tfm_ctx(req->base.tfm);
 	ctx->base.exit_inv = true;
-	ctx->base.send = safexcel_cipher_send_inv;
+	sreq->needs_inv = true;
 
 	spin_lock_bh(&priv->ring[ring].queue_lock);
-	crypto_enqueue_request(&priv->ring[ring].queue, &req.base);
+	crypto_enqueue_request(&priv->ring[ring].queue, &req->base);
 	spin_unlock_bh(&priv->ring[ring].queue_lock);
 
-	if (!priv->ring[ring].need_dequeue)
-		safexcel_dequeue(priv, ring);
+	queue_work(priv->ring[ring].workqueue,
+		   &priv->ring[ring].work_data.work);
 
 	wait_for_completion_interruptible(&result.completion);
 
@@ -424,19 +472,21 @@ static int safexcel_aes(struct skcipher_request *req,
 			enum safexcel_cipher_direction dir, u32 mode)
 {
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct safexcel_cipher_req *sreq = skcipher_request_ctx(req);
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret, ring;
 
-	ctx->direction = dir;
+	sreq->needs_inv = false;
+	sreq->direction = dir;
 	ctx->mode = mode;
 
 	if (ctx->base.ctxr) {
-		if (ctx->base.needs_inv)
-			ctx->base.send = safexcel_cipher_send_inv;
+		if (priv->version == EIP197 && ctx->base.needs_inv) {
+			sreq->needs_inv = true;
+			ctx->base.needs_inv = false;
+		}
 	} else {
 		ctx->base.ring = safexcel_select_ring(priv);
-		ctx->base.send = safexcel_aes_send;
-
 		ctx->base.ctxr = dma_pool_zalloc(priv->context_pool,
 						 EIP197_GFP_FLAGS(req->base),
 						 &ctx->base.ctxr_dma);
@@ -450,8 +500,8 @@ static int safexcel_aes(struct skcipher_request *req,
 	ret = crypto_enqueue_request(&priv->ring[ring].queue, &req->base);
 	spin_unlock_bh(&priv->ring[ring].queue_lock);
 
-	if (!priv->ring[ring].need_dequeue)
-		safexcel_dequeue(priv, ring);
+	queue_work(priv->ring[ring].workqueue,
+		   &priv->ring[ring].work_data.work);
 
 	return ret;
 }
@@ -476,6 +526,11 @@ static int safexcel_skcipher_cra_init(struct crypto_tfm *tfm)
 			     alg.skcipher.base);
 
 	ctx->priv = tmpl->priv;
+	ctx->base.send = safexcel_send;
+	ctx->base.handle_result = safexcel_handle_result;
+
+	crypto_skcipher_set_reqsize(__crypto_skcipher_cast(tfm),
+				    sizeof(struct safexcel_cipher_req));
 
 	return 0;
 }
@@ -494,9 +549,14 @@ static void safexcel_skcipher_cra_exit(struct crypto_tfm *tfm)
 
 	memzero_explicit(ctx->base.ctxr->data, 8 * sizeof(u32));
 
-	ret = safexcel_cipher_exit_inv(tfm);
-	if (ret)
-		dev_warn(priv->dev, "cipher: invalidation error %d\n", ret);
+	if (priv->version == EIP197) {
+		ret = safexcel_cipher_exit_inv(tfm);
+		if (ret)
+			dev_warn(priv->dev, "cipher: invalidation error %d\n", ret);
+	} else {
+		dma_pool_free(priv->context_pool, ctx->base.ctxr,
+			      ctx->base.ctxr_dma);
+	}
 }
 
 struct safexcel_alg_template safexcel_alg_ecb_aes = {
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 74feb6227101..122a2a58e98f 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -14,7 +14,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/dmapool.h>
 
-
 #include "safexcel.h"
 
 struct safexcel_ahash_ctx {
@@ -32,9 +31,12 @@ struct safexcel_ahash_req {
 	bool last_req;
 	bool finish;
 	bool hmac;
+	bool needs_inv;
+
+	int nents;
 
 	u8 state_sz;    /* expected sate size, only set once */
-	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)];
+	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)] __aligned(sizeof(u32));
 
 	u64 len;
 	u64 processed;
@@ -119,15 +121,15 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 	}
 }
 
-static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
-				  struct crypto_async_request *async,
-				  bool *should_complete, int *ret)
+static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int ring,
+				      struct crypto_async_request *async,
+				      bool *should_complete, int *ret)
 {
 	struct safexcel_result_desc *rdesc;
 	struct ahash_request *areq = ahash_request_cast(async);
 	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
 	struct safexcel_ahash_req *sreq = ahash_request_ctx(areq);
-	int cache_len, result_sz = sreq->state_sz;
+	int cache_len;
 
 	*ret = 0;
 
@@ -148,11 +150,13 @@ static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
 	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	if (sreq->finish)
-		result_sz = crypto_ahash_digestsize(ahash);
-	memcpy(sreq->state, areq->result, result_sz);
+		memcpy(areq->result, sreq->state,
+		       crypto_ahash_digestsize(ahash));
 
-	dma_unmap_sg(priv->dev, areq->src,
-		     sg_nents_for_len(areq->src, areq->nbytes), DMA_TO_DEVICE);
+	if (sreq->nents) {
+		dma_unmap_sg(priv->dev, areq->src, sreq->nents, DMA_TO_DEVICE);
+		sreq->nents = 0;
+	}
 
 	safexcel_free_context(priv, async, sreq->state_sz);
 
@@ -165,9 +169,9 @@ static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
 	return 1;
 }
 
-static int safexcel_ahash_send(struct crypto_async_request *async, int ring,
-			       struct safexcel_request *request, int *commands,
-			       int *results)
+static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
+				   struct safexcel_request *request,
+				   int *commands, int *results)
 {
 	struct ahash_request *areq = ahash_request_cast(async);
 	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
@@ -177,7 +181,7 @@ static int safexcel_ahash_send(struct crypto_async_request *async, int ring,
 	struct safexcel_command_desc *cdesc, *first_cdesc = NULL;
 	struct safexcel_result_desc *rdesc;
 	struct scatterlist *sg;
-	int i, nents, queued, len, cache_len, extra, n_cdesc = 0, ret = 0;
+	int i, queued, len, cache_len, extra, n_cdesc = 0, ret = 0;
 
 	queued = len = req->len - req->processed;
 	if (queued < crypto_ahash_blocksize(ahash))
@@ -185,17 +189,31 @@ static int safexcel_ahash_send(struct crypto_async_request *async, int ring,
 	else
 		cache_len = queued - areq->nbytes;
 
-	/*
-	 * If this is not the last request and the queued data does not fit
-	 * into full blocks, cache it for the next send() call.
-	 */
-	extra = queued & (crypto_ahash_blocksize(ahash) - 1);
-	if (!req->last_req && extra) {
-		sg_pcopy_to_buffer(areq->src, sg_nents(areq->src),
-				   req->cache_next, extra, areq->nbytes - extra);
-
-		queued -= extra;
-		len -= extra;
+	if (!req->last_req) {
+		/* If this is not the last request and the queued data does not
+		 * fit into full blocks, cache it for the next send() call.
+		 */
+		extra = queued & (crypto_ahash_blocksize(ahash) - 1);
+		if (!extra)
+			/* If this is not the last request and the queued data
+			 * is a multiple of a block, cache the last one for now.
+			 */
+			extra = queued - crypto_ahash_blocksize(ahash);
+
+		if (extra) {
+			sg_pcopy_to_buffer(areq->src, sg_nents(areq->src),
+					   req->cache_next, extra,
+					   areq->nbytes - extra);
+
+			queued -= extra;
+			len -= extra;
+
+			if (!queued) {
+				*commands = 0;
+				*results = 0;
+				return 0;
+			}
+		}
 	}
 
 	spin_lock_bh(&priv->ring[ring].egress_lock);
@@ -233,15 +251,15 @@ static int safexcel_ahash_send(struct crypto_async_request *async, int ring,
 	}
 
 	/* Now handle the current ahash request buffer(s) */
-	nents = dma_map_sg(priv->dev, areq->src,
-		       sg_nents_for_len(areq->src, areq->nbytes),
-		       DMA_TO_DEVICE);
-	if (!nents) {
+	req->nents = dma_map_sg(priv->dev, areq->src,
+				sg_nents_for_len(areq->src, areq->nbytes),
+				DMA_TO_DEVICE);
+	if (!req->nents) {
 		ret = -ENOMEM;
 		goto cdesc_rollback;
 	}
 
-	for_each_sg(areq->src, sg, nents, i) {
+	for_each_sg(areq->src, sg, req->nents, i) {
 		int sglen = sg_dma_len(sg);
 
 		/* Do not overflow the request */
@@ -273,7 +291,7 @@ send_command:
 	/* Add the token */
 	safexcel_hash_token(first_cdesc, len, req->state_sz);
 
-	ctx->base.result_dma = dma_map_single(priv->dev, areq->result,
+	ctx->base.result_dma = dma_map_single(priv->dev, req->state,
 					      req->state_sz, DMA_FROM_DEVICE);
 	if (dma_mapping_error(priv->dev, ctx->base.result_dma)) {
 		ret = -EINVAL;
@@ -292,7 +310,6 @@ send_command:
 
 	req->processed += len;
 	request->req = &areq->base;
-	ctx->base.handle_result = safexcel_handle_result;
 
 	*commands = n_cdesc;
 	*results = 1;
@@ -374,8 +391,6 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 
 	ring = safexcel_select_ring(priv);
 	ctx->base.ring = ring;
-	ctx->base.needs_inv = false;
-	ctx->base.send = safexcel_ahash_send;
 
 	spin_lock_bh(&priv->ring[ring].queue_lock);
 	enq_ret = crypto_enqueue_request(&priv->ring[ring].queue, async);
@@ -384,14 +399,36 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 	if (enq_ret != -EINPROGRESS)
 		*ret = enq_ret;
 
-	if (!priv->ring[ring].need_dequeue)
-		safexcel_dequeue(priv, ring);
+	queue_work(priv->ring[ring].workqueue,
+		   &priv->ring[ring].work_data.work);
 
 	*should_complete = false;
 
 	return 1;
 }
 
+static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
+				  struct crypto_async_request *async,
+				  bool *should_complete, int *ret)
+{
+	struct ahash_request *areq = ahash_request_cast(async);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+	int err;
+
+	BUG_ON(priv->version == EIP97 && req->needs_inv);
+
+	if (req->needs_inv) {
+		req->needs_inv = false;
+		err = safexcel_handle_inv_result(priv, ring, async,
+						 should_complete, ret);
+	} else {
+		err = safexcel_handle_req_result(priv, ring, async,
+						 should_complete, ret);
+	}
+
+	return err;
+}
+
 static int safexcel_ahash_send_inv(struct crypto_async_request *async,
 				   int ring, struct safexcel_request *request,
 				   int *commands, int *results)
@@ -400,8 +437,7 @@ static int safexcel_ahash_send_inv(struct crypto_async_request *async,
 	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
 	int ret;
 
-	ctx->base.handle_result = safexcel_handle_inv_result;
-	ret = safexcel_invalidate_cache(async, &ctx->base, ctx->priv,
+	ret = safexcel_invalidate_cache(async, ctx->priv,
 					ctx->base.ctxr_dma, ring, request);
 	if (unlikely(ret))
 		return ret;
@@ -412,32 +448,50 @@ static int safexcel_ahash_send_inv(struct crypto_async_request *async,
 	return 0;
 }
 
+static int safexcel_ahash_send(struct crypto_async_request *async,
+			       int ring, struct safexcel_request *request,
+			       int *commands, int *results)
+{
+	struct ahash_request *areq = ahash_request_cast(async);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+	int ret;
+
+	if (req->needs_inv)
+		ret = safexcel_ahash_send_inv(async, ring, request,
+					      commands, results);
+	else
+		ret = safexcel_ahash_send_req(async, ring, request,
+					      commands, results);
+	return ret;
+}
+
 static int safexcel_ahash_exit_inv(struct crypto_tfm *tfm)
 {
 	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
-	struct ahash_request req;
+	AHASH_REQUEST_ON_STACK(req, __crypto_ahash_cast(tfm));
+	struct safexcel_ahash_req *rctx = ahash_request_ctx(req);
 	struct safexcel_inv_result result = {};
 	int ring = ctx->base.ring;
 
-	memset(&req, 0, sizeof(struct ahash_request));
+	memset(req, 0, sizeof(struct ahash_request));
 
 	/* create invalidation request */
 	init_completion(&result.completion);
-	ahash_request_set_callback(&req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				   safexcel_inv_complete, &result);
 
-	ahash_request_set_tfm(&req, __crypto_ahash_cast(tfm));
-	ctx = crypto_tfm_ctx(req.base.tfm);
+	ahash_request_set_tfm(req, __crypto_ahash_cast(tfm));
+	ctx = crypto_tfm_ctx(req->base.tfm);
 	ctx->base.exit_inv = true;
-	ctx->base.send = safexcel_ahash_send_inv;
+	rctx->needs_inv = true;
 
 	spin_lock_bh(&priv->ring[ring].queue_lock);
-	crypto_enqueue_request(&priv->ring[ring].queue, &req.base);
+	crypto_enqueue_request(&priv->ring[ring].queue, &req->base);
 	spin_unlock_bh(&priv->ring[ring].queue_lock);
 
-	if (!priv->ring[ring].need_dequeue)
-		safexcel_dequeue(priv, ring);
+	queue_work(priv->ring[ring].workqueue,
+		   &priv->ring[ring].work_data.work);
 
 	wait_for_completion_interruptible(&result.completion);
 
@@ -450,13 +504,23 @@ static int safexcel_ahash_exit_inv(struct crypto_tfm *tfm)
 	return 0;
 }
 
+/* safexcel_ahash_cache: cache data until at least one request can be sent to
+ * the engine, aka. when there is at least 1 block size in the pipe.
+ */
 static int safexcel_ahash_cache(struct ahash_request *areq)
 {
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
 	int queued, cache_len;
 
+	/* cache_len: everyting accepted by the driver but not sent yet,
+	 * tot sz handled by update() - last req sz - tot sz handled by send()
+	 */
 	cache_len = req->len - areq->nbytes - req->processed;
+	/* queued: everything accepted by the driver which will be handled by
+	 * the next send() calls.
+	 * tot sz handled by update() - tot sz handled by send()
+	 */
 	queued = req->len - req->processed;
 
 	/*
@@ -470,7 +534,7 @@ static int safexcel_ahash_cache(struct ahash_request *areq)
 		return areq->nbytes;
 	}
 
-	/* We could'nt cache all the data */
+	/* We couldn't cache all the data */
 	return -E2BIG;
 }
 
@@ -481,14 +545,23 @@ static int safexcel_ahash_enqueue(struct ahash_request *areq)
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret, ring;
 
-	ctx->base.send = safexcel_ahash_send;
-
-	if (req->processed && ctx->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED)
-		ctx->base.needs_inv = safexcel_ahash_needs_inv_get(areq);
+	req->needs_inv = false;
 
 	if (ctx->base.ctxr) {
-		if (ctx->base.needs_inv)
-			ctx->base.send = safexcel_ahash_send_inv;
+		if (priv->version == EIP197 &&
+		    !ctx->base.needs_inv && req->processed &&
+		    ctx->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED)
+			/* We're still setting needs_inv here, even though it is
+			 * cleared right away, because the needs_inv flag can be
+			 * set in other functions and we want to keep the same
+			 * logic.
+			 */
+			ctx->base.needs_inv = safexcel_ahash_needs_inv_get(areq);
+
+		if (ctx->base.needs_inv) {
+			ctx->base.needs_inv = false;
+			req->needs_inv = true;
+		}
 	} else {
 		ctx->base.ring = safexcel_select_ring(priv);
 		ctx->base.ctxr = dma_pool_zalloc(priv->context_pool,
@@ -504,8 +577,8 @@ static int safexcel_ahash_enqueue(struct ahash_request *areq)
 	ret = crypto_enqueue_request(&priv->ring[ring].queue, &areq->base);
 	spin_unlock_bh(&priv->ring[ring].queue_lock);
 
-	if (!priv->ring[ring].need_dequeue)
-		safexcel_dequeue(priv, ring);
+	queue_work(priv->ring[ring].workqueue,
+		   &priv->ring[ring].work_data.work);
 
 	return ret;
 }
@@ -588,7 +661,6 @@ static int safexcel_ahash_export(struct ahash_request *areq, void *out)
 	export->processed = req->processed;
 
 	memcpy(export->state, req->state, req->state_sz);
-	memset(export->cache, 0, crypto_ahash_blocksize(ahash));
 	memcpy(export->cache, req->cache, crypto_ahash_blocksize(ahash));
 
 	return 0;
@@ -622,6 +694,8 @@ static int safexcel_ahash_cra_init(struct crypto_tfm *tfm)
 			     struct safexcel_alg_template, alg.ahash);
 
 	ctx->priv = tmpl->priv;
+	ctx->base.send = safexcel_ahash_send;
+	ctx->base.handle_result = safexcel_handle_result;
 
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
 				 sizeof(struct safexcel_ahash_req));
@@ -668,9 +742,14 @@ static void safexcel_ahash_cra_exit(struct crypto_tfm *tfm)
 	if (!ctx->base.ctxr)
 		return;
 
-	ret = safexcel_ahash_exit_inv(tfm);
-	if (ret)
-		dev_warn(priv->dev, "hash: invalidation error %d\n", ret);
+	if (priv->version == EIP197) {
+		ret = safexcel_ahash_exit_inv(tfm);
+		if (ret)
+			dev_warn(priv->dev, "hash: invalidation error %d\n", ret);
+	} else {
+		dma_pool_free(priv->context_pool, ctx->base.ctxr,
+			      ctx->base.ctxr_dma);
+	}
 }
 
 struct safexcel_alg_template safexcel_alg_sha1 = {
@@ -809,7 +888,7 @@ static int safexcel_hmac_init_iv(struct ahash_request *areq,
 	req->last_req = true;
 
 	ret = crypto_ahash_update(areq);
-	if (ret && ret != -EINPROGRESS)
+	if (ret && ret != -EINPROGRESS && ret != -EBUSY)
 		return ret;
 
 	wait_for_completion_interruptible(&result.completion);
@@ -874,6 +953,7 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
 				     unsigned int keylen)
 {
 	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+	struct safexcel_crypto_priv *priv = ctx->priv;
 	struct safexcel_ahash_export_state istate, ostate;
 	int ret, i;
 
@@ -881,11 +961,13 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
 	if (ret)
 		return ret;
 
-	for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(u32); i++) {
-		if (ctx->ipad[i] != le32_to_cpu(istate.state[i]) ||
-		    ctx->opad[i] != le32_to_cpu(ostate.state[i])) {
-			ctx->base.needs_inv = true;
-			break;
+	if (priv->version == EIP197 && ctx->base.ctxr) {
+		for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(u32); i++) {
+			if (ctx->ipad[i] != le32_to_cpu(istate.state[i]) ||
+			    ctx->opad[i] != le32_to_cpu(ostate.state[i])) {
+				ctx->base.needs_inv = true;
+				break;
+			}
 		}
 	}
 
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 8705b28eb02c..717a26607bdb 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -260,12 +260,11 @@ static int setup_crypt_desc(void)
 {
 	struct device *dev = &pdev->dev;
 	BUILD_BUG_ON(sizeof(struct crypt_ctl) != 64);
-	crypt_virt = dma_alloc_coherent(dev,
-			NPE_QLEN * sizeof(struct crypt_ctl),
-			&crypt_phys, GFP_ATOMIC);
+	crypt_virt = dma_zalloc_coherent(dev,
+					 NPE_QLEN * sizeof(struct crypt_ctl),
+					 &crypt_phys, GFP_ATOMIC);
 	if (!crypt_virt)
 		return -ENOMEM;
-	memset(crypt_virt, 0, NPE_QLEN * sizeof(struct crypt_ctl));
 	return 0;
 }
 
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index 293832488cc9..aca2373fa1de 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -15,6 +15,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/genalloc.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -24,6 +25,7 @@
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/dma-direct.h> /* XXX: drivers shall never use this directly! */
 #include <linux/clk.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
@@ -409,8 +411,11 @@ static int mv_cesa_get_sram(struct platform_device *pdev, int idx)
 	if (IS_ERR(engine->sram))
 		return PTR_ERR(engine->sram);
 
-	engine->sram_dma = phys_to_dma(cesa->dev,
-				       (phys_addr_t)res->start);
+	engine->sram_dma = dma_map_resource(cesa->dev, res->start,
+					    cesa->sram_size,
+					    DMA_BIDIRECTIONAL, 0);
+	if (dma_mapping_error(cesa->dev, engine->sram_dma))
+		return -ENOMEM;
 
 	return 0;
 }
@@ -420,11 +425,12 @@ static void mv_cesa_put_sram(struct platform_device *pdev, int idx)
 	struct mv_cesa_dev *cesa = platform_get_drvdata(pdev);
 	struct mv_cesa_engine *engine = &cesa->engines[idx];
 
-	if (!engine->pool)
-		return;
-
-	gen_pool_free(engine->pool, (unsigned long)engine->sram,
-		      cesa->sram_size);
+	if (engine->pool)
+		gen_pool_free(engine->pool, (unsigned long)engine->sram,
+			      cesa->sram_size);
+	else
+		dma_unmap_resource(cesa->dev, engine->sram_dma,
+				   cesa->sram_size, DMA_BIDIRECTIONAL, 0);
 }
 
 static int mv_cesa_probe(struct platform_device *pdev)
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index 48de52cf2ecc..662e709812cc 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -1625,6 +1625,7 @@ static int queue_cache_init(void)
 					  CWQ_ENTRY_SIZE, 0, NULL);
 	if (!queue_cache[HV_NCS_QTYPE_CWQ - 1]) {
 		kmem_cache_destroy(queue_cache[HV_NCS_QTYPE_MAU - 1]);
+		queue_cache[HV_NCS_QTYPE_MAU - 1] = NULL;
 		return -ENOMEM;
 	}
 	return 0;
@@ -1634,6 +1635,8 @@ static void queue_cache_destroy(void)
 {
 	kmem_cache_destroy(queue_cache[HV_NCS_QTYPE_MAU - 1]);
 	kmem_cache_destroy(queue_cache[HV_NCS_QTYPE_CWQ - 1]);
+	queue_cache[HV_NCS_QTYPE_MAU - 1] = NULL;
+	queue_cache[HV_NCS_QTYPE_CWQ - 1] = NULL;
 }
 
 static long spu_queue_register_workfn(void *arg)
diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c
index f2246a5abcf6..1e87637c412d 100644
--- a/drivers/crypto/nx/nx-842-powernv.c
+++ b/drivers/crypto/nx/nx-842-powernv.c
@@ -743,8 +743,8 @@ static int nx842_open_percpu_txwins(void)
 		}
 
 		if (!per_cpu(cpu_txwin, i)) {
-			/* shoudn't happen, Each chip will have NX engine */
-			pr_err("NX engine is not availavle for CPU %d\n", i);
+			/* shouldn't happen, Each chip will have NX engine */
+			pr_err("NX engine is not available for CPU %d\n", i);
 			return -EINVAL;
 		}
 	}
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index 5a6dc53b2b9d..4ef52c9d72fc 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -1618,7 +1618,7 @@ MODULE_DEVICE_TABLE(of, spacc_of_id_table);
 
 static int spacc_probe(struct platform_device *pdev)
 {
-	int i, err, ret = -EINVAL;
+	int i, err, ret;
 	struct resource *mem, *irq;
 	struct device_node *np = pdev->dev.of_node;
 	struct spacc_engine *engine = devm_kzalloc(&pdev->dev, sizeof(*engine),
@@ -1679,22 +1679,18 @@ static int spacc_probe(struct platform_device *pdev)
 	engine->clk = clk_get(&pdev->dev, "ref");
 	if (IS_ERR(engine->clk)) {
 		dev_info(&pdev->dev, "clk unavailable\n");
-		device_remove_file(&pdev->dev, &dev_attr_stat_irq_thresh);
 		return PTR_ERR(engine->clk);
 	}
 
 	if (clk_prepare_enable(engine->clk)) {
 		dev_info(&pdev->dev, "unable to prepare/enable clk\n");
-		clk_put(engine->clk);
-		return -EIO;
+		ret = -EIO;
+		goto err_clk_put;
 	}
 
-	err = device_create_file(&pdev->dev, &dev_attr_stat_irq_thresh);
-	if (err) {
-		clk_disable_unprepare(engine->clk);
-		clk_put(engine->clk);
-		return err;
-	}
+	ret = device_create_file(&pdev->dev, &dev_attr_stat_irq_thresh);
+	if (ret)
+		goto err_clk_disable;
 
 
 	/*
@@ -1725,6 +1721,7 @@ static int spacc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, engine);
 
+	ret = -EINVAL;
 	INIT_LIST_HEAD(&engine->registered_algs);
 	for (i = 0; i < engine->num_algs; ++i) {
 		engine->algs[i].engine = engine;
@@ -1759,6 +1756,16 @@ static int spacc_probe(struct platform_device *pdev)
 				engine->aeads[i].alg.base.cra_name);
 	}
 
+	if (!ret)
+		return 0;
+
+	del_timer_sync(&engine->packet_timeout);
+	device_remove_file(&pdev->dev, &dev_attr_stat_irq_thresh);
+err_clk_disable:
+	clk_disable_unprepare(engine->clk);
+err_clk_put:
+	clk_put(engine->clk);
+
 	return ret;
 }
 
diff --git a/drivers/crypto/qat/qat_common/qat_hal.c b/drivers/crypto/qat/qat_common/qat_hal.c
index 8c4fd255a601..ff149e176f64 100644
--- a/drivers/crypto/qat/qat_common/qat_hal.c
+++ b/drivers/crypto/qat/qat_common/qat_hal.c
@@ -117,19 +117,19 @@ void qat_hal_set_live_ctx(struct icp_qat_fw_loader_handle *handle,
 
 #define CSR_RETRY_TIMES 500
 static int qat_hal_rd_ae_csr(struct icp_qat_fw_loader_handle *handle,
-			     unsigned char ae, unsigned int csr,
-			     unsigned int *value)
+			     unsigned char ae, unsigned int csr)
 {
 	unsigned int iterations = CSR_RETRY_TIMES;
+	int value;
 
 	do {
-		*value = GET_AE_CSR(handle, ae, csr);
+		value = GET_AE_CSR(handle, ae, csr);
 		if (!(GET_AE_CSR(handle, ae, LOCAL_CSR_STATUS) & LCS_STATUS))
-			return 0;
+			return value;
 	} while (iterations--);
 
 	pr_err("QAT: Read CSR timeout\n");
-	return -EFAULT;
+	return 0;
 }
 
 static int qat_hal_wr_ae_csr(struct icp_qat_fw_loader_handle *handle,
@@ -154,9 +154,9 @@ static void qat_hal_get_wakeup_event(struct icp_qat_fw_loader_handle *handle,
 {
 	unsigned int cur_ctx;
 
-	qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER, &cur_ctx);
+	cur_ctx = qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER);
 	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, ctx);
-	qat_hal_rd_ae_csr(handle, ae, CTX_WAKEUP_EVENTS_INDIRECT, events);
+	*events = qat_hal_rd_ae_csr(handle, ae, CTX_WAKEUP_EVENTS_INDIRECT);
 	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, cur_ctx);
 }
 
@@ -169,13 +169,13 @@ static int qat_hal_wait_cycles(struct icp_qat_fw_loader_handle *handle,
 	int times = MAX_RETRY_TIMES;
 	int elapsed_cycles = 0;
 
-	qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT, &base_cnt);
+	base_cnt = qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT);
 	base_cnt &= 0xffff;
 	while ((int)cycles > elapsed_cycles && times--) {
 		if (chk_inactive)
-			qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS, &csr);
+			csr = qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS);
 
-		qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT, &cur_cnt);
+		cur_cnt = qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT);
 		cur_cnt &= 0xffff;
 		elapsed_cycles = cur_cnt - base_cnt;
 
@@ -207,7 +207,7 @@ int qat_hal_set_ae_ctx_mode(struct icp_qat_fw_loader_handle *handle,
 	}
 
 	/* Sets the accelaration engine context mode to either four or eight */
-	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &csr);
+	csr = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 	csr = IGNORE_W1C_MASK & csr;
 	new_csr = (mode == 4) ?
 		SET_BIT(csr, CE_INUSE_CONTEXTS_BITPOS) :
@@ -221,7 +221,7 @@ int qat_hal_set_ae_nn_mode(struct icp_qat_fw_loader_handle *handle,
 {
 	unsigned int csr, new_csr;
 
-	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &csr);
+	csr = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 	csr &= IGNORE_W1C_MASK;
 
 	new_csr = (mode) ?
@@ -240,7 +240,7 @@ int qat_hal_set_ae_lm_mode(struct icp_qat_fw_loader_handle *handle,
 {
 	unsigned int csr, new_csr;
 
-	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &csr);
+	csr = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 	csr &= IGNORE_W1C_MASK;
 	switch (lm_type) {
 	case ICP_LMEM0:
@@ -328,7 +328,7 @@ static void qat_hal_wr_indr_csr(struct icp_qat_fw_loader_handle *handle,
 {
 	unsigned int ctx, cur_ctx;
 
-	qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER, &cur_ctx);
+	cur_ctx = qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER);
 
 	for (ctx = 0; ctx < ICP_QAT_UCLO_MAX_CTX; ctx++) {
 		if (!(ctx_mask & (1 << ctx)))
@@ -340,16 +340,18 @@ static void qat_hal_wr_indr_csr(struct icp_qat_fw_loader_handle *handle,
 	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, cur_ctx);
 }
 
-static void qat_hal_rd_indr_csr(struct icp_qat_fw_loader_handle *handle,
+static unsigned int qat_hal_rd_indr_csr(struct icp_qat_fw_loader_handle *handle,
 				unsigned char ae, unsigned char ctx,
-				unsigned int ae_csr, unsigned int *csr_val)
+				unsigned int ae_csr)
 {
-	unsigned int cur_ctx;
+	unsigned int cur_ctx, csr_val;
 
-	qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER, &cur_ctx);
+	cur_ctx = qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER);
 	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, ctx);
-	qat_hal_rd_ae_csr(handle, ae, ae_csr, csr_val);
+	csr_val = qat_hal_rd_ae_csr(handle, ae, ae_csr);
 	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, cur_ctx);
+
+	return csr_val;
 }
 
 static void qat_hal_put_sig_event(struct icp_qat_fw_loader_handle *handle,
@@ -358,7 +360,7 @@ static void qat_hal_put_sig_event(struct icp_qat_fw_loader_handle *handle,
 {
 	unsigned int ctx, cur_ctx;
 
-	qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER, &cur_ctx);
+	cur_ctx = qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER);
 	for (ctx = 0; ctx < ICP_QAT_UCLO_MAX_CTX; ctx++) {
 		if (!(ctx_mask & (1 << ctx)))
 			continue;
@@ -374,7 +376,7 @@ static void qat_hal_put_wakeup_event(struct icp_qat_fw_loader_handle *handle,
 {
 	unsigned int ctx, cur_ctx;
 
-	qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER, &cur_ctx);
+	cur_ctx = qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER);
 	for (ctx = 0; ctx < ICP_QAT_UCLO_MAX_CTX; ctx++) {
 		if (!(ctx_mask & (1 << ctx)))
 			continue;
@@ -392,13 +394,11 @@ static int qat_hal_check_ae_alive(struct icp_qat_fw_loader_handle *handle)
 	int times = MAX_RETRY_TIMES;
 
 	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
-		qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT,
-				  (unsigned int *)&base_cnt);
+		base_cnt = qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT);
 		base_cnt &= 0xffff;
 
 		do {
-			qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT,
-					  (unsigned int *)&cur_cnt);
+			cur_cnt = qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT);
 			cur_cnt &= 0xffff;
 		} while (times-- && (cur_cnt == base_cnt));
 
@@ -416,8 +416,8 @@ int qat_hal_check_ae_active(struct icp_qat_fw_loader_handle *handle,
 {
 	unsigned int enable = 0, active = 0;
 
-	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &enable);
-	qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS, &active);
+	enable = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
+	active = qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS);
 	if ((enable & (0xff << CE_ENABLE_BITPOS)) ||
 	    (active & (1 << ACS_ABO_BITPOS)))
 		return 1;
@@ -540,7 +540,7 @@ static void qat_hal_disable_ctx(struct icp_qat_fw_loader_handle *handle,
 {
 	unsigned int ctx;
 
-	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx);
+	ctx = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 	ctx &= IGNORE_W1C_MASK &
 		(~((ctx_mask & ICP_QAT_UCLO_AE_ALL_CTX) << CE_ENABLE_BITPOS));
 	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx);
@@ -583,7 +583,7 @@ void qat_hal_wr_uwords(struct icp_qat_fw_loader_handle *handle,
 	unsigned int ustore_addr;
 	unsigned int i;
 
-	qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS, &ustore_addr);
+	ustore_addr = qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS);
 	uaddr |= UA_ECS;
 	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, uaddr);
 	for (i = 0; i < words_num; i++) {
@@ -604,7 +604,7 @@ static void qat_hal_enable_ctx(struct icp_qat_fw_loader_handle *handle,
 {
 	unsigned int ctx;
 
-	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx);
+	ctx = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 	ctx &= IGNORE_W1C_MASK;
 	ctx_mask &= (ctx & CE_INUSE_CONTEXTS) ? 0x55 : 0xFF;
 	ctx |= (ctx_mask << CE_ENABLE_BITPOS);
@@ -636,10 +636,10 @@ static int qat_hal_clear_gpr(struct icp_qat_fw_loader_handle *handle)
 	int ret = 0;
 
 	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
-		qat_hal_rd_ae_csr(handle, ae, AE_MISC_CONTROL, &csr_val);
+		csr_val = qat_hal_rd_ae_csr(handle, ae, AE_MISC_CONTROL);
 		csr_val &= ~(1 << MMC_SHARE_CS_BITPOS);
 		qat_hal_wr_ae_csr(handle, ae, AE_MISC_CONTROL, csr_val);
-		qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &csr_val);
+		csr_val = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 		csr_val &= IGNORE_W1C_MASK;
 		csr_val |= CE_NN_MODE;
 		qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, csr_val);
@@ -648,7 +648,7 @@ static int qat_hal_clear_gpr(struct icp_qat_fw_loader_handle *handle)
 		qat_hal_wr_indr_csr(handle, ae, ctx_mask, CTX_STS_INDIRECT,
 				    handle->hal_handle->upc_mask &
 				    INIT_PC_VALUE);
-		qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS, &savctx);
+		savctx = qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS);
 		qat_hal_wr_ae_csr(handle, ae, ACTIVE_CTX_STATUS, 0);
 		qat_hal_put_wakeup_event(handle, ae, ctx_mask, XCWE_VOLUNTARY);
 		qat_hal_wr_indr_csr(handle, ae, ctx_mask,
@@ -760,7 +760,7 @@ int qat_hal_init(struct adf_accel_dev *accel_dev)
 	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
 		unsigned int csr_val = 0;
 
-		qat_hal_rd_ae_csr(handle, ae, SIGNATURE_ENABLE, &csr_val);
+		csr_val = qat_hal_rd_ae_csr(handle, ae, SIGNATURE_ENABLE);
 		csr_val |= 0x1;
 		qat_hal_wr_ae_csr(handle, ae, SIGNATURE_ENABLE, csr_val);
 	}
@@ -826,16 +826,16 @@ static void qat_hal_get_uwords(struct icp_qat_fw_loader_handle *handle,
 	unsigned int i, uwrd_lo, uwrd_hi;
 	unsigned int ustore_addr, misc_control;
 
-	qat_hal_rd_ae_csr(handle, ae, AE_MISC_CONTROL, &misc_control);
+	misc_control = qat_hal_rd_ae_csr(handle, ae, AE_MISC_CONTROL);
 	qat_hal_wr_ae_csr(handle, ae, AE_MISC_CONTROL,
 			  misc_control & 0xfffffffb);
-	qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS, &ustore_addr);
+	ustore_addr = qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS);
 	uaddr |= UA_ECS;
 	for (i = 0; i < words_num; i++) {
 		qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, uaddr);
 		uaddr++;
-		qat_hal_rd_ae_csr(handle, ae, USTORE_DATA_LOWER, &uwrd_lo);
-		qat_hal_rd_ae_csr(handle, ae, USTORE_DATA_UPPER, &uwrd_hi);
+		uwrd_lo = qat_hal_rd_ae_csr(handle, ae, USTORE_DATA_LOWER);
+		uwrd_hi = qat_hal_rd_ae_csr(handle, ae, USTORE_DATA_UPPER);
 		uword[i] = uwrd_hi;
 		uword[i] = (uword[i] << 0x20) | uwrd_lo;
 	}
@@ -849,7 +849,7 @@ void qat_hal_wr_umem(struct icp_qat_fw_loader_handle *handle,
 {
 	unsigned int i, ustore_addr;
 
-	qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS, &ustore_addr);
+	ustore_addr = qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS);
 	uaddr |= UA_ECS;
 	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, uaddr);
 	for (i = 0; i < words_num; i++) {
@@ -890,26 +890,27 @@ static int qat_hal_exec_micro_inst(struct icp_qat_fw_loader_handle *handle,
 		return -EINVAL;
 	}
 	/* save current context */
-	qat_hal_rd_indr_csr(handle, ae, ctx, LM_ADDR_0_INDIRECT, &ind_lm_addr0);
-	qat_hal_rd_indr_csr(handle, ae, ctx, LM_ADDR_1_INDIRECT, &ind_lm_addr1);
-	qat_hal_rd_indr_csr(handle, ae, ctx, INDIRECT_LM_ADDR_0_BYTE_INDEX,
-			    &ind_lm_addr_byte0);
-	qat_hal_rd_indr_csr(handle, ae, ctx, INDIRECT_LM_ADDR_1_BYTE_INDEX,
-			    &ind_lm_addr_byte1);
+	ind_lm_addr0 = qat_hal_rd_indr_csr(handle, ae, ctx, LM_ADDR_0_INDIRECT);
+	ind_lm_addr1 = qat_hal_rd_indr_csr(handle, ae, ctx, LM_ADDR_1_INDIRECT);
+	ind_lm_addr_byte0 = qat_hal_rd_indr_csr(handle, ae, ctx,
+						INDIRECT_LM_ADDR_0_BYTE_INDEX);
+	ind_lm_addr_byte1 = qat_hal_rd_indr_csr(handle, ae, ctx,
+						INDIRECT_LM_ADDR_1_BYTE_INDEX);
 	if (inst_num <= MAX_EXEC_INST)
 		qat_hal_get_uwords(handle, ae, 0, inst_num, savuwords);
 	qat_hal_get_wakeup_event(handle, ae, ctx, &wakeup_events);
-	qat_hal_rd_indr_csr(handle, ae, ctx, CTX_STS_INDIRECT, &savpc);
+	savpc = qat_hal_rd_indr_csr(handle, ae, ctx, CTX_STS_INDIRECT);
 	savpc = (savpc & handle->hal_handle->upc_mask) >> 0;
-	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	ctx_enables = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 	ctx_enables &= IGNORE_W1C_MASK;
-	qat_hal_rd_ae_csr(handle, ae, CC_ENABLE, &savcc);
-	qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS, &savctx);
-	qat_hal_rd_ae_csr(handle, ae, CTX_ARB_CNTL, &ctxarb_ctl);
-	qat_hal_rd_indr_csr(handle, ae, ctx, FUTURE_COUNT_SIGNAL_INDIRECT,
-			    &ind_cnt_sig);
-	qat_hal_rd_indr_csr(handle, ae, ctx, CTX_SIG_EVENTS_INDIRECT, &ind_sig);
-	qat_hal_rd_ae_csr(handle, ae, CTX_SIG_EVENTS_ACTIVE, &act_sig);
+	savcc = qat_hal_rd_ae_csr(handle, ae, CC_ENABLE);
+	savctx = qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS);
+	ctxarb_ctl = qat_hal_rd_ae_csr(handle, ae, CTX_ARB_CNTL);
+	ind_cnt_sig = qat_hal_rd_indr_csr(handle, ae, ctx,
+					  FUTURE_COUNT_SIGNAL_INDIRECT);
+	ind_sig = qat_hal_rd_indr_csr(handle, ae, ctx,
+				      CTX_SIG_EVENTS_INDIRECT);
+	act_sig = qat_hal_rd_ae_csr(handle, ae, CTX_SIG_EVENTS_ACTIVE);
 	/* execute micro codes */
 	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx_enables);
 	qat_hal_wr_uwords(handle, ae, 0, inst_num, micro_inst);
@@ -927,8 +928,8 @@ static int qat_hal_exec_micro_inst(struct icp_qat_fw_loader_handle *handle,
 	if (endpc) {
 		unsigned int ctx_status;
 
-		qat_hal_rd_indr_csr(handle, ae, ctx, CTX_STS_INDIRECT,
-				    &ctx_status);
+		ctx_status = qat_hal_rd_indr_csr(handle, ae, ctx,
+						 CTX_STS_INDIRECT);
 		*endpc = ctx_status & handle->hal_handle->upc_mask;
 	}
 	/* retore to saved context */
@@ -938,7 +939,7 @@ static int qat_hal_exec_micro_inst(struct icp_qat_fw_loader_handle *handle,
 	qat_hal_put_wakeup_event(handle, ae, (1 << ctx), wakeup_events);
 	qat_hal_wr_indr_csr(handle, ae, (1 << ctx), CTX_STS_INDIRECT,
 			    handle->hal_handle->upc_mask & savpc);
-	qat_hal_rd_ae_csr(handle, ae, AE_MISC_CONTROL, &csr_val);
+	csr_val = qat_hal_rd_ae_csr(handle, ae, AE_MISC_CONTROL);
 	newcsr_val = CLR_BIT(csr_val, MMC_SHARE_CS_BITPOS);
 	qat_hal_wr_ae_csr(handle, ae, AE_MISC_CONTROL, newcsr_val);
 	qat_hal_wr_ae_csr(handle, ae, CC_ENABLE, savcc);
@@ -986,16 +987,16 @@ static int qat_hal_rd_rel_reg(struct icp_qat_fw_loader_handle *handle,
 		insts = (uint64_t)0xA030000000ull | ((reg_addr & 0x3ff) << 10);
 		break;
 	}
-	qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS, &savctx);
-	qat_hal_rd_ae_csr(handle, ae, CTX_ARB_CNTL, &ctxarb_cntl);
-	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	savctx = qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS);
+	ctxarb_cntl = qat_hal_rd_ae_csr(handle, ae, CTX_ARB_CNTL);
+	ctx_enables = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 	ctx_enables &= IGNORE_W1C_MASK;
 	if (ctx != (savctx & ACS_ACNO))
 		qat_hal_wr_ae_csr(handle, ae, ACTIVE_CTX_STATUS,
 				  ctx & ACS_ACNO);
 	qat_hal_get_uwords(handle, ae, 0, 1, &savuword);
 	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx_enables);
-	qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS, &ustore_addr);
+	ustore_addr = qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS);
 	uaddr = UA_ECS;
 	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, uaddr);
 	insts = qat_hal_set_uword_ecc(insts);
@@ -1011,7 +1012,7 @@ static int qat_hal_rd_rel_reg(struct icp_qat_fw_loader_handle *handle,
 	 * the instruction should have been executed
 	 * prior to clearing the ECS in putUwords
 	 */
-	qat_hal_rd_ae_csr(handle, ae, ALU_OUT, data);
+	*data = qat_hal_rd_ae_csr(handle, ae, ALU_OUT);
 	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, ustore_addr);
 	qat_hal_wr_uwords(handle, ae, 0, 1, &savuword);
 	if (ctx != (savctx & ACS_ACNO))
@@ -1188,7 +1189,7 @@ static int qat_hal_put_rel_rd_xfer(struct icp_qat_fw_loader_handle *handle,
 	unsigned short mask;
 	unsigned short dr_offset = 0x10;
 
-	status = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	status = ctx_enables = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 	if (CE_INUSE_CONTEXTS & ctx_enables) {
 		if (ctx & 0x1) {
 			pr_err("QAT: bad 4-ctx mode,ctx=0x%x\n", ctx);
@@ -1238,7 +1239,7 @@ static int qat_hal_put_rel_wr_xfer(struct icp_qat_fw_loader_handle *handle,
 	const int num_inst = ARRAY_SIZE(micro_inst), code_off = 1;
 	const unsigned short gprnum = 0, dly = num_inst * 0x5;
 
-	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	ctx_enables = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 	if (CE_INUSE_CONTEXTS & ctx_enables) {
 		if (ctx & 0x1) {
 			pr_err("QAT: 4-ctx mode,ctx=0x%x\n", ctx);
@@ -1282,7 +1283,7 @@ static int qat_hal_put_rel_nn(struct icp_qat_fw_loader_handle *handle,
 	unsigned int ctx_enables;
 	int stat = 0;
 
-	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	ctx_enables = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 	ctx_enables &= IGNORE_W1C_MASK;
 	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx_enables | CE_NN_MODE);
 
@@ -1299,7 +1300,7 @@ static int qat_hal_convert_abs_to_rel(struct icp_qat_fw_loader_handle
 {
 	unsigned int ctx_enables;
 
-	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	ctx_enables = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES);
 	if (ctx_enables & CE_INUSE_CONTEXTS) {
 		/* 4-ctx mode */
 		*relreg = absreg_num & 0x1F;
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index 142c6020cec7..188f44b7eb27 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -1,17 +1,13 @@
-/*
- * Cryptographic API.
- *
- * Support for Samsung S5PV210 and Exynos HW acceleration.
- *
- * Copyright (C) 2011 NetUP Inc. All rights reserved.
- * Copyright (c) 2017 Samsung Electronics Co., Ltd. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
- *
- * Hash part based on omap-sham.c driver.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Cryptographic API.
+//
+// Support for Samsung S5PV210 and Exynos HW acceleration.
+//
+// Copyright (C) 2011 NetUP Inc. All rights reserved.
+// Copyright (c) 2017 Samsung Electronics Co., Ltd. All rights reserved.
+//
+// Hash part based on omap-sham.c driver.
 
 #include <linux/clk.h>
 #include <linux/crypto.h>
@@ -1461,7 +1457,7 @@ static void s5p_hash_tasklet_cb(unsigned long data)
 				       &dd->hash_flags)) {
 			/* hash or semi-hash ready */
 			clear_bit(HASH_FLAGS_DMA_READY, &dd->hash_flags);
-				goto finish;
+			goto finish;
 		}
 	}
 
diff --git a/drivers/crypto/stm32/Kconfig b/drivers/crypto/stm32/Kconfig
index 602332e02729..63aa78c0b12b 100644
--- a/drivers/crypto/stm32/Kconfig
+++ b/drivers/crypto/stm32/Kconfig
@@ -1,4 +1,4 @@
-config CRC_DEV_STM32
+config CRYPTO_DEV_STM32_CRC
 	tristate "Support for STM32 crc accelerators"
 	depends on ARCH_STM32
 	select CRYPTO_HASH
@@ -6,7 +6,7 @@ config CRC_DEV_STM32
           This enables support for the CRC32 hw accelerator which can be found
 	  on STMicroelectronics STM32 SOC.
 
-config HASH_DEV_STM32
+config CRYPTO_DEV_STM32_HASH
 	tristate "Support for STM32 hash accelerators"
 	depends on ARCH_STM32
 	depends on HAS_DMA
@@ -18,3 +18,12 @@ config HASH_DEV_STM32
 	help
           This enables support for the HASH hw accelerator which can be found
 	  on STMicroelectronics STM32 SOC.
+
+config CRYPTO_DEV_STM32_CRYP
+	tristate "Support for STM32 cryp accelerators"
+	depends on ARCH_STM32
+	select CRYPTO_HASH
+	select CRYPTO_ENGINE
+	help
+          This enables support for the CRYP (AES/DES/TDES) hw accelerator which
+	  can be found on STMicroelectronics STM32 SOC.
diff --git a/drivers/crypto/stm32/Makefile b/drivers/crypto/stm32/Makefile
index 73cd56cad0cc..53d1bb94b221 100644
--- a/drivers/crypto/stm32/Makefile
+++ b/drivers/crypto/stm32/Makefile
@@ -1,2 +1,3 @@
-obj-$(CONFIG_CRC_DEV_STM32) += stm32_crc32.o
-obj-$(CONFIG_HASH_DEV_STM32) += stm32-hash.o
-\ No newline at end of file
+obj-$(CONFIG_CRYPTO_DEV_STM32_CRC) += stm32_crc32.o
+obj-$(CONFIG_CRYPTO_DEV_STM32_HASH) += stm32-hash.o
+obj-$(CONFIG_CRYPTO_DEV_STM32_CRYP) += stm32-cryp.o
diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c
new file mode 100644
index 000000000000..4a06a7a665ee
--- /dev/null
+++ b/drivers/crypto/stm32/stm32-cryp.c
@@ -0,0 +1,1170 @@
+/*
+ * Copyright (C) STMicroelectronics SA 2017
+ * Author: Fabien Dessenne <fabien.dessenne@st.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#include <crypto/aes.h>
+#include <crypto/des.h>
+#include <crypto/engine.h>
+#include <crypto/scatterwalk.h>
+
+#define DRIVER_NAME             "stm32-cryp"
+
+/* Bit [0] encrypt / decrypt */
+#define FLG_ENCRYPT             BIT(0)
+/* Bit [8..1] algo & operation mode */
+#define FLG_AES                 BIT(1)
+#define FLG_DES                 BIT(2)
+#define FLG_TDES                BIT(3)
+#define FLG_ECB                 BIT(4)
+#define FLG_CBC                 BIT(5)
+#define FLG_CTR                 BIT(6)
+/* Mode mask = bits [15..0] */
+#define FLG_MODE_MASK           GENMASK(15, 0)
+
+/* Registers */
+#define CRYP_CR                 0x00000000
+#define CRYP_SR                 0x00000004
+#define CRYP_DIN                0x00000008
+#define CRYP_DOUT               0x0000000C
+#define CRYP_DMACR              0x00000010
+#define CRYP_IMSCR              0x00000014
+#define CRYP_RISR               0x00000018
+#define CRYP_MISR               0x0000001C
+#define CRYP_K0LR               0x00000020
+#define CRYP_K0RR               0x00000024
+#define CRYP_K1LR               0x00000028
+#define CRYP_K1RR               0x0000002C
+#define CRYP_K2LR               0x00000030
+#define CRYP_K2RR               0x00000034
+#define CRYP_K3LR               0x00000038
+#define CRYP_K3RR               0x0000003C
+#define CRYP_IV0LR              0x00000040
+#define CRYP_IV0RR              0x00000044
+#define CRYP_IV1LR              0x00000048
+#define CRYP_IV1RR              0x0000004C
+
+/* Registers values */
+#define CR_DEC_NOT_ENC          0x00000004
+#define CR_TDES_ECB             0x00000000
+#define CR_TDES_CBC             0x00000008
+#define CR_DES_ECB              0x00000010
+#define CR_DES_CBC              0x00000018
+#define CR_AES_ECB              0x00000020
+#define CR_AES_CBC              0x00000028
+#define CR_AES_CTR              0x00000030
+#define CR_AES_KP               0x00000038
+#define CR_AES_UNKNOWN          0xFFFFFFFF
+#define CR_ALGO_MASK            0x00080038
+#define CR_DATA32               0x00000000
+#define CR_DATA16               0x00000040
+#define CR_DATA8                0x00000080
+#define CR_DATA1                0x000000C0
+#define CR_KEY128               0x00000000
+#define CR_KEY192               0x00000100
+#define CR_KEY256               0x00000200
+#define CR_FFLUSH               0x00004000
+#define CR_CRYPEN               0x00008000
+
+#define SR_BUSY                 0x00000010
+#define SR_OFNE                 0x00000004
+
+#define IMSCR_IN                BIT(0)
+#define IMSCR_OUT               BIT(1)
+
+#define MISR_IN                 BIT(0)
+#define MISR_OUT                BIT(1)
+
+/* Misc */
+#define AES_BLOCK_32            (AES_BLOCK_SIZE / sizeof(u32))
+#define _walked_in              (cryp->in_walk.offset - cryp->in_sg->offset)
+#define _walked_out             (cryp->out_walk.offset - cryp->out_sg->offset)
+
+struct stm32_cryp_ctx {
+	struct stm32_cryp       *cryp;
+	int                     keylen;
+	u32                     key[AES_KEYSIZE_256 / sizeof(u32)];
+	unsigned long           flags;
+};
+
+struct stm32_cryp_reqctx {
+	unsigned long mode;
+};
+
+struct stm32_cryp {
+	struct list_head        list;
+	struct device           *dev;
+	void __iomem            *regs;
+	struct clk              *clk;
+	unsigned long           flags;
+	u32                     irq_status;
+	struct stm32_cryp_ctx   *ctx;
+
+	struct crypto_engine    *engine;
+
+	struct mutex            lock; /* protects req */
+	struct ablkcipher_request *req;
+
+	size_t                  hw_blocksize;
+
+	size_t                  total_in;
+	size_t                  total_in_save;
+	size_t                  total_out;
+	size_t                  total_out_save;
+
+	struct scatterlist      *in_sg;
+	struct scatterlist      *out_sg;
+	struct scatterlist      *out_sg_save;
+
+	struct scatterlist      in_sgl;
+	struct scatterlist      out_sgl;
+	bool                    sgs_copied;
+
+	int                     in_sg_len;
+	int                     out_sg_len;
+
+	struct scatter_walk     in_walk;
+	struct scatter_walk     out_walk;
+
+	u32                     last_ctr[4];
+};
+
+struct stm32_cryp_list {
+	struct list_head        dev_list;
+	spinlock_t              lock; /* protect dev_list */
+};
+
+static struct stm32_cryp_list cryp_list = {
+	.dev_list = LIST_HEAD_INIT(cryp_list.dev_list),
+	.lock     = __SPIN_LOCK_UNLOCKED(cryp_list.lock),
+};
+
+static inline bool is_aes(struct stm32_cryp *cryp)
+{
+	return cryp->flags & FLG_AES;
+}
+
+static inline bool is_des(struct stm32_cryp *cryp)
+{
+	return cryp->flags & FLG_DES;
+}
+
+static inline bool is_tdes(struct stm32_cryp *cryp)
+{
+	return cryp->flags & FLG_TDES;
+}
+
+static inline bool is_ecb(struct stm32_cryp *cryp)
+{
+	return cryp->flags & FLG_ECB;
+}
+
+static inline bool is_cbc(struct stm32_cryp *cryp)
+{
+	return cryp->flags & FLG_CBC;
+}
+
+static inline bool is_ctr(struct stm32_cryp *cryp)
+{
+	return cryp->flags & FLG_CTR;
+}
+
+static inline bool is_encrypt(struct stm32_cryp *cryp)
+{
+	return cryp->flags & FLG_ENCRYPT;
+}
+
+static inline bool is_decrypt(struct stm32_cryp *cryp)
+{
+	return !is_encrypt(cryp);
+}
+
+static inline u32 stm32_cryp_read(struct stm32_cryp *cryp, u32 ofst)
+{
+	return readl_relaxed(cryp->regs + ofst);
+}
+
+static inline void stm32_cryp_write(struct stm32_cryp *cryp, u32 ofst, u32 val)
+{
+	writel_relaxed(val, cryp->regs + ofst);
+}
+
+static inline int stm32_cryp_wait_busy(struct stm32_cryp *cryp)
+{
+	u32 status;
+
+	return readl_relaxed_poll_timeout(cryp->regs + CRYP_SR, status,
+			!(status & SR_BUSY), 10, 100000);
+}
+
+static struct stm32_cryp *stm32_cryp_find_dev(struct stm32_cryp_ctx *ctx)
+{
+	struct stm32_cryp *tmp, *cryp = NULL;
+
+	spin_lock_bh(&cryp_list.lock);
+	if (!ctx->cryp) {
+		list_for_each_entry(tmp, &cryp_list.dev_list, list) {
+			cryp = tmp;
+			break;
+		}
+		ctx->cryp = cryp;
+	} else {
+		cryp = ctx->cryp;
+	}
+
+	spin_unlock_bh(&cryp_list.lock);
+
+	return cryp;
+}
+
+static int stm32_cryp_check_aligned(struct scatterlist *sg, size_t total,
+				    size_t align)
+{
+	int len = 0;
+
+	if (!total)
+		return 0;
+
+	if (!IS_ALIGNED(total, align))
+		return -EINVAL;
+
+	while (sg) {
+		if (!IS_ALIGNED(sg->offset, sizeof(u32)))
+			return -EINVAL;
+
+		if (!IS_ALIGNED(sg->length, align))
+			return -EINVAL;
+
+		len += sg->length;
+		sg = sg_next(sg);
+	}
+
+	if (len != total)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int stm32_cryp_check_io_aligned(struct stm32_cryp *cryp)
+{
+	int ret;
+
+	ret = stm32_cryp_check_aligned(cryp->in_sg, cryp->total_in,
+				       cryp->hw_blocksize);
+	if (ret)
+		return ret;
+
+	ret = stm32_cryp_check_aligned(cryp->out_sg, cryp->total_out,
+				       cryp->hw_blocksize);
+
+	return ret;
+}
+
+static void sg_copy_buf(void *buf, struct scatterlist *sg,
+			unsigned int start, unsigned int nbytes, int out)
+{
+	struct scatter_walk walk;
+
+	if (!nbytes)
+		return;
+
+	scatterwalk_start(&walk, sg);
+	scatterwalk_advance(&walk, start);
+	scatterwalk_copychunks(buf, &walk, nbytes, out);
+	scatterwalk_done(&walk, out, 0);
+}
+
+static int stm32_cryp_copy_sgs(struct stm32_cryp *cryp)
+{
+	void *buf_in, *buf_out;
+	int pages, total_in, total_out;
+
+	if (!stm32_cryp_check_io_aligned(cryp)) {
+		cryp->sgs_copied = 0;
+		return 0;
+	}
+
+	total_in = ALIGN(cryp->total_in, cryp->hw_blocksize);
+	pages = total_in ? get_order(total_in) : 1;
+	buf_in = (void *)__get_free_pages(GFP_ATOMIC, pages);
+
+	total_out = ALIGN(cryp->total_out, cryp->hw_blocksize);
+	pages = total_out ? get_order(total_out) : 1;
+	buf_out = (void *)__get_free_pages(GFP_ATOMIC, pages);
+
+	if (!buf_in || !buf_out) {
+		dev_err(cryp->dev, "Can't allocate pages when unaligned\n");
+		cryp->sgs_copied = 0;
+		return -EFAULT;
+	}
+
+	sg_copy_buf(buf_in, cryp->in_sg, 0, cryp->total_in, 0);
+
+	sg_init_one(&cryp->in_sgl, buf_in, total_in);
+	cryp->in_sg = &cryp->in_sgl;
+	cryp->in_sg_len = 1;
+
+	sg_init_one(&cryp->out_sgl, buf_out, total_out);
+	cryp->out_sg_save = cryp->out_sg;
+	cryp->out_sg = &cryp->out_sgl;
+	cryp->out_sg_len = 1;
+
+	cryp->sgs_copied = 1;
+
+	return 0;
+}
+
+static void stm32_cryp_hw_write_iv(struct stm32_cryp *cryp, u32 *iv)
+{
+	if (!iv)
+		return;
+
+	stm32_cryp_write(cryp, CRYP_IV0LR, cpu_to_be32(*iv++));
+	stm32_cryp_write(cryp, CRYP_IV0RR, cpu_to_be32(*iv++));
+
+	if (is_aes(cryp)) {
+		stm32_cryp_write(cryp, CRYP_IV1LR, cpu_to_be32(*iv++));
+		stm32_cryp_write(cryp, CRYP_IV1RR, cpu_to_be32(*iv++));
+	}
+}
+
+static void stm32_cryp_hw_write_key(struct stm32_cryp *c)
+{
+	unsigned int i;
+	int r_id;
+
+	if (is_des(c)) {
+		stm32_cryp_write(c, CRYP_K1LR, cpu_to_be32(c->ctx->key[0]));
+		stm32_cryp_write(c, CRYP_K1RR, cpu_to_be32(c->ctx->key[1]));
+	} else {
+		r_id = CRYP_K3RR;
+		for (i = c->ctx->keylen / sizeof(u32); i > 0; i--, r_id -= 4)
+			stm32_cryp_write(c, r_id,
+					 cpu_to_be32(c->ctx->key[i - 1]));
+	}
+}
+
+static u32 stm32_cryp_get_hw_mode(struct stm32_cryp *cryp)
+{
+	if (is_aes(cryp) && is_ecb(cryp))
+		return CR_AES_ECB;
+
+	if (is_aes(cryp) && is_cbc(cryp))
+		return CR_AES_CBC;
+
+	if (is_aes(cryp) && is_ctr(cryp))
+		return CR_AES_CTR;
+
+	if (is_des(cryp) && is_ecb(cryp))
+		return CR_DES_ECB;
+
+	if (is_des(cryp) && is_cbc(cryp))
+		return CR_DES_CBC;
+
+	if (is_tdes(cryp) && is_ecb(cryp))
+		return CR_TDES_ECB;
+
+	if (is_tdes(cryp) && is_cbc(cryp))
+		return CR_TDES_CBC;
+
+	dev_err(cryp->dev, "Unknown mode\n");
+	return CR_AES_UNKNOWN;
+}
+
+static int stm32_cryp_hw_init(struct stm32_cryp *cryp)
+{
+	int ret;
+	u32 cfg, hw_mode;
+
+	/* Disable interrupt */
+	stm32_cryp_write(cryp, CRYP_IMSCR, 0);
+
+	/* Set key */
+	stm32_cryp_hw_write_key(cryp);
+
+	/* Set configuration */
+	cfg = CR_DATA8 | CR_FFLUSH;
+
+	switch (cryp->ctx->keylen) {
+	case AES_KEYSIZE_128:
+		cfg |= CR_KEY128;
+		break;
+
+	case AES_KEYSIZE_192:
+		cfg |= CR_KEY192;
+		break;
+
+	default:
+	case AES_KEYSIZE_256:
+		cfg |= CR_KEY256;
+		break;
+	}
+
+	hw_mode = stm32_cryp_get_hw_mode(cryp);
+	if (hw_mode == CR_AES_UNKNOWN)
+		return -EINVAL;
+
+	/* AES ECB/CBC decrypt: run key preparation first */
+	if (is_decrypt(cryp) &&
+	    ((hw_mode == CR_AES_ECB) || (hw_mode == CR_AES_CBC))) {
+		stm32_cryp_write(cryp, CRYP_CR, cfg | CR_AES_KP | CR_CRYPEN);
+
+		/* Wait for end of processing */
+		ret = stm32_cryp_wait_busy(cryp);
+		if (ret) {
+			dev_err(cryp->dev, "Timeout (key preparation)\n");
+			return ret;
+		}
+	}
+
+	cfg |= hw_mode;
+
+	if (is_decrypt(cryp))
+		cfg |= CR_DEC_NOT_ENC;
+
+	/* Apply config and flush (valid when CRYPEN = 0) */
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	switch (hw_mode) {
+	case CR_DES_CBC:
+	case CR_TDES_CBC:
+	case CR_AES_CBC:
+	case CR_AES_CTR:
+		stm32_cryp_hw_write_iv(cryp, (u32 *)cryp->req->info);
+		break;
+
+	default:
+		break;
+	}
+
+	/* Enable now */
+	cfg |= CR_CRYPEN;
+
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	return 0;
+}
+
+static void stm32_cryp_finish_req(struct stm32_cryp *cryp)
+{
+	int err = 0;
+
+	if (cryp->sgs_copied) {
+		void *buf_in, *buf_out;
+		int pages, len;
+
+		buf_in = sg_virt(&cryp->in_sgl);
+		buf_out = sg_virt(&cryp->out_sgl);
+
+		sg_copy_buf(buf_out, cryp->out_sg_save, 0,
+			    cryp->total_out_save, 1);
+
+		len = ALIGN(cryp->total_in_save, cryp->hw_blocksize);
+		pages = len ? get_order(len) : 1;
+		free_pages((unsigned long)buf_in, pages);
+
+		len = ALIGN(cryp->total_out_save, cryp->hw_blocksize);
+		pages = len ? get_order(len) : 1;
+		free_pages((unsigned long)buf_out, pages);
+	}
+
+	crypto_finalize_cipher_request(cryp->engine, cryp->req, err);
+	cryp->req = NULL;
+
+	memset(cryp->ctx->key, 0, cryp->ctx->keylen);
+
+	mutex_unlock(&cryp->lock);
+}
+
+static int stm32_cryp_cpu_start(struct stm32_cryp *cryp)
+{
+	/* Enable interrupt and let the IRQ handler do everything */
+	stm32_cryp_write(cryp, CRYP_IMSCR, IMSCR_IN | IMSCR_OUT);
+
+	return 0;
+}
+
+static int stm32_cryp_cra_init(struct crypto_tfm *tfm)
+{
+	tfm->crt_ablkcipher.reqsize = sizeof(struct stm32_cryp_reqctx);
+
+	return 0;
+}
+
+static int stm32_cryp_crypt(struct ablkcipher_request *req, unsigned long mode)
+{
+	struct stm32_cryp_ctx *ctx = crypto_ablkcipher_ctx(
+			crypto_ablkcipher_reqtfm(req));
+	struct stm32_cryp_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct stm32_cryp *cryp = stm32_cryp_find_dev(ctx);
+
+	if (!cryp)
+		return -ENODEV;
+
+	rctx->mode = mode;
+
+	return crypto_transfer_cipher_request_to_engine(cryp->engine, req);
+}
+
+static int stm32_cryp_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+			     unsigned int keylen)
+{
+	struct stm32_cryp_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+	memcpy(ctx->key, key, keylen);
+	ctx->keylen = keylen;
+
+	return 0;
+}
+
+static int stm32_cryp_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	if (keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_192 &&
+	    keylen != AES_KEYSIZE_256)
+		return -EINVAL;
+	else
+		return stm32_cryp_setkey(tfm, key, keylen);
+}
+
+static int stm32_cryp_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	if (keylen != DES_KEY_SIZE)
+		return -EINVAL;
+	else
+		return stm32_cryp_setkey(tfm, key, keylen);
+}
+
+static int stm32_cryp_tdes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+				  unsigned int keylen)
+{
+	if (keylen != (3 * DES_KEY_SIZE))
+		return -EINVAL;
+	else
+		return stm32_cryp_setkey(tfm, key, keylen);
+}
+
+static int stm32_cryp_aes_ecb_encrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_AES | FLG_ECB | FLG_ENCRYPT);
+}
+
+static int stm32_cryp_aes_ecb_decrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_AES | FLG_ECB);
+}
+
+static int stm32_cryp_aes_cbc_encrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_AES | FLG_CBC | FLG_ENCRYPT);
+}
+
+static int stm32_cryp_aes_cbc_decrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_AES | FLG_CBC);
+}
+
+static int stm32_cryp_aes_ctr_encrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_AES | FLG_CTR | FLG_ENCRYPT);
+}
+
+static int stm32_cryp_aes_ctr_decrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_AES | FLG_CTR);
+}
+
+static int stm32_cryp_des_ecb_encrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_DES | FLG_ECB | FLG_ENCRYPT);
+}
+
+static int stm32_cryp_des_ecb_decrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_DES | FLG_ECB);
+}
+
+static int stm32_cryp_des_cbc_encrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_DES | FLG_CBC | FLG_ENCRYPT);
+}
+
+static int stm32_cryp_des_cbc_decrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_DES | FLG_CBC);
+}
+
+static int stm32_cryp_tdes_ecb_encrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_TDES | FLG_ECB | FLG_ENCRYPT);
+}
+
+static int stm32_cryp_tdes_ecb_decrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_TDES | FLG_ECB);
+}
+
+static int stm32_cryp_tdes_cbc_encrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_TDES | FLG_CBC | FLG_ENCRYPT);
+}
+
+static int stm32_cryp_tdes_cbc_decrypt(struct ablkcipher_request *req)
+{
+	return stm32_cryp_crypt(req, FLG_TDES | FLG_CBC);
+}
+
+static int stm32_cryp_prepare_req(struct crypto_engine *engine,
+				  struct ablkcipher_request *req)
+{
+	struct stm32_cryp_ctx *ctx;
+	struct stm32_cryp *cryp;
+	struct stm32_cryp_reqctx *rctx;
+	int ret;
+
+	if (!req)
+		return -EINVAL;
+
+	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
+
+	cryp = ctx->cryp;
+
+	if (!cryp)
+		return -ENODEV;
+
+	mutex_lock(&cryp->lock);
+
+	rctx = ablkcipher_request_ctx(req);
+	rctx->mode &= FLG_MODE_MASK;
+
+	ctx->cryp = cryp;
+
+	cryp->flags = (cryp->flags & ~FLG_MODE_MASK) | rctx->mode;
+	cryp->hw_blocksize = is_aes(cryp) ? AES_BLOCK_SIZE : DES_BLOCK_SIZE;
+	cryp->ctx = ctx;
+
+	cryp->req = req;
+	cryp->total_in = req->nbytes;
+	cryp->total_out = cryp->total_in;
+
+	cryp->total_in_save = cryp->total_in;
+	cryp->total_out_save = cryp->total_out;
+
+	cryp->in_sg = req->src;
+	cryp->out_sg = req->dst;
+	cryp->out_sg_save = cryp->out_sg;
+
+	cryp->in_sg_len = sg_nents_for_len(cryp->in_sg, cryp->total_in);
+	if (cryp->in_sg_len < 0) {
+		dev_err(cryp->dev, "Cannot get in_sg_len\n");
+		ret = cryp->in_sg_len;
+		goto out;
+	}
+
+	cryp->out_sg_len = sg_nents_for_len(cryp->out_sg, cryp->total_out);
+	if (cryp->out_sg_len < 0) {
+		dev_err(cryp->dev, "Cannot get out_sg_len\n");
+		ret = cryp->out_sg_len;
+		goto out;
+	}
+
+	ret = stm32_cryp_copy_sgs(cryp);
+	if (ret)
+		goto out;
+
+	scatterwalk_start(&cryp->in_walk, cryp->in_sg);
+	scatterwalk_start(&cryp->out_walk, cryp->out_sg);
+
+	ret = stm32_cryp_hw_init(cryp);
+out:
+	if (ret)
+		mutex_unlock(&cryp->lock);
+
+	return ret;
+}
+
+static int stm32_cryp_prepare_cipher_req(struct crypto_engine *engine,
+					 struct ablkcipher_request *req)
+{
+	return stm32_cryp_prepare_req(engine, req);
+}
+
+static int stm32_cryp_cipher_one_req(struct crypto_engine *engine,
+				     struct ablkcipher_request *req)
+{
+	struct stm32_cryp_ctx *ctx = crypto_ablkcipher_ctx(
+			crypto_ablkcipher_reqtfm(req));
+	struct stm32_cryp *cryp = ctx->cryp;
+
+	if (!cryp)
+		return -ENODEV;
+
+	return stm32_cryp_cpu_start(cryp);
+}
+
+static u32 *stm32_cryp_next_out(struct stm32_cryp *cryp, u32 *dst,
+				unsigned int n)
+{
+	scatterwalk_advance(&cryp->out_walk, n);
+
+	if (unlikely(cryp->out_sg->length == _walked_out)) {
+		cryp->out_sg = sg_next(cryp->out_sg);
+		if (cryp->out_sg) {
+			scatterwalk_start(&cryp->out_walk, cryp->out_sg);
+			return (sg_virt(cryp->out_sg) + _walked_out);
+		}
+	}
+
+	return (u32 *)((u8 *)dst + n);
+}
+
+static u32 *stm32_cryp_next_in(struct stm32_cryp *cryp, u32 *src,
+			       unsigned int n)
+{
+	scatterwalk_advance(&cryp->in_walk, n);
+
+	if (unlikely(cryp->in_sg->length == _walked_in)) {
+		cryp->in_sg = sg_next(cryp->in_sg);
+		if (cryp->in_sg) {
+			scatterwalk_start(&cryp->in_walk, cryp->in_sg);
+			return (sg_virt(cryp->in_sg) + _walked_in);
+		}
+	}
+
+	return (u32 *)((u8 *)src + n);
+}
+
+static void stm32_cryp_check_ctr_counter(struct stm32_cryp *cryp)
+{
+	u32 cr;
+
+	if (unlikely(cryp->last_ctr[3] == 0xFFFFFFFF)) {
+		cryp->last_ctr[3] = 0;
+		cryp->last_ctr[2]++;
+		if (!cryp->last_ctr[2]) {
+			cryp->last_ctr[1]++;
+			if (!cryp->last_ctr[1])
+				cryp->last_ctr[0]++;
+		}
+
+		cr = stm32_cryp_read(cryp, CRYP_CR);
+		stm32_cryp_write(cryp, CRYP_CR, cr & ~CR_CRYPEN);
+
+		stm32_cryp_hw_write_iv(cryp, (u32 *)cryp->last_ctr);
+
+		stm32_cryp_write(cryp, CRYP_CR, cr);
+	}
+
+	cryp->last_ctr[0] = stm32_cryp_read(cryp, CRYP_IV0LR);
+	cryp->last_ctr[1] = stm32_cryp_read(cryp, CRYP_IV0RR);
+	cryp->last_ctr[2] = stm32_cryp_read(cryp, CRYP_IV1LR);
+	cryp->last_ctr[3] = stm32_cryp_read(cryp, CRYP_IV1RR);
+}
+
+static bool stm32_cryp_irq_read_data(struct stm32_cryp *cryp)
+{
+	unsigned int i, j;
+	u32 d32, *dst;
+	u8 *d8;
+
+	dst = sg_virt(cryp->out_sg) + _walked_out;
+
+	for (i = 0; i < cryp->hw_blocksize / sizeof(u32); i++) {
+		if (likely(cryp->total_out >= sizeof(u32))) {
+			/* Read a full u32 */
+			*dst = stm32_cryp_read(cryp, CRYP_DOUT);
+
+			dst = stm32_cryp_next_out(cryp, dst, sizeof(u32));
+			cryp->total_out -= sizeof(u32);
+		} else if (!cryp->total_out) {
+			/* Empty fifo out (data from input padding) */
+			d32 = stm32_cryp_read(cryp, CRYP_DOUT);
+		} else {
+			/* Read less than an u32 */
+			d32 = stm32_cryp_read(cryp, CRYP_DOUT);
+			d8 = (u8 *)&d32;
+
+			for (j = 0; j < cryp->total_out; j++) {
+				*((u8 *)dst) = *(d8++);
+				dst = stm32_cryp_next_out(cryp, dst, 1);
+			}
+			cryp->total_out = 0;
+		}
+	}
+
+	return !cryp->total_out || !cryp->total_in;
+}
+
+static void stm32_cryp_irq_write_block(struct stm32_cryp *cryp)
+{
+	unsigned int i, j;
+	u32 *src;
+	u8 d8[4];
+
+	src = sg_virt(cryp->in_sg) + _walked_in;
+
+	for (i = 0; i < cryp->hw_blocksize / sizeof(u32); i++) {
+		if (likely(cryp->total_in >= sizeof(u32))) {
+			/* Write a full u32 */
+			stm32_cryp_write(cryp, CRYP_DIN, *src);
+
+			src = stm32_cryp_next_in(cryp, src, sizeof(u32));
+			cryp->total_in -= sizeof(u32);
+		} else if (!cryp->total_in) {
+			/* Write padding data */
+			stm32_cryp_write(cryp, CRYP_DIN, 0);
+		} else {
+			/* Write less than an u32 */
+			memset(d8, 0, sizeof(u32));
+			for (j = 0; j < cryp->total_in; j++) {
+				d8[j] = *((u8 *)src);
+				src = stm32_cryp_next_in(cryp, src, 1);
+			}
+
+			stm32_cryp_write(cryp, CRYP_DIN, *(u32 *)d8);
+			cryp->total_in = 0;
+		}
+	}
+}
+
+static void stm32_cryp_irq_write_data(struct stm32_cryp *cryp)
+{
+	if (unlikely(!cryp->total_in)) {
+		dev_warn(cryp->dev, "No more data to process\n");
+		return;
+	}
+
+	if (is_aes(cryp) && is_ctr(cryp))
+		stm32_cryp_check_ctr_counter(cryp);
+
+	stm32_cryp_irq_write_block(cryp);
+}
+
+static irqreturn_t stm32_cryp_irq_thread(int irq, void *arg)
+{
+	struct stm32_cryp *cryp = arg;
+
+	if (cryp->irq_status & MISR_OUT)
+		/* Output FIFO IRQ: read data */
+		if (unlikely(stm32_cryp_irq_read_data(cryp))) {
+			/* All bytes processed, finish */
+			stm32_cryp_write(cryp, CRYP_IMSCR, 0);
+			stm32_cryp_finish_req(cryp);
+			return IRQ_HANDLED;
+		}
+
+	if (cryp->irq_status & MISR_IN) {
+		/* Input FIFO IRQ: write data */
+		stm32_cryp_irq_write_data(cryp);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t stm32_cryp_irq(int irq, void *arg)
+{
+	struct stm32_cryp *cryp = arg;
+
+	cryp->irq_status = stm32_cryp_read(cryp, CRYP_MISR);
+
+	return IRQ_WAKE_THREAD;
+}
+
+static struct crypto_alg crypto_algs[] = {
+{
+	.cra_name		= "ecb(aes)",
+	.cra_driver_name	= "stm32-ecb-aes",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+				  CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
+	.cra_alignmask		= 0xf,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= stm32_cryp_cra_init,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.setkey		= stm32_cryp_aes_setkey,
+		.encrypt	= stm32_cryp_aes_ecb_encrypt,
+		.decrypt	= stm32_cryp_aes_ecb_decrypt,
+	}
+},
+{
+	.cra_name		= "cbc(aes)",
+	.cra_driver_name	= "stm32-cbc-aes",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+				  CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
+	.cra_alignmask		= 0xf,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= stm32_cryp_cra_init,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= stm32_cryp_aes_setkey,
+		.encrypt	= stm32_cryp_aes_cbc_encrypt,
+		.decrypt	= stm32_cryp_aes_cbc_decrypt,
+	}
+},
+{
+	.cra_name		= "ctr(aes)",
+	.cra_driver_name	= "stm32-ctr-aes",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+				  CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
+	.cra_alignmask		= 0xf,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= stm32_cryp_cra_init,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= stm32_cryp_aes_setkey,
+		.encrypt	= stm32_cryp_aes_ctr_encrypt,
+		.decrypt	= stm32_cryp_aes_ctr_decrypt,
+	}
+},
+{
+	.cra_name		= "ecb(des)",
+	.cra_driver_name	= "stm32-ecb-des",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+				  CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= DES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
+	.cra_alignmask		= 0xf,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= stm32_cryp_cra_init,
+	.cra_ablkcipher = {
+		.min_keysize	= DES_BLOCK_SIZE,
+		.max_keysize	= DES_BLOCK_SIZE,
+		.setkey		= stm32_cryp_des_setkey,
+		.encrypt	= stm32_cryp_des_ecb_encrypt,
+		.decrypt	= stm32_cryp_des_ecb_decrypt,
+	}
+},
+{
+	.cra_name		= "cbc(des)",
+	.cra_driver_name	= "stm32-cbc-des",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+				  CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= DES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
+	.cra_alignmask		= 0xf,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= stm32_cryp_cra_init,
+	.cra_ablkcipher = {
+		.min_keysize	= DES_BLOCK_SIZE,
+		.max_keysize	= DES_BLOCK_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= stm32_cryp_des_setkey,
+		.encrypt	= stm32_cryp_des_cbc_encrypt,
+		.decrypt	= stm32_cryp_des_cbc_decrypt,
+	}
+},
+{
+	.cra_name		= "ecb(des3_ede)",
+	.cra_driver_name	= "stm32-ecb-des3",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+				  CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= DES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
+	.cra_alignmask		= 0xf,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= stm32_cryp_cra_init,
+	.cra_ablkcipher = {
+		.min_keysize	= 3 * DES_BLOCK_SIZE,
+		.max_keysize	= 3 * DES_BLOCK_SIZE,
+		.setkey		= stm32_cryp_tdes_setkey,
+		.encrypt	= stm32_cryp_tdes_ecb_encrypt,
+		.decrypt	= stm32_cryp_tdes_ecb_decrypt,
+	}
+},
+{
+	.cra_name		= "cbc(des3_ede)",
+	.cra_driver_name	= "stm32-cbc-des3",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+				  CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= DES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
+	.cra_alignmask		= 0xf,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= stm32_cryp_cra_init,
+	.cra_ablkcipher = {
+		.min_keysize	= 3 * DES_BLOCK_SIZE,
+		.max_keysize	= 3 * DES_BLOCK_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= stm32_cryp_tdes_setkey,
+		.encrypt	= stm32_cryp_tdes_cbc_encrypt,
+		.decrypt	= stm32_cryp_tdes_cbc_decrypt,
+	}
+},
+};
+
+static const struct of_device_id stm32_dt_ids[] = {
+	{ .compatible = "st,stm32f756-cryp", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, stm32_dt_ids);
+
+static int stm32_cryp_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct stm32_cryp *cryp;
+	struct resource *res;
+	struct reset_control *rst;
+	int irq, ret;
+
+	cryp = devm_kzalloc(dev, sizeof(*cryp), GFP_KERNEL);
+	if (!cryp)
+		return -ENOMEM;
+
+	cryp->dev = dev;
+
+	mutex_init(&cryp->lock);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	cryp->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cryp->regs))
+		return PTR_ERR(cryp->regs);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(dev, "Cannot get IRQ resource\n");
+		return irq;
+	}
+
+	ret = devm_request_threaded_irq(dev, irq, stm32_cryp_irq,
+					stm32_cryp_irq_thread, IRQF_ONESHOT,
+					dev_name(dev), cryp);
+	if (ret) {
+		dev_err(dev, "Cannot grab IRQ\n");
+		return ret;
+	}
+
+	cryp->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(cryp->clk)) {
+		dev_err(dev, "Could not get clock\n");
+		return PTR_ERR(cryp->clk);
+	}
+
+	ret = clk_prepare_enable(cryp->clk);
+	if (ret) {
+		dev_err(cryp->dev, "Failed to enable clock\n");
+		return ret;
+	}
+
+	rst = devm_reset_control_get(dev, NULL);
+	if (!IS_ERR(rst)) {
+		reset_control_assert(rst);
+		udelay(2);
+		reset_control_deassert(rst);
+	}
+
+	platform_set_drvdata(pdev, cryp);
+
+	spin_lock(&cryp_list.lock);
+	list_add(&cryp->list, &cryp_list.dev_list);
+	spin_unlock(&cryp_list.lock);
+
+	/* Initialize crypto engine */
+	cryp->engine = crypto_engine_alloc_init(dev, 1);
+	if (!cryp->engine) {
+		dev_err(dev, "Could not init crypto engine\n");
+		ret = -ENOMEM;
+		goto err_engine1;
+	}
+
+	cryp->engine->prepare_cipher_request = stm32_cryp_prepare_cipher_req;
+	cryp->engine->cipher_one_request = stm32_cryp_cipher_one_req;
+
+	ret = crypto_engine_start(cryp->engine);
+	if (ret) {
+		dev_err(dev, "Could not start crypto engine\n");
+		goto err_engine2;
+	}
+
+	ret = crypto_register_algs(crypto_algs, ARRAY_SIZE(crypto_algs));
+	if (ret) {
+		dev_err(dev, "Could not register algs\n");
+		goto err_algs;
+	}
+
+	dev_info(dev, "Initialized\n");
+
+	return 0;
+
+err_algs:
+err_engine2:
+	crypto_engine_exit(cryp->engine);
+err_engine1:
+	spin_lock(&cryp_list.lock);
+	list_del(&cryp->list);
+	spin_unlock(&cryp_list.lock);
+
+	clk_disable_unprepare(cryp->clk);
+
+	return ret;
+}
+
+static int stm32_cryp_remove(struct platform_device *pdev)
+{
+	struct stm32_cryp *cryp = platform_get_drvdata(pdev);
+
+	if (!cryp)
+		return -ENODEV;
+
+	crypto_unregister_algs(crypto_algs, ARRAY_SIZE(crypto_algs));
+
+	crypto_engine_exit(cryp->engine);
+
+	spin_lock(&cryp_list.lock);
+	list_del(&cryp->list);
+	spin_unlock(&cryp_list.lock);
+
+	clk_disable_unprepare(cryp->clk);
+
+	return 0;
+}
+
+static struct platform_driver stm32_cryp_driver = {
+	.probe  = stm32_cryp_probe,
+	.remove = stm32_cryp_remove,
+	.driver = {
+		.name           = DRIVER_NAME,
+		.of_match_table = stm32_dt_ids,
+	},
+};
+
+module_platform_driver(stm32_cryp_driver);
+
+MODULE_AUTHOR("Fabien Dessenne <fabien.dessenne@st.com>");
+MODULE_DESCRIPTION("STMicrolectronics STM32 CRYP hardware driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/stm32/stm32_crc32.c b/drivers/crypto/stm32/stm32_crc32.c
index 090582baecfe..8f09b8430893 100644
--- a/drivers/crypto/stm32/stm32_crc32.c
+++ b/drivers/crypto/stm32/stm32_crc32.c
@@ -208,6 +208,7 @@ static struct shash_alg algs[] = {
 			.cra_name               = "crc32",
 			.cra_driver_name        = DRIVER_NAME,
 			.cra_priority           = 200,
+			.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize          = CHKSUM_BLOCK_SIZE,
 			.cra_alignmask          = 3,
 			.cra_ctxsize            = sizeof(struct stm32_crc_ctx),
@@ -229,6 +230,7 @@ static struct shash_alg algs[] = {
 			.cra_name               = "crc32c",
 			.cra_driver_name        = DRIVER_NAME,
 			.cra_priority           = 200,
+			.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize          = CHKSUM_BLOCK_SIZE,
 			.cra_alignmask          = 3,
 			.cra_ctxsize            = sizeof(struct stm32_crc_ctx),
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 6833ada237ab..7b0bf825c4e7 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -428,9 +428,21 @@ static int dev_dax_fault(struct vm_fault *vmf)
 	return dev_dax_huge_fault(vmf, PE_SIZE_PTE);
 }
 
+static int dev_dax_split(struct vm_area_struct *vma, unsigned long addr)
+{
+	struct file *filp = vma->vm_file;
+	struct dev_dax *dev_dax = filp->private_data;
+	struct dax_region *dax_region = dev_dax->region;
+
+	if (!IS_ALIGNED(addr, dax_region->align))
+		return -EINVAL;
+	return 0;
+}
+
 static const struct vm_operations_struct dax_vm_ops = {
 	.fault = dev_dax_fault,
 	.huge_fault = dev_dax_huge_fault,
+	.split = dev_dax_split,
 };
 
 static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 78fb496ecb4e..fe2af6aa88fc 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -737,7 +737,7 @@ struct devfreq *devm_devfreq_add_device(struct device *dev,
 	devfreq = devfreq_add_device(dev, profile, governor_name, data);
 	if (IS_ERR(devfreq)) {
 		devres_free(ptr);
-		return ERR_PTR(-ENOMEM);
+		return devfreq;
 	}
 
 	*ptr = devfreq;
@@ -996,7 +996,8 @@ static ssize_t governor_store(struct device *dev, struct device_attribute *attr,
 	if (df->governor == governor) {
 		ret = 0;
 		goto out;
-	} else if (df->governor->immutable || governor->immutable) {
+	} else if ((df->governor && df->governor->immutable) ||
+					governor->immutable) {
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index bc1cb284111c..539450713838 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -157,13 +157,13 @@ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 	spin_unlock_irqrestore(&dcb->poll->lock, flags);
 }
 
-static unsigned int dma_buf_poll(struct file *file, poll_table *poll)
+static __poll_t dma_buf_poll(struct file *file, poll_table *poll)
 {
 	struct dma_buf *dmabuf;
 	struct reservation_object *resv;
 	struct reservation_object_list *fobj;
 	struct dma_fence *fence_excl;
-	unsigned long events;
+	__poll_t events;
 	unsigned shared_count, seq;
 
 	dmabuf = file->private_data;
@@ -195,7 +195,7 @@ retry:
 
 	if (fence_excl && (!(events & POLLOUT) || shared_count == 0)) {
 		struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl;
-		unsigned long pevents = POLLIN;
+		__poll_t pevents = POLLIN;
 
 		if (shared_count == 0)
 			pevents |= POLLOUT;
@@ -351,13 +351,13 @@ static inline int is_dma_buf_file(struct file *file)
  *
  * 2. Userspace passes this file-descriptors to all drivers it wants this buffer
  *    to share with: First the filedescriptor is converted to a &dma_buf using
- *    dma_buf_get(). The the buffer is attached to the device using
+ *    dma_buf_get(). Then the buffer is attached to the device using
  *    dma_buf_attach().
  *
  *    Up to this stage the exporter is still free to migrate or reallocate the
  *    backing storage.
  *
- * 3. Once the buffer is attached to all devices userspace can inniate DMA
+ * 3. Once the buffer is attached to all devices userspace can initiate DMA
  *    access to the shared buffer. In the kernel this is done by calling
  *    dma_buf_map_attachment() and dma_buf_unmap_attachment().
  *
@@ -617,7 +617,7 @@ EXPORT_SYMBOL_GPL(dma_buf_detach);
  * Returns sg_table containing the scatterlist to be returned; returns ERR_PTR
  * on error. May return -EINTR if it is interrupted by a signal.
  *
- * A mapping must be unmapped again using dma_buf_map_attachment(). Note that
+ * A mapping must be unmapped by using dma_buf_unmap_attachment(). Note that
  * the underlying backing storage is pinned for as long as a mapping exists,
  * therefore users/importers should not hold onto a mapping for undue amounts of
  * time.
@@ -1179,8 +1179,7 @@ static int dma_buf_init_debugfs(void)
 
 static void dma_buf_uninit_debugfs(void)
 {
-	if (dma_buf_debugfs_dir)
-		debugfs_remove_recursive(dma_buf_debugfs_dir);
+	debugfs_remove_recursive(dma_buf_debugfs_dir);
 }
 #else
 static inline int dma_buf_init_debugfs(void)
diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c
index 0350829ba62e..dd1edfb27b61 100644
--- a/drivers/dma-buf/dma-fence-array.c
+++ b/drivers/dma-buf/dma-fence-array.c
@@ -31,6 +31,14 @@ static const char *dma_fence_array_get_timeline_name(struct dma_fence *fence)
 	return "unbound";
 }
 
+static void irq_dma_fence_array_work(struct irq_work *wrk)
+{
+	struct dma_fence_array *array = container_of(wrk, typeof(*array), work);
+
+	dma_fence_signal(&array->base);
+	dma_fence_put(&array->base);
+}
+
 static void dma_fence_array_cb_func(struct dma_fence *f,
 				    struct dma_fence_cb *cb)
 {
@@ -39,8 +47,9 @@ static void dma_fence_array_cb_func(struct dma_fence *f,
 	struct dma_fence_array *array = array_cb->array;
 
 	if (atomic_dec_and_test(&array->num_pending))
-		dma_fence_signal(&array->base);
-	dma_fence_put(&array->base);
+		irq_work_queue(&array->work);
+	else
+		dma_fence_put(&array->base);
 }
 
 static bool dma_fence_array_enable_signaling(struct dma_fence *fence)
@@ -136,6 +145,7 @@ struct dma_fence_array *dma_fence_array_create(int num_fences,
 	spin_lock_init(&array->lock);
 	dma_fence_init(&array->base, &dma_fence_array_ops, &array->lock,
 		       context, seqno);
+	init_irq_work(&array->work, irq_dma_fence_array_work);
 
 	array->num_fences = num_fences;
 	atomic_set(&array->num_pending, signal_on_any ? 1 : num_fences);
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index b44d9d7db347..04ebe2204c12 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -104,7 +104,8 @@ reservation_object_add_shared_inplace(struct reservation_object *obj,
 				      struct reservation_object_list *fobj,
 				      struct dma_fence *fence)
 {
-	u32 i;
+	struct dma_fence *signaled = NULL;
+	u32 i, signaled_idx;
 
 	dma_fence_get(fence);
 
@@ -126,17 +127,28 @@ reservation_object_add_shared_inplace(struct reservation_object *obj,
 			dma_fence_put(old_fence);
 			return;
 		}
+
+		if (!signaled && dma_fence_is_signaled(old_fence)) {
+			signaled = old_fence;
+			signaled_idx = i;
+		}
 	}
 
 	/*
 	 * memory barrier is added by write_seqcount_begin,
 	 * fobj->shared_count is protected by this lock too
 	 */
-	RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence);
-	fobj->shared_count++;
+	if (signaled) {
+		RCU_INIT_POINTER(fobj->shared[signaled_idx], fence);
+	} else {
+		RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence);
+		fobj->shared_count++;
+	}
 
 	write_seqcount_end(&obj->seq);
 	preempt_enable();
+
+	dma_fence_put(signaled);
 }
 
 static void
@@ -145,8 +157,7 @@ reservation_object_add_shared_replace(struct reservation_object *obj,
 				      struct reservation_object_list *fobj,
 				      struct dma_fence *fence)
 {
-	unsigned i;
-	struct dma_fence *old_fence = NULL;
+	unsigned i, j, k;
 
 	dma_fence_get(fence);
 
@@ -162,24 +173,21 @@ reservation_object_add_shared_replace(struct reservation_object *obj,
 	 * references from the old struct are carried over to
 	 * the new.
 	 */
-	fobj->shared_count = old->shared_count;
-
-	for (i = 0; i < old->shared_count; ++i) {
+	for (i = 0, j = 0, k = fobj->shared_max; i < old->shared_count; ++i) {
 		struct dma_fence *check;
 
 		check = rcu_dereference_protected(old->shared[i],
 						reservation_object_held(obj));
 
-		if (!old_fence && check->context == fence->context) {
-			old_fence = check;
-			RCU_INIT_POINTER(fobj->shared[i], fence);
-		} else
-			RCU_INIT_POINTER(fobj->shared[i], check);
-	}
-	if (!old_fence) {
-		RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence);
-		fobj->shared_count++;
+		if (check->context == fence->context ||
+		    dma_fence_is_signaled(check))
+			RCU_INIT_POINTER(fobj->shared[--k], check);
+		else
+			RCU_INIT_POINTER(fobj->shared[j++], check);
 	}
+	fobj->shared_count = j;
+	RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence);
+	fobj->shared_count++;
 
 done:
 	preempt_disable();
@@ -192,10 +200,18 @@ done:
 	write_seqcount_end(&obj->seq);
 	preempt_enable();
 
-	if (old)
-		kfree_rcu(old, rcu);
+	if (!old)
+		return;
 
-	dma_fence_put(old_fence);
+	/* Drop the references to the signaled fences */
+	for (i = k; i < fobj->shared_max; ++i) {
+		struct dma_fence *f;
+
+		f = rcu_dereference_protected(fobj->shared[i],
+					      reservation_object_held(obj));
+		dma_fence_put(f);
+	}
+	kfree_rcu(old, rcu);
 }
 
 /**
@@ -318,7 +334,7 @@ retry:
 				continue;
 			}
 
-			dst_list->shared[dst_list->shared_count++] = fence;
+			rcu_assign_pointer(dst_list->shared[dst_list->shared_count++], fence);
 		}
 	} else {
 		dst_list = NULL;
@@ -455,13 +471,15 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj,
 					 unsigned long timeout)
 {
 	struct dma_fence *fence;
-	unsigned seq, shared_count, i = 0;
+	unsigned seq, shared_count;
 	long ret = timeout ? timeout : 1;
+	int i;
 
 retry:
 	shared_count = 0;
 	seq = read_seqcount_begin(&obj->seq);
 	rcu_read_lock();
+	i = -1;
 
 	fence = rcu_dereference(obj->fence_excl);
 	if (fence && !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
@@ -477,14 +495,14 @@ retry:
 		fence = NULL;
 	}
 
-	if (!fence && wait_all) {
+	if (wait_all) {
 		struct reservation_object_list *fobj =
 						rcu_dereference(obj->fence);
 
 		if (fobj)
 			shared_count = fobj->shared_count;
 
-		for (i = 0; i < shared_count; ++i) {
+		for (i = 0; !fence && i < shared_count; ++i) {
 			struct dma_fence *lfence = rcu_dereference(fobj->shared[i]);
 
 			if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index 03830634e141..8e8c4a12a0bc 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -312,7 +312,7 @@ static int sync_file_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static unsigned int sync_file_poll(struct file *file, poll_table *wait)
+static __poll_t sync_file_poll(struct file *file, poll_table *wait)
 {
 	struct sync_file *sync_file = file->private_data;
 
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index b52b0d55247e..97483df1f82e 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -2182,7 +2182,7 @@ static int pl08x_terminate_all(struct dma_chan *chan)
 	}
 	/* Dequeue jobs and free LLIs */
 	if (plchan->at) {
-		pl08x_desc_free(&plchan->at->vd);
+		vchan_terminate_vdesc(&plchan->at->vd);
 		plchan->at = NULL;
 	}
 	/* Dequeue jobs not yet fired as well */
@@ -2193,6 +2193,13 @@ static int pl08x_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void pl08x_synchronize(struct dma_chan *chan)
+{
+	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
+
+	vchan_synchronize(&plchan->vc);
+}
+
 static int pl08x_pause(struct dma_chan *chan)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
@@ -2773,6 +2780,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	pl08x->memcpy.device_pause = pl08x_pause;
 	pl08x->memcpy.device_resume = pl08x_resume;
 	pl08x->memcpy.device_terminate_all = pl08x_terminate_all;
+	pl08x->memcpy.device_synchronize = pl08x_synchronize;
 	pl08x->memcpy.src_addr_widths = PL80X_DMA_BUSWIDTHS;
 	pl08x->memcpy.dst_addr_widths = PL80X_DMA_BUSWIDTHS;
 	pl08x->memcpy.directions = BIT(DMA_MEM_TO_MEM);
@@ -2802,6 +2810,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 		pl08x->slave.device_pause = pl08x_pause;
 		pl08x->slave.device_resume = pl08x_resume;
 		pl08x->slave.device_terminate_all = pl08x_terminate_all;
+		pl08x->slave.device_synchronize = pl08x_synchronize;
 		pl08x->slave.src_addr_widths = PL80X_DMA_BUSWIDTHS;
 		pl08x->slave.dst_addr_widths = PL80X_DMA_BUSWIDTHS;
 		pl08x->slave.directions =
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index fbab271b3bf9..a861b5b4d443 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -708,7 +708,7 @@ atc_prep_dma_interleaved(struct dma_chan *chan,
 			 unsigned long flags)
 {
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
-	struct data_chunk	*first = xt->sgl;
+	struct data_chunk	*first;
 	struct at_desc		*desc = NULL;
 	size_t			xfer_count;
 	unsigned int		dwidth;
@@ -720,6 +720,8 @@ atc_prep_dma_interleaved(struct dma_chan *chan,
 	if (unlikely(!xt || xt->numf != 1 || !xt->frame_size))
 		return NULL;
 
+	first = xt->sgl;
+
 	dev_info(chan2dev(chan),
 		 "%s: src=%pad, dest=%pad, numf=%d, frame_size=%d, flags=0x%lx\n",
 		__func__, &xt->src_start, &xt->dst_start, xt->numf,
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index 6204cc32d09c..847f84a41a69 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -812,7 +812,7 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan)
 	 * c->desc is NULL and exit.)
 	 */
 	if (c->desc) {
-		bcm2835_dma_desc_free(&c->desc->vd);
+		vchan_terminate_vdesc(&c->desc->vd);
 		c->desc = NULL;
 		bcm2835_dma_abort(c->chan_base);
 
@@ -836,6 +836,13 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void bcm2835_dma_synchronize(struct dma_chan *chan)
+{
+	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
+
+	vchan_synchronize(&c->vc);
+}
+
 static int bcm2835_dma_chan_init(struct bcm2835_dmadev *d, int chan_id,
 				 int irq, unsigned int irq_flags)
 {
@@ -942,6 +949,7 @@ static int bcm2835_dma_probe(struct platform_device *pdev)
 	od->ddev.device_prep_dma_memcpy = bcm2835_dma_prep_dma_memcpy;
 	od->ddev.device_config = bcm2835_dma_slave_config;
 	od->ddev.device_terminate_all = bcm2835_dma_terminate_all;
+	od->ddev.device_synchronize = bcm2835_dma_synchronize;
 	od->ddev.src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
 	od->ddev.dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
 	od->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV) |
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index f7e965f63274..d9bee65a18a4 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -934,7 +934,7 @@ static bool cpp41_dma_filter_fn(struct dma_chan *chan, void *param)
 
 	BUILD_BUG_ON(ARRAY_SIZE(am335x_usb_queues_rx) !=
 		     ARRAY_SIZE(am335x_usb_queues_tx));
-	if (WARN_ON(cchan->port_num > ARRAY_SIZE(am335x_usb_queues_rx)))
+	if (WARN_ON(cchan->port_num >= ARRAY_SIZE(am335x_usb_queues_rx)))
 		return false;
 
 	cchan->q_num = queues[cchan->port_num].submit;
diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c
index d50273fed715..afd5e10f8927 100644
--- a/drivers/dma/dma-jz4740.c
+++ b/drivers/dma/dma-jz4740.c
@@ -555,7 +555,7 @@ static int jz4740_dma_probe(struct platform_device *pdev)
 
 	ret = dma_async_device_register(dd);
 	if (ret)
-		return ret;
+		goto err_clk;
 
 	irq = platform_get_irq(pdev, 0);
 	ret = request_irq(irq, jz4740_dma_irq, 0, dev_name(&pdev->dev), dmadev);
@@ -568,6 +568,8 @@ static int jz4740_dma_probe(struct platform_device *pdev)
 
 err_unregister:
 	dma_async_device_unregister(dd);
+err_clk:
+	clk_disable_unprepare(dmadev->clk);
 	return ret;
 }
 
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index 7373b7a555ec..85820a2d69d4 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -511,7 +511,7 @@ static int jz4780_dma_terminate_all(struct dma_chan *chan)
 	/* Clear the DMA status and stop the transfer. */
 	jz4780_dma_writel(jzdma, JZ_DMA_REG_DCS(jzchan->id), 0);
 	if (jzchan->desc) {
-		jz4780_dma_desc_free(&jzchan->desc->vdesc);
+		vchan_terminate_vdesc(&jzchan->desc->vdesc);
 		jzchan->desc = NULL;
 	}
 
@@ -523,6 +523,13 @@ static int jz4780_dma_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void jz4780_dma_synchronize(struct dma_chan *chan)
+{
+	struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan);
+
+	vchan_synchronize(&jzchan->vchan);
+}
+
 static int jz4780_dma_config(struct dma_chan *chan,
 	struct dma_slave_config *config)
 {
@@ -813,6 +820,7 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 	dd->device_prep_dma_memcpy = jz4780_dma_prep_dma_memcpy;
 	dd->device_config = jz4780_dma_config;
 	dd->device_terminate_all = jz4780_dma_terminate_all;
+	dd->device_synchronize = jz4780_dma_synchronize;
 	dd->device_tx_status = jz4780_dma_tx_status;
 	dd->device_issue_pending = jz4780_dma_issue_pending;
 	dd->src_addr_widths = JZ_DMA_BUSWIDTHS;
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 47edc7fbf91f..80cc2be6483c 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -155,6 +155,12 @@ MODULE_PARM_DESC(run, "Run the test (default: false)");
 #define PATTERN_COUNT_MASK	0x1f
 #define PATTERN_MEMSET_IDX	0x01
 
+/* poor man's completion - we want to use wait_event_freezable() on it */
+struct dmatest_done {
+	bool			done;
+	wait_queue_head_t	*wait;
+};
+
 struct dmatest_thread {
 	struct list_head	node;
 	struct dmatest_info	*info;
@@ -165,6 +171,8 @@ struct dmatest_thread {
 	u8			**dsts;
 	u8			**udsts;
 	enum dma_transaction_type type;
+	wait_queue_head_t done_wait;
+	struct dmatest_done test_done;
 	bool			done;
 };
 
@@ -342,18 +350,25 @@ static unsigned int dmatest_verify(u8 **bufs, unsigned int start,
 	return error_count;
 }
 
-/* poor man's completion - we want to use wait_event_freezable() on it */
-struct dmatest_done {
-	bool			done;
-	wait_queue_head_t	*wait;
-};
 
 static void dmatest_callback(void *arg)
 {
 	struct dmatest_done *done = arg;
-
-	done->done = true;
-	wake_up_all(done->wait);
+	struct dmatest_thread *thread =
+		container_of(done, struct dmatest_thread, test_done);
+	if (!thread->done) {
+		done->done = true;
+		wake_up_all(done->wait);
+	} else {
+		/*
+		 * If thread->done, it means that this callback occurred
+		 * after the parent thread has cleaned up. This can
+		 * happen in the case that driver doesn't implement
+		 * the terminate_all() functionality and a dma operation
+		 * did not occur within the timeout period
+		 */
+		WARN(1, "dmatest: Kernel memory may be corrupted!!\n");
+	}
 }
 
 static unsigned int min_odd(unsigned int x, unsigned int y)
@@ -424,9 +439,8 @@ static unsigned long long dmatest_KBs(s64 runtime, unsigned long long len)
  */
 static int dmatest_func(void *data)
 {
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(done_wait);
 	struct dmatest_thread	*thread = data;
-	struct dmatest_done	done = { .wait = &done_wait };
+	struct dmatest_done	*done = &thread->test_done;
 	struct dmatest_info	*info;
 	struct dmatest_params	*params;
 	struct dma_chan		*chan;
@@ -673,9 +687,9 @@ static int dmatest_func(void *data)
 			continue;
 		}
 
-		done.done = false;
+		done->done = false;
 		tx->callback = dmatest_callback;
-		tx->callback_param = &done;
+		tx->callback_param = done;
 		cookie = tx->tx_submit(tx);
 
 		if (dma_submit_error(cookie)) {
@@ -688,21 +702,12 @@ static int dmatest_func(void *data)
 		}
 		dma_async_issue_pending(chan);
 
-		wait_event_freezable_timeout(done_wait, done.done,
+		wait_event_freezable_timeout(thread->done_wait, done->done,
 					     msecs_to_jiffies(params->timeout));
 
 		status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
 
-		if (!done.done) {
-			/*
-			 * We're leaving the timed out dma operation with
-			 * dangling pointer to done_wait.  To make this
-			 * correct, we'll need to allocate wait_done for
-			 * each test iteration and perform "who's gonna
-			 * free it this time?" dancing.  For now, just
-			 * leave it dangling.
-			 */
-			WARN(1, "dmatest: Kernel stack may be corrupted!!\n");
+		if (!done->done) {
 			dmaengine_unmap_put(um);
 			result("test timed out", total_tests, src_off, dst_off,
 			       len, 0);
@@ -789,7 +794,7 @@ err_thread_type:
 		dmatest_KBs(runtime, total_len), ret);
 
 	/* terminate all transfers on specified channels */
-	if (ret)
+	if (ret || failed_tests)
 		dmaengine_terminate_all(chan);
 
 	thread->done = true;
@@ -849,6 +854,8 @@ static int dmatest_add_threads(struct dmatest_info *info,
 		thread->info = info;
 		thread->chan = dtc->chan;
 		thread->type = type;
+		thread->test_done.wait = &thread->done_wait;
+		init_waitqueue_head(&thread->done_wait);
 		smp_wmb();
 		thread->task = kthread_create(dmatest_func, thread, "%s-%s%u",
 				dma_chan_name(chan), op, i);
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 9364a3ed345a..948df1ab5f1a 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -860,11 +860,8 @@ static int edma_terminate_all(struct dma_chan *chan)
 		/* Move the cyclic channel back to default queue */
 		if (!echan->tc && echan->edesc->cyclic)
 			edma_assign_channel_eventq(echan, EVENTQ_DEFAULT);
-		/*
-		 * free the running request descriptor
-		 * since it is not in any of the vdesc lists
-		 */
-		edma_desc_free(&echan->edesc->vdesc);
+
+		vchan_terminate_vdesc(&echan->edesc->vdesc);
 		echan->edesc = NULL;
 	}
 
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index 6775f2c74e25..c7568869284e 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -863,11 +863,11 @@ static void fsl_edma_irq_exit(
 	}
 }
 
-static void fsl_disable_clocks(struct fsl_edma_engine *fsl_edma)
+static void fsl_disable_clocks(struct fsl_edma_engine *fsl_edma, int nr_clocks)
 {
 	int i;
 
-	for (i = 0; i < DMAMUX_NR; i++)
+	for (i = 0; i < nr_clocks; i++)
 		clk_disable_unprepare(fsl_edma->muxclk[i]);
 }
 
@@ -904,25 +904,25 @@ static int fsl_edma_probe(struct platform_device *pdev)
 
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 1 + i);
 		fsl_edma->muxbase[i] = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(fsl_edma->muxbase[i]))
+		if (IS_ERR(fsl_edma->muxbase[i])) {
+			/* on error: disable all previously enabled clks */
+			fsl_disable_clocks(fsl_edma, i);
 			return PTR_ERR(fsl_edma->muxbase[i]);
+		}
 
 		sprintf(clkname, "dmamux%d", i);
 		fsl_edma->muxclk[i] = devm_clk_get(&pdev->dev, clkname);
 		if (IS_ERR(fsl_edma->muxclk[i])) {
 			dev_err(&pdev->dev, "Missing DMAMUX block clock.\n");
+			/* on error: disable all previously enabled clks */
+			fsl_disable_clocks(fsl_edma, i);
 			return PTR_ERR(fsl_edma->muxclk[i]);
 		}
 
 		ret = clk_prepare_enable(fsl_edma->muxclk[i]);
-		if (ret) {
-			/* disable only clks which were enabled on error */
-			for (; i >= 0; i--)
-				clk_disable_unprepare(fsl_edma->muxclk[i]);
-
-			dev_err(&pdev->dev, "DMAMUX clk block failed.\n");
-			return ret;
-		}
+		if (ret)
+			/* on error: disable all previously enabled clks */
+			fsl_disable_clocks(fsl_edma, i);
 
 	}
 
@@ -976,7 +976,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(&pdev->dev,
 			"Can't register Freescale eDMA engine. (%d)\n", ret);
-		fsl_disable_clocks(fsl_edma);
+		fsl_disable_clocks(fsl_edma, DMAMUX_NR);
 		return ret;
 	}
 
@@ -985,7 +985,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev,
 			"Can't register Freescale eDMA of_dma. (%d)\n", ret);
 		dma_async_device_unregister(&fsl_edma->dma_dev);
-		fsl_disable_clocks(fsl_edma);
+		fsl_disable_clocks(fsl_edma, DMAMUX_NR);
 		return ret;
 	}
 
@@ -1015,7 +1015,7 @@ static int fsl_edma_remove(struct platform_device *pdev)
 	fsl_edma_cleanup_vchan(&fsl_edma->dma_dev);
 	of_dma_controller_free(np);
 	dma_async_device_unregister(&fsl_edma->dma_dev);
-	fsl_disable_clocks(fsl_edma);
+	fsl_disable_clocks(fsl_edma, DMAMUX_NR);
 
 	return 0;
 }
diff --git a/drivers/dma/img-mdc-dma.c b/drivers/dma/img-mdc-dma.c
index 0391f930aecc..25cec9c243e1 100644
--- a/drivers/dma/img-mdc-dma.c
+++ b/drivers/dma/img-mdc-dma.c
@@ -694,7 +694,6 @@ static unsigned int mdc_get_new_events(struct mdc_chan *mchan)
 static int mdc_terminate_all(struct dma_chan *chan)
 {
 	struct mdc_chan *mchan = to_mdc_chan(chan);
-	struct mdc_tx_desc *mdesc;
 	unsigned long flags;
 	LIST_HEAD(head);
 
@@ -703,21 +702,28 @@ static int mdc_terminate_all(struct dma_chan *chan)
 	mdc_chan_writel(mchan, MDC_CONTROL_AND_STATUS_CANCEL,
 			MDC_CONTROL_AND_STATUS);
 
-	mdesc = mchan->desc;
-	mchan->desc = NULL;
+	if (mchan->desc) {
+		vchan_terminate_vdesc(&mchan->desc->vd);
+		mchan->desc = NULL;
+	}
 	vchan_get_all_descriptors(&mchan->vc, &head);
 
 	mdc_get_new_events(mchan);
 
 	spin_unlock_irqrestore(&mchan->vc.lock, flags);
 
-	if (mdesc)
-		mdc_desc_free(&mdesc->vd);
 	vchan_dma_desc_free_list(&mchan->vc, &head);
 
 	return 0;
 }
 
+static void mdc_synchronize(struct dma_chan *chan)
+{
+	struct mdc_chan *mchan = to_mdc_chan(chan);
+
+	vchan_synchronize(&mchan->vc);
+}
+
 static int mdc_slave_config(struct dma_chan *chan,
 			    struct dma_slave_config *config)
 {
@@ -952,6 +958,7 @@ static int mdc_dma_probe(struct platform_device *pdev)
 	mdma->dma_dev.device_tx_status = mdc_tx_status;
 	mdma->dma_dev.device_issue_pending = mdc_issue_pending;
 	mdma->dma_dev.device_terminate_all = mdc_terminate_all;
+	mdma->dma_dev.device_synchronize = mdc_synchronize;
 	mdma->dma_dev.device_config = mdc_slave_config;
 
 	mdma->dma_dev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 331f863c605e..715b39ae5a46 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -765,7 +765,7 @@ static int imxdma_alloc_chan_resources(struct dma_chan *chan)
 		desc = kzalloc(sizeof(*desc), GFP_KERNEL);
 		if (!desc)
 			break;
-		__memzero(&desc->desc, sizeof(struct dma_async_tx_descriptor));
+		memset(&desc->desc, 0, sizeof(struct dma_async_tx_descriptor));
 		dma_async_tx_descriptor_init(&desc->desc, chan);
 		desc->desc.tx_submit = imxdma_tx_submit;
 		/* txd.flags will be overwritten in prep funcs */
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 2184881afe76..e7db24c67030 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1939,4 +1939,10 @@ module_platform_driver(sdma_driver);
 
 MODULE_AUTHOR("Sascha Hauer, Pengutronix <s.hauer@pengutronix.de>");
 MODULE_DESCRIPTION("i.MX SDMA driver");
+#if IS_ENABLED(CONFIG_SOC_IMX6Q)
+MODULE_FIRMWARE("imx/sdma/sdma-imx6q.bin");
+#endif
+#if IS_ENABLED(CONFIG_SOC_IMX7D)
+MODULE_FIRMWARE("imx/sdma/sdma-imx7d.bin");
+#endif
 MODULE_LICENSE("GPL");
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 58d4ccd33672..8b5b23a8ace9 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -597,7 +597,6 @@ static void __cleanup(struct ioatdma_chan *ioat_chan, dma_addr_t phys_complete)
 	for (i = 0; i < active && !seen_current; i++) {
 		struct dma_async_tx_descriptor *tx;
 
-		smp_read_barrier_depends();
 		prefetch(ioat_get_ring_ent(ioat_chan, idx + i + 1));
 		desc = ioat_get_ring_ent(ioat_chan, idx + i);
 		dump_desc_dbg(ioat_chan, desc);
@@ -715,7 +714,6 @@ static void ioat_abort_descs(struct ioatdma_chan *ioat_chan)
 	for (i = 1; i < active; i++) {
 		struct dma_async_tx_descriptor *tx;
 
-		smp_read_barrier_depends();
 		prefetch(ioat_get_ring_ent(ioat_chan, idx + i + 1));
 		desc = ioat_get_ring_ent(ioat_chan, idx + i);
 
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 2f31d3d0caa6..7792a9186f9c 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -390,7 +390,7 @@ static int ioat_dma_self_test(struct ioatdma_device *ioat_dma)
 	if (memcmp(src, dest, IOAT_TEST_SIZE)) {
 		dev_err(dev, "Self-test copy failed compare, disabling\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto unmap_dma;
 	}
 
 unmap_dma:
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index 01d2a750a621..26b67455208f 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -719,7 +719,7 @@ static int k3_dma_terminate_all(struct dma_chan *chan)
 		c->phy = NULL;
 		p->vchan = NULL;
 		if (p->ds_run) {
-			k3_dma_free_desc(&p->ds_run->vd);
+			vchan_terminate_vdesc(&p->ds_run->vd);
 			p->ds_run = NULL;
 		}
 		p->ds_done = NULL;
@@ -730,6 +730,13 @@ static int k3_dma_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void k3_dma_synchronize(struct dma_chan *chan)
+{
+	struct k3_dma_chan *c = to_k3_chan(chan);
+
+	vchan_synchronize(&c->vc);
+}
+
 static int k3_dma_transfer_pause(struct dma_chan *chan)
 {
 	struct k3_dma_chan *c = to_k3_chan(chan);
@@ -868,6 +875,7 @@ static int k3_dma_probe(struct platform_device *op)
 	d->slave.device_pause = k3_dma_transfer_pause;
 	d->slave.device_resume = k3_dma_transfer_resume;
 	d->slave.device_terminate_all = k3_dma_terminate_all;
+	d->slave.device_synchronize = k3_dma_synchronize;
 	d->slave.copy_align = DMAENGINE_ALIGN_8_BYTES;
 
 	/* init virtual channel */
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
index 5ba5714d0b7c..94d7bd7d2880 100644
--- a/drivers/dma/mic_x100_dma.c
+++ b/drivers/dma/mic_x100_dma.c
@@ -480,9 +480,7 @@ static int mic_dma_setup_irq(struct mic_dma_chan *ch)
 		to_mbus_hw_ops(ch)->request_threaded_irq(to_mbus_device(ch),
 			mic_dma_intr_handler, mic_dma_thread_fn,
 			"mic dma_channel", ch, ch->ch_num);
-	if (IS_ERR(ch->cookie))
-		return PTR_ERR(ch->cookie);
-	return 0;
+	return PTR_ERR_OR_ZERO(ch->cookie);
 }
 
 static inline void mic_dma_free_irq(struct mic_dma_chan *ch)
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index f6dd849159d8..d21c19822feb 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -1311,7 +1311,7 @@ static int omap_dma_terminate_all(struct dma_chan *chan)
 	 * c->desc is NULL and exit.)
 	 */
 	if (c->desc) {
-		omap_dma_desc_free(&c->desc->vd);
+		vchan_terminate_vdesc(&c->desc->vd);
 		c->desc = NULL;
 		/* Avoid stopping the dma twice */
 		if (!c->paused)
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index e3669850aef4..963cc5228d05 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -50,6 +50,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/of_dma.h>
+#include <linux/of_device.h>
 #include <linux/property.h>
 #include <linux/delay.h>
 #include <linux/acpi.h>
@@ -104,6 +105,10 @@ static unsigned int nr_desc_prm;
 module_param(nr_desc_prm, uint, 0644);
 MODULE_PARM_DESC(nr_desc_prm, "number of descriptors (default: 0)");
 
+enum hidma_cap {
+	HIDMA_MSI_CAP = 1,
+	HIDMA_IDENTITY_CAP,
+};
 
 /* process completed descriptors */
 static void hidma_process_completed(struct hidma_chan *mchan)
@@ -736,25 +741,12 @@ static int hidma_request_msi(struct hidma_dev *dmadev,
 #endif
 }
 
-static bool hidma_msi_capable(struct device *dev)
+static bool hidma_test_capability(struct device *dev, enum hidma_cap test_cap)
 {
-	struct acpi_device *adev = ACPI_COMPANION(dev);
-	const char *of_compat;
-	int ret = -EINVAL;
-
-	if (!adev || acpi_disabled) {
-		ret = device_property_read_string(dev, "compatible",
-						  &of_compat);
-		if (ret)
-			return false;
+	enum hidma_cap cap;
 
-		ret = strcmp(of_compat, "qcom,hidma-1.1");
-	} else {
-#ifdef CONFIG_ACPI
-		ret = strcmp(acpi_device_hid(adev), "QCOM8062");
-#endif
-	}
-	return ret == 0;
+	cap = (enum hidma_cap) device_get_match_data(dev);
+	return cap ? ((cap & test_cap) > 0) : 0;
 }
 
 static int hidma_probe(struct platform_device *pdev)
@@ -834,8 +826,7 @@ static int hidma_probe(struct platform_device *pdev)
 	 * Determine the MSI capability of the platform. Old HW doesn't
 	 * support MSI.
 	 */
-	msi = hidma_msi_capable(&pdev->dev);
-
+	msi = hidma_test_capability(&pdev->dev, HIDMA_MSI_CAP);
 	device_property_read_u32(&pdev->dev, "desc-count",
 				 &dmadev->nr_descriptors);
 
@@ -848,7 +839,10 @@ static int hidma_probe(struct platform_device *pdev)
 	if (!dmadev->nr_descriptors)
 		dmadev->nr_descriptors = HIDMA_NR_DEFAULT_DESC;
 
-	dmadev->chidx = readl(dmadev->dev_trca + 0x28);
+	if (hidma_test_capability(&pdev->dev, HIDMA_IDENTITY_CAP))
+		dmadev->chidx = readl(dmadev->dev_trca + 0x40);
+	else
+		dmadev->chidx = readl(dmadev->dev_trca + 0x28);
 
 	/* Set DMA mask to 64 bits. */
 	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
@@ -953,7 +947,8 @@ static int hidma_remove(struct platform_device *pdev)
 #if IS_ENABLED(CONFIG_ACPI)
 static const struct acpi_device_id hidma_acpi_ids[] = {
 	{"QCOM8061"},
-	{"QCOM8062"},
+	{"QCOM8062", HIDMA_MSI_CAP},
+	{"QCOM8063", (HIDMA_MSI_CAP | HIDMA_IDENTITY_CAP)},
 	{},
 };
 MODULE_DEVICE_TABLE(acpi, hidma_acpi_ids);
@@ -961,7 +956,9 @@ MODULE_DEVICE_TABLE(acpi, hidma_acpi_ids);
 
 static const struct of_device_id hidma_match[] = {
 	{.compatible = "qcom,hidma-1.0",},
-	{.compatible = "qcom,hidma-1.1",},
+	{.compatible = "qcom,hidma-1.1", .data = (void *)(HIDMA_MSI_CAP),},
+	{.compatible = "qcom,hidma-1.2",
+	 .data = (void *)(HIDMA_MSI_CAP | HIDMA_IDENTITY_CAP),},
 	{},
 };
 MODULE_DEVICE_TABLE(of, hidma_match);
diff --git a/drivers/dma/qcom/hidma_ll.c b/drivers/dma/qcom/hidma_ll.c
index 4999e266b2de..7c6e2ff212a2 100644
--- a/drivers/dma/qcom/hidma_ll.c
+++ b/drivers/dma/qcom/hidma_ll.c
@@ -393,6 +393,8 @@ static int hidma_ll_reset(struct hidma_lldev *lldev)
  */
 static void hidma_ll_int_handler_internal(struct hidma_lldev *lldev, int cause)
 {
+	unsigned long irqflags;
+
 	if (cause & HIDMA_ERR_INT_MASK) {
 		dev_err(lldev->dev, "error 0x%x, disabling...\n",
 				cause);
@@ -410,6 +412,10 @@ static void hidma_ll_int_handler_internal(struct hidma_lldev *lldev, int cause)
 		return;
 	}
 
+	spin_lock_irqsave(&lldev->lock, irqflags);
+	writel_relaxed(cause, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
+	spin_unlock_irqrestore(&lldev->lock, irqflags);
+
 	/*
 	 * Fine tuned for this HW...
 	 *
@@ -421,9 +427,6 @@ static void hidma_ll_int_handler_internal(struct hidma_lldev *lldev, int cause)
 	 * Try to consume as many EVREs as possible.
 	 */
 	hidma_handle_tre_completion(lldev);
-
-	/* We consumed TREs or there are pending TREs or EVREs. */
-	writel_relaxed(cause, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
 }
 
 irqreturn_t hidma_ll_inthandler(int chirq, void *arg)
diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c
index 7335e2eb9b72..000c7019ca7d 100644
--- a/drivers/dma/qcom/hidma_mgmt.c
+++ b/drivers/dma/qcom/hidma_mgmt.c
@@ -17,6 +17,7 @@
 #include <linux/acpi.h>
 #include <linux/of.h>
 #include <linux/property.h>
+#include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/module.h>
@@ -356,67 +357,37 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 {
 	struct platform_device *pdev_parent = of_find_device_by_node(np);
 	struct platform_device_info pdevinfo;
-	struct of_phandle_args out_irq;
 	struct device_node *child;
-	struct resource *res = NULL;
-	const __be32 *cell;
-	int ret = 0, size, i, num;
-	u64 addr, addr_size;
+	struct resource *res;
+	int ret = 0;
+
+	/* allocate a resource array */
+	res = kcalloc(3, sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
 
 	for_each_available_child_of_node(np, child) {
-		struct resource *res_iter;
 		struct platform_device *new_pdev;
 
-		cell = of_get_property(child, "reg", &size);
-		if (!cell) {
-			ret = -EINVAL;
+		ret = of_address_to_resource(child, 0, &res[0]);
+		if (!ret)
 			goto out;
-		}
-
-		size /= sizeof(*cell);
-		num = size /
-			(of_n_addr_cells(child) + of_n_size_cells(child)) + 1;
 
-		/* allocate a resource array */
-		res = kcalloc(num, sizeof(*res), GFP_KERNEL);
-		if (!res) {
-			ret = -ENOMEM;
+		ret = of_address_to_resource(child, 1, &res[1]);
+		if (!ret)
 			goto out;
-		}
-
-		/* read each reg value */
-		i = 0;
-		res_iter = res;
-		while (i < size) {
-			addr = of_read_number(&cell[i],
-					      of_n_addr_cells(child));
-			i += of_n_addr_cells(child);
-
-			addr_size = of_read_number(&cell[i],
-						   of_n_size_cells(child));
-			i += of_n_size_cells(child);
-
-			res_iter->start = addr;
-			res_iter->end = res_iter->start + addr_size - 1;
-			res_iter->flags = IORESOURCE_MEM;
-			res_iter++;
-		}
 
-		ret = of_irq_parse_one(child, 0, &out_irq);
-		if (ret)
+		ret = of_irq_to_resource(child, 0, &res[2]);
+		if (ret <= 0)
 			goto out;
 
-		res_iter->start = irq_create_of_mapping(&out_irq);
-		res_iter->name = "hidma event irq";
-		res_iter->flags = IORESOURCE_IRQ;
-
 		memset(&pdevinfo, 0, sizeof(pdevinfo));
 		pdevinfo.fwnode = &child->fwnode;
 		pdevinfo.parent = pdev_parent ? &pdev_parent->dev : NULL;
 		pdevinfo.name = child->name;
 		pdevinfo.id = object_counter++;
 		pdevinfo.res = res;
-		pdevinfo.num_res = num;
+		pdevinfo.num_res = 3;
 		pdevinfo.data = NULL;
 		pdevinfo.size_data = 0;
 		pdevinfo.dma_mask = DMA_BIT_MASK(64);
@@ -434,8 +405,6 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 		 */
 		of_msi_configure(&new_pdev->dev, child);
 		of_node_put(child);
-		kfree(res);
-		res = NULL;
 	}
 out:
 	kfree(res);
diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c
index f04c4702d98b..cd92d696bcf9 100644
--- a/drivers/dma/s3c24xx-dma.c
+++ b/drivers/dma/s3c24xx-dma.c
@@ -732,7 +732,7 @@ static int s3c24xx_dma_terminate_all(struct dma_chan *chan)
 
 	/* Dequeue current job */
 	if (s3cchan->at) {
-		s3c24xx_dma_desc_free(&s3cchan->at->vd);
+		vchan_terminate_vdesc(&s3cchan->at->vd);
 		s3cchan->at = NULL;
 	}
 
@@ -744,6 +744,13 @@ unlock:
 	return ret;
 }
 
+static void s3c24xx_dma_synchronize(struct dma_chan *chan)
+{
+	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
+
+	vchan_synchronize(&s3cchan->vc);
+}
+
 static void s3c24xx_dma_free_chan_resources(struct dma_chan *chan)
 {
 	/* Ensure all queued descriptors are freed */
@@ -1282,6 +1289,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev)
 	s3cdma->memcpy.device_issue_pending = s3c24xx_dma_issue_pending;
 	s3cdma->memcpy.device_config = s3c24xx_dma_set_runtime_config;
 	s3cdma->memcpy.device_terminate_all = s3c24xx_dma_terminate_all;
+	s3cdma->memcpy.device_synchronize = s3c24xx_dma_synchronize;
 
 	/* Initialize slave engine for SoC internal dedicated peripherals */
 	dma_cap_set(DMA_SLAVE, s3cdma->slave.cap_mask);
@@ -1296,6 +1304,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev)
 	s3cdma->slave.device_prep_dma_cyclic = s3c24xx_dma_prep_dma_cyclic;
 	s3cdma->slave.device_config = s3c24xx_dma_set_runtime_config;
 	s3cdma->slave.device_terminate_all = s3c24xx_dma_terminate_all;
+	s3cdma->slave.device_synchronize = s3c24xx_dma_synchronize;
 	s3cdma->slave.filter.map = pdata->slave_map;
 	s3cdma->slave.filter.mapcnt = pdata->slavecnt;
 	s3cdma->slave.filter.fn = s3c24xx_dma_filter;
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 2b2c7db3e480..e3ff162c03fc 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -10,6 +10,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
@@ -741,6 +742,41 @@ static int rcar_dmac_fill_hwdesc(struct rcar_dmac_chan *chan,
 /* -----------------------------------------------------------------------------
  * Stop and reset
  */
+static void rcar_dmac_chcr_de_barrier(struct rcar_dmac_chan *chan)
+{
+	u32 chcr;
+	unsigned int i;
+
+	/*
+	 * Ensure that the setting of the DE bit is actually 0 after
+	 * clearing it.
+	 */
+	for (i = 0; i < 1024; i++) {
+		chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);
+		if (!(chcr & RCAR_DMACHCR_DE))
+			return;
+		udelay(1);
+	}
+
+	dev_err(chan->chan.device->dev, "CHCR DE check error\n");
+}
+
+static void rcar_dmac_sync_tcr(struct rcar_dmac_chan *chan)
+{
+	u32 chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);
+
+	if (!(chcr & RCAR_DMACHCR_DE))
+		return;
+
+	/* set DE=0 and flush remaining data */
+	rcar_dmac_chan_write(chan, RCAR_DMACHCR, (chcr & ~RCAR_DMACHCR_DE));
+
+	/* make sure all remaining data was flushed */
+	rcar_dmac_chcr_de_barrier(chan);
+
+	/* back DE */
+	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr);
+}
 
 static void rcar_dmac_chan_halt(struct rcar_dmac_chan *chan)
 {
@@ -749,6 +785,7 @@ static void rcar_dmac_chan_halt(struct rcar_dmac_chan *chan)
 	chcr &= ~(RCAR_DMACHCR_DSE | RCAR_DMACHCR_DSIE | RCAR_DMACHCR_IE |
 		  RCAR_DMACHCR_TE | RCAR_DMACHCR_DE);
 	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr);
+	rcar_dmac_chcr_de_barrier(chan);
 }
 
 static void rcar_dmac_chan_reinit(struct rcar_dmac_chan *chan)
@@ -1309,8 +1346,11 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 		residue += chunk->size;
 	}
 
+	if (desc->direction == DMA_DEV_TO_MEM)
+		rcar_dmac_sync_tcr(chan);
+
 	/* Add the residue for the current chunk. */
-	residue += rcar_dmac_chan_read(chan, RCAR_DMATCR) << desc->xfer_shift;
+	residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift;
 
 	return residue;
 }
@@ -1481,6 +1521,8 @@ static irqreturn_t rcar_dmac_isr_channel(int irq, void *dev)
 	if (chcr & RCAR_DMACHCR_TE)
 		mask |= RCAR_DMACHCR_DE;
 	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr & ~mask);
+	if (mask & RCAR_DMACHCR_DE)
+		rcar_dmac_chcr_de_barrier(chan);
 
 	if (chcr & RCAR_DMACHCR_DSE)
 		ret |= rcar_dmac_isr_desc_stage_end(chan);
@@ -1615,22 +1657,6 @@ static struct dma_chan *rcar_dmac_of_xlate(struct of_phandle_args *dma_spec,
  * Power management
  */
 
-#ifdef CONFIG_PM_SLEEP
-static int rcar_dmac_sleep_suspend(struct device *dev)
-{
-	/*
-	 * TODO: Wait for the current transfer to complete and stop the device.
-	 */
-	return 0;
-}
-
-static int rcar_dmac_sleep_resume(struct device *dev)
-{
-	/* TODO: Resume transfers, if any. */
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_PM
 static int rcar_dmac_runtime_suspend(struct device *dev)
 {
@@ -1646,7 +1672,13 @@ static int rcar_dmac_runtime_resume(struct device *dev)
 #endif
 
 static const struct dev_pm_ops rcar_dmac_pm = {
-	SET_SYSTEM_SLEEP_PM_OPS(rcar_dmac_sleep_suspend, rcar_dmac_sleep_resume)
+	/*
+	 * TODO for system sleep/resume:
+	 *   - Wait for the current transfer to complete and stop the device,
+	 *   - Resume transfers, if any.
+	 */
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				     pm_runtime_force_resume)
 	SET_RUNTIME_PM_OPS(rcar_dmac_runtime_suspend, rcar_dmac_runtime_resume,
 			   NULL)
 };
diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c
index b652071a2096..b106e8a60af6 100644
--- a/drivers/dma/sprd-dma.c
+++ b/drivers/dma/sprd-dma.c
@@ -710,7 +710,7 @@ static int sprd_dma_config(struct dma_chan *chan, struct sprd_dma_desc *sdesc,
 	return 0;
 }
 
-struct dma_async_tx_descriptor *
+static struct dma_async_tx_descriptor *
 sprd_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 			 size_t len, unsigned long flags)
 {
diff --git a/drivers/dma/stm32-dmamux.c b/drivers/dma/stm32-dmamux.c
index d5db0f6e1ff8..4dbb30cf94ac 100644
--- a/drivers/dma/stm32-dmamux.c
+++ b/drivers/dma/stm32-dmamux.c
@@ -253,9 +253,6 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENODEV;
-
 	iomem = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(iomem))
 		return PTR_ERR(iomem);
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index b9d75a54c896..9a558e30c461 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -353,7 +353,8 @@ static int tegra_dma_slave_config(struct dma_chan *dc,
 	}
 
 	memcpy(&tdc->dma_sconfig, sconfig, sizeof(*sconfig));
-	if (tdc->slave_id == TEGRA_APBDMA_SLAVE_ID_INVALID) {
+	if (tdc->slave_id == TEGRA_APBDMA_SLAVE_ID_INVALID &&
+	    sconfig->device_fc) {
 		if (sconfig->slave_id > TEGRA_APBDMA_CSR_REQ_SEL_MASK)
 			return -EINVAL;
 		tdc->slave_id = sconfig->slave_id;
@@ -970,8 +971,13 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 					TEGRA_APBDMA_AHBSEQ_WRAP_SHIFT;
 	ahb_seq |= TEGRA_APBDMA_AHBSEQ_BUS_WIDTH_32;
 
-	csr |= TEGRA_APBDMA_CSR_ONCE | TEGRA_APBDMA_CSR_FLOW;
-	csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
+	csr |= TEGRA_APBDMA_CSR_ONCE;
+
+	if (tdc->slave_id != TEGRA_APBDMA_SLAVE_ID_INVALID) {
+		csr |= TEGRA_APBDMA_CSR_FLOW;
+		csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
+	}
+
 	if (flags & DMA_PREP_INTERRUPT)
 		csr |= TEGRA_APBDMA_CSR_IE_EOC;
 
@@ -1110,10 +1116,13 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 					TEGRA_APBDMA_AHBSEQ_WRAP_SHIFT;
 	ahb_seq |= TEGRA_APBDMA_AHBSEQ_BUS_WIDTH_32;
 
-	csr |= TEGRA_APBDMA_CSR_FLOW;
+	if (tdc->slave_id != TEGRA_APBDMA_SLAVE_ID_INVALID) {
+		csr |= TEGRA_APBDMA_CSR_FLOW;
+		csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
+	}
+
 	if (flags & DMA_PREP_INTERRUPT)
 		csr |= TEGRA_APBDMA_CSR_IE_EOC;
-	csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
 
 	apb_seq |= TEGRA_APBDMA_APBSEQ_WRAP_WORD_1;
 
diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c
index 7df910e7c348..9272b173c746 100644
--- a/drivers/dma/ti-dma-crossbar.c
+++ b/drivers/dma/ti-dma-crossbar.c
@@ -54,7 +54,15 @@ struct ti_am335x_xbar_map {
 
 static inline void ti_am335x_xbar_write(void __iomem *iomem, int event, u8 val)
 {
-	writeb_relaxed(val, iomem + event);
+	/*
+	 * TPCC_EVT_MUX_60_63 register layout is different than the
+	 * rest, in the sense, that event 63 is mapped to lowest byte
+	 * and event 60 is mapped to highest, handle it separately.
+	 */
+	if (event >= 60 && event <= 63)
+		writeb_relaxed(val, iomem + (63 - event % 4));
+	else
+		writeb_relaxed(val, iomem + event);
 }
 
 static void ti_am335x_xbar_free(struct device *dev, void *route_data)
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index 896bafb7a532..395c698edb4d 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -422,7 +422,7 @@ static int td_alloc_chan_resources(struct dma_chan *chan)
 				break;
 			else {
 				dev_err(chan2dev(chan),
-					"Couldnt allocate any descriptors\n");
+					"Couldn't allocate any descriptors\n");
 				return -ENOMEM;
 			}
 		}
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index 545e97279083..88ad8ed2a8d6 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -107,10 +107,7 @@ static void vchan_complete(unsigned long arg)
 		dmaengine_desc_get_callback(&vd->tx, &cb);
 
 		list_del(&vd->node);
-		if (dmaengine_desc_test_reuse(&vd->tx))
-			list_add(&vd->node, &vc->desc_allocated);
-		else
-			vc->desc_free(vd);
+		vchan_vdesc_fini(vd);
 
 		dmaengine_desc_callback_invoke(&cb, NULL);
 	}
diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h
index 3f776a46a29c..b09b75ab0751 100644
--- a/drivers/dma/virt-dma.h
+++ b/drivers/dma/virt-dma.h
@@ -35,6 +35,7 @@ struct virt_dma_chan {
 	struct list_head desc_completed;
 
 	struct virt_dma_desc *cyclic;
+	struct virt_dma_desc *vd_terminated;
 };
 
 static inline struct virt_dma_chan *to_virt_chan(struct dma_chan *chan)
@@ -104,6 +105,20 @@ static inline void vchan_cookie_complete(struct virt_dma_desc *vd)
 }
 
 /**
+ * vchan_vdesc_fini - Free or reuse a descriptor
+ * @vd: virtual descriptor to free/reuse
+ */
+static inline void vchan_vdesc_fini(struct virt_dma_desc *vd)
+{
+	struct virt_dma_chan *vc = to_virt_chan(vd->tx.chan);
+
+	if (dmaengine_desc_test_reuse(&vd->tx))
+		list_add(&vd->node, &vc->desc_allocated);
+	else
+		vc->desc_free(vd);
+}
+
+/**
  * vchan_cyclic_callback - report the completion of a period
  * @vd: virtual descriptor
  */
@@ -116,6 +131,25 @@ static inline void vchan_cyclic_callback(struct virt_dma_desc *vd)
 }
 
 /**
+ * vchan_terminate_vdesc - Disable pending cyclic callback
+ * @vd: virtual descriptor to be terminated
+ *
+ * vc.lock must be held by caller
+ */
+static inline void vchan_terminate_vdesc(struct virt_dma_desc *vd)
+{
+	struct virt_dma_chan *vc = to_virt_chan(vd->tx.chan);
+
+	/* free up stuck descriptor */
+	if (vc->vd_terminated)
+		vchan_vdesc_fini(vc->vd_terminated);
+
+	vc->vd_terminated = vd;
+	if (vc->cyclic == vd)
+		vc->cyclic = NULL;
+}
+
+/**
  * vchan_next_desc - peek at the next descriptor to be processed
  * @vc: virtual channel to obtain descriptor from
  *
@@ -168,10 +202,20 @@ static inline void vchan_free_chan_resources(struct virt_dma_chan *vc)
  * Makes sure that all scheduled or active callbacks have finished running. For
  * proper operation the caller has to ensure that no new callbacks are scheduled
  * after the invocation of this function started.
+ * Free up the terminated cyclic descriptor to prevent memory leakage.
  */
 static inline void vchan_synchronize(struct virt_dma_chan *vc)
 {
+	unsigned long flags;
+
 	tasklet_kill(&vc->task);
+
+	spin_lock_irqsave(&vc->lock, flags);
+	if (vc->vd_terminated) {
+		vchan_vdesc_fini(vc->vd_terminated);
+		vc->vd_terminated = NULL;
+	}
+	spin_unlock_irqrestore(&vc->lock, flags);
 }
 
 #endif
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 5eef13380ca8..27b523530c4a 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -99,7 +99,9 @@
 #define XILINX_DMA_REG_FRMPTR_STS		0x0024
 #define XILINX_DMA_REG_PARK_PTR		0x0028
 #define XILINX_DMA_PARK_PTR_WR_REF_SHIFT	8
+#define XILINX_DMA_PARK_PTR_WR_REF_MASK		GENMASK(12, 8)
 #define XILINX_DMA_PARK_PTR_RD_REF_SHIFT	0
+#define XILINX_DMA_PARK_PTR_RD_REF_MASK		GENMASK(4, 0)
 #define XILINX_DMA_REG_VDMA_VERSION		0x002c
 
 /* Register Direct Mode Registers */
@@ -163,6 +165,7 @@
 #define XILINX_DMA_BD_SOP		BIT(27)
 #define XILINX_DMA_BD_EOP		BIT(26)
 #define XILINX_DMA_COALESCE_MAX		255
+#define XILINX_DMA_NUM_DESCS		255
 #define XILINX_DMA_NUM_APP_WORDS	5
 
 /* Multi-Channel DMA Descriptor offsets*/
@@ -211,8 +214,8 @@ struct xilinx_vdma_desc_hw {
  * @next_desc_msb: MSB of Next Descriptor Pointer @0x04
  * @buf_addr: Buffer address @0x08
  * @buf_addr_msb: MSB of Buffer address @0x0C
- * @pad1: Reserved @0x10
- * @pad2: Reserved @0x14
+ * @mcdma_control: Control field for mcdma @0x10
+ * @vsize_stride: Vsize and Stride field for mcdma @0x14
  * @control: Control field @0x18
  * @status: Status field @0x1C
  * @app: APP Fields @0x20 - 0x30
@@ -232,11 +235,11 @@ struct xilinx_axidma_desc_hw {
 /**
  * struct xilinx_cdma_desc_hw - Hardware Descriptor
  * @next_desc: Next Descriptor Pointer @0x00
- * @next_descmsb: Next Descriptor Pointer MSB @0x04
+ * @next_desc_msb: Next Descriptor Pointer MSB @0x04
  * @src_addr: Source address @0x08
- * @src_addrmsb: Source address MSB @0x0C
+ * @src_addr_msb: Source address MSB @0x0C
  * @dest_addr: Destination address @0x10
- * @dest_addrmsb: Destination address MSB @0x14
+ * @dest_addr_msb: Destination address MSB @0x14
  * @control: Control field @0x18
  * @status: Status field @0x1C
  */
@@ -310,6 +313,7 @@ struct xilinx_dma_tx_descriptor {
  * @pending_list: Descriptors waiting
  * @active_list: Descriptors ready to submit
  * @done_list: Complete descriptors
+ * @free_seg_list: Free descriptors
  * @common: DMA common channel
  * @desc_pool: Descriptors pool
  * @dev: The dma device
@@ -321,6 +325,7 @@ struct xilinx_dma_tx_descriptor {
  * @cyclic: Check for cyclic transfers.
  * @genlock: Support genlock mode
  * @err: Channel has errors
+ * @idle: Check for channel idle
  * @tasklet: Cleanup work after irq
  * @config: Device configuration info
  * @flush_on_fsync: Flush on Frame sync
@@ -329,9 +334,12 @@ struct xilinx_dma_tx_descriptor {
  * @desc_submitcount: Descriptor h/w submitted count
  * @residue: Residue for AXI DMA
  * @seg_v: Statically allocated segments base
+ * @seg_p: Physical allocated segments base
  * @cyclic_seg_v: Statically allocated segment base for cyclic transfers
+ * @cyclic_seg_p: Physical allocated segments base for cyclic dma
  * @start_transfer: Differentiate b/w DMA IP's transfer
  * @stop_transfer: Differentiate b/w DMA IP's quiesce
+ * @tdest: TDEST value for mcdma
  */
 struct xilinx_dma_chan {
 	struct xilinx_dma_device *xdev;
@@ -341,6 +349,7 @@ struct xilinx_dma_chan {
 	struct list_head pending_list;
 	struct list_head active_list;
 	struct list_head done_list;
+	struct list_head free_seg_list;
 	struct dma_chan common;
 	struct dma_pool *desc_pool;
 	struct device *dev;
@@ -352,6 +361,7 @@ struct xilinx_dma_chan {
 	bool cyclic;
 	bool genlock;
 	bool err;
+	bool idle;
 	struct tasklet_struct tasklet;
 	struct xilinx_vdma_config config;
 	bool flush_on_fsync;
@@ -360,18 +370,20 @@ struct xilinx_dma_chan {
 	u32 desc_submitcount;
 	u32 residue;
 	struct xilinx_axidma_tx_segment *seg_v;
+	dma_addr_t seg_p;
 	struct xilinx_axidma_tx_segment *cyclic_seg_v;
+	dma_addr_t cyclic_seg_p;
 	void (*start_transfer)(struct xilinx_dma_chan *chan);
 	int (*stop_transfer)(struct xilinx_dma_chan *chan);
 	u16 tdest;
 };
 
 /**
- * enum xdma_ip_type: DMA IP type.
+ * enum xdma_ip_type - DMA IP type.
  *
- * XDMA_TYPE_AXIDMA: Axi dma ip.
- * XDMA_TYPE_CDMA: Axi cdma ip.
- * XDMA_TYPE_VDMA: Axi vdma ip.
+ * @XDMA_TYPE_AXIDMA: Axi dma ip.
+ * @XDMA_TYPE_CDMA: Axi cdma ip.
+ * @XDMA_TYPE_VDMA: Axi vdma ip.
  *
  */
 enum xdma_ip_type {
@@ -580,18 +592,32 @@ xilinx_cdma_alloc_tx_segment(struct xilinx_dma_chan *chan)
 static struct xilinx_axidma_tx_segment *
 xilinx_axidma_alloc_tx_segment(struct xilinx_dma_chan *chan)
 {
-	struct xilinx_axidma_tx_segment *segment;
-	dma_addr_t phys;
-
-	segment = dma_pool_zalloc(chan->desc_pool, GFP_ATOMIC, &phys);
-	if (!segment)
-		return NULL;
+	struct xilinx_axidma_tx_segment *segment = NULL;
+	unsigned long flags;
 
-	segment->phys = phys;
+	spin_lock_irqsave(&chan->lock, flags);
+	if (!list_empty(&chan->free_seg_list)) {
+		segment = list_first_entry(&chan->free_seg_list,
+					   struct xilinx_axidma_tx_segment,
+					   node);
+		list_del(&segment->node);
+	}
+	spin_unlock_irqrestore(&chan->lock, flags);
 
 	return segment;
 }
 
+static void xilinx_dma_clean_hw_desc(struct xilinx_axidma_desc_hw *hw)
+{
+	u32 next_desc = hw->next_desc;
+	u32 next_desc_msb = hw->next_desc_msb;
+
+	memset(hw, 0, sizeof(struct xilinx_axidma_desc_hw));
+
+	hw->next_desc = next_desc;
+	hw->next_desc_msb = next_desc_msb;
+}
+
 /**
  * xilinx_dma_free_tx_segment - Free transaction segment
  * @chan: Driver specific DMA channel
@@ -600,7 +626,9 @@ xilinx_axidma_alloc_tx_segment(struct xilinx_dma_chan *chan)
 static void xilinx_dma_free_tx_segment(struct xilinx_dma_chan *chan,
 				struct xilinx_axidma_tx_segment *segment)
 {
-	dma_pool_free(chan->desc_pool, segment, segment->phys);
+	xilinx_dma_clean_hw_desc(&segment->hw);
+
+	list_add_tail(&segment->node, &chan->free_seg_list);
 }
 
 /**
@@ -725,16 +753,31 @@ static void xilinx_dma_free_descriptors(struct xilinx_dma_chan *chan)
 static void xilinx_dma_free_chan_resources(struct dma_chan *dchan)
 {
 	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	unsigned long flags;
 
 	dev_dbg(chan->dev, "Free all channel resources.\n");
 
 	xilinx_dma_free_descriptors(chan);
+
 	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
-		xilinx_dma_free_tx_segment(chan, chan->cyclic_seg_v);
-		xilinx_dma_free_tx_segment(chan, chan->seg_v);
+		spin_lock_irqsave(&chan->lock, flags);
+		INIT_LIST_HEAD(&chan->free_seg_list);
+		spin_unlock_irqrestore(&chan->lock, flags);
+
+		/* Free memory that is allocated for BD */
+		dma_free_coherent(chan->dev, sizeof(*chan->seg_v) *
+				  XILINX_DMA_NUM_DESCS, chan->seg_v,
+				  chan->seg_p);
+
+		/* Free Memory that is allocated for cyclic DMA Mode */
+		dma_free_coherent(chan->dev, sizeof(*chan->cyclic_seg_v),
+				  chan->cyclic_seg_v, chan->cyclic_seg_p);
+	}
+
+	if (chan->xdev->dma_config->dmatype != XDMA_TYPE_AXIDMA) {
+		dma_pool_destroy(chan->desc_pool);
+		chan->desc_pool = NULL;
 	}
-	dma_pool_destroy(chan->desc_pool);
-	chan->desc_pool = NULL;
 }
 
 /**
@@ -817,6 +860,7 @@ static void xilinx_dma_do_tasklet(unsigned long data)
 static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 {
 	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	int i;
 
 	/* Has this channel already been allocated? */
 	if (chan->desc_pool)
@@ -827,11 +871,30 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 	 * for meeting Xilinx VDMA specification requirement.
 	 */
 	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
-		chan->desc_pool = dma_pool_create("xilinx_dma_desc_pool",
-				   chan->dev,
-				   sizeof(struct xilinx_axidma_tx_segment),
-				   __alignof__(struct xilinx_axidma_tx_segment),
-				   0);
+		/* Allocate the buffer descriptors. */
+		chan->seg_v = dma_zalloc_coherent(chan->dev,
+						  sizeof(*chan->seg_v) *
+						  XILINX_DMA_NUM_DESCS,
+						  &chan->seg_p, GFP_KERNEL);
+		if (!chan->seg_v) {
+			dev_err(chan->dev,
+				"unable to allocate channel %d descriptors\n",
+				chan->id);
+			return -ENOMEM;
+		}
+
+		for (i = 0; i < XILINX_DMA_NUM_DESCS; i++) {
+			chan->seg_v[i].hw.next_desc =
+			lower_32_bits(chan->seg_p + sizeof(*chan->seg_v) *
+				((i + 1) % XILINX_DMA_NUM_DESCS));
+			chan->seg_v[i].hw.next_desc_msb =
+			upper_32_bits(chan->seg_p + sizeof(*chan->seg_v) *
+				((i + 1) % XILINX_DMA_NUM_DESCS));
+			chan->seg_v[i].phys = chan->seg_p +
+				sizeof(*chan->seg_v) * i;
+			list_add_tail(&chan->seg_v[i].node,
+				      &chan->free_seg_list);
+		}
 	} else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) {
 		chan->desc_pool = dma_pool_create("xilinx_cdma_desc_pool",
 				   chan->dev,
@@ -846,7 +909,8 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 				     0);
 	}
 
-	if (!chan->desc_pool) {
+	if (!chan->desc_pool &&
+	    (chan->xdev->dma_config->dmatype != XDMA_TYPE_AXIDMA)) {
 		dev_err(chan->dev,
 			"unable to allocate channel %d descriptor pool\n",
 			chan->id);
@@ -855,22 +919,20 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 
 	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
 		/*
-		 * For AXI DMA case after submitting a pending_list, keep
-		 * an extra segment allocated so that the "next descriptor"
-		 * pointer on the tail descriptor always points to a
-		 * valid descriptor, even when paused after reaching taildesc.
-		 * This way, it is possible to issue additional
-		 * transfers without halting and restarting the channel.
-		 */
-		chan->seg_v = xilinx_axidma_alloc_tx_segment(chan);
-
-		/*
 		 * For cyclic DMA mode we need to program the tail Descriptor
 		 * register with a value which is not a part of the BD chain
 		 * so allocating a desc segment during channel allocation for
 		 * programming tail descriptor.
 		 */
-		chan->cyclic_seg_v = xilinx_axidma_alloc_tx_segment(chan);
+		chan->cyclic_seg_v = dma_zalloc_coherent(chan->dev,
+					sizeof(*chan->cyclic_seg_v),
+					&chan->cyclic_seg_p, GFP_KERNEL);
+		if (!chan->cyclic_seg_v) {
+			dev_err(chan->dev,
+				"unable to allocate desc segment for cyclic DMA\n");
+			return -ENOMEM;
+		}
+		chan->cyclic_seg_v->phys = chan->cyclic_seg_p;
 	}
 
 	dma_cookie_init(dchan);
@@ -936,34 +998,10 @@ static enum dma_status xilinx_dma_tx_status(struct dma_chan *dchan,
 }
 
 /**
- * xilinx_dma_is_running - Check if DMA channel is running
- * @chan: Driver specific DMA channel
- *
- * Return: '1' if running, '0' if not.
- */
-static bool xilinx_dma_is_running(struct xilinx_dma_chan *chan)
-{
-	return !(dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) &
-		 XILINX_DMA_DMASR_HALTED) &&
-		(dma_ctrl_read(chan, XILINX_DMA_REG_DMACR) &
-		 XILINX_DMA_DMACR_RUNSTOP);
-}
-
-/**
- * xilinx_dma_is_idle - Check if DMA channel is idle
- * @chan: Driver specific DMA channel
- *
- * Return: '1' if idle, '0' if not.
- */
-static bool xilinx_dma_is_idle(struct xilinx_dma_chan *chan)
-{
-	return dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) &
-		XILINX_DMA_DMASR_IDLE;
-}
-
-/**
  * xilinx_dma_stop_transfer - Halt DMA channel
  * @chan: Driver specific DMA channel
+ *
+ * Return: '0' on success and failure value on error
  */
 static int xilinx_dma_stop_transfer(struct xilinx_dma_chan *chan)
 {
@@ -980,6 +1018,8 @@ static int xilinx_dma_stop_transfer(struct xilinx_dma_chan *chan)
 /**
  * xilinx_cdma_stop_transfer - Wait for the current transfer to complete
  * @chan: Driver specific DMA channel
+ *
+ * Return: '0' on success and failure value on error
  */
 static int xilinx_cdma_stop_transfer(struct xilinx_dma_chan *chan)
 {
@@ -1022,13 +1062,16 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 {
 	struct xilinx_vdma_config *config = &chan->config;
 	struct xilinx_dma_tx_descriptor *desc, *tail_desc;
-	u32 reg;
+	u32 reg, j;
 	struct xilinx_vdma_tx_segment *tail_segment;
 
 	/* This function was invoked with lock held */
 	if (chan->err)
 		return;
 
+	if (!chan->idle)
+		return;
+
 	if (list_empty(&chan->pending_list))
 		return;
 
@@ -1040,13 +1083,6 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 	tail_segment = list_last_entry(&tail_desc->segments,
 				       struct xilinx_vdma_tx_segment, node);
 
-	/* If it is SG mode and hardware is busy, cannot submit */
-	if (chan->has_sg && xilinx_dma_is_running(chan) &&
-	    !xilinx_dma_is_idle(chan)) {
-		dev_dbg(chan->dev, "DMA controller still busy\n");
-		return;
-	}
-
 	/*
 	 * If hardware is idle, then all descriptors on the running lists are
 	 * done, start new transfers
@@ -1063,10 +1099,6 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 	else
 		reg &= ~XILINX_DMA_DMACR_FRAMECNT_EN;
 
-	/* Configure channel to allow number frame buffers */
-	dma_ctrl_write(chan, XILINX_DMA_REG_FRMSTORE,
-			chan->desc_pendingcount);
-
 	/*
 	 * With SG, start with circular mode, so that BDs can be fetched.
 	 * In direct register mode, if not parking, enable circular mode
@@ -1079,17 +1111,16 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 
 	dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg);
 
-	if (config->park && (config->park_frm >= 0) &&
-			(config->park_frm < chan->num_frms)) {
-		if (chan->direction == DMA_MEM_TO_DEV)
-			dma_write(chan, XILINX_DMA_REG_PARK_PTR,
-				config->park_frm <<
-					XILINX_DMA_PARK_PTR_RD_REF_SHIFT);
-		else
-			dma_write(chan, XILINX_DMA_REG_PARK_PTR,
-				config->park_frm <<
-					XILINX_DMA_PARK_PTR_WR_REF_SHIFT);
+	j = chan->desc_submitcount;
+	reg = dma_read(chan, XILINX_DMA_REG_PARK_PTR);
+	if (chan->direction == DMA_MEM_TO_DEV) {
+		reg &= ~XILINX_DMA_PARK_PTR_RD_REF_MASK;
+		reg |= j << XILINX_DMA_PARK_PTR_RD_REF_SHIFT;
+	} else {
+		reg &= ~XILINX_DMA_PARK_PTR_WR_REF_MASK;
+		reg |= j << XILINX_DMA_PARK_PTR_WR_REF_SHIFT;
 	}
+	dma_write(chan, XILINX_DMA_REG_PARK_PTR, reg);
 
 	/* Start the hardware */
 	xilinx_dma_start(chan);
@@ -1101,6 +1132,8 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 	if (chan->has_sg) {
 		dma_ctrl_write(chan, XILINX_DMA_REG_TAILDESC,
 				tail_segment->phys);
+		list_splice_tail_init(&chan->pending_list, &chan->active_list);
+		chan->desc_pendingcount = 0;
 	} else {
 		struct xilinx_vdma_tx_segment *segment, *last = NULL;
 		int i = 0;
@@ -1130,19 +1163,16 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 		vdma_desc_write(chan, XILINX_DMA_REG_FRMDLY_STRIDE,
 				last->hw.stride);
 		vdma_desc_write(chan, XILINX_DMA_REG_VSIZE, last->hw.vsize);
-	}
 
-	if (!chan->has_sg) {
-		list_del(&desc->node);
-		list_add_tail(&desc->node, &chan->active_list);
 		chan->desc_submitcount++;
 		chan->desc_pendingcount--;
+		list_del(&desc->node);
+		list_add_tail(&desc->node, &chan->active_list);
 		if (chan->desc_submitcount == chan->num_frms)
 			chan->desc_submitcount = 0;
-	} else {
-		list_splice_tail_init(&chan->pending_list, &chan->active_list);
-		chan->desc_pendingcount = 0;
 	}
+
+	chan->idle = false;
 }
 
 /**
@@ -1158,6 +1188,9 @@ static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)
 	if (chan->err)
 		return;
 
+	if (!chan->idle)
+		return;
+
 	if (list_empty(&chan->pending_list))
 		return;
 
@@ -1176,6 +1209,12 @@ static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)
 	}
 
 	if (chan->has_sg) {
+		dma_ctrl_clr(chan, XILINX_DMA_REG_DMACR,
+			     XILINX_CDMA_CR_SGMODE);
+
+		dma_ctrl_set(chan, XILINX_DMA_REG_DMACR,
+			     XILINX_CDMA_CR_SGMODE);
+
 		xilinx_write(chan, XILINX_DMA_REG_CURDESC,
 			     head_desc->async_tx.phys);
 
@@ -1203,6 +1242,7 @@ static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)
 
 	list_splice_tail_init(&chan->pending_list, &chan->active_list);
 	chan->desc_pendingcount = 0;
+	chan->idle = false;
 }
 
 /**
@@ -1212,7 +1252,7 @@ static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)
 static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 {
 	struct xilinx_dma_tx_descriptor *head_desc, *tail_desc;
-	struct xilinx_axidma_tx_segment *tail_segment, *old_head, *new_head;
+	struct xilinx_axidma_tx_segment *tail_segment;
 	u32 reg;
 
 	if (chan->err)
@@ -1221,12 +1261,8 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 	if (list_empty(&chan->pending_list))
 		return;
 
-	/* If it is SG mode and hardware is busy, cannot submit */
-	if (chan->has_sg && xilinx_dma_is_running(chan) &&
-	    !xilinx_dma_is_idle(chan)) {
-		dev_dbg(chan->dev, "DMA controller still busy\n");
+	if (!chan->idle)
 		return;
-	}
 
 	head_desc = list_first_entry(&chan->pending_list,
 				     struct xilinx_dma_tx_descriptor, node);
@@ -1235,21 +1271,6 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 	tail_segment = list_last_entry(&tail_desc->segments,
 				       struct xilinx_axidma_tx_segment, node);
 
-	if (chan->has_sg && !chan->xdev->mcdma) {
-		old_head = list_first_entry(&head_desc->segments,
-					struct xilinx_axidma_tx_segment, node);
-		new_head = chan->seg_v;
-		/* Copy Buffer Descriptor fields. */
-		new_head->hw = old_head->hw;
-
-		/* Swap and save new reserve */
-		list_replace_init(&old_head->node, &new_head->node);
-		chan->seg_v = old_head;
-
-		tail_segment->hw.next_desc = chan->seg_v->phys;
-		head_desc->async_tx.phys = new_head->phys;
-	}
-
 	reg = dma_ctrl_read(chan, XILINX_DMA_REG_DMACR);
 
 	if (chan->desc_pendingcount <= XILINX_DMA_COALESCE_MAX) {
@@ -1324,6 +1345,7 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 
 	list_splice_tail_init(&chan->pending_list, &chan->active_list);
 	chan->desc_pendingcount = 0;
+	chan->idle = false;
 }
 
 /**
@@ -1388,6 +1410,8 @@ static int xilinx_dma_reset(struct xilinx_dma_chan *chan)
 	}
 
 	chan->err = false;
+	chan->idle = true;
+	chan->desc_submitcount = 0;
 
 	return err;
 }
@@ -1469,6 +1493,7 @@ static irqreturn_t xilinx_dma_irq_handler(int irq, void *data)
 	if (status & XILINX_DMA_DMASR_FRM_CNT_IRQ) {
 		spin_lock(&chan->lock);
 		xilinx_dma_complete_descriptor(chan);
+		chan->idle = true;
 		chan->start_transfer(chan);
 		spin_unlock(&chan->lock);
 	}
@@ -1591,7 +1616,7 @@ xilinx_vdma_dma_prep_interleaved(struct dma_chan *dchan,
 {
 	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
 	struct xilinx_dma_tx_descriptor *desc;
-	struct xilinx_vdma_tx_segment *segment, *prev = NULL;
+	struct xilinx_vdma_tx_segment *segment;
 	struct xilinx_vdma_desc_hw *hw;
 
 	if (!is_slave_direction(xt->dir))
@@ -1645,8 +1670,6 @@ xilinx_vdma_dma_prep_interleaved(struct dma_chan *dchan,
 	/* Insert the segment into the descriptor segments list. */
 	list_add_tail(&segment->node, &desc->segments);
 
-	prev = segment;
-
 	/* Link the last hardware descriptor with the first. */
 	segment = list_first_entry(&desc->segments,
 				   struct xilinx_vdma_tx_segment, node);
@@ -1733,7 +1756,7 @@ static struct dma_async_tx_descriptor *xilinx_dma_prep_slave_sg(
 {
 	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
 	struct xilinx_dma_tx_descriptor *desc;
-	struct xilinx_axidma_tx_segment *segment = NULL, *prev = NULL;
+	struct xilinx_axidma_tx_segment *segment = NULL;
 	u32 *app_w = (u32 *)context;
 	struct scatterlist *sg;
 	size_t copy;
@@ -1784,10 +1807,6 @@ static struct dma_async_tx_descriptor *xilinx_dma_prep_slave_sg(
 					       XILINX_DMA_NUM_APP_WORDS);
 			}
 
-			if (prev)
-				prev->hw.next_desc = segment->phys;
-
-			prev = segment;
 			sg_used += copy;
 
 			/*
@@ -1801,7 +1820,6 @@ static struct dma_async_tx_descriptor *xilinx_dma_prep_slave_sg(
 	segment = list_first_entry(&desc->segments,
 				   struct xilinx_axidma_tx_segment, node);
 	desc->async_tx.phys = segment->phys;
-	prev->hw.next_desc = segment->phys;
 
 	/* For the last DMA_MEM_TO_DEV transfer, set EOP */
 	if (chan->direction == DMA_MEM_TO_DEV) {
@@ -1821,11 +1839,14 @@ error:
 
 /**
  * xilinx_dma_prep_dma_cyclic - prepare descriptors for a DMA_SLAVE transaction
- * @chan: DMA channel
- * @sgl: scatterlist to transfer to/from
- * @sg_len: number of entries in @scatterlist
+ * @dchan: DMA channel
+ * @buf_addr: Physical address of the buffer
+ * @buf_len: Total length of the cyclic buffers
+ * @period_len: length of individual cyclic buffer
  * @direction: DMA direction
  * @flags: transfer ack flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
  */
 static struct dma_async_tx_descriptor *xilinx_dma_prep_dma_cyclic(
 	struct dma_chan *dchan, dma_addr_t buf_addr, size_t buf_len,
@@ -2009,7 +2030,9 @@ error:
 
 /**
  * xilinx_dma_terminate_all - Halt the channel and free descriptors
- * @chan: Driver specific DMA Channel pointer
+ * @dchan: Driver specific DMA Channel pointer
+ *
+ * Return: '0' always.
  */
 static int xilinx_dma_terminate_all(struct dma_chan *dchan)
 {
@@ -2029,6 +2052,7 @@ static int xilinx_dma_terminate_all(struct dma_chan *dchan)
 
 	/* Remove and free all of the descriptors in the lists */
 	xilinx_dma_free_descriptors(chan);
+	chan->idle = true;
 
 	if (chan->cyclic) {
 		reg = dma_ctrl_read(chan, XILINX_DMA_REG_DMACR);
@@ -2037,6 +2061,10 @@ static int xilinx_dma_terminate_all(struct dma_chan *dchan)
 		chan->cyclic = false;
 	}
 
+	if ((chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) && chan->has_sg)
+		dma_ctrl_clr(chan, XILINX_DMA_REG_DMACR,
+			     XILINX_CDMA_CR_SGMODE);
+
 	return 0;
 }
 
@@ -2323,6 +2351,7 @@ static void xdma_disable_allclks(struct xilinx_dma_device *xdev)
  *
  * @xdev: Driver specific device structure
  * @node: Device node
+ * @chan_id: DMA Channel id
  *
  * Return: '0' on success and failure value on error
  */
@@ -2344,11 +2373,18 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 	chan->has_sg = xdev->has_sg;
 	chan->desc_pendingcount = 0x0;
 	chan->ext_addr = xdev->ext_addr;
+	/* This variable ensures that descriptors are not
+	 * Submitted when dma engine is in progress. This variable is
+	 * Added to avoid polling for a bit in the status register to
+	 * Know dma state in the driver hot path.
+	 */
+	chan->idle = true;
 
 	spin_lock_init(&chan->lock);
 	INIT_LIST_HEAD(&chan->pending_list);
 	INIT_LIST_HEAD(&chan->done_list);
 	INIT_LIST_HEAD(&chan->active_list);
+	INIT_LIST_HEAD(&chan->free_seg_list);
 
 	/* Retrieve the channel properties from the device tree */
 	has_dre = of_property_read_bool(node, "xlnx,include-dre");
@@ -2379,6 +2415,7 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		chan->ctrl_offset = XILINX_DMA_MM2S_CTRL_OFFSET;
 		if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
 			chan->desc_offset = XILINX_VDMA_MM2S_DESC_OFFSET;
+			chan->config.park = 1;
 
 			if (xdev->flush_on_fsync == XILINX_DMA_FLUSH_BOTH ||
 			    xdev->flush_on_fsync == XILINX_DMA_FLUSH_MM2S)
@@ -2395,6 +2432,7 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		chan->ctrl_offset = XILINX_DMA_S2MM_CTRL_OFFSET;
 		if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
 			chan->desc_offset = XILINX_VDMA_S2MM_DESC_OFFSET;
+			chan->config.park = 1;
 
 			if (xdev->flush_on_fsync == XILINX_DMA_FLUSH_BOTH ||
 			    xdev->flush_on_fsync == XILINX_DMA_FLUSH_S2MM)
@@ -2459,7 +2497,8 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
  * Return: 0 always.
  */
 static int xilinx_dma_child_probe(struct xilinx_dma_device *xdev,
-				    struct device_node *node) {
+				    struct device_node *node)
+{
 	int ret, i, nr_channels = 1;
 
 	ret = of_property_read_u32(node, "dma-channels", &nr_channels);
@@ -2654,7 +2693,12 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 		goto error;
 	}
 
-	dev_info(&pdev->dev, "Xilinx AXI VDMA Engine Driver Probed!!\n");
+	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA)
+		dev_info(&pdev->dev, "Xilinx AXI DMA Engine Driver Probed!!\n");
+	else if (xdev->dma_config->dmatype == XDMA_TYPE_CDMA)
+		dev_info(&pdev->dev, "Xilinx AXI CDMA Engine Driver Probed!!\n");
+	else
+		dev_info(&pdev->dev, "Xilinx AXI VDMA Engine Driver Probed!!\n");
 
 	return 0;
 
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index 1ee1241ca797..f14645817ed8 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/clk.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/pm_runtime.h>
 
 #include "../dmaengine.h"
 
@@ -47,6 +48,7 @@
 #define ZYNQMP_DMA_SRC_START_MSB	0x15C
 #define ZYNQMP_DMA_DST_START_LSB	0x160
 #define ZYNQMP_DMA_DST_START_MSB	0x164
+#define ZYNQMP_DMA_TOTAL_BYTE		0x188
 #define ZYNQMP_DMA_RATE_CTRL		0x18C
 #define ZYNQMP_DMA_IRQ_SRC_ACCT		0x190
 #define ZYNQMP_DMA_IRQ_DST_ACCT		0x194
@@ -138,6 +140,8 @@
 #define ZYNQMP_DMA_BUS_WIDTH_64		64
 #define ZYNQMP_DMA_BUS_WIDTH_128	128
 
+#define ZDMA_PM_TIMEOUT			100
+
 #define ZYNQMP_DMA_DESC_SIZE(chan)	(chan->desc_size)
 
 #define to_chan(chan)		container_of(chan, struct zynqmp_dma_chan, \
@@ -211,8 +215,6 @@ struct zynqmp_dma_desc_sw {
  * @bus_width: Bus width
  * @src_burst_len: Source burst length
  * @dst_burst_len: Dest burst length
- * @clk_main: Pointer to main clock
- * @clk_apb: Pointer to apb clock
  */
 struct zynqmp_dma_chan {
 	struct zynqmp_dma_device *zdev;
@@ -237,8 +239,6 @@ struct zynqmp_dma_chan {
 	u32 bus_width;
 	u32 src_burst_len;
 	u32 dst_burst_len;
-	struct clk *clk_main;
-	struct clk *clk_apb;
 };
 
 /**
@@ -246,11 +246,15 @@ struct zynqmp_dma_chan {
  * @dev: Device Structure
  * @common: DMA device structure
  * @chan: Driver specific DMA channel
+ * @clk_main: Pointer to main clock
+ * @clk_apb: Pointer to apb clock
  */
 struct zynqmp_dma_device {
 	struct device *dev;
 	struct dma_device common;
 	struct zynqmp_dma_chan *chan;
+	struct clk *clk_main;
+	struct clk *clk_apb;
 };
 
 static inline void zynqmp_dma_writeq(struct zynqmp_dma_chan *chan, u32 reg,
@@ -461,7 +465,11 @@ static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan)
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
 	struct zynqmp_dma_desc_sw *desc;
-	int i;
+	int i, ret;
+
+	ret = pm_runtime_get_sync(chan->dev);
+	if (ret < 0)
+		return ret;
 
 	chan->sw_desc_pool = kzalloc(sizeof(*desc) * ZYNQMP_DMA_NUM_DESCS,
 				     GFP_KERNEL);
@@ -506,6 +514,7 @@ static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan)
 static void zynqmp_dma_start(struct zynqmp_dma_chan *chan)
 {
 	writel(ZYNQMP_DMA_INT_EN_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IER);
+	writel(0, chan->regs + ZYNQMP_DMA_TOTAL_BYTE);
 	chan->idle = false;
 	writel(ZYNQMP_DMA_ENABLE, chan->regs + ZYNQMP_DMA_CTRL2);
 }
@@ -517,12 +526,12 @@ static void zynqmp_dma_start(struct zynqmp_dma_chan *chan)
  */
 static void zynqmp_dma_handle_ovfl_int(struct zynqmp_dma_chan *chan, u32 status)
 {
-	u32 val;
-
+	if (status & ZYNQMP_DMA_BYTE_CNT_OVRFL)
+		writel(0, chan->regs + ZYNQMP_DMA_TOTAL_BYTE);
 	if (status & ZYNQMP_DMA_IRQ_DST_ACCT_ERR)
-		val = readl(chan->regs + ZYNQMP_DMA_IRQ_DST_ACCT);
+		readl(chan->regs + ZYNQMP_DMA_IRQ_DST_ACCT);
 	if (status & ZYNQMP_DMA_IRQ_SRC_ACCT_ERR)
-		val = readl(chan->regs + ZYNQMP_DMA_IRQ_SRC_ACCT);
+		readl(chan->regs + ZYNQMP_DMA_IRQ_SRC_ACCT);
 }
 
 static void zynqmp_dma_config(struct zynqmp_dma_chan *chan)
@@ -545,6 +554,8 @@ static void zynqmp_dma_config(struct zynqmp_dma_chan *chan)
  * zynqmp_dma_device_config - Zynqmp dma device configuration
  * @dchan: DMA channel
  * @config: DMA device config
+ *
+ * Return: 0 always
  */
 static int zynqmp_dma_device_config(struct dma_chan *dchan,
 				    struct dma_slave_config *config)
@@ -640,7 +651,7 @@ static void zynqmp_dma_issue_pending(struct dma_chan *dchan)
 
 /**
  * zynqmp_dma_free_descriptors - Free channel descriptors
- * @dchan: DMA channel pointer
+ * @chan: ZynqMP DMA channel pointer
  */
 static void zynqmp_dma_free_descriptors(struct zynqmp_dma_chan *chan)
 {
@@ -664,6 +675,8 @@ static void zynqmp_dma_free_chan_resources(struct dma_chan *dchan)
 		(2 * ZYNQMP_DMA_DESC_SIZE(chan) * ZYNQMP_DMA_NUM_DESCS),
 		chan->desc_pool_v, chan->desc_pool_p);
 	kfree(chan->sw_desc_pool);
+	pm_runtime_mark_last_busy(chan->dev);
+	pm_runtime_put_autosuspend(chan->dev);
 }
 
 /**
@@ -715,7 +728,7 @@ static irqreturn_t zynqmp_dma_irq_handler(int irq, void *data)
 
 	if (status & ZYNQMP_DMA_INT_OVRFL) {
 		zynqmp_dma_handle_ovfl_int(chan, status);
-		dev_info(chan->dev, "Channel %p overflow interrupt\n", chan);
+		dev_dbg(chan->dev, "Channel %p overflow interrupt\n", chan);
 		ret = IRQ_HANDLED;
 	}
 
@@ -838,11 +851,10 @@ static void zynqmp_dma_chan_remove(struct zynqmp_dma_chan *chan)
 	if (!chan)
 		return;
 
-	devm_free_irq(chan->zdev->dev, chan->irq, chan);
+	if (chan->irq)
+		devm_free_irq(chan->zdev->dev, chan->irq, chan);
 	tasklet_kill(&chan->tasklet);
 	list_del(&chan->common.device_node);
-	clk_disable_unprepare(chan->clk_apb);
-	clk_disable_unprepare(chan->clk_main);
 }
 
 /**
@@ -907,30 +919,6 @@ static int zynqmp_dma_chan_probe(struct zynqmp_dma_device *zdev,
 			       "zynqmp-dma", chan);
 	if (err)
 		return err;
-	chan->clk_main = devm_clk_get(&pdev->dev, "clk_main");
-	if (IS_ERR(chan->clk_main)) {
-		dev_err(&pdev->dev, "main clock not found.\n");
-		return PTR_ERR(chan->clk_main);
-	}
-
-	chan->clk_apb = devm_clk_get(&pdev->dev, "clk_apb");
-	if (IS_ERR(chan->clk_apb)) {
-		dev_err(&pdev->dev, "apb clock not found.\n");
-		return PTR_ERR(chan->clk_apb);
-	}
-
-	err = clk_prepare_enable(chan->clk_main);
-	if (err) {
-		dev_err(&pdev->dev, "Unable to enable main clock.\n");
-		return err;
-	}
-
-	err = clk_prepare_enable(chan->clk_apb);
-	if (err) {
-		clk_disable_unprepare(chan->clk_main);
-		dev_err(&pdev->dev, "Unable to enable apb clock.\n");
-		return err;
-	}
 
 	chan->desc_size = sizeof(struct zynqmp_dma_desc_ll);
 	chan->idle = true;
@@ -953,6 +941,87 @@ static struct dma_chan *of_zynqmp_dma_xlate(struct of_phandle_args *dma_spec,
 }
 
 /**
+ * zynqmp_dma_suspend - Suspend method for the driver
+ * @dev:	Address of the device structure
+ *
+ * Put the driver into low power mode.
+ * Return: 0 on success and failure value on error
+ */
+static int __maybe_unused zynqmp_dma_suspend(struct device *dev)
+{
+	if (!device_may_wakeup(dev))
+		return pm_runtime_force_suspend(dev);
+
+	return 0;
+}
+
+/**
+ * zynqmp_dma_resume - Resume from suspend
+ * @dev:	Address of the device structure
+ *
+ * Resume operation after suspend.
+ * Return: 0 on success and failure value on error
+ */
+static int __maybe_unused zynqmp_dma_resume(struct device *dev)
+{
+	if (!device_may_wakeup(dev))
+		return pm_runtime_force_resume(dev);
+
+	return 0;
+}
+
+/**
+ * zynqmp_dma_runtime_suspend - Runtime suspend method for the driver
+ * @dev:	Address of the device structure
+ *
+ * Put the driver into low power mode.
+ * Return: 0 always
+ */
+static int __maybe_unused zynqmp_dma_runtime_suspend(struct device *dev)
+{
+	struct zynqmp_dma_device *zdev = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(zdev->clk_main);
+	clk_disable_unprepare(zdev->clk_apb);
+
+	return 0;
+}
+
+/**
+ * zynqmp_dma_runtime_resume - Runtime suspend method for the driver
+ * @dev:	Address of the device structure
+ *
+ * Put the driver into low power mode.
+ * Return: 0 always
+ */
+static int __maybe_unused zynqmp_dma_runtime_resume(struct device *dev)
+{
+	struct zynqmp_dma_device *zdev = dev_get_drvdata(dev);
+	int err;
+
+	err = clk_prepare_enable(zdev->clk_main);
+	if (err) {
+		dev_err(dev, "Unable to enable main clock.\n");
+		return err;
+	}
+
+	err = clk_prepare_enable(zdev->clk_apb);
+	if (err) {
+		dev_err(dev, "Unable to enable apb clock.\n");
+		clk_disable_unprepare(zdev->clk_main);
+		return err;
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops zynqmp_dma_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(zynqmp_dma_suspend, zynqmp_dma_resume)
+	SET_RUNTIME_PM_OPS(zynqmp_dma_runtime_suspend,
+			   zynqmp_dma_runtime_resume, NULL)
+};
+
+/**
  * zynqmp_dma_probe - Driver probe function
  * @pdev: Pointer to the platform_device structure
  *
@@ -984,12 +1053,33 @@ static int zynqmp_dma_probe(struct platform_device *pdev)
 	p->device_config = zynqmp_dma_device_config;
 	p->dev = &pdev->dev;
 
+	zdev->clk_main = devm_clk_get(&pdev->dev, "clk_main");
+	if (IS_ERR(zdev->clk_main)) {
+		dev_err(&pdev->dev, "main clock not found.\n");
+		return PTR_ERR(zdev->clk_main);
+	}
+
+	zdev->clk_apb = devm_clk_get(&pdev->dev, "clk_apb");
+	if (IS_ERR(zdev->clk_apb)) {
+		dev_err(&pdev->dev, "apb clock not found.\n");
+		return PTR_ERR(zdev->clk_apb);
+	}
+
 	platform_set_drvdata(pdev, zdev);
+	pm_runtime_set_autosuspend_delay(zdev->dev, ZDMA_PM_TIMEOUT);
+	pm_runtime_use_autosuspend(zdev->dev);
+	pm_runtime_enable(zdev->dev);
+	pm_runtime_get_sync(zdev->dev);
+	if (!pm_runtime_enabled(zdev->dev)) {
+		ret = zynqmp_dma_runtime_resume(zdev->dev);
+		if (ret)
+			return ret;
+	}
 
 	ret = zynqmp_dma_chan_probe(zdev, pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "Probing channel failed\n");
-		goto free_chan_resources;
+		goto err_disable_pm;
 	}
 
 	p->dst_addr_widths = BIT(zdev->chan->bus_width / 8);
@@ -1005,12 +1095,19 @@ static int zynqmp_dma_probe(struct platform_device *pdev)
 		goto free_chan_resources;
 	}
 
+	pm_runtime_mark_last_busy(zdev->dev);
+	pm_runtime_put_sync_autosuspend(zdev->dev);
+
 	dev_info(&pdev->dev, "ZynqMP DMA driver Probe success\n");
 
 	return 0;
 
 free_chan_resources:
 	zynqmp_dma_chan_remove(zdev->chan);
+err_disable_pm:
+	if (!pm_runtime_enabled(zdev->dev))
+		zynqmp_dma_runtime_suspend(zdev->dev);
+	pm_runtime_disable(zdev->dev);
 	return ret;
 }
 
@@ -1028,6 +1125,9 @@ static int zynqmp_dma_remove(struct platform_device *pdev)
 	dma_async_device_unregister(&zdev->common);
 
 	zynqmp_dma_chan_remove(zdev->chan);
+	pm_runtime_disable(zdev->dev);
+	if (!pm_runtime_enabled(zdev->dev))
+		zynqmp_dma_runtime_suspend(zdev->dev);
 
 	return 0;
 }
@@ -1042,6 +1142,7 @@ static struct platform_driver zynqmp_dma_driver = {
 	.driver = {
 		.name = "xilinx-zynqmp-dma",
 		.of_match_table = zynqmp_dma_of_match,
+		.pm = &zynqmp_dma_dev_pm_ops,
 	},
 	.probe = zynqmp_dma_probe,
 	.remove = zynqmp_dma_remove,
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 96afb2aeed18..3c4017007647 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -457,4 +457,11 @@ config EDAC_XGENE
 	  Support for error detection and correction on the
 	  APM X-Gene family of SOCs.
 
+config EDAC_TI
+	tristate "Texas Instruments DDR3 ECC Controller"
+	depends on ARCH_KEYSTONE || SOC_DRA7XX
+	help
+	  Support for error detection and correction on the
+          TI SoCs.
+
 endif # EDAC
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index 0fd9ffa63299..b54912eb39af 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -78,3 +78,4 @@ obj-$(CONFIG_EDAC_THUNDERX)		+= thunderx_edac.o
 obj-$(CONFIG_EDAC_ALTERA)		+= altera_edac.o
 obj-$(CONFIG_EDAC_SYNOPSYS)		+= synopsys_edac.o
 obj-$(CONFIG_EDAC_XGENE)		+= xgene_edac.o
+obj-$(CONFIG_EDAC_TI)			+= ti_edac.o
diff --git a/drivers/edac/mv64x60_edac.c b/drivers/edac/mv64x60_edac.c
index ec5d695bbb72..3c68bb525d5d 100644
--- a/drivers/edac/mv64x60_edac.c
+++ b/drivers/edac/mv64x60_edac.c
@@ -758,7 +758,7 @@ static int mv64x60_mc_err_probe(struct platform_device *pdev)
 		/* Non-ECC RAM? */
 		printk(KERN_WARNING "%s: No ECC DIMMs discovered\n", __func__);
 		res = -ENODEV;
-		goto err2;
+		goto err;
 	}
 
 	edac_dbg(3, "init mci\n");
diff --git a/drivers/edac/octeon_edac-lmc.c b/drivers/edac/octeon_edac-lmc.c
index 9c1ffe3e912b..aeb222ca3ed1 100644
--- a/drivers/edac/octeon_edac-lmc.c
+++ b/drivers/edac/octeon_edac-lmc.c
@@ -78,6 +78,7 @@ static void octeon_lmc_edac_poll_o2(struct mem_ctl_info *mci)
 	if (!pvt->inject)
 		int_reg.u64 = cvmx_read_csr(CVMX_LMCX_INT(mci->mc_idx));
 	else {
+		int_reg.u64 = 0;
 		if (pvt->error_type == 1)
 			int_reg.s.sec_err = 1;
 		if (pvt->error_type == 2)
diff --git a/drivers/edac/ti_edac.c b/drivers/edac/ti_edac.c
new file mode 100644
index 000000000000..6ac26d1b929f
--- /dev/null
+++ b/drivers/edac/ti_edac.c
@@ -0,0 +1,341 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * Texas Instruments DDR3 ECC error correction and detection driver
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/init.h>
+#include <linux/edac.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/module.h>
+
+#include "edac_module.h"
+
+/* EMIF controller registers */
+#define EMIF_SDRAM_CONFIG		0x008
+#define EMIF_IRQ_STATUS			0x0ac
+#define EMIF_IRQ_ENABLE_SET		0x0b4
+#define EMIF_ECC_CTRL			0x110
+#define EMIF_1B_ECC_ERR_CNT		0x130
+#define EMIF_1B_ECC_ERR_THRSH		0x134
+#define EMIF_1B_ECC_ERR_ADDR_LOG	0x13c
+#define EMIF_2B_ECC_ERR_ADDR_LOG	0x140
+
+/* Bit definitions for EMIF_SDRAM_CONFIG */
+#define SDRAM_TYPE_SHIFT		29
+#define SDRAM_TYPE_MASK			GENMASK(31, 29)
+#define SDRAM_TYPE_DDR3			(3 << SDRAM_TYPE_SHIFT)
+#define SDRAM_TYPE_DDR2			(2 << SDRAM_TYPE_SHIFT)
+#define SDRAM_NARROW_MODE_MASK		GENMASK(15, 14)
+#define SDRAM_K2_NARROW_MODE_SHIFT	12
+#define SDRAM_K2_NARROW_MODE_MASK	GENMASK(13, 12)
+#define SDRAM_ROWSIZE_SHIFT		7
+#define SDRAM_ROWSIZE_MASK		GENMASK(9, 7)
+#define SDRAM_IBANK_SHIFT		4
+#define SDRAM_IBANK_MASK		GENMASK(6, 4)
+#define SDRAM_K2_IBANK_SHIFT		5
+#define SDRAM_K2_IBANK_MASK		GENMASK(6, 5)
+#define SDRAM_K2_EBANK_SHIFT		3
+#define SDRAM_K2_EBANK_MASK		BIT(SDRAM_K2_EBANK_SHIFT)
+#define SDRAM_PAGESIZE_SHIFT		0
+#define SDRAM_PAGESIZE_MASK		GENMASK(2, 0)
+#define SDRAM_K2_PAGESIZE_SHIFT		0
+#define SDRAM_K2_PAGESIZE_MASK		GENMASK(1, 0)
+
+#define EMIF_1B_ECC_ERR_THRSH_SHIFT	24
+
+/* IRQ bit definitions */
+#define EMIF_1B_ECC_ERR			BIT(5)
+#define EMIF_2B_ECC_ERR			BIT(4)
+#define EMIF_WR_ECC_ERR			BIT(3)
+#define EMIF_SYS_ERR			BIT(0)
+/* Bit 31 enables ECC and 28 enables RMW */
+#define ECC_ENABLED			(BIT(31) | BIT(28))
+
+#define EDAC_MOD_NAME			"ti-emif-edac"
+
+enum {
+	EMIF_TYPE_DRA7,
+	EMIF_TYPE_K2
+};
+
+struct ti_edac {
+	void __iomem *reg;
+};
+
+static u32 ti_edac_readl(struct ti_edac *edac, u16 offset)
+{
+	return readl_relaxed(edac->reg + offset);
+}
+
+static void ti_edac_writel(struct ti_edac *edac, u32 val, u16 offset)
+{
+	writel_relaxed(val, edac->reg + offset);
+}
+
+static irqreturn_t ti_edac_isr(int irq, void *data)
+{
+	struct mem_ctl_info *mci = data;
+	struct ti_edac *edac = mci->pvt_info;
+	u32 irq_status;
+	u32 err_addr;
+	int err_count;
+
+	irq_status = ti_edac_readl(edac, EMIF_IRQ_STATUS);
+
+	if (irq_status & EMIF_1B_ECC_ERR) {
+		err_addr = ti_edac_readl(edac, EMIF_1B_ECC_ERR_ADDR_LOG);
+		err_count = ti_edac_readl(edac, EMIF_1B_ECC_ERR_CNT);
+		ti_edac_writel(edac, err_count, EMIF_1B_ECC_ERR_CNT);
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, err_count,
+				     err_addr >> PAGE_SHIFT,
+				     err_addr & ~PAGE_MASK, -1, 0, 0, 0,
+				     mci->ctl_name, "1B");
+	}
+
+	if (irq_status & EMIF_2B_ECC_ERR) {
+		err_addr = ti_edac_readl(edac, EMIF_2B_ECC_ERR_ADDR_LOG);
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+				     err_addr >> PAGE_SHIFT,
+				     err_addr & ~PAGE_MASK, -1, 0, 0, 0,
+				     mci->ctl_name, "2B");
+	}
+
+	if (irq_status & EMIF_WR_ECC_ERR)
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+				     0, 0, -1, 0, 0, 0,
+				     mci->ctl_name, "WR");
+
+	ti_edac_writel(edac, irq_status, EMIF_IRQ_STATUS);
+
+	return IRQ_HANDLED;
+}
+
+static void ti_edac_setup_dimm(struct mem_ctl_info *mci, u32 type)
+{
+	struct dimm_info *dimm;
+	struct ti_edac *edac = mci->pvt_info;
+	int bits;
+	u32 val;
+	u32 memsize;
+
+	dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, 0, 0, 0);
+
+	val = ti_edac_readl(edac, EMIF_SDRAM_CONFIG);
+
+	if (type == EMIF_TYPE_DRA7) {
+		bits = ((val & SDRAM_PAGESIZE_MASK) >> SDRAM_PAGESIZE_SHIFT) + 8;
+		bits += ((val & SDRAM_ROWSIZE_MASK) >> SDRAM_ROWSIZE_SHIFT) + 9;
+		bits += (val & SDRAM_IBANK_MASK) >> SDRAM_IBANK_SHIFT;
+
+		if (val & SDRAM_NARROW_MODE_MASK) {
+			bits++;
+			dimm->dtype = DEV_X16;
+		} else {
+			bits += 2;
+			dimm->dtype = DEV_X32;
+		}
+	} else {
+		bits = 16;
+		bits += ((val & SDRAM_K2_PAGESIZE_MASK) >>
+			SDRAM_K2_PAGESIZE_SHIFT) + 8;
+		bits += (val & SDRAM_K2_IBANK_MASK) >> SDRAM_K2_IBANK_SHIFT;
+		bits += (val & SDRAM_K2_EBANK_MASK) >> SDRAM_K2_EBANK_SHIFT;
+
+		val = (val & SDRAM_K2_NARROW_MODE_MASK) >>
+			SDRAM_K2_NARROW_MODE_SHIFT;
+		switch (val) {
+		case 0:
+			bits += 3;
+			dimm->dtype = DEV_X64;
+			break;
+		case 1:
+			bits += 2;
+			dimm->dtype = DEV_X32;
+			break;
+		case 2:
+			bits++;
+			dimm->dtype = DEV_X16;
+			break;
+		}
+	}
+
+	memsize = 1 << bits;
+
+	dimm->nr_pages = memsize >> PAGE_SHIFT;
+	dimm->grain = 4;
+	if ((val & SDRAM_TYPE_MASK) == SDRAM_TYPE_DDR2)
+		dimm->mtype = MEM_DDR2;
+	else
+		dimm->mtype = MEM_DDR3;
+
+	val = ti_edac_readl(edac, EMIF_ECC_CTRL);
+	if (val & ECC_ENABLED)
+		dimm->edac_mode = EDAC_SECDED;
+	else
+		dimm->edac_mode = EDAC_NONE;
+}
+
+static const struct of_device_id ti_edac_of_match[] = {
+	{ .compatible = "ti,emif-keystone", .data = (void *)EMIF_TYPE_K2 },
+	{ .compatible = "ti,emif-dra7xx", .data = (void *)EMIF_TYPE_DRA7 },
+	{},
+};
+
+static int _emif_get_id(struct device_node *node)
+{
+	struct device_node *np;
+	const __be32 *addrp;
+	u32 addr, my_addr;
+	int my_id = 0;
+
+	addrp = of_get_address(node, 0, NULL, NULL);
+	my_addr = (u32)of_translate_address(node, addrp);
+
+	for_each_matching_node(np, ti_edac_of_match) {
+		if (np == node)
+			continue;
+
+		addrp = of_get_address(np, 0, NULL, NULL);
+		addr = (u32)of_translate_address(np, addrp);
+
+		edac_printk(KERN_INFO, EDAC_MOD_NAME,
+			    "addr=%x, my_addr=%x\n",
+			    addr, my_addr);
+
+		if (addr < my_addr)
+			my_id++;
+	}
+
+	return my_id;
+}
+
+static int ti_edac_probe(struct platform_device *pdev)
+{
+	int error_irq = 0, ret = -ENODEV;
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	void __iomem *reg;
+	struct mem_ctl_info *mci;
+	struct edac_mc_layer layers[1];
+	const struct of_device_id *id;
+	struct ti_edac *edac;
+	int emif_id;
+
+	id = of_match_device(ti_edac_of_match, &pdev->dev);
+	if (!id)
+		return -ENODEV;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	reg = devm_ioremap_resource(dev, res);
+	if (IS_ERR(reg)) {
+		edac_printk(KERN_ERR, EDAC_MOD_NAME,
+			    "EMIF controller regs not defined\n");
+		return PTR_ERR(reg);
+	}
+
+	layers[0].type = EDAC_MC_LAYER_ALL_MEM;
+	layers[0].size = 1;
+
+	/* Allocate ID number for our EMIF controller */
+	emif_id = _emif_get_id(pdev->dev.of_node);
+	if (emif_id < 0)
+		return -EINVAL;
+
+	mci = edac_mc_alloc(emif_id, 1, layers, sizeof(*edac));
+	if (!mci)
+		return -ENOMEM;
+
+	mci->pdev = &pdev->dev;
+	edac = mci->pvt_info;
+	edac->reg = reg;
+	platform_set_drvdata(pdev, mci);
+
+	mci->mtype_cap = MEM_FLAG_DDR3 | MEM_FLAG_DDR2;
+	mci->edac_ctl_cap = EDAC_FLAG_SECDED | EDAC_FLAG_NONE;
+	mci->mod_name = EDAC_MOD_NAME;
+	mci->ctl_name = id->compatible;
+	mci->dev_name = dev_name(&pdev->dev);
+
+	/* Setup memory layout */
+	ti_edac_setup_dimm(mci, (u32)(id->data));
+
+	/* add EMIF ECC error handler */
+	error_irq = platform_get_irq(pdev, 0);
+	if (!error_irq) {
+		edac_printk(KERN_ERR, EDAC_MOD_NAME,
+			    "EMIF irq number not defined.\n");
+		goto err;
+	}
+
+	ret = devm_request_irq(dev, error_irq, ti_edac_isr, 0,
+			       "emif-edac-irq", mci);
+	if (ret) {
+		edac_printk(KERN_ERR, EDAC_MOD_NAME,
+			    "request_irq fail for EMIF EDAC irq\n");
+		goto err;
+	}
+
+	ret = edac_mc_add_mc(mci);
+	if (ret) {
+		edac_printk(KERN_ERR, EDAC_MOD_NAME,
+			    "Failed to register mci: %d.\n", ret);
+		goto err;
+	}
+
+	/* Generate an interrupt with each 1b error */
+	ti_edac_writel(edac, 1 << EMIF_1B_ECC_ERR_THRSH_SHIFT,
+		       EMIF_1B_ECC_ERR_THRSH);
+
+	/* Enable interrupts */
+	ti_edac_writel(edac,
+		       EMIF_1B_ECC_ERR | EMIF_2B_ECC_ERR | EMIF_WR_ECC_ERR,
+		       EMIF_IRQ_ENABLE_SET);
+
+	return 0;
+
+err:
+	edac_mc_free(mci);
+	return ret;
+}
+
+static int ti_edac_remove(struct platform_device *pdev)
+{
+	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
+
+	edac_mc_del_mc(&pdev->dev);
+	edac_mc_free(mci);
+
+	return 0;
+}
+
+static struct platform_driver ti_edac_driver = {
+	.probe = ti_edac_probe,
+	.remove = ti_edac_remove,
+	.driver = {
+		   .name = EDAC_MOD_NAME,
+		   .of_match_table = ti_edac_of_match,
+	},
+};
+
+module_platform_driver(ti_edac_driver);
+
+MODULE_AUTHOR("Texas Instruments Inc.");
+MODULE_DESCRIPTION("EDAC Driver for Texas Instruments DDR3 MC");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/eisa/eisa-bus.c b/drivers/eisa/eisa-bus.c
index 612afeaec3cb..1e8062f6dbfc 100644
--- a/drivers/eisa/eisa-bus.c
+++ b/drivers/eisa/eisa-bus.c
@@ -75,9 +75,9 @@ static void __init eisa_name_device(struct eisa_device *edev)
 
 static char __init *decode_eisa_sig(unsigned long addr)
 {
-        static char sig_str[EISA_SIG_LEN];
+	static char sig_str[EISA_SIG_LEN];
 	u8 sig[4];
-        u16 rev;
+	u16 rev;
 	int i;
 
 	for (i = 0; i < 4; i++) {
@@ -96,14 +96,14 @@ static char __init *decode_eisa_sig(unsigned long addr)
 		if (!i && (sig[0] & 0x80))
 			return NULL;
 	}
-	
-        sig_str[0] = ((sig[0] >> 2) & 0x1f) + ('A' - 1);
-        sig_str[1] = (((sig[0] & 3) << 3) | (sig[1] >> 5)) + ('A' - 1);
-        sig_str[2] = (sig[1] & 0x1f) + ('A' - 1);
-        rev = (sig[2] << 8) | sig[3];
-        sprintf(sig_str + 3, "%04X", rev);
-
-        return sig_str;
+
+	sig_str[0] = ((sig[0] >> 2) & 0x1f) + ('A' - 1);
+	sig_str[1] = (((sig[0] & 3) << 3) | (sig[1] >> 5)) + ('A' - 1);
+	sig_str[2] = (sig[1] & 0x1f) + ('A' - 1);
+	rev = (sig[2] << 8) | sig[3];
+	sprintf(sig_str + 3, "%04X", rev);
+
+	return sig_str;
 }
 
 static int eisa_bus_match(struct device *dev, struct device_driver *drv)
@@ -198,7 +198,7 @@ static int __init eisa_init_device(struct eisa_root_device *root,
 	sig = decode_eisa_sig(sig_addr);
 	if (!sig)
 		return -1;	/* No EISA device here */
-	
+
 	memcpy(edev->id.sig, sig, EISA_SIG_LEN);
 	edev->slot = slot;
 	edev->state = inb(SLOT_ADDRESS(root, slot) + EISA_CONFIG_OFFSET)
@@ -222,7 +222,7 @@ static int __init eisa_init_device(struct eisa_root_device *root,
 
 	if (is_forced_dev(enable_dev, enable_dev_count, root, edev))
 		edev->state = EISA_CONFIG_ENABLED | EISA_CONFIG_FORCED;
-	
+
 	if (is_forced_dev(disable_dev, disable_dev_count, root, edev))
 		edev->state = EISA_CONFIG_FORCED;
 
@@ -275,7 +275,7 @@ static int __init eisa_request_resources(struct eisa_root_device *root,
 			edev->res[i].start = edev->res[i].end = 0;
 			continue;
 		}
-		
+
 		if (slot) {
 			edev->res[i].name  = NULL;
 			edev->res[i].start = SLOT_ADDRESS(root, slot)
@@ -295,7 +295,7 @@ static int __init eisa_request_resources(struct eisa_root_device *root,
 	}
 
 	return 0;
-	
+
  failed:
 	while (--i >= 0)
 		release_resource(&edev->res[i]);
@@ -314,7 +314,7 @@ static void __init eisa_release_resources(struct eisa_device *edev)
 
 static int __init eisa_probe(struct eisa_root_device *root)
 {
-        int i, c;
+	int i, c;
 	struct eisa_device *edev;
 	char *enabled_str;
 
@@ -322,16 +322,14 @@ static int __init eisa_probe(struct eisa_root_device *root)
 
 	/* First try to get hold of slot 0. If there is no device
 	 * here, simply fail, unless root->force_probe is set. */
-	
+
 	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
-	if (!edev) {
-		dev_err(root->dev, "EISA: Couldn't allocate mainboard slot\n");
+	if (!edev)
 		return -ENOMEM;
-	}
-		
+
 	if (eisa_request_resources(root, edev, 0)) {
 		dev_warn(root->dev,
-		         "EISA: Cannot allocate resource for mainboard\n");
+			 "EISA: Cannot allocate resource for mainboard\n");
 		kfree(edev);
 		if (!root->force_probe)
 			return -EBUSY;
@@ -350,14 +348,14 @@ static int __init eisa_probe(struct eisa_root_device *root)
 
 	if (eisa_register_device(edev)) {
 		dev_err(&edev->dev, "EISA: Failed to register %s\n",
-		        edev->id.sig);
+			edev->id.sig);
 		eisa_release_resources(edev);
 		kfree(edev);
 	}
-	
+
  force_probe:
-	
-        for (c = 0, i = 1; i <= root->slots; i++) {
+
+	for (c = 0, i = 1; i <= root->slots; i++) {
 		edev = kzalloc(sizeof(*edev), GFP_KERNEL);
 		if (!edev) {
 			dev_err(root->dev, "EISA: Out of memory for slot %d\n",
@@ -367,8 +365,8 @@ static int __init eisa_probe(struct eisa_root_device *root)
 
 		if (eisa_request_resources(root, edev, i)) {
 			dev_warn(root->dev,
-			         "Cannot allocate resource for EISA slot %d\n",
-			         i);
+				 "Cannot allocate resource for EISA slot %d\n",
+				 i);
 			kfree(edev);
 			continue;
 		}
@@ -395,11 +393,11 @@ static int __init eisa_probe(struct eisa_root_device *root)
 
 		if (eisa_register_device(edev)) {
 			dev_err(&edev->dev, "EISA: Failed to register %s\n",
-			        edev->id.sig);
+				edev->id.sig);
 			eisa_release_resources(edev);
 			kfree(edev);
 		}
-        }
+	}
 
 	dev_info(root->dev, "EISA: Detected %d card%s\n", c, c == 1 ? "" : "s");
 	return 0;
@@ -422,7 +420,7 @@ int __init eisa_root_register(struct eisa_root_device *root)
 	 * been already registered. This prevents the virtual root
 	 * device from registering after the real one has, for
 	 * example... */
-	
+
 	root->eisa_root_res.name  = eisa_root_res.name;
 	root->eisa_root_res.start = root->res->start;
 	root->eisa_root_res.end   = root->res->end;
@@ -431,7 +429,7 @@ int __init eisa_root_register(struct eisa_root_device *root)
 	err = request_resource(&eisa_root_res, &root->eisa_root_res);
 	if (err)
 		return err;
-	
+
 	root->bus_nr = eisa_bus_count++;
 
 	err = eisa_probe(root);
@@ -444,7 +442,7 @@ int __init eisa_root_register(struct eisa_root_device *root)
 static int __init eisa_init(void)
 {
 	int r;
-	
+
 	r = bus_register(&eisa_bus_type);
 	if (r)
 		return r;
diff --git a/drivers/eisa/pci_eisa.c b/drivers/eisa/pci_eisa.c
index a333bf3517de..b5f367b44413 100644
--- a/drivers/eisa/pci_eisa.c
+++ b/drivers/eisa/pci_eisa.c
@@ -50,11 +50,11 @@ static int __init pci_eisa_init(struct pci_dev *pdev)
 		return -1;
 	}
 
-	pci_eisa_root.dev              = &pdev->dev;
-	pci_eisa_root.res	       = bus_res;
-	pci_eisa_root.bus_base_addr    = bus_res->start;
-	pci_eisa_root.slots	       = EISA_MAX_SLOTS;
-	pci_eisa_root.dma_mask         = pdev->dma_mask;
+	pci_eisa_root.dev		= &pdev->dev;
+	pci_eisa_root.res		= bus_res;
+	pci_eisa_root.bus_base_addr	= bus_res->start;
+	pci_eisa_root.slots		= EISA_MAX_SLOTS;
+	pci_eisa_root.dma_mask		= pdev->dma_mask;
 	dev_set_drvdata(pci_eisa_root.dev, &pci_eisa_root);
 
 	if (eisa_root_register (&pci_eisa_root)) {
diff --git a/drivers/eisa/virtual_root.c b/drivers/eisa/virtual_root.c
index 535e4f9c83f4..f1221c1d6319 100644
--- a/drivers/eisa/virtual_root.c
+++ b/drivers/eisa/virtual_root.c
@@ -35,11 +35,11 @@ static struct platform_device eisa_root_dev = {
 };
 
 static struct eisa_root_device eisa_bus_root = {
-	.dev           = &eisa_root_dev.dev,
-	.bus_base_addr = 0,
-	.res	       = &ioport_resource,
-	.slots	       = EISA_MAX_SLOTS,
-	.dma_mask      = 0xffffffff,
+	.dev		= &eisa_root_dev.dev,
+	.bus_base_addr	= 0,
+	.res		= &ioport_resource,
+	.slots		= EISA_MAX_SLOTS,
+	.dma_mask	= 0xffffffff,
 };
 
 static void virtual_eisa_release (struct device *dev)
@@ -50,13 +50,12 @@ static void virtual_eisa_release (struct device *dev)
 static int __init virtual_eisa_root_init (void)
 {
 	int r;
-	
-        if ((r = platform_device_register (&eisa_root_dev))) {
-                return r;
-        }
+
+	if ((r = platform_device_register (&eisa_root_dev)))
+		return r;
 
 	eisa_bus_root.force_probe = force_probe;
-	
+
 	dev_set_drvdata(&eisa_root_dev.dev, &eisa_bus_root);
 
 	if (eisa_root_register (&eisa_bus_root)) {
diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c
index 3877d86c746a..18026354c332 100644
--- a/drivers/extcon/extcon-adc-jack.c
+++ b/drivers/extcon/extcon-adc-jack.c
@@ -144,7 +144,7 @@ static int adc_jack_probe(struct platform_device *pdev)
 		return err;
 
 	data->irq = platform_get_irq(pdev, 0);
-	if (!data->irq) {
+	if (data->irq < 0) {
 		dev_err(&pdev->dev, "platform_get_irq failed\n");
 		return -ENODEV;
 	}
diff --git a/drivers/extcon/extcon-axp288.c b/drivers/extcon/extcon-axp288.c
index 981fba56bc18..0a44d43802fe 100644
--- a/drivers/extcon/extcon-axp288.c
+++ b/drivers/extcon/extcon-axp288.c
@@ -1,6 +1,7 @@
 /*
  * extcon-axp288.c - X-Power AXP288 PMIC extcon cable detection driver
  *
+ * Copyright (C) 2016-2017 Hans de Goede <hdegoede@redhat.com>
  * Copyright (C) 2015 Intel Corporation
  * Author: Ramakrishna Pallala <ramakrishna.pallala@intel.com>
  *
@@ -24,8 +25,6 @@
 #include <linux/notifier.h>
 #include <linux/extcon-provider.h>
 #include <linux/regmap.h>
-#include <linux/gpio.h>
-#include <linux/gpio/consumer.h>
 #include <linux/mfd/axp20x.h>
 
 /* Power source status register */
@@ -79,11 +78,6 @@ enum axp288_extcon_reg {
 	AXP288_BC_DET_STAT_REG		= 0x2f,
 };
 
-enum axp288_mux_select {
-	EXTCON_GPIO_MUX_SEL_PMIC = 0,
-	EXTCON_GPIO_MUX_SEL_SOC,
-};
-
 enum axp288_extcon_irq {
 	VBUS_FALLING_IRQ = 0,
 	VBUS_RISING_IRQ,
@@ -104,11 +98,11 @@ struct axp288_extcon_info {
 	struct device *dev;
 	struct regmap *regmap;
 	struct regmap_irq_chip_data *regmap_irqc;
-	struct gpio_desc *gpio_mux_cntl;
+	struct delayed_work det_work;
 	int irq[EXTCON_IRQ_END];
 	struct extcon_dev *edev;
-	struct notifier_block extcon_nb;
 	unsigned int previous_cable;
+	bool first_detect_done;
 };
 
 /* Power up/down reason string array */
@@ -146,6 +140,25 @@ static void axp288_extcon_log_rsi(struct axp288_extcon_info *info)
 	regmap_write(info->regmap, AXP288_PS_BOOT_REASON_REG, clear_mask);
 }
 
+static void axp288_chrg_detect_complete(struct axp288_extcon_info *info)
+{
+	/*
+	 * We depend on other drivers to do things like mux the data lines,
+	 * enable/disable vbus based on the id-pin, etc. Sometimes the BIOS has
+	 * not set these things up correctly resulting in the initial charger
+	 * cable type detection giving a wrong result and we end up not charging
+	 * or charging at only 0.5A.
+	 *
+	 * So we schedule a second cable type detection after 2 seconds to
+	 * give the other drivers time to load and do their thing.
+	 */
+	if (!info->first_detect_done) {
+		queue_delayed_work(system_wq, &info->det_work,
+				   msecs_to_jiffies(2000));
+		info->first_detect_done = true;
+	}
+}
+
 static int axp288_handle_chrg_det_event(struct axp288_extcon_info *info)
 {
 	int ret, stat, cfg, pwr_stat;
@@ -192,20 +205,11 @@ static int axp288_handle_chrg_det_event(struct axp288_extcon_info *info)
 		cable = EXTCON_CHG_USB_DCP;
 		break;
 	default:
-		dev_warn(info->dev,
-			"disconnect or unknown or ID event\n");
+		dev_warn(info->dev, "unknown (reserved) bc detect result\n");
+		cable = EXTCON_CHG_USB_SDP;
 	}
 
 no_vbus:
-	/*
-	 * If VBUS is absent Connect D+/D- lines to PMIC for BC
-	 * detection. Else connect them to SOC for USB communication.
-	 */
-	if (info->gpio_mux_cntl)
-		gpiod_set_value(info->gpio_mux_cntl,
-			vbus_attach ? EXTCON_GPIO_MUX_SEL_SOC
-					: EXTCON_GPIO_MUX_SEL_PMIC);
-
 	extcon_set_state_sync(info->edev, info->previous_cable, false);
 	if (info->previous_cable == EXTCON_CHG_USB_SDP)
 		extcon_set_state_sync(info->edev, EXTCON_USB, false);
@@ -219,6 +223,8 @@ no_vbus:
 		info->previous_cable = cable;
 	}
 
+	axp288_chrg_detect_complete(info);
+
 	return 0;
 
 dev_det_ret:
@@ -240,8 +246,11 @@ static irqreturn_t axp288_extcon_isr(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static void axp288_extcon_enable(struct axp288_extcon_info *info)
+static void axp288_extcon_det_work(struct work_struct *work)
 {
+	struct axp288_extcon_info *info =
+		container_of(work, struct axp288_extcon_info, det_work.work);
+
 	regmap_update_bits(info->regmap, AXP288_BC_GLOBAL_REG,
 						BC_GLOBAL_RUN, 0);
 	/* Enable the charger detection logic */
@@ -253,8 +262,7 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 {
 	struct axp288_extcon_info *info;
 	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
-	struct axp288_extcon_pdata *pdata = pdev->dev.platform_data;
-	int ret, i, pirq, gpio;
+	int ret, i, pirq;
 
 	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
 	if (!info)
@@ -264,8 +272,7 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 	info->regmap = axp20x->regmap;
 	info->regmap_irqc = axp20x->regmap_irqc;
 	info->previous_cable = EXTCON_NONE;
-	if (pdata)
-		info->gpio_mux_cntl = pdata->gpio_mux_cntl;
+	INIT_DELAYED_WORK(&info->det_work, axp288_extcon_det_work);
 
 	platform_set_drvdata(pdev, info);
 
@@ -286,21 +293,11 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	/* Set up gpio control for USB Mux */
-	if (info->gpio_mux_cntl) {
-		gpio = desc_to_gpio(info->gpio_mux_cntl);
-		ret = devm_gpio_request(&pdev->dev, gpio, "USB_MUX");
-		if (ret < 0) {
-			dev_err(&pdev->dev,
-				"failed to request the gpio=%d\n", gpio);
-			return ret;
-		}
-		gpiod_direction_output(info->gpio_mux_cntl,
-						EXTCON_GPIO_MUX_SEL_PMIC);
-	}
-
 	for (i = 0; i < EXTCON_IRQ_END; i++) {
 		pirq = platform_get_irq(pdev, i);
+		if (pirq < 0)
+			return pirq;
+
 		info->irq[i] = regmap_irq_get_virq(info->regmap_irqc, pirq);
 		if (info->irq[i] < 0) {
 			dev_err(&pdev->dev,
@@ -321,7 +318,7 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 	}
 
 	/* Start charger cable type detection */
-	axp288_extcon_enable(info);
+	queue_delayed_work(system_wq, &info->det_work, 0);
 
 	return 0;
 }
diff --git a/drivers/extcon/extcon-max77693.c b/drivers/extcon/extcon-max77693.c
index 643411066ad9..227651ff9666 100644
--- a/drivers/extcon/extcon-max77693.c
+++ b/drivers/extcon/extcon-max77693.c
@@ -266,7 +266,7 @@ static int max77693_muic_set_debounce_time(struct max77693_muic_info *info,
 static int max77693_muic_set_path(struct max77693_muic_info *info,
 		u8 val, bool attached)
 {
-	int ret = 0;
+	int ret;
 	unsigned int ctrl1, ctrl2 = 0;
 
 	if (attached)
diff --git a/drivers/extcon/extcon-max8997.c b/drivers/extcon/extcon-max8997.c
index 8152790d72e1..9f30f4929b72 100644
--- a/drivers/extcon/extcon-max8997.c
+++ b/drivers/extcon/extcon-max8997.c
@@ -204,7 +204,7 @@ static int max8997_muic_set_debounce_time(struct max8997_muic_info *info,
 static int max8997_muic_set_path(struct max8997_muic_info *info,
 		u8 val, bool attached)
 {
-	int ret = 0;
+	int ret;
 	u8 ctrl1, ctrl2 = 0;
 
 	if (attached)
diff --git a/drivers/extcon/extcon-usbc-cros-ec.c b/drivers/extcon/extcon-usbc-cros-ec.c
index 6187f731b29d..6721ab01fe7d 100644
--- a/drivers/extcon/extcon-usbc-cros-ec.c
+++ b/drivers/extcon/extcon-usbc-cros-ec.c
@@ -34,16 +34,26 @@ struct cros_ec_extcon_info {
 
 	struct notifier_block notifier;
 
+	unsigned int dr; /* data role */
+	bool pr; /* power role (true if VBUS enabled) */
 	bool dp; /* DisplayPort enabled */
 	bool mux; /* SuperSpeed (usb3) enabled */
 	unsigned int power_type;
 };
 
 static const unsigned int usb_type_c_cable[] = {
+	EXTCON_USB,
+	EXTCON_USB_HOST,
 	EXTCON_DISP_DP,
 	EXTCON_NONE,
 };
 
+enum usb_data_roles {
+	DR_NONE,
+	DR_HOST,
+	DR_DEVICE,
+};
+
 /**
  * cros_ec_pd_command() - Send a command to the EC.
  * @info: pointer to struct cros_ec_extcon_info
@@ -150,6 +160,7 @@ static int cros_ec_usb_get_role(struct cros_ec_extcon_info *info,
 	pd_control.port = info->port_id;
 	pd_control.role = USB_PD_CTRL_ROLE_NO_CHANGE;
 	pd_control.mux = USB_PD_CTRL_MUX_NO_CHANGE;
+	pd_control.swap = USB_PD_CTRL_SWAP_NONE;
 	ret = cros_ec_pd_command(info, EC_CMD_USB_PD_CONTROL, 1,
 				 &pd_control, sizeof(pd_control),
 				 &resp, sizeof(resp));
@@ -183,11 +194,72 @@ static int cros_ec_pd_get_num_ports(struct cros_ec_extcon_info *info)
 	return resp.num_ports;
 }
 
+static const char *cros_ec_usb_role_string(unsigned int role)
+{
+	return role == DR_NONE ? "DISCONNECTED" :
+		(role == DR_HOST ? "DFP" : "UFP");
+}
+
+static const char *cros_ec_usb_power_type_string(unsigned int type)
+{
+	switch (type) {
+	case USB_CHG_TYPE_NONE:
+		return "USB_CHG_TYPE_NONE";
+	case USB_CHG_TYPE_PD:
+		return "USB_CHG_TYPE_PD";
+	case USB_CHG_TYPE_PROPRIETARY:
+		return "USB_CHG_TYPE_PROPRIETARY";
+	case USB_CHG_TYPE_C:
+		return "USB_CHG_TYPE_C";
+	case USB_CHG_TYPE_BC12_DCP:
+		return "USB_CHG_TYPE_BC12_DCP";
+	case USB_CHG_TYPE_BC12_CDP:
+		return "USB_CHG_TYPE_BC12_CDP";
+	case USB_CHG_TYPE_BC12_SDP:
+		return "USB_CHG_TYPE_BC12_SDP";
+	case USB_CHG_TYPE_OTHER:
+		return "USB_CHG_TYPE_OTHER";
+	case USB_CHG_TYPE_VBUS:
+		return "USB_CHG_TYPE_VBUS";
+	case USB_CHG_TYPE_UNKNOWN:
+		return "USB_CHG_TYPE_UNKNOWN";
+	default:
+		return "USB_CHG_TYPE_UNKNOWN";
+	}
+}
+
+static bool cros_ec_usb_power_type_is_wall_wart(unsigned int type,
+						unsigned int role)
+{
+	switch (type) {
+	/* FIXME : Guppy, Donnettes, and other chargers will be miscategorized
+	 * because they identify with USB_CHG_TYPE_C, but we can't return true
+	 * here from that code because that breaks Suzy-Q and other kinds of
+	 * USB Type-C cables and peripherals.
+	 */
+	case USB_CHG_TYPE_PROPRIETARY:
+	case USB_CHG_TYPE_BC12_DCP:
+		return true;
+	case USB_CHG_TYPE_PD:
+	case USB_CHG_TYPE_C:
+	case USB_CHG_TYPE_BC12_CDP:
+	case USB_CHG_TYPE_BC12_SDP:
+	case USB_CHG_TYPE_OTHER:
+	case USB_CHG_TYPE_VBUS:
+	case USB_CHG_TYPE_UNKNOWN:
+	case USB_CHG_TYPE_NONE:
+	default:
+		return false;
+	}
+}
+
 static int extcon_cros_ec_detect_cable(struct cros_ec_extcon_info *info,
 				       bool force)
 {
 	struct device *dev = info->dev;
 	int role, power_type;
+	unsigned int dr = DR_NONE;
+	bool pr = false;
 	bool polarity = false;
 	bool dp = false;
 	bool mux = false;
@@ -206,9 +278,12 @@ static int extcon_cros_ec_detect_cable(struct cros_ec_extcon_info *info,
 			dev_err(dev, "failed getting role err = %d\n", role);
 			return role;
 		}
+		dev_dbg(dev, "disconnected\n");
 	} else {
 		int pd_mux_state;
 
+		dr = (role & PD_CTRL_RESP_ROLE_DATA) ? DR_HOST : DR_DEVICE;
+		pr = (role & PD_CTRL_RESP_ROLE_POWER);
 		pd_mux_state = cros_ec_usb_get_pd_mux_state(info);
 		if (pd_mux_state < 0)
 			pd_mux_state = USB_PD_MUX_USB_ENABLED;
@@ -216,20 +291,62 @@ static int extcon_cros_ec_detect_cable(struct cros_ec_extcon_info *info,
 		dp = pd_mux_state & USB_PD_MUX_DP_ENABLED;
 		mux = pd_mux_state & USB_PD_MUX_USB_ENABLED;
 		hpd = pd_mux_state & USB_PD_MUX_HPD_IRQ;
-	}
 
-	if (force || info->dp != dp || info->mux != mux ||
-		info->power_type != power_type) {
+		dev_dbg(dev,
+			"connected role 0x%x pwr type %d dr %d pr %d pol %d mux %d dp %d hpd %d\n",
+			role, power_type, dr, pr, polarity, mux, dp, hpd);
+	}
 
+	/*
+	 * When there is no USB host (e.g. USB PD charger),
+	 * we are not really a UFP for the AP.
+	 */
+	if (dr == DR_DEVICE &&
+	    cros_ec_usb_power_type_is_wall_wart(power_type, role))
+		dr = DR_NONE;
+
+	if (force || info->dr != dr || info->pr != pr || info->dp != dp ||
+	    info->mux != mux || info->power_type != power_type) {
+		bool host_connected = false, device_connected = false;
+
+		dev_dbg(dev, "Type/Role switch! type = %s role = %s\n",
+			cros_ec_usb_power_type_string(power_type),
+			cros_ec_usb_role_string(dr));
+		info->dr = dr;
+		info->pr = pr;
 		info->dp = dp;
 		info->mux = mux;
 		info->power_type = power_type;
 
-		extcon_set_state(info->edev, EXTCON_DISP_DP, dp);
+		if (dr == DR_DEVICE)
+			device_connected = true;
+		else if (dr == DR_HOST)
+			host_connected = true;
 
+		extcon_set_state(info->edev, EXTCON_USB, device_connected);
+		extcon_set_state(info->edev, EXTCON_USB_HOST, host_connected);
+		extcon_set_state(info->edev, EXTCON_DISP_DP, dp);
+		extcon_set_property(info->edev, EXTCON_USB,
+				    EXTCON_PROP_USB_VBUS,
+				    (union extcon_property_value)(int)pr);
+		extcon_set_property(info->edev, EXTCON_USB_HOST,
+				    EXTCON_PROP_USB_VBUS,
+				    (union extcon_property_value)(int)pr);
+		extcon_set_property(info->edev, EXTCON_USB,
+				    EXTCON_PROP_USB_TYPEC_POLARITY,
+				    (union extcon_property_value)(int)polarity);
+		extcon_set_property(info->edev, EXTCON_USB_HOST,
+				    EXTCON_PROP_USB_TYPEC_POLARITY,
+				    (union extcon_property_value)(int)polarity);
 		extcon_set_property(info->edev, EXTCON_DISP_DP,
 				    EXTCON_PROP_USB_TYPEC_POLARITY,
 				    (union extcon_property_value)(int)polarity);
+		extcon_set_property(info->edev, EXTCON_USB,
+				    EXTCON_PROP_USB_SS,
+				    (union extcon_property_value)(int)mux);
+		extcon_set_property(info->edev, EXTCON_USB_HOST,
+				    EXTCON_PROP_USB_SS,
+				    (union extcon_property_value)(int)mux);
 		extcon_set_property(info->edev, EXTCON_DISP_DP,
 				    EXTCON_PROP_USB_SS,
 				    (union extcon_property_value)(int)mux);
@@ -237,6 +354,8 @@ static int extcon_cros_ec_detect_cable(struct cros_ec_extcon_info *info,
 				    EXTCON_PROP_DISP_HPD,
 				    (union extcon_property_value)(int)hpd);
 
+		extcon_sync(info->edev, EXTCON_USB);
+		extcon_sync(info->edev, EXTCON_USB_HOST);
 		extcon_sync(info->edev, EXTCON_DISP_DP);
 
 	} else if (hpd) {
@@ -322,13 +441,28 @@ static int extcon_cros_ec_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	extcon_set_property_capability(info->edev, EXTCON_USB,
+				       EXTCON_PROP_USB_VBUS);
+	extcon_set_property_capability(info->edev, EXTCON_USB_HOST,
+				       EXTCON_PROP_USB_VBUS);
+	extcon_set_property_capability(info->edev, EXTCON_USB,
+				       EXTCON_PROP_USB_TYPEC_POLARITY);
+	extcon_set_property_capability(info->edev, EXTCON_USB_HOST,
+				       EXTCON_PROP_USB_TYPEC_POLARITY);
 	extcon_set_property_capability(info->edev, EXTCON_DISP_DP,
 				       EXTCON_PROP_USB_TYPEC_POLARITY);
+	extcon_set_property_capability(info->edev, EXTCON_USB,
+				       EXTCON_PROP_USB_SS);
+	extcon_set_property_capability(info->edev, EXTCON_USB_HOST,
+				       EXTCON_PROP_USB_SS);
 	extcon_set_property_capability(info->edev, EXTCON_DISP_DP,
 				       EXTCON_PROP_USB_SS);
 	extcon_set_property_capability(info->edev, EXTCON_DISP_DP,
 				       EXTCON_PROP_DISP_HPD);
 
+	info->dr = DR_NONE;
+	info->pr = false;
+
 	platform_set_drvdata(pdev, info);
 
 	/* Get PD events from the EC */
diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
index a301fcf46e88..523391bb3fbe 100644
--- a/drivers/firewire/core-cdev.c
+++ b/drivers/firewire/core-cdev.c
@@ -1784,10 +1784,10 @@ static int fw_device_op_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static unsigned int fw_device_op_poll(struct file *file, poll_table * pt)
+static __poll_t fw_device_op_poll(struct file *file, poll_table * pt)
 {
 	struct client *client = file->private_data;
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 
 	poll_wait(file, &client->wait, pt);
 
diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c
index 180f0a96528c..fee2e9e7ea20 100644
--- a/drivers/firewire/nosy.c
+++ b/drivers/firewire/nosy.c
@@ -328,11 +328,11 @@ nosy_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static unsigned int
+static __poll_t
 nosy_poll(struct file *file, poll_table *pt)
 {
 	struct client *client = file->private_data;
-	unsigned int ret = 0;
+	__poll_t ret = 0;
 
 	poll_wait(file, &client->buffer.wait, pt);
 
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index fa87a055905e..b7c748248e53 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -10,7 +10,7 @@ config ARM_PSCI_FW
 
 config ARM_PSCI_CHECKER
 	bool "ARM PSCI checker"
-	depends on ARM_PSCI_FW && HOTPLUG_CPU && !TORTURE_TEST
+	depends on ARM_PSCI_FW && HOTPLUG_CPU && CPU_IDLE && !TORTURE_TEST
 	help
 	  Run the PSCI checker during startup. This checks that hotplug and
 	  suspend operations work correctly when using PSCI.
@@ -48,6 +48,14 @@ config ARM_SCPI_POWER_DOMAIN
 	  This enables support for the SCPI power domains which can be
 	  enabled or disabled via the SCP firmware
 
+config ARM_SDE_INTERFACE
+	bool "ARM Software Delegated Exception Interface (SDEI)"
+	depends on ARM64
+	help
+	  The Software Delegated Exception Interface (SDEI) is an ARM
+	  standard for registering callbacks from the platform firmware
+	  into the OS. This is typically used to implement RAS notifications.
+
 config EDD
 	tristate "BIOS Enhanced Disk Drive calls determine boot disk"
 	depends on X86
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index feaa890197f3..b248238ddc6a 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_ARM_PSCI_FW)	+= psci.o
 obj-$(CONFIG_ARM_PSCI_CHECKER)	+= psci_checker.o
 obj-$(CONFIG_ARM_SCPI_PROTOCOL)	+= arm_scpi.o
 obj-$(CONFIG_ARM_SCPI_POWER_DOMAIN) += scpi_pm_domain.o
+obj-$(CONFIG_ARM_SDE_INTERFACE)	+= arm_sdei.o
 obj-$(CONFIG_DMI)		+= dmi_scan.o
 obj-$(CONFIG_DMI_SYSFS)		+= dmi-sysfs.o
 obj-$(CONFIG_EDD)		+= edd.o
diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c
index dfb373c8ba2a..7da9f1b83ebe 100644
--- a/drivers/firmware/arm_scpi.c
+++ b/drivers/firmware/arm_scpi.c
@@ -28,7 +28,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/bitmap.h>
-#include <linux/bitfield.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/export.h>
@@ -73,13 +72,21 @@
 
 #define MAX_DVFS_DOMAINS	8
 #define MAX_DVFS_OPPS		16
-
-#define PROTO_REV_MAJOR_MASK	GENMASK(31, 16)
-#define PROTO_REV_MINOR_MASK	GENMASK(15, 0)
-
-#define FW_REV_MAJOR_MASK	GENMASK(31, 24)
-#define FW_REV_MINOR_MASK	GENMASK(23, 16)
-#define FW_REV_PATCH_MASK	GENMASK(15, 0)
+#define DVFS_LATENCY(hdr)	(le32_to_cpu(hdr) >> 16)
+#define DVFS_OPP_COUNT(hdr)	((le32_to_cpu(hdr) >> 8) & 0xff)
+
+#define PROTOCOL_REV_MINOR_BITS	16
+#define PROTOCOL_REV_MINOR_MASK	((1U << PROTOCOL_REV_MINOR_BITS) - 1)
+#define PROTOCOL_REV_MAJOR(x)	((x) >> PROTOCOL_REV_MINOR_BITS)
+#define PROTOCOL_REV_MINOR(x)	((x) & PROTOCOL_REV_MINOR_MASK)
+
+#define FW_REV_MAJOR_BITS	24
+#define FW_REV_MINOR_BITS	16
+#define FW_REV_PATCH_MASK	((1U << FW_REV_MINOR_BITS) - 1)
+#define FW_REV_MINOR_MASK	((1U << FW_REV_MAJOR_BITS) - 1)
+#define FW_REV_MAJOR(x)		((x) >> FW_REV_MAJOR_BITS)
+#define FW_REV_MINOR(x)		(((x) & FW_REV_MINOR_MASK) >> FW_REV_MINOR_BITS)
+#define FW_REV_PATCH(x)		((x) & FW_REV_PATCH_MASK)
 
 #define MAX_RX_TIMEOUT		(msecs_to_jiffies(30))
 
@@ -304,6 +311,10 @@ struct clk_get_info {
 	u8 name[20];
 } __packed;
 
+struct clk_get_value {
+	__le32 rate;
+} __packed;
+
 struct clk_set_value {
 	__le16 id;
 	__le16 reserved;
@@ -317,9 +328,7 @@ struct legacy_clk_set_value {
 } __packed;
 
 struct dvfs_info {
-	u8 domain;
-	u8 opp_count;
-	__le16 latency;
+	__le32 header;
 	struct {
 		__le32 freq;
 		__le32 m_volt;
@@ -342,6 +351,11 @@ struct _scpi_sensor_info {
 	char name[20];
 };
 
+struct sensor_value {
+	__le32 lo_val;
+	__le32 hi_val;
+} __packed;
+
 struct dev_pstate_set {
 	__le16 dev_id;
 	u8 pstate;
@@ -405,20 +419,19 @@ static void scpi_process_cmd(struct scpi_chan *ch, u32 cmd)
 		unsigned int len;
 
 		if (scpi_info->is_legacy) {
-			struct legacy_scpi_shared_mem __iomem *mem =
-							ch->rx_payload;
+			struct legacy_scpi_shared_mem *mem = ch->rx_payload;
 
 			/* RX Length is not replied by the legacy Firmware */
 			len = match->rx_len;
 
-			match->status = ioread32(&mem->status);
+			match->status = le32_to_cpu(mem->status);
 			memcpy_fromio(match->rx_buf, mem->payload, len);
 		} else {
-			struct scpi_shared_mem __iomem *mem = ch->rx_payload;
+			struct scpi_shared_mem *mem = ch->rx_payload;
 
 			len = min(match->rx_len, CMD_SIZE(cmd));
 
-			match->status = ioread32(&mem->status);
+			match->status = le32_to_cpu(mem->status);
 			memcpy_fromio(match->rx_buf, mem->payload, len);
 		}
 
@@ -432,11 +445,11 @@ static void scpi_process_cmd(struct scpi_chan *ch, u32 cmd)
 static void scpi_handle_remote_msg(struct mbox_client *c, void *msg)
 {
 	struct scpi_chan *ch = container_of(c, struct scpi_chan, cl);
-	struct scpi_shared_mem __iomem *mem = ch->rx_payload;
+	struct scpi_shared_mem *mem = ch->rx_payload;
 	u32 cmd = 0;
 
 	if (!scpi_info->is_legacy)
-		cmd = ioread32(&mem->command);
+		cmd = le32_to_cpu(mem->command);
 
 	scpi_process_cmd(ch, cmd);
 }
@@ -446,7 +459,7 @@ static void scpi_tx_prepare(struct mbox_client *c, void *msg)
 	unsigned long flags;
 	struct scpi_xfer *t = msg;
 	struct scpi_chan *ch = container_of(c, struct scpi_chan, cl);
-	struct scpi_shared_mem __iomem *mem = ch->tx_payload;
+	struct scpi_shared_mem *mem = (struct scpi_shared_mem *)ch->tx_payload;
 
 	if (t->tx_buf) {
 		if (scpi_info->is_legacy)
@@ -465,7 +478,7 @@ static void scpi_tx_prepare(struct mbox_client *c, void *msg)
 	}
 
 	if (!scpi_info->is_legacy)
-		iowrite32(t->cmd, &mem->command);
+		mem->command = cpu_to_le32(t->cmd);
 }
 
 static struct scpi_xfer *get_scpi_xfer(struct scpi_chan *ch)
@@ -570,13 +583,13 @@ scpi_clk_get_range(u16 clk_id, unsigned long *min, unsigned long *max)
 static unsigned long scpi_clk_get_val(u16 clk_id)
 {
 	int ret;
-	__le32 rate;
+	struct clk_get_value clk;
 	__le16 le_clk_id = cpu_to_le16(clk_id);
 
 	ret = scpi_send_message(CMD_GET_CLOCK_VALUE, &le_clk_id,
-				sizeof(le_clk_id), &rate, sizeof(rate));
+				sizeof(le_clk_id), &clk, sizeof(clk));
 
-	return ret ? ret : le32_to_cpu(rate);
+	return ret ? ret : le32_to_cpu(clk.rate);
 }
 
 static int scpi_clk_set_val(u16 clk_id, unsigned long rate)
@@ -632,34 +645,34 @@ static int opp_cmp_func(const void *opp1, const void *opp2)
 
 static struct scpi_dvfs_info *scpi_dvfs_get_info(u8 domain)
 {
-	if (domain >= MAX_DVFS_DOMAINS)
-		return ERR_PTR(-EINVAL);
-
-	return scpi_info->dvfs[domain] ?: ERR_PTR(-EINVAL);
-}
-
-static int scpi_dvfs_populate_info(struct device *dev, u8 domain)
-{
 	struct scpi_dvfs_info *info;
 	struct scpi_opp *opp;
 	struct dvfs_info buf;
 	int ret, i;
 
+	if (domain >= MAX_DVFS_DOMAINS)
+		return ERR_PTR(-EINVAL);
+
+	if (scpi_info->dvfs[domain])	/* data already populated */
+		return scpi_info->dvfs[domain];
+
 	ret = scpi_send_message(CMD_GET_DVFS_INFO, &domain, sizeof(domain),
 				&buf, sizeof(buf));
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
-	info = devm_kmalloc(dev, sizeof(*info), GFP_KERNEL);
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
-	info->count = buf.opp_count;
-	info->latency = le16_to_cpu(buf.latency) * 1000; /* uS to nS */
+	info->count = DVFS_OPP_COUNT(buf.header);
+	info->latency = DVFS_LATENCY(buf.header) * 1000; /* uS to nS */
 
-	info->opps = devm_kcalloc(dev, info->count, sizeof(*opp), GFP_KERNEL);
-	if (!info->opps)
-		return -ENOMEM;
+	info->opps = kcalloc(info->count, sizeof(*opp), GFP_KERNEL);
+	if (!info->opps) {
+		kfree(info);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	for (i = 0, opp = info->opps; i < info->count; i++, opp++) {
 		opp->freq = le32_to_cpu(buf.opps[i].freq);
@@ -669,15 +682,7 @@ static int scpi_dvfs_populate_info(struct device *dev, u8 domain)
 	sort(info->opps, info->count, sizeof(*opp), opp_cmp_func, NULL);
 
 	scpi_info->dvfs[domain] = info;
-	return 0;
-}
-
-static void scpi_dvfs_populate(struct device *dev)
-{
-	int domain;
-
-	for (domain = 0; domain < MAX_DVFS_DOMAINS; domain++)
-		scpi_dvfs_populate_info(dev, domain);
+	return info;
 }
 
 static int scpi_dev_domain_id(struct device *dev)
@@ -708,6 +713,9 @@ static int scpi_dvfs_get_transition_latency(struct device *dev)
 	if (IS_ERR(info))
 		return PTR_ERR(info);
 
+	if (!info->latency)
+		return 0;
+
 	return info->latency;
 }
 
@@ -768,19 +776,20 @@ static int scpi_sensor_get_info(u16 sensor_id, struct scpi_sensor_info *info)
 static int scpi_sensor_get_value(u16 sensor, u64 *val)
 {
 	__le16 id = cpu_to_le16(sensor);
-	__le64 value;
+	struct sensor_value buf;
 	int ret;
 
 	ret = scpi_send_message(CMD_SENSOR_VALUE, &id, sizeof(id),
-				&value, sizeof(value));
+				&buf, sizeof(buf));
 	if (ret)
 		return ret;
 
 	if (scpi_info->is_legacy)
-		/* only 32-bits supported, upper 32 bits can be junk */
-		*val = le32_to_cpup((__le32 *)&value);
+		/* only 32-bits supported, hi_val can be junk */
+		*val = le32_to_cpu(buf.lo_val);
 	else
-		*val = le64_to_cpu(value);
+		*val = (u64)le32_to_cpu(buf.hi_val) << 32 |
+			le32_to_cpu(buf.lo_val);
 
 	return 0;
 }
@@ -853,19 +862,23 @@ static int scpi_init_versions(struct scpi_drvinfo *info)
 static ssize_t protocol_version_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%lu.%lu\n",
-		FIELD_GET(PROTO_REV_MAJOR_MASK, scpi_info->protocol_version),
-		FIELD_GET(PROTO_REV_MINOR_MASK, scpi_info->protocol_version));
+	struct scpi_drvinfo *scpi_info = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d.%d\n",
+		       PROTOCOL_REV_MAJOR(scpi_info->protocol_version),
+		       PROTOCOL_REV_MINOR(scpi_info->protocol_version));
 }
 static DEVICE_ATTR_RO(protocol_version);
 
 static ssize_t firmware_version_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%lu.%lu.%lu\n",
-		     FIELD_GET(FW_REV_MAJOR_MASK, scpi_info->firmware_version),
-		     FIELD_GET(FW_REV_MINOR_MASK, scpi_info->firmware_version),
-		     FIELD_GET(FW_REV_PATCH_MASK, scpi_info->firmware_version));
+	struct scpi_drvinfo *scpi_info = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d.%d.%d\n",
+		       FW_REV_MAJOR(scpi_info->firmware_version),
+		       FW_REV_MINOR(scpi_info->firmware_version),
+		       FW_REV_PATCH(scpi_info->firmware_version));
 }
 static DEVICE_ATTR_RO(firmware_version);
 
@@ -876,13 +889,39 @@ static struct attribute *versions_attrs[] = {
 };
 ATTRIBUTE_GROUPS(versions);
 
-static void scpi_free_channels(void *data)
+static void
+scpi_free_channels(struct device *dev, struct scpi_chan *pchan, int count)
 {
-	struct scpi_drvinfo *info = data;
 	int i;
 
-	for (i = 0; i < info->num_chans; i++)
-		mbox_free_channel(info->channels[i].chan);
+	for (i = 0; i < count && pchan->chan; i++, pchan++) {
+		mbox_free_channel(pchan->chan);
+		devm_kfree(dev, pchan->xfers);
+		devm_iounmap(dev, pchan->rx_payload);
+	}
+}
+
+static int scpi_remove(struct platform_device *pdev)
+{
+	int i;
+	struct device *dev = &pdev->dev;
+	struct scpi_drvinfo *info = platform_get_drvdata(pdev);
+
+	scpi_info = NULL; /* stop exporting SCPI ops through get_scpi_ops */
+
+	of_platform_depopulate(dev);
+	sysfs_remove_groups(&dev->kobj, versions_groups);
+	scpi_free_channels(dev, info->channels, info->num_chans);
+	platform_set_drvdata(pdev, NULL);
+
+	for (i = 0; i < MAX_DVFS_DOMAINS && info->dvfs[i]; i++) {
+		kfree(info->dvfs[i]->opps);
+		kfree(info->dvfs[i]);
+	}
+	devm_kfree(dev, info->channels);
+	devm_kfree(dev, info);
+
+	return 0;
 }
 
 #define MAX_SCPI_XFERS		10
@@ -913,6 +952,7 @@ static int scpi_probe(struct platform_device *pdev)
 {
 	int count, idx, ret;
 	struct resource res;
+	struct scpi_chan *scpi_chan;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 
@@ -929,19 +969,13 @@ static int scpi_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	scpi_info->channels = devm_kcalloc(dev, count, sizeof(struct scpi_chan),
-					   GFP_KERNEL);
-	if (!scpi_info->channels)
+	scpi_chan = devm_kcalloc(dev, count, sizeof(*scpi_chan), GFP_KERNEL);
+	if (!scpi_chan)
 		return -ENOMEM;
 
-	ret = devm_add_action(dev, scpi_free_channels, scpi_info);
-	if (ret)
-		return ret;
-
-	for (; scpi_info->num_chans < count; scpi_info->num_chans++) {
+	for (idx = 0; idx < count; idx++) {
 		resource_size_t size;
-		int idx = scpi_info->num_chans;
-		struct scpi_chan *pchan = scpi_info->channels + idx;
+		struct scpi_chan *pchan = scpi_chan + idx;
 		struct mbox_client *cl = &pchan->cl;
 		struct device_node *shmem = of_parse_phandle(np, "shmem", idx);
 
@@ -949,14 +983,15 @@ static int scpi_probe(struct platform_device *pdev)
 		of_node_put(shmem);
 		if (ret) {
 			dev_err(dev, "failed to get SCPI payload mem resource\n");
-			return ret;
+			goto err;
 		}
 
 		size = resource_size(&res);
 		pchan->rx_payload = devm_ioremap(dev, res.start, size);
 		if (!pchan->rx_payload) {
 			dev_err(dev, "failed to ioremap SCPI payload\n");
-			return -EADDRNOTAVAIL;
+			ret = -EADDRNOTAVAIL;
+			goto err;
 		}
 		pchan->tx_payload = pchan->rx_payload + (size >> 1);
 
@@ -982,11 +1017,17 @@ static int scpi_probe(struct platform_device *pdev)
 				dev_err(dev, "failed to get channel%d err %d\n",
 					idx, ret);
 		}
+err:
+		scpi_free_channels(dev, scpi_chan, idx);
+		scpi_info = NULL;
 		return ret;
 	}
 
+	scpi_info->channels = scpi_chan;
+	scpi_info->num_chans = count;
 	scpi_info->commands = scpi_std_commands;
-	scpi_info->scpi_ops = &scpi_ops;
+
+	platform_set_drvdata(pdev, scpi_info);
 
 	if (scpi_info->is_legacy) {
 		/* Replace with legacy variants */
@@ -1002,23 +1043,23 @@ static int scpi_probe(struct platform_device *pdev)
 	ret = scpi_init_versions(scpi_info);
 	if (ret) {
 		dev_err(dev, "incorrect or no SCP firmware found\n");
+		scpi_remove(pdev);
 		return ret;
 	}
 
-	scpi_dvfs_populate(dev);
-
-	_dev_info(dev, "SCP Protocol %lu.%lu Firmware %lu.%lu.%lu version\n",
-		  FIELD_GET(PROTO_REV_MAJOR_MASK, scpi_info->protocol_version),
-		  FIELD_GET(PROTO_REV_MINOR_MASK, scpi_info->protocol_version),
-		  FIELD_GET(FW_REV_MAJOR_MASK, scpi_info->firmware_version),
-		  FIELD_GET(FW_REV_MINOR_MASK, scpi_info->firmware_version),
-		  FIELD_GET(FW_REV_PATCH_MASK, scpi_info->firmware_version));
+	_dev_info(dev, "SCP Protocol %d.%d Firmware %d.%d.%d version\n",
+		  PROTOCOL_REV_MAJOR(scpi_info->protocol_version),
+		  PROTOCOL_REV_MINOR(scpi_info->protocol_version),
+		  FW_REV_MAJOR(scpi_info->firmware_version),
+		  FW_REV_MINOR(scpi_info->firmware_version),
+		  FW_REV_PATCH(scpi_info->firmware_version));
+	scpi_info->scpi_ops = &scpi_ops;
 
-	ret = devm_device_add_groups(dev, versions_groups);
+	ret = sysfs_create_groups(&dev->kobj, versions_groups);
 	if (ret)
 		dev_err(dev, "unable to create sysfs version group\n");
 
-	return devm_of_platform_populate(dev);
+	return of_platform_populate(dev->of_node, NULL, NULL, dev);
 }
 
 static const struct of_device_id scpi_of_match[] = {
@@ -1035,6 +1076,7 @@ static struct platform_driver scpi_driver = {
 		.of_match_table = scpi_of_match,
 	},
 	.probe = scpi_probe,
+	.remove = scpi_remove,
 };
 module_platform_driver(scpi_driver);
 
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
new file mode 100644
index 000000000000..1ea71640fdc2
--- /dev/null
+++ b/drivers/firmware/arm_sdei.c
@@ -0,0 +1,1092 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2017 Arm Ltd.
+#define pr_fmt(fmt) "sdei: " fmt
+
+#include <linux/acpi.h>
+#include <linux/arm_sdei.h>
+#include <linux/arm-smccc.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/cpuhotplug.h>
+#include <linux/cpu.h>
+#include <linux/cpu_pm.h>
+#include <linux/errno.h>
+#include <linux/hardirq.h>
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/kvm_host.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/percpu.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/ptrace.h>
+#include <linux/preempt.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+
+/*
+ * The call to use to reach the firmware.
+ */
+static asmlinkage void (*sdei_firmware_call)(unsigned long function_id,
+		      unsigned long arg0, unsigned long arg1,
+		      unsigned long arg2, unsigned long arg3,
+		      unsigned long arg4, struct arm_smccc_res *res);
+
+/* entry point from firmware to arch asm code */
+static unsigned long sdei_entry_point;
+
+struct sdei_event {
+	/* These three are protected by the sdei_list_lock */
+	struct list_head	list;
+	bool			reregister;
+	bool			reenable;
+
+	u32			event_num;
+	u8			type;
+	u8			priority;
+
+	/* This pointer is handed to firmware as the event argument. */
+	union {
+		/* Shared events */
+		struct sdei_registered_event *registered;
+
+		/* CPU private events */
+		struct sdei_registered_event __percpu *private_registered;
+	};
+};
+
+/* Take the mutex for any API call or modification. Take the mutex first. */
+static DEFINE_MUTEX(sdei_events_lock);
+
+/* and then hold this when modifying the list */
+static DEFINE_SPINLOCK(sdei_list_lock);
+static LIST_HEAD(sdei_list);
+
+/* Private events are registered/enabled via IPI passing one of these */
+struct sdei_crosscall_args {
+	struct sdei_event *event;
+	atomic_t errors;
+	int first_error;
+};
+
+#define CROSSCALL_INIT(arg, event)	(arg.event = event, \
+					 arg.first_error = 0, \
+					 atomic_set(&arg.errors, 0))
+
+static inline int sdei_do_cross_call(void *fn, struct sdei_event * event)
+{
+	struct sdei_crosscall_args arg;
+
+	CROSSCALL_INIT(arg, event);
+	on_each_cpu(fn, &arg, true);
+
+	return arg.first_error;
+}
+
+static inline void
+sdei_cross_call_return(struct sdei_crosscall_args *arg, int err)
+{
+	if (err && (atomic_inc_return(&arg->errors) == 1))
+		arg->first_error = err;
+}
+
+static int sdei_to_linux_errno(unsigned long sdei_err)
+{
+	switch (sdei_err) {
+	case SDEI_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	case SDEI_INVALID_PARAMETERS:
+		return -EINVAL;
+	case SDEI_DENIED:
+		return -EPERM;
+	case SDEI_PENDING:
+		return -EINPROGRESS;
+	case SDEI_OUT_OF_RESOURCE:
+		return -ENOMEM;
+	}
+
+	/* Not an error value ... */
+	return sdei_err;
+}
+
+/*
+ * If x0 is any of these values, then the call failed, use sdei_to_linux_errno()
+ * to translate.
+ */
+static int sdei_is_err(struct arm_smccc_res *res)
+{
+	switch (res->a0) {
+	case SDEI_NOT_SUPPORTED:
+	case SDEI_INVALID_PARAMETERS:
+	case SDEI_DENIED:
+	case SDEI_PENDING:
+	case SDEI_OUT_OF_RESOURCE:
+		return true;
+	}
+
+	return false;
+}
+
+static int invoke_sdei_fn(unsigned long function_id, unsigned long arg0,
+			  unsigned long arg1, unsigned long arg2,
+			  unsigned long arg3, unsigned long arg4,
+			  u64 *result)
+{
+	int err = 0;
+	struct arm_smccc_res res;
+
+	if (sdei_firmware_call) {
+		sdei_firmware_call(function_id, arg0, arg1, arg2, arg3, arg4,
+				   &res);
+		if (sdei_is_err(&res))
+			err = sdei_to_linux_errno(res.a0);
+	} else {
+		/*
+		 * !sdei_firmware_call means we failed to probe or called
+		 * sdei_mark_interface_broken(). -EIO is not an error returned
+		 * by sdei_to_linux_errno() and is used to suppress messages
+		 * from this driver.
+		 */
+		err = -EIO;
+		res.a0 = SDEI_NOT_SUPPORTED;
+	}
+
+	if (result)
+		*result = res.a0;
+
+	return err;
+}
+
+static struct sdei_event *sdei_event_find(u32 event_num)
+{
+	struct sdei_event *e, *found = NULL;
+
+	lockdep_assert_held(&sdei_events_lock);
+
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(e, &sdei_list, list) {
+		if (e->event_num == event_num) {
+			found = e;
+			break;
+		}
+	}
+	spin_unlock(&sdei_list_lock);
+
+	return found;
+}
+
+int sdei_api_event_context(u32 query, u64 *result)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_CONTEXT, query, 0, 0, 0, 0,
+			      result);
+}
+NOKPROBE_SYMBOL(sdei_api_event_context);
+
+static int sdei_api_event_get_info(u32 event, u32 info, u64 *result)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_GET_INFO, event, info, 0,
+			      0, 0, result);
+}
+
+static struct sdei_event *sdei_event_create(u32 event_num,
+					    sdei_event_callback *cb,
+					    void *cb_arg)
+{
+	int err;
+	u64 result;
+	struct sdei_event *event;
+	struct sdei_registered_event *reg;
+
+	lockdep_assert_held(&sdei_events_lock);
+
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
+	if (!event)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&event->list);
+	event->event_num = event_num;
+
+	err = sdei_api_event_get_info(event_num, SDEI_EVENT_INFO_EV_PRIORITY,
+				      &result);
+	if (err) {
+		kfree(event);
+		return ERR_PTR(err);
+	}
+	event->priority = result;
+
+	err = sdei_api_event_get_info(event_num, SDEI_EVENT_INFO_EV_TYPE,
+				      &result);
+	if (err) {
+		kfree(event);
+		return ERR_PTR(err);
+	}
+	event->type = result;
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED) {
+		reg = kzalloc(sizeof(*reg), GFP_KERNEL);
+		if (!reg) {
+			kfree(event);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		reg->event_num = event_num;
+		reg->priority = event->priority;
+
+		reg->callback = cb;
+		reg->callback_arg = cb_arg;
+		event->registered = reg;
+	} else {
+		int cpu;
+		struct sdei_registered_event __percpu *regs;
+
+		regs = alloc_percpu(struct sdei_registered_event);
+		if (!regs) {
+			kfree(event);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		for_each_possible_cpu(cpu) {
+			reg = per_cpu_ptr(regs, cpu);
+
+			reg->event_num = event->event_num;
+			reg->priority = event->priority;
+			reg->callback = cb;
+			reg->callback_arg = cb_arg;
+		}
+
+		event->private_registered = regs;
+	}
+
+	if (sdei_event_find(event_num)) {
+		kfree(event->registered);
+		kfree(event);
+		event = ERR_PTR(-EBUSY);
+	} else {
+		spin_lock(&sdei_list_lock);
+		list_add(&event->list, &sdei_list);
+		spin_unlock(&sdei_list_lock);
+	}
+
+	return event;
+}
+
+static void sdei_event_destroy(struct sdei_event *event)
+{
+	lockdep_assert_held(&sdei_events_lock);
+
+	spin_lock(&sdei_list_lock);
+	list_del(&event->list);
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		kfree(event->registered);
+	else
+		free_percpu(event->private_registered);
+
+	kfree(event);
+}
+
+static int sdei_api_get_version(u64 *version)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_VERSION, 0, 0, 0, 0, 0, version);
+}
+
+int sdei_mask_local_cpu(void)
+{
+	int err;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_MASK, 0, 0, 0, 0, 0, NULL);
+	if (err && err != -EIO) {
+		pr_warn_once("failed to mask CPU[%u]: %d\n",
+			      smp_processor_id(), err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void _ipi_mask_cpu(void *ignored)
+{
+	sdei_mask_local_cpu();
+}
+
+int sdei_unmask_local_cpu(void)
+{
+	int err;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_UNMASK, 0, 0, 0, 0, 0, NULL);
+	if (err && err != -EIO) {
+		pr_warn_once("failed to unmask CPU[%u]: %d\n",
+			     smp_processor_id(), err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void _ipi_unmask_cpu(void *ignored)
+{
+	sdei_unmask_local_cpu();
+}
+
+static void _ipi_private_reset(void *ignored)
+{
+	int err;
+
+	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PRIVATE_RESET, 0, 0, 0, 0, 0,
+			     NULL);
+	if (err && err != -EIO)
+		pr_warn_once("failed to reset CPU[%u]: %d\n",
+			     smp_processor_id(), err);
+}
+
+static int sdei_api_shared_reset(void)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_SHARED_RESET, 0, 0, 0, 0, 0,
+			      NULL);
+}
+
+static void sdei_mark_interface_broken(void)
+{
+	pr_err("disabling SDEI firmware interface\n");
+	on_each_cpu(&_ipi_mask_cpu, NULL, true);
+	sdei_firmware_call = NULL;
+}
+
+static int sdei_platform_reset(void)
+{
+	int err;
+
+	on_each_cpu(&_ipi_private_reset, NULL, true);
+	err = sdei_api_shared_reset();
+	if (err) {
+		pr_err("Failed to reset platform: %d\n", err);
+		sdei_mark_interface_broken();
+	}
+
+	return err;
+}
+
+static int sdei_api_event_enable(u32 event_num)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_ENABLE, event_num, 0, 0, 0,
+			      0, NULL);
+}
+
+/* Called directly by the hotplug callbacks */
+static void _local_event_enable(void *data)
+{
+	int err;
+	struct sdei_crosscall_args *arg = data;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = sdei_api_event_enable(arg->event->event_num);
+
+	sdei_cross_call_return(arg, err);
+}
+
+int sdei_event_enable(u32 event_num)
+{
+	int err = -EINVAL;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	event = sdei_event_find(event_num);
+	if (!event) {
+		mutex_unlock(&sdei_events_lock);
+		return -ENOENT;
+	}
+
+	spin_lock(&sdei_list_lock);
+	event->reenable = true;
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		err = sdei_api_event_enable(event->event_num);
+	else
+		err = sdei_do_cross_call(_local_event_enable, event);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+EXPORT_SYMBOL(sdei_event_enable);
+
+static int sdei_api_event_disable(u32 event_num)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_DISABLE, event_num, 0, 0,
+			      0, 0, NULL);
+}
+
+static void _ipi_event_disable(void *data)
+{
+	int err;
+	struct sdei_crosscall_args *arg = data;
+
+	err = sdei_api_event_disable(arg->event->event_num);
+
+	sdei_cross_call_return(arg, err);
+}
+
+int sdei_event_disable(u32 event_num)
+{
+	int err = -EINVAL;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	event = sdei_event_find(event_num);
+	if (!event) {
+		mutex_unlock(&sdei_events_lock);
+		return -ENOENT;
+	}
+
+	spin_lock(&sdei_list_lock);
+	event->reenable = false;
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		err = sdei_api_event_disable(event->event_num);
+	else
+		err = sdei_do_cross_call(_ipi_event_disable, event);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+EXPORT_SYMBOL(sdei_event_disable);
+
+static int sdei_api_event_unregister(u32 event_num)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_UNREGISTER, event_num, 0,
+			      0, 0, 0, NULL);
+}
+
+/* Called directly by the hotplug callbacks */
+static void _local_event_unregister(void *data)
+{
+	int err;
+	struct sdei_crosscall_args *arg = data;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = sdei_api_event_unregister(arg->event->event_num);
+
+	sdei_cross_call_return(arg, err);
+}
+
+static int _sdei_event_unregister(struct sdei_event *event)
+{
+	lockdep_assert_held(&sdei_events_lock);
+
+	spin_lock(&sdei_list_lock);
+	event->reregister = false;
+	event->reenable = false;
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		return sdei_api_event_unregister(event->event_num);
+
+	return sdei_do_cross_call(_local_event_unregister, event);
+}
+
+int sdei_event_unregister(u32 event_num)
+{
+	int err;
+	struct sdei_event *event;
+
+	WARN_ON(in_nmi());
+
+	mutex_lock(&sdei_events_lock);
+	event = sdei_event_find(event_num);
+	do {
+		if (!event) {
+			pr_warn("Event %u not registered\n", event_num);
+			err = -ENOENT;
+			break;
+		}
+
+		err = _sdei_event_unregister(event);
+		if (err)
+			break;
+
+		sdei_event_destroy(event);
+	} while (0);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+EXPORT_SYMBOL(sdei_event_unregister);
+
+/*
+ * unregister events, but don't destroy them as they are re-registered by
+ * sdei_reregister_shared().
+ */
+static int sdei_unregister_shared(void)
+{
+	int err = 0;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type != SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		err = _sdei_event_unregister(event);
+		if (err)
+			break;
+	}
+	spin_unlock(&sdei_list_lock);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+
+static int sdei_api_event_register(u32 event_num, unsigned long entry_point,
+				   void *arg, u64 flags, u64 affinity)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_REGISTER, event_num,
+			      (unsigned long)entry_point, (unsigned long)arg,
+			      flags, affinity, NULL);
+}
+
+/* Called directly by the hotplug callbacks */
+static void _local_event_register(void *data)
+{
+	int err;
+	struct sdei_registered_event *reg;
+	struct sdei_crosscall_args *arg = data;
+
+	WARN_ON(preemptible());
+
+	reg = per_cpu_ptr(arg->event->private_registered, smp_processor_id());
+	err = sdei_api_event_register(arg->event->event_num, sdei_entry_point,
+				      reg, 0, 0);
+
+	sdei_cross_call_return(arg, err);
+}
+
+static int _sdei_event_register(struct sdei_event *event)
+{
+	int err;
+
+	lockdep_assert_held(&sdei_events_lock);
+
+	spin_lock(&sdei_list_lock);
+	event->reregister = true;
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		return sdei_api_event_register(event->event_num,
+					       sdei_entry_point,
+					       event->registered,
+					       SDEI_EVENT_REGISTER_RM_ANY, 0);
+
+
+	err = sdei_do_cross_call(_local_event_register, event);
+	if (err) {
+		spin_lock(&sdei_list_lock);
+		event->reregister = false;
+		event->reenable = false;
+		spin_unlock(&sdei_list_lock);
+
+		sdei_do_cross_call(_local_event_unregister, event);
+	}
+
+	return err;
+}
+
+int sdei_event_register(u32 event_num, sdei_event_callback *cb, void *arg)
+{
+	int err;
+	struct sdei_event *event;
+
+	WARN_ON(in_nmi());
+
+	mutex_lock(&sdei_events_lock);
+	do {
+		if (sdei_event_find(event_num)) {
+			pr_warn("Event %u already registered\n", event_num);
+			err = -EBUSY;
+			break;
+		}
+
+		event = sdei_event_create(event_num, cb, arg);
+		if (IS_ERR(event)) {
+			err = PTR_ERR(event);
+			pr_warn("Failed to create event %u: %d\n", event_num,
+				err);
+			break;
+		}
+
+		err = _sdei_event_register(event);
+		if (err) {
+			sdei_event_destroy(event);
+			pr_warn("Failed to register event %u: %d\n", event_num,
+				err);
+		}
+	} while (0);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+EXPORT_SYMBOL(sdei_event_register);
+
+static int sdei_reregister_event(struct sdei_event *event)
+{
+	int err;
+
+	lockdep_assert_held(&sdei_events_lock);
+
+	err = _sdei_event_register(event);
+	if (err) {
+		pr_err("Failed to re-register event %u\n", event->event_num);
+		sdei_event_destroy(event);
+		return err;
+	}
+
+	if (event->reenable) {
+		if (event->type == SDEI_EVENT_TYPE_SHARED)
+			err = sdei_api_event_enable(event->event_num);
+		else
+			err = sdei_do_cross_call(_local_event_enable, event);
+	}
+
+	if (err)
+		pr_err("Failed to re-enable event %u\n", event->event_num);
+
+	return err;
+}
+
+static int sdei_reregister_shared(void)
+{
+	int err = 0;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type != SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		if (event->reregister) {
+			err = sdei_reregister_event(event);
+			if (err)
+				break;
+		}
+	}
+	spin_unlock(&sdei_list_lock);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+
+static int sdei_cpuhp_down(unsigned int cpu)
+{
+	struct sdei_event *event;
+	struct sdei_crosscall_args arg;
+
+	/* un-register private events */
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type == SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		CROSSCALL_INIT(arg, event);
+		/* call the cross-call function locally... */
+		_local_event_unregister(&arg);
+		if (arg.first_error)
+			pr_err("Failed to unregister event %u: %d\n",
+			       event->event_num, arg.first_error);
+	}
+	spin_unlock(&sdei_list_lock);
+
+	return sdei_mask_local_cpu();
+}
+
+static int sdei_cpuhp_up(unsigned int cpu)
+{
+	struct sdei_event *event;
+	struct sdei_crosscall_args arg;
+
+	/* re-register/enable private events */
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type == SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		if (event->reregister) {
+			CROSSCALL_INIT(arg, event);
+			/* call the cross-call function locally... */
+			_local_event_register(&arg);
+			if (arg.first_error)
+				pr_err("Failed to re-register event %u: %d\n",
+				       event->event_num, arg.first_error);
+		}
+
+		if (event->reenable) {
+			CROSSCALL_INIT(arg, event);
+			_local_event_enable(&arg);
+			if (arg.first_error)
+				pr_err("Failed to re-enable event %u: %d\n",
+				       event->event_num, arg.first_error);
+		}
+	}
+	spin_unlock(&sdei_list_lock);
+
+	return sdei_unmask_local_cpu();
+}
+
+/* When entering idle, mask/unmask events for this cpu */
+static int sdei_pm_notifier(struct notifier_block *nb, unsigned long action,
+			    void *data)
+{
+	int rv;
+
+	switch (action) {
+	case CPU_PM_ENTER:
+		rv = sdei_mask_local_cpu();
+		break;
+	case CPU_PM_EXIT:
+	case CPU_PM_ENTER_FAILED:
+		rv = sdei_unmask_local_cpu();
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	if (rv)
+		return notifier_from_errno(rv);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block sdei_pm_nb = {
+	.notifier_call = sdei_pm_notifier,
+};
+
+static int sdei_device_suspend(struct device *dev)
+{
+	on_each_cpu(_ipi_mask_cpu, NULL, true);
+
+	return 0;
+}
+
+static int sdei_device_resume(struct device *dev)
+{
+	on_each_cpu(_ipi_unmask_cpu, NULL, true);
+
+	return 0;
+}
+
+/*
+ * We need all events to be reregistered when we resume from hibernate.
+ *
+ * The sequence is freeze->thaw. Reboot. freeze->restore. We unregister
+ * events during freeze, then re-register and re-enable them during thaw
+ * and restore.
+ */
+static int sdei_device_freeze(struct device *dev)
+{
+	int err;
+
+	/* unregister private events */
+	cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING);
+
+	err = sdei_unregister_shared();
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int sdei_device_thaw(struct device *dev)
+{
+	int err;
+
+	/* re-register shared events */
+	err = sdei_reregister_shared();
+	if (err) {
+		pr_warn("Failed to re-register shared events...\n");
+		sdei_mark_interface_broken();
+		return err;
+	}
+
+	err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI",
+				&sdei_cpuhp_up, &sdei_cpuhp_down);
+	if (err)
+		pr_warn("Failed to re-register CPU hotplug notifier...\n");
+
+	return err;
+}
+
+static int sdei_device_restore(struct device *dev)
+{
+	int err;
+
+	err = sdei_platform_reset();
+	if (err)
+		return err;
+
+	return sdei_device_thaw(dev);
+}
+
+static const struct dev_pm_ops sdei_pm_ops = {
+	.suspend = sdei_device_suspend,
+	.resume = sdei_device_resume,
+	.freeze = sdei_device_freeze,
+	.thaw = sdei_device_thaw,
+	.restore = sdei_device_restore,
+};
+
+/*
+ * Mask all CPUs and unregister all events on panic, reboot or kexec.
+ */
+static int sdei_reboot_notifier(struct notifier_block *nb, unsigned long action,
+				void *data)
+{
+	/*
+	 * We are going to reset the interface, after this there is no point
+	 * doing work when we take CPUs offline.
+	 */
+	cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING);
+
+	sdei_platform_reset();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block sdei_reboot_nb = {
+	.notifier_call = sdei_reboot_notifier,
+};
+
+static void sdei_smccc_smc(unsigned long function_id,
+			   unsigned long arg0, unsigned long arg1,
+			   unsigned long arg2, unsigned long arg3,
+			   unsigned long arg4, struct arm_smccc_res *res)
+{
+	arm_smccc_smc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
+}
+
+static void sdei_smccc_hvc(unsigned long function_id,
+			   unsigned long arg0, unsigned long arg1,
+			   unsigned long arg2, unsigned long arg3,
+			   unsigned long arg4, struct arm_smccc_res *res)
+{
+	arm_smccc_hvc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
+}
+
+static int sdei_get_conduit(struct platform_device *pdev)
+{
+	const char *method;
+	struct device_node *np = pdev->dev.of_node;
+
+	sdei_firmware_call = NULL;
+	if (np) {
+		if (of_property_read_string(np, "method", &method)) {
+			pr_warn("missing \"method\" property\n");
+			return CONDUIT_INVALID;
+		}
+
+		if (!strcmp("hvc", method)) {
+			sdei_firmware_call = &sdei_smccc_hvc;
+			return CONDUIT_HVC;
+		} else if (!strcmp("smc", method)) {
+			sdei_firmware_call = &sdei_smccc_smc;
+			return CONDUIT_SMC;
+		}
+
+		pr_warn("invalid \"method\" property: %s\n", method);
+	} else if (IS_ENABLED(CONFIG_ACPI) && !acpi_disabled) {
+		if (acpi_psci_use_hvc()) {
+			sdei_firmware_call = &sdei_smccc_hvc;
+			return CONDUIT_HVC;
+		} else {
+			sdei_firmware_call = &sdei_smccc_smc;
+			return CONDUIT_SMC;
+		}
+	}
+
+	return CONDUIT_INVALID;
+}
+
+static int sdei_probe(struct platform_device *pdev)
+{
+	int err;
+	u64 ver = 0;
+	int conduit;
+
+	conduit = sdei_get_conduit(pdev);
+	if (!sdei_firmware_call)
+		return 0;
+
+	err = sdei_api_get_version(&ver);
+	if (err == -EOPNOTSUPP)
+		pr_err("advertised but not implemented in platform firmware\n");
+	if (err) {
+		pr_err("Failed to get SDEI version: %d\n", err);
+		sdei_mark_interface_broken();
+		return err;
+	}
+
+	pr_info("SDEIv%d.%d (0x%x) detected in firmware.\n",
+		(int)SDEI_VERSION_MAJOR(ver), (int)SDEI_VERSION_MINOR(ver),
+		(int)SDEI_VERSION_VENDOR(ver));
+
+	if (SDEI_VERSION_MAJOR(ver) != 1) {
+		pr_warn("Conflicting SDEI version detected.\n");
+		sdei_mark_interface_broken();
+		return -EINVAL;
+	}
+
+	err = sdei_platform_reset();
+	if (err)
+		return err;
+
+	sdei_entry_point = sdei_arch_get_entry_point(conduit);
+	if (!sdei_entry_point) {
+		/* Not supported due to hardware or boot configuration */
+		sdei_mark_interface_broken();
+		return 0;
+	}
+
+	err = cpu_pm_register_notifier(&sdei_pm_nb);
+	if (err) {
+		pr_warn("Failed to register CPU PM notifier...\n");
+		goto error;
+	}
+
+	err = register_reboot_notifier(&sdei_reboot_nb);
+	if (err) {
+		pr_warn("Failed to register reboot notifier...\n");
+		goto remove_cpupm;
+	}
+
+	err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI",
+				&sdei_cpuhp_up, &sdei_cpuhp_down);
+	if (err) {
+		pr_warn("Failed to register CPU hotplug notifier...\n");
+		goto remove_reboot;
+	}
+
+	return 0;
+
+remove_reboot:
+	unregister_reboot_notifier(&sdei_reboot_nb);
+
+remove_cpupm:
+	cpu_pm_unregister_notifier(&sdei_pm_nb);
+
+error:
+	sdei_mark_interface_broken();
+	return err;
+}
+
+static const struct of_device_id sdei_of_match[] = {
+	{ .compatible = "arm,sdei-1.0" },
+	{}
+};
+
+static struct platform_driver sdei_driver = {
+	.driver		= {
+		.name			= "sdei",
+		.pm			= &sdei_pm_ops,
+		.of_match_table		= sdei_of_match,
+	},
+	.probe		= sdei_probe,
+};
+
+static bool __init sdei_present_dt(void)
+{
+	struct platform_device *pdev;
+	struct device_node *np, *fw_np;
+
+	fw_np = of_find_node_by_name(NULL, "firmware");
+	if (!fw_np)
+		return false;
+
+	np = of_find_matching_node(fw_np, sdei_of_match);
+	of_node_put(fw_np);
+	if (!np)
+		return false;
+
+	pdev = of_platform_device_create(np, sdei_driver.driver.name, NULL);
+	of_node_put(np);
+	if (!pdev)
+		return false;
+
+	return true;
+}
+
+static bool __init sdei_present_acpi(void)
+{
+	acpi_status status;
+	struct platform_device *pdev;
+	struct acpi_table_header *sdei_table_header;
+
+	if (acpi_disabled)
+		return false;
+
+	status = acpi_get_table(ACPI_SIG_SDEI, 0, &sdei_table_header);
+	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
+		const char *msg = acpi_format_exception(status);
+
+		pr_info("Failed to get ACPI:SDEI table, %s\n", msg);
+	}
+	if (ACPI_FAILURE(status))
+		return false;
+
+	pdev = platform_device_register_simple(sdei_driver.driver.name, 0, NULL,
+					       0);
+	if (IS_ERR(pdev))
+		return false;
+
+	return true;
+}
+
+static int __init sdei_init(void)
+{
+	if (sdei_present_dt() || sdei_present_acpi())
+		platform_driver_register(&sdei_driver);
+
+	return 0;
+}
+
+/*
+ * On an ACPI system SDEI needs to be ready before HEST:GHES tries to register
+ * its events. ACPI is initialised from a subsys_initcall(), GHES is initialised
+ * by device_initcall(). We want to be called in the middle.
+ */
+subsys_initcall_sync(sdei_init);
+
+int sdei_event_handler(struct pt_regs *regs,
+		       struct sdei_registered_event *arg)
+{
+	int err;
+	mm_segment_t orig_addr_limit;
+	u32 event_num = arg->event_num;
+
+	orig_addr_limit = get_fs();
+	set_fs(USER_DS);
+
+	err = arg->callback(event_num, regs, arg->callback_arg);
+	if (err)
+		pr_err_ratelimited("event %u on CPU %u failed with error: %d\n",
+				   event_num, smp_processor_id(), err);
+
+	set_fs(orig_addr_limit);
+
+	return err;
+}
+NOKPROBE_SYMBOL(sdei_event_handler);
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 2b4c39fdfa91..3098410abad8 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -113,7 +113,7 @@ config EFI_CAPSULE_LOADER
 	  Most users should say N.
 
 config EFI_CAPSULE_QUIRK_QUARK_CSH
-	boolean "Add support for Quark capsules with non-standard headers"
+	bool "Add support for Quark capsules with non-standard headers"
 	depends on X86 && !64BIT
 	select EFI_CAPSULE_LOADER
 	default y
@@ -159,13 +159,21 @@ config RESET_ATTACK_MITIGATION
 	  using the TCG Platform Reset Attack Mitigation specification. This
 	  protects against an attacker forcibly rebooting the system while it
 	  still contains secrets in RAM, booting another OS and extracting the
-	  secrets.
+	  secrets. This should only be enabled when userland is configured to
+	  clear the MemoryOverwriteRequest flag on clean shutdown after secrets
+	  have been evicted, since otherwise it will trigger even on clean
+	  reboots.
 
 endmenu
 
 config UEFI_CPER
 	bool
 
+config UEFI_CPER_ARM
+	bool
+	depends on UEFI_CPER && ( ARM || ARM64 )
+	default y
+
 config EFI_DEV_PATH_PARSER
 	bool
 	depends on ACPI
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 269501dfba53..cb805374f4bc 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -11,7 +11,7 @@
 KASAN_SANITIZE_runtime-wrappers.o	:= n
 
 obj-$(CONFIG_ACPI_BGRT) 		+= efi-bgrt.o
-obj-$(CONFIG_EFI)			+= efi.o vars.o reboot.o memattr.o
+obj-$(CONFIG_EFI)			+= efi.o vars.o reboot.o memattr.o tpm.o
 obj-$(CONFIG_EFI)			+= capsule.o memmap.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
 obj-$(CONFIG_EFI_ESRT)			+= esrt.o
@@ -30,3 +30,4 @@ arm-obj-$(CONFIG_EFI)			:= arm-init.o arm-runtime.o
 obj-$(CONFIG_ARM)			+= $(arm-obj-y)
 obj-$(CONFIG_ARM64)			+= $(arm-obj-y)
 obj-$(CONFIG_EFI_CAPSULE_LOADER)	+= capsule-loader.o
+obj-$(CONFIG_UEFI_CPER_ARM)		+= cper-arm.o
diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c
index ec8ac5c4dd84..e456f4602df1 100644
--- a/drivers/firmware/efi/capsule-loader.c
+++ b/drivers/firmware/efi/capsule-loader.c
@@ -20,10 +20,6 @@
 
 #define NO_FURTHER_WRITE_ACTION -1
 
-#ifndef phys_to_page
-#define phys_to_page(x)		pfn_to_page((x) >> PAGE_SHIFT)
-#endif
-
 /**
  * efi_free_all_buff_pages - free all previous allocated buffer pages
  * @cap_info: pointer to current instance of capsule_info structure
@@ -35,7 +31,7 @@
 static void efi_free_all_buff_pages(struct capsule_info *cap_info)
 {
 	while (cap_info->index > 0)
-		__free_page(phys_to_page(cap_info->pages[--cap_info->index]));
+		__free_page(cap_info->pages[--cap_info->index]);
 
 	cap_info->index = NO_FURTHER_WRITE_ACTION;
 }
@@ -49,7 +45,7 @@ int __efi_capsule_setup_info(struct capsule_info *cap_info)
 	pages_needed = ALIGN(cap_info->total_size, PAGE_SIZE) / PAGE_SIZE;
 
 	if (pages_needed == 0) {
-		pr_err("invalid capsule size");
+		pr_err("invalid capsule size\n");
 		return -EINVAL;
 	}
 
@@ -71,6 +67,14 @@ int __efi_capsule_setup_info(struct capsule_info *cap_info)
 
 	cap_info->pages = temp_page;
 
+	temp_page = krealloc(cap_info->phys,
+			     pages_needed * sizeof(phys_addr_t *),
+			     GFP_KERNEL | __GFP_ZERO);
+	if (!temp_page)
+		return -ENOMEM;
+
+	cap_info->phys = temp_page;
+
 	return 0;
 }
 
@@ -105,9 +109,24 @@ int __weak efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff,
  **/
 static ssize_t efi_capsule_submit_update(struct capsule_info *cap_info)
 {
+	bool do_vunmap = false;
 	int ret;
 
-	ret = efi_capsule_update(&cap_info->header, cap_info->pages);
+	/*
+	 * cap_info->capsule may have been assigned already by a quirk
+	 * handler, so only overwrite it if it is NULL
+	 */
+	if (!cap_info->capsule) {
+		cap_info->capsule = vmap(cap_info->pages, cap_info->index,
+					 VM_MAP, PAGE_KERNEL);
+		if (!cap_info->capsule)
+			return -ENOMEM;
+		do_vunmap = true;
+	}
+
+	ret = efi_capsule_update(cap_info->capsule, cap_info->phys);
+	if (do_vunmap)
+		vunmap(cap_info->capsule);
 	if (ret) {
 		pr_err("capsule update failed\n");
 		return ret;
@@ -165,10 +184,12 @@ static ssize_t efi_capsule_write(struct file *file, const char __user *buff,
 			goto failed;
 		}
 
-		cap_info->pages[cap_info->index++] = page_to_phys(page);
+		cap_info->pages[cap_info->index] = page;
+		cap_info->phys[cap_info->index] = page_to_phys(page);
 		cap_info->page_bytes_remain = PAGE_SIZE;
+		cap_info->index++;
 	} else {
-		page = phys_to_page(cap_info->pages[cap_info->index - 1]);
+		page = cap_info->pages[cap_info->index - 1];
 	}
 
 	kbuff = kmap(page);
@@ -252,6 +273,7 @@ static int efi_capsule_release(struct inode *inode, struct file *file)
 	struct capsule_info *cap_info = file->private_data;
 
 	kfree(cap_info->pages);
+	kfree(cap_info->phys);
 	kfree(file->private_data);
 	file->private_data = NULL;
 	return 0;
@@ -281,6 +303,13 @@ static int efi_capsule_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 	}
 
+	cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL);
+	if (!cap_info->phys) {
+		kfree(cap_info->pages);
+		kfree(cap_info);
+		return -ENOMEM;
+	}
+
 	file->private_data = cap_info;
 
 	return 0;
diff --git a/drivers/firmware/efi/cper-arm.c b/drivers/firmware/efi/cper-arm.c
new file mode 100644
index 000000000000..698e5c8e0c8d
--- /dev/null
+++ b/drivers/firmware/efi/cper-arm.c
@@ -0,0 +1,356 @@
+/*
+ * UEFI Common Platform Error Record (CPER) support
+ *
+ * Copyright (C) 2017, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/cper.h>
+#include <linux/dmi.h>
+#include <linux/acpi.h>
+#include <linux/pci.h>
+#include <linux/aer.h>
+#include <linux/printk.h>
+#include <linux/bcd.h>
+#include <acpi/ghes.h>
+#include <ras/ras_event.h>
+
+#define INDENT_SP	" "
+
+static const char * const arm_reg_ctx_strs[] = {
+	"AArch32 general purpose registers",
+	"AArch32 EL1 context registers",
+	"AArch32 EL2 context registers",
+	"AArch32 secure context registers",
+	"AArch64 general purpose registers",
+	"AArch64 EL1 context registers",
+	"AArch64 EL2 context registers",
+	"AArch64 EL3 context registers",
+	"Misc. system register structure",
+};
+
+static const char * const arm_err_trans_type_strs[] = {
+	"Instruction",
+	"Data Access",
+	"Generic",
+};
+
+static const char * const arm_bus_err_op_strs[] = {
+	"Generic error (type cannot be determined)",
+	"Generic read (type of instruction or data request cannot be determined)",
+	"Generic write (type of instruction of data request cannot be determined)",
+	"Data read",
+	"Data write",
+	"Instruction fetch",
+	"Prefetch",
+};
+
+static const char * const arm_cache_err_op_strs[] = {
+	"Generic error (type cannot be determined)",
+	"Generic read (type of instruction or data request cannot be determined)",
+	"Generic write (type of instruction of data request cannot be determined)",
+	"Data read",
+	"Data write",
+	"Instruction fetch",
+	"Prefetch",
+	"Eviction",
+	"Snooping (processor initiated a cache snoop that resulted in an error)",
+	"Snooped (processor raised a cache error caused by another processor or device snooping its cache)",
+	"Management",
+};
+
+static const char * const arm_tlb_err_op_strs[] = {
+	"Generic error (type cannot be determined)",
+	"Generic read (type of instruction or data request cannot be determined)",
+	"Generic write (type of instruction of data request cannot be determined)",
+	"Data read",
+	"Data write",
+	"Instruction fetch",
+	"Prefetch",
+	"Local management operation (processor initiated a TLB management operation that resulted in an error)",
+	"External management operation (processor raised a TLB error caused by another processor or device broadcasting TLB operations)",
+};
+
+static const char * const arm_bus_err_part_type_strs[] = {
+	"Local processor originated request",
+	"Local processor responded to request",
+	"Local processor observed",
+	"Generic",
+};
+
+static const char * const arm_bus_err_addr_space_strs[] = {
+	"External Memory Access",
+	"Internal Memory Access",
+	"Unknown",
+	"Device Memory Access",
+};
+
+static void cper_print_arm_err_info(const char *pfx, u32 type,
+				    u64 error_info)
+{
+	u8 trans_type, op_type, level, participation_type, address_space;
+	u16 mem_attributes;
+	bool proc_context_corrupt, corrected, precise_pc, restartable_pc;
+	bool time_out, access_mode;
+
+	/* If the type is unknown, bail. */
+	if (type > CPER_ARM_MAX_TYPE)
+		return;
+
+	/*
+	 * Vendor type errors have error information values that are vendor
+	 * specific.
+	 */
+	if (type == CPER_ARM_VENDOR_ERROR)
+		return;
+
+	if (error_info & CPER_ARM_ERR_VALID_TRANSACTION_TYPE) {
+		trans_type = ((error_info >> CPER_ARM_ERR_TRANSACTION_SHIFT)
+			      & CPER_ARM_ERR_TRANSACTION_MASK);
+		if (trans_type < ARRAY_SIZE(arm_err_trans_type_strs)) {
+			printk("%stransaction type: %s\n", pfx,
+			       arm_err_trans_type_strs[trans_type]);
+		}
+	}
+
+	if (error_info & CPER_ARM_ERR_VALID_OPERATION_TYPE) {
+		op_type = ((error_info >> CPER_ARM_ERR_OPERATION_SHIFT)
+			   & CPER_ARM_ERR_OPERATION_MASK);
+		switch (type) {
+		case CPER_ARM_CACHE_ERROR:
+			if (op_type < ARRAY_SIZE(arm_cache_err_op_strs)) {
+				printk("%soperation type: %s\n", pfx,
+				       arm_cache_err_op_strs[op_type]);
+			}
+			break;
+		case CPER_ARM_TLB_ERROR:
+			if (op_type < ARRAY_SIZE(arm_tlb_err_op_strs)) {
+				printk("%soperation type: %s\n", pfx,
+				       arm_tlb_err_op_strs[op_type]);
+			}
+			break;
+		case CPER_ARM_BUS_ERROR:
+			if (op_type < ARRAY_SIZE(arm_bus_err_op_strs)) {
+				printk("%soperation type: %s\n", pfx,
+				       arm_bus_err_op_strs[op_type]);
+			}
+			break;
+		}
+	}
+
+	if (error_info & CPER_ARM_ERR_VALID_LEVEL) {
+		level = ((error_info >> CPER_ARM_ERR_LEVEL_SHIFT)
+			 & CPER_ARM_ERR_LEVEL_MASK);
+		switch (type) {
+		case CPER_ARM_CACHE_ERROR:
+			printk("%scache level: %d\n", pfx, level);
+			break;
+		case CPER_ARM_TLB_ERROR:
+			printk("%sTLB level: %d\n", pfx, level);
+			break;
+		case CPER_ARM_BUS_ERROR:
+			printk("%saffinity level at which the bus error occurred: %d\n",
+			       pfx, level);
+			break;
+		}
+	}
+
+	if (error_info & CPER_ARM_ERR_VALID_PROC_CONTEXT_CORRUPT) {
+		proc_context_corrupt = ((error_info >> CPER_ARM_ERR_PC_CORRUPT_SHIFT)
+					& CPER_ARM_ERR_PC_CORRUPT_MASK);
+		if (proc_context_corrupt)
+			printk("%sprocessor context corrupted\n", pfx);
+		else
+			printk("%sprocessor context not corrupted\n", pfx);
+	}
+
+	if (error_info & CPER_ARM_ERR_VALID_CORRECTED) {
+		corrected = ((error_info >> CPER_ARM_ERR_CORRECTED_SHIFT)
+			     & CPER_ARM_ERR_CORRECTED_MASK);
+		if (corrected)
+			printk("%sthe error has been corrected\n", pfx);
+		else
+			printk("%sthe error has not been corrected\n", pfx);
+	}
+
+	if (error_info & CPER_ARM_ERR_VALID_PRECISE_PC) {
+		precise_pc = ((error_info >> CPER_ARM_ERR_PRECISE_PC_SHIFT)
+			      & CPER_ARM_ERR_PRECISE_PC_MASK);
+		if (precise_pc)
+			printk("%sPC is precise\n", pfx);
+		else
+			printk("%sPC is imprecise\n", pfx);
+	}
+
+	if (error_info & CPER_ARM_ERR_VALID_RESTARTABLE_PC) {
+		restartable_pc = ((error_info >> CPER_ARM_ERR_RESTARTABLE_PC_SHIFT)
+				  & CPER_ARM_ERR_RESTARTABLE_PC_MASK);
+		if (restartable_pc)
+			printk("%sProgram execution can be restarted reliably at the PC associated with the error.\n", pfx);
+	}
+
+	/* The rest of the fields are specific to bus errors */
+	if (type != CPER_ARM_BUS_ERROR)
+		return;
+
+	if (error_info & CPER_ARM_ERR_VALID_PARTICIPATION_TYPE) {
+		participation_type = ((error_info >> CPER_ARM_ERR_PARTICIPATION_TYPE_SHIFT)
+				      & CPER_ARM_ERR_PARTICIPATION_TYPE_MASK);
+		if (participation_type < ARRAY_SIZE(arm_bus_err_part_type_strs)) {
+			printk("%sparticipation type: %s\n", pfx,
+			       arm_bus_err_part_type_strs[participation_type]);
+		}
+	}
+
+	if (error_info & CPER_ARM_ERR_VALID_TIME_OUT) {
+		time_out = ((error_info >> CPER_ARM_ERR_TIME_OUT_SHIFT)
+			    & CPER_ARM_ERR_TIME_OUT_MASK);
+		if (time_out)
+			printk("%srequest timed out\n", pfx);
+	}
+
+	if (error_info & CPER_ARM_ERR_VALID_ADDRESS_SPACE) {
+		address_space = ((error_info >> CPER_ARM_ERR_ADDRESS_SPACE_SHIFT)
+				 & CPER_ARM_ERR_ADDRESS_SPACE_MASK);
+		if (address_space < ARRAY_SIZE(arm_bus_err_addr_space_strs)) {
+			printk("%saddress space: %s\n", pfx,
+			       arm_bus_err_addr_space_strs[address_space]);
+		}
+	}
+
+	if (error_info & CPER_ARM_ERR_VALID_MEM_ATTRIBUTES) {
+		mem_attributes = ((error_info >> CPER_ARM_ERR_MEM_ATTRIBUTES_SHIFT)
+				  & CPER_ARM_ERR_MEM_ATTRIBUTES_MASK);
+		printk("%smemory access attributes:0x%x\n", pfx, mem_attributes);
+	}
+
+	if (error_info & CPER_ARM_ERR_VALID_ACCESS_MODE) {
+		access_mode = ((error_info >> CPER_ARM_ERR_ACCESS_MODE_SHIFT)
+			       & CPER_ARM_ERR_ACCESS_MODE_MASK);
+		if (access_mode)
+			printk("%saccess mode: normal\n", pfx);
+		else
+			printk("%saccess mode: secure\n", pfx);
+	}
+}
+
+void cper_print_proc_arm(const char *pfx,
+			 const struct cper_sec_proc_arm *proc)
+{
+	int i, len, max_ctx_type;
+	struct cper_arm_err_info *err_info;
+	struct cper_arm_ctx_info *ctx_info;
+	char newpfx[64], infopfx[64];
+
+	printk("%sMIDR: 0x%016llx\n", pfx, proc->midr);
+
+	len = proc->section_length - (sizeof(*proc) +
+		proc->err_info_num * (sizeof(*err_info)));
+	if (len < 0) {
+		printk("%ssection length: %d\n", pfx, proc->section_length);
+		printk("%ssection length is too small\n", pfx);
+		printk("%sfirmware-generated error record is incorrect\n", pfx);
+		printk("%sERR_INFO_NUM is %d\n", pfx, proc->err_info_num);
+		return;
+	}
+
+	if (proc->validation_bits & CPER_ARM_VALID_MPIDR)
+		printk("%sMultiprocessor Affinity Register (MPIDR): 0x%016llx\n",
+			pfx, proc->mpidr);
+
+	if (proc->validation_bits & CPER_ARM_VALID_AFFINITY_LEVEL)
+		printk("%serror affinity level: %d\n", pfx,
+			proc->affinity_level);
+
+	if (proc->validation_bits & CPER_ARM_VALID_RUNNING_STATE) {
+		printk("%srunning state: 0x%x\n", pfx, proc->running_state);
+		printk("%sPower State Coordination Interface state: %d\n",
+			pfx, proc->psci_state);
+	}
+
+	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
+
+	err_info = (struct cper_arm_err_info *)(proc + 1);
+	for (i = 0; i < proc->err_info_num; i++) {
+		printk("%sError info structure %d:\n", pfx, i);
+
+		printk("%snum errors: %d\n", pfx, err_info->multiple_error + 1);
+
+		if (err_info->validation_bits & CPER_ARM_INFO_VALID_FLAGS) {
+			if (err_info->flags & CPER_ARM_INFO_FLAGS_FIRST)
+				printk("%sfirst error captured\n", newpfx);
+			if (err_info->flags & CPER_ARM_INFO_FLAGS_LAST)
+				printk("%slast error captured\n", newpfx);
+			if (err_info->flags & CPER_ARM_INFO_FLAGS_PROPAGATED)
+				printk("%spropagated error captured\n",
+				       newpfx);
+			if (err_info->flags & CPER_ARM_INFO_FLAGS_OVERFLOW)
+				printk("%soverflow occurred, error info is incomplete\n",
+				       newpfx);
+		}
+
+		printk("%serror_type: %d, %s\n", newpfx, err_info->type,
+			err_info->type < ARRAY_SIZE(cper_proc_error_type_strs) ?
+			cper_proc_error_type_strs[err_info->type] : "unknown");
+		if (err_info->validation_bits & CPER_ARM_INFO_VALID_ERR_INFO) {
+			printk("%serror_info: 0x%016llx\n", newpfx,
+			       err_info->error_info);
+			snprintf(infopfx, sizeof(infopfx), "%s%s", newpfx, INDENT_SP);
+			cper_print_arm_err_info(infopfx, err_info->type,
+						err_info->error_info);
+		}
+		if (err_info->validation_bits & CPER_ARM_INFO_VALID_VIRT_ADDR)
+			printk("%svirtual fault address: 0x%016llx\n",
+				newpfx, err_info->virt_fault_addr);
+		if (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR)
+			printk("%sphysical fault address: 0x%016llx\n",
+				newpfx, err_info->physical_fault_addr);
+		err_info += 1;
+	}
+
+	ctx_info = (struct cper_arm_ctx_info *)err_info;
+	max_ctx_type = ARRAY_SIZE(arm_reg_ctx_strs) - 1;
+	for (i = 0; i < proc->context_info_num; i++) {
+		int size = sizeof(*ctx_info) + ctx_info->size;
+
+		printk("%sContext info structure %d:\n", pfx, i);
+		if (len < size) {
+			printk("%ssection length is too small\n", newpfx);
+			printk("%sfirmware-generated error record is incorrect\n", pfx);
+			return;
+		}
+		if (ctx_info->type > max_ctx_type) {
+			printk("%sInvalid context type: %d (max: %d)\n",
+				newpfx, ctx_info->type, max_ctx_type);
+			return;
+		}
+		printk("%sregister context type: %s\n", newpfx,
+			arm_reg_ctx_strs[ctx_info->type]);
+		print_hex_dump(newpfx, "", DUMP_PREFIX_OFFSET, 16, 4,
+				(ctx_info + 1), ctx_info->size, 0);
+		len -= size;
+		ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + size);
+	}
+
+	if (len > 0) {
+		printk("%sVendor specific error info has %u bytes:\n", pfx,
+		       len);
+		print_hex_dump(newpfx, "", DUMP_PREFIX_OFFSET, 16, 4, ctx_info,
+				len, true);
+	}
+}
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index d2fcafcea07e..c165933ebf38 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -122,7 +122,7 @@ static const char * const proc_isa_strs[] = {
 	"ARM A64",
 };
 
-static const char * const proc_error_type_strs[] = {
+const char * const cper_proc_error_type_strs[] = {
 	"cache error",
 	"TLB error",
 	"bus error",
@@ -157,8 +157,8 @@ static void cper_print_proc_generic(const char *pfx,
 	if (proc->validation_bits & CPER_PROC_VALID_ERROR_TYPE) {
 		printk("%s""error_type: 0x%02x\n", pfx, proc->proc_error_type);
 		cper_print_bits(pfx, proc->proc_error_type,
-				proc_error_type_strs,
-				ARRAY_SIZE(proc_error_type_strs));
+				cper_proc_error_type_strs,
+				ARRAY_SIZE(cper_proc_error_type_strs));
 	}
 	if (proc->validation_bits & CPER_PROC_VALID_OPERATION)
 		printk("%s""operation: %d, %s\n", pfx, proc->operation,
@@ -188,122 +188,6 @@ static void cper_print_proc_generic(const char *pfx,
 		printk("%s""IP: 0x%016llx\n", pfx, proc->ip);
 }
 
-#if defined(CONFIG_ARM64) || defined(CONFIG_ARM)
-static const char * const arm_reg_ctx_strs[] = {
-	"AArch32 general purpose registers",
-	"AArch32 EL1 context registers",
-	"AArch32 EL2 context registers",
-	"AArch32 secure context registers",
-	"AArch64 general purpose registers",
-	"AArch64 EL1 context registers",
-	"AArch64 EL2 context registers",
-	"AArch64 EL3 context registers",
-	"Misc. system register structure",
-};
-
-static void cper_print_proc_arm(const char *pfx,
-				const struct cper_sec_proc_arm *proc)
-{
-	int i, len, max_ctx_type;
-	struct cper_arm_err_info *err_info;
-	struct cper_arm_ctx_info *ctx_info;
-	char newpfx[64];
-
-	printk("%sMIDR: 0x%016llx\n", pfx, proc->midr);
-
-	len = proc->section_length - (sizeof(*proc) +
-		proc->err_info_num * (sizeof(*err_info)));
-	if (len < 0) {
-		printk("%ssection length: %d\n", pfx, proc->section_length);
-		printk("%ssection length is too small\n", pfx);
-		printk("%sfirmware-generated error record is incorrect\n", pfx);
-		printk("%sERR_INFO_NUM is %d\n", pfx, proc->err_info_num);
-		return;
-	}
-
-	if (proc->validation_bits & CPER_ARM_VALID_MPIDR)
-		printk("%sMultiprocessor Affinity Register (MPIDR): 0x%016llx\n",
-			pfx, proc->mpidr);
-
-	if (proc->validation_bits & CPER_ARM_VALID_AFFINITY_LEVEL)
-		printk("%serror affinity level: %d\n", pfx,
-			proc->affinity_level);
-
-	if (proc->validation_bits & CPER_ARM_VALID_RUNNING_STATE) {
-		printk("%srunning state: 0x%x\n", pfx, proc->running_state);
-		printk("%sPower State Coordination Interface state: %d\n",
-			pfx, proc->psci_state);
-	}
-
-	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
-
-	err_info = (struct cper_arm_err_info *)(proc + 1);
-	for (i = 0; i < proc->err_info_num; i++) {
-		printk("%sError info structure %d:\n", pfx, i);
-
-		printk("%snum errors: %d\n", pfx, err_info->multiple_error + 1);
-
-		if (err_info->validation_bits & CPER_ARM_INFO_VALID_FLAGS) {
-			if (err_info->flags & CPER_ARM_INFO_FLAGS_FIRST)
-				printk("%sfirst error captured\n", newpfx);
-			if (err_info->flags & CPER_ARM_INFO_FLAGS_LAST)
-				printk("%slast error captured\n", newpfx);
-			if (err_info->flags & CPER_ARM_INFO_FLAGS_PROPAGATED)
-				printk("%spropagated error captured\n",
-				       newpfx);
-			if (err_info->flags & CPER_ARM_INFO_FLAGS_OVERFLOW)
-				printk("%soverflow occurred, error info is incomplete\n",
-				       newpfx);
-		}
-
-		printk("%serror_type: %d, %s\n", newpfx, err_info->type,
-			err_info->type < ARRAY_SIZE(proc_error_type_strs) ?
-			proc_error_type_strs[err_info->type] : "unknown");
-		if (err_info->validation_bits & CPER_ARM_INFO_VALID_ERR_INFO)
-			printk("%serror_info: 0x%016llx\n", newpfx,
-			       err_info->error_info);
-		if (err_info->validation_bits & CPER_ARM_INFO_VALID_VIRT_ADDR)
-			printk("%svirtual fault address: 0x%016llx\n",
-				newpfx, err_info->virt_fault_addr);
-		if (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR)
-			printk("%sphysical fault address: 0x%016llx\n",
-				newpfx, err_info->physical_fault_addr);
-		err_info += 1;
-	}
-
-	ctx_info = (struct cper_arm_ctx_info *)err_info;
-	max_ctx_type = ARRAY_SIZE(arm_reg_ctx_strs) - 1;
-	for (i = 0; i < proc->context_info_num; i++) {
-		int size = sizeof(*ctx_info) + ctx_info->size;
-
-		printk("%sContext info structure %d:\n", pfx, i);
-		if (len < size) {
-			printk("%ssection length is too small\n", newpfx);
-			printk("%sfirmware-generated error record is incorrect\n", pfx);
-			return;
-		}
-		if (ctx_info->type > max_ctx_type) {
-			printk("%sInvalid context type: %d (max: %d)\n",
-				newpfx, ctx_info->type, max_ctx_type);
-			return;
-		}
-		printk("%sregister context type: %s\n", newpfx,
-			arm_reg_ctx_strs[ctx_info->type]);
-		print_hex_dump(newpfx, "", DUMP_PREFIX_OFFSET, 16, 4,
-				(ctx_info + 1), ctx_info->size, 0);
-		len -= size;
-		ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + size);
-	}
-
-	if (len > 0) {
-		printk("%sVendor specific error info has %u bytes:\n", pfx,
-		       len);
-		print_hex_dump(newpfx, "", DUMP_PREFIX_OFFSET, 16, 4, ctx_info,
-				len, true);
-	}
-}
-#endif
-
 static const char * const mem_err_type_strs[] = {
 	"unknown",
 	"no error",
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index f70febf680c3..cd42f66a7c85 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -52,6 +52,7 @@ struct efi __read_mostly efi = {
 	.properties_table	= EFI_INVALID_TABLE_ADDR,
 	.mem_attr_table		= EFI_INVALID_TABLE_ADDR,
 	.rng_seed		= EFI_INVALID_TABLE_ADDR,
+	.tpm_log		= EFI_INVALID_TABLE_ADDR
 };
 EXPORT_SYMBOL(efi);
 
@@ -109,6 +110,8 @@ struct kobject *efi_kobj;
 /*
  * Let's not leave out systab information that snuck into
  * the efivars driver
+ * Note, do not add more fields in systab sysfs file as it breaks sysfs
+ * one value per file rule!
  */
 static ssize_t systab_show(struct kobject *kobj,
 			   struct kobj_attribute *attr, char *buf)
@@ -143,8 +146,7 @@ static ssize_t systab_show(struct kobject *kobj,
 	return str - buf;
 }
 
-static struct kobj_attribute efi_attr_systab =
-			__ATTR(systab, 0400, systab_show, NULL);
+static struct kobj_attribute efi_attr_systab = __ATTR_RO_MODE(systab, 0400);
 
 #define EFI_FIELD(var) efi.var
 
@@ -463,6 +465,7 @@ static __initdata efi_config_table_type_t common_tables[] = {
 	{EFI_PROPERTIES_TABLE_GUID, "PROP", &efi.properties_table},
 	{EFI_MEMORY_ATTRIBUTES_TABLE_GUID, "MEMATTR", &efi.mem_attr_table},
 	{LINUX_EFI_RANDOM_SEED_TABLE_GUID, "RNG", &efi.rng_seed},
+	{LINUX_EFI_TPM_EVENT_LOG_GUID, "TPMEventLog", &efi.tpm_log},
 	{NULL_GUID, NULL, NULL},
 };
 
@@ -551,6 +554,8 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz,
 	if (efi_enabled(EFI_MEMMAP))
 		efi_memattr_init();
 
+	efi_tpm_eventlog_init();
+
 	/* Parse the EFI Properties table if it exists */
 	if (efi.properties_table != EFI_INVALID_TABLE_ADDR) {
 		efi_properties_table_t *tbl;
@@ -607,7 +612,7 @@ static int __init efi_load_efivars(void)
 		return 0;
 
 	pdev = platform_device_register_simple("efivars", 0, NULL, 0);
-	return IS_ERR(pdev) ? PTR_ERR(pdev) : 0;
+	return PTR_ERR_OR_ZERO(pdev);
 }
 device_initcall(efi_load_efivars);
 #endif
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index bd7ed3c1148a..c47e0c6ec00f 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -106,7 +106,7 @@ static const struct sysfs_ops esre_attr_ops = {
 };
 
 /* Generic ESRT Entry ("ESRE") support. */
-static ssize_t esre_fw_class_show(struct esre_entry *entry, char *buf)
+static ssize_t fw_class_show(struct esre_entry *entry, char *buf)
 {
 	char *str = buf;
 
@@ -117,18 +117,16 @@ static ssize_t esre_fw_class_show(struct esre_entry *entry, char *buf)
 	return str - buf;
 }
 
-static struct esre_attribute esre_fw_class = __ATTR(fw_class, 0400,
-	esre_fw_class_show, NULL);
+static struct esre_attribute esre_fw_class = __ATTR_RO_MODE(fw_class, 0400);
 
 #define esre_attr_decl(name, size, fmt) \
-static ssize_t esre_##name##_show(struct esre_entry *entry, char *buf) \
+static ssize_t name##_show(struct esre_entry *entry, char *buf) \
 { \
 	return sprintf(buf, fmt "\n", \
 		       le##size##_to_cpu(entry->esre.esre1->name)); \
 } \
 \
-static struct esre_attribute esre_##name = __ATTR(name, 0400, \
-	esre_##name##_show, NULL)
+static struct esre_attribute esre_##name = __ATTR_RO_MODE(name, 0400)
 
 esre_attr_decl(fw_type, 32, "%u");
 esre_attr_decl(fw_version, 32, "%u");
@@ -193,14 +191,13 @@ static int esre_create_sysfs_entry(void *esre, int entry_num)
 
 /* support for displaying ESRT fields at the top level */
 #define esrt_attr_decl(name, size, fmt) \
-static ssize_t esrt_##name##_show(struct kobject *kobj, \
+static ssize_t name##_show(struct kobject *kobj, \
 				  struct kobj_attribute *attr, char *buf)\
 { \
 	return sprintf(buf, fmt "\n", le##size##_to_cpu(esrt->name)); \
 } \
 \
-static struct kobj_attribute esrt_##name = __ATTR(name, 0400, \
-	esrt_##name##_show, NULL)
+static struct kobj_attribute esrt_##name = __ATTR_RO_MODE(name, 0400)
 
 esrt_attr_decl(fw_resource_count, 32, "%u");
 esrt_attr_decl(fw_resource_count_max, 32, "%u");
@@ -431,7 +428,7 @@ err_remove_group:
 err_remove_esrt:
 	kobject_put(esrt_kobj);
 err:
-	kfree(esrt);
+	memunmap(esrt);
 	esrt = NULL;
 	return error;
 }
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index adaa4a964f0c..7b3ba40f0745 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -30,8 +30,7 @@ OBJECT_FILES_NON_STANDARD	:= y
 # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
 KCOV_INSTRUMENT			:= n
 
-lib-y				:= efi-stub-helper.o gop.o secureboot.o
-lib-$(CONFIG_RESET_ATTACK_MITIGATION) += tpm.o
+lib-y				:= efi-stub-helper.o gop.o secureboot.o tpm.o
 
 # include the stub's generic dependencies from lib/ when building for ARM/arm64
 arm-deps-y := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c fdt_empty_tree.c fdt_sw.c
diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c
index 6224cdbc9669..da661bf8cb96 100644
--- a/drivers/firmware/efi/libstub/tpm.c
+++ b/drivers/firmware/efi/libstub/tpm.c
@@ -4,15 +4,18 @@
  * Copyright (C) 2016 CoreOS, Inc
  * Copyright (C) 2017 Google, Inc.
  *     Matthew Garrett <mjg59@google.com>
+ *     Thiebaud Weksteen <tweek@google.com>
  *
  * This file is part of the Linux kernel, and is made available under the
  * terms of the GNU General Public License version 2.
  */
 #include <linux/efi.h>
+#include <linux/tpm_eventlog.h>
 #include <asm/efi.h>
 
 #include "efistub.h"
 
+#ifdef CONFIG_RESET_ATTACK_MITIGATION
 static const efi_char16_t efi_MemoryOverWriteRequest_name[] = {
 	'M', 'e', 'm', 'o', 'r', 'y', 'O', 'v', 'e', 'r', 'w', 'r', 'i', 't',
 	'e', 'R', 'e', 'q', 'u', 'e', 's', 't', 'C', 'o', 'n', 't', 'r', 'o',
@@ -56,3 +59,81 @@ void efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg)
 		    EFI_VARIABLE_BOOTSERVICE_ACCESS |
 		    EFI_VARIABLE_RUNTIME_ACCESS, sizeof(val), &val);
 }
+
+#endif
+
+void efi_retrieve_tpm2_eventlog_1_2(efi_system_table_t *sys_table_arg)
+{
+	efi_guid_t tcg2_guid = EFI_TCG2_PROTOCOL_GUID;
+	efi_guid_t linux_eventlog_guid = LINUX_EFI_TPM_EVENT_LOG_GUID;
+	efi_status_t status;
+	efi_physical_addr_t log_location, log_last_entry;
+	struct linux_efi_tpm_eventlog *log_tbl;
+	unsigned long first_entry_addr, last_entry_addr;
+	size_t log_size, last_entry_size;
+	efi_bool_t truncated;
+	void *tcg2_protocol;
+
+	status = efi_call_early(locate_protocol, &tcg2_guid, NULL,
+				&tcg2_protocol);
+	if (status != EFI_SUCCESS)
+		return;
+
+	status = efi_call_proto(efi_tcg2_protocol, get_event_log, tcg2_protocol,
+				EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2,
+				&log_location, &log_last_entry, &truncated);
+	if (status != EFI_SUCCESS)
+		return;
+
+	if (!log_location)
+		return;
+	first_entry_addr = (unsigned long) log_location;
+
+	/*
+	 * We populate the EFI table even if the logs are empty.
+	 */
+	if (!log_last_entry) {
+		log_size = 0;
+	} else {
+		last_entry_addr = (unsigned long) log_last_entry;
+		/*
+		 * get_event_log only returns the address of the last entry.
+		 * We need to calculate its size to deduce the full size of
+		 * the logs.
+		 */
+		last_entry_size = sizeof(struct tcpa_event) +
+			((struct tcpa_event *) last_entry_addr)->event_size;
+		log_size = log_last_entry - log_location + last_entry_size;
+	}
+
+	/* Allocate space for the logs and copy them. */
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				sizeof(*log_tbl) + log_size,
+				(void **) &log_tbl);
+
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table_arg,
+			   "Unable to allocate memory for event log\n");
+		return;
+	}
+
+	memset(log_tbl, 0, sizeof(*log_tbl) + log_size);
+	log_tbl->size = log_size;
+	log_tbl->version = EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2;
+	memcpy(log_tbl->log, (void *) first_entry_addr, log_size);
+
+	status = efi_call_early(install_configuration_table,
+				&linux_eventlog_guid, log_tbl);
+	if (status != EFI_SUCCESS)
+		goto err_free;
+	return;
+
+err_free:
+	efi_call_early(free_pool, log_tbl);
+}
+
+void efi_retrieve_tpm2_eventlog(efi_system_table_t *sys_table_arg)
+{
+	/* Only try to retrieve the logs in 1.2 format. */
+	efi_retrieve_tpm2_eventlog_1_2(sys_table_arg);
+}
diff --git a/drivers/firmware/efi/runtime-map.c b/drivers/firmware/efi/runtime-map.c
index 8e64b77aeac9..f377609ff141 100644
--- a/drivers/firmware/efi/runtime-map.c
+++ b/drivers/firmware/efi/runtime-map.c
@@ -63,11 +63,11 @@ static ssize_t map_attr_show(struct kobject *kobj, struct attribute *attr,
 	return map_attr->show(entry, buf);
 }
 
-static struct map_attribute map_type_attr = __ATTR_RO(type);
-static struct map_attribute map_phys_addr_attr   = __ATTR_RO(phys_addr);
-static struct map_attribute map_virt_addr_attr  = __ATTR_RO(virt_addr);
-static struct map_attribute map_num_pages_attr  = __ATTR_RO(num_pages);
-static struct map_attribute map_attribute_attr  = __ATTR_RO(attribute);
+static struct map_attribute map_type_attr = __ATTR_RO_MODE(type, 0400);
+static struct map_attribute map_phys_addr_attr = __ATTR_RO_MODE(phys_addr, 0400);
+static struct map_attribute map_virt_addr_attr = __ATTR_RO_MODE(virt_addr, 0400);
+static struct map_attribute map_num_pages_attr = __ATTR_RO_MODE(num_pages, 0400);
+static struct map_attribute map_attribute_attr = __ATTR_RO_MODE(attribute, 0400);
 
 /*
  * These are default attributes that are added for every memmap entry.
diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c
new file mode 100644
index 000000000000..0cbeb3d46b18
--- /dev/null
+++ b/drivers/firmware/efi/tpm.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright (C) 2017 Google, Inc.
+ *     Thiebaud Weksteen <tweek@google.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/memblock.h>
+
+#include <asm/early_ioremap.h>
+
+/*
+ * Reserve the memory associated with the TPM Event Log configuration table.
+ */
+int __init efi_tpm_eventlog_init(void)
+{
+	struct linux_efi_tpm_eventlog *log_tbl;
+	unsigned int tbl_size;
+
+	if (efi.tpm_log == EFI_INVALID_TABLE_ADDR)
+		return 0;
+
+	log_tbl = early_memremap(efi.tpm_log, sizeof(*log_tbl));
+	if (!log_tbl) {
+		pr_err("Failed to map TPM Event Log table @ 0x%lx\n",
+			efi.tpm_log);
+		efi.tpm_log = EFI_INVALID_TABLE_ADDR;
+		return -ENOMEM;
+	}
+
+	tbl_size = sizeof(*log_tbl) + log_tbl->size;
+	memblock_reserve(efi.tpm_log, tbl_size);
+	early_memunmap(log_tbl, sizeof(*log_tbl));
+	return 0;
+}
+
diff --git a/drivers/firmware/google/vpd.c b/drivers/firmware/google/vpd.c
index 35e553b3b190..e4b40f2b4627 100644
--- a/drivers/firmware/google/vpd.c
+++ b/drivers/firmware/google/vpd.c
@@ -295,38 +295,60 @@ static int vpd_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	return vpd_sections_init(entry.cbmem_addr);
+	vpd_kobj = kobject_create_and_add("vpd", firmware_kobj);
+	if (!vpd_kobj)
+		return -ENOMEM;
+
+	ret = vpd_sections_init(entry.cbmem_addr);
+	if (ret) {
+		kobject_put(vpd_kobj);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int vpd_remove(struct platform_device *pdev)
+{
+	vpd_section_destroy(&ro_vpd);
+	vpd_section_destroy(&rw_vpd);
+
+	kobject_put(vpd_kobj);
+
+	return 0;
 }
 
 static struct platform_driver vpd_driver = {
 	.probe = vpd_probe,
+	.remove = vpd_remove,
 	.driver = {
 		.name = "vpd",
 	},
 };
 
+static struct platform_device *vpd_pdev;
+
 static int __init vpd_platform_init(void)
 {
-	struct platform_device *pdev;
-
-	pdev = platform_device_register_simple("vpd", -1, NULL, 0);
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
+	int ret;
 
-	vpd_kobj = kobject_create_and_add("vpd", firmware_kobj);
-	if (!vpd_kobj)
-		return -ENOMEM;
+	ret = platform_driver_register(&vpd_driver);
+	if (ret)
+		return ret;
 
-	platform_driver_register(&vpd_driver);
+	vpd_pdev = platform_device_register_simple("vpd", -1, NULL, 0);
+	if (IS_ERR(vpd_pdev)) {
+		platform_driver_unregister(&vpd_driver);
+		return PTR_ERR(vpd_pdev);
+	}
 
 	return 0;
 }
 
 static void __exit vpd_platform_exit(void)
 {
-	vpd_section_destroy(&ro_vpd);
-	vpd_section_destroy(&rw_vpd);
-	kobject_put(vpd_kobj);
+	platform_device_unregister(vpd_pdev);
+	platform_driver_unregister(&vpd_driver);
 }
 
 module_init(vpd_platform_init);
diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c
index d687ca3d5049..8b25d31e8401 100644
--- a/drivers/firmware/psci.c
+++ b/drivers/firmware/psci.c
@@ -496,6 +496,8 @@ static void __init psci_init_migrate(void)
 static void __init psci_0_2_set_functions(void)
 {
 	pr_info("Using standard PSCI v0.2 function IDs\n");
+	psci_ops.get_version = psci_get_version;
+
 	psci_function_id[PSCI_FN_CPU_SUSPEND] =
 					PSCI_FN_NATIVE(0_2, CPU_SUSPEND);
 	psci_ops.cpu_suspend = psci_cpu_suspend;
diff --git a/drivers/firmware/psci_checker.c b/drivers/firmware/psci_checker.c
index f3f4f810e5df..bb1c068bff19 100644
--- a/drivers/firmware/psci_checker.c
+++ b/drivers/firmware/psci_checker.c
@@ -77,8 +77,8 @@ static int psci_ops_check(void)
 	return 0;
 }
 
-static int find_clusters(const struct cpumask *cpus,
-			 const struct cpumask **clusters)
+static int find_cpu_groups(const struct cpumask *cpus,
+			   const struct cpumask **cpu_groups)
 {
 	unsigned int nb = 0;
 	cpumask_var_t tmp;
@@ -88,11 +88,11 @@ static int find_clusters(const struct cpumask *cpus,
 	cpumask_copy(tmp, cpus);
 
 	while (!cpumask_empty(tmp)) {
-		const struct cpumask *cluster =
+		const struct cpumask *cpu_group =
 			topology_core_cpumask(cpumask_any(tmp));
 
-		clusters[nb++] = cluster;
-		cpumask_andnot(tmp, tmp, cluster);
+		cpu_groups[nb++] = cpu_group;
+		cpumask_andnot(tmp, tmp, cpu_group);
 	}
 
 	free_cpumask_var(tmp);
@@ -170,24 +170,24 @@ static int hotplug_tests(void)
 {
 	int err;
 	cpumask_var_t offlined_cpus;
-	int i, nb_cluster;
-	const struct cpumask **clusters;
+	int i, nb_cpu_group;
+	const struct cpumask **cpu_groups;
 	char *page_buf;
 
 	err = -ENOMEM;
 	if (!alloc_cpumask_var(&offlined_cpus, GFP_KERNEL))
 		return err;
-	/* We may have up to nb_available_cpus clusters. */
-	clusters = kmalloc_array(nb_available_cpus, sizeof(*clusters),
-				 GFP_KERNEL);
-	if (!clusters)
+	/* We may have up to nb_available_cpus cpu_groups. */
+	cpu_groups = kmalloc_array(nb_available_cpus, sizeof(*cpu_groups),
+				   GFP_KERNEL);
+	if (!cpu_groups)
 		goto out_free_cpus;
 	page_buf = (char *)__get_free_page(GFP_KERNEL);
 	if (!page_buf)
-		goto out_free_clusters;
+		goto out_free_cpu_groups;
 
 	err = 0;
-	nb_cluster = find_clusters(cpu_online_mask, clusters);
+	nb_cpu_group = find_cpu_groups(cpu_online_mask, cpu_groups);
 
 	/*
 	 * Of course the last CPU cannot be powered down and cpu_down() should
@@ -197,24 +197,22 @@ static int hotplug_tests(void)
 	err += down_and_up_cpus(cpu_online_mask, offlined_cpus);
 
 	/*
-	 * Take down CPUs by cluster this time. When the last CPU is turned
-	 * off, the cluster itself should shut down.
+	 * Take down CPUs by cpu group this time. When the last CPU is turned
+	 * off, the cpu group itself should shut down.
 	 */
-	for (i = 0; i < nb_cluster; ++i) {
-		int cluster_id =
-			topology_physical_package_id(cpumask_any(clusters[i]));
+	for (i = 0; i < nb_cpu_group; ++i) {
 		ssize_t len = cpumap_print_to_pagebuf(true, page_buf,
-						      clusters[i]);
+						      cpu_groups[i]);
 		/* Remove trailing newline. */
 		page_buf[len - 1] = '\0';
-		pr_info("Trying to turn off and on again cluster %d "
-			"(CPUs %s)\n", cluster_id, page_buf);
-		err += down_and_up_cpus(clusters[i], offlined_cpus);
+		pr_info("Trying to turn off and on again group %d (CPUs %s)\n",
+			i, page_buf);
+		err += down_and_up_cpus(cpu_groups[i], offlined_cpus);
 	}
 
 	free_page((unsigned long)page_buf);
-out_free_clusters:
-	kfree(clusters);
+out_free_cpu_groups:
+	kfree(cpu_groups);
 out_free_cpus:
 	free_cpumask_var(offlined_cpus);
 	return err;
diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c
index af4c75217ea6..5a7d693009ef 100644
--- a/drivers/firmware/qcom_scm.c
+++ b/drivers/firmware/qcom_scm.c
@@ -622,30 +622,6 @@ static struct platform_driver qcom_scm_driver = {
 
 static int __init qcom_scm_init(void)
 {
-	struct device_node *np, *fw_np;
-	int ret;
-
-	fw_np = of_find_node_by_name(NULL, "firmware");
-
-	if (!fw_np)
-		return -ENODEV;
-
-	np = of_find_matching_node(fw_np, qcom_scm_dt_match);
-
-	if (!np) {
-		of_node_put(fw_np);
-		return -ENODEV;
-	}
-
-	of_node_put(np);
-
-	ret = of_platform_populate(fw_np, qcom_scm_dt_match, NULL, NULL);
-
-	of_node_put(fw_np);
-
-	if (ret)
-		return ret;
-
 	return platform_driver_register(&qcom_scm_driver);
 }
 subsys_initcall(qcom_scm_init);
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 5cfe39f7a45f..deb483064f53 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -582,9 +582,10 @@ static int fw_cfg_sysfs_remove(struct platform_device *pdev)
 {
 	pr_debug("fw_cfg: unloading.\n");
 	fw_cfg_sysfs_cache_cleanup();
+	sysfs_remove_file(fw_cfg_top_ko, &fw_cfg_rev_attr.attr);
+	fw_cfg_io_cleanup();
 	fw_cfg_kset_unregister_recursive(fw_cfg_fname_kset);
 	fw_cfg_kobj_cleanup(fw_cfg_sel_ko);
-	fw_cfg_io_cleanup();
 	return 0;
 }
 
diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c
index dd506cd3a5b8..6692888f04cf 100644
--- a/drivers/firmware/raspberrypi.c
+++ b/drivers/firmware/raspberrypi.c
@@ -174,7 +174,7 @@ rpi_firmware_print_firmware_revision(struct rpi_firmware *fw)
 	if (ret == 0) {
 		struct tm tm;
 
-		time_to_tm(packet, 0, &tm);
+		time64_to_tm(packet, 0, &tm);
 
 		dev_info(fw->cl.dev,
 			 "Attached to firmware from %04ld-%02d-%02d %02d:%02d\n",
diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c
index 23b12d99ddfe..5229036dcfbf 100644
--- a/drivers/firmware/ti_sci.c
+++ b/drivers/firmware/ti_sci.c
@@ -287,13 +287,13 @@ static void ti_sci_rx_callback(struct mbox_client *cl, void *m)
 
 	/* Is the message of valid length? */
 	if (mbox_msg->len > info->desc->max_msg_size) {
-		dev_err(dev, "Unable to handle %d xfer(max %d)\n",
+		dev_err(dev, "Unable to handle %zu xfer(max %d)\n",
 			mbox_msg->len, info->desc->max_msg_size);
 		ti_sci_dump_header_dbg(dev, hdr);
 		return;
 	}
 	if (mbox_msg->len < xfer->rx_len) {
-		dev_err(dev, "Recv xfer %d < expected %d length\n",
+		dev_err(dev, "Recv xfer %zu < expected %d length\n",
 			mbox_msg->len, xfer->rx_len);
 		ti_sci_dump_header_dbg(dev, hdr);
 		return;
diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig
index ad5448f718b3..f47ef848bcd0 100644
--- a/drivers/fpga/Kconfig
+++ b/drivers/fpga/Kconfig
@@ -11,25 +11,30 @@ menuconfig FPGA
 
 if FPGA
 
-config FPGA_REGION
-	tristate "FPGA Region"
-	depends on OF && FPGA_BRIDGE
+config FPGA_MGR_SOCFPGA
+	tristate "Altera SOCFPGA FPGA Manager"
+	depends on ARCH_SOCFPGA || COMPILE_TEST
 	help
-	  FPGA Regions allow loading FPGA images under control of
-	  the Device Tree.
+	  FPGA manager driver support for Altera SOCFPGA.
 
-config FPGA_MGR_ICE40_SPI
-	tristate "Lattice iCE40 SPI"
-	depends on OF && SPI
+config FPGA_MGR_SOCFPGA_A10
+	tristate "Altera SoCFPGA Arria10"
+	depends on ARCH_SOCFPGA || COMPILE_TEST
+	select REGMAP_MMIO
 	help
-	  FPGA manager driver support for Lattice iCE40 FPGAs over SPI.
+	  FPGA manager driver support for Altera Arria10 SoCFPGA.
 
-config FPGA_MGR_ALTERA_CVP
-	tristate "Altera Arria-V/Cyclone-V/Stratix-V CvP FPGA Manager"
-	depends on PCI
+config ALTERA_PR_IP_CORE
+        tristate "Altera Partial Reconfiguration IP Core"
+        help
+          Core driver support for Altera Partial Reconfiguration IP component
+
+config ALTERA_PR_IP_CORE_PLAT
+	tristate "Platform support of Altera Partial Reconfiguration IP Core"
+	depends on ALTERA_PR_IP_CORE && OF && HAS_IOMEM
 	help
-	  FPGA manager driver support for Arria-V, Cyclone-V, Stratix-V
-	  and Arria 10 Altera FPGAs using the CvP interface over PCIe.
+	  Platform driver support for Altera Partial Reconfiguration IP
+	  component
 
 config FPGA_MGR_ALTERA_PS_SPI
 	tristate "Altera FPGA Passive Serial over SPI"
@@ -38,25 +43,19 @@ config FPGA_MGR_ALTERA_PS_SPI
 	  FPGA manager driver support for Altera Arria/Cyclone/Stratix
 	  using the passive serial interface over SPI.
 
-config FPGA_MGR_SOCFPGA
-	tristate "Altera SOCFPGA FPGA Manager"
-	depends on ARCH_SOCFPGA || COMPILE_TEST
-	help
-	  FPGA manager driver support for Altera SOCFPGA.
-
-config FPGA_MGR_SOCFPGA_A10
-	tristate "Altera SoCFPGA Arria10"
-	depends on ARCH_SOCFPGA || COMPILE_TEST
-	select REGMAP_MMIO
+config FPGA_MGR_ALTERA_CVP
+	tristate "Altera Arria-V/Cyclone-V/Stratix-V CvP FPGA Manager"
+	depends on PCI
 	help
-	  FPGA manager driver support for Altera Arria10 SoCFPGA.
+	  FPGA manager driver support for Arria-V, Cyclone-V, Stratix-V
+	  and Arria 10 Altera FPGAs using the CvP interface over PCIe.
 
-config FPGA_MGR_TS73XX
-	tristate "Technologic Systems TS-73xx SBC FPGA Manager"
-	depends on ARCH_EP93XX && MACH_TS72XX
+config FPGA_MGR_ZYNQ_FPGA
+	tristate "Xilinx Zynq FPGA"
+	depends on ARCH_ZYNQ || COMPILE_TEST
+	depends on HAS_DMA
 	help
-	  FPGA manager driver support for the Altera Cyclone II FPGA
-	  present on the TS-73xx SBC boards.
+	  FPGA manager driver support for Xilinx Zynq FPGAs.
 
 config FPGA_MGR_XILINX_SPI
 	tristate "Xilinx Configuration over Slave Serial (SPI)"
@@ -65,16 +64,21 @@ config FPGA_MGR_XILINX_SPI
 	  FPGA manager driver support for Xilinx FPGA configuration
 	  over slave serial interface.
 
-config FPGA_MGR_ZYNQ_FPGA
-	tristate "Xilinx Zynq FPGA"
-	depends on ARCH_ZYNQ || COMPILE_TEST
-	depends on HAS_DMA
+config FPGA_MGR_ICE40_SPI
+	tristate "Lattice iCE40 SPI"
+	depends on OF && SPI
 	help
-	  FPGA manager driver support for Xilinx Zynq FPGAs.
+	  FPGA manager driver support for Lattice iCE40 FPGAs over SPI.
+
+config FPGA_MGR_TS73XX
+	tristate "Technologic Systems TS-73xx SBC FPGA Manager"
+	depends on ARCH_EP93XX && MACH_TS72XX
+	help
+	  FPGA manager driver support for the Altera Cyclone II FPGA
+	  present on the TS-73xx SBC boards.
 
 config FPGA_BRIDGE
 	tristate "FPGA Bridge Framework"
-	depends on OF
 	help
 	  Say Y here if you want to support bridges connected between host
 	  processors and FPGAs or between FPGAs.
@@ -95,18 +99,6 @@ config ALTERA_FREEZE_BRIDGE
 	  isolate one region of the FPGA from the busses while that
 	  region is being reprogrammed.
 
-config ALTERA_PR_IP_CORE
-        tristate "Altera Partial Reconfiguration IP Core"
-        help
-          Core driver support for Altera Partial Reconfiguration IP component
-
-config ALTERA_PR_IP_CORE_PLAT
-	tristate "Platform support of Altera Partial Reconfiguration IP Core"
-	depends on ALTERA_PR_IP_CORE && OF && HAS_IOMEM
-	help
-	  Platform driver support for Altera Partial Reconfiguration IP
-	  component
-
 config XILINX_PR_DECOUPLER
 	tristate "Xilinx LogiCORE PR Decoupler"
 	depends on FPGA_BRIDGE
@@ -117,4 +109,19 @@ config XILINX_PR_DECOUPLER
 	  region of the FPGA from the busses while that region is
 	  being reprogrammed during partial reconfig.
 
+config FPGA_REGION
+	tristate "FPGA Region"
+	depends on FPGA_BRIDGE
+	help
+	  FPGA Region common code.  A FPGA Region controls a FPGA Manager
+	  and the FPGA Bridges associated with either a reconfigurable
+	  region of an FPGA or a whole FPGA.
+
+config OF_FPGA_REGION
+	tristate "FPGA Region Device Tree Overlay Support"
+	depends on OF && FPGA_REGION
+	help
+	  Support for loading FPGA images by applying a Device Tree
+	  overlay.
+
 endif # FPGA
diff --git a/drivers/fpga/Makefile b/drivers/fpga/Makefile
index f98dcf1d89e1..3cb276a0f88d 100644
--- a/drivers/fpga/Makefile
+++ b/drivers/fpga/Makefile
@@ -26,3 +26,4 @@ obj-$(CONFIG_XILINX_PR_DECOUPLER)	+= xilinx-pr-decoupler.o
 
 # High Level Interfaces
 obj-$(CONFIG_FPGA_REGION)		+= fpga-region.o
+obj-$(CONFIG_OF_FPGA_REGION)		+= of-fpga-region.o
diff --git a/drivers/fpga/fpga-bridge.c b/drivers/fpga/fpga-bridge.c
index 9651aa56244a..31bd2c59c305 100644
--- a/drivers/fpga/fpga-bridge.c
+++ b/drivers/fpga/fpga-bridge.c
@@ -2,6 +2,7 @@
  * FPGA Bridge Framework Driver
  *
  *  Copyright (C) 2013-2016 Altera Corporation, All Rights Reserved.
+ *  Copyright (C) 2017 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -70,32 +71,13 @@ int fpga_bridge_disable(struct fpga_bridge *bridge)
 }
 EXPORT_SYMBOL_GPL(fpga_bridge_disable);
 
-/**
- * of_fpga_bridge_get - get an exclusive reference to a fpga bridge
- *
- * @np: node pointer of a FPGA bridge
- * @info: fpga image specific information
- *
- * Return fpga_bridge struct if successful.
- * Return -EBUSY if someone already has a reference to the bridge.
- * Return -ENODEV if @np is not a FPGA Bridge.
- */
-struct fpga_bridge *of_fpga_bridge_get(struct device_node *np,
-				       struct fpga_image_info *info)
-
+static struct fpga_bridge *__fpga_bridge_get(struct device *dev,
+					     struct fpga_image_info *info)
 {
-	struct device *dev;
 	struct fpga_bridge *bridge;
 	int ret = -ENODEV;
 
-	dev = class_find_device(fpga_bridge_class, NULL, np,
-				fpga_bridge_of_node_match);
-	if (!dev)
-		goto err_dev;
-
 	bridge = to_fpga_bridge(dev);
-	if (!bridge)
-		goto err_dev;
 
 	bridge->info = info;
 
@@ -117,8 +99,58 @@ err_dev:
 	put_device(dev);
 	return ERR_PTR(ret);
 }
+
+/**
+ * of_fpga_bridge_get - get an exclusive reference to a fpga bridge
+ *
+ * @np: node pointer of a FPGA bridge
+ * @info: fpga image specific information
+ *
+ * Return fpga_bridge struct if successful.
+ * Return -EBUSY if someone already has a reference to the bridge.
+ * Return -ENODEV if @np is not a FPGA Bridge.
+ */
+struct fpga_bridge *of_fpga_bridge_get(struct device_node *np,
+				       struct fpga_image_info *info)
+{
+	struct device *dev;
+
+	dev = class_find_device(fpga_bridge_class, NULL, np,
+				fpga_bridge_of_node_match);
+	if (!dev)
+		return ERR_PTR(-ENODEV);
+
+	return __fpga_bridge_get(dev, info);
+}
 EXPORT_SYMBOL_GPL(of_fpga_bridge_get);
 
+static int fpga_bridge_dev_match(struct device *dev, const void *data)
+{
+	return dev->parent == data;
+}
+
+/**
+ * fpga_bridge_get - get an exclusive reference to a fpga bridge
+ * @dev:	parent device that fpga bridge was registered with
+ *
+ * Given a device, get an exclusive reference to a fpga bridge.
+ *
+ * Return: fpga manager struct or IS_ERR() condition containing error code.
+ */
+struct fpga_bridge *fpga_bridge_get(struct device *dev,
+				    struct fpga_image_info *info)
+{
+	struct device *bridge_dev;
+
+	bridge_dev = class_find_device(fpga_bridge_class, NULL, dev,
+				       fpga_bridge_dev_match);
+	if (!bridge_dev)
+		return ERR_PTR(-ENODEV);
+
+	return __fpga_bridge_get(bridge_dev, info);
+}
+EXPORT_SYMBOL_GPL(fpga_bridge_get);
+
 /**
  * fpga_bridge_put - release a reference to a bridge
  *
@@ -206,7 +238,7 @@ void fpga_bridges_put(struct list_head *bridge_list)
 EXPORT_SYMBOL_GPL(fpga_bridges_put);
 
 /**
- * fpga_bridges_get_to_list - get a bridge, add it to a list
+ * of_fpga_bridge_get_to_list - get a bridge, add it to a list
  *
  * @np: node pointer of a FPGA bridge
  * @info: fpga image specific information
@@ -216,14 +248,44 @@ EXPORT_SYMBOL_GPL(fpga_bridges_put);
  *
  * Return 0 for success, error code from of_fpga_bridge_get() othewise.
  */
-int fpga_bridge_get_to_list(struct device_node *np,
+int of_fpga_bridge_get_to_list(struct device_node *np,
+			       struct fpga_image_info *info,
+			       struct list_head *bridge_list)
+{
+	struct fpga_bridge *bridge;
+	unsigned long flags;
+
+	bridge = of_fpga_bridge_get(np, info);
+	if (IS_ERR(bridge))
+		return PTR_ERR(bridge);
+
+	spin_lock_irqsave(&bridge_list_lock, flags);
+	list_add(&bridge->node, bridge_list);
+	spin_unlock_irqrestore(&bridge_list_lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_fpga_bridge_get_to_list);
+
+/**
+ * fpga_bridge_get_to_list - given device, get a bridge, add it to a list
+ *
+ * @dev: FPGA bridge device
+ * @info: fpga image specific information
+ * @bridge_list: list of FPGA bridges
+ *
+ * Get an exclusive reference to the bridge and and it to the list.
+ *
+ * Return 0 for success, error code from fpga_bridge_get() othewise.
+ */
+int fpga_bridge_get_to_list(struct device *dev,
 			    struct fpga_image_info *info,
 			    struct list_head *bridge_list)
 {
 	struct fpga_bridge *bridge;
 	unsigned long flags;
 
-	bridge = of_fpga_bridge_get(np, info);
+	bridge = fpga_bridge_get(dev, info);
 	if (IS_ERR(bridge))
 		return PTR_ERR(bridge);
 
@@ -303,6 +365,7 @@ int fpga_bridge_register(struct device *dev, const char *name,
 	bridge->priv = priv;
 
 	device_initialize(&bridge->dev);
+	bridge->dev.groups = br_ops->groups;
 	bridge->dev.class = fpga_bridge_class;
 	bridge->dev.parent = dev;
 	bridge->dev.of_node = dev->of_node;
@@ -381,7 +444,7 @@ static void __exit fpga_bridge_dev_exit(void)
 }
 
 MODULE_DESCRIPTION("FPGA Bridge Driver");
-MODULE_AUTHOR("Alan Tull <atull@opensource.altera.com>");
+MODULE_AUTHOR("Alan Tull <atull@kernel.org>");
 MODULE_LICENSE("GPL v2");
 
 subsys_initcall(fpga_bridge_dev_init);
diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c
index 188ffefa3cc3..9939d2cbc9a6 100644
--- a/drivers/fpga/fpga-mgr.c
+++ b/drivers/fpga/fpga-mgr.c
@@ -2,6 +2,7 @@
  * FPGA Manager Core
  *
  *  Copyright (C) 2013-2015 Altera Corporation
+ *  Copyright (C) 2017 Intel Corporation
  *
  * With code from the mailing list:
  * Copyright (C) 2013 Xilinx, Inc.
@@ -31,6 +32,40 @@
 static DEFINE_IDA(fpga_mgr_ida);
 static struct class *fpga_mgr_class;
 
+struct fpga_image_info *fpga_image_info_alloc(struct device *dev)
+{
+	struct fpga_image_info *info;
+
+	get_device(dev);
+
+	info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		put_device(dev);
+		return NULL;
+	}
+
+	info->dev = dev;
+
+	return info;
+}
+EXPORT_SYMBOL_GPL(fpga_image_info_alloc);
+
+void fpga_image_info_free(struct fpga_image_info *info)
+{
+	struct device *dev;
+
+	if (!info)
+		return;
+
+	dev = info->dev;
+	if (info->firmware_name)
+		devm_kfree(dev, info->firmware_name);
+
+	devm_kfree(dev, info);
+	put_device(dev);
+}
+EXPORT_SYMBOL_GPL(fpga_image_info_free);
+
 /*
  * Call the low level driver's write_init function.  This will do the
  * device-specific things to get the FPGA into the state where it is ready to
@@ -137,8 +172,9 @@ static int fpga_mgr_write_complete(struct fpga_manager *mgr,
  *
  * Return: 0 on success, negative error code otherwise.
  */
-int fpga_mgr_buf_load_sg(struct fpga_manager *mgr, struct fpga_image_info *info,
-			 struct sg_table *sgt)
+static int fpga_mgr_buf_load_sg(struct fpga_manager *mgr,
+				struct fpga_image_info *info,
+				struct sg_table *sgt)
 {
 	int ret;
 
@@ -170,7 +206,6 @@ int fpga_mgr_buf_load_sg(struct fpga_manager *mgr, struct fpga_image_info *info,
 
 	return fpga_mgr_write_complete(mgr, info);
 }
-EXPORT_SYMBOL_GPL(fpga_mgr_buf_load_sg);
 
 static int fpga_mgr_buf_load_mapped(struct fpga_manager *mgr,
 				    struct fpga_image_info *info,
@@ -210,8 +245,9 @@ static int fpga_mgr_buf_load_mapped(struct fpga_manager *mgr,
  *
  * Return: 0 on success, negative error code otherwise.
  */
-int fpga_mgr_buf_load(struct fpga_manager *mgr, struct fpga_image_info *info,
-		      const char *buf, size_t count)
+static int fpga_mgr_buf_load(struct fpga_manager *mgr,
+			     struct fpga_image_info *info,
+			     const char *buf, size_t count)
 {
 	struct page **pages;
 	struct sg_table sgt;
@@ -266,7 +302,6 @@ int fpga_mgr_buf_load(struct fpga_manager *mgr, struct fpga_image_info *info,
 
 	return rc;
 }
-EXPORT_SYMBOL_GPL(fpga_mgr_buf_load);
 
 /**
  * fpga_mgr_firmware_load - request firmware and load to fpga
@@ -282,9 +317,9 @@ EXPORT_SYMBOL_GPL(fpga_mgr_buf_load);
  *
  * Return: 0 on success, negative error code otherwise.
  */
-int fpga_mgr_firmware_load(struct fpga_manager *mgr,
-			   struct fpga_image_info *info,
-			   const char *image_name)
+static int fpga_mgr_firmware_load(struct fpga_manager *mgr,
+				  struct fpga_image_info *info,
+				  const char *image_name)
 {
 	struct device *dev = &mgr->dev;
 	const struct firmware *fw;
@@ -307,7 +342,18 @@ int fpga_mgr_firmware_load(struct fpga_manager *mgr,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(fpga_mgr_firmware_load);
+
+int fpga_mgr_load(struct fpga_manager *mgr, struct fpga_image_info *info)
+{
+	if (info->sgt)
+		return fpga_mgr_buf_load_sg(mgr, info, info->sgt);
+	if (info->buf && info->count)
+		return fpga_mgr_buf_load(mgr, info, info->buf, info->count);
+	if (info->firmware_name)
+		return fpga_mgr_firmware_load(mgr, info, info->firmware_name);
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(fpga_mgr_load);
 
 static const char * const state_str[] = {
 	[FPGA_MGR_STATE_UNKNOWN] =		"unknown",
@@ -364,28 +410,17 @@ ATTRIBUTE_GROUPS(fpga_mgr);
 static struct fpga_manager *__fpga_mgr_get(struct device *dev)
 {
 	struct fpga_manager *mgr;
-	int ret = -ENODEV;
 
 	mgr = to_fpga_manager(dev);
-	if (!mgr)
-		goto err_dev;
-
-	/* Get exclusive use of fpga manager */
-	if (!mutex_trylock(&mgr->ref_mutex)) {
-		ret = -EBUSY;
-		goto err_dev;
-	}
 
 	if (!try_module_get(dev->parent->driver->owner))
-		goto err_ll_mod;
+		goto err_dev;
 
 	return mgr;
 
-err_ll_mod:
-	mutex_unlock(&mgr->ref_mutex);
 err_dev:
 	put_device(dev);
-	return ERR_PTR(ret);
+	return ERR_PTR(-ENODEV);
 }
 
 static int fpga_mgr_dev_match(struct device *dev, const void *data)
@@ -394,10 +429,10 @@ static int fpga_mgr_dev_match(struct device *dev, const void *data)
 }
 
 /**
- * fpga_mgr_get - get an exclusive reference to a fpga mgr
+ * fpga_mgr_get - get a reference to a fpga mgr
  * @dev:	parent device that fpga mgr was registered with
  *
- * Given a device, get an exclusive reference to a fpga mgr.
+ * Given a device, get a reference to a fpga mgr.
  *
  * Return: fpga manager struct or IS_ERR() condition containing error code.
  */
@@ -418,10 +453,10 @@ static int fpga_mgr_of_node_match(struct device *dev, const void *data)
 }
 
 /**
- * of_fpga_mgr_get - get an exclusive reference to a fpga mgr
+ * of_fpga_mgr_get - get a reference to a fpga mgr
  * @node:	device node
  *
- * Given a device node, get an exclusive reference to a fpga mgr.
+ * Given a device node, get a reference to a fpga mgr.
  *
  * Return: fpga manager struct or IS_ERR() condition containing error code.
  */
@@ -445,12 +480,41 @@ EXPORT_SYMBOL_GPL(of_fpga_mgr_get);
 void fpga_mgr_put(struct fpga_manager *mgr)
 {
 	module_put(mgr->dev.parent->driver->owner);
-	mutex_unlock(&mgr->ref_mutex);
 	put_device(&mgr->dev);
 }
 EXPORT_SYMBOL_GPL(fpga_mgr_put);
 
 /**
+ * fpga_mgr_lock - Lock FPGA manager for exclusive use
+ * @mgr:	fpga manager
+ *
+ * Given a pointer to FPGA Manager (from fpga_mgr_get() or
+ * of_fpga_mgr_put()) attempt to get the mutex.
+ *
+ * Return: 0 for success or -EBUSY
+ */
+int fpga_mgr_lock(struct fpga_manager *mgr)
+{
+	if (!mutex_trylock(&mgr->ref_mutex)) {
+		dev_err(&mgr->dev, "FPGA manager is in use.\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fpga_mgr_lock);
+
+/**
+ * fpga_mgr_unlock - Unlock FPGA manager
+ * @mgr:	fpga manager
+ */
+void fpga_mgr_unlock(struct fpga_manager *mgr)
+{
+	mutex_unlock(&mgr->ref_mutex);
+}
+EXPORT_SYMBOL_GPL(fpga_mgr_unlock);
+
+/**
  * fpga_mgr_register - register a low level fpga manager driver
  * @dev:	fpga manager device from pdev
  * @name:	fpga manager name
@@ -503,6 +567,7 @@ int fpga_mgr_register(struct device *dev, const char *name,
 
 	device_initialize(&mgr->dev);
 	mgr->dev.class = fpga_mgr_class;
+	mgr->dev.groups = mops->groups;
 	mgr->dev.parent = dev;
 	mgr->dev.of_node = dev->of_node;
 	mgr->dev.id = id;
@@ -578,7 +643,7 @@ static void __exit fpga_mgr_class_exit(void)
 	ida_destroy(&fpga_mgr_ida);
 }
 
-MODULE_AUTHOR("Alan Tull <atull@opensource.altera.com>");
+MODULE_AUTHOR("Alan Tull <atull@kernel.org>");
 MODULE_DESCRIPTION("FPGA manager framework");
 MODULE_LICENSE("GPL v2");
 
diff --git a/drivers/fpga/fpga-region.c b/drivers/fpga/fpga-region.c
index d9ab7c75b14f..edab2a2e03ef 100644
--- a/drivers/fpga/fpga-region.c
+++ b/drivers/fpga/fpga-region.c
@@ -2,6 +2,7 @@
  * FPGA Region - Device Tree support for FPGA programming under Linux
  *
  *  Copyright (C) 2013-2016 Altera Corporation
+ *  Copyright (C) 2017 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -18,61 +19,30 @@
 
 #include <linux/fpga/fpga-bridge.h>
 #include <linux/fpga/fpga-mgr.h>
+#include <linux/fpga/fpga-region.h>
 #include <linux/idr.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/module.h>
-#include <linux/of_platform.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
-/**
- * struct fpga_region - FPGA Region structure
- * @dev: FPGA Region device
- * @mutex: enforces exclusive reference to region
- * @bridge_list: list of FPGA bridges specified in region
- * @info: fpga image specific information
- */
-struct fpga_region {
-	struct device dev;
-	struct mutex mutex; /* for exclusive reference to region */
-	struct list_head bridge_list;
-	struct fpga_image_info *info;
-};
-
-#define to_fpga_region(d) container_of(d, struct fpga_region, dev)
-
 static DEFINE_IDA(fpga_region_ida);
 static struct class *fpga_region_class;
 
-static const struct of_device_id fpga_region_of_match[] = {
-	{ .compatible = "fpga-region", },
-	{},
-};
-MODULE_DEVICE_TABLE(of, fpga_region_of_match);
-
-static int fpga_region_of_node_match(struct device *dev, const void *data)
-{
-	return dev->of_node == data;
-}
-
-/**
- * fpga_region_find - find FPGA region
- * @np: device node of FPGA Region
- * Caller will need to put_device(&region->dev) when done.
- * Returns FPGA Region struct or NULL
- */
-static struct fpga_region *fpga_region_find(struct device_node *np)
+struct fpga_region *fpga_region_class_find(
+	struct device *start, const void *data,
+	int (*match)(struct device *, const void *))
 {
 	struct device *dev;
 
-	dev = class_find_device(fpga_region_class, NULL, np,
-				fpga_region_of_node_match);
+	dev = class_find_device(fpga_region_class, start, data, match);
 	if (!dev)
 		return NULL;
 
 	return to_fpga_region(dev);
 }
+EXPORT_SYMBOL_GPL(fpga_region_class_find);
 
 /**
  * fpga_region_get - get an exclusive reference to a fpga region
@@ -94,15 +64,13 @@ static struct fpga_region *fpga_region_get(struct fpga_region *region)
 	}
 
 	get_device(dev);
-	of_node_get(dev->of_node);
 	if (!try_module_get(dev->parent->driver->owner)) {
-		of_node_put(dev->of_node);
 		put_device(dev);
 		mutex_unlock(&region->mutex);
 		return ERR_PTR(-ENODEV);
 	}
 
-	dev_dbg(&region->dev, "get\n");
+	dev_dbg(dev, "get\n");
 
 	return region;
 }
@@ -116,403 +84,99 @@ static void fpga_region_put(struct fpga_region *region)
 {
 	struct device *dev = &region->dev;
 
-	dev_dbg(&region->dev, "put\n");
+	dev_dbg(dev, "put\n");
 
 	module_put(dev->parent->driver->owner);
-	of_node_put(dev->of_node);
 	put_device(dev);
 	mutex_unlock(&region->mutex);
 }
 
 /**
- * fpga_region_get_manager - get exclusive reference for FPGA manager
- * @region: FPGA region
- *
- * Get FPGA Manager from "fpga-mgr" property or from ancestor region.
- *
- * Caller should call fpga_mgr_put() when done with manager.
- *
- * Return: fpga manager struct or IS_ERR() condition containing error code.
- */
-static struct fpga_manager *fpga_region_get_manager(struct fpga_region *region)
-{
-	struct device *dev = &region->dev;
-	struct device_node *np = dev->of_node;
-	struct device_node  *mgr_node;
-	struct fpga_manager *mgr;
-
-	of_node_get(np);
-	while (np) {
-		if (of_device_is_compatible(np, "fpga-region")) {
-			mgr_node = of_parse_phandle(np, "fpga-mgr", 0);
-			if (mgr_node) {
-				mgr = of_fpga_mgr_get(mgr_node);
-				of_node_put(np);
-				return mgr;
-			}
-		}
-		np = of_get_next_parent(np);
-	}
-	of_node_put(np);
-
-	return ERR_PTR(-EINVAL);
-}
-
-/**
- * fpga_region_get_bridges - create a list of bridges
- * @region: FPGA region
- * @overlay: device node of the overlay
- *
- * Create a list of bridges including the parent bridge and the bridges
- * specified by "fpga-bridges" property.  Note that the
- * fpga_bridges_enable/disable/put functions are all fine with an empty list
- * if that happens.
- *
- * Caller should call fpga_bridges_put(&region->bridge_list) when
- * done with the bridges.
- *
- * Return 0 for success (even if there are no bridges specified)
- * or -EBUSY if any of the bridges are in use.
- */
-static int fpga_region_get_bridges(struct fpga_region *region,
-				   struct device_node *overlay)
-{
-	struct device *dev = &region->dev;
-	struct device_node *region_np = dev->of_node;
-	struct device_node *br, *np, *parent_br = NULL;
-	int i, ret;
-
-	/* If parent is a bridge, add to list */
-	ret = fpga_bridge_get_to_list(region_np->parent, region->info,
-				      &region->bridge_list);
-	if (ret == -EBUSY)
-		return ret;
-
-	if (!ret)
-		parent_br = region_np->parent;
-
-	/* If overlay has a list of bridges, use it. */
-	if (of_parse_phandle(overlay, "fpga-bridges", 0))
-		np = overlay;
-	else
-		np = region_np;
-
-	for (i = 0; ; i++) {
-		br = of_parse_phandle(np, "fpga-bridges", i);
-		if (!br)
-			break;
-
-		/* If parent bridge is in list, skip it. */
-		if (br == parent_br)
-			continue;
-
-		/* If node is a bridge, get it and add to list */
-		ret = fpga_bridge_get_to_list(br, region->info,
-					      &region->bridge_list);
-
-		/* If any of the bridges are in use, give up */
-		if (ret == -EBUSY) {
-			fpga_bridges_put(&region->bridge_list);
-			return -EBUSY;
-		}
-	}
-
-	return 0;
-}
-
-/**
  * fpga_region_program_fpga - program FPGA
  * @region: FPGA region
- * @firmware_name: name of FPGA image firmware file
- * @overlay: device node of the overlay
- * Program an FPGA using information in the device tree.
- * Function assumes that there is a firmware-name property.
+ * Program an FPGA using fpga image info (region->info).
  * Return 0 for success or negative error code.
  */
-static int fpga_region_program_fpga(struct fpga_region *region,
-				    const char *firmware_name,
-				    struct device_node *overlay)
+int fpga_region_program_fpga(struct fpga_region *region)
 {
-	struct fpga_manager *mgr;
+	struct device *dev = &region->dev;
+	struct fpga_image_info *info = region->info;
 	int ret;
 
 	region = fpga_region_get(region);
 	if (IS_ERR(region)) {
-		pr_err("failed to get fpga region\n");
+		dev_err(dev, "failed to get FPGA region\n");
 		return PTR_ERR(region);
 	}
 
-	mgr = fpga_region_get_manager(region);
-	if (IS_ERR(mgr)) {
-		pr_err("failed to get fpga region manager\n");
-		ret = PTR_ERR(mgr);
+	ret = fpga_mgr_lock(region->mgr);
+	if (ret) {
+		dev_err(dev, "FPGA manager is busy\n");
 		goto err_put_region;
 	}
 
-	ret = fpga_region_get_bridges(region, overlay);
-	if (ret) {
-		pr_err("failed to get fpga region bridges\n");
-		goto err_put_mgr;
+	/*
+	 * In some cases, we already have a list of bridges in the
+	 * fpga region struct.  Or we don't have any bridges.
+	 */
+	if (region->get_bridges) {
+		ret = region->get_bridges(region);
+		if (ret) {
+			dev_err(dev, "failed to get fpga region bridges\n");
+			goto err_unlock_mgr;
+		}
 	}
 
 	ret = fpga_bridges_disable(&region->bridge_list);
 	if (ret) {
-		pr_err("failed to disable region bridges\n");
+		dev_err(dev, "failed to disable bridges\n");
 		goto err_put_br;
 	}
 
-	ret = fpga_mgr_firmware_load(mgr, region->info, firmware_name);
+	ret = fpga_mgr_load(region->mgr, info);
 	if (ret) {
-		pr_err("failed to load fpga image\n");
+		dev_err(dev, "failed to load FPGA image\n");
 		goto err_put_br;
 	}
 
 	ret = fpga_bridges_enable(&region->bridge_list);
 	if (ret) {
-		pr_err("failed to enable region bridges\n");
+		dev_err(dev, "failed to enable region bridges\n");
 		goto err_put_br;
 	}
 
-	fpga_mgr_put(mgr);
+	fpga_mgr_unlock(region->mgr);
 	fpga_region_put(region);
 
 	return 0;
 
 err_put_br:
-	fpga_bridges_put(&region->bridge_list);
-err_put_mgr:
-	fpga_mgr_put(mgr);
+	if (region->get_bridges)
+		fpga_bridges_put(&region->bridge_list);
+err_unlock_mgr:
+	fpga_mgr_unlock(region->mgr);
 err_put_region:
 	fpga_region_put(region);
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(fpga_region_program_fpga);
 
-/**
- * child_regions_with_firmware
- * @overlay: device node of the overlay
- *
- * If the overlay adds child FPGA regions, they are not allowed to have
- * firmware-name property.
- *
- * Return 0 for OK or -EINVAL if child FPGA region adds firmware-name.
- */
-static int child_regions_with_firmware(struct device_node *overlay)
-{
-	struct device_node *child_region;
-	const char *child_firmware_name;
-	int ret = 0;
-
-	of_node_get(overlay);
-
-	child_region = of_find_matching_node(overlay, fpga_region_of_match);
-	while (child_region) {
-		if (!of_property_read_string(child_region, "firmware-name",
-					     &child_firmware_name)) {
-			ret = -EINVAL;
-			break;
-		}
-		child_region = of_find_matching_node(child_region,
-						     fpga_region_of_match);
-	}
-
-	of_node_put(child_region);
-
-	if (ret)
-		pr_err("firmware-name not allowed in child FPGA region: %pOF",
-		       child_region);
-
-	return ret;
-}
-
-/**
- * fpga_region_notify_pre_apply - pre-apply overlay notification
- *
- * @region: FPGA region that the overlay was applied to
- * @nd: overlay notification data
- *
- * Called after when an overlay targeted to a FPGA Region is about to be
- * applied.  Function will check the properties that will be added to the FPGA
- * region.  If the checks pass, it will program the FPGA.
- *
- * The checks are:
- * The overlay must add either firmware-name or external-fpga-config property
- * to the FPGA Region.
- *
- *   firmware-name         : program the FPGA
- *   external-fpga-config  : FPGA is already programmed
- *   encrypted-fpga-config : FPGA bitstream is encrypted
- *
- * The overlay can add other FPGA regions, but child FPGA regions cannot have a
- * firmware-name property since those regions don't exist yet.
- *
- * If the overlay that breaks the rules, notifier returns an error and the
- * overlay is rejected before it goes into the main tree.
- *
- * Returns 0 for success or negative error code for failure.
- */
-static int fpga_region_notify_pre_apply(struct fpga_region *region,
-					struct of_overlay_notify_data *nd)
+int fpga_region_register(struct device *dev, struct fpga_region *region)
 {
-	const char *firmware_name = NULL;
-	struct fpga_image_info *info;
-	int ret;
-
-	info = devm_kzalloc(&region->dev, sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	region->info = info;
-
-	/* Reject overlay if child FPGA Regions have firmware-name property */
-	ret = child_regions_with_firmware(nd->overlay);
-	if (ret)
-		return ret;
-
-	/* Read FPGA region properties from the overlay */
-	if (of_property_read_bool(nd->overlay, "partial-fpga-config"))
-		info->flags |= FPGA_MGR_PARTIAL_RECONFIG;
-
-	if (of_property_read_bool(nd->overlay, "external-fpga-config"))
-		info->flags |= FPGA_MGR_EXTERNAL_CONFIG;
-
-	if (of_property_read_bool(nd->overlay, "encrypted-fpga-config"))
-		info->flags |= FPGA_MGR_ENCRYPTED_BITSTREAM;
-
-	of_property_read_string(nd->overlay, "firmware-name", &firmware_name);
-
-	of_property_read_u32(nd->overlay, "region-unfreeze-timeout-us",
-			     &info->enable_timeout_us);
-
-	of_property_read_u32(nd->overlay, "region-freeze-timeout-us",
-			     &info->disable_timeout_us);
-
-	of_property_read_u32(nd->overlay, "config-complete-timeout-us",
-			     &info->config_complete_timeout_us);
-
-	/* If FPGA was externally programmed, don't specify firmware */
-	if ((info->flags & FPGA_MGR_EXTERNAL_CONFIG) && firmware_name) {
-		pr_err("error: specified firmware and external-fpga-config");
-		return -EINVAL;
-	}
-
-	/* FPGA is already configured externally.  We're done. */
-	if (info->flags & FPGA_MGR_EXTERNAL_CONFIG)
-		return 0;
-
-	/* If we got this far, we should be programming the FPGA */
-	if (!firmware_name) {
-		pr_err("should specify firmware-name or external-fpga-config\n");
-		return -EINVAL;
-	}
-
-	return fpga_region_program_fpga(region, firmware_name, nd->overlay);
-}
-
-/**
- * fpga_region_notify_post_remove - post-remove overlay notification
- *
- * @region: FPGA region that was targeted by the overlay that was removed
- * @nd: overlay notification data
- *
- * Called after an overlay has been removed if the overlay's target was a
- * FPGA region.
- */
-static void fpga_region_notify_post_remove(struct fpga_region *region,
-					   struct of_overlay_notify_data *nd)
-{
-	fpga_bridges_disable(&region->bridge_list);
-	fpga_bridges_put(&region->bridge_list);
-	devm_kfree(&region->dev, region->info);
-	region->info = NULL;
-}
-
-/**
- * of_fpga_region_notify - reconfig notifier for dynamic DT changes
- * @nb:		notifier block
- * @action:	notifier action
- * @arg:	reconfig data
- *
- * This notifier handles programming a FPGA when a "firmware-name" property is
- * added to a fpga-region.
- *
- * Returns NOTIFY_OK or error if FPGA programming fails.
- */
-static int of_fpga_region_notify(struct notifier_block *nb,
-				 unsigned long action, void *arg)
-{
-	struct of_overlay_notify_data *nd = arg;
-	struct fpga_region *region;
-	int ret;
-
-	switch (action) {
-	case OF_OVERLAY_PRE_APPLY:
-		pr_debug("%s OF_OVERLAY_PRE_APPLY\n", __func__);
-		break;
-	case OF_OVERLAY_POST_APPLY:
-		pr_debug("%s OF_OVERLAY_POST_APPLY\n", __func__);
-		return NOTIFY_OK;       /* not for us */
-	case OF_OVERLAY_PRE_REMOVE:
-		pr_debug("%s OF_OVERLAY_PRE_REMOVE\n", __func__);
-		return NOTIFY_OK;       /* not for us */
-	case OF_OVERLAY_POST_REMOVE:
-		pr_debug("%s OF_OVERLAY_POST_REMOVE\n", __func__);
-		break;
-	default:			/* should not happen */
-		return NOTIFY_OK;
-	}
-
-	region = fpga_region_find(nd->target);
-	if (!region)
-		return NOTIFY_OK;
-
-	ret = 0;
-	switch (action) {
-	case OF_OVERLAY_PRE_APPLY:
-		ret = fpga_region_notify_pre_apply(region, nd);
-		break;
-
-	case OF_OVERLAY_POST_REMOVE:
-		fpga_region_notify_post_remove(region, nd);
-		break;
-	}
-
-	put_device(&region->dev);
-
-	if (ret)
-		return notifier_from_errno(ret);
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block fpga_region_of_nb = {
-	.notifier_call = of_fpga_region_notify,
-};
-
-static int fpga_region_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct device_node *np = dev->of_node;
-	struct fpga_region *region;
 	int id, ret = 0;
 
-	region = kzalloc(sizeof(*region), GFP_KERNEL);
-	if (!region)
-		return -ENOMEM;
-
 	id = ida_simple_get(&fpga_region_ida, 0, 0, GFP_KERNEL);
-	if (id < 0) {
-		ret = id;
-		goto err_kfree;
-	}
+	if (id < 0)
+		return id;
 
 	mutex_init(&region->mutex);
 	INIT_LIST_HEAD(&region->bridge_list);
-
 	device_initialize(&region->dev);
+	region->dev.groups = region->groups;
 	region->dev.class = fpga_region_class;
 	region->dev.parent = dev;
-	region->dev.of_node = np;
+	region->dev.of_node = dev->of_node;
 	region->dev.id = id;
 	dev_set_drvdata(dev, region);
 
@@ -524,44 +188,27 @@ static int fpga_region_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_remove;
 
-	of_platform_populate(np, fpga_region_of_match, NULL, &region->dev);
-
-	dev_info(dev, "FPGA Region probed\n");
-
 	return 0;
 
 err_remove:
 	ida_simple_remove(&fpga_region_ida, id);
-err_kfree:
-	kfree(region);
-
 	return ret;
 }
+EXPORT_SYMBOL_GPL(fpga_region_register);
 
-static int fpga_region_remove(struct platform_device *pdev)
+int fpga_region_unregister(struct fpga_region *region)
 {
-	struct fpga_region *region = platform_get_drvdata(pdev);
-
 	device_unregister(&region->dev);
 
 	return 0;
 }
-
-static struct platform_driver fpga_region_driver = {
-	.probe = fpga_region_probe,
-	.remove = fpga_region_remove,
-	.driver = {
-		.name	= "fpga-region",
-		.of_match_table = of_match_ptr(fpga_region_of_match),
-	},
-};
+EXPORT_SYMBOL_GPL(fpga_region_unregister);
 
 static void fpga_region_dev_release(struct device *dev)
 {
 	struct fpga_region *region = to_fpga_region(dev);
 
 	ida_simple_remove(&fpga_region_ida, region->dev.id);
-	kfree(region);
 }
 
 /**
@@ -570,36 +217,17 @@ static void fpga_region_dev_release(struct device *dev)
  */
 static int __init fpga_region_init(void)
 {
-	int ret;
-
 	fpga_region_class = class_create(THIS_MODULE, "fpga_region");
 	if (IS_ERR(fpga_region_class))
 		return PTR_ERR(fpga_region_class);
 
 	fpga_region_class->dev_release = fpga_region_dev_release;
 
-	ret = of_overlay_notifier_register(&fpga_region_of_nb);
-	if (ret)
-		goto err_class;
-
-	ret = platform_driver_register(&fpga_region_driver);
-	if (ret)
-		goto err_plat;
-
 	return 0;
-
-err_plat:
-	of_overlay_notifier_unregister(&fpga_region_of_nb);
-err_class:
-	class_destroy(fpga_region_class);
-	ida_destroy(&fpga_region_ida);
-	return ret;
 }
 
 static void __exit fpga_region_exit(void)
 {
-	platform_driver_unregister(&fpga_region_driver);
-	of_overlay_notifier_unregister(&fpga_region_of_nb);
 	class_destroy(fpga_region_class);
 	ida_destroy(&fpga_region_ida);
 }
@@ -608,5 +236,5 @@ subsys_initcall(fpga_region_init);
 module_exit(fpga_region_exit);
 
 MODULE_DESCRIPTION("FPGA Region");
-MODULE_AUTHOR("Alan Tull <atull@opensource.altera.com>");
+MODULE_AUTHOR("Alan Tull <atull@kernel.org>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/fpga/of-fpga-region.c b/drivers/fpga/of-fpga-region.c
new file mode 100644
index 000000000000..119ff75522f1
--- /dev/null
+++ b/drivers/fpga/of-fpga-region.c
@@ -0,0 +1,504 @@
+/*
+ * FPGA Region - Device Tree support for FPGA programming under Linux
+ *
+ *  Copyright (C) 2013-2016 Altera Corporation
+ *  Copyright (C) 2017 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/fpga/fpga-bridge.h>
+#include <linux/fpga/fpga-mgr.h>
+#include <linux/fpga/fpga-region.h>
+#include <linux/idr.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+static const struct of_device_id fpga_region_of_match[] = {
+	{ .compatible = "fpga-region", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, fpga_region_of_match);
+
+static int fpga_region_of_node_match(struct device *dev, const void *data)
+{
+	return dev->of_node == data;
+}
+
+/**
+ * of_fpga_region_find - find FPGA region
+ * @np: device node of FPGA Region
+ *
+ * Caller will need to put_device(&region->dev) when done.
+ *
+ * Returns FPGA Region struct or NULL
+ */
+static struct fpga_region *of_fpga_region_find(struct device_node *np)
+{
+	return fpga_region_class_find(NULL, np, fpga_region_of_node_match);
+}
+
+/**
+ * of_fpga_region_get_mgr - get reference for FPGA manager
+ * @np: device node of FPGA region
+ *
+ * Get FPGA Manager from "fpga-mgr" property or from ancestor region.
+ *
+ * Caller should call fpga_mgr_put() when done with manager.
+ *
+ * Return: fpga manager struct or IS_ERR() condition containing error code.
+ */
+static struct fpga_manager *of_fpga_region_get_mgr(struct device_node *np)
+{
+	struct device_node  *mgr_node;
+	struct fpga_manager *mgr;
+
+	of_node_get(np);
+	while (np) {
+		if (of_device_is_compatible(np, "fpga-region")) {
+			mgr_node = of_parse_phandle(np, "fpga-mgr", 0);
+			if (mgr_node) {
+				mgr = of_fpga_mgr_get(mgr_node);
+				of_node_put(mgr_node);
+				of_node_put(np);
+				return mgr;
+			}
+		}
+		np = of_get_next_parent(np);
+	}
+	of_node_put(np);
+
+	return ERR_PTR(-EINVAL);
+}
+
+/**
+ * of_fpga_region_get_bridges - create a list of bridges
+ * @region: FPGA region
+ *
+ * Create a list of bridges including the parent bridge and the bridges
+ * specified by "fpga-bridges" property.  Note that the
+ * fpga_bridges_enable/disable/put functions are all fine with an empty list
+ * if that happens.
+ *
+ * Caller should call fpga_bridges_put(&region->bridge_list) when
+ * done with the bridges.
+ *
+ * Return 0 for success (even if there are no bridges specified)
+ * or -EBUSY if any of the bridges are in use.
+ */
+static int of_fpga_region_get_bridges(struct fpga_region *region)
+{
+	struct device *dev = &region->dev;
+	struct device_node *region_np = dev->of_node;
+	struct fpga_image_info *info = region->info;
+	struct device_node *br, *np, *parent_br = NULL;
+	int i, ret;
+
+	/* If parent is a bridge, add to list */
+	ret = of_fpga_bridge_get_to_list(region_np->parent, info,
+					 &region->bridge_list);
+
+	/* -EBUSY means parent is a bridge that is under use. Give up. */
+	if (ret == -EBUSY)
+		return ret;
+
+	/* Zero return code means parent was a bridge and was added to list. */
+	if (!ret)
+		parent_br = region_np->parent;
+
+	/* If overlay has a list of bridges, use it. */
+	br = of_parse_phandle(info->overlay, "fpga-bridges", 0);
+	if (br) {
+		of_node_put(br);
+		np = info->overlay;
+	} else {
+		np = region_np;
+	}
+
+	for (i = 0; ; i++) {
+		br = of_parse_phandle(np, "fpga-bridges", i);
+		if (!br)
+			break;
+
+		/* If parent bridge is in list, skip it. */
+		if (br == parent_br) {
+			of_node_put(br);
+			continue;
+		}
+
+		/* If node is a bridge, get it and add to list */
+		ret = of_fpga_bridge_get_to_list(br, info,
+						 &region->bridge_list);
+		of_node_put(br);
+
+		/* If any of the bridges are in use, give up */
+		if (ret == -EBUSY) {
+			fpga_bridges_put(&region->bridge_list);
+			return -EBUSY;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * child_regions_with_firmware
+ * @overlay: device node of the overlay
+ *
+ * If the overlay adds child FPGA regions, they are not allowed to have
+ * firmware-name property.
+ *
+ * Return 0 for OK or -EINVAL if child FPGA region adds firmware-name.
+ */
+static int child_regions_with_firmware(struct device_node *overlay)
+{
+	struct device_node *child_region;
+	const char *child_firmware_name;
+	int ret = 0;
+
+	of_node_get(overlay);
+
+	child_region = of_find_matching_node(overlay, fpga_region_of_match);
+	while (child_region) {
+		if (!of_property_read_string(child_region, "firmware-name",
+					     &child_firmware_name)) {
+			ret = -EINVAL;
+			break;
+		}
+		child_region = of_find_matching_node(child_region,
+						     fpga_region_of_match);
+	}
+
+	of_node_put(child_region);
+
+	if (ret)
+		pr_err("firmware-name not allowed in child FPGA region: %pOF",
+		       child_region);
+
+	return ret;
+}
+
+/**
+ * of_fpga_region_parse_ov - parse and check overlay applied to region
+ *
+ * @region: FPGA region
+ * @overlay: overlay applied to the FPGA region
+ *
+ * Given an overlay applied to a FPGA region, parse the FPGA image specific
+ * info in the overlay and do some checking.
+ *
+ * Returns:
+ *   NULL if overlay doesn't direct us to program the FPGA.
+ *   fpga_image_info struct if there is an image to program.
+ *   error code for invalid overlay.
+ */
+static struct fpga_image_info *of_fpga_region_parse_ov(
+						struct fpga_region *region,
+						struct device_node *overlay)
+{
+	struct device *dev = &region->dev;
+	struct fpga_image_info *info;
+	const char *firmware_name;
+	int ret;
+
+	if (region->info) {
+		dev_err(dev, "Region already has overlay applied.\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Reject overlay if child FPGA Regions added in the overlay have
+	 * firmware-name property (would mean that an FPGA region that has
+	 * not been added to the live tree yet is doing FPGA programming).
+	 */
+	ret = child_regions_with_firmware(overlay);
+	if (ret)
+		return ERR_PTR(ret);
+
+	info = fpga_image_info_alloc(dev);
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	info->overlay = overlay;
+
+	/* Read FPGA region properties from the overlay */
+	if (of_property_read_bool(overlay, "partial-fpga-config"))
+		info->flags |= FPGA_MGR_PARTIAL_RECONFIG;
+
+	if (of_property_read_bool(overlay, "external-fpga-config"))
+		info->flags |= FPGA_MGR_EXTERNAL_CONFIG;
+
+	if (of_property_read_bool(overlay, "encrypted-fpga-config"))
+		info->flags |= FPGA_MGR_ENCRYPTED_BITSTREAM;
+
+	if (!of_property_read_string(overlay, "firmware-name",
+				     &firmware_name)) {
+		info->firmware_name = devm_kstrdup(dev, firmware_name,
+						   GFP_KERNEL);
+		if (!info->firmware_name)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	of_property_read_u32(overlay, "region-unfreeze-timeout-us",
+			     &info->enable_timeout_us);
+
+	of_property_read_u32(overlay, "region-freeze-timeout-us",
+			     &info->disable_timeout_us);
+
+	of_property_read_u32(overlay, "config-complete-timeout-us",
+			     &info->config_complete_timeout_us);
+
+	/* If overlay is not programming the FPGA, don't need FPGA image info */
+	if (!info->firmware_name) {
+		ret = 0;
+		goto ret_no_info;
+	}
+
+	/*
+	 * If overlay informs us FPGA was externally programmed, specifying
+	 * firmware here would be ambiguous.
+	 */
+	if (info->flags & FPGA_MGR_EXTERNAL_CONFIG) {
+		dev_err(dev, "error: specified firmware and external-fpga-config");
+		ret = -EINVAL;
+		goto ret_no_info;
+	}
+
+	return info;
+ret_no_info:
+	fpga_image_info_free(info);
+	return ERR_PTR(ret);
+}
+
+/**
+ * of_fpga_region_notify_pre_apply - pre-apply overlay notification
+ *
+ * @region: FPGA region that the overlay was applied to
+ * @nd: overlay notification data
+ *
+ * Called when an overlay targeted to a FPGA Region is about to be applied.
+ * Parses the overlay for properties that influence how the FPGA will be
+ * programmed and does some checking. If the checks pass, programs the FPGA.
+ * If the checks fail, overlay is rejected and does not get added to the
+ * live tree.
+ *
+ * Returns 0 for success or negative error code for failure.
+ */
+static int of_fpga_region_notify_pre_apply(struct fpga_region *region,
+					   struct of_overlay_notify_data *nd)
+{
+	struct device *dev = &region->dev;
+	struct fpga_image_info *info;
+	int ret;
+
+	info = of_fpga_region_parse_ov(region, nd->overlay);
+	if (IS_ERR(info))
+		return PTR_ERR(info);
+
+	/* If overlay doesn't program the FPGA, accept it anyway. */
+	if (!info)
+		return 0;
+
+	if (region->info) {
+		dev_err(dev, "Region already has overlay applied.\n");
+		return -EINVAL;
+	}
+
+	region->info = info;
+	ret = fpga_region_program_fpga(region);
+	if (ret) {
+		/* error; reject overlay */
+		fpga_image_info_free(info);
+		region->info = NULL;
+	}
+
+	return ret;
+}
+
+/**
+ * of_fpga_region_notify_post_remove - post-remove overlay notification
+ *
+ * @region: FPGA region that was targeted by the overlay that was removed
+ * @nd: overlay notification data
+ *
+ * Called after an overlay has been removed if the overlay's target was a
+ * FPGA region.
+ */
+static void of_fpga_region_notify_post_remove(struct fpga_region *region,
+					      struct of_overlay_notify_data *nd)
+{
+	fpga_bridges_disable(&region->bridge_list);
+	fpga_bridges_put(&region->bridge_list);
+	fpga_image_info_free(region->info);
+	region->info = NULL;
+}
+
+/**
+ * of_fpga_region_notify - reconfig notifier for dynamic DT changes
+ * @nb:		notifier block
+ * @action:	notifier action
+ * @arg:	reconfig data
+ *
+ * This notifier handles programming a FPGA when a "firmware-name" property is
+ * added to a fpga-region.
+ *
+ * Returns NOTIFY_OK or error if FPGA programming fails.
+ */
+static int of_fpga_region_notify(struct notifier_block *nb,
+				 unsigned long action, void *arg)
+{
+	struct of_overlay_notify_data *nd = arg;
+	struct fpga_region *region;
+	int ret;
+
+	switch (action) {
+	case OF_OVERLAY_PRE_APPLY:
+		pr_debug("%s OF_OVERLAY_PRE_APPLY\n", __func__);
+		break;
+	case OF_OVERLAY_POST_APPLY:
+		pr_debug("%s OF_OVERLAY_POST_APPLY\n", __func__);
+		return NOTIFY_OK;       /* not for us */
+	case OF_OVERLAY_PRE_REMOVE:
+		pr_debug("%s OF_OVERLAY_PRE_REMOVE\n", __func__);
+		return NOTIFY_OK;       /* not for us */
+	case OF_OVERLAY_POST_REMOVE:
+		pr_debug("%s OF_OVERLAY_POST_REMOVE\n", __func__);
+		break;
+	default:			/* should not happen */
+		return NOTIFY_OK;
+	}
+
+	region = of_fpga_region_find(nd->target);
+	if (!region)
+		return NOTIFY_OK;
+
+	ret = 0;
+	switch (action) {
+	case OF_OVERLAY_PRE_APPLY:
+		ret = of_fpga_region_notify_pre_apply(region, nd);
+		break;
+
+	case OF_OVERLAY_POST_REMOVE:
+		of_fpga_region_notify_post_remove(region, nd);
+		break;
+	}
+
+	put_device(&region->dev);
+
+	if (ret)
+		return notifier_from_errno(ret);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block fpga_region_of_nb = {
+	.notifier_call = of_fpga_region_notify,
+};
+
+static int of_fpga_region_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct fpga_region *region;
+	struct fpga_manager *mgr;
+	int ret;
+
+	/* Find the FPGA mgr specified by region or parent region. */
+	mgr = of_fpga_region_get_mgr(np);
+	if (IS_ERR(mgr))
+		return -EPROBE_DEFER;
+
+	region = devm_kzalloc(dev, sizeof(*region), GFP_KERNEL);
+	if (!region) {
+		ret = -ENOMEM;
+		goto eprobe_mgr_put;
+	}
+
+	region->mgr = mgr;
+
+	/* Specify how to get bridges for this type of region. */
+	region->get_bridges = of_fpga_region_get_bridges;
+
+	ret = fpga_region_register(dev, region);
+	if (ret)
+		goto eprobe_mgr_put;
+
+	of_platform_populate(np, fpga_region_of_match, NULL, &region->dev);
+
+	dev_info(dev, "FPGA Region probed\n");
+
+	return 0;
+
+eprobe_mgr_put:
+	fpga_mgr_put(mgr);
+	return ret;
+}
+
+static int of_fpga_region_remove(struct platform_device *pdev)
+{
+	struct fpga_region *region = platform_get_drvdata(pdev);
+
+	fpga_region_unregister(region);
+	fpga_mgr_put(region->mgr);
+
+	return 0;
+}
+
+static struct platform_driver of_fpga_region_driver = {
+	.probe = of_fpga_region_probe,
+	.remove = of_fpga_region_remove,
+	.driver = {
+		.name	= "of-fpga-region",
+		.of_match_table = of_match_ptr(fpga_region_of_match),
+	},
+};
+
+/**
+ * fpga_region_init - init function for fpga_region class
+ * Creates the fpga_region class and registers a reconfig notifier.
+ */
+static int __init of_fpga_region_init(void)
+{
+	int ret;
+
+	ret = of_overlay_notifier_register(&fpga_region_of_nb);
+	if (ret)
+		return ret;
+
+	ret = platform_driver_register(&of_fpga_region_driver);
+	if (ret)
+		goto err_plat;
+
+	return 0;
+
+err_plat:
+	of_overlay_notifier_unregister(&fpga_region_of_nb);
+	return ret;
+}
+
+static void __exit of_fpga_region_exit(void)
+{
+	platform_driver_unregister(&of_fpga_region_driver);
+	of_overlay_notifier_unregister(&fpga_region_of_nb);
+}
+
+subsys_initcall(of_fpga_region_init);
+module_exit(of_fpga_region_exit);
+
+MODULE_DESCRIPTION("FPGA Region");
+MODULE_AUTHOR("Alan Tull <atull@kernel.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/fpga/socfpga-a10.c b/drivers/fpga/socfpga-a10.c
index f8770af0f6b5..a46e343a5b72 100644
--- a/drivers/fpga/socfpga-a10.c
+++ b/drivers/fpga/socfpga-a10.c
@@ -519,8 +519,14 @@ static int socfpga_a10_fpga_probe(struct platform_device *pdev)
 		return -EBUSY;
 	}
 
-	return fpga_mgr_register(dev, "SoCFPGA Arria10 FPGA Manager",
+	ret = fpga_mgr_register(dev, "SoCFPGA Arria10 FPGA Manager",
 				 &socfpga_a10_fpga_mgr_ops, priv);
+	if (ret) {
+		clk_disable_unprepare(priv->clk);
+		return ret;
+	}
+
+	return 0;
 }
 
 static int socfpga_a10_fpga_remove(struct platform_device *pdev)
diff --git a/drivers/fsi/Kconfig b/drivers/fsi/Kconfig
index 6821ed0cd5e8..513e35173aaa 100644
--- a/drivers/fsi/Kconfig
+++ b/drivers/fsi/Kconfig
@@ -2,9 +2,7 @@
 # FSI subsystem
 #
 
-menu "FSI support"
-
-config FSI
+menuconfig FSI
 	tristate "FSI support"
 	select CRC4
 	---help---
@@ -34,5 +32,3 @@ config FSI_SCOM
 	This option enables an FSI based SCOM device driver.
 
 endif
-
-endmenu
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index d6a8e851ad13..8dbb2280538d 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -122,12 +122,6 @@ config GPIO_ATH79
 	  Select this option to enable GPIO driver for
 	  Atheros AR71XX/AR724X/AR913X SoC devices.
 
-config GPIO_AXP209
-	tristate "X-Powers AXP209 PMIC GPIO Support"
-	depends on MFD_AXP20X
-	help
-	  Say yes to enable GPIO support for the AXP209 PMIC
-
 config GPIO_BCM_KONA
 	bool "Broadcom Kona GPIO"
 	depends on OF_GPIO && (ARCH_BCM_MOBILE || COMPILE_TEST)
@@ -704,6 +698,22 @@ config GPIO_TS5500
 	  blocks of the TS-5500: DIO1, DIO2 and the LCD port, and the TS-5600
 	  LCD port.
 
+config GPIO_WINBOND
+	tristate "Winbond Super I/O GPIO support"
+	depends on ISA_BUS_API
+	help
+	  This option enables support for GPIOs found on Winbond Super I/O
+	  chips.
+	  Currently, only W83627UHG (also known as Nuvoton NCT6627UD) is
+	  supported.
+
+	  You will need to provide a module parameter "gpios", or a
+	  boot-time parameter "gpio_winbond.gpios" with a bitmask of GPIO
+	  ports to enable (bit 0 is GPIO1, bit 1 is GPIO2, etc.).
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called gpio-winbond.
+
 config GPIO_WS16C48
 	tristate "WinSystems WS16C48 GPIO support"
 	depends on ISA_BUS_API
@@ -1234,6 +1244,16 @@ config GPIO_PCI_IDIO_16
 	  low). Input filter control is not supported by this driver, and the
 	  input filters are deactivated by this driver.
 
+config GPIO_PCIE_IDIO_24
+	tristate "ACCES PCIe-IDIO-24 GPIO support"
+	select GPIOLIB_IRQCHIP
+	help
+	  Enables GPIO support for the ACCES PCIe-IDIO-24 family (PCIe-IDIO-24,
+	  PCIe-IDI-24, PCIe-IDO-24, PCIe-IDIO-12). An interrupt is generated
+	  when any of the inputs change state (low to high or high to low).
+	  Input filter control is not supported by this driver, and the input
+	  filters are deactivated by this driver.
+
 config GPIO_RDC321X
 	tristate "RDC R-321x GPIO support"
 	select MFD_CORE
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 4bc24febb889..cccb0d40846c 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -32,7 +32,6 @@ obj-$(CONFIG_GPIO_AMDPT)	+= gpio-amdpt.o
 obj-$(CONFIG_GPIO_ARIZONA)	+= gpio-arizona.o
 obj-$(CONFIG_GPIO_ATH79)	+= gpio-ath79.o
 obj-$(CONFIG_GPIO_ASPEED)	+= gpio-aspeed.o
-obj-$(CONFIG_GPIO_AXP209)	+= gpio-axp209.o
 obj-$(CONFIG_GPIO_BCM_KONA)	+= gpio-bcm-kona.o
 obj-$(CONFIG_GPIO_BD9571MWV)	+= gpio-bd9571mwv.o
 obj-$(CONFIG_GPIO_BRCMSTB)	+= gpio-brcmstb.o
@@ -96,6 +95,7 @@ obj-$(CONFIG_GPIO_PCA953X)	+= gpio-pca953x.o
 obj-$(CONFIG_GPIO_PCF857X)	+= gpio-pcf857x.o
 obj-$(CONFIG_GPIO_PCH)		+= gpio-pch.o
 obj-$(CONFIG_GPIO_PCI_IDIO_16)	+= gpio-pci-idio-16.o
+obj-$(CONFIG_GPIO_PCIE_IDIO_24)	+= gpio-pcie-idio-24.o
 obj-$(CONFIG_GPIO_PISOSR)	+= gpio-pisosr.o
 obj-$(CONFIG_GPIO_PL061)	+= gpio-pl061.o
 obj-$(CONFIG_GPIO_PXA)		+= gpio-pxa.o
@@ -140,6 +140,7 @@ obj-$(CONFIG_GPIO_VIPERBOARD)	+= gpio-viperboard.o
 obj-$(CONFIG_GPIO_VR41XX)	+= gpio-vr41xx.o
 obj-$(CONFIG_GPIO_VX855)	+= gpio-vx855.o
 obj-$(CONFIG_GPIO_WHISKEY_COVE)	+= gpio-wcove.o
+obj-$(CONFIG_GPIO_WINBOND)	+= gpio-winbond.o
 obj-$(CONFIG_GPIO_WM831X)	+= gpio-wm831x.o
 obj-$(CONFIG_GPIO_WM8350)	+= gpio-wm8350.o
 obj-$(CONFIG_GPIO_WM8994)	+= gpio-wm8994.o
diff --git a/drivers/gpio/devres.c b/drivers/gpio/devres.c
index afbff155a0ba..e82cc763633c 100644
--- a/drivers/gpio/devres.c
+++ b/drivers/gpio/devres.c
@@ -125,6 +125,48 @@ struct gpio_desc *__must_check devm_gpiod_get_index(struct device *dev,
 EXPORT_SYMBOL(devm_gpiod_get_index);
 
 /**
+ * devm_gpiod_get_from_of_node() - obtain a GPIO from an OF node
+ * @dev:	device for lifecycle management
+ * @node:	handle of the OF node
+ * @propname:	name of the DT property representing the GPIO
+ * @index:	index of the GPIO to obtain for the consumer
+ * @dflags:	GPIO initialization flags
+ * @label:	label to attach to the requested GPIO
+ *
+ * Returns:
+ * On successful request the GPIO pin is configured in accordance with
+ * provided @dflags.
+ *
+ * In case of error an ERR_PTR() is returned.
+ */
+struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev,
+					      struct device_node *node,
+					      const char *propname, int index,
+					      enum gpiod_flags dflags,
+					      const char *label)
+{
+	struct gpio_desc **dr;
+	struct gpio_desc *desc;
+
+	dr = devres_alloc(devm_gpiod_release, sizeof(struct gpio_desc *),
+			  GFP_KERNEL);
+	if (!dr)
+		return ERR_PTR(-ENOMEM);
+
+	desc = gpiod_get_from_of_node(node, propname, index, dflags, label);
+	if (IS_ERR(desc)) {
+		devres_free(dr);
+		return desc;
+	}
+
+	*dr = desc;
+	devres_add(dev, dr);
+
+	return desc;
+}
+EXPORT_SYMBOL(devm_gpiod_get_from_of_node);
+
+/**
  * devm_fwnode_get_index_gpiod_from_child - get a GPIO descriptor from a
  *					    device's child node
  * @dev:	GPIO consumer
diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c
index 6b535ec858cc..fb7b620763a2 100644
--- a/drivers/gpio/gpio-74x164.c
+++ b/drivers/gpio/gpio-74x164.c
@@ -9,12 +9,11 @@
  *  published by the Free Software Foundation.
  */
 
-#include <linux/gpio/consumer.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/spi/spi.h>
-#include <linux/gpio.h>
-#include <linux/of_gpio.h>
+#include <linux/gpio/driver.h>
+#include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 
@@ -23,6 +22,7 @@
 struct gen_74x164_chip {
 	struct gpio_chip	gpio_chip;
 	struct mutex		lock;
+	struct gpio_desc	*gpiod_oe;
 	u32			registers;
 	/*
 	 * Since the registers are chained, every byte sent will make
@@ -31,8 +31,7 @@ struct gen_74x164_chip {
 	 * register at the end of the transfer. So, to have a logical
 	 * numbering, store the bytes in reverse order.
 	 */
-	u8			buffer[0];
-	struct gpio_desc	*gpiod_oe;
+	u8			buffer[];
 };
 
 static int __gen_74x164_write_config(struct gen_74x164_chip *chip)
diff --git a/drivers/gpio/gpio-adp5520.c b/drivers/gpio/gpio-adp5520.c
index abf199609546..21452622d954 100644
--- a/drivers/gpio/gpio-adp5520.c
+++ b/drivers/gpio/gpio-adp5520.c
@@ -12,8 +12,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/adp5520.h>
-
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 
 struct adp5520_gpio {
 	struct device *master;
diff --git a/drivers/gpio/gpio-adp5588.c b/drivers/gpio/gpio-adp5588.c
index e717f8dc3966..3530ccd17e04 100644
--- a/drivers/gpio/gpio-adp5588.c
+++ b/drivers/gpio/gpio-adp5588.c
@@ -12,7 +12,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/i2c.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 
diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 8e76d390e653..8c3ff6e2366f 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -18,7 +18,8 @@
 
 #include <linux/io.h>
 #include <linux/module.h>
-#include <linux/of_gpio.h>
+#include <linux/gpio/driver.h>
+#include <linux/of_gpio.h> /* For of_mm_gpio_chip */
 #include <linux/platform_device.h>
 
 #define ALTERA_GPIO_MAX_NGPIO		32
diff --git a/drivers/gpio/gpio-amd8111.c b/drivers/gpio/gpio-amd8111.c
index 30ad7d7c1678..fdcebe59510d 100644
--- a/drivers/gpio/gpio-amd8111.c
+++ b/drivers/gpio/gpio-amd8111.c
@@ -28,7 +28,7 @@
 #include <linux/ioport.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/pci.h>
 #include <linux/spinlock.h>
 
diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c
index d4e6ba0301bc..ba51ea15f379 100644
--- a/drivers/gpio/gpio-arizona.c
+++ b/drivers/gpio/gpio-arizona.c
@@ -15,7 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/seq_file.h>
diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index 6b3ca6601af2..77e485557498 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -60,6 +60,7 @@ struct aspeed_gpio_bank {
 	uint16_t	val_regs;
 	uint16_t	irq_regs;
 	uint16_t	debounce_regs;
+	uint16_t	tolerance_regs;
 	const char	names[4][3];
 };
 
@@ -70,48 +71,56 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 		.val_regs = 0x0000,
 		.irq_regs = 0x0008,
 		.debounce_regs = 0x0040,
+		.tolerance_regs = 0x001c,
 		.names = { "A", "B", "C", "D" },
 	},
 	{
 		.val_regs = 0x0020,
 		.irq_regs = 0x0028,
 		.debounce_regs = 0x0048,
+		.tolerance_regs = 0x003c,
 		.names = { "E", "F", "G", "H" },
 	},
 	{
 		.val_regs = 0x0070,
 		.irq_regs = 0x0098,
 		.debounce_regs = 0x00b0,
+		.tolerance_regs = 0x00ac,
 		.names = { "I", "J", "K", "L" },
 	},
 	{
 		.val_regs = 0x0078,
 		.irq_regs = 0x00e8,
 		.debounce_regs = 0x0100,
+		.tolerance_regs = 0x00fc,
 		.names = { "M", "N", "O", "P" },
 	},
 	{
 		.val_regs = 0x0080,
 		.irq_regs = 0x0118,
 		.debounce_regs = 0x0130,
+		.tolerance_regs = 0x012c,
 		.names = { "Q", "R", "S", "T" },
 	},
 	{
 		.val_regs = 0x0088,
 		.irq_regs = 0x0148,
 		.debounce_regs = 0x0160,
+		.tolerance_regs = 0x015c,
 		.names = { "U", "V", "W", "X" },
 	},
 	{
 		.val_regs = 0x01E0,
 		.irq_regs = 0x0178,
 		.debounce_regs = 0x0190,
+		.tolerance_regs = 0x018c,
 		.names = { "Y", "Z", "AA", "AB" },
 	},
 	{
-		.val_regs = 0x01E8,
-		.irq_regs = 0x01A8,
+		.val_regs = 0x01e8,
+		.irq_regs = 0x01a8,
 		.debounce_regs = 0x01c0,
+		.tolerance_regs = 0x01bc,
 		.names = { "AC", "", "", "" },
 	},
 };
@@ -140,7 +149,7 @@ static const struct aspeed_gpio_bank *to_bank(unsigned int offset)
 {
 	unsigned int bank = GPIO_BANK(offset);
 
-	WARN_ON(bank > ARRAY_SIZE(aspeed_gpio_banks));
+	WARN_ON(bank >= ARRAY_SIZE(aspeed_gpio_banks));
 	return &aspeed_gpio_banks[bank];
 }
 
@@ -534,6 +543,30 @@ static int aspeed_gpio_setup_irqs(struct aspeed_gpio *gpio,
 	return 0;
 }
 
+static int aspeed_gpio_reset_tolerance(struct gpio_chip *chip,
+					unsigned int offset, bool enable)
+{
+	struct aspeed_gpio *gpio = gpiochip_get_data(chip);
+	const struct aspeed_gpio_bank *bank;
+	unsigned long flags;
+	u32 val;
+
+	bank = to_bank(offset);
+
+	spin_lock_irqsave(&gpio->lock, flags);
+	val = readl(gpio->base + bank->tolerance_regs);
+
+	if (enable)
+		val |= GPIO_BIT(offset);
+	else
+		val &= ~GPIO_BIT(offset);
+
+	writel(val, gpio->base + bank->tolerance_regs);
+	spin_unlock_irqrestore(&gpio->lock, flags);
+
+	return 0;
+}
+
 static int aspeed_gpio_request(struct gpio_chip *chip, unsigned int offset)
 {
 	if (!have_gpio(gpiochip_get_data(chip), offset))
@@ -771,6 +804,8 @@ static int aspeed_gpio_set_config(struct gpio_chip *chip, unsigned int offset,
 			param == PIN_CONFIG_DRIVE_OPEN_SOURCE)
 		/* Return -ENOTSUPP to trigger emulation, as per datasheet */
 		return -ENOTSUPP;
+	else if (param == PIN_CONFIG_PERSIST_STATE)
+		return aspeed_gpio_reset_tolerance(chip, offset, arg);
 
 	return -ENOTSUPP;
 }
diff --git a/drivers/gpio/gpio-ath79.c b/drivers/gpio/gpio-ath79.c
index 5fad89dfab7e..3ae7c1876bf4 100644
--- a/drivers/gpio/gpio-ath79.c
+++ b/drivers/gpio/gpio-ath79.c
@@ -324,3 +324,6 @@ static struct platform_driver ath79_gpio_driver = {
 };
 
 module_platform_driver(ath79_gpio_driver);
+
+MODULE_DESCRIPTION("Atheros AR71XX/AR724X/AR913X GPIO API support");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-axp209.c b/drivers/gpio/gpio-axp209.c
deleted file mode 100644
index 4a346b7b4172..000000000000
--- a/drivers/gpio/gpio-axp209.c
+++ /dev/null
@@ -1,188 +0,0 @@
-/*
- * AXP20x GPIO driver
- *
- * Copyright (C) 2016 Maxime Ripard <maxime.ripard@free-electrons.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under  the terms of the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the License, or (at your
- * option) any later version.
- */
-
-#include <linux/bitops.h>
-#include <linux/device.h>
-#include <linux/gpio/driver.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/mfd/axp20x.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/regmap.h>
-#include <linux/slab.h>
-
-#define AXP20X_GPIO_FUNCTIONS		0x7
-#define AXP20X_GPIO_FUNCTION_OUT_LOW	0
-#define AXP20X_GPIO_FUNCTION_OUT_HIGH	1
-#define AXP20X_GPIO_FUNCTION_INPUT	2
-
-struct axp20x_gpio {
-	struct gpio_chip	chip;
-	struct regmap		*regmap;
-};
-
-static int axp20x_gpio_get_reg(unsigned offset)
-{
-	switch (offset) {
-	case 0:
-		return AXP20X_GPIO0_CTRL;
-	case 1:
-		return AXP20X_GPIO1_CTRL;
-	case 2:
-		return AXP20X_GPIO2_CTRL;
-	}
-
-	return -EINVAL;
-}
-
-static int axp20x_gpio_input(struct gpio_chip *chip, unsigned offset)
-{
-	struct axp20x_gpio *gpio = gpiochip_get_data(chip);
-	int reg;
-
-	reg = axp20x_gpio_get_reg(offset);
-	if (reg < 0)
-		return reg;
-
-	return regmap_update_bits(gpio->regmap, reg,
-				  AXP20X_GPIO_FUNCTIONS,
-				  AXP20X_GPIO_FUNCTION_INPUT);
-}
-
-static int axp20x_gpio_get(struct gpio_chip *chip, unsigned offset)
-{
-	struct axp20x_gpio *gpio = gpiochip_get_data(chip);
-	unsigned int val;
-	int ret;
-
-	ret = regmap_read(gpio->regmap, AXP20X_GPIO20_SS, &val);
-	if (ret)
-		return ret;
-
-	return !!(val & BIT(offset + 4));
-}
-
-static int axp20x_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
-{
-	struct axp20x_gpio *gpio = gpiochip_get_data(chip);
-	unsigned int val;
-	int reg, ret;
-
-	reg = axp20x_gpio_get_reg(offset);
-	if (reg < 0)
-		return reg;
-
-	ret = regmap_read(gpio->regmap, reg, &val);
-	if (ret)
-		return ret;
-
-	/*
-	 * This shouldn't really happen if the pin is in use already,
-	 * or if it's not in use yet, it doesn't matter since we're
-	 * going to change the value soon anyway. Default to output.
-	 */
-	if ((val & AXP20X_GPIO_FUNCTIONS) > 2)
-		return 0;
-
-	/*
-	 * The GPIO directions are the three lowest values.
-	 * 2 is input, 0 and 1 are output
-	 */
-	return val & 2;
-}
-
-static int axp20x_gpio_output(struct gpio_chip *chip, unsigned offset,
-			      int value)
-{
-	struct axp20x_gpio *gpio = gpiochip_get_data(chip);
-	int reg;
-
-	reg = axp20x_gpio_get_reg(offset);
-	if (reg < 0)
-		return reg;
-
-	return regmap_update_bits(gpio->regmap, reg,
-				  AXP20X_GPIO_FUNCTIONS,
-				  value ? AXP20X_GPIO_FUNCTION_OUT_HIGH
-				  : AXP20X_GPIO_FUNCTION_OUT_LOW);
-}
-
-static void axp20x_gpio_set(struct gpio_chip *chip, unsigned offset,
-			    int value)
-{
-	axp20x_gpio_output(chip, offset, value);
-}
-
-static int axp20x_gpio_probe(struct platform_device *pdev)
-{
-	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
-	struct axp20x_gpio *gpio;
-	int ret;
-
-	if (!of_device_is_available(pdev->dev.of_node))
-		return -ENODEV;
-
-	if (!axp20x) {
-		dev_err(&pdev->dev, "Parent drvdata not set\n");
-		return -EINVAL;
-	}
-
-	gpio = devm_kzalloc(&pdev->dev, sizeof(*gpio), GFP_KERNEL);
-	if (!gpio)
-		return -ENOMEM;
-
-	gpio->chip.base			= -1;
-	gpio->chip.can_sleep		= true;
-	gpio->chip.parent		= &pdev->dev;
-	gpio->chip.label		= dev_name(&pdev->dev);
-	gpio->chip.owner		= THIS_MODULE;
-	gpio->chip.get			= axp20x_gpio_get;
-	gpio->chip.get_direction	= axp20x_gpio_get_direction;
-	gpio->chip.set			= axp20x_gpio_set;
-	gpio->chip.direction_input	= axp20x_gpio_input;
-	gpio->chip.direction_output	= axp20x_gpio_output;
-	gpio->chip.ngpio		= 3;
-
-	gpio->regmap = axp20x->regmap;
-
-	ret = devm_gpiochip_add_data(&pdev->dev, &gpio->chip, gpio);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to register GPIO chip\n");
-		return ret;
-	}
-
-	dev_info(&pdev->dev, "AXP209 GPIO driver loaded\n");
-
-	return 0;
-}
-
-static const struct of_device_id axp20x_gpio_match[] = {
-	{ .compatible = "x-powers,axp209-gpio" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, axp20x_gpio_match);
-
-static struct platform_driver axp20x_gpio_driver = {
-	.probe		= axp20x_gpio_probe,
-	.driver = {
-		.name		= "axp20x-gpio",
-		.of_match_table	= axp20x_gpio_match,
-	},
-};
-
-module_platform_driver(axp20x_gpio_driver);
-
-MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>");
-MODULE_DESCRIPTION("AXP20x PMIC GPIO driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index dfcf56ee3c61..eb8369b21e90 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -17,7 +17,7 @@
 #include <linux/bitops.h>
 #include <linux/err.h>
 #include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/init.h>
@@ -127,7 +127,7 @@ static int bcm_kona_gpio_get_dir(struct gpio_chip *chip, unsigned gpio)
 	u32 val;
 
 	val = readl(reg_base + GPIO_CONTROL(gpio)) & GPIO_GPCTR0_IOTR_MASK;
-	return val ? GPIOF_DIR_IN : GPIOF_DIR_OUT;
+	return !!val;
 }
 
 static void bcm_kona_gpio_set(struct gpio_chip *chip, unsigned gpio, int value)
@@ -144,7 +144,7 @@ static void bcm_kona_gpio_set(struct gpio_chip *chip, unsigned gpio, int value)
 	raw_spin_lock_irqsave(&kona_gpio->lock, flags);
 
 	/* this function only applies to output pin */
-	if (bcm_kona_gpio_get_dir(chip, gpio) == GPIOF_DIR_IN)
+	if (bcm_kona_gpio_get_dir(chip, gpio) == 1)
 		goto out;
 
 	reg_offset = value ? GPIO_OUT_SET(bank_id) : GPIO_OUT_CLEAR(bank_id);
@@ -170,7 +170,7 @@ static int bcm_kona_gpio_get(struct gpio_chip *chip, unsigned gpio)
 	reg_base = kona_gpio->reg_base;
 	raw_spin_lock_irqsave(&kona_gpio->lock, flags);
 
-	if (bcm_kona_gpio_get_dir(chip, gpio) == GPIOF_DIR_IN)
+	if (bcm_kona_gpio_get_dir(chip, gpio) == 1)
 		reg_offset = GPIO_IN_STATUS(bank_id);
 	else
 		reg_offset = GPIO_OUT_STATUS(bank_id);
@@ -522,6 +522,7 @@ static struct of_device_id const bcm_kona_gpio_of_match[] = {
  * category than their parents, so it won't report false recursion.
  */
 static struct lock_class_key gpio_lock_class;
+static struct lock_class_key gpio_request_class;
 
 static int bcm_kona_gpio_irq_map(struct irq_domain *d, unsigned int irq,
 				 irq_hw_number_t hwirq)
@@ -531,7 +532,7 @@ static int bcm_kona_gpio_irq_map(struct irq_domain *d, unsigned int irq,
 	ret = irq_set_chip_data(irq, d->host_data);
 	if (ret < 0)
 		return ret;
-	irq_set_lockdep_class(irq, &gpio_lock_class);
+	irq_set_lockdep_class(irq, &gpio_lock_class, &gpio_request_class);
 	irq_set_chip_and_handler(irq, &bcm_gpio_irq_chip, handle_simple_irq);
 	irq_set_noprobe(irq);
 
diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c
index 545d43a587b7..16c7f9f49416 100644
--- a/drivers/gpio/gpio-brcmstb.c
+++ b/drivers/gpio/gpio-brcmstb.c
@@ -19,7 +19,6 @@
 #include <linux/irqdomain.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/interrupt.h>
-#include <linux/bitops.h>
 
 enum gio_reg_index {
 	GIO_REG_ODEN = 0,
@@ -327,6 +326,7 @@ static struct brcmstb_gpio_bank *brcmstb_gpio_hwirq_to_bank(
  * category than their parents, so it won't report false recursion.
  */
 static struct lock_class_key brcmstb_gpio_irq_lock_class;
+static struct lock_class_key brcmstb_gpio_irq_request_class;
 
 
 static int brcmstb_gpio_irq_map(struct irq_domain *d, unsigned int irq,
@@ -346,7 +346,8 @@ static int brcmstb_gpio_irq_map(struct irq_domain *d, unsigned int irq,
 	ret = irq_set_chip_data(irq, &bank->gc);
 	if (ret < 0)
 		return ret;
-	irq_set_lockdep_class(irq, &brcmstb_gpio_irq_lock_class);
+	irq_set_lockdep_class(irq, &brcmstb_gpio_irq_lock_class,
+			      &brcmstb_gpio_irq_request_class);
 	irq_set_chip_and_handler(irq, &priv->irq_chip, handle_level_irq);
 	irq_set_noprobe(irq);
 	return 0;
diff --git a/drivers/gpio/gpio-bt8xx.c b/drivers/gpio/gpio-bt8xx.c
index acefb25e8eca..b8ec75cbd4b5 100644
--- a/drivers/gpio/gpio-bt8xx.c
+++ b/drivers/gpio/gpio-bt8xx.c
@@ -46,7 +46,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/spinlock.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/slab.h>
 
 /* Steal the hardware definitions from the bttv driver. */
diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c
index b6f0f729656c..58531d8b8c6e 100644
--- a/drivers/gpio/gpio-crystalcove.c
+++ b/drivers/gpio/gpio-crystalcove.c
@@ -18,7 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/seq_file.h>
 #include <linux/bitops.h>
 #include <linux/regmap.h>
diff --git a/drivers/gpio/gpio-cs5535.c b/drivers/gpio/gpio-cs5535.c
index 90278b19aa0e..8814c8f47e57 100644
--- a/drivers/gpio/gpio-cs5535.c
+++ b/drivers/gpio/gpio-cs5535.c
@@ -12,7 +12,7 @@
 #include <linux/spinlock.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/io.h>
 #include <linux/cs5535.h>
 #include <asm/msr.h>
diff --git a/drivers/gpio/gpio-da9052.c b/drivers/gpio/gpio-da9052.c
index dd8977cf3e85..b6d3e997eb26 100644
--- a/drivers/gpio/gpio-da9052.c
+++ b/drivers/gpio/gpio-da9052.c
@@ -15,7 +15,7 @@
 #include <linux/fs.h>
 #include <linux/uaccess.h>
 #include <linux/platform_device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/syscalls.h>
 #include <linux/seq_file.h>
 
diff --git a/drivers/gpio/gpio-da9055.c b/drivers/gpio/gpio-da9055.c
index 82053b52cba0..2f1b5d23b10c 100644
--- a/drivers/gpio/gpio-da9055.c
+++ b/drivers/gpio/gpio-da9055.c
@@ -13,7 +13,7 @@
  */
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 
 #include <linux/mfd/da9055/core.h>
 #include <linux/mfd/da9055/reg.h>
diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index f75d8443ecaf..0b951ca78ec4 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -9,7 +9,7 @@
  * the Free Software Foundation; either version 2 of the License, or
  * (at your option) any later version.
  */
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/clk.h>
@@ -383,7 +383,7 @@ static int gpio_irq_type_unbanked(struct irq_data *data, unsigned trigger)
 	u32 mask;
 
 	d = (struct davinci_gpio_controller *)irq_data_get_irq_handler_data(data);
-	g = (struct davinci_gpio_regs __iomem *)d->regs;
+	g = (struct davinci_gpio_regs __iomem *)d->regs[0];
 	mask = __gpio_mask(data->irq - d->base_irq);
 
 	if (trigger & ~(IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
diff --git a/drivers/gpio/gpio-ftgpio010.c b/drivers/gpio/gpio-ftgpio010.c
index 7b3394fdc624..b7a3a2db699b 100644
--- a/drivers/gpio/gpio-ftgpio010.c
+++ b/drivers/gpio/gpio-ftgpio010.c
@@ -176,8 +176,8 @@ static int ftgpio_gpio_probe(struct platform_device *pdev)
 		return PTR_ERR(g->base);
 
 	irq = platform_get_irq(pdev, 0);
-	if (!irq)
-		return -EINVAL;
+	if (irq <= 0)
+		return irq ? irq : -EINVAL;
 
 	ret = bgpio_init(&g->gc, dev, 4,
 			 g->base + GPIO_DATA_IN,
diff --git a/drivers/gpio/gpio-iop.c b/drivers/gpio/gpio-iop.c
index 98c7ff2a76e7..8d62db447ec1 100644
--- a/drivers/gpio/gpio-iop.c
+++ b/drivers/gpio/gpio-iop.c
@@ -58,3 +58,7 @@ static int __init iop3xx_gpio_init(void)
 	return platform_driver_register(&iop3xx_gpio_driver);
 }
 arch_initcall(iop3xx_gpio_init);
+
+MODULE_DESCRIPTION("GPIO handling for Intel IOP3xx processors");
+MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpio/gpio-it87.c b/drivers/gpio/gpio-it87.c
index d43d0a2cc4c5..efb46edff81f 100644
--- a/drivers/gpio/gpio-it87.c
+++ b/drivers/gpio/gpio-it87.c
@@ -414,6 +414,6 @@ static void __exit it87_gpio_exit(void)
 module_init(it87_gpio_init);
 module_exit(it87_gpio_exit);
 
-MODULE_AUTHOR("Diego Elio PettenÃ² <flameeyes@flameeyes.eu>");
+MODULE_AUTHOR("Diego Elio Pettenò <flameeyes@flameeyes.eu>");
 MODULE_DESCRIPTION("GPIO interface for IT87xx Super I/O chips");
 MODULE_LICENSE("GPL");
diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c
index c04fae1ba32a..9d8bcc69f245 100644
--- a/drivers/gpio/gpio-max732x.c
+++ b/drivers/gpio/gpio-max732x.c
@@ -709,8 +709,7 @@ static int max732x_probe(struct i2c_client *client,
 	return 0;
 
 out_failed:
-	if (chip->client_dummy)
-		i2c_unregister_device(chip->client_dummy);
+	i2c_unregister_device(chip->client_dummy);
 	return ret;
 }
 
@@ -734,8 +733,7 @@ static int max732x_remove(struct i2c_client *client)
 	gpiochip_remove(&chip->gpio_chip);
 
 	/* unregister any dummy i2c_client */
-	if (chip->client_dummy)
-		i2c_unregister_device(chip->client_dummy);
+	i2c_unregister_device(chip->client_dummy);
 
 	return 0;
 }
diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c
index dd67a31ac337..c38624ea0251 100644
--- a/drivers/gpio/gpio-merrifield.c
+++ b/drivers/gpio/gpio-merrifield.c
@@ -9,6 +9,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/acpi.h>
 #include <linux/bitops.h>
 #include <linux/gpio/driver.h>
 #include <linux/init.h>
@@ -380,9 +381,16 @@ static void mrfld_irq_init_hw(struct mrfld_gpio *priv)
 	}
 }
 
+static const char *mrfld_gpio_get_pinctrl_dev_name(void)
+{
+	const char *dev_name = acpi_dev_get_first_match_name("INTC1002", NULL, -1);
+	return dev_name ? dev_name : "pinctrl-merrifield";
+}
+
 static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	const struct mrfld_gpio_pinrange *range;
+	const char *pinctrl_dev_name;
 	struct mrfld_gpio *priv;
 	u32 gpio_base, irq_base;
 	void __iomem *base;
@@ -439,10 +447,11 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 		return retval;
 	}
 
+	pinctrl_dev_name = mrfld_gpio_get_pinctrl_dev_name();
 	for (i = 0; i < ARRAY_SIZE(mrfld_gpio_ranges); i++) {
 		range = &mrfld_gpio_ranges[i];
 		retval = gpiochip_add_pin_range(&priv->chip,
-						"pinctrl-merrifield",
+						pinctrl_dev_name,
 						range->gpio_base,
 						range->pin_base,
 						range->npins);
diff --git a/drivers/gpio/gpio-mmio.c b/drivers/gpio/gpio-mmio.c
index f9042bcc27a4..7b14d6280e44 100644
--- a/drivers/gpio/gpio-mmio.c
+++ b/drivers/gpio/gpio-mmio.c
@@ -152,14 +152,13 @@ static int bgpio_get_set_multiple(struct gpio_chip *gc, unsigned long *mask,
 {
 	unsigned long get_mask = 0;
 	unsigned long set_mask = 0;
-	int bit = 0;
 
-	while ((bit = find_next_bit(mask, gc->ngpio, bit)) != gc->ngpio) {
-		if (gc->bgpio_dir & BIT(bit))
-			set_mask |= BIT(bit);
-		else
-			get_mask |= BIT(bit);
-	}
+	/* Make sure we first clear any bits that are zero when we read the register */
+	*bits &= ~*mask;
+
+	/* Exploit the fact that we know which directions are set */
+	set_mask = *mask & gc->bgpio_dir;
+	get_mask = *mask & ~gc->bgpio_dir;
 
 	if (set_mask)
 		*bits |= gc->read_reg(gc->reg_set) & set_mask;
@@ -176,13 +175,13 @@ static int bgpio_get(struct gpio_chip *gc, unsigned int gpio)
 
 /*
  * This only works if the bits in the GPIO register are in native endianness.
- * It is dirt simple and fast in this case. (Also the most common case.)
  */
 static int bgpio_get_multiple(struct gpio_chip *gc, unsigned long *mask,
 			      unsigned long *bits)
 {
-
-	*bits = gc->read_reg(gc->reg_dat) & *mask;
+	/* Make sure we first clear any bits that are zero when we read the register */
+	*bits &= ~*mask;
+	*bits |= gc->read_reg(gc->reg_dat) & *mask;
 	return 0;
 }
 
@@ -196,9 +195,12 @@ static int bgpio_get_multiple_be(struct gpio_chip *gc, unsigned long *mask,
 	unsigned long val;
 	int bit;
 
+	/* Make sure we first clear any bits that are zero when we read the register */
+	*bits &= ~*mask;
+
 	/* Create a mirrored mask */
-	bit = 0;
-	while ((bit = find_next_bit(mask, gc->ngpio, bit)) != gc->ngpio)
+	bit = -1;
+	while ((bit = find_next_bit(mask, gc->ngpio, bit + 1)) < gc->ngpio)
 		readmask |= bgpio_line2mask(gc, bit);
 
 	/* Read the register */
@@ -208,8 +210,8 @@ static int bgpio_get_multiple_be(struct gpio_chip *gc, unsigned long *mask,
 	 * Mirror the result into the "bits" result, this will give line 0
 	 * in bit 0 ... line 31 in bit 31 for a 32bit register.
 	 */
-	bit = 0;
-	while ((bit = find_next_bit(&val, gc->ngpio, bit)) != gc->ngpio)
+	bit = -1;
+	while ((bit = find_next_bit(&val, gc->ngpio, bit + 1)) < gc->ngpio)
 		*bits |= bgpio_line2mask(gc, bit);
 
 	return 0;
diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c
index 9532d86a82f7..3a545ad17817 100644
--- a/drivers/gpio/gpio-mockup.c
+++ b/drivers/gpio/gpio-mockup.c
@@ -27,13 +27,15 @@
 #include "gpiolib.h"
 
 #define GPIO_MOCKUP_NAME	"gpio-mockup"
-#define	GPIO_MOCKUP_MAX_GC	10
+#define GPIO_MOCKUP_MAX_GC	10
 /*
  * We're storing two values per chip: the GPIO base and the number
  * of GPIO lines.
  */
 #define GPIO_MOCKUP_MAX_RANGES	(GPIO_MOCKUP_MAX_GC * 2)
 
+#define gpio_mockup_err(...)	pr_err(GPIO_MOCKUP_NAME ": " __VA_ARGS__)
+
 enum {
 	GPIO_MOCKUP_DIR_OUT = 0,
 	GPIO_MOCKUP_DIR_IN = 1,
@@ -46,7 +48,7 @@ enum {
  */
 struct gpio_mockup_line_status {
 	int dir;
-	bool value;
+	int value;
 };
 
 struct gpio_mockup_chip {
@@ -62,17 +64,33 @@ struct gpio_mockup_dbgfs_private {
 	int offset;
 };
 
+struct gpio_mockup_platform_data {
+	int base;
+	int ngpio;
+	int index;
+	bool named_lines;
+};
+
 static int gpio_mockup_ranges[GPIO_MOCKUP_MAX_RANGES];
-static int gpio_mockup_params_nr;
-module_param_array(gpio_mockup_ranges, int, &gpio_mockup_params_nr, 0400);
+static int gpio_mockup_num_ranges;
+module_param_array(gpio_mockup_ranges, int, &gpio_mockup_num_ranges, 0400);
 
 static bool gpio_mockup_named_lines;
 module_param_named(gpio_mockup_named_lines,
 		   gpio_mockup_named_lines, bool, 0400);
 
-static const char gpio_mockup_name_start = 'A';
 static struct dentry *gpio_mockup_dbg_dir;
 
+static int gpio_mockup_range_base(unsigned int index)
+{
+	return gpio_mockup_ranges[index * 2];
+}
+
+static int gpio_mockup_range_ngpio(unsigned int index)
+{
+	return gpio_mockup_ranges[index * 2 + 1];
+}
+
 static int gpio_mockup_get(struct gpio_chip *gc, unsigned int offset)
 {
 	struct gpio_mockup_chip *chip = gpiochip_get_data(gc);
@@ -80,16 +98,26 @@ static int gpio_mockup_get(struct gpio_chip *gc, unsigned int offset)
 	return chip->lines[offset].value;
 }
 
-static void gpio_mockup_set(struct gpio_chip *gc, unsigned int offset,
-			    int value)
+static void gpio_mockup_set(struct gpio_chip *gc,
+			    unsigned int offset, int value)
 {
 	struct gpio_mockup_chip *chip = gpiochip_get_data(gc);
 
 	chip->lines[offset].value = !!value;
 }
 
-static int gpio_mockup_dirout(struct gpio_chip *gc, unsigned int offset,
-			      int value)
+static void gpio_mockup_set_multiple(struct gpio_chip *gc,
+				     unsigned long *mask, unsigned long *bits)
+{
+	unsigned int bit;
+
+	for_each_set_bit(bit, mask, gc->ngpio)
+		gpio_mockup_set(gc, bit, test_bit(bit, bits));
+
+}
+
+static int gpio_mockup_dirout(struct gpio_chip *gc,
+			      unsigned int offset, int value)
 {
 	struct gpio_mockup_chip *chip = gpiochip_get_data(gc);
 
@@ -115,29 +143,6 @@ static int gpio_mockup_get_direction(struct gpio_chip *gc, unsigned int offset)
 	return chip->lines[offset].dir;
 }
 
-static int gpio_mockup_name_lines(struct device *dev,
-				  struct gpio_mockup_chip *chip)
-{
-	struct gpio_chip *gc = &chip->gc;
-	char **names;
-	int i;
-
-	names = devm_kcalloc(dev, gc->ngpio, sizeof(char *), GFP_KERNEL);
-	if (!names)
-		return -ENOMEM;
-
-	for (i = 0; i < gc->ngpio; i++) {
-		names[i] = devm_kasprintf(dev, GFP_KERNEL,
-					  "%s-%d", gc->label, i);
-		if (!names[i])
-			return -ENOMEM;
-	}
-
-	gc->names = (const char *const *)names;
-
-	return 0;
-}
-
 static int gpio_mockup_to_irq(struct gpio_chip *gc, unsigned int offset)
 {
 	struct gpio_mockup_chip *chip = gpiochip_get_data(gc);
@@ -188,15 +193,21 @@ static void gpio_mockup_debugfs_setup(struct device *dev,
 				      struct gpio_mockup_chip *chip)
 {
 	struct gpio_mockup_dbgfs_private *priv;
-	struct dentry *evfile;
+	struct dentry *evfile, *link;
 	struct gpio_chip *gc;
+	const char *devname;
 	char *name;
 	int i;
 
 	gc = &chip->gc;
+	devname = dev_name(&gc->gpiodev->dev);
 
-	chip->dbg_dir = debugfs_create_dir(gc->label, gpio_mockup_dbg_dir);
-	if (!chip->dbg_dir)
+	chip->dbg_dir = debugfs_create_dir(devname, gpio_mockup_dbg_dir);
+	if (IS_ERR_OR_NULL(chip->dbg_dir))
+		goto err;
+
+	link = debugfs_create_symlink(gc->label, gpio_mockup_dbg_dir, devname);
+	if (IS_ERR_OR_NULL(link))
 		goto err;
 
 	for (i = 0; i < gc->ngpio; i++) {
@@ -214,23 +225,63 @@ static void gpio_mockup_debugfs_setup(struct device *dev,
 
 		evfile = debugfs_create_file(name, 0200, chip->dbg_dir, priv,
 					     &gpio_mockup_event_ops);
-		if (!evfile)
+		if (IS_ERR_OR_NULL(evfile))
 			goto err;
 	}
 
 	return;
 
 err:
-	dev_err(dev, "error creating debugfs directory\n");
+	dev_err(dev, "error creating debugfs event files\n");
 }
 
-static int gpio_mockup_add(struct device *dev,
-			   struct gpio_mockup_chip *chip,
-			   const char *name, int base, int ngpio)
+static int gpio_mockup_name_lines(struct device *dev,
+				  struct gpio_mockup_chip *chip)
 {
 	struct gpio_chip *gc = &chip->gc;
-	int ret;
+	char **names;
+	int i;
+
+	names = devm_kcalloc(dev, gc->ngpio, sizeof(char *), GFP_KERNEL);
+	if (!names)
+		return -ENOMEM;
+
+	for (i = 0; i < gc->ngpio; i++) {
+		names[i] = devm_kasprintf(dev, GFP_KERNEL,
+					  "%s-%d", gc->label, i);
+		if (!names[i])
+			return -ENOMEM;
+	}
+
+	gc->names = (const char *const *)names;
+
+	return 0;
+}
+
+static int gpio_mockup_probe(struct platform_device *pdev)
+{
+	struct gpio_mockup_platform_data *pdata;
+	struct gpio_mockup_chip *chip;
+	struct gpio_chip *gc;
+	int rv, base, ngpio;
+	struct device *dev;
+	char *name;
+
+	dev = &pdev->dev;
+	pdata = dev_get_platdata(dev);
+	base = pdata->base;
+	ngpio = pdata->ngpio;
 
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	name = devm_kasprintf(dev, GFP_KERNEL, "%s-%c",
+			      pdev->name, pdata->index);
+	if (!name)
+		return -ENOMEM;
+
+	gc = &chip->gc;
 	gc->base = base;
 	gc->ngpio = ngpio;
 	gc->label = name;
@@ -238,6 +289,7 @@ static int gpio_mockup_add(struct device *dev,
 	gc->parent = dev;
 	gc->get = gpio_mockup_get;
 	gc->set = gpio_mockup_set;
+	gc->set_multiple = gpio_mockup_set_multiple;
 	gc->direction_output = gpio_mockup_dirout;
 	gc->direction_input = gpio_mockup_dirin;
 	gc->get_direction = gpio_mockup_get_direction;
@@ -248,19 +300,19 @@ static int gpio_mockup_add(struct device *dev,
 	if (!chip->lines)
 		return -ENOMEM;
 
-	if (gpio_mockup_named_lines) {
-		ret = gpio_mockup_name_lines(dev, chip);
-		if (ret)
-			return ret;
+	if (pdata->named_lines) {
+		rv = gpio_mockup_name_lines(dev, chip);
+		if (rv)
+			return rv;
 	}
 
-	ret = devm_irq_sim_init(dev, &chip->irqsim, gc->ngpio);
-	if (ret)
-		return ret;
+	rv = devm_irq_sim_init(dev, &chip->irqsim, gc->ngpio);
+	if (rv < 0)
+		return rv;
 
-	ret = devm_gpiochip_add_data(dev, &chip->gc, chip);
-	if (ret)
-		return ret;
+	rv = devm_gpiochip_add_data(dev, &chip->gc, chip);
+	if (rv)
+		return rv;
 
 	if (gpio_mockup_dbg_dir)
 		gpio_mockup_debugfs_setup(dev, chip);
@@ -268,58 +320,6 @@ static int gpio_mockup_add(struct device *dev,
 	return 0;
 }
 
-static int gpio_mockup_probe(struct platform_device *pdev)
-{
-	int ret, i, base, ngpio, num_chips;
-	struct device *dev = &pdev->dev;
-	struct gpio_mockup_chip *chips;
-	char *chip_name;
-
-	if (gpio_mockup_params_nr < 2 || (gpio_mockup_params_nr % 2))
-		return -EINVAL;
-
-	/* Each chip is described by two values. */
-	num_chips = gpio_mockup_params_nr / 2;
-
-	chips = devm_kcalloc(dev, num_chips, sizeof(*chips), GFP_KERNEL);
-	if (!chips)
-		return -ENOMEM;
-
-	platform_set_drvdata(pdev, chips);
-
-	for (i = 0; i < num_chips; i++) {
-		base = gpio_mockup_ranges[i * 2];
-
-		if (base == -1)
-			ngpio = gpio_mockup_ranges[i * 2 + 1];
-		else
-			ngpio = gpio_mockup_ranges[i * 2 + 1] - base;
-
-		if (ngpio >= 0) {
-			chip_name = devm_kasprintf(dev, GFP_KERNEL,
-						   "%s-%c", GPIO_MOCKUP_NAME,
-						   gpio_mockup_name_start + i);
-			if (!chip_name)
-				return -ENOMEM;
-
-			ret = gpio_mockup_add(dev, &chips[i],
-					      chip_name, base, ngpio);
-		} else {
-			ret = -EINVAL;
-		}
-
-		if (ret) {
-			dev_err(dev,
-				"adding gpiochip failed: %d (base: %d, ngpio: %d)\n",
-				ret, base, base < 0 ? ngpio : base + ngpio);
-
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
 static struct platform_driver gpio_mockup_driver = {
 	.driver = {
 		.name = GPIO_MOCKUP_NAME,
@@ -327,44 +327,88 @@ static struct platform_driver gpio_mockup_driver = {
 	.probe = gpio_mockup_probe,
 };
 
-static struct platform_device *pdev;
-static int __init mock_device_init(void)
+static struct platform_device *gpio_mockup_pdevs[GPIO_MOCKUP_MAX_GC];
+
+static void gpio_mockup_unregister_pdevs(void)
 {
-	int err;
+	struct platform_device *pdev;
+	int i;
 
-	gpio_mockup_dbg_dir = debugfs_create_dir("gpio-mockup-event", NULL);
-	if (!gpio_mockup_dbg_dir)
-		pr_err("%s: error creating debugfs directory\n",
-		       GPIO_MOCKUP_NAME);
+	for (i = 0; i < GPIO_MOCKUP_MAX_GC; i++) {
+		pdev = gpio_mockup_pdevs[i];
 
-	pdev = platform_device_alloc(GPIO_MOCKUP_NAME, -1);
-	if (!pdev)
-		return -ENOMEM;
+		if (pdev)
+			platform_device_unregister(pdev);
+	}
+}
 
-	err = platform_device_add(pdev);
-	if (err) {
-		platform_device_put(pdev);
-		return err;
+static int __init gpio_mockup_init(void)
+{
+	int i, num_chips, err = 0, index = 'A';
+	struct gpio_mockup_platform_data pdata;
+	struct platform_device *pdev;
+
+	if ((gpio_mockup_num_ranges < 2) ||
+	    (gpio_mockup_num_ranges % 2) ||
+	    (gpio_mockup_num_ranges > GPIO_MOCKUP_MAX_RANGES))
+		return -EINVAL;
+
+	/* Each chip is described by two values. */
+	num_chips = gpio_mockup_num_ranges / 2;
+
+	/*
+	 * The second value in the <base GPIO - number of GPIOS> pair must
+	 * always be greater than 0.
+	 */
+	for (i = 0; i < num_chips; i++) {
+		if (gpio_mockup_range_ngpio(i) < 0)
+			return -EINVAL;
 	}
 
+	gpio_mockup_dbg_dir = debugfs_create_dir("gpio-mockup-event", NULL);
+	if (IS_ERR_OR_NULL(gpio_mockup_dbg_dir))
+		gpio_mockup_err("error creating debugfs directory\n");
+
 	err = platform_driver_register(&gpio_mockup_driver);
 	if (err) {
-		platform_device_unregister(pdev);
+		gpio_mockup_err("error registering platform driver\n");
 		return err;
 	}
 
+	for (i = 0; i < num_chips; i++) {
+		pdata.index = index++;
+		pdata.base = gpio_mockup_range_base(i);
+		pdata.ngpio = pdata.base < 0
+				? gpio_mockup_range_ngpio(i)
+				: gpio_mockup_range_ngpio(i) - pdata.base;
+		pdata.named_lines = gpio_mockup_named_lines;
+
+		pdev = platform_device_register_resndata(NULL,
+							 GPIO_MOCKUP_NAME,
+							 i, NULL, 0, &pdata,
+							 sizeof(pdata));
+		if (IS_ERR(pdev)) {
+			gpio_mockup_err("error registering device");
+			platform_driver_unregister(&gpio_mockup_driver);
+			gpio_mockup_unregister_pdevs();
+			return PTR_ERR(pdev);
+		}
+
+		gpio_mockup_pdevs[i] = pdev;
+	}
+
 	return 0;
 }
 
-static void __exit mock_device_exit(void)
+static void __exit gpio_mockup_exit(void)
 {
 	debugfs_remove_recursive(gpio_mockup_dbg_dir);
 	platform_driver_unregister(&gpio_mockup_driver);
-	platform_device_unregister(pdev);
+	gpio_mockup_unregister_pdevs();
 }
 
-module_init(mock_device_init);
-module_exit(mock_device_exit);
+module_init(gpio_mockup_init);
+module_exit(gpio_mockup_exit);
 
 MODULE_AUTHOR("Kamlakant Patel <kamlakant.patel@broadcom.com>");
 MODULE_AUTHOR("Bamvor Jian Zhang <bamvor.zhangjian@linaro.org>");
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index e136d666f1e5..ab5035b96886 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -1058,7 +1058,9 @@ static void omap_gpio_mod_init(struct gpio_bank *bank)
 
 static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
 {
+	struct gpio_irq_chip *irq;
 	static int gpio;
+	const char *label;
 	int irq_base = 0;
 	int ret;
 
@@ -1080,21 +1082,15 @@ static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
 			bank->chip.parent = &omap_mpuio_device.dev;
 		bank->chip.base = OMAP_MPUIO(0);
 	} else {
-		bank->chip.label = "gpio";
+		label = devm_kasprintf(bank->chip.parent, GFP_KERNEL, "gpio-%d-%d",
+				       gpio, gpio + bank->width - 1);
+		if (!label)
+			return -ENOMEM;
+		bank->chip.label = label;
 		bank->chip.base = gpio;
 	}
 	bank->chip.ngpio = bank->width;
 
-	ret = gpiochip_add_data(&bank->chip, bank);
-	if (ret) {
-		dev_err(bank->chip.parent,
-			"Could not register gpio chip %d\n", ret);
-		return ret;
-	}
-
-	if (!bank->is_mpuio)
-		gpio += bank->width;
-
 #ifdef CONFIG_ARCH_OMAP1
 	/*
 	 * REVISIT: Once we have OMAP1 supporting SPARSE_IRQ, we can drop
@@ -1115,25 +1111,30 @@ static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
 			irqc->irq_set_wake = NULL;
 	}
 
-	ret = gpiochip_irqchip_add(&bank->chip, irqc,
-				   irq_base, handle_bad_irq,
-				   IRQ_TYPE_NONE);
+	irq = &bank->chip.irq;
+	irq->chip = irqc;
+	irq->handler = handle_bad_irq;
+	irq->default_type = IRQ_TYPE_NONE;
+	irq->num_parents = 1;
+	irq->parents = &bank->irq;
+	irq->first = irq_base;
 
+	ret = gpiochip_add_data(&bank->chip, bank);
 	if (ret) {
 		dev_err(bank->chip.parent,
-			"Couldn't add irqchip to gpiochip %d\n", ret);
-		gpiochip_remove(&bank->chip);
-		return -ENODEV;
+			"Could not register gpio chip %d\n", ret);
+		return ret;
 	}
 
-	gpiochip_set_chained_irqchip(&bank->chip, irqc, bank->irq, NULL);
-
 	ret = devm_request_irq(bank->chip.parent, bank->irq,
 			       omap_gpio_irq_handler,
 			       0, dev_name(bank->chip.parent), bank);
 	if (ret)
 		gpiochip_remove(&bank->chip);
 
+	if (!bank->is_mpuio)
+		gpio += bank->width;
+
 	return ret;
 }
 
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index babb7bd2ba59..a0a5f9730aa7 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -947,7 +947,7 @@ static const struct of_device_id pca953x_dt_ids[] = {
 	{ .compatible = "ti,tca6416", .data = OF_953X(16, PCA_INT), },
 	{ .compatible = "ti,tca6424", .data = OF_953X(24, PCA_INT), },
 
-	{ .compatible = "onsemi,pca9654", .data = OF_953X( 8, PCA_INT), },
+	{ .compatible = "onnn,pca9654", .data = OF_953X( 8, PCA_INT), },
 
 	{ .compatible = "exar,xra1202", .data = OF_953X( 8, 0), },
 	{ }
diff --git a/drivers/gpio/gpio-pcie-idio-24.c b/drivers/gpio/gpio-pcie-idio-24.c
new file mode 100644
index 000000000000..f666e2e69074
--- /dev/null
+++ b/drivers/gpio/gpio-pcie-idio-24.c
@@ -0,0 +1,447 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * GPIO driver for the ACCES PCIe-IDIO-24 family
+ * Copyright (C) 2018 William Breathitt Gray
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * This driver supports the following ACCES devices: PCIe-IDIO-24,
+ * PCIe-IDI-24, PCIe-IDO-24, and PCIe-IDIO-12.
+ */
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/gpio/driver.h>
+#include <linux/interrupt.h>
+#include <linux/irqdesc.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+/**
+ * struct idio_24_gpio_reg - GPIO device registers structure
+ * @out0_7:	Read: FET Outputs 0-7
+ *		Write: FET Outputs 0-7
+ * @out8_15:	Read: FET Outputs 8-15
+ *		Write: FET Outputs 8-15
+ * @out16_23:	Read: FET Outputs 16-23
+ *		Write: FET Outputs 16-23
+ * @ttl_out0_7:	Read: TTL/CMOS Outputs 0-7
+ *		Write: TTL/CMOS Outputs 0-7
+ * @in0_7:	Read: Isolated Inputs 0-7
+ *		Write: Reserved
+ * @in8_15:	Read: Isolated Inputs 8-15
+ *		Write: Reserved
+ * @in16_23:	Read: Isolated Inputs 16-23
+ *		Write: Reserved
+ * @ttl_in0_7:	Read: TTL/CMOS Inputs 0-7
+ *		Write: Reserved
+ * @cos0_7:	Read: COS Status Inputs 0-7
+ *		Write: COS Clear Inputs 0-7
+ * @cos8_15:	Read: COS Status Inputs 8-15
+ *		Write: COS Clear Inputs 8-15
+ * @cos16_23:	Read: COS Status Inputs 16-23
+ *		Write: COS Clear Inputs 16-23
+ * @cos_ttl0_7:	Read: COS Status TTL/CMOS 0-7
+ *		Write: COS Clear TTL/CMOS 0-7
+ * @ctl:	Read: Control Register
+ *		Write: Control Register
+ * @reserved:	Read: Reserved
+ *		Write: Reserved
+ * @cos_enable:	Read: COS Enable
+ *		Write: COS Enable
+ * @soft_reset:	Read: IRQ Output Pin Status
+ *		Write: Software Board Reset
+ */
+struct idio_24_gpio_reg {
+	u8 out0_7;
+	u8 out8_15;
+	u8 out16_23;
+	u8 ttl_out0_7;
+	u8 in0_7;
+	u8 in8_15;
+	u8 in16_23;
+	u8 ttl_in0_7;
+	u8 cos0_7;
+	u8 cos8_15;
+	u8 cos16_23;
+	u8 cos_ttl0_7;
+	u8 ctl;
+	u8 reserved;
+	u8 cos_enable;
+	u8 soft_reset;
+};
+
+/**
+ * struct idio_24_gpio - GPIO device private data structure
+ * @chip:	instance of the gpio_chip
+ * @lock:	synchronization lock to prevent I/O race conditions
+ * @reg:	I/O address offset for the GPIO device registers
+ * @irq_mask:	I/O bits affected by interrupts
+ */
+struct idio_24_gpio {
+	struct gpio_chip chip;
+	raw_spinlock_t lock;
+	struct idio_24_gpio_reg __iomem *reg;
+	unsigned long irq_mask;
+};
+
+static int idio_24_gpio_get_direction(struct gpio_chip *chip,
+	unsigned int offset)
+{
+	struct idio_24_gpio *const idio24gpio = gpiochip_get_data(chip);
+	const unsigned long out_mode_mask = BIT(1);
+
+	/* FET Outputs */
+	if (offset < 24)
+		return 0;
+
+	/* Isolated Inputs */
+	if (offset < 48)
+		return 1;
+
+	/* TTL/CMOS I/O */
+	/* OUT MODE = 1 when TTL/CMOS Output Mode is set */
+	return !(ioread8(&idio24gpio->reg->ctl) & out_mode_mask);
+}
+
+static int idio_24_gpio_direction_input(struct gpio_chip *chip,
+	unsigned int offset)
+{
+	struct idio_24_gpio *const idio24gpio = gpiochip_get_data(chip);
+	unsigned long flags;
+	unsigned int ctl_state;
+	const unsigned long out_mode_mask = BIT(1);
+
+	/* TTL/CMOS I/O */
+	if (offset > 47) {
+		raw_spin_lock_irqsave(&idio24gpio->lock, flags);
+
+		/* Clear TTL/CMOS Output Mode */
+		ctl_state = ioread8(&idio24gpio->reg->ctl) & ~out_mode_mask;
+		iowrite8(ctl_state, &idio24gpio->reg->ctl);
+
+		raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
+	}
+
+	return 0;
+}
+
+static int idio_24_gpio_direction_output(struct gpio_chip *chip,
+	unsigned int offset, int value)
+{
+	struct idio_24_gpio *const idio24gpio = gpiochip_get_data(chip);
+	unsigned long flags;
+	unsigned int ctl_state;
+	const unsigned long out_mode_mask = BIT(1);
+
+	/* TTL/CMOS I/O */
+	if (offset > 47) {
+		raw_spin_lock_irqsave(&idio24gpio->lock, flags);
+
+		/* Set TTL/CMOS Output Mode */
+		ctl_state = ioread8(&idio24gpio->reg->ctl) | out_mode_mask;
+		iowrite8(ctl_state, &idio24gpio->reg->ctl);
+
+		raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
+	}
+
+	chip->set(chip, offset, value);
+	return 0;
+}
+
+static int idio_24_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	struct idio_24_gpio *const idio24gpio = gpiochip_get_data(chip);
+	const unsigned long offset_mask = BIT(offset % 8);
+	const unsigned long out_mode_mask = BIT(1);
+
+	/* FET Outputs */
+	if (offset < 8)
+		return !!(ioread8(&idio24gpio->reg->out0_7) & offset_mask);
+
+	if (offset < 16)
+		return !!(ioread8(&idio24gpio->reg->out8_15) & offset_mask);
+
+	if (offset < 24)
+		return !!(ioread8(&idio24gpio->reg->out16_23) & offset_mask);
+
+	/* Isolated Inputs */
+	if (offset < 32)
+		return !!(ioread8(&idio24gpio->reg->in0_7) & offset_mask);
+
+	if (offset < 40)
+		return !!(ioread8(&idio24gpio->reg->in8_15) & offset_mask);
+
+	if (offset < 48)
+		return !!(ioread8(&idio24gpio->reg->in16_23) & offset_mask);
+
+	/* TTL/CMOS Outputs */
+	if (ioread8(&idio24gpio->reg->ctl) & out_mode_mask)
+		return !!(ioread8(&idio24gpio->reg->ttl_out0_7) & offset_mask);
+
+	/* TTL/CMOS Inputs */
+	return !!(ioread8(&idio24gpio->reg->ttl_in0_7) & offset_mask);
+}
+
+static void idio_24_gpio_set(struct gpio_chip *chip, unsigned int offset,
+	int value)
+{
+	struct idio_24_gpio *const idio24gpio = gpiochip_get_data(chip);
+	const unsigned long out_mode_mask = BIT(1);
+	void __iomem *base;
+	const unsigned int mask = BIT(offset % 8);
+	unsigned long flags;
+	unsigned int out_state;
+
+	/* Isolated Inputs */
+	if (offset > 23 && offset < 48)
+		return;
+
+	/* TTL/CMOS Inputs */
+	if (offset > 47 && !(ioread8(&idio24gpio->reg->ctl) & out_mode_mask))
+		return;
+
+	/* TTL/CMOS Outputs */
+	if (offset > 47)
+		base = &idio24gpio->reg->ttl_out0_7;
+	/* FET Outputs */
+	else if (offset > 15)
+		base = &idio24gpio->reg->out16_23;
+	else if (offset > 7)
+		base = &idio24gpio->reg->out8_15;
+	else
+		base = &idio24gpio->reg->out0_7;
+
+	raw_spin_lock_irqsave(&idio24gpio->lock, flags);
+
+	if (value)
+		out_state = ioread8(base) | mask;
+	else
+		out_state = ioread8(base) & ~mask;
+
+	iowrite8(out_state, base);
+
+	raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
+}
+
+static void idio_24_irq_ack(struct irq_data *data)
+{
+}
+
+static void idio_24_irq_mask(struct irq_data *data)
+{
+	struct gpio_chip *const chip = irq_data_get_irq_chip_data(data);
+	struct idio_24_gpio *const idio24gpio = gpiochip_get_data(chip);
+	unsigned long flags;
+	const unsigned long bit_offset = irqd_to_hwirq(data) - 24;
+	unsigned char new_irq_mask;
+	const unsigned long bank_offset = bit_offset/8 * 8;
+	unsigned char cos_enable_state;
+
+	raw_spin_lock_irqsave(&idio24gpio->lock, flags);
+
+	idio24gpio->irq_mask &= BIT(bit_offset);
+	new_irq_mask = idio24gpio->irq_mask >> bank_offset;
+
+	if (!new_irq_mask) {
+		cos_enable_state = ioread8(&idio24gpio->reg->cos_enable);
+
+		/* Disable Rising Edge detection */
+		cos_enable_state &= ~BIT(bank_offset);
+		/* Disable Falling Edge detection */
+		cos_enable_state &= ~BIT(bank_offset + 4);
+
+		iowrite8(cos_enable_state, &idio24gpio->reg->cos_enable);
+	}
+
+	raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
+}
+
+static void idio_24_irq_unmask(struct irq_data *data)
+{
+	struct gpio_chip *const chip = irq_data_get_irq_chip_data(data);
+	struct idio_24_gpio *const idio24gpio = gpiochip_get_data(chip);
+	unsigned long flags;
+	unsigned char prev_irq_mask;
+	const unsigned long bit_offset = irqd_to_hwirq(data) - 24;
+	const unsigned long bank_offset = bit_offset/8 * 8;
+	unsigned char cos_enable_state;
+
+	raw_spin_lock_irqsave(&idio24gpio->lock, flags);
+
+	prev_irq_mask = idio24gpio->irq_mask >> bank_offset;
+	idio24gpio->irq_mask |= BIT(bit_offset);
+
+	if (!prev_irq_mask) {
+		cos_enable_state = ioread8(&idio24gpio->reg->cos_enable);
+
+		/* Enable Rising Edge detection */
+		cos_enable_state |= BIT(bank_offset);
+		/* Enable Falling Edge detection */
+		cos_enable_state |= BIT(bank_offset + 4);
+
+		iowrite8(cos_enable_state, &idio24gpio->reg->cos_enable);
+	}
+
+	raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
+}
+
+static int idio_24_irq_set_type(struct irq_data *data, unsigned int flow_type)
+{
+	/* The only valid irq types are none and both-edges */
+	if (flow_type != IRQ_TYPE_NONE &&
+		(flow_type & IRQ_TYPE_EDGE_BOTH) != IRQ_TYPE_EDGE_BOTH)
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct irq_chip idio_24_irqchip = {
+	.name = "pcie-idio-24",
+	.irq_ack = idio_24_irq_ack,
+	.irq_mask = idio_24_irq_mask,
+	.irq_unmask = idio_24_irq_unmask,
+	.irq_set_type = idio_24_irq_set_type
+};
+
+static irqreturn_t idio_24_irq_handler(int irq, void *dev_id)
+{
+	struct idio_24_gpio *const idio24gpio = dev_id;
+	unsigned long irq_status;
+	struct gpio_chip *const chip = &idio24gpio->chip;
+	unsigned long irq_mask;
+	int gpio;
+
+	raw_spin_lock(&idio24gpio->lock);
+
+	/* Read Change-Of-State status */
+	irq_status = ioread32(&idio24gpio->reg->cos0_7);
+
+	raw_spin_unlock(&idio24gpio->lock);
+
+	/* Make sure our device generated IRQ */
+	if (!irq_status)
+		return IRQ_NONE;
+
+	/* Handle only unmasked IRQ */
+	irq_mask = idio24gpio->irq_mask & irq_status;
+
+	for_each_set_bit(gpio, &irq_mask, chip->ngpio - 24)
+		generic_handle_irq(irq_find_mapping(chip->irq.domain,
+			gpio + 24));
+
+	raw_spin_lock(&idio24gpio->lock);
+
+	/* Clear Change-Of-State status */
+	iowrite32(irq_status, &idio24gpio->reg->cos0_7);
+
+	raw_spin_unlock(&idio24gpio->lock);
+
+	return IRQ_HANDLED;
+}
+
+#define IDIO_24_NGPIO 56
+static const char *idio_24_names[IDIO_24_NGPIO] = {
+	"OUT0", "OUT1", "OUT2", "OUT3", "OUT4", "OUT5", "OUT6", "OUT7",
+	"OUT8", "OUT9", "OUT10", "OUT11", "OUT12", "OUT13", "OUT14", "OUT15",
+	"OUT16", "OUT17", "OUT18", "OUT19", "OUT20", "OUT21", "OUT22", "OUT23",
+	"IIN0", "IIN1", "IIN2", "IIN3", "IIN4", "IIN5", "IIN6", "IIN7",
+	"IIN8", "IIN9", "IIN10", "IIN11", "IIN12", "IIN13", "IIN14", "IIN15",
+	"IIN16", "IIN17", "IIN18", "IIN19", "IIN20", "IIN21", "IIN22", "IIN23",
+	"TTL0", "TTL1", "TTL2", "TTL3", "TTL4", "TTL5", "TTL6", "TTL7"
+};
+
+static int idio_24_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct device *const dev = &pdev->dev;
+	struct idio_24_gpio *idio24gpio;
+	int err;
+	const size_t pci_bar_index = 2;
+	const char *const name = pci_name(pdev);
+
+	idio24gpio = devm_kzalloc(dev, sizeof(*idio24gpio), GFP_KERNEL);
+	if (!idio24gpio)
+		return -ENOMEM;
+
+	err = pcim_enable_device(pdev);
+	if (err) {
+		dev_err(dev, "Failed to enable PCI device (%d)\n", err);
+		return err;
+	}
+
+	err = pcim_iomap_regions(pdev, BIT(pci_bar_index), name);
+	if (err) {
+		dev_err(dev, "Unable to map PCI I/O addresses (%d)\n", err);
+		return err;
+	}
+
+	idio24gpio->reg = pcim_iomap_table(pdev)[pci_bar_index];
+
+	idio24gpio->chip.label = name;
+	idio24gpio->chip.parent = dev;
+	idio24gpio->chip.owner = THIS_MODULE;
+	idio24gpio->chip.base = -1;
+	idio24gpio->chip.ngpio = IDIO_24_NGPIO;
+	idio24gpio->chip.names = idio_24_names;
+	idio24gpio->chip.get_direction = idio_24_gpio_get_direction;
+	idio24gpio->chip.direction_input = idio_24_gpio_direction_input;
+	idio24gpio->chip.direction_output = idio_24_gpio_direction_output;
+	idio24gpio->chip.get = idio_24_gpio_get;
+	idio24gpio->chip.set = idio_24_gpio_set;
+
+	raw_spin_lock_init(&idio24gpio->lock);
+
+	/* Software board reset */
+	iowrite8(0, &idio24gpio->reg->soft_reset);
+
+	err = devm_gpiochip_add_data(dev, &idio24gpio->chip, idio24gpio);
+	if (err) {
+		dev_err(dev, "GPIO registering failed (%d)\n", err);
+		return err;
+	}
+
+	err = gpiochip_irqchip_add(&idio24gpio->chip, &idio_24_irqchip, 0,
+		handle_edge_irq, IRQ_TYPE_NONE);
+	if (err) {
+		dev_err(dev, "Could not add irqchip (%d)\n", err);
+		return err;
+	}
+
+	err = devm_request_irq(dev, pdev->irq, idio_24_irq_handler, IRQF_SHARED,
+		name, idio24gpio);
+	if (err) {
+		dev_err(dev, "IRQ handler registering failed (%d)\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static const struct pci_device_id idio_24_pci_dev_id[] = {
+	{ PCI_DEVICE(0x494F, 0x0FD0) }, { PCI_DEVICE(0x494F, 0x0BD0) },
+	{ PCI_DEVICE(0x494F, 0x07D0) }, { PCI_DEVICE(0x494F, 0x0FC0) },
+	{ 0 }
+};
+MODULE_DEVICE_TABLE(pci, idio_24_pci_dev_id);
+
+static struct pci_driver idio_24_driver = {
+	.name = "pcie-idio-24",
+	.id_table = idio_24_pci_dev_id,
+	.probe = idio_24_probe
+};
+
+module_pci_driver(idio_24_driver);
+
+MODULE_AUTHOR("William Breathitt Gray <vilhelm.gray@gmail.com>");
+MODULE_DESCRIPTION("ACCES PCIe-IDIO-24 GPIO driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-reg.c b/drivers/gpio/gpio-reg.c
index 23e771dba4c1..e85903eddc68 100644
--- a/drivers/gpio/gpio-reg.c
+++ b/drivers/gpio/gpio-reg.c
@@ -103,8 +103,8 @@ static int gpio_reg_to_irq(struct gpio_chip *gc, unsigned offset)
 	struct gpio_reg *r = to_gpio_reg(gc);
 	int irq = r->irqs[offset];
 
-	if (irq >= 0 && r->irq.domain)
-		irq = irq_find_mapping(r->irq.domain, irq);
+	if (irq >= 0 && r->irqdomain)
+		irq = irq_find_mapping(r->irqdomain, irq);
 
 	return irq;
 }
diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index e6e5cca624a7..f8d7d1cd8488 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -190,6 +190,16 @@ static void stmpe_gpio_irq_sync_unlock(struct irq_data *d)
 	};
 	int i, j;
 
+	/*
+	 * STMPE1600: to be able to get IRQ from pins,
+	 * a read must be done on GPMR register, or a write in
+	 * GPSR or GPCR registers
+	 */
+	if (stmpe->partnum == STMPE1600) {
+		stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_LSB]);
+		stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_CSB]);
+	}
+
 	for (i = 0; i < CACHE_NR_REGS; i++) {
 		/* STMPE801 and STMPE1600 don't have RE and FE registers */
 		if ((stmpe->partnum == STMPE801 ||
@@ -227,21 +237,11 @@ static void stmpe_gpio_irq_unmask(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct stmpe_gpio *stmpe_gpio = gpiochip_get_data(gc);
-	struct stmpe *stmpe = stmpe_gpio->stmpe;
 	int offset = d->hwirq;
 	int regoffset = offset / 8;
 	int mask = BIT(offset % 8);
 
 	stmpe_gpio->regs[REG_IE][regoffset] |= mask;
-
-	/*
-	 * STMPE1600 workaround: to be able to get IRQ from pins,
-	 * a read must be done on GPMR register, or a write in
-	 * GPSR or GPCR registers
-	 */
-	if (stmpe->partnum == STMPE1600)
-		stmpe_reg_read(stmpe,
-			       stmpe->regs[STMPE_IDX_GPMR_LSB + regoffset]);
 }
 
 static void stmpe_dbg_show_one(struct seq_file *s,
@@ -273,15 +273,21 @@ static void stmpe_dbg_show_one(struct seq_file *s,
 		u8 fall_reg;
 		u8 irqen_reg;
 
-		char *edge_det_values[] = {"edge-inactive",
-					   "edge-asserted",
-					   "not-supported"};
-		char *rise_values[] = {"no-rising-edge-detection",
-				       "rising-edge-detection",
-				       "not-supported"};
-		char *fall_values[] = {"no-falling-edge-detection",
-				       "falling-edge-detection",
-				       "not-supported"};
+		static const char * const edge_det_values[] = {
+			"edge-inactive",
+			"edge-asserted",
+			"not-supported"
+		};
+		static const char * const rise_values[] = {
+			"no-rising-edge-detection",
+			"rising-edge-detection",
+			"not-supported"
+		};
+		static const char * const fall_values[] = {
+			"no-falling-edge-detection",
+			"falling-edge-detection",
+			"not-supported"
+		};
 		#define NOT_SUPPORTED_IDX 2
 		u8 edge_det = NOT_SUPPORTED_IDX;
 		u8 rise = NOT_SUPPORTED_IDX;
@@ -344,7 +350,7 @@ static void stmpe_dbg_show(struct seq_file *s, struct gpio_chip *gc)
 
 	for (i = 0; i < gc->ngpio; i++, gpio++) {
 		stmpe_dbg_show_one(s, gc, i, gpio);
-		seq_printf(s, "\n");
+		seq_putc(s, '\n');
 	}
 }
 
@@ -426,12 +432,9 @@ static int stmpe_gpio_probe(struct platform_device *pdev)
 	struct stmpe *stmpe = dev_get_drvdata(pdev->dev.parent);
 	struct device_node *np = pdev->dev.of_node;
 	struct stmpe_gpio *stmpe_gpio;
-	int ret;
-	int irq = 0;
-
-	irq = platform_get_irq(pdev, 0);
+	int ret, irq;
 
-	stmpe_gpio = kzalloc(sizeof(struct stmpe_gpio), GFP_KERNEL);
+	stmpe_gpio = kzalloc(sizeof(*stmpe_gpio), GFP_KERNEL);
 	if (!stmpe_gpio)
 		return -ENOMEM;
 
@@ -453,6 +456,7 @@ static int stmpe_gpio_probe(struct platform_device *pdev)
 	if (stmpe_gpio->norequest_mask)
 		stmpe_gpio->chip.irq.need_valid_mask = true;
 
+	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		dev_info(&pdev->dev,
 			"device configured in no-irq mode: "
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 8db47f671708..02fa8fe2292a 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -565,6 +565,7 @@ static const struct dev_pm_ops tegra_gpio_pm_ops = {
  * than their parents, so it won't report false recursion.
  */
 static struct lock_class_key gpio_lock_class;
+static struct lock_class_key gpio_request_class;
 
 static int tegra_gpio_probe(struct platform_device *pdev)
 {
@@ -670,7 +671,8 @@ static int tegra_gpio_probe(struct platform_device *pdev)
 
 		bank = &tgi->bank_info[GPIO_BANK(gpio)];
 
-		irq_set_lockdep_class(irq, &gpio_lock_class);
+		irq_set_lockdep_class(irq, &gpio_lock_class,
+				      &gpio_request_class);
 		irq_set_chip_data(irq, bank);
 		irq_set_chip_and_handler(irq, &tgi->ic, handle_simple_irq);
 	}
diff --git a/drivers/gpio/gpio-thunderx.c b/drivers/gpio/gpio-thunderx.c
index b5adb79a631a..d16e9d4a129b 100644
--- a/drivers/gpio/gpio-thunderx.c
+++ b/drivers/gpio/gpio-thunderx.c
@@ -553,8 +553,10 @@ static int thunderx_gpio_probe(struct pci_dev *pdev,
 	txgpio->irqd = irq_domain_create_hierarchy(irq_get_irq_data(txgpio->msix_entries[0].vector)->domain,
 						   0, 0, of_node_to_fwnode(dev->of_node),
 						   &thunderx_gpio_irqd_ops, txgpio);
-	if (!txgpio->irqd)
+	if (!txgpio->irqd) {
+		err = -ENOMEM;
 		goto out;
+	}
 
 	/* Push on irq_data and the domain for each line. */
 	for (i = 0; i < ngpio; i++) {
diff --git a/drivers/gpio/gpio-winbond.c b/drivers/gpio/gpio-winbond.c
new file mode 100644
index 000000000000..7f8f5b02e31d
--- /dev/null
+++ b/drivers/gpio/gpio-winbond.c
@@ -0,0 +1,732 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * GPIO interface for Winbond Super I/O chips
+ * Currently, only W83627UHG (Nuvoton NCT6627UD) is supported.
+ *
+ * Author: Maciej S. Szmigiero <mail@maciej.szmigiero.name>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/gpio/driver.h>
+#include <linux/ioport.h>
+#include <linux/isa.h>
+#include <linux/module.h>
+
+#define WB_GPIO_DRIVER_NAME		KBUILD_MODNAME
+
+#define WB_SIO_BASE			0x2e
+#define WB_SIO_BASE_HIGH		0x4e
+
+#define WB_SIO_EXT_ENTER_KEY		0x87
+#define WB_SIO_EXT_EXIT_KEY		0xaa
+
+/* global chip registers */
+
+#define WB_SIO_REG_LOGICAL		0x07
+
+#define WB_SIO_REG_CHIP_MSB		0x20
+#define WB_SIO_REG_CHIP_LSB		0x21
+
+#define WB_SIO_CHIP_ID_W83627UHG	0xa230
+#define WB_SIO_CHIP_ID_W83627UHG_MASK	GENMASK(15, 4)
+
+#define WB_SIO_REG_DPD			0x22
+#define WB_SIO_REG_DPD_UARTA		4
+#define WB_SIO_REG_DPD_UARTB		5
+
+#define WB_SIO_REG_IDPD		0x23
+#define WB_SIO_REG_IDPD_UARTC		4
+#define WB_SIO_REG_IDPD_UARTD		5
+#define WB_SIO_REG_IDPD_UARTE		6
+#define WB_SIO_REG_IDPD_UARTF		7
+
+#define WB_SIO_REG_GLOBAL_OPT		0x24
+#define WB_SIO_REG_GO_ENFDC		1
+
+#define WB_SIO_REG_OVTGPIO3456		0x29
+#define WB_SIO_REG_OG3456_G3PP		3
+#define WB_SIO_REG_OG3456_G4PP		4
+#define WB_SIO_REG_OG3456_G5PP		5
+#define WB_SIO_REG_OG3456_G6PP		7
+
+#define WB_SIO_REG_I2C_PS		0x2a
+#define WB_SIO_REG_I2CPS_I2CFS		1
+
+#define WB_SIO_REG_GPIO1_MF		0x2c
+#define WB_SIO_REG_G1MF_G1PP		6
+#define WB_SIO_REG_G1MF_G2PP		7
+#define WB_SIO_REG_G1MF_FS_MASK	GENMASK(1, 0)
+#define WB_SIO_REG_G1MF_FS_IR_OFF	0
+#define WB_SIO_REG_G1MF_FS_IR		1
+#define WB_SIO_REG_G1MF_FS_GPIO1	2
+#define WB_SIO_REG_G1MF_FS_UARTB	3
+
+/* not an actual device number, just a value meaning 'no device' */
+#define WB_SIO_DEV_NONE		0xff
+
+/* registers with offsets >= 0x30 are specific for a particular device */
+
+/* UART B logical device */
+#define WB_SIO_DEV_UARTB		0x03
+#define WB_SIO_UARTB_REG_ENABLE	0x30
+#define WB_SIO_UARTB_ENABLE_ON		0
+
+/* UART C logical device */
+#define WB_SIO_DEV_UARTC		0x06
+#define WB_SIO_UARTC_REG_ENABLE	0x30
+#define WB_SIO_UARTC_ENABLE_ON		0
+
+/* GPIO3, GPIO4 logical device */
+#define WB_SIO_DEV_GPIO34		0x07
+#define WB_SIO_GPIO34_REG_ENABLE	0x30
+#define WB_SIO_GPIO34_ENABLE_3		0
+#define WB_SIO_GPIO34_ENABLE_4		1
+#define WB_SIO_GPIO34_REG_IO3		0xe0
+#define WB_SIO_GPIO34_REG_DATA3	0xe1
+#define WB_SIO_GPIO34_REG_INV3		0xe2
+#define WB_SIO_GPIO34_REG_IO4		0xe4
+#define WB_SIO_GPIO34_REG_DATA4	0xe5
+#define WB_SIO_GPIO34_REG_INV4		0xe6
+
+/* WDTO, PLED, GPIO5, GPIO6 logical device */
+#define WB_SIO_DEV_WDGPIO56		0x08
+#define WB_SIO_WDGPIO56_REG_ENABLE	0x30
+#define WB_SIO_WDGPIO56_ENABLE_5	1
+#define WB_SIO_WDGPIO56_ENABLE_6	2
+#define WB_SIO_WDGPIO56_REG_IO5	0xe0
+#define WB_SIO_WDGPIO56_REG_DATA5	0xe1
+#define WB_SIO_WDGPIO56_REG_INV5	0xe2
+#define WB_SIO_WDGPIO56_REG_IO6	0xe4
+#define WB_SIO_WDGPIO56_REG_DATA6	0xe5
+#define WB_SIO_WDGPIO56_REG_INV6	0xe6
+
+/* GPIO1, GPIO2, SUSLED logical device */
+#define WB_SIO_DEV_GPIO12		0x09
+#define WB_SIO_GPIO12_REG_ENABLE	0x30
+#define WB_SIO_GPIO12_ENABLE_1		0
+#define WB_SIO_GPIO12_ENABLE_2		1
+#define WB_SIO_GPIO12_REG_IO1		0xe0
+#define WB_SIO_GPIO12_REG_DATA1	0xe1
+#define WB_SIO_GPIO12_REG_INV1		0xe2
+#define WB_SIO_GPIO12_REG_IO2		0xe4
+#define WB_SIO_GPIO12_REG_DATA2	0xe5
+#define WB_SIO_GPIO12_REG_INV2		0xe6
+
+/* UART D logical device */
+#define WB_SIO_DEV_UARTD		0x0d
+#define WB_SIO_UARTD_REG_ENABLE	0x30
+#define WB_SIO_UARTD_ENABLE_ON		0
+
+/* UART E logical device */
+#define WB_SIO_DEV_UARTE		0x0e
+#define WB_SIO_UARTE_REG_ENABLE	0x30
+#define WB_SIO_UARTE_ENABLE_ON		0
+
+/*
+ * for a description what a particular field of this struct means please see
+ * a description of the relevant module parameter at the bottom of this file
+ */
+struct winbond_gpio_params {
+	unsigned long base;
+	unsigned long gpios;
+	unsigned long ppgpios;
+	unsigned long odgpios;
+	bool pledgpio;
+	bool beepgpio;
+	bool i2cgpio;
+};
+
+static struct winbond_gpio_params params;
+
+static int winbond_sio_enter(unsigned long base)
+{
+	if (!request_muxed_region(base, 2, WB_GPIO_DRIVER_NAME))
+		return -EBUSY;
+
+	/*
+	 * datasheet says two successive writes of the "key" value are needed
+	 * in order for chip to enter the "Extended Function Mode"
+	 */
+	outb(WB_SIO_EXT_ENTER_KEY, base);
+	outb(WB_SIO_EXT_ENTER_KEY, base);
+
+	return 0;
+}
+
+static void winbond_sio_select_logical(unsigned long base, u8 dev)
+{
+	outb(WB_SIO_REG_LOGICAL, base);
+	outb(dev, base + 1);
+}
+
+static void winbond_sio_leave(unsigned long base)
+{
+	outb(WB_SIO_EXT_EXIT_KEY, base);
+
+	release_region(base, 2);
+}
+
+static void winbond_sio_reg_write(unsigned long base, u8 reg, u8 data)
+{
+	outb(reg, base);
+	outb(data, base + 1);
+}
+
+static u8 winbond_sio_reg_read(unsigned long base, u8 reg)
+{
+	outb(reg, base);
+	return inb(base + 1);
+}
+
+static void winbond_sio_reg_bset(unsigned long base, u8 reg, u8 bit)
+{
+	u8 val;
+
+	val = winbond_sio_reg_read(base, reg);
+	val |= BIT(bit);
+	winbond_sio_reg_write(base, reg, val);
+}
+
+static void winbond_sio_reg_bclear(unsigned long base, u8 reg, u8 bit)
+{
+	u8 val;
+
+	val = winbond_sio_reg_read(base, reg);
+	val &= ~BIT(bit);
+	winbond_sio_reg_write(base, reg, val);
+}
+
+static bool winbond_sio_reg_btest(unsigned long base, u8 reg, u8 bit)
+{
+	return winbond_sio_reg_read(base, reg) & BIT(bit);
+}
+
+/**
+ * struct winbond_gpio_port_conflict - possibly conflicting device information
+ * @name:	device name (NULL means no conflicting device defined)
+ * @dev:	Super I/O logical device number where the testreg register
+ *		is located (or WB_SIO_DEV_NONE - don't select any
+ *		logical device)
+ * @testreg:	register number where the testbit bit is located
+ * @testbit:	index of a bit to check whether an actual conflict exists
+ * @warnonly:	if set then a conflict isn't fatal (just warn about it),
+ *		otherwise disable the particular GPIO port if a conflict
+ *		is detected
+ */
+struct winbond_gpio_port_conflict {
+	const char *name;
+	u8 dev;
+	u8 testreg;
+	u8 testbit;
+	bool warnonly;
+};
+
+/**
+ * struct winbond_gpio_info - information about a particular GPIO port (device)
+ * @dev:		Super I/O logical device number of the registers
+ *			specified below
+ * @enablereg:		port enable bit register number
+ * @enablebit:		index of a port enable bit
+ * @outputreg:		output driver mode bit register number
+ * @outputppbit:	index of a push-pull output driver mode bit
+ * @ioreg:		data direction register number
+ * @invreg:		pin data inversion register number
+ * @datareg:		pin data register number
+ * @conflict:		description of a device that possibly conflicts with
+ *			this port
+ */
+struct winbond_gpio_info {
+	u8 dev;
+	u8 enablereg;
+	u8 enablebit;
+	u8 outputreg;
+	u8 outputppbit;
+	u8 ioreg;
+	u8 invreg;
+	u8 datareg;
+	struct winbond_gpio_port_conflict conflict;
+};
+
+static const struct winbond_gpio_info winbond_gpio_infos[6] = {
+	{ /* 0 */
+		.dev = WB_SIO_DEV_GPIO12,
+		.enablereg = WB_SIO_GPIO12_REG_ENABLE,
+		.enablebit = WB_SIO_GPIO12_ENABLE_1,
+		.outputreg = WB_SIO_REG_GPIO1_MF,
+		.outputppbit = WB_SIO_REG_G1MF_G1PP,
+		.ioreg = WB_SIO_GPIO12_REG_IO1,
+		.invreg = WB_SIO_GPIO12_REG_INV1,
+		.datareg = WB_SIO_GPIO12_REG_DATA1,
+		.conflict = {
+			.name = "UARTB",
+			.dev = WB_SIO_DEV_UARTB,
+			.testreg = WB_SIO_UARTB_REG_ENABLE,
+			.testbit = WB_SIO_UARTB_ENABLE_ON,
+			.warnonly = true
+		}
+	},
+	{ /* 1 */
+		.dev = WB_SIO_DEV_GPIO12,
+		.enablereg = WB_SIO_GPIO12_REG_ENABLE,
+		.enablebit = WB_SIO_GPIO12_ENABLE_2,
+		.outputreg = WB_SIO_REG_GPIO1_MF,
+		.outputppbit = WB_SIO_REG_G1MF_G2PP,
+		.ioreg = WB_SIO_GPIO12_REG_IO2,
+		.invreg = WB_SIO_GPIO12_REG_INV2,
+		.datareg = WB_SIO_GPIO12_REG_DATA2
+		/* special conflict handling so doesn't use conflict data */
+	},
+	{ /* 2 */
+		.dev = WB_SIO_DEV_GPIO34,
+		.enablereg = WB_SIO_GPIO34_REG_ENABLE,
+		.enablebit = WB_SIO_GPIO34_ENABLE_3,
+		.outputreg = WB_SIO_REG_OVTGPIO3456,
+		.outputppbit = WB_SIO_REG_OG3456_G3PP,
+		.ioreg = WB_SIO_GPIO34_REG_IO3,
+		.invreg = WB_SIO_GPIO34_REG_INV3,
+		.datareg = WB_SIO_GPIO34_REG_DATA3,
+		.conflict = {
+			.name = "UARTC",
+			.dev = WB_SIO_DEV_UARTC,
+			.testreg = WB_SIO_UARTC_REG_ENABLE,
+			.testbit = WB_SIO_UARTC_ENABLE_ON,
+			.warnonly = true
+		}
+	},
+	{ /* 3 */
+		.dev = WB_SIO_DEV_GPIO34,
+		.enablereg = WB_SIO_GPIO34_REG_ENABLE,
+		.enablebit = WB_SIO_GPIO34_ENABLE_4,
+		.outputreg = WB_SIO_REG_OVTGPIO3456,
+		.outputppbit = WB_SIO_REG_OG3456_G4PP,
+		.ioreg = WB_SIO_GPIO34_REG_IO4,
+		.invreg = WB_SIO_GPIO34_REG_INV4,
+		.datareg = WB_SIO_GPIO34_REG_DATA4,
+		.conflict = {
+			.name = "UARTD",
+			.dev = WB_SIO_DEV_UARTD,
+			.testreg = WB_SIO_UARTD_REG_ENABLE,
+			.testbit = WB_SIO_UARTD_ENABLE_ON,
+			.warnonly = true
+		}
+	},
+	{ /* 4 */
+		.dev = WB_SIO_DEV_WDGPIO56,
+		.enablereg = WB_SIO_WDGPIO56_REG_ENABLE,
+		.enablebit = WB_SIO_WDGPIO56_ENABLE_5,
+		.outputreg = WB_SIO_REG_OVTGPIO3456,
+		.outputppbit = WB_SIO_REG_OG3456_G5PP,
+		.ioreg = WB_SIO_WDGPIO56_REG_IO5,
+		.invreg = WB_SIO_WDGPIO56_REG_INV5,
+		.datareg = WB_SIO_WDGPIO56_REG_DATA5,
+		.conflict = {
+			.name = "UARTE",
+			.dev = WB_SIO_DEV_UARTE,
+			.testreg = WB_SIO_UARTE_REG_ENABLE,
+			.testbit = WB_SIO_UARTE_ENABLE_ON,
+			.warnonly = true
+		}
+	},
+	{ /* 5 */
+		.dev = WB_SIO_DEV_WDGPIO56,
+		.enablereg = WB_SIO_WDGPIO56_REG_ENABLE,
+		.enablebit = WB_SIO_WDGPIO56_ENABLE_6,
+		.outputreg = WB_SIO_REG_OVTGPIO3456,
+		.outputppbit = WB_SIO_REG_OG3456_G6PP,
+		.ioreg = WB_SIO_WDGPIO56_REG_IO6,
+		.invreg = WB_SIO_WDGPIO56_REG_INV6,
+		.datareg = WB_SIO_WDGPIO56_REG_DATA6,
+		.conflict = {
+			.name = "FDC",
+			.dev = WB_SIO_DEV_NONE,
+			.testreg = WB_SIO_REG_GLOBAL_OPT,
+			.testbit = WB_SIO_REG_GO_ENFDC,
+			.warnonly = false
+		}
+	}
+};
+
+/* returns whether changing a pin is allowed */
+static bool winbond_gpio_get_info(unsigned int *gpio_num,
+				  const struct winbond_gpio_info **info)
+{
+	bool allow_changing = true;
+	unsigned long i;
+
+	for_each_set_bit(i, &params.gpios, BITS_PER_LONG) {
+		if (*gpio_num < 8)
+			break;
+
+		*gpio_num -= 8;
+	}
+
+	*info = &winbond_gpio_infos[i];
+
+	/*
+	 * GPIO2 (the second port) shares some pins with a basic PC
+	 * functionality, which is very likely controlled by the firmware.
+	 * Don't allow changing these pins by default.
+	 */
+	if (i == 1) {
+		if (*gpio_num == 0 && !params.pledgpio)
+			allow_changing = false;
+		else if (*gpio_num == 1 && !params.beepgpio)
+			allow_changing = false;
+		else if ((*gpio_num == 5 || *gpio_num == 6) && !params.i2cgpio)
+			allow_changing = false;
+	}
+
+	return allow_changing;
+}
+
+static int winbond_gpio_get(struct gpio_chip *gc, unsigned int offset)
+{
+	unsigned long *base = gpiochip_get_data(gc);
+	const struct winbond_gpio_info *info;
+	bool val;
+
+	winbond_gpio_get_info(&offset, &info);
+
+	val = winbond_sio_enter(*base);
+	if (val)
+		return val;
+
+	winbond_sio_select_logical(*base, info->dev);
+
+	val = winbond_sio_reg_btest(*base, info->datareg, offset);
+	if (winbond_sio_reg_btest(*base, info->invreg, offset))
+		val = !val;
+
+	winbond_sio_leave(*base);
+
+	return val;
+}
+
+static int winbond_gpio_direction_in(struct gpio_chip *gc, unsigned int offset)
+{
+	unsigned long *base = gpiochip_get_data(gc);
+	const struct winbond_gpio_info *info;
+	int ret;
+
+	if (!winbond_gpio_get_info(&offset, &info))
+		return -EACCES;
+
+	ret = winbond_sio_enter(*base);
+	if (ret)
+		return ret;
+
+	winbond_sio_select_logical(*base, info->dev);
+
+	winbond_sio_reg_bset(*base, info->ioreg, offset);
+
+	winbond_sio_leave(*base);
+
+	return 0;
+}
+
+static int winbond_gpio_direction_out(struct gpio_chip *gc,
+				      unsigned int offset,
+				      int val)
+{
+	unsigned long *base = gpiochip_get_data(gc);
+	const struct winbond_gpio_info *info;
+	int ret;
+
+	if (!winbond_gpio_get_info(&offset, &info))
+		return -EACCES;
+
+	ret = winbond_sio_enter(*base);
+	if (ret)
+		return ret;
+
+	winbond_sio_select_logical(*base, info->dev);
+
+	winbond_sio_reg_bclear(*base, info->ioreg, offset);
+
+	if (winbond_sio_reg_btest(*base, info->invreg, offset))
+		val = !val;
+
+	if (val)
+		winbond_sio_reg_bset(*base, info->datareg, offset);
+	else
+		winbond_sio_reg_bclear(*base, info->datareg, offset);
+
+	winbond_sio_leave(*base);
+
+	return 0;
+}
+
+static void winbond_gpio_set(struct gpio_chip *gc, unsigned int offset,
+			     int val)
+{
+	unsigned long *base = gpiochip_get_data(gc);
+	const struct winbond_gpio_info *info;
+
+	if (!winbond_gpio_get_info(&offset, &info))
+		return;
+
+	if (winbond_sio_enter(*base) != 0)
+		return;
+
+	winbond_sio_select_logical(*base, info->dev);
+
+	if (winbond_sio_reg_btest(*base, info->invreg, offset))
+		val = !val;
+
+	if (val)
+		winbond_sio_reg_bset(*base, info->datareg, offset);
+	else
+		winbond_sio_reg_bclear(*base, info->datareg, offset);
+
+	winbond_sio_leave(*base);
+}
+
+static struct gpio_chip winbond_gpio_chip = {
+	.base			= -1,
+	.label			= WB_GPIO_DRIVER_NAME,
+	.owner			= THIS_MODULE,
+	.can_sleep		= true,
+	.get			= winbond_gpio_get,
+	.direction_input	= winbond_gpio_direction_in,
+	.set			= winbond_gpio_set,
+	.direction_output	= winbond_gpio_direction_out,
+};
+
+static void winbond_gpio_configure_port0_pins(unsigned long base)
+{
+	unsigned int val;
+
+	val = winbond_sio_reg_read(base, WB_SIO_REG_GPIO1_MF);
+	if ((val & WB_SIO_REG_G1MF_FS_MASK) == WB_SIO_REG_G1MF_FS_GPIO1)
+		return;
+
+	pr_warn("GPIO1 pins were connected to something else (%.2x), fixing\n",
+		val);
+
+	val &= ~WB_SIO_REG_G1MF_FS_MASK;
+	val |= WB_SIO_REG_G1MF_FS_GPIO1;
+
+	winbond_sio_reg_write(base, WB_SIO_REG_GPIO1_MF, val);
+}
+
+static void winbond_gpio_configure_port1_check_i2c(unsigned long base)
+{
+	params.i2cgpio = !winbond_sio_reg_btest(base, WB_SIO_REG_I2C_PS,
+						WB_SIO_REG_I2CPS_I2CFS);
+	if (!params.i2cgpio)
+		pr_warn("disabling GPIO2.5 and GPIO2.6 as I2C is enabled\n");
+}
+
+static bool winbond_gpio_configure_port(unsigned long base, unsigned int idx)
+{
+	const struct winbond_gpio_info *info = &winbond_gpio_infos[idx];
+	const struct winbond_gpio_port_conflict *conflict = &info->conflict;
+
+	/* is there a possible conflicting device defined? */
+	if (conflict->name != NULL) {
+		if (conflict->dev != WB_SIO_DEV_NONE)
+			winbond_sio_select_logical(base, conflict->dev);
+
+		if (winbond_sio_reg_btest(base, conflict->testreg,
+					  conflict->testbit)) {
+			if (conflict->warnonly)
+				pr_warn("enabled GPIO%u share pins with active %s\n",
+					idx + 1, conflict->name);
+			else {
+				pr_warn("disabling GPIO%u as %s is enabled\n",
+					idx + 1, conflict->name);
+				return false;
+			}
+		}
+	}
+
+	/* GPIO1 and GPIO2 need some (additional) special handling */
+	if (idx == 0)
+		winbond_gpio_configure_port0_pins(base);
+	else if (idx == 1)
+		winbond_gpio_configure_port1_check_i2c(base);
+
+	winbond_sio_select_logical(base, info->dev);
+
+	winbond_sio_reg_bset(base, info->enablereg, info->enablebit);
+
+	if (params.ppgpios & BIT(idx))
+		winbond_sio_reg_bset(base, info->outputreg,
+				     info->outputppbit);
+	else if (params.odgpios & BIT(idx))
+		winbond_sio_reg_bclear(base, info->outputreg,
+				       info->outputppbit);
+	else
+		pr_notice("GPIO%u pins are %s\n", idx + 1,
+			  winbond_sio_reg_btest(base, info->outputreg,
+						info->outputppbit) ?
+			  "push-pull" :
+			  "open drain");
+
+	return true;
+}
+
+static int winbond_gpio_configure(unsigned long base)
+{
+	unsigned long i;
+
+	for_each_set_bit(i, &params.gpios, BITS_PER_LONG)
+		if (!winbond_gpio_configure_port(base, i))
+			__clear_bit(i, &params.gpios);
+
+	if (!params.gpios) {
+		pr_err("please use 'gpios' module parameter to select some active GPIO ports to enable\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int winbond_gpio_check_chip(unsigned long base)
+{
+	int ret;
+	unsigned int chip;
+
+	ret = winbond_sio_enter(base);
+	if (ret)
+		return ret;
+
+	chip = winbond_sio_reg_read(base, WB_SIO_REG_CHIP_MSB) << 8;
+	chip |= winbond_sio_reg_read(base, WB_SIO_REG_CHIP_LSB);
+
+	pr_notice("chip ID at %lx is %.4x\n", base, chip);
+
+	if ((chip & WB_SIO_CHIP_ID_W83627UHG_MASK) !=
+	    WB_SIO_CHIP_ID_W83627UHG) {
+		pr_err("not an our chip\n");
+		ret = -ENODEV;
+	}
+
+	winbond_sio_leave(base);
+
+	return ret;
+}
+
+static int winbond_gpio_imatch(struct device *dev, unsigned int id)
+{
+	unsigned long gpios_rem;
+	int ret;
+
+	gpios_rem = params.gpios & ~GENMASK(ARRAY_SIZE(winbond_gpio_infos) - 1,
+					    0);
+	if (gpios_rem) {
+		pr_warn("unknown ports (%lx) enabled in GPIO ports bitmask\n",
+			gpios_rem);
+		params.gpios &= ~gpios_rem;
+	}
+
+	if (params.ppgpios & params.odgpios) {
+		pr_err("some GPIO ports are set both to push-pull and open drain mode at the same time\n");
+		return 0;
+	}
+
+	if (params.base != 0)
+		return winbond_gpio_check_chip(params.base) == 0;
+
+	/*
+	 * if the 'base' module parameter is unset probe two chip default
+	 * I/O port bases
+	 */
+	params.base = WB_SIO_BASE;
+	ret = winbond_gpio_check_chip(params.base);
+	if (ret == 0)
+		return 1;
+	if (ret != -ENODEV && ret != -EBUSY)
+		return 0;
+
+	params.base = WB_SIO_BASE_HIGH;
+	return winbond_gpio_check_chip(params.base) == 0;
+}
+
+static int winbond_gpio_iprobe(struct device *dev, unsigned int id)
+{
+	int ret;
+
+	if (params.base == 0)
+		return -EINVAL;
+
+	ret = winbond_sio_enter(params.base);
+	if (ret)
+		return ret;
+
+	ret = winbond_gpio_configure(params.base);
+
+	winbond_sio_leave(params.base);
+
+	if (ret)
+		return ret;
+
+	/*
+	 * Add 8 gpios for every GPIO port that was enabled in gpios
+	 * module parameter (that wasn't disabled earlier in
+	 * winbond_gpio_configure() & co. due to, for example, a pin conflict).
+	 */
+	winbond_gpio_chip.ngpio = hweight_long(params.gpios) * 8;
+
+	/*
+	 * GPIO6 port has only 5 pins, so if it is enabled we have to adjust
+	 * the total count appropriately
+	 */
+	if (params.gpios & BIT(5))
+		winbond_gpio_chip.ngpio -= (8 - 5);
+
+	winbond_gpio_chip.parent = dev;
+
+	return devm_gpiochip_add_data(dev, &winbond_gpio_chip, &params.base);
+}
+
+static struct isa_driver winbond_gpio_idriver = {
+	.driver = {
+		.name	= WB_GPIO_DRIVER_NAME,
+	},
+	.match	= winbond_gpio_imatch,
+	.probe	= winbond_gpio_iprobe,
+};
+
+module_isa_driver(winbond_gpio_idriver, 1);
+
+module_param_named(base, params.base, ulong, 0444);
+MODULE_PARM_DESC(base,
+		 "I/O port base (when unset - probe chip default ones)");
+
+/* This parameter sets which GPIO devices (ports) we enable */
+module_param_named(gpios, params.gpios, ulong, 0444);
+MODULE_PARM_DESC(gpios,
+		 "bitmask of GPIO ports to enable (bit 0 - GPIO1, bit 1 - GPIO2, etc.");
+
+/*
+ * These two parameters below set how we configure GPIO ports output drivers.
+ * It can't be a one bitmask since we need three values per port: push-pull,
+ * open-drain and keep as-is (this is the default).
+ */
+module_param_named(ppgpios, params.ppgpios, ulong, 0444);
+MODULE_PARM_DESC(ppgpios,
+		 "bitmask of GPIO ports to set to push-pull mode (bit 0 - GPIO1, bit 1 - GPIO2, etc.");
+
+module_param_named(odgpios, params.odgpios, ulong, 0444);
+MODULE_PARM_DESC(odgpios,
+		 "bitmask of GPIO ports to set to open drain mode (bit 0 - GPIO1, bit 1 - GPIO2, etc.");
+
+/*
+ * GPIO2.0 and GPIO2.1 control a basic PC functionality that we
+ * don't allow tinkering with by default (it is very likely that the
+ * firmware owns these pins).
+ * These two parameters below allow overriding these prohibitions.
+ */
+module_param_named(pledgpio, params.pledgpio, bool, 0644);
+MODULE_PARM_DESC(pledgpio,
+		 "enable changing value of GPIO2.0 bit (Power LED), default no.");
+
+module_param_named(beepgpio, params.beepgpio, bool, 0644);
+MODULE_PARM_DESC(beepgpio,
+		 "enable changing value of GPIO2.1 bit (BEEP), default no.");
+
+MODULE_AUTHOR("Maciej S. Szmigiero <mail@maciej.szmigiero.name>");
+MODULE_DESCRIPTION("GPIO interface for Winbond Super I/O chips");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpio/gpio-xgene-sb.c b/drivers/gpio/gpio-xgene-sb.c
index 2313af82fad3..acd59113e08b 100644
--- a/drivers/gpio/gpio-xgene-sb.c
+++ b/drivers/gpio/gpio-xgene-sb.c
@@ -139,7 +139,7 @@ static int xgene_gpio_sb_to_irq(struct gpio_chip *gc, u32 gpio)
 
 static int xgene_gpio_sb_domain_activate(struct irq_domain *d,
 					 struct irq_data *irq_data,
-					 bool early)
+					 bool reserve)
 {
 	struct xgene_gpio_sb *priv = d->host_data;
 	u32 gpio = HWIRQ_TO_GPIO(priv, irq_data->hwirq);
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index eb4528c87c0b..0ecffd172a80 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -414,7 +414,8 @@ EXPORT_SYMBOL_GPL(devm_acpi_dev_remove_driver_gpios);
 
 static bool acpi_get_driver_gpio_data(struct acpi_device *adev,
 				      const char *name, int index,
-				      struct acpi_reference_args *args)
+				      struct acpi_reference_args *args,
+				      unsigned int *quirks)
 {
 	const struct acpi_gpio_mapping *gm;
 
@@ -430,6 +431,8 @@ static bool acpi_get_driver_gpio_data(struct acpi_device *adev,
 			args->args[1] = par->line_index;
 			args->args[2] = par->active_low;
 			args->nargs = 3;
+
+			*quirks = gm->quirks;
 			return true;
 		}
 
@@ -461,8 +464,8 @@ acpi_gpio_to_gpiod_flags(const struct acpi_resource_gpio *agpio)
 	}
 }
 
-int
-acpi_gpio_update_gpiod_flags(enum gpiod_flags *flags, enum gpiod_flags update)
+static int
+__acpi_gpio_update_gpiod_flags(enum gpiod_flags *flags, enum gpiod_flags update)
 {
 	int ret = 0;
 
@@ -489,12 +492,31 @@ acpi_gpio_update_gpiod_flags(enum gpiod_flags *flags, enum gpiod_flags update)
 	return ret;
 }
 
+int
+acpi_gpio_update_gpiod_flags(enum gpiod_flags *flags, struct acpi_gpio_info *info)
+{
+	struct device *dev = &info->adev->dev;
+	enum gpiod_flags old = *flags;
+	int ret;
+
+	ret = __acpi_gpio_update_gpiod_flags(&old, info->flags);
+	if (info->quirks & ACPI_GPIO_QUIRK_NO_IO_RESTRICTION) {
+		if (ret)
+			dev_warn(dev, FW_BUG "GPIO not in correct mode, fixing\n");
+	} else {
+		if (ret)
+			dev_dbg(dev, "Override GPIO initialization flags\n");
+		*flags = old;
+	}
+
+	return ret;
+}
+
 struct acpi_gpio_lookup {
 	struct acpi_gpio_info info;
 	int index;
 	int pin_index;
 	bool active_low;
-	struct acpi_device *adev;
 	struct gpio_desc *desc;
 	int n;
 };
@@ -531,8 +553,8 @@ static int acpi_populate_gpio_lookup(struct acpi_resource *ares, void *data)
 			lookup->info.triggering = agpio->triggering;
 		} else {
 			lookup->info.flags = acpi_gpio_to_gpiod_flags(agpio);
+			lookup->info.polarity = lookup->active_low;
 		}
-
 	}
 
 	return 1;
@@ -541,12 +563,13 @@ static int acpi_populate_gpio_lookup(struct acpi_resource *ares, void *data)
 static int acpi_gpio_resource_lookup(struct acpi_gpio_lookup *lookup,
 				     struct acpi_gpio_info *info)
 {
+	struct acpi_device *adev = lookup->info.adev;
 	struct list_head res_list;
 	int ret;
 
 	INIT_LIST_HEAD(&res_list);
 
-	ret = acpi_dev_get_resources(lookup->adev, &res_list,
+	ret = acpi_dev_get_resources(adev, &res_list,
 				     acpi_populate_gpio_lookup,
 				     lookup);
 	if (ret < 0)
@@ -557,11 +580,8 @@ static int acpi_gpio_resource_lookup(struct acpi_gpio_lookup *lookup,
 	if (!lookup->desc)
 		return -ENOENT;
 
-	if (info) {
+	if (info)
 		*info = lookup->info;
-		if (lookup->active_low)
-			info->polarity = lookup->active_low;
-	}
 	return 0;
 }
 
@@ -570,6 +590,7 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 				     struct acpi_gpio_lookup *lookup)
 {
 	struct acpi_reference_args args;
+	unsigned int quirks = 0;
 	int ret;
 
 	memset(&args, 0, sizeof(args));
@@ -581,14 +602,14 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 		if (!adev)
 			return ret;
 
-		if (!acpi_get_driver_gpio_data(adev, propname, index, &args))
+		if (!acpi_get_driver_gpio_data(adev, propname, index, &args,
+					       &quirks))
 			return ret;
 	}
 	/*
 	 * The property was found and resolved, so need to lookup the GPIO based
 	 * on returned args.
 	 */
-	lookup->adev = args.adev;
 	if (args.nargs != 3)
 		return -EPROTO;
 
@@ -596,6 +617,8 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 	lookup->pin_index = args.args[1];
 	lookup->active_low = !!args.args[2];
 
+	lookup->info.adev = args.adev;
+	lookup->info.quirks = quirks;
 	return 0;
 }
 
@@ -643,11 +666,11 @@ static struct gpio_desc *acpi_get_gpiod_by_index(struct acpi_device *adev,
 			return ERR_PTR(ret);
 
 		dev_dbg(&adev->dev, "GPIO: _DSD returned %s %d %d %u\n",
-			dev_name(&lookup.adev->dev), lookup.index,
+			dev_name(&lookup.info.adev->dev), lookup.index,
 			lookup.pin_index, lookup.active_low);
 	} else {
 		dev_dbg(&adev->dev, "GPIO: looking up %d in _CRS\n", index);
-		lookup.adev = adev;
+		lookup.info.adev = adev;
 	}
 
 	ret = acpi_gpio_resource_lookup(&lookup, info);
@@ -664,7 +687,6 @@ struct gpio_desc *acpi_find_gpio(struct device *dev,
 	struct acpi_gpio_info info;
 	struct gpio_desc *desc;
 	char propname[32];
-	int err;
 	int i;
 
 	/* Try first from _DSD */
@@ -703,10 +725,7 @@ struct gpio_desc *acpi_find_gpio(struct device *dev,
 	if (info.polarity == GPIO_ACTIVE_LOW)
 		*lookupflags |= GPIO_ACTIVE_LOW;
 
-	err = acpi_gpio_update_gpiod_flags(dflags, info.flags);
-	if (err)
-		dev_dbg(dev, "Override GPIO initialization flags\n");
-
+	acpi_gpio_update_gpiod_flags(dflags, &info);
 	return desc;
 }
 
@@ -1074,7 +1093,7 @@ void acpi_gpiochip_add(struct gpio_chip *chip)
 	}
 
 	if (!chip->names)
-		devprop_gpiochip_set_names(chip);
+		devprop_gpiochip_set_names(chip, dev_fwnode(chip->parent));
 
 	acpi_gpiochip_request_regions(acpi_gpio);
 	acpi_gpiochip_scan_gpios(acpi_gpio);
diff --git a/drivers/gpio/gpiolib-devprop.c b/drivers/gpio/gpiolib-devprop.c
index 27f383bda7d9..f748aa3e77f7 100644
--- a/drivers/gpio/gpiolib-devprop.c
+++ b/drivers/gpio/gpiolib-devprop.c
@@ -19,30 +19,27 @@
 /**
  * devprop_gpiochip_set_names - Set GPIO line names using device properties
  * @chip: GPIO chip whose lines should be named, if possible
+ * @fwnode: Property Node containing the gpio-line-names property
  *
  * Looks for device property "gpio-line-names" and if it exists assigns
  * GPIO line names for the chip. The memory allocated for the assigned
  * names belong to the underlying firmware node and should not be released
  * by the caller.
  */
-void devprop_gpiochip_set_names(struct gpio_chip *chip)
+void devprop_gpiochip_set_names(struct gpio_chip *chip,
+				const struct fwnode_handle *fwnode)
 {
 	struct gpio_device *gdev = chip->gpiodev;
 	const char **names;
 	int ret, i;
 
-	if (!chip->parent) {
-		dev_warn(&gdev->dev, "GPIO chip parent is NULL\n");
-		return;
-	}
-
-	ret = device_property_read_string_array(chip->parent, "gpio-line-names",
+	ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
 						NULL, 0);
 	if (ret < 0)
 		return;
 
 	if (ret != gdev->ngpio) {
-		dev_warn(chip->parent,
+		dev_warn(&gdev->dev,
 			 "names %d do not match number of GPIOs %d\n", ret,
 			 gdev->ngpio);
 		return;
@@ -52,10 +49,10 @@ void devprop_gpiochip_set_names(struct gpio_chip *chip)
 	if (!names)
 		return;
 
-	ret = device_property_read_string_array(chip->parent, "gpio-line-names",
+	ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
 						names, gdev->ngpio);
 	if (ret < 0) {
-		dev_warn(chip->parent, "failed to read GPIO line names\n");
+		dev_warn(&gdev->dev, "failed to read GPIO line names\n");
 		kfree(names);
 		return;
 	}
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index e0d59e61b52f..564bb7a31da4 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -56,6 +56,42 @@ static struct gpio_desc *of_xlate_and_get_gpiod_flags(struct gpio_chip *chip,
 	return gpiochip_get_desc(chip, ret);
 }
 
+static void of_gpio_flags_quirks(struct device_node *np,
+				 enum of_gpio_flags *flags)
+{
+	/*
+	 * Some GPIO fixed regulator quirks.
+	 * Note that active low is the default.
+	 */
+	if (IS_ENABLED(CONFIG_REGULATOR) &&
+	    (of_device_is_compatible(np, "reg-fixed-voltage") ||
+	     of_device_is_compatible(np, "regulator-gpio"))) {
+		/*
+		 * The regulator GPIO handles are specified such that the
+		 * presence or absence of "enable-active-high" solely controls
+		 * the polarity of the GPIO line. Any phandle flags must
+		 * be actively ignored.
+		 */
+		if (*flags & OF_GPIO_ACTIVE_LOW) {
+			pr_warn("%s GPIO handle specifies active low - ignored\n",
+				of_node_full_name(np));
+			*flags &= ~OF_GPIO_ACTIVE_LOW;
+		}
+		if (!of_property_read_bool(np, "enable-active-high"))
+			*flags |= OF_GPIO_ACTIVE_LOW;
+	}
+	/*
+	 * Legacy open drain handling for fixed voltage regulators.
+	 */
+	if (IS_ENABLED(CONFIG_REGULATOR) &&
+	    of_device_is_compatible(np, "reg-fixed-voltage") &&
+	    of_property_read_bool(np, "gpio-open-drain")) {
+		*flags |= (OF_GPIO_SINGLE_ENDED | OF_GPIO_OPEN_DRAIN);
+		pr_info("%s uses legacy open drain flag - update the DTS if you can\n",
+			of_node_full_name(np));
+	}
+}
+
 /**
  * of_get_named_gpiod_flags() - Get a GPIO descriptor and flags for GPIO API
  * @np:		device node to get GPIO from
@@ -93,6 +129,9 @@ struct gpio_desc *of_get_named_gpiod_flags(struct device_node *np,
 	if (IS_ERR(desc))
 		goto out;
 
+	if (flags)
+		of_gpio_flags_quirks(np, flags);
+
 	pr_debug("%s: parsed '%s' property of node '%pOF[%d]' - status (%d)\n",
 		 __func__, propname, np, index,
 		 PTR_ERR_OR_ZERO(desc));
@@ -117,6 +156,71 @@ int of_get_named_gpio_flags(struct device_node *np, const char *list_name,
 }
 EXPORT_SYMBOL(of_get_named_gpio_flags);
 
+/*
+ * The SPI GPIO bindings happened before we managed to establish that GPIO
+ * properties should be named "foo-gpios" so we have this special kludge for
+ * them.
+ */
+static struct gpio_desc *of_find_spi_gpio(struct device *dev, const char *con_id,
+					  enum of_gpio_flags *of_flags)
+{
+	char prop_name[32]; /* 32 is max size of property name */
+	struct device_node *np = dev->of_node;
+	struct gpio_desc *desc;
+
+	/*
+	 * Hopefully the compiler stubs the rest of the function if this
+	 * is false.
+	 */
+	if (!IS_ENABLED(CONFIG_SPI_MASTER))
+		return ERR_PTR(-ENOENT);
+
+	/* Allow this specifically for "spi-gpio" devices */
+	if (!of_device_is_compatible(np, "spi-gpio") || !con_id)
+		return ERR_PTR(-ENOENT);
+
+	/* Will be "gpio-sck", "gpio-mosi" or "gpio-miso" */
+	snprintf(prop_name, sizeof(prop_name), "%s-%s", "gpio", con_id);
+
+	desc = of_get_named_gpiod_flags(np, prop_name, 0, of_flags);
+	return desc;
+}
+
+/*
+ * Some regulator bindings happened before we managed to establish that GPIO
+ * properties should be named "foo-gpios" so we have this special kludge for
+ * them.
+ */
+static struct gpio_desc *of_find_regulator_gpio(struct device *dev, const char *con_id,
+						enum of_gpio_flags *of_flags)
+{
+	/* These are the connection IDs we accept as legacy GPIO phandles */
+	const char *whitelist[] = {
+		"wlf,ldoena", /* Arizona */
+		"wlf,ldo1ena", /* WM8994 */
+		"wlf,ldo2ena", /* WM8994 */
+	};
+	struct device_node *np = dev->of_node;
+	struct gpio_desc *desc;
+	int i;
+
+	if (!IS_ENABLED(CONFIG_REGULATOR))
+		return ERR_PTR(-ENOENT);
+
+	if (!con_id)
+		return ERR_PTR(-ENOENT);
+
+	for (i = 0; i < ARRAY_SIZE(whitelist); i++)
+		if (!strcmp(con_id, whitelist[i]))
+			break;
+
+	if (i == ARRAY_SIZE(whitelist))
+		return ERR_PTR(-ENOENT);
+
+	desc = of_get_named_gpiod_flags(np, con_id, 0, of_flags);
+	return desc;
+}
+
 struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id,
 			       unsigned int idx,
 			       enum gpio_lookup_flags *flags)
@@ -126,6 +230,7 @@ struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id,
 	struct gpio_desc *desc;
 	unsigned int i;
 
+	/* Try GPIO property "foo-gpios" and "foo-gpio" */
 	for (i = 0; i < ARRAY_SIZE(gpio_suffixes); i++) {
 		if (con_id)
 			snprintf(prop_name, sizeof(prop_name), "%s-%s", con_id,
@@ -140,6 +245,14 @@ struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id,
 			break;
 	}
 
+	/* Special handling for SPI GPIOs if used */
+	if (IS_ERR(desc))
+		desc = of_find_spi_gpio(dev, con_id, &of_flags);
+
+	/* Special handling for regulator GPIOs if used */
+	if (IS_ERR(desc))
+		desc = of_find_regulator_gpio(dev, con_id, &of_flags);
+
 	if (IS_ERR(desc))
 		return desc;
 
@@ -153,8 +266,8 @@ struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id,
 			*flags |= GPIO_OPEN_SOURCE;
 	}
 
-	if (of_flags & OF_GPIO_SLEEP_MAY_LOSE_VALUE)
-		*flags |= GPIO_SLEEP_MAY_LOSE_VALUE;
+	if (of_flags & OF_GPIO_TRANSITORY)
+		*flags |= GPIO_TRANSITORY;
 
 	return desc;
 }
@@ -214,6 +327,8 @@ static struct gpio_desc *of_parse_own_gpio(struct device_node *np,
 
 	if (xlate_flags & OF_GPIO_ACTIVE_LOW)
 		*lflags |= GPIO_ACTIVE_LOW;
+	if (xlate_flags & OF_GPIO_TRANSITORY)
+		*lflags |= GPIO_TRANSITORY;
 
 	if (of_property_read_bool(np, "input"))
 		*dflags |= GPIOD_IN;
@@ -493,7 +608,8 @@ int of_gpiochip_add(struct gpio_chip *chip)
 
 	/* If the chip defines names itself, these take precedence */
 	if (!chip->names)
-		devprop_gpiochip_set_names(chip);
+		devprop_gpiochip_set_names(chip,
+					   of_fwnode_handle(chip->of_node));
 
 	of_node_get(chip->of_node);
 
diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index 3f454eaf2101..3dbaf489a8a5 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -8,6 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/kdev_t.h>
 #include <linux/slab.h>
+#include <linux/ctype.h>
 
 #include "gpiolib.h"
 
@@ -106,8 +107,14 @@ static ssize_t value_show(struct device *dev,
 
 	mutex_lock(&data->mutex);
 
-	status = sprintf(buf, "%d\n", gpiod_get_value_cansleep(desc));
+	status = gpiod_get_value_cansleep(desc);
+	if (status < 0)
+		goto err;
 
+	buf[0] = '0' + status;
+	buf[1] = '\n';
+	status = 2;
+err:
 	mutex_unlock(&data->mutex);
 
 	return status;
@@ -118,7 +125,7 @@ static ssize_t value_store(struct device *dev,
 {
 	struct gpiod_data *data = dev_get_drvdata(dev);
 	struct gpio_desc *desc = data->desc;
-	ssize_t			status;
+	ssize_t status = 0;
 
 	mutex_lock(&data->mutex);
 
@@ -127,7 +134,11 @@ static ssize_t value_store(struct device *dev,
 	} else {
 		long		value;
 
-		status = kstrtol(buf, 0, &value);
+		if (size <= 2 && isdigit(buf[0]) &&
+		    (size == 1 || buf[1] == '\n'))
+			value = buf[0] - '0';
+		else
+			status = kstrtol(buf, 0, &value);
 		if (status == 0) {
 			gpiod_set_value_cansleep(desc, value);
 			status = size;
@@ -138,7 +149,7 @@ static ssize_t value_store(struct device *dev,
 
 	return status;
 }
-static DEVICE_ATTR_RW(value);
+static DEVICE_ATTR_PREALLOC(value, S_IWUSR | S_IRUGO, value_show, value_store);
 
 static irqreturn_t gpio_sysfs_irq(int irq, void *priv)
 {
@@ -474,11 +485,15 @@ static ssize_t export_store(struct class *class,
 			status = -ENODEV;
 		goto done;
 	}
-	status = gpiod_export(desc, true);
-	if (status < 0)
-		gpiod_free(desc);
-	else
-		set_bit(FLAG_SYSFS, &desc->flags);
+
+	status = gpiod_set_transitory(desc, false);
+	if (!status) {
+		status = gpiod_export(desc, true);
+		if (status < 0)
+			gpiod_free(desc);
+		else
+			set_bit(FLAG_SYSFS, &desc->flags);
+	}
 
 done:
 	if (status)
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index aad84a6306c4..36ca5064486e 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -73,7 +73,8 @@ LIST_HEAD(gpio_devices);
 
 static void gpiochip_free_hogs(struct gpio_chip *chip);
 static int gpiochip_add_irqchip(struct gpio_chip *gpiochip,
-				struct lock_class_key *key);
+				struct lock_class_key *lock_key,
+				struct lock_class_key *request_key);
 static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
 static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gpiochip);
 static void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gpiochip);
@@ -161,7 +162,7 @@ EXPORT_SYMBOL_GPL(desc_to_gpio);
  */
 struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
 {
-	if (!desc || !desc->gdev || !desc->gdev->chip)
+	if (!desc || !desc->gdev)
 		return NULL;
 	return desc->gdev->chip;
 }
@@ -195,7 +196,7 @@ static int gpiochip_find_base(int ngpio)
  * gpiod_get_direction - return the current direction of a GPIO
  * @desc:	GPIO to get the direction of
  *
- * Return GPIOF_DIR_IN or GPIOF_DIR_OUT, or an error code in case of error.
+ * Returns 0 for output, 1 for input, or an error code in case of error.
  *
  * This function may sleep if gpiod_cansleep() is true.
  */
@@ -459,6 +460,15 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 	if (lflags & ~GPIOHANDLE_REQUEST_VALID_FLAGS)
 		return -EINVAL;
 
+	/*
+	 * Do not allow OPEN_SOURCE & OPEN_DRAIN flags in a single request. If
+	 * the hardware actually supports enabling both at the same time the
+	 * electrical result would be disastrous.
+	 */
+	if ((lflags & GPIOHANDLE_REQUEST_OPEN_DRAIN) &&
+	    (lflags & GPIOHANDLE_REQUEST_OPEN_SOURCE))
+		return -EINVAL;
+
 	/* OPEN_DRAIN and OPEN_SOURCE flags only make sense for output mode. */
 	if (!(lflags & GPIOHANDLE_REQUEST_OUTPUT) &&
 	    ((lflags & GPIOHANDLE_REQUEST_OPEN_DRAIN) ||
@@ -505,6 +515,10 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 		if (lflags & GPIOHANDLE_REQUEST_OPEN_SOURCE)
 			set_bit(FLAG_OPEN_SOURCE, &desc->flags);
 
+		ret = gpiod_set_transitory(desc, false);
+		if (ret < 0)
+			goto out_free_descs;
+
 		/*
 		 * Lines have to be requested explicitly for input
 		 * or output, else the line will be treated "as is".
@@ -587,6 +601,9 @@ out_free_lh:
  * @events: KFIFO for the GPIO events
  * @read_lock: mutex lock to protect reads from colliding with adding
  * new events to the FIFO
+ * @timestamp: cache for the timestamp storing it between hardirq
+ * and IRQ thread, used to bring the timestamp close to the actual
+ * event
  */
 struct lineevent_state {
 	struct gpio_device *gdev;
@@ -597,17 +614,18 @@ struct lineevent_state {
 	wait_queue_head_t wait;
 	DECLARE_KFIFO(events, struct gpioevent_data, 16);
 	struct mutex read_lock;
+	u64 timestamp;
 };
 
 #define GPIOEVENT_REQUEST_VALID_FLAGS \
 	(GPIOEVENT_REQUEST_RISING_EDGE | \
 	GPIOEVENT_REQUEST_FALLING_EDGE)
 
-static unsigned int lineevent_poll(struct file *filep,
+static __poll_t lineevent_poll(struct file *filep,
 				   struct poll_table_struct *wait)
 {
 	struct lineevent_state *le = filep->private_data;
-	unsigned int events = 0;
+	__poll_t events = 0;
 
 	poll_wait(filep, &le->wait, wait);
 
@@ -731,7 +749,10 @@ static irqreturn_t lineevent_irq_thread(int irq, void *p)
 	struct gpioevent_data ge;
 	int ret, level;
 
-	ge.timestamp = ktime_get_real_ns();
+	/* Do not leak kernel stack to userspace */
+	memset(&ge, 0, sizeof(ge));
+
+	ge.timestamp = le->timestamp;
 	level = gpiod_get_value_cansleep(le->desc);
 
 	if (le->eflags & GPIOEVENT_REQUEST_RISING_EDGE
@@ -759,6 +780,19 @@ static irqreturn_t lineevent_irq_thread(int irq, void *p)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t lineevent_irq_handler(int irq, void *p)
+{
+	struct lineevent_state *le = p;
+
+	/*
+	 * Just store the timestamp in hardirq context so we get it as
+	 * close in time as possible to the actual event.
+	 */
+	le->timestamp = ktime_get_real_ns();
+
+	return IRQ_WAKE_THREAD;
+}
+
 static int lineevent_create(struct gpio_device *gdev, void __user *ip)
 {
 	struct gpioevent_request eventreq;
@@ -851,7 +885,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
 
 	/* Request a thread to read the events */
 	ret = request_threaded_irq(le->irq,
-			NULL,
+			lineevent_irq_handler,
 			lineevent_irq_thread,
 			irqflags,
 			le->label,
@@ -1049,7 +1083,7 @@ static void gpiodevice_release(struct device *dev)
 
 	list_del(&gdev->list);
 	ida_simple_remove(&gpio_ida, gdev->id);
-	kfree(gdev->label);
+	kfree_const(gdev->label);
 	kfree(gdev->descs);
 	kfree(gdev);
 }
@@ -1100,7 +1134,8 @@ static void gpiochip_setup_devs(void)
 }
 
 int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
-			       struct lock_class_key *key)
+			       struct lock_class_key *lock_key,
+			       struct lock_class_key *request_key)
 {
 	unsigned long	flags;
 	int		status = 0;
@@ -1157,10 +1192,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 		goto err_free_descs;
 	}
 
-	if (chip->label)
-		gdev->label = kstrdup(chip->label, GFP_KERNEL);
-	else
-		gdev->label = kstrdup("unknown", GFP_KERNEL);
+	gdev->label = kstrdup_const(chip->label ?: "unknown", GFP_KERNEL);
 	if (!gdev->label) {
 		status = -ENOMEM;
 		goto err_free_descs;
@@ -1207,31 +1239,14 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 		struct gpio_desc *desc = &gdev->descs[i];
 
 		desc->gdev = gdev;
-		/*
-		 * REVISIT: most hardware initializes GPIOs as inputs
-		 * (often with pullups enabled) so power usage is
-		 * minimized. Linux code should set the gpio direction
-		 * first thing; but until it does, and in case
-		 * chip->get_direction is not set, we may expose the
-		 * wrong direction in sysfs.
-		 */
-
-		if (chip->get_direction) {
-			/*
-			 * If we have .get_direction, set up the initial
-			 * direction flag from the hardware.
-			 */
-			int dir = chip->get_direction(chip, i);
 
-			if (!dir)
-				set_bit(FLAG_IS_OUT, &desc->flags);
-		} else if (!chip->direction_input) {
-			/*
-			 * If the chip lacks the .direction_input callback
-			 * we logically assume all lines are outputs.
-			 */
-			set_bit(FLAG_IS_OUT, &desc->flags);
-		}
+		/* REVISIT: most hardware initializes GPIOs as inputs (often
+		 * with pullups enabled) so power usage is minimized. Linux
+		 * code should set the gpio direction first thing; but until
+		 * it does, and in case chip->get_direction is not set, we may
+		 * expose the wrong direction in sysfs.
+		 */
+		desc->flags = !chip->direction_input ? (1 << FLAG_IS_OUT) : 0;
 	}
 
 #ifdef CONFIG_PINCTRL
@@ -1246,7 +1261,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 	if (status)
 		goto err_remove_from_list;
 
-	status = gpiochip_add_irqchip(chip, key);
+	status = gpiochip_add_irqchip(chip, lock_key, request_key);
 	if (status)
 		goto err_remove_chip;
 
@@ -1281,7 +1296,7 @@ err_remove_from_list:
 	list_del(&gdev->list);
 	spin_unlock_irqrestore(&gpio_lock, flags);
 err_free_label:
-	kfree(gdev->label);
+	kfree_const(gdev->label);
 err_free_descs:
 	kfree(gdev->descs);
 err_free_gdev:
@@ -1381,7 +1396,7 @@ static int devm_gpio_chip_match(struct device *dev, void *res, void *data)
 }
 
 /**
- * devm_gpiochip_add_data() - Resource manager piochip_add_data()
+ * devm_gpiochip_add_data() - Resource manager gpiochip_add_data()
  * @dev: the device pointer on which irq_chip belongs to.
  * @chip: the chip to register, with chip->base initialized
  * @data: driver-private data associated with this chip
@@ -1508,14 +1523,15 @@ static void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gpiochip)
 	gpiochip->irq.valid_mask = NULL;
 }
 
-static bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gpiochip,
-				       unsigned int offset)
+bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gpiochip,
+				unsigned int offset)
 {
 	/* No mask means all valid */
 	if (likely(!gpiochip->irq.valid_mask))
 		return true;
 	return test_bit(offset, gpiochip->irq.valid_mask);
 }
+EXPORT_SYMBOL_GPL(gpiochip_irqchip_irq_valid);
 
 /**
  * gpiochip_set_cascaded_irqchip() - connects a cascaded irqchip to a gpiochip
@@ -1632,7 +1648,7 @@ int gpiochip_irq_map(struct irq_domain *d, unsigned int irq,
 	 * This lock class tells lockdep that GPIO irqs are in a different
 	 * category than their parents, so it won't report false recursion.
 	 */
-	irq_set_lockdep_class(irq, chip->irq.lock_key);
+	irq_set_lockdep_class(irq, chip->irq.lock_key, chip->irq.request_key);
 	irq_set_chip_and_handler(irq, chip->irq.chip, chip->irq.handler);
 	/* Chips that use nested thread handlers have them marked */
 	if (chip->irq.threaded)
@@ -1712,10 +1728,12 @@ static int gpiochip_to_irq(struct gpio_chip *chip, unsigned offset)
 /**
  * gpiochip_add_irqchip() - adds an IRQ chip to a GPIO chip
  * @gpiochip: the GPIO chip to add the IRQ chip to
- * @lock_key: lockdep class
+ * @lock_key: lockdep class for IRQ lock
+ * @request_key: lockdep class for IRQ request
  */
 static int gpiochip_add_irqchip(struct gpio_chip *gpiochip,
-				struct lock_class_key *lock_key)
+				struct lock_class_key *lock_key,
+				struct lock_class_key *request_key)
 {
 	struct irq_chip *irqchip = gpiochip->irq.chip;
 	const struct irq_domain_ops *ops;
@@ -1753,6 +1771,7 @@ static int gpiochip_add_irqchip(struct gpio_chip *gpiochip,
 	gpiochip->to_irq = gpiochip_to_irq;
 	gpiochip->irq.default_type = type;
 	gpiochip->irq.lock_key = lock_key;
+	gpiochip->irq.request_key = request_key;
 
 	if (gpiochip->irq.domain_ops)
 		ops = gpiochip->irq.domain_ops;
@@ -1850,7 +1869,8 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip)
  * @type: the default type for IRQs on this irqchip, pass IRQ_TYPE_NONE
  * to have the core avoid setting up any default type in the hardware.
  * @threaded: whether this irqchip uses a nested thread handler
- * @lock_key: lockdep class
+ * @lock_key: lockdep class for IRQ lock
+ * @request_key: lockdep class for IRQ request
  *
  * This function closely associates a certain irqchip with a certain
  * gpiochip, providing an irq domain to translate the local IRQs to
@@ -1872,7 +1892,8 @@ int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip,
 			     irq_flow_handler_t handler,
 			     unsigned int type,
 			     bool threaded,
-			     struct lock_class_key *lock_key)
+			     struct lock_class_key *lock_key,
+			     struct lock_class_key *request_key)
 {
 	struct device_node *of_node;
 
@@ -1913,6 +1934,7 @@ int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip,
 	gpiochip->irq.default_type = type;
 	gpiochip->to_irq = gpiochip_to_irq;
 	gpiochip->irq.lock_key = lock_key;
+	gpiochip->irq.request_key = request_key;
 	gpiochip->irq.domain = irq_domain_add_simple(of_node,
 					gpiochip->ngpio, first_irq,
 					&gpiochip_domain_ops, gpiochip);
@@ -1940,7 +1962,8 @@ EXPORT_SYMBOL_GPL(gpiochip_irqchip_add_key);
 #else /* CONFIG_GPIOLIB_IRQCHIP */
 
 static inline int gpiochip_add_irqchip(struct gpio_chip *gpiochip,
-				       struct lock_class_key *key)
+				       struct lock_class_key *lock_key,
+				       struct lock_class_key *request_key)
 {
 	return 0;
 }
@@ -2165,40 +2188,37 @@ done:
  * macro to avoid endless duplication. If the desc is NULL it is an
  * optional GPIO and calls should just bail out.
  */
+static int validate_desc(const struct gpio_desc *desc, const char *func)
+{
+	if (!desc)
+		return 0;
+	if (IS_ERR(desc)) {
+		pr_warn("%s: invalid GPIO (errorpointer)\n", func);
+		return PTR_ERR(desc);
+	}
+	if (!desc->gdev) {
+		pr_warn("%s: invalid GPIO (no device)\n", func);
+		return -EINVAL;
+	}
+	if (!desc->gdev->chip) {
+		dev_warn(&desc->gdev->dev,
+			 "%s: backing chip is gone\n", func);
+		return 0;
+	}
+	return 1;
+}
+
 #define VALIDATE_DESC(desc) do { \
-	if (!desc) \
-		return 0; \
-	if (IS_ERR(desc)) {						\
-		pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \
-		return PTR_ERR(desc); \
-	} \
-	if (!desc->gdev) { \
-		pr_warn("%s: invalid GPIO (no device)\n", __func__); \
-		return -EINVAL; \
-	} \
-	if ( !desc->gdev->chip ) { \
-		dev_warn(&desc->gdev->dev, \
-			 "%s: backing chip is gone\n", __func__); \
-		return 0; \
-	} } while (0)
+	int __valid = validate_desc(desc, __func__); \
+	if (__valid <= 0) \
+		return __valid; \
+	} while (0)
 
 #define VALIDATE_DESC_VOID(desc) do { \
-	if (!desc) \
-		return; \
-	if (IS_ERR(desc)) {						\
-		pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \
-		return; \
-	} \
-	if (!desc->gdev) { \
-		pr_warn("%s: invalid GPIO (no device)\n", __func__); \
+	int __valid = validate_desc(desc, __func__); \
+	if (__valid <= 0) \
 		return; \
-	} \
-	if (!desc->gdev->chip) { \
-		dev_warn(&desc->gdev->dev, \
-			 "%s: backing chip is gone\n", __func__); \
-		return; \
-	} } while (0)
-
+	} while (0)
 
 int gpiod_request(struct gpio_desc *desc, const char *label)
 {
@@ -2447,7 +2467,7 @@ EXPORT_SYMBOL_GPL(gpiod_direction_output_raw);
  */
 int gpiod_direction_output(struct gpio_desc *desc, int value)
 {
-	struct gpio_chip *gc = desc->gdev->chip;
+	struct gpio_chip *gc;
 	int ret;
 
 	VALIDATE_DESC(desc);
@@ -2464,6 +2484,7 @@ int gpiod_direction_output(struct gpio_desc *desc, int value)
 		return -EIO;
 	}
 
+	gc = desc->gdev->chip;
 	if (test_bit(FLAG_OPEN_DRAIN, &desc->flags)) {
 		/* First see if we can enable open drain in hardware */
 		ret = gpio_set_drive_single_ended(gc, gpio_chip_hwgpio(desc),
@@ -2521,6 +2542,50 @@ int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce)
 EXPORT_SYMBOL_GPL(gpiod_set_debounce);
 
 /**
+ * gpiod_set_transitory - Lose or retain GPIO state on suspend or reset
+ * @desc: descriptor of the GPIO for which to configure persistence
+ * @transitory: True to lose state on suspend or reset, false for persistence
+ *
+ * Returns:
+ * 0 on success, otherwise a negative error code.
+ */
+int gpiod_set_transitory(struct gpio_desc *desc, bool transitory)
+{
+	struct gpio_chip *chip;
+	unsigned long packed;
+	int gpio;
+	int rc;
+
+	VALIDATE_DESC(desc);
+	/*
+	 * Handle FLAG_TRANSITORY first, enabling queries to gpiolib for
+	 * persistence state.
+	 */
+	if (transitory)
+		set_bit(FLAG_TRANSITORY, &desc->flags);
+	else
+		clear_bit(FLAG_TRANSITORY, &desc->flags);
+
+	/* If the driver supports it, set the persistence state now */
+	chip = desc->gdev->chip;
+	if (!chip->set_config)
+		return 0;
+
+	packed = pinconf_to_config_packed(PIN_CONFIG_PERSIST_STATE,
+					  !transitory);
+	gpio = gpio_chip_hwgpio(desc);
+	rc = chip->set_config(chip, gpio, packed);
+	if (rc == -ENOTSUPP) {
+		dev_dbg(&desc->gdev->dev, "Persistence not supported for GPIO %d\n",
+				gpio);
+		return 0;
+	}
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(gpiod_set_transitory);
+
+/**
  * gpiod_is_active_low - test whether a GPIO is active-low or not
  * @desc: the gpio descriptor to test
  *
@@ -2884,6 +2949,27 @@ void gpiod_set_raw_value(struct gpio_desc *desc, int value)
 EXPORT_SYMBOL_GPL(gpiod_set_raw_value);
 
 /**
+ * gpiod_set_value_nocheck() - set a GPIO line value without checking
+ * @desc: the descriptor to set the value on
+ * @value: value to set
+ *
+ * This sets the value of a GPIO line backing a descriptor, applying
+ * different semantic quirks like active low and open drain/source
+ * handling.
+ */
+static void gpiod_set_value_nocheck(struct gpio_desc *desc, int value)
+{
+	if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
+		value = !value;
+	if (test_bit(FLAG_OPEN_DRAIN, &desc->flags))
+		gpio_set_open_drain_value_commit(desc, value);
+	else if (test_bit(FLAG_OPEN_SOURCE, &desc->flags))
+		gpio_set_open_source_value_commit(desc, value);
+	else
+		gpiod_set_raw_value_commit(desc, value);
+}
+
+/**
  * gpiod_set_value() - assign a gpio's value
  * @desc: gpio whose value will be assigned
  * @value: value to assign
@@ -2897,16 +2983,8 @@ EXPORT_SYMBOL_GPL(gpiod_set_raw_value);
 void gpiod_set_value(struct gpio_desc *desc, int value)
 {
 	VALIDATE_DESC_VOID(desc);
-	/* Should be using gpiod_set_value_cansleep() */
 	WARN_ON(desc->gdev->chip->can_sleep);
-	if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
-		value = !value;
-	if (test_bit(FLAG_OPEN_DRAIN, &desc->flags))
-		gpio_set_open_drain_value_commit(desc, value);
-	else if (test_bit(FLAG_OPEN_SOURCE, &desc->flags))
-		gpio_set_open_source_value_commit(desc, value);
-	else
-		gpiod_set_raw_value_commit(desc, value);
+	gpiod_set_value_nocheck(desc, value);
 }
 EXPORT_SYMBOL_GPL(gpiod_set_value);
 
@@ -3107,8 +3185,7 @@ bool gpiochip_line_is_persistent(struct gpio_chip *chip, unsigned int offset)
 	if (offset >= chip->ngpio)
 		return false;
 
-	return !test_bit(FLAG_SLEEP_MAY_LOSE_VALUE,
-			 &chip->gpiodev->descs[offset].flags);
+	return !test_bit(FLAG_TRANSITORY, &chip->gpiodev->descs[offset].flags);
 }
 EXPORT_SYMBOL_GPL(gpiochip_line_is_persistent);
 
@@ -3234,9 +3311,7 @@ void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
 {
 	might_sleep_if(extra_checks);
 	VALIDATE_DESC_VOID(desc);
-	if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
-		value = !value;
-	gpiod_set_raw_value_commit(desc, value);
+	gpiod_set_value_nocheck(desc, value);
 }
 EXPORT_SYMBOL_GPL(gpiod_set_value_cansleep);
 
@@ -3545,8 +3620,10 @@ int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id,
 
 	if (lflags & GPIO_OPEN_SOURCE)
 		set_bit(FLAG_OPEN_SOURCE, &desc->flags);
-	if (lflags & GPIO_SLEEP_MAY_LOSE_VALUE)
-		set_bit(FLAG_SLEEP_MAY_LOSE_VALUE, &desc->flags);
+
+	status = gpiod_set_transitory(desc, (lflags & GPIO_TRANSITORY));
+	if (status < 0)
+		return status;
 
 	/* No particular flag request, return here... */
 	if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) {
@@ -3586,6 +3663,8 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
 	struct gpio_desc *desc = NULL;
 	int status;
 	enum gpio_lookup_flags lookupflags = 0;
+	/* Maybe we have a device name, maybe not */
+	const char *devname = dev ? dev_name(dev) : "?";
 
 	dev_dbg(dev, "GPIO lookup for consumer %s\n", con_id);
 
@@ -3614,7 +3693,11 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
 		return desc;
 	}
 
-	status = gpiod_request(desc, con_id);
+	/*
+	 * If a connection label was passed use that, else attempt to use
+	 * the device name as label
+	 */
+	status = gpiod_request(desc, con_id ? con_id : devname);
 	if (status < 0)
 		return ERR_PTR(status);
 
@@ -3630,17 +3713,88 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
 EXPORT_SYMBOL_GPL(gpiod_get_index);
 
 /**
+ * gpiod_get_from_of_node() - obtain a GPIO from an OF node
+ * @node:	handle of the OF node
+ * @propname:	name of the DT property representing the GPIO
+ * @index:	index of the GPIO to obtain for the consumer
+ * @dflags:	GPIO initialization flags
+ * @label:	label to attach to the requested GPIO
+ *
+ * Returns:
+ * On successful request the GPIO pin is configured in accordance with
+ * provided @dflags. If the node does not have the requested GPIO
+ * property, NULL is returned.
+ *
+ * In case of error an ERR_PTR() is returned.
+ */
+struct gpio_desc *gpiod_get_from_of_node(struct device_node *node,
+					 const char *propname, int index,
+					 enum gpiod_flags dflags,
+					 const char *label)
+{
+	struct gpio_desc *desc;
+	unsigned long lflags = 0;
+	enum of_gpio_flags flags;
+	bool active_low = false;
+	bool single_ended = false;
+	bool open_drain = false;
+	bool transitory = false;
+	int ret;
+
+	desc = of_get_named_gpiod_flags(node, propname,
+					index, &flags);
+
+	if (!desc || IS_ERR(desc)) {
+		/* If it is not there, just return NULL */
+		if (PTR_ERR(desc) == -ENOENT)
+			return NULL;
+		return desc;
+	}
+
+	active_low = flags & OF_GPIO_ACTIVE_LOW;
+	single_ended = flags & OF_GPIO_SINGLE_ENDED;
+	open_drain = flags & OF_GPIO_OPEN_DRAIN;
+	transitory = flags & OF_GPIO_TRANSITORY;
+
+	ret = gpiod_request(desc, label);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (active_low)
+		lflags |= GPIO_ACTIVE_LOW;
+
+	if (single_ended) {
+		if (open_drain)
+			lflags |= GPIO_OPEN_DRAIN;
+		else
+			lflags |= GPIO_OPEN_SOURCE;
+	}
+
+	if (transitory)
+		lflags |= GPIO_TRANSITORY;
+
+	ret = gpiod_configure_flags(desc, propname, lflags, dflags);
+	if (ret < 0) {
+		gpiod_put(desc);
+		return ERR_PTR(ret);
+	}
+
+	return desc;
+}
+EXPORT_SYMBOL(gpiod_get_from_of_node);
+
+/**
  * fwnode_get_named_gpiod - obtain a GPIO from firmware node
  * @fwnode:	handle of the firmware node
  * @propname:	name of the firmware property representing the GPIO
- * @index:	index of the GPIO to obtain in the consumer
+ * @index:	index of the GPIO to obtain for the consumer
  * @dflags:	GPIO initialization flags
  * @label:	label to attach to the requested GPIO
  *
  * This function can be used for drivers that get their configuration
- * from firmware.
+ * from opaque firmware.
  *
- * Function properly finds the corresponding GPIO using whatever is the
+ * The function properly finds the corresponding GPIO using whatever is the
  * underlying firmware interface and then makes sure that the GPIO
  * descriptor is requested before it is returned to the caller.
  *
@@ -3657,53 +3811,35 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode,
 {
 	struct gpio_desc *desc = ERR_PTR(-ENODEV);
 	unsigned long lflags = 0;
-	bool active_low = false;
-	bool single_ended = false;
-	bool open_drain = false;
 	int ret;
 
 	if (!fwnode)
 		return ERR_PTR(-EINVAL);
 
 	if (is_of_node(fwnode)) {
-		enum of_gpio_flags flags;
-
-		desc = of_get_named_gpiod_flags(to_of_node(fwnode), propname,
-						index, &flags);
-		if (!IS_ERR(desc)) {
-			active_low = flags & OF_GPIO_ACTIVE_LOW;
-			single_ended = flags & OF_GPIO_SINGLE_ENDED;
-			open_drain = flags & OF_GPIO_OPEN_DRAIN;
-		}
+		desc = gpiod_get_from_of_node(to_of_node(fwnode),
+					      propname, index,
+					      dflags,
+					      label);
+		return desc;
 	} else if (is_acpi_node(fwnode)) {
 		struct acpi_gpio_info info;
 
 		desc = acpi_node_get_gpiod(fwnode, propname, index, &info);
-		if (!IS_ERR(desc)) {
-			active_low = info.polarity == GPIO_ACTIVE_LOW;
-			ret = acpi_gpio_update_gpiod_flags(&dflags, info.flags);
-			if (ret)
-				pr_debug("Override GPIO initialization flags\n");
-		}
-	}
+		if (IS_ERR(desc))
+			return desc;
 
-	if (IS_ERR(desc))
-		return desc;
+		acpi_gpio_update_gpiod_flags(&dflags, &info);
+
+		if (info.polarity == GPIO_ACTIVE_LOW)
+			lflags |= GPIO_ACTIVE_LOW;
+	}
 
+	/* Currently only ACPI takes this path */
 	ret = gpiod_request(desc, label);
 	if (ret)
 		return ERR_PTR(ret);
 
-	if (active_low)
-		lflags |= GPIO_ACTIVE_LOW;
-
-	if (single_ended) {
-		if (open_drain)
-			lflags |= GPIO_OPEN_DRAIN;
-		else
-			lflags |= GPIO_OPEN_SOURCE;
-	}
-
 	ret = gpiod_configure_flags(desc, propname, lflags, dflags);
 	if (ret < 0) {
 		gpiod_put(desc);
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index af48322839c3..b17ec6795c81 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -58,7 +58,7 @@ struct gpio_device {
 	struct gpio_desc	*descs;
 	int			base;
 	u16			ngpio;
-	char			*label;
+	const char		*label;
 	void			*data;
 	struct list_head        list;
 
@@ -75,16 +75,20 @@ struct gpio_device {
 
 /**
  * struct acpi_gpio_info - ACPI GPIO specific information
+ * @adev: reference to ACPI device which consumes GPIO resource
  * @flags: GPIO initialization flags
  * @gpioint: if %true this GPIO is of type GpioInt otherwise type is GpioIo
  * @polarity: interrupt polarity as provided by ACPI
  * @triggering: triggering type as provided by ACPI
+ * @quirks: Linux specific quirks as provided by struct acpi_gpio_mapping
  */
 struct acpi_gpio_info {
+	struct acpi_device *adev;
 	enum gpiod_flags flags;
 	bool gpioint;
 	int polarity;
 	int triggering;
+	unsigned int quirks;
 };
 
 /* gpio suffixes used for ACPI and device tree lookup */
@@ -124,7 +128,7 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip);
 void acpi_gpiochip_free_interrupts(struct gpio_chip *chip);
 
 int acpi_gpio_update_gpiod_flags(enum gpiod_flags *flags,
-				 enum gpiod_flags update);
+				 struct acpi_gpio_info *info);
 
 struct gpio_desc *acpi_find_gpio(struct device *dev,
 				 const char *con_id,
@@ -149,7 +153,7 @@ static inline void
 acpi_gpiochip_free_interrupts(struct gpio_chip *chip) { }
 
 static inline int
-acpi_gpio_update_gpiod_flags(enum gpiod_flags *flags, enum gpiod_flags update)
+acpi_gpio_update_gpiod_flags(enum gpiod_flags *flags, struct acpi_gpio_info *info)
 {
 	return 0;
 }
@@ -189,6 +193,12 @@ void gpiod_set_array_value_complex(bool raw, bool can_sleep,
 				   struct gpio_desc **desc_array,
 				   int *value_array);
 
+/* This is just passed between gpiolib and devres */
+struct gpio_desc *gpiod_get_from_of_node(struct device_node *node,
+					 const char *propname, int index,
+					 enum gpiod_flags dflags,
+					 const char *label);
+
 extern struct spinlock gpio_lock;
 extern struct list_head gpio_devices;
 
@@ -205,7 +215,7 @@ struct gpio_desc {
 #define FLAG_OPEN_SOURCE 8	/* Gpio is open source type */
 #define FLAG_USED_AS_IRQ 9	/* GPIO is connected to an IRQ */
 #define FLAG_IS_HOGGED	11	/* GPIO is hogged */
-#define FLAG_SLEEP_MAY_LOSE_VALUE 12	/* GPIO may lose value in sleep */
+#define FLAG_TRANSITORY 12	/* GPIO may lose value in sleep or reset */
 
 	/* Connection label */
 	const char		*label;
@@ -228,7 +238,8 @@ static inline int gpio_chip_hwgpio(const struct gpio_desc *desc)
 	return desc - &desc->gdev->descs[0];
 }
 
-void devprop_gpiochip_set_names(struct gpio_chip *chip);
+void devprop_gpiochip_set_names(struct gpio_chip *chip,
+				const struct fwnode_handle *fwnode);
 
 /* With descriptor prefix */
 
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 4d9f21831741..deeefa7a1773 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -7,6 +7,7 @@
 menuconfig DRM
 	tristate "Direct Rendering Manager (XFree86 4.1.0 and higher DRI support)"
 	depends on (AGP || AGP=n) && !EMULATED_CMPXCHG && HAS_DMA
+	select DRM_PANEL_ORIENTATION_QUIRKS
 	select HDMI
 	select FB_CMDLINE
 	select I2C
@@ -149,6 +150,10 @@ config DRM_VM
 	bool
 	depends on DRM && MMU
 
+config DRM_SCHED
+	tristate
+	depends on DRM
+
 source "drivers/gpu/drm/i2c/Kconfig"
 
 source "drivers/gpu/drm/arm/Kconfig"
@@ -178,6 +183,7 @@ config DRM_AMDGPU
 	depends on DRM && PCI && MMU
 	select FW_LOADER
         select DRM_KMS_HELPER
+	select DRM_SCHED
         select DRM_TTM
 	select POWER_SUPPLY
 	select HWMON
@@ -362,6 +368,10 @@ config DRM_SAVAGE
 
 endif # DRM_LEGACY
 
+# Separate option because drm_panel_orientation_quirks.c is shared with fbdev
+config DRM_PANEL_ORIENTATION_QUIRKS
+	tristate
+
 config DRM_LIB_RANDOM
 	bool
 	default n
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index e9500844333e..50093ff4479b 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -47,8 +47,10 @@ obj-$(CONFIG_DRM_DEBUG_MM_SELFTEST) += selftests/
 
 obj-$(CONFIG_DRM)	+= drm.o
 obj-$(CONFIG_DRM_MIPI_DSI) += drm_mipi_dsi.o
+obj-$(CONFIG_DRM_PANEL_ORIENTATION_QUIRKS) += drm_panel_orientation_quirks.o
 obj-$(CONFIG_DRM_ARM)	+= arm/
 obj-$(CONFIG_DRM_TTM)	+= ttm/
+obj-$(CONFIG_DRM_SCHED)	+= scheduler/
 obj-$(CONFIG_DRM_TDFX)	+= tdfx/
 obj-$(CONFIG_DRM_R128)	+= r128/
 obj-y			+= amd/lib/
diff --git a/drivers/gpu/drm/amd/acp/Makefile b/drivers/gpu/drm/amd/acp/Makefile
index 8a08e81ee90d..d4176a3fb706 100644
--- a/drivers/gpu/drm/amd/acp/Makefile
+++ b/drivers/gpu/drm/amd/acp/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the ACP, which is a sub-component
 # of AMDSOC/AMDGPU drm driver.
 # It provides the HW control for ACP related functionalities.
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 78d609123420..d6e5b7273853 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -1,4 +1,24 @@
-# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
 #
 # Makefile for the drm device driver.  This driver provides support for the
 # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher.
@@ -32,7 +52,8 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_prime.o amdgpu_vm.o amdgpu_ib.o amdgpu_pll.o \
 	amdgpu_ucode.o amdgpu_bo_list.o amdgpu_ctx.o amdgpu_sync.o \
 	amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \
-	amdgpu_queue_mgr.o amdgpu_vf_error.o amdgpu_sched.o
+	amdgpu_queue_mgr.o amdgpu_vf_error.o amdgpu_sched.o amdgpu_debugfs.o \
+	amdgpu_ids.o
 
 # add asic specific block
 amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \
@@ -42,7 +63,7 @@ amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \
 amdgpu-$(CONFIG_DRM_AMDGPU_SI)+= si.o gmc_v6_0.o gfx_v6_0.o si_ih.o si_dma.o dce_v6_0.o si_dpm.o si_smc.o
 
 amdgpu-y += \
-	vi.o mxgpu_vi.o nbio_v6_1.o soc15.o mxgpu_ai.o nbio_v7_0.o
+	vi.o mxgpu_vi.o nbio_v6_1.o soc15.o mxgpu_ai.o nbio_v7_0.o vega10_reg_init.o
 
 # add GMC block
 amdgpu-y += \
@@ -115,10 +136,7 @@ amdgpu-y += \
 amdgpu-y += amdgpu_cgs.o
 
 # GPU scheduler
-amdgpu-y += \
-	../scheduler/gpu_scheduler.o \
-	../scheduler/sched_fence.o \
-	amdgpu_job.o
+amdgpu-y += amdgpu_job.o
 
 # ACP componet
 ifneq ($(CONFIG_DRM_AMD_ACP),)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 5afaf6016b4a..d5a2eefd6c3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -45,8 +45,11 @@
 #include <drm/drmP.h>
 #include <drm/drm_gem.h>
 #include <drm/amdgpu_drm.h>
+#include <drm/gpu_scheduler.h>
 
 #include <kgd_kfd_interface.h>
+#include "dm_pp_interface.h"
+#include "kgd_pp_interface.h"
 
 #include "amd_shared.h"
 #include "amdgpu_mode.h"
@@ -59,7 +62,6 @@
 #include "amdgpu_sync.h"
 #include "amdgpu_ring.h"
 #include "amdgpu_vm.h"
-#include "amd_powerplay.h"
 #include "amdgpu_dpm.h"
 #include "amdgpu_acp.h"
 #include "amdgpu_uvd.h"
@@ -67,10 +69,9 @@
 #include "amdgpu_vcn.h"
 #include "amdgpu_mn.h"
 #include "amdgpu_dm.h"
-
-#include "gpu_scheduler.h"
 #include "amdgpu_virt.h"
 #include "amdgpu_gart.h"
+#include "amdgpu_debugfs.h"
 
 /*
  * Modules parameters.
@@ -125,6 +126,7 @@ extern int amdgpu_param_buf_per_se;
 extern int amdgpu_job_hang_limit;
 extern int amdgpu_lbpw;
 extern int amdgpu_compute_multipipe;
+extern int amdgpu_gpu_recovery;
 
 #ifdef CONFIG_DRM_AMDGPU_SI
 extern int amdgpu_si_support;
@@ -177,6 +179,10 @@ extern int amdgpu_cik_support;
 #define CIK_CURSOR_WIDTH 128
 #define CIK_CURSOR_HEIGHT 128
 
+/* GPU RESET flags */
+#define AMDGPU_RESET_INFO_VRAM_LOST  (1 << 0)
+#define AMDGPU_RESET_INFO_FULLRESET  (1 << 1)
+
 struct amdgpu_device;
 struct amdgpu_ib;
 struct amdgpu_cs_parser;
@@ -218,17 +224,18 @@ enum amdgpu_kiq_irq {
 	AMDGPU_CP_KIQ_IRQ_LAST
 };
 
-int amdgpu_set_clockgating_state(struct amdgpu_device *adev,
-				  enum amd_ip_block_type block_type,
-				  enum amd_clockgating_state state);
-int amdgpu_set_powergating_state(struct amdgpu_device *adev,
-				  enum amd_ip_block_type block_type,
-				  enum amd_powergating_state state);
-void amdgpu_get_clockgating_state(struct amdgpu_device *adev, u32 *flags);
-int amdgpu_wait_for_idle(struct amdgpu_device *adev,
-			 enum amd_ip_block_type block_type);
-bool amdgpu_is_idle(struct amdgpu_device *adev,
-		    enum amd_ip_block_type block_type);
+int amdgpu_device_ip_set_clockgating_state(struct amdgpu_device *adev,
+					   enum amd_ip_block_type block_type,
+					   enum amd_clockgating_state state);
+int amdgpu_device_ip_set_powergating_state(struct amdgpu_device *adev,
+					   enum amd_ip_block_type block_type,
+					   enum amd_powergating_state state);
+void amdgpu_device_ip_get_clockgating_state(struct amdgpu_device *adev,
+					    u32 *flags);
+int amdgpu_device_ip_wait_for_idle(struct amdgpu_device *adev,
+				   enum amd_ip_block_type block_type);
+bool amdgpu_device_ip_is_idle(struct amdgpu_device *adev,
+			      enum amd_ip_block_type block_type);
 
 #define AMDGPU_MAX_IP_NUM 16
 
@@ -253,15 +260,16 @@ struct amdgpu_ip_block {
 	const struct amdgpu_ip_block_version *version;
 };
 
-int amdgpu_ip_block_version_cmp(struct amdgpu_device *adev,
-				enum amd_ip_block_type type,
-				u32 major, u32 minor);
+int amdgpu_device_ip_block_version_cmp(struct amdgpu_device *adev,
+				       enum amd_ip_block_type type,
+				       u32 major, u32 minor);
 
-struct amdgpu_ip_block * amdgpu_get_ip_block(struct amdgpu_device *adev,
-					     enum amd_ip_block_type type);
+struct amdgpu_ip_block *
+amdgpu_device_ip_get_ip_block(struct amdgpu_device *adev,
+			      enum amd_ip_block_type type);
 
-int amdgpu_ip_block_add(struct amdgpu_device *adev,
-			const struct amdgpu_ip_block_version *ip_block_version);
+int amdgpu_device_ip_block_add(struct amdgpu_device *adev,
+			       const struct amdgpu_ip_block_version *ip_block_version);
 
 /* provided by hw blocks that can move/clear data.  e.g., gfx or sdma */
 struct amdgpu_buffer_funcs {
@@ -341,8 +349,9 @@ struct amdgpu_gart_funcs {
 	uint64_t (*get_vm_pte_flags)(struct amdgpu_device *adev,
 				     uint32_t flags);
 	/* get the pde for a given mc addr */
-	u64 (*get_vm_pde)(struct amdgpu_device *adev, u64 addr);
-	uint32_t (*get_invalidate_req)(unsigned int vm_id);
+	void (*get_vm_pde)(struct amdgpu_device *adev, int level,
+			   u64 *dst, u64 *flags);
+	uint32_t (*get_invalidate_req)(unsigned int vmid);
 };
 
 /* provided by the ih block */
@@ -368,9 +377,6 @@ struct amdgpu_dummy_page {
 	struct page	*page;
 	dma_addr_t	addr;
 };
-int amdgpu_dummy_page_init(struct amdgpu_device *adev);
-void amdgpu_dummy_page_fini(struct amdgpu_device *adev);
-
 
 /*
  * Clocks
@@ -418,7 +424,6 @@ struct reservation_object *amdgpu_gem_prime_res_obj(struct drm_gem_object *);
 void *amdgpu_gem_prime_vmap(struct drm_gem_object *obj);
 void amdgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 int amdgpu_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
-int amdgpu_gem_debugfs_init(struct amdgpu_device *adev);
 
 /* sub-allocation manager, it has to be protected by another lock.
  * By conception this is an helper for other part of the driver
@@ -535,6 +540,7 @@ struct amdgpu_mc {
 	u64					private_aperture_end;
 	/* protects concurrent invalidation */
 	spinlock_t		invalidate_lock;
+	bool			translate_further;
 };
 
 /*
@@ -645,12 +651,6 @@ typedef enum _AMDGPU_DOORBELL64_ASSIGNMENT
 	AMDGPU_DOORBELL64_INVALID                 = 0xFFFF
 } AMDGPU_DOORBELL64_ASSIGNMENT;
 
-
-void amdgpu_doorbell_get_kfd_info(struct amdgpu_device *adev,
-				phys_addr_t *aperture_base,
-				size_t *aperture_size,
-				size_t *start_offset);
-
 /*
  * IRQS.
  */
@@ -684,7 +684,7 @@ struct amdgpu_ib {
 	uint32_t			flags;
 };
 
-extern const struct amd_sched_backend_ops amdgpu_sched_ops;
+extern const struct drm_sched_backend_ops amdgpu_sched_ops;
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
 		     struct amdgpu_job **job, struct amdgpu_vm *vm);
@@ -694,7 +694,7 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
 void amdgpu_job_free_resources(struct amdgpu_job *job);
 void amdgpu_job_free(struct amdgpu_job *job);
 int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
-		      struct amd_sched_entity *entity, void *owner,
+		      struct drm_sched_entity *entity, void *owner,
 		      struct dma_fence **f);
 
 /*
@@ -717,7 +717,7 @@ int amdgpu_queue_mgr_fini(struct amdgpu_device *adev,
 			  struct amdgpu_queue_mgr *mgr);
 int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 			 struct amdgpu_queue_mgr *mgr,
-			 int hw_ip, int instance, int ring,
+			 u32 hw_ip, u32 instance, u32 ring,
 			 struct amdgpu_ring **out_ring);
 
 /*
@@ -727,7 +727,7 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 struct amdgpu_ctx_ring {
 	uint64_t		sequence;
 	struct dma_fence	**fences;
-	struct amd_sched_entity	entity;
+	struct drm_sched_entity	entity;
 };
 
 struct amdgpu_ctx {
@@ -735,14 +735,16 @@ struct amdgpu_ctx {
 	struct amdgpu_device    *adev;
 	struct amdgpu_queue_mgr queue_mgr;
 	unsigned		reset_counter;
+	unsigned        reset_counter_query;
 	uint32_t		vram_lost_counter;
 	spinlock_t		ring_lock;
 	struct dma_fence	**fences;
 	struct amdgpu_ctx_ring	rings[AMDGPU_MAX_RINGS];
 	bool			preamble_presented;
-	enum amd_sched_priority init_priority;
-	enum amd_sched_priority override_priority;
+	enum drm_sched_priority init_priority;
+	enum drm_sched_priority override_priority;
 	struct mutex            lock;
+	atomic_t	guilty;
 };
 
 struct amdgpu_ctx_mgr {
@@ -760,7 +762,7 @@ int amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
 struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,
 				   struct amdgpu_ring *ring, uint64_t seq);
 void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx,
-				  enum amd_sched_priority priority);
+				  enum drm_sched_priority priority);
 
 int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 		     struct drm_file *filp);
@@ -957,6 +959,7 @@ struct amdgpu_gfx_config {
 };
 
 struct amdgpu_cu_info {
+	uint32_t simd_per_cu;
 	uint32_t max_waves_per_simd;
 	uint32_t wave_front_size;
 	uint32_t max_scratch_slots_per_cu;
@@ -1109,12 +1112,11 @@ struct amdgpu_cs_parser {
 #define AMDGPU_HAVE_CTX_SWITCH              (1 << 2) /* bit set means context switch occured */
 
 struct amdgpu_job {
-	struct amd_sched_job    base;
+	struct drm_sched_job    base;
 	struct amdgpu_device	*adev;
 	struct amdgpu_vm	*vm;
 	struct amdgpu_ring	*ring;
 	struct amdgpu_sync	sync;
-	struct amdgpu_sync	dep_sync;
 	struct amdgpu_sync	sched_sync;
 	struct amdgpu_ib	*ibs;
 	struct dma_fence	*fence; /* the hw fence */
@@ -1123,7 +1125,7 @@ struct amdgpu_job {
 	void			*owner;
 	uint64_t		fence_ctx; /* the fence_context this job uses */
 	bool                    vm_needs_flush;
-	unsigned		vm_id;
+	unsigned		vmid;
 	uint64_t		vm_pd_addr;
 	uint32_t		gds_base, gds_size;
 	uint32_t		gws_base, gws_size;
@@ -1164,10 +1166,10 @@ struct amdgpu_wb {
 	unsigned long		used[DIV_ROUND_UP(AMDGPU_MAX_WB, BITS_PER_LONG)];
 };
 
-int amdgpu_wb_get(struct amdgpu_device *adev, u32 *wb);
-void amdgpu_wb_free(struct amdgpu_device *adev, u32 wb);
+int amdgpu_device_wb_get(struct amdgpu_device *adev, u32 *wb);
+void amdgpu_device_wb_free(struct amdgpu_device *adev, u32 wb);
 
-void amdgpu_get_pcie_info(struct amdgpu_device *adev);
+void amdgpu_device_get_pcie_info(struct amdgpu_device *adev);
 
 /*
  * SDMA
@@ -1232,24 +1234,6 @@ void amdgpu_benchmark(struct amdgpu_device *adev, int test_number);
  */
 void amdgpu_test_moves(struct amdgpu_device *adev);
 
-/*
- * Debugfs
- */
-struct amdgpu_debugfs {
-	const struct drm_info_list	*files;
-	unsigned		num_files;
-};
-
-int amdgpu_debugfs_add_files(struct amdgpu_device *adev,
-			     const struct drm_info_list *files,
-			     unsigned nfiles);
-int amdgpu_debugfs_fence_init(struct amdgpu_device *adev);
-
-#if defined(CONFIG_DEBUG_FS)
-int amdgpu_debugfs_init(struct drm_minor *minor);
-#endif
-
-int amdgpu_debugfs_firmware_init(struct amdgpu_device *adev);
 
 /*
  * amdgpu smumgr functions
@@ -1404,8 +1388,6 @@ struct amdgpu_fw_vram_usage {
 	void *va;
 };
 
-int amdgpu_fw_reserve_vram_init(struct amdgpu_device *adev);
-
 /*
  * CGS
  */
@@ -1421,6 +1403,87 @@ typedef void (*amdgpu_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
 typedef uint32_t (*amdgpu_block_rreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
 typedef void (*amdgpu_block_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t, uint32_t);
 
+
+/*
+ * amdgpu nbio functions
+ *
+ */
+struct nbio_hdp_flush_reg {
+	u32 ref_and_mask_cp0;
+	u32 ref_and_mask_cp1;
+	u32 ref_and_mask_cp2;
+	u32 ref_and_mask_cp3;
+	u32 ref_and_mask_cp4;
+	u32 ref_and_mask_cp5;
+	u32 ref_and_mask_cp6;
+	u32 ref_and_mask_cp7;
+	u32 ref_and_mask_cp8;
+	u32 ref_and_mask_cp9;
+	u32 ref_and_mask_sdma0;
+	u32 ref_and_mask_sdma1;
+};
+
+struct amdgpu_nbio_funcs {
+	const struct nbio_hdp_flush_reg *hdp_flush_reg;
+	u32 (*get_hdp_flush_req_offset)(struct amdgpu_device *adev);
+	u32 (*get_hdp_flush_done_offset)(struct amdgpu_device *adev);
+	u32 (*get_pcie_index_offset)(struct amdgpu_device *adev);
+	u32 (*get_pcie_data_offset)(struct amdgpu_device *adev);
+	u32 (*get_rev_id)(struct amdgpu_device *adev);
+	void (*mc_access_enable)(struct amdgpu_device *adev, bool enable);
+	void (*hdp_flush)(struct amdgpu_device *adev);
+	u32 (*get_memsize)(struct amdgpu_device *adev);
+	void (*sdma_doorbell_range)(struct amdgpu_device *adev, int instance,
+				    bool use_doorbell, int doorbell_index);
+	void (*enable_doorbell_aperture)(struct amdgpu_device *adev,
+					 bool enable);
+	void (*enable_doorbell_selfring_aperture)(struct amdgpu_device *adev,
+						  bool enable);
+	void (*ih_doorbell_range)(struct amdgpu_device *adev,
+				  bool use_doorbell, int doorbell_index);
+	void (*update_medium_grain_clock_gating)(struct amdgpu_device *adev,
+						 bool enable);
+	void (*update_medium_grain_light_sleep)(struct amdgpu_device *adev,
+						bool enable);
+	void (*get_clockgating_state)(struct amdgpu_device *adev,
+				      u32 *flags);
+	void (*ih_control)(struct amdgpu_device *adev);
+	void (*init_registers)(struct amdgpu_device *adev);
+	void (*detect_hw_virt)(struct amdgpu_device *adev);
+};
+
+
+/* Define the HW IP blocks will be used in driver , add more if necessary */
+enum amd_hw_ip_block_type {
+	GC_HWIP = 1,
+	HDP_HWIP,
+	SDMA0_HWIP,
+	SDMA1_HWIP,
+	MMHUB_HWIP,
+	ATHUB_HWIP,
+	NBIO_HWIP,
+	MP0_HWIP,
+	UVD_HWIP,
+	VCN_HWIP = UVD_HWIP,
+	VCE_HWIP,
+	DF_HWIP,
+	DCE_HWIP,
+	OSSSYS_HWIP,
+	SMUIO_HWIP,
+	PWR_HWIP,
+	NBIF_HWIP,
+	MAX_HWIP
+};
+
+#define HWIP_MAX_INSTANCE	6
+
+struct amd_powerplay {
+	struct cgs_device *cgs_device;
+	void *pp_handle;
+	const struct amd_ip_funcs *ip_funcs;
+	const struct amd_pm_funcs *pp_funcs;
+};
+
 #define AMDGPU_RESET_MAGIC_NUM 64
 struct amdgpu_device {
 	struct device			*dev;
@@ -1572,18 +1635,14 @@ struct amdgpu_device {
 	/* sdma */
 	struct amdgpu_sdma		sdma;
 
-	union {
-		struct {
-			/* uvd */
-			struct amdgpu_uvd		uvd;
+	/* uvd */
+	struct amdgpu_uvd		uvd;
 
-			/* vce */
-			struct amdgpu_vce		vce;
-		};
+	/* vce */
+	struct amdgpu_vce		vce;
 
-		/* vcn */
-		struct amdgpu_vcn		vcn;
-	};
+	/* vcn */
+	struct amdgpu_vcn		vcn;
 
 	/* firmwares */
 	struct amdgpu_firmware		firmware;
@@ -1610,6 +1669,11 @@ struct amdgpu_device {
 	/* amdkfd interface */
 	struct kfd_dev          *kfd;
 
+	/* soc15 register offset based on ip, instance and  segment */
+	uint32_t 		*reg_offset[MAX_HWIP][HWIP_MAX_INSTANCE];
+
+	const struct amdgpu_nbio_funcs	*nbio_funcs;
+
 	/* delayed work_func for deferring clockgating during resume */
 	struct delayed_work     late_init_work;
 
@@ -1620,9 +1684,6 @@ struct amdgpu_device {
 	/* link all shadow bo */
 	struct list_head                shadow_list;
 	struct mutex                    shadow_list_lock;
-	/* link all gtt */
-	spinlock_t			gtt_list_lock;
-	struct list_head                gtt_list;
 	/* keep an lru list of rings by HW IP */
 	struct list_head		ring_lru_list;
 	spinlock_t			ring_lru_list_lock;
@@ -1633,7 +1694,8 @@ struct amdgpu_device {
 
 	/* record last mm index being written through WREG32*/
 	unsigned long last_mm_index;
-	bool                            in_sriov_reset;
+	bool                            in_gpu_reset;
+	struct mutex  lock_reset;
 };
 
 static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)
@@ -1777,7 +1839,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_asic_get_config_memsize(adev) (adev)->asic_funcs->get_config_memsize((adev))
 #define amdgpu_gart_flush_gpu_tlb(adev, vmid) (adev)->gart.gart_funcs->flush_gpu_tlb((adev), (vmid))
 #define amdgpu_gart_set_pte_pde(adev, pt, idx, addr, flags) (adev)->gart.gart_funcs->set_pte_pde((adev), (pt), (idx), (addr), (flags))
-#define amdgpu_gart_get_vm_pde(adev, addr) (adev)->gart.gart_funcs->get_vm_pde((adev), (addr))
+#define amdgpu_gart_get_vm_pde(adev, level, dst, flags) (adev)->gart.gart_funcs->get_vm_pde((adev), (level), (dst), (flags))
 #define amdgpu_vm_copy_pte(adev, ib, pe, src, count) ((adev)->vm_manager.vm_pte_funcs->copy_pte((ib), (pe), (src), (count)))
 #define amdgpu_vm_write_pte(adev, ib, pe, value, count, incr) ((adev)->vm_manager.vm_pte_funcs->write_pte((ib), (pe), (value), (count), (incr)))
 #define amdgpu_vm_set_pte_pde(adev, ib, pe, addr, count, incr, flags) ((adev)->vm_manager.vm_pte_funcs->set_pte_pde((ib), (pe), (addr), (count), (incr), (flags)))
@@ -1788,7 +1850,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r))
 #define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r))
 #define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r))
-#define amdgpu_ring_emit_ib(r, ib, vm_id, c) (r)->funcs->emit_ib((r), (ib), (vm_id), (c))
+#define amdgpu_ring_emit_ib(r, ib, vmid, c) (r)->funcs->emit_ib((r), (ib), (vmid), (c))
 #define amdgpu_ring_emit_pipeline_sync(r) (r)->funcs->emit_pipeline_sync((r))
 #define amdgpu_ring_emit_vm_flush(r, vmid, addr) (r)->funcs->emit_vm_flush((r), (vmid), (addr))
 #define amdgpu_ring_emit_fence(r, addr, seq, flags) (r)->funcs->emit_fence((r), (addr), (seq), (flags))
@@ -1827,22 +1889,25 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_psp_check_fw_loading_status(adev, i) (adev)->firmware.funcs->check_fw_loading_status((adev), (i))
 
 /* Common functions */
-int amdgpu_gpu_reset(struct amdgpu_device *adev);
-bool amdgpu_need_backup(struct amdgpu_device *adev);
-void amdgpu_pci_config_reset(struct amdgpu_device *adev);
-bool amdgpu_need_post(struct amdgpu_device *adev);
+int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
+			      struct amdgpu_job* job, bool force);
+void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
+bool amdgpu_device_need_post(struct amdgpu_device *adev);
 void amdgpu_update_display_priority(struct amdgpu_device *adev);
 
 void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes,
 				  u64 num_vis_bytes);
 void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain);
 bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
-void amdgpu_vram_location(struct amdgpu_device *adev, struct amdgpu_mc *mc, u64 base);
-void amdgpu_gart_location(struct amdgpu_device *adev, struct amdgpu_mc *mc);
+void amdgpu_device_vram_location(struct amdgpu_device *adev,
+				 struct amdgpu_mc *mc, u64 base);
+void amdgpu_device_gart_location(struct amdgpu_device *adev,
+				 struct amdgpu_mc *mc);
+int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev);
 void amdgpu_ttm_set_active_vram_size(struct amdgpu_device *adev, u64 size);
 int amdgpu_ttm_init(struct amdgpu_device *adev);
 void amdgpu_ttm_fini(struct amdgpu_device *adev);
-void amdgpu_program_register_sequence(struct amdgpu_device *adev,
+void amdgpu_device_program_register_sequence(struct amdgpu_device *adev,
 					     const u32 *registers,
 					     const u32 array_size);
 
@@ -1876,7 +1941,7 @@ void amdgpu_driver_lastclose_kms(struct drm_device *dev);
 int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv);
 void amdgpu_driver_postclose_kms(struct drm_device *dev,
 				 struct drm_file *file_priv);
-int amdgpu_suspend(struct amdgpu_device *adev);
+int amdgpu_device_ip_suspend(struct amdgpu_device *adev);
 int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon);
 int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon);
 u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index c04f44a90392..a29362f9ef41 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -277,7 +277,7 @@ static int acp_hw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	const struct amdgpu_ip_block *ip_block =
-		amdgpu_get_ip_block(adev, AMD_IP_BLOCK_TYPE_ACP);
+		amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_ACP);
 
 	if (!ip_block)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 5432af39a674..1d605e1c1d66 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -85,7 +85,7 @@ void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 		kfd2kgd = amdgpu_amdkfd_gfx_8_0_get_functions();
 		break;
 	default:
-		dev_info(adev->dev, "kfd not supported on this ASIC\n");
+		dev_dbg(adev->dev, "kfd not supported on this ASIC\n");
 		return;
 	}
 
@@ -93,6 +93,39 @@ void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 				   adev->pdev, kfd2kgd);
 }
 
+/**
+ * amdgpu_doorbell_get_kfd_info - Report doorbell configuration required to
+ *                                setup amdkfd
+ *
+ * @adev: amdgpu_device pointer
+ * @aperture_base: output returning doorbell aperture base physical address
+ * @aperture_size: output returning doorbell aperture size in bytes
+ * @start_offset: output returning # of doorbell bytes reserved for amdgpu.
+ *
+ * amdgpu and amdkfd share the doorbell aperture. amdgpu sets it up,
+ * takes doorbells required for its own rings and reports the setup to amdkfd.
+ * amdgpu reserved doorbells are at the start of the doorbell aperture.
+ */
+static void amdgpu_doorbell_get_kfd_info(struct amdgpu_device *adev,
+					 phys_addr_t *aperture_base,
+					 size_t *aperture_size,
+					 size_t *start_offset)
+{
+	/*
+	 * The first num_doorbells are used by amdgpu.
+	 * amdkfd takes whatever's left in the aperture.
+	 */
+	if (adev->doorbell.size > adev->doorbell.num_doorbells * sizeof(u32)) {
+		*aperture_base = adev->doorbell.base;
+		*aperture_size = adev->doorbell.size;
+		*start_offset = adev->doorbell.num_doorbells * sizeof(u32);
+	} else {
+		*aperture_base = 0;
+		*aperture_size = 0;
+		*start_offset = 0;
+	}
+}
+
 void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 {
 	int i;
@@ -242,14 +275,34 @@ void free_gtt_mem(struct kgd_dev *kgd, void *mem_obj)
 	kfree(mem);
 }
 
-uint64_t get_vmem_size(struct kgd_dev *kgd)
+void get_local_mem_info(struct kgd_dev *kgd,
+			struct kfd_local_mem_info *mem_info)
 {
-	struct amdgpu_device *adev =
-		(struct amdgpu_device *)kgd;
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+	uint64_t address_mask = adev->dev->dma_mask ? ~*adev->dev->dma_mask :
+					     ~((1ULL << 32) - 1);
+	resource_size_t aper_limit = adev->mc.aper_base + adev->mc.aper_size;
+
+	memset(mem_info, 0, sizeof(*mem_info));
+	if (!(adev->mc.aper_base & address_mask || aper_limit & address_mask)) {
+		mem_info->local_mem_size_public = adev->mc.visible_vram_size;
+		mem_info->local_mem_size_private = adev->mc.real_vram_size -
+				adev->mc.visible_vram_size;
+	} else {
+		mem_info->local_mem_size_public = 0;
+		mem_info->local_mem_size_private = adev->mc.real_vram_size;
+	}
+	mem_info->vram_width = adev->mc.vram_width;
 
-	BUG_ON(kgd == NULL);
+	pr_debug("Address base: %pap limit %pap public 0x%llx private 0x%llx\n",
+			&adev->mc.aper_base, &aper_limit,
+			mem_info->local_mem_size_public,
+			mem_info->local_mem_size_private);
 
-	return adev->mc.real_vram_size;
+	if (amdgpu_sriov_vf(adev))
+		mem_info->mem_clk_max = adev->clock.default_mclk / 100;
+	else
+		mem_info->mem_clk_max = amdgpu_dpm_get_mclk(adev, false) / 100;
 }
 
 uint64_t get_gpu_clock_counter(struct kgd_dev *kgd)
@@ -265,6 +318,39 @@ uint32_t get_max_engine_clock_in_mhz(struct kgd_dev *kgd)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 
-	/* The sclk is in quantas of 10kHz */
-	return adev->pm.dpm.dyn_state.max_clock_voltage_on_ac.sclk / 100;
+	/* the sclk is in quantas of 10kHz */
+	if (amdgpu_sriov_vf(adev))
+		return adev->clock.default_sclk / 100;
+
+	return amdgpu_dpm_get_sclk(adev, false) / 100;
+}
+
+void get_cu_info(struct kgd_dev *kgd, struct kfd_cu_info *cu_info)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+	struct amdgpu_cu_info acu_info = adev->gfx.cu_info;
+
+	memset(cu_info, 0, sizeof(*cu_info));
+	if (sizeof(cu_info->cu_bitmap) != sizeof(acu_info.bitmap))
+		return;
+
+	cu_info->cu_active_number = acu_info.number;
+	cu_info->cu_ao_mask = acu_info.ao_cu_mask;
+	memcpy(&cu_info->cu_bitmap[0], &acu_info.bitmap[0],
+	       sizeof(acu_info.bitmap));
+	cu_info->num_shader_engines = adev->gfx.config.max_shader_engines;
+	cu_info->num_shader_arrays_per_engine = adev->gfx.config.max_sh_per_se;
+	cu_info->num_cu_per_sh = adev->gfx.config.max_cu_per_sh;
+	cu_info->simd_per_cu = acu_info.simd_per_cu;
+	cu_info->max_waves_per_simd = acu_info.max_waves_per_simd;
+	cu_info->wave_front_size = acu_info.wave_front_size;
+	cu_info->max_scratch_slots_per_cu = acu_info.max_scratch_slots_per_cu;
+	cu_info->lds_size = acu_info.lds_size;
+}
+
+uint64_t amdgpu_amdkfd_get_vram_usage(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	return amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 8d689ab7e429..2a519f9062ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -56,10 +56,13 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
 			void **cpu_ptr);
 void free_gtt_mem(struct kgd_dev *kgd, void *mem_obj);
-uint64_t get_vmem_size(struct kgd_dev *kgd);
+void get_local_mem_info(struct kgd_dev *kgd,
+			struct kfd_local_mem_info *mem_info);
 uint64_t get_gpu_clock_counter(struct kgd_dev *kgd);
 
 uint32_t get_max_engine_clock_in_mhz(struct kgd_dev *kgd);
+void get_cu_info(struct kgd_dev *kgd, struct kfd_cu_info *cu_info);
+uint64_t amdgpu_amdkfd_get_vram_usage(struct kgd_dev *kgd);
 
 #define read_user_wptr(mmptr, wptr, dst)				\
 	({								\
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 47d1c132ac40..a9e6aea0e5f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -105,7 +105,14 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr,
 			uint32_t wptr_shift, uint32_t wptr_mask,
 			struct mm_struct *mm);
-static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd);
+static int kgd_hqd_dump(struct kgd_dev *kgd,
+			uint32_t pipe_id, uint32_t queue_id,
+			uint32_t (**dump)[2], uint32_t *n_regs);
+static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
+			     uint32_t __user *wptr, struct mm_struct *mm);
+static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
+			     uint32_t engine_id, uint32_t queue_id,
+			     uint32_t (**dump)[2], uint32_t *n_regs);
 static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
 				uint32_t pipe_id, uint32_t queue_id);
 
@@ -166,17 +173,19 @@ static int get_tile_config(struct kgd_dev *kgd,
 static const struct kfd2kgd_calls kfd2kgd = {
 	.init_gtt_mem_allocation = alloc_gtt_mem,
 	.free_gtt_mem = free_gtt_mem,
-	.get_vmem_size = get_vmem_size,
+	.get_local_mem_info = get_local_mem_info,
 	.get_gpu_clock_counter = get_gpu_clock_counter,
 	.get_max_engine_clock_in_mhz = get_max_engine_clock_in_mhz,
-	.alloc_pasid = amdgpu_vm_alloc_pasid,
-	.free_pasid = amdgpu_vm_free_pasid,
+	.alloc_pasid = amdgpu_pasid_alloc,
+	.free_pasid = amdgpu_pasid_free,
 	.program_sh_mem_settings = kgd_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
 	.init_pipeline = kgd_init_pipeline,
 	.init_interrupts = kgd_init_interrupts,
 	.hqd_load = kgd_hqd_load,
 	.hqd_sdma_load = kgd_hqd_sdma_load,
+	.hqd_dump = kgd_hqd_dump,
+	.hqd_sdma_dump = kgd_hqd_sdma_dump,
 	.hqd_is_occupied = kgd_hqd_is_occupied,
 	.hqd_sdma_is_occupied = kgd_hqd_sdma_is_occupied,
 	.hqd_destroy = kgd_hqd_destroy,
@@ -191,6 +200,8 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.get_fw_version = get_fw_version,
 	.set_scratch_backing_va = set_scratch_backing_va,
 	.get_tile_config = get_tile_config,
+	.get_cu_info = get_cu_info,
+	.get_vram_usage = amdgpu_amdkfd_get_vram_usage
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)
@@ -375,35 +386,129 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	return 0;
 }
 
-static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd)
+static int kgd_hqd_dump(struct kgd_dev *kgd,
+			uint32_t pipe_id, uint32_t queue_id,
+			uint32_t (**dump)[2], uint32_t *n_regs)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	uint32_t i = 0, reg;
+#define HQD_N_REGS (35+4)
+#define DUMP_REG(addr) do {				\
+		if (WARN_ON_ONCE(i >= HQD_N_REGS))	\
+			break;				\
+		(*dump)[i][0] = (addr) << 2;		\
+		(*dump)[i++][1] = RREG32(addr);		\
+	} while (0)
+
+	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	if (*dump == NULL)
+		return -ENOMEM;
+
+	acquire_queue(kgd, pipe_id, queue_id);
+
+	DUMP_REG(mmCOMPUTE_STATIC_THREAD_MGMT_SE0);
+	DUMP_REG(mmCOMPUTE_STATIC_THREAD_MGMT_SE1);
+	DUMP_REG(mmCOMPUTE_STATIC_THREAD_MGMT_SE2);
+	DUMP_REG(mmCOMPUTE_STATIC_THREAD_MGMT_SE3);
+
+	for (reg = mmCP_MQD_BASE_ADDR; reg <= mmCP_MQD_CONTROL; reg++)
+		DUMP_REG(reg);
+
+	release_queue(kgd);
+
+	WARN_ON_ONCE(i != HQD_N_REGS);
+	*n_regs = i;
+
+	return 0;
+}
+
+static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
+			     uint32_t __user *wptr, struct mm_struct *mm)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct cik_sdma_rlc_registers *m;
+	unsigned long end_jiffies;
 	uint32_t sdma_base_addr;
+	uint32_t data;
 
 	m = get_sdma_mqd(mqd);
 	sdma_base_addr = get_sdma_base_addr(m);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_VIRTUAL_ADDR,
-			m->sdma_rlc_virtual_addr);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+		m->sdma_rlc_rb_cntl & (~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK));
+
+	end_jiffies = msecs_to_jiffies(2000) + jiffies;
+	while (true) {
+		data = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		if (data & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
+			break;
+		if (time_after(jiffies, end_jiffies))
+			return -ETIME;
+		usleep_range(500, 1000);
+	}
+	if (m->sdma_engine_id) {
+		data = RREG32(mmSDMA1_GFX_CONTEXT_CNTL);
+		data = REG_SET_FIELD(data, SDMA1_GFX_CONTEXT_CNTL,
+				RESUME_CTX, 0);
+		WREG32(mmSDMA1_GFX_CONTEXT_CNTL, data);
+	} else {
+		data = RREG32(mmSDMA0_GFX_CONTEXT_CNTL);
+		data = REG_SET_FIELD(data, SDMA0_GFX_CONTEXT_CNTL,
+				RESUME_CTX, 0);
+		WREG32(mmSDMA0_GFX_CONTEXT_CNTL, data);
+	}
+
+	data = REG_SET_FIELD(m->sdma_rlc_doorbell, SDMA0_RLC0_DOORBELL,
+			     ENABLE, 1);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, data);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, m->sdma_rlc_rb_rptr);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE,
-			m->sdma_rlc_rb_base);
+	if (read_user_wptr(mm, wptr, data))
+		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, data);
+	else
+		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		       m->sdma_rlc_rb_rptr);
 
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_VIRTUAL_ADDR,
+				m->sdma_rlc_virtual_addr);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, m->sdma_rlc_rb_base);
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE_HI,
 			m->sdma_rlc_rb_base_hi);
-
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
 			m->sdma_rlc_rb_rptr_addr_lo);
-
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
 			m->sdma_rlc_rb_rptr_addr_hi);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL,
-			m->sdma_rlc_doorbell);
+	data = REG_SET_FIELD(m->sdma_rlc_rb_cntl, SDMA0_RLC0_RB_CNTL,
+			     RB_ENABLE, 1);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, data);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
-			m->sdma_rlc_rb_cntl);
+	return 0;
+}
+
+static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
+			     uint32_t engine_id, uint32_t queue_id,
+			     uint32_t (**dump)[2], uint32_t *n_regs)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	uint32_t sdma_offset = engine_id * SDMA1_REGISTER_OFFSET +
+		queue_id * KFD_CIK_SDMA_QUEUE_OFFSET;
+	uint32_t i = 0, reg;
+#undef HQD_N_REGS
+#define HQD_N_REGS (19+4)
+
+	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	if (*dump == NULL)
+		return -ENOMEM;
+
+	for (reg = mmSDMA0_RLC0_RB_CNTL; reg <= mmSDMA0_RLC0_DOORBELL; reg++)
+		DUMP_REG(sdma_offset + reg);
+	for (reg = mmSDMA0_RLC0_VIRTUAL_ADDR; reg <= mmSDMA0_RLC0_WATERMARK;
+	     reg++)
+		DUMP_REG(sdma_offset + reg);
+
+	WARN_ON_ONCE(i != HQD_N_REGS);
+	*n_regs = i;
 
 	return 0;
 }
@@ -554,7 +659,7 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 	struct cik_sdma_rlc_registers *m;
 	uint32_t sdma_base_addr;
 	uint32_t temp;
-	int timeout = utimeout;
+	unsigned long end_jiffies = (utimeout * HZ / 1000) + jiffies;
 
 	m = get_sdma_mqd(mqd);
 	sdma_base_addr = get_sdma_base_addr(m);
@@ -567,16 +672,17 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 		temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
 		if (temp & SDMA0_STATUS_REG__RB_CMD_IDLE__SHIFT)
 			break;
-		if (timeout <= 0)
+		if (time_after(jiffies, end_jiffies))
 			return -ETIME;
-		msleep(20);
-		timeout -= 20;
+		usleep_range(500, 1000);
 	}
 
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, 0);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL) |
+		SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK);
+
+	m->sdma_rlc_rb_rptr = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index 056929b8ccd0..b127259d7d85 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -45,7 +45,7 @@ enum hqd_dequeue_request_type {
 	RESET_WAVES
 };
 
-struct cik_sdma_rlc_registers;
+struct vi_sdma_mqd;
 
 /*
  * Register access functions
@@ -64,7 +64,14 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr,
 			uint32_t wptr_shift, uint32_t wptr_mask,
 			struct mm_struct *mm);
-static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd);
+static int kgd_hqd_dump(struct kgd_dev *kgd,
+			uint32_t pipe_id, uint32_t queue_id,
+			uint32_t (**dump)[2], uint32_t *n_regs);
+static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
+			     uint32_t __user *wptr, struct mm_struct *mm);
+static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
+			     uint32_t engine_id, uint32_t queue_id,
+			     uint32_t (**dump)[2], uint32_t *n_regs);
 static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
 		uint32_t pipe_id, uint32_t queue_id);
 static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd);
@@ -125,17 +132,19 @@ static int get_tile_config(struct kgd_dev *kgd,
 static const struct kfd2kgd_calls kfd2kgd = {
 	.init_gtt_mem_allocation = alloc_gtt_mem,
 	.free_gtt_mem = free_gtt_mem,
-	.get_vmem_size = get_vmem_size,
+	.get_local_mem_info = get_local_mem_info,
 	.get_gpu_clock_counter = get_gpu_clock_counter,
 	.get_max_engine_clock_in_mhz = get_max_engine_clock_in_mhz,
-	.alloc_pasid = amdgpu_vm_alloc_pasid,
-	.free_pasid = amdgpu_vm_free_pasid,
+	.alloc_pasid = amdgpu_pasid_alloc,
+	.free_pasid = amdgpu_pasid_free,
 	.program_sh_mem_settings = kgd_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
 	.init_pipeline = kgd_init_pipeline,
 	.init_interrupts = kgd_init_interrupts,
 	.hqd_load = kgd_hqd_load,
 	.hqd_sdma_load = kgd_hqd_sdma_load,
+	.hqd_dump = kgd_hqd_dump,
+	.hqd_sdma_dump = kgd_hqd_sdma_dump,
 	.hqd_is_occupied = kgd_hqd_is_occupied,
 	.hqd_sdma_is_occupied = kgd_hqd_sdma_is_occupied,
 	.hqd_destroy = kgd_hqd_destroy,
@@ -152,6 +161,8 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.get_fw_version = get_fw_version,
 	.set_scratch_backing_va = set_scratch_backing_va,
 	.get_tile_config = get_tile_config,
+	.get_cu_info = get_cu_info,
+	.get_vram_usage = amdgpu_amdkfd_get_vram_usage
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void)
@@ -268,9 +279,15 @@ static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 	return 0;
 }
 
-static inline uint32_t get_sdma_base_addr(struct cik_sdma_rlc_registers *m)
+static inline uint32_t get_sdma_base_addr(struct vi_sdma_mqd *m)
 {
-	return 0;
+	uint32_t retval;
+
+	retval = m->sdma_engine_id * SDMA1_REGISTER_OFFSET +
+		m->sdma_queue_id * KFD_VI_SDMA_QUEUE_OFFSET;
+	pr_debug("kfd: sdma base address: 0x%x\n", retval);
+
+	return retval;
 }
 
 static inline struct vi_mqd *get_mqd(void *mqd)
@@ -278,9 +295,9 @@ static inline struct vi_mqd *get_mqd(void *mqd)
 	return (struct vi_mqd *)mqd;
 }
 
-static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd)
+static inline struct vi_sdma_mqd *get_sdma_mqd(void *mqd)
 {
-	return (struct cik_sdma_rlc_registers *)mqd;
+	return (struct vi_sdma_mqd *)mqd;
 }
 
 static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
@@ -358,8 +375,138 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	return 0;
 }
 
-static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd)
+static int kgd_hqd_dump(struct kgd_dev *kgd,
+			uint32_t pipe_id, uint32_t queue_id,
+			uint32_t (**dump)[2], uint32_t *n_regs)
 {
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	uint32_t i = 0, reg;
+#define HQD_N_REGS (54+4)
+#define DUMP_REG(addr) do {				\
+		if (WARN_ON_ONCE(i >= HQD_N_REGS))	\
+			break;				\
+		(*dump)[i][0] = (addr) << 2;		\
+		(*dump)[i++][1] = RREG32(addr);		\
+	} while (0)
+
+	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	if (*dump == NULL)
+		return -ENOMEM;
+
+	acquire_queue(kgd, pipe_id, queue_id);
+
+	DUMP_REG(mmCOMPUTE_STATIC_THREAD_MGMT_SE0);
+	DUMP_REG(mmCOMPUTE_STATIC_THREAD_MGMT_SE1);
+	DUMP_REG(mmCOMPUTE_STATIC_THREAD_MGMT_SE2);
+	DUMP_REG(mmCOMPUTE_STATIC_THREAD_MGMT_SE3);
+
+	for (reg = mmCP_MQD_BASE_ADDR; reg <= mmCP_HQD_EOP_DONES; reg++)
+		DUMP_REG(reg);
+
+	release_queue(kgd);
+
+	WARN_ON_ONCE(i != HQD_N_REGS);
+	*n_regs = i;
+
+	return 0;
+}
+
+static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
+			     uint32_t __user *wptr, struct mm_struct *mm)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	struct vi_sdma_mqd *m;
+	unsigned long end_jiffies;
+	uint32_t sdma_base_addr;
+	uint32_t data;
+
+	m = get_sdma_mqd(mqd);
+	sdma_base_addr = get_sdma_base_addr(m);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+		m->sdmax_rlcx_rb_cntl & (~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK));
+
+	end_jiffies = msecs_to_jiffies(2000) + jiffies;
+	while (true) {
+		data = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		if (data & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
+			break;
+		if (time_after(jiffies, end_jiffies))
+			return -ETIME;
+		usleep_range(500, 1000);
+	}
+	if (m->sdma_engine_id) {
+		data = RREG32(mmSDMA1_GFX_CONTEXT_CNTL);
+		data = REG_SET_FIELD(data, SDMA1_GFX_CONTEXT_CNTL,
+				RESUME_CTX, 0);
+		WREG32(mmSDMA1_GFX_CONTEXT_CNTL, data);
+	} else {
+		data = RREG32(mmSDMA0_GFX_CONTEXT_CNTL);
+		data = REG_SET_FIELD(data, SDMA0_GFX_CONTEXT_CNTL,
+				RESUME_CTX, 0);
+		WREG32(mmSDMA0_GFX_CONTEXT_CNTL, data);
+	}
+
+	data = REG_SET_FIELD(m->sdmax_rlcx_doorbell, SDMA0_RLC0_DOORBELL,
+			     ENABLE, 1);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, data);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, m->sdmax_rlcx_rb_rptr);
+
+	if (read_user_wptr(mm, wptr, data))
+		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, data);
+	else
+		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		       m->sdmax_rlcx_rb_rptr);
+
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_VIRTUAL_ADDR,
+				m->sdmax_rlcx_virtual_addr);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, m->sdmax_rlcx_rb_base);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE_HI,
+			m->sdmax_rlcx_rb_base_hi);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
+			m->sdmax_rlcx_rb_rptr_addr_lo);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
+			m->sdmax_rlcx_rb_rptr_addr_hi);
+
+	data = REG_SET_FIELD(m->sdmax_rlcx_rb_cntl, SDMA0_RLC0_RB_CNTL,
+			     RB_ENABLE, 1);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, data);
+
+	return 0;
+}
+
+static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
+			     uint32_t engine_id, uint32_t queue_id,
+			     uint32_t (**dump)[2], uint32_t *n_regs)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	uint32_t sdma_offset = engine_id * SDMA1_REGISTER_OFFSET +
+		queue_id * KFD_VI_SDMA_QUEUE_OFFSET;
+	uint32_t i = 0, reg;
+#undef HQD_N_REGS
+#define HQD_N_REGS (19+4+2+3+7)
+
+	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	if (*dump == NULL)
+		return -ENOMEM;
+
+	for (reg = mmSDMA0_RLC0_RB_CNTL; reg <= mmSDMA0_RLC0_DOORBELL; reg++)
+		DUMP_REG(sdma_offset + reg);
+	for (reg = mmSDMA0_RLC0_VIRTUAL_ADDR; reg <= mmSDMA0_RLC0_WATERMARK;
+	     reg++)
+		DUMP_REG(sdma_offset + reg);
+	for (reg = mmSDMA0_RLC0_CSA_ADDR_LO; reg <= mmSDMA0_RLC0_CSA_ADDR_HI;
+	     reg++)
+		DUMP_REG(sdma_offset + reg);
+	for (reg = mmSDMA0_RLC0_IB_SUB_REMAIN; reg <= mmSDMA0_RLC0_DUMMY_REG;
+	     reg++)
+		DUMP_REG(sdma_offset + reg);
+	for (reg = mmSDMA0_RLC0_MIDCMD_DATA0; reg <= mmSDMA0_RLC0_MIDCMD_CNTL;
+	     reg++)
+		DUMP_REG(sdma_offset + reg);
+
+	WARN_ON_ONCE(i != HQD_N_REGS);
+	*n_regs = i;
+
 	return 0;
 }
 
@@ -388,7 +535,7 @@ static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
 static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
-	struct cik_sdma_rlc_registers *m;
+	struct vi_sdma_mqd *m;
 	uint32_t sdma_base_addr;
 	uint32_t sdma_rlc_rb_cntl;
 
@@ -509,10 +656,10 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 				unsigned int utimeout)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
-	struct cik_sdma_rlc_registers *m;
+	struct vi_sdma_mqd *m;
 	uint32_t sdma_base_addr;
 	uint32_t temp;
-	int timeout = utimeout;
+	unsigned long end_jiffies = (utimeout * HZ / 1000) + jiffies;
 
 	m = get_sdma_mqd(mqd);
 	sdma_base_addr = get_sdma_base_addr(m);
@@ -523,18 +670,19 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 
 	while (true) {
 		temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
-		if (temp & SDMA0_STATUS_REG__RB_CMD_IDLE__SHIFT)
+		if (temp & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
-		if (timeout <= 0)
+		if (time_after(jiffies, end_jiffies))
 			return -ETIME;
-		msleep(20);
-		timeout -= 20;
+		usleep_range(500, 1000);
 	}
 
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, 0);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL) |
+		SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK);
+
+	m->sdmax_rlcx_rb_rptr = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index f450b69323fa..bf872f694f50 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -27,6 +27,7 @@
 #include <drm/amdgpu_drm.h>
 #include "amdgpu.h"
 #include "amdgpu_atombios.h"
+#include "amdgpu_atomfirmware.h"
 #include "amdgpu_i2c.h"
 
 #include "atom.h"
@@ -690,12 +691,12 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev)
 			le32_to_cpu(firmware_info->info_21.ulDefaultDispEngineClkFreq);
 		/* set a reasonable default for DP */
 		if (adev->clock.default_dispclk < 53900) {
-			DRM_INFO("Changing default dispclk from %dMhz to 600Mhz\n",
-				 adev->clock.default_dispclk / 100);
+			DRM_DEBUG("Changing default dispclk from %dMhz to 600Mhz\n",
+				  adev->clock.default_dispclk / 100);
 			adev->clock.default_dispclk = 60000;
 		} else if (adev->clock.default_dispclk <= 60000) {
-			DRM_INFO("Changing default dispclk from %dMhz to 625Mhz\n",
-				 adev->clock.default_dispclk / 100);
+			DRM_DEBUG("Changing default dispclk from %dMhz to 625Mhz\n",
+				  adev->clock.default_dispclk / 100);
 			adev->clock.default_dispclk = 62500;
 		}
 		adev->clock.dp_extclk =
@@ -1699,7 +1700,7 @@ void amdgpu_atombios_scratch_regs_lock(struct amdgpu_device *adev, bool lock)
 	WREG32(adev->bios_scratch_reg_offset + 6, bios_6_scratch);
 }
 
-void amdgpu_atombios_scratch_regs_init(struct amdgpu_device *adev)
+static void amdgpu_atombios_scratch_regs_init(struct amdgpu_device *adev)
 {
 	uint32_t bios_2_scratch, bios_6_scratch;
 
@@ -1721,28 +1722,6 @@ void amdgpu_atombios_scratch_regs_init(struct amdgpu_device *adev)
 	WREG32(adev->bios_scratch_reg_offset + 6, bios_6_scratch);
 }
 
-void amdgpu_atombios_scratch_regs_save(struct amdgpu_device *adev)
-{
-	int i;
-
-	for (i = 0; i < AMDGPU_BIOS_NUM_SCRATCH; i++)
-		adev->bios_scratch[i] = RREG32(adev->bios_scratch_reg_offset + i);
-}
-
-void amdgpu_atombios_scratch_regs_restore(struct amdgpu_device *adev)
-{
-	int i;
-
-	/*
-	 * VBIOS will check ASIC_INIT_COMPLETE bit to decide if
-	 * execute ASIC_Init posting via driver
-	 */
-	adev->bios_scratch[7] &= ~ATOM_S7_ASIC_INIT_COMPLETE_MASK;
-
-	for (i = 0; i < AMDGPU_BIOS_NUM_SCRATCH; i++)
-		WREG32(adev->bios_scratch_reg_offset + i, adev->bios_scratch[i]);
-}
-
 void amdgpu_atombios_scratch_regs_engine_hung(struct amdgpu_device *adev,
 					      bool hung)
 {
@@ -1798,7 +1777,7 @@ void amdgpu_atombios_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
 #endif
 }
 
-int amdgpu_atombios_allocate_fb_scratch(struct amdgpu_device *adev)
+static int amdgpu_atombios_allocate_fb_scratch(struct amdgpu_device *adev)
 {
 	struct atom_context *ctx = adev->mode_info.atom_context;
 	int index = GetIndexIntoMasterTable(DATA, VRAM_UsageByFirmware);
@@ -1841,3 +1820,234 @@ int amdgpu_atombios_allocate_fb_scratch(struct amdgpu_device *adev)
 	ctx->scratch_size_bytes = usage_bytes;
 	return 0;
 }
+
+/* ATOM accessor methods */
+/*
+ * ATOM is an interpreted byte code stored in tables in the vbios.  The
+ * driver registers callbacks to access registers and the interpreter
+ * in the driver parses the tables and executes then to program specific
+ * actions (set display modes, asic init, etc.).  See amdgpu_atombios.c,
+ * atombios.h, and atom.c
+ */
+
+/**
+ * cail_pll_read - read PLL register
+ *
+ * @info: atom card_info pointer
+ * @reg: PLL register offset
+ *
+ * Provides a PLL register accessor for the atom interpreter (r4xx+).
+ * Returns the value of the PLL register.
+ */
+static uint32_t cail_pll_read(struct card_info *info, uint32_t reg)
+{
+	return 0;
+}
+
+/**
+ * cail_pll_write - write PLL register
+ *
+ * @info: atom card_info pointer
+ * @reg: PLL register offset
+ * @val: value to write to the pll register
+ *
+ * Provides a PLL register accessor for the atom interpreter (r4xx+).
+ */
+static void cail_pll_write(struct card_info *info, uint32_t reg, uint32_t val)
+{
+
+}
+
+/**
+ * cail_mc_read - read MC (Memory Controller) register
+ *
+ * @info: atom card_info pointer
+ * @reg: MC register offset
+ *
+ * Provides an MC register accessor for the atom interpreter (r4xx+).
+ * Returns the value of the MC register.
+ */
+static uint32_t cail_mc_read(struct card_info *info, uint32_t reg)
+{
+	return 0;
+}
+
+/**
+ * cail_mc_write - write MC (Memory Controller) register
+ *
+ * @info: atom card_info pointer
+ * @reg: MC register offset
+ * @val: value to write to the pll register
+ *
+ * Provides a MC register accessor for the atom interpreter (r4xx+).
+ */
+static void cail_mc_write(struct card_info *info, uint32_t reg, uint32_t val)
+{
+
+}
+
+/**
+ * cail_reg_write - write MMIO register
+ *
+ * @info: atom card_info pointer
+ * @reg: MMIO register offset
+ * @val: value to write to the pll register
+ *
+ * Provides a MMIO register accessor for the atom interpreter (r4xx+).
+ */
+static void cail_reg_write(struct card_info *info, uint32_t reg, uint32_t val)
+{
+	struct amdgpu_device *adev = info->dev->dev_private;
+
+	WREG32(reg, val);
+}
+
+/**
+ * cail_reg_read - read MMIO register
+ *
+ * @info: atom card_info pointer
+ * @reg: MMIO register offset
+ *
+ * Provides an MMIO register accessor for the atom interpreter (r4xx+).
+ * Returns the value of the MMIO register.
+ */
+static uint32_t cail_reg_read(struct card_info *info, uint32_t reg)
+{
+	struct amdgpu_device *adev = info->dev->dev_private;
+	uint32_t r;
+
+	r = RREG32(reg);
+	return r;
+}
+
+/**
+ * cail_ioreg_write - write IO register
+ *
+ * @info: atom card_info pointer
+ * @reg: IO register offset
+ * @val: value to write to the pll register
+ *
+ * Provides a IO register accessor for the atom interpreter (r4xx+).
+ */
+static void cail_ioreg_write(struct card_info *info, uint32_t reg, uint32_t val)
+{
+	struct amdgpu_device *adev = info->dev->dev_private;
+
+	WREG32_IO(reg, val);
+}
+
+/**
+ * cail_ioreg_read - read IO register
+ *
+ * @info: atom card_info pointer
+ * @reg: IO register offset
+ *
+ * Provides an IO register accessor for the atom interpreter (r4xx+).
+ * Returns the value of the IO register.
+ */
+static uint32_t cail_ioreg_read(struct card_info *info, uint32_t reg)
+{
+	struct amdgpu_device *adev = info->dev->dev_private;
+	uint32_t r;
+
+	r = RREG32_IO(reg);
+	return r;
+}
+
+static ssize_t amdgpu_atombios_get_vbios_version(struct device *dev,
+						 struct device_attribute *attr,
+						 char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	struct atom_context *ctx = adev->mode_info.atom_context;
+
+	return snprintf(buf, PAGE_SIZE, "%s\n", ctx->vbios_version);
+}
+
+static DEVICE_ATTR(vbios_version, 0444, amdgpu_atombios_get_vbios_version,
+		   NULL);
+
+/**
+ * amdgpu_atombios_fini - free the driver info and callbacks for atombios
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Frees the driver info and register access callbacks for the ATOM
+ * interpreter (r4xx+).
+ * Called at driver shutdown.
+ */
+void amdgpu_atombios_fini(struct amdgpu_device *adev)
+{
+	if (adev->mode_info.atom_context) {
+		kfree(adev->mode_info.atom_context->scratch);
+		kfree(adev->mode_info.atom_context->iio);
+	}
+	kfree(adev->mode_info.atom_context);
+	adev->mode_info.atom_context = NULL;
+	kfree(adev->mode_info.atom_card_info);
+	adev->mode_info.atom_card_info = NULL;
+	device_remove_file(adev->dev, &dev_attr_vbios_version);
+}
+
+/**
+ * amdgpu_atombios_init - init the driver info and callbacks for atombios
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Initializes the driver info and register access callbacks for the
+ * ATOM interpreter (r4xx+).
+ * Returns 0 on sucess, -ENOMEM on failure.
+ * Called at driver startup.
+ */
+int amdgpu_atombios_init(struct amdgpu_device *adev)
+{
+	struct card_info *atom_card_info =
+	    kzalloc(sizeof(struct card_info), GFP_KERNEL);
+	int ret;
+
+	if (!atom_card_info)
+		return -ENOMEM;
+
+	adev->mode_info.atom_card_info = atom_card_info;
+	atom_card_info->dev = adev->ddev;
+	atom_card_info->reg_read = cail_reg_read;
+	atom_card_info->reg_write = cail_reg_write;
+	/* needed for iio ops */
+	if (adev->rio_mem) {
+		atom_card_info->ioreg_read = cail_ioreg_read;
+		atom_card_info->ioreg_write = cail_ioreg_write;
+	} else {
+		DRM_DEBUG("PCI I/O BAR is not found. Using MMIO to access ATOM BIOS\n");
+		atom_card_info->ioreg_read = cail_reg_read;
+		atom_card_info->ioreg_write = cail_reg_write;
+	}
+	atom_card_info->mc_read = cail_mc_read;
+	atom_card_info->mc_write = cail_mc_write;
+	atom_card_info->pll_read = cail_pll_read;
+	atom_card_info->pll_write = cail_pll_write;
+
+	adev->mode_info.atom_context = amdgpu_atom_parse(atom_card_info, adev->bios);
+	if (!adev->mode_info.atom_context) {
+		amdgpu_atombios_fini(adev);
+		return -ENOMEM;
+	}
+
+	mutex_init(&adev->mode_info.atom_context->mutex);
+	if (adev->is_atom_fw) {
+		amdgpu_atomfirmware_scratch_regs_init(adev);
+		amdgpu_atomfirmware_allocate_fb_scratch(adev);
+	} else {
+		amdgpu_atombios_scratch_regs_init(adev);
+		amdgpu_atombios_allocate_fb_scratch(adev);
+	}
+
+	ret = device_create_file(adev->dev, &dev_attr_vbios_version);
+	if (ret) {
+		DRM_ERROR("Failed to create device file for VBIOS version\n");
+		return ret;
+	}
+
+	return 0;
+}
+
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
index b0d5d1d7fdba..fd8f18074f7a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
@@ -195,9 +195,6 @@ int amdgpu_atombios_init_mc_reg_table(struct amdgpu_device *adev,
 bool amdgpu_atombios_has_gpu_virtualization_table(struct amdgpu_device *adev);
 
 void amdgpu_atombios_scratch_regs_lock(struct amdgpu_device *adev, bool lock);
-void amdgpu_atombios_scratch_regs_init(struct amdgpu_device *adev);
-void amdgpu_atombios_scratch_regs_save(struct amdgpu_device *adev);
-void amdgpu_atombios_scratch_regs_restore(struct amdgpu_device *adev);
 void amdgpu_atombios_scratch_regs_engine_hung(struct amdgpu_device *adev,
 					      bool hung);
 bool amdgpu_atombios_scratch_need_asic_init(struct amdgpu_device *adev);
@@ -219,6 +216,7 @@ int amdgpu_atombios_get_svi2_info(struct amdgpu_device *adev,
 			      u8 voltage_type,
 			      u8 *svd_gpio_id, u8 *svc_gpio_id);
 
-int amdgpu_atombios_allocate_fb_scratch(struct amdgpu_device *adev);
+void amdgpu_atombios_fini(struct amdgpu_device *adev);
+int amdgpu_atombios_init(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index c13c51af0b68..e2c3c5ec42d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -14,6 +14,16 @@
 
 #include "amd_acpi.h"
 
+#define AMDGPU_PX_QUIRK_FORCE_ATPX  (1 << 0)
+
+struct amdgpu_px_quirk {
+	u32 chip_vendor;
+	u32 chip_device;
+	u32 subsys_vendor;
+	u32 subsys_device;
+	u32 px_quirk_flags;
+};
+
 struct amdgpu_atpx_functions {
 	bool px_params;
 	bool power_cntl;
@@ -35,6 +45,7 @@ struct amdgpu_atpx {
 static struct amdgpu_atpx_priv {
 	bool atpx_detected;
 	bool bridge_pm_usable;
+	unsigned int quirks;
 	/* handle for device - and atpx */
 	acpi_handle dhandle;
 	acpi_handle other_handle;
@@ -205,13 +216,19 @@ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx)
 
 	atpx->is_hybrid = false;
 	if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) {
-		printk("ATPX Hybrid Graphics\n");
-		/*
-		 * Disable legacy PM methods only when pcie port PM is usable,
-		 * otherwise the device might fail to power off or power on.
-		 */
-		atpx->functions.power_cntl = !amdgpu_atpx_priv.bridge_pm_usable;
-		atpx->is_hybrid = true;
+		if (amdgpu_atpx_priv.quirks & AMDGPU_PX_QUIRK_FORCE_ATPX) {
+			printk("ATPX Hybrid Graphics, forcing to ATPX\n");
+			atpx->functions.power_cntl = true;
+			atpx->is_hybrid = false;
+		} else {
+			printk("ATPX Hybrid Graphics\n");
+			/*
+			 * Disable legacy PM methods only when pcie port PM is usable,
+			 * otherwise the device might fail to power off or power on.
+			 */
+			atpx->functions.power_cntl = !amdgpu_atpx_priv.bridge_pm_usable;
+			atpx->is_hybrid = true;
+		}
 	}
 
 	atpx->dgpu_req_power_for_displays = false;
@@ -547,6 +564,30 @@ static const struct vga_switcheroo_handler amdgpu_atpx_handler = {
 	.get_client_id = amdgpu_atpx_get_client_id,
 };
 
+static const struct amdgpu_px_quirk amdgpu_px_quirk_list[] = {
+	/* HG _PR3 doesn't seem to work on this A+A weston board */
+	{ 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX },
+	{ 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX },
+	{ 0, 0, 0, 0, 0 },
+};
+
+static void amdgpu_atpx_get_quirks(struct pci_dev *pdev)
+{
+	const struct amdgpu_px_quirk *p = amdgpu_px_quirk_list;
+
+	/* Apply PX quirks */
+	while (p && p->chip_device != 0) {
+		if (pdev->vendor == p->chip_vendor &&
+		    pdev->device == p->chip_device &&
+		    pdev->subsystem_vendor == p->subsys_vendor &&
+		    pdev->subsystem_device == p->subsys_device) {
+			amdgpu_atpx_priv.quirks |= p->px_quirk_flags;
+			break;
+		}
+		++p;
+	}
+}
+
 /**
  * amdgpu_atpx_detect - detect whether we have PX
  *
@@ -570,6 +611,7 @@ static bool amdgpu_atpx_detect(void)
 
 		parent_pdev = pci_upstream_bridge(pdev);
 		d3_supported |= parent_pdev && parent_pdev->bridge_d3;
+		amdgpu_atpx_get_quirks(pdev);
 	}
 
 	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
@@ -579,6 +621,7 @@ static bool amdgpu_atpx_detect(void)
 
 		parent_pdev = pci_upstream_bridge(pdev);
 		d3_supported |= parent_pdev && parent_pdev->bridge_d3;
+		amdgpu_atpx_get_quirks(pdev);
 	}
 
 	if (has_atpx && vga_count == 2) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index 057e1ecd83ce..a5df80d50d44 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -93,7 +93,7 @@ static bool igp_read_bios_from_vram(struct amdgpu_device *adev)
 	resource_size_t size = 256 * 1024; /* ??? */
 
 	if (!(adev->flags & AMD_IS_APU))
-		if (amdgpu_need_post(adev))
+		if (amdgpu_device_need_post(adev))
 			return false;
 
 	adev->bios = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index f2b72c7c6857..4466f3535e2d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -801,6 +801,11 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 				else
 					strcpy(fw_name, "amdgpu/vega10_smc.bin");
 				break;
+			case CHIP_CARRIZO:
+			case CHIP_STONEY:
+			case CHIP_RAVEN:
+				adev->pm.fw_version = info->version;
+				return 0;
 			default:
 				DRM_ERROR("SMC firmware not supported\n");
 				return -EINVAL;
@@ -948,7 +953,6 @@ static int amdgpu_cgs_get_active_displays_info(struct cgs_device *cgs_device,
 								(amdgpu_crtc->v_border * 2);
 					mode_info->vblank_time_us = vblank_lines * line_time_us;
 					mode_info->refresh_rate = drm_mode_vrefresh(&amdgpu_crtc->hw_mode);
-					mode_info->ref_clock = adev->clock.spll.reference_freq;
 					mode_info = NULL;
 				}
 			}
@@ -958,7 +962,6 @@ static int amdgpu_cgs_get_active_displays_info(struct cgs_device *cgs_device,
 		if (mode_info != NULL) {
 			mode_info->vblank_time_us = adev->pm.pm_display_cfg.min_vblank_time;
 			mode_info->refresh_rate = adev->pm.pm_display_cfg.vrefresh;
-			mode_info->ref_clock = adev->clock.spll.reference_freq;
 		}
 	}
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index df9cbc78e168..8ca3783f2deb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -358,7 +358,6 @@ static int amdgpu_connector_ddc_get_modes(struct drm_connector *connector)
 	if (amdgpu_connector->edid) {
 		drm_mode_connector_update_edid_property(connector, amdgpu_connector->edid);
 		ret = drm_add_edid_modes(connector, amdgpu_connector->edid);
-		drm_edid_to_eld(connector, amdgpu_connector->edid);
 		return ret;
 	}
 	drm_mode_connector_update_edid_property(connector, NULL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index a57cec737c18..e80fc38141b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -90,6 +90,12 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 		goto free_chunk;
 	}
 
+	/* skip guilty context job */
+	if (atomic_read(&p->ctx->guilty) == 1) {
+		ret = -ECANCELED;
+		goto free_chunk;
+	}
+
 	mutex_lock(&p->ctx->lock);
 
 	/* get chunks */
@@ -337,7 +343,12 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 				 struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	u64 initial_bytes_moved, bytes_moved;
+	struct ttm_operation_ctx ctx = {
+		.interruptible = true,
+		.no_wait_gpu = false,
+		.allow_reserved_eviction = false,
+		.resv = bo->tbo.resv
+	};
 	uint32_t domain;
 	int r;
 
@@ -367,15 +378,13 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 
 retry:
 	amdgpu_ttm_placement_from_domain(bo, domain);
-	initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
-	bytes_moved = atomic64_read(&adev->num_bytes_moved) -
-		      initial_bytes_moved;
-	p->bytes_moved += bytes_moved;
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+
+	p->bytes_moved += ctx.bytes_moved;
 	if (adev->mc.visible_vram_size < adev->mc.real_vram_size &&
 	    bo->tbo.mem.mem_type == TTM_PL_VRAM &&
 	    bo->tbo.mem.start < adev->mc.visible_vram_size >> PAGE_SHIFT)
-		p->bytes_moved_vis += bytes_moved;
+		p->bytes_moved_vis += ctx.bytes_moved;
 
 	if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
 		domain = bo->allowed_domains;
@@ -390,6 +399,7 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 				struct amdgpu_bo *validated)
 {
 	uint32_t domain = validated->allowed_domains;
+	struct ttm_operation_ctx ctx = { true, false };
 	int r;
 
 	if (!p->evictable)
@@ -409,6 +419,10 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 		if (candidate->robj == validated)
 			break;
 
+		/* We can't move pinned BOs here */
+		if (bo->pin_count)
+			continue;
+
 		other = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
 
 		/* Check if this BO is in one of the domains we need space for */
@@ -427,7 +441,7 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 			bo->tbo.mem.mem_type == TTM_PL_VRAM &&
 			bo->tbo.mem.start < adev->mc.visible_vram_size >> PAGE_SHIFT;
 		initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
-		r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		bytes_moved = atomic64_read(&adev->num_bytes_moved) -
 			initial_bytes_moved;
 		p->bytes_moved += bytes_moved;
@@ -466,6 +480,7 @@ static int amdgpu_cs_validate(void *param, struct amdgpu_bo *bo)
 static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 			    struct list_head *validated)
 {
+	struct ttm_operation_ctx ctx = { true, false };
 	struct amdgpu_bo_list_entry *lobj;
 	int r;
 
@@ -483,8 +498,7 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 		    lobj->user_pages) {
 			amdgpu_ttm_placement_from_domain(bo,
 							 AMDGPU_GEM_DOMAIN_CPU);
-			r = ttm_bo_validate(&bo->tbo, &bo->placement, true,
-					    false);
+			r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 			if (r)
 				return r;
 			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
@@ -674,7 +688,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	if (!r && p->uf_entry.robj) {
 		struct amdgpu_bo *uf = p->uf_entry.robj;
 
-		r = amdgpu_ttm_bind(&uf->tbo, &uf->tbo.mem);
+		r = amdgpu_ttm_alloc_gart(&uf->tbo);
 		p->job->uf_addr += amdgpu_bo_gpu_offset(uf);
 	}
 
@@ -764,10 +778,6 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 	struct amdgpu_bo *bo;
 	int i, r;
 
-	r = amdgpu_vm_update_directories(adev, vm);
-	if (r)
-		return r;
-
 	r = amdgpu_vm_clear_freed(adev, vm, NULL);
 	if (r)
 		return r;
@@ -777,7 +787,7 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 		return r;
 
 	r = amdgpu_sync_fence(adev, &p->job->sync,
-			      fpriv->prt_va->last_pt_update);
+			      fpriv->prt_va->last_pt_update, false);
 	if (r)
 		return r;
 
@@ -791,7 +801,7 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 			return r;
 
 		f = bo_va->last_pt_update;
-		r = amdgpu_sync_fence(adev, &p->job->sync, f);
+		r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
 		if (r)
 			return r;
 	}
@@ -814,7 +824,7 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 				return r;
 
 			f = bo_va->last_pt_update;
-			r = amdgpu_sync_fence(adev, &p->job->sync, f);
+			r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
 			if (r)
 				return r;
 		}
@@ -825,7 +835,11 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(adev, &p->job->sync, vm->last_update);
+	r = amdgpu_vm_update_directories(adev, vm);
+	if (r)
+		return r;
+
+	r = amdgpu_sync_fence(adev, &p->job->sync, vm->last_update, false);
 	if (r)
 		return r;
 
@@ -861,8 +875,8 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 			struct amdgpu_bo_va_mapping *m;
 			struct amdgpu_bo *aobj = NULL;
 			struct amdgpu_cs_chunk *chunk;
+			uint64_t offset, va_start;
 			struct amdgpu_ib *ib;
-			uint64_t offset;
 			uint8_t *kptr;
 
 			chunk = &p->chunks[i];
@@ -872,14 +886,14 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 			if (chunk->chunk_id != AMDGPU_CHUNK_ID_IB)
 				continue;
 
-			r = amdgpu_cs_find_mapping(p, chunk_ib->va_start,
-						   &aobj, &m);
+			va_start = chunk_ib->va_start & AMDGPU_VA_HOLE_MASK;
+			r = amdgpu_cs_find_mapping(p, va_start, &aobj, &m);
 			if (r) {
 				DRM_ERROR("IB va_start is invalid\n");
 				return r;
 			}
 
-			if ((chunk_ib->va_start + chunk_ib->ib_bytes) >
+			if ((va_start + chunk_ib->ib_bytes) >
 			    (m->last + 1) * AMDGPU_GPU_PAGE_SIZE) {
 				DRM_ERROR("IB va_start+ib_bytes is invalid\n");
 				return -EINVAL;
@@ -892,7 +906,7 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 			}
 
 			offset = m->start * AMDGPU_GPU_PAGE_SIZE;
-			kptr += chunk_ib->va_start - offset;
+			kptr += va_start - offset;
 
 			memcpy(ib->ptr, kptr, chunk_ib->ib_bytes);
 			amdgpu_bo_kunmap(aobj);
@@ -1029,8 +1043,8 @@ static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
 			amdgpu_ctx_put(ctx);
 			return r;
 		} else if (fence) {
-			r = amdgpu_sync_fence(p->adev, &p->job->sync,
-					      fence);
+			r = amdgpu_sync_fence(p->adev, &p->job->sync, fence,
+					true);
 			dma_fence_put(fence);
 			amdgpu_ctx_put(ctx);
 			if (r)
@@ -1049,7 +1063,7 @@ static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(p->adev, &p->job->sync, fence);
+	r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, true);
 	dma_fence_put(fence);
 
 	return r;
@@ -1141,7 +1155,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 			    union drm_amdgpu_cs *cs)
 {
 	struct amdgpu_ring *ring = p->job->ring;
-	struct amd_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
+	struct drm_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
 	struct amdgpu_job *job;
 	unsigned i;
 	uint64_t seq;
@@ -1164,7 +1178,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	job = p->job;
 	p->job = NULL;
 
-	r = amd_sched_job_init(&job->base, &ring->sched, entity, p->filp);
+	r = drm_sched_job_init(&job->base, &ring->sched, entity, p->filp);
 	if (r) {
 		amdgpu_job_free(job);
 		amdgpu_mn_unlock(p->mn);
@@ -1190,11 +1204,10 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	job->uf_sequence = seq;
 
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(job->ring,
-				 amd_sched_get_job_priority(&job->base));
+	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
 
 	trace_amdgpu_cs_ioctl(job);
-	amd_sched_entity_push_job(&job->base);
+	drm_sched_entity_push_job(&job->base, entity);
 
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
 	amdgpu_mn_unlock(p->mn);
@@ -1566,6 +1579,7 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
 			   struct amdgpu_bo_va_mapping **map)
 {
 	struct amdgpu_fpriv *fpriv = parser->filp->driver_priv;
+	struct ttm_operation_ctx ctx = { false, false };
 	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_va_mapping *mapping;
 	int r;
@@ -1586,11 +1600,10 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
 	if (!((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
 		(*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
 		amdgpu_ttm_placement_from_domain(*bo, (*bo)->allowed_domains);
-		r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, false,
-				    false);
+		r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx);
 		if (r)
 			return r;
 	}
 
-	return amdgpu_ttm_bind(&(*bo)->tbo, &(*bo)->tbo.mem);
+	return amdgpu_ttm_alloc_gart(&(*bo)->tbo);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index c184468e2b2b..09d35051fdd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -28,10 +28,10 @@
 #include "amdgpu_sched.h"
 
 static int amdgpu_ctx_priority_permit(struct drm_file *filp,
-				      enum amd_sched_priority priority)
+				      enum drm_sched_priority priority)
 {
 	/* NORMAL and below are accessible by everyone */
-	if (priority <= AMD_SCHED_PRIORITY_NORMAL)
+	if (priority <= DRM_SCHED_PRIORITY_NORMAL)
 		return 0;
 
 	if (capable(CAP_SYS_NICE))
@@ -44,14 +44,14 @@ static int amdgpu_ctx_priority_permit(struct drm_file *filp,
 }
 
 static int amdgpu_ctx_init(struct amdgpu_device *adev,
-			   enum amd_sched_priority priority,
+			   enum drm_sched_priority priority,
 			   struct drm_file *filp,
 			   struct amdgpu_ctx *ctx)
 {
 	unsigned i, j;
 	int r;
 
-	if (priority < 0 || priority >= AMD_SCHED_PRIORITY_MAX)
+	if (priority < 0 || priority >= DRM_SCHED_PRIORITY_MAX)
 		return -EINVAL;
 
 	r = amdgpu_ctx_priority_permit(filp, priority);
@@ -75,22 +75,23 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 	}
 
 	ctx->reset_counter = atomic_read(&adev->gpu_reset_counter);
+	ctx->reset_counter_query = ctx->reset_counter;
 	ctx->vram_lost_counter = atomic_read(&adev->vram_lost_counter);
 	ctx->init_priority = priority;
-	ctx->override_priority = AMD_SCHED_PRIORITY_UNSET;
+	ctx->override_priority = DRM_SCHED_PRIORITY_UNSET;
 
 	/* create context entity for each ring */
 	for (i = 0; i < adev->num_rings; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
-		struct amd_sched_rq *rq;
+		struct drm_sched_rq *rq;
 
 		rq = &ring->sched.sched_rq[priority];
 
 		if (ring == &adev->gfx.kiq.ring)
 			continue;
 
-		r = amd_sched_entity_init(&ring->sched, &ctx->rings[i].entity,
-					  rq, amdgpu_sched_jobs);
+		r = drm_sched_entity_init(&ring->sched, &ctx->rings[i].entity,
+					  rq, amdgpu_sched_jobs, &ctx->guilty);
 		if (r)
 			goto failed;
 	}
@@ -103,7 +104,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 
 failed:
 	for (j = 0; j < i; j++)
-		amd_sched_entity_fini(&adev->rings[j]->sched,
+		drm_sched_entity_fini(&adev->rings[j]->sched,
 				      &ctx->rings[j].entity);
 	kfree(ctx->fences);
 	ctx->fences = NULL;
@@ -125,7 +126,7 @@ static void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
 	ctx->fences = NULL;
 
 	for (i = 0; i < adev->num_rings; i++)
-		amd_sched_entity_fini(&adev->rings[i]->sched,
+		drm_sched_entity_fini(&adev->rings[i]->sched,
 				      &ctx->rings[i].entity);
 
 	amdgpu_queue_mgr_fini(adev, &ctx->queue_mgr);
@@ -136,7 +137,7 @@ static void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
 static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
 			    struct amdgpu_fpriv *fpriv,
 			    struct drm_file *filp,
-			    enum amd_sched_priority priority,
+			    enum drm_sched_priority priority,
 			    uint32_t *id)
 {
 	struct amdgpu_ctx_mgr *mgr = &fpriv->ctx_mgr;
@@ -216,11 +217,45 @@ static int amdgpu_ctx_query(struct amdgpu_device *adev,
 	/* determine if a GPU reset has occured since the last call */
 	reset_counter = atomic_read(&adev->gpu_reset_counter);
 	/* TODO: this should ideally return NO, GUILTY, or INNOCENT. */
-	if (ctx->reset_counter == reset_counter)
+	if (ctx->reset_counter_query == reset_counter)
 		out->state.reset_status = AMDGPU_CTX_NO_RESET;
 	else
 		out->state.reset_status = AMDGPU_CTX_UNKNOWN_RESET;
-	ctx->reset_counter = reset_counter;
+	ctx->reset_counter_query = reset_counter;
+
+	mutex_unlock(&mgr->lock);
+	return 0;
+}
+
+static int amdgpu_ctx_query2(struct amdgpu_device *adev,
+	struct amdgpu_fpriv *fpriv, uint32_t id,
+	union drm_amdgpu_ctx_out *out)
+{
+	struct amdgpu_ctx *ctx;
+	struct amdgpu_ctx_mgr *mgr;
+
+	if (!fpriv)
+		return -EINVAL;
+
+	mgr = &fpriv->ctx_mgr;
+	mutex_lock(&mgr->lock);
+	ctx = idr_find(&mgr->ctx_handles, id);
+	if (!ctx) {
+		mutex_unlock(&mgr->lock);
+		return -EINVAL;
+	}
+
+	out->state.flags = 0x0;
+	out->state.hangs = 0x0;
+
+	if (ctx->reset_counter != atomic_read(&adev->gpu_reset_counter))
+		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RESET;
+
+	if (ctx->vram_lost_counter != atomic_read(&adev->vram_lost_counter))
+		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_VRAMLOST;
+
+	if (atomic_read(&ctx->guilty))
+		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_GUILTY;
 
 	mutex_unlock(&mgr->lock);
 	return 0;
@@ -231,7 +266,7 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 {
 	int r;
 	uint32_t id;
-	enum amd_sched_priority priority;
+	enum drm_sched_priority priority;
 
 	union drm_amdgpu_ctx *args = data;
 	struct amdgpu_device *adev = dev->dev_private;
@@ -243,8 +278,8 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 
 	/* For backwards compatibility reasons, we need to accept
 	 * ioctls with garbage in the priority field */
-	if (priority == AMD_SCHED_PRIORITY_INVALID)
-		priority = AMD_SCHED_PRIORITY_NORMAL;
+	if (priority == DRM_SCHED_PRIORITY_INVALID)
+		priority = DRM_SCHED_PRIORITY_NORMAL;
 
 	switch (args->in.op) {
 	case AMDGPU_CTX_OP_ALLOC_CTX:
@@ -257,6 +292,9 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 	case AMDGPU_CTX_OP_QUERY_STATE:
 		r = amdgpu_ctx_query(adev, fpriv, id, &args->out);
 		break;
+	case AMDGPU_CTX_OP_QUERY_STATE2:
+		r = amdgpu_ctx_query2(adev, fpriv, id, &args->out);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -347,18 +385,18 @@ struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,
 }
 
 void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx,
-				  enum amd_sched_priority priority)
+				  enum drm_sched_priority priority)
 {
 	int i;
 	struct amdgpu_device *adev = ctx->adev;
-	struct amd_sched_rq *rq;
-	struct amd_sched_entity *entity;
+	struct drm_sched_rq *rq;
+	struct drm_sched_entity *entity;
 	struct amdgpu_ring *ring;
-	enum amd_sched_priority ctx_prio;
+	enum drm_sched_priority ctx_prio;
 
 	ctx->override_priority = priority;
 
-	ctx_prio = (ctx->override_priority == AMD_SCHED_PRIORITY_UNSET) ?
+	ctx_prio = (ctx->override_priority == DRM_SCHED_PRIORITY_UNSET) ?
 			ctx->init_priority : ctx->override_priority;
 
 	for (i = 0; i < adev->num_rings; i++) {
@@ -369,7 +407,7 @@ void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx,
 		if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
 			continue;
 
-		amd_sched_entity_set_rq(entity, rq);
+		drm_sched_entity_set_rq(entity, rq);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
new file mode 100644
index 000000000000..ee76b468774a
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -0,0 +1,792 @@
+/*
+ * Copyright 2008 Advanced Micro Devices, Inc.
+ * Copyright 2008 Red Hat Inc.
+ * Copyright 2009 Jerome Glisse.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include <linux/kthread.h>
+#include <drm/drmP.h>
+#include <linux/debugfs.h>
+#include "amdgpu.h"
+
+/*
+ * Debugfs
+ */
+int amdgpu_debugfs_add_files(struct amdgpu_device *adev,
+			     const struct drm_info_list *files,
+			     unsigned nfiles)
+{
+	unsigned i;
+
+	for (i = 0; i < adev->debugfs_count; i++) {
+		if (adev->debugfs[i].files == files) {
+			/* Already registered */
+			return 0;
+		}
+	}
+
+	i = adev->debugfs_count + 1;
+	if (i > AMDGPU_DEBUGFS_MAX_COMPONENTS) {
+		DRM_ERROR("Reached maximum number of debugfs components.\n");
+		DRM_ERROR("Report so we increase "
+			  "AMDGPU_DEBUGFS_MAX_COMPONENTS.\n");
+		return -EINVAL;
+	}
+	adev->debugfs[adev->debugfs_count].files = files;
+	adev->debugfs[adev->debugfs_count].num_files = nfiles;
+	adev->debugfs_count = i;
+#if defined(CONFIG_DEBUG_FS)
+	drm_debugfs_create_files(files, nfiles,
+				 adev->ddev->primary->debugfs_root,
+				 adev->ddev->primary);
+#endif
+	return 0;
+}
+
+#if defined(CONFIG_DEBUG_FS)
+
+static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf,
+					size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+	bool pm_pg_lock, use_bank;
+	unsigned instance_bank, sh_bank, se_bank;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	/* are we reading registers for which a PG lock is necessary? */
+	pm_pg_lock = (*pos >> 23) & 1;
+
+	if (*pos & (1ULL << 62)) {
+		se_bank = (*pos & GENMASK_ULL(33, 24)) >> 24;
+		sh_bank = (*pos & GENMASK_ULL(43, 34)) >> 34;
+		instance_bank = (*pos & GENMASK_ULL(53, 44)) >> 44;
+
+		if (se_bank == 0x3FF)
+			se_bank = 0xFFFFFFFF;
+		if (sh_bank == 0x3FF)
+			sh_bank = 0xFFFFFFFF;
+		if (instance_bank == 0x3FF)
+			instance_bank = 0xFFFFFFFF;
+		use_bank = 1;
+	} else {
+		use_bank = 0;
+	}
+
+	*pos &= (1UL << 22) - 1;
+
+	if (use_bank) {
+		if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
+		    (se_bank != 0xFFFFFFFF && se_bank >= adev->gfx.config.max_shader_engines))
+			return -EINVAL;
+		mutex_lock(&adev->grbm_idx_mutex);
+		amdgpu_gfx_select_se_sh(adev, se_bank,
+					sh_bank, instance_bank);
+	}
+
+	if (pm_pg_lock)
+		mutex_lock(&adev->pm.mutex);
+
+	while (size) {
+		uint32_t value;
+
+		if (*pos > adev->rmmio_size)
+			goto end;
+
+		value = RREG32(*pos >> 2);
+		r = put_user(value, (uint32_t *)buf);
+		if (r) {
+			result = r;
+			goto end;
+		}
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+end:
+	if (use_bank) {
+		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+		mutex_unlock(&adev->grbm_idx_mutex);
+	}
+
+	if (pm_pg_lock)
+		mutex_unlock(&adev->pm.mutex);
+
+	return result;
+}
+
+static ssize_t amdgpu_debugfs_regs_write(struct file *f, const char __user *buf,
+					 size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+	bool pm_pg_lock, use_bank;
+	unsigned instance_bank, sh_bank, se_bank;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	/* are we reading registers for which a PG lock is necessary? */
+	pm_pg_lock = (*pos >> 23) & 1;
+
+	if (*pos & (1ULL << 62)) {
+		se_bank = (*pos & GENMASK_ULL(33, 24)) >> 24;
+		sh_bank = (*pos & GENMASK_ULL(43, 34)) >> 34;
+		instance_bank = (*pos & GENMASK_ULL(53, 44)) >> 44;
+
+		if (se_bank == 0x3FF)
+			se_bank = 0xFFFFFFFF;
+		if (sh_bank == 0x3FF)
+			sh_bank = 0xFFFFFFFF;
+		if (instance_bank == 0x3FF)
+			instance_bank = 0xFFFFFFFF;
+		use_bank = 1;
+	} else {
+		use_bank = 0;
+	}
+
+	*pos &= (1UL << 22) - 1;
+
+	if (use_bank) {
+		if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
+		    (se_bank != 0xFFFFFFFF && se_bank >= adev->gfx.config.max_shader_engines))
+			return -EINVAL;
+		mutex_lock(&adev->grbm_idx_mutex);
+		amdgpu_gfx_select_se_sh(adev, se_bank,
+					sh_bank, instance_bank);
+	}
+
+	if (pm_pg_lock)
+		mutex_lock(&adev->pm.mutex);
+
+	while (size) {
+		uint32_t value;
+
+		if (*pos > adev->rmmio_size)
+			return result;
+
+		r = get_user(value, (uint32_t *)buf);
+		if (r)
+			return r;
+
+		WREG32(*pos >> 2, value);
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	if (use_bank) {
+		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+		mutex_unlock(&adev->grbm_idx_mutex);
+	}
+
+	if (pm_pg_lock)
+		mutex_unlock(&adev->pm.mutex);
+
+	return result;
+}
+
+static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
+					size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	while (size) {
+		uint32_t value;
+
+		value = RREG32_PCIE(*pos >> 2);
+		r = put_user(value, (uint32_t *)buf);
+		if (r)
+			return r;
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	return result;
+}
+
+static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user *buf,
+					 size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	while (size) {
+		uint32_t value;
+
+		r = get_user(value, (uint32_t *)buf);
+		if (r)
+			return r;
+
+		WREG32_PCIE(*pos >> 2, value);
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	return result;
+}
+
+static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
+					size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	while (size) {
+		uint32_t value;
+
+		value = RREG32_DIDT(*pos >> 2);
+		r = put_user(value, (uint32_t *)buf);
+		if (r)
+			return r;
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	return result;
+}
+
+static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user *buf,
+					 size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	while (size) {
+		uint32_t value;
+
+		r = get_user(value, (uint32_t *)buf);
+		if (r)
+			return r;
+
+		WREG32_DIDT(*pos >> 2, value);
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	return result;
+}
+
+static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
+					size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	while (size) {
+		uint32_t value;
+
+		value = RREG32_SMC(*pos);
+		r = put_user(value, (uint32_t *)buf);
+		if (r)
+			return r;
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	return result;
+}
+
+static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *buf,
+					 size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	while (size) {
+		uint32_t value;
+
+		r = get_user(value, (uint32_t *)buf);
+		if (r)
+			return r;
+
+		WREG32_SMC(*pos, value);
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	return result;
+}
+
+static ssize_t amdgpu_debugfs_gca_config_read(struct file *f, char __user *buf,
+					size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+	uint32_t *config, no_regs = 0;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	config = kmalloc_array(256, sizeof(*config), GFP_KERNEL);
+	if (!config)
+		return -ENOMEM;
+
+	/* version, increment each time something is added */
+	config[no_regs++] = 3;
+	config[no_regs++] = adev->gfx.config.max_shader_engines;
+	config[no_regs++] = adev->gfx.config.max_tile_pipes;
+	config[no_regs++] = adev->gfx.config.max_cu_per_sh;
+	config[no_regs++] = adev->gfx.config.max_sh_per_se;
+	config[no_regs++] = adev->gfx.config.max_backends_per_se;
+	config[no_regs++] = adev->gfx.config.max_texture_channel_caches;
+	config[no_regs++] = adev->gfx.config.max_gprs;
+	config[no_regs++] = adev->gfx.config.max_gs_threads;
+	config[no_regs++] = adev->gfx.config.max_hw_contexts;
+	config[no_regs++] = adev->gfx.config.sc_prim_fifo_size_frontend;
+	config[no_regs++] = adev->gfx.config.sc_prim_fifo_size_backend;
+	config[no_regs++] = adev->gfx.config.sc_hiz_tile_fifo_size;
+	config[no_regs++] = adev->gfx.config.sc_earlyz_tile_fifo_size;
+	config[no_regs++] = adev->gfx.config.num_tile_pipes;
+	config[no_regs++] = adev->gfx.config.backend_enable_mask;
+	config[no_regs++] = adev->gfx.config.mem_max_burst_length_bytes;
+	config[no_regs++] = adev->gfx.config.mem_row_size_in_kb;
+	config[no_regs++] = adev->gfx.config.shader_engine_tile_size;
+	config[no_regs++] = adev->gfx.config.num_gpus;
+	config[no_regs++] = adev->gfx.config.multi_gpu_tile_size;
+	config[no_regs++] = adev->gfx.config.mc_arb_ramcfg;
+	config[no_regs++] = adev->gfx.config.gb_addr_config;
+	config[no_regs++] = adev->gfx.config.num_rbs;
+
+	/* rev==1 */
+	config[no_regs++] = adev->rev_id;
+	config[no_regs++] = adev->pg_flags;
+	config[no_regs++] = adev->cg_flags;
+
+	/* rev==2 */
+	config[no_regs++] = adev->family;
+	config[no_regs++] = adev->external_rev_id;
+
+	/* rev==3 */
+	config[no_regs++] = adev->pdev->device;
+	config[no_regs++] = adev->pdev->revision;
+	config[no_regs++] = adev->pdev->subsystem_device;
+	config[no_regs++] = adev->pdev->subsystem_vendor;
+
+	while (size && (*pos < no_regs * 4)) {
+		uint32_t value;
+
+		value = config[*pos >> 2];
+		r = put_user(value, (uint32_t *)buf);
+		if (r) {
+			kfree(config);
+			return r;
+		}
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	kfree(config);
+	return result;
+}
+
+static ssize_t amdgpu_debugfs_sensor_read(struct file *f, char __user *buf,
+					size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	int idx, x, outsize, r, valuesize;
+	uint32_t values[16];
+
+	if (size & 3 || *pos & 0x3)
+		return -EINVAL;
+
+	if (amdgpu_dpm == 0)
+		return -EINVAL;
+
+	/* convert offset to sensor number */
+	idx = *pos >> 2;
+
+	valuesize = sizeof(values);
+	if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->read_sensor)
+		r = amdgpu_dpm_read_sensor(adev, idx, &values[0], &valuesize);
+	else
+		return -EINVAL;
+
+	if (size > valuesize)
+		return -EINVAL;
+
+	outsize = 0;
+	x = 0;
+	if (!r) {
+		while (size) {
+			r = put_user(values[x++], (int32_t *)buf);
+			buf += 4;
+			size -= 4;
+			outsize += 4;
+		}
+	}
+
+	return !r ? outsize : r;
+}
+
+static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
+					size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = f->f_inode->i_private;
+	int r, x;
+	ssize_t result=0;
+	uint32_t offset, se, sh, cu, wave, simd, data[32];
+
+	if (size & 3 || *pos & 3)
+		return -EINVAL;
+
+	/* decode offset */
+	offset = (*pos & GENMASK_ULL(6, 0));
+	se = (*pos & GENMASK_ULL(14, 7)) >> 7;
+	sh = (*pos & GENMASK_ULL(22, 15)) >> 15;
+	cu = (*pos & GENMASK_ULL(30, 23)) >> 23;
+	wave = (*pos & GENMASK_ULL(36, 31)) >> 31;
+	simd = (*pos & GENMASK_ULL(44, 37)) >> 37;
+
+	/* switch to the specific se/sh/cu */
+	mutex_lock(&adev->grbm_idx_mutex);
+	amdgpu_gfx_select_se_sh(adev, se, sh, cu);
+
+	x = 0;
+	if (adev->gfx.funcs->read_wave_data)
+		adev->gfx.funcs->read_wave_data(adev, simd, wave, data, &x);
+
+	amdgpu_gfx_select_se_sh(adev, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF);
+	mutex_unlock(&adev->grbm_idx_mutex);
+
+	if (!x)
+		return -EINVAL;
+
+	while (size && (offset < x * 4)) {
+		uint32_t value;
+
+		value = data[offset >> 2];
+		r = put_user(value, (uint32_t *)buf);
+		if (r)
+			return r;
+
+		result += 4;
+		buf += 4;
+		offset += 4;
+		size -= 4;
+	}
+
+	return result;
+}
+
+static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
+					size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = f->f_inode->i_private;
+	int r;
+	ssize_t result = 0;
+	uint32_t offset, se, sh, cu, wave, simd, thread, bank, *data;
+
+	if (size & 3 || *pos & 3)
+		return -EINVAL;
+
+	/* decode offset */
+	offset = *pos & GENMASK_ULL(11, 0);
+	se = (*pos & GENMASK_ULL(19, 12)) >> 12;
+	sh = (*pos & GENMASK_ULL(27, 20)) >> 20;
+	cu = (*pos & GENMASK_ULL(35, 28)) >> 28;
+	wave = (*pos & GENMASK_ULL(43, 36)) >> 36;
+	simd = (*pos & GENMASK_ULL(51, 44)) >> 44;
+	thread = (*pos & GENMASK_ULL(59, 52)) >> 52;
+	bank = (*pos & GENMASK_ULL(61, 60)) >> 60;
+
+	data = kmalloc_array(1024, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	/* switch to the specific se/sh/cu */
+	mutex_lock(&adev->grbm_idx_mutex);
+	amdgpu_gfx_select_se_sh(adev, se, sh, cu);
+
+	if (bank == 0) {
+		if (adev->gfx.funcs->read_wave_vgprs)
+			adev->gfx.funcs->read_wave_vgprs(adev, simd, wave, thread, offset, size>>2, data);
+	} else {
+		if (adev->gfx.funcs->read_wave_sgprs)
+			adev->gfx.funcs->read_wave_sgprs(adev, simd, wave, offset, size>>2, data);
+	}
+
+	amdgpu_gfx_select_se_sh(adev, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF);
+	mutex_unlock(&adev->grbm_idx_mutex);
+
+	while (size) {
+		uint32_t value;
+
+		value = data[offset++];
+		r = put_user(value, (uint32_t *)buf);
+		if (r) {
+			result = r;
+			goto err;
+		}
+
+		result += 4;
+		buf += 4;
+		size -= 4;
+	}
+
+err:
+	kfree(data);
+	return result;
+}
+
+static const struct file_operations amdgpu_debugfs_regs_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_regs_read,
+	.write = amdgpu_debugfs_regs_write,
+	.llseek = default_llseek
+};
+static const struct file_operations amdgpu_debugfs_regs_didt_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_regs_didt_read,
+	.write = amdgpu_debugfs_regs_didt_write,
+	.llseek = default_llseek
+};
+static const struct file_operations amdgpu_debugfs_regs_pcie_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_regs_pcie_read,
+	.write = amdgpu_debugfs_regs_pcie_write,
+	.llseek = default_llseek
+};
+static const struct file_operations amdgpu_debugfs_regs_smc_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_regs_smc_read,
+	.write = amdgpu_debugfs_regs_smc_write,
+	.llseek = default_llseek
+};
+
+static const struct file_operations amdgpu_debugfs_gca_config_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_gca_config_read,
+	.llseek = default_llseek
+};
+
+static const struct file_operations amdgpu_debugfs_sensors_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_sensor_read,
+	.llseek = default_llseek
+};
+
+static const struct file_operations amdgpu_debugfs_wave_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_wave_read,
+	.llseek = default_llseek
+};
+static const struct file_operations amdgpu_debugfs_gpr_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_gpr_read,
+	.llseek = default_llseek
+};
+
+static const struct file_operations *debugfs_regs[] = {
+	&amdgpu_debugfs_regs_fops,
+	&amdgpu_debugfs_regs_didt_fops,
+	&amdgpu_debugfs_regs_pcie_fops,
+	&amdgpu_debugfs_regs_smc_fops,
+	&amdgpu_debugfs_gca_config_fops,
+	&amdgpu_debugfs_sensors_fops,
+	&amdgpu_debugfs_wave_fops,
+	&amdgpu_debugfs_gpr_fops,
+};
+
+static const char *debugfs_regs_names[] = {
+	"amdgpu_regs",
+	"amdgpu_regs_didt",
+	"amdgpu_regs_pcie",
+	"amdgpu_regs_smc",
+	"amdgpu_gca_config",
+	"amdgpu_sensors",
+	"amdgpu_wave",
+	"amdgpu_gpr",
+};
+
+int amdgpu_debugfs_regs_init(struct amdgpu_device *adev)
+{
+	struct drm_minor *minor = adev->ddev->primary;
+	struct dentry *ent, *root = minor->debugfs_root;
+	unsigned i, j;
+
+	for (i = 0; i < ARRAY_SIZE(debugfs_regs); i++) {
+		ent = debugfs_create_file(debugfs_regs_names[i],
+					  S_IFREG | S_IRUGO, root,
+					  adev, debugfs_regs[i]);
+		if (IS_ERR(ent)) {
+			for (j = 0; j < i; j++) {
+				debugfs_remove(adev->debugfs_regs[i]);
+				adev->debugfs_regs[i] = NULL;
+			}
+			return PTR_ERR(ent);
+		}
+
+		if (!i)
+			i_size_write(ent->d_inode, adev->rmmio_size);
+		adev->debugfs_regs[i] = ent;
+	}
+
+	return 0;
+}
+
+void amdgpu_debugfs_regs_cleanup(struct amdgpu_device *adev)
+{
+	unsigned i;
+
+	for (i = 0; i < ARRAY_SIZE(debugfs_regs); i++) {
+		if (adev->debugfs_regs[i]) {
+			debugfs_remove(adev->debugfs_regs[i]);
+			adev->debugfs_regs[i] = NULL;
+		}
+	}
+}
+
+static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct amdgpu_device *adev = dev->dev_private;
+	int r = 0, i;
+
+	/* hold on the scheduler */
+	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
+		struct amdgpu_ring *ring = adev->rings[i];
+
+		if (!ring || !ring->sched.thread)
+			continue;
+		kthread_park(ring->sched.thread);
+	}
+
+	seq_printf(m, "run ib test:\n");
+	r = amdgpu_ib_ring_tests(adev);
+	if (r)
+		seq_printf(m, "ib ring tests failed (%d).\n", r);
+	else
+		seq_printf(m, "ib ring tests passed.\n");
+
+	/* go on the scheduler */
+	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
+		struct amdgpu_ring *ring = adev->rings[i];
+
+		if (!ring || !ring->sched.thread)
+			continue;
+		kthread_unpark(ring->sched.thread);
+	}
+
+	return 0;
+}
+
+static int amdgpu_debugfs_get_vbios_dump(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct amdgpu_device *adev = dev->dev_private;
+
+	seq_write(m, adev->bios, adev->bios_size);
+	return 0;
+}
+
+static int amdgpu_debugfs_evict_vram(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *)m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct amdgpu_device *adev = dev->dev_private;
+
+	seq_printf(m, "(%d)\n", amdgpu_bo_evict_vram(adev));
+	return 0;
+}
+
+static const struct drm_info_list amdgpu_debugfs_list[] = {
+	{"amdgpu_vbios", amdgpu_debugfs_get_vbios_dump},
+	{"amdgpu_test_ib", &amdgpu_debugfs_test_ib},
+	{"amdgpu_evict_vram", &amdgpu_debugfs_evict_vram}
+};
+
+int amdgpu_debugfs_init(struct amdgpu_device *adev)
+{
+	return amdgpu_debugfs_add_files(adev, amdgpu_debugfs_list,
+					ARRAY_SIZE(amdgpu_debugfs_list));
+}
+
+#else
+int amdgpu_debugfs_init(struct amdgpu_device *adev)
+{
+	return 0;
+}
+int amdgpu_debugfs_regs_init(struct amdgpu_device *adev)
+{
+	return 0;
+}
+void amdgpu_debugfs_regs_cleanup(struct amdgpu_device *adev) { }
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h
new file mode 100644
index 000000000000..8260d8073c26
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h
@@ -0,0 +1,42 @@
+/*
+ * Copyright 2008 Advanced Micro Devices, Inc.
+ * Copyright 2008 Red Hat Inc.
+ * Copyright 2009 Jerome Glisse.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+/*
+ * Debugfs
+ */
+struct amdgpu_debugfs {
+	const struct drm_info_list	*files;
+	unsigned		num_files;
+};
+
+int amdgpu_debugfs_regs_init(struct amdgpu_device *adev);
+void amdgpu_debugfs_regs_cleanup(struct amdgpu_device *adev);
+int amdgpu_debugfs_init(struct amdgpu_device *adev);
+int amdgpu_debugfs_add_files(struct amdgpu_device *adev,
+			     const struct drm_info_list *files,
+			     unsigned nfiles);
+int amdgpu_debugfs_fence_init(struct amdgpu_device *adev);
+int amdgpu_debugfs_firmware_init(struct amdgpu_device *adev);
+int amdgpu_debugfs_gem_init(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 2c574374d9b6..00a50cc5ec9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -28,7 +28,6 @@
 #include <linux/kthread.h>
 #include <linux/console.h>
 #include <linux/slab.h>
-#include <linux/debugfs.h>
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_atomic_helper.h>
@@ -64,11 +63,6 @@ MODULE_FIRMWARE("amdgpu/raven_gpu_info.bin");
 
 #define AMDGPU_RESUME_MS		2000
 
-static int amdgpu_debugfs_regs_init(struct amdgpu_device *adev);
-static void amdgpu_debugfs_regs_cleanup(struct amdgpu_device *adev);
-static int amdgpu_debugfs_test_ib_ring_init(struct amdgpu_device *adev);
-static int amdgpu_debugfs_vbios_dump_init(struct amdgpu_device *adev);
-
 static const char *amdgpu_asic_name[] = {
 	"TAHITI",
 	"PITCAIRN",
@@ -333,7 +327,7 @@ static void amdgpu_block_invalid_wreg(struct amdgpu_device *adev,
 	BUG();
 }
 
-static int amdgpu_vram_scratch_init(struct amdgpu_device *adev)
+static int amdgpu_device_vram_scratch_init(struct amdgpu_device *adev)
 {
 	return amdgpu_bo_create_kernel(adev, AMDGPU_GPU_PAGE_SIZE,
 				       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
@@ -342,13 +336,13 @@ static int amdgpu_vram_scratch_init(struct amdgpu_device *adev)
 				       (void **)&adev->vram_scratch.ptr);
 }
 
-static void amdgpu_vram_scratch_fini(struct amdgpu_device *adev)
+static void amdgpu_device_vram_scratch_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->vram_scratch.robj, NULL, NULL);
 }
 
 /**
- * amdgpu_program_register_sequence - program an array of registers.
+ * amdgpu_device_program_register_sequence - program an array of registers.
  *
  * @adev: amdgpu_device pointer
  * @registers: pointer to the register array
@@ -357,9 +351,9 @@ static void amdgpu_vram_scratch_fini(struct amdgpu_device *adev)
  * Programs an array or registers with and and or masks.
  * This is a helper for setting golden registers.
  */
-void amdgpu_program_register_sequence(struct amdgpu_device *adev,
-				      const u32 *registers,
-				      const u32 array_size)
+void amdgpu_device_program_register_sequence(struct amdgpu_device *adev,
+					     const u32 *registers,
+					     const u32 array_size)
 {
 	u32 tmp, reg, and_mask, or_mask;
 	int i;
@@ -383,7 +377,7 @@ void amdgpu_program_register_sequence(struct amdgpu_device *adev,
 	}
 }
 
-void amdgpu_pci_config_reset(struct amdgpu_device *adev)
+void amdgpu_device_pci_config_reset(struct amdgpu_device *adev)
 {
 	pci_write_config_dword(adev->pdev, 0x7c, AMDGPU_ASIC_RESET_DATA);
 }
@@ -392,14 +386,14 @@ void amdgpu_pci_config_reset(struct amdgpu_device *adev)
  * GPU doorbell aperture helpers function.
  */
 /**
- * amdgpu_doorbell_init - Init doorbell driver information.
+ * amdgpu_device_doorbell_init - Init doorbell driver information.
  *
  * @adev: amdgpu_device pointer
  *
  * Init doorbell driver information (CIK)
  * Returns 0 on success, error on failure.
  */
-static int amdgpu_doorbell_init(struct amdgpu_device *adev)
+static int amdgpu_device_doorbell_init(struct amdgpu_device *adev)
 {
 	/* No doorbell on SI hardware generation */
 	if (adev->asic_type < CHIP_BONAIRE) {
@@ -410,6 +404,9 @@ static int amdgpu_doorbell_init(struct amdgpu_device *adev)
 		return 0;
 	}
 
+	if (pci_resource_flags(adev->pdev, 2) & IORESOURCE_UNSET)
+		return -EINVAL;
+
 	/* doorbell bar mapping */
 	adev->doorbell.base = pci_resource_start(adev->pdev, 2);
 	adev->doorbell.size = pci_resource_len(adev->pdev, 2);
@@ -429,66 +426,35 @@ static int amdgpu_doorbell_init(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_doorbell_fini - Tear down doorbell driver information.
+ * amdgpu_device_doorbell_fini - Tear down doorbell driver information.
  *
  * @adev: amdgpu_device pointer
  *
  * Tear down doorbell driver information (CIK)
  */
-static void amdgpu_doorbell_fini(struct amdgpu_device *adev)
+static void amdgpu_device_doorbell_fini(struct amdgpu_device *adev)
 {
 	iounmap(adev->doorbell.ptr);
 	adev->doorbell.ptr = NULL;
 }
 
-/**
- * amdgpu_doorbell_get_kfd_info - Report doorbell configuration required to
- *                                setup amdkfd
- *
- * @adev: amdgpu_device pointer
- * @aperture_base: output returning doorbell aperture base physical address
- * @aperture_size: output returning doorbell aperture size in bytes
- * @start_offset: output returning # of doorbell bytes reserved for amdgpu.
- *
- * amdgpu and amdkfd share the doorbell aperture. amdgpu sets it up,
- * takes doorbells required for its own rings and reports the setup to amdkfd.
- * amdgpu reserved doorbells are at the start of the doorbell aperture.
- */
-void amdgpu_doorbell_get_kfd_info(struct amdgpu_device *adev,
-				phys_addr_t *aperture_base,
-				size_t *aperture_size,
-				size_t *start_offset)
-{
-	/*
-	 * The first num_doorbells are used by amdgpu.
-	 * amdkfd takes whatever's left in the aperture.
-	 */
-	if (adev->doorbell.size > adev->doorbell.num_doorbells * sizeof(u32)) {
-		*aperture_base = adev->doorbell.base;
-		*aperture_size = adev->doorbell.size;
-		*start_offset = adev->doorbell.num_doorbells * sizeof(u32);
-	} else {
-		*aperture_base = 0;
-		*aperture_size = 0;
-		*start_offset = 0;
-	}
-}
+
 
 /*
- * amdgpu_wb_*()
+ * amdgpu_device_wb_*()
  * Writeback is the method by which the GPU updates special pages in memory
  * with the status of certain GPU events (fences, ring pointers,etc.).
  */
 
 /**
- * amdgpu_wb_fini - Disable Writeback and free memory
+ * amdgpu_device_wb_fini - Disable Writeback and free memory
  *
  * @adev: amdgpu_device pointer
  *
  * Disables Writeback and frees the Writeback memory (all asics).
  * Used at driver shutdown.
  */
-static void amdgpu_wb_fini(struct amdgpu_device *adev)
+static void amdgpu_device_wb_fini(struct amdgpu_device *adev)
 {
 	if (adev->wb.wb_obj) {
 		amdgpu_bo_free_kernel(&adev->wb.wb_obj,
@@ -499,7 +465,7 @@ static void amdgpu_wb_fini(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_wb_init- Init Writeback driver info and allocate memory
+ * amdgpu_device_wb_init- Init Writeback driver info and allocate memory
  *
  * @adev: amdgpu_device pointer
  *
@@ -507,7 +473,7 @@ static void amdgpu_wb_fini(struct amdgpu_device *adev)
  * Used at driver startup.
  * Returns 0 on success or an -error on failure.
  */
-static int amdgpu_wb_init(struct amdgpu_device *adev)
+static int amdgpu_device_wb_init(struct amdgpu_device *adev)
 {
 	int r;
 
@@ -533,7 +499,7 @@ static int amdgpu_wb_init(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_wb_get - Allocate a wb entry
+ * amdgpu_device_wb_get - Allocate a wb entry
  *
  * @adev: amdgpu_device pointer
  * @wb: wb index
@@ -541,7 +507,7 @@ static int amdgpu_wb_init(struct amdgpu_device *adev)
  * Allocate a wb slot for use by the driver (all asics).
  * Returns 0 on success or -EINVAL on failure.
  */
-int amdgpu_wb_get(struct amdgpu_device *adev, u32 *wb)
+int amdgpu_device_wb_get(struct amdgpu_device *adev, u32 *wb)
 {
 	unsigned long offset = find_first_zero_bit(adev->wb.used, adev->wb.num_wb);
 
@@ -555,61 +521,34 @@ int amdgpu_wb_get(struct amdgpu_device *adev, u32 *wb)
 }
 
 /**
- * amdgpu_wb_free - Free a wb entry
+ * amdgpu_device_wb_free - Free a wb entry
  *
  * @adev: amdgpu_device pointer
  * @wb: wb index
  *
  * Free a wb slot allocated for use by the driver (all asics)
  */
-void amdgpu_wb_free(struct amdgpu_device *adev, u32 wb)
+void amdgpu_device_wb_free(struct amdgpu_device *adev, u32 wb)
 {
 	if (wb < adev->wb.num_wb)
 		__clear_bit(wb >> 3, adev->wb.used);
 }
 
 /**
- * amdgpu_vram_location - try to find VRAM location
+ * amdgpu_device_vram_location - try to find VRAM location
  * @adev: amdgpu device structure holding all necessary informations
  * @mc: memory controller structure holding memory informations
  * @base: base address at which to put VRAM
  *
  * Function will try to place VRAM at base address provided
- * as parameter (which is so far either PCI aperture address or
- * for IGP TOM base address).
- *
- * If there is not enough space to fit the unvisible VRAM in the 32bits
- * address space then we limit the VRAM size to the aperture.
- *
- * Note: We don't explicitly enforce VRAM start to be aligned on VRAM size,
- * this shouldn't be a problem as we are using the PCI aperture as a reference.
- * Otherwise this would be needed for rv280, all r3xx, and all r4xx, but
- * not IGP.
- *
- * Note: we use mc_vram_size as on some board we need to program the mc to
- * cover the whole aperture even if VRAM size is inferior to aperture size
- * Novell bug 204882 + along with lots of ubuntu ones
- *
- * Note: when limiting vram it's safe to overwritte real_vram_size because
- * we are not in case where real_vram_size is inferior to mc_vram_size (ie
- * note afected by bogus hw of Novell bug 204882 + along with lots of ubuntu
- * ones)
- *
- * Note: IGP TOM addr should be the same as the aperture addr, we don't
- * explicitly check for that though.
- *
- * FIXME: when reducing VRAM size align new size on power of 2.
+ * as parameter.
  */
-void amdgpu_vram_location(struct amdgpu_device *adev, struct amdgpu_mc *mc, u64 base)
+void amdgpu_device_vram_location(struct amdgpu_device *adev,
+				 struct amdgpu_mc *mc, u64 base)
 {
 	uint64_t limit = (uint64_t)amdgpu_vram_limit << 20;
 
 	mc->vram_start = base;
-	if (mc->mc_vram_size > (adev->mc.mc_mask - base + 1)) {
-		dev_warn(adev->dev, "limiting VRAM to PCI aperture size\n");
-		mc->real_vram_size = mc->aper_size;
-		mc->mc_vram_size = mc->aper_size;
-	}
 	mc->vram_end = mc->vram_start + mc->mc_vram_size - 1;
 	if (limit && limit < mc->real_vram_size)
 		mc->real_vram_size = limit;
@@ -619,7 +558,7 @@ void amdgpu_vram_location(struct amdgpu_device *adev, struct amdgpu_mc *mc, u64
 }
 
 /**
- * amdgpu_gart_location - try to find GTT location
+ * amdgpu_device_gart_location - try to find GTT location
  * @adev: amdgpu device structure holding all necessary informations
  * @mc: memory controller structure holding memory informations
  *
@@ -630,7 +569,8 @@ void amdgpu_vram_location(struct amdgpu_device *adev, struct amdgpu_mc *mc, u64
  *
  * FIXME: when reducing GTT size align new size on power of 2.
  */
-void amdgpu_gart_location(struct amdgpu_device *adev, struct amdgpu_mc *mc)
+void amdgpu_device_gart_location(struct amdgpu_device *adev,
+				 struct amdgpu_mc *mc)
 {
 	u64 size_af, size_bf;
 
@@ -647,93 +587,91 @@ void amdgpu_gart_location(struct amdgpu_device *adev, struct amdgpu_mc *mc)
 			dev_warn(adev->dev, "limiting GTT\n");
 			mc->gart_size = size_af;
 		}
-		mc->gart_start = mc->vram_end + 1;
+		/* VCE doesn't like it when BOs cross a 4GB segment, so align
+		 * the GART base on a 4GB boundary as well.
+		 */
+		mc->gart_start = ALIGN(mc->vram_end + 1, 0x100000000ULL);
 	}
 	mc->gart_end = mc->gart_start + mc->gart_size - 1;
 	dev_info(adev->dev, "GTT: %lluM 0x%016llX - 0x%016llX\n",
 			mc->gart_size >> 20, mc->gart_start, mc->gart_end);
 }
 
-/*
- * Firmware Reservation functions
- */
 /**
- * amdgpu_fw_reserve_vram_fini - free fw reserved vram
+ * amdgpu_device_resize_fb_bar - try to resize FB BAR
  *
  * @adev: amdgpu_device pointer
  *
- * free fw reserved vram if it has been reserved.
+ * Try to resize FB BAR to make all VRAM CPU accessible. We try very hard not
+ * to fail, but if any of the BARs is not accessible after the size we abort
+ * driver loading by returning -ENODEV.
  */
-void amdgpu_fw_reserve_vram_fini(struct amdgpu_device *adev)
+int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev)
 {
-	amdgpu_bo_free_kernel(&adev->fw_vram_usage.reserved_bo,
-		NULL, &adev->fw_vram_usage.va);
-}
+	u64 space_needed = roundup_pow_of_two(adev->mc.real_vram_size);
+	u32 rbar_size = order_base_2(((space_needed >> 20) | 1)) - 1;
+	struct pci_bus *root;
+	struct resource *res;
+	unsigned i;
+	u16 cmd;
+	int r;
 
-/**
- * amdgpu_fw_reserve_vram_init - create bo vram reservation from fw
- *
- * @adev: amdgpu_device pointer
- *
- * create bo vram reservation from fw.
- */
-int amdgpu_fw_reserve_vram_init(struct amdgpu_device *adev)
-{
-	int r = 0;
-	u64 gpu_addr;
-	u64 vram_size = adev->mc.visible_vram_size;
+	/* Bypass for VF */
+	if (amdgpu_sriov_vf(adev))
+		return 0;
 
-	adev->fw_vram_usage.va = NULL;
-	adev->fw_vram_usage.reserved_bo = NULL;
+	/* Check if the root BUS has 64bit memory resources */
+	root = adev->pdev->bus;
+	while (root->parent)
+		root = root->parent;
 
-	if (adev->fw_vram_usage.size > 0 &&
-		adev->fw_vram_usage.size <= vram_size) {
+	pci_bus_for_each_resource(root, res, i) {
+		if (res && res->flags & (IORESOURCE_MEM | IORESOURCE_MEM_64) &&
+		    res->start > 0x100000000ull)
+			break;
+	}
 
-		r = amdgpu_bo_create(adev, adev->fw_vram_usage.size,
-			PAGE_SIZE, true, 0,
-			AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
-			AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS, NULL, NULL, 0,
-			&adev->fw_vram_usage.reserved_bo);
-		if (r)
-			goto error_create;
+	/* Trying to resize is pointless without a root hub window above 4GB */
+	if (!res)
+		return 0;
 
-		r = amdgpu_bo_reserve(adev->fw_vram_usage.reserved_bo, false);
-		if (r)
-			goto error_reserve;
-		r = amdgpu_bo_pin_restricted(adev->fw_vram_usage.reserved_bo,
-			AMDGPU_GEM_DOMAIN_VRAM,
-			adev->fw_vram_usage.start_offset,
-			(adev->fw_vram_usage.start_offset +
-			adev->fw_vram_usage.size), &gpu_addr);
-		if (r)
-			goto error_pin;
-		r = amdgpu_bo_kmap(adev->fw_vram_usage.reserved_bo,
-			&adev->fw_vram_usage.va);
-		if (r)
-			goto error_kmap;
+	/* Disable memory decoding while we change the BAR addresses and size */
+	pci_read_config_word(adev->pdev, PCI_COMMAND, &cmd);
+	pci_write_config_word(adev->pdev, PCI_COMMAND,
+			      cmd & ~PCI_COMMAND_MEMORY);
 
-		amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo);
-	}
-	return r;
+	/* Free the VRAM and doorbell BAR, we most likely need to move both. */
+	amdgpu_device_doorbell_fini(adev);
+	if (adev->asic_type >= CHIP_BONAIRE)
+		pci_release_resource(adev->pdev, 2);
 
-error_kmap:
-	amdgpu_bo_unpin(adev->fw_vram_usage.reserved_bo);
-error_pin:
-	amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo);
-error_reserve:
-	amdgpu_bo_unref(&adev->fw_vram_usage.reserved_bo);
-error_create:
-	adev->fw_vram_usage.va = NULL;
-	adev->fw_vram_usage.reserved_bo = NULL;
-	return r;
-}
+	pci_release_resource(adev->pdev, 0);
+
+	r = pci_resize_resource(adev->pdev, 0, rbar_size);
+	if (r == -ENOSPC)
+		DRM_INFO("Not enough PCI address space for a large BAR.");
+	else if (r && r != -ENOTSUPP)
+		DRM_ERROR("Problem resizing BAR0 (%d).", r);
+
+	pci_assign_unassigned_bus_resources(adev->pdev->bus);
+
+	/* When the doorbell or fb BAR isn't available we have no chance of
+	 * using the device.
+	 */
+	r = amdgpu_device_doorbell_init(adev);
+	if (r || (pci_resource_flags(adev->pdev, 0) & IORESOURCE_UNSET))
+		return -ENODEV;
+
+	pci_write_config_word(adev->pdev, PCI_COMMAND, cmd);
 
+	return 0;
+}
 
 /*
  * GPU helpers function.
  */
 /**
- * amdgpu_need_post - check if the hw need post or not
+ * amdgpu_device_need_post - check if the hw need post or not
  *
  * @adev: amdgpu_device pointer
  *
@@ -741,7 +679,7 @@ error_create:
  * or post is needed if  hw reset is performed.
  * Returns true if need or false if not.
  */
-bool amdgpu_need_post(struct amdgpu_device *adev)
+bool amdgpu_device_need_post(struct amdgpu_device *adev)
 {
 	uint32_t reg;
 
@@ -786,285 +724,9 @@ bool amdgpu_need_post(struct amdgpu_device *adev)
 	return true;
 }
 
-/**
- * amdgpu_dummy_page_init - init dummy page used by the driver
- *
- * @adev: amdgpu_device pointer
- *
- * Allocate the dummy page used by the driver (all asics).
- * This dummy page is used by the driver as a filler for gart entries
- * when pages are taken out of the GART
- * Returns 0 on sucess, -ENOMEM on failure.
- */
-int amdgpu_dummy_page_init(struct amdgpu_device *adev)
-{
-	if (adev->dummy_page.page)
-		return 0;
-	adev->dummy_page.page = alloc_page(GFP_DMA32 | GFP_KERNEL | __GFP_ZERO);
-	if (adev->dummy_page.page == NULL)
-		return -ENOMEM;
-	adev->dummy_page.addr = pci_map_page(adev->pdev, adev->dummy_page.page,
-					0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-	if (pci_dma_mapping_error(adev->pdev, adev->dummy_page.addr)) {
-		dev_err(&adev->pdev->dev, "Failed to DMA MAP the dummy page\n");
-		__free_page(adev->dummy_page.page);
-		adev->dummy_page.page = NULL;
-		return -ENOMEM;
-	}
-	return 0;
-}
-
-/**
- * amdgpu_dummy_page_fini - free dummy page used by the driver
- *
- * @adev: amdgpu_device pointer
- *
- * Frees the dummy page used by the driver (all asics).
- */
-void amdgpu_dummy_page_fini(struct amdgpu_device *adev)
-{
-	if (adev->dummy_page.page == NULL)
-		return;
-	pci_unmap_page(adev->pdev, adev->dummy_page.addr,
-			PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-	__free_page(adev->dummy_page.page);
-	adev->dummy_page.page = NULL;
-}
-
-
-/* ATOM accessor methods */
-/*
- * ATOM is an interpreted byte code stored in tables in the vbios.  The
- * driver registers callbacks to access registers and the interpreter
- * in the driver parses the tables and executes then to program specific
- * actions (set display modes, asic init, etc.).  See amdgpu_atombios.c,
- * atombios.h, and atom.c
- */
-
-/**
- * cail_pll_read - read PLL register
- *
- * @info: atom card_info pointer
- * @reg: PLL register offset
- *
- * Provides a PLL register accessor for the atom interpreter (r4xx+).
- * Returns the value of the PLL register.
- */
-static uint32_t cail_pll_read(struct card_info *info, uint32_t reg)
-{
-	return 0;
-}
-
-/**
- * cail_pll_write - write PLL register
- *
- * @info: atom card_info pointer
- * @reg: PLL register offset
- * @val: value to write to the pll register
- *
- * Provides a PLL register accessor for the atom interpreter (r4xx+).
- */
-static void cail_pll_write(struct card_info *info, uint32_t reg, uint32_t val)
-{
-
-}
-
-/**
- * cail_mc_read - read MC (Memory Controller) register
- *
- * @info: atom card_info pointer
- * @reg: MC register offset
- *
- * Provides an MC register accessor for the atom interpreter (r4xx+).
- * Returns the value of the MC register.
- */
-static uint32_t cail_mc_read(struct card_info *info, uint32_t reg)
-{
-	return 0;
-}
-
-/**
- * cail_mc_write - write MC (Memory Controller) register
- *
- * @info: atom card_info pointer
- * @reg: MC register offset
- * @val: value to write to the pll register
- *
- * Provides a MC register accessor for the atom interpreter (r4xx+).
- */
-static void cail_mc_write(struct card_info *info, uint32_t reg, uint32_t val)
-{
-
-}
-
-/**
- * cail_reg_write - write MMIO register
- *
- * @info: atom card_info pointer
- * @reg: MMIO register offset
- * @val: value to write to the pll register
- *
- * Provides a MMIO register accessor for the atom interpreter (r4xx+).
- */
-static void cail_reg_write(struct card_info *info, uint32_t reg, uint32_t val)
-{
-	struct amdgpu_device *adev = info->dev->dev_private;
-
-	WREG32(reg, val);
-}
-
-/**
- * cail_reg_read - read MMIO register
- *
- * @info: atom card_info pointer
- * @reg: MMIO register offset
- *
- * Provides an MMIO register accessor for the atom interpreter (r4xx+).
- * Returns the value of the MMIO register.
- */
-static uint32_t cail_reg_read(struct card_info *info, uint32_t reg)
-{
-	struct amdgpu_device *adev = info->dev->dev_private;
-	uint32_t r;
-
-	r = RREG32(reg);
-	return r;
-}
-
-/**
- * cail_ioreg_write - write IO register
- *
- * @info: atom card_info pointer
- * @reg: IO register offset
- * @val: value to write to the pll register
- *
- * Provides a IO register accessor for the atom interpreter (r4xx+).
- */
-static void cail_ioreg_write(struct card_info *info, uint32_t reg, uint32_t val)
-{
-	struct amdgpu_device *adev = info->dev->dev_private;
-
-	WREG32_IO(reg, val);
-}
-
-/**
- * cail_ioreg_read - read IO register
- *
- * @info: atom card_info pointer
- * @reg: IO register offset
- *
- * Provides an IO register accessor for the atom interpreter (r4xx+).
- * Returns the value of the IO register.
- */
-static uint32_t cail_ioreg_read(struct card_info *info, uint32_t reg)
-{
-	struct amdgpu_device *adev = info->dev->dev_private;
-	uint32_t r;
-
-	r = RREG32_IO(reg);
-	return r;
-}
-
-static ssize_t amdgpu_atombios_get_vbios_version(struct device *dev,
-						 struct device_attribute *attr,
-						 char *buf)
-{
-	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
-	struct atom_context *ctx = adev->mode_info.atom_context;
-
-	return snprintf(buf, PAGE_SIZE, "%s\n", ctx->vbios_version);
-}
-
-static DEVICE_ATTR(vbios_version, 0444, amdgpu_atombios_get_vbios_version,
-		   NULL);
-
-/**
- * amdgpu_atombios_fini - free the driver info and callbacks for atombios
- *
- * @adev: amdgpu_device pointer
- *
- * Frees the driver info and register access callbacks for the ATOM
- * interpreter (r4xx+).
- * Called at driver shutdown.
- */
-static void amdgpu_atombios_fini(struct amdgpu_device *adev)
-{
-	if (adev->mode_info.atom_context) {
-		kfree(adev->mode_info.atom_context->scratch);
-		kfree(adev->mode_info.atom_context->iio);
-	}
-	kfree(adev->mode_info.atom_context);
-	adev->mode_info.atom_context = NULL;
-	kfree(adev->mode_info.atom_card_info);
-	adev->mode_info.atom_card_info = NULL;
-	device_remove_file(adev->dev, &dev_attr_vbios_version);
-}
-
-/**
- * amdgpu_atombios_init - init the driver info and callbacks for atombios
- *
- * @adev: amdgpu_device pointer
- *
- * Initializes the driver info and register access callbacks for the
- * ATOM interpreter (r4xx+).
- * Returns 0 on sucess, -ENOMEM on failure.
- * Called at driver startup.
- */
-static int amdgpu_atombios_init(struct amdgpu_device *adev)
-{
-	struct card_info *atom_card_info =
-	    kzalloc(sizeof(struct card_info), GFP_KERNEL);
-	int ret;
-
-	if (!atom_card_info)
-		return -ENOMEM;
-
-	adev->mode_info.atom_card_info = atom_card_info;
-	atom_card_info->dev = adev->ddev;
-	atom_card_info->reg_read = cail_reg_read;
-	atom_card_info->reg_write = cail_reg_write;
-	/* needed for iio ops */
-	if (adev->rio_mem) {
-		atom_card_info->ioreg_read = cail_ioreg_read;
-		atom_card_info->ioreg_write = cail_ioreg_write;
-	} else {
-		DRM_INFO("PCI I/O BAR is not found. Using MMIO to access ATOM BIOS\n");
-		atom_card_info->ioreg_read = cail_reg_read;
-		atom_card_info->ioreg_write = cail_reg_write;
-	}
-	atom_card_info->mc_read = cail_mc_read;
-	atom_card_info->mc_write = cail_mc_write;
-	atom_card_info->pll_read = cail_pll_read;
-	atom_card_info->pll_write = cail_pll_write;
-
-	adev->mode_info.atom_context = amdgpu_atom_parse(atom_card_info, adev->bios);
-	if (!adev->mode_info.atom_context) {
-		amdgpu_atombios_fini(adev);
-		return -ENOMEM;
-	}
-
-	mutex_init(&adev->mode_info.atom_context->mutex);
-	if (adev->is_atom_fw) {
-		amdgpu_atomfirmware_scratch_regs_init(adev);
-		amdgpu_atomfirmware_allocate_fb_scratch(adev);
-	} else {
-		amdgpu_atombios_scratch_regs_init(adev);
-		amdgpu_atombios_allocate_fb_scratch(adev);
-	}
-
-	ret = device_create_file(adev->dev, &dev_attr_vbios_version);
-	if (ret) {
-		DRM_ERROR("Failed to create device file for VBIOS version\n");
-		return ret;
-	}
-
-	return 0;
-}
-
 /* if we get transitioned to only one device, take VGA back */
 /**
- * amdgpu_vga_set_decode - enable/disable vga decode
+ * amdgpu_device_vga_set_decode - enable/disable vga decode
  *
  * @cookie: amdgpu_device pointer
  * @state: enable/disable vga decode
@@ -1072,7 +734,7 @@ static int amdgpu_atombios_init(struct amdgpu_device *adev)
  * Enable/disable vga decode (all asics).
  * Returns VGA resource flags.
  */
-static unsigned int amdgpu_vga_set_decode(void *cookie, bool state)
+static unsigned int amdgpu_device_vga_set_decode(void *cookie, bool state)
 {
 	struct amdgpu_device *adev = cookie;
 	amdgpu_asic_set_vga_state(adev, state);
@@ -1083,7 +745,7 @@ static unsigned int amdgpu_vga_set_decode(void *cookie, bool state)
 		return VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
 }
 
-static void amdgpu_check_block_size(struct amdgpu_device *adev)
+static void amdgpu_device_check_block_size(struct amdgpu_device *adev)
 {
 	/* defines number of bits in page table versus page directory,
 	 * a page is 4KB so we have 12 bits offset, minimum 9 bits in the
@@ -1094,64 +756,32 @@ static void amdgpu_check_block_size(struct amdgpu_device *adev)
 	if (amdgpu_vm_block_size < 9) {
 		dev_warn(adev->dev, "VM page table size (%d) too small\n",
 			 amdgpu_vm_block_size);
-		goto def_value;
+		amdgpu_vm_block_size = -1;
 	}
-
-	if (amdgpu_vm_block_size > 24 ||
-	    (amdgpu_vm_size * 1024) < (1ull << amdgpu_vm_block_size)) {
-		dev_warn(adev->dev, "VM page table size (%d) too large\n",
-			 amdgpu_vm_block_size);
-		goto def_value;
-	}
-
-	return;
-
-def_value:
-	amdgpu_vm_block_size = -1;
 }
 
-static void amdgpu_check_vm_size(struct amdgpu_device *adev)
+static void amdgpu_device_check_vm_size(struct amdgpu_device *adev)
 {
 	/* no need to check the default value */
 	if (amdgpu_vm_size == -1)
 		return;
 
-	if (!is_power_of_2(amdgpu_vm_size)) {
-		dev_warn(adev->dev, "VM size (%d) must be a power of 2\n",
-			 amdgpu_vm_size);
-		goto def_value;
-	}
-
 	if (amdgpu_vm_size < 1) {
 		dev_warn(adev->dev, "VM size (%d) too small, min is 1GB\n",
 			 amdgpu_vm_size);
-		goto def_value;
-	}
-
-	/*
-	 * Max GPUVM size for Cayman, SI, CI VI are 40 bits.
-	 */
-	if (amdgpu_vm_size > 1024) {
-		dev_warn(adev->dev, "VM size (%d) too large, max is 1TB\n",
-			 amdgpu_vm_size);
-		goto def_value;
+		amdgpu_vm_size = -1;
 	}
-
-	return;
-
-def_value:
-	amdgpu_vm_size = -1;
 }
 
 /**
- * amdgpu_check_arguments - validate module params
+ * amdgpu_device_check_arguments - validate module params
  *
  * @adev: amdgpu_device pointer
  *
  * Validates certain module parameters and updates
  * the associated values used by the driver (all asics).
  */
-static void amdgpu_check_arguments(struct amdgpu_device *adev)
+static void amdgpu_device_check_arguments(struct amdgpu_device *adev)
 {
 	if (amdgpu_sched_jobs < 4) {
 		dev_warn(adev->dev, "sched jobs (%d) must be at least 4\n",
@@ -1184,9 +814,9 @@ static void amdgpu_check_arguments(struct amdgpu_device *adev)
 		amdgpu_vm_fragment_size = -1;
 	}
 
-	amdgpu_check_vm_size(adev);
+	amdgpu_device_check_vm_size(adev);
 
-	amdgpu_check_block_size(adev);
+	amdgpu_device_check_block_size(adev);
 
 	if (amdgpu_vram_page_split != -1 && (amdgpu_vram_page_split < 16 ||
 	    !is_power_of_2(amdgpu_vram_page_split))) {
@@ -1194,6 +824,11 @@ static void amdgpu_check_arguments(struct amdgpu_device *adev)
 			 amdgpu_vram_page_split);
 		amdgpu_vram_page_split = 1024;
 	}
+
+	if (amdgpu_lockup_timeout == 0) {
+		dev_warn(adev->dev, "lockup_timeout msut be > 0, adjusting to 10000\n");
+		amdgpu_lockup_timeout = 10000;
+	}
 }
 
 /**
@@ -1257,9 +892,9 @@ static const struct vga_switcheroo_client_ops amdgpu_switcheroo_ops = {
 	.can_switch = amdgpu_switcheroo_can_switch,
 };
 
-int amdgpu_set_clockgating_state(struct amdgpu_device *adev,
-				  enum amd_ip_block_type block_type,
-				  enum amd_clockgating_state state)
+int amdgpu_device_ip_set_clockgating_state(struct amdgpu_device *adev,
+					   enum amd_ip_block_type block_type,
+					   enum amd_clockgating_state state)
 {
 	int i, r = 0;
 
@@ -1279,9 +914,9 @@ int amdgpu_set_clockgating_state(struct amdgpu_device *adev,
 	return r;
 }
 
-int amdgpu_set_powergating_state(struct amdgpu_device *adev,
-				  enum amd_ip_block_type block_type,
-				  enum amd_powergating_state state)
+int amdgpu_device_ip_set_powergating_state(struct amdgpu_device *adev,
+					   enum amd_ip_block_type block_type,
+					   enum amd_powergating_state state)
 {
 	int i, r = 0;
 
@@ -1301,7 +936,8 @@ int amdgpu_set_powergating_state(struct amdgpu_device *adev,
 	return r;
 }
 
-void amdgpu_get_clockgating_state(struct amdgpu_device *adev, u32 *flags)
+void amdgpu_device_ip_get_clockgating_state(struct amdgpu_device *adev,
+					    u32 *flags)
 {
 	int i;
 
@@ -1313,8 +949,8 @@ void amdgpu_get_clockgating_state(struct amdgpu_device *adev, u32 *flags)
 	}
 }
 
-int amdgpu_wait_for_idle(struct amdgpu_device *adev,
-			 enum amd_ip_block_type block_type)
+int amdgpu_device_ip_wait_for_idle(struct amdgpu_device *adev,
+				   enum amd_ip_block_type block_type)
 {
 	int i, r;
 
@@ -1332,8 +968,8 @@ int amdgpu_wait_for_idle(struct amdgpu_device *adev,
 
 }
 
-bool amdgpu_is_idle(struct amdgpu_device *adev,
-		    enum amd_ip_block_type block_type)
+bool amdgpu_device_ip_is_idle(struct amdgpu_device *adev,
+			      enum amd_ip_block_type block_type)
 {
 	int i;
 
@@ -1347,8 +983,9 @@ bool amdgpu_is_idle(struct amdgpu_device *adev,
 
 }
 
-struct amdgpu_ip_block * amdgpu_get_ip_block(struct amdgpu_device *adev,
-					     enum amd_ip_block_type type)
+struct amdgpu_ip_block *
+amdgpu_device_ip_get_ip_block(struct amdgpu_device *adev,
+			      enum amd_ip_block_type type)
 {
 	int i;
 
@@ -1360,7 +997,7 @@ struct amdgpu_ip_block * amdgpu_get_ip_block(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_ip_block_version_cmp
+ * amdgpu_device_ip_block_version_cmp
  *
  * @adev: amdgpu_device pointer
  * @type: enum amd_ip_block_type
@@ -1370,11 +1007,11 @@ struct amdgpu_ip_block * amdgpu_get_ip_block(struct amdgpu_device *adev,
  * return 0 if equal or greater
  * return 1 if smaller or the ip_block doesn't exist
  */
-int amdgpu_ip_block_version_cmp(struct amdgpu_device *adev,
-				enum amd_ip_block_type type,
-				u32 major, u32 minor)
+int amdgpu_device_ip_block_version_cmp(struct amdgpu_device *adev,
+				       enum amd_ip_block_type type,
+				       u32 major, u32 minor)
 {
-	struct amdgpu_ip_block *ip_block = amdgpu_get_ip_block(adev, type);
+	struct amdgpu_ip_block *ip_block = amdgpu_device_ip_get_ip_block(adev, type);
 
 	if (ip_block && ((ip_block->version->major > major) ||
 			((ip_block->version->major == major) &&
@@ -1385,7 +1022,7 @@ int amdgpu_ip_block_version_cmp(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_ip_block_add
+ * amdgpu_device_ip_block_add
  *
  * @adev: amdgpu_device pointer
  * @ip_block_version: pointer to the IP to add
@@ -1393,8 +1030,8 @@ int amdgpu_ip_block_version_cmp(struct amdgpu_device *adev,
  * Adds the IP block driver information to the collection of IPs
  * on the asic.
  */
-int amdgpu_ip_block_add(struct amdgpu_device *adev,
-			const struct amdgpu_ip_block_version *ip_block_version)
+int amdgpu_device_ip_block_add(struct amdgpu_device *adev,
+			       const struct amdgpu_ip_block_version *ip_block_version)
 {
 	if (!ip_block_version)
 		return -EINVAL;
@@ -1550,7 +1187,7 @@ out:
 	return err;
 }
 
-static int amdgpu_early_init(struct amdgpu_device *adev)
+static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 {
 	int i, r;
 
@@ -1622,10 +1259,12 @@ static int amdgpu_early_init(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
+	amdgpu_amdkfd_device_probe(adev);
+
 	if (amdgpu_sriov_vf(adev)) {
 		r = amdgpu_virt_request_full_gpu(adev, true);
 		if (r)
-			return r;
+			return -EAGAIN;
 	}
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
@@ -1657,7 +1296,7 @@ static int amdgpu_early_init(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int amdgpu_init(struct amdgpu_device *adev)
+static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 {
 	int i, r;
 
@@ -1673,7 +1312,7 @@ static int amdgpu_init(struct amdgpu_device *adev)
 		adev->ip_blocks[i].status.sw = true;
 		/* need to do gmc hw init early so we can allocate gpu mem */
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
-			r = amdgpu_vram_scratch_init(adev);
+			r = amdgpu_device_vram_scratch_init(adev);
 			if (r) {
 				DRM_ERROR("amdgpu_vram_scratch_init failed %d\n", r);
 				return r;
@@ -1683,9 +1322,9 @@ static int amdgpu_init(struct amdgpu_device *adev)
 				DRM_ERROR("hw_init %d failed %d\n", i, r);
 				return r;
 			}
-			r = amdgpu_wb_init(adev);
+			r = amdgpu_device_wb_init(adev);
 			if (r) {
-				DRM_ERROR("amdgpu_wb_init failed %d\n", r);
+				DRM_ERROR("amdgpu_device_wb_init failed %d\n", r);
 				return r;
 			}
 			adev->ip_blocks[i].status.hw = true;
@@ -1716,21 +1355,26 @@ static int amdgpu_init(struct amdgpu_device *adev)
 		adev->ip_blocks[i].status.hw = true;
 	}
 
+	amdgpu_amdkfd_device_init(adev);
+
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_release_full_gpu(adev, true);
+
 	return 0;
 }
 
-static void amdgpu_fill_reset_magic(struct amdgpu_device *adev)
+static void amdgpu_device_fill_reset_magic(struct amdgpu_device *adev)
 {
 	memcpy(adev->reset_magic, adev->gart.ptr, AMDGPU_RESET_MAGIC_NUM);
 }
 
-static bool amdgpu_check_vram_lost(struct amdgpu_device *adev)
+static bool amdgpu_device_check_vram_lost(struct amdgpu_device *adev)
 {
 	return !!memcmp(adev->gart.ptr, adev->reset_magic,
 			AMDGPU_RESET_MAGIC_NUM);
 }
 
-static int amdgpu_late_set_cg_state(struct amdgpu_device *adev)
+static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 {
 	int i = 0, r;
 
@@ -1753,7 +1397,7 @@ static int amdgpu_late_set_cg_state(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int amdgpu_late_init(struct amdgpu_device *adev)
+static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 {
 	int i = 0, r;
 
@@ -1774,15 +1418,16 @@ static int amdgpu_late_init(struct amdgpu_device *adev)
 	mod_delayed_work(system_wq, &adev->late_init_work,
 			msecs_to_jiffies(AMDGPU_RESUME_MS));
 
-	amdgpu_fill_reset_magic(adev);
+	amdgpu_device_fill_reset_magic(adev);
 
 	return 0;
 }
 
-static int amdgpu_fini(struct amdgpu_device *adev)
+static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 {
 	int i, r;
 
+	amdgpu_amdkfd_device_fini(adev);
 	/* need to disable SMC first */
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.hw)
@@ -1811,8 +1456,9 @@ static int amdgpu_fini(struct amdgpu_device *adev)
 		if (!adev->ip_blocks[i].status.hw)
 			continue;
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
-			amdgpu_wb_fini(adev);
-			amdgpu_vram_scratch_fini(adev);
+			amdgpu_free_static_csa(adev);
+			amdgpu_device_wb_fini(adev);
+			amdgpu_device_vram_scratch_fini(adev);
 		}
 
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
@@ -1837,9 +1483,6 @@ static int amdgpu_fini(struct amdgpu_device *adev)
 		adev->ip_blocks[i].status.hw = false;
 	}
 
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
-		amdgpu_ucode_fini_bo(adev);
-
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.sw)
 			continue;
@@ -1862,19 +1505,20 @@ static int amdgpu_fini(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_sriov_vf(adev))
-		amdgpu_virt_release_full_gpu(adev, false);
+		if (amdgpu_virt_release_full_gpu(adev, false))
+			DRM_ERROR("failed to release exclusive mode on fini\n");
 
 	return 0;
 }
 
-static void amdgpu_late_init_func_handler(struct work_struct *work)
+static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
 {
 	struct amdgpu_device *adev =
 		container_of(work, struct amdgpu_device, late_init_work.work);
-	amdgpu_late_set_cg_state(adev);
+	amdgpu_device_ip_late_set_cg_state(adev);
 }
 
-int amdgpu_suspend(struct amdgpu_device *adev)
+int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 {
 	int i, r;
 
@@ -1882,10 +1526,10 @@ int amdgpu_suspend(struct amdgpu_device *adev)
 		amdgpu_virt_request_full_gpu(adev, false);
 
 	/* ungate SMC block first */
-	r = amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_SMC,
-					 AMD_CG_STATE_UNGATE);
+	r = amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_SMC,
+						   AMD_CG_STATE_UNGATE);
 	if (r) {
-		DRM_ERROR("set_clockgating_state(ungate) SMC failed %d\n",r);
+		DRM_ERROR("set_clockgating_state(ungate) SMC failed %d\n", r);
 	}
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
@@ -1915,7 +1559,7 @@ int amdgpu_suspend(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int amdgpu_sriov_reinit_early(struct amdgpu_device *adev)
+static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 {
 	int i, r;
 
@@ -1944,7 +1588,7 @@ static int amdgpu_sriov_reinit_early(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int amdgpu_sriov_reinit_late(struct amdgpu_device *adev)
+static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev)
 {
 	int i, r;
 
@@ -1977,7 +1621,7 @@ static int amdgpu_sriov_reinit_late(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int amdgpu_resume_phase1(struct amdgpu_device *adev)
+static int amdgpu_device_ip_resume_phase1(struct amdgpu_device *adev)
 {
 	int i, r;
 
@@ -2000,7 +1644,7 @@ static int amdgpu_resume_phase1(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int amdgpu_resume_phase2(struct amdgpu_device *adev)
+static int amdgpu_device_ip_resume_phase2(struct amdgpu_device *adev)
 {
 	int i, r;
 
@@ -2022,14 +1666,14 @@ static int amdgpu_resume_phase2(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int amdgpu_resume(struct amdgpu_device *adev)
+static int amdgpu_device_ip_resume(struct amdgpu_device *adev)
 {
 	int r;
 
-	r = amdgpu_resume_phase1(adev);
+	r = amdgpu_device_ip_resume_phase1(adev);
 	if (r)
 		return r;
-	r = amdgpu_resume_phase2(adev);
+	r = amdgpu_device_ip_resume_phase2(adev);
 
 	return r;
 }
@@ -2166,8 +1810,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->mn_lock);
 	mutex_init(&adev->virt.vf_errors.lock);
 	hash_init(adev->mn_hash);
+	mutex_init(&adev->lock_reset);
 
-	amdgpu_check_arguments(adev);
+	amdgpu_device_check_arguments(adev);
 
 	spin_lock_init(&adev->mmio_idx_lock);
 	spin_lock_init(&adev->smc_idx_lock);
@@ -2182,13 +1827,11 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	INIT_LIST_HEAD(&adev->shadow_list);
 	mutex_init(&adev->shadow_list_lock);
 
-	INIT_LIST_HEAD(&adev->gtt_list);
-	spin_lock_init(&adev->gtt_list_lock);
-
 	INIT_LIST_HEAD(&adev->ring_lru_list);
 	spin_lock_init(&adev->ring_lru_list_lock);
 
-	INIT_DELAYED_WORK(&adev->late_init_work, amdgpu_late_init_func_handler);
+	INIT_DELAYED_WORK(&adev->late_init_work,
+			  amdgpu_device_ip_late_init_func_handler);
 
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */
@@ -2208,7 +1851,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	DRM_INFO("register mmio size: %u\n", (unsigned)adev->rmmio_size);
 
 	/* doorbell bar mapping */
-	amdgpu_doorbell_init(adev);
+	amdgpu_device_doorbell_init(adev);
 
 	/* io port mapping */
 	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
@@ -2222,17 +1865,15 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		DRM_INFO("PCI I/O BAR is not found.\n");
 
 	/* early init functions */
-	r = amdgpu_early_init(adev);
+	r = amdgpu_device_ip_early_init(adev);
 	if (r)
 		return r;
 
 	/* if we have > 1 VGA cards, then disable the amdgpu VGA resources */
 	/* this will fail for cards that aren't VGA class devices, just
 	 * ignore it */
-	vga_client_register(adev->pdev, adev, NULL, amdgpu_vga_set_decode);
+	vga_client_register(adev->pdev, adev, NULL, amdgpu_device_vga_set_decode);
 
-	if (amdgpu_runtime_pm == 1)
-		runtime = true;
 	if (amdgpu_device_is_px(ddev))
 		runtime = true;
 	if (!pci_is_thunderbolt_attached(adev->pdev))
@@ -2258,7 +1899,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	amdgpu_device_detect_sriov_bios(adev);
 
 	/* Post card if necessary */
-	if (amdgpu_need_post(adev)) {
+	if (amdgpu_device_need_post(adev)) {
 		if (!adev->bios) {
 			dev_err(adev->dev, "no vBIOS found\n");
 			r = -EINVAL;
@@ -2270,8 +1911,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 			dev_err(adev->dev, "gpu post error!\n");
 			goto failed;
 		}
-	} else {
-		DRM_INFO("GPU post is not needed\n");
 	}
 
 	if (adev->is_atom_fw) {
@@ -2306,11 +1945,23 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	/* init the mode config */
 	drm_mode_config_init(adev->ddev);
 
-	r = amdgpu_init(adev);
+	r = amdgpu_device_ip_init(adev);
 	if (r) {
-		dev_err(adev->dev, "amdgpu_init failed\n");
+		/* failed in exclusive mode due to timeout */
+		if (amdgpu_sriov_vf(adev) &&
+		    !amdgpu_sriov_runtime(adev) &&
+		    amdgpu_virt_mmio_blocked(adev) &&
+		    !amdgpu_virt_wait_reset(adev)) {
+			dev_err(adev->dev, "VF exclusive mode timeout\n");
+			/* Don't send request since VF is inactive. */
+			adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME;
+			adev->virt.ops = NULL;
+			r = -EAGAIN;
+			goto failed;
+		}
+		dev_err(adev->dev, "amdgpu_device_ip_init failed\n");
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL, 0, 0);
-		amdgpu_fini(adev);
+		amdgpu_device_ip_fini(adev);
 		goto failed;
 	}
 
@@ -2346,7 +1997,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		DRM_ERROR("registering pm debugfs failed (%d).\n", r);
 
-	r = amdgpu_gem_debugfs_init(adev);
+	r = amdgpu_debugfs_gem_init(adev);
 	if (r)
 		DRM_ERROR("registering gem debugfs failed (%d).\n", r);
 
@@ -2354,17 +2005,13 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		DRM_ERROR("registering register debugfs failed (%d).\n", r);
 
-	r = amdgpu_debugfs_test_ib_ring_init(adev);
-	if (r)
-		DRM_ERROR("registering register test ib ring debugfs failed (%d).\n", r);
-
 	r = amdgpu_debugfs_firmware_init(adev);
 	if (r)
 		DRM_ERROR("registering firmware debugfs failed (%d).\n", r);
 
-	r = amdgpu_debugfs_vbios_dump_init(adev);
+	r = amdgpu_debugfs_init(adev);
 	if (r)
-		DRM_ERROR("Creating vbios dump debugfs failed (%d).\n", r);
+		DRM_ERROR("Creating debugfs files failed (%d).\n", r);
 
 	if ((amdgpu_testing & 1)) {
 		if (adev->accel_working)
@@ -2382,9 +2029,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	/* enable clockgating, etc. after ib tests, etc. since some blocks require
 	 * explicit gating rather than handling it automatically.
 	 */
-	r = amdgpu_late_init(adev);
+	r = amdgpu_device_ip_late_init(adev);
 	if (r) {
-		dev_err(adev->dev, "amdgpu_late_init failed\n");
+		dev_err(adev->dev, "amdgpu_device_ip_late_init failed\n");
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_LATE_INIT_FAIL, 0, r);
 		goto failed;
 	}
@@ -2395,6 +2042,7 @@ failed:
 	amdgpu_vf_error_trans_all(adev);
 	if (runtime)
 		vga_switcheroo_fini_domain_pm_ops(adev->dev);
+
 	return r;
 }
 
@@ -2414,13 +2062,11 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	adev->shutdown = true;
 	if (adev->mode_info.mode_config_initialized)
 		drm_crtc_force_disable_all(adev->ddev);
-	/* evict vram memory */
-	amdgpu_bo_evict_vram(adev);
+
 	amdgpu_ib_pool_fini(adev);
-	amdgpu_fw_reserve_vram_fini(adev);
 	amdgpu_fence_driver_fini(adev);
 	amdgpu_fbdev_fini(adev);
-	r = amdgpu_fini(adev);
+	r = amdgpu_device_ip_fini(adev);
 	if (adev->firmware.gpu_info_fw) {
 		release_firmware(adev->firmware.gpu_info_fw);
 		adev->firmware.gpu_info_fw = NULL;
@@ -2443,7 +2089,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	adev->rio_mem = NULL;
 	iounmap(adev->rmmio);
 	adev->rmmio = NULL;
-	amdgpu_doorbell_fini(adev);
+	amdgpu_device_doorbell_fini(adev);
 	amdgpu_pm_sysfs_fini(adev);
 	amdgpu_debugfs_regs_cleanup(adev);
 }
@@ -2524,7 +2170,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 
 	amdgpu_fence_driver_suspend(adev);
 
-	r = amdgpu_suspend(adev);
+	r = amdgpu_device_ip_suspend(adev);
 
 	/* evict remaining vram memory
 	 * This second call to evict vram is to evict the gart page table
@@ -2532,7 +2178,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 	 */
 	amdgpu_bo_evict_vram(adev);
 
-	amdgpu_atombios_scratch_regs_save(adev);
 	pci_save_state(dev->pdev);
 	if (suspend) {
 		/* Shut down the device */
@@ -2581,18 +2226,17 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 		if (r)
 			goto unlock;
 	}
-	amdgpu_atombios_scratch_regs_restore(adev);
 
 	/* post card */
-	if (amdgpu_need_post(adev)) {
+	if (amdgpu_device_need_post(adev)) {
 		r = amdgpu_atom_asic_init(adev->mode_info.atom_context);
 		if (r)
 			DRM_ERROR("amdgpu asic init failed\n");
 	}
 
-	r = amdgpu_resume(adev);
+	r = amdgpu_device_ip_resume(adev);
 	if (r) {
-		DRM_ERROR("amdgpu_resume failed (%d).\n", r);
+		DRM_ERROR("amdgpu_device_ip_resume failed (%d).\n", r);
 		goto unlock;
 	}
 	amdgpu_fence_driver_resume(adev);
@@ -2603,7 +2247,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 			DRM_ERROR("ib ring test failed (%d).\n", r);
 	}
 
-	r = amdgpu_late_init(adev);
+	r = amdgpu_device_ip_late_init(adev);
 	if (r)
 		goto unlock;
 
@@ -2683,7 +2327,7 @@ unlock:
 	return r;
 }
 
-static bool amdgpu_check_soft_reset(struct amdgpu_device *adev)
+static bool amdgpu_device_ip_check_soft_reset(struct amdgpu_device *adev)
 {
 	int i;
 	bool asic_hang = false;
@@ -2705,7 +2349,7 @@ static bool amdgpu_check_soft_reset(struct amdgpu_device *adev)
 	return asic_hang;
 }
 
-static int amdgpu_pre_soft_reset(struct amdgpu_device *adev)
+static int amdgpu_device_ip_pre_soft_reset(struct amdgpu_device *adev)
 {
 	int i, r = 0;
 
@@ -2723,7 +2367,7 @@ static int amdgpu_pre_soft_reset(struct amdgpu_device *adev)
 	return 0;
 }
 
-static bool amdgpu_need_full_reset(struct amdgpu_device *adev)
+static bool amdgpu_device_ip_need_full_reset(struct amdgpu_device *adev)
 {
 	int i;
 
@@ -2744,7 +2388,7 @@ static bool amdgpu_need_full_reset(struct amdgpu_device *adev)
 	return false;
 }
 
-static int amdgpu_soft_reset(struct amdgpu_device *adev)
+static int amdgpu_device_ip_soft_reset(struct amdgpu_device *adev)
 {
 	int i, r = 0;
 
@@ -2762,7 +2406,7 @@ static int amdgpu_soft_reset(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int amdgpu_post_soft_reset(struct amdgpu_device *adev)
+static int amdgpu_device_ip_post_soft_reset(struct amdgpu_device *adev)
 {
 	int i, r = 0;
 
@@ -2779,18 +2423,10 @@ static int amdgpu_post_soft_reset(struct amdgpu_device *adev)
 	return 0;
 }
 
-bool amdgpu_need_backup(struct amdgpu_device *adev)
-{
-	if (adev->flags & AMD_IS_APU)
-		return false;
-
-	return amdgpu_lockup_timeout > 0 ? true : false;
-}
-
-static int amdgpu_recover_vram_from_shadow(struct amdgpu_device *adev,
-					   struct amdgpu_ring *ring,
-					   struct amdgpu_bo *bo,
-					   struct dma_fence **fence)
+static int amdgpu_device_recover_vram_from_shadow(struct amdgpu_device *adev,
+						  struct amdgpu_ring *ring,
+						  struct amdgpu_bo *bo,
+						  struct dma_fence **fence)
 {
 	uint32_t domain;
 	int r;
@@ -2822,163 +2458,181 @@ err:
 	return r;
 }
 
-/**
- * amdgpu_sriov_gpu_reset - reset the asic
+/*
+ * amdgpu_device_reset - reset ASIC/GPU for bare-metal or passthrough
  *
  * @adev: amdgpu device pointer
- * @job: which job trigger hang
+ * @reset_flags: output param tells caller the reset result
  *
- * Attempt the reset the GPU if it has hung (all asics).
- * for SRIOV case.
- * Returns 0 for success or an error on failure.
- */
-int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job)
+ * attempt to do soft-reset or full-reset and reinitialize Asic
+ * return 0 means successed otherwise failed
+*/
+static int amdgpu_device_reset(struct amdgpu_device *adev,
+			       uint64_t* reset_flags)
 {
-	int i, j, r = 0;
-	int resched;
-	struct amdgpu_bo *bo, *tmp;
-	struct amdgpu_ring *ring;
-	struct dma_fence *fence = NULL, *next = NULL;
+	bool need_full_reset, vram_lost = 0;
+	int r;
 
-	mutex_lock(&adev->virt.lock_reset);
-	atomic_inc(&adev->gpu_reset_counter);
-	adev->in_sriov_reset = true;
+	need_full_reset = amdgpu_device_ip_need_full_reset(adev);
 
-	/* block TTM */
-	resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
+	if (!need_full_reset) {
+		amdgpu_device_ip_pre_soft_reset(adev);
+		r = amdgpu_device_ip_soft_reset(adev);
+		amdgpu_device_ip_post_soft_reset(adev);
+		if (r || amdgpu_device_ip_check_soft_reset(adev)) {
+			DRM_INFO("soft reset failed, will fallback to full reset!\n");
+			need_full_reset = true;
+		}
 
-	/* we start from the ring trigger GPU hang */
-	j = job ? job->ring->idx : 0;
+	}
 
-	/* block scheduler */
-	for (i = j; i < j + AMDGPU_MAX_RINGS; ++i) {
-		ring = adev->rings[i % AMDGPU_MAX_RINGS];
-		if (!ring || !ring->sched.thread)
-			continue;
+	if (need_full_reset) {
+		r = amdgpu_device_ip_suspend(adev);
 
-		kthread_park(ring->sched.thread);
+retry:
+		r = amdgpu_asic_reset(adev);
+		/* post card */
+		amdgpu_atom_asic_init(adev->mode_info.atom_context);
 
-		if (job && j != i)
-			continue;
+		if (!r) {
+			dev_info(adev->dev, "GPU reset succeeded, trying to resume\n");
+			r = amdgpu_device_ip_resume_phase1(adev);
+			if (r)
+				goto out;
 
-		/* here give the last chance to check if job removed from mirror-list
-		 * since we already pay some time on kthread_park */
-		if (job && list_empty(&job->base.node)) {
-			kthread_unpark(ring->sched.thread);
-			goto give_up_reset;
+			vram_lost = amdgpu_device_check_vram_lost(adev);
+			if (vram_lost) {
+				DRM_ERROR("VRAM is lost!\n");
+				atomic_inc(&adev->vram_lost_counter);
+			}
+
+			r = amdgpu_gtt_mgr_recover(
+				&adev->mman.bdev.man[TTM_PL_TT]);
+			if (r)
+				goto out;
+
+			r = amdgpu_device_ip_resume_phase2(adev);
+			if (r)
+				goto out;
+
+			if (vram_lost)
+				amdgpu_device_fill_reset_magic(adev);
 		}
+	}
 
-		if (amd_sched_invalidate_job(&job->base, amdgpu_job_hang_limit))
-			amd_sched_job_kickout(&job->base);
+out:
+	if (!r) {
+		amdgpu_irq_gpu_reset_resume_helper(adev);
+		r = amdgpu_ib_ring_tests(adev);
+		if (r) {
+			dev_err(adev->dev, "ib ring test failed (%d).\n", r);
+			r = amdgpu_device_ip_suspend(adev);
+			need_full_reset = true;
+			goto retry;
+		}
+	}
 
-		/* only do job_reset on the hang ring if @job not NULL */
-		amd_sched_hw_job_reset(&ring->sched);
+	if (reset_flags) {
+		if (vram_lost)
+			(*reset_flags) |= AMDGPU_RESET_INFO_VRAM_LOST;
 
-		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
-		amdgpu_fence_driver_force_completion_ring(ring);
+		if (need_full_reset)
+			(*reset_flags) |= AMDGPU_RESET_INFO_FULLRESET;
 	}
 
-	/* request to take full control of GPU before re-initialization  */
-	if (job)
-		amdgpu_virt_reset_gpu(adev);
-	else
-		amdgpu_virt_request_full_gpu(adev, true);
+	return r;
+}
 
+/*
+ * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf
+ *
+ * @adev: amdgpu device pointer
+ * @reset_flags: output param tells caller the reset result
+ *
+ * do VF FLR and reinitialize Asic
+ * return 0 means successed otherwise failed
+*/
+static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
+				     uint64_t *reset_flags,
+				     bool from_hypervisor)
+{
+	int r;
+
+	if (from_hypervisor)
+		r = amdgpu_virt_request_full_gpu(adev, true);
+	else
+		r = amdgpu_virt_reset_gpu(adev);
+	if (r)
+		return r;
 
 	/* Resume IP prior to SMC */
-	amdgpu_sriov_reinit_early(adev);
+	r = amdgpu_device_ip_reinit_early_sriov(adev);
+	if (r)
+		goto error;
 
 	/* we need recover gart prior to run SMC/CP/SDMA resume */
-	amdgpu_ttm_recover_gart(adev);
+	amdgpu_gtt_mgr_recover(&adev->mman.bdev.man[TTM_PL_TT]);
 
 	/* now we are okay to resume SMC/CP/SDMA */
-	amdgpu_sriov_reinit_late(adev);
+	r = amdgpu_device_ip_reinit_late_sriov(adev);
+	if (r)
+		goto error;
 
 	amdgpu_irq_gpu_reset_resume_helper(adev);
-
-	if (amdgpu_ib_ring_tests(adev))
+	r = amdgpu_ib_ring_tests(adev);
+	if (r)
 		dev_err(adev->dev, "[GPU_RESET] ib ring test failed (%d).\n", r);
 
+error:
 	/* release full control of GPU after ib test */
 	amdgpu_virt_release_full_gpu(adev, true);
 
-	DRM_INFO("recover vram bo from shadow\n");
-
-	ring = adev->mman.buffer_funcs_ring;
-	mutex_lock(&adev->shadow_list_lock);
-	list_for_each_entry_safe(bo, tmp, &adev->shadow_list, shadow_list) {
-		next = NULL;
-		amdgpu_recover_vram_from_shadow(adev, ring, bo, &next);
-		if (fence) {
-			r = dma_fence_wait(fence, false);
-			if (r) {
-				WARN(r, "recovery from shadow isn't completed\n");
-				break;
-			}
-		}
-
-		dma_fence_put(fence);
-		fence = next;
-	}
-	mutex_unlock(&adev->shadow_list_lock);
-
-	if (fence) {
-		r = dma_fence_wait(fence, false);
-		if (r)
-			WARN(r, "recovery from shadow isn't completed\n");
-	}
-	dma_fence_put(fence);
-
-	for (i = j; i < j + AMDGPU_MAX_RINGS; ++i) {
-		ring = adev->rings[i % AMDGPU_MAX_RINGS];
-		if (!ring || !ring->sched.thread)
-			continue;
-
-		if (job && j != i) {
-			kthread_unpark(ring->sched.thread);
-			continue;
+	if (reset_flags) {
+		if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
+			(*reset_flags) |= AMDGPU_RESET_INFO_VRAM_LOST;
+			atomic_inc(&adev->vram_lost_counter);
 		}
 
-		amd_sched_job_recovery(&ring->sched);
-		kthread_unpark(ring->sched.thread);
+		/* VF FLR or hotlink reset is always full-reset */
+		(*reset_flags) |= AMDGPU_RESET_INFO_FULLRESET;
 	}
 
-	drm_helper_resume_force_mode(adev->ddev);
-give_up_reset:
-	ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched);
-	if (r) {
-		/* bad news, how to tell it to userspace ? */
-		dev_info(adev->dev, "GPU reset failed\n");
-	} else {
-		dev_info(adev->dev, "GPU reset successed!\n");
-	}
-
-	adev->in_sriov_reset = false;
-	mutex_unlock(&adev->virt.lock_reset);
 	return r;
 }
 
 /**
- * amdgpu_gpu_reset - reset the asic
+ * amdgpu_device_gpu_recover - reset the asic and recover scheduler
  *
  * @adev: amdgpu device pointer
+ * @job: which job trigger hang
+ * @force forces reset regardless of amdgpu_gpu_recovery
  *
- * Attempt the reset the GPU if it has hung (all asics).
+ * Attempt to reset the GPU if it has hung (all asics).
  * Returns 0 for success or an error on failure.
  */
-int amdgpu_gpu_reset(struct amdgpu_device *adev)
+int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
+			      struct amdgpu_job *job, bool force)
 {
 	struct drm_atomic_state *state = NULL;
-	int i, r;
-	int resched;
-	bool need_full_reset, vram_lost = false;
+	uint64_t reset_flags = 0;
+	int i, r, resched;
 
-	if (!amdgpu_check_soft_reset(adev)) {
+	if (!force && !amdgpu_device_ip_check_soft_reset(adev)) {
 		DRM_INFO("No hardware hang detected. Did some blocks stall?\n");
 		return 0;
 	}
 
+	if (!force && (amdgpu_gpu_recovery == 0 ||
+			(amdgpu_gpu_recovery == -1  && !amdgpu_sriov_vf(adev)))) {
+		DRM_INFO("GPU recovery disabled.\n");
+		return 0;
+	}
+
+	dev_info(adev->dev, "GPU reset begin!\n");
+
+	mutex_lock(&adev->lock_reset);
 	atomic_inc(&adev->gpu_reset_counter);
+	adev->in_gpu_reset = 1;
 
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
@@ -2992,69 +2646,26 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev)
 
 		if (!ring || !ring->sched.thread)
 			continue;
-		kthread_park(ring->sched.thread);
-		amd_sched_hw_job_reset(&ring->sched);
-	}
-	/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
-	amdgpu_fence_driver_force_completion(adev);
 
-	need_full_reset = amdgpu_need_full_reset(adev);
+		/* only focus on the ring hit timeout if &job not NULL */
+		if (job && job->ring->idx != i)
+			continue;
 
-	if (!need_full_reset) {
-		amdgpu_pre_soft_reset(adev);
-		r = amdgpu_soft_reset(adev);
-		amdgpu_post_soft_reset(adev);
-		if (r || amdgpu_check_soft_reset(adev)) {
-			DRM_INFO("soft reset failed, will fallback to full reset!\n");
-			need_full_reset = true;
-		}
-	}
+		kthread_park(ring->sched.thread);
+		drm_sched_hw_job_reset(&ring->sched, &job->base);
 
-	if (need_full_reset) {
-		r = amdgpu_suspend(adev);
+		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
+		amdgpu_fence_driver_force_completion(ring);
+	}
 
-retry:
-		amdgpu_atombios_scratch_regs_save(adev);
-		r = amdgpu_asic_reset(adev);
-		amdgpu_atombios_scratch_regs_restore(adev);
-		/* post card */
-		amdgpu_atom_asic_init(adev->mode_info.atom_context);
+	if (amdgpu_sriov_vf(adev))
+		r = amdgpu_device_reset_sriov(adev, &reset_flags, job ? false : true);
+	else
+		r = amdgpu_device_reset(adev, &reset_flags);
 
-		if (!r) {
-			dev_info(adev->dev, "GPU reset succeeded, trying to resume\n");
-			r = amdgpu_resume_phase1(adev);
-			if (r)
-				goto out;
-			vram_lost = amdgpu_check_vram_lost(adev);
-			if (vram_lost) {
-				DRM_ERROR("VRAM is lost!\n");
-				atomic_inc(&adev->vram_lost_counter);
-			}
-			r = amdgpu_ttm_recover_gart(adev);
-			if (r)
-				goto out;
-			r = amdgpu_resume_phase2(adev);
-			if (r)
-				goto out;
-			if (vram_lost)
-				amdgpu_fill_reset_magic(adev);
-		}
-	}
-out:
 	if (!r) {
-		amdgpu_irq_gpu_reset_resume_helper(adev);
-		r = amdgpu_ib_ring_tests(adev);
-		if (r) {
-			dev_err(adev->dev, "ib ring test failed (%d).\n", r);
-			r = amdgpu_suspend(adev);
-			need_full_reset = true;
-			goto retry;
-		}
-		/**
-		 * recovery vm page tables, since we cannot depend on VRAM is
-		 * consistent after gpu full reset.
-		 */
-		if (need_full_reset && amdgpu_need_backup(adev)) {
+		if (((reset_flags & AMDGPU_RESET_INFO_FULLRESET) && !(adev->flags & AMD_IS_APU)) ||
+			(reset_flags & AMDGPU_RESET_INFO_VRAM_LOST)) {
 			struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
 			struct amdgpu_bo *bo, *tmp;
 			struct dma_fence *fence = NULL, *next = NULL;
@@ -3063,7 +2674,7 @@ out:
 			mutex_lock(&adev->shadow_list_lock);
 			list_for_each_entry_safe(bo, tmp, &adev->shadow_list, shadow_list) {
 				next = NULL;
-				amdgpu_recover_vram_from_shadow(adev, ring, bo, &next);
+				amdgpu_device_recover_vram_from_shadow(adev, ring, bo, &next);
 				if (fence) {
 					r = dma_fence_wait(fence, false);
 					if (r) {
@@ -3083,44 +2694,60 @@ out:
 			}
 			dma_fence_put(fence);
 		}
+
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = adev->rings[i];
 
 			if (!ring || !ring->sched.thread)
 				continue;
 
-			amd_sched_job_recovery(&ring->sched);
+			/* only focus on the ring hit timeout if &job not NULL */
+			if (job && job->ring->idx != i)
+				continue;
+
+			drm_sched_job_recovery(&ring->sched);
 			kthread_unpark(ring->sched.thread);
 		}
 	} else {
-		dev_err(adev->dev, "asic resume failed (%d).\n", r);
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
-			if (adev->rings[i] && adev->rings[i]->sched.thread) {
-				kthread_unpark(adev->rings[i]->sched.thread);
-			}
+			struct amdgpu_ring *ring = adev->rings[i];
+
+			if (!ring || !ring->sched.thread)
+				continue;
+
+			/* only focus on the ring hit timeout if &job not NULL */
+			if (job && job->ring->idx != i)
+				continue;
+
+			kthread_unpark(adev->rings[i]->sched.thread);
 		}
 	}
 
 	if (amdgpu_device_has_dc_support(adev)) {
-		r = drm_atomic_helper_resume(adev->ddev, state);
+		if (drm_atomic_helper_resume(adev->ddev, state))
+			dev_info(adev->dev, "drm resume failed:%d\n", r);
 		amdgpu_dm_display_resume(adev);
-	} else
+	} else {
 		drm_helper_resume_force_mode(adev->ddev);
+	}
 
 	ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched);
+
 	if (r) {
 		/* bad news, how to tell it to userspace ? */
-		dev_info(adev->dev, "GPU reset failed\n");
-	}
-	else {
-		dev_info(adev->dev, "GPU reset successed!\n");
+		dev_info(adev->dev, "GPU reset(%d) failed\n", atomic_read(&adev->gpu_reset_counter));
+		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
+	} else {
+		dev_info(adev->dev, "GPU reset(%d) successed!\n",atomic_read(&adev->gpu_reset_counter));
 	}
 
 	amdgpu_vf_error_trans_all(adev);
+	adev->in_gpu_reset = 0;
+	mutex_unlock(&adev->lock_reset);
 	return r;
 }
 
-void amdgpu_get_pcie_info(struct amdgpu_device *adev)
+void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 {
 	u32 mask;
 	int ret;
@@ -3212,773 +2839,3 @@ void amdgpu_get_pcie_info(struct amdgpu_device *adev)
 	}
 }
 
-/*
- * Debugfs
- */
-int amdgpu_debugfs_add_files(struct amdgpu_device *adev,
-			     const struct drm_info_list *files,
-			     unsigned nfiles)
-{
-	unsigned i;
-
-	for (i = 0; i < adev->debugfs_count; i++) {
-		if (adev->debugfs[i].files == files) {
-			/* Already registered */
-			return 0;
-		}
-	}
-
-	i = adev->debugfs_count + 1;
-	if (i > AMDGPU_DEBUGFS_MAX_COMPONENTS) {
-		DRM_ERROR("Reached maximum number of debugfs components.\n");
-		DRM_ERROR("Report so we increase "
-			  "AMDGPU_DEBUGFS_MAX_COMPONENTS.\n");
-		return -EINVAL;
-	}
-	adev->debugfs[adev->debugfs_count].files = files;
-	adev->debugfs[adev->debugfs_count].num_files = nfiles;
-	adev->debugfs_count = i;
-#if defined(CONFIG_DEBUG_FS)
-	drm_debugfs_create_files(files, nfiles,
-				 adev->ddev->primary->debugfs_root,
-				 adev->ddev->primary);
-#endif
-	return 0;
-}
-
-#if defined(CONFIG_DEBUG_FS)
-
-static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf,
-					size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = file_inode(f)->i_private;
-	ssize_t result = 0;
-	int r;
-	bool pm_pg_lock, use_bank;
-	unsigned instance_bank, sh_bank, se_bank;
-
-	if (size & 0x3 || *pos & 0x3)
-		return -EINVAL;
-
-	/* are we reading registers for which a PG lock is necessary? */
-	pm_pg_lock = (*pos >> 23) & 1;
-
-	if (*pos & (1ULL << 62)) {
-		se_bank = (*pos & GENMASK_ULL(33, 24)) >> 24;
-		sh_bank = (*pos & GENMASK_ULL(43, 34)) >> 34;
-		instance_bank = (*pos & GENMASK_ULL(53, 44)) >> 44;
-
-		if (se_bank == 0x3FF)
-			se_bank = 0xFFFFFFFF;
-		if (sh_bank == 0x3FF)
-			sh_bank = 0xFFFFFFFF;
-		if (instance_bank == 0x3FF)
-			instance_bank = 0xFFFFFFFF;
-		use_bank = 1;
-	} else {
-		use_bank = 0;
-	}
-
-	*pos &= (1UL << 22) - 1;
-
-	if (use_bank) {
-		if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
-		    (se_bank != 0xFFFFFFFF && se_bank >= adev->gfx.config.max_shader_engines))
-			return -EINVAL;
-		mutex_lock(&adev->grbm_idx_mutex);
-		amdgpu_gfx_select_se_sh(adev, se_bank,
-					sh_bank, instance_bank);
-	}
-
-	if (pm_pg_lock)
-		mutex_lock(&adev->pm.mutex);
-
-	while (size) {
-		uint32_t value;
-
-		if (*pos > adev->rmmio_size)
-			goto end;
-
-		value = RREG32(*pos >> 2);
-		r = put_user(value, (uint32_t *)buf);
-		if (r) {
-			result = r;
-			goto end;
-		}
-
-		result += 4;
-		buf += 4;
-		*pos += 4;
-		size -= 4;
-	}
-
-end:
-	if (use_bank) {
-		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
-		mutex_unlock(&adev->grbm_idx_mutex);
-	}
-
-	if (pm_pg_lock)
-		mutex_unlock(&adev->pm.mutex);
-
-	return result;
-}
-
-static ssize_t amdgpu_debugfs_regs_write(struct file *f, const char __user *buf,
-					 size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = file_inode(f)->i_private;
-	ssize_t result = 0;
-	int r;
-	bool pm_pg_lock, use_bank;
-	unsigned instance_bank, sh_bank, se_bank;
-
-	if (size & 0x3 || *pos & 0x3)
-		return -EINVAL;
-
-	/* are we reading registers for which a PG lock is necessary? */
-	pm_pg_lock = (*pos >> 23) & 1;
-
-	if (*pos & (1ULL << 62)) {
-		se_bank = (*pos & GENMASK_ULL(33, 24)) >> 24;
-		sh_bank = (*pos & GENMASK_ULL(43, 34)) >> 34;
-		instance_bank = (*pos & GENMASK_ULL(53, 44)) >> 44;
-
-		if (se_bank == 0x3FF)
-			se_bank = 0xFFFFFFFF;
-		if (sh_bank == 0x3FF)
-			sh_bank = 0xFFFFFFFF;
-		if (instance_bank == 0x3FF)
-			instance_bank = 0xFFFFFFFF;
-		use_bank = 1;
-	} else {
-		use_bank = 0;
-	}
-
-	*pos &= (1UL << 22) - 1;
-
-	if (use_bank) {
-		if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
-		    (se_bank != 0xFFFFFFFF && se_bank >= adev->gfx.config.max_shader_engines))
-			return -EINVAL;
-		mutex_lock(&adev->grbm_idx_mutex);
-		amdgpu_gfx_select_se_sh(adev, se_bank,
-					sh_bank, instance_bank);
-	}
-
-	if (pm_pg_lock)
-		mutex_lock(&adev->pm.mutex);
-
-	while (size) {
-		uint32_t value;
-
-		if (*pos > adev->rmmio_size)
-			return result;
-
-		r = get_user(value, (uint32_t *)buf);
-		if (r)
-			return r;
-
-		WREG32(*pos >> 2, value);
-
-		result += 4;
-		buf += 4;
-		*pos += 4;
-		size -= 4;
-	}
-
-	if (use_bank) {
-		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
-		mutex_unlock(&adev->grbm_idx_mutex);
-	}
-
-	if (pm_pg_lock)
-		mutex_unlock(&adev->pm.mutex);
-
-	return result;
-}
-
-static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
-					size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = file_inode(f)->i_private;
-	ssize_t result = 0;
-	int r;
-
-	if (size & 0x3 || *pos & 0x3)
-		return -EINVAL;
-
-	while (size) {
-		uint32_t value;
-
-		value = RREG32_PCIE(*pos >> 2);
-		r = put_user(value, (uint32_t *)buf);
-		if (r)
-			return r;
-
-		result += 4;
-		buf += 4;
-		*pos += 4;
-		size -= 4;
-	}
-
-	return result;
-}
-
-static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user *buf,
-					 size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = file_inode(f)->i_private;
-	ssize_t result = 0;
-	int r;
-
-	if (size & 0x3 || *pos & 0x3)
-		return -EINVAL;
-
-	while (size) {
-		uint32_t value;
-
-		r = get_user(value, (uint32_t *)buf);
-		if (r)
-			return r;
-
-		WREG32_PCIE(*pos >> 2, value);
-
-		result += 4;
-		buf += 4;
-		*pos += 4;
-		size -= 4;
-	}
-
-	return result;
-}
-
-static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
-					size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = file_inode(f)->i_private;
-	ssize_t result = 0;
-	int r;
-
-	if (size & 0x3 || *pos & 0x3)
-		return -EINVAL;
-
-	while (size) {
-		uint32_t value;
-
-		value = RREG32_DIDT(*pos >> 2);
-		r = put_user(value, (uint32_t *)buf);
-		if (r)
-			return r;
-
-		result += 4;
-		buf += 4;
-		*pos += 4;
-		size -= 4;
-	}
-
-	return result;
-}
-
-static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user *buf,
-					 size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = file_inode(f)->i_private;
-	ssize_t result = 0;
-	int r;
-
-	if (size & 0x3 || *pos & 0x3)
-		return -EINVAL;
-
-	while (size) {
-		uint32_t value;
-
-		r = get_user(value, (uint32_t *)buf);
-		if (r)
-			return r;
-
-		WREG32_DIDT(*pos >> 2, value);
-
-		result += 4;
-		buf += 4;
-		*pos += 4;
-		size -= 4;
-	}
-
-	return result;
-}
-
-static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
-					size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = file_inode(f)->i_private;
-	ssize_t result = 0;
-	int r;
-
-	if (size & 0x3 || *pos & 0x3)
-		return -EINVAL;
-
-	while (size) {
-		uint32_t value;
-
-		value = RREG32_SMC(*pos);
-		r = put_user(value, (uint32_t *)buf);
-		if (r)
-			return r;
-
-		result += 4;
-		buf += 4;
-		*pos += 4;
-		size -= 4;
-	}
-
-	return result;
-}
-
-static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *buf,
-					 size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = file_inode(f)->i_private;
-	ssize_t result = 0;
-	int r;
-
-	if (size & 0x3 || *pos & 0x3)
-		return -EINVAL;
-
-	while (size) {
-		uint32_t value;
-
-		r = get_user(value, (uint32_t *)buf);
-		if (r)
-			return r;
-
-		WREG32_SMC(*pos, value);
-
-		result += 4;
-		buf += 4;
-		*pos += 4;
-		size -= 4;
-	}
-
-	return result;
-}
-
-static ssize_t amdgpu_debugfs_gca_config_read(struct file *f, char __user *buf,
-					size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = file_inode(f)->i_private;
-	ssize_t result = 0;
-	int r;
-	uint32_t *config, no_regs = 0;
-
-	if (size & 0x3 || *pos & 0x3)
-		return -EINVAL;
-
-	config = kmalloc_array(256, sizeof(*config), GFP_KERNEL);
-	if (!config)
-		return -ENOMEM;
-
-	/* version, increment each time something is added */
-	config[no_regs++] = 3;
-	config[no_regs++] = adev->gfx.config.max_shader_engines;
-	config[no_regs++] = adev->gfx.config.max_tile_pipes;
-	config[no_regs++] = adev->gfx.config.max_cu_per_sh;
-	config[no_regs++] = adev->gfx.config.max_sh_per_se;
-	config[no_regs++] = adev->gfx.config.max_backends_per_se;
-	config[no_regs++] = adev->gfx.config.max_texture_channel_caches;
-	config[no_regs++] = adev->gfx.config.max_gprs;
-	config[no_regs++] = adev->gfx.config.max_gs_threads;
-	config[no_regs++] = adev->gfx.config.max_hw_contexts;
-	config[no_regs++] = adev->gfx.config.sc_prim_fifo_size_frontend;
-	config[no_regs++] = adev->gfx.config.sc_prim_fifo_size_backend;
-	config[no_regs++] = adev->gfx.config.sc_hiz_tile_fifo_size;
-	config[no_regs++] = adev->gfx.config.sc_earlyz_tile_fifo_size;
-	config[no_regs++] = adev->gfx.config.num_tile_pipes;
-	config[no_regs++] = adev->gfx.config.backend_enable_mask;
-	config[no_regs++] = adev->gfx.config.mem_max_burst_length_bytes;
-	config[no_regs++] = adev->gfx.config.mem_row_size_in_kb;
-	config[no_regs++] = adev->gfx.config.shader_engine_tile_size;
-	config[no_regs++] = adev->gfx.config.num_gpus;
-	config[no_regs++] = adev->gfx.config.multi_gpu_tile_size;
-	config[no_regs++] = adev->gfx.config.mc_arb_ramcfg;
-	config[no_regs++] = adev->gfx.config.gb_addr_config;
-	config[no_regs++] = adev->gfx.config.num_rbs;
-
-	/* rev==1 */
-	config[no_regs++] = adev->rev_id;
-	config[no_regs++] = adev->pg_flags;
-	config[no_regs++] = adev->cg_flags;
-
-	/* rev==2 */
-	config[no_regs++] = adev->family;
-	config[no_regs++] = adev->external_rev_id;
-
-	/* rev==3 */
-	config[no_regs++] = adev->pdev->device;
-	config[no_regs++] = adev->pdev->revision;
-	config[no_regs++] = adev->pdev->subsystem_device;
-	config[no_regs++] = adev->pdev->subsystem_vendor;
-
-	while (size && (*pos < no_regs * 4)) {
-		uint32_t value;
-
-		value = config[*pos >> 2];
-		r = put_user(value, (uint32_t *)buf);
-		if (r) {
-			kfree(config);
-			return r;
-		}
-
-		result += 4;
-		buf += 4;
-		*pos += 4;
-		size -= 4;
-	}
-
-	kfree(config);
-	return result;
-}
-
-static ssize_t amdgpu_debugfs_sensor_read(struct file *f, char __user *buf,
-					size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = file_inode(f)->i_private;
-	int idx, x, outsize, r, valuesize;
-	uint32_t values[16];
-
-	if (size & 3 || *pos & 0x3)
-		return -EINVAL;
-
-	if (amdgpu_dpm == 0)
-		return -EINVAL;
-
-	/* convert offset to sensor number */
-	idx = *pos >> 2;
-
-	valuesize = sizeof(values);
-	if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->read_sensor)
-		r = amdgpu_dpm_read_sensor(adev, idx, &values[0], &valuesize);
-	else
-		return -EINVAL;
-
-	if (size > valuesize)
-		return -EINVAL;
-
-	outsize = 0;
-	x = 0;
-	if (!r) {
-		while (size) {
-			r = put_user(values[x++], (int32_t *)buf);
-			buf += 4;
-			size -= 4;
-			outsize += 4;
-		}
-	}
-
-	return !r ? outsize : r;
-}
-
-static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
-					size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = f->f_inode->i_private;
-	int r, x;
-	ssize_t result=0;
-	uint32_t offset, se, sh, cu, wave, simd, data[32];
-
-	if (size & 3 || *pos & 3)
-		return -EINVAL;
-
-	/* decode offset */
-	offset = (*pos & GENMASK_ULL(6, 0));
-	se = (*pos & GENMASK_ULL(14, 7)) >> 7;
-	sh = (*pos & GENMASK_ULL(22, 15)) >> 15;
-	cu = (*pos & GENMASK_ULL(30, 23)) >> 23;
-	wave = (*pos & GENMASK_ULL(36, 31)) >> 31;
-	simd = (*pos & GENMASK_ULL(44, 37)) >> 37;
-
-	/* switch to the specific se/sh/cu */
-	mutex_lock(&adev->grbm_idx_mutex);
-	amdgpu_gfx_select_se_sh(adev, se, sh, cu);
-
-	x = 0;
-	if (adev->gfx.funcs->read_wave_data)
-		adev->gfx.funcs->read_wave_data(adev, simd, wave, data, &x);
-
-	amdgpu_gfx_select_se_sh(adev, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF);
-	mutex_unlock(&adev->grbm_idx_mutex);
-
-	if (!x)
-		return -EINVAL;
-
-	while (size && (offset < x * 4)) {
-		uint32_t value;
-
-		value = data[offset >> 2];
-		r = put_user(value, (uint32_t *)buf);
-		if (r)
-			return r;
-
-		result += 4;
-		buf += 4;
-		offset += 4;
-		size -= 4;
-	}
-
-	return result;
-}
-
-static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
-					size_t size, loff_t *pos)
-{
-	struct amdgpu_device *adev = f->f_inode->i_private;
-	int r;
-	ssize_t result = 0;
-	uint32_t offset, se, sh, cu, wave, simd, thread, bank, *data;
-
-	if (size & 3 || *pos & 3)
-		return -EINVAL;
-
-	/* decode offset */
-	offset = *pos & GENMASK_ULL(11, 0);
-	se = (*pos & GENMASK_ULL(19, 12)) >> 12;
-	sh = (*pos & GENMASK_ULL(27, 20)) >> 20;
-	cu = (*pos & GENMASK_ULL(35, 28)) >> 28;
-	wave = (*pos & GENMASK_ULL(43, 36)) >> 36;
-	simd = (*pos & GENMASK_ULL(51, 44)) >> 44;
-	thread = (*pos & GENMASK_ULL(59, 52)) >> 52;
-	bank = (*pos & GENMASK_ULL(61, 60)) >> 60;
-
-	data = kmalloc_array(1024, sizeof(*data), GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-
-	/* switch to the specific se/sh/cu */
-	mutex_lock(&adev->grbm_idx_mutex);
-	amdgpu_gfx_select_se_sh(adev, se, sh, cu);
-
-	if (bank == 0) {
-		if (adev->gfx.funcs->read_wave_vgprs)
-			adev->gfx.funcs->read_wave_vgprs(adev, simd, wave, thread, offset, size>>2, data);
-	} else {
-		if (adev->gfx.funcs->read_wave_sgprs)
-			adev->gfx.funcs->read_wave_sgprs(adev, simd, wave, offset, size>>2, data);
-	}
-
-	amdgpu_gfx_select_se_sh(adev, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF);
-	mutex_unlock(&adev->grbm_idx_mutex);
-
-	while (size) {
-		uint32_t value;
-
-		value = data[offset++];
-		r = put_user(value, (uint32_t *)buf);
-		if (r) {
-			result = r;
-			goto err;
-		}
-
-		result += 4;
-		buf += 4;
-		size -= 4;
-	}
-
-err:
-	kfree(data);
-	return result;
-}
-
-static const struct file_operations amdgpu_debugfs_regs_fops = {
-	.owner = THIS_MODULE,
-	.read = amdgpu_debugfs_regs_read,
-	.write = amdgpu_debugfs_regs_write,
-	.llseek = default_llseek
-};
-static const struct file_operations amdgpu_debugfs_regs_didt_fops = {
-	.owner = THIS_MODULE,
-	.read = amdgpu_debugfs_regs_didt_read,
-	.write = amdgpu_debugfs_regs_didt_write,
-	.llseek = default_llseek
-};
-static const struct file_operations amdgpu_debugfs_regs_pcie_fops = {
-	.owner = THIS_MODULE,
-	.read = amdgpu_debugfs_regs_pcie_read,
-	.write = amdgpu_debugfs_regs_pcie_write,
-	.llseek = default_llseek
-};
-static const struct file_operations amdgpu_debugfs_regs_smc_fops = {
-	.owner = THIS_MODULE,
-	.read = amdgpu_debugfs_regs_smc_read,
-	.write = amdgpu_debugfs_regs_smc_write,
-	.llseek = default_llseek
-};
-
-static const struct file_operations amdgpu_debugfs_gca_config_fops = {
-	.owner = THIS_MODULE,
-	.read = amdgpu_debugfs_gca_config_read,
-	.llseek = default_llseek
-};
-
-static const struct file_operations amdgpu_debugfs_sensors_fops = {
-	.owner = THIS_MODULE,
-	.read = amdgpu_debugfs_sensor_read,
-	.llseek = default_llseek
-};
-
-static const struct file_operations amdgpu_debugfs_wave_fops = {
-	.owner = THIS_MODULE,
-	.read = amdgpu_debugfs_wave_read,
-	.llseek = default_llseek
-};
-static const struct file_operations amdgpu_debugfs_gpr_fops = {
-	.owner = THIS_MODULE,
-	.read = amdgpu_debugfs_gpr_read,
-	.llseek = default_llseek
-};
-
-static const struct file_operations *debugfs_regs[] = {
-	&amdgpu_debugfs_regs_fops,
-	&amdgpu_debugfs_regs_didt_fops,
-	&amdgpu_debugfs_regs_pcie_fops,
-	&amdgpu_debugfs_regs_smc_fops,
-	&amdgpu_debugfs_gca_config_fops,
-	&amdgpu_debugfs_sensors_fops,
-	&amdgpu_debugfs_wave_fops,
-	&amdgpu_debugfs_gpr_fops,
-};
-
-static const char *debugfs_regs_names[] = {
-	"amdgpu_regs",
-	"amdgpu_regs_didt",
-	"amdgpu_regs_pcie",
-	"amdgpu_regs_smc",
-	"amdgpu_gca_config",
-	"amdgpu_sensors",
-	"amdgpu_wave",
-	"amdgpu_gpr",
-};
-
-static int amdgpu_debugfs_regs_init(struct amdgpu_device *adev)
-{
-	struct drm_minor *minor = adev->ddev->primary;
-	struct dentry *ent, *root = minor->debugfs_root;
-	unsigned i, j;
-
-	for (i = 0; i < ARRAY_SIZE(debugfs_regs); i++) {
-		ent = debugfs_create_file(debugfs_regs_names[i],
-					  S_IFREG | S_IRUGO, root,
-					  adev, debugfs_regs[i]);
-		if (IS_ERR(ent)) {
-			for (j = 0; j < i; j++) {
-				debugfs_remove(adev->debugfs_regs[i]);
-				adev->debugfs_regs[i] = NULL;
-			}
-			return PTR_ERR(ent);
-		}
-
-		if (!i)
-			i_size_write(ent->d_inode, adev->rmmio_size);
-		adev->debugfs_regs[i] = ent;
-	}
-
-	return 0;
-}
-
-static void amdgpu_debugfs_regs_cleanup(struct amdgpu_device *adev)
-{
-	unsigned i;
-
-	for (i = 0; i < ARRAY_SIZE(debugfs_regs); i++) {
-		if (adev->debugfs_regs[i]) {
-			debugfs_remove(adev->debugfs_regs[i]);
-			adev->debugfs_regs[i] = NULL;
-		}
-	}
-}
-
-static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
-	int r = 0, i;
-
-	/* hold on the scheduler */
-	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
-		struct amdgpu_ring *ring = adev->rings[i];
-
-		if (!ring || !ring->sched.thread)
-			continue;
-		kthread_park(ring->sched.thread);
-	}
-
-	seq_printf(m, "run ib test:\n");
-	r = amdgpu_ib_ring_tests(adev);
-	if (r)
-		seq_printf(m, "ib ring tests failed (%d).\n", r);
-	else
-		seq_printf(m, "ib ring tests passed.\n");
-
-	/* go on the scheduler */
-	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
-		struct amdgpu_ring *ring = adev->rings[i];
-
-		if (!ring || !ring->sched.thread)
-			continue;
-		kthread_unpark(ring->sched.thread);
-	}
-
-	return 0;
-}
-
-static const struct drm_info_list amdgpu_debugfs_test_ib_ring_list[] = {
-	{"amdgpu_test_ib", &amdgpu_debugfs_test_ib}
-};
-
-static int amdgpu_debugfs_test_ib_ring_init(struct amdgpu_device *adev)
-{
-	return amdgpu_debugfs_add_files(adev,
-					amdgpu_debugfs_test_ib_ring_list, 1);
-}
-
-int amdgpu_debugfs_init(struct drm_minor *minor)
-{
-	return 0;
-}
-
-static int amdgpu_debugfs_get_vbios_dump(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
-
-	seq_write(m, adev->bios, adev->bios_size);
-	return 0;
-}
-
-static const struct drm_info_list amdgpu_vbios_dump_list[] = {
-		{"amdgpu_vbios",
-		 amdgpu_debugfs_get_vbios_dump,
-		 0, NULL},
-};
-
-static int amdgpu_debugfs_vbios_dump_init(struct amdgpu_device *adev)
-{
-	return amdgpu_debugfs_add_files(adev,
-					amdgpu_vbios_dump_list, 1);
-}
-#else
-static int amdgpu_debugfs_test_ib_ring_init(struct amdgpu_device *adev)
-{
-	return 0;
-}
-static int amdgpu_debugfs_regs_init(struct amdgpu_device *adev)
-{
-	return 0;
-}
-static int amdgpu_debugfs_vbios_dump_init(struct amdgpu_device *adev)
-{
-	return 0;
-}
-static void amdgpu_debugfs_regs_cleanup(struct amdgpu_device *adev) { }
-#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 138beb550a58..38d47559f098 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -34,6 +34,7 @@
 #include <linux/pm_runtime.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_edid.h>
+#include <drm/drm_fb_helper.h>
 
 static void amdgpu_flip_callback(struct dma_fence *f, struct dma_fence_cb *cb)
 {
@@ -556,15 +557,9 @@ amdgpu_user_framebuffer_create(struct drm_device *dev,
 	return &amdgpu_fb->base;
 }
 
-void amdgpu_output_poll_changed(struct drm_device *dev)
-{
-	struct amdgpu_device *adev = dev->dev_private;
-	amdgpu_fb_output_poll_changed(adev);
-}
-
 const struct drm_mode_config_funcs amdgpu_mode_funcs = {
 	.fb_create = amdgpu_user_framebuffer_create,
-	.output_poll_changed = amdgpu_output_poll_changed
+	.output_poll_changed = drm_fb_helper_output_poll_changed,
 };
 
 static const struct drm_prop_enum_list amdgpu_underscan_enum_list[] =
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h
index 3cc0ef0c055e..0bcb6c6e0ca9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h
@@ -25,9 +25,7 @@
 
 struct drm_framebuffer *
 amdgpu_user_framebuffer_create(struct drm_device *dev,
-						       struct drm_file *file_priv,
-							   const struct drm_mode_fb_cmd2 *mode_cmd);
-
-void amdgpu_output_poll_changed(struct drm_device *dev);
+			       struct drm_file *file_priv,
+			       const struct drm_mode_fb_cmd2 *mode_cmd);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index 56caaeee6fea..a8437a3296a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -360,6 +360,12 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->set_clockgating_by_smu(\
 			(adev)->powerplay.pp_handle, msg_id))
 
+#define amdgpu_dpm_notify_smu_memory_info(adev, virtual_addr_low, \
+			virtual_addr_hi, mc_addr_low, mc_addr_hi, size) \
+		((adev)->powerplay.pp_funcs->notify_smu_memory_info)( \
+			(adev)->powerplay.pp_handle, virtual_addr_low, \
+			virtual_addr_hi, mc_addr_low, mc_addr_hi, size)
+
 struct amdgpu_dpm {
 	struct amdgpu_ps        *ps;
 	/* number of valid power states */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index ec96bb1f9eaf..50afcf65181a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -90,7 +90,7 @@ int amdgpu_disp_priority = 0;
 int amdgpu_hw_i2c = 0;
 int amdgpu_pcie_gen2 = -1;
 int amdgpu_msi = -1;
-int amdgpu_lockup_timeout = 0;
+int amdgpu_lockup_timeout = 10000;
 int amdgpu_dpm = -1;
 int amdgpu_fw_load_type = -1;
 int amdgpu_aspm = -1;
@@ -128,6 +128,7 @@ int amdgpu_param_buf_per_se = 0;
 int amdgpu_job_hang_limit = 0;
 int amdgpu_lbpw = -1;
 int amdgpu_compute_multipipe = -1;
+int amdgpu_gpu_recovery = -1; /* auto */
 
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -165,7 +166,7 @@ module_param_named(pcie_gen2, amdgpu_pcie_gen2, int, 0444);
 MODULE_PARM_DESC(msi, "MSI support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(msi, amdgpu_msi, int, 0444);
 
-MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default 0 = disable)");
+MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms > 0 (default 10000)");
 module_param_named(lockup_timeout, amdgpu_lockup_timeout, int, 0444);
 
 MODULE_PARM_DESC(dpm, "DPM support (1 = enable, 0 = disable, -1 = auto)");
@@ -216,7 +217,7 @@ module_param_named(exp_hw_support, amdgpu_exp_hw_support, int, 0444);
 MODULE_PARM_DESC(dc, "Display Core driver (1 = enable, 0 = disable, -1 = auto (default))");
 module_param_named(dc, amdgpu_dc, int, 0444);
 
-MODULE_PARM_DESC(dc, "Display Core Log Level (0 = minimal (default), 1 = chatty");
+MODULE_PARM_DESC(dc_log, "Display Core Log Level (0 = minimal (default), 1 = chatty");
 module_param_named(dc_log, amdgpu_dc_log, int, 0444);
 
 MODULE_PARM_DESC(sched_jobs, "the max number of jobs supported in the sw queue (default 32)");
@@ -280,6 +281,9 @@ module_param_named(lbpw, amdgpu_lbpw, int, 0444);
 MODULE_PARM_DESC(compute_multipipe, "Force compute queues to be spread across pipes (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444);
 
+MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (1 = enable, 0 = disable, -1 = auto");
+module_param_named(gpu_recovery, amdgpu_gpu_recovery, int, 0444);
+
 #ifdef CONFIG_DRM_AMDGPU_SI
 
 #if defined(CONFIG_DRM_RADEON) || defined(CONFIG_DRM_RADEON_MODULE)
@@ -306,7 +310,6 @@ MODULE_PARM_DESC(cik_support, "CIK support (1 = enabled (default), 0 = disabled)
 module_param_named(cik_support, amdgpu_cik_support, int, 0444);
 #endif
 
-
 static const struct pci_device_id pciidlist[] = {
 #ifdef  CONFIG_DRM_AMDGPU_SI
 	{0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
@@ -536,7 +539,7 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x686c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10},
 	{0x1002, 0x687f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10},
 	/* Raven */
-	{0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU},
 
 	{0, 0, 0}
 };
@@ -566,12 +569,13 @@ static int amdgpu_kick_out_firmware_fb(struct pci_dev *pdev)
 	return 0;
 }
 
+
 static int amdgpu_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *ent)
 {
 	struct drm_device *dev;
 	unsigned long flags = ent->driver_data;
-	int ret;
+	int ret, retry = 0;
 
 	if ((flags & AMD_EXP_HW_SUPPORT) && !amdgpu_exp_hw_support) {
 		DRM_INFO("This hardware requires experimental hardware support.\n"
@@ -604,8 +608,14 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 
 	pci_set_drvdata(pdev, dev);
 
+retry_init:
 	ret = drm_dev_register(dev, ent->driver_data);
-	if (ret)
+	if (ret == -EAGAIN && ++retry <= 3) {
+		DRM_INFO("retry init %d\n", retry);
+		/* Don't request EX mode too frequently which is attacking */
+		msleep(5000);
+		goto retry_init;
+	} else if (ret)
 		goto err_pci;
 
 	return 0;
@@ -639,7 +649,7 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)
 	 * unfortunately we can't detect certain
 	 * hypervisors so just do this all the time.
 	 */
-	amdgpu_suspend(adev);
+	amdgpu_device_ip_suspend(adev);
 }
 
 static int amdgpu_pmops_suspend(struct device *dev)
@@ -844,9 +854,6 @@ static struct drm_driver kms_driver = {
 	.disable_vblank = amdgpu_disable_vblank_kms,
 	.get_vblank_timestamp = drm_calc_vbltimestamp_from_scanoutpos,
 	.get_scanout_position = amdgpu_get_crtc_scanout_position,
-#if defined(CONFIG_DEBUG_FS)
-	.debugfs_init = amdgpu_debugfs_init,
-#endif
 	.irq_preinstall = amdgpu_irq_preinstall,
 	.irq_postinstall = amdgpu_irq_postinstall,
 	.irq_uninstall = amdgpu_irq_uninstall,
@@ -906,10 +913,6 @@ static int __init amdgpu_init(void)
 	if (r)
 		goto error_fence;
 
-	r = amd_sched_fence_slab_init();
-	if (r)
-		goto error_sched;
-
 	if (vgacon_text_force()) {
 		DRM_ERROR("VGACON disables amdgpu kernel modesetting.\n");
 		return -EINVAL;
@@ -922,9 +925,6 @@ static int __init amdgpu_init(void)
 	/* let modprobe override vga console setting */
 	return pci_register_driver(pdriver);
 
-error_sched:
-	amdgpu_fence_slab_fini();
-
 error_fence:
 	amdgpu_sync_fini();
 
@@ -938,7 +938,6 @@ static void __exit amdgpu_exit(void)
 	pci_unregister_driver(pdriver);
 	amdgpu_unregister_atpx_handler();
 	amdgpu_sync_fini();
-	amd_sched_fence_slab_fini();
 	amdgpu_fence_slab_fini();
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 90fa8e8bc6fb..ff3e9beb7d19 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -283,12 +283,6 @@ out:
 	return ret;
 }
 
-void amdgpu_fb_output_poll_changed(struct amdgpu_device *adev)
-{
-	if (adev->mode_info.rfbdev)
-		drm_fb_helper_hotplug_event(&adev->mode_info.rfbdev->helper);
-}
-
 static int amdgpu_fbdev_destroy(struct drm_device *dev, struct amdgpu_fbdev *rfbdev)
 {
 	struct amdgpu_framebuffer *rfb = &rfbdev->rfb;
@@ -393,24 +387,3 @@ bool amdgpu_fbdev_robj_is_fb(struct amdgpu_device *adev, struct amdgpu_bo *robj)
 		return true;
 	return false;
 }
-
-void amdgpu_fbdev_restore_mode(struct amdgpu_device *adev)
-{
-	struct amdgpu_fbdev *afbdev;
-	struct drm_fb_helper *fb_helper;
-	int ret;
-
-	if (!adev)
-		return;
-
-	afbdev = adev->mode_info.rfbdev;
-
-	if (!afbdev)
-		return;
-
-	fb_helper = &afbdev->helper;
-
-	ret = drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
-	if (ret)
-		DRM_DEBUG("failed to restore crtc mode\n");
-}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 2fa95aef74d5..008e1984b7e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -187,7 +187,7 @@ int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s)
 
 	seq = ++ring->fence_drv.sync_seq;
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
-			       seq, AMDGPU_FENCE_FLAG_INT);
+			       seq, 0);
 
 	*s = seq;
 
@@ -391,9 +391,9 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 	ring->fence_drv.irq_type = irq_type;
 	ring->fence_drv.initialized = true;
 
-	dev_info(adev->dev, "fence driver on ring %d use gpu addr 0x%016llx, "
-		 "cpu addr 0x%p\n", ring->idx,
-		 ring->fence_drv.gpu_addr, ring->fence_drv.cpu_addr);
+	dev_dbg(adev->dev, "fence driver on ring %d use gpu addr 0x%016llx, "
+		"cpu addr 0x%p\n", ring->idx,
+		ring->fence_drv.gpu_addr, ring->fence_drv.cpu_addr);
 	return 0;
 }
 
@@ -410,7 +410,6 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 				  unsigned num_hw_submission)
 {
-	long timeout;
 	int r;
 
 	/* Check that num_hw_submission is a power of two */
@@ -434,20 +433,9 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 
 	/* No need to setup the GPU scheduler for KIQ ring */
 	if (ring->funcs->type != AMDGPU_RING_TYPE_KIQ) {
-		timeout = msecs_to_jiffies(amdgpu_lockup_timeout);
-		if (timeout == 0) {
-			/*
-			 * FIXME:
-			 * Delayed workqueue cannot use it directly,
-			 * so the scheduler will not use delayed workqueue if
-			 * MAX_SCHEDULE_TIMEOUT is set.
-			 * Currently keep it simple and silly.
-			 */
-			timeout = MAX_SCHEDULE_TIMEOUT;
-		}
-		r = amd_sched_init(&ring->sched, &amdgpu_sched_ops,
-				   num_hw_submission,
-				   timeout, ring->name);
+		r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
+				   num_hw_submission, amdgpu_job_hang_limit,
+				   msecs_to_jiffies(amdgpu_lockup_timeout), ring->name);
 		if (r) {
 			DRM_ERROR("Failed to create scheduler on ring %s.\n",
 				  ring->name);
@@ -499,11 +487,11 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
 		r = amdgpu_fence_wait_empty(ring);
 		if (r) {
 			/* no need to trigger GPU reset as we are unloading */
-			amdgpu_fence_driver_force_completion(adev);
+			amdgpu_fence_driver_force_completion(ring);
 		}
 		amdgpu_irq_put(adev, ring->fence_drv.irq_src,
 			       ring->fence_drv.irq_type);
-		amd_sched_fini(&ring->sched);
+		drm_sched_fini(&ring->sched);
 		del_timer_sync(&ring->fence_drv.fallback_timer);
 		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
 			dma_fence_put(ring->fence_drv.fences[j]);
@@ -534,7 +522,7 @@ void amdgpu_fence_driver_suspend(struct amdgpu_device *adev)
 		r = amdgpu_fence_wait_empty(ring);
 		if (r) {
 			/* delay GPU reset to resume */
-			amdgpu_fence_driver_force_completion(adev);
+			amdgpu_fence_driver_force_completion(ring);
 		}
 
 		/* disable the interrupt */
@@ -571,30 +559,15 @@ void amdgpu_fence_driver_resume(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_fence_driver_force_completion - force all fence waiter to complete
+ * amdgpu_fence_driver_force_completion - force signal latest fence of ring
  *
- * @adev: amdgpu device pointer
+ * @ring: fence of the ring to signal
  *
- * In case of GPU reset failure make sure no process keep waiting on fence
- * that will never complete.
  */
-void amdgpu_fence_driver_force_completion(struct amdgpu_device *adev)
+void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring)
 {
-	int i;
-
-	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
-		struct amdgpu_ring *ring = adev->rings[i];
-		if (!ring || !ring->fence_drv.initialized)
-			continue;
-
-		amdgpu_fence_write(ring, ring->fence_drv.sync_seq);
-	}
-}
-
-void amdgpu_fence_driver_force_completion_ring(struct amdgpu_ring *ring)
-{
-	if (ring)
-		amdgpu_fence_write(ring, ring->fence_drv.sync_seq);
+	amdgpu_fence_write(ring, ring->fence_drv.sync_seq);
+	amdgpu_fence_process(ring);
 }
 
 /*
@@ -709,25 +682,25 @@ static int amdgpu_debugfs_fence_info(struct seq_file *m, void *data)
 }
 
 /**
- * amdgpu_debugfs_gpu_reset - manually trigger a gpu reset
+ * amdgpu_debugfs_gpu_recover - manually trigger a gpu reset & recover
  *
  * Manually trigger a gpu reset at the next fence wait.
  */
-static int amdgpu_debugfs_gpu_reset(struct seq_file *m, void *data)
+static int amdgpu_debugfs_gpu_recover(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 
-	seq_printf(m, "gpu reset\n");
-	amdgpu_gpu_reset(adev);
+	seq_printf(m, "gpu recover\n");
+	amdgpu_device_gpu_recover(adev, NULL, true);
 
 	return 0;
 }
 
 static const struct drm_info_list amdgpu_debugfs_fence_list[] = {
 	{"amdgpu_fence_info", &amdgpu_debugfs_fence_info, 0, NULL},
-	{"amdgpu_gpu_reset", &amdgpu_debugfs_gpu_reset, 0, NULL}
+	{"amdgpu_gpu_recover", &amdgpu_debugfs_gpu_recover, 0, NULL}
 };
 
 static const struct drm_info_list amdgpu_debugfs_fence_list_sriov[] = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index fe818501c520..0a4f34afaaaa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -57,60 +57,48 @@
  */
 
 /**
- * amdgpu_gart_table_ram_alloc - allocate system ram for gart page table
+ * amdgpu_dummy_page_init - init dummy page used by the driver
  *
  * @adev: amdgpu_device pointer
  *
- * Allocate system memory for GART page table
- * (r1xx-r3xx, non-pcie r4xx, rs400).  These asics require the
- * gart table to be in system memory.
- * Returns 0 for success, -ENOMEM for failure.
+ * Allocate the dummy page used by the driver (all asics).
+ * This dummy page is used by the driver as a filler for gart entries
+ * when pages are taken out of the GART
+ * Returns 0 on sucess, -ENOMEM on failure.
  */
-int amdgpu_gart_table_ram_alloc(struct amdgpu_device *adev)
+static int amdgpu_gart_dummy_page_init(struct amdgpu_device *adev)
 {
-	void *ptr;
-
-	ptr = pci_alloc_consistent(adev->pdev, adev->gart.table_size,
-				   &adev->gart.table_addr);
-	if (ptr == NULL) {
+	if (adev->dummy_page.page)
+		return 0;
+	adev->dummy_page.page = alloc_page(GFP_DMA32 | GFP_KERNEL | __GFP_ZERO);
+	if (adev->dummy_page.page == NULL)
+		return -ENOMEM;
+	adev->dummy_page.addr = pci_map_page(adev->pdev, adev->dummy_page.page,
+					0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+	if (pci_dma_mapping_error(adev->pdev, adev->dummy_page.addr)) {
+		dev_err(&adev->pdev->dev, "Failed to DMA MAP the dummy page\n");
+		__free_page(adev->dummy_page.page);
+		adev->dummy_page.page = NULL;
 		return -ENOMEM;
 	}
-#ifdef CONFIG_X86
-	if (0) {
-		set_memory_uc((unsigned long)ptr,
-			      adev->gart.table_size >> PAGE_SHIFT);
-	}
-#endif
-	adev->gart.ptr = ptr;
-	memset((void *)adev->gart.ptr, 0, adev->gart.table_size);
 	return 0;
 }
 
 /**
- * amdgpu_gart_table_ram_free - free system ram for gart page table
+ * amdgpu_dummy_page_fini - free dummy page used by the driver
  *
  * @adev: amdgpu_device pointer
  *
- * Free system memory for GART page table
- * (r1xx-r3xx, non-pcie r4xx, rs400).  These asics require the
- * gart table to be in system memory.
+ * Frees the dummy page used by the driver (all asics).
  */
-void amdgpu_gart_table_ram_free(struct amdgpu_device *adev)
+static void amdgpu_gart_dummy_page_fini(struct amdgpu_device *adev)
 {
-	if (adev->gart.ptr == NULL) {
+	if (adev->dummy_page.page == NULL)
 		return;
-	}
-#ifdef CONFIG_X86
-	if (0) {
-		set_memory_wb((unsigned long)adev->gart.ptr,
-			      adev->gart.table_size >> PAGE_SHIFT);
-	}
-#endif
-	pci_free_consistent(adev->pdev, adev->gart.table_size,
-			    (void *)adev->gart.ptr,
-			    adev->gart.table_addr);
-	adev->gart.ptr = NULL;
-	adev->gart.table_addr = 0;
+	pci_unmap_page(adev->pdev, adev->dummy_page.addr,
+			PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+	__free_page(adev->dummy_page.page);
+	adev->dummy_page.page = NULL;
 }
 
 /**
@@ -365,7 +353,7 @@ int amdgpu_gart_init(struct amdgpu_device *adev)
 		DRM_ERROR("Page size is smaller than GPU page size!\n");
 		return -EINVAL;
 	}
-	r = amdgpu_dummy_page_init(adev);
+	r = amdgpu_gart_dummy_page_init(adev);
 	if (r)
 		return r;
 	/* Compute table size */
@@ -377,10 +365,8 @@ int amdgpu_gart_init(struct amdgpu_device *adev)
 #ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
 	/* Allocate pages table */
 	adev->gart.pages = vzalloc(sizeof(void *) * adev->gart.num_cpu_pages);
-	if (adev->gart.pages == NULL) {
-		amdgpu_gart_fini(adev);
+	if (adev->gart.pages == NULL)
 		return -ENOMEM;
-	}
 #endif
 
 	return 0;
@@ -395,14 +381,9 @@ int amdgpu_gart_init(struct amdgpu_device *adev)
  */
 void amdgpu_gart_fini(struct amdgpu_device *adev)
 {
-	if (adev->gart.ready) {
-		/* unbind pages */
-		amdgpu_gart_unbind(adev, 0, adev->gart.num_cpu_pages);
-	}
-	adev->gart.ready = false;
 #ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
 	vfree(adev->gart.pages);
 	adev->gart.pages = NULL;
 #endif
-	amdgpu_dummy_page_fini(adev);
+	amdgpu_gart_dummy_page_fini(adev);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
index afbe803b1a13..d4a43302c2be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
@@ -39,7 +39,7 @@ struct amdgpu_gart_funcs;
 #define AMDGPU_GPU_PAGE_ALIGN(a) (((a) + AMDGPU_GPU_PAGE_MASK) & ~AMDGPU_GPU_PAGE_MASK)
 
 struct amdgpu_gart {
-	dma_addr_t			table_addr;
+	u64				table_addr;
 	struct amdgpu_bo		*robj;
 	void				*ptr;
 	unsigned			num_gpu_pages;
@@ -56,8 +56,6 @@ struct amdgpu_gart {
 	const struct amdgpu_gart_funcs *gart_funcs;
 };
 
-int amdgpu_gart_table_ram_alloc(struct amdgpu_device *adev);
-void amdgpu_gart_table_ram_free(struct amdgpu_device *adev);
 int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev);
 void amdgpu_gart_table_vram_free(struct amdgpu_device *adev);
 int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index e87eedcc0da9..e48b4ec88c8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -72,7 +72,7 @@ retry:
 				initial_domain |= AMDGPU_GEM_DOMAIN_GTT;
 				goto retry;
 			}
-			DRM_ERROR("Failed to allocate GEM object (%ld, %d, %u, %d)\n",
+			DRM_DEBUG("Failed to allocate GEM object (%ld, %d, %u, %d)\n",
 				  size, initial_domain, alignment, r);
 		}
 		return r;
@@ -282,6 +282,7 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *filp)
 {
+	struct ttm_operation_ctx ctx = { true, false };
 	struct amdgpu_device *adev = dev->dev_private;
 	struct drm_amdgpu_gem_userptr *args = data;
 	struct drm_gem_object *gobj;
@@ -335,7 +336,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 			goto free_pages;
 
 		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
-		r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		amdgpu_bo_unreserve(bo);
 		if (r)
 			goto free_pages;
@@ -517,10 +518,6 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 	if (!amdgpu_vm_ready(vm))
 		return;
 
-	r = amdgpu_vm_update_directories(adev, vm);
-	if (r)
-		goto error;
-
 	r = amdgpu_vm_clear_freed(adev, vm, NULL);
 	if (r)
 		goto error;
@@ -529,6 +526,10 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 	    operation == AMDGPU_VA_OP_REPLACE)
 		r = amdgpu_vm_bo_update(adev, bo_va, false);
 
+	r = amdgpu_vm_update_directories(adev, vm);
+	if (r)
+		goto error;
+
 error:
 	if (r && r != -ERESTARTSYS)
 		DRM_ERROR("Couldn't update BO_VA (%d)\n", r);
@@ -557,14 +558,25 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 	int r = 0;
 
 	if (args->va_address < AMDGPU_VA_RESERVED_SIZE) {
-		dev_err(&dev->pdev->dev,
+		dev_dbg(&dev->pdev->dev,
 			"va_address 0x%LX is in reserved area 0x%LX\n",
 			args->va_address, AMDGPU_VA_RESERVED_SIZE);
 		return -EINVAL;
 	}
 
+	if (args->va_address >= AMDGPU_VA_HOLE_START &&
+	    args->va_address < AMDGPU_VA_HOLE_END) {
+		dev_dbg(&dev->pdev->dev,
+			"va_address 0x%LX is in VA hole 0x%LX-0x%LX\n",
+			args->va_address, AMDGPU_VA_HOLE_START,
+			AMDGPU_VA_HOLE_END);
+		return -EINVAL;
+	}
+
+	args->va_address &= AMDGPU_VA_HOLE_MASK;
+
 	if ((args->flags & ~valid_flags) && (args->flags & ~prt_flags)) {
-		dev_err(&dev->pdev->dev, "invalid flags combination 0x%08X\n",
+		dev_dbg(&dev->pdev->dev, "invalid flags combination 0x%08X\n",
 			args->flags);
 		return -EINVAL;
 	}
@@ -576,7 +588,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 	case AMDGPU_VA_OP_REPLACE:
 		break;
 	default:
-		dev_err(&dev->pdev->dev, "unsupported operation %d\n",
+		dev_dbg(&dev->pdev->dev, "unsupported operation %d\n",
 			args->operation);
 		return -EINVAL;
 	}
@@ -839,7 +851,7 @@ static const struct drm_info_list amdgpu_debugfs_gem_list[] = {
 };
 #endif
 
-int amdgpu_gem_debugfs_init(struct amdgpu_device *adev)
+int amdgpu_debugfs_gem_init(struct amdgpu_device *adev)
 {
 #if defined(CONFIG_DEBUG_FS)
 	return amdgpu_debugfs_add_files(adev, amdgpu_debugfs_gem_list, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index ef043361009f..bb40d2529a30 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -203,7 +203,7 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
 
 	spin_lock_init(&kiq->ring_lock);
 
-	r = amdgpu_wb_get(adev, &adev->virt.reg_val_offs);
+	r = amdgpu_device_wb_get(adev, &adev->virt.reg_val_offs);
 	if (r)
 		return r;
 
@@ -229,7 +229,7 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
 void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring,
 			      struct amdgpu_irq_src *irq)
 {
-	amdgpu_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
+	amdgpu_device_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
 	amdgpu_ring_fini(ring);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index 00e0ce10862f..e14ab34d8262 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -31,6 +31,11 @@ struct amdgpu_gtt_mgr {
 	atomic64_t available;
 };
 
+struct amdgpu_gtt_node {
+	struct drm_mm_node node;
+	struct ttm_buffer_object *tbo;
+};
+
 /**
  * amdgpu_gtt_mgr_init - init GTT manager and DRM MM
  *
@@ -79,17 +84,17 @@ static int amdgpu_gtt_mgr_fini(struct ttm_mem_type_manager *man)
 }
 
 /**
- * amdgpu_gtt_mgr_is_allocated - Check if mem has address space
+ * amdgpu_gtt_mgr_has_gart_addr - Check if mem has address space
  *
  * @mem: the mem object to check
  *
  * Check if a mem object has already address space allocated.
  */
-bool amdgpu_gtt_mgr_is_allocated(struct ttm_mem_reg *mem)
+bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem)
 {
-	struct drm_mm_node *node = mem->mm_node;
+	struct amdgpu_gtt_node *node = mem->mm_node;
 
-	return (node->start != AMDGPU_BO_INVALID_OFFSET);
+	return (node->node.start != AMDGPU_BO_INVALID_OFFSET);
 }
 
 /**
@@ -109,12 +114,12 @@ static int amdgpu_gtt_mgr_alloc(struct ttm_mem_type_manager *man,
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
 	struct amdgpu_gtt_mgr *mgr = man->priv;
-	struct drm_mm_node *node = mem->mm_node;
+	struct amdgpu_gtt_node *node = mem->mm_node;
 	enum drm_mm_insert_mode mode;
 	unsigned long fpfn, lpfn;
 	int r;
 
-	if (amdgpu_gtt_mgr_is_allocated(mem))
+	if (amdgpu_gtt_mgr_has_gart_addr(mem))
 		return 0;
 
 	if (place)
@@ -132,13 +137,13 @@ static int amdgpu_gtt_mgr_alloc(struct ttm_mem_type_manager *man,
 		mode = DRM_MM_INSERT_HIGH;
 
 	spin_lock(&mgr->lock);
-	r = drm_mm_insert_node_in_range(&mgr->mm, node,
-					mem->num_pages, mem->page_alignment, 0,
-					fpfn, lpfn, mode);
+	r = drm_mm_insert_node_in_range(&mgr->mm, &node->node, mem->num_pages,
+					mem->page_alignment, 0, fpfn, lpfn,
+					mode);
 	spin_unlock(&mgr->lock);
 
 	if (!r)
-		mem->start = node->start;
+		mem->start = node->node.start;
 
 	return r;
 }
@@ -159,7 +164,7 @@ static int amdgpu_gtt_mgr_new(struct ttm_mem_type_manager *man,
 			      struct ttm_mem_reg *mem)
 {
 	struct amdgpu_gtt_mgr *mgr = man->priv;
-	struct drm_mm_node *node;
+	struct amdgpu_gtt_node *node;
 	int r;
 
 	spin_lock(&mgr->lock);
@@ -177,8 +182,9 @@ static int amdgpu_gtt_mgr_new(struct ttm_mem_type_manager *man,
 		goto err_out;
 	}
 
-	node->start = AMDGPU_BO_INVALID_OFFSET;
-	node->size = mem->num_pages;
+	node->node.start = AMDGPU_BO_INVALID_OFFSET;
+	node->node.size = mem->num_pages;
+	node->tbo = tbo;
 	mem->mm_node = node;
 
 	if (place->fpfn || place->lpfn || place->flags & TTM_PL_FLAG_TOPDOWN) {
@@ -190,7 +196,7 @@ static int amdgpu_gtt_mgr_new(struct ttm_mem_type_manager *man,
 			goto err_out;
 		}
 	} else {
-		mem->start = node->start;
+		mem->start = node->node.start;
 	}
 
 	return 0;
@@ -214,14 +220,14 @@ static void amdgpu_gtt_mgr_del(struct ttm_mem_type_manager *man,
 			       struct ttm_mem_reg *mem)
 {
 	struct amdgpu_gtt_mgr *mgr = man->priv;
-	struct drm_mm_node *node = mem->mm_node;
+	struct amdgpu_gtt_node *node = mem->mm_node;
 
 	if (!node)
 		return;
 
 	spin_lock(&mgr->lock);
-	if (node->start != AMDGPU_BO_INVALID_OFFSET)
-		drm_mm_remove_node(node);
+	if (node->node.start != AMDGPU_BO_INVALID_OFFSET)
+		drm_mm_remove_node(&node->node);
 	spin_unlock(&mgr->lock);
 	atomic64_add(mem->num_pages, &mgr->available);
 
@@ -244,6 +250,25 @@ uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man)
 	return (result > 0 ? result : 0) * PAGE_SIZE;
 }
 
+int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man)
+{
+	struct amdgpu_gtt_mgr *mgr = man->priv;
+	struct amdgpu_gtt_node *node;
+	struct drm_mm_node *mm_node;
+	int r = 0;
+
+	spin_lock(&mgr->lock);
+	drm_mm_for_each_node(mm_node, &mgr->mm) {
+		node = container_of(mm_node, struct amdgpu_gtt_node, node);
+		r = amdgpu_ttm_recover_gart(node->tbo);
+		if (r)
+			break;
+	}
+	spin_unlock(&mgr->lock);
+
+	return r;
+}
+
 /**
  * amdgpu_gtt_mgr_debug - dump VRAM table
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 659997bfff30..a162d87ca0c8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -149,7 +149,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		return -EINVAL;
 	}
 
-	if (vm && !job->vm_id) {
+	if (vm && !job->vmid) {
 		dev_err(adev->dev, "VM IB without ID\n");
 		return -EINVAL;
 	}
@@ -164,7 +164,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	}
 
 	if (ring->funcs->emit_pipeline_sync && job &&
-	    ((tmp = amdgpu_sync_get_fence(&job->sched_sync)) ||
+	    ((tmp = amdgpu_sync_get_fence(&job->sched_sync, NULL)) ||
 	     amdgpu_vm_need_pipeline_sync(ring, job))) {
 		need_pipe_sync = true;
 		dma_fence_put(tmp);
@@ -211,7 +211,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 			!amdgpu_sriov_vf(adev)) /* for SRIOV preemption, Preamble CE ib must be inserted anyway */
 			continue;
 
-		amdgpu_ring_emit_ib(ring, ib, job ? job->vm_id : 0,
+		amdgpu_ring_emit_ib(ring, ib, job ? job->vmid : 0,
 				    need_ctx_switch);
 		need_ctx_switch = false;
 	}
@@ -229,9 +229,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	r = amdgpu_fence_emit(ring, f);
 	if (r) {
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
-		if (job && job->vm_id)
-			amdgpu_vm_reset_id(adev, ring->funcs->vmhub,
-					   job->vm_id);
+		if (job && job->vmid)
+			amdgpu_vmid_reset(adev, ring->funcs->vmhub, job->vmid);
 		amdgpu_ring_undo(ring);
 		return r;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
new file mode 100644
index 000000000000..16884a0b677b
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -0,0 +1,459 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu_ids.h"
+
+#include <linux/idr.h>
+#include <linux/dma-fence-array.h>
+#include <drm/drmP.h>
+
+#include "amdgpu.h"
+#include "amdgpu_trace.h"
+
+/*
+ * PASID manager
+ *
+ * PASIDs are global address space identifiers that can be shared
+ * between the GPU, an IOMMU and the driver. VMs on different devices
+ * may use the same PASID if they share the same address
+ * space. Therefore PASIDs are allocated using a global IDA. VMs are
+ * looked up from the PASID per amdgpu_device.
+ */
+static DEFINE_IDA(amdgpu_pasid_ida);
+
+/**
+ * amdgpu_pasid_alloc - Allocate a PASID
+ * @bits: Maximum width of the PASID in bits, must be at least 1
+ *
+ * Allocates a PASID of the given width while keeping smaller PASIDs
+ * available if possible.
+ *
+ * Returns a positive integer on success. Returns %-EINVAL if bits==0.
+ * Returns %-ENOSPC if no PASID was available. Returns %-ENOMEM on
+ * memory allocation failure.
+ */
+int amdgpu_pasid_alloc(unsigned int bits)
+{
+	int pasid = -EINVAL;
+
+	for (bits = min(bits, 31U); bits > 0; bits--) {
+		pasid = ida_simple_get(&amdgpu_pasid_ida,
+				       1U << (bits - 1), 1U << bits,
+				       GFP_KERNEL);
+		if (pasid != -ENOSPC)
+			break;
+	}
+
+	return pasid;
+}
+
+/**
+ * amdgpu_pasid_free - Free a PASID
+ * @pasid: PASID to free
+ */
+void amdgpu_pasid_free(unsigned int pasid)
+{
+	ida_simple_remove(&amdgpu_pasid_ida, pasid);
+}
+
+/*
+ * VMID manager
+ *
+ * VMIDs are a per VMHUB identifier for page tables handling.
+ */
+
+/**
+ * amdgpu_vmid_had_gpu_reset - check if reset occured since last use
+ *
+ * @adev: amdgpu_device pointer
+ * @id: VMID structure
+ *
+ * Check if GPU reset occured since last use of the VMID.
+ */
+bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
+			       struct amdgpu_vmid *id)
+{
+	return id->current_gpu_reset_count !=
+		atomic_read(&adev->gpu_reset_counter);
+}
+
+/* idr_mgr->lock must be held */
+static int amdgpu_vmid_grab_reserved_locked(struct amdgpu_vm *vm,
+					    struct amdgpu_ring *ring,
+					    struct amdgpu_sync *sync,
+					    struct dma_fence *fence,
+					    struct amdgpu_job *job)
+{
+	struct amdgpu_device *adev = ring->adev;
+	unsigned vmhub = ring->funcs->vmhub;
+	uint64_t fence_context = adev->fence_context + ring->idx;
+	struct amdgpu_vmid *id = vm->reserved_vmid[vmhub];
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	struct dma_fence *updates = sync->last_vm_update;
+	int r = 0;
+	struct dma_fence *flushed, *tmp;
+	bool needs_flush = vm->use_cpu_for_update;
+
+	flushed  = id->flushed_updates;
+	if ((amdgpu_vmid_had_gpu_reset(adev, id)) ||
+	    (atomic64_read(&id->owner) != vm->entity.fence_context) ||
+	    (job->vm_pd_addr != id->pd_gpu_addr) ||
+	    (updates && (!flushed || updates->context != flushed->context ||
+			dma_fence_is_later(updates, flushed))) ||
+	    (!id->last_flush || (id->last_flush->context != fence_context &&
+				 !dma_fence_is_signaled(id->last_flush)))) {
+		needs_flush = true;
+		/* to prevent one context starved by another context */
+		id->pd_gpu_addr = 0;
+		tmp = amdgpu_sync_peek_fence(&id->active, ring);
+		if (tmp) {
+			r = amdgpu_sync_fence(adev, sync, tmp, false);
+			return r;
+		}
+	}
+
+	/* Good we can use this VMID. Remember this submission as
+	* user of the VMID.
+	*/
+	r = amdgpu_sync_fence(ring->adev, &id->active, fence, false);
+	if (r)
+		goto out;
+
+	if (updates && (!flushed || updates->context != flushed->context ||
+			dma_fence_is_later(updates, flushed))) {
+		dma_fence_put(id->flushed_updates);
+		id->flushed_updates = dma_fence_get(updates);
+	}
+	id->pd_gpu_addr = job->vm_pd_addr;
+	atomic64_set(&id->owner, vm->entity.fence_context);
+	job->vm_needs_flush = needs_flush;
+	if (needs_flush) {
+		dma_fence_put(id->last_flush);
+		id->last_flush = NULL;
+	}
+	job->vmid = id - id_mgr->ids;
+	trace_amdgpu_vm_grab_id(vm, ring, job);
+out:
+	return r;
+}
+
+/**
+ * amdgpu_vm_grab_id - allocate the next free VMID
+ *
+ * @vm: vm to allocate id for
+ * @ring: ring we want to submit job to
+ * @sync: sync object where we add dependencies
+ * @fence: fence protecting ID from reuse
+ *
+ * Allocate an id for the vm, adding fences to the sync obj as necessary.
+ */
+int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
+		     struct amdgpu_sync *sync, struct dma_fence *fence,
+		     struct amdgpu_job *job)
+{
+	struct amdgpu_device *adev = ring->adev;
+	unsigned vmhub = ring->funcs->vmhub;
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	uint64_t fence_context = adev->fence_context + ring->idx;
+	struct dma_fence *updates = sync->last_vm_update;
+	struct amdgpu_vmid *id, *idle;
+	struct dma_fence **fences;
+	unsigned i;
+	int r = 0;
+
+	mutex_lock(&id_mgr->lock);
+	if (vm->reserved_vmid[vmhub]) {
+		r = amdgpu_vmid_grab_reserved_locked(vm, ring, sync, fence, job);
+		mutex_unlock(&id_mgr->lock);
+		return r;
+	}
+	fences = kmalloc_array(sizeof(void *), id_mgr->num_ids, GFP_KERNEL);
+	if (!fences) {
+		mutex_unlock(&id_mgr->lock);
+		return -ENOMEM;
+	}
+	/* Check if we have an idle VMID */
+	i = 0;
+	list_for_each_entry(idle, &id_mgr->ids_lru, list) {
+		fences[i] = amdgpu_sync_peek_fence(&idle->active, ring);
+		if (!fences[i])
+			break;
+		++i;
+	}
+
+	/* If we can't find a idle VMID to use, wait till one becomes available */
+	if (&idle->list == &id_mgr->ids_lru) {
+		u64 fence_context = adev->vm_manager.fence_context + ring->idx;
+		unsigned seqno = ++adev->vm_manager.seqno[ring->idx];
+		struct dma_fence_array *array;
+		unsigned j;
+
+		for (j = 0; j < i; ++j)
+			dma_fence_get(fences[j]);
+
+		array = dma_fence_array_create(i, fences, fence_context,
+					   seqno, true);
+		if (!array) {
+			for (j = 0; j < i; ++j)
+				dma_fence_put(fences[j]);
+			kfree(fences);
+			r = -ENOMEM;
+			goto error;
+		}
+
+
+		r = amdgpu_sync_fence(ring->adev, sync, &array->base, false);
+		dma_fence_put(&array->base);
+		if (r)
+			goto error;
+
+		mutex_unlock(&id_mgr->lock);
+		return 0;
+
+	}
+	kfree(fences);
+
+	job->vm_needs_flush = vm->use_cpu_for_update;
+	/* Check if we can use a VMID already assigned to this VM */
+	list_for_each_entry_reverse(id, &id_mgr->ids_lru, list) {
+		struct dma_fence *flushed;
+		bool needs_flush = vm->use_cpu_for_update;
+
+		/* Check all the prerequisites to using this VMID */
+		if (amdgpu_vmid_had_gpu_reset(adev, id))
+			continue;
+
+		if (atomic64_read(&id->owner) != vm->entity.fence_context)
+			continue;
+
+		if (job->vm_pd_addr != id->pd_gpu_addr)
+			continue;
+
+		if (!id->last_flush ||
+		    (id->last_flush->context != fence_context &&
+		     !dma_fence_is_signaled(id->last_flush)))
+			needs_flush = true;
+
+		flushed  = id->flushed_updates;
+		if (updates && (!flushed || dma_fence_is_later(updates, flushed)))
+			needs_flush = true;
+
+		/* Concurrent flushes are only possible starting with Vega10 */
+		if (adev->asic_type < CHIP_VEGA10 && needs_flush)
+			continue;
+
+		/* Good we can use this VMID. Remember this submission as
+		 * user of the VMID.
+		 */
+		r = amdgpu_sync_fence(ring->adev, &id->active, fence, false);
+		if (r)
+			goto error;
+
+		if (updates && (!flushed || dma_fence_is_later(updates, flushed))) {
+			dma_fence_put(id->flushed_updates);
+			id->flushed_updates = dma_fence_get(updates);
+		}
+
+		if (needs_flush)
+			goto needs_flush;
+		else
+			goto no_flush_needed;
+
+	};
+
+	/* Still no ID to use? Then use the idle one found earlier */
+	id = idle;
+
+	/* Remember this submission as user of the VMID */
+	r = amdgpu_sync_fence(ring->adev, &id->active, fence, false);
+	if (r)
+		goto error;
+
+	id->pd_gpu_addr = job->vm_pd_addr;
+	dma_fence_put(id->flushed_updates);
+	id->flushed_updates = dma_fence_get(updates);
+	atomic64_set(&id->owner, vm->entity.fence_context);
+
+needs_flush:
+	job->vm_needs_flush = true;
+	dma_fence_put(id->last_flush);
+	id->last_flush = NULL;
+
+no_flush_needed:
+	list_move_tail(&id->list, &id_mgr->ids_lru);
+
+	job->vmid = id - id_mgr->ids;
+	trace_amdgpu_vm_grab_id(vm, ring, job);
+
+error:
+	mutex_unlock(&id_mgr->lock);
+	return r;
+}
+
+int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
+			       struct amdgpu_vm *vm,
+			       unsigned vmhub)
+{
+	struct amdgpu_vmid_mgr *id_mgr;
+	struct amdgpu_vmid *idle;
+	int r = 0;
+
+	id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	mutex_lock(&id_mgr->lock);
+	if (vm->reserved_vmid[vmhub])
+		goto unlock;
+	if (atomic_inc_return(&id_mgr->reserved_vmid_num) >
+	    AMDGPU_VM_MAX_RESERVED_VMID) {
+		DRM_ERROR("Over limitation of reserved vmid\n");
+		atomic_dec(&id_mgr->reserved_vmid_num);
+		r = -EINVAL;
+		goto unlock;
+	}
+	/* Select the first entry VMID */
+	idle = list_first_entry(&id_mgr->ids_lru, struct amdgpu_vmid, list);
+	list_del_init(&idle->list);
+	vm->reserved_vmid[vmhub] = idle;
+	mutex_unlock(&id_mgr->lock);
+
+	return 0;
+unlock:
+	mutex_unlock(&id_mgr->lock);
+	return r;
+}
+
+void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,
+			       struct amdgpu_vm *vm,
+			       unsigned vmhub)
+{
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+
+	mutex_lock(&id_mgr->lock);
+	if (vm->reserved_vmid[vmhub]) {
+		list_add(&vm->reserved_vmid[vmhub]->list,
+			&id_mgr->ids_lru);
+		vm->reserved_vmid[vmhub] = NULL;
+		atomic_dec(&id_mgr->reserved_vmid_num);
+	}
+	mutex_unlock(&id_mgr->lock);
+}
+
+/**
+ * amdgpu_vmid_reset - reset VMID to zero
+ *
+ * @adev: amdgpu device structure
+ * @vmid: vmid number to use
+ *
+ * Reset saved GDW, GWS and OA to force switch on next flush.
+ */
+void amdgpu_vmid_reset(struct amdgpu_device *adev, unsigned vmhub,
+		       unsigned vmid)
+{
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	struct amdgpu_vmid *id = &id_mgr->ids[vmid];
+
+	atomic64_set(&id->owner, 0);
+	id->gds_base = 0;
+	id->gds_size = 0;
+	id->gws_base = 0;
+	id->gws_size = 0;
+	id->oa_base = 0;
+	id->oa_size = 0;
+}
+
+/**
+ * amdgpu_vmid_reset_all - reset VMID to zero
+ *
+ * @adev: amdgpu device structure
+ *
+ * Reset VMID to force flush on next use
+ */
+void amdgpu_vmid_reset_all(struct amdgpu_device *adev)
+{
+	unsigned i, j;
+
+	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
+		struct amdgpu_vmid_mgr *id_mgr =
+			&adev->vm_manager.id_mgr[i];
+
+		for (j = 1; j < id_mgr->num_ids; ++j)
+			amdgpu_vmid_reset(adev, i, j);
+	}
+}
+
+/**
+ * amdgpu_vmid_mgr_init - init the VMID manager
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Initialize the VM manager structures
+ */
+void amdgpu_vmid_mgr_init(struct amdgpu_device *adev)
+{
+	unsigned i, j;
+
+	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
+		struct amdgpu_vmid_mgr *id_mgr =
+			&adev->vm_manager.id_mgr[i];
+
+		mutex_init(&id_mgr->lock);
+		INIT_LIST_HEAD(&id_mgr->ids_lru);
+		atomic_set(&id_mgr->reserved_vmid_num, 0);
+
+		/* skip over VMID 0, since it is the system VM */
+		for (j = 1; j < id_mgr->num_ids; ++j) {
+			amdgpu_vmid_reset(adev, i, j);
+			amdgpu_sync_create(&id_mgr->ids[i].active);
+			list_add_tail(&id_mgr->ids[j].list, &id_mgr->ids_lru);
+		}
+	}
+
+	adev->vm_manager.fence_context =
+		dma_fence_context_alloc(AMDGPU_MAX_RINGS);
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
+		adev->vm_manager.seqno[i] = 0;
+}
+
+/**
+ * amdgpu_vmid_mgr_fini - cleanup VM manager
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Cleanup the VM manager and free resources.
+ */
+void amdgpu_vmid_mgr_fini(struct amdgpu_device *adev)
+{
+	unsigned i, j;
+
+	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
+		struct amdgpu_vmid_mgr *id_mgr =
+			&adev->vm_manager.id_mgr[i];
+
+		mutex_destroy(&id_mgr->lock);
+		for (j = 0; j < AMDGPU_NUM_VMID; ++j) {
+			struct amdgpu_vmid *id = &id_mgr->ids[j];
+
+			amdgpu_sync_free(&id->active);
+			dma_fence_put(id->flushed_updates);
+			dma_fence_put(id->last_flush);
+		}
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
new file mode 100644
index 000000000000..ad931fa570b3
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
@@ -0,0 +1,91 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __AMDGPU_IDS_H__
+#define __AMDGPU_IDS_H__
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/dma-fence.h>
+
+#include "amdgpu_sync.h"
+
+/* maximum number of VMIDs */
+#define AMDGPU_NUM_VMID	16
+
+struct amdgpu_device;
+struct amdgpu_vm;
+struct amdgpu_ring;
+struct amdgpu_sync;
+struct amdgpu_job;
+
+struct amdgpu_vmid {
+	struct list_head	list;
+	struct amdgpu_sync	active;
+	struct dma_fence	*last_flush;
+	atomic64_t		owner;
+
+	uint64_t		pd_gpu_addr;
+	/* last flushed PD/PT update */
+	struct dma_fence	*flushed_updates;
+
+	uint32_t                current_gpu_reset_count;
+
+	uint32_t		gds_base;
+	uint32_t		gds_size;
+	uint32_t		gws_base;
+	uint32_t		gws_size;
+	uint32_t		oa_base;
+	uint32_t		oa_size;
+};
+
+struct amdgpu_vmid_mgr {
+	struct mutex		lock;
+	unsigned		num_ids;
+	struct list_head	ids_lru;
+	struct amdgpu_vmid	ids[AMDGPU_NUM_VMID];
+	atomic_t		reserved_vmid_num;
+};
+
+int amdgpu_pasid_alloc(unsigned int bits);
+void amdgpu_pasid_free(unsigned int pasid);
+
+bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
+			       struct amdgpu_vmid *id);
+int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
+			       struct amdgpu_vm *vm,
+			       unsigned vmhub);
+void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,
+			       struct amdgpu_vm *vm,
+			       unsigned vmhub);
+int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
+		     struct amdgpu_sync *sync, struct dma_fence *fence,
+		     struct amdgpu_job *job);
+void amdgpu_vmid_reset(struct amdgpu_device *adev, unsigned vmhub,
+		       unsigned vmid);
+void amdgpu_vmid_reset_all(struct amdgpu_device *adev);
+
+void amdgpu_vmid_mgr_init(struct amdgpu_device *adev);
+void amdgpu_vmid_mgr_fini(struct amdgpu_device *adev);
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
index f5f27e4f0f7f..06373d44b3da 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -92,15 +92,15 @@ int amdgpu_ih_ring_init(struct amdgpu_device *adev, unsigned ring_size,
 		}
 		return 0;
 	} else {
-		r = amdgpu_wb_get(adev, &adev->irq.ih.wptr_offs);
+		r = amdgpu_device_wb_get(adev, &adev->irq.ih.wptr_offs);
 		if (r) {
 			dev_err(adev->dev, "(%d) ih wptr_offs wb alloc failed\n", r);
 			return r;
 		}
 
-		r = amdgpu_wb_get(adev, &adev->irq.ih.rptr_offs);
+		r = amdgpu_device_wb_get(adev, &adev->irq.ih.rptr_offs);
 		if (r) {
-			amdgpu_wb_free(adev, adev->irq.ih.wptr_offs);
+			amdgpu_device_wb_free(adev, adev->irq.ih.wptr_offs);
 			dev_err(adev->dev, "(%d) ih rptr_offs wb alloc failed\n", r);
 			return r;
 		}
@@ -133,8 +133,8 @@ void amdgpu_ih_ring_fini(struct amdgpu_device *adev)
 		amdgpu_bo_free_kernel(&adev->irq.ih.ring_obj,
 				      &adev->irq.ih.gpu_addr,
 				      (void **)&adev->irq.ih.ring);
-		amdgpu_wb_free(adev, adev->irq.ih.wptr_offs);
-		amdgpu_wb_free(adev, adev->irq.ih.rptr_offs);
+		amdgpu_device_wb_free(adev, adev->irq.ih.wptr_offs);
+		amdgpu_device_wb_free(adev, adev->irq.ih.rptr_offs);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
index ada89358e220..29cf10927a92 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
@@ -105,8 +105,8 @@ struct amdgpu_iv_entry {
 	unsigned client_id;
 	unsigned src_id;
 	unsigned ring_id;
-	unsigned vm_id;
-	unsigned vm_id_src;
+	unsigned vmid;
+	unsigned vmid_src;
 	uint64_t timestamp;
 	unsigned timestamp_src;
 	unsigned pas_id;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 47c5ce9807db..56bcd59c3399 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -88,7 +88,7 @@ static void amdgpu_irq_reset_work_func(struct work_struct *work)
 						  reset_work);
 
 	if (!amdgpu_sriov_vf(adev))
-		amdgpu_gpu_reset(adev);
+		amdgpu_device_gpu_recover(adev, NULL, false);
 }
 
 /* Disable *all* interrupts */
@@ -232,7 +232,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 		int ret = pci_enable_msi(adev->pdev);
 		if (!ret) {
 			adev->irq.msi_enabled = true;
-			dev_info(adev->dev, "amdgpu: using MSI.\n");
+			dev_dbg(adev->dev, "amdgpu: using MSI.\n");
 		}
 	}
 
@@ -262,7 +262,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 		return r;
 	}
 
-	DRM_INFO("amdgpu: irq initialized.\n");
+	DRM_DEBUG("amdgpu: irq initialized.\n");
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 0cfc68db575b..2bd56760c744 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -28,7 +28,7 @@
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
 
-static void amdgpu_job_timedout(struct amd_sched_job *s_job)
+static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 {
 	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
 
@@ -37,10 +37,7 @@ static void amdgpu_job_timedout(struct amd_sched_job *s_job)
 		  atomic_read(&job->ring->fence_drv.last_seq),
 		  job->ring->fence_drv.sync_seq);
 
-	if (amdgpu_sriov_vf(job->adev))
-		amdgpu_sriov_gpu_reset(job->adev, job);
-	else
-		amdgpu_gpu_reset(job->adev);
+	amdgpu_device_gpu_recover(job->adev, job, false);
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
@@ -63,7 +60,6 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
 	(*job)->num_ibs = num_ibs;
 
 	amdgpu_sync_create(&(*job)->sync);
-	amdgpu_sync_create(&(*job)->dep_sync);
 	amdgpu_sync_create(&(*job)->sched_sync);
 	(*job)->vram_lost_counter = atomic_read(&adev->vram_lost_counter);
 
@@ -100,14 +96,13 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 		amdgpu_ib_free(job->adev, &job->ibs[i], f);
 }
 
-static void amdgpu_job_free_cb(struct amd_sched_job *s_job)
+static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
 {
 	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
 
-	amdgpu_ring_priority_put(job->ring, amd_sched_get_job_priority(s_job));
+	amdgpu_ring_priority_put(job->ring, s_job->s_priority);
 	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
-	amdgpu_sync_free(&job->dep_sync);
 	amdgpu_sync_free(&job->sched_sync);
 	kfree(job);
 }
@@ -118,13 +113,12 @@ void amdgpu_job_free(struct amdgpu_job *job)
 
 	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
-	amdgpu_sync_free(&job->dep_sync);
 	amdgpu_sync_free(&job->sched_sync);
 	kfree(job);
 }
 
 int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
-		      struct amd_sched_entity *entity, void *owner,
+		      struct drm_sched_entity *entity, void *owner,
 		      struct dma_fence **f)
 {
 	int r;
@@ -133,7 +127,7 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
 	if (!f)
 		return -EINVAL;
 
-	r = amd_sched_job_init(&job->base, &ring->sched, entity, owner);
+	r = drm_sched_job_init(&job->base, &ring->sched, entity, owner);
 	if (r)
 		return r;
 
@@ -141,46 +135,47 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
 	job->fence_ctx = entity->fence_context;
 	*f = dma_fence_get(&job->base.s_fence->finished);
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(job->ring,
-				 amd_sched_get_job_priority(&job->base));
-	amd_sched_entity_push_job(&job->base);
+	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
+	drm_sched_entity_push_job(&job->base, entity);
 
 	return 0;
 }
 
-static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)
+static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
+					       struct drm_sched_entity *s_entity)
 {
 	struct amdgpu_job *job = to_amdgpu_job(sched_job);
 	struct amdgpu_vm *vm = job->vm;
-
-	struct dma_fence *fence = amdgpu_sync_get_fence(&job->dep_sync);
+	bool explicit = false;
 	int r;
-
-	if (amd_sched_dependency_optimized(fence, sched_job->s_entity)) {
-		r = amdgpu_sync_fence(job->adev, &job->sched_sync, fence);
-		if (r)
-			DRM_ERROR("Error adding fence to sync (%d)\n", r);
+	struct dma_fence *fence = amdgpu_sync_get_fence(&job->sync, &explicit);
+
+	if (fence && explicit) {
+		if (drm_sched_dependency_optimized(fence, s_entity)) {
+			r = amdgpu_sync_fence(job->adev, &job->sched_sync, fence, false);
+			if (r)
+				DRM_ERROR("Error adding fence to sync (%d)\n", r);
+		}
 	}
-	if (!fence)
-		fence = amdgpu_sync_get_fence(&job->sync);
-	while (fence == NULL && vm && !job->vm_id) {
+
+	while (fence == NULL && vm && !job->vmid) {
 		struct amdgpu_ring *ring = job->ring;
 
-		r = amdgpu_vm_grab_id(vm, ring, &job->sync,
-				      &job->base.s_fence->finished,
-				      job);
+		r = amdgpu_vmid_grab(vm, ring, &job->sync,
+				     &job->base.s_fence->finished,
+				     job);
 		if (r)
 			DRM_ERROR("Error getting VM ID (%d)\n", r);
 
-		fence = amdgpu_sync_get_fence(&job->sync);
+		fence = amdgpu_sync_get_fence(&job->sync, NULL);
 	}
 
 	return fence;
 }
 
-static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
+static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 {
-	struct dma_fence *fence = NULL;
+	struct dma_fence *fence = NULL, *finished;
 	struct amdgpu_device *adev;
 	struct amdgpu_job *job;
 	int r;
@@ -190,15 +185,18 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
 		return NULL;
 	}
 	job = to_amdgpu_job(sched_job);
+	finished = &job->base.s_fence->finished;
 	adev = job->adev;
 
 	BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL));
 
 	trace_amdgpu_sched_run_job(job);
-	/* skip ib schedule when vram is lost */
-	if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter)) {
-		dma_fence_set_error(&job->base.s_fence->finished, -ECANCELED);
-		DRM_ERROR("Skip scheduling IBs!\n");
+
+	if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter))
+		dma_fence_set_error(finished, -ECANCELED);/* skip IB as well if VRAM lost */
+
+	if (finished->error < 0) {
+		DRM_INFO("Skip scheduling IBs!\n");
 	} else {
 		r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job,
 				       &fence);
@@ -213,7 +211,7 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
 	return fence;
 }
 
-const struct amd_sched_backend_ops amdgpu_sched_ops = {
+const struct drm_sched_backend_ops amdgpu_sched_ops = {
 	.dependency = amdgpu_job_dependency,
 	.run_job = amdgpu_job_run,
 	.timedout_job = amdgpu_job_timedout,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 720139e182a3..bd6e9a40f421 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -63,8 +63,6 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
 		pm_runtime_forbid(dev->dev);
 	}
 
-	amdgpu_amdkfd_device_fini(adev);
-
 	amdgpu_acpi_fini(adev);
 
 	amdgpu_device_fini(adev);
@@ -159,9 +157,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 				"Error during ACPI methods call\n");
 	}
 
-	amdgpu_amdkfd_device_probe(adev);
-	amdgpu_amdkfd_device_init(adev);
-
 	if (amdgpu_device_is_px(dev)) {
 		pm_runtime_use_autosuspend(dev->dev);
 		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
@@ -171,9 +166,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 		pm_runtime_put_autosuspend(dev->dev);
 	}
 
-	if (amdgpu_sriov_vf(adev))
-		amdgpu_virt_release_full_gpu(adev, true);
-
 out:
 	if (r) {
 		/* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */
@@ -558,6 +550,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 	}
 	case AMDGPU_INFO_DEV_INFO: {
 		struct drm_amdgpu_info_device dev_info = {};
+		uint64_t vm_size;
 
 		dev_info.device_id = dev->pdev->device;
 		dev_info.chip_rev = adev->rev_id;
@@ -585,8 +578,17 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			dev_info.ids_flags |= AMDGPU_IDS_FLAGS_FUSION;
 		if (amdgpu_sriov_vf(adev))
 			dev_info.ids_flags |= AMDGPU_IDS_FLAGS_PREEMPTION;
+
+		vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
 		dev_info.virtual_address_offset = AMDGPU_VA_RESERVED_SIZE;
-		dev_info.virtual_address_max = (uint64_t)adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
+		dev_info.virtual_address_max =
+			min(vm_size, AMDGPU_VA_HOLE_START);
+
+		vm_size -= AMDGPU_VA_RESERVED_SIZE;
+		if (vm_size > AMDGPU_VA_HOLE_START) {
+			dev_info.high_va_offset = AMDGPU_VA_HOLE_END;
+			dev_info.high_va_max = AMDGPU_VA_HOLE_END | vm_size;
+		}
 		dev_info.virtual_address_alignment = max((int)PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE);
 		dev_info.pte_fragment_size = (1 << adev->vm_manager.fragment_size) * AMDGPU_GPU_PAGE_SIZE;
 		dev_info.gart_page_size = AMDGPU_GPU_PAGE_SIZE;
@@ -786,9 +788,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
  */
 void amdgpu_driver_lastclose_kms(struct drm_device *dev)
 {
-	struct amdgpu_device *adev = dev->dev_private;
-
-	amdgpu_fbdev_restore_mode(adev);
+	drm_fb_helper_lastclose(dev);
 	vga_switcheroo_process_delayed_switch();
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index ffde1e9666e8..54f06c959340 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -89,7 +89,6 @@ enum amdgpu_hpd_id {
 	AMDGPU_HPD_4,
 	AMDGPU_HPD_5,
 	AMDGPU_HPD_6,
-	AMDGPU_HPD_LAST,
 	AMDGPU_HPD_NONE = 0xff,
 };
 
@@ -106,7 +105,6 @@ enum amdgpu_crtc_irq {
 	AMDGPU_CRTC_IRQ_VLINE4,
 	AMDGPU_CRTC_IRQ_VLINE5,
 	AMDGPU_CRTC_IRQ_VLINE6,
-	AMDGPU_CRTC_IRQ_LAST,
 	AMDGPU_CRTC_IRQ_NONE = 0xff
 };
 
@@ -117,7 +115,6 @@ enum amdgpu_pageflip_irq {
 	AMDGPU_PAGEFLIP_IRQ_D4,
 	AMDGPU_PAGEFLIP_IRQ_D5,
 	AMDGPU_PAGEFLIP_IRQ_D6,
-	AMDGPU_PAGEFLIP_IRQ_LAST,
 	AMDGPU_PAGEFLIP_IRQ_NONE = 0xff
 };
 
@@ -661,10 +658,6 @@ void amdgpu_fbdev_fini(struct amdgpu_device *adev);
 void amdgpu_fbdev_set_suspend(struct amdgpu_device *adev, int state);
 int amdgpu_fbdev_total_size(struct amdgpu_device *adev);
 bool amdgpu_fbdev_robj_is_fb(struct amdgpu_device *adev, struct amdgpu_bo *robj);
-void amdgpu_fbdev_restore_mode(struct amdgpu_device *adev);
-
-void amdgpu_fb_output_poll_changed(struct amdgpu_device *adev);
-
 
 int amdgpu_align_pitch(struct amdgpu_device *adev, int width, int bpp, bool tiled);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index ea25164e7f4b..5c4c3e0d527b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -37,6 +37,18 @@
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
 
+static bool amdgpu_need_backup(struct amdgpu_device *adev)
+{
+	if (adev->flags & AMD_IS_APU)
+		return false;
+
+	if (amdgpu_gpu_recovery == 0 ||
+	    (amdgpu_gpu_recovery == -1  && !amdgpu_sriov_vf(adev)))
+		return false;
+
+	return true;
+}
+
 static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
@@ -281,6 +293,44 @@ void amdgpu_bo_free_kernel(struct amdgpu_bo **bo, u64 *gpu_addr,
 		*cpu_addr = NULL;
 }
 
+/* Validate bo size is bit bigger then the request domain */
+static bool amdgpu_bo_validate_size(struct amdgpu_device *adev,
+					  unsigned long size, u32 domain)
+{
+	struct ttm_mem_type_manager *man = NULL;
+
+	/*
+	 * If GTT is part of requested domains the check must succeed to
+	 * allow fall back to GTT
+	 */
+	if (domain & AMDGPU_GEM_DOMAIN_GTT) {
+		man = &adev->mman.bdev.man[TTM_PL_TT];
+
+		if (size < (man->size << PAGE_SHIFT))
+			return true;
+		else
+			goto fail;
+	}
+
+	if (domain & AMDGPU_GEM_DOMAIN_VRAM) {
+		man = &adev->mman.bdev.man[TTM_PL_VRAM];
+
+		if (size < (man->size << PAGE_SHIFT))
+			return true;
+		else
+			goto fail;
+	}
+
+
+	/* TODO add more domains checks, such as AMDGPU_GEM_DOMAIN_CPU */
+	return true;
+
+fail:
+	DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size,
+		  man->size << PAGE_SHIFT);
+	return false;
+}
+
 static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 			       unsigned long size, int byte_align,
 			       bool kernel, u32 domain, u64 flags,
@@ -289,16 +339,24 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 			       uint64_t init_value,
 			       struct amdgpu_bo **bo_ptr)
 {
+	struct ttm_operation_ctx ctx = {
+		.interruptible = !kernel,
+		.no_wait_gpu = false,
+		.allow_reserved_eviction = true,
+		.resv = resv
+	};
 	struct amdgpu_bo *bo;
 	enum ttm_bo_type type;
 	unsigned long page_align;
-	u64 initial_bytes_moved, bytes_moved;
 	size_t acc_size;
 	int r;
 
 	page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT;
 	size = ALIGN(size, PAGE_SIZE);
 
+	if (!amdgpu_bo_validate_size(adev, size, domain))
+		return -ENOMEM;
+
 	if (kernel) {
 		type = ttm_bo_type_kernel;
 	} else if (sg) {
@@ -364,22 +422,19 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 	bo->tbo.bdev = &adev->mman.bdev;
 	amdgpu_ttm_placement_from_domain(bo, domain);
 
-	initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
-	/* Kernel allocation are uninterruptible */
 	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type,
-				 &bo->placement, page_align, !kernel, NULL,
+				 &bo->placement, page_align, &ctx, NULL,
 				 acc_size, sg, resv, &amdgpu_ttm_bo_destroy);
 	if (unlikely(r != 0))
 		return r;
 
-	bytes_moved = atomic64_read(&adev->num_bytes_moved) -
-		      initial_bytes_moved;
 	if (adev->mc.visible_vram_size < adev->mc.real_vram_size &&
 	    bo->tbo.mem.mem_type == TTM_PL_VRAM &&
 	    bo->tbo.mem.start < adev->mc.visible_vram_size >> PAGE_SHIFT)
-		amdgpu_cs_report_moved_bytes(adev, bytes_moved, bytes_moved);
+		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved,
+					     ctx.bytes_moved);
 	else
-		amdgpu_cs_report_moved_bytes(adev, bytes_moved, 0);
+		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, 0);
 
 	if (kernel)
 		bo->tbo.priority = 1;
@@ -511,6 +566,7 @@ err:
 
 int amdgpu_bo_validate(struct amdgpu_bo *bo)
 {
+	struct ttm_operation_ctx ctx = { false, false };
 	uint32_t domain;
 	int r;
 
@@ -521,7 +577,7 @@ int amdgpu_bo_validate(struct amdgpu_bo *bo)
 
 retry:
 	amdgpu_ttm_placement_from_domain(bo, domain);
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
 		domain = bo->allowed_domains;
 		goto retry;
@@ -632,6 +688,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 			     u64 *gpu_addr)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	struct ttm_operation_ctx ctx = { false, false };
 	int r, i;
 
 	if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm))
@@ -647,7 +704,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 	if (bo->pin_count) {
 		uint32_t mem_type = bo->tbo.mem.mem_type;
 
-		if (domain != amdgpu_mem_type_to_domain(mem_type))
+		if (!(domain & amdgpu_mem_type_to_domain(mem_type)))
 			return -EINVAL;
 
 		bo->pin_count++;
@@ -682,21 +739,23 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	}
 
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (unlikely(r)) {
 		dev_err(adev->dev, "%p pin failed\n", bo);
 		goto error;
 	}
 
+	r = amdgpu_ttm_alloc_gart(&bo->tbo);
+	if (unlikely(r)) {
+		dev_err(adev->dev, "%p bind failed\n", bo);
+		goto error;
+	}
+
 	bo->pin_count = 1;
-	if (gpu_addr != NULL) {
-		r = amdgpu_ttm_bind(&bo->tbo, &bo->tbo.mem);
-		if (unlikely(r)) {
-			dev_err(adev->dev, "%p bind failed\n", bo);
-			goto error;
-		}
+	if (gpu_addr != NULL)
 		*gpu_addr = amdgpu_bo_gpu_offset(bo);
-	}
+
+	domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
 	if (domain == AMDGPU_GEM_DOMAIN_VRAM) {
 		adev->vram_pin_size += amdgpu_bo_size(bo);
 		if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
@@ -717,6 +776,7 @@ int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain, u64 *gpu_addr)
 int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	struct ttm_operation_ctx ctx = { false, false };
 	int r, i;
 
 	if (!bo->pin_count) {
@@ -730,7 +790,7 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 		bo->placements[i].lpfn = 0;
 		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
 	}
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (unlikely(r)) {
 		dev_err(adev->dev, "%p validate failed for unpin\n", bo);
 		goto error;
@@ -779,8 +839,8 @@ int amdgpu_bo_init(struct amdgpu_device *adev)
 	adev->mc.vram_mtrr = arch_phys_wc_add(adev->mc.aper_base,
 					      adev->mc.aper_size);
 	DRM_INFO("Detected VRAM RAM=%lluM, BAR=%lluM\n",
-		adev->mc.mc_vram_size >> 20,
-		(unsigned long long)adev->mc.aper_size >> 20);
+		 adev->mc.mc_vram_size >> 20,
+		 (unsigned long long)adev->mc.aper_size >> 20);
 	DRM_INFO("RAM width %dbits %s\n",
 		 adev->mc.vram_width, amdgpu_vram_names[adev->mc.vram_type]);
 	return amdgpu_ttm_init(adev);
@@ -902,6 +962,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
+	struct ttm_operation_ctx ctx = { false, false };
 	struct amdgpu_bo *abo;
 	unsigned long offset, size;
 	int r;
@@ -935,7 +996,7 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	abo->placement.num_busy_placement = 1;
 	abo->placement.busy_placement = &abo->placements[1];
 
-	r = ttm_bo_validate(bo, &abo->placement, false, false);
+	r = ttm_bo_validate(bo, &abo->placement, &ctx);
 	if (unlikely(r != 0))
 		return r;
 
@@ -980,7 +1041,7 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo)
 {
 	WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_SYSTEM);
 	WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_TT &&
-		     !amdgpu_ttm_is_bound(bo->tbo.ttm));
+		     !amdgpu_gtt_mgr_has_gart_addr(&bo->tbo.mem));
 	WARN_ON_ONCE(!ww_mutex_is_locked(&bo->tbo.resv->lock) &&
 		     !bo->pin_count);
 	WARN_ON_ONCE(bo->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 428aae048f4b..33615e2ea2e6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -187,7 +187,7 @@ static inline u64 amdgpu_bo_mmap_offset(struct amdgpu_bo *bo)
 static inline bool amdgpu_bo_gpu_accessible(struct amdgpu_bo *bo)
 {
 	switch (bo->tbo.mem.mem_type) {
-	case TTM_PL_TT: return amdgpu_ttm_is_bound(bo->tbo.ttm);
+	case TTM_PL_TT: return amdgpu_gtt_mgr_has_gart_addr(&bo->tbo.mem);
 	case TTM_PL_VRAM: return true;
 	default: return false;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 6c570d4e4516..01a996c6b802 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -1,4 +1,6 @@
 /*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
  * to deal in the Software without restriction, including without limitation
@@ -30,7 +32,6 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 
-#include "amd_powerplay.h"
 
 static int amdgpu_debugfs_pm_init(struct amdgpu_device *adev);
 
@@ -1277,16 +1278,16 @@ void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable)
 			/* XXX select vce level based on ring/task */
 			adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL;
 			mutex_unlock(&adev->pm.mutex);
-			amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
-							AMD_CG_STATE_UNGATE);
-			amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
-							AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+							       AMD_CG_STATE_UNGATE);
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+							       AMD_PG_STATE_UNGATE);
 			amdgpu_pm_compute_clocks(adev);
 		} else {
-			amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
-							AMD_PG_STATE_GATE);
-			amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
-							AMD_CG_STATE_GATE);
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+							       AMD_PG_STATE_GATE);
+			amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+							       AMD_CG_STATE_GATE);
 			mutex_lock(&adev->pm.mutex);
 			adev->pm.dpm.vce_active = false;
 			mutex_unlock(&adev->pm.mutex);
@@ -1583,7 +1584,7 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data)
 	struct drm_device *ddev = adev->ddev;
 	u32 flags = 0;
 
-	amdgpu_get_clockgating_state(adev, &flags);
+	amdgpu_device_ip_get_clockgating_state(adev, &flags);
 	seq_printf(m, "Clock Gating Flags Mask: 0x%x\n", flags);
 	amdgpu_parse_cg_state(m, flags);
 	seq_printf(m, "\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
index 033fba2def6f..5f5aa5fddc16 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
@@ -164,6 +164,9 @@ static int amdgpu_pp_hw_fini(void *handle)
 		ret = adev->powerplay.ip_funcs->hw_fini(
 					adev->powerplay.pp_handle);
 
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
+		amdgpu_ucode_fini_bo(adev);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 7714f4a6c8b0..2157d4509e84 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -264,7 +264,7 @@ static int psp_hw_start(struct psp_context *psp)
 	struct amdgpu_device *adev = psp->adev;
 	int ret;
 
-	if (!amdgpu_sriov_vf(adev) || !adev->in_sriov_reset) {
+	if (!amdgpu_sriov_vf(adev) || !adev->in_gpu_reset) {
 		ret = psp_bootloader_load_sysdrv(psp);
 		if (ret)
 			return ret;
@@ -334,23 +334,26 @@ static int psp_load_fw(struct amdgpu_device *adev)
 	int ret;
 	struct psp_context *psp = &adev->psp;
 
+	if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset != 0)
+		goto skip_memalloc;
+
 	psp->cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
 	if (!psp->cmd)
 		return -ENOMEM;
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-				      AMDGPU_GEM_DOMAIN_GTT,
-				      &psp->fw_pri_bo,
-				      &psp->fw_pri_mc_addr,
-				      &psp->fw_pri_buf);
+					AMDGPU_GEM_DOMAIN_GTT,
+					&psp->fw_pri_bo,
+					&psp->fw_pri_mc_addr,
+					&psp->fw_pri_buf);
 	if (ret)
 		goto failed;
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_FENCE_BUFFER_SIZE, PAGE_SIZE,
-				      AMDGPU_GEM_DOMAIN_VRAM,
-				      &psp->fence_buf_bo,
-				      &psp->fence_buf_mc_addr,
-				      &psp->fence_buf);
+					AMDGPU_GEM_DOMAIN_VRAM,
+					&psp->fence_buf_bo,
+					&psp->fence_buf_mc_addr,
+					&psp->fence_buf);
 	if (ret)
 		goto failed_mem2;
 
@@ -375,6 +378,7 @@ static int psp_load_fw(struct amdgpu_device *adev)
 	if (ret)
 		goto failed_mem;
 
+skip_memalloc:
 	ret = psp_hw_start(psp);
 	if (ret)
 		goto failed_mem;
@@ -442,6 +446,8 @@ static int psp_hw_fini(void *handle)
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP)
 		return 0;
 
+	amdgpu_ucode_fini_bo(adev);
+
 	psp_ring_destroy(psp, PSP_RING_TYPE__KM);
 
 	amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, &psp->tmr_buf);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
index 190e28cb827e..262c1267249e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
@@ -63,7 +63,7 @@ static int amdgpu_update_cached_map(struct amdgpu_queue_mapper *mapper,
 
 static int amdgpu_identity_map(struct amdgpu_device *adev,
 			       struct amdgpu_queue_mapper *mapper,
-			       int ring,
+			       u32 ring,
 			       struct amdgpu_ring **out_ring)
 {
 	switch (mapper->hw_ip) {
@@ -121,7 +121,7 @@ static enum amdgpu_ring_type amdgpu_hw_ip_to_ring_type(int hw_ip)
 
 static int amdgpu_lru_map(struct amdgpu_device *adev,
 			  struct amdgpu_queue_mapper *mapper,
-			  int user_ring, bool lru_pipe_order,
+			  u32 user_ring, bool lru_pipe_order,
 			  struct amdgpu_ring **out_ring)
 {
 	int r, i, j;
@@ -208,7 +208,7 @@ int amdgpu_queue_mgr_fini(struct amdgpu_device *adev,
  */
 int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 			 struct amdgpu_queue_mgr *mgr,
-			 int hw_ip, int instance, int ring,
+			 u32 hw_ip, u32 instance, u32 ring,
 			 struct amdgpu_ring **out_ring)
 {
 	int r, ip_num_rings;
@@ -225,7 +225,7 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 
 	/* Right now all IPs have only one instance - multiple rings. */
 	if (instance != 0) {
-		DRM_ERROR("invalid ip instance: %d\n", instance);
+		DRM_DEBUG("invalid ip instance: %d\n", instance);
 		return -EINVAL;
 	}
 
@@ -255,13 +255,13 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 		ip_num_rings = adev->vcn.num_enc_rings;
 		break;
 	default:
-		DRM_ERROR("unknown ip type: %d\n", hw_ip);
+		DRM_DEBUG("unknown ip type: %d\n", hw_ip);
 		return -EINVAL;
 	}
 
 	if (ring >= ip_num_rings) {
-		DRM_ERROR("Ring index:%d exceeds maximum:%d for ip:%d\n",
-				ring, ip_num_rings, hw_ip);
+		DRM_DEBUG("Ring index:%d exceeds maximum:%d for ip:%d\n",
+			  ring, ip_num_rings, hw_ip);
 		return -EINVAL;
 	}
 
@@ -292,7 +292,7 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 	default:
 		*out_ring = NULL;
 		r = -EINVAL;
-		DRM_ERROR("unknown HW IP type: %d\n", mapper->hw_ip);
+		DRM_DEBUG("unknown HW IP type: %d\n", mapper->hw_ip);
 	}
 
 out_unlock:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index a98fbbb4739f..13044e66dcaf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -164,7 +164,7 @@ void amdgpu_ring_undo(struct amdgpu_ring *ring)
  * Release a request for executing at @priority
  */
 void amdgpu_ring_priority_put(struct amdgpu_ring *ring,
-			      enum amd_sched_priority priority)
+			      enum drm_sched_priority priority)
 {
 	int i;
 
@@ -175,7 +175,7 @@ void amdgpu_ring_priority_put(struct amdgpu_ring *ring,
 		return;
 
 	/* no need to restore if the job is already at the lowest priority */
-	if (priority == AMD_SCHED_PRIORITY_NORMAL)
+	if (priority == DRM_SCHED_PRIORITY_NORMAL)
 		return;
 
 	mutex_lock(&ring->priority_mutex);
@@ -184,8 +184,8 @@ void amdgpu_ring_priority_put(struct amdgpu_ring *ring,
 		goto out_unlock;
 
 	/* decay priority to the next level with a job available */
-	for (i = priority; i >= AMD_SCHED_PRIORITY_MIN; i--) {
-		if (i == AMD_SCHED_PRIORITY_NORMAL
+	for (i = priority; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+		if (i == DRM_SCHED_PRIORITY_NORMAL
 				|| atomic_read(&ring->num_jobs[i])) {
 			ring->priority = i;
 			ring->funcs->set_priority(ring, i);
@@ -206,7 +206,7 @@ out_unlock:
  * Request a ring's priority to be raised to @priority (refcounted).
  */
 void amdgpu_ring_priority_get(struct amdgpu_ring *ring,
-			      enum amd_sched_priority priority)
+			      enum drm_sched_priority priority)
 {
 	if (!ring->funcs->set_priority)
 		return;
@@ -263,25 +263,25 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 			return r;
 	}
 
-	r = amdgpu_wb_get(adev, &ring->rptr_offs);
+	r = amdgpu_device_wb_get(adev, &ring->rptr_offs);
 	if (r) {
 		dev_err(adev->dev, "(%d) ring rptr_offs wb alloc failed\n", r);
 		return r;
 	}
 
-	r = amdgpu_wb_get(adev, &ring->wptr_offs);
+	r = amdgpu_device_wb_get(adev, &ring->wptr_offs);
 	if (r) {
 		dev_err(adev->dev, "(%d) ring wptr_offs wb alloc failed\n", r);
 		return r;
 	}
 
-	r = amdgpu_wb_get(adev, &ring->fence_offs);
+	r = amdgpu_device_wb_get(adev, &ring->fence_offs);
 	if (r) {
 		dev_err(adev->dev, "(%d) ring fence_offs wb alloc failed\n", r);
 		return r;
 	}
 
-	r = amdgpu_wb_get(adev, &ring->cond_exe_offs);
+	r = amdgpu_device_wb_get(adev, &ring->cond_exe_offs);
 	if (r) {
 		dev_err(adev->dev, "(%d) ring cond_exec_polling wb alloc failed\n", r);
 		return r;
@@ -317,12 +317,12 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 	}
 
 	ring->max_dw = max_dw;
-	ring->priority = AMD_SCHED_PRIORITY_NORMAL;
+	ring->priority = DRM_SCHED_PRIORITY_NORMAL;
 	mutex_init(&ring->priority_mutex);
 	INIT_LIST_HEAD(&ring->lru_list);
 	amdgpu_ring_lru_touch(adev, ring);
 
-	for (i = 0; i < AMD_SCHED_PRIORITY_MAX; ++i)
+	for (i = 0; i < DRM_SCHED_PRIORITY_MAX; ++i)
 		atomic_set(&ring->num_jobs[i], 0);
 
 	if (amdgpu_debugfs_ring_init(adev, ring)) {
@@ -348,11 +348,11 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
 	if (!(ring->adev) || !(ring->adev->rings[ring->idx]))
 		return;
 
-	amdgpu_wb_free(ring->adev, ring->rptr_offs);
-	amdgpu_wb_free(ring->adev, ring->wptr_offs);
+	amdgpu_device_wb_free(ring->adev, ring->rptr_offs);
+	amdgpu_device_wb_free(ring->adev, ring->wptr_offs);
 
-	amdgpu_wb_free(ring->adev, ring->cond_exe_offs);
-	amdgpu_wb_free(ring->adev, ring->fence_offs);
+	amdgpu_device_wb_free(ring->adev, ring->cond_exe_offs);
+	amdgpu_device_wb_free(ring->adev, ring->fence_offs);
 
 	amdgpu_bo_free_kernel(&ring->ring_obj,
 			      &ring->gpu_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index b18c2b96691f..102dad3edf6a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -25,7 +25,7 @@
 #define __AMDGPU_RING_H__
 
 #include <drm/amdgpu_drm.h>
-#include "gpu_scheduler.h"
+#include <drm/gpu_scheduler.h>
 
 /* max number of rings */
 #define AMDGPU_MAX_RINGS		18
@@ -79,8 +79,7 @@ struct amdgpu_fence_driver {
 
 int amdgpu_fence_driver_init(struct amdgpu_device *adev);
 void amdgpu_fence_driver_fini(struct amdgpu_device *adev);
-void amdgpu_fence_driver_force_completion(struct amdgpu_device *adev);
-void amdgpu_fence_driver_force_completion_ring(struct amdgpu_ring *ring);
+void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
 
 int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 				  unsigned num_hw_submission);
@@ -122,11 +121,11 @@ struct amdgpu_ring_funcs {
 	/* command emit functions */
 	void (*emit_ib)(struct amdgpu_ring *ring,
 			struct amdgpu_ib *ib,
-			unsigned vm_id, bool ctx_switch);
+			unsigned vmid, bool ctx_switch);
 	void (*emit_fence)(struct amdgpu_ring *ring, uint64_t addr,
 			   uint64_t seq, unsigned flags);
 	void (*emit_pipeline_sync)(struct amdgpu_ring *ring);
-	void (*emit_vm_flush)(struct amdgpu_ring *ring, unsigned vm_id,
+	void (*emit_vm_flush)(struct amdgpu_ring *ring, unsigned vmid,
 			      uint64_t pd_addr);
 	void (*emit_hdp_flush)(struct amdgpu_ring *ring);
 	void (*emit_hdp_invalidate)(struct amdgpu_ring *ring);
@@ -155,14 +154,14 @@ struct amdgpu_ring_funcs {
 	void (*emit_tmz)(struct amdgpu_ring *ring, bool start);
 	/* priority functions */
 	void (*set_priority) (struct amdgpu_ring *ring,
-			      enum amd_sched_priority priority);
+			      enum drm_sched_priority priority);
 };
 
 struct amdgpu_ring {
 	struct amdgpu_device		*adev;
 	const struct amdgpu_ring_funcs	*funcs;
 	struct amdgpu_fence_driver	fence_drv;
-	struct amd_gpu_scheduler	sched;
+	struct drm_gpu_scheduler	sched;
 	struct list_head		lru_list;
 
 	struct amdgpu_bo	*ring_obj;
@@ -187,6 +186,7 @@ struct amdgpu_ring {
 	uint64_t                eop_gpu_addr;
 	u32			doorbell_index;
 	bool			use_doorbell;
+	bool			use_pollmem;
 	unsigned		wptr_offs;
 	unsigned		fence_offs;
 	uint64_t		current_ctx;
@@ -197,7 +197,7 @@ struct amdgpu_ring {
 	unsigned		vm_inv_eng;
 	bool			has_compute_vm_bug;
 
-	atomic_t		num_jobs[AMD_SCHED_PRIORITY_MAX];
+	atomic_t		num_jobs[DRM_SCHED_PRIORITY_MAX];
 	struct mutex		priority_mutex;
 	/* protected by priority_mutex */
 	int			priority;
@@ -213,9 +213,9 @@ void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib);
 void amdgpu_ring_commit(struct amdgpu_ring *ring);
 void amdgpu_ring_undo(struct amdgpu_ring *ring);
 void amdgpu_ring_priority_get(struct amdgpu_ring *ring,
-			      enum amd_sched_priority priority);
+			      enum drm_sched_priority priority);
 void amdgpu_ring_priority_put(struct amdgpu_ring *ring,
-			      enum amd_sched_priority priority);
+			      enum drm_sched_priority priority);
 int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		     unsigned ring_size, struct amdgpu_irq_src *irq_src,
 		     unsigned irq_type);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
index 290cc3f9c433..86a0715d9431 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -29,29 +29,29 @@
 
 #include "amdgpu_vm.h"
 
-enum amd_sched_priority amdgpu_to_sched_priority(int amdgpu_priority)
+enum drm_sched_priority amdgpu_to_sched_priority(int amdgpu_priority)
 {
 	switch (amdgpu_priority) {
 	case AMDGPU_CTX_PRIORITY_VERY_HIGH:
-		return AMD_SCHED_PRIORITY_HIGH_HW;
+		return DRM_SCHED_PRIORITY_HIGH_HW;
 	case AMDGPU_CTX_PRIORITY_HIGH:
-		return AMD_SCHED_PRIORITY_HIGH_SW;
+		return DRM_SCHED_PRIORITY_HIGH_SW;
 	case AMDGPU_CTX_PRIORITY_NORMAL:
-		return AMD_SCHED_PRIORITY_NORMAL;
+		return DRM_SCHED_PRIORITY_NORMAL;
 	case AMDGPU_CTX_PRIORITY_LOW:
 	case AMDGPU_CTX_PRIORITY_VERY_LOW:
-		return AMD_SCHED_PRIORITY_LOW;
+		return DRM_SCHED_PRIORITY_LOW;
 	case AMDGPU_CTX_PRIORITY_UNSET:
-		return AMD_SCHED_PRIORITY_UNSET;
+		return DRM_SCHED_PRIORITY_UNSET;
 	default:
 		WARN(1, "Invalid context priority %d\n", amdgpu_priority);
-		return AMD_SCHED_PRIORITY_INVALID;
+		return DRM_SCHED_PRIORITY_INVALID;
 	}
 }
 
 static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev,
 						  int fd,
-						  enum amd_sched_priority priority)
+						  enum drm_sched_priority priority)
 {
 	struct file *filp = fcheck(fd);
 	struct drm_file *file;
@@ -86,11 +86,11 @@ int amdgpu_sched_ioctl(struct drm_device *dev, void *data,
 {
 	union drm_amdgpu_sched *args = data;
 	struct amdgpu_device *adev = dev->dev_private;
-	enum amd_sched_priority priority;
+	enum drm_sched_priority priority;
 	int r;
 
 	priority = amdgpu_to_sched_priority(args->in.priority);
-	if (args->in.flags || priority == AMD_SCHED_PRIORITY_INVALID)
+	if (args->in.flags || priority == DRM_SCHED_PRIORITY_INVALID)
 		return -EINVAL;
 
 	switch (args->in.op) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h
index b28c067d3822..2a1a0c734bdd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h
@@ -27,7 +27,7 @@
 
 #include <drm/drmP.h>
 
-enum amd_sched_priority amdgpu_to_sched_priority(int amdgpu_priority);
+enum drm_sched_priority amdgpu_to_sched_priority(int amdgpu_priority);
 int amdgpu_sched_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *filp);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index a4bf21f8f1c1..df65c66dc956 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -35,6 +35,7 @@
 struct amdgpu_sync_entry {
 	struct hlist_node	node;
 	struct dma_fence	*fence;
+	bool	explicit;
 };
 
 static struct kmem_cache *amdgpu_sync_slab;
@@ -63,7 +64,7 @@ void amdgpu_sync_create(struct amdgpu_sync *sync)
 static bool amdgpu_sync_same_dev(struct amdgpu_device *adev,
 				 struct dma_fence *f)
 {
-	struct amd_sched_fence *s_fence = to_amd_sched_fence(f);
+	struct drm_sched_fence *s_fence = to_drm_sched_fence(f);
 
 	if (s_fence) {
 		struct amdgpu_ring *ring;
@@ -84,7 +85,7 @@ static bool amdgpu_sync_same_dev(struct amdgpu_device *adev,
  */
 static void *amdgpu_sync_get_owner(struct dma_fence *f)
 {
-	struct amd_sched_fence *s_fence = to_amd_sched_fence(f);
+	struct drm_sched_fence *s_fence = to_drm_sched_fence(f);
 
 	if (s_fence)
 		return s_fence->owner;
@@ -119,7 +120,7 @@ static void amdgpu_sync_keep_later(struct dma_fence **keep,
  * Tries to add the fence to an existing hash entry. Returns true when an entry
  * was found, false otherwise.
  */
-static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f)
+static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f, bool explicit)
 {
 	struct amdgpu_sync_entry *e;
 
@@ -128,6 +129,10 @@ static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f)
 			continue;
 
 		amdgpu_sync_keep_later(&e->fence, f);
+
+		/* Preserve eplicit flag to not loose pipe line sync */
+		e->explicit |= explicit;
+
 		return true;
 	}
 	return false;
@@ -141,24 +146,25 @@ static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f)
  *
  */
 int amdgpu_sync_fence(struct amdgpu_device *adev, struct amdgpu_sync *sync,
-		      struct dma_fence *f)
+		      struct dma_fence *f, bool explicit)
 {
 	struct amdgpu_sync_entry *e;
 
 	if (!f)
 		return 0;
-
 	if (amdgpu_sync_same_dev(adev, f) &&
 	    amdgpu_sync_get_owner(f) == AMDGPU_FENCE_OWNER_VM)
 		amdgpu_sync_keep_later(&sync->last_vm_update, f);
 
-	if (amdgpu_sync_add_later(sync, f))
+	if (amdgpu_sync_add_later(sync, f, explicit))
 		return 0;
 
 	e = kmem_cache_alloc(amdgpu_sync_slab, GFP_KERNEL);
 	if (!e)
 		return -ENOMEM;
 
+	e->explicit = explicit;
+
 	hash_add(sync->fences, &e->node, f->context);
 	e->fence = dma_fence_get(f);
 	return 0;
@@ -189,10 +195,7 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 
 	/* always sync to the exclusive fence */
 	f = reservation_object_get_excl(resv);
-	r = amdgpu_sync_fence(adev, sync, f);
-
-	if (explicit_sync)
-		return r;
+	r = amdgpu_sync_fence(adev, sync, f, false);
 
 	flist = reservation_object_get_list(resv);
 	if (!flist || r)
@@ -212,15 +215,15 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 			     (fence_owner == AMDGPU_FENCE_OWNER_VM)))
 				continue;
 
-			/* Ignore fence from the same owner as
+			/* Ignore fence from the same owner and explicit one as
 			 * long as it isn't undefined.
 			 */
 			if (owner != AMDGPU_FENCE_OWNER_UNDEFINED &&
-			    fence_owner == owner)
+			    (fence_owner == owner || explicit_sync))
 				continue;
 		}
 
-		r = amdgpu_sync_fence(adev, sync, f);
+		r = amdgpu_sync_fence(adev, sync, f, false);
 		if (r)
 			break;
 	}
@@ -245,7 +248,7 @@ struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync,
 
 	hash_for_each_safe(sync->fences, i, tmp, e, node) {
 		struct dma_fence *f = e->fence;
-		struct amd_sched_fence *s_fence = to_amd_sched_fence(f);
+		struct drm_sched_fence *s_fence = to_drm_sched_fence(f);
 
 		if (dma_fence_is_signaled(f)) {
 			hash_del(&e->node);
@@ -275,19 +278,21 @@ struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync,
  * amdgpu_sync_get_fence - get the next fence from the sync object
  *
  * @sync: sync object to use
+ * @explicit: true if the next fence is explicit
  *
  * Get and removes the next fence from the sync object not signaled yet.
  */
-struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync)
+struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync, bool *explicit)
 {
 	struct amdgpu_sync_entry *e;
 	struct hlist_node *tmp;
 	struct dma_fence *f;
 	int i;
-
 	hash_for_each_safe(sync->fences, i, tmp, e, node) {
 
 		f = e->fence;
+		if (explicit)
+			*explicit = e->explicit;
 
 		hash_del(&e->node);
 		kmem_cache_free(amdgpu_sync_slab, e);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
index 70d7e3a279a0..7aba38d5c9df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
@@ -41,7 +41,7 @@ struct amdgpu_sync {
 
 void amdgpu_sync_create(struct amdgpu_sync *sync);
 int amdgpu_sync_fence(struct amdgpu_device *adev, struct amdgpu_sync *sync,
-		      struct dma_fence *f);
+		      struct dma_fence *f, bool explicit);
 int amdgpu_sync_resv(struct amdgpu_device *adev,
 		     struct amdgpu_sync *sync,
 		     struct reservation_object *resv,
@@ -49,7 +49,7 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 		     bool explicit_sync);
 struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync,
 				     struct amdgpu_ring *ring);
-struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync);
+struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync, bool *explicit);
 int amdgpu_sync_wait(struct amdgpu_sync *sync, bool intr);
 void amdgpu_sync_free(struct amdgpu_sync *sync);
 int amdgpu_sync_init(void);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index f337c316ec2c..cace7a93fc94 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -1,4 +1,26 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
 #if !defined(_AMDGPU_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _AMDGPU_TRACE_H_
 
@@ -60,8 +82,8 @@ TRACE_EVENT(amdgpu_iv,
 			     __field(unsigned, client_id)
 			     __field(unsigned, src_id)
 			     __field(unsigned, ring_id)
-			     __field(unsigned, vm_id)
-			     __field(unsigned, vm_id_src)
+			     __field(unsigned, vmid)
+			     __field(unsigned, vmid_src)
 			     __field(uint64_t, timestamp)
 			     __field(unsigned, timestamp_src)
 			     __field(unsigned, pas_id)
@@ -71,8 +93,8 @@ TRACE_EVENT(amdgpu_iv,
 			   __entry->client_id = iv->client_id;
 			   __entry->src_id = iv->src_id;
 			   __entry->ring_id = iv->ring_id;
-			   __entry->vm_id = iv->vm_id;
-			   __entry->vm_id_src = iv->vm_id_src;
+			   __entry->vmid = iv->vmid;
+			   __entry->vmid_src = iv->vmid_src;
 			   __entry->timestamp = iv->timestamp;
 			   __entry->timestamp_src = iv->timestamp_src;
 			   __entry->pas_id = iv->pas_id;
@@ -81,9 +103,9 @@ TRACE_EVENT(amdgpu_iv,
 			   __entry->src_data[2] = iv->src_data[2];
 			   __entry->src_data[3] = iv->src_data[3];
 			   ),
-	    TP_printk("client_id:%u src_id:%u ring:%u vm_id:%u timestamp: %llu pas_id:%u src_data: %08x %08x %08x %08x\n",
+	    TP_printk("client_id:%u src_id:%u ring:%u vmid:%u timestamp: %llu pas_id:%u src_data: %08x %08x %08x %08x\n",
 		      __entry->client_id, __entry->src_id,
-		      __entry->ring_id, __entry->vm_id,
+		      __entry->ring_id, __entry->vmid,
 		      __entry->timestamp, __entry->pas_id,
 		      __entry->src_data[0], __entry->src_data[1],
 		      __entry->src_data[2], __entry->src_data[3])
@@ -197,7 +219,7 @@ TRACE_EVENT(amdgpu_vm_grab_id,
 	    TP_STRUCT__entry(
 			     __field(struct amdgpu_vm *, vm)
 			     __field(u32, ring)
-			     __field(u32, vm_id)
+			     __field(u32, vmid)
 			     __field(u32, vm_hub)
 			     __field(u64, pd_addr)
 			     __field(u32, needs_flush)
@@ -206,13 +228,13 @@ TRACE_EVENT(amdgpu_vm_grab_id,
 	    TP_fast_assign(
 			   __entry->vm = vm;
 			   __entry->ring = ring->idx;
-			   __entry->vm_id = job->vm_id;
+			   __entry->vmid = job->vmid;
 			   __entry->vm_hub = ring->funcs->vmhub,
 			   __entry->pd_addr = job->vm_pd_addr;
 			   __entry->needs_flush = job->vm_needs_flush;
 			   ),
 	    TP_printk("vm=%p, ring=%u, id=%u, hub=%u, pd_addr=%010Lx needs_flush=%u",
-		      __entry->vm, __entry->ring, __entry->vm_id,
+		      __entry->vm, __entry->ring, __entry->vmid,
 		      __entry->vm_hub, __entry->pd_addr, __entry->needs_flush)
 );
 
@@ -335,24 +357,24 @@ TRACE_EVENT(amdgpu_vm_copy_ptes,
 );
 
 TRACE_EVENT(amdgpu_vm_flush,
-	    TP_PROTO(struct amdgpu_ring *ring, unsigned vm_id,
+	    TP_PROTO(struct amdgpu_ring *ring, unsigned vmid,
 		     uint64_t pd_addr),
-	    TP_ARGS(ring, vm_id, pd_addr),
+	    TP_ARGS(ring, vmid, pd_addr),
 	    TP_STRUCT__entry(
 			     __field(u32, ring)
-			     __field(u32, vm_id)
+			     __field(u32, vmid)
 			     __field(u32, vm_hub)
 			     __field(u64, pd_addr)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->ring = ring->idx;
-			   __entry->vm_id = vm_id;
+			   __entry->vmid = vmid;
 			   __entry->vm_hub = ring->funcs->vmhub;
 			   __entry->pd_addr = pd_addr;
 			   ),
 	    TP_printk("ring=%u, id=%u, hub=%u, pd_addr=%010Lx",
-		      __entry->ring, __entry->vm_id,
+		      __entry->ring, __entry->vmid,
 		      __entry->vm_hub,__entry->pd_addr)
 );
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index ad5bf86ee8a3..e4bb435e614b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -76,7 +76,7 @@ static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
 {
 	struct drm_global_reference *global_ref;
 	struct amdgpu_ring *ring;
-	struct amd_sched_rq *rq;
+	struct drm_sched_rq *rq;
 	int r;
 
 	adev->mman.mem_global_referenced = false;
@@ -108,9 +108,9 @@ static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
 	mutex_init(&adev->mman.gtt_window_lock);
 
 	ring = adev->mman.buffer_funcs_ring;
-	rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_KERNEL];
-	r = amd_sched_entity_init(&ring->sched, &adev->mman.entity,
-				  rq, amdgpu_sched_jobs);
+	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+	r = drm_sched_entity_init(&ring->sched, &adev->mman.entity,
+				  rq, amdgpu_sched_jobs, NULL);
 	if (r) {
 		DRM_ERROR("Failed setting up TTM BO move run queue.\n");
 		goto error_entity;
@@ -131,7 +131,7 @@ error_mem:
 static void amdgpu_ttm_global_fini(struct amdgpu_device *adev)
 {
 	if (adev->mman.mem_global_referenced) {
-		amd_sched_entity_fini(adev->mman.entity.sched,
+		drm_sched_entity_fini(adev->mman.entity.sched,
 				      &adev->mman.entity);
 		mutex_destroy(&adev->mman.gtt_window_lock);
 		drm_global_item_unref(&adev->mman.bo_global_ref.ref);
@@ -282,8 +282,7 @@ static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
 {
 	uint64_t addr = 0;
 
-	if (mem->mem_type != TTM_PL_TT ||
-	    amdgpu_gtt_mgr_is_allocated(mem)) {
+	if (mem->mem_type != TTM_PL_TT || amdgpu_gtt_mgr_has_gart_addr(mem)) {
 		addr = mm_node->start << PAGE_SHIFT;
 		addr += bo->bdev->man[mem->mem_type].gpu_offset;
 	}
@@ -369,7 +368,7 @@ int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
 		 * dst to window 1
 		 */
 		if (src->mem->mem_type == TTM_PL_TT &&
-		    !amdgpu_gtt_mgr_is_allocated(src->mem)) {
+		    !amdgpu_gtt_mgr_has_gart_addr(src->mem)) {
 			r = amdgpu_map_buffer(src->bo, src->mem,
 					PFN_UP(cur_size + src_page_offset),
 					src_node_start, 0, ring,
@@ -383,7 +382,7 @@ int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
 		}
 
 		if (dst->mem->mem_type == TTM_PL_TT &&
-		    !amdgpu_gtt_mgr_is_allocated(dst->mem)) {
+		    !amdgpu_gtt_mgr_has_gart_addr(dst->mem)) {
 			r = amdgpu_map_buffer(dst->bo, dst->mem,
 					PFN_UP(cur_size + dst_page_offset),
 					dst_node_start, 1, ring,
@@ -467,9 +466,8 @@ error:
 	return r;
 }
 
-static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo,
-				bool evict, bool interruptible,
-				bool no_wait_gpu,
+static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
+				struct ttm_operation_ctx *ctx,
 				struct ttm_mem_reg *new_mem)
 {
 	struct amdgpu_device *adev;
@@ -489,8 +487,7 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo,
 	placements.fpfn = 0;
 	placements.lpfn = 0;
 	placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
-	r = ttm_bo_mem_space(bo, &placement, &tmp_mem,
-			     interruptible, no_wait_gpu);
+	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, ctx);
 	if (unlikely(r)) {
 		return r;
 	}
@@ -500,23 +497,22 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo,
 		goto out_cleanup;
 	}
 
-	r = ttm_tt_bind(bo->ttm, &tmp_mem);
+	r = ttm_tt_bind(bo->ttm, &tmp_mem, ctx);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
-	r = amdgpu_move_blit(bo, true, no_wait_gpu, &tmp_mem, old_mem);
+	r = amdgpu_move_blit(bo, true, ctx->no_wait_gpu, &tmp_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
-	r = ttm_bo_move_ttm(bo, interruptible, no_wait_gpu, new_mem);
+	r = ttm_bo_move_ttm(bo, ctx, new_mem);
 out_cleanup:
 	ttm_bo_mem_put(bo, &tmp_mem);
 	return r;
 }
 
-static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo,
-				bool evict, bool interruptible,
-				bool no_wait_gpu,
+static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, bool evict,
+				struct ttm_operation_ctx *ctx,
 				struct ttm_mem_reg *new_mem)
 {
 	struct amdgpu_device *adev;
@@ -536,16 +532,15 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo,
 	placements.fpfn = 0;
 	placements.lpfn = 0;
 	placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
-	r = ttm_bo_mem_space(bo, &placement, &tmp_mem,
-			     interruptible, no_wait_gpu);
+	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, ctx);
 	if (unlikely(r)) {
 		return r;
 	}
-	r = ttm_bo_move_ttm(bo, interruptible, no_wait_gpu, &tmp_mem);
+	r = ttm_bo_move_ttm(bo, ctx, &tmp_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
-	r = amdgpu_move_blit(bo, true, no_wait_gpu, new_mem, old_mem);
+	r = amdgpu_move_blit(bo, true, ctx->no_wait_gpu, new_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
@@ -554,10 +549,9 @@ out_cleanup:
 	return r;
 }
 
-static int amdgpu_bo_move(struct ttm_buffer_object *bo,
-			bool evict, bool interruptible,
-			bool no_wait_gpu,
-			struct ttm_mem_reg *new_mem)
+static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
+			  struct ttm_operation_ctx *ctx,
+			  struct ttm_mem_reg *new_mem)
 {
 	struct amdgpu_device *adev;
 	struct amdgpu_bo *abo;
@@ -592,19 +586,18 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo,
 
 	if (old_mem->mem_type == TTM_PL_VRAM &&
 	    new_mem->mem_type == TTM_PL_SYSTEM) {
-		r = amdgpu_move_vram_ram(bo, evict, interruptible,
-					no_wait_gpu, new_mem);
+		r = amdgpu_move_vram_ram(bo, evict, ctx, new_mem);
 	} else if (old_mem->mem_type == TTM_PL_SYSTEM &&
 		   new_mem->mem_type == TTM_PL_VRAM) {
-		r = amdgpu_move_ram_vram(bo, evict, interruptible,
-					    no_wait_gpu, new_mem);
+		r = amdgpu_move_ram_vram(bo, evict, ctx, new_mem);
 	} else {
-		r = amdgpu_move_blit(bo, evict, no_wait_gpu, new_mem, old_mem);
+		r = amdgpu_move_blit(bo, evict, ctx->no_wait_gpu,
+				     new_mem, old_mem);
 	}
 
 	if (r) {
 memcpy:
-		r = ttm_bo_move_memcpy(bo, interruptible, no_wait_gpu, new_mem);
+		r = ttm_bo_move_memcpy(bo, ctx, new_mem);
 		if (r) {
 			return r;
 		}
@@ -690,7 +683,6 @@ struct amdgpu_ttm_tt {
 	struct list_head        guptasks;
 	atomic_t		mmu_invalidations;
 	uint32_t		last_set_pages;
-	struct list_head        list;
 };
 
 int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
@@ -861,44 +853,35 @@ static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm,
 	    bo_mem->mem_type == AMDGPU_PL_OA)
 		return -EINVAL;
 
-	if (!amdgpu_gtt_mgr_is_allocated(bo_mem))
+	if (!amdgpu_gtt_mgr_has_gart_addr(bo_mem)) {
+		gtt->offset = AMDGPU_BO_INVALID_OFFSET;
 		return 0;
+	}
 
-	spin_lock(&gtt->adev->gtt_list_lock);
 	flags = amdgpu_ttm_tt_pte_flags(gtt->adev, ttm, bo_mem);
 	gtt->offset = (u64)bo_mem->start << PAGE_SHIFT;
 	r = amdgpu_gart_bind(gtt->adev, gtt->offset, ttm->num_pages,
 		ttm->pages, gtt->ttm.dma_address, flags);
 
-	if (r) {
+	if (r)
 		DRM_ERROR("failed to bind %lu pages at 0x%08llX\n",
 			  ttm->num_pages, gtt->offset);
-		goto error_gart_bind;
-	}
-
-	list_add_tail(&gtt->list, &gtt->adev->gtt_list);
-error_gart_bind:
-	spin_unlock(&gtt->adev->gtt_list_lock);
 	return r;
 }
 
-bool amdgpu_ttm_is_bound(struct ttm_tt *ttm)
-{
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
-
-	return gtt && !list_empty(&gtt->list);
-}
-
-int amdgpu_ttm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *bo_mem)
+int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
-	struct ttm_tt *ttm = bo->ttm;
+	struct ttm_operation_ctx ctx = { false, false };
+	struct amdgpu_ttm_tt *gtt = (void*)bo->ttm;
 	struct ttm_mem_reg tmp;
 	struct ttm_placement placement;
 	struct ttm_place placements;
+	uint64_t flags;
 	int r;
 
-	if (!ttm || amdgpu_ttm_is_bound(ttm))
+	if (bo->mem.mem_type != TTM_PL_TT ||
+	    amdgpu_gtt_mgr_has_gart_addr(&bo->mem))
 		return 0;
 
 	tmp = bo->mem;
@@ -912,43 +895,44 @@ int amdgpu_ttm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *bo_mem)
 	placements.flags = (bo->mem.placement & ~TTM_PL_MASK_MEM) |
 		TTM_PL_FLAG_TT;
 
-	r = ttm_bo_mem_space(bo, &placement, &tmp, true, false);
+	r = ttm_bo_mem_space(bo, &placement, &tmp, &ctx);
 	if (unlikely(r))
 		return r;
 
-	r = ttm_bo_move_ttm(bo, true, false, &tmp);
-	if (unlikely(r))
+	flags = amdgpu_ttm_tt_pte_flags(adev, bo->ttm, &tmp);
+	gtt->offset = (u64)tmp.start << PAGE_SHIFT;
+	r = amdgpu_gart_bind(adev, gtt->offset, bo->ttm->num_pages,
+			     bo->ttm->pages, gtt->ttm.dma_address, flags);
+	if (unlikely(r)) {
 		ttm_bo_mem_put(bo, &tmp);
-	else
-		bo->offset = (bo->mem.start << PAGE_SHIFT) +
-			bo->bdev->man[bo->mem.mem_type].gpu_offset;
+		return r;
+	}
 
-	return r;
+	ttm_bo_mem_put(bo, &bo->mem);
+	bo->mem = tmp;
+	bo->offset = (bo->mem.start << PAGE_SHIFT) +
+		bo->bdev->man[bo->mem.mem_type].gpu_offset;
+
+	return 0;
 }
 
-int amdgpu_ttm_recover_gart(struct amdgpu_device *adev)
+int amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo)
 {
-	struct amdgpu_ttm_tt *gtt, *tmp;
-	struct ttm_mem_reg bo_mem;
+	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
+	struct amdgpu_ttm_tt *gtt = (void *)tbo->ttm;
 	uint64_t flags;
 	int r;
 
-	bo_mem.mem_type = TTM_PL_TT;
-	spin_lock(&adev->gtt_list_lock);
-	list_for_each_entry_safe(gtt, tmp, &adev->gtt_list, list) {
-		flags = amdgpu_ttm_tt_pte_flags(gtt->adev, &gtt->ttm.ttm, &bo_mem);
-		r = amdgpu_gart_bind(adev, gtt->offset, gtt->ttm.ttm.num_pages,
-				     gtt->ttm.ttm.pages, gtt->ttm.dma_address,
-				     flags);
-		if (r) {
-			spin_unlock(&adev->gtt_list_lock);
-			DRM_ERROR("failed to bind %lu pages at 0x%08llX\n",
-				  gtt->ttm.ttm.num_pages, gtt->offset);
-			return r;
-		}
-	}
-	spin_unlock(&adev->gtt_list_lock);
-	return 0;
+	if (!gtt)
+		return 0;
+
+	flags = amdgpu_ttm_tt_pte_flags(adev, &gtt->ttm.ttm, &tbo->mem);
+	r = amdgpu_gart_bind(adev, gtt->offset, gtt->ttm.ttm.num_pages,
+			     gtt->ttm.ttm.pages, gtt->ttm.dma_address, flags);
+	if (r)
+		DRM_ERROR("failed to bind %lu pages at 0x%08llX\n",
+			  gtt->ttm.ttm.num_pages, gtt->offset);
+	return r;
 }
 
 static int amdgpu_ttm_backend_unbind(struct ttm_tt *ttm)
@@ -959,20 +943,14 @@ static int amdgpu_ttm_backend_unbind(struct ttm_tt *ttm)
 	if (gtt->userptr)
 		amdgpu_ttm_tt_unpin_userptr(ttm);
 
-	if (!amdgpu_ttm_is_bound(ttm))
+	if (gtt->offset == AMDGPU_BO_INVALID_OFFSET)
 		return 0;
 
 	/* unbind shouldn't be done for GDS/GWS/OA in ttm_bo_clean_mm */
-	spin_lock(&gtt->adev->gtt_list_lock);
 	r = amdgpu_gart_unbind(gtt->adev, gtt->offset, ttm->num_pages);
-	if (r) {
+	if (r)
 		DRM_ERROR("failed to unbind %lu pages at 0x%08llX\n",
 			  gtt->ttm.ttm.num_pages, gtt->offset);
-		goto error_unbind;
-	}
-	list_del_init(&gtt->list);
-error_unbind:
-	spin_unlock(&gtt->adev->gtt_list_lock);
 	return r;
 }
 
@@ -1009,11 +987,11 @@ static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_bo_device *bdev,
 		kfree(gtt);
 		return NULL;
 	}
-	INIT_LIST_HEAD(&gtt->list);
 	return &gtt->ttm.ttm;
 }
 
-static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm)
+static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
+			struct ttm_operation_ctx *ctx)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
@@ -1041,11 +1019,11 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm)
 
 #ifdef CONFIG_SWIOTLB
 	if (swiotlb_nr_tbl()) {
-		return ttm_dma_populate(&gtt->ttm, adev->dev);
+		return ttm_dma_populate(&gtt->ttm, adev->dev, ctx);
 	}
 #endif
 
-	return ttm_populate_and_map_pages(adev->dev, &gtt->ttm);
+	return ttm_populate_and_map_pages(adev->dev, &gtt->ttm, ctx);
 }
 
 static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
@@ -1292,6 +1270,101 @@ static struct ttm_bo_driver amdgpu_bo_driver = {
 	.access_memory = &amdgpu_ttm_access_memory
 };
 
+/*
+ * Firmware Reservation functions
+ */
+/**
+ * amdgpu_ttm_fw_reserve_vram_fini - free fw reserved vram
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * free fw reserved vram if it has been reserved.
+ */
+static void amdgpu_ttm_fw_reserve_vram_fini(struct amdgpu_device *adev)
+{
+	amdgpu_bo_free_kernel(&adev->fw_vram_usage.reserved_bo,
+		NULL, &adev->fw_vram_usage.va);
+}
+
+/**
+ * amdgpu_ttm_fw_reserve_vram_init - create bo vram reservation from fw
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * create bo vram reservation from fw.
+ */
+static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev)
+{
+	struct ttm_operation_ctx ctx = { false, false };
+	int r = 0;
+	int i;
+	u64 vram_size = adev->mc.visible_vram_size;
+	u64 offset = adev->fw_vram_usage.start_offset;
+	u64 size = adev->fw_vram_usage.size;
+	struct amdgpu_bo *bo;
+
+	adev->fw_vram_usage.va = NULL;
+	adev->fw_vram_usage.reserved_bo = NULL;
+
+	if (adev->fw_vram_usage.size > 0 &&
+		adev->fw_vram_usage.size <= vram_size) {
+
+		r = amdgpu_bo_create(adev, adev->fw_vram_usage.size,
+			PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_VRAM,
+			AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
+			AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS, NULL, NULL, 0,
+			&adev->fw_vram_usage.reserved_bo);
+		if (r)
+			goto error_create;
+
+		r = amdgpu_bo_reserve(adev->fw_vram_usage.reserved_bo, false);
+		if (r)
+			goto error_reserve;
+
+		/* remove the original mem node and create a new one at the
+		 * request position
+		 */
+		bo = adev->fw_vram_usage.reserved_bo;
+		offset = ALIGN(offset, PAGE_SIZE);
+		for (i = 0; i < bo->placement.num_placement; ++i) {
+			bo->placements[i].fpfn = offset >> PAGE_SHIFT;
+			bo->placements[i].lpfn = (offset + size) >> PAGE_SHIFT;
+		}
+
+		ttm_bo_mem_put(&bo->tbo, &bo->tbo.mem);
+		r = ttm_bo_mem_space(&bo->tbo, &bo->placement,
+				     &bo->tbo.mem, &ctx);
+		if (r)
+			goto error_pin;
+
+		r = amdgpu_bo_pin_restricted(adev->fw_vram_usage.reserved_bo,
+			AMDGPU_GEM_DOMAIN_VRAM,
+			adev->fw_vram_usage.start_offset,
+			(adev->fw_vram_usage.start_offset +
+			adev->fw_vram_usage.size), NULL);
+		if (r)
+			goto error_pin;
+		r = amdgpu_bo_kmap(adev->fw_vram_usage.reserved_bo,
+			&adev->fw_vram_usage.va);
+		if (r)
+			goto error_kmap;
+
+		amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo);
+	}
+	return r;
+
+error_kmap:
+	amdgpu_bo_unpin(adev->fw_vram_usage.reserved_bo);
+error_pin:
+	amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo);
+error_reserve:
+	amdgpu_bo_unref(&adev->fw_vram_usage.reserved_bo);
+error_create:
+	adev->fw_vram_usage.va = NULL;
+	adev->fw_vram_usage.reserved_bo = NULL;
+	return r;
+}
+
 int amdgpu_ttm_init(struct amdgpu_device *adev)
 {
 	uint64_t gtt_size;
@@ -1334,7 +1407,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	 *The reserved vram for firmware must be pinned to the specified
 	 *place on the VRAM, so reserve it early.
 	 */
-	r = amdgpu_fw_reserve_vram_init(adev);
+	r = amdgpu_ttm_fw_reserve_vram_init(adev);
 	if (r) {
 		return r;
 	}
@@ -1348,9 +1421,14 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	DRM_INFO("amdgpu: %uM of VRAM memory ready\n",
 		 (unsigned) (adev->mc.real_vram_size / (1024 * 1024)));
 
-	if (amdgpu_gtt_size == -1)
-		gtt_size = max((AMDGPU_DEFAULT_GTT_SIZE_MB << 20),
-			       adev->mc.mc_vram_size);
+	if (amdgpu_gtt_size == -1) {
+		struct sysinfo si;
+
+		si_meminfo(&si);
+		gtt_size = min(max((AMDGPU_DEFAULT_GTT_SIZE_MB << 20),
+			       adev->mc.mc_vram_size),
+			       ((uint64_t)si.totalram * si.mem_unit * 3/4));
+	}
 	else
 		gtt_size = (uint64_t)amdgpu_gtt_size << 20;
 	r = ttm_bo_init_mm(&adev->mman.bdev, TTM_PL_TT, gtt_size >> PAGE_SHIFT);
@@ -1410,19 +1488,13 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 
 void amdgpu_ttm_fini(struct amdgpu_device *adev)
 {
-	int r;
-
 	if (!adev->mman.initialized)
 		return;
+
 	amdgpu_ttm_debugfs_fini(adev);
-	if (adev->stolen_vga_memory) {
-		r = amdgpu_bo_reserve(adev->stolen_vga_memory, true);
-		if (r == 0) {
-			amdgpu_bo_unpin(adev->stolen_vga_memory);
-			amdgpu_bo_unreserve(adev->stolen_vga_memory);
-		}
-		amdgpu_bo_unref(&adev->stolen_vga_memory);
-	}
+	amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, NULL);
+	amdgpu_ttm_fw_reserve_vram_fini(adev);
+
 	ttm_bo_clean_mm(&adev->mman.bdev, TTM_PL_VRAM);
 	ttm_bo_clean_mm(&adev->mman.bdev, TTM_PL_TT);
 	if (adev->gds.mem.total_size)
@@ -1432,7 +1504,6 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
 	if (adev->gds.oa.total_size)
 		ttm_bo_clean_mm(&adev->mman.bdev, AMDGPU_PL_OA);
 	ttm_bo_device_release(&adev->mman.bdev);
-	amdgpu_gart_fini(adev);
 	amdgpu_ttm_global_fini(adev);
 	adev->mman.initialized = false;
 	DRM_INFO("amdgpu: ttm finalized\n");
@@ -1628,7 +1699,7 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo,
 	}
 
 	if (bo->tbo.mem.mem_type == TTM_PL_TT) {
-		r = amdgpu_ttm_bind(&bo->tbo, &bo->tbo.mem);
+		r = amdgpu_ttm_alloc_gart(&bo->tbo);
 		if (r)
 			return r;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index abd4084982a3..167856f6080f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -25,7 +25,7 @@
 #define __AMDGPU_TTM_H__
 
 #include "amdgpu.h"
-#include "gpu_scheduler.h"
+#include <drm/gpu_scheduler.h>
 
 #define AMDGPU_PL_GDS		(TTM_PL_PRIV + 0)
 #define AMDGPU_PL_GWS		(TTM_PL_PRIV + 1)
@@ -55,7 +55,7 @@ struct amdgpu_mman {
 
 	struct mutex				gtt_window_lock;
 	/* Scheduler entity for buffer moves */
-	struct amd_sched_entity			entity;
+	struct drm_sched_entity			entity;
 };
 
 struct amdgpu_copy_mem {
@@ -67,8 +67,9 @@ struct amdgpu_copy_mem {
 extern const struct ttm_mem_type_manager_func amdgpu_gtt_mgr_func;
 extern const struct ttm_mem_type_manager_func amdgpu_vram_mgr_func;
 
-bool amdgpu_gtt_mgr_is_allocated(struct ttm_mem_reg *mem);
+bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem);
 uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man);
+int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man);
 
 uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man);
 uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
@@ -90,9 +91,8 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo,
 			struct dma_fence **fence);
 
 int amdgpu_mmap(struct file *filp, struct vm_area_struct *vma);
-bool amdgpu_ttm_is_bound(struct ttm_tt *ttm);
-int amdgpu_ttm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *bo_mem);
-int amdgpu_ttm_recover_gart(struct amdgpu_device *adev);
+int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo);
+int amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo);
 
 int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages);
 void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct page **pages);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 65649026b836..474f88fbafce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -359,7 +359,6 @@ static int amdgpu_ucode_patch_jt(struct amdgpu_firmware_info *ucode,
 
 int amdgpu_ucode_init_bo(struct amdgpu_device *adev)
 {
-	struct amdgpu_bo **bo = &adev->firmware.fw_buf;
 	uint64_t fw_offset = 0;
 	int i, err;
 	struct amdgpu_firmware_info *ucode = NULL;
@@ -370,36 +369,16 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)
 		return 0;
 	}
 
-	if (!amdgpu_sriov_vf(adev) || !adev->in_sriov_reset) {
-		err = amdgpu_bo_create(adev, adev->firmware.fw_size, PAGE_SIZE, true,
+	if (!adev->in_gpu_reset) {
+		err = amdgpu_bo_create_kernel(adev, adev->firmware.fw_size, PAGE_SIZE,
 					amdgpu_sriov_vf(adev) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
-					AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
-					NULL, NULL, 0, bo);
+					&adev->firmware.fw_buf,
+					&adev->firmware.fw_buf_mc,
+					&adev->firmware.fw_buf_ptr);
 		if (err) {
-			dev_err(adev->dev, "(%d) Firmware buffer allocate failed\n", err);
+			dev_err(adev->dev, "failed to create kernel buffer for firmware.fw_buf\n");
 			goto failed;
 		}
-
-		err = amdgpu_bo_reserve(*bo, false);
-		if (err) {
-			dev_err(adev->dev, "(%d) Firmware buffer reserve failed\n", err);
-			goto failed_reserve;
-		}
-
-		err = amdgpu_bo_pin(*bo, amdgpu_sriov_vf(adev) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
-					&adev->firmware.fw_buf_mc);
-		if (err) {
-			dev_err(adev->dev, "(%d) Firmware buffer pin failed\n", err);
-			goto failed_pin;
-		}
-
-		err = amdgpu_bo_kmap(*bo, &adev->firmware.fw_buf_ptr);
-		if (err) {
-			dev_err(adev->dev, "(%d) Firmware buffer kmap failed\n", err);
-			goto failed_kmap;
-		}
-
-		amdgpu_bo_unreserve(*bo);
 	}
 
 	memset(adev->firmware.fw_buf_ptr, 0, adev->firmware.fw_size);
@@ -436,12 +415,6 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)
 	}
 	return 0;
 
-failed_kmap:
-	amdgpu_bo_unpin(*bo);
-failed_pin:
-	amdgpu_bo_unreserve(*bo);
-failed_reserve:
-	amdgpu_bo_unref(bo);
 failed:
 	if (err)
 		adev->firmware.load_type = AMDGPU_FW_LOAD_DIRECT;
@@ -464,8 +437,10 @@ int amdgpu_ucode_fini_bo(struct amdgpu_device *adev)
 			ucode->kaddr = NULL;
 		}
 	}
-	amdgpu_bo_unref(&adev->firmware.fw_buf);
-	adev->firmware.fw_buf = NULL;
+
+	amdgpu_bo_free_kernel(&adev->firmware.fw_buf,
+				&adev->firmware.fw_buf_mc,
+				&adev->firmware.fw_buf_ptr);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index e8bd50cf9785..b2eae86bf906 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -116,7 +116,7 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work);
 int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring;
-	struct amd_sched_rq *rq;
+	struct drm_sched_rq *rq;
 	unsigned long bo_size;
 	const char *fw_name;
 	const struct common_firmware_header *hdr;
@@ -230,9 +230,9 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	}
 
 	ring = &adev->uvd.ring;
-	rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
-	r = amd_sched_entity_init(&ring->sched, &adev->uvd.entity,
-				  rq, amdgpu_sched_jobs);
+	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+	r = drm_sched_entity_init(&ring->sched, &adev->uvd.entity,
+				  rq, amdgpu_sched_jobs, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up UVD run queue.\n");
 		return r;
@@ -244,7 +244,7 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	}
 
 	/* from uvd v5.0 HW addressing capacity increased to 64 bits */
-	if (!amdgpu_ip_block_version_cmp(adev, AMD_IP_BLOCK_TYPE_UVD, 5, 0))
+	if (!amdgpu_device_ip_block_version_cmp(adev, AMD_IP_BLOCK_TYPE_UVD, 5, 0))
 		adev->uvd.address_64_bit = true;
 
 	switch (adev->asic_type) {
@@ -272,7 +272,7 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 	int i;
 	kfree(adev->uvd.saved_bo);
 
-	amd_sched_entity_fini(&adev->uvd.ring.sched, &adev->uvd.entity);
+	drm_sched_entity_fini(&adev->uvd.ring.sched, &adev->uvd.entity);
 
 	amdgpu_bo_free_kernel(&adev->uvd.vcpu_bo,
 			      &adev->uvd.gpu_addr,
@@ -297,6 +297,8 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 	if (adev->uvd.vcpu_bo == NULL)
 		return 0;
 
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
 	for (i = 0; i < adev->uvd.max_handles; ++i)
 		if (atomic_read(&adev->uvd.handles[i]))
 			break;
@@ -304,8 +306,6 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 	if (i == AMDGPU_MAX_UVD_HANDLES)
 		return 0;
 
-	cancel_delayed_work_sync(&adev->uvd.idle_work);
-
 	size = amdgpu_bo_size(adev->uvd.vcpu_bo);
 	ptr = adev->uvd.cpu_addr;
 
@@ -346,6 +346,8 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev)
 			ptr += le32_to_cpu(hdr->ucode_size_bytes);
 		}
 		memset_io(ptr, 0, size);
+		/* to restore uvd fence seq */
+		amdgpu_fence_driver_force_completion(&adev->uvd.ring);
 	}
 
 	return 0;
@@ -408,6 +410,7 @@ static u64 amdgpu_uvd_get_addr_from_ctx(struct amdgpu_uvd_cs_ctx *ctx)
  */
 static int amdgpu_uvd_cs_pass1(struct amdgpu_uvd_cs_ctx *ctx)
 {
+	struct ttm_operation_ctx tctx = { false, false };
 	struct amdgpu_bo_va_mapping *mapping;
 	struct amdgpu_bo *bo;
 	uint32_t cmd;
@@ -430,7 +433,7 @@ static int amdgpu_uvd_cs_pass1(struct amdgpu_uvd_cs_ctx *ctx)
 		}
 		amdgpu_uvd_force_into_uvd_segment(bo);
 
-		r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, &tctx);
 	}
 
 	return r;
@@ -949,6 +952,7 @@ int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx)
 static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 			       bool direct, struct dma_fence **fence)
 {
+	struct ttm_operation_ctx ctx = { true, false };
 	struct ttm_validate_buffer tv;
 	struct ww_acquire_ctx ticket;
 	struct list_head head;
@@ -975,7 +979,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 		amdgpu_uvd_force_into_uvd_segment(bo);
 	}
 
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (r)
 		goto err;
 
@@ -1151,10 +1155,10 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 		} else {
 			amdgpu_asic_set_uvd_clocks(adev, 0, 0);
 			/* shutdown the UVD block */
-			amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
-							    AMD_PG_STATE_GATE);
-			amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
-							    AMD_CG_STATE_GATE);
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+							       AMD_PG_STATE_GATE);
+			amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+							       AMD_CG_STATE_GATE);
 		}
 	} else {
 		schedule_delayed_work(&adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
@@ -1174,10 +1178,10 @@ void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring)
 			amdgpu_dpm_enable_uvd(adev, true);
 		} else {
 			amdgpu_asic_set_uvd_clocks(adev, 53300, 40000);
-			amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
-							    AMD_CG_STATE_UNGATE);
-			amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
-							    AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+							       AMD_CG_STATE_UNGATE);
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+							       AMD_PG_STATE_UNGATE);
 		}
 	}
 }
@@ -1218,7 +1222,7 @@ int amdgpu_uvd_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	} else if (r < 0) {
 		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 	} else {
-		DRM_INFO("ib test on ring %d succeeded\n",  ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n",  ring->idx);
 		r = 0;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
index 3553b92bf69a..32ea20b99e53 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
@@ -31,6 +31,10 @@
 #define AMDGPU_UVD_SESSION_SIZE		(50*1024)
 #define AMDGPU_UVD_FIRMWARE_OFFSET	256
 
+#define AMDGPU_UVD_FIRMWARE_SIZE(adev)    \
+	(AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(((const struct common_firmware_header *)(adev)->uvd.fw->data)->ucode_size_bytes) + \
+			       8) - AMDGPU_UVD_FIRMWARE_OFFSET)
+
 struct amdgpu_uvd {
 	struct amdgpu_bo	*vcpu_bo;
 	void			*cpu_addr;
@@ -47,8 +51,8 @@ struct amdgpu_uvd {
 	struct amdgpu_irq_src	irq;
 	bool			address_64_bit;
 	bool			use_ctx_buf;
-	struct amd_sched_entity entity;
-	struct amd_sched_entity entity_enc;
+	struct drm_sched_entity entity;
+	struct drm_sched_entity entity_enc;
 	uint32_t                srbm_soft_reset;
 	unsigned		num_enc_rings;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 2918de2f39ec..d274ae535530 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -85,7 +85,7 @@ static void amdgpu_vce_idle_work_handler(struct work_struct *work);
 int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 {
 	struct amdgpu_ring *ring;
-	struct amd_sched_rq *rq;
+	struct drm_sched_rq *rq;
 	const char *fw_name;
 	const struct common_firmware_header *hdr;
 	unsigned ucode_version, version_major, version_minor, binary_id;
@@ -174,9 +174,9 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 	}
 
 	ring = &adev->vce.ring[0];
-	rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
-	r = amd_sched_entity_init(&ring->sched, &adev->vce.entity,
-				  rq, amdgpu_sched_jobs);
+	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+	r = drm_sched_entity_init(&ring->sched, &adev->vce.entity,
+				  rq, amdgpu_sched_jobs, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCE run queue.\n");
 		return r;
@@ -207,7 +207,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
 	if (adev->vce.vcpu_bo == NULL)
 		return 0;
 
-	amd_sched_entity_fini(&adev->vce.ring[0].sched, &adev->vce.entity);
+	drm_sched_entity_fini(&adev->vce.ring[0].sched, &adev->vce.entity);
 
 	amdgpu_bo_free_kernel(&adev->vce.vcpu_bo, &adev->vce.gpu_addr,
 		(void **)&adev->vce.cpu_addr);
@@ -311,10 +311,10 @@ static void amdgpu_vce_idle_work_handler(struct work_struct *work)
 			amdgpu_dpm_enable_vce(adev, false);
 		} else {
 			amdgpu_asic_set_vce_clocks(adev, 0, 0);
-			amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
-							    AMD_PG_STATE_GATE);
-			amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
-							    AMD_CG_STATE_GATE);
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+							       AMD_PG_STATE_GATE);
+			amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+							       AMD_CG_STATE_GATE);
 		}
 	} else {
 		schedule_delayed_work(&adev->vce.idle_work, VCE_IDLE_TIMEOUT);
@@ -343,10 +343,10 @@ void amdgpu_vce_ring_begin_use(struct amdgpu_ring *ring)
 			amdgpu_dpm_enable_vce(adev, true);
 		} else {
 			amdgpu_asic_set_vce_clocks(adev, 53300, 40000);
-			amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
-							    AMD_CG_STATE_UNGATE);
-			amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
-							    AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+							       AMD_CG_STATE_UNGATE);
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE,
+							       AMD_PG_STATE_UNGATE);
 
 		}
 	}
@@ -544,6 +544,55 @@ err:
 }
 
 /**
+ * amdgpu_vce_cs_validate_bo - make sure not to cross 4GB boundary
+ *
+ * @p: parser context
+ * @lo: address of lower dword
+ * @hi: address of higher dword
+ * @size: minimum size
+ * @index: bs/fb index
+ *
+ * Make sure that no BO cross a 4GB boundary.
+ */
+static int amdgpu_vce_validate_bo(struct amdgpu_cs_parser *p, uint32_t ib_idx,
+				  int lo, int hi, unsigned size, int32_t index)
+{
+	int64_t offset = ((uint64_t)size) * ((int64_t)index);
+	struct ttm_operation_ctx ctx = { false, false };
+	struct amdgpu_bo_va_mapping *mapping;
+	unsigned i, fpfn, lpfn;
+	struct amdgpu_bo *bo;
+	uint64_t addr;
+	int r;
+
+	addr = ((uint64_t)amdgpu_get_ib_value(p, ib_idx, lo)) |
+	       ((uint64_t)amdgpu_get_ib_value(p, ib_idx, hi)) << 32;
+	if (index >= 0) {
+		addr += offset;
+		fpfn = PAGE_ALIGN(offset) >> PAGE_SHIFT;
+		lpfn = 0x100000000ULL >> PAGE_SHIFT;
+	} else {
+		fpfn = 0;
+		lpfn = (0x100000000ULL - PAGE_ALIGN(offset)) >> PAGE_SHIFT;
+	}
+
+	r = amdgpu_cs_find_mapping(p, addr, &bo, &mapping);
+	if (r) {
+		DRM_ERROR("Can't find BO for addr 0x%010Lx %d %d %d %d\n",
+			  addr, lo, hi, size, index);
+		return r;
+	}
+
+	for (i = 0; i < bo->placement.num_placement; ++i) {
+		bo->placements[i].fpfn = max(bo->placements[i].fpfn, fpfn);
+		bo->placements[i].lpfn = bo->placements[i].lpfn ?
+			min(bo->placements[i].lpfn, lpfn) : lpfn;
+	}
+	return ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+}
+
+
+/**
  * amdgpu_vce_cs_reloc - command submission relocation
  *
  * @p: parser context
@@ -648,12 +697,13 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 	uint32_t allocated = 0;
 	uint32_t tmp, handle = 0;
 	uint32_t *size = &tmp;
-	int i, r = 0, idx = 0;
+	unsigned idx;
+	int i, r = 0;
 
 	p->job->vm = NULL;
 	ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo);
 
-	while (idx < ib->length_dw) {
+	for (idx = 0; idx < ib->length_dw;) {
 		uint32_t len = amdgpu_get_ib_value(p, ib_idx, idx);
 		uint32_t cmd = amdgpu_get_ib_value(p, ib_idx, idx + 1);
 
@@ -664,6 +714,54 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 		}
 
 		switch (cmd) {
+		case 0x00000002: /* task info */
+			fb_idx = amdgpu_get_ib_value(p, ib_idx, idx + 6);
+			bs_idx = amdgpu_get_ib_value(p, ib_idx, idx + 7);
+			break;
+
+		case 0x03000001: /* encode */
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 10,
+						   idx + 9, 0, 0);
+			if (r)
+				goto out;
+
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 12,
+						   idx + 11, 0, 0);
+			if (r)
+				goto out;
+			break;
+
+		case 0x05000001: /* context buffer */
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 3,
+						   idx + 2, 0, 0);
+			if (r)
+				goto out;
+			break;
+
+		case 0x05000004: /* video bitstream buffer */
+			tmp = amdgpu_get_ib_value(p, ib_idx, idx + 4);
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 3, idx + 2,
+						   tmp, bs_idx);
+			if (r)
+				goto out;
+			break;
+
+		case 0x05000005: /* feedback buffer */
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 3, idx + 2,
+						   4096, fb_idx);
+			if (r)
+				goto out;
+			break;
+		}
+
+		idx += len / 4;
+	}
+
+	for (idx = 0; idx < ib->length_dw;) {
+		uint32_t len = amdgpu_get_ib_value(p, ib_idx, idx);
+		uint32_t cmd = amdgpu_get_ib_value(p, ib_idx, idx + 1);
+
+		switch (cmd) {
 		case 0x00000001: /* session */
 			handle = amdgpu_get_ib_value(p, ib_idx, idx + 2);
 			session_idx = amdgpu_vce_validate_handle(p, handle,
@@ -893,7 +991,7 @@ out:
  *
  */
 void amdgpu_vce_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib,
-			     unsigned vm_id, bool ctx_switch)
+			     unsigned vmid, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, VCE_CMD_IB);
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
@@ -954,7 +1052,7 @@ int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed\n",
@@ -999,7 +1097,7 @@ int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	} else if (r < 0) {
 		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 	} else {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	}
 error:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
index 5ce54cde472d..0fd378ae92c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
@@ -46,7 +46,7 @@ struct amdgpu_vce {
 	struct amdgpu_ring	ring[AMDGPU_MAX_VCE_RINGS];
 	struct amdgpu_irq_src	irq;
 	unsigned		harvest_config;
-	struct amd_sched_entity	entity;
+	struct drm_sched_entity	entity;
 	uint32_t                srbm_soft_reset;
 	unsigned		num_rings;
 };
@@ -63,7 +63,7 @@ void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp);
 int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx);
 int amdgpu_vce_ring_parse_cs_vm(struct amdgpu_cs_parser *p, uint32_t ib_idx);
 void amdgpu_vce_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib,
-			     unsigned vm_id, bool ctx_switch);
+			     unsigned vmid, bool ctx_switch);
 void amdgpu_vce_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
 				unsigned flags);
 int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 041e0121590c..837962118dbc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -35,8 +35,7 @@
 #include "soc15d.h"
 #include "soc15_common.h"
 
-#include "vega10/soc15ip.h"
-#include "raven1/VCN/vcn_1_0_offset.h"
+#include "vcn/vcn_1_0_offset.h"
 
 /* 1 second timeout */
 #define VCN_IDLE_TIMEOUT	msecs_to_jiffies(1000)
@@ -51,7 +50,7 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work);
 int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring;
-	struct amd_sched_rq *rq;
+	struct drm_sched_rq *rq;
 	unsigned long bo_size;
 	const char *fw_name;
 	const struct common_firmware_header *hdr;
@@ -104,18 +103,18 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 	}
 
 	ring = &adev->vcn.ring_dec;
-	rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
-	r = amd_sched_entity_init(&ring->sched, &adev->vcn.entity_dec,
-				  rq, amdgpu_sched_jobs);
+	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+	r = drm_sched_entity_init(&ring->sched, &adev->vcn.entity_dec,
+				  rq, amdgpu_sched_jobs, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCN dec run queue.\n");
 		return r;
 	}
 
 	ring = &adev->vcn.ring_enc[0];
-	rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
-	r = amd_sched_entity_init(&ring->sched, &adev->vcn.entity_enc,
-				  rq, amdgpu_sched_jobs);
+	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+	r = drm_sched_entity_init(&ring->sched, &adev->vcn.entity_enc,
+				  rq, amdgpu_sched_jobs, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCN enc run queue.\n");
 		return r;
@@ -130,9 +129,9 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 
 	kfree(adev->vcn.saved_bo);
 
-	amd_sched_entity_fini(&adev->vcn.ring_dec.sched, &adev->vcn.entity_dec);
+	drm_sched_entity_fini(&adev->vcn.ring_dec.sched, &adev->vcn.entity_dec);
 
-	amd_sched_entity_fini(&adev->vcn.ring_enc[0].sched, &adev->vcn.entity_enc);
+	drm_sched_entity_fini(&adev->vcn.ring_enc[0].sched, &adev->vcn.entity_enc);
 
 	amdgpu_bo_free_kernel(&adev->vcn.vcpu_bo,
 			      &adev->vcn.gpu_addr,
@@ -261,7 +260,7 @@ int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
@@ -274,6 +273,7 @@ int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring)
 static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 			       bool direct, struct dma_fence **fence)
 {
+	struct ttm_operation_ctx ctx = { true, false };
 	struct ttm_validate_buffer tv;
 	struct ww_acquire_ctx ticket;
 	struct list_head head;
@@ -294,7 +294,7 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *b
 	if (r)
 		return r;
 
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (r)
 		goto err;
 
@@ -467,7 +467,7 @@ int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	} else if (r < 0) {
 		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 	} else {
-		DRM_INFO("ib test on ring %d succeeded\n",  ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n",  ring->idx);
 		r = 0;
 	}
 
@@ -500,7 +500,7 @@ int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed\n",
@@ -643,7 +643,7 @@ int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	} else if (r < 0) {
 		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 	} else {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	}
 error:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index d50ba0657854..2fd7db891689 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -56,8 +56,8 @@ struct amdgpu_vcn {
 	struct amdgpu_ring	ring_dec;
 	struct amdgpu_ring	ring_enc[AMDGPU_VCN_MAX_ENC_RINGS];
 	struct amdgpu_irq_src	irq;
-	struct amd_sched_entity entity_dec;
-	struct amd_sched_entity entity_enc;
+	struct drm_sched_entity entity_dec;
+	struct drm_sched_entity entity_enc;
 	unsigned		num_enc_rings;
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 6738df836a70..e7dfb7b44b4b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -24,6 +24,14 @@
 #include "amdgpu.h"
 #define MAX_KIQ_REG_WAIT	100000000 /* in usecs */
 
+bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev)
+{
+	/* By now all MMIO pages except mailbox are blocked */
+	/* if blocking is enabled in hypervisor. Choose the */
+	/* SCRATCH_REG0 to test. */
+	return RREG32_NO_KIQ(0xc040) == 0xffffffff;
+}
+
 int amdgpu_allocate_static_csa(struct amdgpu_device *adev)
 {
 	int r;
@@ -39,6 +47,12 @@ int amdgpu_allocate_static_csa(struct amdgpu_device *adev)
 	return 0;
 }
 
+void amdgpu_free_static_csa(struct amdgpu_device *adev) {
+	amdgpu_bo_free_kernel(&adev->virt.csa_obj,
+						&adev->virt.csa_vmid0_addr,
+						NULL);
+}
+
 /*
  * amdgpu_map_static_csa should be called during amdgpu_vm_init
  * it maps virtual address "AMDGPU_VA_RESERVED_SIZE - AMDGPU_CSA_SIZE"
@@ -107,8 +121,6 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev)
 	adev->enable_virtual_display = true;
 	adev->cg_flags = 0;
 	adev->pg_flags = 0;
-
-	mutex_init(&adev->virt.lock_reset);
 }
 
 uint32_t amdgpu_virt_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
@@ -228,6 +240,22 @@ int amdgpu_virt_reset_gpu(struct amdgpu_device *adev)
 }
 
 /**
+ * amdgpu_virt_wait_reset() - wait for reset gpu completed
+ * @amdgpu:	amdgpu device.
+ * Wait for GPU reset completed.
+ * Return: Zero if reset success, otherwise will return error.
+ */
+int amdgpu_virt_wait_reset(struct amdgpu_device *adev)
+{
+	struct amdgpu_virt *virt = &adev->virt;
+
+	if (!virt->ops || !virt->ops->wait_reset)
+		return -EINVAL;
+
+	return virt->ops->wait_reset(adev);
+}
+
+/**
  * amdgpu_virt_alloc_mm_table() - alloc memory for mm table
  * @amdgpu:	amdgpu device.
  * MM table is used by UVD and VCE for its initialization
@@ -296,7 +324,6 @@ int amdgpu_virt_fw_reserve_get_checksum(void *obj,
 
 void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 {
-	uint32_t pf2vf_ver = 0;
 	uint32_t pf2vf_size = 0;
 	uint32_t checksum = 0;
 	uint32_t checkval;
@@ -309,9 +336,9 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 		adev->virt.fw_reserve.p_pf2vf =
 			(struct amdgim_pf2vf_info_header *)(
 			adev->fw_vram_usage.va + AMDGIM_DATAEXCHANGE_OFFSET);
-		pf2vf_ver = adev->virt.fw_reserve.p_pf2vf->version;
 		AMDGPU_FW_VRAM_PF2VF_READ(adev, header.size, &pf2vf_size);
 		AMDGPU_FW_VRAM_PF2VF_READ(adev, checksum, &checksum);
+		AMDGPU_FW_VRAM_PF2VF_READ(adev, feature_flags, &adev->virt.gim_feature);
 
 		/* pf2vf message must be in 4K */
 		if (pf2vf_size > 0 && pf2vf_size < 4096) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index b89d37fc406f..6a83425aa9ed 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -55,6 +55,7 @@ struct amdgpu_virt_ops {
 	int (*req_full_gpu)(struct amdgpu_device *adev, bool init);
 	int (*rel_full_gpu)(struct amdgpu_device *adev, bool init);
 	int (*reset_gpu)(struct amdgpu_device *adev);
+	int (*wait_reset)(struct amdgpu_device *adev);
 	void (*trans_msg)(struct amdgpu_device *adev, u32 req, u32 data1, u32 data2, u32 data3);
 };
 
@@ -80,6 +81,8 @@ enum AMDGIM_FEATURE_FLAG {
 	AMDGIM_FEATURE_ERROR_LOG_COLLECT = 0x1,
 	/* GIM supports feature of loading uCodes */
 	AMDGIM_FEATURE_GIM_LOAD_UCODES   = 0x2,
+	/* VRAM LOST by GIM */
+	AMDGIM_FEATURE_GIM_FLR_VRAMLOST = 0x4,
 };
 
 struct amdgim_pf2vf_info_header {
@@ -238,7 +241,6 @@ struct amdgpu_virt {
 	uint64_t			csa_vmid0_addr;
 	bool chained_ib_support;
 	uint32_t			reg_val_offs;
-	struct mutex                    lock_reset;
 	struct amdgpu_irq_src		ack_irq;
 	struct amdgpu_irq_src		rcv_irq;
 	struct work_struct		flr_work;
@@ -246,6 +248,7 @@ struct amdgpu_virt {
 	const struct amdgpu_virt_ops	*ops;
 	struct amdgpu_vf_error_buffer   vf_errors;
 	struct amdgpu_virt_fw_reserve	fw_reserve;
+	uint32_t gim_feature;
 };
 
 #define AMDGPU_CSA_SIZE    (8 * 1024)
@@ -276,16 +279,18 @@ static inline bool is_virtual_machine(void)
 }
 
 struct amdgpu_vm;
+bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev);
 int amdgpu_allocate_static_csa(struct amdgpu_device *adev);
 int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			  struct amdgpu_bo_va **bo_va);
+void amdgpu_free_static_csa(struct amdgpu_device *adev);
 void amdgpu_virt_init_setting(struct amdgpu_device *adev);
 uint32_t amdgpu_virt_kiq_rreg(struct amdgpu_device *adev, uint32_t reg);
 void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v);
 int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init);
 int amdgpu_virt_release_full_gpu(struct amdgpu_device *adev, bool init);
 int amdgpu_virt_reset_gpu(struct amdgpu_device *adev);
-int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job);
+int amdgpu_virt_wait_reset(struct amdgpu_device *adev);
 int amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev);
 void amdgpu_virt_free_mm_table(struct amdgpu_device *adev);
 int amdgpu_virt_fw_reserve_get_checksum(void *obj, unsigned long obj_size,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index c8c26f21993c..6fc16eecf2dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -34,52 +34,6 @@
 #include "amdgpu_trace.h"
 
 /*
- * PASID manager
- *
- * PASIDs are global address space identifiers that can be shared
- * between the GPU, an IOMMU and the driver. VMs on different devices
- * may use the same PASID if they share the same address
- * space. Therefore PASIDs are allocated using a global IDA. VMs are
- * looked up from the PASID per amdgpu_device.
- */
-static DEFINE_IDA(amdgpu_vm_pasid_ida);
-
-/**
- * amdgpu_vm_alloc_pasid - Allocate a PASID
- * @bits: Maximum width of the PASID in bits, must be at least 1
- *
- * Allocates a PASID of the given width while keeping smaller PASIDs
- * available if possible.
- *
- * Returns a positive integer on success. Returns %-EINVAL if bits==0.
- * Returns %-ENOSPC if no PASID was available. Returns %-ENOMEM on
- * memory allocation failure.
- */
-int amdgpu_vm_alloc_pasid(unsigned int bits)
-{
-	int pasid = -EINVAL;
-
-	for (bits = min(bits, 31U); bits > 0; bits--) {
-		pasid = ida_simple_get(&amdgpu_vm_pasid_ida,
-				       1U << (bits - 1), 1U << bits,
-				       GFP_KERNEL);
-		if (pasid != -ENOSPC)
-			break;
-	}
-
-	return pasid;
-}
-
-/**
- * amdgpu_vm_free_pasid - Free a PASID
- * @pasid: PASID to free
- */
-void amdgpu_vm_free_pasid(unsigned int pasid)
-{
-	ida_simple_remove(&amdgpu_vm_pasid_ida, pasid);
-}
-
-/*
  * GPUVM
  * GPUVM is similar to the legacy gart on older asics, however
  * rather than there being a single global gart table
@@ -139,6 +93,35 @@ struct amdgpu_prt_cb {
 };
 
 /**
+ * amdgpu_vm_level_shift - return the addr shift for each level
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Returns the number of bits the pfn needs to be right shifted for a level.
+ */
+static unsigned amdgpu_vm_level_shift(struct amdgpu_device *adev,
+				      unsigned level)
+{
+	unsigned shift = 0xff;
+
+	switch (level) {
+	case AMDGPU_VM_PDB2:
+	case AMDGPU_VM_PDB1:
+	case AMDGPU_VM_PDB0:
+		shift = 9 * (AMDGPU_VM_PDB0 - level) +
+			adev->vm_manager.block_size;
+		break;
+	case AMDGPU_VM_PTB:
+		shift = 0;
+		break;
+	default:
+		dev_err(adev->dev, "the level%d isn't supported.\n", level);
+	}
+
+	return shift;
+}
+
+/**
  * amdgpu_vm_num_entries - return the number of entries in a PD/PT
  *
  * @adev: amdgpu_device pointer
@@ -148,17 +131,18 @@ struct amdgpu_prt_cb {
 static unsigned amdgpu_vm_num_entries(struct amdgpu_device *adev,
 				      unsigned level)
 {
-	if (level == 0)
+	unsigned shift = amdgpu_vm_level_shift(adev,
+					       adev->vm_manager.root_level);
+
+	if (level == adev->vm_manager.root_level)
 		/* For the root directory */
-		return adev->vm_manager.max_pfn >>
-			(adev->vm_manager.block_size *
-			 adev->vm_manager.num_level);
-	else if (level == adev->vm_manager.num_level)
+		return round_up(adev->vm_manager.max_pfn, 1 << shift) >> shift;
+	else if (level != AMDGPU_VM_PTB)
+		/* Everything in between */
+		return 512;
+	else
 		/* For the page tables on the leaves */
 		return AMDGPU_VM_PTE_COUNT(adev);
-	else
-		/* Everything in between */
-		return 1 << adev->vm_manager.block_size;
 }
 
 /**
@@ -288,8 +272,7 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 				  uint64_t saddr, uint64_t eaddr,
 				  unsigned level)
 {
-	unsigned shift = (adev->vm_manager.num_level - level) *
-		adev->vm_manager.block_size;
+	unsigned shift = amdgpu_vm_level_shift(adev, level);
 	unsigned pt_idx, from, to;
 	int r;
 	u64 flags;
@@ -312,9 +295,6 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 	    to >= amdgpu_vm_num_entries(adev, level))
 		return -EINVAL;
 
-	if (to > parent->last_entry_used)
-		parent->last_entry_used = to;
-
 	++level;
 	saddr = saddr & ((1 << shift) - 1);
 	eaddr = eaddr & ((1 << shift) - 1);
@@ -329,7 +309,7 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 
 	if (vm->pte_support_ats) {
 		init_value = AMDGPU_PTE_DEFAULT_ATC;
-		if (level != adev->vm_manager.num_level - 1)
+		if (level != AMDGPU_VM_PTB)
 			init_value |= AMDGPU_PDE_PTE;
 
 	}
@@ -369,10 +349,9 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 			spin_lock(&vm->status_lock);
 			list_add(&entry->base.vm_status, &vm->relocated);
 			spin_unlock(&vm->status_lock);
-			entry->addr = 0;
 		}
 
-		if (level < adev->vm_manager.num_level) {
+		if (level < AMDGPU_VM_PTB) {
 			uint64_t sub_saddr = (pt_idx == from) ? saddr : 0;
 			uint64_t sub_eaddr = (pt_idx == to) ? eaddr :
 				((1 << shift) - 1);
@@ -418,287 +397,8 @@ int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
 	saddr /= AMDGPU_GPU_PAGE_SIZE;
 	eaddr /= AMDGPU_GPU_PAGE_SIZE;
 
-	return amdgpu_vm_alloc_levels(adev, vm, &vm->root, saddr, eaddr, 0);
-}
-
-/**
- * amdgpu_vm_had_gpu_reset - check if reset occured since last use
- *
- * @adev: amdgpu_device pointer
- * @id: VMID structure
- *
- * Check if GPU reset occured since last use of the VMID.
- */
-static bool amdgpu_vm_had_gpu_reset(struct amdgpu_device *adev,
-				    struct amdgpu_vm_id *id)
-{
-	return id->current_gpu_reset_count !=
-		atomic_read(&adev->gpu_reset_counter);
-}
-
-static bool amdgpu_vm_reserved_vmid_ready(struct amdgpu_vm *vm, unsigned vmhub)
-{
-	return !!vm->reserved_vmid[vmhub];
-}
-
-/* idr_mgr->lock must be held */
-static int amdgpu_vm_grab_reserved_vmid_locked(struct amdgpu_vm *vm,
-					       struct amdgpu_ring *ring,
-					       struct amdgpu_sync *sync,
-					       struct dma_fence *fence,
-					       struct amdgpu_job *job)
-{
-	struct amdgpu_device *adev = ring->adev;
-	unsigned vmhub = ring->funcs->vmhub;
-	uint64_t fence_context = adev->fence_context + ring->idx;
-	struct amdgpu_vm_id *id = vm->reserved_vmid[vmhub];
-	struct amdgpu_vm_id_manager *id_mgr = &adev->vm_manager.id_mgr[vmhub];
-	struct dma_fence *updates = sync->last_vm_update;
-	int r = 0;
-	struct dma_fence *flushed, *tmp;
-	bool needs_flush = vm->use_cpu_for_update;
-
-	flushed  = id->flushed_updates;
-	if ((amdgpu_vm_had_gpu_reset(adev, id)) ||
-	    (atomic64_read(&id->owner) != vm->client_id) ||
-	    (job->vm_pd_addr != id->pd_gpu_addr) ||
-	    (updates && (!flushed || updates->context != flushed->context ||
-			dma_fence_is_later(updates, flushed))) ||
-	    (!id->last_flush || (id->last_flush->context != fence_context &&
-				 !dma_fence_is_signaled(id->last_flush)))) {
-		needs_flush = true;
-		/* to prevent one context starved by another context */
-		id->pd_gpu_addr = 0;
-		tmp = amdgpu_sync_peek_fence(&id->active, ring);
-		if (tmp) {
-			r = amdgpu_sync_fence(adev, sync, tmp);
-			return r;
-		}
-	}
-
-	/* Good we can use this VMID. Remember this submission as
-	* user of the VMID.
-	*/
-	r = amdgpu_sync_fence(ring->adev, &id->active, fence);
-	if (r)
-		goto out;
-
-	if (updates && (!flushed || updates->context != flushed->context ||
-			dma_fence_is_later(updates, flushed))) {
-		dma_fence_put(id->flushed_updates);
-		id->flushed_updates = dma_fence_get(updates);
-	}
-	id->pd_gpu_addr = job->vm_pd_addr;
-	atomic64_set(&id->owner, vm->client_id);
-	job->vm_needs_flush = needs_flush;
-	if (needs_flush) {
-		dma_fence_put(id->last_flush);
-		id->last_flush = NULL;
-	}
-	job->vm_id = id - id_mgr->ids;
-	trace_amdgpu_vm_grab_id(vm, ring, job);
-out:
-	return r;
-}
-
-/**
- * amdgpu_vm_grab_id - allocate the next free VMID
- *
- * @vm: vm to allocate id for
- * @ring: ring we want to submit job to
- * @sync: sync object where we add dependencies
- * @fence: fence protecting ID from reuse
- *
- * Allocate an id for the vm, adding fences to the sync obj as necessary.
- */
-int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
-		      struct amdgpu_sync *sync, struct dma_fence *fence,
-		      struct amdgpu_job *job)
-{
-	struct amdgpu_device *adev = ring->adev;
-	unsigned vmhub = ring->funcs->vmhub;
-	struct amdgpu_vm_id_manager *id_mgr = &adev->vm_manager.id_mgr[vmhub];
-	uint64_t fence_context = adev->fence_context + ring->idx;
-	struct dma_fence *updates = sync->last_vm_update;
-	struct amdgpu_vm_id *id, *idle;
-	struct dma_fence **fences;
-	unsigned i;
-	int r = 0;
-
-	mutex_lock(&id_mgr->lock);
-	if (amdgpu_vm_reserved_vmid_ready(vm, vmhub)) {
-		r = amdgpu_vm_grab_reserved_vmid_locked(vm, ring, sync, fence, job);
-		mutex_unlock(&id_mgr->lock);
-		return r;
-	}
-	fences = kmalloc_array(sizeof(void *), id_mgr->num_ids, GFP_KERNEL);
-	if (!fences) {
-		mutex_unlock(&id_mgr->lock);
-		return -ENOMEM;
-	}
-	/* Check if we have an idle VMID */
-	i = 0;
-	list_for_each_entry(idle, &id_mgr->ids_lru, list) {
-		fences[i] = amdgpu_sync_peek_fence(&idle->active, ring);
-		if (!fences[i])
-			break;
-		++i;
-	}
-
-	/* If we can't find a idle VMID to use, wait till one becomes available */
-	if (&idle->list == &id_mgr->ids_lru) {
-		u64 fence_context = adev->vm_manager.fence_context + ring->idx;
-		unsigned seqno = ++adev->vm_manager.seqno[ring->idx];
-		struct dma_fence_array *array;
-		unsigned j;
-
-		for (j = 0; j < i; ++j)
-			dma_fence_get(fences[j]);
-
-		array = dma_fence_array_create(i, fences, fence_context,
-					   seqno, true);
-		if (!array) {
-			for (j = 0; j < i; ++j)
-				dma_fence_put(fences[j]);
-			kfree(fences);
-			r = -ENOMEM;
-			goto error;
-		}
-
-
-		r = amdgpu_sync_fence(ring->adev, sync, &array->base);
-		dma_fence_put(&array->base);
-		if (r)
-			goto error;
-
-		mutex_unlock(&id_mgr->lock);
-		return 0;
-
-	}
-	kfree(fences);
-
-	job->vm_needs_flush = vm->use_cpu_for_update;
-	/* Check if we can use a VMID already assigned to this VM */
-	list_for_each_entry_reverse(id, &id_mgr->ids_lru, list) {
-		struct dma_fence *flushed;
-		bool needs_flush = vm->use_cpu_for_update;
-
-		/* Check all the prerequisites to using this VMID */
-		if (amdgpu_vm_had_gpu_reset(adev, id))
-			continue;
-
-		if (atomic64_read(&id->owner) != vm->client_id)
-			continue;
-
-		if (job->vm_pd_addr != id->pd_gpu_addr)
-			continue;
-
-		if (!id->last_flush ||
-		    (id->last_flush->context != fence_context &&
-		     !dma_fence_is_signaled(id->last_flush)))
-			needs_flush = true;
-
-		flushed  = id->flushed_updates;
-		if (updates && (!flushed || dma_fence_is_later(updates, flushed)))
-			needs_flush = true;
-
-		/* Concurrent flushes are only possible starting with Vega10 */
-		if (adev->asic_type < CHIP_VEGA10 && needs_flush)
-			continue;
-
-		/* Good we can use this VMID. Remember this submission as
-		 * user of the VMID.
-		 */
-		r = amdgpu_sync_fence(ring->adev, &id->active, fence);
-		if (r)
-			goto error;
-
-		if (updates && (!flushed || dma_fence_is_later(updates, flushed))) {
-			dma_fence_put(id->flushed_updates);
-			id->flushed_updates = dma_fence_get(updates);
-		}
-
-		if (needs_flush)
-			goto needs_flush;
-		else
-			goto no_flush_needed;
-
-	};
-
-	/* Still no ID to use? Then use the idle one found earlier */
-	id = idle;
-
-	/* Remember this submission as user of the VMID */
-	r = amdgpu_sync_fence(ring->adev, &id->active, fence);
-	if (r)
-		goto error;
-
-	id->pd_gpu_addr = job->vm_pd_addr;
-	dma_fence_put(id->flushed_updates);
-	id->flushed_updates = dma_fence_get(updates);
-	atomic64_set(&id->owner, vm->client_id);
-
-needs_flush:
-	job->vm_needs_flush = true;
-	dma_fence_put(id->last_flush);
-	id->last_flush = NULL;
-
-no_flush_needed:
-	list_move_tail(&id->list, &id_mgr->ids_lru);
-
-	job->vm_id = id - id_mgr->ids;
-	trace_amdgpu_vm_grab_id(vm, ring, job);
-
-error:
-	mutex_unlock(&id_mgr->lock);
-	return r;
-}
-
-static void amdgpu_vm_free_reserved_vmid(struct amdgpu_device *adev,
-					  struct amdgpu_vm *vm,
-					  unsigned vmhub)
-{
-	struct amdgpu_vm_id_manager *id_mgr = &adev->vm_manager.id_mgr[vmhub];
-
-	mutex_lock(&id_mgr->lock);
-	if (vm->reserved_vmid[vmhub]) {
-		list_add(&vm->reserved_vmid[vmhub]->list,
-			&id_mgr->ids_lru);
-		vm->reserved_vmid[vmhub] = NULL;
-		atomic_dec(&id_mgr->reserved_vmid_num);
-	}
-	mutex_unlock(&id_mgr->lock);
-}
-
-static int amdgpu_vm_alloc_reserved_vmid(struct amdgpu_device *adev,
-					 struct amdgpu_vm *vm,
-					 unsigned vmhub)
-{
-	struct amdgpu_vm_id_manager *id_mgr;
-	struct amdgpu_vm_id *idle;
-	int r = 0;
-
-	id_mgr = &adev->vm_manager.id_mgr[vmhub];
-	mutex_lock(&id_mgr->lock);
-	if (vm->reserved_vmid[vmhub])
-		goto unlock;
-	if (atomic_inc_return(&id_mgr->reserved_vmid_num) >
-	    AMDGPU_VM_MAX_RESERVED_VMID) {
-		DRM_ERROR("Over limitation of reserved vmid\n");
-		atomic_dec(&id_mgr->reserved_vmid_num);
-		r = -EINVAL;
-		goto unlock;
-	}
-	/* Select the first entry VMID */
-	idle = list_first_entry(&id_mgr->ids_lru, struct amdgpu_vm_id, list);
-	list_del_init(&idle->list);
-	vm->reserved_vmid[vmhub] = idle;
-	mutex_unlock(&id_mgr->lock);
-
-	return 0;
-unlock:
-	mutex_unlock(&id_mgr->lock);
-	return r;
+	return amdgpu_vm_alloc_levels(adev, vm, &vm->root, saddr, eaddr,
+				      adev->vm_manager.root_level);
 }
 
 /**
@@ -715,7 +415,7 @@ void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev)
 
 	has_compute_vm_bug = false;
 
-	ip_block = amdgpu_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX);
+	ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX);
 	if (ip_block) {
 		/* Compute has a VM bug for GFX version < 7.
 		   Compute has a VM bug for GFX 8 MEC firmware version < 673.*/
@@ -741,14 +441,14 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 {
 	struct amdgpu_device *adev = ring->adev;
 	unsigned vmhub = ring->funcs->vmhub;
-	struct amdgpu_vm_id_manager *id_mgr = &adev->vm_manager.id_mgr[vmhub];
-	struct amdgpu_vm_id *id;
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	struct amdgpu_vmid *id;
 	bool gds_switch_needed;
 	bool vm_flush_needed = job->vm_needs_flush || ring->has_compute_vm_bug;
 
-	if (job->vm_id == 0)
+	if (job->vmid == 0)
 		return false;
-	id = &id_mgr->ids[job->vm_id];
+	id = &id_mgr->ids[job->vmid];
 	gds_switch_needed = ring->funcs->emit_gds_switch && (
 		id->gds_base != job->gds_base ||
 		id->gds_size != job->gds_size ||
@@ -757,7 +457,7 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 		id->oa_base != job->oa_base ||
 		id->oa_size != job->oa_size);
 
-	if (amdgpu_vm_had_gpu_reset(adev, id))
+	if (amdgpu_vmid_had_gpu_reset(adev, id))
 		return true;
 
 	return vm_flush_needed || gds_switch_needed;
@@ -772,7 +472,7 @@ static bool amdgpu_vm_is_large_bar(struct amdgpu_device *adev)
  * amdgpu_vm_flush - hardware flush the vm
  *
  * @ring: ring to use for flush
- * @vm_id: vmid number to use
+ * @vmid: vmid number to use
  * @pd_addr: address of the page directory
  *
  * Emit a VM flush when it is necessary.
@@ -781,8 +481,8 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
 {
 	struct amdgpu_device *adev = ring->adev;
 	unsigned vmhub = ring->funcs->vmhub;
-	struct amdgpu_vm_id_manager *id_mgr = &adev->vm_manager.id_mgr[vmhub];
-	struct amdgpu_vm_id *id = &id_mgr->ids[job->vm_id];
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	struct amdgpu_vmid *id = &id_mgr->ids[job->vmid];
 	bool gds_switch_needed = ring->funcs->emit_gds_switch && (
 		id->gds_base != job->gds_base ||
 		id->gds_size != job->gds_size ||
@@ -794,7 +494,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
 	unsigned patch_offset = 0;
 	int r;
 
-	if (amdgpu_vm_had_gpu_reset(adev, id)) {
+	if (amdgpu_vmid_had_gpu_reset(adev, id)) {
 		gds_switch_needed = true;
 		vm_flush_needed = true;
 	}
@@ -811,8 +511,8 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
 	if (ring->funcs->emit_vm_flush && vm_flush_needed) {
 		struct dma_fence *fence;
 
-		trace_amdgpu_vm_flush(ring, job->vm_id, job->vm_pd_addr);
-		amdgpu_ring_emit_vm_flush(ring, job->vm_id, job->vm_pd_addr);
+		trace_amdgpu_vm_flush(ring, job->vmid, job->vm_pd_addr);
+		amdgpu_ring_emit_vm_flush(ring, job->vmid, job->vm_pd_addr);
 
 		r = amdgpu_fence_emit(ring, &fence);
 		if (r)
@@ -832,7 +532,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
 		id->gws_size = job->gws_size;
 		id->oa_base = job->oa_base;
 		id->oa_size = job->oa_size;
-		amdgpu_ring_emit_gds_switch(ring, job->vm_id, job->gds_base,
+		amdgpu_ring_emit_gds_switch(ring, job->vmid, job->gds_base,
 					    job->gds_size, job->gws_base,
 					    job->gws_size, job->oa_base,
 					    job->oa_size);
@@ -850,49 +550,6 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
 }
 
 /**
- * amdgpu_vm_reset_id - reset VMID to zero
- *
- * @adev: amdgpu device structure
- * @vm_id: vmid number to use
- *
- * Reset saved GDW, GWS and OA to force switch on next flush.
- */
-void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vmhub,
-			unsigned vmid)
-{
-	struct amdgpu_vm_id_manager *id_mgr = &adev->vm_manager.id_mgr[vmhub];
-	struct amdgpu_vm_id *id = &id_mgr->ids[vmid];
-
-	atomic64_set(&id->owner, 0);
-	id->gds_base = 0;
-	id->gds_size = 0;
-	id->gws_base = 0;
-	id->gws_size = 0;
-	id->oa_base = 0;
-	id->oa_size = 0;
-}
-
-/**
- * amdgpu_vm_reset_all_id - reset VMID to zero
- *
- * @adev: amdgpu device structure
- *
- * Reset VMID to force flush on next use
- */
-void amdgpu_vm_reset_all_ids(struct amdgpu_device *adev)
-{
-	unsigned i, j;
-
-	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
-		struct amdgpu_vm_id_manager *id_mgr =
-			&adev->vm_manager.id_mgr[i];
-
-		for (j = 1; j < id_mgr->num_ids; ++j)
-			amdgpu_vm_reset_id(adev, i, j);
-	}
-}
-
-/**
  * amdgpu_vm_bo_find - find the bo_va for a specific vm & bo
  *
  * @vm: requested vm
@@ -1043,162 +700,52 @@ static int amdgpu_vm_wait_pd(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 }
 
 /*
- * amdgpu_vm_update_level - update a single level in the hierarchy
+ * amdgpu_vm_update_pde - update a single level in the hierarchy
  *
- * @adev: amdgpu_device pointer
+ * @param: parameters for the update
  * @vm: requested vm
  * @parent: parent directory
+ * @entry: entry to update
  *
- * Makes sure all entries in @parent are up to date.
- * Returns 0 for success, error for failure.
+ * Makes sure the requested entry in parent is up to date.
  */
-static int amdgpu_vm_update_level(struct amdgpu_device *adev,
-				  struct amdgpu_vm *vm,
-				  struct amdgpu_vm_pt *parent)
+static void amdgpu_vm_update_pde(struct amdgpu_pte_update_params *params,
+				 struct amdgpu_vm *vm,
+				 struct amdgpu_vm_pt *parent,
+				 struct amdgpu_vm_pt *entry)
 {
-	struct amdgpu_bo *shadow;
-	struct amdgpu_ring *ring = NULL;
+	struct amdgpu_bo *bo = entry->base.bo, *shadow = NULL, *pbo;
 	uint64_t pd_addr, shadow_addr = 0;
-	uint64_t last_pde = ~0, last_pt = ~0, last_shadow = ~0;
-	unsigned count = 0, pt_idx, ndw = 0;
-	struct amdgpu_job *job;
-	struct amdgpu_pte_update_params params;
-	struct dma_fence *fence = NULL;
-	uint32_t incr;
-
-	int r;
-
-	if (!parent->entries)
-		return 0;
+	uint64_t pde, pt, flags;
+	unsigned level;
 
-	memset(&params, 0, sizeof(params));
-	params.adev = adev;
-	shadow = parent->base.bo->shadow;
+	/* Don't update huge pages here */
+	if (entry->huge)
+		return;
 
 	if (vm->use_cpu_for_update) {
 		pd_addr = (unsigned long)amdgpu_bo_kptr(parent->base.bo);
-		r = amdgpu_vm_wait_pd(adev, vm, AMDGPU_FENCE_OWNER_VM);
-		if (unlikely(r))
-			return r;
-
-		params.func = amdgpu_vm_cpu_set_ptes;
 	} else {
-		ring = container_of(vm->entity.sched, struct amdgpu_ring,
-				    sched);
-
-		/* padding, etc. */
-		ndw = 64;
-
-		/* assume the worst case */
-		ndw += parent->last_entry_used * 6;
-
 		pd_addr = amdgpu_bo_gpu_offset(parent->base.bo);
-
-		if (shadow) {
+		shadow = parent->base.bo->shadow;
+		if (shadow)
 			shadow_addr = amdgpu_bo_gpu_offset(shadow);
-			ndw *= 2;
-		} else {
-			shadow_addr = 0;
-		}
-
-		r = amdgpu_job_alloc_with_ib(adev, ndw * 4, &job);
-		if (r)
-			return r;
-
-		params.ib = &job->ibs[0];
-		params.func = amdgpu_vm_do_set_ptes;
-	}
-
-
-	/* walk over the address space and update the directory */
-	for (pt_idx = 0; pt_idx <= parent->last_entry_used; ++pt_idx) {
-		struct amdgpu_vm_pt *entry = &parent->entries[pt_idx];
-		struct amdgpu_bo *bo = entry->base.bo;
-		uint64_t pde, pt;
-
-		if (bo == NULL)
-			continue;
-
-		spin_lock(&vm->status_lock);
-		list_del_init(&entry->base.vm_status);
-		spin_unlock(&vm->status_lock);
-
-		pt = amdgpu_bo_gpu_offset(bo);
-		pt = amdgpu_gart_get_vm_pde(adev, pt);
-		/* Don't update huge pages here */
-		if ((parent->entries[pt_idx].addr & AMDGPU_PDE_PTE) ||
-		    parent->entries[pt_idx].addr == (pt | AMDGPU_PTE_VALID))
-			continue;
-
-		parent->entries[pt_idx].addr = pt | AMDGPU_PTE_VALID;
-
-		pde = pd_addr + pt_idx * 8;
-		incr = amdgpu_bo_size(bo);
-		if (((last_pde + 8 * count) != pde) ||
-		    ((last_pt + incr * count) != pt) ||
-		    (count == AMDGPU_VM_MAX_UPDATE_SIZE)) {
-
-			if (count) {
-				if (shadow)
-					params.func(&params,
-						    last_shadow,
-						    last_pt, count,
-						    incr,
-						    AMDGPU_PTE_VALID);
-
-				params.func(&params, last_pde,
-					    last_pt, count, incr,
-					    AMDGPU_PTE_VALID);
-			}
-
-			count = 1;
-			last_pde = pde;
-			last_shadow = shadow_addr + pt_idx * 8;
-			last_pt = pt;
-		} else {
-			++count;
-		}
-	}
-
-	if (count) {
-		if (vm->root.base.bo->shadow)
-			params.func(&params, last_shadow, last_pt,
-				    count, incr, AMDGPU_PTE_VALID);
-
-		params.func(&params, last_pde, last_pt,
-			    count, incr, AMDGPU_PTE_VALID);
 	}
 
-	if (!vm->use_cpu_for_update) {
-		if (params.ib->length_dw == 0) {
-			amdgpu_job_free(job);
-		} else {
-			amdgpu_ring_pad_ib(ring, params.ib);
-			amdgpu_sync_resv(adev, &job->sync,
-					 parent->base.bo->tbo.resv,
-					 AMDGPU_FENCE_OWNER_VM, false);
-			if (shadow)
-				amdgpu_sync_resv(adev, &job->sync,
-						 shadow->tbo.resv,
-						 AMDGPU_FENCE_OWNER_VM, false);
-
-			WARN_ON(params.ib->length_dw > ndw);
-			r = amdgpu_job_submit(job, ring, &vm->entity,
-					AMDGPU_FENCE_OWNER_VM, &fence);
-			if (r)
-				goto error_free;
+	for (level = 0, pbo = parent->base.bo->parent; pbo; ++level)
+		pbo = pbo->parent;
 
-			amdgpu_bo_fence(parent->base.bo, fence, true);
-			dma_fence_put(vm->last_update);
-			vm->last_update = fence;
-		}
+	level += params->adev->vm_manager.root_level;
+	pt = amdgpu_bo_gpu_offset(bo);
+	flags = AMDGPU_PTE_VALID;
+	amdgpu_gart_get_vm_pde(params->adev, level, &pt, &flags);
+	if (shadow) {
+		pde = shadow_addr + (entry - parent->entries) * 8;
+		params->func(params, pde, pt, 1, 0, flags);
 	}
 
-	return 0;
-
-error_free:
-	amdgpu_job_free(job);
-	return r;
+	pde = pd_addr + (entry - parent->entries) * 8;
+	params->func(params, pde, pt, 1, 0, flags);
 }
 
 /*
@@ -1208,27 +755,29 @@ error_free:
  *
  * Mark all PD level as invalid after an error.
  */
-static void amdgpu_vm_invalidate_level(struct amdgpu_vm *vm,
-				       struct amdgpu_vm_pt *parent)
+static void amdgpu_vm_invalidate_level(struct amdgpu_device *adev,
+				       struct amdgpu_vm *vm,
+				       struct amdgpu_vm_pt *parent,
+				       unsigned level)
 {
-	unsigned pt_idx;
+	unsigned pt_idx, num_entries;
 
 	/*
 	 * Recurse into the subdirectories. This recursion is harmless because
 	 * we only have a maximum of 5 layers.
 	 */
-	for (pt_idx = 0; pt_idx <= parent->last_entry_used; ++pt_idx) {
+	num_entries = amdgpu_vm_num_entries(adev, level);
+	for (pt_idx = 0; pt_idx < num_entries; ++pt_idx) {
 		struct amdgpu_vm_pt *entry = &parent->entries[pt_idx];
 
 		if (!entry->base.bo)
 			continue;
 
-		entry->addr = ~0ULL;
 		spin_lock(&vm->status_lock);
 		if (list_empty(&entry->base.vm_status))
 			list_add(&entry->base.vm_status, &vm->relocated);
 		spin_unlock(&vm->status_lock);
-		amdgpu_vm_invalidate_level(vm, entry);
+		amdgpu_vm_invalidate_level(adev, vm, entry, level + 1);
 	}
 }
 
@@ -1244,38 +793,63 @@ static void amdgpu_vm_invalidate_level(struct amdgpu_vm *vm,
 int amdgpu_vm_update_directories(struct amdgpu_device *adev,
 				 struct amdgpu_vm *vm)
 {
+	struct amdgpu_pte_update_params params;
+	struct amdgpu_job *job;
+	unsigned ndw = 0;
 	int r = 0;
 
+	if (list_empty(&vm->relocated))
+		return 0;
+
+restart:
+	memset(&params, 0, sizeof(params));
+	params.adev = adev;
+
+	if (vm->use_cpu_for_update) {
+		r = amdgpu_vm_wait_pd(adev, vm, AMDGPU_FENCE_OWNER_VM);
+		if (unlikely(r))
+			return r;
+
+		params.func = amdgpu_vm_cpu_set_ptes;
+	} else {
+		ndw = 512 * 8;
+		r = amdgpu_job_alloc_with_ib(adev, ndw * 4, &job);
+		if (r)
+			return r;
+
+		params.ib = &job->ibs[0];
+		params.func = amdgpu_vm_do_set_ptes;
+	}
+
 	spin_lock(&vm->status_lock);
 	while (!list_empty(&vm->relocated)) {
-		struct amdgpu_vm_bo_base *bo_base;
+		struct amdgpu_vm_bo_base *bo_base, *parent;
+		struct amdgpu_vm_pt *pt, *entry;
 		struct amdgpu_bo *bo;
 
 		bo_base = list_first_entry(&vm->relocated,
 					   struct amdgpu_vm_bo_base,
 					   vm_status);
+		list_del_init(&bo_base->vm_status);
 		spin_unlock(&vm->status_lock);
 
 		bo = bo_base->bo->parent;
-		if (bo) {
-			struct amdgpu_vm_bo_base *parent;
-			struct amdgpu_vm_pt *pt;
-
-			parent = list_first_entry(&bo->va,
-						  struct amdgpu_vm_bo_base,
-						  bo_list);
-			pt = container_of(parent, struct amdgpu_vm_pt, base);
-
-			r = amdgpu_vm_update_level(adev, vm, pt);
-			if (r) {
-				amdgpu_vm_invalidate_level(vm, &vm->root);
-				return r;
-			}
-			spin_lock(&vm->status_lock);
-		} else {
+		if (!bo) {
 			spin_lock(&vm->status_lock);
-			list_del_init(&bo_base->vm_status);
+			continue;
 		}
+
+		parent = list_first_entry(&bo->va, struct amdgpu_vm_bo_base,
+					  bo_list);
+		pt = container_of(parent, struct amdgpu_vm_pt, base);
+		entry = container_of(bo_base, struct amdgpu_vm_pt, base);
+
+		amdgpu_vm_update_pde(&params, vm, pt, entry);
+
+		spin_lock(&vm->status_lock);
+		if (!vm->use_cpu_for_update &&
+		    (ndw - params.ib->length_dw) < 32)
+			break;
 	}
 	spin_unlock(&vm->status_lock);
 
@@ -1283,8 +857,44 @@ int amdgpu_vm_update_directories(struct amdgpu_device *adev,
 		/* Flush HDP */
 		mb();
 		amdgpu_gart_flush_gpu_tlb(adev, 0);
+	} else if (params.ib->length_dw == 0) {
+		amdgpu_job_free(job);
+	} else {
+		struct amdgpu_bo *root = vm->root.base.bo;
+		struct amdgpu_ring *ring;
+		struct dma_fence *fence;
+
+		ring = container_of(vm->entity.sched, struct amdgpu_ring,
+				    sched);
+
+		amdgpu_ring_pad_ib(ring, params.ib);
+		amdgpu_sync_resv(adev, &job->sync, root->tbo.resv,
+				 AMDGPU_FENCE_OWNER_VM, false);
+		if (root->shadow)
+			amdgpu_sync_resv(adev, &job->sync,
+					 root->shadow->tbo.resv,
+					 AMDGPU_FENCE_OWNER_VM, false);
+
+		WARN_ON(params.ib->length_dw > ndw);
+		r = amdgpu_job_submit(job, ring, &vm->entity,
+				      AMDGPU_FENCE_OWNER_VM, &fence);
+		if (r)
+			goto error;
+
+		amdgpu_bo_fence(root, fence, true);
+		dma_fence_put(vm->last_update);
+		vm->last_update = fence;
 	}
 
+	if (!list_empty(&vm->relocated))
+		goto restart;
+
+	return 0;
+
+error:
+	amdgpu_vm_invalidate_level(adev, vm, &vm->root,
+				   adev->vm_manager.root_level);
+	amdgpu_job_free(job);
 	return r;
 }
 
@@ -1302,18 +912,19 @@ void amdgpu_vm_get_entry(struct amdgpu_pte_update_params *p, uint64_t addr,
 			 struct amdgpu_vm_pt **entry,
 			 struct amdgpu_vm_pt **parent)
 {
-	unsigned idx, level = p->adev->vm_manager.num_level;
+	unsigned level = p->adev->vm_manager.root_level;
 
 	*parent = NULL;
 	*entry = &p->vm->root;
 	while ((*entry)->entries) {
-		idx = addr >> (p->adev->vm_manager.block_size * level--);
-		idx %= amdgpu_bo_size((*entry)->base.bo) / 8;
+		unsigned shift = amdgpu_vm_level_shift(p->adev, level++);
+
 		*parent = *entry;
-		*entry = &(*entry)->entries[idx];
+		*entry = &(*entry)->entries[addr >> shift];
+		addr &= (1ULL << shift) - 1;
 	}
 
-	if (level)
+	if (level != AMDGPU_VM_PTB)
 		*entry = NULL;
 }
 
@@ -1335,56 +946,42 @@ static void amdgpu_vm_handle_huge_pages(struct amdgpu_pte_update_params *p,
 					unsigned nptes, uint64_t dst,
 					uint64_t flags)
 {
-	bool use_cpu_update = (p->func == amdgpu_vm_cpu_set_ptes);
 	uint64_t pd_addr, pde;
 
 	/* In the case of a mixed PT the PDE must point to it*/
-	if (p->adev->asic_type < CHIP_VEGA10 ||
-	    nptes != AMDGPU_VM_PTE_COUNT(p->adev) ||
-	    p->src ||
-	    !(flags & AMDGPU_PTE_VALID)) {
-
-		dst = amdgpu_bo_gpu_offset(entry->base.bo);
-		dst = amdgpu_gart_get_vm_pde(p->adev, dst);
-		flags = AMDGPU_PTE_VALID;
-	} else {
+	if (p->adev->asic_type >= CHIP_VEGA10 && !p->src &&
+	    nptes == AMDGPU_VM_PTE_COUNT(p->adev)) {
 		/* Set the huge page flag to stop scanning at this PDE */
 		flags |= AMDGPU_PDE_PTE;
 	}
 
-	if (entry->addr == (dst | flags))
+	if (!(flags & AMDGPU_PDE_PTE)) {
+		if (entry->huge) {
+			/* Add the entry to the relocated list to update it. */
+			entry->huge = false;
+			spin_lock(&p->vm->status_lock);
+			list_move(&entry->base.vm_status, &p->vm->relocated);
+			spin_unlock(&p->vm->status_lock);
+		}
 		return;
+	}
 
-	entry->addr = (dst | flags);
-
-	if (use_cpu_update) {
-		/* In case a huge page is replaced with a system
-		 * memory mapping, p->pages_addr != NULL and
-		 * amdgpu_vm_cpu_set_ptes would try to translate dst
-		 * through amdgpu_vm_map_gart. But dst is already a
-		 * GPU address (of the page table). Disable
-		 * amdgpu_vm_map_gart temporarily.
-		 */
-		dma_addr_t *tmp;
-
-		tmp = p->pages_addr;
-		p->pages_addr = NULL;
+	entry->huge = true;
+	amdgpu_gart_get_vm_pde(p->adev, AMDGPU_VM_PDB0,
+			       &dst, &flags);
 
+	if (p->func == amdgpu_vm_cpu_set_ptes) {
 		pd_addr = (unsigned long)amdgpu_bo_kptr(parent->base.bo);
-		pde = pd_addr + (entry - parent->entries) * 8;
-		amdgpu_vm_cpu_set_ptes(p, pde, dst, 1, 0, flags);
-
-		p->pages_addr = tmp;
 	} else {
 		if (parent->base.bo->shadow) {
 			pd_addr = amdgpu_bo_gpu_offset(parent->base.bo->shadow);
 			pde = pd_addr + (entry - parent->entries) * 8;
-			amdgpu_vm_do_set_ptes(p, pde, dst, 1, 0, flags);
+			p->func(p, pde, dst, 1, 0, flags);
 		}
 		pd_addr = amdgpu_bo_gpu_offset(parent->base.bo);
-		pde = pd_addr + (entry - parent->entries) * 8;
-		amdgpu_vm_do_set_ptes(p, pde, dst, 1, 0, flags);
 	}
+	pde = pd_addr + (entry - parent->entries) * 8;
+	p->func(p, pde, dst, 1, 0, flags);
 }
 
 /**
@@ -1429,7 +1026,7 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 		amdgpu_vm_handle_huge_pages(params, entry, parent,
 					    nptes, dst, flags);
 		/* We don't need to update PTEs for huge pages */
-		if (entry->addr & AMDGPU_PDE_PTE)
+		if (entry->huge)
 			continue;
 
 		pt = entry->base.bo;
@@ -1588,14 +1185,14 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
          *
          * The second command is for the shadow pagetables.
 	 */
-	ncmds = ((nptes >> min(adev->vm_manager.block_size, 11u)) + 1) * 2;
+	if (vm->root.base.bo->shadow)
+		ncmds = ((nptes >> min(adev->vm_manager.block_size, 11u)) + 1) * 2;
+	else
+		ncmds = ((nptes >> min(adev->vm_manager.block_size, 11u)) + 1);
 
 	/* padding, etc. */
 	ndw = 64;
 
-	/* one PDE write for each huge page */
-	ndw += ((nptes >> adev->vm_manager.block_size) + 1) * 6;
-
 	if (pages_addr) {
 		/* copy commands needed */
 		ndw += ncmds * adev->vm_manager.vm_pte_funcs->copy_pte_num_dw;
@@ -1639,7 +1236,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 		addr = 0;
 	}
 
-	r = amdgpu_sync_fence(adev, &job->sync, exclusive);
+	r = amdgpu_sync_fence(adev, &job->sync, exclusive, false);
 	if (r)
 		goto error_free;
 
@@ -1670,7 +1267,6 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 
 error_free:
 	amdgpu_job_free(job);
-	amdgpu_vm_invalidate_level(vm, &vm->root);
 	return r;
 }
 
@@ -2081,18 +1677,31 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 	spin_lock(&vm->status_lock);
 	while (!list_empty(&vm->moved)) {
 		struct amdgpu_bo_va *bo_va;
+		struct reservation_object *resv;
 
 		bo_va = list_first_entry(&vm->moved,
 			struct amdgpu_bo_va, base.vm_status);
 		spin_unlock(&vm->status_lock);
 
+		resv = bo_va->base.bo->tbo.resv;
+
 		/* Per VM BOs never need to bo cleared in the page tables */
-		clear = bo_va->base.bo->tbo.resv != vm->root.base.bo->tbo.resv;
+		if (resv == vm->root.base.bo->tbo.resv)
+			clear = false;
+		/* Try to reserve the BO to avoid clearing its ptes */
+		else if (!amdgpu_vm_debug && reservation_object_trylock(resv))
+			clear = false;
+		/* Somebody else is using the BO right now */
+		else
+			clear = true;
 
 		r = amdgpu_vm_bo_update(adev, bo_va, clear);
 		if (r)
 			return r;
 
+		if (!clear && resv != vm->root.base.bo->tbo.resv)
+			reservation_object_unlock(resv);
+
 		spin_lock(&vm->status_lock);
 	}
 	spin_unlock(&vm->status_lock);
@@ -2132,8 +1741,26 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
 	INIT_LIST_HEAD(&bo_va->valids);
 	INIT_LIST_HEAD(&bo_va->invalids);
 
-	if (bo)
-		list_add_tail(&bo_va->base.bo_list, &bo->va);
+	if (!bo)
+		return bo_va;
+
+	list_add_tail(&bo_va->base.bo_list, &bo->va);
+
+	if (bo->tbo.resv != vm->root.base.bo->tbo.resv)
+		return bo_va;
+
+	if (bo->preferred_domains &
+	    amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type))
+		return bo_va;
+
+	/*
+	 * We checked all the prerequisites, but it looks like this per VM BO
+	 * is currently evicted. add the BO to the evicted list to make sure it
+	 * is validated on next VM use to avoid fault.
+	 * */
+	spin_lock(&vm->status_lock);
+	list_move_tail(&bo_va->base.vm_status, &vm->evicted);
+	spin_unlock(&vm->status_lock);
 
 	return bo_va;
 }
@@ -2556,47 +2183,69 @@ static uint32_t amdgpu_vm_get_block_size(uint64_t vm_size)
 }
 
 /**
- * amdgpu_vm_set_fragment_size - adjust fragment size in PTE
- *
- * @adev: amdgpu_device pointer
- * @fragment_size_default: the default fragment size if it's set auto
- */
-void amdgpu_vm_set_fragment_size(struct amdgpu_device *adev,
-				 uint32_t fragment_size_default)
-{
-	if (amdgpu_vm_fragment_size == -1)
-		adev->vm_manager.fragment_size = fragment_size_default;
-	else
-		adev->vm_manager.fragment_size = amdgpu_vm_fragment_size;
-}
-
-/**
  * amdgpu_vm_adjust_size - adjust vm size, block size and fragment size
  *
  * @adev: amdgpu_device pointer
  * @vm_size: the default vm size if it's set auto
  */
-void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint64_t vm_size,
-			   uint32_t fragment_size_default)
+void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size,
+			   uint32_t fragment_size_default, unsigned max_level,
+			   unsigned max_bits)
 {
-	/* adjust vm size firstly */
-	if (amdgpu_vm_size == -1)
-		adev->vm_manager.vm_size = vm_size;
-	else
-		adev->vm_manager.vm_size = amdgpu_vm_size;
+	uint64_t tmp;
+
+	/* adjust vm size first */
+	if (amdgpu_vm_size != -1) {
+		unsigned max_size = 1 << (max_bits - 30);
 
-	/* block size depends on vm size */
-	if (amdgpu_vm_block_size == -1)
+		vm_size = amdgpu_vm_size;
+		if (vm_size > max_size) {
+			dev_warn(adev->dev, "VM size (%d) too large, max is %u GB\n",
+				 amdgpu_vm_size, max_size);
+			vm_size = max_size;
+		}
+	}
+
+	adev->vm_manager.max_pfn = (uint64_t)vm_size << 18;
+
+	tmp = roundup_pow_of_two(adev->vm_manager.max_pfn);
+	if (amdgpu_vm_block_size != -1)
+		tmp >>= amdgpu_vm_block_size - 9;
+	tmp = DIV_ROUND_UP(fls64(tmp) - 1, 9) - 1;
+	adev->vm_manager.num_level = min(max_level, (unsigned)tmp);
+	switch (adev->vm_manager.num_level) {
+	case 3:
+		adev->vm_manager.root_level = AMDGPU_VM_PDB2;
+		break;
+	case 2:
+		adev->vm_manager.root_level = AMDGPU_VM_PDB1;
+		break;
+	case 1:
+		adev->vm_manager.root_level = AMDGPU_VM_PDB0;
+		break;
+	default:
+		dev_err(adev->dev, "VMPT only supports 2~4+1 levels\n");
+	}
+	/* block size depends on vm size and hw setup*/
+	if (amdgpu_vm_block_size != -1)
 		adev->vm_manager.block_size =
-			amdgpu_vm_get_block_size(adev->vm_manager.vm_size);
+			min((unsigned)amdgpu_vm_block_size, max_bits
+			    - AMDGPU_GPU_PAGE_SHIFT
+			    - 9 * adev->vm_manager.num_level);
+	else if (adev->vm_manager.num_level > 1)
+		adev->vm_manager.block_size = 9;
 	else
-		adev->vm_manager.block_size = amdgpu_vm_block_size;
+		adev->vm_manager.block_size = amdgpu_vm_get_block_size(tmp);
 
-	amdgpu_vm_set_fragment_size(adev, fragment_size_default);
+	if (amdgpu_vm_fragment_size == -1)
+		adev->vm_manager.fragment_size = fragment_size_default;
+	else
+		adev->vm_manager.fragment_size = amdgpu_vm_fragment_size;
 
-	DRM_INFO("vm size is %llu GB, block size is %u-bit, fragment size is %u-bit\n",
-		adev->vm_manager.vm_size, adev->vm_manager.block_size,
-		adev->vm_manager.fragment_size);
+	DRM_INFO("vm size is %u GB, %u levels, block size is %u-bit, fragment size is %u-bit\n",
+		 vm_size, adev->vm_manager.num_level + 1,
+		 adev->vm_manager.block_size,
+		 adev->vm_manager.fragment_size);
 }
 
 /**
@@ -2615,13 +2264,12 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		AMDGPU_VM_PTE_COUNT(adev) * 8);
 	unsigned ring_instance;
 	struct amdgpu_ring *ring;
-	struct amd_sched_rq *rq;
+	struct drm_sched_rq *rq;
 	int r, i;
 	u64 flags;
 	uint64_t init_pde_value = 0;
 
 	vm->va = RB_ROOT_CACHED;
-	vm->client_id = atomic64_inc_return(&adev->vm_manager.client_counter);
 	for (i = 0; i < AMDGPU_MAX_VMHUBS; i++)
 		vm->reserved_vmid[i] = NULL;
 	spin_lock_init(&vm->status_lock);
@@ -2635,9 +2283,9 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	ring_instance = atomic_inc_return(&adev->vm_manager.vm_pte_next_ring);
 	ring_instance %= adev->vm_manager.vm_pte_num_rings;
 	ring = adev->vm_manager.vm_pte_rings[ring_instance];
-	rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_KERNEL];
-	r = amd_sched_entity_init(&ring->sched, &vm->entity,
-				  rq, amdgpu_sched_jobs);
+	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+	r = drm_sched_entity_init(&ring->sched, &vm->entity,
+				  rq, amdgpu_sched_jobs, NULL);
 	if (r)
 		return r;
 
@@ -2670,7 +2318,9 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		flags |= (AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
 				AMDGPU_GEM_CREATE_SHADOW);
 
-	r = amdgpu_bo_create(adev, amdgpu_vm_bo_size(adev, 0), align, true,
+	r = amdgpu_bo_create(adev,
+			     amdgpu_vm_bo_size(adev, adev->vm_manager.root_level),
+			     align, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     flags,
 			     NULL, NULL, init_pde_value, &vm->root.base.bo);
@@ -2716,7 +2366,7 @@ error_free_root:
 	vm->root.base.bo = NULL;
 
 error_free_sched_entity:
-	amd_sched_entity_fini(&ring->sched, &vm->entity);
+	drm_sched_entity_fini(&ring->sched, &vm->entity);
 
 	return r;
 }
@@ -2724,26 +2374,31 @@ error_free_sched_entity:
 /**
  * amdgpu_vm_free_levels - free PD/PT levels
  *
- * @level: PD/PT starting level to free
+ * @adev: amdgpu device structure
+ * @parent: PD/PT starting level to free
+ * @level: level of parent structure
  *
  * Free the page directory or page table level and all sub levels.
  */
-static void amdgpu_vm_free_levels(struct amdgpu_vm_pt *level)
+static void amdgpu_vm_free_levels(struct amdgpu_device *adev,
+				  struct amdgpu_vm_pt *parent,
+				  unsigned level)
 {
-	unsigned i;
+	unsigned i, num_entries = amdgpu_vm_num_entries(adev, level);
 
-	if (level->base.bo) {
-		list_del(&level->base.bo_list);
-		list_del(&level->base.vm_status);
-		amdgpu_bo_unref(&level->base.bo->shadow);
-		amdgpu_bo_unref(&level->base.bo);
+	if (parent->base.bo) {
+		list_del(&parent->base.bo_list);
+		list_del(&parent->base.vm_status);
+		amdgpu_bo_unref(&parent->base.bo->shadow);
+		amdgpu_bo_unref(&parent->base.bo);
 	}
 
-	if (level->entries)
-		for (i = 0; i <= level->last_entry_used; i++)
-			amdgpu_vm_free_levels(&level->entries[i]);
+	if (parent->entries)
+		for (i = 0; i < num_entries; i++)
+			amdgpu_vm_free_levels(adev, &parent->entries[i],
+					      level + 1);
 
-	kvfree(level->entries);
+	kvfree(parent->entries);
 }
 
 /**
@@ -2775,7 +2430,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
 	}
 
-	amd_sched_entity_fini(vm->entity.sched, &vm->entity);
+	drm_sched_entity_fini(vm->entity.sched, &vm->entity);
 
 	if (!RB_EMPTY_ROOT(&vm->va.rb_root)) {
 		dev_err(adev->dev, "still active bo inside vm\n");
@@ -2801,13 +2456,14 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	if (r) {
 		dev_err(adev->dev, "Leaking page tables because BO reservation failed\n");
 	} else {
-		amdgpu_vm_free_levels(&vm->root);
+		amdgpu_vm_free_levels(adev, &vm->root,
+				      adev->vm_manager.root_level);
 		amdgpu_bo_unreserve(root);
 	}
 	amdgpu_bo_unref(&root);
 	dma_fence_put(vm->last_update);
 	for (i = 0; i < AMDGPU_MAX_VMHUBS; i++)
-		amdgpu_vm_free_reserved_vmid(adev, vm, i);
+		amdgpu_vmid_free_reserved(adev, vm, i);
 }
 
 /**
@@ -2826,17 +2482,21 @@ bool amdgpu_vm_pasid_fault_credit(struct amdgpu_device *adev,
 
 	spin_lock(&adev->vm_manager.pasid_lock);
 	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
-	spin_unlock(&adev->vm_manager.pasid_lock);
-	if (!vm)
+	if (!vm) {
 		/* VM not found, can't track fault credit */
+		spin_unlock(&adev->vm_manager.pasid_lock);
 		return true;
+	}
 
 	/* No lock needed. only accessed by IRQ handler */
-	if (!vm->fault_credit)
+	if (!vm->fault_credit) {
 		/* Too many faults in this VM */
+		spin_unlock(&adev->vm_manager.pasid_lock);
 		return false;
+	}
 
 	vm->fault_credit--;
+	spin_unlock(&adev->vm_manager.pasid_lock);
 	return true;
 }
 
@@ -2849,23 +2509,9 @@ bool amdgpu_vm_pasid_fault_credit(struct amdgpu_device *adev,
  */
 void amdgpu_vm_manager_init(struct amdgpu_device *adev)
 {
-	unsigned i, j;
-
-	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
-		struct amdgpu_vm_id_manager *id_mgr =
-			&adev->vm_manager.id_mgr[i];
-
-		mutex_init(&id_mgr->lock);
-		INIT_LIST_HEAD(&id_mgr->ids_lru);
-		atomic_set(&id_mgr->reserved_vmid_num, 0);
+	unsigned i;
 
-		/* skip over VMID 0, since it is the system VM */
-		for (j = 1; j < id_mgr->num_ids; ++j) {
-			amdgpu_vm_reset_id(adev, i, j);
-			amdgpu_sync_create(&id_mgr->ids[i].active);
-			list_add_tail(&id_mgr->ids[j].list, &id_mgr->ids_lru);
-		}
-	}
+	amdgpu_vmid_mgr_init(adev);
 
 	adev->vm_manager.fence_context =
 		dma_fence_context_alloc(AMDGPU_MAX_RINGS);
@@ -2873,7 +2519,6 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
 		adev->vm_manager.seqno[i] = 0;
 
 	atomic_set(&adev->vm_manager.vm_pte_next_ring, 0);
-	atomic64_set(&adev->vm_manager.client_counter, 0);
 	spin_lock_init(&adev->vm_manager.prt_lock);
 	atomic_set(&adev->vm_manager.num_prt_users, 0);
 
@@ -2906,24 +2551,10 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
  */
 void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
 {
-	unsigned i, j;
-
 	WARN_ON(!idr_is_empty(&adev->vm_manager.pasid_idr));
 	idr_destroy(&adev->vm_manager.pasid_idr);
 
-	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
-		struct amdgpu_vm_id_manager *id_mgr =
-			&adev->vm_manager.id_mgr[i];
-
-		mutex_destroy(&id_mgr->lock);
-		for (j = 0; j < AMDGPU_NUM_VM; ++j) {
-			struct amdgpu_vm_id *id = &id_mgr->ids[j];
-
-			amdgpu_sync_free(&id->active);
-			dma_fence_put(id->flushed_updates);
-			dma_fence_put(id->last_flush);
-		}
-	}
+	amdgpu_vmid_mgr_fini(adev);
 }
 
 int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
@@ -2936,13 +2567,12 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	switch (args->in.op) {
 	case AMDGPU_VM_OP_RESERVE_VMID:
 		/* current, we only have requirement to reserve vmid from gfxhub */
-		r = amdgpu_vm_alloc_reserved_vmid(adev, &fpriv->vm,
-						  AMDGPU_GFXHUB);
+		r = amdgpu_vmid_alloc_reserved(adev, &fpriv->vm, AMDGPU_GFXHUB);
 		if (r)
 			return r;
 		break;
 	case AMDGPU_VM_OP_UNRESERVE_VMID:
-		amdgpu_vm_free_reserved_vmid(adev, &fpriv->vm, AMDGPU_GFXHUB);
+		amdgpu_vmid_free_reserved(adev, &fpriv->vm, AMDGPU_GFXHUB);
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index bae77353447b..21a80f1bb2b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -24,12 +24,14 @@
 #ifndef __AMDGPU_VM_H__
 #define __AMDGPU_VM_H__
 
-#include <linux/rbtree.h>
 #include <linux/idr.h>
+#include <linux/kfifo.h>
+#include <linux/rbtree.h>
+#include <drm/gpu_scheduler.h>
 
-#include "gpu_scheduler.h"
 #include "amdgpu_sync.h"
 #include "amdgpu_ring.h"
+#include "amdgpu_ids.h"
 
 struct amdgpu_bo_va;
 struct amdgpu_job;
@@ -39,9 +41,6 @@ struct amdgpu_bo_list_entry;
  * GPUVM handling
  */
 
-/* maximum number of VMIDs */
-#define AMDGPU_NUM_VM	16
-
 /* Maximum number of PTEs the hardware can write with one command */
 #define AMDGPU_VM_MAX_UPDATE_SIZE	0x3FFFF
 
@@ -69,6 +68,12 @@ struct amdgpu_bo_list_entry;
 /* PDE is handled as PTE for VEGA10 */
 #define AMDGPU_PDE_PTE		(1ULL << 54)
 
+/* PTE is handled as PDE for VEGA10 (Translate Further) */
+#define AMDGPU_PTE_TF		(1ULL << 56)
+
+/* PDE Block Fragment Size for VEGA10 */
+#define AMDGPU_PDE_BFS(a)	((uint64_t)a << 59)
+
 /* VEGA10 only */
 #define AMDGPU_PTE_MTYPE(a)    ((uint64_t)a << 57)
 #define AMDGPU_PTE_MTYPE_MASK	AMDGPU_PTE_MTYPE(3ULL)
@@ -96,6 +101,19 @@ struct amdgpu_bo_list_entry;
 /* hardcode that limit for now */
 #define AMDGPU_VA_RESERVED_SIZE			(8ULL << 20)
 
+/* VA hole for 48bit addresses on Vega10 */
+#define AMDGPU_VA_HOLE_START			0x0000800000000000ULL
+#define AMDGPU_VA_HOLE_END			0xffff800000000000ULL
+
+/*
+ * Hardware is programmed as if the hole doesn't exists with start and end
+ * address values.
+ *
+ * This mask is used to remove the upper 16bits of the VA and so come up with
+ * the linear addr value.
+ */
+#define AMDGPU_VA_HOLE_MASK			0x0000ffffffffffffULL
+
 /* max vmids dedicated for process */
 #define AMDGPU_VM_MAX_RESERVED_VMID	1
 
@@ -106,6 +124,16 @@ struct amdgpu_bo_list_entry;
 #define AMDGPU_VM_USE_CPU_FOR_GFX (1 << 0)
 #define AMDGPU_VM_USE_CPU_FOR_COMPUTE (1 << 1)
 
+/* VMPT level enumerate, and the hiberachy is:
+ * PDB2->PDB1->PDB0->PTB
+ */
+enum amdgpu_vm_level {
+	AMDGPU_VM_PDB2,
+	AMDGPU_VM_PDB1,
+	AMDGPU_VM_PDB0,
+	AMDGPU_VM_PTB
+};
+
 /* base structure for tracking BO usage in a VM */
 struct amdgpu_vm_bo_base {
 	/* constant after initialization */
@@ -124,11 +152,10 @@ struct amdgpu_vm_bo_base {
 
 struct amdgpu_vm_pt {
 	struct amdgpu_vm_bo_base	base;
-	uint64_t			addr;
+	bool				huge;
 
 	/* array of page tables, one for each directory entry */
 	struct amdgpu_vm_pt		*entries;
-	unsigned			last_entry_used;
 };
 
 #define AMDGPU_VM_FAULT(pasid, addr) (((u64)(pasid) << 48) | (addr))
@@ -162,13 +189,11 @@ struct amdgpu_vm {
 	spinlock_t		freed_lock;
 
 	/* Scheduler entity for page table updates */
-	struct amd_sched_entity	entity;
+	struct drm_sched_entity	entity;
 
-	/* client id and PASID (TODO: replace client_id with PASID) */
-	u64                     client_id;
 	unsigned int		pasid;
 	/* dedicated to vm */
-	struct amdgpu_vm_id	*reserved_vmid[AMDGPU_MAX_VMHUBS];
+	struct amdgpu_vmid	*reserved_vmid[AMDGPU_MAX_VMHUBS];
 
 	/* Flag to indicate if VM tables are updated by CPU or GPU (SDMA) */
 	bool                    use_cpu_for_update;
@@ -183,37 +208,9 @@ struct amdgpu_vm {
 	unsigned int		fault_credit;
 };
 
-struct amdgpu_vm_id {
-	struct list_head	list;
-	struct amdgpu_sync	active;
-	struct dma_fence		*last_flush;
-	atomic64_t		owner;
-
-	uint64_t		pd_gpu_addr;
-	/* last flushed PD/PT update */
-	struct dma_fence		*flushed_updates;
-
-	uint32_t                current_gpu_reset_count;
-
-	uint32_t		gds_base;
-	uint32_t		gds_size;
-	uint32_t		gws_base;
-	uint32_t		gws_size;
-	uint32_t		oa_base;
-	uint32_t		oa_size;
-};
-
-struct amdgpu_vm_id_manager {
-	struct mutex		lock;
-	unsigned		num_ids;
-	struct list_head	ids_lru;
-	struct amdgpu_vm_id	ids[AMDGPU_NUM_VM];
-	atomic_t		reserved_vmid_num;
-};
-
 struct amdgpu_vm_manager {
 	/* Handling of VMIDs */
-	struct amdgpu_vm_id_manager		id_mgr[AMDGPU_MAX_VMHUBS];
+	struct amdgpu_vmid_mgr			id_mgr[AMDGPU_MAX_VMHUBS];
 
 	/* Handling of VM fences */
 	u64					fence_context;
@@ -221,9 +218,9 @@ struct amdgpu_vm_manager {
 
 	uint64_t				max_pfn;
 	uint32_t				num_level;
-	uint64_t				vm_size;
 	uint32_t				block_size;
 	uint32_t				fragment_size;
+	enum amdgpu_vm_level			root_level;
 	/* vram base address for page table entry  */
 	u64					vram_base_offset;
 	/* vm pte handling */
@@ -231,8 +228,6 @@ struct amdgpu_vm_manager {
 	struct amdgpu_ring                      *vm_pte_rings[AMDGPU_MAX_RINGS];
 	unsigned				vm_pte_num_rings;
 	atomic_t				vm_pte_next_ring;
-	/* client id counter */
-	atomic64_t				client_counter;
 
 	/* partial resident texture handling */
 	spinlock_t				prt_lock;
@@ -251,8 +246,6 @@ struct amdgpu_vm_manager {
 	spinlock_t				pasid_lock;
 };
 
-int amdgpu_vm_alloc_pasid(unsigned int bits);
-void amdgpu_vm_free_pasid(unsigned int pasid);
 void amdgpu_vm_manager_init(struct amdgpu_device *adev);
 void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
@@ -270,13 +263,7 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
 			struct amdgpu_vm *vm,
 			uint64_t saddr, uint64_t size);
-int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
-		      struct amdgpu_sync *sync, struct dma_fence *fence,
-		      struct amdgpu_job *job);
 int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_pipe_sync);
-void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vmhub,
-			unsigned vmid);
-void amdgpu_vm_reset_all_ids(struct amdgpu_device *adev);
 int amdgpu_vm_update_directories(struct amdgpu_device *adev,
 				 struct amdgpu_vm *vm);
 int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
@@ -312,10 +299,9 @@ struct amdgpu_bo_va_mapping *amdgpu_vm_bo_lookup_mapping(struct amdgpu_vm *vm,
 							 uint64_t addr);
 void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 		      struct amdgpu_bo_va *bo_va);
-void amdgpu_vm_set_fragment_size(struct amdgpu_device *adev,
-				uint32_t fragment_size_default);
-void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint64_t vm_size,
-				uint32_t fragment_size_default);
+void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size,
+			   uint32_t fragment_size_default, unsigned max_level,
+			   unsigned max_bits);
 int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
 bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 				  struct amdgpu_job *job);
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
index b374653bd6cf..f9b2ce9a98f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
@@ -65,8 +65,15 @@ static int amdgpu_atombios_i2c_process_i2c_ch(struct amdgpu_i2c_chan *chan,
 			args.ucRegIndex = buf[0];
 		if (num)
 			num--;
-		if (num)
-			memcpy(&out, &buf[1], num);
+		if (num) {
+			if (buf) {
+				memcpy(&out, &buf[1], num);
+			} else {
+				DRM_ERROR("hw i2c: missing buf with num > 1\n");
+				r = -EINVAL;
+				goto done;
+			}
+		}
 		args.lpI2CDataOut = cpu_to_le16(out);
 	} else {
 		if (num > ATOM_MAX_HW_I2C_READ) {
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 68b505c768ad..a0943aa8d1d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -891,12 +891,12 @@ static void ci_dpm_powergate_uvd(void *handle, bool gate)
 
 	if (gate) {
 		/* stop the UVD block */
-		amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
-							AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_PG_STATE_GATE);
 		ci_update_uvd_dpm(adev, gate);
 	} else {
-		amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
-							AMD_PG_STATE_UNGATE);
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+						       AMD_PG_STATE_UNGATE);
 		ci_update_uvd_dpm(adev, gate);
 	}
 }
@@ -4540,9 +4540,9 @@ static int ci_set_mc_special_registers(struct amdgpu_device *adev,
 					((temp_reg & 0xffff0000)) | ((table->mc_reg_table_entry[k].mc_data[i] & 0xffff0000) >> 16);
 			}
 			j++;
+
 			if (j >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
-
 			temp_reg = RREG32(mmMC_PMG_CMD_MRS);
 			table->mc_reg_address[j].s1 = mmMC_PMG_CMD_MRS;
 			table->mc_reg_address[j].s0 = mmMC_SEQ_PMG_CMD_MRS_LP;
@@ -4553,10 +4553,10 @@ static int ci_set_mc_special_registers(struct amdgpu_device *adev,
 					table->mc_reg_table_entry[k].mc_data[j] |= 0x100;
 			}
 			j++;
-			if (j > SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
-				return -EINVAL;
 
 			if (adev->mc.vram_type != AMDGPU_VRAM_TYPE_GDDR5) {
+				if (j >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
+					return -EINVAL;
 				table->mc_reg_address[j].s1 = mmMC_PMG_AUTO_CMD;
 				table->mc_reg_address[j].s0 = mmMC_PMG_AUTO_CMD;
 				for (k = 0; k < table->num_entries; k++) {
@@ -4564,8 +4564,6 @@ static int ci_set_mc_special_registers(struct amdgpu_device *adev,
 						(table->mc_reg_table_entry[k].mc_data[i] & 0xffff0000) >> 16;
 				}
 				j++;
-				if (j > SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
-					return -EINVAL;
 			}
 			break;
 		case mmMC_SEQ_RESERVE_M:
@@ -4577,8 +4575,6 @@ static int ci_set_mc_special_registers(struct amdgpu_device *adev,
 					(temp_reg & 0xffff0000) | (table->mc_reg_table_entry[k].mc_data[i] & 0x0000ffff);
 			}
 			j++;
-			if (j > SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
-				return -EINVAL;
 			break;
 		default:
 			break;
@@ -6625,9 +6621,9 @@ static int ci_dpm_print_clock_levels(void *handle,
 
 		for (i = 0; i < pcie_table->count; i++)
 			size += sprintf(buf + size, "%d: %s %s\n", i,
-					(pcie_table->dpm_levels[i].value == 0) ? "2.5GB, x1" :
-					(pcie_table->dpm_levels[i].value == 1) ? "5.0GB, x16" :
-					(pcie_table->dpm_levels[i].value == 2) ? "8.0GB, x16" : "",
+					(pcie_table->dpm_levels[i].value == 0) ? "2.5GT/s, x1" :
+					(pcie_table->dpm_levels[i].value == 1) ? "5.0GT/s, x16" :
+					(pcie_table->dpm_levels[i].value == 2) ? "8.0GT/s, x16" : "",
 					(i == now) ? "*" : "");
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 793b1470284d..8e59e65efd44 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -755,74 +755,74 @@ static void cik_init_golden_registers(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_BONAIRE:
-		amdgpu_program_register_sequence(adev,
-						 bonaire_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(bonaire_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 bonaire_golden_registers,
-						 (const u32)ARRAY_SIZE(bonaire_golden_registers));
-		amdgpu_program_register_sequence(adev,
-						 bonaire_golden_common_registers,
-						 (const u32)ARRAY_SIZE(bonaire_golden_common_registers));
-		amdgpu_program_register_sequence(adev,
-						 bonaire_golden_spm_registers,
-						 (const u32)ARRAY_SIZE(bonaire_golden_spm_registers));
+		amdgpu_device_program_register_sequence(adev,
+							bonaire_mgcg_cgcg_init,
+							ARRAY_SIZE(bonaire_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							bonaire_golden_registers,
+							ARRAY_SIZE(bonaire_golden_registers));
+		amdgpu_device_program_register_sequence(adev,
+							bonaire_golden_common_registers,
+							ARRAY_SIZE(bonaire_golden_common_registers));
+		amdgpu_device_program_register_sequence(adev,
+							bonaire_golden_spm_registers,
+							ARRAY_SIZE(bonaire_golden_spm_registers));
 		break;
 	case CHIP_KABINI:
-		amdgpu_program_register_sequence(adev,
-						 kalindi_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(kalindi_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 kalindi_golden_registers,
-						 (const u32)ARRAY_SIZE(kalindi_golden_registers));
-		amdgpu_program_register_sequence(adev,
-						 kalindi_golden_common_registers,
-						 (const u32)ARRAY_SIZE(kalindi_golden_common_registers));
-		amdgpu_program_register_sequence(adev,
-						 kalindi_golden_spm_registers,
-						 (const u32)ARRAY_SIZE(kalindi_golden_spm_registers));
+		amdgpu_device_program_register_sequence(adev,
+							kalindi_mgcg_cgcg_init,
+							ARRAY_SIZE(kalindi_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							kalindi_golden_registers,
+							ARRAY_SIZE(kalindi_golden_registers));
+		amdgpu_device_program_register_sequence(adev,
+							kalindi_golden_common_registers,
+							ARRAY_SIZE(kalindi_golden_common_registers));
+		amdgpu_device_program_register_sequence(adev,
+							kalindi_golden_spm_registers,
+							ARRAY_SIZE(kalindi_golden_spm_registers));
 		break;
 	case CHIP_MULLINS:
-		amdgpu_program_register_sequence(adev,
-						 kalindi_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(kalindi_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 godavari_golden_registers,
-						 (const u32)ARRAY_SIZE(godavari_golden_registers));
-		amdgpu_program_register_sequence(adev,
-						 kalindi_golden_common_registers,
-						 (const u32)ARRAY_SIZE(kalindi_golden_common_registers));
-		amdgpu_program_register_sequence(adev,
-						 kalindi_golden_spm_registers,
-						 (const u32)ARRAY_SIZE(kalindi_golden_spm_registers));
+		amdgpu_device_program_register_sequence(adev,
+							kalindi_mgcg_cgcg_init,
+							ARRAY_SIZE(kalindi_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							godavari_golden_registers,
+							ARRAY_SIZE(godavari_golden_registers));
+		amdgpu_device_program_register_sequence(adev,
+							kalindi_golden_common_registers,
+							ARRAY_SIZE(kalindi_golden_common_registers));
+		amdgpu_device_program_register_sequence(adev,
+							kalindi_golden_spm_registers,
+							ARRAY_SIZE(kalindi_golden_spm_registers));
 		break;
 	case CHIP_KAVERI:
-		amdgpu_program_register_sequence(adev,
-						 spectre_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(spectre_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 spectre_golden_registers,
-						 (const u32)ARRAY_SIZE(spectre_golden_registers));
-		amdgpu_program_register_sequence(adev,
-						 spectre_golden_common_registers,
-						 (const u32)ARRAY_SIZE(spectre_golden_common_registers));
-		amdgpu_program_register_sequence(adev,
-						 spectre_golden_spm_registers,
-						 (const u32)ARRAY_SIZE(spectre_golden_spm_registers));
+		amdgpu_device_program_register_sequence(adev,
+							spectre_mgcg_cgcg_init,
+							ARRAY_SIZE(spectre_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							spectre_golden_registers,
+							ARRAY_SIZE(spectre_golden_registers));
+		amdgpu_device_program_register_sequence(adev,
+							spectre_golden_common_registers,
+							ARRAY_SIZE(spectre_golden_common_registers));
+		amdgpu_device_program_register_sequence(adev,
+							spectre_golden_spm_registers,
+							ARRAY_SIZE(spectre_golden_spm_registers));
 		break;
 	case CHIP_HAWAII:
-		amdgpu_program_register_sequence(adev,
-						 hawaii_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(hawaii_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 hawaii_golden_registers,
-						 (const u32)ARRAY_SIZE(hawaii_golden_registers));
-		amdgpu_program_register_sequence(adev,
-						 hawaii_golden_common_registers,
-						 (const u32)ARRAY_SIZE(hawaii_golden_common_registers));
-		amdgpu_program_register_sequence(adev,
-						 hawaii_golden_spm_registers,
-						 (const u32)ARRAY_SIZE(hawaii_golden_spm_registers));
+		amdgpu_device_program_register_sequence(adev,
+							hawaii_mgcg_cgcg_init,
+							ARRAY_SIZE(hawaii_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							hawaii_golden_registers,
+							ARRAY_SIZE(hawaii_golden_registers));
+		amdgpu_device_program_register_sequence(adev,
+							hawaii_golden_common_registers,
+							ARRAY_SIZE(hawaii_golden_common_registers));
+		amdgpu_device_program_register_sequence(adev,
+							hawaii_golden_spm_registers,
+							ARRAY_SIZE(hawaii_golden_spm_registers));
 		break;
 	default:
 		break;
@@ -1023,22 +1023,101 @@ static const struct amdgpu_allowed_register_entry cik_allowed_read_registers[] =
 	{mmPA_SC_RASTER_CONFIG_1, true},
 };
 
-static uint32_t cik_read_indexed_register(struct amdgpu_device *adev,
-					  u32 se_num, u32 sh_num,
-					  u32 reg_offset)
+
+static uint32_t cik_get_register_value(struct amdgpu_device *adev,
+				       bool indexed, u32 se_num,
+				       u32 sh_num, u32 reg_offset)
 {
-	uint32_t val;
+	if (indexed) {
+		uint32_t val;
+		unsigned se_idx = (se_num == 0xffffffff) ? 0 : se_num;
+		unsigned sh_idx = (sh_num == 0xffffffff) ? 0 : sh_num;
+
+		switch (reg_offset) {
+		case mmCC_RB_BACKEND_DISABLE:
+			return adev->gfx.config.rb_config[se_idx][sh_idx].rb_backend_disable;
+		case mmGC_USER_RB_BACKEND_DISABLE:
+			return adev->gfx.config.rb_config[se_idx][sh_idx].user_rb_backend_disable;
+		case mmPA_SC_RASTER_CONFIG:
+			return adev->gfx.config.rb_config[se_idx][sh_idx].raster_config;
+		case mmPA_SC_RASTER_CONFIG_1:
+			return adev->gfx.config.rb_config[se_idx][sh_idx].raster_config_1;
+		}
 
-	mutex_lock(&adev->grbm_idx_mutex);
-	if (se_num != 0xffffffff || sh_num != 0xffffffff)
-		amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff);
+		mutex_lock(&adev->grbm_idx_mutex);
+		if (se_num != 0xffffffff || sh_num != 0xffffffff)
+			amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff);
 
-	val = RREG32(reg_offset);
+		val = RREG32(reg_offset);
 
-	if (se_num != 0xffffffff || sh_num != 0xffffffff)
-		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
-	mutex_unlock(&adev->grbm_idx_mutex);
-	return val;
+		if (se_num != 0xffffffff || sh_num != 0xffffffff)
+			amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+		mutex_unlock(&adev->grbm_idx_mutex);
+		return val;
+	} else {
+		unsigned idx;
+
+		switch (reg_offset) {
+		case mmGB_ADDR_CONFIG:
+			return adev->gfx.config.gb_addr_config;
+		case mmMC_ARB_RAMCFG:
+			return adev->gfx.config.mc_arb_ramcfg;
+		case mmGB_TILE_MODE0:
+		case mmGB_TILE_MODE1:
+		case mmGB_TILE_MODE2:
+		case mmGB_TILE_MODE3:
+		case mmGB_TILE_MODE4:
+		case mmGB_TILE_MODE5:
+		case mmGB_TILE_MODE6:
+		case mmGB_TILE_MODE7:
+		case mmGB_TILE_MODE8:
+		case mmGB_TILE_MODE9:
+		case mmGB_TILE_MODE10:
+		case mmGB_TILE_MODE11:
+		case mmGB_TILE_MODE12:
+		case mmGB_TILE_MODE13:
+		case mmGB_TILE_MODE14:
+		case mmGB_TILE_MODE15:
+		case mmGB_TILE_MODE16:
+		case mmGB_TILE_MODE17:
+		case mmGB_TILE_MODE18:
+		case mmGB_TILE_MODE19:
+		case mmGB_TILE_MODE20:
+		case mmGB_TILE_MODE21:
+		case mmGB_TILE_MODE22:
+		case mmGB_TILE_MODE23:
+		case mmGB_TILE_MODE24:
+		case mmGB_TILE_MODE25:
+		case mmGB_TILE_MODE26:
+		case mmGB_TILE_MODE27:
+		case mmGB_TILE_MODE28:
+		case mmGB_TILE_MODE29:
+		case mmGB_TILE_MODE30:
+		case mmGB_TILE_MODE31:
+			idx = (reg_offset - mmGB_TILE_MODE0);
+			return adev->gfx.config.tile_mode_array[idx];
+		case mmGB_MACROTILE_MODE0:
+		case mmGB_MACROTILE_MODE1:
+		case mmGB_MACROTILE_MODE2:
+		case mmGB_MACROTILE_MODE3:
+		case mmGB_MACROTILE_MODE4:
+		case mmGB_MACROTILE_MODE5:
+		case mmGB_MACROTILE_MODE6:
+		case mmGB_MACROTILE_MODE7:
+		case mmGB_MACROTILE_MODE8:
+		case mmGB_MACROTILE_MODE9:
+		case mmGB_MACROTILE_MODE10:
+		case mmGB_MACROTILE_MODE11:
+		case mmGB_MACROTILE_MODE12:
+		case mmGB_MACROTILE_MODE13:
+		case mmGB_MACROTILE_MODE14:
+		case mmGB_MACROTILE_MODE15:
+			idx = (reg_offset - mmGB_MACROTILE_MODE0);
+			return adev->gfx.config.macrotile_mode_array[idx];
+		default:
+			return RREG32(reg_offset);
+		}
+	}
 }
 
 static int cik_read_register(struct amdgpu_device *adev, u32 se_num,
@@ -1048,13 +1127,13 @@ static int cik_read_register(struct amdgpu_device *adev, u32 se_num,
 
 	*value = 0;
 	for (i = 0; i < ARRAY_SIZE(cik_allowed_read_registers); i++) {
+		bool indexed = cik_allowed_read_registers[i].grbm_indexed;
+
 		if (reg_offset != cik_allowed_read_registers[i].reg_offset)
 			continue;
 
-		*value = cik_allowed_read_registers[i].grbm_indexed ?
-			 cik_read_indexed_register(adev, se_num,
-						   sh_num, reg_offset) :
-			 RREG32(reg_offset);
+		*value = cik_get_register_value(adev, indexed, se_num, sh_num,
+						reg_offset);
 		return 0;
 	}
 	return -EINVAL;
@@ -1167,7 +1246,7 @@ static int cik_gpu_pci_config_reset(struct amdgpu_device *adev)
 	/* disable BM */
 	pci_clear_master(adev->pdev);
 	/* reset */
-	amdgpu_pci_config_reset(adev);
+	amdgpu_device_pci_config_reset(adev);
 
 	udelay(100);
 
@@ -1787,7 +1866,7 @@ static int cik_common_early_init(void *handle)
 
 	adev->firmware.load_type = amdgpu_ucode_get_load_type(adev, amdgpu_fw_load_type);
 
-	amdgpu_get_pcie_info(adev);
+	amdgpu_device_get_pcie_info(adev);
 
 	return 0;
 }
@@ -1895,77 +1974,77 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_BONAIRE:
-		amdgpu_ip_block_add(adev, &cik_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v7_0_ip_block);
-		amdgpu_ip_block_add(adev, &cik_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
-			amdgpu_ip_block_add(adev, &dm_ip_block);
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		else
-			amdgpu_ip_block_add(adev, &dce_v8_2_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v7_2_ip_block);
-		amdgpu_ip_block_add(adev, &cik_sdma_ip_block);
-		amdgpu_ip_block_add(adev, &uvd_v4_2_ip_block);
-		amdgpu_ip_block_add(adev, &vce_v2_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_v8_2_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v7_2_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
+		amdgpu_device_ip_block_add(adev, &uvd_v4_2_ip_block);
+		amdgpu_device_ip_block_add(adev, &vce_v2_0_ip_block);
 		break;
 	case CHIP_HAWAII:
-		amdgpu_ip_block_add(adev, &cik_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v7_0_ip_block);
-		amdgpu_ip_block_add(adev, &cik_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
-			amdgpu_ip_block_add(adev, &dm_ip_block);
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		else
-			amdgpu_ip_block_add(adev, &dce_v8_5_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v7_3_ip_block);
-		amdgpu_ip_block_add(adev, &cik_sdma_ip_block);
-		amdgpu_ip_block_add(adev, &uvd_v4_2_ip_block);
-		amdgpu_ip_block_add(adev, &vce_v2_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_v8_5_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v7_3_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
+		amdgpu_device_ip_block_add(adev, &uvd_v4_2_ip_block);
+		amdgpu_device_ip_block_add(adev, &vce_v2_0_ip_block);
 		break;
 	case CHIP_KAVERI:
-		amdgpu_ip_block_add(adev, &cik_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v7_0_ip_block);
-		amdgpu_ip_block_add(adev, &cik_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
-			amdgpu_ip_block_add(adev, &dm_ip_block);
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		else
-			amdgpu_ip_block_add(adev, &dce_v8_1_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v7_1_ip_block);
-		amdgpu_ip_block_add(adev, &cik_sdma_ip_block);
-		amdgpu_ip_block_add(adev, &uvd_v4_2_ip_block);
-		amdgpu_ip_block_add(adev, &vce_v2_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_v8_1_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v7_1_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
+		amdgpu_device_ip_block_add(adev, &uvd_v4_2_ip_block);
+		amdgpu_device_ip_block_add(adev, &vce_v2_0_ip_block);
 		break;
 	case CHIP_KABINI:
 	case CHIP_MULLINS:
-		amdgpu_ip_block_add(adev, &cik_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v7_0_ip_block);
-		amdgpu_ip_block_add(adev, &cik_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
-			amdgpu_ip_block_add(adev, &dm_ip_block);
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		else
-			amdgpu_ip_block_add(adev, &dce_v8_3_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v7_2_ip_block);
-		amdgpu_ip_block_add(adev, &cik_sdma_ip_block);
-		amdgpu_ip_block_add(adev, &uvd_v4_2_ip_block);
-		amdgpu_ip_block_add(adev, &vce_v2_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_v8_3_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v7_2_ip_block);
+		amdgpu_device_ip_block_add(adev, &cik_sdma_ip_block);
+		amdgpu_device_ip_block_add(adev, &uvd_v4_2_ip_block);
+		amdgpu_device_ip_block_add(adev, &vce_v2_0_ip_block);
 		break;
 	default:
 		/* FIXME: not supported yet */
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
index a870b354e3f7..d5a05c19708f 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -280,7 +280,7 @@ static void cik_ih_decode_iv(struct amdgpu_device *adev,
 	entry->src_id = dw[0] & 0xff;
 	entry->src_data[0] = dw[1] & 0xfffffff;
 	entry->ring_id = dw[2] & 0xff;
-	entry->vm_id = (dw[2] >> 8) & 0xff;
+	entry->vmid = (dw[2] >> 8) & 0xff;
 	entry->pas_id = (dw[2] >> 16) & 0xffff;
 
 	/* wptr/rptr are in bytes! */
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 60cecd117705..6e8278e689b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -221,9 +221,9 @@ static void cik_sdma_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
  */
 static void cik_sdma_ring_emit_ib(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib,
-				  unsigned vm_id, bool ctx_switch)
+				  unsigned vmid, bool ctx_switch)
 {
-	u32 extra_bits = vm_id & 0xf;
+	u32 extra_bits = vmid & 0xf;
 
 	/* IB packet must end on a 8 DW boundary */
 	cik_sdma_ring_insert_nop(ring, (12 - (lower_32_bits(ring->wptr) & 7)) % 8);
@@ -626,7 +626,7 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring)
 	u32 tmp;
 	u64 gpu_addr;
 
-	r = amdgpu_wb_get(adev, &index);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r);
 		return r;
@@ -639,7 +639,7 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring)
 	r = amdgpu_ring_alloc(ring, 5);
 	if (r) {
 		DRM_ERROR("amdgpu: dma failed to lock ring %d (%d).\n", ring->idx, r);
-		amdgpu_wb_free(adev, index);
+		amdgpu_device_wb_free(adev, index);
 		return r;
 	}
 	amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0));
@@ -657,13 +657,13 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n", ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
 			  ring->idx, tmp);
 		r = -EINVAL;
 	}
-	amdgpu_wb_free(adev, index);
+	amdgpu_device_wb_free(adev, index);
 
 	return r;
 }
@@ -686,7 +686,7 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	u64 gpu_addr;
 	long r;
 
-	r = amdgpu_wb_get(adev, &index);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
 		dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
 		return r;
@@ -724,7 +724,7 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	}
 	tmp = le32_to_cpu(adev->wb.wb[index]);
 	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp);
@@ -735,7 +735,7 @@ err1:
 	amdgpu_ib_free(adev, &ib, NULL);
 	dma_fence_put(f);
 err0:
-	amdgpu_wb_free(adev, index);
+	amdgpu_device_wb_free(adev, index);
 	return r;
 }
 
@@ -880,23 +880,23 @@ static void cik_sdma_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using sDMA (CIK).
  */
 static void cik_sdma_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vm_id, uint64_t pd_addr)
+					unsigned vmid, uint64_t pd_addr)
 {
 	u32 extra_bits = (SDMA_POLL_REG_MEM_EXTRA_OP(0) |
 			  SDMA_POLL_REG_MEM_EXTRA_FUNC(0)); /* always */
 
 	amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
-	if (vm_id < 8) {
-		amdgpu_ring_write(ring, (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id));
+	if (vmid < 8) {
+		amdgpu_ring_write(ring, (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vmid));
 	} else {
-		amdgpu_ring_write(ring, (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vm_id - 8));
+		amdgpu_ring_write(ring, (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vmid - 8));
 	}
 	amdgpu_ring_write(ring, pd_addr >> 12);
 
 	/* flush TLB */
 	amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
 	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST);
-	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vmid);
 
 	amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_POLL_REG_MEM, 0, extra_bits));
 	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST << 2);
diff --git a/drivers/gpu/drm/amd/amdgpu/cikd.h b/drivers/gpu/drm/amd/amdgpu/cikd.h
index 6a9e38a3d2a0..cee6e8a3ad9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/cikd.h
+++ b/drivers/gpu/drm/amd/amdgpu/cikd.h
@@ -562,7 +562,7 @@
 #define	PRIVATE_BASE(x)	((x) << 0) /* scratch */
 #define	SHARED_BASE(x)	((x) << 16) /* LDS */
 
-#define KFD_CIK_SDMA_QUEUE_OFFSET	0x200
+#define KFD_CIK_SDMA_QUEUE_OFFSET (mmSDMA0_RLC1_RB_CNTL - mmSDMA0_RLC0_RB_CNTL)
 
 /* valid for both DEFAULT_MTYPE and APE1_MTYPE */
 enum {
diff --git a/drivers/gpu/drm/amd/amdgpu/clearstate_gfx9.h b/drivers/gpu/drm/amd/amdgpu/clearstate_gfx9.h
index 003a131bad47..567a904804bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/clearstate_gfx9.h
+++ b/drivers/gpu/drm/amd/amdgpu/clearstate_gfx9.h
@@ -48,7 +48,7 @@ static const unsigned int gfx9_SECT_CONTEXT_def_1[] =
     0x00000000, // DB_STENCIL_WRITE_BASE
     0x00000000, // DB_STENCIL_WRITE_BASE_HI
     0x00000000, // DB_DFSM_CONTROL
-    0x00000000, // DB_RENDER_FILTER
+    0, // HOLE
     0x00000000, // DB_Z_INFO2
     0x00000000, // DB_STENCIL_INFO2
     0, // HOLE
@@ -259,8 +259,8 @@ static const unsigned int gfx9_SECT_CONTEXT_def_2[] =
     0x00000000, // PA_SC_RIGHT_VERT_GRID
     0x00000000, // PA_SC_LEFT_VERT_GRID
     0x00000000, // PA_SC_HORIZ_GRID
-    0x00000000, // PA_SC_FOV_WINDOW_LR
-    0x00000000, // PA_SC_FOV_WINDOW_TB
+    0, // HOLE
+    0, // HOLE
     0, // HOLE
     0, // HOLE
     0, // HOLE
@@ -701,7 +701,7 @@ static const unsigned int gfx9_SECT_CONTEXT_def_7[] =
 {
     0x00000000, // VGT_GS_MAX_PRIMS_PER_SUBGROUP
     0x00000000, // VGT_DRAW_PAYLOAD_CNTL
-    0x00000000, // VGT_INDEX_PAYLOAD_CNTL
+    0, // HOLE
     0x00000000, // VGT_INSTANCE_STEP_RATE_0
     0x00000000, // VGT_INSTANCE_STEP_RATE_1
     0, // HOLE
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index fa61d649bb44..f576e9cbbc61 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -259,7 +259,7 @@ static void cz_ih_decode_iv(struct amdgpu_device *adev,
 	entry->src_id = dw[0] & 0xff;
 	entry->src_data[0] = dw[1] & 0xfffffff;
 	entry->ring_id = dw[2] & 0xff;
-	entry->vm_id = (dw[2] >> 8) & 0xff;
+	entry->vmid = (dw[2] >> 8) & 0xff;
 	entry->pas_id = (dw[2] >> 16) & 0xffff;
 
 	/* wptr/rptr are in bytes! */
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 4e519dc42916..f34bc68aadfb 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -145,20 +145,20 @@ static void dce_v10_0_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_FIJI:
-		amdgpu_program_register_sequence(adev,
-						 fiji_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(fiji_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_fiji_a10,
-						 (const u32)ARRAY_SIZE(golden_settings_fiji_a10));
+		amdgpu_device_program_register_sequence(adev,
+							fiji_mgcg_cgcg_init,
+							ARRAY_SIZE(fiji_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_fiji_a10,
+							ARRAY_SIZE(golden_settings_fiji_a10));
 		break;
 	case CHIP_TONGA:
-		amdgpu_program_register_sequence(adev,
-						 tonga_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(tonga_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_tonga_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_tonga_a11));
+		amdgpu_device_program_register_sequence(adev,
+							tonga_mgcg_cgcg_init,
+							ARRAY_SIZE(tonga_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_tonga_a11,
+							ARRAY_SIZE(golden_settings_tonga_a11));
 		break;
 	default:
 		break;
@@ -2773,7 +2773,6 @@ static int dce_v10_0_early_init(void *handle)
 	adev->audio_endpt_wreg = &dce_v10_0_audio_endpt_wreg;
 
 	dce_v10_0_set_display_funcs(adev);
-	dce_v10_0_set_irq_funcs(adev);
 
 	adev->mode_info.num_crtc = dce_v10_0_get_num_crtc(adev);
 
@@ -2788,6 +2787,8 @@ static int dce_v10_0_early_init(void *handle)
 		return -EINVAL;
 	}
 
+	dce_v10_0_set_irq_funcs(adev);
+
 	return 0;
 }
 
@@ -3635,13 +3636,16 @@ static const struct amdgpu_irq_src_funcs dce_v10_0_hpd_irq_funcs = {
 
 static void dce_v10_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_LAST;
+	if (adev->mode_info.num_crtc > 0)
+		adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VLINE1 + adev->mode_info.num_crtc;
+	else
+		adev->crtc_irq.num_types = 0;
 	adev->crtc_irq.funcs = &dce_v10_0_crtc_irq_funcs;
 
-	adev->pageflip_irq.num_types = AMDGPU_PAGEFLIP_IRQ_LAST;
+	adev->pageflip_irq.num_types = adev->mode_info.num_crtc;
 	adev->pageflip_irq.funcs = &dce_v10_0_pageflip_irq_funcs;
 
-	adev->hpd_irq.num_types = AMDGPU_HPD_LAST;
+	adev->hpd_irq.num_types = adev->mode_info.num_hpd;
 	adev->hpd_irq.funcs = &dce_v10_0_hpd_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 11edc75edaa9..26378bd6aba4 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -154,28 +154,28 @@ static void dce_v11_0_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_CARRIZO:
-		amdgpu_program_register_sequence(adev,
-						 cz_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(cz_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 cz_golden_settings_a11,
-						 (const u32)ARRAY_SIZE(cz_golden_settings_a11));
+		amdgpu_device_program_register_sequence(adev,
+							cz_mgcg_cgcg_init,
+							ARRAY_SIZE(cz_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							cz_golden_settings_a11,
+							ARRAY_SIZE(cz_golden_settings_a11));
 		break;
 	case CHIP_STONEY:
-		amdgpu_program_register_sequence(adev,
-						 stoney_golden_settings_a11,
-						 (const u32)ARRAY_SIZE(stoney_golden_settings_a11));
+		amdgpu_device_program_register_sequence(adev,
+							stoney_golden_settings_a11,
+							ARRAY_SIZE(stoney_golden_settings_a11));
 		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
-		amdgpu_program_register_sequence(adev,
-						 polaris11_golden_settings_a11,
-						 (const u32)ARRAY_SIZE(polaris11_golden_settings_a11));
+		amdgpu_device_program_register_sequence(adev,
+							polaris11_golden_settings_a11,
+							ARRAY_SIZE(polaris11_golden_settings_a11));
 		break;
 	case CHIP_POLARIS10:
-		amdgpu_program_register_sequence(adev,
-						 polaris10_golden_settings_a11,
-						 (const u32)ARRAY_SIZE(polaris10_golden_settings_a11));
+		amdgpu_device_program_register_sequence(adev,
+							polaris10_golden_settings_a11,
+							ARRAY_SIZE(polaris10_golden_settings_a11));
 		break;
 	default:
 		break;
@@ -2876,7 +2876,6 @@ static int dce_v11_0_early_init(void *handle)
 	adev->audio_endpt_wreg = &dce_v11_0_audio_endpt_wreg;
 
 	dce_v11_0_set_display_funcs(adev);
-	dce_v11_0_set_irq_funcs(adev);
 
 	adev->mode_info.num_crtc = dce_v11_0_get_num_crtc(adev);
 
@@ -2903,6 +2902,8 @@ static int dce_v11_0_early_init(void *handle)
 		return -EINVAL;
 	}
 
+	dce_v11_0_set_irq_funcs(adev);
+
 	return 0;
 }
 
@@ -3759,13 +3760,16 @@ static const struct amdgpu_irq_src_funcs dce_v11_0_hpd_irq_funcs = {
 
 static void dce_v11_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_LAST;
+	if (adev->mode_info.num_crtc > 0)
+		adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VLINE1 + adev->mode_info.num_crtc;
+	else
+		adev->crtc_irq.num_types = 0;
 	adev->crtc_irq.funcs = &dce_v11_0_crtc_irq_funcs;
 
-	adev->pageflip_irq.num_types = AMDGPU_PAGEFLIP_IRQ_LAST;
+	adev->pageflip_irq.num_types = adev->mode_info.num_crtc;
 	adev->pageflip_irq.funcs = &dce_v11_0_pageflip_irq_funcs;
 
-	adev->hpd_irq.num_types = AMDGPU_HPD_LAST;
+	adev->hpd_irq.num_types = adev->mode_info.num_hpd;
 	adev->hpd_irq.funcs = &dce_v11_0_hpd_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index a51e35f824a1..bd2c4f727df6 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -2639,7 +2639,6 @@ static int dce_v6_0_early_init(void *handle)
 	adev->audio_endpt_wreg = &dce_v6_0_audio_endpt_wreg;
 
 	dce_v6_0_set_display_funcs(adev);
-	dce_v6_0_set_irq_funcs(adev);
 
 	adev->mode_info.num_crtc = dce_v6_0_get_num_crtc(adev);
 
@@ -2658,6 +2657,8 @@ static int dce_v6_0_early_init(void *handle)
 		return -EINVAL;
 	}
 
+	dce_v6_0_set_irq_funcs(adev);
+
 	return 0;
 }
 
@@ -3441,13 +3442,16 @@ static const struct amdgpu_irq_src_funcs dce_v6_0_hpd_irq_funcs = {
 
 static void dce_v6_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_LAST;
+	if (adev->mode_info.num_crtc > 0)
+		adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VLINE1 + adev->mode_info.num_crtc;
+	else
+		adev->crtc_irq.num_types = 0;
 	adev->crtc_irq.funcs = &dce_v6_0_crtc_irq_funcs;
 
-	adev->pageflip_irq.num_types = AMDGPU_PAGEFLIP_IRQ_LAST;
+	adev->pageflip_irq.num_types = adev->mode_info.num_crtc;
 	adev->pageflip_irq.funcs = &dce_v6_0_pageflip_irq_funcs;
 
-	adev->hpd_irq.num_types = AMDGPU_HPD_LAST;
+	adev->hpd_irq.num_types = adev->mode_info.num_hpd;
 	adev->hpd_irq.funcs = &dce_v6_0_hpd_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 9cf14b8b2db9..c008dc030687 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -2664,7 +2664,6 @@ static int dce_v8_0_early_init(void *handle)
 	adev->audio_endpt_wreg = &dce_v8_0_audio_endpt_wreg;
 
 	dce_v8_0_set_display_funcs(adev);
-	dce_v8_0_set_irq_funcs(adev);
 
 	adev->mode_info.num_crtc = dce_v8_0_get_num_crtc(adev);
 
@@ -2688,6 +2687,8 @@ static int dce_v8_0_early_init(void *handle)
 		return -EINVAL;
 	}
 
+	dce_v8_0_set_irq_funcs(adev);
+
 	return 0;
 }
 
@@ -3525,13 +3526,16 @@ static const struct amdgpu_irq_src_funcs dce_v8_0_hpd_irq_funcs = {
 
 static void dce_v8_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_LAST;
+	if (adev->mode_info.num_crtc > 0)
+		adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VLINE1 + adev->mode_info.num_crtc;
+	else
+		adev->crtc_irq.num_types = 0;
 	adev->crtc_irq.funcs = &dce_v8_0_crtc_irq_funcs;
 
-	adev->pageflip_irq.num_types = AMDGPU_PAGEFLIP_IRQ_LAST;
+	adev->pageflip_irq.num_types = adev->mode_info.num_crtc;
 	adev->pageflip_irq.funcs = &dce_v8_0_pageflip_irq_funcs;
 
-	adev->hpd_irq.num_types = AMDGPU_HPD_LAST;
+	adev->hpd_irq.num_types = adev->mode_info.num_hpd;
 	adev->hpd_irq.funcs = &dce_v8_0_hpd_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index a8829af120c1..120dd3b26fc2 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -44,6 +44,9 @@ static void dce_virtual_set_display_funcs(struct amdgpu_device *adev);
 static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev);
 static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev,
 					      int index);
+static void dce_virtual_set_crtc_vblank_interrupt_state(struct amdgpu_device *adev,
+							int crtc,
+							enum amdgpu_interrupt_state state);
 
 /**
  * dce_virtual_vblank_wait - vblank wait asic callback.
@@ -437,6 +440,8 @@ static int dce_virtual_sw_fini(void *handle)
 	drm_kms_helper_poll_fini(adev->ddev);
 
 	drm_mode_config_cleanup(adev->ddev);
+	/* clear crtcs pointer to avoid dce irq finish routine access freed data */
+	memset(adev->mode_info.crtcs, 0, sizeof(adev->mode_info.crtcs[0]) * AMDGPU_MAX_CRTCS);
 	adev->mode_info.mode_config_initialized = false;
 	return 0;
 }
@@ -489,6 +494,13 @@ static int dce_virtual_hw_init(void *handle)
 
 static int dce_virtual_hw_fini(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i = 0;
+
+	for (i = 0; i<adev->mode_info.num_crtc; i++)
+		if (adev->mode_info.crtcs[i])
+			dce_virtual_set_crtc_vblank_interrupt_state(adev, i, AMDGPU_IRQ_STATE_DISABLE);
+
 	return 0;
 }
 
@@ -723,7 +735,7 @@ static void dce_virtual_set_crtc_vblank_interrupt_state(struct amdgpu_device *ad
 							int crtc,
 							enum amdgpu_interrupt_state state)
 {
-	if (crtc >= adev->mode_info.num_crtc) {
+	if (crtc >= adev->mode_info.num_crtc || !adev->mode_info.crtcs[crtc]) {
 		DRM_DEBUG("invalid crtc %d\n", crtc);
 		return;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index dbbe986f90f2..9870d83b68c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -1798,7 +1798,7 @@ static int gfx_v6_0_ring_test_ring(struct amdgpu_ring *ring)
 		DRM_UDELAY(1);
 	}
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n", ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (scratch(0x%04X)=0x%08X)\n",
 			  ring->idx, scratch, tmp);
@@ -1874,7 +1874,7 @@ static void gfx_v6_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
 
 static void gfx_v6_0_ring_emit_ib(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib,
-				  unsigned vm_id, bool ctx_switch)
+				  unsigned vmid, bool ctx_switch)
 {
 	u32 header, control = 0;
 
@@ -1889,7 +1889,7 @@ static void gfx_v6_0_ring_emit_ib(struct amdgpu_ring *ring,
 	else
 		header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
 
-	control |= ib->length_dw | (vm_id << 24);
+	control |= ib->length_dw | (vmid << 24);
 
 	amdgpu_ring_write(ring, header);
 	amdgpu_ring_write(ring,
@@ -1951,7 +1951,7 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	}
 	tmp = RREG32(scratch);
 	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n",
@@ -2354,7 +2354,7 @@ static void gfx_v6_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 }
 
 static void gfx_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vm_id, uint64_t pd_addr)
+					unsigned vmid, uint64_t pd_addr)
 {
 	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
 
@@ -2362,10 +2362,10 @@ static void gfx_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
 				 WRITE_DATA_DST_SEL(0)));
-	if (vm_id < 8) {
-		amdgpu_ring_write(ring, (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id ));
+	if (vmid < 8) {
+		amdgpu_ring_write(ring, (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vmid ));
 	} else {
-		amdgpu_ring_write(ring, (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + (vm_id - 8)));
+		amdgpu_ring_write(ring, (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + (vmid - 8)));
 	}
 	amdgpu_ring_write(ring, 0);
 	amdgpu_ring_write(ring, pd_addr >> 12);
@@ -2376,7 +2376,7 @@ static void gfx_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 				 WRITE_DATA_DST_SEL(0)));
 	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST);
 	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vmid);
 
 	/* wait for the invalidate to complete */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
@@ -2962,25 +2962,7 @@ static void gfx_v6_0_get_csb_buffer(struct amdgpu_device *adev,
 
 	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_SET_CONTEXT_REG, 1));
 	buffer[count++] = cpu_to_le32(mmPA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START);
-
-	switch (adev->asic_type) {
-	case CHIP_TAHITI:
-	case CHIP_PITCAIRN:
-		buffer[count++] = cpu_to_le32(0x2a00126a);
-		break;
-	case CHIP_VERDE:
-		buffer[count++] = cpu_to_le32(0x0000124a);
-		break;
-	case CHIP_OLAND:
-		buffer[count++] = cpu_to_le32(0x00000082);
-		break;
-	case CHIP_HAINAN:
-		buffer[count++] = cpu_to_le32(0x00000000);
-		break;
-	default:
-		buffer[count++] = cpu_to_le32(0x00000000);
-		break;
-	}
+	buffer[count++] = cpu_to_le32(adev->gfx.config.rb_config[0][0].raster_config);
 
 	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0));
 	buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_END_CLEAR_STATE);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 5c8a7a48a4ad..a066c5eda135 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -48,6 +48,8 @@
 #include "oss/oss_2_0_d.h"
 #include "oss/oss_2_0_sh_mask.h"
 
+#define NUM_SIMD_PER_CU 0x4 /* missing from the gfx_7 IP headers */
+
 #define GFX7_NUM_GFX_RINGS     1
 #define GFX7_MEC_HPD_SIZE      2048
 
@@ -1819,6 +1821,22 @@ static void gfx_v7_0_setup_rb(struct amdgpu_device *adev)
 							adev->gfx.config.backend_enable_mask,
 							num_rb_pipes);
 	}
+
+	/* cache the values for userspace */
+	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
+		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+			gfx_v7_0_select_se_sh(adev, i, j, 0xffffffff);
+			adev->gfx.config.rb_config[i][j].rb_backend_disable =
+				RREG32(mmCC_RB_BACKEND_DISABLE);
+			adev->gfx.config.rb_config[i][j].user_rb_backend_disable =
+				RREG32(mmGC_USER_RB_BACKEND_DISABLE);
+			adev->gfx.config.rb_config[i][j].raster_config =
+				RREG32(mmPA_SC_RASTER_CONFIG);
+			adev->gfx.config.rb_config[i][j].raster_config_1 =
+				RREG32(mmPA_SC_RASTER_CONFIG_1);
+		}
+	}
+	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	mutex_unlock(&adev->grbm_idx_mutex);
 }
 
@@ -2069,7 +2087,7 @@ static int gfx_v7_0_ring_test_ring(struct amdgpu_ring *ring)
 		DRM_UDELAY(1);
 	}
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n", ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (scratch(0x%04X)=0x%08X)\n",
 			  ring->idx, scratch, tmp);
@@ -2236,7 +2254,7 @@ static void gfx_v7_0_ring_emit_fence_compute(struct amdgpu_ring *ring,
  */
 static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 				      struct amdgpu_ib *ib,
-				      unsigned vm_id, bool ctx_switch)
+				      unsigned vmid, bool ctx_switch)
 {
 	u32 header, control = 0;
 
@@ -2251,7 +2269,7 @@ static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	else
 		header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
 
-	control |= ib->length_dw | (vm_id << 24);
+	control |= ib->length_dw | (vmid << 24);
 
 	amdgpu_ring_write(ring, header);
 	amdgpu_ring_write(ring,
@@ -2265,9 +2283,9 @@ static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 
 static void gfx_v7_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
 					  struct amdgpu_ib *ib,
-					  unsigned vm_id, bool ctx_switch)
+					  unsigned vmid, bool ctx_switch)
 {
-	u32 control = INDIRECT_BUFFER_VALID | ib->length_dw | (vm_id << 24);
+	u32 control = INDIRECT_BUFFER_VALID | ib->length_dw | (vmid << 24);
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
 	amdgpu_ring_write(ring,
@@ -2349,7 +2367,7 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	}
 	tmp = RREG32(scratch);
 	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n",
@@ -2535,29 +2553,8 @@ static int gfx_v7_0_cp_gfx_start(struct amdgpu_device *adev)
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 2));
 	amdgpu_ring_write(ring, mmPA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START);
-	switch (adev->asic_type) {
-	case CHIP_BONAIRE:
-		amdgpu_ring_write(ring, 0x16000012);
-		amdgpu_ring_write(ring, 0x00000000);
-		break;
-	case CHIP_KAVERI:
-		amdgpu_ring_write(ring, 0x00000000); /* XXX */
-		amdgpu_ring_write(ring, 0x00000000);
-		break;
-	case CHIP_KABINI:
-	case CHIP_MULLINS:
-		amdgpu_ring_write(ring, 0x00000000); /* XXX */
-		amdgpu_ring_write(ring, 0x00000000);
-		break;
-	case CHIP_HAWAII:
-		amdgpu_ring_write(ring, 0x3a00161a);
-		amdgpu_ring_write(ring, 0x0000002e);
-		break;
-	default:
-		amdgpu_ring_write(ring, 0x00000000);
-		amdgpu_ring_write(ring, 0x00000000);
-		break;
-	}
+	amdgpu_ring_write(ring, adev->gfx.config.rb_config[0][0].raster_config);
+	amdgpu_ring_write(ring, adev->gfx.config.rb_config[0][0].raster_config_1);
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_PREAMBLE_CNTL, 0));
 	amdgpu_ring_write(ring, PACKET3_PREAMBLE_END_CLEAR_STATE);
@@ -3242,19 +3239,19 @@ static void gfx_v7_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using the CP (CIK).
  */
 static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vm_id, uint64_t pd_addr)
+					unsigned vmid, uint64_t pd_addr)
 {
 	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
 				 WRITE_DATA_DST_SEL(0)));
-	if (vm_id < 8) {
+	if (vmid < 8) {
 		amdgpu_ring_write(ring,
-				  (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id));
+				  (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vmid));
 	} else {
 		amdgpu_ring_write(ring,
-				  (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vm_id - 8));
+				  (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vmid - 8));
 	}
 	amdgpu_ring_write(ring, 0);
 	amdgpu_ring_write(ring, pd_addr >> 12);
@@ -3265,7 +3262,7 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 				 WRITE_DATA_DST_SEL(0)));
 	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST);
 	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vmid);
 
 	/* wait for the invalidate to complete */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
@@ -5282,6 +5279,11 @@ static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev)
 
 	cu_info->number = active_cu_number;
 	cu_info->ao_cu_mask = ao_cu_mask;
+	cu_info->simd_per_cu = NUM_SIMD_PER_CU;
+	cu_info->max_waves_per_simd = 10;
+	cu_info->max_scratch_slots_per_cu = 32;
+	cu_info->wave_front_size = 64;
+	cu_info->lds_size = 64;
 }
 
 const struct amdgpu_ip_block_version gfx_v7_0_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 9ecdf621a74a..4e694ae9f308 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -679,55 +679,55 @@ static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_TOPAZ:
-		amdgpu_program_register_sequence(adev,
-						 iceland_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(iceland_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_iceland_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_iceland_a11));
-		amdgpu_program_register_sequence(adev,
-						 iceland_golden_common_all,
-						 (const u32)ARRAY_SIZE(iceland_golden_common_all));
+		amdgpu_device_program_register_sequence(adev,
+							iceland_mgcg_cgcg_init,
+							ARRAY_SIZE(iceland_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_iceland_a11,
+							ARRAY_SIZE(golden_settings_iceland_a11));
+		amdgpu_device_program_register_sequence(adev,
+							iceland_golden_common_all,
+							ARRAY_SIZE(iceland_golden_common_all));
 		break;
 	case CHIP_FIJI:
-		amdgpu_program_register_sequence(adev,
-						 fiji_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(fiji_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_fiji_a10,
-						 (const u32)ARRAY_SIZE(golden_settings_fiji_a10));
-		amdgpu_program_register_sequence(adev,
-						 fiji_golden_common_all,
-						 (const u32)ARRAY_SIZE(fiji_golden_common_all));
+		amdgpu_device_program_register_sequence(adev,
+							fiji_mgcg_cgcg_init,
+							ARRAY_SIZE(fiji_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_fiji_a10,
+							ARRAY_SIZE(golden_settings_fiji_a10));
+		amdgpu_device_program_register_sequence(adev,
+							fiji_golden_common_all,
+							ARRAY_SIZE(fiji_golden_common_all));
 		break;
 
 	case CHIP_TONGA:
-		amdgpu_program_register_sequence(adev,
-						 tonga_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(tonga_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_tonga_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_tonga_a11));
-		amdgpu_program_register_sequence(adev,
-						 tonga_golden_common_all,
-						 (const u32)ARRAY_SIZE(tonga_golden_common_all));
+		amdgpu_device_program_register_sequence(adev,
+							tonga_mgcg_cgcg_init,
+							ARRAY_SIZE(tonga_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_tonga_a11,
+							ARRAY_SIZE(golden_settings_tonga_a11));
+		amdgpu_device_program_register_sequence(adev,
+							tonga_golden_common_all,
+							ARRAY_SIZE(tonga_golden_common_all));
 		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_polaris11_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_polaris11_a11));
-		amdgpu_program_register_sequence(adev,
-						 polaris11_golden_common_all,
-						 (const u32)ARRAY_SIZE(polaris11_golden_common_all));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_polaris11_a11,
+							ARRAY_SIZE(golden_settings_polaris11_a11));
+		amdgpu_device_program_register_sequence(adev,
+							polaris11_golden_common_all,
+							ARRAY_SIZE(polaris11_golden_common_all));
 		break;
 	case CHIP_POLARIS10:
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_polaris10_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_polaris10_a11));
-		amdgpu_program_register_sequence(adev,
-						 polaris10_golden_common_all,
-						 (const u32)ARRAY_SIZE(polaris10_golden_common_all));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_polaris10_a11,
+							ARRAY_SIZE(golden_settings_polaris10_a11));
+		amdgpu_device_program_register_sequence(adev,
+							polaris10_golden_common_all,
+							ARRAY_SIZE(polaris10_golden_common_all));
 		WREG32_SMC(ixCG_ACLK_CNTL, 0x0000001C);
 		if (adev->pdev->revision == 0xc7 &&
 		    ((adev->pdev->subsystem_device == 0xb37 && adev->pdev->subsystem_vendor == 0x1002) ||
@@ -738,26 +738,26 @@ static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev)
 		}
 		break;
 	case CHIP_CARRIZO:
-		amdgpu_program_register_sequence(adev,
-						 cz_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(cz_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 cz_golden_settings_a11,
-						 (const u32)ARRAY_SIZE(cz_golden_settings_a11));
-		amdgpu_program_register_sequence(adev,
-						 cz_golden_common_all,
-						 (const u32)ARRAY_SIZE(cz_golden_common_all));
+		amdgpu_device_program_register_sequence(adev,
+							cz_mgcg_cgcg_init,
+							ARRAY_SIZE(cz_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							cz_golden_settings_a11,
+							ARRAY_SIZE(cz_golden_settings_a11));
+		amdgpu_device_program_register_sequence(adev,
+							cz_golden_common_all,
+							ARRAY_SIZE(cz_golden_common_all));
 		break;
 	case CHIP_STONEY:
-		amdgpu_program_register_sequence(adev,
-						 stoney_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(stoney_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 stoney_golden_settings_a11,
-						 (const u32)ARRAY_SIZE(stoney_golden_settings_a11));
-		amdgpu_program_register_sequence(adev,
-						 stoney_golden_common_all,
-						 (const u32)ARRAY_SIZE(stoney_golden_common_all));
+		amdgpu_device_program_register_sequence(adev,
+							stoney_mgcg_cgcg_init,
+							ARRAY_SIZE(stoney_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							stoney_golden_settings_a11,
+							ARRAY_SIZE(stoney_golden_settings_a11));
+		amdgpu_device_program_register_sequence(adev,
+							stoney_golden_common_all,
+							ARRAY_SIZE(stoney_golden_common_all));
 		break;
 	default:
 		break;
@@ -804,7 +804,7 @@ static int gfx_v8_0_ring_test_ring(struct amdgpu_ring *ring)
 		DRM_UDELAY(1);
 	}
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (scratch(0x%04X)=0x%08X)\n",
@@ -856,7 +856,7 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	}
 	tmp = RREG32(scratch);
 	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n",
@@ -2114,7 +2114,6 @@ static int gfx_v8_0_sw_fini(void *handle)
 	amdgpu_gfx_compute_mqd_sw_fini(adev);
 	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring, &adev->gfx.kiq.irq);
 	amdgpu_gfx_kiq_fini(adev);
-	amdgpu_bo_free_kernel(&adev->virt.csa_obj, &adev->virt.csa_vmid0_addr, NULL);
 
 	gfx_v8_0_mec_fini(adev);
 	gfx_v8_0_rlc_fini(adev);
@@ -3851,6 +3850,14 @@ static void gfx_v8_0_wait_for_rlc_serdes(struct amdgpu_device *adev)
 					break;
 				udelay(1);
 			}
+			if (k == adev->usec_timeout) {
+				gfx_v8_0_select_se_sh(adev, 0xffffffff,
+						      0xffffffff, 0xffffffff);
+				mutex_unlock(&adev->grbm_idx_mutex);
+				DRM_INFO("Timeout wait for RLC serdes %u,%u\n",
+					 i, j);
+				return;
+			}
 		}
 	}
 	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
@@ -4305,37 +4312,8 @@ static int gfx_v8_0_cp_gfx_start(struct amdgpu_device *adev)
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 2));
 	amdgpu_ring_write(ring, mmPA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START);
-	switch (adev->asic_type) {
-	case CHIP_TONGA:
-	case CHIP_POLARIS10:
-		amdgpu_ring_write(ring, 0x16000012);
-		amdgpu_ring_write(ring, 0x0000002A);
-		break;
-	case CHIP_POLARIS11:
-	case CHIP_POLARIS12:
-		amdgpu_ring_write(ring, 0x16000012);
-		amdgpu_ring_write(ring, 0x00000000);
-		break;
-	case CHIP_FIJI:
-		amdgpu_ring_write(ring, 0x3a00161a);
-		amdgpu_ring_write(ring, 0x0000002e);
-		break;
-	case CHIP_CARRIZO:
-		amdgpu_ring_write(ring, 0x00000002);
-		amdgpu_ring_write(ring, 0x00000000);
-		break;
-	case CHIP_TOPAZ:
-		amdgpu_ring_write(ring, adev->gfx.config.num_rbs == 1 ?
-				0x00000000 : 0x00000002);
-		amdgpu_ring_write(ring, 0x00000000);
-		break;
-	case CHIP_STONEY:
-		amdgpu_ring_write(ring, 0x00000000);
-		amdgpu_ring_write(ring, 0x00000000);
-		break;
-	default:
-		BUG();
-	}
+	amdgpu_ring_write(ring, adev->gfx.config.rb_config[0][0].raster_config);
+	amdgpu_ring_write(ring, adev->gfx.config.rb_config[0][0].raster_config_1);
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_PREAMBLE_CNTL, 0));
 	amdgpu_ring_write(ring, PACKET3_PREAMBLE_END_CLEAR_STATE);
@@ -4816,7 +4794,7 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
 
 	gfx_v8_0_kiq_setting(ring);
 
-	if (adev->in_sriov_reset) { /* for GPU_RESET case */
+	if (adev->in_gpu_reset) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(struct vi_mqd_allocation));
@@ -4853,7 +4831,7 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)
 	struct vi_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = ring - &adev->gfx.compute_ring[0];
 
-	if (!adev->in_sriov_reset && !adev->gfx.in_suspend) {
+	if (!adev->in_gpu_reset && !adev->gfx.in_suspend) {
 		memset((void *)mqd, 0, sizeof(struct vi_mqd_allocation));
 		((struct vi_mqd_allocation *)mqd)->dynamic_cu_mask = 0xFFFFFFFF;
 		((struct vi_mqd_allocation *)mqd)->dynamic_rb_mask = 0xFFFFFFFF;
@@ -4865,13 +4843,10 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(struct vi_mqd_allocation));
-	} else if (adev->in_sriov_reset) { /* for GPU_RESET case */
+	} else if (adev->in_gpu_reset) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(struct vi_mqd_allocation));
-		/* reset ring buffer */
-		ring->wptr = 0;
-		amdgpu_ring_clear_ring(ring);
 	} else {
 		amdgpu_ring_clear_ring(ring);
 	}
@@ -4946,6 +4921,13 @@ static int gfx_v8_0_kiq_resume(struct amdgpu_device *adev)
 	/* Test KCQs */
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		ring = &adev->gfx.compute_ring[i];
+		if (adev->in_gpu_reset) {
+			/* move reset ring buffer to here to workaround
+			 * compute ring test failed
+			 */
+			ring->wptr = 0;
+			amdgpu_ring_clear_ring(ring);
+		}
 		ring->ready = true;
 		r = amdgpu_ring_test_ring(ring);
 		if (r)
@@ -5080,8 +5062,9 @@ static int gfx_v8_0_hw_fini(void *handle)
 	gfx_v8_0_cp_enable(adev, false);
 	gfx_v8_0_rlc_stop(adev);
 
-	amdgpu_set_powergating_state(adev,
-			AMD_IP_BLOCK_TYPE_GFX, AMD_PG_STATE_UNGATE);
+	amdgpu_device_ip_set_powergating_state(adev,
+					       AMD_IP_BLOCK_TYPE_GFX,
+					       AMD_PG_STATE_UNGATE);
 
 	return 0;
 }
@@ -5498,8 +5481,9 @@ static int gfx_v8_0_late_init(void *handle)
 	if (r)
 		return r;
 
-	amdgpu_set_powergating_state(adev,
-			AMD_IP_BLOCK_TYPE_GFX, AMD_PG_STATE_GATE);
+	amdgpu_device_ip_set_powergating_state(adev,
+					       AMD_IP_BLOCK_TYPE_GFX,
+					       AMD_PG_STATE_GATE);
 
 	return 0;
 }
@@ -5510,10 +5494,10 @@ static void gfx_v8_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *ade
 	if ((adev->asic_type == CHIP_POLARIS11) ||
 	    (adev->asic_type == CHIP_POLARIS12))
 		/* Send msg to SMU via Powerplay */
-		amdgpu_set_powergating_state(adev,
-					     AMD_IP_BLOCK_TYPE_SMC,
-					     enable ?
-					     AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE);
+		amdgpu_device_ip_set_powergating_state(adev,
+						       AMD_IP_BLOCK_TYPE_SMC,
+						       enable ?
+						       AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE);
 
 	WREG32_FIELD(RLC_PG_CNTL, STATIC_PER_CU_PG_ENABLE, enable ? 1 : 0);
 }
@@ -6261,7 +6245,7 @@ static void gfx_v8_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
 
 static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 				      struct amdgpu_ib *ib,
-				      unsigned vm_id, bool ctx_switch)
+				      unsigned vmid, bool ctx_switch)
 {
 	u32 header, control = 0;
 
@@ -6270,7 +6254,7 @@ static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	else
 		header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
 
-	control |= ib->length_dw | (vm_id << 24);
+	control |= ib->length_dw | (vmid << 24);
 
 	if (amdgpu_sriov_vf(ring->adev) && (ib->flags & AMDGPU_IB_FLAG_PREEMPT)) {
 		control |= INDIRECT_BUFFER_PRE_ENB(1);
@@ -6291,9 +6275,9 @@ static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 
 static void gfx_v8_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
 					  struct amdgpu_ib *ib,
-					  unsigned vm_id, bool ctx_switch)
+					  unsigned vmid, bool ctx_switch)
 {
-	u32 control = INDIRECT_BUFFER_VALID | ib->length_dw | (vm_id << 24);
+	u32 control = INDIRECT_BUFFER_VALID | ib->length_dw | (vmid << 24);
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
 	amdgpu_ring_write(ring,
@@ -6344,7 +6328,7 @@ static void gfx_v8_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 }
 
 static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vm_id, uint64_t pd_addr)
+					unsigned vmid, uint64_t pd_addr)
 {
 	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
 
@@ -6352,12 +6336,12 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
 				 WRITE_DATA_DST_SEL(0)) |
 				 WR_CONFIRM);
-	if (vm_id < 8) {
+	if (vmid < 8) {
 		amdgpu_ring_write(ring,
-				  (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id));
+				  (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vmid));
 	} else {
 		amdgpu_ring_write(ring,
-				  (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vm_id - 8));
+				  (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vmid - 8));
 	}
 	amdgpu_ring_write(ring, 0);
 	amdgpu_ring_write(ring, pd_addr >> 12);
@@ -6369,7 +6353,7 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 				 WRITE_DATA_DST_SEL(0)));
 	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST);
 	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vmid);
 
 	/* wait for the invalidate to complete */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
@@ -6490,10 +6474,10 @@ static void gfx_v8_0_hqd_set_priority(struct amdgpu_device *adev,
 	mutex_unlock(&adev->srbm_mutex);
 }
 static void gfx_v8_0_ring_set_priority_compute(struct amdgpu_ring *ring,
-					       enum amd_sched_priority priority)
+					       enum drm_sched_priority priority)
 {
 	struct amdgpu_device *adev = ring->adev;
-	bool acquire = priority == AMD_SCHED_PRIORITY_HIGH_HW;
+	bool acquire = priority == DRM_SCHED_PRIORITY_HIGH_HW;
 
 	if (ring->funcs->type != AMDGPU_RING_TYPE_COMPUTE)
 		return;
@@ -7132,6 +7116,11 @@ static void gfx_v8_0_get_cu_info(struct amdgpu_device *adev)
 
 	cu_info->number = active_cu_number;
 	cu_info->ao_cu_mask = ao_cu_mask;
+	cu_info->simd_per_cu = NUM_SIMD_PER_CU;
+	cu_info->max_waves_per_simd = 10;
+	cu_info->max_scratch_slots_per_cu = 32;
+	cu_info->wave_front_size = 64;
+	cu_info->lds_size = 64;
 }
 
 const struct amdgpu_ip_block_version gfx_v8_0_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index da43813d67a4..c06479615e8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -28,11 +28,10 @@
 #include "soc15.h"
 #include "soc15d.h"
 
-#include "vega10/soc15ip.h"
-#include "vega10/GC/gc_9_0_offset.h"
-#include "vega10/GC/gc_9_0_sh_mask.h"
-#include "vega10/vega10_enum.h"
-#include "vega10/HDP/hdp_4_0_offset.h"
+#include "gc/gc_9_0_offset.h"
+#include "gc/gc_9_0_sh_mask.h"
+#include "vega10_enum.h"
+#include "hdp/hdp_4_0_offset.h"
 
 #include "soc15_common.h"
 #include "clearstate_gfx9.h"
@@ -65,152 +64,84 @@ MODULE_FIRMWARE("amdgpu/raven_mec.bin");
 MODULE_FIRMWARE("amdgpu/raven_mec2.bin");
 MODULE_FIRMWARE("amdgpu/raven_rlc.bin");
 
-static const struct amdgpu_gds_reg_offset amdgpu_gds_reg_offset[] =
-{
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID0),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID0) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID1_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID1_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID1),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID1) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID2_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID2_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID2),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID2) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID3_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID3_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID3),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID3) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID4_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID4_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID4),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID4) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID5_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID5_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID5),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID5) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID6_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID6_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID6),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID6) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID7_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID7_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID7),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID7) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID8_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID8_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID8),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID8) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID9_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID9_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID9),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID9) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID10_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID10_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID10),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID10) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID11_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID11_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID11),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID11) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID12_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID12_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID12),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID12)},
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID13_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID13_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID13),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID13) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID14_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID14_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID14),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID14) },
-	{ SOC15_REG_OFFSET(GC, 0, mmGDS_VMID15_BASE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_VMID15_SIZE),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID15),
-	  SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID15) }
+static const struct soc15_reg_golden golden_settings_gc_9_0[] =
+{
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPC_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPF_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPG_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG2, 0xf00fffff, 0x00000420),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_GPU_ID, 0x0000000f, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmIA_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_EVENT_CNTL_3, 0x00000003, 0x82400024),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE, 0x3fffffff, 0x00000001),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_0, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_1, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_2, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_PREWALKER_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_SPM_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSH_MEM_CONFIG, 0x00001000, 0x00001000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x0000000f, 0x01000107),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQC_CONFIG, 0x03000000, 0x020a2000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfffffeef, 0x010b0000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x4a2c0e68),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_LO, 0xffffffff, 0xb5d3f197),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_CACHE_INVALIDATION, 0x3fff3af3, 0x19200000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000003ff),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL, 0x08000000, 0x08000080)
 };
 
-static const u32 golden_settings_gc_9_0[] =
-{
-	SOC15_REG_OFFSET(GC, 0, mmCPC_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmCPF_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmCPG_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmDB_DEBUG2), 0xf00fffff, 0x00000420,
-	SOC15_REG_OFFSET(GC, 0, mmGB_GPU_ID), 0x0000000f, 0x00000000,
-	SOC15_REG_OFFSET(GC, 0, mmIA_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmPA_SC_BINNER_EVENT_CNTL_3), 0x00000003, 0x82400024,
-	SOC15_REG_OFFSET(GC, 0, mmPA_SC_ENHANCE), 0x3fffffff, 0x00000001,
-	SOC15_REG_OFFSET(GC, 0, mmPA_SC_LINE_STIPPLE_STATE), 0x0000ff0f, 0x00000000,
-	SOC15_REG_OFFSET(GC, 0, mmRLC_GPM_UTCL1_CNTL_0), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmRLC_GPM_UTCL1_CNTL_1), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmRLC_GPM_UTCL1_CNTL_2), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmRLC_PREWALKER_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG), 0x00001000, 0x00001000,
-	SOC15_REG_OFFSET(GC, 0, mmSPI_CONFIG_CNTL_1), 0x0000000f, 0x01000107,
-	SOC15_REG_OFFSET(GC, 0, mmSQC_CONFIG), 0x03000000, 0x020a2000,
-	SOC15_REG_OFFSET(GC, 0, mmTA_CNTL_AUX), 0xfffffeef, 0x010b0000,
-	SOC15_REG_OFFSET(GC, 0, mmTCP_CHAN_STEER_HI), 0xffffffff, 0x4a2c0e68,
-	SOC15_REG_OFFSET(GC, 0, mmTCP_CHAN_STEER_LO), 0xffffffff, 0xb5d3f197,
-	SOC15_REG_OFFSET(GC, 0, mmVGT_CACHE_INVALIDATION), 0x3fff3af3, 0x19200000,
-	SOC15_REG_OFFSET(GC, 0, mmVGT_GS_MAX_WAVE_ID), 0x00000fff, 0x000003ff,
-	SOC15_REG_OFFSET(GC, 0, mmWD_UTCL1_CNTL), 0x08000000, 0x08000080
-};
-
-static const u32 golden_settings_gc_9_0_vg10[] =
+static const struct soc15_reg_golden golden_settings_gc_9_0_vg10[] =
 {
-	SOC15_REG_OFFSET(GC, 0, mmCB_HW_CONTROL), 0x0000f000, 0x00012107,
-	SOC15_REG_OFFSET(GC, 0, mmCB_HW_CONTROL_3), 0x30000000, 0x10000000,
-	SOC15_REG_OFFSET(GC, 0, mmGB_ADDR_CONFIG), 0xffff77ff, 0x2a114042,
-	SOC15_REG_OFFSET(GC, 0, mmGB_ADDR_CONFIG_READ), 0xffff77ff, 0x2a114042,
-	SOC15_REG_OFFSET(GC, 0, mmPA_SC_ENHANCE_1), 0x00008000, 0x00048000,
-	SOC15_REG_OFFSET(GC, 0, mmRMI_UTCL1_CNTL2), 0x00030000, 0x00020000,
-	SOC15_REG_OFFSET(GC, 0, mmTD_CNTL), 0x00001800, 0x00000800
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL, 0x0000f000, 0x00012107),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_3, 0x30000000, 0x10000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0xffff77ff, 0x2a114042),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG_READ, 0xffff77ff, 0x2a114042),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_1, 0x00008000, 0x00048000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_UTCL1_CNTL2, 0x00030000, 0x00020000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x00001800, 0x00000800)
 };
 
-static const u32 golden_settings_gc_9_1[] =
-{
-	SOC15_REG_OFFSET(GC, 0, mmCB_HW_CONTROL), 0xfffdf3cf, 0x00014104,
-	SOC15_REG_OFFSET(GC, 0, mmCPC_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmCPF_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmCPG_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmDB_DEBUG2), 0xf00fffff, 0x00000420,
-	SOC15_REG_OFFSET(GC, 0, mmGB_GPU_ID), 0x0000000f, 0x00000000,
-	SOC15_REG_OFFSET(GC, 0, mmIA_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmPA_SC_BINNER_EVENT_CNTL_3), 0x00000003, 0x82400024,
-	SOC15_REG_OFFSET(GC, 0, mmPA_SC_ENHANCE), 0x3fffffff, 0x00000001,
-	SOC15_REG_OFFSET(GC, 0, mmPA_SC_LINE_STIPPLE_STATE), 0x0000ff0f, 0x00000000,
-	SOC15_REG_OFFSET(GC, 0, mmRLC_GPM_UTCL1_CNTL_0), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmRLC_GPM_UTCL1_CNTL_1), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmRLC_GPM_UTCL1_CNTL_2), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmRLC_PREWALKER_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_UTCL1_CNTL), 0x08000000, 0x08000080,
-	SOC15_REG_OFFSET(GC, 0, mmTA_CNTL_AUX), 0xfffffeef, 0x010b0000,
-	SOC15_REG_OFFSET(GC, 0, mmTCP_CHAN_STEER_HI), 0xffffffff, 0x00000000,
-	SOC15_REG_OFFSET(GC, 0, mmTCP_CHAN_STEER_LO), 0xffffffff, 0x00003120,
-	SOC15_REG_OFFSET(GC, 0, mmVGT_CACHE_INVALIDATION), 0x3fff3af3, 0x19200000,
-	SOC15_REG_OFFSET(GC, 0, mmVGT_GS_MAX_WAVE_ID), 0x00000fff, 0x000000ff,
-	SOC15_REG_OFFSET(GC, 0, mmWD_UTCL1_CNTL), 0x08000000, 0x08000080
+static const struct soc15_reg_golden golden_settings_gc_9_1[] =
+{
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL, 0xfffdf3cf, 0x00014104),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPC_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPF_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPG_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG2, 0xf00fffff, 0x00000420),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_GPU_ID, 0x0000000f, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmIA_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_EVENT_CNTL_3, 0x00000003, 0x82400024),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE, 0x3fffffff, 0x00000001),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_0, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_1, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_2, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_PREWALKER_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_SPM_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfffffeef, 0x010b0000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_LO, 0xffffffff, 0x00003120),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_CACHE_INVALIDATION, 0x3fff3af3, 0x19200000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000000ff),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL, 0x08000000, 0x08000080)
 };
 
-static const u32 golden_settings_gc_9_1_rv1[] =
+static const struct soc15_reg_golden golden_settings_gc_9_1_rv1[] =
 {
-	SOC15_REG_OFFSET(GC, 0, mmCB_HW_CONTROL_3), 0x30000000, 0x10000000,
-	SOC15_REG_OFFSET(GC, 0, mmGB_ADDR_CONFIG), 0xffff77ff, 0x24000042,
-	SOC15_REG_OFFSET(GC, 0, mmGB_ADDR_CONFIG_READ), 0xffff77ff, 0x24000042,
-	SOC15_REG_OFFSET(GC, 0, mmPA_SC_ENHANCE_1), 0xffffffff, 0x04048000,
-	SOC15_REG_OFFSET(GC, 0, mmPA_SC_MODE_CNTL_1), 0x06000000, 0x06000000,
-	SOC15_REG_OFFSET(GC, 0, mmRMI_UTCL1_CNTL2), 0x00030000, 0x00020000,
-	SOC15_REG_OFFSET(GC, 0, mmTD_CNTL), 0x01bd9f33, 0x00000800
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_3, 0x30000000, 0x10000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0xffff77ff, 0x24000042),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG_READ, 0xffff77ff, 0x24000042),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_1, 0xffffffff, 0x04048000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_MODE_CNTL_1, 0x06000000, 0x06000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_UTCL1_CNTL2, 0x00030000, 0x00020000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x01bd9f33, 0x00000800)
 };
 
-static const u32 golden_settings_gc_9_x_common[] =
+static const struct soc15_reg_golden golden_settings_gc_9_x_common[] =
 {
-	SOC15_REG_OFFSET(GC, 0, mmGRBM_CAM_INDEX), 0xffffffff, 0x00000000,
-	SOC15_REG_OFFSET(GC, 0, mmGRBM_CAM_DATA), 0xffffffff, 0x2544c382
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_INDEX, 0xffffffff, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x2544c382)
 };
 
 #define VEGA10_GB_ADDR_CONFIG_GOLDEN 0x2a114042
@@ -230,26 +161,26 @@ static void gfx_v9_0_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
-		amdgpu_program_register_sequence(adev,
+		soc15_program_register_sequence(adev,
 						 golden_settings_gc_9_0,
-						 (const u32)ARRAY_SIZE(golden_settings_gc_9_0));
-		amdgpu_program_register_sequence(adev,
+						 ARRAY_SIZE(golden_settings_gc_9_0));
+		soc15_program_register_sequence(adev,
 						 golden_settings_gc_9_0_vg10,
-						 (const u32)ARRAY_SIZE(golden_settings_gc_9_0_vg10));
+						 ARRAY_SIZE(golden_settings_gc_9_0_vg10));
 		break;
 	case CHIP_RAVEN:
-		amdgpu_program_register_sequence(adev,
+		soc15_program_register_sequence(adev,
 						 golden_settings_gc_9_1,
-						 (const u32)ARRAY_SIZE(golden_settings_gc_9_1));
-		amdgpu_program_register_sequence(adev,
+						 ARRAY_SIZE(golden_settings_gc_9_1));
+		soc15_program_register_sequence(adev,
 						 golden_settings_gc_9_1_rv1,
-						 (const u32)ARRAY_SIZE(golden_settings_gc_9_1_rv1));
+						 ARRAY_SIZE(golden_settings_gc_9_1_rv1));
 		break;
 	default:
 		break;
 	}
 
-	amdgpu_program_register_sequence(adev, golden_settings_gc_9_x_common,
+	soc15_program_register_sequence(adev, golden_settings_gc_9_x_common,
 					(const u32)ARRAY_SIZE(golden_settings_gc_9_x_common));
 }
 
@@ -327,7 +258,7 @@ static int gfx_v9_0_ring_test_ring(struct amdgpu_ring *ring)
 		DRM_UDELAY(1);
 	}
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (scratch(0x%04X)=0x%08X)\n",
@@ -379,7 +310,7 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
         }
         tmp = RREG32(scratch);
         if (tmp == 0xDEADBEEF) {
-                DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+                DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
                 r = 0;
         } else {
                 DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n",
@@ -1137,8 +1068,8 @@ static int gfx_v9_0_ngg_init(struct amdgpu_device *adev)
 	adev->gfx.ngg.gds_reserve_size = ALIGN(5 * 4, 0x40);
 	adev->gds.mem.total_size -= adev->gfx.ngg.gds_reserve_size;
 	adev->gds.mem.gfx_partition_size -= adev->gfx.ngg.gds_reserve_size;
-	adev->gfx.ngg.gds_reserve_addr = amdgpu_gds_reg_offset[0].mem_base;
-	adev->gfx.ngg.gds_reserve_addr += adev->gds.mem.gfx_partition_size;
+	adev->gfx.ngg.gds_reserve_addr = RREG32_SOC15(GC, 0, mmGDS_VMID0_BASE);
+	adev->gfx.ngg.gds_reserve_addr += RREG32_SOC15(GC, 0, mmGDS_VMID0_SIZE);
 
 	/* Primitive Buffer */
 	r = gfx_v9_0_ngg_create_buf(adev, &adev->gfx.ngg.buf[NGG_PRIM],
@@ -1243,23 +1174,24 @@ static int gfx_v9_0_ngg_en(struct amdgpu_device *adev)
 	}
 
 	gfx_v9_0_write_data_to_reg(ring, 0, false,
-				   amdgpu_gds_reg_offset[0].mem_size,
+				   SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_SIZE),
 			           (adev->gds.mem.total_size +
 				    adev->gfx.ngg.gds_reserve_size) >>
 				   AMDGPU_GDS_SHIFT);
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_DMA_DATA, 5));
 	amdgpu_ring_write(ring, (PACKET3_DMA_DATA_CP_SYNC |
+				PACKET3_DMA_DATA_DST_SEL(1) |
 				PACKET3_DMA_DATA_SRC_SEL(2)));
 	amdgpu_ring_write(ring, 0);
 	amdgpu_ring_write(ring, 0);
 	amdgpu_ring_write(ring, adev->gfx.ngg.gds_reserve_addr);
 	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, adev->gfx.ngg.gds_reserve_size);
-
+	amdgpu_ring_write(ring, PACKET3_DMA_DATA_CMD_RAW_WAIT |
+				adev->gfx.ngg.gds_reserve_size);
 
 	gfx_v9_0_write_data_to_reg(ring, 0, false,
-				   amdgpu_gds_reg_offset[0].mem_size, 0);
+				   SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_SIZE), 0);
 
 	amdgpu_ring_commit(ring);
 
@@ -1464,7 +1396,6 @@ static int gfx_v9_0_sw_fini(void *handle)
 	amdgpu_gfx_compute_mqd_sw_fini(adev);
 	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring, &adev->gfx.kiq.irq);
 	amdgpu_gfx_kiq_fini(adev);
-	amdgpu_bo_free_kernel(&adev->virt.csa_obj, &adev->virt.csa_vmid0_addr, NULL);
 
 	gfx_v9_0_mec_fini(adev);
 	gfx_v9_0_ngg_fini(adev);
@@ -1596,14 +1527,21 @@ static void gfx_v9_0_gpu_init(struct amdgpu_device *adev)
 	/* XXX SH_MEM regs */
 	/* where to put LDS, scratch, GPUVM in FSA64 space */
 	mutex_lock(&adev->srbm_mutex);
-	for (i = 0; i < 16; i++) {
+	for (i = 0; i < adev->vm_manager.id_mgr[AMDGPU_GFXHUB].num_ids; i++) {
 		soc15_grbm_select(adev, 0, 0, 0, i);
 		/* CP and shaders */
-		tmp = 0;
-		tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
-				    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
-		WREG32_SOC15(GC, 0, mmSH_MEM_CONFIG, tmp);
-		WREG32_SOC15(GC, 0, mmSH_MEM_BASES, 0);
+		if (i == 0) {
+			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
+					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
+			WREG32_SOC15(GC, 0, mmSH_MEM_CONFIG, tmp);
+			WREG32_SOC15(GC, 0, mmSH_MEM_BASES, 0);
+		} else {
+			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
+					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
+			WREG32_SOC15(GC, 0, mmSH_MEM_CONFIG, tmp);
+			tmp = adev->mc.shared_aperture_start >> 48;
+			WREG32_SOC15(GC, 0, mmSH_MEM_BASES, tmp);
+		}
 	}
 	soc15_grbm_select(adev, 0, 0, 0, 0);
 
@@ -1645,6 +1583,14 @@ static void gfx_v9_0_wait_for_rlc_serdes(struct amdgpu_device *adev)
 					break;
 				udelay(1);
 			}
+			if (k == adev->usec_timeout) {
+				gfx_v9_0_select_se_sh(adev, 0xffffffff,
+						      0xffffffff, 0xffffffff);
+				mutex_unlock(&adev->grbm_idx_mutex);
+				DRM_INFO("Timeout wait for RLC serdes %u,%u\n",
+					 i, j);
+				return;
+			}
 		}
 	}
 	gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
@@ -2467,7 +2413,7 @@ static int gfx_v9_0_kiq_kcq_enable(struct amdgpu_device *adev)
 				  PACKET3_MAP_QUEUES_PIPE(ring->pipe) |
 				  PACKET3_MAP_QUEUES_ME((ring->me == 1 ? 0 : 1)) |
 				  PACKET3_MAP_QUEUES_QUEUE_TYPE(0) | /*queue_type: normal compute queue */
-				  PACKET3_MAP_QUEUES_ALLOC_FORMAT(1) | /* alloc format: all_on_one_pipe */
+				  PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) | /* alloc format: all_on_one_pipe */
 				  PACKET3_MAP_QUEUES_ENGINE_SEL(0) | /* engine_sel: compute */
 				  PACKET3_MAP_QUEUES_NUM_QUEUES(1)); /* num_queues: must be 1 */
 		amdgpu_ring_write(kiq_ring, PACKET3_MAP_QUEUES_DOORBELL_OFFSET(ring->doorbell_index));
@@ -2749,7 +2695,7 @@ static int gfx_v9_0_kiq_init_queue(struct amdgpu_ring *ring)
 
 	gfx_v9_0_kiq_setting(ring);
 
-	if (adev->in_sriov_reset) { /* for GPU_RESET case */
+	if (adev->in_gpu_reset) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(struct v9_mqd_allocation));
@@ -2787,7 +2733,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)
 	struct v9_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = ring - &adev->gfx.compute_ring[0];
 
-	if (!adev->in_sriov_reset && !adev->gfx.in_suspend) {
+	if (!adev->in_gpu_reset && !adev->gfx.in_suspend) {
 		memset((void *)mqd, 0, sizeof(struct v9_mqd_allocation));
 		((struct v9_mqd_allocation *)mqd)->dynamic_cu_mask = 0xFFFFFFFF;
 		((struct v9_mqd_allocation *)mqd)->dynamic_rb_mask = 0xFFFFFFFF;
@@ -2799,7 +2745,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(struct v9_mqd_allocation));
-	} else if (adev->in_sriov_reset) { /* for GPU_RESET case */
+	} else if (adev->in_gpu_reset) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(struct v9_mqd_allocation));
@@ -3139,6 +3085,8 @@ static void gfx_v9_0_ring_emit_gds_switch(struct amdgpu_ring *ring,
 					  uint32_t gws_base, uint32_t gws_size,
 					  uint32_t oa_base, uint32_t oa_size)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	gds_base = gds_base >> AMDGPU_GDS_SHIFT;
 	gds_size = gds_size >> AMDGPU_GDS_SHIFT;
 
@@ -3150,22 +3098,22 @@ static void gfx_v9_0_ring_emit_gds_switch(struct amdgpu_ring *ring,
 
 	/* GDS Base */
 	gfx_v9_0_write_data_to_reg(ring, 0, false,
-				   amdgpu_gds_reg_offset[vmid].mem_base,
+				   SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_BASE) + 2 * vmid,
 				   gds_base);
 
 	/* GDS Size */
 	gfx_v9_0_write_data_to_reg(ring, 0, false,
-				   amdgpu_gds_reg_offset[vmid].mem_size,
+				   SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_SIZE) + 2 * vmid,
 				   gds_size);
 
 	/* GWS */
 	gfx_v9_0_write_data_to_reg(ring, 0, false,
-				   amdgpu_gds_reg_offset[vmid].gws,
+				   SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID0) + vmid,
 				   gws_size << GDS_GWS_VMID0__SIZE__SHIFT | gws_base);
 
 	/* OA */
 	gfx_v9_0_write_data_to_reg(ring, 0, false,
-				   amdgpu_gds_reg_offset[vmid].oa,
+				   SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID0) + vmid,
 				   (1 << (oa_size + oa_base)) - (1 << oa_base));
 }
 
@@ -3610,13 +3558,9 @@ static void gfx_v9_0_ring_set_wptr_gfx(struct amdgpu_ring *ring)
 
 static void gfx_v9_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
 	u32 ref_and_mask, reg_mem_engine;
-	const struct nbio_hdp_flush_reg *nbio_hf_reg;
-
-	if (ring->adev->flags & AMD_IS_APU)
-		nbio_hf_reg = &nbio_v7_0_hdp_flush_reg;
-	else
-		nbio_hf_reg = &nbio_v6_1_hdp_flush_reg;
+	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio_funcs->hdp_flush_reg;
 
 	if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE) {
 		switch (ring->me) {
@@ -3636,20 +3580,22 @@ static void gfx_v9_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	}
 
 	gfx_v9_0_wait_reg_mem(ring, reg_mem_engine, 0, 1,
-			      nbio_hf_reg->hdp_flush_req_offset,
-			      nbio_hf_reg->hdp_flush_done_offset,
+			      adev->nbio_funcs->get_hdp_flush_req_offset(adev),
+			      adev->nbio_funcs->get_hdp_flush_done_offset(adev),
 			      ref_and_mask, ref_and_mask, 0x20);
 }
 
 static void gfx_v9_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	gfx_v9_0_write_data_to_reg(ring, 0, true,
 				   SOC15_REG_OFFSET(HDP, 0, mmHDP_READ_CACHE_INVALIDATE), 1);
 }
 
 static void gfx_v9_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
                                       struct amdgpu_ib *ib,
-                                      unsigned vm_id, bool ctx_switch)
+                                      unsigned vmid, bool ctx_switch)
 {
 	u32 header, control = 0;
 
@@ -3658,7 +3604,7 @@ static void gfx_v9_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	else
 		header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
 
-	control |= ib->length_dw | (vm_id << 24);
+	control |= ib->length_dw | (vmid << 24);
 
 	if (amdgpu_sriov_vf(ring->adev) && (ib->flags & AMDGPU_IB_FLAG_PREEMPT)) {
 		control |= INDIRECT_BUFFER_PRE_ENB(1);
@@ -3680,9 +3626,9 @@ BUG_ON(ib->gpu_addr & 0x3); /* Dword align */
 
 static void gfx_v9_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
                                           struct amdgpu_ib *ib,
-                                          unsigned vm_id, bool ctx_switch)
+                                          unsigned vmid, bool ctx_switch)
 {
-        u32 control = INDIRECT_BUFFER_VALID | ib->length_dw | (vm_id << 24);
+        u32 control = INDIRECT_BUFFER_VALID | ib->length_dw | (vmid << 24);
 
         amdgpu_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
 	BUG_ON(ib->gpu_addr & 0x3); /* Dword align */
@@ -3738,22 +3684,23 @@ static void gfx_v9_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 }
 
 static void gfx_v9_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vm_id, uint64_t pd_addr)
+					unsigned vmid, uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
 	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
-	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vm_id);
+	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vmid);
+	uint64_t flags = AMDGPU_PTE_VALID;
 	unsigned eng = ring->vm_inv_eng;
 
-	pd_addr = amdgpu_gart_get_vm_pde(ring->adev, pd_addr);
-	pd_addr |= AMDGPU_PTE_VALID;
+	amdgpu_gart_get_vm_pde(ring->adev, -1, &pd_addr, &flags);
+	pd_addr |= flags;
 
 	gfx_v9_0_write_data_to_reg(ring, usepfp, true,
-				   hub->ctx0_ptb_addr_lo32 + (2 * vm_id),
+				   hub->ctx0_ptb_addr_lo32 + (2 * vmid),
 				   lower_32_bits(pd_addr));
 
 	gfx_v9_0_write_data_to_reg(ring, usepfp, true,
-				   hub->ctx0_ptb_addr_hi32 + (2 * vm_id),
+				   hub->ctx0_ptb_addr_hi32 + (2 * vmid),
 				   upper_32_bits(pd_addr));
 
 	gfx_v9_0_write_data_to_reg(ring, usepfp, true,
@@ -3761,7 +3708,7 @@ static void gfx_v9_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 
 	/* wait for the invalidate to complete */
 	gfx_v9_0_wait_reg_mem(ring, 0, 0, 0, hub->vm_inv_eng0_ack +
-			      eng, 0, 1 << vm_id, 1 << vm_id, 0x20);
+			      eng, 0, 1 << vmid, 1 << vmid, 0x20);
 
 	/* compute doesn't have PFP */
 	if (usepfp) {
@@ -3804,6 +3751,8 @@ static void gfx_v9_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
 static void gfx_v9_0_ring_emit_fence_kiq(struct amdgpu_ring *ring, u64 addr,
 					 u64 seq, unsigned int flags)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	/* we only allocate 32bit for each seq wb address */
 	BUG_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index c17996e18086..56f5fe4e2fee 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -23,11 +23,10 @@
 #include "amdgpu.h"
 #include "gfxhub_v1_0.h"
 
-#include "vega10/soc15ip.h"
-#include "vega10/GC/gc_9_0_offset.h"
-#include "vega10/GC/gc_9_0_sh_mask.h"
-#include "vega10/GC/gc_9_0_default.h"
-#include "vega10/vega10_enum.h"
+#include "gc/gc_9_0_offset.h"
+#include "gc/gc_9_0_sh_mask.h"
+#include "gc/gc_9_0_default.h"
+#include "vega10_enum.h"
 
 #include "soc15_common.h"
 
@@ -144,8 +143,15 @@ static void gfxhub_v1_0_init_cache_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmVM_L2_CNTL2, tmp);
 
 	tmp = mmVM_L2_CNTL3_DEFAULT;
-	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 9);
-	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	if (adev->mc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 	WREG32_SOC15(GC, 0, mmVM_L2_CNTL3, tmp);
 
 	tmp = mmVM_L2_CNTL4_DEFAULT;
@@ -183,31 +189,40 @@ static void gfxhub_v1_0_disable_identity_aperture(struct amdgpu_device *adev)
 
 static void gfxhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
 {
-	int i;
+	unsigned num_level, block_size;
 	uint32_t tmp;
+	int i;
+
+	num_level = adev->vm_manager.num_level;
+	block_size = adev->vm_manager.block_size;
+	if (adev->mc.translate_further)
+		num_level -= 1;
+	else
+		block_size -= 9;
 
 	for (i = 0; i <= 14; i++) {
 		tmp = RREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_CNTL, i);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, ENABLE_CONTEXT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_DEPTH,
-				    adev->vm_manager.num_level);
+				    num_level);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT,
+				    1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				VALID_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    VALID_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				READ_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    READ_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				PAGE_TABLE_BLOCK_SIZE,
-				adev->vm_manager.block_size - 9);
+				    PAGE_TABLE_BLOCK_SIZE,
+				    block_size);
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index f4603a7c8ef3..8e28270d1ea9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -222,13 +222,8 @@ static void gmc_v6_0_vram_gtt_location(struct amdgpu_device *adev,
 	u64 base = RREG32(mmMC_VM_FB_LOCATION) & 0xFFFF;
 	base <<= 24;
 
-	if (mc->mc_vram_size > 0xFFC0000000ULL) {
-		dev_warn(adev->dev, "limiting VRAM\n");
-		mc->real_vram_size = 0xFFC0000000ULL;
-		mc->mc_vram_size = 0xFFC0000000ULL;
-	}
-	amdgpu_vram_location(adev, &adev->mc, base);
-	amdgpu_gart_location(adev, mc);
+	amdgpu_device_vram_location(adev, &adev->mc, base);
+	amdgpu_device_gart_location(adev, mc);
 }
 
 static void gmc_v6_0_mc_program(struct amdgpu_device *adev)
@@ -283,6 +278,7 @@ static int gmc_v6_0_mc_init(struct amdgpu_device *adev)
 
 	u32 tmp;
 	int chansize, numchan;
+	int r;
 
 	tmp = RREG32(mmMC_ARB_RAMCFG);
 	if (tmp & (1 << 11)) {
@@ -324,12 +320,17 @@ static int gmc_v6_0_mc_init(struct amdgpu_device *adev)
 		break;
 	}
 	adev->mc.vram_width = numchan * chansize;
-	/* Could aper size report 0 ? */
-	adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
-	adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
 	/* size in MB on si */
 	adev->mc.mc_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
 	adev->mc.real_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
+
+	if (!(adev->flags & AMD_IS_APU)) {
+		r = amdgpu_device_resize_fb_bar(adev);
+		if (r)
+			return r;
+	}
+	adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
+	adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
 	adev->mc.visible_vram_size = adev->mc.aper_size;
 
 	/* set the gart size */
@@ -394,10 +395,10 @@ static uint64_t gmc_v6_0_get_vm_pte_flags(struct amdgpu_device *adev,
 	return pte_flag;
 }
 
-static uint64_t gmc_v6_0_get_vm_pde(struct amdgpu_device *adev, uint64_t addr)
+static void gmc_v6_0_get_vm_pde(struct amdgpu_device *adev, int level,
+				uint64_t *addr, uint64_t *flags)
 {
-	BUG_ON(addr & 0xFFFFFF0000000FFFULL);
-	return addr;
+	BUG_ON(*addr & 0xFFFFFF0000000FFFULL);
 }
 
 static void gmc_v6_0_set_fault_enable_default(struct amdgpu_device *adev,
@@ -831,8 +832,7 @@ static int gmc_v6_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	amdgpu_vm_adjust_size(adev, 64, 9);
-	adev->vm_manager.max_pfn = adev->vm_manager.vm_size << 18;
+	amdgpu_vm_adjust_size(adev, 64, 9, 1, 40);
 
 	adev->mc.mc_mask = 0xffffffffffULL;
 
@@ -877,7 +877,6 @@ static int gmc_v6_0_sw_init(void *handle)
 	 * amdkfd will use VMIDs 8-15
 	 */
 	adev->vm_manager.id_mgr[0].num_ids = AMDGPU_NUM_OF_VMIDS;
-	adev->vm_manager.num_level = 1;
 	amdgpu_vm_manager_init(adev);
 
 	/* base offset of vram pages */
@@ -897,9 +896,9 @@ static int gmc_v6_0_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
 	gmc_v6_0_gart_fini(adev);
-	amdgpu_gem_force_release(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->mc.fw);
 	adev->mc.fw = NULL;
@@ -957,7 +956,7 @@ static int gmc_v6_0_resume(void *handle)
 	if (r)
 		return r;
 
-	amdgpu_vm_reset_all_ids(adev);
+	amdgpu_vmid_reset_all(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index b0528ca9207b..86e9d682c59e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -67,12 +67,12 @@ static void gmc_v7_0_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_TOPAZ:
-		amdgpu_program_register_sequence(adev,
-						 iceland_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(iceland_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_iceland_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_iceland_a11));
+		amdgpu_device_program_register_sequence(adev,
+							iceland_mgcg_cgcg_init,
+							ARRAY_SIZE(iceland_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_iceland_a11,
+							ARRAY_SIZE(golden_settings_iceland_a11));
 		break;
 	default:
 		break;
@@ -240,14 +240,8 @@ static void gmc_v7_0_vram_gtt_location(struct amdgpu_device *adev,
 	u64 base = RREG32(mmMC_VM_FB_LOCATION) & 0xFFFF;
 	base <<= 24;
 
-	if (mc->mc_vram_size > 0xFFC0000000ULL) {
-		/* leave room for at least 1024M GTT */
-		dev_warn(adev->dev, "limiting VRAM\n");
-		mc->real_vram_size = 0xFFC0000000ULL;
-		mc->mc_vram_size = 0xFFC0000000ULL;
-	}
-	amdgpu_vram_location(adev, &adev->mc, base);
-	amdgpu_gart_location(adev, mc);
+	amdgpu_device_vram_location(adev, &adev->mc, base);
+	amdgpu_device_gart_location(adev, mc);
 }
 
 /**
@@ -322,6 +316,8 @@ static void gmc_v7_0_mc_program(struct amdgpu_device *adev)
  */
 static int gmc_v7_0_mc_init(struct amdgpu_device *adev)
 {
+	int r;
+
 	adev->mc.vram_width = amdgpu_atombios_get_vram_width(adev);
 	if (!adev->mc.vram_width) {
 		u32 tmp;
@@ -367,13 +363,18 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev)
 		}
 		adev->mc.vram_width = numchan * chansize;
 	}
-	/* Could aper size report 0 ? */
-	adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
-	adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
 	/* size in MB on si */
 	adev->mc.mc_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
 	adev->mc.real_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
 
+	if (!(adev->flags & AMD_IS_APU)) {
+		r = amdgpu_device_resize_fb_bar(adev);
+		if (r)
+			return r;
+	}
+	adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
+	adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
+
 #ifdef CONFIG_X86_64
 	if (adev->flags & AMD_IS_APU) {
 		adev->mc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22;
@@ -479,10 +480,10 @@ static uint64_t gmc_v7_0_get_vm_pte_flags(struct amdgpu_device *adev,
 	return pte_flag;
 }
 
-static uint64_t gmc_v7_0_get_vm_pde(struct amdgpu_device *adev, uint64_t addr)
+static void gmc_v7_0_get_vm_pde(struct amdgpu_device *adev, int level,
+				uint64_t *addr, uint64_t *flags)
 {
-	BUG_ON(addr & 0xFFFFFF0000000FFFULL);
-	return addr;
+	BUG_ON(*addr & 0xFFFFFF0000000FFFULL);
 }
 
 /**
@@ -970,8 +971,7 @@ static int gmc_v7_0_sw_init(void *handle)
 	 * Currently set to 4GB ((1 << 20) 4k pages).
 	 * Max GPUVM size for cayman and SI is 40 bits.
 	 */
-	amdgpu_vm_adjust_size(adev, 64, 9);
-	adev->vm_manager.max_pfn = adev->vm_manager.vm_size << 18;
+	amdgpu_vm_adjust_size(adev, 64, 9, 1, 40);
 
 	/* Set the internal MC address mask
 	 * This is the max address of the GPU's
@@ -1026,7 +1026,6 @@ static int gmc_v7_0_sw_init(void *handle)
 	 * amdkfd will use VMIDs 8-15
 	 */
 	adev->vm_manager.id_mgr[0].num_ids = AMDGPU_NUM_OF_VMIDS;
-	adev->vm_manager.num_level = 1;
 	amdgpu_vm_manager_init(adev);
 
 	/* base offset of vram pages */
@@ -1046,9 +1045,9 @@ static int gmc_v7_0_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
 	gmc_v7_0_gart_fini(adev);
-	amdgpu_gem_force_release(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->mc.fw);
 	adev->mc.fw = NULL;
@@ -1108,7 +1107,7 @@ static int gmc_v7_0_resume(void *handle)
 	if (r)
 		return r;
 
-	amdgpu_vm_reset_all_ids(adev);
+	amdgpu_vmid_reset_all(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index f368cfe2f585..9a813d834f1a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -120,44 +120,44 @@ static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_FIJI:
-		amdgpu_program_register_sequence(adev,
-						 fiji_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(fiji_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_fiji_a10,
-						 (const u32)ARRAY_SIZE(golden_settings_fiji_a10));
+		amdgpu_device_program_register_sequence(adev,
+							fiji_mgcg_cgcg_init,
+							ARRAY_SIZE(fiji_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_fiji_a10,
+							ARRAY_SIZE(golden_settings_fiji_a10));
 		break;
 	case CHIP_TONGA:
-		amdgpu_program_register_sequence(adev,
-						 tonga_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(tonga_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_tonga_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_tonga_a11));
+		amdgpu_device_program_register_sequence(adev,
+							tonga_mgcg_cgcg_init,
+							ARRAY_SIZE(tonga_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_tonga_a11,
+							ARRAY_SIZE(golden_settings_tonga_a11));
 		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_polaris11_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_polaris11_a11));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_polaris11_a11,
+							ARRAY_SIZE(golden_settings_polaris11_a11));
 		break;
 	case CHIP_POLARIS10:
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_polaris10_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_polaris10_a11));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_polaris10_a11,
+							ARRAY_SIZE(golden_settings_polaris10_a11));
 		break;
 	case CHIP_CARRIZO:
-		amdgpu_program_register_sequence(adev,
-						 cz_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(cz_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							cz_mgcg_cgcg_init,
+							ARRAY_SIZE(cz_mgcg_cgcg_init));
 		break;
 	case CHIP_STONEY:
-		amdgpu_program_register_sequence(adev,
-						 stoney_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(stoney_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_stoney_common,
-						 (const u32)ARRAY_SIZE(golden_settings_stoney_common));
+		amdgpu_device_program_register_sequence(adev,
+							stoney_mgcg_cgcg_init,
+							ARRAY_SIZE(stoney_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_stoney_common,
+							ARRAY_SIZE(golden_settings_stoney_common));
 		break;
 	default:
 		break;
@@ -405,14 +405,8 @@ static void gmc_v8_0_vram_gtt_location(struct amdgpu_device *adev,
 		base = RREG32(mmMC_VM_FB_LOCATION) & 0xFFFF;
 	base <<= 24;
 
-	if (mc->mc_vram_size > 0xFFC0000000ULL) {
-		/* leave room for at least 1024M GTT */
-		dev_warn(adev->dev, "limiting VRAM\n");
-		mc->real_vram_size = 0xFFC0000000ULL;
-		mc->mc_vram_size = 0xFFC0000000ULL;
-	}
-	amdgpu_vram_location(adev, &adev->mc, base);
-	amdgpu_gart_location(adev, mc);
+	amdgpu_device_vram_location(adev, &adev->mc, base);
+	amdgpu_device_gart_location(adev, mc);
 }
 
 /**
@@ -498,6 +492,8 @@ static void gmc_v8_0_mc_program(struct amdgpu_device *adev)
  */
 static int gmc_v8_0_mc_init(struct amdgpu_device *adev)
 {
+	int r;
+
 	adev->mc.vram_width = amdgpu_atombios_get_vram_width(adev);
 	if (!adev->mc.vram_width) {
 		u32 tmp;
@@ -543,13 +539,18 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev)
 		}
 		adev->mc.vram_width = numchan * chansize;
 	}
-	/* Could aper size report 0 ? */
-	adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
-	adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
 	/* size in MB on si */
 	adev->mc.mc_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
 	adev->mc.real_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
 
+	if (!(adev->flags & AMD_IS_APU)) {
+		r = amdgpu_device_resize_fb_bar(adev);
+		if (r)
+			return r;
+	}
+	adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
+	adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
+
 #ifdef CONFIG_X86_64
 	if (adev->flags & AMD_IS_APU) {
 		adev->mc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22;
@@ -676,10 +677,10 @@ static uint64_t gmc_v8_0_get_vm_pte_flags(struct amdgpu_device *adev,
 	return pte_flag;
 }
 
-static uint64_t gmc_v8_0_get_vm_pde(struct amdgpu_device *adev, uint64_t addr)
+static void gmc_v8_0_get_vm_pde(struct amdgpu_device *adev, int level,
+				uint64_t *addr, uint64_t *flags)
 {
-	BUG_ON(addr & 0xFFFFFF0000000FFFULL);
-	return addr;
+	BUG_ON(*addr & 0xFFFFFF0000000FFFULL);
 }
 
 /**
@@ -1067,8 +1068,7 @@ static int gmc_v8_0_sw_init(void *handle)
 	 * Currently set to 4GB ((1 << 20) 4k pages).
 	 * Max GPUVM size for cayman and SI is 40 bits.
 	 */
-	amdgpu_vm_adjust_size(adev, 64, 9);
-	adev->vm_manager.max_pfn = adev->vm_manager.vm_size << 18;
+	amdgpu_vm_adjust_size(adev, 64, 9, 1, 40);
 
 	/* Set the internal MC address mask
 	 * This is the max address of the GPU's
@@ -1123,7 +1123,6 @@ static int gmc_v8_0_sw_init(void *handle)
 	 * amdkfd will use VMIDs 8-15
 	 */
 	adev->vm_manager.id_mgr[0].num_ids = AMDGPU_NUM_OF_VMIDS;
-	adev->vm_manager.num_level = 1;
 	amdgpu_vm_manager_init(adev);
 
 	/* base offset of vram pages */
@@ -1143,9 +1142,9 @@ static int gmc_v8_0_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
 	gmc_v8_0_gart_fini(adev);
-	amdgpu_gem_force_release(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->mc.fw);
 	adev->mc.fw = NULL;
@@ -1213,7 +1212,7 @@ static int gmc_v8_0_resume(void *handle)
 	if (r)
 		return r;
 
-	amdgpu_vm_reset_all_ids(adev);
+	amdgpu_vmid_reset_all(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index c8f1aebeac7a..2719937e09d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -25,20 +25,19 @@
 #include "gmc_v9_0.h"
 #include "amdgpu_atomfirmware.h"
 
-#include "vega10/soc15ip.h"
-#include "vega10/HDP/hdp_4_0_offset.h"
-#include "vega10/HDP/hdp_4_0_sh_mask.h"
-#include "vega10/GC/gc_9_0_sh_mask.h"
-#include "vega10/DC/dce_12_0_offset.h"
-#include "vega10/DC/dce_12_0_sh_mask.h"
-#include "vega10/vega10_enum.h"
-#include "vega10/MMHUB/mmhub_1_0_offset.h"
-#include "vega10/ATHUB/athub_1_0_offset.h"
-
+#include "hdp/hdp_4_0_offset.h"
+#include "hdp/hdp_4_0_sh_mask.h"
+#include "gc/gc_9_0_sh_mask.h"
+#include "dce/dce_12_0_offset.h"
+#include "dce/dce_12_0_sh_mask.h"
+#include "vega10_enum.h"
+#include "mmhub/mmhub_1_0_offset.h"
+#include "athub/athub_1_0_offset.h"
+
+#include "soc15.h"
 #include "soc15_common.h"
+#include "umc/umc_6_0_sh_mask.h"
 
-#include "nbio_v6_1.h"
-#include "nbio_v7_0.h"
 #include "gfxhub_v1_0.h"
 #include "mmhub_v1_0.h"
 
@@ -73,16 +72,131 @@ static const u32 golden_settings_vega10_hdp[] =
 	0xf6e, 0x0fffffff, 0x00000000,
 };
 
-static const u32 golden_settings_mmhub_1_0_0[] =
+static const struct soc15_reg_golden golden_settings_mmhub_1_0_0[] =
 {
-	SOC15_REG_OFFSET(MMHUB, 0, mmDAGB1_WRCLI2), 0x00000007, 0xfe5fe0fa,
-	SOC15_REG_OFFSET(MMHUB, 0, mmMMEA1_DRAM_WR_CLI2GRP_MAP0), 0x00000030, 0x55555565
+	SOC15_REG_GOLDEN_VALUE(MMHUB, 0, mmDAGB1_WRCLI2, 0x00000007, 0xfe5fe0fa),
+	SOC15_REG_GOLDEN_VALUE(MMHUB, 0, mmMMEA1_DRAM_WR_CLI2GRP_MAP0, 0x00000030, 0x55555565)
 };
 
-static const u32 golden_settings_athub_1_0_0[] =
+static const struct soc15_reg_golden golden_settings_athub_1_0_0[] =
 {
-	SOC15_REG_OFFSET(ATHUB, 0, mmRPB_ARB_CNTL), 0x0000ff00, 0x00000800,
-	SOC15_REG_OFFSET(ATHUB, 0, mmRPB_ARB_CNTL2), 0x00ff00ff, 0x00080008
+	SOC15_REG_GOLDEN_VALUE(ATHUB, 0, mmRPB_ARB_CNTL, 0x0000ff00, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(ATHUB, 0, mmRPB_ARB_CNTL2, 0x00ff00ff, 0x00080008)
+};
+
+/* Ecc related register addresses, (BASE + reg offset) */
+/* Universal Memory Controller caps (may be fused). */
+/* UMCCH:UmcLocalCap */
+#define UMCLOCALCAPS_ADDR0	(0x00014306 + 0x00000000)
+#define UMCLOCALCAPS_ADDR1	(0x00014306 + 0x00000800)
+#define UMCLOCALCAPS_ADDR2	(0x00014306 + 0x00001000)
+#define UMCLOCALCAPS_ADDR3	(0x00014306 + 0x00001800)
+#define UMCLOCALCAPS_ADDR4	(0x00054306 + 0x00000000)
+#define UMCLOCALCAPS_ADDR5	(0x00054306 + 0x00000800)
+#define UMCLOCALCAPS_ADDR6	(0x00054306 + 0x00001000)
+#define UMCLOCALCAPS_ADDR7	(0x00054306 + 0x00001800)
+#define UMCLOCALCAPS_ADDR8	(0x00094306 + 0x00000000)
+#define UMCLOCALCAPS_ADDR9	(0x00094306 + 0x00000800)
+#define UMCLOCALCAPS_ADDR10	(0x00094306 + 0x00001000)
+#define UMCLOCALCAPS_ADDR11	(0x00094306 + 0x00001800)
+#define UMCLOCALCAPS_ADDR12	(0x000d4306 + 0x00000000)
+#define UMCLOCALCAPS_ADDR13	(0x000d4306 + 0x00000800)
+#define UMCLOCALCAPS_ADDR14	(0x000d4306 + 0x00001000)
+#define UMCLOCALCAPS_ADDR15	(0x000d4306 + 0x00001800)
+
+/* Universal Memory Controller Channel config. */
+/* UMCCH:UMC_CONFIG */
+#define UMCCH_UMC_CONFIG_ADDR0	(0x00014040 + 0x00000000)
+#define UMCCH_UMC_CONFIG_ADDR1	(0x00014040 + 0x00000800)
+#define UMCCH_UMC_CONFIG_ADDR2	(0x00014040 + 0x00001000)
+#define UMCCH_UMC_CONFIG_ADDR3	(0x00014040 + 0x00001800)
+#define UMCCH_UMC_CONFIG_ADDR4	(0x00054040 + 0x00000000)
+#define UMCCH_UMC_CONFIG_ADDR5	(0x00054040 + 0x00000800)
+#define UMCCH_UMC_CONFIG_ADDR6	(0x00054040 + 0x00001000)
+#define UMCCH_UMC_CONFIG_ADDR7	(0x00054040 + 0x00001800)
+#define UMCCH_UMC_CONFIG_ADDR8	(0x00094040 + 0x00000000)
+#define UMCCH_UMC_CONFIG_ADDR9	(0x00094040 + 0x00000800)
+#define UMCCH_UMC_CONFIG_ADDR10	(0x00094040 + 0x00001000)
+#define UMCCH_UMC_CONFIG_ADDR11	(0x00094040 + 0x00001800)
+#define UMCCH_UMC_CONFIG_ADDR12	(0x000d4040 + 0x00000000)
+#define UMCCH_UMC_CONFIG_ADDR13	(0x000d4040 + 0x00000800)
+#define UMCCH_UMC_CONFIG_ADDR14	(0x000d4040 + 0x00001000)
+#define UMCCH_UMC_CONFIG_ADDR15	(0x000d4040 + 0x00001800)
+
+/* Universal Memory Controller Channel Ecc config. */
+/* UMCCH:EccCtrl */
+#define UMCCH_ECCCTRL_ADDR0	(0x00014053 + 0x00000000)
+#define UMCCH_ECCCTRL_ADDR1	(0x00014053 + 0x00000800)
+#define UMCCH_ECCCTRL_ADDR2	(0x00014053 + 0x00001000)
+#define UMCCH_ECCCTRL_ADDR3	(0x00014053 + 0x00001800)
+#define UMCCH_ECCCTRL_ADDR4	(0x00054053 + 0x00000000)
+#define UMCCH_ECCCTRL_ADDR5	(0x00054053 + 0x00000800)
+#define UMCCH_ECCCTRL_ADDR6	(0x00054053 + 0x00001000)
+#define UMCCH_ECCCTRL_ADDR7	(0x00054053 + 0x00001800)
+#define UMCCH_ECCCTRL_ADDR8	(0x00094053 + 0x00000000)
+#define UMCCH_ECCCTRL_ADDR9	(0x00094053 + 0x00000800)
+#define UMCCH_ECCCTRL_ADDR10	(0x00094053 + 0x00001000)
+#define UMCCH_ECCCTRL_ADDR11	(0x00094053 + 0x00001800)
+#define UMCCH_ECCCTRL_ADDR12	(0x000d4053 + 0x00000000)
+#define UMCCH_ECCCTRL_ADDR13	(0x000d4053 + 0x00000800)
+#define UMCCH_ECCCTRL_ADDR14	(0x000d4053 + 0x00001000)
+#define UMCCH_ECCCTRL_ADDR15	(0x000d4053 + 0x00001800)
+
+static const uint32_t ecc_umclocalcap_addrs[] = {
+	UMCLOCALCAPS_ADDR0,
+	UMCLOCALCAPS_ADDR1,
+	UMCLOCALCAPS_ADDR2,
+	UMCLOCALCAPS_ADDR3,
+	UMCLOCALCAPS_ADDR4,
+	UMCLOCALCAPS_ADDR5,
+	UMCLOCALCAPS_ADDR6,
+	UMCLOCALCAPS_ADDR7,
+	UMCLOCALCAPS_ADDR8,
+	UMCLOCALCAPS_ADDR9,
+	UMCLOCALCAPS_ADDR10,
+	UMCLOCALCAPS_ADDR11,
+	UMCLOCALCAPS_ADDR12,
+	UMCLOCALCAPS_ADDR13,
+	UMCLOCALCAPS_ADDR14,
+	UMCLOCALCAPS_ADDR15,
+};
+
+static const uint32_t ecc_umcch_umc_config_addrs[] = {
+	UMCCH_UMC_CONFIG_ADDR0,
+	UMCCH_UMC_CONFIG_ADDR1,
+	UMCCH_UMC_CONFIG_ADDR2,
+	UMCCH_UMC_CONFIG_ADDR3,
+	UMCCH_UMC_CONFIG_ADDR4,
+	UMCCH_UMC_CONFIG_ADDR5,
+	UMCCH_UMC_CONFIG_ADDR6,
+	UMCCH_UMC_CONFIG_ADDR7,
+	UMCCH_UMC_CONFIG_ADDR8,
+	UMCCH_UMC_CONFIG_ADDR9,
+	UMCCH_UMC_CONFIG_ADDR10,
+	UMCCH_UMC_CONFIG_ADDR11,
+	UMCCH_UMC_CONFIG_ADDR12,
+	UMCCH_UMC_CONFIG_ADDR13,
+	UMCCH_UMC_CONFIG_ADDR14,
+	UMCCH_UMC_CONFIG_ADDR15,
+};
+
+static const uint32_t ecc_umcch_eccctrl_addrs[] = {
+	UMCCH_ECCCTRL_ADDR0,
+	UMCCH_ECCCTRL_ADDR1,
+	UMCCH_ECCCTRL_ADDR2,
+	UMCCH_ECCCTRL_ADDR3,
+	UMCCH_ECCCTRL_ADDR4,
+	UMCCH_ECCCTRL_ADDR5,
+	UMCCH_ECCCTRL_ADDR6,
+	UMCCH_ECCCTRL_ADDR7,
+	UMCCH_ECCCTRL_ADDR8,
+	UMCCH_ECCCTRL_ADDR9,
+	UMCCH_ECCCTRL_ADDR10,
+	UMCCH_ECCCTRL_ADDR11,
+	UMCCH_ECCCTRL_ADDR12,
+	UMCCH_ECCCTRL_ADDR13,
+	UMCCH_ECCCTRL_ADDR14,
+	UMCCH_ECCCTRL_ADDR15,
 };
 
 static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
@@ -134,7 +248,7 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 				struct amdgpu_irq_src *source,
 				struct amdgpu_iv_entry *entry)
 {
-	struct amdgpu_vmhub *hub = &adev->vmhub[entry->vm_id_src];
+	struct amdgpu_vmhub *hub = &adev->vmhub[entry->vmid_src];
 	uint32_t status = 0;
 	u64 addr;
 
@@ -148,9 +262,9 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 
 	if (printk_ratelimit()) {
 		dev_err(adev->dev,
-			"[%s] VMC page fault (src_id:%u ring:%u vm_id:%u pas_id:%u)\n",
-			entry->vm_id_src ? "mmhub" : "gfxhub",
-			entry->src_id, entry->ring_id, entry->vm_id,
+			"[%s] VMC page fault (src_id:%u ring:%u vmid:%u pas_id:%u)\n",
+			entry->vmid_src ? "mmhub" : "gfxhub",
+			entry->src_id, entry->ring_id, entry->vmid,
 			entry->pas_id);
 		dev_err(adev->dev, "  at page 0x%016llx from %d\n",
 			addr, entry->client_id);
@@ -174,13 +288,13 @@ static void gmc_v9_0_set_irq_funcs(struct amdgpu_device *adev)
 	adev->mc.vm_fault.funcs = &gmc_v9_0_irq_funcs;
 }
 
-static uint32_t gmc_v9_0_get_invalidate_req(unsigned int vm_id)
+static uint32_t gmc_v9_0_get_invalidate_req(unsigned int vmid)
 {
 	u32 req = 0;
 
-	/* invalidate using legacy mode on vm_id*/
+	/* invalidate using legacy mode on vmid*/
 	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ,
-			    PER_VMID_INVALIDATE_REQ, 1 << vm_id);
+			    PER_VMID_INVALIDATE_REQ, 1 << vmid);
 	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, FLUSH_TYPE, 0);
 	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PTES, 1);
 	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE0, 1);
@@ -216,10 +330,7 @@ static void gmc_v9_0_gart_flush_gpu_tlb(struct amdgpu_device *adev,
 	unsigned i, j;
 
 	/* flush hdp cache */
-	if (adev->flags & AMD_IS_APU)
-		nbio_v7_0_hdp_flush(adev);
-	else
-		nbio_v6_1_hdp_flush(adev);
+	adev->nbio_funcs->hdp_flush(adev);
 
 	spin_lock(&adev->mc.invalidate_lock);
 
@@ -358,11 +469,28 @@ static uint64_t gmc_v9_0_get_vm_pte_flags(struct amdgpu_device *adev,
 	return pte_flag;
 }
 
-static u64 gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, u64 addr)
+static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level,
+				uint64_t *addr, uint64_t *flags)
 {
-	addr = adev->vm_manager.vram_base_offset + addr - adev->mc.vram_start;
-	BUG_ON(addr & 0xFFFF00000000003FULL);
-	return addr;
+	if (!(*flags & AMDGPU_PDE_PTE))
+		*addr = adev->vm_manager.vram_base_offset + *addr -
+			adev->mc.vram_start;
+	BUG_ON(*addr & 0xFFFF00000000003FULL);
+
+	if (!adev->mc.translate_further)
+		return;
+
+	if (level == AMDGPU_VM_PDB1) {
+		/* Set the block fragment size */
+		if (!(*flags & AMDGPU_PDE_PTE))
+			*flags |= AMDGPU_PDE_BFS(0x9);
+
+	} else if (level == AMDGPU_VM_PDB0) {
+		if (*flags & AMDGPU_PDE_PTE)
+			*flags &= ~AMDGPU_PDE_PTE;
+		else
+			*flags |= AMDGPU_PTE_TF;
+	}
 }
 
 static const struct amdgpu_gart_funcs gmc_v9_0_gart_funcs = {
@@ -386,9 +514,96 @@ static int gmc_v9_0_early_init(void *handle)
 	gmc_v9_0_set_gart_funcs(adev);
 	gmc_v9_0_set_irq_funcs(adev);
 
+	adev->mc.shared_aperture_start = 0x2000000000000000ULL;
+	adev->mc.shared_aperture_end =
+		adev->mc.shared_aperture_start + (4ULL << 30) - 1;
+	adev->mc.private_aperture_start =
+		adev->mc.shared_aperture_end + 1;
+	adev->mc.private_aperture_end =
+		adev->mc.private_aperture_start + (4ULL << 30) - 1;
+
 	return 0;
 }
 
+static int gmc_v9_0_ecc_available(struct amdgpu_device *adev)
+{
+	uint32_t reg_val;
+	uint32_t reg_addr;
+	uint32_t field_val;
+	size_t i;
+	uint32_t fv2;
+	size_t lost_sheep;
+
+	DRM_DEBUG("ecc: gmc_v9_0_ecc_available()\n");
+
+	lost_sheep = 0;
+	for (i = 0; i < ARRAY_SIZE(ecc_umclocalcap_addrs); ++i) {
+		reg_addr = ecc_umclocalcap_addrs[i];
+		DRM_DEBUG("ecc: "
+			  "UMCCH_UmcLocalCap[%zu]: reg_addr: 0x%08x\n",
+			  i, reg_addr);
+		reg_val = RREG32(reg_addr);
+		field_val = REG_GET_FIELD(reg_val, UMCCH0_0_UmcLocalCap,
+					  EccDis);
+		DRM_DEBUG("ecc: "
+			  "reg_val: 0x%08x, "
+			  "EccDis: 0x%08x, ",
+			  reg_val, field_val);
+		if (field_val) {
+			DRM_ERROR("ecc: UmcLocalCap:EccDis is set.\n");
+			++lost_sheep;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(ecc_umcch_umc_config_addrs); ++i) {
+		reg_addr = ecc_umcch_umc_config_addrs[i];
+		DRM_DEBUG("ecc: "
+			  "UMCCH0_0_UMC_CONFIG[%zu]: reg_addr: 0x%08x",
+			  i, reg_addr);
+		reg_val = RREG32(reg_addr);
+		field_val = REG_GET_FIELD(reg_val, UMCCH0_0_UMC_CONFIG,
+					  DramReady);
+		DRM_DEBUG("ecc: "
+			  "reg_val: 0x%08x, "
+			  "DramReady: 0x%08x\n",
+			  reg_val, field_val);
+
+		if (!field_val) {
+			DRM_ERROR("ecc: UMC_CONFIG:DramReady is not set.\n");
+			++lost_sheep;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(ecc_umcch_eccctrl_addrs); ++i) {
+		reg_addr = ecc_umcch_eccctrl_addrs[i];
+		DRM_DEBUG("ecc: "
+			  "UMCCH_EccCtrl[%zu]: reg_addr: 0x%08x, ",
+			  i, reg_addr);
+		reg_val = RREG32(reg_addr);
+		field_val = REG_GET_FIELD(reg_val, UMCCH0_0_EccCtrl,
+					  WrEccEn);
+		fv2 = REG_GET_FIELD(reg_val, UMCCH0_0_EccCtrl,
+				    RdEccEn);
+		DRM_DEBUG("ecc: "
+			  "reg_val: 0x%08x, "
+			  "WrEccEn: 0x%08x, "
+			  "RdEccEn: 0x%08x\n",
+			  reg_val, field_val, fv2);
+
+		if (!field_val) {
+			DRM_DEBUG("ecc: WrEccEn is not set\n");
+			++lost_sheep;
+		}
+		if (!fv2) {
+			DRM_DEBUG("ecc: RdEccEn is not set\n");
+			++lost_sheep;
+		}
+	}
+
+	DRM_DEBUG("ecc: lost_sheep: %zu\n", lost_sheep);
+	return lost_sheep == 0;
+}
+
 static int gmc_v9_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -403,6 +618,7 @@ static int gmc_v9_0_late_init(void *handle)
 	 */
 	unsigned vm_inv_eng[AMDGPU_MAX_VMHUBS] = { 4, 4 };
 	unsigned i;
+	int r;
 
 	for(i = 0; i < adev->num_rings; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
@@ -418,6 +634,18 @@ static int gmc_v9_0_late_init(void *handle)
 	for(i = 0; i < AMDGPU_MAX_VMHUBS; ++i)
 		BUG_ON(vm_inv_eng[i] > 16);
 
+	if (adev->asic_type == CHIP_VEGA10) {
+		r = gmc_v9_0_ecc_available(adev);
+		if (r == 1) {
+			DRM_INFO("ECC is active.\n");
+		} else if (r == 0) {
+			DRM_INFO("ECC is not present.\n");
+		} else {
+			DRM_ERROR("gmc_v9_0_ecc_available() failed. r: %d\n", r);
+			return r;
+		}
+	}
+
 	return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
 }
 
@@ -427,8 +655,8 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
 	u64 base = 0;
 	if (!amdgpu_sriov_vf(adev))
 		base = mmhub_v1_0_get_fb_location(adev);
-	amdgpu_vram_location(adev, &adev->mc, base);
-	amdgpu_gart_location(adev, mc);
+	amdgpu_device_vram_location(adev, &adev->mc, base);
+	amdgpu_device_gart_location(adev, mc);
 	/* base offset of vram pages */
 	if (adev->flags & AMD_IS_APU)
 		adev->vm_manager.vram_base_offset = gfxhub_v1_0_get_mc_fb_offset(adev);
@@ -449,6 +677,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 {
 	u32 tmp;
 	int chansize, numchan;
+	int r;
 
 	adev->mc.vram_width = amdgpu_atomfirmware_get_vram_width(adev);
 	if (!adev->mc.vram_width) {
@@ -491,17 +720,21 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 		adev->mc.vram_width = numchan * chansize;
 	}
 
-	/* Could aper size report 0 ? */
-	adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
-	adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
 	/* size in MB on si */
 	adev->mc.mc_vram_size =
-		((adev->flags & AMD_IS_APU) ? nbio_v7_0_get_memsize(adev) :
-		 nbio_v6_1_get_memsize(adev)) * 1024ULL * 1024ULL;
+		adev->nbio_funcs->get_memsize(adev) * 1024ULL * 1024ULL;
 	adev->mc.real_vram_size = adev->mc.mc_vram_size;
-	adev->mc.visible_vram_size = adev->mc.aper_size;
+
+	if (!(adev->flags & AMD_IS_APU)) {
+		r = amdgpu_device_resize_fb_bar(adev);
+		if (r)
+			return r;
+	}
+	adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
+	adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
 
 	/* In case the PCI BAR is larger than the actual amount of vram */
+	adev->mc.visible_vram_size = adev->mc.aper_size;
 	if (adev->mc.visible_vram_size > adev->mc.real_vram_size)
 		adev->mc.visible_vram_size = adev->mc.real_vram_size;
 
@@ -558,14 +791,12 @@ static int gmc_v9_0_sw_init(void *handle)
 	case CHIP_RAVEN:
 		adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN;
 		if (adev->rev_id == 0x0 || adev->rev_id == 0x1) {
-			adev->vm_manager.vm_size = 1U << 18;
-			adev->vm_manager.block_size = 9;
-			adev->vm_manager.num_level = 3;
-			amdgpu_vm_set_fragment_size(adev, 9);
+			amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);
 		} else {
-			/* vm_size is 64GB for legacy 2-level page support */
-			amdgpu_vm_adjust_size(adev, 64, 9);
-			adev->vm_manager.num_level = 1;
+			/* vm_size is 128TB + 512GB for legacy 3-level page support */
+			amdgpu_vm_adjust_size(adev, 128 * 1024 + 512, 9, 2, 48);
+			adev->mc.translate_further =
+				adev->vm_manager.num_level > 1;
 		}
 		break;
 	case CHIP_VEGA10:
@@ -576,20 +807,12 @@ static int gmc_v9_0_sw_init(void *handle)
 		 * vm size is 256TB (48bit), maximum size of Vega10,
 		 * block size 512 (9bit)
 		 */
-		adev->vm_manager.vm_size = 1U << 18;
-		adev->vm_manager.block_size = 9;
-		adev->vm_manager.num_level = 3;
-		amdgpu_vm_set_fragment_size(adev, 9);
+		amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);
 		break;
 	default:
 		break;
 	}
 
-	DRM_INFO("vm size is %llu GB, block size is %u-bit,fragment size is %u-bit\n",
-			adev->vm_manager.vm_size,
-			adev->vm_manager.block_size,
-			adev->vm_manager.fragment_size);
-
 	/* This interrupt is VMC page fault.*/
 	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_VMC, 0,
 				&adev->mc.vm_fault);
@@ -599,8 +822,6 @@ static int gmc_v9_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	adev->vm_manager.max_pfn = adev->vm_manager.vm_size << 18;
-
 	/* Set the internal MC address mask
 	 * This is the max address of the GPU's
 	 * internal address space.
@@ -660,7 +881,7 @@ static int gmc_v9_0_sw_init(void *handle)
 }
 
 /**
- * gmc_v8_0_gart_fini - vm fini callback
+ * gmc_v9_0_gart_fini - vm fini callback
  *
  * @adev: amdgpu_device pointer
  *
@@ -676,9 +897,9 @@ static int gmc_v9_0_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
 	gmc_v9_0_gart_fini(adev);
-	amdgpu_gem_force_release(adev);
 	amdgpu_bo_fini(adev);
 
 	return 0;
@@ -686,19 +907,20 @@ static int gmc_v9_0_sw_fini(void *handle)
 
 static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev)
 {
+
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
-		amdgpu_program_register_sequence(adev,
+		soc15_program_register_sequence(adev,
 						golden_settings_mmhub_1_0_0,
-						(const u32)ARRAY_SIZE(golden_settings_mmhub_1_0_0));
-		amdgpu_program_register_sequence(adev,
+						ARRAY_SIZE(golden_settings_mmhub_1_0_0));
+		soc15_program_register_sequence(adev,
 						golden_settings_athub_1_0_0,
-						(const u32)ARRAY_SIZE(golden_settings_athub_1_0_0));
+						ARRAY_SIZE(golden_settings_athub_1_0_0));
 		break;
 	case CHIP_RAVEN:
-		amdgpu_program_register_sequence(adev,
+		soc15_program_register_sequence(adev,
 						golden_settings_athub_1_0_0,
-						(const u32)ARRAY_SIZE(golden_settings_athub_1_0_0));
+						ARRAY_SIZE(golden_settings_athub_1_0_0));
 		break;
 	default:
 		break;
@@ -716,9 +938,9 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
 	bool value;
 	u32 tmp;
 
-	amdgpu_program_register_sequence(adev,
-		golden_settings_vega10_hdp,
-		(const u32)ARRAY_SIZE(golden_settings_vega10_hdp));
+	amdgpu_device_program_register_sequence(adev,
+						golden_settings_vega10_hdp,
+						ARRAY_SIZE(golden_settings_vega10_hdp));
 
 	if (adev->gart.robj == NULL) {
 		dev_err(adev->dev, "No VRAM object for PCIE GART.\n");
@@ -751,10 +973,7 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
 	WREG32_SOC15(HDP, 0, mmHDP_HOST_PATH_CNTL, tmp);
 
 	/* After HDP is initialized, flush HDP.*/
-	if (adev->flags & AMD_IS_APU)
-		nbio_v7_0_hdp_flush(adev);
-	else
-		nbio_v6_1_hdp_flush(adev);
+	adev->nbio_funcs->hdp_flush(adev);
 
 	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS)
 		value = false;
@@ -839,7 +1058,7 @@ static int gmc_v9_0_resume(void *handle)
 	if (r)
 		return r;
 
-	amdgpu_vm_reset_all_ids(adev);
+	amdgpu_vmid_reset_all(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index bd592cb39f37..c4e4be3dd31d 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -259,7 +259,7 @@ static void iceland_ih_decode_iv(struct amdgpu_device *adev,
 	entry->src_id = dw[0] & 0xff;
 	entry->src_data[0] = dw[1] & 0xfffffff;
 	entry->ring_id = dw[2] & 0xff;
-	entry->vm_id = (dw[2] >> 8) & 0xff;
+	entry->vmid = (dw[2] >> 8) & 0xff;
 	entry->pas_id = (dw[2] >> 16) & 0xffff;
 
 	/* wptr/rptr are in bytes! */
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index f33d1ffdb20b..d9e9e52a0def 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -1682,8 +1682,8 @@ static void kv_dpm_powergate_uvd(void *handle, bool gate)
 
 	if (gate) {
 		/* stop the UVD block */
-		ret = amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
-							AMD_PG_STATE_GATE);
+		ret = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+							     AMD_PG_STATE_GATE);
 		kv_update_uvd_dpm(adev, gate);
 		if (pi->caps_uvd_pg)
 			/* power off the UVD block */
@@ -1695,8 +1695,8 @@ static void kv_dpm_powergate_uvd(void *handle, bool gate)
 			/* re-init the UVD block */
 		kv_update_uvd_dpm(adev, gate);
 
-		ret = amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
-							AMD_PG_STATE_UNGATE);
+		ret = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD,
+							     AMD_PG_STATE_UNGATE);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index cc21c4bdec27..ffd5b7ee49c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -23,14 +23,12 @@
 #include "amdgpu.h"
 #include "mmhub_v1_0.h"
 
-#include "vega10/soc15ip.h"
-#include "vega10/MMHUB/mmhub_1_0_offset.h"
-#include "vega10/MMHUB/mmhub_1_0_sh_mask.h"
-#include "vega10/MMHUB/mmhub_1_0_default.h"
-#include "vega10/ATHUB/athub_1_0_offset.h"
-#include "vega10/ATHUB/athub_1_0_sh_mask.h"
-#include "vega10/ATHUB/athub_1_0_default.h"
-#include "vega10/vega10_enum.h"
+#include "mmhub/mmhub_1_0_offset.h"
+#include "mmhub/mmhub_1_0_sh_mask.h"
+#include "mmhub/mmhub_1_0_default.h"
+#include "athub/athub_1_0_offset.h"
+#include "athub/athub_1_0_sh_mask.h"
+#include "vega10_enum.h"
 
 #include "soc15_common.h"
 
@@ -157,10 +155,15 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev)
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1);
 	WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL2, tmp);
 
-	tmp = mmVM_L2_CNTL3_DEFAULT;
-	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 9);
-	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
-	WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL3, tmp);
+	if (adev->mc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 
 	tmp = mmVM_L2_CNTL4_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL4, VMC_TAP_PDE_REQUEST_PHYSICAL, 0);
@@ -198,32 +201,40 @@ static void mmhub_v1_0_disable_identity_aperture(struct amdgpu_device *adev)
 
 static void mmhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
 {
-	int i;
+	unsigned num_level, block_size;
 	uint32_t tmp;
+	int i;
+
+	num_level = adev->vm_manager.num_level;
+	block_size = adev->vm_manager.block_size;
+	if (adev->mc.translate_further)
+		num_level -= 1;
+	else
+		block_size -= 9;
 
 	for (i = 0; i <= 14; i++) {
 		tmp = RREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_CNTL, i);
+		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, ENABLE_CONTEXT, 1);
+		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_DEPTH,
+				    num_level);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				ENABLE_CONTEXT, 1);
-		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				PAGE_TABLE_DEPTH, adev->vm_manager.num_level);
-		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT,
+				    1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				VALID_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    VALID_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				READ_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    READ_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+				    EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
-				PAGE_TABLE_BLOCK_SIZE,
-				adev->vm_manager.block_size - 9);
+				    PAGE_TABLE_BLOCK_SIZE,
+				    block_size);
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index b4906d2f30d3..271452d3999a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -22,11 +22,10 @@
  */
 
 #include "amdgpu.h"
-#include "vega10/soc15ip.h"
-#include "vega10/NBIO/nbio_6_1_offset.h"
-#include "vega10/NBIO/nbio_6_1_sh_mask.h"
-#include "vega10/GC/gc_9_0_offset.h"
-#include "vega10/GC/gc_9_0_sh_mask.h"
+#include "nbio/nbio_6_1_offset.h"
+#include "nbio/nbio_6_1_sh_mask.h"
+#include "gc/gc_9_0_offset.h"
+#include "gc/gc_9_0_sh_mask.h"
 #include "soc15.h"
 #include "vega10_ih.h"
 #include "soc15_common.h"
@@ -254,7 +253,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	}
 
 	/* Trigger recovery due to world switch failure */
-	amdgpu_sriov_gpu_reset(adev, NULL);
+	amdgpu_device_gpu_recover(adev, NULL, false);
 }
 
 static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev,
@@ -278,13 +277,21 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,
 	int r;
 
 	/* trigger gpu-reset by hypervisor only if TDR disbaled */
-	if (amdgpu_lockup_timeout == 0) {
+	if (!amdgpu_gpu_recovery) {
 		/* see what event we get */
 		r = xgpu_ai_mailbox_rcv_msg(adev, IDH_FLR_NOTIFICATION);
 
-		/* only handle FLR_NOTIFY now */
-		if (!r)
-			schedule_work(&adev->virt.flr_work);
+		/* sometimes the interrupt is delayed to inject to VM, so under such case
+		 * the IDH_FLR_NOTIFICATION is overwritten by VF FLR from GIM side, thus
+		 * above recieve message could be failed, we should schedule the flr_work
+		 * anyway
+		 */
+		if (r) {
+			DRM_ERROR("FLR_NOTIFICATION is missed\n");
+			xgpu_ai_mailbox_send_ack(adev);
+		}
+
+		schedule_work(&adev->virt.flr_work);
 	}
 
 	return 0;
@@ -353,5 +360,6 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = {
 	.req_full_gpu	= xgpu_ai_request_full_gpu_access,
 	.rel_full_gpu	= xgpu_ai_release_full_gpu_access,
 	.reset_gpu = xgpu_ai_request_reset,
+	.wait_reset = NULL,
 	.trans_msg = xgpu_ai_mailbox_trans_msg,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
index c25a831f94ec..9fc1c37344ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
@@ -279,32 +279,32 @@ void xgpu_vi_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_FIJI:
-		amdgpu_program_register_sequence(adev,
-						 xgpu_fiji_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(
-						 xgpu_fiji_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 xgpu_fiji_golden_settings_a10,
-						 (const u32)ARRAY_SIZE(
-						 xgpu_fiji_golden_settings_a10));
-		amdgpu_program_register_sequence(adev,
-						 xgpu_fiji_golden_common_all,
-						 (const u32)ARRAY_SIZE(
-						 xgpu_fiji_golden_common_all));
+		amdgpu_device_program_register_sequence(adev,
+							xgpu_fiji_mgcg_cgcg_init,
+							ARRAY_SIZE(
+								xgpu_fiji_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							xgpu_fiji_golden_settings_a10,
+							ARRAY_SIZE(
+								xgpu_fiji_golden_settings_a10));
+		amdgpu_device_program_register_sequence(adev,
+							xgpu_fiji_golden_common_all,
+							ARRAY_SIZE(
+								xgpu_fiji_golden_common_all));
 		break;
 	case CHIP_TONGA:
-		amdgpu_program_register_sequence(adev,
-						 xgpu_tonga_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(
-						 xgpu_tonga_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 xgpu_tonga_golden_settings_a11,
-						 (const u32)ARRAY_SIZE(
-						 xgpu_tonga_golden_settings_a11));
-		amdgpu_program_register_sequence(adev,
-						 xgpu_tonga_golden_common_all,
-						 (const u32)ARRAY_SIZE(
-						 xgpu_tonga_golden_common_all));
+		amdgpu_device_program_register_sequence(adev,
+							xgpu_tonga_mgcg_cgcg_init,
+							ARRAY_SIZE(
+								xgpu_tonga_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							xgpu_tonga_golden_settings_a11,
+							ARRAY_SIZE(
+								xgpu_tonga_golden_settings_a11));
+		amdgpu_device_program_register_sequence(adev,
+							xgpu_tonga_golden_common_all,
+							ARRAY_SIZE(
+								xgpu_tonga_golden_common_all));
 		break;
 	default:
 		BUG_ON("Doesn't support chip type.\n");
@@ -446,8 +446,10 @@ static int xgpu_vi_send_access_requests(struct amdgpu_device *adev,
 		request == IDH_REQ_GPU_FINI_ACCESS ||
 		request == IDH_REQ_GPU_RESET_ACCESS) {
 		r = xgpu_vi_poll_msg(adev, IDH_READY_TO_ACCESS_GPU);
-		if (r)
-			pr_err("Doesn't get ack from pf, continue\n");
+		if (r) {
+			pr_err("Doesn't get ack from pf, give up\n");
+			return r;
+		}
 	}
 
 	return 0;
@@ -458,6 +460,11 @@ static int xgpu_vi_request_reset(struct amdgpu_device *adev)
 	return xgpu_vi_send_access_requests(adev, IDH_REQ_GPU_RESET_ACCESS);
 }
 
+static int xgpu_vi_wait_reset_cmpl(struct amdgpu_device *adev)
+{
+	return xgpu_vi_poll_msg(adev, IDH_FLR_NOTIFICATION_CMPL);
+}
+
 static int xgpu_vi_request_full_gpu_access(struct amdgpu_device *adev,
 					   bool init)
 {
@@ -514,7 +521,7 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work)
 	}
 
 	/* Trigger recovery due to world switch failure */
-	amdgpu_sriov_gpu_reset(adev, NULL);
+	amdgpu_device_gpu_recover(adev, NULL, false);
 }
 
 static int xgpu_vi_set_mailbox_rcv_irq(struct amdgpu_device *adev,
@@ -538,7 +545,7 @@ static int xgpu_vi_mailbox_rcv_irq(struct amdgpu_device *adev,
 	int r;
 
 	/* trigger gpu-reset by hypervisor only if TDR disbaled */
-	if (amdgpu_lockup_timeout == 0) {
+	if (!amdgpu_gpu_recovery) {
 		/* see what event we get */
 		r = xgpu_vi_mailbox_rcv_msg(adev, IDH_FLR_NOTIFICATION);
 
@@ -613,5 +620,6 @@ const struct amdgpu_virt_ops xgpu_vi_virt_ops = {
 	.req_full_gpu		= xgpu_vi_request_full_gpu_access,
 	.rel_full_gpu		= xgpu_vi_release_full_gpu_access,
 	.reset_gpu		= xgpu_vi_request_reset,
+	.wait_reset             = xgpu_vi_wait_reset_cmpl,
 	.trans_msg		= NULL, /* Does not need to trans VF errors to host. */
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
index 904a1bab9b9f..d4da663d5eb0 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
@@ -24,17 +24,16 @@
 #include "amdgpu_atombios.h"
 #include "nbio_v6_1.h"
 
-#include "vega10/soc15ip.h"
-#include "vega10/NBIO/nbio_6_1_default.h"
-#include "vega10/NBIO/nbio_6_1_offset.h"
-#include "vega10/NBIO/nbio_6_1_sh_mask.h"
-#include "vega10/vega10_enum.h"
+#include "nbio/nbio_6_1_default.h"
+#include "nbio/nbio_6_1_offset.h"
+#include "nbio/nbio_6_1_sh_mask.h"
+#include "vega10_enum.h"
 
 #define smnCPM_CONTROL                                                                                  0x11180460
 #define smnPCIE_CNTL2                                                                                   0x11180070
 #define smnPCIE_CONFIG_CNTL                                                                             0x11180044
 
-u32 nbio_v6_1_get_rev_id(struct amdgpu_device *adev)
+static u32 nbio_v6_1_get_rev_id(struct amdgpu_device *adev)
 {
         u32 tmp = RREG32_SOC15(NBIO, 0, mmRCC_DEV0_EPF0_STRAP0);
 
@@ -44,19 +43,7 @@ u32 nbio_v6_1_get_rev_id(struct amdgpu_device *adev)
 	return tmp;
 }
 
-u32 nbio_v6_1_get_atombios_scratch_regs(struct amdgpu_device *adev,
-					uint32_t idx)
-{
-	return RREG32_SOC15_OFFSET(NBIO, 0, mmBIOS_SCRATCH_0, idx);
-}
-
-void nbio_v6_1_set_atombios_scratch_regs(struct amdgpu_device *adev,
-					 uint32_t idx, uint32_t val)
-{
-	WREG32_SOC15_OFFSET(NBIO, 0, mmBIOS_SCRATCH_0, idx, val);
-}
-
-void nbio_v6_1_mc_access_enable(struct amdgpu_device *adev, bool enable)
+static void nbio_v6_1_mc_access_enable(struct amdgpu_device *adev, bool enable)
 {
 	if (enable)
 		WREG32_SOC15(NBIO, 0, mmBIF_FB_EN,
@@ -66,26 +53,23 @@ void nbio_v6_1_mc_access_enable(struct amdgpu_device *adev, bool enable)
 		WREG32_SOC15(NBIO, 0, mmBIF_FB_EN, 0);
 }
 
-void nbio_v6_1_hdp_flush(struct amdgpu_device *adev)
+static void nbio_v6_1_hdp_flush(struct amdgpu_device *adev)
 {
 	WREG32_SOC15_NO_KIQ(NBIO, 0, mmBIF_BX_PF0_HDP_MEM_COHERENCY_FLUSH_CNTL, 0);
 }
 
-u32 nbio_v6_1_get_memsize(struct amdgpu_device *adev)
+static u32 nbio_v6_1_get_memsize(struct amdgpu_device *adev)
 {
 	return RREG32_SOC15(NBIO, 0, mmRCC_PF_0_0_RCC_CONFIG_MEMSIZE);
 }
 
-static const u32 nbio_sdma_doorbell_range_reg[] =
-{
-	SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA0_DOORBELL_RANGE),
-	SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA1_DOORBELL_RANGE)
-};
-
-void nbio_v6_1_sdma_doorbell_range(struct amdgpu_device *adev, int instance,
+static void nbio_v6_1_sdma_doorbell_range(struct amdgpu_device *adev, int instance,
 				  bool use_doorbell, int doorbell_index)
 {
-	u32 doorbell_range = RREG32(nbio_sdma_doorbell_range_reg[instance]);
+	u32 reg = instance == 0 ? SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA0_DOORBELL_RANGE) :
+			SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA1_DOORBELL_RANGE);
+
+	u32 doorbell_range = RREG32(reg);
 
 	if (use_doorbell) {
 		doorbell_range = REG_SET_FIELD(doorbell_range, BIF_SDMA0_DOORBELL_RANGE, OFFSET, doorbell_index);
@@ -93,17 +77,18 @@ void nbio_v6_1_sdma_doorbell_range(struct amdgpu_device *adev, int instance,
 	} else
 		doorbell_range = REG_SET_FIELD(doorbell_range, BIF_SDMA0_DOORBELL_RANGE, SIZE, 0);
 
-	WREG32(nbio_sdma_doorbell_range_reg[instance], doorbell_range);
+	WREG32(reg, doorbell_range);
+
 }
 
-void nbio_v6_1_enable_doorbell_aperture(struct amdgpu_device *adev,
-					bool enable)
+static void nbio_v6_1_enable_doorbell_aperture(struct amdgpu_device *adev,
+					       bool enable)
 {
 	WREG32_FIELD15(NBIO, 0, RCC_PF_0_0_RCC_DOORBELL_APER_EN, BIF_DOORBELL_APER_EN, enable ? 1 : 0);
 }
 
-void nbio_v6_1_enable_doorbell_selfring_aperture(struct amdgpu_device *adev,
-					bool enable)
+static void nbio_v6_1_enable_doorbell_selfring_aperture(struct amdgpu_device *adev,
+							bool enable)
 {
 	u32 tmp = 0;
 
@@ -122,8 +107,8 @@ void nbio_v6_1_enable_doorbell_selfring_aperture(struct amdgpu_device *adev,
 }
 
 
-void nbio_v6_1_ih_doorbell_range(struct amdgpu_device *adev,
-				bool use_doorbell, int doorbell_index)
+static void nbio_v6_1_ih_doorbell_range(struct amdgpu_device *adev,
+					bool use_doorbell, int doorbell_index)
 {
 	u32 ih_doorbell_range = RREG32_SOC15(NBIO, 0 , mmBIF_IH_DOORBELL_RANGE);
 
@@ -136,7 +121,7 @@ void nbio_v6_1_ih_doorbell_range(struct amdgpu_device *adev,
 	WREG32_SOC15(NBIO, 0, mmBIF_IH_DOORBELL_RANGE, ih_doorbell_range);
 }
 
-void nbio_v6_1_ih_control(struct amdgpu_device *adev)
+static void nbio_v6_1_ih_control(struct amdgpu_device *adev)
 {
 	u32 interrupt_cntl;
 
@@ -152,8 +137,8 @@ void nbio_v6_1_ih_control(struct amdgpu_device *adev)
 	WREG32_SOC15(NBIO, 0, mmINTERRUPT_CNTL, interrupt_cntl);
 }
 
-void nbio_v6_1_update_medium_grain_clock_gating(struct amdgpu_device *adev,
-						bool enable)
+static void nbio_v6_1_update_medium_grain_clock_gating(struct amdgpu_device *adev,
+						       bool enable)
 {
 	uint32_t def, data;
 
@@ -180,8 +165,8 @@ void nbio_v6_1_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 		WREG32_PCIE(smnCPM_CONTROL, data);
 }
 
-void nbio_v6_1_update_medium_grain_light_sleep(struct amdgpu_device *adev,
-					       bool enable)
+static void nbio_v6_1_update_medium_grain_light_sleep(struct amdgpu_device *adev,
+						      bool enable)
 {
 	uint32_t def, data;
 
@@ -200,7 +185,8 @@ void nbio_v6_1_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 		WREG32_PCIE(smnPCIE_CNTL2, data);
 }
 
-void nbio_v6_1_get_clockgating_state(struct amdgpu_device *adev, u32 *flags)
+static void nbio_v6_1_get_clockgating_state(struct amdgpu_device *adev,
+					    u32 *flags)
 {
 	int data;
 
@@ -215,9 +201,27 @@ void nbio_v6_1_get_clockgating_state(struct amdgpu_device *adev, u32 *flags)
 		*flags |= AMD_CG_SUPPORT_BIF_LS;
 }
 
-const struct nbio_hdp_flush_reg nbio_v6_1_hdp_flush_reg = {
-	.hdp_flush_req_offset = SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_GPU_HDP_FLUSH_REQ),
-	.hdp_flush_done_offset = SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_GPU_HDP_FLUSH_DONE),
+static u32 nbio_v6_1_get_hdp_flush_req_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_GPU_HDP_FLUSH_REQ);
+}
+
+static u32 nbio_v6_1_get_hdp_flush_done_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_GPU_HDP_FLUSH_DONE);
+}
+
+static u32 nbio_v6_1_get_pcie_index_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmPCIE_INDEX);
+}
+
+static u32 nbio_v6_1_get_pcie_data_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmPCIE_DATA);
+}
+
+static const struct nbio_hdp_flush_reg nbio_v6_1_hdp_flush_reg = {
 	.ref_and_mask_cp0 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP0_MASK,
 	.ref_and_mask_cp1 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP1_MASK,
 	.ref_and_mask_cp2 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP2_MASK,
@@ -232,12 +236,7 @@ const struct nbio_hdp_flush_reg nbio_v6_1_hdp_flush_reg = {
 	.ref_and_mask_sdma1 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__SDMA1_MASK
 };
 
-const struct nbio_pcie_index_data nbio_v6_1_pcie_index_data = {
-	.index_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_INDEX),
-	.data_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_DATA),
-};
-
-void nbio_v6_1_detect_hw_virt(struct amdgpu_device *adev)
+static void nbio_v6_1_detect_hw_virt(struct amdgpu_device *adev)
 {
 	uint32_t reg;
 
@@ -254,7 +253,7 @@ void nbio_v6_1_detect_hw_virt(struct amdgpu_device *adev)
 	}
 }
 
-void nbio_v6_1_init_registers(struct amdgpu_device *adev)
+static void nbio_v6_1_init_registers(struct amdgpu_device *adev)
 {
 	uint32_t def, data;
 
@@ -265,3 +264,25 @@ void nbio_v6_1_init_registers(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnPCIE_CONFIG_CNTL, data);
 }
+
+const struct amdgpu_nbio_funcs nbio_v6_1_funcs = {
+	.hdp_flush_reg = &nbio_v6_1_hdp_flush_reg,
+	.get_hdp_flush_req_offset = nbio_v6_1_get_hdp_flush_req_offset,
+	.get_hdp_flush_done_offset = nbio_v6_1_get_hdp_flush_done_offset,
+	.get_pcie_index_offset = nbio_v6_1_get_pcie_index_offset,
+	.get_pcie_data_offset = nbio_v6_1_get_pcie_data_offset,
+	.get_rev_id = nbio_v6_1_get_rev_id,
+	.mc_access_enable = nbio_v6_1_mc_access_enable,
+	.hdp_flush = nbio_v6_1_hdp_flush,
+	.get_memsize = nbio_v6_1_get_memsize,
+	.sdma_doorbell_range = nbio_v6_1_sdma_doorbell_range,
+	.enable_doorbell_aperture = nbio_v6_1_enable_doorbell_aperture,
+	.enable_doorbell_selfring_aperture = nbio_v6_1_enable_doorbell_selfring_aperture,
+	.ih_doorbell_range = nbio_v6_1_ih_doorbell_range,
+	.update_medium_grain_clock_gating = nbio_v6_1_update_medium_grain_clock_gating,
+	.update_medium_grain_light_sleep = nbio_v6_1_update_medium_grain_light_sleep,
+	.get_clockgating_state = nbio_v6_1_get_clockgating_state,
+	.ih_control = nbio_v6_1_ih_control,
+	.init_registers = nbio_v6_1_init_registers,
+	.detect_hw_virt = nbio_v6_1_detect_hw_virt,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h
index 14ca8d45a46c..0743a6f016f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h
@@ -26,30 +26,6 @@
 
 #include "soc15_common.h"
 
-extern const struct nbio_hdp_flush_reg nbio_v6_1_hdp_flush_reg;
-extern const struct nbio_pcie_index_data nbio_v6_1_pcie_index_data;
-int nbio_v6_1_init(struct amdgpu_device *adev);
-u32 nbio_v6_1_get_atombios_scratch_regs(struct amdgpu_device *adev,
-                                        uint32_t idx);
-void nbio_v6_1_set_atombios_scratch_regs(struct amdgpu_device *adev,
-                                         uint32_t idx, uint32_t val);
-void nbio_v6_1_mc_access_enable(struct amdgpu_device *adev, bool enable);
-void nbio_v6_1_hdp_flush(struct amdgpu_device *adev);
-u32 nbio_v6_1_get_memsize(struct amdgpu_device *adev);
-void nbio_v6_1_sdma_doorbell_range(struct amdgpu_device *adev, int instance,
-				  bool use_doorbell, int doorbell_index);
-void nbio_v6_1_enable_doorbell_aperture(struct amdgpu_device *adev,
-					bool enable);
-void nbio_v6_1_enable_doorbell_selfring_aperture(struct amdgpu_device *adev,
-					bool enable);
-void nbio_v6_1_ih_doorbell_range(struct amdgpu_device *adev,
-				bool use_doorbell, int doorbell_index);
-void nbio_v6_1_ih_control(struct amdgpu_device *adev);
-u32 nbio_v6_1_get_rev_id(struct amdgpu_device *adev);
-void nbio_v6_1_update_medium_grain_clock_gating(struct amdgpu_device *adev, bool enable);
-void nbio_v6_1_update_medium_grain_light_sleep(struct amdgpu_device *adev, bool enable);
-void nbio_v6_1_get_clockgating_state(struct amdgpu_device *adev, u32 *flags);
-void nbio_v6_1_detect_hw_virt(struct amdgpu_device *adev);
-void nbio_v6_1_init_registers(struct amdgpu_device *adev);
+extern const struct amdgpu_nbio_funcs nbio_v6_1_funcs;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
index f802b973410a..17a9131a4598 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
@@ -24,15 +24,17 @@
 #include "amdgpu_atombios.h"
 #include "nbio_v7_0.h"
 
-#include "vega10/soc15ip.h"
-#include "raven1/NBIO/nbio_7_0_default.h"
-#include "raven1/NBIO/nbio_7_0_offset.h"
-#include "raven1/NBIO/nbio_7_0_sh_mask.h"
-#include "vega10/vega10_enum.h"
+#include "nbio/nbio_7_0_default.h"
+#include "nbio/nbio_7_0_offset.h"
+#include "nbio/nbio_7_0_sh_mask.h"
+#include "vega10_enum.h"
 
 #define smnNBIF_MGCG_CTRL_LCLK	0x1013a05c
 
-u32 nbio_v7_0_get_rev_id(struct amdgpu_device *adev)
+#define smnCPM_CONTROL                                                                                  0x11180460
+#define smnPCIE_CNTL2                                                                                   0x11180070
+
+static u32 nbio_v7_0_get_rev_id(struct amdgpu_device *adev)
 {
         u32 tmp = RREG32_SOC15(NBIO, 0, mmRCC_DEV0_EPF0_STRAP0);
 
@@ -42,19 +44,7 @@ u32 nbio_v7_0_get_rev_id(struct amdgpu_device *adev)
 	return tmp;
 }
 
-u32 nbio_v7_0_get_atombios_scratch_regs(struct amdgpu_device *adev,
-					uint32_t idx)
-{
-	return RREG32_SOC15_OFFSET(NBIO, 0, mmBIOS_SCRATCH_0, idx);
-}
-
-void nbio_v7_0_set_atombios_scratch_regs(struct amdgpu_device *adev,
-					 uint32_t idx, uint32_t val)
-{
-	WREG32_SOC15_OFFSET(NBIO, 0, mmBIOS_SCRATCH_0, idx, val);
-}
-
-void nbio_v7_0_mc_access_enable(struct amdgpu_device *adev, bool enable)
+static void nbio_v7_0_mc_access_enable(struct amdgpu_device *adev, bool enable)
 {
 	if (enable)
 		WREG32_SOC15(NBIO, 0, mmBIF_FB_EN,
@@ -63,26 +53,23 @@ void nbio_v7_0_mc_access_enable(struct amdgpu_device *adev, bool enable)
 		WREG32_SOC15(NBIO, 0, mmBIF_FB_EN, 0);
 }
 
-void nbio_v7_0_hdp_flush(struct amdgpu_device *adev)
+static void nbio_v7_0_hdp_flush(struct amdgpu_device *adev)
 {
 	WREG32_SOC15_NO_KIQ(NBIO, 0, mmHDP_MEM_COHERENCY_FLUSH_CNTL, 0);
 }
 
-u32 nbio_v7_0_get_memsize(struct amdgpu_device *adev)
+static u32 nbio_v7_0_get_memsize(struct amdgpu_device *adev)
 {
 	return RREG32_SOC15(NBIO, 0, mmRCC_CONFIG_MEMSIZE);
 }
 
-static const u32 nbio_sdma_doorbell_range_reg[] =
+static void nbio_v7_0_sdma_doorbell_range(struct amdgpu_device *adev, int instance,
+					  bool use_doorbell, int doorbell_index)
 {
-	SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA0_DOORBELL_RANGE),
-	SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA1_DOORBELL_RANGE)
-};
+	u32 reg = instance == 0 ? SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA0_DOORBELL_RANGE) :
+			SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA1_DOORBELL_RANGE);
 
-void nbio_v7_0_sdma_doorbell_range(struct amdgpu_device *adev, int instance,
-				  bool use_doorbell, int doorbell_index)
-{
-	u32 doorbell_range = RREG32(nbio_sdma_doorbell_range_reg[instance]);
+	u32 doorbell_range = RREG32(reg);
 
 	if (use_doorbell) {
 		doorbell_range = REG_SET_FIELD(doorbell_range, BIF_SDMA0_DOORBELL_RANGE, OFFSET, doorbell_index);
@@ -90,17 +77,23 @@ void nbio_v7_0_sdma_doorbell_range(struct amdgpu_device *adev, int instance,
 	} else
 		doorbell_range = REG_SET_FIELD(doorbell_range, BIF_SDMA0_DOORBELL_RANGE, SIZE, 0);
 
-	WREG32(nbio_sdma_doorbell_range_reg[instance], doorbell_range);
+	WREG32(reg, doorbell_range);
 }
 
-void nbio_v7_0_enable_doorbell_aperture(struct amdgpu_device *adev,
-					bool enable)
+static void nbio_v7_0_enable_doorbell_aperture(struct amdgpu_device *adev,
+					       bool enable)
 {
 	WREG32_FIELD15(NBIO, 0, RCC_DOORBELL_APER_EN, BIF_DOORBELL_APER_EN, enable ? 1 : 0);
 }
 
-void nbio_v7_0_ih_doorbell_range(struct amdgpu_device *adev,
-				bool use_doorbell, int doorbell_index)
+static void nbio_v7_0_enable_doorbell_selfring_aperture(struct amdgpu_device *adev,
+							bool enable)
+{
+
+}
+
+static void nbio_v7_0_ih_doorbell_range(struct amdgpu_device *adev,
+					bool use_doorbell, int doorbell_index)
 {
 	u32 ih_doorbell_range = RREG32_SOC15(NBIO, 0 , mmBIF_IH_DOORBELL_RANGE);
 
@@ -130,8 +123,8 @@ static void nbio_7_0_write_syshub_ind_mmr(struct amdgpu_device *adev, uint32_t o
 	WREG32_SOC15(NBIO, 0, mmSYSHUB_DATA, data);
 }
 
-void nbio_v7_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
-						bool enable)
+static void nbio_v7_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
+						       bool enable)
 {
 	uint32_t def, data;
 
@@ -169,7 +162,43 @@ void nbio_v7_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 		nbio_7_0_write_syshub_ind_mmr(adev, ixSYSHUB_MMREG_IND_SYSHUB_MGCG_CTRL_SHUBCLK, data);
 }
 
-void nbio_v7_0_ih_control(struct amdgpu_device *adev)
+static void nbio_v7_0_update_medium_grain_light_sleep(struct amdgpu_device *adev,
+						      bool enable)
+{
+	uint32_t def, data;
+
+	def = data = RREG32_PCIE(smnPCIE_CNTL2);
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_BIF_LS)) {
+		data |= (PCIE_CNTL2__SLV_MEM_LS_EN_MASK |
+			 PCIE_CNTL2__MST_MEM_LS_EN_MASK |
+			 PCIE_CNTL2__REPLAY_MEM_LS_EN_MASK);
+	} else {
+		data &= ~(PCIE_CNTL2__SLV_MEM_LS_EN_MASK |
+			  PCIE_CNTL2__MST_MEM_LS_EN_MASK |
+			  PCIE_CNTL2__REPLAY_MEM_LS_EN_MASK);
+	}
+
+	if (def != data)
+		WREG32_PCIE(smnPCIE_CNTL2, data);
+}
+
+static void nbio_v7_0_get_clockgating_state(struct amdgpu_device *adev,
+					    u32 *flags)
+{
+	int data;
+
+	/* AMD_CG_SUPPORT_BIF_MGCG */
+	data = RREG32_PCIE(smnCPM_CONTROL);
+	if (data & CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK)
+		*flags |= AMD_CG_SUPPORT_BIF_MGCG;
+
+	/* AMD_CG_SUPPORT_BIF_LS */
+	data = RREG32_PCIE(smnPCIE_CNTL2);
+	if (data & PCIE_CNTL2__SLV_MEM_LS_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_BIF_LS;
+}
+
+static void nbio_v7_0_ih_control(struct amdgpu_device *adev)
 {
 	u32 interrupt_cntl;
 
@@ -185,9 +214,27 @@ void nbio_v7_0_ih_control(struct amdgpu_device *adev)
 	WREG32_SOC15(NBIO, 0, mmINTERRUPT_CNTL, interrupt_cntl);
 }
 
+static u32 nbio_v7_0_get_hdp_flush_req_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmGPU_HDP_FLUSH_REQ);
+}
+
+static u32 nbio_v7_0_get_hdp_flush_done_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmGPU_HDP_FLUSH_DONE);
+}
+
+static u32 nbio_v7_0_get_pcie_index_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmPCIE_INDEX2);
+}
+
+static u32 nbio_v7_0_get_pcie_data_offset(struct amdgpu_device *adev)
+{
+	return SOC15_REG_OFFSET(NBIO, 0, mmPCIE_DATA2);
+}
+
 const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg = {
-	.hdp_flush_req_offset = SOC15_REG_OFFSET(NBIO, 0, mmGPU_HDP_FLUSH_REQ),
-	.hdp_flush_done_offset = SOC15_REG_OFFSET(NBIO, 0, mmGPU_HDP_FLUSH_DONE),
 	.ref_and_mask_cp0 = GPU_HDP_FLUSH_DONE__CP0_MASK,
 	.ref_and_mask_cp1 = GPU_HDP_FLUSH_DONE__CP1_MASK,
 	.ref_and_mask_cp2 = GPU_HDP_FLUSH_DONE__CP2_MASK,
@@ -202,7 +249,35 @@ const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg = {
 	.ref_and_mask_sdma1 = GPU_HDP_FLUSH_DONE__SDMA1_MASK,
 };
 
-const struct nbio_pcie_index_data nbio_v7_0_pcie_index_data = {
-	.index_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_INDEX2),
-	.data_offset = SOC15_REG_OFFSET(NBIO, 0, mmPCIE_DATA2)
+static void nbio_v7_0_detect_hw_virt(struct amdgpu_device *adev)
+{
+	if (is_virtual_machine())	/* passthrough mode exclus sriov mod */
+		adev->virt.caps |= AMDGPU_PASSTHROUGH_MODE;
+}
+
+static void nbio_v7_0_init_registers(struct amdgpu_device *adev)
+{
+
+}
+
+const struct amdgpu_nbio_funcs nbio_v7_0_funcs = {
+	.hdp_flush_reg = &nbio_v7_0_hdp_flush_reg,
+	.get_hdp_flush_req_offset = nbio_v7_0_get_hdp_flush_req_offset,
+	.get_hdp_flush_done_offset = nbio_v7_0_get_hdp_flush_done_offset,
+	.get_pcie_index_offset = nbio_v7_0_get_pcie_index_offset,
+	.get_pcie_data_offset = nbio_v7_0_get_pcie_data_offset,
+	.get_rev_id = nbio_v7_0_get_rev_id,
+	.mc_access_enable = nbio_v7_0_mc_access_enable,
+	.hdp_flush = nbio_v7_0_hdp_flush,
+	.get_memsize = nbio_v7_0_get_memsize,
+	.sdma_doorbell_range = nbio_v7_0_sdma_doorbell_range,
+	.enable_doorbell_aperture = nbio_v7_0_enable_doorbell_aperture,
+	.enable_doorbell_selfring_aperture = nbio_v7_0_enable_doorbell_selfring_aperture,
+	.ih_doorbell_range = nbio_v7_0_ih_doorbell_range,
+	.update_medium_grain_clock_gating = nbio_v7_0_update_medium_grain_clock_gating,
+	.update_medium_grain_light_sleep = nbio_v7_0_update_medium_grain_light_sleep,
+	.get_clockgating_state = nbio_v7_0_get_clockgating_state,
+	.ih_control = nbio_v7_0_ih_control,
+	.init_registers = nbio_v7_0_init_registers,
+	.detect_hw_virt = nbio_v7_0_detect_hw_virt,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h
index df8fa90f40d7..508d549c5029 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h
@@ -26,24 +26,6 @@
 
 #include "soc15_common.h"
 
-extern const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg;
-extern const struct nbio_pcie_index_data nbio_v7_0_pcie_index_data;
-int nbio_v7_0_init(struct amdgpu_device *adev);
-u32 nbio_v7_0_get_atombios_scratch_regs(struct amdgpu_device *adev,
-                                        uint32_t idx);
-void nbio_v7_0_set_atombios_scratch_regs(struct amdgpu_device *adev,
-                                         uint32_t idx, uint32_t val);
-void nbio_v7_0_mc_access_enable(struct amdgpu_device *adev, bool enable);
-void nbio_v7_0_hdp_flush(struct amdgpu_device *adev);
-u32 nbio_v7_0_get_memsize(struct amdgpu_device *adev);
-void nbio_v7_0_sdma_doorbell_range(struct amdgpu_device *adev, int instance,
-				  bool use_doorbell, int doorbell_index);
-void nbio_v7_0_enable_doorbell_aperture(struct amdgpu_device *adev,
-					bool enable);
-void nbio_v7_0_ih_doorbell_range(struct amdgpu_device *adev,
-				bool use_doorbell, int doorbell_index);
-void nbio_v7_0_ih_control(struct amdgpu_device *adev);
-u32 nbio_v7_0_get_rev_id(struct amdgpu_device *adev);
-void nbio_v7_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
-						bool enable);
+extern const struct amdgpu_nbio_funcs nbio_v7_0_funcs;
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
index 4e20d91d5d50..5a9fe24697f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
@@ -30,10 +30,9 @@
 #include "soc15_common.h"
 #include "psp_v10_0.h"
 
-#include "vega10/soc15ip.h"
-#include "raven1/MP/mp_10_0_offset.h"
-#include "raven1/GC/gc_9_1_offset.h"
-#include "raven1/SDMA0/sdma0_4_1_offset.h"
+#include "mp/mp_10_0_offset.h"
+#include "gc/gc_9_1_offset.h"
+#include "sdma0/sdma0_4_1_offset.h"
 
 MODULE_FIRMWARE("amdgpu/raven_asd.bin");
 
@@ -298,9 +297,10 @@ int psp_v10_0_cmd_submit(struct psp_context *psp,
 }
 
 static int
-psp_v10_0_sram_map(unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
-		  unsigned int *sram_data_reg_offset,
-		  enum AMDGPU_UCODE_ID ucode_id)
+psp_v10_0_sram_map(struct amdgpu_device *adev,
+		unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
+		unsigned int *sram_data_reg_offset,
+		enum AMDGPU_UCODE_ID ucode_id)
 {
 	int ret = 0;
 
@@ -395,7 +395,7 @@ bool psp_v10_0_compare_sram_data(struct psp_context *psp,
 	uint32_t *ucode_mem = NULL;
 	struct amdgpu_device *adev = psp->adev;
 
-	err = psp_v10_0_sram_map(&fw_sram_reg_val, &fw_sram_addr_reg_offset,
+	err = psp_v10_0_sram_map(adev, &fw_sram_reg_val, &fw_sram_addr_reg_offset,
 				&fw_sram_data_reg_offset, ucode_type);
 	if (err)
 		return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
index c7bcfe8e286c..19bd1934e63d 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
@@ -31,12 +31,11 @@
 #include "soc15_common.h"
 #include "psp_v3_1.h"
 
-#include "vega10/soc15ip.h"
-#include "vega10/MP/mp_9_0_offset.h"
-#include "vega10/MP/mp_9_0_sh_mask.h"
-#include "vega10/GC/gc_9_0_offset.h"
-#include "vega10/SDMA0/sdma0_4_0_offset.h"
-#include "vega10/NBIO/nbio_6_1_offset.h"
+#include "mp/mp_9_0_offset.h"
+#include "mp/mp_9_0_sh_mask.h"
+#include "gc/gc_9_0_offset.h"
+#include "sdma0/sdma0_4_0_offset.h"
+#include "nbio/nbio_6_1_offset.h"
 
 MODULE_FIRMWARE("amdgpu/vega10_sos.bin");
 MODULE_FIRMWARE("amdgpu/vega10_asd.bin");
@@ -410,9 +409,10 @@ int psp_v3_1_cmd_submit(struct psp_context *psp,
 }
 
 static int
-psp_v3_1_sram_map(unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
-		  unsigned int *sram_data_reg_offset,
-		  enum AMDGPU_UCODE_ID ucode_id)
+psp_v3_1_sram_map(struct amdgpu_device *adev,
+		unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
+		unsigned int *sram_data_reg_offset,
+		enum AMDGPU_UCODE_ID ucode_id)
 {
 	int ret = 0;
 
@@ -507,7 +507,7 @@ bool psp_v3_1_compare_sram_data(struct psp_context *psp,
 	uint32_t *ucode_mem = NULL;
 	struct amdgpu_device *adev = psp->adev;
 
-	err = psp_v3_1_sram_map(&fw_sram_reg_val, &fw_sram_addr_reg_offset,
+	err = psp_v3_1_sram_map(adev, &fw_sram_reg_val, &fw_sram_addr_reg_offset,
 				&fw_sram_data_reg_offset, ucode_type);
 	if (err)
 		return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 67f375bfe452..d4787ad4d346 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -93,12 +93,12 @@ static void sdma_v2_4_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_TOPAZ:
-		amdgpu_program_register_sequence(adev,
-						 iceland_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(iceland_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_iceland_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_iceland_a11));
+		amdgpu_device_program_register_sequence(adev,
+							iceland_mgcg_cgcg_init,
+							ARRAY_SIZE(iceland_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_iceland_a11,
+							ARRAY_SIZE(golden_settings_iceland_a11));
 		break;
 	default:
 		break;
@@ -246,15 +246,13 @@ static void sdma_v2_4_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
  */
 static void sdma_v2_4_ring_emit_ib(struct amdgpu_ring *ring,
 				   struct amdgpu_ib *ib,
-				   unsigned vm_id, bool ctx_switch)
+				   unsigned vmid, bool ctx_switch)
 {
-	u32 vmid = vm_id & 0xf;
-
 	/* IB packet must end on a 8 DW boundary */
 	sdma_v2_4_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
-			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid));
+			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
 	/* base must be 32 byte aligned */
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr) & 0xffffffe0);
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
@@ -600,7 +598,7 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring)
 	u32 tmp;
 	u64 gpu_addr;
 
-	r = amdgpu_wb_get(adev, &index);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r);
 		return r;
@@ -613,7 +611,7 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring)
 	r = amdgpu_ring_alloc(ring, 5);
 	if (r) {
 		DRM_ERROR("amdgpu: dma failed to lock ring %d (%d).\n", ring->idx, r);
-		amdgpu_wb_free(adev, index);
+		amdgpu_device_wb_free(adev, index);
 		return r;
 	}
 
@@ -633,13 +631,13 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n", ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
 			  ring->idx, tmp);
 		r = -EINVAL;
 	}
-	amdgpu_wb_free(adev, index);
+	amdgpu_device_wb_free(adev, index);
 
 	return r;
 }
@@ -662,7 +660,7 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	u64 gpu_addr;
 	long r;
 
-	r = amdgpu_wb_get(adev, &index);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
 		dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
 		return r;
@@ -704,7 +702,7 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	}
 	tmp = le32_to_cpu(adev->wb.wb[index]);
 	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp);
@@ -715,7 +713,7 @@ err1:
 	amdgpu_ib_free(adev, &ib, NULL);
 	dma_fence_put(f);
 err0:
-	amdgpu_wb_free(adev, index);
+	amdgpu_device_wb_free(adev, index);
 	return r;
 }
 
@@ -861,14 +859,14 @@ static void sdma_v2_4_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using sDMA (VI).
  */
 static void sdma_v2_4_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					 unsigned vm_id, uint64_t pd_addr)
+					 unsigned vmid, uint64_t pd_addr)
 {
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_SRBM_WRITE) |
 			  SDMA_PKT_SRBM_WRITE_HEADER_BYTE_EN(0xf));
-	if (vm_id < 8) {
-		amdgpu_ring_write(ring, (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id));
+	if (vmid < 8) {
+		amdgpu_ring_write(ring, (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vmid));
 	} else {
-		amdgpu_ring_write(ring, (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vm_id - 8));
+		amdgpu_ring_write(ring, (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vmid - 8));
 	}
 	amdgpu_ring_write(ring, pd_addr >> 12);
 
@@ -876,7 +874,7 @@ static void sdma_v2_4_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_SRBM_WRITE) |
 			  SDMA_PKT_SRBM_WRITE_HEADER_BYTE_EN(0xf));
 	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST);
-	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vmid);
 
 	/* wait for flush */
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 6d06f8eb659f..521978c40537 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -192,47 +192,47 @@ static void sdma_v3_0_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_FIJI:
-		amdgpu_program_register_sequence(adev,
-						 fiji_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(fiji_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_fiji_a10,
-						 (const u32)ARRAY_SIZE(golden_settings_fiji_a10));
+		amdgpu_device_program_register_sequence(adev,
+							fiji_mgcg_cgcg_init,
+							ARRAY_SIZE(fiji_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_fiji_a10,
+							ARRAY_SIZE(golden_settings_fiji_a10));
 		break;
 	case CHIP_TONGA:
-		amdgpu_program_register_sequence(adev,
-						 tonga_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(tonga_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_tonga_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_tonga_a11));
+		amdgpu_device_program_register_sequence(adev,
+							tonga_mgcg_cgcg_init,
+							ARRAY_SIZE(tonga_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_tonga_a11,
+							ARRAY_SIZE(golden_settings_tonga_a11));
 		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_polaris11_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_polaris11_a11));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_polaris11_a11,
+							ARRAY_SIZE(golden_settings_polaris11_a11));
 		break;
 	case CHIP_POLARIS10:
-		amdgpu_program_register_sequence(adev,
-						 golden_settings_polaris10_a11,
-						 (const u32)ARRAY_SIZE(golden_settings_polaris10_a11));
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_polaris10_a11,
+							ARRAY_SIZE(golden_settings_polaris10_a11));
 		break;
 	case CHIP_CARRIZO:
-		amdgpu_program_register_sequence(adev,
-						 cz_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(cz_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 cz_golden_settings_a11,
-						 (const u32)ARRAY_SIZE(cz_golden_settings_a11));
+		amdgpu_device_program_register_sequence(adev,
+							cz_mgcg_cgcg_init,
+							ARRAY_SIZE(cz_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							cz_golden_settings_a11,
+							ARRAY_SIZE(cz_golden_settings_a11));
 		break;
 	case CHIP_STONEY:
-		amdgpu_program_register_sequence(adev,
-						 stoney_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(stoney_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 stoney_golden_settings_a11,
-						 (const u32)ARRAY_SIZE(stoney_golden_settings_a11));
+		amdgpu_device_program_register_sequence(adev,
+							stoney_mgcg_cgcg_init,
+							ARRAY_SIZE(stoney_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							stoney_golden_settings_a11,
+							ARRAY_SIZE(stoney_golden_settings_a11));
 		break;
 	default:
 		break;
@@ -355,7 +355,7 @@ static uint64_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 	u32 wptr;
 
-	if (ring->use_doorbell) {
+	if (ring->use_doorbell || ring->use_pollmem) {
 		/* XXX check if swapping is necessary on BE */
 		wptr = ring->adev->wb.wb[ring->wptr_offs] >> 2;
 	} else {
@@ -380,10 +380,13 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		u32 *wb = (u32 *)&adev->wb.wb[ring->wptr_offs];
-
 		/* XXX check if swapping is necessary on BE */
 		WRITE_ONCE(*wb, (lower_32_bits(ring->wptr) << 2));
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr) << 2);
+	} else if (ring->use_pollmem) {
+		u32 *wb = (u32 *)&adev->wb.wb[ring->wptr_offs];
+
+		WRITE_ONCE(*wb, (lower_32_bits(ring->wptr) << 2));
 	} else {
 		int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
 
@@ -414,15 +417,13 @@ static void sdma_v3_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
  */
 static void sdma_v3_0_ring_emit_ib(struct amdgpu_ring *ring,
 				   struct amdgpu_ib *ib,
-				   unsigned vm_id, bool ctx_switch)
+				   unsigned vmid, bool ctx_switch)
 {
-	u32 vmid = vm_id & 0xf;
-
 	/* IB packet must end on a 8 DW boundary */
 	sdma_v3_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
-			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid));
+			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
 	/* base must be 32 byte aligned */
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr) & 0xffffffe0);
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
@@ -718,10 +719,14 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
 		WREG32(mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI + sdma_offsets[i],
 		       upper_32_bits(wptr_gpu_addr));
 		wptr_poll_cntl = RREG32(mmSDMA0_GFX_RB_WPTR_POLL_CNTL + sdma_offsets[i]);
-		if (amdgpu_sriov_vf(adev))
-			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 1);
+		if (ring->use_pollmem)
+			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl,
+						       SDMA0_GFX_RB_WPTR_POLL_CNTL,
+						       ENABLE, 1);
 		else
-			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 0);
+			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl,
+						       SDMA0_GFX_RB_WPTR_POLL_CNTL,
+						       ENABLE, 0);
 		WREG32(mmSDMA0_GFX_RB_WPTR_POLL_CNTL + sdma_offsets[i], wptr_poll_cntl);
 
 		/* enable DMA RB */
@@ -860,7 +865,7 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring)
 	u32 tmp;
 	u64 gpu_addr;
 
-	r = amdgpu_wb_get(adev, &index);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r);
 		return r;
@@ -873,7 +878,7 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring)
 	r = amdgpu_ring_alloc(ring, 5);
 	if (r) {
 		DRM_ERROR("amdgpu: dma failed to lock ring %d (%d).\n", ring->idx, r);
-		amdgpu_wb_free(adev, index);
+		amdgpu_device_wb_free(adev, index);
 		return r;
 	}
 
@@ -893,13 +898,13 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n", ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
 			  ring->idx, tmp);
 		r = -EINVAL;
 	}
-	amdgpu_wb_free(adev, index);
+	amdgpu_device_wb_free(adev, index);
 
 	return r;
 }
@@ -922,7 +927,7 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	u64 gpu_addr;
 	long r;
 
-	r = amdgpu_wb_get(adev, &index);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
 		dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
 		return r;
@@ -964,7 +969,7 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	}
 	tmp = le32_to_cpu(adev->wb.wb[index]);
 	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp);
@@ -974,7 +979,7 @@ err1:
 	amdgpu_ib_free(adev, &ib, NULL);
 	dma_fence_put(f);
 err0:
-	amdgpu_wb_free(adev, index);
+	amdgpu_device_wb_free(adev, index);
 	return r;
 }
 
@@ -1120,14 +1125,14 @@ static void sdma_v3_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using sDMA (VI).
  */
 static void sdma_v3_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					 unsigned vm_id, uint64_t pd_addr)
+					 unsigned vmid, uint64_t pd_addr)
 {
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_SRBM_WRITE) |
 			  SDMA_PKT_SRBM_WRITE_HEADER_BYTE_EN(0xf));
-	if (vm_id < 8) {
-		amdgpu_ring_write(ring, (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id));
+	if (vmid < 8) {
+		amdgpu_ring_write(ring, (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vmid));
 	} else {
-		amdgpu_ring_write(ring, (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vm_id - 8));
+		amdgpu_ring_write(ring, (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vmid - 8));
 	}
 	amdgpu_ring_write(ring, pd_addr >> 12);
 
@@ -1135,7 +1140,7 @@ static void sdma_v3_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_SRBM_WRITE) |
 			  SDMA_PKT_SRBM_WRITE_HEADER_BYTE_EN(0xf));
 	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST);
-	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vmid);
 
 	/* wait for flush */
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
@@ -1203,9 +1208,13 @@ static int sdma_v3_0_sw_init(void *handle)
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		ring = &adev->sdma.instance[i].ring;
 		ring->ring_obj = NULL;
-		ring->use_doorbell = true;
-		ring->doorbell_index = (i == 0) ?
-			AMDGPU_DOORBELL_sDMA_ENGINE0 : AMDGPU_DOORBELL_sDMA_ENGINE1;
+		if (!amdgpu_sriov_vf(adev)) {
+			ring->use_doorbell = true;
+			ring->doorbell_index = (i == 0) ?
+				AMDGPU_DOORBELL_sDMA_ENGINE0 : AMDGPU_DOORBELL_sDMA_ENGINE1;
+		} else {
+			ring->use_pollmem = true;
+		}
 
 		sprintf(ring->name, "sdma%d", i);
 		r = amdgpu_ring_init(adev, ring, 1024,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 46009db3d195..e92fb372bc99 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -27,15 +27,14 @@
 #include "amdgpu_ucode.h"
 #include "amdgpu_trace.h"
 
-#include "vega10/soc15ip.h"
-#include "vega10/SDMA0/sdma0_4_0_offset.h"
-#include "vega10/SDMA0/sdma0_4_0_sh_mask.h"
-#include "vega10/SDMA1/sdma1_4_0_offset.h"
-#include "vega10/SDMA1/sdma1_4_0_sh_mask.h"
-#include "vega10/MMHUB/mmhub_1_0_offset.h"
-#include "vega10/MMHUB/mmhub_1_0_sh_mask.h"
-#include "vega10/HDP/hdp_4_0_offset.h"
-#include "raven1/SDMA0/sdma0_4_1_default.h"
+#include "sdma0/sdma0_4_0_offset.h"
+#include "sdma0/sdma0_4_0_sh_mask.h"
+#include "sdma1/sdma1_4_0_offset.h"
+#include "sdma1/sdma1_4_0_sh_mask.h"
+#include "mmhub/mmhub_1_0_offset.h"
+#include "mmhub/mmhub_1_0_sh_mask.h"
+#include "hdp/hdp_4_0_offset.h"
+#include "sdma0/sdma0_4_1_default.h"
 
 #include "soc15_common.h"
 #include "soc15.h"
@@ -53,97 +52,85 @@ static void sdma_v4_0_set_buffer_funcs(struct amdgpu_device *adev);
 static void sdma_v4_0_set_vm_pte_funcs(struct amdgpu_device *adev);
 static void sdma_v4_0_set_irq_funcs(struct amdgpu_device *adev);
 
-static const u32 golden_settings_sdma_4[] = {
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_CHICKEN_BITS), 0xfe931f07, 0x02831d07,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_CLK_CTRL), 0xff000ff0, 0x3f000100,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_GFX_IB_CNTL), 0x800f0100, 0x00000100,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_GFX_RB_WPTR_POLL_CNTL), 0xfffffff7, 0x00403000,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_PAGE_IB_CNTL), 0x800f0100, 0x00000100,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_PAGE_RB_WPTR_POLL_CNTL), 0x0000fff0, 0x00403000,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_POWER_CNTL), 0x003ff006, 0x0003c000,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_RLC0_IB_CNTL), 0x800f0100, 0x00000100,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL), 0x0000fff0, 0x00403000,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL), 0x800f0100, 0x00000100,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL), 0x0000fff0, 0x00403000,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_UTCL1_PAGE), 0x000003ff, 0x000003c0,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_CHICKEN_BITS), 0xfe931f07, 0x02831f07,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_CLK_CTRL), 0xffffffff, 0x3f000100,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_GFX_IB_CNTL), 0x800f0100, 0x00000100,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_GFX_RB_WPTR_POLL_CNTL), 0x0000fff0, 0x00403000,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_PAGE_IB_CNTL), 0x800f0100, 0x00000100,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_PAGE_RB_WPTR_POLL_CNTL), 0x0000fff0, 0x00403000,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_POWER_CNTL), 0x003ff000, 0x0003c000,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_RLC0_IB_CNTL), 0x800f0100, 0x00000100,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_RLC0_RB_WPTR_POLL_CNTL), 0x0000fff0, 0x00403000,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_RLC1_IB_CNTL), 0x800f0100, 0x00000100,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_RLC1_RB_WPTR_POLL_CNTL), 0x0000fff0, 0x00403000,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_UTCL1_PAGE), 0x000003ff, 0x000003c0
+static const struct soc15_reg_golden golden_settings_sdma_4[] = {
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CHICKEN_BITS, 0xfe931f07, 0x02831d07),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CLK_CTRL, 0xff000ff0, 0x3f000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GFX_IB_CNTL, 0x800f0100, 0x00000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GFX_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_PAGE_IB_CNTL, 0x800f0100, 0x00000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_PAGE_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_POWER_CNTL, 0x003ff006, 0x0003c000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_IB_CNTL, 0x800f0100, 0x00000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL, 0x800f0100, 0x00000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CHICKEN_BITS, 0xfe931f07, 0x02831f07),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CLK_CTRL, 0xffffffff, 0x3f000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GFX_IB_CNTL, 0x800f0100, 0x00000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GFX_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_PAGE_IB_CNTL, 0x800f0100, 0x00000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_PAGE_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_POWER_CNTL, 0x003ff000, 0x0003c000),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC0_IB_CNTL, 0x800f0100, 0x00000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC0_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC1_IB_CNTL, 0x800f0100, 0x00000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC1_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_UTCL1_PAGE, 0x000003ff, 0x000003c0)
 };
 
-static const u32 golden_settings_sdma_vg10[] = {
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG), 0x0018773f, 0x00104002,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG_READ), 0x0018773f, 0x00104002,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_GB_ADDR_CONFIG), 0x0018773f, 0x00104002,
-	SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_GB_ADDR_CONFIG_READ), 0x0018773f, 0x00104002
+static const struct soc15_reg_golden golden_settings_sdma_vg10[] = {
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG, 0x0018773f, 0x00104002),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG_READ, 0x0018773f, 0x00104002),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GB_ADDR_CONFIG, 0x0018773f, 0x00104002),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GB_ADDR_CONFIG_READ, 0x0018773f, 0x00104002)
 };
 
-static const u32 golden_settings_sdma_4_1[] =
+static const struct soc15_reg_golden golden_settings_sdma_4_1[] =
 {
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_CHICKEN_BITS), 0xfe931f07, 0x02831d07,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_CLK_CTRL), 0xffffffff, 0x3f000100,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_GFX_IB_CNTL), 0x800f0111, 0x00000100,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_GFX_RB_WPTR_POLL_CNTL), 0xfffffff7, 0x00403000,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_POWER_CNTL), 0xfc3fffff, 0x40000051,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_RLC0_IB_CNTL), 0x800f0111, 0x00000100,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL), 0xfffffff7, 0x00403000,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL), 0x800f0111, 0x00000100,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL), 0xfffffff7, 0x00403000,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_UTCL1_PAGE), 0x000003ff, 0x000003c0
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CHICKEN_BITS, 0xfe931f07, 0x02831d07),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CLK_CTRL, 0xffffffff, 0x3f000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GFX_IB_CNTL, 0x800f0111, 0x00000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GFX_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_POWER_CNTL, 0xfc3fffff, 0x40000051),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_IB_CNTL, 0x800f0111, 0x00000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL, 0x800f0111, 0x00000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0)
 };
 
-static const u32 golden_settings_sdma_rv1[] =
+static const struct soc15_reg_golden golden_settings_sdma_rv1[] =
 {
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG), 0x0018773f, 0x00000002,
-	SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG_READ), 0x0018773f, 0x00000002
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG, 0x0018773f, 0x00000002),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG_READ, 0x0018773f, 0x00000002)
 };
 
-static u32 sdma_v4_0_get_reg_offset(u32 instance, u32 internal_offset)
+static u32 sdma_v4_0_get_reg_offset(struct amdgpu_device *adev,
+		u32 instance, u32 offset)
 {
-	u32 base = 0;
-
-	switch (instance) {
-	case 0:
-		base = SDMA0_BASE.instance[0].segment[0];
-		break;
-	case 1:
-		base = SDMA1_BASE.instance[0].segment[0];
-		break;
-	default:
-		BUG();
-		break;
-	}
-
-	return base + internal_offset;
+	return ( 0 == instance ? (adev->reg_offset[SDMA0_HWIP][0][0] + offset) :
+			(adev->reg_offset[SDMA1_HWIP][0][0] + offset));
 }
 
 static void sdma_v4_0_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
-		amdgpu_program_register_sequence(adev,
+		soc15_program_register_sequence(adev,
 						 golden_settings_sdma_4,
-						 (const u32)ARRAY_SIZE(golden_settings_sdma_4));
-		amdgpu_program_register_sequence(adev,
+						 ARRAY_SIZE(golden_settings_sdma_4));
+		soc15_program_register_sequence(adev,
 						 golden_settings_sdma_vg10,
-						 (const u32)ARRAY_SIZE(golden_settings_sdma_vg10));
+						 ARRAY_SIZE(golden_settings_sdma_vg10));
 		break;
 	case CHIP_RAVEN:
-		amdgpu_program_register_sequence(adev,
+		soc15_program_register_sequence(adev,
 						 golden_settings_sdma_4_1,
-						 (const u32)ARRAY_SIZE(golden_settings_sdma_4_1));
-		amdgpu_program_register_sequence(adev,
+						 ARRAY_SIZE(golden_settings_sdma_4_1));
+		soc15_program_register_sequence(adev,
 						 golden_settings_sdma_rv1,
-						 (const u32)ARRAY_SIZE(golden_settings_sdma_rv1));
+						 ARRAY_SIZE(golden_settings_sdma_rv1));
 		break;
 	default:
 		break;
@@ -265,8 +252,8 @@ static uint64_t sdma_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
 		int me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
 		wptr = &local_wptr;
-		lowbit = RREG32(sdma_v4_0_get_reg_offset(me, mmSDMA0_GFX_RB_WPTR)) >> 2;
-		highbit = RREG32(sdma_v4_0_get_reg_offset(me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
+		lowbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR)) >> 2;
+		highbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
 
 		DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n",
 				me, highbit, lowbit);
@@ -315,8 +302,8 @@ static void sdma_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 				lower_32_bits(ring->wptr << 2),
 				me,
 				upper_32_bits(ring->wptr << 2));
-		WREG32(sdma_v4_0_get_reg_offset(me, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr << 2));
-		WREG32(sdma_v4_0_get_reg_offset(me, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr << 2));
+		WREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr << 2));
+		WREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr << 2));
 	}
 }
 
@@ -343,15 +330,13 @@ static void sdma_v4_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
  */
 static void sdma_v4_0_ring_emit_ib(struct amdgpu_ring *ring,
 					struct amdgpu_ib *ib,
-					unsigned vm_id, bool ctx_switch)
+					unsigned vmid, bool ctx_switch)
 {
-	u32 vmid = vm_id & 0xf;
-
 	/* IB packet must end on a 8 DW boundary */
 	sdma_v4_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
-			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid));
+			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
 	/* base must be 32 byte aligned */
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr) & 0xffffffe0);
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
@@ -370,13 +355,9 @@ static void sdma_v4_0_ring_emit_ib(struct amdgpu_ring *ring,
  */
 static void sdma_v4_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
 	u32 ref_and_mask = 0;
-	const struct nbio_hdp_flush_reg *nbio_hf_reg;
-
-	if (ring->adev->flags & AMD_IS_APU)
-		nbio_hf_reg = &nbio_v7_0_hdp_flush_reg;
-	else
-		nbio_hf_reg = &nbio_v6_1_hdp_flush_reg;
+	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio_funcs->hdp_flush_reg;
 
 	if (ring == &ring->adev->sdma.instance[0].ring)
 		ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0;
@@ -386,8 +367,8 @@ static void sdma_v4_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
 			  SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) |
 			  SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */
-	amdgpu_ring_write(ring, nbio_hf_reg->hdp_flush_done_offset << 2);
-	amdgpu_ring_write(ring, nbio_hf_reg->hdp_flush_req_offset << 2);
+	amdgpu_ring_write(ring, (adev->nbio_funcs->get_hdp_flush_done_offset(adev)) << 2);
+	amdgpu_ring_write(ring, (adev->nbio_funcs->get_hdp_flush_req_offset(adev)) << 2);
 	amdgpu_ring_write(ring, ref_and_mask); /* reference */
 	amdgpu_ring_write(ring, ref_and_mask); /* mask */
 	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
@@ -396,6 +377,8 @@ static void sdma_v4_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 
 static void sdma_v4_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_SRBM_WRITE) |
 			  SDMA_PKT_SRBM_WRITE_HEADER_BYTE_EN(0xf));
 	amdgpu_ring_write(ring, SOC15_REG_OFFSET(HDP, 0, mmHDP_READ_CACHE_INVALIDATE));
@@ -460,12 +443,12 @@ static void sdma_v4_0_gfx_stop(struct amdgpu_device *adev)
 		amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size);
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		rb_cntl = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_CNTL));
+		rb_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
-		ib_cntl = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_IB_CNTL));
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
+		ib_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL));
 		ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 0);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
 	}
 
 	sdma0->ready = false;
@@ -522,18 +505,18 @@ static void sdma_v4_0_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
 	}
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		f32_cntl = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_CNTL));
+		f32_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_CNTL));
 		f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
 				AUTO_CTXSW_ENABLE, enable ? 1 : 0);
 		if (enable && amdgpu_sdma_phase_quantum) {
-			WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_PHASE0_QUANTUM),
+			WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_PHASE0_QUANTUM),
 			       phase_quantum);
-			WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_PHASE1_QUANTUM),
+			WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_PHASE1_QUANTUM),
 			       phase_quantum);
-			WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_PHASE2_QUANTUM),
+			WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_PHASE2_QUANTUM),
 			       phase_quantum);
 		}
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_CNTL), f32_cntl);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_CNTL), f32_cntl);
 	}
 
 }
@@ -557,9 +540,9 @@ static void sdma_v4_0_enable(struct amdgpu_device *adev, bool enable)
 	}
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		f32_cntl = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_F32_CNTL));
+		f32_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_F32_CNTL));
 		f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, enable ? 0 : 1);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_F32_CNTL), f32_cntl);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_F32_CNTL), f32_cntl);
 	}
 }
 
@@ -587,48 +570,48 @@ static int sdma_v4_0_gfx_resume(struct amdgpu_device *adev)
 		ring = &adev->sdma.instance[i].ring;
 		wb_offset = (ring->rptr_offs * 4);
 
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL), 0);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL), 0);
 
 		/* Set ring buffer size in dwords */
 		rb_bufsz = order_base_2(ring->ring_size / 4);
-		rb_cntl = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_CNTL));
+		rb_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SIZE, rb_bufsz);
 #ifdef __BIG_ENDIAN
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SWAP_ENABLE, 1);
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL,
 					RPTR_WRITEBACK_SWAP_ENABLE, 1);
 #endif
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
 
 		/* Initialize the ring buffer's read and write pointers */
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_RPTR), 0);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_RPTR_HI), 0);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR), 0);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_HI), 0);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR), 0);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_HI), 0);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), 0);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), 0);
 
 		/* set the wb address whether it's enabled or not */
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_RPTR_ADDR_HI),
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_HI),
 		       upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_RPTR_ADDR_LO),
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_LO),
 		       lower_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC);
 
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RPTR_WRITEBACK_ENABLE, 1);
 
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_BASE), ring->gpu_addr >> 8);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_BASE_HI), ring->gpu_addr >> 40);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_BASE), ring->gpu_addr >> 8);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_BASE_HI), ring->gpu_addr >> 40);
 
 		ring->wptr = 0;
 
 		/* before programing wptr to a less value, need set minor_ptr_update first */
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 1);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 1);
 
 		if (!amdgpu_sriov_vf(adev)) { /* only bare-metal use register write for wptr */
-			WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr) << 2);
-			WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr) << 2);
+			WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr) << 2);
+			WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr) << 2);
 		}
 
-		doorbell = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_DOORBELL));
-		doorbell_offset = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_DOORBELL_OFFSET));
+		doorbell = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL));
+		doorbell_offset = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL_OFFSET));
 
 		if (ring->use_doorbell) {
 			doorbell = REG_SET_FIELD(doorbell, SDMA0_GFX_DOORBELL, ENABLE, 1);
@@ -637,55 +620,53 @@ static int sdma_v4_0_gfx_resume(struct amdgpu_device *adev)
 		} else {
 			doorbell = REG_SET_FIELD(doorbell, SDMA0_GFX_DOORBELL, ENABLE, 0);
 		}
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_DOORBELL), doorbell);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_DOORBELL_OFFSET), doorbell_offset);
-		if (adev->flags & AMD_IS_APU)
-			nbio_v7_0_sdma_doorbell_range(adev, i, ring->use_doorbell, ring->doorbell_index);
-		else
-			nbio_v6_1_sdma_doorbell_range(adev, i, ring->use_doorbell, ring->doorbell_index);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL), doorbell);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL_OFFSET), doorbell_offset);
+		adev->nbio_funcs->sdma_doorbell_range(adev, i, ring->use_doorbell,
+						      ring->doorbell_index);
 
 		if (amdgpu_sriov_vf(adev))
 			sdma_v4_0_ring_set_wptr(ring);
 
 		/* set minor_ptr_update to 0 after wptr programed */
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 0);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 0);
 
 		/* set utc l1 enable flag always to 1 */
-		temp = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_CNTL));
+		temp = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_CNTL));
 		temp = REG_SET_FIELD(temp, SDMA0_CNTL, UTC_L1_ENABLE, 1);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_CNTL), temp);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_CNTL), temp);
 
 		if (!amdgpu_sriov_vf(adev)) {
 			/* unhalt engine */
-			temp = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_F32_CNTL));
+			temp = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_F32_CNTL));
 			temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0);
-			WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_F32_CNTL), temp);
+			WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_F32_CNTL), temp);
 		}
 
 		/* setup the wptr shadow polling */
 		wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO),
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO),
 		       lower_32_bits(wptr_gpu_addr));
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI),
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI),
 		       upper_32_bits(wptr_gpu_addr));
-		wptr_poll_cntl = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL));
+		wptr_poll_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL));
 		if (amdgpu_sriov_vf(adev))
 			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 1);
 		else
 			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 0);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL), wptr_poll_cntl);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL), wptr_poll_cntl);
 
 		/* enable DMA RB */
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 1);
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
 
-		ib_cntl = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_IB_CNTL));
+		ib_cntl = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL));
 		ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 1);
 #ifdef __BIG_ENDIAN
 		ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_SWAP_ENABLE, 1);
 #endif
 		/* enable DMA IBs */
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
 
 		ring->ready = true;
 
@@ -816,12 +797,12 @@ static int sdma_v4_0_load_microcode(struct amdgpu_device *adev)
 			(adev->sdma.instance[i].fw->data +
 				le32_to_cpu(hdr->header.ucode_array_offset_bytes));
 
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_UCODE_ADDR), 0);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_UCODE_ADDR), 0);
 
 		for (j = 0; j < fw_size; j++)
-			WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_UCODE_DATA), le32_to_cpup(fw_data++));
+			WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_UCODE_DATA), le32_to_cpup(fw_data++));
 
-		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_UCODE_ADDR), adev->sdma.instance[i].fw_version);
+		WREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_UCODE_ADDR), adev->sdma.instance[i].fw_version);
 	}
 
 	return 0;
@@ -886,7 +867,7 @@ static int sdma_v4_0_ring_test_ring(struct amdgpu_ring *ring)
 	u32 tmp;
 	u64 gpu_addr;
 
-	r = amdgpu_wb_get(adev, &index);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r);
 		return r;
@@ -899,7 +880,7 @@ static int sdma_v4_0_ring_test_ring(struct amdgpu_ring *ring)
 	r = amdgpu_ring_alloc(ring, 5);
 	if (r) {
 		DRM_ERROR("amdgpu: dma failed to lock ring %d (%d).\n", ring->idx, r);
-		amdgpu_wb_free(adev, index);
+		amdgpu_device_wb_free(adev, index);
 		return r;
 	}
 
@@ -919,13 +900,13 @@ static int sdma_v4_0_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n", ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
 			  ring->idx, tmp);
 		r = -EINVAL;
 	}
-	amdgpu_wb_free(adev, index);
+	amdgpu_device_wb_free(adev, index);
 
 	return r;
 }
@@ -948,7 +929,7 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	u32 tmp = 0;
 	u64 gpu_addr;
 
-	r = amdgpu_wb_get(adev, &index);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
 		dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
 		return r;
@@ -990,7 +971,7 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	}
 	tmp = le32_to_cpu(adev->wb.wb[index]);
 	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp);
@@ -1000,7 +981,7 @@ err1:
 	amdgpu_ib_free(adev, &ib, NULL);
 	dma_fence_put(f);
 err0:
-	amdgpu_wb_free(adev, index);
+	amdgpu_device_wb_free(adev, index);
 	return r;
 }
 
@@ -1152,23 +1133,24 @@ static void sdma_v4_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using sDMA (VEGA10).
  */
 static void sdma_v4_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					 unsigned vm_id, uint64_t pd_addr)
+					 unsigned vmid, uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
-	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vm_id);
+	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vmid);
+	uint64_t flags = AMDGPU_PTE_VALID;
 	unsigned eng = ring->vm_inv_eng;
 
-	pd_addr = amdgpu_gart_get_vm_pde(ring->adev, pd_addr);
-	pd_addr |= AMDGPU_PTE_VALID;
+	amdgpu_gart_get_vm_pde(ring->adev, -1, &pd_addr, &flags);
+	pd_addr |= flags;
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_SRBM_WRITE) |
 			  SDMA_PKT_SRBM_WRITE_HEADER_BYTE_EN(0xf));
-	amdgpu_ring_write(ring, hub->ctx0_ptb_addr_lo32 + vm_id * 2);
+	amdgpu_ring_write(ring, hub->ctx0_ptb_addr_lo32 + vmid * 2);
 	amdgpu_ring_write(ring, lower_32_bits(pd_addr));
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_SRBM_WRITE) |
 			  SDMA_PKT_SRBM_WRITE_HEADER_BYTE_EN(0xf));
-	amdgpu_ring_write(ring, hub->ctx0_ptb_addr_hi32 + vm_id * 2);
+	amdgpu_ring_write(ring, hub->ctx0_ptb_addr_hi32 + vmid * 2);
 	amdgpu_ring_write(ring, upper_32_bits(pd_addr));
 
 	/* flush TLB */
@@ -1183,8 +1165,8 @@ static void sdma_v4_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 			  SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* equal */
 	amdgpu_ring_write(ring, (hub->vm_inv_eng0_ack + eng) << 2);
 	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, 1 << vm_id); /* reference */
-	amdgpu_ring_write(ring, 1 << vm_id); /* mask */
+	amdgpu_ring_write(ring, 1 << vmid); /* reference */
+	amdgpu_ring_write(ring, 1 << vmid); /* mask */
 	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
 			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10));
 }
@@ -1317,7 +1299,7 @@ static bool sdma_v4_0_is_idle(void *handle)
 	u32 i;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		u32 tmp = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_STATUS_REG));
+		u32 tmp = RREG32(sdma_v4_0_get_reg_offset(adev, i, mmSDMA0_STATUS_REG));
 
 		if (!(tmp & SDMA0_STATUS_REG__IDLE_MASK))
 			return false;
@@ -1333,8 +1315,8 @@ static int sdma_v4_0_wait_for_idle(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		sdma0 = RREG32(sdma_v4_0_get_reg_offset(0, mmSDMA0_STATUS_REG));
-		sdma1 = RREG32(sdma_v4_0_get_reg_offset(1, mmSDMA0_STATUS_REG));
+		sdma0 = RREG32(sdma_v4_0_get_reg_offset(adev, 0, mmSDMA0_STATUS_REG));
+		sdma1 = RREG32(sdma_v4_0_get_reg_offset(adev, 1, mmSDMA0_STATUS_REG));
 
 		if (sdma0 & sdma1 & SDMA0_STATUS_REG__IDLE_MASK)
 			return 0;
@@ -1358,8 +1340,8 @@ static int sdma_v4_0_set_trap_irq_state(struct amdgpu_device *adev,
 	u32 sdma_cntl;
 
 	u32 reg_offset = (type == AMDGPU_SDMA_IRQ_TRAP0) ?
-		sdma_v4_0_get_reg_offset(0, mmSDMA0_CNTL) :
-		sdma_v4_0_get_reg_offset(1, mmSDMA0_CNTL);
+		sdma_v4_0_get_reg_offset(adev, 0, mmSDMA0_CNTL) :
+		sdma_v4_0_get_reg_offset(adev, 1, mmSDMA0_CNTL);
 
 	sdma_cntl = RREG32(reg_offset);
 	sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA0_CNTL, TRAP_ENABLE,
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index 8284d5dbfc30..543101d5a5ed 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -1390,65 +1390,65 @@ static void si_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_TAHITI:
-		amdgpu_program_register_sequence(adev,
-						 tahiti_golden_registers,
-						 (const u32)ARRAY_SIZE(tahiti_golden_registers));
-		amdgpu_program_register_sequence(adev,
-						 tahiti_golden_rlc_registers,
-						 (const u32)ARRAY_SIZE(tahiti_golden_rlc_registers));
-		amdgpu_program_register_sequence(adev,
-						 tahiti_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(tahiti_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 tahiti_golden_registers2,
-						 (const u32)ARRAY_SIZE(tahiti_golden_registers2));
+		amdgpu_device_program_register_sequence(adev,
+							tahiti_golden_registers,
+							ARRAY_SIZE(tahiti_golden_registers));
+		amdgpu_device_program_register_sequence(adev,
+							tahiti_golden_rlc_registers,
+							ARRAY_SIZE(tahiti_golden_rlc_registers));
+		amdgpu_device_program_register_sequence(adev,
+							tahiti_mgcg_cgcg_init,
+							ARRAY_SIZE(tahiti_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							tahiti_golden_registers2,
+							ARRAY_SIZE(tahiti_golden_registers2));
 		break;
 	case CHIP_PITCAIRN:
-		amdgpu_program_register_sequence(adev,
-						 pitcairn_golden_registers,
-						 (const u32)ARRAY_SIZE(pitcairn_golden_registers));
-		amdgpu_program_register_sequence(adev,
-						 pitcairn_golden_rlc_registers,
-						 (const u32)ARRAY_SIZE(pitcairn_golden_rlc_registers));
-		amdgpu_program_register_sequence(adev,
-						 pitcairn_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(pitcairn_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							pitcairn_golden_registers,
+							ARRAY_SIZE(pitcairn_golden_registers));
+		amdgpu_device_program_register_sequence(adev,
+							pitcairn_golden_rlc_registers,
+							ARRAY_SIZE(pitcairn_golden_rlc_registers));
+		amdgpu_device_program_register_sequence(adev,
+							pitcairn_mgcg_cgcg_init,
+							ARRAY_SIZE(pitcairn_mgcg_cgcg_init));
 		break;
 	case CHIP_VERDE:
-		amdgpu_program_register_sequence(adev,
-						 verde_golden_registers,
-						 (const u32)ARRAY_SIZE(verde_golden_registers));
-		amdgpu_program_register_sequence(adev,
-						 verde_golden_rlc_registers,
-						 (const u32)ARRAY_SIZE(verde_golden_rlc_registers));
-		amdgpu_program_register_sequence(adev,
-						 verde_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(verde_mgcg_cgcg_init));
-		amdgpu_program_register_sequence(adev,
-						 verde_pg_init,
-						 (const u32)ARRAY_SIZE(verde_pg_init));
+		amdgpu_device_program_register_sequence(adev,
+							verde_golden_registers,
+							ARRAY_SIZE(verde_golden_registers));
+		amdgpu_device_program_register_sequence(adev,
+							verde_golden_rlc_registers,
+							ARRAY_SIZE(verde_golden_rlc_registers));
+		amdgpu_device_program_register_sequence(adev,
+							verde_mgcg_cgcg_init,
+							ARRAY_SIZE(verde_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							verde_pg_init,
+							ARRAY_SIZE(verde_pg_init));
 		break;
 	case CHIP_OLAND:
-		amdgpu_program_register_sequence(adev,
-						 oland_golden_registers,
-						 (const u32)ARRAY_SIZE(oland_golden_registers));
-		amdgpu_program_register_sequence(adev,
-						 oland_golden_rlc_registers,
-						 (const u32)ARRAY_SIZE(oland_golden_rlc_registers));
-		amdgpu_program_register_sequence(adev,
-						 oland_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(oland_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							oland_golden_registers,
+							ARRAY_SIZE(oland_golden_registers));
+		amdgpu_device_program_register_sequence(adev,
+							oland_golden_rlc_registers,
+							ARRAY_SIZE(oland_golden_rlc_registers));
+		amdgpu_device_program_register_sequence(adev,
+							oland_mgcg_cgcg_init,
+							ARRAY_SIZE(oland_mgcg_cgcg_init));
 		break;
 	case CHIP_HAINAN:
-		amdgpu_program_register_sequence(adev,
-						 hainan_golden_registers,
-						 (const u32)ARRAY_SIZE(hainan_golden_registers));
-		amdgpu_program_register_sequence(adev,
-						 hainan_golden_registers2,
-						 (const u32)ARRAY_SIZE(hainan_golden_registers2));
-		amdgpu_program_register_sequence(adev,
-						 hainan_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(hainan_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							hainan_golden_registers,
+							ARRAY_SIZE(hainan_golden_registers));
+		amdgpu_device_program_register_sequence(adev,
+							hainan_golden_registers2,
+							ARRAY_SIZE(hainan_golden_registers2));
+		amdgpu_device_program_register_sequence(adev,
+							hainan_mgcg_cgcg_init,
+							ARRAY_SIZE(hainan_mgcg_cgcg_init));
 		break;
 
 
@@ -1959,42 +1959,42 @@ int si_set_ip_blocks(struct amdgpu_device *adev)
 	case CHIP_VERDE:
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
-		amdgpu_ip_block_add(adev, &si_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v6_0_ip_block);
-		amdgpu_ip_block_add(adev, &si_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v6_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 		else
-			amdgpu_ip_block_add(adev, &dce_v6_0_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v6_0_ip_block);
-		amdgpu_ip_block_add(adev, &si_dma_ip_block);
-		/* amdgpu_ip_block_add(adev, &uvd_v3_1_ip_block); */
-		/* amdgpu_ip_block_add(adev, &vce_v1_0_ip_block); */
+			amdgpu_device_ip_block_add(adev, &dce_v6_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v6_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
+		/* amdgpu_device_ip_block_add(adev, &uvd_v3_1_ip_block); */
+		/* amdgpu_device_ip_block_add(adev, &vce_v1_0_ip_block); */
 		break;
 	case CHIP_OLAND:
-		amdgpu_ip_block_add(adev, &si_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v6_0_ip_block);
-		amdgpu_ip_block_add(adev, &si_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v6_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 		else
-			amdgpu_ip_block_add(adev, &dce_v6_4_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v6_0_ip_block);
-		amdgpu_ip_block_add(adev, &si_dma_ip_block);
-		/* amdgpu_ip_block_add(adev, &uvd_v3_1_ip_block); */
-		/* amdgpu_ip_block_add(adev, &vce_v1_0_ip_block); */
+			amdgpu_device_ip_block_add(adev, &dce_v6_4_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v6_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
+		/* amdgpu_device_ip_block_add(adev, &uvd_v3_1_ip_block); */
+		/* amdgpu_device_ip_block_add(adev, &vce_v1_0_ip_block); */
 		break;
 	case CHIP_HAINAN:
-		amdgpu_ip_block_add(adev, &si_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v6_0_ip_block);
-		amdgpu_ip_block_add(adev, &si_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v6_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v6_0_ip_block);
-		amdgpu_ip_block_add(adev, &si_dma_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v6_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &si_dma_ip_block);
 		break;
 	default:
 		BUG();
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index 3fa2fbf8c9a1..9a29c1399091 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
@@ -61,14 +61,14 @@ static void si_dma_ring_set_wptr(struct amdgpu_ring *ring)
 
 static void si_dma_ring_emit_ib(struct amdgpu_ring *ring,
 				struct amdgpu_ib *ib,
-				unsigned vm_id, bool ctx_switch)
+				unsigned vmid, bool ctx_switch)
 {
 	/* The indirect buffer packet must end on an 8 DW boundary in the DMA ring.
 	 * Pad as necessary with NOPs.
 	 */
 	while ((lower_32_bits(ring->wptr) & 7) != 5)
 		amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0, 0));
-	amdgpu_ring_write(ring, DMA_IB_PACKET(DMA_PACKET_INDIRECT_BUFFER, vm_id, 0));
+	amdgpu_ring_write(ring, DMA_IB_PACKET(DMA_PACKET_INDIRECT_BUFFER, vmid, 0));
 	amdgpu_ring_write(ring, (ib->gpu_addr & 0xFFFFFFE0));
 	amdgpu_ring_write(ring, (ib->length_dw << 12) | (upper_32_bits(ib->gpu_addr) & 0xFF));
 
@@ -221,7 +221,7 @@ static int si_dma_ring_test_ring(struct amdgpu_ring *ring)
 	u32 tmp;
 	u64 gpu_addr;
 
-	r = amdgpu_wb_get(adev, &index);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r);
 		return r;
@@ -234,7 +234,7 @@ static int si_dma_ring_test_ring(struct amdgpu_ring *ring)
 	r = amdgpu_ring_alloc(ring, 4);
 	if (r) {
 		DRM_ERROR("amdgpu: dma failed to lock ring %d (%d).\n", ring->idx, r);
-		amdgpu_wb_free(adev, index);
+		amdgpu_device_wb_free(adev, index);
 		return r;
 	}
 
@@ -252,13 +252,13 @@ static int si_dma_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n", ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
 			  ring->idx, tmp);
 		r = -EINVAL;
 	}
-	amdgpu_wb_free(adev, index);
+	amdgpu_device_wb_free(adev, index);
 
 	return r;
 }
@@ -281,7 +281,7 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	u64 gpu_addr;
 	long r;
 
-	r = amdgpu_wb_get(adev, &index);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
 		dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
 		return r;
@@ -317,7 +317,7 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	}
 	tmp = le32_to_cpu(adev->wb.wb[index]);
 	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp);
@@ -328,7 +328,7 @@ err1:
 	amdgpu_ib_free(adev, &ib, NULL);
 	dma_fence_put(f);
 err0:
-	amdgpu_wb_free(adev, index);
+	amdgpu_device_wb_free(adev, index);
 	return r;
 }
 
@@ -473,25 +473,25 @@ static void si_dma_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using sDMA (VI).
  */
 static void si_dma_ring_emit_vm_flush(struct amdgpu_ring *ring,
-				      unsigned vm_id, uint64_t pd_addr)
+				      unsigned vmid, uint64_t pd_addr)
 {
 	amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
-	if (vm_id < 8)
-		amdgpu_ring_write(ring, (0xf << 16) | (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id));
+	if (vmid < 8)
+		amdgpu_ring_write(ring, (0xf << 16) | (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vmid));
 	else
-		amdgpu_ring_write(ring, (0xf << 16) | (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + (vm_id - 8)));
+		amdgpu_ring_write(ring, (0xf << 16) | (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + (vmid - 8)));
 	amdgpu_ring_write(ring, pd_addr >> 12);
 
 	/* bits 0-7 are the VM contexts0-7 */
 	amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
 	amdgpu_ring_write(ring, (0xf << 16) | (VM_INVALIDATE_REQUEST));
-	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vmid);
 
 	/* wait for invalidate to complete */
 	amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_POLL_REG_MEM, 0, 0, 0, 0));
 	amdgpu_ring_write(ring, VM_INVALIDATE_REQUEST);
 	amdgpu_ring_write(ring, 0xff << 16); /* retry */
-	amdgpu_ring_write(ring, 1 << vm_id); /* mask */
+	amdgpu_ring_write(ring, 1 << vmid); /* mask */
 	amdgpu_ring_write(ring, 0); /* value */
 	amdgpu_ring_write(ring, (0 << 28) | 0x20); /* func(always) | poll interval */
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 51fd0c9a20a5..ce675a7f179a 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -3464,6 +3464,11 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		    (adev->pdev->device == 0x6667)) {
 			max_sclk = 75000;
 		}
+		if ((adev->pdev->revision == 0xC3) ||
+		    (adev->pdev->device == 0x6665)) {
+			max_sclk = 60000;
+			max_mclk = 80000;
+		}
 	} else if (adev->asic_type == CHIP_OLAND) {
 		if ((adev->pdev->revision == 0xC7) ||
 		    (adev->pdev->revision == 0x80) ||
@@ -5845,9 +5850,9 @@ static int si_set_mc_special_registers(struct amdgpu_device *adev,
 					((temp_reg & 0xffff0000)) |
 					((table->mc_reg_table_entry[k].mc_data[i] & 0xffff0000) >> 16);
 			j++;
+
 			if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
-
 			temp_reg = RREG32(MC_PMG_CMD_MRS);
 			table->mc_reg_address[j].s1 = MC_PMG_CMD_MRS;
 			table->mc_reg_address[j].s0 = MC_SEQ_PMG_CMD_MRS_LP;
@@ -5859,18 +5864,16 @@ static int si_set_mc_special_registers(struct amdgpu_device *adev,
 					table->mc_reg_table_entry[k].mc_data[j] |= 0x100;
 			}
 			j++;
-			if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
-				return -EINVAL;
 
 			if (adev->mc.vram_type != AMDGPU_VRAM_TYPE_GDDR5) {
+				if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
+					return -EINVAL;
 				table->mc_reg_address[j].s1 = MC_PMG_AUTO_CMD;
 				table->mc_reg_address[j].s0 = MC_PMG_AUTO_CMD;
 				for (k = 0; k < table->num_entries; k++)
 					table->mc_reg_table_entry[k].mc_data[j] =
 						(table->mc_reg_table_entry[k].mc_data[i] & 0xffff0000) >> 16;
 				j++;
-				if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
-					return -EINVAL;
 			}
 			break;
 		case MC_SEQ_RESERVE_M:
@@ -5882,8 +5885,6 @@ static int si_set_mc_special_registers(struct amdgpu_device *adev,
 					(temp_reg & 0xffff0000) |
 					(table->mc_reg_table_entry[k].mc_data[i] & 0x0000ffff);
 			j++;
-			if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
-				return -EINVAL;
 			break;
 		default:
 			break;
diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
index d2c6b80309c8..60dad63098a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
@@ -146,7 +146,7 @@ static void si_ih_decode_iv(struct amdgpu_device *adev,
 	entry->src_id = dw[0] & 0xff;
 	entry->src_data[0] = dw[1] & 0xfffffff;
 	entry->ring_id = dw[2] & 0xff;
-	entry->vm_id = (dw[2] >> 8) & 0xff;
+	entry->vmid = (dw[2] >> 8) & 0xff;
 
 	adev->irq.ih.rptr += 16;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 4e67fe1e7955..a04a033f57de 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -34,18 +34,17 @@
 #include "atom.h"
 #include "amd_pcie.h"
 
-#include "vega10/soc15ip.h"
-#include "vega10/UVD/uvd_7_0_offset.h"
-#include "vega10/GC/gc_9_0_offset.h"
-#include "vega10/GC/gc_9_0_sh_mask.h"
-#include "vega10/SDMA0/sdma0_4_0_offset.h"
-#include "vega10/SDMA1/sdma1_4_0_offset.h"
-#include "vega10/HDP/hdp_4_0_offset.h"
-#include "vega10/HDP/hdp_4_0_sh_mask.h"
-#include "vega10/MP/mp_9_0_offset.h"
-#include "vega10/MP/mp_9_0_sh_mask.h"
-#include "vega10/SMUIO/smuio_9_0_offset.h"
-#include "vega10/SMUIO/smuio_9_0_sh_mask.h"
+#include "uvd/uvd_7_0_offset.h"
+#include "gc/gc_9_0_offset.h"
+#include "gc/gc_9_0_sh_mask.h"
+#include "sdma0/sdma0_4_0_offset.h"
+#include "sdma1/sdma1_4_0_offset.h"
+#include "hdp/hdp_4_0_offset.h"
+#include "hdp/hdp_4_0_sh_mask.h"
+#include "mp/mp_9_0_offset.h"
+#include "mp/mp_9_0_sh_mask.h"
+#include "smuio/smuio_9_0_offset.h"
+#include "smuio/smuio_9_0_sh_mask.h"
 
 #include "soc15.h"
 #include "soc15_common.h"
@@ -101,15 +100,8 @@ static u32 soc15_pcie_rreg(struct amdgpu_device *adev, u32 reg)
 {
 	unsigned long flags, address, data;
 	u32 r;
-	const struct nbio_pcie_index_data *nbio_pcie_id;
-
-	if (adev->flags & AMD_IS_APU)
-		nbio_pcie_id = &nbio_v7_0_pcie_index_data;
-	else
-		nbio_pcie_id = &nbio_v6_1_pcie_index_data;
-
-	address = nbio_pcie_id->index_offset;
-	data = nbio_pcie_id->data_offset;
+	address = adev->nbio_funcs->get_pcie_index_offset(adev);
+	data = adev->nbio_funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	WREG32(address, reg);
@@ -122,15 +114,9 @@ static u32 soc15_pcie_rreg(struct amdgpu_device *adev, u32 reg)
 static void soc15_pcie_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 {
 	unsigned long flags, address, data;
-	const struct nbio_pcie_index_data *nbio_pcie_id;
 
-	if (adev->flags & AMD_IS_APU)
-		nbio_pcie_id = &nbio_v7_0_pcie_index_data;
-	else
-		nbio_pcie_id = &nbio_v6_1_pcie_index_data;
-
-	address = nbio_pcie_id->index_offset;
-	data = nbio_pcie_id->data_offset;
+	address = adev->nbio_funcs->get_pcie_index_offset(adev);
+	data = adev->nbio_funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	WREG32(address, reg);
@@ -242,41 +228,9 @@ static void soc15_se_cac_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 
 static u32 soc15_get_config_memsize(struct amdgpu_device *adev)
 {
-	if (adev->flags & AMD_IS_APU)
-		return nbio_v7_0_get_memsize(adev);
-	else
-		return nbio_v6_1_get_memsize(adev);
+	return adev->nbio_funcs->get_memsize(adev);
 }
 
-static const u32 vega10_golden_init[] =
-{
-};
-
-static const u32 raven_golden_init[] =
-{
-};
-
-static void soc15_init_golden_registers(struct amdgpu_device *adev)
-{
-	/* Some of the registers might be dependent on GRBM_GFX_INDEX */
-	mutex_lock(&adev->grbm_idx_mutex);
-
-	switch (adev->asic_type) {
-	case CHIP_VEGA10:
-		amdgpu_program_register_sequence(adev,
-						 vega10_golden_init,
-						 (const u32)ARRAY_SIZE(vega10_golden_init));
-		break;
-	case CHIP_RAVEN:
-		amdgpu_program_register_sequence(adev,
-						 raven_golden_init,
-						 (const u32)ARRAY_SIZE(raven_golden_init));
-		break;
-	default:
-		break;
-	}
-	mutex_unlock(&adev->grbm_idx_mutex);
-}
 static u32 soc15_get_xclk(struct amdgpu_device *adev)
 {
 	return adev->clock.spll.reference_freq;
@@ -332,25 +286,34 @@ static bool soc15_read_bios_from_rom(struct amdgpu_device *adev,
 	return true;
 }
 
-static struct amdgpu_allowed_register_entry soc15_allowed_read_registers[] = {
-	{ SOC15_REG_OFFSET(GC, 0, mmGRBM_STATUS)},
-	{ SOC15_REG_OFFSET(GC, 0, mmGRBM_STATUS2)},
-	{ SOC15_REG_OFFSET(GC, 0, mmGRBM_STATUS_SE0)},
-	{ SOC15_REG_OFFSET(GC, 0, mmGRBM_STATUS_SE1)},
-	{ SOC15_REG_OFFSET(GC, 0, mmGRBM_STATUS_SE2)},
-	{ SOC15_REG_OFFSET(GC, 0, mmGRBM_STATUS_SE3)},
-	{ SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_STATUS_REG)},
-	{ SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_STATUS_REG)},
-	{ SOC15_REG_OFFSET(GC, 0, mmCP_STAT)},
-	{ SOC15_REG_OFFSET(GC, 0, mmCP_STALLED_STAT1)},
-	{ SOC15_REG_OFFSET(GC, 0, mmCP_STALLED_STAT2)},
-	{ SOC15_REG_OFFSET(GC, 0, mmCP_STALLED_STAT3)},
-	{ SOC15_REG_OFFSET(GC, 0, mmCP_CPF_BUSY_STAT)},
-	{ SOC15_REG_OFFSET(GC, 0, mmCP_CPF_STALLED_STAT1)},
-	{ SOC15_REG_OFFSET(GC, 0, mmCP_CPF_STATUS)},
-	{ SOC15_REG_OFFSET(GC, 0, mmCP_CPC_STALLED_STAT1)},
-	{ SOC15_REG_OFFSET(GC, 0, mmCP_CPC_STATUS)},
-	{ SOC15_REG_OFFSET(GC, 0, mmGB_ADDR_CONFIG)},
+struct soc15_allowed_register_entry {
+	uint32_t hwip;
+	uint32_t inst;
+	uint32_t seg;
+	uint32_t reg_offset;
+	bool grbm_indexed;
+};
+
+
+static struct soc15_allowed_register_entry soc15_allowed_read_registers[] = {
+	{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS)},
+	{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS2)},
+	{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS_SE0)},
+	{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS_SE1)},
+	{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS_SE2)},
+	{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS_SE3)},
+	{ SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_STATUS_REG)},
+	{ SOC15_REG_ENTRY(SDMA1, 0, mmSDMA1_STATUS_REG)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_STAT)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_STALLED_STAT1)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_STALLED_STAT2)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_STALLED_STAT3)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_BUSY_STAT)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STALLED_STAT1)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STATUS)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STALLED_STAT1)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STATUS)},
+	{ SOC15_REG_ENTRY(GC, 0, mmGB_ADDR_CONFIG)},
 };
 
 static uint32_t soc15_read_indexed_register(struct amdgpu_device *adev, u32 se_num,
@@ -377,12 +340,9 @@ static uint32_t soc15_get_register_value(struct amdgpu_device *adev,
 	if (indexed) {
 		return soc15_read_indexed_register(adev, se_num, sh_num, reg_offset);
 	} else {
-		switch (reg_offset) {
-		case SOC15_REG_OFFSET(GC, 0, mmGB_ADDR_CONFIG):
+		if (reg_offset == SOC15_REG_OFFSET(GC, 0, mmGB_ADDR_CONFIG))
 			return adev->gfx.config.gb_addr_config;
-		default:
-			return RREG32(reg_offset);
-		}
+		return RREG32(reg_offset);
 	}
 }
 
@@ -390,10 +350,13 @@ static int soc15_read_register(struct amdgpu_device *adev, u32 se_num,
 			    u32 sh_num, u32 reg_offset, u32 *value)
 {
 	uint32_t i;
+	struct soc15_allowed_register_entry  *en;
 
 	*value = 0;
 	for (i = 0; i < ARRAY_SIZE(soc15_allowed_read_registers); i++) {
-		if (reg_offset != soc15_allowed_read_registers[i].reg_offset)
+		en = &soc15_allowed_read_registers[i];
+		if (reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg]
+					+ en->reg_offset))
 			continue;
 
 		*value = soc15_get_register_value(adev,
@@ -404,6 +367,43 @@ static int soc15_read_register(struct amdgpu_device *adev, u32 se_num,
 	return -EINVAL;
 }
 
+
+/**
+ * soc15_program_register_sequence - program an array of registers.
+ *
+ * @adev: amdgpu_device pointer
+ * @regs: pointer to the register array
+ * @array_size: size of the register array
+ *
+ * Programs an array or registers with and and or masks.
+ * This is a helper for setting golden registers.
+ */
+
+void soc15_program_register_sequence(struct amdgpu_device *adev,
+					     const struct soc15_reg_golden *regs,
+					     const u32 array_size)
+{
+	const struct soc15_reg_golden *entry;
+	u32 tmp, reg;
+	int i;
+
+	for (i = 0; i < array_size; ++i) {
+		entry = &regs[i];
+		reg =  adev->reg_offset[entry->hwip][entry->instance][entry->segment] + entry->reg;
+
+		if (entry->and_mask == 0xffffffff) {
+			tmp = entry->or_mask;
+		} else {
+			tmp = RREG32(reg);
+			tmp &= ~(entry->and_mask);
+			tmp |= entry->or_mask;
+		}
+		WREG32(reg, tmp);
+	}
+
+}
+
+
 static int soc15_asic_reset(struct amdgpu_device *adev)
 {
 	u32 i;
@@ -428,9 +428,8 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 
 	/* wait for asic to come out of reset */
 	for (i = 0; i < adev->usec_timeout; i++) {
-		u32 memsize = (adev->flags & AMD_IS_APU) ?
-			nbio_v7_0_get_memsize(adev) :
-			nbio_v6_1_get_memsize(adev);
+		u32 memsize = adev->nbio_funcs->get_memsize(adev);
+
 		if (memsize != 0xffffffff)
 			break;
 		udelay(1);
@@ -495,14 +494,10 @@ static void soc15_program_aspm(struct amdgpu_device *adev)
 }
 
 static void soc15_enable_doorbell_aperture(struct amdgpu_device *adev,
-					bool enable)
+					   bool enable)
 {
-	if (adev->flags & AMD_IS_APU) {
-		nbio_v7_0_enable_doorbell_aperture(adev, enable);
-	} else {
-		nbio_v6_1_enable_doorbell_aperture(adev, enable);
-		nbio_v6_1_enable_doorbell_selfring_aperture(adev, enable);
-	}
+	adev->nbio_funcs->enable_doorbell_aperture(adev, enable);
+	adev->nbio_funcs->enable_doorbell_selfring_aperture(adev, enable);
 }
 
 static const struct amdgpu_ip_block_version vega10_common_ip_block =
@@ -516,50 +511,65 @@ static const struct amdgpu_ip_block_version vega10_common_ip_block =
 
 int soc15_set_ip_blocks(struct amdgpu_device *adev)
 {
-	nbio_v6_1_detect_hw_virt(adev);
+	/* Set IP register base before any HW register access */
+	switch (adev->asic_type) {
+	case CHIP_VEGA10:
+	case CHIP_RAVEN:
+		vega10_reg_base_init(adev);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (adev->flags & AMD_IS_APU)
+		adev->nbio_funcs = &nbio_v7_0_funcs;
+	else
+		adev->nbio_funcs = &nbio_v6_1_funcs;
+
+	adev->nbio_funcs->detect_hw_virt(adev);
 
 	if (amdgpu_sriov_vf(adev))
 		adev->virt.ops = &xgpu_ai_virt_ops;
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
-		amdgpu_ip_block_add(adev, &vega10_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v9_0_ip_block);
-		amdgpu_ip_block_add(adev, &vega10_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &vega10_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v9_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block);
 		if (amdgpu_fw_load_type == 2 || amdgpu_fw_load_type == -1)
-			amdgpu_ip_block_add(adev, &psp_v3_1_ip_block);
+			amdgpu_device_ip_block_add(adev, &psp_v3_1_ip_block);
 		if (!amdgpu_sriov_vf(adev))
-			amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+			amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
-			amdgpu_ip_block_add(adev, &dm_ip_block);
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #else
 #	warning "Enable CONFIG_DRM_AMD_DC for display support on SOC15."
 #endif
-		amdgpu_ip_block_add(adev, &gfx_v9_0_ip_block);
-		amdgpu_ip_block_add(adev, &sdma_v4_0_ip_block);
-		amdgpu_ip_block_add(adev, &uvd_v7_0_ip_block);
-		amdgpu_ip_block_add(adev, &vce_v4_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &uvd_v7_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &vce_v4_0_ip_block);
 		break;
 	case CHIP_RAVEN:
-		amdgpu_ip_block_add(adev, &vega10_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v9_0_ip_block);
-		amdgpu_ip_block_add(adev, &vega10_ih_ip_block);
-		amdgpu_ip_block_add(adev, &psp_v10_0_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &vega10_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v9_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &psp_v10_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
-			amdgpu_ip_block_add(adev, &dm_ip_block);
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #else
 #	warning "Enable CONFIG_DRM_AMD_DC for display support on SOC15."
 #endif
-		amdgpu_ip_block_add(adev, &gfx_v9_0_ip_block);
-		amdgpu_ip_block_add(adev, &sdma_v4_0_ip_block);
-		amdgpu_ip_block_add(adev, &vcn_v1_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &vcn_v1_0_ip_block);
 		break;
 	default:
 		return -EINVAL;
@@ -570,10 +580,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 
 static uint32_t soc15_get_rev_id(struct amdgpu_device *adev)
 {
-	if (adev->flags & AMD_IS_APU)
-		return nbio_v7_0_get_rev_id(adev);
-	else
-		return nbio_v6_1_get_rev_id(adev);
+	return adev->nbio_funcs->get_rev_id(adev);
 }
 
 static const struct amdgpu_asic_funcs soc15_asic_funcs =
@@ -609,8 +616,8 @@ static int soc15_common_early_init(void *handle)
 
 	adev->asic_funcs = &soc15_asic_funcs;
 
-	if (amdgpu_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP) &&
-		(amdgpu_ip_block_mask & (1 << AMD_IP_BLOCK_TYPE_PSP)))
+	if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP) &&
+	    (amdgpu_ip_block_mask & (1 << AMD_IP_BLOCK_TYPE_PSP)))
 		psp_enabled = true;
 
 	adev->rev_id = soc15_get_rev_id(adev);
@@ -659,8 +666,8 @@ static int soc15_common_early_init(void *handle)
 			AMD_CG_SUPPORT_MC_LS |
 			AMD_CG_SUPPORT_SDMA_MGCG |
 			AMD_CG_SUPPORT_SDMA_LS;
-		adev->pg_flags = AMD_PG_SUPPORT_SDMA |
-				 AMD_PG_SUPPORT_MMHUB;
+		adev->pg_flags = AMD_PG_SUPPORT_SDMA;
+
 		adev->external_rev_id = 0x1;
 		break;
 	default:
@@ -675,7 +682,7 @@ static int soc15_common_early_init(void *handle)
 
 	adev->firmware.load_type = amdgpu_ucode_get_load_type(adev, amdgpu_fw_load_type);
 
-	amdgpu_get_pcie_info(adev);
+	amdgpu_device_get_pcie_info(adev);
 
 	return 0;
 }
@@ -709,15 +716,12 @@ static int soc15_common_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	/* move the golden regs per IP block */
-	soc15_init_golden_registers(adev);
 	/* enable pcie gen2/3 link */
 	soc15_pcie_gen3_enable(adev);
 	/* enable aspm */
 	soc15_program_aspm(adev);
 	/* setup nbio registers */
-	if (!(adev->flags & AMD_IS_APU))
-		nbio_v6_1_init_registers(adev);
+	adev->nbio_funcs->init_registers(adev);
 	/* enable the doorbell aperture */
 	soc15_enable_doorbell_aperture(adev, true);
 
@@ -878,9 +882,9 @@ static int soc15_common_set_clockgating_state(void *handle,
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
-		nbio_v6_1_update_medium_grain_clock_gating(adev,
+		adev->nbio_funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
-		nbio_v6_1_update_medium_grain_light_sleep(adev,
+		adev->nbio_funcs->update_medium_grain_light_sleep(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
 		soc15_update_hdp_light_sleep(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
@@ -894,9 +898,9 @@ static int soc15_common_set_clockgating_state(void *handle,
 				state == AMD_CG_STATE_GATE ? true : false);
 		break;
 	case CHIP_RAVEN:
-		nbio_v7_0_update_medium_grain_clock_gating(adev,
+		adev->nbio_funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
-		nbio_v6_1_update_medium_grain_light_sleep(adev,
+		adev->nbio_funcs->update_medium_grain_light_sleep(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
 		soc15_update_hdp_light_sleep(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
@@ -921,7 +925,7 @@ static void soc15_common_get_clockgating_state(void *handle, u32 *flags)
 	if (amdgpu_sriov_vf(adev))
 		*flags = 0;
 
-	nbio_v6_1_get_clockgating_state(adev, flags);
+	adev->nbio_funcs->get_clockgating_state(adev, flags);
 
 	/* AMD_CG_SUPPORT_HDP_LS */
 	data = RREG32(SOC15_REG_OFFSET(HDP, 0, mmHDP_MEM_POWER_LS));
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.h b/drivers/gpu/drm/amd/amdgpu/soc15.h
index acb3cdb119f2..26b3feac5d06 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.h
@@ -29,8 +29,28 @@
 
 extern const struct amd_ip_funcs soc15_common_ip_funcs;
 
+struct soc15_reg_golden {
+	u32	hwip;
+	u32	instance;
+	u32	segment;
+	u32	reg;
+	u32	and_mask;
+	u32	or_mask;
+};
+
+#define SOC15_REG_ENTRY(ip, inst, reg)	ip##_HWIP, inst, reg##_BASE_IDX, reg
+
+#define SOC15_REG_GOLDEN_VALUE(ip, inst, reg, and_mask, or_mask) \
+	{ ip##_HWIP, inst, reg##_BASE_IDX, reg, and_mask, or_mask }
+
 void soc15_grbm_select(struct amdgpu_device *adev,
 		    u32 me, u32 pipe, u32 queue, u32 vmid);
 int soc15_set_ip_blocks(struct amdgpu_device *adev);
 
+void soc15_program_register_sequence(struct amdgpu_device *adev,
+					     const struct soc15_reg_golden *registers,
+					     const u32 array_size);
+
+int vega10_reg_base_init(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index 7a8e4e28abb2..def865067edd 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -24,72 +24,28 @@
 #ifndef __SOC15_COMMON_H__
 #define __SOC15_COMMON_H__
 
-struct nbio_hdp_flush_reg {
-	u32 hdp_flush_req_offset;
-	u32 hdp_flush_done_offset;
-	u32 ref_and_mask_cp0;
-	u32 ref_and_mask_cp1;
-	u32 ref_and_mask_cp2;
-	u32 ref_and_mask_cp3;
-	u32 ref_and_mask_cp4;
-	u32 ref_and_mask_cp5;
-	u32 ref_and_mask_cp6;
-	u32 ref_and_mask_cp7;
-	u32 ref_and_mask_cp8;
-	u32 ref_and_mask_cp9;
-	u32 ref_and_mask_sdma0;
-	u32 ref_and_mask_sdma1;
-};
-
-struct nbio_pcie_index_data {
-	u32 index_offset;
-	u32 data_offset;
-};
-
 /* Register Access Macros */
-#define SOC15_REG_OFFSET(ip, inst, reg)       (0 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG0 + reg : \
-                                                (1 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG1 + reg : \
-                                                    (2 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG2 + reg : \
-                                                        (3 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG3 + reg : \
-                                                            (ip##_BASE__INST##inst##_SEG4 + reg)))))
+#define SOC15_REG_OFFSET(ip, inst, reg)	(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg)
 
 #define WREG32_FIELD15(ip, idx, reg, field, val)	\
-	WREG32(SOC15_REG_OFFSET(ip, idx, mm##reg), (RREG32(SOC15_REG_OFFSET(ip, idx, mm##reg)) & ~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field))
+	WREG32(adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg,	\
+	(RREG32(adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg)	\
+	& ~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field))
 
 #define RREG32_SOC15(ip, inst, reg) \
-	RREG32( (0 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG0 + reg : \
-		(1 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG1 + reg : \
-		(2 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG2 + reg : \
-		(3 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG3 + reg : \
-		(ip##_BASE__INST##inst##_SEG4 + reg))))))
+	RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg)
 
 #define RREG32_SOC15_OFFSET(ip, inst, reg, offset) \
-	RREG32( (0 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG0 + reg : \
-		(1 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG1 + reg : \
-		(2 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG2 + reg : \
-		(3 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG3 + reg : \
-		(ip##_BASE__INST##inst##_SEG4 + reg))))) + offset)
+	RREG32((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset)
 
 #define WREG32_SOC15(ip, inst, reg, value) \
-	WREG32( (0 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG0 + reg : \
-		(1 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG1 + reg : \
-		(2 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG2 + reg : \
-		(3 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG3 + reg : \
-		(ip##_BASE__INST##inst##_SEG4 + reg))))), value)
+	WREG32((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg), value)
 
 #define WREG32_SOC15_NO_KIQ(ip, inst, reg, value) \
-	WREG32_NO_KIQ( (0 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG0 + reg : \
-		(1 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG1 + reg : \
-		(2 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG2 + reg : \
-		(3 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG3 + reg : \
-		(ip##_BASE__INST##inst##_SEG4 + reg))))), value)
+	WREG32_NO_KIQ((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg), value)
 
 #define WREG32_SOC15_OFFSET(ip, inst, reg, offset, value) \
-	WREG32( (0 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG0 + reg : \
-		(1 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG1 + reg : \
-		(2 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG2 + reg : \
-		(3 == reg##_BASE_IDX ? ip##_BASE__INST##inst##_SEG3 + reg : \
-		(ip##_BASE__INST##inst##_SEG4 + reg))))) + offset, value)
+	WREG32((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset, value)
 
 #endif
 
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index aa4e320e31f8..5995ffc183de 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -270,7 +270,7 @@ static void tonga_ih_decode_iv(struct amdgpu_device *adev,
 	entry->src_id = dw[0] & 0xff;
 	entry->src_data[0] = dw[1] & 0xfffffff;
 	entry->ring_id = dw[2] & 0xff;
-	entry->vm_id = (dw[2] >> 8) & 0xff;
+	entry->vmid = (dw[2] >> 8) & 0xff;
 	entry->pas_id = (dw[2] >> 16) & 0xffff;
 
 	/* wptr/rptr are in bytes! */
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 8ab0f78794a5..8ab10c220910 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -521,7 +521,7 @@ static int uvd_v4_2_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
@@ -541,7 +541,7 @@ static int uvd_v4_2_ring_test_ring(struct amdgpu_ring *ring)
  */
 static void uvd_v4_2_ring_emit_ib(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib,
-				  unsigned vm_id, bool ctx_switch)
+				  unsigned vmid, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, PACKET0(mmUVD_RBC_IB_BASE, 0));
 	amdgpu_ring_write(ring, ib->gpu_addr);
@@ -563,7 +563,7 @@ static void uvd_v4_2_mc_resume(struct amdgpu_device *adev)
 
 	/* programm the VCPU memory controller bits 0-27 */
 	addr = (adev->uvd.gpu_addr + AMDGPU_UVD_FIRMWARE_OFFSET) >> 3;
-	size = AMDGPU_GPU_PAGE_ALIGN(adev->uvd.fw->size + 4) >> 3;
+	size = AMDGPU_UVD_FIRMWARE_SIZE(adev) >> 3;
 	WREG32(mmUVD_VCPU_CACHE_OFFSET0, addr);
 	WREG32(mmUVD_VCPU_CACHE_SIZE0, size);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index bb6d46e168a3..c1fe30cdba32 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -258,7 +258,7 @@ static void uvd_v5_0_mc_resume(struct amdgpu_device *adev)
 			upper_32_bits(adev->uvd.gpu_addr));
 
 	offset = AMDGPU_UVD_FIRMWARE_OFFSET;
-	size = AMDGPU_GPU_PAGE_ALIGN(adev->uvd.fw->size + 4);
+	size = AMDGPU_UVD_FIRMWARE_SIZE(adev);
 	WREG32(mmUVD_VCPU_CACHE_OFFSET0, offset >> 3);
 	WREG32(mmUVD_VCPU_CACHE_SIZE0, size);
 
@@ -536,7 +536,7 @@ static int uvd_v5_0_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
@@ -556,7 +556,7 @@ static int uvd_v5_0_ring_test_ring(struct amdgpu_ring *ring)
  */
 static void uvd_v5_0_ring_emit_ib(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib,
-				  unsigned vm_id, bool ctx_switch)
+				  unsigned vmid, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_64BIT_BAR_LOW, 0));
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 920910ac8663..b2bfedaf57f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -37,6 +37,9 @@
 #include "gmc/gmc_8_1_d.h"
 #include "vi.h"
 
+/* Polaris10/11/12 firmware version */
+#define FW_1_130_16 ((1 << 24) | (130 << 16) | (16 << 8))
+
 static void uvd_v6_0_set_ring_funcs(struct amdgpu_device *adev);
 static void uvd_v6_0_set_enc_ring_funcs(struct amdgpu_device *adev);
 
@@ -58,7 +61,9 @@ static void uvd_v6_0_enable_mgcg(struct amdgpu_device *adev,
 */
 static inline bool uvd_v6_0_enc_support(struct amdgpu_device *adev)
 {
-	return ((adev->asic_type >= CHIP_POLARIS10) && (adev->asic_type <= CHIP_POLARIS12));
+	return ((adev->asic_type >= CHIP_POLARIS10) &&
+			(adev->asic_type <= CHIP_POLARIS12) &&
+			(!adev->uvd.fw_version || adev->uvd.fw_version >= FW_1_130_16));
 }
 
 /**
@@ -184,7 +189,7 @@ static int uvd_v6_0_enc_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed\n",
@@ -360,7 +365,7 @@ static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	} else if (r < 0) {
 		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 	} else {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	}
 error:
@@ -411,12 +416,20 @@ static int uvd_v6_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	if (uvd_v6_0_enc_support(adev)) {
-		struct amd_sched_rq *rq;
+	if (!uvd_v6_0_enc_support(adev)) {
+		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
+			adev->uvd.ring_enc[i].funcs = NULL;
+
+		adev->uvd.irq.num_types = 1;
+		adev->uvd.num_enc_rings = 0;
+
+		DRM_INFO("UVD ENC is disabled\n");
+	} else {
+		struct drm_sched_rq *rq;
 		ring = &adev->uvd.ring_enc[0];
-		rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
-		r = amd_sched_entity_init(&ring->sched, &adev->uvd.entity_enc,
-					  rq, amdgpu_sched_jobs);
+		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+		r = drm_sched_entity_init(&ring->sched, &adev->uvd.entity_enc,
+					  rq, amdgpu_sched_jobs, NULL);
 		if (r) {
 			DRM_ERROR("Failed setting up UVD ENC run queue.\n");
 			return r;
@@ -456,7 +469,7 @@ static int uvd_v6_0_sw_fini(void *handle)
 		return r;
 
 	if (uvd_v6_0_enc_support(adev)) {
-		amd_sched_entity_fini(&adev->uvd.ring_enc[0].sched, &adev->uvd.entity_enc);
+		drm_sched_entity_fini(&adev->uvd.ring_enc[0].sched, &adev->uvd.entity_enc);
 
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->uvd.ring_enc[i]);
@@ -603,7 +616,7 @@ static void uvd_v6_0_mc_resume(struct amdgpu_device *adev)
 			upper_32_bits(adev->uvd.gpu_addr));
 
 	offset = AMDGPU_UVD_FIRMWARE_OFFSET;
-	size = AMDGPU_GPU_PAGE_ALIGN(adev->uvd.fw->size + 4);
+	size = AMDGPU_UVD_FIRMWARE_SIZE(adev);
 	WREG32(mmUVD_VCPU_CACHE_OFFSET0, offset >> 3);
 	WREG32(mmUVD_VCPU_CACHE_SIZE0, size);
 
@@ -1008,7 +1021,7 @@ static int uvd_v6_0_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
@@ -1028,10 +1041,10 @@ static int uvd_v6_0_ring_test_ring(struct amdgpu_ring *ring)
  */
 static void uvd_v6_0_ring_emit_ib(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib,
-				  unsigned vm_id, bool ctx_switch)
+				  unsigned vmid, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_VMID, 0));
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 
 	amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_64BIT_BAR_LOW, 0));
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
@@ -1050,24 +1063,24 @@ static void uvd_v6_0_ring_emit_ib(struct amdgpu_ring *ring,
  * Write enc ring commands to execute the indirect buffer
  */
 static void uvd_v6_0_enc_ring_emit_ib(struct amdgpu_ring *ring,
-		struct amdgpu_ib *ib, unsigned int vm_id, bool ctx_switch)
+		struct amdgpu_ib *ib, unsigned int vmid, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_IB_VM);
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, ib->length_dw);
 }
 
 static void uvd_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					 unsigned vm_id, uint64_t pd_addr)
+					 unsigned vmid, uint64_t pd_addr)
 {
 	uint32_t reg;
 
-	if (vm_id < 8)
-		reg = mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id;
+	if (vmid < 8)
+		reg = mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vmid;
 	else
-		reg = mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vm_id - 8;
+		reg = mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vmid - 8;
 
 	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0));
 	amdgpu_ring_write(ring, reg << 2);
@@ -1079,7 +1092,7 @@ static void uvd_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0));
 	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST << 2);
 	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0));
-	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vmid);
 	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0));
 	amdgpu_ring_write(ring, 0x8);
 
@@ -1088,7 +1101,7 @@ static void uvd_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0));
 	amdgpu_ring_write(ring, 0);
 	amdgpu_ring_write(ring, PACKET0(mmUVD_GP_SCRATCH8, 0));
-	amdgpu_ring_write(ring, 1 << vm_id); /* mask */
+	amdgpu_ring_write(ring, 1 << vmid); /* mask */
 	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0));
 	amdgpu_ring_write(ring, 0xC);
 }
@@ -1127,14 +1140,14 @@ static void uvd_v6_0_enc_ring_insert_end(struct amdgpu_ring *ring)
 }
 
 static void uvd_v6_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
-        unsigned int vm_id, uint64_t pd_addr)
+        unsigned int vmid, uint64_t pd_addr)
 {
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_UPDATE_PTB);
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 	amdgpu_ring_write(ring, pd_addr >> 12);
 
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_FLUSH_TLB);
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 }
 
 static bool uvd_v6_0_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 6634545060fd..6b95f4f344b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -29,16 +29,15 @@
 #include "soc15_common.h"
 #include "mmsch_v1_0.h"
 
-#include "vega10/soc15ip.h"
-#include "vega10/UVD/uvd_7_0_offset.h"
-#include "vega10/UVD/uvd_7_0_sh_mask.h"
-#include "vega10/VCE/vce_4_0_offset.h"
-#include "vega10/VCE/vce_4_0_default.h"
-#include "vega10/VCE/vce_4_0_sh_mask.h"
-#include "vega10/NBIF/nbif_6_1_offset.h"
-#include "vega10/HDP/hdp_4_0_offset.h"
-#include "vega10/MMHUB/mmhub_1_0_offset.h"
-#include "vega10/MMHUB/mmhub_1_0_sh_mask.h"
+#include "uvd/uvd_7_0_offset.h"
+#include "uvd/uvd_7_0_sh_mask.h"
+#include "vce/vce_4_0_offset.h"
+#include "vce/vce_4_0_default.h"
+#include "vce/vce_4_0_sh_mask.h"
+#include "nbif/nbif_6_1_offset.h"
+#include "hdp/hdp_4_0_offset.h"
+#include "mmhub/mmhub_1_0_offset.h"
+#include "mmhub/mmhub_1_0_sh_mask.h"
 
 static void uvd_v7_0_set_ring_funcs(struct amdgpu_device *adev);
 static void uvd_v7_0_set_enc_ring_funcs(struct amdgpu_device *adev);
@@ -184,7 +183,7 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed\n",
@@ -359,7 +358,7 @@ static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	} else if (r < 0) {
 		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 	} else {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	}
 error:
@@ -385,7 +384,7 @@ static int uvd_v7_0_early_init(void *handle)
 static int uvd_v7_0_sw_init(void *handle)
 {
 	struct amdgpu_ring *ring;
-	struct amd_sched_rq *rq;
+	struct drm_sched_rq *rq;
 	int i, r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
@@ -416,9 +415,9 @@ static int uvd_v7_0_sw_init(void *handle)
 	}
 
 	ring = &adev->uvd.ring_enc[0];
-	rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
-	r = amd_sched_entity_init(&ring->sched, &adev->uvd.entity_enc,
-				  rq, amdgpu_sched_jobs);
+	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+	r = drm_sched_entity_init(&ring->sched, &adev->uvd.entity_enc,
+				  rq, amdgpu_sched_jobs, NULL);
 	if (r) {
 		DRM_ERROR("Failed setting up UVD ENC run queue.\n");
 		return r;
@@ -472,7 +471,7 @@ static int uvd_v7_0_sw_fini(void *handle)
 	if (r)
 		return r;
 
-	amd_sched_entity_fini(&adev->uvd.ring_enc[0].sched, &adev->uvd.entity_enc);
+	drm_sched_entity_fini(&adev->uvd.ring_enc[0].sched, &adev->uvd.entity_enc);
 
 	for (i = 0; i < adev->uvd.num_enc_rings; ++i)
 		amdgpu_ring_fini(&adev->uvd.ring_enc[i]);
@@ -616,7 +615,7 @@ static int uvd_v7_0_resume(void *handle)
  */
 static void uvd_v7_0_mc_resume(struct amdgpu_device *adev)
 {
-	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->uvd.fw->size + 4);
+	uint32_t size = AMDGPU_UVD_FIRMWARE_SIZE(adev);
 	uint32_t offset;
 
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
@@ -1086,6 +1085,8 @@ static void uvd_v7_0_stop(struct amdgpu_device *adev)
 static void uvd_v7_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
 				     unsigned flags)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
 
 	amdgpu_ring_write(ring,
@@ -1123,6 +1124,7 @@ static void uvd_v7_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq
 static void uvd_v7_0_enc_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
 			u64 seq, unsigned flags)
 {
+
 	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
 
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_FENCE);
@@ -1141,6 +1143,8 @@ static void uvd_v7_0_enc_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
  */
 static void uvd_v7_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(NBIF, 0,
 		mmHDP_MEM_COHERENCY_FLUSH_CNTL), 0));
 	amdgpu_ring_write(ring, 0);
@@ -1155,6 +1159,8 @@ static void uvd_v7_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
  */
 static void uvd_v7_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(HDP, 0, mmHDP_READ_CACHE_INVALIDATE), 0));
 	amdgpu_ring_write(ring, 1);
 }
@@ -1192,7 +1198,7 @@ static int uvd_v7_0_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
@@ -1212,11 +1218,13 @@ static int uvd_v7_0_ring_test_ring(struct amdgpu_ring *ring)
  */
 static void uvd_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib,
-				  unsigned vm_id, bool ctx_switch)
+				  unsigned vmid, bool ctx_switch)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring,
 		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_RBC_IB_VMID), 0));
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 
 	amdgpu_ring_write(ring,
 		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_RBC_IB_64BIT_BAR_LOW), 0));
@@ -1238,10 +1246,10 @@ static void uvd_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
  * Write enc ring commands to execute the indirect buffer
  */
 static void uvd_v7_0_enc_ring_emit_ib(struct amdgpu_ring *ring,
-		struct amdgpu_ib *ib, unsigned int vm_id, bool ctx_switch)
+		struct amdgpu_ib *ib, unsigned int vmid, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_IB_VM);
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, ib->length_dw);
@@ -1250,6 +1258,8 @@ static void uvd_v7_0_enc_ring_emit_ib(struct amdgpu_ring *ring,
 static void uvd_v7_0_vm_reg_write(struct amdgpu_ring *ring,
 				uint32_t data0, uint32_t data1)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring,
 		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0), 0));
 	amdgpu_ring_write(ring, data0);
@@ -1264,6 +1274,8 @@ static void uvd_v7_0_vm_reg_write(struct amdgpu_ring *ring,
 static void uvd_v7_0_vm_reg_wait(struct amdgpu_ring *ring,
 				uint32_t data0, uint32_t data1, uint32_t mask)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring,
 		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0), 0));
 	amdgpu_ring_write(ring, data0);
@@ -1279,25 +1291,26 @@ static void uvd_v7_0_vm_reg_wait(struct amdgpu_ring *ring,
 }
 
 static void uvd_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vm_id, uint64_t pd_addr)
+					unsigned vmid, uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
-	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vm_id);
-	uint32_t data0, data1, mask;
+	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vmid);
+	uint64_t flags = AMDGPU_PTE_VALID;
 	unsigned eng = ring->vm_inv_eng;
+	uint32_t data0, data1, mask;
 
-	pd_addr = amdgpu_gart_get_vm_pde(ring->adev, pd_addr);
-	pd_addr |= AMDGPU_PTE_VALID;
+	amdgpu_gart_get_vm_pde(ring->adev, -1, &pd_addr, &flags);
+	pd_addr |= flags;
 
-	data0 = (hub->ctx0_ptb_addr_hi32 + vm_id * 2) << 2;
+	data0 = (hub->ctx0_ptb_addr_hi32 + vmid * 2) << 2;
 	data1 = upper_32_bits(pd_addr);
 	uvd_v7_0_vm_reg_write(ring, data0, data1);
 
-	data0 = (hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2;
+	data0 = (hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2;
 	data1 = lower_32_bits(pd_addr);
 	uvd_v7_0_vm_reg_write(ring, data0, data1);
 
-	data0 = (hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2;
+	data0 = (hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2;
 	data1 = lower_32_bits(pd_addr);
 	mask = 0xffffffff;
 	uvd_v7_0_vm_reg_wait(ring, data0, data1, mask);
@@ -1309,36 +1322,47 @@ static void uvd_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 
 	/* wait for flush */
 	data0 = (hub->vm_inv_eng0_ack + eng) << 2;
-	data1 = 1 << vm_id;
-	mask =  1 << vm_id;
+	data1 = 1 << vmid;
+	mask =  1 << vmid;
 	uvd_v7_0_vm_reg_wait(ring, data0, data1, mask);
 }
 
+static void uvd_v7_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+	struct amdgpu_device *adev = ring->adev;
+
+	for (i = 0; i < count; i++)
+		amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP), 0));
+
+}
+
 static void uvd_v7_0_enc_ring_insert_end(struct amdgpu_ring *ring)
 {
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_END);
 }
 
 static void uvd_v7_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
-			 unsigned int vm_id, uint64_t pd_addr)
+			 unsigned int vmid, uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
-	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vm_id);
+	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vmid);
+	uint64_t flags = AMDGPU_PTE_VALID;
 	unsigned eng = ring->vm_inv_eng;
 
-	pd_addr = amdgpu_gart_get_vm_pde(ring->adev, pd_addr);
-	pd_addr |= AMDGPU_PTE_VALID;
+	amdgpu_gart_get_vm_pde(ring->adev, -1, &pd_addr, &flags);
+	pd_addr |= flags;
 
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_REG_WRITE);
-	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_hi32 + vm_id * 2) << 2);
+	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_hi32 + vmid * 2) << 2);
 	amdgpu_ring_write(ring, upper_32_bits(pd_addr));
 
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_REG_WRITE);
-	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
+	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2);
 	amdgpu_ring_write(ring, lower_32_bits(pd_addr));
 
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_REG_WAIT);
-	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
+	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2);
 	amdgpu_ring_write(ring, 0xffffffff);
 	amdgpu_ring_write(ring, lower_32_bits(pd_addr));
 
@@ -1350,8 +1374,8 @@ static void uvd_v7_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	/* wait for flush */
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_REG_WAIT);
 	amdgpu_ring_write(ring, (hub->vm_inv_eng0_ack + eng) << 2);
-	amdgpu_ring_write(ring, 1 << vm_id);
-	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vmid);
+	amdgpu_ring_write(ring, 1 << vmid);
 }
 
 #if 0
@@ -1681,7 +1705,7 @@ const struct amd_ip_funcs uvd_v7_0_ip_funcs = {
 static const struct amdgpu_ring_funcs uvd_v7_0_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_UVD,
 	.align_mask = 0xf,
-	.nop = PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP), 0),
+	.nop = PACKET0(0x81ff, 0),
 	.support_64bit_ptrs = false,
 	.vmhub = AMDGPU_MMHUB,
 	.get_rptr = uvd_v7_0_ring_get_rptr,
@@ -1700,7 +1724,7 @@ static const struct amdgpu_ring_funcs uvd_v7_0_ring_vm_funcs = {
 	.emit_hdp_invalidate = uvd_v7_0_ring_emit_hdp_invalidate,
 	.test_ring = uvd_v7_0_ring_test_ring,
 	.test_ib = amdgpu_uvd_ring_test_ib,
-	.insert_nop = amdgpu_ring_insert_nop,
+	.insert_nop = uvd_v7_0_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = amdgpu_uvd_ring_begin_use,
 	.end_use = amdgpu_uvd_ring_end_use,
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index cf81065e3c5a..a5355eb689f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -834,24 +834,24 @@ out:
 }
 
 static void vce_v3_0_ring_emit_ib(struct amdgpu_ring *ring,
-		struct amdgpu_ib *ib, unsigned int vm_id, bool ctx_switch)
+		struct amdgpu_ib *ib, unsigned int vmid, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, VCE_CMD_IB_VM);
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, ib->length_dw);
 }
 
 static void vce_v3_0_emit_vm_flush(struct amdgpu_ring *ring,
-			 unsigned int vm_id, uint64_t pd_addr)
+			 unsigned int vmid, uint64_t pd_addr)
 {
 	amdgpu_ring_write(ring, VCE_CMD_UPDATE_PTB);
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 	amdgpu_ring_write(ring, pd_addr >> 12);
 
 	amdgpu_ring_write(ring, VCE_CMD_FLUSH_TLB);
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 	amdgpu_ring_write(ring, VCE_CMD_END);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index 75745544600a..7cf2eef68cf2 100644..100755
--- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
@@ -32,12 +32,11 @@
 #include "soc15_common.h"
 #include "mmsch_v1_0.h"
 
-#include "vega10/soc15ip.h"
-#include "vega10/VCE/vce_4_0_offset.h"
-#include "vega10/VCE/vce_4_0_default.h"
-#include "vega10/VCE/vce_4_0_sh_mask.h"
-#include "vega10/MMHUB/mmhub_1_0_offset.h"
-#include "vega10/MMHUB/mmhub_1_0_sh_mask.h"
+#include "vce/vce_4_0_offset.h"
+#include "vce/vce_4_0_default.h"
+#include "vce/vce_4_0_sh_mask.h"
+#include "mmhub/mmhub_1_0_offset.h"
+#include "mmhub/mmhub_1_0_sh_mask.h"
 
 #define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK	0x02
 
@@ -243,37 +242,49 @@ static int vce_v4_0_sriov_start(struct amdgpu_device *adev)
 		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VM_CTRL), 0);
 
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
-		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR0),
-						adev->firmware.ucode[AMDGPU_UCODE_ID_VCE].mc_addr >> 8);
-		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR1),
-						adev->firmware.ucode[AMDGPU_UCODE_ID_VCE].mc_addr >> 8);
-		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR2),
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
+						mmVCE_LMI_VCPU_CACHE_40BIT_BAR0),
 						adev->firmware.ucode[AMDGPU_UCODE_ID_VCE].mc_addr >> 8);
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
+						mmVCE_LMI_VCPU_CACHE_64BIT_BAR0),
+						(adev->firmware.ucode[AMDGPU_UCODE_ID_VCE].mc_addr >> 40) & 0xff);
 		} else {
-		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR0),
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
+						mmVCE_LMI_VCPU_CACHE_40BIT_BAR0),
 						adev->vce.gpu_addr >> 8);
-		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR1),
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
+						mmVCE_LMI_VCPU_CACHE_64BIT_BAR0),
+						(adev->vce.gpu_addr >> 40) & 0xff);
+		}
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
+						mmVCE_LMI_VCPU_CACHE_40BIT_BAR1),
 						adev->vce.gpu_addr >> 8);
-		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR2),
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
+						mmVCE_LMI_VCPU_CACHE_64BIT_BAR1),
+						(adev->vce.gpu_addr >> 40) & 0xff);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
+						mmVCE_LMI_VCPU_CACHE_40BIT_BAR2),
 						adev->vce.gpu_addr >> 8);
-		}
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
+						mmVCE_LMI_VCPU_CACHE_64BIT_BAR2),
+						(adev->vce.gpu_addr >> 40) & 0xff);
 
 		offset = AMDGPU_VCE_FIRMWARE_OFFSET;
 		size = VCE_V4_0_FW_SIZE;
 		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET0),
-					    offset & 0x7FFFFFFF);
+					offset & ~0x0f000000);
 		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_SIZE0), size);
 
-		offset += size;
+		offset = (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) ? offset + size : 0;
 		size = VCE_V4_0_STACK_SIZE;
 		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET1),
-					    offset & 0x7FFFFFFF);
+					(offset & ~0x0f000000) | (1 << 24));
 		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_SIZE1), size);
 
 		offset += size;
 		size = VCE_V4_0_DATA_SIZE;
 		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET2),
-					    offset & 0x7FFFFFFF);
+					(offset & ~0x0f000000) | (2 << 24));
 		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_SIZE2), size);
 
 		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_CTRL2), ~0x100, 0);
@@ -412,7 +423,7 @@ static int vce_v4_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	size  = (VCE_V4_0_STACK_SIZE + VCE_V4_0_DATA_SIZE) * 2;
+	size  = VCE_V4_0_STACK_SIZE + VCE_V4_0_DATA_SIZE;
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP)
 		size += VCE_V4_0_FW_SIZE;
 
@@ -927,10 +938,10 @@ static int vce_v4_0_set_powergating_state(void *handle,
 #endif
 
 static void vce_v4_0_ring_emit_ib(struct amdgpu_ring *ring,
-		struct amdgpu_ib *ib, unsigned int vm_id, bool ctx_switch)
+		struct amdgpu_ib *ib, unsigned int vmid, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, VCE_CMD_IB_VM);
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, ib->length_dw);
@@ -954,25 +965,26 @@ static void vce_v4_0_ring_insert_end(struct amdgpu_ring *ring)
 }
 
 static void vce_v4_0_emit_vm_flush(struct amdgpu_ring *ring,
-			 unsigned int vm_id, uint64_t pd_addr)
+			 unsigned int vmid, uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
-	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vm_id);
+	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vmid);
+	uint64_t flags = AMDGPU_PTE_VALID;
 	unsigned eng = ring->vm_inv_eng;
 
-	pd_addr = amdgpu_gart_get_vm_pde(ring->adev, pd_addr);
-	pd_addr |= AMDGPU_PTE_VALID;
+	amdgpu_gart_get_vm_pde(ring->adev, -1, &pd_addr, &flags);
+	pd_addr |= flags;
 
 	amdgpu_ring_write(ring, VCE_CMD_REG_WRITE);
-	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_hi32 + vm_id * 2) << 2);
+	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_hi32 + vmid * 2) << 2);
 	amdgpu_ring_write(ring, upper_32_bits(pd_addr));
 
 	amdgpu_ring_write(ring, VCE_CMD_REG_WRITE);
-	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
+	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2);
 	amdgpu_ring_write(ring, lower_32_bits(pd_addr));
 
 	amdgpu_ring_write(ring, VCE_CMD_REG_WAIT);
-	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
+	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2);
 	amdgpu_ring_write(ring, 0xffffffff);
 	amdgpu_ring_write(ring, lower_32_bits(pd_addr));
 
@@ -984,8 +996,8 @@ static void vce_v4_0_emit_vm_flush(struct amdgpu_ring *ring,
 	/* wait for flush */
 	amdgpu_ring_write(ring, VCE_CMD_REG_WAIT);
 	amdgpu_ring_write(ring, (hub->vm_inv_eng0_ack + eng) << 2);
-	amdgpu_ring_write(ring, 1 << vm_id);
-	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vmid);
+	amdgpu_ring_write(ring, 1 << vmid);
 }
 
 static int vce_v4_0_set_interrupt_state(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 1eb4d79d6e30..b99e15c43e45 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -28,12 +28,11 @@
 #include "soc15d.h"
 #include "soc15_common.h"
 
-#include "vega10/soc15ip.h"
-#include "raven1/VCN/vcn_1_0_offset.h"
-#include "raven1/VCN/vcn_1_0_sh_mask.h"
-#include "vega10/HDP/hdp_4_0_offset.h"
-#include "raven1/MMHUB/mmhub_9_1_offset.h"
-#include "raven1/MMHUB/mmhub_9_1_sh_mask.h"
+#include "vcn/vcn_1_0_offset.h"
+#include "vcn/vcn_1_0_sh_mask.h"
+#include "hdp/hdp_4_0_offset.h"
+#include "mmhub/mmhub_9_1_offset.h"
+#include "mmhub/mmhub_9_1_sh_mask.h"
 
 static int vcn_v1_0_start(struct amdgpu_device *adev);
 static int vcn_v1_0_stop(struct amdgpu_device *adev);
@@ -744,6 +743,8 @@ static void vcn_v1_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
  */
 static void vcn_v1_0_dec_ring_insert_start(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring,
 		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0), 0));
 	amdgpu_ring_write(ring, 0);
@@ -761,6 +762,8 @@ static void vcn_v1_0_dec_ring_insert_start(struct amdgpu_ring *ring)
  */
 static void vcn_v1_0_dec_ring_insert_end(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring,
 		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD), 0));
 	amdgpu_ring_write(ring, VCN_DEC_CMD_PACKET_END << 1);
@@ -777,6 +780,8 @@ static void vcn_v1_0_dec_ring_insert_end(struct amdgpu_ring *ring)
 static void vcn_v1_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
 				     unsigned flags)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
 
 	amdgpu_ring_write(ring,
@@ -812,6 +817,8 @@ static void vcn_v1_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64
  */
 static void vcn_v1_0_dec_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(HDP, 0, mmHDP_READ_CACHE_INVALIDATE), 0));
 	amdgpu_ring_write(ring, 1);
 }
@@ -826,11 +833,13 @@ static void vcn_v1_0_dec_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
  */
 static void vcn_v1_0_dec_ring_emit_ib(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib,
-				  unsigned vm_id, bool ctx_switch)
+				  unsigned vmid, bool ctx_switch)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring,
 		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_RBC_IB_VMID), 0));
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 
 	amdgpu_ring_write(ring,
 		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_RBC_IB_64BIT_BAR_LOW), 0));
@@ -846,6 +855,8 @@ static void vcn_v1_0_dec_ring_emit_ib(struct amdgpu_ring *ring,
 static void vcn_v1_0_dec_vm_reg_write(struct amdgpu_ring *ring,
 				uint32_t data0, uint32_t data1)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring,
 		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0), 0));
 	amdgpu_ring_write(ring, data0);
@@ -860,6 +871,8 @@ static void vcn_v1_0_dec_vm_reg_write(struct amdgpu_ring *ring,
 static void vcn_v1_0_dec_vm_reg_wait(struct amdgpu_ring *ring,
 				uint32_t data0, uint32_t data1, uint32_t mask)
 {
+	struct amdgpu_device *adev = ring->adev;
+
 	amdgpu_ring_write(ring,
 		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0), 0));
 	amdgpu_ring_write(ring, data0);
@@ -875,25 +888,26 @@ static void vcn_v1_0_dec_vm_reg_wait(struct amdgpu_ring *ring,
 }
 
 static void vcn_v1_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vm_id, uint64_t pd_addr)
+					unsigned vmid, uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
-	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vm_id);
-	uint32_t data0, data1, mask;
+	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vmid);
+	uint64_t flags = AMDGPU_PTE_VALID;
 	unsigned eng = ring->vm_inv_eng;
+	uint32_t data0, data1, mask;
 
-	pd_addr = amdgpu_gart_get_vm_pde(ring->adev, pd_addr);
-	pd_addr |= AMDGPU_PTE_VALID;
+	amdgpu_gart_get_vm_pde(ring->adev, -1, &pd_addr, &flags);
+	pd_addr |= flags;
 
-	data0 = (hub->ctx0_ptb_addr_hi32 + vm_id * 2) << 2;
+	data0 = (hub->ctx0_ptb_addr_hi32 + vmid * 2) << 2;
 	data1 = upper_32_bits(pd_addr);
 	vcn_v1_0_dec_vm_reg_write(ring, data0, data1);
 
-	data0 = (hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2;
+	data0 = (hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2;
 	data1 = lower_32_bits(pd_addr);
 	vcn_v1_0_dec_vm_reg_write(ring, data0, data1);
 
-	data0 = (hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2;
+	data0 = (hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2;
 	data1 = lower_32_bits(pd_addr);
 	mask = 0xffffffff;
 	vcn_v1_0_dec_vm_reg_wait(ring, data0, data1, mask);
@@ -905,8 +919,8 @@ static void vcn_v1_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
 
 	/* wait for flush */
 	data0 = (hub->vm_inv_eng0_ack + eng) << 2;
-	data1 = 1 << vm_id;
-	mask =  1 << vm_id;
+	data1 = 1 << vmid;
+	mask =  1 << vmid;
 	vcn_v1_0_dec_vm_reg_wait(ring, data0, data1, mask);
 }
 
@@ -997,38 +1011,39 @@ static void vcn_v1_0_enc_ring_insert_end(struct amdgpu_ring *ring)
  * Write enc ring commands to execute the indirect buffer
  */
 static void vcn_v1_0_enc_ring_emit_ib(struct amdgpu_ring *ring,
-		struct amdgpu_ib *ib, unsigned int vm_id, bool ctx_switch)
+		struct amdgpu_ib *ib, unsigned int vmid, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, VCN_ENC_CMD_IB);
-	amdgpu_ring_write(ring, vm_id);
+	amdgpu_ring_write(ring, vmid);
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, ib->length_dw);
 }
 
 static void vcn_v1_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
-			 unsigned int vm_id, uint64_t pd_addr)
+			 unsigned int vmid, uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
-	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vm_id);
+	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vmid);
+	uint64_t flags = AMDGPU_PTE_VALID;
 	unsigned eng = ring->vm_inv_eng;
 
-	pd_addr = amdgpu_gart_get_vm_pde(ring->adev, pd_addr);
-	pd_addr |= AMDGPU_PTE_VALID;
+	amdgpu_gart_get_vm_pde(ring->adev, -1, &pd_addr, &flags);
+	pd_addr |= flags;
 
 	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WRITE);
 	amdgpu_ring_write(ring,
-			  (hub->ctx0_ptb_addr_hi32 + vm_id * 2) << 2);
+			  (hub->ctx0_ptb_addr_hi32 + vmid * 2) << 2);
 	amdgpu_ring_write(ring, upper_32_bits(pd_addr));
 
 	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WRITE);
 	amdgpu_ring_write(ring,
-			  (hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
+			  (hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2);
 	amdgpu_ring_write(ring, lower_32_bits(pd_addr));
 
 	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WAIT);
 	amdgpu_ring_write(ring,
-			  (hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
+			  (hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2);
 	amdgpu_ring_write(ring, 0xffffffff);
 	amdgpu_ring_write(ring, lower_32_bits(pd_addr));
 
@@ -1040,8 +1055,8 @@ static void vcn_v1_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	/* wait for flush */
 	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WAIT);
 	amdgpu_ring_write(ring, (hub->vm_inv_eng0_ack + eng) << 2);
-	amdgpu_ring_write(ring, 1 << vm_id);
-	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vmid);
+	amdgpu_ring_write(ring, 1 << vmid);
 }
 
 static int vcn_v1_0_set_interrupt_state(struct amdgpu_device *adev,
@@ -1077,6 +1092,17 @@ static int vcn_v1_0_process_interrupt(struct amdgpu_device *adev,
 	return 0;
 }
 
+static void vcn_v1_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+	struct amdgpu_device *adev = ring->adev;
+
+	for (i = 0; i < count; i++)
+		amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP), 0));
+
+}
+
+
 static const struct amd_ip_funcs vcn_v1_0_ip_funcs = {
 	.name = "vcn_v1_0",
 	.early_init = vcn_v1_0_early_init,
@@ -1100,7 +1126,7 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = {
 static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_VCN_DEC,
 	.align_mask = 0xf,
-	.nop = PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP), 0),
+	.nop = PACKET0(0x81ff, 0),
 	.support_64bit_ptrs = false,
 	.vmhub = AMDGPU_MMHUB,
 	.get_rptr = vcn_v1_0_dec_ring_get_rptr,
@@ -1118,7 +1144,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
 	.emit_hdp_invalidate = vcn_v1_0_dec_ring_emit_hdp_invalidate,
 	.test_ring = amdgpu_vcn_dec_ring_test_ring,
 	.test_ib = amdgpu_vcn_dec_ring_test_ib,
-	.insert_nop = amdgpu_ring_insert_nop,
+	.insert_nop = vcn_v1_0_ring_insert_nop,
 	.insert_start = vcn_v1_0_dec_ring_insert_start,
 	.insert_end = vcn_v1_0_dec_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
@@ -1175,7 +1201,7 @@ static const struct amdgpu_irq_src_funcs vcn_v1_0_irq_funcs = {
 
 static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->uvd.irq.num_types = adev->vcn.num_enc_rings + 1;
+	adev->vcn.irq.num_types = adev->vcn.num_enc_rings + 1;
 	adev->vcn.irq.funcs = &vcn_v1_0_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index 697325737ba8..b69ceafb7888 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -25,10 +25,8 @@
 #include "amdgpu_ih.h"
 #include "soc15.h"
 
-
-#include "vega10/soc15ip.h"
-#include "vega10/OSSSYS/osssys_4_0_offset.h"
-#include "vega10/OSSSYS/osssys_4_0_sh_mask.h"
+#include "oss/osssys_4_0_offset.h"
+#include "oss/osssys_4_0_sh_mask.h"
 
 #include "soc15_common.h"
 #include "vega10_ih.h"
@@ -46,11 +44,11 @@ static void vega10_ih_set_interrupt_funcs(struct amdgpu_device *adev);
  */
 static void vega10_ih_enable_interrupts(struct amdgpu_device *adev)
 {
-	u32 ih_rb_cntl = RREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_CNTL));
+	u32 ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL);
 
 	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RB_ENABLE, 1);
 	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, ENABLE_INTR, 1);
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_CNTL), ih_rb_cntl);
+	WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl);
 	adev->irq.ih.enabled = true;
 }
 
@@ -63,14 +61,14 @@ static void vega10_ih_enable_interrupts(struct amdgpu_device *adev)
  */
 static void vega10_ih_disable_interrupts(struct amdgpu_device *adev)
 {
-	u32 ih_rb_cntl = RREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_CNTL));
+	u32 ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL);
 
 	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RB_ENABLE, 0);
 	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, ENABLE_INTR, 0);
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_CNTL), ih_rb_cntl);
+	WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl);
 	/* set rptr, wptr to 0 */
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_RPTR), 0);
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_WPTR), 0);
+	WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR, 0);
+	WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR, 0);
 	adev->irq.ih.enabled = false;
 	adev->irq.ih.rptr = 0;
 }
@@ -97,20 +95,17 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 	/* disable irqs */
 	vega10_ih_disable_interrupts(adev);
 
-	if (adev->flags & AMD_IS_APU)
-		nbio_v7_0_ih_control(adev);
-	else
-		nbio_v6_1_ih_control(adev);
+	adev->nbio_funcs->ih_control(adev);
 
-	ih_rb_cntl = RREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_CNTL));
+	ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL);
 	/* Ring Buffer base. [39:8] of 40-bit address of the beginning of the ring buffer*/
 	if (adev->irq.ih.use_bus_addr) {
-		WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_BASE), adev->irq.ih.rb_dma_addr >> 8);
-		WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_BASE_HI), ((u64)adev->irq.ih.rb_dma_addr >> 40) & 0xff);
+		WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE, adev->irq.ih.rb_dma_addr >> 8);
+		WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE_HI, ((u64)adev->irq.ih.rb_dma_addr >> 40) & 0xff);
 		ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, MC_SPACE, 1);
 	} else {
-		WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_BASE), adev->irq.ih.gpu_addr >> 8);
-		WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_BASE_HI), (adev->irq.ih.gpu_addr >> 40) & 0xff);
+		WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE, adev->irq.ih.gpu_addr >> 8);
+		WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE_HI, (adev->irq.ih.gpu_addr >> 40) & 0xff);
 		ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, MC_SPACE, 4);
 	}
 	rb_bufsz = order_base_2(adev->irq.ih.ring_size / 4);
@@ -126,21 +121,21 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 	if (adev->irq.msi_enabled)
 		ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RPTR_REARM, 1);
 
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_CNTL), ih_rb_cntl);
+	WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl);
 
 	/* set the writeback address whether it's enabled or not */
 	if (adev->irq.ih.use_bus_addr)
 		wptr_off = adev->irq.ih.rb_dma_addr + (adev->irq.ih.wptr_offs * 4);
 	else
 		wptr_off = adev->wb.gpu_addr + (adev->irq.ih.wptr_offs * 4);
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_WPTR_ADDR_LO), lower_32_bits(wptr_off));
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_WPTR_ADDR_HI), upper_32_bits(wptr_off) & 0xFF);
+	WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_LO, lower_32_bits(wptr_off));
+	WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_HI, upper_32_bits(wptr_off) & 0xFF);
 
 	/* set rptr, wptr to 0 */
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_RPTR), 0);
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_WPTR), 0);
+	WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR, 0);
+	WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR, 0);
 
-	ih_doorbell_rtpr = RREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_DOORBELL_RPTR));
+	ih_doorbell_rtpr = RREG32_SOC15(OSSSYS, 0, mmIH_DOORBELL_RPTR);
 	if (adev->irq.ih.use_doorbell) {
 		ih_doorbell_rtpr = REG_SET_FIELD(ih_doorbell_rtpr, IH_DOORBELL_RPTR,
 						 OFFSET, adev->irq.ih.doorbell_index);
@@ -150,20 +145,18 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 		ih_doorbell_rtpr = REG_SET_FIELD(ih_doorbell_rtpr, IH_DOORBELL_RPTR,
 						 ENABLE, 0);
 	}
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_DOORBELL_RPTR), ih_doorbell_rtpr);
-	if (adev->flags & AMD_IS_APU)
-		nbio_v7_0_ih_doorbell_range(adev, adev->irq.ih.use_doorbell, adev->irq.ih.doorbell_index);
-	else
-		nbio_v6_1_ih_doorbell_range(adev, adev->irq.ih.use_doorbell, adev->irq.ih.doorbell_index);
+	WREG32_SOC15(OSSSYS, 0, mmIH_DOORBELL_RPTR, ih_doorbell_rtpr);
+	adev->nbio_funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
+					    adev->irq.ih.doorbell_index);
 
-	tmp = RREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL));
+	tmp = RREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL);
 	tmp = REG_SET_FIELD(tmp, IH_STORM_CLIENT_LIST_CNTL,
 			    CLIENT18_IS_STORM_CLIENT, 1);
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL), tmp);
+	WREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL, tmp);
 
-	tmp = RREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_INT_FLOOD_CNTL));
+	tmp = RREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL);
 	tmp = REG_SET_FIELD(tmp, IH_INT_FLOOD_CNTL, FLOOD_CNTL_ENABLE, 1);
-	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_INT_FLOOD_CNTL), tmp);
+	WREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL, tmp);
 
 	pci_set_master(adev->pdev);
 
@@ -334,8 +327,8 @@ static void vega10_ih_decode_iv(struct amdgpu_device *adev,
 	entry->client_id = dw[0] & 0xff;
 	entry->src_id = (dw[0] >> 8) & 0xff;
 	entry->ring_id = (dw[0] >> 16) & 0xff;
-	entry->vm_id = (dw[0] >> 24) & 0xf;
-	entry->vm_id_src = (dw[0] >> 31);
+	entry->vmid = (dw[0] >> 24) & 0xf;
+	entry->vmid_src = (dw[0] >> 31);
 	entry->timestamp = dw[1] | ((u64)(dw[2] & 0xffff) << 32);
 	entry->timestamp_src = dw[2] >> 31;
 	entry->pas_id = dw[3] & 0xffff;
@@ -367,7 +360,7 @@ static void vega10_ih_set_rptr(struct amdgpu_device *adev)
 			adev->wb.wb[adev->irq.ih.rptr_offs] = adev->irq.ih.rptr;
 		WDOORBELL32(adev->irq.ih.doorbell_index, adev->irq.ih.rptr);
 	} else {
-		WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_RPTR), adev->irq.ih.rptr);
+		WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR, adev->irq.ih.rptr);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
new file mode 100644
index 000000000000..b7bdd04793d6
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "soc15.h"
+
+#include "soc15_common.h"
+#include "soc15ip.h"
+
+int vega10_reg_base_init(struct amdgpu_device *adev)
+{
+	/* HW has more IP blocks,  only initialized the blocke beend by our driver  */
+	uint32_t i;
+	for (i = 0 ; i < MAX_INSTANCE ; ++i) {
+		adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i]));
+		adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i]));
+		adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i]));
+		adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i]));
+		adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i]));
+		adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i]));
+		adev->reg_offset[UVD_HWIP][i] = (uint32_t *)(&(UVD_BASE.instance[i]));
+		adev->reg_offset[VCE_HWIP][i] = (uint32_t *)(&(VCE_BASE.instance[i]));
+		adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(VCN_BASE.instance[i]));
+		adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i]));
+		adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DCE_BASE.instance[i]));
+		adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i]));
+		adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(SDMA0_BASE.instance[i]));
+		adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(SDMA1_BASE.instance[i]));
+		adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i]));
+		adev->reg_offset[PWR_HWIP][i] = (uint32_t *)(&(PWR_BASE.instance[i]));
+		adev->reg_offset[NBIF_HWIP][i] = (uint32_t *)(&(NBIF_BASE.instance[i]));
+
+	}
+	return 0;
+}
+
+
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 3a4c2fa7e36d..da2b99c2d95f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -282,29 +282,29 @@ static void vi_init_golden_registers(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_TOPAZ:
-		amdgpu_program_register_sequence(adev,
-						 iceland_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(iceland_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							iceland_mgcg_cgcg_init,
+							ARRAY_SIZE(iceland_mgcg_cgcg_init));
 		break;
 	case CHIP_FIJI:
-		amdgpu_program_register_sequence(adev,
-						 fiji_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(fiji_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							fiji_mgcg_cgcg_init,
+							ARRAY_SIZE(fiji_mgcg_cgcg_init));
 		break;
 	case CHIP_TONGA:
-		amdgpu_program_register_sequence(adev,
-						 tonga_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(tonga_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							tonga_mgcg_cgcg_init,
+							ARRAY_SIZE(tonga_mgcg_cgcg_init));
 		break;
 	case CHIP_CARRIZO:
-		amdgpu_program_register_sequence(adev,
-						 cz_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(cz_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							cz_mgcg_cgcg_init,
+							ARRAY_SIZE(cz_mgcg_cgcg_init));
 		break;
 	case CHIP_STONEY:
-		amdgpu_program_register_sequence(adev,
-						 stoney_mgcg_cgcg_init,
-						 (const u32)ARRAY_SIZE(stoney_mgcg_cgcg_init));
+		amdgpu_device_program_register_sequence(adev,
+							stoney_mgcg_cgcg_init,
+							ARRAY_SIZE(stoney_mgcg_cgcg_init));
 		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
@@ -449,14 +449,18 @@ static bool vi_read_bios_from_rom(struct amdgpu_device *adev,
 
 static void vi_detect_hw_virtualization(struct amdgpu_device *adev)
 {
-	uint32_t reg = RREG32(mmBIF_IOV_FUNC_IDENTIFIER);
-	/* bit0: 0 means pf and 1 means vf */
-	/* bit31: 0 means disable IOV and 1 means enable */
-	if (reg & 1)
-		adev->virt.caps |= AMDGPU_SRIOV_CAPS_IS_VF;
-
-	if (reg & 0x80000000)
-		adev->virt.caps |= AMDGPU_SRIOV_CAPS_ENABLE_IOV;
+	uint32_t reg = 0;
+
+	if (adev->asic_type == CHIP_TONGA ||
+	    adev->asic_type == CHIP_FIJI) {
+	       reg = RREG32(mmBIF_IOV_FUNC_IDENTIFIER);
+	       /* bit0: 0 means pf and 1 means vf */
+	       if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, FUNC_IDENTIFIER))
+		       adev->virt.caps |= AMDGPU_SRIOV_CAPS_IS_VF;
+	       /* bit31: 0 means disable IOV and 1 means enable */
+	       if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, IOV_ENABLE))
+		       adev->virt.caps |= AMDGPU_SRIOV_CAPS_ENABLE_IOV;
+	}
 
 	if (reg == 0) {
 		if (is_virtual_machine()) /* passthrough mode exclus sr-iov mode */
@@ -667,7 +671,7 @@ static int vi_gpu_pci_config_reset(struct amdgpu_device *adev)
 	/* disable BM */
 	pci_clear_master(adev->pdev);
 	/* reset */
-	amdgpu_pci_config_reset(adev);
+	amdgpu_device_pci_config_reset(adev);
 
 	udelay(100);
 
@@ -891,8 +895,8 @@ static int vi_common_early_init(void *handle)
 
 	adev->asic_funcs = &vi_asic_funcs;
 
-	if (amdgpu_get_ip_block(adev, AMD_IP_BLOCK_TYPE_SMC) &&
-		(amdgpu_ip_block_mask & (1 << AMD_IP_BLOCK_TYPE_SMC)))
+	if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_SMC) &&
+	    (amdgpu_ip_block_mask & (1 << AMD_IP_BLOCK_TYPE_SMC)))
 		smc_enabled = true;
 
 	adev->rev_id = vi_get_rev_id(adev);
@@ -1074,7 +1078,7 @@ static int vi_common_early_init(void *handle)
 	/* vi use smc load by default */
 	adev->firmware.load_type = amdgpu_ucode_get_load_type(adev, amdgpu_fw_load_type);
 
-	amdgpu_get_pcie_info(adev);
+	amdgpu_device_get_pcie_info(adev);
 
 	return 0;
 }
@@ -1487,115 +1491,115 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 	switch (adev->asic_type) {
 	case CHIP_TOPAZ:
 		/* topaz has no DCE, UVD, VCE */
-		amdgpu_ip_block_add(adev, &vi_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v7_4_ip_block);
-		amdgpu_ip_block_add(adev, &iceland_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v7_4_ip_block);
+		amdgpu_device_ip_block_add(adev, &iceland_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v8_0_ip_block);
-		amdgpu_ip_block_add(adev, &sdma_v2_4_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v2_4_ip_block);
 		break;
 	case CHIP_FIJI:
-		amdgpu_ip_block_add(adev, &vi_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v8_5_ip_block);
-		amdgpu_ip_block_add(adev, &tonga_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v8_5_ip_block);
+		amdgpu_device_ip_block_add(adev, &tonga_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
-			amdgpu_ip_block_add(adev, &dm_ip_block);
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		else
-			amdgpu_ip_block_add(adev, &dce_v10_1_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v8_0_ip_block);
-		amdgpu_ip_block_add(adev, &sdma_v3_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_v10_1_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		if (!amdgpu_sriov_vf(adev)) {
-			amdgpu_ip_block_add(adev, &uvd_v6_0_ip_block);
-			amdgpu_ip_block_add(adev, &vce_v3_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &uvd_v6_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &vce_v3_0_ip_block);
 		}
 		break;
 	case CHIP_TONGA:
-		amdgpu_ip_block_add(adev, &vi_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v8_0_ip_block);
-		amdgpu_ip_block_add(adev, &tonga_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &tonga_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
-			amdgpu_ip_block_add(adev, &dm_ip_block);
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		else
-			amdgpu_ip_block_add(adev, &dce_v10_0_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v8_0_ip_block);
-		amdgpu_ip_block_add(adev, &sdma_v3_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_v10_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
 		if (!amdgpu_sriov_vf(adev)) {
-			amdgpu_ip_block_add(adev, &uvd_v5_0_ip_block);
-			amdgpu_ip_block_add(adev, &vce_v3_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &uvd_v5_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &vce_v3_0_ip_block);
 		}
 		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
 	case CHIP_POLARIS12:
-		amdgpu_ip_block_add(adev, &vi_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v8_1_ip_block);
-		amdgpu_ip_block_add(adev, &tonga_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v8_1_ip_block);
+		amdgpu_device_ip_block_add(adev, &tonga_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
-			amdgpu_ip_block_add(adev, &dm_ip_block);
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		else
-			amdgpu_ip_block_add(adev, &dce_v11_2_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v8_0_ip_block);
-		amdgpu_ip_block_add(adev, &sdma_v3_1_ip_block);
-		amdgpu_ip_block_add(adev, &uvd_v6_3_ip_block);
-		amdgpu_ip_block_add(adev, &vce_v3_4_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_v11_2_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v3_1_ip_block);
+		amdgpu_device_ip_block_add(adev, &uvd_v6_3_ip_block);
+		amdgpu_device_ip_block_add(adev, &vce_v3_4_ip_block);
 		break;
 	case CHIP_CARRIZO:
-		amdgpu_ip_block_add(adev, &vi_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v8_0_ip_block);
-		amdgpu_ip_block_add(adev, &cz_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &cz_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
-			amdgpu_ip_block_add(adev, &dm_ip_block);
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		else
-			amdgpu_ip_block_add(adev, &dce_v11_0_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v8_0_ip_block);
-		amdgpu_ip_block_add(adev, &sdma_v3_0_ip_block);
-		amdgpu_ip_block_add(adev, &uvd_v6_0_ip_block);
-		amdgpu_ip_block_add(adev, &vce_v3_1_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_v11_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &uvd_v6_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &vce_v3_1_ip_block);
 #if defined(CONFIG_DRM_AMD_ACP)
-		amdgpu_ip_block_add(adev, &acp_ip_block);
+		amdgpu_device_ip_block_add(adev, &acp_ip_block);
 #endif
 		break;
 	case CHIP_STONEY:
-		amdgpu_ip_block_add(adev, &vi_common_ip_block);
-		amdgpu_ip_block_add(adev, &gmc_v8_0_ip_block);
-		amdgpu_ip_block_add(adev, &cz_ih_ip_block);
-		amdgpu_ip_block_add(adev, &amdgpu_pp_ip_block);
+		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
+		amdgpu_device_ip_block_add(adev, &gmc_v8_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &cz_ih_ip_block);
+		amdgpu_device_ip_block_add(adev, &amdgpu_pp_ip_block);
 		if (adev->enable_virtual_display)
-			amdgpu_ip_block_add(adev, &dce_virtual_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev))
-			amdgpu_ip_block_add(adev, &dm_ip_block);
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		else
-			amdgpu_ip_block_add(adev, &dce_v11_0_ip_block);
-		amdgpu_ip_block_add(adev, &gfx_v8_1_ip_block);
-		amdgpu_ip_block_add(adev, &sdma_v3_0_ip_block);
-		amdgpu_ip_block_add(adev, &uvd_v6_2_ip_block);
-		amdgpu_ip_block_add(adev, &vce_v3_4_ip_block);
+			amdgpu_device_ip_block_add(adev, &dce_v11_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &gfx_v8_1_ip_block);
+		amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &uvd_v6_2_ip_block);
+		amdgpu_device_ip_block_add(adev, &vce_v3_4_ip_block);
 #if defined(CONFIG_DRM_AMD_ACP)
-		amdgpu_ip_block_add(adev, &acp_ip_block);
+		amdgpu_device_ip_block_add(adev, &acp_ip_block);
 #endif
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/vid.h b/drivers/gpu/drm/amd/amdgpu/vid.h
index dbf3703cbd1b..19ddd2312e00 100644
--- a/drivers/gpu/drm/amd/amdgpu/vid.h
+++ b/drivers/gpu/drm/amd/amdgpu/vid.h
@@ -27,6 +27,8 @@
 #define SDMA1_REGISTER_OFFSET                             0x200 /* not a register */
 #define SDMA_MAX_INSTANCE 2
 
+#define KFD_VI_SDMA_QUEUE_OFFSET                      0x80 /* not a register */
+
 /* crtc instance offsets */
 #define CRTC0_REGISTER_OFFSET                 (0x1b9c - 0x1b9c)
 #define CRTC1_REGISTER_OFFSET                 (0x1d9c - 0x1b9c)
diff --git a/drivers/gpu/drm/amd/amdkfd/Makefile b/drivers/gpu/drm/amd/amdkfd/Makefile
index 7bb0bc0ca3d6..a317e76ffb5e 100644
--- a/drivers/gpu/drm/amd/amdkfd/Makefile
+++ b/drivers/gpu/drm/amd/amdkfd/Makefile
@@ -1,4 +1,24 @@
-# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
 #
 # Makefile for Heterogenous System Architecture support for AMD GPU devices
 #
@@ -15,6 +35,8 @@ amdkfd-y	:= kfd_module.o kfd_device.o kfd_chardev.o kfd_topology.o \
 		kfd_process_queue_manager.o kfd_device_queue_manager.o \
 		kfd_device_queue_manager_cik.o kfd_device_queue_manager_vi.o \
 		kfd_interrupt.o kfd_events.o cik_event_interrupt.o \
-		kfd_dbgdev.o kfd_dbgmgr.o
+		kfd_dbgdev.o kfd_dbgmgr.o kfd_crat.o
+
+amdkfd-$(CONFIG_DEBUG_FS) += kfd_debugfs.o
 
 obj-$(CONFIG_HSA_AMD)	+= amdkfd.o
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
new file mode 100644
index 000000000000..997a383dcb8b
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
@@ -0,0 +1,1384 @@
+/*
+ * Copyright 2015-2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#if 0
+HW (VI) source code for CWSR trap handler
+#Version 18 + multiple trap handler
+
+// this performance-optimal version was originally from Seven Xu at SRDC
+
+// Revison #18   --...
+/* Rev History
+** #1. Branch from gc dv.   //gfxip/gfx8/main/src/test/suites/block/cs/sr/cs_trap_handler.sp3#1,#50, #51, #52-53(Skip, Already Fixed by PV), #54-56(merged),#57-58(mergerd, skiped-already fixed by PV)
+** #4. SR Memory Layout:
+**             1. VGPR-SGPR-HWREG-{LDS}
+**             2. tba_hi.bits.26 - reconfigured as the first wave in tg bits, for defer Save LDS for a threadgroup.. performance concern..
+** #5. Update: 1. Accurate g8sr_ts_save_d timestamp
+** #6. Update: 1. Fix s_barrier usage; 2. VGPR s/r using swizzle buffer?(NoNeed, already matched the swizzle pattern, more investigation)
+** #7. Update: 1. don't barrier if noLDS
+** #8. Branch: 1. Branch to ver#0, which is very similar to gc dv version
+**             2. Fix SQ issue by s_sleep 2
+** #9. Update: 1. Fix scc restore failed issue, restore wave_status at last
+**             2. optimize s_buffer save by burst 16sgprs...
+** #10. Update 1. Optimize restore sgpr by busrt 16 sgprs.
+** #11. Update 1. Add 2 more timestamp for debug version
+** #12. Update 1. Add VGPR SR using DWx4, some case improve and some case drop performance
+** #13. Integ  1. Always use MUBUF for PV trap shader...
+** #14. Update 1. s_buffer_store soft clause...
+** #15. Update 1. PERF - sclar write with glc:0/mtype0 to allow L2 combine. perf improvement a lot.
+** #16. Update 1. PRRF - UNROLL LDS_DMA got 2500cycle save in IP tree
+** #17. Update 1. FUNC - LDS_DMA has issues while ATC, replace with ds_read/buffer_store for save part[TODO restore part]
+**             2. PERF - Save LDS before save VGPR to cover LDS save long latency...
+** #18. Update 1. FUNC - Implicitly estore STATUS.VCCZ, which is not writable by s_setreg_b32
+**             2. FUNC - Handle non-CWSR traps
+*/
+
+var G8SR_WDMEM_HWREG_OFFSET = 0
+var G8SR_WDMEM_SGPR_OFFSET  = 128  // in bytes
+
+// Keep definition same as the app shader, These 2 time stamps are part of the app shader... Should before any Save and after restore.
+
+var G8SR_DEBUG_TIMESTAMP = 0
+var G8SR_DEBUG_TS_SAVE_D_OFFSET = 40*4  // ts_save_d timestamp offset relative to SGPR_SR_memory_offset
+var s_g8sr_ts_save_s    = s[34:35]   // save start
+var s_g8sr_ts_sq_save_msg  = s[36:37]   // The save shader send SAVEWAVE msg to spi
+var s_g8sr_ts_spi_wrexec   = s[38:39]   // the SPI write the sr address to SQ
+var s_g8sr_ts_save_d    = s[40:41]   // save end
+var s_g8sr_ts_restore_s = s[42:43]   // restore start
+var s_g8sr_ts_restore_d = s[44:45]   // restore end
+
+var G8SR_VGPR_SR_IN_DWX4 = 0
+var G8SR_SAVE_BUF_RSRC_WORD1_STRIDE_DWx4 = 0x00100000    // DWx4 stride is 4*4Bytes
+var G8SR_RESTORE_BUF_RSRC_WORD1_STRIDE_DWx4  = G8SR_SAVE_BUF_RSRC_WORD1_STRIDE_DWx4
+
+
+/*************************************************************************/
+/*                  control on how to run the shader                     */
+/*************************************************************************/
+//any hack that needs to be made to run this code in EMU (either because various EMU code are not ready or no compute save & restore in EMU run)
+var EMU_RUN_HACK                    =   0
+var EMU_RUN_HACK_RESTORE_NORMAL     =   0
+var EMU_RUN_HACK_SAVE_NORMAL_EXIT   =   0
+var EMU_RUN_HACK_SAVE_SINGLE_WAVE   =   0
+var EMU_RUN_HACK_SAVE_FIRST_TIME    =   0                   //for interrupted restore in which the first save is through EMU_RUN_HACK
+var EMU_RUN_HACK_SAVE_FIRST_TIME_TBA_LO =   0                   //for interrupted restore in which the first save is through EMU_RUN_HACK
+var EMU_RUN_HACK_SAVE_FIRST_TIME_TBA_HI =   0                   //for interrupted restore in which the first save is through EMU_RUN_HACK
+var SAVE_LDS                        =   1
+var WG_BASE_ADDR_LO                 =   0x9000a000
+var WG_BASE_ADDR_HI                 =   0x0
+var WAVE_SPACE                      =   0x5000              //memory size that each wave occupies in workgroup state mem
+var CTX_SAVE_CONTROL                =   0x0
+var CTX_RESTORE_CONTROL             =   CTX_SAVE_CONTROL
+var SIM_RUN_HACK                    =   0                   //any hack that needs to be made to run this code in SIM (either because various RTL code are not ready or no compute save & restore in RTL run)
+var SGPR_SAVE_USE_SQC               =   1                   //use SQC D$ to do the write
+var USE_MTBUF_INSTEAD_OF_MUBUF      =   0                   //because TC EMU currently asserts on 0 of // overload DFMT field to carry 4 more bits of stride for MUBUF opcodes
+var SWIZZLE_EN                      =   0                   //whether we use swizzled buffer addressing
+
+/**************************************************************************/
+/*                      variables                                         */
+/**************************************************************************/
+var SQ_WAVE_STATUS_INST_ATC_SHIFT  = 23
+var SQ_WAVE_STATUS_INST_ATC_MASK   = 0x00800000
+var SQ_WAVE_STATUS_SPI_PRIO_MASK   = 0x00000006
+
+var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT    = 12
+var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE     = 9
+var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT   = 8
+var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE    = 6
+var SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SHIFT   = 24
+var SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SIZE    = 3                     //FIXME  sq.blk still has 4 bits at this time while SQ programming guide has 3 bits
+
+var SQ_WAVE_TRAPSTS_SAVECTX_MASK    =   0x400
+var SQ_WAVE_TRAPSTS_EXCE_MASK       =   0x1FF                   // Exception mask
+var SQ_WAVE_TRAPSTS_SAVECTX_SHIFT   =   10
+var SQ_WAVE_TRAPSTS_MEM_VIOL_MASK   =   0x100
+var SQ_WAVE_TRAPSTS_MEM_VIOL_SHIFT  =   8
+var SQ_WAVE_TRAPSTS_PRE_SAVECTX_MASK    =   0x3FF
+var SQ_WAVE_TRAPSTS_PRE_SAVECTX_SHIFT   =   0x0
+var SQ_WAVE_TRAPSTS_PRE_SAVECTX_SIZE    =   10
+var SQ_WAVE_TRAPSTS_POST_SAVECTX_MASK   =   0xFFFFF800
+var SQ_WAVE_TRAPSTS_POST_SAVECTX_SHIFT  =   11
+var SQ_WAVE_TRAPSTS_POST_SAVECTX_SIZE   =   21
+
+var SQ_WAVE_IB_STS_RCNT_SHIFT           =   16                  //FIXME
+var SQ_WAVE_IB_STS_RCNT_SIZE            =   4                   //FIXME
+var SQ_WAVE_IB_STS_FIRST_REPLAY_SHIFT   =   15                  //FIXME
+var SQ_WAVE_IB_STS_FIRST_REPLAY_SIZE    =   1                   //FIXME
+var SQ_WAVE_IB_STS_RCNT_FIRST_REPLAY_MASK_NEG   = 0x00007FFF    //FIXME
+
+var SQ_BUF_RSRC_WORD1_ATC_SHIFT     =   24
+var SQ_BUF_RSRC_WORD3_MTYPE_SHIFT   =   27
+
+
+/*      Save        */
+var S_SAVE_BUF_RSRC_WORD1_STRIDE        =   0x00040000          //stride is 4 bytes
+var S_SAVE_BUF_RSRC_WORD3_MISC          =   0x00807FAC          //SQ_SEL_X/Y/Z/W, BUF_NUM_FORMAT_FLOAT, (0 for MUBUF stride[17:14] when ADD_TID_ENABLE and BUF_DATA_FORMAT_32 for MTBUF), ADD_TID_ENABLE
+
+var S_SAVE_SPI_INIT_ATC_MASK            =   0x08000000          //bit[27]: ATC bit
+var S_SAVE_SPI_INIT_ATC_SHIFT           =   27
+var S_SAVE_SPI_INIT_MTYPE_MASK          =   0x70000000          //bit[30:28]: Mtype
+var S_SAVE_SPI_INIT_MTYPE_SHIFT         =   28
+var S_SAVE_SPI_INIT_FIRST_WAVE_MASK     =   0x04000000          //bit[26]: FirstWaveInTG
+var S_SAVE_SPI_INIT_FIRST_WAVE_SHIFT    =   26
+
+var S_SAVE_PC_HI_RCNT_SHIFT             =   28                  //FIXME  check with Brian to ensure all fields other than PC[47:0] can be used
+var S_SAVE_PC_HI_RCNT_MASK              =   0xF0000000          //FIXME
+var S_SAVE_PC_HI_FIRST_REPLAY_SHIFT     =   27                  //FIXME
+var S_SAVE_PC_HI_FIRST_REPLAY_MASK      =   0x08000000          //FIXME
+
+var s_save_spi_init_lo              =   exec_lo
+var s_save_spi_init_hi              =   exec_hi
+
+                                                //tba_lo and tba_hi need to be saved/restored
+var s_save_pc_lo            =   ttmp0           //{TTMP1, TTMP0} = {3??h0,pc_rewind[3:0], HT[0],trapID[7:0], PC[47:0]}
+var s_save_pc_hi            =   ttmp1
+var s_save_exec_lo          =   ttmp2
+var s_save_exec_hi          =   ttmp3
+var s_save_status           =   ttmp4
+var s_save_trapsts          =   ttmp5           //not really used until the end of the SAVE routine
+var s_save_xnack_mask_lo    =   ttmp6
+var s_save_xnack_mask_hi    =   ttmp7
+var s_save_buf_rsrc0        =   ttmp8
+var s_save_buf_rsrc1        =   ttmp9
+var s_save_buf_rsrc2        =   ttmp10
+var s_save_buf_rsrc3        =   ttmp11
+
+var s_save_mem_offset       =   tma_lo
+var s_save_alloc_size       =   s_save_trapsts          //conflict
+var s_save_tmp              =   s_save_buf_rsrc2        //shared with s_save_buf_rsrc2  (conflict: should not use mem access with s_save_tmp at the same time)
+var s_save_m0               =   tma_hi
+
+/*      Restore     */
+var S_RESTORE_BUF_RSRC_WORD1_STRIDE         =   S_SAVE_BUF_RSRC_WORD1_STRIDE
+var S_RESTORE_BUF_RSRC_WORD3_MISC           =   S_SAVE_BUF_RSRC_WORD3_MISC
+
+var S_RESTORE_SPI_INIT_ATC_MASK             =   0x08000000          //bit[27]: ATC bit
+var S_RESTORE_SPI_INIT_ATC_SHIFT            =   27
+var S_RESTORE_SPI_INIT_MTYPE_MASK           =   0x70000000          //bit[30:28]: Mtype
+var S_RESTORE_SPI_INIT_MTYPE_SHIFT          =   28
+var S_RESTORE_SPI_INIT_FIRST_WAVE_MASK      =   0x04000000          //bit[26]: FirstWaveInTG
+var S_RESTORE_SPI_INIT_FIRST_WAVE_SHIFT     =   26
+
+var S_RESTORE_PC_HI_RCNT_SHIFT              =   S_SAVE_PC_HI_RCNT_SHIFT
+var S_RESTORE_PC_HI_RCNT_MASK               =   S_SAVE_PC_HI_RCNT_MASK
+var S_RESTORE_PC_HI_FIRST_REPLAY_SHIFT      =   S_SAVE_PC_HI_FIRST_REPLAY_SHIFT
+var S_RESTORE_PC_HI_FIRST_REPLAY_MASK       =   S_SAVE_PC_HI_FIRST_REPLAY_MASK
+
+var s_restore_spi_init_lo                   =   exec_lo
+var s_restore_spi_init_hi                   =   exec_hi
+
+var s_restore_mem_offset        =   ttmp2
+var s_restore_alloc_size        =   ttmp3
+var s_restore_tmp               =   ttmp6               //tba_lo/hi need to be restored
+var s_restore_mem_offset_save   =   s_restore_tmp       //no conflict
+
+var s_restore_m0            =   s_restore_alloc_size    //no conflict
+
+var s_restore_mode          =   ttmp7
+
+var s_restore_pc_lo         =   ttmp0
+var s_restore_pc_hi         =   ttmp1
+var s_restore_exec_lo       =   tma_lo                  //no conflict
+var s_restore_exec_hi       =   tma_hi                  //no conflict
+var s_restore_status        =   ttmp4
+var s_restore_trapsts       =   ttmp5
+var s_restore_xnack_mask_lo =   xnack_mask_lo
+var s_restore_xnack_mask_hi =   xnack_mask_hi
+var s_restore_buf_rsrc0     =   ttmp8
+var s_restore_buf_rsrc1     =   ttmp9
+var s_restore_buf_rsrc2     =   ttmp10
+var s_restore_buf_rsrc3     =   ttmp11
+
+/**************************************************************************/
+/*                      trap handler entry points                         */
+/**************************************************************************/
+/* Shader Main*/
+
+shader main
+  asic(VI)
+  type(CS)
+
+
+    if ((EMU_RUN_HACK) && (!EMU_RUN_HACK_RESTORE_NORMAL))                   //hack to use trap_id for determining save/restore
+        //FIXME VCCZ un-init assertion s_getreg_b32     s_save_status, hwreg(HW_REG_STATUS)         //save STATUS since we will change SCC
+        s_and_b32 s_save_tmp, s_save_pc_hi, 0xffff0000              //change SCC
+        s_cmp_eq_u32 s_save_tmp, 0x007e0000                         //Save: trap_id = 0x7e. Restore: trap_id = 0x7f.
+        s_cbranch_scc0 L_JUMP_TO_RESTORE                            //do not need to recover STATUS here  since we are going to RESTORE
+        //FIXME  s_setreg_b32   hwreg(HW_REG_STATUS),   s_save_status       //need to recover STATUS since we are going to SAVE
+        s_branch L_SKIP_RESTORE                                     //NOT restore, SAVE actually
+    else
+        s_branch L_SKIP_RESTORE                                     //NOT restore. might be a regular trap or save
+    end
+
+L_JUMP_TO_RESTORE:
+    s_branch L_RESTORE                                              //restore
+
+L_SKIP_RESTORE:
+
+    s_getreg_b32    s_save_status, hwreg(HW_REG_STATUS)                             //save STATUS since we will change SCC
+    s_andn2_b32     s_save_status, s_save_status, SQ_WAVE_STATUS_SPI_PRIO_MASK      //check whether this is for save
+    s_getreg_b32    s_save_trapsts, hwreg(HW_REG_TRAPSTS)
+    s_and_b32       s_save_trapsts, s_save_trapsts, SQ_WAVE_TRAPSTS_SAVECTX_MASK    //check whether this is for save
+    s_cbranch_scc1  L_SAVE                                      //this is the operation for save
+
+    // *********    Handle non-CWSR traps       *******************
+if (!EMU_RUN_HACK)
+    /* read tba and tma for next level trap handler, ttmp4 is used as s_save_status */
+    s_load_dwordx4  [ttmp8,ttmp9,ttmp10, ttmp11], [tma_lo,tma_hi], 0
+    s_waitcnt lgkmcnt(0)
+    s_or_b32        ttmp7, ttmp8, ttmp9
+    s_cbranch_scc0  L_NO_NEXT_TRAP //next level trap handler not been set
+    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC)
+    s_setpc_b64     [ttmp8,ttmp9] //jump to next level trap handler
+
+L_NO_NEXT_TRAP:
+    s_getreg_b32    s_save_trapsts, hwreg(HW_REG_TRAPSTS)
+    s_and_b32       s_save_trapsts, s_save_trapsts, SQ_WAVE_TRAPSTS_EXCE_MASK // Check whether it is an exception
+    s_cbranch_scc1  L_EXCP_CASE   // Exception, jump back to the shader program directly.
+    s_add_u32       ttmp0, ttmp0, 4   // S_TRAP case, add 4 to ttmp0
+    s_addc_u32  ttmp1, ttmp1, 0
+L_EXCP_CASE:
+    s_and_b32   ttmp1, ttmp1, 0xFFFF
+    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC)
+    s_rfe_b64       [ttmp0, ttmp1]
+end
+    // *********        End handling of non-CWSR traps   *******************
+
+/**************************************************************************/
+/*                      save routine                                      */
+/**************************************************************************/
+
+L_SAVE:
+
+if G8SR_DEBUG_TIMESTAMP
+        s_memrealtime   s_g8sr_ts_save_s
+        s_waitcnt lgkmcnt(0)         //FIXME, will cause xnack??
+end
+
+    //check whether there is mem_viol
+    s_getreg_b32    s_save_trapsts, hwreg(HW_REG_TRAPSTS)
+    s_and_b32   s_save_trapsts, s_save_trapsts, SQ_WAVE_TRAPSTS_MEM_VIOL_MASK
+    s_cbranch_scc0  L_NO_PC_REWIND
+
+    //if so, need rewind PC assuming GDS operation gets NACKed
+    s_mov_b32       s_save_tmp, 0                                                           //clear mem_viol bit
+    s_setreg_b32    hwreg(HW_REG_TRAPSTS, SQ_WAVE_TRAPSTS_MEM_VIOL_SHIFT, 1), s_save_tmp    //clear mem_viol bit
+    s_and_b32       s_save_pc_hi, s_save_pc_hi, 0x0000ffff    //pc[47:32]
+    s_sub_u32       s_save_pc_lo, s_save_pc_lo, 8             //pc[31:0]-8
+    s_subb_u32      s_save_pc_hi, s_save_pc_hi, 0x0           // -scc
+
+L_NO_PC_REWIND:
+    s_mov_b32       s_save_tmp, 0                                                           //clear saveCtx bit
+    s_setreg_b32    hwreg(HW_REG_TRAPSTS, SQ_WAVE_TRAPSTS_SAVECTX_SHIFT, 1), s_save_tmp     //clear saveCtx bit
+
+    s_mov_b32       s_save_xnack_mask_lo,   xnack_mask_lo                                   //save XNACK_MASK
+    s_mov_b32       s_save_xnack_mask_hi,   xnack_mask_hi    //save XNACK must before any memory operation
+    s_getreg_b32    s_save_tmp, hwreg(HW_REG_IB_STS, SQ_WAVE_IB_STS_RCNT_SHIFT, SQ_WAVE_IB_STS_RCNT_SIZE)                   //save RCNT
+    s_lshl_b32      s_save_tmp, s_save_tmp, S_SAVE_PC_HI_RCNT_SHIFT
+    s_or_b32        s_save_pc_hi, s_save_pc_hi, s_save_tmp
+    s_getreg_b32    s_save_tmp, hwreg(HW_REG_IB_STS, SQ_WAVE_IB_STS_FIRST_REPLAY_SHIFT, SQ_WAVE_IB_STS_FIRST_REPLAY_SIZE)   //save FIRST_REPLAY
+    s_lshl_b32      s_save_tmp, s_save_tmp, S_SAVE_PC_HI_FIRST_REPLAY_SHIFT
+    s_or_b32        s_save_pc_hi, s_save_pc_hi, s_save_tmp
+    s_getreg_b32    s_save_tmp, hwreg(HW_REG_IB_STS)                                        //clear RCNT and FIRST_REPLAY in IB_STS
+    s_and_b32       s_save_tmp, s_save_tmp, SQ_WAVE_IB_STS_RCNT_FIRST_REPLAY_MASK_NEG
+
+    s_setreg_b32    hwreg(HW_REG_IB_STS), s_save_tmp
+
+    /*      inform SPI the readiness and wait for SPI's go signal */
+    s_mov_b32       s_save_exec_lo, exec_lo                                                 //save EXEC and use EXEC for the go signal from SPI
+    s_mov_b32       s_save_exec_hi, exec_hi
+    s_mov_b64       exec,   0x0                                                             //clear EXEC to get ready to receive
+
+if G8SR_DEBUG_TIMESTAMP
+        s_memrealtime  s_g8sr_ts_sq_save_msg
+        s_waitcnt lgkmcnt(0)
+end
+
+    if (EMU_RUN_HACK)
+
+    else
+        s_sendmsg   sendmsg(MSG_SAVEWAVE)  //send SPI a message and wait for SPI's write to EXEC
+    end
+
+  L_SLEEP:
+    s_sleep 0x2                // sleep 1 (64clk) is not enough for 8 waves per SIMD, which will cause SQ hang, since the 7,8th wave could not get arbit to exec inst, while other waves are stuck into the sleep-loop and waiting for wrexec!=0
+
+    if (EMU_RUN_HACK)
+
+    else
+        s_cbranch_execz L_SLEEP
+    end
+
+if G8SR_DEBUG_TIMESTAMP
+        s_memrealtime  s_g8sr_ts_spi_wrexec
+        s_waitcnt lgkmcnt(0)
+end
+
+    /*      setup Resource Contants    */
+    if ((EMU_RUN_HACK) && (!EMU_RUN_HACK_SAVE_SINGLE_WAVE))
+        //calculate wd_addr using absolute thread id
+        v_readlane_b32 s_save_tmp, v9, 0
+        s_lshr_b32 s_save_tmp, s_save_tmp, 6
+        s_mul_i32 s_save_tmp, s_save_tmp, WAVE_SPACE
+        s_add_i32 s_save_spi_init_lo, s_save_tmp, WG_BASE_ADDR_LO
+        s_mov_b32 s_save_spi_init_hi, WG_BASE_ADDR_HI
+        s_and_b32 s_save_spi_init_hi, s_save_spi_init_hi, CTX_SAVE_CONTROL
+    else
+    end
+    if ((EMU_RUN_HACK) && (EMU_RUN_HACK_SAVE_SINGLE_WAVE))
+        s_add_i32 s_save_spi_init_lo, s_save_tmp, WG_BASE_ADDR_LO
+        s_mov_b32 s_save_spi_init_hi, WG_BASE_ADDR_HI
+        s_and_b32 s_save_spi_init_hi, s_save_spi_init_hi, CTX_SAVE_CONTROL
+    else
+    end
+
+
+    s_mov_b32       s_save_buf_rsrc0,   s_save_spi_init_lo                                                      //base_addr_lo
+    s_and_b32       s_save_buf_rsrc1,   s_save_spi_init_hi, 0x0000FFFF                                          //base_addr_hi
+    s_or_b32        s_save_buf_rsrc1,   s_save_buf_rsrc1,  S_SAVE_BUF_RSRC_WORD1_STRIDE
+    s_mov_b32       s_save_buf_rsrc2,   0                                                                       //NUM_RECORDS initial value = 0 (in bytes) although not neccessarily inited
+    s_mov_b32       s_save_buf_rsrc3,   S_SAVE_BUF_RSRC_WORD3_MISC
+    s_and_b32       s_save_tmp,         s_save_spi_init_hi, S_SAVE_SPI_INIT_ATC_MASK
+    s_lshr_b32      s_save_tmp,         s_save_tmp, (S_SAVE_SPI_INIT_ATC_SHIFT-SQ_BUF_RSRC_WORD1_ATC_SHIFT)         //get ATC bit into position
+    s_or_b32        s_save_buf_rsrc3,   s_save_buf_rsrc3,  s_save_tmp                                           //or ATC
+    s_and_b32       s_save_tmp,         s_save_spi_init_hi, S_SAVE_SPI_INIT_MTYPE_MASK
+    s_lshr_b32      s_save_tmp,         s_save_tmp, (S_SAVE_SPI_INIT_MTYPE_SHIFT-SQ_BUF_RSRC_WORD3_MTYPE_SHIFT)     //get MTYPE bits into position
+    s_or_b32        s_save_buf_rsrc3,   s_save_buf_rsrc3,  s_save_tmp                                           //or MTYPE
+
+    //FIXME  right now s_save_m0/s_save_mem_offset use tma_lo/tma_hi  (might need to save them before using them?)
+    s_mov_b32       s_save_m0,          m0                                                                  //save M0
+
+    /*      global mem offset           */
+    s_mov_b32       s_save_mem_offset,  0x0                                                                     //mem offset initial value = 0
+
+
+
+
+    /*      save HW registers   */
+    //////////////////////////////
+
+  L_SAVE_HWREG:
+        // HWREG SR memory offset : size(VGPR)+size(SGPR)
+       get_vgpr_size_bytes(s_save_mem_offset)
+       get_sgpr_size_bytes(s_save_tmp)
+       s_add_u32 s_save_mem_offset, s_save_mem_offset, s_save_tmp
+
+
+    s_mov_b32       s_save_buf_rsrc2, 0x4                               //NUM_RECORDS   in bytes
+    if (SWIZZLE_EN)
+        s_add_u32       s_save_buf_rsrc2, s_save_buf_rsrc2, 0x0                     //FIXME need to use swizzle to enable bounds checking?
+    else
+        s_mov_b32       s_save_buf_rsrc2,  0x1000000                                //NUM_RECORDS in bytes
+    end
+
+
+    write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset)                  //M0
+
+    if ((EMU_RUN_HACK) && (EMU_RUN_HACK_SAVE_FIRST_TIME))
+        s_add_u32 s_save_pc_lo, s_save_pc_lo, 4             //pc[31:0]+4
+        s_addc_u32 s_save_pc_hi, s_save_pc_hi, 0x0          //carry bit over
+        s_mov_b32   tba_lo, EMU_RUN_HACK_SAVE_FIRST_TIME_TBA_LO
+        s_mov_b32   tba_hi, EMU_RUN_HACK_SAVE_FIRST_TIME_TBA_HI
+    end
+
+    write_hwreg_to_mem(s_save_pc_lo, s_save_buf_rsrc0, s_save_mem_offset)                   //PC
+    write_hwreg_to_mem(s_save_pc_hi, s_save_buf_rsrc0, s_save_mem_offset)
+    write_hwreg_to_mem(s_save_exec_lo, s_save_buf_rsrc0, s_save_mem_offset)             //EXEC
+    write_hwreg_to_mem(s_save_exec_hi, s_save_buf_rsrc0, s_save_mem_offset)
+    write_hwreg_to_mem(s_save_status, s_save_buf_rsrc0, s_save_mem_offset)              //STATUS
+
+    //s_save_trapsts conflicts with s_save_alloc_size
+    s_getreg_b32    s_save_trapsts, hwreg(HW_REG_TRAPSTS)
+    write_hwreg_to_mem(s_save_trapsts, s_save_buf_rsrc0, s_save_mem_offset)             //TRAPSTS
+
+    write_hwreg_to_mem(s_save_xnack_mask_lo, s_save_buf_rsrc0, s_save_mem_offset)           //XNACK_MASK_LO
+    write_hwreg_to_mem(s_save_xnack_mask_hi, s_save_buf_rsrc0, s_save_mem_offset)           //XNACK_MASK_HI
+
+    //use s_save_tmp would introduce conflict here between s_save_tmp and s_save_buf_rsrc2
+    s_getreg_b32    s_save_m0, hwreg(HW_REG_MODE)                                                   //MODE
+    write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset)
+    write_hwreg_to_mem(tba_lo, s_save_buf_rsrc0, s_save_mem_offset)                     //TBA_LO
+    write_hwreg_to_mem(tba_hi, s_save_buf_rsrc0, s_save_mem_offset)                     //TBA_HI
+
+
+
+    /*      the first wave in the threadgroup    */
+        // save fist_wave bits in tba_hi unused bit.26
+    s_and_b32       s_save_tmp, s_save_spi_init_hi, S_SAVE_SPI_INIT_FIRST_WAVE_MASK     // extract fisrt wave bit
+    //s_or_b32        tba_hi, s_save_tmp, tba_hi                                        // save first wave bit to tba_hi.bits[26]
+    s_mov_b32        s_save_exec_hi, 0x0
+    s_or_b32         s_save_exec_hi, s_save_tmp, s_save_exec_hi                          // save first wave bit to s_save_exec_hi.bits[26]
+
+
+    /*          save SGPRs      */
+        // Save SGPR before LDS save, then the s0 to s4 can be used during LDS save...
+    //////////////////////////////
+
+    // SGPR SR memory offset : size(VGPR)
+    get_vgpr_size_bytes(s_save_mem_offset)
+    // TODO, change RSRC word to rearrange memory layout for SGPRS
+
+    s_getreg_b32    s_save_alloc_size, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SIZE)               //spgr_size
+    s_add_u32       s_save_alloc_size, s_save_alloc_size, 1
+    s_lshl_b32      s_save_alloc_size, s_save_alloc_size, 4                         //Number of SGPRs = (sgpr_size + 1) * 16   (non-zero value)
+
+    if (SGPR_SAVE_USE_SQC)
+        s_lshl_b32      s_save_buf_rsrc2,   s_save_alloc_size, 2                    //NUM_RECORDS in bytes
+    else
+        s_lshl_b32      s_save_buf_rsrc2,   s_save_alloc_size, 8                    //NUM_RECORDS in bytes (64 threads)
+    end
+
+    if (SWIZZLE_EN)
+        s_add_u32       s_save_buf_rsrc2, s_save_buf_rsrc2, 0x0                     //FIXME need to use swizzle to enable bounds checking?
+    else
+        s_mov_b32       s_save_buf_rsrc2,  0x1000000                                //NUM_RECORDS in bytes
+    end
+
+
+    // backup s_save_buf_rsrc0,1 to s_save_pc_lo/hi, since write_16sgpr_to_mem function will change the rsrc0
+    //s_mov_b64 s_save_pc_lo, s_save_buf_rsrc0
+    s_mov_b64 s_save_xnack_mask_lo, s_save_buf_rsrc0
+    s_add_u32 s_save_buf_rsrc0, s_save_buf_rsrc0, s_save_mem_offset
+    s_addc_u32 s_save_buf_rsrc1, s_save_buf_rsrc1, 0
+
+    s_mov_b32       m0, 0x0                         //SGPR initial index value =0
+  L_SAVE_SGPR_LOOP:
+    // SGPR is allocated in 16 SGPR granularity
+    s_movrels_b64   s0, s0     //s0 = s[0+m0], s1 = s[1+m0]
+    s_movrels_b64   s2, s2     //s2 = s[2+m0], s3 = s[3+m0]
+    s_movrels_b64   s4, s4     //s4 = s[4+m0], s5 = s[5+m0]
+    s_movrels_b64   s6, s6     //s6 = s[6+m0], s7 = s[7+m0]
+    s_movrels_b64   s8, s8     //s8 = s[8+m0], s9 = s[9+m0]
+    s_movrels_b64   s10, s10   //s10 = s[10+m0], s11 = s[11+m0]
+    s_movrels_b64   s12, s12   //s12 = s[12+m0], s13 = s[13+m0]
+    s_movrels_b64   s14, s14   //s14 = s[14+m0], s15 = s[15+m0]
+
+    write_16sgpr_to_mem(s0, s_save_buf_rsrc0, s_save_mem_offset) //PV: the best performance should be using s_buffer_store_dwordx4
+    s_add_u32       m0, m0, 16                                                      //next sgpr index
+    s_cmp_lt_u32    m0, s_save_alloc_size                                           //scc = (m0 < s_save_alloc_size) ? 1 : 0
+    s_cbranch_scc1  L_SAVE_SGPR_LOOP                                    //SGPR save is complete?
+    // restore s_save_buf_rsrc0,1
+    //s_mov_b64 s_save_buf_rsrc0, s_save_pc_lo
+    s_mov_b64 s_save_buf_rsrc0, s_save_xnack_mask_lo
+
+
+
+
+    /*          save first 4 VGPR, then LDS save could use   */
+        // each wave will alloc 4 vgprs at least...
+    /////////////////////////////////////////////////////////////////////////////////////
+
+    s_mov_b32       s_save_mem_offset, 0
+    s_mov_b32       exec_lo, 0xFFFFFFFF                                             //need every thread from now on
+    s_mov_b32       exec_hi, 0xFFFFFFFF
+
+    if (SWIZZLE_EN)
+        s_add_u32       s_save_buf_rsrc2, s_save_buf_rsrc2, 0x0                     //FIXME need to use swizzle to enable bounds checking?
+    else
+        s_mov_b32       s_save_buf_rsrc2,  0x1000000                                //NUM_RECORDS in bytes
+    end
+
+
+    // VGPR Allocated in 4-GPR granularity
+
+if G8SR_VGPR_SR_IN_DWX4
+        // the const stride for DWx4 is 4*4 bytes
+        s_and_b32 s_save_buf_rsrc1, s_save_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+        s_or_b32  s_save_buf_rsrc1, s_save_buf_rsrc1, G8SR_SAVE_BUF_RSRC_WORD1_STRIDE_DWx4  // const stride to 4*4 bytes
+
+        buffer_store_dwordx4 v0, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1
+
+        s_and_b32 s_save_buf_rsrc1, s_save_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+        s_or_b32  s_save_buf_rsrc1, s_save_buf_rsrc1, S_SAVE_BUF_RSRC_WORD1_STRIDE  // reset const stride to 4 bytes
+else
+        buffer_store_dword v0, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1
+        buffer_store_dword v1, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256
+        buffer_store_dword v2, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256*2
+        buffer_store_dword v3, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256*3
+end
+
+
+
+    /*          save LDS        */
+    //////////////////////////////
+
+  L_SAVE_LDS:
+
+        // Change EXEC to all threads...
+    s_mov_b32       exec_lo, 0xFFFFFFFF   //need every thread from now on
+    s_mov_b32       exec_hi, 0xFFFFFFFF
+
+    s_getreg_b32    s_save_alloc_size, hwreg(HW_REG_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE)             //lds_size
+    s_and_b32       s_save_alloc_size, s_save_alloc_size, 0xFFFFFFFF                //lds_size is zero?
+    s_cbranch_scc0  L_SAVE_LDS_DONE                                                                            //no lds used? jump to L_SAVE_DONE
+
+    s_barrier               //LDS is used? wait for other waves in the same TG
+    //s_and_b32     s_save_tmp, tba_hi, S_SAVE_SPI_INIT_FIRST_WAVE_MASK                //exec is still used here
+    s_and_b32       s_save_tmp, s_save_exec_hi, S_SAVE_SPI_INIT_FIRST_WAVE_MASK                //exec is still used here
+    s_cbranch_scc0  L_SAVE_LDS_DONE
+
+        // first wave do LDS save;
+
+    s_lshl_b32      s_save_alloc_size, s_save_alloc_size, 6                         //LDS size in dwords = lds_size * 64dw
+    s_lshl_b32      s_save_alloc_size, s_save_alloc_size, 2                         //LDS size in bytes
+    s_mov_b32       s_save_buf_rsrc2,  s_save_alloc_size                            //NUM_RECORDS in bytes
+
+    // LDS at offset: size(VGPR)+SIZE(SGPR)+SIZE(HWREG)
+    //
+    get_vgpr_size_bytes(s_save_mem_offset)
+    get_sgpr_size_bytes(s_save_tmp)
+    s_add_u32  s_save_mem_offset, s_save_mem_offset, s_save_tmp
+    s_add_u32 s_save_mem_offset, s_save_mem_offset, get_hwreg_size_bytes()
+
+
+    if (SWIZZLE_EN)
+        s_add_u32       s_save_buf_rsrc2, s_save_buf_rsrc2, 0x0       //FIXME need to use swizzle to enable bounds checking?
+    else
+        s_mov_b32       s_save_buf_rsrc2,  0x1000000                  //NUM_RECORDS in bytes
+    end
+
+    s_mov_b32       m0, 0x0                                               //lds_offset initial value = 0
+
+
+var LDS_DMA_ENABLE = 0
+var UNROLL = 0
+if UNROLL==0 && LDS_DMA_ENABLE==1
+        s_mov_b32  s3, 256*2
+        s_nop 0
+        s_nop 0
+        s_nop 0
+  L_SAVE_LDS_LOOP:
+        //TODO: looks the 2 buffer_store/load clause for s/r will hurt performance.???
+    if (SAVE_LDS)     //SPI always alloc LDS space in 128DW granularity
+            buffer_store_lds_dword s_save_buf_rsrc0, s_save_mem_offset lds:1            // first 64DW
+            buffer_store_lds_dword s_save_buf_rsrc0, s_save_mem_offset lds:1 offset:256 // second 64DW
+    end
+
+    s_add_u32       m0, m0, s3                                          //every buffer_store_lds does 256 bytes
+    s_add_u32       s_save_mem_offset, s_save_mem_offset, s3                            //mem offset increased by 256 bytes
+    s_cmp_lt_u32    m0, s_save_alloc_size                                               //scc=(m0 < s_save_alloc_size) ? 1 : 0
+    s_cbranch_scc1  L_SAVE_LDS_LOOP                                                     //LDS save is complete?
+
+elsif LDS_DMA_ENABLE==1 && UNROLL==1 // UNROOL  , has ichace miss
+      // store from higest LDS address to lowest
+      s_mov_b32  s3, 256*2
+      s_sub_u32  m0, s_save_alloc_size, s3
+      s_add_u32 s_save_mem_offset, s_save_mem_offset, m0
+      s_lshr_b32 s_save_alloc_size, s_save_alloc_size, 9   // how many 128 trunks...
+      s_sub_u32 s_save_alloc_size, 128, s_save_alloc_size   // store from higheset addr to lowest
+      s_mul_i32 s_save_alloc_size, s_save_alloc_size, 6*4   // PC offset increment,  each LDS save block cost 6*4 Bytes instruction
+      s_add_u32 s_save_alloc_size, s_save_alloc_size, 3*4   //2is the below 2 inst...//s_addc and s_setpc
+      s_nop 0
+      s_nop 0
+      s_nop 0   //pad 3 dw to let LDS_DMA align with 64Bytes
+      s_getpc_b64 s[0:1]                              // reuse s[0:1], since s[0:1] already saved
+      s_add_u32   s0, s0,s_save_alloc_size
+      s_addc_u32  s1, s1, 0
+      s_setpc_b64 s[0:1]
+
+
+       for var i =0; i< 128; i++
+            // be careful to make here a 64Byte aligned address, which could improve performance...
+            buffer_store_lds_dword s_save_buf_rsrc0, s_save_mem_offset lds:1 offset:0           // first 64DW
+            buffer_store_lds_dword s_save_buf_rsrc0, s_save_mem_offset lds:1 offset:256           // second 64DW
+
+        if i!=127
+        s_sub_u32  m0, m0, s3      // use a sgpr to shrink 2DW-inst to 1DW inst to improve performance , i.e.  pack more LDS_DMA inst to one Cacheline
+            s_sub_u32  s_save_mem_offset, s_save_mem_offset,  s3
+            end
+       end
+
+else   // BUFFER_STORE
+      v_mbcnt_lo_u32_b32 v2, 0xffffffff, 0x0
+      v_mbcnt_hi_u32_b32 v3, 0xffffffff, v2     // tid
+      v_mul_i32_i24 v2, v3, 8   // tid*8
+      v_mov_b32 v3, 256*2
+      s_mov_b32 m0, 0x10000
+      s_mov_b32 s0, s_save_buf_rsrc3
+      s_and_b32 s_save_buf_rsrc3, s_save_buf_rsrc3, 0xFF7FFFFF    // disable add_tid
+      s_or_b32 s_save_buf_rsrc3, s_save_buf_rsrc3, 0x58000   //DFMT
+
+L_SAVE_LDS_LOOP_VECTOR:
+      ds_read_b64 v[0:1], v2    //x =LDS[a], byte address
+      s_waitcnt lgkmcnt(0)
+      buffer_store_dwordx2  v[0:1], v2, s_save_buf_rsrc0, s_save_mem_offset offen:1  glc:1  slc:1
+//      s_waitcnt vmcnt(0)
+      v_add_u32 v2, vcc[0:1], v2, v3
+      v_cmp_lt_u32 vcc[0:1], v2, s_save_alloc_size
+      s_cbranch_vccnz L_SAVE_LDS_LOOP_VECTOR
+
+      // restore rsrc3
+      s_mov_b32 s_save_buf_rsrc3, s0
+
+end
+
+L_SAVE_LDS_DONE:
+
+
+    /*          save VGPRs  - set the Rest VGPRs        */
+    //////////////////////////////////////////////////////////////////////////////////////
+  L_SAVE_VGPR:
+    // VGPR SR memory offset: 0
+    // TODO rearrange the RSRC words to use swizzle for VGPR save...
+
+    s_mov_b32       s_save_mem_offset, (0+256*4)                                    // for the rest VGPRs
+    s_mov_b32       exec_lo, 0xFFFFFFFF                                             //need every thread from now on
+    s_mov_b32       exec_hi, 0xFFFFFFFF
+
+    s_getreg_b32    s_save_alloc_size, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE)                   //vpgr_size
+    s_add_u32       s_save_alloc_size, s_save_alloc_size, 1
+    s_lshl_b32      s_save_alloc_size, s_save_alloc_size, 2                         //Number of VGPRs = (vgpr_size + 1) * 4    (non-zero value)   //FIXME for GFX, zero is possible
+    s_lshl_b32      s_save_buf_rsrc2,  s_save_alloc_size, 8                         //NUM_RECORDS in bytes (64 threads*4)
+    if (SWIZZLE_EN)
+        s_add_u32       s_save_buf_rsrc2, s_save_buf_rsrc2, 0x0                     //FIXME need to use swizzle to enable bounds checking?
+    else
+        s_mov_b32       s_save_buf_rsrc2,  0x1000000                                //NUM_RECORDS in bytes
+    end
+
+
+    // VGPR Allocated in 4-GPR granularity
+
+if G8SR_VGPR_SR_IN_DWX4
+        // the const stride for DWx4 is 4*4 bytes
+        s_and_b32 s_save_buf_rsrc1, s_save_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+        s_or_b32  s_save_buf_rsrc1, s_save_buf_rsrc1, G8SR_SAVE_BUF_RSRC_WORD1_STRIDE_DWx4  // const stride to 4*4 bytes
+
+        s_mov_b32         m0, 4     // skip first 4 VGPRs
+        s_cmp_lt_u32      m0, s_save_alloc_size
+        s_cbranch_scc0    L_SAVE_VGPR_LOOP_END      // no more vgprs
+
+        s_set_gpr_idx_on  m0, 0x1   // This will change M0
+        s_add_u32         s_save_alloc_size, s_save_alloc_size, 0x1000  // because above inst change m0
+L_SAVE_VGPR_LOOP:
+        v_mov_b32         v0, v0   // v0 = v[0+m0]
+        v_mov_b32         v1, v1
+        v_mov_b32         v2, v2
+        v_mov_b32         v3, v3
+
+
+        buffer_store_dwordx4 v0, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1
+        s_add_u32         m0, m0, 4
+        s_add_u32         s_save_mem_offset, s_save_mem_offset, 256*4
+        s_cmp_lt_u32      m0, s_save_alloc_size
+    s_cbranch_scc1  L_SAVE_VGPR_LOOP                                                //VGPR save is complete?
+    s_set_gpr_idx_off
+L_SAVE_VGPR_LOOP_END:
+
+        s_and_b32 s_save_buf_rsrc1, s_save_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+        s_or_b32  s_save_buf_rsrc1, s_save_buf_rsrc1, S_SAVE_BUF_RSRC_WORD1_STRIDE  // reset const stride to 4 bytes
+else
+    // VGPR store using dw burst
+    s_mov_b32         m0, 0x4   //VGPR initial index value =0
+    s_cmp_lt_u32      m0, s_save_alloc_size
+    s_cbranch_scc0    L_SAVE_VGPR_END
+
+
+    s_set_gpr_idx_on    m0, 0x1 //M0[7:0] = M0[7:0] and M0[15:12] = 0x1
+    s_add_u32       s_save_alloc_size, s_save_alloc_size, 0x1000                    //add 0x1000 since we compare m0 against it later
+
+  L_SAVE_VGPR_LOOP:
+    v_mov_b32       v0, v0              //v0 = v[0+m0]
+    v_mov_b32       v1, v1              //v0 = v[0+m0]
+    v_mov_b32       v2, v2              //v0 = v[0+m0]
+    v_mov_b32       v3, v3              //v0 = v[0+m0]
+
+    if(USE_MTBUF_INSTEAD_OF_MUBUF)
+        tbuffer_store_format_x v0, v0, s_save_buf_rsrc0, s_save_mem_offset format:BUF_NUM_FORMAT_FLOAT format: BUF_DATA_FORMAT_32 slc:1 glc:1
+    else
+        buffer_store_dword v0, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1
+        buffer_store_dword v1, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256
+        buffer_store_dword v2, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256*2
+        buffer_store_dword v3, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256*3
+    end
+
+    s_add_u32       m0, m0, 4                                                       //next vgpr index
+    s_add_u32       s_save_mem_offset, s_save_mem_offset, 256*4                     //every buffer_store_dword does 256 bytes
+    s_cmp_lt_u32    m0, s_save_alloc_size                                           //scc = (m0 < s_save_alloc_size) ? 1 : 0
+    s_cbranch_scc1  L_SAVE_VGPR_LOOP                                                //VGPR save is complete?
+    s_set_gpr_idx_off
+end
+
+L_SAVE_VGPR_END:
+
+
+
+
+
+
+    /*     S_PGM_END_SAVED  */                              //FIXME  graphics ONLY
+    if ((EMU_RUN_HACK) && (!EMU_RUN_HACK_SAVE_NORMAL_EXIT))
+        s_and_b32 s_save_pc_hi, s_save_pc_hi, 0x0000ffff    //pc[47:32]
+        s_add_u32 s_save_pc_lo, s_save_pc_lo, 4             //pc[31:0]+4
+        s_addc_u32 s_save_pc_hi, s_save_pc_hi, 0x0          //carry bit over
+        s_rfe_b64 s_save_pc_lo                              //Return to the main shader program
+    else
+    end
+
+// Save Done timestamp
+if G8SR_DEBUG_TIMESTAMP
+        s_memrealtime   s_g8sr_ts_save_d
+        // SGPR SR memory offset : size(VGPR)
+        get_vgpr_size_bytes(s_save_mem_offset)
+        s_add_u32 s_save_mem_offset, s_save_mem_offset, G8SR_DEBUG_TS_SAVE_D_OFFSET
+        s_waitcnt lgkmcnt(0)         //FIXME, will cause xnack??
+        // Need reset rsrc2??
+        s_mov_b32 m0, s_save_mem_offset
+        s_mov_b32 s_save_buf_rsrc2,  0x1000000                                  //NUM_RECORDS in bytes
+        s_buffer_store_dwordx2 s_g8sr_ts_save_d, s_save_buf_rsrc0, m0       glc:1
+end
+
+
+    s_branch    L_END_PGM
+
+
+
+/**************************************************************************/
+/*                      restore routine                                   */
+/**************************************************************************/
+
+L_RESTORE:
+    /*      Setup Resource Contants    */
+    if ((EMU_RUN_HACK) && (!EMU_RUN_HACK_RESTORE_NORMAL))
+        //calculate wd_addr using absolute thread id
+        v_readlane_b32 s_restore_tmp, v9, 0
+        s_lshr_b32 s_restore_tmp, s_restore_tmp, 6
+        s_mul_i32 s_restore_tmp, s_restore_tmp, WAVE_SPACE
+        s_add_i32 s_restore_spi_init_lo, s_restore_tmp, WG_BASE_ADDR_LO
+        s_mov_b32 s_restore_spi_init_hi, WG_BASE_ADDR_HI
+        s_and_b32 s_restore_spi_init_hi, s_restore_spi_init_hi, CTX_RESTORE_CONTROL
+    else
+    end
+
+if G8SR_DEBUG_TIMESTAMP
+        s_memrealtime   s_g8sr_ts_restore_s
+        s_waitcnt lgkmcnt(0)         //FIXME, will cause xnack??
+        // tma_lo/hi are sgpr 110, 111, which will not used for 112 SGPR allocated case...
+        s_mov_b32 s_restore_pc_lo, s_g8sr_ts_restore_s[0]
+        s_mov_b32 s_restore_pc_hi, s_g8sr_ts_restore_s[1]   //backup ts to ttmp0/1, sicne exec will be finally restored..
+end
+
+
+
+    s_mov_b32       s_restore_buf_rsrc0,    s_restore_spi_init_lo                                                           //base_addr_lo
+    s_and_b32       s_restore_buf_rsrc1,    s_restore_spi_init_hi, 0x0000FFFF                                               //base_addr_hi
+    s_or_b32        s_restore_buf_rsrc1,    s_restore_buf_rsrc1,  S_RESTORE_BUF_RSRC_WORD1_STRIDE
+    s_mov_b32       s_restore_buf_rsrc2,    0                                                                               //NUM_RECORDS initial value = 0 (in bytes)
+    s_mov_b32       s_restore_buf_rsrc3,    S_RESTORE_BUF_RSRC_WORD3_MISC
+    s_and_b32       s_restore_tmp,          s_restore_spi_init_hi, S_RESTORE_SPI_INIT_ATC_MASK
+    s_lshr_b32      s_restore_tmp,          s_restore_tmp, (S_RESTORE_SPI_INIT_ATC_SHIFT-SQ_BUF_RSRC_WORD1_ATC_SHIFT)       //get ATC bit into position
+    s_or_b32        s_restore_buf_rsrc3,    s_restore_buf_rsrc3,  s_restore_tmp                                             //or ATC
+    s_and_b32       s_restore_tmp,          s_restore_spi_init_hi, S_RESTORE_SPI_INIT_MTYPE_MASK
+    s_lshr_b32      s_restore_tmp,          s_restore_tmp, (S_RESTORE_SPI_INIT_MTYPE_SHIFT-SQ_BUF_RSRC_WORD3_MTYPE_SHIFT)   //get MTYPE bits into position
+    s_or_b32        s_restore_buf_rsrc3,    s_restore_buf_rsrc3,  s_restore_tmp                                             //or MTYPE
+
+    /*      global mem offset           */
+//  s_mov_b32       s_restore_mem_offset, 0x0                               //mem offset initial value = 0
+
+    /*      the first wave in the threadgroup    */
+    s_and_b32       s_restore_tmp, s_restore_spi_init_hi, S_RESTORE_SPI_INIT_FIRST_WAVE_MASK
+    s_cbranch_scc0  L_RESTORE_VGPR
+
+    /*          restore LDS     */
+    //////////////////////////////
+  L_RESTORE_LDS:
+
+    s_mov_b32       exec_lo, 0xFFFFFFFF                                                     //need every thread from now on   //be consistent with SAVE although can be moved ahead
+    s_mov_b32       exec_hi, 0xFFFFFFFF
+
+    s_getreg_b32    s_restore_alloc_size, hwreg(HW_REG_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE)              //lds_size
+    s_and_b32       s_restore_alloc_size, s_restore_alloc_size, 0xFFFFFFFF                  //lds_size is zero?
+    s_cbranch_scc0  L_RESTORE_VGPR                                                          //no lds used? jump to L_RESTORE_VGPR
+    s_lshl_b32      s_restore_alloc_size, s_restore_alloc_size, 6                           //LDS size in dwords = lds_size * 64dw
+    s_lshl_b32      s_restore_alloc_size, s_restore_alloc_size, 2                           //LDS size in bytes
+    s_mov_b32       s_restore_buf_rsrc2,    s_restore_alloc_size                            //NUM_RECORDS in bytes
+
+    // LDS at offset: size(VGPR)+SIZE(SGPR)+SIZE(HWREG)
+    //
+    get_vgpr_size_bytes(s_restore_mem_offset)
+    get_sgpr_size_bytes(s_restore_tmp)
+    s_add_u32  s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp
+    s_add_u32  s_restore_mem_offset, s_restore_mem_offset, get_hwreg_size_bytes()            //FIXME, Check if offset overflow???
+
+
+    if (SWIZZLE_EN)
+        s_add_u32       s_restore_buf_rsrc2, s_restore_buf_rsrc2, 0x0                       //FIXME need to use swizzle to enable bounds checking?
+    else
+        s_mov_b32       s_restore_buf_rsrc2,  0x1000000                                     //NUM_RECORDS in bytes
+    end
+    s_mov_b32       m0, 0x0                                                                 //lds_offset initial value = 0
+
+  L_RESTORE_LDS_LOOP:
+    if (SAVE_LDS)
+        buffer_load_dword   v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset lds:1                    // first 64DW
+        buffer_load_dword   v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset lds:1 offset:256         // second 64DW
+    end
+    s_add_u32       m0, m0, 256*2                                               // 128 DW
+    s_add_u32       s_restore_mem_offset, s_restore_mem_offset, 256*2           //mem offset increased by 128DW
+    s_cmp_lt_u32    m0, s_restore_alloc_size                                    //scc=(m0 < s_restore_alloc_size) ? 1 : 0
+    s_cbranch_scc1  L_RESTORE_LDS_LOOP                                                      //LDS restore is complete?
+
+
+    /*          restore VGPRs       */
+    //////////////////////////////
+  L_RESTORE_VGPR:
+        // VGPR SR memory offset : 0
+    s_mov_b32       s_restore_mem_offset, 0x0
+    s_mov_b32       exec_lo, 0xFFFFFFFF                                                     //need every thread from now on   //be consistent with SAVE although can be moved ahead
+    s_mov_b32       exec_hi, 0xFFFFFFFF
+
+    s_getreg_b32    s_restore_alloc_size, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE)    //vpgr_size
+    s_add_u32       s_restore_alloc_size, s_restore_alloc_size, 1
+    s_lshl_b32      s_restore_alloc_size, s_restore_alloc_size, 2                           //Number of VGPRs = (vgpr_size + 1) * 4    (non-zero value)
+    s_lshl_b32      s_restore_buf_rsrc2,  s_restore_alloc_size, 8                           //NUM_RECORDS in bytes (64 threads*4)
+    if (SWIZZLE_EN)
+        s_add_u32       s_restore_buf_rsrc2, s_restore_buf_rsrc2, 0x0                       //FIXME need to use swizzle to enable bounds checking?
+    else
+        s_mov_b32       s_restore_buf_rsrc2,  0x1000000                                     //NUM_RECORDS in bytes
+    end
+
+if G8SR_VGPR_SR_IN_DWX4
+     get_vgpr_size_bytes(s_restore_mem_offset)
+     s_sub_u32         s_restore_mem_offset, s_restore_mem_offset, 256*4
+
+     // the const stride for DWx4 is 4*4 bytes
+     s_and_b32 s_restore_buf_rsrc1, s_restore_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+     s_or_b32  s_restore_buf_rsrc1, s_restore_buf_rsrc1, G8SR_RESTORE_BUF_RSRC_WORD1_STRIDE_DWx4  // const stride to 4*4 bytes
+
+     s_mov_b32         m0, s_restore_alloc_size
+     s_set_gpr_idx_on  m0, 0x8    // Note.. This will change m0
+
+L_RESTORE_VGPR_LOOP:
+     buffer_load_dwordx4 v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset slc:1 glc:1
+     s_waitcnt vmcnt(0)
+     s_sub_u32         m0, m0, 4
+     v_mov_b32         v0, v0   // v[0+m0] = v0
+     v_mov_b32         v1, v1
+     v_mov_b32         v2, v2
+     v_mov_b32         v3, v3
+     s_sub_u32         s_restore_mem_offset, s_restore_mem_offset, 256*4
+     s_cmp_eq_u32      m0, 0x8000
+     s_cbranch_scc0    L_RESTORE_VGPR_LOOP
+     s_set_gpr_idx_off
+
+     s_and_b32 s_restore_buf_rsrc1, s_restore_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+     s_or_b32  s_restore_buf_rsrc1, s_restore_buf_rsrc1, S_RESTORE_BUF_RSRC_WORD1_STRIDE  // const stride to 4*4 bytes
+
+else
+    // VGPR load using dw burst
+    s_mov_b32       s_restore_mem_offset_save, s_restore_mem_offset     // restore start with v1, v0 will be the last
+    s_add_u32       s_restore_mem_offset, s_restore_mem_offset, 256*4
+    s_mov_b32       m0, 4                               //VGPR initial index value = 1
+    s_set_gpr_idx_on  m0, 0x8                       //M0[7:0] = M0[7:0] and M0[15:12] = 0x8
+    s_add_u32       s_restore_alloc_size, s_restore_alloc_size, 0x8000                      //add 0x8000 since we compare m0 against it later
+
+  L_RESTORE_VGPR_LOOP:
+    if(USE_MTBUF_INSTEAD_OF_MUBUF)
+        tbuffer_load_format_x v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset format:BUF_NUM_FORMAT_FLOAT format: BUF_DATA_FORMAT_32 slc:1 glc:1
+    else
+        buffer_load_dword v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset slc:1 glc:1
+        buffer_load_dword v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset slc:1 glc:1 offset:256
+        buffer_load_dword v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset slc:1 glc:1 offset:256*2
+        buffer_load_dword v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset slc:1 glc:1 offset:256*3
+    end
+    s_waitcnt       vmcnt(0)                                                                //ensure data ready
+    v_mov_b32       v0, v0                                                                  //v[0+m0] = v0
+    v_mov_b32       v1, v1
+    v_mov_b32       v2, v2
+    v_mov_b32       v3, v3
+    s_add_u32       m0, m0, 4                                                               //next vgpr index
+    s_add_u32       s_restore_mem_offset, s_restore_mem_offset, 256*4                           //every buffer_load_dword does 256 bytes
+    s_cmp_lt_u32    m0, s_restore_alloc_size                                                //scc = (m0 < s_restore_alloc_size) ? 1 : 0
+    s_cbranch_scc1  L_RESTORE_VGPR_LOOP                                                     //VGPR restore (except v0) is complete?
+    s_set_gpr_idx_off
+                                                                                            /* VGPR restore on v0 */
+    if(USE_MTBUF_INSTEAD_OF_MUBUF)
+        tbuffer_load_format_x v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save format:BUF_NUM_FORMAT_FLOAT format: BUF_DATA_FORMAT_32 slc:1 glc:1
+    else
+        buffer_load_dword v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save    slc:1 glc:1
+        buffer_load_dword v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save    slc:1 glc:1 offset:256
+        buffer_load_dword v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save    slc:1 glc:1 offset:256*2
+        buffer_load_dword v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save    slc:1 glc:1 offset:256*3
+    end
+
+end
+
+    /*          restore SGPRs       */
+    //////////////////////////////
+
+    // SGPR SR memory offset : size(VGPR)
+    get_vgpr_size_bytes(s_restore_mem_offset)
+    get_sgpr_size_bytes(s_restore_tmp)
+    s_add_u32 s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp
+    s_sub_u32 s_restore_mem_offset, s_restore_mem_offset, 16*4     // restore SGPR from S[n] to S[0], by 16 sgprs group
+    // TODO, change RSRC word to rearrange memory layout for SGPRS
+
+    s_getreg_b32    s_restore_alloc_size, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SIZE)                //spgr_size
+    s_add_u32       s_restore_alloc_size, s_restore_alloc_size, 1
+    s_lshl_b32      s_restore_alloc_size, s_restore_alloc_size, 4                           //Number of SGPRs = (sgpr_size + 1) * 16   (non-zero value)
+
+    if (SGPR_SAVE_USE_SQC)
+        s_lshl_b32      s_restore_buf_rsrc2,    s_restore_alloc_size, 2                     //NUM_RECORDS in bytes
+    else
+        s_lshl_b32      s_restore_buf_rsrc2,    s_restore_alloc_size, 8                     //NUM_RECORDS in bytes (64 threads)
+    end
+    if (SWIZZLE_EN)
+        s_add_u32       s_restore_buf_rsrc2, s_restore_buf_rsrc2, 0x0                       //FIXME need to use swizzle to enable bounds checking?
+    else
+        s_mov_b32       s_restore_buf_rsrc2,  0x1000000                                     //NUM_RECORDS in bytes
+    end
+
+    /* If 112 SGPRs ar allocated, 4 sgprs are not used TBA(108,109),TMA(110,111),
+       However, we are safe to restore these 4 SGPRs anyway, since TBA,TMA will later be restored by HWREG
+    */
+    s_mov_b32 m0, s_restore_alloc_size
+
+ L_RESTORE_SGPR_LOOP:
+    read_16sgpr_from_mem(s0, s_restore_buf_rsrc0, s_restore_mem_offset)  //PV: further performance improvement can be made
+    s_waitcnt       lgkmcnt(0)                                                              //ensure data ready
+
+    s_sub_u32 m0, m0, 16    // Restore from S[n] to S[0]
+
+    s_movreld_b64   s0, s0      //s[0+m0] = s0
+    s_movreld_b64   s2, s2
+    s_movreld_b64   s4, s4
+    s_movreld_b64   s6, s6
+    s_movreld_b64   s8, s8
+    s_movreld_b64   s10, s10
+    s_movreld_b64   s12, s12
+    s_movreld_b64   s14, s14
+
+    s_cmp_eq_u32    m0, 0               //scc = (m0 < s_restore_alloc_size) ? 1 : 0
+    s_cbranch_scc0  L_RESTORE_SGPR_LOOP             //SGPR restore (except s0) is complete?
+
+    /*      restore HW registers    */
+    //////////////////////////////
+  L_RESTORE_HWREG:
+
+
+if G8SR_DEBUG_TIMESTAMP
+      s_mov_b32 s_g8sr_ts_restore_s[0], s_restore_pc_lo
+      s_mov_b32 s_g8sr_ts_restore_s[1], s_restore_pc_hi
+end
+
+    // HWREG SR memory offset : size(VGPR)+size(SGPR)
+    get_vgpr_size_bytes(s_restore_mem_offset)
+    get_sgpr_size_bytes(s_restore_tmp)
+    s_add_u32 s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp
+
+
+    s_mov_b32       s_restore_buf_rsrc2, 0x4                                                //NUM_RECORDS   in bytes
+    if (SWIZZLE_EN)
+        s_add_u32       s_restore_buf_rsrc2, s_restore_buf_rsrc2, 0x0                       //FIXME need to use swizzle to enable bounds checking?
+    else
+        s_mov_b32       s_restore_buf_rsrc2,  0x1000000                                     //NUM_RECORDS in bytes
+    end
+
+    read_hwreg_from_mem(s_restore_m0, s_restore_buf_rsrc0, s_restore_mem_offset)                    //M0
+    read_hwreg_from_mem(s_restore_pc_lo, s_restore_buf_rsrc0, s_restore_mem_offset)             //PC
+    read_hwreg_from_mem(s_restore_pc_hi, s_restore_buf_rsrc0, s_restore_mem_offset)
+    read_hwreg_from_mem(s_restore_exec_lo, s_restore_buf_rsrc0, s_restore_mem_offset)               //EXEC
+    read_hwreg_from_mem(s_restore_exec_hi, s_restore_buf_rsrc0, s_restore_mem_offset)
+    read_hwreg_from_mem(s_restore_status, s_restore_buf_rsrc0, s_restore_mem_offset)                //STATUS
+    read_hwreg_from_mem(s_restore_trapsts, s_restore_buf_rsrc0, s_restore_mem_offset)               //TRAPSTS
+    read_hwreg_from_mem(xnack_mask_lo, s_restore_buf_rsrc0, s_restore_mem_offset)                   //XNACK_MASK_LO
+    read_hwreg_from_mem(xnack_mask_hi, s_restore_buf_rsrc0, s_restore_mem_offset)                   //XNACK_MASK_HI
+    read_hwreg_from_mem(s_restore_mode, s_restore_buf_rsrc0, s_restore_mem_offset)              //MODE
+    read_hwreg_from_mem(tba_lo, s_restore_buf_rsrc0, s_restore_mem_offset)                      //TBA_LO
+    read_hwreg_from_mem(tba_hi, s_restore_buf_rsrc0, s_restore_mem_offset)                      //TBA_HI
+
+    s_waitcnt       lgkmcnt(0)                                                                                      //from now on, it is safe to restore STATUS and IB_STS
+
+    s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff      //pc[47:32]        //Do it here in order not to affect STATUS
+
+    //for normal save & restore, the saved PC points to the next inst to execute, no adjustment needs to be made, otherwise:
+    if ((EMU_RUN_HACK) && (!EMU_RUN_HACK_RESTORE_NORMAL))
+        s_add_u32 s_restore_pc_lo, s_restore_pc_lo, 8            //pc[31:0]+8     //two back-to-back s_trap are used (first for save and second for restore)
+        s_addc_u32  s_restore_pc_hi, s_restore_pc_hi, 0x0        //carry bit over
+    end
+    if ((EMU_RUN_HACK) && (EMU_RUN_HACK_RESTORE_NORMAL))
+        s_add_u32 s_restore_pc_lo, s_restore_pc_lo, 4            //pc[31:0]+4     // save is hack through s_trap but restore is normal
+        s_addc_u32  s_restore_pc_hi, s_restore_pc_hi, 0x0        //carry bit over
+    end
+
+    s_mov_b32       m0,         s_restore_m0
+    s_mov_b32       exec_lo,    s_restore_exec_lo
+    s_mov_b32       exec_hi,    s_restore_exec_hi
+
+    s_and_b32       s_restore_m0, SQ_WAVE_TRAPSTS_PRE_SAVECTX_MASK, s_restore_trapsts
+    s_setreg_b32    hwreg(HW_REG_TRAPSTS, SQ_WAVE_TRAPSTS_PRE_SAVECTX_SHIFT, SQ_WAVE_TRAPSTS_PRE_SAVECTX_SIZE), s_restore_m0
+    s_and_b32       s_restore_m0, SQ_WAVE_TRAPSTS_POST_SAVECTX_MASK, s_restore_trapsts
+    s_lshr_b32      s_restore_m0, s_restore_m0, SQ_WAVE_TRAPSTS_POST_SAVECTX_SHIFT
+    s_setreg_b32    hwreg(HW_REG_TRAPSTS, SQ_WAVE_TRAPSTS_POST_SAVECTX_SHIFT, SQ_WAVE_TRAPSTS_POST_SAVECTX_SIZE), s_restore_m0
+    //s_setreg_b32  hwreg(HW_REG_TRAPSTS),  s_restore_trapsts      //don't overwrite SAVECTX bit as it may be set through external SAVECTX during restore
+    s_setreg_b32    hwreg(HW_REG_MODE),     s_restore_mode
+    //reuse s_restore_m0 as a temp register
+    s_and_b32       s_restore_m0, s_restore_pc_hi, S_SAVE_PC_HI_RCNT_MASK
+    s_lshr_b32      s_restore_m0, s_restore_m0, S_SAVE_PC_HI_RCNT_SHIFT
+    s_lshl_b32      s_restore_m0, s_restore_m0, SQ_WAVE_IB_STS_RCNT_SHIFT
+    s_mov_b32       s_restore_tmp, 0x0                                                                              //IB_STS is zero
+    s_or_b32        s_restore_tmp, s_restore_tmp, s_restore_m0
+    s_and_b32       s_restore_m0, s_restore_pc_hi, S_SAVE_PC_HI_FIRST_REPLAY_MASK
+    s_lshr_b32      s_restore_m0, s_restore_m0, S_SAVE_PC_HI_FIRST_REPLAY_SHIFT
+    s_lshl_b32      s_restore_m0, s_restore_m0, SQ_WAVE_IB_STS_FIRST_REPLAY_SHIFT
+    s_or_b32        s_restore_tmp, s_restore_tmp, s_restore_m0
+    s_and_b32       s_restore_m0, s_restore_status, SQ_WAVE_STATUS_INST_ATC_MASK
+    s_lshr_b32      s_restore_m0, s_restore_m0, SQ_WAVE_STATUS_INST_ATC_SHIFT
+    s_setreg_b32    hwreg(HW_REG_IB_STS),   s_restore_tmp
+
+    s_and_b64    exec, exec, exec  // Restore STATUS.EXECZ, not writable by s_setreg_b32
+    s_and_b64    vcc, vcc, vcc  // Restore STATUS.VCCZ, not writable by s_setreg_b32
+    s_setreg_b32    hwreg(HW_REG_STATUS),   s_restore_status     // SCC is included, which is changed by previous salu
+
+    s_barrier                                                   //barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time
+
+if G8SR_DEBUG_TIMESTAMP
+    s_memrealtime s_g8sr_ts_restore_d
+    s_waitcnt lgkmcnt(0)
+end
+
+//  s_rfe_b64 s_restore_pc_lo                                   //Return to the main shader program and resume execution
+    s_rfe_restore_b64  s_restore_pc_lo, s_restore_m0            // s_restore_m0[0] is used to set STATUS.inst_atc
+
+
+/**************************************************************************/
+/*                      the END                                           */
+/**************************************************************************/
+L_END_PGM:
+    s_endpgm
+
+end
+
+
+/**************************************************************************/
+/*                      the helper functions                              */
+/**************************************************************************/
+
+//Only for save hwreg to mem
+function write_hwreg_to_mem(s, s_rsrc, s_mem_offset)
+        s_mov_b32 exec_lo, m0                   //assuming exec_lo is not needed anymore from this point on
+        s_mov_b32 m0, s_mem_offset
+        s_buffer_store_dword s, s_rsrc, m0      glc:1
+        s_add_u32       s_mem_offset, s_mem_offset, 4
+        s_mov_b32   m0, exec_lo
+end
+
+
+// HWREG are saved before SGPRs, so all HWREG could be use.
+function write_16sgpr_to_mem(s, s_rsrc, s_mem_offset)
+
+        s_buffer_store_dwordx4 s[0], s_rsrc, 0  glc:1
+        s_buffer_store_dwordx4 s[4], s_rsrc, 16  glc:1
+        s_buffer_store_dwordx4 s[8], s_rsrc, 32  glc:1
+        s_buffer_store_dwordx4 s[12], s_rsrc, 48 glc:1
+        s_add_u32       s_rsrc[0], s_rsrc[0], 4*16
+        s_addc_u32      s_rsrc[1], s_rsrc[1], 0x0             // +scc
+end
+
+
+function read_hwreg_from_mem(s, s_rsrc, s_mem_offset)
+    s_buffer_load_dword s, s_rsrc, s_mem_offset     glc:1
+    s_add_u32       s_mem_offset, s_mem_offset, 4
+end
+
+function read_16sgpr_from_mem(s, s_rsrc, s_mem_offset)
+    s_buffer_load_dwordx16 s, s_rsrc, s_mem_offset      glc:1
+    s_sub_u32       s_mem_offset, s_mem_offset, 4*16
+end
+
+
+
+function get_lds_size_bytes(s_lds_size_byte)
+    // SQ LDS granularity is 64DW, while PGM_RSRC2.lds_size is in granularity 128DW
+    s_getreg_b32   s_lds_size_byte, hwreg(HW_REG_LDS_ALLOC, SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT, SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE)          // lds_size
+    s_lshl_b32     s_lds_size_byte, s_lds_size_byte, 8                      //LDS size in dwords = lds_size * 64 *4Bytes    // granularity 64DW
+end
+
+function get_vgpr_size_bytes(s_vgpr_size_byte)
+    s_getreg_b32   s_vgpr_size_byte, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE)  //vpgr_size
+    s_add_u32      s_vgpr_size_byte, s_vgpr_size_byte, 1
+    s_lshl_b32     s_vgpr_size_byte, s_vgpr_size_byte, (2+8) //Number of VGPRs = (vgpr_size + 1) * 4 * 64 * 4   (non-zero value)   //FIXME for GFX, zero is possible
+end
+
+function get_sgpr_size_bytes(s_sgpr_size_byte)
+    s_getreg_b32   s_sgpr_size_byte, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SIZE)  //spgr_size
+    s_add_u32      s_sgpr_size_byte, s_sgpr_size_byte, 1
+    s_lshl_b32     s_sgpr_size_byte, s_sgpr_size_byte, 6 //Number of SGPRs = (sgpr_size + 1) * 16 *4   (non-zero value)
+end
+
+function get_hwreg_size_bytes
+    return 128 //HWREG size 128 bytes
+end
+
+
+#endif
+
+static const uint32_t cwsr_trap_gfx8_hex[] = {
+	0xbf820001, 0xbf820123,
+	0xb8f4f802, 0x89748674,
+	0xb8f5f803, 0x8675ff75,
+	0x00000400, 0xbf850011,
+	0xc00a1e37, 0x00000000,
+	0xbf8c007f, 0x87777978,
+	0xbf840002, 0xb974f802,
+	0xbe801d78, 0xb8f5f803,
+	0x8675ff75, 0x000001ff,
+	0xbf850002, 0x80708470,
+	0x82718071, 0x8671ff71,
+	0x0000ffff, 0xb974f802,
+	0xbe801f70, 0xb8f5f803,
+	0x8675ff75, 0x00000100,
+	0xbf840006, 0xbefa0080,
+	0xb97a0203, 0x8671ff71,
+	0x0000ffff, 0x80f08870,
+	0x82f18071, 0xbefa0080,
+	0xb97a0283, 0xbef60068,
+	0xbef70069, 0xb8fa1c07,
+	0x8e7a9c7a, 0x87717a71,
+	0xb8fa03c7, 0x8e7a9b7a,
+	0x87717a71, 0xb8faf807,
+	0x867aff7a, 0x00007fff,
+	0xb97af807, 0xbef2007e,
+	0xbef3007f, 0xbefe0180,
+	0xbf900004, 0xbf8e0002,
+	0xbf88fffe, 0xbef8007e,
+	0x8679ff7f, 0x0000ffff,
+	0x8779ff79, 0x00040000,
+	0xbefa0080, 0xbefb00ff,
+	0x00807fac, 0x867aff7f,
+	0x08000000, 0x8f7a837a,
+	0x877b7a7b, 0x867aff7f,
+	0x70000000, 0x8f7a817a,
+	0x877b7a7b, 0xbeef007c,
+	0xbeee0080, 0xb8ee2a05,
+	0x806e816e, 0x8e6e8a6e,
+	0xb8fa1605, 0x807a817a,
+	0x8e7a867a, 0x806e7a6e,
+	0xbefa0084, 0xbefa00ff,
+	0x01000000, 0xbefe007c,
+	0xbefc006e, 0xc0611bfc,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611c3c,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611c7c,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611cbc,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611cfc,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611d3c,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xb8f5f803,
+	0xbefe007c, 0xbefc006e,
+	0xc0611d7c, 0x0000007c,
+	0x806e846e, 0xbefc007e,
+	0xbefe007c, 0xbefc006e,
+	0xc0611dbc, 0x0000007c,
+	0x806e846e, 0xbefc007e,
+	0xbefe007c, 0xbefc006e,
+	0xc0611dfc, 0x0000007c,
+	0x806e846e, 0xbefc007e,
+	0xb8eff801, 0xbefe007c,
+	0xbefc006e, 0xc0611bfc,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611b3c,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611b7c,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0x867aff7f,
+	0x04000000, 0xbef30080,
+	0x8773737a, 0xb8ee2a05,
+	0x806e816e, 0x8e6e8a6e,
+	0xb8f51605, 0x80758175,
+	0x8e758475, 0x8e7a8275,
+	0xbefa00ff, 0x01000000,
+	0xbef60178, 0x80786e78,
+	0x82798079, 0xbefc0080,
+	0xbe802b00, 0xbe822b02,
+	0xbe842b04, 0xbe862b06,
+	0xbe882b08, 0xbe8a2b0a,
+	0xbe8c2b0c, 0xbe8e2b0e,
+	0xc06b003c, 0x00000000,
+	0xc06b013c, 0x00000010,
+	0xc06b023c, 0x00000020,
+	0xc06b033c, 0x00000030,
+	0x8078c078, 0x82798079,
+	0x807c907c, 0xbf0a757c,
+	0xbf85ffeb, 0xbef80176,
+	0xbeee0080, 0xbefe00c1,
+	0xbeff00c1, 0xbefa00ff,
+	0x01000000, 0xe0724000,
+	0x6e1e0000, 0xe0724100,
+	0x6e1e0100, 0xe0724200,
+	0x6e1e0200, 0xe0724300,
+	0x6e1e0300, 0xbefe00c1,
+	0xbeff00c1, 0xb8f54306,
+	0x8675c175, 0xbf84002c,
+	0xbf8a0000, 0x867aff73,
+	0x04000000, 0xbf840028,
+	0x8e758675, 0x8e758275,
+	0xbefa0075, 0xb8ee2a05,
+	0x806e816e, 0x8e6e8a6e,
+	0xb8fa1605, 0x807a817a,
+	0x8e7a867a, 0x806e7a6e,
+	0x806eff6e, 0x00000080,
+	0xbefa00ff, 0x01000000,
+	0xbefc0080, 0xd28c0002,
+	0x000100c1, 0xd28d0003,
+	0x000204c1, 0xd1060002,
+	0x00011103, 0x7e0602ff,
+	0x00000200, 0xbefc00ff,
+	0x00010000, 0xbe80007b,
+	0x867bff7b, 0xff7fffff,
+	0x877bff7b, 0x00058000,
+	0xd8ec0000, 0x00000002,
+	0xbf8c007f, 0xe0765000,
+	0x6e1e0002, 0x32040702,
+	0xd0c9006a, 0x0000eb02,
+	0xbf87fff7, 0xbefb0000,
+	0xbeee00ff, 0x00000400,
+	0xbefe00c1, 0xbeff00c1,
+	0xb8f52a05, 0x80758175,
+	0x8e758275, 0x8e7a8875,
+	0xbefa00ff, 0x01000000,
+	0xbefc0084, 0xbf0a757c,
+	0xbf840015, 0xbf11017c,
+	0x8075ff75, 0x00001000,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
+	0xe0724000, 0x6e1e0000,
+	0xe0724100, 0x6e1e0100,
+	0xe0724200, 0x6e1e0200,
+	0xe0724300, 0x6e1e0300,
+	0x807c847c, 0x806eff6e,
+	0x00000400, 0xbf0a757c,
+	0xbf85ffef, 0xbf9c0000,
+	0xbf8200ca, 0xbef8007e,
+	0x8679ff7f, 0x0000ffff,
+	0x8779ff79, 0x00040000,
+	0xbefa0080, 0xbefb00ff,
+	0x00807fac, 0x8676ff7f,
+	0x08000000, 0x8f768376,
+	0x877b767b, 0x8676ff7f,
+	0x70000000, 0x8f768176,
+	0x877b767b, 0x8676ff7f,
+	0x04000000, 0xbf84001e,
+	0xbefe00c1, 0xbeff00c1,
+	0xb8f34306, 0x8673c173,
+	0xbf840019, 0x8e738673,
+	0x8e738273, 0xbefa0073,
+	0xb8f22a05, 0x80728172,
+	0x8e728a72, 0xb8f61605,
+	0x80768176, 0x8e768676,
+	0x80727672, 0x8072ff72,
+	0x00000080, 0xbefa00ff,
+	0x01000000, 0xbefc0080,
+	0xe0510000, 0x721e0000,
+	0xe0510100, 0x721e0000,
+	0x807cff7c, 0x00000200,
+	0x8072ff72, 0x00000200,
+	0xbf0a737c, 0xbf85fff6,
+	0xbef20080, 0xbefe00c1,
+	0xbeff00c1, 0xb8f32a05,
+	0x80738173, 0x8e738273,
+	0x8e7a8873, 0xbefa00ff,
+	0x01000000, 0xbef60072,
+	0x8072ff72, 0x00000400,
+	0xbefc0084, 0xbf11087c,
+	0x8073ff73, 0x00008000,
+	0xe0524000, 0x721e0000,
+	0xe0524100, 0x721e0100,
+	0xe0524200, 0x721e0200,
+	0xe0524300, 0x721e0300,
+	0xbf8c0f70, 0x7e000300,
+	0x7e020301, 0x7e040302,
+	0x7e060303, 0x807c847c,
+	0x8072ff72, 0x00000400,
+	0xbf0a737c, 0xbf85ffee,
+	0xbf9c0000, 0xe0524000,
+	0x761e0000, 0xe0524100,
+	0x761e0100, 0xe0524200,
+	0x761e0200, 0xe0524300,
+	0x761e0300, 0xb8f22a05,
+	0x80728172, 0x8e728a72,
+	0xb8f61605, 0x80768176,
+	0x8e768676, 0x80727672,
+	0x80f2c072, 0xb8f31605,
+	0x80738173, 0x8e738473,
+	0x8e7a8273, 0xbefa00ff,
+	0x01000000, 0xbefc0073,
+	0xc031003c, 0x00000072,
+	0x80f2c072, 0xbf8c007f,
+	0x80fc907c, 0xbe802d00,
+	0xbe822d02, 0xbe842d04,
+	0xbe862d06, 0xbe882d08,
+	0xbe8a2d0a, 0xbe8c2d0c,
+	0xbe8e2d0e, 0xbf06807c,
+	0xbf84fff1, 0xb8f22a05,
+	0x80728172, 0x8e728a72,
+	0xb8f61605, 0x80768176,
+	0x8e768676, 0x80727672,
+	0xbefa0084, 0xbefa00ff,
+	0x01000000, 0xc0211cfc,
+	0x00000072, 0x80728472,
+	0xc0211c3c, 0x00000072,
+	0x80728472, 0xc0211c7c,
+	0x00000072, 0x80728472,
+	0xc0211bbc, 0x00000072,
+	0x80728472, 0xc0211bfc,
+	0x00000072, 0x80728472,
+	0xc0211d3c, 0x00000072,
+	0x80728472, 0xc0211d7c,
+	0x00000072, 0x80728472,
+	0xc0211a3c, 0x00000072,
+	0x80728472, 0xc0211a7c,
+	0x00000072, 0x80728472,
+	0xc0211dfc, 0x00000072,
+	0x80728472, 0xc0211b3c,
+	0x00000072, 0x80728472,
+	0xc0211b7c, 0x00000072,
+	0x80728472, 0xbf8c007f,
+	0x8671ff71, 0x0000ffff,
+	0xbefc0073, 0xbefe006e,
+	0xbeff006f, 0x867375ff,
+	0x000003ff, 0xb9734803,
+	0x867375ff, 0xfffff800,
+	0x8f738b73, 0xb973a2c3,
+	0xb977f801, 0x8673ff71,
+	0xf0000000, 0x8f739c73,
+	0x8e739073, 0xbef60080,
+	0x87767376, 0x8673ff71,
+	0x08000000, 0x8f739b73,
+	0x8e738f73, 0x87767376,
+	0x8673ff74, 0x00800000,
+	0x8f739773, 0xb976f807,
+	0x86fe7e7e, 0x86ea6a6a,
+	0xb974f802, 0xbf8a0000,
+	0x95807370, 0xbf810000,
+};
+
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 505d39156acd..62c3d9cd6ef1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -117,7 +117,7 @@ static int kfd_open(struct inode *inode, struct file *filep)
 		return -EPERM;
 	}
 
-	process = kfd_create_process(current);
+	process = kfd_create_process(filep);
 	if (IS_ERR(process))
 		return PTR_ERR(process);
 
@@ -206,6 +206,7 @@ static int set_queue_properties_from_user(struct queue_properties *q_properties,
 	q_properties->ctx_save_restore_area_address =
 			args->ctx_save_restore_address;
 	q_properties->ctx_save_restore_area_size = args->ctx_save_restore_size;
+	q_properties->ctl_stack_size = args->ctl_stack_size;
 	if (args->queue_type == KFD_IOC_QUEUE_TYPE_COMPUTE ||
 		args->queue_type == KFD_IOC_QUEUE_TYPE_COMPUTE_AQL)
 		q_properties->type = KFD_QUEUE_TYPE_COMPUTE;
@@ -431,6 +432,38 @@ out:
 	return err;
 }
 
+static int kfd_ioctl_set_trap_handler(struct file *filep,
+					struct kfd_process *p, void *data)
+{
+	struct kfd_ioctl_set_trap_handler_args *args = data;
+	struct kfd_dev *dev;
+	int err = 0;
+	struct kfd_process_device *pdd;
+
+	dev = kfd_device_by_id(args->gpu_id);
+	if (dev == NULL)
+		return -EINVAL;
+
+	mutex_lock(&p->mutex);
+
+	pdd = kfd_bind_process_to_device(dev, p);
+	if (IS_ERR(pdd)) {
+		err = -ESRCH;
+		goto out;
+	}
+
+	if (dev->dqm->ops.set_trap_handler(dev->dqm,
+					&pdd->qpd,
+					args->tba_addr,
+					args->tma_addr))
+		err = -EINVAL;
+
+out:
+	mutex_unlock(&p->mutex);
+
+	return err;
+}
+
 static int kfd_ioctl_dbg_register(struct file *filep,
 				struct kfd_process *p, void *data)
 {
@@ -493,7 +526,7 @@ static int kfd_ioctl_dbg_unregister(struct file *filep,
 	long status;
 
 	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
+	if (!dev || !dev->dbgmgr)
 		return -EINVAL;
 
 	if (dev->device_info->asic_family == CHIP_CARRIZO) {
@@ -979,7 +1012,10 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
 			kfd_ioctl_set_scratch_backing_va, 0),
 
 	AMDKFD_IOCTL_DEF(AMDKFD_IOC_GET_TILE_CONFIG,
-			kfd_ioctl_get_tile_config, 0)
+			kfd_ioctl_get_tile_config, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_TRAP_HANDLER,
+			kfd_ioctl_set_trap_handler, 0),
 };
 
 #define AMDKFD_CORE_IOCTL_COUNT	ARRAY_SIZE(amdkfd_ioctls)
@@ -1088,6 +1124,10 @@ static int kfd_mmap(struct file *filp, struct vm_area_struct *vma)
 			KFD_MMAP_EVENTS_MASK) {
 		vma->vm_pgoff = vma->vm_pgoff ^ KFD_MMAP_EVENTS_MASK;
 		return kfd_event_mmap(process, vma);
+	} else if ((vma->vm_pgoff & KFD_MMAP_RESERVED_MEM_MASK) ==
+			KFD_MMAP_RESERVED_MEM_MASK) {
+		vma->vm_pgoff = vma->vm_pgoff ^ KFD_MMAP_RESERVED_MEM_MASK;
+		return kfd_reserved_mem_mmap(process, vma);
 	}
 
 	return -EFAULT;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
new file mode 100644
index 000000000000..2bc2816767a7
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -0,0 +1,1267 @@
+/*
+ * Copyright 2015-2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <linux/pci.h>
+#include <linux/acpi.h>
+#include <linux/amd-iommu.h>
+#include "kfd_crat.h"
+#include "kfd_priv.h"
+#include "kfd_topology.h"
+
+/* GPU Processor ID base for dGPUs for which VCRAT needs to be created.
+ * GPU processor ID are expressed with Bit[31]=1.
+ * The base is set to 0x8000_0000 + 0x1000 to avoid collision with GPU IDs
+ * used in the CRAT.
+ */
+static uint32_t gpu_processor_id_low = 0x80001000;
+
+/* Return the next available gpu_processor_id and increment it for next GPU
+ *	@total_cu_count - Total CUs present in the GPU including ones
+ *			  masked off
+ */
+static inline unsigned int get_and_inc_gpu_processor_id(
+				unsigned int total_cu_count)
+{
+	int current_id = gpu_processor_id_low;
+
+	gpu_processor_id_low += total_cu_count;
+	return current_id;
+}
+
+/* Static table to describe GPU Cache information */
+struct kfd_gpu_cache_info {
+	uint32_t	cache_size;
+	uint32_t	cache_level;
+	uint32_t	flags;
+	/* Indicates how many Compute Units share this cache
+	 * Value = 1 indicates the cache is not shared
+	 */
+	uint32_t	num_cu_shared;
+};
+
+static struct kfd_gpu_cache_info kaveri_cache_info[] = {
+	{
+		/* TCP L1 Cache per CU */
+		.cache_size = 16,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+				CRAT_CACHE_FLAGS_DATA_CACHE |
+				CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 1,
+
+	},
+	{
+		/* Scalar L1 Instruction Cache (in SQC module) per bank */
+		.cache_size = 16,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+				CRAT_CACHE_FLAGS_INST_CACHE |
+				CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 2,
+	},
+	{
+		/* Scalar L1 Data Cache (in SQC module) per bank */
+		.cache_size = 8,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+				CRAT_CACHE_FLAGS_DATA_CACHE |
+				CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 2,
+	},
+
+	/* TODO: Add L2 Cache information */
+};
+
+
+static struct kfd_gpu_cache_info carrizo_cache_info[] = {
+	{
+		/* TCP L1 Cache per CU */
+		.cache_size = 16,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+				CRAT_CACHE_FLAGS_DATA_CACHE |
+				CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 1,
+	},
+	{
+		/* Scalar L1 Instruction Cache (in SQC module) per bank */
+		.cache_size = 8,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+				CRAT_CACHE_FLAGS_INST_CACHE |
+				CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 4,
+	},
+	{
+		/* Scalar L1 Data Cache (in SQC module) per bank. */
+		.cache_size = 4,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+				CRAT_CACHE_FLAGS_DATA_CACHE |
+				CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 4,
+	},
+
+	/* TODO: Add L2 Cache information */
+};
+
+/* NOTE: In future if more information is added to struct kfd_gpu_cache_info
+ * the following ASICs may need a separate table.
+ */
+#define hawaii_cache_info kaveri_cache_info
+#define tonga_cache_info carrizo_cache_info
+#define fiji_cache_info  carrizo_cache_info
+#define polaris10_cache_info carrizo_cache_info
+#define polaris11_cache_info carrizo_cache_info
+
+static void kfd_populated_cu_info_cpu(struct kfd_topology_device *dev,
+		struct crat_subtype_computeunit *cu)
+{
+	dev->node_props.cpu_cores_count = cu->num_cpu_cores;
+	dev->node_props.cpu_core_id_base = cu->processor_id_low;
+	if (cu->hsa_capability & CRAT_CU_FLAGS_IOMMU_PRESENT)
+		dev->node_props.capability |= HSA_CAP_ATS_PRESENT;
+
+	pr_debug("CU CPU: cores=%d id_base=%d\n", cu->num_cpu_cores,
+			cu->processor_id_low);
+}
+
+static void kfd_populated_cu_info_gpu(struct kfd_topology_device *dev,
+		struct crat_subtype_computeunit *cu)
+{
+	dev->node_props.simd_id_base = cu->processor_id_low;
+	dev->node_props.simd_count = cu->num_simd_cores;
+	dev->node_props.lds_size_in_kb = cu->lds_size_in_kb;
+	dev->node_props.max_waves_per_simd = cu->max_waves_simd;
+	dev->node_props.wave_front_size = cu->wave_front_size;
+	dev->node_props.array_count = cu->array_count;
+	dev->node_props.cu_per_simd_array = cu->num_cu_per_array;
+	dev->node_props.simd_per_cu = cu->num_simd_per_cu;
+	dev->node_props.max_slots_scratch_cu = cu->max_slots_scatch_cu;
+	if (cu->hsa_capability & CRAT_CU_FLAGS_HOT_PLUGGABLE)
+		dev->node_props.capability |= HSA_CAP_HOT_PLUGGABLE;
+	pr_debug("CU GPU: id_base=%d\n", cu->processor_id_low);
+}
+
+/* kfd_parse_subtype_cu - parse compute unit subtypes and attach it to correct
+ * topology device present in the device_list
+ */
+static int kfd_parse_subtype_cu(struct crat_subtype_computeunit *cu,
+				struct list_head *device_list)
+{
+	struct kfd_topology_device *dev;
+
+	pr_debug("Found CU entry in CRAT table with proximity_domain=%d caps=%x\n",
+			cu->proximity_domain, cu->hsa_capability);
+	list_for_each_entry(dev, device_list, list) {
+		if (cu->proximity_domain == dev->proximity_domain) {
+			if (cu->flags & CRAT_CU_FLAGS_CPU_PRESENT)
+				kfd_populated_cu_info_cpu(dev, cu);
+
+			if (cu->flags & CRAT_CU_FLAGS_GPU_PRESENT)
+				kfd_populated_cu_info_gpu(dev, cu);
+			break;
+		}
+	}
+
+	return 0;
+}
+
+/* kfd_parse_subtype_mem - parse memory subtypes and attach it to correct
+ * topology device present in the device_list
+ */
+static int kfd_parse_subtype_mem(struct crat_subtype_memory *mem,
+				struct list_head *device_list)
+{
+	struct kfd_mem_properties *props;
+	struct kfd_topology_device *dev;
+
+	pr_debug("Found memory entry in CRAT table with proximity_domain=%d\n",
+			mem->proximity_domain);
+	list_for_each_entry(dev, device_list, list) {
+		if (mem->proximity_domain == dev->proximity_domain) {
+			props = kfd_alloc_struct(props);
+			if (!props)
+				return -ENOMEM;
+
+			/* We're on GPU node */
+			if (dev->node_props.cpu_cores_count == 0) {
+				/* APU */
+				if (mem->visibility_type == 0)
+					props->heap_type =
+						HSA_MEM_HEAP_TYPE_FB_PRIVATE;
+				/* dGPU */
+				else
+					props->heap_type = mem->visibility_type;
+			} else
+				props->heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
+
+			if (mem->flags & CRAT_MEM_FLAGS_HOT_PLUGGABLE)
+				props->flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
+			if (mem->flags & CRAT_MEM_FLAGS_NON_VOLATILE)
+				props->flags |= HSA_MEM_FLAGS_NON_VOLATILE;
+
+			props->size_in_bytes =
+				((uint64_t)mem->length_high << 32) +
+							mem->length_low;
+			props->width = mem->width;
+
+			dev->node_props.mem_banks_count++;
+			list_add_tail(&props->list, &dev->mem_props);
+
+			break;
+		}
+	}
+
+	return 0;
+}
+
+/* kfd_parse_subtype_cache - parse cache subtypes and attach it to correct
+ * topology device present in the device_list
+ */
+static int kfd_parse_subtype_cache(struct crat_subtype_cache *cache,
+			struct list_head *device_list)
+{
+	struct kfd_cache_properties *props;
+	struct kfd_topology_device *dev;
+	uint32_t id;
+	uint32_t total_num_of_cu;
+
+	id = cache->processor_id_low;
+
+	pr_debug("Found cache entry in CRAT table with processor_id=%d\n", id);
+	list_for_each_entry(dev, device_list, list) {
+		total_num_of_cu = (dev->node_props.array_count *
+					dev->node_props.cu_per_simd_array);
+
+		/* Cache infomration in CRAT doesn't have proximity_domain
+		 * information as it is associated with a CPU core or GPU
+		 * Compute Unit. So map the cache using CPU core Id or SIMD
+		 * (GPU) ID.
+		 * TODO: This works because currently we can safely assume that
+		 *  Compute Units are parsed before caches are parsed. In
+		 *  future, remove this dependency
+		 */
+		if ((id >= dev->node_props.cpu_core_id_base &&
+			id <= dev->node_props.cpu_core_id_base +
+				dev->node_props.cpu_cores_count) ||
+			(id >= dev->node_props.simd_id_base &&
+			id < dev->node_props.simd_id_base +
+				total_num_of_cu)) {
+			props = kfd_alloc_struct(props);
+			if (!props)
+				return -ENOMEM;
+
+			props->processor_id_low = id;
+			props->cache_level = cache->cache_level;
+			props->cache_size = cache->cache_size;
+			props->cacheline_size = cache->cache_line_size;
+			props->cachelines_per_tag = cache->lines_per_tag;
+			props->cache_assoc = cache->associativity;
+			props->cache_latency = cache->cache_latency;
+			memcpy(props->sibling_map, cache->sibling_map,
+					sizeof(props->sibling_map));
+
+			if (cache->flags & CRAT_CACHE_FLAGS_DATA_CACHE)
+				props->cache_type |= HSA_CACHE_TYPE_DATA;
+			if (cache->flags & CRAT_CACHE_FLAGS_INST_CACHE)
+				props->cache_type |= HSA_CACHE_TYPE_INSTRUCTION;
+			if (cache->flags & CRAT_CACHE_FLAGS_CPU_CACHE)
+				props->cache_type |= HSA_CACHE_TYPE_CPU;
+			if (cache->flags & CRAT_CACHE_FLAGS_SIMD_CACHE)
+				props->cache_type |= HSA_CACHE_TYPE_HSACU;
+
+			dev->cache_count++;
+			dev->node_props.caches_count++;
+			list_add_tail(&props->list, &dev->cache_props);
+
+			break;
+		}
+	}
+
+	return 0;
+}
+
+/* kfd_parse_subtype_iolink - parse iolink subtypes and attach it to correct
+ * topology device present in the device_list
+ */
+static int kfd_parse_subtype_iolink(struct crat_subtype_iolink *iolink,
+					struct list_head *device_list)
+{
+	struct kfd_iolink_properties *props = NULL, *props2;
+	struct kfd_topology_device *dev, *cpu_dev;
+	uint32_t id_from;
+	uint32_t id_to;
+
+	id_from = iolink->proximity_domain_from;
+	id_to = iolink->proximity_domain_to;
+
+	pr_debug("Found IO link entry in CRAT table with id_from=%d\n",
+			id_from);
+	list_for_each_entry(dev, device_list, list) {
+		if (id_from == dev->proximity_domain) {
+			props = kfd_alloc_struct(props);
+			if (!props)
+				return -ENOMEM;
+
+			props->node_from = id_from;
+			props->node_to = id_to;
+			props->ver_maj = iolink->version_major;
+			props->ver_min = iolink->version_minor;
+			props->iolink_type = iolink->io_interface_type;
+
+			if (props->iolink_type == CRAT_IOLINK_TYPE_PCIEXPRESS)
+				props->weight = 20;
+			else
+				props->weight = node_distance(id_from, id_to);
+
+			props->min_latency = iolink->minimum_latency;
+			props->max_latency = iolink->maximum_latency;
+			props->min_bandwidth = iolink->minimum_bandwidth_mbs;
+			props->max_bandwidth = iolink->maximum_bandwidth_mbs;
+			props->rec_transfer_size =
+					iolink->recommended_transfer_size;
+
+			dev->io_link_count++;
+			dev->node_props.io_links_count++;
+			list_add_tail(&props->list, &dev->io_link_props);
+			break;
+		}
+	}
+
+	/* CPU topology is created before GPUs are detected, so CPU->GPU
+	 * links are not built at that time. If a PCIe type is discovered, it
+	 * means a GPU is detected and we are adding GPU->CPU to the topology.
+	 * At this time, also add the corresponded CPU->GPU link.
+	 */
+	if (props && props->iolink_type == CRAT_IOLINK_TYPE_PCIEXPRESS) {
+		cpu_dev = kfd_topology_device_by_proximity_domain(id_to);
+		if (!cpu_dev)
+			return -ENODEV;
+		/* same everything but the other direction */
+		props2 = kmemdup(props, sizeof(*props2), GFP_KERNEL);
+		props2->node_from = id_to;
+		props2->node_to = id_from;
+		props2->kobj = NULL;
+		cpu_dev->io_link_count++;
+		cpu_dev->node_props.io_links_count++;
+		list_add_tail(&props2->list, &cpu_dev->io_link_props);
+	}
+
+	return 0;
+}
+
+/* kfd_parse_subtype - parse subtypes and attach it to correct topology device
+ * present in the device_list
+ *	@sub_type_hdr - subtype section of crat_image
+ *	@device_list - list of topology devices present in this crat_image
+ */
+static int kfd_parse_subtype(struct crat_subtype_generic *sub_type_hdr,
+				struct list_head *device_list)
+{
+	struct crat_subtype_computeunit *cu;
+	struct crat_subtype_memory *mem;
+	struct crat_subtype_cache *cache;
+	struct crat_subtype_iolink *iolink;
+	int ret = 0;
+
+	switch (sub_type_hdr->type) {
+	case CRAT_SUBTYPE_COMPUTEUNIT_AFFINITY:
+		cu = (struct crat_subtype_computeunit *)sub_type_hdr;
+		ret = kfd_parse_subtype_cu(cu, device_list);
+		break;
+	case CRAT_SUBTYPE_MEMORY_AFFINITY:
+		mem = (struct crat_subtype_memory *)sub_type_hdr;
+		ret = kfd_parse_subtype_mem(mem, device_list);
+		break;
+	case CRAT_SUBTYPE_CACHE_AFFINITY:
+		cache = (struct crat_subtype_cache *)sub_type_hdr;
+		ret = kfd_parse_subtype_cache(cache, device_list);
+		break;
+	case CRAT_SUBTYPE_TLB_AFFINITY:
+		/*
+		 * For now, nothing to do here
+		 */
+		pr_debug("Found TLB entry in CRAT table (not processing)\n");
+		break;
+	case CRAT_SUBTYPE_CCOMPUTE_AFFINITY:
+		/*
+		 * For now, nothing to do here
+		 */
+		pr_debug("Found CCOMPUTE entry in CRAT table (not processing)\n");
+		break;
+	case CRAT_SUBTYPE_IOLINK_AFFINITY:
+		iolink = (struct crat_subtype_iolink *)sub_type_hdr;
+		ret = kfd_parse_subtype_iolink(iolink, device_list);
+		break;
+	default:
+		pr_warn("Unknown subtype %d in CRAT\n",
+				sub_type_hdr->type);
+	}
+
+	return ret;
+}
+
+/* kfd_parse_crat_table - parse CRAT table. For each node present in CRAT
+ * create a kfd_topology_device and add in to device_list. Also parse
+ * CRAT subtypes and attach it to appropriate kfd_topology_device
+ *	@crat_image - input image containing CRAT
+ *	@device_list - [OUT] list of kfd_topology_device generated after
+ *		       parsing crat_image
+ *	@proximity_domain - Proximity domain of the first device in the table
+ *
+ *	Return - 0 if successful else -ve value
+ */
+int kfd_parse_crat_table(void *crat_image, struct list_head *device_list,
+			 uint32_t proximity_domain)
+{
+	struct kfd_topology_device *top_dev = NULL;
+	struct crat_subtype_generic *sub_type_hdr;
+	uint16_t node_id;
+	int ret = 0;
+	struct crat_header *crat_table = (struct crat_header *)crat_image;
+	uint16_t num_nodes;
+	uint32_t image_len;
+
+	if (!crat_image)
+		return -EINVAL;
+
+	if (!list_empty(device_list)) {
+		pr_warn("Error device list should be empty\n");
+		return -EINVAL;
+	}
+
+	num_nodes = crat_table->num_domains;
+	image_len = crat_table->length;
+
+	pr_info("Parsing CRAT table with %d nodes\n", num_nodes);
+
+	for (node_id = 0; node_id < num_nodes; node_id++) {
+		top_dev = kfd_create_topology_device(device_list);
+		if (!top_dev)
+			break;
+		top_dev->proximity_domain = proximity_domain++;
+	}
+
+	if (!top_dev) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	memcpy(top_dev->oem_id, crat_table->oem_id, CRAT_OEMID_LENGTH);
+	memcpy(top_dev->oem_table_id, crat_table->oem_table_id,
+			CRAT_OEMTABLEID_LENGTH);
+	top_dev->oem_revision = crat_table->oem_revision;
+
+	sub_type_hdr = (struct crat_subtype_generic *)(crat_table+1);
+	while ((char *)sub_type_hdr + sizeof(struct crat_subtype_generic) <
+			((char *)crat_image) + image_len) {
+		if (sub_type_hdr->flags & CRAT_SUBTYPE_FLAGS_ENABLED) {
+			ret = kfd_parse_subtype(sub_type_hdr, device_list);
+			if (ret)
+				break;
+		}
+
+		sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
+				sub_type_hdr->length);
+	}
+
+err:
+	if (ret)
+		kfd_release_topology_device_list(device_list);
+
+	return ret;
+}
+
+/* Helper function. See kfd_fill_gpu_cache_info for parameter description */
+static int fill_in_pcache(struct crat_subtype_cache *pcache,
+				struct kfd_gpu_cache_info *pcache_info,
+				struct kfd_cu_info *cu_info,
+				int mem_available,
+				int cu_bitmask,
+				int cache_type, unsigned int cu_processor_id,
+				int cu_block)
+{
+	unsigned int cu_sibling_map_mask;
+	int first_active_cu;
+
+	/* First check if enough memory is available */
+	if (sizeof(struct crat_subtype_cache) > mem_available)
+		return -ENOMEM;
+
+	cu_sibling_map_mask = cu_bitmask;
+	cu_sibling_map_mask >>= cu_block;
+	cu_sibling_map_mask &=
+		((1 << pcache_info[cache_type].num_cu_shared) - 1);
+	first_active_cu = ffs(cu_sibling_map_mask);
+
+	/* CU could be inactive. In case of shared cache find the first active
+	 * CU. and incase of non-shared cache check if the CU is inactive. If
+	 * inactive active skip it
+	 */
+	if (first_active_cu) {
+		memset(pcache, 0, sizeof(struct crat_subtype_cache));
+		pcache->type = CRAT_SUBTYPE_CACHE_AFFINITY;
+		pcache->length = sizeof(struct crat_subtype_cache);
+		pcache->flags = pcache_info[cache_type].flags;
+		pcache->processor_id_low = cu_processor_id
+					 + (first_active_cu - 1);
+		pcache->cache_level = pcache_info[cache_type].cache_level;
+		pcache->cache_size = pcache_info[cache_type].cache_size;
+
+		/* Sibling map is w.r.t processor_id_low, so shift out
+		 * inactive CU
+		 */
+		cu_sibling_map_mask =
+			cu_sibling_map_mask >> (first_active_cu - 1);
+
+		pcache->sibling_map[0] = (uint8_t)(cu_sibling_map_mask & 0xFF);
+		pcache->sibling_map[1] =
+				(uint8_t)((cu_sibling_map_mask >> 8) & 0xFF);
+		pcache->sibling_map[2] =
+				(uint8_t)((cu_sibling_map_mask >> 16) & 0xFF);
+		pcache->sibling_map[3] =
+				(uint8_t)((cu_sibling_map_mask >> 24) & 0xFF);
+		return 0;
+	}
+	return 1;
+}
+
+/* kfd_fill_gpu_cache_info - Fill GPU cache info using kfd_gpu_cache_info
+ * tables
+ *
+ *	@kdev - [IN] GPU device
+ *	@gpu_processor_id - [IN] GPU processor ID to which these caches
+ *			    associate
+ *	@available_size - [IN] Amount of memory available in pcache
+ *	@cu_info - [IN] Compute Unit info obtained from KGD
+ *	@pcache - [OUT] memory into which cache data is to be filled in.
+ *	@size_filled - [OUT] amount of data used up in pcache.
+ *	@num_of_entries - [OUT] number of caches added
+ */
+static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev,
+			int gpu_processor_id,
+			int available_size,
+			struct kfd_cu_info *cu_info,
+			struct crat_subtype_cache *pcache,
+			int *size_filled,
+			int *num_of_entries)
+{
+	struct kfd_gpu_cache_info *pcache_info;
+	int num_of_cache_types = 0;
+	int i, j, k;
+	int ct = 0;
+	int mem_available = available_size;
+	unsigned int cu_processor_id;
+	int ret;
+
+	switch (kdev->device_info->asic_family) {
+	case CHIP_KAVERI:
+		pcache_info = kaveri_cache_info;
+		num_of_cache_types = ARRAY_SIZE(kaveri_cache_info);
+		break;
+	case CHIP_HAWAII:
+		pcache_info = hawaii_cache_info;
+		num_of_cache_types = ARRAY_SIZE(hawaii_cache_info);
+		break;
+	case CHIP_CARRIZO:
+		pcache_info = carrizo_cache_info;
+		num_of_cache_types = ARRAY_SIZE(carrizo_cache_info);
+		break;
+	case CHIP_TONGA:
+		pcache_info = tonga_cache_info;
+		num_of_cache_types = ARRAY_SIZE(tonga_cache_info);
+		break;
+	case CHIP_FIJI:
+		pcache_info = fiji_cache_info;
+		num_of_cache_types = ARRAY_SIZE(fiji_cache_info);
+		break;
+	case CHIP_POLARIS10:
+		pcache_info = polaris10_cache_info;
+		num_of_cache_types = ARRAY_SIZE(polaris10_cache_info);
+		break;
+	case CHIP_POLARIS11:
+		pcache_info = polaris11_cache_info;
+		num_of_cache_types = ARRAY_SIZE(polaris11_cache_info);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*size_filled = 0;
+	*num_of_entries = 0;
+
+	/* For each type of cache listed in the kfd_gpu_cache_info table,
+	 * go through all available Compute Units.
+	 * The [i,j,k] loop will
+	 *		if kfd_gpu_cache_info.num_cu_shared = 1
+	 *			will parse through all available CU
+	 *		If (kfd_gpu_cache_info.num_cu_shared != 1)
+	 *			then it will consider only one CU from
+	 *			the shared unit
+	 */
+
+	for (ct = 0; ct < num_of_cache_types; ct++) {
+		cu_processor_id = gpu_processor_id;
+		for (i = 0; i < cu_info->num_shader_engines; i++) {
+			for (j = 0; j < cu_info->num_shader_arrays_per_engine;
+				j++) {
+				for (k = 0; k < cu_info->num_cu_per_sh;
+					k += pcache_info[ct].num_cu_shared) {
+
+					ret = fill_in_pcache(pcache,
+						pcache_info,
+						cu_info,
+						mem_available,
+						cu_info->cu_bitmap[i][j],
+						ct,
+						cu_processor_id,
+						k);
+
+					if (ret < 0)
+						break;
+
+					if (!ret) {
+						pcache++;
+						(*num_of_entries)++;
+						mem_available -=
+							sizeof(*pcache);
+						(*size_filled) +=
+							sizeof(*pcache);
+					}
+
+					/* Move to next CU block */
+					cu_processor_id +=
+						pcache_info[ct].num_cu_shared;
+				}
+			}
+		}
+	}
+
+	pr_debug("Added [%d] GPU cache entries\n", *num_of_entries);
+
+	return 0;
+}
+
+/*
+ * kfd_create_crat_image_acpi - Allocates memory for CRAT image and
+ * copies CRAT from ACPI (if available).
+ * NOTE: Call kfd_destroy_crat_image to free CRAT image memory
+ *
+ *	@crat_image: CRAT read from ACPI. If no CRAT in ACPI then
+ *		     crat_image will be NULL
+ *	@size: [OUT] size of crat_image
+ *
+ *	Return 0 if successful else return error code
+ */
+int kfd_create_crat_image_acpi(void **crat_image, size_t *size)
+{
+	struct acpi_table_header *crat_table;
+	acpi_status status;
+	void *pcrat_image;
+
+	if (!crat_image)
+		return -EINVAL;
+
+	*crat_image = NULL;
+
+	/* Fetch the CRAT table from ACPI */
+	status = acpi_get_table(CRAT_SIGNATURE, 0, &crat_table);
+	if (status == AE_NOT_FOUND) {
+		pr_warn("CRAT table not found\n");
+		return -ENODATA;
+	} else if (ACPI_FAILURE(status)) {
+		const char *err = acpi_format_exception(status);
+
+		pr_err("CRAT table error: %s\n", err);
+		return -EINVAL;
+	}
+
+	if (ignore_crat) {
+		pr_info("CRAT table disabled by module option\n");
+		return -ENODATA;
+	}
+
+	pcrat_image = kmalloc(crat_table->length, GFP_KERNEL);
+	if (!pcrat_image)
+		return -ENOMEM;
+
+	memcpy(pcrat_image, crat_table, crat_table->length);
+
+	*crat_image = pcrat_image;
+	*size = crat_table->length;
+
+	return 0;
+}
+
+/* Memory required to create Virtual CRAT.
+ * Since there is no easy way to predict the amount of memory required, the
+ * following amount are allocated for CPU and GPU Virtual CRAT. This is
+ * expected to cover all known conditions. But to be safe additional check
+ * is put in the code to ensure we don't overwrite.
+ */
+#define VCRAT_SIZE_FOR_CPU	(2 * PAGE_SIZE)
+#define VCRAT_SIZE_FOR_GPU	(3 * PAGE_SIZE)
+
+/* kfd_fill_cu_for_cpu - Fill in Compute info for the given CPU NUMA node
+ *
+ *	@numa_node_id: CPU NUMA node id
+ *	@avail_size: Available size in the memory
+ *	@sub_type_hdr: Memory into which compute info will be filled in
+ *
+ *	Return 0 if successful else return -ve value
+ */
+static int kfd_fill_cu_for_cpu(int numa_node_id, int *avail_size,
+				int proximity_domain,
+				struct crat_subtype_computeunit *sub_type_hdr)
+{
+	const struct cpumask *cpumask;
+
+	*avail_size -= sizeof(struct crat_subtype_computeunit);
+	if (*avail_size < 0)
+		return -ENOMEM;
+
+	memset(sub_type_hdr, 0, sizeof(struct crat_subtype_computeunit));
+
+	/* Fill in subtype header data */
+	sub_type_hdr->type = CRAT_SUBTYPE_COMPUTEUNIT_AFFINITY;
+	sub_type_hdr->length = sizeof(struct crat_subtype_computeunit);
+	sub_type_hdr->flags = CRAT_SUBTYPE_FLAGS_ENABLED;
+
+	cpumask = cpumask_of_node(numa_node_id);
+
+	/* Fill in CU data */
+	sub_type_hdr->flags |= CRAT_CU_FLAGS_CPU_PRESENT;
+	sub_type_hdr->proximity_domain = proximity_domain;
+	sub_type_hdr->processor_id_low = kfd_numa_node_to_apic_id(numa_node_id);
+	if (sub_type_hdr->processor_id_low == -1)
+		return -EINVAL;
+
+	sub_type_hdr->num_cpu_cores = cpumask_weight(cpumask);
+
+	return 0;
+}
+
+/* kfd_fill_mem_info_for_cpu - Fill in Memory info for the given CPU NUMA node
+ *
+ *	@numa_node_id: CPU NUMA node id
+ *	@avail_size: Available size in the memory
+ *	@sub_type_hdr: Memory into which compute info will be filled in
+ *
+ *	Return 0 if successful else return -ve value
+ */
+static int kfd_fill_mem_info_for_cpu(int numa_node_id, int *avail_size,
+			int proximity_domain,
+			struct crat_subtype_memory *sub_type_hdr)
+{
+	uint64_t mem_in_bytes = 0;
+	pg_data_t *pgdat;
+	int zone_type;
+
+	*avail_size -= sizeof(struct crat_subtype_memory);
+	if (*avail_size < 0)
+		return -ENOMEM;
+
+	memset(sub_type_hdr, 0, sizeof(struct crat_subtype_memory));
+
+	/* Fill in subtype header data */
+	sub_type_hdr->type = CRAT_SUBTYPE_MEMORY_AFFINITY;
+	sub_type_hdr->length = sizeof(struct crat_subtype_memory);
+	sub_type_hdr->flags = CRAT_SUBTYPE_FLAGS_ENABLED;
+
+	/* Fill in Memory Subunit data */
+
+	/* Unlike si_meminfo, si_meminfo_node is not exported. So
+	 * the following lines are duplicated from si_meminfo_node
+	 * function
+	 */
+	pgdat = NODE_DATA(numa_node_id);
+	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
+		mem_in_bytes += pgdat->node_zones[zone_type].managed_pages;
+	mem_in_bytes <<= PAGE_SHIFT;
+
+	sub_type_hdr->length_low = lower_32_bits(mem_in_bytes);
+	sub_type_hdr->length_high = upper_32_bits(mem_in_bytes);
+	sub_type_hdr->proximity_domain = proximity_domain;
+
+	return 0;
+}
+
+static int kfd_fill_iolink_info_for_cpu(int numa_node_id, int *avail_size,
+				uint32_t *num_entries,
+				struct crat_subtype_iolink *sub_type_hdr)
+{
+	int nid;
+	struct cpuinfo_x86 *c = &cpu_data(0);
+	uint8_t link_type;
+
+	if (c->x86_vendor == X86_VENDOR_AMD)
+		link_type = CRAT_IOLINK_TYPE_HYPERTRANSPORT;
+	else
+		link_type = CRAT_IOLINK_TYPE_QPI_1_1;
+
+	*num_entries = 0;
+
+	/* Create IO links from this node to other CPU nodes */
+	for_each_online_node(nid) {
+		if (nid == numa_node_id) /* node itself */
+			continue;
+
+		*avail_size -= sizeof(struct crat_subtype_iolink);
+		if (*avail_size < 0)
+			return -ENOMEM;
+
+		memset(sub_type_hdr, 0, sizeof(struct crat_subtype_iolink));
+
+		/* Fill in subtype header data */
+		sub_type_hdr->type = CRAT_SUBTYPE_IOLINK_AFFINITY;
+		sub_type_hdr->length = sizeof(struct crat_subtype_iolink);
+		sub_type_hdr->flags = CRAT_SUBTYPE_FLAGS_ENABLED;
+
+		/* Fill in IO link data */
+		sub_type_hdr->proximity_domain_from = numa_node_id;
+		sub_type_hdr->proximity_domain_to = nid;
+		sub_type_hdr->io_interface_type = link_type;
+
+		(*num_entries)++;
+		sub_type_hdr++;
+	}
+
+	return 0;
+}
+
+/* kfd_create_vcrat_image_cpu - Create Virtual CRAT for CPU
+ *
+ *	@pcrat_image: Fill in VCRAT for CPU
+ *	@size:	[IN] allocated size of crat_image.
+ *		[OUT] actual size of data filled in crat_image
+ */
+static int kfd_create_vcrat_image_cpu(void *pcrat_image, size_t *size)
+{
+	struct crat_header *crat_table = (struct crat_header *)pcrat_image;
+	struct acpi_table_header *acpi_table;
+	acpi_status status;
+	struct crat_subtype_generic *sub_type_hdr;
+	int avail_size = *size;
+	int numa_node_id;
+	uint32_t entries = 0;
+	int ret = 0;
+
+	if (!pcrat_image || avail_size < VCRAT_SIZE_FOR_CPU)
+		return -EINVAL;
+
+	/* Fill in CRAT Header.
+	 * Modify length and total_entries as subunits are added.
+	 */
+	avail_size -= sizeof(struct crat_header);
+	if (avail_size < 0)
+		return -ENOMEM;
+
+	memset(crat_table, 0, sizeof(struct crat_header));
+	memcpy(&crat_table->signature, CRAT_SIGNATURE,
+			sizeof(crat_table->signature));
+	crat_table->length = sizeof(struct crat_header);
+
+	status = acpi_get_table("DSDT", 0, &acpi_table);
+	if (status == AE_NOT_FOUND)
+		pr_warn("DSDT table not found for OEM information\n");
+	else {
+		crat_table->oem_revision = acpi_table->revision;
+		memcpy(crat_table->oem_id, acpi_table->oem_id,
+				CRAT_OEMID_LENGTH);
+		memcpy(crat_table->oem_table_id, acpi_table->oem_table_id,
+				CRAT_OEMTABLEID_LENGTH);
+	}
+	crat_table->total_entries = 0;
+	crat_table->num_domains = 0;
+
+	sub_type_hdr = (struct crat_subtype_generic *)(crat_table+1);
+
+	for_each_online_node(numa_node_id) {
+		if (kfd_numa_node_to_apic_id(numa_node_id) == -1)
+			continue;
+
+		/* Fill in Subtype: Compute Unit */
+		ret = kfd_fill_cu_for_cpu(numa_node_id, &avail_size,
+			crat_table->num_domains,
+			(struct crat_subtype_computeunit *)sub_type_hdr);
+		if (ret < 0)
+			return ret;
+		crat_table->length += sub_type_hdr->length;
+		crat_table->total_entries++;
+
+		sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
+			sub_type_hdr->length);
+
+		/* Fill in Subtype: Memory */
+		ret = kfd_fill_mem_info_for_cpu(numa_node_id, &avail_size,
+			crat_table->num_domains,
+			(struct crat_subtype_memory *)sub_type_hdr);
+		if (ret < 0)
+			return ret;
+		crat_table->length += sub_type_hdr->length;
+		crat_table->total_entries++;
+
+		sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
+			sub_type_hdr->length);
+
+		/* Fill in Subtype: IO Link */
+		ret = kfd_fill_iolink_info_for_cpu(numa_node_id, &avail_size,
+				&entries,
+				(struct crat_subtype_iolink *)sub_type_hdr);
+		if (ret < 0)
+			return ret;
+		crat_table->length += (sub_type_hdr->length * entries);
+		crat_table->total_entries += entries;
+
+		sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
+				sub_type_hdr->length * entries);
+
+		crat_table->num_domains++;
+	}
+
+	/* TODO: Add cache Subtype for CPU.
+	 * Currently, CPU cache information is available in function
+	 * detect_cache_attributes(cpu) defined in the file
+	 * ./arch/x86/kernel/cpu/intel_cacheinfo.c. This function is not
+	 * exported and to get the same information the code needs to be
+	 * duplicated.
+	 */
+
+	*size = crat_table->length;
+	pr_info("Virtual CRAT table created for CPU\n");
+
+	return 0;
+}
+
+static int kfd_fill_gpu_memory_affinity(int *avail_size,
+		struct kfd_dev *kdev, uint8_t type, uint64_t size,
+		struct crat_subtype_memory *sub_type_hdr,
+		uint32_t proximity_domain,
+		const struct kfd_local_mem_info *local_mem_info)
+{
+	*avail_size -= sizeof(struct crat_subtype_memory);
+	if (*avail_size < 0)
+		return -ENOMEM;
+
+	memset((void *)sub_type_hdr, 0, sizeof(struct crat_subtype_memory));
+	sub_type_hdr->type = CRAT_SUBTYPE_MEMORY_AFFINITY;
+	sub_type_hdr->length = sizeof(struct crat_subtype_memory);
+	sub_type_hdr->flags |= CRAT_SUBTYPE_FLAGS_ENABLED;
+
+	sub_type_hdr->proximity_domain = proximity_domain;
+
+	pr_debug("Fill gpu memory affinity - type 0x%x size 0x%llx\n",
+			type, size);
+
+	sub_type_hdr->length_low = lower_32_bits(size);
+	sub_type_hdr->length_high = upper_32_bits(size);
+
+	sub_type_hdr->width = local_mem_info->vram_width;
+	sub_type_hdr->visibility_type = type;
+
+	return 0;
+}
+
+/* kfd_fill_gpu_direct_io_link - Fill in direct io link from GPU
+ * to its NUMA node
+ *	@avail_size: Available size in the memory
+ *	@kdev - [IN] GPU device
+ *	@sub_type_hdr: Memory into which io link info will be filled in
+ *	@proximity_domain - proximity domain of the GPU node
+ *
+ *	Return 0 if successful else return -ve value
+ */
+static int kfd_fill_gpu_direct_io_link(int *avail_size,
+			struct kfd_dev *kdev,
+			struct crat_subtype_iolink *sub_type_hdr,
+			uint32_t proximity_domain)
+{
+	*avail_size -= sizeof(struct crat_subtype_iolink);
+	if (*avail_size < 0)
+		return -ENOMEM;
+
+	memset((void *)sub_type_hdr, 0, sizeof(struct crat_subtype_iolink));
+
+	/* Fill in subtype header data */
+	sub_type_hdr->type = CRAT_SUBTYPE_IOLINK_AFFINITY;
+	sub_type_hdr->length = sizeof(struct crat_subtype_iolink);
+	sub_type_hdr->flags |= CRAT_SUBTYPE_FLAGS_ENABLED;
+
+	/* Fill in IOLINK subtype.
+	 * TODO: Fill-in other fields of iolink subtype
+	 */
+	sub_type_hdr->io_interface_type = CRAT_IOLINK_TYPE_PCIEXPRESS;
+	sub_type_hdr->proximity_domain_from = proximity_domain;
+#ifdef CONFIG_NUMA
+	if (kdev->pdev->dev.numa_node == NUMA_NO_NODE)
+		sub_type_hdr->proximity_domain_to = 0;
+	else
+		sub_type_hdr->proximity_domain_to = kdev->pdev->dev.numa_node;
+#else
+	sub_type_hdr->proximity_domain_to = 0;
+#endif
+	return 0;
+}
+
+/* kfd_create_vcrat_image_gpu - Create Virtual CRAT for CPU
+ *
+ *	@pcrat_image: Fill in VCRAT for GPU
+ *	@size:	[IN] allocated size of crat_image.
+ *		[OUT] actual size of data filled in crat_image
+ */
+static int kfd_create_vcrat_image_gpu(void *pcrat_image,
+				      size_t *size, struct kfd_dev *kdev,
+				      uint32_t proximity_domain)
+{
+	struct crat_header *crat_table = (struct crat_header *)pcrat_image;
+	struct crat_subtype_generic *sub_type_hdr;
+	struct crat_subtype_computeunit *cu;
+	struct kfd_cu_info cu_info;
+	struct amd_iommu_device_info iommu_info;
+	int avail_size = *size;
+	uint32_t total_num_of_cu;
+	int num_of_cache_entries = 0;
+	int cache_mem_filled = 0;
+	int ret = 0;
+	const u32 required_iommu_flags = AMD_IOMMU_DEVICE_FLAG_ATS_SUP |
+					 AMD_IOMMU_DEVICE_FLAG_PRI_SUP |
+					 AMD_IOMMU_DEVICE_FLAG_PASID_SUP;
+	struct kfd_local_mem_info local_mem_info;
+
+	if (!pcrat_image || avail_size < VCRAT_SIZE_FOR_GPU)
+		return -EINVAL;
+
+	/* Fill the CRAT Header.
+	 * Modify length and total_entries as subunits are added.
+	 */
+	avail_size -= sizeof(struct crat_header);
+	if (avail_size < 0)
+		return -ENOMEM;
+
+	memset(crat_table, 0, sizeof(struct crat_header));
+
+	memcpy(&crat_table->signature, CRAT_SIGNATURE,
+			sizeof(crat_table->signature));
+	/* Change length as we add more subtypes*/
+	crat_table->length = sizeof(struct crat_header);
+	crat_table->num_domains = 1;
+	crat_table->total_entries = 0;
+
+	/* Fill in Subtype: Compute Unit
+	 * First fill in the sub type header and then sub type data
+	 */
+	avail_size -= sizeof(struct crat_subtype_computeunit);
+	if (avail_size < 0)
+		return -ENOMEM;
+
+	sub_type_hdr = (struct crat_subtype_generic *)(crat_table + 1);
+	memset(sub_type_hdr, 0, sizeof(struct crat_subtype_computeunit));
+
+	sub_type_hdr->type = CRAT_SUBTYPE_COMPUTEUNIT_AFFINITY;
+	sub_type_hdr->length = sizeof(struct crat_subtype_computeunit);
+	sub_type_hdr->flags = CRAT_SUBTYPE_FLAGS_ENABLED;
+
+	/* Fill CU subtype data */
+	cu = (struct crat_subtype_computeunit *)sub_type_hdr;
+	cu->flags |= CRAT_CU_FLAGS_GPU_PRESENT;
+	cu->proximity_domain = proximity_domain;
+
+	kdev->kfd2kgd->get_cu_info(kdev->kgd, &cu_info);
+	cu->num_simd_per_cu = cu_info.simd_per_cu;
+	cu->num_simd_cores = cu_info.simd_per_cu * cu_info.cu_active_number;
+	cu->max_waves_simd = cu_info.max_waves_per_simd;
+
+	cu->wave_front_size = cu_info.wave_front_size;
+	cu->array_count = cu_info.num_shader_arrays_per_engine *
+		cu_info.num_shader_engines;
+	total_num_of_cu = (cu->array_count * cu_info.num_cu_per_sh);
+	cu->processor_id_low = get_and_inc_gpu_processor_id(total_num_of_cu);
+	cu->num_cu_per_array = cu_info.num_cu_per_sh;
+	cu->max_slots_scatch_cu = cu_info.max_scratch_slots_per_cu;
+	cu->num_banks = cu_info.num_shader_engines;
+	cu->lds_size_in_kb = cu_info.lds_size;
+
+	cu->hsa_capability = 0;
+
+	/* Check if this node supports IOMMU. During parsing this flag will
+	 * translate to HSA_CAP_ATS_PRESENT
+	 */
+	iommu_info.flags = 0;
+	if (amd_iommu_device_info(kdev->pdev, &iommu_info) == 0) {
+		if ((iommu_info.flags & required_iommu_flags) ==
+				required_iommu_flags)
+			cu->hsa_capability |= CRAT_CU_FLAGS_IOMMU_PRESENT;
+	}
+
+	crat_table->length += sub_type_hdr->length;
+	crat_table->total_entries++;
+
+	/* Fill in Subtype: Memory. Only on systems with large BAR (no
+	 * private FB), report memory as public. On other systems
+	 * report the total FB size (public+private) as a single
+	 * private heap.
+	 */
+	kdev->kfd2kgd->get_local_mem_info(kdev->kgd, &local_mem_info);
+	sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
+			sub_type_hdr->length);
+
+	if (local_mem_info.local_mem_size_private == 0)
+		ret = kfd_fill_gpu_memory_affinity(&avail_size,
+				kdev, HSA_MEM_HEAP_TYPE_FB_PUBLIC,
+				local_mem_info.local_mem_size_public,
+				(struct crat_subtype_memory *)sub_type_hdr,
+				proximity_domain,
+				&local_mem_info);
+	else
+		ret = kfd_fill_gpu_memory_affinity(&avail_size,
+				kdev, HSA_MEM_HEAP_TYPE_FB_PRIVATE,
+				local_mem_info.local_mem_size_public +
+				local_mem_info.local_mem_size_private,
+				(struct crat_subtype_memory *)sub_type_hdr,
+				proximity_domain,
+				&local_mem_info);
+	if (ret < 0)
+		return ret;
+
+	crat_table->length += sizeof(struct crat_subtype_memory);
+	crat_table->total_entries++;
+
+	/* TODO: Fill in cache information. This information is NOT readily
+	 * available in KGD
+	 */
+	sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
+		sub_type_hdr->length);
+	ret = kfd_fill_gpu_cache_info(kdev, cu->processor_id_low,
+				avail_size,
+				&cu_info,
+				(struct crat_subtype_cache *)sub_type_hdr,
+				&cache_mem_filled,
+				&num_of_cache_entries);
+
+	if (ret < 0)
+		return ret;
+
+	crat_table->length += cache_mem_filled;
+	crat_table->total_entries += num_of_cache_entries;
+	avail_size -= cache_mem_filled;
+
+	/* Fill in Subtype: IO_LINKS
+	 *  Only direct links are added here which is Link from GPU to
+	 *  to its NUMA node. Indirect links are added by userspace.
+	 */
+	sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
+		cache_mem_filled);
+	ret = kfd_fill_gpu_direct_io_link(&avail_size, kdev,
+		(struct crat_subtype_iolink *)sub_type_hdr, proximity_domain);
+
+	if (ret < 0)
+		return ret;
+
+	crat_table->length += sub_type_hdr->length;
+	crat_table->total_entries++;
+
+	*size = crat_table->length;
+	pr_info("Virtual CRAT table created for GPU\n");
+
+	return ret;
+}
+
+/* kfd_create_crat_image_virtual - Allocates memory for CRAT image and
+ *		creates a Virtual CRAT (VCRAT) image
+ *
+ * NOTE: Call kfd_destroy_crat_image to free CRAT image memory
+ *
+ *	@crat_image: VCRAT image created because ACPI does not have a
+ *		     CRAT for this device
+ *	@size: [OUT] size of virtual crat_image
+ *	@flags:	COMPUTE_UNIT_CPU - Create VCRAT for CPU device
+ *		COMPUTE_UNIT_GPU - Create VCRAT for GPU
+ *		(COMPUTE_UNIT_CPU | COMPUTE_UNIT_GPU) - Create VCRAT for APU
+ *			-- this option is not currently implemented.
+ *			The assumption is that all AMD APUs will have CRAT
+ *	@kdev: Valid kfd_device required if flags contain COMPUTE_UNIT_GPU
+ *
+ *	Return 0 if successful else return -ve value
+ */
+int kfd_create_crat_image_virtual(void **crat_image, size_t *size,
+				  int flags, struct kfd_dev *kdev,
+				  uint32_t proximity_domain)
+{
+	void *pcrat_image = NULL;
+	int ret = 0;
+
+	if (!crat_image)
+		return -EINVAL;
+
+	*crat_image = NULL;
+
+	/* Allocate one VCRAT_SIZE_FOR_CPU for CPU virtual CRAT image and
+	 * VCRAT_SIZE_FOR_GPU for GPU virtual CRAT image. This should cover
+	 * all the current conditions. A check is put not to overwrite beyond
+	 * allocated size
+	 */
+	switch (flags) {
+	case COMPUTE_UNIT_CPU:
+		pcrat_image = kmalloc(VCRAT_SIZE_FOR_CPU, GFP_KERNEL);
+		if (!pcrat_image)
+			return -ENOMEM;
+		*size = VCRAT_SIZE_FOR_CPU;
+		ret = kfd_create_vcrat_image_cpu(pcrat_image, size);
+		break;
+	case COMPUTE_UNIT_GPU:
+		if (!kdev)
+			return -EINVAL;
+		pcrat_image = kmalloc(VCRAT_SIZE_FOR_GPU, GFP_KERNEL);
+		if (!pcrat_image)
+			return -ENOMEM;
+		*size = VCRAT_SIZE_FOR_GPU;
+		ret = kfd_create_vcrat_image_gpu(pcrat_image, size, kdev,
+						 proximity_domain);
+		break;
+	case (COMPUTE_UNIT_CPU | COMPUTE_UNIT_GPU):
+		/* TODO: */
+		ret = -EINVAL;
+		pr_err("VCRAT not implemented for APU\n");
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (!ret)
+		*crat_image = pcrat_image;
+	else
+		kfree(pcrat_image);
+
+	return ret;
+}
+
+
+/* kfd_destroy_crat_image
+ *
+ *	@crat_image: [IN] - crat_image from kfd_create_crat_image_xxx(..)
+ *
+ */
+void kfd_destroy_crat_image(void *crat_image)
+{
+	kfree(crat_image);
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.h b/drivers/gpu/drm/amd/amdkfd/kfd_crat.h
index a374fa3d3ee6..b5cd182b9edd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.h
@@ -44,6 +44,10 @@
 
 #define CRAT_OEMID_64BIT_MASK ((1ULL << (CRAT_OEMID_LENGTH * 8)) - 1)
 
+/* Compute Unit flags */
+#define COMPUTE_UNIT_CPU	(1 << 0)  /* Create Virtual CRAT for CPU */
+#define COMPUTE_UNIT_GPU	(1 << 1)  /* Create Virtual CRAT for GPU */
+
 struct crat_header {
 	uint32_t	signature;
 	uint32_t	length;
@@ -105,7 +109,7 @@ struct crat_subtype_computeunit {
 	uint8_t		wave_front_size;
 	uint8_t		num_banks;
 	uint16_t	micro_engine_id;
-	uint8_t		num_arrays;
+	uint8_t		array_count;
 	uint8_t		num_cu_per_array;
 	uint8_t		num_simd_per_cu;
 	uint8_t		max_slots_scatch_cu;
@@ -127,13 +131,14 @@ struct crat_subtype_memory {
 	uint8_t		length;
 	uint16_t	reserved;
 	uint32_t	flags;
-	uint32_t	promixity_domain;
+	uint32_t	proximity_domain;
 	uint32_t	base_addr_low;
 	uint32_t	base_addr_high;
 	uint32_t	length_low;
 	uint32_t	length_high;
 	uint32_t	width;
-	uint8_t		reserved2[CRAT_MEMORY_RESERVED_LENGTH];
+	uint8_t		visibility_type; /* for virtual (dGPU) CRAT */
+	uint8_t		reserved2[CRAT_MEMORY_RESERVED_LENGTH - 1];
 };
 
 /*
@@ -222,9 +227,12 @@ struct crat_subtype_ccompute {
 /*
  * HSA IO Link Affinity structure and definitions
  */
-#define CRAT_IOLINK_FLAGS_ENABLED	0x00000001
-#define CRAT_IOLINK_FLAGS_COHERENCY	0x00000002
-#define CRAT_IOLINK_FLAGS_RESERVED	0xfffffffc
+#define CRAT_IOLINK_FLAGS_ENABLED		(1 << 0)
+#define CRAT_IOLINK_FLAGS_NON_COHERENT		(1 << 1)
+#define CRAT_IOLINK_FLAGS_NO_ATOMICS_32_BIT	(1 << 2)
+#define CRAT_IOLINK_FLAGS_NO_ATOMICS_64_BIT	(1 << 3)
+#define CRAT_IOLINK_FLAGS_NO_PEER_TO_PEER_DMA	(1 << 4)
+#define CRAT_IOLINK_FLAGS_RESERVED_MASK		0xffffffe0
 
 /*
  * IO interface types
@@ -232,10 +240,18 @@ struct crat_subtype_ccompute {
 #define CRAT_IOLINK_TYPE_UNDEFINED	0
 #define CRAT_IOLINK_TYPE_HYPERTRANSPORT	1
 #define CRAT_IOLINK_TYPE_PCIEXPRESS	2
-#define CRAT_IOLINK_TYPE_OTHER		3
+#define CRAT_IOLINK_TYPE_AMBA		3
+#define CRAT_IOLINK_TYPE_MIPI		4
+#define CRAT_IOLINK_TYPE_QPI_1_1	5
+#define CRAT_IOLINK_TYPE_RESERVED1	6
+#define CRAT_IOLINK_TYPE_RESERVED2	7
+#define CRAT_IOLINK_TYPE_RAPID_IO	8
+#define CRAT_IOLINK_TYPE_INFINIBAND	9
+#define CRAT_IOLINK_TYPE_RESERVED3	10
+#define CRAT_IOLINK_TYPE_OTHER		11
 #define CRAT_IOLINK_TYPE_MAX		255
 
-#define CRAT_IOLINK_RESERVED_LENGTH 24
+#define CRAT_IOLINK_RESERVED_LENGTH	24
 
 struct crat_subtype_iolink {
 	uint8_t		type;
@@ -291,4 +307,14 @@ struct cdit_header {
 
 #pragma pack()
 
+struct kfd_dev;
+
+int kfd_create_crat_image_acpi(void **crat_image, size_t *size);
+void kfd_destroy_crat_image(void *crat_image);
+int kfd_parse_crat_table(void *crat_image, struct list_head *device_list,
+			 uint32_t proximity_domain);
+int kfd_create_crat_image_virtual(void **crat_image, size_t *size,
+				  int flags, struct kfd_dev *kdev,
+				  uint32_t proximity_domain);
+
 #endif /* KFD_CRAT_H_INCLUDED */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index c407f6bd9956..afb26f205d29 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -95,7 +95,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
 	ib_packet->bitfields3.ib_base_hi = largep->u.high_part;
 
 	ib_packet->control = (1 << 23) | (1 << 31) |
-			((size_in_bytes / sizeof(uint32_t)) & 0xfffff);
+			((size_in_bytes / 4) & 0xfffff);
 
 	ib_packet->bitfields5.pasid = pasid;
 
@@ -126,8 +126,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
 
 	rm_packet->header.opcode = IT_RELEASE_MEM;
 	rm_packet->header.type = PM4_TYPE_3;
-	rm_packet->header.count = sizeof(struct pm4__release_mem) /
-					sizeof(unsigned int) - 2;
+	rm_packet->header.count = sizeof(struct pm4__release_mem) / 4 - 2;
 
 	rm_packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
 	rm_packet->bitfields2.event_index =
@@ -652,8 +651,7 @@ static int dbgdev_wave_control_diq(struct kfd_dbgdev *dbgdev,
 	packets_vec[0].header.opcode = IT_SET_UCONFIG_REG;
 	packets_vec[0].header.type = PM4_TYPE_3;
 	packets_vec[0].bitfields2.reg_offset =
-			GRBM_GFX_INDEX / (sizeof(uint32_t)) -
-				USERCONFIG_REG_BASE;
+			GRBM_GFX_INDEX / 4 - USERCONFIG_REG_BASE;
 
 	packets_vec[0].bitfields2.insert_vmid = 0;
 	packets_vec[0].reg_data[0] = reg_gfx_index.u32All;
@@ -661,8 +659,7 @@ static int dbgdev_wave_control_diq(struct kfd_dbgdev *dbgdev,
 	packets_vec[1].header.count = 1;
 	packets_vec[1].header.opcode = IT_SET_CONFIG_REG;
 	packets_vec[1].header.type = PM4_TYPE_3;
-	packets_vec[1].bitfields2.reg_offset = SQ_CMD / (sizeof(uint32_t)) -
-						AMD_CONFIG_REG_BASE;
+	packets_vec[1].bitfields2.reg_offset = SQ_CMD / 4 - AMD_CONFIG_REG_BASE;
 
 	packets_vec[1].bitfields2.vmid_shift = SQ_CMD_VMID_OFFSET;
 	packets_vec[1].bitfields2.insert_vmid = 1;
@@ -678,8 +675,7 @@ static int dbgdev_wave_control_diq(struct kfd_dbgdev *dbgdev,
 
 	packets_vec[2].ordinal1 = packets_vec[0].ordinal1;
 	packets_vec[2].bitfields2.reg_offset =
-				GRBM_GFX_INDEX / (sizeof(uint32_t)) -
-					USERCONFIG_REG_BASE;
+				GRBM_GFX_INDEX / 4 - USERCONFIG_REG_BASE;
 
 	packets_vec[2].bitfields2.insert_vmid = 0;
 	packets_vec[2].reg_data[0] = reg_gfx_index.u32All;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
new file mode 100644
index 000000000000..4bd6ebfaf425
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
@@ -0,0 +1,75 @@
+/*
+ * Copyright 2016-2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <linux/debugfs.h>
+#include "kfd_priv.h"
+
+static struct dentry *debugfs_root;
+
+static int kfd_debugfs_open(struct inode *inode, struct file *file)
+{
+	int (*show)(struct seq_file *, void *) = inode->i_private;
+
+	return single_open(file, show, NULL);
+}
+
+static const struct file_operations kfd_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.open = kfd_debugfs_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+void kfd_debugfs_init(void)
+{
+	struct dentry *ent;
+
+	debugfs_root = debugfs_create_dir("kfd", NULL);
+	if (!debugfs_root || debugfs_root == ERR_PTR(-ENODEV)) {
+		pr_warn("Failed to create kfd debugfs dir\n");
+		return;
+	}
+
+	ent = debugfs_create_file("mqds", S_IFREG | 0444, debugfs_root,
+				  kfd_debugfs_mqds_by_process,
+				  &kfd_debugfs_fops);
+	if (!ent)
+		pr_warn("Failed to create mqds in kfd debugfs\n");
+
+	ent = debugfs_create_file("hqds", S_IFREG | 0444, debugfs_root,
+				  kfd_debugfs_hqds_by_device,
+				  &kfd_debugfs_fops);
+	if (!ent)
+		pr_warn("Failed to create hqds in kfd debugfs\n");
+
+	ent = debugfs_create_file("rls", S_IFREG | 0444, debugfs_root,
+				  kfd_debugfs_rls_by_device,
+				  &kfd_debugfs_fops);
+	if (!ent)
+		pr_warn("Failed to create rls in kfd debugfs\n");
+}
+
+void kfd_debugfs_fini(void)
+{
+	debugfs_remove_recursive(debugfs_root);
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 621a3b53a038..a8fa33a08de3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -27,6 +27,7 @@
 #include "kfd_priv.h"
 #include "kfd_device_queue_manager.h"
 #include "kfd_pm4_headers_vi.h"
+#include "cwsr_trap_handler_gfx8.asm"
 
 #define MQD_SIZE_ALIGNED 768
 
@@ -38,7 +39,8 @@ static const struct kfd_device_info kaveri_device_info = {
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
-	.mqd_size_aligned = MQD_SIZE_ALIGNED
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cwsr = false,
 };
 
 static const struct kfd_device_info carrizo_device_info = {
@@ -49,7 +51,8 @@ static const struct kfd_device_info carrizo_device_info = {
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
-	.mqd_size_aligned = MQD_SIZE_ALIGNED
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cwsr = true,
 };
 
 struct kfd_deviceid {
@@ -212,6 +215,17 @@ static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid,
 	return AMD_IOMMU_INV_PRI_RSP_INVALID;
 }
 
+static void kfd_cwsr_init(struct kfd_dev *kfd)
+{
+	if (cwsr_enable && kfd->device_info->supports_cwsr) {
+		BUILD_BUG_ON(sizeof(cwsr_trap_gfx8_hex) > PAGE_SIZE);
+
+		kfd->cwsr_isa = cwsr_trap_gfx8_hex;
+		kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx8_hex);
+		kfd->cwsr_enabled = true;
+	}
+}
+
 bool kgd2kfd_device_init(struct kfd_dev *kfd,
 			 const struct kgd2kfd_shared_resources *gpu_resources)
 {
@@ -224,6 +238,17 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 	kfd->vm_info.vmid_num_kfd = kfd->vm_info.last_vmid_kfd
 			- kfd->vm_info.first_vmid_kfd + 1;
 
+	/* Verify module parameters regarding mapped process number*/
+	if ((hws_max_conc_proc < 0)
+			|| (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) {
+		dev_err(kfd_device,
+			"hws_max_conc_proc %d must be between 0 and %d, use %d instead\n",
+			hws_max_conc_proc, kfd->vm_info.vmid_num_kfd,
+			kfd->vm_info.vmid_num_kfd);
+		kfd->max_proc_per_quantum = kfd->vm_info.vmid_num_kfd;
+	} else
+		kfd->max_proc_per_quantum = hws_max_conc_proc;
+
 	/* calculate max size of mqds needed for queues */
 	size = max_num_of_queues_per_device *
 			kfd->device_info->mqd_size_aligned;
@@ -286,6 +311,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 		goto device_iommu_pasid_error;
 	}
 
+	kfd_cwsr_init(kfd);
+
 	if (kfd_resume(kfd))
 		goto kfd_resume_error;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index e202921c150e..b21285afa4ea 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -149,8 +149,7 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
 
 static int create_queue_nocpsch(struct device_queue_manager *dqm,
 				struct queue *q,
-				struct qcm_process_device *qpd,
-				int *allocated_vmid)
+				struct qcm_process_device *qpd)
 {
 	int retval;
 
@@ -170,9 +169,11 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 		if (retval)
 			goto out_unlock;
 	}
-	*allocated_vmid = qpd->vmid;
 	q->properties.vmid = qpd->vmid;
 
+	q->properties.tba_addr = qpd->tba_addr;
+	q->properties.tma_addr = qpd->tma_addr;
+
 	if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE)
 		retval = create_compute_queue_nocpsch(dqm, q, qpd);
 	else if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
@@ -181,10 +182,8 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 		retval = -EINVAL;
 
 	if (retval) {
-		if (list_empty(&qpd->queues_list)) {
+		if (list_empty(&qpd->queues_list))
 			deallocate_vmid(dqm, qpd, q);
-			*allocated_vmid = 0;
-		}
 		goto out_unlock;
 	}
 
@@ -809,16 +808,13 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 }
 
 static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
-			struct qcm_process_device *qpd, int *allocate_vmid)
+			struct qcm_process_device *qpd)
 {
 	int retval;
 	struct mqd_manager *mqd;
 
 	retval = 0;
 
-	if (allocate_vmid)
-		*allocate_vmid = 0;
-
 	mutex_lock(&dqm->lock);
 
 	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
@@ -846,6 +842,9 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	}
 
 	dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
+
+	q->properties.tba_addr = qpd->tba_addr;
+	q->properties.tma_addr = qpd->tma_addr;
 	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
@@ -1014,13 +1013,13 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
 	list_del(&q->list);
 	qpd->queue_count--;
-	if (q->properties.is_active)
+	if (q->properties.is_active) {
 		dqm->queue_count--;
-
-	retval = execute_queues_cpsch(dqm,
+		retval = execute_queues_cpsch(dqm,
 				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
-	if (retval == -ETIME)
-		qpd->reset_wavefronts = true;
+		if (retval == -ETIME)
+			qpd->reset_wavefronts = true;
+	}
 
 	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
 
@@ -1034,7 +1033,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
 	mutex_unlock(&dqm->lock);
 
-	return 0;
+	return retval;
 
 failed:
 failed_try_destroy_debugged_queue:
@@ -1110,6 +1109,26 @@ out:
 	return retval;
 }
 
+static int set_trap_handler(struct device_queue_manager *dqm,
+				struct qcm_process_device *qpd,
+				uint64_t tba_addr,
+				uint64_t tma_addr)
+{
+	uint64_t *tma;
+
+	if (dqm->dev->cwsr_enabled) {
+		/* Jump from CWSR trap handler to user trap */
+		tma = (uint64_t *)(qpd->cwsr_kaddr + KFD_CWSR_TMA_OFFSET);
+		tma[0] = tba_addr;
+		tma[1] = tma_addr;
+	} else {
+		qpd->tba_addr = tba_addr;
+		qpd->tma_addr = tma_addr;
+	}
+
+	return 0;
+}
+
 static int process_termination_nocpsch(struct device_queue_manager *dqm,
 		struct qcm_process_device *qpd)
 {
@@ -1241,6 +1260,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 		dqm->ops.create_kernel_queue = create_kernel_queue_cpsch;
 		dqm->ops.destroy_kernel_queue = destroy_kernel_queue_cpsch;
 		dqm->ops.set_cache_memory_policy = set_cache_memory_policy;
+		dqm->ops.set_trap_handler = set_trap_handler;
 		dqm->ops.process_termination = process_termination_cpsch;
 		break;
 	case KFD_SCHED_POLICY_NO_HWS:
@@ -1256,6 +1276,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 		dqm->ops.initialize = initialize_nocpsch;
 		dqm->ops.uninitialize = uninitialize;
 		dqm->ops.set_cache_memory_policy = set_cache_memory_policy;
+		dqm->ops.set_trap_handler = set_trap_handler;
 		dqm->ops.process_termination = process_termination_nocpsch;
 		break;
 	default:
@@ -1290,3 +1311,74 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm)
 	dqm->ops.uninitialize(dqm);
 	kfree(dqm);
 }
+
+#if defined(CONFIG_DEBUG_FS)
+
+static void seq_reg_dump(struct seq_file *m,
+			 uint32_t (*dump)[2], uint32_t n_regs)
+{
+	uint32_t i, count;
+
+	for (i = 0, count = 0; i < n_regs; i++) {
+		if (count == 0 ||
+		    dump[i-1][0] + sizeof(uint32_t) != dump[i][0]) {
+			seq_printf(m, "%s    %08x: %08x",
+				   i ? "\n" : "",
+				   dump[i][0], dump[i][1]);
+			count = 7;
+		} else {
+			seq_printf(m, " %08x", dump[i][1]);
+			count--;
+		}
+	}
+
+	seq_puts(m, "\n");
+}
+
+int dqm_debugfs_hqds(struct seq_file *m, void *data)
+{
+	struct device_queue_manager *dqm = data;
+	uint32_t (*dump)[2], n_regs;
+	int pipe, queue;
+	int r = 0;
+
+	for (pipe = 0; pipe < get_pipes_per_mec(dqm); pipe++) {
+		int pipe_offset = pipe * get_queues_per_pipe(dqm);
+
+		for (queue = 0; queue < get_queues_per_pipe(dqm); queue++) {
+			if (!test_bit(pipe_offset + queue,
+				      dqm->dev->shared_resources.queue_bitmap))
+				continue;
+
+			r = dqm->dev->kfd2kgd->hqd_dump(
+				dqm->dev->kgd, pipe, queue, &dump, &n_regs);
+			if (r)
+				break;
+
+			seq_printf(m, "  CP Pipe %d, Queue %d\n",
+				  pipe, queue);
+			seq_reg_dump(m, dump, n_regs);
+
+			kfree(dump);
+		}
+	}
+
+	for (pipe = 0; pipe < CIK_SDMA_ENGINE_NUM; pipe++) {
+		for (queue = 0; queue < CIK_SDMA_QUEUES_PER_ENGINE; queue++) {
+			r = dqm->dev->kfd2kgd->hqd_sdma_dump(
+				dqm->dev->kgd, pipe, queue, &dump, &n_regs);
+			if (r)
+				break;
+
+			seq_printf(m, "  SDMA Engine %d, RLC %d\n",
+				  pipe, queue);
+			seq_reg_dump(m, dump, n_regs);
+
+			kfree(dump);
+		}
+	}
+
+	return r;
+}
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 5b77cb69f732..c61b693bfa8c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -84,8 +84,7 @@ struct device_process_node {
 struct device_queue_manager_ops {
 	int	(*create_queue)(struct device_queue_manager *dqm,
 				struct queue *q,
-				struct qcm_process_device *qpd,
-				int *allocate_vmid);
+				struct qcm_process_device *qpd);
 
 	int	(*destroy_queue)(struct device_queue_manager *dqm,
 				struct qcm_process_device *qpd,
@@ -123,6 +122,11 @@ struct device_queue_manager_ops {
 					   void __user *alternate_aperture_base,
 					   uint64_t alternate_aperture_size);
 
+	int	(*set_trap_handler)(struct device_queue_manager *dqm,
+				    struct qcm_process_device *qpd,
+				    uint64_t tba_addr,
+				    uint64_t tma_addr);
+
 	int (*process_termination)(struct device_queue_manager *dqm,
 			struct qcm_process_device *qpd);
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index feb76c235b1a..ebb4da14e3df 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -116,8 +116,7 @@ int kfd_doorbell_init(struct kfd_dev *kfd)
 	pr_debug("doorbell aperture size  == 0x%08lX\n",
 			kfd->shared_resources.doorbell_aperture_size);
 
-	pr_debug("doorbell kernel address == 0x%08lX\n",
-			(uintptr_t)kfd->doorbell_kernel_ptr);
+	pr_debug("doorbell kernel address == %p\n", kfd->doorbell_kernel_ptr);
 
 	return 0;
 }
@@ -194,8 +193,8 @@ u32 __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 
 	pr_debug("Get kernel queue doorbell\n"
 			 "     doorbell offset   == 0x%08X\n"
-			 "     kernel address    == 0x%08lX\n",
-		*doorbell_off, (uintptr_t)(kfd->doorbell_kernel_ptr + inx));
+			 "     kernel address    == %p\n",
+		*doorbell_off, (kfd->doorbell_kernel_ptr + inx));
 
 	return kfd->doorbell_kernel_ptr + inx;
 }
@@ -215,7 +214,7 @@ inline void write_kernel_doorbell(u32 __iomem *db, u32 value)
 {
 	if (db) {
 		writel(value, db);
-		pr_debug("Writing %d to doorbell address 0x%p\n", value, db);
+		pr_debug("Writing %d to doorbell address %p\n", value, db);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index cb92d4b72400..93aae5c1e78b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -441,7 +441,7 @@ void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
 	/*
 	 * Because we are called from arbitrary context (workqueue) as opposed
 	 * to process context, kfd_process could attempt to exit while we are
-	 * running so the lookup function returns a locked process.
+	 * running so the lookup function increments the process ref count.
 	 */
 	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
 
@@ -493,7 +493,7 @@ void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
 	}
 
 	mutex_unlock(&p->event_mutex);
-	mutex_unlock(&p->mutex);
+	kfd_unref_process(p);
 }
 
 static struct kfd_event_waiter *alloc_event_waiters(uint32_t num_events)
@@ -847,7 +847,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 	/*
 	 * Because we are called from arbitrary context (workqueue) as opposed
 	 * to process context, kfd_process could attempt to exit while we are
-	 * running so the lookup function returns a locked process.
+	 * running so the lookup function increments the process ref count.
 	 */
 	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
 	struct mm_struct *mm;
@@ -860,7 +860,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 	 */
 	mm = get_task_mm(p->lead_thread);
 	if (!mm) {
-		mutex_unlock(&p->mutex);
+		kfd_unref_process(p);
 		return; /* Process is exiting */
 	}
 
@@ -903,7 +903,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 			&memory_exception_data);
 
 	mutex_unlock(&p->event_mutex);
-	mutex_unlock(&p->mutex);
+	kfd_unref_process(p);
 }
 
 void kfd_signal_hw_exception_event(unsigned int pasid)
@@ -911,7 +911,7 @@ void kfd_signal_hw_exception_event(unsigned int pasid)
 	/*
 	 * Because we are called from arbitrary context (workqueue) as opposed
 	 * to process context, kfd_process could attempt to exit while we are
-	 * running so the lookup function returns a locked process.
+	 * running so the lookup function increments the process ref count.
 	 */
 	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
 
@@ -924,5 +924,5 @@ void kfd_signal_hw_exception_event(unsigned int pasid)
 	lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_HW_EXCEPTION, NULL);
 
 	mutex_unlock(&p->event_mutex);
-	mutex_unlock(&p->mutex);
+	kfd_unref_process(p);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
index c59384bbbc5f..7377513050e6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
@@ -300,9 +300,14 @@ int kfd_init_apertures(struct kfd_process *process)
 	struct kfd_process_device *pdd;
 
 	/*Iterating over all devices*/
-	while ((dev = kfd_topology_enum_kfd_devices(id)) != NULL &&
+	while (kfd_topology_enum_kfd_devices(id, &dev) == 0 &&
 		id < NUM_OF_SUPPORTED_GPUS) {
 
+		if (!dev) {
+			id++; /* Skip non GPU devices */
+			continue;
+		}
+
 		pdd = kfd_create_process_device_data(dev, process);
 		if (!pdd) {
 			pr_err("Failed to create process device data\n");
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 8b0c0645d7c0..5dc6567d4a13 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -218,7 +218,7 @@ static int acquire_packet_buffer(struct kernel_queue *kq,
 	rptr = *kq->rptr_kernel;
 	wptr = *kq->wptr_kernel;
 	queue_address = (unsigned int *)kq->pq_kernel_addr;
-	queue_size_dwords = kq->queue->properties.queue_size / sizeof(uint32_t);
+	queue_size_dwords = kq->queue->properties.queue_size / 4;
 
 	pr_debug("rptr: %d\n", rptr);
 	pr_debug("wptr: %d\n", wptr);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index 6c5a9cab55de..3ac72bed4f31 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -24,6 +24,7 @@
 #include <linux/sched.h>
 #include <linux/moduleparam.h>
 #include <linux/device.h>
+#include <linux/printk.h>
 #include "kfd_priv.h"
 
 #define KFD_DRIVER_AUTHOR	"AMD Inc. and others"
@@ -49,6 +50,15 @@ module_param(sched_policy, int, 0444);
 MODULE_PARM_DESC(sched_policy,
 	"Scheduling policy (0 = HWS (Default), 1 = HWS without over-subscription, 2 = Non-HWS (Used for debugging only)");
 
+int hws_max_conc_proc = 8;
+module_param(hws_max_conc_proc, int, 0444);
+MODULE_PARM_DESC(hws_max_conc_proc,
+	"Max # processes HWS can execute concurrently when sched_policy=0 (0 = no concurrency, #VMIDs for KFD = Maximum(default))");
+
+int cwsr_enable = 1;
+module_param(cwsr_enable, int, 0444);
+MODULE_PARM_DESC(cwsr_enable, "CWSR enable (0 = Off, 1 = On (Default))");
+
 int max_num_of_queues_per_device = KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT;
 module_param(max_num_of_queues_per_device, int, 0444);
 MODULE_PARM_DESC(max_num_of_queues_per_device,
@@ -59,6 +69,11 @@ module_param(send_sigterm, int, 0444);
 MODULE_PARM_DESC(send_sigterm,
 	"Send sigterm to HSA process on unhandled exception (0 = disable, 1 = enable)");
 
+int ignore_crat;
+module_param(ignore_crat, int, 0444);
+MODULE_PARM_DESC(ignore_crat,
+	"Ignore CRAT table during KFD initialization (0 = use CRAT (default), 1 = ignore CRAT)");
+
 static int amdkfd_init_completed;
 
 int kgd2kfd_init(unsigned int interface_version,
@@ -113,6 +128,8 @@ static int __init kfd_module_init(void)
 
 	kfd_process_create_wq();
 
+	kfd_debugfs_init();
+
 	amdkfd_init_completed = 1;
 
 	dev_info(kfd_device, "Initialized module\n");
@@ -129,10 +146,11 @@ static void __exit kfd_module_exit(void)
 {
 	amdkfd_init_completed = 0;
 
+	kfd_debugfs_fini();
 	kfd_process_destroy_wq();
 	kfd_topology_shutdown();
 	kfd_chardev_exit();
-	dev_info(kfd_device, "Removed module\n");
+	pr_info("amdkfd: Removed module\n");
 }
 
 module_init(kfd_module_init);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
index 1f3a6ba7eed2..8972bcfbf701 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
@@ -85,6 +85,10 @@ struct mqd_manager {
 				uint64_t queue_address,	uint32_t pipe_id,
 				uint32_t queue_id);
 
+#if defined(CONFIG_DEBUG_FS)
+	int	(*debugfs_show_mqd)(struct seq_file *m, void *data);
+#endif
+
 	struct mutex	mqd_mutex;
 	struct kfd_dev	*dev;
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index 4859d263fa2a..f8ef4a051e08 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -36,6 +36,11 @@ static inline struct cik_mqd *get_mqd(void *mqd)
 	return (struct cik_mqd *)mqd;
 }
 
+static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd)
+{
+	return (struct cik_sdma_rlc_registers *)mqd;
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 		struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 		struct queue_properties *q)
@@ -149,7 +154,7 @@ static int load_mqd(struct mqd_manager *mm, void *mqd, uint32_t pipe_id,
 {
 	/* AQL write pointer counts in 64B packets, PM4/CP counts in dwords. */
 	uint32_t wptr_shift = (p->format == KFD_QUEUE_FORMAT_AQL ? 4 : 0);
-	uint32_t wptr_mask = (uint32_t)((p->queue_size / sizeof(uint32_t)) - 1);
+	uint32_t wptr_mask = (uint32_t)((p->queue_size / 4) - 1);
 
 	return mm->dev->kfd2kgd->hqd_load(mm->dev->kgd, mqd, pipe_id, queue_id,
 					  (uint32_t __user *)p->write_ptr,
@@ -160,7 +165,9 @@ static int load_mqd_sdma(struct mqd_manager *mm, void *mqd,
 			 uint32_t pipe_id, uint32_t queue_id,
 			 struct queue_properties *p, struct mm_struct *mms)
 {
-	return mm->dev->kfd2kgd->hqd_sdma_load(mm->dev->kgd, mqd);
+	return mm->dev->kfd2kgd->hqd_sdma_load(mm->dev->kgd, mqd,
+					       (uint32_t __user *)p->write_ptr,
+					       mms);
 }
 
 static int update_mqd(struct mqd_manager *mm, void *mqd,
@@ -176,8 +183,7 @@ static int update_mqd(struct mqd_manager *mm, void *mqd,
 	 * Calculating queue size which is log base 2 of actual queue size -1
 	 * dwords and another -1 for ffs
 	 */
-	m->cp_hqd_pq_control |= ffs(q->queue_size / sizeof(unsigned int))
-								- 1 - 1;
+	m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1;
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
 	m->cp_hqd_pq_base_hi = upper_32_bits((uint64_t)q->queue_address >> 8);
 	m->cp_hqd_pq_rptr_report_addr_lo = lower_32_bits((uint64_t)q->read_ptr);
@@ -202,8 +208,8 @@ static int update_mqd_sdma(struct mqd_manager *mm, void *mqd,
 	struct cik_sdma_rlc_registers *m;
 
 	m = get_sdma_mqd(mqd);
-	m->sdma_rlc_rb_cntl = ffs(q->queue_size / sizeof(unsigned int)) <<
-			SDMA0_RLC0_RB_CNTL__RB_SIZE__SHIFT |
+	m->sdma_rlc_rb_cntl = order_base_2(q->queue_size / 4)
+			<< SDMA0_RLC0_RB_CNTL__RB_SIZE__SHIFT |
 			q->vmid << SDMA0_RLC0_RB_CNTL__RB_VMID__SHIFT |
 			1 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT |
 			6 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT;
@@ -343,8 +349,7 @@ static int update_mqd_hiq(struct mqd_manager *mm, void *mqd,
 	 * Calculating queue size which is log base 2 of actual queue
 	 * size -1 dwords
 	 */
-	m->cp_hqd_pq_control |= ffs(q->queue_size / sizeof(unsigned int))
-								- 1 - 1;
+	m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1;
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
 	m->cp_hqd_pq_base_hi = upper_32_bits((uint64_t)q->queue_address >> 8);
 	m->cp_hqd_pq_rptr_report_addr_lo = lower_32_bits((uint64_t)q->read_ptr);
@@ -360,15 +365,25 @@ static int update_mqd_hiq(struct mqd_manager *mm, void *mqd,
 	return 0;
 }
 
-struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd)
-{
-	struct cik_sdma_rlc_registers *m;
+#if defined(CONFIG_DEBUG_FS)
 
-	m = (struct cik_sdma_rlc_registers *)mqd;
+static int debugfs_show_mqd(struct seq_file *m, void *data)
+{
+	seq_hex_dump(m, "    ", DUMP_PREFIX_OFFSET, 32, 4,
+		     data, sizeof(struct cik_mqd), false);
+	return 0;
+}
 
-	return m;
+static int debugfs_show_mqd_sdma(struct seq_file *m, void *data)
+{
+	seq_hex_dump(m, "    ", DUMP_PREFIX_OFFSET, 32, 4,
+		     data, sizeof(struct cik_sdma_rlc_registers), false);
+	return 0;
 }
 
+#endif
+
+
 struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 		struct kfd_dev *dev)
 {
@@ -392,6 +407,9 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 		mqd->update_mqd = update_mqd;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd;
+#endif
 		break;
 	case KFD_MQD_TYPE_HIQ:
 		mqd->init_mqd = init_mqd_hiq;
@@ -400,6 +418,9 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 		mqd->update_mqd = update_mqd_hiq;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd;
+#endif
 		break;
 	case KFD_MQD_TYPE_SDMA:
 		mqd->init_mqd = init_mqd_sdma;
@@ -408,6 +429,9 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 		mqd->update_mqd = update_mqd_sdma;
 		mqd->destroy_mqd = destroy_mqd_sdma;
 		mqd->is_occupied = is_occupied_sdma;
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
+#endif
 		break;
 	default:
 		kfree(mqd);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
index 4ea854f9007b..971aec0637dc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -30,7 +30,7 @@
 #include "vi_structs.h"
 #include "gca/gfx_8_0_sh_mask.h"
 #include "gca/gfx_8_0_enum.h"
-
+#include "oss/oss_3_0_sh_mask.h"
 #define CP_MQD_CONTROL__PRIV_STATE__SHIFT 0x8
 
 static inline struct vi_mqd *get_mqd(void *mqd)
@@ -38,6 +38,11 @@ static inline struct vi_mqd *get_mqd(void *mqd)
 	return (struct vi_mqd *)mqd;
 }
 
+static inline struct vi_sdma_mqd *get_sdma_mqd(void *mqd)
+{
+	return (struct vi_sdma_mqd *)mqd;
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -84,6 +89,28 @@ static int init_mqd(struct mqd_manager *mm, void **mqd,
 	if (q->format == KFD_QUEUE_FORMAT_AQL)
 		m->cp_hqd_iq_rptr = 1;
 
+	if (q->tba_addr) {
+		m->compute_tba_lo = lower_32_bits(q->tba_addr >> 8);
+		m->compute_tba_hi = upper_32_bits(q->tba_addr >> 8);
+		m->compute_tma_lo = lower_32_bits(q->tma_addr >> 8);
+		m->compute_tma_hi = upper_32_bits(q->tma_addr >> 8);
+		m->compute_pgm_rsrc2 |=
+			(1 << COMPUTE_PGM_RSRC2__TRAP_PRESENT__SHIFT);
+	}
+
+	if (mm->dev->cwsr_enabled && q->ctx_save_restore_area_address) {
+		m->cp_hqd_persistent_state |=
+			(1 << CP_HQD_PERSISTENT_STATE__QSWITCH_MODE__SHIFT);
+		m->cp_hqd_ctx_save_base_addr_lo =
+			lower_32_bits(q->ctx_save_restore_area_address);
+		m->cp_hqd_ctx_save_base_addr_hi =
+			upper_32_bits(q->ctx_save_restore_area_address);
+		m->cp_hqd_ctx_save_size = q->ctx_save_restore_area_size;
+		m->cp_hqd_cntl_stack_size = q->ctl_stack_size;
+		m->cp_hqd_cntl_stack_offset = q->ctl_stack_size;
+		m->cp_hqd_wg_state_offset = q->ctl_stack_size;
+	}
+
 	*mqd = m;
 	if (gart_addr)
 		*gart_addr = addr;
@@ -98,7 +125,7 @@ static int load_mqd(struct mqd_manager *mm, void *mqd,
 {
 	/* AQL write pointer counts in 64B packets, PM4/CP counts in dwords. */
 	uint32_t wptr_shift = (p->format == KFD_QUEUE_FORMAT_AQL ? 4 : 0);
-	uint32_t wptr_mask = (uint32_t)((p->queue_size / sizeof(uint32_t)) - 1);
+	uint32_t wptr_mask = (uint32_t)((p->queue_size / 4) - 1);
 
 	return mm->dev->kfd2kgd->hqd_load(mm->dev->kgd, mqd, pipe_id, queue_id,
 					  (uint32_t __user *)p->write_ptr,
@@ -116,8 +143,7 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT |
 			atc_bit << CP_HQD_PQ_CONTROL__PQ_ATC__SHIFT |
 			mtype << CP_HQD_PQ_CONTROL__MTYPE__SHIFT;
-	m->cp_hqd_pq_control |=
-			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
+	m->cp_hqd_pq_control |=	order_base_2(q->queue_size / 4) - 1;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
@@ -147,7 +173,7 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 	 * is safe, giving a maximum field value of 0xA.
 	 */
 	m->cp_hqd_eop_control |= min(0xA,
-		ffs(q->eop_ring_buffer_size / sizeof(unsigned int)) - 1 - 1);
+		order_base_2(q->eop_ring_buffer_size / 4) - 1);
 	m->cp_hqd_eop_base_addr_lo =
 			lower_32_bits(q->eop_ring_buffer_address >> 8);
 	m->cp_hqd_eop_base_addr_hi =
@@ -163,6 +189,11 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 				2 << CP_HQD_PQ_CONTROL__SLOT_BASED_WPTR__SHIFT;
 	}
 
+	if (mm->dev->cwsr_enabled && q->ctx_save_restore_area_address)
+		m->cp_hqd_ctx_save_control =
+			atc_bit << CP_HQD_CTX_SAVE_CONTROL__ATC__SHIFT |
+			mtype << CP_HQD_CTX_SAVE_CONTROL__MTYPE__SHIFT;
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0);
@@ -234,6 +265,117 @@ static int update_mqd_hiq(struct mqd_manager *mm, void *mqd,
 	return retval;
 }
 
+static int init_mqd_sdma(struct mqd_manager *mm, void **mqd,
+		struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
+		struct queue_properties *q)
+{
+	int retval;
+	struct vi_sdma_mqd *m;
+
+
+	retval = kfd_gtt_sa_allocate(mm->dev,
+			sizeof(struct vi_sdma_mqd),
+			mqd_mem_obj);
+
+	if (retval != 0)
+		return -ENOMEM;
+
+	m = (struct vi_sdma_mqd *) (*mqd_mem_obj)->cpu_ptr;
+
+	memset(m, 0, sizeof(struct vi_sdma_mqd));
+
+	*mqd = m;
+	if (gart_addr != NULL)
+		*gart_addr = (*mqd_mem_obj)->gpu_addr;
+
+	retval = mm->update_mqd(mm, m, q);
+
+	return retval;
+}
+
+static void uninit_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		struct kfd_mem_obj *mqd_mem_obj)
+{
+	kfd_gtt_sa_free(mm->dev, mqd_mem_obj);
+}
+
+static int load_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		uint32_t pipe_id, uint32_t queue_id,
+		struct queue_properties *p, struct mm_struct *mms)
+{
+	return mm->dev->kfd2kgd->hqd_sdma_load(mm->dev->kgd, mqd,
+					       (uint32_t __user *)p->write_ptr,
+					       mms);
+}
+
+static int update_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		struct queue_properties *q)
+{
+	struct vi_sdma_mqd *m;
+
+	m = get_sdma_mqd(mqd);
+	m->sdmax_rlcx_rb_cntl = order_base_2(q->queue_size / 4)
+		<< SDMA0_RLC0_RB_CNTL__RB_SIZE__SHIFT |
+		q->vmid << SDMA0_RLC0_RB_CNTL__RB_VMID__SHIFT |
+		1 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT |
+		6 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT;
+
+	m->sdmax_rlcx_rb_base = lower_32_bits(q->queue_address >> 8);
+	m->sdmax_rlcx_rb_base_hi = upper_32_bits(q->queue_address >> 8);
+	m->sdmax_rlcx_rb_rptr_addr_lo = lower_32_bits((uint64_t)q->read_ptr);
+	m->sdmax_rlcx_rb_rptr_addr_hi = upper_32_bits((uint64_t)q->read_ptr);
+	m->sdmax_rlcx_doorbell =
+		q->doorbell_off << SDMA0_RLC0_DOORBELL__OFFSET__SHIFT;
+
+	m->sdmax_rlcx_virtual_addr = q->sdma_vm_addr;
+
+	m->sdma_engine_id = q->sdma_engine_id;
+	m->sdma_queue_id = q->sdma_queue_id;
+
+	q->is_active = (q->queue_size > 0 &&
+			q->queue_address != 0 &&
+			q->queue_percent > 0);
+
+	return 0;
+}
+
+/*
+ *  * preempt type here is ignored because there is only one way
+ *  * to preempt sdma queue
+ */
+static int destroy_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		enum kfd_preempt_type type,
+		unsigned int timeout, uint32_t pipe_id,
+		uint32_t queue_id)
+{
+	return mm->dev->kfd2kgd->hqd_sdma_destroy(mm->dev->kgd, mqd, timeout);
+}
+
+static bool is_occupied_sdma(struct mqd_manager *mm, void *mqd,
+		uint64_t queue_address, uint32_t pipe_id,
+		uint32_t queue_id)
+{
+	return mm->dev->kfd2kgd->hqd_sdma_is_occupied(mm->dev->kgd, mqd);
+}
+
+#if defined(CONFIG_DEBUG_FS)
+
+static int debugfs_show_mqd(struct seq_file *m, void *data)
+{
+	seq_hex_dump(m, "    ", DUMP_PREFIX_OFFSET, 32, 4,
+		     data, sizeof(struct vi_mqd), false);
+	return 0;
+}
+
+static int debugfs_show_mqd_sdma(struct seq_file *m, void *data)
+{
+	seq_hex_dump(m, "    ", DUMP_PREFIX_OFFSET, 32, 4,
+		     data, sizeof(struct vi_sdma_mqd), false);
+	return 0;
+}
+
+#endif
+
 struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 		struct kfd_dev *dev)
 {
@@ -257,6 +399,9 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 		mqd->update_mqd = update_mqd;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd;
+#endif
 		break;
 	case KFD_MQD_TYPE_HIQ:
 		mqd->init_mqd = init_mqd_hiq;
@@ -265,8 +410,20 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 		mqd->update_mqd = update_mqd_hiq;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd;
+#endif
 		break;
 	case KFD_MQD_TYPE_SDMA:
+		mqd->init_mqd = init_mqd_sdma;
+		mqd->uninit_mqd = uninit_mqd_sdma;
+		mqd->load_mqd = load_mqd_sdma;
+		mqd->update_mqd = update_mqd_sdma;
+		mqd->destroy_mqd = destroy_mqd_sdma;
+		mqd->is_occupied = is_occupied_sdma;
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
+#endif
 		break;
 	default:
 		kfree(mqd);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 16da8ad02d8b..0ecbd1f9b606 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -45,7 +45,7 @@ static unsigned int build_pm4_header(unsigned int opcode, size_t packet_size)
 
 	header.u32All = 0;
 	header.opcode = opcode;
-	header.count = packet_size/sizeof(uint32_t) - 2;
+	header.count = packet_size / 4 - 2;
 	header.type = PM4_TYPE_3;
 
 	return header.u32All;
@@ -55,15 +55,27 @@ static void pm_calc_rlib_size(struct packet_manager *pm,
 				unsigned int *rlib_size,
 				bool *over_subscription)
 {
-	unsigned int process_count, queue_count;
+	unsigned int process_count, queue_count, compute_queue_count;
 	unsigned int map_queue_size;
+	unsigned int max_proc_per_quantum = 1;
+	struct kfd_dev *dev = pm->dqm->dev;
 
 	process_count = pm->dqm->processes_count;
 	queue_count = pm->dqm->queue_count;
+	compute_queue_count = queue_count - pm->dqm->sdma_queue_count;
 
-	/* check if there is over subscription*/
+	/* check if there is over subscription
+	 * Note: the arbitration between the number of VMIDs and
+	 * hws_max_conc_proc has been done in
+	 * kgd2kfd_device_init().
+	 */
 	*over_subscription = false;
-	if ((process_count > 1) || queue_count > get_queues_num(pm->dqm)) {
+
+	if (dev->max_proc_per_quantum > 1)
+		max_proc_per_quantum = dev->max_proc_per_quantum;
+
+	if ((process_count > max_proc_per_quantum) ||
+	    compute_queue_count > get_queues_num(pm->dqm)) {
 		*over_subscription = true;
 		pr_debug("Over subscribed runlist\n");
 	}
@@ -116,10 +128,24 @@ static int pm_create_runlist(struct packet_manager *pm, uint32_t *buffer,
 			uint64_t ib, size_t ib_size_in_dwords, bool chain)
 {
 	struct pm4_mes_runlist *packet;
+	int concurrent_proc_cnt = 0;
+	struct kfd_dev *kfd = pm->dqm->dev;
 
 	if (WARN_ON(!ib))
 		return -EFAULT;
 
+	/* Determine the number of processes to map together to HW:
+	 * it can not exceed the number of VMIDs available to the
+	 * scheduler, and it is determined by the smaller of the number
+	 * of processes in the runlist and kfd module parameter
+	 * hws_max_conc_proc.
+	 * Note: the arbitration between the number of VMIDs and
+	 * hws_max_conc_proc has been done in
+	 * kgd2kfd_device_init().
+	 */
+	concurrent_proc_cnt = min(pm->dqm->processes_count,
+			kfd->max_proc_per_quantum);
+
 	packet = (struct pm4_mes_runlist *)buffer;
 
 	memset(buffer, 0, sizeof(struct pm4_mes_runlist));
@@ -130,6 +156,7 @@ static int pm_create_runlist(struct packet_manager *pm, uint32_t *buffer,
 	packet->bitfields4.chain = chain ? 1 : 0;
 	packet->bitfields4.offload_polling = 0;
 	packet->bitfields4.valid = 1;
+	packet->bitfields4.process_cnt = concurrent_proc_cnt;
 	packet->ordinal2 = lower_32_bits(ib);
 	packet->bitfields3.ib_base_hi = upper_32_bits(ib);
 
@@ -251,6 +278,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
 		return retval;
 
 	*rl_size_bytes = alloc_size_bytes;
+	pm->ib_size_bytes = alloc_size_bytes;
 
 	pr_debug("Building runlist ib process count: %d queues count %d\n",
 		pm->dqm->processes_count, pm->dqm->queue_count);
@@ -564,3 +592,26 @@ void pm_release_ib(struct packet_manager *pm)
 	}
 	mutex_unlock(&pm->lock);
 }
+
+#if defined(CONFIG_DEBUG_FS)
+
+int pm_debugfs_runlist(struct seq_file *m, void *data)
+{
+	struct packet_manager *pm = data;
+
+	mutex_lock(&pm->lock);
+
+	if (!pm->allocated) {
+		seq_puts(m, "  No active runlist\n");
+		goto out;
+	}
+
+	seq_hex_dump(m, "  ", DUMP_PREFIX_OFFSET, 32, 4,
+		     pm->ib_buffer_obj->cpu_ptr, pm->ib_size_bytes, false);
+
+out:
+	mutex_unlock(&pm->lock);
+	return 0;
+}
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
index d6a796144269..15fff4420e53 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
@@ -59,7 +59,7 @@ unsigned int kfd_pasid_alloc(void)
 		struct kfd_dev *dev = NULL;
 		unsigned int i = 0;
 
-		while ((dev = kfd_topology_enum_kfd_devices(i)) != NULL) {
+		while ((kfd_topology_enum_kfd_devices(i, &dev)) == 0) {
 			if (dev && dev->kfd2kgd) {
 				kfd2kgd = dev->kfd2kgd;
 				break;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 9e4134c5b481..0bedcf9cc08c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -33,14 +33,17 @@
 #include <linux/kfd_ioctl.h>
 #include <linux/idr.h>
 #include <linux/kfifo.h>
+#include <linux/seq_file.h>
+#include <linux/kref.h>
 #include <kgd_kfd_interface.h>
 
 #include "amd_shared.h"
 
 #define KFD_SYSFS_FILE_MODE 0444
 
-#define KFD_MMAP_DOORBELL_MASK 0x8000000000000
-#define KFD_MMAP_EVENTS_MASK 0x4000000000000
+#define KFD_MMAP_DOORBELL_MASK 0x8000000000000ull
+#define KFD_MMAP_EVENTS_MASK 0x4000000000000ull
+#define KFD_MMAP_RESERVED_MEM_MASK 0x2000000000000ull
 
 /*
  * When working with cp scheduler we should assign the HIQ manually or via
@@ -63,6 +66,15 @@
 #define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS 1024
 
 /*
+ * Size of the per-process TBA+TMA buffer: 2 pages
+ *
+ * The first page is the TBA used for the CWSR ISA code. The second
+ * page is used as TMA for daisy changing a user-mode trap handler.
+ */
+#define KFD_CWSR_TBA_TMA_SIZE (PAGE_SIZE * 2)
+#define KFD_CWSR_TMA_OFFSET PAGE_SIZE
+
+/*
  * Kernel module parameter to specify maximum number of supported queues per
  * device
  */
@@ -79,11 +91,25 @@ extern int max_num_of_queues_per_device;
 extern int sched_policy;
 
 /*
+ * Kernel module parameter to specify the maximum process
+ * number per HW scheduler
+ */
+extern int hws_max_conc_proc;
+
+extern int cwsr_enable;
+
+/*
  * Kernel module parameter to specify whether to send sigterm to HSA process on
  * unhandled exception
  */
 extern int send_sigterm;
 
+/*
+ * Ignore CRAT table during KFD initialization, can be used to work around
+ * broken CRAT tables on some AMD systems
+ */
+extern int ignore_crat;
+
 /**
  * enum kfd_sched_policy
  *
@@ -131,6 +157,7 @@ struct kfd_device_info {
 	size_t ih_ring_entry_size;
 	uint8_t num_of_watch_points;
 	uint16_t mqd_size_aligned;
+	bool supports_cwsr;
 };
 
 struct kfd_mem_obj {
@@ -200,6 +227,14 @@ struct kfd_dev {
 
 	/* Debug manager */
 	struct kfd_dbgmgr           *dbgmgr;
+
+	/* Maximum process number mapped to HW scheduler */
+	unsigned int max_proc_per_quantum;
+
+	/* CWSR */
+	bool cwsr_enabled;
+	const void *cwsr_isa;
+	unsigned int cwsr_isa_size;
 };
 
 /* KGD2KFD callbacks */
@@ -332,6 +367,9 @@ struct queue_properties {
 	uint32_t eop_ring_buffer_size;
 	uint64_t ctx_save_restore_area_address;
 	uint32_t ctx_save_restore_area_size;
+	uint32_t ctl_stack_size;
+	uint64_t tba_addr;
+	uint64_t tma_addr;
 };
 
 /**
@@ -439,6 +477,11 @@ struct qcm_process_device {
 	uint32_t num_gws;
 	uint32_t num_oac;
 	uint32_t sh_hidden_private_base;
+
+	/* CWSR memory */
+	void *cwsr_kaddr;
+	uint64_t tba_addr;
+	uint64_t tma_addr;
 };
 
 
@@ -501,6 +544,9 @@ struct kfd_process {
 	 */
 	void *mm;
 
+	struct kref ref;
+	struct work_struct release_work;
+
 	struct mutex mutex;
 
 	/*
@@ -563,9 +609,10 @@ struct amdkfd_ioctl_desc {
 
 void kfd_process_create_wq(void);
 void kfd_process_destroy_wq(void);
-struct kfd_process *kfd_create_process(const struct task_struct *);
+struct kfd_process *kfd_create_process(struct file *filep);
 struct kfd_process *kfd_get_process(const struct task_struct *);
 struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid);
+void kfd_unref_process(struct kfd_process *p);
 
 struct kfd_process_device *kfd_bind_process_to_device(struct kfd_dev *dev,
 						struct kfd_process *p);
@@ -577,6 +624,9 @@ struct kfd_process_device *kfd_get_process_device_data(struct kfd_dev *dev,
 struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 							struct kfd_process *p);
 
+int kfd_reserved_mem_mmap(struct kfd_process *process,
+			  struct vm_area_struct *vma);
+
 /* Process device data iterator */
 struct kfd_process_device *kfd_get_first_process_device_data(
 							struct kfd_process *p);
@@ -624,9 +674,12 @@ int kfd_topology_init(void);
 void kfd_topology_shutdown(void);
 int kfd_topology_add_device(struct kfd_dev *gpu);
 int kfd_topology_remove_device(struct kfd_dev *gpu);
+struct kfd_topology_device *kfd_topology_device_by_proximity_domain(
+						uint32_t proximity_domain);
 struct kfd_dev *kfd_device_by_id(uint32_t gpu_id);
 struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev);
-struct kfd_dev *kfd_topology_enum_kfd_devices(uint8_t idx);
+int kfd_topology_enum_kfd_devices(uint8_t idx, struct kfd_dev **kdev);
+int kfd_numa_node_to_apic_id(int numa_node_id);
 
 /* Interrupts */
 int kfd_interrupt_init(struct kfd_dev *dev);
@@ -643,8 +696,6 @@ int kgd2kfd_resume(struct kfd_dev *kfd);
 int kfd_init_apertures(struct kfd_process *process);
 
 /* Queue Context Management */
-struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd);
-
 int init_queue(struct queue **q, const struct queue_properties *properties);
 void uninit_queue(struct queue *q);
 void print_queue_properties(struct queue_properties *q);
@@ -699,6 +750,7 @@ struct packet_manager {
 	struct mutex lock;
 	bool allocated;
 	struct kfd_mem_obj *ib_buffer_obj;
+	unsigned int ib_size_bytes;
 };
 
 int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm);
@@ -745,4 +797,23 @@ int kfd_event_destroy(struct kfd_process *p, uint32_t event_id);
 
 int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p);
 
+/* Debugfs */
+#if defined(CONFIG_DEBUG_FS)
+
+void kfd_debugfs_init(void);
+void kfd_debugfs_fini(void);
+int kfd_debugfs_mqds_by_process(struct seq_file *m, void *data);
+int pqm_debugfs_mqds(struct seq_file *m, void *data);
+int kfd_debugfs_hqds_by_device(struct seq_file *m, void *data);
+int dqm_debugfs_hqds(struct seq_file *m, void *data);
+int kfd_debugfs_rls_by_device(struct seq_file *m, void *data);
+int pm_debugfs_runlist(struct seq_file *m, void *data);
+
+#else
+
+static inline void kfd_debugfs_init(void) {}
+static inline void kfd_debugfs_fini(void) {}
+
+#endif
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 1f5ccd28bd41..4ff5f0fe6db8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -24,10 +24,12 @@
 #include <linux/log2.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/amd-iommu.h>
 #include <linux/notifier.h>
 #include <linux/compat.h>
+#include <linux/mman.h>
 
 struct mm_struct;
 
@@ -46,13 +48,12 @@ DEFINE_STATIC_SRCU(kfd_processes_srcu);
 
 static struct workqueue_struct *kfd_process_wq;
 
-struct kfd_process_release_work {
-	struct work_struct kfd_work;
-	struct kfd_process *p;
-};
-
 static struct kfd_process *find_process(const struct task_struct *thread);
-static struct kfd_process *create_process(const struct task_struct *thread);
+static void kfd_process_ref_release(struct kref *ref);
+static struct kfd_process *create_process(const struct task_struct *thread,
+					struct file *filep);
+static int kfd_process_init_cwsr(struct kfd_process *p, struct file *filep);
+
 
 void kfd_process_create_wq(void)
 {
@@ -68,9 +69,10 @@ void kfd_process_destroy_wq(void)
 	}
 }
 
-struct kfd_process *kfd_create_process(const struct task_struct *thread)
+struct kfd_process *kfd_create_process(struct file *filep)
 {
 	struct kfd_process *process;
+	struct task_struct *thread = current;
 
 	if (!thread->mm)
 		return ERR_PTR(-EINVAL);
@@ -79,9 +81,6 @@ struct kfd_process *kfd_create_process(const struct task_struct *thread)
 	if (thread->group_leader->mm != thread->mm)
 		return ERR_PTR(-EINVAL);
 
-	/* Take mmap_sem because we call __mmu_notifier_register inside */
-	down_write(&thread->mm->mmap_sem);
-
 	/*
 	 * take kfd processes mutex before starting of process creation
 	 * so there won't be a case where two threads of the same process
@@ -93,14 +92,11 @@ struct kfd_process *kfd_create_process(const struct task_struct *thread)
 	process = find_process(thread);
 	if (process)
 		pr_debug("Process already found\n");
-
-	if (!process)
-		process = create_process(thread);
+	else
+		process = create_process(thread, filep);
 
 	mutex_unlock(&kfd_processes_mutex);
 
-	up_write(&thread->mm->mmap_sem);
-
 	return process;
 }
 
@@ -144,63 +140,75 @@ static struct kfd_process *find_process(const struct task_struct *thread)
 	return p;
 }
 
-static void kfd_process_wq_release(struct work_struct *work)
+void kfd_unref_process(struct kfd_process *p)
+{
+	kref_put(&p->ref, kfd_process_ref_release);
+}
+
+static void kfd_process_destroy_pdds(struct kfd_process *p)
 {
-	struct kfd_process_release_work *my_work;
 	struct kfd_process_device *pdd, *temp;
-	struct kfd_process *p;
 
-	my_work = (struct kfd_process_release_work *) work;
+	list_for_each_entry_safe(pdd, temp, &p->per_device_data,
+				 per_device_list) {
+		pr_debug("Releasing pdd (topology id %d) for process (pasid %d)\n",
+				pdd->dev->id, p->pasid);
 
-	p = my_work->p;
+		list_del(&pdd->per_device_list);
 
-	pr_debug("Releasing process (pasid %d) in workqueue\n",
-			p->pasid);
+		if (pdd->qpd.cwsr_kaddr)
+			free_pages((unsigned long)pdd->qpd.cwsr_kaddr,
+				get_order(KFD_CWSR_TBA_TMA_SIZE));
 
-	mutex_lock(&p->mutex);
+		kfree(pdd);
+	}
+}
 
-	list_for_each_entry_safe(pdd, temp, &p->per_device_data,
-							per_device_list) {
-		pr_debug("Releasing pdd (topology id %d) for process (pasid %d) in workqueue\n",
-				pdd->dev->id, p->pasid);
+/* No process locking is needed in this function, because the process
+ * is not findable any more. We must assume that no other thread is
+ * using it any more, otherwise we couldn't safely free the process
+ * structure in the end.
+ */
+static void kfd_process_wq_release(struct work_struct *work)
+{
+	struct kfd_process *p = container_of(work, struct kfd_process,
+					     release_work);
+	struct kfd_process_device *pdd;
 
+	pr_debug("Releasing process (pasid %d) in workqueue\n", p->pasid);
+
+	list_for_each_entry(pdd, &p->per_device_data, per_device_list) {
 		if (pdd->bound == PDD_BOUND)
 			amd_iommu_unbind_pasid(pdd->dev->pdev, p->pasid);
-
-		list_del(&pdd->per_device_list);
-		kfree(pdd);
 	}
 
+	kfd_process_destroy_pdds(p);
+
 	kfd_event_free_process(p);
 
 	kfd_pasid_free(p->pasid);
 	kfd_free_process_doorbells(p);
 
-	mutex_unlock(&p->mutex);
-
 	mutex_destroy(&p->mutex);
 
-	kfree(p);
+	put_task_struct(p->lead_thread);
 
-	kfree(work);
+	kfree(p);
 }
 
-static void kfd_process_destroy_delayed(struct rcu_head *rcu)
+static void kfd_process_ref_release(struct kref *ref)
 {
-	struct kfd_process_release_work *work;
-	struct kfd_process *p;
-
-	p = container_of(rcu, struct kfd_process, rcu);
+	struct kfd_process *p = container_of(ref, struct kfd_process, ref);
 
-	mmdrop(p->mm);
+	INIT_WORK(&p->release_work, kfd_process_wq_release);
+	queue_work(kfd_process_wq, &p->release_work);
+}
 
-	work = kmalloc(sizeof(struct kfd_process_release_work), GFP_ATOMIC);
+static void kfd_process_destroy_delayed(struct rcu_head *rcu)
+{
+	struct kfd_process *p = container_of(rcu, struct kfd_process, rcu);
 
-	if (work) {
-		INIT_WORK((struct work_struct *) work, kfd_process_wq_release);
-		work->p = p;
-		queue_work(kfd_process_wq, (struct work_struct *) work);
-	}
+	kfd_unref_process(p);
 }
 
 static void kfd_process_notifier_release(struct mmu_notifier *mn,
@@ -244,15 +252,12 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
 	kfd_process_dequeue_from_all_devices(p);
 	pqm_uninit(&p->pqm);
 
+	/* Indicate to other users that MM is no longer valid */
+	p->mm = NULL;
+
 	mutex_unlock(&p->mutex);
 
-	/*
-	 * Because we drop mm_count inside kfd_process_destroy_delayed
-	 * and because the mmu_notifier_unregister function also drop
-	 * mm_count we need to take an extra count here.
-	 */
-	mmgrab(p->mm);
-	mmu_notifier_unregister_no_release(&p->mmu_notifier, p->mm);
+	mmu_notifier_unregister_no_release(&p->mmu_notifier, mm);
 	mmu_notifier_call_srcu(&p->rcu, &kfd_process_destroy_delayed);
 }
 
@@ -260,7 +265,44 @@ static const struct mmu_notifier_ops kfd_process_mmu_notifier_ops = {
 	.release = kfd_process_notifier_release,
 };
 
-static struct kfd_process *create_process(const struct task_struct *thread)
+static int kfd_process_init_cwsr(struct kfd_process *p, struct file *filep)
+{
+	unsigned long  offset;
+	struct kfd_process_device *pdd = NULL;
+	struct kfd_dev *dev = NULL;
+	struct qcm_process_device *qpd = NULL;
+
+	list_for_each_entry(pdd, &p->per_device_data, per_device_list) {
+		dev = pdd->dev;
+		qpd = &pdd->qpd;
+		if (!dev->cwsr_enabled || qpd->cwsr_kaddr)
+			continue;
+		offset = (dev->id | KFD_MMAP_RESERVED_MEM_MASK) << PAGE_SHIFT;
+		qpd->tba_addr = (int64_t)vm_mmap(filep, 0,
+			KFD_CWSR_TBA_TMA_SIZE, PROT_READ | PROT_EXEC,
+			MAP_SHARED, offset);
+
+		if (IS_ERR_VALUE(qpd->tba_addr)) {
+			int err = qpd->tba_addr;
+
+			pr_err("Failure to set tba address. error %d.\n", err);
+			qpd->tba_addr = 0;
+			qpd->cwsr_kaddr = NULL;
+			return err;
+		}
+
+		memcpy(qpd->cwsr_kaddr, dev->cwsr_isa, dev->cwsr_isa_size);
+
+		qpd->tma_addr = qpd->tba_addr + KFD_CWSR_TMA_OFFSET;
+		pr_debug("set tba :0x%llx, tma:0x%llx, cwsr_kaddr:%p for pqm.\n",
+			qpd->tba_addr, qpd->tma_addr, qpd->cwsr_kaddr);
+	}
+
+	return 0;
+}
+
+static struct kfd_process *create_process(const struct task_struct *thread,
+					struct file *filep)
 {
 	struct kfd_process *process;
 	int err = -ENOMEM;
@@ -277,13 +319,15 @@ static struct kfd_process *create_process(const struct task_struct *thread)
 	if (kfd_alloc_process_doorbells(process) < 0)
 		goto err_alloc_doorbells;
 
+	kref_init(&process->ref);
+
 	mutex_init(&process->mutex);
 
 	process->mm = thread->mm;
 
 	/* register notifier */
 	process->mmu_notifier.ops = &kfd_process_mmu_notifier_ops;
-	err = __mmu_notifier_register(&process->mmu_notifier, process->mm);
+	err = mmu_notifier_register(&process->mmu_notifier, process->mm);
 	if (err)
 		goto err_mmu_notifier;
 
@@ -291,6 +335,7 @@ static struct kfd_process *create_process(const struct task_struct *thread)
 			(uintptr_t)process->mm);
 
 	process->lead_thread = thread->group_leader;
+	get_task_struct(process->lead_thread);
 
 	INIT_LIST_HEAD(&process->per_device_data);
 
@@ -306,8 +351,14 @@ static struct kfd_process *create_process(const struct task_struct *thread)
 	if (err != 0)
 		goto err_init_apertures;
 
+	err = kfd_process_init_cwsr(process, filep);
+	if (err)
+		goto err_init_cwsr;
+
 	return process;
 
+err_init_cwsr:
+	kfd_process_destroy_pdds(process);
 err_init_apertures:
 	pqm_uninit(&process->pqm);
 err_process_pqm_init:
@@ -343,16 +394,18 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 	struct kfd_process_device *pdd = NULL;
 
 	pdd = kzalloc(sizeof(*pdd), GFP_KERNEL);
-	if (pdd != NULL) {
-		pdd->dev = dev;
-		INIT_LIST_HEAD(&pdd->qpd.queues_list);
-		INIT_LIST_HEAD(&pdd->qpd.priv_queue_list);
-		pdd->qpd.dqm = dev->dqm;
-		pdd->process = p;
-		pdd->bound = PDD_UNBOUND;
-		pdd->already_dequeued = false;
-		list_add(&pdd->per_device_list, &p->per_device_data);
-	}
+	if (!pdd)
+		return NULL;
+
+	pdd->dev = dev;
+	INIT_LIST_HEAD(&pdd->qpd.queues_list);
+	INIT_LIST_HEAD(&pdd->qpd.priv_queue_list);
+	pdd->qpd.dqm = dev->dqm;
+	pdd->qpd.pqm = &p->pqm;
+	pdd->process = p;
+	pdd->bound = PDD_UNBOUND;
+	pdd->already_dequeued = false;
+	list_add(&pdd->per_device_list, &p->per_device_data);
 
 	return pdd;
 }
@@ -408,7 +461,8 @@ int kfd_bind_processes_to_device(struct kfd_dev *dev)
 	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
 		mutex_lock(&p->mutex);
 		pdd = kfd_get_process_device_data(dev, p);
-		if (pdd->bound != PDD_BOUND_SUSPENDED) {
+
+		if (WARN_ON(!pdd) || pdd->bound != PDD_BOUND_SUSPENDED) {
 			mutex_unlock(&p->mutex);
 			continue;
 		}
@@ -448,6 +502,11 @@ void kfd_unbind_processes_from_device(struct kfd_dev *dev)
 		mutex_lock(&p->mutex);
 		pdd = kfd_get_process_device_data(dev, p);
 
+		if (WARN_ON(!pdd)) {
+			mutex_unlock(&p->mutex);
+			continue;
+		}
+
 		if (pdd->bound == PDD_BOUND)
 			pdd->bound = PDD_BOUND_SUSPENDED;
 		mutex_unlock(&p->mutex);
@@ -483,6 +542,8 @@ void kfd_process_iommu_unbind_callback(struct kfd_dev *dev, unsigned int pasid)
 
 	mutex_unlock(kfd_get_dbgmgr_mutex());
 
+	mutex_lock(&p->mutex);
+
 	pdd = kfd_get_process_device_data(dev, p);
 	if (pdd)
 		/* For GPU relying on IOMMU, we need to dequeue here
@@ -491,6 +552,8 @@ void kfd_process_iommu_unbind_callback(struct kfd_dev *dev, unsigned int pasid)
 		kfd_process_dequeue_from_device(pdd);
 
 	mutex_unlock(&p->mutex);
+
+	kfd_unref_process(p);
 }
 
 struct kfd_process_device *kfd_get_first_process_device_data(
@@ -515,22 +578,86 @@ bool kfd_has_process_device_data(struct kfd_process *p)
 	return !(list_empty(&p->per_device_data));
 }
 
-/* This returns with process->mutex locked. */
+/* This increments the process->ref counter. */
 struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid)
 {
-	struct kfd_process *p;
+	struct kfd_process *p, *ret_p = NULL;
 	unsigned int temp;
 
 	int idx = srcu_read_lock(&kfd_processes_srcu);
 
 	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
 		if (p->pasid == pasid) {
-			mutex_lock(&p->mutex);
+			kref_get(&p->ref);
+			ret_p = p;
 			break;
 		}
 	}
 
 	srcu_read_unlock(&kfd_processes_srcu, idx);
 
-	return p;
+	return ret_p;
+}
+
+int kfd_reserved_mem_mmap(struct kfd_process *process,
+			  struct vm_area_struct *vma)
+{
+	struct kfd_dev *dev = kfd_device_by_id(vma->vm_pgoff);
+	struct kfd_process_device *pdd;
+	struct qcm_process_device *qpd;
+
+	if (!dev)
+		return -EINVAL;
+	if ((vma->vm_end - vma->vm_start) != KFD_CWSR_TBA_TMA_SIZE) {
+		pr_err("Incorrect CWSR mapping size.\n");
+		return -EINVAL;
+	}
+
+	pdd = kfd_get_process_device_data(dev, process);
+	if (!pdd)
+		return -EINVAL;
+	qpd = &pdd->qpd;
+
+	qpd->cwsr_kaddr = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+					get_order(KFD_CWSR_TBA_TMA_SIZE));
+	if (!qpd->cwsr_kaddr) {
+		pr_err("Error allocating per process CWSR buffer.\n");
+		return -ENOMEM;
+	}
+
+	vma->vm_flags |= VM_IO | VM_DONTCOPY | VM_DONTEXPAND
+		| VM_NORESERVE | VM_DONTDUMP | VM_PFNMAP;
+	/* Mapping pages to user process */
+	return remap_pfn_range(vma, vma->vm_start,
+			       PFN_DOWN(__pa(qpd->cwsr_kaddr)),
+			       KFD_CWSR_TBA_TMA_SIZE, vma->vm_page_prot);
+}
+
+#if defined(CONFIG_DEBUG_FS)
+
+int kfd_debugfs_mqds_by_process(struct seq_file *m, void *data)
+{
+	struct kfd_process *p;
+	unsigned int temp;
+	int r = 0;
+
+	int idx = srcu_read_lock(&kfd_processes_srcu);
+
+	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
+		seq_printf(m, "Process %d PASID %d:\n",
+			   p->lead_thread->tgid, p->pasid);
+
+		mutex_lock(&p->mutex);
+		r = pqm_debugfs_mqds(m, &p->pqm);
+		mutex_unlock(&p->mutex);
+
+		if (r)
+			break;
+	}
+
+	srcu_read_unlock(&kfd_processes_srcu, idx);
+
+	return r;
 }
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 2bec902fc939..876380632668 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -178,10 +178,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 		return retval;
 
 	if (list_empty(&pdd->qpd.queues_list) &&
-	    list_empty(&pdd->qpd.priv_queue_list)) {
-		pdd->qpd.pqm = pqm;
+	    list_empty(&pdd->qpd.priv_queue_list))
 		dev->dqm->ops.register_process(dev->dqm, &pdd->qpd);
-	}
 
 	pqn = kzalloc(sizeof(*pqn), GFP_KERNEL);
 	if (!pqn) {
@@ -191,6 +189,23 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 
 	switch (type) {
 	case KFD_QUEUE_TYPE_SDMA:
+		if (dev->dqm->queue_count >=
+			CIK_SDMA_QUEUES_PER_ENGINE * CIK_SDMA_ENGINE_NUM) {
+			pr_err("Over-subscription is not allowed for SDMA.\n");
+			retval = -EPERM;
+			goto err_create_queue;
+		}
+
+		retval = create_cp_queue(pqm, dev, &q, properties, f, *qid);
+		if (retval != 0)
+			goto err_create_queue;
+		pqn->q = q;
+		pqn->kq = NULL;
+		retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd);
+		pr_debug("DQM returned %d for create_queue\n", retval);
+		print_queue(q);
+		break;
+
 	case KFD_QUEUE_TYPE_COMPUTE:
 		/* check if there is over subscription */
 		if ((sched_policy == KFD_SCHED_POLICY_HWS_NO_OVERSUBSCRIPTION) &&
@@ -206,8 +221,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			goto err_create_queue;
 		pqn->q = q;
 		pqn->kq = NULL;
-		retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd,
-						&q->properties.vmid);
+		retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd);
 		pr_debug("DQM returned %d for create_queue\n", retval);
 		print_queue(q);
 		break;
@@ -297,6 +311,10 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 	if (pqn->q) {
 		dqm = pqn->q->device->dqm;
 		retval = dqm->ops.destroy_queue(dqm, &pdd->qpd, pqn->q);
+		if (retval) {
+			pr_debug("Destroy queue failed, returned %d\n", retval);
+			goto err_destroy_queue;
+		}
 		uninit_queue(pqn->q);
 	}
 
@@ -308,6 +326,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 	    list_empty(&pdd->qpd.priv_queue_list))
 		dqm->ops.unregister_process(dqm, &pdd->qpd);
 
+err_destroy_queue:
 	return retval;
 }
 
@@ -349,4 +368,67 @@ struct kernel_queue *pqm_get_kernel_queue(
 	return NULL;
 }
 
+#if defined(CONFIG_DEBUG_FS)
+
+int pqm_debugfs_mqds(struct seq_file *m, void *data)
+{
+	struct process_queue_manager *pqm = data;
+	struct process_queue_node *pqn;
+	struct queue *q;
+	enum KFD_MQD_TYPE mqd_type;
+	struct mqd_manager *mqd_manager;
+	int r = 0;
+
+	list_for_each_entry(pqn, &pqm->queues, process_queue_list) {
+		if (pqn->q) {
+			q = pqn->q;
+			switch (q->properties.type) {
+			case KFD_QUEUE_TYPE_SDMA:
+				seq_printf(m, "  SDMA queue on device %x\n",
+					   q->device->id);
+				mqd_type = KFD_MQD_TYPE_SDMA;
+				break;
+			case KFD_QUEUE_TYPE_COMPUTE:
+				seq_printf(m, "  Compute queue on device %x\n",
+					   q->device->id);
+				mqd_type = KFD_MQD_TYPE_CP;
+				break;
+			default:
+				seq_printf(m,
+				"  Bad user queue type %d on device %x\n",
+					   q->properties.type, q->device->id);
+				continue;
+			}
+			mqd_manager = q->device->dqm->ops.get_mqd_manager(
+				q->device->dqm, mqd_type);
+		} else if (pqn->kq) {
+			q = pqn->kq->queue;
+			mqd_manager = pqn->kq->mqd;
+			switch (q->properties.type) {
+			case KFD_QUEUE_TYPE_DIQ:
+				seq_printf(m, "  DIQ on device %x\n",
+					   pqn->kq->dev->id);
+				mqd_type = KFD_MQD_TYPE_HIQ;
+				break;
+			default:
+				seq_printf(m,
+				"  Bad kernel queue type %d on device %x\n",
+					   q->properties.type,
+					   pqn->kq->dev->id);
+				continue;
+			}
+		} else {
+			seq_printf(m,
+		"  Weird: Queue node with neither kernel nor user queue\n");
+			continue;
+		}
+
+		r = mqd_manager->debugfs_show_mqd(m, q->mqd);
+		if (r != 0)
+			break;
+	}
+
+	return r;
+}
 
+#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 19ce59028d6b..c6a76090a725 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -28,27 +28,32 @@
 #include <linux/hash.h>
 #include <linux/cpufreq.h>
 #include <linux/log2.h>
+#include <linux/dmi.h>
+#include <linux/atomic.h>
 
 #include "kfd_priv.h"
 #include "kfd_crat.h"
 #include "kfd_topology.h"
+#include "kfd_device_queue_manager.h"
 
+/* topology_device_list - Master list of all topology devices */
 static struct list_head topology_device_list;
-static int topology_crat_parsed;
 static struct kfd_system_properties sys_props;
 
 static DECLARE_RWSEM(topology_lock);
+static atomic_t topology_crat_proximity_domain;
 
-struct kfd_dev *kfd_device_by_id(uint32_t gpu_id)
+struct kfd_topology_device *kfd_topology_device_by_proximity_domain(
+						uint32_t proximity_domain)
 {
 	struct kfd_topology_device *top_dev;
-	struct kfd_dev *device = NULL;
+	struct kfd_topology_device *device = NULL;
 
 	down_read(&topology_lock);
 
 	list_for_each_entry(top_dev, &topology_device_list, list)
-		if (top_dev->gpu_id == gpu_id) {
-			device = top_dev->gpu;
+		if (top_dev->proximity_domain == proximity_domain) {
+			device = top_dev;
 			break;
 		}
 
@@ -57,7 +62,7 @@ struct kfd_dev *kfd_device_by_id(uint32_t gpu_id)
 	return device;
 }
 
-struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev)
+struct kfd_dev *kfd_device_by_id(uint32_t gpu_id)
 {
 	struct kfd_topology_device *top_dev;
 	struct kfd_dev *device = NULL;
@@ -65,7 +70,7 @@ struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev)
 	down_read(&topology_lock);
 
 	list_for_each_entry(top_dev, &topology_device_list, list)
-		if (top_dev->gpu->pdev == pdev) {
+		if (top_dev->gpu_id == gpu_id) {
 			device = top_dev->gpu;
 			break;
 		}
@@ -75,282 +80,31 @@ struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev)
 	return device;
 }
 
-static int kfd_topology_get_crat_acpi(void *crat_image, size_t *size)
-{
-	struct acpi_table_header *crat_table;
-	acpi_status status;
-
-	if (!size)
-		return -EINVAL;
-
-	/*
-	 * Fetch the CRAT table from ACPI
-	 */
-	status = acpi_get_table(CRAT_SIGNATURE, 0, &crat_table);
-	if (status == AE_NOT_FOUND) {
-		pr_warn("CRAT table not found\n");
-		return -ENODATA;
-	} else if (ACPI_FAILURE(status)) {
-		const char *err = acpi_format_exception(status);
-
-		pr_err("CRAT table error: %s\n", err);
-		return -EINVAL;
-	}
-
-	if (*size >= crat_table->length && crat_image != NULL)
-		memcpy(crat_image, crat_table, crat_table->length);
-
-	*size = crat_table->length;
-
-	return 0;
-}
-
-static void kfd_populated_cu_info_cpu(struct kfd_topology_device *dev,
-		struct crat_subtype_computeunit *cu)
-{
-	dev->node_props.cpu_cores_count = cu->num_cpu_cores;
-	dev->node_props.cpu_core_id_base = cu->processor_id_low;
-	if (cu->hsa_capability & CRAT_CU_FLAGS_IOMMU_PRESENT)
-		dev->node_props.capability |= HSA_CAP_ATS_PRESENT;
-
-	pr_info("CU CPU: cores=%d id_base=%d\n", cu->num_cpu_cores,
-			cu->processor_id_low);
-}
-
-static void kfd_populated_cu_info_gpu(struct kfd_topology_device *dev,
-		struct crat_subtype_computeunit *cu)
-{
-	dev->node_props.simd_id_base = cu->processor_id_low;
-	dev->node_props.simd_count = cu->num_simd_cores;
-	dev->node_props.lds_size_in_kb = cu->lds_size_in_kb;
-	dev->node_props.max_waves_per_simd = cu->max_waves_simd;
-	dev->node_props.wave_front_size = cu->wave_front_size;
-	dev->node_props.mem_banks_count = cu->num_banks;
-	dev->node_props.array_count = cu->num_arrays;
-	dev->node_props.cu_per_simd_array = cu->num_cu_per_array;
-	dev->node_props.simd_per_cu = cu->num_simd_per_cu;
-	dev->node_props.max_slots_scratch_cu = cu->max_slots_scatch_cu;
-	if (cu->hsa_capability & CRAT_CU_FLAGS_HOT_PLUGGABLE)
-		dev->node_props.capability |= HSA_CAP_HOT_PLUGGABLE;
-	pr_info("CU GPU: simds=%d id_base=%d\n", cu->num_simd_cores,
-				cu->processor_id_low);
-}
-
-/* kfd_parse_subtype_cu is called when the topology mutex is already acquired */
-static int kfd_parse_subtype_cu(struct crat_subtype_computeunit *cu)
-{
-	struct kfd_topology_device *dev;
-	int i = 0;
-
-	pr_info("Found CU entry in CRAT table with proximity_domain=%d caps=%x\n",
-			cu->proximity_domain, cu->hsa_capability);
-	list_for_each_entry(dev, &topology_device_list, list) {
-		if (cu->proximity_domain == i) {
-			if (cu->flags & CRAT_CU_FLAGS_CPU_PRESENT)
-				kfd_populated_cu_info_cpu(dev, cu);
-
-			if (cu->flags & CRAT_CU_FLAGS_GPU_PRESENT)
-				kfd_populated_cu_info_gpu(dev, cu);
-			break;
-		}
-		i++;
-	}
-
-	return 0;
-}
-
-/*
- * kfd_parse_subtype_mem is called when the topology mutex is
- * already acquired
- */
-static int kfd_parse_subtype_mem(struct crat_subtype_memory *mem)
-{
-	struct kfd_mem_properties *props;
-	struct kfd_topology_device *dev;
-	int i = 0;
-
-	pr_info("Found memory entry in CRAT table with proximity_domain=%d\n",
-			mem->promixity_domain);
-	list_for_each_entry(dev, &topology_device_list, list) {
-		if (mem->promixity_domain == i) {
-			props = kfd_alloc_struct(props);
-			if (props == NULL)
-				return -ENOMEM;
-
-			if (dev->node_props.cpu_cores_count == 0)
-				props->heap_type = HSA_MEM_HEAP_TYPE_FB_PRIVATE;
-			else
-				props->heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
-
-			if (mem->flags & CRAT_MEM_FLAGS_HOT_PLUGGABLE)
-				props->flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
-			if (mem->flags & CRAT_MEM_FLAGS_NON_VOLATILE)
-				props->flags |= HSA_MEM_FLAGS_NON_VOLATILE;
-
-			props->size_in_bytes =
-				((uint64_t)mem->length_high << 32) +
-							mem->length_low;
-			props->width = mem->width;
-
-			dev->mem_bank_count++;
-			list_add_tail(&props->list, &dev->mem_props);
-
-			break;
-		}
-		i++;
-	}
-
-	return 0;
-}
-
-/*
- * kfd_parse_subtype_cache is called when the topology mutex
- * is already acquired
- */
-static int kfd_parse_subtype_cache(struct crat_subtype_cache *cache)
-{
-	struct kfd_cache_properties *props;
-	struct kfd_topology_device *dev;
-	uint32_t id;
-
-	id = cache->processor_id_low;
-
-	pr_info("Found cache entry in CRAT table with processor_id=%d\n", id);
-	list_for_each_entry(dev, &topology_device_list, list)
-		if (id == dev->node_props.cpu_core_id_base ||
-		    id == dev->node_props.simd_id_base) {
-			props = kfd_alloc_struct(props);
-			if (props == NULL)
-				return -ENOMEM;
-
-			props->processor_id_low = id;
-			props->cache_level = cache->cache_level;
-			props->cache_size = cache->cache_size;
-			props->cacheline_size = cache->cache_line_size;
-			props->cachelines_per_tag = cache->lines_per_tag;
-			props->cache_assoc = cache->associativity;
-			props->cache_latency = cache->cache_latency;
-
-			if (cache->flags & CRAT_CACHE_FLAGS_DATA_CACHE)
-				props->cache_type |= HSA_CACHE_TYPE_DATA;
-			if (cache->flags & CRAT_CACHE_FLAGS_INST_CACHE)
-				props->cache_type |= HSA_CACHE_TYPE_INSTRUCTION;
-			if (cache->flags & CRAT_CACHE_FLAGS_CPU_CACHE)
-				props->cache_type |= HSA_CACHE_TYPE_CPU;
-			if (cache->flags & CRAT_CACHE_FLAGS_SIMD_CACHE)
-				props->cache_type |= HSA_CACHE_TYPE_HSACU;
-
-			dev->cache_count++;
-			dev->node_props.caches_count++;
-			list_add_tail(&props->list, &dev->cache_props);
-
-			break;
-		}
-
-	return 0;
-}
-
-/*
- * kfd_parse_subtype_iolink is called when the topology mutex
- * is already acquired
- */
-static int kfd_parse_subtype_iolink(struct crat_subtype_iolink *iolink)
+struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev)
 {
-	struct kfd_iolink_properties *props;
-	struct kfd_topology_device *dev;
-	uint32_t i = 0;
-	uint32_t id_from;
-	uint32_t id_to;
-
-	id_from = iolink->proximity_domain_from;
-	id_to = iolink->proximity_domain_to;
+	struct kfd_topology_device *top_dev;
+	struct kfd_dev *device = NULL;
 
-	pr_info("Found IO link entry in CRAT table with id_from=%d\n", id_from);
-	list_for_each_entry(dev, &topology_device_list, list) {
-		if (id_from == i) {
-			props = kfd_alloc_struct(props);
-			if (props == NULL)
-				return -ENOMEM;
-
-			props->node_from = id_from;
-			props->node_to = id_to;
-			props->ver_maj = iolink->version_major;
-			props->ver_min = iolink->version_minor;
-
-			/*
-			 * weight factor (derived from CDIR), currently always 1
-			 */
-			props->weight = 1;
-
-			props->min_latency = iolink->minimum_latency;
-			props->max_latency = iolink->maximum_latency;
-			props->min_bandwidth = iolink->minimum_bandwidth_mbs;
-			props->max_bandwidth = iolink->maximum_bandwidth_mbs;
-			props->rec_transfer_size =
-					iolink->recommended_transfer_size;
-
-			dev->io_link_count++;
-			dev->node_props.io_links_count++;
-			list_add_tail(&props->list, &dev->io_link_props);
+	down_read(&topology_lock);
 
+	list_for_each_entry(top_dev, &topology_device_list, list)
+		if (top_dev->gpu->pdev == pdev) {
+			device = top_dev->gpu;
 			break;
 		}
-		i++;
-	}
 
-	return 0;
-}
-
-static int kfd_parse_subtype(struct crat_subtype_generic *sub_type_hdr)
-{
-	struct crat_subtype_computeunit *cu;
-	struct crat_subtype_memory *mem;
-	struct crat_subtype_cache *cache;
-	struct crat_subtype_iolink *iolink;
-	int ret = 0;
-
-	switch (sub_type_hdr->type) {
-	case CRAT_SUBTYPE_COMPUTEUNIT_AFFINITY:
-		cu = (struct crat_subtype_computeunit *)sub_type_hdr;
-		ret = kfd_parse_subtype_cu(cu);
-		break;
-	case CRAT_SUBTYPE_MEMORY_AFFINITY:
-		mem = (struct crat_subtype_memory *)sub_type_hdr;
-		ret = kfd_parse_subtype_mem(mem);
-		break;
-	case CRAT_SUBTYPE_CACHE_AFFINITY:
-		cache = (struct crat_subtype_cache *)sub_type_hdr;
-		ret = kfd_parse_subtype_cache(cache);
-		break;
-	case CRAT_SUBTYPE_TLB_AFFINITY:
-		/*
-		 * For now, nothing to do here
-		 */
-		pr_info("Found TLB entry in CRAT table (not processing)\n");
-		break;
-	case CRAT_SUBTYPE_CCOMPUTE_AFFINITY:
-		/*
-		 * For now, nothing to do here
-		 */
-		pr_info("Found CCOMPUTE entry in CRAT table (not processing)\n");
-		break;
-	case CRAT_SUBTYPE_IOLINK_AFFINITY:
-		iolink = (struct crat_subtype_iolink *)sub_type_hdr;
-		ret = kfd_parse_subtype_iolink(iolink);
-		break;
-	default:
-		pr_warn("Unknown subtype (%d) in CRAT\n",
-				sub_type_hdr->type);
-	}
+	up_read(&topology_lock);
 
-	return ret;
+	return device;
 }
 
+/* Called with write topology_lock acquired */
 static void kfd_release_topology_device(struct kfd_topology_device *dev)
 {
 	struct kfd_mem_properties *mem;
 	struct kfd_cache_properties *cache;
 	struct kfd_iolink_properties *iolink;
+	struct kfd_perf_properties *perf;
 
 	list_del(&dev->list);
 
@@ -375,25 +129,35 @@ static void kfd_release_topology_device(struct kfd_topology_device *dev)
 		kfree(iolink);
 	}
 
-	kfree(dev);
+	while (dev->perf_props.next != &dev->perf_props) {
+		perf = container_of(dev->perf_props.next,
+				struct kfd_perf_properties, list);
+		list_del(&perf->list);
+		kfree(perf);
+	}
 
-	sys_props.num_devices--;
+	kfree(dev);
 }
 
-static void kfd_release_live_view(void)
+void kfd_release_topology_device_list(struct list_head *device_list)
 {
 	struct kfd_topology_device *dev;
 
-	while (topology_device_list.next != &topology_device_list) {
-		dev = container_of(topology_device_list.next,
-				 struct kfd_topology_device, list);
+	while (!list_empty(device_list)) {
+		dev = list_first_entry(device_list,
+				       struct kfd_topology_device, list);
 		kfd_release_topology_device(dev);
+	}
 }
 
+static void kfd_release_live_view(void)
+{
+	kfd_release_topology_device_list(&topology_device_list);
 	memset(&sys_props, 0, sizeof(sys_props));
 }
 
-static struct kfd_topology_device *kfd_create_topology_device(void)
+struct kfd_topology_device *kfd_create_topology_device(
+				struct list_head *device_list)
 {
 	struct kfd_topology_device *dev;
 
@@ -406,65 +170,13 @@ static struct kfd_topology_device *kfd_create_topology_device(void)
 	INIT_LIST_HEAD(&dev->mem_props);
 	INIT_LIST_HEAD(&dev->cache_props);
 	INIT_LIST_HEAD(&dev->io_link_props);
+	INIT_LIST_HEAD(&dev->perf_props);
 
-	list_add_tail(&dev->list, &topology_device_list);
-	sys_props.num_devices++;
+	list_add_tail(&dev->list, device_list);
 
 	return dev;
 }
 
-static int kfd_parse_crat_table(void *crat_image)
-{
-	struct kfd_topology_device *top_dev;
-	struct crat_subtype_generic *sub_type_hdr;
-	uint16_t node_id;
-	int ret;
-	struct crat_header *crat_table = (struct crat_header *)crat_image;
-	uint16_t num_nodes;
-	uint32_t image_len;
-
-	if (!crat_image)
-		return -EINVAL;
-
-	num_nodes = crat_table->num_domains;
-	image_len = crat_table->length;
-
-	pr_info("Parsing CRAT table with %d nodes\n", num_nodes);
-
-	for (node_id = 0; node_id < num_nodes; node_id++) {
-		top_dev = kfd_create_topology_device();
-		if (!top_dev) {
-			kfd_release_live_view();
-			return -ENOMEM;
-		}
-	}
-
-	sys_props.platform_id =
-		(*((uint64_t *)crat_table->oem_id)) & CRAT_OEMID_64BIT_MASK;
-	sys_props.platform_oem = *((uint64_t *)crat_table->oem_table_id);
-	sys_props.platform_rev = crat_table->revision;
-
-	sub_type_hdr = (struct crat_subtype_generic *)(crat_table+1);
-	while ((char *)sub_type_hdr + sizeof(struct crat_subtype_generic) <
-			((char *)crat_image) + image_len) {
-		if (sub_type_hdr->flags & CRAT_SUBTYPE_FLAGS_ENABLED) {
-			ret = kfd_parse_subtype(sub_type_hdr);
-			if (ret != 0) {
-				kfd_release_live_view();
-				return ret;
-			}
-		}
-
-		sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
-				sub_type_hdr->length);
-	}
-
-	sys_props.generation_count++;
-	topology_crat_parsed = 1;
-
-	return 0;
-}
-
 
 #define sysfs_show_gen_prop(buffer, fmt, ...) \
 		snprintf(buffer, PAGE_SIZE, "%s"fmt, buffer, __VA_ARGS__)
@@ -501,11 +213,17 @@ static ssize_t sysprops_show(struct kobject *kobj, struct attribute *attr,
 	return ret;
 }
 
+static void kfd_topology_kobj_release(struct kobject *kobj)
+{
+	kfree(kobj);
+}
+
 static const struct sysfs_ops sysprops_ops = {
 	.show = sysprops_show,
 };
 
 static struct kobj_type sysprops_type = {
+	.release = kfd_topology_kobj_release,
 	.sysfs_ops = &sysprops_ops,
 };
 
@@ -541,6 +259,7 @@ static const struct sysfs_ops iolink_ops = {
 };
 
 static struct kobj_type iolink_type = {
+	.release = kfd_topology_kobj_release,
 	.sysfs_ops = &iolink_ops,
 };
 
@@ -568,6 +287,7 @@ static const struct sysfs_ops mem_ops = {
 };
 
 static struct kobj_type mem_type = {
+	.release = kfd_topology_kobj_release,
 	.sysfs_ops = &mem_ops,
 };
 
@@ -575,7 +295,7 @@ static ssize_t kfd_cache_show(struct kobject *kobj, struct attribute *attr,
 		char *buffer)
 {
 	ssize_t ret;
-	uint32_t i;
+	uint32_t i, j;
 	struct kfd_cache_properties *cache;
 
 	/* Making sure that the buffer is an empty string */
@@ -593,12 +313,18 @@ static ssize_t kfd_cache_show(struct kobject *kobj, struct attribute *attr,
 	sysfs_show_32bit_prop(buffer, "latency", cache->cache_latency);
 	sysfs_show_32bit_prop(buffer, "type", cache->cache_type);
 	snprintf(buffer, PAGE_SIZE, "%ssibling_map ", buffer);
-	for (i = 0; i < KFD_TOPOLOGY_CPU_SIBLINGS; i++)
-		ret = snprintf(buffer, PAGE_SIZE, "%s%d%s",
-				buffer, cache->sibling_map[i],
-				(i == KFD_TOPOLOGY_CPU_SIBLINGS-1) ?
-						"\n" : ",");
-
+	for (i = 0; i < CRAT_SIBLINGMAP_SIZE; i++)
+		for (j = 0; j < sizeof(cache->sibling_map[0])*8; j++) {
+			/* Check each bit */
+			if (cache->sibling_map[i] & (1 << j))
+				ret = snprintf(buffer, PAGE_SIZE,
+					 "%s%d%s", buffer, 1, ",");
+			else
+				ret = snprintf(buffer, PAGE_SIZE,
+					 "%s%d%s", buffer, 0, ",");
+		}
+	/* Replace the last "," with end of line */
+	*(buffer + strlen(buffer) - 1) = 0xA;
 	return ret;
 }
 
@@ -607,9 +333,43 @@ static const struct sysfs_ops cache_ops = {
 };
 
 static struct kobj_type cache_type = {
+	.release = kfd_topology_kobj_release,
 	.sysfs_ops = &cache_ops,
 };
 
+/****** Sysfs of Performance Counters ******/
+
+struct kfd_perf_attr {
+	struct kobj_attribute attr;
+	uint32_t data;
+};
+
+static ssize_t perf_show(struct kobject *kobj, struct kobj_attribute *attrs,
+			char *buf)
+{
+	struct kfd_perf_attr *attr;
+
+	buf[0] = 0;
+	attr = container_of(attrs, struct kfd_perf_attr, attr);
+	if (!attr->data) /* invalid data for PMC */
+		return 0;
+	else
+		return sysfs_show_32bit_val(buf, attr->data);
+}
+
+#define KFD_PERF_DESC(_name, _data)			\
+{							\
+	.attr  = __ATTR(_name, 0444, perf_show, NULL),	\
+	.data = _data,					\
+}
+
+static struct kfd_perf_attr perf_attr_iommu[] = {
+	KFD_PERF_DESC(max_concurrent, 0),
+	KFD_PERF_DESC(num_counters, 0),
+	KFD_PERF_DESC(counter_ids, 0),
+};
+/****************************************/
+
 static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 		char *buffer)
 {
@@ -646,18 +406,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 			dev->node_props.cpu_cores_count);
 	sysfs_show_32bit_prop(buffer, "simd_count",
 			dev->node_props.simd_count);
-
-	if (dev->mem_bank_count < dev->node_props.mem_banks_count) {
-		pr_info_once("mem_banks_count truncated from %d to %d\n",
-				dev->node_props.mem_banks_count,
-				dev->mem_bank_count);
-		sysfs_show_32bit_prop(buffer, "mem_banks_count",
-				dev->mem_bank_count);
-	} else {
-		sysfs_show_32bit_prop(buffer, "mem_banks_count",
-				dev->node_props.mem_banks_count);
-	}
-
+	sysfs_show_32bit_prop(buffer, "mem_banks_count",
+			dev->node_props.mem_banks_count);
 	sysfs_show_32bit_prop(buffer, "caches_count",
 			dev->node_props.caches_count);
 	sysfs_show_32bit_prop(buffer, "io_links_count",
@@ -705,9 +455,12 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 				HSA_CAP_WATCH_POINTS_TOTALBITS_MASK);
 		}
 
+		if (dev->gpu->device_info->asic_family == CHIP_TONGA)
+			dev->node_props.capability |=
+					HSA_CAP_AQL_QUEUE_DOUBLE_MAP;
+
 		sysfs_show_32bit_prop(buffer, "max_engine_clk_fcompute",
-			dev->gpu->kfd2kgd->get_max_engine_clock_in_mhz(
-					dev->gpu->kgd));
+			dev->node_props.max_engine_clk_fcompute);
 
 		sysfs_show_64bit_prop(buffer, "local_mem_size",
 				(unsigned long long int) 0);
@@ -729,6 +482,7 @@ static const struct sysfs_ops node_ops = {
 };
 
 static struct kobj_type node_type = {
+	.release = kfd_topology_kobj_release,
 	.sysfs_ops = &node_ops,
 };
 
@@ -744,6 +498,7 @@ static void kfd_remove_sysfs_node_entry(struct kfd_topology_device *dev)
 	struct kfd_iolink_properties *iolink;
 	struct kfd_cache_properties *cache;
 	struct kfd_mem_properties *mem;
+	struct kfd_perf_properties *perf;
 
 	if (dev->kobj_iolink) {
 		list_for_each_entry(iolink, &dev->io_link_props, list)
@@ -780,6 +535,16 @@ static void kfd_remove_sysfs_node_entry(struct kfd_topology_device *dev)
 		dev->kobj_mem = NULL;
 	}
 
+	if (dev->kobj_perf) {
+		list_for_each_entry(perf, &dev->perf_props, list) {
+			kfree(perf->attr_group);
+			perf->attr_group = NULL;
+		}
+		kobject_del(dev->kobj_perf);
+		kobject_put(dev->kobj_perf);
+		dev->kobj_perf = NULL;
+	}
+
 	if (dev->kobj_node) {
 		sysfs_remove_file(dev->kobj_node, &dev->attr_gpuid);
 		sysfs_remove_file(dev->kobj_node, &dev->attr_name);
@@ -796,8 +561,10 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev,
 	struct kfd_iolink_properties *iolink;
 	struct kfd_cache_properties *cache;
 	struct kfd_mem_properties *mem;
+	struct kfd_perf_properties *perf;
 	int ret;
-	uint32_t i;
+	uint32_t i, num_attrs;
+	struct attribute **attrs;
 
 	if (WARN_ON(dev->kobj_node))
 		return -EEXIST;
@@ -826,6 +593,10 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev,
 	if (!dev->kobj_iolink)
 		return -ENOMEM;
 
+	dev->kobj_perf = kobject_create_and_add("perf", dev->kobj_node);
+	if (!dev->kobj_perf)
+		return -ENOMEM;
+
 	/*
 	 * Creating sysfs files for node properties
 	 */
@@ -903,11 +674,38 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev,
 		if (ret < 0)
 			return ret;
 		i++;
-}
+	}
+
+	/* All hardware blocks have the same number of attributes. */
+	num_attrs = sizeof(perf_attr_iommu)/sizeof(struct kfd_perf_attr);
+	list_for_each_entry(perf, &dev->perf_props, list) {
+		perf->attr_group = kzalloc(sizeof(struct kfd_perf_attr)
+			* num_attrs + sizeof(struct attribute_group),
+			GFP_KERNEL);
+		if (!perf->attr_group)
+			return -ENOMEM;
+
+		attrs = (struct attribute **)(perf->attr_group + 1);
+		if (!strcmp(perf->block_name, "iommu")) {
+		/* Information of IOMMU's num_counters and counter_ids is shown
+		 * under /sys/bus/event_source/devices/amd_iommu. We don't
+		 * duplicate here.
+		 */
+			perf_attr_iommu[0].data = perf->max_concurrent;
+			for (i = 0; i < num_attrs; i++)
+				attrs[i] = &perf_attr_iommu[i].attr.attr;
+		}
+		perf->attr_group->name = perf->block_name;
+		perf->attr_group->attrs = attrs;
+		ret = sysfs_create_group(dev->kobj_perf, perf->attr_group);
+		if (ret < 0)
+			return ret;
+	}
 
 	return 0;
 }
 
+/* Called with write topology lock acquired */
 static int kfd_build_sysfs_node_tree(void)
 {
 	struct kfd_topology_device *dev;
@@ -924,6 +722,7 @@ static int kfd_build_sysfs_node_tree(void)
 	return 0;
 }
 
+/* Called with write topology lock acquired */
 static void kfd_remove_sysfs_node_tree(void)
 {
 	struct kfd_topology_device *dev;
@@ -995,75 +794,246 @@ static void kfd_topology_release_sysfs(void)
 	}
 }
 
+/* Called with write topology_lock acquired */
+static void kfd_topology_update_device_list(struct list_head *temp_list,
+					struct list_head *master_list)
+{
+	while (!list_empty(temp_list)) {
+		list_move_tail(temp_list->next, master_list);
+		sys_props.num_devices++;
+	}
+}
+
+static void kfd_debug_print_topology(void)
+{
+	struct kfd_topology_device *dev;
+
+	down_read(&topology_lock);
+
+	dev = list_last_entry(&topology_device_list,
+			struct kfd_topology_device, list);
+	if (dev) {
+		if (dev->node_props.cpu_cores_count &&
+				dev->node_props.simd_count) {
+			pr_info("Topology: Add APU node [0x%0x:0x%0x]\n",
+				dev->node_props.device_id,
+				dev->node_props.vendor_id);
+		} else if (dev->node_props.cpu_cores_count)
+			pr_info("Topology: Add CPU node\n");
+		else if (dev->node_props.simd_count)
+			pr_info("Topology: Add dGPU node [0x%0x:0x%0x]\n",
+				dev->node_props.device_id,
+				dev->node_props.vendor_id);
+	}
+	up_read(&topology_lock);
+}
+
+/* Helper function for intializing platform_xx members of
+ * kfd_system_properties. Uses OEM info from the last CPU/APU node.
+ */
+static void kfd_update_system_properties(void)
+{
+	struct kfd_topology_device *dev;
+
+	down_read(&topology_lock);
+	dev = list_last_entry(&topology_device_list,
+			struct kfd_topology_device, list);
+	if (dev) {
+		sys_props.platform_id =
+			(*((uint64_t *)dev->oem_id)) & CRAT_OEMID_64BIT_MASK;
+		sys_props.platform_oem = *((uint64_t *)dev->oem_table_id);
+		sys_props.platform_rev = dev->oem_revision;
+	}
+	up_read(&topology_lock);
+}
+
+static void find_system_memory(const struct dmi_header *dm,
+	void *private)
+{
+	struct kfd_mem_properties *mem;
+	u16 mem_width, mem_clock;
+	struct kfd_topology_device *kdev =
+		(struct kfd_topology_device *)private;
+	const u8 *dmi_data = (const u8 *)(dm + 1);
+
+	if (dm->type == DMI_ENTRY_MEM_DEVICE && dm->length >= 0x15) {
+		mem_width = (u16)(*(const u16 *)(dmi_data + 0x6));
+		mem_clock = (u16)(*(const u16 *)(dmi_data + 0x11));
+		list_for_each_entry(mem, &kdev->mem_props, list) {
+			if (mem_width != 0xFFFF && mem_width != 0)
+				mem->width = mem_width;
+			if (mem_clock != 0)
+				mem->mem_clk_max = mem_clock;
+		}
+	}
+}
+
+/*
+ * Performance counters information is not part of CRAT but we would like to
+ * put them in the sysfs under topology directory for Thunk to get the data.
+ * This function is called before updating the sysfs.
+ */
+static int kfd_add_perf_to_topology(struct kfd_topology_device *kdev)
+{
+	struct kfd_perf_properties *props;
+
+	if (amd_iommu_pc_supported()) {
+		props = kfd_alloc_struct(props);
+		if (!props)
+			return -ENOMEM;
+		strcpy(props->block_name, "iommu");
+		props->max_concurrent = amd_iommu_pc_get_max_banks(0) *
+			amd_iommu_pc_get_max_counters(0); /* assume one iommu */
+		list_add_tail(&props->list, &kdev->perf_props);
+	}
+
+	return 0;
+}
+
+/* kfd_add_non_crat_information - Add information that is not currently
+ *	defined in CRAT but is necessary for KFD topology
+ * @dev - topology device to which addition info is added
+ */
+static void kfd_add_non_crat_information(struct kfd_topology_device *kdev)
+{
+	/* Check if CPU only node. */
+	if (!kdev->gpu) {
+		/* Add system memory information */
+		dmi_walk(find_system_memory, kdev);
+	}
+	/* TODO: For GPU node, rearrange code from kfd_topology_add_device */
+}
+
+/* kfd_is_acpi_crat_invalid - CRAT from ACPI is valid only for AMD APU devices.
+ *	Ignore CRAT for all other devices. AMD APU is identified if both CPU
+ *	and GPU cores are present.
+ * @device_list - topology device list created by parsing ACPI CRAT table.
+ * @return - TRUE if invalid, FALSE is valid.
+ */
+static bool kfd_is_acpi_crat_invalid(struct list_head *device_list)
+{
+	struct kfd_topology_device *dev;
+
+	list_for_each_entry(dev, device_list, list) {
+		if (dev->node_props.cpu_cores_count &&
+			dev->node_props.simd_count)
+			return false;
+	}
+	pr_info("Ignoring ACPI CRAT on non-APU system\n");
+	return true;
+}
+
 int kfd_topology_init(void)
 {
 	void *crat_image = NULL;
 	size_t image_size = 0;
 	int ret;
-
-	/*
-	 * Initialize the head for the topology device list
+	struct list_head temp_topology_device_list;
+	int cpu_only_node = 0;
+	struct kfd_topology_device *kdev;
+	int proximity_domain;
+
+	/* topology_device_list - Master list of all topology devices
+	 * temp_topology_device_list - temporary list created while parsing CRAT
+	 * or VCRAT. Once parsing is complete the contents of list is moved to
+	 * topology_device_list
 	 */
+
+	/* Initialize the head for the both the lists */
 	INIT_LIST_HEAD(&topology_device_list);
+	INIT_LIST_HEAD(&temp_topology_device_list);
 	init_rwsem(&topology_lock);
-	topology_crat_parsed = 0;
 
 	memset(&sys_props, 0, sizeof(sys_props));
 
+	/* Proximity domains in ACPI CRAT tables start counting at
+	 * 0. The same should be true for virtual CRAT tables created
+	 * at this stage. GPUs added later in kfd_topology_add_device
+	 * use a counter.
+	 */
+	proximity_domain = 0;
+
 	/*
-	 * Get the CRAT image from the ACPI
+	 * Get the CRAT image from the ACPI. If ACPI doesn't have one
+	 * or if ACPI CRAT is invalid create a virtual CRAT.
+	 * NOTE: The current implementation expects all AMD APUs to have
+	 *	CRAT. If no CRAT is available, it is assumed to be a CPU
 	 */
-	ret = kfd_topology_get_crat_acpi(crat_image, &image_size);
-	if (ret == 0 && image_size > 0) {
-		pr_info("Found CRAT image with size=%zd\n", image_size);
-		crat_image = kmalloc(image_size, GFP_KERNEL);
-		if (!crat_image) {
-			ret = -ENOMEM;
-			pr_err("No memory for allocating CRAT image\n");
-			goto err;
+	ret = kfd_create_crat_image_acpi(&crat_image, &image_size);
+	if (!ret) {
+		ret = kfd_parse_crat_table(crat_image,
+					   &temp_topology_device_list,
+					   proximity_domain);
+		if (ret ||
+		    kfd_is_acpi_crat_invalid(&temp_topology_device_list)) {
+			kfd_release_topology_device_list(
+				&temp_topology_device_list);
+			kfd_destroy_crat_image(crat_image);
+			crat_image = NULL;
 		}
-		ret = kfd_topology_get_crat_acpi(crat_image, &image_size);
-
-		if (ret == 0) {
-			down_write(&topology_lock);
-			ret = kfd_parse_crat_table(crat_image);
-			if (ret == 0)
-				ret = kfd_topology_update_sysfs();
-			up_write(&topology_lock);
-		} else {
-			pr_err("Couldn't get CRAT table size from ACPI\n");
+	}
+
+	if (!crat_image) {
+		ret = kfd_create_crat_image_virtual(&crat_image, &image_size,
+						    COMPUTE_UNIT_CPU, NULL,
+						    proximity_domain);
+		cpu_only_node = 1;
+		if (ret) {
+			pr_err("Error creating VCRAT table for CPU\n");
+			return ret;
 		}
-		kfree(crat_image);
-	} else if (ret == -ENODATA) {
-		ret = 0;
-	} else {
-		pr_err("Couldn't get CRAT table size from ACPI\n");
+
+		ret = kfd_parse_crat_table(crat_image,
+					   &temp_topology_device_list,
+					   proximity_domain);
+		if (ret) {
+			pr_err("Error parsing VCRAT table for CPU\n");
+			goto err;
+		}
+	}
+
+	kdev = list_first_entry(&temp_topology_device_list,
+				struct kfd_topology_device, list);
+	kfd_add_perf_to_topology(kdev);
+
+	down_write(&topology_lock);
+	kfd_topology_update_device_list(&temp_topology_device_list,
+					&topology_device_list);
+	atomic_set(&topology_crat_proximity_domain, sys_props.num_devices-1);
+	ret = kfd_topology_update_sysfs();
+	up_write(&topology_lock);
+
+	if (!ret) {
+		sys_props.generation_count++;
+		kfd_update_system_properties();
+		kfd_debug_print_topology();
+		pr_info("Finished initializing topology\n");
+	} else
+		pr_err("Failed to update topology in sysfs ret=%d\n", ret);
+
+	/* For nodes with GPU, this information gets added
+	 * when GPU is detected (kfd_topology_add_device).
+	 */
+	if (cpu_only_node) {
+		/* Add additional information to CPU only node created above */
+		down_write(&topology_lock);
+		kdev = list_first_entry(&topology_device_list,
+				struct kfd_topology_device, list);
+		up_write(&topology_lock);
+		kfd_add_non_crat_information(kdev);
 	}
 
 err:
-	pr_info("Finished initializing topology ret=%d\n", ret);
+	kfd_destroy_crat_image(crat_image);
 	return ret;
 }
 
 void kfd_topology_shutdown(void)
 {
+	down_write(&topology_lock);
 	kfd_topology_release_sysfs();
 	kfd_release_live_view();
-}
-
-static void kfd_debug_print_topology(void)
-{
-	struct kfd_topology_device *dev;
-	uint32_t i = 0;
-
-	pr_info("DEBUG PRINT OF TOPOLOGY:");
-	list_for_each_entry(dev, &topology_device_list, list) {
-		pr_info("Node: %d\n", i);
-		pr_info("\tGPU assigned: %s\n", (dev->gpu ? "yes" : "no"));
-		pr_info("\tCPU count: %d\n", dev->node_props.cpu_cores_count);
-		pr_info("\tSIMD count: %d", dev->node_props.simd_count);
-		i++;
-	}
+	up_write(&topology_lock);
 }
 
 static uint32_t kfd_generate_gpu_id(struct kfd_dev *gpu)
@@ -1072,11 +1042,15 @@ static uint32_t kfd_generate_gpu_id(struct kfd_dev *gpu)
 	uint32_t buf[7];
 	uint64_t local_mem_size;
 	int i;
+	struct kfd_local_mem_info local_mem_info;
 
 	if (!gpu)
 		return 0;
 
-	local_mem_size = gpu->kfd2kgd->get_vmem_size(gpu->kgd);
+	gpu->kfd2kgd->get_local_mem_info(gpu->kgd, &local_mem_info);
+
+	local_mem_size = local_mem_info.local_mem_size_private +
+			local_mem_info.local_mem_size_public;
 
 	buf[0] = gpu->pdev->devfn;
 	buf[1] = gpu->pdev->subsystem_vendor;
@@ -1091,19 +1065,26 @@ static uint32_t kfd_generate_gpu_id(struct kfd_dev *gpu)
 
 	return hashout;
 }
-
+/* kfd_assign_gpu - Attach @gpu to the correct kfd topology device. If
+ *		the GPU device is not already present in the topology device
+ *		list then return NULL. This means a new topology device has to
+ *		be created for this GPU.
+ * TODO: Rather than assiging @gpu to first topology device withtout
+ *		gpu attached, it will better to have more stringent check.
+ */
 static struct kfd_topology_device *kfd_assign_gpu(struct kfd_dev *gpu)
 {
 	struct kfd_topology_device *dev;
 	struct kfd_topology_device *out_dev = NULL;
 
+	down_write(&topology_lock);
 	list_for_each_entry(dev, &topology_device_list, list)
 		if (!dev->gpu && (dev->node_props.simd_count > 0)) {
 			dev->gpu = gpu;
 			out_dev = dev;
 			break;
 		}
-
+	up_write(&topology_lock);
 	return out_dev;
 }
 
@@ -1115,84 +1096,196 @@ static void kfd_notify_gpu_change(uint32_t gpu_id, int arrival)
 	 */
 }
 
+/* kfd_fill_mem_clk_max_info - Since CRAT doesn't have memory clock info,
+ *		patch this after CRAT parsing.
+ */
+static void kfd_fill_mem_clk_max_info(struct kfd_topology_device *dev)
+{
+	struct kfd_mem_properties *mem;
+	struct kfd_local_mem_info local_mem_info;
+
+	if (!dev)
+		return;
+
+	/* Currently, amdgpu driver (amdgpu_mc) deals only with GPUs with
+	 * single bank of VRAM local memory.
+	 * for dGPUs - VCRAT reports only one bank of Local Memory
+	 * for APUs - If CRAT from ACPI reports more than one bank, then
+	 *	all the banks will report the same mem_clk_max information
+	 */
+	dev->gpu->kfd2kgd->get_local_mem_info(dev->gpu->kgd,
+		&local_mem_info);
+
+	list_for_each_entry(mem, &dev->mem_props, list)
+		mem->mem_clk_max = local_mem_info.mem_clk_max;
+}
+
+static void kfd_fill_iolink_non_crat_info(struct kfd_topology_device *dev)
+{
+	struct kfd_iolink_properties *link;
+
+	if (!dev || !dev->gpu)
+		return;
+
+	/* GPU only creates direck links so apply flags setting to all */
+	if (dev->gpu->device_info->asic_family == CHIP_HAWAII)
+		list_for_each_entry(link, &dev->io_link_props, list)
+			link->flags = CRAT_IOLINK_FLAGS_ENABLED |
+				CRAT_IOLINK_FLAGS_NO_ATOMICS_32_BIT |
+				CRAT_IOLINK_FLAGS_NO_ATOMICS_64_BIT;
+}
+
 int kfd_topology_add_device(struct kfd_dev *gpu)
 {
 	uint32_t gpu_id;
 	struct kfd_topology_device *dev;
-	int res;
+	struct kfd_cu_info cu_info;
+	int res = 0;
+	struct list_head temp_topology_device_list;
+	void *crat_image = NULL;
+	size_t image_size = 0;
+	int proximity_domain;
+
+	INIT_LIST_HEAD(&temp_topology_device_list);
 
 	gpu_id = kfd_generate_gpu_id(gpu);
 
 	pr_debug("Adding new GPU (ID: 0x%x) to topology\n", gpu_id);
 
-	down_write(&topology_lock);
-	/*
-	 * Try to assign the GPU to existing topology device (generated from
-	 * CRAT table
+	proximity_domain = atomic_inc_return(&topology_crat_proximity_domain);
+
+	/* Check to see if this gpu device exists in the topology_device_list.
+	 * If so, assign the gpu to that device,
+	 * else create a Virtual CRAT for this gpu device and then parse that
+	 * CRAT to create a new topology device. Once created assign the gpu to
+	 * that topology device
 	 */
 	dev = kfd_assign_gpu(gpu);
 	if (!dev) {
-		pr_info("GPU was not found in the current topology. Extending.\n");
-		kfd_debug_print_topology();
-		dev = kfd_create_topology_device();
-		if (!dev) {
-			res = -ENOMEM;
+		res = kfd_create_crat_image_virtual(&crat_image, &image_size,
+						    COMPUTE_UNIT_GPU, gpu,
+						    proximity_domain);
+		if (res) {
+			pr_err("Error creating VCRAT for GPU (ID: 0x%x)\n",
+			       gpu_id);
+			return res;
+		}
+		res = kfd_parse_crat_table(crat_image,
+					   &temp_topology_device_list,
+					   proximity_domain);
+		if (res) {
+			pr_err("Error parsing VCRAT for GPU (ID: 0x%x)\n",
+			       gpu_id);
 			goto err;
 		}
-		dev->gpu = gpu;
 
-		/*
-		 * TODO: Make a call to retrieve topology information from the
-		 * GPU vBIOS
-		 */
+		down_write(&topology_lock);
+		kfd_topology_update_device_list(&temp_topology_device_list,
+			&topology_device_list);
 
 		/* Update the SYSFS tree, since we added another topology
 		 * device
 		 */
-		if (kfd_topology_update_sysfs() < 0)
-			kfd_topology_release_sysfs();
-
+		res = kfd_topology_update_sysfs();
+		up_write(&topology_lock);
+
+		if (!res)
+			sys_props.generation_count++;
+		else
+			pr_err("Failed to update GPU (ID: 0x%x) to sysfs topology. res=%d\n",
+						gpu_id, res);
+		dev = kfd_assign_gpu(gpu);
+		if (WARN_ON(!dev)) {
+			res = -ENODEV;
+			goto err;
+		}
 	}
 
 	dev->gpu_id = gpu_id;
 	gpu->id = gpu_id;
+
+	/* TODO: Move the following lines to function
+	 *	kfd_add_non_crat_information
+	 */
+
+	/* Fill-in additional information that is not available in CRAT but
+	 * needed for the topology
+	 */
+
+	dev->gpu->kfd2kgd->get_cu_info(dev->gpu->kgd, &cu_info);
+	dev->node_props.simd_arrays_per_engine =
+		cu_info.num_shader_arrays_per_engine;
+
 	dev->node_props.vendor_id = gpu->pdev->vendor;
 	dev->node_props.device_id = gpu->pdev->device;
-	dev->node_props.location_id = (gpu->pdev->bus->number << 24) +
-			(gpu->pdev->devfn & 0xffffff);
-	/*
-	 * TODO: Retrieve max engine clock values from KGD
-	 */
+	dev->node_props.location_id = PCI_DEVID(gpu->pdev->bus->number,
+		gpu->pdev->devfn);
+	dev->node_props.max_engine_clk_fcompute =
+		dev->gpu->kfd2kgd->get_max_engine_clock_in_mhz(dev->gpu->kgd);
+	dev->node_props.max_engine_clk_ccompute =
+		cpufreq_quick_get_max(0) / 1000;
+
+	kfd_fill_mem_clk_max_info(dev);
+	kfd_fill_iolink_non_crat_info(dev);
+
+	switch (dev->gpu->device_info->asic_family) {
+	case CHIP_KAVERI:
+	case CHIP_HAWAII:
+	case CHIP_TONGA:
+		dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_PRE_1_0 <<
+			HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) &
+			HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK);
+		break;
+	case CHIP_CARRIZO:
+	case CHIP_FIJI:
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+		pr_debug("Adding doorbell packet type capability\n");
+		dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_1_0 <<
+			HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) &
+			HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK);
+		break;
+	default:
+		WARN(1, "Unexpected ASIC family %u",
+		     dev->gpu->device_info->asic_family);
+	}
 
+	/* Fix errors in CZ CRAT.
+	 * simd_count: Carrizo CRAT reports wrong simd_count, probably
+	 *		because it doesn't consider masked out CUs
+	 * max_waves_per_simd: Carrizo reports wrong max_waves_per_simd
+	 * capability flag: Carrizo CRAT doesn't report IOMMU flags
+	 */
 	if (dev->gpu->device_info->asic_family == CHIP_CARRIZO) {
-		dev->node_props.capability |= HSA_CAP_DOORBELL_PACKET_TYPE;
-		pr_info("Adding doorbell packet type capability\n");
+		dev->node_props.simd_count =
+			cu_info.simd_per_cu * cu_info.cu_active_number;
+		dev->node_props.max_waves_per_simd = 10;
+		dev->node_props.capability |= HSA_CAP_ATS_PRESENT;
 	}
 
-	res = 0;
-
-err:
-	up_write(&topology_lock);
+	kfd_debug_print_topology();
 
-	if (res == 0)
+	if (!res)
 		kfd_notify_gpu_change(gpu_id, 1);
-
+err:
+	kfd_destroy_crat_image(crat_image);
 	return res;
 }
 
 int kfd_topology_remove_device(struct kfd_dev *gpu)
 {
-	struct kfd_topology_device *dev;
+	struct kfd_topology_device *dev, *tmp;
 	uint32_t gpu_id;
 	int res = -ENODEV;
 
 	down_write(&topology_lock);
 
-	list_for_each_entry(dev, &topology_device_list, list)
+	list_for_each_entry_safe(dev, tmp, &topology_device_list, list)
 		if (dev->gpu == gpu) {
 			gpu_id = dev->gpu_id;
 			kfd_remove_sysfs_node_entry(dev);
 			kfd_release_topology_device(dev);
+			sys_props.num_devices--;
 			res = 0;
 			if (kfd_topology_update_sysfs() < 0)
 				kfd_topology_release_sysfs();
@@ -1201,28 +1294,32 @@ int kfd_topology_remove_device(struct kfd_dev *gpu)
 
 	up_write(&topology_lock);
 
-	if (res == 0)
+	if (!res)
 		kfd_notify_gpu_change(gpu_id, 0);
 
 	return res;
 }
 
-/*
- * When idx is out of bounds, the function will return NULL
+/* kfd_topology_enum_kfd_devices - Enumerate through all devices in KFD
+ *	topology. If GPU device is found @idx, then valid kfd_dev pointer is
+ *	returned through @kdev
+ * Return -	0: On success (@kdev will be NULL for non GPU nodes)
+ *		-1: If end of list
  */
-struct kfd_dev *kfd_topology_enum_kfd_devices(uint8_t idx)
+int kfd_topology_enum_kfd_devices(uint8_t idx, struct kfd_dev **kdev)
 {
 
 	struct kfd_topology_device *top_dev;
-	struct kfd_dev *device = NULL;
 	uint8_t device_idx = 0;
 
+	*kdev = NULL;
 	down_read(&topology_lock);
 
 	list_for_each_entry(top_dev, &topology_device_list, list) {
 		if (device_idx == idx) {
-			device = top_dev->gpu;
-			break;
+			*kdev = top_dev->gpu;
+			up_read(&topology_lock);
+			return 0;
 		}
 
 		device_idx++;
@@ -1230,6 +1327,88 @@ struct kfd_dev *kfd_topology_enum_kfd_devices(uint8_t idx)
 
 	up_read(&topology_lock);
 
-	return device;
+	return -1;
+
+}
+
+static int kfd_cpumask_to_apic_id(const struct cpumask *cpumask)
+{
+	const struct cpuinfo_x86 *cpuinfo;
+	int first_cpu_of_numa_node;
+
+	if (!cpumask || cpumask == cpu_none_mask)
+		return -1;
+	first_cpu_of_numa_node = cpumask_first(cpumask);
+	if (first_cpu_of_numa_node >= nr_cpu_ids)
+		return -1;
+	cpuinfo = &cpu_data(first_cpu_of_numa_node);
 
+	return cpuinfo->apicid;
 }
+
+/* kfd_numa_node_to_apic_id - Returns the APIC ID of the first logical processor
+ *	of the given NUMA node (numa_node_id)
+ * Return -1 on failure
+ */
+int kfd_numa_node_to_apic_id(int numa_node_id)
+{
+	if (numa_node_id == -1) {
+		pr_warn("Invalid NUMA Node. Use online CPU mask\n");
+		return kfd_cpumask_to_apic_id(cpu_online_mask);
+	}
+	return kfd_cpumask_to_apic_id(cpumask_of_node(numa_node_id));
+}
+
+#if defined(CONFIG_DEBUG_FS)
+
+int kfd_debugfs_hqds_by_device(struct seq_file *m, void *data)
+{
+	struct kfd_topology_device *dev;
+	unsigned int i = 0;
+	int r = 0;
+
+	down_read(&topology_lock);
+
+	list_for_each_entry(dev, &topology_device_list, list) {
+		if (!dev->gpu) {
+			i++;
+			continue;
+		}
+
+		seq_printf(m, "Node %u, gpu_id %x:\n", i++, dev->gpu->id);
+		r = dqm_debugfs_hqds(m, dev->gpu->dqm);
+		if (r)
+			break;
+	}
+
+	up_read(&topology_lock);
+
+	return r;
+}
+
+int kfd_debugfs_rls_by_device(struct seq_file *m, void *data)
+{
+	struct kfd_topology_device *dev;
+	unsigned int i = 0;
+	int r = 0;
+
+	down_read(&topology_lock);
+
+	list_for_each_entry(dev, &topology_device_list, list) {
+		if (!dev->gpu) {
+			i++;
+			continue;
+		}
+
+		seq_printf(m, "Node %u, gpu_id %x:\n", i++, dev->gpu->id);
+		r = pm_debugfs_runlist(m, &dev->gpu->dqm->packets);
+		if (r)
+			break;
+	}
+
+	up_read(&topology_lock);
+
+	return r;
+}
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
index c3ddb9b95ff8..53fca1f45401 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
@@ -39,8 +39,13 @@
 #define HSA_CAP_WATCH_POINTS_SUPPORTED		0x00000080
 #define HSA_CAP_WATCH_POINTS_TOTALBITS_MASK	0x00000f00
 #define HSA_CAP_WATCH_POINTS_TOTALBITS_SHIFT	8
-#define HSA_CAP_RESERVED			0xfffff000
-#define HSA_CAP_DOORBELL_PACKET_TYPE		0x00001000
+#define HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK	0x00003000
+#define HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT	12
+#define HSA_CAP_RESERVED			0xffffc000
+
+#define HSA_CAP_DOORBELL_TYPE_PRE_1_0		0x0
+#define HSA_CAP_DOORBELL_TYPE_1_0		0x1
+#define HSA_CAP_AQL_QUEUE_DOUBLE_MAP		0x00004000
 
 struct kfd_node_properties {
 	uint32_t cpu_cores_count;
@@ -91,8 +96,6 @@ struct kfd_mem_properties {
 	struct attribute	attr;
 };
 
-#define KFD_TOPOLOGY_CPU_SIBLINGS 256
-
 #define HSA_CACHE_TYPE_DATA		0x00000001
 #define HSA_CACHE_TYPE_INSTRUCTION	0x00000002
 #define HSA_CACHE_TYPE_CPU		0x00000004
@@ -109,7 +112,7 @@ struct kfd_cache_properties {
 	uint32_t		cache_assoc;
 	uint32_t		cache_latency;
 	uint32_t		cache_type;
-	uint8_t			sibling_map[KFD_TOPOLOGY_CPU_SIBLINGS];
+	uint8_t			sibling_map[CRAT_SIBLINGMAP_SIZE];
 	struct kobject		*kobj;
 	struct attribute	attr;
 };
@@ -132,24 +135,36 @@ struct kfd_iolink_properties {
 	struct attribute	attr;
 };
 
+struct kfd_perf_properties {
+	struct list_head	list;
+	char			block_name[16];
+	uint32_t		max_concurrent;
+	struct attribute_group	*attr_group;
+};
+
 struct kfd_topology_device {
 	struct list_head		list;
 	uint32_t			gpu_id;
+	uint32_t			proximity_domain;
 	struct kfd_node_properties	node_props;
-	uint32_t			mem_bank_count;
 	struct list_head		mem_props;
 	uint32_t			cache_count;
 	struct list_head		cache_props;
 	uint32_t			io_link_count;
 	struct list_head		io_link_props;
+	struct list_head		perf_props;
 	struct kfd_dev			*gpu;
 	struct kobject			*kobj_node;
 	struct kobject			*kobj_mem;
 	struct kobject			*kobj_cache;
 	struct kobject			*kobj_iolink;
+	struct kobject			*kobj_perf;
 	struct attribute		attr_gpuid;
 	struct attribute		attr_name;
 	struct attribute		attr_props;
+	uint8_t				oem_id[CRAT_OEMID_LENGTH];
+	uint8_t				oem_table_id[CRAT_OEMTABLEID_LENGTH];
+	uint32_t			oem_revision;
 };
 
 struct kfd_system_properties {
@@ -164,6 +179,12 @@ struct kfd_system_properties {
 	struct attribute	attr_props;
 };
 
+struct kfd_topology_device *kfd_create_topology_device(
+		struct list_head *device_list);
+void kfd_release_topology_device_list(struct list_head *device_list);
 
+extern bool amd_iommu_pc_supported(void);
+extern u8 amd_iommu_pc_get_max_banks(u16 devid);
+extern u8 amd_iommu_pc_get_max_counters(u16 devid);
 
 #endif /* __KFD_TOPOLOGY_H__ */
diff --git a/drivers/gpu/drm/amd/display/Makefile b/drivers/gpu/drm/amd/display/Makefile
index 8ba37dd9cf7f..c27c81cdeed3 100644
--- a/drivers/gpu/drm/amd/display/Makefile
+++ b/drivers/gpu/drm/amd/display/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the DAL (Display Abstract Layer), which is a  sub-component
 # of the AMDGPU drm driver.
 # It provides the HW control for display related functionalities.
diff --git a/drivers/gpu/drm/amd/display/TODO b/drivers/gpu/drm/amd/display/TODO
index 46464678f2b3..357d59648401 100644
--- a/drivers/gpu/drm/amd/display/TODO
+++ b/drivers/gpu/drm/amd/display/TODO
@@ -105,3 +105,6 @@ useless with filtering output. dynamic debug printing might be an option.
 20. Use kernel i2c device to program HDMI retimer. Some boards have an HDMI
 retimer that we need to program to pass PHY compliance. Currently that's
 bypassing the i2c device and goes directly to HW. This should be changed.
+
+21. Remove vector.c from dc/basics. It's used in DDC code which can probably
+be simplified enough to no longer need a vector implementation.
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
index 4699e47aa76b..2b72009844f8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'dm' sub-component of DAL.
 # It provides the control and status of dm blocks.
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 889ed24084e8..1ce4c98385e3 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -59,9 +59,9 @@
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 #include "ivsrcid/irqsrcs_dcn_1_0.h"
 
-#include "raven1/DCN/dcn_1_0_offset.h"
-#include "raven1/DCN/dcn_1_0_sh_mask.h"
-#include "vega10/soc15ip.h"
+#include "dcn/dcn_1_0_offset.h"
+#include "dcn/dcn_1_0_sh_mask.h"
+#include "soc15ip.h"
 
 #include "soc15_common.h"
 #endif
@@ -431,9 +431,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	adev->dm.dc = dc_create(&init_data);
 
 	if (adev->dm.dc) {
-		DRM_INFO("Display Core initialized!\n");
+		DRM_INFO("Display Core initialized with v%s!\n", DC_VER);
 	} else {
-		DRM_INFO("Display Core failed to initialize!\n");
+		DRM_INFO("Display Core failed to initialize with v%s!\n", DC_VER);
 		goto error;
 	}
 
@@ -520,7 +520,8 @@ static int detect_mst_link_for_all_connectors(struct drm_device *dev)
 
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		aconnector = to_amdgpu_dm_connector(connector);
-		if (aconnector->dc_link->type == dc_connection_mst_branch) {
+		if (aconnector->dc_link->type == dc_connection_mst_branch &&
+		    aconnector->mst_mgr.aux) {
 			DRM_DEBUG_DRIVER("DM_MST: starting TM on aconnector: %p [id: %d]\n",
 					aconnector, aconnector->base.base.id);
 
@@ -677,6 +678,10 @@ int amdgpu_dm_display_resume(struct amdgpu_device *adev)
 
 		mutex_lock(&aconnector->hpd_lock);
 		dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD);
+
+		if (aconnector->fake_enable && aconnector->dc_link->local_sink)
+			aconnector->fake_enable = false;
+
 		aconnector->dc_sink = NULL;
 		amdgpu_dm_update_connector_after_detect(aconnector);
 		mutex_unlock(&aconnector->hpd_lock);
@@ -711,7 +716,6 @@ int amdgpu_dm_display_resume(struct amdgpu_device *adev)
 
 	ret = drm_atomic_helper_resume(ddev, adev->dm.cached_state);
 
-	drm_atomic_state_put(adev->dm.cached_state);
 	adev->dm.cached_state = NULL;
 
 	amdgpu_dm_irq_resume_late(adev);
@@ -788,7 +792,7 @@ dm_atomic_state_alloc_free(struct drm_atomic_state *state)
 
 static const struct drm_mode_config_funcs amdgpu_dm_mode_funcs = {
 	.fb_create = amdgpu_user_framebuffer_create,
-	.output_poll_changed = amdgpu_output_poll_changed,
+	.output_poll_changed = drm_fb_helper_output_poll_changed,
 	.atomic_check = amdgpu_dm_atomic_check,
 	.atomic_commit = amdgpu_dm_atomic_commit,
 	.atomic_state_alloc = dm_atomic_state_alloc,
@@ -1586,7 +1590,6 @@ static int dm_early_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	adev->ddev->driver->driver_features |= DRIVER_ATOMIC;
-	amdgpu_dm_set_irq_funcs(adev);
 
 	switch (adev->asic_type) {
 	case CHIP_BONAIRE:
@@ -1660,6 +1663,8 @@ static int dm_early_init(void *handle)
 		return -EINVAL;
 	}
 
+	amdgpu_dm_set_irq_funcs(adev);
+
 	if (adev->mode_info.funcs == NULL)
 		adev->mode_info.funcs = &dm_display_funcs;
 
@@ -1675,18 +1680,6 @@ static int dm_early_init(void *handle)
 	return 0;
 }
 
-struct dm_connector_state {
-	struct drm_connector_state base;
-
-	enum amdgpu_rmx_type scaling;
-	uint8_t underscan_vborder;
-	uint8_t underscan_hborder;
-	bool underscan_enable;
-};
-
-#define to_dm_connector_state(x)\
-	container_of((x), struct dm_connector_state, base)
-
 static bool modeset_required(struct drm_crtc_state *crtc_state,
 			     struct dc_stream_state *new_stream,
 			     struct dc_stream_state *old_stream)
@@ -1769,8 +1762,7 @@ static bool fill_rects_from_plane_state(const struct drm_plane_state *state,
 	return true;
 }
 static int get_fb_info(const struct amdgpu_framebuffer *amdgpu_fb,
-		       uint64_t *tiling_flags,
-		       uint64_t *fb_location)
+		       uint64_t *tiling_flags)
 {
 	struct amdgpu_bo *rbo = gem_to_amdgpu_bo(amdgpu_fb->obj);
 	int r = amdgpu_bo_reserve(rbo, false);
@@ -1782,9 +1774,6 @@ static int get_fb_info(const struct amdgpu_framebuffer *amdgpu_fb,
 		return r;
 	}
 
-	if (fb_location)
-		*fb_location = amdgpu_bo_gpu_offset(rbo);
-
 	if (tiling_flags)
 		amdgpu_bo_get_tiling_flags(rbo, tiling_flags);
 
@@ -1795,12 +1784,9 @@ static int get_fb_info(const struct amdgpu_framebuffer *amdgpu_fb,
 
 static int fill_plane_attributes_from_fb(struct amdgpu_device *adev,
 					 struct dc_plane_state *plane_state,
-					 const struct amdgpu_framebuffer *amdgpu_fb,
-					 bool addReq)
+					 const struct amdgpu_framebuffer *amdgpu_fb)
 {
 	uint64_t tiling_flags;
-	uint64_t fb_location = 0;
-	uint64_t chroma_addr = 0;
 	unsigned int awidth;
 	const struct drm_framebuffer *fb = &amdgpu_fb->base;
 	int ret = 0;
@@ -1808,8 +1794,7 @@ static int fill_plane_attributes_from_fb(struct amdgpu_device *adev,
 
 	ret = get_fb_info(
 		amdgpu_fb,
-		&tiling_flags,
-		addReq == true ? &fb_location:NULL);
+		&tiling_flags);
 
 	if (ret)
 		return ret;
@@ -1847,8 +1832,6 @@ static int fill_plane_attributes_from_fb(struct amdgpu_device *adev,
 
 	if (plane_state->format < SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) {
 		plane_state->address.type = PLN_ADDR_TYPE_GRAPHICS;
-		plane_state->address.grph.addr.low_part = lower_32_bits(fb_location);
-		plane_state->address.grph.addr.high_part = upper_32_bits(fb_location);
 		plane_state->plane_size.grph.surface_size.x = 0;
 		plane_state->plane_size.grph.surface_size.y = 0;
 		plane_state->plane_size.grph.surface_size.width = fb->width;
@@ -1861,15 +1844,6 @@ static int fill_plane_attributes_from_fb(struct amdgpu_device *adev,
 	} else {
 		awidth = ALIGN(fb->width, 64);
 		plane_state->address.type = PLN_ADDR_TYPE_VIDEO_PROGRESSIVE;
-		plane_state->address.video_progressive.luma_addr.low_part
-						= lower_32_bits(fb_location);
-		plane_state->address.video_progressive.luma_addr.high_part
-						= upper_32_bits(fb_location);
-		chroma_addr = fb_location + (u64)(awidth * fb->height);
-		plane_state->address.video_progressive.chroma_addr.low_part
-						= lower_32_bits(chroma_addr);
-		plane_state->address.video_progressive.chroma_addr.high_part
-						= upper_32_bits(chroma_addr);
 		plane_state->plane_size.video.luma_size.x = 0;
 		plane_state->plane_size.video.luma_size.y = 0;
 		plane_state->plane_size.video.luma_size.width = awidth;
@@ -1979,8 +1953,7 @@ static void fill_gamma_from_crtc_state(const struct drm_crtc_state *crtc_state,
 static int fill_plane_attributes(struct amdgpu_device *adev,
 				 struct dc_plane_state *dc_plane_state,
 				 struct drm_plane_state *plane_state,
-				 struct drm_crtc_state *crtc_state,
-				 bool addrReq)
+				 struct drm_crtc_state *crtc_state)
 {
 	const struct amdgpu_framebuffer *amdgpu_fb =
 		to_amdgpu_framebuffer(plane_state->fb);
@@ -1994,8 +1967,7 @@ static int fill_plane_attributes(struct amdgpu_device *adev,
 	ret = fill_plane_attributes_from_fb(
 		crtc->dev->dev_private,
 		dc_plane_state,
-		amdgpu_fb,
-		addrReq);
+		amdgpu_fb);
 
 	if (ret)
 		return ret;
@@ -2170,6 +2142,7 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 					     const struct drm_connector *connector)
 {
 	struct dc_crtc_timing *timing_out = &stream->timing;
+	struct dc_transfer_func *tf = dc_create_transfer_func();
 
 	memset(timing_out, 0, sizeof(struct dc_crtc_timing));
 
@@ -2213,13 +2186,9 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 
 	stream->output_color_space = get_output_color_space(timing_out);
 
-	{
-		struct dc_transfer_func *tf = dc_create_transfer_func();
-
-		tf->type = TF_TYPE_PREDEFINED;
-		tf->tf = TRANSFER_FUNCTION_SRGB;
-		stream->out_transfer_func = tf;
-	}
+	tf->type = TF_TYPE_PREDEFINED;
+	tf->tf = TRANSFER_FUNCTION_SRGB;
+	stream->out_transfer_func = tf;
 }
 
 static void fill_audio_info(struct audio_info *audio_info,
@@ -2326,13 +2295,63 @@ static int create_fake_sink(struct amdgpu_dm_connector *aconnector)
 	return 0;
 }
 
+static void set_multisync_trigger_params(
+		struct dc_stream_state *stream)
+{
+	if (stream->triggered_crtc_reset.enabled) {
+		stream->triggered_crtc_reset.event = CRTC_EVENT_VSYNC_RISING;
+		stream->triggered_crtc_reset.delay = TRIGGER_DELAY_NEXT_LINE;
+	}
+}
+
+static void set_master_stream(struct dc_stream_state *stream_set[],
+			      int stream_count)
+{
+	int j, highest_rfr = 0, master_stream = 0;
+
+	for (j = 0;  j < stream_count; j++) {
+		if (stream_set[j] && stream_set[j]->triggered_crtc_reset.enabled) {
+			int refresh_rate = 0;
+
+			refresh_rate = (stream_set[j]->timing.pix_clk_khz*1000)/
+				(stream_set[j]->timing.h_total*stream_set[j]->timing.v_total);
+			if (refresh_rate > highest_rfr) {
+				highest_rfr = refresh_rate;
+				master_stream = j;
+			}
+		}
+	}
+	for (j = 0;  j < stream_count; j++) {
+		if (stream_set[j] && j != master_stream)
+			stream_set[j]->triggered_crtc_reset.event_source = stream_set[master_stream];
+	}
+}
+
+static void dm_enable_per_frame_crtc_master_sync(struct dc_state *context)
+{
+	int i = 0;
+
+	if (context->stream_count < 2)
+		return;
+	for (i = 0; i < context->stream_count ; i++) {
+		if (!context->streams[i])
+			continue;
+		/* TODO: add a function to read AMD VSDB bits and will set
+		 * crtc_sync_master.multi_sync_enabled flag
+		 * For now its set to false
+		 */
+		set_multisync_trigger_params(context->streams[i]);
+	}
+	set_master_stream(context->streams, context->stream_count);
+}
+
 static struct dc_stream_state *
 create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 		       const struct drm_display_mode *drm_mode,
 		       const struct dm_connector_state *dm_state)
 {
 	struct drm_display_mode *preferred_mode = NULL;
-	const struct drm_connector *drm_connector;
+	struct drm_connector *drm_connector;
 	struct dc_stream_state *stream = NULL;
 	struct drm_display_mode mode = *drm_mode;
 	bool native_mode_found = false;
@@ -2351,11 +2370,13 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 
 	if (!aconnector->dc_sink) {
 		/*
-		 * Exclude MST from creating fake_sink
-		 * TODO: need to enable MST into fake_sink feature
+		 * Create dc_sink when necessary to MST
+		 * Don't apply fake_sink to MST
 		 */
-		if (aconnector->mst_port)
-			goto stream_create_fail;
+		if (aconnector->mst_port) {
+			dm_dp_mst_dc_sink_create(drm_connector);
+			goto mst_dc_sink_create_done;
+		}
 
 		if (create_fake_sink(aconnector))
 			goto stream_create_fail;
@@ -2406,6 +2427,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 stream_create_fail:
 dm_state_null:
 drm_connector_null:
+mst_dc_sink_create_done:
 	return stream;
 }
 
@@ -2704,10 +2726,9 @@ static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
 			.link = aconnector->dc_link,
 			.sink_signal = SIGNAL_TYPE_VIRTUAL
 	};
-	struct edid *edid = (struct edid *) aconnector->base.edid_blob_ptr->data;
+	struct edid *edid;
 
-	if (!aconnector->base.edid_blob_ptr ||
-		!aconnector->base.edid_blob_ptr->data) {
+	if (!aconnector->base.edid_blob_ptr) {
 		DRM_ERROR("No EDID firmware found on connector: %s ,forcing to OFF!\n",
 				aconnector->base.name);
 
@@ -2716,6 +2737,8 @@ static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
 		return;
 	}
 
+	edid = (struct edid *) aconnector->base.edid_blob_ptr->data;
+
 	aconnector->edid = edid;
 
 	aconnector->dc_em_sink = dc_link_add_remote_sink(
@@ -2980,7 +3003,7 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 							= lower_32_bits(afb->address);
 			plane_state->address.video_progressive.luma_addr.high_part
 							= upper_32_bits(afb->address);
-			chroma_addr = afb->address + (u64)(awidth * new_state->fb->height);
+			chroma_addr = afb->address + (u64)awidth * new_state->fb->height;
 			plane_state->address.video_progressive.chroma_addr.low_part
 							= lower_32_bits(chroma_addr);
 			plane_state->address.video_progressive.chroma_addr.high_part
@@ -3327,8 +3350,6 @@ static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector,
 		amdgpu_dm_connector->num_modes =
 				drm_add_edid_modes(connector, edid);
 
-		drm_edid_to_eld(connector, edid);
-
 		amdgpu_dm_get_native_mode(connector);
 	} else {
 		amdgpu_dm_connector->num_modes = 0;
@@ -3990,6 +4011,19 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 	}
 }
 
+/**
+ * amdgpu_dm_crtc_copy_transient_flags - copy mirrored flags from DRM to DC
+ * @crtc_state: the DRM CRTC state
+ * @stream_state: the DC stream state.
+ *
+ * Copy the mirrored transient state flags from DRM, to DC. It is used to bring
+ * a dc_stream_state's flags in sync with a drm_crtc_state's flags.
+ */
+static void amdgpu_dm_crtc_copy_transient_flags(struct drm_crtc_state *crtc_state,
+						struct dc_stream_state *stream_state)
+{
+	stream_state->mode_changed = crtc_state->mode_changed;
+}
 
 static int amdgpu_dm_atomic_commit(struct drm_device *dev,
 				   struct drm_atomic_state *state,
@@ -4029,11 +4063,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	struct amdgpu_display_manager *dm = &adev->dm;
 	struct dm_atomic_state *dm_state;
 	uint32_t i, j;
-	uint32_t new_crtcs_count = 0;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
-	struct amdgpu_crtc *new_crtcs[MAX_STREAMS];
-	struct dc_stream_state *new_stream = NULL;
 	unsigned long flags;
 	bool wait_for_vblank = true;
 	struct drm_connector *connector;
@@ -4063,6 +4094,12 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 			new_crtc_state->active_changed,
 			new_crtc_state->connectors_changed);
 
+		/* Copy all transient state flags into dc state */
+		if (dm_new_crtc_state->stream) {
+			amdgpu_dm_crtc_copy_transient_flags(&dm_new_crtc_state->base,
+							    dm_new_crtc_state->stream);
+		}
+
 		/* handles headless hotplug case, updating new_state and
 		 * aconnector as needed
 		 */
@@ -4092,25 +4129,9 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 				continue;
 			}
 
-
 			if (dm_old_crtc_state->stream)
 				remove_stream(adev, acrtc, dm_old_crtc_state->stream);
 
-
-			/*
-			 * this loop saves set mode crtcs
-			 * we needed to enable vblanks once all
-			 * resources acquired in dc after dc_commit_streams
-			 */
-
-			/*TODO move all this into dm_crtc_state, get rid of
-			 * new_crtcs array and use old and new atomic states
-			 * instead
-			 */
-			new_crtcs[new_crtcs_count] = acrtc;
-			new_crtcs_count++;
-
-			new_crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
 			acrtc->enabled = true;
 			acrtc->hw_mode = new_crtc_state->mode;
 			crtc->hwmode = new_crtc_state->mode;
@@ -4128,31 +4149,61 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	 * are removed from freesync module
 	 */
 	if (adev->dm.freesync_module) {
-		for (i = 0; i < new_crtcs_count; i++) {
+		for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
+					      new_crtc_state, i) {
 			struct amdgpu_dm_connector *aconnector = NULL;
+			struct dm_connector_state *dm_new_con_state = NULL;
+			struct amdgpu_crtc *acrtc = NULL;
+			bool modeset_needed;
 
-			new_crtc_state = drm_atomic_get_new_crtc_state(state,
-					&new_crtcs[i]->base);
 			dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
+			dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
+			modeset_needed = modeset_required(
+					new_crtc_state,
+					dm_new_crtc_state->stream,
+					dm_old_crtc_state->stream);
+			/* We add stream to freesync if:
+			 * 1. Said stream is not null, and
+			 * 2. A modeset is requested. This means that the
+			 *    stream was removed previously, and needs to be
+			 *    replaced.
+			 */
+			if (dm_new_crtc_state->stream == NULL ||
+					!modeset_needed)
+				continue;
+
+			acrtc = to_amdgpu_crtc(crtc);
 
-			new_stream = dm_new_crtc_state->stream;
-			aconnector = amdgpu_dm_find_first_crtc_matching_connector(
-					state,
-					&new_crtcs[i]->base);
+			aconnector =
+				amdgpu_dm_find_first_crtc_matching_connector(
+					state, crtc);
 			if (!aconnector) {
-				DRM_DEBUG_DRIVER("Atomic commit: Failed to find connector for acrtc id:%d "
-					 "skipping freesync init\n",
-					 new_crtcs[i]->crtc_id);
+				DRM_DEBUG_DRIVER("Atomic commit: Failed to "
+						 "find connector for acrtc "
+						 "id:%d skipping freesync "
+						 "init\n",
+						 acrtc->crtc_id);
 				continue;
 			}
 
 			mod_freesync_add_stream(adev->dm.freesync_module,
-						new_stream, &aconnector->caps);
+						dm_new_crtc_state->stream,
+						&aconnector->caps);
+			new_con_state = drm_atomic_get_new_connector_state(
+					state, &aconnector->base);
+			dm_new_con_state = to_dm_connector_state(new_con_state);
+
+			mod_freesync_set_user_enable(adev->dm.freesync_module,
+						     &dm_new_crtc_state->stream,
+						     1,
+						     &dm_new_con_state->user_enable);
 		}
 	}
 
-	if (dm_state->context)
+	if (dm_state->context) {
+		dm_enable_per_frame_crtc_master_sync(dm_state->context);
 		WARN_ON(!dc_commit_state(dm->dc, dm_state->context));
+	}
 
 	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
@@ -4193,13 +4244,13 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		update_stream_scaling_settings(&dm_new_con_state->base.crtc->mode,
 				dm_new_con_state, (struct dc_stream_state *)dm_new_crtc_state->stream);
 
+		if (!dm_new_crtc_state->stream)
+			continue;
+
 		status = dc_stream_get_status(dm_new_crtc_state->stream);
 		WARN_ON(!status);
 		WARN_ON(!status->plane_count);
 
-		if (!dm_new_crtc_state->stream)
-			continue;
-
 		/*TODO How it works with MPO ?*/
 		if (!dc_commit_planes_to_stream(
 				dm->dc,
@@ -4210,18 +4261,28 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 			dm_error("%s: Failed to update stream scaling!\n", __func__);
 	}
 
-	for (i = 0; i < new_crtcs_count; i++) {
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
+			new_crtc_state, i) {
 		/*
 		 * loop to enable interrupts on newly arrived crtc
 		 */
-		struct amdgpu_crtc *acrtc = new_crtcs[i];
+		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
+		bool modeset_needed;
 
-		new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base);
 		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
+		dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
+		modeset_needed = modeset_required(
+				new_crtc_state,
+				dm_new_crtc_state->stream,
+				dm_old_crtc_state->stream);
+
+		if (dm_new_crtc_state->stream == NULL || !modeset_needed)
+			continue;
 
 		if (adev->dm.freesync_module)
 			mod_freesync_notify_mode_change(
-				adev->dm.freesync_module, &dm_new_crtc_state->stream, 1);
+				adev->dm.freesync_module,
+				&dm_new_crtc_state->stream, 1);
 
 		manage_dm_interrupts(adev, acrtc, true);
 	}
@@ -4253,7 +4314,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	drm_atomic_helper_commit_hw_done(state);
 
 	if (wait_for_vblank)
-		drm_atomic_helper_wait_for_vblanks(dev, state);
+		drm_atomic_helper_wait_for_flip_done(dev, state);
 
 	drm_atomic_helper_cleanup_planes(dev, state);
 }
@@ -4332,9 +4393,11 @@ void dm_restore_drm_connector_state(struct drm_device *dev,
 		return;
 
 	disconnected_acrtc = to_amdgpu_crtc(connector->encoder->crtc);
-	acrtc_state = to_dm_crtc_state(disconnected_acrtc->base.state);
+	if (!disconnected_acrtc)
+		return;
 
-	if (!disconnected_acrtc || !acrtc_state->stream)
+	acrtc_state = to_dm_crtc_state(disconnected_acrtc->base.state);
+	if (!acrtc_state->stream)
 		return;
 
 	/*
@@ -4453,18 +4516,15 @@ static int dm_update_crtcs_state(struct dc *dc,
 						__func__, acrtc->base.base.id);
 				break;
 			}
-		}
-
-		if (dc_is_stream_unchanged(new_stream, dm_old_crtc_state->stream) &&
-				dc_is_stream_scaling_unchanged(new_stream, dm_old_crtc_state->stream)) {
-
-			new_crtc_state->mode_changed = false;
 
-			DRM_DEBUG_DRIVER("Mode change not required, setting mode_changed to %d",
-				         new_crtc_state->mode_changed);
+			if (dc_is_stream_unchanged(new_stream, dm_old_crtc_state->stream) &&
+			    dc_is_stream_scaling_unchanged(new_stream, dm_old_crtc_state->stream)) {
+				new_crtc_state->mode_changed = false;
+				DRM_DEBUG_DRIVER("Mode change not required, setting mode_changed to %d",
+						 new_crtc_state->mode_changed);
+			}
 		}
 
-
 		if (!drm_atomic_crtc_needs_modeset(new_crtc_state))
 			goto next_crtc;
 
@@ -4521,6 +4581,7 @@ static int dm_update_crtcs_state(struct dc *dc,
 				WARN_ON(dm_new_crtc_state->stream);
 
 				dm_new_crtc_state->stream = new_stream;
+
 				dc_stream_retain(new_stream);
 
 				DRM_DEBUG_DRIVER("Enabling DRM crtc: %d\n",
@@ -4646,8 +4707,7 @@ static int dm_update_planes_state(struct dc *dc,
 				new_plane_crtc->dev->dev_private,
 				dm_new_plane_state->dc_state,
 				new_plane_state,
-				new_crtc_state,
-				false);
+				new_crtc_state);
 			if (ret)
 				return ret;
 
@@ -4662,6 +4722,11 @@ static int dm_update_planes_state(struct dc *dc,
 				return ret;
 			}
 
+			/* Tell DC to do a full surface update every time there
+			 * is a plane change. Inefficient, but works for now.
+			 */
+			dm_new_plane_state->dc_state->update_flags.bits.full_update = 1;
+
 			*lock_and_validation_needed = true;
 		}
 	}
@@ -4673,8 +4738,6 @@ static int dm_update_planes_state(struct dc *dc,
 static int amdgpu_dm_atomic_check(struct drm_device *dev,
 				  struct drm_atomic_state *state)
 {
-	int i;
-	int ret;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct dc *dc = adev->dm.dc;
 	struct dm_atomic_state *dm_state = to_dm_atomic_state(state);
@@ -4682,6 +4745,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 	struct drm_connector_state *old_con_state, *new_con_state;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	int ret, i;
 
 	/*
 	 * This bool will be set for true for any modeset/reset
@@ -4693,36 +4757,21 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 	if (ret)
 		goto fail;
 
-	/*
-	 * legacy_cursor_update should be made false for SoC's having
-	 * a dedicated hardware plane for cursor in amdgpu_dm_atomic_commit(),
-	 * otherwise for software cursor plane,
-	 * we should not add it to list of affected planes.
-	 */
-	if (state->legacy_cursor_update) {
-		for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
-			if (new_crtc_state->color_mgmt_changed) {
-				ret = drm_atomic_add_affected_planes(state, crtc);
-				if (ret)
-					goto fail;
-			}
-		}
-	} else {
-		for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
-			if (!drm_atomic_crtc_needs_modeset(new_crtc_state))
-				continue;
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		if (!drm_atomic_crtc_needs_modeset(new_crtc_state) &&
+		    !new_crtc_state->color_mgmt_changed)
+			continue;
 
-			if (!new_crtc_state->enable)
-				continue;
+		if (!new_crtc_state->enable)
+			continue;
 
-			ret = drm_atomic_add_affected_connectors(state, crtc);
-			if (ret)
-				return ret;
+		ret = drm_atomic_add_affected_connectors(state, crtc);
+		if (ret)
+			return ret;
 
-			ret = drm_atomic_add_affected_planes(state, crtc);
-			if (ret)
-				goto fail;
-		}
+		ret = drm_atomic_add_affected_planes(state, crtc);
+		if (ret)
+			goto fail;
 	}
 
 	dm_state->context = dc_create_state();
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 117521c6a6ed..2faa77a7eeda 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -189,6 +189,8 @@ struct amdgpu_dm_connector {
 	struct mutex hpd_lock;
 
 	bool fake_enable;
+
+	bool mst_connected;
 };
 
 #define to_amdgpu_dm_connector(x) container_of(x, struct amdgpu_dm_connector, base)
@@ -220,6 +222,18 @@ struct dm_atomic_state {
 
 #define to_dm_atomic_state(x) container_of(x, struct dm_atomic_state, base)
 
+struct dm_connector_state {
+	struct drm_connector_state base;
+
+	enum amdgpu_rmx_type scaling;
+	uint8_t underscan_vborder;
+	uint8_t underscan_hborder;
+	bool underscan_enable;
+	struct mod_freesync_user_enable user_enable;
+};
+
+#define to_dm_connector_state(x)\
+	container_of((x), struct dm_connector_state, base)
 
 void amdgpu_dm_connector_funcs_reset(struct drm_connector *connector);
 struct drm_connector_state *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index ca5d0d1581dc..1874b6cee6af 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -683,13 +683,16 @@ static const struct amdgpu_irq_src_funcs dm_hpd_irq_funcs = {
 
 void amdgpu_dm_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_LAST;
+	if (adev->mode_info.num_crtc > 0)
+		adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VLINE1 + adev->mode_info.num_crtc;
+	else
+		adev->crtc_irq.num_types = 0;
 	adev->crtc_irq.funcs = &dm_crtc_irq_funcs;
 
-	adev->pageflip_irq.num_types = AMDGPU_PAGEFLIP_IRQ_LAST;
+	adev->pageflip_irq.num_types = adev->mode_info.num_crtc;
 	adev->pageflip_irq.funcs = &dm_pageflip_irq_funcs;
 
-	adev->hpd_irq.num_types = AMDGPU_HPD_LAST;
+	adev->hpd_irq.num_types = adev->mode_info.num_hpd;
 	adev->hpd_irq.funcs = &dm_hpd_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index f8efb98b1fa7..f3d87f418d2e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -177,12 +177,43 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = {
 static int dm_connector_update_modes(struct drm_connector *connector,
 				struct edid *edid)
 {
-	int ret;
+	return drm_add_edid_modes(connector, edid);
+}
+
+void dm_dp_mst_dc_sink_create(struct drm_connector *connector)
+{
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+	struct edid *edid;
+	struct dc_sink *dc_sink;
+	struct dc_sink_init_data init_params = {
+			.link = aconnector->dc_link,
+			.sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
 
-	ret = drm_add_edid_modes(connector, edid);
-	drm_edid_to_eld(connector, edid);
+	edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port);
 
-	return ret;
+	if (!edid) {
+		drm_mode_connector_update_edid_property(
+			&aconnector->base,
+			NULL);
+		return;
+	}
+
+	aconnector->edid = edid;
+
+	dc_sink = dc_link_add_remote_sink(
+		aconnector->dc_link,
+		(uint8_t *)aconnector->edid,
+		(aconnector->edid->extensions + 1) * EDID_LENGTH,
+		&init_params);
+
+	dc_sink->priv = aconnector;
+	aconnector->dc_sink = dc_sink;
+
+	amdgpu_dm_add_sink_to_freesync_module(
+			connector, aconnector->edid);
+
+	drm_mode_connector_update_edid_property(
+					&aconnector->base, aconnector->edid);
 }
 
 static int dm_dp_mst_get_modes(struct drm_connector *connector)
@@ -311,6 +342,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 			drm_mode_connector_set_path_property(connector, pathprop);
 
 			drm_connector_list_iter_end(&conn_iter);
+			aconnector->mst_connected = true;
 			return &aconnector->base;
 		}
 	}
@@ -363,6 +395,8 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	 */
 	amdgpu_dm_connector_funcs_reset(connector);
 
+	aconnector->mst_connected = true;
+
 	DRM_INFO("DM_MST: added connector: %p [id: %d] [master: %p]\n",
 			aconnector, connector->base.id, aconnector->mst_port);
 
@@ -394,6 +428,8 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	drm_mode_connector_update_edid_property(
 			&aconnector->base,
 			NULL);
+
+	aconnector->mst_connected = false;
 }
 
 static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
@@ -404,10 +440,18 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
 	drm_kms_helper_hotplug_event(dev);
 }
 
+static void dm_dp_mst_link_status_reset(struct drm_connector *connector)
+{
+	mutex_lock(&connector->dev->mode_config.mutex);
+	drm_mode_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD);
+	mutex_unlock(&connector->dev->mode_config.mutex);
+}
+
 static void dm_dp_mst_register_connector(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 
 	if (adev->mode_info.rfbdev)
 		drm_fb_helper_add_one_connector(&adev->mode_info.rfbdev->helper, connector);
@@ -416,6 +460,8 @@ static void dm_dp_mst_register_connector(struct drm_connector *connector)
 
 	drm_connector_register(connector);
 
+	if (aconnector->mst_connected)
+		dm_dp_mst_link_status_reset(connector);
 }
 
 static const struct drm_dp_mst_topology_cbs dm_mst_cbs = {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index 2da851b40042..8cf51da26657 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -31,5 +31,6 @@ struct amdgpu_dm_connector;
 
 void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 				       struct amdgpu_dm_connector *aconnector);
+void dm_dp_mst_dc_sink_create(struct drm_connector *connector);
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index 5df8fd5b537c..56e549249134 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -41,6 +41,10 @@ unsigned long long dm_get_timestamp(struct dc_context *ctx)
 	return 0;
 }
 
+void dm_perf_trace_timestamp(const char *func_name, unsigned int line)
+{
+}
+
 bool dm_write_persistent_data(struct dc_context *ctx,
 		const struct dc_sink *sink,
 		const char *module_name,
@@ -131,11 +135,12 @@ bool dm_pp_apply_display_requirements(
 		adev->pm.pm_display_cfg.min_bus_bandwidth = 0;
 
 		/* TODO: complete implementation of
-		 * amd_powerplay_display_configuration_change().
+		 * pp_display_configuration_change().
 		 * Follow example of:
 		 * PHM_StoreDALConfigurationData - powerplay\hwmgr\hardwaremanager.c
 		 * PP_IRI_DisplayConfigurationChange - powerplay\eventmgr\iri.c */
-		amd_powerplay_display_configuration_change(
+		if (adev->powerplay.pp_funcs->display_configuration_change)
+			adev->powerplay.pp_funcs->display_configuration_change(
 				adev->powerplay.pp_handle,
 				&adev->pm.pm_display_cfg);
 
@@ -264,22 +269,26 @@ bool dm_pp_get_clock_levels_by_type(
 	struct amd_pp_simple_clock_info validation_clks = { 0 };
 	uint32_t i;
 
-	if (amd_powerplay_get_clock_by_type(pp_handle,
+	if (adev->powerplay.pp_funcs->get_clock_by_type) {
+		if (adev->powerplay.pp_funcs->get_clock_by_type(pp_handle,
 			dc_to_pp_clock_type(clk_type), &pp_clks)) {
 		/* Error in pplib. Provide default values. */
-		get_default_clock_levels(clk_type, dc_clks);
-		return true;
+			get_default_clock_levels(clk_type, dc_clks);
+			return true;
+		}
 	}
 
 	pp_to_dc_clock_levels(&pp_clks, dc_clks, clk_type);
 
-	if (amd_powerplay_get_display_mode_validation_clocks(pp_handle,
-			&validation_clks)) {
-		/* Error in pplib. Provide default values. */
-		DRM_INFO("DM_PPLIB: Warning: using default validation clocks!\n");
-		validation_clks.engine_max_clock = 72000;
-		validation_clks.memory_max_clock = 80000;
-		validation_clks.level = 0;
+	if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks) {
+		if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks(
+						pp_handle, &validation_clks)) {
+			/* Error in pplib. Provide default values. */
+			DRM_INFO("DM_PPLIB: Warning: using default validation clocks!\n");
+			validation_clks.engine_max_clock = 72000;
+			validation_clks.memory_max_clock = 80000;
+			validation_clks.level = 0;
+		}
 	}
 
 	DRM_INFO("DM_PPLIB: Validation clocks:\n");
diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index 4f83e3011743..aed538a4d1ba 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for Display Core (dc) component.
 #
 
diff --git a/drivers/gpu/drm/amd/display/dc/basics/Makefile b/drivers/gpu/drm/amd/display/dc/basics/Makefile
index 43c5ccdeeb72..bca33bd9a0d2 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/basics/Makefile
@@ -1,9 +1,30 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'utils' sub-component of DAL.
 # It provides the general basic services required by other DAL
 # subcomponents.
 
-BASICS = conversion.o fixpt31_32.o fixpt32_32.o grph_object_id.o \
+BASICS = conversion.o fixpt31_32.o fixpt32_32.o \
 	logger.o log_helpers.o vector.o
 
 AMD_DAL_BASICS = $(addprefix $(AMDDALPATH)/dc/basics/,$(BASICS))
diff --git a/drivers/gpu/drm/amd/display/dc/basics/conversion.c b/drivers/gpu/drm/amd/display/dc/basics/conversion.c
index 23c9a0ec0181..310964915a83 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/conversion.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/conversion.c
@@ -46,7 +46,7 @@ uint16_t fixed_point_to_int_frac(
 			arg));
 
 	if (d <= (uint16_t)(1 << integer_bits) - (1 / (uint16_t)divisor))
-		numerator = (uint16_t)dal_fixed31_32_floor(
+		numerator = (uint16_t)dal_fixed31_32_round(
 			dal_fixed31_32_mul_int(
 				arg,
 				divisor));
diff --git a/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c b/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c
index 26936892c6f5..011a97f82fb6 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c
@@ -554,6 +554,22 @@ static inline uint32_t ux_dy(
 	return result | fractional_part;
 }
 
+static inline uint32_t clamp_ux_dy(
+	int64_t value,
+	uint32_t integer_bits,
+	uint32_t fractional_bits,
+	uint32_t min_clamp)
+{
+	uint32_t truncated_val = ux_dy(value, integer_bits, fractional_bits);
+
+	if (value >= (1LL << (integer_bits + FIXED31_32_BITS_PER_FRACTIONAL_PART)))
+		return (1 << (integer_bits + fractional_bits)) - 1;
+	else if (truncated_val > min_clamp)
+		return truncated_val;
+	else
+		return min_clamp;
+}
+
 uint32_t dal_fixed31_32_u2d19(
 	struct fixed31_32 arg)
 {
@@ -565,3 +581,15 @@ uint32_t dal_fixed31_32_u0d19(
 {
 	return ux_dy(arg.value, 0, 19);
 }
+
+uint32_t dal_fixed31_32_clamp_u0d14(
+	struct fixed31_32 arg)
+{
+	return clamp_ux_dy(arg.value, 0, 14, 1);
+}
+
+uint32_t dal_fixed31_32_clamp_u0d10(
+	struct fixed31_32 arg)
+{
+	return clamp_ux_dy(arg.value, 0, 10, 1);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
index 785b943b60ed..854678a0c54b 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
@@ -75,20 +75,19 @@ void dc_conn_log(struct dc_context *ctx,
 		if (signal == signal_type_info_tbl[i].type)
 			break;
 
+	if (i == NUM_ELEMENTS(signal_type_info_tbl))
+		goto fail;
+
 	dm_logger_append(&entry, "[%s][ConnIdx:%d] ",
 			signal_type_info_tbl[i].name,
 			link->link_index);
 
 	va_start(args, msg);
-	entry.buf_offset += dm_log_to_buffer(
-		&entry.buf[entry.buf_offset],
-		LOG_MAX_LINE_SIZE - entry.buf_offset,
-		msg, args);
+	dm_logger_append_va(&entry, msg, args);
 
-	if (entry.buf[strlen(entry.buf) - 1] == '\n') {
-		entry.buf[strlen(entry.buf) - 1] = '\0';
+	if (entry.buf_offset > 0 &&
+	    entry.buf[entry.buf_offset - 1] == '\n')
 		entry.buf_offset--;
-	}
 
 	if (hex_data)
 		for (i = 0; i < hex_data_count; i++)
@@ -96,6 +95,8 @@ void dc_conn_log(struct dc_context *ctx,
 
 	dm_logger_append(&entry, "^\n");
 	dm_helpers_dc_conn_log(ctx, &entry, event);
+
+fail:
 	dm_logger_close(&entry);
 
 	va_end(args);
diff --git a/drivers/gpu/drm/amd/display/dc/basics/logger.c b/drivers/gpu/drm/amd/display/dc/basics/logger.c
index e04e8ecd4874..180a9d69d351 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/logger.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/logger.c
@@ -70,9 +70,8 @@ static bool construct(struct dc_context *ctx, struct dal_logger *logger,
 {
 	/* malloc buffer and init offsets */
 	logger->log_buffer_size = DAL_LOGGER_BUFFER_MAX_SIZE;
-	logger->log_buffer = (char *)kzalloc(logger->log_buffer_size * sizeof(char),
-					     GFP_KERNEL);
-
+	logger->log_buffer = kcalloc(logger->log_buffer_size, sizeof(char),
+				     GFP_KERNEL);
 	if (!logger->log_buffer)
 		return false;
 
@@ -313,6 +312,18 @@ void dm_logger_append(
 	const char *msg,
 	...)
 {
+	va_list args;
+
+	va_start(args, msg);
+	dm_logger_append_va(entry, msg, args);
+	va_end(args);
+}
+
+void dm_logger_append_va(
+	struct log_entry *entry,
+	const char *msg,
+	va_list args)
+{
 	struct dal_logger *logger;
 
 	if (!entry) {
@@ -326,11 +337,8 @@ void dm_logger_append(
 		dal_logger_should_log(logger, entry->type)) {
 
 		uint32_t size;
-		va_list args;
 		char buffer[LOG_MAX_LINE_SIZE];
 
-		va_start(args, msg);
-
 		size = dm_log_to_buffer(
 			buffer, LOG_MAX_LINE_SIZE, msg, args);
 
@@ -339,8 +347,6 @@ void dm_logger_append(
 		} else {
 			append_entry(entry, "LOG_ERROR, line too long\n", 27);
 		}
-
-		va_end(args);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/Makefile b/drivers/gpu/drm/amd/display/dc/bios/Makefile
index 6ec815dce9cc..239e86bbec5a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/bios/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'bios' sub-component of DAL.
 # It provides the parsing and executing controls for atom bios image.
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
index aaaebd06d7ee..c00e405b63e8 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -190,6 +190,7 @@ static struct graphics_object_id bios_parser_get_connector_id(
 	struct bios_parser *bp = BP_FROM_DCB(dcb);
 	struct graphics_object_id object_id = dal_graphics_object_id_init(
 		0, ENUM_ID_UNKNOWN, OBJECT_TYPE_UNKNOWN);
+	uint16_t id;
 
 	uint32_t connector_table_offset = bp->object_info_tbl_offset
 		+ le16_to_cpu(bp->object_info_tbl.v1_1->usConnectorObjectTableOffset);
@@ -197,12 +198,19 @@ static struct graphics_object_id bios_parser_get_connector_id(
 	ATOM_OBJECT_TABLE *tbl =
 		GET_IMAGE(ATOM_OBJECT_TABLE, connector_table_offset);
 
-	if (tbl && tbl->ucNumberOfObjects > i) {
-		const uint16_t id = le16_to_cpu(tbl->asObjects[i].usObjectID);
+	if (!tbl) {
+		dm_error("Can't get connector table from atom bios.\n");
+		return object_id;
+	}
 
-		object_id = object_id_from_bios_object_id(id);
+	if (tbl->ucNumberOfObjects <= i) {
+		dm_error("Can't find connector id %d in connector table of size %d.\n",
+			 i, tbl->ucNumberOfObjects);
+		return object_id;
 	}
 
+	id = le16_to_cpu(tbl->asObjects[i].usObjectID);
+	object_id = object_id_from_bios_object_id(id);
 	return object_id;
 }
 
@@ -249,7 +257,7 @@ static enum bp_result bios_parser_get_dst_obj(struct dc_bios *dcb,
 	struct graphics_object_id *dest_object_id)
 {
 	uint32_t number;
-	uint16_t *id;
+	uint16_t *id = NULL;
 	ATOM_OBJECT *object;
 	struct bios_parser *bp = BP_FROM_DCB(dcb);
 
@@ -260,7 +268,7 @@ static enum bp_result bios_parser_get_dst_obj(struct dc_bios *dcb,
 
 	number = get_dest_obj_list(bp, object, &id);
 
-	if (number <= index)
+	if (number <= index || !id)
 		return BP_RESULT_BADINPUT;
 
 	*dest_object_id = object_id_from_bios_object_id(id[index]);
@@ -2254,6 +2262,52 @@ static enum bp_result get_gpio_i2c_info(struct bios_parser *bp,
 	return BP_RESULT_OK;
 }
 
+static bool dal_graphics_object_id_is_valid(struct graphics_object_id id)
+{
+	bool rc = true;
+
+	switch (id.type) {
+	case OBJECT_TYPE_UNKNOWN:
+		rc = false;
+		break;
+	case OBJECT_TYPE_GPU:
+	case OBJECT_TYPE_ENGINE:
+		/* do NOT check for id.id == 0 */
+		if (id.enum_id == ENUM_ID_UNKNOWN)
+			rc = false;
+		break;
+	default:
+		if (id.id == 0 || id.enum_id == ENUM_ID_UNKNOWN)
+			rc = false;
+		break;
+	}
+
+	return rc;
+}
+
+static bool dal_graphics_object_id_is_equal(
+	struct graphics_object_id id1,
+	struct graphics_object_id id2)
+{
+	if (false == dal_graphics_object_id_is_valid(id1)) {
+		dm_output_to_console(
+		"%s: Warning: comparing invalid object 'id1'!\n", __func__);
+		return false;
+	}
+
+	if (false == dal_graphics_object_id_is_valid(id2)) {
+		dm_output_to_console(
+		"%s: Warning: comparing invalid object 'id2'!\n", __func__);
+		return false;
+	}
+
+	if (id1.id == id2.id && id1.enum_id == id2.enum_id
+		&& id1.type == id2.type)
+		return true;
+
+	return false;
+}
+
 static ATOM_OBJECT *get_bios_object(struct bios_parser *bp,
 	struct graphics_object_id id)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
index 3f7b2dabc2b0..4b5fdd577848 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
@@ -387,6 +387,7 @@ static void init_transmitter_control(struct bios_parser *bp)
 		bp->cmd_tbl.transmitter_control = transmitter_control_v1_6;
 		break;
 	default:
+		dm_output_to_console("Don't have transmitter_control for v%d\n", crev);
 		bp->cmd_tbl.transmitter_control = NULL;
 		break;
 	}
@@ -910,6 +911,8 @@ static void init_set_pixel_clock(struct bios_parser *bp)
 		bp->cmd_tbl.set_pixel_clock = set_pixel_clock_v7;
 		break;
 	default:
+		dm_output_to_console("Don't have set_pixel_clock for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(SetPixelClock));
 		bp->cmd_tbl.set_pixel_clock = NULL;
 		break;
 	}
@@ -1227,6 +1230,8 @@ static void init_enable_spread_spectrum_on_ppll(struct bios_parser *bp)
 				enable_spread_spectrum_on_ppll_v3;
 		break;
 	default:
+		dm_output_to_console("Don't have enable_spread_spectrum_on_ppll for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(EnableSpreadSpectrumOnPPLL));
 		bp->cmd_tbl.enable_spread_spectrum_on_ppll = NULL;
 		break;
 	}
@@ -1422,6 +1427,8 @@ static void init_adjust_display_pll(struct bios_parser *bp)
 		bp->cmd_tbl.adjust_display_pll = adjust_display_pll_v3;
 		break;
 	default:
+		dm_output_to_console("Don't have adjust_display_pll for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(AdjustDisplayPll));
 		bp->cmd_tbl.adjust_display_pll = NULL;
 		break;
 	}
@@ -1695,6 +1702,8 @@ static void init_set_crtc_timing(struct bios_parser *bp)
 					set_crtc_using_dtd_timing_v3;
 			break;
 		default:
+			dm_output_to_console("Don't have set_crtc_timing for dtd v%d\n",
+				 dtd_version);
 			bp->cmd_tbl.set_crtc_timing = NULL;
 			break;
 		}
@@ -1704,6 +1713,8 @@ static void init_set_crtc_timing(struct bios_parser *bp)
 			bp->cmd_tbl.set_crtc_timing = set_crtc_timing_v1;
 			break;
 		default:
+			dm_output_to_console("Don't have set_crtc_timing for v%d\n",
+				 BIOS_CMD_TABLE_PARA_REVISION(SetCRTC_Timing));
 			bp->cmd_tbl.set_crtc_timing = NULL;
 			break;
 		}
@@ -1890,6 +1901,8 @@ static void init_select_crtc_source(struct bios_parser *bp)
 		bp->cmd_tbl.select_crtc_source = select_crtc_source_v3;
 		break;
 	default:
+		dm_output_to_console("Don't select_crtc_source enable_crtc for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(SelectCRTC_Source));
 		bp->cmd_tbl.select_crtc_source = NULL;
 		break;
 	}
@@ -1997,6 +2010,8 @@ static void init_enable_crtc(struct bios_parser *bp)
 		bp->cmd_tbl.enable_crtc = enable_crtc_v1;
 		break;
 	default:
+		dm_output_to_console("Don't have enable_crtc for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(EnableCRTC));
 		bp->cmd_tbl.enable_crtc = NULL;
 		break;
 	}
@@ -2103,6 +2118,8 @@ static void init_program_clock(struct bios_parser *bp)
 		bp->cmd_tbl.program_clock = program_clock_v6;
 		break;
 	default:
+		dm_output_to_console("Don't have program_clock for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(SetPixelClock));
 		bp->cmd_tbl.program_clock = NULL;
 		break;
 	}
@@ -2324,6 +2341,8 @@ static void init_enable_disp_power_gating(
 				enable_disp_power_gating_v2_1;
 		break;
 	default:
+		dm_output_to_console("Don't enable_disp_power_gating enable_crtc for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(EnableDispPowerGating));
 		bp->cmd_tbl.enable_disp_power_gating = NULL;
 		break;
 	}
@@ -2371,6 +2390,8 @@ static void init_set_dce_clock(struct bios_parser *bp)
 		bp->cmd_tbl.set_dce_clock = set_dce_clock_v2_1;
 		break;
 	default:
+		dm_output_to_console("Don't have set_dce_clock for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(SetDCEClock));
 		bp->cmd_tbl.set_dce_clock = NULL;
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
index ba68693758a7..fea5e83736fd 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
@@ -118,6 +118,7 @@ static void init_dig_encoder_control(struct bios_parser *bp)
 		bp->cmd_tbl.dig_encoder_control = encoder_control_digx_v1_5;
 		break;
 	default:
+		dm_output_to_console("Don't have dig_encoder_control for v%d\n", version);
 		bp->cmd_tbl.dig_encoder_control = NULL;
 		break;
 	}
@@ -205,6 +206,7 @@ static void init_transmitter_control(struct bios_parser *bp)
 		bp->cmd_tbl.transmitter_control = transmitter_control_v1_6;
 		break;
 	default:
+		dm_output_to_console("Don't have transmitter_control for v%d\n", crev);
 		bp->cmd_tbl.transmitter_control = NULL;
 		break;
 	}
@@ -268,6 +270,8 @@ static void init_set_pixel_clock(struct bios_parser *bp)
 		bp->cmd_tbl.set_pixel_clock = set_pixel_clock_v7;
 		break;
 	default:
+		dm_output_to_console("Don't have set_pixel_clock for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(setpixelclock));
 		bp->cmd_tbl.set_pixel_clock = NULL;
 		break;
 	}
@@ -379,6 +383,7 @@ static void init_set_crtc_timing(struct bios_parser *bp)
 			set_crtc_using_dtd_timing_v3;
 		break;
 	default:
+		dm_output_to_console("Don't have set_crtc_timing for v%d\n", dtd_version);
 		bp->cmd_tbl.set_crtc_timing = NULL;
 		break;
 	}
@@ -498,6 +503,8 @@ static void init_select_crtc_source(struct bios_parser *bp)
 		bp->cmd_tbl.select_crtc_source = select_crtc_source_v3;
 		break;
 	default:
+		dm_output_to_console("Don't select_crtc_source enable_crtc for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(selectcrtc_source));
 		bp->cmd_tbl.select_crtc_source = NULL;
 		break;
 	}
@@ -565,6 +572,8 @@ static void init_enable_crtc(struct bios_parser *bp)
 		bp->cmd_tbl.enable_crtc = enable_crtc_v1;
 		break;
 	default:
+		dm_output_to_console("Don't have enable_crtc for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(enablecrtc));
 		bp->cmd_tbl.enable_crtc = NULL;
 		break;
 	}
@@ -661,6 +670,8 @@ static void init_enable_disp_power_gating(
 				enable_disp_power_gating_v2_1;
 		break;
 	default:
+		dm_output_to_console("Don't enable_disp_power_gating enable_crtc for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(enabledisppowergating));
 		bp->cmd_tbl.enable_disp_power_gating = NULL;
 		break;
 	}
@@ -710,6 +721,8 @@ static void init_set_dce_clock(struct bios_parser *bp)
 		bp->cmd_tbl.set_dce_clock = set_dce_clock_v2_1;
 		break;
 	default:
+		dm_output_to_console("Don't have set_dce_clock for v%d\n",
+			 BIOS_CMD_TABLE_PARA_REVISION(setdceclock));
 		bp->cmd_tbl.set_dce_clock = NULL;
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 41ef35995b02..7959e382ed28 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'calcs' sub-component of DAL.
 # It calculates Bandwidth and Watermarks values for HW programming
 #
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
index 6347712db834..2e11fac2a63d 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
@@ -29,6 +29,15 @@
 #include "core_types.h"
 #include "dal_asic_id.h"
 
+/*
+ * NOTE:
+ *   This file is gcc-parseable HW gospel, coming straight from HW engineers.
+ *
+ * It doesn't adhere to Linux kernel style and sometimes will do things in odd
+ * ways. Unless there is something clearly wrong with it the code should
+ * remain as-is as it provides us with a guarantee from HW that it is correct.
+ */
+
 /*******************************************************************************
  * Private Functions
  ******************************************************************************/
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_auto.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_auto.c
index 626f9cf8aad2..5e2ea12fbb73 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_auto.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_auto.c
@@ -27,6 +27,15 @@
 #include "dcn_calc_auto.h"
 #include "dcn_calc_math.h"
 
+/*
+ * NOTE:
+ *   This file is gcc-parseable HW gospel, coming straight from HW engineers.
+ *
+ * It doesn't adhere to Linux kernel style and sometimes will do things in odd
+ * ways. Unless there is something clearly wrong with it the code should
+ * remain as-is as it provides us with a guarantee from HW that it is correct.
+ */
+
 /*REVISION#250*/
 void scaler_settings_calculation(struct dcn_bw_internal_vars *v)
 {
@@ -773,11 +782,11 @@ void mode_support_and_system_configuration(struct dcn_bw_internal_vars *v)
 					v->dst_y_after_scaler = 0.0;
 				}
 				v->time_calc = 24.0 / v->projected_dcfclk_deep_sleep;
-				v->v_update_offset[k] =dcn_bw_ceil2(v->htotal[k] / 4.0, 1.0);
+				v->v_update_offset[k][j] = dcn_bw_ceil2(v->htotal[k] / 4.0, 1.0);
 				v->total_repeater_delay = v->max_inter_dcn_tile_repeaters * (2.0 / (v->required_dispclk[i][j] / (j + 1)) + 3.0 / v->required_dispclk[i][j]);
-				v->v_update_width[k] = (14.0 / v->projected_dcfclk_deep_sleep + 12.0 / (v->required_dispclk[i][j] / (j + 1)) + v->total_repeater_delay) * v->pixel_clock[k];
-				v->v_ready_offset[k] =dcn_bw_max2(150.0 / (v->required_dispclk[i][j] / (j + 1)), v->total_repeater_delay + 20.0 / v->projected_dcfclk_deep_sleep + 10.0 / (v->required_dispclk[i][j] / (j + 1))) * v->pixel_clock[k];
-				v->time_setup = (v->v_update_offset[k] + v->v_update_width[k] + v->v_ready_offset[k]) / v->pixel_clock[k];
+				v->v_update_width[k][j] = (14.0 / v->projected_dcfclk_deep_sleep + 12.0 / (v->required_dispclk[i][j] / (j + 1)) + v->total_repeater_delay) * v->pixel_clock[k];
+				v->v_ready_offset[k][j] = dcn_bw_max2(150.0 / (v->required_dispclk[i][j] / (j + 1)), v->total_repeater_delay + 20.0 / v->projected_dcfclk_deep_sleep + 10.0 / (v->required_dispclk[i][j] / (j + 1))) * v->pixel_clock[k];
+				v->time_setup = (v->v_update_offset[k][j] + v->v_update_width[k][j] + v->v_ready_offset[k][j]) / v->pixel_clock[k];
 				v->extra_latency = v->urgent_round_trip_and_out_of_order_latency_per_state[i] + (v->total_number_of_active_dpp[i][j] * v->pixel_chunk_size_in_kbyte + v->total_number_of_dcc_active_dpp[i][j] * v->meta_chunk_size) * 1024.0 / v->return_bw_per_state[i];
 				if (v->pte_enable == dcn_bw_yes) {
 					v->extra_latency = v->extra_latency + v->total_number_of_active_dpp[i][j] * v->pte_chunk_size * 1024.0 / v->return_bw_per_state[i];
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.c
index b6abe0f3bb15..7600a4a4abc7 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.c
@@ -25,37 +25,44 @@
 
 #include "dcn_calc_math.h"
 
+#define isNaN(number) ((number) != (number))
+
+/*
+ * NOTE:
+ *   This file is gcc-parseable HW gospel, coming straight from HW engineers.
+ *
+ * It doesn't adhere to Linux kernel style and sometimes will do things in odd
+ * ways. Unless there is something clearly wrong with it the code should
+ * remain as-is as it provides us with a guarantee from HW that it is correct.
+ */
+
 float dcn_bw_mod(const float arg1, const float arg2)
 {
-	if (arg1 != arg1)
+	if (isNaN(arg1))
 		return arg2;
-	if (arg2 != arg2)
+	if (isNaN(arg2))
 		return arg1;
 	return arg1 - arg1 * ((int) (arg1 / arg2));
 }
 
 float dcn_bw_min2(const float arg1, const float arg2)
 {
-	if (arg1 != arg1)
+	if (isNaN(arg1))
 		return arg2;
-	if (arg2 != arg2)
+	if (isNaN(arg2))
 		return arg1;
 	return arg1 < arg2 ? arg1 : arg2;
 }
 
 unsigned int dcn_bw_max(const unsigned int arg1, const unsigned int arg2)
 {
-	if (arg1 != arg1)
-		return arg2;
-	if (arg2 != arg2)
-		return arg1;
 	return arg1 > arg2 ? arg1 : arg2;
 }
 float dcn_bw_max2(const float arg1, const float arg2)
 {
-	if (arg1 != arg1)
+	if (isNaN(arg1))
 		return arg2;
-	if (arg2 != arg2)
+	if (isNaN(arg2))
 		return arg1;
 	return arg1 > arg2 ? arg1 : arg2;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 3dce35e66b09..331891c2c71a 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -33,6 +33,15 @@
 #include "dcn10/dcn10_resource.h"
 #include "dcn_calc_math.h"
 
+/*
+ * NOTE:
+ *   This file is gcc-parseable HW gospel, coming straight from HW engineers.
+ *
+ * It doesn't adhere to Linux kernel style and sometimes will do things in odd
+ * ways. Unless there is something clearly wrong with it the code should
+ * remain as-is as it provides us with a guarantee from HW that it is correct.
+ */
+
 /* Defaults from spreadsheet rev#247 */
 const struct dcn_soc_bounding_box dcn10_soc_defaults = {
 		/* latencies */
@@ -432,25 +441,13 @@ static void dcn_bw_calc_rq_dlg_ttu(
 	input.clks_cfg.dcfclk_mhz = v->dcfclk;
 	input.clks_cfg.dispclk_mhz = v->dispclk;
 	input.clks_cfg.dppclk_mhz = v->dppclk;
-	input.clks_cfg.refclk_mhz = dc->res_pool->ref_clock_inKhz/1000;
+	input.clks_cfg.refclk_mhz = dc->res_pool->ref_clock_inKhz / 1000.0;
 	input.clks_cfg.socclk_mhz = v->socclk;
 	input.clks_cfg.voltage = v->voltage_level;
 //	dc->dml.logger = pool->base.logger;
 	input.dout.output_format = (v->output_format[in_idx] == dcn_bw_420) ? dm_420 : dm_444;
 	input.dout.output_type  = (v->output[in_idx] == dcn_bw_hdmi) ? dm_hdmi : dm_dp;
 	//input[in_idx].dout.output_standard;
-	switch (v->output_deep_color[in_idx]) {
-	case dcn_bw_encoder_12bpc:
-		input.dout.output_bpc = dm_out_12;
-	break;
-	case dcn_bw_encoder_10bpc:
-		input.dout.output_bpc = dm_out_10;
-	break;
-	case dcn_bw_encoder_8bpc:
-	default:
-		input.dout.output_bpc = dm_out_8;
-	break;
-	}
 
 	/*todo: soc->sr_enter_plus_exit_time??*/
 	dlg_sys_param.t_srx_delay_us = dc->dcn_ip->dcfclk_cstate_latency / v->dcf_clk_deep_sleep;
@@ -890,6 +887,17 @@ bool dcn_validate_bandwidth(
 						+ pipe->bottom_pipe->plane_res.scl_data.recout.width;
 			}
 
+			if (pipe->plane_state->rotation % 2 == 0) {
+				ASSERT(pipe->plane_res.scl_data.ratios.horz.value != dal_fixed31_32_one.value
+					|| v->scaler_rec_out_width[input_idx] == v->viewport_width[input_idx]);
+				ASSERT(pipe->plane_res.scl_data.ratios.vert.value != dal_fixed31_32_one.value
+					|| v->scaler_recout_height[input_idx] == v->viewport_height[input_idx]);
+			} else {
+				ASSERT(pipe->plane_res.scl_data.ratios.horz.value != dal_fixed31_32_one.value
+					|| v->scaler_recout_height[input_idx] == v->viewport_width[input_idx]);
+				ASSERT(pipe->plane_res.scl_data.ratios.vert.value != dal_fixed31_32_one.value
+					|| v->scaler_rec_out_width[input_idx] == v->viewport_height[input_idx]);
+			}
 			v->dcc_enable[input_idx] = pipe->plane_state->dcc.enable ? dcn_bw_yes : dcn_bw_no;
 			v->source_pixel_format[input_idx] = tl_pixel_format_to_bw_defs(
 					pipe->plane_state->format);
@@ -900,6 +908,15 @@ bool dcn_validate_bandwidth(
 			v->override_vta_ps[input_idx] = pipe->plane_res.scl_data.taps.v_taps;
 			v->override_hta_pschroma[input_idx] = pipe->plane_res.scl_data.taps.h_taps_c;
 			v->override_vta_pschroma[input_idx] = pipe->plane_res.scl_data.taps.v_taps_c;
+			/*
+			 * Spreadsheet doesn't handle taps_c is one properly,
+			 * need to force Chroma to always be scaled to pass
+			 * bandwidth validation.
+			 */
+			if (v->override_hta_pschroma[input_idx] == 1)
+				v->override_hta_pschroma[input_idx] = 2;
+			if (v->override_vta_pschroma[input_idx] == 1)
+				v->override_vta_pschroma[input_idx] = 2;
 			v->source_scan[input_idx] = (pipe->plane_state->rotation % 2) ? dcn_bw_vert : dcn_bw_hor;
 		}
 		if (v->is_line_buffer_bpp_fixed == dcn_bw_yes)
@@ -997,9 +1014,9 @@ bool dcn_validate_bandwidth(
 			if (pipe->top_pipe && pipe->top_pipe->plane_state == pipe->plane_state)
 				continue;
 
-			pipe->pipe_dlg_param.vupdate_width = v->v_update_width[input_idx];
-			pipe->pipe_dlg_param.vupdate_offset = v->v_update_offset[input_idx];
-			pipe->pipe_dlg_param.vready_offset = v->v_ready_offset[input_idx];
+			pipe->pipe_dlg_param.vupdate_width = v->v_update_width[input_idx][v->dpp_per_plane[input_idx] == 2 ? 1 : 0];
+			pipe->pipe_dlg_param.vupdate_offset = v->v_update_offset[input_idx][v->dpp_per_plane[input_idx] == 2 ? 1 : 0];
+			pipe->pipe_dlg_param.vready_offset = v->v_ready_offset[input_idx][v->dpp_per_plane[input_idx] == 2 ? 1 : 0];
 			pipe->pipe_dlg_param.vstartup_start = v->v_startup[input_idx];
 
 			pipe->pipe_dlg_param.htotal = pipe->stream->timing.h_total;
@@ -1025,6 +1042,8 @@ bool dcn_validate_bandwidth(
 			if (pipe->plane_state) {
 				struct pipe_ctx *hsplit_pipe = pipe->bottom_pipe;
 
+				pipe->plane_state->update_flags.bits.full_update = 1;
+
 				if (v->dpp_per_plane[input_idx] == 2 ||
 					((pipe->stream->view_format ==
 					  VIEW_3D_FORMAT_SIDE_BY_SIDE ||
@@ -1036,9 +1055,9 @@ bool dcn_validate_bandwidth(
 					 TIMING_3D_FORMAT_SIDE_BY_SIDE))) {
 					if (hsplit_pipe && hsplit_pipe->plane_state == pipe->plane_state) {
 						/* update previously split pipe */
-						hsplit_pipe->pipe_dlg_param.vupdate_width = v->v_update_width[input_idx];
-						hsplit_pipe->pipe_dlg_param.vupdate_offset = v->v_update_offset[input_idx];
-						hsplit_pipe->pipe_dlg_param.vready_offset = v->v_ready_offset[input_idx];
+						hsplit_pipe->pipe_dlg_param.vupdate_width = v->v_update_width[input_idx][v->dpp_per_plane[input_idx] == 2 ? 1 : 0];
+						hsplit_pipe->pipe_dlg_param.vupdate_offset = v->v_update_offset[input_idx][v->dpp_per_plane[input_idx] == 2 ? 1 : 0];
+						hsplit_pipe->pipe_dlg_param.vready_offset = v->v_ready_offset[input_idx][v->dpp_per_plane[input_idx] == 2 ? 1 : 0];
 						hsplit_pipe->pipe_dlg_param.vstartup_start = v->v_startup[input_idx];
 
 						hsplit_pipe->pipe_dlg_param.htotal = pipe->stream->timing.h_total;
@@ -1064,6 +1083,9 @@ bool dcn_validate_bandwidth(
 					hsplit_pipe->stream = NULL;
 					hsplit_pipe->top_pipe = NULL;
 					hsplit_pipe->bottom_pipe = NULL;
+					/* Clear plane_res and stream_res */
+					memset(&hsplit_pipe->plane_res, 0, sizeof(hsplit_pipe->plane_res));
+					memset(&hsplit_pipe->stream_res, 0, sizeof(hsplit_pipe->stream_res));
 					resource_build_scaling_params(pipe);
 				}
 				/* for now important to do this after pipe split for building e2e params */
@@ -1231,40 +1253,62 @@ unsigned int dcn_find_dcfclk_suits_all(
 	return dcf_clk;
 }
 
+static bool verify_clock_values(struct dm_pp_clock_levels_with_voltage *clks)
+{
+	int i;
+
+	if (clks->num_levels == 0)
+		return false;
+
+	for (i = 0; i < clks->num_levels; i++)
+		/* Ensure that the result is sane */
+		if (clks->data[i].clocks_in_khz == 0)
+			return false;
+
+	return true;
+}
+
 void dcn_bw_update_from_pplib(struct dc *dc)
 {
 	struct dc_context *ctx = dc->ctx;
-	struct dm_pp_clock_levels_with_voltage clks = {0};
+	struct dm_pp_clock_levels_with_voltage fclks = {0}, dcfclks = {0};
+	bool res;
 
 	kernel_fpu_begin();
 
 	/* TODO: This is not the proper way to obtain fabric_and_dram_bandwidth, should be min(fclk, memclk) */
-
-	if (dm_pp_get_clock_levels_by_type_with_voltage(
-			ctx, DM_PP_CLOCK_TYPE_FCLK, &clks) &&
-			clks.num_levels != 0) {
-		ASSERT(clks.num_levels >= 3);
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 32 * (clks.data[0].clocks_in_khz / 1000.0) / 1000.0;
-		if (clks.num_levels > 2) {
-			dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = dc->dcn_soc->number_of_channels *
-					(clks.data[clks.num_levels - 3].clocks_in_khz / 1000.0) * ddr4_dram_factor_single_Channel / 1000.0;
-		} else {
-			dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = dc->dcn_soc->number_of_channels *
-					(clks.data[clks.num_levels - 2].clocks_in_khz / 1000.0) * ddr4_dram_factor_single_Channel / 1000.0;
-		}
+	res = dm_pp_get_clock_levels_by_type_with_voltage(
+			ctx, DM_PP_CLOCK_TYPE_FCLK, &fclks);
+
+	if (res)
+		res = verify_clock_values(&fclks);
+
+	if (res) {
+		ASSERT(fclks.num_levels >= 3);
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 32 * (fclks.data[0].clocks_in_khz / 1000.0) / 1000.0;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = dc->dcn_soc->number_of_channels *
+				(fclks.data[fclks.num_levels - (fclks.num_levels > 2 ? 3 : 2)].clocks_in_khz / 1000.0)
+				* ddr4_dram_factor_single_Channel / 1000.0;
 		dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = dc->dcn_soc->number_of_channels *
-				(clks.data[clks.num_levels - 2].clocks_in_khz / 1000.0) * ddr4_dram_factor_single_Channel / 1000.0;
+				(fclks.data[fclks.num_levels - 2].clocks_in_khz / 1000.0)
+				* ddr4_dram_factor_single_Channel / 1000.0;
 		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = dc->dcn_soc->number_of_channels *
-				(clks.data[clks.num_levels - 1].clocks_in_khz / 1000.0) * ddr4_dram_factor_single_Channel / 1000.0;
+				(fclks.data[fclks.num_levels - 1].clocks_in_khz / 1000.0)
+				* ddr4_dram_factor_single_Channel / 1000.0;
 	} else
 		BREAK_TO_DEBUGGER();
-	if (dm_pp_get_clock_levels_by_type_with_voltage(
-				ctx, DM_PP_CLOCK_TYPE_DCFCLK, &clks) &&
-				clks.num_levels >= 3) {
-		dc->dcn_soc->dcfclkv_min0p65 = clks.data[0].clocks_in_khz / 1000.0;
-		dc->dcn_soc->dcfclkv_mid0p72 = clks.data[clks.num_levels - 3].clocks_in_khz / 1000.0;
-		dc->dcn_soc->dcfclkv_nom0p8 = clks.data[clks.num_levels - 2].clocks_in_khz / 1000.0;
-		dc->dcn_soc->dcfclkv_max0p9 = clks.data[clks.num_levels - 1].clocks_in_khz / 1000.0;
+
+	res = dm_pp_get_clock_levels_by_type_with_voltage(
+			ctx, DM_PP_CLOCK_TYPE_DCFCLK, &dcfclks);
+
+	if (res)
+		res = verify_clock_values(&dcfclks);
+
+	if (res && dcfclks.num_levels >= 3) {
+		dc->dcn_soc->dcfclkv_min0p65 = dcfclks.data[0].clocks_in_khz / 1000.0;
+		dc->dcn_soc->dcfclkv_mid0p72 = dcfclks.data[dcfclks.num_levels - 3].clocks_in_khz / 1000.0;
+		dc->dcn_soc->dcfclkv_nom0p8 = dcfclks.data[dcfclks.num_levels - 2].clocks_in_khz / 1000.0;
+		dc->dcn_soc->dcfclkv_max0p9 = dcfclks.data[dcfclks.num_levels - 1].clocks_in_khz / 1000.0;
 	} else
 		BREAK_TO_DEBUGGER();
 
@@ -1541,35 +1585,6 @@ void dcn_bw_sync_calcs_and_dml(struct dc *dc)
 			dc->dcn_ip->can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one,
 			dc->dcn_ip->bug_forcing_luma_and_chroma_request_to_same_size_fixed,
 			dc->dcn_ip->dcfclk_cstate_latency);
-	dc->dml.soc.vmin.socclk_mhz = dc->dcn_soc->socclk;
-	dc->dml.soc.vmid.socclk_mhz = dc->dcn_soc->socclk;
-	dc->dml.soc.vnom.socclk_mhz = dc->dcn_soc->socclk;
-	dc->dml.soc.vmax.socclk_mhz = dc->dcn_soc->socclk;
-
-	dc->dml.soc.vmin.dcfclk_mhz = dc->dcn_soc->dcfclkv_min0p65;
-	dc->dml.soc.vmid.dcfclk_mhz = dc->dcn_soc->dcfclkv_mid0p72;
-	dc->dml.soc.vnom.dcfclk_mhz = dc->dcn_soc->dcfclkv_nom0p8;
-	dc->dml.soc.vmax.dcfclk_mhz = dc->dcn_soc->dcfclkv_max0p9;
-
-	dc->dml.soc.vmin.dispclk_mhz = dc->dcn_soc->max_dispclk_vmin0p65;
-	dc->dml.soc.vmid.dispclk_mhz = dc->dcn_soc->max_dispclk_vmid0p72;
-	dc->dml.soc.vnom.dispclk_mhz = dc->dcn_soc->max_dispclk_vnom0p8;
-	dc->dml.soc.vmax.dispclk_mhz = dc->dcn_soc->max_dispclk_vmax0p9;
-
-	dc->dml.soc.vmin.dppclk_mhz = dc->dcn_soc->max_dppclk_vmin0p65;
-	dc->dml.soc.vmid.dppclk_mhz = dc->dcn_soc->max_dppclk_vmid0p72;
-	dc->dml.soc.vnom.dppclk_mhz = dc->dcn_soc->max_dppclk_vnom0p8;
-	dc->dml.soc.vmax.dppclk_mhz = dc->dcn_soc->max_dppclk_vmax0p9;
-
-	dc->dml.soc.vmin.phyclk_mhz = dc->dcn_soc->phyclkv_min0p65;
-	dc->dml.soc.vmid.phyclk_mhz = dc->dcn_soc->phyclkv_mid0p72;
-	dc->dml.soc.vnom.phyclk_mhz = dc->dcn_soc->phyclkv_nom0p8;
-	dc->dml.soc.vmax.phyclk_mhz = dc->dcn_soc->phyclkv_max0p9;
-
-	dc->dml.soc.vmin.dram_bw_per_chan_gbps = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65;
-	dc->dml.soc.vmid.dram_bw_per_chan_gbps = dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72;
-	dc->dml.soc.vnom.dram_bw_per_chan_gbps = dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8;
-	dc->dml.soc.vmax.dram_bw_per_chan_gbps = dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9;
 
 	dc->dml.soc.sr_exit_time_us = dc->dcn_soc->sr_exit_time;
 	dc->dml.soc.sr_enter_plus_exit_time_us = dc->dcn_soc->sr_enter_plus_exit_time;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index fe63f5894d43..35e84ed031de 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -54,6 +54,13 @@
 /*******************************************************************************
  * Private functions
  ******************************************************************************/
+
+static inline void elevate_update_type(enum surface_update_type *original, enum surface_update_type new)
+{
+	if (new > *original)
+		*original = new;
+}
+
 static void destroy_links(struct dc *dc)
 {
 	uint32_t i;
@@ -121,6 +128,10 @@ static bool create_links(
 			goto failed_alloc;
 		}
 
+		link->link_index = dc->link_count;
+		dc->links[dc->link_count] = link;
+		dc->link_count++;
+
 		link->ctx = dc->ctx;
 		link->dc = dc;
 		link->connector_signal = SIGNAL_TYPE_VIRTUAL;
@@ -129,6 +140,13 @@ static bool create_links(
 		link->link_id.enum_id = ENUM_ID_1;
 		link->link_enc = kzalloc(sizeof(*link->link_enc), GFP_KERNEL);
 
+		if (!link->link_enc) {
+			BREAK_TO_DEBUGGER();
+			goto failed_alloc;
+		}
+
+		link->link_status.dpcd_caps = &link->dpcd_caps;
+
 		enc_init.ctx = dc->ctx;
 		enc_init.channel = CHANNEL_ID_UNKNOWN;
 		enc_init.hpd_source = HPD_SOURCEID_UNKNOWN;
@@ -138,10 +156,6 @@ static bool create_links(
 		enc_init.encoder.id = ENCODER_ID_INTERNAL_VIRTUAL;
 		enc_init.encoder.enum_id = ENUM_ID_1;
 		virtual_link_encoder_construct(link->link_enc, &enc_init);
-
-		link->link_index = dc->link_count;
-		dc->links[dc->link_count] = link;
-		dc->link_count++;
 	}
 
 	return true;
@@ -150,7 +164,7 @@ failed_alloc:
 	return false;
 }
 
-static bool stream_adjust_vmin_vmax(struct dc *dc,
+bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 		struct dc_stream_state **streams, int num_streams,
 		int vmin, int vmax)
 {
@@ -175,7 +189,7 @@ static bool stream_adjust_vmin_vmax(struct dc *dc,
 	return ret;
 }
 
-static bool stream_get_crtc_position(struct dc *dc,
+bool dc_stream_get_crtc_position(struct dc *dc,
 		struct dc_stream_state **streams, int num_streams,
 		unsigned int *v_pos, unsigned int *nom_v_pos)
 {
@@ -200,45 +214,7 @@ static bool stream_get_crtc_position(struct dc *dc,
 	return ret;
 }
 
-static bool set_gamut_remap(struct dc *dc, const struct dc_stream_state *stream)
-{
-	int i = 0;
-	bool ret = false;
-	struct pipe_ctx *pipes;
-
-	for (i = 0; i < MAX_PIPES; i++) {
-		if (dc->current_state->res_ctx.pipe_ctx[i].stream == stream) {
-			pipes = &dc->current_state->res_ctx.pipe_ctx[i];
-			dc->hwss.program_gamut_remap(pipes);
-			ret = true;
-		}
-	}
-
-	return ret;
-}
-
-static bool program_csc_matrix(struct dc *dc, struct dc_stream_state *stream)
-{
-	int i = 0;
-	bool ret = false;
-	struct pipe_ctx *pipes;
-
-	for (i = 0; i < MAX_PIPES; i++) {
-		if (dc->current_state->res_ctx.pipe_ctx[i].stream
-				== stream) {
-
-			pipes = &dc->current_state->res_ctx.pipe_ctx[i];
-			dc->hwss.program_csc_matrix(pipes,
-			stream->output_color_space,
-			stream->csc_color_matrix.matrix);
-			ret = true;
-		}
-	}
-
-	return ret;
-}
-
-static void set_static_screen_events(struct dc *dc,
+void dc_stream_set_static_screen_events(struct dc *dc,
 		struct dc_stream_state **streams,
 		int num_streams,
 		const struct dc_static_screen_events *events)
@@ -263,177 +239,6 @@ static void set_static_screen_events(struct dc *dc,
 	dc->hwss.set_static_screen_control(pipes_affected, num_pipes_affected, events);
 }
 
-static void set_drive_settings(struct dc *dc,
-		struct link_training_settings *lt_settings,
-		const struct dc_link *link)
-{
-
-	int i;
-
-	for (i = 0; i < dc->link_count; i++) {
-		if (dc->links[i] == link)
-			break;
-	}
-
-	if (i >= dc->link_count)
-		ASSERT_CRITICAL(false);
-
-	dc_link_dp_set_drive_settings(dc->links[i], lt_settings);
-}
-
-static void perform_link_training(struct dc *dc,
-		struct dc_link_settings *link_setting,
-		bool skip_video_pattern)
-{
-	int i;
-
-	for (i = 0; i < dc->link_count; i++)
-		dc_link_dp_perform_link_training(
-			dc->links[i],
-			link_setting,
-			skip_video_pattern);
-}
-
-static void set_preferred_link_settings(struct dc *dc,
-		struct dc_link_settings *link_setting,
-		struct dc_link *link)
-{
-	link->preferred_link_setting = *link_setting;
-	dp_retrain_link_dp_test(link, link_setting, false);
-}
-
-static void enable_hpd(const struct dc_link *link)
-{
-	dc_link_dp_enable_hpd(link);
-}
-
-static void disable_hpd(const struct dc_link *link)
-{
-	dc_link_dp_disable_hpd(link);
-}
-
-
-static void set_test_pattern(
-		struct dc_link *link,
-		enum dp_test_pattern test_pattern,
-		const struct link_training_settings *p_link_settings,
-		const unsigned char *p_custom_pattern,
-		unsigned int cust_pattern_size)
-{
-	if (link != NULL)
-		dc_link_dp_set_test_pattern(
-			link,
-			test_pattern,
-			p_link_settings,
-			p_custom_pattern,
-			cust_pattern_size);
-}
-
-static void set_dither_option(struct dc_stream_state *stream,
-		enum dc_dither_option option)
-{
-	struct bit_depth_reduction_params params;
-	struct dc_link *link = stream->status.link;
-	struct pipe_ctx *pipes = NULL;
-	int i;
-
-	for (i = 0; i < MAX_PIPES; i++) {
-		if (link->dc->current_state->res_ctx.pipe_ctx[i].stream ==
-				stream) {
-			pipes = &link->dc->current_state->res_ctx.pipe_ctx[i];
-			break;
-		}
-	}
-
-	memset(&params, 0, sizeof(params));
-	if (!pipes)
-		return;
-	if (option > DITHER_OPTION_MAX)
-		return;
-
-	stream->dither_option = option;
-
-	resource_build_bit_depth_reduction_params(stream,
-				&params);
-	stream->bit_depth_params = params;
-	pipes->stream_res.opp->funcs->
-		opp_program_bit_depth_reduction(pipes->stream_res.opp, &params);
-}
-
-void set_dpms(
-	struct dc *dc,
-	struct dc_stream_state *stream,
-	bool dpms_off)
-{
-	struct pipe_ctx *pipe_ctx = NULL;
-	int i;
-
-	for (i = 0; i < MAX_PIPES; i++) {
-		if (dc->current_state->res_ctx.pipe_ctx[i].stream == stream) {
-			pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
-			break;
-		}
-	}
-
-	if (!pipe_ctx) {
-		ASSERT(0);
-		return;
-	}
-
-	if (stream->dpms_off != dpms_off) {
-		stream->dpms_off = dpms_off;
-		if (dpms_off)
-			core_link_disable_stream(pipe_ctx,
-					KEEP_ACQUIRED_RESOURCE);
-		else
-			core_link_enable_stream(dc->current_state, pipe_ctx);
-	}
-}
-
-static void allocate_dc_stream_funcs(struct dc  *dc)
-{
-	if (dc->hwss.set_drr != NULL) {
-		dc->stream_funcs.adjust_vmin_vmax =
-				stream_adjust_vmin_vmax;
-	}
-
-	dc->stream_funcs.set_static_screen_events =
-			set_static_screen_events;
-
-	dc->stream_funcs.get_crtc_position =
-			stream_get_crtc_position;
-
-	dc->stream_funcs.set_gamut_remap =
-			set_gamut_remap;
-
-	dc->stream_funcs.program_csc_matrix =
-			program_csc_matrix;
-
-	dc->stream_funcs.set_dither_option =
-			set_dither_option;
-
-	dc->stream_funcs.set_dpms =
-			set_dpms;
-
-	dc->link_funcs.set_drive_settings =
-			set_drive_settings;
-
-	dc->link_funcs.perform_link_training =
-			perform_link_training;
-
-	dc->link_funcs.set_preferred_link_settings =
-			set_preferred_link_settings;
-
-	dc->link_funcs.enable_hpd =
-			enable_hpd;
-
-	dc->link_funcs.disable_hpd =
-			disable_hpd;
-
-	dc->link_funcs.set_test_pattern =
-			set_test_pattern;
-}
-
 static void destruct(struct dc *dc)
 {
 	dc_release_state(dc->current_state);
@@ -478,19 +283,17 @@ static bool construct(struct dc *dc,
 		const struct dc_init_data *init_params)
 {
 	struct dal_logger *logger;
-	struct dc_context *dc_ctx = kzalloc(sizeof(*dc_ctx), GFP_KERNEL);
-	struct bw_calcs_dceip *dc_dceip = kzalloc(sizeof(*dc_dceip),
-						  GFP_KERNEL);
-	struct bw_calcs_vbios *dc_vbios = kzalloc(sizeof(*dc_vbios),
-						  GFP_KERNEL);
+	struct dc_context *dc_ctx;
+	struct bw_calcs_dceip *dc_dceip;
+	struct bw_calcs_vbios *dc_vbios;
 #ifdef CONFIG_DRM_AMD_DC_DCN1_0
-	struct dcn_soc_bounding_box *dcn_soc = kzalloc(sizeof(*dcn_soc),
-						       GFP_KERNEL);
-	struct dcn_ip_params *dcn_ip = kzalloc(sizeof(*dcn_ip), GFP_KERNEL);
+	struct dcn_soc_bounding_box *dcn_soc;
+	struct dcn_ip_params *dcn_ip;
 #endif
 
 	enum dce_version dc_version = DCE_VERSION_UNKNOWN;
 
+	dc_dceip = kzalloc(sizeof(*dc_dceip), GFP_KERNEL);
 	if (!dc_dceip) {
 		dm_error("%s: failed to create dceip\n", __func__);
 		goto fail;
@@ -498,6 +301,7 @@ static bool construct(struct dc *dc,
 
 	dc->bw_dceip = dc_dceip;
 
+	dc_vbios = kzalloc(sizeof(*dc_vbios), GFP_KERNEL);
 	if (!dc_vbios) {
 		dm_error("%s: failed to create vbios\n", __func__);
 		goto fail;
@@ -505,6 +309,7 @@ static bool construct(struct dc *dc,
 
 	dc->bw_vbios = dc_vbios;
 #ifdef CONFIG_DRM_AMD_DC_DCN1_0
+	dcn_soc = kzalloc(sizeof(*dcn_soc), GFP_KERNEL);
 	if (!dcn_soc) {
 		dm_error("%s: failed to create dcn_soc\n", __func__);
 		goto fail;
@@ -512,6 +317,7 @@ static bool construct(struct dc *dc,
 
 	dc->dcn_soc = dcn_soc;
 
+	dcn_ip = kzalloc(sizeof(*dcn_ip), GFP_KERNEL);
 	if (!dcn_ip) {
 		dm_error("%s: failed to create dcn_ip\n", __func__);
 		goto fail;
@@ -520,11 +326,18 @@ static bool construct(struct dc *dc,
 	dc->dcn_ip = dcn_ip;
 #endif
 
+	dc_ctx = kzalloc(sizeof(*dc_ctx), GFP_KERNEL);
 	if (!dc_ctx) {
 		dm_error("%s: failed to create ctx\n", __func__);
 		goto fail;
 	}
 
+	dc_ctx->cgs_device = init_params->cgs_device;
+	dc_ctx->driver_context = init_params->driver;
+	dc_ctx->dc = dc;
+	dc_ctx->asic_id = init_params->asic_id;
+	dc->ctx = dc_ctx;
+
 	dc->current_state = dc_create_state();
 
 	if (!dc->current_state) {
@@ -532,11 +345,6 @@ static bool construct(struct dc *dc,
 		goto fail;
 	}
 
-	dc_ctx->cgs_device = init_params->cgs_device;
-	dc_ctx->driver_context = init_params->driver;
-	dc_ctx->dc = dc;
-	dc_ctx->asic_id = init_params->asic_id;
-
 	/* Create logger */
 	logger = dal_logger_create(dc_ctx, init_params->log_mask);
 
@@ -546,11 +354,11 @@ static bool construct(struct dc *dc,
 		goto fail;
 	}
 	dc_ctx->logger = logger;
-	dc->ctx = dc_ctx;
-	dc->ctx->dce_environment = init_params->dce_environment;
+	dc_ctx->dce_environment = init_params->dce_environment;
 
 	dc_version = resource_parse_asic_id(init_params->asic_id);
-	dc->ctx->dce_version = dc_version;
+	dc_ctx->dce_version = dc_version;
+
 #if defined(CONFIG_DRM_AMD_DC_FBC)
 	dc->ctx->fbc_gpu_addr = init_params->fbc_gpu_addr;
 #endif
@@ -609,8 +417,6 @@ static bool construct(struct dc *dc,
 	if (!create_links(dc, init_params->num_virtual_links))
 		goto fail;
 
-	allocate_dc_stream_funcs(dc);
-
 	return true;
 
 fail:
@@ -679,6 +485,7 @@ struct dc *dc_create(const struct dc_init_data *init_params)
 
 	dc->caps.max_links = dc->link_count;
 	dc->caps.max_audios = dc->res_pool->audio_count;
+	dc->caps.linear_pitch_alignment = 64;
 
 	dc->config = init_params->flags;
 
@@ -705,6 +512,28 @@ void dc_destroy(struct dc **dc)
 	*dc = NULL;
 }
 
+static void enable_timing_multisync(
+		struct dc *dc,
+		struct dc_state *ctx)
+{
+	int i = 0, multisync_count = 0;
+	int pipe_count = dc->res_pool->pipe_count;
+	struct pipe_ctx *multisync_pipes[MAX_PIPES] = { NULL };
+
+	for (i = 0; i < pipe_count; i++) {
+		if (!ctx->res_ctx.pipe_ctx[i].stream ||
+				!ctx->res_ctx.pipe_ctx[i].stream->triggered_crtc_reset.enabled)
+			continue;
+		multisync_pipes[multisync_count] = &ctx->res_ctx.pipe_ctx[i];
+		multisync_count++;
+	}
+
+	if (multisync_count > 1) {
+		dc->hwss.enable_per_frame_crtc_position_reset(
+			dc, multisync_count, multisync_pipes);
+	}
+}
+
 static void program_timing_sync(
 		struct dc *dc,
 		struct dc_state *ctx)
@@ -751,7 +580,7 @@ static void program_timing_sync(
 		for (j = 0; j < group_size; j++) {
 			struct pipe_ctx *temp;
 
-			if (!pipe_set[j]->stream_res.tg->funcs->is_blanked(pipe_set[j]->stream_res.tg)) {
+			if (pipe_set[j]->stream_res.tg->funcs->is_blanked && !pipe_set[j]->stream_res.tg->funcs->is_blanked(pipe_set[j]->stream_res.tg)) {
 				if (j == 0)
 					break;
 
@@ -764,7 +593,7 @@ static void program_timing_sync(
 
 		/* remove any other unblanked pipes as they have already been synced */
 		for (j = j + 1; j < group_size; j++) {
-			if (!pipe_set[j]->stream_res.tg->funcs->is_blanked(pipe_set[j]->stream_res.tg)) {
+			if (pipe_set[j]->stream_res.tg->funcs->is_blanked && !pipe_set[j]->stream_res.tg->funcs->is_blanked(pipe_set[j]->stream_res.tg)) {
 				group_size--;
 				pipe_set[j] = pipe_set[group_size];
 				j--;
@@ -831,7 +660,7 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 	struct dc_bios *dcb = dc->ctx->dc_bios;
 	enum dc_status result = DC_ERROR_UNEXPECTED;
 	struct pipe_ctx *pipe;
-	int i, j, k, l;
+	int i, k, l;
 	struct dc_stream_state *dc_streams[MAX_STREAMS] = {0};
 
 	disable_dangling_plane(dc, context);
@@ -842,9 +671,44 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 	if (!dcb->funcs->is_accelerated_mode(dcb))
 		dc->hwss.enable_accelerated_mode(dc);
 
+	/* re-program planes for existing stream, in case we need to
+	 * free up plane resource for later use
+	 */
+	for (i = 0; i < context->stream_count; i++) {
+		if (context->streams[i]->mode_changed)
+			continue;
+
+		dc->hwss.apply_ctx_for_surface(
+			dc, context->streams[i],
+			context->stream_status[i].plane_count,
+			context); /* use new pipe config in new context */
+	}
+
+	/* Program hardware */
+	dc->hwss.ready_shared_resources(dc, context);
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		pipe = &context->res_ctx.pipe_ctx[i];
+		dc->hwss.wait_for_mpcc_disconnect(dc, dc->res_pool, pipe);
+	}
+
+	result = dc->hwss.apply_ctx_to_hw(dc, context);
+
+	if (result != DC_OK)
+		return result;
+
+	if (context->stream_count > 1) {
+		enable_timing_multisync(dc, context);
+		program_timing_sync(dc, context);
+	}
+
+	/* Program all planes within new context*/
 	for (i = 0; i < context->stream_count; i++) {
 		const struct dc_sink *sink = context->streams[i]->sink;
 
+		if (!context->streams[i]->mode_changed)
+			continue;
+
 		dc->hwss.apply_ctx_for_surface(
 				dc, context->streams[i],
 				context->stream_status[i].plane_count,
@@ -873,27 +737,8 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 				context->streams[i]->timing.pix_clk_khz);
 	}
 
-	dc->hwss.ready_shared_resources(dc, context);
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		pipe = &context->res_ctx.pipe_ctx[i];
-		dc->hwss.wait_for_mpcc_disconnect(dc, dc->res_pool, pipe);
-	}
-	result = dc->hwss.apply_ctx_to_hw(dc, context);
-
-	program_timing_sync(dc, context);
-
 	dc_enable_stereo(dc, context, dc_streams, context->stream_count);
 
-	for (i = 0; i < context->stream_count; i++) {
-		for (j = 0; j < MAX_PIPES; j++) {
-			pipe = &context->res_ctx.pipe_ctx[j];
-
-			if (!pipe->top_pipe && pipe->stream == context->streams[i])
-				dc->hwss.pipe_control_lock(dc, pipe, false);
-		}
-	}
-
 	dc_release_state(dc->current_state);
 
 	dc->current_state = context;
@@ -929,7 +774,6 @@ bool dc_commit_state(struct dc *dc, struct dc_state *context)
 	return (result == DC_OK);
 }
 
-
 bool dc_post_update_surfaces_to_stream(struct dc *dc)
 {
 	int i;
@@ -938,9 +782,13 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc)
 	post_surface_trace(dc);
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++)
-		if (context->res_ctx.pipe_ctx[i].stream == NULL
-				|| context->res_ctx.pipe_ctx[i].plane_state == NULL)
-			dc->hwss.power_down_front_end(dc, i);
+		if (context->res_ctx.pipe_ctx[i].stream == NULL ||
+		    context->res_ctx.pipe_ctx[i].plane_state == NULL) {
+			context->res_ctx.pipe_ctx[i].pipe_idx = i;
+			dc->hwss.disable_plane(dc, &context->res_ctx.pipe_ctx[i]);
+		}
+
+	dc->optimized_required = false;
 
 	/* 3rd param should be true, temp w/a for RV*/
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
@@ -1007,6 +855,7 @@ bool dc_commit_planes_to_stream(
 		flip_addr[i].address = plane_states[i]->address;
 		flip_addr[i].flip_immediate = plane_states[i]->flip_immediate;
 		plane_info[i].color_space = plane_states[i]->color_space;
+		plane_info[i].input_tf = plane_states[i]->input_tf;
 		plane_info[i].format = plane_states[i]->format;
 		plane_info[i].plane_size = plane_states[i]->plane_size;
 		plane_info[i].rotation = plane_states[i]->rotation;
@@ -1111,79 +960,96 @@ static unsigned int pixel_format_to_bpp(enum surface_pixel_format format)
 	}
 }
 
-static enum surface_update_type get_plane_info_update_type(
-		const struct dc_surface_update *u,
-		int surface_index)
+static enum surface_update_type get_plane_info_update_type(const struct dc_surface_update *u)
 {
-	struct dc_plane_info temp_plane_info;
-	memset(&temp_plane_info, 0, sizeof(temp_plane_info));
+	union surface_update_flags *update_flags = &u->surface->update_flags;
 
 	if (!u->plane_info)
 		return UPDATE_TYPE_FAST;
 
-	temp_plane_info = *u->plane_info;
+	if (u->plane_info->color_space != u->surface->color_space)
+		update_flags->bits.color_space_change = 1;
 
-	/* Copy all parameters that will cause a full update
-	 * from current surface, the rest of the parameters
-	 * from provided plane configuration.
-	 * Perform memory compare and special validation
-	 * for those that can cause fast/medium updates
-	 */
+	if (u->plane_info->input_tf != u->surface->input_tf)
+		update_flags->bits.input_tf_change = 1;
 
-	/* Full update parameters */
-	temp_plane_info.color_space = u->surface->color_space;
-	temp_plane_info.dcc = u->surface->dcc;
-	temp_plane_info.horizontal_mirror = u->surface->horizontal_mirror;
-	temp_plane_info.plane_size = u->surface->plane_size;
-	temp_plane_info.rotation = u->surface->rotation;
-	temp_plane_info.stereo_format = u->surface->stereo_format;
-
-	if (surface_index == 0)
-		temp_plane_info.visible = u->plane_info->visible;
-	else
-		temp_plane_info.visible = u->surface->visible;
-
-	if (memcmp(u->plane_info, &temp_plane_info,
-			sizeof(struct dc_plane_info)) != 0)
-		return UPDATE_TYPE_FULL;
+	if (u->plane_info->horizontal_mirror != u->surface->horizontal_mirror)
+		update_flags->bits.horizontal_mirror_change = 1;
+
+	if (u->plane_info->rotation != u->surface->rotation)
+		update_flags->bits.rotation_change = 1;
+
+	if (u->plane_info->stereo_format != u->surface->stereo_format)
+		update_flags->bits.stereo_format_change = 1;
+
+	if (u->plane_info->per_pixel_alpha != u->surface->per_pixel_alpha)
+		update_flags->bits.per_pixel_alpha_change = 1;
+
+	if (u->plane_info->dcc.enable != u->surface->dcc.enable
+			|| u->plane_info->dcc.grph.independent_64b_blks != u->surface->dcc.grph.independent_64b_blks
+			|| u->plane_info->dcc.grph.meta_pitch != u->surface->dcc.grph.meta_pitch)
+		update_flags->bits.dcc_change = 1;
 
 	if (pixel_format_to_bpp(u->plane_info->format) !=
-			pixel_format_to_bpp(u->surface->format)) {
+			pixel_format_to_bpp(u->surface->format))
 		/* different bytes per element will require full bandwidth
 		 * and DML calculation
 		 */
-		return UPDATE_TYPE_FULL;
-	}
+		update_flags->bits.bpp_change = 1;
 
 	if (memcmp(&u->plane_info->tiling_info, &u->surface->tiling_info,
 			sizeof(union dc_tiling_info)) != 0) {
+		update_flags->bits.swizzle_change = 1;
 		/* todo: below are HW dependent, we should add a hook to
 		 * DCE/N resource and validated there.
 		 */
-		if (u->plane_info->tiling_info.gfx9.swizzle != DC_SW_LINEAR) {
+		if (u->plane_info->tiling_info.gfx9.swizzle != DC_SW_LINEAR)
 			/* swizzled mode requires RQ to be setup properly,
 			 * thus need to run DML to calculate RQ settings
 			 */
-			return UPDATE_TYPE_FULL;
-		}
+			update_flags->bits.bandwidth_change = 1;
 	}
 
+	if (update_flags->bits.rotation_change
+			|| update_flags->bits.stereo_format_change
+			|| update_flags->bits.bpp_change
+			|| update_flags->bits.bandwidth_change)
+		return UPDATE_TYPE_FULL;
+
 	return UPDATE_TYPE_MED;
 }
 
-static enum surface_update_type  get_scaling_info_update_type(
+static enum surface_update_type get_scaling_info_update_type(
 		const struct dc_surface_update *u)
 {
+	union surface_update_flags *update_flags = &u->surface->update_flags;
+
 	if (!u->scaling_info)
 		return UPDATE_TYPE_FAST;
 
-	if (u->scaling_info->src_rect.width != u->surface->src_rect.width
-			|| u->scaling_info->src_rect.height != u->surface->src_rect.height
-			|| u->scaling_info->clip_rect.width != u->surface->clip_rect.width
+	if (u->scaling_info->clip_rect.width != u->surface->clip_rect.width
 			|| u->scaling_info->clip_rect.height != u->surface->clip_rect.height
 			|| u->scaling_info->dst_rect.width != u->surface->dst_rect.width
-			|| u->scaling_info->dst_rect.height != u->surface->dst_rect.height)
-		return UPDATE_TYPE_FULL;
+			|| u->scaling_info->dst_rect.height != u->surface->dst_rect.height) {
+		update_flags->bits.scaling_change = 1;
+
+		if ((u->scaling_info->dst_rect.width < u->surface->dst_rect.width
+			|| u->scaling_info->dst_rect.height < u->surface->dst_rect.height)
+				&& (u->scaling_info->dst_rect.width < u->surface->src_rect.width
+					|| u->scaling_info->dst_rect.height < u->surface->src_rect.height))
+			/* Making dst rect smaller requires a bandwidth change */
+			update_flags->bits.bandwidth_change = 1;
+	}
+
+	if (u->scaling_info->src_rect.width != u->surface->src_rect.width
+		|| u->scaling_info->src_rect.height != u->surface->src_rect.height) {
+
+		update_flags->bits.scaling_change = 1;
+		if (u->scaling_info->src_rect.width > u->surface->src_rect.width
+				&& u->scaling_info->src_rect.height > u->surface->src_rect.height)
+			/* Making src rect bigger requires a bandwidth change */
+			update_flags->bits.clock_change = 1;
+	}
 
 	if (u->scaling_info->src_rect.x != u->surface->src_rect.x
 			|| u->scaling_info->src_rect.y != u->surface->src_rect.y
@@ -1191,41 +1057,56 @@ static enum surface_update_type  get_scaling_info_update_type(
 			|| u->scaling_info->clip_rect.y != u->surface->clip_rect.y
 			|| u->scaling_info->dst_rect.x != u->surface->dst_rect.x
 			|| u->scaling_info->dst_rect.y != u->surface->dst_rect.y)
+		update_flags->bits.position_change = 1;
+
+	if (update_flags->bits.clock_change
+			|| update_flags->bits.bandwidth_change)
+		return UPDATE_TYPE_FULL;
+
+	if (update_flags->bits.scaling_change
+			|| update_flags->bits.position_change)
 		return UPDATE_TYPE_MED;
 
 	return UPDATE_TYPE_FAST;
 }
 
-static enum surface_update_type det_surface_update(
-		const struct dc *dc,
-		const struct dc_surface_update *u,
-		int surface_index)
+static enum surface_update_type det_surface_update(const struct dc *dc,
+		const struct dc_surface_update *u)
 {
 	const struct dc_state *context = dc->current_state;
-	enum surface_update_type type = UPDATE_TYPE_FAST;
+	enum surface_update_type type;
 	enum surface_update_type overall_type = UPDATE_TYPE_FAST;
+	union surface_update_flags *update_flags = &u->surface->update_flags;
+
+	update_flags->raw = 0; // Reset all flags
 
-	if (!is_surface_in_context(context, u->surface))
+	if (!is_surface_in_context(context, u->surface)) {
+		update_flags->bits.new_plane = 1;
 		return UPDATE_TYPE_FULL;
+	}
 
-	type = get_plane_info_update_type(u, surface_index);
-	if (overall_type < type)
-		overall_type = type;
+	type = get_plane_info_update_type(u);
+	elevate_update_type(&overall_type, type);
 
 	type = get_scaling_info_update_type(u);
-	if (overall_type < type)
-		overall_type = type;
+	elevate_update_type(&overall_type, type);
+
+	if (u->in_transfer_func)
+		update_flags->bits.in_transfer_func = 1;
 
-	if (u->in_transfer_func ||
-		u->hdr_static_metadata) {
-		if (overall_type < UPDATE_TYPE_MED)
-			overall_type = UPDATE_TYPE_MED;
+	if (u->input_csc_color_matrix)
+		update_flags->bits.input_csc_change = 1;
+
+	if (update_flags->bits.in_transfer_func
+			|| update_flags->bits.input_csc_change) {
+		type = UPDATE_TYPE_MED;
+		elevate_update_type(&overall_type, type);
 	}
 
 	return overall_type;
 }
 
-enum surface_update_type dc_check_update_surfaces_for_stream(
+static enum surface_update_type check_update_surfaces_for_stream(
 		struct dc *dc,
 		struct dc_surface_update *updates,
 		int surface_count,
@@ -1243,18 +1124,38 @@ enum surface_update_type dc_check_update_surfaces_for_stream(
 
 	for (i = 0 ; i < surface_count; i++) {
 		enum surface_update_type type =
-				det_surface_update(dc, &updates[i], i);
+				det_surface_update(dc, &updates[i]);
 
 		if (type == UPDATE_TYPE_FULL)
 			return type;
 
-		if (overall_type < type)
-			overall_type = type;
+		elevate_update_type(&overall_type, type);
 	}
 
 	return overall_type;
 }
 
+enum surface_update_type dc_check_update_surfaces_for_stream(
+		struct dc *dc,
+		struct dc_surface_update *updates,
+		int surface_count,
+		struct dc_stream_update *stream_update,
+		const struct dc_stream_status *stream_status)
+{
+	int i;
+	enum surface_update_type type;
+
+	for (i = 0; i < surface_count; i++)
+		updates[i].surface->update_flags.raw = 0;
+
+	type = check_update_surfaces_for_stream(dc, updates, surface_count, stream_update, stream_status);
+	if (type == UPDATE_TYPE_FULL)
+		for (i = 0; i < surface_count; i++)
+			updates[i].surface->update_flags.bits.full_update = 1;
+
+	return type;
+}
+
 static struct dc_stream_status *stream_get_status(
 	struct dc_state *ctx,
 	struct dc_stream_state *stream)
@@ -1288,14 +1189,6 @@ static void commit_planes_for_stream(struct dc *dc,
 		context_clock_trace(dc, context);
 	}
 
-	if (update_type > UPDATE_TYPE_FAST) {
-		for (j = 0; j < dc->res_pool->pipe_count; j++) {
-			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[j];
-
-			dc->hwss.wait_for_mpcc_disconnect(dc, dc->res_pool, pipe_ctx);
-		}
-	}
-
 	if (surface_count == 0) {
 		/*
 		 * In case of turning off screen, no need to program front end a second time.
@@ -1305,103 +1198,58 @@ static void commit_planes_for_stream(struct dc *dc,
 		return;
 	}
 
-	/* Lock pipes for provided surfaces, or all active if full update*/
-	for (i = 0; i < surface_count; i++) {
-		struct dc_plane_state *plane_state = srf_updates[i].surface;
-
-		for (j = 0; j < dc->res_pool->pipe_count; j++) {
-			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[j];
-
-			if (update_type != UPDATE_TYPE_FULL && pipe_ctx->plane_state != plane_state)
-				continue;
-			if (!pipe_ctx->plane_state || pipe_ctx->top_pipe)
-				continue;
-
-			dc->hwss.pipe_control_lock(
-					dc,
-					pipe_ctx,
-					true);
-		}
-		if (update_type == UPDATE_TYPE_FULL)
-			break;
-	}
-
 	/* Full fe update*/
 	for (j = 0; j < dc->res_pool->pipe_count; j++) {
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[j];
 
-		if (update_type != UPDATE_TYPE_FULL || !pipe_ctx->plane_state)
+		if (update_type == UPDATE_TYPE_FAST || !pipe_ctx->plane_state)
 			continue;
 
-		if (!pipe_ctx->top_pipe && pipe_ctx->stream) {
-			struct dc_stream_status *stream_status = stream_get_status(context, pipe_ctx->stream);
+		if (!pipe_ctx->top_pipe &&
+		    pipe_ctx->stream &&
+		    pipe_ctx->stream == stream) {
+			struct dc_stream_status *stream_status =
+					stream_get_status(context, pipe_ctx->stream);
 
 			dc->hwss.apply_ctx_for_surface(
 					dc, pipe_ctx->stream, stream_status->plane_count, context);
 		}
 	}
 
-	if (update_type > UPDATE_TYPE_FAST)
+	if (update_type == UPDATE_TYPE_FULL)
 		context_timing_trace(dc, &context->res_ctx);
 
 	/* Perform requested Updates */
 	for (i = 0; i < surface_count; i++) {
 		struct dc_plane_state *plane_state = srf_updates[i].surface;
 
-		if (update_type == UPDATE_TYPE_MED)
-			dc->hwss.apply_ctx_for_surface(
-					dc, stream, surface_count, context);
-
 		for (j = 0; j < dc->res_pool->pipe_count; j++) {
 			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[j];
 
-			if (pipe_ctx->plane_state != plane_state)
+			if (pipe_ctx->stream != stream)
 				continue;
 
-			if (srf_updates[i].flip_addr)
-				dc->hwss.update_plane_addr(dc, pipe_ctx);
-
-			if (update_type == UPDATE_TYPE_FAST)
+			if (pipe_ctx->plane_state != plane_state)
 				continue;
 
-			/* work around to program degamma regs for split pipe after set mode. */
-			if (srf_updates[i].in_transfer_func || (pipe_ctx->top_pipe &&
-					pipe_ctx->top_pipe->plane_state == pipe_ctx->plane_state))
-				dc->hwss.set_input_transfer_func(
-						pipe_ctx, pipe_ctx->plane_state);
-
-			if (stream_update != NULL &&
-					stream_update->out_transfer_func != NULL) {
-				dc->hwss.set_output_transfer_func(
-						pipe_ctx, pipe_ctx->stream);
-			}
-
-			if (srf_updates[i].hdr_static_metadata) {
-				resource_build_info_frame(pipe_ctx);
-				dc->hwss.update_info_frame(pipe_ctx);
-			}
+			if (update_type == UPDATE_TYPE_FAST && srf_updates[i].flip_addr)
+					dc->hwss.update_plane_addr(dc, pipe_ctx);
 		}
 	}
 
-	/* Unlock pipes */
-	for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) {
-		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+	if (stream && stream_update && update_type > UPDATE_TYPE_FAST)
+		for (j = 0; j < dc->res_pool->pipe_count; j++) {
+			struct pipe_ctx *pipe_ctx =
+					&context->res_ctx.pipe_ctx[j];
 
-		for (j = 0; j < surface_count; j++) {
-			if (update_type != UPDATE_TYPE_FULL &&
-			    srf_updates[j].surface != pipe_ctx->plane_state)
+			if (pipe_ctx->stream != stream)
 				continue;
-			if (!pipe_ctx->plane_state || pipe_ctx->top_pipe)
-				continue;
-
-			dc->hwss.pipe_control_lock(
-					dc,
-					pipe_ctx,
-					false);
 
-			break;
+			if (stream_update->hdr_static_metadata) {
+				resource_build_info_frame(pipe_ctx);
+				dc->hwss.update_info_frame(pipe_ctx);
+			}
 		}
-	}
 }
 
 void dc_commit_updates_for_stream(struct dc *dc,
@@ -1473,10 +1321,7 @@ void dc_commit_updates_for_stream(struct dc *dc,
 				stream_update,
 				update_type,
 				context);
-
-	if (update_type >= UPDATE_TYPE_FULL)
-		dc_post_update_surfaces_to_stream(dc);
-
+	/*update current_State*/
 	if (dc->current_state != context) {
 
 		struct dc_state *old = dc->current_state;
@@ -1485,6 +1330,9 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		dc_release_state(old);
 
 	}
+	/*let's use current_state to update watermark etc*/
+	if (update_type >= UPDATE_TYPE_FULL)
+		dc_post_update_surfaces_to_stream(dc);
 
 	return;
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
index 6acee5426e4b..1babac07bcc9 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
@@ -1,4 +1,26 @@
 /*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+/*
  * dc_debug.c
  *
  *  Created on: Nov 3, 2016
@@ -137,6 +159,7 @@ void pre_surface_trace(
 				"plane_state->tiling_info.gfx8.pipe_config = %d;\n"
 				"plane_state->tiling_info.gfx8.array_mode = %d;\n"
 				"plane_state->color_space = %d;\n"
+				"plane_state->input_tf = %d;\n"
 				"plane_state->dcc.enable = %d;\n"
 				"plane_state->format = %d;\n"
 				"plane_state->rotation = %d;\n"
@@ -144,6 +167,7 @@ void pre_surface_trace(
 				plane_state->tiling_info.gfx8.pipe_config,
 				plane_state->tiling_info.gfx8.array_mode,
 				plane_state->color_space,
+				plane_state->input_tf,
 				plane_state->dcc.enable,
 				plane_state->format,
 				plane_state->rotation,
@@ -184,6 +208,7 @@ void update_surface_trace(
 		if (update->plane_info) {
 			SURFACE_TRACE(
 					"plane_info->color_space = %d;\n"
+					"plane_info->input_tf = %d;\n"
 					"plane_info->format = %d;\n"
 					"plane_info->plane_size.grph.surface_pitch = %d;\n"
 					"plane_info->plane_size.grph.surface_size.height = %d;\n"
@@ -192,6 +217,7 @@ void update_surface_trace(
 					"plane_info->plane_size.grph.surface_size.y = %d;\n"
 					"plane_info->rotation = %d;\n",
 					update->plane_info->color_space,
+					update->plane_info->input_tf,
 					update->plane_info->format,
 					update->plane_info->plane_size.grph.surface_pitch,
 					update->plane_info->plane_size.grph.surface_size.height,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
index 71993d5983bf..ebc96b720083 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
@@ -28,6 +28,8 @@
 #include "timing_generator.h"
 #include "hw_sequencer.h"
 
+#define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0]))
+
 /* used as index in array of black_color_format */
 enum black_color_format {
 	BLACK_COLOR_FORMAT_RGB_FULLRANGE = 0,
@@ -38,6 +40,15 @@ enum black_color_format {
 	BLACK_COLOR_FORMAT_DEBUG,
 };
 
+enum dc_color_space_type {
+	COLOR_SPACE_RGB_TYPE,
+	COLOR_SPACE_RGB_LIMITED_TYPE,
+	COLOR_SPACE_YCBCR601_TYPE,
+	COLOR_SPACE_YCBCR709_TYPE,
+	COLOR_SPACE_YCBCR601_LIMITED_TYPE,
+	COLOR_SPACE_YCBCR709_LIMITED_TYPE
+};
+
 static const struct tg_color black_color_format[] = {
 	/* BlackColorFormat_RGB_FullRange */
 	{0, 0, 0},
@@ -53,6 +64,140 @@ static const struct tg_color black_color_format[] = {
 	{0xff, 0xff, 0},
 };
 
+struct out_csc_color_matrix_type {
+	enum dc_color_space_type color_space_type;
+	uint16_t regval[12];
+};
+
+static const struct out_csc_color_matrix_type output_csc_matrix[] = {
+	{ COLOR_SPACE_RGB_TYPE,
+		{ 0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} },
+	{ COLOR_SPACE_RGB_LIMITED_TYPE,
+		{ 0x1B67, 0, 0, 0x201, 0, 0x1B67, 0, 0x201, 0, 0, 0x1B67, 0x201} },
+	{ COLOR_SPACE_YCBCR601_TYPE,
+		{ 0xE04, 0xF444, 0xFDB9, 0x1004, 0x831, 0x1016, 0x320, 0x201, 0xFB45,
+				0xF6B7, 0xE04, 0x1004} },
+	{ COLOR_SPACE_YCBCR709_TYPE,
+		{ 0xE04, 0xF345, 0xFEB7, 0x1004, 0x5D3, 0x1399, 0x1FA,
+				0x201, 0xFCCA, 0xF533, 0xE04, 0x1004} },
+
+	/* TODO: correct values below */
+	{ COLOR_SPACE_YCBCR601_LIMITED_TYPE,
+		{ 0xE00, 0xF447, 0xFDB9, 0x1000, 0x991,
+				0x12C9, 0x3A6, 0x200, 0xFB47, 0xF6B9, 0xE00, 0x1000} },
+	{ COLOR_SPACE_YCBCR709_LIMITED_TYPE,
+		{ 0xE00, 0xF349, 0xFEB7, 0x1000, 0x6CE, 0x16E3,
+				0x24F, 0x200, 0xFCCB, 0xF535, 0xE00, 0x1000} },
+};
+
+static bool is_rgb_type(
+		enum dc_color_space color_space)
+{
+	bool ret = false;
+
+	if (color_space == COLOR_SPACE_SRGB			||
+		color_space == COLOR_SPACE_XR_RGB		||
+		color_space == COLOR_SPACE_MSREF_SCRGB		||
+		color_space == COLOR_SPACE_2020_RGB_FULLRANGE	||
+		color_space == COLOR_SPACE_ADOBERGB		||
+		color_space == COLOR_SPACE_DCIP3	||
+		color_space == COLOR_SPACE_DOLBYVISION)
+		ret = true;
+	return ret;
+}
+
+static bool is_rgb_limited_type(
+		enum dc_color_space color_space)
+{
+	bool ret = false;
+
+	if (color_space == COLOR_SPACE_SRGB_LIMITED		||
+		color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE)
+		ret = true;
+	return ret;
+}
+
+static bool is_ycbcr601_type(
+		enum dc_color_space color_space)
+{
+	bool ret = false;
+
+	if (color_space == COLOR_SPACE_YCBCR601	||
+		color_space == COLOR_SPACE_XV_YCC_601)
+		ret = true;
+	return ret;
+}
+
+static bool is_ycbcr601_limited_type(
+		enum dc_color_space color_space)
+{
+	bool ret = false;
+
+	if (color_space == COLOR_SPACE_YCBCR601_LIMITED)
+		ret = true;
+	return ret;
+}
+
+static bool is_ycbcr709_type(
+		enum dc_color_space color_space)
+{
+	bool ret = false;
+
+	if (color_space == COLOR_SPACE_YCBCR709	||
+		color_space == COLOR_SPACE_XV_YCC_709)
+		ret = true;
+	return ret;
+}
+
+static bool is_ycbcr709_limited_type(
+		enum dc_color_space color_space)
+{
+	bool ret = false;
+
+	if (color_space == COLOR_SPACE_YCBCR709_LIMITED)
+		ret = true;
+	return ret;
+}
+enum dc_color_space_type get_color_space_type(enum dc_color_space color_space)
+{
+	enum dc_color_space_type type = COLOR_SPACE_RGB_TYPE;
+
+	if (is_rgb_type(color_space))
+		type = COLOR_SPACE_RGB_TYPE;
+	else if (is_rgb_limited_type(color_space))
+		type = COLOR_SPACE_RGB_LIMITED_TYPE;
+	else if (is_ycbcr601_type(color_space))
+		type = COLOR_SPACE_YCBCR601_TYPE;
+	else if (is_ycbcr709_type(color_space))
+		type = COLOR_SPACE_YCBCR709_TYPE;
+	else if (is_ycbcr601_limited_type(color_space))
+		type = COLOR_SPACE_YCBCR601_LIMITED_TYPE;
+	else if (is_ycbcr709_limited_type(color_space))
+		type = COLOR_SPACE_YCBCR709_LIMITED_TYPE;
+
+	return type;
+}
+
+const uint16_t *find_color_matrix(enum dc_color_space color_space,
+							uint32_t *array_size)
+{
+	int i;
+	enum dc_color_space_type type;
+	const uint16_t *val = NULL;
+	int arr_size = NUM_ELEMENTS(output_csc_matrix);
+
+	type = get_color_space_type(color_space);
+	for (i = 0; i < arr_size; i++)
+		if (output_csc_matrix[i].color_space_type == type) {
+			val = output_csc_matrix[i].regval;
+			*array_size = 12;
+			break;
+		}
+
+	return val;
+}
+
+
 void color_space_to_black_color(
 	const struct dc *dc,
 	enum dc_color_space colorspace,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 0602610489d7..a37428271573 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -480,22 +480,6 @@ static void detect_dp(
 		sink_caps->signal = SIGNAL_TYPE_DISPLAY_PORT;
 		detect_dp_sink_caps(link);
 
-		/* DP active dongles */
-		if (is_dp_active_dongle(link)) {
-			link->type = dc_connection_active_dongle;
-			if (!link->dpcd_caps.sink_count.bits.SINK_COUNT) {
-				/*
-				 * active dongle unplug processing for short irq
-				 */
-				link_disconnect_sink(link);
-				return;
-			}
-
-			if (link->dpcd_caps.dongle_type !=
-			DISPLAY_DONGLE_DP_HDMI_CONVERTER) {
-				*converter_disable_audio = true;
-			}
-		}
 		if (is_mst_supported(link)) {
 			sink_caps->signal = SIGNAL_TYPE_DISPLAY_PORT_MST;
 			link->type = dc_connection_mst_branch;
@@ -535,6 +519,22 @@ static void detect_dp(
 				sink_caps->signal = SIGNAL_TYPE_DISPLAY_PORT;
 			}
 		}
+
+		if (link->type != dc_connection_mst_branch &&
+			is_dp_active_dongle(link)) {
+			/* DP active dongles */
+			link->type = dc_connection_active_dongle;
+			if (!link->dpcd_caps.sink_count.bits.SINK_COUNT) {
+				/*
+				 * active dongle unplug processing for short irq
+				 */
+				link_disconnect_sink(link);
+				return;
+			}
+
+			if (link->dpcd_caps.dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER)
+				*converter_disable_audio = true;
+		}
 	} else {
 		/* DP passive dongles */
 		sink_caps->signal = dp_passive_dongle_detection(link->ddc,
@@ -938,8 +938,9 @@ static bool construct(
 	link->link_id = bios->funcs->get_connector_id(bios, init_params->connector_index);
 
 	if (link->link_id.type != OBJECT_TYPE_CONNECTOR) {
-		dm_error("%s: Invalid Connector ObjectID from Adapter Service for connector index:%d!\n",
-				__func__, init_params->connector_index);
+		dm_error("%s: Invalid Connector ObjectID from Adapter Service for connector index:%d! type %d expected %d\n",
+			 __func__, init_params->connector_index,
+			 link->link_id.type, OBJECT_TYPE_CONNECTOR);
 		goto create_fail;
 	}
 
@@ -1271,6 +1272,24 @@ static enum dc_status enable_link_dp(
 	return status;
 }
 
+static enum dc_status enable_link_edp(
+		struct dc_state *state,
+		struct pipe_ctx *pipe_ctx)
+{
+	enum dc_status status;
+	struct dc_stream_state *stream = pipe_ctx->stream;
+	struct dc_link *link = stream->sink->link;
+
+	link->dc->hwss.edp_power_control(link, true);
+	link->dc->hwss.edp_wait_for_hpd_ready(link, true);
+
+	status = enable_link_dp(state, pipe_ctx);
+
+	link->dc->hwss.edp_backlight_control(link, true);
+
+	return status;
+}
+
 static enum dc_status enable_link_dp_mst(
 		struct dc_state *state,
 		struct pipe_ctx *pipe_ctx)
@@ -1746,9 +1765,11 @@ static enum dc_status enable_link(
 	enum dc_status status = DC_ERROR_UNEXPECTED;
 	switch (pipe_ctx->stream->signal) {
 	case SIGNAL_TYPE_DISPLAY_PORT:
-	case SIGNAL_TYPE_EDP:
 		status = enable_link_dp(state, pipe_ctx);
 		break;
+	case SIGNAL_TYPE_EDP:
+		status = enable_link_edp(state, pipe_ctx);
+		break;
 	case SIGNAL_TYPE_DISPLAY_PORT_MST:
 		status = enable_link_dp_mst(state, pipe_ctx);
 		msleep(200);
@@ -1798,7 +1819,71 @@ static void disable_link(struct dc_link *link, enum signal_type signal)
 		else
 			dp_disable_link_phy_mst(link, signal);
 	} else
-		link->link_enc->funcs->disable_output(link->link_enc, signal, link);
+		link->link_enc->funcs->disable_output(link->link_enc, signal);
+}
+
+static bool dp_active_dongle_validate_timing(
+		const struct dc_crtc_timing *timing,
+		const struct dc_dongle_caps *dongle_caps)
+{
+	unsigned int required_pix_clk = timing->pix_clk_khz;
+
+	if (dongle_caps->dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER ||
+		dongle_caps->extendedCapValid == false)
+		return true;
+
+	/* Check Pixel Encoding */
+	switch (timing->pixel_encoding) {
+	case PIXEL_ENCODING_RGB:
+	case PIXEL_ENCODING_YCBCR444:
+		break;
+	case PIXEL_ENCODING_YCBCR422:
+		if (!dongle_caps->is_dp_hdmi_ycbcr422_pass_through)
+			return false;
+		break;
+	case PIXEL_ENCODING_YCBCR420:
+		if (!dongle_caps->is_dp_hdmi_ycbcr420_pass_through)
+			return false;
+		break;
+	default:
+		/* Invalid Pixel Encoding*/
+		return false;
+	}
+
+
+	/* Check Color Depth and Pixel Clock */
+	if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		required_pix_clk /= 2;
+	else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
+		required_pix_clk = required_pix_clk * 2 / 3;
+
+	switch (timing->display_color_depth) {
+	case COLOR_DEPTH_666:
+	case COLOR_DEPTH_888:
+		/*888 and 666 should always be supported*/
+		break;
+	case COLOR_DEPTH_101010:
+		if (dongle_caps->dp_hdmi_max_bpc < 10)
+			return false;
+		required_pix_clk = required_pix_clk * 10 / 8;
+		break;
+	case COLOR_DEPTH_121212:
+		if (dongle_caps->dp_hdmi_max_bpc < 12)
+			return false;
+		required_pix_clk = required_pix_clk * 12 / 8;
+		break;
+
+	case COLOR_DEPTH_141414:
+	case COLOR_DEPTH_161616:
+	default:
+		/* These color depths are currently not supported */
+		return false;
+	}
+
+	if (required_pix_clk > dongle_caps->dp_hdmi_max_pixel_clk)
+		return false;
+
+	return true;
 }
 
 enum dc_status dc_link_validate_mode_timing(
@@ -1807,6 +1892,7 @@ enum dc_status dc_link_validate_mode_timing(
 		const struct dc_crtc_timing *timing)
 {
 	uint32_t max_pix_clk = stream->sink->dongle_max_pix_clk;
+	struct dc_dongle_caps *dongle_caps = &link->dpcd_caps.dongle_caps;
 
 	/* A hack to avoid failing any modes for EDID override feature on
 	 * topology change such as lower quality cable for DP or different dongle
@@ -1814,8 +1900,13 @@ enum dc_status dc_link_validate_mode_timing(
 	if (link->remote_sinks[0])
 		return DC_OK;
 
+	/* Passive Dongle */
 	if (0 != max_pix_clk && timing->pix_clk_khz > max_pix_clk)
-		return DC_EXCEED_DONGLE_MAX_CLK;
+		return DC_EXCEED_DONGLE_CAP;
+
+	/* Active Dongle*/
+	if (!dp_active_dongle_validate_timing(timing, dongle_caps))
+		return DC_EXCEED_DONGLE_CAP;
 
 	switch (stream->signal) {
 	case SIGNAL_TYPE_EDP:
@@ -1839,12 +1930,18 @@ bool dc_link_set_backlight_level(const struct dc_link *link, uint32_t level,
 {
 	struct dc  *core_dc = link->ctx->dc;
 	struct abm *abm = core_dc->res_pool->abm;
+	struct dmcu *dmcu = core_dc->res_pool->dmcu;
 	unsigned int controller_id = 0;
+	bool use_smooth_brightness = true;
 	int i;
 
-	if ((abm == NULL) || (abm->funcs->set_backlight_level == NULL))
+	if ((dmcu == NULL) ||
+		(abm == NULL) ||
+		(abm->funcs->set_backlight_level == NULL))
 		return false;
 
+	use_smooth_brightness = dmcu->funcs->is_dmcu_initialized(dmcu);
+
 	dm_logger_write(link->ctx->logger, LOG_BACKLIGHT,
 			"New Backlight level: %d (0x%X)\n", level, level);
 
@@ -1867,7 +1964,8 @@ bool dc_link_set_backlight_level(const struct dc_link *link, uint32_t level,
 				abm,
 				level,
 				frame_ramp,
-				controller_id);
+				controller_id,
+				use_smooth_brightness);
 	}
 
 	return true;
@@ -1884,144 +1982,6 @@ bool dc_link_set_psr_enable(const struct dc_link *link, bool enable, bool wait)
 	return true;
 }
 
-bool dc_link_get_psr_state(const struct dc_link *link, uint32_t *psr_state)
-{
-	struct dc  *core_dc = link->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
-
-	if (dmcu != NULL && link->psr_enabled)
-		dmcu->funcs->get_psr_state(dmcu, psr_state);
-
-	return true;
-}
-
-bool dc_link_setup_psr(struct dc_link *link,
-		const struct dc_stream_state *stream, struct psr_config *psr_config,
-		struct psr_context *psr_context)
-{
-	struct dc  *core_dc = link->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
-	int i;
-
-	psr_context->controllerId = CONTROLLER_ID_UNDEFINED;
-
-	if (link != NULL &&
-		dmcu != NULL) {
-		/* updateSinkPsrDpcdConfig*/
-		union dpcd_psr_configuration psr_configuration;
-
-		memset(&psr_configuration, 0, sizeof(psr_configuration));
-
-		psr_configuration.bits.ENABLE                    = 1;
-		psr_configuration.bits.CRC_VERIFICATION          = 1;
-		psr_configuration.bits.FRAME_CAPTURE_INDICATION  =
-				psr_config->psr_frame_capture_indication_req;
-
-		/* Check for PSR v2*/
-		if (psr_config->psr_version == 0x2) {
-			/* For PSR v2 selective update.
-			 * Indicates whether sink should start capturing
-			 * immediately following active scan line,
-			 * or starting with the 2nd active scan line.
-			 */
-			psr_configuration.bits.LINE_CAPTURE_INDICATION = 0;
-			/*For PSR v2, determines whether Sink should generate
-			 * IRQ_HPD when CRC mismatch is detected.
-			 */
-			psr_configuration.bits.IRQ_HPD_WITH_CRC_ERROR    = 1;
-		}
-
-		dm_helpers_dp_write_dpcd(
-			link->ctx,
-			link,
-			368,
-			&psr_configuration.raw,
-			sizeof(psr_configuration.raw));
-
-		psr_context->channel = link->ddc->ddc_pin->hw_info.ddc_channel;
-		psr_context->transmitterId = link->link_enc->transmitter;
-		psr_context->engineId = link->link_enc->preferred_engine;
-
-		for (i = 0; i < MAX_PIPES; i++) {
-			if (core_dc->current_state->res_ctx.pipe_ctx[i].stream
-					== stream) {
-				/* dmcu -1 for all controller id values,
-				 * therefore +1 here
-				 */
-				psr_context->controllerId =
-					core_dc->current_state->res_ctx.
-					pipe_ctx[i].stream_res.tg->inst + 1;
-				break;
-			}
-		}
-
-		/* Hardcoded for now.  Can be Pcie or Uniphy (or Unknown)*/
-		psr_context->phyType = PHY_TYPE_UNIPHY;
-		/*PhyId is associated with the transmitter id*/
-		psr_context->smuPhyId = link->link_enc->transmitter;
-
-		psr_context->crtcTimingVerticalTotal = stream->timing.v_total;
-		psr_context->vsyncRateHz = div64_u64(div64_u64((stream->
-						timing.pix_clk_khz * 1000),
-						stream->timing.v_total),
-						stream->timing.h_total);
-
-		psr_context->psrSupportedDisplayConfig = true;
-		psr_context->psrExitLinkTrainingRequired =
-			psr_config->psr_exit_link_training_required;
-		psr_context->sdpTransmitLineNumDeadline =
-			psr_config->psr_sdp_transmit_line_num_deadline;
-		psr_context->psrFrameCaptureIndicationReq =
-			psr_config->psr_frame_capture_indication_req;
-
-		psr_context->skipPsrWaitForPllLock = 0; /* only = 1 in KV */
-
-		psr_context->numberOfControllers =
-				link->dc->res_pool->res_cap->num_timing_generator;
-
-		psr_context->rfb_update_auto_en = true;
-
-		/* 2 frames before enter PSR. */
-		psr_context->timehyst_frames = 2;
-		/* half a frame
-		 * (units in 100 lines, i.e. a value of 1 represents 100 lines)
-		 */
-		psr_context->hyst_lines = stream->timing.v_total / 2 / 100;
-		psr_context->aux_repeats = 10;
-
-		psr_context->psr_level.u32all = 0;
-
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-		/*skip power down the single pipe since it blocks the cstate*/
-		if (ASIC_REV_IS_RAVEN(link->ctx->asic_id.hw_internal_rev))
-			psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true;
-#endif
-
-		/* SMU will perform additional powerdown sequence.
-		 * For unsupported ASICs, set psr_level flag to skip PSR
-		 *  static screen notification to SMU.
-		 *  (Always set for DAL2, did not check ASIC)
-		 */
-		psr_context->psr_level.bits.SKIP_SMU_NOTIFICATION = 1;
-
-		/* Complete PSR entry before aborting to prevent intermittent
-		 * freezes on certain eDPs
-		 */
-		psr_context->psr_level.bits.DISABLE_PSR_ENTRY_ABORT = 1;
-
-		/* Controls additional delay after remote frame capture before
-		 * continuing power down, default = 0
-		 */
-		psr_context->frame_delay = 0;
-
-		link->psr_enabled = true;
-		dmcu->funcs->setup_psr(dmcu, link, psr_context);
-		return true;
-	} else
-		return false;
-
-}
-
 const struct dc_link_status *dc_link_get_status(const struct dc_link *link)
 {
 	return &link->link_status;
@@ -2350,6 +2310,9 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx, int option)
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 		deallocate_mst_payload(pipe_ctx);
 
+	if (pipe_ctx->stream->signal == SIGNAL_TYPE_EDP)
+		core_dc->hwss.edp_backlight_control(pipe_ctx->stream->sink->link, false);
+
 	core_dc->hwss.disable_stream(pipe_ctx, option);
 
 	disable_link(pipe_ctx->stream->sink->link, pipe_ctx->stream->signal);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index ced42484dcfc..61e8c3e02d16 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -220,8 +220,7 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 		size_in_bytes);
 
 	dm_logger_write(link->ctx->logger, LOG_HW_LINK_TRAINING,
-		"%s:\n %x VS set = %x  PE set = %x \
-		max VS Reached = %x  max PE Reached = %x\n",
+		"%s:\n %x VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
 		__func__,
 		DP_TRAINING_LANE0_SET,
 		dpcd_lane[0].bits.VOLTAGE_SWING_SET,
@@ -558,8 +557,7 @@ static void dpcd_set_lane_settings(
 	*/
 
 	dm_logger_write(link->ctx->logger, LOG_HW_LINK_TRAINING,
-		"%s\n %x VS set = %x  PE set = %x \
-		max VS Reached = %x  max PE Reached = %x\n",
+		"%s\n %x VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
 		__func__,
 		DP_TRAINING_LANE0_SET,
 		dpcd_lane[0].bits.VOLTAGE_SWING_SET,
@@ -872,9 +870,8 @@ static bool perform_clock_recovery_sequence(
 	if (retry_count >= LINK_TRAINING_MAX_CR_RETRY) {
 		ASSERT(0);
 		dm_logger_write(link->ctx->logger, LOG_ERROR,
-			"%s: Link Training Error, could not \
-			 get CR after %d tries. \
-			Possibly voltage swing issue", __func__,
+			"%s: Link Training Error, could not get CR after %d tries. Possibly voltage swing issue",
+			__func__,
 			LINK_TRAINING_MAX_CR_RETRY);
 
 	}
@@ -1473,6 +1470,12 @@ void decide_link_settings(struct dc_stream_state *stream,
 		return;
 	}
 
+	/* EDP use the link cap setting */
+	if (stream->sink->sink_signal == SIGNAL_TYPE_EDP) {
+		*link_setting = link->verified_link_cap;
+		return;
+	}
+
 	/* search for the minimum link setting that:
 	 * 1. is supported according to the link training result
 	 * 2. could support the b/w requested by the timing
@@ -1512,7 +1515,7 @@ static bool hpd_rx_irq_check_link_loss_status(
 	struct dc_link *link,
 	union hpd_irq_data *hpd_irq_dpcd_data)
 {
-	uint8_t irq_reg_rx_power_state;
+	uint8_t irq_reg_rx_power_state = 0;
 	enum dc_status dpcd_result = DC_ERROR_UNEXPECTED;
 	union lane_status lane_status;
 	uint32_t lane;
@@ -1524,60 +1527,55 @@ static bool hpd_rx_irq_check_link_loss_status(
 
 	if (link->cur_link_settings.lane_count == 0)
 		return return_code;
-	/*1. Check that we can handle interrupt: Not in FS DOS,
-	 *  Not in "Display Timeout" state, Link is trained.
-	 */
 
-	dpcd_result = core_link_read_dpcd(link,
-		DP_SET_POWER,
-		&irq_reg_rx_power_state,
-		sizeof(irq_reg_rx_power_state));
+	/*1. Check that Link Status changed, before re-training.*/
 
-	if (dpcd_result != DC_OK) {
-		irq_reg_rx_power_state = DP_SET_POWER_D0;
-		dm_logger_write(link->ctx->logger, LOG_HW_HPD_IRQ,
-			"%s: DPCD read failed to obtain power state.\n",
-			__func__);
+	/*parse lane status*/
+	for (lane = 0; lane < link->cur_link_settings.lane_count; lane++) {
+		/* check status of lanes 0,1
+		 * changed DpcdAddress_Lane01Status (0x202)
+		 */
+		lane_status.raw = get_nibble_at_index(
+			&hpd_irq_dpcd_data->bytes.lane01_status.raw,
+			lane);
+
+		if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
+			!lane_status.bits.CR_DONE_0 ||
+			!lane_status.bits.SYMBOL_LOCKED_0) {
+			/* if one of the channel equalization, clock
+			 * recovery or symbol lock is dropped
+			 * consider it as (link has been
+			 * dropped) dp sink status has changed
+			 */
+			sink_status_changed = true;
+			break;
+		}
 	}
 
-	if (irq_reg_rx_power_state == DP_SET_POWER_D0) {
-
-		/*2. Check that Link Status changed, before re-training.*/
-
-		/*parse lane status*/
-		for (lane = 0;
-			lane < link->cur_link_settings.lane_count;
-			lane++) {
+	/* Check interlane align.*/
+	if (sink_status_changed ||
+		!hpd_irq_dpcd_data->bytes.lane_status_updated.bits.INTERLANE_ALIGN_DONE) {
 
-			/* check status of lanes 0,1
-			 * changed DpcdAddress_Lane01Status (0x202)*/
-			lane_status.raw = get_nibble_at_index(
-				&hpd_irq_dpcd_data->bytes.lane01_status.raw,
-				lane);
-
-			if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
-				!lane_status.bits.CR_DONE_0 ||
-				!lane_status.bits.SYMBOL_LOCKED_0) {
-				/* if one of the channel equalization, clock
-				 * recovery or symbol lock is dropped
-				 * consider it as (link has been
-				 * dropped) dp sink status has changed*/
-				sink_status_changed = true;
-				break;
-			}
+		dm_logger_write(link->ctx->logger, LOG_HW_HPD_IRQ,
+			"%s: Link Status changed.\n", __func__);
 
-		}
+		return_code = true;
 
-		/* Check interlane align.*/
-		if (sink_status_changed ||
-			!hpd_irq_dpcd_data->bytes.lane_status_updated.bits.
-			INTERLANE_ALIGN_DONE) {
+		/*2. Check that we can handle interrupt: Not in FS DOS,
+		 *  Not in "Display Timeout" state, Link is trained.
+		 */
+		dpcd_result = core_link_read_dpcd(link,
+			DP_SET_POWER,
+			&irq_reg_rx_power_state,
+			sizeof(irq_reg_rx_power_state));
 
+		if (dpcd_result != DC_OK) {
 			dm_logger_write(link->ctx->logger, LOG_HW_HPD_IRQ,
-				"%s: Link Status changed.\n",
+				"%s: DPCD read failed to obtain power state.\n",
 				__func__);
-
-			return_code = true;
+		} else {
+			if (irq_reg_rx_power_state != DP_SET_POWER_D0)
+				return_code = false;
 		}
 	}
 
@@ -2062,6 +2060,24 @@ bool is_dp_active_dongle(const struct dc_link *link)
 			(dongle_type == DISPLAY_DONGLE_DP_HDMI_CONVERTER);
 }
 
+static int translate_dpcd_max_bpc(enum dpcd_downstream_port_max_bpc bpc)
+{
+	switch (bpc) {
+	case DOWN_STREAM_MAX_8BPC:
+		return 8;
+	case DOWN_STREAM_MAX_10BPC:
+		return 10;
+	case DOWN_STREAM_MAX_12BPC:
+		return 12;
+	case DOWN_STREAM_MAX_16BPC:
+		return 16;
+	default:
+		break;
+	}
+
+	return -1;
+}
+
 static void get_active_converter_info(
 	uint8_t data, struct dc_link *link)
 {
@@ -2114,7 +2130,7 @@ static void get_active_converter_info(
 
 				union dwnstream_port_caps_byte3_hdmi
 					hdmi_caps = {.raw = det_caps[3] };
-				union dwnstream_port_caps_byte1
+				union dwnstream_port_caps_byte2
 					hdmi_color_caps = {.raw = det_caps[2] };
 				link->dpcd_caps.dongle_caps.dp_hdmi_max_pixel_clk =
 					det_caps[1] * 25000;
@@ -2131,7 +2147,8 @@ static void get_active_converter_info(
 					hdmi_caps.bits.YCrCr420_CONVERSION;
 
 				link->dpcd_caps.dongle_caps.dp_hdmi_max_bpc =
-					hdmi_color_caps.bits.MAX_BITS_PER_COLOR_COMPONENT;
+					translate_dpcd_max_bpc(
+						hdmi_color_caps.bits.MAX_BITS_PER_COLOR_COMPONENT);
 
 				link->dpcd_caps.dongle_caps.extendedCapValid = true;
 			}
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
index 9a33b471270a..2096f2a179f2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
@@ -88,15 +88,7 @@ void dp_enable_link_phy(
 	}
 
 	if (dc_is_dp_sst_signal(signal)) {
-		if (signal == SIGNAL_TYPE_EDP) {
-			link->dc->hwss.edp_power_control(link->link_enc, true);
-			link_enc->funcs->enable_dp_output(
-						link_enc,
-						link_settings,
-						clock_source);
-			link->dc->hwss.edp_backlight_control(link, true);
-		} else
-			link_enc->funcs->enable_dp_output(
+		link_enc->funcs->enable_dp_output(
 						link_enc,
 						link_settings,
 						clock_source);
@@ -138,12 +130,11 @@ void dp_disable_link_phy(struct dc_link *link, enum signal_type signal)
 		dp_receiver_power_ctrl(link, false);
 
 	if (signal == SIGNAL_TYPE_EDP) {
-		link->dc->hwss.edp_backlight_control(link, false);
 		edp_receiver_ready_T9(link);
-		link->link_enc->funcs->disable_output(link->link_enc, signal, link);
-		link->dc->hwss.edp_power_control(link->link_enc, false);
+		link->link_enc->funcs->disable_output(link->link_enc, signal);
+		link->dc->hwss.edp_power_control(link, false);
 	} else
-		link->link_enc->funcs->disable_output(link->link_enc, signal, link);
+		link->link_enc->funcs->disable_output(link->link_enc, signal);
 
 	/* Clear current link setting.*/
 	memset(&link->cur_link_settings, 0,
@@ -286,8 +277,7 @@ void dp_retrain_link_dp_test(struct dc_link *link,
 
 			link->link_enc->funcs->disable_output(
 					link->link_enc,
-					SIGNAL_TYPE_DISPLAY_PORT,
-					link);
+					SIGNAL_TYPE_DISPLAY_PORT);
 
 			/* Clear current link setting. */
 			memset(&link->cur_link_settings, 0,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index d1cdf9f8853d..95b8dd0e53c6 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1,5 +1,5 @@
 /*
-* Copyright 2012-15 Advanced Micro Devices, Inc.
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -426,15 +426,8 @@ static enum pixel_format convert_pixel_format_to_dalsurface(
 
 static void rect_swap_helper(struct rect *rect)
 {
-	uint32_t temp = 0;
-
-	temp = rect->height;
-	rect->height = rect->width;
-	rect->width = temp;
-
-	temp = rect->x;
-	rect->x = rect->y;
-	rect->y = temp;
+	swap(rect->height, rect->width);
+	swap(rect->x, rect->y);
 }
 
 static void calculate_viewport(struct pipe_ctx *pipe_ctx)
@@ -505,28 +498,15 @@ static void calculate_viewport(struct pipe_ctx *pipe_ctx)
 	data->viewport_c.height = (data->viewport.height + vpc_div - 1) / vpc_div;
 
 	/* Handle hsplit */
-	if (pri_split || sec_split) {
-		/* HMirror XOR Secondary_pipe XOR Rotation_180 */
-		bool right_view = (sec_split != plane_state->horizontal_mirror) !=
-					(plane_state->rotation == ROTATION_ANGLE_180);
-
-		if (plane_state->rotation == ROTATION_ANGLE_90
-				|| plane_state->rotation == ROTATION_ANGLE_270)
-			/* Secondary_pipe XOR Rotation_270 */
-			right_view = (plane_state->rotation == ROTATION_ANGLE_270) != sec_split;
-
-		if (right_view) {
-			data->viewport.width /= 2;
-			data->viewport_c.width /= 2;
-			data->viewport.x +=  data->viewport.width;
-			data->viewport_c.x +=  data->viewport_c.width;
-			/* Ceil offset pipe */
-			data->viewport.width += data->viewport.width % 2;
-			data->viewport_c.width += data->viewport_c.width % 2;
-		} else {
-			data->viewport.width /= 2;
-			data->viewport_c.width /= 2;
-		}
+	if (sec_split) {
+		data->viewport.x +=  data->viewport.width / 2;
+		data->viewport_c.x +=  data->viewport_c.width / 2;
+		/* Ceil offset pipe */
+		data->viewport.width = (data->viewport.width + 1) / 2;
+		data->viewport_c.width = (data->viewport_c.width + 1) / 2;
+	} else if (pri_split) {
+		data->viewport.width /= 2;
+		data->viewport_c.width /= 2;
 	}
 
 	if (plane_state->rotation == ROTATION_ANGLE_90 ||
@@ -543,6 +523,11 @@ static void calculate_recout(struct pipe_ctx *pipe_ctx, struct view *recout_skip
 	struct rect surf_src = plane_state->src_rect;
 	struct rect surf_clip = plane_state->clip_rect;
 	int recout_full_x, recout_full_y;
+	bool pri_split = pipe_ctx->bottom_pipe &&
+			pipe_ctx->bottom_pipe->plane_state == pipe_ctx->plane_state;
+	bool sec_split = pipe_ctx->top_pipe &&
+			pipe_ctx->top_pipe->plane_state == pipe_ctx->plane_state;
+	bool top_bottom_split = stream->view_format == VIEW_3D_FORMAT_TOP_AND_BOTTOM;
 
 	if (pipe_ctx->plane_state->rotation == ROTATION_ANGLE_90 ||
 			pipe_ctx->plane_state->rotation == ROTATION_ANGLE_270)
@@ -577,35 +562,43 @@ static void calculate_recout(struct pipe_ctx *pipe_ctx, struct view *recout_skip
 						- pipe_ctx->plane_res.scl_data.recout.y;
 
 	/* Handle h & vsplit */
-	if (pipe_ctx->top_pipe && pipe_ctx->top_pipe->plane_state ==
-		pipe_ctx->plane_state) {
-		if (stream->view_format == VIEW_3D_FORMAT_TOP_AND_BOTTOM) {
-			pipe_ctx->plane_res.scl_data.recout.height /= 2;
-			pipe_ctx->plane_res.scl_data.recout.y += pipe_ctx->plane_res.scl_data.recout.height;
-			/* Floor primary pipe, ceil 2ndary pipe */
-			pipe_ctx->plane_res.scl_data.recout.height += pipe_ctx->plane_res.scl_data.recout.height % 2;
+	if (sec_split && top_bottom_split) {
+		pipe_ctx->plane_res.scl_data.recout.y +=
+				pipe_ctx->plane_res.scl_data.recout.height / 2;
+		/* Floor primary pipe, ceil 2ndary pipe */
+		pipe_ctx->plane_res.scl_data.recout.height =
+				(pipe_ctx->plane_res.scl_data.recout.height + 1) / 2;
+	} else if (pri_split && top_bottom_split)
+		pipe_ctx->plane_res.scl_data.recout.height /= 2;
+	else if (pri_split || sec_split) {
+		/* HMirror XOR Secondary_pipe XOR Rotation_180 */
+		bool right_view = (sec_split != plane_state->horizontal_mirror) !=
+					(plane_state->rotation == ROTATION_ANGLE_180);
+
+		if (plane_state->rotation == ROTATION_ANGLE_90
+				|| plane_state->rotation == ROTATION_ANGLE_270)
+			/* Secondary_pipe XOR Rotation_270 */
+			right_view = (plane_state->rotation == ROTATION_ANGLE_270) != sec_split;
+
+		if (right_view) {
+			pipe_ctx->plane_res.scl_data.recout.x +=
+					pipe_ctx->plane_res.scl_data.recout.width / 2;
+			/* Ceil offset pipe */
+			pipe_ctx->plane_res.scl_data.recout.width =
+					(pipe_ctx->plane_res.scl_data.recout.width + 1) / 2;
 		} else {
 			pipe_ctx->plane_res.scl_data.recout.width /= 2;
-			pipe_ctx->plane_res.scl_data.recout.x += pipe_ctx->plane_res.scl_data.recout.width;
-			pipe_ctx->plane_res.scl_data.recout.width += pipe_ctx->plane_res.scl_data.recout.width % 2;
 		}
-	} else if (pipe_ctx->bottom_pipe &&
-			pipe_ctx->bottom_pipe->plane_state == pipe_ctx->plane_state) {
-		if (stream->view_format == VIEW_3D_FORMAT_TOP_AND_BOTTOM)
-			pipe_ctx->plane_res.scl_data.recout.height /= 2;
-		else
-			pipe_ctx->plane_res.scl_data.recout.width /= 2;
 	}
-
 	/* Unclipped recout offset = stream dst offset + ((surf dst offset - stream surf_src offset)
 	 * 				* 1/ stream scaling ratio) - (surf surf_src offset * 1/ full scl
 	 * 				ratio)
 	 */
-	recout_full_x = stream->dst.x + (plane_state->dst_rect.x -  stream->src.x)
+	recout_full_x = stream->dst.x + (plane_state->dst_rect.x - stream->src.x)
 					* stream->dst.width / stream->src.width -
 			surf_src.x * plane_state->dst_rect.width / surf_src.width
 					* stream->dst.width / stream->src.width;
-	recout_full_y = stream->dst.y + (plane_state->dst_rect.y -  stream->src.y)
+	recout_full_y = stream->dst.y + (plane_state->dst_rect.y - stream->src.y)
 					* stream->dst.height / stream->src.height -
 			surf_src.y * plane_state->dst_rect.height / surf_src.height
 					* stream->dst.height / stream->src.height;
@@ -661,7 +654,20 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 	struct rect src = pipe_ctx->plane_state->src_rect;
 	int vpc_div = (data->format == PIXEL_FORMAT_420BPP8
 			|| data->format == PIXEL_FORMAT_420BPP10) ? 2 : 1;
+	bool flip_vert_scan_dir = false, flip_horz_scan_dir = false;
 
+	/*
+	 * Need to calculate the scan direction for viewport to make adjustments
+	 */
+	if (pipe_ctx->plane_state->rotation == ROTATION_ANGLE_180) {
+		flip_vert_scan_dir = true;
+		flip_horz_scan_dir = true;
+	} else if (pipe_ctx->plane_state->rotation == ROTATION_ANGLE_90)
+		flip_vert_scan_dir = true;
+	else if (pipe_ctx->plane_state->rotation == ROTATION_ANGLE_270)
+		flip_horz_scan_dir = true;
+	if (pipe_ctx->plane_state->horizontal_mirror)
+		flip_horz_scan_dir = !flip_horz_scan_dir;
 
 	if (pipe_ctx->plane_state->rotation == ROTATION_ANGLE_90 ||
 			pipe_ctx->plane_state->rotation == ROTATION_ANGLE_270) {
@@ -726,7 +732,7 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 	}
 
 	/* Adjust for non-0 viewport offset */
-	if (data->viewport.x) {
+	if (data->viewport.x && !flip_horz_scan_dir) {
 		int int_part;
 
 		data->inits.h = dal_fixed31_32_add(data->inits.h, dal_fixed31_32_mul_int(
@@ -747,7 +753,7 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 		data->inits.h = dal_fixed31_32_add_int(data->inits.h, int_part);
 	}
 
-	if (data->viewport_c.x) {
+	if (data->viewport_c.x && !flip_horz_scan_dir) {
 		int int_part;
 
 		data->inits.h_c = dal_fixed31_32_add(data->inits.h_c, dal_fixed31_32_mul_int(
@@ -768,7 +774,7 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 		data->inits.h_c = dal_fixed31_32_add_int(data->inits.h_c, int_part);
 	}
 
-	if (data->viewport.y) {
+	if (data->viewport.y && !flip_vert_scan_dir) {
 		int int_part;
 
 		data->inits.v = dal_fixed31_32_add(data->inits.v, dal_fixed31_32_mul_int(
@@ -789,7 +795,7 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 		data->inits.v = dal_fixed31_32_add_int(data->inits.v, int_part);
 	}
 
-	if (data->viewport_c.y) {
+	if (data->viewport_c.y && !flip_vert_scan_dir) {
 		int int_part;
 
 		data->inits.v_c = dal_fixed31_32_add(data->inits.v_c, dal_fixed31_32_mul_int(
@@ -856,6 +862,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	pipe_ctx->plane_res.scl_data.h_active = timing->h_addressable + timing->h_border_left + timing->h_border_right;
 	pipe_ctx->plane_res.scl_data.v_active = timing->v_addressable + timing->v_border_top + timing->v_border_bottom;
 
+
 	/* Taps calculations */
 	if (pipe_ctx->plane_res.xfm != NULL)
 		res = pipe_ctx->plane_res.xfm->funcs->transform_get_optimal_number_of_taps(
@@ -864,16 +871,21 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	if (pipe_ctx->plane_res.dpp != NULL)
 		res = pipe_ctx->plane_res.dpp->funcs->dpp_get_optimal_number_of_taps(
 				pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data, &plane_state->scaling_quality);
-
 	if (!res) {
 		/* Try 24 bpp linebuffer */
 		pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_24BPP;
 
-		res = pipe_ctx->plane_res.xfm->funcs->transform_get_optimal_number_of_taps(
-			pipe_ctx->plane_res.xfm, &pipe_ctx->plane_res.scl_data, &plane_state->scaling_quality);
+		if (pipe_ctx->plane_res.xfm != NULL)
+			res = pipe_ctx->plane_res.xfm->funcs->transform_get_optimal_number_of_taps(
+					pipe_ctx->plane_res.xfm,
+					&pipe_ctx->plane_res.scl_data,
+					&plane_state->scaling_quality);
 
-		res = pipe_ctx->plane_res.dpp->funcs->dpp_get_optimal_number_of_taps(
-			pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data, &plane_state->scaling_quality);
+		if (pipe_ctx->plane_res.dpp != NULL)
+			res = pipe_ctx->plane_res.dpp->funcs->dpp_get_optimal_number_of_taps(
+					pipe_ctx->plane_res.dpp,
+					&pipe_ctx->plane_res.scl_data,
+					&plane_state->scaling_quality);
 	}
 
 	if (res)
@@ -991,8 +1003,10 @@ static struct pipe_ctx *acquire_free_pipe_for_stream(
 
 	head_pipe = resource_get_head_pipe_for_stream(res_ctx, stream);
 
-	if (!head_pipe)
+	if (!head_pipe) {
 		ASSERT(0);
+		return NULL;
+	}
 
 	if (!head_pipe->plane_state)
 		return head_pipe;
@@ -1447,11 +1461,16 @@ static struct stream_encoder *find_first_free_match_stream_enc_for_link(
 
 static struct audio *find_first_free_audio(
 		struct resource_context *res_ctx,
-		const struct resource_pool *pool)
+		const struct resource_pool *pool,
+		enum engine_id id)
 {
 	int i;
 	for (i = 0; i < pool->audio_count; i++) {
 		if ((res_ctx->is_audio_acquired[i] == false) && (res_ctx->is_stream_enc_acquired[i] == true)) {
+			/*we have enough audio endpoint, find the matching inst*/
+			if (id != i)
+				continue;
+
 			return pool->audios[i];
 		}
 	}
@@ -1700,7 +1719,7 @@ enum dc_status resource_map_pool_resources(
 	    dc_is_audio_capable_signal(pipe_ctx->stream->signal) &&
 	    stream->audio_info.mode_count) {
 		pipe_ctx->stream_res.audio = find_first_free_audio(
-		&context->res_ctx, pool);
+		&context->res_ctx, pool, pipe_ctx->stream_res.stream_enc->id);
 
 		/*
 		 * Audio assigned in order first come first get.
@@ -1765,13 +1784,16 @@ enum dc_status dc_validate_global_state(
 	enum dc_status result = DC_ERROR_UNEXPECTED;
 	int i, j;
 
+	if (!new_ctx)
+		return DC_ERROR_UNEXPECTED;
+
 	if (dc->res_pool->funcs->validate_global) {
 			result = dc->res_pool->funcs->validate_global(dc, new_ctx);
 			if (result != DC_OK)
 				return result;
 	}
 
-	for (i = 0; new_ctx && i < new_ctx->stream_count; i++) {
+	for (i = 0; i < new_ctx->stream_count; i++) {
 		struct dc_stream_state *stream = new_ctx->streams[i];
 
 		for (j = 0; j < dc->res_pool->pipe_count; j++) {
@@ -2307,20 +2329,13 @@ static void set_spd_info_packet(
 
 static void set_hdr_static_info_packet(
 		struct encoder_info_packet *info_packet,
-		struct dc_plane_state *plane_state,
 		struct dc_stream_state *stream)
 {
 	uint16_t i = 0;
 	enum signal_type signal = stream->signal;
-	struct dc_hdr_static_metadata hdr_metadata;
 	uint32_t data;
 
-	if (!plane_state)
-		return;
-
-	hdr_metadata = plane_state->hdr_static_ctx;
-
-	if (!hdr_metadata.hdr_supported)
+	if (!stream->hdr_static_metadata.hdr_supported)
 		return;
 
 	if (dc_is_hdmi_signal(signal)) {
@@ -2340,55 +2355,55 @@ static void set_hdr_static_info_packet(
 		i = 2;
 	}
 
-	data = hdr_metadata.is_hdr;
+	data = stream->hdr_static_metadata.is_hdr;
 	info_packet->sb[i++] = data ? 0x02 : 0x00;
 	info_packet->sb[i++] = 0x00;
 
-	data = hdr_metadata.chromaticity_green_x / 2;
+	data = stream->hdr_static_metadata.chromaticity_green_x / 2;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
-	data = hdr_metadata.chromaticity_green_y / 2;
+	data = stream->hdr_static_metadata.chromaticity_green_y / 2;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
-	data = hdr_metadata.chromaticity_blue_x / 2;
+	data = stream->hdr_static_metadata.chromaticity_blue_x / 2;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
-	data = hdr_metadata.chromaticity_blue_y / 2;
+	data = stream->hdr_static_metadata.chromaticity_blue_y / 2;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
-	data = hdr_metadata.chromaticity_red_x / 2;
+	data = stream->hdr_static_metadata.chromaticity_red_x / 2;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
-	data = hdr_metadata.chromaticity_red_y / 2;
+	data = stream->hdr_static_metadata.chromaticity_red_y / 2;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
-	data = hdr_metadata.chromaticity_white_point_x / 2;
+	data = stream->hdr_static_metadata.chromaticity_white_point_x / 2;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
-	data = hdr_metadata.chromaticity_white_point_y / 2;
+	data = stream->hdr_static_metadata.chromaticity_white_point_y / 2;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
-	data = hdr_metadata.max_luminance;
+	data = stream->hdr_static_metadata.max_luminance;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
-	data = hdr_metadata.min_luminance;
+	data = stream->hdr_static_metadata.min_luminance;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
-	data = hdr_metadata.maximum_content_light_level;
+	data = stream->hdr_static_metadata.maximum_content_light_level;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
-	data = hdr_metadata.maximum_frame_average_light_level;
+	data = stream->hdr_static_metadata.maximum_frame_average_light_level;
 	info_packet->sb[i++] = data & 0xFF;
 	info_packet->sb[i++] = (data & 0xFF00) >> 8;
 
@@ -2539,16 +2554,14 @@ void resource_build_info_frame(struct pipe_ctx *pipe_ctx)
 
 		set_spd_info_packet(&info->spd, pipe_ctx->stream);
 
-		set_hdr_static_info_packet(&info->hdrsmd,
-				pipe_ctx->plane_state, pipe_ctx->stream);
+		set_hdr_static_info_packet(&info->hdrsmd, pipe_ctx->stream);
 
 	} else if (dc_is_dp_signal(signal)) {
 		set_vsc_info_packet(&info->vsc, pipe_ctx->stream);
 
 		set_spd_info_packet(&info->spd, pipe_ctx->stream);
 
-		set_hdr_static_info_packet(&info->hdrsmd,
-				pipe_ctx->plane_state, pipe_ctx->stream);
+		set_hdr_static_info_packet(&info->hdrsmd, pipe_ctx->stream);
 	}
 
 	patch_gamut_packet_checksum(&info->gamut);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index b00a6040a697..261811e0c094 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -36,16 +36,13 @@
 #define TMDS_MAX_PIXEL_CLOCK_IN_KHZ_UPMOST 297000
 static void update_stream_signal(struct dc_stream_state *stream)
 {
-	if (stream->output_signal == SIGNAL_TYPE_NONE) {
-		struct dc_sink *dc_sink = stream->sink;
 
-		if (dc_sink->sink_signal == SIGNAL_TYPE_NONE)
-			stream->signal = stream->sink->link->connector_signal;
-		else
-			stream->signal = dc_sink->sink_signal;
-	} else {
-		stream->signal = stream->output_signal;
-	}
+	struct dc_sink *dc_sink = stream->sink;
+
+	if (dc_sink->sink_signal == SIGNAL_TYPE_NONE)
+		stream->signal = stream->sink->link->connector_signal;
+	else
+		stream->signal = dc_sink->sink_signal;
 
 	if (dc_is_dvi_signal(stream->signal)) {
 		if (stream->timing.pix_clk_khz > TMDS_MAX_PIXEL_CLOCK_IN_KHZ_UPMOST &&
@@ -229,7 +226,7 @@ bool dc_stream_set_cursor_attributes(
 		if (pipe_ctx->plane_res.dpp != NULL &&
 				pipe_ctx->plane_res.dpp->funcs->set_cursor_attributes != NULL)
 			pipe_ctx->plane_res.dpp->funcs->set_cursor_attributes(
-				pipe_ctx->plane_res.dpp, attributes);
+				pipe_ctx->plane_res.dpp, attributes->color_format);
 	}
 
 	stream->cursor_attributes = *attributes;
@@ -263,7 +260,6 @@ bool dc_stream_set_cursor_position(
 		struct input_pixel_processor *ipp = pipe_ctx->plane_res.ipp;
 		struct mem_input *mi = pipe_ctx->plane_res.mi;
 		struct hubp *hubp = pipe_ctx->plane_res.hubp;
-		struct transform *xfm = pipe_ctx->plane_res.xfm;
 		struct dpp *dpp = pipe_ctx->plane_res.dpp;
 		struct dc_cursor_position pos_cpy = *position;
 		struct dc_cursor_mi_param param = {
@@ -294,17 +290,19 @@ bool dc_stream_set_cursor_position(
 		if (mi != NULL && mi->funcs->set_cursor_position != NULL)
 			mi->funcs->set_cursor_position(mi, &pos_cpy, &param);
 
-		if (hubp != NULL && hubp->funcs->set_cursor_position != NULL)
-			hubp->funcs->set_cursor_position(hubp, &pos_cpy, &param);
+		if (!hubp)
+			continue;
 
-		if (xfm != NULL && xfm->funcs->set_cursor_position != NULL)
-			xfm->funcs->set_cursor_position(xfm, &pos_cpy, &param, hubp->curs_attr.width);
+		if (hubp->funcs->set_cursor_position != NULL)
+			hubp->funcs->set_cursor_position(hubp, &pos_cpy, &param);
 
 		if (dpp != NULL && dpp->funcs->set_cursor_position != NULL)
 			dpp->funcs->set_cursor_position(dpp, &pos_cpy, &param, hubp->curs_attr.width);
 
 	}
 
+	stream->cursor_position = *position;
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 9d8f4a55c74e..e2e3c9df79ea 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.07"
+#define DC_VER "3.1.27"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
@@ -58,8 +58,10 @@ struct dc_caps {
 	uint32_t i2c_speed_in_khz;
 	unsigned int max_cursor_size;
 	unsigned int max_video_width;
+	int linear_pitch_alignment;
 	bool dcc_const_color;
 	bool dynamic_audio;
+	bool is_apu;
 };
 
 struct dc_dcc_surface_param {
@@ -97,69 +99,53 @@ struct dc_static_screen_events {
 	bool overlay_update;
 };
 
+
+/* Surface update type is used by dc_update_surfaces_and_stream
+ * The update type is determined at the very beginning of the function based
+ * on parameters passed in and decides how much programming (or updating) is
+ * going to be done during the call.
+ *
+ * UPDATE_TYPE_FAST is used for really fast updates that do not require much
+ * logical calculations or hardware register programming. This update MUST be
+ * ISR safe on windows. Currently fast update will only be used to flip surface
+ * address.
+ *
+ * UPDATE_TYPE_MED is used for slower updates which require significant hw
+ * re-programming however do not affect bandwidth consumption or clock
+ * requirements. At present, this is the level at which front end updates
+ * that do not require us to run bw_calcs happen. These are in/out transfer func
+ * updates, viewport offset changes, recout size changes and pixel depth changes.
+ * This update can be done at ISR, but we want to minimize how often this happens.
+ *
+ * UPDATE_TYPE_FULL is slow. Really slow. This requires us to recalculate our
+ * bandwidth and clocks, possibly rearrange some pipes and reprogram anything front
+ * end related. Any time viewport dimensions, recout dimensions, scaling ratios or
+ * gamma need to be adjusted or pipe needs to be turned on (or disconnected) we do
+ * a full update. This cannot be done at ISR level and should be a rare event.
+ * Unless someone is stress testing mpo enter/exit, playing with colour or adjusting
+ * underscan we don't expect to see this call at all.
+ */
+
+enum surface_update_type {
+	UPDATE_TYPE_FAST, /* super fast, safe to execute in isr */
+	UPDATE_TYPE_MED,  /* ISR safe, most of programming needed, no bw/clk change*/
+	UPDATE_TYPE_FULL, /* may need to shuffle resources */
+};
+
 /* Forward declaration*/
 struct dc;
 struct dc_plane_state;
 struct dc_state;
 
+
 struct dc_cap_funcs {
 	bool (*get_dcc_compression_cap)(const struct dc *dc,
 			const struct dc_dcc_surface_param *input,
 			struct dc_surface_dcc_cap *output);
 };
 
-struct dc_stream_state_funcs {
-	bool (*adjust_vmin_vmax)(struct dc *dc,
-			struct dc_stream_state **stream,
-			int num_streams,
-			int vmin,
-			int vmax);
-	bool (*get_crtc_position)(struct dc *dc,
-			struct dc_stream_state **stream,
-			int num_streams,
-			unsigned int *v_pos,
-			unsigned int *nom_v_pos);
-
-	bool (*set_gamut_remap)(struct dc *dc,
-			const struct dc_stream_state *stream);
-
-	bool (*program_csc_matrix)(struct dc *dc,
-			struct dc_stream_state *stream);
-
-	void (*set_static_screen_events)(struct dc *dc,
-			struct dc_stream_state **stream,
-			int num_streams,
-			const struct dc_static_screen_events *events);
-
-	void (*set_dither_option)(struct dc_stream_state *stream,
-			enum dc_dither_option option);
-
-	void (*set_dpms)(struct dc *dc,
-			struct dc_stream_state *stream,
-			bool dpms_off);
-};
-
 struct link_training_settings;
 
-struct dc_link_funcs {
-	void (*set_drive_settings)(struct dc *dc,
-			struct link_training_settings *lt_settings,
-			const struct dc_link *link);
-	void (*perform_link_training)(struct dc *dc,
-			struct dc_link_settings *link_setting,
-			bool skip_video_pattern);
-	void (*set_preferred_link_settings)(struct dc *dc,
-			struct dc_link_settings *link_setting,
-			struct dc_link *link);
-	void (*enable_hpd)(const struct dc_link *link);
-	void (*disable_hpd)(const struct dc_link *link);
-	void (*set_test_pattern)(
-			struct dc_link *link,
-			enum dp_test_pattern test_pattern,
-			const struct link_training_settings *p_link_settings,
-			const unsigned char *p_custom_pattern,
-			unsigned int cust_pattern_size);
-};
 
 /* Structure to hold configuration flags set by dm at dc creation. */
 struct dc_config {
@@ -232,8 +218,6 @@ struct dce_hwseq;
 struct dc {
 	struct dc_caps caps;
 	struct dc_cap_funcs cap_funcs;
-	struct dc_stream_state_funcs stream_funcs;
-	struct dc_link_funcs link_funcs;
 	struct dc_config config;
 	struct dc_debug debug;
 
@@ -266,6 +250,8 @@ struct dc {
 	 */
 	struct dm_pp_display_configuration prev_display_config;
 
+	bool optimized_required;
+
 	/* FBC compressor */
 #if defined(CONFIG_DRM_AMD_DC_FBC)
 	struct compressor *fbc_compressor;
@@ -333,24 +319,6 @@ enum color_transfer_func {
 	transfer_func_gamma_26
 };
 
-enum color_color_space {
-	color_space_unsupported,
-	color_space_srgb,
-	color_space_bt601,
-	color_space_bt709,
-	color_space_xv_ycc_bt601,
-	color_space_xv_ycc_bt709,
-	color_space_xr_rgb,
-	color_space_bt2020,
-	color_space_adobe,
-	color_space_dci_p3,
-	color_space_sc_rgb_ms_ref,
-	color_space_display_native,
-	color_space_app_ctrl,
-	color_space_dolby_vision,
-	color_space_custom_coordinates
-};
-
 struct dc_hdr_static_metadata {
 	/* display chromaticities and white point in units of 0.00001 */
 	unsigned int chromaticity_green_x;
@@ -374,7 +342,7 @@ struct dc_hdr_static_metadata {
 enum dc_transfer_func_type {
 	TF_TYPE_PREDEFINED,
 	TF_TYPE_DISTRIBUTED_POINTS,
-	TF_TYPE_BYPASS
+	TF_TYPE_BYPASS,
 };
 
 struct dc_transfer_func_distributed_points {
@@ -393,6 +361,7 @@ enum dc_transfer_func_predefined {
 	TRANSFER_FUNCTION_BT709,
 	TRANSFER_FUNCTION_PQ,
 	TRANSFER_FUNCTION_LINEAR,
+	TRANSFER_FUNCTION_UNITY,
 };
 
 struct dc_transfer_func {
@@ -415,6 +384,34 @@ struct dc_plane_status {
 	bool is_right_eye;
 };
 
+union surface_update_flags {
+
+	struct {
+		/* Medium updates */
+		uint32_t dcc_change:1;
+		uint32_t color_space_change:1;
+		uint32_t input_tf_change:1;
+		uint32_t horizontal_mirror_change:1;
+		uint32_t per_pixel_alpha_change:1;
+		uint32_t rotation_change:1;
+		uint32_t swizzle_change:1;
+		uint32_t scaling_change:1;
+		uint32_t position_change:1;
+		uint32_t in_transfer_func:1;
+		uint32_t input_csc_change:1;
+
+		/* Full updates */
+		uint32_t new_plane:1;
+		uint32_t bpp_change:1;
+		uint32_t bandwidth_change:1;
+		uint32_t clock_change:1;
+		uint32_t stereo_format_change:1;
+		uint32_t full_update:1;
+	} bits;
+
+	uint32_t raw;
+};
+
 struct dc_plane_state {
 	struct dc_plane_address address;
 	struct scaling_taps scaling_quality;
@@ -426,27 +423,30 @@ struct dc_plane_state {
 	union dc_tiling_info tiling_info;
 
 	struct dc_plane_dcc_param dcc;
-	struct dc_hdr_static_metadata hdr_static_ctx;
 
 	struct dc_gamma *gamma_correction;
 	struct dc_transfer_func *in_transfer_func;
+	struct dc_bias_and_scale *bias_and_scale;
+	struct csc_transform input_csc_color_matrix;
+	struct fixed31_32 coeff_reduction_factor;
 
-	// sourceContentAttribute cache
-	bool is_source_input_valid;
-	struct dc_hdr_static_metadata source_input_mastering_info;
-	enum color_color_space source_input_color_space;
-	enum color_transfer_func source_input_tf;
+	// TODO: No longer used, remove
+	struct dc_hdr_static_metadata hdr_static_ctx;
 
 	enum dc_color_space color_space;
+	enum color_transfer_func input_tf;
+
 	enum surface_pixel_format format;
 	enum dc_rotation_angle rotation;
 	enum plane_stereo_format stereo_format;
 
+	bool is_tiling_rotated;
 	bool per_pixel_alpha;
 	bool visible;
 	bool flip_immediate;
 	bool horizontal_mirror;
 
+	union surface_update_flags update_flags;
 	/* private to DC core */
 	struct dc_plane_status status;
 	struct dc_context *ctx;
@@ -463,10 +463,12 @@ struct dc_plane_info {
 	enum surface_pixel_format format;
 	enum dc_rotation_angle rotation;
 	enum plane_stereo_format stereo_format;
-	enum dc_color_space color_space; /*todo: wrong place, fits in scaling info*/
+	enum dc_color_space color_space;
+	enum color_transfer_func input_tf;
 	bool horizontal_mirror;
 	bool visible;
 	bool per_pixel_alpha;
+	bool input_csc_enabled;
 };
 
 struct dc_scaling_info {
@@ -483,13 +485,18 @@ struct dc_surface_update {
 	struct dc_flip_addrs *flip_addr;
 	struct dc_plane_info *plane_info;
 	struct dc_scaling_info *scaling_info;
+
 	/* following updates require alloc/sleep/spin that is not isr safe,
 	 * null means no updates
 	 */
 	/* gamma TO BE REMOVED */
 	struct dc_gamma *gamma;
+	enum color_transfer_func color_input_tf;
+	enum color_transfer_func color_output_tf;
 	struct dc_transfer_func *in_transfer_func;
-	struct dc_hdr_static_metadata *hdr_static_metadata;
+
+	struct csc_transform *input_csc_color_matrix;
+	struct fixed31_32 *coeff_reduction_factor;
 };
 
 /*
@@ -524,197 +531,7 @@ struct dc_flip_addrs {
 bool dc_post_update_surfaces_to_stream(
 		struct dc *dc);
 
-/* Surface update type is used by dc_update_surfaces_and_stream
- * The update type is determined at the very beginning of the function based
- * on parameters passed in and decides how much programming (or updating) is
- * going to be done during the call.
- *
- * UPDATE_TYPE_FAST is used for really fast updates that do not require much
- * logical calculations or hardware register programming. This update MUST be
- * ISR safe on windows. Currently fast update will only be used to flip surface
- * address.
- *
- * UPDATE_TYPE_MED is used for slower updates which require significant hw
- * re-programming however do not affect bandwidth consumption or clock
- * requirements. At present, this is the level at which front end updates
- * that do not require us to run bw_calcs happen. These are in/out transfer func
- * updates, viewport offset changes, recout size changes and pixel depth changes.
- * This update can be done at ISR, but we want to minimize how often this happens.
- *
- * UPDATE_TYPE_FULL is slow. Really slow. This requires us to recalculate our
- * bandwidth and clocks, possibly rearrange some pipes and reprogram anything front
- * end related. Any time viewport dimensions, recout dimensions, scaling ratios or
- * gamma need to be adjusted or pipe needs to be turned on (or disconnected) we do
- * a full update. This cannot be done at ISR level and should be a rare event.
- * Unless someone is stress testing mpo enter/exit, playing with colour or adjusting
- * underscan we don't expect to see this call at all.
- */
-
-enum surface_update_type {
-	UPDATE_TYPE_FAST, /* super fast, safe to execute in isr */
-	UPDATE_TYPE_MED,  /* ISR safe, most of programming needed, no bw/clk change*/
-	UPDATE_TYPE_FULL, /* may need to shuffle resources */
-};
-
-/*******************************************************************************
- * Stream Interfaces
- ******************************************************************************/
-
-struct dc_stream_status {
-	int primary_otg_inst;
-	int stream_enc_inst;
-	int plane_count;
-	struct dc_plane_state *plane_states[MAX_SURFACE_NUM];
-
-	/*
-	 * link this stream passes through
-	 */
-	struct dc_link *link;
-};
-
-struct dc_stream_state {
-	struct dc_sink *sink;
-	struct dc_crtc_timing timing;
-
-	struct rect src; /* composition area */
-	struct rect dst; /* stream addressable area */
-
-	struct audio_info audio_info;
-
-	struct freesync_context freesync_ctx;
-
-	struct dc_transfer_func *out_transfer_func;
-	struct colorspace_transform gamut_remap_matrix;
-	struct csc_transform csc_color_matrix;
-
-	enum signal_type output_signal;
-
-	enum dc_color_space output_color_space;
-	enum dc_dither_option dither_option;
-
-	enum view_3d_format view_format;
-
-	bool ignore_msa_timing_param;
-	/* TODO: custom INFO packets */
-	/* TODO: ABM info (DMCU) */
-	/* TODO: PSR info */
-	/* TODO: CEA VIC */
-
-	/* from core_stream struct */
-	struct dc_context *ctx;
-
-	/* used by DCP and FMT */
-	struct bit_depth_reduction_params bit_depth_params;
-	struct clamping_and_pixel_encoding_params clamping;
-
-	int phy_pix_clk;
-	enum signal_type signal;
-	bool dpms_off;
-
-	struct dc_stream_status status;
-
-	struct dc_cursor_attributes cursor_attributes;
-
-	/* from stream struct */
-	struct kref refcount;
-};
-
-struct dc_stream_update {
-	struct rect src;
-	struct rect dst;
-	struct dc_transfer_func *out_transfer_func;
-};
-
-bool dc_is_stream_unchanged(
-	struct dc_stream_state *old_stream, struct dc_stream_state *stream);
-bool dc_is_stream_scaling_unchanged(
-	struct dc_stream_state *old_stream, struct dc_stream_state *stream);
-
-/*
- * Set up surface attributes and associate to a stream
- * The surfaces parameter is an absolute set of all surface active for the stream.
- * If no surfaces are provided, the stream will be blanked; no memory read.
- * Any flip related attribute changes must be done through this interface.
- *
- * After this call:
- *   Surfaces attributes are programmed and configured to be composed into stream.
- *   This does not trigger a flip.  No surface address is programmed.
- */
-
-bool dc_commit_planes_to_stream(
-		struct dc *dc,
-		struct dc_plane_state **plane_states,
-		uint8_t new_plane_count,
-		struct dc_stream_state *dc_stream,
-		struct dc_state *state);
-
-void dc_commit_updates_for_stream(struct dc *dc,
-		struct dc_surface_update *srf_updates,
-		int surface_count,
-		struct dc_stream_state *stream,
-		struct dc_stream_update *stream_update,
-		struct dc_plane_state **plane_states,
-		struct dc_state *state);
-/*
- * Log the current stream state.
- */
-void dc_stream_log(
-	const struct dc_stream_state *stream,
-	struct dal_logger *dc_logger,
-	enum dc_log_type log_type);
-
-uint8_t dc_get_current_stream_count(struct dc *dc);
-struct dc_stream_state *dc_get_stream_at_index(struct dc *dc, uint8_t i);
-
-/*
- * Return the current frame counter.
- */
-uint32_t dc_stream_get_vblank_counter(const struct dc_stream_state *stream);
-
-/* TODO: Return parsed values rather than direct register read
- * This has a dependency on the caller (amdgpu_get_crtc_scanoutpos)
- * being refactored properly to be dce-specific
- */
-bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream,
-				  uint32_t *v_blank_start,
-				  uint32_t *v_blank_end,
-				  uint32_t *h_position,
-				  uint32_t *v_position);
-
-enum dc_status dc_add_stream_to_ctx(
-			struct dc *dc,
-		struct dc_state *new_ctx,
-		struct dc_stream_state *stream);
-
-enum dc_status dc_remove_stream_from_ctx(
-		struct dc *dc,
-			struct dc_state *new_ctx,
-			struct dc_stream_state *stream);
-
-
-bool dc_add_plane_to_context(
-		const struct dc *dc,
-		struct dc_stream_state *stream,
-		struct dc_plane_state *plane_state,
-		struct dc_state *context);
-
-bool dc_remove_plane_from_context(
-		const struct dc *dc,
-		struct dc_stream_state *stream,
-		struct dc_plane_state *plane_state,
-		struct dc_state *context);
-
-bool dc_rem_all_planes_for_stream(
-		const struct dc *dc,
-		struct dc_stream_state *stream,
-		struct dc_state *context);
-
-bool dc_add_all_planes_for_stream(
-		const struct dc *dc,
-		struct dc_stream_state *stream,
-		struct dc_plane_state * const *plane_states,
-		int plane_count,
-		struct dc_state *context);
+#include "dc_stream.h"
 
 /*
  * Structure to store surface/stream associations for validation
@@ -725,22 +542,12 @@ struct dc_validation_set {
 	uint8_t plane_count;
 };
 
-enum dc_status dc_validate_stream(struct dc *dc, struct dc_stream_state *stream);
-
 enum dc_status dc_validate_plane(struct dc *dc, const struct dc_plane_state *plane_state);
 
 enum dc_status dc_validate_global_state(
 		struct dc *dc,
 		struct dc_state *new_ctx);
 
-/*
- * This function takes a stream and checks if it is guaranteed to be supported.
- * Guaranteed means that MAX_COFUNC similar streams are supported.
- *
- * After this call:
- *   No hardware is programmed for call.  Only validation is done.
- */
-
 
 void dc_resource_state_construct(
 		const struct dc *dc,
@@ -767,42 +574,6 @@ void dc_resource_state_destruct(struct dc_state *context);
  */
 bool dc_commit_state(struct dc *dc, struct dc_state *context);
 
-/*
- * Set up streams and links associated to drive sinks
- * The streams parameter is an absolute set of all active streams.
- *
- * After this call:
- *   Phy, Encoder, Timing Generator are programmed and enabled.
- *   New streams are enabled with blank stream; no memory read.
- */
-/*
- * Enable stereo when commit_streams is not required,
- * for example, frame alternate.
- */
-bool dc_enable_stereo(
-	struct dc *dc,
-	struct dc_state *context,
-	struct dc_stream_state *streams[],
-	uint8_t stream_count);
-
-/**
- * Create a new default stream for the requested sink
- */
-struct dc_stream_state *dc_create_stream_for_sink(struct dc_sink *dc_sink);
-
-void dc_stream_retain(struct dc_stream_state *dc_stream);
-void dc_stream_release(struct dc_stream_state *dc_stream);
-
-struct dc_stream_status *dc_stream_get_status(
-	struct dc_stream_state *dc_stream);
-
-enum surface_update_type dc_check_update_surfaces_for_stream(
-		struct dc *dc,
-		struct dc_surface_update *updates,
-		int surface_count,
-		struct dc_stream_update *stream_update,
-		const struct dc_stream_status *stream_status);
-
 
 struct dc_state *dc_create_state(void);
 void dc_retain_state(struct dc_state *context);
@@ -835,171 +606,7 @@ struct dpcd_caps {
 	bool dpcd_display_control_capable;
 };
 
-struct dc_link_status {
-	struct dpcd_caps *dpcd_caps;
-};
-
-/* DP MST stream allocation (payload bandwidth number) */
-struct link_mst_stream_allocation {
-	/* DIG front */
-	const struct stream_encoder *stream_enc;
-	/* associate DRM payload table with DC stream encoder */
-	uint8_t vcp_id;
-	/* number of slots required for the DP stream in transport packet */
-	uint8_t slot_count;
-};
-
-/* DP MST stream allocation table */
-struct link_mst_stream_allocation_table {
-	/* number of DP video streams */
-	int stream_count;
-	/* array of stream allocations */
-	struct link_mst_stream_allocation stream_allocations[MAX_CONTROLLER_NUM];
-};
-
-/*
- * A link contains one or more sinks and their connected status.
- * The currently active signal type (HDMI, DP-SST, DP-MST) is also reported.
- */
-struct dc_link {
-	struct dc_sink *remote_sinks[MAX_SINKS_PER_LINK];
-	unsigned int sink_count;
-	struct dc_sink *local_sink;
-	unsigned int link_index;
-	enum dc_connection_type type;
-	enum signal_type connector_signal;
-	enum dc_irq_source irq_source_hpd;
-	enum dc_irq_source irq_source_hpd_rx;/* aka DP Short Pulse  */
-	/* caps is the same as reported_link_cap. link_traing use
-	 * reported_link_cap. Will clean up.  TODO
-	 */
-	struct dc_link_settings reported_link_cap;
-	struct dc_link_settings verified_link_cap;
-	struct dc_link_settings cur_link_settings;
-	struct dc_lane_settings cur_lane_setting;
-	struct dc_link_settings preferred_link_setting;
-
-	uint8_t ddc_hw_inst;
-
-	uint8_t hpd_src;
-
-	uint8_t link_enc_hw_inst;
-
-	bool test_pattern_enabled;
-	union compliance_test_state compliance_test_state;
-
-	void *priv;
-
-	struct ddc_service *ddc;
-
-	bool aux_mode;
-
-	/* Private to DC core */
-
-	const struct dc *dc;
-
-	struct dc_context *ctx;
-
-	struct link_encoder *link_enc;
-	struct graphics_object_id link_id;
-	union ddi_channel_mapping ddi_channel_mapping;
-	struct connector_device_tag_info device_tag;
-	struct dpcd_caps dpcd_caps;
-	unsigned short chip_caps;
-	unsigned int dpcd_sink_count;
-	enum edp_revision edp_revision;
-	bool psr_enabled;
-
-	/* MST record stream using this link */
-	struct link_flags {
-		bool dp_keep_receiver_powered;
-	} wa_flags;
-	struct link_mst_stream_allocation_table mst_stream_alloc_table;
-
-	struct dc_link_status link_status;
-
-};
-
-const struct dc_link_status *dc_link_get_status(const struct dc_link *dc_link);
-
-/*
- * Return an enumerated dc_link.  dc_link order is constant and determined at
- * boot time.  They cannot be created or destroyed.
- * Use dc_get_caps() to get number of links.
- */
-static inline struct dc_link *dc_get_link_at_index(struct dc *dc, uint32_t link_index)
-{
-	return dc->links[link_index];
-}
-
-/* Set backlight level of an embedded panel (eDP, LVDS). */
-bool dc_link_set_backlight_level(const struct dc_link *dc_link, uint32_t level,
-		uint32_t frame_ramp, const struct dc_stream_state *stream);
-
-bool dc_link_set_psr_enable(const struct dc_link *dc_link, bool enable, bool wait);
-
-bool dc_link_get_psr_state(const struct dc_link *dc_link, uint32_t *psr_state);
-
-bool dc_link_setup_psr(struct dc_link *dc_link,
-		const struct dc_stream_state *stream, struct psr_config *psr_config,
-		struct psr_context *psr_context);
-
-/* Request DC to detect if there is a Panel connected.
- * boot - If this call is during initial boot.
- * Return false for any type of detection failure or MST detection
- * true otherwise. True meaning further action is required (status update
- * and OS notification).
- */
-enum dc_detect_reason {
-	DETECT_REASON_BOOT,
-	DETECT_REASON_HPD,
-	DETECT_REASON_HPDRX,
-};
-
-bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason);
-
-/* Notify DC about DP RX Interrupt (aka Short Pulse Interrupt).
- * Return:
- * true - Downstream port status changed. DM should call DC to do the
- * detection.
- * false - no change in Downstream port status. No further action required
- * from DM. */
-bool dc_link_handle_hpd_rx_irq(struct dc_link *dc_link,
-		union hpd_irq_data *hpd_irq_dpcd_data);
-
-struct dc_sink_init_data;
-
-struct dc_sink *dc_link_add_remote_sink(
-		struct dc_link *dc_link,
-		const uint8_t *edid,
-		int len,
-		struct dc_sink_init_data *init_data);
-
-void dc_link_remove_remote_sink(
-	struct dc_link *link,
-	struct dc_sink *sink);
-
-/* Used by diagnostics for virtual link at the moment */
-
-void dc_link_dp_set_drive_settings(
-	struct dc_link *link,
-	struct link_training_settings *lt_settings);
-
-enum link_training_result dc_link_dp_perform_link_training(
-	struct dc_link *link,
-	const struct dc_link_settings *link_setting,
-	bool skip_video_pattern);
-
-void dc_link_dp_enable_hpd(const struct dc_link *link);
-
-void dc_link_dp_disable_hpd(const struct dc_link *link);
-
-bool dc_link_dp_set_test_pattern(
-	struct dc_link *link,
-	enum dp_test_pattern test_pattern,
-	const struct link_training_settings *p_link_settings,
-	const unsigned char *p_custom_pattern,
-	unsigned int cust_pattern_size);
+#include "dc_link.h"
 
 /*******************************************************************************
  * Sink Interfaces - A sink corresponds to a display output device
@@ -1037,6 +644,7 @@ struct dc_sink {
 
 	/* private to dc_sink.c */
 	struct kref refcount;
+
 };
 
 void dc_sink_retain(struct dc_sink *sink);
@@ -1051,18 +659,6 @@ struct dc_sink_init_data {
 
 struct dc_sink *dc_sink_create(const struct dc_sink_init_data *init_params);
 
-/*******************************************************************************
- * Cursor interfaces - To manages the cursor within a stream
- ******************************************************************************/
-/* TODO: Deprecated once we switch to dc_set_cursor_position */
-bool dc_stream_set_cursor_attributes(
-	struct dc_stream_state *stream,
-	const struct dc_cursor_attributes *attributes);
-
-bool dc_stream_set_cursor_position(
-	struct dc_stream_state *stream,
-	const struct dc_cursor_position *position);
-
 /* Newer interfaces  */
 struct dc_cursor {
 	struct dc_plane_address address;
@@ -1090,14 +686,4 @@ void dc_set_power_state(
 		enum dc_acpi_cm_power_state power_state);
 void dc_resume(struct dc *dc);
 
-/*
- * DPCD access interfaces
- */
-
-bool dc_submit_i2c(
-		struct dc *dc,
-		uint32_t link_index,
-		struct i2c_command *cmd);
-
-
 #endif /* DC_INTERFACE_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index 77e2de69cca3..2726b02e006b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -255,7 +255,7 @@ enum dpcd_downstream_port_detailed_type {
 	DOWN_STREAM_DETAILED_DP_PLUS_PLUS
 };
 
-union dwnstream_port_caps_byte1 {
+union dwnstream_port_caps_byte2 {
 	struct {
 		uint8_t MAX_BITS_PER_COLOR_COMPONENT:2;
 		uint8_t RESERVED:6;
@@ -298,6 +298,32 @@ union dwnstream_port_caps_byte3_hdmi {
 
 /*4-byte structure for detailed capabilities of a down-stream port
 (DP-to-TMDS converter).*/
+union dwnstream_portxcaps {
+	struct {
+		union dwnstream_port_caps_byte0 byte0;
+		unsigned char max_TMDS_clock;   //byte1
+		union dwnstream_port_caps_byte2 byte2;
+
+		union {
+			union dwnstream_port_caps_byte3_dvi byteDVI;
+			union dwnstream_port_caps_byte3_hdmi byteHDMI;
+		} byte3;
+	} bytes;
+
+	unsigned char raw[4];
+};
+
+union downstream_port {
+	struct {
+		unsigned char   present:1;
+		unsigned char   type:2;
+		unsigned char   format_conv:1;
+		unsigned char   detailed_caps:1;
+		unsigned char   reserved:3;
+	} bits;
+	unsigned char raw;
+};
+
 
 union sink_status {
 	struct {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
index 0d84b2a1ccfd..48e1fcf53d43 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -1,4 +1,26 @@
 /*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+/*
  * dc_helper.c
  *
  *  Created on: Aug 30, 2016
@@ -156,8 +178,13 @@ uint32_t generic_reg_wait(const struct dc_context *ctx,
 
 		field_value = get_reg_field_value_ex(reg_val, mask, shift);
 
-		if (field_value == condition_value)
+		if (field_value == condition_value) {
+			if (i * delay_between_poll_us > 1000)
+				dm_output_to_console("REG_WAIT taking a while: %dms in %s line:%d\n",
+						delay_between_poll_us * i / 1000,
+						func_name, line);
 			return reg_val;
+		}
 	}
 
 	dm_error("REG_WAIT timeout %dus * %d tries - %s line:%d\n",
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index 1a9f57fb0838..03029f72dc3f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -492,15 +492,24 @@ struct dc_cursor_attributes {
 enum dc_color_space {
 	COLOR_SPACE_UNKNOWN,
 	COLOR_SPACE_SRGB,
+	COLOR_SPACE_XR_RGB,
 	COLOR_SPACE_SRGB_LIMITED,
+	COLOR_SPACE_MSREF_SCRGB,
 	COLOR_SPACE_YCBCR601,
 	COLOR_SPACE_YCBCR709,
+	COLOR_SPACE_XV_YCC_709,
+	COLOR_SPACE_XV_YCC_601,
 	COLOR_SPACE_YCBCR601_LIMITED,
 	COLOR_SPACE_YCBCR709_LIMITED,
 	COLOR_SPACE_2020_RGB_FULLRANGE,
 	COLOR_SPACE_2020_RGB_LIMITEDRANGE,
 	COLOR_SPACE_2020_YCBCR,
 	COLOR_SPACE_ADOBERGB,
+	COLOR_SPACE_DCIP3,
+	COLOR_SPACE_DISPLAYNATIVE,
+	COLOR_SPACE_DOLBYVISION,
+	COLOR_SPACE_APPCTRL,
+	COLOR_SPACE_CUSTOMPOINTS,
 };
 
 enum dc_dither_option {
@@ -570,8 +579,6 @@ enum dc_timing_standard {
 	TIMING_STANDARD_MAX
 };
 
-
-
 enum dc_color_depth {
 	COLOR_DEPTH_UNDEFINED,
 	COLOR_DEPTH_666,
@@ -664,6 +671,22 @@ enum dc_timing_3d_format {
 	TIMING_3D_FORMAT_MAX,
 };
 
+enum trigger_delay {
+	TRIGGER_DELAY_NEXT_PIXEL = 0,
+	TRIGGER_DELAY_NEXT_LINE,
+};
+
+enum crtc_event {
+	CRTC_EVENT_VSYNC_RISING = 0,
+	CRTC_EVENT_VSYNC_FALLING
+};
+
+struct crtc_trigger_info {
+	bool enabled;
+	struct dc_stream_state *event_source;
+	enum crtc_event event;
+	enum trigger_delay delay;
+};
 
 struct dc_crtc_timing {
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
new file mode 100644
index 000000000000..f11a734da1db
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -0,0 +1,207 @@
+/*
+ * Copyright 2012-14 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef DC_LINK_H_
+#define DC_LINK_H_
+
+#include "dc_types.h"
+#include "grph_object_defs.h"
+
+struct dc_link_status {
+	struct dpcd_caps *dpcd_caps;
+};
+
+/* DP MST stream allocation (payload bandwidth number) */
+struct link_mst_stream_allocation {
+	/* DIG front */
+	const struct stream_encoder *stream_enc;
+	/* associate DRM payload table with DC stream encoder */
+	uint8_t vcp_id;
+	/* number of slots required for the DP stream in transport packet */
+	uint8_t slot_count;
+};
+
+/* DP MST stream allocation table */
+struct link_mst_stream_allocation_table {
+	/* number of DP video streams */
+	int stream_count;
+	/* array of stream allocations */
+	struct link_mst_stream_allocation stream_allocations[MAX_CONTROLLER_NUM];
+};
+
+/*
+ * A link contains one or more sinks and their connected status.
+ * The currently active signal type (HDMI, DP-SST, DP-MST) is also reported.
+ */
+struct dc_link {
+	struct dc_sink *remote_sinks[MAX_SINKS_PER_LINK];
+	unsigned int sink_count;
+	struct dc_sink *local_sink;
+	unsigned int link_index;
+	enum dc_connection_type type;
+	enum signal_type connector_signal;
+	enum dc_irq_source irq_source_hpd;
+	enum dc_irq_source irq_source_hpd_rx;/* aka DP Short Pulse  */
+	/* caps is the same as reported_link_cap. link_traing use
+	 * reported_link_cap. Will clean up.  TODO
+	 */
+	struct dc_link_settings reported_link_cap;
+	struct dc_link_settings verified_link_cap;
+	struct dc_link_settings cur_link_settings;
+	struct dc_lane_settings cur_lane_setting;
+	struct dc_link_settings preferred_link_setting;
+
+	uint8_t ddc_hw_inst;
+
+	uint8_t hpd_src;
+
+	uint8_t link_enc_hw_inst;
+
+	bool test_pattern_enabled;
+	union compliance_test_state compliance_test_state;
+
+	void *priv;
+
+	struct ddc_service *ddc;
+
+	bool aux_mode;
+
+	/* Private to DC core */
+
+	const struct dc *dc;
+
+	struct dc_context *ctx;
+
+	struct link_encoder *link_enc;
+	struct graphics_object_id link_id;
+	union ddi_channel_mapping ddi_channel_mapping;
+	struct connector_device_tag_info device_tag;
+	struct dpcd_caps dpcd_caps;
+	unsigned short chip_caps;
+	unsigned int dpcd_sink_count;
+	enum edp_revision edp_revision;
+	bool psr_enabled;
+
+	/* MST record stream using this link */
+	struct link_flags {
+		bool dp_keep_receiver_powered;
+	} wa_flags;
+	struct link_mst_stream_allocation_table mst_stream_alloc_table;
+
+	struct dc_link_status link_status;
+
+};
+
+const struct dc_link_status *dc_link_get_status(const struct dc_link *dc_link);
+
+/*
+ * Return an enumerated dc_link.  dc_link order is constant and determined at
+ * boot time.  They cannot be created or destroyed.
+ * Use dc_get_caps() to get number of links.
+ */
+static inline struct dc_link *dc_get_link_at_index(struct dc *dc, uint32_t link_index)
+{
+	return dc->links[link_index];
+}
+
+/* Set backlight level of an embedded panel (eDP, LVDS). */
+bool dc_link_set_backlight_level(const struct dc_link *dc_link, uint32_t level,
+		uint32_t frame_ramp, const struct dc_stream_state *stream);
+
+bool dc_link_set_psr_enable(const struct dc_link *dc_link, bool enable, bool wait);
+
+bool dc_link_get_psr_state(const struct dc_link *dc_link, uint32_t *psr_state);
+
+bool dc_link_setup_psr(struct dc_link *dc_link,
+		const struct dc_stream_state *stream, struct psr_config *psr_config,
+		struct psr_context *psr_context);
+
+/* Request DC to detect if there is a Panel connected.
+ * boot - If this call is during initial boot.
+ * Return false for any type of detection failure or MST detection
+ * true otherwise. True meaning further action is required (status update
+ * and OS notification).
+ */
+enum dc_detect_reason {
+	DETECT_REASON_BOOT,
+	DETECT_REASON_HPD,
+	DETECT_REASON_HPDRX,
+};
+
+bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason);
+
+/* Notify DC about DP RX Interrupt (aka Short Pulse Interrupt).
+ * Return:
+ * true - Downstream port status changed. DM should call DC to do the
+ * detection.
+ * false - no change in Downstream port status. No further action required
+ * from DM. */
+bool dc_link_handle_hpd_rx_irq(struct dc_link *dc_link,
+		union hpd_irq_data *hpd_irq_dpcd_data);
+
+struct dc_sink_init_data;
+
+struct dc_sink *dc_link_add_remote_sink(
+		struct dc_link *dc_link,
+		const uint8_t *edid,
+		int len,
+		struct dc_sink_init_data *init_data);
+
+void dc_link_remove_remote_sink(
+	struct dc_link *link,
+	struct dc_sink *sink);
+
+/* Used by diagnostics for virtual link at the moment */
+
+void dc_link_dp_set_drive_settings(
+	struct dc_link *link,
+	struct link_training_settings *lt_settings);
+
+enum link_training_result dc_link_dp_perform_link_training(
+	struct dc_link *link,
+	const struct dc_link_settings *link_setting,
+	bool skip_video_pattern);
+
+void dc_link_dp_enable_hpd(const struct dc_link *link);
+
+void dc_link_dp_disable_hpd(const struct dc_link *link);
+
+bool dc_link_dp_set_test_pattern(
+	struct dc_link *link,
+	enum dp_test_pattern test_pattern,
+	const struct link_training_settings *p_link_settings,
+	const unsigned char *p_custom_pattern,
+	unsigned int cust_pattern_size);
+
+/*
+ * DPCD access interfaces
+ */
+
+bool dc_submit_i2c(
+		struct dc *dc,
+		uint32_t link_index,
+		struct i2c_command *cmd);
+
+#endif /* DC_LINK_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
new file mode 100644
index 000000000000..01c60f11b2bd
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -0,0 +1,293 @@
+/*
+ * Copyright 2012-14 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef DC_STREAM_H_
+#define DC_STREAM_H_
+
+#include "dc_types.h"
+#include "grph_object_defs.h"
+
+/*******************************************************************************
+ * Stream Interfaces
+ ******************************************************************************/
+
+struct dc_stream_status {
+	int primary_otg_inst;
+	int stream_enc_inst;
+	int plane_count;
+	struct dc_plane_state *plane_states[MAX_SURFACE_NUM];
+
+	/*
+	 * link this stream passes through
+	 */
+	struct dc_link *link;
+};
+
+struct dc_stream_state {
+	struct dc_sink *sink;
+	struct dc_crtc_timing timing;
+
+	struct rect src; /* composition area */
+	struct rect dst; /* stream addressable area */
+
+	struct audio_info audio_info;
+
+	struct freesync_context freesync_ctx;
+
+	struct dc_hdr_static_metadata hdr_static_metadata;
+	struct dc_transfer_func *out_transfer_func;
+	struct colorspace_transform gamut_remap_matrix;
+	struct csc_transform csc_color_matrix;
+
+	enum dc_color_space output_color_space;
+	enum dc_dither_option dither_option;
+
+	enum view_3d_format view_format;
+
+	bool ignore_msa_timing_param;
+	/* TODO: custom INFO packets */
+	/* TODO: ABM info (DMCU) */
+	/* TODO: PSR info */
+	/* TODO: CEA VIC */
+
+	/* from core_stream struct */
+	struct dc_context *ctx;
+
+	/* used by DCP and FMT */
+	struct bit_depth_reduction_params bit_depth_params;
+	struct clamping_and_pixel_encoding_params clamping;
+
+	int phy_pix_clk;
+	enum signal_type signal;
+	bool dpms_off;
+
+	struct dc_stream_status status;
+
+	struct dc_cursor_attributes cursor_attributes;
+	struct dc_cursor_position cursor_position;
+
+	/* from stream struct */
+	struct kref refcount;
+
+	struct crtc_trigger_info triggered_crtc_reset;
+
+	/* Computed state bits */
+	bool mode_changed : 1;
+
+};
+
+struct dc_stream_update {
+	struct rect src;
+	struct rect dst;
+	struct dc_transfer_func *out_transfer_func;
+	struct dc_hdr_static_metadata *hdr_static_metadata;
+};
+
+bool dc_is_stream_unchanged(
+	struct dc_stream_state *old_stream, struct dc_stream_state *stream);
+bool dc_is_stream_scaling_unchanged(
+	struct dc_stream_state *old_stream, struct dc_stream_state *stream);
+
+/*
+ * Set up surface attributes and associate to a stream
+ * The surfaces parameter is an absolute set of all surface active for the stream.
+ * If no surfaces are provided, the stream will be blanked; no memory read.
+ * Any flip related attribute changes must be done through this interface.
+ *
+ * After this call:
+ *   Surfaces attributes are programmed and configured to be composed into stream.
+ *   This does not trigger a flip.  No surface address is programmed.
+ */
+
+bool dc_commit_planes_to_stream(
+		struct dc *dc,
+		struct dc_plane_state **plane_states,
+		uint8_t new_plane_count,
+		struct dc_stream_state *dc_stream,
+		struct dc_state *state);
+
+void dc_commit_updates_for_stream(struct dc *dc,
+		struct dc_surface_update *srf_updates,
+		int surface_count,
+		struct dc_stream_state *stream,
+		struct dc_stream_update *stream_update,
+		struct dc_plane_state **plane_states,
+		struct dc_state *state);
+/*
+ * Log the current stream state.
+ */
+void dc_stream_log(
+	const struct dc_stream_state *stream,
+	struct dal_logger *dc_logger,
+	enum dc_log_type log_type);
+
+uint8_t dc_get_current_stream_count(struct dc *dc);
+struct dc_stream_state *dc_get_stream_at_index(struct dc *dc, uint8_t i);
+
+/*
+ * Return the current frame counter.
+ */
+uint32_t dc_stream_get_vblank_counter(const struct dc_stream_state *stream);
+
+/* TODO: Return parsed values rather than direct register read
+ * This has a dependency on the caller (amdgpu_get_crtc_scanoutpos)
+ * being refactored properly to be dce-specific
+ */
+bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream,
+				  uint32_t *v_blank_start,
+				  uint32_t *v_blank_end,
+				  uint32_t *h_position,
+				  uint32_t *v_position);
+
+enum dc_status dc_add_stream_to_ctx(
+			struct dc *dc,
+		struct dc_state *new_ctx,
+		struct dc_stream_state *stream);
+
+enum dc_status dc_remove_stream_from_ctx(
+		struct dc *dc,
+			struct dc_state *new_ctx,
+			struct dc_stream_state *stream);
+
+
+bool dc_add_plane_to_context(
+		const struct dc *dc,
+		struct dc_stream_state *stream,
+		struct dc_plane_state *plane_state,
+		struct dc_state *context);
+
+bool dc_remove_plane_from_context(
+		const struct dc *dc,
+		struct dc_stream_state *stream,
+		struct dc_plane_state *plane_state,
+		struct dc_state *context);
+
+bool dc_rem_all_planes_for_stream(
+		const struct dc *dc,
+		struct dc_stream_state *stream,
+		struct dc_state *context);
+
+bool dc_add_all_planes_for_stream(
+		const struct dc *dc,
+		struct dc_stream_state *stream,
+		struct dc_plane_state * const *plane_states,
+		int plane_count,
+		struct dc_state *context);
+
+enum dc_status dc_validate_stream(struct dc *dc, struct dc_stream_state *stream);
+
+/*
+ * This function takes a stream and checks if it is guaranteed to be supported.
+ * Guaranteed means that MAX_COFUNC similar streams are supported.
+ *
+ * After this call:
+ *   No hardware is programmed for call.  Only validation is done.
+ */
+
+/*
+ * Set up streams and links associated to drive sinks
+ * The streams parameter is an absolute set of all active streams.
+ *
+ * After this call:
+ *   Phy, Encoder, Timing Generator are programmed and enabled.
+ *   New streams are enabled with blank stream; no memory read.
+ */
+/*
+ * Enable stereo when commit_streams is not required,
+ * for example, frame alternate.
+ */
+bool dc_enable_stereo(
+	struct dc *dc,
+	struct dc_state *context,
+	struct dc_stream_state *streams[],
+	uint8_t stream_count);
+
+
+enum surface_update_type dc_check_update_surfaces_for_stream(
+		struct dc *dc,
+		struct dc_surface_update *updates,
+		int surface_count,
+		struct dc_stream_update *stream_update,
+		const struct dc_stream_status *stream_status);
+
+/**
+ * Create a new default stream for the requested sink
+ */
+struct dc_stream_state *dc_create_stream_for_sink(struct dc_sink *dc_sink);
+
+void dc_stream_retain(struct dc_stream_state *dc_stream);
+void dc_stream_release(struct dc_stream_state *dc_stream);
+
+struct dc_stream_status *dc_stream_get_status(
+	struct dc_stream_state *dc_stream);
+
+/*******************************************************************************
+ * Cursor interfaces - To manages the cursor within a stream
+ ******************************************************************************/
+/* TODO: Deprecated once we switch to dc_set_cursor_position */
+bool dc_stream_set_cursor_attributes(
+	struct dc_stream_state *stream,
+	const struct dc_cursor_attributes *attributes);
+
+bool dc_stream_set_cursor_position(
+	struct dc_stream_state *stream,
+	const struct dc_cursor_position *position);
+
+bool dc_stream_adjust_vmin_vmax(struct dc *dc,
+				struct dc_stream_state **stream,
+				int num_streams,
+				int vmin,
+				int vmax);
+
+bool dc_stream_get_crtc_position(struct dc *dc,
+				 struct dc_stream_state **stream,
+				 int num_streams,
+				 unsigned int *v_pos,
+				 unsigned int *nom_v_pos);
+
+void dc_stream_set_static_screen_events(struct dc *dc,
+					struct dc_stream_state **stream,
+					int num_streams,
+					const struct dc_static_screen_events *events);
+
+
+bool dc_stream_adjust_vmin_vmax(struct dc *dc,
+				struct dc_stream_state **stream,
+				int num_streams,
+				int vmin,
+				int vmax);
+
+bool dc_stream_get_crtc_position(struct dc *dc,
+				 struct dc_stream_state **stream,
+				 int num_streams,
+				 unsigned int *v_pos,
+				 unsigned int *nom_v_pos);
+
+void dc_stream_set_static_screen_events(struct dc *dc,
+					struct dc_stream_state **stream,
+					int num_streams,
+					const struct dc_static_screen_events *events);
+
+#endif /* DC_STREAM_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index a8698e399111..9faddfae241d 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -218,6 +218,7 @@ struct dc_edid_caps {
 	bool lte_340mcsc_scramble;
 
 	bool edid_hdmi;
+	bool hdr_supported;
 };
 
 struct view {
@@ -638,11 +639,6 @@ struct colorspace_transform {
 	bool enable_remap;
 };
 
-struct csc_transform {
-	uint16_t matrix[12];
-	bool enable_adjustment;
-};
-
 enum i2c_mot_mode {
 	I2C_MOT_UNDEF,
 	I2C_MOT_TRUE,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/Makefile b/drivers/gpu/drm/amd/display/dc/dce/Makefile
index 8abec0bed379..11401fd8e535 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for common 'dce' logic
 # HW object file under this folder follow similar pattern for HW programming
 #   - register offset and/or shift + mask stored in the dec_hw struct
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
index 0e0336c5af4e..b48190f54907 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
@@ -51,16 +51,6 @@
 
 #define MCP_DISABLE_ABM_IMMEDIATELY 255
 
-struct abm_backlight_registers {
-	unsigned int BL_PWM_CNTL;
-	unsigned int BL_PWM_CNTL2;
-	unsigned int BL_PWM_PERIOD_CNTL;
-	unsigned int LVTMA_PWRSEQ_REF_DIV_BL_PWM_REF_DIV;
-};
-
-/* registers setting needs to be save and restored used at InitBacklight */
-static struct abm_backlight_registers stored_backlight_registers = {0};
-
 
 static unsigned int get_current_backlight_16_bit(struct dce_abm *abm_dce)
 {
@@ -347,16 +337,16 @@ static bool dce_abm_init_backlight(struct abm *abm)
 	 */
 	REG_GET(BL_PWM_CNTL, BL_ACTIVE_INT_FRAC_CNT, &value);
 	if (value == 0 || value == 1) {
-		if (stored_backlight_registers.BL_PWM_CNTL != 0) {
+		if (abm->stored_backlight_registers.BL_PWM_CNTL != 0) {
 			REG_WRITE(BL_PWM_CNTL,
-				stored_backlight_registers.BL_PWM_CNTL);
+				abm->stored_backlight_registers.BL_PWM_CNTL);
 			REG_WRITE(BL_PWM_CNTL2,
-				stored_backlight_registers.BL_PWM_CNTL2);
+				abm->stored_backlight_registers.BL_PWM_CNTL2);
 			REG_WRITE(BL_PWM_PERIOD_CNTL,
-				stored_backlight_registers.BL_PWM_PERIOD_CNTL);
+				abm->stored_backlight_registers.BL_PWM_PERIOD_CNTL);
 			REG_UPDATE(LVTMA_PWRSEQ_REF_DIV,
 				BL_PWM_REF_DIV,
-				stored_backlight_registers.
+				abm->stored_backlight_registers.
 				LVTMA_PWRSEQ_REF_DIV_BL_PWM_REF_DIV);
 		} else {
 			/* TODO: Note: This should not really happen since VBIOS
@@ -366,15 +356,15 @@ static bool dce_abm_init_backlight(struct abm *abm)
 			REG_WRITE(BL_PWM_PERIOD_CNTL, 0x000C0FA0);
 		}
 	} else {
-		stored_backlight_registers.BL_PWM_CNTL =
+		abm->stored_backlight_registers.BL_PWM_CNTL =
 				REG_READ(BL_PWM_CNTL);
-		stored_backlight_registers.BL_PWM_CNTL2 =
+		abm->stored_backlight_registers.BL_PWM_CNTL2 =
 				REG_READ(BL_PWM_CNTL2);
-		stored_backlight_registers.BL_PWM_PERIOD_CNTL =
+		abm->stored_backlight_registers.BL_PWM_PERIOD_CNTL =
 				REG_READ(BL_PWM_PERIOD_CNTL);
 
 		REG_GET(LVTMA_PWRSEQ_REF_DIV, BL_PWM_REF_DIV,
-				&stored_backlight_registers.
+				&abm->stored_backlight_registers.
 				LVTMA_PWRSEQ_REF_DIV_BL_PWM_REF_DIV);
 	}
 
@@ -395,21 +385,12 @@ static bool dce_abm_init_backlight(struct abm *abm)
 	return true;
 }
 
-static bool is_dmcu_initialized(struct abm *abm)
-{
-	struct dce_abm *abm_dce = TO_DCE_ABM(abm);
-	unsigned int dmcu_uc_reset;
-
-	REG_GET(DMCU_STATUS, UC_IN_RESET, &dmcu_uc_reset);
-
-	return !dmcu_uc_reset;
-}
-
 static bool dce_abm_set_backlight_level(
 		struct abm *abm,
 		unsigned int backlight_level,
 		unsigned int frame_ramp,
-		unsigned int controller_id)
+		unsigned int controller_id,
+		bool use_smooth_brightness)
 {
 	struct dce_abm *abm_dce = TO_DCE_ABM(abm);
 
@@ -418,7 +399,7 @@ static bool dce_abm_set_backlight_level(
 			backlight_level, backlight_level);
 
 	/* If DMCU is in reset state, DMCU is uninitialized */
-	if (is_dmcu_initialized(abm))
+	if (use_smooth_brightness)
 		dmcu_set_backlight_level(abm_dce,
 				backlight_level,
 				frame_ramp,
@@ -435,8 +416,7 @@ static const struct abm_funcs dce_funcs = {
 	.init_backlight = dce_abm_init_backlight,
 	.set_backlight_level = dce_abm_set_backlight_level,
 	.get_current_backlight_8_bit = dce_abm_get_current_backlight_8_bit,
-	.set_abm_immediate_disable = dce_abm_immediate_disable,
-	.is_dmcu_initialized = is_dmcu_initialized
+	.set_abm_immediate_disable = dce_abm_immediate_disable
 };
 
 static void dce_abm_construct(
@@ -450,6 +430,10 @@ static void dce_abm_construct(
 
 	base->ctx = ctx;
 	base->funcs = &dce_funcs;
+	base->stored_backlight_registers.BL_PWM_CNTL = 0;
+	base->stored_backlight_registers.BL_PWM_CNTL2 = 0;
+	base->stored_backlight_registers.BL_PWM_PERIOD_CNTL = 0;
+	base->stored_backlight_registers.LVTMA_PWRSEQ_REF_DIV_BL_PWM_REF_DIV = 0;
 
 	abm_dce->regs = regs;
 	abm_dce->abm_shift = abm_shift;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
index 59e909ec88f2..ff9436966041 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
@@ -37,8 +37,7 @@
 	SR(LVTMA_PWRSEQ_REF_DIV), \
 	SR(MASTER_COMM_CNTL_REG), \
 	SR(MASTER_COMM_CMD_REG), \
-	SR(MASTER_COMM_DATA_REG1), \
-	SR(DMCU_STATUS)
+	SR(MASTER_COMM_DATA_REG1)
 
 #define ABM_DCE110_COMMON_REG_LIST() \
 	ABM_COMMON_REG_LIST_DCE_BASE(), \
@@ -84,8 +83,7 @@
 	ABM_SF(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, mask_sh), \
 	ABM_SF(MASTER_COMM_CMD_REG, MASTER_COMM_CMD_REG_BYTE0, mask_sh), \
 	ABM_SF(MASTER_COMM_CMD_REG, MASTER_COMM_CMD_REG_BYTE1, mask_sh), \
-	ABM_SF(MASTER_COMM_CMD_REG, MASTER_COMM_CMD_REG_BYTE2, mask_sh), \
-	ABM_SF(DMCU_STATUS, UC_IN_RESET, mask_sh)
+	ABM_SF(MASTER_COMM_CMD_REG, MASTER_COMM_CMD_REG_BYTE2, mask_sh)
 
 #define ABM_MASK_SH_LIST_DCE110(mask_sh) \
 	ABM_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(mask_sh), \
@@ -174,7 +172,6 @@
 	type MASTER_COMM_CMD_REG_BYTE2; \
 	type BL_PWM_REF_DIV; \
 	type BL_PWM_EN; \
-	type UC_IN_RESET; \
 	type BL_PWM_GRP1_IGNORE_MASTER_LOCK_EN; \
 	type BL_PWM_GRP1_REG_LOCK; \
 	type BL_PWM_GRP1_REG_UPDATE_PENDING
@@ -206,7 +203,6 @@ struct dce_abm_registers {
 	uint32_t MASTER_COMM_CMD_REG;
 	uint32_t MASTER_COMM_DATA_REG1;
 	uint32_t BIOS_SCRATCH_2;
-	uint32_t DMCU_STATUS;
 	uint32_t BL_PWM_GRP1_REG_LOCK;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
index 81c40f8864db..0df9ecb2710c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
@@ -352,11 +352,11 @@ void dce_aud_az_enable(struct audio *audio)
 	uint32_t value = AZ_REG_READ(AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL);
 
 	set_reg_field_value(value, 1,
-			AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL,
-			CLOCK_GATING_DISABLE);
-		set_reg_field_value(value, 1,
-			AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL,
-			AUDIO_ENABLED);
+			    AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL,
+			    CLOCK_GATING_DISABLE);
+	set_reg_field_value(value, 1,
+			    AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL,
+			    AUDIO_ENABLED);
 
 	AZ_REG_WRITE(AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL, value);
 	value = AZ_REG_READ(AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL);
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 9031d22285ea..9e98a5f39a6d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -29,7 +29,6 @@
 #include "fixed32_32.h"
 #include "bios_parser_interface.h"
 #include "dc.h"
-#include "dce_abm.h"
 #include "dmcu.h"
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 #include "dcn_calcs.h"
@@ -384,7 +383,6 @@ static int dce112_set_clock(
 	struct bp_set_dce_clock_parameters dce_clk_params;
 	struct dc_bios *bp = clk->ctx->dc_bios;
 	struct dc *core_dc = clk->ctx->dc;
-	struct abm *abm =  core_dc->res_pool->abm;
 	struct dmcu *dmcu = core_dc->res_pool->dmcu;
 	int actual_clock = requested_clk_khz;
 	/* Prepare to program display clock*/
@@ -417,7 +415,7 @@ static int dce112_set_clock(
 
 	bp->funcs->set_dce_clock(bp, &dce_clk_params);
 
-	if (abm->funcs->is_dmcu_initialized(abm) && clk_dce->dfs_bypass_disp_clk != actual_clock)
+	if (clk_dce->dfs_bypass_disp_clk != actual_clock)
 		dmcu->funcs->set_psr_wait_loop(dmcu,
 				actual_clock / 1000 / 7);
 	clk_dce->dfs_bypass_disp_clk = actual_clock;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
index fd77df573b61..f663adb33584 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
@@ -49,8 +49,16 @@
 #define PSR_EXIT 0x21
 #define PSR_SET 0x23
 #define PSR_SET_WAITLOOP 0x31
+#define MCP_INIT_DMCU 0x88
+#define MCP_INIT_IRAM 0x89
+#define MCP_DMCU_VERSION 0x90
 #define MASTER_COMM_CNTL_REG__MASTER_COMM_INTERRUPT_MASK   0x00000001L
-unsigned int cached_wait_loop_number = 0;
+
+static bool dce_dmcu_init(struct dmcu *dmcu)
+{
+	// Do nothing
+	return true;
+}
 
 bool dce_dmcu_load_iram(struct dmcu *dmcu,
 		unsigned int start_offset,
@@ -84,7 +92,7 @@ static void dce_get_dmcu_psr_state(struct dmcu *dmcu, uint32_t *psr_state)
 {
 	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
 
-	uint32_t psrStateOffset = 0xf0;
+	uint32_t psr_state_offset = 0xf0;
 
 	/* Enable write access to IRAM */
 	REG_UPDATE(DMCU_RAM_ACCESS_CTRL, IRAM_HOST_ACCESS_EN, 1);
@@ -92,7 +100,7 @@ static void dce_get_dmcu_psr_state(struct dmcu *dmcu, uint32_t *psr_state)
 	REG_WAIT(DCI_MEM_PWR_STATUS, DMCU_IRAM_MEM_PWR_STATE, 0, 2, 10);
 
 	/* Write address to IRAM_RD_ADDR in DMCU_IRAM_RD_CTRL */
-	REG_WRITE(DMCU_IRAM_RD_CTRL, psrStateOffset);
+	REG_WRITE(DMCU_IRAM_RD_CTRL, psr_state_offset);
 
 	/* Read data from IRAM_RD_DATA in DMCU_IRAM_RD_DATA*/
 	*psr_state = REG_READ(DMCU_IRAM_RD_DATA);
@@ -255,13 +263,33 @@ static void dce_dmcu_setup_psr(struct dmcu *dmcu,
 	REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1);
 }
 
+static bool dce_is_dmcu_initialized(struct dmcu *dmcu)
+{
+	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
+	unsigned int dmcu_uc_reset;
+
+	/* microcontroller is not running */
+	REG_GET(DMCU_STATUS, UC_IN_RESET, &dmcu_uc_reset);
+
+	/* DMCU is not running */
+	if (dmcu_uc_reset)
+		return false;
+
+	return true;
+}
+
 static void dce_psr_wait_loop(
 	struct dmcu *dmcu,
 	unsigned int wait_loop_number)
 {
 	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
 	union dce_dmcu_psr_config_data_wait_loop_reg1 masterCmdData1;
-	if (cached_wait_loop_number == wait_loop_number)
+
+	if (dmcu->cached_wait_loop_number == wait_loop_number)
+		return;
+
+	/* DMCU is not running */
+	if (!dce_is_dmcu_initialized(dmcu))
 		return;
 
 	/* waitDMCUReadyForCmd */
@@ -269,7 +297,7 @@ static void dce_psr_wait_loop(
 
 	masterCmdData1.u32 = 0;
 	masterCmdData1.bits.wait_loop = wait_loop_number;
-	cached_wait_loop_number = wait_loop_number;
+	dmcu->cached_wait_loop_number = wait_loop_number;
 	dm_write_reg(dmcu->ctx, REG(MASTER_COMM_DATA_REG1), masterCmdData1.u32);
 
 	/* setDMCUParam_Cmd */
@@ -279,14 +307,136 @@ static void dce_psr_wait_loop(
 	REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1);
 }
 
-static void dce_get_psr_wait_loop(unsigned int *psr_wait_loop_number)
+static void dce_get_psr_wait_loop(
+		struct dmcu *dmcu, unsigned int *psr_wait_loop_number)
 {
-	*psr_wait_loop_number = cached_wait_loop_number;
+	*psr_wait_loop_number = dmcu->cached_wait_loop_number;
 	return;
 }
 
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-bool dcn10_dmcu_load_iram(struct dmcu *dmcu,
+static void dcn10_get_dmcu_state(struct dmcu *dmcu)
+{
+	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
+	uint32_t dmcu_state_offset = 0xf6;
+
+	/* Enable write access to IRAM */
+	REG_UPDATE_2(DMCU_RAM_ACCESS_CTRL,
+			IRAM_HOST_ACCESS_EN, 1,
+			IRAM_RD_ADDR_AUTO_INC, 1);
+
+	REG_WAIT(DMU_MEM_PWR_CNTL, DMCU_IRAM_MEM_PWR_STATE, 0, 2, 10);
+
+	/* Write address to IRAM_RD_ADDR in DMCU_IRAM_RD_CTRL */
+	REG_WRITE(DMCU_IRAM_RD_CTRL, dmcu_state_offset);
+
+	/* Read data from IRAM_RD_DATA in DMCU_IRAM_RD_DATA*/
+	dmcu->dmcu_state = REG_READ(DMCU_IRAM_RD_DATA);
+
+	/* Disable write access to IRAM to allow dynamic sleep state */
+	REG_UPDATE_2(DMCU_RAM_ACCESS_CTRL,
+			IRAM_HOST_ACCESS_EN, 0,
+			IRAM_RD_ADDR_AUTO_INC, 0);
+}
+
+static void dcn10_get_dmcu_version(struct dmcu *dmcu)
+{
+	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
+	uint32_t dmcu_version_offset = 0xf1;
+
+	/* Clear scratch */
+	REG_WRITE(DC_DMCU_SCRATCH, 0);
+
+	/* Enable write access to IRAM */
+	REG_UPDATE_2(DMCU_RAM_ACCESS_CTRL,
+			IRAM_HOST_ACCESS_EN, 1,
+			IRAM_RD_ADDR_AUTO_INC, 1);
+
+	REG_WAIT(DMU_MEM_PWR_CNTL, DMCU_IRAM_MEM_PWR_STATE, 0, 2, 10);
+
+	/* Write address to IRAM_RD_ADDR and read from DATA register */
+	REG_WRITE(DMCU_IRAM_RD_CTRL, dmcu_version_offset);
+	dmcu->dmcu_version.interface_version = REG_READ(DMCU_IRAM_RD_DATA);
+	dmcu->dmcu_version.year = ((REG_READ(DMCU_IRAM_RD_DATA) << 8) |
+						REG_READ(DMCU_IRAM_RD_DATA));
+	dmcu->dmcu_version.month = REG_READ(DMCU_IRAM_RD_DATA);
+	dmcu->dmcu_version.day = REG_READ(DMCU_IRAM_RD_DATA);
+
+	/* Disable write access to IRAM to allow dynamic sleep state */
+	REG_UPDATE_2(DMCU_RAM_ACCESS_CTRL,
+			IRAM_HOST_ACCESS_EN, 0,
+			IRAM_RD_ADDR_AUTO_INC, 0);
+
+	/* Send MCP command message to DMCU to get version reply from FW.
+	 * We expect this version should match the one in IRAM, otherwise
+	 * something is wrong with DMCU and we should fail and disable UC.
+	 */
+	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0, 100, 800);
+
+	/* Set command to get DMCU version from microcontroller */
+	REG_UPDATE(MASTER_COMM_CMD_REG, MASTER_COMM_CMD_REG_BYTE0,
+			MCP_DMCU_VERSION);
+
+	/* Notify microcontroller of new command */
+	REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1);
+
+	/* Ensure command has been executed before continuing */
+	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0, 100, 800);
+
+	/* Somehow version does not match, so fail and return version 0 */
+	if (dmcu->dmcu_version.interface_version != REG_READ(DC_DMCU_SCRATCH))
+		dmcu->dmcu_version.interface_version = 0;
+}
+
+static bool dcn10_dmcu_init(struct dmcu *dmcu)
+{
+	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
+
+	/* DMCU FW should populate the scratch register if running */
+	if (REG_READ(DC_DMCU_SCRATCH) == 0)
+		return false;
+
+	/* Check state is uninitialized */
+	dcn10_get_dmcu_state(dmcu);
+
+	/* If microcontroller is already initialized, do nothing */
+	if (dmcu->dmcu_state == DMCU_RUNNING)
+		return true;
+
+	/* Retrieve and cache the DMCU firmware version. */
+	dcn10_get_dmcu_version(dmcu);
+
+	/* Check interface version to confirm firmware is loaded and running */
+	if (dmcu->dmcu_version.interface_version == 0)
+		return false;
+
+	/* Wait until microcontroller is ready to process interrupt */
+	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0, 100, 800);
+
+	/* Set initialized ramping boundary value */
+	REG_WRITE(MASTER_COMM_DATA_REG1, 0xFFFF);
+
+	/* Set command to initialize microcontroller */
+	REG_UPDATE(MASTER_COMM_CMD_REG, MASTER_COMM_CMD_REG_BYTE0,
+			MCP_INIT_DMCU);
+
+	/* Notify microcontroller of new command */
+	REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1);
+
+	/* Ensure command has been executed before continuing */
+	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0, 100, 800);
+
+	// Check state is initialized
+	dcn10_get_dmcu_state(dmcu);
+
+	// If microcontroller is not in running state, fail
+	if (dmcu->dmcu_state != DMCU_RUNNING)
+		return false;
+
+	return true;
+}
+
+static bool dcn10_dmcu_load_iram(struct dmcu *dmcu,
 		unsigned int start_offset,
 		const char *src,
 		unsigned int bytes)
@@ -294,7 +444,9 @@ bool dcn10_dmcu_load_iram(struct dmcu *dmcu,
 	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
 	unsigned int count = 0;
 
-	REG_UPDATE(DMCU_CTRL, DMCU_ENABLE, 1);
+	/* If microcontroller is not running, do nothing */
+	if (dmcu->dmcu_state != DMCU_RUNNING)
+		return false;
 
 	/* Enable write access to IRAM */
 	REG_UPDATE_2(DMCU_RAM_ACCESS_CTRL,
@@ -313,6 +465,19 @@ bool dcn10_dmcu_load_iram(struct dmcu *dmcu,
 			IRAM_HOST_ACCESS_EN, 0,
 			IRAM_WR_ADDR_AUTO_INC, 0);
 
+	/* Wait until microcontroller is ready to process interrupt */
+	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0, 100, 800);
+
+	/* Set command to signal IRAM is loaded and to initialize IRAM */
+	REG_UPDATE(MASTER_COMM_CMD_REG, MASTER_COMM_CMD_REG_BYTE0,
+			MCP_INIT_IRAM);
+
+	/* Notify microcontroller of new command */
+	REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1);
+
+	/* Ensure command has been executed before continuing */
+	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0, 100, 800);
+
 	return true;
 }
 
@@ -320,7 +485,11 @@ static void dcn10_get_dmcu_psr_state(struct dmcu *dmcu, uint32_t *psr_state)
 {
 	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
 
-	uint32_t psrStateOffset = 0xf0;
+	uint32_t psr_state_offset = 0xf0;
+
+	/* If microcontroller is not running, do nothing */
+	if (dmcu->dmcu_state != DMCU_RUNNING)
+		return;
 
 	/* Enable write access to IRAM */
 	REG_UPDATE(DMCU_RAM_ACCESS_CTRL, IRAM_HOST_ACCESS_EN, 1);
@@ -328,7 +497,7 @@ static void dcn10_get_dmcu_psr_state(struct dmcu *dmcu, uint32_t *psr_state)
 	REG_WAIT(DMU_MEM_PWR_CNTL, DMCU_IRAM_MEM_PWR_STATE, 0, 2, 10);
 
 	/* Write address to IRAM_RD_ADDR in DMCU_IRAM_RD_CTRL */
-	REG_WRITE(DMCU_IRAM_RD_CTRL, psrStateOffset);
+	REG_WRITE(DMCU_IRAM_RD_CTRL, psr_state_offset);
 
 	/* Read data from IRAM_RD_DATA in DMCU_IRAM_RD_DATA*/
 	*psr_state = REG_READ(DMCU_IRAM_RD_DATA);
@@ -348,6 +517,10 @@ static void dcn10_dmcu_set_psr_enable(struct dmcu *dmcu, bool enable, bool wait)
 	unsigned int retryCount;
 	uint32_t psr_state = 0;
 
+	/* If microcontroller is not running, do nothing */
+	if (dmcu->dmcu_state != DMCU_RUNNING)
+		return;
+
 	/* waitDMCUReadyForCmd */
 	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0,
 				dmcu_wait_reg_ready_interval,
@@ -399,6 +572,10 @@ static void dcn10_dmcu_setup_psr(struct dmcu *dmcu,
 	union dce_dmcu_psr_config_data_reg2 masterCmdData2;
 	union dce_dmcu_psr_config_data_reg3 masterCmdData3;
 
+	/* If microcontroller is not running, do nothing */
+	if (dmcu->dmcu_state != DMCU_RUNNING)
+		return;
+
 	link->link_enc->funcs->psr_program_dp_dphy_fast_training(link->link_enc,
 			psr_context->psrExitLinkTrainingRequired);
 
@@ -505,13 +682,18 @@ static void dcn10_psr_wait_loop(
 {
 	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
 	union dce_dmcu_psr_config_data_wait_loop_reg1 masterCmdData1;
+
+	/* If microcontroller is not running, do nothing */
+	if (dmcu->dmcu_state != DMCU_RUNNING)
+		return;
+
 	if (wait_loop_number != 0) {
 	/* waitDMCUReadyForCmd */
 	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0, 1, 10000);
 
 	masterCmdData1.u32 = 0;
 	masterCmdData1.bits.wait_loop = wait_loop_number;
-	cached_wait_loop_number = wait_loop_number;
+	dmcu->cached_wait_loop_number = wait_loop_number;
 	dm_write_reg(dmcu->ctx, REG(MASTER_COMM_DATA_REG1), masterCmdData1.u32);
 
 	/* setDMCUParam_Cmd */
@@ -522,31 +704,44 @@ static void dcn10_psr_wait_loop(
 	}
 }
 
-static void dcn10_get_psr_wait_loop(unsigned int *psr_wait_loop_number)
+static void dcn10_get_psr_wait_loop(
+		struct dmcu *dmcu, unsigned int *psr_wait_loop_number)
 {
-	*psr_wait_loop_number = cached_wait_loop_number;
+	*psr_wait_loop_number = dmcu->cached_wait_loop_number;
 	return;
 }
 
+static bool dcn10_is_dmcu_initialized(struct dmcu *dmcu)
+{
+	/* microcontroller is not running */
+	if (dmcu->dmcu_state != DMCU_RUNNING)
+		return false;
+	return true;
+}
+
 #endif
 
 static const struct dmcu_funcs dce_funcs = {
+	.dmcu_init = dce_dmcu_init,
 	.load_iram = dce_dmcu_load_iram,
 	.set_psr_enable = dce_dmcu_set_psr_enable,
 	.setup_psr = dce_dmcu_setup_psr,
 	.get_psr_state = dce_get_dmcu_psr_state,
 	.set_psr_wait_loop = dce_psr_wait_loop,
-	.get_psr_wait_loop = dce_get_psr_wait_loop
+	.get_psr_wait_loop = dce_get_psr_wait_loop,
+	.is_dmcu_initialized = dce_is_dmcu_initialized
 };
 
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 static const struct dmcu_funcs dcn10_funcs = {
+	.dmcu_init = dcn10_dmcu_init,
 	.load_iram = dcn10_dmcu_load_iram,
 	.set_psr_enable = dcn10_dmcu_set_psr_enable,
 	.setup_psr = dcn10_dmcu_setup_psr,
 	.get_psr_state = dcn10_get_dmcu_psr_state,
 	.set_psr_wait_loop = dcn10_psr_wait_loop,
-	.get_psr_wait_loop = dcn10_get_psr_wait_loop
+	.get_psr_wait_loop = dcn10_get_psr_wait_loop,
+	.is_dmcu_initialized = dcn10_is_dmcu_initialized
 };
 #endif
 
@@ -561,6 +756,7 @@ static void dce_dmcu_construct(
 
 	base->ctx = ctx;
 	base->funcs = &dce_funcs;
+	base->cached_wait_loop_number = 0;
 
 	dmcu_dce->regs = regs;
 	dmcu_dce->dmcu_shift = dmcu_shift;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
index b85f53c2f6f8..1d4546f23135 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
@@ -31,6 +31,7 @@
 
 #define DMCU_COMMON_REG_LIST_DCE_BASE() \
 	SR(DMCU_CTRL), \
+	SR(DMCU_STATUS), \
 	SR(DMCU_RAM_ACCESS_CTRL), \
 	SR(DMCU_IRAM_WR_CTRL), \
 	SR(DMCU_IRAM_WR_DATA), \
@@ -42,7 +43,8 @@
 	SR(DMCU_IRAM_RD_CTRL), \
 	SR(DMCU_IRAM_RD_DATA), \
 	SR(DMCU_INTERRUPT_TO_UC_EN_MASK), \
-	SR(SMU_INTERRUPT_CONTROL)
+	SR(SMU_INTERRUPT_CONTROL), \
+	SR(DC_DMCU_SCRATCH)
 
 #define DMCU_DCE110_COMMON_REG_LIST() \
 	DMCU_COMMON_REG_LIST_DCE_BASE(), \
@@ -58,10 +60,16 @@
 #define DMCU_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(mask_sh) \
 	DMCU_SF(DMCU_CTRL, \
 			DMCU_ENABLE, mask_sh), \
+	DMCU_SF(DMCU_STATUS, \
+			UC_IN_STOP_MODE, mask_sh), \
+	DMCU_SF(DMCU_STATUS, \
+			UC_IN_RESET, mask_sh), \
 	DMCU_SF(DMCU_RAM_ACCESS_CTRL, \
 			IRAM_HOST_ACCESS_EN, mask_sh), \
 	DMCU_SF(DMCU_RAM_ACCESS_CTRL, \
 			IRAM_WR_ADDR_AUTO_INC, mask_sh), \
+	DMCU_SF(DMCU_RAM_ACCESS_CTRL, \
+			IRAM_RD_ADDR_AUTO_INC, mask_sh), \
 	DMCU_SF(MASTER_COMM_CMD_REG, \
 			MASTER_COMM_CMD_REG_BYTE0, mask_sh), \
 	DMCU_SF(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, mask_sh), \
@@ -89,7 +97,10 @@
 	type DMCU_IRAM_MEM_PWR_STATE; \
 	type IRAM_HOST_ACCESS_EN; \
 	type IRAM_WR_ADDR_AUTO_INC; \
+	type IRAM_RD_ADDR_AUTO_INC; \
 	type DMCU_ENABLE; \
+	type UC_IN_STOP_MODE; \
+	type UC_IN_RESET; \
 	type MASTER_COMM_CMD_REG_BYTE0; \
 	type MASTER_COMM_INTERRUPT; \
 	type DPHY_RX_FAST_TRAINING_CAPABLE; \
@@ -112,6 +123,7 @@ struct dce_dmcu_mask {
 
 struct dce_dmcu_registers {
 	uint32_t DMCU_CTRL;
+	uint32_t DMCU_STATUS;
 	uint32_t DMCU_RAM_ACCESS_CTRL;
 	uint32_t DCI_MEM_PWR_STATUS;
 	uint32_t DMU_MEM_PWR_CNTL;
@@ -127,6 +139,7 @@ struct dce_dmcu_registers {
 	uint32_t DMCU_IRAM_RD_DATA;
 	uint32_t DMCU_INTERRUPT_TO_UC_EN_MASK;
 	uint32_t SMU_INTERRUPT_CONTROL;
+	uint32_t DC_DMCU_SCRATCH;
 };
 
 struct dce_dmcu {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index 52506155e361..b73db9e78437 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -140,10 +140,6 @@
 	BL_REG_LIST()
 
 #define HWSEQ_DCN_REG_LIST()\
-	SRII(OTG_GLOBAL_SYNC_STATUS, OTG, 0), \
-	SRII(OTG_GLOBAL_SYNC_STATUS, OTG, 1), \
-	SRII(OTG_GLOBAL_SYNC_STATUS, OTG, 2), \
-	SRII(OTG_GLOBAL_SYNC_STATUS, OTG, 3), \
 	SRII(DCHUBP_CNTL, HUBP, 0), \
 	SRII(DCHUBP_CNTL, HUBP, 1), \
 	SRII(DCHUBP_CNTL, HUBP, 2), \
@@ -264,7 +260,6 @@ struct dce_hwseq_registers {
 	uint32_t DCHUB_AGP_BOT;
 	uint32_t DCHUB_AGP_TOP;
 
-	uint32_t OTG_GLOBAL_SYNC_STATUS[4];
 	uint32_t DCHUBP_CNTL[4];
 	uint32_t HUBP_CLK_CNTL[4];
 	uint32_t DPP_CONTROL[4];
@@ -438,8 +433,6 @@ struct dce_hwseq_registers {
 #define HWSEQ_DCN_MASK_SH_LIST(mask_sh)\
 	HWSEQ_PIXEL_RATE_MASK_SH_LIST(mask_sh, OTG0_),\
 	HWS_SF1(OTG0_, PHYPLL_PIXEL_RATE_CNTL, PHYPLL_PIXEL_RATE_SOURCE, mask_sh), \
-	HWS_SF(OTG0_, OTG_GLOBAL_SYNC_STATUS, VUPDATE_NO_LOCK_EVENT_CLEAR, mask_sh), \
-	HWS_SF(OTG0_, OTG_GLOBAL_SYNC_STATUS, VUPDATE_NO_LOCK_EVENT_OCCURRED, mask_sh), \
 	HWS_SF(HUBP0_, DCHUBP_CNTL, HUBP_VTG_SEL, mask_sh), \
 	HWS_SF(HUBP0_, HUBP_CLK_CNTL, HUBP_CLOCK_ENABLE, mask_sh), \
 	HWS_SF(DPP_TOP0_, DPP_CONTROL, DPP_CLOCK_ENABLE, mask_sh), \
@@ -536,8 +529,6 @@ struct dce_hwseq_registers {
 	type LVTMA_PWRSEQ_TARGET_STATE_R;
 
 #define HWSEQ_DCN_REG_FIELD_LIST(type) \
-	type VUPDATE_NO_LOCK_EVENT_CLEAR; \
-	type VUPDATE_NO_LOCK_EVENT_OCCURRED; \
 	type HUBP_VTG_SEL; \
 	type HUBP_CLOCK_ENABLE; \
 	type DPP_CLOCK_ENABLE; \
@@ -591,7 +582,8 @@ struct dce_hwseq_registers {
 	type DOMAIN7_PGFSM_PWR_STATUS; \
 	type DCFCLK_GATE_DIS; \
 	type DCHUBBUB_GLOBAL_TIMER_REFDIV; \
-	type DENTIST_DPPCLK_WDIVIDER;
+	type DENTIST_DPPCLK_WDIVIDER; \
+	type DENTIST_DISPCLK_WDIVIDER;
 
 struct dce_hwseq_shift {
 	HWSEQ_REG_FIELD_LIST(uint8_t)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c b/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c
index d618fdd0cc82..d737e911971b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c
@@ -135,36 +135,34 @@ static void dce_ipp_cursor_set_attributes(
 }
 
 
-static void dce_ipp_program_prescale(
-	struct input_pixel_processor *ipp,
-	struct ipp_prescale_params *params)
+static void dce_ipp_program_prescale(struct input_pixel_processor *ipp,
+				     struct ipp_prescale_params *params)
 {
 	struct dce_ipp *ipp_dce = TO_DCE_IPP(ipp);
 
 	/* set to bypass mode first before change */
 	REG_UPDATE(PRESCALE_GRPH_CONTROL,
-		GRPH_PRESCALE_BYPASS,
-		1);
+		   GRPH_PRESCALE_BYPASS, 1);
 
 	REG_SET_2(PRESCALE_VALUES_GRPH_R, 0,
-		GRPH_PRESCALE_SCALE_R, params->scale,
-		GRPH_PRESCALE_BIAS_R, params->bias);
+		  GRPH_PRESCALE_SCALE_R, params->scale,
+		  GRPH_PRESCALE_BIAS_R, params->bias);
 
 	REG_SET_2(PRESCALE_VALUES_GRPH_G, 0,
-		GRPH_PRESCALE_SCALE_G, params->scale,
-		GRPH_PRESCALE_BIAS_G, params->bias);
+		  GRPH_PRESCALE_SCALE_G, params->scale,
+		  GRPH_PRESCALE_BIAS_G, params->bias);
 
 	REG_SET_2(PRESCALE_VALUES_GRPH_B, 0,
-		GRPH_PRESCALE_SCALE_B, params->scale,
-		GRPH_PRESCALE_BIAS_B, params->bias);
+		  GRPH_PRESCALE_SCALE_B, params->scale,
+		  GRPH_PRESCALE_BIAS_B, params->bias);
 
 	if (params->mode != IPP_PRESCALE_MODE_BYPASS) {
 		REG_UPDATE(PRESCALE_GRPH_CONTROL,
-				GRPH_PRESCALE_BYPASS, 0);
+			   GRPH_PRESCALE_BYPASS, 0);
 
 		/* If prescale is in use, then legacy lut should be bypassed */
 		REG_UPDATE(INPUT_GAMMA_CONTROL,
-				GRPH_INPUT_GAMMA_MODE, 1);
+			   GRPH_INPUT_GAMMA_MODE, 1);
 	}
 }
 
@@ -223,13 +221,12 @@ static void dce_ipp_set_degamma(
 	struct dce_ipp *ipp_dce = TO_DCE_IPP(ipp);
 	uint32_t degamma_type = (mode == IPP_DEGAMMA_MODE_HW_sRGB) ? 1 : 0;
 
-	ASSERT(mode == IPP_DEGAMMA_MODE_BYPASS ||
-			mode == IPP_DEGAMMA_MODE_HW_sRGB);
+	ASSERT(mode == IPP_DEGAMMA_MODE_BYPASS || mode == IPP_DEGAMMA_MODE_HW_sRGB);
 
 	REG_SET_3(DEGAMMA_CONTROL, 0,
-		GRPH_DEGAMMA_MODE, degamma_type,
-		CURSOR_DEGAMMA_MODE, degamma_type,
-		CURSOR2_DEGAMMA_MODE, degamma_type);
+		  GRPH_DEGAMMA_MODE, degamma_type,
+		  CURSOR_DEGAMMA_MODE, degamma_type,
+		  CURSOR2_DEGAMMA_MODE, degamma_type);
 }
 
 static const struct ipp_funcs dce_ipp_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
index fe88852b4774..a266e3f5e75f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
@@ -845,8 +845,6 @@ void dce110_link_encoder_hw_init(
 
 		ASSERT(result == BP_RESULT_OK);
 
-	} else if (enc110->base.connector.id == CONNECTOR_ID_EDP) {
-		ctx->dc->hwss.edp_power_control(enc, true);
 	}
 	aux_initialize(enc110);
 
@@ -1033,8 +1031,7 @@ void dce110_link_encoder_enable_dp_mst_output(
  */
 void dce110_link_encoder_disable_output(
 	struct link_encoder *enc,
-	enum signal_type signal,
-	struct dc_link *link)
+	enum signal_type signal)
 {
 	struct dce110_link_encoder *enc110 = TO_DCE110_LINK_ENC(enc);
 	struct dc_context *ctx = enc110->base.ctx;
@@ -1045,8 +1042,6 @@ void dce110_link_encoder_disable_output(
 		/* OF_SKIP_POWER_DOWN_INACTIVE_ENCODER */
 		return;
 	}
-	if (enc110->base.connector.id == CONNECTOR_ID_EDP)
-		ctx->dc->hwss.edp_backlight_control(link, false);
 	/* Power-down RX and disable GPU PHY should be paired.
 	 * Disabling PHY without powering down RX may cause
 	 * symbol lock loss, on which we will get DP Sink interrupt. */
@@ -1077,20 +1072,6 @@ void dce110_link_encoder_disable_output(
 	/* disable encoder */
 	if (dc_is_dp_signal(signal))
 		link_encoder_disable(enc110);
-
-	if (enc110->base.connector.id == CONNECTOR_ID_EDP) {
-		/* power down eDP panel */
-		/* TODO: Power control cause regression, we should implement
-		 * it properly, for now just comment it.
-		 *
-		 * link_encoder_edp_wait_for_hpd_ready(
-			link_enc,
-			link_enc->connector,
-			false);
-
-		 * link_encoder_edp_power_control(
-				link_enc, false); */
-	}
 }
 
 void dce110_link_encoder_dp_set_lane_settings(
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
index 494067dedd03..8ca9afe47a2b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
@@ -228,9 +228,8 @@ void dce110_link_encoder_enable_dp_mst_output(
 
 /* disable PHY output */
 void dce110_link_encoder_disable_output(
-	struct link_encoder *link_enc,
-	enum signal_type signal,
-	struct dc_link *link);
+	struct link_encoder *enc,
+	enum signal_type signal);
 
 /* set DP lane settings */
 void dce110_link_encoder_dp_set_lane_settings(
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
index 4fd49a16c3b6..83bae207371d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
@@ -87,6 +87,9 @@ static void dce110_update_generic_info_packet(
 	 */
 	uint32_t max_retries = 50;
 
+	/*we need turn on clock before programming AFMT block*/
+	REG_UPDATE(AFMT_CNTL, AFMT_AUDIO_CLOCK_EN, 1);
+
 	if (REG(AFMT_VBI_PACKET_CONTROL1)) {
 		if (packet_index >= 8)
 			ASSERT(0);
@@ -297,6 +300,8 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	uint32_t h_back_porch;
 	uint8_t synchronous_clock = 0; /* asynchronous mode */
 	uint8_t colorimetry_bpc;
+	uint8_t dynamic_range_rgb = 0; /*full range*/
+	uint8_t dynamic_range_ycbcr = 1; /*bt709*/
 #endif
 
 	struct dce110_stream_encoder *enc110 = DCE110STRENC_FROM_STRENC(enc);
@@ -377,11 +382,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	}
 
 	/* set dynamic range and YCbCr range */
-	if (enc110->se_mask->DP_DYN_RANGE && enc110->se_mask->DP_YCBCR_RANGE)
-		REG_UPDATE_2(
-			DP_PIXEL_FORMAT,
-			DP_DYN_RANGE, 0,
-			DP_YCBCR_RANGE, 0);
+
 
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 	switch (crtc_timing->display_color_depth) {
@@ -410,37 +411,57 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		case COLOR_SPACE_SRGB:
 			misc0 = misc0 | 0x0;
 			misc1 = misc1 & ~0x80; /* bit7 = 0*/
+			dynamic_range_rgb = 0; /*full range*/
 			break;
 		case COLOR_SPACE_SRGB_LIMITED:
 			misc0 = misc0 | 0x8; /* bit3=1 */
 			misc1 = misc1 & ~0x80; /* bit7 = 0*/
+			dynamic_range_rgb = 1; /*limited range*/
 			break;
 		case COLOR_SPACE_YCBCR601:
+		case COLOR_SPACE_YCBCR601_LIMITED:
 			misc0 = misc0 | 0x8; /* bit3=1, bit4=0 */
 			misc1 = misc1 & ~0x80; /* bit7 = 0*/
+			dynamic_range_ycbcr = 0; /*bt601*/
 			if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
 				misc0 = misc0 | 0x2; /* bit2=0, bit1=1 */
 			else if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR444)
 				misc0 = misc0 | 0x4; /* bit2=1, bit1=0 */
 			break;
 		case COLOR_SPACE_YCBCR709:
+		case COLOR_SPACE_YCBCR709_LIMITED:
 			misc0 = misc0 | 0x18; /* bit3=1, bit4=1 */
 			misc1 = misc1 & ~0x80; /* bit7 = 0*/
+			dynamic_range_ycbcr = 1; /*bt709*/
 			if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
 				misc0 = misc0 | 0x2; /* bit2=0, bit1=1 */
 			else if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR444)
 				misc0 = misc0 | 0x4; /* bit2=1, bit1=0 */
 			break;
-		case COLOR_SPACE_2020_RGB_FULLRANGE:
 		case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
+			dynamic_range_rgb = 1; /*limited range*/
+			break;
+		case COLOR_SPACE_2020_RGB_FULLRANGE:
 		case COLOR_SPACE_2020_YCBCR:
+		case COLOR_SPACE_XR_RGB:
+		case COLOR_SPACE_MSREF_SCRGB:
 		case COLOR_SPACE_ADOBERGB:
+		case COLOR_SPACE_DCIP3:
+		case COLOR_SPACE_XV_YCC_709:
+		case COLOR_SPACE_XV_YCC_601:
+		case COLOR_SPACE_DISPLAYNATIVE:
+		case COLOR_SPACE_DOLBYVISION:
+		case COLOR_SPACE_APPCTRL:
+		case COLOR_SPACE_CUSTOMPOINTS:
 		case COLOR_SPACE_UNKNOWN:
-		case COLOR_SPACE_YCBCR601_LIMITED:
-		case COLOR_SPACE_YCBCR709_LIMITED:
 			/* do nothing */
 			break;
 		}
+		if (enc110->se_mask->DP_DYN_RANGE && enc110->se_mask->DP_YCBCR_RANGE)
+			REG_UPDATE_2(
+				DP_PIXEL_FORMAT,
+				DP_DYN_RANGE, dynamic_range_rgb,
+				DP_YCBCR_RANGE, dynamic_range_ycbcr);
 
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 		if (REG(DP_MSA_COLORIMETRY))
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
index ae32af31eff1..0f662e6ee9bd 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
@@ -1177,207 +1177,160 @@ void dce110_opp_set_csc_default(
 		default_adjust->out_color_space);
 }
 
-static void program_pwl(
-	struct dce_transform *xfm_dce,
-	const struct pwl_params *params)
+static void program_pwl(struct dce_transform *xfm_dce,
+			const struct pwl_params *params)
 {
-	uint32_t value;
 	int retval;
+	uint8_t max_tries = 10;
+	uint8_t counter = 0;
+	uint32_t i = 0;
+	const struct pwl_result_data *rgb = params->rgb_resulted;
 
-	{
-		uint8_t max_tries = 10;
-		uint8_t counter = 0;
+	/* Power on LUT memory */
+	if (REG(DCFE_MEM_PWR_CTRL))
+		REG_UPDATE(DCFE_MEM_PWR_CTRL,
+			   DCP_REGAMMA_MEM_PWR_DIS, 1);
+	else
+		REG_UPDATE(DCFE_MEM_LIGHT_SLEEP_CNTL,
+			   REGAMMA_LUT_LIGHT_SLEEP_DIS, 1);
 
-		/* Power on LUT memory */
-		if (REG(DCFE_MEM_PWR_CTRL))
-			REG_UPDATE(DCFE_MEM_PWR_CTRL,
-				DCP_REGAMMA_MEM_PWR_DIS, 1);
-		else
-			REG_UPDATE(DCFE_MEM_LIGHT_SLEEP_CNTL,
-				REGAMMA_LUT_LIGHT_SLEEP_DIS, 1);
-
-		while (counter < max_tries) {
-			if (REG(DCFE_MEM_PWR_STATUS)) {
-				value = REG_READ(DCFE_MEM_PWR_STATUS);
-				REG_GET(DCFE_MEM_PWR_STATUS,
-						DCP_REGAMMA_MEM_PWR_STATE,
-						&retval);
-
-				if (retval == 0)
-						break;
-				++counter;
-			} else {
-				value = REG_READ(DCFE_MEM_LIGHT_SLEEP_CNTL);
-				REG_GET(DCFE_MEM_LIGHT_SLEEP_CNTL,
-						REGAMMA_LUT_MEM_PWR_STATE,
-						&retval);
-
-				if (retval == 0)
-						break;
-				++counter;
-			}
+	while (counter < max_tries) {
+		if (REG(DCFE_MEM_PWR_STATUS)) {
+			REG_GET(DCFE_MEM_PWR_STATUS,
+				DCP_REGAMMA_MEM_PWR_STATE,
+				&retval);
+
+			if (retval == 0)
+				break;
+			++counter;
+		} else {
+			REG_GET(DCFE_MEM_LIGHT_SLEEP_CNTL,
+				REGAMMA_LUT_MEM_PWR_STATE,
+				&retval);
+
+			if (retval == 0)
+				break;
+			++counter;
 		}
+	}
 
-		if (counter == max_tries) {
-			dm_logger_write(xfm_dce->base.ctx->logger, LOG_WARNING,
+	if (counter == max_tries) {
+		dm_logger_write(xfm_dce->base.ctx->logger, LOG_WARNING,
 				"%s: regamma lut was not powered on "
 				"in a timely manner,"
 				" programming still proceeds\n",
 				__func__);
-		}
 	}
 
 	REG_UPDATE(REGAMMA_LUT_WRITE_EN_MASK,
-			REGAMMA_LUT_WRITE_EN_MASK, 7);
+		   REGAMMA_LUT_WRITE_EN_MASK, 7);
 
 	REG_WRITE(REGAMMA_LUT_INDEX, 0);
 
 	/* Program REGAMMA_LUT_DATA */
-	{
-		uint32_t i = 0;
-		const struct pwl_result_data *rgb = params->rgb_resulted;
-
-		while (i != params->hw_points_num) {
+	while (i != params->hw_points_num) {
 
-			REG_WRITE(REGAMMA_LUT_DATA, rgb->red_reg);
-			REG_WRITE(REGAMMA_LUT_DATA, rgb->green_reg);
-			REG_WRITE(REGAMMA_LUT_DATA, rgb->blue_reg);
-			REG_WRITE(REGAMMA_LUT_DATA, rgb->delta_red_reg);
-			REG_WRITE(REGAMMA_LUT_DATA, rgb->delta_green_reg);
-			REG_WRITE(REGAMMA_LUT_DATA, rgb->delta_blue_reg);
+		REG_WRITE(REGAMMA_LUT_DATA, rgb->red_reg);
+		REG_WRITE(REGAMMA_LUT_DATA, rgb->green_reg);
+		REG_WRITE(REGAMMA_LUT_DATA, rgb->blue_reg);
+		REG_WRITE(REGAMMA_LUT_DATA, rgb->delta_red_reg);
+		REG_WRITE(REGAMMA_LUT_DATA, rgb->delta_green_reg);
+		REG_WRITE(REGAMMA_LUT_DATA, rgb->delta_blue_reg);
 
-			++rgb;
-			++i;
-		}
+		++rgb;
+		++i;
 	}
 
 	/*  we are done with DCP LUT memory; re-enable low power mode */
 	if (REG(DCFE_MEM_PWR_CTRL))
 		REG_UPDATE(DCFE_MEM_PWR_CTRL,
-			DCP_REGAMMA_MEM_PWR_DIS, 0);
+			   DCP_REGAMMA_MEM_PWR_DIS, 0);
 	else
 		REG_UPDATE(DCFE_MEM_LIGHT_SLEEP_CNTL,
-			REGAMMA_LUT_LIGHT_SLEEP_DIS, 0);
+			   REGAMMA_LUT_LIGHT_SLEEP_DIS, 0);
 }
 
-static void regamma_config_regions_and_segments(
-	struct dce_transform *xfm_dce,
-	const struct pwl_params *params)
+static void regamma_config_regions_and_segments(struct dce_transform *xfm_dce,
+						const struct pwl_params *params)
 {
 	const struct gamma_curve *curve;
 
-	{
-		REG_SET_2(REGAMMA_CNTLA_START_CNTL, 0,
-			REGAMMA_CNTLA_EXP_REGION_START, params->arr_points[0].custom_float_x,
-			REGAMMA_CNTLA_EXP_REGION_START_SEGMENT, 0);
-	}
-	{
-		REG_SET(REGAMMA_CNTLA_SLOPE_CNTL, 0,
-			REGAMMA_CNTLA_EXP_REGION_LINEAR_SLOPE, params->arr_points[0].custom_float_slope);
+	REG_SET_2(REGAMMA_CNTLA_START_CNTL, 0,
+		  REGAMMA_CNTLA_EXP_REGION_START, params->arr_points[0].custom_float_x,
+		  REGAMMA_CNTLA_EXP_REGION_START_SEGMENT, 0);
 
-	}
-	{
-		REG_SET(REGAMMA_CNTLA_END_CNTL1, 0,
-			REGAMMA_CNTLA_EXP_REGION_END, params->arr_points[1].custom_float_x);
-	}
-	{
-		REG_SET_2(REGAMMA_CNTLA_END_CNTL2, 0,
-			REGAMMA_CNTLA_EXP_REGION_END_BASE, params->arr_points[1].custom_float_y,
-			REGAMMA_CNTLA_EXP_REGION_END_SLOPE, params->arr_points[2].custom_float_slope);
-	}
+	REG_SET(REGAMMA_CNTLA_SLOPE_CNTL, 0,
+		REGAMMA_CNTLA_EXP_REGION_LINEAR_SLOPE, params->arr_points[0].custom_float_slope);
 
-	curve = params->arr_curve_points;
+	REG_SET(REGAMMA_CNTLA_END_CNTL1, 0,
+		REGAMMA_CNTLA_EXP_REGION_END, params->arr_points[1].custom_float_x);
 
-	{
-		REG_SET_4(REGAMMA_CNTLA_REGION_0_1, 0,
-			REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
-			REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
-			REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
-			REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
-	}
+	REG_SET_2(REGAMMA_CNTLA_END_CNTL2, 0,
+		  REGAMMA_CNTLA_EXP_REGION_END_BASE, params->arr_points[1].custom_float_y,
+		  REGAMMA_CNTLA_EXP_REGION_END_SLOPE, params->arr_points[1].custom_float_slope);
 
-	curve += 2;
-
-	{
-		REG_SET_4(REGAMMA_CNTLA_REGION_2_3, 0,
-			REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
-			REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
-			REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
-			REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
-
-	}
+	curve = params->arr_curve_points;
 
+	REG_SET_4(REGAMMA_CNTLA_REGION_0_1, 0,
+		  REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
+		  REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
+		  REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
+		  REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
 	curve += 2;
 
-	{
-		REG_SET_4(REGAMMA_CNTLA_REGION_4_5, 0,
-			REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
-			REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
-			REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
-			REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
-
-	}
-
+	REG_SET_4(REGAMMA_CNTLA_REGION_2_3, 0,
+		  REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
+		  REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
+		  REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
+		  REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
 	curve += 2;
 
-	{
-		REG_SET_4(REGAMMA_CNTLA_REGION_6_7, 0,
-			REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
-			REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
-			REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
-			REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
-
-	}
-
+	REG_SET_4(REGAMMA_CNTLA_REGION_4_5, 0,
+		  REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
+		  REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
+		  REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
+		  REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
 	curve += 2;
 
-	{
-		REG_SET_4(REGAMMA_CNTLA_REGION_8_9, 0,
-			REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
-			REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
-			REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
-			REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
-
-	}
-
+	REG_SET_4(REGAMMA_CNTLA_REGION_6_7, 0,
+		  REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
+		  REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
+		  REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
+		  REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
 	curve += 2;
 
-	{
-		REG_SET_4(REGAMMA_CNTLA_REGION_10_11, 0,
-			REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
-			REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
-			REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
-			REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
-
-	}
-
+	REG_SET_4(REGAMMA_CNTLA_REGION_8_9, 0,
+		  REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
+		  REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
+		  REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
+		  REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
 	curve += 2;
 
-	{
-		REG_SET_4(REGAMMA_CNTLA_REGION_12_13, 0,
-			REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
-			REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
-			REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
-			REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
-
-	}
+	REG_SET_4(REGAMMA_CNTLA_REGION_10_11, 0,
+		  REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
+		  REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
+		  REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
+		  REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
+	curve += 2;
 
+	REG_SET_4(REGAMMA_CNTLA_REGION_12_13, 0,
+		  REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
+		  REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
+		  REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
+		  REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
 	curve += 2;
 
-	{
-		REG_SET_4(REGAMMA_CNTLA_REGION_14_15, 0,
-			REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
-			REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
-			REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
-			REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
-	}
+	REG_SET_4(REGAMMA_CNTLA_REGION_14_15, 0,
+		  REGAMMA_CNTLA_EXP_REGION0_LUT_OFFSET, curve[0].offset,
+		  REGAMMA_CNTLA_EXP_REGION0_NUM_SEGMENTS, curve[0].segments_num,
+		  REGAMMA_CNTLA_EXP_REGION1_LUT_OFFSET, curve[1].offset,
+		  REGAMMA_CNTLA_EXP_REGION1_NUM_SEGMENTS, curve[1].segments_num);
 }
 
 
 
-void dce110_opp_program_regamma_pwl(
-	struct transform *xfm,
-	const struct pwl_params *params)
+void dce110_opp_program_regamma_pwl(struct transform *xfm,
+				    const struct pwl_params *params)
 {
 	struct dce_transform *xfm_dce = TO_DCE_TRANSFORM(xfm);
 
@@ -1388,47 +1341,42 @@ void dce110_opp_program_regamma_pwl(
 	program_pwl(xfm_dce, params);
 }
 
-void dce110_opp_power_on_regamma_lut(
-	struct transform *xfm,
-	bool power_on)
+void dce110_opp_power_on_regamma_lut(struct transform *xfm,
+				     bool power_on)
 {
 	struct dce_transform *xfm_dce = TO_DCE_TRANSFORM(xfm);
 
 	if (REG(DCFE_MEM_PWR_CTRL))
 		REG_UPDATE_2(DCFE_MEM_PWR_CTRL,
-			DCP_REGAMMA_MEM_PWR_DIS, power_on,
-			DCP_LUT_MEM_PWR_DIS, power_on);
+			     DCP_REGAMMA_MEM_PWR_DIS, power_on,
+			     DCP_LUT_MEM_PWR_DIS, power_on);
 	else
 		REG_UPDATE_2(DCFE_MEM_LIGHT_SLEEP_CNTL,
-			REGAMMA_LUT_LIGHT_SLEEP_DIS, power_on,
-			DCP_LUT_LIGHT_SLEEP_DIS, power_on);
+			    REGAMMA_LUT_LIGHT_SLEEP_DIS, power_on,
+			    DCP_LUT_LIGHT_SLEEP_DIS, power_on);
 
 }
 
 void dce110_opp_set_regamma_mode(struct transform *xfm,
-		enum opp_regamma mode)
+				 enum opp_regamma mode)
 {
 	struct dce_transform *xfm_dce = TO_DCE_TRANSFORM(xfm);
 
 	REG_SET(REGAMMA_CONTROL, 0,
-			GRPH_REGAMMA_MODE, mode);
+		GRPH_REGAMMA_MODE, mode);
 }
 
 static const struct transform_funcs dce_transform_funcs = {
 	.transform_reset = dce_transform_reset,
-	.transform_set_scaler =
-		dce_transform_set_scaler,
-	.transform_set_gamut_remap =
-		dce_transform_set_gamut_remap,
+	.transform_set_scaler = dce_transform_set_scaler,
+	.transform_set_gamut_remap = dce_transform_set_gamut_remap,
 	.opp_set_csc_adjustment = dce110_opp_set_csc_adjustment,
 	.opp_set_csc_default = dce110_opp_set_csc_default,
 	.opp_power_on_regamma_lut = dce110_opp_power_on_regamma_lut,
 	.opp_program_regamma_pwl = dce110_opp_program_regamma_pwl,
 	.opp_set_regamma_mode = dce110_opp_set_regamma_mode,
-	.transform_set_pixel_storage_depth =
-		dce_transform_set_pixel_storage_depth,
-	.transform_get_optimal_number_of_taps =
-		dce_transform_get_optimal_number_of_taps
+	.transform_set_pixel_storage_depth = dce_transform_set_pixel_storage_depth,
+	.transform_get_optimal_number_of_taps = dce_transform_get_optimal_number_of_taps
 };
 
 /*****************************************/
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/Makefile b/drivers/gpu/drm/amd/display/dc/dce100/Makefile
index ea40870624b3..a822d4e2a169 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce100/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'controller' sub-component of DAL.
 # It provides the control and status of HW CRTC block.
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
index e7a694835e3e..469af0587604 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
@@ -148,5 +148,7 @@ void dce100_hw_sequencer_construct(struct dc *dc)
 
 	dc->hwss.enable_display_power_gating = dce100_enable_display_power_gating;
 	dc->hwss.set_bandwidth = dce100_set_bandwidth;
+	dc->hwss.pplib_apply_display_requirements =
+			dce100_pplib_apply_display_requirements;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index 90911258bdb3..3ea43e2a9450 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -1,5 +1,5 @@
 /*
-* Copyright 2012-15 Advanced Micro Devices, Inc.
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.h b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.h
index de8fdf438f9b..2f366d66635d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.h
@@ -1,4 +1,27 @@
 /*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ *
+ */
+/*
  * dce100_resource.h
  *
  *  Created on: 2016-01-20
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/Makefile b/drivers/gpu/drm/amd/display/dc/dce110/Makefile
index 98d956e2f218..d564c0eb8b04 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce110/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'controller' sub-component of DAL.
 # It provides the control and status of HW CRTC block.
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 1229a3315018..86cdd7b4811f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -257,9 +257,9 @@ static void build_prescale_params(struct ipp_prescale_params *prescale_params,
 	}
 }
 
-static bool dce110_set_input_transfer_func(
-	struct pipe_ctx *pipe_ctx,
-	const struct dc_plane_state *plane_state)
+static bool
+dce110_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
+			       const struct dc_plane_state *plane_state)
 {
 	struct input_pixel_processor *ipp = pipe_ctx->plane_res.ipp;
 	const struct dc_transfer_func *tf = NULL;
@@ -280,25 +280,19 @@ static bool dce110_set_input_transfer_func(
 
 	if (tf == NULL) {
 		/* Default case if no input transfer function specified */
-		ipp->funcs->ipp_set_degamma(ipp,
-				IPP_DEGAMMA_MODE_HW_sRGB);
+		ipp->funcs->ipp_set_degamma(ipp, IPP_DEGAMMA_MODE_HW_sRGB);
 	} else if (tf->type == TF_TYPE_PREDEFINED) {
 		switch (tf->tf) {
 		case TRANSFER_FUNCTION_SRGB:
-			ipp->funcs->ipp_set_degamma(ipp,
-					IPP_DEGAMMA_MODE_HW_sRGB);
+			ipp->funcs->ipp_set_degamma(ipp, IPP_DEGAMMA_MODE_HW_sRGB);
 			break;
 		case TRANSFER_FUNCTION_BT709:
-			ipp->funcs->ipp_set_degamma(ipp,
-					IPP_DEGAMMA_MODE_HW_xvYCC);
+			ipp->funcs->ipp_set_degamma(ipp, IPP_DEGAMMA_MODE_HW_xvYCC);
 			break;
 		case TRANSFER_FUNCTION_LINEAR:
-			ipp->funcs->ipp_set_degamma(ipp,
-					IPP_DEGAMMA_MODE_BYPASS);
+			ipp->funcs->ipp_set_degamma(ipp, IPP_DEGAMMA_MODE_BYPASS);
 			break;
 		case TRANSFER_FUNCTION_PQ:
-			result = false;
-			break;
 		default:
 			result = false;
 			break;
@@ -313,10 +307,9 @@ static bool dce110_set_input_transfer_func(
 	return result;
 }
 
-static bool convert_to_custom_float(
-		struct pwl_result_data *rgb_resulted,
-		struct curve_points *arr_points,
-		uint32_t hw_points_num)
+static bool convert_to_custom_float(struct pwl_result_data *rgb_resulted,
+				    struct curve_points *arr_points,
+				    uint32_t hw_points_num)
 {
 	struct custom_float_format fmt;
 
@@ -328,26 +321,20 @@ static bool convert_to_custom_float(
 	fmt.mantissa_bits = 12;
 	fmt.sign = true;
 
-	if (!convert_to_custom_float_format(
-		arr_points[0].x,
-		&fmt,
-		&arr_points[0].custom_float_x)) {
+	if (!convert_to_custom_float_format(arr_points[0].x, &fmt,
+					    &arr_points[0].custom_float_x)) {
 		BREAK_TO_DEBUGGER();
 		return false;
 	}
 
-	if (!convert_to_custom_float_format(
-		arr_points[0].offset,
-		&fmt,
-		&arr_points[0].custom_float_offset)) {
+	if (!convert_to_custom_float_format(arr_points[0].offset, &fmt,
+					    &arr_points[0].custom_float_offset)) {
 		BREAK_TO_DEBUGGER();
 		return false;
 	}
 
-	if (!convert_to_custom_float_format(
-		arr_points[0].slope,
-		&fmt,
-		&arr_points[0].custom_float_slope)) {
+	if (!convert_to_custom_float_format(arr_points[0].slope, &fmt,
+					    &arr_points[0].custom_float_slope)) {
 		BREAK_TO_DEBUGGER();
 		return false;
 	}
@@ -355,26 +342,20 @@ static bool convert_to_custom_float(
 	fmt.mantissa_bits = 10;
 	fmt.sign = false;
 
-	if (!convert_to_custom_float_format(
-		arr_points[1].x,
-		&fmt,
-		&arr_points[1].custom_float_x)) {
+	if (!convert_to_custom_float_format(arr_points[1].x, &fmt,
+					    &arr_points[1].custom_float_x)) {
 		BREAK_TO_DEBUGGER();
 		return false;
 	}
 
-	if (!convert_to_custom_float_format(
-		arr_points[1].y,
-		&fmt,
-		&arr_points[1].custom_float_y)) {
+	if (!convert_to_custom_float_format(arr_points[1].y, &fmt,
+					    &arr_points[1].custom_float_y)) {
 		BREAK_TO_DEBUGGER();
 		return false;
 	}
 
-	if (!convert_to_custom_float_format(
-		arr_points[2].slope,
-		&fmt,
-		&arr_points[2].custom_float_slope)) {
+	if (!convert_to_custom_float_format(arr_points[1].slope, &fmt,
+					    &arr_points[1].custom_float_slope)) {
 		BREAK_TO_DEBUGGER();
 		return false;
 	}
@@ -383,50 +364,38 @@ static bool convert_to_custom_float(
 	fmt.sign = true;
 
 	while (i != hw_points_num) {
-		if (!convert_to_custom_float_format(
-			rgb->red,
-			&fmt,
-			&rgb->red_reg)) {
+		if (!convert_to_custom_float_format(rgb->red, &fmt,
+						    &rgb->red_reg)) {
 			BREAK_TO_DEBUGGER();
 			return false;
 		}
 
-		if (!convert_to_custom_float_format(
-			rgb->green,
-			&fmt,
-			&rgb->green_reg)) {
+		if (!convert_to_custom_float_format(rgb->green, &fmt,
+						    &rgb->green_reg)) {
 			BREAK_TO_DEBUGGER();
 			return false;
 		}
 
-		if (!convert_to_custom_float_format(
-			rgb->blue,
-			&fmt,
-			&rgb->blue_reg)) {
+		if (!convert_to_custom_float_format(rgb->blue, &fmt,
+						    &rgb->blue_reg)) {
 			BREAK_TO_DEBUGGER();
 			return false;
 		}
 
-		if (!convert_to_custom_float_format(
-			rgb->delta_red,
-			&fmt,
-			&rgb->delta_red_reg)) {
+		if (!convert_to_custom_float_format(rgb->delta_red, &fmt,
+						    &rgb->delta_red_reg)) {
 			BREAK_TO_DEBUGGER();
 			return false;
 		}
 
-		if (!convert_to_custom_float_format(
-			rgb->delta_green,
-			&fmt,
-			&rgb->delta_green_reg)) {
+		if (!convert_to_custom_float_format(rgb->delta_green, &fmt,
+						    &rgb->delta_green_reg)) {
 			BREAK_TO_DEBUGGER();
 			return false;
 		}
 
-		if (!convert_to_custom_float_format(
-			rgb->delta_blue,
-			&fmt,
-			&rgb->delta_blue_reg)) {
+		if (!convert_to_custom_float_format(rgb->delta_blue, &fmt,
+						    &rgb->delta_blue_reg)) {
 			BREAK_TO_DEBUGGER();
 			return false;
 		}
@@ -438,8 +407,9 @@ static bool convert_to_custom_float(
 	return true;
 }
 
-static bool dce110_translate_regamma_to_hw_format(const struct dc_transfer_func
-		*output_tf, struct pwl_params *regamma_params)
+static bool
+dce110_translate_regamma_to_hw_format(const struct dc_transfer_func *output_tf,
+				      struct pwl_params *regamma_params)
 {
 	struct curve_points *arr_points;
 	struct pwl_result_data *rgb_resulted;
@@ -454,8 +424,7 @@ static bool dce110_translate_regamma_to_hw_format(const struct dc_transfer_func
 	int32_t segment_start, segment_end;
 	uint32_t i, j, k, seg_distr[16], increment, start_index, hw_points;
 
-	if (output_tf == NULL || regamma_params == NULL ||
-			output_tf->type == TF_TYPE_BYPASS)
+	if (output_tf == NULL || regamma_params == NULL || output_tf->type == TF_TYPE_BYPASS)
 		return false;
 
 	arr_points = regamma_params->arr_points;
@@ -534,19 +503,14 @@ static bool dce110_translate_regamma_to_hw_format(const struct dc_transfer_func
 
 	/* last point */
 	start_index = (segment_end + 25) * 32;
-	rgb_resulted[hw_points - 1].red =
-			output_tf->tf_pts.red[start_index];
-	rgb_resulted[hw_points - 1].green =
-			output_tf->tf_pts.green[start_index];
-	rgb_resulted[hw_points - 1].blue =
-			output_tf->tf_pts.blue[start_index];
+	rgb_resulted[hw_points - 1].red = output_tf->tf_pts.red[start_index];
+	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
+	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
 	arr_points[0].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-			dal_fixed31_32_from_int(segment_start));
+					     dal_fixed31_32_from_int(segment_start));
 	arr_points[1].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-			dal_fixed31_32_from_int(segment_end));
-	arr_points[2].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-			dal_fixed31_32_from_int(segment_end));
+					     dal_fixed31_32_from_int(segment_end));
 
 	y_r = rgb_resulted[0].red;
 	y_g = rgb_resulted[0].green;
@@ -555,9 +519,8 @@ static bool dce110_translate_regamma_to_hw_format(const struct dc_transfer_func
 	y1_min = dal_fixed31_32_min(y_r, dal_fixed31_32_min(y_g, y_b));
 
 	arr_points[0].y = y1_min;
-	arr_points[0].slope = dal_fixed31_32_div(
-					arr_points[0].y,
-					arr_points[0].x);
+	arr_points[0].slope = dal_fixed31_32_div(arr_points[0].y,
+						 arr_points[0].x);
 
 	y_r = rgb_resulted[hw_points - 1].red;
 	y_g = rgb_resulted[hw_points - 1].green;
@@ -569,24 +532,18 @@ static bool dce110_translate_regamma_to_hw_format(const struct dc_transfer_func
 	y3_max = dal_fixed31_32_max(y_r, dal_fixed31_32_max(y_g, y_b));
 
 	arr_points[1].y = y3_max;
-	arr_points[2].y = y3_max;
 
 	arr_points[1].slope = dal_fixed31_32_zero;
-	arr_points[2].slope = dal_fixed31_32_zero;
 
 	if (output_tf->tf == TRANSFER_FUNCTION_PQ) {
 		/* for PQ, we want to have a straight line from last HW X point,
 		 * and the slope to be such that we hit 1.0 at 10000 nits.
 		 */
-		const struct fixed31_32 end_value =
-				dal_fixed31_32_from_int(125);
+		const struct fixed31_32 end_value = dal_fixed31_32_from_int(125);
 
 		arr_points[1].slope = dal_fixed31_32_div(
-			dal_fixed31_32_sub(dal_fixed31_32_one, arr_points[1].y),
-			dal_fixed31_32_sub(end_value, arr_points[1].x));
-		arr_points[2].slope = dal_fixed31_32_div(
-			dal_fixed31_32_sub(dal_fixed31_32_one, arr_points[1].y),
-			dal_fixed31_32_sub(end_value, arr_points[1].x));
+				dal_fixed31_32_sub(dal_fixed31_32_one, arr_points[1].y),
+				dal_fixed31_32_sub(end_value, arr_points[1].x));
 	}
 
 	regamma_params->hw_points_num = hw_points;
@@ -594,18 +551,15 @@ static bool dce110_translate_regamma_to_hw_format(const struct dc_transfer_func
 	i = 1;
 	for (k = 0; k < 16 && i < 16; k++) {
 		if (seg_distr[k] != -1) {
-			regamma_params->arr_curve_points[k].segments_num =
-					seg_distr[k];
+			regamma_params->arr_curve_points[k].segments_num = seg_distr[k];
 			regamma_params->arr_curve_points[i].offset =
-					regamma_params->arr_curve_points[k].
-					offset + (1 << seg_distr[k]);
+					regamma_params->arr_curve_points[k].offset + (1 << seg_distr[k]);
 		}
 		i++;
 	}
 
 	if (seg_distr[k] != -1)
-		regamma_params->arr_curve_points[k].segments_num =
-				seg_distr[k];
+		regamma_params->arr_curve_points[k].segments_num = seg_distr[k];
 
 	rgb = rgb_resulted;
 	rgb_plus_1 = rgb_resulted + 1;
@@ -620,15 +574,9 @@ static bool dce110_translate_regamma_to_hw_format(const struct dc_transfer_func
 		if (dal_fixed31_32_lt(rgb_plus_1->blue, rgb->blue))
 			rgb_plus_1->blue = rgb->blue;
 
-		rgb->delta_red = dal_fixed31_32_sub(
-			rgb_plus_1->red,
-			rgb->red);
-		rgb->delta_green = dal_fixed31_32_sub(
-			rgb_plus_1->green,
-			rgb->green);
-		rgb->delta_blue = dal_fixed31_32_sub(
-			rgb_plus_1->blue,
-			rgb->blue);
+		rgb->delta_red = dal_fixed31_32_sub(rgb_plus_1->red, rgb->red);
+		rgb->delta_green = dal_fixed31_32_sub(rgb_plus_1->green, rgb->green);
+		rgb->delta_blue = dal_fixed31_32_sub(rgb_plus_1->blue, rgb->blue);
 
 		++rgb_plus_1;
 		++rgb;
@@ -640,9 +588,9 @@ static bool dce110_translate_regamma_to_hw_format(const struct dc_transfer_func
 	return true;
 }
 
-static bool dce110_set_output_transfer_func(
-	struct pipe_ctx *pipe_ctx,
-	const struct dc_stream_state *stream)
+static bool
+dce110_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
+				const struct dc_stream_state *stream)
 {
 	struct transform *xfm = pipe_ctx->plane_res.xfm;
 
@@ -650,13 +598,11 @@ static bool dce110_set_output_transfer_func(
 	xfm->regamma_params.hw_points_num = GAMMA_HW_POINTS_NUM;
 
 	if (stream->out_transfer_func &&
-		stream->out_transfer_func->type ==
-			TF_TYPE_PREDEFINED &&
-		stream->out_transfer_func->tf ==
-			TRANSFER_FUNCTION_SRGB) {
+	    stream->out_transfer_func->type == TF_TYPE_PREDEFINED &&
+	    stream->out_transfer_func->tf == TRANSFER_FUNCTION_SRGB) {
 		xfm->funcs->opp_set_regamma_mode(xfm, OPP_REGAMMA_SRGB);
-	} else if (dce110_translate_regamma_to_hw_format(
-				stream->out_transfer_func, &xfm->regamma_params)) {
+	} else if (dce110_translate_regamma_to_hw_format(stream->out_transfer_func,
+							 &xfm->regamma_params)) {
 		xfm->funcs->opp_program_regamma_pwl(xfm, &xfm->regamma_params);
 		xfm->funcs->opp_set_regamma_mode(xfm, OPP_REGAMMA_USER);
 	} else {
@@ -814,11 +760,11 @@ static enum bp_result link_transmitter_control(
  * eDP only.
  */
 void hwss_edp_wait_for_hpd_ready(
-	struct link_encoder *enc,
-	bool power_up)
+		struct dc_link *link,
+		bool power_up)
 {
-	struct dc_context *ctx = enc->ctx;
-	struct graphics_object_id connector = enc->connector;
+	struct dc_context *ctx = link->ctx;
+	struct graphics_object_id connector = link->link_enc->connector;
 	struct gpio *hpd;
 	bool edp_hpd_high = false;
 	uint32_t time_elapsed = 0;
@@ -882,16 +828,16 @@ void hwss_edp_wait_for_hpd_ready(
 }
 
 void hwss_edp_power_control(
-	struct link_encoder *enc,
-	bool power_up)
+		struct dc_link *link,
+		bool power_up)
 {
-	struct dc_context *ctx = enc->ctx;
+	struct dc_context *ctx = link->ctx;
 	struct dce_hwseq *hwseq = ctx->dc->hwseq;
 	struct bp_transmitter_control cntl = { 0 };
 	enum bp_result bp_result;
 
 
-	if (dal_graphics_object_id_get_connector_id(enc->connector)
+	if (dal_graphics_object_id_get_connector_id(link->link_enc->connector)
 			!= CONNECTOR_ID_EDP) {
 		BREAK_TO_DEBUGGER();
 		return;
@@ -907,11 +853,11 @@ void hwss_edp_power_control(
 		cntl.action = power_up ?
 			TRANSMITTER_CONTROL_POWER_ON :
 			TRANSMITTER_CONTROL_POWER_OFF;
-		cntl.transmitter = enc->transmitter;
-		cntl.connector_obj_id = enc->connector;
+		cntl.transmitter = link->link_enc->transmitter;
+		cntl.connector_obj_id = link->link_enc->connector;
 		cntl.coherent = false;
 		cntl.lanes_number = LANE_COUNT_FOUR;
-		cntl.hpd_sel = enc->hpd_source;
+		cntl.hpd_sel = link->link_enc->hpd_source;
 
 		bp_result = link_transmitter_control(ctx->dc_bios, &cntl);
 
@@ -924,8 +870,6 @@ void hwss_edp_power_control(
 				"%s: Skipping Panel Power action: %s\n",
 				__func__, (power_up ? "On":"Off"));
 	}
-
-	hwss_edp_wait_for_hpd_ready(enc, true);
 }
 
 /*todo: cloned in stream enc, fix*/
@@ -934,14 +878,14 @@ void hwss_edp_power_control(
  * eDP only. Control the backlight of the eDP panel
  */
 void hwss_edp_backlight_control(
-	struct dc_link *link,
-	bool enable)
+		struct dc_link *link,
+		bool enable)
 {
-	struct dce_hwseq *hws = link->dc->hwseq;
-	struct dc_context *ctx = link->dc->ctx;
+	struct dc_context *ctx = link->ctx;
+	struct dce_hwseq *hws = ctx->dc->hwseq;
 	struct bp_transmitter_control cntl = { 0 };
 
-	if (dal_graphics_object_id_get_connector_id(link->link_id)
+	if (dal_graphics_object_id_get_connector_id(link->link_enc->connector)
 		!= CONNECTOR_ID_EDP) {
 		BREAK_TO_DEBUGGER();
 		return;
@@ -982,7 +926,7 @@ void hwss_edp_backlight_control(
 	 * Enable it in the future if necessary.
 	 */
 	/* dc_service_sleep_in_milliseconds(50); */
-	link_transmitter_control(link->dc->ctx->dc_bios, &cntl);
+	link_transmitter_control(ctx->dc_bios, &cntl);
 }
 
 void dce110_disable_stream(struct pipe_ctx *pipe_ctx, int option)
@@ -991,6 +935,16 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx, int option)
 	struct dc_link *link = stream->sink->link;
 	struct dc *dc = pipe_ctx->stream->ctx->dc;
 
+	if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
+		pipe_ctx->stream_res.stream_enc->funcs->stop_hdmi_info_packets(
+			pipe_ctx->stream_res.stream_enc);
+
+	if (dc_is_dp_signal(pipe_ctx->stream->signal))
+		pipe_ctx->stream_res.stream_enc->funcs->stop_dp_info_packets(
+			pipe_ctx->stream_res.stream_enc);
+
+	pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control(
+			pipe_ctx->stream_res.stream_enc, true);
 	if (pipe_ctx->stream_res.audio) {
 		pipe_ctx->stream_res.audio->funcs->az_disable(pipe_ctx->stream_res.audio);
 
@@ -1015,24 +969,10 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx, int option)
 		 */
 	}
 
-	if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
-		pipe_ctx->stream_res.stream_enc->funcs->stop_hdmi_info_packets(
-			pipe_ctx->stream_res.stream_enc);
-
-	if (dc_is_dp_signal(pipe_ctx->stream->signal))
-		pipe_ctx->stream_res.stream_enc->funcs->stop_dp_info_packets(
-			pipe_ctx->stream_res.stream_enc);
-
-	pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control(
-			pipe_ctx->stream_res.stream_enc, true);
-
-
 	/* blank at encoder level */
-	if (dc_is_dp_signal(pipe_ctx->stream->signal)) {
-		if (pipe_ctx->stream->sink->link->connector_signal == SIGNAL_TYPE_EDP)
-			hwss_edp_backlight_control(link, false);
+	if (dc_is_dp_signal(pipe_ctx->stream->signal))
 		pipe_ctx->stream_res.stream_enc->funcs->dp_blank(pipe_ctx->stream_res.stream_enc);
-	}
+
 	link->link_enc->funcs->connect_dig_be_to_fe(
 			link->link_enc,
 			pipe_ctx->stream_res.stream_enc->id,
@@ -1044,15 +984,12 @@ void dce110_unblank_stream(struct pipe_ctx *pipe_ctx,
 		struct dc_link_settings *link_settings)
 {
 	struct encoder_unblank_param params = { { 0 } };
-	struct dc_link *link = pipe_ctx->stream->sink->link;
 
 	/* only 3 items below are used by unblank */
 	params.pixel_clk_khz =
 		pipe_ctx->stream->timing.pix_clk_khz;
 	params.link_settings.link_rate = link_settings->link_rate;
 	pipe_ctx->stream_res.stream_enc->funcs->dp_unblank(pipe_ctx->stream_res.stream_enc, &params);
-	if (link->connector_signal == SIGNAL_TYPE_EDP)
-		hwss_edp_backlight_control(link, true);
 }
 
 
@@ -1403,7 +1340,7 @@ static void power_down_encoders(struct dc *dc)
 		}
 
 		dc->links[i]->link_enc->funcs->disable_output(
-				dc->links[i]->link_enc, signal, dc->links[i]);
+				dc->links[i]->link_enc, signal);
 	}
 }
 
@@ -1464,7 +1401,9 @@ static void disable_vga_and_power_gate_all_controllers(
 		enable_display_pipe_clock_gating(ctx,
 				true);
 
-		dc->hwss.power_down_front_end(dc, i);
+		dc->current_state->res_ctx.pipe_ctx[i].pipe_idx = i;
+		dc->hwss.disable_plane(dc,
+			&dc->current_state->res_ctx.pipe_ctx[i]);
 	}
 }
 
@@ -1750,56 +1689,54 @@ static void apply_min_clocks(
 /*
  *  Check if FBC can be enabled
  */
-static enum dc_status validate_fbc(struct dc *dc,
-		struct dc_state *context)
+static bool should_enable_fbc(struct dc *dc,
+			      struct dc_state *context)
 {
-	struct pipe_ctx *pipe_ctx =
-			      &context->res_ctx.pipe_ctx[0];
+	struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[0];
 
 	ASSERT(dc->fbc_compressor);
 
 	/* FBC memory should be allocated */
 	if (!dc->ctx->fbc_gpu_addr)
-		return DC_ERROR_UNEXPECTED;
+		return false;
 
 	/* Only supports single display */
 	if (context->stream_count != 1)
-		return DC_ERROR_UNEXPECTED;
+		return false;
 
 	/* Only supports eDP */
 	if (pipe_ctx->stream->sink->link->connector_signal != SIGNAL_TYPE_EDP)
-		return DC_ERROR_UNEXPECTED;
+		return false;
 
 	/* PSR should not be enabled */
 	if (pipe_ctx->stream->sink->link->psr_enabled)
-		return DC_ERROR_UNEXPECTED;
+		return false;
+
+	/* Nothing to compress */
+	if (!pipe_ctx->plane_state)
+		return false;
 
 	/* Only for non-linear tiling */
 	if (pipe_ctx->plane_state->tiling_info.gfx8.array_mode == DC_ARRAY_LINEAR_GENERAL)
-		return DC_ERROR_UNEXPECTED;
+		return false;
 
-	return DC_OK;
+	return true;
 }
 
 /*
  *  Enable FBC
  */
-static enum dc_status enable_fbc(struct dc *dc,
-		struct dc_state *context)
+static void enable_fbc(struct dc *dc,
+		       struct dc_state *context)
 {
-	enum dc_status status = validate_fbc(dc, context);
-
-	if (status == DC_OK) {
+	if (should_enable_fbc(dc, context)) {
 		/* Program GRPH COMPRESSED ADDRESS and PITCH */
 		struct compr_addr_and_pitch_params params = {0, 0, 0};
 		struct compressor *compr = dc->fbc_compressor;
-		struct pipe_ctx *pipe_ctx =
-				      &context->res_ctx.pipe_ctx[0];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[0];
 
-		params.source_view_width =
-				pipe_ctx->stream->timing.h_addressable;
-		params.source_view_height =
-				pipe_ctx->stream->timing.v_addressable;
+		params.source_view_width = pipe_ctx->stream->timing.h_addressable;
+		params.source_view_height = pipe_ctx->stream->timing.v_addressable;
 
 		compr->compr_surface_address.quad_part = dc->ctx->fbc_gpu_addr;
 
@@ -1808,7 +1745,6 @@ static enum dc_status enable_fbc(struct dc *dc,
 
 		compr->funcs->enable_fbc(compr, &params);
 	}
-	return status;
 }
 #endif
 
@@ -1868,8 +1804,10 @@ static void dce110_reset_hw_ctx_wrap(
 				pipe_need_reprogram(pipe_ctx_old, pipe_ctx)) {
 			struct clock_source *old_clk = pipe_ctx_old->clock_source;
 
-			/* disable already, no need to disable again */
-			if (pipe_ctx->stream && !pipe_ctx->stream->dpms_off)
+			/* Disable if new stream is null. O/w, if stream is
+			 * disabled already, no need to disable again.
+			 */
+			if (!pipe_ctx->stream || !pipe_ctx->stream->dpms_off)
 				core_link_disable_stream(pipe_ctx_old, FREE_ACQUIRED_RESOURCE);
 
 			pipe_ctx_old->stream_res.tg->funcs->set_blank(pipe_ctx_old->stream_res.tg, true);
@@ -1884,7 +1822,7 @@ static void dce110_reset_hw_ctx_wrap(
 			if (old_clk)
 				old_clk->funcs->cs_power_down(old_clk);
 
-			dc->hwss.power_down_front_end(dc, pipe_ctx_old->pipe_idx);
+			dc->hwss.disable_plane(dc, pipe_ctx_old);
 
 			pipe_ctx_old->stream = NULL;
 		}
@@ -2072,8 +2010,7 @@ enum dc_status dce110_apply_ctx_to_hw(
 		if (pipe_ctx->stream == pipe_ctx_old->stream)
 			continue;
 
-		if (pipe_ctx->stream && pipe_ctx_old->stream
-				&& !pipe_need_reprogram(pipe_ctx_old, pipe_ctx))
+		if (pipe_ctx_old->stream && !pipe_need_reprogram(pipe_ctx_old, pipe_ctx))
 			continue;
 
 		if (pipe_ctx->top_pipe)
@@ -2109,9 +2046,6 @@ enum dc_status dce110_apply_ctx_to_hw(
 				context,
 				dc);
 
-		if (dc->hwss.power_on_front_end)
-			dc->hwss.power_on_front_end(dc, pipe_ctx, context);
-
 		if (DC_OK != status)
 			return status;
 	}
@@ -2141,16 +2075,8 @@ static void set_default_colors(struct pipe_ctx *pipe_ctx)
 	struct default_adjustment default_adjust = { 0 };
 
 	default_adjust.force_hw_default = false;
-	if (pipe_ctx->plane_state == NULL)
-		default_adjust.in_color_space = COLOR_SPACE_SRGB;
-	else
-		default_adjust.in_color_space =
-				pipe_ctx->plane_state->color_space;
-	if (pipe_ctx->stream == NULL)
-		default_adjust.out_color_space = COLOR_SPACE_SRGB;
-	else
-		default_adjust.out_color_space =
-				pipe_ctx->stream->output_color_space;
+	default_adjust.in_color_space = pipe_ctx->plane_state->color_space;
+	default_adjust.out_color_space = pipe_ctx->stream->output_color_space;
 	default_adjust.csc_adjust_type = GRAPHICS_CSC_ADJUST_TYPE_SW;
 	default_adjust.surface_pixel_format = pipe_ctx->plane_res.scl_data.format;
 
@@ -2275,8 +2201,7 @@ static void set_plane_config(
 	dce_enable_fe_clock(dc->hwseq, pipe_ctx->pipe_idx, true);
 
 	set_default_colors(pipe_ctx);
-	if (pipe_ctx->stream->csc_color_matrix.enable_adjustment
-			== true) {
+	if (pipe_ctx->stream->csc_color_matrix.enable_adjustment == true) {
 		tbl_entry.color_space =
 			pipe_ctx->stream->output_color_space;
 
@@ -2454,20 +2379,16 @@ static void dce110_enable_timing_synchronization(
 
 	for (i = 1 /* skip the master */; i < group_size; i++)
 		grouped_pipes[i]->stream_res.tg->funcs->enable_reset_trigger(
-					grouped_pipes[i]->stream_res.tg, gsl_params.gsl_group);
-
-
+				grouped_pipes[i]->stream_res.tg,
+				gsl_params.gsl_group);
 
 	for (i = 1 /* skip the master */; i < group_size; i++) {
 		DC_SYNC_INFO("GSL: waiting for reset to occur.\n");
 		wait_for_reset_trigger_to_occur(dc_ctx, grouped_pipes[i]->stream_res.tg);
-		/* Regardless of success of the wait above, remove the reset or
-		 * the driver will start timing out on Display requests. */
-		DC_SYNC_INFO("GSL: disabling trigger-reset.\n");
-		grouped_pipes[i]->stream_res.tg->funcs->disable_reset_trigger(grouped_pipes[i]->stream_res.tg);
+		grouped_pipes[i]->stream_res.tg->funcs->disable_reset_trigger(
+				grouped_pipes[i]->stream_res.tg);
 	}
 
-
 	/* GSL Vblank synchronization is a one time sync mechanism, assumption
 	 * is that the sync'ed displays will not drift out of sync over time*/
 	DC_SYNC_INFO("GSL: Restoring register states.\n");
@@ -2477,6 +2398,39 @@ static void dce110_enable_timing_synchronization(
 	DC_SYNC_INFO("GSL: Set-up complete.\n");
 }
 
+static void dce110_enable_per_frame_crtc_position_reset(
+		struct dc *dc,
+		int group_size,
+		struct pipe_ctx *grouped_pipes[])
+{
+	struct dc_context *dc_ctx = dc->ctx;
+	struct dcp_gsl_params gsl_params = { 0 };
+	int i;
+
+	gsl_params.gsl_group = 0;
+	gsl_params.gsl_master = grouped_pipes[0]->stream->triggered_crtc_reset.event_source->status.primary_otg_inst;
+
+	for (i = 0; i < group_size; i++)
+		grouped_pipes[i]->stream_res.tg->funcs->setup_global_swap_lock(
+					grouped_pipes[i]->stream_res.tg, &gsl_params);
+
+	DC_SYNC_INFO("GSL: enabling trigger-reset\n");
+
+	for (i = 1; i < group_size; i++)
+		grouped_pipes[i]->stream_res.tg->funcs->enable_crtc_reset(
+				grouped_pipes[i]->stream_res.tg,
+				gsl_params.gsl_master,
+				&grouped_pipes[i]->stream->triggered_crtc_reset);
+
+	DC_SYNC_INFO("GSL: waiting for reset to occur.\n");
+	for (i = 1; i < group_size; i++)
+		wait_for_reset_trigger_to_occur(dc_ctx, grouped_pipes[i]->stream_res.tg);
+
+	for (i = 0; i < group_size; i++)
+		grouped_pipes[i]->stream_res.tg->funcs->tear_down_global_swap_lock(grouped_pipes[i]->stream_res.tg);
+
+}
+
 static void init_hw(struct dc *dc)
 {
 	int i;
@@ -2509,6 +2463,10 @@ static void init_hw(struct dc *dc)
 		 * required signal (which may be different from the
 		 * default signal on connector). */
 		struct dc_link *link = dc->links[i];
+
+		if (link->link_enc->connector.id == CONNECTOR_ID_EDP)
+			dc->hwss.edp_power_control(link, true);
+
 		link->link_enc->funcs->hw_init(link->link_enc);
 	}
 
@@ -2563,6 +2521,10 @@ void dce110_fill_display_configs(
 
 		ASSERT(pipe_ctx != NULL);
 
+		/* only notify active stream */
+		if (stream->dpms_off)
+			continue;
+
 		num_cfgs++;
 		cfg->signal = pipe_ctx->stream->signal;
 		cfg->pipe_idx = pipe_ctx->pipe_idx;
@@ -2718,8 +2680,7 @@ static void dce110_program_front_end_for_pipe(
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct xfm_grph_csc_adjustment adjust;
 	struct out_csc_color_matrix tbl_entry;
-	struct pipe_ctx *cur_pipe_ctx =
-					&dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx];
+	struct pipe_ctx *cur_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx];
 	unsigned int i;
 
 	memset(&tbl_entry, 0, sizeof(tbl_entry));
@@ -2812,10 +2773,8 @@ static void dce110_program_front_end_for_pipe(
 
 	/* Moved programming gamma from dc to hwss */
 	if (cur_pipe_ctx->plane_state != pipe_ctx->plane_state) {
-		dc->hwss.set_input_transfer_func(
-				pipe_ctx, pipe_ctx->plane_state);
-		dc->hwss.set_output_transfer_func(
-				pipe_ctx, pipe_ctx->stream);
+		dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
+		dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
 	}
 
 	dm_logger_write(dc->ctx->logger, LOG_SURFACE,
@@ -2862,16 +2821,19 @@ static void dce110_apply_ctx_for_surface(
 		int num_planes,
 		struct dc_state *context)
 {
-	int i, be_idx;
+	int i;
 
 	if (num_planes == 0)
 		return;
 
-	be_idx = -1;
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (stream == context->res_ctx.pipe_ctx[i].stream) {
-			be_idx = context->res_ctx.pipe_ctx[i].stream_res.tg->inst;
-			break;
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *old_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
+
+		if (stream == pipe_ctx->stream) {
+			if (!pipe_ctx->top_pipe &&
+				(pipe_ctx->plane_state || old_pipe_ctx->plane_state))
+				dc->hwss.pipe_control_lock(dc, pipe_ctx, true);
 		}
 	}
 
@@ -2882,22 +2844,36 @@ static void dce110_apply_ctx_for_surface(
 			continue;
 
 		/* Need to allocate mem before program front end for Fiji */
-		if (pipe_ctx->plane_res.mi != NULL)
-			pipe_ctx->plane_res.mi->funcs->allocate_mem_input(
-					pipe_ctx->plane_res.mi,
-					pipe_ctx->stream->timing.h_total,
-					pipe_ctx->stream->timing.v_total,
-					pipe_ctx->stream->timing.pix_clk_khz,
-					context->stream_count);
+		pipe_ctx->plane_res.mi->funcs->allocate_mem_input(
+				pipe_ctx->plane_res.mi,
+				pipe_ctx->stream->timing.h_total,
+				pipe_ctx->stream->timing.v_total,
+				pipe_ctx->stream->timing.pix_clk_khz,
+				context->stream_count);
 
 		dce110_program_front_end_for_pipe(dc, pipe_ctx);
+
+		dc->hwss.update_plane_addr(dc, pipe_ctx);
+
 		program_surface_visibility(dc, pipe_ctx);
 
 	}
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *old_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
+
+		if ((stream == pipe_ctx->stream) &&
+			(!pipe_ctx->top_pipe) &&
+			(pipe_ctx->plane_state || old_pipe_ctx->plane_state))
+			dc->hwss.pipe_control_lock(dc, pipe_ctx, false);
+	}
 }
 
-static void dce110_power_down_fe(struct dc *dc, int fe_idx)
+static void dce110_power_down_fe(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	int fe_idx = pipe_ctx->pipe_idx;
+
 	/* Do not power down fe when stream is active on dce*/
 	if (dc->current_state->res_ctx.pipe_ctx[fe_idx].stream)
 		return;
@@ -2957,13 +2933,14 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.power_down = dce110_power_down,
 	.enable_accelerated_mode = dce110_enable_accelerated_mode,
 	.enable_timing_synchronization = dce110_enable_timing_synchronization,
+	.enable_per_frame_crtc_position_reset = dce110_enable_per_frame_crtc_position_reset,
 	.update_info_frame = dce110_update_info_frame,
 	.enable_stream = dce110_enable_stream,
 	.disable_stream = dce110_disable_stream,
 	.unblank_stream = dce110_unblank_stream,
 	.enable_display_pipe_clock_gating = enable_display_pipe_clock_gating,
 	.enable_display_power_gating = dce110_enable_display_power_gating,
-	.power_down_front_end = dce110_power_down_fe,
+	.disable_plane = dce110_power_down_fe,
 	.pipe_control_lock = dce_pipe_control_lock,
 	.set_bandwidth = dce110_set_bandwidth,
 	.set_drr = set_drr,
@@ -2976,8 +2953,10 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.wait_for_mpcc_disconnect = dce110_wait_for_mpcc_disconnect,
 	.ready_shared_resources = ready_shared_resources,
 	.optimize_shared_resources = optimize_shared_resources,
+	.pplib_apply_display_requirements = pplib_apply_display_requirements,
 	.edp_backlight_control = hwss_edp_backlight_control,
 	.edp_power_control = hwss_edp_power_control,
+	.edp_wait_for_hpd_ready = hwss_edp_wait_for_hpd_ready,
 };
 
 void dce110_hw_sequencer_construct(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
index 4d72bb99be93..fc637647f643 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
@@ -70,12 +70,16 @@ uint32_t dce110_get_min_vblank_time_us(const struct dc_state *context);
 void dp_receiver_power_ctrl(struct dc_link *link, bool on);
 
 void hwss_edp_power_control(
-	struct link_encoder *enc,
-	bool power_up);
+		struct dc_link *link,
+		bool power_up);
 
 void hwss_edp_backlight_control(
 	struct dc_link *link,
 	bool enable);
 
+void hwss_edp_wait_for_hpd_ready(
+		struct dc_link *link,
+		bool power_up);
+
 #endif /* __DC_HWSS_DCE110_H__ */
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
index a06c6024deb4..7bab8c6d2a73 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
@@ -237,26 +237,14 @@ static void program_size_and_rotation(
 	if (rotation == ROTATION_ANGLE_90 ||
 		rotation == ROTATION_ANGLE_270) {
 
-		uint32_t swap;
-		swap = local_size.video.luma_size.x;
-		local_size.video.luma_size.x =
-			local_size.video.luma_size.y;
-		local_size.video.luma_size.y  = swap;
-
-		swap = local_size.video.luma_size.width;
-		local_size.video.luma_size.width =
-			local_size.video.luma_size.height;
-		local_size.video.luma_size.height = swap;
-
-		swap = local_size.video.chroma_size.x;
-		local_size.video.chroma_size.x =
-			local_size.video.chroma_size.y;
-		local_size.video.chroma_size.y  = swap;
-
-		swap = local_size.video.chroma_size.width;
-		local_size.video.chroma_size.width =
-			local_size.video.chroma_size.height;
-		local_size.video.chroma_size.height = swap;
+		swap(local_size.video.luma_size.x,
+		     local_size.video.luma_size.y);
+		swap(local_size.video.luma_size.width,
+		     local_size.video.luma_size.height);
+		swap(local_size.video.chroma_size.x,
+		     local_size.video.chroma_size.y);
+		swap(local_size.video.chroma_size.width,
+		     local_size.video.chroma_size.height);
 	}
 
 	value = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_opp_regamma_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_opp_regamma_v.c
index e98ed3058ea2..9b65b77e8823 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_opp_regamma_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_opp_regamma_v.c
@@ -175,7 +175,7 @@ static void regamma_config_regions_and_segments(
 		value = 0;
 		set_reg_field_value(
 			value,
-			params->arr_points[2].custom_float_slope,
+			params->arr_points[1].custom_float_slope,
 			GAMMA_CORR_CNTLA_END_CNTL2,
 			GAMMA_CORR_CNTLA_EXP_REGION_END_BASE);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index db96d2b47ff1..7c4779578fb7 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -1,5 +1,5 @@
 /*
-* Copyright 2012-15 Advanced Micro Devices, Inc.
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -1037,11 +1037,13 @@ static bool underlay_create(struct dc_context *ctx, struct resource_pool *pool)
 	struct dce110_opp *dce110_oppv = kzalloc(sizeof(*dce110_oppv),
 						 GFP_KERNEL);
 
-	if ((dce110_tgv == NULL) ||
-		(dce110_xfmv == NULL) ||
-		(dce110_miv == NULL) ||
-		(dce110_oppv == NULL))
-			return false;
+	if (!dce110_tgv || !dce110_xfmv || !dce110_miv || !dce110_oppv) {
+		kfree(dce110_tgv);
+		kfree(dce110_xfmv);
+		kfree(dce110_miv);
+		kfree(dce110_oppv);
+		return false;
+	}
 
 	dce110_opp_v_construct(dce110_oppv, ctx);
 
@@ -1154,6 +1156,7 @@ static bool construct(
 	dc->caps.max_downscale_ratio = 150;
 	dc->caps.i2c_speed_in_khz = 100;
 	dc->caps.max_cursor_size = 128;
+	dc->caps.is_apu = true;
 
 	/*************************************************
 	 *  Create resources                             *
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
index 67ac737eaa7e..25ca72139e5f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
@@ -1112,10 +1112,7 @@ bool dce110_timing_generator_validate_timing(
 	enum signal_type signal)
 {
 	uint32_t h_blank;
-	uint32_t h_back_porch;
-	uint32_t hsync_offset = timing->h_border_right +
-			timing->h_front_porch;
-	uint32_t h_sync_start = timing->h_addressable + hsync_offset;
+	uint32_t h_back_porch, hsync_offset, h_sync_start;
 
 	struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg);
 
@@ -1124,6 +1121,9 @@ bool dce110_timing_generator_validate_timing(
 	if (!timing)
 		return false;
 
+	hsync_offset = timing->h_border_right + timing->h_front_porch;
+	h_sync_start = timing->h_addressable + hsync_offset;
+
 	/* Currently we don't support 3D, so block all 3D timings */
 	if (timing->timing_3d_format != TIMING_3D_FORMAT_NONE)
 		return false;
@@ -1224,26 +1224,46 @@ void dce110_timing_generator_setup_global_swap_lock(
 
 	/* This pipe will belong to GSL Group zero. */
 	set_reg_field_value(value,
-			1,
-			DCP_GSL_CONTROL,
-			DCP_GSL0_EN);
+			    1,
+			    DCP_GSL_CONTROL,
+			    DCP_GSL0_EN);
 
 	set_reg_field_value(value,
-			gsl_params->gsl_master == tg->inst,
-			DCP_GSL_CONTROL,
-			DCP_GSL_MASTER_EN);
+			    gsl_params->gsl_master == tg->inst,
+			    DCP_GSL_CONTROL,
+			    DCP_GSL_MASTER_EN);
 
 	set_reg_field_value(value,
-			HFLIP_READY_DELAY,
-			DCP_GSL_CONTROL,
-			DCP_GSL_HSYNC_FLIP_FORCE_DELAY);
+			    HFLIP_READY_DELAY,
+			    DCP_GSL_CONTROL,
+			    DCP_GSL_HSYNC_FLIP_FORCE_DELAY);
 
 	/* Keep signal low (pending high) during 6 lines.
 	 * Also defines minimum interval before re-checking signal. */
 	set_reg_field_value(value,
-			HFLIP_CHECK_DELAY,
-			DCP_GSL_CONTROL,
-			DCP_GSL_HSYNC_FLIP_CHECK_DELAY);
+			    HFLIP_CHECK_DELAY,
+			    DCP_GSL_CONTROL,
+			    DCP_GSL_HSYNC_FLIP_CHECK_DELAY);
+
+	dm_write_reg(tg->ctx, CRTC_REG(mmDCP_GSL_CONTROL), value);
+	value = 0;
+
+	set_reg_field_value(value,
+			    gsl_params->gsl_master,
+			    DCIO_GSL0_CNTL,
+			    DCIO_GSL0_VSYNC_SEL);
+
+	set_reg_field_value(value,
+			    0,
+			    DCIO_GSL0_CNTL,
+			    DCIO_GSL0_TIMING_SYNC_SEL);
+
+	set_reg_field_value(value,
+			    0,
+			    DCIO_GSL0_CNTL,
+			    DCIO_GSL0_GLOBAL_UNLOCK_SEL);
+
+	dm_write_reg(tg->ctx, CRTC_REG(mmDCIO_GSL0_CNTL), value);
 
 
 	{
@@ -1253,38 +1273,38 @@ void dce110_timing_generator_setup_global_swap_lock(
 				CRTC_REG(mmCRTC_V_TOTAL));
 
 		set_reg_field_value(value,
-				0,/* DCP_GSL_PURPOSE_SURFACE_FLIP */
-				DCP_GSL_CONTROL,
-				DCP_GSL_SYNC_SOURCE);
+				    0,/* DCP_GSL_PURPOSE_SURFACE_FLIP */
+				    DCP_GSL_CONTROL,
+				    DCP_GSL_SYNC_SOURCE);
 
 		/* Checkpoint relative to end of frame */
 		check_point = get_reg_field_value(value_crtc_vtotal,
-				CRTC_V_TOTAL,
-				CRTC_V_TOTAL);
+						  CRTC_V_TOTAL,
+						  CRTC_V_TOTAL);
 
 		dm_write_reg(tg->ctx, CRTC_REG(mmCRTC_GSL_WINDOW), 0);
 	}
 
 	set_reg_field_value(value,
-			1,
-			DCP_GSL_CONTROL,
-			DCP_GSL_DELAY_SURFACE_UPDATE_PENDING);
+			    1,
+			    DCP_GSL_CONTROL,
+			    DCP_GSL_DELAY_SURFACE_UPDATE_PENDING);
 
 	dm_write_reg(tg->ctx, address, value);
 
 	/********************************************************************/
 	address = CRTC_REG(mmCRTC_GSL_CONTROL);
 
-	value = 0;
+	value = dm_read_reg(tg->ctx, address);
 	set_reg_field_value(value,
-			check_point - FLIP_READY_BACK_LOOKUP,
-			CRTC_GSL_CONTROL,
-			CRTC_GSL_CHECK_LINE_NUM);
+			    check_point - FLIP_READY_BACK_LOOKUP,
+			    CRTC_GSL_CONTROL,
+			    CRTC_GSL_CHECK_LINE_NUM);
 
 	set_reg_field_value(value,
-			VFLIP_READY_DELAY,
-			CRTC_GSL_CONTROL,
-			CRTC_GSL_FORCE_DELAY);
+			    VFLIP_READY_DELAY,
+			    CRTC_GSL_CONTROL,
+			    CRTC_GSL_FORCE_DELAY);
 
 	dm_write_reg(tg->ctx, address, value);
 }
@@ -1555,6 +1575,138 @@ void dce110_timing_generator_enable_reset_trigger(
 	dm_write_reg(tg->ctx, CRTC_REG(mmCRTC_FORCE_COUNT_NOW_CNTL), value);
 }
 
+void dce110_timing_generator_enable_crtc_reset(
+		struct timing_generator *tg,
+		int source_tg_inst,
+		struct crtc_trigger_info *crtc_tp)
+{
+	uint32_t value = 0;
+	uint32_t rising_edge = 0;
+	uint32_t falling_edge = 0;
+	struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg);
+
+	/* Setup trigger edge */
+	switch (crtc_tp->event) {
+	case CRTC_EVENT_VSYNC_RISING:
+			rising_edge = 1;
+			break;
+
+	case CRTC_EVENT_VSYNC_FALLING:
+		falling_edge = 1;
+		break;
+	}
+
+	value = dm_read_reg(tg->ctx, CRTC_REG(mmCRTC_TRIGB_CNTL));
+
+	set_reg_field_value(value,
+			    source_tg_inst,
+			    CRTC_TRIGB_CNTL,
+			    CRTC_TRIGB_SOURCE_SELECT);
+
+	set_reg_field_value(value,
+			    TRIGGER_POLARITY_SELECT_LOGIC_ZERO,
+			    CRTC_TRIGB_CNTL,
+			    CRTC_TRIGB_POLARITY_SELECT);
+
+	set_reg_field_value(value,
+			    rising_edge,
+			    CRTC_TRIGB_CNTL,
+			    CRTC_TRIGB_RISING_EDGE_DETECT_CNTL);
+
+	set_reg_field_value(value,
+			    falling_edge,
+			    CRTC_TRIGB_CNTL,
+			    CRTC_TRIGB_FALLING_EDGE_DETECT_CNTL);
+
+	set_reg_field_value(value,
+			    1, /* clear trigger status */
+			    CRTC_TRIGB_CNTL,
+			    CRTC_TRIGB_CLEAR);
+
+	dm_write_reg(tg->ctx, CRTC_REG(mmCRTC_TRIGB_CNTL), value);
+
+	/**************************************************************/
+
+	switch (crtc_tp->delay) {
+	case TRIGGER_DELAY_NEXT_LINE:
+		value = dm_read_reg(tg->ctx, CRTC_REG(mmCRTC_FORCE_COUNT_NOW_CNTL));
+
+		set_reg_field_value(value,
+				    0, /* force H count to H_TOTAL and V count to V_TOTAL */
+				    CRTC_FORCE_COUNT_NOW_CNTL,
+				    CRTC_FORCE_COUNT_NOW_MODE);
+
+		set_reg_field_value(value,
+				    0, /* TriggerB - we never use TriggerA */
+				    CRTC_FORCE_COUNT_NOW_CNTL,
+				    CRTC_FORCE_COUNT_NOW_TRIG_SEL);
+
+		set_reg_field_value(value,
+				    1, /* clear trigger status */
+				    CRTC_FORCE_COUNT_NOW_CNTL,
+				    CRTC_FORCE_COUNT_NOW_CLEAR);
+
+		dm_write_reg(tg->ctx, CRTC_REG(mmCRTC_FORCE_COUNT_NOW_CNTL), value);
+
+		value = dm_read_reg(tg->ctx, CRTC_REG(mmCRTC_VERT_SYNC_CONTROL));
+
+		set_reg_field_value(value,
+				    1,
+				    CRTC_VERT_SYNC_CONTROL,
+				    CRTC_FORCE_VSYNC_NEXT_LINE_CLEAR);
+
+		set_reg_field_value(value,
+				    2,
+				    CRTC_VERT_SYNC_CONTROL,
+				    CRTC_AUTO_FORCE_VSYNC_MODE);
+
+		break;
+
+	case TRIGGER_DELAY_NEXT_PIXEL:
+		value = dm_read_reg(tg->ctx, CRTC_REG(mmCRTC_VERT_SYNC_CONTROL));
+
+		set_reg_field_value(value,
+				    1,
+				    CRTC_VERT_SYNC_CONTROL,
+				    CRTC_FORCE_VSYNC_NEXT_LINE_CLEAR);
+
+		set_reg_field_value(value,
+				    0,
+				    CRTC_VERT_SYNC_CONTROL,
+				    CRTC_AUTO_FORCE_VSYNC_MODE);
+
+		dm_write_reg(tg->ctx, CRTC_REG(mmCRTC_VERT_SYNC_CONTROL), value);
+
+		value = dm_read_reg(tg->ctx, CRTC_REG(mmCRTC_FORCE_COUNT_NOW_CNTL));
+
+		set_reg_field_value(value,
+				    2, /* force H count to H_TOTAL and V count to V_TOTAL */
+				    CRTC_FORCE_COUNT_NOW_CNTL,
+				    CRTC_FORCE_COUNT_NOW_MODE);
+
+		set_reg_field_value(value,
+				    1, /* TriggerB - we never use TriggerA */
+				    CRTC_FORCE_COUNT_NOW_CNTL,
+				    CRTC_FORCE_COUNT_NOW_TRIG_SEL);
+
+		set_reg_field_value(value,
+				    1, /* clear trigger status */
+				    CRTC_FORCE_COUNT_NOW_CNTL,
+				    CRTC_FORCE_COUNT_NOW_CLEAR);
+
+		dm_write_reg(tg->ctx, CRTC_REG(mmCRTC_FORCE_COUNT_NOW_CNTL), value);
+		break;
+	}
+
+	value = dm_read_reg(tg->ctx, CRTC_REG(mmCRTC_MASTER_UPDATE_MODE));
+
+	set_reg_field_value(value,
+			    2,
+			    CRTC_MASTER_UPDATE_MODE,
+			    MASTER_UPDATE_MODE);
+
+	dm_write_reg(tg->ctx, CRTC_REG(mmCRTC_MASTER_UPDATE_MODE), value);
+}
 void dce110_timing_generator_disable_reset_trigger(
 	struct timing_generator *tg)
 {
@@ -1564,34 +1716,48 @@ void dce110_timing_generator_disable_reset_trigger(
 	value = dm_read_reg(tg->ctx, CRTC_REG(mmCRTC_FORCE_COUNT_NOW_CNTL));
 
 	set_reg_field_value(value,
-			0, /* force counter now mode is disabled */
-			CRTC_FORCE_COUNT_NOW_CNTL,
-			CRTC_FORCE_COUNT_NOW_MODE);
+			    0, /* force counter now mode is disabled */
+			    CRTC_FORCE_COUNT_NOW_CNTL,
+			    CRTC_FORCE_COUNT_NOW_MODE);
 
 	set_reg_field_value(value,
-			1, /* clear trigger status */
-			CRTC_FORCE_COUNT_NOW_CNTL,
-			CRTC_FORCE_COUNT_NOW_CLEAR);
+			    1, /* clear trigger status */
+			    CRTC_FORCE_COUNT_NOW_CNTL,
+			    CRTC_FORCE_COUNT_NOW_CLEAR);
 
 	dm_write_reg(tg->ctx, CRTC_REG(mmCRTC_FORCE_COUNT_NOW_CNTL), value);
 
+	value = dm_read_reg(tg->ctx, CRTC_REG(mmCRTC_VERT_SYNC_CONTROL));
+
+	set_reg_field_value(value,
+			    1,
+			    CRTC_VERT_SYNC_CONTROL,
+			    CRTC_FORCE_VSYNC_NEXT_LINE_CLEAR);
+
+	set_reg_field_value(value,
+			    0,
+			    CRTC_VERT_SYNC_CONTROL,
+			    CRTC_AUTO_FORCE_VSYNC_MODE);
+
+	dm_write_reg(tg->ctx, CRTC_REG(mmCRTC_VERT_SYNC_CONTROL), value);
+
 	/********************************************************************/
 	value = dm_read_reg(tg->ctx, CRTC_REG(mmCRTC_TRIGB_CNTL));
 
 	set_reg_field_value(value,
-			TRIGGER_SOURCE_SELECT_LOGIC_ZERO,
-			CRTC_TRIGB_CNTL,
-			CRTC_TRIGB_SOURCE_SELECT);
+			    TRIGGER_SOURCE_SELECT_LOGIC_ZERO,
+			    CRTC_TRIGB_CNTL,
+			    CRTC_TRIGB_SOURCE_SELECT);
 
 	set_reg_field_value(value,
-			TRIGGER_POLARITY_SELECT_LOGIC_ZERO,
-			CRTC_TRIGB_CNTL,
-			CRTC_TRIGB_POLARITY_SELECT);
+			    TRIGGER_POLARITY_SELECT_LOGIC_ZERO,
+			    CRTC_TRIGB_CNTL,
+			    CRTC_TRIGB_POLARITY_SELECT);
 
 	set_reg_field_value(value,
-			1, /* clear trigger status */
-			CRTC_TRIGB_CNTL,
-			CRTC_TRIGB_CLEAR);
+			    1, /* clear trigger status */
+			    CRTC_TRIGB_CNTL,
+			    CRTC_TRIGB_CLEAR);
 
 	dm_write_reg(tg->ctx, CRTC_REG(mmCRTC_TRIGB_CNTL), value);
 }
@@ -1611,10 +1777,16 @@ bool dce110_timing_generator_did_triggered_reset_occur(
 	struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg);
 	uint32_t value = dm_read_reg(tg->ctx,
 			CRTC_REG(mmCRTC_FORCE_COUNT_NOW_CNTL));
-
-	return get_reg_field_value(value,
-			CRTC_FORCE_COUNT_NOW_CNTL,
-			CRTC_FORCE_COUNT_NOW_OCCURRED) != 0;
+	uint32_t value1 = dm_read_reg(tg->ctx,
+			CRTC_REG(mmCRTC_VERT_SYNC_CONTROL));
+	bool force = get_reg_field_value(value,
+					 CRTC_FORCE_COUNT_NOW_CNTL,
+					 CRTC_FORCE_COUNT_NOW_OCCURRED) != 0;
+	bool vert_sync = get_reg_field_value(value1,
+					     CRTC_VERT_SYNC_CONTROL,
+					     CRTC_FORCE_VSYNC_NEXT_LINE_OCCURRED) != 0;
+
+	return (force || vert_sync);
 }
 
 /**
@@ -1928,6 +2100,7 @@ static const struct timing_generator_funcs dce110_tg_funcs = {
 		.setup_global_swap_lock =
 				dce110_timing_generator_setup_global_swap_lock,
 		.enable_reset_trigger = dce110_timing_generator_enable_reset_trigger,
+		.enable_crtc_reset = dce110_timing_generator_enable_crtc_reset,
 		.disable_reset_trigger = dce110_timing_generator_disable_reset_trigger,
 		.tear_down_global_swap_lock =
 				dce110_timing_generator_tear_down_global_swap_lock,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h
index 82737dea6984..232747c7c60b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h
@@ -174,6 +174,12 @@ void dce110_timing_generator_setup_global_swap_lock(
 void dce110_timing_generator_tear_down_global_swap_lock(
 	struct timing_generator *tg);
 
+/* Reset crtc position on master VSync */
+void dce110_timing_generator_enable_crtc_reset(
+	struct timing_generator *tg,
+	int source,
+	struct crtc_trigger_info *crtc_tp);
+
 /* Reset slave controllers on master VSync */
 void dce110_timing_generator_enable_reset_trigger(
 	struct timing_generator *tg,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator_v.c
index 07d9303d5477..59b4cd329715 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator_v.c
@@ -1,3 +1,26 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
 #include "dm_services.h"
 
 /* include DCE11 register header files */
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/Makefile b/drivers/gpu/drm/amd/display/dc/dce112/Makefile
index 265ac4310d85..8e090446d511 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce112/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'controller' sub-component of DAL.
 # It provides the control and status of HW CRTC block.
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/Makefile b/drivers/gpu/drm/amd/display/dc/dce120/Makefile
index 1779b963525c..37db1f8d45ea 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce120/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'controller' sub-component of DAL.
 # It provides the control and status of HW CRTC block.
 
@@ -8,4 +29,4 @@ dce120_hw_sequencer.o
 
 AMD_DAL_DCE120 = $(addprefix $(AMDDALPATH)/dc/dce120/,$(DCE120))
 
-AMD_DISPLAY_FILES += $(AMD_DAL_DCE120)
-\ No newline at end of file
+AMD_DISPLAY_FILES += $(AMD_DAL_DCE120)
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
index 1a0b54d6034e..75d029742f96 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
@@ -31,9 +31,9 @@
 
 #include "dce110/dce110_hw_sequencer.h"
 
-#include "vega10/DC/dce_12_0_offset.h"
-#include "vega10/DC/dce_12_0_sh_mask.h"
-#include "vega10/soc15ip.h"
+#include "dce/dce_12_0_offset.h"
+#include "dce/dce_12_0_sh_mask.h"
+#include "soc15ip.h"
 #include "reg_helper.h"
 
 #define CTX \
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 5c48c22d9d98..57cd67359567 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -54,10 +54,10 @@
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
 
-#include "vega10/DC/dce_12_0_offset.h"
-#include "vega10/DC/dce_12_0_sh_mask.h"
-#include "vega10/soc15ip.h"
-#include "vega10/NBIO/nbio_6_1_offset.h"
+#include "dce/dce_12_0_offset.h"
+#include "dce/dce_12_0_sh_mask.h"
+#include "soc15ip.h"
+#include "nbio/nbio_6_1_offset.h"
 #include "reg_helper.h"
 
 #include "dce100/dce100_resource.h"
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
index 2502182d5e82..0aa60e5727e0 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
@@ -25,9 +25,9 @@
 
 #include "dm_services.h"
 
-#include "vega10/DC/dce_12_0_offset.h"
-#include "vega10/DC/dce_12_0_sh_mask.h"
-#include "vega10/soc15ip.h"
+#include "dce/dce_12_0_offset.h"
+#include "dce/dce_12_0_sh_mask.h"
+#include "soc15ip.h"
 
 #include "dc_types.h"
 #include "dc_bios_types.h"
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/Makefile b/drivers/gpu/drm/amd/display/dc/dce80/Makefile
index c1105895e5fa..bc388aa4b2f5 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce80/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'controller' sub-component of DAL.
 # It provides the control and status of HW CRTC block.
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 9c18efd3446f..8f2bd56f3461 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -957,6 +957,7 @@ static bool dce81_construct(
 	dc->caps.max_downscale_ratio = 200;
 	dc->caps.i2c_speed_in_khz = 40;
 	dc->caps.max_cursor_size = 128;
+	dc->caps.is_apu = true;
 
 	/*************************************************
 	 *  Create resources                             *
@@ -1121,6 +1122,7 @@ static bool dce83_construct(
 	dc->caps.max_downscale_ratio = 200;
 	dc->caps.i2c_speed_in_khz = 40;
 	dc->caps.max_cursor_size = 128;
+	dc->caps.is_apu = true;
 
 	/*************************************************
 	 *  Create resources                             *
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
index ebeb88283a14..5469bdfe19f3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
@@ -1,10 +1,32 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for DCN.
 
 DCN10 = dcn10_resource.o dcn10_ipp.o dcn10_hw_sequencer.o \
-		dcn10_dpp.o dcn10_opp.o dcn10_timing_generator.o \
+		dcn10_dpp.o dcn10_opp.o dcn10_optc.o \
 		dcn10_hubp.o dcn10_mpc.o \
-		dcn10_dpp_dscl.o dcn10_dpp_cm.o dcn10_cm_common.o
+		dcn10_dpp_dscl.o dcn10_dpp_cm.o dcn10_cm_common.o \
+		dcn10_hubbub.o
 
 AMD_DAL_DCN10 = $(addprefix $(AMDDALPATH)/dc/dcn10/,$(DCN10))
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
index 7f579cb19f4b..53ba3600ee6a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
@@ -22,11 +22,12 @@
  * Authors: AMD
  *
  */
-
+#include "dc.h"
 #include "reg_helper.h"
 #include "dcn10_dpp.h"
 
 #include "dcn10_cm_common.h"
+#include "custom_float.h"
 
 #define REG(reg) reg
 
@@ -121,3 +122,294 @@ void cm_helper_program_xfer_func(
 	}
 
 }
+
+
+
+bool cm_helper_convert_to_custom_float(
+		struct pwl_result_data *rgb_resulted,
+		struct curve_points *arr_points,
+		uint32_t hw_points_num,
+		bool fixpoint)
+{
+	struct custom_float_format fmt;
+
+	struct pwl_result_data *rgb = rgb_resulted;
+
+	uint32_t i = 0;
+
+	fmt.exponenta_bits = 6;
+	fmt.mantissa_bits = 12;
+	fmt.sign = false;
+
+	if (!convert_to_custom_float_format(arr_points[0].x, &fmt,
+					    &arr_points[0].custom_float_x)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	if (!convert_to_custom_float_format(arr_points[0].offset, &fmt,
+					    &arr_points[0].custom_float_offset)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	if (!convert_to_custom_float_format(arr_points[0].slope, &fmt,
+					    &arr_points[0].custom_float_slope)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	fmt.mantissa_bits = 10;
+	fmt.sign = false;
+
+	if (!convert_to_custom_float_format(arr_points[1].x, &fmt,
+					    &arr_points[1].custom_float_x)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	if (fixpoint == true)
+		arr_points[1].custom_float_y = dal_fixed31_32_clamp_u0d14(arr_points[1].y);
+	else if (!convert_to_custom_float_format(arr_points[1].y, &fmt,
+		&arr_points[1].custom_float_y)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	if (!convert_to_custom_float_format(arr_points[1].slope, &fmt,
+					    &arr_points[1].custom_float_slope)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	if (hw_points_num == 0 || rgb_resulted == NULL || fixpoint == true)
+		return true;
+
+	fmt.mantissa_bits = 12;
+	fmt.sign = true;
+
+	while (i != hw_points_num) {
+		if (!convert_to_custom_float_format(rgb->red, &fmt,
+						    &rgb->red_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		if (!convert_to_custom_float_format(rgb->green, &fmt,
+						    &rgb->green_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		if (!convert_to_custom_float_format(rgb->blue, &fmt,
+						    &rgb->blue_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		if (!convert_to_custom_float_format(rgb->delta_red, &fmt,
+						    &rgb->delta_red_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		if (!convert_to_custom_float_format(rgb->delta_green, &fmt,
+						    &rgb->delta_green_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		if (!convert_to_custom_float_format(rgb->delta_blue, &fmt,
+						    &rgb->delta_blue_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		++rgb;
+		++i;
+	}
+
+	return true;
+}
+
+
+#define MAX_REGIONS_NUMBER 34
+#define MAX_LOW_POINT      25
+#define NUMBER_SEGMENTS    32
+
+bool cm_helper_translate_curve_to_hw_format(
+				const struct dc_transfer_func *output_tf,
+				struct pwl_params *lut_params, bool fixpoint)
+{
+	struct curve_points *arr_points;
+	struct pwl_result_data *rgb_resulted;
+	struct pwl_result_data *rgb;
+	struct pwl_result_data *rgb_plus_1;
+	struct fixed31_32 y_r;
+	struct fixed31_32 y_g;
+	struct fixed31_32 y_b;
+	struct fixed31_32 y1_min;
+	struct fixed31_32 y3_max;
+
+	int32_t segment_start, segment_end;
+	int32_t i;
+	uint32_t j, k, seg_distr[MAX_REGIONS_NUMBER], increment, start_index, hw_points;
+
+	if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS)
+		return false;
+
+	PERF_TRACE();
+
+	arr_points = lut_params->arr_points;
+	rgb_resulted = lut_params->rgb_resulted;
+	hw_points = 0;
+
+	memset(lut_params, 0, sizeof(struct pwl_params));
+	memset(seg_distr, 0, sizeof(seg_distr));
+
+	if (output_tf->tf == TRANSFER_FUNCTION_PQ) {
+		/* 32 segments
+		 * segments are from 2^-25 to 2^7
+		 */
+		for (i = 0; i < 32 ; i++)
+			seg_distr[i] = 3;
+
+		segment_start = -25;
+		segment_end   = 7;
+	} else {
+		/* 10 segments
+		 * segment is from 2^-10 to 2^0
+		 * There are less than 256 points, for optimization
+		 */
+		seg_distr[0] = 3;
+		seg_distr[1] = 4;
+		seg_distr[2] = 4;
+		seg_distr[3] = 4;
+		seg_distr[4] = 4;
+		seg_distr[5] = 4;
+		seg_distr[6] = 4;
+		seg_distr[7] = 4;
+		seg_distr[8] = 5;
+		seg_distr[9] = 5;
+
+		segment_start = -10;
+		segment_end = 0;
+	}
+
+	for (i = segment_end - segment_start; i < MAX_REGIONS_NUMBER ; i++)
+		seg_distr[i] = -1;
+
+	for (k = 0; k < MAX_REGIONS_NUMBER; k++) {
+		if (seg_distr[k] != -1)
+			hw_points += (1 << seg_distr[k]);
+	}
+
+	j = 0;
+	for (k = 0; k < (segment_end - segment_start); k++) {
+		increment = NUMBER_SEGMENTS / (1 << seg_distr[k]);
+		start_index = (segment_start + k + MAX_LOW_POINT) * NUMBER_SEGMENTS;
+		for (i = start_index; i < start_index + NUMBER_SEGMENTS; i += increment) {
+			if (j == hw_points - 1)
+				break;
+			rgb_resulted[j].red = output_tf->tf_pts.red[i];
+			rgb_resulted[j].green = output_tf->tf_pts.green[i];
+			rgb_resulted[j].blue = output_tf->tf_pts.blue[i];
+			j++;
+		}
+	}
+
+	/* last point */
+	start_index = (segment_end + MAX_LOW_POINT) * NUMBER_SEGMENTS;
+	rgb_resulted[hw_points - 1].red = output_tf->tf_pts.red[start_index];
+	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
+	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
+
+	arr_points[0].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
+					     dal_fixed31_32_from_int(segment_start));
+	arr_points[1].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
+					     dal_fixed31_32_from_int(segment_end));
+
+	y_r = rgb_resulted[0].red;
+	y_g = rgb_resulted[0].green;
+	y_b = rgb_resulted[0].blue;
+
+	y1_min = dal_fixed31_32_min(y_r, dal_fixed31_32_min(y_g, y_b));
+
+	arr_points[0].y = y1_min;
+	arr_points[0].slope = dal_fixed31_32_div(arr_points[0].y, arr_points[0].x);
+	y_r = rgb_resulted[hw_points - 1].red;
+	y_g = rgb_resulted[hw_points - 1].green;
+	y_b = rgb_resulted[hw_points - 1].blue;
+
+	/* see comment above, m_arrPoints[1].y should be the Y value for the
+	 * region end (m_numOfHwPoints), not last HW point(m_numOfHwPoints - 1)
+	 */
+	y3_max = dal_fixed31_32_max(y_r, dal_fixed31_32_max(y_g, y_b));
+
+	arr_points[1].y = y3_max;
+
+	arr_points[1].slope = dal_fixed31_32_zero;
+
+	if (output_tf->tf == TRANSFER_FUNCTION_PQ) {
+		/* for PQ, we want to have a straight line from last HW X point,
+		 * and the slope to be such that we hit 1.0 at 10000 nits.
+		 */
+		const struct fixed31_32 end_value =
+				dal_fixed31_32_from_int(125);
+
+		arr_points[1].slope = dal_fixed31_32_div(
+			dal_fixed31_32_sub(dal_fixed31_32_one, arr_points[1].y),
+			dal_fixed31_32_sub(end_value, arr_points[1].x));
+	}
+
+	lut_params->hw_points_num = hw_points;
+
+	i = 1;
+	for (k = 0; k < MAX_REGIONS_NUMBER && i < MAX_REGIONS_NUMBER; k++) {
+		if (seg_distr[k] != -1) {
+			lut_params->arr_curve_points[k].segments_num =
+					seg_distr[k];
+			lut_params->arr_curve_points[i].offset =
+					lut_params->arr_curve_points[k].offset + (1 << seg_distr[k]);
+		}
+		i++;
+	}
+
+	if (seg_distr[k] != -1)
+		lut_params->arr_curve_points[k].segments_num = seg_distr[k];
+
+	rgb = rgb_resulted;
+	rgb_plus_1 = rgb_resulted + 1;
+
+	i = 1;
+	while (i != hw_points + 1) {
+		if (dal_fixed31_32_lt(rgb_plus_1->red, rgb->red))
+			rgb_plus_1->red = rgb->red;
+		if (dal_fixed31_32_lt(rgb_plus_1->green, rgb->green))
+			rgb_plus_1->green = rgb->green;
+		if (dal_fixed31_32_lt(rgb_plus_1->blue, rgb->blue))
+			rgb_plus_1->blue = rgb->blue;
+
+		rgb->delta_red   = dal_fixed31_32_sub(rgb_plus_1->red,   rgb->red);
+		rgb->delta_green = dal_fixed31_32_sub(rgb_plus_1->green, rgb->green);
+		rgb->delta_blue  = dal_fixed31_32_sub(rgb_plus_1->blue,  rgb->blue);
+
+		if (fixpoint == true) {
+			rgb->delta_red_reg   = dal_fixed31_32_clamp_u0d10(rgb->delta_red);
+			rgb->delta_green_reg = dal_fixed31_32_clamp_u0d10(rgb->delta_green);
+			rgb->delta_blue_reg  = dal_fixed31_32_clamp_u0d10(rgb->delta_blue);
+			rgb->red_reg         = dal_fixed31_32_clamp_u0d14(rgb->red);
+			rgb->green_reg       = dal_fixed31_32_clamp_u0d14(rgb->green);
+			rgb->blue_reg        = dal_fixed31_32_clamp_u0d14(rgb->blue);
+		}
+
+		++rgb_plus_1;
+		++rgb;
+		++i;
+	}
+	cm_helper_convert_to_custom_float(rgb_resulted,
+						lut_params->arr_points,
+						hw_points, fixpoint);
+
+	return true;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.h
index 64836dcf21f2..64e476b83bcb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.h
@@ -96,4 +96,14 @@ void cm_helper_program_xfer_func(
 		const struct pwl_params *params,
 		const struct xfer_func_reg *reg);
 
+bool cm_helper_convert_to_custom_float(
+		struct pwl_result_data *rgb_resulted,
+		struct curve_points *arr_points,
+		uint32_t hw_points_num,
+		bool fixpoint);
+
+bool cm_helper_translate_curve_to_hw_format(
+		const struct dc_transfer_func *output_tf,
+		struct pwl_params *lut_params, bool fixpoint);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
index 74e7c82bdc76..f2a08b156cf0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -159,11 +159,10 @@ bool dpp_get_optimal_number_of_taps(
 			scl_data->taps.h_taps = 1;
 		if (IDENTITY_RATIO(scl_data->ratios.vert))
 			scl_data->taps.v_taps = 1;
-		/*
-		 * Spreadsheet doesn't handle taps_c is one properly,
-		 * need to force Chroma to always be scaled to pass
-		 * bandwidth validation.
-		 */
+		if (IDENTITY_RATIO(scl_data->ratios.horz_c))
+			scl_data->taps.h_taps_c = 1;
+		if (IDENTITY_RATIO(scl_data->ratios.vert_c))
+			scl_data->taps.v_taps_c = 1;
 	}
 
 	return true;
@@ -178,37 +177,17 @@ void dpp_reset(struct dpp *dpp_base)
 	dpp->filter_h = NULL;
 	dpp->filter_v = NULL;
 
-	/* set boundary mode to 0 */
-	REG_SET(DSCL_CONTROL, 0, SCL_BOUNDARY_MODE, 0);
+	memset(&dpp->scl_data, 0, sizeof(dpp->scl_data));
+	memset(&dpp->pwl_data, 0, sizeof(dpp->pwl_data));
 }
 
 
 
 static void dpp1_cm_set_regamma_pwl(
-	struct dpp *dpp_base, const struct pwl_params *params)
-{
-	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
-
-	dpp1_cm_power_on_regamma_lut(dpp_base, true);
-	dpp1_cm_configure_regamma_lut(dpp_base, dpp->is_write_to_ram_a_safe);
-
-	if (dpp->is_write_to_ram_a_safe)
-		dpp1_cm_program_regamma_luta_settings(dpp_base, params);
-	else
-		dpp1_cm_program_regamma_lutb_settings(dpp_base, params);
-
-	dpp1_cm_program_regamma_lut(
-			dpp_base, params->rgb_resulted, params->hw_points_num);
-}
-
-static void dpp1_cm_set_regamma_mode(
-	struct dpp *dpp_base,
-	enum opp_regamma mode)
+	struct dpp *dpp_base, const struct pwl_params *params, enum opp_regamma mode)
 {
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
 	uint32_t re_mode = 0;
-	uint32_t obuf_bypass = 0; /* need for pipe split */
-	uint32_t obuf_hupscale = 0;
 
 	switch (mode) {
 	case OPP_REGAMMA_BYPASS:
@@ -221,17 +200,29 @@ static void dpp1_cm_set_regamma_mode(
 		re_mode = 2;
 		break;
 	case OPP_REGAMMA_USER:
+		re_mode = dpp->is_write_to_ram_a_safe ? 4 : 3;
+		if (memcmp(&dpp->pwl_data, params, sizeof(*params)) == 0)
+			break;
+
+		dpp1_cm_power_on_regamma_lut(dpp_base, true);
+		dpp1_cm_configure_regamma_lut(dpp_base, dpp->is_write_to_ram_a_safe);
+
+		if (dpp->is_write_to_ram_a_safe)
+			dpp1_cm_program_regamma_luta_settings(dpp_base, params);
+		else
+			dpp1_cm_program_regamma_lutb_settings(dpp_base, params);
+
+		dpp1_cm_program_regamma_lut(dpp_base, params->rgb_resulted,
+					    params->hw_points_num);
+		dpp->pwl_data = *params;
+
 		re_mode = dpp->is_write_to_ram_a_safe ? 3 : 4;
 		dpp->is_write_to_ram_a_safe = !dpp->is_write_to_ram_a_safe;
 		break;
 	default:
 		break;
 	}
-
 	REG_SET(CM_RGAM_CONTROL, 0, CM_RGAM_LUT_MODE, re_mode);
-	REG_UPDATE_2(OBUF_CONTROL,
-			OBUF_BYPASS, obuf_bypass,
-			OBUF_H_2X_UPSCALE_EN, obuf_hupscale);
 }
 
 static void dpp1_setup_format_flags(enum surface_pixel_format input_format,\
@@ -264,8 +255,10 @@ static void dpp1_set_degamma_format_float(
 
 void dpp1_cnv_setup (
 		struct dpp *dpp_base,
-		enum surface_pixel_format input_format,
-		enum expansion_mode mode)
+		enum surface_pixel_format format,
+		enum expansion_mode mode,
+		struct csc_transform input_csc_color_matrix,
+		enum dc_color_space input_color_space)
 {
 	uint32_t pixel_format;
 	uint32_t alpha_en;
@@ -275,8 +268,10 @@ void dpp1_cnv_setup (
 	bool is_float;
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
 	bool force_disable_cursor = false;
+	struct out_csc_color_matrix tbl_entry;
+	int i = 0;
 
-	dpp1_setup_format_flags(input_format, &fmt);
+	dpp1_setup_format_flags(format, &fmt);
 	alpha_en = 1;
 	pixel_format = 0;
 	color_space = COLOR_SPACE_SRGB;
@@ -306,7 +301,7 @@ void dpp1_cnv_setup (
 
 	dpp1_set_degamma_format_float(dpp_base, is_float);
 
-	switch (input_format) {
+	switch (format) {
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB1555:
 		pixel_format = 1;
 		break;
@@ -362,7 +357,23 @@ void dpp1_cnv_setup (
 			CNVC_SURFACE_PIXEL_FORMAT, pixel_format);
 	REG_UPDATE(FORMAT_CONTROL, FORMAT_CONTROL__ALPHA_EN, alpha_en);
 
-	dpp1_program_input_csc(dpp_base, color_space, select);
+	// if input adjustments exist, program icsc with those values
+
+	if (input_csc_color_matrix.enable_adjustment
+				== true) {
+		for (i = 0; i < 12; i++)
+			tbl_entry.regval[i] = input_csc_color_matrix.matrix[i];
+
+		tbl_entry.color_space = input_color_space;
+
+		if (color_space >= COLOR_SPACE_YCBCR601)
+			select = INPUT_CSC_SELECT_ICSC;
+		else
+			select = INPUT_CSC_SELECT_BYPASS;
+
+		dpp1_program_input_csc(dpp_base, color_space, select, &tbl_entry);
+	} else
+		dpp1_program_input_csc(dpp_base, color_space, select, NULL);
 
 	if (force_disable_cursor) {
 		REG_UPDATE(CURSOR_CONTROL,
@@ -374,10 +385,9 @@ void dpp1_cnv_setup (
 
 void dpp1_set_cursor_attributes(
 		struct dpp *dpp_base,
-		const struct dc_cursor_attributes *attr)
+		enum dc_cursor_color_format color_format)
 {
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
-	enum dc_cursor_color_format color_format = attr->color_format;
 
 	REG_UPDATE_2(CURSOR0_CONTROL,
 			CUR0_MODE, color_format,
@@ -390,13 +400,6 @@ void dpp1_set_cursor_attributes(
 		REG_UPDATE(CURSOR0_COLOR1,
 				CUR0_COLOR1, 0xFFFFFFFF);
 	}
-
-	/* TODO: Fixed vs float */
-
-	REG_UPDATE_3(FORMAT_CONTROL,
-				CNVC_BYPASS, 0,
-				FORMAT_CONTROL__ALPHA_EN, 1,
-				FORMAT_EXPANSION_MODE, 0);
 }
 
 
@@ -426,20 +429,20 @@ static const struct dpp_funcs dcn10_dpp_funcs = {
 		.dpp_set_scaler = dpp1_dscl_set_scaler_manual_scale,
 		.dpp_get_optimal_number_of_taps = dpp_get_optimal_number_of_taps,
 		.dpp_set_gamut_remap = dpp1_cm_set_gamut_remap,
-		.opp_set_csc_adjustment = dpp1_cm_set_output_csc_adjustment,
-		.opp_set_csc_default = dpp1_cm_set_output_csc_default,
-		.opp_power_on_regamma_lut = dpp1_cm_power_on_regamma_lut,
-		.opp_program_regamma_lut = dpp1_cm_program_regamma_lut,
-		.opp_configure_regamma_lut = dpp1_cm_configure_regamma_lut,
-		.opp_program_regamma_lutb_settings = dpp1_cm_program_regamma_lutb_settings,
-		.opp_program_regamma_luta_settings = dpp1_cm_program_regamma_luta_settings,
-		.opp_program_regamma_pwl = dpp1_cm_set_regamma_pwl,
-		.opp_set_regamma_mode = dpp1_cm_set_regamma_mode,
-		.ipp_set_degamma = dpp1_set_degamma,
-		.ipp_program_input_lut		= dpp1_program_input_lut,
-		.ipp_program_degamma_pwl	= dpp1_set_degamma_pwl,
-		.ipp_setup			= dpp1_cnv_setup,
-		.ipp_full_bypass		= dpp1_full_bypass,
+		.dpp_set_csc_adjustment = dpp1_cm_set_output_csc_adjustment,
+		.dpp_set_csc_default = dpp1_cm_set_output_csc_default,
+		.dpp_power_on_regamma_lut = dpp1_cm_power_on_regamma_lut,
+		.dpp_program_regamma_lut = dpp1_cm_program_regamma_lut,
+		.dpp_configure_regamma_lut = dpp1_cm_configure_regamma_lut,
+		.dpp_program_regamma_lutb_settings = dpp1_cm_program_regamma_lutb_settings,
+		.dpp_program_regamma_luta_settings = dpp1_cm_program_regamma_luta_settings,
+		.dpp_program_regamma_pwl = dpp1_cm_set_regamma_pwl,
+		.dpp_program_bias_and_scale = dpp1_program_bias_and_scale,
+		.dpp_set_degamma = dpp1_set_degamma,
+		.dpp_program_input_lut		= dpp1_program_input_lut,
+		.dpp_program_degamma_pwl	= dpp1_set_degamma_pwl,
+		.dpp_setup			= dpp1_cnv_setup,
+		.dpp_full_bypass		= dpp1_full_bypass,
 		.set_cursor_attributes = dpp1_set_cursor_attributes,
 		.set_cursor_position = dpp1_set_cursor_position,
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
index a9782b1aba47..f56ee4d08d89 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
@@ -54,7 +54,6 @@
 	SRI(LB_MEMORY_CTRL, DSCL, id), \
 	SRI(DSCL_AUTOCAL, DSCL, id), \
 	SRI(SCL_BLACK_OFFSET, DSCL, id), \
-	SRI(DSCL_CONTROL, DSCL, id), \
 	SRI(SCL_TAP_CONTROL, DSCL, id), \
 	SRI(SCL_COEF_RAM_TAP_SELECT, DSCL, id), \
 	SRI(SCL_COEF_RAM_TAP_DATA, DSCL, id), \
@@ -72,7 +71,6 @@
 	SRI(SCL_VERT_FILTER_INIT_BOT_C, DSCL, id), \
 	SRI(RECOUT_START, DSCL, id), \
 	SRI(RECOUT_SIZE, DSCL, id), \
-	SRI(OBUF_CONTROL, DSCL, id), \
 	SRI(CM_ICSC_CONTROL, CM, id), \
 	SRI(CM_ICSC_C11_C12, CM, id), \
 	SRI(CM_ICSC_C33_C34, CM, id), \
@@ -127,6 +125,9 @@
 	SRI(CM_OCSC_CONTROL, CM, id), \
 	SRI(CM_OCSC_C11_C12, CM, id), \
 	SRI(CM_OCSC_C33_C34, CM, id), \
+	SRI(CM_BNS_VALUES_R, CM, id), \
+	SRI(CM_BNS_VALUES_G, CM, id), \
+	SRI(CM_BNS_VALUES_B, CM, id), \
 	SRI(CM_MEM_PWR_CTRL, CM, id), \
 	SRI(CM_RGAM_LUT_DATA, CM, id), \
 	SRI(CM_RGAM_LUT_WRITE_EN_MASK, CM, id),\
@@ -191,7 +192,6 @@
 	TF_SF(DSCL0_DSCL_AUTOCAL, AUTOCAL_PIPE_ID, mask_sh),\
 	TF_SF(DSCL0_SCL_BLACK_OFFSET, SCL_BLACK_OFFSET_RGB_Y, mask_sh),\
 	TF_SF(DSCL0_SCL_BLACK_OFFSET, SCL_BLACK_OFFSET_CBCR, mask_sh),\
-	TF_SF(DSCL0_DSCL_CONTROL, SCL_BOUNDARY_MODE, mask_sh),\
 	TF_SF(DSCL0_SCL_TAP_CONTROL, SCL_V_NUM_TAPS, mask_sh),\
 	TF_SF(DSCL0_SCL_TAP_CONTROL, SCL_H_NUM_TAPS, mask_sh),\
 	TF_SF(DSCL0_SCL_TAP_CONTROL, SCL_V_NUM_TAPS_C, mask_sh),\
@@ -235,7 +235,6 @@
 	TF_SF(DSCL0_SCL_VERT_FILTER_INIT_BOT_C, SCL_V_INIT_INT_BOT_C, mask_sh),\
 	TF_SF(DSCL0_SCL_MODE, SCL_CHROMA_COEF_MODE, mask_sh),\
 	TF_SF(DSCL0_SCL_MODE, SCL_COEF_RAM_SELECT_CURRENT, mask_sh), \
-	TF_SF(DSCL0_OBUF_CONTROL, OBUF_BYPASS, mask_sh), \
 	TF_SF(CM0_CM_ICSC_CONTROL, CM_ICSC_MODE, mask_sh), \
 	TF_SF(CM0_CM_ICSC_C11_C12, CM_ICSC_C11, mask_sh), \
 	TF_SF(CM0_CM_ICSC_C11_C12, CM_ICSC_C12, mask_sh), \
@@ -329,6 +328,12 @@
 	TF_SF(CM0_CM_OCSC_C11_C12, CM_OCSC_C12, mask_sh), \
 	TF_SF(CM0_CM_OCSC_C33_C34, CM_OCSC_C33, mask_sh), \
 	TF_SF(CM0_CM_OCSC_C33_C34, CM_OCSC_C34, mask_sh), \
+	TF_SF(CM0_CM_BNS_VALUES_R, CM_BNS_BIAS_R, mask_sh), \
+	TF_SF(CM0_CM_BNS_VALUES_G, CM_BNS_BIAS_G, mask_sh), \
+	TF_SF(CM0_CM_BNS_VALUES_B, CM_BNS_BIAS_B, mask_sh), \
+	TF_SF(CM0_CM_BNS_VALUES_R, CM_BNS_SCALE_R, mask_sh), \
+	TF_SF(CM0_CM_BNS_VALUES_G, CM_BNS_SCALE_G, mask_sh), \
+	TF_SF(CM0_CM_BNS_VALUES_B, CM_BNS_SCALE_B, mask_sh), \
 	TF_SF(CM0_CM_MEM_PWR_CTRL, RGAM_MEM_PWR_FORCE, mask_sh), \
 	TF_SF(CM0_CM_RGAM_LUT_DATA, CM_RGAM_LUT_DATA, mask_sh), \
 	TF_SF(CM0_CM_RGAM_LUT_WRITE_EN_MASK, CM_RGAM_LUT_WRITE_EN_MASK, mask_sh), \
@@ -387,7 +392,6 @@
 	TF_SF(CM0_CM_RGAM_RAMA_REGION_32_33, CM_RGAM_RAMA_EXP_REGION33_LUT_OFFSET, mask_sh), \
 	TF_SF(CM0_CM_RGAM_RAMA_REGION_32_33, CM_RGAM_RAMA_EXP_REGION33_NUM_SEGMENTS, mask_sh), \
 	TF_SF(CM0_CM_RGAM_CONTROL, CM_RGAM_LUT_MODE, mask_sh), \
-	TF_SF(DSCL0_OBUF_CONTROL, OBUF_H_2X_UPSCALE_EN, mask_sh), \
 	TF_SF(CM0_CM_IGAM_CONTROL, CM_IGAM_LUT_MODE, mask_sh), \
 	TF_SF(CM0_CM_IGAM_CONTROL, CM_IGAM_LUT_FORMAT_R, mask_sh), \
 	TF_SF(CM0_CM_IGAM_CONTROL, CM_IGAM_LUT_FORMAT_G, mask_sh), \
@@ -431,7 +435,6 @@
 	type AUTOCAL_PIPE_ID; \
 	type SCL_BLACK_OFFSET_RGB_Y; \
 	type SCL_BLACK_OFFSET_CBCR; \
-	type SCL_BOUNDARY_MODE; \
 	type SCL_V_NUM_TAPS; \
 	type SCL_H_NUM_TAPS; \
 	type SCL_V_NUM_TAPS_C; \
@@ -552,8 +555,6 @@
 	type CM_RGAM_RAMA_EXP_REGION33_NUM_SEGMENTS; \
 	type CM_RGAM_LUT_MODE; \
 	type CM_CMOUT_ROUND_TRUNC_MODE; \
-	type OBUF_BYPASS; \
-	type OBUF_H_2X_UPSCALE_EN; \
 	type CM_BLNDGAM_LUT_MODE; \
 	type CM_BLNDGAM_RAMB_EXP_REGION_START_B; \
 	type CM_BLNDGAM_RAMB_EXP_REGION_START_SEGMENT_B; \
@@ -729,8 +730,9 @@
 	type CM_BLNDGAM_RAMA_EXP_REGION33_NUM_SEGMENTS; \
 	type CM_BLNDGAM_LUT_WRITE_EN_MASK; \
 	type CM_BLNDGAM_LUT_WRITE_SEL; \
+	type CM_BLNDGAM_CONFIG_STATUS; \
 	type CM_BLNDGAM_LUT_INDEX; \
-	type CM_BLNDGAM_LUT_DATA; \
+	type BLNDGAM_MEM_PWR_FORCE; \
 	type CM_3DLUT_MODE; \
 	type CM_3DLUT_SIZE; \
 	type CM_3DLUT_INDEX; \
@@ -904,6 +906,7 @@
 	type CM_SHAPER_RAMA_EXP_REGION33_LUT_OFFSET; \
 	type CM_SHAPER_RAMA_EXP_REGION33_NUM_SEGMENTS; \
 	type CM_SHAPER_LUT_WRITE_EN_MASK; \
+	type CM_SHAPER_CONFIG_STATUS; \
 	type CM_SHAPER_LUT_WRITE_SEL; \
 	type CM_SHAPER_LUT_INDEX; \
 	type CM_SHAPER_LUT_DATA; \
@@ -913,6 +916,12 @@
 	type CM_ICSC_C12; \
 	type CM_ICSC_C33; \
 	type CM_ICSC_C34; \
+	type CM_BNS_BIAS_R; \
+	type CM_BNS_BIAS_G; \
+	type CM_BNS_BIAS_B; \
+	type CM_BNS_SCALE_R; \
+	type CM_BNS_SCALE_G; \
+	type CM_BNS_SCALE_B; \
 	type CM_DGAM_RAMB_EXP_REGION_START_B; \
 	type CM_DGAM_RAMB_EXP_REGION_START_SEGMENT_B; \
 	type CM_DGAM_RAMB_EXP_REGION_START_G; \
@@ -998,257 +1007,255 @@
 	type CM_BYPASS; \
 	type FORMAT_CONTROL__ALPHA_EN; \
 	type CUR0_COLOR0; \
-	type CUR0_COLOR1
-
-
+	type CUR0_COLOR1;
 
 struct dcn_dpp_shift {
-	TF_REG_FIELD_LIST(uint8_t);
+	TF_REG_FIELD_LIST(uint8_t)
 };
 
 struct dcn_dpp_mask {
-	TF_REG_FIELD_LIST(uint32_t);
+	TF_REG_FIELD_LIST(uint32_t)
 };
 
-
-
+#define DPP_COMMON_REG_VARIABLE_LIST \
+	uint32_t DSCL_EXT_OVERSCAN_LEFT_RIGHT; \
+	uint32_t DSCL_EXT_OVERSCAN_TOP_BOTTOM; \
+	uint32_t OTG_H_BLANK; \
+	uint32_t OTG_V_BLANK; \
+	uint32_t SCL_MODE; \
+	uint32_t LB_DATA_FORMAT; \
+	uint32_t LB_MEMORY_CTRL; \
+	uint32_t DSCL_AUTOCAL; \
+	uint32_t SCL_BLACK_OFFSET; \
+	uint32_t SCL_TAP_CONTROL; \
+	uint32_t SCL_COEF_RAM_TAP_SELECT; \
+	uint32_t SCL_COEF_RAM_TAP_DATA; \
+	uint32_t DSCL_2TAP_CONTROL; \
+	uint32_t MPC_SIZE; \
+	uint32_t SCL_HORZ_FILTER_SCALE_RATIO; \
+	uint32_t SCL_VERT_FILTER_SCALE_RATIO; \
+	uint32_t SCL_HORZ_FILTER_SCALE_RATIO_C; \
+	uint32_t SCL_VERT_FILTER_SCALE_RATIO_C; \
+	uint32_t SCL_HORZ_FILTER_INIT; \
+	uint32_t SCL_HORZ_FILTER_INIT_C; \
+	uint32_t SCL_VERT_FILTER_INIT; \
+	uint32_t SCL_VERT_FILTER_INIT_BOT; \
+	uint32_t SCL_VERT_FILTER_INIT_C; \
+	uint32_t SCL_VERT_FILTER_INIT_BOT_C; \
+	uint32_t RECOUT_START; \
+	uint32_t RECOUT_SIZE; \
+	uint32_t CM_GAMUT_REMAP_CONTROL; \
+	uint32_t CM_GAMUT_REMAP_C11_C12; \
+	uint32_t CM_GAMUT_REMAP_C33_C34; \
+	uint32_t CM_COMA_C11_C12; \
+	uint32_t CM_COMA_C33_C34; \
+	uint32_t CM_COMB_C11_C12; \
+	uint32_t CM_COMB_C33_C34; \
+	uint32_t CM_OCSC_CONTROL; \
+	uint32_t CM_OCSC_C11_C12; \
+	uint32_t CM_OCSC_C33_C34; \
+	uint32_t CM_MEM_PWR_CTRL; \
+	uint32_t CM_RGAM_LUT_DATA; \
+	uint32_t CM_RGAM_LUT_WRITE_EN_MASK; \
+	uint32_t CM_RGAM_LUT_INDEX; \
+	uint32_t CM_RGAM_RAMB_START_CNTL_B; \
+	uint32_t CM_RGAM_RAMB_START_CNTL_G; \
+	uint32_t CM_RGAM_RAMB_START_CNTL_R; \
+	uint32_t CM_RGAM_RAMB_SLOPE_CNTL_B; \
+	uint32_t CM_RGAM_RAMB_SLOPE_CNTL_G; \
+	uint32_t CM_RGAM_RAMB_SLOPE_CNTL_R; \
+	uint32_t CM_RGAM_RAMB_END_CNTL1_B; \
+	uint32_t CM_RGAM_RAMB_END_CNTL2_B; \
+	uint32_t CM_RGAM_RAMB_END_CNTL1_G; \
+	uint32_t CM_RGAM_RAMB_END_CNTL2_G; \
+	uint32_t CM_RGAM_RAMB_END_CNTL1_R; \
+	uint32_t CM_RGAM_RAMB_END_CNTL2_R; \
+	uint32_t CM_RGAM_RAMB_REGION_0_1; \
+	uint32_t CM_RGAM_RAMB_REGION_32_33; \
+	uint32_t CM_RGAM_RAMA_START_CNTL_B; \
+	uint32_t CM_RGAM_RAMA_START_CNTL_G; \
+	uint32_t CM_RGAM_RAMA_START_CNTL_R; \
+	uint32_t CM_RGAM_RAMA_SLOPE_CNTL_B; \
+	uint32_t CM_RGAM_RAMA_SLOPE_CNTL_G; \
+	uint32_t CM_RGAM_RAMA_SLOPE_CNTL_R; \
+	uint32_t CM_RGAM_RAMA_END_CNTL1_B; \
+	uint32_t CM_RGAM_RAMA_END_CNTL2_B; \
+	uint32_t CM_RGAM_RAMA_END_CNTL1_G; \
+	uint32_t CM_RGAM_RAMA_END_CNTL2_G; \
+	uint32_t CM_RGAM_RAMA_END_CNTL1_R; \
+	uint32_t CM_RGAM_RAMA_END_CNTL2_R; \
+	uint32_t CM_RGAM_RAMA_REGION_0_1; \
+	uint32_t CM_RGAM_RAMA_REGION_32_33; \
+	uint32_t CM_RGAM_CONTROL; \
+	uint32_t CM_CMOUT_CONTROL; \
+	uint32_t CM_BLNDGAM_LUT_WRITE_EN_MASK; \
+	uint32_t CM_BLNDGAM_CONTROL; \
+	uint32_t CM_BLNDGAM_RAMB_START_CNTL_B; \
+	uint32_t CM_BLNDGAM_RAMB_START_CNTL_G; \
+	uint32_t CM_BLNDGAM_RAMB_START_CNTL_R; \
+	uint32_t CM_BLNDGAM_RAMB_SLOPE_CNTL_B; \
+	uint32_t CM_BLNDGAM_RAMB_SLOPE_CNTL_G; \
+	uint32_t CM_BLNDGAM_RAMB_SLOPE_CNTL_R; \
+	uint32_t CM_BLNDGAM_RAMB_END_CNTL1_B; \
+	uint32_t CM_BLNDGAM_RAMB_END_CNTL2_B; \
+	uint32_t CM_BLNDGAM_RAMB_END_CNTL1_G; \
+	uint32_t CM_BLNDGAM_RAMB_END_CNTL2_G; \
+	uint32_t CM_BLNDGAM_RAMB_END_CNTL1_R; \
+	uint32_t CM_BLNDGAM_RAMB_END_CNTL2_R; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_0_1; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_2_3; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_4_5; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_6_7; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_8_9; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_10_11; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_12_13; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_14_15; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_16_17; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_18_19; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_20_21; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_22_23; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_24_25; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_26_27; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_28_29; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_30_31; \
+	uint32_t CM_BLNDGAM_RAMB_REGION_32_33; \
+	uint32_t CM_BLNDGAM_RAMA_START_CNTL_B; \
+	uint32_t CM_BLNDGAM_RAMA_START_CNTL_G; \
+	uint32_t CM_BLNDGAM_RAMA_START_CNTL_R; \
+	uint32_t CM_BLNDGAM_RAMA_SLOPE_CNTL_B; \
+	uint32_t CM_BLNDGAM_RAMA_SLOPE_CNTL_G; \
+	uint32_t CM_BLNDGAM_RAMA_SLOPE_CNTL_R; \
+	uint32_t CM_BLNDGAM_RAMA_END_CNTL1_B; \
+	uint32_t CM_BLNDGAM_RAMA_END_CNTL2_B; \
+	uint32_t CM_BLNDGAM_RAMA_END_CNTL1_G; \
+	uint32_t CM_BLNDGAM_RAMA_END_CNTL2_G; \
+	uint32_t CM_BLNDGAM_RAMA_END_CNTL1_R; \
+	uint32_t CM_BLNDGAM_RAMA_END_CNTL2_R; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_0_1; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_2_3; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_4_5; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_6_7; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_8_9; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_10_11; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_12_13; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_14_15; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_16_17; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_18_19; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_20_21; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_22_23; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_24_25; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_26_27; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_28_29; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_30_31; \
+	uint32_t CM_BLNDGAM_RAMA_REGION_32_33; \
+	uint32_t CM_BLNDGAM_LUT_INDEX; \
+	uint32_t CM_3DLUT_MODE; \
+	uint32_t CM_3DLUT_INDEX; \
+	uint32_t CM_3DLUT_DATA; \
+	uint32_t CM_3DLUT_DATA_30BIT; \
+	uint32_t CM_3DLUT_READ_WRITE_CONTROL; \
+	uint32_t CM_SHAPER_LUT_WRITE_EN_MASK; \
+	uint32_t CM_SHAPER_CONTROL; \
+	uint32_t CM_SHAPER_RAMB_START_CNTL_B; \
+	uint32_t CM_SHAPER_RAMB_START_CNTL_G; \
+	uint32_t CM_SHAPER_RAMB_START_CNTL_R; \
+	uint32_t CM_SHAPER_RAMB_END_CNTL_B; \
+	uint32_t CM_SHAPER_RAMB_END_CNTL_G; \
+	uint32_t CM_SHAPER_RAMB_END_CNTL_R; \
+	uint32_t CM_SHAPER_RAMB_REGION_0_1; \
+	uint32_t CM_SHAPER_RAMB_REGION_2_3; \
+	uint32_t CM_SHAPER_RAMB_REGION_4_5; \
+	uint32_t CM_SHAPER_RAMB_REGION_6_7; \
+	uint32_t CM_SHAPER_RAMB_REGION_8_9; \
+	uint32_t CM_SHAPER_RAMB_REGION_10_11; \
+	uint32_t CM_SHAPER_RAMB_REGION_12_13; \
+	uint32_t CM_SHAPER_RAMB_REGION_14_15; \
+	uint32_t CM_SHAPER_RAMB_REGION_16_17; \
+	uint32_t CM_SHAPER_RAMB_REGION_18_19; \
+	uint32_t CM_SHAPER_RAMB_REGION_20_21; \
+	uint32_t CM_SHAPER_RAMB_REGION_22_23; \
+	uint32_t CM_SHAPER_RAMB_REGION_24_25; \
+	uint32_t CM_SHAPER_RAMB_REGION_26_27; \
+	uint32_t CM_SHAPER_RAMB_REGION_28_29; \
+	uint32_t CM_SHAPER_RAMB_REGION_30_31; \
+	uint32_t CM_SHAPER_RAMB_REGION_32_33; \
+	uint32_t CM_SHAPER_RAMA_START_CNTL_B; \
+	uint32_t CM_SHAPER_RAMA_START_CNTL_G; \
+	uint32_t CM_SHAPER_RAMA_START_CNTL_R; \
+	uint32_t CM_SHAPER_RAMA_END_CNTL_B; \
+	uint32_t CM_SHAPER_RAMA_END_CNTL_G; \
+	uint32_t CM_SHAPER_RAMA_END_CNTL_R; \
+	uint32_t CM_SHAPER_RAMA_REGION_0_1; \
+	uint32_t CM_SHAPER_RAMA_REGION_2_3; \
+	uint32_t CM_SHAPER_RAMA_REGION_4_5; \
+	uint32_t CM_SHAPER_RAMA_REGION_6_7; \
+	uint32_t CM_SHAPER_RAMA_REGION_8_9; \
+	uint32_t CM_SHAPER_RAMA_REGION_10_11; \
+	uint32_t CM_SHAPER_RAMA_REGION_12_13; \
+	uint32_t CM_SHAPER_RAMA_REGION_14_15; \
+	uint32_t CM_SHAPER_RAMA_REGION_16_17; \
+	uint32_t CM_SHAPER_RAMA_REGION_18_19; \
+	uint32_t CM_SHAPER_RAMA_REGION_20_21; \
+	uint32_t CM_SHAPER_RAMA_REGION_22_23; \
+	uint32_t CM_SHAPER_RAMA_REGION_24_25; \
+	uint32_t CM_SHAPER_RAMA_REGION_26_27; \
+	uint32_t CM_SHAPER_RAMA_REGION_28_29; \
+	uint32_t CM_SHAPER_RAMA_REGION_30_31; \
+	uint32_t CM_SHAPER_RAMA_REGION_32_33; \
+	uint32_t CM_SHAPER_LUT_INDEX; \
+	uint32_t CM_SHAPER_LUT_DATA; \
+	uint32_t CM_ICSC_CONTROL; \
+	uint32_t CM_ICSC_C11_C12; \
+	uint32_t CM_ICSC_C33_C34; \
+	uint32_t CM_BNS_VALUES_R; \
+	uint32_t CM_BNS_VALUES_G; \
+	uint32_t CM_BNS_VALUES_B; \
+	uint32_t CM_DGAM_RAMB_START_CNTL_B; \
+	uint32_t CM_DGAM_RAMB_START_CNTL_G; \
+	uint32_t CM_DGAM_RAMB_START_CNTL_R; \
+	uint32_t CM_DGAM_RAMB_SLOPE_CNTL_B; \
+	uint32_t CM_DGAM_RAMB_SLOPE_CNTL_G; \
+	uint32_t CM_DGAM_RAMB_SLOPE_CNTL_R; \
+	uint32_t CM_DGAM_RAMB_END_CNTL1_B; \
+	uint32_t CM_DGAM_RAMB_END_CNTL2_B; \
+	uint32_t CM_DGAM_RAMB_END_CNTL1_G; \
+	uint32_t CM_DGAM_RAMB_END_CNTL2_G; \
+	uint32_t CM_DGAM_RAMB_END_CNTL1_R; \
+	uint32_t CM_DGAM_RAMB_END_CNTL2_R; \
+	uint32_t CM_DGAM_RAMB_REGION_0_1; \
+	uint32_t CM_DGAM_RAMB_REGION_14_15; \
+	uint32_t CM_DGAM_RAMA_START_CNTL_B; \
+	uint32_t CM_DGAM_RAMA_START_CNTL_G; \
+	uint32_t CM_DGAM_RAMA_START_CNTL_R; \
+	uint32_t CM_DGAM_RAMA_SLOPE_CNTL_B; \
+	uint32_t CM_DGAM_RAMA_SLOPE_CNTL_G; \
+	uint32_t CM_DGAM_RAMA_SLOPE_CNTL_R; \
+	uint32_t CM_DGAM_RAMA_END_CNTL1_B; \
+	uint32_t CM_DGAM_RAMA_END_CNTL2_B; \
+	uint32_t CM_DGAM_RAMA_END_CNTL1_G; \
+	uint32_t CM_DGAM_RAMA_END_CNTL2_G; \
+	uint32_t CM_DGAM_RAMA_END_CNTL1_R; \
+	uint32_t CM_DGAM_RAMA_END_CNTL2_R; \
+	uint32_t CM_DGAM_RAMA_REGION_0_1; \
+	uint32_t CM_DGAM_RAMA_REGION_14_15; \
+	uint32_t CM_DGAM_LUT_WRITE_EN_MASK; \
+	uint32_t CM_DGAM_LUT_INDEX; \
+	uint32_t CM_DGAM_LUT_DATA; \
+	uint32_t CM_CONTROL; \
+	uint32_t CM_DGAM_CONTROL; \
+	uint32_t CM_IGAM_CONTROL; \
+	uint32_t CM_IGAM_LUT_RW_CONTROL; \
+	uint32_t CM_IGAM_LUT_RW_INDEX; \
+	uint32_t CM_IGAM_LUT_SEQ_COLOR; \
+	uint32_t FORMAT_CONTROL; \
+	uint32_t CNVC_SURFACE_PIXEL_FORMAT; \
+	uint32_t CURSOR_CONTROL; \
+	uint32_t CURSOR0_CONTROL; \
+	uint32_t CURSOR0_COLOR0; \
+	uint32_t CURSOR0_COLOR1;
 
 struct dcn_dpp_registers {
-	uint32_t DSCL_EXT_OVERSCAN_LEFT_RIGHT;
-	uint32_t DSCL_EXT_OVERSCAN_TOP_BOTTOM;
-	uint32_t OTG_H_BLANK;
-	uint32_t OTG_V_BLANK;
-	uint32_t SCL_MODE;
-	uint32_t LB_DATA_FORMAT;
-	uint32_t LB_MEMORY_CTRL;
-	uint32_t DSCL_AUTOCAL;
-	uint32_t SCL_BLACK_OFFSET;
-	uint32_t DSCL_CONTROL;
-	uint32_t SCL_TAP_CONTROL;
-	uint32_t SCL_COEF_RAM_TAP_SELECT;
-	uint32_t SCL_COEF_RAM_TAP_DATA;
-	uint32_t DSCL_2TAP_CONTROL;
-	uint32_t MPC_SIZE;
-	uint32_t SCL_HORZ_FILTER_SCALE_RATIO;
-	uint32_t SCL_VERT_FILTER_SCALE_RATIO;
-	uint32_t SCL_HORZ_FILTER_SCALE_RATIO_C;
-	uint32_t SCL_VERT_FILTER_SCALE_RATIO_C;
-	uint32_t SCL_HORZ_FILTER_INIT;
-	uint32_t SCL_HORZ_FILTER_INIT_C;
-	uint32_t SCL_VERT_FILTER_INIT;
-	uint32_t SCL_VERT_FILTER_INIT_BOT;
-	uint32_t SCL_VERT_FILTER_INIT_C;
-	uint32_t SCL_VERT_FILTER_INIT_BOT_C;
-	uint32_t RECOUT_START;
-	uint32_t RECOUT_SIZE;
-	uint32_t CM_GAMUT_REMAP_CONTROL;
-	uint32_t CM_GAMUT_REMAP_C11_C12;
-	uint32_t CM_GAMUT_REMAP_C33_C34;
-	uint32_t CM_COMA_C11_C12;
-	uint32_t CM_COMA_C33_C34;
-	uint32_t CM_COMB_C11_C12;
-	uint32_t CM_COMB_C33_C34;
-	uint32_t CM_OCSC_CONTROL;
-	uint32_t CM_OCSC_C11_C12;
-	uint32_t CM_OCSC_C33_C34;
-	uint32_t CM_MEM_PWR_CTRL;
-	uint32_t CM_RGAM_LUT_DATA;
-	uint32_t CM_RGAM_LUT_WRITE_EN_MASK;
-	uint32_t CM_RGAM_LUT_INDEX;
-	uint32_t CM_RGAM_RAMB_START_CNTL_B;
-	uint32_t CM_RGAM_RAMB_START_CNTL_G;
-	uint32_t CM_RGAM_RAMB_START_CNTL_R;
-	uint32_t CM_RGAM_RAMB_SLOPE_CNTL_B;
-	uint32_t CM_RGAM_RAMB_SLOPE_CNTL_G;
-	uint32_t CM_RGAM_RAMB_SLOPE_CNTL_R;
-	uint32_t CM_RGAM_RAMB_END_CNTL1_B;
-	uint32_t CM_RGAM_RAMB_END_CNTL2_B;
-	uint32_t CM_RGAM_RAMB_END_CNTL1_G;
-	uint32_t CM_RGAM_RAMB_END_CNTL2_G;
-	uint32_t CM_RGAM_RAMB_END_CNTL1_R;
-	uint32_t CM_RGAM_RAMB_END_CNTL2_R;
-	uint32_t CM_RGAM_RAMB_REGION_0_1;
-	uint32_t CM_RGAM_RAMB_REGION_32_33;
-	uint32_t CM_RGAM_RAMA_START_CNTL_B;
-	uint32_t CM_RGAM_RAMA_START_CNTL_G;
-	uint32_t CM_RGAM_RAMA_START_CNTL_R;
-	uint32_t CM_RGAM_RAMA_SLOPE_CNTL_B;
-	uint32_t CM_RGAM_RAMA_SLOPE_CNTL_G;
-	uint32_t CM_RGAM_RAMA_SLOPE_CNTL_R;
-	uint32_t CM_RGAM_RAMA_END_CNTL1_B;
-	uint32_t CM_RGAM_RAMA_END_CNTL2_B;
-	uint32_t CM_RGAM_RAMA_END_CNTL1_G;
-	uint32_t CM_RGAM_RAMA_END_CNTL2_G;
-	uint32_t CM_RGAM_RAMA_END_CNTL1_R;
-	uint32_t CM_RGAM_RAMA_END_CNTL2_R;
-	uint32_t CM_RGAM_RAMA_REGION_0_1;
-	uint32_t CM_RGAM_RAMA_REGION_32_33;
-	uint32_t CM_RGAM_CONTROL;
-	uint32_t CM_CMOUT_CONTROL;
-	uint32_t OBUF_CONTROL;
-	uint32_t CM_BLNDGAM_LUT_WRITE_EN_MASK;
-	uint32_t CM_BLNDGAM_CONTROL;
-	uint32_t CM_BLNDGAM_RAMB_START_CNTL_B;
-	uint32_t CM_BLNDGAM_RAMB_START_CNTL_G;
-	uint32_t CM_BLNDGAM_RAMB_START_CNTL_R;
-	uint32_t CM_BLNDGAM_RAMB_SLOPE_CNTL_B;
-	uint32_t CM_BLNDGAM_RAMB_SLOPE_CNTL_G;
-	uint32_t CM_BLNDGAM_RAMB_SLOPE_CNTL_R;
-	uint32_t CM_BLNDGAM_RAMB_END_CNTL1_B;
-	uint32_t CM_BLNDGAM_RAMB_END_CNTL2_B;
-	uint32_t CM_BLNDGAM_RAMB_END_CNTL1_G;
-	uint32_t CM_BLNDGAM_RAMB_END_CNTL2_G;
-	uint32_t CM_BLNDGAM_RAMB_END_CNTL1_R;
-	uint32_t CM_BLNDGAM_RAMB_END_CNTL2_R;
-	uint32_t CM_BLNDGAM_RAMB_REGION_0_1;
-	uint32_t CM_BLNDGAM_RAMB_REGION_2_3;
-	uint32_t CM_BLNDGAM_RAMB_REGION_4_5;
-	uint32_t CM_BLNDGAM_RAMB_REGION_6_7;
-	uint32_t CM_BLNDGAM_RAMB_REGION_8_9;
-	uint32_t CM_BLNDGAM_RAMB_REGION_10_11;
-	uint32_t CM_BLNDGAM_RAMB_REGION_12_13;
-	uint32_t CM_BLNDGAM_RAMB_REGION_14_15;
-	uint32_t CM_BLNDGAM_RAMB_REGION_16_17;
-	uint32_t CM_BLNDGAM_RAMB_REGION_18_19;
-	uint32_t CM_BLNDGAM_RAMB_REGION_20_21;
-	uint32_t CM_BLNDGAM_RAMB_REGION_22_23;
-	uint32_t CM_BLNDGAM_RAMB_REGION_24_25;
-	uint32_t CM_BLNDGAM_RAMB_REGION_26_27;
-	uint32_t CM_BLNDGAM_RAMB_REGION_28_29;
-	uint32_t CM_BLNDGAM_RAMB_REGION_30_31;
-	uint32_t CM_BLNDGAM_RAMB_REGION_32_33;
-	uint32_t CM_BLNDGAM_RAMA_START_CNTL_B;
-	uint32_t CM_BLNDGAM_RAMA_START_CNTL_G;
-	uint32_t CM_BLNDGAM_RAMA_START_CNTL_R;
-	uint32_t CM_BLNDGAM_RAMA_SLOPE_CNTL_B;
-	uint32_t CM_BLNDGAM_RAMA_SLOPE_CNTL_G;
-	uint32_t CM_BLNDGAM_RAMA_SLOPE_CNTL_R;
-	uint32_t CM_BLNDGAM_RAMA_END_CNTL1_B;
-	uint32_t CM_BLNDGAM_RAMA_END_CNTL2_B;
-	uint32_t CM_BLNDGAM_RAMA_END_CNTL1_G;
-	uint32_t CM_BLNDGAM_RAMA_END_CNTL2_G;
-	uint32_t CM_BLNDGAM_RAMA_END_CNTL1_R;
-	uint32_t CM_BLNDGAM_RAMA_END_CNTL2_R;
-	uint32_t CM_BLNDGAM_RAMA_REGION_0_1;
-	uint32_t CM_BLNDGAM_RAMA_REGION_2_3;
-	uint32_t CM_BLNDGAM_RAMA_REGION_4_5;
-	uint32_t CM_BLNDGAM_RAMA_REGION_6_7;
-	uint32_t CM_BLNDGAM_RAMA_REGION_8_9;
-	uint32_t CM_BLNDGAM_RAMA_REGION_10_11;
-	uint32_t CM_BLNDGAM_RAMA_REGION_12_13;
-	uint32_t CM_BLNDGAM_RAMA_REGION_14_15;
-	uint32_t CM_BLNDGAM_RAMA_REGION_16_17;
-	uint32_t CM_BLNDGAM_RAMA_REGION_18_19;
-	uint32_t CM_BLNDGAM_RAMA_REGION_20_21;
-	uint32_t CM_BLNDGAM_RAMA_REGION_22_23;
-	uint32_t CM_BLNDGAM_RAMA_REGION_24_25;
-	uint32_t CM_BLNDGAM_RAMA_REGION_26_27;
-	uint32_t CM_BLNDGAM_RAMA_REGION_28_29;
-	uint32_t CM_BLNDGAM_RAMA_REGION_30_31;
-	uint32_t CM_BLNDGAM_RAMA_REGION_32_33;
-	uint32_t CM_BLNDGAM_LUT_INDEX;
-	uint32_t CM_BLNDGAM_LUT_DATA;
-	uint32_t CM_3DLUT_MODE;
-	uint32_t CM_3DLUT_INDEX;
-	uint32_t CM_3DLUT_DATA;
-	uint32_t CM_3DLUT_DATA_30BIT;
-	uint32_t CM_3DLUT_READ_WRITE_CONTROL;
-	uint32_t CM_SHAPER_LUT_WRITE_EN_MASK;
-	uint32_t CM_SHAPER_CONTROL;
-	uint32_t CM_SHAPER_RAMB_START_CNTL_B;
-	uint32_t CM_SHAPER_RAMB_START_CNTL_G;
-	uint32_t CM_SHAPER_RAMB_START_CNTL_R;
-	uint32_t CM_SHAPER_RAMB_END_CNTL_B;
-	uint32_t CM_SHAPER_RAMB_END_CNTL_G;
-	uint32_t CM_SHAPER_RAMB_END_CNTL_R;
-	uint32_t CM_SHAPER_RAMB_REGION_0_1;
-	uint32_t CM_SHAPER_RAMB_REGION_2_3;
-	uint32_t CM_SHAPER_RAMB_REGION_4_5;
-	uint32_t CM_SHAPER_RAMB_REGION_6_7;
-	uint32_t CM_SHAPER_RAMB_REGION_8_9;
-	uint32_t CM_SHAPER_RAMB_REGION_10_11;
-	uint32_t CM_SHAPER_RAMB_REGION_12_13;
-	uint32_t CM_SHAPER_RAMB_REGION_14_15;
-	uint32_t CM_SHAPER_RAMB_REGION_16_17;
-	uint32_t CM_SHAPER_RAMB_REGION_18_19;
-	uint32_t CM_SHAPER_RAMB_REGION_20_21;
-	uint32_t CM_SHAPER_RAMB_REGION_22_23;
-	uint32_t CM_SHAPER_RAMB_REGION_24_25;
-	uint32_t CM_SHAPER_RAMB_REGION_26_27;
-	uint32_t CM_SHAPER_RAMB_REGION_28_29;
-	uint32_t CM_SHAPER_RAMB_REGION_30_31;
-	uint32_t CM_SHAPER_RAMB_REGION_32_33;
-	uint32_t CM_SHAPER_RAMA_START_CNTL_B;
-	uint32_t CM_SHAPER_RAMA_START_CNTL_G;
-	uint32_t CM_SHAPER_RAMA_START_CNTL_R;
-	uint32_t CM_SHAPER_RAMA_END_CNTL_B;
-	uint32_t CM_SHAPER_RAMA_END_CNTL_G;
-	uint32_t CM_SHAPER_RAMA_END_CNTL_R;
-	uint32_t CM_SHAPER_RAMA_REGION_0_1;
-	uint32_t CM_SHAPER_RAMA_REGION_2_3;
-	uint32_t CM_SHAPER_RAMA_REGION_4_5;
-	uint32_t CM_SHAPER_RAMA_REGION_6_7;
-	uint32_t CM_SHAPER_RAMA_REGION_8_9;
-	uint32_t CM_SHAPER_RAMA_REGION_10_11;
-	uint32_t CM_SHAPER_RAMA_REGION_12_13;
-	uint32_t CM_SHAPER_RAMA_REGION_14_15;
-	uint32_t CM_SHAPER_RAMA_REGION_16_17;
-	uint32_t CM_SHAPER_RAMA_REGION_18_19;
-	uint32_t CM_SHAPER_RAMA_REGION_20_21;
-	uint32_t CM_SHAPER_RAMA_REGION_22_23;
-	uint32_t CM_SHAPER_RAMA_REGION_24_25;
-	uint32_t CM_SHAPER_RAMA_REGION_26_27;
-	uint32_t CM_SHAPER_RAMA_REGION_28_29;
-	uint32_t CM_SHAPER_RAMA_REGION_30_31;
-	uint32_t CM_SHAPER_RAMA_REGION_32_33;
-	uint32_t CM_SHAPER_LUT_INDEX;
-	uint32_t CM_SHAPER_LUT_DATA;
-	uint32_t CM_ICSC_CONTROL;
-	uint32_t CM_ICSC_C11_C12;
-	uint32_t CM_ICSC_C33_C34;
-	uint32_t CM_DGAM_RAMB_START_CNTL_B;
-	uint32_t CM_DGAM_RAMB_START_CNTL_G;
-	uint32_t CM_DGAM_RAMB_START_CNTL_R;
-	uint32_t CM_DGAM_RAMB_SLOPE_CNTL_B;
-	uint32_t CM_DGAM_RAMB_SLOPE_CNTL_G;
-	uint32_t CM_DGAM_RAMB_SLOPE_CNTL_R;
-	uint32_t CM_DGAM_RAMB_END_CNTL1_B;
-	uint32_t CM_DGAM_RAMB_END_CNTL2_B;
-	uint32_t CM_DGAM_RAMB_END_CNTL1_G;
-	uint32_t CM_DGAM_RAMB_END_CNTL2_G;
-	uint32_t CM_DGAM_RAMB_END_CNTL1_R;
-	uint32_t CM_DGAM_RAMB_END_CNTL2_R;
-	uint32_t CM_DGAM_RAMB_REGION_0_1;
-	uint32_t CM_DGAM_RAMB_REGION_14_15;
-	uint32_t CM_DGAM_RAMA_START_CNTL_B;
-	uint32_t CM_DGAM_RAMA_START_CNTL_G;
-	uint32_t CM_DGAM_RAMA_START_CNTL_R;
-	uint32_t CM_DGAM_RAMA_SLOPE_CNTL_B;
-	uint32_t CM_DGAM_RAMA_SLOPE_CNTL_G;
-	uint32_t CM_DGAM_RAMA_SLOPE_CNTL_R;
-	uint32_t CM_DGAM_RAMA_END_CNTL1_B;
-	uint32_t CM_DGAM_RAMA_END_CNTL2_B;
-	uint32_t CM_DGAM_RAMA_END_CNTL1_G;
-	uint32_t CM_DGAM_RAMA_END_CNTL2_G;
-	uint32_t CM_DGAM_RAMA_END_CNTL1_R;
-	uint32_t CM_DGAM_RAMA_END_CNTL2_R;
-	uint32_t CM_DGAM_RAMA_REGION_0_1;
-	uint32_t CM_DGAM_RAMA_REGION_14_15;
-	uint32_t CM_DGAM_LUT_WRITE_EN_MASK;
-	uint32_t CM_DGAM_LUT_INDEX;
-	uint32_t CM_DGAM_LUT_DATA;
-	uint32_t CM_CONTROL;
-	uint32_t CM_DGAM_CONTROL;
-	uint32_t CM_IGAM_CONTROL;
-	uint32_t CM_IGAM_LUT_RW_CONTROL;
-	uint32_t CM_IGAM_LUT_RW_INDEX;
-	uint32_t CM_IGAM_LUT_SEQ_COLOR;
-	uint32_t FORMAT_CONTROL;
-	uint32_t CNVC_SURFACE_PIXEL_FORMAT;
-	uint32_t CURSOR_CONTROL;
-	uint32_t CURSOR0_CONTROL;
-	uint32_t CURSOR0_COLOR0;
-	uint32_t CURSOR0_COLOR1;
+	DPP_COMMON_REG_VARIABLE_LIST
 };
 
 struct dcn10_dpp {
@@ -1266,6 +1273,8 @@ struct dcn10_dpp {
 	int lb_memory_size;
 	int lb_bits_per_entry;
 	bool is_write_to_ram_a_safe;
+	struct scaler_data scl_data;
+	struct pwl_params pwl_data;
 };
 
 enum dcn10_input_csc_select {
@@ -1274,6 +1283,10 @@ enum dcn10_input_csc_select {
 	INPUT_CSC_SELECT_COMA
 };
 
+void dpp1_set_cursor_attributes(
+		struct dpp *dpp_base,
+		enum dc_cursor_color_format color_format);
+
 bool dpp1_dscl_is_lb_conf_valid(
 		int ceil_vratio,
 		int num_partitions,
@@ -1310,7 +1323,12 @@ void dpp1_power_on_degamma_lut(
 void dpp1_program_input_csc(
 		struct dpp *dpp_base,
 		enum dc_color_space color_space,
-		enum dcn10_input_csc_select select);
+		enum dcn10_input_csc_select select,
+		const struct out_csc_color_matrix *tbl_entry);
+
+void dpp1_program_bias_and_scale(
+		struct dpp *dpp_base,
+		struct dc_bias_and_scale *params);
 
 void dpp1_program_input_lut(
 		struct dpp *dpp_base,
@@ -1356,11 +1374,11 @@ void dpp1_cm_program_regamma_lutb_settings(
 		const struct pwl_params *params);
 void dpp1_cm_set_output_csc_adjustment(
 		struct dpp *dpp_base,
-		const struct out_csc_color_matrix *tbl_entry);
+		const uint16_t *regval);
 
 void dpp1_cm_set_output_csc_default(
 		struct dpp *dpp_base,
-		const struct default_adjustment *default_adjust);
+		enum dc_color_space colorspace);
 
 void dpp1_cm_set_gamut_remap(
 	struct dpp *dpp,
@@ -1372,8 +1390,10 @@ void dpp1_dscl_set_scaler_manual_scale(
 
 void dpp1_cnv_setup (
 		struct dpp *dpp_base,
-		enum surface_pixel_format input_format,
-		enum expansion_mode mode);
+		enum surface_pixel_format format,
+		enum expansion_mode mode,
+		struct csc_transform input_csc_color_matrix,
+		enum dc_color_space input_color_space);
 
 void dpp1_full_bypass(struct dpp *dpp_base);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
index 40627c244bf5..a5b099023652 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
@@ -49,6 +49,8 @@
 #define FN(reg_name, field_name) \
 	dpp->tf_shift->field_name, dpp->tf_mask->field_name
 
+#define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0]))
+
 struct dcn10_input_csc_matrix {
 	enum dc_color_space color_space;
 	uint16_t regval[12];
@@ -117,8 +119,6 @@ static const struct dcn10_input_csc_matrix dcn10_input_csc_matrix[] = {
 						0x2568, 0x43ee, 0xdbb2} }
 };
 
-
-
 static void program_gamut_remap(
 		struct dcn10_dpp *dpp,
 		const uint16_t *regval,
@@ -223,84 +223,20 @@ void dpp1_cm_set_gamut_remap(
 	}
 }
 
-void dpp1_cm_set_output_csc_default(
-		struct dpp *dpp_base,
-		const struct default_adjustment *default_adjust)
-{
-
-	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
-	uint32_t ocsc_mode = 0;
-
-	if (default_adjust != NULL) {
-		switch (default_adjust->out_color_space) {
-		case COLOR_SPACE_SRGB:
-		case COLOR_SPACE_2020_RGB_FULLRANGE:
-			ocsc_mode = 0;
-			break;
-		case COLOR_SPACE_SRGB_LIMITED:
-		case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
-			ocsc_mode = 1;
-			break;
-		case COLOR_SPACE_YCBCR601:
-		case COLOR_SPACE_YCBCR601_LIMITED:
-			ocsc_mode = 2;
-			break;
-		case COLOR_SPACE_YCBCR709:
-		case COLOR_SPACE_YCBCR709_LIMITED:
-		case COLOR_SPACE_2020_YCBCR:
-			ocsc_mode = 3;
-			break;
-		case COLOR_SPACE_UNKNOWN:
-		default:
-			break;
-		}
-	}
-
-	REG_SET(CM_OCSC_CONTROL, 0, CM_OCSC_MODE, ocsc_mode);
-
-}
-
-static void dpp1_cm_get_reg_field(
-		struct dcn10_dpp *dpp,
-		struct xfer_func_reg *reg)
-{
-	reg->shifts.exp_region0_lut_offset = dpp->tf_shift->CM_RGAM_RAMA_EXP_REGION0_LUT_OFFSET;
-	reg->masks.exp_region0_lut_offset = dpp->tf_mask->CM_RGAM_RAMA_EXP_REGION0_LUT_OFFSET;
-	reg->shifts.exp_region0_num_segments = dpp->tf_shift->CM_RGAM_RAMA_EXP_REGION0_NUM_SEGMENTS;
-	reg->masks.exp_region0_num_segments = dpp->tf_mask->CM_RGAM_RAMA_EXP_REGION0_NUM_SEGMENTS;
-	reg->shifts.exp_region1_lut_offset = dpp->tf_shift->CM_RGAM_RAMA_EXP_REGION1_LUT_OFFSET;
-	reg->masks.exp_region1_lut_offset = dpp->tf_mask->CM_RGAM_RAMA_EXP_REGION1_LUT_OFFSET;
-	reg->shifts.exp_region1_num_segments = dpp->tf_shift->CM_RGAM_RAMA_EXP_REGION1_NUM_SEGMENTS;
-	reg->masks.exp_region1_num_segments = dpp->tf_mask->CM_RGAM_RAMA_EXP_REGION1_NUM_SEGMENTS;
-
-	reg->shifts.field_region_end = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_END_B;
-	reg->masks.field_region_end = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_END_B;
-	reg->shifts.field_region_end_slope = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_END_SLOPE_B;
-	reg->masks.field_region_end_slope = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_END_SLOPE_B;
-	reg->shifts.field_region_end_base = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_END_BASE_B;
-	reg->masks.field_region_end_base = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_END_BASE_B;
-	reg->shifts.field_region_linear_slope = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_LINEAR_SLOPE_B;
-	reg->masks.field_region_linear_slope = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_LINEAR_SLOPE_B;
-	reg->shifts.exp_region_start = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_START_B;
-	reg->masks.exp_region_start = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_START_B;
-	reg->shifts.exp_resion_start_segment = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_START_SEGMENT_B;
-	reg->masks.exp_resion_start_segment = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_START_SEGMENT_B;
-}
-
 static void dpp1_cm_program_color_matrix(
 		struct dcn10_dpp *dpp,
-		const struct out_csc_color_matrix *tbl_entry)
+		const uint16_t *regval)
 {
 	uint32_t mode;
 	struct color_matrices_reg gam_regs;
 
 	REG_GET(CM_OCSC_CONTROL, CM_OCSC_MODE, &mode);
 
-	if (tbl_entry == NULL) {
+	if (regval == NULL) {
 		BREAK_TO_DEBUGGER();
 		return;
 	}
-
+	mode = 4;
 	gam_regs.shifts.csc_c11 = dpp->tf_shift->CM_OCSC_C11;
 	gam_regs.masks.csc_c11  = dpp->tf_mask->CM_OCSC_C11;
 	gam_regs.shifts.csc_c12 = dpp->tf_shift->CM_OCSC_C12;
@@ -313,7 +249,7 @@ static void dpp1_cm_program_color_matrix(
 
 		cm_helper_program_color_matrices(
 				dpp->base.ctx,
-				tbl_entry->regval,
+				regval,
 				&gam_regs);
 
 	} else {
@@ -323,78 +259,91 @@ static void dpp1_cm_program_color_matrix(
 
 		cm_helper_program_color_matrices(
 				dpp->base.ctx,
-				tbl_entry->regval,
+				regval,
 				&gam_regs);
 	}
 }
 
-void dpp1_cm_set_output_csc_adjustment(
+void dpp1_cm_set_output_csc_default(
 		struct dpp *dpp_base,
-		const struct out_csc_color_matrix *tbl_entry)
+		enum dc_color_space colorspace)
 {
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
-	//enum csc_color_mode config = CSC_COLOR_MODE_GRAPHICS_OUTPUT_CSC;
+	const uint16_t *regval = NULL;
+	int arr_size;
 	uint32_t ocsc_mode = 4;
 
-	/**
-	*if (tbl_entry != NULL) {
-	*	switch (tbl_entry->color_space) {
-	*	case COLOR_SPACE_SRGB:
-	*	case COLOR_SPACE_2020_RGB_FULLRANGE:
-	*		ocsc_mode = 0;
-	*		break;
-	*	case COLOR_SPACE_SRGB_LIMITED:
-	*	case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
-	*		ocsc_mode = 1;
-	*		break;
-	*	case COLOR_SPACE_YCBCR601:
-	*	case COLOR_SPACE_YCBCR601_LIMITED:
-	*		ocsc_mode = 2;
-	*		break;
-	*	case COLOR_SPACE_YCBCR709:
-	*	case COLOR_SPACE_YCBCR709_LIMITED:
-	*	case COLOR_SPACE_2020_YCBCR:
-	*		ocsc_mode = 3;
-	*		break;
-	*	case COLOR_SPACE_UNKNOWN:
-	*	default:
-	*		break;
-	*	}
-	*}
-	*/
+	regval = find_color_matrix(colorspace, &arr_size);
+	if (regval == NULL) {
+		BREAK_TO_DEBUGGER();
+		return;
+	}
+	dpp1_cm_program_color_matrix(dpp, regval);
+	REG_SET(CM_OCSC_CONTROL, 0, CM_OCSC_MODE, ocsc_mode);
+}
+
+static void dpp1_cm_get_reg_field(
+		struct dcn10_dpp *dpp,
+		struct xfer_func_reg *reg)
+{
+	reg->shifts.exp_region0_lut_offset = dpp->tf_shift->CM_RGAM_RAMA_EXP_REGION0_LUT_OFFSET;
+	reg->masks.exp_region0_lut_offset = dpp->tf_mask->CM_RGAM_RAMA_EXP_REGION0_LUT_OFFSET;
+	reg->shifts.exp_region0_num_segments = dpp->tf_shift->CM_RGAM_RAMA_EXP_REGION0_NUM_SEGMENTS;
+	reg->masks.exp_region0_num_segments = dpp->tf_mask->CM_RGAM_RAMA_EXP_REGION0_NUM_SEGMENTS;
+	reg->shifts.exp_region1_lut_offset = dpp->tf_shift->CM_RGAM_RAMA_EXP_REGION1_LUT_OFFSET;
+	reg->masks.exp_region1_lut_offset = dpp->tf_mask->CM_RGAM_RAMA_EXP_REGION1_LUT_OFFSET;
+	reg->shifts.exp_region1_num_segments = dpp->tf_shift->CM_RGAM_RAMA_EXP_REGION1_NUM_SEGMENTS;
+	reg->masks.exp_region1_num_segments = dpp->tf_mask->CM_RGAM_RAMA_EXP_REGION1_NUM_SEGMENTS;
 
+	reg->shifts.field_region_end = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_END_B;
+	reg->masks.field_region_end = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_END_B;
+	reg->shifts.field_region_end_slope = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_END_SLOPE_B;
+	reg->masks.field_region_end_slope = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_END_SLOPE_B;
+	reg->shifts.field_region_end_base = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_END_BASE_B;
+	reg->masks.field_region_end_base = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_END_BASE_B;
+	reg->shifts.field_region_linear_slope = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_LINEAR_SLOPE_B;
+	reg->masks.field_region_linear_slope = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_LINEAR_SLOPE_B;
+	reg->shifts.exp_region_start = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_START_B;
+	reg->masks.exp_region_start = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_START_B;
+	reg->shifts.exp_resion_start_segment = dpp->tf_shift->CM_RGAM_RAMB_EXP_REGION_START_SEGMENT_B;
+	reg->masks.exp_resion_start_segment = dpp->tf_mask->CM_RGAM_RAMB_EXP_REGION_START_SEGMENT_B;
+}
+
+void dpp1_cm_set_output_csc_adjustment(
+		struct dpp *dpp_base,
+		const uint16_t *regval)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+	uint32_t ocsc_mode = 4;
+	dpp1_cm_program_color_matrix(dpp, regval);
 	REG_SET(CM_OCSC_CONTROL, 0, CM_OCSC_MODE, ocsc_mode);
-	dpp1_cm_program_color_matrix(dpp, tbl_entry);
 }
 
-void dpp1_cm_power_on_regamma_lut(
-	struct dpp *dpp_base,
-	bool power_on)
+void dpp1_cm_power_on_regamma_lut(struct dpp *dpp_base,
+				  bool power_on)
 {
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
 	REG_SET(CM_MEM_PWR_CTRL, 0,
-			RGAM_MEM_PWR_FORCE, power_on == true ? 0:1);
+		RGAM_MEM_PWR_FORCE, power_on == true ? 0:1);
 
 }
 
-void dpp1_cm_program_regamma_lut(
-		struct dpp *dpp_base,
-		const struct pwl_result_data *rgb,
-		uint32_t num)
+void dpp1_cm_program_regamma_lut(struct dpp *dpp_base,
+				 const struct pwl_result_data *rgb,
+				 uint32_t num)
 {
 	uint32_t i;
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
 	for (i = 0 ; i < num; i++) {
 		REG_SET(CM_RGAM_LUT_DATA, 0, CM_RGAM_LUT_DATA, rgb[i].red_reg);
 		REG_SET(CM_RGAM_LUT_DATA, 0, CM_RGAM_LUT_DATA, rgb[i].green_reg);
 		REG_SET(CM_RGAM_LUT_DATA, 0, CM_RGAM_LUT_DATA, rgb[i].blue_reg);
 
-		REG_SET(CM_RGAM_LUT_DATA, 0,
-				CM_RGAM_LUT_DATA, rgb[i].delta_red_reg);
-		REG_SET(CM_RGAM_LUT_DATA, 0,
-				CM_RGAM_LUT_DATA, rgb[i].delta_green_reg);
-		REG_SET(CM_RGAM_LUT_DATA, 0,
-				CM_RGAM_LUT_DATA, rgb[i].delta_blue_reg);
+		REG_SET(CM_RGAM_LUT_DATA, 0, CM_RGAM_LUT_DATA, rgb[i].delta_red_reg);
+		REG_SET(CM_RGAM_LUT_DATA, 0, CM_RGAM_LUT_DATA, rgb[i].delta_green_reg);
+		REG_SET(CM_RGAM_LUT_DATA, 0, CM_RGAM_LUT_DATA, rgb[i].delta_blue_reg);
 
 	}
 
@@ -473,7 +422,8 @@ void dpp1_cm_program_regamma_lutb_settings(
 void dpp1_program_input_csc(
 		struct dpp *dpp_base,
 		enum dc_color_space color_space,
-		enum dcn10_input_csc_select select)
+		enum dcn10_input_csc_select select,
+		const struct out_csc_color_matrix *tbl_entry)
 {
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
 	int i;
@@ -487,15 +437,19 @@ void dpp1_program_input_csc(
 		return;
 	}
 
-	for (i = 0; i < arr_size; i++)
-		if (dcn10_input_csc_matrix[i].color_space == color_space) {
-			regval = dcn10_input_csc_matrix[i].regval;
-			break;
+	if (tbl_entry == NULL) {
+		for (i = 0; i < arr_size; i++)
+			if (dcn10_input_csc_matrix[i].color_space == color_space) {
+				regval = dcn10_input_csc_matrix[i].regval;
+				break;
+			}
+
+		if (regval == NULL) {
+			BREAK_TO_DEBUGGER();
+			return;
 		}
-
-	if (regval == NULL) {
-		BREAK_TO_DEBUGGER();
-		return;
+	} else {
+		regval = tbl_entry->regval;
 	}
 
 	if (select == INPUT_CSC_SELECT_COMA)
@@ -530,6 +484,27 @@ void dpp1_program_input_csc(
 	}
 }
 
+//keep here for now, decide multi dce support later
+void dpp1_program_bias_and_scale(
+	struct dpp *dpp_base,
+	struct dc_bias_and_scale *params)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	REG_SET_2(CM_BNS_VALUES_R, 0,
+		CM_BNS_SCALE_R, params->scale_red,
+		CM_BNS_BIAS_R, params->bias_red);
+
+	REG_SET_2(CM_BNS_VALUES_G, 0,
+		CM_BNS_SCALE_G, params->scale_green,
+		CM_BNS_BIAS_G, params->bias_green);
+
+	REG_SET_2(CM_BNS_VALUES_B, 0,
+		CM_BNS_SCALE_B, params->scale_blue,
+		CM_BNS_BIAS_B, params->bias_blue);
+
+}
+
 /*program de gamma RAM B*/
 void dpp1_program_degamma_lutb_settings(
 		struct dpp *dpp_base,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
index cbad36410b32..3eb824debf43 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
@@ -648,6 +648,13 @@ void dpp1_dscl_set_scaler_manual_scale(
 	bool ycbcr = scl_data->format >= PIXEL_FORMAT_VIDEO_BEGIN
 				&& scl_data->format <= PIXEL_FORMAT_VIDEO_END;
 
+	if (memcmp(&dpp->scl_data, scl_data, sizeof(*scl_data)) == 0)
+		return;
+
+	PERF_TRACE();
+
+	dpp->scl_data = *scl_data;
+
 	/* Recout */
 	dpp1_dscl_set_recout(dpp, &scl_data->recout);
 
@@ -699,4 +706,5 @@ void dpp1_dscl_set_scaler_manual_scale(
 		SCL_H_NUM_TAPS_C, scl_data->taps.h_taps_c - 1);
 
 	dpp1_dscl_set_scl_filter(dpp, scl_data, ycbcr);
+	PERF_TRACE();
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
new file mode 100644
index 000000000000..eb8317187f30
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -0,0 +1,516 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dm_services.h"
+#include "dcn10_hubp.h"
+#include "dcn10_hubbub.h"
+#include "reg_helper.h"
+
+#define CTX \
+	hubbub->ctx
+#define REG(reg)\
+	hubbub->regs->reg
+
+#undef FN
+#define FN(reg_name, field_name) \
+	hubbub->shifts->field_name, hubbub->masks->field_name
+
+void hubbub1_wm_read_state(struct hubbub *hubbub,
+		struct dcn_hubbub_wm *wm)
+{
+	struct dcn_hubbub_wm_set *s;
+
+	memset(wm, 0, sizeof(struct dcn_hubbub_wm));
+
+	s = &wm->sets[0];
+	s->wm_set = 0;
+	s->data_urgent = REG_READ(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A);
+	s->pte_meta_urgent = REG_READ(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A);
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A)) {
+		s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A);
+		s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A);
+	}
+	s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A);
+
+	s = &wm->sets[1];
+	s->wm_set = 1;
+	s->data_urgent = REG_READ(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B);
+	s->pte_meta_urgent = REG_READ(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B);
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B)) {
+		s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B);
+		s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B);
+	}
+	s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B);
+
+	s = &wm->sets[2];
+	s->wm_set = 2;
+	s->data_urgent = REG_READ(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C);
+	s->pte_meta_urgent = REG_READ(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C);
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C)) {
+		s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C);
+		s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C);
+	}
+	s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C);
+
+	s = &wm->sets[3];
+	s->wm_set = 3;
+	s->data_urgent = REG_READ(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D);
+	s->pte_meta_urgent = REG_READ(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D);
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D)) {
+		s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D);
+		s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D);
+	}
+	s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D);
+}
+
+bool hubbub1_verify_allow_pstate_change_high(
+	struct hubbub *hubbub)
+{
+	/* pstate latency is ~20us so if we wait over 40us and pstate allow
+	 * still not asserted, we are probably stuck and going to hang
+	 *
+	 * TODO: Figure out why it takes ~100us on linux
+	 * pstate takes around ~100us on linux. Unknown currently as to
+	 * why it takes that long on linux
+	 */
+	static unsigned int pstate_wait_timeout_us = 200;
+	static unsigned int pstate_wait_expected_timeout_us = 40;
+	static unsigned int max_sampled_pstate_wait_us; /* data collection */
+	static bool forced_pstate_allow; /* help with revert wa */
+
+	unsigned int debug_index = 0x7;
+	unsigned int debug_data;
+	unsigned int i;
+
+	if (forced_pstate_allow) {
+		/* we hacked to force pstate allow to prevent hang last time
+		 * we verify_allow_pstate_change_high.  so disable force
+		 * here so we can check status
+		 */
+		REG_UPDATE_2(DCHUBBUB_ARB_DRAM_STATE_CNTL,
+			     DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_VALUE, 0,
+			     DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_ENABLE, 0);
+		forced_pstate_allow = false;
+	}
+
+	/* description "3-0:   Pipe0 cursor0 QOS
+	 * 7-4:   Pipe1 cursor0 QOS
+	 * 11-8:  Pipe2 cursor0 QOS
+	 * 15-12: Pipe3 cursor0 QOS
+	 * 16:    Pipe0 Plane0 Allow Pstate Change
+	 * 17:    Pipe1 Plane0 Allow Pstate Change
+	 * 18:    Pipe2 Plane0 Allow Pstate Change
+	 * 19:    Pipe3 Plane0 Allow Pstate Change
+	 * 20:    Pipe0 Plane1 Allow Pstate Change
+	 * 21:    Pipe1 Plane1 Allow Pstate Change
+	 * 22:    Pipe2 Plane1 Allow Pstate Change
+	 * 23:    Pipe3 Plane1 Allow Pstate Change
+	 * 24:    Pipe0 cursor0 Allow Pstate Change
+	 * 25:    Pipe1 cursor0 Allow Pstate Change
+	 * 26:    Pipe2 cursor0 Allow Pstate Change
+	 * 27:    Pipe3 cursor0 Allow Pstate Change
+	 * 28:    WB0 Allow Pstate Change
+	 * 29:    WB1 Allow Pstate Change
+	 * 30:    Arbiter's allow_pstate_change
+	 * 31:    SOC pstate change request
+	 */
+
+	REG_WRITE(DCHUBBUB_TEST_DEBUG_INDEX, debug_index);
+
+	for (i = 0; i < pstate_wait_timeout_us; i++) {
+		debug_data = REG_READ(DCHUBBUB_TEST_DEBUG_DATA);
+
+		if (debug_data & (1 << 30)) {
+
+			if (i > pstate_wait_expected_timeout_us)
+				dm_logger_write(hubbub->ctx->logger, LOG_WARNING,
+						"pstate took longer than expected ~%dus\n",
+						i);
+
+			return true;
+		}
+		if (max_sampled_pstate_wait_us < i)
+			max_sampled_pstate_wait_us = i;
+
+		udelay(1);
+	}
+
+	/* force pstate allow to prevent system hang
+	 * and break to debugger to investigate
+	 */
+	REG_UPDATE_2(DCHUBBUB_ARB_DRAM_STATE_CNTL,
+		     DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_VALUE, 1,
+		     DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_ENABLE, 1);
+	forced_pstate_allow = true;
+
+	dm_logger_write(hubbub->ctx->logger, LOG_WARNING,
+			"pstate TEST_DEBUG_DATA: 0x%X\n",
+			debug_data);
+
+	return false;
+}
+
+static uint32_t convert_and_clamp(
+	uint32_t wm_ns,
+	uint32_t refclk_mhz,
+	uint32_t clamp_value)
+{
+	uint32_t ret_val = 0;
+	ret_val = wm_ns * refclk_mhz;
+	ret_val /= 1000;
+
+	if (ret_val > clamp_value)
+		ret_val = clamp_value;
+
+	return ret_val;
+}
+
+
+void hubbub1_program_watermarks(
+		struct hubbub *hubbub,
+		struct dcn_watermark_set *watermarks,
+		unsigned int refclk_mhz)
+{
+	uint32_t force_en = hubbub->ctx->dc->debug.disable_stutter ? 1 : 0;
+	/*
+	 * Need to clamp to max of the register values (i.e. no wrap)
+	 * for dcn1, all wm registers are 21-bit wide
+	 */
+	uint32_t prog_wm_value;
+
+	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
+			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 0);
+
+	/* Repeat for water mark set A, B, C and D. */
+	/* clock state A */
+	prog_wm_value = convert_and_clamp(watermarks->a.urgent_ns,
+			refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A, prog_wm_value);
+
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"URGENCY_WATERMARK_A calculated =%d\n"
+		"HW register value = 0x%x\n",
+		watermarks->a.urgent_ns, prog_wm_value);
+
+	prog_wm_value = convert_and_clamp(watermarks->a.pte_meta_urgent_ns,
+			refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A, prog_wm_value);
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"PTE_META_URGENCY_WATERMARK_A calculated =%d\n"
+		"HW register value = 0x%x\n",
+		watermarks->a.pte_meta_urgent_ns, prog_wm_value);
+
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A)) {
+		prog_wm_value = convert_and_clamp(
+				watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A, prog_wm_value);
+		dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+			"SR_ENTER_EXIT_WATERMARK_A calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+
+
+		prog_wm_value = convert_and_clamp(
+				watermarks->a.cstate_pstate.cstate_exit_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A, prog_wm_value);
+		dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+			"SR_EXIT_WATERMARK_A calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->a.cstate_pstate.cstate_exit_ns, prog_wm_value);
+	}
+
+	prog_wm_value = convert_and_clamp(
+			watermarks->a.cstate_pstate.pstate_change_ns,
+			refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, prog_wm_value);
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"DRAM_CLK_CHANGE_WATERMARK_A calculated =%d\n"
+		"HW register value = 0x%x\n\n",
+		watermarks->a.cstate_pstate.pstate_change_ns, prog_wm_value);
+
+
+	/* clock state B */
+	prog_wm_value = convert_and_clamp(
+			watermarks->b.urgent_ns, refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B, prog_wm_value);
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"URGENCY_WATERMARK_B calculated =%d\n"
+		"HW register value = 0x%x\n",
+		watermarks->b.urgent_ns, prog_wm_value);
+
+
+	prog_wm_value = convert_and_clamp(
+			watermarks->b.pte_meta_urgent_ns,
+			refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B, prog_wm_value);
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"PTE_META_URGENCY_WATERMARK_B calculated =%d\n"
+		"HW register value = 0x%x\n",
+		watermarks->b.pte_meta_urgent_ns, prog_wm_value);
+
+
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B)) {
+		prog_wm_value = convert_and_clamp(
+				watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B, prog_wm_value);
+		dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+			"SR_ENTER_WATERMARK_B calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+
+
+		prog_wm_value = convert_and_clamp(
+				watermarks->b.cstate_pstate.cstate_exit_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B, prog_wm_value);
+		dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+			"SR_EXIT_WATERMARK_B calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->b.cstate_pstate.cstate_exit_ns, prog_wm_value);
+	}
+
+	prog_wm_value = convert_and_clamp(
+			watermarks->b.cstate_pstate.pstate_change_ns,
+			refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, prog_wm_value);
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"DRAM_CLK_CHANGE_WATERMARK_B calculated =%d\n\n"
+		"HW register value = 0x%x\n",
+		watermarks->b.cstate_pstate.pstate_change_ns, prog_wm_value);
+
+	/* clock state C */
+	prog_wm_value = convert_and_clamp(
+			watermarks->c.urgent_ns, refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C, prog_wm_value);
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"URGENCY_WATERMARK_C calculated =%d\n"
+		"HW register value = 0x%x\n",
+		watermarks->c.urgent_ns, prog_wm_value);
+
+
+	prog_wm_value = convert_and_clamp(
+			watermarks->c.pte_meta_urgent_ns,
+			refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C, prog_wm_value);
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"PTE_META_URGENCY_WATERMARK_C calculated =%d\n"
+		"HW register value = 0x%x\n",
+		watermarks->c.pte_meta_urgent_ns, prog_wm_value);
+
+
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C)) {
+		prog_wm_value = convert_and_clamp(
+				watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C, prog_wm_value);
+		dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+			"SR_ENTER_WATERMARK_C calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+
+
+		prog_wm_value = convert_and_clamp(
+				watermarks->c.cstate_pstate.cstate_exit_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C, prog_wm_value);
+		dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+			"SR_EXIT_WATERMARK_C calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->c.cstate_pstate.cstate_exit_ns, prog_wm_value);
+	}
+
+	prog_wm_value = convert_and_clamp(
+			watermarks->c.cstate_pstate.pstate_change_ns,
+			refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, prog_wm_value);
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"DRAM_CLK_CHANGE_WATERMARK_C calculated =%d\n\n"
+		"HW register value = 0x%x\n",
+		watermarks->c.cstate_pstate.pstate_change_ns, prog_wm_value);
+
+	/* clock state D */
+	prog_wm_value = convert_and_clamp(
+			watermarks->d.urgent_ns, refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D, prog_wm_value);
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"URGENCY_WATERMARK_D calculated =%d\n"
+		"HW register value = 0x%x\n",
+		watermarks->d.urgent_ns, prog_wm_value);
+
+	prog_wm_value = convert_and_clamp(
+			watermarks->d.pte_meta_urgent_ns,
+			refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D, prog_wm_value);
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"PTE_META_URGENCY_WATERMARK_D calculated =%d\n"
+		"HW register value = 0x%x\n",
+		watermarks->d.pte_meta_urgent_ns, prog_wm_value);
+
+
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D)) {
+		prog_wm_value = convert_and_clamp(
+				watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D, prog_wm_value);
+		dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+			"SR_ENTER_WATERMARK_D calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+
+
+		prog_wm_value = convert_and_clamp(
+				watermarks->d.cstate_pstate.cstate_exit_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D, prog_wm_value);
+		dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+			"SR_EXIT_WATERMARK_D calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->d.cstate_pstate.cstate_exit_ns, prog_wm_value);
+	}
+
+
+	prog_wm_value = convert_and_clamp(
+			watermarks->d.cstate_pstate.pstate_change_ns,
+			refclk_mhz, 0x1fffff);
+	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, prog_wm_value);
+	dm_logger_write(hubbub->ctx->logger, LOG_BANDWIDTH_CALCS,
+		"DRAM_CLK_CHANGE_WATERMARK_D calculated =%d\n"
+		"HW register value = 0x%x\n\n",
+		watermarks->d.cstate_pstate.pstate_change_ns, prog_wm_value);
+
+	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
+			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 1);
+
+	REG_UPDATE(DCHUBBUB_ARB_SAT_LEVEL,
+			DCHUBBUB_ARB_SAT_LEVEL, 60 * refclk_mhz);
+	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND,
+			DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 68);
+
+	REG_UPDATE_2(DCHUBBUB_ARB_DRAM_STATE_CNTL,
+			DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_VALUE, 0,
+			DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_ENABLE, force_en);
+
+#if 0
+	REG_UPDATE_2(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
+			DCHUBBUB_ARB_WATERMARK_CHANGE_DONE_INTERRUPT_DISABLE, 1,
+			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 1);
+#endif
+}
+
+void hubbub1_update_dchub(
+	struct hubbub *hubbub,
+	struct dchub_init_data *dh_data)
+{
+	/* TODO: port code from dal2 */
+	switch (dh_data->fb_mode) {
+	case FRAME_BUFFER_MODE_ZFB_ONLY:
+		/*For ZFB case need to put DCHUB FB BASE and TOP upside down to indicate ZFB mode*/
+		REG_UPDATE(DCHUBBUB_SDPIF_FB_TOP,
+				SDPIF_FB_TOP, 0);
+
+		REG_UPDATE(DCHUBBUB_SDPIF_FB_BASE,
+				SDPIF_FB_BASE, 0x0FFFF);
+
+		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BASE,
+				SDPIF_AGP_BASE, dh_data->zfb_phys_addr_base >> 22);
+
+		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BOT,
+				SDPIF_AGP_BOT, dh_data->zfb_mc_base_addr >> 22);
+
+		REG_UPDATE(DCHUBBUB_SDPIF_AGP_TOP,
+				SDPIF_AGP_TOP, (dh_data->zfb_mc_base_addr +
+						dh_data->zfb_size_in_byte - 1) >> 22);
+		break;
+	case FRAME_BUFFER_MODE_MIXED_ZFB_AND_LOCAL:
+		/*Should not touch FB LOCATION (done by VBIOS on AsicInit table)*/
+
+		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BASE,
+				SDPIF_AGP_BASE, dh_data->zfb_phys_addr_base >> 22);
+
+		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BOT,
+				SDPIF_AGP_BOT, dh_data->zfb_mc_base_addr >> 22);
+
+		REG_UPDATE(DCHUBBUB_SDPIF_AGP_TOP,
+				SDPIF_AGP_TOP, (dh_data->zfb_mc_base_addr +
+						dh_data->zfb_size_in_byte - 1) >> 22);
+		break;
+	case FRAME_BUFFER_MODE_LOCAL_ONLY:
+		/*Should not touch FB LOCATION (done by VBIOS on AsicInit table)*/
+		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BASE,
+				SDPIF_AGP_BASE, 0);
+
+		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BOT,
+				SDPIF_AGP_BOT, 0X03FFFF);
+
+		REG_UPDATE(DCHUBBUB_SDPIF_AGP_TOP,
+				SDPIF_AGP_TOP, 0);
+		break;
+	default:
+		break;
+	}
+
+	dh_data->dchub_initialzied = true;
+	dh_data->dchub_info_valid = false;
+}
+
+void hubbub1_toggle_watermark_change_req(struct hubbub *hubbub)
+{
+	uint32_t watermark_change_req;
+
+	REG_GET(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
+			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, &watermark_change_req);
+
+	if (watermark_change_req)
+		watermark_change_req = 0;
+	else
+		watermark_change_req = 1;
+
+	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
+			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, watermark_change_req);
+}
+
+static const struct hubbub_funcs hubbub1_funcs = {
+	.update_dchub = hubbub1_update_dchub
+};
+
+void hubbub1_construct(struct hubbub *hubbub,
+	struct dc_context *ctx,
+	const struct dcn_hubbub_registers *hubbub_regs,
+	const struct dcn_hubbub_shift *hubbub_shift,
+	const struct dcn_hubbub_mask *hubbub_mask)
+{
+	hubbub->ctx = ctx;
+
+	hubbub->funcs = &hubbub1_funcs;
+
+	hubbub->regs = hubbub_regs;
+	hubbub->shifts = hubbub_shift;
+	hubbub->masks = hubbub_mask;
+
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
new file mode 100644
index 000000000000..d5c97844312f
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
@@ -0,0 +1,214 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_HUBBUB_DCN10_H__
+#define __DC_HUBBUB_DCN10_H__
+
+#include "core_types.h"
+
+#define HUBHUB_REG_LIST_DCN()\
+	SR(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A),\
+	SR(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A),\
+	SR(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A),\
+	SR(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B),\
+	SR(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B),\
+	SR(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B),\
+	SR(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C),\
+	SR(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C),\
+	SR(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C),\
+	SR(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D),\
+	SR(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D),\
+	SR(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D),\
+	SR(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL),\
+	SR(DCHUBBUB_ARB_DRAM_STATE_CNTL),\
+	SR(DCHUBBUB_ARB_SAT_LEVEL),\
+	SR(DCHUBBUB_ARB_DF_REQ_OUTSTAND),\
+	SR(DCHUBBUB_GLOBAL_TIMER_CNTL), \
+	SR(DCHUBBUB_TEST_DEBUG_INDEX), \
+	SR(DCHUBBUB_TEST_DEBUG_DATA)
+
+#define HUBBUB_SR_WATERMARK_REG_LIST()\
+	SR(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A),\
+	SR(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A),\
+	SR(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B),\
+	SR(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B),\
+	SR(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C),\
+	SR(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C),\
+	SR(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D),\
+	SR(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D)
+
+#define HUBBUB_REG_LIST_DCN10(id)\
+	HUBHUB_REG_LIST_DCN(), \
+	HUBBUB_SR_WATERMARK_REG_LIST(), \
+	SR(DCHUBBUB_SDPIF_FB_TOP),\
+	SR(DCHUBBUB_SDPIF_FB_BASE),\
+	SR(DCHUBBUB_SDPIF_FB_OFFSET),\
+	SR(DCHUBBUB_SDPIF_AGP_BASE),\
+	SR(DCHUBBUB_SDPIF_AGP_BOT),\
+	SR(DCHUBBUB_SDPIF_AGP_TOP)
+
+struct dcn_hubbub_registers {
+	uint32_t DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A;
+	uint32_t DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A;
+	uint32_t DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A;
+	uint32_t DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A;
+	uint32_t DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A;
+	uint32_t DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B;
+	uint32_t DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B;
+	uint32_t DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B;
+	uint32_t DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B;
+	uint32_t DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B;
+	uint32_t DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C;
+	uint32_t DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C;
+	uint32_t DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C;
+	uint32_t DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C;
+	uint32_t DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C;
+	uint32_t DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D;
+	uint32_t DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D;
+	uint32_t DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D;
+	uint32_t DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D;
+	uint32_t DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D;
+	uint32_t DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL;
+	uint32_t DCHUBBUB_ARB_SAT_LEVEL;
+	uint32_t DCHUBBUB_ARB_DF_REQ_OUTSTAND;
+	uint32_t DCHUBBUB_GLOBAL_TIMER_CNTL;
+	uint32_t DCHUBBUB_ARB_DRAM_STATE_CNTL;
+	uint32_t DCHUBBUB_TEST_DEBUG_INDEX;
+	uint32_t DCHUBBUB_TEST_DEBUG_DATA;
+	uint32_t DCHUBBUB_SDPIF_FB_TOP;
+	uint32_t DCHUBBUB_SDPIF_FB_BASE;
+	uint32_t DCHUBBUB_SDPIF_FB_OFFSET;
+	uint32_t DCHUBBUB_SDPIF_AGP_BASE;
+	uint32_t DCHUBBUB_SDPIF_AGP_BOT;
+	uint32_t DCHUBBUB_SDPIF_AGP_TOP;
+	uint32_t DCHUBBUB_CRC_CTRL;
+};
+
+/* set field name */
+#define HUBBUB_SF(reg_name, field_name, post_fix)\
+	.field_name = reg_name ## __ ## field_name ## post_fix
+
+
+#define HUBBUB_MASK_SH_LIST_DCN(mask_sh)\
+		HUBBUB_SF(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL, DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL, DCHUBBUB_ARB_WATERMARK_CHANGE_DONE_INTERRUPT_DISABLE, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_ARB_DRAM_STATE_CNTL, DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_VALUE, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_ARB_DRAM_STATE_CNTL, DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_ENABLE, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_ARB_DRAM_STATE_CNTL, DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_VALUE, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_ARB_DRAM_STATE_CNTL, DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_ENABLE, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_ARB_SAT_LEVEL, DCHUBBUB_ARB_SAT_LEVEL, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_ARB_DF_REQ_OUTSTAND, DCHUBBUB_ARB_MIN_REQ_OUTSTAND, mask_sh)
+
+#define HUBBUB_MASK_SH_LIST_DCN10(mask_sh)\
+		HUBBUB_MASK_SH_LIST_DCN(mask_sh), \
+		HUBBUB_SF(DCHUBBUB_SDPIF_FB_TOP, SDPIF_FB_TOP, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_SDPIF_FB_BASE, SDPIF_FB_BASE, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_SDPIF_FB_OFFSET, SDPIF_FB_OFFSET, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_SDPIF_AGP_BASE, SDPIF_AGP_BASE, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_SDPIF_AGP_BOT, SDPIF_AGP_BOT, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_SDPIF_AGP_TOP, SDPIF_AGP_TOP, mask_sh)
+
+#define DCN_HUBBUB_REG_FIELD_LIST(type) \
+		type DCHUBBUB_GLOBAL_TIMER_ENABLE; \
+		type DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST;\
+		type DCHUBBUB_ARB_WATERMARK_CHANGE_DONE_INTERRUPT_DISABLE;\
+		type DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_VALUE;\
+		type DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_ENABLE;\
+		type DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_VALUE;\
+		type DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_ENABLE;\
+		type DCHUBBUB_ARB_SAT_LEVEL;\
+		type DCHUBBUB_ARB_MIN_REQ_OUTSTAND;\
+		type DCHUBBUB_GLOBAL_TIMER_REFDIV;\
+		type SDPIF_FB_TOP;\
+		type SDPIF_FB_BASE;\
+		type SDPIF_FB_OFFSET;\
+		type SDPIF_AGP_BASE;\
+		type SDPIF_AGP_BOT;\
+		type SDPIF_AGP_TOP
+
+
+struct dcn_hubbub_shift {
+	DCN_HUBBUB_REG_FIELD_LIST(uint8_t);
+};
+
+struct dcn_hubbub_mask {
+	DCN_HUBBUB_REG_FIELD_LIST(uint32_t);
+};
+
+struct dc;
+
+struct dcn_hubbub_wm_set {
+	uint32_t wm_set;
+	uint32_t data_urgent;
+	uint32_t pte_meta_urgent;
+	uint32_t sr_enter;
+	uint32_t sr_exit;
+	uint32_t dram_clk_chanage;
+};
+
+struct dcn_hubbub_wm {
+	struct dcn_hubbub_wm_set sets[4];
+};
+
+struct hubbub_funcs {
+	void (*update_dchub)(
+			struct hubbub *hubbub,
+			struct dchub_init_data *dh_data);
+};
+
+struct hubbub {
+	const struct hubbub_funcs *funcs;
+	struct dc_context *ctx;
+	const struct dcn_hubbub_registers *regs;
+	const struct dcn_hubbub_shift *shifts;
+	const struct dcn_hubbub_mask *masks;
+};
+
+void hubbub1_update_dchub(
+	struct hubbub *hubbub,
+	struct dchub_init_data *dh_data);
+
+bool hubbub1_verify_allow_pstate_change_high(
+	struct hubbub *hubbub);
+
+void hubbub1_program_watermarks(
+		struct hubbub *hubbub,
+		struct dcn_watermark_set *watermarks,
+		unsigned int refclk_mhz);
+
+void hubbub1_toggle_watermark_change_req(
+		struct hubbub *hubbub);
+
+void hubbub1_wm_read_state(struct hubbub *hubbub,
+		struct dcn_hubbub_wm *wm);
+
+void hubbub1_construct(struct hubbub *hubbub,
+	struct dc_context *ctx,
+	const struct dcn_hubbub_registers *hubbub_regs,
+	const struct dcn_hubbub_shift *hubbub_shift,
+	const struct dcn_hubbub_mask *hubbub_mask);
+
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index b13dee64e0ce..585b33384002 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -29,14 +29,14 @@
 #include "dcn10_hubp.h"
 
 #define REG(reg)\
-	hubp1->mi_regs->reg
+	hubp1->hubp_regs->reg
 
 #define CTX \
 	hubp1->base.ctx
 
 #undef FN
 #define FN(reg_name, field_name) \
-	hubp1->mi_shift->field_name, hubp1->mi_mask->field_name
+	hubp1->hubp_shift->field_name, hubp1->hubp_mask->field_name
 
 void hubp1_set_blank(struct hubp *hubp, bool blank)
 {
@@ -48,14 +48,33 @@ void hubp1_set_blank(struct hubp *hubp, bool blank)
 			HUBP_TTU_DISABLE, blank_en);
 
 	if (blank) {
-		REG_WAIT(DCHUBP_CNTL,
-				HUBP_NO_OUTSTANDING_REQ, 1,
-				1, 200);
+		uint32_t reg_val = REG_READ(DCHUBP_CNTL);
+
+		if (reg_val) {
+			/* init sequence workaround: in case HUBP is
+			 * power gated, this wait would timeout.
+			 *
+			 * we just wrote reg_val to non-0, if it stay 0
+			 * it means HUBP is gated
+			 */
+			REG_WAIT(DCHUBP_CNTL,
+					HUBP_NO_OUTSTANDING_REQ, 1,
+					1, 200);
+		}
+
 		hubp->mpcc_id = 0xf;
 		hubp->opp_id = 0xf;
 	}
 }
 
+static void hubp1_disconnect(struct hubp *hubp)
+{
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+
+	REG_UPDATE(DCHUBP_CNTL,
+			HUBP_TTU_DISABLE, 1);
+}
+
 static void hubp1_set_hubp_blank_en(struct hubp *hubp, bool blank)
 {
 	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
@@ -88,10 +107,12 @@ static void hubp1_vready_workaround(struct hubp *hubp,
 }
 
 void hubp1_program_tiling(
-	struct dcn10_hubp *hubp1,
+	struct hubp *hubp,
 	const union dc_tiling_info *info,
 	const enum surface_pixel_format pixel_format)
 {
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+
 	REG_UPDATE_6(DCSURF_ADDR_CONFIG,
 			NUM_PIPES, log_2(info->gfx9.num_pipes),
 			NUM_BANKS, log_2(info->gfx9.num_banks),
@@ -108,13 +129,14 @@ void hubp1_program_tiling(
 }
 
 void hubp1_program_size_and_rotation(
-	struct dcn10_hubp *hubp1,
+	struct hubp *hubp,
 	enum dc_rotation_angle rotation,
 	enum surface_pixel_format format,
 	const union plane_size *plane_size,
 	struct dc_plane_dcc_param *dcc,
 	bool horizontal_mirror)
 {
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
 	uint32_t pitch, meta_pitch, pitch_c, meta_pitch_c, mirror;
 
 	/* Program data and meta surface pitch (calculation from addrlib)
@@ -170,9 +192,10 @@ void hubp1_program_size_and_rotation(
 }
 
 void hubp1_program_pixel_format(
-	struct dcn10_hubp *hubp1,
+	struct hubp *hubp,
 	enum surface_pixel_format format)
 {
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
 	uint32_t red_bar = 3;
 	uint32_t blue_bar = 2;
 
@@ -416,13 +439,11 @@ void hubp1_program_surface_config(
 	struct dc_plane_dcc_param *dcc,
 	bool horizontal_mirror)
 {
-	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
-
 	hubp1_dcc_control(hubp, dcc->enable, dcc->grph.independent_64b_blks);
-	hubp1_program_tiling(hubp1, tiling_info, format);
+	hubp1_program_tiling(hubp, tiling_info, format);
 	hubp1_program_size_and_rotation(
-			hubp1, rotation, format, plane_size, dcc, horizontal_mirror);
-	hubp1_program_pixel_format(hubp1, format);
+			hubp, rotation, format, plane_size, dcc, horizontal_mirror);
+	hubp1_program_pixel_format(hubp, format);
 }
 
 void hubp1_program_requestor(
@@ -757,42 +778,7 @@ void hubp1_read_state(struct dcn10_hubp *hubp1,
 			QoS_LEVEL_HIGH_WM, &s->qos_level_high_wm);
 }
 
-enum cursor_pitch {
-	CURSOR_PITCH_64_PIXELS = 0,
-	CURSOR_PITCH_128_PIXELS,
-	CURSOR_PITCH_256_PIXELS
-};
-
-enum cursor_lines_per_chunk {
-	CURSOR_LINE_PER_CHUNK_2 = 1,
-	CURSOR_LINE_PER_CHUNK_4,
-	CURSOR_LINE_PER_CHUNK_8,
-	CURSOR_LINE_PER_CHUNK_16
-};
-
-static bool ippn10_cursor_program_control(
-		struct dcn10_hubp *hubp1,
-		bool pixel_data_invert,
-		enum dc_cursor_color_format color_format)
-{
-	if (REG(CURSOR_SETTINS))
-		REG_SET_2(CURSOR_SETTINS, 0,
-				/* no shift of the cursor HDL schedule */
-				CURSOR0_DST_Y_OFFSET, 0,
-				 /* used to shift the cursor chunk request deadline */
-				CURSOR0_CHUNK_HDL_ADJUST, 3);
-	else
-		REG_SET_2(CURSOR_SETTINGS, 0,
-				/* no shift of the cursor HDL schedule */
-				CURSOR0_DST_Y_OFFSET, 0,
-				 /* used to shift the cursor chunk request deadline */
-				CURSOR0_CHUNK_HDL_ADJUST, 3);
-
-	return true;
-}
-
-static enum cursor_pitch ippn10_get_cursor_pitch(
-		unsigned int pitch)
+enum cursor_pitch hubp1_get_cursor_pitch(unsigned int pitch)
 {
 	enum cursor_pitch hw_pitch;
 
@@ -815,7 +801,7 @@ static enum cursor_pitch ippn10_get_cursor_pitch(
 	return hw_pitch;
 }
 
-static enum cursor_lines_per_chunk ippn10_get_lines_per_chunk(
+static enum cursor_lines_per_chunk hubp1_get_lines_per_chunk(
 		unsigned int cur_width,
 		enum dc_cursor_color_format format)
 {
@@ -841,8 +827,8 @@ void hubp1_cursor_set_attributes(
 		const struct dc_cursor_attributes *attr)
 {
 	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
-	enum cursor_pitch hw_pitch = ippn10_get_cursor_pitch(attr->pitch);
-	enum cursor_lines_per_chunk lpc = ippn10_get_lines_per_chunk(
+	enum cursor_pitch hw_pitch = hubp1_get_cursor_pitch(attr->pitch);
+	enum cursor_lines_per_chunk lpc = hubp1_get_lines_per_chunk(
 			attr->width, attr->color_format);
 
 	hubp->curs_attr = *attr;
@@ -855,13 +841,17 @@ void hubp1_cursor_set_attributes(
 	REG_UPDATE_2(CURSOR_SIZE,
 			CURSOR_WIDTH, attr->width,
 			CURSOR_HEIGHT, attr->height);
+
 	REG_UPDATE_3(CURSOR_CONTROL,
 			CURSOR_MODE, attr->color_format,
 			CURSOR_PITCH, hw_pitch,
 			CURSOR_LINES_PER_CHUNK, lpc);
-	ippn10_cursor_program_control(hubp1,
-			attr->attribute_flags.bits.INVERT_PIXEL_DATA,
-			attr->color_format);
+
+	REG_SET_2(CURSOR_SETTINS, 0,
+			/* no shift of the cursor HDL schedule */
+			CURSOR0_DST_Y_OFFSET, 0,
+			 /* used to shift the cursor chunk request deadline */
+			CURSOR0_CHUNK_HDL_ADJUST, 3);
 }
 
 void hubp1_cursor_set_position(
@@ -901,7 +891,8 @@ void hubp1_cursor_set_position(
 		cur_en = 0;  /* not visible beyond left edge*/
 
 	if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
-		hubp1_cursor_set_attributes(hubp, &hubp->curs_attr);
+		hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
+
 	REG_UPDATE(CURSOR_CONTROL,
 			CURSOR_ENABLE, cur_en);
 
@@ -933,6 +924,7 @@ static struct hubp_funcs dcn10_hubp_funcs = {
 	.set_hubp_blank_en = hubp1_set_hubp_blank_en,
 	.set_cursor_attributes	= hubp1_cursor_set_attributes,
 	.set_cursor_position	= hubp1_cursor_set_position,
+	.hubp_disconnect = hubp1_disconnect,
 };
 
 /*****************************************/
@@ -943,15 +935,15 @@ void dcn10_hubp_construct(
 	struct dcn10_hubp *hubp1,
 	struct dc_context *ctx,
 	uint32_t inst,
-	const struct dcn_mi_registers *mi_regs,
-	const struct dcn_mi_shift *mi_shift,
-	const struct dcn_mi_mask *mi_mask)
+	const struct dcn_mi_registers *hubp_regs,
+	const struct dcn_mi_shift *hubp_shift,
+	const struct dcn_mi_mask *hubp_mask)
 {
 	hubp1->base.funcs = &dcn10_hubp_funcs;
 	hubp1->base.ctx = ctx;
-	hubp1->mi_regs = mi_regs;
-	hubp1->mi_shift = mi_shift;
-	hubp1->mi_mask = mi_mask;
+	hubp1->hubp_regs = hubp_regs;
+	hubp1->hubp_shift = hubp_shift;
+	hubp1->hubp_mask = hubp_mask;
 	hubp1->base.inst = inst;
 	hubp1->base.opp_id = 0xf;
 	hubp1->base.mpcc_id = 0xf;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
index 66db453c801b..33e91d9c010f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -30,7 +30,7 @@
 #define TO_DCN10_HUBP(hubp)\
 	container_of(hubp, struct dcn10_hubp, base)
 
-#define MI_REG_LIST_DCN(id)\
+#define HUBP_REG_LIST_DCN(id)\
 	SRI(DCHUBP_CNTL, HUBP, id),\
 	SRI(HUBPREQ_DEBUG_DB, HUBP, id),\
 	SRI(DCSURF_ADDR_CONFIG, HUBP, id),\
@@ -98,8 +98,8 @@
 	SRI(DCN_SURF1_TTU_CNTL1, HUBPREQ, id),\
 	SRI(DCN_VM_MX_L1_TLB_CNTL, HUBPREQ, id)
 
-#define MI_REG_LIST_DCN10(id)\
-	MI_REG_LIST_DCN(id),\
+#define HUBP_REG_LIST_DCN10(id)\
+	HUBP_REG_LIST_DCN(id),\
 	SRI(PREFETCH_SETTINS, HUBPREQ, id),\
 	SRI(PREFETCH_SETTINS_C, HUBPREQ, id),\
 	SRI(DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_MSB, HUBPREQ, id),\
@@ -127,277 +127,274 @@
 	SRI(CURSOR_HOT_SPOT, CURSOR, id), \
 	SRI(CURSOR_DST_OFFSET, CURSOR, id)
 
-
-
-struct dcn_mi_registers {
-	uint32_t DCHUBP_CNTL;
-	uint32_t HUBPREQ_DEBUG_DB;
-	uint32_t DCSURF_ADDR_CONFIG;
-	uint32_t DCSURF_TILING_CONFIG;
-	uint32_t DCSURF_SURFACE_PITCH;
-	uint32_t DCSURF_SURFACE_PITCH_C;
-	uint32_t DCSURF_SURFACE_CONFIG;
-	uint32_t DCSURF_FLIP_CONTROL;
-	uint32_t DCSURF_PRI_VIEWPORT_DIMENSION;
-	uint32_t DCSURF_PRI_VIEWPORT_START;
-	uint32_t DCSURF_SEC_VIEWPORT_DIMENSION;
-	uint32_t DCSURF_SEC_VIEWPORT_START;
-	uint32_t DCSURF_PRI_VIEWPORT_DIMENSION_C;
-	uint32_t DCSURF_PRI_VIEWPORT_START_C;
-	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH;
-	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS;
-	uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH;
-	uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS;
-	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH;
-	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS;
-	uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH;
-	uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS;
-	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C;
-	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_C;
-	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C;
-	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_C;
-	uint32_t DCSURF_SURFACE_INUSE;
-	uint32_t DCSURF_SURFACE_INUSE_HIGH;
-	uint32_t DCSURF_SURFACE_INUSE_C;
-	uint32_t DCSURF_SURFACE_INUSE_HIGH_C;
-	uint32_t DCSURF_SURFACE_EARLIEST_INUSE;
-	uint32_t DCSURF_SURFACE_EARLIEST_INUSE_HIGH;
-	uint32_t DCSURF_SURFACE_EARLIEST_INUSE_C;
-	uint32_t DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C;
-	uint32_t DCSURF_SURFACE_CONTROL;
-	uint32_t HUBPRET_CONTROL;
-	uint32_t DCN_EXPANSION_MODE;
-	uint32_t DCHUBP_REQ_SIZE_CONFIG;
-	uint32_t DCHUBP_REQ_SIZE_CONFIG_C;
-	uint32_t BLANK_OFFSET_0;
-	uint32_t BLANK_OFFSET_1;
-	uint32_t DST_DIMENSIONS;
-	uint32_t DST_AFTER_SCALER;
-	uint32_t PREFETCH_SETTINS;
-	uint32_t PREFETCH_SETTINGS;
-	uint32_t VBLANK_PARAMETERS_0;
-	uint32_t REF_FREQ_TO_PIX_FREQ;
-	uint32_t VBLANK_PARAMETERS_1;
-	uint32_t VBLANK_PARAMETERS_3;
-	uint32_t NOM_PARAMETERS_0;
-	uint32_t NOM_PARAMETERS_1;
-	uint32_t NOM_PARAMETERS_4;
-	uint32_t NOM_PARAMETERS_5;
-	uint32_t PER_LINE_DELIVERY_PRE;
-	uint32_t PER_LINE_DELIVERY;
-	uint32_t PREFETCH_SETTINS_C;
-	uint32_t PREFETCH_SETTINGS_C;
-	uint32_t VBLANK_PARAMETERS_2;
-	uint32_t VBLANK_PARAMETERS_4;
-	uint32_t NOM_PARAMETERS_2;
-	uint32_t NOM_PARAMETERS_3;
-	uint32_t NOM_PARAMETERS_6;
-	uint32_t NOM_PARAMETERS_7;
-	uint32_t DCN_TTU_QOS_WM;
-	uint32_t DCN_GLOBAL_TTU_CNTL;
-	uint32_t DCN_SURF0_TTU_CNTL0;
-	uint32_t DCN_SURF0_TTU_CNTL1;
-	uint32_t DCN_SURF1_TTU_CNTL0;
-	uint32_t DCN_SURF1_TTU_CNTL1;
-	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_MSB;
-	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LSB;
-	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_START_ADDR_MSB;
-	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_START_ADDR_LSB;
-	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_END_ADDR_MSB;
-	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_END_ADDR_LSB;
-	uint32_t DCN_VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_MSB;
-	uint32_t DCN_VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_LSB;
-	uint32_t DCN_VM_MX_L1_TLB_CNTL;
-	uint32_t DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB;
-	uint32_t DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB;
-	uint32_t DCN_VM_SYSTEM_APERTURE_LOW_ADDR_MSB;
-	uint32_t DCN_VM_SYSTEM_APERTURE_LOW_ADDR_LSB;
-	uint32_t DCN_VM_SYSTEM_APERTURE_HIGH_ADDR_MSB;
-	uint32_t DCN_VM_SYSTEM_APERTURE_HIGH_ADDR_LSB;
-	uint32_t DCN_VM_SYSTEM_APERTURE_LOW_ADDR;
-	uint32_t DCN_VM_SYSTEM_APERTURE_HIGH_ADDR;
-	uint32_t DCHUBBUB_SDPIF_FB_BASE;
-	uint32_t DCHUBBUB_SDPIF_FB_OFFSET;
-	uint32_t DCN_VM_FB_LOCATION_TOP;
-	uint32_t DCN_VM_FB_LOCATION_BASE;
-	uint32_t DCN_VM_FB_OFFSET;
-	uint32_t DCN_VM_AGP_BASE;
-	uint32_t DCN_VM_AGP_BOT;
-	uint32_t DCN_VM_AGP_TOP;
-	uint32_t CURSOR_SETTINS;
-	uint32_t CURSOR_SETTINGS;
-	uint32_t CURSOR_SURFACE_ADDRESS_HIGH;
-	uint32_t CURSOR_SURFACE_ADDRESS;
-	uint32_t CURSOR_SIZE;
-	uint32_t CURSOR_CONTROL;
-	uint32_t CURSOR_POSITION;
-	uint32_t CURSOR_HOT_SPOT;
-	uint32_t CURSOR_DST_OFFSET;
-};
-
-#define MI_SF(reg_name, field_name, post_fix)\
+#define HUBP_COMMON_REG_VARIABLE_LIST \
+	uint32_t DCHUBP_CNTL; \
+	uint32_t HUBPREQ_DEBUG_DB; \
+	uint32_t DCSURF_ADDR_CONFIG; \
+	uint32_t DCSURF_TILING_CONFIG; \
+	uint32_t DCSURF_SURFACE_PITCH; \
+	uint32_t DCSURF_SURFACE_PITCH_C; \
+	uint32_t DCSURF_SURFACE_CONFIG; \
+	uint32_t DCSURF_FLIP_CONTROL; \
+	uint32_t DCSURF_PRI_VIEWPORT_DIMENSION; \
+	uint32_t DCSURF_PRI_VIEWPORT_START; \
+	uint32_t DCSURF_SEC_VIEWPORT_DIMENSION; \
+	uint32_t DCSURF_SEC_VIEWPORT_START; \
+	uint32_t DCSURF_PRI_VIEWPORT_DIMENSION_C; \
+	uint32_t DCSURF_PRI_VIEWPORT_START_C; \
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH; \
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS; \
+	uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH; \
+	uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS; \
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH; \
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS; \
+	uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH; \
+	uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS; \
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C; \
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_C; \
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C; \
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_C; \
+	uint32_t DCSURF_SURFACE_INUSE; \
+	uint32_t DCSURF_SURFACE_INUSE_HIGH; \
+	uint32_t DCSURF_SURFACE_INUSE_C; \
+	uint32_t DCSURF_SURFACE_INUSE_HIGH_C; \
+	uint32_t DCSURF_SURFACE_EARLIEST_INUSE; \
+	uint32_t DCSURF_SURFACE_EARLIEST_INUSE_HIGH; \
+	uint32_t DCSURF_SURFACE_EARLIEST_INUSE_C; \
+	uint32_t DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C; \
+	uint32_t DCSURF_SURFACE_CONTROL; \
+	uint32_t HUBPRET_CONTROL; \
+	uint32_t DCN_EXPANSION_MODE; \
+	uint32_t DCHUBP_REQ_SIZE_CONFIG; \
+	uint32_t DCHUBP_REQ_SIZE_CONFIG_C; \
+	uint32_t BLANK_OFFSET_0; \
+	uint32_t BLANK_OFFSET_1; \
+	uint32_t DST_DIMENSIONS; \
+	uint32_t DST_AFTER_SCALER; \
+	uint32_t PREFETCH_SETTINS; \
+	uint32_t PREFETCH_SETTINGS; \
+	uint32_t VBLANK_PARAMETERS_0; \
+	uint32_t REF_FREQ_TO_PIX_FREQ; \
+	uint32_t VBLANK_PARAMETERS_1; \
+	uint32_t VBLANK_PARAMETERS_3; \
+	uint32_t NOM_PARAMETERS_0; \
+	uint32_t NOM_PARAMETERS_1; \
+	uint32_t NOM_PARAMETERS_4; \
+	uint32_t NOM_PARAMETERS_5; \
+	uint32_t PER_LINE_DELIVERY_PRE; \
+	uint32_t PER_LINE_DELIVERY; \
+	uint32_t PREFETCH_SETTINS_C; \
+	uint32_t PREFETCH_SETTINGS_C; \
+	uint32_t VBLANK_PARAMETERS_2; \
+	uint32_t VBLANK_PARAMETERS_4; \
+	uint32_t NOM_PARAMETERS_2; \
+	uint32_t NOM_PARAMETERS_3; \
+	uint32_t NOM_PARAMETERS_6; \
+	uint32_t NOM_PARAMETERS_7; \
+	uint32_t DCN_TTU_QOS_WM; \
+	uint32_t DCN_GLOBAL_TTU_CNTL; \
+	uint32_t DCN_SURF0_TTU_CNTL0; \
+	uint32_t DCN_SURF0_TTU_CNTL1; \
+	uint32_t DCN_SURF1_TTU_CNTL0; \
+	uint32_t DCN_SURF1_TTU_CNTL1; \
+	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_MSB; \
+	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LSB; \
+	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_START_ADDR_MSB; \
+	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_START_ADDR_LSB; \
+	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_END_ADDR_MSB; \
+	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_END_ADDR_LSB; \
+	uint32_t DCN_VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_MSB; \
+	uint32_t DCN_VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_LSB; \
+	uint32_t DCN_VM_MX_L1_TLB_CNTL; \
+	uint32_t DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB; \
+	uint32_t DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB; \
+	uint32_t DCN_VM_SYSTEM_APERTURE_LOW_ADDR_MSB; \
+	uint32_t DCN_VM_SYSTEM_APERTURE_LOW_ADDR_LSB; \
+	uint32_t DCN_VM_SYSTEM_APERTURE_HIGH_ADDR_MSB; \
+	uint32_t DCN_VM_SYSTEM_APERTURE_HIGH_ADDR_LSB; \
+	uint32_t DCN_VM_SYSTEM_APERTURE_LOW_ADDR; \
+	uint32_t DCN_VM_SYSTEM_APERTURE_HIGH_ADDR; \
+	uint32_t DCHUBBUB_SDPIF_FB_BASE; \
+	uint32_t DCHUBBUB_SDPIF_FB_OFFSET; \
+	uint32_t DCN_VM_FB_LOCATION_TOP; \
+	uint32_t DCN_VM_FB_LOCATION_BASE; \
+	uint32_t DCN_VM_FB_OFFSET; \
+	uint32_t DCN_VM_AGP_BASE; \
+	uint32_t DCN_VM_AGP_BOT; \
+	uint32_t DCN_VM_AGP_TOP; \
+	uint32_t CURSOR_SETTINS; \
+	uint32_t CURSOR_SETTINGS; \
+	uint32_t CURSOR_SURFACE_ADDRESS_HIGH; \
+	uint32_t CURSOR_SURFACE_ADDRESS; \
+	uint32_t CURSOR_SIZE; \
+	uint32_t CURSOR_CONTROL; \
+	uint32_t CURSOR_POSITION; \
+	uint32_t CURSOR_HOT_SPOT; \
+	uint32_t CURSOR_DST_OFFSET
+
+#define HUBP_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
-#define MI_MASK_SH_LIST_DCN(mask_sh)\
-	MI_SF(HUBP0_DCHUBP_CNTL, HUBP_BLANK_EN, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_CNTL, HUBP_TTU_DISABLE, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_CNTL, HUBP_UNDERFLOW_STATUS, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_CNTL, HUBP_NO_OUTSTANDING_REQ, mask_sh),\
-	MI_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_PIPES, mask_sh),\
-	MI_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_BANKS, mask_sh),\
-	MI_SF(HUBP0_DCSURF_ADDR_CONFIG, PIPE_INTERLEAVE, mask_sh),\
-	MI_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_SE, mask_sh),\
-	MI_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_RB_PER_SE, mask_sh),\
-	MI_SF(HUBP0_DCSURF_ADDR_CONFIG, MAX_COMPRESSED_FRAGS, mask_sh),\
-	MI_SF(HUBP0_DCSURF_TILING_CONFIG, SW_MODE, mask_sh),\
-	MI_SF(HUBP0_DCSURF_TILING_CONFIG, META_LINEAR, mask_sh),\
-	MI_SF(HUBP0_DCSURF_TILING_CONFIG, RB_ALIGNED, mask_sh),\
-	MI_SF(HUBP0_DCSURF_TILING_CONFIG, PIPE_ALIGNED, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_PITCH, PITCH, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_PITCH, META_PITCH, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_PITCH_C, PITCH_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_PITCH_C, META_PITCH_C, mask_sh),\
-	MI_SF(HUBP0_DCSURF_SURFACE_CONFIG, ROTATION_ANGLE, mask_sh),\
-	MI_SF(HUBP0_DCSURF_SURFACE_CONFIG, H_MIRROR_EN, mask_sh),\
-	MI_SF(HUBP0_DCSURF_SURFACE_CONFIG, SURFACE_PIXEL_FORMAT, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_FLIP_TYPE, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_FLIP_PENDING, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_UPDATE_LOCK, mask_sh),\
-	MI_SF(HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_WIDTH, mask_sh),\
-	MI_SF(HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT, mask_sh),\
-	MI_SF(HUBP0_DCSURF_PRI_VIEWPORT_START, PRI_VIEWPORT_X_START, mask_sh),\
-	MI_SF(HUBP0_DCSURF_PRI_VIEWPORT_START, PRI_VIEWPORT_Y_START, mask_sh),\
-	MI_SF(HUBP0_DCSURF_SEC_VIEWPORT_DIMENSION, SEC_VIEWPORT_WIDTH, mask_sh),\
-	MI_SF(HUBP0_DCSURF_SEC_VIEWPORT_DIMENSION, SEC_VIEWPORT_HEIGHT, mask_sh),\
-	MI_SF(HUBP0_DCSURF_SEC_VIEWPORT_START, SEC_VIEWPORT_X_START, mask_sh),\
-	MI_SF(HUBP0_DCSURF_SEC_VIEWPORT_START, SEC_VIEWPORT_Y_START, mask_sh),\
-	MI_SF(HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_C, PRI_VIEWPORT_WIDTH_C, mask_sh),\
-	MI_SF(HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_C, PRI_VIEWPORT_HEIGHT_C, mask_sh),\
-	MI_SF(HUBP0_DCSURF_PRI_VIEWPORT_START_C, PRI_VIEWPORT_X_START_C, mask_sh),\
-	MI_SF(HUBP0_DCSURF_PRI_VIEWPORT_START_C, PRI_VIEWPORT_Y_START_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH, PRIMARY_SURFACE_ADDRESS_HIGH, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS, PRIMARY_SURFACE_ADDRESS, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH, SECONDARY_SURFACE_ADDRESS_HIGH, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SECONDARY_SURFACE_ADDRESS, SECONDARY_SURFACE_ADDRESS, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH, PRIMARY_META_SURFACE_ADDRESS_HIGH, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_PRIMARY_META_SURFACE_ADDRESS, PRIMARY_META_SURFACE_ADDRESS, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH, SECONDARY_META_SURFACE_ADDRESS_HIGH, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SECONDARY_META_SURFACE_ADDRESS, SECONDARY_META_SURFACE_ADDRESS, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C, PRIMARY_SURFACE_ADDRESS_HIGH_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS_C, PRIMARY_SURFACE_ADDRESS_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C, PRIMARY_META_SURFACE_ADDRESS_HIGH_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_PRIMARY_META_SURFACE_ADDRESS_C, PRIMARY_META_SURFACE_ADDRESS_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_INUSE, SURFACE_INUSE_ADDRESS, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_INUSE_HIGH, SURFACE_INUSE_ADDRESS_HIGH, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_INUSE_C, SURFACE_INUSE_ADDRESS_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_INUSE_HIGH_C, SURFACE_INUSE_ADDRESS_HIGH_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_EARLIEST_INUSE, SURFACE_EARLIEST_INUSE_ADDRESS, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_EARLIEST_INUSE_HIGH, SURFACE_EARLIEST_INUSE_ADDRESS_HIGH, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_EARLIEST_INUSE_C, SURFACE_EARLIEST_INUSE_ADDRESS_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C, SURFACE_EARLIEST_INUSE_ADDRESS_HIGH_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, PRIMARY_SURFACE_TMZ, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, PRIMARY_SURFACE_DCC_EN, mask_sh),\
-	MI_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, PRIMARY_SURFACE_DCC_IND_64B_BLK, mask_sh),\
-	MI_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\
-	MI_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\
-	MI_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_EXPANSION_MODE, DRQ_EXPANSION_MODE, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_EXPANSION_MODE, PRQ_EXPANSION_MODE, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_EXPANSION_MODE, MRQ_EXPANSION_MODE, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_EXPANSION_MODE, CRQ_EXPANSION_MODE, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, CHUNK_SIZE, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, MIN_CHUNK_SIZE, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, META_CHUNK_SIZE, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, MIN_META_CHUNK_SIZE, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, DPTE_GROUP_SIZE, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, MPTE_GROUP_SIZE, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, SWATH_HEIGHT, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, PTE_ROW_HEIGHT_LINEAR, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, CHUNK_SIZE_C, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, MIN_CHUNK_SIZE_C, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, META_CHUNK_SIZE_C, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, MIN_META_CHUNK_SIZE_C, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, DPTE_GROUP_SIZE_C, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, MPTE_GROUP_SIZE_C, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, SWATH_HEIGHT_C, mask_sh),\
-	MI_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, PTE_ROW_HEIGHT_LINEAR_C, mask_sh),\
-	MI_SF(HUBPREQ0_BLANK_OFFSET_0, REFCYC_H_BLANK_END, mask_sh),\
-	MI_SF(HUBPREQ0_BLANK_OFFSET_0, DLG_V_BLANK_END, mask_sh),\
-	MI_SF(HUBPREQ0_BLANK_OFFSET_1, MIN_DST_Y_NEXT_START, mask_sh),\
-	MI_SF(HUBPREQ0_DST_DIMENSIONS, REFCYC_PER_HTOTAL, mask_sh),\
-	MI_SF(HUBPREQ0_DST_AFTER_SCALER, REFCYC_X_AFTER_SCALER, mask_sh),\
-	MI_SF(HUBPREQ0_DST_AFTER_SCALER, DST_Y_AFTER_SCALER, mask_sh),\
-	MI_SF(HUBPREQ0_VBLANK_PARAMETERS_0, DST_Y_PER_VM_VBLANK, mask_sh),\
-	MI_SF(HUBPREQ0_VBLANK_PARAMETERS_0, DST_Y_PER_ROW_VBLANK, mask_sh),\
-	MI_SF(HUBPREQ0_REF_FREQ_TO_PIX_FREQ, REF_FREQ_TO_PIX_FREQ, mask_sh),\
-	MI_SF(HUBPREQ0_VBLANK_PARAMETERS_1, REFCYC_PER_PTE_GROUP_VBLANK_L, mask_sh),\
-	MI_SF(HUBPREQ0_VBLANK_PARAMETERS_3, REFCYC_PER_META_CHUNK_VBLANK_L, mask_sh),\
-	MI_SF(HUBPREQ0_NOM_PARAMETERS_0, DST_Y_PER_PTE_ROW_NOM_L, mask_sh),\
-	MI_SF(HUBPREQ0_NOM_PARAMETERS_1, REFCYC_PER_PTE_GROUP_NOM_L, mask_sh),\
-	MI_SF(HUBPREQ0_NOM_PARAMETERS_4, DST_Y_PER_META_ROW_NOM_L, mask_sh),\
-	MI_SF(HUBPREQ0_NOM_PARAMETERS_5, REFCYC_PER_META_CHUNK_NOM_L, mask_sh),\
-	MI_SF(HUBPREQ0_PER_LINE_DELIVERY_PRE, REFCYC_PER_LINE_DELIVERY_PRE_L, mask_sh),\
-	MI_SF(HUBPREQ0_PER_LINE_DELIVERY_PRE, REFCYC_PER_LINE_DELIVERY_PRE_C, mask_sh),\
-	MI_SF(HUBPREQ0_PER_LINE_DELIVERY, REFCYC_PER_LINE_DELIVERY_L, mask_sh),\
-	MI_SF(HUBPREQ0_PER_LINE_DELIVERY, REFCYC_PER_LINE_DELIVERY_C, mask_sh),\
-	MI_SF(HUBPREQ0_VBLANK_PARAMETERS_2, REFCYC_PER_PTE_GROUP_VBLANK_C, mask_sh),\
-	MI_SF(HUBPREQ0_VBLANK_PARAMETERS_4, REFCYC_PER_META_CHUNK_VBLANK_C, mask_sh),\
-	MI_SF(HUBPREQ0_NOM_PARAMETERS_2, DST_Y_PER_PTE_ROW_NOM_C, mask_sh),\
-	MI_SF(HUBPREQ0_NOM_PARAMETERS_3, REFCYC_PER_PTE_GROUP_NOM_C, mask_sh),\
-	MI_SF(HUBPREQ0_NOM_PARAMETERS_6, DST_Y_PER_META_ROW_NOM_C, mask_sh),\
-	MI_SF(HUBPREQ0_NOM_PARAMETERS_7, REFCYC_PER_META_CHUNK_NOM_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_TTU_QOS_WM, QoS_LEVEL_LOW_WM, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_TTU_QOS_WM, QoS_LEVEL_HIGH_WM, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_GLOBAL_TTU_CNTL, MIN_TTU_VBLANK, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_GLOBAL_TTU_CNTL, QoS_LEVEL_FLIP, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_SURF0_TTU_CNTL0, REFCYC_PER_REQ_DELIVERY, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_SURF0_TTU_CNTL0, QoS_LEVEL_FIXED, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_SURF0_TTU_CNTL0, QoS_RAMP_DISABLE, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_SURF0_TTU_CNTL1, REFCYC_PER_REQ_DELIVERY_PRE, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_MX_L1_TLB_CNTL, ENABLE_L1_TLB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_MX_L1_TLB_CNTL, SYSTEM_ACCESS_MODE, mask_sh)
-
-#define MI_MASK_SH_LIST_DCN10(mask_sh)\
-	MI_MASK_SH_LIST_DCN(mask_sh),\
-	MI_SF(HUBPREQ0_PREFETCH_SETTINS, DST_Y_PREFETCH, mask_sh),\
-	MI_SF(HUBPREQ0_PREFETCH_SETTINS, VRATIO_PREFETCH, mask_sh),\
-	MI_SF(HUBPREQ0_PREFETCH_SETTINS_C, VRATIO_PREFETCH_C, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_MSB, VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_MSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LSB, VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_START_ADDR_MSB, VM_CONTEXT0_PAGE_TABLE_START_ADDR_MSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_START_ADDR_LSB, VM_CONTEXT0_PAGE_TABLE_START_ADDR_LSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_END_ADDR_MSB, VM_CONTEXT0_PAGE_TABLE_END_ADDR_MSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_END_ADDR_LSB, VM_CONTEXT0_PAGE_TABLE_END_ADDR_LSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_MSB, VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_MSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_MSB, VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_SYSTEM, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_LSB, VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_LSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_LOW_ADDR_MSB, MC_VM_SYSTEM_APERTURE_LOW_ADDR_MSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_LOW_ADDR_LSB, MC_VM_SYSTEM_APERTURE_LOW_ADDR_LSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_HIGH_ADDR_MSB, MC_VM_SYSTEM_APERTURE_HIGH_ADDR_MSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_HIGH_ADDR_LSB, MC_VM_SYSTEM_APERTURE_HIGH_ADDR_LSB, mask_sh),\
-	MI_SF(DCHUBBUB_SDPIF_FB_BASE, SDPIF_FB_BASE, mask_sh),\
-	MI_SF(DCHUBBUB_SDPIF_FB_OFFSET, SDPIF_FB_OFFSET, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, MC_VM_SYSTEM_APERTURE_DEFAULT_SYSTEM, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, mask_sh),\
-	MI_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, mask_sh),\
-	MI_SF(HUBPREQ0_CURSOR_SETTINS, CURSOR0_DST_Y_OFFSET, mask_sh), \
-	MI_SF(HUBPREQ0_CURSOR_SETTINS, CURSOR0_CHUNK_HDL_ADJUST, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_SURFACE_ADDRESS_HIGH, CURSOR_SURFACE_ADDRESS_HIGH, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_SURFACE_ADDRESS, CURSOR_SURFACE_ADDRESS, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_SIZE, CURSOR_WIDTH, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_SIZE, CURSOR_HEIGHT, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_CONTROL, CURSOR_MODE, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_CONTROL, CURSOR_2X_MAGNIFY, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_CONTROL, CURSOR_PITCH, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_CONTROL, CURSOR_LINES_PER_CHUNK, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_CONTROL, CURSOR_ENABLE, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_POSITION, CURSOR_X_POSITION, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_POSITION, CURSOR_Y_POSITION, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_X, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_Y, mask_sh), \
-	MI_SF(CURSOR0_CURSOR_DST_OFFSET, CURSOR_DST_X_OFFSET, mask_sh)
-
-#define DCN_MI_REG_FIELD_LIST(type) \
+#define HUBP_MASK_SH_LIST_DCN(mask_sh)\
+	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_BLANK_EN, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_TTU_DISABLE, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_UNDERFLOW_STATUS, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_NO_OUTSTANDING_REQ, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_PIPES, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_BANKS, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, PIPE_INTERLEAVE, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_SE, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_RB_PER_SE, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, MAX_COMPRESSED_FRAGS, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_TILING_CONFIG, SW_MODE, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_TILING_CONFIG, META_LINEAR, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_TILING_CONFIG, RB_ALIGNED, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_TILING_CONFIG, PIPE_ALIGNED, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH, PITCH, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH, META_PITCH, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH_C, PITCH_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH_C, META_PITCH_C, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, ROTATION_ANGLE, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, H_MIRROR_EN, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, SURFACE_PIXEL_FORMAT, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_FLIP_TYPE, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_FLIP_PENDING, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_UPDATE_LOCK, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_WIDTH, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_PRI_VIEWPORT_START, PRI_VIEWPORT_X_START, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_PRI_VIEWPORT_START, PRI_VIEWPORT_Y_START, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SEC_VIEWPORT_DIMENSION, SEC_VIEWPORT_WIDTH, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SEC_VIEWPORT_DIMENSION, SEC_VIEWPORT_HEIGHT, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SEC_VIEWPORT_START, SEC_VIEWPORT_X_START, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SEC_VIEWPORT_START, SEC_VIEWPORT_Y_START, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_C, PRI_VIEWPORT_WIDTH_C, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_C, PRI_VIEWPORT_HEIGHT_C, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_PRI_VIEWPORT_START_C, PRI_VIEWPORT_X_START_C, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_PRI_VIEWPORT_START_C, PRI_VIEWPORT_Y_START_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH, PRIMARY_SURFACE_ADDRESS_HIGH, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS, PRIMARY_SURFACE_ADDRESS, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH, SECONDARY_SURFACE_ADDRESS_HIGH, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SECONDARY_SURFACE_ADDRESS, SECONDARY_SURFACE_ADDRESS, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH, PRIMARY_META_SURFACE_ADDRESS_HIGH, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_META_SURFACE_ADDRESS, PRIMARY_META_SURFACE_ADDRESS, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH, SECONDARY_META_SURFACE_ADDRESS_HIGH, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SECONDARY_META_SURFACE_ADDRESS, SECONDARY_META_SURFACE_ADDRESS, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C, PRIMARY_SURFACE_ADDRESS_HIGH_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS_C, PRIMARY_SURFACE_ADDRESS_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C, PRIMARY_META_SURFACE_ADDRESS_HIGH_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_META_SURFACE_ADDRESS_C, PRIMARY_META_SURFACE_ADDRESS_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_INUSE, SURFACE_INUSE_ADDRESS, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_INUSE_HIGH, SURFACE_INUSE_ADDRESS_HIGH, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_INUSE_C, SURFACE_INUSE_ADDRESS_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_INUSE_HIGH_C, SURFACE_INUSE_ADDRESS_HIGH_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_EARLIEST_INUSE, SURFACE_EARLIEST_INUSE_ADDRESS, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_EARLIEST_INUSE_HIGH, SURFACE_EARLIEST_INUSE_ADDRESS_HIGH, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_EARLIEST_INUSE_C, SURFACE_EARLIEST_INUSE_ADDRESS_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C, SURFACE_EARLIEST_INUSE_ADDRESS_HIGH_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, PRIMARY_SURFACE_TMZ, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, PRIMARY_SURFACE_DCC_EN, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, PRIMARY_SURFACE_DCC_IND_64B_BLK, mask_sh),\
+	HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\
+	HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\
+	HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_EXPANSION_MODE, DRQ_EXPANSION_MODE, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_EXPANSION_MODE, PRQ_EXPANSION_MODE, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_EXPANSION_MODE, MRQ_EXPANSION_MODE, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_EXPANSION_MODE, CRQ_EXPANSION_MODE, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, CHUNK_SIZE, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, MIN_CHUNK_SIZE, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, META_CHUNK_SIZE, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, MIN_META_CHUNK_SIZE, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, DPTE_GROUP_SIZE, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, MPTE_GROUP_SIZE, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, SWATH_HEIGHT, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, PTE_ROW_HEIGHT_LINEAR, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, CHUNK_SIZE_C, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, MIN_CHUNK_SIZE_C, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, META_CHUNK_SIZE_C, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, MIN_META_CHUNK_SIZE_C, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, DPTE_GROUP_SIZE_C, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, MPTE_GROUP_SIZE_C, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, SWATH_HEIGHT_C, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG_C, PTE_ROW_HEIGHT_LINEAR_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_BLANK_OFFSET_0, REFCYC_H_BLANK_END, mask_sh),\
+	HUBP_SF(HUBPREQ0_BLANK_OFFSET_0, DLG_V_BLANK_END, mask_sh),\
+	HUBP_SF(HUBPREQ0_BLANK_OFFSET_1, MIN_DST_Y_NEXT_START, mask_sh),\
+	HUBP_SF(HUBPREQ0_DST_DIMENSIONS, REFCYC_PER_HTOTAL, mask_sh),\
+	HUBP_SF(HUBPREQ0_DST_AFTER_SCALER, REFCYC_X_AFTER_SCALER, mask_sh),\
+	HUBP_SF(HUBPREQ0_DST_AFTER_SCALER, DST_Y_AFTER_SCALER, mask_sh),\
+	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_0, DST_Y_PER_VM_VBLANK, mask_sh),\
+	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_0, DST_Y_PER_ROW_VBLANK, mask_sh),\
+	HUBP_SF(HUBPREQ0_REF_FREQ_TO_PIX_FREQ, REF_FREQ_TO_PIX_FREQ, mask_sh),\
+	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_1, REFCYC_PER_PTE_GROUP_VBLANK_L, mask_sh),\
+	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_3, REFCYC_PER_META_CHUNK_VBLANK_L, mask_sh),\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_0, DST_Y_PER_PTE_ROW_NOM_L, mask_sh),\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_1, REFCYC_PER_PTE_GROUP_NOM_L, mask_sh),\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_4, DST_Y_PER_META_ROW_NOM_L, mask_sh),\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_5, REFCYC_PER_META_CHUNK_NOM_L, mask_sh),\
+	HUBP_SF(HUBPREQ0_PER_LINE_DELIVERY_PRE, REFCYC_PER_LINE_DELIVERY_PRE_L, mask_sh),\
+	HUBP_SF(HUBPREQ0_PER_LINE_DELIVERY_PRE, REFCYC_PER_LINE_DELIVERY_PRE_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_PER_LINE_DELIVERY, REFCYC_PER_LINE_DELIVERY_L, mask_sh),\
+	HUBP_SF(HUBPREQ0_PER_LINE_DELIVERY, REFCYC_PER_LINE_DELIVERY_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_2, REFCYC_PER_PTE_GROUP_VBLANK_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_4, REFCYC_PER_META_CHUNK_VBLANK_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_2, DST_Y_PER_PTE_ROW_NOM_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_3, REFCYC_PER_PTE_GROUP_NOM_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_6, DST_Y_PER_META_ROW_NOM_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_7, REFCYC_PER_META_CHUNK_NOM_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_TTU_QOS_WM, QoS_LEVEL_LOW_WM, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_TTU_QOS_WM, QoS_LEVEL_HIGH_WM, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_GLOBAL_TTU_CNTL, MIN_TTU_VBLANK, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_GLOBAL_TTU_CNTL, QoS_LEVEL_FLIP, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_SURF0_TTU_CNTL0, REFCYC_PER_REQ_DELIVERY, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_SURF0_TTU_CNTL0, QoS_LEVEL_FIXED, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_SURF0_TTU_CNTL0, QoS_RAMP_DISABLE, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_SURF0_TTU_CNTL1, REFCYC_PER_REQ_DELIVERY_PRE, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_MX_L1_TLB_CNTL, ENABLE_L1_TLB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_MX_L1_TLB_CNTL, SYSTEM_ACCESS_MODE, mask_sh)
+
+#define HUBP_MASK_SH_LIST_DCN10(mask_sh)\
+	HUBP_MASK_SH_LIST_DCN(mask_sh),\
+	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS, DST_Y_PREFETCH, mask_sh),\
+	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS, VRATIO_PREFETCH, mask_sh),\
+	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS_C, VRATIO_PREFETCH_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_MSB, VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_MSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LSB, VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_START_ADDR_MSB, VM_CONTEXT0_PAGE_TABLE_START_ADDR_MSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_START_ADDR_LSB, VM_CONTEXT0_PAGE_TABLE_START_ADDR_LSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_END_ADDR_MSB, VM_CONTEXT0_PAGE_TABLE_END_ADDR_MSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_CONTEXT0_PAGE_TABLE_END_ADDR_LSB, VM_CONTEXT0_PAGE_TABLE_END_ADDR_LSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_MSB, VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_MSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_MSB, VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_SYSTEM, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_LSB, VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR_LSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_LOW_ADDR_MSB, MC_VM_SYSTEM_APERTURE_LOW_ADDR_MSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_LOW_ADDR_LSB, MC_VM_SYSTEM_APERTURE_LOW_ADDR_LSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_HIGH_ADDR_MSB, MC_VM_SYSTEM_APERTURE_HIGH_ADDR_MSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_HIGH_ADDR_LSB, MC_VM_SYSTEM_APERTURE_HIGH_ADDR_LSB, mask_sh),\
+	HUBP_SF(DCHUBBUB_SDPIF_FB_BASE, SDPIF_FB_BASE, mask_sh),\
+	HUBP_SF(DCHUBBUB_SDPIF_FB_OFFSET, SDPIF_FB_OFFSET, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, MC_VM_SYSTEM_APERTURE_DEFAULT_SYSTEM, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, mask_sh),\
+	HUBP_SF(HUBPREQ0_CURSOR_SETTINS, CURSOR0_DST_Y_OFFSET, mask_sh), \
+	HUBP_SF(HUBPREQ0_CURSOR_SETTINS, CURSOR0_CHUNK_HDL_ADJUST, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_SURFACE_ADDRESS_HIGH, CURSOR_SURFACE_ADDRESS_HIGH, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_SURFACE_ADDRESS, CURSOR_SURFACE_ADDRESS, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_SIZE, CURSOR_WIDTH, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_SIZE, CURSOR_HEIGHT, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_CONTROL, CURSOR_MODE, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_CONTROL, CURSOR_2X_MAGNIFY, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_CONTROL, CURSOR_PITCH, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_CONTROL, CURSOR_LINES_PER_CHUNK, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_CONTROL, CURSOR_ENABLE, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_POSITION, CURSOR_X_POSITION, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_POSITION, CURSOR_Y_POSITION, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_X, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_Y, mask_sh), \
+	HUBP_SF(CURSOR0_CURSOR_DST_OFFSET, CURSOR_DST_X_OFFSET, mask_sh)
+
+#define DCN_HUBP_REG_FIELD_LIST(type) \
 	type HUBP_BLANK_EN;\
 	type HUBP_TTU_DISABLE;\
 	type HUBP_NO_OUTSTANDING_REQ;\
@@ -576,19 +573,23 @@ struct dcn_mi_registers {
 	type CURSOR_DST_X_OFFSET; \
 	type OUTPUT_FP
 
+struct dcn_mi_registers {
+	HUBP_COMMON_REG_VARIABLE_LIST;
+};
+
 struct dcn_mi_shift {
-	DCN_MI_REG_FIELD_LIST(uint8_t);
+	DCN_HUBP_REG_FIELD_LIST(uint8_t);
 };
 
 struct dcn_mi_mask {
-	DCN_MI_REG_FIELD_LIST(uint32_t);
+	DCN_HUBP_REG_FIELD_LIST(uint32_t);
 };
 
 struct dcn10_hubp {
 	struct hubp base;
-	const struct dcn_mi_registers *mi_regs;
-	const struct dcn_mi_shift *mi_shift;
-	const struct dcn_mi_mask *mi_mask;
+	const struct dcn_mi_registers *hubp_regs;
+	const struct dcn_mi_shift *hubp_shift;
+	const struct dcn_mi_mask *hubp_mask;
 };
 
 void hubp1_program_surface_config(
@@ -610,11 +611,11 @@ void hubp1_program_requestor(
 		struct _vcs_dpi_display_rq_regs_st *rq_regs);
 
 void hubp1_program_pixel_format(
-	struct dcn10_hubp *hubp,
+	struct hubp *hubp,
 	enum surface_pixel_format format);
 
 void hubp1_program_size_and_rotation(
-	struct dcn10_hubp *hubp,
+	struct hubp *hubp,
 	enum dc_rotation_angle rotation,
 	enum surface_pixel_format format,
 	const union plane_size *plane_size,
@@ -622,7 +623,7 @@ void hubp1_program_size_and_rotation(
 	bool horizontal_mirror);
 
 void hubp1_program_tiling(
-	struct dcn10_hubp *hubp,
+	struct hubp *hubp,
 	const union dc_tiling_info *info,
 	const enum surface_pixel_format pixel_format);
 
@@ -656,9 +657,9 @@ void dcn10_hubp_construct(
 	struct dcn10_hubp *hubp1,
 	struct dc_context *ctx,
 	uint32_t inst,
-	const struct dcn_mi_registers *mi_regs,
-	const struct dcn_mi_shift *mi_shift,
-	const struct dcn_mi_mask *mi_mask);
+	const struct dcn_mi_registers *hubp_regs,
+	const struct dcn_mi_shift *hubp_shift,
+	const struct dcn_mi_mask *hubp_mask);
 
 
 struct dcn_hubp_state {
@@ -680,4 +681,6 @@ struct dcn_hubp_state {
 void hubp1_read_state(struct dcn10_hubp *hubp1,
 		struct dcn_hubp_state *s);
 
+enum cursor_pitch hubp1_get_cursor_pitch(unsigned int pitch);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 961ad5c3b454..82572863acab 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -31,7 +31,8 @@
 #include "dce110/dce110_hw_sequencer.h"
 #include "dce/dce_hwseq.h"
 #include "abm.h"
-#include "dcn10/dcn10_timing_generator.h"
+#include "dmcu.h"
+#include "dcn10_optc.h"
 #include "dcn10/dcn10_dpp.h"
 #include "dcn10/dcn10_mpc.h"
 #include "timing_generator.h"
@@ -41,6 +42,8 @@
 #include "reg_helper.h"
 #include "custom_float.h"
 #include "dcn10_hubp.h"
+#include "dcn10_hubbub.h"
+#include "dcn10_cm_common.h"
 
 #define CTX \
 	hws->ctx
@@ -51,18 +54,8 @@
 #define FN(reg_name, field_name) \
 	hws->shifts->field_name, hws->masks->field_name
 
-static void log_mpc_crc(struct dc *dc)
-{
-	struct dc_context *dc_ctx = dc->ctx;
-	struct dce_hwseq *hws = dc->hwseq;
-
-	if (REG(MPC_CRC_RESULT_GB))
-		DTN_INFO("MPC_CRC_RESULT_GB:%d MPC_CRC_RESULT_C:%d MPC_CRC_RESULT_AR:%d\n",
-		REG_READ(MPC_CRC_RESULT_GB), REG_READ(MPC_CRC_RESULT_C), REG_READ(MPC_CRC_RESULT_AR));
-	if (REG(DPP_TOP0_DPP_CRC_VAL_B_A))
-		DTN_INFO("DPP_TOP0_DPP_CRC_VAL_B_A:%d DPP_TOP0_DPP_CRC_VAL_R_G:%d\n",
-		REG_READ(DPP_TOP0_DPP_CRC_VAL_B_A), REG_READ(DPP_TOP0_DPP_CRC_VAL_R_G));
-}
+#define DTN_INFO_MICRO_SEC(ref_cycle) \
+	print_microsec(dc_ctx, ref_cycle)
 
 void print_microsec(struct dc_context *dc_ctx, uint32_t ref_cycle)
 {
@@ -75,67 +68,27 @@ void print_microsec(struct dc_context *dc_ctx, uint32_t ref_cycle)
 			us_x10 % frac);
 }
 
-#define DTN_INFO_MICRO_SEC(ref_cycle) \
-	print_microsec(dc_ctx, ref_cycle)
 
-struct dcn_hubbub_wm_set {
-	uint32_t wm_set;
-	uint32_t data_urgent;
-	uint32_t pte_meta_urgent;
-	uint32_t sr_enter;
-	uint32_t sr_exit;
-	uint32_t dram_clk_chanage;
-};
+static void log_mpc_crc(struct dc *dc)
+{
+	struct dc_context *dc_ctx = dc->ctx;
+	struct dce_hwseq *hws = dc->hwseq;
 
-struct dcn_hubbub_wm {
-	struct dcn_hubbub_wm_set sets[4];
-};
+	if (REG(MPC_CRC_RESULT_GB))
+		DTN_INFO("MPC_CRC_RESULT_GB:%d MPC_CRC_RESULT_C:%d MPC_CRC_RESULT_AR:%d\n",
+		REG_READ(MPC_CRC_RESULT_GB), REG_READ(MPC_CRC_RESULT_C), REG_READ(MPC_CRC_RESULT_AR));
+	if (REG(DPP_TOP0_DPP_CRC_VAL_B_A))
+		DTN_INFO("DPP_TOP0_DPP_CRC_VAL_B_A:%d DPP_TOP0_DPP_CRC_VAL_R_G:%d\n",
+		REG_READ(DPP_TOP0_DPP_CRC_VAL_B_A), REG_READ(DPP_TOP0_DPP_CRC_VAL_R_G));
+}
 
-static void dcn10_hubbub_wm_read_state(struct dce_hwseq *hws,
-		struct dcn_hubbub_wm *wm)
-{
-	struct dcn_hubbub_wm_set *s;
-
-	s = &wm->sets[0];
-	s->wm_set = 0;
-	s->data_urgent = REG_READ(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A);
-	s->pte_meta_urgent = REG_READ(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A);
-	s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A);
-	s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A);
-	s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A);
-
-	s = &wm->sets[1];
-	s->wm_set = 1;
-	s->data_urgent = REG_READ(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B);
-	s->pte_meta_urgent = REG_READ(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B);
-	s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B);
-	s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B);
-	s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B);
-
-	s = &wm->sets[2];
-	s->wm_set = 2;
-	s->data_urgent = REG_READ(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C);
-	s->pte_meta_urgent = REG_READ(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C);
-	s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C);
-	s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C);
-	s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C);
-
-	s = &wm->sets[3];
-	s->wm_set = 3;
-	s->data_urgent = REG_READ(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D);
-	s->pte_meta_urgent = REG_READ(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D);
-	s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D);
-	s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D);
-	s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D);
-}
-
-static void dcn10_log_hubbub_state(struct dc *dc)
+void dcn10_log_hubbub_state(struct dc *dc)
 {
 	struct dc_context *dc_ctx = dc->ctx;
 	struct dcn_hubbub_wm wm;
 	int i;
 
-	dcn10_hubbub_wm_read_state(dc->hwseq, &wm);
+	hubbub1_wm_read_state(dc->res_pool->hubbub, &wm);
 
 	DTN_INFO("HUBBUB WM: \t data_urgent \t pte_meta_urgent \t "
 			"sr_enter \t sr_exit \t dram_clk_change \n");
@@ -156,7 +109,7 @@ static void dcn10_log_hubbub_state(struct dc *dc)
 	DTN_INFO("\n");
 }
 
-static void dcn10_log_hw_state(struct dc *dc)
+void dcn10_log_hw_state(struct dc *dc)
 {
 	struct dc_context *dc_ctx = dc->ctx;
 	struct resource_pool *pool = dc->res_pool;
@@ -206,7 +159,7 @@ static void dcn10_log_hw_state(struct dc *dc)
 		struct timing_generator *tg = pool->timing_generators[i];
 		struct dcn_otg_state s = {0};
 
-		tgn10_read_otg_state(DCN10TG_FROM_TG(tg), &s);
+		optc1_read_otg_state(DCN10TG_FROM_TG(tg), &s);
 
 		//only print if OTG master is enabled
 		if ((s.otg_enabled & 1) == 0)
@@ -240,97 +193,6 @@ static void dcn10_log_hw_state(struct dc *dc)
 	DTN_INFO_END();
 }
 
-static void verify_allow_pstate_change_high(
-	struct dce_hwseq *hws)
-{
-	/* pstate latency is ~20us so if we wait over 40us and pstate allow
-	 * still not asserted, we are probably stuck and going to hang
-	 *
-	 * TODO: Figure out why it takes ~100us on linux
-	 * pstate takes around ~100us on linux. Unknown currently as to
-	 * why it takes that long on linux
-	 */
-	static unsigned int pstate_wait_timeout_us = 200;
-	static unsigned int pstate_wait_expected_timeout_us = 40;
-	static unsigned int max_sampled_pstate_wait_us; /* data collection */
-	static bool forced_pstate_allow; /* help with revert wa */
-	static bool should_log_hw_state; /* prevent hw state log by default */
-
-	unsigned int debug_index = 0x7;
-	unsigned int debug_data;
-	unsigned int i;
-
-	if (forced_pstate_allow) {
-		/* we hacked to force pstate allow to prevent hang last time
-		 * we verify_allow_pstate_change_high.  so disable force
-		 * here so we can check status
-		 */
-		REG_UPDATE_2(DCHUBBUB_ARB_DRAM_STATE_CNTL,
-			     DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_VALUE, 0,
-			     DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_ENABLE, 0);
-		forced_pstate_allow = false;
-	}
-
-	/* description "3-0:   Pipe0 cursor0 QOS
-	 * 7-4:   Pipe1 cursor0 QOS
-	 * 11-8:  Pipe2 cursor0 QOS
-	 * 15-12: Pipe3 cursor0 QOS
-	 * 16:    Pipe0 Plane0 Allow Pstate Change
-	 * 17:    Pipe1 Plane0 Allow Pstate Change
-	 * 18:    Pipe2 Plane0 Allow Pstate Change
-	 * 19:    Pipe3 Plane0 Allow Pstate Change
-	 * 20:    Pipe0 Plane1 Allow Pstate Change
-	 * 21:    Pipe1 Plane1 Allow Pstate Change
-	 * 22:    Pipe2 Plane1 Allow Pstate Change
-	 * 23:    Pipe3 Plane1 Allow Pstate Change
-	 * 24:    Pipe0 cursor0 Allow Pstate Change
-	 * 25:    Pipe1 cursor0 Allow Pstate Change
-	 * 26:    Pipe2 cursor0 Allow Pstate Change
-	 * 27:    Pipe3 cursor0 Allow Pstate Change
-	 * 28:    WB0 Allow Pstate Change
-	 * 29:    WB1 Allow Pstate Change
-	 * 30:    Arbiter's allow_pstate_change
-	 * 31:    SOC pstate change request
-	 */
-
-	REG_WRITE(DCHUBBUB_TEST_DEBUG_INDEX, debug_index);
-
-	for (i = 0; i < pstate_wait_timeout_us; i++) {
-		debug_data = REG_READ(DCHUBBUB_TEST_DEBUG_DATA);
-
-		if (debug_data & (1 << 30)) {
-
-			if (i > pstate_wait_expected_timeout_us)
-				dm_logger_write(hws->ctx->logger, LOG_WARNING,
-						"pstate took longer than expected ~%dus\n",
-						i);
-
-			return;
-		}
-		if (max_sampled_pstate_wait_us < i)
-			max_sampled_pstate_wait_us = i;
-
-		udelay(1);
-	}
-
-	/* force pstate allow to prevent system hang
-	 * and break to debugger to investigate
-	 */
-	REG_UPDATE_2(DCHUBBUB_ARB_DRAM_STATE_CNTL,
-		     DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_VALUE, 1,
-		     DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_ENABLE, 1);
-	forced_pstate_allow = true;
-
-	if (should_log_hw_state) {
-		dcn10_log_hw_state(hws->ctx->dc);
-	}
-
-	dm_logger_write(hws->ctx->logger, LOG_WARNING,
-			"pstate TEST_DEBUG_DATA: 0x%X\n",
-			debug_data);
-	BREAK_TO_DEBUGGER();
-}
-
 static void enable_dppclk(
 	struct dce_hwseq *hws,
 	uint8_t plane_id,
@@ -432,312 +294,6 @@ static void dpp_pg_control(
 	}
 }
 
-static uint32_t convert_and_clamp(
-	uint32_t wm_ns,
-	uint32_t refclk_mhz,
-	uint32_t clamp_value)
-{
-	uint32_t ret_val = 0;
-	ret_val = wm_ns * refclk_mhz;
-	ret_val /= 1000;
-
-	if (ret_val > clamp_value)
-		ret_val = clamp_value;
-
-	return ret_val;
-}
-
-static void program_watermarks(
-		struct dce_hwseq *hws,
-		struct dcn_watermark_set *watermarks,
-		unsigned int refclk_mhz)
-{
-	uint32_t force_en = hws->ctx->dc->debug.disable_stutter ? 1 : 0;
-	/*
-	 * Need to clamp to max of the register values (i.e. no wrap)
-	 * for dcn1, all wm registers are 21-bit wide
-	 */
-	uint32_t prog_wm_value;
-
-	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 0);
-
-	/* Repeat for water mark set A, B, C and D. */
-	/* clock state A */
-	prog_wm_value = convert_and_clamp(watermarks->a.urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A, prog_wm_value);
-
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"URGENCY_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->a.urgent_ns, prog_wm_value);
-
-	prog_wm_value = convert_and_clamp(watermarks->a.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A, prog_wm_value);
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"PTE_META_URGENCY_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->a.pte_meta_urgent_ns, prog_wm_value);
-
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns,
-				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A, prog_wm_value);
-		dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-			"SR_ENTER_EXIT_WATERMARK_A calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
-
-
-		prog_wm_value = convert_and_clamp(
-				watermarks->a.cstate_pstate.cstate_exit_ns,
-				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A, prog_wm_value);
-		dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-			"SR_EXIT_WATERMARK_A calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->a.cstate_pstate.cstate_exit_ns, prog_wm_value);
-	}
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->a.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, prog_wm_value);
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"DRAM_CLK_CHANGE_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n\n",
-		watermarks->a.cstate_pstate.pstate_change_ns, prog_wm_value);
-
-
-	/* clock state B */
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B, prog_wm_value);
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"URGENCY_WATERMARK_B calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.urgent_ns, prog_wm_value);
-
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B, prog_wm_value);
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"PTE_META_URGENCY_WATERMARK_B calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.pte_meta_urgent_ns, prog_wm_value);
-
-
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns,
-				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B, prog_wm_value);
-		dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-			"SR_ENTER_WATERMARK_B calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
-
-
-		prog_wm_value = convert_and_clamp(
-				watermarks->b.cstate_pstate.cstate_exit_ns,
-				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B, prog_wm_value);
-		dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-			"SR_EXIT_WATERMARK_B calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->b.cstate_pstate.cstate_exit_ns, prog_wm_value);
-	}
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, prog_wm_value);
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"DRAM_CLK_CHANGE_WATERMARK_B calculated =%d\n\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.cstate_pstate.pstate_change_ns, prog_wm_value);
-
-	/* clock state C */
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C, prog_wm_value);
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"URGENCY_WATERMARK_C calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.urgent_ns, prog_wm_value);
-
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C, prog_wm_value);
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"PTE_META_URGENCY_WATERMARK_C calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.pte_meta_urgent_ns, prog_wm_value);
-
-
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns,
-				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C, prog_wm_value);
-		dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-			"SR_ENTER_WATERMARK_C calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
-
-
-		prog_wm_value = convert_and_clamp(
-				watermarks->c.cstate_pstate.cstate_exit_ns,
-				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C, prog_wm_value);
-		dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-			"SR_EXIT_WATERMARK_C calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->c.cstate_pstate.cstate_exit_ns, prog_wm_value);
-	}
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, prog_wm_value);
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"DRAM_CLK_CHANGE_WATERMARK_C calculated =%d\n\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.cstate_pstate.pstate_change_ns, prog_wm_value);
-
-	/* clock state D */
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D, prog_wm_value);
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"URGENCY_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->d.urgent_ns, prog_wm_value);
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D, prog_wm_value);
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"PTE_META_URGENCY_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->d.pte_meta_urgent_ns, prog_wm_value);
-
-
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns,
-				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D, prog_wm_value);
-		dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-			"SR_ENTER_WATERMARK_D calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
-
-
-		prog_wm_value = convert_and_clamp(
-				watermarks->d.cstate_pstate.cstate_exit_ns,
-				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D, prog_wm_value);
-		dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-			"SR_EXIT_WATERMARK_D calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->d.cstate_pstate.cstate_exit_ns, prog_wm_value);
-	}
-
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, prog_wm_value);
-	dm_logger_write(hws->ctx->logger, LOG_BANDWIDTH_CALCS,
-		"DRAM_CLK_CHANGE_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n\n",
-		watermarks->d.cstate_pstate.pstate_change_ns, prog_wm_value);
-
-	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 1);
-
-	REG_UPDATE(DCHUBBUB_ARB_SAT_LEVEL,
-			DCHUBBUB_ARB_SAT_LEVEL, 60 * refclk_mhz);
-	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND,
-			DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 68);
-
-	REG_UPDATE_2(DCHUBBUB_ARB_DRAM_STATE_CNTL,
-			DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_VALUE, 0,
-			DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_ENABLE, force_en);
-
-#if 0
-	REG_UPDATE_2(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_DONE_INTERRUPT_DISABLE, 1,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 1);
-#endif
-}
-
-
-static void dcn10_update_dchub(
-	struct dce_hwseq *hws,
-	struct dchub_init_data *dh_data)
-{
-	/* TODO: port code from dal2 */
-	switch (dh_data->fb_mode) {
-	case FRAME_BUFFER_MODE_ZFB_ONLY:
-		/*For ZFB case need to put DCHUB FB BASE and TOP upside down to indicate ZFB mode*/
-		REG_UPDATE(DCHUBBUB_SDPIF_FB_TOP,
-				SDPIF_FB_TOP, 0);
-
-		REG_UPDATE(DCHUBBUB_SDPIF_FB_BASE,
-				SDPIF_FB_BASE, 0x0FFFF);
-
-		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BASE,
-				SDPIF_AGP_BASE, dh_data->zfb_phys_addr_base >> 22);
-
-		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BOT,
-				SDPIF_AGP_BOT, dh_data->zfb_mc_base_addr >> 22);
-
-		REG_UPDATE(DCHUBBUB_SDPIF_AGP_TOP,
-				SDPIF_AGP_TOP, (dh_data->zfb_mc_base_addr +
-						dh_data->zfb_size_in_byte - 1) >> 22);
-		break;
-	case FRAME_BUFFER_MODE_MIXED_ZFB_AND_LOCAL:
-		/*Should not touch FB LOCATION (done by VBIOS on AsicInit table)*/
-
-		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BASE,
-				SDPIF_AGP_BASE, dh_data->zfb_phys_addr_base >> 22);
-
-		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BOT,
-				SDPIF_AGP_BOT, dh_data->zfb_mc_base_addr >> 22);
-
-		REG_UPDATE(DCHUBBUB_SDPIF_AGP_TOP,
-				SDPIF_AGP_TOP, (dh_data->zfb_mc_base_addr +
-						dh_data->zfb_size_in_byte - 1) >> 22);
-		break;
-	case FRAME_BUFFER_MODE_LOCAL_ONLY:
-		/*Should not touch FB LOCATION (done by VBIOS on AsicInit table)*/
-		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BASE,
-				SDPIF_AGP_BASE, 0);
-
-		REG_UPDATE(DCHUBBUB_SDPIF_AGP_BOT,
-				SDPIF_AGP_BOT, 0X03FFFF);
-
-		REG_UPDATE(DCHUBBUB_SDPIF_AGP_TOP,
-				SDPIF_AGP_TOP, 0);
-		break;
-	default:
-		break;
-	}
-
-	dh_data->dchub_initialzied = true;
-	dh_data->dchub_info_valid = false;
-}
-
 static void hubp_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int hubp_inst,
@@ -808,11 +364,8 @@ static void undo_DEGVIDCN10_253_wa(struct dc *dc)
 {
 	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = dc->res_pool->hubps[0];
-	int pwr_status = 0;
 
-	REG_GET(DOMAIN0_PG_STATUS, DOMAIN0_PGFSM_PWR_STATUS, &pwr_status);
-	/* Don't need to blank if hubp is power gated*/
-	if (pwr_status == 2)
+	if (!hws->wa_state.DEGVIDCN10_253_applied)
 		return;
 
 	hubp->funcs->set_blank(hubp, true);
@@ -823,16 +376,29 @@ static void undo_DEGVIDCN10_253_wa(struct dc *dc)
 	hubp_pg_control(hws, 0, false);
 	REG_SET(DC_IP_REQUEST_CNTL, 0,
 			IP_REQUEST_EN, 0);
+
+	hws->wa_state.DEGVIDCN10_253_applied = false;
 }
 
 static void apply_DEGVIDCN10_253_wa(struct dc *dc)
 {
 	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = dc->res_pool->hubps[0];
+	int i;
 
 	if (dc->debug.disable_stutter)
 		return;
 
+	if (!hws->wa.DEGVIDCN10_253)
+		return;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (!dc->res_pool->hubps[i]->power_gated)
+			return;
+	}
+
+	/* all pipe power gated, apply work around to enable stutter. */
+
 	REG_SET(DC_IP_REQUEST_CNTL, 0,
 			IP_REQUEST_EN, 1);
 
@@ -841,6 +407,7 @@ static void apply_DEGVIDCN10_253_wa(struct dc *dc)
 			IP_REQUEST_EN, 0);
 
 	hubp->funcs->set_hubp_blank_en(hubp, false);
+	hws->wa_state.DEGVIDCN10_253_applied = true;
 }
 
 static void bios_golden_init(struct dc *dc)
@@ -859,85 +426,32 @@ static void bios_golden_init(struct dc *dc)
 	}
 }
 
-static void dcn10_init_hw(struct dc *dc)
+static void false_optc_underflow_wa(
+		struct dc *dc,
+		const struct dc_stream_state *stream,
+		struct timing_generator *tg)
 {
 	int i;
-	struct abm *abm = dc->res_pool->abm;
-	struct dce_hwseq *hws = dc->hwseq;
-
-	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
-		REG_WRITE(REFCLK_CNTL, 0);
-		REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, 1);
-		REG_WRITE(DIO_MEM_PWR_CTRL, 0);
+	bool underflow;
 
-		if (!dc->debug.disable_clock_gate) {
-			/* enable all DCN clock gating */
-			REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0);
-
-			REG_WRITE(DCCG_GATE_DISABLE_CNTL2, 0);
-
-			REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0);
-		}
-
-		enable_power_gating_plane(dc->hwseq, true);
+	if (!dc->hwseq->wa.false_optc_underflow)
 		return;
-	}
-	/* end of FPGA. Below if real ASIC */
 
-	bios_golden_init(dc);
-
-	disable_vga(dc->hwseq);
-
-	for (i = 0; i < dc->link_count; i++) {
-		/* Power up AND update implementation according to the
-		 * required signal (which may be different from the
-		 * default signal on connector).
-		 */
-		struct dc_link *link = dc->links[i];
-
-		link->link_enc->funcs->hw_init(link->link_enc);
-	}
+	underflow = tg->funcs->is_optc_underflow_occurred(tg);
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct dpp *dpp = dc->res_pool->dpps[i];
-		struct timing_generator *tg = dc->res_pool->timing_generators[i];
+		struct pipe_ctx *old_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
 
-		dpp->funcs->dpp_reset(dpp);
-		dc->res_pool->mpc->funcs->remove(
-				dc->res_pool->mpc, &(dc->res_pool->opps[i]->mpc_tree),
-				dc->res_pool->opps[i]->inst, i);
-
-		/* Blank controller using driver code instead of
-		 * command table.
-		 */
-		tg->funcs->set_blank(tg, true);
-		hwss_wait_for_blank_complete(tg);
-	}
-
-	for (i = 0; i < dc->res_pool->audio_count; i++) {
-		struct audio *audio = dc->res_pool->audios[i];
-
-		audio->funcs->hw_init(audio);
-	}
+		if (old_pipe_ctx->stream != stream)
+			continue;
 
-	if (abm != NULL) {
-		abm->funcs->init_backlight(abm);
-		abm->funcs->abm_init(abm);
+		dc->hwss.wait_for_mpcc_disconnect(dc, dc->res_pool, old_pipe_ctx);
 	}
 
-	/* power AFMT HDMI memory TODO: may move to dis/en output save power*/
-	REG_WRITE(DIO_MEM_PWR_CTRL, 0);
-
-	if (!dc->debug.disable_clock_gate) {
-		/* enable all DCN clock gating */
-		REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0);
-
-		REG_WRITE(DCCG_GATE_DISABLE_CNTL2, 0);
-
-		REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0);
-	}
+	tg->funcs->set_blank_data_double_buffer(tg, true);
 
-	enable_power_gating_plane(dc->hwseq, true);
+	if (tg->funcs->is_optc_underflow_occurred(tg) && !underflow)
+		tg->funcs->clear_optc_underflow(tg);
 }
 
 static enum dc_status dcn10_prog_pixclk_crtc_otg(
@@ -948,10 +462,6 @@ static enum dc_status dcn10_prog_pixclk_crtc_otg(
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	enum dc_color_space color_space;
 	struct tg_color black_color = {0};
-	bool enableStereo    = stream->timing.timing_3d_format == TIMING_3D_FORMAT_NONE ?
-			false:true;
-	bool rightEyePolarity = stream->timing.flags.RIGHT_EYE_3D_POLARITY;
-
 
 	/* by upper caller loop, pipe0 is parent pipe and be called first.
 	 * back end is set up by for pipe0. Other children pipe share back end
@@ -986,11 +496,6 @@ static enum dc_status dcn10_prog_pixclk_crtc_otg(
 			&stream->timing,
 			true);
 
-	pipe_ctx->stream_res.opp->funcs->opp_set_stereo_polarity(
-				pipe_ctx->stream_res.opp,
-				enableStereo,
-				rightEyePolarity);
-
 #if 0 /* move to after enable_crtc */
 	/* TODO: OPP FMT, ABM. etc. should be done here. */
 	/* or FPGA now. instance 0 only. TODO: move to opp.c */
@@ -1005,12 +510,18 @@ static enum dc_status dcn10_prog_pixclk_crtc_otg(
 	/* program otg blank color */
 	color_space = stream->output_color_space;
 	color_space_to_black_color(dc, color_space, &black_color);
-	pipe_ctx->stream_res.tg->funcs->set_blank_color(
-			pipe_ctx->stream_res.tg,
-			&black_color);
 
-	pipe_ctx->stream_res.tg->funcs->set_blank(pipe_ctx->stream_res.tg, true);
-	hwss_wait_for_blank_complete(pipe_ctx->stream_res.tg);
+	if (pipe_ctx->stream_res.tg->funcs->set_blank_color)
+		pipe_ctx->stream_res.tg->funcs->set_blank_color(
+				pipe_ctx->stream_res.tg,
+				&black_color);
+
+	if (pipe_ctx->stream_res.tg->funcs->is_blanked &&
+			!pipe_ctx->stream_res.tg->funcs->is_blanked(pipe_ctx->stream_res.tg)) {
+		pipe_ctx->stream_res.tg->funcs->set_blank(pipe_ctx->stream_res.tg, true);
+		hwss_wait_for_blank_complete(pipe_ctx->stream_res.tg);
+		false_optc_underflow_wa(dc, pipe_ctx->stream, pipe_ctx->stream_res.tg);
+	}
 
 	/* VTG is  within DCHUB command block. DCFCLK is always on */
 	if (false == pipe_ctx->stream_res.tg->funcs->enable_crtc(pipe_ctx->stream_res.tg)) {
@@ -1070,83 +581,55 @@ static void reset_back_end_for_pipe(
 					pipe_ctx->pipe_idx, pipe_ctx->stream_res.tg->inst);
 }
 
+static void dcn10_verify_allow_pstate_change_high(struct dc *dc)
+{
+	static bool should_log_hw_state; /* prevent hw state log by default */
+
+	if (!hubbub1_verify_allow_pstate_change_high(dc->res_pool->hubbub)) {
+		if (should_log_hw_state) {
+			dcn10_log_hw_state(dc);
+		}
+
+		BREAK_TO_DEBUGGER();
+	}
+}
+
 /* trigger HW to start disconnect plane from stream on the next vsync */
-static void plane_atomic_disconnect(struct dc *dc,
-		int fe_idx)
+static void plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	int fe_idx = pipe_ctx->pipe_idx;
 	struct hubp *hubp = dc->res_pool->hubps[fe_idx];
 	struct mpc *mpc = dc->res_pool->mpc;
-	int opp_id, z_idx;
-	int mpcc_id = -1;
+	int opp_id;
+	struct mpc_tree *mpc_tree_params;
+	struct mpcc *mpcc_to_remove = NULL;
 
 	/* look at tree rather than mi here to know if we already reset */
 	for (opp_id = 0; opp_id < dc->res_pool->pipe_count; opp_id++) {
 		struct output_pixel_processor *opp = dc->res_pool->opps[opp_id];
 
-		for (z_idx = 0; z_idx < opp->mpc_tree.num_pipes; z_idx++) {
-			if (opp->mpc_tree.dpp[z_idx] == fe_idx) {
-				mpcc_id = opp->mpc_tree.mpcc[z_idx];
-				break;
-			}
-		}
-		if (mpcc_id != -1)
+		mpc_tree_params = &(opp->mpc_tree_params);
+		mpcc_to_remove = mpc->funcs->get_mpcc_for_dpp(mpc_tree_params, fe_idx);
+		if (mpcc_to_remove != NULL)
 			break;
 	}
+
 	/*Already reset*/
 	if (opp_id == dc->res_pool->pipe_count)
 		return;
 
-	if (dc->debug.sanity_checks)
-		verify_allow_pstate_change_high(dc->hwseq);
-	hubp->funcs->dcc_control(hubp, false, false);
-	if (dc->debug.sanity_checks)
-		verify_allow_pstate_change_high(dc->hwseq);
-
-	mpc->funcs->remove(mpc, &(dc->res_pool->opps[opp_id]->mpc_tree),
-			dc->res_pool->opps[opp_id]->inst, fe_idx);
-}
-
-/* disable HW used by plane.
- * note:  cannot disable until disconnect is complete */
-static void plane_atomic_disable(struct dc *dc,
-		int fe_idx)
-{
-	struct dce_hwseq *hws = dc->hwseq;
-	struct hubp *hubp = dc->res_pool->hubps[fe_idx];
-	struct mpc *mpc = dc->res_pool->mpc;
-	int opp_id = hubp->opp_id;
-
-	if (opp_id == 0xf)
-		return;
-
-	mpc->funcs->wait_for_idle(mpc, hubp->mpcc_id);
-	dc->res_pool->opps[hubp->opp_id]->mpcc_disconnect_pending[hubp->mpcc_id] = false;
-	/*dm_logger_write(dc->ctx->logger, LOG_ERROR,
-			"[debug_mpo: atomic disable finished on mpcc %d]\n",
-			fe_idx);*/
+	mpc->funcs->remove_mpcc(mpc, mpc_tree_params, mpcc_to_remove);
+	dc->res_pool->opps[opp_id]->mpcc_disconnect_pending[fe_idx] = true;
 
-	hubp->funcs->set_blank(hubp, true);
-
-	if (dc->debug.sanity_checks)
-		verify_allow_pstate_change_high(dc->hwseq);
-
-	REG_UPDATE(HUBP_CLK_CNTL[fe_idx],
-			HUBP_CLOCK_ENABLE, 0);
-	REG_UPDATE(DPP_CONTROL[fe_idx],
-			DPP_CLOCK_ENABLE, 0);
+	dc->optimized_required = true;
 
-	if (dc->res_pool->opps[opp_id]->mpc_tree.num_pipes == 0)
-		REG_UPDATE(OPP_PIPE_CONTROL[opp_id],
-				OPP_PIPE_CLOCK_EN, 0);
+	if (hubp->funcs->hubp_disconnect)
+		hubp->funcs->hubp_disconnect(hubp);
 
 	if (dc->debug.sanity_checks)
-		verify_allow_pstate_change_high(dc->hwseq);
+		dcn10_verify_allow_pstate_change_high(dc);
 }
 
-/*
- * kill power to plane hw
- * note: cannot power down until plane is disable
- */
 static void plane_atomic_power_down(struct dc *dc, int fe_idx)
 {
 	struct dce_hwseq *hws = dc->hwseq;
@@ -1162,125 +645,200 @@ static void plane_atomic_power_down(struct dc *dc, int fe_idx)
 				IP_REQUEST_EN, 0);
 		dm_logger_write(dc->ctx->logger, LOG_DEBUG,
 				"Power gated front end %d\n", fe_idx);
-
-		if (dc->debug.sanity_checks)
-			verify_allow_pstate_change_high(dc->hwseq);
 	}
 }
 
-
-static void reset_front_end(
-		struct dc *dc,
-		int fe_idx)
+/* disable HW used by plane.
+ * note:  cannot disable until disconnect is complete
+ */
+static void plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	int fe_idx = pipe_ctx->pipe_idx;
 	struct dce_hwseq *hws = dc->hwseq;
-	struct timing_generator *tg;
-	int opp_id = dc->res_pool->hubps[fe_idx]->opp_id;
+	struct hubp *hubp = dc->res_pool->hubps[fe_idx];
+	int opp_id = hubp->opp_id;
 
-	/*Already reset*/
-	if (opp_id == 0xf)
-		return;
+	dc->hwss.wait_for_mpcc_disconnect(dc, dc->res_pool, pipe_ctx);
 
-	tg = dc->res_pool->timing_generators[opp_id];
-	tg->funcs->lock(tg);
+	REG_UPDATE(HUBP_CLK_CNTL[fe_idx],
+			HUBP_CLOCK_ENABLE, 0);
+	REG_UPDATE(DPP_CONTROL[fe_idx],
+			DPP_CLOCK_ENABLE, 0);
 
-	plane_atomic_disconnect(dc, fe_idx);
+	if (opp_id != 0xf && dc->res_pool->opps[opp_id]->mpc_tree_params.opp_list == NULL)
+		REG_UPDATE(OPP_PIPE_CONTROL[opp_id],
+				OPP_PIPE_CLOCK_EN, 0);
 
-	REG_UPDATE(OTG_GLOBAL_SYNC_STATUS[tg->inst], VUPDATE_NO_LOCK_EVENT_CLEAR, 1);
-	tg->funcs->unlock(tg);
+	hubp->power_gated = true;
+	dc->optimized_required = false; /* We're powering off, no need to optimize */
 
-	if (dc->debug.sanity_checks)
-		verify_allow_pstate_change_high(hws);
+	plane_atomic_power_down(dc, fe_idx);
 
-	if (tg->ctx->dce_environment != DCE_ENV_FPGA_MAXIMUS)
-		REG_WAIT(OTG_GLOBAL_SYNC_STATUS[tg->inst],
-				VUPDATE_NO_LOCK_EVENT_OCCURRED, 1,
-				1, 100000);
+	pipe_ctx->stream = NULL;
+	memset(&pipe_ctx->stream_res, 0, sizeof(pipe_ctx->stream_res));
+	memset(&pipe_ctx->plane_res, 0, sizeof(pipe_ctx->plane_res));
+	pipe_ctx->top_pipe = NULL;
+	pipe_ctx->bottom_pipe = NULL;
+	pipe_ctx->plane_state = NULL;
+}
 
-	plane_atomic_disable(dc, fe_idx);
+static void dcn10_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx)
+{
+	if (dc->res_pool->hubps[pipe_ctx->pipe_idx]->power_gated)
+		return;
+
+	plane_atomic_disable(dc, pipe_ctx);
+
+	apply_DEGVIDCN10_253_wa(dc);
 
 	dm_logger_write(dc->ctx->logger, LOG_DC,
-					"Reset front end %d\n",
-					fe_idx);
+					"Power down front end %d\n",
+					pipe_ctx->pipe_idx);
 }
 
-static void dcn10_power_down_fe(struct dc *dc, int fe_idx)
+static void dcn10_init_hw(struct dc *dc)
 {
+	int i;
+	struct abm *abm = dc->res_pool->abm;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 	struct dce_hwseq *hws = dc->hwseq;
-	struct dpp *dpp = dc->res_pool->dpps[fe_idx];
+	struct dc_bios *dcb = dc->ctx->dc_bios;
+	struct dc_state  *context = dc->current_state;
 
-	reset_front_end(dc, fe_idx);
+	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
+		REG_WRITE(REFCLK_CNTL, 0);
+		REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, 1);
+		REG_WRITE(DIO_MEM_PWR_CTRL, 0);
 
-	REG_SET(DC_IP_REQUEST_CNTL, 0,
-			IP_REQUEST_EN, 1);
-	dpp_pg_control(hws, fe_idx, false);
-	hubp_pg_control(hws, fe_idx, false);
-	dpp->funcs->dpp_reset(dpp);
-	REG_SET(DC_IP_REQUEST_CNTL, 0,
-			IP_REQUEST_EN, 0);
-	dm_logger_write(dc->ctx->logger, LOG_DEBUG,
-			"Power gated front end %d\n", fe_idx);
+		if (!dc->debug.disable_clock_gate) {
+			/* enable all DCN clock gating */
+			REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0);
 
-	if (dc->debug.sanity_checks)
-		verify_allow_pstate_change_high(dc->hwseq);
-}
+			REG_WRITE(DCCG_GATE_DISABLE_CNTL2, 0);
 
-static void reset_hw_ctx_wrap(
-		struct dc *dc,
-		struct dc_state *context)
-{
-	int i;
+			REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0);
+		}
+
+		enable_power_gating_plane(dc->hwseq, true);
+		return;
+	}
+	/* end of FPGA. Below if real ASIC */
+
+	if (!dcb->funcs->is_accelerated_mode(dcb)) {
+		bios_golden_init(dc);
+		disable_vga(dc->hwseq);
+	}
+
+	for (i = 0; i < dc->link_count; i++) {
+		/* Power up AND update implementation according to the
+		 * required signal (which may be different from the
+		 * default signal on connector).
+		 */
+		struct dc_link *link = dc->links[i];
+
+		if (link->link_enc->connector.id == CONNECTOR_ID_EDP)
+			dc->hwss.edp_power_control(link, true);
+
+		link->link_enc->funcs->hw_init(link->link_enc);
+	}
 
-	/* Reset Front End*/
-	/* Lock*/
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *cur_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
-		struct timing_generator *tg = cur_pipe_ctx->stream_res.tg;
+		struct timing_generator *tg = dc->res_pool->timing_generators[i];
 
-		if (cur_pipe_ctx->stream)
+		if (tg->funcs->is_tg_enabled(tg))
 			tg->funcs->lock(tg);
 	}
-	/* Disconnect*/
-	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
-		struct pipe_ctx *pipe_ctx_old =
-			&dc->current_state->res_ctx.pipe_ctx[i];
-		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
-		if (!pipe_ctx->stream ||
-				!pipe_ctx->plane_state ||
-				pipe_need_reprogram(pipe_ctx_old, pipe_ctx)) {
+	/* Blank controller using driver code instead of
+	 * command table.
+	 */
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct timing_generator *tg = dc->res_pool->timing_generators[i];
 
-			plane_atomic_disconnect(dc, i);
+		if (tg->funcs->is_tg_enabled(tg)) {
+			tg->funcs->set_blank(tg, true);
+			hwss_wait_for_blank_complete(tg);
 		}
 	}
-	/* Unlock*/
-	for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) {
-		struct pipe_ctx *cur_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
-		struct timing_generator *tg = cur_pipe_ctx->stream_res.tg;
 
-		if (cur_pipe_ctx->stream)
+	/* Reset all MPCC muxes */
+	dc->res_pool->mpc->funcs->mpc_init(dc->res_pool->mpc);
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct timing_generator *tg = dc->res_pool->timing_generators[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+		struct hubp *hubp = dc->res_pool->hubps[i];
+
+		pipe_ctx->stream_res.tg = tg;
+		pipe_ctx->pipe_idx = i;
+
+		pipe_ctx->plane_res.hubp = hubp;
+		hubp->mpcc_id = i;
+		hubp->opp_id = 0xf;
+		hubp->power_gated = false;
+
+		dc->res_pool->opps[i]->mpc_tree_params.opp_id = dc->res_pool->opps[i]->inst;
+		dc->res_pool->opps[i]->mpc_tree_params.opp_list = NULL;
+		dc->res_pool->opps[i]->mpcc_disconnect_pending[i] = true;
+		pipe_ctx->stream_res.opp = dc->res_pool->opps[i];
+
+		plane_atomic_disconnect(dc, pipe_ctx);
+	}
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct timing_generator *tg = dc->res_pool->timing_generators[i];
+
+		if (tg->funcs->is_tg_enabled(tg))
 			tg->funcs->unlock(tg);
 	}
 
-	/* Disable and Powerdown*/
-	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
-		struct pipe_ctx *pipe_ctx_old =
-			&dc->current_state->res_ctx.pipe_ctx[i];
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct timing_generator *tg = dc->res_pool->timing_generators[i];
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
-		/*if (!pipe_ctx_old->stream)
-			continue;*/
+		dcn10_disable_plane(dc, pipe_ctx);
 
-		if (pipe_ctx->stream && pipe_ctx->plane_state
-				&& !pipe_need_reprogram(pipe_ctx_old, pipe_ctx))
-			continue;
+		pipe_ctx->stream_res.tg = NULL;
+		pipe_ctx->plane_res.hubp = NULL;
+
+		tg->funcs->tg_init(tg);
+	}
 
-		plane_atomic_disable(dc, i);
+	for (i = 0; i < dc->res_pool->audio_count; i++) {
+		struct audio *audio = dc->res_pool->audios[i];
 
-		if (!pipe_ctx->stream || !pipe_ctx->plane_state)
-			plane_atomic_power_down(dc, i);
+		audio->funcs->hw_init(audio);
 	}
 
+	if (abm != NULL) {
+		abm->funcs->init_backlight(abm);
+		abm->funcs->abm_init(abm);
+	}
+
+	if (dmcu != NULL)
+		dmcu->funcs->dmcu_init(dmcu);
+
+	/* power AFMT HDMI memory TODO: may move to dis/en output save power*/
+	REG_WRITE(DIO_MEM_PWR_CTRL, 0);
+
+	if (!dc->debug.disable_clock_gate) {
+		/* enable all DCN clock gating */
+		REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0);
+
+		REG_WRITE(DCCG_GATE_DISABLE_CNTL2, 0);
+
+		REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0);
+	}
+
+	enable_power_gating_plane(dc->hwseq, true);
+}
+
+static void reset_hw_ctx_wrap(
+		struct dc *dc,
+		struct dc_state *context)
+{
+	int i;
+
 	/* Reset Back End*/
 	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
 		struct pipe_ctx *pipe_ctx_old =
@@ -1298,7 +856,6 @@ static void reset_hw_ctx_wrap(
 			struct clock_source *old_clk = pipe_ctx_old->clock_source;
 
 			reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
-
 			if (old_clk)
 				old_clk->funcs->cs_power_down(old_clk);
 		}
@@ -1332,21 +889,7 @@ static bool patch_address_for_sbs_tb_stereo(
 	return false;
 }
 
-static void toggle_watermark_change_req(struct dce_hwseq *hws)
-{
-	uint32_t watermark_change_req;
-
-	REG_GET(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, &watermark_change_req);
-
-	if (watermark_change_req)
-		watermark_change_req = 0;
-	else
-		watermark_change_req = 1;
 
-	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, watermark_change_req);
-}
 
 static void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
@@ -1366,8 +909,8 @@ static void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_c
 		pipe_ctx->plane_state->address.grph_stereo.left_addr = addr;
 }
 
-static bool dcn10_set_input_transfer_func(
-	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state)
+static bool dcn10_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
+					  const struct dc_plane_state *plane_state)
 {
 	struct dpp *dpp_base = pipe_ctx->plane_res.dpp;
 	const struct dc_transfer_func *tf = NULL;
@@ -1380,34 +923,28 @@ static bool dcn10_set_input_transfer_func(
 		tf = plane_state->in_transfer_func;
 
 	if (plane_state->gamma_correction && dce_use_lut(plane_state))
-		dpp_base->funcs->ipp_program_input_lut(dpp_base,
-				plane_state->gamma_correction);
+		dpp_base->funcs->dpp_program_input_lut(dpp_base, plane_state->gamma_correction);
 
 	if (tf == NULL)
-		dpp_base->funcs->ipp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_BYPASS);
+		dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_BYPASS);
 	else if (tf->type == TF_TYPE_PREDEFINED) {
 		switch (tf->tf) {
 		case TRANSFER_FUNCTION_SRGB:
-			dpp_base->funcs->ipp_set_degamma(dpp_base,
-					IPP_DEGAMMA_MODE_HW_sRGB);
+			dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_HW_sRGB);
 			break;
 		case TRANSFER_FUNCTION_BT709:
-			dpp_base->funcs->ipp_set_degamma(dpp_base,
-					IPP_DEGAMMA_MODE_HW_xvYCC);
+			dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_HW_xvYCC);
 			break;
 		case TRANSFER_FUNCTION_LINEAR:
-			dpp_base->funcs->ipp_set_degamma(dpp_base,
-					IPP_DEGAMMA_MODE_BYPASS);
+			dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_BYPASS);
 			break;
 		case TRANSFER_FUNCTION_PQ:
-			result = false;
-			break;
 		default:
 			result = false;
 			break;
 		}
 	} else if (tf->type == TF_TYPE_BYPASS) {
-		dpp_base->funcs->ipp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_BYPASS);
+		dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_BYPASS);
 	} else {
 		/*TF_TYPE_DISTRIBUTED_POINTS*/
 		result = false;
@@ -1415,324 +952,14 @@ static bool dcn10_set_input_transfer_func(
 
 	return result;
 }
-/*modify the method to handle rgb for arr_points*/
-static bool convert_to_custom_float(
-		struct pwl_result_data *rgb_resulted,
-		struct curve_points *arr_points,
-		uint32_t hw_points_num)
-{
-	struct custom_float_format fmt;
-
-	struct pwl_result_data *rgb = rgb_resulted;
 
-	uint32_t i = 0;
 
-	fmt.exponenta_bits = 6;
-	fmt.mantissa_bits = 12;
-	fmt.sign = false;
 
-	if (!convert_to_custom_float_format(
-		arr_points[0].x,
-		&fmt,
-		&arr_points[0].custom_float_x)) {
-		BREAK_TO_DEBUGGER();
-		return false;
-	}
-
-	if (!convert_to_custom_float_format(
-		arr_points[0].offset,
-		&fmt,
-		&arr_points[0].custom_float_offset)) {
-		BREAK_TO_DEBUGGER();
-		return false;
-	}
-
-	if (!convert_to_custom_float_format(
-		arr_points[0].slope,
-		&fmt,
-		&arr_points[0].custom_float_slope)) {
-		BREAK_TO_DEBUGGER();
-		return false;
-	}
 
-	fmt.mantissa_bits = 10;
-	fmt.sign = false;
 
-	if (!convert_to_custom_float_format(
-		arr_points[1].x,
-		&fmt,
-		&arr_points[1].custom_float_x)) {
-		BREAK_TO_DEBUGGER();
-		return false;
-	}
-
-	if (!convert_to_custom_float_format(
-		arr_points[1].y,
-		&fmt,
-		&arr_points[1].custom_float_y)) {
-		BREAK_TO_DEBUGGER();
-		return false;
-	}
-
-	if (!convert_to_custom_float_format(
-		arr_points[1].slope,
-		&fmt,
-		&arr_points[1].custom_float_slope)) {
-		BREAK_TO_DEBUGGER();
-		return false;
-	}
-
-	fmt.mantissa_bits = 12;
-	fmt.sign = true;
-
-	while (i != hw_points_num) {
-		if (!convert_to_custom_float_format(
-			rgb->red,
-			&fmt,
-			&rgb->red_reg)) {
-			BREAK_TO_DEBUGGER();
-			return false;
-		}
-
-		if (!convert_to_custom_float_format(
-			rgb->green,
-			&fmt,
-			&rgb->green_reg)) {
-			BREAK_TO_DEBUGGER();
-			return false;
-		}
-
-		if (!convert_to_custom_float_format(
-			rgb->blue,
-			&fmt,
-			&rgb->blue_reg)) {
-			BREAK_TO_DEBUGGER();
-			return false;
-		}
-
-		if (!convert_to_custom_float_format(
-			rgb->delta_red,
-			&fmt,
-			&rgb->delta_red_reg)) {
-			BREAK_TO_DEBUGGER();
-			return false;
-		}
-
-		if (!convert_to_custom_float_format(
-			rgb->delta_green,
-			&fmt,
-			&rgb->delta_green_reg)) {
-			BREAK_TO_DEBUGGER();
-			return false;
-		}
-
-		if (!convert_to_custom_float_format(
-			rgb->delta_blue,
-			&fmt,
-			&rgb->delta_blue_reg)) {
-			BREAK_TO_DEBUGGER();
-			return false;
-		}
-
-		++rgb;
-		++i;
-	}
-
-	return true;
-}
-#define MAX_REGIONS_NUMBER 34
-#define MAX_LOW_POINT      25
-#define NUMBER_SEGMENTS    32
-
-static bool dcn10_translate_regamma_to_hw_format(const struct dc_transfer_func
-		*output_tf, struct pwl_params *regamma_params)
-{
-	struct curve_points *arr_points;
-	struct pwl_result_data *rgb_resulted;
-	struct pwl_result_data *rgb;
-	struct pwl_result_data *rgb_plus_1;
-	struct fixed31_32 y_r;
-	struct fixed31_32 y_g;
-	struct fixed31_32 y_b;
-	struct fixed31_32 y1_min;
-	struct fixed31_32 y3_max;
-
-	int32_t segment_start, segment_end;
-	int32_t i;
-	uint32_t j, k, seg_distr[MAX_REGIONS_NUMBER], increment, start_index, hw_points;
-
-	if (output_tf == NULL || regamma_params == NULL ||
-			output_tf->type == TF_TYPE_BYPASS)
-		return false;
-
-	arr_points = regamma_params->arr_points;
-	rgb_resulted = regamma_params->rgb_resulted;
-	hw_points = 0;
-
-	memset(regamma_params, 0, sizeof(struct pwl_params));
-	memset(seg_distr, 0, sizeof(seg_distr));
-
-	if (output_tf->tf == TRANSFER_FUNCTION_PQ) {
-		/* 32 segments
-		 * segments are from 2^-25 to 2^7
-		 */
-		for (i = 0; i < 32 ; i++)
-			seg_distr[i] = 3;
-
-		segment_start = -25;
-		segment_end   = 7;
-	} else {
-		/* 10 segments
-		 * segment is from 2^-10 to 2^0
-		 * There are less than 256 points, for optimization
-		 */
-		seg_distr[0] = 3;
-		seg_distr[1] = 4;
-		seg_distr[2] = 4;
-		seg_distr[3] = 4;
-		seg_distr[4] = 4;
-		seg_distr[5] = 4;
-		seg_distr[6] = 4;
-		seg_distr[7] = 4;
-		seg_distr[8] = 5;
-		seg_distr[9] = 5;
-
-		segment_start = -10;
-		segment_end = 0;
-	}
-
-	for (i = segment_end - segment_start; i < MAX_REGIONS_NUMBER ; i++)
-		seg_distr[i] = -1;
-
-	for (k = 0; k < MAX_REGIONS_NUMBER; k++) {
-		if (seg_distr[k] != -1)
-			hw_points += (1 << seg_distr[k]);
-	}
-
-	j = 0;
-	for (k = 0; k < (segment_end - segment_start); k++) {
-		increment = NUMBER_SEGMENTS / (1 << seg_distr[k]);
-		start_index = (segment_start + k + MAX_LOW_POINT) * NUMBER_SEGMENTS;
-		for (i = start_index; i < start_index + NUMBER_SEGMENTS; i += increment) {
-			if (j == hw_points - 1)
-				break;
-			rgb_resulted[j].red = output_tf->tf_pts.red[i];
-			rgb_resulted[j].green = output_tf->tf_pts.green[i];
-			rgb_resulted[j].blue = output_tf->tf_pts.blue[i];
-			j++;
-		}
-	}
-
-	/* last point */
-	start_index = (segment_end + MAX_LOW_POINT) * NUMBER_SEGMENTS;
-	rgb_resulted[hw_points - 1].red =
-			output_tf->tf_pts.red[start_index];
-	rgb_resulted[hw_points - 1].green =
-			output_tf->tf_pts.green[start_index];
-	rgb_resulted[hw_points - 1].blue =
-			output_tf->tf_pts.blue[start_index];
-
-	arr_points[0].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-			dal_fixed31_32_from_int(segment_start));
-	arr_points[1].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-			dal_fixed31_32_from_int(segment_end));
-	arr_points[2].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-			dal_fixed31_32_from_int(segment_end));
-
-	y_r = rgb_resulted[0].red;
-	y_g = rgb_resulted[0].green;
-	y_b = rgb_resulted[0].blue;
-
-	y1_min = dal_fixed31_32_min(y_r, dal_fixed31_32_min(y_g, y_b));
-
-	arr_points[0].y = y1_min;
-	arr_points[0].slope = dal_fixed31_32_div(
-					arr_points[0].y,
-					arr_points[0].x);
-	y_r = rgb_resulted[hw_points - 1].red;
-	y_g = rgb_resulted[hw_points - 1].green;
-	y_b = rgb_resulted[hw_points - 1].blue;
-
-	/* see comment above, m_arrPoints[1].y should be the Y value for the
-	 * region end (m_numOfHwPoints), not last HW point(m_numOfHwPoints - 1)
-	 */
-	y3_max = dal_fixed31_32_max(y_r, dal_fixed31_32_max(y_g, y_b));
-
-	arr_points[1].y = y3_max;
-	arr_points[2].y = y3_max;
-
-	arr_points[1].slope = dal_fixed31_32_zero;
-	arr_points[2].slope = dal_fixed31_32_zero;
-
-	if (output_tf->tf == TRANSFER_FUNCTION_PQ) {
-		/* for PQ, we want to have a straight line from last HW X point,
-		 * and the slope to be such that we hit 1.0 at 10000 nits.
-		 */
-		const struct fixed31_32 end_value =
-				dal_fixed31_32_from_int(125);
-
-		arr_points[1].slope = dal_fixed31_32_div(
-			dal_fixed31_32_sub(dal_fixed31_32_one, arr_points[1].y),
-			dal_fixed31_32_sub(end_value, arr_points[1].x));
-		arr_points[2].slope = dal_fixed31_32_div(
-			dal_fixed31_32_sub(dal_fixed31_32_one, arr_points[1].y),
-			dal_fixed31_32_sub(end_value, arr_points[1].x));
-	}
-
-	regamma_params->hw_points_num = hw_points;
-
-	i = 1;
-	for (k = 0; k < MAX_REGIONS_NUMBER && i < MAX_REGIONS_NUMBER; k++) {
-		if (seg_distr[k] != -1) {
-			regamma_params->arr_curve_points[k].segments_num =
-					seg_distr[k];
-			regamma_params->arr_curve_points[i].offset =
-					regamma_params->arr_curve_points[k].
-					offset + (1 << seg_distr[k]);
-		}
-		i++;
-	}
-
-	if (seg_distr[k] != -1)
-		regamma_params->arr_curve_points[k].segments_num =
-				seg_distr[k];
-
-	rgb = rgb_resulted;
-	rgb_plus_1 = rgb_resulted + 1;
-
-	i = 1;
-
-	while (i != hw_points + 1) {
-		if (dal_fixed31_32_lt(rgb_plus_1->red, rgb->red))
-			rgb_plus_1->red = rgb->red;
-		if (dal_fixed31_32_lt(rgb_plus_1->green, rgb->green))
-			rgb_plus_1->green = rgb->green;
-		if (dal_fixed31_32_lt(rgb_plus_1->blue, rgb->blue))
-			rgb_plus_1->blue = rgb->blue;
-
-		rgb->delta_red = dal_fixed31_32_sub(
-			rgb_plus_1->red,
-			rgb->red);
-		rgb->delta_green = dal_fixed31_32_sub(
-			rgb_plus_1->green,
-			rgb->green);
-		rgb->delta_blue = dal_fixed31_32_sub(
-			rgb_plus_1->blue,
-			rgb->blue);
-
-		++rgb_plus_1;
-		++rgb;
-		++i;
-	}
-
-	convert_to_custom_float(rgb_resulted, arr_points, hw_points);
-
-	return true;
-}
-
-static bool dcn10_set_output_transfer_func(
-	struct pipe_ctx *pipe_ctx,
-	const struct dc_stream_state *stream)
+static bool
+dcn10_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
+			       const struct dc_stream_state *stream)
 {
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 
@@ -1742,18 +969,21 @@ static bool dcn10_set_output_transfer_func(
 	dpp->regamma_params.hw_points_num = GAMMA_HW_POINTS_NUM;
 
 	if (stream->out_transfer_func &&
-		stream->out_transfer_func->type ==
-			TF_TYPE_PREDEFINED &&
-		stream->out_transfer_func->tf ==
-			TRANSFER_FUNCTION_SRGB) {
-		dpp->funcs->opp_set_regamma_mode(dpp, OPP_REGAMMA_SRGB);
-	} else if (dcn10_translate_regamma_to_hw_format(
-				stream->out_transfer_func, &dpp->regamma_params)) {
-			dpp->funcs->opp_program_regamma_pwl(dpp, &dpp->regamma_params);
-			dpp->funcs->opp_set_regamma_mode(dpp, OPP_REGAMMA_USER);
-	} else {
-		dpp->funcs->opp_set_regamma_mode(dpp, OPP_REGAMMA_BYPASS);
-	}
+	    stream->out_transfer_func->type == TF_TYPE_PREDEFINED &&
+	    stream->out_transfer_func->tf == TRANSFER_FUNCTION_SRGB)
+		dpp->funcs->dpp_program_regamma_pwl(dpp, NULL, OPP_REGAMMA_SRGB);
+
+	/* dcn10_translate_regamma_to_hw_format takes 750us, only do it when full
+	 * update.
+	 */
+	else if (cm_helper_translate_curve_to_hw_format(
+			stream->out_transfer_func,
+			&dpp->regamma_params, false)) {
+		dpp->funcs->dpp_program_regamma_pwl(
+				dpp,
+				&dpp->regamma_params, OPP_REGAMMA_USER);
+	} else
+		dpp->funcs->dpp_program_regamma_pwl(dpp, NULL, OPP_REGAMMA_BYPASS);
 
 	return true;
 }
@@ -1772,7 +1002,7 @@ static void dcn10_pipe_control_lock(
 		return;
 
 	if (dc->debug.sanity_checks)
-		verify_allow_pstate_change_high(dc->hwseq);
+		dcn10_verify_allow_pstate_change_high(dc);
 
 	if (lock)
 		pipe->stream_res.tg->funcs->lock(pipe->stream_res.tg);
@@ -1780,7 +1010,7 @@ static void dcn10_pipe_control_lock(
 		pipe->stream_res.tg->funcs->unlock(pipe->stream_res.tg);
 
 	if (dc->debug.sanity_checks)
-		verify_allow_pstate_change_high(dc->hwseq);
+		dcn10_verify_allow_pstate_change_high(dc);
 }
 
 static bool wait_for_reset_trigger_to_occur(
@@ -1833,14 +1063,15 @@ static void dcn10_enable_timing_synchronization(
 
 	for (i = 1; i < group_size; i++)
 		grouped_pipes[i]->stream_res.tg->funcs->enable_reset_trigger(
-				grouped_pipes[i]->stream_res.tg, grouped_pipes[0]->stream_res.tg->inst);
-
+				grouped_pipes[i]->stream_res.tg,
+				grouped_pipes[0]->stream_res.tg->inst);
 
 	DC_SYNC_INFO("Waiting for trigger\n");
 
 	/* Need to get only check 1 pipe for having reset as all the others are
 	 * synchronized. Look at last pipe programmed to reset.
 	 */
+
 	wait_for_reset_trigger_to_occur(dc_ctx, grouped_pipes[1]->stream_res.tg);
 	for (i = 1; i < group_size; i++)
 		grouped_pipes[i]->stream_res.tg->funcs->disable_reset_trigger(
@@ -1849,7 +1080,30 @@ static void dcn10_enable_timing_synchronization(
 	DC_SYNC_INFO("Sync complete\n");
 }
 
-static void print_rq_dlg_ttu(
+static void dcn10_enable_per_frame_crtc_position_reset(
+	struct dc *dc,
+	int group_size,
+	struct pipe_ctx *grouped_pipes[])
+{
+	struct dc_context *dc_ctx = dc->ctx;
+	int i;
+
+	DC_SYNC_INFO("Setting up\n");
+	for (i = 0; i < group_size; i++)
+		grouped_pipes[i]->stream_res.tg->funcs->enable_crtc_reset(
+				grouped_pipes[i]->stream_res.tg,
+				grouped_pipes[i]->stream->triggered_crtc_reset.event_source->status.primary_otg_inst,
+				&grouped_pipes[i]->stream->triggered_crtc_reset);
+
+	DC_SYNC_INFO("Waiting for trigger\n");
+
+	for (i = 1; i < group_size; i++)
+		wait_for_reset_trigger_to_occur(dc_ctx, grouped_pipes[i]->stream_res.tg);
+
+	DC_SYNC_INFO("Multi-display sync is complete\n");
+}
+
+/*static void print_rq_dlg_ttu(
 		struct dc *core_dc,
 		struct pipe_ctx *pipe_ctx)
 {
@@ -1970,19 +1224,104 @@ static void print_rq_dlg_ttu(
 			pipe_ctx->rq_regs.rq_regs_l.pte_row_height_linear
 			);
 }
+*/
+
+static void mmhub_read_vm_system_aperture_settings(struct dcn10_hubp *hubp1,
+		struct vm_system_aperture_param *apt,
+		struct dce_hwseq *hws)
+{
+	PHYSICAL_ADDRESS_LOC physical_page_number;
+	uint32_t logical_addr_low;
+	uint32_t logical_addr_high;
+
+	REG_GET(MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB,
+			PHYSICAL_PAGE_NUMBER_MSB, &physical_page_number.high_part);
+	REG_GET(MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB,
+			PHYSICAL_PAGE_NUMBER_LSB, &physical_page_number.low_part);
+
+	REG_GET(MC_VM_SYSTEM_APERTURE_LOW_ADDR,
+			LOGICAL_ADDR, &logical_addr_low);
+
+	REG_GET(MC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+			LOGICAL_ADDR, &logical_addr_high);
+
+	apt->sys_default.quad_part =  physical_page_number.quad_part << 12;
+	apt->sys_low.quad_part =  (int64_t)logical_addr_low << 18;
+	apt->sys_high.quad_part =  (int64_t)logical_addr_high << 18;
+}
+
+/* Temporary read settings, future will get values from kmd directly */
+static void mmhub_read_vm_context0_settings(struct dcn10_hubp *hubp1,
+		struct vm_context0_param *vm0,
+		struct dce_hwseq *hws)
+{
+	PHYSICAL_ADDRESS_LOC fb_base;
+	PHYSICAL_ADDRESS_LOC fb_offset;
+	uint32_t fb_base_value;
+	uint32_t fb_offset_value;
+
+	REG_GET(DCHUBBUB_SDPIF_FB_BASE, SDPIF_FB_BASE, &fb_base_value);
+	REG_GET(DCHUBBUB_SDPIF_FB_OFFSET, SDPIF_FB_OFFSET, &fb_offset_value);
+
+	REG_GET(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32,
+			PAGE_DIRECTORY_ENTRY_HI32, &vm0->pte_base.high_part);
+	REG_GET(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32,
+			PAGE_DIRECTORY_ENTRY_LO32, &vm0->pte_base.low_part);
+
+	REG_GET(VM_CONTEXT0_PAGE_TABLE_START_ADDR_HI32,
+			LOGICAL_PAGE_NUMBER_HI4, &vm0->pte_start.high_part);
+	REG_GET(VM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32,
+			LOGICAL_PAGE_NUMBER_LO32, &vm0->pte_start.low_part);
+
+	REG_GET(VM_CONTEXT0_PAGE_TABLE_END_ADDR_HI32,
+			LOGICAL_PAGE_NUMBER_HI4, &vm0->pte_end.high_part);
+	REG_GET(VM_CONTEXT0_PAGE_TABLE_END_ADDR_LO32,
+			LOGICAL_PAGE_NUMBER_LO32, &vm0->pte_end.low_part);
+
+	REG_GET(VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_HI32,
+			PHYSICAL_PAGE_ADDR_HI4, &vm0->fault_default.high_part);
+	REG_GET(VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_LO32,
+			PHYSICAL_PAGE_ADDR_LO32, &vm0->fault_default.low_part);
+
+	/*
+	 * The values in VM_CONTEXT0_PAGE_TABLE_BASE_ADDR is in UMA space.
+	 * Therefore we need to do
+	 * DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR = VM_CONTEXT0_PAGE_TABLE_BASE_ADDR
+	 * - DCHUBBUB_SDPIF_FB_OFFSET + DCHUBBUB_SDPIF_FB_BASE
+	 */
+	fb_base.quad_part = (uint64_t)fb_base_value << 24;
+	fb_offset.quad_part = (uint64_t)fb_offset_value << 24;
+	vm0->pte_base.quad_part += fb_base.quad_part;
+	vm0->pte_base.quad_part -= fb_offset.quad_part;
+}
+
 
-static void dcn10_power_on_fe(
+static void dcn10_program_pte_vm(struct dce_hwseq *hws, struct hubp *hubp)
+{
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+	struct vm_system_aperture_param apt = { {{ 0 } } };
+	struct vm_context0_param vm0 = { { { 0 } } };
+
+	mmhub_read_vm_system_aperture_settings(hubp1, &apt, hws);
+	mmhub_read_vm_context0_settings(hubp1, &vm0, hws);
+
+	hubp->funcs->hubp_set_vm_system_aperture_settings(hubp, &apt);
+	hubp->funcs->hubp_set_vm_context0_settings(hubp, &vm0);
+}
+
+static void dcn10_enable_plane(
 	struct dc *dc,
 	struct pipe_ctx *pipe_ctx,
 	struct dc_state *context)
 {
-	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct dce_hwseq *hws = dc->hwseq;
 
 	if (dc->debug.sanity_checks) {
-		verify_allow_pstate_change_high(dc->hwseq);
+		dcn10_verify_allow_pstate_change_high(dc);
 	}
 
+	undo_DEGVIDCN10_253_wa(dc);
+
 	power_on_plane(dc->hwseq,
 		pipe_ctx->pipe_idx);
 
@@ -1993,8 +1332,8 @@ static void dcn10_power_on_fe(
 	/* make sure OPP_PIPE_CLOCK_EN = 1 */
 	REG_UPDATE(OPP_PIPE_CONTROL[pipe_ctx->stream_res.tg->inst],
 			OPP_PIPE_CLOCK_EN, 1);
-	/*TODO: REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, 0x1f);*/
 
+/* TODO: enable/disable in dm as per update type.
 	if (plane_state) {
 		dm_logger_write(dc->ctx->logger, LOG_DC,
 				"Pipe:%d 0x%x: addr hi:0x%x, "
@@ -2030,9 +1369,12 @@ static void dcn10_power_on_fe(
 				pipe_ctx->plane_res.scl_data.recout.y);
 		print_rq_dlg_ttu(dc, pipe_ctx);
 	}
+*/
+	if (dc->config.gpu_vm_support)
+		dcn10_program_pte_vm(hws, pipe_ctx->plane_res.hubp);
 
 	if (dc->debug.sanity_checks) {
-		verify_allow_pstate_change_high(dc->hwseq);
+		dcn10_verify_allow_pstate_change_high(dc);
 	}
 }
 
@@ -2082,23 +1424,27 @@ static void program_csc_matrix(struct pipe_ctx *pipe_ctx,
 		enum dc_color_space colorspace,
 		uint16_t *matrix)
 {
-	int i;
-	struct out_csc_color_matrix tbl_entry;
-
-	if (pipe_ctx->stream->csc_color_matrix.enable_adjustment
-				== true) {
-			enum dc_color_space color_space =
-				pipe_ctx->stream->output_color_space;
-
-			//uint16_t matrix[12];
-			for (i = 0; i < 12; i++)
-				tbl_entry.regval[i] = pipe_ctx->stream->csc_color_matrix.matrix[i];
-
-			tbl_entry.color_space = color_space;
-			//tbl_entry.regval = matrix;
-			pipe_ctx->plane_res.dpp->funcs->opp_set_csc_adjustment(pipe_ctx->plane_res.dpp, &tbl_entry);
+	if (pipe_ctx->stream->csc_color_matrix.enable_adjustment == true) {
+			if (pipe_ctx->plane_res.dpp->funcs->dpp_set_csc_adjustment != NULL)
+				pipe_ctx->plane_res.dpp->funcs->dpp_set_csc_adjustment(pipe_ctx->plane_res.dpp, matrix);
+	} else {
+		if (pipe_ctx->plane_res.dpp->funcs->dpp_set_csc_default != NULL)
+			pipe_ctx->plane_res.dpp->funcs->dpp_set_csc_default(pipe_ctx->plane_res.dpp, colorspace);
 	}
 }
+
+static void program_output_csc(struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		enum dc_color_space colorspace,
+		uint16_t *matrix,
+		int opp_id)
+{
+	if (pipe_ctx->plane_res.dpp->funcs->dpp_set_csc_adjustment != NULL)
+		program_csc_matrix(pipe_ctx,
+				colorspace,
+				matrix);
+}
+
 static bool is_lower_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
 {
 	if (pipe_ctx->plane_state->visible)
@@ -2186,91 +1532,169 @@ static void dcn10_get_surface_visual_confirm_color(
 	}
 }
 
-static void mmhub_read_vm_system_aperture_settings(struct dcn10_hubp *hubp1,
-		struct vm_system_aperture_param *apt,
-		struct dce_hwseq *hws)
+static uint16_t fixed_point_to_int_frac(
+	struct fixed31_32 arg,
+	uint8_t integer_bits,
+	uint8_t fractional_bits)
 {
-	PHYSICAL_ADDRESS_LOC physical_page_number;
-	uint32_t logical_addr_low;
-	uint32_t logical_addr_high;
+	int32_t numerator;
+	int32_t divisor = 1 << fractional_bits;
 
-	REG_GET(MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB,
-			PHYSICAL_PAGE_NUMBER_MSB, &physical_page_number.high_part);
-	REG_GET(MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB,
-			PHYSICAL_PAGE_NUMBER_LSB, &physical_page_number.low_part);
+	uint16_t result;
 
-	REG_GET(MC_VM_SYSTEM_APERTURE_LOW_ADDR,
-			LOGICAL_ADDR, &logical_addr_low);
+	uint16_t d = (uint16_t)dal_fixed31_32_floor(
+		dal_fixed31_32_abs(
+			arg));
 
-	REG_GET(MC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			LOGICAL_ADDR, &logical_addr_high);
+	if (d <= (uint16_t)(1 << integer_bits) - (1 / (uint16_t)divisor))
+		numerator = (uint16_t)dal_fixed31_32_floor(
+			dal_fixed31_32_mul_int(
+				arg,
+				divisor));
+	else {
+		numerator = dal_fixed31_32_floor(
+			dal_fixed31_32_sub(
+				dal_fixed31_32_from_int(
+					1LL << integer_bits),
+				dal_fixed31_32_recip(
+					dal_fixed31_32_from_int(
+						divisor))));
+	}
 
-	apt->sys_default.quad_part =  physical_page_number.quad_part << 12;
-	apt->sys_low.quad_part =  (int64_t)logical_addr_low << 18;
-	apt->sys_high.quad_part =  (int64_t)logical_addr_high << 18;
+	if (numerator >= 0)
+		result = (uint16_t)numerator;
+	else
+		result = (uint16_t)(
+		(1 << (integer_bits + fractional_bits + 1)) + numerator);
+
+	if ((result != 0) && dal_fixed31_32_lt(
+		arg, dal_fixed31_32_zero))
+		result |= 1 << (integer_bits + fractional_bits);
+
+	return result;
 }
 
-/* Temporary read settings, future will get values from kmd directly */
-static void mmhub_read_vm_context0_settings(struct dcn10_hubp *hubp1,
-		struct vm_context0_param *vm0,
-		struct dce_hwseq *hws)
+void build_prescale_params(struct  dc_bias_and_scale *bias_and_scale,
+		const struct dc_plane_state *plane_state)
+{
+	if (plane_state->format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN
+			&& plane_state->format != SURFACE_PIXEL_FORMAT_INVALID
+			&& plane_state->input_csc_color_matrix.enable_adjustment
+			&& plane_state->coeff_reduction_factor.value != 0) {
+		bias_and_scale->scale_blue = fixed_point_to_int_frac(
+			dal_fixed31_32_mul(plane_state->coeff_reduction_factor,
+					dal_fixed31_32_from_fraction(256, 255)),
+				2,
+				13);
+		bias_and_scale->scale_red = bias_and_scale->scale_blue;
+		bias_and_scale->scale_green = bias_and_scale->scale_blue;
+	} else {
+		bias_and_scale->scale_blue = 0x2000;
+		bias_and_scale->scale_red = 0x2000;
+		bias_and_scale->scale_green = 0x2000;
+	}
+}
+
+static void update_dpp(struct dpp *dpp, struct dc_plane_state *plane_state)
 {
-	PHYSICAL_ADDRESS_LOC fb_base;
-	PHYSICAL_ADDRESS_LOC fb_offset;
-	uint32_t fb_base_value;
-	uint32_t fb_offset_value;
+	struct dc_bias_and_scale bns_params = {0};
 
-	REG_GET(DCHUBBUB_SDPIF_FB_BASE, SDPIF_FB_BASE, &fb_base_value);
-	REG_GET(DCHUBBUB_SDPIF_FB_OFFSET, SDPIF_FB_OFFSET, &fb_offset_value);
+	// program the input csc
+	dpp->funcs->dpp_setup(dpp,
+			plane_state->format,
+			EXPANSION_MODE_ZERO,
+			plane_state->input_csc_color_matrix,
+			COLOR_SPACE_YCBCR601_LIMITED);
 
-	REG_GET(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32,
-			PAGE_DIRECTORY_ENTRY_HI32, &vm0->pte_base.high_part);
-	REG_GET(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32,
-			PAGE_DIRECTORY_ENTRY_LO32, &vm0->pte_base.low_part);
+	//set scale and bias registers
+	build_prescale_params(&bns_params, plane_state);
+	if (dpp->funcs->dpp_program_bias_and_scale)
+		dpp->funcs->dpp_program_bias_and_scale(dpp, &bns_params);
+}
 
-	REG_GET(VM_CONTEXT0_PAGE_TABLE_START_ADDR_HI32,
-			LOGICAL_PAGE_NUMBER_HI4, &vm0->pte_start.high_part);
-	REG_GET(VM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32,
-			LOGICAL_PAGE_NUMBER_LO32, &vm0->pte_start.low_part);
+static void update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
+{
+	struct hubp *hubp = pipe_ctx->plane_res.hubp;
+	struct mpcc_blnd_cfg blnd_cfg;
+	bool per_pixel_alpha = pipe_ctx->plane_state->per_pixel_alpha && pipe_ctx->bottom_pipe;
+	int mpcc_id;
+	struct mpcc *new_mpcc;
+	struct mpc *mpc = dc->res_pool->mpc;
+	struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params);
 
-	REG_GET(VM_CONTEXT0_PAGE_TABLE_END_ADDR_HI32,
-			LOGICAL_PAGE_NUMBER_HI4, &vm0->pte_end.high_part);
-	REG_GET(VM_CONTEXT0_PAGE_TABLE_END_ADDR_LO32,
-			LOGICAL_PAGE_NUMBER_LO32, &vm0->pte_end.low_part);
+	/* TODO: proper fix once fpga works */
 
-	REG_GET(VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_HI32,
-			PHYSICAL_PAGE_ADDR_HI4, &vm0->fault_default.high_part);
-	REG_GET(VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_LO32,
-			PHYSICAL_PAGE_ADDR_LO32, &vm0->fault_default.low_part);
+	if (dc->debug.surface_visual_confirm)
+		dcn10_get_surface_visual_confirm_color(
+				pipe_ctx, &blnd_cfg.black_color);
+	else
+		color_space_to_black_color(
+			dc, pipe_ctx->stream->output_color_space,
+			&blnd_cfg.black_color);
+
+	if (per_pixel_alpha)
+		blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA;
+	else
+		blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA;
+
+	blnd_cfg.overlap_only = false;
+	blnd_cfg.global_alpha = 0xff;
+	blnd_cfg.global_gain = 0xff;
+
+	/* DCN1.0 has output CM before MPC which seems to screw with
+	 * pre-multiplied alpha.
+	 */
+	blnd_cfg.pre_multiplied_alpha = is_rgb_cspace(
+			pipe_ctx->stream->output_color_space)
+					&& per_pixel_alpha;
 
 	/*
-	 * The values in VM_CONTEXT0_PAGE_TABLE_BASE_ADDR is in UMA space.
-	 * Therefore we need to do
-	 * DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR = VM_CONTEXT0_PAGE_TABLE_BASE_ADDR
-	 * - DCHUBBUB_SDPIF_FB_OFFSET + DCHUBBUB_SDPIF_FB_BASE
+	 * TODO: remove hack
+	 * Note: currently there is a bug in init_hw such that
+	 * on resume from hibernate, BIOS sets up MPCC0, and
+	 * we do mpcc_remove but the mpcc cannot go to idle
+	 * after remove. This cause us to pick mpcc1 here,
+	 * which causes a pstate hang for yet unknown reason.
 	 */
-	fb_base.quad_part = (uint64_t)fb_base_value << 24;
-	fb_offset.quad_part = (uint64_t)fb_offset_value << 24;
-	vm0->pte_base.quad_part += fb_base.quad_part;
-	vm0->pte_base.quad_part -= fb_offset.quad_part;
+	mpcc_id = hubp->inst;
+
+	/* check if this MPCC is already being used */
+	new_mpcc = mpc->funcs->get_mpcc_for_dpp(mpc_tree_params, mpcc_id);
+	/* remove MPCC if being used */
+	if (new_mpcc != NULL)
+		mpc->funcs->remove_mpcc(mpc, mpc_tree_params, new_mpcc);
+	else
+		if (dc->debug.sanity_checks)
+			mpc->funcs->assert_mpcc_idle_before_connect(
+					dc->res_pool->mpc, mpcc_id);
+
+	/* Call MPC to insert new plane */
+	new_mpcc = mpc->funcs->insert_plane(dc->res_pool->mpc,
+			mpc_tree_params,
+			&blnd_cfg,
+			NULL,
+			NULL,
+			hubp->inst,
+			mpcc_id);
+
+	ASSERT(new_mpcc != NULL);
+
+	hubp->opp_id = pipe_ctx->stream_res.opp->inst;
+	hubp->mpcc_id = mpcc_id;
 }
 
-static void dcn10_program_pte_vm(struct hubp *hubp,
-		enum surface_pixel_format format,
-		union dc_tiling_info *tiling_info,
-		enum dc_rotation_angle rotation,
-		struct dce_hwseq *hws)
+static void update_scaler(struct pipe_ctx *pipe_ctx)
 {
-	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
-	struct vm_system_aperture_param apt = { {{ 0 } } };
-	struct vm_context0_param vm0 = { { { 0 } } };
-
+	bool per_pixel_alpha =
+			pipe_ctx->plane_state->per_pixel_alpha && pipe_ctx->bottom_pipe;
 
-	mmhub_read_vm_system_aperture_settings(hubp1, &apt, hws);
-	mmhub_read_vm_context0_settings(hubp1, &vm0, hws);
+	/* TODO: proper fix once fpga works */
 
-	hubp->funcs->hubp_set_vm_system_aperture_settings(hubp, &apt);
-	hubp->funcs->hubp_set_vm_context0_settings(hubp, &vm0);
+	pipe_ctx->plane_res.scl_data.lb_params.alpha_en = per_pixel_alpha;
+	pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP;
+	/* scaler configuration */
+	pipe_ctx->plane_res.dpp->funcs->dpp_set_scaler(
+			pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data);
 }
 
 static void update_dchubp_dpp(
@@ -2283,95 +1707,89 @@ static void update_dchubp_dpp(
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	union plane_size size = plane_state->plane_size;
-	struct mpcc_cfg mpcc_cfg = {0};
-	struct pipe_ctx *top_pipe;
-	bool per_pixel_alpha = plane_state->per_pixel_alpha && pipe_ctx->bottom_pipe;
 
-	/* TODO: proper fix once fpga works */
 	/* depends on DML calculation, DPP clock value may change dynamically */
-	enable_dppclk(
-		dc->hwseq,
-		pipe_ctx->pipe_idx,
-		pipe_ctx->stream_res.pix_clk_params.requested_pix_clk,
-		context->bw.dcn.calc_clk.dppclk_div);
-	dc->current_state->bw.dcn.cur_clk.dppclk_div =
-			context->bw.dcn.calc_clk.dppclk_div;
-	context->bw.dcn.cur_clk.dppclk_div = context->bw.dcn.calc_clk.dppclk_div;
+	if (plane_state->update_flags.bits.full_update) {
+		enable_dppclk(
+			dc->hwseq,
+			pipe_ctx->pipe_idx,
+			pipe_ctx->stream_res.pix_clk_params.requested_pix_clk,
+			context->bw.dcn.calc_clk.dppclk_div);
+		dc->current_state->bw.dcn.cur_clk.dppclk_div =
+				context->bw.dcn.calc_clk.dppclk_div;
+		context->bw.dcn.cur_clk.dppclk_div = context->bw.dcn.calc_clk.dppclk_div;
+	}
 
 	/* TODO: Need input parameter to tell current DCHUB pipe tie to which OTG
 	 * VTG is within DCHUBBUB which is commond block share by each pipe HUBP.
 	 * VTG is 1:1 mapping with OTG. Each pipe HUBP will select which VTG
 	 */
-	REG_UPDATE(DCHUBP_CNTL[pipe_ctx->pipe_idx], HUBP_VTG_SEL, pipe_ctx->stream_res.tg->inst);
+	if (plane_state->update_flags.bits.full_update) {
+		REG_UPDATE(DCHUBP_CNTL[pipe_ctx->pipe_idx], HUBP_VTG_SEL, pipe_ctx->stream_res.tg->inst);
 
-	hubp->funcs->hubp_setup(
-		hubp,
-		&pipe_ctx->dlg_regs,
-		&pipe_ctx->ttu_regs,
-		&pipe_ctx->rq_regs,
-		&pipe_ctx->pipe_dlg_param);
+		hubp->funcs->hubp_setup(
+			hubp,
+			&pipe_ctx->dlg_regs,
+			&pipe_ctx->ttu_regs,
+			&pipe_ctx->rq_regs,
+			&pipe_ctx->pipe_dlg_param);
+	}
 
 	size.grph.surface_size = pipe_ctx->plane_res.scl_data.viewport;
 
-	if (dc->config.gpu_vm_support)
-		dcn10_program_pte_vm(
-				pipe_ctx->plane_res.hubp,
-				plane_state->format,
-				&plane_state->tiling_info,
-				plane_state->rotation,
-				hws
-				);
-
-	dpp->funcs->ipp_setup(dpp,
+	if (plane_state->update_flags.bits.full_update ||
+		plane_state->update_flags.bits.bpp_change)
+		update_dpp(dpp, plane_state);
+
+	if (plane_state->update_flags.bits.full_update ||
+		plane_state->update_flags.bits.per_pixel_alpha_change)
+		update_mpcc(dc, pipe_ctx);
+
+	if (plane_state->update_flags.bits.full_update ||
+		plane_state->update_flags.bits.per_pixel_alpha_change ||
+		plane_state->update_flags.bits.scaling_change ||
+		plane_state->update_flags.bits.position_change) {
+		update_scaler(pipe_ctx);
+	}
+
+	if (plane_state->update_flags.bits.full_update ||
+		plane_state->update_flags.bits.scaling_change ||
+		plane_state->update_flags.bits.position_change) {
+		hubp->funcs->mem_program_viewport(
+			hubp,
+			&pipe_ctx->plane_res.scl_data.viewport,
+			&pipe_ctx->plane_res.scl_data.viewport_c);
+	}
+
+	if (plane_state->update_flags.bits.full_update) {
+		/*gamut remap*/
+		program_gamut_remap(pipe_ctx);
+
+		program_output_csc(dc,
+				pipe_ctx,
+				pipe_ctx->stream->output_color_space,
+				pipe_ctx->stream->csc_color_matrix.matrix,
+				hubp->opp_id);
+	}
+
+	if (plane_state->update_flags.bits.full_update ||
+		plane_state->update_flags.bits.horizontal_mirror_change ||
+		plane_state->update_flags.bits.rotation_change ||
+		plane_state->update_flags.bits.swizzle_change ||
+		plane_state->update_flags.bits.dcc_change ||
+		plane_state->update_flags.bits.bpp_change ||
+		plane_state->update_flags.bits.scaling_change) {
+		hubp->funcs->hubp_program_surface_config(
+			hubp,
 			plane_state->format,
-			EXPANSION_MODE_ZERO);
-
-	mpcc_cfg.dpp_id = hubp->inst;
-	mpcc_cfg.opp_id = pipe_ctx->stream_res.opp->inst;
-	mpcc_cfg.tree_cfg = &(pipe_ctx->stream_res.opp->mpc_tree);
-	for (top_pipe = pipe_ctx->top_pipe; top_pipe; top_pipe = top_pipe->top_pipe)
-		mpcc_cfg.z_index++;
-	if (dc->debug.surface_visual_confirm)
-		dcn10_get_surface_visual_confirm_color(
-				pipe_ctx, &mpcc_cfg.black_color);
-	else
-		color_space_to_black_color(
-			dc, pipe_ctx->stream->output_color_space,
-			&mpcc_cfg.black_color);
-	mpcc_cfg.per_pixel_alpha = per_pixel_alpha;
-	/* DCN1.0 has output CM before MPC which seems to screw with
-	 * pre-multiplied alpha.
-	 */
-	mpcc_cfg.pre_multiplied_alpha = is_rgb_cspace(
-			pipe_ctx->stream->output_color_space)
-					&& per_pixel_alpha;
-	hubp->mpcc_id = dc->res_pool->mpc->funcs->add(dc->res_pool->mpc, &mpcc_cfg);
-	hubp->opp_id = mpcc_cfg.opp_id;
-
-	pipe_ctx->plane_res.scl_data.lb_params.alpha_en = per_pixel_alpha;
-	pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP;
-	/* scaler configuration */
-	pipe_ctx->plane_res.dpp->funcs->dpp_set_scaler(
-			pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data);
-
-	hubp->funcs->mem_program_viewport(hubp,
-			&pipe_ctx->plane_res.scl_data.viewport, &pipe_ctx->plane_res.scl_data.viewport_c);
-
-	/*gamut remap*/
-	program_gamut_remap(pipe_ctx);
-
-	program_csc_matrix(pipe_ctx,
-			pipe_ctx->stream->output_color_space,
-			pipe_ctx->stream->csc_color_matrix.matrix);
+			&plane_state->tiling_info,
+			&size,
+			plane_state->rotation,
+			&plane_state->dcc,
+			plane_state->horizontal_mirror);
+	}
 
-	hubp->funcs->hubp_program_surface_config(
-		hubp,
-		plane_state->format,
-		&plane_state->tiling_info,
-		&size,
-		plane_state->rotation,
-		&plane_state->dcc,
-		plane_state->horizontal_mirror);
+	hubp->power_gated = false;
 
 	dc->hwss.update_plane_addr(dc, pipe_ctx);
 
@@ -2385,23 +1803,9 @@ static void program_all_pipe_in_tree(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
 {
-	unsigned int ref_clk_mhz = dc->res_pool->ref_clock_inKhz/1000;
 
 	if (pipe_ctx->top_pipe == NULL) {
 
-		/* lock otg_master_update to process all pipes associated with
-		 * this OTG. this is done only one time.
-		 */
-		/* watermark is for all pipes */
-		program_watermarks(dc->hwseq, &context->bw.dcn.watermarks, ref_clk_mhz);
-
-		if (dc->debug.sanity_checks) {
-			/* pstate stuck check after watermark update */
-			verify_allow_pstate_change_high(dc->hwseq);
-		}
-
-		pipe_ctx->stream_res.tg->funcs->lock(pipe_ctx->stream_res.tg);
-
 		pipe_ctx->stream_res.tg->dlg_otg_param.vready_offset = pipe_ctx->pipe_dlg_param.vready_offset;
 		pipe_ctx->stream_res.tg->dlg_otg_param.vstartup_start = pipe_ctx->pipe_dlg_param.vstartup_start;
 		pipe_ctx->stream_res.tg->dlg_otg_param.vupdate_offset = pipe_ctx->pipe_dlg_param.vupdate_offset;
@@ -2410,46 +1814,33 @@ static void program_all_pipe_in_tree(
 
 		pipe_ctx->stream_res.tg->funcs->program_global_sync(
 				pipe_ctx->stream_res.tg);
-		pipe_ctx->stream_res.tg->funcs->set_blank(pipe_ctx->stream_res.tg, !is_pipe_tree_visible(pipe_ctx));
+
+		if (pipe_ctx->stream_res.tg->funcs->set_blank)
+			pipe_ctx->stream_res.tg->funcs->set_blank(
+					pipe_ctx->stream_res.tg,
+					!is_pipe_tree_visible(pipe_ctx));
 	}
 
 	if (pipe_ctx->plane_state != NULL) {
-		struct dc_cursor_position position = { 0 };
 		struct pipe_ctx *cur_pipe_ctx =
 				&dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx];
 
-		dcn10_power_on_fe(dc, pipe_ctx, context);
-
-		/* temporary dcn1 wa:
-		 *   watermark update requires toggle after a/b/c/d sets are programmed
-		 *   if hubp is pg then wm value doesn't get properaged to hubp
-		 *   need to toggle after ungate to ensure wm gets to hubp.
-		 *
-		 * final solution:  we need to get SMU to do the toggle as
-		 * DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST is owned by SMU we should have
-		 * both driver and fw accessing same register
-		 */
-		toggle_watermark_change_req(dc->hwseq);
+		if (pipe_ctx->plane_state->update_flags.bits.full_update)
+			dcn10_enable_plane(dc, pipe_ctx, context);
 
 		update_dchubp_dpp(dc, pipe_ctx, context);
 
-		/* TODO: this is a hack w/a for switching from mpo to pipe split */
-		dc_stream_set_cursor_position(pipe_ctx->stream, &position);
+		if (cur_pipe_ctx->plane_state != pipe_ctx->plane_state)
+			dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
 
-		dc_stream_set_cursor_attributes(pipe_ctx->stream,
-				&pipe_ctx->stream->cursor_attributes);
-
-		if (cur_pipe_ctx->plane_state != pipe_ctx->plane_state) {
-			dc->hwss.set_input_transfer_func(
-					pipe_ctx, pipe_ctx->plane_state);
-			dc->hwss.set_output_transfer_func(
-					pipe_ctx, pipe_ctx->stream);
-		}
-	}
-
-	if (dc->debug.sanity_checks) {
-		/* pstate stuck check after each pipe is programmed */
-		verify_allow_pstate_change_high(dc->hwseq);
+		/* dcn10_translate_regamma_to_hw_format takes 750us to finish
+		 * only do gamma programming for full update.
+		 * TODO: This can be further optimized/cleaned up
+		 * Always call this for now since it does memcmp inside before
+		 * doing heavy calculation and programming
+		 */
+		if (pipe_ctx->plane_state->update_flags.bits.full_update)
+			dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
 	}
 
 	if (pipe_ctx->bottom_pipe != NULL && pipe_ctx->bottom_pipe != pipe_ctx)
@@ -2486,7 +1877,6 @@ static void dcn10_pplib_apply_display_requirements(
 static void optimize_shared_resources(struct dc *dc)
 {
 	if (dc->current_state->stream_count == 0) {
-		apply_DEGVIDCN10_253_wa(dc);
 		/* S0i2 message */
 		dcn10_pplib_apply_display_requirements(dc, dc->current_state);
 	}
@@ -2497,67 +1887,84 @@ static void optimize_shared_resources(struct dc *dc)
 
 static void ready_shared_resources(struct dc *dc, struct dc_state *context)
 {
-	if (dc->current_state->stream_count == 0 &&
-			!dc->debug.disable_stutter)
-		undo_DEGVIDCN10_253_wa(dc);
-
 	/* S0i2 message */
 	if (dc->current_state->stream_count == 0 &&
 			context->stream_count != 0)
 		dcn10_pplib_apply_display_requirements(dc, context);
 }
 
+static struct pipe_ctx *find_top_pipe_for_stream(
+		struct dc *dc,
+		struct dc_state *context,
+		const struct dc_stream_state *stream)
+{
+	int i;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *old_pipe_ctx =
+				&dc->current_state->res_ctx.pipe_ctx[i];
+
+		if (!pipe_ctx->plane_state && !old_pipe_ctx->plane_state)
+			continue;
+
+		if (pipe_ctx->stream != stream)
+			continue;
+
+		if (!pipe_ctx->top_pipe)
+			return pipe_ctx;
+	}
+	return NULL;
+}
+
 static void dcn10_apply_ctx_for_surface(
 		struct dc *dc,
 		const struct dc_stream_state *stream,
 		int num_planes,
 		struct dc_state *context)
 {
-	int i, be_idx;
+	int i;
+	struct timing_generator *tg;
+	struct output_pixel_processor *opp;
+	bool removed_pipe[4] = { false };
+	unsigned int ref_clk_mhz = dc->res_pool->ref_clock_inKhz/1000;
+	bool program_water_mark = false;
 
-	if (dc->debug.sanity_checks)
-		verify_allow_pstate_change_high(dc->hwseq);
+	struct pipe_ctx *top_pipe_to_program =
+			find_top_pipe_for_stream(dc, context, stream);
 
-	be_idx = -1;
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (stream == context->res_ctx.pipe_ctx[i].stream) {
-			be_idx = context->res_ctx.pipe_ctx[i].stream_res.tg->inst;
-			break;
-		}
-	}
+	if (!top_pipe_to_program)
+		return;
+
+	opp = top_pipe_to_program->stream_res.opp;
 
-	ASSERT(be_idx != -1);
+	tg = top_pipe_to_program->stream_res.tg;
+
+	tg->funcs->lock(tg);
 
 	if (num_planes == 0) {
-		for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
-			struct pipe_ctx *old_pipe_ctx =
-							&dc->current_state->res_ctx.pipe_ctx[i];
 
-			if (old_pipe_ctx->stream_res.tg && old_pipe_ctx->stream_res.tg->inst == be_idx) {
-				old_pipe_ctx->stream_res.tg->funcs->set_blank(old_pipe_ctx->stream_res.tg, true);
-				dcn10_power_down_fe(dc, old_pipe_ctx->pipe_idx);
-			}
-		}
-		return;
+		/* OTG blank before remove all front end */
+		if (tg->funcs->set_blank)
+			tg->funcs->set_blank(tg, true);
 	}
 
-	/* reset unused mpcc */
+	/* Disconnect unused mpcc */
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 		struct pipe_ctx *old_pipe_ctx =
 				&dc->current_state->res_ctx.pipe_ctx[i];
-
-		if (!pipe_ctx->plane_state && !old_pipe_ctx->plane_state)
-			continue;
-
 		/*
 		 * Powergate reused pipes that are not powergated
 		 * fairly hacky right now, using opp_id as indicator
+		 * TODO: After move dc_post to dc_update, this will
+		 * be removed.
 		 */
-
 		if (pipe_ctx->plane_state && !old_pipe_ctx->plane_state) {
-			if (pipe_ctx->plane_res.hubp->opp_id != 0xf && pipe_ctx->stream_res.tg->inst == be_idx) {
-				dcn10_power_down_fe(dc, pipe_ctx->pipe_idx);
+			if (old_pipe_ctx->stream_res.tg == tg &&
+				old_pipe_ctx->plane_res.hubp &&
+				old_pipe_ctx->plane_res.hubp->opp_id != 0xf) {
+				dcn10_disable_plane(dc, pipe_ctx);
 				/*
 				 * power down fe will unlock when calling reset, need
 				 * to lock it back here. Messy, need rework.
@@ -2566,36 +1973,12 @@ static void dcn10_apply_ctx_for_surface(
 			}
 		}
 
+		if (!pipe_ctx->plane_state &&
+			old_pipe_ctx->plane_state &&
+			old_pipe_ctx->stream_res.tg == tg) {
 
-		if ((!pipe_ctx->plane_state && old_pipe_ctx->plane_state)
-				|| (!pipe_ctx->stream && old_pipe_ctx->stream)) {
-			if (old_pipe_ctx->stream_res.tg->inst != be_idx)
-				continue;
-
-			if (!old_pipe_ctx->top_pipe) {
-				ASSERT(0);
-				continue;
-			}
-
-			/* reset mpc */
-			dc->res_pool->mpc->funcs->remove(
-					dc->res_pool->mpc,
-					&(old_pipe_ctx->stream_res.opp->mpc_tree),
-					old_pipe_ctx->stream_res.opp->inst,
-					old_pipe_ctx->pipe_idx);
-			old_pipe_ctx->stream_res.opp->mpcc_disconnect_pending[old_pipe_ctx->plane_res.hubp->mpcc_id] = true;
-
-			/*dm_logger_write(dc->ctx->logger, LOG_ERROR,
-					"[debug_mpo: apply_ctx disconnect pending on mpcc %d]\n",
-					old_pipe_ctx->mpcc->inst);*/
-
-			if (dc->debug.sanity_checks)
-				verify_allow_pstate_change_high(dc->hwseq);
-
-			old_pipe_ctx->top_pipe = NULL;
-			old_pipe_ctx->bottom_pipe = NULL;
-			old_pipe_ctx->plane_state = NULL;
-			old_pipe_ctx->stream = NULL;
+			plane_atomic_disconnect(dc, old_pipe_ctx);
+			removed_pipe[i] = true;
 
 			dm_logger_write(dc->ctx->logger, LOG_DC,
 					"Reset mpcc for pipe %d\n",
@@ -2603,18 +1986,44 @@ static void dcn10_apply_ctx_for_surface(
 		}
 	}
 
+	if (num_planes > 0)
+		program_all_pipe_in_tree(dc, top_pipe_to_program, context);
+
+	tg->funcs->unlock(tg);
+
+	if (num_planes == 0)
+		false_optc_underflow_wa(dc, stream, tg);
+
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *old_pipe_ctx =
+				&dc->current_state->res_ctx.pipe_ctx[i];
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
-		if (pipe_ctx->stream != stream)
-			continue;
+		if (pipe_ctx->stream == stream &&
+				pipe_ctx->plane_state &&
+			pipe_ctx->plane_state->update_flags.bits.full_update)
+			program_water_mark = true;
 
-		/* looking for top pipe to program */
-		if (!pipe_ctx->top_pipe)
-			program_all_pipe_in_tree(dc, pipe_ctx, context);
+		if (removed_pipe[i])
+			dcn10_disable_plane(dc, old_pipe_ctx);
 	}
 
-	dm_logger_write(dc->ctx->logger, LOG_BANDWIDTH_CALCS,
+	if (program_water_mark) {
+		if (dc->debug.sanity_checks) {
+			/* pstate stuck check after watermark update */
+			dcn10_verify_allow_pstate_change_high(dc);
+		}
+
+		/* watermark is for all pipes */
+		hubbub1_program_watermarks(dc->res_pool->hubbub,
+				&context->bw.dcn.watermarks, ref_clk_mhz);
+
+		if (dc->debug.sanity_checks) {
+			/* pstate stuck check after watermark update */
+			dcn10_verify_allow_pstate_change_high(dc);
+		}
+	}
+/*	dm_logger_write(dc->ctx->logger, LOG_BANDWIDTH_CALCS,
 			"\n============== Watermark parameters ==============\n"
 			"a.urgent_ns: %d \n"
 			"a.cstate_enter_plus_exit: %d \n"
@@ -2660,9 +2069,7 @@ static void dcn10_apply_ctx_for_surface(
 			context->bw.dcn.watermarks.d.cstate_pstate.pstate_change_ns,
 			context->bw.dcn.watermarks.d.pte_meta_urgent_ns
 			);
-
-	if (dc->debug.sanity_checks)
-		verify_allow_pstate_change_high(dc->hwseq);
+*/
 }
 
 static void dcn10_set_bandwidth(
@@ -2676,7 +2083,7 @@ static void dcn10_set_bandwidth(
 	struct pp_smu_funcs_rv *pp_smu = dc->res_pool->pp_smu;
 
 	if (dc->debug.sanity_checks) {
-		verify_allow_pstate_change_high(dc->hwseq);
+		dcn10_verify_allow_pstate_change_high(dc);
 	}
 
 	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
@@ -2732,7 +2139,7 @@ static void dcn10_set_bandwidth(
 	dcn10_pplib_apply_display_requirements(dc, context);
 
 	if (dc->debug.sanity_checks) {
-		verify_allow_pstate_change_high(dc->hwseq);
+		dcn10_verify_allow_pstate_change_high(dc);
 	}
 
 	/* need to fix this function.  not doing the right thing here */
@@ -2836,10 +2243,10 @@ static void dcn10_setup_stereo(struct pipe_ctx *pipe_ctx, struct dc *dc)
 
 	dcn10_config_stereo_parameters(stream, &flags);
 
-	pipe_ctx->stream_res.opp->funcs->opp_set_stereo_polarity(
+	pipe_ctx->stream_res.opp->funcs->opp_program_stereo(
 		pipe_ctx->stream_res.opp,
 		flags.PROGRAM_STEREO == 1 ? true:false,
-		stream->timing.flags.RIGHT_EYE_3D_POLARITY == 1 ? true:false);
+		&stream->timing);
 
 	pipe_ctx->stream_res.tg->funcs->program_stereo(
 		pipe_ctx->stream_res.tg,
@@ -2857,7 +2264,7 @@ static void dcn10_wait_for_mpcc_disconnect(
 	int i;
 
 	if (dc->debug.sanity_checks) {
-		verify_allow_pstate_change_high(dc->hwseq);
+		dcn10_verify_allow_pstate_change_high(dc);
 	}
 
 	if (!pipe_ctx->stream_res.opp)
@@ -2875,7 +2282,7 @@ static void dcn10_wait_for_mpcc_disconnect(
 	}
 
 	if (dc->debug.sanity_checks) {
-		verify_allow_pstate_change_high(dc->hwseq);
+		dcn10_verify_allow_pstate_change_high(dc);
 	}
 
 }
@@ -2909,7 +2316,11 @@ void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx)
 	}
 }
 
-
+void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data)
+{
+	if (hws->ctx->dc->res_pool->hubbub != NULL)
+		hubbub1_update_dchub(hws->ctx->dc->res_pool->hubbub, dh_data);
+}
 
 static const struct hw_sequencer_funcs dcn10_funcs = {
 	.program_gamut_remap = program_gamut_remap,
@@ -2926,13 +2337,13 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.power_down = dce110_power_down,
 	.enable_accelerated_mode = dce110_enable_accelerated_mode,
 	.enable_timing_synchronization = dcn10_enable_timing_synchronization,
+	.enable_per_frame_crtc_position_reset = dcn10_enable_per_frame_crtc_position_reset,
 	.update_info_frame = dce110_update_info_frame,
 	.enable_stream = dce110_enable_stream,
 	.disable_stream = dce110_disable_stream,
 	.unblank_stream = dce110_unblank_stream,
 	.enable_display_power_gating = dcn10_dummy_display_power_gating,
-	.power_down_front_end = dcn10_power_down_fe,
-	.power_on_front_end = dcn10_power_on_fe,
+	.disable_plane = dcn10_disable_plane,
 	.pipe_control_lock = dcn10_pipe_control_lock,
 	.set_bandwidth = dcn10_set_bandwidth,
 	.reset_hw_ctx_wrap = reset_hw_ctx_wrap,
@@ -2946,8 +2357,11 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
 	.ready_shared_resources = ready_shared_resources,
 	.optimize_shared_resources = optimize_shared_resources,
+	.pplib_apply_display_requirements =
+			dcn10_pplib_apply_display_requirements,
 	.edp_backlight_control = hwss_edp_backlight_control,
-	.edp_power_control = hwss_edp_power_control
+	.edp_power_control = hwss_edp_power_control,
+	.edp_wait_for_hpd_ready = hwss_edp_wait_for_hpd_ready,
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
index ca53dc1cc19b..b9d326082717 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
@@ -35,4 +35,5 @@ extern void fill_display_configs(
 	const struct dc_state *context,
 	struct dm_pp_display_configuration *pp_display_cfg);
 
+
 #endif /* __DC_HWSS_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 76573e1f5b01..179890b1a8c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -25,8 +25,6 @@
 
 #include "reg_helper.h"
 #include "dcn10_mpc.h"
-#include "dc.h"
-#include "mem_input.h"
 
 #define REG(reg)\
 	mpc10->mpc_regs->reg
@@ -38,17 +36,13 @@
 #define FN(reg_name, field_name) \
 	mpc10->mpc_shift->field_name, mpc10->mpc_mask->field_name
 
-#define MODE_TOP_ONLY 1
-#define MODE_BLEND 3
-#define BLND_PP_ALPHA 0
-#define BLND_GLOBAL_ALPHA 2
 
-
-static void mpc10_set_bg_color(
-		struct dcn10_mpc *mpc10,
+void mpc1_set_bg_color(struct mpc *mpc,
 		struct tg_color *bg_color,
-		int id)
+		int mpcc_id)
 {
+	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+
 	/* mpc color is 12 bit.  tg_color is 10 bit */
 	/* todo: might want to use 16 bit to represent color and have each
 	 * hw block translate to correct color depth.
@@ -57,15 +51,47 @@ static void mpc10_set_bg_color(
 	uint32_t bg_g_y = bg_color->color_g_y << 2;
 	uint32_t bg_b_cb = bg_color->color_b_cb << 2;
 
-	REG_SET(MPCC_BG_R_CR[id], 0,
+	REG_SET(MPCC_BG_R_CR[mpcc_id], 0,
 			MPCC_BG_R_CR, bg_r_cr);
-	REG_SET(MPCC_BG_G_Y[id], 0,
+	REG_SET(MPCC_BG_G_Y[mpcc_id], 0,
 			MPCC_BG_G_Y, bg_g_y);
-	REG_SET(MPCC_BG_B_CB[id], 0,
+	REG_SET(MPCC_BG_B_CB[mpcc_id], 0,
 			MPCC_BG_B_CB, bg_b_cb);
 }
 
-void mpc10_assert_idle_mpcc(struct mpc *mpc, int id)
+static void mpc1_update_blending(
+	struct mpc *mpc,
+	struct mpcc_blnd_cfg *blnd_cfg,
+	int mpcc_id)
+{
+	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+
+	REG_UPDATE_5(MPCC_CONTROL[mpcc_id],
+			MPCC_ALPHA_BLND_MODE,		blnd_cfg->alpha_mode,
+			MPCC_ALPHA_MULTIPLIED_MODE,	blnd_cfg->pre_multiplied_alpha,
+			MPCC_BLND_ACTIVE_OVERLAP_ONLY,	blnd_cfg->overlap_only,
+			MPCC_GLOBAL_ALPHA,		blnd_cfg->global_alpha,
+			MPCC_GLOBAL_GAIN,		blnd_cfg->global_gain);
+
+	mpc1_set_bg_color(mpc, &blnd_cfg->black_color, mpcc_id);
+}
+
+void mpc1_update_stereo_mix(
+	struct mpc *mpc,
+	struct mpcc_sm_cfg *sm_cfg,
+	int mpcc_id)
+{
+	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+
+	REG_UPDATE_6(MPCC_SM_CONTROL[mpcc_id],
+			MPCC_SM_EN,			sm_cfg->enable,
+			MPCC_SM_MODE,			sm_cfg->sm_mode,
+			MPCC_SM_FRAME_ALT,		sm_cfg->frame_alt,
+			MPCC_SM_FIELD_ALT,		sm_cfg->field_alt,
+			MPCC_SM_FORCE_NEXT_FRAME_POL,	sm_cfg->force_next_frame_porlarity,
+			MPCC_SM_FORCE_NEXT_TOP_POL,	sm_cfg->force_next_field_polarity);
+}
+void mpc1_assert_idle_mpcc(struct mpc *mpc, int id)
 {
 	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
 
@@ -75,39 +101,52 @@ void mpc10_assert_idle_mpcc(struct mpc *mpc, int id)
 			1, 100000);
 }
 
-static int mpc10_get_idle_mpcc_id(struct dcn10_mpc *mpc10)
+struct mpcc *mpc1_get_mpcc(struct mpc *mpc, int mpcc_id)
 {
-	int i;
-	int last_free_mpcc_id = -1;
+	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
 
-	for (i = 0; i < mpc10->num_mpcc; i++) {
-		uint32_t is_idle = 0;
+	ASSERT(mpcc_id < mpc10->num_mpcc);
+	return &(mpc->mpcc_array[mpcc_id]);
+}
 
-		if (mpc10->mpcc_in_use_mask & 1 << i)
-			continue;
+struct mpcc *mpc1_get_mpcc_for_dpp(struct mpc_tree *tree, int dpp_id)
+{
+	struct mpcc *tmp_mpcc = tree->opp_list;
 
-		last_free_mpcc_id = i;
-		REG_GET(MPCC_STATUS[i], MPCC_IDLE, &is_idle);
-		if (is_idle)
-			return i;
+	while (tmp_mpcc != NULL) {
+		if (tmp_mpcc->dpp_id == dpp_id)
+			return tmp_mpcc;
+		tmp_mpcc = tmp_mpcc->mpcc_bot;
 	}
+	return NULL;
+}
 
-	/* This assert should never trigger, we have mpcc leak if it does */
-	ASSERT(last_free_mpcc_id != -1);
-
-	mpc10_assert_idle_mpcc(&mpc10->base, last_free_mpcc_id);
-	return last_free_mpcc_id;
+bool mpc1_is_mpcc_idle(struct mpc *mpc, int mpcc_id)
+{
+	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+	unsigned int top_sel;
+	unsigned int opp_id;
+	unsigned int idle;
+
+	REG_GET(MPCC_TOP_SEL[mpcc_id], MPCC_TOP_SEL, &top_sel);
+	REG_GET(MPCC_OPP_ID[mpcc_id],  MPCC_OPP_ID, &opp_id);
+	REG_GET(MPCC_STATUS[mpcc_id],  MPCC_IDLE,   &idle);
+	if (top_sel == 0xf && opp_id == 0xf && idle)
+		return true;
+	else
+		return false;
 }
 
-static void mpc10_assert_mpcc_idle_before_connect(struct dcn10_mpc *mpc10, int id)
+void mpc1_assert_mpcc_idle_before_connect(struct mpc *mpc, int mpcc_id)
 {
+	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
 	unsigned int top_sel, mpc_busy, mpc_idle;
 
-	REG_GET(MPCC_TOP_SEL[id],
+	REG_GET(MPCC_TOP_SEL[mpcc_id],
 			MPCC_TOP_SEL, &top_sel);
 
 	if (top_sel == 0xf) {
-		REG_GET_2(MPCC_STATUS[id],
+		REG_GET_2(MPCC_STATUS[mpcc_id],
 				MPCC_BUSY, &mpc_busy,
 				MPCC_IDLE, &mpc_idle);
 
@@ -116,230 +155,269 @@ static void mpc10_assert_mpcc_idle_before_connect(struct dcn10_mpc *mpc10, int i
 	}
 }
 
-void mpc10_mpcc_remove(
-		struct mpc *mpc,
-		struct mpc_tree_cfg *tree_cfg,
-		int opp_id,
-		int dpp_id)
-{
-	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
-	int mpcc_id, z_idx;
-
-	/* find z_idx for the dpp to be removed */
-	for (z_idx = 0; z_idx < tree_cfg->num_pipes; z_idx++)
-		if (tree_cfg->dpp[z_idx] == dpp_id)
-			break;
-
-	if (z_idx == tree_cfg->num_pipes) {
-		/* In case of resume from S3/S4, remove mpcc from bios left over */
-		REG_SET(MPCC_OPP_ID[dpp_id], 0,
-				MPCC_OPP_ID, 0xf);
-		REG_SET(MPCC_TOP_SEL[dpp_id], 0,
-				MPCC_TOP_SEL, 0xf);
-		REG_SET(MPCC_BOT_SEL[dpp_id], 0,
-				MPCC_BOT_SEL, 0xf);
-		return;
-	}
-
-	mpcc_id = tree_cfg->mpcc[z_idx];
-
-	REG_SET(MPCC_OPP_ID[mpcc_id], 0,
-			MPCC_OPP_ID, 0xf);
-	REG_SET(MPCC_TOP_SEL[mpcc_id], 0,
-			MPCC_TOP_SEL, 0xf);
-	REG_SET(MPCC_BOT_SEL[mpcc_id], 0,
-			MPCC_BOT_SEL, 0xf);
-
-	if (z_idx > 0) {
-		int top_mpcc_id = tree_cfg->mpcc[z_idx - 1];
-
-		if (z_idx + 1 < tree_cfg->num_pipes)
-			/* mpcc to be removed is in the middle of the tree */
-			REG_SET(MPCC_BOT_SEL[top_mpcc_id], 0,
-					MPCC_BOT_SEL, tree_cfg->mpcc[z_idx + 1]);
-		else {
-			/* mpcc to be removed is at the bottom of the tree */
-			REG_SET(MPCC_BOT_SEL[top_mpcc_id], 0,
-					MPCC_BOT_SEL, 0xf);
-			REG_UPDATE(MPCC_CONTROL[top_mpcc_id],
-					MPCC_MODE, MODE_TOP_ONLY);
-		}
-	} else if (tree_cfg->num_pipes > 1)
-		/* mpcc to be removed is at the top of the tree */
-		REG_SET(MUX[opp_id], 0,
-				MPC_OUT_MUX, tree_cfg->mpcc[z_idx + 1]);
-	else
-		/* mpcc to be removed is the only one in the tree */
-		REG_SET(MUX[opp_id], 0, MPC_OUT_MUX, 0xf);
-
-	/* mark this mpcc as not in use */
-	mpc10->mpcc_in_use_mask &= ~(1 << mpcc_id);
-	tree_cfg->num_pipes--;
-	for (; z_idx < tree_cfg->num_pipes; z_idx++) {
-		tree_cfg->dpp[z_idx] = tree_cfg->dpp[z_idx + 1];
-		tree_cfg->mpcc[z_idx] = tree_cfg->mpcc[z_idx + 1];
-	}
-	tree_cfg->dpp[tree_cfg->num_pipes] = 0xdeadbeef;
-	tree_cfg->mpcc[tree_cfg->num_pipes] = 0xdeadbeef;
-}
-
-static void mpc10_add_to_tree_cfg(
+/*
+ * Insert DPP into MPC tree based on specified blending position.
+ * Only used for planes that are part of blending chain for OPP output
+ *
+ * Parameters:
+ * [in/out] mpc		- MPC context.
+ * [in/out] tree	- MPC tree structure that plane will be added to.
+ * [in]	blnd_cfg	- MPCC blending configuration for the new blending layer.
+ * [in]	sm_cfg		- MPCC stereo mix configuration for the new blending layer.
+ *			  stereo mix must disable for the very bottom layer of the tree config.
+ * [in]	insert_above_mpcc - Insert new plane above this MPCC.  If NULL, insert as bottom plane.
+ * [in]	dpp_id		- DPP instance for the plane to be added.
+ * [in]	mpcc_id		- The MPCC physical instance to use for blending.
+ *
+ * Return:  struct mpcc* - MPCC that was added.
+ */
+struct mpcc *mpc1_insert_plane(
 	struct mpc *mpc,
-	struct mpcc_cfg *cfg,
+	struct mpc_tree *tree,
+	struct mpcc_blnd_cfg *blnd_cfg,
+	struct mpcc_sm_cfg *sm_cfg,
+	struct mpcc *insert_above_mpcc,
+	int dpp_id,
 	int mpcc_id)
 {
 	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
-	int mpcc_mode = MODE_TOP_ONLY;
-	int position = cfg->z_index;
-	struct mpc_tree_cfg *tree_cfg = cfg->tree_cfg;
-	int alpha_blnd_mode = cfg->per_pixel_alpha ?
-			BLND_PP_ALPHA : BLND_GLOBAL_ALPHA;
-	int z_idx;
+	struct mpcc *new_mpcc = NULL;
 
-	REG_SET(MPCC_OPP_ID[mpcc_id], 0,
-			MPCC_OPP_ID, cfg->opp_id);
+	/* sanity check parameters */
+	ASSERT(mpcc_id < mpc10->num_mpcc);
+	ASSERT(!(mpc10->mpcc_in_use_mask & 1 << mpcc_id));
 
-	REG_SET(MPCC_TOP_SEL[mpcc_id], 0,
-			MPCC_TOP_SEL, cfg->dpp_id);
+	if (insert_above_mpcc) {
+		/* check insert_above_mpcc exist in tree->opp_list */
+		struct mpcc *temp_mpcc = tree->opp_list;
 
-	if (position == 0) {
-		/* idle dpp/mpcc is added to the top layer of tree */
+		while (temp_mpcc && temp_mpcc->mpcc_bot != insert_above_mpcc)
+			temp_mpcc = temp_mpcc->mpcc_bot;
+		if (temp_mpcc == NULL)
+			return NULL;
+	}
 
-		if (tree_cfg->num_pipes > 0) {
-			/* get instance of previous top mpcc */
-			int prev_top_mpcc_id = tree_cfg->mpcc[0];
+	/* Get and update MPCC struct parameters */
+	new_mpcc = mpc1_get_mpcc(mpc, mpcc_id);
+	new_mpcc->dpp_id = dpp_id;
 
-			REG_SET(MPCC_BOT_SEL[mpcc_id], 0,
-					MPCC_BOT_SEL, prev_top_mpcc_id);
-			mpcc_mode = MODE_BLEND;
+	/* program mux and MPCC_MODE */
+	if (insert_above_mpcc) {
+		new_mpcc->mpcc_bot = insert_above_mpcc;
+		REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, insert_above_mpcc->mpcc_id);
+		REG_UPDATE(MPCC_CONTROL[mpcc_id], MPCC_MODE, MPCC_BLEND_MODE_TOP_BOT_BLENDING);
+	} else {
+		new_mpcc->mpcc_bot = NULL;
+		REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
+		REG_UPDATE(MPCC_CONTROL[mpcc_id], MPCC_MODE, MPCC_BLEND_MODE_TOP_LAYER_PASSTHROUGH);
+	}
+	REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, dpp_id);
+	REG_SET(MPCC_OPP_ID[mpcc_id], 0, MPCC_OPP_ID, tree->opp_id);
+
+	/* update mpc tree mux setting */
+	if (tree->opp_list == insert_above_mpcc) {
+		/* insert the toppest mpcc */
+		tree->opp_list = new_mpcc;
+		REG_UPDATE(MUX[tree->opp_id], MPC_OUT_MUX, mpcc_id);
+	} else {
+		/* find insert position */
+		struct mpcc *temp_mpcc = tree->opp_list;
+
+		while (temp_mpcc && temp_mpcc->mpcc_bot != insert_above_mpcc)
+			temp_mpcc = temp_mpcc->mpcc_bot;
+		if (temp_mpcc && temp_mpcc->mpcc_bot == insert_above_mpcc) {
+			REG_SET(MPCC_BOT_SEL[temp_mpcc->mpcc_id], 0, MPCC_BOT_SEL, mpcc_id);
+			temp_mpcc->mpcc_bot = new_mpcc;
+			if (!insert_above_mpcc)
+				REG_UPDATE(MPCC_CONTROL[temp_mpcc->mpcc_id],
+						MPCC_MODE, MPCC_BLEND_MODE_TOP_BOT_BLENDING);
 		}
+	}
 
-		/* opp will get new output. from new added mpcc */
-		REG_SET(MUX[cfg->opp_id], 0, MPC_OUT_MUX, mpcc_id);
-
-	} else if (position == tree_cfg->num_pipes) {
-		/* idle dpp/mpcc is added to the bottom layer of tree */
-
-		/* get instance of previous bottom mpcc, set to middle layer */
-		int prev_bot_mpcc_id = tree_cfg->mpcc[tree_cfg->num_pipes - 1];
-
-		REG_SET(MPCC_BOT_SEL[prev_bot_mpcc_id], 0,
-				MPCC_BOT_SEL, mpcc_id);
-		REG_UPDATE(MPCC_CONTROL[prev_bot_mpcc_id],
-				MPCC_MODE, MODE_BLEND);
-
-		/* mpcc_id become new bottom mpcc*/
-		REG_SET(MPCC_BOT_SEL[mpcc_id], 0,
-				MPCC_BOT_SEL, 0xf);
+	/* update the blending configuration */
+	new_mpcc->blnd_cfg = *blnd_cfg;
+	mpc->funcs->update_blending(mpc, &new_mpcc->blnd_cfg, mpcc_id);
 
-	} else {
-		/* idle dpp/mpcc is added to middle of tree */
-		int above_mpcc_id = tree_cfg->mpcc[position - 1];
-		int below_mpcc_id = tree_cfg->mpcc[position];
-
-		/* mpcc above new mpcc_id has new bottom mux*/
-		REG_SET(MPCC_BOT_SEL[above_mpcc_id], 0,
-				MPCC_BOT_SEL, mpcc_id);
-		REG_UPDATE(MPCC_CONTROL[above_mpcc_id],
-				MPCC_MODE, MODE_BLEND);
-
-		/* mpcc_id bottom mux is from below mpcc*/
-		REG_SET(MPCC_BOT_SEL[mpcc_id], 0,
-				MPCC_BOT_SEL, below_mpcc_id);
-		mpcc_mode = MODE_BLEND;
+	/* update the stereo mix settings, if provided */
+	if (sm_cfg != NULL) {
+		new_mpcc->sm_cfg = *sm_cfg;
+		mpc1_update_stereo_mix(mpc, sm_cfg, mpcc_id);
 	}
 
-	REG_SET_4(MPCC_CONTROL[mpcc_id], 0xffffffff,
-		MPCC_MODE, mpcc_mode,
-		MPCC_ALPHA_BLND_MODE, alpha_blnd_mode,
-		MPCC_ALPHA_MULTIPLIED_MODE, cfg->pre_multiplied_alpha,
-		MPCC_BLND_ACTIVE_OVERLAP_ONLY, false);
+	/* mark this mpcc as in use */
+	mpc10->mpcc_in_use_mask |= 1 << mpcc_id;
 
-	/* update mpc_tree_cfg with new mpcc */
-	for (z_idx = tree_cfg->num_pipes; z_idx > position; z_idx--) {
-		tree_cfg->dpp[z_idx] = tree_cfg->dpp[z_idx - 1];
-		tree_cfg->mpcc[z_idx] = tree_cfg->mpcc[z_idx - 1];
-	}
-	tree_cfg->dpp[position] = cfg->dpp_id;
-	tree_cfg->mpcc[position] = mpcc_id;
-	tree_cfg->num_pipes++;
+	return new_mpcc;
 }
 
-int mpc10_mpcc_add(struct mpc *mpc, struct mpcc_cfg *cfg)
+/*
+ * Remove a specified MPCC from the MPC tree.
+ *
+ * Parameters:
+ * [in/out] mpc		- MPC context.
+ * [in/out] tree	- MPC tree structure that plane will be removed from.
+ * [in/out] mpcc	- MPCC to be removed from tree.
+ *
+ * Return:  void
+ */
+void mpc1_remove_mpcc(
+	struct mpc *mpc,
+	struct mpc_tree *tree,
+	struct mpcc *mpcc_to_remove)
 {
 	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
-	int mpcc_id, z_idx;
-
-	ASSERT(cfg->z_index < mpc10->num_mpcc);
-
-	/* check in dpp already exists in mpc tree */
-	for (z_idx = 0; z_idx < cfg->tree_cfg->num_pipes; z_idx++)
-		if (cfg->tree_cfg->dpp[z_idx] == cfg->dpp_id)
-			break;
-	if (z_idx == cfg->tree_cfg->num_pipes) {
-		ASSERT(cfg->z_index <= cfg->tree_cfg->num_pipes);
-		mpcc_id = mpc10_get_idle_mpcc_id(mpc10);
-
-		/*
-		 * TODO: remove hack
-		 * Note: currently there is a bug in init_hw such that
-		 * on resume from hibernate, BIOS sets up MPCC0, and
-		 * we do mpcc_remove but the mpcc cannot go to idle
-		 * after remove. This cause us to pick mpcc1 here,
-		 * which causes a pstate hang for yet unknown reason.
-		 */
-		mpcc_id = cfg->dpp_id;
-		/* end hack*/
-
-		ASSERT(!(mpc10->mpcc_in_use_mask & 1 << mpcc_id));
-
-		if (mpc->ctx->dc->debug.sanity_checks)
-			mpc10_assert_mpcc_idle_before_connect(mpc10, mpcc_id);
+	bool found = false;
+	int mpcc_id = mpcc_to_remove->mpcc_id;
+
+	if (tree->opp_list == mpcc_to_remove) {
+		found = true;
+		/* remove MPCC from top of tree */
+		if (mpcc_to_remove->mpcc_bot) {
+			/* set the next MPCC in list to be the top MPCC */
+			tree->opp_list = mpcc_to_remove->mpcc_bot;
+			REG_UPDATE(MUX[tree->opp_id], MPC_OUT_MUX, tree->opp_list->mpcc_id);
+		} else {
+			/* there are no other MPCC is list */
+			tree->opp_list = NULL;
+			REG_UPDATE(MUX[tree->opp_id], MPC_OUT_MUX, 0xf);
+		}
 	} else {
-		ASSERT(cfg->z_index < cfg->tree_cfg->num_pipes);
-		mpcc_id = cfg->tree_cfg->mpcc[z_idx];
-		mpc10_mpcc_remove(mpc, cfg->tree_cfg, cfg->opp_id, cfg->dpp_id);
+		/* find mpcc to remove MPCC list */
+		struct mpcc *temp_mpcc = tree->opp_list;
+
+		while (temp_mpcc && temp_mpcc->mpcc_bot != mpcc_to_remove)
+			temp_mpcc = temp_mpcc->mpcc_bot;
+
+		if (temp_mpcc && temp_mpcc->mpcc_bot == mpcc_to_remove) {
+			found = true;
+			temp_mpcc->mpcc_bot = mpcc_to_remove->mpcc_bot;
+			if (mpcc_to_remove->mpcc_bot) {
+				/* remove MPCC in middle of list */
+				REG_SET(MPCC_BOT_SEL[temp_mpcc->mpcc_id], 0,
+						MPCC_BOT_SEL, mpcc_to_remove->mpcc_bot->mpcc_id);
+			} else {
+				/* remove MPCC from bottom of list */
+				REG_SET(MPCC_BOT_SEL[temp_mpcc->mpcc_id], 0,
+						MPCC_BOT_SEL, 0xf);
+				REG_UPDATE(MPCC_CONTROL[temp_mpcc->mpcc_id],
+						MPCC_MODE, MPCC_BLEND_MODE_TOP_LAYER_PASSTHROUGH);
+			}
+		}
 	}
 
-	/* add dpp/mpcc pair to mpc_tree_cfg and update mpcc registers */
-	mpc10_add_to_tree_cfg(mpc, cfg, mpcc_id);
-
-	/* set background color */
-	mpc10_set_bg_color(mpc10, &cfg->black_color, mpcc_id);
+	if (found) {
+		/* turn off MPCC mux registers */
+		REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf);
+		REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
+		REG_SET(MPCC_OPP_ID[mpcc_id],  0, MPCC_OPP_ID,  0xf);
 
-	/* mark this mpcc as in use */
-	mpc10->mpcc_in_use_mask |= 1 << mpcc_id;
+		/* mark this mpcc as not in use */
+		mpc10->mpcc_in_use_mask &= ~(1 << mpcc_id);
+		mpcc_to_remove->dpp_id = 0xf;
+		mpcc_to_remove->mpcc_bot = NULL;
+	} else {
+		/* In case of resume from S3/S4, remove mpcc from bios left over */
+		REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf);
+		REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
+		REG_SET(MPCC_OPP_ID[mpcc_id],  0, MPCC_OPP_ID,  0xf);
+	}
+}
 
-	return mpcc_id;
+static void mpc1_init_mpcc(struct mpcc *mpcc, int mpcc_inst)
+{
+	mpcc->mpcc_id = mpcc_inst;
+	mpcc->dpp_id = 0xf;
+	mpcc->mpcc_bot = NULL;
+	mpcc->blnd_cfg.overlap_only = false;
+	mpcc->blnd_cfg.global_alpha = 0xff;
+	mpcc->blnd_cfg.global_gain = 0xff;
+	mpcc->sm_cfg.enable = false;
 }
 
-void mpc10_update_blend_mode(
-		struct mpc *mpc,
-		struct mpcc_cfg *cfg)
+/*
+ * Reset the MPCC HW status by disconnecting all muxes.
+ *
+ * Parameters:
+ * [in/out] mpc		- MPC context.
+ *
+ * Return:  void
+ */
+void mpc1_mpc_init(struct mpc *mpc)
 {
 	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
-	int mpcc_id, z_idx;
-	int alpha_blnd_mode = cfg->per_pixel_alpha ?
-			BLND_PP_ALPHA : BLND_GLOBAL_ALPHA;
+	int mpcc_id;
+	int opp_id;
+
+	mpc10->mpcc_in_use_mask = 0;
+	for (mpcc_id = 0; mpcc_id < mpc10->num_mpcc; mpcc_id++) {
+		REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf);
+		REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
+		REG_SET(MPCC_OPP_ID[mpcc_id],  0, MPCC_OPP_ID,  0xf);
 
-	/* find z_idx for the dpp that requires blending mode update*/
-	for (z_idx = 0; z_idx < cfg->tree_cfg->num_pipes; z_idx++)
-		if (cfg->tree_cfg->dpp[z_idx] == cfg->dpp_id)
-			break;
+		mpc1_init_mpcc(&(mpc->mpcc_array[mpcc_id]), mpcc_id);
+	}
 
-	ASSERT(z_idx < cfg->tree_cfg->num_pipes);
-	mpcc_id = cfg->tree_cfg->mpcc[z_idx];
+	for (opp_id = 0; opp_id < MAX_OPP; opp_id++) {
+		if (REG(MUX[opp_id]))
+			REG_UPDATE(MUX[opp_id], MPC_OUT_MUX, 0xf);
+	}
+}
 
-	REG_UPDATE_2(MPCC_CONTROL[mpcc_id],
-			MPCC_ALPHA_BLND_MODE, alpha_blnd_mode,
-			MPCC_ALPHA_MULTIPLIED_MODE, cfg->pre_multiplied_alpha);
+void mpc1_init_mpcc_list_from_hw(
+	struct mpc *mpc,
+	struct mpc_tree *tree)
+{
+	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+	unsigned int opp_id;
+	unsigned int top_sel;
+	unsigned int bot_sel;
+	unsigned int out_mux;
+	struct mpcc *mpcc;
+	int mpcc_id;
+	int bot_mpcc_id;
+
+	REG_GET(MUX[tree->opp_id], MPC_OUT_MUX, &out_mux);
+
+	if (out_mux != 0xf) {
+		for (mpcc_id = 0; mpcc_id < mpc10->num_mpcc; mpcc_id++) {
+			REG_GET(MPCC_OPP_ID[mpcc_id],  MPCC_OPP_ID,  &opp_id);
+			REG_GET(MPCC_TOP_SEL[mpcc_id], MPCC_TOP_SEL, &top_sel);
+			REG_GET(MPCC_BOT_SEL[mpcc_id],  MPCC_BOT_SEL, &bot_sel);
+
+			if (bot_sel == mpcc_id)
+				bot_sel = 0xf;
+
+			if ((opp_id == tree->opp_id) && (top_sel != 0xf)) {
+				mpcc = mpc1_get_mpcc(mpc, mpcc_id);
+				mpcc->dpp_id = top_sel;
+				mpc10->mpcc_in_use_mask |= 1 << mpcc_id;
+
+				if (out_mux == mpcc_id)
+					tree->opp_list = mpcc;
+				if (bot_sel != 0xf && bot_sel < mpc10->num_mpcc) {
+					bot_mpcc_id = bot_sel;
+					REG_GET(MPCC_OPP_ID[bot_mpcc_id],  MPCC_OPP_ID,  &opp_id);
+					REG_GET(MPCC_TOP_SEL[bot_mpcc_id], MPCC_TOP_SEL, &top_sel);
+					if ((opp_id == tree->opp_id) && (top_sel != 0xf)) {
+						struct mpcc *mpcc_bottom = mpc1_get_mpcc(mpc, bot_mpcc_id);
+
+						mpcc->mpcc_bot = mpcc_bottom;
+					}
+				}
+			}
+		}
+	}
 }
 
 const struct mpc_funcs dcn10_mpc_funcs = {
-		.add = mpc10_mpcc_add,
-		.remove = mpc10_mpcc_remove,
-		.wait_for_idle = mpc10_assert_idle_mpcc,
-		.update_blend_mode = mpc10_update_blend_mode,
+	.insert_plane = mpc1_insert_plane,
+	.remove_mpcc = mpc1_remove_mpcc,
+	.mpc_init = mpc1_mpc_init,
+	.get_mpcc_for_dpp = mpc1_get_mpcc_for_dpp,
+	.wait_for_idle = mpc1_assert_idle_mpcc,
+	.assert_mpcc_idle_before_connect = mpc1_assert_mpcc_idle_before_connect,
+	.init_mpcc_list_from_hw = mpc1_init_mpcc_list_from_hw,
+	.update_blending = mpc1_update_blending,
 };
 
 void dcn10_mpc_construct(struct dcn10_mpc *mpc10,
@@ -349,6 +427,8 @@ void dcn10_mpc_construct(struct dcn10_mpc *mpc10,
 	const struct dcn_mpc_mask *mpc_mask,
 	int num_mpcc)
 {
+	int i;
+
 	mpc10->base.ctx = ctx;
 
 	mpc10->base.funcs = &dcn10_mpc_funcs;
@@ -359,5 +439,8 @@ void dcn10_mpc_construct(struct dcn10_mpc *mpc10,
 
 	mpc10->mpcc_in_use_mask = 0;
 	mpc10->num_mpcc = num_mpcc;
+
+	for (i = 0; i < MAX_MPCC; i++)
+		mpc1_init_mpcc(&mpc10->base.mpcc_array[i], i);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
index 683ce4aaa76e..267a2995ef6e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
@@ -30,9 +30,6 @@
 #define TO_DCN10_MPC(mpc_base) \
 	container_of(mpc_base, struct dcn10_mpc, base)
 
-#define MAX_MPCC 6
-#define MAX_OPP 6
-
 #define MPC_COMMON_REG_LIST_DCN1_0(inst) \
 	SRII(MPCC_TOP_SEL, MPCC, inst),\
 	SRII(MPCC_BOT_SEL, MPCC, inst),\
@@ -42,7 +39,8 @@
 	SRII(MPCC_BG_G_Y, MPCC, inst),\
 	SRII(MPCC_BG_R_CR, MPCC, inst),\
 	SRII(MPCC_BG_B_CB, MPCC, inst),\
-	SRII(MPCC_BG_B_CB, MPCC, inst)
+	SRII(MPCC_BG_B_CB, MPCC, inst),\
+	SRII(MPCC_SM_CONTROL, MPCC, inst)
 
 #define MPC_OUT_MUX_COMMON_REG_LIST_DCN1_0(inst) \
 	SRII(MUX, MPC_OUT, inst)
@@ -56,6 +54,7 @@
 	uint32_t MPCC_BG_G_Y[MAX_MPCC]; \
 	uint32_t MPCC_BG_R_CR[MAX_MPCC]; \
 	uint32_t MPCC_BG_B_CB[MAX_MPCC]; \
+	uint32_t MPCC_SM_CONTROL[MAX_MPCC]; \
 	uint32_t MUX[MAX_OPP];
 
 #define MPC_COMMON_MASK_SH_LIST_DCN1_0(mask_sh)\
@@ -65,12 +64,20 @@
 	SF(MPCC0_MPCC_CONTROL, MPCC_ALPHA_BLND_MODE, mask_sh),\
 	SF(MPCC0_MPCC_CONTROL, MPCC_ALPHA_MULTIPLIED_MODE, mask_sh),\
 	SF(MPCC0_MPCC_CONTROL, MPCC_BLND_ACTIVE_OVERLAP_ONLY, mask_sh),\
+	SF(MPCC0_MPCC_CONTROL, MPCC_GLOBAL_ALPHA, mask_sh),\
+	SF(MPCC0_MPCC_CONTROL, MPCC_GLOBAL_GAIN, mask_sh),\
 	SF(MPCC0_MPCC_STATUS, MPCC_IDLE, mask_sh),\
 	SF(MPCC0_MPCC_STATUS, MPCC_BUSY, mask_sh),\
 	SF(MPCC0_MPCC_OPP_ID, MPCC_OPP_ID, mask_sh),\
 	SF(MPCC0_MPCC_BG_G_Y, MPCC_BG_G_Y, mask_sh),\
 	SF(MPCC0_MPCC_BG_R_CR, MPCC_BG_R_CR, mask_sh),\
 	SF(MPCC0_MPCC_BG_B_CB, MPCC_BG_B_CB, mask_sh),\
+	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_EN, mask_sh),\
+	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_MODE, mask_sh),\
+	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FRAME_ALT, mask_sh),\
+	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FIELD_ALT, mask_sh),\
+	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FORCE_NEXT_FRAME_POL, mask_sh),\
+	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FORCE_NEXT_TOP_POL, mask_sh),\
 	SF(MPC_OUT0_MUX, MPC_OUT_MUX, mask_sh)
 
 #define MPC_REG_FIELD_LIST(type) \
@@ -80,12 +87,20 @@
 	type MPCC_ALPHA_BLND_MODE;\
 	type MPCC_ALPHA_MULTIPLIED_MODE;\
 	type MPCC_BLND_ACTIVE_OVERLAP_ONLY;\
+	type MPCC_GLOBAL_ALPHA;\
+	type MPCC_GLOBAL_GAIN;\
 	type MPCC_IDLE;\
 	type MPCC_BUSY;\
 	type MPCC_OPP_ID;\
 	type MPCC_BG_G_Y;\
 	type MPCC_BG_R_CR;\
 	type MPCC_BG_B_CB;\
+	type MPCC_SM_EN;\
+	type MPCC_SM_MODE;\
+	type MPCC_SM_FRAME_ALT;\
+	type MPCC_SM_FIELD_ALT;\
+	type MPCC_SM_FORCE_NEXT_FRAME_POL;\
+	type MPCC_SM_FORCE_NEXT_TOP_POL;\
 	type MPC_OUT_MUX;
 
 struct dcn_mpc_registers {
@@ -117,22 +132,55 @@ void dcn10_mpc_construct(struct dcn10_mpc *mpcc10,
 	const struct dcn_mpc_mask *mpc_mask,
 	int num_mpcc);
 
-int mpc10_mpcc_add(
-		struct mpc *mpc,
-		struct mpcc_cfg *cfg);
-
-void mpc10_mpcc_remove(
-		struct mpc *mpc,
-		struct mpc_tree_cfg *tree_cfg,
-		int opp_id,
-		int dpp_id);
-
-void mpc10_assert_idle_mpcc(
-		struct mpc *mpc,
-		int id);
-
-void mpc10_update_blend_mode(
-		struct mpc *mpc,
-		struct mpcc_cfg *cfg);
+struct mpcc *mpc1_insert_plane(
+	struct mpc *mpc,
+	struct mpc_tree *tree,
+	struct mpcc_blnd_cfg *blnd_cfg,
+	struct mpcc_sm_cfg *sm_cfg,
+	struct mpcc *insert_above_mpcc,
+	int dpp_id,
+	int mpcc_id);
+
+void mpc1_remove_mpcc(
+	struct mpc *mpc,
+	struct mpc_tree *tree,
+	struct mpcc *mpcc);
+
+void mpc1_mpc_init(
+	struct mpc *mpc);
+
+void mpc1_assert_idle_mpcc(
+	struct mpc *mpc,
+	int id);
+
+void mpc1_set_bg_color(
+	struct mpc *mpc,
+	struct tg_color *bg_color,
+	int id);
+
+void mpc1_update_stereo_mix(
+	struct mpc *mpc,
+	struct mpcc_sm_cfg *sm_cfg,
+	int mpcc_id);
+
+bool mpc1_is_mpcc_idle(
+	struct mpc *mpc,
+	int mpcc_id);
+
+void mpc1_assert_mpcc_idle_before_connect(
+	struct mpc *mpc,
+	int mpcc_id);
+
+void mpc1_init_mpcc_list_from_hw(
+	struct mpc *mpc,
+	struct mpc_tree *tree);
+
+struct mpcc *mpc1_get_mpcc(
+	struct mpc *mpc,
+	int mpcc_id);
+
+struct mpcc *mpc1_get_mpcc_for_dpp(
+	struct mpc_tree *tree,
+	int dpp_id);
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
index a136f70b7a3c..f6ba0eef4489 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
@@ -38,7 +38,6 @@
 	oppn10->base.ctx
 
 
-
 /************* FORMATTER ************/
 
 /**
@@ -47,7 +46,7 @@
  *	2) enable truncation
  *	3) HW remove 12bit FMT support for DCE11 power saving reason.
  */
-static void set_truncation(
+static void opp1_set_truncation(
 		struct dcn10_opp *oppn10,
 		const struct bit_depth_reduction_params *params)
 {
@@ -57,7 +56,7 @@ static void set_truncation(
 		FMT_TRUNCATE_MODE, params->flags.TRUNCATE_MODE);
 }
 
-static void set_spatial_dither(
+static void opp1_set_spatial_dither(
 	struct dcn10_opp *oppn10,
 	const struct bit_depth_reduction_params *params)
 {
@@ -136,14 +135,14 @@ static void set_spatial_dither(
 			FMT_RGB_RANDOM_ENABLE, params->flags.RGB_RANDOM);
 }
 
-static void oppn10_program_bit_depth_reduction(
+void opp1_program_bit_depth_reduction(
 	struct output_pixel_processor *opp,
 	const struct bit_depth_reduction_params *params)
 {
 	struct dcn10_opp *oppn10 = TO_DCN10_OPP(opp);
 
-	set_truncation(oppn10, params);
-	set_spatial_dither(oppn10, params);
+	opp1_set_truncation(oppn10, params);
+	opp1_set_spatial_dither(oppn10, params);
 	/* TODO
 	 * set_temporal_dither(oppn10, params);
 	 */
@@ -156,7 +155,7 @@ static void oppn10_program_bit_depth_reduction(
  *		0: RGB 4:4:4 or YCbCr 4:4:4 or YOnly
  *		1: YCbCr 4:2:2
  */
-static void set_pixel_encoding(
+static void opp1_set_pixel_encoding(
 	struct dcn10_opp *oppn10,
 	const struct clamping_and_pixel_encoding_params *params)
 {
@@ -186,7 +185,7 @@ static void set_pixel_encoding(
  *		7 for programable
  *	2) Enable clamp if Limited range requested
  */
-static void opp_set_clamping(
+static void opp1_set_clamping(
 	struct dcn10_opp *oppn10,
 	const struct clamping_and_pixel_encoding_params *params)
 {
@@ -224,7 +223,7 @@ static void opp_set_clamping(
 
 }
 
-static void oppn10_set_dyn_expansion(
+void opp1_set_dyn_expansion(
 	struct output_pixel_processor *opp,
 	enum dc_color_space color_sp,
 	enum dc_color_depth color_dpth,
@@ -264,17 +263,17 @@ static void oppn10_set_dyn_expansion(
 	}
 }
 
-static void opp_program_clamping_and_pixel_encoding(
+static void opp1_program_clamping_and_pixel_encoding(
 	struct output_pixel_processor *opp,
 	const struct clamping_and_pixel_encoding_params *params)
 {
 	struct dcn10_opp *oppn10 = TO_DCN10_OPP(opp);
 
-	opp_set_clamping(oppn10, params);
-	set_pixel_encoding(oppn10, params);
+	opp1_set_clamping(oppn10, params);
+	opp1_set_pixel_encoding(oppn10, params);
 }
 
-static void oppn10_program_fmt(
+void opp1_program_fmt(
 	struct output_pixel_processor *opp,
 	struct bit_depth_reduction_params *fmt_bit_depth,
 	struct clamping_and_pixel_encoding_params *clamping)
@@ -286,44 +285,104 @@ static void oppn10_program_fmt(
 
 	/* dithering is affected by <CrtcSourceSelect>, hence should be
 	 * programmed afterwards */
-	oppn10_program_bit_depth_reduction(
+	opp1_program_bit_depth_reduction(
 		opp,
 		fmt_bit_depth);
 
-	opp_program_clamping_and_pixel_encoding(
+	opp1_program_clamping_and_pixel_encoding(
 		opp,
 		clamping);
 
 	return;
 }
 
+void opp1_program_stereo(
+	struct output_pixel_processor *opp,
+	bool enable,
+	const struct dc_crtc_timing *timing)
+{
+	struct dcn10_opp *oppn10 = TO_DCN10_OPP(opp);
+
+	uint32_t active_width = timing->h_addressable - timing->h_border_right - timing->h_border_right;
+	uint32_t space1_size = timing->v_total - timing->v_addressable;
+	/* TODO: confirm computation of space2_size */
+	uint32_t space2_size = timing->v_total - timing->v_addressable;
 
+	if (!enable) {
+		active_width = 0;
+		space1_size = 0;
+		space2_size = 0;
+	}
+
+	/* TODO: for which cases should FMT_STEREOSYNC_OVERRIDE be set? */
+	REG_UPDATE(FMT_CONTROL, FMT_STEREOSYNC_OVERRIDE, 0);
+
+	REG_UPDATE(OPPBUF_CONTROL, OPPBUF_ACTIVE_WIDTH, active_width);
+
+	/* Program OPPBUF_3D_VACT_SPACE1_SIZE and OPPBUF_VACT_SPACE2_SIZE registers
+	 * In 3D progressive frames, Vactive space happens only in between the 2 frames,
+	 * so only need to program OPPBUF_3D_VACT_SPACE1_SIZE
+	 * In 3D alternative frames, left and right frames, top and bottom field.
+	 */
+	if (timing->timing_3d_format == TIMING_3D_FORMAT_FRAME_ALTERNATE)
+		REG_UPDATE(OPPBUF_3D_PARAMETERS_0, OPPBUF_3D_VACT_SPACE2_SIZE, space2_size);
+	else
+		REG_UPDATE(OPPBUF_3D_PARAMETERS_0, OPPBUF_3D_VACT_SPACE1_SIZE, space1_size);
+
+	/* TODO: Is programming of OPPBUF_DUMMY_DATA_R/G/B needed? */
+	/*
+	REG_UPDATE(OPPBUF_3D_PARAMETERS_0,
+			OPPBUF_DUMMY_DATA_R, data_r);
+	REG_UPDATE(OPPBUF_3D_PARAMETERS_1,
+			OPPBUF_DUMMY_DATA_G, data_g);
+	REG_UPDATE(OPPBUF_3D_PARAMETERS_1,
+			OPPBUF_DUMMY_DATA_B, _data_b);
+	*/
+}
 
-static void oppn10_set_stereo_polarity(
-		struct output_pixel_processor *opp,
-		bool enable, bool rightEyePolarity)
+void opp1_program_oppbuf(
+	struct output_pixel_processor *opp,
+	struct oppbuf_params *oppbuf)
 {
 	struct dcn10_opp *oppn10 = TO_DCN10_OPP(opp);
 
-	REG_UPDATE(FMT_CONTROL, FMT_STEREOSYNC_OVERRIDE, enable);
+	/* Program the oppbuf active width to be the frame width from mpc */
+	REG_UPDATE(OPPBUF_CONTROL, OPPBUF_ACTIVE_WIDTH, oppbuf->active_width);
+
+	/* Specifies the number of segments in multi-segment mode (DP-MSO operation)
+	 * description  "In 1/2/4 segment mode, specifies the horizontal active width in pixels of the display panel.
+	 * In 4 segment split left/right mode, specifies the horizontal 1/2 active width in pixels of the display panel.
+	 * Used to determine segment boundaries in multi-segment mode. Used to determine the width of the vertical active space in 3D frame packed modes.
+	 * OPPBUF_ACTIVE_WIDTH must be integer divisible by the total number of segments."
+	 */
+	REG_UPDATE(OPPBUF_CONTROL, OPPBUF_DISPLAY_SEGMENTATION, oppbuf->mso_segmentation);
+
+	/* description  "Specifies the number of overlap pixels (1-8 overlapping pixels supported), used in multi-segment mode (DP-MSO operation)" */
+	REG_UPDATE(OPPBUF_CONTROL, OPPBUF_OVERLAP_PIXEL_NUM, oppbuf->mso_overlap_pixel_num);
+
+	/* description  "Specifies the number of times a pixel is replicated (0-15 pixel replications supported).
+	 * A value of 0 disables replication. The total number of times a pixel is output is OPPBUF_PIXEL_REPETITION + 1."
+	 */
+	REG_UPDATE(OPPBUF_CONTROL, OPPBUF_PIXEL_REPETITION, oppbuf->pixel_repetition);
+
 }
 
 /*****************************************/
 /* Constructor, Destructor               */
 /*****************************************/
 
-static void dcn10_opp_destroy(struct output_pixel_processor **opp)
+void opp1_destroy(struct output_pixel_processor **opp)
 {
 	kfree(TO_DCN10_OPP(*opp));
 	*opp = NULL;
 }
 
 static struct opp_funcs dcn10_opp_funcs = {
-		.opp_set_dyn_expansion = oppn10_set_dyn_expansion,
-		.opp_program_fmt = oppn10_program_fmt,
-		.opp_program_bit_depth_reduction = oppn10_program_bit_depth_reduction,
-		.opp_set_stereo_polarity = oppn10_set_stereo_polarity,
-		.opp_destroy = dcn10_opp_destroy
+		.opp_set_dyn_expansion = opp1_set_dyn_expansion,
+		.opp_program_fmt = opp1_program_fmt,
+		.opp_program_bit_depth_reduction = opp1_program_bit_depth_reduction,
+		.opp_program_stereo = opp1_program_stereo,
+		.opp_destroy = opp1_destroy
 };
 
 void dcn10_opp_construct(struct dcn10_opp *oppn10,
@@ -333,19 +392,12 @@ void dcn10_opp_construct(struct dcn10_opp *oppn10,
 	const struct dcn10_opp_shift *opp_shift,
 	const struct dcn10_opp_mask *opp_mask)
 {
-	int i;
+
 	oppn10->base.ctx = ctx;
 	oppn10->base.inst = inst;
 	oppn10->base.funcs = &dcn10_opp_funcs;
 
-	oppn10->base.mpc_tree.dpp[0] = inst;
-	oppn10->base.mpc_tree.mpcc[0] = inst;
-	oppn10->base.mpc_tree.num_pipes = 1;
-	for (i = 0; i < MAX_PIPES; i++)
-		oppn10->base.mpcc_disconnect_pending[i] = false;
-
 	oppn10->regs = regs;
 	oppn10->opp_shift = opp_shift;
 	oppn10->opp_mask = opp_mask;
 }
-
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.h
index 790ce6014832..bc5058af6266 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.h
@@ -41,11 +41,28 @@
 	SRI(FMT_DITHER_RAND_B_SEED, FMT, id), \
 	SRI(FMT_CLAMP_CNTL, FMT, id), \
 	SRI(FMT_DYNAMIC_EXP_CNTL, FMT, id), \
-	SRI(FMT_MAP420_MEMORY_CONTROL, FMT, id)
+	SRI(FMT_MAP420_MEMORY_CONTROL, FMT, id), \
+	SRI(OPPBUF_CONTROL, OPPBUF, id),\
+	SRI(OPPBUF_3D_PARAMETERS_0, OPPBUF, id), \
+	SRI(OPPBUF_3D_PARAMETERS_1, OPPBUF, id)
 
 #define OPP_REG_LIST_DCN10(id) \
 	OPP_REG_LIST_DCN(id)
 
+#define OPP_COMMON_REG_VARIABLE_LIST \
+	uint32_t FMT_BIT_DEPTH_CONTROL; \
+	uint32_t FMT_CONTROL; \
+	uint32_t FMT_DITHER_RAND_R_SEED; \
+	uint32_t FMT_DITHER_RAND_G_SEED; \
+	uint32_t FMT_DITHER_RAND_B_SEED; \
+	uint32_t FMT_CLAMP_CNTL; \
+	uint32_t FMT_DYNAMIC_EXP_CNTL; \
+	uint32_t FMT_MAP420_MEMORY_CONTROL; \
+	uint32_t OPPBUF_CONTROL; \
+	uint32_t OPPBUF_CONTROL1; \
+	uint32_t OPPBUF_3D_PARAMETERS_0; \
+	uint32_t OPPBUF_3D_PARAMETERS_1
+
 #define OPP_MASK_SH_LIST_DCN(mask_sh) \
 	OPP_SF(FMT0_FMT_BIT_DEPTH_CONTROL, FMT_TRUNCATE_EN, mask_sh), \
 	OPP_SF(FMT0_FMT_BIT_DEPTH_CONTROL, FMT_TRUNCATE_DEPTH, mask_sh), \
@@ -68,46 +85,18 @@
 	OPP_SF(FMT0_FMT_CLAMP_CNTL, FMT_CLAMP_COLOR_FORMAT, mask_sh), \
 	OPP_SF(FMT0_FMT_DYNAMIC_EXP_CNTL, FMT_DYNAMIC_EXP_EN, mask_sh), \
 	OPP_SF(FMT0_FMT_DYNAMIC_EXP_CNTL, FMT_DYNAMIC_EXP_MODE, mask_sh), \
-	OPP_SF(FMT0_FMT_MAP420_MEMORY_CONTROL, FMT_MAP420MEM_PWR_FORCE, mask_sh)
+	OPP_SF(FMT0_FMT_MAP420_MEMORY_CONTROL, FMT_MAP420MEM_PWR_FORCE, mask_sh), \
+	OPP_SF(OPPBUF0_OPPBUF_CONTROL, OPPBUF_ACTIVE_WIDTH, mask_sh),\
+	OPP_SF(OPPBUF0_OPPBUF_CONTROL, OPPBUF_PIXEL_REPETITION, mask_sh),\
+	OPP_SF(OPPBUF0_OPPBUF_3D_PARAMETERS_0, OPPBUF_3D_VACT_SPACE1_SIZE, mask_sh), \
+	OPP_SF(OPPBUF0_OPPBUF_3D_PARAMETERS_0, OPPBUF_3D_VACT_SPACE2_SIZE, mask_sh)
 
 #define OPP_MASK_SH_LIST_DCN10(mask_sh) \
-	OPP_MASK_SH_LIST_DCN(mask_sh)
+	OPP_MASK_SH_LIST_DCN(mask_sh), \
+	OPP_SF(OPPBUF0_OPPBUF_CONTROL, OPPBUF_DISPLAY_SEGMENTATION, mask_sh),\
+	OPP_SF(OPPBUF0_OPPBUF_CONTROL, OPPBUF_OVERLAP_PIXEL_NUM, mask_sh)
 
 #define OPP_DCN10_REG_FIELD_LIST(type) \
-	type DPG_EN; \
-	type DPG_MODE; \
-	type DPG_VRES; \
-	type DPG_HRES; \
-	type DPG_COLOUR0_R_CR; \
-	type DPG_COLOUR1_R_CR; \
-	type DPG_COLOUR0_B_CB; \
-	type DPG_COLOUR1_B_CB; \
-	type DPG_COLOUR0_G_Y; \
-	type DPG_COLOUR1_G_Y; \
-	type CM_OCSC_C11; \
-	type CM_OCSC_C12; \
-	type CM_OCSC_C13; \
-	type CM_OCSC_C14; \
-	type CM_OCSC_C21; \
-	type CM_OCSC_C22; \
-	type CM_OCSC_C23; \
-	type CM_OCSC_C24; \
-	type CM_OCSC_C31; \
-	type CM_OCSC_C32; \
-	type CM_OCSC_C33; \
-	type CM_OCSC_C34; \
-	type CM_COMB_C11; \
-	type CM_COMB_C12; \
-	type CM_COMB_C13; \
-	type CM_COMB_C14; \
-	type CM_COMB_C21; \
-	type CM_COMB_C22; \
-	type CM_COMB_C23; \
-	type CM_COMB_C24; \
-	type CM_COMB_C31; \
-	type CM_COMB_C32; \
-	type CM_COMB_C33; \
-	type CM_COMB_C34; \
 	type FMT_TRUNCATE_EN; \
 	type FMT_TRUNCATE_DEPTH; \
 	type FMT_TRUNCATE_MODE; \
@@ -129,7 +118,18 @@
 	type FMT_DYNAMIC_EXP_EN; \
 	type FMT_DYNAMIC_EXP_MODE; \
 	type FMT_MAP420MEM_PWR_FORCE; \
-	type FMT_STEREOSYNC_OVERRIDE
+	type FMT_STEREOSYNC_OVERRIDE; \
+	type OPPBUF_ACTIVE_WIDTH;\
+	type OPPBUF_PIXEL_REPETITION;\
+	type OPPBUF_DISPLAY_SEGMENTATION;\
+	type OPPBUF_OVERLAP_PIXEL_NUM;\
+	type OPPBUF_NUM_SEGMENT_PADDED_PIXELS; \
+	type OPPBUF_3D_VACT_SPACE1_SIZE; \
+	type OPPBUF_3D_VACT_SPACE2_SIZE
+
+struct dcn10_opp_registers {
+	OPP_COMMON_REG_VARIABLE_LIST;
+};
 
 struct dcn10_opp_shift {
 	OPP_DCN10_REG_FIELD_LIST(uint8_t);
@@ -139,33 +139,6 @@ struct dcn10_opp_mask {
 	OPP_DCN10_REG_FIELD_LIST(uint32_t);
 };
 
-struct dcn10_opp_registers {
-	uint32_t DPG_CONTROL;
-	uint32_t DPG_COLOUR_B_CB;
-	uint32_t DPG_COLOUR_G_Y;
-	uint32_t DPG_COLOUR_R_CR;
-	uint32_t CM_OCSC_C11_C12;
-	uint32_t CM_OCSC_C13_C14;
-	uint32_t CM_OCSC_C21_C22;
-	uint32_t CM_OCSC_C23_C24;
-	uint32_t CM_OCSC_C31_C32;
-	uint32_t CM_OCSC_C33_C34;
-	uint32_t CM_COMB_C11_C12;
-	uint32_t CM_COMB_C13_C14;
-	uint32_t CM_COMB_C21_C22;
-	uint32_t CM_COMB_C23_C24;
-	uint32_t CM_COMB_C31_C32;
-	uint32_t CM_COMB_C33_C34;
-	uint32_t FMT_BIT_DEPTH_CONTROL;
-	uint32_t FMT_CONTROL;
-	uint32_t FMT_DITHER_RAND_R_SEED;
-	uint32_t FMT_DITHER_RAND_G_SEED;
-	uint32_t FMT_DITHER_RAND_B_SEED;
-	uint32_t FMT_CLAMP_CNTL;
-	uint32_t FMT_DYNAMIC_EXP_CNTL;
-	uint32_t FMT_MAP420_MEMORY_CONTROL;
-};
-
 struct dcn10_opp {
 	struct output_pixel_processor base;
 
@@ -183,4 +156,26 @@ void dcn10_opp_construct(struct dcn10_opp *oppn10,
 	const struct dcn10_opp_shift *opp_shift,
 	const struct dcn10_opp_mask *opp_mask);
 
+void opp1_set_dyn_expansion(
+	struct output_pixel_processor *opp,
+	enum dc_color_space color_sp,
+	enum dc_color_depth color_dpth,
+	enum signal_type signal);
+
+void opp1_program_fmt(
+	struct output_pixel_processor *opp,
+	struct bit_depth_reduction_params *fmt_bit_depth,
+	struct clamping_and_pixel_encoding_params *clamping);
+
+void opp1_program_bit_depth_reduction(
+	struct output_pixel_processor *opp,
+	const struct bit_depth_reduction_params *params);
+
+void opp1_program_stereo(
+	struct output_pixel_processor *opp,
+	bool enable,
+	const struct dc_crtc_timing *timing);
+
+void opp1_destroy(struct output_pixel_processor **opp);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index c7333cdf1802..4bf64d1b2c60 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_timing_generator.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -23,19 +23,20 @@
  *
  */
 
+
 #include "reg_helper.h"
-#include "dcn10_timing_generator.h"
+#include "dcn10_optc.h"
 #include "dc.h"
 
 #define REG(reg)\
-	tgn10->tg_regs->reg
+	optc1->tg_regs->reg
 
 #define CTX \
-	tgn10->base.ctx
+	optc1->base.ctx
 
 #undef FN
 #define FN(reg_name, field_name) \
-	tgn10->tg_shift->field_name, tgn10->tg_mask->field_name
+	optc1->tg_shift->field_name, optc1->tg_mask->field_name
 
 #define STATIC_SCREEN_EVENT_MASK_RANGETIMING_DOUBLE_BUFFER_UPDATE_EN 0x100
 
@@ -45,8 +46,8 @@
 * This is a workaround for a bug that has existed since R5xx and has not been
 * fixed keep Front porch at minimum 2 for Interlaced mode or 1 for progressive.
 */
-static void tgn10_apply_front_porch_workaround(
-	struct timing_generator *tg,
+static void optc1_apply_front_porch_workaround(
+	struct timing_generator *optc,
 	struct dc_crtc_timing *timing)
 {
 	if (timing->flags.INTERLACE == 1) {
@@ -58,30 +59,30 @@ static void tgn10_apply_front_porch_workaround(
 	}
 }
 
-static void tgn10_program_global_sync(
-		struct timing_generator *tg)
+void optc1_program_global_sync(
+		struct timing_generator *optc)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
-	if (tg->dlg_otg_param.vstartup_start == 0) {
+	if (optc->dlg_otg_param.vstartup_start == 0) {
 		BREAK_TO_DEBUGGER();
 		return;
 	}
 
 	REG_SET(OTG_VSTARTUP_PARAM, 0,
-		VSTARTUP_START, tg->dlg_otg_param.vstartup_start);
+		VSTARTUP_START, optc->dlg_otg_param.vstartup_start);
 
 	REG_SET_2(OTG_VUPDATE_PARAM, 0,
-			VUPDATE_OFFSET, tg->dlg_otg_param.vupdate_offset,
-			VUPDATE_WIDTH, tg->dlg_otg_param.vupdate_width);
+			VUPDATE_OFFSET, optc->dlg_otg_param.vupdate_offset,
+			VUPDATE_WIDTH, optc->dlg_otg_param.vupdate_width);
 
 	REG_SET(OTG_VREADY_PARAM, 0,
-			VREADY_OFFSET, tg->dlg_otg_param.vready_offset);
+			VREADY_OFFSET, optc->dlg_otg_param.vready_offset);
 }
 
-static void tgn10_disable_stereo(struct timing_generator *tg)
+static void optc1_disable_stereo(struct timing_generator *optc)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	REG_SET(OTG_STEREO_CONTROL, 0,
 		OTG_STEREO_EN, 0);
@@ -90,11 +91,6 @@ static void tgn10_disable_stereo(struct timing_generator *tg)
 		OTG_3D_STRUCTURE_EN, 0,
 		OTG_3D_STRUCTURE_V_UPDATE_MODE, 0,
 		OTG_3D_STRUCTURE_STEREO_SEL_OVR, 0);
-
-	REG_UPDATE(OPPBUF_CONTROL,
-		OPPBUF_ACTIVE_WIDTH, 0);
-	REG_UPDATE(OPPBUF_3D_PARAMETERS_0,
-		OPPBUF_3D_VACT_SPACE1_SIZE, 0);
 }
 
 /**
@@ -102,8 +98,8 @@ static void tgn10_disable_stereo(struct timing_generator *tg)
  * Program CRTC Timing Registers - OTG_H_*, OTG_V_*, Pixel repetition.
  * Including SYNC. Call BIOS command table to program Timings.
  */
-static void tgn10_program_timing(
-	struct timing_generator *tg,
+void optc1_program_timing(
+	struct timing_generator *optc,
 	const struct dc_crtc_timing *dc_crtc_timing,
 	bool use_vbios)
 {
@@ -121,10 +117,10 @@ static void tgn10_program_timing(
 	uint32_t h_div_2;
 	int32_t vertical_line_start;
 
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	patched_crtc_timing = *dc_crtc_timing;
-	tgn10_apply_front_porch_workaround(tg, &patched_crtc_timing);
+	optc1_apply_front_porch_workaround(optc, &patched_crtc_timing);
 
 	/* Load horizontal timing */
 
@@ -217,7 +213,7 @@ static void tgn10_program_timing(
 	/* Use OTG_VERTICAL_INTERRUPT2 replace VUPDATE interrupt,
 	 * program the reg for interrupt postition.
 	 */
-	vertical_line_start = asic_blank_end - tg->dlg_otg_param.vstartup_start + 1;
+	vertical_line_start = asic_blank_end - optc->dlg_otg_param.vstartup_start + 1;
 	if (vertical_line_start < 0) {
 		ASSERT(0);
 		vertical_line_start = 0;
@@ -233,26 +229,25 @@ static void tgn10_program_timing(
 			OTG_V_SYNC_A_POL, v_sync_polarity);
 
 	v_init = asic_blank_start;
-	if (tg->dlg_otg_param.signal == SIGNAL_TYPE_DISPLAY_PORT ||
-		tg->dlg_otg_param.signal == SIGNAL_TYPE_DISPLAY_PORT_MST ||
-		tg->dlg_otg_param.signal == SIGNAL_TYPE_EDP) {
+	if (optc->dlg_otg_param.signal == SIGNAL_TYPE_DISPLAY_PORT ||
+		optc->dlg_otg_param.signal == SIGNAL_TYPE_DISPLAY_PORT_MST ||
+		optc->dlg_otg_param.signal == SIGNAL_TYPE_EDP) {
 		start_point = 1;
 		if (patched_crtc_timing.flags.INTERLACE == 1)
 			field_num = 1;
 	}
 	v_fp2 = 0;
-	if (tg->dlg_otg_param.vstartup_start > asic_blank_end)
-		v_fp2 = tg->dlg_otg_param.vstartup_start > asic_blank_end;
+	if (optc->dlg_otg_param.vstartup_start > asic_blank_end)
+		v_fp2 = optc->dlg_otg_param.vstartup_start > asic_blank_end;
 
 	/* Interlace */
 	if (patched_crtc_timing.flags.INTERLACE == 1) {
 		REG_UPDATE(OTG_INTERLACE_CONTROL,
 				OTG_INTERLACE_ENABLE, 1);
 		v_init = v_init / 2;
-		if ((tg->dlg_otg_param.vstartup_start/2)*2 > asic_blank_end)
+		if ((optc->dlg_otg_param.vstartup_start/2)*2 > asic_blank_end)
 			v_fp2 = v_fp2 / 2;
-	}
-	else
+	} else
 		REG_UPDATE(OTG_INTERLACE_CONTROL,
 				OTG_INTERLACE_ENABLE, 0);
 
@@ -270,13 +265,13 @@ static void tgn10_program_timing(
 			OTG_START_POINT_CNTL, start_point,
 			OTG_FIELD_NUMBER_CNTL, field_num);
 
-	tgn10_program_global_sync(tg);
+	optc1_program_global_sync(optc);
 
 	/* TODO
 	 * patched_crtc_timing.flags.HORZ_COUNT_BY_TWO == 1
 	 * program_horz_count_by_2
 	 * for DVI 30bpp mode, 0 otherwise
-	 * program_horz_count_by_2(tg, &patched_crtc_timing);
+	 * program_horz_count_by_2(optc, &patched_crtc_timing);
 	 */
 
 	/* Enable stereo - only when we need to pack 3D frame. Other types
@@ -290,13 +285,23 @@ static void tgn10_program_timing(
 
 }
 
+static void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enable)
+{
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+	uint32_t blank_data_double_buffer_enable = enable ? 1 : 0;
+
+	REG_UPDATE(OTG_DOUBLE_BUFFER_CONTROL,
+			OTG_BLANK_DATA_DOUBLE_BUFFER_EN, blank_data_double_buffer_enable);
+}
+
 /**
  * unblank_crtc
  * Call ASIC Control Object to UnBlank CRTC.
  */
-static void tgn10_unblank_crtc(struct timing_generator *tg)
+static void optc1_unblank_crtc(struct timing_generator *optc)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 	uint32_t vertical_interrupt_enable = 0;
 
 	REG_GET(OTG_VERTICAL_INTERRUPT2_CONTROL,
@@ -306,8 +311,7 @@ static void tgn10_unblank_crtc(struct timing_generator *tg)
 	 * this check will be removed.
 	 */
 	if (vertical_interrupt_enable)
-		REG_UPDATE(OTG_DOUBLE_BUFFER_CONTROL,
-				OTG_BLANK_DATA_DOUBLE_BUFFER_EN, 1);
+		optc1_set_blank_data_double_buffer(optc, true);
 
 	REG_UPDATE_2(OTG_BLANK_CONTROL,
 			OTG_BLANK_DATA_EN, 0,
@@ -319,37 +323,29 @@ static void tgn10_unblank_crtc(struct timing_generator *tg)
  * Call ASIC Control Object to Blank CRTC.
  */
 
-static void tgn10_blank_crtc(struct timing_generator *tg)
+static void optc1_blank_crtc(struct timing_generator *optc)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	REG_UPDATE_2(OTG_BLANK_CONTROL,
 			OTG_BLANK_DATA_EN, 1,
 			OTG_BLANK_DE_MODE, 0);
 
-	/* todo: why are we waiting for BLANK_DATA_EN?  shouldn't we be waiting
-	 * for status?
-	 */
-	REG_WAIT(OTG_BLANK_CONTROL,
-			OTG_BLANK_DATA_EN, 1,
-			1, 100000);
-
-	REG_UPDATE(OTG_DOUBLE_BUFFER_CONTROL,
-			OTG_BLANK_DATA_DOUBLE_BUFFER_EN, 0);
+	optc1_set_blank_data_double_buffer(optc, false);
 }
 
-static void tgn10_set_blank(struct timing_generator *tg,
+void optc1_set_blank(struct timing_generator *optc,
 		bool enable_blanking)
 {
 	if (enable_blanking)
-		tgn10_blank_crtc(tg);
+		optc1_blank_crtc(optc);
 	else
-		tgn10_unblank_crtc(tg);
+		optc1_unblank_crtc(optc);
 }
 
-static bool tgn10_is_blanked(struct timing_generator *tg)
+bool optc1_is_blanked(struct timing_generator *optc)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 	uint32_t blank_en;
 	uint32_t blank_state;
 
@@ -360,9 +356,9 @@ static bool tgn10_is_blanked(struct timing_generator *tg)
 	return blank_en && blank_state;
 }
 
-static void tgn10_enable_optc_clock(struct timing_generator *tg, bool enable)
+void optc1_enable_optc_clock(struct timing_generator *optc, bool enable)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	if (enable) {
 		REG_UPDATE_2(OPTC_INPUT_CLOCK_CONTROL,
@@ -385,19 +381,9 @@ static void tgn10_enable_optc_clock(struct timing_generator *tg, bool enable)
 				OTG_CLOCK_GATE_DIS, 0,
 				OTG_CLOCK_EN, 0);
 
-		if (tg->ctx->dce_environment != DCE_ENV_FPGA_MAXIMUS)
-			REG_WAIT(OTG_CLOCK_CONTROL,
-					OTG_CLOCK_ON, 0,
-					1, 1000);
-
 		REG_UPDATE_2(OPTC_INPUT_CLOCK_CONTROL,
 				OPTC_INPUT_CLK_GATE_DIS, 0,
 				OPTC_INPUT_CLK_EN, 0);
-
-		if (tg->ctx->dce_environment != DCE_ENV_FPGA_MAXIMUS)
-			REG_WAIT(OPTC_INPUT_CLOCK_CONTROL,
-					OPTC_INPUT_CLK_ON, 0,
-					1, 1000);
 	}
 }
 
@@ -405,19 +391,19 @@ static void tgn10_enable_optc_clock(struct timing_generator *tg, bool enable)
  * Enable CRTC
  * Enable CRTC - call ASIC Control Object to enable Timing generator.
  */
-static bool tgn10_enable_crtc(struct timing_generator *tg)
+static bool optc1_enable_crtc(struct timing_generator *optc)
 {
 	/* TODO FPGA wait for answer
 	 * OTG_MASTER_UPDATE_MODE != CRTC_MASTER_UPDATE_MODE
 	 * OTG_MASTER_UPDATE_LOCK != CRTC_MASTER_UPDATE_LOCK
 	 */
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	/* opp instance for OTG. For DCN1.0, ODM is remoed.
 	 * OPP and OPTC should 1:1 mapping
 	 */
 	REG_UPDATE(OPTC_DATA_SOURCE_SELECT,
-			OPTC_SRC_SEL, tg->inst);
+			OPTC_SRC_SEL, optc->inst);
 
 	/* VTG enable first is for HW workaround */
 	REG_UPDATE(CONTROL,
@@ -432,9 +418,9 @@ static bool tgn10_enable_crtc(struct timing_generator *tg)
 }
 
 /* disable_crtc - call ASIC Control Object to disable Timing generator. */
-static bool tgn10_disable_crtc(struct timing_generator *tg)
+bool optc1_disable_crtc(struct timing_generator *optc)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	/* disable otg request until end of the first line
 	 * in the vertical blank region
@@ -455,11 +441,11 @@ static bool tgn10_disable_crtc(struct timing_generator *tg)
 }
 
 
-static void tgn10_program_blank_color(
-		struct timing_generator *tg,
+void optc1_program_blank_color(
+		struct timing_generator *optc,
 		const struct tg_color *black_color)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	REG_SET_3(OTG_BLACK_COLOR, 0,
 			OTG_BLACK_COLOR_B_CB, black_color->color_b_cb,
@@ -467,15 +453,15 @@ static void tgn10_program_blank_color(
 			OTG_BLACK_COLOR_R_CR, black_color->color_r_cr);
 }
 
-static bool tgn10_validate_timing(
-	struct timing_generator *tg,
+bool optc1_validate_timing(
+	struct timing_generator *optc,
 	const struct dc_crtc_timing *timing)
 {
 	uint32_t interlace_factor;
 	uint32_t v_blank;
 	uint32_t h_blank;
 	uint32_t min_v_blank;
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	ASSERT(timing != NULL);
 
@@ -496,9 +482,6 @@ static bool tgn10_validate_timing(
 		timing->timing_3d_format != TIMING_3D_FORMAT_INBAND_FA)
 		return false;
 
-	if (timing->timing_3d_format != TIMING_3D_FORMAT_NONE &&
-		tg->ctx->dc->debug.disable_stereo_support)
-		return false;
 	/* Temporarily blocking interlacing mode until it's supported */
 	if (timing->flags.INTERLACE == 1)
 		return false;
@@ -508,19 +491,19 @@ static bool tgn10_validate_timing(
 	 * needs more than 8192 horizontal and
 	 * more than 8192 vertical total pixels)
 	 */
-	if (timing->h_total > tgn10->max_h_total ||
-		timing->v_total > tgn10->max_v_total)
+	if (timing->h_total > optc1->max_h_total ||
+		timing->v_total > optc1->max_v_total)
 		return false;
 
 
-	if (h_blank < tgn10->min_h_blank)
+	if (h_blank < optc1->min_h_blank)
 		return false;
 
-	if (timing->h_sync_width  < tgn10->min_h_sync_width ||
-		 timing->v_sync_width  < tgn10->min_v_sync_width)
+	if (timing->h_sync_width  < optc1->min_h_sync_width ||
+		 timing->v_sync_width  < optc1->min_v_sync_width)
 		return false;
 
-	min_v_blank = timing->flags.INTERLACE?tgn10->min_v_blank_interlace:tgn10->min_v_blank;
+	min_v_blank = timing->flags.INTERLACE?optc1->min_v_blank_interlace:optc1->min_v_blank;
 
 	if (v_blank < min_v_blank)
 		return false;
@@ -537,15 +520,15 @@ static bool tgn10_validate_timing(
  * holds the counter of frames.
  *
  * @param
- * struct timing_generator *tg - [in] timing generator which controls the
+ * struct timing_generator *optc - [in] timing generator which controls the
  * desired CRTC
  *
  * @return
  * Counter of frames, which should equal to number of vblanks.
  */
-static uint32_t tgn10_get_vblank_counter(struct timing_generator *tg)
+uint32_t optc1_get_vblank_counter(struct timing_generator *optc)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 	uint32_t frame_count;
 
 	REG_GET(OTG_STATUS_FRAME_COUNT,
@@ -554,38 +537,34 @@ static uint32_t tgn10_get_vblank_counter(struct timing_generator *tg)
 	return frame_count;
 }
 
-static void tgn10_lock(struct timing_generator *tg)
+void optc1_lock(struct timing_generator *optc)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	REG_SET(OTG_GLOBAL_CONTROL0, 0,
-			OTG_MASTER_UPDATE_LOCK_SEL, tg->inst);
+			OTG_MASTER_UPDATE_LOCK_SEL, optc->inst);
 	REG_SET(OTG_MASTER_UPDATE_LOCK, 0,
 			OTG_MASTER_UPDATE_LOCK, 1);
 
-	if (tg->ctx->dce_environment != DCE_ENV_FPGA_MAXIMUS)
+	/* Should be fast, status does not update on maximus */
+	if (optc->ctx->dce_environment != DCE_ENV_FPGA_MAXIMUS)
 		REG_WAIT(OTG_MASTER_UPDATE_LOCK,
 				UPDATE_LOCK_STATUS, 1,
-				1, 100);
+				1, 10);
 }
 
-static void tgn10_unlock(struct timing_generator *tg)
+void optc1_unlock(struct timing_generator *optc)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	REG_SET(OTG_MASTER_UPDATE_LOCK, 0,
 			OTG_MASTER_UPDATE_LOCK, 0);
-
-	/* why are we waiting here? */
-	REG_WAIT(OTG_DOUBLE_BUFFER_CONTROL,
-			OTG_UPDATE_PENDING, 0,
-			1, 100000);
 }
 
-static void tgn10_get_position(struct timing_generator *tg,
+void optc1_get_position(struct timing_generator *optc,
 		struct crtc_position *position)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	REG_GET_2(OTG_STATUS_POSITION,
 			OTG_HORZ_COUNT, &position->horizontal_count,
@@ -595,12 +574,12 @@ static void tgn10_get_position(struct timing_generator *tg,
 			OTG_VERT_COUNT_NOM, &position->nominal_vcount);
 }
 
-static bool tgn10_is_counter_moving(struct timing_generator *tg)
+bool optc1_is_counter_moving(struct timing_generator *optc)
 {
 	struct crtc_position position1, position2;
 
-	tg->funcs->get_position(tg, &position1);
-	tg->funcs->get_position(tg, &position2);
+	optc->funcs->get_position(optc, &position1);
+	optc->funcs->get_position(optc, &position2);
 
 	if (position1.horizontal_count == position2.horizontal_count &&
 		position1.vertical_count == position2.vertical_count)
@@ -609,21 +588,37 @@ static bool tgn10_is_counter_moving(struct timing_generator *tg)
 		return true;
 }
 
-static bool tgn10_did_triggered_reset_occur(
-	struct timing_generator *tg)
+bool optc1_did_triggered_reset_occur(
+	struct timing_generator *optc)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
-	uint32_t occurred;
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+	uint32_t occurred_force, occurred_vsync;
 
 	REG_GET(OTG_FORCE_COUNT_NOW_CNTL,
-		OTG_FORCE_COUNT_NOW_OCCURRED, &occurred);
+		OTG_FORCE_COUNT_NOW_OCCURRED, &occurred_force);
+
+	REG_GET(OTG_VERT_SYNC_CONTROL,
+		OTG_FORCE_VSYNC_NEXT_LINE_OCCURRED, &occurred_vsync);
 
-	return occurred != 0;
+	return occurred_vsync != 0 || occurred_force != 0;
 }
 
-static void tgn10_enable_reset_trigger(struct timing_generator *tg, int source_tg_inst)
+void optc1_disable_reset_trigger(struct timing_generator *optc)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+	REG_WRITE(OTG_TRIGA_CNTL, 0);
+
+	REG_SET(OTG_FORCE_COUNT_NOW_CNTL, 0,
+		OTG_FORCE_COUNT_NOW_CLEAR, 1);
+
+	REG_SET(OTG_VERT_SYNC_CONTROL, 0,
+		OTG_FORCE_VSYNC_NEXT_LINE_CLEAR, 1);
+}
+
+void optc1_enable_reset_trigger(struct timing_generator *optc, int source_tg_inst)
+{
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 	uint32_t falling_edge;
 
 	REG_GET(OTG_V_SYNC_A_CNTL,
@@ -655,20 +650,55 @@ static void tgn10_enable_reset_trigger(struct timing_generator *tg, int source_t
 			OTG_FORCE_COUNT_NOW_MODE, 2);
 }
 
-static void tgn10_disable_reset_trigger(struct timing_generator *tg)
+void optc1_enable_crtc_reset(
+		struct timing_generator *optc,
+		int source_tg_inst,
+		struct crtc_trigger_info *crtc_tp)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+	uint32_t falling_edge = 0;
+	uint32_t rising_edge = 0;
 
-	REG_WRITE(OTG_TRIGA_CNTL, 0);
+	switch (crtc_tp->event) {
 
-	REG_SET(OTG_FORCE_COUNT_NOW_CNTL, 0,
-			OTG_FORCE_COUNT_NOW_CLEAR, 1);
+	case CRTC_EVENT_VSYNC_RISING:
+		rising_edge = 1;
+		break;
+
+	case CRTC_EVENT_VSYNC_FALLING:
+		falling_edge = 1;
+		break;
+	}
+
+	REG_SET_4(OTG_TRIGA_CNTL, 0,
+		 /* vsync signal from selected OTG pipe based
+		  * on OTG_TRIG_SOURCE_PIPE_SELECT setting
+		  */
+		  OTG_TRIGA_SOURCE_SELECT, 20,
+		  OTG_TRIGA_SOURCE_PIPE_SELECT, source_tg_inst,
+		  /* always detect falling edge */
+		  OTG_TRIGA_RISING_EDGE_DETECT_CNTL, rising_edge,
+		  OTG_TRIGA_FALLING_EDGE_DETECT_CNTL, falling_edge);
+
+	switch (crtc_tp->delay) {
+	case TRIGGER_DELAY_NEXT_LINE:
+		REG_SET(OTG_VERT_SYNC_CONTROL, 0,
+				OTG_AUTO_FORCE_VSYNC_MODE, 1);
+		break;
+	case TRIGGER_DELAY_NEXT_PIXEL:
+		REG_SET(OTG_FORCE_COUNT_NOW_CNTL, 0,
+			/* force H count to H_TOTAL and V count to V_TOTAL in
+			 * progressive mode and V_TOTAL-1 in interlaced mode
+			 */
+			OTG_FORCE_COUNT_NOW_MODE, 2);
+		break;
+	}
 }
 
-static void tgn10_wait_for_state(struct timing_generator *tg,
+void optc1_wait_for_state(struct timing_generator *optc,
 		enum crtc_state state)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	switch (state) {
 	case CRTC_STATE_VBLANK:
@@ -688,8 +718,8 @@ static void tgn10_wait_for_state(struct timing_generator *tg,
 	}
 }
 
-static void tgn10_set_early_control(
-	struct timing_generator *tg,
+void optc1_set_early_control(
+	struct timing_generator *optc,
 	uint32_t early_cntl)
 {
 	/* asic design change, do not need this control
@@ -698,11 +728,11 @@ static void tgn10_set_early_control(
 }
 
 
-static void tgn10_set_static_screen_control(
-	struct timing_generator *tg,
+void optc1_set_static_screen_control(
+	struct timing_generator *optc,
 	uint32_t value)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	/* Bit 8 is no longer applicable in RV for PSR case,
 	 * set bit 8 to 0 if given
@@ -727,11 +757,11 @@ static void tgn10_set_static_screen_control(
  *
  *****************************************************************************
  */
-static void tgn10_set_drr(
-	struct timing_generator *tg,
+void optc1_set_drr(
+	struct timing_generator *optc,
 	const struct drr_params *params)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	if (params != NULL &&
 		params->vertical_total_max > 0 &&
@@ -764,15 +794,15 @@ static void tgn10_set_drr(
 	}
 }
 
-static void tgn10_set_test_pattern(
-	struct timing_generator *tg,
+static void optc1_set_test_pattern(
+	struct timing_generator *optc,
 	/* TODO: replace 'controller_dp_test_pattern' by 'test_pattern_mode'
 	 * because this is not DP-specific (which is probably somewhere in DP
 	 * encoder) */
 	enum controller_dp_test_pattern test_pattern,
 	enum dc_color_depth color_depth)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 	enum test_pattern_color_format bit_depth;
 	enum test_pattern_dyn_range dyn_range;
 	enum test_pattern_mode mode;
@@ -1023,35 +1053,30 @@ static void tgn10_set_test_pattern(
 	}
 }
 
-static void tgn10_get_crtc_scanoutpos(
-	struct timing_generator *tg,
+void optc1_get_crtc_scanoutpos(
+	struct timing_generator *optc,
 	uint32_t *v_blank_start,
 	uint32_t *v_blank_end,
 	uint32_t *h_position,
 	uint32_t *v_position)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 	struct crtc_position position;
 
 	REG_GET_2(OTG_V_BLANK_START_END,
 			OTG_V_BLANK_START, v_blank_start,
 			OTG_V_BLANK_END, v_blank_end);
 
-	tgn10_get_position(tg, &position);
+	optc1_get_position(optc, &position);
 
 	*h_position = position.horizontal_count;
 	*v_position = position.vertical_count;
 }
 
-
-
-static void tgn10_enable_stereo(struct timing_generator *tg,
+static void optc1_enable_stereo(struct timing_generator *optc,
 	const struct dc_crtc_timing *timing, struct crtc_stereo_flags *flags)
 {
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
-
-	uint32_t active_width = timing->h_addressable;
-	uint32_t space1_size = timing->v_total - timing->v_addressable;
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	if (flags) {
 		uint32_t stereo_en;
@@ -1079,29 +1104,23 @@ static void tgn10_enable_stereo(struct timing_generator *tg,
 				OTG_3D_STRUCTURE_STEREO_SEL_OVR, flags->FRAME_PACKED);
 
 	}
-
-	REG_UPDATE(OPPBUF_CONTROL,
-		OPPBUF_ACTIVE_WIDTH, active_width);
-
-	REG_UPDATE(OPPBUF_3D_PARAMETERS_0,
-		OPPBUF_3D_VACT_SPACE1_SIZE, space1_size);
 }
 
-static void tgn10_program_stereo(struct timing_generator *tg,
+void optc1_program_stereo(struct timing_generator *optc,
 	const struct dc_crtc_timing *timing, struct crtc_stereo_flags *flags)
 {
 	if (flags->PROGRAM_STEREO)
-		tgn10_enable_stereo(tg, timing, flags);
+		optc1_enable_stereo(optc, timing, flags);
 	else
-		tgn10_disable_stereo(tg);
+		optc1_disable_stereo(optc);
 }
 
 
-static bool tgn10_is_stereo_left_eye(struct timing_generator *tg)
+bool optc1_is_stereo_left_eye(struct timing_generator *optc)
 {
 	bool ret = false;
 	uint32_t left_eye = 0;
-	struct dcn10_timing_generator *tgn10 = DCN10TG_FROM_TG(tg);
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	REG_GET(OTG_STEREO_STATUS,
 		OTG_STEREO_CURRENT_EYE, &left_eye);
@@ -1113,7 +1132,7 @@ static bool tgn10_is_stereo_left_eye(struct timing_generator *tg)
 	return ret;
 }
 
-void tgn10_read_otg_state(struct dcn10_timing_generator *tgn10,
+void optc1_read_otg_state(struct optc *optc1,
 		struct dcn_otg_state *s)
 {
 	REG_GET(OTG_CONTROL,
@@ -1157,47 +1176,88 @@ void tgn10_read_otg_state(struct dcn10_timing_generator *tgn10,
 			OPTC_UNDERFLOW_OCCURRED_STATUS, &s->underflow_occurred_status);
 }
 
+static void optc1_clear_optc_underflow(struct timing_generator *optc)
+{
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+	REG_UPDATE(OPTC_INPUT_GLOBAL_CONTROL, OPTC_UNDERFLOW_CLEAR, 1);
+}
+
+static void optc1_tg_init(struct timing_generator *optc)
+{
+	optc1_set_blank_data_double_buffer(optc, true);
+	optc1_clear_optc_underflow(optc);
+}
+
+static bool optc1_is_tg_enabled(struct timing_generator *optc)
+{
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+	uint32_t otg_enabled = 0;
+
+	REG_GET(OTG_CONTROL, OTG_MASTER_EN, &otg_enabled);
+
+	return (otg_enabled != 0);
+
+}
+
+static bool optc1_is_optc_underflow_occurred(struct timing_generator *optc)
+{
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+	uint32_t underflow_occurred = 0;
+
+	REG_GET(OPTC_INPUT_GLOBAL_CONTROL,
+			OPTC_UNDERFLOW_OCCURRED_STATUS,
+			&underflow_occurred);
+
+	return (underflow_occurred == 1);
+}
 
 static const struct timing_generator_funcs dcn10_tg_funcs = {
-		.validate_timing = tgn10_validate_timing,
-		.program_timing = tgn10_program_timing,
-		.program_global_sync = tgn10_program_global_sync,
-		.enable_crtc = tgn10_enable_crtc,
-		.disable_crtc = tgn10_disable_crtc,
+		.validate_timing = optc1_validate_timing,
+		.program_timing = optc1_program_timing,
+		.program_global_sync = optc1_program_global_sync,
+		.enable_crtc = optc1_enable_crtc,
+		.disable_crtc = optc1_disable_crtc,
 		/* used by enable_timing_synchronization. Not need for FPGA */
-		.is_counter_moving = tgn10_is_counter_moving,
-		.get_position = tgn10_get_position,
-		.get_frame_count = tgn10_get_vblank_counter,
-		.get_scanoutpos = tgn10_get_crtc_scanoutpos,
-		.set_early_control = tgn10_set_early_control,
+		.is_counter_moving = optc1_is_counter_moving,
+		.get_position = optc1_get_position,
+		.get_frame_count = optc1_get_vblank_counter,
+		.get_scanoutpos = optc1_get_crtc_scanoutpos,
+		.set_early_control = optc1_set_early_control,
 		/* used by enable_timing_synchronization. Not need for FPGA */
-		.wait_for_state = tgn10_wait_for_state,
-		.set_blank = tgn10_set_blank,
-		.is_blanked = tgn10_is_blanked,
-		.set_blank_color = tgn10_program_blank_color,
-		.did_triggered_reset_occur = tgn10_did_triggered_reset_occur,
-		.enable_reset_trigger = tgn10_enable_reset_trigger,
-		.disable_reset_trigger = tgn10_disable_reset_trigger,
-		.lock = tgn10_lock,
-		.unlock = tgn10_unlock,
-		.enable_optc_clock = tgn10_enable_optc_clock,
-		.set_drr = tgn10_set_drr,
-		.set_static_screen_control = tgn10_set_static_screen_control,
-		.set_test_pattern = tgn10_set_test_pattern,
-		.program_stereo = tgn10_program_stereo,
-		.is_stereo_left_eye = tgn10_is_stereo_left_eye
+		.wait_for_state = optc1_wait_for_state,
+		.set_blank = optc1_set_blank,
+		.is_blanked = optc1_is_blanked,
+		.set_blank_color = optc1_program_blank_color,
+		.did_triggered_reset_occur = optc1_did_triggered_reset_occur,
+		.enable_reset_trigger = optc1_enable_reset_trigger,
+		.enable_crtc_reset = optc1_enable_crtc_reset,
+		.disable_reset_trigger = optc1_disable_reset_trigger,
+		.lock = optc1_lock,
+		.unlock = optc1_unlock,
+		.enable_optc_clock = optc1_enable_optc_clock,
+		.set_drr = optc1_set_drr,
+		.set_static_screen_control = optc1_set_static_screen_control,
+		.set_test_pattern = optc1_set_test_pattern,
+		.program_stereo = optc1_program_stereo,
+		.is_stereo_left_eye = optc1_is_stereo_left_eye,
+		.set_blank_data_double_buffer = optc1_set_blank_data_double_buffer,
+		.tg_init = optc1_tg_init,
+		.is_tg_enabled = optc1_is_tg_enabled,
+		.is_optc_underflow_occurred = optc1_is_optc_underflow_occurred,
+		.clear_optc_underflow = optc1_clear_optc_underflow,
 };
 
-void dcn10_timing_generator_init(struct dcn10_timing_generator *tgn10)
+void dcn10_timing_generator_init(struct optc *optc1)
 {
-	tgn10->base.funcs = &dcn10_tg_funcs;
+	optc1->base.funcs = &dcn10_tg_funcs;
 
-	tgn10->max_h_total = tgn10->tg_mask->OTG_H_TOTAL + 1;
-	tgn10->max_v_total = tgn10->tg_mask->OTG_V_TOTAL + 1;
+	optc1->max_h_total = optc1->tg_mask->OTG_H_TOTAL + 1;
+	optc1->max_v_total = optc1->tg_mask->OTG_V_TOTAL + 1;
 
-	tgn10->min_h_blank = 32;
-	tgn10->min_v_blank = 3;
-	tgn10->min_v_blank_interlace = 5;
-	tgn10->min_h_sync_width = 8;
-	tgn10->min_v_sync_width = 1;
+	optc1->min_h_blank = 32;
+	optc1->min_v_blank = 3;
+	optc1->min_v_blank_interlace = 5;
+	optc1->min_h_sync_width = 8;
+	optc1->min_v_sync_width = 1;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_timing_generator.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
index 7d4818d7aa31..a3c7c2012f05 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -29,7 +29,7 @@
 #include "timing_generator.h"
 
 #define DCN10TG_FROM_TG(tg)\
-	container_of(tg, struct dcn10_timing_generator, base)
+	container_of(tg, struct optc, base)
 
 #define TG_COMMON_REG_LIST_DCN(inst) \
 	SRI(OTG_VSTARTUP_PARAM, OTG, inst),\
@@ -70,9 +70,10 @@
 	SRI(OPTC_INPUT_CLOCK_CONTROL, ODM, inst),\
 	SRI(OPTC_DATA_SOURCE_SELECT, ODM, inst),\
 	SRI(OPTC_INPUT_GLOBAL_CONTROL, ODM, inst),\
-	SRI(OPPBUF_CONTROL, OPPBUF, inst),\
-	SRI(OPPBUF_3D_PARAMETERS_0, OPPBUF, inst),\
-	SRI(CONTROL, VTG, inst)
+	SRI(CONTROL, VTG, inst),\
+	SRI(OTG_VERT_SYNC_CONTROL, OTG, inst),\
+	SRI(OTG_MASTER_UPDATE_MODE, OTG, inst),\
+	SRI(OTG_GSL_CONTROL, OTG, inst)
 
 #define TG_COMMON_REG_LIST_DCN1_0(inst) \
 	TG_COMMON_REG_LIST_DCN(inst),\
@@ -81,7 +82,10 @@
 	SRI(OTG_TEST_PATTERN_COLOR, OTG, inst)
 
 
-struct dcn_tg_registers {
+struct dcn_optc_registers {
+	uint32_t OTG_VERT_SYNC_CONTROL;
+	uint32_t OTG_MASTER_UPDATE_MODE;
+	uint32_t OTG_GSL_CONTROL;
 	uint32_t OTG_VSTARTUP_PARAM;
 	uint32_t OTG_VUPDATE_PARAM;
 	uint32_t OTG_VREADY_PARAM;
@@ -123,9 +127,11 @@ struct dcn_tg_registers {
 	uint32_t OPTC_INPUT_CLOCK_CONTROL;
 	uint32_t OPTC_DATA_SOURCE_SELECT;
 	uint32_t OPTC_INPUT_GLOBAL_CONTROL;
-	uint32_t OPPBUF_CONTROL;
-	uint32_t OPPBUF_3D_PARAMETERS_0;
 	uint32_t CONTROL;
+	uint32_t OTG_GSL_WINDOW_X;
+	uint32_t OTG_GSL_WINDOW_Y;
+	uint32_t OTG_VUPDATE_KEEPOUT;
+	uint32_t OTG_DSC_START_POSITION;
 };
 
 #define TG_COMMON_MASK_SH_LIST_DCN(mask_sh)\
@@ -204,11 +210,21 @@ struct dcn_tg_registers {
 	SF(ODM0_OPTC_INPUT_CLOCK_CONTROL, OPTC_INPUT_CLK_ON, mask_sh),\
 	SF(ODM0_OPTC_INPUT_CLOCK_CONTROL, OPTC_INPUT_CLK_GATE_DIS, mask_sh),\
 	SF(ODM0_OPTC_INPUT_GLOBAL_CONTROL, OPTC_UNDERFLOW_OCCURRED_STATUS, mask_sh),\
-	SF(OPPBUF0_OPPBUF_CONTROL, OPPBUF_ACTIVE_WIDTH, mask_sh),\
-	SF(OPPBUF0_OPPBUF_3D_PARAMETERS_0, OPPBUF_3D_VACT_SPACE1_SIZE, mask_sh),\
+	SF(ODM0_OPTC_INPUT_GLOBAL_CONTROL, OPTC_UNDERFLOW_CLEAR, mask_sh),\
 	SF(VTG0_CONTROL, VTG0_ENABLE, mask_sh),\
 	SF(VTG0_CONTROL, VTG0_FP2, mask_sh),\
-	SF(VTG0_CONTROL, VTG0_VCOUNT_INIT, mask_sh)
+	SF(VTG0_CONTROL, VTG0_VCOUNT_INIT, mask_sh),\
+	SF(OTG0_OTG_VERT_SYNC_CONTROL, OTG_FORCE_VSYNC_NEXT_LINE_OCCURRED, mask_sh),\
+	SF(OTG0_OTG_VERT_SYNC_CONTROL, OTG_FORCE_VSYNC_NEXT_LINE_CLEAR, mask_sh),\
+	SF(OTG0_OTG_VERT_SYNC_CONTROL, OTG_AUTO_FORCE_VSYNC_MODE, mask_sh),\
+	SF(OTG0_OTG_MASTER_UPDATE_MODE, MASTER_UPDATE_INTERLACED_MODE, mask_sh),\
+	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL0_EN, mask_sh),\
+	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL1_EN, mask_sh),\
+	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL2_EN, mask_sh),\
+	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_MASTER_EN, mask_sh),\
+	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_FORCE_DELAY, mask_sh),\
+	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_CHECK_ALL_FIELDS, mask_sh)
+
 
 #define TG_COMMON_MASK_SH_LIST_DCN1_0(mask_sh)\
 	TG_COMMON_MASK_SH_LIST_DCN(mask_sh),\
@@ -313,26 +329,48 @@ struct dcn_tg_registers {
 	type OPTC_SRC_SEL;\
 	type OPTC_SEG0_SRC_SEL;\
 	type OPTC_UNDERFLOW_OCCURRED_STATUS;\
-	type OPPBUF_ACTIVE_WIDTH;\
-	type OPPBUF_3D_VACT_SPACE1_SIZE;\
+	type OPTC_UNDERFLOW_CLEAR;\
 	type VTG0_ENABLE;\
 	type VTG0_FP2;\
-	type VTG0_VCOUNT_INIT;
+	type VTG0_VCOUNT_INIT;\
+	type OTG_FORCE_VSYNC_NEXT_LINE_OCCURRED;\
+	type OTG_FORCE_VSYNC_NEXT_LINE_CLEAR;\
+	type OTG_AUTO_FORCE_VSYNC_MODE;\
+	type MASTER_UPDATE_INTERLACED_MODE;\
+	type OTG_GSL0_EN;\
+	type OTG_GSL1_EN;\
+	type OTG_GSL2_EN;\
+	type OTG_GSL_MASTER_EN;\
+	type OTG_GSL_FORCE_DELAY;\
+	type OTG_GSL_CHECK_ALL_FIELDS;\
+	type OTG_GSL_WINDOW_START_X;\
+	type OTG_GSL_WINDOW_END_X;\
+	type OTG_GSL_WINDOW_START_Y;\
+	type OTG_GSL_WINDOW_END_Y;\
+	type OTG_RANGE_TIMING_DBUF_UPDATE_MODE;\
+	type OTG_GSL_MASTER_MODE;\
+	type OTG_MASTER_UPDATE_LOCK_GSL_EN;\
+	type MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_START_OFFSET;\
+	type MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_END_OFFSET;\
+	type OTG_DSC_START_POSITION_X;\
+	type OTG_DSC_START_POSITION_LINE_NUM;\
+	type OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN;
+
 
-struct dcn_tg_shift {
+struct dcn_optc_shift {
 	TG_REG_FIELD_LIST(uint8_t)
 };
 
-struct dcn_tg_mask {
+struct dcn_optc_mask {
 	TG_REG_FIELD_LIST(uint32_t)
 };
 
-struct dcn10_timing_generator {
+struct optc {
 	struct timing_generator base;
 
-	const struct dcn_tg_registers *tg_regs;
-	const struct dcn_tg_shift *tg_shift;
-	const struct dcn_tg_mask *tg_mask;
+	const struct dcn_optc_registers *tg_regs;
+	const struct dcn_optc_shift *tg_shift;
+	const struct dcn_optc_mask *tg_mask;
 
 	enum controller_id controller_id;
 
@@ -347,7 +385,7 @@ struct dcn10_timing_generator {
 	uint32_t min_v_blank_interlace;
 };
 
-void dcn10_timing_generator_init(struct dcn10_timing_generator *tg);
+void dcn10_timing_generator_init(struct optc *optc);
 
 struct dcn_otg_state {
 	uint32_t v_blank_start;
@@ -368,7 +406,77 @@ struct dcn_otg_state {
 	uint32_t otg_enabled;
 };
 
-void tgn10_read_otg_state(struct dcn10_timing_generator *tgn10,
+void optc1_read_otg_state(struct optc *optc1,
 		struct dcn_otg_state *s);
 
+bool optc1_validate_timing(
+	struct timing_generator *optc,
+	const struct dc_crtc_timing *timing);
+
+void optc1_program_timing(
+	struct timing_generator *optc,
+	const struct dc_crtc_timing *dc_crtc_timing,
+	bool use_vbios);
+
+void optc1_program_global_sync(
+		struct timing_generator *optc);
+
+bool optc1_disable_crtc(struct timing_generator *optc);
+
+bool optc1_is_counter_moving(struct timing_generator *optc);
+
+void optc1_get_position(struct timing_generator *optc,
+		struct crtc_position *position);
+
+uint32_t optc1_get_vblank_counter(struct timing_generator *optc);
+
+void optc1_get_crtc_scanoutpos(
+	struct timing_generator *optc,
+	uint32_t *v_blank_start,
+	uint32_t *v_blank_end,
+	uint32_t *h_position,
+	uint32_t *v_position);
+
+void optc1_set_early_control(
+	struct timing_generator *optc,
+	uint32_t early_cntl);
+
+void optc1_wait_for_state(struct timing_generator *optc,
+		enum crtc_state state);
+
+void optc1_set_blank(struct timing_generator *optc,
+		bool enable_blanking);
+
+bool optc1_is_blanked(struct timing_generator *optc);
+
+void optc1_program_blank_color(
+		struct timing_generator *optc,
+		const struct tg_color *black_color);
+
+bool optc1_did_triggered_reset_occur(
+	struct timing_generator *optc);
+
+void optc1_enable_reset_trigger(struct timing_generator *optc, int source_tg_inst);
+
+void optc1_disable_reset_trigger(struct timing_generator *optc);
+
+void optc1_lock(struct timing_generator *optc);
+
+void optc1_unlock(struct timing_generator *optc);
+
+void optc1_enable_optc_clock(struct timing_generator *optc, bool enable);
+
+void optc1_set_drr(
+	struct timing_generator *optc,
+	const struct drr_params *params);
+
+void optc1_set_static_screen_control(
+	struct timing_generator *optc,
+	uint32_t value);
+
+void optc1_program_stereo(struct timing_generator *optc,
+	const struct dc_crtc_timing *timing, struct crtc_stereo_flags *flags);
+
+bool optc1_is_stereo_left_eye(struct timing_generator *optc);
+
 #endif /* __DC_TIMING_GENERATOR_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 4c4bd72d4e40..44825e2c9ebb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -34,7 +34,7 @@
 #include "dcn10/dcn10_mpc.h"
 #include "irq/dcn10/irq_service_dcn10.h"
 #include "dcn10/dcn10_dpp.h"
-#include "dcn10/dcn10_timing_generator.h"
+#include "dcn10_optc.h"
 #include "dcn10/dcn10_hw_sequencer.h"
 #include "dce110/dce110_hw_sequencer.h"
 #include "dcn10/dcn10_opp.h"
@@ -48,16 +48,17 @@
 #include "dce110/dce110_resource.h"
 #include "dce112/dce112_resource.h"
 #include "dcn10_hubp.h"
+#include "dcn10_hubbub.h"
 
-#include "vega10/soc15ip.h"
+#include "soc15ip.h"
 
-#include "raven1/DCN/dcn_1_0_offset.h"
-#include "raven1/DCN/dcn_1_0_sh_mask.h"
+#include "dcn/dcn_1_0_offset.h"
+#include "dcn/dcn_1_0_sh_mask.h"
 
-#include "raven1/NBIO/nbio_7_0_offset.h"
+#include "nbio/nbio_7_0_offset.h"
 
-#include "raven1/MMHUB/mmhub_9_1_offset.h"
-#include "raven1/MMHUB/mmhub_9_1_sh_mask.h"
+#include "mmhub/mmhub_9_1_offset.h"
+#include "mmhub/mmhub_9_1_sh_mask.h"
 
 #include "reg_helper.h"
 #include "dce/dce_abm.h"
@@ -347,18 +348,18 @@ static const struct dcn_mpc_mask mpc_mask = {
 #define tg_regs(id)\
 [id] = {TG_COMMON_REG_LIST_DCN1_0(id)}
 
-static const struct dcn_tg_registers tg_regs[] = {
+static const struct dcn_optc_registers tg_regs[] = {
 	tg_regs(0),
 	tg_regs(1),
 	tg_regs(2),
 	tg_regs(3),
 };
 
-static const struct dcn_tg_shift tg_shift = {
+static const struct dcn_optc_shift tg_shift = {
 	TG_COMMON_MASK_SH_LIST_DCN1_0(__SHIFT)
 };
 
-static const struct dcn_tg_mask tg_mask = {
+static const struct dcn_optc_mask tg_mask = {
 	TG_COMMON_MASK_SH_LIST_DCN1_0(_MASK)
 };
 
@@ -367,25 +368,38 @@ static const struct bios_registers bios_regs = {
 		NBIO_SR(BIOS_SCRATCH_6)
 };
 
-#define mi_regs(id)\
+#define hubp_regs(id)\
 [id] = {\
-	MI_REG_LIST_DCN10(id)\
+	HUBP_REG_LIST_DCN10(id)\
 }
 
 
-static const struct dcn_mi_registers mi_regs[] = {
-	mi_regs(0),
-	mi_regs(1),
-	mi_regs(2),
-	mi_regs(3),
+static const struct dcn_mi_registers hubp_regs[] = {
+	hubp_regs(0),
+	hubp_regs(1),
+	hubp_regs(2),
+	hubp_regs(3),
 };
 
-static const struct dcn_mi_shift mi_shift = {
-		MI_MASK_SH_LIST_DCN10(__SHIFT)
+static const struct dcn_mi_shift hubp_shift = {
+		HUBP_MASK_SH_LIST_DCN10(__SHIFT)
 };
 
-static const struct dcn_mi_mask mi_mask = {
-		MI_MASK_SH_LIST_DCN10(_MASK)
+static const struct dcn_mi_mask hubp_mask = {
+		HUBP_MASK_SH_LIST_DCN10(_MASK)
+};
+
+
+static const struct dcn_hubbub_registers hubbub_reg = {
+		HUBBUB_REG_LIST_DCN10(0)
+};
+
+static const struct dcn_hubbub_shift hubbub_shift = {
+		HUBBUB_MASK_SH_LIST_DCN10(__SHIFT)
+};
+
+static const struct dcn_hubbub_mask hubbub_mask = {
+		HUBBUB_MASK_SH_LIST_DCN10(_MASK)
 };
 
 #define clk_src_regs(index, pllid)\
@@ -519,12 +533,28 @@ static struct mpc *dcn10_mpc_create(struct dc_context *ctx)
 	return &mpc10->base;
 }
 
+static struct hubbub *dcn10_hubbub_create(struct dc_context *ctx)
+{
+	struct hubbub *hubbub = kzalloc(sizeof(struct hubbub),
+					  GFP_KERNEL);
+
+	if (!hubbub)
+		return NULL;
+
+	hubbub1_construct(hubbub, ctx,
+			&hubbub_reg,
+			&hubbub_shift,
+			&hubbub_mask);
+
+	return hubbub;
+}
+
 static struct timing_generator *dcn10_timing_generator_create(
 		struct dc_context *ctx,
 		uint32_t instance)
 {
-	struct dcn10_timing_generator *tgn10 =
-		kzalloc(sizeof(struct dcn10_timing_generator), GFP_KERNEL);
+	struct optc *tgn10 =
+		kzalloc(sizeof(struct optc), GFP_KERNEL);
 
 	if (!tgn10)
 		return NULL;
@@ -647,6 +677,8 @@ static struct dce_hwseq *dcn10_hwseq_create(
 		hws->regs = &hwseq_reg;
 		hws->shifts = &hwseq_shift;
 		hws->masks = &hwseq_mask;
+		hws->wa.DEGVIDCN10_253 = true;
+		hws->wa.false_optc_underflow = true;
 	}
 	return hws;
 }
@@ -700,6 +732,12 @@ static void destruct(struct dcn10_resource_pool *pool)
 		kfree(TO_DCN10_MPC(pool->base.mpc));
 		pool->base.mpc = NULL;
 	}
+
+	if (pool->base.hubbub != NULL) {
+		kfree(pool->base.hubbub);
+		pool->base.hubbub = NULL;
+	}
+
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		if (pool->base.opps[i] != NULL)
 			pool->base.opps[i]->funcs->opp_destroy(&pool->base.opps[i]);
@@ -768,7 +806,7 @@ static struct hubp *dcn10_hubp_create(
 		return NULL;
 
 	dcn10_hubp_construct(hubp1, ctx, inst,
-			     &mi_regs[inst], &mi_shift, &mi_mask);
+			     &hubp_regs[inst], &hubp_shift, &hubp_mask);
 	return &hubp1->base;
 }
 
@@ -912,11 +950,13 @@ static struct pipe_ctx *dcn10_acquire_idle_pipe_for_layer(
 	struct pipe_ctx *head_pipe = resource_get_head_pipe_for_stream(res_ctx, stream);
 	struct pipe_ctx *idle_pipe = find_idle_secondary_pipe(res_ctx, pool);
 
-	if (!head_pipe)
+	if (!head_pipe) {
 		ASSERT(0);
+		return NULL;
+	}
 
 	if (!idle_pipe)
-		return false;
+		return NULL;
 
 	idle_pipe->stream = head_pipe->stream;
 	idle_pipe->stream_res.tg = head_pipe->stream_res.tg;
@@ -1231,8 +1271,8 @@ static bool construct(
 	dc->caps.max_downscale_ratio = 200;
 	dc->caps.i2c_speed_in_khz = 100;
 	dc->caps.max_cursor_size = 256;
-
 	dc->caps.max_slave_planes = 1;
+	dc->caps.is_apu = true;
 
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
 		dc->debug = debug_defaults_drv;
@@ -1272,7 +1312,7 @@ static bool construct(
 		if (pool->base.clock_sources[i] == NULL) {
 			dm_error("DC: failed to create clock sources!\n");
 			BREAK_TO_DEBUGGER();
-			goto clock_source_create_fail;
+			goto fail;
 		}
 	}
 
@@ -1281,7 +1321,7 @@ static bool construct(
 		if (pool->base.display_clock == NULL) {
 			dm_error("DC: failed to create display clock!\n");
 			BREAK_TO_DEBUGGER();
-			goto disp_clk_create_fail;
+			goto fail;
 		}
 	}
 
@@ -1292,7 +1332,7 @@ static bool construct(
 	if (pool->base.dmcu == NULL) {
 		dm_error("DC: failed to create dmcu!\n");
 		BREAK_TO_DEBUGGER();
-		goto res_create_fail;
+		goto fail;
 	}
 
 	pool->base.abm = dce_abm_create(ctx,
@@ -1302,7 +1342,7 @@ static bool construct(
 	if (pool->base.abm == NULL) {
 		dm_error("DC: failed to create abm!\n");
 		BREAK_TO_DEBUGGER();
-		goto res_create_fail;
+		goto fail;
 	}
 
 	dml_init_instance(&dc->dml, DML_PROJECT_RAVEN1);
@@ -1342,13 +1382,11 @@ static bool construct(
 	}
 
 	{
-	#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 		struct irq_service_init_data init_data;
 		init_data.ctx = dc->ctx;
 		pool->base.irqs = dal_irq_service_dcn10_create(&init_data);
 		if (!pool->base.irqs)
-			goto irqs_create_fail;
-	#endif
+			goto fail;
 	}
 
 	/* index to valid pipe resource  */
@@ -1366,7 +1404,7 @@ static bool construct(
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create memory input!\n");
-			goto mi_create_fail;
+			goto fail;
 		}
 
 		pool->base.ipps[j] = dcn10_ipp_create(ctx, i);
@@ -1374,7 +1412,7 @@ static bool construct(
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create input pixel processor!\n");
-			goto ipp_create_fail;
+			goto fail;
 		}
 
 		pool->base.dpps[j] = dcn10_dpp_create(ctx, i);
@@ -1382,7 +1420,7 @@ static bool construct(
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create dpp!\n");
-			goto dpp_create_fail;
+			goto fail;
 		}
 
 		pool->base.opps[j] = dcn10_opp_create(ctx, i);
@@ -1390,7 +1428,7 @@ static bool construct(
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create output pixel processor!\n");
-			goto opp_create_fail;
+			goto fail;
 		}
 
 		pool->base.timing_generators[j] = dcn10_timing_generator_create(
@@ -1398,8 +1436,9 @@ static bool construct(
 		if (pool->base.timing_generators[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error("DC: failed to create tg!\n");
-			goto otg_create_fail;
+			goto fail;
 		}
+
 		/* check next valid pipe */
 		j++;
 	}
@@ -1417,13 +1456,20 @@ static bool construct(
 	if (pool->base.mpc == NULL) {
 		BREAK_TO_DEBUGGER();
 		dm_error("DC: failed to create mpc!\n");
-		goto mpc_create_fail;
+		goto fail;
+	}
+
+	pool->base.hubbub = dcn10_hubbub_create(ctx);
+	if (pool->base.hubbub == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create hubbub!\n");
+		goto fail;
 	}
 
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
 			(!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) ?
 			&res_create_funcs : &res_create_maximus_funcs)))
-			goto res_create_fail;
+			goto fail;
 
 	dcn10_hw_sequencer_construct(dc);
 	dc->caps.max_planes =  pool->base.pipe_count;
@@ -1432,16 +1478,7 @@ static bool construct(
 
 	return true;
 
-disp_clk_create_fail:
-mpc_create_fail:
-otg_create_fail:
-opp_create_fail:
-dpp_create_fail:
-ipp_create_fail:
-mi_create_fail:
-irqs_create_fail:
-res_create_fail:
-clock_source_create_fail:
+fail:
 
 	destruct(pool);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h
index d4917037ac42..225b7bfb09a9 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services.h
@@ -373,6 +373,13 @@ bool dm_dmcu_set_pipe(struct dc_context *ctx, unsigned int controller_id);
 unsigned long long dm_get_timestamp(struct dc_context *ctx);
 
 /*
+ * performance tracing
+ */
+void dm_perf_trace_timestamp(const char *func_name, unsigned int line);
+#define PERF_TRACE()	dm_perf_trace_timestamp(__func__, __LINE__)
+
+
+/*
  * Debug and verification hooks
  */
 bool dm_helpers_dc_conn_log(
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 87bab8e8139f..3488af2b5786 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'utils' sub-component of DAL.
 # It provides the general basic services required by other DAL
 # subcomponents.
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
index 4c31fa54af39..c109b2c34c8f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
@@ -35,35 +35,6 @@ static void set_soc_bounding_box(struct _vcs_dpi_soc_bounding_box_st *soc, enum
 		soc->writeback_latency_us = 12.0;
 		soc->ideal_dram_bw_after_urgent_percent = 80.0;
 		soc->max_request_size_bytes = 256;
-
-		soc->vmin.dcfclk_mhz = 300.0;
-		soc->vmin.dispclk_mhz = 608.0;
-		soc->vmin.dppclk_mhz = 435.0;
-		soc->vmin.dram_bw_per_chan_gbps = 12.8;
-		soc->vmin.phyclk_mhz = 540.0;
-		soc->vmin.socclk_mhz = 208.0;
-
-		soc->vmid.dcfclk_mhz = 600.0;
-		soc->vmid.dispclk_mhz = 661.0;
-		soc->vmid.dppclk_mhz = 661.0;
-		soc->vmid.dram_bw_per_chan_gbps = 12.8;
-		soc->vmid.phyclk_mhz = 540.0;
-		soc->vmid.socclk_mhz = 208.0;
-
-		soc->vnom.dcfclk_mhz = 600.0;
-		soc->vnom.dispclk_mhz = 661.0;
-		soc->vnom.dppclk_mhz = 661.0;
-		soc->vnom.dram_bw_per_chan_gbps = 38.4;
-		soc->vnom.phyclk_mhz = 810;
-		soc->vnom.socclk_mhz = 208.0;
-
-		soc->vmax.dcfclk_mhz = 600.0;
-		soc->vmax.dispclk_mhz = 1086.0;
-		soc->vmax.dppclk_mhz = 661.0;
-		soc->vmax.dram_bw_per_chan_gbps = 38.4;
-		soc->vmax.phyclk_mhz = 810.0;
-		soc->vmax.socclk_mhz = 208.0;
-
 		soc->downspread_percent = 0.5;
 		soc->dram_page_open_time_ns = 50.0;
 		soc->dram_rw_turnaround_time_ns = 17.5;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index baf182177736..aeebd8bee628 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -79,10 +79,6 @@ struct	_vcs_dpi_soc_bounding_box_st	{
 	double	writeback_latency_us;
 	double	ideal_dram_bw_after_urgent_percent;
 	unsigned int	max_request_size_bytes;
-	struct _vcs_dpi_voltage_scaling_st	vmin;
-	struct _vcs_dpi_voltage_scaling_st	vmid;
-	struct _vcs_dpi_voltage_scaling_st	vnom;
-	struct _vcs_dpi_voltage_scaling_st	vmax;
 	double	downspread_percent;
 	double	dram_page_open_time_ns;
 	double	dram_rw_turnaround_time_ns;
@@ -229,7 +225,7 @@ struct	_vcs_dpi_display_output_params_st	{
 	int	output_bpp;
 	int	dsc_enable;
 	int	wb_enable;
-	int	output_bpc;
+	int	opp_input_bpc;
 	int	output_type;
 	int	output_format;
 	int	output_standard;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
index ea661ee44674..260e113fcc02 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
@@ -28,6 +28,17 @@
 
 #include "dml_inline_defs.h"
 
+/*
+ * NOTE:
+ *   This file is gcc-parseable HW gospel, coming straight from HW engineers.
+ *
+ * It doesn't adhere to Linux kernel style and sometimes will do things in odd
+ * ways. Unless there is something clearly wrong with it the code should
+ * remain as-is as it provides us with a guarantee from HW that it is correct.
+ */
+
+#define BPP_INVALID 0
+#define BPP_BLENDED_PIPE 0xffffffff
 static const unsigned int NumberOfStates = DC__VOLTAGE_STATES;
 
 static void fetch_socbb_params(struct display_mode_lib *mode_lib);
@@ -587,7 +598,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 		mode_lib->vba.NumberOfDSCSlices[mode_lib->vba.NumberOfActivePlanes] =
 				dout->dsc_slices;
 		mode_lib->vba.DSCInputBitPerComponent[mode_lib->vba.NumberOfActivePlanes] =
-				dout->output_bpc == 0 ? 12 : dout->output_bpc;
+				dout->opp_input_bpc == 0 ? 12 : dout->opp_input_bpc;
 		mode_lib->vba.WritebackEnable[mode_lib->vba.NumberOfActivePlanes] = dout->wb_enable;
 		mode_lib->vba.WritebackSourceHeight[mode_lib->vba.NumberOfActivePlanes] =
 				dout->wb.wb_src_height;
@@ -3928,7 +3939,7 @@ static unsigned int TruncToValidBPP(
 			else if (DecimalBPP >= 12)
 				return 12;
 			else
-				return 0;
+				return BPP_INVALID;
 		} else if (Format == dm_444) {
 			if (DecimalBPP >= 36)
 				return 36;
@@ -3937,7 +3948,7 @@ static unsigned int TruncToValidBPP(
 			else if (DecimalBPP >= 24)
 				return 24;
 			else
-				return 0;
+				return BPP_INVALID;
 		} else {
 			if (DecimalBPP / 1.5 >= 24)
 				return 24;
@@ -3946,27 +3957,27 @@ static unsigned int TruncToValidBPP(
 			else if (DecimalBPP / 1.5 >= 16)
 				return 16;
 			else
-				return 0;
+				return BPP_INVALID;
 		}
 	} else {
 		if (DSCEnabled) {
 			if (Format == dm_420) {
 				if (DecimalBPP < 6)
-					return 0;
+					return BPP_INVALID;
 				else if (DecimalBPP >= 1.5 * DSCInputBitPerComponent - 1 / 16)
 					return 1.5 * DSCInputBitPerComponent - 1 / 16;
 				else
 					return dml_floor(16 * DecimalBPP, 1) / 16;
 			} else if (Format == dm_n422) {
 				if (DecimalBPP < 7)
-					return 0;
+					return BPP_INVALID;
 				else if (DecimalBPP >= 2 * DSCInputBitPerComponent - 1 / 16)
 					return 2 * DSCInputBitPerComponent - 1 / 16;
 				else
 					return dml_floor(16 * DecimalBPP, 1) / 16;
 			} else {
 				if (DecimalBPP < 8)
-					return 0;
+					return BPP_INVALID;
 				else if (DecimalBPP >= 3 * DSCInputBitPerComponent - 1 / 16)
 					return 3 * DSCInputBitPerComponent - 1 / 16;
 				else
@@ -3980,7 +3991,7 @@ static unsigned int TruncToValidBPP(
 			else if (DecimalBPP >= 12)
 				return 12;
 			else
-				return 0;
+				return BPP_INVALID;
 		} else if (Format == dm_s422 || Format == dm_n422) {
 			if (DecimalBPP >= 24)
 				return 24;
@@ -3989,7 +4000,7 @@ static unsigned int TruncToValidBPP(
 			else if (DecimalBPP >= 16)
 				return 16;
 			else
-				return 0;
+				return BPP_INVALID;
 		} else {
 			if (DecimalBPP >= 36)
 				return 36;
@@ -3998,7 +4009,7 @@ static unsigned int TruncToValidBPP(
 			else if (DecimalBPP >= 24)
 				return 24;
 			else
-				return 0;
+				return BPP_INVALID;
 		}
 	}
 }
@@ -4922,11 +4933,7 @@ static void ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 		mode_lib->vba.ViewportSizeSupport[i] = true;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 			if (mode_lib->vba.ODMCombineEnablePerState[i][k] == true) {
-				if (dml_min(
-						mode_lib->vba.SwathWidthYSingleDPP[k],
-						dml_round(
-								mode_lib->vba.HActive[k] / 2.0
-										* mode_lib->vba.HRatio[k]))
+				if (dml_min(mode_lib->vba.SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k]))
 						> mode_lib->vba.MaximumSwathWidth[k]) {
 					mode_lib->vba.ViewportSizeSupport[i] = false;
 				}
@@ -4980,12 +4987,8 @@ static void ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 					mode_lib->vba.RequiresDSC[i][k] = 0;
 					mode_lib->vba.RequiresFEC[i][k] = 0;
 					mode_lib->vba.OutputBppPerState[i][k] =
-							TruncToValidBPP(
-									dml_min(
-											600.0,
-											mode_lib->vba.PHYCLKPerState[i])
-											/ mode_lib->vba.PixelClockBackEnd[k]
-											* 24,
+							TruncToValidBPP(dml_min(600.0, mode_lib->vba.PHYCLKPerState[i])
+										/ mode_lib->vba.PixelClockBackEnd[k] * 24,
 									false,
 									mode_lib->vba.Output[k],
 									mode_lib->vba.OutputFormat[k],
@@ -5000,30 +5003,16 @@ static void ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 					}
 					if (mode_lib->vba.PHYCLKPerState[i] >= 270.0) {
 						mode_lib->vba.Outbpp =
-								TruncToValidBPP(
-										(1.0
-												- mode_lib->vba.Downspreading
-														/ 100.0)
-												* 270.0
-												* mode_lib->vba.OutputLinkDPLanes[k]
-												/ mode_lib->vba.PixelClockBackEnd[k]
-												* 8.0,
+								TruncToValidBPP((1.0 - mode_lib->vba.Downspreading / 100.0) * 270.0
+											* mode_lib->vba.OutputLinkDPLanes[k] / mode_lib->vba.PixelClockBackEnd[k] * 8.0,
 										false,
 										mode_lib->vba.Output[k],
 										mode_lib->vba.OutputFormat[k],
 										mode_lib->vba.DSCInputBitPerComponent[k]);
 						mode_lib->vba.OutbppDSC =
-								TruncToValidBPP(
-										(1.0
-												- mode_lib->vba.Downspreading
-														/ 100.0)
-												* (1.0
-														- mode_lib->vba.EffectiveFECOverhead
-																/ 100.0)
-												* 270.0
-												* mode_lib->vba.OutputLinkDPLanes[k]
-												/ mode_lib->vba.PixelClockBackEnd[k]
-												* 8.0,
+								TruncToValidBPP((1.0 - mode_lib->vba.Downspreading / 100.0)
+											* (1.0 - mode_lib->vba.EffectiveFECOverhead / 100.0) * 270.0
+											* mode_lib->vba.OutputLinkDPLanes[k] / mode_lib->vba.PixelClockBackEnd[k] * 8.0,
 										true,
 										mode_lib->vba.Output[k],
 										mode_lib->vba.OutputFormat[k],
@@ -5046,32 +5035,18 @@ static void ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 						mode_lib->vba.OutputBppPerState[i][k] =
 								mode_lib->vba.Outbpp;
 					}
-					if (mode_lib->vba.Outbpp == 0) {
+					if (mode_lib->vba.Outbpp == BPP_INVALID) {
 						mode_lib->vba.Outbpp =
-								TruncToValidBPP(
-										(1.0
-												- mode_lib->vba.Downspreading
-														/ 100.0)
-												* 540.0
-												* mode_lib->vba.OutputLinkDPLanes[k]
-												/ mode_lib->vba.PixelClockBackEnd[k]
-												* 8.0,
+								TruncToValidBPP((1.0 - mode_lib->vba.Downspreading / 100.0) * 540.0
+											* mode_lib->vba.OutputLinkDPLanes[k] / mode_lib->vba.PixelClockBackEnd[k] * 8.0,
 										false,
 										mode_lib->vba.Output[k],
 										mode_lib->vba.OutputFormat[k],
 										mode_lib->vba.DSCInputBitPerComponent[k]);
 						mode_lib->vba.OutbppDSC =
-								TruncToValidBPP(
-										(1.0
-												- mode_lib->vba.Downspreading
-														/ 100.0)
-												* (1.0
-														- mode_lib->vba.EffectiveFECOverhead
-																/ 100.0)
-												* 540.0
-												* mode_lib->vba.OutputLinkDPLanes[k]
-												/ mode_lib->vba.PixelClockBackEnd[k]
-												* 8.0,
+								TruncToValidBPP((1.0 - mode_lib->vba.Downspreading / 100.0)
+											* (1.0 - mode_lib->vba.EffectiveFECOverhead / 100.0) * 540.0
+											* mode_lib->vba.OutputLinkDPLanes[k] / mode_lib->vba.PixelClockBackEnd[k] * 8.0,
 										true,
 										mode_lib->vba.Output[k],
 										mode_lib->vba.OutputFormat[k],
@@ -5094,40 +5069,26 @@ static void ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 						mode_lib->vba.OutputBppPerState[i][k] =
 								mode_lib->vba.Outbpp;
 					}
-					if (mode_lib->vba.Outbpp == 0
+					if (mode_lib->vba.Outbpp == BPP_INVALID
 							&& mode_lib->vba.PHYCLKPerState[i]
 									>= 810.0) {
 						mode_lib->vba.Outbpp =
-								TruncToValidBPP(
-										(1.0
-												- mode_lib->vba.Downspreading
-														/ 100.0)
-												* 810.0
-												* mode_lib->vba.OutputLinkDPLanes[k]
-												/ mode_lib->vba.PixelClockBackEnd[k]
-												* 8.0,
+								TruncToValidBPP((1.0 - mode_lib->vba.Downspreading / 100.0) * 810.0
+											* mode_lib->vba.OutputLinkDPLanes[k] / mode_lib->vba.PixelClockBackEnd[k] * 8.0,
 										false,
 										mode_lib->vba.Output[k],
 										mode_lib->vba.OutputFormat[k],
 										mode_lib->vba.DSCInputBitPerComponent[k]);
 						mode_lib->vba.OutbppDSC =
-								TruncToValidBPP(
-										(1.0
-												- mode_lib->vba.Downspreading
-														/ 100.0)
-												* (1.0
-														- mode_lib->vba.EffectiveFECOverhead
-																/ 100.0)
-												* 810.0
-												* mode_lib->vba.OutputLinkDPLanes[k]
-												/ mode_lib->vba.PixelClockBackEnd[k]
-												* 8.0,
+								TruncToValidBPP((1.0 - mode_lib->vba.Downspreading / 100.0)
+											* (1.0 - mode_lib->vba.EffectiveFECOverhead / 100.0) * 810.0
+											* mode_lib->vba.OutputLinkDPLanes[k] / mode_lib->vba.PixelClockBackEnd[k] * 8.0,
 										true,
 										mode_lib->vba.Output[k],
 										mode_lib->vba.OutputFormat[k],
 										mode_lib->vba.DSCInputBitPerComponent[k]);
 						if (mode_lib->vba.DSCEnabled[k] == true
-								|| mode_lib->vba.Outbpp == 0) {
+								|| mode_lib->vba.Outbpp == BPP_INVALID) {
 							mode_lib->vba.RequiresDSC[i][k] = true;
 							if (mode_lib->vba.Output[k] == dm_dp) {
 								mode_lib->vba.RequiresFEC[i][k] =
@@ -5147,14 +5108,14 @@ static void ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 					}
 				}
 			} else {
-				mode_lib->vba.OutputBppPerState[i][k] = 0;
+				mode_lib->vba.OutputBppPerState[i][k] = BPP_BLENDED_PIPE;
 			}
 		}
 	}
 	for (i = 0; i <= DC__VOLTAGE_STATES; i++) {
 		mode_lib->vba.DIOSupport[i] = true;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-			if (mode_lib->vba.OutputBppPerState[i][k] == 0
+			if (mode_lib->vba.OutputBppPerState[i][k] == BPP_INVALID
 					|| (mode_lib->vba.OutputFormat[k] == dm_420
 							&& mode_lib->vba.ProgressiveToInterlaceUnitInOPP
 									== true)) {
@@ -5243,8 +5204,8 @@ static void ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 			} else {
 				mode_lib->vba.slices = 1.0;
 			}
-			if (mode_lib->vba.OutputBppPerState[i][k] == 0
-					|| mode_lib->vba.OutputBppPerState[i][k] == 0) {
+			if (mode_lib->vba.OutputBppPerState[i][k] == BPP_BLENDED_PIPE
+					|| mode_lib->vba.OutputBppPerState[i][k] == BPP_INVALID) {
 				mode_lib->vba.bpp = 0.0;
 			} else {
 				mode_lib->vba.bpp = mode_lib->vba.OutputBppPerState[i][k];
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_calc.c b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_calc.c
index 8ba962df42e6..325dd2b757d6 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_calc.c
@@ -27,6 +27,15 @@
 #include "display_mode_vba.h"
 #include "display_rq_dlg_calc.h"
 
+/*
+ * NOTE:
+ *   This file is gcc-parseable HW gospel, coming straight from HW engineers.
+ *
+ * It doesn't adhere to Linux kernel style and sometimes will do things in odd
+ * ways. Unless there is something clearly wrong with it the code should
+ * remain as-is as it provides us with a guarantee from HW that it is correct.
+ */
+
 static void calculate_ttu_cursor(struct display_mode_lib *mode_lib,
 		double *refcyc_per_req_delivery_pre_cur,
 		double *refcyc_per_req_delivery_cur,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
index 1e4b1e383401..c2037daa8e66 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
@@ -28,6 +28,15 @@
 
 #include "dml_inline_defs.h"
 
+/*
+ * NOTE:
+ *   This file is gcc-parseable HW gospel, coming straight from HW engineers.
+ *
+ * It doesn't adhere to Linux kernel style and sometimes will do things in odd
+ * ways. Unless there is something clearly wrong with it the code should
+ * remain as-is as it provides us with a guarantee from HW that it is correct.
+ */
+
 static unsigned int get_bytes_per_element(enum source_format_class source_format, bool is_chroma)
 {
 	unsigned int ret_val = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c b/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c
index bc7d8c707221..324239c77958 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c
@@ -27,6 +27,16 @@
 #include "dc_features.h"
 
 #include "dml_inline_defs.h"
+
+/*
+ * NOTE:
+ *   This file is gcc-parseable HW gospel, coming straight from HW engineers.
+ *
+ * It doesn't adhere to Linux kernel style and sometimes will do things in odd
+ * ways. Unless there is something clearly wrong with it the code should
+ * remain as-is as it provides us with a guarantee from HW that it is correct.
+ */
+
 void dml_socbb_set_latencies(soc_bounding_box_st *to_box, soc_bounding_box_st *from_box)
 {
 	to_box->dram_clock_change_latency_us = from_box->dram_clock_change_latency_us;
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/Makefile b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
index 70d01a9e9676..562ee189d780 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'gpio' sub-component of DAL.
 # It provides the control and status of HW GPIO pins.
 
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c b/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c
index 4ced9a7d63dd..0c2314efb47e 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c
@@ -34,9 +34,9 @@
 
 #include "hw_factory_dce120.h"
 
-#include "vega10/DC/dce_12_0_offset.h"
-#include "vega10/DC/dce_12_0_sh_mask.h"
-#include "vega10/soc15ip.h"
+#include "dce/dce_12_0_offset.h"
+#include "dce/dce_12_0_sh_mask.h"
+#include "soc15ip.h"
 
 #define block HPD
 #define reg_num 0
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_translate_dce120.c b/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_translate_dce120.c
index af3843a69652..a225b02cc779 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_translate_dce120.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_translate_dce120.c
@@ -33,9 +33,9 @@
 #include "include/gpio_types.h"
 #include "../hw_translate.h"
 
-#include "vega10/DC/dce_12_0_offset.h"
-#include "vega10/DC/dce_12_0_sh_mask.h"
-#include "vega10/soc15ip.h"
+#include "dce/dce_12_0_offset.h"
+#include "dce/dce_12_0_sh_mask.h"
+#include "soc15ip.h"
 
 /* begin *********************
  * macros to expend register list macro defined in HW object header file */
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c
index 409763c70ce5..5235f69f0602 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c
@@ -34,9 +34,9 @@
 
 #include "hw_factory_dcn10.h"
 
-#include "raven1/DCN/dcn_1_0_offset.h"
-#include "raven1/DCN/dcn_1_0_sh_mask.h"
-#include "vega10/soc15ip.h"
+#include "dcn/dcn_1_0_offset.h"
+#include "dcn/dcn_1_0_sh_mask.h"
+#include "soc15ip.h"
 
 #define block HPD
 #define reg_num 0
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_translate_dcn10.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_translate_dcn10.c
index 64a6915b846b..347864810d01 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_translate_dcn10.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_translate_dcn10.c
@@ -33,9 +33,9 @@
 #include "include/gpio_types.h"
 #include "../hw_translate.h"
 
-#include "raven1/DCN/dcn_1_0_offset.h"
-#include "raven1/DCN/dcn_1_0_sh_mask.h"
-#include "vega10/soc15ip.h"
+#include "dcn/dcn_1_0_offset.h"
+#include "dcn/dcn_1_0_sh_mask.h"
+#include "soc15ip.h"
 
 /* begin *********************
  * macros to expend register list macro defined in HW object header file */
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/Makefile b/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
index 55603400acd9..352885cb4d07 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'i2c' sub-component of DAL.
 # It provides the control and status of HW i2c engine of the adapter.
 
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
index 668981a4c285..a401636bf3f8 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
@@ -36,9 +36,9 @@
 #include "../dce110/aux_engine_dce110.h"
 #include "../dce110/i2caux_dce110.h"
 
-#include "vega10/DC/dce_12_0_offset.h"
-#include "vega10/DC/dce_12_0_sh_mask.h"
-#include "vega10/soc15ip.h"
+#include "dce/dce_12_0_offset.h"
+#include "dce/dce_12_0_sh_mask.h"
+#include "soc15ip.h"
 
 /* begin *********************
  * macros to expend register list macro defined in HW object header file */
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c b/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
index 13b807d8aff8..bed7cc3e77de 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
@@ -36,9 +36,9 @@
 #include "../dce110/i2c_hw_engine_dce110.h"
 #include "../dce110/i2caux_dce110.h"
 
-#include "raven1/DCN/dcn_1_0_offset.h"
-#include "raven1/DCN/dcn_1_0_sh_mask.h"
-#include "vega10/soc15ip.h"
+#include "dcn/dcn_1_0_offset.h"
+#include "dcn/dcn_1_0_sh_mask.h"
+#include "soc15ip.h"
 
 /* begin *********************
  * macros to expend register list macro defined in HW object header file */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_status.h b/drivers/gpu/drm/amd/display/dc/inc/core_status.h
index 01df85641684..94fc31080fda 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_status.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_status.h
@@ -38,7 +38,7 @@ enum dc_status {
 	DC_FAIL_DETACH_SURFACES = 8,
 	DC_FAIL_SURFACE_VALIDATE = 9,
 	DC_NO_DP_LINK_BANDWIDTH = 10,
-	DC_EXCEED_DONGLE_MAX_CLK = 11,
+	DC_EXCEED_DONGLE_CAP = 11,
 	DC_SURFACE_PIXEL_FORMAT_UNSUPPORTED = 12,
 	DC_FAIL_BANDWIDTH_VALIDATE = 13, /* BW and Watermark validation */
 	DC_FAIL_SCALING = 14,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index b69f321e2ab6..d6971054ec07 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -139,6 +139,7 @@ struct resource_pool {
 	struct timing_generator *timing_generators[MAX_PIPES];
 	struct stream_encoder *stream_enc[MAX_PIPES * 2];
 
+	struct hubbub *hubbub;
 	struct mpc *mpc;
 	struct pp_smu_funcs_rv *pp_smu;
 	struct pp_smu_display_requirement_rv pp_smu_req;
@@ -211,7 +212,6 @@ struct pipe_ctx {
 	struct _vcs_dpi_display_rq_regs_st rq_regs;
 	struct _vcs_dpi_display_pipe_dest_params_st pipe_dlg_param;
 #endif
-	struct dwbc *dwbc;
 };
 
 struct resource_context {
@@ -240,6 +240,7 @@ struct dce_bw_output {
 
 struct dcn_bw_clocks {
 	int dispclk_khz;
+	int dppclk_khz;
 	bool dppclk_div;
 	int dcfclk_khz;
 	int dcfclk_deep_sleep_khz;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
index 1e231f6de732..132d18d4b293 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
@@ -349,10 +349,10 @@ struct dcn_bw_internal_vars {
 	float dst_x_after_scaler;
 	float dst_y_after_scaler;
 	float time_calc;
-	float v_update_offset[number_of_planes_minus_one + 1];
+	float v_update_offset[number_of_planes_minus_one + 1][2];
 	float total_repeater_delay;
-	float v_update_width[number_of_planes_minus_one + 1];
-	float v_ready_offset[number_of_planes_minus_one + 1];
+	float v_update_width[number_of_planes_minus_one + 1][2];
+	float v_ready_offset[number_of_planes_minus_one + 1][2];
 	float time_setup;
 	float extra_latency;
 	float maximum_vstartup;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/abm.h b/drivers/gpu/drm/amd/display/dc/inc/hw/abm.h
index c93b9b9a817c..a83a48494613 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/abm.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/abm.h
@@ -27,9 +27,19 @@
 
 #include "dm_services_types.h"
 
+struct abm_backlight_registers {
+	unsigned int BL_PWM_CNTL;
+	unsigned int BL_PWM_CNTL2;
+	unsigned int BL_PWM_PERIOD_CNTL;
+	unsigned int LVTMA_PWRSEQ_REF_DIV_BL_PWM_REF_DIV;
+};
+
 struct abm {
 	struct dc_context *ctx;
 	const struct abm_funcs *funcs;
+
+	/* registers setting needs to be saved and restored at InitBacklight */
+	struct abm_backlight_registers stored_backlight_registers;
 };
 
 struct abm_funcs {
@@ -40,9 +50,9 @@ struct abm_funcs {
 	bool (*set_backlight_level)(struct abm *abm,
 			unsigned int backlight_level,
 			unsigned int frame_ramp,
-			unsigned int controller_id);
+			unsigned int controller_id,
+			bool use_smooth_brightness);
 	unsigned int (*get_current_backlight_8_bit)(struct abm *abm);
-	bool (*is_dmcu_initialized)(struct abm *abm);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
index 0574c29cc4a8..ce206355461b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
@@ -27,12 +27,29 @@
 
 #include "dm_services_types.h"
 
+enum dmcu_state {
+	DMCU_NOT_INITIALIZED = 0,
+	DMCU_RUNNING = 1
+};
+
+struct dmcu_version {
+	unsigned int day;
+	unsigned int month;
+	unsigned int year;
+	unsigned int interface_version;
+};
+
 struct dmcu {
 	struct dc_context *ctx;
 	const struct dmcu_funcs *funcs;
+
+	enum dmcu_state dmcu_state;
+	struct dmcu_version dmcu_version;
+	unsigned int cached_wait_loop_number;
 };
 
 struct dmcu_funcs {
+	bool (*dmcu_init)(struct dmcu *dmcu);
 	bool (*load_iram)(struct dmcu *dmcu,
 			unsigned int start_offset,
 			const char *src,
@@ -44,7 +61,9 @@ struct dmcu_funcs {
 	void (*get_psr_state)(struct dmcu *dmcu, uint32_t *psr_state);
 	void (*set_psr_wait_loop)(struct dmcu *dmcu,
 			unsigned int wait_loop_number);
-	void (*get_psr_wait_loop)(unsigned int *psr_wait_loop_number);
+	void (*get_psr_wait_loop)(struct dmcu *dmcu,
+			unsigned int *psr_wait_loop_number);
+	bool (*is_dmcu_initialized)(struct dmcu *dmcu);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 83a68460edcd..25edbde6163e 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -62,63 +62,67 @@ struct dpp_funcs {
 			struct dpp *dpp,
 			const struct dpp_grph_csc_adjustment *adjust);
 
-	void (*opp_set_csc_default)(
+	void (*dpp_set_csc_default)(
 		struct dpp *dpp,
-		const struct default_adjustment *default_adjust);
+		enum dc_color_space colorspace);
 
-	void (*opp_set_csc_adjustment)(
+	void (*dpp_set_csc_adjustment)(
 		struct dpp *dpp,
-		const struct out_csc_color_matrix *tbl_entry);
+		const uint16_t *regval);
 
-	void (*opp_power_on_regamma_lut)(
+	void (*dpp_power_on_regamma_lut)(
 		struct dpp *dpp,
 		bool power_on);
 
-	void (*opp_program_regamma_lut)(
+	void (*dpp_program_regamma_lut)(
 			struct dpp *dpp,
 			const struct pwl_result_data *rgb,
 			uint32_t num);
 
-	void (*opp_configure_regamma_lut)(
+	void (*dpp_configure_regamma_lut)(
 			struct dpp *dpp,
 			bool is_ram_a);
 
-	void (*opp_program_regamma_lutb_settings)(
+	void (*dpp_program_regamma_lutb_settings)(
 			struct dpp *dpp,
 			const struct pwl_params *params);
 
-	void (*opp_program_regamma_luta_settings)(
+	void (*dpp_program_regamma_luta_settings)(
 			struct dpp *dpp,
 			const struct pwl_params *params);
 
-	void (*opp_program_regamma_pwl)(
-		struct dpp *dpp, const struct pwl_params *params);
+	void (*dpp_program_regamma_pwl)(
+		struct dpp *dpp,
+		const struct pwl_params *params,
+		enum opp_regamma mode);
 
-	void (*opp_set_regamma_mode)(
-			struct dpp *dpp_base,
-			enum opp_regamma mode);
+	void (*dpp_program_bias_and_scale)(
+			struct dpp *dpp,
+			struct dc_bias_and_scale *params);
 
-	void (*ipp_set_degamma)(
+	void (*dpp_set_degamma)(
 			struct dpp *dpp_base,
 			enum ipp_degamma_mode mode);
 
-	void (*ipp_program_input_lut)(
+	void (*dpp_program_input_lut)(
 			struct dpp *dpp_base,
 			const struct dc_gamma *gamma);
 
-	void (*ipp_program_degamma_pwl)(struct dpp *dpp_base,
+	void (*dpp_program_degamma_pwl)(struct dpp *dpp_base,
 									 const struct pwl_params *params);
 
-	void (*ipp_setup)(
+	void (*dpp_setup)(
 			struct dpp *dpp_base,
-			enum surface_pixel_format input_format,
-			enum expansion_mode mode);
+			enum surface_pixel_format format,
+			enum expansion_mode mode,
+			struct csc_transform input_csc_color_matrix,
+			enum dc_color_space input_color_space);
 
-	void (*ipp_full_bypass)(struct dpp *dpp_base);
+	void (*dpp_full_bypass)(struct dpp *dpp_base);
 
 	void (*set_cursor_attributes)(
 			struct dpp *dpp_base,
-			const struct dc_cursor_attributes *attr);
+			enum dc_cursor_color_format color_format);
 
 	void (*set_cursor_position)(
 			struct dpp *dpp_base,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 0d186be24cf4..b7c7e70022e4 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -28,15 +28,32 @@
 
 #include "mem_input.h"
 
+
+enum cursor_pitch {
+	CURSOR_PITCH_64_PIXELS = 0,
+	CURSOR_PITCH_128_PIXELS,
+	CURSOR_PITCH_256_PIXELS
+};
+
+enum cursor_lines_per_chunk {
+	CURSOR_LINE_PER_CHUNK_2 = 1,
+	CURSOR_LINE_PER_CHUNK_4,
+	CURSOR_LINE_PER_CHUNK_8,
+	CURSOR_LINE_PER_CHUNK_16
+};
+
 struct hubp {
 	struct hubp_funcs *funcs;
 	struct dc_context *ctx;
 	struct dc_plane_address request_address;
 	struct dc_plane_address current_address;
 	int inst;
+
+	/* run time states */
 	int opp_id;
 	int mpcc_id;
 	struct dc_cursor_attributes curs_attr;
+	bool power_gated;
 };
 
 
@@ -100,6 +117,8 @@ struct hubp_funcs {
 			const struct dc_cursor_position *pos,
 			const struct dc_cursor_mi_param *param);
 
+	void (*hubp_disconnect)(struct hubp *hubp);
+
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
index 9602f261b614..e3f0b4056318 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
@@ -73,7 +73,7 @@ struct pwl_result_data {
 
 struct pwl_params {
 	struct gamma_curve arr_curve_points[34];
-	struct curve_points arr_points[3];
+	struct curve_points arr_points[2];
 	struct pwl_result_data rgb_resulted[256 + 3];
 	uint32_t hw_points_num;
 };
@@ -126,11 +126,13 @@ struct default_adjustment {
 	bool force_hw_default;
 };
 
+
 struct out_csc_color_matrix {
 	enum dc_color_space color_space;
 	uint16_t regval[12];
 };
 
+
 enum opp_regamma {
 	OPP_REGAMMA_BYPASS = 0,
 	OPP_REGAMMA_SRGB,
@@ -138,4 +140,55 @@ enum opp_regamma {
 	OPP_REGAMMA_USER
 };
 
+struct csc_transform {
+	uint16_t matrix[12];
+	bool enable_adjustment;
+};
+
+struct dc_bias_and_scale {
+	uint16_t scale_red;
+	uint16_t bias_red;
+	uint16_t scale_green;
+	uint16_t bias_green;
+	uint16_t scale_blue;
+	uint16_t bias_blue;
+};
+
+enum test_pattern_dyn_range {
+	TEST_PATTERN_DYN_RANGE_VESA = 0,
+	TEST_PATTERN_DYN_RANGE_CEA
+};
+
+enum test_pattern_mode {
+	TEST_PATTERN_MODE_COLORSQUARES_RGB = 0,
+	TEST_PATTERN_MODE_COLORSQUARES_YCBCR601,
+	TEST_PATTERN_MODE_COLORSQUARES_YCBCR709,
+	TEST_PATTERN_MODE_VERTICALBARS,
+	TEST_PATTERN_MODE_HORIZONTALBARS,
+	TEST_PATTERN_MODE_SINGLERAMP_RGB,
+	TEST_PATTERN_MODE_DUALRAMP_RGB
+};
+
+enum test_pattern_color_format {
+	TEST_PATTERN_COLOR_FORMAT_BPC_6 = 0,
+	TEST_PATTERN_COLOR_FORMAT_BPC_8,
+	TEST_PATTERN_COLOR_FORMAT_BPC_10,
+	TEST_PATTERN_COLOR_FORMAT_BPC_12
+};
+
+enum controller_dp_test_pattern {
+	CONTROLLER_DP_TEST_PATTERN_D102 = 0,
+	CONTROLLER_DP_TEST_PATTERN_SYMBOLERROR,
+	CONTROLLER_DP_TEST_PATTERN_PRBS7,
+	CONTROLLER_DP_TEST_PATTERN_COLORSQUARES,
+	CONTROLLER_DP_TEST_PATTERN_VERTICALBARS,
+	CONTROLLER_DP_TEST_PATTERN_HORIZONTALBARS,
+	CONTROLLER_DP_TEST_PATTERN_COLORRAMP,
+	CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
+	CONTROLLER_DP_TEST_PATTERN_RESERVED_8,
+	CONTROLLER_DP_TEST_PATTERN_RESERVED_9,
+	CONTROLLER_DP_TEST_PATTERN_RESERVED_A,
+	CONTROLLER_DP_TEST_PATTERN_COLORSQUARES_CEA
+};
+
 #endif /* __DAL_HW_SHARED_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/ipp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/ipp.h
index f11aa484f46e..2109eac20a3d 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/ipp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/ipp.h
@@ -85,8 +85,10 @@ struct ipp_funcs {
 	/* setup ipp to expand/convert input to pixel processor internal format */
 	void (*ipp_setup)(
 		struct input_pixel_processor *ipp,
-		enum surface_pixel_format input_format,
-		enum expansion_mode mode);
+		enum surface_pixel_format format,
+		enum expansion_mode mode,
+		struct csc_transform input_csc_color_matrix,
+		enum dc_color_space input_color_space);
 
 	/* DCE function to setup IPP.  TODO: see if we can consolidate to setup */
 	void (*ipp_program_prescale)(
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
index 3d33bcda7059..0fd329deacd8 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
@@ -1,4 +1,26 @@
 /*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+/*
  * link_encoder.h
  *
  *  Created on: Oct 6, 2015
@@ -111,7 +133,7 @@ struct link_encoder_funcs {
 		const struct dc_link_settings *link_settings,
 		enum clock_source_id clock_source);
 	void (*disable_output)(struct link_encoder *link_enc,
-		enum signal_type signal, struct dc_link *link);
+		enum signal_type signal);
 	void (*dp_set_lane_settings)(struct link_encoder *enc,
 		const struct link_training_settings *link_settings);
 	void (*dp_set_phy_pattern)(struct link_encoder *enc,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
index d4188b2c0626..23a8d5e53a89 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@@ -26,35 +26,162 @@
 #define __DC_MPCC_H__
 
 #include "dc_hw_types.h"
-#include "opp.h"
+#include "hw_shared.h"
 
-struct mpcc_cfg {
-	int dpp_id;
-	int opp_id;
-	struct mpc_tree_cfg *tree_cfg;
-	unsigned int z_index;
+#define MAX_MPCC 6
+#define MAX_OPP 6
 
-	struct tg_color black_color;
-	bool per_pixel_alpha;
-	bool pre_multiplied_alpha;
+enum mpc_output_csc_mode {
+	MPC_OUTPUT_CSC_DISABLE = 0,
+	MPC_OUTPUT_CSC_COEF_A,
+	MPC_OUTPUT_CSC_COEF_B
+};
+
+
+enum mpcc_blend_mode {
+	MPCC_BLEND_MODE_BYPASS,
+	MPCC_BLEND_MODE_TOP_LAYER_PASSTHROUGH,
+	MPCC_BLEND_MODE_TOP_LAYER_ONLY,
+	MPCC_BLEND_MODE_TOP_BOT_BLENDING
+};
+
+enum mpcc_alpha_blend_mode {
+	MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA,
+	MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA_COMBINED_GLOBAL_GAIN,
+	MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA
+};
+
+/*
+ * MPCC blending configuration
+ */
+struct mpcc_blnd_cfg {
+	struct tg_color black_color;	/* background color */
+	enum mpcc_alpha_blend_mode alpha_mode;	/* alpha blend mode */
+	bool pre_multiplied_alpha;	/* alpha pre-multiplied mode flag */
+	int global_gain;
+	int global_alpha;
+	bool overlap_only;
+
+};
+
+struct mpcc_sm_cfg {
+	bool enable;
+	/* 0-single plane,2-row subsampling,4-column subsampling,6-checkboard subsampling */
+	int sm_mode;
+	/* 0- disable frame alternate, 1- enable frame alternate */
+	bool frame_alt;
+	/* 0- disable field alternate, 1- enable field alternate */
+	bool field_alt;
+	/* 0-no force,2-force frame polarity from top,3-force frame polarity from bottom */
+	int force_next_frame_porlarity;
+	/* 0-no force,2-force field polarity from top,3-force field polarity from bottom */
+	int force_next_field_polarity;
+};
+
+/*
+ * MPCC connection and blending configuration for a single MPCC instance.
+ * This struct is used as a node in an MPC tree.
+ */
+struct mpcc {
+	int mpcc_id;			/* MPCC physical instance */
+	int dpp_id;			/* DPP input to this MPCC */
+	struct mpcc *mpcc_bot;		/* pointer to bottom layer MPCC.  NULL when not connected */
+	struct mpcc_blnd_cfg blnd_cfg;	/* The blending configuration for this MPCC */
+	struct mpcc_sm_cfg sm_cfg;	/* stereo mix setting for this MPCC */
+};
+
+/*
+ * MPC tree represents all MPCC connections for a pipe.
+ */
+struct mpc_tree {
+	int opp_id;			/* The OPP instance that owns this MPC tree */
+	struct mpcc *opp_list;		/* The top MPCC layer of the MPC tree that outputs to OPP endpoint */
 };
 
 struct mpc {
 	const struct mpc_funcs *funcs;
 	struct dc_context *ctx;
+
+	struct mpcc mpcc_array[MAX_MPCC];
 };
 
 struct mpc_funcs {
-	int (*add)(struct mpc *mpc, struct mpcc_cfg *cfg);
+	/*
+	 * Insert DPP into MPC tree based on specified blending position.
+	 * Only used for planes that are part of blending chain for OPP output
+	 *
+	 * Parameters:
+	 * [in/out] mpc		- MPC context.
+	 * [in/out] tree	- MPC tree structure that plane will be added to.
+	 * [in]	blnd_cfg	- MPCC blending configuration for the new blending layer.
+	 * [in]	sm_cfg		- MPCC stereo mix configuration for the new blending layer.
+	 *			  stereo mix must disable for the very bottom layer of the tree config.
+	 * [in]	insert_above_mpcc - Insert new plane above this MPCC.  If NULL, insert as bottom plane.
+	 * [in]	dpp_id		 - DPP instance for the plane to be added.
+	 * [in]	mpcc_id		 - The MPCC physical instance to use for blending.
+	 *
+	 * Return:  struct mpcc* - MPCC that was added.
+	 */
+	struct mpcc* (*insert_plane)(
+			struct mpc *mpc,
+			struct mpc_tree *tree,
+			struct mpcc_blnd_cfg *blnd_cfg,
+			struct mpcc_sm_cfg *sm_cfg,
+			struct mpcc *insert_above_mpcc,
+			int dpp_id,
+			int mpcc_id);
+
+	/*
+	 * Remove a specified MPCC from the MPC tree.
+	 *
+	 * Parameters:
+	 * [in/out] mpc		- MPC context.
+	 * [in/out] tree	- MPC tree structure that plane will be removed from.
+	 * [in/out] mpcc	- MPCC to be removed from tree.
+	 *
+	 * Return:  void
+	 */
+	void (*remove_mpcc)(
+			struct mpc *mpc,
+			struct mpc_tree *tree,
+			struct mpcc *mpcc);
+
+	/*
+	 * Reset the MPCC HW status by disconnecting all muxes.
+	 *
+	 * Parameters:
+	 * [in/out] mpc		- MPC context.
+	 *
+	 * Return:  void
+	 */
+	void (*mpc_init)(struct mpc *mpc);
 
-	void (*remove)(struct mpc *mpc,
-			struct mpc_tree_cfg *tree_cfg,
-			int opp_id,
-			int mpcc_inst);
+	/*
+	 * Update the blending configuration for a specified MPCC.
+	 *
+	 * Parameters:
+	 * [in/out] mpc		- MPC context.
+	 * [in]     blnd_cfg	- MPCC blending configuration.
+	 * [in]     mpcc_id	- The MPCC physical instance.
+	 *
+	 * Return:  void
+	 */
+	void (*update_blending)(
+		struct mpc *mpc,
+		struct mpcc_blnd_cfg *blnd_cfg,
+		int mpcc_id);
+
+	struct mpcc* (*get_mpcc_for_dpp)(
+			struct mpc_tree *tree,
+			int dpp_id);
 
 	void (*wait_for_idle)(struct mpc *mpc, int id);
 
-	void (*update_blend_mode)(struct mpc *mpc, struct mpcc_cfg *cfg);
+	void (*assert_mpcc_idle_before_connect)(struct mpc *mpc, int mpcc_id);
+
+	void (*init_mpcc_list_from_hw)(
+		struct mpc *mpc,
+		struct mpc_tree *tree);
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
index 75adb8fec551..ab8fb77f1ae5 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
@@ -29,6 +29,7 @@
 #include "hw_shared.h"
 #include "dc_hw_types.h"
 #include "transform.h"
+#include "mpc.h"
 
 struct fixed31_32;
 
@@ -204,7 +205,7 @@ struct output_pixel_processor {
 	struct dc_context *ctx;
 	uint32_t inst;
 	struct pwl_params regamma_params;
-	struct mpc_tree_cfg mpc_tree;
+	struct mpc_tree mpc_tree_params;
 	bool mpcc_disconnect_pending[MAX_PIPES];
 	const struct opp_funcs *funcs;
 };
@@ -248,6 +249,21 @@ enum ovl_csc_adjust_item {
 	OVERLAY_COLOR_TEMPERATURE
 };
 
+enum oppbuf_display_segmentation {
+	OPPBUF_DISPLAY_SEGMENTATION_1_SEGMENT = 0,
+	OPPBUF_DISPLAY_SEGMENTATION_2_SEGMENT = 1,
+	OPPBUF_DISPLAY_SEGMENTATION_4_SEGMENT = 2,
+	OPPBUF_DISPLAY_SEGMENTATION_4_SEGMENT_SPLIT_LEFT = 3,
+	OPPBUF_DISPLAY_SEGMENTATION_4_SEGMENT_SPLIT_RIGHT = 4
+};
+
+struct oppbuf_params {
+	uint32_t active_width;
+	enum oppbuf_display_segmentation mso_segmentation;
+	uint32_t mso_overlap_pixel_num;
+	uint32_t pixel_repetition;
+};
+
 struct opp_funcs {
 
 
@@ -276,14 +292,11 @@ struct opp_funcs {
 
 	void (*opp_destroy)(struct output_pixel_processor **opp);
 
-	void (*opp_set_stereo_polarity)(
-			struct output_pixel_processor *opp,
-			bool enable,
-			bool rightEyePolarity);
+	void (*opp_program_stereo)(
+		struct output_pixel_processor *opp,
+		bool enable,
+		const struct dc_crtc_timing *timing);
 
-	void (*opp_set_test_pattern)(
-			struct output_pixel_processor *opp,
-			bool enable);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
index 3050afe8e8a9..b5db1692393c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
@@ -1,4 +1,26 @@
 /*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+/*
  * stream_encoder.h
  *
  */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
index c6ab38c5b2be..ec312f1a3e55 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
@@ -26,6 +26,8 @@
 #ifndef __DAL_TIMING_GENERATOR_TYPES_H__
 #define __DAL_TIMING_GENERATOR_TYPES_H__
 
+#include "hw_shared.h"
+
 struct dc_bios;
 
 /* Contains CRTC vertical/horizontal pixel counters */
@@ -40,6 +42,19 @@ struct dcp_gsl_params {
 	int gsl_master;
 };
 
+struct gsl_params {
+	int gsl0_en;
+	int gsl1_en;
+	int gsl2_en;
+	int gsl_master_en;
+	int gsl_master_mode;
+	int master_update_lock_gsl_en;
+	int gsl_window_start_x;
+	int gsl_window_end_x;
+	int gsl_window_start_y;
+	int gsl_window_end_y;
+};
+
 /* define the structure of Dynamic Refresh Mode */
 struct drr_params {
 	uint32_t vertical_total_min;
@@ -50,43 +65,6 @@ struct drr_params {
 #define LEFT_EYE_3D_PRIMARY_SURFACE 1
 #define RIGHT_EYE_3D_PRIMARY_SURFACE 0
 
-enum test_pattern_dyn_range {
-	TEST_PATTERN_DYN_RANGE_VESA = 0,
-	TEST_PATTERN_DYN_RANGE_CEA
-};
-
-enum test_pattern_mode {
-	TEST_PATTERN_MODE_COLORSQUARES_RGB = 0,
-	TEST_PATTERN_MODE_COLORSQUARES_YCBCR601,
-	TEST_PATTERN_MODE_COLORSQUARES_YCBCR709,
-	TEST_PATTERN_MODE_VERTICALBARS,
-	TEST_PATTERN_MODE_HORIZONTALBARS,
-	TEST_PATTERN_MODE_SINGLERAMP_RGB,
-	TEST_PATTERN_MODE_DUALRAMP_RGB
-};
-
-enum test_pattern_color_format {
-	TEST_PATTERN_COLOR_FORMAT_BPC_6 = 0,
-	TEST_PATTERN_COLOR_FORMAT_BPC_8,
-	TEST_PATTERN_COLOR_FORMAT_BPC_10,
-	TEST_PATTERN_COLOR_FORMAT_BPC_12
-};
-
-enum controller_dp_test_pattern {
-	CONTROLLER_DP_TEST_PATTERN_D102 = 0,
-	CONTROLLER_DP_TEST_PATTERN_SYMBOLERROR,
-	CONTROLLER_DP_TEST_PATTERN_PRBS7,
-	CONTROLLER_DP_TEST_PATTERN_COLORSQUARES,
-	CONTROLLER_DP_TEST_PATTERN_VERTICALBARS,
-	CONTROLLER_DP_TEST_PATTERN_HORIZONTALBARS,
-	CONTROLLER_DP_TEST_PATTERN_COLORRAMP,
-	CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
-	CONTROLLER_DP_TEST_PATTERN_RESERVED_8,
-	CONTROLLER_DP_TEST_PATTERN_RESERVED_9,
-	CONTROLLER_DP_TEST_PATTERN_RESERVED_A,
-	CONTROLLER_DP_TEST_PATTERN_COLORSQUARES_CEA
-};
-
 enum crtc_state {
 	CRTC_STATE_VBLANK = 0,
 	CRTC_STATE_VACTIVE
@@ -100,6 +78,12 @@ struct _dlg_otg_param {
 	enum signal_type signal;
 };
 
+struct vupdate_keepout_params {
+	int start_offset;
+	int end_offset;
+	int enable;
+};
+
 struct crtc_stereo_flags {
 	uint8_t PROGRAM_STEREO         : 1;
 	uint8_t PROGRAM_POLARITY       : 1;
@@ -158,7 +142,11 @@ struct timing_generator_funcs {
 							const struct dcp_gsl_params *gsl_params);
 	void (*unlock)(struct timing_generator *tg);
 	void (*lock)(struct timing_generator *tg);
-	void (*enable_reset_trigger)(struct timing_generator *tg, int source_tg_inst);
+	void (*enable_reset_trigger)(struct timing_generator *tg,
+				     int source_tg_inst);
+	void (*enable_crtc_reset)(struct timing_generator *tg,
+				  int source_tg_inst,
+				  struct crtc_trigger_info *crtc_tp);
 	void (*disable_reset_trigger)(struct timing_generator *tg);
 	void (*tear_down_global_swap_lock)(struct timing_generator *tg);
 	void (*enable_advanced_request)(struct timing_generator *tg,
@@ -178,6 +166,13 @@ struct timing_generator_funcs {
 	void (*program_stereo)(struct timing_generator *tg,
 		const struct dc_crtc_timing *timing, struct crtc_stereo_flags *flags);
 	bool (*is_stereo_left_eye)(struct timing_generator *tg);
+
+	void (*set_blank_data_double_buffer)(struct timing_generator *tg, bool enable);
+
+	void (*tg_init)(struct timing_generator *tg);
+	bool (*is_tg_enabled)(struct timing_generator *tg);
+	bool (*is_optc_underflow_occurred)(struct timing_generator *tg);
+	void (*clear_optc_underflow)(struct timing_generator *tg);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h b/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
index 7c08bc62c1f5..6f6c02b89f90 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
@@ -250,8 +250,10 @@ struct transform_funcs {
 
 	void (*ipp_setup)(
 			struct transform *xfm_base,
-			enum surface_pixel_format input_format,
-			enum expansion_mode mode);
+			enum surface_pixel_format format,
+			enum expansion_mode mode,
+			struct csc_transform input_csc_color_matrix,
+			enum dc_color_space input_color_space);
 
 	void (*ipp_full_bypass)(struct transform *xfm_base);
 
@@ -259,13 +261,6 @@ struct transform_funcs {
 			struct transform *xfm_base,
 			const struct dc_cursor_attributes *attr);
 
-	void (*set_cursor_position)(
-			struct transform *xfm_base,
-			const struct dc_cursor_position *pos,
-			const struct dc_cursor_mi_param *param,
-			uint32_t width
-			);
-
 };
 
 const uint16_t *get_filter_2tap_16p(void);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index 8734689a9245..4c0aa56f7bae 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -28,6 +28,7 @@
 #include "dc_types.h"
 #include "clock_source.h"
 #include "inc/hw/timing_generator.h"
+#include "inc/hw/opp.h"
 #include "inc/hw/link_encoder.h"
 #include "core_status.h"
 
@@ -39,6 +40,12 @@ enum pipe_gating_control {
 
 struct dce_hwseq_wa {
 	bool blnd_crtc_trigger;
+	bool DEGVIDCN10_253;
+	bool false_optc_underflow;
+};
+
+struct hwseq_wa_state {
+	bool DEGVIDCN10_253_applied;
 };
 
 struct dce_hwseq {
@@ -47,6 +54,7 @@ struct dce_hwseq {
 	const struct dce_hwseq_shift *shifts;
 	const struct dce_hwseq_mask *masks;
 	struct dce_hwseq_wa wa;
+	struct hwseq_wa_state wa_state;
 };
 
 struct pipe_ctx;
@@ -114,6 +122,11 @@ struct hw_sequencer_funcs {
 			int group_size,
 			struct pipe_ctx *grouped_pipes[]);
 
+	void (*enable_per_frame_crtc_position_reset)(
+			struct dc *dc,
+			int group_size,
+			struct pipe_ctx *grouped_pipes[]);
+
 	void (*enable_display_pipe_clock_gating)(
 					struct dc_context *ctx,
 					bool clock_gating);
@@ -124,11 +137,7 @@ struct hw_sequencer_funcs {
 					struct dc_bios *dcb,
 					enum pipe_gating_control power_gating);
 
-	void (*power_down_front_end)(struct dc *dc, int fe_idx);
-
-	void (*power_on_front_end)(struct dc *dc,
-			struct pipe_ctx *pipe,
-			struct dc_state *context);
+	void (*disable_plane)(struct dc *dc, struct pipe_ctx *pipe_ctx);
 
 	void (*update_info_frame)(struct pipe_ctx *pipe_ctx);
 
@@ -178,12 +187,17 @@ struct hw_sequencer_funcs {
 
 	void (*ready_shared_resources)(struct dc *dc, struct dc_state *context);
 	void (*optimize_shared_resources)(struct dc *dc);
+	void (*pplib_apply_display_requirements)(
+			struct dc *dc,
+			struct dc_state *context);
 	void (*edp_power_control)(
-			struct link_encoder *enc,
+			struct dc_link *link,
 			bool enable);
 	void (*edp_backlight_control)(
 			struct dc_link *link,
 			bool enable);
+	void (*edp_wait_for_hpd_ready)(struct dc_link *link, bool power_up);
+
 };
 
 void color_space_to_black_color(
@@ -194,4 +208,8 @@ void color_space_to_black_color(
 bool hwss_wait_for_blank_complete(
 		struct timing_generator *tg);
 
+const uint16_t *find_color_matrix(
+		enum dc_color_space color_space,
+		uint32_t *array_size);
+
 #endif /* __DC_HW_SEQUENCER_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/irq/Makefile b/drivers/gpu/drm/amd/display/dc/irq/Makefile
index c7e93f7223bd..498515aad4a5 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/irq/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'audio' sub-component of DAL.
 # It provides the control and status of HW adapter resources,
 # that are global for the ASIC and sharable between pipes.
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c b/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c
index 2ad56b1a4099..66d52580e29f 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c
@@ -30,9 +30,9 @@
 #include "irq_service_dce120.h"
 #include "../dce110/irq_service_dce110.h"
 
-#include "vega10/DC/dce_12_0_offset.h"
-#include "vega10/DC/dce_12_0_sh_mask.h"
-#include "vega10/soc15ip.h"
+#include "dce/dce_12_0_offset.h"
+#include "dce/dce_12_0_sh_mask.h"
+#include "soc15ip.h"
 
 #include "ivsrcid/ivsrcid_vislands30.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c b/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c
index 74ad24714f6b..7f7db66c48b0 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c
@@ -29,9 +29,9 @@
 
 #include "../dce110/irq_service_dce110.h"
 
-#include "raven1/DCN/dcn_1_0_offset.h"
-#include "raven1/DCN/dcn_1_0_sh_mask.h"
-#include "vega10/soc15ip.h"
+#include "dcn/dcn_1_0_offset.h"
+#include "dcn/dcn_1_0_sh_mask.h"
+#include "soc15ip.h"
 
 #include "irq_service_dcn10.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index a87c0329541f..1fcbc99e63b5 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -26,8 +26,6 @@
 #ifndef _OS_TYPES_H_
 #define _OS_TYPES_H_
 
-#if defined __KERNEL__
-
 #include <asm/byteorder.h>
 #include <linux/types.h>
 #include <drm/drmP.h>
@@ -46,14 +44,12 @@
 #undef WRITE
 #undef FRAME_SIZE
 
-#define dm_output_to_console(fmt, ...) DRM_INFO(fmt, ##__VA_ARGS__)
+#define dm_output_to_console(fmt, ...) DRM_DEBUG_KMS(fmt, ##__VA_ARGS__)
 
 #define dm_error(fmt, ...) DRM_ERROR(fmt, ##__VA_ARGS__)
 
-#define dm_debug(fmt, ...) DRM_DEBUG_KMS(fmt, ##__VA_ARGS__)
-
-#define dm_vlog(fmt, args) vprintk(fmt, args)
-
+#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#include <asm/fpu/api.h>
 #endif
 
 /*
@@ -89,8 +85,4 @@
 	BREAK_TO_DEBUGGER(); \
 } while (0)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-#include <asm/fpu/api.h>
-#endif
-
 #endif /* _OS_TYPES_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/virtual/Makefile b/drivers/gpu/drm/amd/display/dc/virtual/Makefile
index fc0b7318d9cc..07326d244d50 100644
--- a/drivers/gpu/drm/amd/display/dc/virtual/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/virtual/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the virtual sub-component of DAL.
 # It provides the control and status of HW CRTC block.
 
diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c
index 88c2bde3f039..57a54a7b89e5 100644
--- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c
@@ -58,8 +58,7 @@ static void virtual_link_encoder_enable_dp_mst_output(
 
 static void virtual_link_encoder_disable_output(
 	struct link_encoder *link_enc,
-	enum signal_type signal,
-	struct dc_link *link) {}
+	enum signal_type signal) {}
 
 static void virtual_link_encoder_dp_set_lane_settings(
 	struct link_encoder *enc,
diff --git a/drivers/gpu/drm/amd/display/include/ddc_service_types.h b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
index 0ff2a899b8f7..019e7a095ea1 100644
--- a/drivers/gpu/drm/amd/display/include/ddc_service_types.h
+++ b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
@@ -27,12 +27,8 @@
 
 #define DP_BRANCH_DEVICE_ID_1 0x0010FA
 #define DP_BRANCH_DEVICE_ID_2 0x0022B9
-#define DP_SINK_DEVICE_ID_1 0x4CE000
 #define DP_BRANCH_DEVICE_ID_3 0x00001A
 #define DP_BRANCH_DEVICE_ID_4 0x0080e1
-#define DP_BRANCH_DEVICE_ID_5 0x006037
-#define DP_SINK_DEVICE_ID_2 0x001CF8
-
 
 enum ddc_result {
 	DDC_RESULT_UNKNOWN = 0,
@@ -115,40 +111,11 @@ struct av_sync_data {
 	uint8_t aud_del_ins3;/* DPCD 0002Dh */
 };
 
-/*DP to VGA converter*/
-static const uint8_t DP_VGA_CONVERTER_ID_1[] = "mVGAa";
-/*DP to Dual link DVI converter*/
-static const uint8_t DP_DVI_CONVERTER_ID_1[] = "m2DVIa";
 /*Travis*/
 static const uint8_t DP_VGA_LVDS_CONVERTER_ID_2[] = "sivarT";
 /*Nutmeg*/
 static const uint8_t DP_VGA_LVDS_CONVERTER_ID_3[] = "dnomlA";
-/*DP to VGA converter*/
-static const uint8_t DP_VGA_CONVERTER_ID_4[] = "DpVga";
 /*DP to Dual link DVI converter*/
 static const uint8_t DP_DVI_CONVERTER_ID_4[] = "m2DVIa";
-/*DP to Dual link DVI converter 2*/
-static const uint8_t DP_DVI_CONVERTER_ID_42[] = "v2DVIa";
-
-static const uint8_t DP_SINK_DEV_STRING_ID2_REV0[] = "\0\0\0\0\0\0";
-
-/* Identifies second generation PSR TCON from Parade: Device ID string:
- * yy-xx-**-**-**-**
- */
-/* xx - Hw ID high byte */
-static const uint32_t DP_SINK_DEV_STRING_ID2_REV1_HW_ID_HIGH_BYTE =
-	0x06;
-
-/* yy - HW ID low byte, the same silicon has several package/feature flavors */
-static const uint32_t DP_SINK_DEV_STRING_ID2_REV1_HW_ID_LOW_BYTE1 =
-	0x61;
-static const uint32_t DP_SINK_DEV_STRING_ID2_REV1_HW_ID_LOW_BYTE2 =
-	0x62;
-static const uint32_t DP_SINK_DEV_STRING_ID2_REV1_HW_ID_LOW_BYTE3 =
-	0x63;
-static const uint32_t DP_SINK_DEV_STRING_ID2_REV1_HW_ID_LOW_BYTE4 =
-	0x72;
-static const uint32_t DP_SINK_DEV_STRING_ID2_REV1_HW_ID_LOW_BYTE5 =
-	0x73;
 
 #endif /* __DAL_DDC_SERVICE_TYPES_H__ */
diff --git a/drivers/gpu/drm/amd/display/include/fixed31_32.h b/drivers/gpu/drm/amd/display/include/fixed31_32.h
index 3248f699daf2..4badaedbaadd 100644
--- a/drivers/gpu/drm/amd/display/include/fixed31_32.h
+++ b/drivers/gpu/drm/amd/display/include/fixed31_32.h
@@ -463,4 +463,11 @@ uint32_t dal_fixed31_32_u2d19(
 uint32_t dal_fixed31_32_u0d19(
 	struct fixed31_32 arg);
 
+
+uint32_t dal_fixed31_32_clamp_u0d14(
+	struct fixed31_32 arg);
+
+uint32_t dal_fixed31_32_clamp_u0d10(
+	struct fixed31_32 arg);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_id.h b/drivers/gpu/drm/amd/display/include/grph_object_id.h
index 5eb2b4dc7b9c..c4197432eb7c 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_id.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_id.h
@@ -233,10 +233,6 @@ static inline struct graphics_object_id dal_graphics_object_id_init(
 	return result;
 }
 
-bool dal_graphics_object_id_is_equal(
-	struct graphics_object_id id1,
-	struct graphics_object_id id2);
-
 /* Based on internal data members memory layout */
 static inline uint32_t dal_graphics_object_id_to_uint(
 	struct graphics_object_id id)
@@ -248,7 +244,7 @@ static inline enum controller_id dal_graphics_object_id_get_controller_id(
 	struct graphics_object_id id)
 {
 	if (id.type == OBJECT_TYPE_CONTROLLER)
-		return id.id;
+		return (enum controller_id) id.id;
 	return CONTROLLER_ID_UNDEFINED;
 }
 
@@ -256,7 +252,7 @@ static inline enum clock_source_id dal_graphics_object_id_get_clock_source_id(
 	struct graphics_object_id id)
 {
 	if (id.type == OBJECT_TYPE_CLOCK_SOURCE)
-		return id.id;
+		return (enum clock_source_id) id.id;
 	return CLOCK_SOURCE_ID_UNDEFINED;
 }
 
@@ -264,7 +260,7 @@ static inline enum encoder_id dal_graphics_object_id_get_encoder_id(
 	struct graphics_object_id id)
 {
 	if (id.type == OBJECT_TYPE_ENCODER)
-		return id.id;
+		return (enum encoder_id) id.id;
 	return ENCODER_ID_UNKNOWN;
 }
 
@@ -272,7 +268,7 @@ static inline enum connector_id dal_graphics_object_id_get_connector_id(
 	struct graphics_object_id id)
 {
 	if (id.type == OBJECT_TYPE_CONNECTOR)
-		return id.id;
+		return (enum connector_id) id.id;
 	return CONNECTOR_ID_UNKNOWN;
 }
 
@@ -280,7 +276,7 @@ static inline enum audio_id dal_graphics_object_id_get_audio_id(
 	struct graphics_object_id id)
 {
 	if (id.type == OBJECT_TYPE_AUDIO)
-		return id.id;
+		return (enum audio_id) id.id;
 	return AUDIO_ID_UNKNOWN;
 }
 
@@ -288,7 +284,7 @@ static inline enum engine_id dal_graphics_object_id_get_engine_id(
 	struct graphics_object_id id)
 {
 	if (id.type == OBJECT_TYPE_ENGINE)
-		return id.id;
+		return (enum engine_id) id.id;
 	return ENGINE_ID_UNKNOWN;
 }
 #endif
diff --git a/drivers/gpu/drm/amd/display/include/logger_interface.h b/drivers/gpu/drm/amd/display/include/logger_interface.h
index 8e1fe70097be..28dee960d509 100644
--- a/drivers/gpu/drm/amd/display/include/logger_interface.h
+++ b/drivers/gpu/drm/amd/display/include/logger_interface.h
@@ -57,6 +57,11 @@ void dm_logger_append(
 		const char *msg,
 		...);
 
+void dm_logger_append_va(
+		struct log_entry *entry,
+		const char *msg,
+		va_list args);
+
 void dm_logger_open(
 		struct dal_logger *logger,
 		struct log_entry *entry,
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/Makefile b/drivers/gpu/drm/amd/display/modules/freesync/Makefile
index db8e0ff6d7a9..fb9a499780e8 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/Makefile
+++ b/drivers/gpu/drm/amd/display/modules/freesync/Makefile
@@ -1,4 +1,25 @@
 #
+# Copyright 2017 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
 # Makefile for the 'freesync' sub-module of DAL.
 #
 
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index 4d7db4aa28e0..b4723af368a5 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -132,14 +132,6 @@ struct core_freesync {
 #define MOD_FREESYNC_TO_CORE(mod_freesync)\
 		container_of(mod_freesync, struct core_freesync, public)
 
-static bool check_dc_support(const struct dc *dc)
-{
-	if (dc->stream_funcs.adjust_vmin_vmax == NULL)
-		return false;
-
-	return true;
-}
-
 struct mod_freesync *mod_freesync_create(struct dc *dc)
 {
 	struct core_freesync *core_freesync =
@@ -169,9 +161,6 @@ struct mod_freesync *mod_freesync_create(struct dc *dc)
 
 	core_freesync->dc = dc;
 
-	if (!check_dc_support(dc))
-		goto fail_construct;
-
 	/* Create initial module folder in registry for freesync enable data */
 	flag.save_per_edid = true;
 	flag.save_per_link = false;
@@ -599,10 +588,9 @@ static bool set_freesync_on_streams(struct core_freesync *core_freesync,
 				update_stream_freesync_context(core_freesync,
 						streams[stream_idx]);
 
-				core_freesync->dc->stream_funcs.
-				adjust_vmin_vmax(core_freesync->dc, streams,
-						num_streams, v_total_min,
-						v_total_max);
+				dc_stream_adjust_vmin_vmax(core_freesync->dc, streams,
+							   num_streams, v_total_min,
+							   v_total_max);
 
 				return true;
 
@@ -625,8 +613,7 @@ static bool set_freesync_on_streams(struct core_freesync *core_freesync,
 						core_freesync,
 						streams[stream_idx]);
 
-					core_freesync->dc->stream_funcs.
-					adjust_vmin_vmax(
+					dc_stream_adjust_vmin_vmax(
 						core_freesync->dc, streams,
 						num_streams, v_total_nominal,
 						v_total_nominal);
@@ -645,11 +632,9 @@ static bool set_freesync_on_streams(struct core_freesync *core_freesync,
 					core_freesync,
 					streams[stream_idx]);
 
-				core_freesync->dc->stream_funcs.
-						adjust_vmin_vmax(
-						core_freesync->dc, streams,
-						num_streams, v_total_nominal,
-						v_total_nominal);
+				dc_stream_adjust_vmin_vmax(core_freesync->dc, streams,
+							   num_streams, v_total_nominal,
+							   v_total_nominal);
 
 				/* Reset the cached variables */
 				reset_freesync_state_variables(state);
@@ -665,11 +650,9 @@ static bool set_freesync_on_streams(struct core_freesync *core_freesync,
 			 * not support freesync because a former stream has
 			 * be programmed
 			 */
-			core_freesync->dc->stream_funcs.
-					adjust_vmin_vmax(
-					core_freesync->dc, streams,
-					num_streams, v_total_nominal,
-					v_total_nominal);
+			dc_stream_adjust_vmin_vmax(core_freesync->dc, streams,
+						   num_streams, v_total_nominal,
+						   v_total_nominal);
 			/* Reset the cached variables */
 			reset_freesync_state_variables(state);
 		}
@@ -786,9 +769,8 @@ void mod_freesync_handle_v_update(struct mod_freesync *mod_freesync,
 			vmin = inserted_frame_v_total;
 
 			/* Program V_TOTAL */
-			core_freesync->dc->stream_funcs.adjust_vmin_vmax(
-				core_freesync->dc, streams,
-				num_streams, vmin, vmax);
+			dc_stream_adjust_vmin_vmax(core_freesync->dc, streams,
+						   num_streams, vmin, vmax);
 		}
 
 		if (state->btr.frame_counter > 0)
@@ -822,17 +804,15 @@ void mod_freesync_handle_v_update(struct mod_freesync *mod_freesync,
 		update_stream_freesync_context(core_freesync, streams[0]);
 
 		/* Program static screen ramp values */
-		core_freesync->dc->stream_funcs.adjust_vmin_vmax(
-					core_freesync->dc, streams,
-					num_streams, v_total,
-					v_total);
+		dc_stream_adjust_vmin_vmax(core_freesync->dc, streams,
+					   num_streams, v_total,
+					   v_total);
 
 		triggers.overlay_update = true;
 		triggers.surface_update = true;
 
-		core_freesync->dc->stream_funcs.set_static_screen_events(
-					core_freesync->dc, streams,	num_streams,
-					&triggers);
+		dc_stream_set_static_screen_events(core_freesync->dc, streams,
+						   num_streams, &triggers);
 	}
 }
 
@@ -916,9 +896,8 @@ void mod_freesync_update_state(struct mod_freesync *mod_freesync,
 	triggers.overlay_update = true;
 	triggers.surface_update = true;
 
-	core_freesync->dc->stream_funcs.set_static_screen_events(
-		core_freesync->dc, streams, num_streams,
-		&triggers);
+	dc_stream_set_static_screen_events(core_freesync->dc, streams,
+					   num_streams, &triggers);
 
 	if (freesync_program_required)
 		/* Program freesync according to current state*/
@@ -1084,10 +1063,9 @@ bool mod_freesync_override_min_max(struct mod_freesync *mod_freesync,
 				max_refresh);
 
 		/* Program vtotal min/max */
-		core_freesync->dc->stream_funcs.adjust_vmin_vmax(
-			core_freesync->dc, &streams, 1,
-			state->freesync_range.vmin,
-			state->freesync_range.vmax);
+		dc_stream_adjust_vmin_vmax(core_freesync->dc, &streams, 1,
+					   state->freesync_range.vmin,
+					   state->freesync_range.vmax);
 	}
 
 	if (min_refresh != 0 &&
@@ -1163,9 +1141,9 @@ bool mod_freesync_get_v_position(struct mod_freesync *mod_freesync,
 	core_freesync = MOD_FREESYNC_TO_CORE(mod_freesync);
 	index = map_index_from_stream(core_freesync, stream);
 
-	if (core_freesync->dc->stream_funcs.get_crtc_position(
-			core_freesync->dc, &stream, 1,
-			&position.vertical_count, &position.nominal_vcount)) {
+	if (dc_stream_get_crtc_position(core_freesync->dc, &stream, 1,
+					&position.vertical_count,
+					&position.nominal_vcount)) {
 
 		*nom_v_pos = position.nominal_vcount;
 		*v_pos = position.vertical_count;
@@ -1223,9 +1201,9 @@ void mod_freesync_notify_mode_change(struct mod_freesync *mod_freesync,
 			triggers.overlay_update = true;
 			triggers.surface_update = true;
 
-			core_freesync->dc->stream_funcs.set_static_screen_events(
-				core_freesync->dc, streams, num_streams,
-				&triggers);
+			dc_stream_set_static_screen_events(core_freesync->dc,
+							   streams, num_streams,
+							   &triggers);
 		}
 	}
 
@@ -1424,10 +1402,8 @@ static void apply_fixed_refresh(struct core_freesync *core_freesync,
 
 		vmax = vmin;
 
-		core_freesync->dc->stream_funcs.adjust_vmin_vmax(
-				core_freesync->dc, &stream,
-				1, vmin,
-				vmax);
+		dc_stream_adjust_vmin_vmax(core_freesync->dc, &stream,
+					   1, vmin, vmax);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index b72f8a43d86b..9fa3aaef3f33 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -25,7 +25,6 @@
 
 #include <drm/amd_asic_type.h>
 
-struct seq_file;
 
 #define AMD_MAX_USEC_TIMEOUT		200000  /* 200 ms */
 
@@ -61,71 +60,12 @@ enum amd_clockgating_state {
 	AMD_CG_STATE_UNGATE,
 };
 
-enum amd_dpm_forced_level {
-	AMD_DPM_FORCED_LEVEL_AUTO = 0x1,
-	AMD_DPM_FORCED_LEVEL_MANUAL = 0x2,
-	AMD_DPM_FORCED_LEVEL_LOW = 0x4,
-	AMD_DPM_FORCED_LEVEL_HIGH = 0x8,
-	AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD = 0x10,
-	AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK = 0x20,
-	AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK = 0x40,
-	AMD_DPM_FORCED_LEVEL_PROFILE_PEAK = 0x80,
-	AMD_DPM_FORCED_LEVEL_PROFILE_EXIT = 0x100,
-};
 
 enum amd_powergating_state {
 	AMD_PG_STATE_GATE = 0,
 	AMD_PG_STATE_UNGATE,
 };
 
-struct amd_vce_state {
-	/* vce clocks */
-	u32 evclk;
-	u32 ecclk;
-	/* gpu clocks */
-	u32 sclk;
-	u32 mclk;
-	u8 clk_idx;
-	u8 pstate;
-};
-
-
-#define AMD_MAX_VCE_LEVELS 6
-
-enum amd_vce_level {
-	AMD_VCE_LEVEL_AC_ALL = 0,     /* AC, All cases */
-	AMD_VCE_LEVEL_DC_EE = 1,      /* DC, entropy encoding */
-	AMD_VCE_LEVEL_DC_LL_LOW = 2,  /* DC, low latency queue, res <= 720 */
-	AMD_VCE_LEVEL_DC_LL_HIGH = 3, /* DC, low latency queue, 1080 >= res > 720 */
-	AMD_VCE_LEVEL_DC_GP_LOW = 4,  /* DC, general purpose queue, res <= 720 */
-	AMD_VCE_LEVEL_DC_GP_HIGH = 5, /* DC, general purpose queue, 1080 >= res > 720 */
-};
-
-enum amd_pp_profile_type {
-	AMD_PP_GFX_PROFILE,
-	AMD_PP_COMPUTE_PROFILE,
-};
-
-struct amd_pp_profile {
-	enum amd_pp_profile_type type;
-	uint32_t min_sclk;
-	uint32_t min_mclk;
-	uint16_t activity_threshold;
-	uint8_t up_hyst;
-	uint8_t down_hyst;
-};
-
-enum amd_fan_ctrl_mode {
-	AMD_FAN_CTRL_NONE = 0,
-	AMD_FAN_CTRL_MANUAL = 1,
-	AMD_FAN_CTRL_AUTO = 2,
-};
-
-enum pp_clock_type {
-	PP_SCLK,
-	PP_MCLK,
-	PP_PCIE,
-};
 
 /* CG flags */
 #define AMD_CG_SUPPORT_GFX_MGCG			(1 << 0)
@@ -169,27 +109,6 @@ enum pp_clock_type {
 #define AMD_PG_SUPPORT_GFX_PIPELINE		(1 << 12)
 #define AMD_PG_SUPPORT_MMHUB			(1 << 13)
 
-enum amd_pm_state_type {
-	/* not used for dpm */
-	POWER_STATE_TYPE_DEFAULT,
-	POWER_STATE_TYPE_POWERSAVE,
-	/* user selectable states */
-	POWER_STATE_TYPE_BATTERY,
-	POWER_STATE_TYPE_BALANCED,
-	POWER_STATE_TYPE_PERFORMANCE,
-	/* internal states */
-	POWER_STATE_TYPE_INTERNAL_UVD,
-	POWER_STATE_TYPE_INTERNAL_UVD_SD,
-	POWER_STATE_TYPE_INTERNAL_UVD_HD,
-	POWER_STATE_TYPE_INTERNAL_UVD_HD2,
-	POWER_STATE_TYPE_INTERNAL_UVD_MVC,
-	POWER_STATE_TYPE_INTERNAL_BOOT,
-	POWER_STATE_TYPE_INTERNAL_THERMAL,
-	POWER_STATE_TYPE_INTERNAL_ACPI,
-	POWER_STATE_TYPE_INTERNAL_ULV,
-	POWER_STATE_TYPE_INTERNAL_3DPERF,
-};
-
 struct amd_ip_funcs {
 	/* Name of IP block */
 	char *name;
@@ -233,95 +152,4 @@ struct amd_ip_funcs {
 };
 
 
-enum amd_pp_task;
-enum amd_pp_clock_type;
-struct pp_states_info;
-struct amd_pp_simple_clock_info;
-struct amd_pp_display_configuration;
-struct amd_pp_clock_info;
-struct pp_display_clock_request;
-struct pp_wm_sets_with_clock_ranges_soc15;
-struct pp_clock_levels_with_voltage;
-struct pp_clock_levels_with_latency;
-struct amd_pp_clocks;
-
-struct amd_pm_funcs {
-/* export for dpm on ci and si */
-	int (*pre_set_power_state)(void *handle);
-	int (*set_power_state)(void *handle);
-	void (*post_set_power_state)(void *handle);
-	void (*display_configuration_changed)(void *handle);
-	void (*print_power_state)(void *handle, void *ps);
-	bool (*vblank_too_short)(void *handle);
-	void (*enable_bapm)(void *handle, bool enable);
-	int (*check_state_equal)(void *handle,
-				void  *cps,
-				void  *rps,
-				bool  *equal);
-/* export for sysfs */
-	int (*get_temperature)(void *handle);
-	void (*set_fan_control_mode)(void *handle, u32 mode);
-	u32 (*get_fan_control_mode)(void *handle);
-	int (*set_fan_speed_percent)(void *handle, u32 speed);
-	int (*get_fan_speed_percent)(void *handle, u32 *speed);
-	int (*force_clock_level)(void *handle, enum pp_clock_type type, uint32_t mask);
-	int (*print_clock_levels)(void *handle, enum pp_clock_type type, char *buf);
-	int (*force_performance_level)(void *handle, enum amd_dpm_forced_level level);
-	int (*get_sclk_od)(void *handle);
-	int (*set_sclk_od)(void *handle, uint32_t value);
-	int (*get_mclk_od)(void *handle);
-	int (*set_mclk_od)(void *handle, uint32_t value);
-	int (*read_sensor)(void *handle, int idx, void *value, int *size);
-	enum amd_dpm_forced_level (*get_performance_level)(void *handle);
-	enum amd_pm_state_type (*get_current_power_state)(void *handle);
-	int (*get_fan_speed_rpm)(void *handle, uint32_t *rpm);
-	int (*get_pp_num_states)(void *handle, struct pp_states_info *data);
-	int (*get_pp_table)(void *handle, char **table);
-	int (*set_pp_table)(void *handle, const char *buf, size_t size);
-	void (*debugfs_print_current_performance_level)(void *handle, struct seq_file *m);
-
-	int (*reset_power_profile_state)(void *handle,
-			struct amd_pp_profile *request);
-	int (*get_power_profile_state)(void *handle,
-			struct amd_pp_profile *query);
-	int (*set_power_profile_state)(void *handle,
-			struct amd_pp_profile *request);
-	int (*switch_power_profile)(void *handle,
-			enum amd_pp_profile_type type);
-/* export to amdgpu */
-	void (*powergate_uvd)(void *handle, bool gate);
-	void (*powergate_vce)(void *handle, bool gate);
-	struct amd_vce_state* (*get_vce_clock_state)(void *handle, u32 idx);
-	int (*dispatch_tasks)(void *handle, enum amd_pp_task task_id,
-				   void *input, void *output);
-	int (*load_firmware)(void *handle);
-	int (*wait_for_fw_loading_complete)(void *handle);
-	int (*set_clockgating_by_smu)(void *handle, uint32_t msg_id);
-/* export to DC */
-	u32 (*get_sclk)(void *handle, bool low);
-	u32 (*get_mclk)(void *handle, bool low);
-	int (*display_configuration_change)(void *handle,
-		const struct amd_pp_display_configuration *input);
-	int (*get_display_power_level)(void *handle,
-		struct amd_pp_simple_clock_info *output);
-	int (*get_current_clocks)(void *handle,
-		struct amd_pp_clock_info *clocks);
-	int (*get_clock_by_type)(void *handle,
-		enum amd_pp_clock_type type,
-		struct amd_pp_clocks *clocks);
-	int (*get_clock_by_type_with_latency)(void *handle,
-		enum amd_pp_clock_type type,
-		struct pp_clock_levels_with_latency *clocks);
-	int (*get_clock_by_type_with_voltage)(void *handle,
-		enum amd_pp_clock_type type,
-		struct pp_clock_levels_with_voltage *clocks);
-	int (*set_watermarks_for_clocks_ranges)(void *handle,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
-	int (*display_clock_voltage_request)(void *handle,
-		struct pp_display_clock_request *clock);
-	int (*get_display_mode_validation_clocks)(void *handle,
-		struct amd_pp_simple_clock_info *clocks);
-};
-
-
 #endif /* __AMD_SHARED_H__ */
diff --git a/drivers/gpu/drm/amd/include/asic_reg/athub/athub_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/athub/athub_1_0_offset.h
new file mode 100644
index 000000000000..b1e878ecf9bf
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/athub/athub_1_0_offset.h
@@ -0,0 +1,453 @@
+/*
+ * Copyright (C) 2017  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _athub_1_0_OFFSET_HEADER
+#define _athub_1_0_OFFSET_HEADER
+
+
+
+// addressBlock: athub_atsdec
+// base address:	0x3080
+#define mmATC_ATS_CNTL	0x0000
+#define mmATC_ATS_CNTL_BASE_IDX	0
+#define mmATC_ATS_STATUS	0x0003
+#define mmATC_ATS_STATUS_BASE_IDX	0
+#define mmATC_ATS_FAULT_CNTL	0x0004
+#define mmATC_ATS_FAULT_CNTL_BASE_IDX	0
+#define mmATC_ATS_FAULT_STATUS_INFO	0x0005
+#define mmATC_ATS_FAULT_STATUS_INFO_BASE_IDX	0
+#define mmATC_ATS_FAULT_STATUS_ADDR	0x0006
+#define mmATC_ATS_FAULT_STATUS_ADDR_BASE_IDX	0
+#define mmATC_ATS_DEFAULT_PAGE_LOW	0x0007
+#define mmATC_ATS_DEFAULT_PAGE_LOW_BASE_IDX	0
+#define mmATC_TRANS_FAULT_RSPCNTRL	0x0008
+#define mmATC_TRANS_FAULT_RSPCNTRL_BASE_IDX	0
+#define mmATC_ATS_FAULT_STATUS_INFO2	0x0009
+#define mmATC_ATS_FAULT_STATUS_INFO2_BASE_IDX	0
+#define mmATHUB_MISC_CNTL	0x000a
+#define mmATHUB_MISC_CNTL_BASE_IDX	0
+#define mmATC_VMID_PASID_MAPPING_UPDATE_STATUS	0x000b
+#define mmATC_VMID_PASID_MAPPING_UPDATE_STATUS_BASE_IDX	0
+#define mmATC_VMID0_PASID_MAPPING	0x000c
+#define mmATC_VMID0_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID1_PASID_MAPPING	0x000d
+#define mmATC_VMID1_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID2_PASID_MAPPING	0x000e
+#define mmATC_VMID2_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID3_PASID_MAPPING	0x000f
+#define mmATC_VMID3_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID4_PASID_MAPPING	0x0010
+#define mmATC_VMID4_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID5_PASID_MAPPING	0x0011
+#define mmATC_VMID5_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID6_PASID_MAPPING	0x0012
+#define mmATC_VMID6_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID7_PASID_MAPPING	0x0013
+#define mmATC_VMID7_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID8_PASID_MAPPING	0x0014
+#define mmATC_VMID8_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID9_PASID_MAPPING	0x0015
+#define mmATC_VMID9_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID10_PASID_MAPPING	0x0016
+#define mmATC_VMID10_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID11_PASID_MAPPING	0x0017
+#define mmATC_VMID11_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID12_PASID_MAPPING	0x0018
+#define mmATC_VMID12_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID13_PASID_MAPPING	0x0019
+#define mmATC_VMID13_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID14_PASID_MAPPING	0x001a
+#define mmATC_VMID14_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID15_PASID_MAPPING	0x001b
+#define mmATC_VMID15_PASID_MAPPING_BASE_IDX	0
+#define mmATC_ATS_VMID_STATUS	0x001c
+#define mmATC_ATS_VMID_STATUS_BASE_IDX	0
+#define mmATC_ATS_GFX_ATCL2_STATUS	0x001d
+#define mmATC_ATS_GFX_ATCL2_STATUS_BASE_IDX	0
+#define mmATC_PERFCOUNTER0_CFG	0x001e
+#define mmATC_PERFCOUNTER0_CFG_BASE_IDX	0
+#define mmATC_PERFCOUNTER1_CFG	0x001f
+#define mmATC_PERFCOUNTER1_CFG_BASE_IDX	0
+#define mmATC_PERFCOUNTER2_CFG	0x0020
+#define mmATC_PERFCOUNTER2_CFG_BASE_IDX	0
+#define mmATC_PERFCOUNTER3_CFG	0x0021
+#define mmATC_PERFCOUNTER3_CFG_BASE_IDX	0
+#define mmATC_PERFCOUNTER_RSLT_CNTL	0x0022
+#define mmATC_PERFCOUNTER_RSLT_CNTL_BASE_IDX	0
+#define mmATC_PERFCOUNTER_LO	0x0023
+#define mmATC_PERFCOUNTER_LO_BASE_IDX	0
+#define mmATC_PERFCOUNTER_HI	0x0024
+#define mmATC_PERFCOUNTER_HI_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL	0x0025
+#define mmATHUB_PCIE_ATS_CNTL_BASE_IDX	0
+#define mmATHUB_PCIE_PASID_CNTL	0x0026
+#define mmATHUB_PCIE_PASID_CNTL_BASE_IDX	0
+#define mmATHUB_PCIE_PAGE_REQ_CNTL	0x0027
+#define mmATHUB_PCIE_PAGE_REQ_CNTL_BASE_IDX	0
+#define mmATHUB_PCIE_OUTSTAND_PAGE_REQ_ALLOC	0x0028
+#define mmATHUB_PCIE_OUTSTAND_PAGE_REQ_ALLOC_BASE_IDX	0
+#define mmATHUB_COMMAND	0x0029
+#define mmATHUB_COMMAND_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_0	0x002a
+#define mmATHUB_PCIE_ATS_CNTL_VF_0_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_1	0x002b
+#define mmATHUB_PCIE_ATS_CNTL_VF_1_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_2	0x002c
+#define mmATHUB_PCIE_ATS_CNTL_VF_2_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_3	0x002d
+#define mmATHUB_PCIE_ATS_CNTL_VF_3_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_4	0x002e
+#define mmATHUB_PCIE_ATS_CNTL_VF_4_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_5	0x002f
+#define mmATHUB_PCIE_ATS_CNTL_VF_5_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_6	0x0030
+#define mmATHUB_PCIE_ATS_CNTL_VF_6_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_7	0x0031
+#define mmATHUB_PCIE_ATS_CNTL_VF_7_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_8	0x0032
+#define mmATHUB_PCIE_ATS_CNTL_VF_8_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_9	0x0033
+#define mmATHUB_PCIE_ATS_CNTL_VF_9_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_10	0x0034
+#define mmATHUB_PCIE_ATS_CNTL_VF_10_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_11	0x0035
+#define mmATHUB_PCIE_ATS_CNTL_VF_11_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_12	0x0036
+#define mmATHUB_PCIE_ATS_CNTL_VF_12_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_13	0x0037
+#define mmATHUB_PCIE_ATS_CNTL_VF_13_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_14	0x0038
+#define mmATHUB_PCIE_ATS_CNTL_VF_14_BASE_IDX	0
+#define mmATHUB_PCIE_ATS_CNTL_VF_15	0x0039
+#define mmATHUB_PCIE_ATS_CNTL_VF_15_BASE_IDX	0
+#define mmATHUB_MEM_POWER_LS	0x003a
+#define mmATHUB_MEM_POWER_LS_BASE_IDX	0
+#define mmATS_IH_CREDIT	0x003b
+#define mmATS_IH_CREDIT_BASE_IDX	0
+#define mmATHUB_IH_CREDIT	0x003c
+#define mmATHUB_IH_CREDIT_BASE_IDX	0
+#define mmATC_VMID16_PASID_MAPPING	0x003d
+#define mmATC_VMID16_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID17_PASID_MAPPING	0x003e
+#define mmATC_VMID17_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID18_PASID_MAPPING	0x003f
+#define mmATC_VMID18_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID19_PASID_MAPPING	0x0040
+#define mmATC_VMID19_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID20_PASID_MAPPING	0x0041
+#define mmATC_VMID20_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID21_PASID_MAPPING	0x0042
+#define mmATC_VMID21_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID22_PASID_MAPPING	0x0043
+#define mmATC_VMID22_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID23_PASID_MAPPING	0x0044
+#define mmATC_VMID23_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID24_PASID_MAPPING	0x0045
+#define mmATC_VMID24_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID25_PASID_MAPPING	0x0046
+#define mmATC_VMID25_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID26_PASID_MAPPING	0x0047
+#define mmATC_VMID26_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID27_PASID_MAPPING	0x0048
+#define mmATC_VMID27_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID28_PASID_MAPPING	0x0049
+#define mmATC_VMID28_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID29_PASID_MAPPING	0x004a
+#define mmATC_VMID29_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID30_PASID_MAPPING	0x004b
+#define mmATC_VMID30_PASID_MAPPING_BASE_IDX	0
+#define mmATC_VMID31_PASID_MAPPING	0x004c
+#define mmATC_VMID31_PASID_MAPPING_BASE_IDX	0
+#define mmATC_ATS_MMHUB_ATCL2_STATUS	0x004d
+#define mmATC_ATS_MMHUB_ATCL2_STATUS_BASE_IDX	0
+#define mmATHUB_SHARED_VIRT_RESET_REQ	0x004e
+#define mmATHUB_SHARED_VIRT_RESET_REQ_BASE_IDX	0
+#define mmATHUB_SHARED_ACTIVE_FCN_ID	0x004f
+#define mmATHUB_SHARED_ACTIVE_FCN_ID_BASE_IDX	0
+#define mmATC_ATS_SDPPORT_CNTL	0x0050
+#define mmATC_ATS_SDPPORT_CNTL_BASE_IDX	0
+#define mmATC_ATS_VMID_SNAPSHOT_GFX_STAT	0x0052
+#define mmATC_ATS_VMID_SNAPSHOT_GFX_STAT_BASE_IDX	0
+#define mmATC_ATS_VMID_SNAPSHOT_MMHUB_STAT	0x0053
+#define mmATC_ATS_VMID_SNAPSHOT_MMHUB_STAT_BASE_IDX	0
+
+
+// addressBlock: athub_xpbdec
+// base address:	0x31f0
+#define mmXPB_RTR_SRC_APRTR0	0x005c
+#define mmXPB_RTR_SRC_APRTR0_BASE_IDX	0
+#define mmXPB_RTR_SRC_APRTR1	0x005d
+#define mmXPB_RTR_SRC_APRTR1_BASE_IDX	0
+#define mmXPB_RTR_SRC_APRTR2	0x005e
+#define mmXPB_RTR_SRC_APRTR2_BASE_IDX	0
+#define mmXPB_RTR_SRC_APRTR3	0x005f
+#define mmXPB_RTR_SRC_APRTR3_BASE_IDX	0
+#define mmXPB_RTR_SRC_APRTR4	0x0060
+#define mmXPB_RTR_SRC_APRTR4_BASE_IDX	0
+#define mmXPB_RTR_SRC_APRTR5	0x0061
+#define mmXPB_RTR_SRC_APRTR5_BASE_IDX	0
+#define mmXPB_RTR_SRC_APRTR6	0x0062
+#define mmXPB_RTR_SRC_APRTR6_BASE_IDX	0
+#define mmXPB_RTR_SRC_APRTR7	0x0063
+#define mmXPB_RTR_SRC_APRTR7_BASE_IDX	0
+#define mmXPB_RTR_SRC_APRTR8	0x0064
+#define mmXPB_RTR_SRC_APRTR8_BASE_IDX	0
+#define mmXPB_RTR_SRC_APRTR9	0x0065
+#define mmXPB_RTR_SRC_APRTR9_BASE_IDX	0
+#define mmXPB_XDMA_RTR_SRC_APRTR0	0x0066
+#define mmXPB_XDMA_RTR_SRC_APRTR0_BASE_IDX	0
+#define mmXPB_XDMA_RTR_SRC_APRTR1	0x0067
+#define mmXPB_XDMA_RTR_SRC_APRTR1_BASE_IDX	0
+#define mmXPB_XDMA_RTR_SRC_APRTR2	0x0068
+#define mmXPB_XDMA_RTR_SRC_APRTR2_BASE_IDX	0
+#define mmXPB_XDMA_RTR_SRC_APRTR3	0x0069
+#define mmXPB_XDMA_RTR_SRC_APRTR3_BASE_IDX	0
+#define mmXPB_RTR_DEST_MAP0	0x006a
+#define mmXPB_RTR_DEST_MAP0_BASE_IDX	0
+#define mmXPB_RTR_DEST_MAP1	0x006b
+#define mmXPB_RTR_DEST_MAP1_BASE_IDX	0
+#define mmXPB_RTR_DEST_MAP2	0x006c
+#define mmXPB_RTR_DEST_MAP2_BASE_IDX	0
+#define mmXPB_RTR_DEST_MAP3	0x006d
+#define mmXPB_RTR_DEST_MAP3_BASE_IDX	0
+#define mmXPB_RTR_DEST_MAP4	0x006e
+#define mmXPB_RTR_DEST_MAP4_BASE_IDX	0
+#define mmXPB_RTR_DEST_MAP5	0x006f
+#define mmXPB_RTR_DEST_MAP5_BASE_IDX	0
+#define mmXPB_RTR_DEST_MAP6	0x0070
+#define mmXPB_RTR_DEST_MAP6_BASE_IDX	0
+#define mmXPB_RTR_DEST_MAP7	0x0071
+#define mmXPB_RTR_DEST_MAP7_BASE_IDX	0
+#define mmXPB_RTR_DEST_MAP8	0x0072
+#define mmXPB_RTR_DEST_MAP8_BASE_IDX	0
+#define mmXPB_RTR_DEST_MAP9	0x0073
+#define mmXPB_RTR_DEST_MAP9_BASE_IDX	0
+#define mmXPB_XDMA_RTR_DEST_MAP0	0x0074
+#define mmXPB_XDMA_RTR_DEST_MAP0_BASE_IDX	0
+#define mmXPB_XDMA_RTR_DEST_MAP1	0x0075
+#define mmXPB_XDMA_RTR_DEST_MAP1_BASE_IDX	0
+#define mmXPB_XDMA_RTR_DEST_MAP2	0x0076
+#define mmXPB_XDMA_RTR_DEST_MAP2_BASE_IDX	0
+#define mmXPB_XDMA_RTR_DEST_MAP3	0x0077
+#define mmXPB_XDMA_RTR_DEST_MAP3_BASE_IDX	0
+#define mmXPB_CLG_CFG0	0x0078
+#define mmXPB_CLG_CFG0_BASE_IDX	0
+#define mmXPB_CLG_CFG1	0x0079
+#define mmXPB_CLG_CFG1_BASE_IDX	0
+#define mmXPB_CLG_CFG2	0x007a
+#define mmXPB_CLG_CFG2_BASE_IDX	0
+#define mmXPB_CLG_CFG3	0x007b
+#define mmXPB_CLG_CFG3_BASE_IDX	0
+#define mmXPB_CLG_CFG4	0x007c
+#define mmXPB_CLG_CFG4_BASE_IDX	0
+#define mmXPB_CLG_CFG5	0x007d
+#define mmXPB_CLG_CFG5_BASE_IDX	0
+#define mmXPB_CLG_CFG6	0x007e
+#define mmXPB_CLG_CFG6_BASE_IDX	0
+#define mmXPB_CLG_CFG7	0x007f
+#define mmXPB_CLG_CFG7_BASE_IDX	0
+#define mmXPB_CLG_EXTRA	0x0080
+#define mmXPB_CLG_EXTRA_BASE_IDX	0
+#define mmXPB_CLG_EXTRA_MSK	0x0081
+#define mmXPB_CLG_EXTRA_MSK_BASE_IDX	0
+#define mmXPB_LB_ADDR	0x0082
+#define mmXPB_LB_ADDR_BASE_IDX	0
+#define mmXPB_WCB_STS	0x0083
+#define mmXPB_WCB_STS_BASE_IDX	0
+#define mmXPB_HST_CFG	0x0084
+#define mmXPB_HST_CFG_BASE_IDX	0
+#define mmXPB_P2P_BAR_CFG	0x0085
+#define mmXPB_P2P_BAR_CFG_BASE_IDX	0
+#define mmXPB_P2P_BAR0	0x0086
+#define mmXPB_P2P_BAR0_BASE_IDX	0
+#define mmXPB_P2P_BAR1	0x0087
+#define mmXPB_P2P_BAR1_BASE_IDX	0
+#define mmXPB_P2P_BAR2	0x0088
+#define mmXPB_P2P_BAR2_BASE_IDX	0
+#define mmXPB_P2P_BAR3	0x0089
+#define mmXPB_P2P_BAR3_BASE_IDX	0
+#define mmXPB_P2P_BAR4	0x008a
+#define mmXPB_P2P_BAR4_BASE_IDX	0
+#define mmXPB_P2P_BAR5	0x008b
+#define mmXPB_P2P_BAR5_BASE_IDX	0
+#define mmXPB_P2P_BAR6	0x008c
+#define mmXPB_P2P_BAR6_BASE_IDX	0
+#define mmXPB_P2P_BAR7	0x008d
+#define mmXPB_P2P_BAR7_BASE_IDX	0
+#define mmXPB_P2P_BAR_SETUP	0x008e
+#define mmXPB_P2P_BAR_SETUP_BASE_IDX	0
+#define mmXPB_P2P_BAR_DELTA_ABOVE	0x0090
+#define mmXPB_P2P_BAR_DELTA_ABOVE_BASE_IDX	0
+#define mmXPB_P2P_BAR_DELTA_BELOW	0x0091
+#define mmXPB_P2P_BAR_DELTA_BELOW_BASE_IDX	0
+#define mmXPB_PEER_SYS_BAR0	0x0092
+#define mmXPB_PEER_SYS_BAR0_BASE_IDX	0
+#define mmXPB_PEER_SYS_BAR1	0x0093
+#define mmXPB_PEER_SYS_BAR1_BASE_IDX	0
+#define mmXPB_PEER_SYS_BAR2	0x0094
+#define mmXPB_PEER_SYS_BAR2_BASE_IDX	0
+#define mmXPB_PEER_SYS_BAR3	0x0095
+#define mmXPB_PEER_SYS_BAR3_BASE_IDX	0
+#define mmXPB_PEER_SYS_BAR4	0x0096
+#define mmXPB_PEER_SYS_BAR4_BASE_IDX	0
+#define mmXPB_PEER_SYS_BAR5	0x0097
+#define mmXPB_PEER_SYS_BAR5_BASE_IDX	0
+#define mmXPB_PEER_SYS_BAR6	0x0098
+#define mmXPB_PEER_SYS_BAR6_BASE_IDX	0
+#define mmXPB_PEER_SYS_BAR7	0x0099
+#define mmXPB_PEER_SYS_BAR7_BASE_IDX	0
+#define mmXPB_PEER_SYS_BAR8	0x009a
+#define mmXPB_PEER_SYS_BAR8_BASE_IDX	0
+#define mmXPB_PEER_SYS_BAR9	0x009b
+#define mmXPB_PEER_SYS_BAR9_BASE_IDX	0
+#define mmXPB_XDMA_PEER_SYS_BAR0	0x009c
+#define mmXPB_XDMA_PEER_SYS_BAR0_BASE_IDX	0
+#define mmXPB_XDMA_PEER_SYS_BAR1	0x009d
+#define mmXPB_XDMA_PEER_SYS_BAR1_BASE_IDX	0
+#define mmXPB_XDMA_PEER_SYS_BAR2	0x009e
+#define mmXPB_XDMA_PEER_SYS_BAR2_BASE_IDX	0
+#define mmXPB_XDMA_PEER_SYS_BAR3	0x009f
+#define mmXPB_XDMA_PEER_SYS_BAR3_BASE_IDX	0
+#define mmXPB_CLK_GAT	0x00a0
+#define mmXPB_CLK_GAT_BASE_IDX	0
+#define mmXPB_INTF_CFG	0x00a1
+#define mmXPB_INTF_CFG_BASE_IDX	0
+#define mmXPB_INTF_STS	0x00a2
+#define mmXPB_INTF_STS_BASE_IDX	0
+#define mmXPB_PIPE_STS	0x00a3
+#define mmXPB_PIPE_STS_BASE_IDX	0
+#define mmXPB_SUB_CTRL	0x00a4
+#define mmXPB_SUB_CTRL_BASE_IDX	0
+#define mmXPB_MAP_INVERT_FLUSH_NUM_LSB	0x00a5
+#define mmXPB_MAP_INVERT_FLUSH_NUM_LSB_BASE_IDX	0
+#define mmXPB_PERF_KNOBS	0x00a6
+#define mmXPB_PERF_KNOBS_BASE_IDX	0
+#define mmXPB_STICKY	0x00a7
+#define mmXPB_STICKY_BASE_IDX	0
+#define mmXPB_STICKY_W1C	0x00a8
+#define mmXPB_STICKY_W1C_BASE_IDX	0
+#define mmXPB_MISC_CFG	0x00a9
+#define mmXPB_MISC_CFG_BASE_IDX	0
+#define mmXPB_INTF_CFG2	0x00aa
+#define mmXPB_INTF_CFG2_BASE_IDX	0
+#define mmXPB_CLG_EXTRA_RD	0x00ab
+#define mmXPB_CLG_EXTRA_RD_BASE_IDX	0
+#define mmXPB_CLG_EXTRA_MSK_RD	0x00ac
+#define mmXPB_CLG_EXTRA_MSK_RD_BASE_IDX	0
+#define mmXPB_CLG_GFX_MATCH	0x00ad
+#define mmXPB_CLG_GFX_MATCH_BASE_IDX	0
+#define mmXPB_CLG_GFX_MATCH_MSK	0x00ae
+#define mmXPB_CLG_GFX_MATCH_MSK_BASE_IDX	0
+#define mmXPB_CLG_MM_MATCH	0x00af
+#define mmXPB_CLG_MM_MATCH_BASE_IDX	0
+#define mmXPB_CLG_MM_MATCH_MSK	0x00b0
+#define mmXPB_CLG_MM_MATCH_MSK_BASE_IDX	0
+#define mmXPB_CLG_GFX_UNITID_MAPPING0	0x00b1
+#define mmXPB_CLG_GFX_UNITID_MAPPING0_BASE_IDX	0
+#define mmXPB_CLG_GFX_UNITID_MAPPING1	0x00b2
+#define mmXPB_CLG_GFX_UNITID_MAPPING1_BASE_IDX	0
+#define mmXPB_CLG_GFX_UNITID_MAPPING2	0x00b3
+#define mmXPB_CLG_GFX_UNITID_MAPPING2_BASE_IDX	0
+#define mmXPB_CLG_GFX_UNITID_MAPPING3	0x00b4
+#define mmXPB_CLG_GFX_UNITID_MAPPING3_BASE_IDX	0
+#define mmXPB_CLG_GFX_UNITID_MAPPING4	0x00b5
+#define mmXPB_CLG_GFX_UNITID_MAPPING4_BASE_IDX	0
+#define mmXPB_CLG_GFX_UNITID_MAPPING5	0x00b6
+#define mmXPB_CLG_GFX_UNITID_MAPPING5_BASE_IDX	0
+#define mmXPB_CLG_GFX_UNITID_MAPPING6	0x00b7
+#define mmXPB_CLG_GFX_UNITID_MAPPING6_BASE_IDX	0
+#define mmXPB_CLG_GFX_UNITID_MAPPING7	0x00b8
+#define mmXPB_CLG_GFX_UNITID_MAPPING7_BASE_IDX	0
+#define mmXPB_CLG_MM_UNITID_MAPPING0	0x00b9
+#define mmXPB_CLG_MM_UNITID_MAPPING0_BASE_IDX	0
+#define mmXPB_CLG_MM_UNITID_MAPPING1	0x00ba
+#define mmXPB_CLG_MM_UNITID_MAPPING1_BASE_IDX	0
+#define mmXPB_CLG_MM_UNITID_MAPPING2	0x00bb
+#define mmXPB_CLG_MM_UNITID_MAPPING2_BASE_IDX	0
+#define mmXPB_CLG_MM_UNITID_MAPPING3	0x00bc
+#define mmXPB_CLG_MM_UNITID_MAPPING3_BASE_IDX	0
+
+
+// addressBlock: athub_rpbdec
+// base address:	0x33b0
+#define mmRPB_PASSPW_CONF	0x00cc
+#define mmRPB_PASSPW_CONF_BASE_IDX	0
+#define mmRPB_BLOCKLEVEL_CONF	0x00cd
+#define mmRPB_BLOCKLEVEL_CONF_BASE_IDX	0
+#define mmRPB_TAG_CONF	0x00cf
+#define mmRPB_TAG_CONF_BASE_IDX	0
+#define mmRPB_EFF_CNTL	0x00d1
+#define mmRPB_EFF_CNTL_BASE_IDX	0
+#define mmRPB_ARB_CNTL	0x00d2
+#define mmRPB_ARB_CNTL_BASE_IDX	0
+#define mmRPB_ARB_CNTL2	0x00d3
+#define mmRPB_ARB_CNTL2_BASE_IDX	0
+#define mmRPB_BIF_CNTL	0x00d4
+#define mmRPB_BIF_CNTL_BASE_IDX	0
+#define mmRPB_WR_SWITCH_CNTL	0x00d5
+#define mmRPB_WR_SWITCH_CNTL_BASE_IDX	0
+#define mmRPB_RD_SWITCH_CNTL	0x00d7
+#define mmRPB_RD_SWITCH_CNTL_BASE_IDX	0
+#define mmRPB_CID_QUEUE_WR	0x00d8
+#define mmRPB_CID_QUEUE_WR_BASE_IDX	0
+#define mmRPB_CID_QUEUE_RD	0x00d9
+#define mmRPB_CID_QUEUE_RD_BASE_IDX	0
+#define mmRPB_CID_QUEUE_EX	0x00dc
+#define mmRPB_CID_QUEUE_EX_BASE_IDX	0
+#define mmRPB_CID_QUEUE_EX_DATA	0x00dd
+#define mmRPB_CID_QUEUE_EX_DATA_BASE_IDX	0
+#define mmRPB_SWITCH_CNTL2	0x00de
+#define mmRPB_SWITCH_CNTL2_BASE_IDX	0
+#define mmRPB_DEINTRLV_COMBINE_CNTL	0x00df
+#define mmRPB_DEINTRLV_COMBINE_CNTL_BASE_IDX	0
+#define mmRPB_VC_SWITCH_RDWR	0x00e0
+#define mmRPB_VC_SWITCH_RDWR_BASE_IDX	0
+#define mmRPB_PERFCOUNTER_LO	0x00e1
+#define mmRPB_PERFCOUNTER_LO_BASE_IDX	0
+#define mmRPB_PERFCOUNTER_HI	0x00e2
+#define mmRPB_PERFCOUNTER_HI_BASE_IDX	0
+#define mmRPB_PERFCOUNTER0_CFG	0x00e3
+#define mmRPB_PERFCOUNTER0_CFG_BASE_IDX	0
+#define mmRPB_PERFCOUNTER1_CFG	0x00e4
+#define mmRPB_PERFCOUNTER1_CFG_BASE_IDX	0
+#define mmRPB_PERFCOUNTER2_CFG	0x00e5
+#define mmRPB_PERFCOUNTER2_CFG_BASE_IDX	0
+#define mmRPB_PERFCOUNTER3_CFG	0x00e6
+#define mmRPB_PERFCOUNTER3_CFG_BASE_IDX	0
+#define mmRPB_PERFCOUNTER_RSLT_CNTL	0x00e7
+#define mmRPB_PERFCOUNTER_RSLT_CNTL_BASE_IDX	0
+#define mmRPB_RD_QUEUE_CNTL	0x00e9
+#define mmRPB_RD_QUEUE_CNTL_BASE_IDX	0
+#define mmRPB_RD_QUEUE_CNTL2	0x00ea
+#define mmRPB_RD_QUEUE_CNTL2_BASE_IDX	0
+#define mmRPB_WR_QUEUE_CNTL	0x00eb
+#define mmRPB_WR_QUEUE_CNTL_BASE_IDX	0
+#define mmRPB_WR_QUEUE_CNTL2	0x00ec
+#define mmRPB_WR_QUEUE_CNTL2_BASE_IDX	0
+#define mmRPB_EA_QUEUE_WR	0x00ed
+#define mmRPB_EA_QUEUE_WR_BASE_IDX	0
+#define mmRPB_ATS_CNTL	0x00ee
+#define mmRPB_ATS_CNTL_BASE_IDX	0
+#define mmRPB_ATS_CNTL2	0x00ef
+#define mmRPB_ATS_CNTL2_BASE_IDX	0
+#define mmRPB_SDPPORT_CNTL	0x00f0
+#define mmRPB_SDPPORT_CNTL_BASE_IDX	0
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/athub/athub_1_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/athub/athub_1_0_sh_mask.h
new file mode 100644
index 000000000000..2968c6e2f7b9
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/athub/athub_1_0_sh_mask.h
@@ -0,0 +1,2045 @@
+/*
+ * Copyright (C) 2017  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _athub_1_0_SH_MASK_HEADER
+#define _athub_1_0_SH_MASK_HEADER
+
+
+// addressBlock: athub_atsdec
+//ATC_ATS_CNTL
+#define ATC_ATS_CNTL__DISABLE_ATC__SHIFT	0x0
+#define ATC_ATS_CNTL__DISABLE_PRI__SHIFT	0x1
+#define ATC_ATS_CNTL__DISABLE_PASID__SHIFT	0x2
+#define ATC_ATS_CNTL__CREDITS_ATS_RPB__SHIFT	0x8
+#define ATC_ATS_CNTL__INVALIDATION_LOG_KEEP_ORDER__SHIFT	0x14
+#define ATC_ATS_CNTL__TRANS_LOG_KEEP_ORDER__SHIFT	0x15
+#define ATC_ATS_CNTL__TRANS_EXE_RETURN__SHIFT	0x16
+#define ATC_ATS_CNTL__DISABLE_ATC_MASK	0x00000001L
+#define ATC_ATS_CNTL__DISABLE_PRI_MASK	0x00000002L
+#define ATC_ATS_CNTL__DISABLE_PASID_MASK	0x00000004L
+#define ATC_ATS_CNTL__CREDITS_ATS_RPB_MASK	0x00003F00L
+#define ATC_ATS_CNTL__INVALIDATION_LOG_KEEP_ORDER_MASK	0x00100000L
+#define ATC_ATS_CNTL__TRANS_LOG_KEEP_ORDER_MASK	0x00200000L
+#define ATC_ATS_CNTL__TRANS_EXE_RETURN_MASK	0x00C00000L
+//ATC_ATS_STATUS
+#define ATC_ATS_STATUS__BUSY__SHIFT	0x0
+#define ATC_ATS_STATUS__CRASHED__SHIFT	0x1
+#define ATC_ATS_STATUS__DEADLOCK_DETECTION__SHIFT	0x2
+#define ATC_ATS_STATUS__FLUSH_INVALIDATION_OUTSTANDING__SHIFT	0x3
+#define ATC_ATS_STATUS__NONFLUSH_INVALIDATION_OUTSTANDING__SHIFT	0x6
+#define ATC_ATS_STATUS__BUSY_MASK	0x00000001L
+#define ATC_ATS_STATUS__CRASHED_MASK	0x00000002L
+#define ATC_ATS_STATUS__DEADLOCK_DETECTION_MASK	0x00000004L
+#define ATC_ATS_STATUS__FLUSH_INVALIDATION_OUTSTANDING_MASK	0x00000038L
+#define ATC_ATS_STATUS__NONFLUSH_INVALIDATION_OUTSTANDING_MASK	0x000001C0L
+//ATC_ATS_FAULT_CNTL
+#define ATC_ATS_FAULT_CNTL__FAULT_REGISTER_LOG__SHIFT	0x0
+#define ATC_ATS_FAULT_CNTL__FAULT_INTERRUPT_TABLE__SHIFT	0xa
+#define ATC_ATS_FAULT_CNTL__FAULT_CRASH_TABLE__SHIFT	0x14
+#define ATC_ATS_FAULT_CNTL__FAULT_REGISTER_LOG_MASK	0x000001FFL
+#define ATC_ATS_FAULT_CNTL__FAULT_INTERRUPT_TABLE_MASK	0x0007FC00L
+#define ATC_ATS_FAULT_CNTL__FAULT_CRASH_TABLE_MASK	0x1FF00000L
+//ATC_ATS_FAULT_STATUS_INFO
+#define ATC_ATS_FAULT_STATUS_INFO__FAULT_TYPE__SHIFT	0x0
+#define ATC_ATS_FAULT_STATUS_INFO__VMID__SHIFT	0xa
+#define ATC_ATS_FAULT_STATUS_INFO__EXTRA_INFO__SHIFT	0xf
+#define ATC_ATS_FAULT_STATUS_INFO__EXTRA_INFO2__SHIFT	0x10
+#define ATC_ATS_FAULT_STATUS_INFO__INVALIDATION__SHIFT	0x11
+#define ATC_ATS_FAULT_STATUS_INFO__PAGE_REQUEST__SHIFT	0x12
+#define ATC_ATS_FAULT_STATUS_INFO__STATUS__SHIFT	0x13
+#define ATC_ATS_FAULT_STATUS_INFO__PAGE_ADDR_HIGH__SHIFT	0x18
+#define ATC_ATS_FAULT_STATUS_INFO__FAULT_TYPE_MASK	0x000001FFL
+#define ATC_ATS_FAULT_STATUS_INFO__VMID_MASK	0x00007C00L
+#define ATC_ATS_FAULT_STATUS_INFO__EXTRA_INFO_MASK	0x00008000L
+#define ATC_ATS_FAULT_STATUS_INFO__EXTRA_INFO2_MASK	0x00010000L
+#define ATC_ATS_FAULT_STATUS_INFO__INVALIDATION_MASK	0x00020000L
+#define ATC_ATS_FAULT_STATUS_INFO__PAGE_REQUEST_MASK	0x00040000L
+#define ATC_ATS_FAULT_STATUS_INFO__STATUS_MASK	0x00F80000L
+#define ATC_ATS_FAULT_STATUS_INFO__PAGE_ADDR_HIGH_MASK	0x0F000000L
+//ATC_ATS_FAULT_STATUS_ADDR
+#define ATC_ATS_FAULT_STATUS_ADDR__PAGE_ADDR__SHIFT	0x0
+#define ATC_ATS_FAULT_STATUS_ADDR__PAGE_ADDR_MASK	0xFFFFFFFFL
+//ATC_ATS_DEFAULT_PAGE_LOW
+#define ATC_ATS_DEFAULT_PAGE_LOW__DEFAULT_PAGE__SHIFT	0x0
+#define ATC_ATS_DEFAULT_PAGE_LOW__DEFAULT_PAGE_MASK	0xFFFFFFFFL
+//ATC_TRANS_FAULT_RSPCNTRL
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID0__SHIFT	0x0
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID1__SHIFT	0x1
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID2__SHIFT	0x2
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID3__SHIFT	0x3
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID4__SHIFT	0x4
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID5__SHIFT	0x5
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID6__SHIFT	0x6
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID7__SHIFT	0x7
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID8__SHIFT	0x8
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID9__SHIFT	0x9
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID10__SHIFT	0xa
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID11__SHIFT	0xb
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID12__SHIFT	0xc
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID13__SHIFT	0xd
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID14__SHIFT	0xe
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID15__SHIFT	0xf
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID16__SHIFT	0x10
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID17__SHIFT	0x11
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID18__SHIFT	0x12
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID19__SHIFT	0x13
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID20__SHIFT	0x14
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID21__SHIFT	0x15
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID22__SHIFT	0x16
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID23__SHIFT	0x17
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID24__SHIFT	0x18
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID25__SHIFT	0x19
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID26__SHIFT	0x1a
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID27__SHIFT	0x1b
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID28__SHIFT	0x1c
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID29__SHIFT	0x1d
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID30__SHIFT	0x1e
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID31__SHIFT	0x1f
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID0_MASK	0x00000001L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID1_MASK	0x00000002L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID2_MASK	0x00000004L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID3_MASK	0x00000008L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID4_MASK	0x00000010L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID5_MASK	0x00000020L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID6_MASK	0x00000040L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID7_MASK	0x00000080L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID8_MASK	0x00000100L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID9_MASK	0x00000200L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID10_MASK	0x00000400L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID11_MASK	0x00000800L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID12_MASK	0x00001000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID13_MASK	0x00002000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID14_MASK	0x00004000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID15_MASK	0x00008000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID16_MASK	0x00010000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID17_MASK	0x00020000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID18_MASK	0x00040000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID19_MASK	0x00080000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID20_MASK	0x00100000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID21_MASK	0x00200000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID22_MASK	0x00400000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID23_MASK	0x00800000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID24_MASK	0x01000000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID25_MASK	0x02000000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID26_MASK	0x04000000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID27_MASK	0x08000000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID28_MASK	0x10000000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID29_MASK	0x20000000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID30_MASK	0x40000000L
+#define ATC_TRANS_FAULT_RSPCNTRL__VMID31_MASK	0x80000000L
+//ATC_ATS_FAULT_STATUS_INFO2
+#define ATC_ATS_FAULT_STATUS_INFO2__VF__SHIFT	0x0
+#define ATC_ATS_FAULT_STATUS_INFO2__VFID__SHIFT	0x1
+#define ATC_ATS_FAULT_STATUS_INFO2__MMHUB_INV_VMID__SHIFT	0x9
+#define ATC_ATS_FAULT_STATUS_INFO2__VF_MASK	0x00000001L
+#define ATC_ATS_FAULT_STATUS_INFO2__VFID_MASK	0x0000001EL
+#define ATC_ATS_FAULT_STATUS_INFO2__MMHUB_INV_VMID_MASK	0x00003E00L
+//ATHUB_MISC_CNTL
+#define ATHUB_MISC_CNTL__CG_OFFDLY__SHIFT	0x6
+#define ATHUB_MISC_CNTL__CG_ENABLE__SHIFT	0x12
+#define ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE__SHIFT	0x13
+#define ATHUB_MISC_CNTL__PG_ENABLE__SHIFT	0x14
+#define ATHUB_MISC_CNTL__PG_OFFDLY__SHIFT	0x15
+#define ATHUB_MISC_CNTL__CG_STATUS__SHIFT	0x1b
+#define ATHUB_MISC_CNTL__PG_STATUS__SHIFT	0x1c
+#define ATHUB_MISC_CNTL__CG_OFFDLY_MASK	0x00000FC0L
+#define ATHUB_MISC_CNTL__CG_ENABLE_MASK	0x00040000L
+#define ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK	0x00080000L
+#define ATHUB_MISC_CNTL__PG_ENABLE_MASK	0x00100000L
+#define ATHUB_MISC_CNTL__PG_OFFDLY_MASK	0x07E00000L
+#define ATHUB_MISC_CNTL__CG_STATUS_MASK	0x08000000L
+#define ATHUB_MISC_CNTL__PG_STATUS_MASK	0x10000000L
+//ATC_VMID_PASID_MAPPING_UPDATE_STATUS
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID0_REMAPPING_FINISHED__SHIFT	0x0
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID1_REMAPPING_FINISHED__SHIFT	0x1
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID2_REMAPPING_FINISHED__SHIFT	0x2
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID3_REMAPPING_FINISHED__SHIFT	0x3
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID4_REMAPPING_FINISHED__SHIFT	0x4
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID5_REMAPPING_FINISHED__SHIFT	0x5
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID6_REMAPPING_FINISHED__SHIFT	0x6
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID7_REMAPPING_FINISHED__SHIFT	0x7
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID8_REMAPPING_FINISHED__SHIFT	0x8
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID9_REMAPPING_FINISHED__SHIFT	0x9
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID10_REMAPPING_FINISHED__SHIFT	0xa
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID11_REMAPPING_FINISHED__SHIFT	0xb
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID12_REMAPPING_FINISHED__SHIFT	0xc
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID13_REMAPPING_FINISHED__SHIFT	0xd
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID14_REMAPPING_FINISHED__SHIFT	0xe
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID15_REMAPPING_FINISHED__SHIFT	0xf
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID16_REMAPPING_FINISHED__SHIFT	0x10
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID17_REMAPPING_FINISHED__SHIFT	0x11
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID18_REMAPPING_FINISHED__SHIFT	0x12
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID19_REMAPPING_FINISHED__SHIFT	0x13
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID20_REMAPPING_FINISHED__SHIFT	0x14
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID21_REMAPPING_FINISHED__SHIFT	0x15
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID22_REMAPPING_FINISHED__SHIFT	0x16
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID23_REMAPPING_FINISHED__SHIFT	0x17
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID24_REMAPPING_FINISHED__SHIFT	0x18
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID25_REMAPPING_FINISHED__SHIFT	0x19
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID26_REMAPPING_FINISHED__SHIFT	0x1a
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID27_REMAPPING_FINISHED__SHIFT	0x1b
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID28_REMAPPING_FINISHED__SHIFT	0x1c
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID29_REMAPPING_FINISHED__SHIFT	0x1d
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID30_REMAPPING_FINISHED__SHIFT	0x1e
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID31_REMAPPING_FINISHED__SHIFT	0x1f
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID0_REMAPPING_FINISHED_MASK	0x00000001L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID1_REMAPPING_FINISHED_MASK	0x00000002L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID2_REMAPPING_FINISHED_MASK	0x00000004L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID3_REMAPPING_FINISHED_MASK	0x00000008L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID4_REMAPPING_FINISHED_MASK	0x00000010L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID5_REMAPPING_FINISHED_MASK	0x00000020L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID6_REMAPPING_FINISHED_MASK	0x00000040L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID7_REMAPPING_FINISHED_MASK	0x00000080L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID8_REMAPPING_FINISHED_MASK	0x00000100L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID9_REMAPPING_FINISHED_MASK	0x00000200L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID10_REMAPPING_FINISHED_MASK	0x00000400L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID11_REMAPPING_FINISHED_MASK	0x00000800L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID12_REMAPPING_FINISHED_MASK	0x00001000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID13_REMAPPING_FINISHED_MASK	0x00002000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID14_REMAPPING_FINISHED_MASK	0x00004000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID15_REMAPPING_FINISHED_MASK	0x00008000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID16_REMAPPING_FINISHED_MASK	0x00010000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID17_REMAPPING_FINISHED_MASK	0x00020000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID18_REMAPPING_FINISHED_MASK	0x00040000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID19_REMAPPING_FINISHED_MASK	0x00080000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID20_REMAPPING_FINISHED_MASK	0x00100000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID21_REMAPPING_FINISHED_MASK	0x00200000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID22_REMAPPING_FINISHED_MASK	0x00400000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID23_REMAPPING_FINISHED_MASK	0x00800000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID24_REMAPPING_FINISHED_MASK	0x01000000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID25_REMAPPING_FINISHED_MASK	0x02000000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID26_REMAPPING_FINISHED_MASK	0x04000000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID27_REMAPPING_FINISHED_MASK	0x08000000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID28_REMAPPING_FINISHED_MASK	0x10000000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID29_REMAPPING_FINISHED_MASK	0x20000000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID30_REMAPPING_FINISHED_MASK	0x40000000L
+#define ATC_VMID_PASID_MAPPING_UPDATE_STATUS__VMID31_REMAPPING_FINISHED_MASK	0x80000000L
+//ATC_VMID0_PASID_MAPPING
+#define ATC_VMID0_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID0_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID0_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID0_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID0_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID0_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID1_PASID_MAPPING
+#define ATC_VMID1_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID1_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID1_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID1_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID1_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID1_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID2_PASID_MAPPING
+#define ATC_VMID2_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID2_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID2_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID2_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID2_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID2_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID3_PASID_MAPPING
+#define ATC_VMID3_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID3_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID3_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID3_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID3_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID3_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID4_PASID_MAPPING
+#define ATC_VMID4_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID4_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID4_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID4_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID4_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID4_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID5_PASID_MAPPING
+#define ATC_VMID5_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID5_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID5_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID5_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID5_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID5_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID6_PASID_MAPPING
+#define ATC_VMID6_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID6_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID6_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID6_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID6_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID6_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID7_PASID_MAPPING
+#define ATC_VMID7_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID7_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID7_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID7_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID7_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID7_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID8_PASID_MAPPING
+#define ATC_VMID8_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID8_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID8_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID8_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID8_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID8_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID9_PASID_MAPPING
+#define ATC_VMID9_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID9_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID9_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID9_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID9_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID9_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID10_PASID_MAPPING
+#define ATC_VMID10_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID10_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID10_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID10_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID10_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID10_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID11_PASID_MAPPING
+#define ATC_VMID11_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID11_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID11_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID11_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID11_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID11_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID12_PASID_MAPPING
+#define ATC_VMID12_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID12_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID12_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID12_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID12_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID12_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID13_PASID_MAPPING
+#define ATC_VMID13_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID13_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID13_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID13_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID13_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID13_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID14_PASID_MAPPING
+#define ATC_VMID14_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID14_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID14_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID14_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID14_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID14_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID15_PASID_MAPPING
+#define ATC_VMID15_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID15_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID15_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID15_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID15_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID15_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_ATS_VMID_STATUS
+#define ATC_ATS_VMID_STATUS__VMID0_OUTSTANDING__SHIFT	0x0
+#define ATC_ATS_VMID_STATUS__VMID1_OUTSTANDING__SHIFT	0x1
+#define ATC_ATS_VMID_STATUS__VMID2_OUTSTANDING__SHIFT	0x2
+#define ATC_ATS_VMID_STATUS__VMID3_OUTSTANDING__SHIFT	0x3
+#define ATC_ATS_VMID_STATUS__VMID4_OUTSTANDING__SHIFT	0x4
+#define ATC_ATS_VMID_STATUS__VMID5_OUTSTANDING__SHIFT	0x5
+#define ATC_ATS_VMID_STATUS__VMID6_OUTSTANDING__SHIFT	0x6
+#define ATC_ATS_VMID_STATUS__VMID7_OUTSTANDING__SHIFT	0x7
+#define ATC_ATS_VMID_STATUS__VMID8_OUTSTANDING__SHIFT	0x8
+#define ATC_ATS_VMID_STATUS__VMID9_OUTSTANDING__SHIFT	0x9
+#define ATC_ATS_VMID_STATUS__VMID10_OUTSTANDING__SHIFT	0xa
+#define ATC_ATS_VMID_STATUS__VMID11_OUTSTANDING__SHIFT	0xb
+#define ATC_ATS_VMID_STATUS__VMID12_OUTSTANDING__SHIFT	0xc
+#define ATC_ATS_VMID_STATUS__VMID13_OUTSTANDING__SHIFT	0xd
+#define ATC_ATS_VMID_STATUS__VMID14_OUTSTANDING__SHIFT	0xe
+#define ATC_ATS_VMID_STATUS__VMID15_OUTSTANDING__SHIFT	0xf
+#define ATC_ATS_VMID_STATUS__VMID16_OUTSTANDING__SHIFT	0x10
+#define ATC_ATS_VMID_STATUS__VMID17_OUTSTANDING__SHIFT	0x11
+#define ATC_ATS_VMID_STATUS__VMID18_OUTSTANDING__SHIFT	0x12
+#define ATC_ATS_VMID_STATUS__VMID19_OUTSTANDING__SHIFT	0x13
+#define ATC_ATS_VMID_STATUS__VMID20_OUTSTANDING__SHIFT	0x14
+#define ATC_ATS_VMID_STATUS__VMID21_OUTSTANDING__SHIFT	0x15
+#define ATC_ATS_VMID_STATUS__VMID22_OUTSTANDING__SHIFT	0x16
+#define ATC_ATS_VMID_STATUS__VMID23_OUTSTANDING__SHIFT	0x17
+#define ATC_ATS_VMID_STATUS__VMID24_OUTSTANDING__SHIFT	0x18
+#define ATC_ATS_VMID_STATUS__VMID25_OUTSTANDING__SHIFT	0x19
+#define ATC_ATS_VMID_STATUS__VMID26_OUTSTANDING__SHIFT	0x1a
+#define ATC_ATS_VMID_STATUS__VMID27_OUTSTANDING__SHIFT	0x1b
+#define ATC_ATS_VMID_STATUS__VMID28_OUTSTANDING__SHIFT	0x1c
+#define ATC_ATS_VMID_STATUS__VMID29_OUTSTANDING__SHIFT	0x1d
+#define ATC_ATS_VMID_STATUS__VMID30_OUTSTANDING__SHIFT	0x1e
+#define ATC_ATS_VMID_STATUS__VMID31_OUTSTANDING__SHIFT	0x1f
+#define ATC_ATS_VMID_STATUS__VMID0_OUTSTANDING_MASK	0x00000001L
+#define ATC_ATS_VMID_STATUS__VMID1_OUTSTANDING_MASK	0x00000002L
+#define ATC_ATS_VMID_STATUS__VMID2_OUTSTANDING_MASK	0x00000004L
+#define ATC_ATS_VMID_STATUS__VMID3_OUTSTANDING_MASK	0x00000008L
+#define ATC_ATS_VMID_STATUS__VMID4_OUTSTANDING_MASK	0x00000010L
+#define ATC_ATS_VMID_STATUS__VMID5_OUTSTANDING_MASK	0x00000020L
+#define ATC_ATS_VMID_STATUS__VMID6_OUTSTANDING_MASK	0x00000040L
+#define ATC_ATS_VMID_STATUS__VMID7_OUTSTANDING_MASK	0x00000080L
+#define ATC_ATS_VMID_STATUS__VMID8_OUTSTANDING_MASK	0x00000100L
+#define ATC_ATS_VMID_STATUS__VMID9_OUTSTANDING_MASK	0x00000200L
+#define ATC_ATS_VMID_STATUS__VMID10_OUTSTANDING_MASK	0x00000400L
+#define ATC_ATS_VMID_STATUS__VMID11_OUTSTANDING_MASK	0x00000800L
+#define ATC_ATS_VMID_STATUS__VMID12_OUTSTANDING_MASK	0x00001000L
+#define ATC_ATS_VMID_STATUS__VMID13_OUTSTANDING_MASK	0x00002000L
+#define ATC_ATS_VMID_STATUS__VMID14_OUTSTANDING_MASK	0x00004000L
+#define ATC_ATS_VMID_STATUS__VMID15_OUTSTANDING_MASK	0x00008000L
+#define ATC_ATS_VMID_STATUS__VMID16_OUTSTANDING_MASK	0x00010000L
+#define ATC_ATS_VMID_STATUS__VMID17_OUTSTANDING_MASK	0x00020000L
+#define ATC_ATS_VMID_STATUS__VMID18_OUTSTANDING_MASK	0x00040000L
+#define ATC_ATS_VMID_STATUS__VMID19_OUTSTANDING_MASK	0x00080000L
+#define ATC_ATS_VMID_STATUS__VMID20_OUTSTANDING_MASK	0x00100000L
+#define ATC_ATS_VMID_STATUS__VMID21_OUTSTANDING_MASK	0x00200000L
+#define ATC_ATS_VMID_STATUS__VMID22_OUTSTANDING_MASK	0x00400000L
+#define ATC_ATS_VMID_STATUS__VMID23_OUTSTANDING_MASK	0x00800000L
+#define ATC_ATS_VMID_STATUS__VMID24_OUTSTANDING_MASK	0x01000000L
+#define ATC_ATS_VMID_STATUS__VMID25_OUTSTANDING_MASK	0x02000000L
+#define ATC_ATS_VMID_STATUS__VMID26_OUTSTANDING_MASK	0x04000000L
+#define ATC_ATS_VMID_STATUS__VMID27_OUTSTANDING_MASK	0x08000000L
+#define ATC_ATS_VMID_STATUS__VMID28_OUTSTANDING_MASK	0x10000000L
+#define ATC_ATS_VMID_STATUS__VMID29_OUTSTANDING_MASK	0x20000000L
+#define ATC_ATS_VMID_STATUS__VMID30_OUTSTANDING_MASK	0x40000000L
+#define ATC_ATS_VMID_STATUS__VMID31_OUTSTANDING_MASK	0x80000000L
+//ATC_ATS_GFX_ATCL2_STATUS
+#define ATC_ATS_GFX_ATCL2_STATUS__POWERED_DOWN__SHIFT	0x0
+#define ATC_ATS_GFX_ATCL2_STATUS__POWERED_DOWN_MASK	0x00000001L
+//ATC_PERFCOUNTER0_CFG
+#define ATC_PERFCOUNTER0_CFG__PERF_SEL__SHIFT	0x0
+#define ATC_PERFCOUNTER0_CFG__PERF_SEL_END__SHIFT	0x8
+#define ATC_PERFCOUNTER0_CFG__PERF_MODE__SHIFT	0x18
+#define ATC_PERFCOUNTER0_CFG__ENABLE__SHIFT	0x1c
+#define ATC_PERFCOUNTER0_CFG__CLEAR__SHIFT	0x1d
+#define ATC_PERFCOUNTER0_CFG__PERF_SEL_MASK	0x000000FFL
+#define ATC_PERFCOUNTER0_CFG__PERF_SEL_END_MASK	0x0000FF00L
+#define ATC_PERFCOUNTER0_CFG__PERF_MODE_MASK	0x0F000000L
+#define ATC_PERFCOUNTER0_CFG__ENABLE_MASK	0x10000000L
+#define ATC_PERFCOUNTER0_CFG__CLEAR_MASK	0x20000000L
+//ATC_PERFCOUNTER1_CFG
+#define ATC_PERFCOUNTER1_CFG__PERF_SEL__SHIFT	0x0
+#define ATC_PERFCOUNTER1_CFG__PERF_SEL_END__SHIFT	0x8
+#define ATC_PERFCOUNTER1_CFG__PERF_MODE__SHIFT	0x18
+#define ATC_PERFCOUNTER1_CFG__ENABLE__SHIFT	0x1c
+#define ATC_PERFCOUNTER1_CFG__CLEAR__SHIFT	0x1d
+#define ATC_PERFCOUNTER1_CFG__PERF_SEL_MASK	0x000000FFL
+#define ATC_PERFCOUNTER1_CFG__PERF_SEL_END_MASK	0x0000FF00L
+#define ATC_PERFCOUNTER1_CFG__PERF_MODE_MASK	0x0F000000L
+#define ATC_PERFCOUNTER1_CFG__ENABLE_MASK	0x10000000L
+#define ATC_PERFCOUNTER1_CFG__CLEAR_MASK	0x20000000L
+//ATC_PERFCOUNTER2_CFG
+#define ATC_PERFCOUNTER2_CFG__PERF_SEL__SHIFT	0x0
+#define ATC_PERFCOUNTER2_CFG__PERF_SEL_END__SHIFT	0x8
+#define ATC_PERFCOUNTER2_CFG__PERF_MODE__SHIFT	0x18
+#define ATC_PERFCOUNTER2_CFG__ENABLE__SHIFT	0x1c
+#define ATC_PERFCOUNTER2_CFG__CLEAR__SHIFT	0x1d
+#define ATC_PERFCOUNTER2_CFG__PERF_SEL_MASK	0x000000FFL
+#define ATC_PERFCOUNTER2_CFG__PERF_SEL_END_MASK	0x0000FF00L
+#define ATC_PERFCOUNTER2_CFG__PERF_MODE_MASK	0x0F000000L
+#define ATC_PERFCOUNTER2_CFG__ENABLE_MASK	0x10000000L
+#define ATC_PERFCOUNTER2_CFG__CLEAR_MASK	0x20000000L
+//ATC_PERFCOUNTER3_CFG
+#define ATC_PERFCOUNTER3_CFG__PERF_SEL__SHIFT	0x0
+#define ATC_PERFCOUNTER3_CFG__PERF_SEL_END__SHIFT	0x8
+#define ATC_PERFCOUNTER3_CFG__PERF_MODE__SHIFT	0x18
+#define ATC_PERFCOUNTER3_CFG__ENABLE__SHIFT	0x1c
+#define ATC_PERFCOUNTER3_CFG__CLEAR__SHIFT	0x1d
+#define ATC_PERFCOUNTER3_CFG__PERF_SEL_MASK	0x000000FFL
+#define ATC_PERFCOUNTER3_CFG__PERF_SEL_END_MASK	0x0000FF00L
+#define ATC_PERFCOUNTER3_CFG__PERF_MODE_MASK	0x0F000000L
+#define ATC_PERFCOUNTER3_CFG__ENABLE_MASK	0x10000000L
+#define ATC_PERFCOUNTER3_CFG__CLEAR_MASK	0x20000000L
+//ATC_PERFCOUNTER_RSLT_CNTL
+#define ATC_PERFCOUNTER_RSLT_CNTL__PERF_COUNTER_SELECT__SHIFT	0x0
+#define ATC_PERFCOUNTER_RSLT_CNTL__START_TRIGGER__SHIFT	0x8
+#define ATC_PERFCOUNTER_RSLT_CNTL__STOP_TRIGGER__SHIFT	0x10
+#define ATC_PERFCOUNTER_RSLT_CNTL__ENABLE_ANY__SHIFT	0x18
+#define ATC_PERFCOUNTER_RSLT_CNTL__CLEAR_ALL__SHIFT	0x19
+#define ATC_PERFCOUNTER_RSLT_CNTL__STOP_ALL_ON_SATURATE__SHIFT	0x1a
+#define ATC_PERFCOUNTER_RSLT_CNTL__PERF_COUNTER_SELECT_MASK	0x0000000FL
+#define ATC_PERFCOUNTER_RSLT_CNTL__START_TRIGGER_MASK	0x0000FF00L
+#define ATC_PERFCOUNTER_RSLT_CNTL__STOP_TRIGGER_MASK	0x00FF0000L
+#define ATC_PERFCOUNTER_RSLT_CNTL__ENABLE_ANY_MASK	0x01000000L
+#define ATC_PERFCOUNTER_RSLT_CNTL__CLEAR_ALL_MASK	0x02000000L
+#define ATC_PERFCOUNTER_RSLT_CNTL__STOP_ALL_ON_SATURATE_MASK	0x04000000L
+//ATC_PERFCOUNTER_LO
+#define ATC_PERFCOUNTER_LO__COUNTER_LO__SHIFT	0x0
+#define ATC_PERFCOUNTER_LO__COUNTER_LO_MASK	0xFFFFFFFFL
+//ATC_PERFCOUNTER_HI
+#define ATC_PERFCOUNTER_HI__COUNTER_HI__SHIFT	0x0
+#define ATC_PERFCOUNTER_HI__COMPARE_VALUE__SHIFT	0x10
+#define ATC_PERFCOUNTER_HI__COUNTER_HI_MASK	0x0000FFFFL
+#define ATC_PERFCOUNTER_HI__COMPARE_VALUE_MASK	0xFFFF0000L
+//ATHUB_PCIE_ATS_CNTL
+#define ATHUB_PCIE_ATS_CNTL__STU__SHIFT	0x10
+#define ATHUB_PCIE_ATS_CNTL__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL__STU_MASK	0x001F0000L
+#define ATHUB_PCIE_ATS_CNTL__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_PASID_CNTL
+#define ATHUB_PCIE_PASID_CNTL__PASID_EN__SHIFT	0x10
+#define ATHUB_PCIE_PASID_CNTL__PASID_EXE_PERMISSION_ENABLE__SHIFT	0x11
+#define ATHUB_PCIE_PASID_CNTL__PASID_PRIV_MODE_SUPPORTED_ENABLE__SHIFT	0x12
+#define ATHUB_PCIE_PASID_CNTL__PASID_EN_MASK	0x00010000L
+#define ATHUB_PCIE_PASID_CNTL__PASID_EXE_PERMISSION_ENABLE_MASK	0x00020000L
+#define ATHUB_PCIE_PASID_CNTL__PASID_PRIV_MODE_SUPPORTED_ENABLE_MASK	0x00040000L
+//ATHUB_PCIE_PAGE_REQ_CNTL
+#define ATHUB_PCIE_PAGE_REQ_CNTL__PRI_ENABLE__SHIFT	0x0
+#define ATHUB_PCIE_PAGE_REQ_CNTL__PRI_RESET__SHIFT	0x1
+#define ATHUB_PCIE_PAGE_REQ_CNTL__PRI_ENABLE_MASK	0x00000001L
+#define ATHUB_PCIE_PAGE_REQ_CNTL__PRI_RESET_MASK	0x00000002L
+//ATHUB_PCIE_OUTSTAND_PAGE_REQ_ALLOC
+#define ATHUB_PCIE_OUTSTAND_PAGE_REQ_ALLOC__OUTSTAND_PAGE_REQ_ALLOC__SHIFT	0x0
+#define ATHUB_PCIE_OUTSTAND_PAGE_REQ_ALLOC__OUTSTAND_PAGE_REQ_ALLOC_MASK	0xFFFFFFFFL
+//ATHUB_COMMAND
+#define ATHUB_COMMAND__BUS_MASTER_EN__SHIFT	0x2
+#define ATHUB_COMMAND__BUS_MASTER_EN_MASK	0x00000004L
+//ATHUB_PCIE_ATS_CNTL_VF_0
+#define ATHUB_PCIE_ATS_CNTL_VF_0__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_0__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_1
+#define ATHUB_PCIE_ATS_CNTL_VF_1__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_1__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_2
+#define ATHUB_PCIE_ATS_CNTL_VF_2__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_2__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_3
+#define ATHUB_PCIE_ATS_CNTL_VF_3__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_3__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_4
+#define ATHUB_PCIE_ATS_CNTL_VF_4__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_4__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_5
+#define ATHUB_PCIE_ATS_CNTL_VF_5__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_5__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_6
+#define ATHUB_PCIE_ATS_CNTL_VF_6__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_6__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_7
+#define ATHUB_PCIE_ATS_CNTL_VF_7__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_7__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_8
+#define ATHUB_PCIE_ATS_CNTL_VF_8__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_8__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_9
+#define ATHUB_PCIE_ATS_CNTL_VF_9__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_9__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_10
+#define ATHUB_PCIE_ATS_CNTL_VF_10__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_10__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_11
+#define ATHUB_PCIE_ATS_CNTL_VF_11__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_11__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_12
+#define ATHUB_PCIE_ATS_CNTL_VF_12__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_12__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_13
+#define ATHUB_PCIE_ATS_CNTL_VF_13__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_13__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_14
+#define ATHUB_PCIE_ATS_CNTL_VF_14__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_14__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_PCIE_ATS_CNTL_VF_15
+#define ATHUB_PCIE_ATS_CNTL_VF_15__ATC_ENABLE__SHIFT	0x1f
+#define ATHUB_PCIE_ATS_CNTL_VF_15__ATC_ENABLE_MASK	0x80000000L
+//ATHUB_MEM_POWER_LS
+#define ATHUB_MEM_POWER_LS__LS_SETUP__SHIFT	0x0
+#define ATHUB_MEM_POWER_LS__LS_HOLD__SHIFT	0x6
+#define ATHUB_MEM_POWER_LS__LS_SETUP_MASK	0x0000003FL
+#define ATHUB_MEM_POWER_LS__LS_HOLD_MASK	0x00000FC0L
+//ATS_IH_CREDIT
+#define ATS_IH_CREDIT__CREDIT_VALUE__SHIFT	0x0
+#define ATS_IH_CREDIT__IH_CLIENT_ID__SHIFT	0x10
+#define ATS_IH_CREDIT__CREDIT_VALUE_MASK	0x00000003L
+#define ATS_IH_CREDIT__IH_CLIENT_ID_MASK	0x00FF0000L
+//ATHUB_IH_CREDIT
+#define ATHUB_IH_CREDIT__CREDIT_VALUE__SHIFT	0x0
+#define ATHUB_IH_CREDIT__IH_CLIENT_ID__SHIFT	0x10
+#define ATHUB_IH_CREDIT__CREDIT_VALUE_MASK	0x00000003L
+#define ATHUB_IH_CREDIT__IH_CLIENT_ID_MASK	0x00FF0000L
+//ATC_VMID16_PASID_MAPPING
+#define ATC_VMID16_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID16_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID16_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID16_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID16_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID16_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID17_PASID_MAPPING
+#define ATC_VMID17_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID17_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID17_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID17_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID17_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID17_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID18_PASID_MAPPING
+#define ATC_VMID18_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID18_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID18_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID18_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID18_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID18_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID19_PASID_MAPPING
+#define ATC_VMID19_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID19_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID19_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID19_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID19_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID19_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID20_PASID_MAPPING
+#define ATC_VMID20_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID20_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID20_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID20_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID20_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID20_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID21_PASID_MAPPING
+#define ATC_VMID21_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID21_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID21_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID21_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID21_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID21_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID22_PASID_MAPPING
+#define ATC_VMID22_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID22_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID22_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID22_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID22_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID22_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID23_PASID_MAPPING
+#define ATC_VMID23_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID23_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID23_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID23_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID23_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID23_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID24_PASID_MAPPING
+#define ATC_VMID24_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID24_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID24_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID24_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID24_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID24_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID25_PASID_MAPPING
+#define ATC_VMID25_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID25_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID25_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID25_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID25_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID25_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID26_PASID_MAPPING
+#define ATC_VMID26_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID26_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID26_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID26_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID26_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID26_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID27_PASID_MAPPING
+#define ATC_VMID27_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID27_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID27_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID27_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID27_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID27_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID28_PASID_MAPPING
+#define ATC_VMID28_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID28_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID28_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID28_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID28_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID28_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID29_PASID_MAPPING
+#define ATC_VMID29_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID29_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID29_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID29_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID29_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID29_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID30_PASID_MAPPING
+#define ATC_VMID30_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID30_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID30_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID30_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID30_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID30_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_VMID31_PASID_MAPPING
+#define ATC_VMID31_PASID_MAPPING__PASID__SHIFT	0x0
+#define ATC_VMID31_PASID_MAPPING__NO_INVALIDATION__SHIFT	0x1e
+#define ATC_VMID31_PASID_MAPPING__VALID__SHIFT	0x1f
+#define ATC_VMID31_PASID_MAPPING__PASID_MASK	0x0000FFFFL
+#define ATC_VMID31_PASID_MAPPING__NO_INVALIDATION_MASK	0x40000000L
+#define ATC_VMID31_PASID_MAPPING__VALID_MASK	0x80000000L
+//ATC_ATS_MMHUB_ATCL2_STATUS
+#define ATC_ATS_MMHUB_ATCL2_STATUS__POWERED_DOWN__SHIFT	0x0
+#define ATC_ATS_MMHUB_ATCL2_STATUS__POWERED_DOWN_MASK	0x00000001L
+//ATHUB_SHARED_VIRT_RESET_REQ
+#define ATHUB_SHARED_VIRT_RESET_REQ__VF__SHIFT	0x0
+#define ATHUB_SHARED_VIRT_RESET_REQ__PF__SHIFT	0x1f
+#define ATHUB_SHARED_VIRT_RESET_REQ__VF_MASK	0x0000FFFFL
+#define ATHUB_SHARED_VIRT_RESET_REQ__PF_MASK	0x80000000L
+//ATHUB_SHARED_ACTIVE_FCN_ID
+#define ATHUB_SHARED_ACTIVE_FCN_ID__VFID__SHIFT	0x0
+#define ATHUB_SHARED_ACTIVE_FCN_ID__VF__SHIFT	0x1f
+#define ATHUB_SHARED_ACTIVE_FCN_ID__VFID_MASK	0x0000000FL
+#define ATHUB_SHARED_ACTIVE_FCN_ID__VF_MASK	0x80000000L
+//ATC_ATS_SDPPORT_CNTL
+#define ATC_ATS_SDPPORT_CNTL__ATS_INV_SELF_ACTIVATE__SHIFT	0x0
+#define ATC_ATS_SDPPORT_CNTL__ATS_INV_CFG_MODE__SHIFT	0x1
+#define ATC_ATS_SDPPORT_CNTL__ATS_INV_HALT_THRESHOLD__SHIFT	0x3
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_TRANS_SELF_ACTIVATE__SHIFT	0x7
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_TRANS_QUICK_COMACK__SHIFT	0x8
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_TRANS_HALT_THRESHOLD__SHIFT	0x9
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_TRANS_PASSIVE_MODE__SHIFT	0xd
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_RDY_MODE__SHIFT	0xe
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_MMHUB_RDY_MODE__SHIFT	0xf
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_RDRSPCKEN__SHIFT	0x10
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_RDRSPCKENRCV__SHIFT	0x11
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_RDRSPDATACKEN__SHIFT	0x12
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_RDRSPDATACKENRCV__SHIFT	0x13
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_WRRSPCKEN__SHIFT	0x14
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_WRRSPCKENRCV__SHIFT	0x15
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_REQCKEN__SHIFT	0x16
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_REQCKENRCV__SHIFT	0x17
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_ORIGDATACKEN__SHIFT	0x18
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_ORIGDATACKENRCV__SHIFT	0x19
+#define ATC_ATS_SDPPORT_CNTL__ATS_INV_SELF_ACTIVATE_MASK	0x00000001L
+#define ATC_ATS_SDPPORT_CNTL__ATS_INV_CFG_MODE_MASK	0x00000006L
+#define ATC_ATS_SDPPORT_CNTL__ATS_INV_HALT_THRESHOLD_MASK	0x00000078L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_TRANS_SELF_ACTIVATE_MASK	0x00000080L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_TRANS_QUICK_COMACK_MASK	0x00000100L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_TRANS_HALT_THRESHOLD_MASK	0x00001E00L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_TRANS_PASSIVE_MODE_MASK	0x00002000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_RDY_MODE_MASK	0x00004000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_MMHUB_RDY_MODE_MASK	0x00008000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_RDRSPCKEN_MASK	0x00010000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_RDRSPCKENRCV_MASK	0x00020000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_RDRSPDATACKEN_MASK	0x00040000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_RDRSPDATACKENRCV_MASK	0x00080000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_WRRSPCKEN_MASK	0x00100000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_WRRSPCKENRCV_MASK	0x00200000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_REQCKEN_MASK	0x00400000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_REQCKENRCV_MASK	0x00800000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_ORIGDATACKEN_MASK	0x01000000L
+#define ATC_ATS_SDPPORT_CNTL__UTCL2_GFX_SDPVDCI_ORIGDATACKENRCV_MASK	0x02000000L
+//ATC_ATS_VMID_SNAPSHOT_GFX_STAT
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID0__SHIFT	0x0
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID1__SHIFT	0x1
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID2__SHIFT	0x2
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID3__SHIFT	0x3
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID4__SHIFT	0x4
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID5__SHIFT	0x5
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID6__SHIFT	0x6
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID7__SHIFT	0x7
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID8__SHIFT	0x8
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID9__SHIFT	0x9
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID10__SHIFT	0xa
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID11__SHIFT	0xb
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID12__SHIFT	0xc
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID13__SHIFT	0xd
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID14__SHIFT	0xe
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID15__SHIFT	0xf
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID0_MASK	0x00000001L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID1_MASK	0x00000002L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID2_MASK	0x00000004L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID3_MASK	0x00000008L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID4_MASK	0x00000010L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID5_MASK	0x00000020L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID6_MASK	0x00000040L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID7_MASK	0x00000080L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID8_MASK	0x00000100L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID9_MASK	0x00000200L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID10_MASK	0x00000400L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID11_MASK	0x00000800L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID12_MASK	0x00001000L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID13_MASK	0x00002000L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID14_MASK	0x00004000L
+#define ATC_ATS_VMID_SNAPSHOT_GFX_STAT__VMID15_MASK	0x00008000L
+//ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID0__SHIFT	0x0
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID1__SHIFT	0x1
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID2__SHIFT	0x2
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID3__SHIFT	0x3
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID4__SHIFT	0x4
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID5__SHIFT	0x5
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID6__SHIFT	0x6
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID7__SHIFT	0x7
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID8__SHIFT	0x8
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID9__SHIFT	0x9
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID10__SHIFT	0xa
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID11__SHIFT	0xb
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID12__SHIFT	0xc
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID13__SHIFT	0xd
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID14__SHIFT	0xe
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID15__SHIFT	0xf
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID0_MASK	0x00000001L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID1_MASK	0x00000002L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID2_MASK	0x00000004L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID3_MASK	0x00000008L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID4_MASK	0x00000010L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID5_MASK	0x00000020L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID6_MASK	0x00000040L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID7_MASK	0x00000080L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID8_MASK	0x00000100L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID9_MASK	0x00000200L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID10_MASK	0x00000400L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID11_MASK	0x00000800L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID12_MASK	0x00001000L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID13_MASK	0x00002000L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID14_MASK	0x00004000L
+#define ATC_ATS_VMID_SNAPSHOT_MMHUB_STAT__VMID15_MASK	0x00008000L
+
+
+// addressBlock: athub_xpbdec
+//XPB_RTR_SRC_APRTR0
+#define XPB_RTR_SRC_APRTR0__BASE_ADDR__SHIFT	0x0
+#define XPB_RTR_SRC_APRTR0__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_RTR_SRC_APRTR1
+#define XPB_RTR_SRC_APRTR1__BASE_ADDR__SHIFT	0x0
+#define XPB_RTR_SRC_APRTR1__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_RTR_SRC_APRTR2
+#define XPB_RTR_SRC_APRTR2__BASE_ADDR__SHIFT	0x0
+#define XPB_RTR_SRC_APRTR2__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_RTR_SRC_APRTR3
+#define XPB_RTR_SRC_APRTR3__BASE_ADDR__SHIFT	0x0
+#define XPB_RTR_SRC_APRTR3__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_RTR_SRC_APRTR4
+#define XPB_RTR_SRC_APRTR4__BASE_ADDR__SHIFT	0x0
+#define XPB_RTR_SRC_APRTR4__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_RTR_SRC_APRTR5
+#define XPB_RTR_SRC_APRTR5__BASE_ADDR__SHIFT	0x0
+#define XPB_RTR_SRC_APRTR5__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_RTR_SRC_APRTR6
+#define XPB_RTR_SRC_APRTR6__BASE_ADDR__SHIFT	0x0
+#define XPB_RTR_SRC_APRTR6__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_RTR_SRC_APRTR7
+#define XPB_RTR_SRC_APRTR7__BASE_ADDR__SHIFT	0x0
+#define XPB_RTR_SRC_APRTR7__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_RTR_SRC_APRTR8
+#define XPB_RTR_SRC_APRTR8__BASE_ADDR__SHIFT	0x0
+#define XPB_RTR_SRC_APRTR8__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_RTR_SRC_APRTR9
+#define XPB_RTR_SRC_APRTR9__BASE_ADDR__SHIFT	0x0
+#define XPB_RTR_SRC_APRTR9__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_XDMA_RTR_SRC_APRTR0
+#define XPB_XDMA_RTR_SRC_APRTR0__BASE_ADDR__SHIFT	0x0
+#define XPB_XDMA_RTR_SRC_APRTR0__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_XDMA_RTR_SRC_APRTR1
+#define XPB_XDMA_RTR_SRC_APRTR1__BASE_ADDR__SHIFT	0x0
+#define XPB_XDMA_RTR_SRC_APRTR1__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_XDMA_RTR_SRC_APRTR2
+#define XPB_XDMA_RTR_SRC_APRTR2__BASE_ADDR__SHIFT	0x0
+#define XPB_XDMA_RTR_SRC_APRTR2__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_XDMA_RTR_SRC_APRTR3
+#define XPB_XDMA_RTR_SRC_APRTR3__BASE_ADDR__SHIFT	0x0
+#define XPB_XDMA_RTR_SRC_APRTR3__BASE_ADDR_MASK	0x7FFFFFFFL
+//XPB_RTR_DEST_MAP0
+#define XPB_RTR_DEST_MAP0__NMR__SHIFT	0x0
+#define XPB_RTR_DEST_MAP0__DEST_OFFSET__SHIFT	0x1
+#define XPB_RTR_DEST_MAP0__DEST_SEL__SHIFT	0x14
+#define XPB_RTR_DEST_MAP0__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_RTR_DEST_MAP0__APRTR_SIZE__SHIFT	0x1a
+#define XPB_RTR_DEST_MAP0__NMR_MASK	0x00000001L
+#define XPB_RTR_DEST_MAP0__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_RTR_DEST_MAP0__DEST_SEL_MASK	0x00F00000L
+#define XPB_RTR_DEST_MAP0__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_RTR_DEST_MAP0__APRTR_SIZE_MASK	0x7C000000L
+//XPB_RTR_DEST_MAP1
+#define XPB_RTR_DEST_MAP1__NMR__SHIFT	0x0
+#define XPB_RTR_DEST_MAP1__DEST_OFFSET__SHIFT	0x1
+#define XPB_RTR_DEST_MAP1__DEST_SEL__SHIFT	0x14
+#define XPB_RTR_DEST_MAP1__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_RTR_DEST_MAP1__APRTR_SIZE__SHIFT	0x1a
+#define XPB_RTR_DEST_MAP1__NMR_MASK	0x00000001L
+#define XPB_RTR_DEST_MAP1__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_RTR_DEST_MAP1__DEST_SEL_MASK	0x00F00000L
+#define XPB_RTR_DEST_MAP1__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_RTR_DEST_MAP1__APRTR_SIZE_MASK	0x7C000000L
+//XPB_RTR_DEST_MAP2
+#define XPB_RTR_DEST_MAP2__NMR__SHIFT	0x0
+#define XPB_RTR_DEST_MAP2__DEST_OFFSET__SHIFT	0x1
+#define XPB_RTR_DEST_MAP2__DEST_SEL__SHIFT	0x14
+#define XPB_RTR_DEST_MAP2__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_RTR_DEST_MAP2__APRTR_SIZE__SHIFT	0x1a
+#define XPB_RTR_DEST_MAP2__NMR_MASK	0x00000001L
+#define XPB_RTR_DEST_MAP2__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_RTR_DEST_MAP2__DEST_SEL_MASK	0x00F00000L
+#define XPB_RTR_DEST_MAP2__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_RTR_DEST_MAP2__APRTR_SIZE_MASK	0x7C000000L
+//XPB_RTR_DEST_MAP3
+#define XPB_RTR_DEST_MAP3__NMR__SHIFT	0x0
+#define XPB_RTR_DEST_MAP3__DEST_OFFSET__SHIFT	0x1
+#define XPB_RTR_DEST_MAP3__DEST_SEL__SHIFT	0x14
+#define XPB_RTR_DEST_MAP3__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_RTR_DEST_MAP3__APRTR_SIZE__SHIFT	0x1a
+#define XPB_RTR_DEST_MAP3__NMR_MASK	0x00000001L
+#define XPB_RTR_DEST_MAP3__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_RTR_DEST_MAP3__DEST_SEL_MASK	0x00F00000L
+#define XPB_RTR_DEST_MAP3__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_RTR_DEST_MAP3__APRTR_SIZE_MASK	0x7C000000L
+//XPB_RTR_DEST_MAP4
+#define XPB_RTR_DEST_MAP4__NMR__SHIFT	0x0
+#define XPB_RTR_DEST_MAP4__DEST_OFFSET__SHIFT	0x1
+#define XPB_RTR_DEST_MAP4__DEST_SEL__SHIFT	0x14
+#define XPB_RTR_DEST_MAP4__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_RTR_DEST_MAP4__APRTR_SIZE__SHIFT	0x1a
+#define XPB_RTR_DEST_MAP4__NMR_MASK	0x00000001L
+#define XPB_RTR_DEST_MAP4__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_RTR_DEST_MAP4__DEST_SEL_MASK	0x00F00000L
+#define XPB_RTR_DEST_MAP4__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_RTR_DEST_MAP4__APRTR_SIZE_MASK	0x7C000000L
+//XPB_RTR_DEST_MAP5
+#define XPB_RTR_DEST_MAP5__NMR__SHIFT	0x0
+#define XPB_RTR_DEST_MAP5__DEST_OFFSET__SHIFT	0x1
+#define XPB_RTR_DEST_MAP5__DEST_SEL__SHIFT	0x14
+#define XPB_RTR_DEST_MAP5__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_RTR_DEST_MAP5__APRTR_SIZE__SHIFT	0x1a
+#define XPB_RTR_DEST_MAP5__NMR_MASK	0x00000001L
+#define XPB_RTR_DEST_MAP5__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_RTR_DEST_MAP5__DEST_SEL_MASK	0x00F00000L
+#define XPB_RTR_DEST_MAP5__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_RTR_DEST_MAP5__APRTR_SIZE_MASK	0x7C000000L
+//XPB_RTR_DEST_MAP6
+#define XPB_RTR_DEST_MAP6__NMR__SHIFT	0x0
+#define XPB_RTR_DEST_MAP6__DEST_OFFSET__SHIFT	0x1
+#define XPB_RTR_DEST_MAP6__DEST_SEL__SHIFT	0x14
+#define XPB_RTR_DEST_MAP6__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_RTR_DEST_MAP6__APRTR_SIZE__SHIFT	0x1a
+#define XPB_RTR_DEST_MAP6__NMR_MASK	0x00000001L
+#define XPB_RTR_DEST_MAP6__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_RTR_DEST_MAP6__DEST_SEL_MASK	0x00F00000L
+#define XPB_RTR_DEST_MAP6__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_RTR_DEST_MAP6__APRTR_SIZE_MASK	0x7C000000L
+//XPB_RTR_DEST_MAP7
+#define XPB_RTR_DEST_MAP7__NMR__SHIFT	0x0
+#define XPB_RTR_DEST_MAP7__DEST_OFFSET__SHIFT	0x1
+#define XPB_RTR_DEST_MAP7__DEST_SEL__SHIFT	0x14
+#define XPB_RTR_DEST_MAP7__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_RTR_DEST_MAP7__APRTR_SIZE__SHIFT	0x1a
+#define XPB_RTR_DEST_MAP7__NMR_MASK	0x00000001L
+#define XPB_RTR_DEST_MAP7__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_RTR_DEST_MAP7__DEST_SEL_MASK	0x00F00000L
+#define XPB_RTR_DEST_MAP7__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_RTR_DEST_MAP7__APRTR_SIZE_MASK	0x7C000000L
+//XPB_RTR_DEST_MAP8
+#define XPB_RTR_DEST_MAP8__NMR__SHIFT	0x0
+#define XPB_RTR_DEST_MAP8__DEST_OFFSET__SHIFT	0x1
+#define XPB_RTR_DEST_MAP8__DEST_SEL__SHIFT	0x14
+#define XPB_RTR_DEST_MAP8__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_RTR_DEST_MAP8__APRTR_SIZE__SHIFT	0x1a
+#define XPB_RTR_DEST_MAP8__NMR_MASK	0x00000001L
+#define XPB_RTR_DEST_MAP8__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_RTR_DEST_MAP8__DEST_SEL_MASK	0x00F00000L
+#define XPB_RTR_DEST_MAP8__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_RTR_DEST_MAP8__APRTR_SIZE_MASK	0x7C000000L
+//XPB_RTR_DEST_MAP9
+#define XPB_RTR_DEST_MAP9__NMR__SHIFT	0x0
+#define XPB_RTR_DEST_MAP9__DEST_OFFSET__SHIFT	0x1
+#define XPB_RTR_DEST_MAP9__DEST_SEL__SHIFT	0x14
+#define XPB_RTR_DEST_MAP9__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_RTR_DEST_MAP9__APRTR_SIZE__SHIFT	0x1a
+#define XPB_RTR_DEST_MAP9__NMR_MASK	0x00000001L
+#define XPB_RTR_DEST_MAP9__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_RTR_DEST_MAP9__DEST_SEL_MASK	0x00F00000L
+#define XPB_RTR_DEST_MAP9__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_RTR_DEST_MAP9__APRTR_SIZE_MASK	0x7C000000L
+//XPB_XDMA_RTR_DEST_MAP0
+#define XPB_XDMA_RTR_DEST_MAP0__NMR__SHIFT	0x0
+#define XPB_XDMA_RTR_DEST_MAP0__DEST_OFFSET__SHIFT	0x1
+#define XPB_XDMA_RTR_DEST_MAP0__DEST_SEL__SHIFT	0x14
+#define XPB_XDMA_RTR_DEST_MAP0__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_XDMA_RTR_DEST_MAP0__APRTR_SIZE__SHIFT	0x1a
+#define XPB_XDMA_RTR_DEST_MAP0__NMR_MASK	0x00000001L
+#define XPB_XDMA_RTR_DEST_MAP0__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_XDMA_RTR_DEST_MAP0__DEST_SEL_MASK	0x00F00000L
+#define XPB_XDMA_RTR_DEST_MAP0__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_XDMA_RTR_DEST_MAP0__APRTR_SIZE_MASK	0x7C000000L
+//XPB_XDMA_RTR_DEST_MAP1
+#define XPB_XDMA_RTR_DEST_MAP1__NMR__SHIFT	0x0
+#define XPB_XDMA_RTR_DEST_MAP1__DEST_OFFSET__SHIFT	0x1
+#define XPB_XDMA_RTR_DEST_MAP1__DEST_SEL__SHIFT	0x14
+#define XPB_XDMA_RTR_DEST_MAP1__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_XDMA_RTR_DEST_MAP1__APRTR_SIZE__SHIFT	0x1a
+#define XPB_XDMA_RTR_DEST_MAP1__NMR_MASK	0x00000001L
+#define XPB_XDMA_RTR_DEST_MAP1__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_XDMA_RTR_DEST_MAP1__DEST_SEL_MASK	0x00F00000L
+#define XPB_XDMA_RTR_DEST_MAP1__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_XDMA_RTR_DEST_MAP1__APRTR_SIZE_MASK	0x7C000000L
+//XPB_XDMA_RTR_DEST_MAP2
+#define XPB_XDMA_RTR_DEST_MAP2__NMR__SHIFT	0x0
+#define XPB_XDMA_RTR_DEST_MAP2__DEST_OFFSET__SHIFT	0x1
+#define XPB_XDMA_RTR_DEST_MAP2__DEST_SEL__SHIFT	0x14
+#define XPB_XDMA_RTR_DEST_MAP2__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_XDMA_RTR_DEST_MAP2__APRTR_SIZE__SHIFT	0x1a
+#define XPB_XDMA_RTR_DEST_MAP2__NMR_MASK	0x00000001L
+#define XPB_XDMA_RTR_DEST_MAP2__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_XDMA_RTR_DEST_MAP2__DEST_SEL_MASK	0x00F00000L
+#define XPB_XDMA_RTR_DEST_MAP2__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_XDMA_RTR_DEST_MAP2__APRTR_SIZE_MASK	0x7C000000L
+//XPB_XDMA_RTR_DEST_MAP3
+#define XPB_XDMA_RTR_DEST_MAP3__NMR__SHIFT	0x0
+#define XPB_XDMA_RTR_DEST_MAP3__DEST_OFFSET__SHIFT	0x1
+#define XPB_XDMA_RTR_DEST_MAP3__DEST_SEL__SHIFT	0x14
+#define XPB_XDMA_RTR_DEST_MAP3__DEST_SEL_RPB__SHIFT	0x18
+#define XPB_XDMA_RTR_DEST_MAP3__APRTR_SIZE__SHIFT	0x1a
+#define XPB_XDMA_RTR_DEST_MAP3__NMR_MASK	0x00000001L
+#define XPB_XDMA_RTR_DEST_MAP3__DEST_OFFSET_MASK	0x000FFFFEL
+#define XPB_XDMA_RTR_DEST_MAP3__DEST_SEL_MASK	0x00F00000L
+#define XPB_XDMA_RTR_DEST_MAP3__DEST_SEL_RPB_MASK	0x01000000L
+#define XPB_XDMA_RTR_DEST_MAP3__APRTR_SIZE_MASK	0x7C000000L
+//XPB_CLG_CFG0
+#define XPB_CLG_CFG0__WCB_NUM__SHIFT	0x0
+#define XPB_CLG_CFG0__P2P_BAR__SHIFT	0x7
+#define XPB_CLG_CFG0__HOST_FLUSH__SHIFT	0xa
+#define XPB_CLG_CFG0__WCB_NUM_MASK	0x0000000FL
+#define XPB_CLG_CFG0__P2P_BAR_MASK	0x00000380L
+#define XPB_CLG_CFG0__HOST_FLUSH_MASK	0x00003C00L
+//XPB_CLG_CFG1
+#define XPB_CLG_CFG1__WCB_NUM__SHIFT	0x0
+#define XPB_CLG_CFG1__P2P_BAR__SHIFT	0x7
+#define XPB_CLG_CFG1__HOST_FLUSH__SHIFT	0xa
+#define XPB_CLG_CFG1__WCB_NUM_MASK	0x0000000FL
+#define XPB_CLG_CFG1__P2P_BAR_MASK	0x00000380L
+#define XPB_CLG_CFG1__HOST_FLUSH_MASK	0x00003C00L
+//XPB_CLG_CFG2
+#define XPB_CLG_CFG2__WCB_NUM__SHIFT	0x0
+#define XPB_CLG_CFG2__P2P_BAR__SHIFT	0x7
+#define XPB_CLG_CFG2__HOST_FLUSH__SHIFT	0xa
+#define XPB_CLG_CFG2__WCB_NUM_MASK	0x0000000FL
+#define XPB_CLG_CFG2__P2P_BAR_MASK	0x00000380L
+#define XPB_CLG_CFG2__HOST_FLUSH_MASK	0x00003C00L
+//XPB_CLG_CFG3
+#define XPB_CLG_CFG3__WCB_NUM__SHIFT	0x0
+#define XPB_CLG_CFG3__P2P_BAR__SHIFT	0x7
+#define XPB_CLG_CFG3__HOST_FLUSH__SHIFT	0xa
+#define XPB_CLG_CFG3__WCB_NUM_MASK	0x0000000FL
+#define XPB_CLG_CFG3__P2P_BAR_MASK	0x00000380L
+#define XPB_CLG_CFG3__HOST_FLUSH_MASK	0x00003C00L
+//XPB_CLG_CFG4
+#define XPB_CLG_CFG4__WCB_NUM__SHIFT	0x0
+#define XPB_CLG_CFG4__P2P_BAR__SHIFT	0x7
+#define XPB_CLG_CFG4__HOST_FLUSH__SHIFT	0xa
+#define XPB_CLG_CFG4__WCB_NUM_MASK	0x0000000FL
+#define XPB_CLG_CFG4__P2P_BAR_MASK	0x00000380L
+#define XPB_CLG_CFG4__HOST_FLUSH_MASK	0x00003C00L
+//XPB_CLG_CFG5
+#define XPB_CLG_CFG5__WCB_NUM__SHIFT	0x0
+#define XPB_CLG_CFG5__P2P_BAR__SHIFT	0x7
+#define XPB_CLG_CFG5__HOST_FLUSH__SHIFT	0xa
+#define XPB_CLG_CFG5__WCB_NUM_MASK	0x0000000FL
+#define XPB_CLG_CFG5__P2P_BAR_MASK	0x00000380L
+#define XPB_CLG_CFG5__HOST_FLUSH_MASK	0x00003C00L
+//XPB_CLG_CFG6
+#define XPB_CLG_CFG6__WCB_NUM__SHIFT	0x0
+#define XPB_CLG_CFG6__P2P_BAR__SHIFT	0x7
+#define XPB_CLG_CFG6__HOST_FLUSH__SHIFT	0xa
+#define XPB_CLG_CFG6__WCB_NUM_MASK	0x0000000FL
+#define XPB_CLG_CFG6__P2P_BAR_MASK	0x00000380L
+#define XPB_CLG_CFG6__HOST_FLUSH_MASK	0x00003C00L
+//XPB_CLG_CFG7
+#define XPB_CLG_CFG7__WCB_NUM__SHIFT	0x0
+#define XPB_CLG_CFG7__P2P_BAR__SHIFT	0x7
+#define XPB_CLG_CFG7__HOST_FLUSH__SHIFT	0xa
+#define XPB_CLG_CFG7__WCB_NUM_MASK	0x0000000FL
+#define XPB_CLG_CFG7__P2P_BAR_MASK	0x00000380L
+#define XPB_CLG_CFG7__HOST_FLUSH_MASK	0x00003C00L
+//XPB_CLG_EXTRA
+#define XPB_CLG_EXTRA__CMP0_HIGH__SHIFT	0x0
+#define XPB_CLG_EXTRA__CMP0_LOW__SHIFT	0x6
+#define XPB_CLG_EXTRA__VLD0__SHIFT	0xb
+#define XPB_CLG_EXTRA__CLG0_NUM__SHIFT	0xc
+#define XPB_CLG_EXTRA__CMP1_HIGH__SHIFT	0xf
+#define XPB_CLG_EXTRA__CMP1_LOW__SHIFT	0x15
+#define XPB_CLG_EXTRA__VLD1__SHIFT	0x1a
+#define XPB_CLG_EXTRA__CLG1_NUM__SHIFT	0x1b
+#define XPB_CLG_EXTRA__CMP0_HIGH_MASK	0x0000003FL
+#define XPB_CLG_EXTRA__CMP0_LOW_MASK	0x000007C0L
+#define XPB_CLG_EXTRA__VLD0_MASK	0x00000800L
+#define XPB_CLG_EXTRA__CLG0_NUM_MASK	0x00007000L
+#define XPB_CLG_EXTRA__CMP1_HIGH_MASK	0x001F8000L
+#define XPB_CLG_EXTRA__CMP1_LOW_MASK	0x03E00000L
+#define XPB_CLG_EXTRA__VLD1_MASK	0x04000000L
+#define XPB_CLG_EXTRA__CLG1_NUM_MASK	0x38000000L
+//XPB_CLG_EXTRA_MSK
+#define XPB_CLG_EXTRA_MSK__MSK0_HIGH__SHIFT	0x0
+#define XPB_CLG_EXTRA_MSK__MSK0_LOW__SHIFT	0x6
+#define XPB_CLG_EXTRA_MSK__MSK1_HIGH__SHIFT	0xb
+#define XPB_CLG_EXTRA_MSK__MSK1_LOW__SHIFT	0x11
+#define XPB_CLG_EXTRA_MSK__MSK0_HIGH_MASK	0x0000003FL
+#define XPB_CLG_EXTRA_MSK__MSK0_LOW_MASK	0x000007C0L
+#define XPB_CLG_EXTRA_MSK__MSK1_HIGH_MASK	0x0001F800L
+#define XPB_CLG_EXTRA_MSK__MSK1_LOW_MASK	0x003E0000L
+//XPB_LB_ADDR
+#define XPB_LB_ADDR__CMP0__SHIFT	0x0
+#define XPB_LB_ADDR__MASK0__SHIFT	0xa
+#define XPB_LB_ADDR__CMP1__SHIFT	0x14
+#define XPB_LB_ADDR__MASK1__SHIFT	0x1a
+#define XPB_LB_ADDR__CMP0_MASK	0x000003FFL
+#define XPB_LB_ADDR__MASK0_MASK	0x000FFC00L
+#define XPB_LB_ADDR__CMP1_MASK	0x03F00000L
+#define XPB_LB_ADDR__MASK1_MASK	0xFC000000L
+//XPB_WCB_STS
+#define XPB_WCB_STS__PBUF_VLD__SHIFT	0x0
+#define XPB_WCB_STS__WCB_HST_DATA_BUF_CNT__SHIFT	0x10
+#define XPB_WCB_STS__WCB_SID_DATA_BUF_CNT__SHIFT	0x17
+#define XPB_WCB_STS__PBUF_VLD_MASK	0x0000FFFFL
+#define XPB_WCB_STS__WCB_HST_DATA_BUF_CNT_MASK	0x007F0000L
+#define XPB_WCB_STS__WCB_SID_DATA_BUF_CNT_MASK	0x3F800000L
+//XPB_HST_CFG
+#define XPB_HST_CFG__BAR_UP_WR_CMD__SHIFT	0x0
+#define XPB_HST_CFG__BAR_UP_WR_CMD_MASK	0x00000001L
+//XPB_P2P_BAR_CFG
+#define XPB_P2P_BAR_CFG__ADDR_SIZE__SHIFT	0x0
+#define XPB_P2P_BAR_CFG__SEND_BAR__SHIFT	0x4
+#define XPB_P2P_BAR_CFG__SNOOP__SHIFT	0x6
+#define XPB_P2P_BAR_CFG__SEND_DIS__SHIFT	0x7
+#define XPB_P2P_BAR_CFG__COMPRESS_DIS__SHIFT	0x8
+#define XPB_P2P_BAR_CFG__UPDATE_DIS__SHIFT	0x9
+#define XPB_P2P_BAR_CFG__REGBAR_FROM_SYSBAR__SHIFT	0xa
+#define XPB_P2P_BAR_CFG__RD_EN__SHIFT	0xb
+#define XPB_P2P_BAR_CFG__ATC_TRANSLATED__SHIFT	0xc
+#define XPB_P2P_BAR_CFG__ADDR_SIZE_MASK	0x0000000FL
+#define XPB_P2P_BAR_CFG__SEND_BAR_MASK	0x00000030L
+#define XPB_P2P_BAR_CFG__SNOOP_MASK	0x00000040L
+#define XPB_P2P_BAR_CFG__SEND_DIS_MASK	0x00000080L
+#define XPB_P2P_BAR_CFG__COMPRESS_DIS_MASK	0x00000100L
+#define XPB_P2P_BAR_CFG__UPDATE_DIS_MASK	0x00000200L
+#define XPB_P2P_BAR_CFG__REGBAR_FROM_SYSBAR_MASK	0x00000400L
+#define XPB_P2P_BAR_CFG__RD_EN_MASK	0x00000800L
+#define XPB_P2P_BAR_CFG__ATC_TRANSLATED_MASK	0x00001000L
+//XPB_P2P_BAR0
+#define XPB_P2P_BAR0__HOST_FLUSH__SHIFT	0x0
+#define XPB_P2P_BAR0__REG_SYS_BAR__SHIFT	0x4
+#define XPB_P2P_BAR0__MEM_SYS_BAR__SHIFT	0x8
+#define XPB_P2P_BAR0__VALID__SHIFT	0xc
+#define XPB_P2P_BAR0__SEND_DIS__SHIFT	0xd
+#define XPB_P2P_BAR0__COMPRESS_DIS__SHIFT	0xe
+#define XPB_P2P_BAR0__RESERVED__SHIFT	0xf
+#define XPB_P2P_BAR0__ADDRESS__SHIFT	0x10
+#define XPB_P2P_BAR0__HOST_FLUSH_MASK	0x0000000FL
+#define XPB_P2P_BAR0__REG_SYS_BAR_MASK	0x000000F0L
+#define XPB_P2P_BAR0__MEM_SYS_BAR_MASK	0x00000F00L
+#define XPB_P2P_BAR0__VALID_MASK	0x00001000L
+#define XPB_P2P_BAR0__SEND_DIS_MASK	0x00002000L
+#define XPB_P2P_BAR0__COMPRESS_DIS_MASK	0x00004000L
+#define XPB_P2P_BAR0__RESERVED_MASK	0x00008000L
+#define XPB_P2P_BAR0__ADDRESS_MASK	0xFFFF0000L
+//XPB_P2P_BAR1
+#define XPB_P2P_BAR1__HOST_FLUSH__SHIFT	0x0
+#define XPB_P2P_BAR1__REG_SYS_BAR__SHIFT	0x4
+#define XPB_P2P_BAR1__MEM_SYS_BAR__SHIFT	0x8
+#define XPB_P2P_BAR1__VALID__SHIFT	0xc
+#define XPB_P2P_BAR1__SEND_DIS__SHIFT	0xd
+#define XPB_P2P_BAR1__COMPRESS_DIS__SHIFT	0xe
+#define XPB_P2P_BAR1__RESERVED__SHIFT	0xf
+#define XPB_P2P_BAR1__ADDRESS__SHIFT	0x10
+#define XPB_P2P_BAR1__HOST_FLUSH_MASK	0x0000000FL
+#define XPB_P2P_BAR1__REG_SYS_BAR_MASK	0x000000F0L
+#define XPB_P2P_BAR1__MEM_SYS_BAR_MASK	0x00000F00L
+#define XPB_P2P_BAR1__VALID_MASK	0x00001000L
+#define XPB_P2P_BAR1__SEND_DIS_MASK	0x00002000L
+#define XPB_P2P_BAR1__COMPRESS_DIS_MASK	0x00004000L
+#define XPB_P2P_BAR1__RESERVED_MASK	0x00008000L
+#define XPB_P2P_BAR1__ADDRESS_MASK	0xFFFF0000L
+//XPB_P2P_BAR2
+#define XPB_P2P_BAR2__HOST_FLUSH__SHIFT	0x0
+#define XPB_P2P_BAR2__REG_SYS_BAR__SHIFT	0x4
+#define XPB_P2P_BAR2__MEM_SYS_BAR__SHIFT	0x8
+#define XPB_P2P_BAR2__VALID__SHIFT	0xc
+#define XPB_P2P_BAR2__SEND_DIS__SHIFT	0xd
+#define XPB_P2P_BAR2__COMPRESS_DIS__SHIFT	0xe
+#define XPB_P2P_BAR2__RESERVED__SHIFT	0xf
+#define XPB_P2P_BAR2__ADDRESS__SHIFT	0x10
+#define XPB_P2P_BAR2__HOST_FLUSH_MASK	0x0000000FL
+#define XPB_P2P_BAR2__REG_SYS_BAR_MASK	0x000000F0L
+#define XPB_P2P_BAR2__MEM_SYS_BAR_MASK	0x00000F00L
+#define XPB_P2P_BAR2__VALID_MASK	0x00001000L
+#define XPB_P2P_BAR2__SEND_DIS_MASK	0x00002000L
+#define XPB_P2P_BAR2__COMPRESS_DIS_MASK	0x00004000L
+#define XPB_P2P_BAR2__RESERVED_MASK	0x00008000L
+#define XPB_P2P_BAR2__ADDRESS_MASK	0xFFFF0000L
+//XPB_P2P_BAR3
+#define XPB_P2P_BAR3__HOST_FLUSH__SHIFT	0x0
+#define XPB_P2P_BAR3__REG_SYS_BAR__SHIFT	0x4
+#define XPB_P2P_BAR3__MEM_SYS_BAR__SHIFT	0x8
+#define XPB_P2P_BAR3__VALID__SHIFT	0xc
+#define XPB_P2P_BAR3__SEND_DIS__SHIFT	0xd
+#define XPB_P2P_BAR3__COMPRESS_DIS__SHIFT	0xe
+#define XPB_P2P_BAR3__RESERVED__SHIFT	0xf
+#define XPB_P2P_BAR3__ADDRESS__SHIFT	0x10
+#define XPB_P2P_BAR3__HOST_FLUSH_MASK	0x0000000FL
+#define XPB_P2P_BAR3__REG_SYS_BAR_MASK	0x000000F0L
+#define XPB_P2P_BAR3__MEM_SYS_BAR_MASK	0x00000F00L
+#define XPB_P2P_BAR3__VALID_MASK	0x00001000L
+#define XPB_P2P_BAR3__SEND_DIS_MASK	0x00002000L
+#define XPB_P2P_BAR3__COMPRESS_DIS_MASK	0x00004000L
+#define XPB_P2P_BAR3__RESERVED_MASK	0x00008000L
+#define XPB_P2P_BAR3__ADDRESS_MASK	0xFFFF0000L
+//XPB_P2P_BAR4
+#define XPB_P2P_BAR4__HOST_FLUSH__SHIFT	0x0
+#define XPB_P2P_BAR4__REG_SYS_BAR__SHIFT	0x4
+#define XPB_P2P_BAR4__MEM_SYS_BAR__SHIFT	0x8
+#define XPB_P2P_BAR4__VALID__SHIFT	0xc
+#define XPB_P2P_BAR4__SEND_DIS__SHIFT	0xd
+#define XPB_P2P_BAR4__COMPRESS_DIS__SHIFT	0xe
+#define XPB_P2P_BAR4__RESERVED__SHIFT	0xf
+#define XPB_P2P_BAR4__ADDRESS__SHIFT	0x10
+#define XPB_P2P_BAR4__HOST_FLUSH_MASK	0x0000000FL
+#define XPB_P2P_BAR4__REG_SYS_BAR_MASK	0x000000F0L
+#define XPB_P2P_BAR4__MEM_SYS_BAR_MASK	0x00000F00L
+#define XPB_P2P_BAR4__VALID_MASK	0x00001000L
+#define XPB_P2P_BAR4__SEND_DIS_MASK	0x00002000L
+#define XPB_P2P_BAR4__COMPRESS_DIS_MASK	0x00004000L
+#define XPB_P2P_BAR4__RESERVED_MASK	0x00008000L
+#define XPB_P2P_BAR4__ADDRESS_MASK	0xFFFF0000L
+//XPB_P2P_BAR5
+#define XPB_P2P_BAR5__HOST_FLUSH__SHIFT	0x0
+#define XPB_P2P_BAR5__REG_SYS_BAR__SHIFT	0x4
+#define XPB_P2P_BAR5__MEM_SYS_BAR__SHIFT	0x8
+#define XPB_P2P_BAR5__VALID__SHIFT	0xc
+#define XPB_P2P_BAR5__SEND_DIS__SHIFT	0xd
+#define XPB_P2P_BAR5__COMPRESS_DIS__SHIFT	0xe
+#define XPB_P2P_BAR5__RESERVED__SHIFT	0xf
+#define XPB_P2P_BAR5__ADDRESS__SHIFT	0x10
+#define XPB_P2P_BAR5__HOST_FLUSH_MASK	0x0000000FL
+#define XPB_P2P_BAR5__REG_SYS_BAR_MASK	0x000000F0L
+#define XPB_P2P_BAR5__MEM_SYS_BAR_MASK	0x00000F00L
+#define XPB_P2P_BAR5__VALID_MASK	0x00001000L
+#define XPB_P2P_BAR5__SEND_DIS_MASK	0x00002000L
+#define XPB_P2P_BAR5__COMPRESS_DIS_MASK	0x00004000L
+#define XPB_P2P_BAR5__RESERVED_MASK	0x00008000L
+#define XPB_P2P_BAR5__ADDRESS_MASK	0xFFFF0000L
+//XPB_P2P_BAR6
+#define XPB_P2P_BAR6__HOST_FLUSH__SHIFT	0x0
+#define XPB_P2P_BAR6__REG_SYS_BAR__SHIFT	0x4
+#define XPB_P2P_BAR6__MEM_SYS_BAR__SHIFT	0x8
+#define XPB_P2P_BAR6__VALID__SHIFT	0xc
+#define XPB_P2P_BAR6__SEND_DIS__SHIFT	0xd
+#define XPB_P2P_BAR6__COMPRESS_DIS__SHIFT	0xe
+#define XPB_P2P_BAR6__RESERVED__SHIFT	0xf
+#define XPB_P2P_BAR6__ADDRESS__SHIFT	0x10
+#define XPB_P2P_BAR6__HOST_FLUSH_MASK	0x0000000FL
+#define XPB_P2P_BAR6__REG_SYS_BAR_MASK	0x000000F0L
+#define XPB_P2P_BAR6__MEM_SYS_BAR_MASK	0x00000F00L
+#define XPB_P2P_BAR6__VALID_MASK	0x00001000L
+#define XPB_P2P_BAR6__SEND_DIS_MASK	0x00002000L
+#define XPB_P2P_BAR6__COMPRESS_DIS_MASK	0x00004000L
+#define XPB_P2P_BAR6__RESERVED_MASK	0x00008000L
+#define XPB_P2P_BAR6__ADDRESS_MASK	0xFFFF0000L
+//XPB_P2P_BAR7
+#define XPB_P2P_BAR7__HOST_FLUSH__SHIFT	0x0
+#define XPB_P2P_BAR7__REG_SYS_BAR__SHIFT	0x4
+#define XPB_P2P_BAR7__MEM_SYS_BAR__SHIFT	0x8
+#define XPB_P2P_BAR7__VALID__SHIFT	0xc
+#define XPB_P2P_BAR7__SEND_DIS__SHIFT	0xd
+#define XPB_P2P_BAR7__COMPRESS_DIS__SHIFT	0xe
+#define XPB_P2P_BAR7__RESERVED__SHIFT	0xf
+#define XPB_P2P_BAR7__ADDRESS__SHIFT	0x10
+#define XPB_P2P_BAR7__HOST_FLUSH_MASK	0x0000000FL
+#define XPB_P2P_BAR7__REG_SYS_BAR_MASK	0x000000F0L
+#define XPB_P2P_BAR7__MEM_SYS_BAR_MASK	0x00000F00L
+#define XPB_P2P_BAR7__VALID_MASK	0x00001000L
+#define XPB_P2P_BAR7__SEND_DIS_MASK	0x00002000L
+#define XPB_P2P_BAR7__COMPRESS_DIS_MASK	0x00004000L
+#define XPB_P2P_BAR7__RESERVED_MASK	0x00008000L
+#define XPB_P2P_BAR7__ADDRESS_MASK	0xFFFF0000L
+//XPB_P2P_BAR_SETUP
+#define XPB_P2P_BAR_SETUP__SEL__SHIFT	0x0
+#define XPB_P2P_BAR_SETUP__REG_SYS_BAR__SHIFT	0x8
+#define XPB_P2P_BAR_SETUP__VALID__SHIFT	0xc
+#define XPB_P2P_BAR_SETUP__SEND_DIS__SHIFT	0xd
+#define XPB_P2P_BAR_SETUP__COMPRESS_DIS__SHIFT	0xe
+#define XPB_P2P_BAR_SETUP__RESERVED__SHIFT	0xf
+#define XPB_P2P_BAR_SETUP__ADDRESS__SHIFT	0x10
+#define XPB_P2P_BAR_SETUP__SEL_MASK	0x000000FFL
+#define XPB_P2P_BAR_SETUP__REG_SYS_BAR_MASK	0x00000F00L
+#define XPB_P2P_BAR_SETUP__VALID_MASK	0x00001000L
+#define XPB_P2P_BAR_SETUP__SEND_DIS_MASK	0x00002000L
+#define XPB_P2P_BAR_SETUP__COMPRESS_DIS_MASK	0x00004000L
+#define XPB_P2P_BAR_SETUP__RESERVED_MASK	0x00008000L
+#define XPB_P2P_BAR_SETUP__ADDRESS_MASK	0xFFFF0000L
+//XPB_P2P_BAR_DELTA_ABOVE
+#define XPB_P2P_BAR_DELTA_ABOVE__EN__SHIFT	0x0
+#define XPB_P2P_BAR_DELTA_ABOVE__DELTA__SHIFT	0x8
+#define XPB_P2P_BAR_DELTA_ABOVE__EN_MASK	0x000000FFL
+#define XPB_P2P_BAR_DELTA_ABOVE__DELTA_MASK	0x0FFFFF00L
+//XPB_P2P_BAR_DELTA_BELOW
+#define XPB_P2P_BAR_DELTA_BELOW__EN__SHIFT	0x0
+#define XPB_P2P_BAR_DELTA_BELOW__DELTA__SHIFT	0x8
+#define XPB_P2P_BAR_DELTA_BELOW__EN_MASK	0x000000FFL
+#define XPB_P2P_BAR_DELTA_BELOW__DELTA_MASK	0x0FFFFF00L
+//XPB_PEER_SYS_BAR0
+#define XPB_PEER_SYS_BAR0__VALID__SHIFT	0x0
+#define XPB_PEER_SYS_BAR0__ADDR__SHIFT	0x1
+#define XPB_PEER_SYS_BAR0__VALID_MASK	0x00000001L
+#define XPB_PEER_SYS_BAR0__ADDR_MASK	0xFFFFFFFEL
+//XPB_PEER_SYS_BAR1
+#define XPB_PEER_SYS_BAR1__VALID__SHIFT	0x0
+#define XPB_PEER_SYS_BAR1__ADDR__SHIFT	0x1
+#define XPB_PEER_SYS_BAR1__VALID_MASK	0x00000001L
+#define XPB_PEER_SYS_BAR1__ADDR_MASK	0xFFFFFFFEL
+//XPB_PEER_SYS_BAR2
+#define XPB_PEER_SYS_BAR2__VALID__SHIFT	0x0
+#define XPB_PEER_SYS_BAR2__ADDR__SHIFT	0x1
+#define XPB_PEER_SYS_BAR2__VALID_MASK	0x00000001L
+#define XPB_PEER_SYS_BAR2__ADDR_MASK	0xFFFFFFFEL
+//XPB_PEER_SYS_BAR3
+#define XPB_PEER_SYS_BAR3__VALID__SHIFT	0x0
+#define XPB_PEER_SYS_BAR3__ADDR__SHIFT	0x1
+#define XPB_PEER_SYS_BAR3__VALID_MASK	0x00000001L
+#define XPB_PEER_SYS_BAR3__ADDR_MASK	0xFFFFFFFEL
+//XPB_PEER_SYS_BAR4
+#define XPB_PEER_SYS_BAR4__VALID__SHIFT	0x0
+#define XPB_PEER_SYS_BAR4__ADDR__SHIFT	0x1
+#define XPB_PEER_SYS_BAR4__VALID_MASK	0x00000001L
+#define XPB_PEER_SYS_BAR4__ADDR_MASK	0xFFFFFFFEL
+//XPB_PEER_SYS_BAR5
+#define XPB_PEER_SYS_BAR5__VALID__SHIFT	0x0
+#define XPB_PEER_SYS_BAR5__ADDR__SHIFT	0x1
+#define XPB_PEER_SYS_BAR5__VALID_MASK	0x00000001L
+#define XPB_PEER_SYS_BAR5__ADDR_MASK	0xFFFFFFFEL
+//XPB_PEER_SYS_BAR6
+#define XPB_PEER_SYS_BAR6__VALID__SHIFT	0x0
+#define XPB_PEER_SYS_BAR6__ADDR__SHIFT	0x1
+#define XPB_PEER_SYS_BAR6__VALID_MASK	0x00000001L
+#define XPB_PEER_SYS_BAR6__ADDR_MASK	0xFFFFFFFEL
+//XPB_PEER_SYS_BAR7
+#define XPB_PEER_SYS_BAR7__VALID__SHIFT	0x0
+#define XPB_PEER_SYS_BAR7__ADDR__SHIFT	0x1
+#define XPB_PEER_SYS_BAR7__VALID_MASK	0x00000001L
+#define XPB_PEER_SYS_BAR7__ADDR_MASK	0xFFFFFFFEL
+//XPB_PEER_SYS_BAR8
+#define XPB_PEER_SYS_BAR8__VALID__SHIFT	0x0
+#define XPB_PEER_SYS_BAR8__ADDR__SHIFT	0x1
+#define XPB_PEER_SYS_BAR8__VALID_MASK	0x00000001L
+#define XPB_PEER_SYS_BAR8__ADDR_MASK	0xFFFFFFFEL
+//XPB_PEER_SYS_BAR9
+#define XPB_PEER_SYS_BAR9__VALID__SHIFT	0x0
+#define XPB_PEER_SYS_BAR9__ADDR__SHIFT	0x1
+#define XPB_PEER_SYS_BAR9__VALID_MASK	0x00000001L
+#define XPB_PEER_SYS_BAR9__ADDR_MASK	0xFFFFFFFEL
+//XPB_XDMA_PEER_SYS_BAR0
+#define XPB_XDMA_PEER_SYS_BAR0__VALID__SHIFT	0x0
+#define XPB_XDMA_PEER_SYS_BAR0__ADDR__SHIFT	0x1
+#define XPB_XDMA_PEER_SYS_BAR0__VALID_MASK	0x00000001L
+#define XPB_XDMA_PEER_SYS_BAR0__ADDR_MASK	0xFFFFFFFEL
+//XPB_XDMA_PEER_SYS_BAR1
+#define XPB_XDMA_PEER_SYS_BAR1__VALID__SHIFT	0x0
+#define XPB_XDMA_PEER_SYS_BAR1__ADDR__SHIFT	0x1
+#define XPB_XDMA_PEER_SYS_BAR1__VALID_MASK	0x00000001L
+#define XPB_XDMA_PEER_SYS_BAR1__ADDR_MASK	0xFFFFFFFEL
+//XPB_XDMA_PEER_SYS_BAR2
+#define XPB_XDMA_PEER_SYS_BAR2__VALID__SHIFT	0x0
+#define XPB_XDMA_PEER_SYS_BAR2__ADDR__SHIFT	0x1
+#define XPB_XDMA_PEER_SYS_BAR2__VALID_MASK	0x00000001L
+#define XPB_XDMA_PEER_SYS_BAR2__ADDR_MASK	0xFFFFFFFEL
+//XPB_XDMA_PEER_SYS_BAR3
+#define XPB_XDMA_PEER_SYS_BAR3__VALID__SHIFT	0x0
+#define XPB_XDMA_PEER_SYS_BAR3__ADDR__SHIFT	0x1
+#define XPB_XDMA_PEER_SYS_BAR3__VALID_MASK	0x00000001L
+#define XPB_XDMA_PEER_SYS_BAR3__ADDR_MASK	0xFFFFFFFEL
+//XPB_CLK_GAT
+#define XPB_CLK_GAT__ONDLY__SHIFT	0x0
+#define XPB_CLK_GAT__OFFDLY__SHIFT	0x6
+#define XPB_CLK_GAT__RDYDLY__SHIFT	0xc
+#define XPB_CLK_GAT__ENABLE__SHIFT	0x12
+#define XPB_CLK_GAT__MEM_LS_ENABLE__SHIFT	0x13
+#define XPB_CLK_GAT__ONDLY_MASK	0x0000003FL
+#define XPB_CLK_GAT__OFFDLY_MASK	0x00000FC0L
+#define XPB_CLK_GAT__RDYDLY_MASK	0x0003F000L
+#define XPB_CLK_GAT__ENABLE_MASK	0x00040000L
+#define XPB_CLK_GAT__MEM_LS_ENABLE_MASK	0x00080000L
+//XPB_INTF_CFG
+#define XPB_INTF_CFG__RPB_WRREQ_CRD__SHIFT	0x0
+#define XPB_INTF_CFG__MC_WRRET_ASK__SHIFT	0x8
+#define XPB_INTF_CFG__XSP_REQ_CRD__SHIFT	0x10
+#define XPB_INTF_CFG__BIF_REG_SNOOP_SEL__SHIFT	0x17
+#define XPB_INTF_CFG__BIF_REG_SNOOP_VAL__SHIFT	0x18
+#define XPB_INTF_CFG__BIF_MEM_SNOOP_SEL__SHIFT	0x19
+#define XPB_INTF_CFG__BIF_MEM_SNOOP_VAL__SHIFT	0x1a
+#define XPB_INTF_CFG__XSP_SNOOP_SEL__SHIFT	0x1b
+#define XPB_INTF_CFG__XSP_SNOOP_VAL__SHIFT	0x1d
+#define XPB_INTF_CFG__XSP_ORDERING_SEL__SHIFT	0x1e
+#define XPB_INTF_CFG__XSP_ORDERING_VAL__SHIFT	0x1f
+#define XPB_INTF_CFG__RPB_WRREQ_CRD_MASK	0x000000FFL
+#define XPB_INTF_CFG__MC_WRRET_ASK_MASK	0x0000FF00L
+#define XPB_INTF_CFG__XSP_REQ_CRD_MASK	0x007F0000L
+#define XPB_INTF_CFG__BIF_REG_SNOOP_SEL_MASK	0x00800000L
+#define XPB_INTF_CFG__BIF_REG_SNOOP_VAL_MASK	0x01000000L
+#define XPB_INTF_CFG__BIF_MEM_SNOOP_SEL_MASK	0x02000000L
+#define XPB_INTF_CFG__BIF_MEM_SNOOP_VAL_MASK	0x04000000L
+#define XPB_INTF_CFG__XSP_SNOOP_SEL_MASK	0x18000000L
+#define XPB_INTF_CFG__XSP_SNOOP_VAL_MASK	0x20000000L
+#define XPB_INTF_CFG__XSP_ORDERING_SEL_MASK	0x40000000L
+#define XPB_INTF_CFG__XSP_ORDERING_VAL_MASK	0x80000000L
+//XPB_INTF_STS
+#define XPB_INTF_STS__RPB_WRREQ_CRD__SHIFT	0x0
+#define XPB_INTF_STS__XSP_REQ_CRD__SHIFT	0x8
+#define XPB_INTF_STS__HOP_DATA_BUF_FULL__SHIFT	0xf
+#define XPB_INTF_STS__HOP_ATTR_BUF_FULL__SHIFT	0x10
+#define XPB_INTF_STS__CNS_BUF_FULL__SHIFT	0x11
+#define XPB_INTF_STS__CNS_BUF_BUSY__SHIFT	0x12
+#define XPB_INTF_STS__RPB_RDREQ_CRD__SHIFT	0x13
+#define XPB_INTF_STS__RPB_WRREQ_CRD_MASK	0x000000FFL
+#define XPB_INTF_STS__XSP_REQ_CRD_MASK	0x00007F00L
+#define XPB_INTF_STS__HOP_DATA_BUF_FULL_MASK	0x00008000L
+#define XPB_INTF_STS__HOP_ATTR_BUF_FULL_MASK	0x00010000L
+#define XPB_INTF_STS__CNS_BUF_FULL_MASK	0x00020000L
+#define XPB_INTF_STS__CNS_BUF_BUSY_MASK	0x00040000L
+#define XPB_INTF_STS__RPB_RDREQ_CRD_MASK	0x07F80000L
+//XPB_PIPE_STS
+#define XPB_PIPE_STS__WCB_ANY_PBUF__SHIFT	0x0
+#define XPB_PIPE_STS__WCB_HST_DATA_BUF_CNT__SHIFT	0x1
+#define XPB_PIPE_STS__WCB_SID_DATA_BUF_CNT__SHIFT	0x8
+#define XPB_PIPE_STS__WCB_HST_RD_PTR_BUF_FULL__SHIFT	0xf
+#define XPB_PIPE_STS__WCB_SID_RD_PTR_BUF_FULL__SHIFT	0x10
+#define XPB_PIPE_STS__WCB_HST_REQ_FIFO_FULL__SHIFT	0x11
+#define XPB_PIPE_STS__WCB_SID_REQ_FIFO_FULL__SHIFT	0x12
+#define XPB_PIPE_STS__WCB_HST_REQ_OBUF_FULL__SHIFT	0x13
+#define XPB_PIPE_STS__WCB_SID_REQ_OBUF_FULL__SHIFT	0x14
+#define XPB_PIPE_STS__WCB_HST_DATA_OBUF_FULL__SHIFT	0x15
+#define XPB_PIPE_STS__WCB_SID_DATA_OBUF_FULL__SHIFT	0x16
+#define XPB_PIPE_STS__RET_BUF_FULL__SHIFT	0x17
+#define XPB_PIPE_STS__XPB_CLK_BUSY_BITS__SHIFT	0x18
+#define XPB_PIPE_STS__WCB_ANY_PBUF_MASK	0x00000001L
+#define XPB_PIPE_STS__WCB_HST_DATA_BUF_CNT_MASK	0x000000FEL
+#define XPB_PIPE_STS__WCB_SID_DATA_BUF_CNT_MASK	0x00007F00L
+#define XPB_PIPE_STS__WCB_HST_RD_PTR_BUF_FULL_MASK	0x00008000L
+#define XPB_PIPE_STS__WCB_SID_RD_PTR_BUF_FULL_MASK	0x00010000L
+#define XPB_PIPE_STS__WCB_HST_REQ_FIFO_FULL_MASK	0x00020000L
+#define XPB_PIPE_STS__WCB_SID_REQ_FIFO_FULL_MASK	0x00040000L
+#define XPB_PIPE_STS__WCB_HST_REQ_OBUF_FULL_MASK	0x00080000L
+#define XPB_PIPE_STS__WCB_SID_REQ_OBUF_FULL_MASK	0x00100000L
+#define XPB_PIPE_STS__WCB_HST_DATA_OBUF_FULL_MASK	0x00200000L
+#define XPB_PIPE_STS__WCB_SID_DATA_OBUF_FULL_MASK	0x00400000L
+#define XPB_PIPE_STS__RET_BUF_FULL_MASK	0x00800000L
+#define XPB_PIPE_STS__XPB_CLK_BUSY_BITS_MASK	0xFF000000L
+//XPB_SUB_CTRL
+#define XPB_SUB_CTRL__WRREQ_BYPASS_XPB__SHIFT	0x0
+#define XPB_SUB_CTRL__STALL_CNS_RTR_REQ__SHIFT	0x1
+#define XPB_SUB_CTRL__STALL_RTR_RPB_WRREQ__SHIFT	0x2
+#define XPB_SUB_CTRL__STALL_RTR_MAP_REQ__SHIFT	0x3
+#define XPB_SUB_CTRL__STALL_MAP_WCB_REQ__SHIFT	0x4
+#define XPB_SUB_CTRL__STALL_WCB_SID_REQ__SHIFT	0x5
+#define XPB_SUB_CTRL__STALL_MC_XSP_REQ_SEND__SHIFT	0x6
+#define XPB_SUB_CTRL__STALL_WCB_HST_REQ__SHIFT	0x7
+#define XPB_SUB_CTRL__STALL_HST_HOP_REQ__SHIFT	0x8
+#define XPB_SUB_CTRL__STALL_XPB_RPB_REQ_ATTR__SHIFT	0x9
+#define XPB_SUB_CTRL__RESET_CNS__SHIFT	0xa
+#define XPB_SUB_CTRL__RESET_RTR__SHIFT	0xb
+#define XPB_SUB_CTRL__RESET_RET__SHIFT	0xc
+#define XPB_SUB_CTRL__RESET_MAP__SHIFT	0xd
+#define XPB_SUB_CTRL__RESET_WCB__SHIFT	0xe
+#define XPB_SUB_CTRL__RESET_HST__SHIFT	0xf
+#define XPB_SUB_CTRL__RESET_HOP__SHIFT	0x10
+#define XPB_SUB_CTRL__RESET_SID__SHIFT	0x11
+#define XPB_SUB_CTRL__RESET_SRB__SHIFT	0x12
+#define XPB_SUB_CTRL__RESET_CGR__SHIFT	0x13
+#define XPB_SUB_CTRL__WRREQ_BYPASS_XPB_MASK	0x00000001L
+#define XPB_SUB_CTRL__STALL_CNS_RTR_REQ_MASK	0x00000002L
+#define XPB_SUB_CTRL__STALL_RTR_RPB_WRREQ_MASK	0x00000004L
+#define XPB_SUB_CTRL__STALL_RTR_MAP_REQ_MASK	0x00000008L
+#define XPB_SUB_CTRL__STALL_MAP_WCB_REQ_MASK	0x00000010L
+#define XPB_SUB_CTRL__STALL_WCB_SID_REQ_MASK	0x00000020L
+#define XPB_SUB_CTRL__STALL_MC_XSP_REQ_SEND_MASK	0x00000040L
+#define XPB_SUB_CTRL__STALL_WCB_HST_REQ_MASK	0x00000080L
+#define XPB_SUB_CTRL__STALL_HST_HOP_REQ_MASK	0x00000100L
+#define XPB_SUB_CTRL__STALL_XPB_RPB_REQ_ATTR_MASK	0x00000200L
+#define XPB_SUB_CTRL__RESET_CNS_MASK	0x00000400L
+#define XPB_SUB_CTRL__RESET_RTR_MASK	0x00000800L
+#define XPB_SUB_CTRL__RESET_RET_MASK	0x00001000L
+#define XPB_SUB_CTRL__RESET_MAP_MASK	0x00002000L
+#define XPB_SUB_CTRL__RESET_WCB_MASK	0x00004000L
+#define XPB_SUB_CTRL__RESET_HST_MASK	0x00008000L
+#define XPB_SUB_CTRL__RESET_HOP_MASK	0x00010000L
+#define XPB_SUB_CTRL__RESET_SID_MASK	0x00020000L
+#define XPB_SUB_CTRL__RESET_SRB_MASK	0x00040000L
+#define XPB_SUB_CTRL__RESET_CGR_MASK	0x00080000L
+//XPB_MAP_INVERT_FLUSH_NUM_LSB
+#define XPB_MAP_INVERT_FLUSH_NUM_LSB__ALTER_FLUSH_NUM__SHIFT	0x0
+#define XPB_MAP_INVERT_FLUSH_NUM_LSB__ALTER_FLUSH_NUM_MASK	0x0000FFFFL
+//XPB_PERF_KNOBS
+#define XPB_PERF_KNOBS__CNS_FIFO_DEPTH__SHIFT	0x0
+#define XPB_PERF_KNOBS__WCB_HST_FIFO_DEPTH__SHIFT	0x6
+#define XPB_PERF_KNOBS__WCB_SID_FIFO_DEPTH__SHIFT	0xc
+#define XPB_PERF_KNOBS__CNS_FIFO_DEPTH_MASK	0x0000003FL
+#define XPB_PERF_KNOBS__WCB_HST_FIFO_DEPTH_MASK	0x00000FC0L
+#define XPB_PERF_KNOBS__WCB_SID_FIFO_DEPTH_MASK	0x0003F000L
+//XPB_STICKY
+#define XPB_STICKY__BITS__SHIFT	0x0
+#define XPB_STICKY__BITS_MASK	0xFFFFFFFFL
+//XPB_STICKY_W1C
+#define XPB_STICKY_W1C__BITS__SHIFT	0x0
+#define XPB_STICKY_W1C__BITS_MASK	0xFFFFFFFFL
+//XPB_MISC_CFG
+#define XPB_MISC_CFG__FIELDNAME0__SHIFT	0x0
+#define XPB_MISC_CFG__FIELDNAME1__SHIFT	0x8
+#define XPB_MISC_CFG__FIELDNAME2__SHIFT	0x10
+#define XPB_MISC_CFG__FIELDNAME3__SHIFT	0x18
+#define XPB_MISC_CFG__TRIGGERNAME__SHIFT	0x1f
+#define XPB_MISC_CFG__FIELDNAME0_MASK	0x000000FFL
+#define XPB_MISC_CFG__FIELDNAME1_MASK	0x0000FF00L
+#define XPB_MISC_CFG__FIELDNAME2_MASK	0x00FF0000L
+#define XPB_MISC_CFG__FIELDNAME3_MASK	0x7F000000L
+#define XPB_MISC_CFG__TRIGGERNAME_MASK	0x80000000L
+//XPB_INTF_CFG2
+#define XPB_INTF_CFG2__RPB_RDREQ_CRD__SHIFT	0x0
+#define XPB_INTF_CFG2__RPB_RDREQ_CRD_MASK	0x000000FFL
+//XPB_CLG_EXTRA_RD
+#define XPB_CLG_EXTRA_RD__CMP0_HIGH__SHIFT	0x0
+#define XPB_CLG_EXTRA_RD__CMP0_LOW__SHIFT	0x6
+#define XPB_CLG_EXTRA_RD__VLD0__SHIFT	0xb
+#define XPB_CLG_EXTRA_RD__CLG0_NUM__SHIFT	0xc
+#define XPB_CLG_EXTRA_RD__CMP1_HIGH__SHIFT	0xf
+#define XPB_CLG_EXTRA_RD__CMP1_LOW__SHIFT	0x15
+#define XPB_CLG_EXTRA_RD__VLD1__SHIFT	0x1a
+#define XPB_CLG_EXTRA_RD__CLG1_NUM__SHIFT	0x1b
+#define XPB_CLG_EXTRA_RD__CMP0_HIGH_MASK	0x0000003FL
+#define XPB_CLG_EXTRA_RD__CMP0_LOW_MASK	0x000007C0L
+#define XPB_CLG_EXTRA_RD__VLD0_MASK	0x00000800L
+#define XPB_CLG_EXTRA_RD__CLG0_NUM_MASK	0x00007000L
+#define XPB_CLG_EXTRA_RD__CMP1_HIGH_MASK	0x001F8000L
+#define XPB_CLG_EXTRA_RD__CMP1_LOW_MASK	0x03E00000L
+#define XPB_CLG_EXTRA_RD__VLD1_MASK	0x04000000L
+#define XPB_CLG_EXTRA_RD__CLG1_NUM_MASK	0x38000000L
+//XPB_CLG_EXTRA_MSK_RD
+#define XPB_CLG_EXTRA_MSK_RD__MSK0_HIGH__SHIFT	0x0
+#define XPB_CLG_EXTRA_MSK_RD__MSK0_LOW__SHIFT	0x6
+#define XPB_CLG_EXTRA_MSK_RD__MSK1_HIGH__SHIFT	0xb
+#define XPB_CLG_EXTRA_MSK_RD__MSK1_LOW__SHIFT	0x11
+#define XPB_CLG_EXTRA_MSK_RD__MSK0_HIGH_MASK	0x0000003FL
+#define XPB_CLG_EXTRA_MSK_RD__MSK0_LOW_MASK	0x000007C0L
+#define XPB_CLG_EXTRA_MSK_RD__MSK1_HIGH_MASK	0x0001F800L
+#define XPB_CLG_EXTRA_MSK_RD__MSK1_LOW_MASK	0x003E0000L
+//XPB_CLG_GFX_MATCH
+#define XPB_CLG_GFX_MATCH__FARBIRC0_ID__SHIFT	0x0
+#define XPB_CLG_GFX_MATCH__FARBIRC1_ID__SHIFT	0x6
+#define XPB_CLG_GFX_MATCH__FARBIRC2_ID__SHIFT	0xc
+#define XPB_CLG_GFX_MATCH__FARBIRC3_ID__SHIFT	0x12
+#define XPB_CLG_GFX_MATCH__FARBIRC0_VLD__SHIFT	0x18
+#define XPB_CLG_GFX_MATCH__FARBIRC1_VLD__SHIFT	0x19
+#define XPB_CLG_GFX_MATCH__FARBIRC2_VLD__SHIFT	0x1a
+#define XPB_CLG_GFX_MATCH__FARBIRC3_VLD__SHIFT	0x1b
+#define XPB_CLG_GFX_MATCH__FARBIRC0_ID_MASK	0x0000003FL
+#define XPB_CLG_GFX_MATCH__FARBIRC1_ID_MASK	0x00000FC0L
+#define XPB_CLG_GFX_MATCH__FARBIRC2_ID_MASK	0x0003F000L
+#define XPB_CLG_GFX_MATCH__FARBIRC3_ID_MASK	0x00FC0000L
+#define XPB_CLG_GFX_MATCH__FARBIRC0_VLD_MASK	0x01000000L
+#define XPB_CLG_GFX_MATCH__FARBIRC1_VLD_MASK	0x02000000L
+#define XPB_CLG_GFX_MATCH__FARBIRC2_VLD_MASK	0x04000000L
+#define XPB_CLG_GFX_MATCH__FARBIRC3_VLD_MASK	0x08000000L
+//XPB_CLG_GFX_MATCH_MSK
+#define XPB_CLG_GFX_MATCH_MSK__FARBIRC0_ID_MSK__SHIFT	0x0
+#define XPB_CLG_GFX_MATCH_MSK__FARBIRC1_ID_MSK__SHIFT	0x6
+#define XPB_CLG_GFX_MATCH_MSK__FARBIRC2_ID_MSK__SHIFT	0xc
+#define XPB_CLG_GFX_MATCH_MSK__FARBIRC3_ID_MSK__SHIFT	0x12
+#define XPB_CLG_GFX_MATCH_MSK__FARBIRC0_ID_MSK_MASK	0x0000003FL
+#define XPB_CLG_GFX_MATCH_MSK__FARBIRC1_ID_MSK_MASK	0x00000FC0L
+#define XPB_CLG_GFX_MATCH_MSK__FARBIRC2_ID_MSK_MASK	0x0003F000L
+#define XPB_CLG_GFX_MATCH_MSK__FARBIRC3_ID_MSK_MASK	0x00FC0000L
+//XPB_CLG_MM_MATCH
+#define XPB_CLG_MM_MATCH__FARBIRC0_ID__SHIFT	0x0
+#define XPB_CLG_MM_MATCH__FARBIRC1_ID__SHIFT	0x6
+#define XPB_CLG_MM_MATCH__FARBIRC2_ID__SHIFT	0xc
+#define XPB_CLG_MM_MATCH__FARBIRC3_ID__SHIFT	0x12
+#define XPB_CLG_MM_MATCH__FARBIRC0_VLD__SHIFT	0x18
+#define XPB_CLG_MM_MATCH__FARBIRC1_VLD__SHIFT	0x19
+#define XPB_CLG_MM_MATCH__FARBIRC2_VLD__SHIFT	0x1a
+#define XPB_CLG_MM_MATCH__FARBIRC3_VLD__SHIFT	0x1b
+#define XPB_CLG_MM_MATCH__FARBIRC0_ID_MASK	0x0000003FL
+#define XPB_CLG_MM_MATCH__FARBIRC1_ID_MASK	0x00000FC0L
+#define XPB_CLG_MM_MATCH__FARBIRC2_ID_MASK	0x0003F000L
+#define XPB_CLG_MM_MATCH__FARBIRC3_ID_MASK	0x00FC0000L
+#define XPB_CLG_MM_MATCH__FARBIRC0_VLD_MASK	0x01000000L
+#define XPB_CLG_MM_MATCH__FARBIRC1_VLD_MASK	0x02000000L
+#define XPB_CLG_MM_MATCH__FARBIRC2_VLD_MASK	0x04000000L
+#define XPB_CLG_MM_MATCH__FARBIRC3_VLD_MASK	0x08000000L
+//XPB_CLG_MM_MATCH_MSK
+#define XPB_CLG_MM_MATCH_MSK__FARBIRC0_ID_MSK__SHIFT	0x0
+#define XPB_CLG_MM_MATCH_MSK__FARBIRC1_ID_MSK__SHIFT	0x6
+#define XPB_CLG_MM_MATCH_MSK__FARBIRC2_ID_MSK__SHIFT	0xc
+#define XPB_CLG_MM_MATCH_MSK__FARBIRC3_ID_MSK__SHIFT	0x12
+#define XPB_CLG_MM_MATCH_MSK__FARBIRC0_ID_MSK_MASK	0x0000003FL
+#define XPB_CLG_MM_MATCH_MSK__FARBIRC1_ID_MSK_MASK	0x00000FC0L
+#define XPB_CLG_MM_MATCH_MSK__FARBIRC2_ID_MSK_MASK	0x0003F000L
+#define XPB_CLG_MM_MATCH_MSK__FARBIRC3_ID_MSK_MASK	0x00FC0000L
+//XPB_CLG_GFX_UNITID_MAPPING0
+#define XPB_CLG_GFX_UNITID_MAPPING0__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_GFX_UNITID_MAPPING0__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_GFX_UNITID_MAPPING0__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_GFX_UNITID_MAPPING0__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_GFX_UNITID_MAPPING0__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_GFX_UNITID_MAPPING0__DEST_CLG_NUM_MASK	0x000001C0L
+//XPB_CLG_GFX_UNITID_MAPPING1
+#define XPB_CLG_GFX_UNITID_MAPPING1__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_GFX_UNITID_MAPPING1__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_GFX_UNITID_MAPPING1__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_GFX_UNITID_MAPPING1__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_GFX_UNITID_MAPPING1__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_GFX_UNITID_MAPPING1__DEST_CLG_NUM_MASK	0x000001C0L
+//XPB_CLG_GFX_UNITID_MAPPING2
+#define XPB_CLG_GFX_UNITID_MAPPING2__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_GFX_UNITID_MAPPING2__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_GFX_UNITID_MAPPING2__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_GFX_UNITID_MAPPING2__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_GFX_UNITID_MAPPING2__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_GFX_UNITID_MAPPING2__DEST_CLG_NUM_MASK	0x000001C0L
+//XPB_CLG_GFX_UNITID_MAPPING3
+#define XPB_CLG_GFX_UNITID_MAPPING3__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_GFX_UNITID_MAPPING3__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_GFX_UNITID_MAPPING3__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_GFX_UNITID_MAPPING3__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_GFX_UNITID_MAPPING3__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_GFX_UNITID_MAPPING3__DEST_CLG_NUM_MASK	0x000001C0L
+//XPB_CLG_GFX_UNITID_MAPPING4
+#define XPB_CLG_GFX_UNITID_MAPPING4__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_GFX_UNITID_MAPPING4__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_GFX_UNITID_MAPPING4__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_GFX_UNITID_MAPPING4__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_GFX_UNITID_MAPPING4__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_GFX_UNITID_MAPPING4__DEST_CLG_NUM_MASK	0x000001C0L
+//XPB_CLG_GFX_UNITID_MAPPING5
+#define XPB_CLG_GFX_UNITID_MAPPING5__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_GFX_UNITID_MAPPING5__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_GFX_UNITID_MAPPING5__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_GFX_UNITID_MAPPING5__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_GFX_UNITID_MAPPING5__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_GFX_UNITID_MAPPING5__DEST_CLG_NUM_MASK	0x000001C0L
+//XPB_CLG_GFX_UNITID_MAPPING6
+#define XPB_CLG_GFX_UNITID_MAPPING6__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_GFX_UNITID_MAPPING6__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_GFX_UNITID_MAPPING6__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_GFX_UNITID_MAPPING6__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_GFX_UNITID_MAPPING6__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_GFX_UNITID_MAPPING6__DEST_CLG_NUM_MASK	0x000001C0L
+//XPB_CLG_GFX_UNITID_MAPPING7
+#define XPB_CLG_GFX_UNITID_MAPPING7__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_GFX_UNITID_MAPPING7__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_GFX_UNITID_MAPPING7__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_GFX_UNITID_MAPPING7__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_GFX_UNITID_MAPPING7__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_GFX_UNITID_MAPPING7__DEST_CLG_NUM_MASK	0x000001C0L
+//XPB_CLG_MM_UNITID_MAPPING0
+#define XPB_CLG_MM_UNITID_MAPPING0__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_MM_UNITID_MAPPING0__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_MM_UNITID_MAPPING0__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_MM_UNITID_MAPPING0__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_MM_UNITID_MAPPING0__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_MM_UNITID_MAPPING0__DEST_CLG_NUM_MASK	0x000001C0L
+//XPB_CLG_MM_UNITID_MAPPING1
+#define XPB_CLG_MM_UNITID_MAPPING1__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_MM_UNITID_MAPPING1__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_MM_UNITID_MAPPING1__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_MM_UNITID_MAPPING1__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_MM_UNITID_MAPPING1__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_MM_UNITID_MAPPING1__DEST_CLG_NUM_MASK	0x000001C0L
+//XPB_CLG_MM_UNITID_MAPPING2
+#define XPB_CLG_MM_UNITID_MAPPING2__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_MM_UNITID_MAPPING2__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_MM_UNITID_MAPPING2__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_MM_UNITID_MAPPING2__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_MM_UNITID_MAPPING2__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_MM_UNITID_MAPPING2__DEST_CLG_NUM_MASK	0x000001C0L
+//XPB_CLG_MM_UNITID_MAPPING3
+#define XPB_CLG_MM_UNITID_MAPPING3__UNITID_LOW__SHIFT	0x0
+#define XPB_CLG_MM_UNITID_MAPPING3__UNITID_VLD__SHIFT	0x5
+#define XPB_CLG_MM_UNITID_MAPPING3__DEST_CLG_NUM__SHIFT	0x6
+#define XPB_CLG_MM_UNITID_MAPPING3__UNITID_LOW_MASK	0x0000001FL
+#define XPB_CLG_MM_UNITID_MAPPING3__UNITID_VLD_MASK	0x00000020L
+#define XPB_CLG_MM_UNITID_MAPPING3__DEST_CLG_NUM_MASK	0x000001C0L
+
+
+// addressBlock: athub_rpbdec
+//RPB_PASSPW_CONF
+#define RPB_PASSPW_CONF__XPB_PASSPW_OVERRIDE__SHIFT	0x0
+#define RPB_PASSPW_CONF__XPB_RSPPASSPW_OVERRIDE__SHIFT	0x1
+#define RPB_PASSPW_CONF__ATC_TR_PASSPW_OVERRIDE__SHIFT	0x2
+#define RPB_PASSPW_CONF__ATC_PAGE_PASSPW_OVERRIDE__SHIFT	0x3
+#define RPB_PASSPW_CONF__WR_PASSPW_OVERRIDE__SHIFT	0x4
+#define RPB_PASSPW_CONF__RD_PASSPW_OVERRIDE__SHIFT	0x5
+#define RPB_PASSPW_CONF__WR_RSPPASSPW_OVERRIDE__SHIFT	0x6
+#define RPB_PASSPW_CONF__RD_RSPPASSPW_OVERRIDE__SHIFT	0x7
+#define RPB_PASSPW_CONF__ATC_RSPPASSPW_OVERRIDE__SHIFT	0x8
+#define RPB_PASSPW_CONF__ATOMIC_PASSPW_OVERRIDE__SHIFT	0x9
+#define RPB_PASSPW_CONF__ATOMIC_RSPPASSPW_OVERRIDE__SHIFT	0xa
+#define RPB_PASSPW_CONF__ATC_TR_PASSPW_OVERRIDE_EN__SHIFT	0xb
+#define RPB_PASSPW_CONF__ATC_PAGE_PASSPW_OVERRIDE_EN__SHIFT	0xc
+#define RPB_PASSPW_CONF__ATC_RSPPASSPW_OVERRIDE_EN__SHIFT	0xd
+#define RPB_PASSPW_CONF__WRRSP_PASSPW_OVERRIDE__SHIFT	0xe
+#define RPB_PASSPW_CONF__WRRSP_PASSPW_OVERRIDE_EN__SHIFT	0xf
+#define RPB_PASSPW_CONF__RDRSP_PASSPW_OVERRIDE__SHIFT	0x10
+#define RPB_PASSPW_CONF__RDRSP_PASSPW_OVERRIDE_EN__SHIFT	0x11
+#define RPB_PASSPW_CONF__XPB_PASSPW_OVERRIDE_MASK	0x00000001L
+#define RPB_PASSPW_CONF__XPB_RSPPASSPW_OVERRIDE_MASK	0x00000002L
+#define RPB_PASSPW_CONF__ATC_TR_PASSPW_OVERRIDE_MASK	0x00000004L
+#define RPB_PASSPW_CONF__ATC_PAGE_PASSPW_OVERRIDE_MASK	0x00000008L
+#define RPB_PASSPW_CONF__WR_PASSPW_OVERRIDE_MASK	0x00000010L
+#define RPB_PASSPW_CONF__RD_PASSPW_OVERRIDE_MASK	0x00000020L
+#define RPB_PASSPW_CONF__WR_RSPPASSPW_OVERRIDE_MASK	0x00000040L
+#define RPB_PASSPW_CONF__RD_RSPPASSPW_OVERRIDE_MASK	0x00000080L
+#define RPB_PASSPW_CONF__ATC_RSPPASSPW_OVERRIDE_MASK	0x00000100L
+#define RPB_PASSPW_CONF__ATOMIC_PASSPW_OVERRIDE_MASK	0x00000200L
+#define RPB_PASSPW_CONF__ATOMIC_RSPPASSPW_OVERRIDE_MASK	0x00000400L
+#define RPB_PASSPW_CONF__ATC_TR_PASSPW_OVERRIDE_EN_MASK	0x00000800L
+#define RPB_PASSPW_CONF__ATC_PAGE_PASSPW_OVERRIDE_EN_MASK	0x00001000L
+#define RPB_PASSPW_CONF__ATC_RSPPASSPW_OVERRIDE_EN_MASK	0x00002000L
+#define RPB_PASSPW_CONF__WRRSP_PASSPW_OVERRIDE_MASK	0x00004000L
+#define RPB_PASSPW_CONF__WRRSP_PASSPW_OVERRIDE_EN_MASK	0x00008000L
+#define RPB_PASSPW_CONF__RDRSP_PASSPW_OVERRIDE_MASK	0x00010000L
+#define RPB_PASSPW_CONF__RDRSP_PASSPW_OVERRIDE_EN_MASK	0x00020000L
+//RPB_BLOCKLEVEL_CONF
+#define RPB_BLOCKLEVEL_CONF__XPB_BLOCKLEVEL_OVERRIDE__SHIFT	0x0
+#define RPB_BLOCKLEVEL_CONF__ATC_TR_BLOCKLEVEL__SHIFT	0x2
+#define RPB_BLOCKLEVEL_CONF__ATC_PAGE_BLOCKLEVEL__SHIFT	0x4
+#define RPB_BLOCKLEVEL_CONF__ATC_INV_BLOCKLEVEL__SHIFT	0x6
+#define RPB_BLOCKLEVEL_CONF__IO_WR_BLOCKLEVEL_OVERRIDE__SHIFT	0x8
+#define RPB_BLOCKLEVEL_CONF__IO_RD_BLOCKLEVEL_OVERRIDE__SHIFT	0xa
+#define RPB_BLOCKLEVEL_CONF__ATOMIC_BLOCKLEVEL_OVERRIDE__SHIFT	0xc
+#define RPB_BLOCKLEVEL_CONF__XPB_BLOCKLEVEL_OVERRIDE_EN__SHIFT	0xe
+#define RPB_BLOCKLEVEL_CONF__IO_WR_BLOCKLEVEL_OVERRIDE_EN__SHIFT	0xf
+#define RPB_BLOCKLEVEL_CONF__IO_RD_BLOCKLEVEL_OVERRIDE_EN__SHIFT	0x10
+#define RPB_BLOCKLEVEL_CONF__ATOMIC_BLOCKLEVEL_OVERRIDE_EN__SHIFT	0x11
+#define RPB_BLOCKLEVEL_CONF__XPB_BLOCKLEVEL_OVERRIDE_MASK	0x00000003L
+#define RPB_BLOCKLEVEL_CONF__ATC_TR_BLOCKLEVEL_MASK	0x0000000CL
+#define RPB_BLOCKLEVEL_CONF__ATC_PAGE_BLOCKLEVEL_MASK	0x00000030L
+#define RPB_BLOCKLEVEL_CONF__ATC_INV_BLOCKLEVEL_MASK	0x000000C0L
+#define RPB_BLOCKLEVEL_CONF__IO_WR_BLOCKLEVEL_OVERRIDE_MASK	0x00000300L
+#define RPB_BLOCKLEVEL_CONF__IO_RD_BLOCKLEVEL_OVERRIDE_MASK	0x00000C00L
+#define RPB_BLOCKLEVEL_CONF__ATOMIC_BLOCKLEVEL_OVERRIDE_MASK	0x00003000L
+#define RPB_BLOCKLEVEL_CONF__XPB_BLOCKLEVEL_OVERRIDE_EN_MASK	0x00004000L
+#define RPB_BLOCKLEVEL_CONF__IO_WR_BLOCKLEVEL_OVERRIDE_EN_MASK	0x00008000L
+#define RPB_BLOCKLEVEL_CONF__IO_RD_BLOCKLEVEL_OVERRIDE_EN_MASK	0x00010000L
+#define RPB_BLOCKLEVEL_CONF__ATOMIC_BLOCKLEVEL_OVERRIDE_EN_MASK	0x00020000L
+//RPB_TAG_CONF
+#define RPB_TAG_CONF__RPB_ATS_TR__SHIFT	0x0
+#define RPB_TAG_CONF__RPB_IO_WR__SHIFT	0x8
+#define RPB_TAG_CONF__RPB_ATS_PR__SHIFT	0x10
+#define RPB_TAG_CONF__RPB_ATS_TR_MASK	0x000000FFL
+#define RPB_TAG_CONF__RPB_IO_WR_MASK	0x0000FF00L
+#define RPB_TAG_CONF__RPB_ATS_PR_MASK	0x00FF0000L
+//RPB_EFF_CNTL
+#define RPB_EFF_CNTL__WR_LAZY_TIMER__SHIFT	0x0
+#define RPB_EFF_CNTL__RD_LAZY_TIMER__SHIFT	0x8
+#define RPB_EFF_CNTL__WR_LAZY_TIMER_MASK	0x000000FFL
+#define RPB_EFF_CNTL__RD_LAZY_TIMER_MASK	0x0000FF00L
+//RPB_ARB_CNTL
+#define RPB_ARB_CNTL__RD_SWITCH_NUM__SHIFT	0x0
+#define RPB_ARB_CNTL__WR_SWITCH_NUM__SHIFT	0x8
+#define RPB_ARB_CNTL__ATC_TR_SWITCH_NUM__SHIFT	0x10
+#define RPB_ARB_CNTL__ARB_MODE__SHIFT	0x18
+#define RPB_ARB_CNTL__SWITCH_NUM_MODE__SHIFT	0x19
+#define RPB_ARB_CNTL__RD_SWITCH_NUM_MASK	0x000000FFL
+#define RPB_ARB_CNTL__WR_SWITCH_NUM_MASK	0x0000FF00L
+#define RPB_ARB_CNTL__ATC_TR_SWITCH_NUM_MASK	0x00FF0000L
+#define RPB_ARB_CNTL__ARB_MODE_MASK	0x01000000L
+#define RPB_ARB_CNTL__SWITCH_NUM_MODE_MASK	0x02000000L
+//RPB_ARB_CNTL2
+#define RPB_ARB_CNTL2__P2P_SWITCH_NUM__SHIFT	0x0
+#define RPB_ARB_CNTL2__ATOMIC_SWITCH_NUM__SHIFT	0x8
+#define RPB_ARB_CNTL2__ATC_PAGE_SWITCH_NUM__SHIFT	0x10
+#define RPB_ARB_CNTL2__P2P_SWITCH_NUM_MASK	0x000000FFL
+#define RPB_ARB_CNTL2__ATOMIC_SWITCH_NUM_MASK	0x0000FF00L
+#define RPB_ARB_CNTL2__ATC_PAGE_SWITCH_NUM_MASK	0x00FF0000L
+//RPB_BIF_CNTL
+#define RPB_BIF_CNTL__VC0_SWITCH_NUM__SHIFT	0x0
+#define RPB_BIF_CNTL__VC1_SWITCH_NUM__SHIFT	0x8
+#define RPB_BIF_CNTL__ARB_MODE__SHIFT	0x10
+#define RPB_BIF_CNTL__DRAIN_VC_NUM__SHIFT	0x11
+#define RPB_BIF_CNTL__SWITCH_ENABLE__SHIFT	0x12
+#define RPB_BIF_CNTL__SWITCH_THRESHOLD__SHIFT	0x13
+#define RPB_BIF_CNTL__PAGE_PRI_EN__SHIFT	0x1b
+#define RPB_BIF_CNTL__TR_PRI_EN__SHIFT	0x1c
+#define RPB_BIF_CNTL__VC0_CHAINED_OVERRIDE__SHIFT	0x1d
+#define RPB_BIF_CNTL__PARITY_CHECK_EN__SHIFT	0x1e
+#define RPB_BIF_CNTL__VC0_SWITCH_NUM_MASK	0x000000FFL
+#define RPB_BIF_CNTL__VC1_SWITCH_NUM_MASK	0x0000FF00L
+#define RPB_BIF_CNTL__ARB_MODE_MASK	0x00010000L
+#define RPB_BIF_CNTL__DRAIN_VC_NUM_MASK	0x00020000L
+#define RPB_BIF_CNTL__SWITCH_ENABLE_MASK	0x00040000L
+#define RPB_BIF_CNTL__SWITCH_THRESHOLD_MASK	0x07F80000L
+#define RPB_BIF_CNTL__PAGE_PRI_EN_MASK	0x08000000L
+#define RPB_BIF_CNTL__TR_PRI_EN_MASK	0x10000000L
+#define RPB_BIF_CNTL__VC0_CHAINED_OVERRIDE_MASK	0x20000000L
+#define RPB_BIF_CNTL__PARITY_CHECK_EN_MASK	0x40000000L
+//RPB_WR_SWITCH_CNTL
+#define RPB_WR_SWITCH_CNTL__QUEUE0_SWITCH_NUM__SHIFT	0x0
+#define RPB_WR_SWITCH_CNTL__QUEUE1_SWITCH_NUM__SHIFT	0x7
+#define RPB_WR_SWITCH_CNTL__QUEUE2_SWITCH_NUM__SHIFT	0xe
+#define RPB_WR_SWITCH_CNTL__QUEUE3_SWITCH_NUM__SHIFT	0x15
+#define RPB_WR_SWITCH_CNTL__SWITCH_NUM_MODE__SHIFT	0x1c
+#define RPB_WR_SWITCH_CNTL__QUEUE0_SWITCH_NUM_MASK	0x0000007FL
+#define RPB_WR_SWITCH_CNTL__QUEUE1_SWITCH_NUM_MASK	0x00003F80L
+#define RPB_WR_SWITCH_CNTL__QUEUE2_SWITCH_NUM_MASK	0x001FC000L
+#define RPB_WR_SWITCH_CNTL__QUEUE3_SWITCH_NUM_MASK	0x0FE00000L
+#define RPB_WR_SWITCH_CNTL__SWITCH_NUM_MODE_MASK	0x10000000L
+//RPB_RD_SWITCH_CNTL
+#define RPB_RD_SWITCH_CNTL__QUEUE0_SWITCH_NUM__SHIFT	0x0
+#define RPB_RD_SWITCH_CNTL__QUEUE1_SWITCH_NUM__SHIFT	0x7
+#define RPB_RD_SWITCH_CNTL__QUEUE2_SWITCH_NUM__SHIFT	0xe
+#define RPB_RD_SWITCH_CNTL__QUEUE3_SWITCH_NUM__SHIFT	0x15
+#define RPB_RD_SWITCH_CNTL__SWITCH_NUM_MODE__SHIFT	0x1c
+#define RPB_RD_SWITCH_CNTL__QUEUE0_SWITCH_NUM_MASK	0x0000007FL
+#define RPB_RD_SWITCH_CNTL__QUEUE1_SWITCH_NUM_MASK	0x00003F80L
+#define RPB_RD_SWITCH_CNTL__QUEUE2_SWITCH_NUM_MASK	0x001FC000L
+#define RPB_RD_SWITCH_CNTL__QUEUE3_SWITCH_NUM_MASK	0x0FE00000L
+#define RPB_RD_SWITCH_CNTL__SWITCH_NUM_MODE_MASK	0x10000000L
+//RPB_CID_QUEUE_WR
+#define RPB_CID_QUEUE_WR__CLIENT_ID_LOW__SHIFT	0x0
+#define RPB_CID_QUEUE_WR__CLIENT_ID_HIGH__SHIFT	0x5
+#define RPB_CID_QUEUE_WR__UPDATE_MODE__SHIFT	0xb
+#define RPB_CID_QUEUE_WR__WRITE_QUEUE__SHIFT	0xc
+#define RPB_CID_QUEUE_WR__READ_QUEUE__SHIFT	0xf
+#define RPB_CID_QUEUE_WR__UPDATE__SHIFT	0x12
+#define RPB_CID_QUEUE_WR__CLIENT_ID_LOW_MASK	0x0000001FL
+#define RPB_CID_QUEUE_WR__CLIENT_ID_HIGH_MASK	0x000007E0L
+#define RPB_CID_QUEUE_WR__UPDATE_MODE_MASK	0x00000800L
+#define RPB_CID_QUEUE_WR__WRITE_QUEUE_MASK	0x00007000L
+#define RPB_CID_QUEUE_WR__READ_QUEUE_MASK	0x00038000L
+#define RPB_CID_QUEUE_WR__UPDATE_MASK	0x00040000L
+//RPB_CID_QUEUE_RD
+#define RPB_CID_QUEUE_RD__CLIENT_ID_LOW__SHIFT	0x0
+#define RPB_CID_QUEUE_RD__CLIENT_ID_HIGH__SHIFT	0x5
+#define RPB_CID_QUEUE_RD__WRITE_QUEUE__SHIFT	0xb
+#define RPB_CID_QUEUE_RD__READ_QUEUE__SHIFT	0xe
+#define RPB_CID_QUEUE_RD__CLIENT_ID_LOW_MASK	0x0000001FL
+#define RPB_CID_QUEUE_RD__CLIENT_ID_HIGH_MASK	0x000007E0L
+#define RPB_CID_QUEUE_RD__WRITE_QUEUE_MASK	0x00003800L
+#define RPB_CID_QUEUE_RD__READ_QUEUE_MASK	0x0001C000L
+//RPB_CID_QUEUE_EX
+#define RPB_CID_QUEUE_EX__START__SHIFT	0x0
+#define RPB_CID_QUEUE_EX__OFFSET__SHIFT	0x1
+#define RPB_CID_QUEUE_EX__START_MASK	0x00000001L
+#define RPB_CID_QUEUE_EX__OFFSET_MASK	0x000001FEL
+//RPB_CID_QUEUE_EX_DATA
+#define RPB_CID_QUEUE_EX_DATA__WRITE_ENTRIES__SHIFT	0x0
+#define RPB_CID_QUEUE_EX_DATA__READ_ENTRIES__SHIFT	0x10
+#define RPB_CID_QUEUE_EX_DATA__WRITE_ENTRIES_MASK	0x0000FFFFL
+#define RPB_CID_QUEUE_EX_DATA__READ_ENTRIES_MASK	0xFFFF0000L
+//RPB_SWITCH_CNTL2
+#define RPB_SWITCH_CNTL2__RD_QUEUE4_SWITCH_NUM__SHIFT	0x0
+#define RPB_SWITCH_CNTL2__RD_QUEUE5_SWITCH_NUM__SHIFT	0x7
+#define RPB_SWITCH_CNTL2__WR_QUEUE4_SWITCH_NUM__SHIFT	0xe
+#define RPB_SWITCH_CNTL2__WR_QUEUE5_SWITCH_NUM__SHIFT	0x15
+#define RPB_SWITCH_CNTL2__RD_QUEUE4_SWITCH_NUM_MASK	0x0000007FL
+#define RPB_SWITCH_CNTL2__RD_QUEUE5_SWITCH_NUM_MASK	0x00003F80L
+#define RPB_SWITCH_CNTL2__WR_QUEUE4_SWITCH_NUM_MASK	0x001FC000L
+#define RPB_SWITCH_CNTL2__WR_QUEUE5_SWITCH_NUM_MASK	0x0FE00000L
+//RPB_DEINTRLV_COMBINE_CNTL
+#define RPB_DEINTRLV_COMBINE_CNTL__WC_CHAINED_FLUSH_TIMER__SHIFT	0x0
+#define RPB_DEINTRLV_COMBINE_CNTL__WC_CHAINED_BREAK_EN__SHIFT	0x4
+#define RPB_DEINTRLV_COMBINE_CNTL__WC_HANDLE_CHECK_DISABLE__SHIFT	0x5
+#define RPB_DEINTRLV_COMBINE_CNTL__WC_CHAINED_FLUSH_TIMER_MASK	0x0000000FL
+#define RPB_DEINTRLV_COMBINE_CNTL__WC_CHAINED_BREAK_EN_MASK	0x00000010L
+#define RPB_DEINTRLV_COMBINE_CNTL__WC_HANDLE_CHECK_DISABLE_MASK	0x00000020L
+//RPB_VC_SWITCH_RDWR
+#define RPB_VC_SWITCH_RDWR__MODE__SHIFT	0x0
+#define RPB_VC_SWITCH_RDWR__NUM_RD__SHIFT	0x2
+#define RPB_VC_SWITCH_RDWR__NUM_WR__SHIFT	0xa
+#define RPB_VC_SWITCH_RDWR__MODE_MASK	0x00000003L
+#define RPB_VC_SWITCH_RDWR__NUM_RD_MASK	0x000003FCL
+#define RPB_VC_SWITCH_RDWR__NUM_WR_MASK	0x0003FC00L
+//RPB_PERFCOUNTER_LO
+#define RPB_PERFCOUNTER_LO__COUNTER_LO__SHIFT	0x0
+#define RPB_PERFCOUNTER_LO__COUNTER_LO_MASK	0xFFFFFFFFL
+//RPB_PERFCOUNTER_HI
+#define RPB_PERFCOUNTER_HI__COUNTER_HI__SHIFT	0x0
+#define RPB_PERFCOUNTER_HI__COMPARE_VALUE__SHIFT	0x10
+#define RPB_PERFCOUNTER_HI__COUNTER_HI_MASK	0x0000FFFFL
+#define RPB_PERFCOUNTER_HI__COMPARE_VALUE_MASK	0xFFFF0000L
+//RPB_PERFCOUNTER0_CFG
+#define RPB_PERFCOUNTER0_CFG__PERF_SEL__SHIFT	0x0
+#define RPB_PERFCOUNTER0_CFG__PERF_SEL_END__SHIFT	0x8
+#define RPB_PERFCOUNTER0_CFG__PERF_MODE__SHIFT	0x18
+#define RPB_PERFCOUNTER0_CFG__ENABLE__SHIFT	0x1c
+#define RPB_PERFCOUNTER0_CFG__CLEAR__SHIFT	0x1d
+#define RPB_PERFCOUNTER0_CFG__PERF_SEL_MASK	0x000000FFL
+#define RPB_PERFCOUNTER0_CFG__PERF_SEL_END_MASK	0x0000FF00L
+#define RPB_PERFCOUNTER0_CFG__PERF_MODE_MASK	0x0F000000L
+#define RPB_PERFCOUNTER0_CFG__ENABLE_MASK	0x10000000L
+#define RPB_PERFCOUNTER0_CFG__CLEAR_MASK	0x20000000L
+//RPB_PERFCOUNTER1_CFG
+#define RPB_PERFCOUNTER1_CFG__PERF_SEL__SHIFT	0x0
+#define RPB_PERFCOUNTER1_CFG__PERF_SEL_END__SHIFT	0x8
+#define RPB_PERFCOUNTER1_CFG__PERF_MODE__SHIFT	0x18
+#define RPB_PERFCOUNTER1_CFG__ENABLE__SHIFT	0x1c
+#define RPB_PERFCOUNTER1_CFG__CLEAR__SHIFT	0x1d
+#define RPB_PERFCOUNTER1_CFG__PERF_SEL_MASK	0x000000FFL
+#define RPB_PERFCOUNTER1_CFG__PERF_SEL_END_MASK	0x0000FF00L
+#define RPB_PERFCOUNTER1_CFG__PERF_MODE_MASK	0x0F000000L
+#define RPB_PERFCOUNTER1_CFG__ENABLE_MASK	0x10000000L
+#define RPB_PERFCOUNTER1_CFG__CLEAR_MASK	0x20000000L
+//RPB_PERFCOUNTER2_CFG
+#define RPB_PERFCOUNTER2_CFG__PERF_SEL__SHIFT	0x0
+#define RPB_PERFCOUNTER2_CFG__PERF_SEL_END__SHIFT	0x8
+#define RPB_PERFCOUNTER2_CFG__PERF_MODE__SHIFT	0x18
+#define RPB_PERFCOUNTER2_CFG__ENABLE__SHIFT	0x1c
+#define RPB_PERFCOUNTER2_CFG__CLEAR__SHIFT	0x1d
+#define RPB_PERFCOUNTER2_CFG__PERF_SEL_MASK	0x000000FFL
+#define RPB_PERFCOUNTER2_CFG__PERF_SEL_END_MASK	0x0000FF00L
+#define RPB_PERFCOUNTER2_CFG__PERF_MODE_MASK	0x0F000000L
+#define RPB_PERFCOUNTER2_CFG__ENABLE_MASK	0x10000000L
+#define RPB_PERFCOUNTER2_CFG__CLEAR_MASK	0x20000000L
+//RPB_PERFCOUNTER3_CFG
+#define RPB_PERFCOUNTER3_CFG__PERF_SEL__SHIFT	0x0
+#define RPB_PERFCOUNTER3_CFG__PERF_SEL_END__SHIFT	0x8
+#define RPB_PERFCOUNTER3_CFG__PERF_MODE__SHIFT	0x18
+#define RPB_PERFCOUNTER3_CFG__ENABLE__SHIFT	0x1c
+#define RPB_PERFCOUNTER3_CFG__CLEAR__SHIFT	0x1d
+#define RPB_PERFCOUNTER3_CFG__PERF_SEL_MASK	0x000000FFL
+#define RPB_PERFCOUNTER3_CFG__PERF_SEL_END_MASK	0x0000FF00L
+#define RPB_PERFCOUNTER3_CFG__PERF_MODE_MASK	0x0F000000L
+#define RPB_PERFCOUNTER3_CFG__ENABLE_MASK	0x10000000L
+#define RPB_PERFCOUNTER3_CFG__CLEAR_MASK	0x20000000L
+//RPB_PERFCOUNTER_RSLT_CNTL
+#define RPB_PERFCOUNTER_RSLT_CNTL__PERF_COUNTER_SELECT__SHIFT	0x0
+#define RPB_PERFCOUNTER_RSLT_CNTL__START_TRIGGER__SHIFT	0x8
+#define RPB_PERFCOUNTER_RSLT_CNTL__STOP_TRIGGER__SHIFT	0x10
+#define RPB_PERFCOUNTER_RSLT_CNTL__ENABLE_ANY__SHIFT	0x18
+#define RPB_PERFCOUNTER_RSLT_CNTL__CLEAR_ALL__SHIFT	0x19
+#define RPB_PERFCOUNTER_RSLT_CNTL__STOP_ALL_ON_SATURATE__SHIFT	0x1a
+#define RPB_PERFCOUNTER_RSLT_CNTL__PERF_COUNTER_SELECT_MASK	0x0000000FL
+#define RPB_PERFCOUNTER_RSLT_CNTL__START_TRIGGER_MASK	0x0000FF00L
+#define RPB_PERFCOUNTER_RSLT_CNTL__STOP_TRIGGER_MASK	0x00FF0000L
+#define RPB_PERFCOUNTER_RSLT_CNTL__ENABLE_ANY_MASK	0x01000000L
+#define RPB_PERFCOUNTER_RSLT_CNTL__CLEAR_ALL_MASK	0x02000000L
+#define RPB_PERFCOUNTER_RSLT_CNTL__STOP_ALL_ON_SATURATE_MASK	0x04000000L
+//RPB_RD_QUEUE_CNTL
+#define RPB_RD_QUEUE_CNTL__ARB_MODE__SHIFT	0x0
+#define RPB_RD_QUEUE_CNTL__Q4_SHARED__SHIFT	0x1
+#define RPB_RD_QUEUE_CNTL__Q5_SHARED__SHIFT	0x2
+#define RPB_RD_QUEUE_CNTL__Q4_UNITID_EA_MODE__SHIFT	0x3
+#define RPB_RD_QUEUE_CNTL__Q5_UNITID_EA_MODE__SHIFT	0x4
+#define RPB_RD_QUEUE_CNTL__Q4_PATTERN_LOW__SHIFT	0x5
+#define RPB_RD_QUEUE_CNTL__Q4_PATTERN_HIGH__SHIFT	0xa
+#define RPB_RD_QUEUE_CNTL__Q5_PATTERN_LOW__SHIFT	0x10
+#define RPB_RD_QUEUE_CNTL__Q5_PATTERN_HIGH__SHIFT	0x15
+#define RPB_RD_QUEUE_CNTL__ARB_MODE_MASK	0x00000001L
+#define RPB_RD_QUEUE_CNTL__Q4_SHARED_MASK	0x00000002L
+#define RPB_RD_QUEUE_CNTL__Q5_SHARED_MASK	0x00000004L
+#define RPB_RD_QUEUE_CNTL__Q4_UNITID_EA_MODE_MASK	0x00000008L
+#define RPB_RD_QUEUE_CNTL__Q5_UNITID_EA_MODE_MASK	0x00000010L
+#define RPB_RD_QUEUE_CNTL__Q4_PATTERN_LOW_MASK	0x000003E0L
+#define RPB_RD_QUEUE_CNTL__Q4_PATTERN_HIGH_MASK	0x0000FC00L
+#define RPB_RD_QUEUE_CNTL__Q5_PATTERN_LOW_MASK	0x001F0000L
+#define RPB_RD_QUEUE_CNTL__Q5_PATTERN_HIGH_MASK	0x07E00000L
+//RPB_RD_QUEUE_CNTL2
+#define RPB_RD_QUEUE_CNTL2__Q4_PATTERN_MASK_LOW__SHIFT	0x0
+#define RPB_RD_QUEUE_CNTL2__Q4_PATTERN_MASK_HIGH__SHIFT	0x5
+#define RPB_RD_QUEUE_CNTL2__Q5_PATTERN_MASK_LOW__SHIFT	0xb
+#define RPB_RD_QUEUE_CNTL2__Q5_PATTERN_MASK_HIGH__SHIFT	0x10
+#define RPB_RD_QUEUE_CNTL2__Q4_PATTERN_MASK_LOW_MASK	0x0000001FL
+#define RPB_RD_QUEUE_CNTL2__Q4_PATTERN_MASK_HIGH_MASK	0x000007E0L
+#define RPB_RD_QUEUE_CNTL2__Q5_PATTERN_MASK_LOW_MASK	0x0000F800L
+#define RPB_RD_QUEUE_CNTL2__Q5_PATTERN_MASK_HIGH_MASK	0x003F0000L
+//RPB_WR_QUEUE_CNTL
+#define RPB_WR_QUEUE_CNTL__ARB_MODE__SHIFT	0x0
+#define RPB_WR_QUEUE_CNTL__Q4_SHARED__SHIFT	0x1
+#define RPB_WR_QUEUE_CNTL__Q5_SHARED__SHIFT	0x2
+#define RPB_WR_QUEUE_CNTL__Q4_UNITID_EA_MODE__SHIFT	0x3
+#define RPB_WR_QUEUE_CNTL__Q5_UNITID_EA_MODE__SHIFT	0x4
+#define RPB_WR_QUEUE_CNTL__Q4_PATTERN_LOW__SHIFT	0x5
+#define RPB_WR_QUEUE_CNTL__Q4_PATTERN_HIGH__SHIFT	0xa
+#define RPB_WR_QUEUE_CNTL__Q5_PATTERN_LOW__SHIFT	0x10
+#define RPB_WR_QUEUE_CNTL__Q5_PATTERN_HIGH__SHIFT	0x15
+#define RPB_WR_QUEUE_CNTL__ARB_MODE_MASK	0x00000001L
+#define RPB_WR_QUEUE_CNTL__Q4_SHARED_MASK	0x00000002L
+#define RPB_WR_QUEUE_CNTL__Q5_SHARED_MASK	0x00000004L
+#define RPB_WR_QUEUE_CNTL__Q4_UNITID_EA_MODE_MASK	0x00000008L
+#define RPB_WR_QUEUE_CNTL__Q5_UNITID_EA_MODE_MASK	0x00000010L
+#define RPB_WR_QUEUE_CNTL__Q4_PATTERN_LOW_MASK	0x000003E0L
+#define RPB_WR_QUEUE_CNTL__Q4_PATTERN_HIGH_MASK	0x0000FC00L
+#define RPB_WR_QUEUE_CNTL__Q5_PATTERN_LOW_MASK	0x001F0000L
+#define RPB_WR_QUEUE_CNTL__Q5_PATTERN_HIGH_MASK	0x07E00000L
+//RPB_WR_QUEUE_CNTL2
+#define RPB_WR_QUEUE_CNTL2__Q4_PATTERN_MASK_LOW__SHIFT	0x0
+#define RPB_WR_QUEUE_CNTL2__Q4_PATTERN_MASK_HIGH__SHIFT	0x5
+#define RPB_WR_QUEUE_CNTL2__Q5_PATTERN_MASK_LOW__SHIFT	0xb
+#define RPB_WR_QUEUE_CNTL2__Q5_PATTERN_MASK_HIGH__SHIFT	0x10
+#define RPB_WR_QUEUE_CNTL2__Q4_PATTERN_MASK_LOW_MASK	0x0000001FL
+#define RPB_WR_QUEUE_CNTL2__Q4_PATTERN_MASK_HIGH_MASK	0x000007E0L
+#define RPB_WR_QUEUE_CNTL2__Q5_PATTERN_MASK_LOW_MASK	0x0000F800L
+#define RPB_WR_QUEUE_CNTL2__Q5_PATTERN_MASK_HIGH_MASK	0x003F0000L
+//RPB_EA_QUEUE_WR
+#define RPB_EA_QUEUE_WR__EA_NUMBER__SHIFT	0x0
+#define RPB_EA_QUEUE_WR__WRITE_QUEUE__SHIFT	0x5
+#define RPB_EA_QUEUE_WR__READ_QUEUE__SHIFT	0x8
+#define RPB_EA_QUEUE_WR__UPDATE__SHIFT	0xb
+#define RPB_EA_QUEUE_WR__EA_NUMBER_MASK	0x0000001FL
+#define RPB_EA_QUEUE_WR__WRITE_QUEUE_MASK	0x000000E0L
+#define RPB_EA_QUEUE_WR__READ_QUEUE_MASK	0x00000700L
+#define RPB_EA_QUEUE_WR__UPDATE_MASK	0x00000800L
+//RPB_ATS_CNTL
+#define RPB_ATS_CNTL__PAGE_MIN_LATENCY_ENABLE__SHIFT	0x0
+#define RPB_ATS_CNTL__TR_MIN_LATENCY_ENABLE__SHIFT	0x1
+#define RPB_ATS_CNTL__SWITCH_THRESHOLD__SHIFT	0x2
+#define RPB_ATS_CNTL__TIME_SLICE__SHIFT	0x7
+#define RPB_ATS_CNTL__ATCTR_SWITCH_NUM__SHIFT	0xf
+#define RPB_ATS_CNTL__ATCPAGE_SWITCH_NUM__SHIFT	0x13
+#define RPB_ATS_CNTL__WR_AT__SHIFT	0x17
+#define RPB_ATS_CNTL__INVAL_COM_CMD__SHIFT	0x19
+#define RPB_ATS_CNTL__PAGE_MIN_LATENCY_ENABLE_MASK	0x00000001L
+#define RPB_ATS_CNTL__TR_MIN_LATENCY_ENABLE_MASK	0x00000002L
+#define RPB_ATS_CNTL__SWITCH_THRESHOLD_MASK	0x0000007CL
+#define RPB_ATS_CNTL__TIME_SLICE_MASK	0x00007F80L
+#define RPB_ATS_CNTL__ATCTR_SWITCH_NUM_MASK	0x00078000L
+#define RPB_ATS_CNTL__ATCPAGE_SWITCH_NUM_MASK	0x00780000L
+#define RPB_ATS_CNTL__WR_AT_MASK	0x01800000L
+#define RPB_ATS_CNTL__INVAL_COM_CMD_MASK	0x7E000000L
+//RPB_ATS_CNTL2
+#define RPB_ATS_CNTL2__TRANS_CMD__SHIFT	0x0
+#define RPB_ATS_CNTL2__PAGE_REQ_CMD__SHIFT	0x6
+#define RPB_ATS_CNTL2__PAGE_ROUTING_CODE__SHIFT	0xc
+#define RPB_ATS_CNTL2__INVAL_COM_ROUTING_CODE__SHIFT	0xf
+#define RPB_ATS_CNTL2__VENDOR_ID__SHIFT	0x12
+#define RPB_ATS_CNTL2__TRANS_CMD_MASK	0x0000003FL
+#define RPB_ATS_CNTL2__PAGE_REQ_CMD_MASK	0x00000FC0L
+#define RPB_ATS_CNTL2__PAGE_ROUTING_CODE_MASK	0x00007000L
+#define RPB_ATS_CNTL2__INVAL_COM_ROUTING_CODE_MASK	0x00038000L
+#define RPB_ATS_CNTL2__VENDOR_ID_MASK	0x000C0000L
+//RPB_SDPPORT_CNTL
+#define RPB_SDPPORT_CNTL__NBIF_DMA_SELF_ACTIVATE__SHIFT	0x0
+#define RPB_SDPPORT_CNTL__NBIF_DMA_CFG_MODE__SHIFT	0x1
+#define RPB_SDPPORT_CNTL__NBIF_DMA_ENABLE_REISSUE_CREDIT__SHIFT	0x3
+#define RPB_SDPPORT_CNTL__NBIF_DMA_ENABLE_SATURATE_COUNTER__SHIFT	0x4
+#define RPB_SDPPORT_CNTL__NBIF_DMA_ENABLE_DISRUPT_FULLDIS__SHIFT	0x5
+#define RPB_SDPPORT_CNTL__NBIF_DMA_HALT_THRESHOLD__SHIFT	0x6
+#define RPB_SDPPORT_CNTL__NBIF_HST_SELF_ACTIVATE__SHIFT	0xa
+#define RPB_SDPPORT_CNTL__NBIF_HST_CFG_MODE__SHIFT	0xb
+#define RPB_SDPPORT_CNTL__NBIF_HST_ENABLE_REISSUE_CREDIT__SHIFT	0xd
+#define RPB_SDPPORT_CNTL__NBIF_HST_ENABLE_SATURATE_COUNTER__SHIFT	0xe
+#define RPB_SDPPORT_CNTL__NBIF_HST_ENABLE_DISRUPT_FULLDIS__SHIFT	0xf
+#define RPB_SDPPORT_CNTL__NBIF_HST_HALT_THRESHOLD__SHIFT	0x10
+#define RPB_SDPPORT_CNTL__NBIF_HST_PASSIVE_MODE__SHIFT	0x14
+#define RPB_SDPPORT_CNTL__NBIF_HST_QUICK_COMACK__SHIFT	0x15
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_RDRSPCKEN__SHIFT	0x16
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_RDRSPCKENRCV__SHIFT	0x17
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_RDRSPDATACKEN__SHIFT	0x18
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_RDRSPDATACKENRCV__SHIFT	0x19
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_WRRSPCKEN__SHIFT	0x1a
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_WRRSPCKENRCV__SHIFT	0x1b
+#define RPB_SDPPORT_CNTL__NBIF_DMA_SELF_ACTIVATE_MASK	0x00000001L
+#define RPB_SDPPORT_CNTL__NBIF_DMA_CFG_MODE_MASK	0x00000006L
+#define RPB_SDPPORT_CNTL__NBIF_DMA_ENABLE_REISSUE_CREDIT_MASK	0x00000008L
+#define RPB_SDPPORT_CNTL__NBIF_DMA_ENABLE_SATURATE_COUNTER_MASK	0x00000010L
+#define RPB_SDPPORT_CNTL__NBIF_DMA_ENABLE_DISRUPT_FULLDIS_MASK	0x00000020L
+#define RPB_SDPPORT_CNTL__NBIF_DMA_HALT_THRESHOLD_MASK	0x000003C0L
+#define RPB_SDPPORT_CNTL__NBIF_HST_SELF_ACTIVATE_MASK	0x00000400L
+#define RPB_SDPPORT_CNTL__NBIF_HST_CFG_MODE_MASK	0x00001800L
+#define RPB_SDPPORT_CNTL__NBIF_HST_ENABLE_REISSUE_CREDIT_MASK	0x00002000L
+#define RPB_SDPPORT_CNTL__NBIF_HST_ENABLE_SATURATE_COUNTER_MASK	0x00004000L
+#define RPB_SDPPORT_CNTL__NBIF_HST_ENABLE_DISRUPT_FULLDIS_MASK	0x00008000L
+#define RPB_SDPPORT_CNTL__NBIF_HST_HALT_THRESHOLD_MASK	0x000F0000L
+#define RPB_SDPPORT_CNTL__NBIF_HST_PASSIVE_MODE_MASK	0x00100000L
+#define RPB_SDPPORT_CNTL__NBIF_HST_QUICK_COMACK_MASK	0x00200000L
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_RDRSPCKEN_MASK	0x00400000L
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_RDRSPCKENRCV_MASK	0x00800000L
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_RDRSPDATACKEN_MASK	0x01000000L
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_RDRSPDATACKENRCV_MASK	0x02000000L
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_WRRSPCKEN_MASK	0x04000000L
+#define RPB_SDPPORT_CNTL__DF_SDPVDCI_WRRSPCKENRCV_MASK	0x08000000L
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/DC/dce_12_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
index f730d0629020..f730d0629020 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/DC/dce_12_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/DC/dce_12_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_sh_mask.h
index 6d3162c42957..6d3162c42957 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/DC/dce_12_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_sh_mask.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/raven1/DCN/dcn_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_offset.h
index 4ccf9681c45d..4ccf9681c45d 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/raven1/DCN/dcn_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_offset.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/raven1/DCN/dcn_1_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_sh_mask.h
index b28d4b64c05d..b28d4b64c05d 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/raven1/DCN/dcn_1_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_sh_mask.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/GC/gc_9_0_default.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_default.h
index 663d3af35baf..5bf84c6d0ec3 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/GC/gc_9_0_default.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_default.h
@@ -436,7 +436,6 @@
 #define mmTA_CNTL_DEFAULT                                                        0x8004d850
 #define mmTA_CNTL_AUX_DEFAULT                                                    0x00000000
 #define mmTA_RESERVED_010C_DEFAULT                                               0x00000000
-#define mmTA_GRAD_ADJ_DEFAULT                                                    0x40000040
 #define mmTA_STATUS_DEFAULT                                                      0x00000000
 #define mmTA_SCRATCH_DEFAULT                                                     0x00000000
 
@@ -1700,7 +1699,6 @@
 #define mmDB_STENCIL_WRITE_BASE_DEFAULT                                          0x00000000
 #define mmDB_STENCIL_WRITE_BASE_HI_DEFAULT                                       0x00000000
 #define mmDB_DFSM_CONTROL_DEFAULT                                                0x00000000
-#define mmDB_RENDER_FILTER_DEFAULT                                               0x00000000
 #define mmDB_Z_INFO2_DEFAULT                                                     0x00000000
 #define mmDB_STENCIL_INFO2_DEFAULT                                               0x00000000
 #define mmTA_BC_BASE_ADDR_DEFAULT                                                0x00000000
@@ -1806,8 +1804,6 @@
 #define mmPA_SC_RIGHT_VERT_GRID_DEFAULT                                          0x00000000
 #define mmPA_SC_LEFT_VERT_GRID_DEFAULT                                           0x00000000
 #define mmPA_SC_HORIZ_GRID_DEFAULT                                               0x00000000
-#define mmPA_SC_FOV_WINDOW_LR_DEFAULT                                            0x00000000
-#define mmPA_SC_FOV_WINDOW_TB_DEFAULT                                            0x00000000
 #define mmVGT_MULTI_PRIM_IB_RESET_INDX_DEFAULT                                   0x00000000
 #define mmCB_BLEND_RED_DEFAULT                                                   0x00000000
 #define mmCB_BLEND_GREEN_DEFAULT                                                 0x00000000
@@ -2072,7 +2068,6 @@
 #define mmVGT_EVENT_INITIATOR_DEFAULT                                            0x00000000
 #define mmVGT_GS_MAX_PRIMS_PER_SUBGROUP_DEFAULT                                  0x00000000
 #define mmVGT_DRAW_PAYLOAD_CNTL_DEFAULT                                          0x00000000
-#define mmVGT_INDEX_PAYLOAD_CNTL_DEFAULT                                         0x00000000
 #define mmVGT_INSTANCE_STEP_RATE_0_DEFAULT                                       0x00000000
 #define mmVGT_INSTANCE_STEP_RATE_1_DEFAULT                                       0x00000000
 #define mmVGT_ESGS_RING_ITEMSIZE_DEFAULT                                         0x00000000
@@ -2490,7 +2485,6 @@
 #define mmWD_INDEX_BUF_BASE_DEFAULT                                              0x00000000
 #define mmWD_INDEX_BUF_BASE_HI_DEFAULT                                           0x00000000
 #define mmIA_MULTI_VGT_PARAM_DEFAULT                                             0x006000ff
-#define mmVGT_OBJECT_ID_DEFAULT                                                  0x00000000
 #define mmVGT_INSTANCE_BASE_ID_DEFAULT                                           0x00000000
 #define mmPA_SU_LINE_STIPPLE_VALUE_DEFAULT                                       0x00000000
 #define mmPA_SC_LINE_STIPPLE_STATE_DEFAULT                                       0x00000000
@@ -2534,7 +2528,6 @@
 #define mmSQC_WRITEBACK_DEFAULT                                                  0x00000000
 #define mmTA_CS_BC_BASE_ADDR_DEFAULT                                             0x00000000
 #define mmTA_CS_BC_BASE_ADDR_HI_DEFAULT                                          0x00000000
-#define mmTA_GRAD_ADJ_UCONFIG_DEFAULT                                            0x40000040
 #define mmDB_OCCLUSION_COUNT0_LOW_DEFAULT                                        0x00000000
 #define mmDB_OCCLUSION_COUNT0_HI_DEFAULT                                         0x00000000
 #define mmDB_OCCLUSION_COUNT1_LOW_DEFAULT                                        0x00000000
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/GC/gc_9_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
index e6d6171aa8b9..4ce090db7ef7 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/GC/gc_9_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
@@ -841,8 +841,6 @@
 #define mmTA_CNTL_AUX_BASE_IDX                                                                         0
 #define mmTA_RESERVED_010C                                                                             0x0543
 #define mmTA_RESERVED_010C_BASE_IDX                                                                    0
-#define mmTA_GRAD_ADJ                                                                                  0x0544
-#define mmTA_GRAD_ADJ_BASE_IDX                                                                         0
 #define mmTA_STATUS                                                                                    0x0548
 #define mmTA_STATUS_BASE_IDX                                                                           0
 #define mmTA_SCRATCH                                                                                   0x0564
@@ -3330,8 +3328,6 @@
 #define mmDB_STENCIL_WRITE_BASE_HI_BASE_IDX                                                            1
 #define mmDB_DFSM_CONTROL                                                                              0x0018
 #define mmDB_DFSM_CONTROL_BASE_IDX                                                                     1
-#define mmDB_RENDER_FILTER                                                                             0x0019
-#define mmDB_RENDER_FILTER_BASE_IDX                                                                    1
 #define mmDB_Z_INFO2                                                                                   0x001a
 #define mmDB_Z_INFO2_BASE_IDX                                                                          1
 #define mmDB_STENCIL_INFO2                                                                             0x001b
@@ -3542,10 +3538,6 @@
 #define mmPA_SC_LEFT_VERT_GRID_BASE_IDX                                                                1
 #define mmPA_SC_HORIZ_GRID                                                                             0x00ea
 #define mmPA_SC_HORIZ_GRID_BASE_IDX                                                                    1
-#define mmPA_SC_FOV_WINDOW_LR                                                                          0x00eb
-#define mmPA_SC_FOV_WINDOW_LR_BASE_IDX                                                                 1
-#define mmPA_SC_FOV_WINDOW_TB                                                                          0x00ec
-#define mmPA_SC_FOV_WINDOW_TB_BASE_IDX                                                                 1
 #define mmVGT_MULTI_PRIM_IB_RESET_INDX                                                                 0x0103
 #define mmVGT_MULTI_PRIM_IB_RESET_INDX_BASE_IDX                                                        1
 #define mmCB_BLEND_RED                                                                                 0x0105
@@ -4074,8 +4066,6 @@
 #define mmVGT_GS_MAX_PRIMS_PER_SUBGROUP_BASE_IDX                                                       1
 #define mmVGT_DRAW_PAYLOAD_CNTL                                                                        0x02a6
 #define mmVGT_DRAW_PAYLOAD_CNTL_BASE_IDX                                                               1
-#define mmVGT_INDEX_PAYLOAD_CNTL                                                                       0x02a7
-#define mmVGT_INDEX_PAYLOAD_CNTL_BASE_IDX                                                              1
 #define mmVGT_INSTANCE_STEP_RATE_0                                                                     0x02a8
 #define mmVGT_INSTANCE_STEP_RATE_0_BASE_IDX                                                            1
 #define mmVGT_INSTANCE_STEP_RATE_1                                                                     0x02a9
@@ -4908,8 +4898,6 @@
 #define mmWD_INDEX_BUF_BASE_HI_BASE_IDX                                                                1
 #define mmIA_MULTI_VGT_PARAM                                                                           0x2258
 #define mmIA_MULTI_VGT_PARAM_BASE_IDX                                                                  1
-#define mmVGT_OBJECT_ID                                                                                0x2259
-#define mmVGT_OBJECT_ID_BASE_IDX                                                                       1
 #define mmVGT_INSTANCE_BASE_ID                                                                         0x225a
 #define mmVGT_INSTANCE_BASE_ID_BASE_IDX                                                                1
 #define mmPA_SU_LINE_STIPPLE_VALUE                                                                     0x2280
@@ -4996,8 +4984,6 @@
 #define mmTA_CS_BC_BASE_ADDR_BASE_IDX                                                                  1
 #define mmTA_CS_BC_BASE_ADDR_HI                                                                        0x2381
 #define mmTA_CS_BC_BASE_ADDR_HI_BASE_IDX                                                               1
-#define mmTA_GRAD_ADJ_UCONFIG                                                                          0x2382
-#define mmTA_GRAD_ADJ_UCONFIG_BASE_IDX                                                                 1
 #define mmDB_OCCLUSION_COUNT0_LOW                                                                      0x23c0
 #define mmDB_OCCLUSION_COUNT0_LOW_BASE_IDX                                                             1
 #define mmDB_OCCLUSION_COUNT0_HI                                                                       0x23c1
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/GC/gc_9_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h
index 5c5e9b445432..2e1214be67a2 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/GC/gc_9_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h
@@ -4576,15 +4576,6 @@
 //TA_RESERVED_010C
 #define TA_RESERVED_010C__Unused__SHIFT                                                                       0x0
 #define TA_RESERVED_010C__Unused_MASK                                                                         0xFFFFFFFFL
-//TA_GRAD_ADJ
-#define TA_GRAD_ADJ__GRAD_ADJ_0__SHIFT                                                                        0x0
-#define TA_GRAD_ADJ__GRAD_ADJ_1__SHIFT                                                                        0x8
-#define TA_GRAD_ADJ__GRAD_ADJ_2__SHIFT                                                                        0x10
-#define TA_GRAD_ADJ__GRAD_ADJ_3__SHIFT                                                                        0x18
-#define TA_GRAD_ADJ__GRAD_ADJ_0_MASK                                                                          0x000000FFL
-#define TA_GRAD_ADJ__GRAD_ADJ_1_MASK                                                                          0x0000FF00L
-#define TA_GRAD_ADJ__GRAD_ADJ_2_MASK                                                                          0x00FF0000L
-#define TA_GRAD_ADJ__GRAD_ADJ_3_MASK                                                                          0xFF000000L
 //TA_STATUS
 #define TA_STATUS__FG_PFIFO_EMPTYB__SHIFT                                                                     0xc
 #define TA_STATUS__FG_LFIFO_EMPTYB__SHIFT                                                                     0xd
@@ -14459,9 +14450,6 @@
 #define DB_DFSM_CONTROL__PUNCHOUT_MODE_MASK                                                                   0x00000003L
 #define DB_DFSM_CONTROL__POPS_DRAIN_PS_ON_OVERLAP_MASK                                                        0x00000004L
 #define DB_DFSM_CONTROL__DISALLOW_OVERFLOW_MASK                                                               0x00000008L
-//DB_RENDER_FILTER
-#define DB_RENDER_FILTER__PS_INVOKE_MASK__SHIFT                                                               0x0
-#define DB_RENDER_FILTER__PS_INVOKE_MASK_MASK                                                                 0x0000FFFFL
 //DB_Z_INFO2
 #define DB_Z_INFO2__EPITCH__SHIFT                                                                             0x0
 #define DB_Z_INFO2__EPITCH_MASK                                                                               0x0000FFFFL
@@ -14959,11 +14947,9 @@
 #define PA_SC_TILE_STEERING_OVERRIDE__ENABLE__SHIFT                                                           0x0
 #define PA_SC_TILE_STEERING_OVERRIDE__NUM_SE__SHIFT                                                           0x1
 #define PA_SC_TILE_STEERING_OVERRIDE__NUM_RB_PER_SE__SHIFT                                                    0x5
-#define PA_SC_TILE_STEERING_OVERRIDE__DISABLE_SRBSL_DB_OPTIMIZED_PACKING__SHIFT                               0x8
 #define PA_SC_TILE_STEERING_OVERRIDE__ENABLE_MASK                                                             0x00000001L
 #define PA_SC_TILE_STEERING_OVERRIDE__NUM_SE_MASK                                                             0x00000006L
 #define PA_SC_TILE_STEERING_OVERRIDE__NUM_RB_PER_SE_MASK                                                      0x00000060L
-#define PA_SC_TILE_STEERING_OVERRIDE__DISABLE_SRBSL_DB_OPTIMIZED_PACKING_MASK                                 0x00000100L
 //CP_PERFMON_CNTX_CNTL
 #define CP_PERFMON_CNTX_CNTL__PERFMON_ENABLE__SHIFT                                                           0x1f
 #define CP_PERFMON_CNTX_CNTL__PERFMON_ENABLE_MASK                                                             0x80000000L
@@ -15003,20 +14989,6 @@
 #define PA_SC_HORIZ_GRID__TOP_HALF_MASK                                                                       0x0000FF00L
 #define PA_SC_HORIZ_GRID__BOT_HALF_MASK                                                                       0x00FF0000L
 #define PA_SC_HORIZ_GRID__BOT_QTR_MASK                                                                        0xFF000000L
-//PA_SC_FOV_WINDOW_LR
-#define PA_SC_FOV_WINDOW_LR__LEFT_EYE_FOV_LEFT__SHIFT                                                         0x0
-#define PA_SC_FOV_WINDOW_LR__LEFT_EYE_FOV_RIGHT__SHIFT                                                        0x8
-#define PA_SC_FOV_WINDOW_LR__RIGHT_EYE_FOV_LEFT__SHIFT                                                        0x10
-#define PA_SC_FOV_WINDOW_LR__RIGHT_EYE_FOV_RIGHT__SHIFT                                                       0x18
-#define PA_SC_FOV_WINDOW_LR__LEFT_EYE_FOV_LEFT_MASK                                                           0x000000FFL
-#define PA_SC_FOV_WINDOW_LR__LEFT_EYE_FOV_RIGHT_MASK                                                          0x0000FF00L
-#define PA_SC_FOV_WINDOW_LR__RIGHT_EYE_FOV_LEFT_MASK                                                          0x00FF0000L
-#define PA_SC_FOV_WINDOW_LR__RIGHT_EYE_FOV_RIGHT_MASK                                                         0xFF000000L
-//PA_SC_FOV_WINDOW_TB
-#define PA_SC_FOV_WINDOW_TB__FOV_TOP__SHIFT                                                                   0x0
-#define PA_SC_FOV_WINDOW_TB__FOV_BOT__SHIFT                                                                   0x8
-#define PA_SC_FOV_WINDOW_TB__FOV_TOP_MASK                                                                     0x000000FFL
-#define PA_SC_FOV_WINDOW_TB__FOV_BOT_MASK                                                                     0x0000FF00L
 //VGT_MULTI_PRIM_IB_RESET_INDX
 #define VGT_MULTI_PRIM_IB_RESET_INDX__RESET_INDX__SHIFT                                                       0x0
 #define VGT_MULTI_PRIM_IB_RESET_INDX__RESET_INDX_MASK                                                         0xFFFFFFFFL
@@ -17010,13 +16982,11 @@
 #define PA_SU_SMALL_PRIM_FILTER_CNTL__LINE_FILTER_DISABLE__SHIFT                                              0x2
 #define PA_SU_SMALL_PRIM_FILTER_CNTL__POINT_FILTER_DISABLE__SHIFT                                             0x3
 #define PA_SU_SMALL_PRIM_FILTER_CNTL__RECTANGLE_FILTER_DISABLE__SHIFT                                         0x4
-#define PA_SU_SMALL_PRIM_FILTER_CNTL__SRBSL_ENABLE__SHIFT                                                     0x5
 #define PA_SU_SMALL_PRIM_FILTER_CNTL__SMALL_PRIM_FILTER_ENABLE_MASK                                           0x00000001L
 #define PA_SU_SMALL_PRIM_FILTER_CNTL__TRIANGLE_FILTER_DISABLE_MASK                                            0x00000002L
 #define PA_SU_SMALL_PRIM_FILTER_CNTL__LINE_FILTER_DISABLE_MASK                                                0x00000004L
 #define PA_SU_SMALL_PRIM_FILTER_CNTL__POINT_FILTER_DISABLE_MASK                                               0x00000008L
 #define PA_SU_SMALL_PRIM_FILTER_CNTL__RECTANGLE_FILTER_DISABLE_MASK                                           0x00000010L
-#define PA_SU_SMALL_PRIM_FILTER_CNTL__SRBSL_ENABLE_MASK                                                       0x00000020L
 //PA_CL_OBJPRIM_ID_CNTL
 #define PA_CL_OBJPRIM_ID_CNTL__OBJ_ID_SEL__SHIFT                                                              0x0
 #define PA_CL_OBJPRIM_ID_CNTL__ADD_PIPED_PRIM_ID__SHIFT                                                       0x1
@@ -17345,9 +17315,6 @@
 #define VGT_DRAW_PAYLOAD_CNTL__EN_REG_RT_INDEX_MASK                                                           0x00000002L
 #define VGT_DRAW_PAYLOAD_CNTL__EN_PIPELINE_PRIMID_MASK                                                        0x00000004L
 #define VGT_DRAW_PAYLOAD_CNTL__OBJECT_ID_INST_EN_MASK                                                         0x00000008L
-//VGT_INDEX_PAYLOAD_CNTL
-#define VGT_INDEX_PAYLOAD_CNTL__COMPOUND_INDEX_EN__SHIFT                                                      0x0
-#define VGT_INDEX_PAYLOAD_CNTL__COMPOUND_INDEX_EN_MASK                                                        0x00000001L
 //VGT_INSTANCE_STEP_RATE_0
 #define VGT_INSTANCE_STEP_RATE_0__STEP_RATE__SHIFT                                                            0x0
 #define VGT_INSTANCE_STEP_RATE_0__STEP_RATE_MASK                                                              0xFFFFFFFFL
@@ -19849,9 +19816,6 @@
 #define IA_MULTI_VGT_PARAM__EN_INST_OPT_BASIC_MASK                                                            0x00200000L
 #define IA_MULTI_VGT_PARAM__EN_INST_OPT_ADV_MASK                                                              0x00400000L
 #define IA_MULTI_VGT_PARAM__HW_USE_ONLY_MASK                                                                  0x00800000L
-//VGT_OBJECT_ID
-#define VGT_OBJECT_ID__REG_OBJ_ID__SHIFT                                                                      0x0
-#define VGT_OBJECT_ID__REG_OBJ_ID_MASK                                                                        0xFFFFFFFFL
 //VGT_INSTANCE_BASE_ID
 #define VGT_INSTANCE_BASE_ID__INSTANCE_BASE_ID__SHIFT                                                         0x0
 #define VGT_INSTANCE_BASE_ID__INSTANCE_BASE_ID_MASK                                                           0xFFFFFFFFL
@@ -20067,15 +20031,6 @@
 //TA_CS_BC_BASE_ADDR_HI
 #define TA_CS_BC_BASE_ADDR_HI__ADDRESS__SHIFT                                                                 0x0
 #define TA_CS_BC_BASE_ADDR_HI__ADDRESS_MASK                                                                   0x000000FFL
-//TA_GRAD_ADJ_UCONFIG
-#define TA_GRAD_ADJ_UCONFIG__GRAD_ADJ_0__SHIFT                                                                0x0
-#define TA_GRAD_ADJ_UCONFIG__GRAD_ADJ_1__SHIFT                                                                0x8
-#define TA_GRAD_ADJ_UCONFIG__GRAD_ADJ_2__SHIFT                                                                0x10
-#define TA_GRAD_ADJ_UCONFIG__GRAD_ADJ_3__SHIFT                                                                0x18
-#define TA_GRAD_ADJ_UCONFIG__GRAD_ADJ_0_MASK                                                                  0x000000FFL
-#define TA_GRAD_ADJ_UCONFIG__GRAD_ADJ_1_MASK                                                                  0x0000FF00L
-#define TA_GRAD_ADJ_UCONFIG__GRAD_ADJ_2_MASK                                                                  0x00FF0000L
-#define TA_GRAD_ADJ_UCONFIG__GRAD_ADJ_3_MASK                                                                  0xFF000000L
 //DB_OCCLUSION_COUNT0_LOW
 #define DB_OCCLUSION_COUNT0_LOW__COUNT_LOW__SHIFT                                                             0x0
 #define DB_OCCLUSION_COUNT0_LOW__COUNT_LOW_MASK                                                               0xFFFFFFFFL
diff --git a/drivers/gpu/drm/amd/include/asic_reg/raven1/GC/gc_9_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_1_offset.h
index db7ef5ede0e5..030e0020902b 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/raven1/GC/gc_9_1_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_1_offset.h
@@ -815,8 +815,6 @@
 #define mmTA_CNTL_AUX_BASE_IDX                                                                         0
 #define mmTA_RESERVED_010C                                                                             0x0543
 #define mmTA_RESERVED_010C_BASE_IDX                                                                    0
-#define mmTA_GRAD_ADJ                                                                                  0x0544
-#define mmTA_GRAD_ADJ_BASE_IDX                                                                         0
 #define mmTA_STATUS                                                                                    0x0548
 #define mmTA_STATUS_BASE_IDX                                                                           0
 #define mmTA_SCRATCH                                                                                   0x0564
@@ -3617,8 +3615,6 @@
 #define mmDB_STENCIL_WRITE_BASE_HI_BASE_IDX                                                            1
 #define mmDB_DFSM_CONTROL                                                                              0x0018
 #define mmDB_DFSM_CONTROL_BASE_IDX                                                                     1
-#define mmDB_RENDER_FILTER                                                                             0x0019
-#define mmDB_RENDER_FILTER_BASE_IDX                                                                    1
 #define mmDB_Z_INFO2                                                                                   0x001a
 #define mmDB_Z_INFO2_BASE_IDX                                                                          1
 #define mmDB_STENCIL_INFO2                                                                             0x001b
@@ -3829,10 +3825,6 @@
 #define mmPA_SC_LEFT_VERT_GRID_BASE_IDX                                                                1
 #define mmPA_SC_HORIZ_GRID                                                                             0x00ea
 #define mmPA_SC_HORIZ_GRID_BASE_IDX                                                                    1
-#define mmPA_SC_FOV_WINDOW_LR                                                                          0x00eb
-#define mmPA_SC_FOV_WINDOW_LR_BASE_IDX                                                                 1
-#define mmPA_SC_FOV_WINDOW_TB                                                                          0x00ec
-#define mmPA_SC_FOV_WINDOW_TB_BASE_IDX                                                                 1
 #define mmVGT_MULTI_PRIM_IB_RESET_INDX                                                                 0x0103
 #define mmVGT_MULTI_PRIM_IB_RESET_INDX_BASE_IDX                                                        1
 #define mmCB_BLEND_RED                                                                                 0x0105
@@ -4361,8 +4353,6 @@
 #define mmVGT_GS_MAX_PRIMS_PER_SUBGROUP_BASE_IDX                                                       1
 #define mmVGT_DRAW_PAYLOAD_CNTL                                                                        0x02a6
 #define mmVGT_DRAW_PAYLOAD_CNTL_BASE_IDX                                                               1
-#define mmVGT_INDEX_PAYLOAD_CNTL                                                                       0x02a7
-#define mmVGT_INDEX_PAYLOAD_CNTL_BASE_IDX                                                              1
 #define mmVGT_INSTANCE_STEP_RATE_0                                                                     0x02a8
 #define mmVGT_INSTANCE_STEP_RATE_0_BASE_IDX                                                            1
 #define mmVGT_INSTANCE_STEP_RATE_1                                                                     0x02a9
@@ -5195,8 +5185,6 @@
 #define mmWD_INDEX_BUF_BASE_HI_BASE_IDX                                                                1
 #define mmIA_MULTI_VGT_PARAM                                                                           0x2258
 #define mmIA_MULTI_VGT_PARAM_BASE_IDX                                                                  1
-#define mmVGT_OBJECT_ID                                                                                0x2259
-#define mmVGT_OBJECT_ID_BASE_IDX                                                                       1
 #define mmVGT_INSTANCE_BASE_ID                                                                         0x225a
 #define mmVGT_INSTANCE_BASE_ID_BASE_IDX                                                                1
 #define mmPA_SU_LINE_STIPPLE_VALUE                                                                     0x2280
@@ -5283,8 +5271,6 @@
 #define mmTA_CS_BC_BASE_ADDR_BASE_IDX                                                                  1
 #define mmTA_CS_BC_BASE_ADDR_HI                                                                        0x2381
 #define mmTA_CS_BC_BASE_ADDR_HI_BASE_IDX                                                               1
-#define mmTA_GRAD_ADJ_UCONFIG                                                                          0x2382
-#define mmTA_GRAD_ADJ_UCONFIG_BASE_IDX                                                                 1
 #define mmDB_OCCLUSION_COUNT0_LOW                                                                      0x23c0
 #define mmDB_OCCLUSION_COUNT0_LOW_BASE_IDX                                                             1
 #define mmDB_OCCLUSION_COUNT0_HI                                                                       0x23c1
diff --git a/drivers/gpu/drm/amd/include/asic_reg/hdp/hdp_4_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/hdp/hdp_4_0_offset.h
new file mode 100644
index 000000000000..94325fc3abd5
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/hdp/hdp_4_0_offset.h
@@ -0,0 +1,209 @@
+/*
+ * Copyright (C) 2017  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _hdp_4_0_OFFSET_HEADER
+#define _hdp_4_0_OFFSET_HEADER
+
+
+
+// addressBlock: hdp_hdpdec
+// base address:	0x3c80
+#define mmHDP_MMHUB_TLVL	0x0000
+#define mmHDP_MMHUB_TLVL_BASE_IDX	0
+#define mmHDP_MMHUB_UNITID	0x0001
+#define mmHDP_MMHUB_UNITID_BASE_IDX	0
+#define mmHDP_NONSURFACE_BASE	0x0040
+#define mmHDP_NONSURFACE_BASE_BASE_IDX	0
+#define mmHDP_NONSURFACE_INFO	0x0041
+#define mmHDP_NONSURFACE_INFO_BASE_IDX	0
+#define mmHDP_NONSURFACE_BASE_HI	0x0042
+#define mmHDP_NONSURFACE_BASE_HI_BASE_IDX	0
+#define mmHDP_NONSURF_FLAGS	0x00c8
+#define mmHDP_NONSURF_FLAGS_BASE_IDX	0
+#define mmHDP_NONSURF_FLAGS_CLR	0x00c9
+#define mmHDP_NONSURF_FLAGS_CLR_BASE_IDX	0
+#define mmHDP_HOST_PATH_CNTL	0x00cc
+#define mmHDP_HOST_PATH_CNTL_BASE_IDX	0
+#define mmHDP_SW_SEMAPHORE	0x00cd
+#define mmHDP_SW_SEMAPHORE_BASE_IDX	0
+#define mmHDP_DEBUG0	0x00ce
+#define mmHDP_DEBUG0_BASE_IDX	0
+#define mmHDP_LAST_SURFACE_HIT	0x00d0
+#define mmHDP_LAST_SURFACE_HIT_BASE_IDX	0
+#define mmHDP_READ_CACHE_INVALIDATE	0x00d1
+#define mmHDP_READ_CACHE_INVALIDATE_BASE_IDX	0
+#define mmHDP_OUTSTANDING_REQ	0x00d2
+#define mmHDP_OUTSTANDING_REQ_BASE_IDX	0
+#define mmHDP_MISC_CNTL	0x00d3
+#define mmHDP_MISC_CNTL_BASE_IDX	0
+#define mmHDP_MEM_POWER_LS	0x00d4
+#define mmHDP_MEM_POWER_LS_BASE_IDX	0
+#define mmHDP_MMHUB_CNTL	0x00d5
+#define mmHDP_MMHUB_CNTL_BASE_IDX	0
+#define mmHDP_EDC_CNT	0x00d6
+#define mmHDP_EDC_CNT_BASE_IDX	0
+#define mmHDP_VERSION	0x00d7
+#define mmHDP_VERSION_BASE_IDX	0
+#define mmHDP_CLK_CNTL	0x00d8
+#define mmHDP_CLK_CNTL_BASE_IDX	0
+#define mmHDP_MEMIO_CNTL	0x00f6
+#define mmHDP_MEMIO_CNTL_BASE_IDX	0
+#define mmHDP_MEMIO_ADDR	0x00f7
+#define mmHDP_MEMIO_ADDR_BASE_IDX	0
+#define mmHDP_MEMIO_STATUS	0x00f8
+#define mmHDP_MEMIO_STATUS_BASE_IDX	0
+#define mmHDP_MEMIO_WR_DATA	0x00f9
+#define mmHDP_MEMIO_WR_DATA_BASE_IDX	0
+#define mmHDP_MEMIO_RD_DATA	0x00fa
+#define mmHDP_MEMIO_RD_DATA_BASE_IDX	0
+#define mmHDP_XDP_DIRECT2HDP_FIRST	0x0100
+#define mmHDP_XDP_DIRECT2HDP_FIRST_BASE_IDX	0
+#define mmHDP_XDP_D2H_FLUSH	0x0101
+#define mmHDP_XDP_D2H_FLUSH_BASE_IDX	0
+#define mmHDP_XDP_D2H_BAR_UPDATE	0x0102
+#define mmHDP_XDP_D2H_BAR_UPDATE_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_3	0x0103
+#define mmHDP_XDP_D2H_RSVD_3_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_4	0x0104
+#define mmHDP_XDP_D2H_RSVD_4_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_5	0x0105
+#define mmHDP_XDP_D2H_RSVD_5_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_6	0x0106
+#define mmHDP_XDP_D2H_RSVD_6_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_7	0x0107
+#define mmHDP_XDP_D2H_RSVD_7_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_8	0x0108
+#define mmHDP_XDP_D2H_RSVD_8_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_9	0x0109
+#define mmHDP_XDP_D2H_RSVD_9_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_10	0x010a
+#define mmHDP_XDP_D2H_RSVD_10_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_11	0x010b
+#define mmHDP_XDP_D2H_RSVD_11_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_12	0x010c
+#define mmHDP_XDP_D2H_RSVD_12_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_13	0x010d
+#define mmHDP_XDP_D2H_RSVD_13_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_14	0x010e
+#define mmHDP_XDP_D2H_RSVD_14_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_15	0x010f
+#define mmHDP_XDP_D2H_RSVD_15_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_16	0x0110
+#define mmHDP_XDP_D2H_RSVD_16_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_17	0x0111
+#define mmHDP_XDP_D2H_RSVD_17_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_18	0x0112
+#define mmHDP_XDP_D2H_RSVD_18_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_19	0x0113
+#define mmHDP_XDP_D2H_RSVD_19_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_20	0x0114
+#define mmHDP_XDP_D2H_RSVD_20_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_21	0x0115
+#define mmHDP_XDP_D2H_RSVD_21_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_22	0x0116
+#define mmHDP_XDP_D2H_RSVD_22_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_23	0x0117
+#define mmHDP_XDP_D2H_RSVD_23_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_24	0x0118
+#define mmHDP_XDP_D2H_RSVD_24_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_25	0x0119
+#define mmHDP_XDP_D2H_RSVD_25_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_26	0x011a
+#define mmHDP_XDP_D2H_RSVD_26_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_27	0x011b
+#define mmHDP_XDP_D2H_RSVD_27_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_28	0x011c
+#define mmHDP_XDP_D2H_RSVD_28_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_29	0x011d
+#define mmHDP_XDP_D2H_RSVD_29_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_30	0x011e
+#define mmHDP_XDP_D2H_RSVD_30_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_31	0x011f
+#define mmHDP_XDP_D2H_RSVD_31_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_32	0x0120
+#define mmHDP_XDP_D2H_RSVD_32_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_33	0x0121
+#define mmHDP_XDP_D2H_RSVD_33_BASE_IDX	0
+#define mmHDP_XDP_D2H_RSVD_34	0x0122
+#define mmHDP_XDP_D2H_RSVD_34_BASE_IDX	0
+#define mmHDP_XDP_DIRECT2HDP_LAST	0x0123
+#define mmHDP_XDP_DIRECT2HDP_LAST_BASE_IDX	0
+#define mmHDP_XDP_P2P_BAR_CFG	0x0124
+#define mmHDP_XDP_P2P_BAR_CFG_BASE_IDX	0
+#define mmHDP_XDP_P2P_MBX_OFFSET	0x0125
+#define mmHDP_XDP_P2P_MBX_OFFSET_BASE_IDX	0
+#define mmHDP_XDP_P2P_MBX_ADDR0	0x0126
+#define mmHDP_XDP_P2P_MBX_ADDR0_BASE_IDX	0
+#define mmHDP_XDP_P2P_MBX_ADDR1	0x0127
+#define mmHDP_XDP_P2P_MBX_ADDR1_BASE_IDX	0
+#define mmHDP_XDP_P2P_MBX_ADDR2	0x0128
+#define mmHDP_XDP_P2P_MBX_ADDR2_BASE_IDX	0
+#define mmHDP_XDP_P2P_MBX_ADDR3	0x0129
+#define mmHDP_XDP_P2P_MBX_ADDR3_BASE_IDX	0
+#define mmHDP_XDP_P2P_MBX_ADDR4	0x012a
+#define mmHDP_XDP_P2P_MBX_ADDR4_BASE_IDX	0
+#define mmHDP_XDP_P2P_MBX_ADDR5	0x012b
+#define mmHDP_XDP_P2P_MBX_ADDR5_BASE_IDX	0
+#define mmHDP_XDP_P2P_MBX_ADDR6	0x012c
+#define mmHDP_XDP_P2P_MBX_ADDR6_BASE_IDX	0
+#define mmHDP_XDP_HDP_MBX_MC_CFG	0x012d
+#define mmHDP_XDP_HDP_MBX_MC_CFG_BASE_IDX	0
+#define mmHDP_XDP_HDP_MC_CFG	0x012e
+#define mmHDP_XDP_HDP_MC_CFG_BASE_IDX	0
+#define mmHDP_XDP_HST_CFG	0x012f
+#define mmHDP_XDP_HST_CFG_BASE_IDX	0
+#define mmHDP_XDP_HDP_IPH_CFG	0x0131
+#define mmHDP_XDP_HDP_IPH_CFG_BASE_IDX	0
+#define mmHDP_XDP_P2P_BAR0	0x0134
+#define mmHDP_XDP_P2P_BAR0_BASE_IDX	0
+#define mmHDP_XDP_P2P_BAR1	0x0135
+#define mmHDP_XDP_P2P_BAR1_BASE_IDX	0
+#define mmHDP_XDP_P2P_BAR2	0x0136
+#define mmHDP_XDP_P2P_BAR2_BASE_IDX	0
+#define mmHDP_XDP_P2P_BAR3	0x0137
+#define mmHDP_XDP_P2P_BAR3_BASE_IDX	0
+#define mmHDP_XDP_P2P_BAR4	0x0138
+#define mmHDP_XDP_P2P_BAR4_BASE_IDX	0
+#define mmHDP_XDP_P2P_BAR5	0x0139
+#define mmHDP_XDP_P2P_BAR5_BASE_IDX	0
+#define mmHDP_XDP_P2P_BAR6	0x013a
+#define mmHDP_XDP_P2P_BAR6_BASE_IDX	0
+#define mmHDP_XDP_P2P_BAR7	0x013b
+#define mmHDP_XDP_P2P_BAR7_BASE_IDX	0
+#define mmHDP_XDP_FLUSH_ARMED_STS	0x013c
+#define mmHDP_XDP_FLUSH_ARMED_STS_BASE_IDX	0
+#define mmHDP_XDP_FLUSH_CNTR0_STS	0x013d
+#define mmHDP_XDP_FLUSH_CNTR0_STS_BASE_IDX	0
+#define mmHDP_XDP_BUSY_STS	0x013e
+#define mmHDP_XDP_BUSY_STS_BASE_IDX	0
+#define mmHDP_XDP_STICKY	0x013f
+#define mmHDP_XDP_STICKY_BASE_IDX	0
+#define mmHDP_XDP_CHKN	0x0140
+#define mmHDP_XDP_CHKN_BASE_IDX	0
+#define mmHDP_XDP_BARS_ADDR_39_36	0x0144
+#define mmHDP_XDP_BARS_ADDR_39_36_BASE_IDX	0
+#define mmHDP_XDP_MC_VM_FB_LOCATION_BASE	0x0145
+#define mmHDP_XDP_MC_VM_FB_LOCATION_BASE_BASE_IDX	0
+#define mmHDP_XDP_GPU_IOV_VIOLATION_LOG	0x0148
+#define mmHDP_XDP_GPU_IOV_VIOLATION_LOG_BASE_IDX	0
+#define mmHDP_XDP_MMHUB_ERROR	0x0149
+#define mmHDP_XDP_MMHUB_ERROR_BASE_IDX	0
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/hdp/hdp_4_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/hdp/hdp_4_0_sh_mask.h
new file mode 100644
index 000000000000..25e28691d62d
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/hdp/hdp_4_0_sh_mask.h
@@ -0,0 +1,601 @@
+/*
+ * Copyright (C) 2017  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _hdp_4_0_SH_MASK_HEADER
+#define _hdp_4_0_SH_MASK_HEADER
+
+
+// addressBlock: hdp_hdpdec
+//HDP_MMHUB_TLVL
+#define HDP_MMHUB_TLVL__HDP_WR_TLVL__SHIFT	0x0
+#define HDP_MMHUB_TLVL__HDP_RD_TLVL__SHIFT	0x4
+#define HDP_MMHUB_TLVL__XDP_WR_TLVL__SHIFT	0x8
+#define HDP_MMHUB_TLVL__XDP_RD_TLVL__SHIFT	0xc
+#define HDP_MMHUB_TLVL__XDP_MBX_WR_TLVL__SHIFT	0x10
+#define HDP_MMHUB_TLVL__HDP_WR_TLVL_MASK	0x00000007L
+#define HDP_MMHUB_TLVL__HDP_RD_TLVL_MASK	0x00000070L
+#define HDP_MMHUB_TLVL__XDP_WR_TLVL_MASK	0x00000700L
+#define HDP_MMHUB_TLVL__XDP_RD_TLVL_MASK	0x00007000L
+#define HDP_MMHUB_TLVL__XDP_MBX_WR_TLVL_MASK	0x00070000L
+//HDP_MMHUB_UNITID
+#define HDP_MMHUB_UNITID__HDP_UNITID__SHIFT	0x0
+#define HDP_MMHUB_UNITID__XDP_UNITID__SHIFT	0x8
+#define HDP_MMHUB_UNITID__XDP_MBX_UNITID__SHIFT	0x10
+#define HDP_MMHUB_UNITID__HDP_UNITID_MASK	0x0000003FL
+#define HDP_MMHUB_UNITID__XDP_UNITID_MASK	0x00003F00L
+#define HDP_MMHUB_UNITID__XDP_MBX_UNITID_MASK	0x003F0000L
+//HDP_NONSURFACE_BASE
+#define HDP_NONSURFACE_BASE__NONSURF_BASE_39_8__SHIFT	0x0
+#define HDP_NONSURFACE_BASE__NONSURF_BASE_39_8_MASK	0xFFFFFFFFL
+//HDP_NONSURFACE_INFO
+#define HDP_NONSURFACE_INFO__NONSURF_SWAP__SHIFT	0x4
+#define HDP_NONSURFACE_INFO__NONSURF_VMID__SHIFT	0x8
+#define HDP_NONSURFACE_INFO__NONSURF_SWAP_MASK	0x00000030L
+#define HDP_NONSURFACE_INFO__NONSURF_VMID_MASK	0x00000F00L
+//HDP_NONSURFACE_BASE_HI
+#define HDP_NONSURFACE_BASE_HI__NONSURF_BASE_47_40__SHIFT	0x0
+#define HDP_NONSURFACE_BASE_HI__NONSURF_BASE_47_40_MASK	0x000000FFL
+//HDP_NONSURF_FLAGS
+#define HDP_NONSURF_FLAGS__NONSURF_WRITE_FLAG__SHIFT	0x0
+#define HDP_NONSURF_FLAGS__NONSURF_READ_FLAG__SHIFT	0x1
+#define HDP_NONSURF_FLAGS__NONSURF_WRITE_FLAG_MASK	0x00000001L
+#define HDP_NONSURF_FLAGS__NONSURF_READ_FLAG_MASK	0x00000002L
+//HDP_NONSURF_FLAGS_CLR
+#define HDP_NONSURF_FLAGS_CLR__NONSURF_WRITE_FLAG_CLR__SHIFT	0x0
+#define HDP_NONSURF_FLAGS_CLR__NONSURF_READ_FLAG_CLR__SHIFT	0x1
+#define HDP_NONSURF_FLAGS_CLR__NONSURF_WRITE_FLAG_CLR_MASK	0x00000001L
+#define HDP_NONSURF_FLAGS_CLR__NONSURF_READ_FLAG_CLR_MASK	0x00000002L
+//HDP_HOST_PATH_CNTL
+#define HDP_HOST_PATH_CNTL__WR_STALL_TIMER__SHIFT	0x9
+#define HDP_HOST_PATH_CNTL__RD_STALL_TIMER__SHIFT	0xb
+#define HDP_HOST_PATH_CNTL__WRITE_COMBINE_TIMER_PRELOAD_CFG__SHIFT	0x12
+#define HDP_HOST_PATH_CNTL__WRITE_COMBINE_TIMER__SHIFT	0x13
+#define HDP_HOST_PATH_CNTL__WRITE_COMBINE_EN__SHIFT	0x15
+#define HDP_HOST_PATH_CNTL__WRITE_COMBINE_64B_EN__SHIFT	0x16
+#define HDP_HOST_PATH_CNTL__ALL_SURFACES_DIS__SHIFT	0x1d
+#define HDP_HOST_PATH_CNTL__WRITE_THROUGH_CACHE_DIS__SHIFT	0x1e
+#define HDP_HOST_PATH_CNTL__LIN_RD_CACHE_DIS__SHIFT	0x1f
+#define HDP_HOST_PATH_CNTL__WR_STALL_TIMER_MASK	0x00000600L
+#define HDP_HOST_PATH_CNTL__RD_STALL_TIMER_MASK	0x00001800L
+#define HDP_HOST_PATH_CNTL__WRITE_COMBINE_TIMER_PRELOAD_CFG_MASK	0x00040000L
+#define HDP_HOST_PATH_CNTL__WRITE_COMBINE_TIMER_MASK	0x00180000L
+#define HDP_HOST_PATH_CNTL__WRITE_COMBINE_EN_MASK	0x00200000L
+#define HDP_HOST_PATH_CNTL__WRITE_COMBINE_64B_EN_MASK	0x00400000L
+#define HDP_HOST_PATH_CNTL__ALL_SURFACES_DIS_MASK	0x20000000L
+#define HDP_HOST_PATH_CNTL__WRITE_THROUGH_CACHE_DIS_MASK	0x40000000L
+#define HDP_HOST_PATH_CNTL__LIN_RD_CACHE_DIS_MASK	0x80000000L
+//HDP_SW_SEMAPHORE
+#define HDP_SW_SEMAPHORE__SW_SEMAPHORE__SHIFT	0x0
+#define HDP_SW_SEMAPHORE__SW_SEMAPHORE_MASK	0xFFFFFFFFL
+//HDP_DEBUG0
+#define HDP_DEBUG0__HDP_DEBUG__SHIFT	0x0
+#define HDP_DEBUG0__HDP_DEBUG_MASK	0xFFFFFFFFL
+//HDP_LAST_SURFACE_HIT
+#define HDP_LAST_SURFACE_HIT__LAST_SURFACE_HIT__SHIFT	0x0
+#define HDP_LAST_SURFACE_HIT__LAST_SURFACE_HIT_MASK	0x00000003L
+//HDP_READ_CACHE_INVALIDATE
+#define HDP_READ_CACHE_INVALIDATE__READ_CACHE_INVALIDATE__SHIFT	0x0
+#define HDP_READ_CACHE_INVALIDATE__READ_CACHE_INVALIDATE_MASK	0x00000001L
+//HDP_OUTSTANDING_REQ
+#define HDP_OUTSTANDING_REQ__WRITE_REQ__SHIFT	0x0
+#define HDP_OUTSTANDING_REQ__READ_REQ__SHIFT	0x8
+#define HDP_OUTSTANDING_REQ__WRITE_REQ_MASK	0x000000FFL
+#define HDP_OUTSTANDING_REQ__READ_REQ_MASK	0x0000FF00L
+//HDP_MISC_CNTL
+#define HDP_MISC_CNTL__FLUSH_INVALIDATE_CACHE__SHIFT	0x0
+#define HDP_MISC_CNTL__IDLE_HYSTERESIS_CNTL__SHIFT	0x2
+#define HDP_MISC_CNTL__OUTSTANDING_WRITE_COUNT_1024__SHIFT	0x5
+#define HDP_MISC_CNTL__MULTIPLE_READS__SHIFT	0x6
+#define HDP_MISC_CNTL__SIMULTANEOUS_READS_WRITES__SHIFT	0xb
+#define HDP_MISC_CNTL__FED_ENABLE__SHIFT	0x15
+#define HDP_MISC_CNTL__SYSHUB_CHANNEL_PRIORITY__SHIFT	0x17
+#define HDP_MISC_CNTL__MMHUB_WRBURST_ENABLE__SHIFT	0x18
+#define HDP_MISC_CNTL__ALL_FUNCTION_CACHELINE_INVALID__SHIFT	0x19
+#define HDP_MISC_CNTL__HDP_MMHUB_PENDING_WR_TAG_CHECK__SHIFT	0x1a
+#define HDP_MISC_CNTL__XDP_MMHUB_PENDING_WR_TAG_CHECK__SHIFT	0x1b
+#define HDP_MISC_CNTL__VARIABLE_CACHELINE_SIZE__SHIFT	0x1c
+#define HDP_MISC_CNTL__ADAPTIVE_CACHELINE_SIZE__SHIFT	0x1d
+#define HDP_MISC_CNTL__MMHUB_WRBURST_SIZE__SHIFT	0x1e
+#define HDP_MISC_CNTL__FLUSH_INVALIDATE_CACHE_MASK	0x00000001L
+#define HDP_MISC_CNTL__IDLE_HYSTERESIS_CNTL_MASK	0x0000000CL
+#define HDP_MISC_CNTL__OUTSTANDING_WRITE_COUNT_1024_MASK	0x00000020L
+#define HDP_MISC_CNTL__MULTIPLE_READS_MASK	0x00000040L
+#define HDP_MISC_CNTL__SIMULTANEOUS_READS_WRITES_MASK	0x00000800L
+#define HDP_MISC_CNTL__FED_ENABLE_MASK	0x00200000L
+#define HDP_MISC_CNTL__SYSHUB_CHANNEL_PRIORITY_MASK	0x00800000L
+#define HDP_MISC_CNTL__MMHUB_WRBURST_ENABLE_MASK	0x01000000L
+#define HDP_MISC_CNTL__ALL_FUNCTION_CACHELINE_INVALID_MASK	0x02000000L
+#define HDP_MISC_CNTL__HDP_MMHUB_PENDING_WR_TAG_CHECK_MASK	0x04000000L
+#define HDP_MISC_CNTL__XDP_MMHUB_PENDING_WR_TAG_CHECK_MASK	0x08000000L
+#define HDP_MISC_CNTL__VARIABLE_CACHELINE_SIZE_MASK	0x10000000L
+#define HDP_MISC_CNTL__ADAPTIVE_CACHELINE_SIZE_MASK	0x20000000L
+#define HDP_MISC_CNTL__MMHUB_WRBURST_SIZE_MASK	0x40000000L
+//HDP_MEM_POWER_LS
+#define HDP_MEM_POWER_LS__LS_ENABLE__SHIFT	0x0
+#define HDP_MEM_POWER_LS__LS_HOLD__SHIFT	0x7
+#define HDP_MEM_POWER_LS__LS_ENABLE_MASK	0x00000001L
+#define HDP_MEM_POWER_LS__LS_HOLD_MASK	0x00001F80L
+//HDP_MMHUB_CNTL
+#define HDP_MMHUB_CNTL__HDP_MMHUB_RO__SHIFT	0x0
+#define HDP_MMHUB_CNTL__HDP_MMHUB_GCC__SHIFT	0x1
+#define HDP_MMHUB_CNTL__HDP_MMHUB_SNOOP__SHIFT	0x2
+#define HDP_MMHUB_CNTL__HDP_MMHUB_RO_MASK	0x00000001L
+#define HDP_MMHUB_CNTL__HDP_MMHUB_GCC_MASK	0x00000002L
+#define HDP_MMHUB_CNTL__HDP_MMHUB_SNOOP_MASK	0x00000004L
+//HDP_EDC_CNT
+#define HDP_EDC_CNT__MEM0_SED_COUNT__SHIFT	0x0
+#define HDP_EDC_CNT__MEM1_SED_COUNT__SHIFT	0x2
+#define HDP_EDC_CNT__MEM0_SED_COUNT_MASK	0x00000003L
+#define HDP_EDC_CNT__MEM1_SED_COUNT_MASK	0x0000000CL
+//HDP_VERSION
+#define HDP_VERSION__MINVER__SHIFT	0x0
+#define HDP_VERSION__MAJVER__SHIFT	0x8
+#define HDP_VERSION__REV__SHIFT	0x10
+#define HDP_VERSION__MINVER_MASK	0x000000FFL
+#define HDP_VERSION__MAJVER_MASK	0x0000FF00L
+#define HDP_VERSION__REV_MASK	0x00FF0000L
+//HDP_CLK_CNTL
+#define HDP_CLK_CNTL__REG_CLK_ENABLE_COUNT__SHIFT	0x0
+#define HDP_CLK_CNTL__REG_WAKE_DYN_CLK__SHIFT	0x4
+#define HDP_CLK_CNTL__DBUS_CLK_SOFT_OVERRIDE__SHIFT	0x1c
+#define HDP_CLK_CNTL__DYN_CLK_SOFT_OVERRIDE__SHIFT	0x1d
+#define HDP_CLK_CNTL__XDP_REG_CLK_SOFT_OVERRIDE__SHIFT	0x1e
+#define HDP_CLK_CNTL__HDP_REG_CLK_SOFT_OVERRIDE__SHIFT	0x1f
+#define HDP_CLK_CNTL__REG_CLK_ENABLE_COUNT_MASK	0x0000000FL
+#define HDP_CLK_CNTL__REG_WAKE_DYN_CLK_MASK	0x00000010L
+#define HDP_CLK_CNTL__DBUS_CLK_SOFT_OVERRIDE_MASK	0x10000000L
+#define HDP_CLK_CNTL__DYN_CLK_SOFT_OVERRIDE_MASK	0x20000000L
+#define HDP_CLK_CNTL__XDP_REG_CLK_SOFT_OVERRIDE_MASK	0x40000000L
+#define HDP_CLK_CNTL__HDP_REG_CLK_SOFT_OVERRIDE_MASK	0x80000000L
+//HDP_MEMIO_CNTL
+#define HDP_MEMIO_CNTL__MEMIO_SEND__SHIFT	0x0
+#define HDP_MEMIO_CNTL__MEMIO_OP__SHIFT	0x1
+#define HDP_MEMIO_CNTL__MEMIO_BE__SHIFT	0x2
+#define HDP_MEMIO_CNTL__MEMIO_WR_STROBE__SHIFT	0x6
+#define HDP_MEMIO_CNTL__MEMIO_RD_STROBE__SHIFT	0x7
+#define HDP_MEMIO_CNTL__MEMIO_ADDR_UPPER__SHIFT	0x8
+#define HDP_MEMIO_CNTL__MEMIO_CLR_WR_ERROR__SHIFT	0xe
+#define HDP_MEMIO_CNTL__MEMIO_CLR_RD_ERROR__SHIFT	0xf
+#define HDP_MEMIO_CNTL__MEMIO_VF__SHIFT	0x10
+#define HDP_MEMIO_CNTL__MEMIO_VFID__SHIFT	0x11
+#define HDP_MEMIO_CNTL__MEMIO_SEND_MASK	0x00000001L
+#define HDP_MEMIO_CNTL__MEMIO_OP_MASK	0x00000002L
+#define HDP_MEMIO_CNTL__MEMIO_BE_MASK	0x0000003CL
+#define HDP_MEMIO_CNTL__MEMIO_WR_STROBE_MASK	0x00000040L
+#define HDP_MEMIO_CNTL__MEMIO_RD_STROBE_MASK	0x00000080L
+#define HDP_MEMIO_CNTL__MEMIO_ADDR_UPPER_MASK	0x00003F00L
+#define HDP_MEMIO_CNTL__MEMIO_CLR_WR_ERROR_MASK	0x00004000L
+#define HDP_MEMIO_CNTL__MEMIO_CLR_RD_ERROR_MASK	0x00008000L
+#define HDP_MEMIO_CNTL__MEMIO_VF_MASK	0x00010000L
+#define HDP_MEMIO_CNTL__MEMIO_VFID_MASK	0x003E0000L
+//HDP_MEMIO_ADDR
+#define HDP_MEMIO_ADDR__MEMIO_ADDR_LOWER__SHIFT	0x0
+#define HDP_MEMIO_ADDR__MEMIO_ADDR_LOWER_MASK	0xFFFFFFFFL
+//HDP_MEMIO_STATUS
+#define HDP_MEMIO_STATUS__MEMIO_WR_STATUS__SHIFT	0x0
+#define HDP_MEMIO_STATUS__MEMIO_RD_STATUS__SHIFT	0x1
+#define HDP_MEMIO_STATUS__MEMIO_WR_ERROR__SHIFT	0x2
+#define HDP_MEMIO_STATUS__MEMIO_RD_ERROR__SHIFT	0x3
+#define HDP_MEMIO_STATUS__MEMIO_WR_STATUS_MASK	0x00000001L
+#define HDP_MEMIO_STATUS__MEMIO_RD_STATUS_MASK	0x00000002L
+#define HDP_MEMIO_STATUS__MEMIO_WR_ERROR_MASK	0x00000004L
+#define HDP_MEMIO_STATUS__MEMIO_RD_ERROR_MASK	0x00000008L
+//HDP_MEMIO_WR_DATA
+#define HDP_MEMIO_WR_DATA__MEMIO_WR_DATA__SHIFT	0x0
+#define HDP_MEMIO_WR_DATA__MEMIO_WR_DATA_MASK	0xFFFFFFFFL
+//HDP_MEMIO_RD_DATA
+#define HDP_MEMIO_RD_DATA__MEMIO_RD_DATA__SHIFT	0x0
+#define HDP_MEMIO_RD_DATA__MEMIO_RD_DATA_MASK	0xFFFFFFFFL
+//HDP_XDP_DIRECT2HDP_FIRST
+#define HDP_XDP_DIRECT2HDP_FIRST__RESERVED__SHIFT	0x0
+#define HDP_XDP_DIRECT2HDP_FIRST__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_FLUSH
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_FLUSH_NUM__SHIFT	0x0
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_MBX_ENC_DATA__SHIFT	0x4
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_MBX_ADDR_SEL__SHIFT	0x8
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_XPB_CLG__SHIFT	0xb
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_SEND_HOST__SHIFT	0x10
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_ALTER_FLUSH_NUM__SHIFT	0x12
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_RSVD_0__SHIFT	0x13
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_RSVD_1__SHIFT	0x14
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_FLUSH_NUM_MASK	0x0000000FL
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_MBX_ENC_DATA_MASK	0x000000F0L
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_MBX_ADDR_SEL_MASK	0x00000700L
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_XPB_CLG_MASK	0x0000F800L
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_SEND_HOST_MASK	0x00010000L
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_ALTER_FLUSH_NUM_MASK	0x00040000L
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_RSVD_0_MASK	0x00080000L
+#define HDP_XDP_D2H_FLUSH__D2H_FLUSH_RSVD_1_MASK	0x00100000L
+//HDP_XDP_D2H_BAR_UPDATE
+#define HDP_XDP_D2H_BAR_UPDATE__D2H_BAR_UPDATE_ADDR__SHIFT	0x0
+#define HDP_XDP_D2H_BAR_UPDATE__D2H_BAR_UPDATE_FLUSH_NUM__SHIFT	0x10
+#define HDP_XDP_D2H_BAR_UPDATE__D2H_BAR_UPDATE_BAR_NUM__SHIFT	0x14
+#define HDP_XDP_D2H_BAR_UPDATE__D2H_BAR_UPDATE_ADDR_MASK	0x0000FFFFL
+#define HDP_XDP_D2H_BAR_UPDATE__D2H_BAR_UPDATE_FLUSH_NUM_MASK	0x000F0000L
+#define HDP_XDP_D2H_BAR_UPDATE__D2H_BAR_UPDATE_BAR_NUM_MASK	0x00700000L
+//HDP_XDP_D2H_RSVD_3
+#define HDP_XDP_D2H_RSVD_3__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_3__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_4
+#define HDP_XDP_D2H_RSVD_4__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_4__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_5
+#define HDP_XDP_D2H_RSVD_5__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_5__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_6
+#define HDP_XDP_D2H_RSVD_6__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_6__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_7
+#define HDP_XDP_D2H_RSVD_7__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_7__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_8
+#define HDP_XDP_D2H_RSVD_8__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_8__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_9
+#define HDP_XDP_D2H_RSVD_9__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_9__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_10
+#define HDP_XDP_D2H_RSVD_10__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_10__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_11
+#define HDP_XDP_D2H_RSVD_11__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_11__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_12
+#define HDP_XDP_D2H_RSVD_12__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_12__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_13
+#define HDP_XDP_D2H_RSVD_13__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_13__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_14
+#define HDP_XDP_D2H_RSVD_14__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_14__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_15
+#define HDP_XDP_D2H_RSVD_15__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_15__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_16
+#define HDP_XDP_D2H_RSVD_16__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_16__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_17
+#define HDP_XDP_D2H_RSVD_17__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_17__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_18
+#define HDP_XDP_D2H_RSVD_18__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_18__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_19
+#define HDP_XDP_D2H_RSVD_19__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_19__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_20
+#define HDP_XDP_D2H_RSVD_20__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_20__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_21
+#define HDP_XDP_D2H_RSVD_21__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_21__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_22
+#define HDP_XDP_D2H_RSVD_22__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_22__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_23
+#define HDP_XDP_D2H_RSVD_23__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_23__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_24
+#define HDP_XDP_D2H_RSVD_24__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_24__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_25
+#define HDP_XDP_D2H_RSVD_25__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_25__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_26
+#define HDP_XDP_D2H_RSVD_26__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_26__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_27
+#define HDP_XDP_D2H_RSVD_27__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_27__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_28
+#define HDP_XDP_D2H_RSVD_28__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_28__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_29
+#define HDP_XDP_D2H_RSVD_29__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_29__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_30
+#define HDP_XDP_D2H_RSVD_30__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_30__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_31
+#define HDP_XDP_D2H_RSVD_31__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_31__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_32
+#define HDP_XDP_D2H_RSVD_32__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_32__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_33
+#define HDP_XDP_D2H_RSVD_33__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_33__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_D2H_RSVD_34
+#define HDP_XDP_D2H_RSVD_34__RESERVED__SHIFT	0x0
+#define HDP_XDP_D2H_RSVD_34__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_DIRECT2HDP_LAST
+#define HDP_XDP_DIRECT2HDP_LAST__RESERVED__SHIFT	0x0
+#define HDP_XDP_DIRECT2HDP_LAST__RESERVED_MASK	0xFFFFFFFFL
+//HDP_XDP_P2P_BAR_CFG
+#define HDP_XDP_P2P_BAR_CFG__P2P_BAR_CFG_ADDR_SIZE__SHIFT	0x0
+#define HDP_XDP_P2P_BAR_CFG__P2P_BAR_CFG_BAR_FROM__SHIFT	0x4
+#define HDP_XDP_P2P_BAR_CFG__P2P_BAR_CFG_ADDR_SIZE_MASK	0x0000000FL
+#define HDP_XDP_P2P_BAR_CFG__P2P_BAR_CFG_BAR_FROM_MASK	0x00000030L
+//HDP_XDP_P2P_MBX_OFFSET
+#define HDP_XDP_P2P_MBX_OFFSET__P2P_MBX_OFFSET__SHIFT	0x0
+#define HDP_XDP_P2P_MBX_OFFSET__P2P_MBX_OFFSET_MASK	0x0001FFFFL
+//HDP_XDP_P2P_MBX_ADDR0
+#define HDP_XDP_P2P_MBX_ADDR0__VALID__SHIFT	0x0
+#define HDP_XDP_P2P_MBX_ADDR0__ADDR_35_19__SHIFT	0x3
+#define HDP_XDP_P2P_MBX_ADDR0__ADDR_39_36__SHIFT	0x14
+#define HDP_XDP_P2P_MBX_ADDR0__ADDR_47_40__SHIFT	0x18
+#define HDP_XDP_P2P_MBX_ADDR0__VALID_MASK	0x00000001L
+#define HDP_XDP_P2P_MBX_ADDR0__ADDR_35_19_MASK	0x000FFFF8L
+#define HDP_XDP_P2P_MBX_ADDR0__ADDR_39_36_MASK	0x00F00000L
+#define HDP_XDP_P2P_MBX_ADDR0__ADDR_47_40_MASK	0xFF000000L
+//HDP_XDP_P2P_MBX_ADDR1
+#define HDP_XDP_P2P_MBX_ADDR1__VALID__SHIFT	0x0
+#define HDP_XDP_P2P_MBX_ADDR1__ADDR_35_19__SHIFT	0x3
+#define HDP_XDP_P2P_MBX_ADDR1__ADDR_39_36__SHIFT	0x14
+#define HDP_XDP_P2P_MBX_ADDR1__ADDR_47_40__SHIFT	0x18
+#define HDP_XDP_P2P_MBX_ADDR1__VALID_MASK	0x00000001L
+#define HDP_XDP_P2P_MBX_ADDR1__ADDR_35_19_MASK	0x000FFFF8L
+#define HDP_XDP_P2P_MBX_ADDR1__ADDR_39_36_MASK	0x00F00000L
+#define HDP_XDP_P2P_MBX_ADDR1__ADDR_47_40_MASK	0xFF000000L
+//HDP_XDP_P2P_MBX_ADDR2
+#define HDP_XDP_P2P_MBX_ADDR2__VALID__SHIFT	0x0
+#define HDP_XDP_P2P_MBX_ADDR2__ADDR_35_19__SHIFT	0x3
+#define HDP_XDP_P2P_MBX_ADDR2__ADDR_39_36__SHIFT	0x14
+#define HDP_XDP_P2P_MBX_ADDR2__ADDR_47_40__SHIFT	0x18
+#define HDP_XDP_P2P_MBX_ADDR2__VALID_MASK	0x00000001L
+#define HDP_XDP_P2P_MBX_ADDR2__ADDR_35_19_MASK	0x000FFFF8L
+#define HDP_XDP_P2P_MBX_ADDR2__ADDR_39_36_MASK	0x00F00000L
+#define HDP_XDP_P2P_MBX_ADDR2__ADDR_47_40_MASK	0xFF000000L
+//HDP_XDP_P2P_MBX_ADDR3
+#define HDP_XDP_P2P_MBX_ADDR3__VALID__SHIFT	0x0
+#define HDP_XDP_P2P_MBX_ADDR3__ADDR_35_19__SHIFT	0x3
+#define HDP_XDP_P2P_MBX_ADDR3__ADDR_39_36__SHIFT	0x14
+#define HDP_XDP_P2P_MBX_ADDR3__ADDR_47_40__SHIFT	0x18
+#define HDP_XDP_P2P_MBX_ADDR3__VALID_MASK	0x00000001L
+#define HDP_XDP_P2P_MBX_ADDR3__ADDR_35_19_MASK	0x000FFFF8L
+#define HDP_XDP_P2P_MBX_ADDR3__ADDR_39_36_MASK	0x00F00000L
+#define HDP_XDP_P2P_MBX_ADDR3__ADDR_47_40_MASK	0xFF000000L
+//HDP_XDP_P2P_MBX_ADDR4
+#define HDP_XDP_P2P_MBX_ADDR4__VALID__SHIFT	0x0
+#define HDP_XDP_P2P_MBX_ADDR4__ADDR_35_19__SHIFT	0x3
+#define HDP_XDP_P2P_MBX_ADDR4__ADDR_39_36__SHIFT	0x14
+#define HDP_XDP_P2P_MBX_ADDR4__ADDR_47_40__SHIFT	0x18
+#define HDP_XDP_P2P_MBX_ADDR4__VALID_MASK	0x00000001L
+#define HDP_XDP_P2P_MBX_ADDR4__ADDR_35_19_MASK	0x000FFFF8L
+#define HDP_XDP_P2P_MBX_ADDR4__ADDR_39_36_MASK	0x00F00000L
+#define HDP_XDP_P2P_MBX_ADDR4__ADDR_47_40_MASK	0xFF000000L
+//HDP_XDP_P2P_MBX_ADDR5
+#define HDP_XDP_P2P_MBX_ADDR5__VALID__SHIFT	0x0
+#define HDP_XDP_P2P_MBX_ADDR5__ADDR_35_19__SHIFT	0x3
+#define HDP_XDP_P2P_MBX_ADDR5__ADDR_39_36__SHIFT	0x14
+#define HDP_XDP_P2P_MBX_ADDR5__ADDR_47_40__SHIFT	0x18
+#define HDP_XDP_P2P_MBX_ADDR5__VALID_MASK	0x00000001L
+#define HDP_XDP_P2P_MBX_ADDR5__ADDR_35_19_MASK	0x000FFFF8L
+#define HDP_XDP_P2P_MBX_ADDR5__ADDR_39_36_MASK	0x00F00000L
+#define HDP_XDP_P2P_MBX_ADDR5__ADDR_47_40_MASK	0xFF000000L
+//HDP_XDP_P2P_MBX_ADDR6
+#define HDP_XDP_P2P_MBX_ADDR6__VALID__SHIFT	0x0
+#define HDP_XDP_P2P_MBX_ADDR6__ADDR_35_19__SHIFT	0x3
+#define HDP_XDP_P2P_MBX_ADDR6__ADDR_39_36__SHIFT	0x14
+#define HDP_XDP_P2P_MBX_ADDR6__ADDR_47_40__SHIFT	0x18
+#define HDP_XDP_P2P_MBX_ADDR6__VALID_MASK	0x00000001L
+#define HDP_XDP_P2P_MBX_ADDR6__ADDR_35_19_MASK	0x000FFFF8L
+#define HDP_XDP_P2P_MBX_ADDR6__ADDR_39_36_MASK	0x00F00000L
+#define HDP_XDP_P2P_MBX_ADDR6__ADDR_47_40_MASK	0xFF000000L
+//HDP_XDP_HDP_MBX_MC_CFG
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_QOS__SHIFT	0x0
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_SWAP__SHIFT	0x4
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_VMID__SHIFT	0x8
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_RO__SHIFT	0xc
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_GCC__SHIFT	0xd
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_SNOOP__SHIFT	0xe
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_QOS_MASK	0x0000000FL
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_SWAP_MASK	0x00000030L
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_VMID_MASK	0x00000F00L
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_RO_MASK	0x00001000L
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_GCC_MASK	0x00002000L
+#define HDP_XDP_HDP_MBX_MC_CFG__HDP_MBX_MC_CFG_TAP_WRREQ_SNOOP_MASK	0x00004000L
+//HDP_XDP_HDP_MC_CFG
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_HST_TAP_REQ_SNOOP__SHIFT	0x3
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_HST_TAP_REQ_SWAP__SHIFT	0x4
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_HST_TAP_REQ_VMID__SHIFT	0x8
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_HST_TAP_REQ_RO__SHIFT	0xc
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_HST_TAP_REQ_GCC__SHIFT	0xd
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_XDP_HIGHER_PRI_THRESH__SHIFT	0xe
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_HST_TAP_REQ_SNOOP_MASK	0x00000008L
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_HST_TAP_REQ_SWAP_MASK	0x00000030L
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_HST_TAP_REQ_VMID_MASK	0x00000F00L
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_HST_TAP_REQ_RO_MASK	0x00001000L
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_HST_TAP_REQ_GCC_MASK	0x00002000L
+#define HDP_XDP_HDP_MC_CFG__HDP_MC_CFG_XDP_HIGHER_PRI_THRESH_MASK	0x000FC000L
+//HDP_XDP_HST_CFG
+#define HDP_XDP_HST_CFG__HST_CFG_WR_COMBINE_EN__SHIFT	0x0
+#define HDP_XDP_HST_CFG__HST_CFG_WR_COMBINE_TIMER__SHIFT	0x1
+#define HDP_XDP_HST_CFG__HST_CFG_WR_BURST_EN__SHIFT	0x3
+#define HDP_XDP_HST_CFG__HST_CFG_WR_COMBINE_64B_EN__SHIFT	0x4
+#define HDP_XDP_HST_CFG__HST_CFG_WR_COMBINE_TIMER_PRELOAD_CFG__SHIFT	0x5
+#define HDP_XDP_HST_CFG__HST_CFG_WR_COMBINE_EN_MASK	0x00000001L
+#define HDP_XDP_HST_CFG__HST_CFG_WR_COMBINE_TIMER_MASK	0x00000006L
+#define HDP_XDP_HST_CFG__HST_CFG_WR_BURST_EN_MASK	0x00000008L
+#define HDP_XDP_HST_CFG__HST_CFG_WR_COMBINE_64B_EN_MASK	0x00000010L
+#define HDP_XDP_HST_CFG__HST_CFG_WR_COMBINE_TIMER_PRELOAD_CFG_MASK	0x00000020L
+//HDP_XDP_HDP_IPH_CFG
+#define HDP_XDP_HDP_IPH_CFG__HDP_IPH_CFG_SYS_FIFO_DEPTH_OVERRIDE__SHIFT	0x0
+#define HDP_XDP_HDP_IPH_CFG__HDP_IPH_CFG_XDP_FIFO_DEPTH_OVERRIDE__SHIFT	0x6
+#define HDP_XDP_HDP_IPH_CFG__HDP_IPH_CFG_INVERSE_PEER_TAG_MATCHING__SHIFT	0xc
+#define HDP_XDP_HDP_IPH_CFG__HDP_IPH_CFG_P2P_RD_EN__SHIFT	0xd
+#define HDP_XDP_HDP_IPH_CFG__HDP_IPH_CFG_SYS_FIFO_DEPTH_OVERRIDE_MASK	0x0000003FL
+#define HDP_XDP_HDP_IPH_CFG__HDP_IPH_CFG_XDP_FIFO_DEPTH_OVERRIDE_MASK	0x00000FC0L
+#define HDP_XDP_HDP_IPH_CFG__HDP_IPH_CFG_INVERSE_PEER_TAG_MATCHING_MASK	0x00001000L
+#define HDP_XDP_HDP_IPH_CFG__HDP_IPH_CFG_P2P_RD_EN_MASK	0x00002000L
+//HDP_XDP_P2P_BAR0
+#define HDP_XDP_P2P_BAR0__ADDR__SHIFT	0x0
+#define HDP_XDP_P2P_BAR0__FLUSH__SHIFT	0x10
+#define HDP_XDP_P2P_BAR0__VALID__SHIFT	0x14
+#define HDP_XDP_P2P_BAR0__ADDR_MASK	0x0000FFFFL
+#define HDP_XDP_P2P_BAR0__FLUSH_MASK	0x000F0000L
+#define HDP_XDP_P2P_BAR0__VALID_MASK	0x00100000L
+//HDP_XDP_P2P_BAR1
+#define HDP_XDP_P2P_BAR1__ADDR__SHIFT	0x0
+#define HDP_XDP_P2P_BAR1__FLUSH__SHIFT	0x10
+#define HDP_XDP_P2P_BAR1__VALID__SHIFT	0x14
+#define HDP_XDP_P2P_BAR1__ADDR_MASK	0x0000FFFFL
+#define HDP_XDP_P2P_BAR1__FLUSH_MASK	0x000F0000L
+#define HDP_XDP_P2P_BAR1__VALID_MASK	0x00100000L
+//HDP_XDP_P2P_BAR2
+#define HDP_XDP_P2P_BAR2__ADDR__SHIFT	0x0
+#define HDP_XDP_P2P_BAR2__FLUSH__SHIFT	0x10
+#define HDP_XDP_P2P_BAR2__VALID__SHIFT	0x14
+#define HDP_XDP_P2P_BAR2__ADDR_MASK	0x0000FFFFL
+#define HDP_XDP_P2P_BAR2__FLUSH_MASK	0x000F0000L
+#define HDP_XDP_P2P_BAR2__VALID_MASK	0x00100000L
+//HDP_XDP_P2P_BAR3
+#define HDP_XDP_P2P_BAR3__ADDR__SHIFT	0x0
+#define HDP_XDP_P2P_BAR3__FLUSH__SHIFT	0x10
+#define HDP_XDP_P2P_BAR3__VALID__SHIFT	0x14
+#define HDP_XDP_P2P_BAR3__ADDR_MASK	0x0000FFFFL
+#define HDP_XDP_P2P_BAR3__FLUSH_MASK	0x000F0000L
+#define HDP_XDP_P2P_BAR3__VALID_MASK	0x00100000L
+//HDP_XDP_P2P_BAR4
+#define HDP_XDP_P2P_BAR4__ADDR__SHIFT	0x0
+#define HDP_XDP_P2P_BAR4__FLUSH__SHIFT	0x10
+#define HDP_XDP_P2P_BAR4__VALID__SHIFT	0x14
+#define HDP_XDP_P2P_BAR4__ADDR_MASK	0x0000FFFFL
+#define HDP_XDP_P2P_BAR4__FLUSH_MASK	0x000F0000L
+#define HDP_XDP_P2P_BAR4__VALID_MASK	0x00100000L
+//HDP_XDP_P2P_BAR5
+#define HDP_XDP_P2P_BAR5__ADDR__SHIFT	0x0
+#define HDP_XDP_P2P_BAR5__FLUSH__SHIFT	0x10
+#define HDP_XDP_P2P_BAR5__VALID__SHIFT	0x14
+#define HDP_XDP_P2P_BAR5__ADDR_MASK	0x0000FFFFL
+#define HDP_XDP_P2P_BAR5__FLUSH_MASK	0x000F0000L
+#define HDP_XDP_P2P_BAR5__VALID_MASK	0x00100000L
+//HDP_XDP_P2P_BAR6
+#define HDP_XDP_P2P_BAR6__ADDR__SHIFT	0x0
+#define HDP_XDP_P2P_BAR6__FLUSH__SHIFT	0x10
+#define HDP_XDP_P2P_BAR6__VALID__SHIFT	0x14
+#define HDP_XDP_P2P_BAR6__ADDR_MASK	0x0000FFFFL
+#define HDP_XDP_P2P_BAR6__FLUSH_MASK	0x000F0000L
+#define HDP_XDP_P2P_BAR6__VALID_MASK	0x00100000L
+//HDP_XDP_P2P_BAR7
+#define HDP_XDP_P2P_BAR7__ADDR__SHIFT	0x0
+#define HDP_XDP_P2P_BAR7__FLUSH__SHIFT	0x10
+#define HDP_XDP_P2P_BAR7__VALID__SHIFT	0x14
+#define HDP_XDP_P2P_BAR7__ADDR_MASK	0x0000FFFFL
+#define HDP_XDP_P2P_BAR7__FLUSH_MASK	0x000F0000L
+#define HDP_XDP_P2P_BAR7__VALID_MASK	0x00100000L
+//HDP_XDP_FLUSH_ARMED_STS
+#define HDP_XDP_FLUSH_ARMED_STS__FLUSH_ARMED_STS__SHIFT	0x0
+#define HDP_XDP_FLUSH_ARMED_STS__FLUSH_ARMED_STS_MASK	0xFFFFFFFFL
+//HDP_XDP_FLUSH_CNTR0_STS
+#define HDP_XDP_FLUSH_CNTR0_STS__FLUSH_CNTR0_STS__SHIFT	0x0
+#define HDP_XDP_FLUSH_CNTR0_STS__FLUSH_CNTR0_STS_MASK	0x03FFFFFFL
+//HDP_XDP_BUSY_STS
+#define HDP_XDP_BUSY_STS__BUSY_BITS__SHIFT	0x0
+#define HDP_XDP_BUSY_STS__BUSY_BITS_MASK	0x0003FFFFL
+//HDP_XDP_STICKY
+#define HDP_XDP_STICKY__STICKY_STS__SHIFT	0x0
+#define HDP_XDP_STICKY__STICKY_W1C__SHIFT	0x10
+#define HDP_XDP_STICKY__STICKY_STS_MASK	0x0000FFFFL
+#define HDP_XDP_STICKY__STICKY_W1C_MASK	0xFFFF0000L
+//HDP_XDP_CHKN
+#define HDP_XDP_CHKN__CHKN_0_RSVD__SHIFT	0x0
+#define HDP_XDP_CHKN__CHKN_1_RSVD__SHIFT	0x8
+#define HDP_XDP_CHKN__CHKN_2_RSVD__SHIFT	0x10
+#define HDP_XDP_CHKN__CHKN_3_RSVD__SHIFT	0x18
+#define HDP_XDP_CHKN__CHKN_0_RSVD_MASK	0x000000FFL
+#define HDP_XDP_CHKN__CHKN_1_RSVD_MASK	0x0000FF00L
+#define HDP_XDP_CHKN__CHKN_2_RSVD_MASK	0x00FF0000L
+#define HDP_XDP_CHKN__CHKN_3_RSVD_MASK	0xFF000000L
+//HDP_XDP_BARS_ADDR_39_36
+#define HDP_XDP_BARS_ADDR_39_36__BAR0_ADDR_39_36__SHIFT	0x0
+#define HDP_XDP_BARS_ADDR_39_36__BAR1_ADDR_39_36__SHIFT	0x4
+#define HDP_XDP_BARS_ADDR_39_36__BAR2_ADDR_39_36__SHIFT	0x8
+#define HDP_XDP_BARS_ADDR_39_36__BAR3_ADDR_39_36__SHIFT	0xc
+#define HDP_XDP_BARS_ADDR_39_36__BAR4_ADDR_39_36__SHIFT	0x10
+#define HDP_XDP_BARS_ADDR_39_36__BAR5_ADDR_39_36__SHIFT	0x14
+#define HDP_XDP_BARS_ADDR_39_36__BAR6_ADDR_39_36__SHIFT	0x18
+#define HDP_XDP_BARS_ADDR_39_36__BAR7_ADDR_39_36__SHIFT	0x1c
+#define HDP_XDP_BARS_ADDR_39_36__BAR0_ADDR_39_36_MASK	0x0000000FL
+#define HDP_XDP_BARS_ADDR_39_36__BAR1_ADDR_39_36_MASK	0x000000F0L
+#define HDP_XDP_BARS_ADDR_39_36__BAR2_ADDR_39_36_MASK	0x00000F00L
+#define HDP_XDP_BARS_ADDR_39_36__BAR3_ADDR_39_36_MASK	0x0000F000L
+#define HDP_XDP_BARS_ADDR_39_36__BAR4_ADDR_39_36_MASK	0x000F0000L
+#define HDP_XDP_BARS_ADDR_39_36__BAR5_ADDR_39_36_MASK	0x00F00000L
+#define HDP_XDP_BARS_ADDR_39_36__BAR6_ADDR_39_36_MASK	0x0F000000L
+#define HDP_XDP_BARS_ADDR_39_36__BAR7_ADDR_39_36_MASK	0xF0000000L
+//HDP_XDP_MC_VM_FB_LOCATION_BASE
+#define HDP_XDP_MC_VM_FB_LOCATION_BASE__FB_BASE__SHIFT	0x0
+#define HDP_XDP_MC_VM_FB_LOCATION_BASE__FB_BASE_MASK	0x03FFFFFFL
+//HDP_XDP_GPU_IOV_VIOLATION_LOG
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__VIOLATION_STATUS__SHIFT	0x0
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__MULTIPLE_VIOLATION_STATUS__SHIFT	0x1
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__ADDRESS__SHIFT	0x2
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__OPCODE__SHIFT	0x12
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__VF__SHIFT	0x13
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__VFID__SHIFT	0x14
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__INITIATOR_ID__SHIFT	0x18
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__VIOLATION_STATUS_MASK	0x00000001L
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__MULTIPLE_VIOLATION_STATUS_MASK	0x00000002L
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__ADDRESS_MASK	0x0003FFFCL
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__OPCODE_MASK	0x00040000L
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__VF_MASK	0x00080000L
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__VFID_MASK	0x00F00000L
+#define HDP_XDP_GPU_IOV_VIOLATION_LOG__INITIATOR_ID_MASK	0xFF000000L
+//HDP_XDP_MMHUB_ERROR
+#define HDP_XDP_MMHUB_ERROR__HDP_BRESP_01__SHIFT	0x1
+#define HDP_XDP_MMHUB_ERROR__HDP_BRESP_10__SHIFT	0x2
+#define HDP_XDP_MMHUB_ERROR__HDP_BRESP_11__SHIFT	0x3
+#define HDP_XDP_MMHUB_ERROR__HDP_BUSER_NACK_01__SHIFT	0x5
+#define HDP_XDP_MMHUB_ERROR__HDP_BUSER_NACK_10__SHIFT	0x6
+#define HDP_XDP_MMHUB_ERROR__HDP_BUSER_NACK_11__SHIFT	0x7
+#define HDP_XDP_MMHUB_ERROR__HDP_RRESP_01__SHIFT	0x9
+#define HDP_XDP_MMHUB_ERROR__HDP_RRESP_10__SHIFT	0xa
+#define HDP_XDP_MMHUB_ERROR__HDP_RRESP_11__SHIFT	0xb
+#define HDP_XDP_MMHUB_ERROR__HDP_RUSER_NACK_01__SHIFT	0xd
+#define HDP_XDP_MMHUB_ERROR__HDP_RUSER_NACK_10__SHIFT	0xe
+#define HDP_XDP_MMHUB_ERROR__HDP_RUSER_NACK_11__SHIFT	0xf
+#define HDP_XDP_MMHUB_ERROR__XDP_BRESP_01__SHIFT	0x11
+#define HDP_XDP_MMHUB_ERROR__XDP_BRESP_10__SHIFT	0x12
+#define HDP_XDP_MMHUB_ERROR__XDP_BRESP_11__SHIFT	0x13
+#define HDP_XDP_MMHUB_ERROR__XDP_BUSER_NACK_01__SHIFT	0x15
+#define HDP_XDP_MMHUB_ERROR__XDP_BUSER_NACK_10__SHIFT	0x16
+#define HDP_XDP_MMHUB_ERROR__XDP_BUSER_NACK_11__SHIFT	0x17
+#define HDP_XDP_MMHUB_ERROR__HDP_BRESP_01_MASK	0x00000002L
+#define HDP_XDP_MMHUB_ERROR__HDP_BRESP_10_MASK	0x00000004L
+#define HDP_XDP_MMHUB_ERROR__HDP_BRESP_11_MASK	0x00000008L
+#define HDP_XDP_MMHUB_ERROR__HDP_BUSER_NACK_01_MASK	0x00000020L
+#define HDP_XDP_MMHUB_ERROR__HDP_BUSER_NACK_10_MASK	0x00000040L
+#define HDP_XDP_MMHUB_ERROR__HDP_BUSER_NACK_11_MASK	0x00000080L
+#define HDP_XDP_MMHUB_ERROR__HDP_RRESP_01_MASK	0x00000200L
+#define HDP_XDP_MMHUB_ERROR__HDP_RRESP_10_MASK	0x00000400L
+#define HDP_XDP_MMHUB_ERROR__HDP_RRESP_11_MASK	0x00000800L
+#define HDP_XDP_MMHUB_ERROR__HDP_RUSER_NACK_01_MASK	0x00002000L
+#define HDP_XDP_MMHUB_ERROR__HDP_RUSER_NACK_10_MASK	0x00004000L
+#define HDP_XDP_MMHUB_ERROR__HDP_RUSER_NACK_11_MASK	0x00008000L
+#define HDP_XDP_MMHUB_ERROR__XDP_BRESP_01_MASK	0x00020000L
+#define HDP_XDP_MMHUB_ERROR__XDP_BRESP_10_MASK	0x00040000L
+#define HDP_XDP_MMHUB_ERROR__XDP_BRESP_11_MASK	0x00080000L
+#define HDP_XDP_MMHUB_ERROR__XDP_BUSER_NACK_01_MASK	0x00200000L
+#define HDP_XDP_MMHUB_ERROR__XDP_BUSER_NACK_10_MASK	0x00400000L
+#define HDP_XDP_MMHUB_ERROR__XDP_BUSER_NACK_11_MASK	0x00800000L
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/MMHUB/mmhub_1_0_default.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_default.h
index 02989fe9f7bd..02989fe9f7bd 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/MMHUB/mmhub_1_0_default.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_default.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/MMHUB/mmhub_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h
index 352ffae7a7ca..352ffae7a7ca 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/MMHUB/mmhub_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/MMHUB/mmhub_1_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_sh_mask.h
index 34278ef2aa1b..34278ef2aa1b 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/MMHUB/mmhub_1_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_sh_mask.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/raven1/MMHUB/mmhub_9_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_1_offset.h
index 4b6fc7242277..4b6fc7242277 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/raven1/MMHUB/mmhub_9_1_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_1_offset.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/raven1/MMHUB/mmhub_9_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_1_sh_mask.h
index 8effec70a3c0..8effec70a3c0 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/raven1/MMHUB/mmhub_9_1_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_1_sh_mask.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/raven1/MP/mp_10_0_default.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_10_0_default.h
index f087a2bf3863..f087a2bf3863 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/raven1/MP/mp_10_0_default.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_10_0_default.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/raven1/MP/mp_10_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_10_0_offset.h
index 1063e5e8ea0e..1063e5e8ea0e 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/raven1/MP/mp_10_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_10_0_offset.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/raven1/MP/mp_10_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_10_0_sh_mask.h
index 9b0c8c575160..9b0c8c575160 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/raven1/MP/mp_10_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_10_0_sh_mask.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_9_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_9_0_offset.h
new file mode 100644
index 000000000000..299e5266a8c0
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_9_0_offset.h
@@ -0,0 +1,375 @@
+/*
+ * Copyright (C) 2017  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _mp_9_0_OFFSET_HEADER
+#define _mp_9_0_OFFSET_HEADER
+
+
+
+// addressBlock: mp_SmuMp0_SmnDec
+// base address:	0x0
+#define mmMP0_SMN_C2PMSG_32	0x0060
+#define mmMP0_SMN_C2PMSG_32_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_33	0x0061
+#define mmMP0_SMN_C2PMSG_33_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_34	0x0062
+#define mmMP0_SMN_C2PMSG_34_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_35	0x0063
+#define mmMP0_SMN_C2PMSG_35_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_36	0x0064
+#define mmMP0_SMN_C2PMSG_36_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_37	0x0065
+#define mmMP0_SMN_C2PMSG_37_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_38	0x0066
+#define mmMP0_SMN_C2PMSG_38_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_39	0x0067
+#define mmMP0_SMN_C2PMSG_39_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_40	0x0068
+#define mmMP0_SMN_C2PMSG_40_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_41	0x0069
+#define mmMP0_SMN_C2PMSG_41_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_42	0x006a
+#define mmMP0_SMN_C2PMSG_42_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_43	0x006b
+#define mmMP0_SMN_C2PMSG_43_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_44	0x006c
+#define mmMP0_SMN_C2PMSG_44_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_45	0x006d
+#define mmMP0_SMN_C2PMSG_45_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_46	0x006e
+#define mmMP0_SMN_C2PMSG_46_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_47	0x006f
+#define mmMP0_SMN_C2PMSG_47_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_48	0x0070
+#define mmMP0_SMN_C2PMSG_48_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_49	0x0071
+#define mmMP0_SMN_C2PMSG_49_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_50	0x0072
+#define mmMP0_SMN_C2PMSG_50_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_51	0x0073
+#define mmMP0_SMN_C2PMSG_51_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_52	0x0074
+#define mmMP0_SMN_C2PMSG_52_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_53	0x0075
+#define mmMP0_SMN_C2PMSG_53_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_54	0x0076
+#define mmMP0_SMN_C2PMSG_54_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_55	0x0077
+#define mmMP0_SMN_C2PMSG_55_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_56	0x0078
+#define mmMP0_SMN_C2PMSG_56_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_57	0x0079
+#define mmMP0_SMN_C2PMSG_57_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_58	0x007a
+#define mmMP0_SMN_C2PMSG_58_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_59	0x007b
+#define mmMP0_SMN_C2PMSG_59_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_60	0x007c
+#define mmMP0_SMN_C2PMSG_60_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_61	0x007d
+#define mmMP0_SMN_C2PMSG_61_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_62	0x007e
+#define mmMP0_SMN_C2PMSG_62_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_63	0x007f
+#define mmMP0_SMN_C2PMSG_63_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_64	0x0080
+#define mmMP0_SMN_C2PMSG_64_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_65	0x0081
+#define mmMP0_SMN_C2PMSG_65_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_66	0x0082
+#define mmMP0_SMN_C2PMSG_66_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_67	0x0083
+#define mmMP0_SMN_C2PMSG_67_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_68	0x0084
+#define mmMP0_SMN_C2PMSG_68_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_69	0x0085
+#define mmMP0_SMN_C2PMSG_69_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_70	0x0086
+#define mmMP0_SMN_C2PMSG_70_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_71	0x0087
+#define mmMP0_SMN_C2PMSG_71_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_72	0x0088
+#define mmMP0_SMN_C2PMSG_72_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_73	0x0089
+#define mmMP0_SMN_C2PMSG_73_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_74	0x008a
+#define mmMP0_SMN_C2PMSG_74_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_75	0x008b
+#define mmMP0_SMN_C2PMSG_75_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_76	0x008c
+#define mmMP0_SMN_C2PMSG_76_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_77	0x008d
+#define mmMP0_SMN_C2PMSG_77_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_78	0x008e
+#define mmMP0_SMN_C2PMSG_78_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_79	0x008f
+#define mmMP0_SMN_C2PMSG_79_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_80	0x0090
+#define mmMP0_SMN_C2PMSG_80_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_81	0x0091
+#define mmMP0_SMN_C2PMSG_81_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_82	0x0092
+#define mmMP0_SMN_C2PMSG_82_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_83	0x0093
+#define mmMP0_SMN_C2PMSG_83_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_84	0x0094
+#define mmMP0_SMN_C2PMSG_84_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_85	0x0095
+#define mmMP0_SMN_C2PMSG_85_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_86	0x0096
+#define mmMP0_SMN_C2PMSG_86_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_87	0x0097
+#define mmMP0_SMN_C2PMSG_87_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_88	0x0098
+#define mmMP0_SMN_C2PMSG_88_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_89	0x0099
+#define mmMP0_SMN_C2PMSG_89_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_90	0x009a
+#define mmMP0_SMN_C2PMSG_90_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_91	0x009b
+#define mmMP0_SMN_C2PMSG_91_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_92	0x009c
+#define mmMP0_SMN_C2PMSG_92_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_93	0x009d
+#define mmMP0_SMN_C2PMSG_93_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_94	0x009e
+#define mmMP0_SMN_C2PMSG_94_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_95	0x009f
+#define mmMP0_SMN_C2PMSG_95_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_96	0x00a0
+#define mmMP0_SMN_C2PMSG_96_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_97	0x00a1
+#define mmMP0_SMN_C2PMSG_97_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_98	0x00a2
+#define mmMP0_SMN_C2PMSG_98_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_99	0x00a3
+#define mmMP0_SMN_C2PMSG_99_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_100	0x00a4
+#define mmMP0_SMN_C2PMSG_100_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_101	0x00a5
+#define mmMP0_SMN_C2PMSG_101_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_102	0x00a6
+#define mmMP0_SMN_C2PMSG_102_BASE_IDX	0
+#define mmMP0_SMN_C2PMSG_103	0x00a7
+#define mmMP0_SMN_C2PMSG_103_BASE_IDX	0
+#define mmMP0_SMN_ACTIVE_FCN_ID	0x00c0
+#define mmMP0_SMN_ACTIVE_FCN_ID_BASE_IDX	0
+#define mmMP0_SMN_IH_CREDIT	0x00c1
+#define mmMP0_SMN_IH_CREDIT_BASE_IDX	0
+#define mmMP0_SMN_IH_SW_INT	0x00c2
+#define mmMP0_SMN_IH_SW_INT_BASE_IDX	0
+#define mmMP0_SMN_IH_SW_INT_CTRL	0x00c3
+#define mmMP0_SMN_IH_SW_INT_CTRL_BASE_IDX	0
+
+
+// addressBlock: mp_SmuMp1_SmnDec
+// base address:	0x0
+#define mmMP1_SMN_ACP2MP_RESP	0x0240
+#define mmMP1_SMN_ACP2MP_RESP_BASE_IDX	0
+#define mmMP1_SMN_DC2MP_RESP	0x0241
+#define mmMP1_SMN_DC2MP_RESP_BASE_IDX	0
+#define mmMP1_SMN_UVD2MP_RESP	0x0242
+#define mmMP1_SMN_UVD2MP_RESP_BASE_IDX	0
+#define mmMP1_SMN_VCE2MP_RESP	0x0243
+#define mmMP1_SMN_VCE2MP_RESP_BASE_IDX	0
+#define mmMP1_SMN_RLC2MP_RESP	0x0244
+#define mmMP1_SMN_RLC2MP_RESP_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_32	0x0260
+#define mmMP1_SMN_C2PMSG_32_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_33	0x0261
+#define mmMP1_SMN_C2PMSG_33_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_34	0x0262
+#define mmMP1_SMN_C2PMSG_34_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_35	0x0263
+#define mmMP1_SMN_C2PMSG_35_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_36	0x0264
+#define mmMP1_SMN_C2PMSG_36_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_37	0x0265
+#define mmMP1_SMN_C2PMSG_37_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_38	0x0266
+#define mmMP1_SMN_C2PMSG_38_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_39	0x0267
+#define mmMP1_SMN_C2PMSG_39_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_40	0x0268
+#define mmMP1_SMN_C2PMSG_40_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_41	0x0269
+#define mmMP1_SMN_C2PMSG_41_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_42	0x026a
+#define mmMP1_SMN_C2PMSG_42_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_43	0x026b
+#define mmMP1_SMN_C2PMSG_43_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_44	0x026c
+#define mmMP1_SMN_C2PMSG_44_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_45	0x026d
+#define mmMP1_SMN_C2PMSG_45_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_46	0x026e
+#define mmMP1_SMN_C2PMSG_46_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_47	0x026f
+#define mmMP1_SMN_C2PMSG_47_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_48	0x0270
+#define mmMP1_SMN_C2PMSG_48_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_49	0x0271
+#define mmMP1_SMN_C2PMSG_49_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_50	0x0272
+#define mmMP1_SMN_C2PMSG_50_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_51	0x0273
+#define mmMP1_SMN_C2PMSG_51_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_52	0x0274
+#define mmMP1_SMN_C2PMSG_52_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_53	0x0275
+#define mmMP1_SMN_C2PMSG_53_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_54	0x0276
+#define mmMP1_SMN_C2PMSG_54_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_55	0x0277
+#define mmMP1_SMN_C2PMSG_55_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_56	0x0278
+#define mmMP1_SMN_C2PMSG_56_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_57	0x0279
+#define mmMP1_SMN_C2PMSG_57_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_58	0x027a
+#define mmMP1_SMN_C2PMSG_58_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_59	0x027b
+#define mmMP1_SMN_C2PMSG_59_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_60	0x027c
+#define mmMP1_SMN_C2PMSG_60_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_61	0x027d
+#define mmMP1_SMN_C2PMSG_61_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_62	0x027e
+#define mmMP1_SMN_C2PMSG_62_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_63	0x027f
+#define mmMP1_SMN_C2PMSG_63_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_64	0x0280
+#define mmMP1_SMN_C2PMSG_64_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_65	0x0281
+#define mmMP1_SMN_C2PMSG_65_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_66	0x0282
+#define mmMP1_SMN_C2PMSG_66_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_67	0x0283
+#define mmMP1_SMN_C2PMSG_67_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_68	0x0284
+#define mmMP1_SMN_C2PMSG_68_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_69	0x0285
+#define mmMP1_SMN_C2PMSG_69_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_70	0x0286
+#define mmMP1_SMN_C2PMSG_70_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_71	0x0287
+#define mmMP1_SMN_C2PMSG_71_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_72	0x0288
+#define mmMP1_SMN_C2PMSG_72_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_73	0x0289
+#define mmMP1_SMN_C2PMSG_73_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_74	0x028a
+#define mmMP1_SMN_C2PMSG_74_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_75	0x028b
+#define mmMP1_SMN_C2PMSG_75_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_76	0x028c
+#define mmMP1_SMN_C2PMSG_76_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_77	0x028d
+#define mmMP1_SMN_C2PMSG_77_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_78	0x028e
+#define mmMP1_SMN_C2PMSG_78_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_79	0x028f
+#define mmMP1_SMN_C2PMSG_79_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_80	0x0290
+#define mmMP1_SMN_C2PMSG_80_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_81	0x0291
+#define mmMP1_SMN_C2PMSG_81_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_82	0x0292
+#define mmMP1_SMN_C2PMSG_82_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_83	0x0293
+#define mmMP1_SMN_C2PMSG_83_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_84	0x0294
+#define mmMP1_SMN_C2PMSG_84_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_85	0x0295
+#define mmMP1_SMN_C2PMSG_85_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_86	0x0296
+#define mmMP1_SMN_C2PMSG_86_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_87	0x0297
+#define mmMP1_SMN_C2PMSG_87_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_88	0x0298
+#define mmMP1_SMN_C2PMSG_88_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_89	0x0299
+#define mmMP1_SMN_C2PMSG_89_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_90	0x029a
+#define mmMP1_SMN_C2PMSG_90_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_91	0x029b
+#define mmMP1_SMN_C2PMSG_91_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_92	0x029c
+#define mmMP1_SMN_C2PMSG_92_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_93	0x029d
+#define mmMP1_SMN_C2PMSG_93_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_94	0x029e
+#define mmMP1_SMN_C2PMSG_94_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_95	0x029f
+#define mmMP1_SMN_C2PMSG_95_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_96	0x02a0
+#define mmMP1_SMN_C2PMSG_96_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_97	0x02a1
+#define mmMP1_SMN_C2PMSG_97_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_98	0x02a2
+#define mmMP1_SMN_C2PMSG_98_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_99	0x02a3
+#define mmMP1_SMN_C2PMSG_99_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_100	0x02a4
+#define mmMP1_SMN_C2PMSG_100_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_101	0x02a5
+#define mmMP1_SMN_C2PMSG_101_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_102	0x02a6
+#define mmMP1_SMN_C2PMSG_102_BASE_IDX	0
+#define mmMP1_SMN_C2PMSG_103	0x02a7
+#define mmMP1_SMN_C2PMSG_103_BASE_IDX	0
+#define mmMP1_SMN_ACTIVE_FCN_ID	0x02c0
+#define mmMP1_SMN_ACTIVE_FCN_ID_BASE_IDX	0
+#define mmMP1_SMN_IH_CREDIT	0x02c1
+#define mmMP1_SMN_IH_CREDIT_BASE_IDX	0
+#define mmMP1_SMN_IH_SW_INT	0x02c2
+#define mmMP1_SMN_IH_SW_INT_BASE_IDX	0
+#define mmMP1_SMN_IH_SW_INT_CTRL	0x02c3
+#define mmMP1_SMN_IH_SW_INT_CTRL_BASE_IDX	0
+#define mmMP1_SMN_FPS_CNT	0x02c4
+#define mmMP1_SMN_FPS_CNT_BASE_IDX	0
+#define mmMP1_SMN_EXT_SCRATCH0	0x03c0
+#define mmMP1_SMN_EXT_SCRATCH0_BASE_IDX	0
+#define mmMP1_SMN_EXT_SCRATCH1	0x03c1
+#define mmMP1_SMN_EXT_SCRATCH1_BASE_IDX	0
+#define mmMP1_SMN_EXT_SCRATCH2	0x03c2
+#define mmMP1_SMN_EXT_SCRATCH2_BASE_IDX	0
+#define mmMP1_SMN_EXT_SCRATCH3	0x03c3
+#define mmMP1_SMN_EXT_SCRATCH3_BASE_IDX	0
+#define mmMP1_SMN_EXT_SCRATCH4	0x03c4
+#define mmMP1_SMN_EXT_SCRATCH4_BASE_IDX	0
+#define mmMP1_SMN_EXT_SCRATCH5	0x03c5
+#define mmMP1_SMN_EXT_SCRATCH5_BASE_IDX	0
+#define mmMP1_SMN_EXT_SCRATCH6	0x03c6
+#define mmMP1_SMN_EXT_SCRATCH6_BASE_IDX	0
+#define mmMP1_SMN_EXT_SCRATCH7	0x03c7
+#define mmMP1_SMN_EXT_SCRATCH7_BASE_IDX	0
+#define mmMP1_SMN_EXT_SCRATCH8	0x03c8
+#define mmMP1_SMN_EXT_SCRATCH8_BASE_IDX	0
+
+
+// addressBlock: mp_SmuMp1Pub_CruDec
+// base address:	0x0
+#define mmMP1_SMN_PUB_CTRL	0x02c5
+#define mmMP1_SMN_PUB_CTRL_BASE_IDX	0
+
+
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_9_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_9_0_sh_mask.h
new file mode 100644
index 000000000000..d5a623deca77
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_9_0_sh_mask.h
@@ -0,0 +1,1463 @@
+/*
+ * Copyright (C) 2017  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _mp_9_0_SH_MASK_HEADER
+#define _mp_9_0_SH_MASK_HEADER
+
+
+// addressBlock: mp_SmuMp0_SmnDec
+//MP0_SMN_C2PMSG_32
+#define MP0_SMN_C2PMSG_32__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_32__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_33
+#define MP0_SMN_C2PMSG_33__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_33__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_34
+#define MP0_SMN_C2PMSG_34__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_34__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_35
+#define MP0_SMN_C2PMSG_35__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_35__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_36
+#define MP0_SMN_C2PMSG_36__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_36__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_37
+#define MP0_SMN_C2PMSG_37__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_37__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_38
+#define MP0_SMN_C2PMSG_38__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_38__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_39
+#define MP0_SMN_C2PMSG_39__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_39__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_40
+#define MP0_SMN_C2PMSG_40__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_40__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_41
+#define MP0_SMN_C2PMSG_41__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_41__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_42
+#define MP0_SMN_C2PMSG_42__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_42__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_43
+#define MP0_SMN_C2PMSG_43__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_43__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_44
+#define MP0_SMN_C2PMSG_44__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_44__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_45
+#define MP0_SMN_C2PMSG_45__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_45__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_46
+#define MP0_SMN_C2PMSG_46__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_46__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_47
+#define MP0_SMN_C2PMSG_47__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_47__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_48
+#define MP0_SMN_C2PMSG_48__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_48__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_49
+#define MP0_SMN_C2PMSG_49__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_49__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_50
+#define MP0_SMN_C2PMSG_50__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_50__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_51
+#define MP0_SMN_C2PMSG_51__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_51__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_52
+#define MP0_SMN_C2PMSG_52__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_52__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_53
+#define MP0_SMN_C2PMSG_53__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_53__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_54
+#define MP0_SMN_C2PMSG_54__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_54__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_55
+#define MP0_SMN_C2PMSG_55__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_55__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_56
+#define MP0_SMN_C2PMSG_56__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_56__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_57
+#define MP0_SMN_C2PMSG_57__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_57__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_58
+#define MP0_SMN_C2PMSG_58__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_58__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_59
+#define MP0_SMN_C2PMSG_59__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_59__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_60
+#define MP0_SMN_C2PMSG_60__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_60__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_61
+#define MP0_SMN_C2PMSG_61__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_61__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_62
+#define MP0_SMN_C2PMSG_62__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_62__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_63
+#define MP0_SMN_C2PMSG_63__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_63__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_64
+#define MP0_SMN_C2PMSG_64__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_64__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_65
+#define MP0_SMN_C2PMSG_65__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_65__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_66
+#define MP0_SMN_C2PMSG_66__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_66__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_67
+#define MP0_SMN_C2PMSG_67__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_67__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_68
+#define MP0_SMN_C2PMSG_68__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_68__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_69
+#define MP0_SMN_C2PMSG_69__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_69__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_70
+#define MP0_SMN_C2PMSG_70__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_70__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_71
+#define MP0_SMN_C2PMSG_71__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_71__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_72
+#define MP0_SMN_C2PMSG_72__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_72__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_73
+#define MP0_SMN_C2PMSG_73__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_73__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_74
+#define MP0_SMN_C2PMSG_74__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_74__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_75
+#define MP0_SMN_C2PMSG_75__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_75__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_76
+#define MP0_SMN_C2PMSG_76__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_76__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_77
+#define MP0_SMN_C2PMSG_77__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_77__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_78
+#define MP0_SMN_C2PMSG_78__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_78__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_79
+#define MP0_SMN_C2PMSG_79__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_79__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_80
+#define MP0_SMN_C2PMSG_80__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_80__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_81
+#define MP0_SMN_C2PMSG_81__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_81__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_82
+#define MP0_SMN_C2PMSG_82__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_82__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_83
+#define MP0_SMN_C2PMSG_83__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_83__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_84
+#define MP0_SMN_C2PMSG_84__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_84__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_85
+#define MP0_SMN_C2PMSG_85__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_85__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_86
+#define MP0_SMN_C2PMSG_86__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_86__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_87
+#define MP0_SMN_C2PMSG_87__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_87__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_88
+#define MP0_SMN_C2PMSG_88__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_88__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_89
+#define MP0_SMN_C2PMSG_89__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_89__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_90
+#define MP0_SMN_C2PMSG_90__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_90__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_91
+#define MP0_SMN_C2PMSG_91__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_91__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_92
+#define MP0_SMN_C2PMSG_92__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_92__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_93
+#define MP0_SMN_C2PMSG_93__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_93__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_94
+#define MP0_SMN_C2PMSG_94__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_94__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_95
+#define MP0_SMN_C2PMSG_95__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_95__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_96
+#define MP0_SMN_C2PMSG_96__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_96__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_97
+#define MP0_SMN_C2PMSG_97__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_97__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_98
+#define MP0_SMN_C2PMSG_98__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_98__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_99
+#define MP0_SMN_C2PMSG_99__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_99__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_100
+#define MP0_SMN_C2PMSG_100__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_100__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_101
+#define MP0_SMN_C2PMSG_101__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_101__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_102
+#define MP0_SMN_C2PMSG_102__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_102__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_C2PMSG_103
+#define MP0_SMN_C2PMSG_103__CONTENT__SHIFT	0x0
+#define MP0_SMN_C2PMSG_103__CONTENT_MASK	0xFFFFFFFFL
+//MP0_SMN_ACTIVE_FCN_ID
+#define MP0_SMN_ACTIVE_FCN_ID__VFID__SHIFT	0x0
+#define MP0_SMN_ACTIVE_FCN_ID__VF__SHIFT	0x1f
+#define MP0_SMN_ACTIVE_FCN_ID__VFID_MASK	0x0000000FL
+#define MP0_SMN_ACTIVE_FCN_ID__VF_MASK	0x80000000L
+//MP0_SMN_IH_CREDIT
+#define MP0_SMN_IH_CREDIT__CREDIT_VALUE__SHIFT	0x0
+#define MP0_SMN_IH_CREDIT__CLIENT_ID__SHIFT	0x10
+#define MP0_SMN_IH_CREDIT__CREDIT_VALUE_MASK	0x00000003L
+#define MP0_SMN_IH_CREDIT__CLIENT_ID_MASK	0x00FF0000L
+//MP0_SMN_IH_SW_INT
+#define MP0_SMN_IH_SW_INT__VALID__SHIFT	0x0
+#define MP0_SMN_IH_SW_INT__ID__SHIFT	0x1
+#define MP0_SMN_IH_SW_INT__VALID_MASK	0x00000001L
+#define MP0_SMN_IH_SW_INT__ID_MASK	0x000001FEL
+//MP0_SMN_IH_SW_INT_CTRL
+#define MP0_SMN_IH_SW_INT_CTRL__SW_TRIG_MASK__SHIFT	0x0
+#define MP0_SMN_IH_SW_INT_CTRL__SW_INT_ACK__SHIFT	0x8
+#define MP0_SMN_IH_SW_INT_CTRL__SW_TRIG_MASK_MASK	0x00000001L
+#define MP0_SMN_IH_SW_INT_CTRL__SW_INT_ACK_MASK	0x00000100L
+
+
+// addressBlock: mp_SmuMp1_SmnDec
+//MP1_SMN_ACP2MP_RESP
+#define MP1_SMN_ACP2MP_RESP__CONTENT__SHIFT	0x0
+#define MP1_SMN_ACP2MP_RESP__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_DC2MP_RESP
+#define MP1_SMN_DC2MP_RESP__CONTENT__SHIFT	0x0
+#define MP1_SMN_DC2MP_RESP__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_UVD2MP_RESP
+#define MP1_SMN_UVD2MP_RESP__CONTENT__SHIFT	0x0
+#define MP1_SMN_UVD2MP_RESP__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_VCE2MP_RESP
+#define MP1_SMN_VCE2MP_RESP__CONTENT__SHIFT	0x0
+#define MP1_SMN_VCE2MP_RESP__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_RLC2MP_RESP
+#define MP1_SMN_RLC2MP_RESP__CONTENT__SHIFT	0x0
+#define MP1_SMN_RLC2MP_RESP__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_32
+#define MP1_SMN_C2PMSG_32__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_32__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_33
+#define MP1_SMN_C2PMSG_33__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_33__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_34
+#define MP1_SMN_C2PMSG_34__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_34__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_35
+#define MP1_SMN_C2PMSG_35__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_35__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_36
+#define MP1_SMN_C2PMSG_36__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_36__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_37
+#define MP1_SMN_C2PMSG_37__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_37__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_38
+#define MP1_SMN_C2PMSG_38__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_38__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_39
+#define MP1_SMN_C2PMSG_39__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_39__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_40
+#define MP1_SMN_C2PMSG_40__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_40__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_41
+#define MP1_SMN_C2PMSG_41__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_41__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_42
+#define MP1_SMN_C2PMSG_42__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_42__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_43
+#define MP1_SMN_C2PMSG_43__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_43__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_44
+#define MP1_SMN_C2PMSG_44__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_44__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_45
+#define MP1_SMN_C2PMSG_45__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_45__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_46
+#define MP1_SMN_C2PMSG_46__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_46__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_47
+#define MP1_SMN_C2PMSG_47__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_47__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_48
+#define MP1_SMN_C2PMSG_48__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_48__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_49
+#define MP1_SMN_C2PMSG_49__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_49__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_50
+#define MP1_SMN_C2PMSG_50__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_50__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_51
+#define MP1_SMN_C2PMSG_51__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_51__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_52
+#define MP1_SMN_C2PMSG_52__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_52__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_53
+#define MP1_SMN_C2PMSG_53__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_53__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_54
+#define MP1_SMN_C2PMSG_54__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_54__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_55
+#define MP1_SMN_C2PMSG_55__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_55__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_56
+#define MP1_SMN_C2PMSG_56__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_56__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_57
+#define MP1_SMN_C2PMSG_57__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_57__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_58
+#define MP1_SMN_C2PMSG_58__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_58__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_59
+#define MP1_SMN_C2PMSG_59__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_59__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_60
+#define MP1_SMN_C2PMSG_60__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_60__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_61
+#define MP1_SMN_C2PMSG_61__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_61__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_62
+#define MP1_SMN_C2PMSG_62__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_62__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_63
+#define MP1_SMN_C2PMSG_63__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_63__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_64
+#define MP1_SMN_C2PMSG_64__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_64__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_65
+#define MP1_SMN_C2PMSG_65__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_65__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_66
+#define MP1_SMN_C2PMSG_66__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_66__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_67
+#define MP1_SMN_C2PMSG_67__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_67__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_68
+#define MP1_SMN_C2PMSG_68__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_68__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_69
+#define MP1_SMN_C2PMSG_69__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_69__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_70
+#define MP1_SMN_C2PMSG_70__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_70__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_71
+#define MP1_SMN_C2PMSG_71__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_71__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_72
+#define MP1_SMN_C2PMSG_72__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_72__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_73
+#define MP1_SMN_C2PMSG_73__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_73__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_74
+#define MP1_SMN_C2PMSG_74__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_74__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_75
+#define MP1_SMN_C2PMSG_75__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_75__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_76
+#define MP1_SMN_C2PMSG_76__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_76__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_77
+#define MP1_SMN_C2PMSG_77__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_77__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_78
+#define MP1_SMN_C2PMSG_78__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_78__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_79
+#define MP1_SMN_C2PMSG_79__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_79__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_80
+#define MP1_SMN_C2PMSG_80__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_80__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_81
+#define MP1_SMN_C2PMSG_81__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_81__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_82
+#define MP1_SMN_C2PMSG_82__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_82__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_83
+#define MP1_SMN_C2PMSG_83__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_83__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_84
+#define MP1_SMN_C2PMSG_84__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_84__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_85
+#define MP1_SMN_C2PMSG_85__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_85__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_86
+#define MP1_SMN_C2PMSG_86__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_86__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_87
+#define MP1_SMN_C2PMSG_87__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_87__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_88
+#define MP1_SMN_C2PMSG_88__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_88__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_89
+#define MP1_SMN_C2PMSG_89__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_89__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_90
+#define MP1_SMN_C2PMSG_90__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_90__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_91
+#define MP1_SMN_C2PMSG_91__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_91__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_92
+#define MP1_SMN_C2PMSG_92__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_92__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_93
+#define MP1_SMN_C2PMSG_93__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_93__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_94
+#define MP1_SMN_C2PMSG_94__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_94__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_95
+#define MP1_SMN_C2PMSG_95__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_95__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_96
+#define MP1_SMN_C2PMSG_96__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_96__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_97
+#define MP1_SMN_C2PMSG_97__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_97__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_98
+#define MP1_SMN_C2PMSG_98__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_98__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_99
+#define MP1_SMN_C2PMSG_99__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_99__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_100
+#define MP1_SMN_C2PMSG_100__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_100__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_101
+#define MP1_SMN_C2PMSG_101__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_101__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_102
+#define MP1_SMN_C2PMSG_102__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_102__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_C2PMSG_103
+#define MP1_SMN_C2PMSG_103__CONTENT__SHIFT	0x0
+#define MP1_SMN_C2PMSG_103__CONTENT_MASK	0xFFFFFFFFL
+//MP1_SMN_ACTIVE_FCN_ID
+#define MP1_SMN_ACTIVE_FCN_ID__VFID__SHIFT	0x0
+#define MP1_SMN_ACTIVE_FCN_ID__VF__SHIFT	0x1f
+#define MP1_SMN_ACTIVE_FCN_ID__VFID_MASK	0x0000000FL
+#define MP1_SMN_ACTIVE_FCN_ID__VF_MASK	0x80000000L
+//MP1_SMN_IH_CREDIT
+#define MP1_SMN_IH_CREDIT__CREDIT_VALUE__SHIFT	0x0
+#define MP1_SMN_IH_CREDIT__CLIENT_ID__SHIFT	0x10
+#define MP1_SMN_IH_CREDIT__CREDIT_VALUE_MASK	0x00000003L
+#define MP1_SMN_IH_CREDIT__CLIENT_ID_MASK	0x00FF0000L
+//MP1_SMN_IH_SW_INT
+#define MP1_SMN_IH_SW_INT__VALID__SHIFT	0x0
+#define MP1_SMN_IH_SW_INT__ID__SHIFT	0x1
+#define MP1_SMN_IH_SW_INT__VALID_MASK	0x00000001L
+#define MP1_SMN_IH_SW_INT__ID_MASK	0x000001FEL
+//MP1_SMN_IH_SW_INT_CTRL
+#define MP1_SMN_IH_SW_INT_CTRL__SW_TRIG_MASK__SHIFT	0x0
+#define MP1_SMN_IH_SW_INT_CTRL__SW_INT_ACK__SHIFT	0x8
+#define MP1_SMN_IH_SW_INT_CTRL__SW_TRIG_MASK_MASK	0x00000001L
+#define MP1_SMN_IH_SW_INT_CTRL__SW_INT_ACK_MASK	0x00000100L
+//MP1_SMN_FPS_CNT
+#define MP1_SMN_FPS_CNT__COUNT__SHIFT	0x0
+#define MP1_SMN_FPS_CNT__COUNT_MASK	0xFFFFFFFFL
+//MP1_SMN_EXT_SCRATCH0
+#define MP1_SMN_EXT_SCRATCH0__DATA__SHIFT	0x0
+#define MP1_SMN_EXT_SCRATCH0__DATA_MASK	0xFFFFFFFFL
+//MP1_SMN_EXT_SCRATCH1
+#define MP1_SMN_EXT_SCRATCH1__DATA__SHIFT	0x0
+#define MP1_SMN_EXT_SCRATCH1__DATA_MASK	0xFFFFFFFFL
+//MP1_SMN_EXT_SCRATCH2
+#define MP1_SMN_EXT_SCRATCH2__DATA__SHIFT	0x0
+#define MP1_SMN_EXT_SCRATCH2__DATA_MASK	0xFFFFFFFFL
+//MP1_SMN_EXT_SCRATCH3
+#define MP1_SMN_EXT_SCRATCH3__DATA__SHIFT	0x0
+#define MP1_SMN_EXT_SCRATCH3__DATA_MASK	0xFFFFFFFFL
+//MP1_SMN_EXT_SCRATCH4
+#define MP1_SMN_EXT_SCRATCH4__DATA__SHIFT	0x0
+#define MP1_SMN_EXT_SCRATCH4__DATA_MASK	0xFFFFFFFFL
+//MP1_SMN_EXT_SCRATCH5
+#define MP1_SMN_EXT_SCRATCH5__DATA__SHIFT	0x0
+#define MP1_SMN_EXT_SCRATCH5__DATA_MASK	0xFFFFFFFFL
+//MP1_SMN_EXT_SCRATCH6
+#define MP1_SMN_EXT_SCRATCH6__DATA__SHIFT	0x0
+#define MP1_SMN_EXT_SCRATCH6__DATA_MASK	0xFFFFFFFFL
+//MP1_SMN_EXT_SCRATCH7
+#define MP1_SMN_EXT_SCRATCH7__DATA__SHIFT	0x0
+#define MP1_SMN_EXT_SCRATCH7__DATA_MASK	0xFFFFFFFFL
+//MP1_SMN_EXT_SCRATCH8
+#define MP1_SMN_EXT_SCRATCH8__DATA__SHIFT	0x0
+#define MP1_SMN_EXT_SCRATCH8__DATA_MASK	0xFFFFFFFFL
+
+
+
+
+// addressBlock: mp_SmuMp0Pub_CruDec
+//MP0_SOC_INFO
+#define MP0_SOC_INFO__SOC_DIE_ID__SHIFT	0x0
+#define MP0_SOC_INFO__SOC_PKG_TYPE__SHIFT	0x2
+#define MP0_SOC_INFO__SOC_DIE_ID_MASK	0x00000003L
+#define MP0_SOC_INFO__SOC_PKG_TYPE_MASK	0x0000001CL
+//MP0_PUB_SCRATCH0
+#define MP0_PUB_SCRATCH0__DATA__SHIFT	0x0
+#define MP0_PUB_SCRATCH0__DATA_MASK	0xFFFFFFFFL
+//MP0_PUB_SCRATCH1
+#define MP0_PUB_SCRATCH1__DATA__SHIFT	0x0
+#define MP0_PUB_SCRATCH1__DATA_MASK	0xFFFFFFFFL
+//MP0_PUB_SCRATCH2
+#define MP0_PUB_SCRATCH2__DATA__SHIFT	0x0
+#define MP0_PUB_SCRATCH2__DATA_MASK	0xFFFFFFFFL
+//MP0_PUB_SCRATCH3
+#define MP0_PUB_SCRATCH3__DATA__SHIFT	0x0
+#define MP0_PUB_SCRATCH3__DATA_MASK	0xFFFFFFFFL
+//MP0_FW_INTF
+#define MP0_FW_INTF__SS_SECURE__SHIFT	0x13
+#define MP0_FW_INTF__SS_SECURE_MASK	0x00080000L
+//MP0_C2PMSG_0
+#define MP0_C2PMSG_0__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_0__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_1
+#define MP0_C2PMSG_1__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_1__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_2
+#define MP0_C2PMSG_2__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_2__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_3
+#define MP0_C2PMSG_3__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_3__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_4
+#define MP0_C2PMSG_4__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_4__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_5
+#define MP0_C2PMSG_5__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_5__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_6
+#define MP0_C2PMSG_6__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_6__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_7
+#define MP0_C2PMSG_7__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_7__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_8
+#define MP0_C2PMSG_8__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_8__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_9
+#define MP0_C2PMSG_9__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_9__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_10
+#define MP0_C2PMSG_10__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_10__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_11
+#define MP0_C2PMSG_11__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_11__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_12
+#define MP0_C2PMSG_12__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_12__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_13
+#define MP0_C2PMSG_13__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_13__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_14
+#define MP0_C2PMSG_14__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_14__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_15
+#define MP0_C2PMSG_15__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_15__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_16
+#define MP0_C2PMSG_16__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_16__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_17
+#define MP0_C2PMSG_17__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_17__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_18
+#define MP0_C2PMSG_18__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_18__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_19
+#define MP0_C2PMSG_19__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_19__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_20
+#define MP0_C2PMSG_20__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_20__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_21
+#define MP0_C2PMSG_21__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_21__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_22
+#define MP0_C2PMSG_22__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_22__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_23
+#define MP0_C2PMSG_23__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_23__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_24
+#define MP0_C2PMSG_24__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_24__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_25
+#define MP0_C2PMSG_25__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_25__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_26
+#define MP0_C2PMSG_26__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_26__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_27
+#define MP0_C2PMSG_27__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_27__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_28
+#define MP0_C2PMSG_28__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_28__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_29
+#define MP0_C2PMSG_29__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_29__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_30
+#define MP0_C2PMSG_30__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_30__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_31
+#define MP0_C2PMSG_31__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_31__CONTENT_MASK	0xFFFFFFFFL
+//MP0_P2CMSG_0
+#define MP0_P2CMSG_0__CONTENT__SHIFT	0x0
+#define MP0_P2CMSG_0__CONTENT_MASK	0xFFFFFFFFL
+//MP0_P2CMSG_1
+#define MP0_P2CMSG_1__CONTENT__SHIFT	0x0
+#define MP0_P2CMSG_1__CONTENT_MASK	0xFFFFFFFFL
+//MP0_P2CMSG_2
+#define MP0_P2CMSG_2__CONTENT__SHIFT	0x0
+#define MP0_P2CMSG_2__CONTENT_MASK	0xFFFFFFFFL
+//MP0_P2CMSG_3
+#define MP0_P2CMSG_3__CONTENT__SHIFT	0x0
+#define MP0_P2CMSG_3__CONTENT_MASK	0xFFFFFFFFL
+//MP0_P2CMSG_INTEN
+#define MP0_P2CMSG_INTEN__INTEN__SHIFT	0x0
+#define MP0_P2CMSG_INTEN__INTEN_MASK	0x0000000FL
+//MP0_P2CMSG_INTSTS
+#define MP0_P2CMSG_INTSTS__INTSTS0__SHIFT	0x0
+#define MP0_P2CMSG_INTSTS__INTSTS1__SHIFT	0x1
+#define MP0_P2CMSG_INTSTS__INTSTS2__SHIFT	0x2
+#define MP0_P2CMSG_INTSTS__INTSTS3__SHIFT	0x3
+#define MP0_P2CMSG_INTSTS__INTSTS0_MASK	0x00000001L
+#define MP0_P2CMSG_INTSTS__INTSTS1_MASK	0x00000002L
+#define MP0_P2CMSG_INTSTS__INTSTS2_MASK	0x00000004L
+#define MP0_P2CMSG_INTSTS__INTSTS3_MASK	0x00000008L
+//MP0_C2PMSG_ATTR_0
+#define MP0_C2PMSG_ATTR_0__MSG_ATTR__SHIFT	0x0
+#define MP0_C2PMSG_ATTR_0__MSG_ATTR_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_ATTR_1
+#define MP0_C2PMSG_ATTR_1__MSG_ATTR__SHIFT	0x0
+#define MP0_C2PMSG_ATTR_1__MSG_ATTR_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_ATTR_2
+#define MP0_C2PMSG_ATTR_2__MSG_ATTR__SHIFT	0x0
+#define MP0_C2PMSG_ATTR_2__MSG_ATTR_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_ATTR_3
+#define MP0_C2PMSG_ATTR_3__MSG_ATTR__SHIFT	0x0
+#define MP0_C2PMSG_ATTR_3__MSG_ATTR_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_ATTR_4
+#define MP0_C2PMSG_ATTR_4__MSG_ATTR__SHIFT	0x0
+#define MP0_C2PMSG_ATTR_4__MSG_ATTR_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_ATTR_5
+#define MP0_C2PMSG_ATTR_5__MSG_ATTR__SHIFT	0x0
+#define MP0_C2PMSG_ATTR_5__MSG_ATTR_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_ATTR_6
+#define MP0_C2PMSG_ATTR_6__MSG_ATTR__SHIFT	0x0
+#define MP0_C2PMSG_ATTR_6__MSG_ATTR_MASK	0x0000FFFFL
+//MP0_P2CMSG_ATTR
+#define MP0_P2CMSG_ATTR__MSG_ATTR__SHIFT	0x0
+#define MP0_P2CMSG_ATTR__MSG_ATTR_MASK	0x000000FFL
+//MP0_P2SMSG_0
+#define MP0_P2SMSG_0__CONTENT__SHIFT	0x0
+#define MP0_P2SMSG_0__CONTENT_MASK	0xFFFFFFFFL
+//MP0_P2SMSG_1
+#define MP0_P2SMSG_1__CONTENT__SHIFT	0x0
+#define MP0_P2SMSG_1__CONTENT_MASK	0xFFFFFFFFL
+//MP0_P2SMSG_2
+#define MP0_P2SMSG_2__CONTENT__SHIFT	0x0
+#define MP0_P2SMSG_2__CONTENT_MASK	0xFFFFFFFFL
+//MP0_P2SMSG_3
+#define MP0_P2SMSG_3__CONTENT__SHIFT	0x0
+#define MP0_P2SMSG_3__CONTENT_MASK	0xFFFFFFFFL
+//MP0_P2SMSG_ATTR
+#define MP0_P2SMSG_ATTR__MSG_ATTR__SHIFT	0x0
+#define MP0_P2SMSG_ATTR__MSG_ATTR_MASK	0x000000FFL
+//MP0_S2PMSG_ATTR
+#define MP0_S2PMSG_ATTR__MSG_ATTR__SHIFT	0x0
+#define MP0_S2PMSG_ATTR__MSG_ATTR_MASK	0x00000003L
+//MP0_P2SMSG_INTSTS
+#define MP0_P2SMSG_INTSTS__INTSTS0__SHIFT	0x0
+#define MP0_P2SMSG_INTSTS__INTSTS1__SHIFT	0x1
+#define MP0_P2SMSG_INTSTS__INTSTS2__SHIFT	0x2
+#define MP0_P2SMSG_INTSTS__INTSTS3__SHIFT	0x3
+#define MP0_P2SMSG_INTSTS__INTSTS0_MASK	0x00000001L
+#define MP0_P2SMSG_INTSTS__INTSTS1_MASK	0x00000002L
+#define MP0_P2SMSG_INTSTS__INTSTS2_MASK	0x00000004L
+#define MP0_P2SMSG_INTSTS__INTSTS3_MASK	0x00000008L
+//MP0_S2PMSG_0
+#define MP0_S2PMSG_0__CONTENT__SHIFT	0x0
+#define MP0_S2PMSG_0__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_32
+#define MP0_C2PMSG_32__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_32__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_33
+#define MP0_C2PMSG_33__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_33__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_34
+#define MP0_C2PMSG_34__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_34__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_35
+#define MP0_C2PMSG_35__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_35__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_36
+#define MP0_C2PMSG_36__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_36__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_37
+#define MP0_C2PMSG_37__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_37__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_38
+#define MP0_C2PMSG_38__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_38__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_39
+#define MP0_C2PMSG_39__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_39__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_40
+#define MP0_C2PMSG_40__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_40__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_41
+#define MP0_C2PMSG_41__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_41__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_42
+#define MP0_C2PMSG_42__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_42__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_43
+#define MP0_C2PMSG_43__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_43__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_44
+#define MP0_C2PMSG_44__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_44__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_45
+#define MP0_C2PMSG_45__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_45__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_46
+#define MP0_C2PMSG_46__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_46__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_47
+#define MP0_C2PMSG_47__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_47__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_48
+#define MP0_C2PMSG_48__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_48__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_49
+#define MP0_C2PMSG_49__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_49__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_50
+#define MP0_C2PMSG_50__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_50__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_51
+#define MP0_C2PMSG_51__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_51__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_52
+#define MP0_C2PMSG_52__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_52__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_53
+#define MP0_C2PMSG_53__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_53__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_54
+#define MP0_C2PMSG_54__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_54__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_55
+#define MP0_C2PMSG_55__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_55__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_56
+#define MP0_C2PMSG_56__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_56__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_57
+#define MP0_C2PMSG_57__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_57__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_58
+#define MP0_C2PMSG_58__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_58__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_59
+#define MP0_C2PMSG_59__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_59__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_60
+#define MP0_C2PMSG_60__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_60__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_61
+#define MP0_C2PMSG_61__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_61__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_62
+#define MP0_C2PMSG_62__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_62__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_63
+#define MP0_C2PMSG_63__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_63__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_64
+#define MP0_C2PMSG_64__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_64__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_65
+#define MP0_C2PMSG_65__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_65__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_66
+#define MP0_C2PMSG_66__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_66__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_67
+#define MP0_C2PMSG_67__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_67__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_68
+#define MP0_C2PMSG_68__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_68__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_69
+#define MP0_C2PMSG_69__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_69__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_70
+#define MP0_C2PMSG_70__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_70__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_71
+#define MP0_C2PMSG_71__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_71__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_72
+#define MP0_C2PMSG_72__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_72__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_73
+#define MP0_C2PMSG_73__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_73__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_74
+#define MP0_C2PMSG_74__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_74__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_75
+#define MP0_C2PMSG_75__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_75__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_76
+#define MP0_C2PMSG_76__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_76__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_77
+#define MP0_C2PMSG_77__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_77__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_78
+#define MP0_C2PMSG_78__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_78__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_79
+#define MP0_C2PMSG_79__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_79__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_80
+#define MP0_C2PMSG_80__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_80__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_81
+#define MP0_C2PMSG_81__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_81__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_82
+#define MP0_C2PMSG_82__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_82__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_83
+#define MP0_C2PMSG_83__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_83__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_84
+#define MP0_C2PMSG_84__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_84__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_85
+#define MP0_C2PMSG_85__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_85__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_86
+#define MP0_C2PMSG_86__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_86__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_87
+#define MP0_C2PMSG_87__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_87__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_88
+#define MP0_C2PMSG_88__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_88__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_89
+#define MP0_C2PMSG_89__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_89__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_90
+#define MP0_C2PMSG_90__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_90__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_91
+#define MP0_C2PMSG_91__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_91__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_92
+#define MP0_C2PMSG_92__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_92__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_93
+#define MP0_C2PMSG_93__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_93__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_94
+#define MP0_C2PMSG_94__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_94__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_95
+#define MP0_C2PMSG_95__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_95__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_96
+#define MP0_C2PMSG_96__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_96__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_97
+#define MP0_C2PMSG_97__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_97__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_98
+#define MP0_C2PMSG_98__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_98__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_99
+#define MP0_C2PMSG_99__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_99__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_100
+#define MP0_C2PMSG_100__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_100__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_101
+#define MP0_C2PMSG_101__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_101__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_102
+#define MP0_C2PMSG_102__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_102__CONTENT_MASK	0xFFFFFFFFL
+//MP0_C2PMSG_103
+#define MP0_C2PMSG_103__CONTENT__SHIFT	0x0
+#define MP0_C2PMSG_103__CONTENT_MASK	0xFFFFFFFFL
+//MP0_ACTIVE_FCN_ID
+#define MP0_ACTIVE_FCN_ID__VFID__SHIFT	0x0
+#define MP0_ACTIVE_FCN_ID__VF__SHIFT	0x1f
+#define MP0_ACTIVE_FCN_ID__VFID_MASK	0x0000000FL
+#define MP0_ACTIVE_FCN_ID__VF_MASK	0x80000000L
+//MP0_IH_CREDIT
+#define MP0_IH_CREDIT__CREDIT_VALUE__SHIFT	0x0
+#define MP0_IH_CREDIT__CLIENT_ID__SHIFT	0x10
+#define MP0_IH_CREDIT__CREDIT_VALUE_MASK	0x00000003L
+#define MP0_IH_CREDIT__CLIENT_ID_MASK	0x00FF0000L
+//MP0_IH_SW_INT
+#define MP0_IH_SW_INT__ID__SHIFT	0x0
+#define MP0_IH_SW_INT__VALID__SHIFT	0x8
+#define MP0_IH_SW_INT__ID_MASK	0x000000FFL
+#define MP0_IH_SW_INT__VALID_MASK	0x00000100L
+//MP0_IH_SW_INT_CTRL
+#define MP0_IH_SW_INT_CTRL__INT_MASK__SHIFT	0x0
+#define MP0_IH_SW_INT_CTRL__INT_ACK__SHIFT	0x8
+#define MP0_IH_SW_INT_CTRL__INT_MASK_MASK	0x00000001L
+#define MP0_IH_SW_INT_CTRL__INT_ACK_MASK	0x00000100L
+
+
+//CGTT_DRM_CLK_CTRL0
+#define CGTT_DRM_CLK_CTRL0__ON_DELAY__SHIFT	0x0
+#define CGTT_DRM_CLK_CTRL0__OFF_HYSTERESIS__SHIFT	0x4
+#define CGTT_DRM_CLK_CTRL0__DIV_ID__SHIFT	0xc
+#define CGTT_DRM_CLK_CTRL0__RAMP_DIS_CLK_0__SHIFT	0x15
+#define CGTT_DRM_CLK_CTRL0__RAMP_DIS_CLK_REG__SHIFT	0x16
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE7__SHIFT	0x18
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE6__SHIFT	0x19
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE5__SHIFT	0x1a
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE4__SHIFT	0x1b
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE3__SHIFT	0x1c
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE2__SHIFT	0x1d
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE1__SHIFT	0x1e
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE0__SHIFT	0x1f
+#define CGTT_DRM_CLK_CTRL0__ON_DELAY_MASK	0x0000000FL
+#define CGTT_DRM_CLK_CTRL0__OFF_HYSTERESIS_MASK	0x00000FF0L
+#define CGTT_DRM_CLK_CTRL0__DIV_ID_MASK	0x00007000L
+#define CGTT_DRM_CLK_CTRL0__RAMP_DIS_CLK_0_MASK	0x00200000L
+#define CGTT_DRM_CLK_CTRL0__RAMP_DIS_CLK_REG_MASK	0x00400000L
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE7_MASK	0x01000000L
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE6_MASK	0x02000000L
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE5_MASK	0x04000000L
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE4_MASK	0x08000000L
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE3_MASK	0x10000000L
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE2_MASK	0x20000000L
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE1_MASK	0x40000000L
+#define CGTT_DRM_CLK_CTRL0__SOFT_OVERRIDE0_MASK	0x80000000L
+//DRM_LIGHT_SLEEP_CTRL
+#define DRM_LIGHT_SLEEP_CTRL__MEM_LIGHT_SLEEP_EN__SHIFT	0x0
+#define DRM_LIGHT_SLEEP_CTRL__MEM_LIGHT_SLEEP_EN_MASK	0x00000001L
+
+
+// addressBlock: mp_SmuMp1Pub_CruDec
+//MP1_SMN_PUB_CTRL
+#define MP1_SMN_PUB_CTRL__RESET__SHIFT	0x0
+#define MP1_SMN_PUB_CTRL__RESET_MASK	0x00000001L
+//MP1_FIRMWARE_FLAGS
+#define MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT	0x0
+#define MP1_FIRMWARE_FLAGS__RESERVED__SHIFT	0x1
+#define MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK	0x00000001L
+#define MP1_FIRMWARE_FLAGS__RESERVED_MASK	0xFFFFFFFEL
+//MP1_PUB_SCRATCH0
+#define MP1_PUB_SCRATCH0__DATA__SHIFT	0x0
+#define MP1_PUB_SCRATCH0__DATA_MASK	0xFFFFFFFFL
+//MP1_PUB_SCRATCH1
+#define MP1_PUB_SCRATCH1__DATA__SHIFT	0x0
+#define MP1_PUB_SCRATCH1__DATA_MASK	0xFFFFFFFFL
+//MP1_PUB_SCRATCH2
+#define MP1_PUB_SCRATCH2__DATA__SHIFT	0x0
+#define MP1_PUB_SCRATCH2__DATA_MASK	0xFFFFFFFFL
+//MP1_PUB_SCRATCH3
+#define MP1_PUB_SCRATCH3__DATA__SHIFT	0x0
+#define MP1_PUB_SCRATCH3__DATA_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_0
+#define MP1_C2PMSG_0__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_0__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_1
+#define MP1_C2PMSG_1__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_1__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_2
+#define MP1_C2PMSG_2__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_2__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_3
+#define MP1_C2PMSG_3__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_3__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_4
+#define MP1_C2PMSG_4__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_4__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_5
+#define MP1_C2PMSG_5__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_5__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_6
+#define MP1_C2PMSG_6__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_6__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_7
+#define MP1_C2PMSG_7__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_7__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_8
+#define MP1_C2PMSG_8__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_8__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_9
+#define MP1_C2PMSG_9__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_9__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_10
+#define MP1_C2PMSG_10__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_10__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_11
+#define MP1_C2PMSG_11__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_11__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_12
+#define MP1_C2PMSG_12__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_12__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_13
+#define MP1_C2PMSG_13__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_13__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_14
+#define MP1_C2PMSG_14__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_14__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_15
+#define MP1_C2PMSG_15__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_15__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_16
+#define MP1_C2PMSG_16__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_16__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_17
+#define MP1_C2PMSG_17__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_17__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_18
+#define MP1_C2PMSG_18__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_18__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_19
+#define MP1_C2PMSG_19__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_19__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_20
+#define MP1_C2PMSG_20__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_20__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_21
+#define MP1_C2PMSG_21__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_21__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_22
+#define MP1_C2PMSG_22__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_22__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_23
+#define MP1_C2PMSG_23__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_23__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_24
+#define MP1_C2PMSG_24__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_24__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_25
+#define MP1_C2PMSG_25__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_25__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_26
+#define MP1_C2PMSG_26__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_26__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_27
+#define MP1_C2PMSG_27__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_27__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_28
+#define MP1_C2PMSG_28__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_28__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_29
+#define MP1_C2PMSG_29__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_29__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_30
+#define MP1_C2PMSG_30__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_30__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_31
+#define MP1_C2PMSG_31__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_31__CONTENT_MASK	0xFFFFFFFFL
+//MP1_P2CMSG_0
+#define MP1_P2CMSG_0__CONTENT__SHIFT	0x0
+#define MP1_P2CMSG_0__CONTENT_MASK	0xFFFFFFFFL
+//MP1_P2CMSG_1
+#define MP1_P2CMSG_1__CONTENT__SHIFT	0x0
+#define MP1_P2CMSG_1__CONTENT_MASK	0xFFFFFFFFL
+//MP1_P2CMSG_2
+#define MP1_P2CMSG_2__CONTENT__SHIFT	0x0
+#define MP1_P2CMSG_2__CONTENT_MASK	0xFFFFFFFFL
+//MP1_P2CMSG_3
+#define MP1_P2CMSG_3__CONTENT__SHIFT	0x0
+#define MP1_P2CMSG_3__CONTENT_MASK	0xFFFFFFFFL
+//MP1_P2CMSG_INTEN
+#define MP1_P2CMSG_INTEN__INTEN__SHIFT	0x0
+#define MP1_P2CMSG_INTEN__INTEN_MASK	0x0000000FL
+//MP1_P2CMSG_INTSTS
+#define MP1_P2CMSG_INTSTS__INTSTS0__SHIFT	0x0
+#define MP1_P2CMSG_INTSTS__INTSTS1__SHIFT	0x1
+#define MP1_P2CMSG_INTSTS__INTSTS2__SHIFT	0x2
+#define MP1_P2CMSG_INTSTS__INTSTS3__SHIFT	0x3
+#define MP1_P2CMSG_INTSTS__INTSTS0_MASK	0x00000001L
+#define MP1_P2CMSG_INTSTS__INTSTS1_MASK	0x00000002L
+#define MP1_P2CMSG_INTSTS__INTSTS2_MASK	0x00000004L
+#define MP1_P2CMSG_INTSTS__INTSTS3_MASK	0x00000008L
+//MP1_P2SMSG_0
+#define MP1_P2SMSG_0__CONTENT__SHIFT	0x0
+#define MP1_P2SMSG_0__CONTENT_MASK	0xFFFFFFFFL
+//MP1_P2SMSG_1
+#define MP1_P2SMSG_1__CONTENT__SHIFT	0x0
+#define MP1_P2SMSG_1__CONTENT_MASK	0xFFFFFFFFL
+//MP1_P2SMSG_2
+#define MP1_P2SMSG_2__CONTENT__SHIFT	0x0
+#define MP1_P2SMSG_2__CONTENT_MASK	0xFFFFFFFFL
+//MP1_P2SMSG_3
+#define MP1_P2SMSG_3__CONTENT__SHIFT	0x0
+#define MP1_P2SMSG_3__CONTENT_MASK	0xFFFFFFFFL
+//MP1_P2SMSG_INTSTS
+#define MP1_P2SMSG_INTSTS__INTSTS0__SHIFT	0x0
+#define MP1_P2SMSG_INTSTS__INTSTS1__SHIFT	0x1
+#define MP1_P2SMSG_INTSTS__INTSTS2__SHIFT	0x2
+#define MP1_P2SMSG_INTSTS__INTSTS3__SHIFT	0x3
+#define MP1_P2SMSG_INTSTS__INTSTS0_MASK	0x00000001L
+#define MP1_P2SMSG_INTSTS__INTSTS1_MASK	0x00000002L
+#define MP1_P2SMSG_INTSTS__INTSTS2_MASK	0x00000004L
+#define MP1_P2SMSG_INTSTS__INTSTS3_MASK	0x00000008L
+//MP1_S2PMSG_0
+#define MP1_S2PMSG_0__CONTENT__SHIFT	0x0
+#define MP1_S2PMSG_0__CONTENT_MASK	0xFFFFFFFFL
+//MP1_ACP2MP_RESP
+#define MP1_ACP2MP_RESP__CONTENT__SHIFT	0x0
+#define MP1_ACP2MP_RESP__CONTENT_MASK	0xFFFFFFFFL
+//MP1_DC2MP_RESP
+#define MP1_DC2MP_RESP__CONTENT__SHIFT	0x0
+#define MP1_DC2MP_RESP__CONTENT_MASK	0xFFFFFFFFL
+//MP1_UVD2MP_RESP
+#define MP1_UVD2MP_RESP__CONTENT__SHIFT	0x0
+#define MP1_UVD2MP_RESP__CONTENT_MASK	0xFFFFFFFFL
+//MP1_VCE2MP_RESP
+#define MP1_VCE2MP_RESP__CONTENT__SHIFT	0x0
+#define MP1_VCE2MP_RESP__CONTENT_MASK	0xFFFFFFFFL
+//MP1_RLC2MP_RESP
+#define MP1_RLC2MP_RESP__CONTENT__SHIFT	0x0
+#define MP1_RLC2MP_RESP__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_32
+#define MP1_C2PMSG_32__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_32__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_33
+#define MP1_C2PMSG_33__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_33__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_34
+#define MP1_C2PMSG_34__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_34__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_35
+#define MP1_C2PMSG_35__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_35__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_36
+#define MP1_C2PMSG_36__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_36__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_37
+#define MP1_C2PMSG_37__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_37__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_38
+#define MP1_C2PMSG_38__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_38__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_39
+#define MP1_C2PMSG_39__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_39__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_40
+#define MP1_C2PMSG_40__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_40__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_41
+#define MP1_C2PMSG_41__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_41__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_42
+#define MP1_C2PMSG_42__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_42__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_43
+#define MP1_C2PMSG_43__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_43__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_44
+#define MP1_C2PMSG_44__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_44__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_45
+#define MP1_C2PMSG_45__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_45__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_46
+#define MP1_C2PMSG_46__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_46__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_47
+#define MP1_C2PMSG_47__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_47__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_48
+#define MP1_C2PMSG_48__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_48__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_49
+#define MP1_C2PMSG_49__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_49__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_50
+#define MP1_C2PMSG_50__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_50__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_51
+#define MP1_C2PMSG_51__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_51__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_52
+#define MP1_C2PMSG_52__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_52__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_53
+#define MP1_C2PMSG_53__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_53__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_54
+#define MP1_C2PMSG_54__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_54__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_55
+#define MP1_C2PMSG_55__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_55__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_56
+#define MP1_C2PMSG_56__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_56__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_57
+#define MP1_C2PMSG_57__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_57__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_58
+#define MP1_C2PMSG_58__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_58__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_59
+#define MP1_C2PMSG_59__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_59__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_60
+#define MP1_C2PMSG_60__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_60__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_61
+#define MP1_C2PMSG_61__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_61__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_62
+#define MP1_C2PMSG_62__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_62__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_63
+#define MP1_C2PMSG_63__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_63__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_64
+#define MP1_C2PMSG_64__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_64__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_65
+#define MP1_C2PMSG_65__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_65__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_66
+#define MP1_C2PMSG_66__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_66__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_67
+#define MP1_C2PMSG_67__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_67__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_68
+#define MP1_C2PMSG_68__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_68__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_69
+#define MP1_C2PMSG_69__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_69__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_70
+#define MP1_C2PMSG_70__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_70__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_71
+#define MP1_C2PMSG_71__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_71__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_72
+#define MP1_C2PMSG_72__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_72__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_73
+#define MP1_C2PMSG_73__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_73__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_74
+#define MP1_C2PMSG_74__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_74__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_75
+#define MP1_C2PMSG_75__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_75__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_76
+#define MP1_C2PMSG_76__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_76__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_77
+#define MP1_C2PMSG_77__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_77__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_78
+#define MP1_C2PMSG_78__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_78__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_79
+#define MP1_C2PMSG_79__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_79__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_80
+#define MP1_C2PMSG_80__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_80__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_81
+#define MP1_C2PMSG_81__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_81__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_82
+#define MP1_C2PMSG_82__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_82__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_83
+#define MP1_C2PMSG_83__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_83__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_84
+#define MP1_C2PMSG_84__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_84__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_85
+#define MP1_C2PMSG_85__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_85__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_86
+#define MP1_C2PMSG_86__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_86__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_87
+#define MP1_C2PMSG_87__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_87__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_88
+#define MP1_C2PMSG_88__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_88__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_89
+#define MP1_C2PMSG_89__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_89__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_90
+#define MP1_C2PMSG_90__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_90__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_91
+#define MP1_C2PMSG_91__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_91__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_92
+#define MP1_C2PMSG_92__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_92__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_93
+#define MP1_C2PMSG_93__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_93__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_94
+#define MP1_C2PMSG_94__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_94__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_95
+#define MP1_C2PMSG_95__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_95__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_96
+#define MP1_C2PMSG_96__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_96__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_97
+#define MP1_C2PMSG_97__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_97__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_98
+#define MP1_C2PMSG_98__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_98__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_99
+#define MP1_C2PMSG_99__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_99__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_100
+#define MP1_C2PMSG_100__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_100__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_101
+#define MP1_C2PMSG_101__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_101__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_102
+#define MP1_C2PMSG_102__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_102__CONTENT_MASK	0xFFFFFFFFL
+//MP1_C2PMSG_103
+#define MP1_C2PMSG_103__CONTENT__SHIFT	0x0
+#define MP1_C2PMSG_103__CONTENT_MASK	0xFFFFFFFFL
+//MP1_ACTIVE_FCN_ID
+#define MP1_ACTIVE_FCN_ID__VFID__SHIFT	0x0
+#define MP1_ACTIVE_FCN_ID__VF__SHIFT	0x1f
+#define MP1_ACTIVE_FCN_ID__VFID_MASK	0x0000000FL
+#define MP1_ACTIVE_FCN_ID__VF_MASK	0x80000000L
+//MP1_IH_CREDIT
+#define MP1_IH_CREDIT__CREDIT_VALUE__SHIFT	0x0
+#define MP1_IH_CREDIT__CLIENT_ID__SHIFT	0x10
+#define MP1_IH_CREDIT__CREDIT_VALUE_MASK	0x00000003L
+#define MP1_IH_CREDIT__CLIENT_ID_MASK	0x00FF0000L
+//MP1_IH_SW_INT
+#define MP1_IH_SW_INT__ID__SHIFT	0x0
+#define MP1_IH_SW_INT__VALID__SHIFT	0x8
+#define MP1_IH_SW_INT__ID_MASK	0x000000FFL
+#define MP1_IH_SW_INT__VALID_MASK	0x00000100L
+//MP1_IH_SW_INT_CTRL
+#define MP1_IH_SW_INT_CTRL__INT_MASK__SHIFT	0x0
+#define MP1_IH_SW_INT_CTRL__INT_ACK__SHIFT	0x8
+#define MP1_IH_SW_INT_CTRL__INT_MASK_MASK	0x00000001L
+#define MP1_IH_SW_INT_CTRL__INT_ACK_MASK	0x00000100L
+//MP1_FPS_CNT
+#define MP1_FPS_CNT__COUNT__SHIFT	0x0
+#define MP1_FPS_CNT__COUNT_MASK	0xFFFFFFFFL
+//MP1_PUB_CTRL
+#define MP1_PUB_CTRL__RESET__SHIFT	0x0
+#define MP1_PUB_CTRL__RESET_MASK	0x00000001L
+//MP1_EXT_SCRATCH0
+#define MP1_EXT_SCRATCH0__DATA__SHIFT	0x0
+#define MP1_EXT_SCRATCH0__DATA_MASK	0xFFFFFFFFL
+//MP1_EXT_SCRATCH1
+#define MP1_EXT_SCRATCH1__DATA__SHIFT	0x0
+#define MP1_EXT_SCRATCH1__DATA_MASK	0xFFFFFFFFL
+//MP1_EXT_SCRATCH2
+#define MP1_EXT_SCRATCH2__DATA__SHIFT	0x0
+#define MP1_EXT_SCRATCH2__DATA_MASK	0xFFFFFFFFL
+//MP1_EXT_SCRATCH3
+#define MP1_EXT_SCRATCH3__DATA__SHIFT	0x0
+#define MP1_EXT_SCRATCH3__DATA_MASK	0xFFFFFFFFL
+//MP1_EXT_SCRATCH4
+#define MP1_EXT_SCRATCH4__DATA__SHIFT	0x0
+#define MP1_EXT_SCRATCH4__DATA_MASK	0xFFFFFFFFL
+//MP1_EXT_SCRATCH5
+#define MP1_EXT_SCRATCH5__DATA__SHIFT	0x0
+#define MP1_EXT_SCRATCH5__DATA_MASK	0xFFFFFFFFL
+//MP1_EXT_SCRATCH6
+#define MP1_EXT_SCRATCH6__DATA__SHIFT	0x0
+#define MP1_EXT_SCRATCH6__DATA_MASK	0xFFFFFFFFL
+//MP1_EXT_SCRATCH7
+#define MP1_EXT_SCRATCH7__DATA__SHIFT	0x0
+#define MP1_EXT_SCRATCH7__DATA_MASK	0xFFFFFFFFL
+
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/NBIF/nbif_6_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbif/nbif_6_1_offset.h
index 68d0ffad28c7..68d0ffad28c7 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/NBIF/nbif_6_1_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbif/nbif_6_1_offset.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/NBIF/nbif_6_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/nbif/nbif_6_1_sh_mask.h
index c7518b84f559..c7518b84f559 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/NBIF/nbif_6_1_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbif/nbif_6_1_sh_mask.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/NBIO/nbio_6_1_default.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_6_1_default.h
index 8058796d658a..8058796d658a 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/NBIO/nbio_6_1_default.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_6_1_default.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/NBIO/nbio_6_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_6_1_offset.h
index 13d4de645190..13d4de645190 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/NBIO/nbio_6_1_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_6_1_offset.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vega10/NBIO/nbio_6_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_6_1_sh_mask.h
index a02b67943372..a02b67943372 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vega10/NBIO/nbio_6_1_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_6_1_sh_mask.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/raven1/NBIO/nbio_7_0_default.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_0_default.h
index f5fc31ffcd73..f5fc31ffcd73 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/raven1/NBIO/nbio_7_0_default.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_0_default.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/raven1/NBIO/nbio_7_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_0_offset.h
index 435462294fbc..435462294fbc 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/raven1/NBIO/nbio_7_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_0_offset.h
author	Florian Fainelli	2016-04-20 20:37:08 +0200
committer	David S. Miller	2016-04-21 21:06:04 +0200
commit	ba90950c94713f294e8778e891eef4143183957c (patch)
tree	e8136c9d614d94326476d04070b831c79344821a
parent	Merge branch 'nlattr_align' (diff)
download	kernel-qcow2-linux-ba90950c94713f294e8778e891eef4143183957c.tar.gz kernel-qcow2-linux-ba90950c94713f294e8778e891eef4143183957c.tar.xz kernel-qcow2-linux-ba90950c94713f294e8778e891eef4143183957c.zip